diff --git "a/checkpoint-17941/trainer_state.json" "b/checkpoint-17941/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-17941/trainer_state.json" @@ -0,0 +1,125620 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.0, + "eval_steps": 500, + "global_step": 17941, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 5.573825316314587e-05, + "grad_norm": 0.5498427152633667, + "learning_rate": 3.3333333333333335e-07, + "loss": 1.7989, + "step": 1 + }, + { + "epoch": 0.00011147650632629174, + "grad_norm": 0.6303576827049255, + "learning_rate": 6.666666666666667e-07, + "loss": 1.996, + "step": 2 + }, + { + "epoch": 0.0001672147594894376, + "grad_norm": 0.5333236455917358, + "learning_rate": 1.0000000000000002e-06, + "loss": 1.8613, + "step": 3 + }, + { + "epoch": 0.00022295301265258348, + "grad_norm": 0.5659189224243164, + "learning_rate": 1.3333333333333334e-06, + "loss": 1.8904, + "step": 4 + }, + { + "epoch": 0.0002786912658157293, + "grad_norm": 0.6221416592597961, + "learning_rate": 1.6666666666666667e-06, + "loss": 2.0151, + "step": 5 + }, + { + "epoch": 0.0003344295189788752, + "grad_norm": 0.6198977828025818, + "learning_rate": 2.0000000000000003e-06, + "loss": 1.9774, + "step": 6 + }, + { + "epoch": 0.0003901677721420211, + "grad_norm": 0.6328762173652649, + "learning_rate": 2.3333333333333336e-06, + "loss": 1.8994, + "step": 7 + }, + { + "epoch": 0.00044590602530516696, + "grad_norm": 0.6075513362884521, + "learning_rate": 2.666666666666667e-06, + "loss": 1.894, + "step": 8 + }, + { + "epoch": 0.0005016442784683128, + "grad_norm": 0.6397244930267334, + "learning_rate": 3e-06, + "loss": 2.0865, + "step": 9 + }, + { + "epoch": 0.0005573825316314586, + "grad_norm": 0.6115519404411316, + "learning_rate": 3.3333333333333333e-06, + "loss": 1.9688, + "step": 10 + }, + { + "epoch": 0.0006131207847946045, + "grad_norm": 0.546791672706604, + "learning_rate": 3.666666666666667e-06, + "loss": 1.8239, + "step": 11 + }, + { + "epoch": 0.0006688590379577504, + "grad_norm": 0.690762996673584, + "learning_rate": 4.000000000000001e-06, + "loss": 2.0367, + "step": 12 + }, + { + "epoch": 0.0007245972911208963, + "grad_norm": 0.7190566062927246, + "learning_rate": 4.333333333333334e-06, + "loss": 1.9817, + "step": 13 + }, + { + "epoch": 0.0007803355442840422, + "grad_norm": 0.6093202233314514, + "learning_rate": 4.666666666666667e-06, + "loss": 2.01, + "step": 14 + }, + { + "epoch": 0.000836073797447188, + "grad_norm": 0.5230669975280762, + "learning_rate": 5e-06, + "loss": 1.8419, + "step": 15 + }, + { + "epoch": 0.0008918120506103339, + "grad_norm": 0.5391668677330017, + "learning_rate": 5.333333333333334e-06, + "loss": 1.8663, + "step": 16 + }, + { + "epoch": 0.0009475503037734797, + "grad_norm": 0.6359019875526428, + "learning_rate": 5.666666666666667e-06, + "loss": 2.2089, + "step": 17 + }, + { + "epoch": 0.0010032885569366257, + "grad_norm": 0.61967533826828, + "learning_rate": 6e-06, + "loss": 2.0842, + "step": 18 + }, + { + "epoch": 0.0010590268100997716, + "grad_norm": 0.491642028093338, + "learning_rate": 6.333333333333334e-06, + "loss": 1.755, + "step": 19 + }, + { + "epoch": 0.0011147650632629172, + "grad_norm": 0.7064740657806396, + "learning_rate": 6.666666666666667e-06, + "loss": 2.2494, + "step": 20 + }, + { + "epoch": 0.0011705033164260631, + "grad_norm": 0.5671775937080383, + "learning_rate": 7.000000000000001e-06, + "loss": 2.0236, + "step": 21 + }, + { + "epoch": 0.001226241569589209, + "grad_norm": 0.5698847770690918, + "learning_rate": 7.333333333333334e-06, + "loss": 1.8295, + "step": 22 + }, + { + "epoch": 0.001281979822752355, + "grad_norm": 0.5910470485687256, + "learning_rate": 7.666666666666667e-06, + "loss": 2.1311, + "step": 23 + }, + { + "epoch": 0.0013377180759155008, + "grad_norm": 0.567130446434021, + "learning_rate": 8.000000000000001e-06, + "loss": 1.888, + "step": 24 + }, + { + "epoch": 0.0013934563290786467, + "grad_norm": 0.5540428757667542, + "learning_rate": 8.333333333333334e-06, + "loss": 1.6625, + "step": 25 + }, + { + "epoch": 0.0014491945822417925, + "grad_norm": 0.5729663372039795, + "learning_rate": 8.666666666666668e-06, + "loss": 2.0062, + "step": 26 + }, + { + "epoch": 0.0015049328354049384, + "grad_norm": 0.5232088565826416, + "learning_rate": 9e-06, + "loss": 1.7991, + "step": 27 + }, + { + "epoch": 0.0015606710885680843, + "grad_norm": 0.5638092160224915, + "learning_rate": 9.333333333333334e-06, + "loss": 2.0728, + "step": 28 + }, + { + "epoch": 0.0016164093417312302, + "grad_norm": 0.5504807829856873, + "learning_rate": 9.666666666666667e-06, + "loss": 1.808, + "step": 29 + }, + { + "epoch": 0.001672147594894376, + "grad_norm": 0.5935587882995605, + "learning_rate": 1e-05, + "loss": 1.9738, + "step": 30 + }, + { + "epoch": 0.001727885848057522, + "grad_norm": 0.6431534886360168, + "learning_rate": 1.0333333333333333e-05, + "loss": 2.0967, + "step": 31 + }, + { + "epoch": 0.0017836241012206678, + "grad_norm": 0.5587693452835083, + "learning_rate": 1.0666666666666667e-05, + "loss": 1.6821, + "step": 32 + }, + { + "epoch": 0.0018393623543838135, + "grad_norm": 0.5473759174346924, + "learning_rate": 1.1000000000000001e-05, + "loss": 1.8442, + "step": 33 + }, + { + "epoch": 0.0018951006075469594, + "grad_norm": 0.6185194849967957, + "learning_rate": 1.1333333333333334e-05, + "loss": 2.0705, + "step": 34 + }, + { + "epoch": 0.0019508388607101053, + "grad_norm": 0.5253747701644897, + "learning_rate": 1.1666666666666668e-05, + "loss": 1.7944, + "step": 35 + }, + { + "epoch": 0.0020065771138732514, + "grad_norm": 0.5742389559745789, + "learning_rate": 1.2e-05, + "loss": 2.0, + "step": 36 + }, + { + "epoch": 0.0020623153670363973, + "grad_norm": 0.6290589570999146, + "learning_rate": 1.2333333333333334e-05, + "loss": 2.1365, + "step": 37 + }, + { + "epoch": 0.002118053620199543, + "grad_norm": 0.5194576382637024, + "learning_rate": 1.2666666666666668e-05, + "loss": 1.8569, + "step": 38 + }, + { + "epoch": 0.0021737918733626886, + "grad_norm": 0.5665763020515442, + "learning_rate": 1.3000000000000001e-05, + "loss": 1.9313, + "step": 39 + }, + { + "epoch": 0.0022295301265258345, + "grad_norm": 0.5268619060516357, + "learning_rate": 1.3333333333333333e-05, + "loss": 1.8843, + "step": 40 + }, + { + "epoch": 0.0022852683796889804, + "grad_norm": 0.7840973734855652, + "learning_rate": 1.3666666666666666e-05, + "loss": 1.929, + "step": 41 + }, + { + "epoch": 0.0023410066328521262, + "grad_norm": 0.5785960555076599, + "learning_rate": 1.4000000000000001e-05, + "loss": 2.0276, + "step": 42 + }, + { + "epoch": 0.002396744886015272, + "grad_norm": 0.5202842354774475, + "learning_rate": 1.4333333333333334e-05, + "loss": 1.949, + "step": 43 + }, + { + "epoch": 0.002452483139178418, + "grad_norm": 0.72431480884552, + "learning_rate": 1.4666666666666668e-05, + "loss": 2.2978, + "step": 44 + }, + { + "epoch": 0.002508221392341564, + "grad_norm": 0.5558940768241882, + "learning_rate": 1.5e-05, + "loss": 1.9125, + "step": 45 + }, + { + "epoch": 0.00256395964550471, + "grad_norm": 0.5687503814697266, + "learning_rate": 1.5333333333333334e-05, + "loss": 1.8533, + "step": 46 + }, + { + "epoch": 0.0026196978986678557, + "grad_norm": 0.5703473091125488, + "learning_rate": 1.5666666666666667e-05, + "loss": 1.9015, + "step": 47 + }, + { + "epoch": 0.0026754361518310016, + "grad_norm": 0.5496488809585571, + "learning_rate": 1.6000000000000003e-05, + "loss": 1.682, + "step": 48 + }, + { + "epoch": 0.0027311744049941474, + "grad_norm": 0.6371431946754456, + "learning_rate": 1.6333333333333335e-05, + "loss": 2.0425, + "step": 49 + }, + { + "epoch": 0.0027869126581572933, + "grad_norm": 0.6071433424949646, + "learning_rate": 1.6666666666666667e-05, + "loss": 1.8745, + "step": 50 + }, + { + "epoch": 0.002842650911320439, + "grad_norm": 0.5981681942939758, + "learning_rate": 1.7000000000000003e-05, + "loss": 1.8872, + "step": 51 + }, + { + "epoch": 0.002898389164483585, + "grad_norm": 0.6591808795928955, + "learning_rate": 1.7333333333333336e-05, + "loss": 2.0187, + "step": 52 + }, + { + "epoch": 0.002954127417646731, + "grad_norm": 0.6213610172271729, + "learning_rate": 1.7666666666666668e-05, + "loss": 2.0231, + "step": 53 + }, + { + "epoch": 0.003009865670809877, + "grad_norm": 0.6377214789390564, + "learning_rate": 1.8e-05, + "loss": 1.8641, + "step": 54 + }, + { + "epoch": 0.0030656039239730227, + "grad_norm": 0.675821840763092, + "learning_rate": 1.8333333333333333e-05, + "loss": 2.215, + "step": 55 + }, + { + "epoch": 0.0031213421771361686, + "grad_norm": 0.5989570021629333, + "learning_rate": 1.866666666666667e-05, + "loss": 1.9232, + "step": 56 + }, + { + "epoch": 0.0031770804302993145, + "grad_norm": 0.6279881596565247, + "learning_rate": 1.9e-05, + "loss": 1.8452, + "step": 57 + }, + { + "epoch": 0.0032328186834624604, + "grad_norm": 0.5670164227485657, + "learning_rate": 1.9333333333333333e-05, + "loss": 1.5623, + "step": 58 + }, + { + "epoch": 0.0032885569366256063, + "grad_norm": 0.5822334289550781, + "learning_rate": 1.9666666666666666e-05, + "loss": 1.7901, + "step": 59 + }, + { + "epoch": 0.003344295189788752, + "grad_norm": 0.6322411298751831, + "learning_rate": 2e-05, + "loss": 1.8802, + "step": 60 + }, + { + "epoch": 0.003400033442951898, + "grad_norm": 0.6066840291023254, + "learning_rate": 2.0333333333333334e-05, + "loss": 1.8334, + "step": 61 + }, + { + "epoch": 0.003455771696115044, + "grad_norm": 0.6801030039787292, + "learning_rate": 2.0666666666666666e-05, + "loss": 2.1029, + "step": 62 + }, + { + "epoch": 0.00351150994927819, + "grad_norm": 0.6445280909538269, + "learning_rate": 2.1e-05, + "loss": 2.0333, + "step": 63 + }, + { + "epoch": 0.0035672482024413357, + "grad_norm": 0.6259938478469849, + "learning_rate": 2.1333333333333335e-05, + "loss": 1.6012, + "step": 64 + }, + { + "epoch": 0.003622986455604481, + "grad_norm": 0.6786999702453613, + "learning_rate": 2.1666666666666667e-05, + "loss": 2.0818, + "step": 65 + }, + { + "epoch": 0.003678724708767627, + "grad_norm": 0.6728941202163696, + "learning_rate": 2.2000000000000003e-05, + "loss": 1.9022, + "step": 66 + }, + { + "epoch": 0.003734462961930773, + "grad_norm": 0.6992253661155701, + "learning_rate": 2.2333333333333335e-05, + "loss": 1.7435, + "step": 67 + }, + { + "epoch": 0.003790201215093919, + "grad_norm": 0.6083998084068298, + "learning_rate": 2.2666666666666668e-05, + "loss": 1.7816, + "step": 68 + }, + { + "epoch": 0.0038459394682570647, + "grad_norm": 0.6070435643196106, + "learning_rate": 2.3000000000000003e-05, + "loss": 1.672, + "step": 69 + }, + { + "epoch": 0.0039016777214202106, + "grad_norm": 0.6032823920249939, + "learning_rate": 2.3333333333333336e-05, + "loss": 1.771, + "step": 70 + }, + { + "epoch": 0.0039574159745833564, + "grad_norm": 0.689372181892395, + "learning_rate": 2.3666666666666668e-05, + "loss": 1.9594, + "step": 71 + }, + { + "epoch": 0.004013154227746503, + "grad_norm": 0.6333785653114319, + "learning_rate": 2.4e-05, + "loss": 1.8492, + "step": 72 + }, + { + "epoch": 0.004068892480909648, + "grad_norm": 0.638140857219696, + "learning_rate": 2.4333333333333336e-05, + "loss": 1.798, + "step": 73 + }, + { + "epoch": 0.0041246307340727945, + "grad_norm": 0.6000136137008667, + "learning_rate": 2.466666666666667e-05, + "loss": 1.6625, + "step": 74 + }, + { + "epoch": 0.00418036898723594, + "grad_norm": 0.7654765248298645, + "learning_rate": 2.5e-05, + "loss": 2.1015, + "step": 75 + }, + { + "epoch": 0.004236107240399086, + "grad_norm": 0.6845409870147705, + "learning_rate": 2.5333333333333337e-05, + "loss": 1.9176, + "step": 76 + }, + { + "epoch": 0.004291845493562232, + "grad_norm": 0.6557128429412842, + "learning_rate": 2.5666666666666666e-05, + "loss": 1.8244, + "step": 77 + }, + { + "epoch": 0.004347583746725377, + "grad_norm": 0.6574406027793884, + "learning_rate": 2.6000000000000002e-05, + "loss": 1.851, + "step": 78 + }, + { + "epoch": 0.0044033219998885235, + "grad_norm": 0.6624826192855835, + "learning_rate": 2.633333333333333e-05, + "loss": 1.8332, + "step": 79 + }, + { + "epoch": 0.004459060253051669, + "grad_norm": 0.7041051983833313, + "learning_rate": 2.6666666666666667e-05, + "loss": 1.8357, + "step": 80 + }, + { + "epoch": 0.004514798506214815, + "grad_norm": 0.6737162470817566, + "learning_rate": 2.7000000000000002e-05, + "loss": 1.8162, + "step": 81 + }, + { + "epoch": 0.004570536759377961, + "grad_norm": 0.6803858280181885, + "learning_rate": 2.733333333333333e-05, + "loss": 1.9187, + "step": 82 + }, + { + "epoch": 0.004626275012541107, + "grad_norm": 0.6441910862922668, + "learning_rate": 2.7666666666666667e-05, + "loss": 1.9235, + "step": 83 + }, + { + "epoch": 0.0046820132657042525, + "grad_norm": 0.6409979462623596, + "learning_rate": 2.8000000000000003e-05, + "loss": 1.9148, + "step": 84 + }, + { + "epoch": 0.004737751518867399, + "grad_norm": 0.722623348236084, + "learning_rate": 2.8333333333333335e-05, + "loss": 1.9738, + "step": 85 + }, + { + "epoch": 0.004793489772030544, + "grad_norm": 0.6637834310531616, + "learning_rate": 2.8666666666666668e-05, + "loss": 1.6872, + "step": 86 + }, + { + "epoch": 0.004849228025193691, + "grad_norm": 0.7143079042434692, + "learning_rate": 2.9e-05, + "loss": 1.9944, + "step": 87 + }, + { + "epoch": 0.004904966278356836, + "grad_norm": 0.7566176652908325, + "learning_rate": 2.9333333333333336e-05, + "loss": 1.7542, + "step": 88 + }, + { + "epoch": 0.004960704531519982, + "grad_norm": 0.6472474932670593, + "learning_rate": 2.9666666666666672e-05, + "loss": 1.9534, + "step": 89 + }, + { + "epoch": 0.005016442784683128, + "grad_norm": 0.6678224205970764, + "learning_rate": 3e-05, + "loss": 1.7684, + "step": 90 + }, + { + "epoch": 0.005072181037846274, + "grad_norm": 0.6665822267532349, + "learning_rate": 3.0333333333333337e-05, + "loss": 1.9028, + "step": 91 + }, + { + "epoch": 0.00512791929100942, + "grad_norm": 0.7907567620277405, + "learning_rate": 3.066666666666667e-05, + "loss": 1.8876, + "step": 92 + }, + { + "epoch": 0.005183657544172566, + "grad_norm": 0.6738147735595703, + "learning_rate": 3.1e-05, + "loss": 1.7623, + "step": 93 + }, + { + "epoch": 0.005239395797335711, + "grad_norm": 0.6898536086082458, + "learning_rate": 3.1333333333333334e-05, + "loss": 1.7103, + "step": 94 + }, + { + "epoch": 0.005295134050498858, + "grad_norm": 0.6961106061935425, + "learning_rate": 3.1666666666666666e-05, + "loss": 1.537, + "step": 95 + }, + { + "epoch": 0.005350872303662003, + "grad_norm": 0.6331319808959961, + "learning_rate": 3.2000000000000005e-05, + "loss": 1.6681, + "step": 96 + }, + { + "epoch": 0.005406610556825149, + "grad_norm": 0.7678634524345398, + "learning_rate": 3.233333333333333e-05, + "loss": 2.1339, + "step": 97 + }, + { + "epoch": 0.005462348809988295, + "grad_norm": 0.7012338638305664, + "learning_rate": 3.266666666666667e-05, + "loss": 1.7591, + "step": 98 + }, + { + "epoch": 0.005518087063151441, + "grad_norm": 0.7289243340492249, + "learning_rate": 3.3e-05, + "loss": 1.901, + "step": 99 + }, + { + "epoch": 0.005573825316314587, + "grad_norm": 0.6416298747062683, + "learning_rate": 3.3333333333333335e-05, + "loss": 1.5989, + "step": 100 + }, + { + "epoch": 0.005629563569477733, + "grad_norm": 0.6193853616714478, + "learning_rate": 3.366666666666667e-05, + "loss": 1.7429, + "step": 101 + }, + { + "epoch": 0.005685301822640878, + "grad_norm": 0.7283613681793213, + "learning_rate": 3.4000000000000007e-05, + "loss": 1.9885, + "step": 102 + }, + { + "epoch": 0.005741040075804025, + "grad_norm": 0.6713369488716125, + "learning_rate": 3.433333333333333e-05, + "loss": 1.8521, + "step": 103 + }, + { + "epoch": 0.00579677832896717, + "grad_norm": 0.6700227856636047, + "learning_rate": 3.466666666666667e-05, + "loss": 1.8404, + "step": 104 + }, + { + "epoch": 0.005852516582130316, + "grad_norm": 0.6885061860084534, + "learning_rate": 3.5e-05, + "loss": 1.8081, + "step": 105 + }, + { + "epoch": 0.005908254835293462, + "grad_norm": 0.6814194917678833, + "learning_rate": 3.5333333333333336e-05, + "loss": 1.8672, + "step": 106 + }, + { + "epoch": 0.005963993088456607, + "grad_norm": 0.6492342948913574, + "learning_rate": 3.566666666666667e-05, + "loss": 1.7029, + "step": 107 + }, + { + "epoch": 0.006019731341619754, + "grad_norm": 0.5920109748840332, + "learning_rate": 3.6e-05, + "loss": 1.5455, + "step": 108 + }, + { + "epoch": 0.006075469594782899, + "grad_norm": 0.6685107946395874, + "learning_rate": 3.633333333333333e-05, + "loss": 1.9576, + "step": 109 + }, + { + "epoch": 0.0061312078479460455, + "grad_norm": 0.6917557716369629, + "learning_rate": 3.6666666666666666e-05, + "loss": 1.9341, + "step": 110 + }, + { + "epoch": 0.006186946101109191, + "grad_norm": 0.730872631072998, + "learning_rate": 3.7e-05, + "loss": 1.9828, + "step": 111 + }, + { + "epoch": 0.006242684354272337, + "grad_norm": 0.7139527797698975, + "learning_rate": 3.733333333333334e-05, + "loss": 2.0277, + "step": 112 + }, + { + "epoch": 0.006298422607435483, + "grad_norm": 0.6276320219039917, + "learning_rate": 3.766666666666667e-05, + "loss": 1.7702, + "step": 113 + }, + { + "epoch": 0.006354160860598629, + "grad_norm": 0.6891281008720398, + "learning_rate": 3.8e-05, + "loss": 1.9062, + "step": 114 + }, + { + "epoch": 0.0064098991137617745, + "grad_norm": 0.7155683636665344, + "learning_rate": 3.8333333333333334e-05, + "loss": 1.8527, + "step": 115 + }, + { + "epoch": 0.006465637366924921, + "grad_norm": 0.6917515397071838, + "learning_rate": 3.866666666666667e-05, + "loss": 1.8439, + "step": 116 + }, + { + "epoch": 0.006521375620088066, + "grad_norm": 0.7216237783432007, + "learning_rate": 3.9000000000000006e-05, + "loss": 2.0114, + "step": 117 + }, + { + "epoch": 0.0065771138732512125, + "grad_norm": 0.6636412739753723, + "learning_rate": 3.933333333333333e-05, + "loss": 1.6951, + "step": 118 + }, + { + "epoch": 0.006632852126414358, + "grad_norm": 0.7715172171592712, + "learning_rate": 3.966666666666667e-05, + "loss": 1.9907, + "step": 119 + }, + { + "epoch": 0.006688590379577504, + "grad_norm": 0.6481485366821289, + "learning_rate": 4e-05, + "loss": 1.7934, + "step": 120 + }, + { + "epoch": 0.00674432863274065, + "grad_norm": 0.6104344725608826, + "learning_rate": 4.0333333333333336e-05, + "loss": 1.6549, + "step": 121 + }, + { + "epoch": 0.006800066885903796, + "grad_norm": 0.706912100315094, + "learning_rate": 4.066666666666667e-05, + "loss": 1.9666, + "step": 122 + }, + { + "epoch": 0.0068558051390669415, + "grad_norm": 0.7835676670074463, + "learning_rate": 4.1e-05, + "loss": 2.024, + "step": 123 + }, + { + "epoch": 0.006911543392230088, + "grad_norm": 0.6462398171424866, + "learning_rate": 4.133333333333333e-05, + "loss": 1.6993, + "step": 124 + }, + { + "epoch": 0.006967281645393233, + "grad_norm": 0.7756698727607727, + "learning_rate": 4.166666666666667e-05, + "loss": 2.0135, + "step": 125 + }, + { + "epoch": 0.00702301989855638, + "grad_norm": 0.6666940450668335, + "learning_rate": 4.2e-05, + "loss": 1.9444, + "step": 126 + }, + { + "epoch": 0.007078758151719525, + "grad_norm": 0.6363375782966614, + "learning_rate": 4.233333333333334e-05, + "loss": 1.6977, + "step": 127 + }, + { + "epoch": 0.007134496404882671, + "grad_norm": 0.6881687045097351, + "learning_rate": 4.266666666666667e-05, + "loss": 1.7938, + "step": 128 + }, + { + "epoch": 0.007190234658045817, + "grad_norm": 0.7950214147567749, + "learning_rate": 4.3e-05, + "loss": 2.1036, + "step": 129 + }, + { + "epoch": 0.007245972911208962, + "grad_norm": 0.6743674874305725, + "learning_rate": 4.3333333333333334e-05, + "loss": 2.0052, + "step": 130 + }, + { + "epoch": 0.007301711164372109, + "grad_norm": 0.7302188277244568, + "learning_rate": 4.3666666666666666e-05, + "loss": 1.7815, + "step": 131 + }, + { + "epoch": 0.007357449417535254, + "grad_norm": 0.691747784614563, + "learning_rate": 4.4000000000000006e-05, + "loss": 1.7225, + "step": 132 + }, + { + "epoch": 0.0074131876706984, + "grad_norm": 0.6021103262901306, + "learning_rate": 4.433333333333334e-05, + "loss": 1.5821, + "step": 133 + }, + { + "epoch": 0.007468925923861546, + "grad_norm": 0.7083866000175476, + "learning_rate": 4.466666666666667e-05, + "loss": 1.7831, + "step": 134 + }, + { + "epoch": 0.007524664177024692, + "grad_norm": 0.6396238207817078, + "learning_rate": 4.5e-05, + "loss": 1.7933, + "step": 135 + }, + { + "epoch": 0.007580402430187838, + "grad_norm": 0.6446027159690857, + "learning_rate": 4.5333333333333335e-05, + "loss": 1.697, + "step": 136 + }, + { + "epoch": 0.007636140683350984, + "grad_norm": 0.6570568084716797, + "learning_rate": 4.566666666666667e-05, + "loss": 1.8226, + "step": 137 + }, + { + "epoch": 0.007691878936514129, + "grad_norm": 0.7829813361167908, + "learning_rate": 4.600000000000001e-05, + "loss": 1.9071, + "step": 138 + }, + { + "epoch": 0.007747617189677276, + "grad_norm": 0.6894962787628174, + "learning_rate": 4.633333333333333e-05, + "loss": 1.8796, + "step": 139 + }, + { + "epoch": 0.007803355442840421, + "grad_norm": 0.6631702184677124, + "learning_rate": 4.666666666666667e-05, + "loss": 1.7765, + "step": 140 + }, + { + "epoch": 0.007859093696003567, + "grad_norm": 0.7325467467308044, + "learning_rate": 4.7e-05, + "loss": 1.9653, + "step": 141 + }, + { + "epoch": 0.007914831949166713, + "grad_norm": 0.7264820337295532, + "learning_rate": 4.7333333333333336e-05, + "loss": 1.9019, + "step": 142 + }, + { + "epoch": 0.00797057020232986, + "grad_norm": 0.6573049426078796, + "learning_rate": 4.766666666666667e-05, + "loss": 1.8028, + "step": 143 + }, + { + "epoch": 0.008026308455493006, + "grad_norm": 0.6475189328193665, + "learning_rate": 4.8e-05, + "loss": 1.8229, + "step": 144 + }, + { + "epoch": 0.00808204670865615, + "grad_norm": 0.6277217864990234, + "learning_rate": 4.8333333333333334e-05, + "loss": 1.8648, + "step": 145 + }, + { + "epoch": 0.008137784961819296, + "grad_norm": 0.6631461381912231, + "learning_rate": 4.866666666666667e-05, + "loss": 1.7499, + "step": 146 + }, + { + "epoch": 0.008193523214982443, + "grad_norm": 0.8212792873382568, + "learning_rate": 4.9e-05, + "loss": 1.9345, + "step": 147 + }, + { + "epoch": 0.008249261468145589, + "grad_norm": 0.6783550977706909, + "learning_rate": 4.933333333333334e-05, + "loss": 2.0028, + "step": 148 + }, + { + "epoch": 0.008304999721308734, + "grad_norm": 0.7066723704338074, + "learning_rate": 4.966666666666667e-05, + "loss": 2.0291, + "step": 149 + }, + { + "epoch": 0.00836073797447188, + "grad_norm": 0.772089958190918, + "learning_rate": 5e-05, + "loss": 2.0909, + "step": 150 + }, + { + "epoch": 0.008416476227635026, + "grad_norm": 0.6396070718765259, + "learning_rate": 5.0333333333333335e-05, + "loss": 1.75, + "step": 151 + }, + { + "epoch": 0.008472214480798173, + "grad_norm": 0.6549371480941772, + "learning_rate": 5.0666666666666674e-05, + "loss": 1.8499, + "step": 152 + }, + { + "epoch": 0.008527952733961317, + "grad_norm": 0.7041524648666382, + "learning_rate": 5.1000000000000006e-05, + "loss": 1.9604, + "step": 153 + }, + { + "epoch": 0.008583690987124463, + "grad_norm": 0.6144838929176331, + "learning_rate": 5.133333333333333e-05, + "loss": 1.813, + "step": 154 + }, + { + "epoch": 0.00863942924028761, + "grad_norm": 0.5433954000473022, + "learning_rate": 5.166666666666667e-05, + "loss": 1.7692, + "step": 155 + }, + { + "epoch": 0.008695167493450754, + "grad_norm": 0.6341120600700378, + "learning_rate": 5.2000000000000004e-05, + "loss": 1.8756, + "step": 156 + }, + { + "epoch": 0.0087509057466139, + "grad_norm": 0.6475428938865662, + "learning_rate": 5.2333333333333336e-05, + "loss": 2.0465, + "step": 157 + }, + { + "epoch": 0.008806643999777047, + "grad_norm": 0.6457498669624329, + "learning_rate": 5.266666666666666e-05, + "loss": 1.9387, + "step": 158 + }, + { + "epoch": 0.008862382252940193, + "grad_norm": 0.562533974647522, + "learning_rate": 5.300000000000001e-05, + "loss": 1.7746, + "step": 159 + }, + { + "epoch": 0.008918120506103338, + "grad_norm": 0.6415228247642517, + "learning_rate": 5.333333333333333e-05, + "loss": 1.7729, + "step": 160 + }, + { + "epoch": 0.008973858759266484, + "grad_norm": 0.6404130458831787, + "learning_rate": 5.3666666666666666e-05, + "loss": 1.7488, + "step": 161 + }, + { + "epoch": 0.00902959701242963, + "grad_norm": 0.6626627445220947, + "learning_rate": 5.4000000000000005e-05, + "loss": 1.8962, + "step": 162 + }, + { + "epoch": 0.009085335265592777, + "grad_norm": 0.6191387176513672, + "learning_rate": 5.433333333333334e-05, + "loss": 1.8141, + "step": 163 + }, + { + "epoch": 0.009141073518755921, + "grad_norm": 0.5454838871955872, + "learning_rate": 5.466666666666666e-05, + "loss": 1.5107, + "step": 164 + }, + { + "epoch": 0.009196811771919068, + "grad_norm": 0.6767019033432007, + "learning_rate": 5.500000000000001e-05, + "loss": 2.1324, + "step": 165 + }, + { + "epoch": 0.009252550025082214, + "grad_norm": 0.6267591714859009, + "learning_rate": 5.5333333333333334e-05, + "loss": 1.7378, + "step": 166 + }, + { + "epoch": 0.00930828827824536, + "grad_norm": 0.5743867754936218, + "learning_rate": 5.566666666666667e-05, + "loss": 1.7654, + "step": 167 + }, + { + "epoch": 0.009364026531408505, + "grad_norm": 0.5550642013549805, + "learning_rate": 5.6000000000000006e-05, + "loss": 1.8091, + "step": 168 + }, + { + "epoch": 0.009419764784571651, + "grad_norm": 0.5943305492401123, + "learning_rate": 5.633333333333334e-05, + "loss": 1.6823, + "step": 169 + }, + { + "epoch": 0.009475503037734798, + "grad_norm": 0.6027736663818359, + "learning_rate": 5.666666666666667e-05, + "loss": 1.7736, + "step": 170 + }, + { + "epoch": 0.009531241290897944, + "grad_norm": 0.6379444003105164, + "learning_rate": 5.6999999999999996e-05, + "loss": 2.0331, + "step": 171 + }, + { + "epoch": 0.009586979544061089, + "grad_norm": 0.6117588877677917, + "learning_rate": 5.7333333333333336e-05, + "loss": 1.8546, + "step": 172 + }, + { + "epoch": 0.009642717797224235, + "grad_norm": 0.6109329462051392, + "learning_rate": 5.766666666666667e-05, + "loss": 2.0427, + "step": 173 + }, + { + "epoch": 0.009698456050387381, + "grad_norm": 0.5530399084091187, + "learning_rate": 5.8e-05, + "loss": 1.7323, + "step": 174 + }, + { + "epoch": 0.009754194303550527, + "grad_norm": 0.7092908024787903, + "learning_rate": 5.833333333333334e-05, + "loss": 2.2, + "step": 175 + }, + { + "epoch": 0.009809932556713672, + "grad_norm": 0.5897237658500671, + "learning_rate": 5.866666666666667e-05, + "loss": 1.5879, + "step": 176 + }, + { + "epoch": 0.009865670809876818, + "grad_norm": 0.5485551357269287, + "learning_rate": 5.9e-05, + "loss": 1.6043, + "step": 177 + }, + { + "epoch": 0.009921409063039965, + "grad_norm": 0.5792586803436279, + "learning_rate": 5.9333333333333343e-05, + "loss": 1.8772, + "step": 178 + }, + { + "epoch": 0.009977147316203111, + "grad_norm": 0.6716285943984985, + "learning_rate": 5.966666666666667e-05, + "loss": 1.7887, + "step": 179 + }, + { + "epoch": 0.010032885569366256, + "grad_norm": 0.5866957902908325, + "learning_rate": 6e-05, + "loss": 1.7228, + "step": 180 + }, + { + "epoch": 0.010088623822529402, + "grad_norm": 0.6197178363800049, + "learning_rate": 6.033333333333334e-05, + "loss": 1.7767, + "step": 181 + }, + { + "epoch": 0.010144362075692548, + "grad_norm": 0.6811436414718628, + "learning_rate": 6.066666666666667e-05, + "loss": 2.002, + "step": 182 + }, + { + "epoch": 0.010200100328855693, + "grad_norm": 0.6519239544868469, + "learning_rate": 6.1e-05, + "loss": 1.7755, + "step": 183 + }, + { + "epoch": 0.01025583858201884, + "grad_norm": 0.5758973360061646, + "learning_rate": 6.133333333333334e-05, + "loss": 1.7244, + "step": 184 + }, + { + "epoch": 0.010311576835181985, + "grad_norm": 0.5882923007011414, + "learning_rate": 6.166666666666667e-05, + "loss": 1.8041, + "step": 185 + }, + { + "epoch": 0.010367315088345132, + "grad_norm": 0.5509873032569885, + "learning_rate": 6.2e-05, + "loss": 1.7813, + "step": 186 + }, + { + "epoch": 0.010423053341508276, + "grad_norm": 0.5870537757873535, + "learning_rate": 6.233333333333334e-05, + "loss": 1.9419, + "step": 187 + }, + { + "epoch": 0.010478791594671423, + "grad_norm": 0.5315700173377991, + "learning_rate": 6.266666666666667e-05, + "loss": 1.6804, + "step": 188 + }, + { + "epoch": 0.010534529847834569, + "grad_norm": 0.5694735646247864, + "learning_rate": 6.3e-05, + "loss": 1.8406, + "step": 189 + }, + { + "epoch": 0.010590268100997715, + "grad_norm": 0.5579227209091187, + "learning_rate": 6.333333333333333e-05, + "loss": 1.9451, + "step": 190 + }, + { + "epoch": 0.01064600635416086, + "grad_norm": 0.5777730941772461, + "learning_rate": 6.366666666666668e-05, + "loss": 1.7783, + "step": 191 + }, + { + "epoch": 0.010701744607324006, + "grad_norm": 0.5626804828643799, + "learning_rate": 6.400000000000001e-05, + "loss": 1.8944, + "step": 192 + }, + { + "epoch": 0.010757482860487153, + "grad_norm": 0.5726325511932373, + "learning_rate": 6.433333333333333e-05, + "loss": 1.8799, + "step": 193 + }, + { + "epoch": 0.010813221113650299, + "grad_norm": 0.6156812906265259, + "learning_rate": 6.466666666666666e-05, + "loss": 1.8651, + "step": 194 + }, + { + "epoch": 0.010868959366813443, + "grad_norm": 0.545893669128418, + "learning_rate": 6.500000000000001e-05, + "loss": 1.6938, + "step": 195 + }, + { + "epoch": 0.01092469761997659, + "grad_norm": 0.5374442934989929, + "learning_rate": 6.533333333333334e-05, + "loss": 1.756, + "step": 196 + }, + { + "epoch": 0.010980435873139736, + "grad_norm": 0.5943235754966736, + "learning_rate": 6.566666666666666e-05, + "loss": 1.8388, + "step": 197 + }, + { + "epoch": 0.011036174126302882, + "grad_norm": 0.7199476361274719, + "learning_rate": 6.6e-05, + "loss": 2.0311, + "step": 198 + }, + { + "epoch": 0.011091912379466027, + "grad_norm": 0.65143883228302, + "learning_rate": 6.633333333333334e-05, + "loss": 2.0285, + "step": 199 + }, + { + "epoch": 0.011147650632629173, + "grad_norm": 0.5984755754470825, + "learning_rate": 6.666666666666667e-05, + "loss": 1.7062, + "step": 200 + }, + { + "epoch": 0.01120338888579232, + "grad_norm": 0.5733404755592346, + "learning_rate": 6.7e-05, + "loss": 1.916, + "step": 201 + }, + { + "epoch": 0.011259127138955466, + "grad_norm": 0.5946204662322998, + "learning_rate": 6.733333333333333e-05, + "loss": 1.9394, + "step": 202 + }, + { + "epoch": 0.01131486539211861, + "grad_norm": 0.677741527557373, + "learning_rate": 6.766666666666667e-05, + "loss": 2.248, + "step": 203 + }, + { + "epoch": 0.011370603645281757, + "grad_norm": 0.5983121991157532, + "learning_rate": 6.800000000000001e-05, + "loss": 1.835, + "step": 204 + }, + { + "epoch": 0.011426341898444903, + "grad_norm": 0.5219351053237915, + "learning_rate": 6.833333333333333e-05, + "loss": 1.7373, + "step": 205 + }, + { + "epoch": 0.01148208015160805, + "grad_norm": 0.657131552696228, + "learning_rate": 6.866666666666666e-05, + "loss": 2.1801, + "step": 206 + }, + { + "epoch": 0.011537818404771194, + "grad_norm": 0.6068251132965088, + "learning_rate": 6.9e-05, + "loss": 1.7873, + "step": 207 + }, + { + "epoch": 0.01159355665793434, + "grad_norm": 0.5744972825050354, + "learning_rate": 6.933333333333334e-05, + "loss": 1.9491, + "step": 208 + }, + { + "epoch": 0.011649294911097487, + "grad_norm": 0.5395380854606628, + "learning_rate": 6.966666666666668e-05, + "loss": 1.7532, + "step": 209 + }, + { + "epoch": 0.011705033164260631, + "grad_norm": 0.5843316912651062, + "learning_rate": 7e-05, + "loss": 1.7694, + "step": 210 + }, + { + "epoch": 0.011760771417423778, + "grad_norm": 0.6699615716934204, + "learning_rate": 7.033333333333334e-05, + "loss": 2.2063, + "step": 211 + }, + { + "epoch": 0.011816509670586924, + "grad_norm": 0.5723788738250732, + "learning_rate": 7.066666666666667e-05, + "loss": 1.8842, + "step": 212 + }, + { + "epoch": 0.01187224792375007, + "grad_norm": 0.5478008985519409, + "learning_rate": 7.1e-05, + "loss": 1.7411, + "step": 213 + }, + { + "epoch": 0.011927986176913215, + "grad_norm": 0.567477285861969, + "learning_rate": 7.133333333333334e-05, + "loss": 1.8457, + "step": 214 + }, + { + "epoch": 0.011983724430076361, + "grad_norm": 0.5568417310714722, + "learning_rate": 7.166666666666667e-05, + "loss": 1.8425, + "step": 215 + }, + { + "epoch": 0.012039462683239507, + "grad_norm": 0.552416205406189, + "learning_rate": 7.2e-05, + "loss": 1.9535, + "step": 216 + }, + { + "epoch": 0.012095200936402654, + "grad_norm": 0.6089819073677063, + "learning_rate": 7.233333333333335e-05, + "loss": 1.8465, + "step": 217 + }, + { + "epoch": 0.012150939189565798, + "grad_norm": 0.6218812465667725, + "learning_rate": 7.266666666666667e-05, + "loss": 2.1711, + "step": 218 + }, + { + "epoch": 0.012206677442728945, + "grad_norm": 0.5704020261764526, + "learning_rate": 7.3e-05, + "loss": 1.7793, + "step": 219 + }, + { + "epoch": 0.012262415695892091, + "grad_norm": 0.5598061084747314, + "learning_rate": 7.333333333333333e-05, + "loss": 1.9454, + "step": 220 + }, + { + "epoch": 0.012318153949055237, + "grad_norm": 0.5439260601997375, + "learning_rate": 7.366666666666668e-05, + "loss": 1.8544, + "step": 221 + }, + { + "epoch": 0.012373892202218382, + "grad_norm": 0.5953371524810791, + "learning_rate": 7.4e-05, + "loss": 1.8335, + "step": 222 + }, + { + "epoch": 0.012429630455381528, + "grad_norm": 0.5699326395988464, + "learning_rate": 7.433333333333333e-05, + "loss": 1.6647, + "step": 223 + }, + { + "epoch": 0.012485368708544674, + "grad_norm": 0.5833302140235901, + "learning_rate": 7.466666666666667e-05, + "loss": 1.9092, + "step": 224 + }, + { + "epoch": 0.01254110696170782, + "grad_norm": 0.5663686394691467, + "learning_rate": 7.500000000000001e-05, + "loss": 1.7344, + "step": 225 + }, + { + "epoch": 0.012596845214870965, + "grad_norm": 0.5459832549095154, + "learning_rate": 7.533333333333334e-05, + "loss": 1.6805, + "step": 226 + }, + { + "epoch": 0.012652583468034112, + "grad_norm": 0.6193357110023499, + "learning_rate": 7.566666666666667e-05, + "loss": 1.6711, + "step": 227 + }, + { + "epoch": 0.012708321721197258, + "grad_norm": 0.6414167284965515, + "learning_rate": 7.6e-05, + "loss": 1.9194, + "step": 228 + }, + { + "epoch": 0.012764059974360404, + "grad_norm": 0.541812539100647, + "learning_rate": 7.633333333333334e-05, + "loss": 1.9374, + "step": 229 + }, + { + "epoch": 0.012819798227523549, + "grad_norm": 0.5368767976760864, + "learning_rate": 7.666666666666667e-05, + "loss": 1.605, + "step": 230 + }, + { + "epoch": 0.012875536480686695, + "grad_norm": 0.622112512588501, + "learning_rate": 7.7e-05, + "loss": 1.804, + "step": 231 + }, + { + "epoch": 0.012931274733849842, + "grad_norm": 0.5820221900939941, + "learning_rate": 7.733333333333333e-05, + "loss": 1.796, + "step": 232 + }, + { + "epoch": 0.012987012987012988, + "grad_norm": 0.5530866980552673, + "learning_rate": 7.766666666666667e-05, + "loss": 1.704, + "step": 233 + }, + { + "epoch": 0.013042751240176132, + "grad_norm": 0.5967001914978027, + "learning_rate": 7.800000000000001e-05, + "loss": 2.0598, + "step": 234 + }, + { + "epoch": 0.013098489493339279, + "grad_norm": 0.5761673450469971, + "learning_rate": 7.833333333333333e-05, + "loss": 1.9391, + "step": 235 + }, + { + "epoch": 0.013154227746502425, + "grad_norm": 0.582139253616333, + "learning_rate": 7.866666666666666e-05, + "loss": 1.851, + "step": 236 + }, + { + "epoch": 0.01320996599966557, + "grad_norm": 0.6047868132591248, + "learning_rate": 7.900000000000001e-05, + "loss": 1.9757, + "step": 237 + }, + { + "epoch": 0.013265704252828716, + "grad_norm": 0.6394466757774353, + "learning_rate": 7.933333333333334e-05, + "loss": 2.2063, + "step": 238 + }, + { + "epoch": 0.013321442505991862, + "grad_norm": 0.6129965782165527, + "learning_rate": 7.966666666666666e-05, + "loss": 1.8813, + "step": 239 + }, + { + "epoch": 0.013377180759155009, + "grad_norm": 0.5982023477554321, + "learning_rate": 8e-05, + "loss": 1.928, + "step": 240 + }, + { + "epoch": 0.013432919012318153, + "grad_norm": 0.515180230140686, + "learning_rate": 8.033333333333334e-05, + "loss": 1.5582, + "step": 241 + }, + { + "epoch": 0.0134886572654813, + "grad_norm": 0.669916033744812, + "learning_rate": 8.066666666666667e-05, + "loss": 2.1044, + "step": 242 + }, + { + "epoch": 0.013544395518644446, + "grad_norm": 0.5825132131576538, + "learning_rate": 8.1e-05, + "loss": 1.7521, + "step": 243 + }, + { + "epoch": 0.013600133771807592, + "grad_norm": 0.6118985414505005, + "learning_rate": 8.133333333333334e-05, + "loss": 1.9605, + "step": 244 + }, + { + "epoch": 0.013655872024970737, + "grad_norm": 0.5747547745704651, + "learning_rate": 8.166666666666667e-05, + "loss": 1.8198, + "step": 245 + }, + { + "epoch": 0.013711610278133883, + "grad_norm": 0.609553337097168, + "learning_rate": 8.2e-05, + "loss": 2.0001, + "step": 246 + }, + { + "epoch": 0.01376734853129703, + "grad_norm": 0.5751491189002991, + "learning_rate": 8.233333333333333e-05, + "loss": 1.9317, + "step": 247 + }, + { + "epoch": 0.013823086784460176, + "grad_norm": 0.599029541015625, + "learning_rate": 8.266666666666667e-05, + "loss": 1.7716, + "step": 248 + }, + { + "epoch": 0.01387882503762332, + "grad_norm": 0.5347121953964233, + "learning_rate": 8.3e-05, + "loss": 1.82, + "step": 249 + }, + { + "epoch": 0.013934563290786467, + "grad_norm": 0.5724605917930603, + "learning_rate": 8.333333333333334e-05, + "loss": 1.8309, + "step": 250 + }, + { + "epoch": 0.013990301543949613, + "grad_norm": 0.531136691570282, + "learning_rate": 8.366666666666668e-05, + "loss": 1.682, + "step": 251 + }, + { + "epoch": 0.01404603979711276, + "grad_norm": 0.5464481115341187, + "learning_rate": 8.4e-05, + "loss": 2.001, + "step": 252 + }, + { + "epoch": 0.014101778050275904, + "grad_norm": 0.5945254564285278, + "learning_rate": 8.433333333333334e-05, + "loss": 1.7766, + "step": 253 + }, + { + "epoch": 0.01415751630343905, + "grad_norm": 0.5452976226806641, + "learning_rate": 8.466666666666667e-05, + "loss": 1.6948, + "step": 254 + }, + { + "epoch": 0.014213254556602196, + "grad_norm": 0.5722144842147827, + "learning_rate": 8.5e-05, + "loss": 1.8978, + "step": 255 + }, + { + "epoch": 0.014268992809765343, + "grad_norm": 0.5629029870033264, + "learning_rate": 8.533333333333334e-05, + "loss": 1.7381, + "step": 256 + }, + { + "epoch": 0.014324731062928487, + "grad_norm": 0.584661066532135, + "learning_rate": 8.566666666666667e-05, + "loss": 1.7016, + "step": 257 + }, + { + "epoch": 0.014380469316091634, + "grad_norm": 0.544104814529419, + "learning_rate": 8.6e-05, + "loss": 1.8649, + "step": 258 + }, + { + "epoch": 0.01443620756925478, + "grad_norm": 0.5734279751777649, + "learning_rate": 8.633333333333334e-05, + "loss": 1.7844, + "step": 259 + }, + { + "epoch": 0.014491945822417925, + "grad_norm": 0.5523878335952759, + "learning_rate": 8.666666666666667e-05, + "loss": 2.0572, + "step": 260 + }, + { + "epoch": 0.014547684075581071, + "grad_norm": 0.5634390115737915, + "learning_rate": 8.7e-05, + "loss": 1.8073, + "step": 261 + }, + { + "epoch": 0.014603422328744217, + "grad_norm": 0.5875604152679443, + "learning_rate": 8.733333333333333e-05, + "loss": 1.9706, + "step": 262 + }, + { + "epoch": 0.014659160581907364, + "grad_norm": 0.534288227558136, + "learning_rate": 8.766666666666668e-05, + "loss": 1.7742, + "step": 263 + }, + { + "epoch": 0.014714898835070508, + "grad_norm": 0.5286023020744324, + "learning_rate": 8.800000000000001e-05, + "loss": 1.6763, + "step": 264 + }, + { + "epoch": 0.014770637088233654, + "grad_norm": 0.5768111944198608, + "learning_rate": 8.833333333333333e-05, + "loss": 1.5731, + "step": 265 + }, + { + "epoch": 0.0148263753413968, + "grad_norm": 0.552629292011261, + "learning_rate": 8.866666666666668e-05, + "loss": 1.9837, + "step": 266 + }, + { + "epoch": 0.014882113594559947, + "grad_norm": 0.5081507563591003, + "learning_rate": 8.900000000000001e-05, + "loss": 1.8844, + "step": 267 + }, + { + "epoch": 0.014937851847723092, + "grad_norm": 0.563845694065094, + "learning_rate": 8.933333333333334e-05, + "loss": 1.9141, + "step": 268 + }, + { + "epoch": 0.014993590100886238, + "grad_norm": 0.5855246186256409, + "learning_rate": 8.966666666666666e-05, + "loss": 2.1101, + "step": 269 + }, + { + "epoch": 0.015049328354049384, + "grad_norm": 0.5010532736778259, + "learning_rate": 9e-05, + "loss": 1.8388, + "step": 270 + }, + { + "epoch": 0.01510506660721253, + "grad_norm": 0.5565475225448608, + "learning_rate": 9.033333333333334e-05, + "loss": 1.8648, + "step": 271 + }, + { + "epoch": 0.015160804860375675, + "grad_norm": 0.5293692350387573, + "learning_rate": 9.066666666666667e-05, + "loss": 1.7059, + "step": 272 + }, + { + "epoch": 0.015216543113538821, + "grad_norm": 0.5180760025978088, + "learning_rate": 9.1e-05, + "loss": 1.8659, + "step": 273 + }, + { + "epoch": 0.015272281366701968, + "grad_norm": 0.5416427254676819, + "learning_rate": 9.133333333333334e-05, + "loss": 1.6187, + "step": 274 + }, + { + "epoch": 0.015328019619865114, + "grad_norm": 0.603060781955719, + "learning_rate": 9.166666666666667e-05, + "loss": 1.8554, + "step": 275 + }, + { + "epoch": 0.015383757873028259, + "grad_norm": 0.5260182023048401, + "learning_rate": 9.200000000000001e-05, + "loss": 1.8108, + "step": 276 + }, + { + "epoch": 0.015439496126191405, + "grad_norm": 0.5307485461235046, + "learning_rate": 9.233333333333333e-05, + "loss": 1.7369, + "step": 277 + }, + { + "epoch": 0.015495234379354551, + "grad_norm": 0.5671928524971008, + "learning_rate": 9.266666666666666e-05, + "loss": 1.7879, + "step": 278 + }, + { + "epoch": 0.015550972632517698, + "grad_norm": 0.5482888221740723, + "learning_rate": 9.300000000000001e-05, + "loss": 1.8687, + "step": 279 + }, + { + "epoch": 0.015606710885680842, + "grad_norm": 0.5492271184921265, + "learning_rate": 9.333333333333334e-05, + "loss": 2.0486, + "step": 280 + }, + { + "epoch": 0.01566244913884399, + "grad_norm": 0.5533493757247925, + "learning_rate": 9.366666666666668e-05, + "loss": 1.8764, + "step": 281 + }, + { + "epoch": 0.015718187392007133, + "grad_norm": 0.5373388528823853, + "learning_rate": 9.4e-05, + "loss": 1.8098, + "step": 282 + }, + { + "epoch": 0.01577392564517028, + "grad_norm": 0.5737355351448059, + "learning_rate": 9.433333333333334e-05, + "loss": 1.8023, + "step": 283 + }, + { + "epoch": 0.015829663898333426, + "grad_norm": 0.6059421896934509, + "learning_rate": 9.466666666666667e-05, + "loss": 1.9003, + "step": 284 + }, + { + "epoch": 0.015885402151496572, + "grad_norm": 0.545070230960846, + "learning_rate": 9.5e-05, + "loss": 1.6793, + "step": 285 + }, + { + "epoch": 0.01594114040465972, + "grad_norm": 0.5391154885292053, + "learning_rate": 9.533333333333334e-05, + "loss": 1.7691, + "step": 286 + }, + { + "epoch": 0.015996878657822865, + "grad_norm": 0.5233768820762634, + "learning_rate": 9.566666666666667e-05, + "loss": 1.8312, + "step": 287 + }, + { + "epoch": 0.01605261691098601, + "grad_norm": 0.5520955920219421, + "learning_rate": 9.6e-05, + "loss": 1.9652, + "step": 288 + }, + { + "epoch": 0.016108355164149154, + "grad_norm": 0.5521306991577148, + "learning_rate": 9.633333333333335e-05, + "loss": 1.8264, + "step": 289 + }, + { + "epoch": 0.0161640934173123, + "grad_norm": 0.5325077176094055, + "learning_rate": 9.666666666666667e-05, + "loss": 1.9074, + "step": 290 + }, + { + "epoch": 0.016219831670475447, + "grad_norm": 0.5402048230171204, + "learning_rate": 9.7e-05, + "loss": 1.9993, + "step": 291 + }, + { + "epoch": 0.016275569923638593, + "grad_norm": 0.5164310336112976, + "learning_rate": 9.733333333333335e-05, + "loss": 1.6385, + "step": 292 + }, + { + "epoch": 0.01633130817680174, + "grad_norm": 0.5265329480171204, + "learning_rate": 9.766666666666668e-05, + "loss": 1.8513, + "step": 293 + }, + { + "epoch": 0.016387046429964885, + "grad_norm": 0.5051769614219666, + "learning_rate": 9.8e-05, + "loss": 1.7628, + "step": 294 + }, + { + "epoch": 0.016442784683128032, + "grad_norm": 0.5061401128768921, + "learning_rate": 9.833333333333333e-05, + "loss": 1.8406, + "step": 295 + }, + { + "epoch": 0.016498522936291178, + "grad_norm": 0.6622328162193298, + "learning_rate": 9.866666666666668e-05, + "loss": 1.9504, + "step": 296 + }, + { + "epoch": 0.01655426118945432, + "grad_norm": 0.5525157451629639, + "learning_rate": 9.900000000000001e-05, + "loss": 1.9845, + "step": 297 + }, + { + "epoch": 0.016609999442617467, + "grad_norm": 0.5412437319755554, + "learning_rate": 9.933333333333334e-05, + "loss": 1.8234, + "step": 298 + }, + { + "epoch": 0.016665737695780614, + "grad_norm": 0.53217613697052, + "learning_rate": 9.966666666666667e-05, + "loss": 1.6132, + "step": 299 + }, + { + "epoch": 0.01672147594894376, + "grad_norm": 0.6531130075454712, + "learning_rate": 0.0001, + "loss": 2.0395, + "step": 300 + }, + { + "epoch": 0.016777214202106906, + "grad_norm": 0.49301308393478394, + "learning_rate": 9.999999920714576e-05, + "loss": 1.6945, + "step": 301 + }, + { + "epoch": 0.016832952455270053, + "grad_norm": 0.49394482374191284, + "learning_rate": 9.999999682858307e-05, + "loss": 1.6877, + "step": 302 + }, + { + "epoch": 0.0168886907084332, + "grad_norm": 0.504688024520874, + "learning_rate": 9.9999992864312e-05, + "loss": 1.6779, + "step": 303 + }, + { + "epoch": 0.016944428961596345, + "grad_norm": 0.5286409258842468, + "learning_rate": 9.999998731433267e-05, + "loss": 1.64, + "step": 304 + }, + { + "epoch": 0.017000167214759488, + "grad_norm": 0.4911554157733917, + "learning_rate": 9.999998017864527e-05, + "loss": 1.66, + "step": 305 + }, + { + "epoch": 0.017055905467922634, + "grad_norm": 0.4851885735988617, + "learning_rate": 9.999997145725001e-05, + "loss": 1.8884, + "step": 306 + }, + { + "epoch": 0.01711164372108578, + "grad_norm": 0.521120011806488, + "learning_rate": 9.999996115014719e-05, + "loss": 1.6844, + "step": 307 + }, + { + "epoch": 0.017167381974248927, + "grad_norm": 0.5494885444641113, + "learning_rate": 9.99999492573371e-05, + "loss": 1.7733, + "step": 308 + }, + { + "epoch": 0.017223120227412073, + "grad_norm": 0.4475904703140259, + "learning_rate": 9.999993577882016e-05, + "loss": 1.6295, + "step": 309 + }, + { + "epoch": 0.01727885848057522, + "grad_norm": 0.4610547721385956, + "learning_rate": 9.999992071459676e-05, + "loss": 1.6118, + "step": 310 + }, + { + "epoch": 0.017334596733738366, + "grad_norm": 0.49445369839668274, + "learning_rate": 9.999990406466741e-05, + "loss": 1.594, + "step": 311 + }, + { + "epoch": 0.01739033498690151, + "grad_norm": 0.5013507008552551, + "learning_rate": 9.999988582903262e-05, + "loss": 1.6829, + "step": 312 + }, + { + "epoch": 0.017446073240064655, + "grad_norm": 0.5492314100265503, + "learning_rate": 9.999986600769295e-05, + "loss": 1.662, + "step": 313 + }, + { + "epoch": 0.0175018114932278, + "grad_norm": 0.49456071853637695, + "learning_rate": 9.999984460064908e-05, + "loss": 1.7087, + "step": 314 + }, + { + "epoch": 0.017557549746390948, + "grad_norm": 0.587954580783844, + "learning_rate": 9.999982160790164e-05, + "loss": 1.8628, + "step": 315 + }, + { + "epoch": 0.017613287999554094, + "grad_norm": 0.6061418652534485, + "learning_rate": 9.999979702945138e-05, + "loss": 2.143, + "step": 316 + }, + { + "epoch": 0.01766902625271724, + "grad_norm": 0.52556973695755, + "learning_rate": 9.999977086529909e-05, + "loss": 1.6862, + "step": 317 + }, + { + "epoch": 0.017724764505880387, + "grad_norm": 0.5804201364517212, + "learning_rate": 9.999974311544556e-05, + "loss": 1.8495, + "step": 318 + }, + { + "epoch": 0.017780502759043533, + "grad_norm": 0.5533789396286011, + "learning_rate": 9.999971377989172e-05, + "loss": 1.9501, + "step": 319 + }, + { + "epoch": 0.017836241012206676, + "grad_norm": 0.5596528649330139, + "learning_rate": 9.999968285863848e-05, + "loss": 1.981, + "step": 320 + }, + { + "epoch": 0.017891979265369822, + "grad_norm": 0.538735568523407, + "learning_rate": 9.99996503516868e-05, + "loss": 1.9126, + "step": 321 + }, + { + "epoch": 0.01794771751853297, + "grad_norm": 0.48604801297187805, + "learning_rate": 9.999961625903774e-05, + "loss": 1.7568, + "step": 322 + }, + { + "epoch": 0.018003455771696115, + "grad_norm": 0.5091099143028259, + "learning_rate": 9.999958058069237e-05, + "loss": 1.9625, + "step": 323 + }, + { + "epoch": 0.01805919402485926, + "grad_norm": 0.4944256842136383, + "learning_rate": 9.999954331665182e-05, + "loss": 1.6326, + "step": 324 + }, + { + "epoch": 0.018114932278022407, + "grad_norm": 0.5379263162612915, + "learning_rate": 9.999950446691728e-05, + "loss": 1.8484, + "step": 325 + }, + { + "epoch": 0.018170670531185554, + "grad_norm": 0.5548909306526184, + "learning_rate": 9.999946403148997e-05, + "loss": 1.8855, + "step": 326 + }, + { + "epoch": 0.0182264087843487, + "grad_norm": 0.5878908634185791, + "learning_rate": 9.999942201037118e-05, + "loss": 1.8222, + "step": 327 + }, + { + "epoch": 0.018282147037511843, + "grad_norm": 0.48953092098236084, + "learning_rate": 9.999937840356224e-05, + "loss": 1.4395, + "step": 328 + }, + { + "epoch": 0.01833788529067499, + "grad_norm": 0.503923237323761, + "learning_rate": 9.999933321106452e-05, + "loss": 1.7122, + "step": 329 + }, + { + "epoch": 0.018393623543838136, + "grad_norm": 0.5150753855705261, + "learning_rate": 9.999928643287948e-05, + "loss": 1.8863, + "step": 330 + }, + { + "epoch": 0.018449361797001282, + "grad_norm": 0.5160688757896423, + "learning_rate": 9.999923806900859e-05, + "loss": 1.8184, + "step": 331 + }, + { + "epoch": 0.018505100050164428, + "grad_norm": 0.5423057079315186, + "learning_rate": 9.99991881194534e-05, + "loss": 1.843, + "step": 332 + }, + { + "epoch": 0.018560838303327575, + "grad_norm": 0.5026907324790955, + "learning_rate": 9.999913658421544e-05, + "loss": 1.7728, + "step": 333 + }, + { + "epoch": 0.01861657655649072, + "grad_norm": 0.5391967296600342, + "learning_rate": 9.999908346329642e-05, + "loss": 1.9225, + "step": 334 + }, + { + "epoch": 0.018672314809653867, + "grad_norm": 0.5050860047340393, + "learning_rate": 9.999902875669797e-05, + "loss": 1.7579, + "step": 335 + }, + { + "epoch": 0.01872805306281701, + "grad_norm": 0.48109737038612366, + "learning_rate": 9.999897246442184e-05, + "loss": 1.8859, + "step": 336 + }, + { + "epoch": 0.018783791315980156, + "grad_norm": 0.5002635717391968, + "learning_rate": 9.999891458646983e-05, + "loss": 1.6809, + "step": 337 + }, + { + "epoch": 0.018839529569143303, + "grad_norm": 0.5138371586799622, + "learning_rate": 9.999885512284375e-05, + "loss": 1.7961, + "step": 338 + }, + { + "epoch": 0.01889526782230645, + "grad_norm": 0.47246232628822327, + "learning_rate": 9.999879407354551e-05, + "loss": 1.6943, + "step": 339 + }, + { + "epoch": 0.018951006075469595, + "grad_norm": 0.47807106375694275, + "learning_rate": 9.999873143857704e-05, + "loss": 1.7652, + "step": 340 + }, + { + "epoch": 0.01900674432863274, + "grad_norm": 0.4725436270236969, + "learning_rate": 9.99986672179403e-05, + "loss": 1.7483, + "step": 341 + }, + { + "epoch": 0.019062482581795888, + "grad_norm": 0.5131480693817139, + "learning_rate": 9.999860141163736e-05, + "loss": 1.8883, + "step": 342 + }, + { + "epoch": 0.01911822083495903, + "grad_norm": 0.6150394678115845, + "learning_rate": 9.99985340196703e-05, + "loss": 2.1536, + "step": 343 + }, + { + "epoch": 0.019173959088122177, + "grad_norm": 0.5729528069496155, + "learning_rate": 9.999846504204124e-05, + "loss": 1.9443, + "step": 344 + }, + { + "epoch": 0.019229697341285323, + "grad_norm": 0.4936676323413849, + "learning_rate": 9.999839447875238e-05, + "loss": 1.7273, + "step": 345 + }, + { + "epoch": 0.01928543559444847, + "grad_norm": 0.5480337738990784, + "learning_rate": 9.999832232980597e-05, + "loss": 1.8024, + "step": 346 + }, + { + "epoch": 0.019341173847611616, + "grad_norm": 0.4883441925048828, + "learning_rate": 9.999824859520428e-05, + "loss": 1.6531, + "step": 347 + }, + { + "epoch": 0.019396912100774762, + "grad_norm": 0.6438686847686768, + "learning_rate": 9.999817327494967e-05, + "loss": 2.1477, + "step": 348 + }, + { + "epoch": 0.01945265035393791, + "grad_norm": 0.540684700012207, + "learning_rate": 9.999809636904449e-05, + "loss": 2.0333, + "step": 349 + }, + { + "epoch": 0.019508388607101055, + "grad_norm": 0.5322266221046448, + "learning_rate": 9.999801787749121e-05, + "loss": 1.7542, + "step": 350 + }, + { + "epoch": 0.019564126860264198, + "grad_norm": 0.5497377514839172, + "learning_rate": 9.999793780029232e-05, + "loss": 1.9207, + "step": 351 + }, + { + "epoch": 0.019619865113427344, + "grad_norm": 0.5375553369522095, + "learning_rate": 9.999785613745035e-05, + "loss": 1.8293, + "step": 352 + }, + { + "epoch": 0.01967560336659049, + "grad_norm": 0.5242462754249573, + "learning_rate": 9.999777288896787e-05, + "loss": 1.8176, + "step": 353 + }, + { + "epoch": 0.019731341619753637, + "grad_norm": 0.5194500088691711, + "learning_rate": 9.999768805484757e-05, + "loss": 1.961, + "step": 354 + }, + { + "epoch": 0.019787079872916783, + "grad_norm": 0.4952162504196167, + "learning_rate": 9.999760163509209e-05, + "loss": 1.6902, + "step": 355 + }, + { + "epoch": 0.01984281812607993, + "grad_norm": 0.4688204824924469, + "learning_rate": 9.99975136297042e-05, + "loss": 1.352, + "step": 356 + }, + { + "epoch": 0.019898556379243076, + "grad_norm": 0.5171904563903809, + "learning_rate": 9.999742403868668e-05, + "loss": 1.952, + "step": 357 + }, + { + "epoch": 0.019954294632406222, + "grad_norm": 0.542300283908844, + "learning_rate": 9.999733286204238e-05, + "loss": 1.8768, + "step": 358 + }, + { + "epoch": 0.020010032885569365, + "grad_norm": 0.5278236865997314, + "learning_rate": 9.99972400997742e-05, + "loss": 1.8014, + "step": 359 + }, + { + "epoch": 0.02006577113873251, + "grad_norm": 0.587790846824646, + "learning_rate": 9.999714575188505e-05, + "loss": 1.9884, + "step": 360 + }, + { + "epoch": 0.020121509391895658, + "grad_norm": 0.5114203095436096, + "learning_rate": 9.999704981837794e-05, + "loss": 1.9038, + "step": 361 + }, + { + "epoch": 0.020177247645058804, + "grad_norm": 0.538783609867096, + "learning_rate": 9.999695229925591e-05, + "loss": 1.9049, + "step": 362 + }, + { + "epoch": 0.02023298589822195, + "grad_norm": 0.5289005637168884, + "learning_rate": 9.999685319452208e-05, + "loss": 1.7111, + "step": 363 + }, + { + "epoch": 0.020288724151385096, + "grad_norm": 0.5257157683372498, + "learning_rate": 9.999675250417954e-05, + "loss": 1.6416, + "step": 364 + }, + { + "epoch": 0.020344462404548243, + "grad_norm": 0.480473130941391, + "learning_rate": 9.999665022823152e-05, + "loss": 1.7197, + "step": 365 + }, + { + "epoch": 0.020400200657711386, + "grad_norm": 0.5564152598381042, + "learning_rate": 9.999654636668125e-05, + "loss": 1.8762, + "step": 366 + }, + { + "epoch": 0.020455938910874532, + "grad_norm": 0.6517108082771301, + "learning_rate": 9.999644091953204e-05, + "loss": 2.4684, + "step": 367 + }, + { + "epoch": 0.02051167716403768, + "grad_norm": 0.5357886552810669, + "learning_rate": 9.999633388678723e-05, + "loss": 1.8079, + "step": 368 + }, + { + "epoch": 0.020567415417200825, + "grad_norm": 0.498740553855896, + "learning_rate": 9.999622526845021e-05, + "loss": 1.6885, + "step": 369 + }, + { + "epoch": 0.02062315367036397, + "grad_norm": 0.49749207496643066, + "learning_rate": 9.999611506452439e-05, + "loss": 1.8686, + "step": 370 + }, + { + "epoch": 0.020678891923527117, + "grad_norm": 0.5339593291282654, + "learning_rate": 9.999600327501333e-05, + "loss": 1.8592, + "step": 371 + }, + { + "epoch": 0.020734630176690264, + "grad_norm": 0.5533782839775085, + "learning_rate": 9.999588989992052e-05, + "loss": 1.8752, + "step": 372 + }, + { + "epoch": 0.02079036842985341, + "grad_norm": 0.459504634141922, + "learning_rate": 9.99957749392496e-05, + "loss": 1.7596, + "step": 373 + }, + { + "epoch": 0.020846106683016553, + "grad_norm": 0.4722179174423218, + "learning_rate": 9.999565839300419e-05, + "loss": 1.7573, + "step": 374 + }, + { + "epoch": 0.0209018449361797, + "grad_norm": 0.49677354097366333, + "learning_rate": 9.999554026118798e-05, + "loss": 1.9692, + "step": 375 + }, + { + "epoch": 0.020957583189342845, + "grad_norm": 0.49444639682769775, + "learning_rate": 9.999542054380473e-05, + "loss": 1.8881, + "step": 376 + }, + { + "epoch": 0.02101332144250599, + "grad_norm": 0.4882863461971283, + "learning_rate": 9.999529924085824e-05, + "loss": 1.8369, + "step": 377 + }, + { + "epoch": 0.021069059695669138, + "grad_norm": 0.475211501121521, + "learning_rate": 9.999517635235237e-05, + "loss": 1.3352, + "step": 378 + }, + { + "epoch": 0.021124797948832284, + "grad_norm": 0.5699715614318848, + "learning_rate": 9.999505187829096e-05, + "loss": 1.763, + "step": 379 + }, + { + "epoch": 0.02118053620199543, + "grad_norm": 0.5538257360458374, + "learning_rate": 9.9994925818678e-05, + "loss": 1.7431, + "step": 380 + }, + { + "epoch": 0.021236274455158577, + "grad_norm": 0.48163720965385437, + "learning_rate": 9.99947981735175e-05, + "loss": 1.7356, + "step": 381 + }, + { + "epoch": 0.02129201270832172, + "grad_norm": 0.5482640266418457, + "learning_rate": 9.99946689428135e-05, + "loss": 1.861, + "step": 382 + }, + { + "epoch": 0.021347750961484866, + "grad_norm": 0.5083199739456177, + "learning_rate": 9.999453812657007e-05, + "loss": 1.9594, + "step": 383 + }, + { + "epoch": 0.021403489214648012, + "grad_norm": 0.513034999370575, + "learning_rate": 9.99944057247914e-05, + "loss": 2.0073, + "step": 384 + }, + { + "epoch": 0.02145922746781116, + "grad_norm": 0.5045239329338074, + "learning_rate": 9.999427173748164e-05, + "loss": 1.6862, + "step": 385 + }, + { + "epoch": 0.021514965720974305, + "grad_norm": 0.5097934603691101, + "learning_rate": 9.999413616464508e-05, + "loss": 1.8631, + "step": 386 + }, + { + "epoch": 0.02157070397413745, + "grad_norm": 0.522888720035553, + "learning_rate": 9.999399900628601e-05, + "loss": 1.8636, + "step": 387 + }, + { + "epoch": 0.021626442227300598, + "grad_norm": 0.49189141392707825, + "learning_rate": 9.999386026240878e-05, + "loss": 1.7465, + "step": 388 + }, + { + "epoch": 0.021682180480463744, + "grad_norm": 0.5114362239837646, + "learning_rate": 9.999371993301779e-05, + "loss": 1.6336, + "step": 389 + }, + { + "epoch": 0.021737918733626887, + "grad_norm": 0.4647996723651886, + "learning_rate": 9.999357801811748e-05, + "loss": 1.6755, + "step": 390 + }, + { + "epoch": 0.021793656986790033, + "grad_norm": 0.5380472540855408, + "learning_rate": 9.999343451771234e-05, + "loss": 1.9477, + "step": 391 + }, + { + "epoch": 0.02184939523995318, + "grad_norm": 0.4583854377269745, + "learning_rate": 9.999328943180697e-05, + "loss": 1.7902, + "step": 392 + }, + { + "epoch": 0.021905133493116326, + "grad_norm": 0.45304641127586365, + "learning_rate": 9.999314276040592e-05, + "loss": 1.6744, + "step": 393 + }, + { + "epoch": 0.021960871746279472, + "grad_norm": 0.49699023365974426, + "learning_rate": 9.999299450351387e-05, + "loss": 1.8258, + "step": 394 + }, + { + "epoch": 0.02201660999944262, + "grad_norm": 0.49681130051612854, + "learning_rate": 9.999284466113552e-05, + "loss": 1.8488, + "step": 395 + }, + { + "epoch": 0.022072348252605765, + "grad_norm": 0.5959085822105408, + "learning_rate": 9.999269323327561e-05, + "loss": 2.1775, + "step": 396 + }, + { + "epoch": 0.022128086505768908, + "grad_norm": 0.5063357949256897, + "learning_rate": 9.999254021993895e-05, + "loss": 1.6503, + "step": 397 + }, + { + "epoch": 0.022183824758932054, + "grad_norm": 0.5273301005363464, + "learning_rate": 9.999238562113038e-05, + "loss": 1.8169, + "step": 398 + }, + { + "epoch": 0.0222395630120952, + "grad_norm": 0.5033614635467529, + "learning_rate": 9.999222943685482e-05, + "loss": 1.647, + "step": 399 + }, + { + "epoch": 0.022295301265258347, + "grad_norm": 0.5118756890296936, + "learning_rate": 9.999207166711723e-05, + "loss": 1.6712, + "step": 400 + }, + { + "epoch": 0.022351039518421493, + "grad_norm": 0.5338667035102844, + "learning_rate": 9.999191231192258e-05, + "loss": 1.8125, + "step": 401 + }, + { + "epoch": 0.02240677777158464, + "grad_norm": 0.5460575819015503, + "learning_rate": 9.999175137127596e-05, + "loss": 1.8486, + "step": 402 + }, + { + "epoch": 0.022462516024747785, + "grad_norm": 0.4892098009586334, + "learning_rate": 9.999158884518245e-05, + "loss": 1.6692, + "step": 403 + }, + { + "epoch": 0.022518254277910932, + "grad_norm": 0.4894774258136749, + "learning_rate": 9.999142473364722e-05, + "loss": 1.5916, + "step": 404 + }, + { + "epoch": 0.022573992531074075, + "grad_norm": 0.4909743070602417, + "learning_rate": 9.999125903667545e-05, + "loss": 1.646, + "step": 405 + }, + { + "epoch": 0.02262973078423722, + "grad_norm": 0.48369649052619934, + "learning_rate": 9.999109175427243e-05, + "loss": 1.6874, + "step": 406 + }, + { + "epoch": 0.022685469037400367, + "grad_norm": 0.4719717502593994, + "learning_rate": 9.999092288644345e-05, + "loss": 1.9116, + "step": 407 + }, + { + "epoch": 0.022741207290563514, + "grad_norm": 0.4719882309436798, + "learning_rate": 9.999075243319386e-05, + "loss": 1.4898, + "step": 408 + }, + { + "epoch": 0.02279694554372666, + "grad_norm": 0.5169988870620728, + "learning_rate": 9.999058039452906e-05, + "loss": 1.7671, + "step": 409 + }, + { + "epoch": 0.022852683796889806, + "grad_norm": 0.4469069540500641, + "learning_rate": 9.999040677045453e-05, + "loss": 1.7068, + "step": 410 + }, + { + "epoch": 0.022908422050052953, + "grad_norm": 0.508651077747345, + "learning_rate": 9.999023156097575e-05, + "loss": 1.912, + "step": 411 + }, + { + "epoch": 0.0229641603032161, + "grad_norm": 0.48365309834480286, + "learning_rate": 9.99900547660983e-05, + "loss": 1.7907, + "step": 412 + }, + { + "epoch": 0.02301989855637924, + "grad_norm": 0.5189946889877319, + "learning_rate": 9.998987638582775e-05, + "loss": 1.8333, + "step": 413 + }, + { + "epoch": 0.023075636809542388, + "grad_norm": 0.5238891839981079, + "learning_rate": 9.99896964201698e-05, + "loss": 2.0069, + "step": 414 + }, + { + "epoch": 0.023131375062705534, + "grad_norm": 0.5390001535415649, + "learning_rate": 9.998951486913015e-05, + "loss": 1.8571, + "step": 415 + }, + { + "epoch": 0.02318711331586868, + "grad_norm": 0.5339745283126831, + "learning_rate": 9.998933173271453e-05, + "loss": 1.6536, + "step": 416 + }, + { + "epoch": 0.023242851569031827, + "grad_norm": 0.48661404848098755, + "learning_rate": 9.998914701092877e-05, + "loss": 1.8969, + "step": 417 + }, + { + "epoch": 0.023298589822194973, + "grad_norm": 0.5701104402542114, + "learning_rate": 9.998896070377873e-05, + "loss": 1.9305, + "step": 418 + }, + { + "epoch": 0.02335432807535812, + "grad_norm": 0.5289365649223328, + "learning_rate": 9.99887728112703e-05, + "loss": 1.9801, + "step": 419 + }, + { + "epoch": 0.023410066328521262, + "grad_norm": 0.4870493412017822, + "learning_rate": 9.998858333340945e-05, + "loss": 1.879, + "step": 420 + }, + { + "epoch": 0.02346580458168441, + "grad_norm": 0.46179860830307007, + "learning_rate": 9.998839227020221e-05, + "loss": 1.6029, + "step": 421 + }, + { + "epoch": 0.023521542834847555, + "grad_norm": 0.5245276689529419, + "learning_rate": 9.998819962165462e-05, + "loss": 1.9165, + "step": 422 + }, + { + "epoch": 0.0235772810880107, + "grad_norm": 0.4952642321586609, + "learning_rate": 9.998800538777278e-05, + "loss": 1.6276, + "step": 423 + }, + { + "epoch": 0.023633019341173848, + "grad_norm": 0.48968929052352905, + "learning_rate": 9.998780956856285e-05, + "loss": 1.5287, + "step": 424 + }, + { + "epoch": 0.023688757594336994, + "grad_norm": 0.4968630373477936, + "learning_rate": 9.998761216403106e-05, + "loss": 1.8008, + "step": 425 + }, + { + "epoch": 0.02374449584750014, + "grad_norm": 0.5983918309211731, + "learning_rate": 9.998741317418366e-05, + "loss": 2.0055, + "step": 426 + }, + { + "epoch": 0.023800234100663287, + "grad_norm": 0.49322110414505005, + "learning_rate": 9.998721259902694e-05, + "loss": 1.6324, + "step": 427 + }, + { + "epoch": 0.02385597235382643, + "grad_norm": 0.4888675808906555, + "learning_rate": 9.99870104385673e-05, + "loss": 1.6075, + "step": 428 + }, + { + "epoch": 0.023911710606989576, + "grad_norm": 0.4783425033092499, + "learning_rate": 9.998680669281116e-05, + "loss": 1.6517, + "step": 429 + }, + { + "epoch": 0.023967448860152722, + "grad_norm": 0.5173685550689697, + "learning_rate": 9.998660136176492e-05, + "loss": 1.6884, + "step": 430 + }, + { + "epoch": 0.02402318711331587, + "grad_norm": 0.518741250038147, + "learning_rate": 9.998639444543514e-05, + "loss": 1.7113, + "step": 431 + }, + { + "epoch": 0.024078925366479015, + "grad_norm": 0.446850448846817, + "learning_rate": 9.998618594382836e-05, + "loss": 1.5067, + "step": 432 + }, + { + "epoch": 0.02413466361964216, + "grad_norm": 0.46661272644996643, + "learning_rate": 9.99859758569512e-05, + "loss": 1.6967, + "step": 433 + }, + { + "epoch": 0.024190401872805307, + "grad_norm": 0.5824592709541321, + "learning_rate": 9.998576418481033e-05, + "loss": 2.0151, + "step": 434 + }, + { + "epoch": 0.024246140125968454, + "grad_norm": 0.4715226888656616, + "learning_rate": 9.998555092741247e-05, + "loss": 1.6199, + "step": 435 + }, + { + "epoch": 0.024301878379131597, + "grad_norm": 0.5396628975868225, + "learning_rate": 9.998533608476435e-05, + "loss": 1.8874, + "step": 436 + }, + { + "epoch": 0.024357616632294743, + "grad_norm": 0.4999384582042694, + "learning_rate": 9.99851196568728e-05, + "loss": 1.8761, + "step": 437 + }, + { + "epoch": 0.02441335488545789, + "grad_norm": 0.4719383418560028, + "learning_rate": 9.998490164374472e-05, + "loss": 1.6399, + "step": 438 + }, + { + "epoch": 0.024469093138621036, + "grad_norm": 0.49223801493644714, + "learning_rate": 9.998468204538696e-05, + "loss": 1.8343, + "step": 439 + }, + { + "epoch": 0.024524831391784182, + "grad_norm": 0.5116458535194397, + "learning_rate": 9.998446086180653e-05, + "loss": 2.0423, + "step": 440 + }, + { + "epoch": 0.024580569644947328, + "grad_norm": 0.48448118567466736, + "learning_rate": 9.998423809301043e-05, + "loss": 1.5796, + "step": 441 + }, + { + "epoch": 0.024636307898110475, + "grad_norm": 0.48682916164398193, + "learning_rate": 9.998401373900573e-05, + "loss": 1.661, + "step": 442 + }, + { + "epoch": 0.024692046151273617, + "grad_norm": 0.5474771857261658, + "learning_rate": 9.998378779979954e-05, + "loss": 1.9646, + "step": 443 + }, + { + "epoch": 0.024747784404436764, + "grad_norm": 0.48878610134124756, + "learning_rate": 9.998356027539901e-05, + "loss": 1.7896, + "step": 444 + }, + { + "epoch": 0.02480352265759991, + "grad_norm": 0.49135512113571167, + "learning_rate": 9.99833311658114e-05, + "loss": 1.7329, + "step": 445 + }, + { + "epoch": 0.024859260910763056, + "grad_norm": 0.5220357775688171, + "learning_rate": 9.998310047104393e-05, + "loss": 2.0303, + "step": 446 + }, + { + "epoch": 0.024914999163926203, + "grad_norm": 0.4597051739692688, + "learning_rate": 9.998286819110394e-05, + "loss": 1.6114, + "step": 447 + }, + { + "epoch": 0.02497073741708935, + "grad_norm": 0.5005029439926147, + "learning_rate": 9.99826343259988e-05, + "loss": 1.8658, + "step": 448 + }, + { + "epoch": 0.025026475670252495, + "grad_norm": 0.5835437774658203, + "learning_rate": 9.99823988757359e-05, + "loss": 1.8958, + "step": 449 + }, + { + "epoch": 0.02508221392341564, + "grad_norm": 0.4960596263408661, + "learning_rate": 9.998216184032274e-05, + "loss": 1.7768, + "step": 450 + }, + { + "epoch": 0.025137952176578784, + "grad_norm": 0.4787440299987793, + "learning_rate": 9.99819232197668e-05, + "loss": 1.7367, + "step": 451 + }, + { + "epoch": 0.02519369042974193, + "grad_norm": 0.4575479030609131, + "learning_rate": 9.99816830140757e-05, + "loss": 1.6027, + "step": 452 + }, + { + "epoch": 0.025249428682905077, + "grad_norm": 0.5182919502258301, + "learning_rate": 9.998144122325702e-05, + "loss": 1.8879, + "step": 453 + }, + { + "epoch": 0.025305166936068223, + "grad_norm": 0.49592286348342896, + "learning_rate": 9.998119784731843e-05, + "loss": 1.954, + "step": 454 + }, + { + "epoch": 0.02536090518923137, + "grad_norm": 0.4686327576637268, + "learning_rate": 9.998095288626765e-05, + "loss": 1.6971, + "step": 455 + }, + { + "epoch": 0.025416643442394516, + "grad_norm": 0.5634790658950806, + "learning_rate": 9.998070634011246e-05, + "loss": 1.8801, + "step": 456 + }, + { + "epoch": 0.025472381695557662, + "grad_norm": 0.49380773305892944, + "learning_rate": 9.998045820886068e-05, + "loss": 1.8882, + "step": 457 + }, + { + "epoch": 0.02552811994872081, + "grad_norm": 0.5319178104400635, + "learning_rate": 9.998020849252017e-05, + "loss": 1.7204, + "step": 458 + }, + { + "epoch": 0.02558385820188395, + "grad_norm": 0.4578639268875122, + "learning_rate": 9.997995719109884e-05, + "loss": 1.6934, + "step": 459 + }, + { + "epoch": 0.025639596455047098, + "grad_norm": 0.4672851264476776, + "learning_rate": 9.997970430460468e-05, + "loss": 1.5534, + "step": 460 + }, + { + "epoch": 0.025695334708210244, + "grad_norm": 0.4967419505119324, + "learning_rate": 9.99794498330457e-05, + "loss": 1.7817, + "step": 461 + }, + { + "epoch": 0.02575107296137339, + "grad_norm": 0.494781494140625, + "learning_rate": 9.997919377642997e-05, + "loss": 1.759, + "step": 462 + }, + { + "epoch": 0.025806811214536537, + "grad_norm": 0.47715312242507935, + "learning_rate": 9.997893613476561e-05, + "loss": 1.6342, + "step": 463 + }, + { + "epoch": 0.025862549467699683, + "grad_norm": 0.5014367699623108, + "learning_rate": 9.99786769080608e-05, + "loss": 1.7754, + "step": 464 + }, + { + "epoch": 0.02591828772086283, + "grad_norm": 0.503808319568634, + "learning_rate": 9.997841609632375e-05, + "loss": 1.9323, + "step": 465 + }, + { + "epoch": 0.025974025974025976, + "grad_norm": 0.4935349225997925, + "learning_rate": 9.997815369956273e-05, + "loss": 1.945, + "step": 466 + }, + { + "epoch": 0.02602976422718912, + "grad_norm": 0.45313507318496704, + "learning_rate": 9.997788971778608e-05, + "loss": 1.5908, + "step": 467 + }, + { + "epoch": 0.026085502480352265, + "grad_norm": 0.48407676815986633, + "learning_rate": 9.997762415100214e-05, + "loss": 1.449, + "step": 468 + }, + { + "epoch": 0.02614124073351541, + "grad_norm": 0.4917304813861847, + "learning_rate": 9.997735699921938e-05, + "loss": 1.7667, + "step": 469 + }, + { + "epoch": 0.026196978986678558, + "grad_norm": 0.5684965252876282, + "learning_rate": 9.997708826244623e-05, + "loss": 2.0801, + "step": 470 + }, + { + "epoch": 0.026252717239841704, + "grad_norm": 0.5034363865852356, + "learning_rate": 9.997681794069123e-05, + "loss": 1.9385, + "step": 471 + }, + { + "epoch": 0.02630845549300485, + "grad_norm": 0.5185155272483826, + "learning_rate": 9.997654603396294e-05, + "loss": 1.9021, + "step": 472 + }, + { + "epoch": 0.026364193746167996, + "grad_norm": 0.4756320118904114, + "learning_rate": 9.997627254227e-05, + "loss": 1.7698, + "step": 473 + }, + { + "epoch": 0.02641993199933114, + "grad_norm": 0.47013306617736816, + "learning_rate": 9.997599746562108e-05, + "loss": 1.6786, + "step": 474 + }, + { + "epoch": 0.026475670252494286, + "grad_norm": 0.4797370731830597, + "learning_rate": 9.997572080402488e-05, + "loss": 1.8663, + "step": 475 + }, + { + "epoch": 0.026531408505657432, + "grad_norm": 0.4647987186908722, + "learning_rate": 9.997544255749021e-05, + "loss": 1.6064, + "step": 476 + }, + { + "epoch": 0.02658714675882058, + "grad_norm": 0.5362509489059448, + "learning_rate": 9.99751627260259e-05, + "loss": 2.035, + "step": 477 + }, + { + "epoch": 0.026642885011983725, + "grad_norm": 0.501615047454834, + "learning_rate": 9.997488130964077e-05, + "loss": 1.7838, + "step": 478 + }, + { + "epoch": 0.02669862326514687, + "grad_norm": 0.48956695199012756, + "learning_rate": 9.997459830834379e-05, + "loss": 1.7242, + "step": 479 + }, + { + "epoch": 0.026754361518310017, + "grad_norm": 0.518091082572937, + "learning_rate": 9.997431372214394e-05, + "loss": 1.8634, + "step": 480 + }, + { + "epoch": 0.026810099771473164, + "grad_norm": 0.5070821642875671, + "learning_rate": 9.997402755105022e-05, + "loss": 1.678, + "step": 481 + }, + { + "epoch": 0.026865838024636306, + "grad_norm": 0.49108657240867615, + "learning_rate": 9.997373979507169e-05, + "loss": 1.6952, + "step": 482 + }, + { + "epoch": 0.026921576277799453, + "grad_norm": 0.4824698269367218, + "learning_rate": 9.997345045421753e-05, + "loss": 1.6948, + "step": 483 + }, + { + "epoch": 0.0269773145309626, + "grad_norm": 0.537356972694397, + "learning_rate": 9.997315952849688e-05, + "loss": 1.9746, + "step": 484 + }, + { + "epoch": 0.027033052784125745, + "grad_norm": 0.5354846119880676, + "learning_rate": 9.997286701791896e-05, + "loss": 1.9413, + "step": 485 + }, + { + "epoch": 0.02708879103728889, + "grad_norm": 0.49684658646583557, + "learning_rate": 9.99725729224931e-05, + "loss": 1.7646, + "step": 486 + }, + { + "epoch": 0.027144529290452038, + "grad_norm": 0.5149616599082947, + "learning_rate": 9.997227724222855e-05, + "loss": 1.6941, + "step": 487 + }, + { + "epoch": 0.027200267543615184, + "grad_norm": 0.48285308480262756, + "learning_rate": 9.997197997713473e-05, + "loss": 1.6994, + "step": 488 + }, + { + "epoch": 0.02725600579677833, + "grad_norm": 0.47129902243614197, + "learning_rate": 9.997168112722107e-05, + "loss": 1.8408, + "step": 489 + }, + { + "epoch": 0.027311744049941473, + "grad_norm": 0.44259312748908997, + "learning_rate": 9.997138069249703e-05, + "loss": 1.636, + "step": 490 + }, + { + "epoch": 0.02736748230310462, + "grad_norm": 0.4475281238555908, + "learning_rate": 9.997107867297216e-05, + "loss": 1.5011, + "step": 491 + }, + { + "epoch": 0.027423220556267766, + "grad_norm": 0.5637838244438171, + "learning_rate": 9.997077506865602e-05, + "loss": 2.0265, + "step": 492 + }, + { + "epoch": 0.027478958809430912, + "grad_norm": 0.5333039164543152, + "learning_rate": 9.997046987955824e-05, + "loss": 2.0372, + "step": 493 + }, + { + "epoch": 0.02753469706259406, + "grad_norm": 0.49768728017807007, + "learning_rate": 9.997016310568851e-05, + "loss": 1.8226, + "step": 494 + }, + { + "epoch": 0.027590435315757205, + "grad_norm": 0.5524271130561829, + "learning_rate": 9.996985474705654e-05, + "loss": 1.7598, + "step": 495 + }, + { + "epoch": 0.02764617356892035, + "grad_norm": 0.5334012508392334, + "learning_rate": 9.996954480367214e-05, + "loss": 1.9021, + "step": 496 + }, + { + "epoch": 0.027701911822083494, + "grad_norm": 0.5297475457191467, + "learning_rate": 9.996923327554511e-05, + "loss": 1.7989, + "step": 497 + }, + { + "epoch": 0.02775765007524664, + "grad_norm": 0.5096792578697205, + "learning_rate": 9.996892016268535e-05, + "loss": 1.7904, + "step": 498 + }, + { + "epoch": 0.027813388328409787, + "grad_norm": 0.47295787930488586, + "learning_rate": 9.996860546510278e-05, + "loss": 1.5494, + "step": 499 + }, + { + "epoch": 0.027869126581572933, + "grad_norm": 0.48092177510261536, + "learning_rate": 9.996828918280737e-05, + "loss": 1.6759, + "step": 500 + }, + { + "epoch": 0.02792486483473608, + "grad_norm": 0.4752250611782074, + "learning_rate": 9.996797131580917e-05, + "loss": 1.7032, + "step": 501 + }, + { + "epoch": 0.027980603087899226, + "grad_norm": 0.49519795179367065, + "learning_rate": 9.996765186411827e-05, + "loss": 1.7786, + "step": 502 + }, + { + "epoch": 0.028036341341062372, + "grad_norm": 0.5053145289421082, + "learning_rate": 9.996733082774477e-05, + "loss": 1.9493, + "step": 503 + }, + { + "epoch": 0.02809207959422552, + "grad_norm": 0.5514931678771973, + "learning_rate": 9.996700820669886e-05, + "loss": 2.0257, + "step": 504 + }, + { + "epoch": 0.02814781784738866, + "grad_norm": 0.5103058218955994, + "learning_rate": 9.996668400099077e-05, + "loss": 1.8291, + "step": 505 + }, + { + "epoch": 0.028203556100551808, + "grad_norm": 0.4987359941005707, + "learning_rate": 9.99663582106308e-05, + "loss": 1.6841, + "step": 506 + }, + { + "epoch": 0.028259294353714954, + "grad_norm": 0.570788562297821, + "learning_rate": 9.996603083562928e-05, + "loss": 2.1915, + "step": 507 + }, + { + "epoch": 0.0283150326068781, + "grad_norm": 0.4610704481601715, + "learning_rate": 9.996570187599658e-05, + "loss": 1.6893, + "step": 508 + }, + { + "epoch": 0.028370770860041247, + "grad_norm": 0.4623680114746094, + "learning_rate": 9.996537133174313e-05, + "loss": 1.5927, + "step": 509 + }, + { + "epoch": 0.028426509113204393, + "grad_norm": 0.4911310076713562, + "learning_rate": 9.996503920287942e-05, + "loss": 1.6685, + "step": 510 + }, + { + "epoch": 0.02848224736636754, + "grad_norm": 0.4995778799057007, + "learning_rate": 9.996470548941598e-05, + "loss": 1.8294, + "step": 511 + }, + { + "epoch": 0.028537985619530686, + "grad_norm": 0.518905758857727, + "learning_rate": 9.996437019136342e-05, + "loss": 1.6819, + "step": 512 + }, + { + "epoch": 0.02859372387269383, + "grad_norm": 0.5348454117774963, + "learning_rate": 9.996403330873233e-05, + "loss": 1.8129, + "step": 513 + }, + { + "epoch": 0.028649462125856975, + "grad_norm": 0.49906015396118164, + "learning_rate": 9.996369484153342e-05, + "loss": 1.8961, + "step": 514 + }, + { + "epoch": 0.02870520037902012, + "grad_norm": 0.5471760034561157, + "learning_rate": 9.996335478977741e-05, + "loss": 1.7716, + "step": 515 + }, + { + "epoch": 0.028760938632183267, + "grad_norm": 0.4836637079715729, + "learning_rate": 9.99630131534751e-05, + "loss": 1.7395, + "step": 516 + }, + { + "epoch": 0.028816676885346414, + "grad_norm": 0.4034901261329651, + "learning_rate": 9.996266993263732e-05, + "loss": 0.9524, + "step": 517 + }, + { + "epoch": 0.02887241513850956, + "grad_norm": 0.5080105662345886, + "learning_rate": 9.996232512727495e-05, + "loss": 1.5957, + "step": 518 + }, + { + "epoch": 0.028928153391672706, + "grad_norm": 0.4828059673309326, + "learning_rate": 9.996197873739892e-05, + "loss": 1.8356, + "step": 519 + }, + { + "epoch": 0.02898389164483585, + "grad_norm": 0.47908416390419006, + "learning_rate": 9.996163076302023e-05, + "loss": 1.7832, + "step": 520 + }, + { + "epoch": 0.029039629897998995, + "grad_norm": 0.5064157247543335, + "learning_rate": 9.996128120414989e-05, + "loss": 1.696, + "step": 521 + }, + { + "epoch": 0.029095368151162142, + "grad_norm": 0.5058413147926331, + "learning_rate": 9.996093006079903e-05, + "loss": 1.8185, + "step": 522 + }, + { + "epoch": 0.029151106404325288, + "grad_norm": 0.5816233158111572, + "learning_rate": 9.996057733297876e-05, + "loss": 2.0013, + "step": 523 + }, + { + "epoch": 0.029206844657488434, + "grad_norm": 0.506596028804779, + "learning_rate": 9.996022302070025e-05, + "loss": 1.7923, + "step": 524 + }, + { + "epoch": 0.02926258291065158, + "grad_norm": 0.48481589555740356, + "learning_rate": 9.995986712397477e-05, + "loss": 1.674, + "step": 525 + }, + { + "epoch": 0.029318321163814727, + "grad_norm": 0.6215664148330688, + "learning_rate": 9.995950964281357e-05, + "loss": 2.041, + "step": 526 + }, + { + "epoch": 0.029374059416977873, + "grad_norm": 0.5243876576423645, + "learning_rate": 9.995915057722804e-05, + "loss": 1.9253, + "step": 527 + }, + { + "epoch": 0.029429797670141016, + "grad_norm": 0.4525597393512726, + "learning_rate": 9.995878992722951e-05, + "loss": 1.5032, + "step": 528 + }, + { + "epoch": 0.029485535923304163, + "grad_norm": 0.5035833716392517, + "learning_rate": 9.995842769282946e-05, + "loss": 1.8901, + "step": 529 + }, + { + "epoch": 0.02954127417646731, + "grad_norm": 0.5944721698760986, + "learning_rate": 9.995806387403934e-05, + "loss": 2.1208, + "step": 530 + }, + { + "epoch": 0.029597012429630455, + "grad_norm": 0.5121837854385376, + "learning_rate": 9.995769847087073e-05, + "loss": 1.9563, + "step": 531 + }, + { + "epoch": 0.0296527506827936, + "grad_norm": 0.5083540678024292, + "learning_rate": 9.99573314833352e-05, + "loss": 2.0126, + "step": 532 + }, + { + "epoch": 0.029708488935956748, + "grad_norm": 0.4877237379550934, + "learning_rate": 9.995696291144438e-05, + "loss": 1.92, + "step": 533 + }, + { + "epoch": 0.029764227189119894, + "grad_norm": 0.4935770034790039, + "learning_rate": 9.995659275520995e-05, + "loss": 1.5072, + "step": 534 + }, + { + "epoch": 0.02981996544228304, + "grad_norm": 0.5800178050994873, + "learning_rate": 9.995622101464368e-05, + "loss": 2.0751, + "step": 535 + }, + { + "epoch": 0.029875703695446183, + "grad_norm": 0.5653755068778992, + "learning_rate": 9.995584768975734e-05, + "loss": 2.0538, + "step": 536 + }, + { + "epoch": 0.02993144194860933, + "grad_norm": 0.463131844997406, + "learning_rate": 9.995547278056279e-05, + "loss": 1.6813, + "step": 537 + }, + { + "epoch": 0.029987180201772476, + "grad_norm": 0.5227254629135132, + "learning_rate": 9.995509628707189e-05, + "loss": 1.9213, + "step": 538 + }, + { + "epoch": 0.030042918454935622, + "grad_norm": 0.49530157446861267, + "learning_rate": 9.99547182092966e-05, + "loss": 1.7977, + "step": 539 + }, + { + "epoch": 0.03009865670809877, + "grad_norm": 0.5396206974983215, + "learning_rate": 9.99543385472489e-05, + "loss": 1.9346, + "step": 540 + }, + { + "epoch": 0.030154394961261915, + "grad_norm": 0.517638087272644, + "learning_rate": 9.995395730094083e-05, + "loss": 1.7214, + "step": 541 + }, + { + "epoch": 0.03021013321442506, + "grad_norm": 0.5086343884468079, + "learning_rate": 9.99535744703845e-05, + "loss": 1.6459, + "step": 542 + }, + { + "epoch": 0.030265871467588207, + "grad_norm": 0.49579426646232605, + "learning_rate": 9.995319005559202e-05, + "loss": 1.7781, + "step": 543 + }, + { + "epoch": 0.03032160972075135, + "grad_norm": 0.500481128692627, + "learning_rate": 9.995280405657561e-05, + "loss": 1.8662, + "step": 544 + }, + { + "epoch": 0.030377347973914497, + "grad_norm": 0.47389981150627136, + "learning_rate": 9.99524164733475e-05, + "loss": 1.7803, + "step": 545 + }, + { + "epoch": 0.030433086227077643, + "grad_norm": 0.4981273114681244, + "learning_rate": 9.995202730591997e-05, + "loss": 1.7344, + "step": 546 + }, + { + "epoch": 0.03048882448024079, + "grad_norm": 0.507570207118988, + "learning_rate": 9.995163655430539e-05, + "loss": 1.864, + "step": 547 + }, + { + "epoch": 0.030544562733403936, + "grad_norm": 0.4923110008239746, + "learning_rate": 9.995124421851614e-05, + "loss": 1.711, + "step": 548 + }, + { + "epoch": 0.030600300986567082, + "grad_norm": 0.42948779463768005, + "learning_rate": 9.995085029856464e-05, + "loss": 1.4136, + "step": 549 + }, + { + "epoch": 0.030656039239730228, + "grad_norm": 0.5023720264434814, + "learning_rate": 9.99504547944634e-05, + "loss": 1.8524, + "step": 550 + }, + { + "epoch": 0.03071177749289337, + "grad_norm": 0.4656638205051422, + "learning_rate": 9.995005770622499e-05, + "loss": 1.5452, + "step": 551 + }, + { + "epoch": 0.030767515746056517, + "grad_norm": 0.49939560890197754, + "learning_rate": 9.994965903386198e-05, + "loss": 1.8935, + "step": 552 + }, + { + "epoch": 0.030823253999219664, + "grad_norm": 0.5469990372657776, + "learning_rate": 9.994925877738698e-05, + "loss": 1.9558, + "step": 553 + }, + { + "epoch": 0.03087899225238281, + "grad_norm": 0.46579065918922424, + "learning_rate": 9.994885693681274e-05, + "loss": 1.6339, + "step": 554 + }, + { + "epoch": 0.030934730505545956, + "grad_norm": 0.4826100468635559, + "learning_rate": 9.994845351215199e-05, + "loss": 1.6943, + "step": 555 + }, + { + "epoch": 0.030990468758709103, + "grad_norm": 0.527716338634491, + "learning_rate": 9.994804850341748e-05, + "loss": 1.9641, + "step": 556 + }, + { + "epoch": 0.03104620701187225, + "grad_norm": 0.4857400059700012, + "learning_rate": 9.994764191062212e-05, + "loss": 1.9041, + "step": 557 + }, + { + "epoch": 0.031101945265035395, + "grad_norm": 0.483614057302475, + "learning_rate": 9.994723373377876e-05, + "loss": 1.6671, + "step": 558 + }, + { + "epoch": 0.031157683518198538, + "grad_norm": 0.46863991022109985, + "learning_rate": 9.994682397290036e-05, + "loss": 1.6415, + "step": 559 + }, + { + "epoch": 0.031213421771361684, + "grad_norm": 0.5118616223335266, + "learning_rate": 9.99464126279999e-05, + "loss": 1.9253, + "step": 560 + }, + { + "epoch": 0.03126916002452483, + "grad_norm": 0.4958517849445343, + "learning_rate": 9.994599969909047e-05, + "loss": 1.5449, + "step": 561 + }, + { + "epoch": 0.03132489827768798, + "grad_norm": 0.513558030128479, + "learning_rate": 9.99455851861851e-05, + "loss": 1.8665, + "step": 562 + }, + { + "epoch": 0.03138063653085112, + "grad_norm": 0.49571189284324646, + "learning_rate": 9.9945169089297e-05, + "loss": 1.8442, + "step": 563 + }, + { + "epoch": 0.031436374784014266, + "grad_norm": 0.550983190536499, + "learning_rate": 9.994475140843933e-05, + "loss": 1.8436, + "step": 564 + }, + { + "epoch": 0.031492113037177416, + "grad_norm": 0.4547099173069, + "learning_rate": 9.994433214362532e-05, + "loss": 1.7172, + "step": 565 + }, + { + "epoch": 0.03154785129034056, + "grad_norm": 0.4933796525001526, + "learning_rate": 9.994391129486833e-05, + "loss": 1.6919, + "step": 566 + }, + { + "epoch": 0.03160358954350371, + "grad_norm": 0.5890671610832214, + "learning_rate": 9.994348886218163e-05, + "loss": 2.1026, + "step": 567 + }, + { + "epoch": 0.03165932779666685, + "grad_norm": 0.5334300398826599, + "learning_rate": 9.994306484557868e-05, + "loss": 1.9232, + "step": 568 + }, + { + "epoch": 0.03171506604983, + "grad_norm": 0.4899601340293884, + "learning_rate": 9.99426392450729e-05, + "loss": 1.6408, + "step": 569 + }, + { + "epoch": 0.031770804302993144, + "grad_norm": 0.5135582089424133, + "learning_rate": 9.994221206067777e-05, + "loss": 1.8562, + "step": 570 + }, + { + "epoch": 0.03182654255615629, + "grad_norm": 0.5050702095031738, + "learning_rate": 9.994178329240686e-05, + "loss": 1.7045, + "step": 571 + }, + { + "epoch": 0.03188228080931944, + "grad_norm": 0.4874882102012634, + "learning_rate": 9.994135294027378e-05, + "loss": 1.8015, + "step": 572 + }, + { + "epoch": 0.03193801906248258, + "grad_norm": 0.6017099022865295, + "learning_rate": 9.994092100429215e-05, + "loss": 2.1681, + "step": 573 + }, + { + "epoch": 0.03199375731564573, + "grad_norm": 0.4922308325767517, + "learning_rate": 9.994048748447569e-05, + "loss": 1.6771, + "step": 574 + }, + { + "epoch": 0.03204949556880887, + "grad_norm": 0.5013367533683777, + "learning_rate": 9.994005238083815e-05, + "loss": 1.7157, + "step": 575 + }, + { + "epoch": 0.03210523382197202, + "grad_norm": 0.47761455178260803, + "learning_rate": 9.99396156933933e-05, + "loss": 1.8095, + "step": 576 + }, + { + "epoch": 0.032160972075135165, + "grad_norm": 0.5500997304916382, + "learning_rate": 9.993917742215502e-05, + "loss": 2.2013, + "step": 577 + }, + { + "epoch": 0.03221671032829831, + "grad_norm": 0.5222569108009338, + "learning_rate": 9.993873756713719e-05, + "loss": 1.9967, + "step": 578 + }, + { + "epoch": 0.03227244858146146, + "grad_norm": 0.520000696182251, + "learning_rate": 9.993829612835378e-05, + "loss": 1.6328, + "step": 579 + }, + { + "epoch": 0.0323281868346246, + "grad_norm": 0.501677930355072, + "learning_rate": 9.993785310581875e-05, + "loss": 1.9793, + "step": 580 + }, + { + "epoch": 0.03238392508778775, + "grad_norm": 0.4832457900047302, + "learning_rate": 9.993740849954619e-05, + "loss": 1.7687, + "step": 581 + }, + { + "epoch": 0.03243966334095089, + "grad_norm": 0.4854641556739807, + "learning_rate": 9.99369623095502e-05, + "loss": 1.8983, + "step": 582 + }, + { + "epoch": 0.03249540159411404, + "grad_norm": 0.48794299364089966, + "learning_rate": 9.993651453584491e-05, + "loss": 1.6625, + "step": 583 + }, + { + "epoch": 0.032551139847277186, + "grad_norm": 0.4691779911518097, + "learning_rate": 9.993606517844452e-05, + "loss": 1.7413, + "step": 584 + }, + { + "epoch": 0.032606878100440335, + "grad_norm": 0.531639039516449, + "learning_rate": 9.993561423736331e-05, + "loss": 1.875, + "step": 585 + }, + { + "epoch": 0.03266261635360348, + "grad_norm": 0.5259484648704529, + "learning_rate": 9.993516171261555e-05, + "loss": 1.9669, + "step": 586 + }, + { + "epoch": 0.03271835460676662, + "grad_norm": 0.4976826012134552, + "learning_rate": 9.993470760421559e-05, + "loss": 1.808, + "step": 587 + }, + { + "epoch": 0.03277409285992977, + "grad_norm": 0.4722268283367157, + "learning_rate": 9.993425191217787e-05, + "loss": 1.7654, + "step": 588 + }, + { + "epoch": 0.032829831113092914, + "grad_norm": 0.4951403737068176, + "learning_rate": 9.993379463651679e-05, + "loss": 1.8282, + "step": 589 + }, + { + "epoch": 0.032885569366256064, + "grad_norm": 0.4893924295902252, + "learning_rate": 9.99333357772469e-05, + "loss": 1.6477, + "step": 590 + }, + { + "epoch": 0.032941307619419206, + "grad_norm": 0.4877261519432068, + "learning_rate": 9.993287533438273e-05, + "loss": 1.6518, + "step": 591 + }, + { + "epoch": 0.032997045872582356, + "grad_norm": 0.48906272649765015, + "learning_rate": 9.993241330793888e-05, + "loss": 1.6485, + "step": 592 + }, + { + "epoch": 0.0330527841257455, + "grad_norm": 0.5735100507736206, + "learning_rate": 9.993194969792999e-05, + "loss": 2.0397, + "step": 593 + }, + { + "epoch": 0.03310852237890864, + "grad_norm": 0.45156189799308777, + "learning_rate": 9.99314845043708e-05, + "loss": 1.6368, + "step": 594 + }, + { + "epoch": 0.03316426063207179, + "grad_norm": 0.4821372628211975, + "learning_rate": 9.993101772727602e-05, + "loss": 1.6886, + "step": 595 + }, + { + "epoch": 0.033219998885234935, + "grad_norm": 0.501278817653656, + "learning_rate": 9.993054936666048e-05, + "loss": 1.7587, + "step": 596 + }, + { + "epoch": 0.033275737138398084, + "grad_norm": 0.5598791241645813, + "learning_rate": 9.993007942253905e-05, + "loss": 1.8861, + "step": 597 + }, + { + "epoch": 0.03333147539156123, + "grad_norm": 0.48821693658828735, + "learning_rate": 9.99296078949266e-05, + "loss": 1.6563, + "step": 598 + }, + { + "epoch": 0.03338721364472438, + "grad_norm": 0.4853152632713318, + "learning_rate": 9.99291347838381e-05, + "loss": 1.5493, + "step": 599 + }, + { + "epoch": 0.03344295189788752, + "grad_norm": 0.5629671812057495, + "learning_rate": 9.992866008928855e-05, + "loss": 2.1359, + "step": 600 + }, + { + "epoch": 0.03349869015105066, + "grad_norm": 0.5176377892494202, + "learning_rate": 9.9928183811293e-05, + "loss": 2.0139, + "step": 601 + }, + { + "epoch": 0.03355442840421381, + "grad_norm": 0.46964964270591736, + "learning_rate": 9.992770594986658e-05, + "loss": 1.6594, + "step": 602 + }, + { + "epoch": 0.033610166657376955, + "grad_norm": 0.49720609188079834, + "learning_rate": 9.992722650502442e-05, + "loss": 1.8432, + "step": 603 + }, + { + "epoch": 0.033665904910540105, + "grad_norm": 0.4787680506706238, + "learning_rate": 9.992674547678171e-05, + "loss": 1.8071, + "step": 604 + }, + { + "epoch": 0.03372164316370325, + "grad_norm": 0.4432480037212372, + "learning_rate": 9.992626286515373e-05, + "loss": 1.6391, + "step": 605 + }, + { + "epoch": 0.0337773814168664, + "grad_norm": 0.5781794786453247, + "learning_rate": 9.992577867015581e-05, + "loss": 2.0711, + "step": 606 + }, + { + "epoch": 0.03383311967002954, + "grad_norm": 0.45807138085365295, + "learning_rate": 9.992529289180326e-05, + "loss": 1.5886, + "step": 607 + }, + { + "epoch": 0.03388885792319269, + "grad_norm": 0.5234102606773376, + "learning_rate": 9.992480553011151e-05, + "loss": 1.9211, + "step": 608 + }, + { + "epoch": 0.03394459617635583, + "grad_norm": 0.5202253460884094, + "learning_rate": 9.9924316585096e-05, + "loss": 1.819, + "step": 609 + }, + { + "epoch": 0.034000334429518976, + "grad_norm": 0.4516846537590027, + "learning_rate": 9.992382605677226e-05, + "loss": 1.6631, + "step": 610 + }, + { + "epoch": 0.034056072682682126, + "grad_norm": 0.5501968860626221, + "learning_rate": 9.992333394515583e-05, + "loss": 2.0759, + "step": 611 + }, + { + "epoch": 0.03411181093584527, + "grad_norm": 0.4812159836292267, + "learning_rate": 9.992284025026231e-05, + "loss": 1.6721, + "step": 612 + }, + { + "epoch": 0.03416754918900842, + "grad_norm": 0.5236145257949829, + "learning_rate": 9.992234497210737e-05, + "loss": 1.807, + "step": 613 + }, + { + "epoch": 0.03422328744217156, + "grad_norm": 0.5123412609100342, + "learning_rate": 9.992184811070673e-05, + "loss": 1.9095, + "step": 614 + }, + { + "epoch": 0.03427902569533471, + "grad_norm": 0.49797573685646057, + "learning_rate": 9.992134966607612e-05, + "loss": 1.7303, + "step": 615 + }, + { + "epoch": 0.034334763948497854, + "grad_norm": 0.48441436886787415, + "learning_rate": 9.992084963823136e-05, + "loss": 1.6339, + "step": 616 + }, + { + "epoch": 0.034390502201661, + "grad_norm": 0.5459060668945312, + "learning_rate": 9.992034802718832e-05, + "loss": 1.8881, + "step": 617 + }, + { + "epoch": 0.03444624045482415, + "grad_norm": 0.5051499009132385, + "learning_rate": 9.991984483296288e-05, + "loss": 1.9386, + "step": 618 + }, + { + "epoch": 0.03450197870798729, + "grad_norm": 0.5421403050422668, + "learning_rate": 9.991934005557103e-05, + "loss": 2.0836, + "step": 619 + }, + { + "epoch": 0.03455771696115044, + "grad_norm": 0.4838196933269501, + "learning_rate": 9.991883369502874e-05, + "loss": 1.6526, + "step": 620 + }, + { + "epoch": 0.03461345521431358, + "grad_norm": 0.49810105562210083, + "learning_rate": 9.991832575135211e-05, + "loss": 1.7326, + "step": 621 + }, + { + "epoch": 0.03466919346747673, + "grad_norm": 0.46195507049560547, + "learning_rate": 9.991781622455723e-05, + "loss": 1.6398, + "step": 622 + }, + { + "epoch": 0.034724931720639875, + "grad_norm": 0.46615251898765564, + "learning_rate": 9.991730511466026e-05, + "loss": 1.7927, + "step": 623 + }, + { + "epoch": 0.03478066997380302, + "grad_norm": 0.5302008390426636, + "learning_rate": 9.991679242167741e-05, + "loss": 1.8047, + "step": 624 + }, + { + "epoch": 0.03483640822696617, + "grad_norm": 0.49787190556526184, + "learning_rate": 9.991627814562494e-05, + "loss": 1.9146, + "step": 625 + }, + { + "epoch": 0.03489214648012931, + "grad_norm": 0.5156252384185791, + "learning_rate": 9.991576228651915e-05, + "loss": 1.9453, + "step": 626 + }, + { + "epoch": 0.03494788473329246, + "grad_norm": 0.45635107159614563, + "learning_rate": 9.991524484437642e-05, + "loss": 1.7143, + "step": 627 + }, + { + "epoch": 0.0350036229864556, + "grad_norm": 0.48797038197517395, + "learning_rate": 9.991472581921316e-05, + "loss": 1.7371, + "step": 628 + }, + { + "epoch": 0.03505936123961875, + "grad_norm": 0.549708366394043, + "learning_rate": 9.99142052110458e-05, + "loss": 1.9569, + "step": 629 + }, + { + "epoch": 0.035115099492781895, + "grad_norm": 0.4693654179573059, + "learning_rate": 9.991368301989088e-05, + "loss": 1.4609, + "step": 630 + }, + { + "epoch": 0.035170837745945045, + "grad_norm": 0.5259846448898315, + "learning_rate": 9.991315924576495e-05, + "loss": 1.7577, + "step": 631 + }, + { + "epoch": 0.03522657599910819, + "grad_norm": 0.49805745482444763, + "learning_rate": 9.991263388868461e-05, + "loss": 1.8534, + "step": 632 + }, + { + "epoch": 0.03528231425227133, + "grad_norm": 0.4565132260322571, + "learning_rate": 9.991210694866654e-05, + "loss": 1.6853, + "step": 633 + }, + { + "epoch": 0.03533805250543448, + "grad_norm": 0.5158933401107788, + "learning_rate": 9.991157842572747e-05, + "loss": 1.8088, + "step": 634 + }, + { + "epoch": 0.035393790758597624, + "grad_norm": 0.49667277932167053, + "learning_rate": 9.991104831988412e-05, + "loss": 1.9148, + "step": 635 + }, + { + "epoch": 0.03544952901176077, + "grad_norm": 0.48701363801956177, + "learning_rate": 9.991051663115331e-05, + "loss": 1.7816, + "step": 636 + }, + { + "epoch": 0.035505267264923916, + "grad_norm": 0.5608890056610107, + "learning_rate": 9.990998335955193e-05, + "loss": 1.8764, + "step": 637 + }, + { + "epoch": 0.035561005518087066, + "grad_norm": 0.49871060252189636, + "learning_rate": 9.990944850509685e-05, + "loss": 1.6103, + "step": 638 + }, + { + "epoch": 0.03561674377125021, + "grad_norm": 0.46610593795776367, + "learning_rate": 9.990891206780506e-05, + "loss": 1.7798, + "step": 639 + }, + { + "epoch": 0.03567248202441335, + "grad_norm": 0.5284513831138611, + "learning_rate": 9.990837404769358e-05, + "loss": 1.8771, + "step": 640 + }, + { + "epoch": 0.0357282202775765, + "grad_norm": 0.5929260849952698, + "learning_rate": 9.990783444477946e-05, + "loss": 2.0712, + "step": 641 + }, + { + "epoch": 0.035783958530739644, + "grad_norm": 0.5146616697311401, + "learning_rate": 9.990729325907981e-05, + "loss": 1.7693, + "step": 642 + }, + { + "epoch": 0.035839696783902794, + "grad_norm": 0.5243765711784363, + "learning_rate": 9.99067504906118e-05, + "loss": 1.8675, + "step": 643 + }, + { + "epoch": 0.03589543503706594, + "grad_norm": 0.48738136887550354, + "learning_rate": 9.990620613939263e-05, + "loss": 1.7557, + "step": 644 + }, + { + "epoch": 0.03595117329022909, + "grad_norm": 0.5006791353225708, + "learning_rate": 9.990566020543959e-05, + "loss": 1.7199, + "step": 645 + }, + { + "epoch": 0.03600691154339223, + "grad_norm": 0.5283340811729431, + "learning_rate": 9.990511268876998e-05, + "loss": 1.9156, + "step": 646 + }, + { + "epoch": 0.03606264979655538, + "grad_norm": 0.47615885734558105, + "learning_rate": 9.990456358940115e-05, + "loss": 1.6183, + "step": 647 + }, + { + "epoch": 0.03611838804971852, + "grad_norm": 0.48326513171195984, + "learning_rate": 9.990401290735053e-05, + "loss": 1.8159, + "step": 648 + }, + { + "epoch": 0.036174126302881665, + "grad_norm": 0.489183247089386, + "learning_rate": 9.990346064263558e-05, + "loss": 1.9306, + "step": 649 + }, + { + "epoch": 0.036229864556044815, + "grad_norm": 0.44880211353302, + "learning_rate": 9.990290679527382e-05, + "loss": 1.4257, + "step": 650 + }, + { + "epoch": 0.03628560280920796, + "grad_norm": 0.49666327238082886, + "learning_rate": 9.990235136528281e-05, + "loss": 1.6587, + "step": 651 + }, + { + "epoch": 0.03634134106237111, + "grad_norm": 0.5396116971969604, + "learning_rate": 9.990179435268017e-05, + "loss": 1.9138, + "step": 652 + }, + { + "epoch": 0.03639707931553425, + "grad_norm": 0.512506902217865, + "learning_rate": 9.990123575748355e-05, + "loss": 2.0153, + "step": 653 + }, + { + "epoch": 0.0364528175686974, + "grad_norm": 0.48785391449928284, + "learning_rate": 9.990067557971068e-05, + "loss": 1.9489, + "step": 654 + }, + { + "epoch": 0.03650855582186054, + "grad_norm": 0.49123311042785645, + "learning_rate": 9.990011381937933e-05, + "loss": 1.6926, + "step": 655 + }, + { + "epoch": 0.036564294075023686, + "grad_norm": 0.4744409918785095, + "learning_rate": 9.98995504765073e-05, + "loss": 1.7961, + "step": 656 + }, + { + "epoch": 0.036620032328186836, + "grad_norm": 0.5175344944000244, + "learning_rate": 9.989898555111245e-05, + "loss": 1.8846, + "step": 657 + }, + { + "epoch": 0.03667577058134998, + "grad_norm": 0.4825249910354614, + "learning_rate": 9.989841904321274e-05, + "loss": 1.7094, + "step": 658 + }, + { + "epoch": 0.03673150883451313, + "grad_norm": 0.5392758250236511, + "learning_rate": 9.989785095282609e-05, + "loss": 1.8777, + "step": 659 + }, + { + "epoch": 0.03678724708767627, + "grad_norm": 0.5122122764587402, + "learning_rate": 9.989728127997052e-05, + "loss": 1.8686, + "step": 660 + }, + { + "epoch": 0.03684298534083942, + "grad_norm": 0.4976766109466553, + "learning_rate": 9.989671002466412e-05, + "loss": 1.7542, + "step": 661 + }, + { + "epoch": 0.036898723594002564, + "grad_norm": 0.4618877172470093, + "learning_rate": 9.989613718692501e-05, + "loss": 1.4741, + "step": 662 + }, + { + "epoch": 0.03695446184716571, + "grad_norm": 0.4870270788669586, + "learning_rate": 9.989556276677133e-05, + "loss": 1.6816, + "step": 663 + }, + { + "epoch": 0.037010200100328856, + "grad_norm": 0.5549145936965942, + "learning_rate": 9.989498676422131e-05, + "loss": 1.8716, + "step": 664 + }, + { + "epoch": 0.037065938353492, + "grad_norm": 0.501438319683075, + "learning_rate": 9.989440917929321e-05, + "loss": 1.7686, + "step": 665 + }, + { + "epoch": 0.03712167660665515, + "grad_norm": 0.5713873505592346, + "learning_rate": 9.989383001200536e-05, + "loss": 2.116, + "step": 666 + }, + { + "epoch": 0.03717741485981829, + "grad_norm": 0.4839586615562439, + "learning_rate": 9.989324926237613e-05, + "loss": 1.8245, + "step": 667 + }, + { + "epoch": 0.03723315311298144, + "grad_norm": 0.5154809355735779, + "learning_rate": 9.989266693042394e-05, + "loss": 1.661, + "step": 668 + }, + { + "epoch": 0.037288891366144584, + "grad_norm": 0.4965420365333557, + "learning_rate": 9.989208301616724e-05, + "loss": 1.6531, + "step": 669 + }, + { + "epoch": 0.037344629619307734, + "grad_norm": 0.4850505292415619, + "learning_rate": 9.989149751962455e-05, + "loss": 1.8691, + "step": 670 + }, + { + "epoch": 0.03740036787247088, + "grad_norm": 0.47275611758232117, + "learning_rate": 9.989091044081445e-05, + "loss": 1.7718, + "step": 671 + }, + { + "epoch": 0.03745610612563402, + "grad_norm": 0.5606955885887146, + "learning_rate": 9.989032177975554e-05, + "loss": 2.2129, + "step": 672 + }, + { + "epoch": 0.03751184437879717, + "grad_norm": 0.49657538533210754, + "learning_rate": 9.988973153646654e-05, + "loss": 1.9084, + "step": 673 + }, + { + "epoch": 0.03756758263196031, + "grad_norm": 0.5135958790779114, + "learning_rate": 9.988913971096611e-05, + "loss": 1.9491, + "step": 674 + }, + { + "epoch": 0.03762332088512346, + "grad_norm": 0.48900923132896423, + "learning_rate": 9.988854630327305e-05, + "loss": 1.7176, + "step": 675 + }, + { + "epoch": 0.037679059138286605, + "grad_norm": 0.463521808385849, + "learning_rate": 9.988795131340616e-05, + "loss": 1.5625, + "step": 676 + }, + { + "epoch": 0.037734797391449755, + "grad_norm": 0.48082444071769714, + "learning_rate": 9.988735474138433e-05, + "loss": 1.7208, + "step": 677 + }, + { + "epoch": 0.0377905356446129, + "grad_norm": 0.5012754201889038, + "learning_rate": 9.988675658722648e-05, + "loss": 1.9678, + "step": 678 + }, + { + "epoch": 0.03784627389777604, + "grad_norm": 0.5888019800186157, + "learning_rate": 9.988615685095155e-05, + "loss": 2.2239, + "step": 679 + }, + { + "epoch": 0.03790201215093919, + "grad_norm": 0.47830748558044434, + "learning_rate": 9.98855555325786e-05, + "loss": 1.6574, + "step": 680 + }, + { + "epoch": 0.03795775040410233, + "grad_norm": 0.47648170590400696, + "learning_rate": 9.988495263212667e-05, + "loss": 1.6185, + "step": 681 + }, + { + "epoch": 0.03801348865726548, + "grad_norm": 0.5321143269538879, + "learning_rate": 9.98843481496149e-05, + "loss": 2.0788, + "step": 682 + }, + { + "epoch": 0.038069226910428626, + "grad_norm": 0.4451909363269806, + "learning_rate": 9.988374208506243e-05, + "loss": 1.7213, + "step": 683 + }, + { + "epoch": 0.038124965163591776, + "grad_norm": 0.4888899028301239, + "learning_rate": 9.988313443848853e-05, + "loss": 1.9524, + "step": 684 + }, + { + "epoch": 0.03818070341675492, + "grad_norm": 0.5075884461402893, + "learning_rate": 9.988252520991244e-05, + "loss": 1.9489, + "step": 685 + }, + { + "epoch": 0.03823644166991806, + "grad_norm": 0.5244428515434265, + "learning_rate": 9.988191439935348e-05, + "loss": 1.8805, + "step": 686 + }, + { + "epoch": 0.03829217992308121, + "grad_norm": 0.5269452333450317, + "learning_rate": 9.988130200683103e-05, + "loss": 1.916, + "step": 687 + }, + { + "epoch": 0.038347918176244354, + "grad_norm": 0.40096086263656616, + "learning_rate": 9.98806880323645e-05, + "loss": 1.3248, + "step": 688 + }, + { + "epoch": 0.038403656429407504, + "grad_norm": 0.555325984954834, + "learning_rate": 9.988007247597337e-05, + "loss": 1.945, + "step": 689 + }, + { + "epoch": 0.03845939468257065, + "grad_norm": 0.4987097382545471, + "learning_rate": 9.987945533767717e-05, + "loss": 1.9159, + "step": 690 + }, + { + "epoch": 0.0385151329357338, + "grad_norm": 0.46860477328300476, + "learning_rate": 9.987883661749548e-05, + "loss": 1.7105, + "step": 691 + }, + { + "epoch": 0.03857087118889694, + "grad_norm": 0.4867911636829376, + "learning_rate": 9.987821631544789e-05, + "loss": 1.6607, + "step": 692 + }, + { + "epoch": 0.03862660944206009, + "grad_norm": 0.5149185061454773, + "learning_rate": 9.987759443155409e-05, + "loss": 1.8422, + "step": 693 + }, + { + "epoch": 0.03868234769522323, + "grad_norm": 0.508399248123169, + "learning_rate": 9.98769709658338e-05, + "loss": 1.8393, + "step": 694 + }, + { + "epoch": 0.038738085948386375, + "grad_norm": 0.4841381907463074, + "learning_rate": 9.987634591830679e-05, + "loss": 1.8819, + "step": 695 + }, + { + "epoch": 0.038793824201549525, + "grad_norm": 0.4869403541088104, + "learning_rate": 9.987571928899288e-05, + "loss": 1.7872, + "step": 696 + }, + { + "epoch": 0.03884956245471267, + "grad_norm": 0.49572715163230896, + "learning_rate": 9.987509107791196e-05, + "loss": 1.8078, + "step": 697 + }, + { + "epoch": 0.03890530070787582, + "grad_norm": 0.5188158750534058, + "learning_rate": 9.987446128508396e-05, + "loss": 1.7838, + "step": 698 + }, + { + "epoch": 0.03896103896103896, + "grad_norm": 0.4589369595050812, + "learning_rate": 9.98738299105288e-05, + "loss": 1.7299, + "step": 699 + }, + { + "epoch": 0.03901677721420211, + "grad_norm": 0.5023289322853088, + "learning_rate": 9.987319695426657e-05, + "loss": 1.7414, + "step": 700 + }, + { + "epoch": 0.03907251546736525, + "grad_norm": 0.5241897702217102, + "learning_rate": 9.98725624163173e-05, + "loss": 1.8223, + "step": 701 + }, + { + "epoch": 0.039128253720528396, + "grad_norm": 0.4720919728279114, + "learning_rate": 9.987192629670112e-05, + "loss": 1.791, + "step": 702 + }, + { + "epoch": 0.039183991973691545, + "grad_norm": 0.5045210719108582, + "learning_rate": 9.987128859543824e-05, + "loss": 1.7428, + "step": 703 + }, + { + "epoch": 0.03923973022685469, + "grad_norm": 0.5130773782730103, + "learning_rate": 9.987064931254884e-05, + "loss": 1.6701, + "step": 704 + }, + { + "epoch": 0.03929546848001784, + "grad_norm": 0.5155162215232849, + "learning_rate": 9.987000844805319e-05, + "loss": 1.9592, + "step": 705 + }, + { + "epoch": 0.03935120673318098, + "grad_norm": 0.46410509943962097, + "learning_rate": 9.986936600197165e-05, + "loss": 1.786, + "step": 706 + }, + { + "epoch": 0.03940694498634413, + "grad_norm": 0.5000941157341003, + "learning_rate": 9.986872197432459e-05, + "loss": 1.7937, + "step": 707 + }, + { + "epoch": 0.039462683239507274, + "grad_norm": 0.4663851261138916, + "learning_rate": 9.986807636513241e-05, + "loss": 1.8019, + "step": 708 + }, + { + "epoch": 0.039518421492670416, + "grad_norm": 0.5445390343666077, + "learning_rate": 9.986742917441561e-05, + "loss": 1.9214, + "step": 709 + }, + { + "epoch": 0.039574159745833566, + "grad_norm": 0.49968406558036804, + "learning_rate": 9.986678040219469e-05, + "loss": 1.7621, + "step": 710 + }, + { + "epoch": 0.03962989799899671, + "grad_norm": 0.514168381690979, + "learning_rate": 9.986613004849024e-05, + "loss": 1.7435, + "step": 711 + }, + { + "epoch": 0.03968563625215986, + "grad_norm": 0.4899461269378662, + "learning_rate": 9.986547811332289e-05, + "loss": 1.7199, + "step": 712 + }, + { + "epoch": 0.039741374505323, + "grad_norm": 0.5172072052955627, + "learning_rate": 9.986482459671332e-05, + "loss": 1.9435, + "step": 713 + }, + { + "epoch": 0.03979711275848615, + "grad_norm": 0.5198094844818115, + "learning_rate": 9.986416949868223e-05, + "loss": 1.799, + "step": 714 + }, + { + "epoch": 0.039852851011649294, + "grad_norm": 0.47976863384246826, + "learning_rate": 9.986351281925042e-05, + "loss": 1.8455, + "step": 715 + }, + { + "epoch": 0.039908589264812444, + "grad_norm": 0.4702402949333191, + "learning_rate": 9.986285455843872e-05, + "loss": 1.5848, + "step": 716 + }, + { + "epoch": 0.03996432751797559, + "grad_norm": 0.4698415994644165, + "learning_rate": 9.986219471626797e-05, + "loss": 1.6527, + "step": 717 + }, + { + "epoch": 0.04002006577113873, + "grad_norm": 0.5518625974655151, + "learning_rate": 9.986153329275913e-05, + "loss": 1.8773, + "step": 718 + }, + { + "epoch": 0.04007580402430188, + "grad_norm": 0.5149457454681396, + "learning_rate": 9.986087028793316e-05, + "loss": 1.8737, + "step": 719 + }, + { + "epoch": 0.04013154227746502, + "grad_norm": 0.527282178401947, + "learning_rate": 9.98602057018111e-05, + "loss": 1.9581, + "step": 720 + }, + { + "epoch": 0.04018728053062817, + "grad_norm": 0.48371025919914246, + "learning_rate": 9.985953953441402e-05, + "loss": 1.887, + "step": 721 + }, + { + "epoch": 0.040243018783791315, + "grad_norm": 0.5474866032600403, + "learning_rate": 9.985887178576305e-05, + "loss": 1.9981, + "step": 722 + }, + { + "epoch": 0.040298757036954465, + "grad_norm": 0.5417437553405762, + "learning_rate": 9.985820245587936e-05, + "loss": 2.0195, + "step": 723 + }, + { + "epoch": 0.04035449529011761, + "grad_norm": 0.458363801240921, + "learning_rate": 9.985753154478418e-05, + "loss": 1.6134, + "step": 724 + }, + { + "epoch": 0.04041023354328075, + "grad_norm": 0.49649447202682495, + "learning_rate": 9.98568590524988e-05, + "loss": 1.7501, + "step": 725 + }, + { + "epoch": 0.0404659717964439, + "grad_norm": 0.5304057002067566, + "learning_rate": 9.985618497904453e-05, + "loss": 1.9164, + "step": 726 + }, + { + "epoch": 0.04052171004960704, + "grad_norm": 0.4757838249206543, + "learning_rate": 9.985550932444275e-05, + "loss": 1.8159, + "step": 727 + }, + { + "epoch": 0.04057744830277019, + "grad_norm": 0.48324036598205566, + "learning_rate": 9.98548320887149e-05, + "loss": 1.6184, + "step": 728 + }, + { + "epoch": 0.040633186555933336, + "grad_norm": 0.5059638023376465, + "learning_rate": 9.985415327188245e-05, + "loss": 1.8383, + "step": 729 + }, + { + "epoch": 0.040688924809096486, + "grad_norm": 0.4717106819152832, + "learning_rate": 9.985347287396692e-05, + "loss": 1.67, + "step": 730 + }, + { + "epoch": 0.04074466306225963, + "grad_norm": 0.4953088164329529, + "learning_rate": 9.98527908949899e-05, + "loss": 1.8185, + "step": 731 + }, + { + "epoch": 0.04080040131542277, + "grad_norm": 0.49030283093452454, + "learning_rate": 9.985210733497301e-05, + "loss": 1.7909, + "step": 732 + }, + { + "epoch": 0.04085613956858592, + "grad_norm": 0.5224010944366455, + "learning_rate": 9.985142219393795e-05, + "loss": 1.8615, + "step": 733 + }, + { + "epoch": 0.040911877821749064, + "grad_norm": 0.5008676648139954, + "learning_rate": 9.985073547190641e-05, + "loss": 1.9337, + "step": 734 + }, + { + "epoch": 0.040967616074912214, + "grad_norm": 0.4777420163154602, + "learning_rate": 9.98500471689002e-05, + "loss": 1.8345, + "step": 735 + }, + { + "epoch": 0.04102335432807536, + "grad_norm": 0.4995800852775574, + "learning_rate": 9.984935728494113e-05, + "loss": 1.843, + "step": 736 + }, + { + "epoch": 0.041079092581238506, + "grad_norm": 0.5097813010215759, + "learning_rate": 9.984866582005111e-05, + "loss": 1.9642, + "step": 737 + }, + { + "epoch": 0.04113483083440165, + "grad_norm": 0.4956590533256531, + "learning_rate": 9.984797277425204e-05, + "loss": 1.8874, + "step": 738 + }, + { + "epoch": 0.0411905690875648, + "grad_norm": 0.5304232239723206, + "learning_rate": 9.98472781475659e-05, + "loss": 1.9269, + "step": 739 + }, + { + "epoch": 0.04124630734072794, + "grad_norm": 0.5134212374687195, + "learning_rate": 9.984658194001474e-05, + "loss": 1.5059, + "step": 740 + }, + { + "epoch": 0.041302045593891085, + "grad_norm": 0.4551413953304291, + "learning_rate": 9.984588415162061e-05, + "loss": 1.7386, + "step": 741 + }, + { + "epoch": 0.041357783847054234, + "grad_norm": 0.5477944612503052, + "learning_rate": 9.984518478240568e-05, + "loss": 1.9075, + "step": 742 + }, + { + "epoch": 0.04141352210021738, + "grad_norm": 0.4997386038303375, + "learning_rate": 9.98444838323921e-05, + "loss": 1.7812, + "step": 743 + }, + { + "epoch": 0.04146926035338053, + "grad_norm": 0.5239866971969604, + "learning_rate": 9.984378130160208e-05, + "loss": 1.9155, + "step": 744 + }, + { + "epoch": 0.04152499860654367, + "grad_norm": 0.46206948161125183, + "learning_rate": 9.984307719005795e-05, + "loss": 1.6661, + "step": 745 + }, + { + "epoch": 0.04158073685970682, + "grad_norm": 0.4978305399417877, + "learning_rate": 9.984237149778201e-05, + "loss": 1.8456, + "step": 746 + }, + { + "epoch": 0.04163647511286996, + "grad_norm": 0.50936359167099, + "learning_rate": 9.984166422479663e-05, + "loss": 1.9118, + "step": 747 + }, + { + "epoch": 0.041692213366033105, + "grad_norm": 0.49744611978530884, + "learning_rate": 9.984095537112429e-05, + "loss": 1.7721, + "step": 748 + }, + { + "epoch": 0.041747951619196255, + "grad_norm": 0.536056637763977, + "learning_rate": 9.984024493678743e-05, + "loss": 1.7968, + "step": 749 + }, + { + "epoch": 0.0418036898723594, + "grad_norm": 0.5262266993522644, + "learning_rate": 9.983953292180857e-05, + "loss": 1.858, + "step": 750 + }, + { + "epoch": 0.04185942812552255, + "grad_norm": 0.5085186958312988, + "learning_rate": 9.983881932621033e-05, + "loss": 1.751, + "step": 751 + }, + { + "epoch": 0.04191516637868569, + "grad_norm": 0.4641915261745453, + "learning_rate": 9.983810415001531e-05, + "loss": 1.5998, + "step": 752 + }, + { + "epoch": 0.04197090463184884, + "grad_norm": 0.5268242955207825, + "learning_rate": 9.983738739324621e-05, + "loss": 1.7263, + "step": 753 + }, + { + "epoch": 0.04202664288501198, + "grad_norm": 0.5283384919166565, + "learning_rate": 9.983666905592576e-05, + "loss": 1.9334, + "step": 754 + }, + { + "epoch": 0.042082381138175126, + "grad_norm": 0.5007447600364685, + "learning_rate": 9.983594913807672e-05, + "loss": 1.6944, + "step": 755 + }, + { + "epoch": 0.042138119391338276, + "grad_norm": 0.5626598596572876, + "learning_rate": 9.983522763972196e-05, + "loss": 2.042, + "step": 756 + }, + { + "epoch": 0.04219385764450142, + "grad_norm": 0.46739470958709717, + "learning_rate": 9.983450456088432e-05, + "loss": 1.6733, + "step": 757 + }, + { + "epoch": 0.04224959589766457, + "grad_norm": 0.5124320983886719, + "learning_rate": 9.983377990158676e-05, + "loss": 1.8463, + "step": 758 + }, + { + "epoch": 0.04230533415082771, + "grad_norm": 0.4762093722820282, + "learning_rate": 9.983305366185223e-05, + "loss": 1.7602, + "step": 759 + }, + { + "epoch": 0.04236107240399086, + "grad_norm": 0.5182420015335083, + "learning_rate": 9.983232584170381e-05, + "loss": 1.8644, + "step": 760 + }, + { + "epoch": 0.042416810657154004, + "grad_norm": 0.4640427231788635, + "learning_rate": 9.983159644116454e-05, + "loss": 1.6919, + "step": 761 + }, + { + "epoch": 0.042472548910317154, + "grad_norm": 0.4894956946372986, + "learning_rate": 9.983086546025759e-05, + "loss": 1.9491, + "step": 762 + }, + { + "epoch": 0.0425282871634803, + "grad_norm": 0.49869638681411743, + "learning_rate": 9.98301328990061e-05, + "loss": 1.9184, + "step": 763 + }, + { + "epoch": 0.04258402541664344, + "grad_norm": 0.5161083936691284, + "learning_rate": 9.982939875743333e-05, + "loss": 1.826, + "step": 764 + }, + { + "epoch": 0.04263976366980659, + "grad_norm": 0.4913845956325531, + "learning_rate": 9.982866303556258e-05, + "loss": 1.7675, + "step": 765 + }, + { + "epoch": 0.04269550192296973, + "grad_norm": 0.49277618527412415, + "learning_rate": 9.982792573341713e-05, + "loss": 1.8539, + "step": 766 + }, + { + "epoch": 0.04275124017613288, + "grad_norm": 0.5222828388214111, + "learning_rate": 9.982718685102039e-05, + "loss": 1.9196, + "step": 767 + }, + { + "epoch": 0.042806978429296025, + "grad_norm": 0.5137212872505188, + "learning_rate": 9.982644638839583e-05, + "loss": 1.8719, + "step": 768 + }, + { + "epoch": 0.042862716682459175, + "grad_norm": 0.646440327167511, + "learning_rate": 9.982570434556686e-05, + "loss": 1.9678, + "step": 769 + }, + { + "epoch": 0.04291845493562232, + "grad_norm": 0.4992925524711609, + "learning_rate": 9.982496072255708e-05, + "loss": 1.7078, + "step": 770 + }, + { + "epoch": 0.04297419318878546, + "grad_norm": 0.4863613247871399, + "learning_rate": 9.982421551939003e-05, + "loss": 1.8064, + "step": 771 + }, + { + "epoch": 0.04302993144194861, + "grad_norm": 0.4646783769130707, + "learning_rate": 9.982346873608937e-05, + "loss": 1.6427, + "step": 772 + }, + { + "epoch": 0.04308566969511175, + "grad_norm": 0.5143455266952515, + "learning_rate": 9.982272037267877e-05, + "loss": 1.7367, + "step": 773 + }, + { + "epoch": 0.0431414079482749, + "grad_norm": 0.4936600923538208, + "learning_rate": 9.982197042918195e-05, + "loss": 1.6834, + "step": 774 + }, + { + "epoch": 0.043197146201438046, + "grad_norm": 0.4923505485057831, + "learning_rate": 9.982121890562273e-05, + "loss": 1.7545, + "step": 775 + }, + { + "epoch": 0.043252884454601195, + "grad_norm": 0.5399130582809448, + "learning_rate": 9.982046580202493e-05, + "loss": 1.784, + "step": 776 + }, + { + "epoch": 0.04330862270776434, + "grad_norm": 0.49087220430374146, + "learning_rate": 9.98197111184124e-05, + "loss": 1.8328, + "step": 777 + }, + { + "epoch": 0.04336436096092749, + "grad_norm": 0.5504277348518372, + "learning_rate": 9.981895485480912e-05, + "loss": 1.8808, + "step": 778 + }, + { + "epoch": 0.04342009921409063, + "grad_norm": 0.45953568816185, + "learning_rate": 9.981819701123907e-05, + "loss": 1.577, + "step": 779 + }, + { + "epoch": 0.043475837467253774, + "grad_norm": 0.4762939214706421, + "learning_rate": 9.981743758772625e-05, + "loss": 1.6959, + "step": 780 + }, + { + "epoch": 0.043531575720416923, + "grad_norm": 0.4667057991027832, + "learning_rate": 9.981667658429477e-05, + "loss": 1.6635, + "step": 781 + }, + { + "epoch": 0.043587313973580066, + "grad_norm": 0.5036124587059021, + "learning_rate": 9.981591400096877e-05, + "loss": 1.854, + "step": 782 + }, + { + "epoch": 0.043643052226743216, + "grad_norm": 0.48234641551971436, + "learning_rate": 9.98151498377724e-05, + "loss": 1.781, + "step": 783 + }, + { + "epoch": 0.04369879047990636, + "grad_norm": 0.4990682005882263, + "learning_rate": 9.981438409472994e-05, + "loss": 1.6629, + "step": 784 + }, + { + "epoch": 0.04375452873306951, + "grad_norm": 0.4655357599258423, + "learning_rate": 9.981361677186566e-05, + "loss": 1.7694, + "step": 785 + }, + { + "epoch": 0.04381026698623265, + "grad_norm": 0.4690426290035248, + "learning_rate": 9.981284786920388e-05, + "loss": 1.7242, + "step": 786 + }, + { + "epoch": 0.043866005239395794, + "grad_norm": 0.46350887417793274, + "learning_rate": 9.981207738676899e-05, + "loss": 1.6032, + "step": 787 + }, + { + "epoch": 0.043921743492558944, + "grad_norm": 0.5220307111740112, + "learning_rate": 9.981130532458544e-05, + "loss": 1.8624, + "step": 788 + }, + { + "epoch": 0.04397748174572209, + "grad_norm": 0.465497761964798, + "learning_rate": 9.98105316826777e-05, + "loss": 1.6831, + "step": 789 + }, + { + "epoch": 0.04403321999888524, + "grad_norm": 0.4893016219139099, + "learning_rate": 9.980975646107032e-05, + "loss": 1.7933, + "step": 790 + }, + { + "epoch": 0.04408895825204838, + "grad_norm": 0.4457073509693146, + "learning_rate": 9.980897965978787e-05, + "loss": 1.6383, + "step": 791 + }, + { + "epoch": 0.04414469650521153, + "grad_norm": 0.5064904093742371, + "learning_rate": 9.980820127885497e-05, + "loss": 1.8771, + "step": 792 + }, + { + "epoch": 0.04420043475837467, + "grad_norm": 0.5663847327232361, + "learning_rate": 9.980742131829635e-05, + "loss": 2.0977, + "step": 793 + }, + { + "epoch": 0.044256173011537815, + "grad_norm": 0.558462381362915, + "learning_rate": 9.980663977813672e-05, + "loss": 1.9813, + "step": 794 + }, + { + "epoch": 0.044311911264700965, + "grad_norm": 0.5043233633041382, + "learning_rate": 9.980585665840087e-05, + "loss": 1.7362, + "step": 795 + }, + { + "epoch": 0.04436764951786411, + "grad_norm": 0.5110850930213928, + "learning_rate": 9.980507195911363e-05, + "loss": 1.5489, + "step": 796 + }, + { + "epoch": 0.04442338777102726, + "grad_norm": 0.5611404180526733, + "learning_rate": 9.980428568029989e-05, + "loss": 1.9545, + "step": 797 + }, + { + "epoch": 0.0444791260241904, + "grad_norm": 0.44059324264526367, + "learning_rate": 9.98034978219846e-05, + "loss": 1.6321, + "step": 798 + }, + { + "epoch": 0.04453486427735355, + "grad_norm": 0.5034955143928528, + "learning_rate": 9.980270838419273e-05, + "loss": 1.7045, + "step": 799 + }, + { + "epoch": 0.04459060253051669, + "grad_norm": 0.49383604526519775, + "learning_rate": 9.98019173669493e-05, + "loss": 1.6414, + "step": 800 + }, + { + "epoch": 0.04464634078367984, + "grad_norm": 0.5035958290100098, + "learning_rate": 9.980112477027942e-05, + "loss": 1.8683, + "step": 801 + }, + { + "epoch": 0.044702079036842986, + "grad_norm": 0.4942208230495453, + "learning_rate": 9.980033059420826e-05, + "loss": 1.7773, + "step": 802 + }, + { + "epoch": 0.04475781729000613, + "grad_norm": 0.5211103558540344, + "learning_rate": 9.979953483876095e-05, + "loss": 2.0631, + "step": 803 + }, + { + "epoch": 0.04481355554316928, + "grad_norm": 0.5940659046173096, + "learning_rate": 9.979873750396273e-05, + "loss": 2.0601, + "step": 804 + }, + { + "epoch": 0.04486929379633242, + "grad_norm": 0.5211898684501648, + "learning_rate": 9.979793858983891e-05, + "loss": 1.7687, + "step": 805 + }, + { + "epoch": 0.04492503204949557, + "grad_norm": 0.5175243020057678, + "learning_rate": 9.979713809641482e-05, + "loss": 1.9662, + "step": 806 + }, + { + "epoch": 0.044980770302658714, + "grad_norm": 0.5139010548591614, + "learning_rate": 9.979633602371586e-05, + "loss": 1.7011, + "step": 807 + }, + { + "epoch": 0.045036508555821864, + "grad_norm": 0.4817015826702118, + "learning_rate": 9.979553237176744e-05, + "loss": 1.7632, + "step": 808 + }, + { + "epoch": 0.045092246808985006, + "grad_norm": 0.49766993522644043, + "learning_rate": 9.979472714059506e-05, + "loss": 1.917, + "step": 809 + }, + { + "epoch": 0.04514798506214815, + "grad_norm": 0.5208562612533569, + "learning_rate": 9.979392033022427e-05, + "loss": 1.946, + "step": 810 + }, + { + "epoch": 0.0452037233153113, + "grad_norm": 0.4790688753128052, + "learning_rate": 9.979311194068064e-05, + "loss": 1.8072, + "step": 811 + }, + { + "epoch": 0.04525946156847444, + "grad_norm": 0.46075010299682617, + "learning_rate": 9.979230197198981e-05, + "loss": 1.6243, + "step": 812 + }, + { + "epoch": 0.04531519982163759, + "grad_norm": 0.488349974155426, + "learning_rate": 9.979149042417749e-05, + "loss": 1.7733, + "step": 813 + }, + { + "epoch": 0.045370938074800735, + "grad_norm": 0.4905661940574646, + "learning_rate": 9.979067729726938e-05, + "loss": 1.821, + "step": 814 + }, + { + "epoch": 0.045426676327963884, + "grad_norm": 0.5073617696762085, + "learning_rate": 9.978986259129129e-05, + "loss": 1.8286, + "step": 815 + }, + { + "epoch": 0.04548241458112703, + "grad_norm": 0.5074631571769714, + "learning_rate": 9.978904630626904e-05, + "loss": 1.7967, + "step": 816 + }, + { + "epoch": 0.04553815283429017, + "grad_norm": 0.5455936193466187, + "learning_rate": 9.978822844222855e-05, + "loss": 1.9883, + "step": 817 + }, + { + "epoch": 0.04559389108745332, + "grad_norm": 0.5111860632896423, + "learning_rate": 9.978740899919574e-05, + "loss": 1.8694, + "step": 818 + }, + { + "epoch": 0.04564962934061646, + "grad_norm": 0.4975983202457428, + "learning_rate": 9.978658797719658e-05, + "loss": 1.714, + "step": 819 + }, + { + "epoch": 0.04570536759377961, + "grad_norm": 0.4770795702934265, + "learning_rate": 9.978576537625714e-05, + "loss": 1.8288, + "step": 820 + }, + { + "epoch": 0.045761105846942755, + "grad_norm": 0.5559741854667664, + "learning_rate": 9.97849411964035e-05, + "loss": 2.093, + "step": 821 + }, + { + "epoch": 0.045816844100105905, + "grad_norm": 0.4961313307285309, + "learning_rate": 9.978411543766177e-05, + "loss": 1.6607, + "step": 822 + }, + { + "epoch": 0.04587258235326905, + "grad_norm": 0.5356935262680054, + "learning_rate": 9.978328810005816e-05, + "loss": 1.9762, + "step": 823 + }, + { + "epoch": 0.0459283206064322, + "grad_norm": 0.4933258295059204, + "learning_rate": 9.978245918361893e-05, + "loss": 1.6018, + "step": 824 + }, + { + "epoch": 0.04598405885959534, + "grad_norm": 0.5278127193450928, + "learning_rate": 9.978162868837034e-05, + "loss": 1.8532, + "step": 825 + }, + { + "epoch": 0.04603979711275848, + "grad_norm": 0.4802572429180145, + "learning_rate": 9.978079661433873e-05, + "loss": 1.7551, + "step": 826 + }, + { + "epoch": 0.04609553536592163, + "grad_norm": 0.4906105101108551, + "learning_rate": 9.977996296155049e-05, + "loss": 1.7463, + "step": 827 + }, + { + "epoch": 0.046151273619084776, + "grad_norm": 0.43020668625831604, + "learning_rate": 9.977912773003206e-05, + "loss": 1.6216, + "step": 828 + }, + { + "epoch": 0.046207011872247926, + "grad_norm": 0.49433162808418274, + "learning_rate": 9.977829091980995e-05, + "loss": 1.9011, + "step": 829 + }, + { + "epoch": 0.04626275012541107, + "grad_norm": 0.45222243666648865, + "learning_rate": 9.977745253091067e-05, + "loss": 1.3583, + "step": 830 + }, + { + "epoch": 0.04631848837857422, + "grad_norm": 0.4955357015132904, + "learning_rate": 9.977661256336081e-05, + "loss": 1.7256, + "step": 831 + }, + { + "epoch": 0.04637422663173736, + "grad_norm": 0.5137125253677368, + "learning_rate": 9.977577101718701e-05, + "loss": 1.8484, + "step": 832 + }, + { + "epoch": 0.046429964884900504, + "grad_norm": 0.49741753935813904, + "learning_rate": 9.977492789241598e-05, + "loss": 1.6564, + "step": 833 + }, + { + "epoch": 0.046485703138063654, + "grad_norm": 0.4994182586669922, + "learning_rate": 9.977408318907444e-05, + "loss": 1.721, + "step": 834 + }, + { + "epoch": 0.0465414413912268, + "grad_norm": 0.539135754108429, + "learning_rate": 9.97732369071892e-05, + "loss": 2.0474, + "step": 835 + }, + { + "epoch": 0.04659717964438995, + "grad_norm": 0.49502313137054443, + "learning_rate": 9.977238904678707e-05, + "loss": 1.4078, + "step": 836 + }, + { + "epoch": 0.04665291789755309, + "grad_norm": 0.4542715549468994, + "learning_rate": 9.977153960789497e-05, + "loss": 1.5402, + "step": 837 + }, + { + "epoch": 0.04670865615071624, + "grad_norm": 0.48588764667510986, + "learning_rate": 9.97706885905398e-05, + "loss": 1.8641, + "step": 838 + }, + { + "epoch": 0.04676439440387938, + "grad_norm": 0.529255211353302, + "learning_rate": 9.976983599474857e-05, + "loss": 1.8055, + "step": 839 + }, + { + "epoch": 0.046820132657042525, + "grad_norm": 0.4630698561668396, + "learning_rate": 9.976898182054832e-05, + "loss": 1.5263, + "step": 840 + }, + { + "epoch": 0.046875870910205675, + "grad_norm": 0.5334575176239014, + "learning_rate": 9.976812606796615e-05, + "loss": 1.7926, + "step": 841 + }, + { + "epoch": 0.04693160916336882, + "grad_norm": 0.49275916814804077, + "learning_rate": 9.976726873702918e-05, + "loss": 1.6341, + "step": 842 + }, + { + "epoch": 0.04698734741653197, + "grad_norm": 0.5276961326599121, + "learning_rate": 9.976640982776461e-05, + "loss": 1.882, + "step": 843 + }, + { + "epoch": 0.04704308566969511, + "grad_norm": 0.49929726123809814, + "learning_rate": 9.97655493401997e-05, + "loss": 1.6004, + "step": 844 + }, + { + "epoch": 0.04709882392285826, + "grad_norm": 0.4716168940067291, + "learning_rate": 9.97646872743617e-05, + "loss": 1.7355, + "step": 845 + }, + { + "epoch": 0.0471545621760214, + "grad_norm": 0.5293796062469482, + "learning_rate": 9.976382363027797e-05, + "loss": 1.9073, + "step": 846 + }, + { + "epoch": 0.04721030042918455, + "grad_norm": 0.47008490562438965, + "learning_rate": 9.976295840797589e-05, + "loss": 1.6875, + "step": 847 + }, + { + "epoch": 0.047266038682347696, + "grad_norm": 0.48457372188568115, + "learning_rate": 9.976209160748292e-05, + "loss": 1.6172, + "step": 848 + }, + { + "epoch": 0.04732177693551084, + "grad_norm": 0.500151515007019, + "learning_rate": 9.976122322882653e-05, + "loss": 1.6371, + "step": 849 + }, + { + "epoch": 0.04737751518867399, + "grad_norm": 0.5459775924682617, + "learning_rate": 9.976035327203427e-05, + "loss": 1.9283, + "step": 850 + }, + { + "epoch": 0.04743325344183713, + "grad_norm": 0.5352368950843811, + "learning_rate": 9.975948173713374e-05, + "loss": 2.0407, + "step": 851 + }, + { + "epoch": 0.04748899169500028, + "grad_norm": 0.5491572618484497, + "learning_rate": 9.975860862415254e-05, + "loss": 1.7475, + "step": 852 + }, + { + "epoch": 0.047544729948163424, + "grad_norm": 0.49011510610580444, + "learning_rate": 9.975773393311841e-05, + "loss": 1.7922, + "step": 853 + }, + { + "epoch": 0.04760046820132657, + "grad_norm": 0.5197030305862427, + "learning_rate": 9.975685766405906e-05, + "loss": 1.7012, + "step": 854 + }, + { + "epoch": 0.047656206454489716, + "grad_norm": 0.487704336643219, + "learning_rate": 9.975597981700228e-05, + "loss": 1.6647, + "step": 855 + }, + { + "epoch": 0.04771194470765286, + "grad_norm": 0.4743403196334839, + "learning_rate": 9.975510039197592e-05, + "loss": 1.5522, + "step": 856 + }, + { + "epoch": 0.04776768296081601, + "grad_norm": 0.46670085191726685, + "learning_rate": 9.975421938900789e-05, + "loss": 1.5235, + "step": 857 + }, + { + "epoch": 0.04782342121397915, + "grad_norm": 0.48920536041259766, + "learning_rate": 9.975333680812609e-05, + "loss": 1.8876, + "step": 858 + }, + { + "epoch": 0.0478791594671423, + "grad_norm": 0.5793198943138123, + "learning_rate": 9.975245264935852e-05, + "loss": 1.8422, + "step": 859 + }, + { + "epoch": 0.047934897720305444, + "grad_norm": 0.49111589789390564, + "learning_rate": 9.975156691273324e-05, + "loss": 1.7702, + "step": 860 + }, + { + "epoch": 0.047990635973468594, + "grad_norm": 0.5276595950126648, + "learning_rate": 9.975067959827833e-05, + "loss": 1.9332, + "step": 861 + }, + { + "epoch": 0.04804637422663174, + "grad_norm": 0.4866962134838104, + "learning_rate": 9.974979070602192e-05, + "loss": 1.7497, + "step": 862 + }, + { + "epoch": 0.04810211247979488, + "grad_norm": 0.5197125673294067, + "learning_rate": 9.974890023599222e-05, + "loss": 2.0405, + "step": 863 + }, + { + "epoch": 0.04815785073295803, + "grad_norm": 0.49782440066337585, + "learning_rate": 9.974800818821746e-05, + "loss": 1.7609, + "step": 864 + }, + { + "epoch": 0.04821358898612117, + "grad_norm": 0.52313232421875, + "learning_rate": 9.974711456272593e-05, + "loss": 1.9515, + "step": 865 + }, + { + "epoch": 0.04826932723928432, + "grad_norm": 0.4546637237071991, + "learning_rate": 9.974621935954597e-05, + "loss": 1.645, + "step": 866 + }, + { + "epoch": 0.048325065492447465, + "grad_norm": 0.47760143876075745, + "learning_rate": 9.974532257870596e-05, + "loss": 1.7104, + "step": 867 + }, + { + "epoch": 0.048380803745610615, + "grad_norm": 0.4868486225605011, + "learning_rate": 9.974442422023438e-05, + "loss": 1.8043, + "step": 868 + }, + { + "epoch": 0.04843654199877376, + "grad_norm": 0.5107572078704834, + "learning_rate": 9.974352428415968e-05, + "loss": 1.9662, + "step": 869 + }, + { + "epoch": 0.04849228025193691, + "grad_norm": 0.5269783139228821, + "learning_rate": 9.974262277051041e-05, + "loss": 1.8876, + "step": 870 + }, + { + "epoch": 0.04854801850510005, + "grad_norm": 0.48782503604888916, + "learning_rate": 9.974171967931519e-05, + "loss": 1.5996, + "step": 871 + }, + { + "epoch": 0.04860375675826319, + "grad_norm": 0.5057775974273682, + "learning_rate": 9.974081501060259e-05, + "loss": 1.6907, + "step": 872 + }, + { + "epoch": 0.04865949501142634, + "grad_norm": 0.4904307723045349, + "learning_rate": 9.973990876440138e-05, + "loss": 1.7377, + "step": 873 + }, + { + "epoch": 0.048715233264589486, + "grad_norm": 0.4725581407546997, + "learning_rate": 9.973900094074027e-05, + "loss": 1.8001, + "step": 874 + }, + { + "epoch": 0.048770971517752636, + "grad_norm": 0.527885913848877, + "learning_rate": 9.973809153964804e-05, + "loss": 1.8128, + "step": 875 + }, + { + "epoch": 0.04882670977091578, + "grad_norm": 0.5520697236061096, + "learning_rate": 9.973718056115354e-05, + "loss": 2.0648, + "step": 876 + }, + { + "epoch": 0.04888244802407893, + "grad_norm": 0.4812840223312378, + "learning_rate": 9.973626800528566e-05, + "loss": 1.8552, + "step": 877 + }, + { + "epoch": 0.04893818627724207, + "grad_norm": 0.46856966614723206, + "learning_rate": 9.973535387207333e-05, + "loss": 1.577, + "step": 878 + }, + { + "epoch": 0.048993924530405214, + "grad_norm": 0.4921995997428894, + "learning_rate": 9.973443816154557e-05, + "loss": 1.66, + "step": 879 + }, + { + "epoch": 0.049049662783568364, + "grad_norm": 0.5018383264541626, + "learning_rate": 9.97335208737314e-05, + "loss": 1.7623, + "step": 880 + }, + { + "epoch": 0.04910540103673151, + "grad_norm": 0.5345847010612488, + "learning_rate": 9.973260200865991e-05, + "loss": 1.8681, + "step": 881 + }, + { + "epoch": 0.049161139289894656, + "grad_norm": 0.5296522974967957, + "learning_rate": 9.973168156636025e-05, + "loss": 1.9225, + "step": 882 + }, + { + "epoch": 0.0492168775430578, + "grad_norm": 0.5303376317024231, + "learning_rate": 9.97307595468616e-05, + "loss": 1.8308, + "step": 883 + }, + { + "epoch": 0.04927261579622095, + "grad_norm": 0.45620301365852356, + "learning_rate": 9.97298359501932e-05, + "loss": 1.5791, + "step": 884 + }, + { + "epoch": 0.04932835404938409, + "grad_norm": 0.5314328074455261, + "learning_rate": 9.972891077638438e-05, + "loss": 1.7279, + "step": 885 + }, + { + "epoch": 0.049384092302547235, + "grad_norm": 0.4765213429927826, + "learning_rate": 9.972798402546441e-05, + "loss": 1.5131, + "step": 886 + }, + { + "epoch": 0.049439830555710385, + "grad_norm": 0.4913032054901123, + "learning_rate": 9.972705569746274e-05, + "loss": 1.6591, + "step": 887 + }, + { + "epoch": 0.04949556880887353, + "grad_norm": 0.48732152581214905, + "learning_rate": 9.972612579240881e-05, + "loss": 1.7141, + "step": 888 + }, + { + "epoch": 0.04955130706203668, + "grad_norm": 0.5283141732215881, + "learning_rate": 9.972519431033206e-05, + "loss": 1.8636, + "step": 889 + }, + { + "epoch": 0.04960704531519982, + "grad_norm": 0.5298954844474792, + "learning_rate": 9.972426125126209e-05, + "loss": 1.7943, + "step": 890 + }, + { + "epoch": 0.04966278356836297, + "grad_norm": 0.5104478597640991, + "learning_rate": 9.972332661522845e-05, + "loss": 1.6949, + "step": 891 + }, + { + "epoch": 0.04971852182152611, + "grad_norm": 0.5439249873161316, + "learning_rate": 9.972239040226082e-05, + "loss": 1.9313, + "step": 892 + }, + { + "epoch": 0.04977426007468926, + "grad_norm": 0.4874706566333771, + "learning_rate": 9.972145261238884e-05, + "loss": 1.8589, + "step": 893 + }, + { + "epoch": 0.049829998327852405, + "grad_norm": 0.5243585705757141, + "learning_rate": 9.972051324564229e-05, + "loss": 1.9736, + "step": 894 + }, + { + "epoch": 0.04988573658101555, + "grad_norm": 0.5669842958450317, + "learning_rate": 9.971957230205096e-05, + "loss": 2.1093, + "step": 895 + }, + { + "epoch": 0.0499414748341787, + "grad_norm": 0.4888775050640106, + "learning_rate": 9.971862978164466e-05, + "loss": 1.6786, + "step": 896 + }, + { + "epoch": 0.04999721308734184, + "grad_norm": 0.5279240608215332, + "learning_rate": 9.971768568445332e-05, + "loss": 1.8162, + "step": 897 + }, + { + "epoch": 0.05005295134050499, + "grad_norm": 0.4473552405834198, + "learning_rate": 9.971674001050686e-05, + "loss": 1.3044, + "step": 898 + }, + { + "epoch": 0.05010868959366813, + "grad_norm": 0.4724571704864502, + "learning_rate": 9.971579275983527e-05, + "loss": 1.7169, + "step": 899 + }, + { + "epoch": 0.05016442784683128, + "grad_norm": 0.4805344343185425, + "learning_rate": 9.971484393246861e-05, + "loss": 1.4898, + "step": 900 + }, + { + "epoch": 0.050220166099994426, + "grad_norm": 0.4852250814437866, + "learning_rate": 9.971389352843695e-05, + "loss": 1.6325, + "step": 901 + }, + { + "epoch": 0.05027590435315757, + "grad_norm": 0.49681854248046875, + "learning_rate": 9.971294154777044e-05, + "loss": 1.5962, + "step": 902 + }, + { + "epoch": 0.05033164260632072, + "grad_norm": 0.5085350871086121, + "learning_rate": 9.971198799049928e-05, + "loss": 1.8215, + "step": 903 + }, + { + "epoch": 0.05038738085948386, + "grad_norm": 0.49748629331588745, + "learning_rate": 9.971103285665369e-05, + "loss": 1.9647, + "step": 904 + }, + { + "epoch": 0.05044311911264701, + "grad_norm": 0.4835662543773651, + "learning_rate": 9.971007614626397e-05, + "loss": 1.6109, + "step": 905 + }, + { + "epoch": 0.050498857365810154, + "grad_norm": 0.5058585405349731, + "learning_rate": 9.970911785936047e-05, + "loss": 1.6419, + "step": 906 + }, + { + "epoch": 0.050554595618973304, + "grad_norm": 0.5386664271354675, + "learning_rate": 9.970815799597358e-05, + "loss": 1.6144, + "step": 907 + }, + { + "epoch": 0.05061033387213645, + "grad_norm": 0.5337561964988708, + "learning_rate": 9.970719655613373e-05, + "loss": 1.7978, + "step": 908 + }, + { + "epoch": 0.05066607212529959, + "grad_norm": 0.532317578792572, + "learning_rate": 9.970623353987141e-05, + "loss": 1.8175, + "step": 909 + }, + { + "epoch": 0.05072181037846274, + "grad_norm": 0.5630917549133301, + "learning_rate": 9.97052689472172e-05, + "loss": 2.043, + "step": 910 + }, + { + "epoch": 0.05077754863162588, + "grad_norm": 0.554322361946106, + "learning_rate": 9.970430277820165e-05, + "loss": 1.9165, + "step": 911 + }, + { + "epoch": 0.05083328688478903, + "grad_norm": 0.49685636162757874, + "learning_rate": 9.970333503285539e-05, + "loss": 1.8203, + "step": 912 + }, + { + "epoch": 0.050889025137952175, + "grad_norm": 0.5380950570106506, + "learning_rate": 9.970236571120915e-05, + "loss": 1.9429, + "step": 913 + }, + { + "epoch": 0.050944763391115325, + "grad_norm": 0.5279613733291626, + "learning_rate": 9.970139481329364e-05, + "loss": 2.0989, + "step": 914 + }, + { + "epoch": 0.05100050164427847, + "grad_norm": 0.509904682636261, + "learning_rate": 9.970042233913968e-05, + "loss": 1.7213, + "step": 915 + }, + { + "epoch": 0.05105623989744162, + "grad_norm": 0.48252367973327637, + "learning_rate": 9.96994482887781e-05, + "loss": 1.6979, + "step": 916 + }, + { + "epoch": 0.05111197815060476, + "grad_norm": 0.5245582461357117, + "learning_rate": 9.969847266223979e-05, + "loss": 1.7629, + "step": 917 + }, + { + "epoch": 0.0511677164037679, + "grad_norm": 0.48625627160072327, + "learning_rate": 9.969749545955567e-05, + "loss": 1.7208, + "step": 918 + }, + { + "epoch": 0.05122345465693105, + "grad_norm": 0.5168225169181824, + "learning_rate": 9.969651668075678e-05, + "loss": 1.952, + "step": 919 + }, + { + "epoch": 0.051279192910094196, + "grad_norm": 0.47759923338890076, + "learning_rate": 9.969553632587409e-05, + "loss": 1.6574, + "step": 920 + }, + { + "epoch": 0.051334931163257345, + "grad_norm": 0.49498680233955383, + "learning_rate": 9.969455439493877e-05, + "loss": 1.6173, + "step": 921 + }, + { + "epoch": 0.05139066941642049, + "grad_norm": 0.48092684149742126, + "learning_rate": 9.96935708879819e-05, + "loss": 1.6471, + "step": 922 + }, + { + "epoch": 0.05144640766958364, + "grad_norm": 0.5342095494270325, + "learning_rate": 9.969258580503471e-05, + "loss": 2.0134, + "step": 923 + }, + { + "epoch": 0.05150214592274678, + "grad_norm": 0.58601975440979, + "learning_rate": 9.969159914612843e-05, + "loss": 2.1658, + "step": 924 + }, + { + "epoch": 0.051557884175909924, + "grad_norm": 0.4867340922355652, + "learning_rate": 9.969061091129433e-05, + "loss": 1.9766, + "step": 925 + }, + { + "epoch": 0.051613622429073074, + "grad_norm": 0.4857270121574402, + "learning_rate": 9.968962110056379e-05, + "loss": 1.678, + "step": 926 + }, + { + "epoch": 0.051669360682236216, + "grad_norm": 0.5170820355415344, + "learning_rate": 9.968862971396816e-05, + "loss": 1.8249, + "step": 927 + }, + { + "epoch": 0.051725098935399366, + "grad_norm": 0.4657866358757019, + "learning_rate": 9.96876367515389e-05, + "loss": 1.7606, + "step": 928 + }, + { + "epoch": 0.05178083718856251, + "grad_norm": 0.5119996666908264, + "learning_rate": 9.968664221330751e-05, + "loss": 1.8612, + "step": 929 + }, + { + "epoch": 0.05183657544172566, + "grad_norm": 0.5372640490531921, + "learning_rate": 9.968564609930553e-05, + "loss": 1.8672, + "step": 930 + }, + { + "epoch": 0.0518923136948888, + "grad_norm": 0.49778059124946594, + "learning_rate": 9.968464840956453e-05, + "loss": 1.766, + "step": 931 + }, + { + "epoch": 0.05194805194805195, + "grad_norm": 0.5260003805160522, + "learning_rate": 9.968364914411616e-05, + "loss": 1.8631, + "step": 932 + }, + { + "epoch": 0.052003790201215094, + "grad_norm": 0.5278846621513367, + "learning_rate": 9.968264830299213e-05, + "loss": 1.5441, + "step": 933 + }, + { + "epoch": 0.05205952845437824, + "grad_norm": 0.5427425503730774, + "learning_rate": 9.968164588622415e-05, + "loss": 1.7751, + "step": 934 + }, + { + "epoch": 0.05211526670754139, + "grad_norm": 0.4653323292732239, + "learning_rate": 9.968064189384403e-05, + "loss": 1.662, + "step": 935 + }, + { + "epoch": 0.05217100496070453, + "grad_norm": 0.5192728638648987, + "learning_rate": 9.967963632588362e-05, + "loss": 1.7384, + "step": 936 + }, + { + "epoch": 0.05222674321386768, + "grad_norm": 0.4995409846305847, + "learning_rate": 9.96786291823748e-05, + "loss": 1.8133, + "step": 937 + }, + { + "epoch": 0.05228248146703082, + "grad_norm": 0.5626217722892761, + "learning_rate": 9.96776204633495e-05, + "loss": 1.8851, + "step": 938 + }, + { + "epoch": 0.05233821972019397, + "grad_norm": 0.5185354351997375, + "learning_rate": 9.967661016883972e-05, + "loss": 1.6583, + "step": 939 + }, + { + "epoch": 0.052393957973357115, + "grad_norm": 0.5034851431846619, + "learning_rate": 9.967559829887749e-05, + "loss": 1.6385, + "step": 940 + }, + { + "epoch": 0.05244969622652026, + "grad_norm": 0.4795439541339874, + "learning_rate": 9.967458485349492e-05, + "loss": 1.6901, + "step": 941 + }, + { + "epoch": 0.05250543447968341, + "grad_norm": 0.6365668177604675, + "learning_rate": 9.967356983272414e-05, + "loss": 1.9757, + "step": 942 + }, + { + "epoch": 0.05256117273284655, + "grad_norm": 0.48566654324531555, + "learning_rate": 9.967255323659734e-05, + "loss": 1.6266, + "step": 943 + }, + { + "epoch": 0.0526169109860097, + "grad_norm": 0.4971524775028229, + "learning_rate": 9.967153506514677e-05, + "loss": 1.6938, + "step": 944 + }, + { + "epoch": 0.05267264923917284, + "grad_norm": 0.5263299345970154, + "learning_rate": 9.967051531840471e-05, + "loss": 1.8448, + "step": 945 + }, + { + "epoch": 0.05272838749233599, + "grad_norm": 0.4903882145881653, + "learning_rate": 9.96694939964035e-05, + "loss": 1.5313, + "step": 946 + }, + { + "epoch": 0.052784125745499136, + "grad_norm": 0.5515956878662109, + "learning_rate": 9.966847109917555e-05, + "loss": 1.9398, + "step": 947 + }, + { + "epoch": 0.05283986399866228, + "grad_norm": 0.47069814801216125, + "learning_rate": 9.966744662675326e-05, + "loss": 1.8052, + "step": 948 + }, + { + "epoch": 0.05289560225182543, + "grad_norm": 0.4904758036136627, + "learning_rate": 9.966642057916915e-05, + "loss": 1.7875, + "step": 949 + }, + { + "epoch": 0.05295134050498857, + "grad_norm": 0.5010367035865784, + "learning_rate": 9.966539295645576e-05, + "loss": 1.6786, + "step": 950 + }, + { + "epoch": 0.05300707875815172, + "grad_norm": 0.4812747538089752, + "learning_rate": 9.966436375864567e-05, + "loss": 1.473, + "step": 951 + }, + { + "epoch": 0.053062817011314864, + "grad_norm": 0.5010087490081787, + "learning_rate": 9.966333298577154e-05, + "loss": 1.7648, + "step": 952 + }, + { + "epoch": 0.053118555264478014, + "grad_norm": 0.5247920155525208, + "learning_rate": 9.966230063786602e-05, + "loss": 1.6435, + "step": 953 + }, + { + "epoch": 0.05317429351764116, + "grad_norm": 0.5183125734329224, + "learning_rate": 9.96612667149619e-05, + "loss": 1.762, + "step": 954 + }, + { + "epoch": 0.053230031770804306, + "grad_norm": 0.5197505950927734, + "learning_rate": 9.966023121709192e-05, + "loss": 1.8957, + "step": 955 + }, + { + "epoch": 0.05328577002396745, + "grad_norm": 0.4871842563152313, + "learning_rate": 9.965919414428896e-05, + "loss": 1.8783, + "step": 956 + }, + { + "epoch": 0.05334150827713059, + "grad_norm": 0.4965290427207947, + "learning_rate": 9.965815549658589e-05, + "loss": 1.8575, + "step": 957 + }, + { + "epoch": 0.05339724653029374, + "grad_norm": 0.5005083680152893, + "learning_rate": 9.965711527401567e-05, + "loss": 1.7704, + "step": 958 + }, + { + "epoch": 0.053452984783456885, + "grad_norm": 0.4561206102371216, + "learning_rate": 9.965607347661125e-05, + "loss": 1.6103, + "step": 959 + }, + { + "epoch": 0.053508723036620034, + "grad_norm": 0.5352826714515686, + "learning_rate": 9.965503010440571e-05, + "loss": 1.9864, + "step": 960 + }, + { + "epoch": 0.05356446128978318, + "grad_norm": 0.4568333327770233, + "learning_rate": 9.965398515743212e-05, + "loss": 1.7264, + "step": 961 + }, + { + "epoch": 0.05362019954294633, + "grad_norm": 0.5570031404495239, + "learning_rate": 9.965293863572363e-05, + "loss": 2.2176, + "step": 962 + }, + { + "epoch": 0.05367593779610947, + "grad_norm": 0.5380359888076782, + "learning_rate": 9.96518905393134e-05, + "loss": 2.0434, + "step": 963 + }, + { + "epoch": 0.05373167604927261, + "grad_norm": 0.46430766582489014, + "learning_rate": 9.965084086823472e-05, + "loss": 1.4151, + "step": 964 + }, + { + "epoch": 0.05378741430243576, + "grad_norm": 0.4653235077857971, + "learning_rate": 9.964978962252085e-05, + "loss": 1.7144, + "step": 965 + }, + { + "epoch": 0.053843152555598905, + "grad_norm": 0.49018028378486633, + "learning_rate": 9.964873680220512e-05, + "loss": 1.6531, + "step": 966 + }, + { + "epoch": 0.053898890808762055, + "grad_norm": 0.5718449354171753, + "learning_rate": 9.964768240732093e-05, + "loss": 1.9851, + "step": 967 + }, + { + "epoch": 0.0539546290619252, + "grad_norm": 0.5048679113388062, + "learning_rate": 9.964662643790173e-05, + "loss": 1.9137, + "step": 968 + }, + { + "epoch": 0.05401036731508835, + "grad_norm": 0.5291681885719299, + "learning_rate": 9.9645568893981e-05, + "loss": 1.8972, + "step": 969 + }, + { + "epoch": 0.05406610556825149, + "grad_norm": 0.5041894316673279, + "learning_rate": 9.964450977559226e-05, + "loss": 1.5612, + "step": 970 + }, + { + "epoch": 0.054121843821414634, + "grad_norm": 0.561788022518158, + "learning_rate": 9.964344908276914e-05, + "loss": 2.0708, + "step": 971 + }, + { + "epoch": 0.05417758207457778, + "grad_norm": 0.4838697016239166, + "learning_rate": 9.964238681554524e-05, + "loss": 1.6573, + "step": 972 + }, + { + "epoch": 0.054233320327740926, + "grad_norm": 0.5092923641204834, + "learning_rate": 9.964132297395428e-05, + "loss": 1.918, + "step": 973 + }, + { + "epoch": 0.054289058580904076, + "grad_norm": 0.5128215551376343, + "learning_rate": 9.964025755802997e-05, + "loss": 1.721, + "step": 974 + }, + { + "epoch": 0.05434479683406722, + "grad_norm": 0.597062885761261, + "learning_rate": 9.963919056780612e-05, + "loss": 1.9453, + "step": 975 + }, + { + "epoch": 0.05440053508723037, + "grad_norm": 0.5623565316200256, + "learning_rate": 9.963812200331656e-05, + "loss": 1.9271, + "step": 976 + }, + { + "epoch": 0.05445627334039351, + "grad_norm": 0.4568030834197998, + "learning_rate": 9.963705186459517e-05, + "loss": 1.5766, + "step": 977 + }, + { + "epoch": 0.05451201159355666, + "grad_norm": 0.4906899631023407, + "learning_rate": 9.963598015167592e-05, + "loss": 1.7721, + "step": 978 + }, + { + "epoch": 0.054567749846719804, + "grad_norm": 0.5041657090187073, + "learning_rate": 9.963490686459277e-05, + "loss": 1.6293, + "step": 979 + }, + { + "epoch": 0.05462348809988295, + "grad_norm": 0.533762514591217, + "learning_rate": 9.963383200337977e-05, + "loss": 1.8723, + "step": 980 + }, + { + "epoch": 0.0546792263530461, + "grad_norm": 0.4968359172344208, + "learning_rate": 9.963275556807098e-05, + "loss": 1.7368, + "step": 981 + }, + { + "epoch": 0.05473496460620924, + "grad_norm": 0.4822302758693695, + "learning_rate": 9.963167755870059e-05, + "loss": 1.4994, + "step": 982 + }, + { + "epoch": 0.05479070285937239, + "grad_norm": 0.5066803097724915, + "learning_rate": 9.963059797530274e-05, + "loss": 1.8058, + "step": 983 + }, + { + "epoch": 0.05484644111253553, + "grad_norm": 0.518132209777832, + "learning_rate": 9.96295168179117e-05, + "loss": 1.7393, + "step": 984 + }, + { + "epoch": 0.05490217936569868, + "grad_norm": 0.5607625842094421, + "learning_rate": 9.962843408656176e-05, + "loss": 2.149, + "step": 985 + }, + { + "epoch": 0.054957917618861825, + "grad_norm": 0.5685406923294067, + "learning_rate": 9.962734978128723e-05, + "loss": 2.1734, + "step": 986 + }, + { + "epoch": 0.05501365587202497, + "grad_norm": 0.5319599509239197, + "learning_rate": 9.962626390212251e-05, + "loss": 1.8782, + "step": 987 + }, + { + "epoch": 0.05506939412518812, + "grad_norm": 0.4679426848888397, + "learning_rate": 9.962517644910204e-05, + "loss": 1.7033, + "step": 988 + }, + { + "epoch": 0.05512513237835126, + "grad_norm": 0.5416939854621887, + "learning_rate": 9.962408742226032e-05, + "loss": 1.969, + "step": 989 + }, + { + "epoch": 0.05518087063151441, + "grad_norm": 0.49005210399627686, + "learning_rate": 9.962299682163186e-05, + "loss": 1.8229, + "step": 990 + }, + { + "epoch": 0.05523660888467755, + "grad_norm": 0.5170348286628723, + "learning_rate": 9.962190464725128e-05, + "loss": 1.8161, + "step": 991 + }, + { + "epoch": 0.0552923471378407, + "grad_norm": 0.5188906192779541, + "learning_rate": 9.962081089915319e-05, + "loss": 1.938, + "step": 992 + }, + { + "epoch": 0.055348085391003846, + "grad_norm": 0.4945777952671051, + "learning_rate": 9.961971557737227e-05, + "loss": 1.7414, + "step": 993 + }, + { + "epoch": 0.05540382364416699, + "grad_norm": 0.511976420879364, + "learning_rate": 9.96186186819433e-05, + "loss": 1.8595, + "step": 994 + }, + { + "epoch": 0.05545956189733014, + "grad_norm": 0.5381083488464355, + "learning_rate": 9.961752021290103e-05, + "loss": 1.8233, + "step": 995 + }, + { + "epoch": 0.05551530015049328, + "grad_norm": 0.4679305851459503, + "learning_rate": 9.961642017028033e-05, + "loss": 1.6666, + "step": 996 + }, + { + "epoch": 0.05557103840365643, + "grad_norm": 0.5513458847999573, + "learning_rate": 9.961531855411603e-05, + "loss": 2.0589, + "step": 997 + }, + { + "epoch": 0.055626776656819574, + "grad_norm": 0.5168341994285583, + "learning_rate": 9.961421536444313e-05, + "loss": 2.0774, + "step": 998 + }, + { + "epoch": 0.055682514909982724, + "grad_norm": 0.5111126899719238, + "learning_rate": 9.961311060129659e-05, + "loss": 1.5936, + "step": 999 + }, + { + "epoch": 0.055738253163145866, + "grad_norm": 0.5352098941802979, + "learning_rate": 9.961200426471142e-05, + "loss": 1.8414, + "step": 1000 + }, + { + "epoch": 0.055793991416309016, + "grad_norm": 0.47616758942604065, + "learning_rate": 9.961089635472276e-05, + "loss": 1.6496, + "step": 1001 + }, + { + "epoch": 0.05584972966947216, + "grad_norm": 0.4767918288707733, + "learning_rate": 9.96097868713657e-05, + "loss": 1.3193, + "step": 1002 + }, + { + "epoch": 0.0559054679226353, + "grad_norm": 0.46608811616897583, + "learning_rate": 9.960867581467546e-05, + "loss": 1.6453, + "step": 1003 + }, + { + "epoch": 0.05596120617579845, + "grad_norm": 0.5042111277580261, + "learning_rate": 9.960756318468726e-05, + "loss": 1.8798, + "step": 1004 + }, + { + "epoch": 0.056016944428961594, + "grad_norm": 0.5502855777740479, + "learning_rate": 9.960644898143639e-05, + "loss": 1.9322, + "step": 1005 + }, + { + "epoch": 0.056072682682124744, + "grad_norm": 0.4749864935874939, + "learning_rate": 9.960533320495818e-05, + "loss": 1.5659, + "step": 1006 + }, + { + "epoch": 0.05612842093528789, + "grad_norm": 0.4787498712539673, + "learning_rate": 9.960421585528802e-05, + "loss": 1.8482, + "step": 1007 + }, + { + "epoch": 0.05618415918845104, + "grad_norm": 0.578971266746521, + "learning_rate": 9.960309693246135e-05, + "loss": 1.9905, + "step": 1008 + }, + { + "epoch": 0.05623989744161418, + "grad_norm": 0.4983009099960327, + "learning_rate": 9.960197643651363e-05, + "loss": 1.722, + "step": 1009 + }, + { + "epoch": 0.05629563569477732, + "grad_norm": 0.5528213977813721, + "learning_rate": 9.960085436748044e-05, + "loss": 1.8293, + "step": 1010 + }, + { + "epoch": 0.05635137394794047, + "grad_norm": 0.49824774265289307, + "learning_rate": 9.959973072539734e-05, + "loss": 1.8081, + "step": 1011 + }, + { + "epoch": 0.056407112201103615, + "grad_norm": 0.49810606241226196, + "learning_rate": 9.959860551029996e-05, + "loss": 1.5834, + "step": 1012 + }, + { + "epoch": 0.056462850454266765, + "grad_norm": 0.515215277671814, + "learning_rate": 9.9597478722224e-05, + "loss": 1.8318, + "step": 1013 + }, + { + "epoch": 0.05651858870742991, + "grad_norm": 0.5139912962913513, + "learning_rate": 9.959635036120518e-05, + "loss": 1.7475, + "step": 1014 + }, + { + "epoch": 0.05657432696059306, + "grad_norm": 0.4912470579147339, + "learning_rate": 9.959522042727932e-05, + "loss": 1.6809, + "step": 1015 + }, + { + "epoch": 0.0566300652137562, + "grad_norm": 0.4990215003490448, + "learning_rate": 9.959408892048219e-05, + "loss": 1.7024, + "step": 1016 + }, + { + "epoch": 0.05668580346691934, + "grad_norm": 0.5626692771911621, + "learning_rate": 9.959295584084974e-05, + "loss": 1.9791, + "step": 1017 + }, + { + "epoch": 0.05674154172008249, + "grad_norm": 0.4737264811992645, + "learning_rate": 9.959182118841786e-05, + "loss": 1.5592, + "step": 1018 + }, + { + "epoch": 0.056797279973245636, + "grad_norm": 0.5367196798324585, + "learning_rate": 9.959068496322256e-05, + "loss": 2.012, + "step": 1019 + }, + { + "epoch": 0.056853018226408786, + "grad_norm": 0.5062724947929382, + "learning_rate": 9.958954716529987e-05, + "loss": 1.6301, + "step": 1020 + }, + { + "epoch": 0.05690875647957193, + "grad_norm": 0.5419873595237732, + "learning_rate": 9.958840779468586e-05, + "loss": 1.8351, + "step": 1021 + }, + { + "epoch": 0.05696449473273508, + "grad_norm": 0.5291727781295776, + "learning_rate": 9.958726685141668e-05, + "loss": 1.8221, + "step": 1022 + }, + { + "epoch": 0.05702023298589822, + "grad_norm": 0.5285983085632324, + "learning_rate": 9.958612433552852e-05, + "loss": 1.8575, + "step": 1023 + }, + { + "epoch": 0.05707597123906137, + "grad_norm": 0.49050652980804443, + "learning_rate": 9.95849802470576e-05, + "loss": 1.7646, + "step": 1024 + }, + { + "epoch": 0.057131709492224514, + "grad_norm": 0.49379006028175354, + "learning_rate": 9.95838345860402e-05, + "loss": 1.6789, + "step": 1025 + }, + { + "epoch": 0.05718744774538766, + "grad_norm": 0.4859938621520996, + "learning_rate": 9.958268735251266e-05, + "loss": 1.8542, + "step": 1026 + }, + { + "epoch": 0.057243185998550807, + "grad_norm": 0.5445101857185364, + "learning_rate": 9.958153854651136e-05, + "loss": 1.819, + "step": 1027 + }, + { + "epoch": 0.05729892425171395, + "grad_norm": 0.5075321197509766, + "learning_rate": 9.958038816807276e-05, + "loss": 1.7872, + "step": 1028 + }, + { + "epoch": 0.0573546625048771, + "grad_norm": 0.4982723593711853, + "learning_rate": 9.957923621723329e-05, + "loss": 1.8243, + "step": 1029 + }, + { + "epoch": 0.05741040075804024, + "grad_norm": 0.49452096223831177, + "learning_rate": 9.957808269402954e-05, + "loss": 1.7316, + "step": 1030 + }, + { + "epoch": 0.05746613901120339, + "grad_norm": 0.5450426936149597, + "learning_rate": 9.957692759849806e-05, + "loss": 2.0758, + "step": 1031 + }, + { + "epoch": 0.057521877264366535, + "grad_norm": 0.5058251023292542, + "learning_rate": 9.957577093067548e-05, + "loss": 1.6588, + "step": 1032 + }, + { + "epoch": 0.05757761551752968, + "grad_norm": 0.4902496039867401, + "learning_rate": 9.957461269059851e-05, + "loss": 1.8477, + "step": 1033 + }, + { + "epoch": 0.05763335377069283, + "grad_norm": 0.5185796618461609, + "learning_rate": 9.957345287830386e-05, + "loss": 1.7541, + "step": 1034 + }, + { + "epoch": 0.05768909202385597, + "grad_norm": 0.5609437227249146, + "learning_rate": 9.95722914938283e-05, + "loss": 1.8738, + "step": 1035 + }, + { + "epoch": 0.05774483027701912, + "grad_norm": 0.47249266505241394, + "learning_rate": 9.957112853720871e-05, + "loss": 1.6668, + "step": 1036 + }, + { + "epoch": 0.05780056853018226, + "grad_norm": 0.4762544333934784, + "learning_rate": 9.956996400848191e-05, + "loss": 1.5023, + "step": 1037 + }, + { + "epoch": 0.05785630678334541, + "grad_norm": 0.5092499852180481, + "learning_rate": 9.956879790768489e-05, + "loss": 1.7614, + "step": 1038 + }, + { + "epoch": 0.057912045036508555, + "grad_norm": 0.4864351451396942, + "learning_rate": 9.95676302348546e-05, + "loss": 1.7874, + "step": 1039 + }, + { + "epoch": 0.0579677832896717, + "grad_norm": 0.5312706828117371, + "learning_rate": 9.956646099002807e-05, + "loss": 1.7864, + "step": 1040 + }, + { + "epoch": 0.05802352154283485, + "grad_norm": 0.5099919438362122, + "learning_rate": 9.95652901732424e-05, + "loss": 1.9396, + "step": 1041 + }, + { + "epoch": 0.05807925979599799, + "grad_norm": 0.4992043375968933, + "learning_rate": 9.95641177845347e-05, + "loss": 1.8373, + "step": 1042 + }, + { + "epoch": 0.05813499804916114, + "grad_norm": 0.557106614112854, + "learning_rate": 9.956294382394218e-05, + "loss": 2.0565, + "step": 1043 + }, + { + "epoch": 0.058190736302324284, + "grad_norm": 0.5183643102645874, + "learning_rate": 9.956176829150204e-05, + "loss": 1.837, + "step": 1044 + }, + { + "epoch": 0.05824647455548743, + "grad_norm": 0.4911157488822937, + "learning_rate": 9.956059118725158e-05, + "loss": 1.736, + "step": 1045 + }, + { + "epoch": 0.058302212808650576, + "grad_norm": 0.524387538433075, + "learning_rate": 9.955941251122812e-05, + "loss": 1.9561, + "step": 1046 + }, + { + "epoch": 0.058357951061813726, + "grad_norm": 0.4891200065612793, + "learning_rate": 9.955823226346905e-05, + "loss": 1.723, + "step": 1047 + }, + { + "epoch": 0.05841368931497687, + "grad_norm": 0.5014610886573792, + "learning_rate": 9.95570504440118e-05, + "loss": 1.6632, + "step": 1048 + }, + { + "epoch": 0.05846942756814001, + "grad_norm": 0.46674925088882446, + "learning_rate": 9.955586705289386e-05, + "loss": 1.5877, + "step": 1049 + }, + { + "epoch": 0.05852516582130316, + "grad_norm": 0.5613251328468323, + "learning_rate": 9.955468209015273e-05, + "loss": 2.0043, + "step": 1050 + }, + { + "epoch": 0.058580904074466304, + "grad_norm": 0.49603840708732605, + "learning_rate": 9.9553495555826e-05, + "loss": 1.7604, + "step": 1051 + }, + { + "epoch": 0.058636642327629454, + "grad_norm": 0.5199983716011047, + "learning_rate": 9.955230744995132e-05, + "loss": 1.8945, + "step": 1052 + }, + { + "epoch": 0.0586923805807926, + "grad_norm": 0.5177999138832092, + "learning_rate": 9.955111777256635e-05, + "loss": 1.9154, + "step": 1053 + }, + { + "epoch": 0.05874811883395575, + "grad_norm": 0.49996909499168396, + "learning_rate": 9.954992652370885e-05, + "loss": 1.6888, + "step": 1054 + }, + { + "epoch": 0.05880385708711889, + "grad_norm": 0.5143979787826538, + "learning_rate": 9.954873370341656e-05, + "loss": 1.7544, + "step": 1055 + }, + { + "epoch": 0.05885959534028203, + "grad_norm": 0.498963862657547, + "learning_rate": 9.954753931172733e-05, + "loss": 1.9448, + "step": 1056 + }, + { + "epoch": 0.05891533359344518, + "grad_norm": 0.5648823976516724, + "learning_rate": 9.954634334867902e-05, + "loss": 2.0281, + "step": 1057 + }, + { + "epoch": 0.058971071846608325, + "grad_norm": 0.4741098880767822, + "learning_rate": 9.95451458143096e-05, + "loss": 1.7383, + "step": 1058 + }, + { + "epoch": 0.059026810099771475, + "grad_norm": 0.5303511023521423, + "learning_rate": 9.9543946708657e-05, + "loss": 1.9047, + "step": 1059 + }, + { + "epoch": 0.05908254835293462, + "grad_norm": 0.6070243716239929, + "learning_rate": 9.95427460317593e-05, + "loss": 2.1998, + "step": 1060 + }, + { + "epoch": 0.05913828660609777, + "grad_norm": 0.509857177734375, + "learning_rate": 9.954154378365453e-05, + "loss": 1.9788, + "step": 1061 + }, + { + "epoch": 0.05919402485926091, + "grad_norm": 0.4909118711948395, + "learning_rate": 9.954033996438084e-05, + "loss": 1.7906, + "step": 1062 + }, + { + "epoch": 0.05924976311242406, + "grad_norm": 0.5275348424911499, + "learning_rate": 9.95391345739764e-05, + "loss": 1.9644, + "step": 1063 + }, + { + "epoch": 0.0593055013655872, + "grad_norm": 0.5134482979774475, + "learning_rate": 9.953792761247946e-05, + "loss": 1.7528, + "step": 1064 + }, + { + "epoch": 0.059361239618750346, + "grad_norm": 0.4846155345439911, + "learning_rate": 9.953671907992827e-05, + "loss": 1.7198, + "step": 1065 + }, + { + "epoch": 0.059416977871913496, + "grad_norm": 0.508575975894928, + "learning_rate": 9.953550897636117e-05, + "loss": 1.8502, + "step": 1066 + }, + { + "epoch": 0.05947271612507664, + "grad_norm": 0.6168702244758606, + "learning_rate": 9.953429730181653e-05, + "loss": 1.8859, + "step": 1067 + }, + { + "epoch": 0.05952845437823979, + "grad_norm": 0.5224670767784119, + "learning_rate": 9.953308405633281e-05, + "loss": 1.9667, + "step": 1068 + }, + { + "epoch": 0.05958419263140293, + "grad_norm": 0.5521063208580017, + "learning_rate": 9.953186923994845e-05, + "loss": 1.9502, + "step": 1069 + }, + { + "epoch": 0.05963993088456608, + "grad_norm": 0.5243295431137085, + "learning_rate": 9.953065285270198e-05, + "loss": 1.7872, + "step": 1070 + }, + { + "epoch": 0.059695669137729224, + "grad_norm": 0.457383394241333, + "learning_rate": 9.952943489463199e-05, + "loss": 1.4861, + "step": 1071 + }, + { + "epoch": 0.059751407390892367, + "grad_norm": 0.5042887330055237, + "learning_rate": 9.95282153657771e-05, + "loss": 1.8046, + "step": 1072 + }, + { + "epoch": 0.059807145644055516, + "grad_norm": 0.5393437147140503, + "learning_rate": 9.9526994266176e-05, + "loss": 2.0209, + "step": 1073 + }, + { + "epoch": 0.05986288389721866, + "grad_norm": 0.5133099555969238, + "learning_rate": 9.952577159586739e-05, + "loss": 2.0277, + "step": 1074 + }, + { + "epoch": 0.05991862215038181, + "grad_norm": 0.538661539554596, + "learning_rate": 9.952454735489007e-05, + "loss": 1.9108, + "step": 1075 + }, + { + "epoch": 0.05997436040354495, + "grad_norm": 0.5276675224304199, + "learning_rate": 9.952332154328286e-05, + "loss": 2.0656, + "step": 1076 + }, + { + "epoch": 0.0600300986567081, + "grad_norm": 0.5048499703407288, + "learning_rate": 9.952209416108461e-05, + "loss": 1.757, + "step": 1077 + }, + { + "epoch": 0.060085836909871244, + "grad_norm": 0.5175162553787231, + "learning_rate": 9.952086520833428e-05, + "loss": 1.7967, + "step": 1078 + }, + { + "epoch": 0.06014157516303439, + "grad_norm": 0.5084596276283264, + "learning_rate": 9.951963468507084e-05, + "loss": 1.705, + "step": 1079 + }, + { + "epoch": 0.06019731341619754, + "grad_norm": 0.45831501483917236, + "learning_rate": 9.95184025913333e-05, + "loss": 1.6394, + "step": 1080 + }, + { + "epoch": 0.06025305166936068, + "grad_norm": 0.47496846318244934, + "learning_rate": 9.951716892716074e-05, + "loss": 1.5622, + "step": 1081 + }, + { + "epoch": 0.06030878992252383, + "grad_norm": 0.5142143964767456, + "learning_rate": 9.951593369259229e-05, + "loss": 1.943, + "step": 1082 + }, + { + "epoch": 0.06036452817568697, + "grad_norm": 0.4750124216079712, + "learning_rate": 9.951469688766712e-05, + "loss": 1.7855, + "step": 1083 + }, + { + "epoch": 0.06042026642885012, + "grad_norm": 0.5169959664344788, + "learning_rate": 9.951345851242445e-05, + "loss": 1.8589, + "step": 1084 + }, + { + "epoch": 0.060476004682013265, + "grad_norm": 0.4891696572303772, + "learning_rate": 9.951221856690355e-05, + "loss": 1.8431, + "step": 1085 + }, + { + "epoch": 0.060531742935176415, + "grad_norm": 0.49664726853370667, + "learning_rate": 9.951097705114378e-05, + "loss": 1.8495, + "step": 1086 + }, + { + "epoch": 0.06058748118833956, + "grad_norm": 0.4737338423728943, + "learning_rate": 9.950973396518449e-05, + "loss": 1.6244, + "step": 1087 + }, + { + "epoch": 0.0606432194415027, + "grad_norm": 0.4466894865036011, + "learning_rate": 9.950848930906506e-05, + "loss": 1.569, + "step": 1088 + }, + { + "epoch": 0.06069895769466585, + "grad_norm": 0.5531814694404602, + "learning_rate": 9.950724308282504e-05, + "loss": 1.8739, + "step": 1089 + }, + { + "epoch": 0.06075469594782899, + "grad_norm": 0.5358182191848755, + "learning_rate": 9.95059952865039e-05, + "loss": 1.5985, + "step": 1090 + }, + { + "epoch": 0.06081043420099214, + "grad_norm": 0.5551037788391113, + "learning_rate": 9.950474592014123e-05, + "loss": 1.9313, + "step": 1091 + }, + { + "epoch": 0.060866172454155286, + "grad_norm": 0.46842116117477417, + "learning_rate": 9.950349498377666e-05, + "loss": 1.5846, + "step": 1092 + }, + { + "epoch": 0.060921910707318436, + "grad_norm": 0.5490810871124268, + "learning_rate": 9.950224247744986e-05, + "loss": 1.7246, + "step": 1093 + }, + { + "epoch": 0.06097764896048158, + "grad_norm": 0.46604838967323303, + "learning_rate": 9.950098840120055e-05, + "loss": 1.3499, + "step": 1094 + }, + { + "epoch": 0.06103338721364472, + "grad_norm": 0.4957679808139801, + "learning_rate": 9.949973275506847e-05, + "loss": 1.7099, + "step": 1095 + }, + { + "epoch": 0.06108912546680787, + "grad_norm": 0.5058358907699585, + "learning_rate": 9.94984755390935e-05, + "loss": 2.0376, + "step": 1096 + }, + { + "epoch": 0.061144863719971014, + "grad_norm": 0.5344205498695374, + "learning_rate": 9.949721675331546e-05, + "loss": 1.8721, + "step": 1097 + }, + { + "epoch": 0.061200601973134164, + "grad_norm": 0.5005959272384644, + "learning_rate": 9.94959563977743e-05, + "loss": 1.8502, + "step": 1098 + }, + { + "epoch": 0.06125634022629731, + "grad_norm": 0.5033101439476013, + "learning_rate": 9.949469447250998e-05, + "loss": 1.762, + "step": 1099 + }, + { + "epoch": 0.061312078479460456, + "grad_norm": 0.489114373922348, + "learning_rate": 9.949343097756253e-05, + "loss": 1.779, + "step": 1100 + }, + { + "epoch": 0.0613678167326236, + "grad_norm": 0.49902451038360596, + "learning_rate": 9.949216591297203e-05, + "loss": 1.6705, + "step": 1101 + }, + { + "epoch": 0.06142355498578674, + "grad_norm": 0.5019201636314392, + "learning_rate": 9.949089927877858e-05, + "loss": 1.6734, + "step": 1102 + }, + { + "epoch": 0.06147929323894989, + "grad_norm": 0.5644415020942688, + "learning_rate": 9.948963107502235e-05, + "loss": 2.0193, + "step": 1103 + }, + { + "epoch": 0.061535031492113035, + "grad_norm": 0.55086749792099, + "learning_rate": 9.948836130174358e-05, + "loss": 1.9377, + "step": 1104 + }, + { + "epoch": 0.061590769745276185, + "grad_norm": 0.48262813687324524, + "learning_rate": 9.94870899589825e-05, + "loss": 1.6455, + "step": 1105 + }, + { + "epoch": 0.06164650799843933, + "grad_norm": 0.5041834115982056, + "learning_rate": 9.948581704677949e-05, + "loss": 1.9186, + "step": 1106 + }, + { + "epoch": 0.06170224625160248, + "grad_norm": 0.5112140774726868, + "learning_rate": 9.948454256517486e-05, + "loss": 1.9353, + "step": 1107 + }, + { + "epoch": 0.06175798450476562, + "grad_norm": 0.5558189749717712, + "learning_rate": 9.948326651420907e-05, + "loss": 1.6834, + "step": 1108 + }, + { + "epoch": 0.06181372275792877, + "grad_norm": 0.5652199983596802, + "learning_rate": 9.948198889392255e-05, + "loss": 1.8998, + "step": 1109 + }, + { + "epoch": 0.06186946101109191, + "grad_norm": 0.5617989301681519, + "learning_rate": 9.948070970435587e-05, + "loss": 2.1707, + "step": 1110 + }, + { + "epoch": 0.061925199264255056, + "grad_norm": 0.5738351941108704, + "learning_rate": 9.947942894554956e-05, + "loss": 1.9854, + "step": 1111 + }, + { + "epoch": 0.061980937517418205, + "grad_norm": 0.4870631694793701, + "learning_rate": 9.947814661754425e-05, + "loss": 1.6627, + "step": 1112 + }, + { + "epoch": 0.06203667577058135, + "grad_norm": 0.5056869387626648, + "learning_rate": 9.947686272038059e-05, + "loss": 2.0686, + "step": 1113 + }, + { + "epoch": 0.0620924140237445, + "grad_norm": 0.47897595167160034, + "learning_rate": 9.947557725409934e-05, + "loss": 1.7178, + "step": 1114 + }, + { + "epoch": 0.06214815227690764, + "grad_norm": 0.5754001140594482, + "learning_rate": 9.947429021874123e-05, + "loss": 1.9185, + "step": 1115 + }, + { + "epoch": 0.06220389053007079, + "grad_norm": 0.5134566426277161, + "learning_rate": 9.94730016143471e-05, + "loss": 1.7684, + "step": 1116 + }, + { + "epoch": 0.06225962878323393, + "grad_norm": 0.5307061076164246, + "learning_rate": 9.947171144095779e-05, + "loss": 1.8471, + "step": 1117 + }, + { + "epoch": 0.062315367036397076, + "grad_norm": 0.5750778913497925, + "learning_rate": 9.947041969861424e-05, + "loss": 2.0452, + "step": 1118 + }, + { + "epoch": 0.062371105289560226, + "grad_norm": 0.4882142245769501, + "learning_rate": 9.946912638735741e-05, + "loss": 1.6376, + "step": 1119 + }, + { + "epoch": 0.06242684354272337, + "grad_norm": 0.5403459668159485, + "learning_rate": 9.946783150722832e-05, + "loss": 1.7909, + "step": 1120 + }, + { + "epoch": 0.06248258179588652, + "grad_norm": 0.6261606812477112, + "learning_rate": 9.946653505826802e-05, + "loss": 2.3971, + "step": 1121 + }, + { + "epoch": 0.06253832004904966, + "grad_norm": 0.5000771880149841, + "learning_rate": 9.946523704051765e-05, + "loss": 1.6772, + "step": 1122 + }, + { + "epoch": 0.0625940583022128, + "grad_norm": 0.5789170265197754, + "learning_rate": 9.946393745401836e-05, + "loss": 1.5496, + "step": 1123 + }, + { + "epoch": 0.06264979655537596, + "grad_norm": 0.5486829280853271, + "learning_rate": 9.946263629881137e-05, + "loss": 1.926, + "step": 1124 + }, + { + "epoch": 0.0627055348085391, + "grad_norm": 0.4877256751060486, + "learning_rate": 9.946133357493794e-05, + "loss": 1.8916, + "step": 1125 + }, + { + "epoch": 0.06276127306170225, + "grad_norm": 0.505279541015625, + "learning_rate": 9.946002928243939e-05, + "loss": 1.7043, + "step": 1126 + }, + { + "epoch": 0.06281701131486539, + "grad_norm": 0.5650628805160522, + "learning_rate": 9.945872342135709e-05, + "loss": 2.0595, + "step": 1127 + }, + { + "epoch": 0.06287274956802853, + "grad_norm": 0.5424087047576904, + "learning_rate": 9.945741599173244e-05, + "loss": 1.7227, + "step": 1128 + }, + { + "epoch": 0.06292848782119169, + "grad_norm": 0.5090418457984924, + "learning_rate": 9.945610699360692e-05, + "loss": 1.7466, + "step": 1129 + }, + { + "epoch": 0.06298422607435483, + "grad_norm": 0.5532562732696533, + "learning_rate": 9.945479642702203e-05, + "loss": 1.9668, + "step": 1130 + }, + { + "epoch": 0.06303996432751797, + "grad_norm": 0.4829805791378021, + "learning_rate": 9.945348429201933e-05, + "loss": 1.664, + "step": 1131 + }, + { + "epoch": 0.06309570258068112, + "grad_norm": 0.5276423096656799, + "learning_rate": 9.945217058864045e-05, + "loss": 1.7043, + "step": 1132 + }, + { + "epoch": 0.06315144083384426, + "grad_norm": 0.49455907940864563, + "learning_rate": 9.945085531692704e-05, + "loss": 1.6095, + "step": 1133 + }, + { + "epoch": 0.06320717908700742, + "grad_norm": 0.49773842096328735, + "learning_rate": 9.944953847692082e-05, + "loss": 1.6696, + "step": 1134 + }, + { + "epoch": 0.06326291734017056, + "grad_norm": 0.5351307988166809, + "learning_rate": 9.944822006866356e-05, + "loss": 1.8795, + "step": 1135 + }, + { + "epoch": 0.0633186555933337, + "grad_norm": 0.5688774585723877, + "learning_rate": 9.944690009219705e-05, + "loss": 1.6658, + "step": 1136 + }, + { + "epoch": 0.06337439384649685, + "grad_norm": 0.5083485841751099, + "learning_rate": 9.944557854756316e-05, + "loss": 1.5768, + "step": 1137 + }, + { + "epoch": 0.06343013209966, + "grad_norm": 0.5670489072799683, + "learning_rate": 9.944425543480382e-05, + "loss": 1.9228, + "step": 1138 + }, + { + "epoch": 0.06348587035282315, + "grad_norm": 0.49227067828178406, + "learning_rate": 9.944293075396098e-05, + "loss": 1.5889, + "step": 1139 + }, + { + "epoch": 0.06354160860598629, + "grad_norm": 0.5258840918540955, + "learning_rate": 9.944160450507665e-05, + "loss": 1.7821, + "step": 1140 + }, + { + "epoch": 0.06359734685914943, + "grad_norm": 0.5238833427429199, + "learning_rate": 9.944027668819286e-05, + "loss": 1.6987, + "step": 1141 + }, + { + "epoch": 0.06365308511231257, + "grad_norm": 0.45374488830566406, + "learning_rate": 9.943894730335179e-05, + "loss": 1.4687, + "step": 1142 + }, + { + "epoch": 0.06370882336547573, + "grad_norm": 0.496855765581131, + "learning_rate": 9.943761635059554e-05, + "loss": 1.6539, + "step": 1143 + }, + { + "epoch": 0.06376456161863887, + "grad_norm": 0.5250856876373291, + "learning_rate": 9.943628382996634e-05, + "loss": 1.9439, + "step": 1144 + }, + { + "epoch": 0.06382029987180202, + "grad_norm": 0.49122875928878784, + "learning_rate": 9.943494974150644e-05, + "loss": 1.6248, + "step": 1145 + }, + { + "epoch": 0.06387603812496516, + "grad_norm": 0.5038126111030579, + "learning_rate": 9.943361408525818e-05, + "loss": 1.8027, + "step": 1146 + }, + { + "epoch": 0.06393177637812832, + "grad_norm": 0.5918904542922974, + "learning_rate": 9.94322768612639e-05, + "loss": 2.1447, + "step": 1147 + }, + { + "epoch": 0.06398751463129146, + "grad_norm": 0.46479690074920654, + "learning_rate": 9.943093806956601e-05, + "loss": 1.8147, + "step": 1148 + }, + { + "epoch": 0.0640432528844546, + "grad_norm": 0.5129300355911255, + "learning_rate": 9.942959771020694e-05, + "loss": 1.9251, + "step": 1149 + }, + { + "epoch": 0.06409899113761774, + "grad_norm": 0.5755007266998291, + "learning_rate": 9.942825578322926e-05, + "loss": 1.9842, + "step": 1150 + }, + { + "epoch": 0.06415472939078089, + "grad_norm": 0.4916748106479645, + "learning_rate": 9.942691228867546e-05, + "loss": 1.7163, + "step": 1151 + }, + { + "epoch": 0.06421046764394404, + "grad_norm": 0.5524545311927795, + "learning_rate": 9.94255672265882e-05, + "loss": 1.8273, + "step": 1152 + }, + { + "epoch": 0.06426620589710719, + "grad_norm": 0.5353971719741821, + "learning_rate": 9.942422059701012e-05, + "loss": 1.8914, + "step": 1153 + }, + { + "epoch": 0.06432194415027033, + "grad_norm": 0.48068755865097046, + "learning_rate": 9.942287239998392e-05, + "loss": 1.7668, + "step": 1154 + }, + { + "epoch": 0.06437768240343347, + "grad_norm": 0.48459264636039734, + "learning_rate": 9.942152263555237e-05, + "loss": 1.5809, + "step": 1155 + }, + { + "epoch": 0.06443342065659662, + "grad_norm": 0.5255505442619324, + "learning_rate": 9.942017130375825e-05, + "loss": 1.8543, + "step": 1156 + }, + { + "epoch": 0.06448915890975977, + "grad_norm": 0.5935083627700806, + "learning_rate": 9.941881840464447e-05, + "loss": 1.7744, + "step": 1157 + }, + { + "epoch": 0.06454489716292292, + "grad_norm": 0.5216168761253357, + "learning_rate": 9.941746393825386e-05, + "loss": 1.5802, + "step": 1158 + }, + { + "epoch": 0.06460063541608606, + "grad_norm": 0.5127310752868652, + "learning_rate": 9.941610790462946e-05, + "loss": 1.8704, + "step": 1159 + }, + { + "epoch": 0.0646563736692492, + "grad_norm": 0.5310918688774109, + "learning_rate": 9.94147503038142e-05, + "loss": 1.7503, + "step": 1160 + }, + { + "epoch": 0.06471211192241236, + "grad_norm": 0.5417837500572205, + "learning_rate": 9.941339113585117e-05, + "loss": 1.7069, + "step": 1161 + }, + { + "epoch": 0.0647678501755755, + "grad_norm": 0.46583306789398193, + "learning_rate": 9.94120304007835e-05, + "loss": 1.6529, + "step": 1162 + }, + { + "epoch": 0.06482358842873864, + "grad_norm": 0.5210421681404114, + "learning_rate": 9.941066809865429e-05, + "loss": 1.8965, + "step": 1163 + }, + { + "epoch": 0.06487932668190179, + "grad_norm": 0.4983007311820984, + "learning_rate": 9.940930422950679e-05, + "loss": 1.797, + "step": 1164 + }, + { + "epoch": 0.06493506493506493, + "grad_norm": 0.5835360884666443, + "learning_rate": 9.940793879338424e-05, + "loss": 1.9707, + "step": 1165 + }, + { + "epoch": 0.06499080318822809, + "grad_norm": 0.48875924944877625, + "learning_rate": 9.940657179032993e-05, + "loss": 1.8563, + "step": 1166 + }, + { + "epoch": 0.06504654144139123, + "grad_norm": 0.4999620020389557, + "learning_rate": 9.940520322038722e-05, + "loss": 1.6063, + "step": 1167 + }, + { + "epoch": 0.06510227969455437, + "grad_norm": 0.49378272891044617, + "learning_rate": 9.940383308359951e-05, + "loss": 1.8387, + "step": 1168 + }, + { + "epoch": 0.06515801794771751, + "grad_norm": 0.44992733001708984, + "learning_rate": 9.940246138001027e-05, + "loss": 1.4808, + "step": 1169 + }, + { + "epoch": 0.06521375620088067, + "grad_norm": 0.5133140683174133, + "learning_rate": 9.9401088109663e-05, + "loss": 1.9234, + "step": 1170 + }, + { + "epoch": 0.06526949445404381, + "grad_norm": 0.6143995523452759, + "learning_rate": 9.939971327260122e-05, + "loss": 2.1587, + "step": 1171 + }, + { + "epoch": 0.06532523270720696, + "grad_norm": 0.5144213438034058, + "learning_rate": 9.939833686886857e-05, + "loss": 1.8453, + "step": 1172 + }, + { + "epoch": 0.0653809709603701, + "grad_norm": 0.48773664236068726, + "learning_rate": 9.939695889850869e-05, + "loss": 1.7421, + "step": 1173 + }, + { + "epoch": 0.06543670921353324, + "grad_norm": 0.48457232117652893, + "learning_rate": 9.939557936156527e-05, + "loss": 1.7447, + "step": 1174 + }, + { + "epoch": 0.0654924474666964, + "grad_norm": 0.48477059602737427, + "learning_rate": 9.939419825808207e-05, + "loss": 1.5579, + "step": 1175 + }, + { + "epoch": 0.06554818571985954, + "grad_norm": 0.5835525393486023, + "learning_rate": 9.93928155881029e-05, + "loss": 2.1224, + "step": 1176 + }, + { + "epoch": 0.06560392397302268, + "grad_norm": 0.5277059078216553, + "learning_rate": 9.939143135167158e-05, + "loss": 1.8331, + "step": 1177 + }, + { + "epoch": 0.06565966222618583, + "grad_norm": 0.5046493411064148, + "learning_rate": 9.939004554883205e-05, + "loss": 1.7895, + "step": 1178 + }, + { + "epoch": 0.06571540047934897, + "grad_norm": 0.5206563472747803, + "learning_rate": 9.938865817962822e-05, + "loss": 1.7342, + "step": 1179 + }, + { + "epoch": 0.06577113873251213, + "grad_norm": 0.43598276376724243, + "learning_rate": 9.938726924410412e-05, + "loss": 1.5657, + "step": 1180 + }, + { + "epoch": 0.06582687698567527, + "grad_norm": 0.49584537744522095, + "learning_rate": 9.938587874230379e-05, + "loss": 1.7487, + "step": 1181 + }, + { + "epoch": 0.06588261523883841, + "grad_norm": 0.539125382900238, + "learning_rate": 9.938448667427131e-05, + "loss": 1.8534, + "step": 1182 + }, + { + "epoch": 0.06593835349200156, + "grad_norm": 0.4833453595638275, + "learning_rate": 9.938309304005086e-05, + "loss": 1.6074, + "step": 1183 + }, + { + "epoch": 0.06599409174516471, + "grad_norm": 0.5339459180831909, + "learning_rate": 9.938169783968663e-05, + "loss": 1.7358, + "step": 1184 + }, + { + "epoch": 0.06604982999832786, + "grad_norm": 0.5234376788139343, + "learning_rate": 9.938030107322283e-05, + "loss": 1.5923, + "step": 1185 + }, + { + "epoch": 0.066105568251491, + "grad_norm": 0.5175224542617798, + "learning_rate": 9.93789027407038e-05, + "loss": 1.8394, + "step": 1186 + }, + { + "epoch": 0.06616130650465414, + "grad_norm": 0.5155382752418518, + "learning_rate": 9.937750284217389e-05, + "loss": 1.6385, + "step": 1187 + }, + { + "epoch": 0.06621704475781728, + "grad_norm": 0.47023966908454895, + "learning_rate": 9.937610137767747e-05, + "loss": 1.6236, + "step": 1188 + }, + { + "epoch": 0.06627278301098044, + "grad_norm": 0.4659249484539032, + "learning_rate": 9.937469834725898e-05, + "loss": 1.6139, + "step": 1189 + }, + { + "epoch": 0.06632852126414358, + "grad_norm": 0.4964550733566284, + "learning_rate": 9.937329375096297e-05, + "loss": 1.62, + "step": 1190 + }, + { + "epoch": 0.06638425951730673, + "grad_norm": 0.5324812531471252, + "learning_rate": 9.937188758883393e-05, + "loss": 1.8803, + "step": 1191 + }, + { + "epoch": 0.06643999777046987, + "grad_norm": 0.5404229164123535, + "learning_rate": 9.937047986091646e-05, + "loss": 1.9219, + "step": 1192 + }, + { + "epoch": 0.06649573602363303, + "grad_norm": 0.49228188395500183, + "learning_rate": 9.936907056725524e-05, + "loss": 1.7777, + "step": 1193 + }, + { + "epoch": 0.06655147427679617, + "grad_norm": 0.5689822435379028, + "learning_rate": 9.936765970789492e-05, + "loss": 1.9888, + "step": 1194 + }, + { + "epoch": 0.06660721252995931, + "grad_norm": 0.5374904274940491, + "learning_rate": 9.936624728288029e-05, + "loss": 1.6308, + "step": 1195 + }, + { + "epoch": 0.06666295078312245, + "grad_norm": 0.48381903767585754, + "learning_rate": 9.93648332922561e-05, + "loss": 1.6621, + "step": 1196 + }, + { + "epoch": 0.0667186890362856, + "grad_norm": 0.5000702738761902, + "learning_rate": 9.936341773606723e-05, + "loss": 1.6883, + "step": 1197 + }, + { + "epoch": 0.06677442728944875, + "grad_norm": 0.4849522113800049, + "learning_rate": 9.936200061435857e-05, + "loss": 1.6099, + "step": 1198 + }, + { + "epoch": 0.0668301655426119, + "grad_norm": 0.5355091094970703, + "learning_rate": 9.936058192717502e-05, + "loss": 1.725, + "step": 1199 + }, + { + "epoch": 0.06688590379577504, + "grad_norm": 0.4482690095901489, + "learning_rate": 9.935916167456163e-05, + "loss": 1.5314, + "step": 1200 + }, + { + "epoch": 0.06694164204893818, + "grad_norm": 0.4166151285171509, + "learning_rate": 9.93577398565634e-05, + "loss": 1.094, + "step": 1201 + }, + { + "epoch": 0.06699738030210133, + "grad_norm": 0.569545328617096, + "learning_rate": 9.935631647322544e-05, + "loss": 1.9806, + "step": 1202 + }, + { + "epoch": 0.06705311855526448, + "grad_norm": 0.528708279132843, + "learning_rate": 9.93548915245929e-05, + "loss": 1.7586, + "step": 1203 + }, + { + "epoch": 0.06710885680842762, + "grad_norm": 0.48107293248176575, + "learning_rate": 9.935346501071095e-05, + "loss": 1.6344, + "step": 1204 + }, + { + "epoch": 0.06716459506159077, + "grad_norm": 0.5078762769699097, + "learning_rate": 9.935203693162483e-05, + "loss": 1.7792, + "step": 1205 + }, + { + "epoch": 0.06722033331475391, + "grad_norm": 0.4985436797142029, + "learning_rate": 9.935060728737986e-05, + "loss": 1.8226, + "step": 1206 + }, + { + "epoch": 0.06727607156791707, + "grad_norm": 0.5001996755599976, + "learning_rate": 9.934917607802135e-05, + "loss": 1.65, + "step": 1207 + }, + { + "epoch": 0.06733180982108021, + "grad_norm": 0.4552146792411804, + "learning_rate": 9.934774330359471e-05, + "loss": 1.5889, + "step": 1208 + }, + { + "epoch": 0.06738754807424335, + "grad_norm": 0.4674372673034668, + "learning_rate": 9.934630896414536e-05, + "loss": 1.6367, + "step": 1209 + }, + { + "epoch": 0.0674432863274065, + "grad_norm": 0.4658129811286926, + "learning_rate": 9.93448730597188e-05, + "loss": 1.6565, + "step": 1210 + }, + { + "epoch": 0.06749902458056964, + "grad_norm": 0.4953976273536682, + "learning_rate": 9.934343559036056e-05, + "loss": 1.7874, + "step": 1211 + }, + { + "epoch": 0.0675547628337328, + "grad_norm": 0.5296363830566406, + "learning_rate": 9.934199655611624e-05, + "loss": 1.4178, + "step": 1212 + }, + { + "epoch": 0.06761050108689594, + "grad_norm": 0.5114982724189758, + "learning_rate": 9.934055595703149e-05, + "loss": 1.8371, + "step": 1213 + }, + { + "epoch": 0.06766623934005908, + "grad_norm": 0.54044109582901, + "learning_rate": 9.933911379315198e-05, + "loss": 1.77, + "step": 1214 + }, + { + "epoch": 0.06772197759322222, + "grad_norm": 0.5306605100631714, + "learning_rate": 9.933767006452341e-05, + "loss": 1.7457, + "step": 1215 + }, + { + "epoch": 0.06777771584638538, + "grad_norm": 0.45446470379829407, + "learning_rate": 9.933622477119165e-05, + "loss": 1.4759, + "step": 1216 + }, + { + "epoch": 0.06783345409954852, + "grad_norm": 0.5077145099639893, + "learning_rate": 9.933477791320246e-05, + "loss": 1.5853, + "step": 1217 + }, + { + "epoch": 0.06788919235271167, + "grad_norm": 0.4767955541610718, + "learning_rate": 9.933332949060177e-05, + "loss": 1.624, + "step": 1218 + }, + { + "epoch": 0.06794493060587481, + "grad_norm": 0.5637747049331665, + "learning_rate": 9.93318795034355e-05, + "loss": 1.9126, + "step": 1219 + }, + { + "epoch": 0.06800066885903795, + "grad_norm": 0.5085890889167786, + "learning_rate": 9.933042795174963e-05, + "loss": 1.7807, + "step": 1220 + }, + { + "epoch": 0.06805640711220111, + "grad_norm": 0.539089024066925, + "learning_rate": 9.93289748355902e-05, + "loss": 1.8777, + "step": 1221 + }, + { + "epoch": 0.06811214536536425, + "grad_norm": 0.557056725025177, + "learning_rate": 9.93275201550033e-05, + "loss": 1.7479, + "step": 1222 + }, + { + "epoch": 0.0681678836185274, + "grad_norm": 0.5699108839035034, + "learning_rate": 9.932606391003508e-05, + "loss": 1.9158, + "step": 1223 + }, + { + "epoch": 0.06822362187169054, + "grad_norm": 0.5341405868530273, + "learning_rate": 9.932460610073167e-05, + "loss": 1.7554, + "step": 1224 + }, + { + "epoch": 0.06827936012485368, + "grad_norm": 0.6143330335617065, + "learning_rate": 9.932314672713936e-05, + "loss": 1.7927, + "step": 1225 + }, + { + "epoch": 0.06833509837801684, + "grad_norm": 0.500853419303894, + "learning_rate": 9.932168578930439e-05, + "loss": 1.7221, + "step": 1226 + }, + { + "epoch": 0.06839083663117998, + "grad_norm": 0.5622022151947021, + "learning_rate": 9.932022328727313e-05, + "loss": 2.0262, + "step": 1227 + }, + { + "epoch": 0.06844657488434312, + "grad_norm": 0.4860107898712158, + "learning_rate": 9.931875922109195e-05, + "loss": 1.7353, + "step": 1228 + }, + { + "epoch": 0.06850231313750627, + "grad_norm": 0.5524904131889343, + "learning_rate": 9.931729359080726e-05, + "loss": 1.8789, + "step": 1229 + }, + { + "epoch": 0.06855805139066942, + "grad_norm": 0.5192303657531738, + "learning_rate": 9.931582639646556e-05, + "loss": 1.9549, + "step": 1230 + }, + { + "epoch": 0.06861378964383257, + "grad_norm": 0.47247666120529175, + "learning_rate": 9.931435763811338e-05, + "loss": 1.7371, + "step": 1231 + }, + { + "epoch": 0.06866952789699571, + "grad_norm": 0.5242395401000977, + "learning_rate": 9.93128873157973e-05, + "loss": 1.8187, + "step": 1232 + }, + { + "epoch": 0.06872526615015885, + "grad_norm": 0.4895036816596985, + "learning_rate": 9.931141542956394e-05, + "loss": 1.6269, + "step": 1233 + }, + { + "epoch": 0.068781004403322, + "grad_norm": 0.5657653212547302, + "learning_rate": 9.930994197945999e-05, + "loss": 1.9831, + "step": 1234 + }, + { + "epoch": 0.06883674265648515, + "grad_norm": 0.5430802702903748, + "learning_rate": 9.930846696553219e-05, + "loss": 1.9577, + "step": 1235 + }, + { + "epoch": 0.0688924809096483, + "grad_norm": 0.6241572499275208, + "learning_rate": 9.930699038782729e-05, + "loss": 1.7921, + "step": 1236 + }, + { + "epoch": 0.06894821916281144, + "grad_norm": 0.5370758175849915, + "learning_rate": 9.930551224639215e-05, + "loss": 1.921, + "step": 1237 + }, + { + "epoch": 0.06900395741597458, + "grad_norm": 0.5141679048538208, + "learning_rate": 9.930403254127363e-05, + "loss": 1.8209, + "step": 1238 + }, + { + "epoch": 0.06905969566913774, + "grad_norm": 0.511951208114624, + "learning_rate": 9.930255127251866e-05, + "loss": 1.9209, + "step": 1239 + }, + { + "epoch": 0.06911543392230088, + "grad_norm": 0.5124894976615906, + "learning_rate": 9.93010684401742e-05, + "loss": 1.9073, + "step": 1240 + }, + { + "epoch": 0.06917117217546402, + "grad_norm": 0.49549224972724915, + "learning_rate": 9.929958404428732e-05, + "loss": 1.6648, + "step": 1241 + }, + { + "epoch": 0.06922691042862716, + "grad_norm": 0.4937445819377899, + "learning_rate": 9.929809808490505e-05, + "loss": 1.6878, + "step": 1242 + }, + { + "epoch": 0.06928264868179031, + "grad_norm": 0.5082506537437439, + "learning_rate": 9.929661056207455e-05, + "loss": 1.8051, + "step": 1243 + }, + { + "epoch": 0.06933838693495346, + "grad_norm": 0.5111956596374512, + "learning_rate": 9.929512147584297e-05, + "loss": 1.7016, + "step": 1244 + }, + { + "epoch": 0.0693941251881166, + "grad_norm": 0.46468988060951233, + "learning_rate": 9.929363082625755e-05, + "loss": 1.7512, + "step": 1245 + }, + { + "epoch": 0.06944986344127975, + "grad_norm": 0.5274616479873657, + "learning_rate": 9.929213861336557e-05, + "loss": 1.7578, + "step": 1246 + }, + { + "epoch": 0.06950560169444289, + "grad_norm": 0.5274865031242371, + "learning_rate": 9.929064483721435e-05, + "loss": 1.7655, + "step": 1247 + }, + { + "epoch": 0.06956133994760604, + "grad_norm": 0.5010793209075928, + "learning_rate": 9.928914949785124e-05, + "loss": 1.8085, + "step": 1248 + }, + { + "epoch": 0.06961707820076919, + "grad_norm": 0.5141963362693787, + "learning_rate": 9.928765259532371e-05, + "loss": 1.4068, + "step": 1249 + }, + { + "epoch": 0.06967281645393233, + "grad_norm": 0.5250492691993713, + "learning_rate": 9.928615412967919e-05, + "loss": 1.9137, + "step": 1250 + }, + { + "epoch": 0.06972855470709548, + "grad_norm": 0.5868452191352844, + "learning_rate": 9.928465410096521e-05, + "loss": 1.6562, + "step": 1251 + }, + { + "epoch": 0.06978429296025862, + "grad_norm": 0.553932785987854, + "learning_rate": 9.928315250922937e-05, + "loss": 1.7661, + "step": 1252 + }, + { + "epoch": 0.06984003121342178, + "grad_norm": 0.49618422985076904, + "learning_rate": 9.928164935451927e-05, + "loss": 1.9336, + "step": 1253 + }, + { + "epoch": 0.06989576946658492, + "grad_norm": 0.5094950199127197, + "learning_rate": 9.928014463688257e-05, + "loss": 1.8955, + "step": 1254 + }, + { + "epoch": 0.06995150771974806, + "grad_norm": 0.5146217942237854, + "learning_rate": 9.927863835636703e-05, + "loss": 1.7892, + "step": 1255 + }, + { + "epoch": 0.0700072459729112, + "grad_norm": 0.5579236745834351, + "learning_rate": 9.927713051302037e-05, + "loss": 1.8628, + "step": 1256 + }, + { + "epoch": 0.07006298422607435, + "grad_norm": 0.5719481706619263, + "learning_rate": 9.927562110689046e-05, + "loss": 1.9999, + "step": 1257 + }, + { + "epoch": 0.0701187224792375, + "grad_norm": 0.5164546966552734, + "learning_rate": 9.927411013802512e-05, + "loss": 1.6341, + "step": 1258 + }, + { + "epoch": 0.07017446073240065, + "grad_norm": 0.5111738443374634, + "learning_rate": 9.927259760647232e-05, + "loss": 1.8801, + "step": 1259 + }, + { + "epoch": 0.07023019898556379, + "grad_norm": 0.47879326343536377, + "learning_rate": 9.927108351227998e-05, + "loss": 1.6122, + "step": 1260 + }, + { + "epoch": 0.07028593723872693, + "grad_norm": 0.6105756759643555, + "learning_rate": 9.926956785549616e-05, + "loss": 2.0343, + "step": 1261 + }, + { + "epoch": 0.07034167549189009, + "grad_norm": 0.5080457329750061, + "learning_rate": 9.92680506361689e-05, + "loss": 1.9449, + "step": 1262 + }, + { + "epoch": 0.07039741374505323, + "grad_norm": 0.4686660170555115, + "learning_rate": 9.926653185434634e-05, + "loss": 1.7354, + "step": 1263 + }, + { + "epoch": 0.07045315199821638, + "grad_norm": 0.5146884322166443, + "learning_rate": 9.926501151007662e-05, + "loss": 1.8347, + "step": 1264 + }, + { + "epoch": 0.07050889025137952, + "grad_norm": 0.5533162355422974, + "learning_rate": 9.926348960340796e-05, + "loss": 1.887, + "step": 1265 + }, + { + "epoch": 0.07056462850454266, + "grad_norm": 0.5264948606491089, + "learning_rate": 9.926196613438865e-05, + "loss": 1.8267, + "step": 1266 + }, + { + "epoch": 0.07062036675770582, + "grad_norm": 0.5064124464988708, + "learning_rate": 9.926044110306698e-05, + "loss": 1.4021, + "step": 1267 + }, + { + "epoch": 0.07067610501086896, + "grad_norm": 0.5374730229377747, + "learning_rate": 9.925891450949135e-05, + "loss": 2.1346, + "step": 1268 + }, + { + "epoch": 0.0707318432640321, + "grad_norm": 0.5050212144851685, + "learning_rate": 9.925738635371011e-05, + "loss": 1.7458, + "step": 1269 + }, + { + "epoch": 0.07078758151719525, + "grad_norm": 0.5477495789527893, + "learning_rate": 9.925585663577181e-05, + "loss": 1.9184, + "step": 1270 + }, + { + "epoch": 0.0708433197703584, + "grad_norm": 0.4926922917366028, + "learning_rate": 9.92543253557249e-05, + "loss": 1.7406, + "step": 1271 + }, + { + "epoch": 0.07089905802352155, + "grad_norm": 0.5027531981468201, + "learning_rate": 9.925279251361795e-05, + "loss": 1.6771, + "step": 1272 + }, + { + "epoch": 0.07095479627668469, + "grad_norm": 0.44907525181770325, + "learning_rate": 9.92512581094996e-05, + "loss": 1.534, + "step": 1273 + }, + { + "epoch": 0.07101053452984783, + "grad_norm": 0.4935868978500366, + "learning_rate": 9.92497221434185e-05, + "loss": 1.6932, + "step": 1274 + }, + { + "epoch": 0.07106627278301098, + "grad_norm": 0.5403043031692505, + "learning_rate": 9.924818461542335e-05, + "loss": 1.7863, + "step": 1275 + }, + { + "epoch": 0.07112201103617413, + "grad_norm": 0.49991410970687866, + "learning_rate": 9.924664552556293e-05, + "loss": 1.5134, + "step": 1276 + }, + { + "epoch": 0.07117774928933727, + "grad_norm": 0.5363178849220276, + "learning_rate": 9.924510487388603e-05, + "loss": 1.7264, + "step": 1277 + }, + { + "epoch": 0.07123348754250042, + "grad_norm": 0.6076151728630066, + "learning_rate": 9.924356266044153e-05, + "loss": 2.0642, + "step": 1278 + }, + { + "epoch": 0.07128922579566356, + "grad_norm": 0.5013806223869324, + "learning_rate": 9.924201888527833e-05, + "loss": 1.5962, + "step": 1279 + }, + { + "epoch": 0.0713449640488267, + "grad_norm": 0.4695322513580322, + "learning_rate": 9.924047354844539e-05, + "loss": 1.657, + "step": 1280 + }, + { + "epoch": 0.07140070230198986, + "grad_norm": 0.5039030909538269, + "learning_rate": 9.923892664999173e-05, + "loss": 1.8447, + "step": 1281 + }, + { + "epoch": 0.071456440555153, + "grad_norm": 0.5190325379371643, + "learning_rate": 9.923737818996639e-05, + "loss": 1.7732, + "step": 1282 + }, + { + "epoch": 0.07151217880831615, + "grad_norm": 0.4986951947212219, + "learning_rate": 9.92358281684185e-05, + "loss": 1.5262, + "step": 1283 + }, + { + "epoch": 0.07156791706147929, + "grad_norm": 0.5534316897392273, + "learning_rate": 9.92342765853972e-05, + "loss": 2.0328, + "step": 1284 + }, + { + "epoch": 0.07162365531464245, + "grad_norm": 0.49968552589416504, + "learning_rate": 9.923272344095169e-05, + "loss": 1.7766, + "step": 1285 + }, + { + "epoch": 0.07167939356780559, + "grad_norm": 0.5316057205200195, + "learning_rate": 9.923116873513125e-05, + "loss": 1.9544, + "step": 1286 + }, + { + "epoch": 0.07173513182096873, + "grad_norm": 0.49467048048973083, + "learning_rate": 9.922961246798516e-05, + "loss": 1.6245, + "step": 1287 + }, + { + "epoch": 0.07179087007413187, + "grad_norm": 0.5283698439598083, + "learning_rate": 9.922805463956282e-05, + "loss": 1.8113, + "step": 1288 + }, + { + "epoch": 0.07184660832729502, + "grad_norm": 0.5117636322975159, + "learning_rate": 9.922649524991359e-05, + "loss": 1.5682, + "step": 1289 + }, + { + "epoch": 0.07190234658045817, + "grad_norm": 0.524705708026886, + "learning_rate": 9.922493429908695e-05, + "loss": 1.7724, + "step": 1290 + }, + { + "epoch": 0.07195808483362132, + "grad_norm": 0.5265300273895264, + "learning_rate": 9.922337178713238e-05, + "loss": 1.8775, + "step": 1291 + }, + { + "epoch": 0.07201382308678446, + "grad_norm": 0.4668891429901123, + "learning_rate": 9.922180771409945e-05, + "loss": 1.6585, + "step": 1292 + }, + { + "epoch": 0.0720695613399476, + "grad_norm": 0.5392476916313171, + "learning_rate": 9.922024208003777e-05, + "loss": 1.7811, + "step": 1293 + }, + { + "epoch": 0.07212529959311076, + "grad_norm": 0.45741191506385803, + "learning_rate": 9.921867488499699e-05, + "loss": 1.5123, + "step": 1294 + }, + { + "epoch": 0.0721810378462739, + "grad_norm": 0.5779647827148438, + "learning_rate": 9.92171061290268e-05, + "loss": 1.798, + "step": 1295 + }, + { + "epoch": 0.07223677609943704, + "grad_norm": 0.5434536337852478, + "learning_rate": 9.921553581217697e-05, + "loss": 1.8681, + "step": 1296 + }, + { + "epoch": 0.07229251435260019, + "grad_norm": 0.47686439752578735, + "learning_rate": 9.921396393449727e-05, + "loss": 1.5803, + "step": 1297 + }, + { + "epoch": 0.07234825260576333, + "grad_norm": 0.5182580947875977, + "learning_rate": 9.921239049603759e-05, + "loss": 1.8512, + "step": 1298 + }, + { + "epoch": 0.07240399085892649, + "grad_norm": 0.5331408977508545, + "learning_rate": 9.921081549684779e-05, + "loss": 1.9001, + "step": 1299 + }, + { + "epoch": 0.07245972911208963, + "grad_norm": 0.49691641330718994, + "learning_rate": 9.920923893697786e-05, + "loss": 1.718, + "step": 1300 + }, + { + "epoch": 0.07251546736525277, + "grad_norm": 0.526009202003479, + "learning_rate": 9.920766081647779e-05, + "loss": 1.6531, + "step": 1301 + }, + { + "epoch": 0.07257120561841592, + "grad_norm": 0.5836690664291382, + "learning_rate": 9.92060811353976e-05, + "loss": 1.6522, + "step": 1302 + }, + { + "epoch": 0.07262694387157906, + "grad_norm": 0.5216406583786011, + "learning_rate": 9.920449989378742e-05, + "loss": 1.5131, + "step": 1303 + }, + { + "epoch": 0.07268268212474222, + "grad_norm": 0.4874148964881897, + "learning_rate": 9.920291709169737e-05, + "loss": 1.5922, + "step": 1304 + }, + { + "epoch": 0.07273842037790536, + "grad_norm": 0.4904099404811859, + "learning_rate": 9.920133272917767e-05, + "loss": 1.83, + "step": 1305 + }, + { + "epoch": 0.0727941586310685, + "grad_norm": 0.5295507907867432, + "learning_rate": 9.919974680627856e-05, + "loss": 1.8742, + "step": 1306 + }, + { + "epoch": 0.07284989688423164, + "grad_norm": 0.5288472175598145, + "learning_rate": 9.919815932305034e-05, + "loss": 1.8706, + "step": 1307 + }, + { + "epoch": 0.0729056351373948, + "grad_norm": 0.48234906792640686, + "learning_rate": 9.919657027954335e-05, + "loss": 1.6827, + "step": 1308 + }, + { + "epoch": 0.07296137339055794, + "grad_norm": 0.5203633904457092, + "learning_rate": 9.919497967580798e-05, + "loss": 1.7064, + "step": 1309 + }, + { + "epoch": 0.07301711164372109, + "grad_norm": 0.51950603723526, + "learning_rate": 9.919338751189468e-05, + "loss": 1.7643, + "step": 1310 + }, + { + "epoch": 0.07307284989688423, + "grad_norm": 0.5219436883926392, + "learning_rate": 9.919179378785396e-05, + "loss": 1.928, + "step": 1311 + }, + { + "epoch": 0.07312858815004737, + "grad_norm": 0.5543720722198486, + "learning_rate": 9.919019850373635e-05, + "loss": 2.0754, + "step": 1312 + }, + { + "epoch": 0.07318432640321053, + "grad_norm": 0.4778376817703247, + "learning_rate": 9.918860165959243e-05, + "loss": 1.652, + "step": 1313 + }, + { + "epoch": 0.07324006465637367, + "grad_norm": 0.5367230772972107, + "learning_rate": 9.918700325547286e-05, + "loss": 1.9413, + "step": 1314 + }, + { + "epoch": 0.07329580290953681, + "grad_norm": 0.5712525248527527, + "learning_rate": 9.918540329142831e-05, + "loss": 1.7279, + "step": 1315 + }, + { + "epoch": 0.07335154116269996, + "grad_norm": 0.5032913088798523, + "learning_rate": 9.918380176750955e-05, + "loss": 1.7546, + "step": 1316 + }, + { + "epoch": 0.07340727941586311, + "grad_norm": 0.4760904908180237, + "learning_rate": 9.918219868376737e-05, + "loss": 1.657, + "step": 1317 + }, + { + "epoch": 0.07346301766902626, + "grad_norm": 0.5059273838996887, + "learning_rate": 9.91805940402526e-05, + "loss": 1.8728, + "step": 1318 + }, + { + "epoch": 0.0735187559221894, + "grad_norm": 0.5608049631118774, + "learning_rate": 9.917898783701612e-05, + "loss": 2.008, + "step": 1319 + }, + { + "epoch": 0.07357449417535254, + "grad_norm": 0.5329555869102478, + "learning_rate": 9.917738007410888e-05, + "loss": 1.6254, + "step": 1320 + }, + { + "epoch": 0.07363023242851569, + "grad_norm": 0.5802140831947327, + "learning_rate": 9.917577075158186e-05, + "loss": 2.0478, + "step": 1321 + }, + { + "epoch": 0.07368597068167884, + "grad_norm": 0.5300236940383911, + "learning_rate": 9.917415986948612e-05, + "loss": 1.8852, + "step": 1322 + }, + { + "epoch": 0.07374170893484198, + "grad_norm": 0.4858631491661072, + "learning_rate": 9.917254742787273e-05, + "loss": 1.5704, + "step": 1323 + }, + { + "epoch": 0.07379744718800513, + "grad_norm": 0.5059242248535156, + "learning_rate": 9.917093342679284e-05, + "loss": 1.6683, + "step": 1324 + }, + { + "epoch": 0.07385318544116827, + "grad_norm": 0.4971073567867279, + "learning_rate": 9.916931786629761e-05, + "loss": 1.6127, + "step": 1325 + }, + { + "epoch": 0.07390892369433141, + "grad_norm": 0.5727537274360657, + "learning_rate": 9.916770074643831e-05, + "loss": 1.8274, + "step": 1326 + }, + { + "epoch": 0.07396466194749457, + "grad_norm": 0.5242769718170166, + "learning_rate": 9.91660820672662e-05, + "loss": 1.7747, + "step": 1327 + }, + { + "epoch": 0.07402040020065771, + "grad_norm": 0.5268994569778442, + "learning_rate": 9.916446182883264e-05, + "loss": 1.8716, + "step": 1328 + }, + { + "epoch": 0.07407613845382086, + "grad_norm": 0.5069685578346252, + "learning_rate": 9.916284003118897e-05, + "loss": 1.572, + "step": 1329 + }, + { + "epoch": 0.074131876706984, + "grad_norm": 0.5535740852355957, + "learning_rate": 9.916121667438667e-05, + "loss": 1.852, + "step": 1330 + }, + { + "epoch": 0.07418761496014716, + "grad_norm": 0.5100526213645935, + "learning_rate": 9.915959175847723e-05, + "loss": 1.8053, + "step": 1331 + }, + { + "epoch": 0.0742433532133103, + "grad_norm": 0.5486835837364197, + "learning_rate": 9.915796528351212e-05, + "loss": 1.9061, + "step": 1332 + }, + { + "epoch": 0.07429909146647344, + "grad_norm": 0.546424150466919, + "learning_rate": 9.915633724954299e-05, + "loss": 1.8031, + "step": 1333 + }, + { + "epoch": 0.07435482971963658, + "grad_norm": 0.5596832036972046, + "learning_rate": 9.915470765662143e-05, + "loss": 1.7918, + "step": 1334 + }, + { + "epoch": 0.07441056797279973, + "grad_norm": 0.5737068057060242, + "learning_rate": 9.915307650479914e-05, + "loss": 1.7687, + "step": 1335 + }, + { + "epoch": 0.07446630622596288, + "grad_norm": 0.5227526426315308, + "learning_rate": 9.915144379412784e-05, + "loss": 1.6509, + "step": 1336 + }, + { + "epoch": 0.07452204447912603, + "grad_norm": 0.5172739028930664, + "learning_rate": 9.914980952465932e-05, + "loss": 1.7922, + "step": 1337 + }, + { + "epoch": 0.07457778273228917, + "grad_norm": 0.5068166851997375, + "learning_rate": 9.91481736964454e-05, + "loss": 1.6475, + "step": 1338 + }, + { + "epoch": 0.07463352098545231, + "grad_norm": 0.5804305076599121, + "learning_rate": 9.914653630953797e-05, + "loss": 1.9451, + "step": 1339 + }, + { + "epoch": 0.07468925923861547, + "grad_norm": 0.5118273496627808, + "learning_rate": 9.914489736398895e-05, + "loss": 1.6014, + "step": 1340 + }, + { + "epoch": 0.07474499749177861, + "grad_norm": 0.47122183442115784, + "learning_rate": 9.914325685985033e-05, + "loss": 1.7206, + "step": 1341 + }, + { + "epoch": 0.07480073574494175, + "grad_norm": 0.5404577851295471, + "learning_rate": 9.914161479717413e-05, + "loss": 1.984, + "step": 1342 + }, + { + "epoch": 0.0748564739981049, + "grad_norm": 0.5037184953689575, + "learning_rate": 9.91399711760124e-05, + "loss": 1.8535, + "step": 1343 + }, + { + "epoch": 0.07491221225126804, + "grad_norm": 0.5099769830703735, + "learning_rate": 9.91383259964173e-05, + "loss": 1.7632, + "step": 1344 + }, + { + "epoch": 0.0749679505044312, + "grad_norm": 0.5458886623382568, + "learning_rate": 9.9136679258441e-05, + "loss": 2.0607, + "step": 1345 + }, + { + "epoch": 0.07502368875759434, + "grad_norm": 0.4648517668247223, + "learning_rate": 9.913503096213572e-05, + "loss": 1.914, + "step": 1346 + }, + { + "epoch": 0.07507942701075748, + "grad_norm": 0.5120497941970825, + "learning_rate": 9.913338110755375e-05, + "loss": 1.8349, + "step": 1347 + }, + { + "epoch": 0.07513516526392063, + "grad_norm": 0.4551779329776764, + "learning_rate": 9.913172969474737e-05, + "loss": 1.5673, + "step": 1348 + }, + { + "epoch": 0.07519090351708377, + "grad_norm": 0.5728102326393127, + "learning_rate": 9.913007672376899e-05, + "loss": 2.1014, + "step": 1349 + }, + { + "epoch": 0.07524664177024692, + "grad_norm": 0.47414430975914, + "learning_rate": 9.912842219467105e-05, + "loss": 1.6999, + "step": 1350 + }, + { + "epoch": 0.07530238002341007, + "grad_norm": 0.5111278891563416, + "learning_rate": 9.912676610750598e-05, + "loss": 1.9367, + "step": 1351 + }, + { + "epoch": 0.07535811827657321, + "grad_norm": 0.5118902325630188, + "learning_rate": 9.91251084623263e-05, + "loss": 1.8136, + "step": 1352 + }, + { + "epoch": 0.07541385652973635, + "grad_norm": 0.5514450669288635, + "learning_rate": 9.912344925918462e-05, + "loss": 1.7309, + "step": 1353 + }, + { + "epoch": 0.07546959478289951, + "grad_norm": 0.4836481511592865, + "learning_rate": 9.912178849813353e-05, + "loss": 1.2918, + "step": 1354 + }, + { + "epoch": 0.07552533303606265, + "grad_norm": 0.5168613791465759, + "learning_rate": 9.91201261792257e-05, + "loss": 1.8673, + "step": 1355 + }, + { + "epoch": 0.0755810712892258, + "grad_norm": 0.48082637786865234, + "learning_rate": 9.911846230251388e-05, + "loss": 1.6275, + "step": 1356 + }, + { + "epoch": 0.07563680954238894, + "grad_norm": 0.504571259021759, + "learning_rate": 9.91167968680508e-05, + "loss": 1.7718, + "step": 1357 + }, + { + "epoch": 0.07569254779555208, + "grad_norm": 0.499100923538208, + "learning_rate": 9.911512987588932e-05, + "loss": 1.7842, + "step": 1358 + }, + { + "epoch": 0.07574828604871524, + "grad_norm": 0.4926021993160248, + "learning_rate": 9.911346132608225e-05, + "loss": 1.5556, + "step": 1359 + }, + { + "epoch": 0.07580402430187838, + "grad_norm": 0.5981921553611755, + "learning_rate": 9.911179121868255e-05, + "loss": 1.853, + "step": 1360 + }, + { + "epoch": 0.07585976255504152, + "grad_norm": 0.4938274621963501, + "learning_rate": 9.911011955374316e-05, + "loss": 1.646, + "step": 1361 + }, + { + "epoch": 0.07591550080820467, + "grad_norm": 0.4952639937400818, + "learning_rate": 9.910844633131713e-05, + "loss": 1.6188, + "step": 1362 + }, + { + "epoch": 0.07597123906136782, + "grad_norm": 0.5024005770683289, + "learning_rate": 9.91067715514575e-05, + "loss": 1.9164, + "step": 1363 + }, + { + "epoch": 0.07602697731453097, + "grad_norm": 0.5488448143005371, + "learning_rate": 9.910509521421738e-05, + "loss": 1.9139, + "step": 1364 + }, + { + "epoch": 0.07608271556769411, + "grad_norm": 0.5247362852096558, + "learning_rate": 9.910341731964996e-05, + "loss": 1.8488, + "step": 1365 + }, + { + "epoch": 0.07613845382085725, + "grad_norm": 0.5229883193969727, + "learning_rate": 9.910173786780842e-05, + "loss": 1.8503, + "step": 1366 + }, + { + "epoch": 0.0761941920740204, + "grad_norm": 0.49642667174339294, + "learning_rate": 9.910005685874603e-05, + "loss": 1.7051, + "step": 1367 + }, + { + "epoch": 0.07624993032718355, + "grad_norm": 0.48131421208381653, + "learning_rate": 9.909837429251614e-05, + "loss": 1.4925, + "step": 1368 + }, + { + "epoch": 0.0763056685803467, + "grad_norm": 0.4743631184101105, + "learning_rate": 9.909669016917204e-05, + "loss": 1.5833, + "step": 1369 + }, + { + "epoch": 0.07636140683350984, + "grad_norm": 0.5918928980827332, + "learning_rate": 9.909500448876721e-05, + "loss": 2.1295, + "step": 1370 + }, + { + "epoch": 0.07641714508667298, + "grad_norm": 0.5590381622314453, + "learning_rate": 9.909331725135509e-05, + "loss": 1.862, + "step": 1371 + }, + { + "epoch": 0.07647288333983612, + "grad_norm": 0.5015060305595398, + "learning_rate": 9.909162845698916e-05, + "loss": 1.7541, + "step": 1372 + }, + { + "epoch": 0.07652862159299928, + "grad_norm": 0.5213440656661987, + "learning_rate": 9.9089938105723e-05, + "loss": 1.7944, + "step": 1373 + }, + { + "epoch": 0.07658435984616242, + "grad_norm": 0.5424663424491882, + "learning_rate": 9.908824619761023e-05, + "loss": 1.8207, + "step": 1374 + }, + { + "epoch": 0.07664009809932557, + "grad_norm": 0.548622727394104, + "learning_rate": 9.908655273270449e-05, + "loss": 1.8224, + "step": 1375 + }, + { + "epoch": 0.07669583635248871, + "grad_norm": 0.5018399953842163, + "learning_rate": 9.908485771105949e-05, + "loss": 1.856, + "step": 1376 + }, + { + "epoch": 0.07675157460565186, + "grad_norm": 0.5578395128250122, + "learning_rate": 9.908316113272897e-05, + "loss": 1.7791, + "step": 1377 + }, + { + "epoch": 0.07680731285881501, + "grad_norm": 0.5207507610321045, + "learning_rate": 9.908146299776678e-05, + "loss": 1.7608, + "step": 1378 + }, + { + "epoch": 0.07686305111197815, + "grad_norm": 0.5391795039176941, + "learning_rate": 9.907976330622674e-05, + "loss": 1.772, + "step": 1379 + }, + { + "epoch": 0.0769187893651413, + "grad_norm": 0.47418221831321716, + "learning_rate": 9.907806205816277e-05, + "loss": 1.2319, + "step": 1380 + }, + { + "epoch": 0.07697452761830444, + "grad_norm": 0.49630096554756165, + "learning_rate": 9.90763592536288e-05, + "loss": 1.676, + "step": 1381 + }, + { + "epoch": 0.0770302658714676, + "grad_norm": 0.533801257610321, + "learning_rate": 9.907465489267886e-05, + "loss": 1.7612, + "step": 1382 + }, + { + "epoch": 0.07708600412463074, + "grad_norm": 0.5061699748039246, + "learning_rate": 9.907294897536699e-05, + "loss": 1.8883, + "step": 1383 + }, + { + "epoch": 0.07714174237779388, + "grad_norm": 0.5732898116111755, + "learning_rate": 9.90712415017473e-05, + "loss": 1.8195, + "step": 1384 + }, + { + "epoch": 0.07719748063095702, + "grad_norm": 0.5062339901924133, + "learning_rate": 9.906953247187392e-05, + "loss": 1.765, + "step": 1385 + }, + { + "epoch": 0.07725321888412018, + "grad_norm": 0.4672509729862213, + "learning_rate": 9.906782188580107e-05, + "loss": 1.5199, + "step": 1386 + }, + { + "epoch": 0.07730895713728332, + "grad_norm": 0.5902494788169861, + "learning_rate": 9.9066109743583e-05, + "loss": 2.1369, + "step": 1387 + }, + { + "epoch": 0.07736469539044646, + "grad_norm": 0.4874188005924225, + "learning_rate": 9.9064396045274e-05, + "loss": 1.6941, + "step": 1388 + }, + { + "epoch": 0.0774204336436096, + "grad_norm": 0.5620763301849365, + "learning_rate": 9.906268079092843e-05, + "loss": 1.7395, + "step": 1389 + }, + { + "epoch": 0.07747617189677275, + "grad_norm": 0.5454680919647217, + "learning_rate": 9.906096398060067e-05, + "loss": 1.7771, + "step": 1390 + }, + { + "epoch": 0.0775319101499359, + "grad_norm": 0.5270059704780579, + "learning_rate": 9.905924561434519e-05, + "loss": 1.8375, + "step": 1391 + }, + { + "epoch": 0.07758764840309905, + "grad_norm": 0.4714577794075012, + "learning_rate": 9.905752569221647e-05, + "loss": 1.4259, + "step": 1392 + }, + { + "epoch": 0.07764338665626219, + "grad_norm": 0.4905398190021515, + "learning_rate": 9.905580421426905e-05, + "loss": 1.7302, + "step": 1393 + }, + { + "epoch": 0.07769912490942534, + "grad_norm": 0.5166676640510559, + "learning_rate": 9.905408118055755e-05, + "loss": 1.665, + "step": 1394 + }, + { + "epoch": 0.07775486316258848, + "grad_norm": 0.5545955896377563, + "learning_rate": 9.905235659113658e-05, + "loss": 1.7589, + "step": 1395 + }, + { + "epoch": 0.07781060141575163, + "grad_norm": 0.5974867343902588, + "learning_rate": 9.905063044606088e-05, + "loss": 1.9677, + "step": 1396 + }, + { + "epoch": 0.07786633966891478, + "grad_norm": 0.538375198841095, + "learning_rate": 9.904890274538516e-05, + "loss": 1.6438, + "step": 1397 + }, + { + "epoch": 0.07792207792207792, + "grad_norm": 0.5226508378982544, + "learning_rate": 9.904717348916421e-05, + "loss": 1.8672, + "step": 1398 + }, + { + "epoch": 0.07797781617524106, + "grad_norm": 0.5076341032981873, + "learning_rate": 9.904544267745288e-05, + "loss": 1.6942, + "step": 1399 + }, + { + "epoch": 0.07803355442840422, + "grad_norm": 0.5587323307991028, + "learning_rate": 9.904371031030608e-05, + "loss": 2.0127, + "step": 1400 + }, + { + "epoch": 0.07808929268156736, + "grad_norm": 0.5744814276695251, + "learning_rate": 9.904197638777872e-05, + "loss": 1.6781, + "step": 1401 + }, + { + "epoch": 0.0781450309347305, + "grad_norm": 0.4966742992401123, + "learning_rate": 9.904024090992581e-05, + "loss": 1.7314, + "step": 1402 + }, + { + "epoch": 0.07820076918789365, + "grad_norm": 0.5050981640815735, + "learning_rate": 9.903850387680238e-05, + "loss": 1.8782, + "step": 1403 + }, + { + "epoch": 0.07825650744105679, + "grad_norm": 0.518583357334137, + "learning_rate": 9.903676528846352e-05, + "loss": 1.9028, + "step": 1404 + }, + { + "epoch": 0.07831224569421995, + "grad_norm": 0.5047330856323242, + "learning_rate": 9.903502514496436e-05, + "loss": 1.6501, + "step": 1405 + }, + { + "epoch": 0.07836798394738309, + "grad_norm": 0.5036478042602539, + "learning_rate": 9.903328344636012e-05, + "loss": 1.7873, + "step": 1406 + }, + { + "epoch": 0.07842372220054623, + "grad_norm": 0.49196913838386536, + "learning_rate": 9.903154019270599e-05, + "loss": 1.6404, + "step": 1407 + }, + { + "epoch": 0.07847946045370938, + "grad_norm": 0.5227888226509094, + "learning_rate": 9.90297953840573e-05, + "loss": 1.8049, + "step": 1408 + }, + { + "epoch": 0.07853519870687253, + "grad_norm": 0.5419712662696838, + "learning_rate": 9.902804902046935e-05, + "loss": 1.8979, + "step": 1409 + }, + { + "epoch": 0.07859093696003568, + "grad_norm": 0.5512637495994568, + "learning_rate": 9.902630110199753e-05, + "loss": 1.5322, + "step": 1410 + }, + { + "epoch": 0.07864667521319882, + "grad_norm": 0.5147241353988647, + "learning_rate": 9.90245516286973e-05, + "loss": 1.8126, + "step": 1411 + }, + { + "epoch": 0.07870241346636196, + "grad_norm": 0.5257126092910767, + "learning_rate": 9.902280060062413e-05, + "loss": 1.9197, + "step": 1412 + }, + { + "epoch": 0.0787581517195251, + "grad_norm": 0.5739386677742004, + "learning_rate": 9.902104801783352e-05, + "loss": 2.0767, + "step": 1413 + }, + { + "epoch": 0.07881388997268826, + "grad_norm": 0.47901228070259094, + "learning_rate": 9.90192938803811e-05, + "loss": 1.4594, + "step": 1414 + }, + { + "epoch": 0.0788696282258514, + "grad_norm": 0.4943484663963318, + "learning_rate": 9.901753818832248e-05, + "loss": 1.6394, + "step": 1415 + }, + { + "epoch": 0.07892536647901455, + "grad_norm": 0.5033669471740723, + "learning_rate": 9.901578094171333e-05, + "loss": 1.6963, + "step": 1416 + }, + { + "epoch": 0.07898110473217769, + "grad_norm": 0.5039759874343872, + "learning_rate": 9.90140221406094e-05, + "loss": 1.5721, + "step": 1417 + }, + { + "epoch": 0.07903684298534083, + "grad_norm": 0.49595627188682556, + "learning_rate": 9.901226178506646e-05, + "loss": 1.7414, + "step": 1418 + }, + { + "epoch": 0.07909258123850399, + "grad_norm": 0.5233118534088135, + "learning_rate": 9.901049987514033e-05, + "loss": 1.7728, + "step": 1419 + }, + { + "epoch": 0.07914831949166713, + "grad_norm": 0.5164638757705688, + "learning_rate": 9.90087364108869e-05, + "loss": 1.8569, + "step": 1420 + }, + { + "epoch": 0.07920405774483028, + "grad_norm": 0.5309315323829651, + "learning_rate": 9.900697139236209e-05, + "loss": 1.7734, + "step": 1421 + }, + { + "epoch": 0.07925979599799342, + "grad_norm": 0.4936157464981079, + "learning_rate": 9.900520481962188e-05, + "loss": 1.6859, + "step": 1422 + }, + { + "epoch": 0.07931553425115657, + "grad_norm": 0.4760551452636719, + "learning_rate": 9.90034366927223e-05, + "loss": 1.7148, + "step": 1423 + }, + { + "epoch": 0.07937127250431972, + "grad_norm": 0.5099088549613953, + "learning_rate": 9.90016670117194e-05, + "loss": 1.7605, + "step": 1424 + }, + { + "epoch": 0.07942701075748286, + "grad_norm": 0.512695848941803, + "learning_rate": 9.899989577666933e-05, + "loss": 1.7824, + "step": 1425 + }, + { + "epoch": 0.079482749010646, + "grad_norm": 0.5051438212394714, + "learning_rate": 9.899812298762826e-05, + "loss": 1.8003, + "step": 1426 + }, + { + "epoch": 0.07953848726380915, + "grad_norm": 0.5289508700370789, + "learning_rate": 9.899634864465241e-05, + "loss": 1.7588, + "step": 1427 + }, + { + "epoch": 0.0795942255169723, + "grad_norm": 0.4910021424293518, + "learning_rate": 9.899457274779804e-05, + "loss": 1.7284, + "step": 1428 + }, + { + "epoch": 0.07964996377013545, + "grad_norm": 0.6068856716156006, + "learning_rate": 9.899279529712148e-05, + "loss": 1.9947, + "step": 1429 + }, + { + "epoch": 0.07970570202329859, + "grad_norm": 0.5239669680595398, + "learning_rate": 9.899101629267911e-05, + "loss": 1.5956, + "step": 1430 + }, + { + "epoch": 0.07976144027646173, + "grad_norm": 0.5577272176742554, + "learning_rate": 9.898923573452734e-05, + "loss": 2.0396, + "step": 1431 + }, + { + "epoch": 0.07981717852962489, + "grad_norm": 0.4893241822719574, + "learning_rate": 9.898745362272264e-05, + "loss": 1.5054, + "step": 1432 + }, + { + "epoch": 0.07987291678278803, + "grad_norm": 0.48603859543800354, + "learning_rate": 9.898566995732153e-05, + "loss": 1.6304, + "step": 1433 + }, + { + "epoch": 0.07992865503595117, + "grad_norm": 0.5560683012008667, + "learning_rate": 9.898388473838056e-05, + "loss": 1.8177, + "step": 1434 + }, + { + "epoch": 0.07998439328911432, + "grad_norm": 0.5030083060264587, + "learning_rate": 9.898209796595636e-05, + "loss": 1.7325, + "step": 1435 + }, + { + "epoch": 0.08004013154227746, + "grad_norm": 0.48422524333000183, + "learning_rate": 9.898030964010562e-05, + "loss": 1.5905, + "step": 1436 + }, + { + "epoch": 0.08009586979544062, + "grad_norm": 0.5284083485603333, + "learning_rate": 9.897851976088501e-05, + "loss": 1.672, + "step": 1437 + }, + { + "epoch": 0.08015160804860376, + "grad_norm": 0.5937215685844421, + "learning_rate": 9.897672832835135e-05, + "loss": 1.9549, + "step": 1438 + }, + { + "epoch": 0.0802073463017669, + "grad_norm": 0.4896755516529083, + "learning_rate": 9.89749353425614e-05, + "loss": 1.7438, + "step": 1439 + }, + { + "epoch": 0.08026308455493004, + "grad_norm": 0.5281119346618652, + "learning_rate": 9.897314080357202e-05, + "loss": 1.6437, + "step": 1440 + }, + { + "epoch": 0.08031882280809319, + "grad_norm": 0.5150919556617737, + "learning_rate": 9.897134471144019e-05, + "loss": 1.742, + "step": 1441 + }, + { + "epoch": 0.08037456106125634, + "grad_norm": 0.5028387308120728, + "learning_rate": 9.896954706622281e-05, + "loss": 1.5031, + "step": 1442 + }, + { + "epoch": 0.08043029931441949, + "grad_norm": 0.5158771276473999, + "learning_rate": 9.896774786797691e-05, + "loss": 1.533, + "step": 1443 + }, + { + "epoch": 0.08048603756758263, + "grad_norm": 0.5377411842346191, + "learning_rate": 9.896594711675954e-05, + "loss": 2.0242, + "step": 1444 + }, + { + "epoch": 0.08054177582074577, + "grad_norm": 0.4912663698196411, + "learning_rate": 9.896414481262784e-05, + "loss": 1.815, + "step": 1445 + }, + { + "epoch": 0.08059751407390893, + "grad_norm": 0.47936177253723145, + "learning_rate": 9.896234095563893e-05, + "loss": 1.5458, + "step": 1446 + }, + { + "epoch": 0.08065325232707207, + "grad_norm": 0.5695403218269348, + "learning_rate": 9.896053554585006e-05, + "loss": 2.1062, + "step": 1447 + }, + { + "epoch": 0.08070899058023522, + "grad_norm": 0.5067823529243469, + "learning_rate": 9.895872858331843e-05, + "loss": 1.7228, + "step": 1448 + }, + { + "epoch": 0.08076472883339836, + "grad_norm": 0.5249797105789185, + "learning_rate": 9.89569200681014e-05, + "loss": 1.8915, + "step": 1449 + }, + { + "epoch": 0.0808204670865615, + "grad_norm": 0.5042678713798523, + "learning_rate": 9.895511000025629e-05, + "loss": 1.857, + "step": 1450 + }, + { + "epoch": 0.08087620533972466, + "grad_norm": 0.5119437575340271, + "learning_rate": 9.895329837984053e-05, + "loss": 1.7033, + "step": 1451 + }, + { + "epoch": 0.0809319435928878, + "grad_norm": 0.5357143878936768, + "learning_rate": 9.895148520691155e-05, + "loss": 1.9076, + "step": 1452 + }, + { + "epoch": 0.08098768184605094, + "grad_norm": 0.47728776931762695, + "learning_rate": 9.894967048152688e-05, + "loss": 1.4164, + "step": 1453 + }, + { + "epoch": 0.08104342009921409, + "grad_norm": 0.5269622206687927, + "learning_rate": 9.894785420374405e-05, + "loss": 1.9833, + "step": 1454 + }, + { + "epoch": 0.08109915835237724, + "grad_norm": 0.5312412977218628, + "learning_rate": 9.894603637362068e-05, + "loss": 1.8342, + "step": 1455 + }, + { + "epoch": 0.08115489660554039, + "grad_norm": 0.5786725282669067, + "learning_rate": 9.894421699121439e-05, + "loss": 2.1415, + "step": 1456 + }, + { + "epoch": 0.08121063485870353, + "grad_norm": 0.4990336000919342, + "learning_rate": 9.894239605658292e-05, + "loss": 1.8387, + "step": 1457 + }, + { + "epoch": 0.08126637311186667, + "grad_norm": 0.5438005924224854, + "learning_rate": 9.8940573569784e-05, + "loss": 1.9307, + "step": 1458 + }, + { + "epoch": 0.08132211136502981, + "grad_norm": 0.5444794297218323, + "learning_rate": 9.893874953087543e-05, + "loss": 1.7991, + "step": 1459 + }, + { + "epoch": 0.08137784961819297, + "grad_norm": 0.5221540331840515, + "learning_rate": 9.893692393991504e-05, + "loss": 1.7898, + "step": 1460 + }, + { + "epoch": 0.08143358787135611, + "grad_norm": 0.509023129940033, + "learning_rate": 9.893509679696077e-05, + "loss": 1.8955, + "step": 1461 + }, + { + "epoch": 0.08148932612451926, + "grad_norm": 0.5018633008003235, + "learning_rate": 9.893326810207053e-05, + "loss": 1.6774, + "step": 1462 + }, + { + "epoch": 0.0815450643776824, + "grad_norm": 0.5234403610229492, + "learning_rate": 9.893143785530233e-05, + "loss": 1.5989, + "step": 1463 + }, + { + "epoch": 0.08160080263084554, + "grad_norm": 0.5122543573379517, + "learning_rate": 9.892960605671421e-05, + "loss": 1.6129, + "step": 1464 + }, + { + "epoch": 0.0816565408840087, + "grad_norm": 0.5005357265472412, + "learning_rate": 9.892777270636426e-05, + "loss": 1.7568, + "step": 1465 + }, + { + "epoch": 0.08171227913717184, + "grad_norm": 0.4521070420742035, + "learning_rate": 9.892593780431063e-05, + "loss": 1.5785, + "step": 1466 + }, + { + "epoch": 0.08176801739033498, + "grad_norm": 0.5116862058639526, + "learning_rate": 9.892410135061151e-05, + "loss": 1.6021, + "step": 1467 + }, + { + "epoch": 0.08182375564349813, + "grad_norm": 0.5345929861068726, + "learning_rate": 9.892226334532515e-05, + "loss": 1.7185, + "step": 1468 + }, + { + "epoch": 0.08187949389666128, + "grad_norm": 0.5190909504890442, + "learning_rate": 9.892042378850983e-05, + "loss": 1.7729, + "step": 1469 + }, + { + "epoch": 0.08193523214982443, + "grad_norm": 0.5051796436309814, + "learning_rate": 9.89185826802239e-05, + "loss": 1.7497, + "step": 1470 + }, + { + "epoch": 0.08199097040298757, + "grad_norm": 0.49057456851005554, + "learning_rate": 9.891674002052572e-05, + "loss": 1.7032, + "step": 1471 + }, + { + "epoch": 0.08204670865615071, + "grad_norm": 0.48970887064933777, + "learning_rate": 9.891489580947377e-05, + "loss": 1.697, + "step": 1472 + }, + { + "epoch": 0.08210244690931386, + "grad_norm": 0.466226726770401, + "learning_rate": 9.891305004712652e-05, + "loss": 1.676, + "step": 1473 + }, + { + "epoch": 0.08215818516247701, + "grad_norm": 0.5120090246200562, + "learning_rate": 9.891120273354248e-05, + "loss": 1.7862, + "step": 1474 + }, + { + "epoch": 0.08221392341564016, + "grad_norm": 0.5071076154708862, + "learning_rate": 9.890935386878029e-05, + "loss": 1.7835, + "step": 1475 + }, + { + "epoch": 0.0822696616688033, + "grad_norm": 0.5432698726654053, + "learning_rate": 9.890750345289855e-05, + "loss": 1.9147, + "step": 1476 + }, + { + "epoch": 0.08232539992196644, + "grad_norm": 0.5131239295005798, + "learning_rate": 9.890565148595594e-05, + "loss": 1.9944, + "step": 1477 + }, + { + "epoch": 0.0823811381751296, + "grad_norm": 0.49580785632133484, + "learning_rate": 9.890379796801122e-05, + "loss": 1.7003, + "step": 1478 + }, + { + "epoch": 0.08243687642829274, + "grad_norm": 0.5251078605651855, + "learning_rate": 9.890194289912315e-05, + "loss": 1.5901, + "step": 1479 + }, + { + "epoch": 0.08249261468145588, + "grad_norm": 0.4522892236709595, + "learning_rate": 9.890008627935057e-05, + "loss": 1.4628, + "step": 1480 + }, + { + "epoch": 0.08254835293461903, + "grad_norm": 0.49866771697998047, + "learning_rate": 9.889822810875236e-05, + "loss": 1.797, + "step": 1481 + }, + { + "epoch": 0.08260409118778217, + "grad_norm": 0.5042446851730347, + "learning_rate": 9.889636838738745e-05, + "loss": 1.7715, + "step": 1482 + }, + { + "epoch": 0.08265982944094533, + "grad_norm": 0.5398827791213989, + "learning_rate": 9.889450711531482e-05, + "loss": 1.7935, + "step": 1483 + }, + { + "epoch": 0.08271556769410847, + "grad_norm": 0.5085358023643494, + "learning_rate": 9.889264429259351e-05, + "loss": 1.7009, + "step": 1484 + }, + { + "epoch": 0.08277130594727161, + "grad_norm": 0.5344458222389221, + "learning_rate": 9.889077991928257e-05, + "loss": 1.9159, + "step": 1485 + }, + { + "epoch": 0.08282704420043475, + "grad_norm": 0.5375879406929016, + "learning_rate": 9.888891399544116e-05, + "loss": 1.8089, + "step": 1486 + }, + { + "epoch": 0.0828827824535979, + "grad_norm": 0.5068013668060303, + "learning_rate": 9.888704652112841e-05, + "loss": 1.81, + "step": 1487 + }, + { + "epoch": 0.08293852070676105, + "grad_norm": 0.5293126106262207, + "learning_rate": 9.88851774964036e-05, + "loss": 1.8359, + "step": 1488 + }, + { + "epoch": 0.0829942589599242, + "grad_norm": 0.538372814655304, + "learning_rate": 9.8883306921326e-05, + "loss": 1.7542, + "step": 1489 + }, + { + "epoch": 0.08304999721308734, + "grad_norm": 0.5009732246398926, + "learning_rate": 9.888143479595487e-05, + "loss": 1.761, + "step": 1490 + }, + { + "epoch": 0.08310573546625048, + "grad_norm": 0.5073357820510864, + "learning_rate": 9.887956112034965e-05, + "loss": 1.961, + "step": 1491 + }, + { + "epoch": 0.08316147371941364, + "grad_norm": 0.5246378779411316, + "learning_rate": 9.887768589456973e-05, + "loss": 1.6075, + "step": 1492 + }, + { + "epoch": 0.08321721197257678, + "grad_norm": 0.5965234637260437, + "learning_rate": 9.88758091186746e-05, + "loss": 1.7721, + "step": 1493 + }, + { + "epoch": 0.08327295022573993, + "grad_norm": 0.580460250377655, + "learning_rate": 9.887393079272378e-05, + "loss": 2.0317, + "step": 1494 + }, + { + "epoch": 0.08332868847890307, + "grad_norm": 0.47487667202949524, + "learning_rate": 9.88720509167768e-05, + "loss": 1.614, + "step": 1495 + }, + { + "epoch": 0.08338442673206621, + "grad_norm": 0.511886715888977, + "learning_rate": 9.887016949089333e-05, + "loss": 1.7988, + "step": 1496 + }, + { + "epoch": 0.08344016498522937, + "grad_norm": 0.5386150479316711, + "learning_rate": 9.886828651513302e-05, + "loss": 1.6694, + "step": 1497 + }, + { + "epoch": 0.08349590323839251, + "grad_norm": 0.5117900967597961, + "learning_rate": 9.886640198955557e-05, + "loss": 1.9023, + "step": 1498 + }, + { + "epoch": 0.08355164149155565, + "grad_norm": 0.5726772546768188, + "learning_rate": 9.886451591422076e-05, + "loss": 1.8974, + "step": 1499 + }, + { + "epoch": 0.0836073797447188, + "grad_norm": 0.5696210861206055, + "learning_rate": 9.886262828918842e-05, + "loss": 2.011, + "step": 1500 + }, + { + "epoch": 0.08366311799788195, + "grad_norm": 0.5422051548957825, + "learning_rate": 9.886073911451838e-05, + "loss": 1.853, + "step": 1501 + }, + { + "epoch": 0.0837188562510451, + "grad_norm": 0.5856989622116089, + "learning_rate": 9.88588483902706e-05, + "loss": 2.0279, + "step": 1502 + }, + { + "epoch": 0.08377459450420824, + "grad_norm": 0.49369946122169495, + "learning_rate": 9.8856956116505e-05, + "loss": 1.9006, + "step": 1503 + }, + { + "epoch": 0.08383033275737138, + "grad_norm": 0.5601094961166382, + "learning_rate": 9.88550622932816e-05, + "loss": 1.8549, + "step": 1504 + }, + { + "epoch": 0.08388607101053452, + "grad_norm": 0.5482882857322693, + "learning_rate": 9.885316692066048e-05, + "loss": 1.6991, + "step": 1505 + }, + { + "epoch": 0.08394180926369768, + "grad_norm": 0.5111584663391113, + "learning_rate": 9.885126999870173e-05, + "loss": 1.7942, + "step": 1506 + }, + { + "epoch": 0.08399754751686082, + "grad_norm": 0.5061234831809998, + "learning_rate": 9.884937152746553e-05, + "loss": 1.7333, + "step": 1507 + }, + { + "epoch": 0.08405328577002397, + "grad_norm": 0.5409541726112366, + "learning_rate": 9.884747150701207e-05, + "loss": 1.8288, + "step": 1508 + }, + { + "epoch": 0.08410902402318711, + "grad_norm": 0.5025638341903687, + "learning_rate": 9.884556993740161e-05, + "loss": 1.7986, + "step": 1509 + }, + { + "epoch": 0.08416476227635025, + "grad_norm": 0.544328510761261, + "learning_rate": 9.884366681869447e-05, + "loss": 1.9335, + "step": 1510 + }, + { + "epoch": 0.08422050052951341, + "grad_norm": 0.5425384640693665, + "learning_rate": 9.8841762150951e-05, + "loss": 1.952, + "step": 1511 + }, + { + "epoch": 0.08427623878267655, + "grad_norm": 0.546819269657135, + "learning_rate": 9.883985593423158e-05, + "loss": 1.6983, + "step": 1512 + }, + { + "epoch": 0.0843319770358397, + "grad_norm": 0.5102137327194214, + "learning_rate": 9.88379481685967e-05, + "loss": 1.9128, + "step": 1513 + }, + { + "epoch": 0.08438771528900284, + "grad_norm": 0.5642107725143433, + "learning_rate": 9.883603885410686e-05, + "loss": 1.8798, + "step": 1514 + }, + { + "epoch": 0.084443453542166, + "grad_norm": 0.5285095572471619, + "learning_rate": 9.88341279908226e-05, + "loss": 1.987, + "step": 1515 + }, + { + "epoch": 0.08449919179532914, + "grad_norm": 0.5712692737579346, + "learning_rate": 9.88322155788045e-05, + "loss": 1.9272, + "step": 1516 + }, + { + "epoch": 0.08455493004849228, + "grad_norm": 0.5068216919898987, + "learning_rate": 9.883030161811324e-05, + "loss": 1.747, + "step": 1517 + }, + { + "epoch": 0.08461066830165542, + "grad_norm": 0.5292205810546875, + "learning_rate": 9.882838610880954e-05, + "loss": 1.7361, + "step": 1518 + }, + { + "epoch": 0.08466640655481857, + "grad_norm": 0.5131486654281616, + "learning_rate": 9.88264690509541e-05, + "loss": 1.7197, + "step": 1519 + }, + { + "epoch": 0.08472214480798172, + "grad_norm": 0.5345507860183716, + "learning_rate": 9.882455044460773e-05, + "loss": 1.6553, + "step": 1520 + }, + { + "epoch": 0.08477788306114487, + "grad_norm": 0.5729446411132812, + "learning_rate": 9.88226302898313e-05, + "loss": 1.9354, + "step": 1521 + }, + { + "epoch": 0.08483362131430801, + "grad_norm": 0.5425586700439453, + "learning_rate": 9.882070858668568e-05, + "loss": 1.7173, + "step": 1522 + }, + { + "epoch": 0.08488935956747115, + "grad_norm": 0.5828628540039062, + "learning_rate": 9.881878533523185e-05, + "loss": 1.5161, + "step": 1523 + }, + { + "epoch": 0.08494509782063431, + "grad_norm": 0.4496408998966217, + "learning_rate": 9.881686053553077e-05, + "loss": 1.4486, + "step": 1524 + }, + { + "epoch": 0.08500083607379745, + "grad_norm": 0.5365184545516968, + "learning_rate": 9.88149341876435e-05, + "loss": 1.7378, + "step": 1525 + }, + { + "epoch": 0.0850565743269606, + "grad_norm": 0.5183097720146179, + "learning_rate": 9.881300629163113e-05, + "loss": 1.7466, + "step": 1526 + }, + { + "epoch": 0.08511231258012374, + "grad_norm": 0.5500345826148987, + "learning_rate": 9.88110768475548e-05, + "loss": 2.05, + "step": 1527 + }, + { + "epoch": 0.08516805083328688, + "grad_norm": 0.5311182141304016, + "learning_rate": 9.88091458554757e-05, + "loss": 1.9213, + "step": 1528 + }, + { + "epoch": 0.08522378908645004, + "grad_norm": 0.5297403335571289, + "learning_rate": 9.880721331545507e-05, + "loss": 1.7725, + "step": 1529 + }, + { + "epoch": 0.08527952733961318, + "grad_norm": 0.4777231514453888, + "learning_rate": 9.880527922755418e-05, + "loss": 1.7671, + "step": 1530 + }, + { + "epoch": 0.08533526559277632, + "grad_norm": 0.5027580261230469, + "learning_rate": 9.880334359183441e-05, + "loss": 1.5094, + "step": 1531 + }, + { + "epoch": 0.08539100384593946, + "grad_norm": 0.5496742725372314, + "learning_rate": 9.880140640835711e-05, + "loss": 1.8291, + "step": 1532 + }, + { + "epoch": 0.08544674209910261, + "grad_norm": 0.5041139721870422, + "learning_rate": 9.879946767718374e-05, + "loss": 1.6669, + "step": 1533 + }, + { + "epoch": 0.08550248035226576, + "grad_norm": 0.5976061820983887, + "learning_rate": 9.879752739837578e-05, + "loss": 2.1902, + "step": 1534 + }, + { + "epoch": 0.0855582186054289, + "grad_norm": 0.5422946810722351, + "learning_rate": 9.879558557199475e-05, + "loss": 1.5727, + "step": 1535 + }, + { + "epoch": 0.08561395685859205, + "grad_norm": 0.4999959170818329, + "learning_rate": 9.879364219810226e-05, + "loss": 1.6102, + "step": 1536 + }, + { + "epoch": 0.08566969511175519, + "grad_norm": 0.5026562213897705, + "learning_rate": 9.879169727675991e-05, + "loss": 1.7124, + "step": 1537 + }, + { + "epoch": 0.08572543336491835, + "grad_norm": 0.5175659656524658, + "learning_rate": 9.87897508080294e-05, + "loss": 1.7585, + "step": 1538 + }, + { + "epoch": 0.08578117161808149, + "grad_norm": 0.5337525010108948, + "learning_rate": 9.878780279197247e-05, + "loss": 1.7857, + "step": 1539 + }, + { + "epoch": 0.08583690987124463, + "grad_norm": 0.5325166583061218, + "learning_rate": 9.878585322865087e-05, + "loss": 1.865, + "step": 1540 + }, + { + "epoch": 0.08589264812440778, + "grad_norm": 0.46590784192085266, + "learning_rate": 9.878390211812646e-05, + "loss": 1.627, + "step": 1541 + }, + { + "epoch": 0.08594838637757092, + "grad_norm": 0.4856724441051483, + "learning_rate": 9.87819494604611e-05, + "loss": 1.7221, + "step": 1542 + }, + { + "epoch": 0.08600412463073408, + "grad_norm": 0.5396975874900818, + "learning_rate": 9.877999525571673e-05, + "loss": 1.7696, + "step": 1543 + }, + { + "epoch": 0.08605986288389722, + "grad_norm": 0.49516481161117554, + "learning_rate": 9.87780395039553e-05, + "loss": 1.6928, + "step": 1544 + }, + { + "epoch": 0.08611560113706036, + "grad_norm": 0.5212313532829285, + "learning_rate": 9.877608220523886e-05, + "loss": 1.8461, + "step": 1545 + }, + { + "epoch": 0.0861713393902235, + "grad_norm": 0.5174347162246704, + "learning_rate": 9.877412335962948e-05, + "loss": 1.6598, + "step": 1546 + }, + { + "epoch": 0.08622707764338666, + "grad_norm": 0.5417358875274658, + "learning_rate": 9.877216296718929e-05, + "loss": 1.8449, + "step": 1547 + }, + { + "epoch": 0.0862828158965498, + "grad_norm": 0.6204573512077332, + "learning_rate": 9.877020102798044e-05, + "loss": 2.0521, + "step": 1548 + }, + { + "epoch": 0.08633855414971295, + "grad_norm": 0.548689067363739, + "learning_rate": 9.876823754206517e-05, + "loss": 1.8019, + "step": 1549 + }, + { + "epoch": 0.08639429240287609, + "grad_norm": 0.5634471774101257, + "learning_rate": 9.876627250950573e-05, + "loss": 1.9138, + "step": 1550 + }, + { + "epoch": 0.08645003065603923, + "grad_norm": 0.517440915107727, + "learning_rate": 9.876430593036445e-05, + "loss": 1.6576, + "step": 1551 + }, + { + "epoch": 0.08650576890920239, + "grad_norm": 0.5255969762802124, + "learning_rate": 9.876233780470373e-05, + "loss": 1.9165, + "step": 1552 + }, + { + "epoch": 0.08656150716236553, + "grad_norm": 0.5497751235961914, + "learning_rate": 9.876036813258593e-05, + "loss": 1.7924, + "step": 1553 + }, + { + "epoch": 0.08661724541552868, + "grad_norm": 0.49066075682640076, + "learning_rate": 9.875839691407355e-05, + "loss": 1.7025, + "step": 1554 + }, + { + "epoch": 0.08667298366869182, + "grad_norm": 0.5411027669906616, + "learning_rate": 9.875642414922913e-05, + "loss": 1.7742, + "step": 1555 + }, + { + "epoch": 0.08672872192185498, + "grad_norm": 0.5388767123222351, + "learning_rate": 9.875444983811517e-05, + "loss": 1.7676, + "step": 1556 + }, + { + "epoch": 0.08678446017501812, + "grad_norm": 0.540668249130249, + "learning_rate": 9.875247398079434e-05, + "loss": 1.7824, + "step": 1557 + }, + { + "epoch": 0.08684019842818126, + "grad_norm": 0.4785401523113251, + "learning_rate": 9.875049657732928e-05, + "loss": 1.5643, + "step": 1558 + }, + { + "epoch": 0.0868959366813444, + "grad_norm": 0.4758340120315552, + "learning_rate": 9.87485176277827e-05, + "loss": 1.7751, + "step": 1559 + }, + { + "epoch": 0.08695167493450755, + "grad_norm": 0.5260589122772217, + "learning_rate": 9.874653713221736e-05, + "loss": 1.6758, + "step": 1560 + }, + { + "epoch": 0.0870074131876707, + "grad_norm": 0.5716840624809265, + "learning_rate": 9.874455509069608e-05, + "loss": 1.9237, + "step": 1561 + }, + { + "epoch": 0.08706315144083385, + "grad_norm": 0.5434233546257019, + "learning_rate": 9.874257150328171e-05, + "loss": 1.8882, + "step": 1562 + }, + { + "epoch": 0.08711888969399699, + "grad_norm": 0.562435507774353, + "learning_rate": 9.874058637003715e-05, + "loss": 2.0451, + "step": 1563 + }, + { + "epoch": 0.08717462794716013, + "grad_norm": 0.5642979741096497, + "learning_rate": 9.87385996910254e-05, + "loss": 1.924, + "step": 1564 + }, + { + "epoch": 0.08723036620032328, + "grad_norm": 0.5052669048309326, + "learning_rate": 9.87366114663094e-05, + "loss": 1.58, + "step": 1565 + }, + { + "epoch": 0.08728610445348643, + "grad_norm": 0.5220628380775452, + "learning_rate": 9.873462169595225e-05, + "loss": 1.7895, + "step": 1566 + }, + { + "epoch": 0.08734184270664958, + "grad_norm": 0.517431378364563, + "learning_rate": 9.873263038001706e-05, + "loss": 1.6593, + "step": 1567 + }, + { + "epoch": 0.08739758095981272, + "grad_norm": 0.5140258073806763, + "learning_rate": 9.873063751856693e-05, + "loss": 1.8271, + "step": 1568 + }, + { + "epoch": 0.08745331921297586, + "grad_norm": 0.4922142028808594, + "learning_rate": 9.872864311166513e-05, + "loss": 1.6083, + "step": 1569 + }, + { + "epoch": 0.08750905746613902, + "grad_norm": 0.5390502214431763, + "learning_rate": 9.872664715937485e-05, + "loss": 1.4434, + "step": 1570 + }, + { + "epoch": 0.08756479571930216, + "grad_norm": 0.5033831596374512, + "learning_rate": 9.872464966175943e-05, + "loss": 1.7666, + "step": 1571 + }, + { + "epoch": 0.0876205339724653, + "grad_norm": 0.5968888401985168, + "learning_rate": 9.872265061888222e-05, + "loss": 2.129, + "step": 1572 + }, + { + "epoch": 0.08767627222562845, + "grad_norm": 0.4963712990283966, + "learning_rate": 9.87206500308066e-05, + "loss": 1.757, + "step": 1573 + }, + { + "epoch": 0.08773201047879159, + "grad_norm": 0.561555802822113, + "learning_rate": 9.871864789759602e-05, + "loss": 1.8953, + "step": 1574 + }, + { + "epoch": 0.08778774873195475, + "grad_norm": 0.5095016956329346, + "learning_rate": 9.871664421931397e-05, + "loss": 1.5125, + "step": 1575 + }, + { + "epoch": 0.08784348698511789, + "grad_norm": 0.5717408061027527, + "learning_rate": 9.8714638996024e-05, + "loss": 1.9326, + "step": 1576 + }, + { + "epoch": 0.08789922523828103, + "grad_norm": 0.5086256861686707, + "learning_rate": 9.871263222778972e-05, + "loss": 1.4956, + "step": 1577 + }, + { + "epoch": 0.08795496349144417, + "grad_norm": 0.5559898614883423, + "learning_rate": 9.871062391467476e-05, + "loss": 2.0481, + "step": 1578 + }, + { + "epoch": 0.08801070174460733, + "grad_norm": 0.511561930179596, + "learning_rate": 9.870861405674281e-05, + "loss": 1.6748, + "step": 1579 + }, + { + "epoch": 0.08806643999777047, + "grad_norm": 0.46475693583488464, + "learning_rate": 9.87066026540576e-05, + "loss": 1.5146, + "step": 1580 + }, + { + "epoch": 0.08812217825093362, + "grad_norm": 0.619973361492157, + "learning_rate": 9.870458970668295e-05, + "loss": 1.9752, + "step": 1581 + }, + { + "epoch": 0.08817791650409676, + "grad_norm": 0.5257066488265991, + "learning_rate": 9.870257521468267e-05, + "loss": 1.8943, + "step": 1582 + }, + { + "epoch": 0.0882336547572599, + "grad_norm": 0.48758870363235474, + "learning_rate": 9.870055917812066e-05, + "loss": 1.7243, + "step": 1583 + }, + { + "epoch": 0.08828939301042306, + "grad_norm": 0.500957190990448, + "learning_rate": 9.869854159706087e-05, + "loss": 1.608, + "step": 1584 + }, + { + "epoch": 0.0883451312635862, + "grad_norm": 0.5307281613349915, + "learning_rate": 9.869652247156726e-05, + "loss": 1.8326, + "step": 1585 + }, + { + "epoch": 0.08840086951674934, + "grad_norm": 0.5321508049964905, + "learning_rate": 9.869450180170388e-05, + "loss": 1.5715, + "step": 1586 + }, + { + "epoch": 0.08845660776991249, + "grad_norm": 0.512824296951294, + "learning_rate": 9.869247958753483e-05, + "loss": 1.9452, + "step": 1587 + }, + { + "epoch": 0.08851234602307563, + "grad_norm": 0.5297205448150635, + "learning_rate": 9.86904558291242e-05, + "loss": 1.7894, + "step": 1588 + }, + { + "epoch": 0.08856808427623879, + "grad_norm": 0.5388361215591431, + "learning_rate": 9.86884305265362e-05, + "loss": 1.8428, + "step": 1589 + }, + { + "epoch": 0.08862382252940193, + "grad_norm": 0.5642775297164917, + "learning_rate": 9.868640367983507e-05, + "loss": 1.9602, + "step": 1590 + }, + { + "epoch": 0.08867956078256507, + "grad_norm": 0.5613628029823303, + "learning_rate": 9.868437528908507e-05, + "loss": 1.8967, + "step": 1591 + }, + { + "epoch": 0.08873529903572822, + "grad_norm": 0.4843713641166687, + "learning_rate": 9.868234535435052e-05, + "loss": 1.5939, + "step": 1592 + }, + { + "epoch": 0.08879103728889137, + "grad_norm": 0.5549110770225525, + "learning_rate": 9.868031387569583e-05, + "loss": 1.7461, + "step": 1593 + }, + { + "epoch": 0.08884677554205452, + "grad_norm": 0.5344760417938232, + "learning_rate": 9.867828085318541e-05, + "loss": 1.7843, + "step": 1594 + }, + { + "epoch": 0.08890251379521766, + "grad_norm": 0.49532350897789, + "learning_rate": 9.867624628688374e-05, + "loss": 1.981, + "step": 1595 + }, + { + "epoch": 0.0889582520483808, + "grad_norm": 0.48208191990852356, + "learning_rate": 9.867421017685531e-05, + "loss": 1.3437, + "step": 1596 + }, + { + "epoch": 0.08901399030154394, + "grad_norm": 0.489444762468338, + "learning_rate": 9.867217252316476e-05, + "loss": 1.6426, + "step": 1597 + }, + { + "epoch": 0.0890697285547071, + "grad_norm": 0.5148588418960571, + "learning_rate": 9.867013332587667e-05, + "loss": 1.5808, + "step": 1598 + }, + { + "epoch": 0.08912546680787024, + "grad_norm": 0.5365609526634216, + "learning_rate": 9.86680925850557e-05, + "loss": 1.8197, + "step": 1599 + }, + { + "epoch": 0.08918120506103339, + "grad_norm": 0.48567450046539307, + "learning_rate": 9.86660503007666e-05, + "loss": 1.6238, + "step": 1600 + }, + { + "epoch": 0.08923694331419653, + "grad_norm": 0.515129029750824, + "learning_rate": 9.866400647307413e-05, + "loss": 1.8063, + "step": 1601 + }, + { + "epoch": 0.08929268156735969, + "grad_norm": 0.5591225028038025, + "learning_rate": 9.86619611020431e-05, + "loss": 1.8849, + "step": 1602 + }, + { + "epoch": 0.08934841982052283, + "grad_norm": 0.4950789213180542, + "learning_rate": 9.865991418773837e-05, + "loss": 1.5961, + "step": 1603 + }, + { + "epoch": 0.08940415807368597, + "grad_norm": 0.5623775124549866, + "learning_rate": 9.865786573022488e-05, + "loss": 1.782, + "step": 1604 + }, + { + "epoch": 0.08945989632684911, + "grad_norm": 0.5508179664611816, + "learning_rate": 9.865581572956759e-05, + "loss": 1.9102, + "step": 1605 + }, + { + "epoch": 0.08951563458001226, + "grad_norm": 0.5296784043312073, + "learning_rate": 9.86537641858315e-05, + "loss": 1.8494, + "step": 1606 + }, + { + "epoch": 0.08957137283317541, + "grad_norm": 0.5068146586418152, + "learning_rate": 9.865171109908169e-05, + "loss": 1.7515, + "step": 1607 + }, + { + "epoch": 0.08962711108633856, + "grad_norm": 0.5015462636947632, + "learning_rate": 9.864965646938326e-05, + "loss": 1.6874, + "step": 1608 + }, + { + "epoch": 0.0896828493395017, + "grad_norm": 0.5293746590614319, + "learning_rate": 9.864760029680137e-05, + "loss": 1.7417, + "step": 1609 + }, + { + "epoch": 0.08973858759266484, + "grad_norm": 0.5211681127548218, + "learning_rate": 9.864554258140124e-05, + "loss": 1.7553, + "step": 1610 + }, + { + "epoch": 0.08979432584582799, + "grad_norm": 0.7411361336708069, + "learning_rate": 9.864348332324811e-05, + "loss": 1.7663, + "step": 1611 + }, + { + "epoch": 0.08985006409899114, + "grad_norm": 0.4988972842693329, + "learning_rate": 9.864142252240731e-05, + "loss": 1.6, + "step": 1612 + }, + { + "epoch": 0.08990580235215428, + "grad_norm": 0.5340063571929932, + "learning_rate": 9.863936017894418e-05, + "loss": 1.8076, + "step": 1613 + }, + { + "epoch": 0.08996154060531743, + "grad_norm": 0.5994722247123718, + "learning_rate": 9.863729629292414e-05, + "loss": 1.7864, + "step": 1614 + }, + { + "epoch": 0.09001727885848057, + "grad_norm": 0.541131854057312, + "learning_rate": 9.863523086441264e-05, + "loss": 1.931, + "step": 1615 + }, + { + "epoch": 0.09007301711164373, + "grad_norm": 0.5259929299354553, + "learning_rate": 9.863316389347517e-05, + "loss": 1.7562, + "step": 1616 + }, + { + "epoch": 0.09012875536480687, + "grad_norm": 0.5242890119552612, + "learning_rate": 9.863109538017729e-05, + "loss": 1.6973, + "step": 1617 + }, + { + "epoch": 0.09018449361797001, + "grad_norm": 0.5834923386573792, + "learning_rate": 9.862902532458461e-05, + "loss": 2.0494, + "step": 1618 + }, + { + "epoch": 0.09024023187113316, + "grad_norm": 0.4912288188934326, + "learning_rate": 9.862695372676278e-05, + "loss": 1.6505, + "step": 1619 + }, + { + "epoch": 0.0902959701242963, + "grad_norm": 0.5288010239601135, + "learning_rate": 9.862488058677748e-05, + "loss": 1.734, + "step": 1620 + }, + { + "epoch": 0.09035170837745946, + "grad_norm": 0.5029554963111877, + "learning_rate": 9.862280590469448e-05, + "loss": 1.8098, + "step": 1621 + }, + { + "epoch": 0.0904074466306226, + "grad_norm": 0.531711995601654, + "learning_rate": 9.862072968057956e-05, + "loss": 1.8394, + "step": 1622 + }, + { + "epoch": 0.09046318488378574, + "grad_norm": 0.4818442165851593, + "learning_rate": 9.861865191449858e-05, + "loss": 1.6742, + "step": 1623 + }, + { + "epoch": 0.09051892313694888, + "grad_norm": 0.4834239184856415, + "learning_rate": 9.861657260651742e-05, + "loss": 1.6425, + "step": 1624 + }, + { + "epoch": 0.09057466139011204, + "grad_norm": 0.4923589825630188, + "learning_rate": 9.861449175670204e-05, + "loss": 1.5693, + "step": 1625 + }, + { + "epoch": 0.09063039964327518, + "grad_norm": 0.48194825649261475, + "learning_rate": 9.861240936511842e-05, + "loss": 1.6782, + "step": 1626 + }, + { + "epoch": 0.09068613789643833, + "grad_norm": 0.5542406439781189, + "learning_rate": 9.86103254318326e-05, + "loss": 1.9775, + "step": 1627 + }, + { + "epoch": 0.09074187614960147, + "grad_norm": 0.6013079881668091, + "learning_rate": 9.860823995691068e-05, + "loss": 1.9425, + "step": 1628 + }, + { + "epoch": 0.09079761440276461, + "grad_norm": 0.5376304984092712, + "learning_rate": 9.860615294041879e-05, + "loss": 1.6473, + "step": 1629 + }, + { + "epoch": 0.09085335265592777, + "grad_norm": 0.5485152006149292, + "learning_rate": 9.860406438242313e-05, + "loss": 1.6367, + "step": 1630 + }, + { + "epoch": 0.09090909090909091, + "grad_norm": 0.5142073035240173, + "learning_rate": 9.860197428298991e-05, + "loss": 1.7602, + "step": 1631 + }, + { + "epoch": 0.09096482916225405, + "grad_norm": 0.49521228671073914, + "learning_rate": 9.859988264218546e-05, + "loss": 1.546, + "step": 1632 + }, + { + "epoch": 0.0910205674154172, + "grad_norm": 0.5011737942695618, + "learning_rate": 9.859778946007608e-05, + "loss": 1.5578, + "step": 1633 + }, + { + "epoch": 0.09107630566858034, + "grad_norm": 0.4523265063762665, + "learning_rate": 9.859569473672816e-05, + "loss": 1.3888, + "step": 1634 + }, + { + "epoch": 0.0911320439217435, + "grad_norm": 0.48054036498069763, + "learning_rate": 9.859359847220815e-05, + "loss": 1.7516, + "step": 1635 + }, + { + "epoch": 0.09118778217490664, + "grad_norm": 0.5349341034889221, + "learning_rate": 9.85915006665825e-05, + "loss": 1.7055, + "step": 1636 + }, + { + "epoch": 0.09124352042806978, + "grad_norm": 0.5274312496185303, + "learning_rate": 9.858940131991777e-05, + "loss": 1.8203, + "step": 1637 + }, + { + "epoch": 0.09129925868123293, + "grad_norm": 0.4654419720172882, + "learning_rate": 9.85873004322805e-05, + "loss": 1.5783, + "step": 1638 + }, + { + "epoch": 0.09135499693439608, + "grad_norm": 0.5258073806762695, + "learning_rate": 9.858519800373738e-05, + "loss": 1.7707, + "step": 1639 + }, + { + "epoch": 0.09141073518755923, + "grad_norm": 0.4929850995540619, + "learning_rate": 9.858309403435501e-05, + "loss": 1.6027, + "step": 1640 + }, + { + "epoch": 0.09146647344072237, + "grad_norm": 0.5121711492538452, + "learning_rate": 9.85809885242002e-05, + "loss": 1.7874, + "step": 1641 + }, + { + "epoch": 0.09152221169388551, + "grad_norm": 0.4955439567565918, + "learning_rate": 9.857888147333965e-05, + "loss": 1.7223, + "step": 1642 + }, + { + "epoch": 0.09157794994704865, + "grad_norm": 0.519477903842926, + "learning_rate": 9.857677288184022e-05, + "loss": 1.8618, + "step": 1643 + }, + { + "epoch": 0.09163368820021181, + "grad_norm": 0.5247395038604736, + "learning_rate": 9.857466274976878e-05, + "loss": 1.761, + "step": 1644 + }, + { + "epoch": 0.09168942645337495, + "grad_norm": 0.4881756901741028, + "learning_rate": 9.857255107719225e-05, + "loss": 1.7272, + "step": 1645 + }, + { + "epoch": 0.0917451647065381, + "grad_norm": 0.5688063502311707, + "learning_rate": 9.857043786417759e-05, + "loss": 1.7532, + "step": 1646 + }, + { + "epoch": 0.09180090295970124, + "grad_norm": 0.531910240650177, + "learning_rate": 9.856832311079183e-05, + "loss": 1.9235, + "step": 1647 + }, + { + "epoch": 0.0918566412128644, + "grad_norm": 0.5271464586257935, + "learning_rate": 9.856620681710205e-05, + "loss": 1.8481, + "step": 1648 + }, + { + "epoch": 0.09191237946602754, + "grad_norm": 0.5019913911819458, + "learning_rate": 9.856408898317533e-05, + "loss": 1.7273, + "step": 1649 + }, + { + "epoch": 0.09196811771919068, + "grad_norm": 0.5375306010246277, + "learning_rate": 9.856196960907887e-05, + "loss": 1.8292, + "step": 1650 + }, + { + "epoch": 0.09202385597235382, + "grad_norm": 0.551287829875946, + "learning_rate": 9.855984869487985e-05, + "loss": 1.7672, + "step": 1651 + }, + { + "epoch": 0.09207959422551697, + "grad_norm": 0.5110806226730347, + "learning_rate": 9.855772624064557e-05, + "loss": 1.7338, + "step": 1652 + }, + { + "epoch": 0.09213533247868012, + "grad_norm": 0.5807773470878601, + "learning_rate": 9.855560224644332e-05, + "loss": 1.8558, + "step": 1653 + }, + { + "epoch": 0.09219107073184327, + "grad_norm": 0.5399064421653748, + "learning_rate": 9.855347671234045e-05, + "loss": 1.7338, + "step": 1654 + }, + { + "epoch": 0.09224680898500641, + "grad_norm": 0.5670611262321472, + "learning_rate": 9.855134963840441e-05, + "loss": 1.9314, + "step": 1655 + }, + { + "epoch": 0.09230254723816955, + "grad_norm": 0.49795302748680115, + "learning_rate": 9.854922102470262e-05, + "loss": 1.7196, + "step": 1656 + }, + { + "epoch": 0.0923582854913327, + "grad_norm": 0.5752295255661011, + "learning_rate": 9.85470908713026e-05, + "loss": 1.7249, + "step": 1657 + }, + { + "epoch": 0.09241402374449585, + "grad_norm": 0.4967830181121826, + "learning_rate": 9.854495917827191e-05, + "loss": 1.7368, + "step": 1658 + }, + { + "epoch": 0.092469761997659, + "grad_norm": 0.4957406520843506, + "learning_rate": 9.854282594567816e-05, + "loss": 1.8287, + "step": 1659 + }, + { + "epoch": 0.09252550025082214, + "grad_norm": 0.49035385251045227, + "learning_rate": 9.854069117358899e-05, + "loss": 1.743, + "step": 1660 + }, + { + "epoch": 0.09258123850398528, + "grad_norm": 0.5366220474243164, + "learning_rate": 9.853855486207211e-05, + "loss": 1.7903, + "step": 1661 + }, + { + "epoch": 0.09263697675714844, + "grad_norm": 0.5238292217254639, + "learning_rate": 9.853641701119525e-05, + "loss": 1.6038, + "step": 1662 + }, + { + "epoch": 0.09269271501031158, + "grad_norm": 0.507854700088501, + "learning_rate": 9.853427762102625e-05, + "loss": 1.7459, + "step": 1663 + }, + { + "epoch": 0.09274845326347472, + "grad_norm": 0.5182837247848511, + "learning_rate": 9.853213669163293e-05, + "loss": 1.7409, + "step": 1664 + }, + { + "epoch": 0.09280419151663787, + "grad_norm": 0.5023046135902405, + "learning_rate": 9.852999422308319e-05, + "loss": 1.8207, + "step": 1665 + }, + { + "epoch": 0.09285992976980101, + "grad_norm": 0.6185427308082581, + "learning_rate": 9.852785021544499e-05, + "loss": 1.9794, + "step": 1666 + }, + { + "epoch": 0.09291566802296417, + "grad_norm": 0.5567124485969543, + "learning_rate": 9.852570466878632e-05, + "loss": 1.8052, + "step": 1667 + }, + { + "epoch": 0.09297140627612731, + "grad_norm": 0.5299728512763977, + "learning_rate": 9.852355758317523e-05, + "loss": 1.6414, + "step": 1668 + }, + { + "epoch": 0.09302714452929045, + "grad_norm": 0.47446316480636597, + "learning_rate": 9.85214089586798e-05, + "loss": 1.561, + "step": 1669 + }, + { + "epoch": 0.0930828827824536, + "grad_norm": 0.5260158181190491, + "learning_rate": 9.851925879536817e-05, + "loss": 1.7192, + "step": 1670 + }, + { + "epoch": 0.09313862103561675, + "grad_norm": 0.5200673341751099, + "learning_rate": 9.851710709330855e-05, + "loss": 1.6869, + "step": 1671 + }, + { + "epoch": 0.0931943592887799, + "grad_norm": 0.5707138180732727, + "learning_rate": 9.851495385256915e-05, + "loss": 1.7307, + "step": 1672 + }, + { + "epoch": 0.09325009754194304, + "grad_norm": 0.6008026003837585, + "learning_rate": 9.851279907321829e-05, + "loss": 1.8593, + "step": 1673 + }, + { + "epoch": 0.09330583579510618, + "grad_norm": 0.4921055734157562, + "learning_rate": 9.851064275532428e-05, + "loss": 1.7155, + "step": 1674 + }, + { + "epoch": 0.09336157404826932, + "grad_norm": 0.48389917612075806, + "learning_rate": 9.850848489895553e-05, + "loss": 1.7011, + "step": 1675 + }, + { + "epoch": 0.09341731230143248, + "grad_norm": 0.6712982058525085, + "learning_rate": 9.850632550418046e-05, + "loss": 1.8851, + "step": 1676 + }, + { + "epoch": 0.09347305055459562, + "grad_norm": 0.49884751439094543, + "learning_rate": 9.850416457106755e-05, + "loss": 1.7392, + "step": 1677 + }, + { + "epoch": 0.09352878880775876, + "grad_norm": 0.5436164736747742, + "learning_rate": 9.850200209968535e-05, + "loss": 1.8583, + "step": 1678 + }, + { + "epoch": 0.09358452706092191, + "grad_norm": 0.543387234210968, + "learning_rate": 9.849983809010242e-05, + "loss": 1.9008, + "step": 1679 + }, + { + "epoch": 0.09364026531408505, + "grad_norm": 0.5220986604690552, + "learning_rate": 9.849767254238741e-05, + "loss": 1.8536, + "step": 1680 + }, + { + "epoch": 0.0936960035672482, + "grad_norm": 0.5086224675178528, + "learning_rate": 9.849550545660898e-05, + "loss": 1.6492, + "step": 1681 + }, + { + "epoch": 0.09375174182041135, + "grad_norm": 0.5263844728469849, + "learning_rate": 9.849333683283587e-05, + "loss": 1.8646, + "step": 1682 + }, + { + "epoch": 0.09380748007357449, + "grad_norm": 0.48118674755096436, + "learning_rate": 9.849116667113684e-05, + "loss": 1.6978, + "step": 1683 + }, + { + "epoch": 0.09386321832673764, + "grad_norm": 0.5442405939102173, + "learning_rate": 9.848899497158075e-05, + "loss": 1.7446, + "step": 1684 + }, + { + "epoch": 0.09391895657990079, + "grad_norm": 0.5518308877944946, + "learning_rate": 9.848682173423642e-05, + "loss": 1.9409, + "step": 1685 + }, + { + "epoch": 0.09397469483306393, + "grad_norm": 0.5064495205879211, + "learning_rate": 9.848464695917283e-05, + "loss": 1.9023, + "step": 1686 + }, + { + "epoch": 0.09403043308622708, + "grad_norm": 0.5437746644020081, + "learning_rate": 9.84824706464589e-05, + "loss": 1.8456, + "step": 1687 + }, + { + "epoch": 0.09408617133939022, + "grad_norm": 0.4933926463127136, + "learning_rate": 9.848029279616369e-05, + "loss": 1.6156, + "step": 1688 + }, + { + "epoch": 0.09414190959255336, + "grad_norm": 0.5288189649581909, + "learning_rate": 9.847811340835625e-05, + "loss": 1.8053, + "step": 1689 + }, + { + "epoch": 0.09419764784571652, + "grad_norm": 0.5238629579544067, + "learning_rate": 9.847593248310569e-05, + "loss": 1.8396, + "step": 1690 + }, + { + "epoch": 0.09425338609887966, + "grad_norm": 0.5135747790336609, + "learning_rate": 9.847375002048119e-05, + "loss": 1.702, + "step": 1691 + }, + { + "epoch": 0.0943091243520428, + "grad_norm": 0.48049938678741455, + "learning_rate": 9.847156602055196e-05, + "loss": 1.7258, + "step": 1692 + }, + { + "epoch": 0.09436486260520595, + "grad_norm": 0.5790214538574219, + "learning_rate": 9.846938048338728e-05, + "loss": 1.9521, + "step": 1693 + }, + { + "epoch": 0.0944206008583691, + "grad_norm": 0.49259278178215027, + "learning_rate": 9.846719340905643e-05, + "loss": 1.7358, + "step": 1694 + }, + { + "epoch": 0.09447633911153225, + "grad_norm": 0.5396574139595032, + "learning_rate": 9.846500479762879e-05, + "loss": 1.9847, + "step": 1695 + }, + { + "epoch": 0.09453207736469539, + "grad_norm": 0.5003666877746582, + "learning_rate": 9.846281464917377e-05, + "loss": 1.777, + "step": 1696 + }, + { + "epoch": 0.09458781561785853, + "grad_norm": 0.5158617496490479, + "learning_rate": 9.846062296376083e-05, + "loss": 1.6861, + "step": 1697 + }, + { + "epoch": 0.09464355387102168, + "grad_norm": 0.5154086351394653, + "learning_rate": 9.845842974145947e-05, + "loss": 1.8176, + "step": 1698 + }, + { + "epoch": 0.09469929212418483, + "grad_norm": 0.5052759051322937, + "learning_rate": 9.845623498233926e-05, + "loss": 1.6658, + "step": 1699 + }, + { + "epoch": 0.09475503037734798, + "grad_norm": 0.6677058339118958, + "learning_rate": 9.845403868646979e-05, + "loss": 1.7287, + "step": 1700 + }, + { + "epoch": 0.09481076863051112, + "grad_norm": 0.5167236924171448, + "learning_rate": 9.845184085392072e-05, + "loss": 1.6861, + "step": 1701 + }, + { + "epoch": 0.09486650688367426, + "grad_norm": 0.57721346616745, + "learning_rate": 9.844964148476175e-05, + "loss": 1.9309, + "step": 1702 + }, + { + "epoch": 0.0949222451368374, + "grad_norm": 0.4876415729522705, + "learning_rate": 9.844744057906263e-05, + "loss": 1.738, + "step": 1703 + }, + { + "epoch": 0.09497798339000056, + "grad_norm": 0.5089074373245239, + "learning_rate": 9.844523813689316e-05, + "loss": 1.8729, + "step": 1704 + }, + { + "epoch": 0.0950337216431637, + "grad_norm": 0.5102959871292114, + "learning_rate": 9.844303415832322e-05, + "loss": 1.901, + "step": 1705 + }, + { + "epoch": 0.09508945989632685, + "grad_norm": 0.5445943474769592, + "learning_rate": 9.844082864342265e-05, + "loss": 1.7838, + "step": 1706 + }, + { + "epoch": 0.09514519814948999, + "grad_norm": 0.5227236151695251, + "learning_rate": 9.843862159226142e-05, + "loss": 1.7044, + "step": 1707 + }, + { + "epoch": 0.09520093640265315, + "grad_norm": 0.5036524534225464, + "learning_rate": 9.843641300490956e-05, + "loss": 1.6637, + "step": 1708 + }, + { + "epoch": 0.09525667465581629, + "grad_norm": 0.5071728825569153, + "learning_rate": 9.843420288143706e-05, + "loss": 1.5714, + "step": 1709 + }, + { + "epoch": 0.09531241290897943, + "grad_norm": 0.563736081123352, + "learning_rate": 9.843199122191404e-05, + "loss": 2.0123, + "step": 1710 + }, + { + "epoch": 0.09536815116214258, + "grad_norm": 0.5531306266784668, + "learning_rate": 9.842977802641065e-05, + "loss": 1.74, + "step": 1711 + }, + { + "epoch": 0.09542388941530572, + "grad_norm": 0.5610520243644714, + "learning_rate": 9.842756329499704e-05, + "loss": 1.8003, + "step": 1712 + }, + { + "epoch": 0.09547962766846887, + "grad_norm": 0.498121440410614, + "learning_rate": 9.842534702774349e-05, + "loss": 1.6448, + "step": 1713 + }, + { + "epoch": 0.09553536592163202, + "grad_norm": 0.5231457948684692, + "learning_rate": 9.842312922472028e-05, + "loss": 1.8862, + "step": 1714 + }, + { + "epoch": 0.09559110417479516, + "grad_norm": 0.520879864692688, + "learning_rate": 9.842090988599772e-05, + "loss": 1.7858, + "step": 1715 + }, + { + "epoch": 0.0956468424279583, + "grad_norm": 0.5959715247154236, + "learning_rate": 9.841868901164622e-05, + "loss": 1.8487, + "step": 1716 + }, + { + "epoch": 0.09570258068112146, + "grad_norm": 0.5337534546852112, + "learning_rate": 9.84164666017362e-05, + "loss": 1.5147, + "step": 1717 + }, + { + "epoch": 0.0957583189342846, + "grad_norm": 0.5244635939598083, + "learning_rate": 9.841424265633816e-05, + "loss": 1.9583, + "step": 1718 + }, + { + "epoch": 0.09581405718744775, + "grad_norm": 0.5573442578315735, + "learning_rate": 9.84120171755226e-05, + "loss": 1.7111, + "step": 1719 + }, + { + "epoch": 0.09586979544061089, + "grad_norm": 0.5416032671928406, + "learning_rate": 9.840979015936014e-05, + "loss": 1.9152, + "step": 1720 + }, + { + "epoch": 0.09592553369377403, + "grad_norm": 0.5546048283576965, + "learning_rate": 9.840756160792138e-05, + "loss": 1.7902, + "step": 1721 + }, + { + "epoch": 0.09598127194693719, + "grad_norm": 0.5208713412284851, + "learning_rate": 9.840533152127697e-05, + "loss": 1.864, + "step": 1722 + }, + { + "epoch": 0.09603701020010033, + "grad_norm": 0.5275363326072693, + "learning_rate": 9.840309989949769e-05, + "loss": 1.7866, + "step": 1723 + }, + { + "epoch": 0.09609274845326347, + "grad_norm": 0.5389683246612549, + "learning_rate": 9.84008667426543e-05, + "loss": 1.8186, + "step": 1724 + }, + { + "epoch": 0.09614848670642662, + "grad_norm": 0.5352590680122375, + "learning_rate": 9.839863205081761e-05, + "loss": 1.8207, + "step": 1725 + }, + { + "epoch": 0.09620422495958976, + "grad_norm": 0.5303811430931091, + "learning_rate": 9.839639582405849e-05, + "loss": 1.8912, + "step": 1726 + }, + { + "epoch": 0.09625996321275292, + "grad_norm": 0.4606251120567322, + "learning_rate": 9.839415806244785e-05, + "loss": 1.6001, + "step": 1727 + }, + { + "epoch": 0.09631570146591606, + "grad_norm": 0.48041149973869324, + "learning_rate": 9.839191876605668e-05, + "loss": 1.6385, + "step": 1728 + }, + { + "epoch": 0.0963714397190792, + "grad_norm": 0.5307428240776062, + "learning_rate": 9.838967793495601e-05, + "loss": 1.8683, + "step": 1729 + }, + { + "epoch": 0.09642717797224234, + "grad_norm": 0.48561206459999084, + "learning_rate": 9.838743556921688e-05, + "loss": 1.7169, + "step": 1730 + }, + { + "epoch": 0.0964829162254055, + "grad_norm": 0.5501610040664673, + "learning_rate": 9.83851916689104e-05, + "loss": 1.7714, + "step": 1731 + }, + { + "epoch": 0.09653865447856864, + "grad_norm": 0.5766540765762329, + "learning_rate": 9.838294623410776e-05, + "loss": 1.961, + "step": 1732 + }, + { + "epoch": 0.09659439273173179, + "grad_norm": 0.5572078824043274, + "learning_rate": 9.838069926488016e-05, + "loss": 1.9466, + "step": 1733 + }, + { + "epoch": 0.09665013098489493, + "grad_norm": 0.5235105156898499, + "learning_rate": 9.837845076129885e-05, + "loss": 1.6369, + "step": 1734 + }, + { + "epoch": 0.09670586923805807, + "grad_norm": 0.49561917781829834, + "learning_rate": 9.837620072343514e-05, + "loss": 1.6879, + "step": 1735 + }, + { + "epoch": 0.09676160749122123, + "grad_norm": 0.577617883682251, + "learning_rate": 9.83739491513604e-05, + "loss": 2.0888, + "step": 1736 + }, + { + "epoch": 0.09681734574438437, + "grad_norm": 0.559758722782135, + "learning_rate": 9.837169604514605e-05, + "loss": 2.0155, + "step": 1737 + }, + { + "epoch": 0.09687308399754752, + "grad_norm": 0.4803854525089264, + "learning_rate": 9.83694414048635e-05, + "loss": 1.7143, + "step": 1738 + }, + { + "epoch": 0.09692882225071066, + "grad_norm": 0.5286114811897278, + "learning_rate": 9.83671852305843e-05, + "loss": 1.7708, + "step": 1739 + }, + { + "epoch": 0.09698456050387382, + "grad_norm": 0.5186529159545898, + "learning_rate": 9.836492752237998e-05, + "loss": 1.8367, + "step": 1740 + }, + { + "epoch": 0.09704029875703696, + "grad_norm": 0.5168614983558655, + "learning_rate": 9.836266828032214e-05, + "loss": 1.6913, + "step": 1741 + }, + { + "epoch": 0.0970960370102001, + "grad_norm": 0.5508823990821838, + "learning_rate": 9.836040750448246e-05, + "loss": 1.8108, + "step": 1742 + }, + { + "epoch": 0.09715177526336324, + "grad_norm": 0.5152462720870972, + "learning_rate": 9.835814519493258e-05, + "loss": 1.7643, + "step": 1743 + }, + { + "epoch": 0.09720751351652639, + "grad_norm": 0.5197470188140869, + "learning_rate": 9.835588135174432e-05, + "loss": 1.753, + "step": 1744 + }, + { + "epoch": 0.09726325176968954, + "grad_norm": 0.5595375895500183, + "learning_rate": 9.83536159749894e-05, + "loss": 1.9646, + "step": 1745 + }, + { + "epoch": 0.09731899002285269, + "grad_norm": 0.5276100635528564, + "learning_rate": 9.835134906473973e-05, + "loss": 1.8053, + "step": 1746 + }, + { + "epoch": 0.09737472827601583, + "grad_norm": 0.543694257736206, + "learning_rate": 9.834908062106716e-05, + "loss": 1.9073, + "step": 1747 + }, + { + "epoch": 0.09743046652917897, + "grad_norm": 0.5280660390853882, + "learning_rate": 9.834681064404366e-05, + "loss": 1.8642, + "step": 1748 + }, + { + "epoch": 0.09748620478234211, + "grad_norm": 0.5228556394577026, + "learning_rate": 9.83445391337412e-05, + "loss": 1.7084, + "step": 1749 + }, + { + "epoch": 0.09754194303550527, + "grad_norm": 0.5147905349731445, + "learning_rate": 9.834226609023183e-05, + "loss": 1.7273, + "step": 1750 + }, + { + "epoch": 0.09759768128866841, + "grad_norm": 0.6363779306411743, + "learning_rate": 9.833999151358763e-05, + "loss": 2.3455, + "step": 1751 + }, + { + "epoch": 0.09765341954183156, + "grad_norm": 0.4779658317565918, + "learning_rate": 9.833771540388074e-05, + "loss": 1.5965, + "step": 1752 + }, + { + "epoch": 0.0977091577949947, + "grad_norm": 0.5493218302726746, + "learning_rate": 9.833543776118334e-05, + "loss": 1.7655, + "step": 1753 + }, + { + "epoch": 0.09776489604815786, + "grad_norm": 0.5027639865875244, + "learning_rate": 9.833315858556769e-05, + "loss": 1.6425, + "step": 1754 + }, + { + "epoch": 0.097820634301321, + "grad_norm": 0.5259470343589783, + "learning_rate": 9.833087787710604e-05, + "loss": 1.8848, + "step": 1755 + }, + { + "epoch": 0.09787637255448414, + "grad_norm": 0.5296250581741333, + "learning_rate": 9.832859563587073e-05, + "loss": 1.6713, + "step": 1756 + }, + { + "epoch": 0.09793211080764729, + "grad_norm": 0.5273899435997009, + "learning_rate": 9.832631186193414e-05, + "loss": 1.7833, + "step": 1757 + }, + { + "epoch": 0.09798784906081043, + "grad_norm": 0.5987624526023865, + "learning_rate": 9.832402655536869e-05, + "loss": 2.0934, + "step": 1758 + }, + { + "epoch": 0.09804358731397358, + "grad_norm": 0.5442295074462891, + "learning_rate": 9.83217397162469e-05, + "loss": 1.6506, + "step": 1759 + }, + { + "epoch": 0.09809932556713673, + "grad_norm": 0.6511545181274414, + "learning_rate": 9.831945134464123e-05, + "loss": 2.1311, + "step": 1760 + }, + { + "epoch": 0.09815506382029987, + "grad_norm": 0.5505144596099854, + "learning_rate": 9.831716144062431e-05, + "loss": 1.7606, + "step": 1761 + }, + { + "epoch": 0.09821080207346301, + "grad_norm": 0.5241886973381042, + "learning_rate": 9.831487000426871e-05, + "loss": 1.7404, + "step": 1762 + }, + { + "epoch": 0.09826654032662617, + "grad_norm": 0.5306397080421448, + "learning_rate": 9.831257703564715e-05, + "loss": 1.7232, + "step": 1763 + }, + { + "epoch": 0.09832227857978931, + "grad_norm": 0.5829235315322876, + "learning_rate": 9.831028253483232e-05, + "loss": 1.8867, + "step": 1764 + }, + { + "epoch": 0.09837801683295246, + "grad_norm": 0.5258575677871704, + "learning_rate": 9.8307986501897e-05, + "loss": 1.6442, + "step": 1765 + }, + { + "epoch": 0.0984337550861156, + "grad_norm": 0.5493606328964233, + "learning_rate": 9.8305688936914e-05, + "loss": 2.025, + "step": 1766 + }, + { + "epoch": 0.09848949333927874, + "grad_norm": 0.5285725593566895, + "learning_rate": 9.83033898399562e-05, + "loss": 1.683, + "step": 1767 + }, + { + "epoch": 0.0985452315924419, + "grad_norm": 0.590203046798706, + "learning_rate": 9.830108921109648e-05, + "loss": 2.0356, + "step": 1768 + }, + { + "epoch": 0.09860096984560504, + "grad_norm": 0.47736695408821106, + "learning_rate": 9.829878705040784e-05, + "loss": 1.2685, + "step": 1769 + }, + { + "epoch": 0.09865670809876818, + "grad_norm": 0.5433778762817383, + "learning_rate": 9.829648335796327e-05, + "loss": 1.5734, + "step": 1770 + }, + { + "epoch": 0.09871244635193133, + "grad_norm": 0.533301591873169, + "learning_rate": 9.829417813383584e-05, + "loss": 1.6253, + "step": 1771 + }, + { + "epoch": 0.09876818460509447, + "grad_norm": 0.5619016289710999, + "learning_rate": 9.829187137809865e-05, + "loss": 1.9336, + "step": 1772 + }, + { + "epoch": 0.09882392285825763, + "grad_norm": 0.5166584849357605, + "learning_rate": 9.828956309082487e-05, + "loss": 1.6934, + "step": 1773 + }, + { + "epoch": 0.09887966111142077, + "grad_norm": 0.550294041633606, + "learning_rate": 9.828725327208769e-05, + "loss": 1.7357, + "step": 1774 + }, + { + "epoch": 0.09893539936458391, + "grad_norm": 0.5708268880844116, + "learning_rate": 9.828494192196037e-05, + "loss": 1.75, + "step": 1775 + }, + { + "epoch": 0.09899113761774705, + "grad_norm": 0.5142853856086731, + "learning_rate": 9.828262904051621e-05, + "loss": 1.8905, + "step": 1776 + }, + { + "epoch": 0.09904687587091021, + "grad_norm": 0.5133590698242188, + "learning_rate": 9.828031462782858e-05, + "loss": 1.7111, + "step": 1777 + }, + { + "epoch": 0.09910261412407335, + "grad_norm": 0.491804838180542, + "learning_rate": 9.827799868397086e-05, + "loss": 1.7898, + "step": 1778 + }, + { + "epoch": 0.0991583523772365, + "grad_norm": 0.5558345913887024, + "learning_rate": 9.827568120901649e-05, + "loss": 1.8621, + "step": 1779 + }, + { + "epoch": 0.09921409063039964, + "grad_norm": 0.5390424132347107, + "learning_rate": 9.827336220303898e-05, + "loss": 1.5574, + "step": 1780 + }, + { + "epoch": 0.09926982888356278, + "grad_norm": 0.5201495885848999, + "learning_rate": 9.827104166611188e-05, + "loss": 1.7218, + "step": 1781 + }, + { + "epoch": 0.09932556713672594, + "grad_norm": 0.49533358216285706, + "learning_rate": 9.826871959830877e-05, + "loss": 1.6587, + "step": 1782 + }, + { + "epoch": 0.09938130538988908, + "grad_norm": 0.5522517561912537, + "learning_rate": 9.826639599970331e-05, + "loss": 1.9942, + "step": 1783 + }, + { + "epoch": 0.09943704364305223, + "grad_norm": 0.5211175680160522, + "learning_rate": 9.826407087036918e-05, + "loss": 1.7953, + "step": 1784 + }, + { + "epoch": 0.09949278189621537, + "grad_norm": 0.5591548681259155, + "learning_rate": 9.82617442103801e-05, + "loss": 1.7257, + "step": 1785 + }, + { + "epoch": 0.09954852014937852, + "grad_norm": 0.5057593584060669, + "learning_rate": 9.82594160198099e-05, + "loss": 1.6209, + "step": 1786 + }, + { + "epoch": 0.09960425840254167, + "grad_norm": 0.4974839389324188, + "learning_rate": 9.82570862987324e-05, + "loss": 1.7242, + "step": 1787 + }, + { + "epoch": 0.09965999665570481, + "grad_norm": 0.580697238445282, + "learning_rate": 9.825475504722147e-05, + "loss": 1.8402, + "step": 1788 + }, + { + "epoch": 0.09971573490886795, + "grad_norm": 0.5298492908477783, + "learning_rate": 9.825242226535106e-05, + "loss": 1.5434, + "step": 1789 + }, + { + "epoch": 0.0997714731620311, + "grad_norm": 0.5714828372001648, + "learning_rate": 9.825008795319514e-05, + "loss": 1.8505, + "step": 1790 + }, + { + "epoch": 0.09982721141519425, + "grad_norm": 0.5840202569961548, + "learning_rate": 9.824775211082776e-05, + "loss": 1.9345, + "step": 1791 + }, + { + "epoch": 0.0998829496683574, + "grad_norm": 0.495969295501709, + "learning_rate": 9.824541473832298e-05, + "loss": 1.6482, + "step": 1792 + }, + { + "epoch": 0.09993868792152054, + "grad_norm": 0.537111759185791, + "learning_rate": 9.824307583575494e-05, + "loss": 1.6791, + "step": 1793 + }, + { + "epoch": 0.09999442617468368, + "grad_norm": 0.5053449869155884, + "learning_rate": 9.82407354031978e-05, + "loss": 1.6764, + "step": 1794 + }, + { + "epoch": 0.10005016442784682, + "grad_norm": 0.5327693223953247, + "learning_rate": 9.82383934407258e-05, + "loss": 1.7993, + "step": 1795 + }, + { + "epoch": 0.10010590268100998, + "grad_norm": 0.49914291501045227, + "learning_rate": 9.823604994841322e-05, + "loss": 1.9674, + "step": 1796 + }, + { + "epoch": 0.10016164093417312, + "grad_norm": 0.5144324898719788, + "learning_rate": 9.823370492633435e-05, + "loss": 1.7585, + "step": 1797 + }, + { + "epoch": 0.10021737918733627, + "grad_norm": 0.5108045935630798, + "learning_rate": 9.823135837456362e-05, + "loss": 1.7215, + "step": 1798 + }, + { + "epoch": 0.10027311744049941, + "grad_norm": 0.5693103671073914, + "learning_rate": 9.822901029317537e-05, + "loss": 1.7812, + "step": 1799 + }, + { + "epoch": 0.10032885569366257, + "grad_norm": 0.49847400188446045, + "learning_rate": 9.822666068224412e-05, + "loss": 1.6675, + "step": 1800 + }, + { + "epoch": 0.10038459394682571, + "grad_norm": 0.5565662384033203, + "learning_rate": 9.822430954184439e-05, + "loss": 1.8071, + "step": 1801 + }, + { + "epoch": 0.10044033219998885, + "grad_norm": 0.5412677526473999, + "learning_rate": 9.82219568720507e-05, + "loss": 1.7311, + "step": 1802 + }, + { + "epoch": 0.100496070453152, + "grad_norm": 0.5256420373916626, + "learning_rate": 9.821960267293771e-05, + "loss": 1.8179, + "step": 1803 + }, + { + "epoch": 0.10055180870631514, + "grad_norm": 0.486968457698822, + "learning_rate": 9.821724694458006e-05, + "loss": 1.7443, + "step": 1804 + }, + { + "epoch": 0.1006075469594783, + "grad_norm": 0.5230684280395508, + "learning_rate": 9.821488968705246e-05, + "loss": 1.8426, + "step": 1805 + }, + { + "epoch": 0.10066328521264144, + "grad_norm": 0.5057176351547241, + "learning_rate": 9.821253090042967e-05, + "loss": 1.6857, + "step": 1806 + }, + { + "epoch": 0.10071902346580458, + "grad_norm": 0.5477109551429749, + "learning_rate": 9.821017058478653e-05, + "loss": 1.904, + "step": 1807 + }, + { + "epoch": 0.10077476171896772, + "grad_norm": 0.5054430961608887, + "learning_rate": 9.820780874019782e-05, + "loss": 1.8538, + "step": 1808 + }, + { + "epoch": 0.10083049997213088, + "grad_norm": 0.5614181160926819, + "learning_rate": 9.82054453667385e-05, + "loss": 1.9318, + "step": 1809 + }, + { + "epoch": 0.10088623822529402, + "grad_norm": 0.49829983711242676, + "learning_rate": 9.820308046448353e-05, + "loss": 1.6044, + "step": 1810 + }, + { + "epoch": 0.10094197647845717, + "grad_norm": 0.53876793384552, + "learning_rate": 9.820071403350787e-05, + "loss": 1.7234, + "step": 1811 + }, + { + "epoch": 0.10099771473162031, + "grad_norm": 0.5352075695991516, + "learning_rate": 9.81983460738866e-05, + "loss": 1.7911, + "step": 1812 + }, + { + "epoch": 0.10105345298478345, + "grad_norm": 0.5328055024147034, + "learning_rate": 9.819597658569479e-05, + "loss": 1.8147, + "step": 1813 + }, + { + "epoch": 0.10110919123794661, + "grad_norm": 0.5261515378952026, + "learning_rate": 9.819360556900763e-05, + "loss": 1.8057, + "step": 1814 + }, + { + "epoch": 0.10116492949110975, + "grad_norm": 0.5476046204566956, + "learning_rate": 9.819123302390027e-05, + "loss": 1.7813, + "step": 1815 + }, + { + "epoch": 0.1012206677442729, + "grad_norm": 0.5293675661087036, + "learning_rate": 9.818885895044799e-05, + "loss": 1.7398, + "step": 1816 + }, + { + "epoch": 0.10127640599743604, + "grad_norm": 0.6075041890144348, + "learning_rate": 9.818648334872607e-05, + "loss": 1.985, + "step": 1817 + }, + { + "epoch": 0.10133214425059918, + "grad_norm": 0.5815473794937134, + "learning_rate": 9.818410621880982e-05, + "loss": 1.7932, + "step": 1818 + }, + { + "epoch": 0.10138788250376234, + "grad_norm": 0.546378493309021, + "learning_rate": 9.818172756077466e-05, + "loss": 1.8672, + "step": 1819 + }, + { + "epoch": 0.10144362075692548, + "grad_norm": 0.5089141130447388, + "learning_rate": 9.817934737469603e-05, + "loss": 1.4847, + "step": 1820 + }, + { + "epoch": 0.10149935901008862, + "grad_norm": 0.5070534348487854, + "learning_rate": 9.81769656606494e-05, + "loss": 1.6301, + "step": 1821 + }, + { + "epoch": 0.10155509726325176, + "grad_norm": 0.5128391981124878, + "learning_rate": 9.817458241871032e-05, + "loss": 1.8199, + "step": 1822 + }, + { + "epoch": 0.10161083551641492, + "grad_norm": 0.5569765567779541, + "learning_rate": 9.817219764895435e-05, + "loss": 1.7238, + "step": 1823 + }, + { + "epoch": 0.10166657376957806, + "grad_norm": 0.5038780570030212, + "learning_rate": 9.816981135145714e-05, + "loss": 1.7099, + "step": 1824 + }, + { + "epoch": 0.10172231202274121, + "grad_norm": 0.5122333765029907, + "learning_rate": 9.816742352629437e-05, + "loss": 1.7679, + "step": 1825 + }, + { + "epoch": 0.10177805027590435, + "grad_norm": 0.5544700026512146, + "learning_rate": 9.816503417354174e-05, + "loss": 2.0049, + "step": 1826 + }, + { + "epoch": 0.10183378852906749, + "grad_norm": 0.5663131475448608, + "learning_rate": 9.816264329327507e-05, + "loss": 1.7042, + "step": 1827 + }, + { + "epoch": 0.10188952678223065, + "grad_norm": 0.5186511278152466, + "learning_rate": 9.816025088557015e-05, + "loss": 1.7472, + "step": 1828 + }, + { + "epoch": 0.10194526503539379, + "grad_norm": 0.5595180988311768, + "learning_rate": 9.815785695050288e-05, + "loss": 1.6525, + "step": 1829 + }, + { + "epoch": 0.10200100328855694, + "grad_norm": 0.49748462438583374, + "learning_rate": 9.815546148814915e-05, + "loss": 1.6744, + "step": 1830 + }, + { + "epoch": 0.10205674154172008, + "grad_norm": 0.47154897451400757, + "learning_rate": 9.815306449858497e-05, + "loss": 1.6183, + "step": 1831 + }, + { + "epoch": 0.10211247979488323, + "grad_norm": 0.5415584444999695, + "learning_rate": 9.815066598188631e-05, + "loss": 1.842, + "step": 1832 + }, + { + "epoch": 0.10216821804804638, + "grad_norm": 0.5106571912765503, + "learning_rate": 9.814826593812928e-05, + "loss": 1.6504, + "step": 1833 + }, + { + "epoch": 0.10222395630120952, + "grad_norm": 0.5451028347015381, + "learning_rate": 9.814586436738998e-05, + "loss": 1.8817, + "step": 1834 + }, + { + "epoch": 0.10227969455437266, + "grad_norm": 0.5032516121864319, + "learning_rate": 9.814346126974455e-05, + "loss": 1.8143, + "step": 1835 + }, + { + "epoch": 0.1023354328075358, + "grad_norm": 0.4844000041484833, + "learning_rate": 9.814105664526925e-05, + "loss": 1.8255, + "step": 1836 + }, + { + "epoch": 0.10239117106069896, + "grad_norm": 0.8231089115142822, + "learning_rate": 9.81386504940403e-05, + "loss": 1.5754, + "step": 1837 + }, + { + "epoch": 0.1024469093138621, + "grad_norm": 0.5142394304275513, + "learning_rate": 9.813624281613403e-05, + "loss": 1.7516, + "step": 1838 + }, + { + "epoch": 0.10250264756702525, + "grad_norm": 0.5010998249053955, + "learning_rate": 9.813383361162678e-05, + "loss": 1.7164, + "step": 1839 + }, + { + "epoch": 0.10255838582018839, + "grad_norm": 0.5169504284858704, + "learning_rate": 9.813142288059497e-05, + "loss": 1.4974, + "step": 1840 + }, + { + "epoch": 0.10261412407335155, + "grad_norm": 0.5264306664466858, + "learning_rate": 9.812901062311507e-05, + "loss": 1.6087, + "step": 1841 + }, + { + "epoch": 0.10266986232651469, + "grad_norm": 0.5117889642715454, + "learning_rate": 9.812659683926355e-05, + "loss": 1.734, + "step": 1842 + }, + { + "epoch": 0.10272560057967783, + "grad_norm": 0.5216721296310425, + "learning_rate": 9.812418152911697e-05, + "loss": 1.7643, + "step": 1843 + }, + { + "epoch": 0.10278133883284098, + "grad_norm": 0.5514086484909058, + "learning_rate": 9.812176469275196e-05, + "loss": 1.7052, + "step": 1844 + }, + { + "epoch": 0.10283707708600412, + "grad_norm": 0.5310468077659607, + "learning_rate": 9.811934633024514e-05, + "loss": 1.8478, + "step": 1845 + }, + { + "epoch": 0.10289281533916728, + "grad_norm": 0.5535829067230225, + "learning_rate": 9.811692644167318e-05, + "loss": 1.7884, + "step": 1846 + }, + { + "epoch": 0.10294855359233042, + "grad_norm": 0.5332193374633789, + "learning_rate": 9.811450502711288e-05, + "loss": 1.7511, + "step": 1847 + }, + { + "epoch": 0.10300429184549356, + "grad_norm": 0.5547590851783752, + "learning_rate": 9.8112082086641e-05, + "loss": 1.7348, + "step": 1848 + }, + { + "epoch": 0.1030600300986567, + "grad_norm": 0.5098549127578735, + "learning_rate": 9.810965762033439e-05, + "loss": 1.8117, + "step": 1849 + }, + { + "epoch": 0.10311576835181985, + "grad_norm": 0.4965379238128662, + "learning_rate": 9.810723162826994e-05, + "loss": 1.6535, + "step": 1850 + }, + { + "epoch": 0.103171506604983, + "grad_norm": 0.5498190522193909, + "learning_rate": 9.810480411052458e-05, + "loss": 1.8094, + "step": 1851 + }, + { + "epoch": 0.10322724485814615, + "grad_norm": 0.5419559478759766, + "learning_rate": 9.81023750671753e-05, + "loss": 1.8347, + "step": 1852 + }, + { + "epoch": 0.10328298311130929, + "grad_norm": 0.5136609077453613, + "learning_rate": 9.809994449829916e-05, + "loss": 1.8038, + "step": 1853 + }, + { + "epoch": 0.10333872136447243, + "grad_norm": 0.4600328207015991, + "learning_rate": 9.809751240397321e-05, + "loss": 1.5616, + "step": 1854 + }, + { + "epoch": 0.10339445961763559, + "grad_norm": 0.5725501775741577, + "learning_rate": 9.80950787842746e-05, + "loss": 2.0217, + "step": 1855 + }, + { + "epoch": 0.10345019787079873, + "grad_norm": 0.4968816936016083, + "learning_rate": 9.809264363928049e-05, + "loss": 1.6151, + "step": 1856 + }, + { + "epoch": 0.10350593612396188, + "grad_norm": 0.5521273016929626, + "learning_rate": 9.809020696906815e-05, + "loss": 1.5242, + "step": 1857 + }, + { + "epoch": 0.10356167437712502, + "grad_norm": 0.526759684085846, + "learning_rate": 9.80877687737148e-05, + "loss": 1.6917, + "step": 1858 + }, + { + "epoch": 0.10361741263028816, + "grad_norm": 0.5235029458999634, + "learning_rate": 9.808532905329781e-05, + "loss": 1.785, + "step": 1859 + }, + { + "epoch": 0.10367315088345132, + "grad_norm": 0.5284624099731445, + "learning_rate": 9.808288780789454e-05, + "loss": 1.8857, + "step": 1860 + }, + { + "epoch": 0.10372888913661446, + "grad_norm": 0.5086808800697327, + "learning_rate": 9.80804450375824e-05, + "loss": 1.5768, + "step": 1861 + }, + { + "epoch": 0.1037846273897776, + "grad_norm": 0.6029835343360901, + "learning_rate": 9.807800074243888e-05, + "loss": 2.1482, + "step": 1862 + }, + { + "epoch": 0.10384036564294075, + "grad_norm": 0.5451070666313171, + "learning_rate": 9.80755549225415e-05, + "loss": 1.6884, + "step": 1863 + }, + { + "epoch": 0.1038961038961039, + "grad_norm": 0.5617519021034241, + "learning_rate": 9.807310757796781e-05, + "loss": 1.9665, + "step": 1864 + }, + { + "epoch": 0.10395184214926705, + "grad_norm": 0.6114406585693359, + "learning_rate": 9.807065870879544e-05, + "loss": 1.9696, + "step": 1865 + }, + { + "epoch": 0.10400758040243019, + "grad_norm": 0.5124810338020325, + "learning_rate": 9.806820831510204e-05, + "loss": 1.6848, + "step": 1866 + }, + { + "epoch": 0.10406331865559333, + "grad_norm": 0.5385152697563171, + "learning_rate": 9.806575639696533e-05, + "loss": 1.6808, + "step": 1867 + }, + { + "epoch": 0.10411905690875647, + "grad_norm": 0.49392756819725037, + "learning_rate": 9.806330295446307e-05, + "loss": 1.8179, + "step": 1868 + }, + { + "epoch": 0.10417479516191963, + "grad_norm": 0.49383312463760376, + "learning_rate": 9.806084798767307e-05, + "loss": 1.5517, + "step": 1869 + }, + { + "epoch": 0.10423053341508277, + "grad_norm": 0.5276709198951721, + "learning_rate": 9.805839149667319e-05, + "loss": 1.7125, + "step": 1870 + }, + { + "epoch": 0.10428627166824592, + "grad_norm": 0.5694584250450134, + "learning_rate": 9.805593348154131e-05, + "loss": 1.9891, + "step": 1871 + }, + { + "epoch": 0.10434200992140906, + "grad_norm": 0.5705782771110535, + "learning_rate": 9.805347394235543e-05, + "loss": 1.779, + "step": 1872 + }, + { + "epoch": 0.1043977481745722, + "grad_norm": 0.543282151222229, + "learning_rate": 9.805101287919352e-05, + "loss": 1.898, + "step": 1873 + }, + { + "epoch": 0.10445348642773536, + "grad_norm": 0.5607357025146484, + "learning_rate": 9.804855029213365e-05, + "loss": 1.9422, + "step": 1874 + }, + { + "epoch": 0.1045092246808985, + "grad_norm": 0.548055112361908, + "learning_rate": 9.804608618125388e-05, + "loss": 1.776, + "step": 1875 + }, + { + "epoch": 0.10456496293406164, + "grad_norm": 0.528634250164032, + "learning_rate": 9.804362054663241e-05, + "loss": 1.7196, + "step": 1876 + }, + { + "epoch": 0.10462070118722479, + "grad_norm": 0.5074811577796936, + "learning_rate": 9.80411533883474e-05, + "loss": 1.6667, + "step": 1877 + }, + { + "epoch": 0.10467643944038794, + "grad_norm": 0.5272465944290161, + "learning_rate": 9.80386847064771e-05, + "loss": 1.8897, + "step": 1878 + }, + { + "epoch": 0.10473217769355109, + "grad_norm": 0.5819423198699951, + "learning_rate": 9.80362145010998e-05, + "loss": 1.868, + "step": 1879 + }, + { + "epoch": 0.10478791594671423, + "grad_norm": 0.4952581226825714, + "learning_rate": 9.803374277229387e-05, + "loss": 1.7449, + "step": 1880 + }, + { + "epoch": 0.10484365419987737, + "grad_norm": 0.5459893345832825, + "learning_rate": 9.803126952013766e-05, + "loss": 1.7454, + "step": 1881 + }, + { + "epoch": 0.10489939245304052, + "grad_norm": 0.4974026381969452, + "learning_rate": 9.802879474470964e-05, + "loss": 1.5892, + "step": 1882 + }, + { + "epoch": 0.10495513070620367, + "grad_norm": 0.503982424736023, + "learning_rate": 9.802631844608825e-05, + "loss": 1.608, + "step": 1883 + }, + { + "epoch": 0.10501086895936682, + "grad_norm": 0.5444994568824768, + "learning_rate": 9.802384062435206e-05, + "loss": 1.8286, + "step": 1884 + }, + { + "epoch": 0.10506660721252996, + "grad_norm": 0.5099791288375854, + "learning_rate": 9.802136127957965e-05, + "loss": 1.7811, + "step": 1885 + }, + { + "epoch": 0.1051223454656931, + "grad_norm": 0.5670564770698547, + "learning_rate": 9.801888041184963e-05, + "loss": 2.0036, + "step": 1886 + }, + { + "epoch": 0.10517808371885626, + "grad_norm": 0.5026718378067017, + "learning_rate": 9.801639802124071e-05, + "loss": 1.6716, + "step": 1887 + }, + { + "epoch": 0.1052338219720194, + "grad_norm": 0.519005298614502, + "learning_rate": 9.801391410783161e-05, + "loss": 1.6815, + "step": 1888 + }, + { + "epoch": 0.10528956022518254, + "grad_norm": 0.46930474042892456, + "learning_rate": 9.801142867170106e-05, + "loss": 1.7429, + "step": 1889 + }, + { + "epoch": 0.10534529847834569, + "grad_norm": 0.5434656143188477, + "learning_rate": 9.800894171292793e-05, + "loss": 1.8671, + "step": 1890 + }, + { + "epoch": 0.10540103673150883, + "grad_norm": 0.5062917470932007, + "learning_rate": 9.80064532315911e-05, + "loss": 1.6347, + "step": 1891 + }, + { + "epoch": 0.10545677498467199, + "grad_norm": 0.5208712220191956, + "learning_rate": 9.800396322776945e-05, + "loss": 1.601, + "step": 1892 + }, + { + "epoch": 0.10551251323783513, + "grad_norm": 0.49505361914634705, + "learning_rate": 9.800147170154199e-05, + "loss": 1.7157, + "step": 1893 + }, + { + "epoch": 0.10556825149099827, + "grad_norm": 0.5282744765281677, + "learning_rate": 9.79989786529877e-05, + "loss": 1.7322, + "step": 1894 + }, + { + "epoch": 0.10562398974416141, + "grad_norm": 0.5821601748466492, + "learning_rate": 9.799648408218567e-05, + "loss": 2.0407, + "step": 1895 + }, + { + "epoch": 0.10567972799732456, + "grad_norm": 0.5044925212860107, + "learning_rate": 9.7993987989215e-05, + "loss": 1.6443, + "step": 1896 + }, + { + "epoch": 0.10573546625048771, + "grad_norm": 0.5207780599594116, + "learning_rate": 9.799149037415485e-05, + "loss": 1.6341, + "step": 1897 + }, + { + "epoch": 0.10579120450365086, + "grad_norm": 0.5176671743392944, + "learning_rate": 9.798899123708444e-05, + "loss": 1.7532, + "step": 1898 + }, + { + "epoch": 0.105846942756814, + "grad_norm": 0.585341215133667, + "learning_rate": 9.798649057808302e-05, + "loss": 1.7511, + "step": 1899 + }, + { + "epoch": 0.10590268100997714, + "grad_norm": 0.5633143782615662, + "learning_rate": 9.798398839722991e-05, + "loss": 1.8548, + "step": 1900 + }, + { + "epoch": 0.1059584192631403, + "grad_norm": 0.5425167083740234, + "learning_rate": 9.798148469460444e-05, + "loss": 1.7457, + "step": 1901 + }, + { + "epoch": 0.10601415751630344, + "grad_norm": 0.5065333247184753, + "learning_rate": 9.797897947028602e-05, + "loss": 1.6342, + "step": 1902 + }, + { + "epoch": 0.10606989576946659, + "grad_norm": 0.4805918037891388, + "learning_rate": 9.797647272435413e-05, + "loss": 1.6272, + "step": 1903 + }, + { + "epoch": 0.10612563402262973, + "grad_norm": 0.49736079573631287, + "learning_rate": 9.797396445688825e-05, + "loss": 1.6666, + "step": 1904 + }, + { + "epoch": 0.10618137227579287, + "grad_norm": 0.5496745705604553, + "learning_rate": 9.797145466796791e-05, + "loss": 1.7214, + "step": 1905 + }, + { + "epoch": 0.10623711052895603, + "grad_norm": 0.5134656429290771, + "learning_rate": 9.796894335767272e-05, + "loss": 1.7156, + "step": 1906 + }, + { + "epoch": 0.10629284878211917, + "grad_norm": 0.5449696183204651, + "learning_rate": 9.796643052608232e-05, + "loss": 1.7284, + "step": 1907 + }, + { + "epoch": 0.10634858703528231, + "grad_norm": 0.5344961881637573, + "learning_rate": 9.796391617327643e-05, + "loss": 1.514, + "step": 1908 + }, + { + "epoch": 0.10640432528844546, + "grad_norm": 0.5717931389808655, + "learning_rate": 9.796140029933474e-05, + "loss": 1.9562, + "step": 1909 + }, + { + "epoch": 0.10646006354160861, + "grad_norm": 0.5507314205169678, + "learning_rate": 9.795888290433708e-05, + "loss": 1.8475, + "step": 1910 + }, + { + "epoch": 0.10651580179477176, + "grad_norm": 0.4807168245315552, + "learning_rate": 9.795636398836328e-05, + "loss": 1.4198, + "step": 1911 + }, + { + "epoch": 0.1065715400479349, + "grad_norm": 0.5163860321044922, + "learning_rate": 9.795384355149321e-05, + "loss": 1.7098, + "step": 1912 + }, + { + "epoch": 0.10662727830109804, + "grad_norm": 0.5876139998435974, + "learning_rate": 9.795132159380683e-05, + "loss": 1.8379, + "step": 1913 + }, + { + "epoch": 0.10668301655426118, + "grad_norm": 0.5147418975830078, + "learning_rate": 9.794879811538409e-05, + "loss": 1.8069, + "step": 1914 + }, + { + "epoch": 0.10673875480742434, + "grad_norm": 0.5539793372154236, + "learning_rate": 9.794627311630503e-05, + "loss": 1.9336, + "step": 1915 + }, + { + "epoch": 0.10679449306058748, + "grad_norm": 0.5565729737281799, + "learning_rate": 9.794374659664975e-05, + "loss": 1.8024, + "step": 1916 + }, + { + "epoch": 0.10685023131375063, + "grad_norm": 0.509848952293396, + "learning_rate": 9.794121855649834e-05, + "loss": 1.6553, + "step": 1917 + }, + { + "epoch": 0.10690596956691377, + "grad_norm": 0.5031093955039978, + "learning_rate": 9.793868899593101e-05, + "loss": 1.6452, + "step": 1918 + }, + { + "epoch": 0.10696170782007691, + "grad_norm": 0.5101149082183838, + "learning_rate": 9.793615791502794e-05, + "loss": 1.5787, + "step": 1919 + }, + { + "epoch": 0.10701744607324007, + "grad_norm": 0.5462785363197327, + "learning_rate": 9.793362531386946e-05, + "loss": 1.7273, + "step": 1920 + }, + { + "epoch": 0.10707318432640321, + "grad_norm": 0.5313560366630554, + "learning_rate": 9.793109119253584e-05, + "loss": 1.7061, + "step": 1921 + }, + { + "epoch": 0.10712892257956635, + "grad_norm": 0.49144747853279114, + "learning_rate": 9.792855555110747e-05, + "loss": 1.6418, + "step": 1922 + }, + { + "epoch": 0.1071846608327295, + "grad_norm": 0.5435053110122681, + "learning_rate": 9.792601838966477e-05, + "loss": 1.8774, + "step": 1923 + }, + { + "epoch": 0.10724039908589265, + "grad_norm": 0.5598286390304565, + "learning_rate": 9.792347970828819e-05, + "loss": 1.8705, + "step": 1924 + }, + { + "epoch": 0.1072961373390558, + "grad_norm": 0.5478824377059937, + "learning_rate": 9.792093950705824e-05, + "loss": 1.6882, + "step": 1925 + }, + { + "epoch": 0.10735187559221894, + "grad_norm": 0.5779083967208862, + "learning_rate": 9.79183977860555e-05, + "loss": 1.993, + "step": 1926 + }, + { + "epoch": 0.10740761384538208, + "grad_norm": 0.5614520907402039, + "learning_rate": 9.791585454536054e-05, + "loss": 1.7984, + "step": 1927 + }, + { + "epoch": 0.10746335209854523, + "grad_norm": 0.5752551555633545, + "learning_rate": 9.791330978505406e-05, + "loss": 1.781, + "step": 1928 + }, + { + "epoch": 0.10751909035170838, + "grad_norm": 0.5250864624977112, + "learning_rate": 9.791076350521675e-05, + "loss": 1.8367, + "step": 1929 + }, + { + "epoch": 0.10757482860487153, + "grad_norm": 0.5408803224563599, + "learning_rate": 9.790821570592937e-05, + "loss": 1.9812, + "step": 1930 + }, + { + "epoch": 0.10763056685803467, + "grad_norm": 0.5511845350265503, + "learning_rate": 9.790566638727268e-05, + "loss": 1.9631, + "step": 1931 + }, + { + "epoch": 0.10768630511119781, + "grad_norm": 0.5966324806213379, + "learning_rate": 9.790311554932758e-05, + "loss": 1.6961, + "step": 1932 + }, + { + "epoch": 0.10774204336436097, + "grad_norm": 0.5062892436981201, + "learning_rate": 9.790056319217495e-05, + "loss": 1.4829, + "step": 1933 + }, + { + "epoch": 0.10779778161752411, + "grad_norm": 0.5916358232498169, + "learning_rate": 9.789800931589574e-05, + "loss": 1.7646, + "step": 1934 + }, + { + "epoch": 0.10785351987068725, + "grad_norm": 0.5008646845817566, + "learning_rate": 9.789545392057093e-05, + "loss": 1.6985, + "step": 1935 + }, + { + "epoch": 0.1079092581238504, + "grad_norm": 0.557442843914032, + "learning_rate": 9.789289700628158e-05, + "loss": 1.6734, + "step": 1936 + }, + { + "epoch": 0.10796499637701354, + "grad_norm": 0.5303389430046082, + "learning_rate": 9.789033857310876e-05, + "loss": 1.8051, + "step": 1937 + }, + { + "epoch": 0.1080207346301767, + "grad_norm": 0.5422589182853699, + "learning_rate": 9.788777862113363e-05, + "loss": 1.7073, + "step": 1938 + }, + { + "epoch": 0.10807647288333984, + "grad_norm": 0.49321499466896057, + "learning_rate": 9.788521715043736e-05, + "loss": 1.6106, + "step": 1939 + }, + { + "epoch": 0.10813221113650298, + "grad_norm": 0.5515221953392029, + "learning_rate": 9.78826541611012e-05, + "loss": 1.9005, + "step": 1940 + }, + { + "epoch": 0.10818794938966612, + "grad_norm": 0.5055232048034668, + "learning_rate": 9.788008965320643e-05, + "loss": 1.6169, + "step": 1941 + }, + { + "epoch": 0.10824368764282927, + "grad_norm": 0.5074330568313599, + "learning_rate": 9.787752362683438e-05, + "loss": 1.6712, + "step": 1942 + }, + { + "epoch": 0.10829942589599242, + "grad_norm": 0.5290434956550598, + "learning_rate": 9.78749560820664e-05, + "loss": 1.6697, + "step": 1943 + }, + { + "epoch": 0.10835516414915557, + "grad_norm": 0.5382573008537292, + "learning_rate": 9.787238701898397e-05, + "loss": 1.6955, + "step": 1944 + }, + { + "epoch": 0.10841090240231871, + "grad_norm": 0.5350417494773865, + "learning_rate": 9.786981643766852e-05, + "loss": 1.695, + "step": 1945 + }, + { + "epoch": 0.10846664065548185, + "grad_norm": 0.5305573344230652, + "learning_rate": 9.78672443382016e-05, + "loss": 1.8205, + "step": 1946 + }, + { + "epoch": 0.10852237890864501, + "grad_norm": 0.5057222247123718, + "learning_rate": 9.786467072066478e-05, + "loss": 1.7815, + "step": 1947 + }, + { + "epoch": 0.10857811716180815, + "grad_norm": 0.5606647729873657, + "learning_rate": 9.786209558513968e-05, + "loss": 2.0612, + "step": 1948 + }, + { + "epoch": 0.1086338554149713, + "grad_norm": 0.5300911068916321, + "learning_rate": 9.785951893170795e-05, + "loss": 1.8648, + "step": 1949 + }, + { + "epoch": 0.10868959366813444, + "grad_norm": 0.5408658385276794, + "learning_rate": 9.785694076045133e-05, + "loss": 1.7291, + "step": 1950 + }, + { + "epoch": 0.10874533192129758, + "grad_norm": 0.5921101570129395, + "learning_rate": 9.785436107145156e-05, + "loss": 1.9079, + "step": 1951 + }, + { + "epoch": 0.10880107017446074, + "grad_norm": 0.5365302562713623, + "learning_rate": 9.785177986479048e-05, + "loss": 1.888, + "step": 1952 + }, + { + "epoch": 0.10885680842762388, + "grad_norm": 0.5375866293907166, + "learning_rate": 9.784919714054993e-05, + "loss": 1.7309, + "step": 1953 + }, + { + "epoch": 0.10891254668078702, + "grad_norm": 0.5292702317237854, + "learning_rate": 9.784661289881183e-05, + "loss": 1.7366, + "step": 1954 + }, + { + "epoch": 0.10896828493395017, + "grad_norm": 0.5953987240791321, + "learning_rate": 9.784402713965815e-05, + "loss": 1.6749, + "step": 1955 + }, + { + "epoch": 0.10902402318711332, + "grad_norm": 0.5666269659996033, + "learning_rate": 9.784143986317084e-05, + "loss": 1.8123, + "step": 1956 + }, + { + "epoch": 0.10907976144027647, + "grad_norm": 0.4942094683647156, + "learning_rate": 9.783885106943203e-05, + "loss": 1.5919, + "step": 1957 + }, + { + "epoch": 0.10913549969343961, + "grad_norm": 0.5365981459617615, + "learning_rate": 9.783626075852377e-05, + "loss": 1.8938, + "step": 1958 + }, + { + "epoch": 0.10919123794660275, + "grad_norm": 0.4730222523212433, + "learning_rate": 9.783366893052822e-05, + "loss": 1.6972, + "step": 1959 + }, + { + "epoch": 0.1092469761997659, + "grad_norm": 0.5012983679771423, + "learning_rate": 9.783107558552759e-05, + "loss": 1.5967, + "step": 1960 + }, + { + "epoch": 0.10930271445292905, + "grad_norm": 0.47032400965690613, + "learning_rate": 9.782848072360411e-05, + "loss": 1.4359, + "step": 1961 + }, + { + "epoch": 0.1093584527060922, + "grad_norm": 0.6051558256149292, + "learning_rate": 9.782588434484008e-05, + "loss": 1.8727, + "step": 1962 + }, + { + "epoch": 0.10941419095925534, + "grad_norm": 0.5087974667549133, + "learning_rate": 9.782328644931784e-05, + "loss": 1.6863, + "step": 1963 + }, + { + "epoch": 0.10946992921241848, + "grad_norm": 0.5419572591781616, + "learning_rate": 9.782068703711979e-05, + "loss": 1.8686, + "step": 1964 + }, + { + "epoch": 0.10952566746558162, + "grad_norm": 0.5740787386894226, + "learning_rate": 9.781808610832837e-05, + "loss": 1.8671, + "step": 1965 + }, + { + "epoch": 0.10958140571874478, + "grad_norm": 0.5375397801399231, + "learning_rate": 9.781548366302604e-05, + "loss": 1.855, + "step": 1966 + }, + { + "epoch": 0.10963714397190792, + "grad_norm": 0.5186393857002258, + "learning_rate": 9.781287970129536e-05, + "loss": 1.8296, + "step": 1967 + }, + { + "epoch": 0.10969288222507106, + "grad_norm": 0.5058977007865906, + "learning_rate": 9.781027422321891e-05, + "loss": 1.6181, + "step": 1968 + }, + { + "epoch": 0.10974862047823421, + "grad_norm": 0.5131574273109436, + "learning_rate": 9.78076672288793e-05, + "loss": 1.8194, + "step": 1969 + }, + { + "epoch": 0.10980435873139736, + "grad_norm": 0.5668989419937134, + "learning_rate": 9.780505871835924e-05, + "loss": 1.857, + "step": 1970 + }, + { + "epoch": 0.1098600969845605, + "grad_norm": 0.5090118646621704, + "learning_rate": 9.780244869174142e-05, + "loss": 1.5722, + "step": 1971 + }, + { + "epoch": 0.10991583523772365, + "grad_norm": 0.5472584962844849, + "learning_rate": 9.779983714910865e-05, + "loss": 1.7926, + "step": 1972 + }, + { + "epoch": 0.10997157349088679, + "grad_norm": 0.5904543399810791, + "learning_rate": 9.779722409054374e-05, + "loss": 1.9054, + "step": 1973 + }, + { + "epoch": 0.11002731174404994, + "grad_norm": 0.4884478747844696, + "learning_rate": 9.779460951612955e-05, + "loss": 1.5573, + "step": 1974 + }, + { + "epoch": 0.11008304999721309, + "grad_norm": 0.6380166411399841, + "learning_rate": 9.779199342594902e-05, + "loss": 2.0516, + "step": 1975 + }, + { + "epoch": 0.11013878825037623, + "grad_norm": 0.5148760080337524, + "learning_rate": 9.778937582008509e-05, + "loss": 1.7119, + "step": 1976 + }, + { + "epoch": 0.11019452650353938, + "grad_norm": 0.5153675079345703, + "learning_rate": 9.77867566986208e-05, + "loss": 1.6784, + "step": 1977 + }, + { + "epoch": 0.11025026475670252, + "grad_norm": 0.5181575417518616, + "learning_rate": 9.77841360616392e-05, + "loss": 1.4993, + "step": 1978 + }, + { + "epoch": 0.11030600300986568, + "grad_norm": 0.557270348072052, + "learning_rate": 9.778151390922341e-05, + "loss": 1.8278, + "step": 1979 + }, + { + "epoch": 0.11036174126302882, + "grad_norm": 0.570976972579956, + "learning_rate": 9.777889024145657e-05, + "loss": 1.9032, + "step": 1980 + }, + { + "epoch": 0.11041747951619196, + "grad_norm": 0.5794844031333923, + "learning_rate": 9.777626505842193e-05, + "loss": 1.8758, + "step": 1981 + }, + { + "epoch": 0.1104732177693551, + "grad_norm": 0.5161063075065613, + "learning_rate": 9.777363836020268e-05, + "loss": 1.8698, + "step": 1982 + }, + { + "epoch": 0.11052895602251825, + "grad_norm": 0.5546018481254578, + "learning_rate": 9.777101014688219e-05, + "loss": 1.87, + "step": 1983 + }, + { + "epoch": 0.1105846942756814, + "grad_norm": 0.5865330696105957, + "learning_rate": 9.776838041854377e-05, + "loss": 1.9022, + "step": 1984 + }, + { + "epoch": 0.11064043252884455, + "grad_norm": 0.5667337775230408, + "learning_rate": 9.776574917527083e-05, + "loss": 2.0603, + "step": 1985 + }, + { + "epoch": 0.11069617078200769, + "grad_norm": 0.5092570185661316, + "learning_rate": 9.776311641714683e-05, + "loss": 1.7887, + "step": 1986 + }, + { + "epoch": 0.11075190903517083, + "grad_norm": 0.5329071879386902, + "learning_rate": 9.776048214425525e-05, + "loss": 1.7294, + "step": 1987 + }, + { + "epoch": 0.11080764728833398, + "grad_norm": 0.5048893690109253, + "learning_rate": 9.775784635667964e-05, + "loss": 1.7357, + "step": 1988 + }, + { + "epoch": 0.11086338554149713, + "grad_norm": 0.4852405786514282, + "learning_rate": 9.77552090545036e-05, + "loss": 1.7027, + "step": 1989 + }, + { + "epoch": 0.11091912379466028, + "grad_norm": 0.5363536477088928, + "learning_rate": 9.775257023781074e-05, + "loss": 1.9082, + "step": 1990 + }, + { + "epoch": 0.11097486204782342, + "grad_norm": 0.5514358878135681, + "learning_rate": 9.774992990668479e-05, + "loss": 1.8572, + "step": 1991 + }, + { + "epoch": 0.11103060030098656, + "grad_norm": 0.5773457884788513, + "learning_rate": 9.774728806120945e-05, + "loss": 1.9287, + "step": 1992 + }, + { + "epoch": 0.11108633855414972, + "grad_norm": 0.5018163323402405, + "learning_rate": 9.774464470146851e-05, + "loss": 1.6721, + "step": 1993 + }, + { + "epoch": 0.11114207680731286, + "grad_norm": 0.5004386305809021, + "learning_rate": 9.774199982754584e-05, + "loss": 1.6999, + "step": 1994 + }, + { + "epoch": 0.111197815060476, + "grad_norm": 0.5078005194664001, + "learning_rate": 9.773935343952527e-05, + "loss": 1.6968, + "step": 1995 + }, + { + "epoch": 0.11125355331363915, + "grad_norm": 0.5355806946754456, + "learning_rate": 9.773670553749075e-05, + "loss": 1.8122, + "step": 1996 + }, + { + "epoch": 0.11130929156680229, + "grad_norm": 0.5051989555358887, + "learning_rate": 9.773405612152626e-05, + "loss": 1.6712, + "step": 1997 + }, + { + "epoch": 0.11136502981996545, + "grad_norm": 0.5549625754356384, + "learning_rate": 9.773140519171582e-05, + "loss": 1.8872, + "step": 1998 + }, + { + "epoch": 0.11142076807312859, + "grad_norm": 0.5879496335983276, + "learning_rate": 9.77287527481435e-05, + "loss": 1.7659, + "step": 1999 + }, + { + "epoch": 0.11147650632629173, + "grad_norm": 0.6350980401039124, + "learning_rate": 9.772609879089341e-05, + "loss": 1.9805, + "step": 2000 + }, + { + "epoch": 0.11153224457945488, + "grad_norm": 0.5255335569381714, + "learning_rate": 9.772344332004975e-05, + "loss": 1.7215, + "step": 2001 + }, + { + "epoch": 0.11158798283261803, + "grad_norm": 0.5538710355758667, + "learning_rate": 9.77207863356967e-05, + "loss": 1.8071, + "step": 2002 + }, + { + "epoch": 0.11164372108578118, + "grad_norm": 0.5447118878364563, + "learning_rate": 9.771812783791854e-05, + "loss": 1.6401, + "step": 2003 + }, + { + "epoch": 0.11169945933894432, + "grad_norm": 0.5420034527778625, + "learning_rate": 9.771546782679959e-05, + "loss": 1.7649, + "step": 2004 + }, + { + "epoch": 0.11175519759210746, + "grad_norm": 0.5717622637748718, + "learning_rate": 9.771280630242419e-05, + "loss": 1.9245, + "step": 2005 + }, + { + "epoch": 0.1118109358452706, + "grad_norm": 0.533752977848053, + "learning_rate": 9.771014326487675e-05, + "loss": 1.6562, + "step": 2006 + }, + { + "epoch": 0.11186667409843376, + "grad_norm": 0.5668651461601257, + "learning_rate": 9.770747871424175e-05, + "loss": 1.8504, + "step": 2007 + }, + { + "epoch": 0.1119224123515969, + "grad_norm": 0.5300382375717163, + "learning_rate": 9.770481265060368e-05, + "loss": 1.5858, + "step": 2008 + }, + { + "epoch": 0.11197815060476005, + "grad_norm": 0.5205538272857666, + "learning_rate": 9.770214507404709e-05, + "loss": 1.8421, + "step": 2009 + }, + { + "epoch": 0.11203388885792319, + "grad_norm": 0.5641254186630249, + "learning_rate": 9.769947598465657e-05, + "loss": 1.7521, + "step": 2010 + }, + { + "epoch": 0.11208962711108633, + "grad_norm": 0.5881509184837341, + "learning_rate": 9.76968053825168e-05, + "loss": 1.8359, + "step": 2011 + }, + { + "epoch": 0.11214536536424949, + "grad_norm": 0.5264688730239868, + "learning_rate": 9.769413326771243e-05, + "loss": 1.7792, + "step": 2012 + }, + { + "epoch": 0.11220110361741263, + "grad_norm": 0.5596029758453369, + "learning_rate": 9.769145964032824e-05, + "loss": 1.8502, + "step": 2013 + }, + { + "epoch": 0.11225684187057577, + "grad_norm": 0.5555474758148193, + "learning_rate": 9.768878450044902e-05, + "loss": 1.9158, + "step": 2014 + }, + { + "epoch": 0.11231258012373892, + "grad_norm": 0.5508490800857544, + "learning_rate": 9.768610784815959e-05, + "loss": 1.5545, + "step": 2015 + }, + { + "epoch": 0.11236831837690207, + "grad_norm": 0.5072826743125916, + "learning_rate": 9.768342968354484e-05, + "loss": 1.6679, + "step": 2016 + }, + { + "epoch": 0.11242405663006522, + "grad_norm": 0.4995681941509247, + "learning_rate": 9.768075000668974e-05, + "loss": 1.7114, + "step": 2017 + }, + { + "epoch": 0.11247979488322836, + "grad_norm": 0.5590416789054871, + "learning_rate": 9.767806881767923e-05, + "loss": 1.8553, + "step": 2018 + }, + { + "epoch": 0.1125355331363915, + "grad_norm": 0.542676568031311, + "learning_rate": 9.767538611659837e-05, + "loss": 1.9799, + "step": 2019 + }, + { + "epoch": 0.11259127138955465, + "grad_norm": 0.6015095710754395, + "learning_rate": 9.767270190353221e-05, + "loss": 2.0631, + "step": 2020 + }, + { + "epoch": 0.1126470096427178, + "grad_norm": 0.5182809829711914, + "learning_rate": 9.767001617856591e-05, + "loss": 1.8081, + "step": 2021 + }, + { + "epoch": 0.11270274789588094, + "grad_norm": 0.539851725101471, + "learning_rate": 9.766732894178463e-05, + "loss": 1.6224, + "step": 2022 + }, + { + "epoch": 0.11275848614904409, + "grad_norm": 0.5738646388053894, + "learning_rate": 9.766464019327359e-05, + "loss": 1.8425, + "step": 2023 + }, + { + "epoch": 0.11281422440220723, + "grad_norm": 0.5035516619682312, + "learning_rate": 9.766194993311809e-05, + "loss": 1.8101, + "step": 2024 + }, + { + "epoch": 0.11286996265537039, + "grad_norm": 0.4765785038471222, + "learning_rate": 9.76592581614034e-05, + "loss": 1.7461, + "step": 2025 + }, + { + "epoch": 0.11292570090853353, + "grad_norm": 0.5692024230957031, + "learning_rate": 9.765656487821492e-05, + "loss": 1.9905, + "step": 2026 + }, + { + "epoch": 0.11298143916169667, + "grad_norm": 0.5034509301185608, + "learning_rate": 9.765387008363807e-05, + "loss": 1.7689, + "step": 2027 + }, + { + "epoch": 0.11303717741485982, + "grad_norm": 0.5591553449630737, + "learning_rate": 9.76511737777583e-05, + "loss": 1.7994, + "step": 2028 + }, + { + "epoch": 0.11309291566802296, + "grad_norm": 0.533530592918396, + "learning_rate": 9.764847596066111e-05, + "loss": 1.5192, + "step": 2029 + }, + { + "epoch": 0.11314865392118612, + "grad_norm": 0.5049347281455994, + "learning_rate": 9.764577663243209e-05, + "loss": 1.5906, + "step": 2030 + }, + { + "epoch": 0.11320439217434926, + "grad_norm": 0.4710226058959961, + "learning_rate": 9.764307579315681e-05, + "loss": 1.4503, + "step": 2031 + }, + { + "epoch": 0.1132601304275124, + "grad_norm": 0.5490729212760925, + "learning_rate": 9.764037344292096e-05, + "loss": 1.7865, + "step": 2032 + }, + { + "epoch": 0.11331586868067554, + "grad_norm": 0.5714886784553528, + "learning_rate": 9.763766958181022e-05, + "loss": 1.6803, + "step": 2033 + }, + { + "epoch": 0.11337160693383869, + "grad_norm": 0.5637816786766052, + "learning_rate": 9.763496420991037e-05, + "loss": 1.902, + "step": 2034 + }, + { + "epoch": 0.11342734518700184, + "grad_norm": 0.5324851870536804, + "learning_rate": 9.763225732730716e-05, + "loss": 1.7774, + "step": 2035 + }, + { + "epoch": 0.11348308344016499, + "grad_norm": 0.542209267616272, + "learning_rate": 9.762954893408646e-05, + "loss": 1.7369, + "step": 2036 + }, + { + "epoch": 0.11353882169332813, + "grad_norm": 0.5353888273239136, + "learning_rate": 9.762683903033419e-05, + "loss": 1.914, + "step": 2037 + }, + { + "epoch": 0.11359455994649127, + "grad_norm": 0.5152493119239807, + "learning_rate": 9.762412761613624e-05, + "loss": 1.8155, + "step": 2038 + }, + { + "epoch": 0.11365029819965443, + "grad_norm": 0.4723453223705292, + "learning_rate": 9.762141469157865e-05, + "loss": 1.6183, + "step": 2039 + }, + { + "epoch": 0.11370603645281757, + "grad_norm": 0.5671008229255676, + "learning_rate": 9.761870025674743e-05, + "loss": 1.887, + "step": 2040 + }, + { + "epoch": 0.11376177470598071, + "grad_norm": 0.5240710377693176, + "learning_rate": 9.761598431172868e-05, + "loss": 1.7928, + "step": 2041 + }, + { + "epoch": 0.11381751295914386, + "grad_norm": 0.4852540194988251, + "learning_rate": 9.761326685660852e-05, + "loss": 1.6132, + "step": 2042 + }, + { + "epoch": 0.113873251212307, + "grad_norm": 0.46512627601623535, + "learning_rate": 9.761054789147315e-05, + "loss": 1.4053, + "step": 2043 + }, + { + "epoch": 0.11392898946547016, + "grad_norm": 0.5127692222595215, + "learning_rate": 9.760782741640879e-05, + "loss": 1.649, + "step": 2044 + }, + { + "epoch": 0.1139847277186333, + "grad_norm": 0.5368222594261169, + "learning_rate": 9.76051054315017e-05, + "loss": 1.7286, + "step": 2045 + }, + { + "epoch": 0.11404046597179644, + "grad_norm": 0.5699864625930786, + "learning_rate": 9.760238193683824e-05, + "loss": 1.7911, + "step": 2046 + }, + { + "epoch": 0.11409620422495959, + "grad_norm": 0.59310382604599, + "learning_rate": 9.759965693250477e-05, + "loss": 1.7731, + "step": 2047 + }, + { + "epoch": 0.11415194247812274, + "grad_norm": 0.5524492859840393, + "learning_rate": 9.75969304185877e-05, + "loss": 1.7917, + "step": 2048 + }, + { + "epoch": 0.11420768073128588, + "grad_norm": 0.529346227645874, + "learning_rate": 9.75942023951735e-05, + "loss": 1.7298, + "step": 2049 + }, + { + "epoch": 0.11426341898444903, + "grad_norm": 0.5188475847244263, + "learning_rate": 9.75914728623487e-05, + "loss": 1.8422, + "step": 2050 + }, + { + "epoch": 0.11431915723761217, + "grad_norm": 0.5141621232032776, + "learning_rate": 9.758874182019986e-05, + "loss": 1.7194, + "step": 2051 + }, + { + "epoch": 0.11437489549077531, + "grad_norm": 0.5103389024734497, + "learning_rate": 9.758600926881358e-05, + "loss": 1.782, + "step": 2052 + }, + { + "epoch": 0.11443063374393847, + "grad_norm": 0.5371511578559875, + "learning_rate": 9.758327520827654e-05, + "loss": 1.8925, + "step": 2053 + }, + { + "epoch": 0.11448637199710161, + "grad_norm": 0.528293788433075, + "learning_rate": 9.758053963867544e-05, + "loss": 1.5632, + "step": 2054 + }, + { + "epoch": 0.11454211025026476, + "grad_norm": 0.5670381784439087, + "learning_rate": 9.757780256009704e-05, + "loss": 2.0612, + "step": 2055 + }, + { + "epoch": 0.1145978485034279, + "grad_norm": 0.4997304677963257, + "learning_rate": 9.757506397262814e-05, + "loss": 1.4963, + "step": 2056 + }, + { + "epoch": 0.11465358675659104, + "grad_norm": 0.5154783129692078, + "learning_rate": 9.757232387635559e-05, + "loss": 1.7024, + "step": 2057 + }, + { + "epoch": 0.1147093250097542, + "grad_norm": 0.5076404213905334, + "learning_rate": 9.75695822713663e-05, + "loss": 1.7356, + "step": 2058 + }, + { + "epoch": 0.11476506326291734, + "grad_norm": 0.5490261912345886, + "learning_rate": 9.75668391577472e-05, + "loss": 1.9454, + "step": 2059 + }, + { + "epoch": 0.11482080151608048, + "grad_norm": 0.49244236946105957, + "learning_rate": 9.756409453558531e-05, + "loss": 1.7741, + "step": 2060 + }, + { + "epoch": 0.11487653976924363, + "grad_norm": 0.5007554292678833, + "learning_rate": 9.756134840496763e-05, + "loss": 1.6877, + "step": 2061 + }, + { + "epoch": 0.11493227802240678, + "grad_norm": 0.5688347816467285, + "learning_rate": 9.75586007659813e-05, + "loss": 1.8947, + "step": 2062 + }, + { + "epoch": 0.11498801627556993, + "grad_norm": 0.49076688289642334, + "learning_rate": 9.755585161871344e-05, + "loss": 1.632, + "step": 2063 + }, + { + "epoch": 0.11504375452873307, + "grad_norm": 0.5263219475746155, + "learning_rate": 9.755310096325123e-05, + "loss": 1.8176, + "step": 2064 + }, + { + "epoch": 0.11509949278189621, + "grad_norm": 0.5379471778869629, + "learning_rate": 9.755034879968193e-05, + "loss": 1.9844, + "step": 2065 + }, + { + "epoch": 0.11515523103505935, + "grad_norm": 0.6128638982772827, + "learning_rate": 9.754759512809277e-05, + "loss": 2.0891, + "step": 2066 + }, + { + "epoch": 0.11521096928822251, + "grad_norm": 0.513877272605896, + "learning_rate": 9.754483994857115e-05, + "loss": 1.7906, + "step": 2067 + }, + { + "epoch": 0.11526670754138565, + "grad_norm": 0.5699423551559448, + "learning_rate": 9.75420832612044e-05, + "loss": 1.9245, + "step": 2068 + }, + { + "epoch": 0.1153224457945488, + "grad_norm": 0.49974846839904785, + "learning_rate": 9.753932506607995e-05, + "loss": 1.5529, + "step": 2069 + }, + { + "epoch": 0.11537818404771194, + "grad_norm": 0.5551686882972717, + "learning_rate": 9.753656536328528e-05, + "loss": 1.7138, + "step": 2070 + }, + { + "epoch": 0.1154339223008751, + "grad_norm": 0.5302468538284302, + "learning_rate": 9.753380415290792e-05, + "loss": 1.7991, + "step": 2071 + }, + { + "epoch": 0.11548966055403824, + "grad_norm": 0.5461943745613098, + "learning_rate": 9.753104143503544e-05, + "loss": 1.6249, + "step": 2072 + }, + { + "epoch": 0.11554539880720138, + "grad_norm": 0.5242646336555481, + "learning_rate": 9.752827720975544e-05, + "loss": 1.7194, + "step": 2073 + }, + { + "epoch": 0.11560113706036453, + "grad_norm": 0.5647328495979309, + "learning_rate": 9.75255114771556e-05, + "loss": 1.6221, + "step": 2074 + }, + { + "epoch": 0.11565687531352767, + "grad_norm": 0.5108300447463989, + "learning_rate": 9.752274423732364e-05, + "loss": 1.5454, + "step": 2075 + }, + { + "epoch": 0.11571261356669083, + "grad_norm": 0.5370137691497803, + "learning_rate": 9.75199754903473e-05, + "loss": 1.8162, + "step": 2076 + }, + { + "epoch": 0.11576835181985397, + "grad_norm": 0.5308608412742615, + "learning_rate": 9.75172052363144e-05, + "loss": 1.8913, + "step": 2077 + }, + { + "epoch": 0.11582409007301711, + "grad_norm": 0.5060725808143616, + "learning_rate": 9.751443347531279e-05, + "loss": 1.6392, + "step": 2078 + }, + { + "epoch": 0.11587982832618025, + "grad_norm": 0.5402329564094543, + "learning_rate": 9.751166020743037e-05, + "loss": 1.6481, + "step": 2079 + }, + { + "epoch": 0.1159355665793434, + "grad_norm": 0.5728126168251038, + "learning_rate": 9.750888543275511e-05, + "loss": 1.7507, + "step": 2080 + }, + { + "epoch": 0.11599130483250655, + "grad_norm": 0.5055838227272034, + "learning_rate": 9.750610915137502e-05, + "loss": 1.7667, + "step": 2081 + }, + { + "epoch": 0.1160470430856697, + "grad_norm": 0.5178690552711487, + "learning_rate": 9.750333136337811e-05, + "loss": 1.7303, + "step": 2082 + }, + { + "epoch": 0.11610278133883284, + "grad_norm": 0.5922085642814636, + "learning_rate": 9.750055206885249e-05, + "loss": 1.9936, + "step": 2083 + }, + { + "epoch": 0.11615851959199598, + "grad_norm": 0.5285540223121643, + "learning_rate": 9.74977712678863e-05, + "loss": 1.8642, + "step": 2084 + }, + { + "epoch": 0.11621425784515914, + "grad_norm": 0.5517610907554626, + "learning_rate": 9.749498896056775e-05, + "loss": 1.8, + "step": 2085 + }, + { + "epoch": 0.11626999609832228, + "grad_norm": 0.519136905670166, + "learning_rate": 9.749220514698505e-05, + "loss": 1.8553, + "step": 2086 + }, + { + "epoch": 0.11632573435148542, + "grad_norm": 0.47392770648002625, + "learning_rate": 9.748941982722652e-05, + "loss": 1.5635, + "step": 2087 + }, + { + "epoch": 0.11638147260464857, + "grad_norm": 0.5580193400382996, + "learning_rate": 9.748663300138046e-05, + "loss": 2.0887, + "step": 2088 + }, + { + "epoch": 0.11643721085781171, + "grad_norm": 0.5110911726951599, + "learning_rate": 9.748384466953529e-05, + "loss": 1.7254, + "step": 2089 + }, + { + "epoch": 0.11649294911097487, + "grad_norm": 0.5411677360534668, + "learning_rate": 9.748105483177939e-05, + "loss": 2.0895, + "step": 2090 + }, + { + "epoch": 0.11654868736413801, + "grad_norm": 0.5149423480033875, + "learning_rate": 9.747826348820129e-05, + "loss": 1.6339, + "step": 2091 + }, + { + "epoch": 0.11660442561730115, + "grad_norm": 0.48806729912757874, + "learning_rate": 9.747547063888947e-05, + "loss": 1.8714, + "step": 2092 + }, + { + "epoch": 0.1166601638704643, + "grad_norm": 0.5147302746772766, + "learning_rate": 9.747267628393252e-05, + "loss": 1.8269, + "step": 2093 + }, + { + "epoch": 0.11671590212362745, + "grad_norm": 0.512217104434967, + "learning_rate": 9.746988042341906e-05, + "loss": 1.7604, + "step": 2094 + }, + { + "epoch": 0.1167716403767906, + "grad_norm": 0.66917484998703, + "learning_rate": 9.746708305743778e-05, + "loss": 2.2348, + "step": 2095 + }, + { + "epoch": 0.11682737862995374, + "grad_norm": 0.5376080870628357, + "learning_rate": 9.746428418607737e-05, + "loss": 1.811, + "step": 2096 + }, + { + "epoch": 0.11688311688311688, + "grad_norm": 0.5490595102310181, + "learning_rate": 9.746148380942661e-05, + "loss": 1.7822, + "step": 2097 + }, + { + "epoch": 0.11693885513628002, + "grad_norm": 0.5195513367652893, + "learning_rate": 9.745868192757429e-05, + "loss": 1.815, + "step": 2098 + }, + { + "epoch": 0.11699459338944318, + "grad_norm": 0.4978055953979492, + "learning_rate": 9.745587854060929e-05, + "loss": 1.6799, + "step": 2099 + }, + { + "epoch": 0.11705033164260632, + "grad_norm": 0.47539737820625305, + "learning_rate": 9.74530736486205e-05, + "loss": 1.3444, + "step": 2100 + }, + { + "epoch": 0.11710606989576947, + "grad_norm": 0.49834421277046204, + "learning_rate": 9.74502672516969e-05, + "loss": 1.6343, + "step": 2101 + }, + { + "epoch": 0.11716180814893261, + "grad_norm": 0.5414234399795532, + "learning_rate": 9.744745934992747e-05, + "loss": 1.8732, + "step": 2102 + }, + { + "epoch": 0.11721754640209577, + "grad_norm": 0.55171799659729, + "learning_rate": 9.744464994340126e-05, + "loss": 1.823, + "step": 2103 + }, + { + "epoch": 0.11727328465525891, + "grad_norm": 0.545732319355011, + "learning_rate": 9.744183903220738e-05, + "loss": 1.6152, + "step": 2104 + }, + { + "epoch": 0.11732902290842205, + "grad_norm": 0.5116435885429382, + "learning_rate": 9.743902661643498e-05, + "loss": 1.8159, + "step": 2105 + }, + { + "epoch": 0.1173847611615852, + "grad_norm": 0.5736915469169617, + "learning_rate": 9.743621269617324e-05, + "loss": 2.0891, + "step": 2106 + }, + { + "epoch": 0.11744049941474834, + "grad_norm": 0.5401880741119385, + "learning_rate": 9.74333972715114e-05, + "loss": 1.6851, + "step": 2107 + }, + { + "epoch": 0.1174962376679115, + "grad_norm": 0.4980708658695221, + "learning_rate": 9.743058034253876e-05, + "loss": 1.7487, + "step": 2108 + }, + { + "epoch": 0.11755197592107464, + "grad_norm": 0.5513383150100708, + "learning_rate": 9.742776190934464e-05, + "loss": 1.7077, + "step": 2109 + }, + { + "epoch": 0.11760771417423778, + "grad_norm": 0.48612821102142334, + "learning_rate": 9.742494197201845e-05, + "loss": 1.7193, + "step": 2110 + }, + { + "epoch": 0.11766345242740092, + "grad_norm": 0.5319970846176147, + "learning_rate": 9.742212053064959e-05, + "loss": 1.8341, + "step": 2111 + }, + { + "epoch": 0.11771919068056406, + "grad_norm": 0.5188704133033752, + "learning_rate": 9.741929758532758e-05, + "loss": 1.7452, + "step": 2112 + }, + { + "epoch": 0.11777492893372722, + "grad_norm": 0.569303035736084, + "learning_rate": 9.741647313614191e-05, + "loss": 1.7242, + "step": 2113 + }, + { + "epoch": 0.11783066718689036, + "grad_norm": 0.5230869650840759, + "learning_rate": 9.741364718318216e-05, + "loss": 1.7484, + "step": 2114 + }, + { + "epoch": 0.11788640544005351, + "grad_norm": 0.5458916425704956, + "learning_rate": 9.741081972653798e-05, + "loss": 1.8975, + "step": 2115 + }, + { + "epoch": 0.11794214369321665, + "grad_norm": 0.5454350113868713, + "learning_rate": 9.740799076629902e-05, + "loss": 1.7848, + "step": 2116 + }, + { + "epoch": 0.1179978819463798, + "grad_norm": 0.5229981541633606, + "learning_rate": 9.7405160302555e-05, + "loss": 1.7087, + "step": 2117 + }, + { + "epoch": 0.11805362019954295, + "grad_norm": 0.5540334582328796, + "learning_rate": 9.740232833539567e-05, + "loss": 1.712, + "step": 2118 + }, + { + "epoch": 0.11810935845270609, + "grad_norm": 0.5371966361999512, + "learning_rate": 9.739949486491088e-05, + "loss": 1.6682, + "step": 2119 + }, + { + "epoch": 0.11816509670586924, + "grad_norm": 0.5578680038452148, + "learning_rate": 9.739665989119047e-05, + "loss": 1.7035, + "step": 2120 + }, + { + "epoch": 0.11822083495903238, + "grad_norm": 0.49404215812683105, + "learning_rate": 9.739382341432434e-05, + "loss": 1.6535, + "step": 2121 + }, + { + "epoch": 0.11827657321219553, + "grad_norm": 0.5198866724967957, + "learning_rate": 9.739098543440246e-05, + "loss": 1.9483, + "step": 2122 + }, + { + "epoch": 0.11833231146535868, + "grad_norm": 0.5561308860778809, + "learning_rate": 9.738814595151481e-05, + "loss": 1.6287, + "step": 2123 + }, + { + "epoch": 0.11838804971852182, + "grad_norm": 0.5929575562477112, + "learning_rate": 9.73853049657515e-05, + "loss": 1.8991, + "step": 2124 + }, + { + "epoch": 0.11844378797168496, + "grad_norm": 0.5198292136192322, + "learning_rate": 9.738246247720257e-05, + "loss": 1.7004, + "step": 2125 + }, + { + "epoch": 0.11849952622484812, + "grad_norm": 0.4800911247730255, + "learning_rate": 9.73796184859582e-05, + "loss": 1.8126, + "step": 2126 + }, + { + "epoch": 0.11855526447801126, + "grad_norm": 0.5122108459472656, + "learning_rate": 9.737677299210857e-05, + "loss": 1.6761, + "step": 2127 + }, + { + "epoch": 0.1186110027311744, + "grad_norm": 0.5015464425086975, + "learning_rate": 9.737392599574391e-05, + "loss": 1.6405, + "step": 2128 + }, + { + "epoch": 0.11866674098433755, + "grad_norm": 0.560658872127533, + "learning_rate": 9.737107749695456e-05, + "loss": 1.8458, + "step": 2129 + }, + { + "epoch": 0.11872247923750069, + "grad_norm": 0.5312667489051819, + "learning_rate": 9.73682274958308e-05, + "loss": 1.9419, + "step": 2130 + }, + { + "epoch": 0.11877821749066385, + "grad_norm": 0.5537664294242859, + "learning_rate": 9.736537599246305e-05, + "loss": 2.0495, + "step": 2131 + }, + { + "epoch": 0.11883395574382699, + "grad_norm": 0.5166563391685486, + "learning_rate": 9.736252298694172e-05, + "loss": 1.7997, + "step": 2132 + }, + { + "epoch": 0.11888969399699013, + "grad_norm": 0.5567119121551514, + "learning_rate": 9.735966847935732e-05, + "loss": 2.0086, + "step": 2133 + }, + { + "epoch": 0.11894543225015328, + "grad_norm": 0.5614973306655884, + "learning_rate": 9.735681246980035e-05, + "loss": 1.8669, + "step": 2134 + }, + { + "epoch": 0.11900117050331642, + "grad_norm": 0.4755729138851166, + "learning_rate": 9.73539549583614e-05, + "loss": 1.4678, + "step": 2135 + }, + { + "epoch": 0.11905690875647958, + "grad_norm": 0.5338446497917175, + "learning_rate": 9.73510959451311e-05, + "loss": 1.758, + "step": 2136 + }, + { + "epoch": 0.11911264700964272, + "grad_norm": 0.5301800966262817, + "learning_rate": 9.734823543020009e-05, + "loss": 1.6377, + "step": 2137 + }, + { + "epoch": 0.11916838526280586, + "grad_norm": 0.5584478378295898, + "learning_rate": 9.734537341365914e-05, + "loss": 1.8973, + "step": 2138 + }, + { + "epoch": 0.119224123515969, + "grad_norm": 0.5499609112739563, + "learning_rate": 9.734250989559896e-05, + "loss": 1.8316, + "step": 2139 + }, + { + "epoch": 0.11927986176913216, + "grad_norm": 0.5567249655723572, + "learning_rate": 9.733964487611042e-05, + "loss": 1.9231, + "step": 2140 + }, + { + "epoch": 0.1193356000222953, + "grad_norm": 0.5121795535087585, + "learning_rate": 9.733677835528434e-05, + "loss": 1.7316, + "step": 2141 + }, + { + "epoch": 0.11939133827545845, + "grad_norm": 0.5235653519630432, + "learning_rate": 9.733391033321164e-05, + "loss": 1.7328, + "step": 2142 + }, + { + "epoch": 0.11944707652862159, + "grad_norm": 0.5482314229011536, + "learning_rate": 9.733104080998329e-05, + "loss": 1.9832, + "step": 2143 + }, + { + "epoch": 0.11950281478178473, + "grad_norm": 0.4945628345012665, + "learning_rate": 9.732816978569028e-05, + "loss": 1.6102, + "step": 2144 + }, + { + "epoch": 0.11955855303494789, + "grad_norm": 0.532642126083374, + "learning_rate": 9.732529726042365e-05, + "loss": 1.6543, + "step": 2145 + }, + { + "epoch": 0.11961429128811103, + "grad_norm": 0.5531574487686157, + "learning_rate": 9.732242323427455e-05, + "loss": 1.8017, + "step": 2146 + }, + { + "epoch": 0.11967002954127418, + "grad_norm": 0.595876932144165, + "learning_rate": 9.731954770733407e-05, + "loss": 2.0041, + "step": 2147 + }, + { + "epoch": 0.11972576779443732, + "grad_norm": 0.5025404095649719, + "learning_rate": 9.731667067969344e-05, + "loss": 1.716, + "step": 2148 + }, + { + "epoch": 0.11978150604760048, + "grad_norm": 0.5070561766624451, + "learning_rate": 9.731379215144388e-05, + "loss": 1.8201, + "step": 2149 + }, + { + "epoch": 0.11983724430076362, + "grad_norm": 0.5182836651802063, + "learning_rate": 9.73109121226767e-05, + "loss": 1.51, + "step": 2150 + }, + { + "epoch": 0.11989298255392676, + "grad_norm": 0.5657908320426941, + "learning_rate": 9.730803059348323e-05, + "loss": 2.0817, + "step": 2151 + }, + { + "epoch": 0.1199487208070899, + "grad_norm": 0.5556692481040955, + "learning_rate": 9.730514756395485e-05, + "loss": 1.854, + "step": 2152 + }, + { + "epoch": 0.12000445906025305, + "grad_norm": 0.4503386616706848, + "learning_rate": 9.7302263034183e-05, + "loss": 1.4719, + "step": 2153 + }, + { + "epoch": 0.1200601973134162, + "grad_norm": 0.5425733327865601, + "learning_rate": 9.729937700425916e-05, + "loss": 1.8686, + "step": 2154 + }, + { + "epoch": 0.12011593556657935, + "grad_norm": 0.5144285559654236, + "learning_rate": 9.729648947427484e-05, + "loss": 1.8232, + "step": 2155 + }, + { + "epoch": 0.12017167381974249, + "grad_norm": 0.5346119999885559, + "learning_rate": 9.729360044432166e-05, + "loss": 1.7735, + "step": 2156 + }, + { + "epoch": 0.12022741207290563, + "grad_norm": 0.5558546185493469, + "learning_rate": 9.729070991449119e-05, + "loss": 1.9485, + "step": 2157 + }, + { + "epoch": 0.12028315032606877, + "grad_norm": 0.495919406414032, + "learning_rate": 9.728781788487513e-05, + "loss": 1.6713, + "step": 2158 + }, + { + "epoch": 0.12033888857923193, + "grad_norm": 0.5348759889602661, + "learning_rate": 9.72849243555652e-05, + "loss": 1.6913, + "step": 2159 + }, + { + "epoch": 0.12039462683239507, + "grad_norm": 0.5228710174560547, + "learning_rate": 9.728202932665316e-05, + "loss": 1.6557, + "step": 2160 + }, + { + "epoch": 0.12045036508555822, + "grad_norm": 0.49766623973846436, + "learning_rate": 9.727913279823081e-05, + "loss": 1.6087, + "step": 2161 + }, + { + "epoch": 0.12050610333872136, + "grad_norm": 0.5042500495910645, + "learning_rate": 9.727623477039005e-05, + "loss": 1.8017, + "step": 2162 + }, + { + "epoch": 0.12056184159188452, + "grad_norm": 0.5221708416938782, + "learning_rate": 9.727333524322274e-05, + "loss": 1.7577, + "step": 2163 + }, + { + "epoch": 0.12061757984504766, + "grad_norm": 0.5310743451118469, + "learning_rate": 9.727043421682087e-05, + "loss": 1.7025, + "step": 2164 + }, + { + "epoch": 0.1206733180982108, + "grad_norm": 0.5771050453186035, + "learning_rate": 9.726753169127643e-05, + "loss": 1.8185, + "step": 2165 + }, + { + "epoch": 0.12072905635137395, + "grad_norm": 0.4827874004840851, + "learning_rate": 9.726462766668147e-05, + "loss": 1.5869, + "step": 2166 + }, + { + "epoch": 0.12078479460453709, + "grad_norm": 0.5001873970031738, + "learning_rate": 9.72617221431281e-05, + "loss": 1.6207, + "step": 2167 + }, + { + "epoch": 0.12084053285770024, + "grad_norm": 0.47895923256874084, + "learning_rate": 9.725881512070845e-05, + "loss": 1.5611, + "step": 2168 + }, + { + "epoch": 0.12089627111086339, + "grad_norm": 0.5227773785591125, + "learning_rate": 9.725590659951473e-05, + "loss": 1.7524, + "step": 2169 + }, + { + "epoch": 0.12095200936402653, + "grad_norm": 0.5513851046562195, + "learning_rate": 9.725299657963916e-05, + "loss": 1.9093, + "step": 2170 + }, + { + "epoch": 0.12100774761718967, + "grad_norm": 0.5206924080848694, + "learning_rate": 9.725008506117405e-05, + "loss": 1.6196, + "step": 2171 + }, + { + "epoch": 0.12106348587035283, + "grad_norm": 0.5124804377555847, + "learning_rate": 9.724717204421175e-05, + "loss": 1.5592, + "step": 2172 + }, + { + "epoch": 0.12111922412351597, + "grad_norm": 0.49579185247421265, + "learning_rate": 9.724425752884458e-05, + "loss": 1.7796, + "step": 2173 + }, + { + "epoch": 0.12117496237667912, + "grad_norm": 0.4806743562221527, + "learning_rate": 9.724134151516504e-05, + "loss": 1.5684, + "step": 2174 + }, + { + "epoch": 0.12123070062984226, + "grad_norm": 0.5735479593276978, + "learning_rate": 9.72384240032656e-05, + "loss": 1.9183, + "step": 2175 + }, + { + "epoch": 0.1212864388830054, + "grad_norm": 0.49125027656555176, + "learning_rate": 9.723550499323874e-05, + "loss": 1.5609, + "step": 2176 + }, + { + "epoch": 0.12134217713616856, + "grad_norm": 0.5535476207733154, + "learning_rate": 9.723258448517707e-05, + "loss": 1.8593, + "step": 2177 + }, + { + "epoch": 0.1213979153893317, + "grad_norm": 0.5923840403556824, + "learning_rate": 9.722966247917322e-05, + "loss": 1.8673, + "step": 2178 + }, + { + "epoch": 0.12145365364249484, + "grad_norm": 0.5120698809623718, + "learning_rate": 9.722673897531983e-05, + "loss": 1.6219, + "step": 2179 + }, + { + "epoch": 0.12150939189565799, + "grad_norm": 0.5636369585990906, + "learning_rate": 9.722381397370963e-05, + "loss": 1.9298, + "step": 2180 + }, + { + "epoch": 0.12156513014882113, + "grad_norm": 0.5421077609062195, + "learning_rate": 9.722088747443539e-05, + "loss": 1.4028, + "step": 2181 + }, + { + "epoch": 0.12162086840198429, + "grad_norm": 0.5058643817901611, + "learning_rate": 9.721795947758991e-05, + "loss": 1.6988, + "step": 2182 + }, + { + "epoch": 0.12167660665514743, + "grad_norm": 0.5012438297271729, + "learning_rate": 9.721502998326607e-05, + "loss": 1.6624, + "step": 2183 + }, + { + "epoch": 0.12173234490831057, + "grad_norm": 0.47187769412994385, + "learning_rate": 9.721209899155675e-05, + "loss": 1.5275, + "step": 2184 + }, + { + "epoch": 0.12178808316147371, + "grad_norm": 0.525303065776825, + "learning_rate": 9.720916650255492e-05, + "loss": 1.7458, + "step": 2185 + }, + { + "epoch": 0.12184382141463687, + "grad_norm": 0.586681604385376, + "learning_rate": 9.720623251635357e-05, + "loss": 1.7205, + "step": 2186 + }, + { + "epoch": 0.12189955966780001, + "grad_norm": 0.5550994873046875, + "learning_rate": 9.720329703304577e-05, + "loss": 1.6508, + "step": 2187 + }, + { + "epoch": 0.12195529792096316, + "grad_norm": 0.5518259406089783, + "learning_rate": 9.720036005272459e-05, + "loss": 1.7847, + "step": 2188 + }, + { + "epoch": 0.1220110361741263, + "grad_norm": 0.4833231270313263, + "learning_rate": 9.719742157548319e-05, + "loss": 1.578, + "step": 2189 + }, + { + "epoch": 0.12206677442728944, + "grad_norm": 0.5002262592315674, + "learning_rate": 9.719448160141476e-05, + "loss": 1.7526, + "step": 2190 + }, + { + "epoch": 0.1221225126804526, + "grad_norm": 0.4701862335205078, + "learning_rate": 9.719154013061253e-05, + "loss": 1.369, + "step": 2191 + }, + { + "epoch": 0.12217825093361574, + "grad_norm": 0.5255539417266846, + "learning_rate": 9.71885971631698e-05, + "loss": 1.9266, + "step": 2192 + }, + { + "epoch": 0.12223398918677889, + "grad_norm": 0.5181805491447449, + "learning_rate": 9.71856526991799e-05, + "loss": 1.8049, + "step": 2193 + }, + { + "epoch": 0.12228972743994203, + "grad_norm": 0.5119277834892273, + "learning_rate": 9.71827067387362e-05, + "loss": 1.6141, + "step": 2194 + }, + { + "epoch": 0.12234546569310518, + "grad_norm": 0.46822264790534973, + "learning_rate": 9.717975928193214e-05, + "loss": 1.4462, + "step": 2195 + }, + { + "epoch": 0.12240120394626833, + "grad_norm": 0.5520098209381104, + "learning_rate": 9.717681032886119e-05, + "loss": 1.7872, + "step": 2196 + }, + { + "epoch": 0.12245694219943147, + "grad_norm": 0.5204572677612305, + "learning_rate": 9.717385987961686e-05, + "loss": 1.7539, + "step": 2197 + }, + { + "epoch": 0.12251268045259461, + "grad_norm": 0.5343250036239624, + "learning_rate": 9.717090793429276e-05, + "loss": 1.8575, + "step": 2198 + }, + { + "epoch": 0.12256841870575776, + "grad_norm": 0.521108865737915, + "learning_rate": 9.716795449298248e-05, + "loss": 1.9104, + "step": 2199 + }, + { + "epoch": 0.12262415695892091, + "grad_norm": 0.49352675676345825, + "learning_rate": 9.71649995557797e-05, + "loss": 1.6201, + "step": 2200 + }, + { + "epoch": 0.12267989521208406, + "grad_norm": 0.5716384649276733, + "learning_rate": 9.716204312277812e-05, + "loss": 1.928, + "step": 2201 + }, + { + "epoch": 0.1227356334652472, + "grad_norm": 0.5332071781158447, + "learning_rate": 9.715908519407149e-05, + "loss": 1.6348, + "step": 2202 + }, + { + "epoch": 0.12279137171841034, + "grad_norm": 0.5008523464202881, + "learning_rate": 9.715612576975366e-05, + "loss": 1.8211, + "step": 2203 + }, + { + "epoch": 0.12284710997157348, + "grad_norm": 0.5112088322639465, + "learning_rate": 9.715316484991845e-05, + "loss": 1.8334, + "step": 2204 + }, + { + "epoch": 0.12290284822473664, + "grad_norm": 0.5519534349441528, + "learning_rate": 9.715020243465976e-05, + "loss": 1.8001, + "step": 2205 + }, + { + "epoch": 0.12295858647789978, + "grad_norm": 0.46493321657180786, + "learning_rate": 9.714723852407157e-05, + "loss": 1.4173, + "step": 2206 + }, + { + "epoch": 0.12301432473106293, + "grad_norm": 0.5702951550483704, + "learning_rate": 9.714427311824786e-05, + "loss": 1.7186, + "step": 2207 + }, + { + "epoch": 0.12307006298422607, + "grad_norm": 0.5255847573280334, + "learning_rate": 9.714130621728266e-05, + "loss": 1.6884, + "step": 2208 + }, + { + "epoch": 0.12312580123738923, + "grad_norm": 0.581146776676178, + "learning_rate": 9.713833782127008e-05, + "loss": 1.8707, + "step": 2209 + }, + { + "epoch": 0.12318153949055237, + "grad_norm": 0.5044531226158142, + "learning_rate": 9.713536793030429e-05, + "loss": 1.555, + "step": 2210 + }, + { + "epoch": 0.12323727774371551, + "grad_norm": 0.543787956237793, + "learning_rate": 9.713239654447943e-05, + "loss": 1.8188, + "step": 2211 + }, + { + "epoch": 0.12329301599687865, + "grad_norm": 0.6438772678375244, + "learning_rate": 9.712942366388975e-05, + "loss": 1.8096, + "step": 2212 + }, + { + "epoch": 0.1233487542500418, + "grad_norm": 0.5758397579193115, + "learning_rate": 9.712644928862953e-05, + "loss": 1.8329, + "step": 2213 + }, + { + "epoch": 0.12340449250320495, + "grad_norm": 0.5573188066482544, + "learning_rate": 9.712347341879311e-05, + "loss": 1.8994, + "step": 2214 + }, + { + "epoch": 0.1234602307563681, + "grad_norm": 0.5477108359336853, + "learning_rate": 9.712049605447486e-05, + "loss": 1.8856, + "step": 2215 + }, + { + "epoch": 0.12351596900953124, + "grad_norm": 0.5133275985717773, + "learning_rate": 9.711751719576922e-05, + "loss": 1.7319, + "step": 2216 + }, + { + "epoch": 0.12357170726269438, + "grad_norm": 0.5406665802001953, + "learning_rate": 9.711453684277063e-05, + "loss": 1.9889, + "step": 2217 + }, + { + "epoch": 0.12362744551585754, + "grad_norm": 0.48421719670295715, + "learning_rate": 9.711155499557364e-05, + "loss": 1.5177, + "step": 2218 + }, + { + "epoch": 0.12368318376902068, + "grad_norm": 0.5295604467391968, + "learning_rate": 9.710857165427281e-05, + "loss": 1.5376, + "step": 2219 + }, + { + "epoch": 0.12373892202218383, + "grad_norm": 0.5241243243217468, + "learning_rate": 9.710558681896274e-05, + "loss": 1.7389, + "step": 2220 + }, + { + "epoch": 0.12379466027534697, + "grad_norm": 0.48620593547821045, + "learning_rate": 9.71026004897381e-05, + "loss": 1.7281, + "step": 2221 + }, + { + "epoch": 0.12385039852851011, + "grad_norm": 0.5162755846977234, + "learning_rate": 9.70996126666936e-05, + "loss": 1.6421, + "step": 2222 + }, + { + "epoch": 0.12390613678167327, + "grad_norm": 0.5603106021881104, + "learning_rate": 9.7096623349924e-05, + "loss": 2.0405, + "step": 2223 + }, + { + "epoch": 0.12396187503483641, + "grad_norm": 0.5636157393455505, + "learning_rate": 9.70936325395241e-05, + "loss": 1.7629, + "step": 2224 + }, + { + "epoch": 0.12401761328799955, + "grad_norm": 0.5287961363792419, + "learning_rate": 9.709064023558874e-05, + "loss": 1.7357, + "step": 2225 + }, + { + "epoch": 0.1240733515411627, + "grad_norm": 0.5584306120872498, + "learning_rate": 9.708764643821284e-05, + "loss": 1.905, + "step": 2226 + }, + { + "epoch": 0.12412908979432584, + "grad_norm": 0.5021309852600098, + "learning_rate": 9.708465114749132e-05, + "loss": 1.7439, + "step": 2227 + }, + { + "epoch": 0.124184828047489, + "grad_norm": 0.5482348799705505, + "learning_rate": 9.708165436351921e-05, + "loss": 1.7851, + "step": 2228 + }, + { + "epoch": 0.12424056630065214, + "grad_norm": 0.498470276594162, + "learning_rate": 9.707865608639152e-05, + "loss": 1.494, + "step": 2229 + }, + { + "epoch": 0.12429630455381528, + "grad_norm": 0.5526018142700195, + "learning_rate": 9.707565631620334e-05, + "loss": 1.973, + "step": 2230 + }, + { + "epoch": 0.12435204280697842, + "grad_norm": 0.5773054957389832, + "learning_rate": 9.707265505304982e-05, + "loss": 1.9693, + "step": 2231 + }, + { + "epoch": 0.12440778106014158, + "grad_norm": 0.5307757258415222, + "learning_rate": 9.706965229702614e-05, + "loss": 1.8978, + "step": 2232 + }, + { + "epoch": 0.12446351931330472, + "grad_norm": 0.5740475654602051, + "learning_rate": 9.70666480482275e-05, + "loss": 2.0298, + "step": 2233 + }, + { + "epoch": 0.12451925756646787, + "grad_norm": 0.5156608819961548, + "learning_rate": 9.706364230674923e-05, + "loss": 1.5383, + "step": 2234 + }, + { + "epoch": 0.12457499581963101, + "grad_norm": 0.4921102225780487, + "learning_rate": 9.706063507268661e-05, + "loss": 1.6472, + "step": 2235 + }, + { + "epoch": 0.12463073407279415, + "grad_norm": 0.5701449513435364, + "learning_rate": 9.705762634613502e-05, + "loss": 1.7692, + "step": 2236 + }, + { + "epoch": 0.12468647232595731, + "grad_norm": 0.49713411927223206, + "learning_rate": 9.705461612718991e-05, + "loss": 1.5998, + "step": 2237 + }, + { + "epoch": 0.12474221057912045, + "grad_norm": 0.5252828598022461, + "learning_rate": 9.705160441594671e-05, + "loss": 1.6545, + "step": 2238 + }, + { + "epoch": 0.1247979488322836, + "grad_norm": 0.543063759803772, + "learning_rate": 9.704859121250095e-05, + "loss": 1.8984, + "step": 2239 + }, + { + "epoch": 0.12485368708544674, + "grad_norm": 0.5450255274772644, + "learning_rate": 9.704557651694818e-05, + "loss": 1.7794, + "step": 2240 + }, + { + "epoch": 0.1249094253386099, + "grad_norm": 0.4936400353908539, + "learning_rate": 9.704256032938403e-05, + "loss": 1.4191, + "step": 2241 + }, + { + "epoch": 0.12496516359177304, + "grad_norm": 0.5075535774230957, + "learning_rate": 9.703954264990414e-05, + "loss": 1.7634, + "step": 2242 + }, + { + "epoch": 0.12502090184493617, + "grad_norm": 0.5337166786193848, + "learning_rate": 9.703652347860422e-05, + "loss": 1.9257, + "step": 2243 + }, + { + "epoch": 0.12507664009809932, + "grad_norm": 0.5265361666679382, + "learning_rate": 9.703350281558002e-05, + "loss": 1.8102, + "step": 2244 + }, + { + "epoch": 0.12513237835126248, + "grad_norm": 0.5706486701965332, + "learning_rate": 9.703048066092733e-05, + "loss": 2.1658, + "step": 2245 + }, + { + "epoch": 0.1251881166044256, + "grad_norm": 0.5012516975402832, + "learning_rate": 9.7027457014742e-05, + "loss": 1.6586, + "step": 2246 + }, + { + "epoch": 0.12524385485758877, + "grad_norm": 0.5617608428001404, + "learning_rate": 9.702443187711992e-05, + "loss": 1.7678, + "step": 2247 + }, + { + "epoch": 0.12529959311075192, + "grad_norm": 0.5820160508155823, + "learning_rate": 9.702140524815704e-05, + "loss": 1.848, + "step": 2248 + }, + { + "epoch": 0.12535533136391505, + "grad_norm": 0.5511069297790527, + "learning_rate": 9.701837712794932e-05, + "loss": 1.8369, + "step": 2249 + }, + { + "epoch": 0.1254110696170782, + "grad_norm": 0.5301650166511536, + "learning_rate": 9.701534751659283e-05, + "loss": 1.8621, + "step": 2250 + }, + { + "epoch": 0.12546680787024134, + "grad_norm": 0.519693911075592, + "learning_rate": 9.701231641418363e-05, + "loss": 1.7069, + "step": 2251 + }, + { + "epoch": 0.1255225461234045, + "grad_norm": 0.5177733302116394, + "learning_rate": 9.700928382081786e-05, + "loss": 1.7311, + "step": 2252 + }, + { + "epoch": 0.12557828437656765, + "grad_norm": 0.5452710390090942, + "learning_rate": 9.700624973659169e-05, + "loss": 1.6022, + "step": 2253 + }, + { + "epoch": 0.12563402262973078, + "grad_norm": 0.49126002192497253, + "learning_rate": 9.700321416160134e-05, + "loss": 1.6004, + "step": 2254 + }, + { + "epoch": 0.12568976088289394, + "grad_norm": 0.4859536290168762, + "learning_rate": 9.70001770959431e-05, + "loss": 1.627, + "step": 2255 + }, + { + "epoch": 0.12574549913605707, + "grad_norm": 0.5808461308479309, + "learning_rate": 9.699713853971324e-05, + "loss": 1.9893, + "step": 2256 + }, + { + "epoch": 0.12580123738922022, + "grad_norm": 0.5044426321983337, + "learning_rate": 9.699409849300818e-05, + "loss": 1.6269, + "step": 2257 + }, + { + "epoch": 0.12585697564238338, + "grad_norm": 0.5458354353904724, + "learning_rate": 9.69910569559243e-05, + "loss": 1.6803, + "step": 2258 + }, + { + "epoch": 0.1259127138955465, + "grad_norm": 0.5350721478462219, + "learning_rate": 9.698801392855808e-05, + "loss": 1.7217, + "step": 2259 + }, + { + "epoch": 0.12596845214870966, + "grad_norm": 0.511223554611206, + "learning_rate": 9.698496941100601e-05, + "loss": 1.6904, + "step": 2260 + }, + { + "epoch": 0.1260241904018728, + "grad_norm": 0.46969008445739746, + "learning_rate": 9.698192340336468e-05, + "loss": 1.5411, + "step": 2261 + }, + { + "epoch": 0.12607992865503595, + "grad_norm": 0.5638684630393982, + "learning_rate": 9.697887590573063e-05, + "loss": 1.6144, + "step": 2262 + }, + { + "epoch": 0.1261356669081991, + "grad_norm": 0.5146279335021973, + "learning_rate": 9.697582691820054e-05, + "loss": 1.605, + "step": 2263 + }, + { + "epoch": 0.12619140516136224, + "grad_norm": 0.46321019530296326, + "learning_rate": 9.697277644087113e-05, + "loss": 1.0444, + "step": 2264 + }, + { + "epoch": 0.1262471434145254, + "grad_norm": 0.5038657784461975, + "learning_rate": 9.69697244738391e-05, + "loss": 1.7319, + "step": 2265 + }, + { + "epoch": 0.12630288166768852, + "grad_norm": 0.593559205532074, + "learning_rate": 9.696667101720127e-05, + "loss": 1.9173, + "step": 2266 + }, + { + "epoch": 0.12635861992085168, + "grad_norm": 0.5412843227386475, + "learning_rate": 9.696361607105448e-05, + "loss": 1.6603, + "step": 2267 + }, + { + "epoch": 0.12641435817401483, + "grad_norm": 0.5422548055648804, + "learning_rate": 9.69605596354956e-05, + "loss": 1.7048, + "step": 2268 + }, + { + "epoch": 0.12647009642717796, + "grad_norm": 0.5455138087272644, + "learning_rate": 9.695750171062156e-05, + "loss": 1.669, + "step": 2269 + }, + { + "epoch": 0.12652583468034112, + "grad_norm": 0.5468176007270813, + "learning_rate": 9.695444229652935e-05, + "loss": 1.6744, + "step": 2270 + }, + { + "epoch": 0.12658157293350428, + "grad_norm": 0.49385011196136475, + "learning_rate": 9.6951381393316e-05, + "loss": 1.6182, + "step": 2271 + }, + { + "epoch": 0.1266373111866674, + "grad_norm": 0.5301021933555603, + "learning_rate": 9.694831900107857e-05, + "loss": 1.7818, + "step": 2272 + }, + { + "epoch": 0.12669304943983056, + "grad_norm": 0.6178646087646484, + "learning_rate": 9.69452551199142e-05, + "loss": 1.9646, + "step": 2273 + }, + { + "epoch": 0.1267487876929937, + "grad_norm": 0.5421885848045349, + "learning_rate": 9.694218974992005e-05, + "loss": 1.6862, + "step": 2274 + }, + { + "epoch": 0.12680452594615685, + "grad_norm": 0.5251665115356445, + "learning_rate": 9.693912289119332e-05, + "loss": 1.7259, + "step": 2275 + }, + { + "epoch": 0.12686026419932, + "grad_norm": 0.5069818496704102, + "learning_rate": 9.693605454383128e-05, + "loss": 1.8426, + "step": 2276 + }, + { + "epoch": 0.12691600245248313, + "grad_norm": 0.5525764226913452, + "learning_rate": 9.693298470793126e-05, + "loss": 1.9999, + "step": 2277 + }, + { + "epoch": 0.1269717407056463, + "grad_norm": 0.5717039108276367, + "learning_rate": 9.69299133835906e-05, + "loss": 1.736, + "step": 2278 + }, + { + "epoch": 0.12702747895880942, + "grad_norm": 0.4768933057785034, + "learning_rate": 9.69268405709067e-05, + "loss": 1.4284, + "step": 2279 + }, + { + "epoch": 0.12708321721197258, + "grad_norm": 0.5677302479743958, + "learning_rate": 9.692376626997703e-05, + "loss": 1.8972, + "step": 2280 + }, + { + "epoch": 0.12713895546513573, + "grad_norm": 0.5202549695968628, + "learning_rate": 9.692069048089907e-05, + "loss": 1.6173, + "step": 2281 + }, + { + "epoch": 0.12719469371829886, + "grad_norm": 0.5106683373451233, + "learning_rate": 9.691761320377037e-05, + "loss": 1.5599, + "step": 2282 + }, + { + "epoch": 0.12725043197146202, + "grad_norm": 0.5042096376419067, + "learning_rate": 9.691453443868854e-05, + "loss": 1.7705, + "step": 2283 + }, + { + "epoch": 0.12730617022462515, + "grad_norm": 0.5391340255737305, + "learning_rate": 9.691145418575122e-05, + "loss": 1.9065, + "step": 2284 + }, + { + "epoch": 0.1273619084777883, + "grad_norm": 0.5074059963226318, + "learning_rate": 9.690837244505607e-05, + "loss": 1.7623, + "step": 2285 + }, + { + "epoch": 0.12741764673095146, + "grad_norm": 0.5277912616729736, + "learning_rate": 9.690528921670084e-05, + "loss": 1.7758, + "step": 2286 + }, + { + "epoch": 0.1274733849841146, + "grad_norm": 0.5068628787994385, + "learning_rate": 9.69022045007833e-05, + "loss": 1.6409, + "step": 2287 + }, + { + "epoch": 0.12752912323727775, + "grad_norm": 0.5209136009216309, + "learning_rate": 9.689911829740133e-05, + "loss": 1.6144, + "step": 2288 + }, + { + "epoch": 0.12758486149044088, + "grad_norm": 0.5280535221099854, + "learning_rate": 9.689603060665273e-05, + "loss": 1.8711, + "step": 2289 + }, + { + "epoch": 0.12764059974360403, + "grad_norm": 0.5511658191680908, + "learning_rate": 9.689294142863548e-05, + "loss": 1.8228, + "step": 2290 + }, + { + "epoch": 0.1276963379967672, + "grad_norm": 0.5436153411865234, + "learning_rate": 9.688985076344754e-05, + "loss": 1.696, + "step": 2291 + }, + { + "epoch": 0.12775207624993032, + "grad_norm": 0.5065414309501648, + "learning_rate": 9.68867586111869e-05, + "loss": 1.6989, + "step": 2292 + }, + { + "epoch": 0.12780781450309348, + "grad_norm": 0.5280441045761108, + "learning_rate": 9.688366497195166e-05, + "loss": 1.6764, + "step": 2293 + }, + { + "epoch": 0.12786355275625663, + "grad_norm": 0.46777546405792236, + "learning_rate": 9.68805698458399e-05, + "loss": 1.4595, + "step": 2294 + }, + { + "epoch": 0.12791929100941976, + "grad_norm": 0.5001897811889648, + "learning_rate": 9.687747323294982e-05, + "loss": 1.4642, + "step": 2295 + }, + { + "epoch": 0.12797502926258292, + "grad_norm": 0.5615783929824829, + "learning_rate": 9.687437513337961e-05, + "loss": 1.7116, + "step": 2296 + }, + { + "epoch": 0.12803076751574605, + "grad_norm": 0.5208621621131897, + "learning_rate": 9.687127554722749e-05, + "loss": 1.637, + "step": 2297 + }, + { + "epoch": 0.1280865057689092, + "grad_norm": 0.5435874462127686, + "learning_rate": 9.68681744745918e-05, + "loss": 1.7629, + "step": 2298 + }, + { + "epoch": 0.12814224402207236, + "grad_norm": 0.5296335220336914, + "learning_rate": 9.686507191557089e-05, + "loss": 1.827, + "step": 2299 + }, + { + "epoch": 0.1281979822752355, + "grad_norm": 0.5191251635551453, + "learning_rate": 9.686196787026311e-05, + "loss": 1.9385, + "step": 2300 + }, + { + "epoch": 0.12825372052839865, + "grad_norm": 0.5494365096092224, + "learning_rate": 9.685886233876695e-05, + "loss": 1.8378, + "step": 2301 + }, + { + "epoch": 0.12830945878156177, + "grad_norm": 0.583207905292511, + "learning_rate": 9.685575532118089e-05, + "loss": 1.6812, + "step": 2302 + }, + { + "epoch": 0.12836519703472493, + "grad_norm": 0.5473710894584656, + "learning_rate": 9.685264681760345e-05, + "loss": 1.9602, + "step": 2303 + }, + { + "epoch": 0.1284209352878881, + "grad_norm": 0.567272424697876, + "learning_rate": 9.684953682813322e-05, + "loss": 1.8125, + "step": 2304 + }, + { + "epoch": 0.12847667354105122, + "grad_norm": 0.4732169806957245, + "learning_rate": 9.684642535286885e-05, + "loss": 1.5566, + "step": 2305 + }, + { + "epoch": 0.12853241179421437, + "grad_norm": 0.516720712184906, + "learning_rate": 9.684331239190899e-05, + "loss": 1.5688, + "step": 2306 + }, + { + "epoch": 0.1285881500473775, + "grad_norm": 0.5574965476989746, + "learning_rate": 9.684019794535237e-05, + "loss": 1.7452, + "step": 2307 + }, + { + "epoch": 0.12864388830054066, + "grad_norm": 0.5443317294120789, + "learning_rate": 9.683708201329777e-05, + "loss": 1.6624, + "step": 2308 + }, + { + "epoch": 0.12869962655370382, + "grad_norm": 0.5809649229049683, + "learning_rate": 9.683396459584404e-05, + "loss": 1.7721, + "step": 2309 + }, + { + "epoch": 0.12875536480686695, + "grad_norm": 0.5913598537445068, + "learning_rate": 9.683084569308997e-05, + "loss": 2.1623, + "step": 2310 + }, + { + "epoch": 0.1288111030600301, + "grad_norm": 0.5404501557350159, + "learning_rate": 9.682772530513453e-05, + "loss": 1.7165, + "step": 2311 + }, + { + "epoch": 0.12886684131319323, + "grad_norm": 0.4902174174785614, + "learning_rate": 9.682460343207669e-05, + "loss": 1.6391, + "step": 2312 + }, + { + "epoch": 0.1289225795663564, + "grad_norm": 0.5791998505592346, + "learning_rate": 9.682148007401541e-05, + "loss": 1.891, + "step": 2313 + }, + { + "epoch": 0.12897831781951954, + "grad_norm": 0.5695587992668152, + "learning_rate": 9.681835523104978e-05, + "loss": 1.9901, + "step": 2314 + }, + { + "epoch": 0.12903405607268267, + "grad_norm": 0.6025593876838684, + "learning_rate": 9.681522890327889e-05, + "loss": 1.7748, + "step": 2315 + }, + { + "epoch": 0.12908979432584583, + "grad_norm": 0.5111005902290344, + "learning_rate": 9.681210109080189e-05, + "loss": 1.6, + "step": 2316 + }, + { + "epoch": 0.129145532579009, + "grad_norm": 0.533204972743988, + "learning_rate": 9.680897179371798e-05, + "loss": 1.6863, + "step": 2317 + }, + { + "epoch": 0.12920127083217212, + "grad_norm": 0.5172824859619141, + "learning_rate": 9.68058410121264e-05, + "loss": 1.7456, + "step": 2318 + }, + { + "epoch": 0.12925700908533527, + "grad_norm": 0.5905986428260803, + "learning_rate": 9.680270874612643e-05, + "loss": 1.572, + "step": 2319 + }, + { + "epoch": 0.1293127473384984, + "grad_norm": 0.5090576410293579, + "learning_rate": 9.679957499581742e-05, + "loss": 1.7946, + "step": 2320 + }, + { + "epoch": 0.12936848559166156, + "grad_norm": 0.5587893724441528, + "learning_rate": 9.679643976129876e-05, + "loss": 1.7792, + "step": 2321 + }, + { + "epoch": 0.12942422384482472, + "grad_norm": 0.6383116841316223, + "learning_rate": 9.679330304266988e-05, + "loss": 2.0051, + "step": 2322 + }, + { + "epoch": 0.12947996209798784, + "grad_norm": 0.5700294375419617, + "learning_rate": 9.679016484003023e-05, + "loss": 1.8419, + "step": 2323 + }, + { + "epoch": 0.129535700351151, + "grad_norm": 0.6416967511177063, + "learning_rate": 9.678702515347938e-05, + "loss": 1.7893, + "step": 2324 + }, + { + "epoch": 0.12959143860431413, + "grad_norm": 0.5761459469795227, + "learning_rate": 9.678388398311686e-05, + "loss": 1.8868, + "step": 2325 + }, + { + "epoch": 0.1296471768574773, + "grad_norm": 0.5779362320899963, + "learning_rate": 9.678074132904231e-05, + "loss": 1.6472, + "step": 2326 + }, + { + "epoch": 0.12970291511064044, + "grad_norm": 0.5250251293182373, + "learning_rate": 9.677759719135542e-05, + "loss": 1.8353, + "step": 2327 + }, + { + "epoch": 0.12975865336380357, + "grad_norm": 0.5306884050369263, + "learning_rate": 9.677445157015585e-05, + "loss": 1.8419, + "step": 2328 + }, + { + "epoch": 0.12981439161696673, + "grad_norm": 0.5761096477508545, + "learning_rate": 9.67713044655434e-05, + "loss": 1.846, + "step": 2329 + }, + { + "epoch": 0.12987012987012986, + "grad_norm": 0.5438225269317627, + "learning_rate": 9.676815587761787e-05, + "loss": 1.734, + "step": 2330 + }, + { + "epoch": 0.12992586812329301, + "grad_norm": 0.5154998898506165, + "learning_rate": 9.676500580647912e-05, + "loss": 1.8124, + "step": 2331 + }, + { + "epoch": 0.12998160637645617, + "grad_norm": 0.5288179516792297, + "learning_rate": 9.676185425222704e-05, + "loss": 2.0132, + "step": 2332 + }, + { + "epoch": 0.1300373446296193, + "grad_norm": 0.5507707595825195, + "learning_rate": 9.675870121496158e-05, + "loss": 1.7686, + "step": 2333 + }, + { + "epoch": 0.13009308288278246, + "grad_norm": 0.4893222451210022, + "learning_rate": 9.675554669478272e-05, + "loss": 1.8113, + "step": 2334 + }, + { + "epoch": 0.13014882113594559, + "grad_norm": 0.5455611944198608, + "learning_rate": 9.675239069179056e-05, + "loss": 1.7593, + "step": 2335 + }, + { + "epoch": 0.13020455938910874, + "grad_norm": 0.5068415403366089, + "learning_rate": 9.674923320608513e-05, + "loss": 1.5302, + "step": 2336 + }, + { + "epoch": 0.1302602976422719, + "grad_norm": 0.5160056948661804, + "learning_rate": 9.674607423776661e-05, + "loss": 1.5793, + "step": 2337 + }, + { + "epoch": 0.13031603589543503, + "grad_norm": 0.5414824485778809, + "learning_rate": 9.674291378693515e-05, + "loss": 1.6392, + "step": 2338 + }, + { + "epoch": 0.13037177414859819, + "grad_norm": 0.5210713744163513, + "learning_rate": 9.673975185369098e-05, + "loss": 1.9403, + "step": 2339 + }, + { + "epoch": 0.13042751240176134, + "grad_norm": 0.5296798944473267, + "learning_rate": 9.673658843813442e-05, + "loss": 1.7093, + "step": 2340 + }, + { + "epoch": 0.13048325065492447, + "grad_norm": 0.5705276131629944, + "learning_rate": 9.673342354036574e-05, + "loss": 1.7645, + "step": 2341 + }, + { + "epoch": 0.13053898890808763, + "grad_norm": 0.5289913415908813, + "learning_rate": 9.673025716048536e-05, + "loss": 1.81, + "step": 2342 + }, + { + "epoch": 0.13059472716125076, + "grad_norm": 0.5237072706222534, + "learning_rate": 9.672708929859368e-05, + "loss": 2.0053, + "step": 2343 + }, + { + "epoch": 0.1306504654144139, + "grad_norm": 0.5144554376602173, + "learning_rate": 9.672391995479115e-05, + "loss": 1.7236, + "step": 2344 + }, + { + "epoch": 0.13070620366757707, + "grad_norm": 0.5384603142738342, + "learning_rate": 9.672074912917831e-05, + "loss": 1.7492, + "step": 2345 + }, + { + "epoch": 0.1307619419207402, + "grad_norm": 0.5475570559501648, + "learning_rate": 9.67175768218557e-05, + "loss": 1.9068, + "step": 2346 + }, + { + "epoch": 0.13081768017390336, + "grad_norm": 0.512937068939209, + "learning_rate": 9.671440303292395e-05, + "loss": 1.7364, + "step": 2347 + }, + { + "epoch": 0.13087341842706648, + "grad_norm": 0.48609036207199097, + "learning_rate": 9.67112277624837e-05, + "loss": 1.5916, + "step": 2348 + }, + { + "epoch": 0.13092915668022964, + "grad_norm": 0.5132019519805908, + "learning_rate": 9.670805101063563e-05, + "loss": 1.7222, + "step": 2349 + }, + { + "epoch": 0.1309848949333928, + "grad_norm": 0.5112780928611755, + "learning_rate": 9.670487277748052e-05, + "loss": 1.6418, + "step": 2350 + }, + { + "epoch": 0.13104063318655593, + "grad_norm": 0.531306803226471, + "learning_rate": 9.670169306311916e-05, + "loss": 1.7323, + "step": 2351 + }, + { + "epoch": 0.13109637143971908, + "grad_norm": 0.48118212819099426, + "learning_rate": 9.669851186765238e-05, + "loss": 1.4822, + "step": 2352 + }, + { + "epoch": 0.1311521096928822, + "grad_norm": 0.5309464931488037, + "learning_rate": 9.669532919118108e-05, + "loss": 1.767, + "step": 2353 + }, + { + "epoch": 0.13120784794604537, + "grad_norm": 0.532576322555542, + "learning_rate": 9.669214503380617e-05, + "loss": 1.7228, + "step": 2354 + }, + { + "epoch": 0.13126358619920853, + "grad_norm": 0.49597617983818054, + "learning_rate": 9.668895939562868e-05, + "loss": 1.4792, + "step": 2355 + }, + { + "epoch": 0.13131932445237166, + "grad_norm": 0.5480032563209534, + "learning_rate": 9.66857722767496e-05, + "loss": 1.7285, + "step": 2356 + }, + { + "epoch": 0.1313750627055348, + "grad_norm": 0.5191400647163391, + "learning_rate": 9.668258367727002e-05, + "loss": 1.5942, + "step": 2357 + }, + { + "epoch": 0.13143080095869794, + "grad_norm": 0.5335458517074585, + "learning_rate": 9.667939359729109e-05, + "loss": 1.8991, + "step": 2358 + }, + { + "epoch": 0.1314865392118611, + "grad_norm": 0.5872248411178589, + "learning_rate": 9.667620203691393e-05, + "loss": 1.8247, + "step": 2359 + }, + { + "epoch": 0.13154227746502425, + "grad_norm": 0.5811527967453003, + "learning_rate": 9.667300899623976e-05, + "loss": 2.0837, + "step": 2360 + }, + { + "epoch": 0.13159801571818738, + "grad_norm": 0.5214108824729919, + "learning_rate": 9.66698144753699e-05, + "loss": 1.681, + "step": 2361 + }, + { + "epoch": 0.13165375397135054, + "grad_norm": 0.5067755579948425, + "learning_rate": 9.666661847440563e-05, + "loss": 1.7168, + "step": 2362 + }, + { + "epoch": 0.1317094922245137, + "grad_norm": 0.5883169770240784, + "learning_rate": 9.666342099344829e-05, + "loss": 1.8355, + "step": 2363 + }, + { + "epoch": 0.13176523047767683, + "grad_norm": 0.5047624111175537, + "learning_rate": 9.666022203259931e-05, + "loss": 1.6872, + "step": 2364 + }, + { + "epoch": 0.13182096873083998, + "grad_norm": 0.5165308117866516, + "learning_rate": 9.665702159196013e-05, + "loss": 1.6867, + "step": 2365 + }, + { + "epoch": 0.1318767069840031, + "grad_norm": 0.5131801962852478, + "learning_rate": 9.665381967163227e-05, + "loss": 1.5836, + "step": 2366 + }, + { + "epoch": 0.13193244523716627, + "grad_norm": 0.5561967492103577, + "learning_rate": 9.665061627171726e-05, + "loss": 1.6933, + "step": 2367 + }, + { + "epoch": 0.13198818349032942, + "grad_norm": 0.6118646860122681, + "learning_rate": 9.664741139231668e-05, + "loss": 2.0988, + "step": 2368 + }, + { + "epoch": 0.13204392174349255, + "grad_norm": 0.5255211591720581, + "learning_rate": 9.664420503353218e-05, + "loss": 1.7087, + "step": 2369 + }, + { + "epoch": 0.1320996599966557, + "grad_norm": 0.555664598941803, + "learning_rate": 9.664099719546547e-05, + "loss": 1.8029, + "step": 2370 + }, + { + "epoch": 0.13215539824981884, + "grad_norm": 0.5417226552963257, + "learning_rate": 9.663778787821825e-05, + "loss": 1.7483, + "step": 2371 + }, + { + "epoch": 0.132211136502982, + "grad_norm": 0.5773631930351257, + "learning_rate": 9.663457708189232e-05, + "loss": 1.7137, + "step": 2372 + }, + { + "epoch": 0.13226687475614515, + "grad_norm": 0.5354270935058594, + "learning_rate": 9.66313648065895e-05, + "loss": 1.8748, + "step": 2373 + }, + { + "epoch": 0.13232261300930828, + "grad_norm": 0.5149551033973694, + "learning_rate": 9.662815105241168e-05, + "loss": 1.5948, + "step": 2374 + }, + { + "epoch": 0.13237835126247144, + "grad_norm": 0.5566468238830566, + "learning_rate": 9.662493581946074e-05, + "loss": 1.7724, + "step": 2375 + }, + { + "epoch": 0.13243408951563457, + "grad_norm": 0.5304192304611206, + "learning_rate": 9.66217191078387e-05, + "loss": 1.8068, + "step": 2376 + }, + { + "epoch": 0.13248982776879772, + "grad_norm": 0.5885264873504639, + "learning_rate": 9.661850091764756e-05, + "loss": 1.9129, + "step": 2377 + }, + { + "epoch": 0.13254556602196088, + "grad_norm": 0.4796747863292694, + "learning_rate": 9.661528124898937e-05, + "loss": 1.6931, + "step": 2378 + }, + { + "epoch": 0.132601304275124, + "grad_norm": 0.49771320819854736, + "learning_rate": 9.661206010196624e-05, + "loss": 1.5938, + "step": 2379 + }, + { + "epoch": 0.13265704252828717, + "grad_norm": 0.530432939529419, + "learning_rate": 9.660883747668034e-05, + "loss": 2.0283, + "step": 2380 + }, + { + "epoch": 0.1327127807814503, + "grad_norm": 0.515631914138794, + "learning_rate": 9.660561337323385e-05, + "loss": 1.8549, + "step": 2381 + }, + { + "epoch": 0.13276851903461345, + "grad_norm": 0.6954619288444519, + "learning_rate": 9.660238779172905e-05, + "loss": 2.0152, + "step": 2382 + }, + { + "epoch": 0.1328242572877766, + "grad_norm": 0.5233824253082275, + "learning_rate": 9.65991607322682e-05, + "loss": 1.7353, + "step": 2383 + }, + { + "epoch": 0.13287999554093974, + "grad_norm": 0.5527575016021729, + "learning_rate": 9.659593219495368e-05, + "loss": 1.6361, + "step": 2384 + }, + { + "epoch": 0.1329357337941029, + "grad_norm": 0.48741617798805237, + "learning_rate": 9.659270217988786e-05, + "loss": 1.682, + "step": 2385 + }, + { + "epoch": 0.13299147204726605, + "grad_norm": 0.5804024338722229, + "learning_rate": 9.658947068717316e-05, + "loss": 1.5736, + "step": 2386 + }, + { + "epoch": 0.13304721030042918, + "grad_norm": 0.5614018440246582, + "learning_rate": 9.658623771691211e-05, + "loss": 1.9172, + "step": 2387 + }, + { + "epoch": 0.13310294855359234, + "grad_norm": 0.5239617824554443, + "learning_rate": 9.658300326920722e-05, + "loss": 1.7751, + "step": 2388 + }, + { + "epoch": 0.13315868680675547, + "grad_norm": 0.5195541381835938, + "learning_rate": 9.657976734416106e-05, + "loss": 1.875, + "step": 2389 + }, + { + "epoch": 0.13321442505991862, + "grad_norm": 0.531480610370636, + "learning_rate": 9.657652994187625e-05, + "loss": 1.7631, + "step": 2390 + }, + { + "epoch": 0.13327016331308178, + "grad_norm": 0.5037621259689331, + "learning_rate": 9.657329106245547e-05, + "loss": 1.6134, + "step": 2391 + }, + { + "epoch": 0.1333259015662449, + "grad_norm": 0.4974221885204315, + "learning_rate": 9.657005070600144e-05, + "loss": 1.7501, + "step": 2392 + }, + { + "epoch": 0.13338163981940807, + "grad_norm": 0.5308098196983337, + "learning_rate": 9.656680887261693e-05, + "loss": 1.7283, + "step": 2393 + }, + { + "epoch": 0.1334373780725712, + "grad_norm": 0.4996281862258911, + "learning_rate": 9.656356556240473e-05, + "loss": 1.7897, + "step": 2394 + }, + { + "epoch": 0.13349311632573435, + "grad_norm": 0.6450517773628235, + "learning_rate": 9.656032077546772e-05, + "loss": 1.7089, + "step": 2395 + }, + { + "epoch": 0.1335488545788975, + "grad_norm": 0.5968025326728821, + "learning_rate": 9.655707451190883e-05, + "loss": 1.8664, + "step": 2396 + }, + { + "epoch": 0.13360459283206064, + "grad_norm": 0.470813512802124, + "learning_rate": 9.655382677183095e-05, + "loss": 1.5199, + "step": 2397 + }, + { + "epoch": 0.1336603310852238, + "grad_norm": 0.5651730298995972, + "learning_rate": 9.655057755533712e-05, + "loss": 1.9733, + "step": 2398 + }, + { + "epoch": 0.13371606933838692, + "grad_norm": 0.5370044112205505, + "learning_rate": 9.654732686253039e-05, + "loss": 1.8281, + "step": 2399 + }, + { + "epoch": 0.13377180759155008, + "grad_norm": 0.5285357236862183, + "learning_rate": 9.654407469351383e-05, + "loss": 1.592, + "step": 2400 + }, + { + "epoch": 0.13382754584471324, + "grad_norm": 0.5265277624130249, + "learning_rate": 9.654082104839059e-05, + "loss": 1.8503, + "step": 2401 + }, + { + "epoch": 0.13388328409787636, + "grad_norm": 0.5449655652046204, + "learning_rate": 9.653756592726386e-05, + "loss": 1.8579, + "step": 2402 + }, + { + "epoch": 0.13393902235103952, + "grad_norm": 0.5737154483795166, + "learning_rate": 9.653430933023689e-05, + "loss": 1.8618, + "step": 2403 + }, + { + "epoch": 0.13399476060420265, + "grad_norm": 0.5164530873298645, + "learning_rate": 9.653105125741292e-05, + "loss": 1.6213, + "step": 2404 + }, + { + "epoch": 0.1340504988573658, + "grad_norm": 0.5017974376678467, + "learning_rate": 9.65277917088953e-05, + "loss": 1.6255, + "step": 2405 + }, + { + "epoch": 0.13410623711052896, + "grad_norm": 0.5122340321540833, + "learning_rate": 9.652453068478741e-05, + "loss": 1.5653, + "step": 2406 + }, + { + "epoch": 0.1341619753636921, + "grad_norm": 0.6067832708358765, + "learning_rate": 9.652126818519266e-05, + "loss": 2.0985, + "step": 2407 + }, + { + "epoch": 0.13421771361685525, + "grad_norm": 0.5796366333961487, + "learning_rate": 9.651800421021453e-05, + "loss": 1.9636, + "step": 2408 + }, + { + "epoch": 0.1342734518700184, + "grad_norm": 0.5619643926620483, + "learning_rate": 9.651473875995651e-05, + "loss": 1.7129, + "step": 2409 + }, + { + "epoch": 0.13432919012318154, + "grad_norm": 0.5060097575187683, + "learning_rate": 9.651147183452219e-05, + "loss": 1.5304, + "step": 2410 + }, + { + "epoch": 0.1343849283763447, + "grad_norm": 0.532145619392395, + "learning_rate": 9.650820343401515e-05, + "loss": 1.7844, + "step": 2411 + }, + { + "epoch": 0.13444066662950782, + "grad_norm": 0.5342923402786255, + "learning_rate": 9.650493355853906e-05, + "loss": 1.8585, + "step": 2412 + }, + { + "epoch": 0.13449640488267098, + "grad_norm": 0.49805736541748047, + "learning_rate": 9.650166220819764e-05, + "loss": 1.4576, + "step": 2413 + }, + { + "epoch": 0.13455214313583413, + "grad_norm": 0.5234712362289429, + "learning_rate": 9.64983893830946e-05, + "loss": 1.6994, + "step": 2414 + }, + { + "epoch": 0.13460788138899726, + "grad_norm": 0.5124284029006958, + "learning_rate": 9.649511508333375e-05, + "loss": 1.6614, + "step": 2415 + }, + { + "epoch": 0.13466361964216042, + "grad_norm": 0.4958679676055908, + "learning_rate": 9.649183930901895e-05, + "loss": 1.56, + "step": 2416 + }, + { + "epoch": 0.13471935789532355, + "grad_norm": 0.5191091895103455, + "learning_rate": 9.648856206025407e-05, + "loss": 1.7004, + "step": 2417 + }, + { + "epoch": 0.1347750961484867, + "grad_norm": 0.5366125702857971, + "learning_rate": 9.648528333714304e-05, + "loss": 1.7206, + "step": 2418 + }, + { + "epoch": 0.13483083440164986, + "grad_norm": 0.5979599952697754, + "learning_rate": 9.648200313978986e-05, + "loss": 1.757, + "step": 2419 + }, + { + "epoch": 0.134886572654813, + "grad_norm": 0.5878745317459106, + "learning_rate": 9.647872146829855e-05, + "loss": 1.7236, + "step": 2420 + }, + { + "epoch": 0.13494231090797615, + "grad_norm": 0.5160901546478271, + "learning_rate": 9.647543832277317e-05, + "loss": 1.7274, + "step": 2421 + }, + { + "epoch": 0.13499804916113928, + "grad_norm": 0.5626492500305176, + "learning_rate": 9.647215370331786e-05, + "loss": 1.9507, + "step": 2422 + }, + { + "epoch": 0.13505378741430243, + "grad_norm": 0.5624846816062927, + "learning_rate": 9.646886761003679e-05, + "loss": 1.9476, + "step": 2423 + }, + { + "epoch": 0.1351095256674656, + "grad_norm": 0.5468912720680237, + "learning_rate": 9.646558004303419e-05, + "loss": 1.7836, + "step": 2424 + }, + { + "epoch": 0.13516526392062872, + "grad_norm": 0.5446691513061523, + "learning_rate": 9.646229100241429e-05, + "loss": 1.7664, + "step": 2425 + }, + { + "epoch": 0.13522100217379188, + "grad_norm": 0.5568925738334656, + "learning_rate": 9.64590004882814e-05, + "loss": 2.0063, + "step": 2426 + }, + { + "epoch": 0.135276740426955, + "grad_norm": 0.560264527797699, + "learning_rate": 9.64557085007399e-05, + "loss": 1.8132, + "step": 2427 + }, + { + "epoch": 0.13533247868011816, + "grad_norm": 0.5093153715133667, + "learning_rate": 9.64524150398942e-05, + "loss": 1.4198, + "step": 2428 + }, + { + "epoch": 0.13538821693328132, + "grad_norm": 0.5184745192527771, + "learning_rate": 9.64491201058487e-05, + "loss": 1.6062, + "step": 2429 + }, + { + "epoch": 0.13544395518644445, + "grad_norm": 0.5188031792640686, + "learning_rate": 9.644582369870794e-05, + "loss": 1.8179, + "step": 2430 + }, + { + "epoch": 0.1354996934396076, + "grad_norm": 0.537381112575531, + "learning_rate": 9.644252581857647e-05, + "loss": 1.9697, + "step": 2431 + }, + { + "epoch": 0.13555543169277076, + "grad_norm": 0.5132935047149658, + "learning_rate": 9.643922646555883e-05, + "loss": 1.6746, + "step": 2432 + }, + { + "epoch": 0.1356111699459339, + "grad_norm": 0.5265336036682129, + "learning_rate": 9.64359256397597e-05, + "loss": 1.6561, + "step": 2433 + }, + { + "epoch": 0.13566690819909705, + "grad_norm": 0.5241510272026062, + "learning_rate": 9.643262334128374e-05, + "loss": 1.577, + "step": 2434 + }, + { + "epoch": 0.13572264645226018, + "grad_norm": 0.5073732137680054, + "learning_rate": 9.642931957023569e-05, + "loss": 1.6821, + "step": 2435 + }, + { + "epoch": 0.13577838470542333, + "grad_norm": 0.4868320822715759, + "learning_rate": 9.642601432672034e-05, + "loss": 1.4476, + "step": 2436 + }, + { + "epoch": 0.1358341229585865, + "grad_norm": 0.5248389840126038, + "learning_rate": 9.642270761084249e-05, + "loss": 1.9406, + "step": 2437 + }, + { + "epoch": 0.13588986121174962, + "grad_norm": 0.492227166891098, + "learning_rate": 9.641939942270701e-05, + "loss": 1.6538, + "step": 2438 + }, + { + "epoch": 0.13594559946491278, + "grad_norm": 0.5446291565895081, + "learning_rate": 9.641608976241883e-05, + "loss": 1.8208, + "step": 2439 + }, + { + "epoch": 0.1360013377180759, + "grad_norm": 0.5214070677757263, + "learning_rate": 9.64127786300829e-05, + "loss": 1.6889, + "step": 2440 + }, + { + "epoch": 0.13605707597123906, + "grad_norm": 0.5892273187637329, + "learning_rate": 9.640946602580426e-05, + "loss": 2.0888, + "step": 2441 + }, + { + "epoch": 0.13611281422440222, + "grad_norm": 0.5230244994163513, + "learning_rate": 9.640615194968791e-05, + "loss": 1.7068, + "step": 2442 + }, + { + "epoch": 0.13616855247756535, + "grad_norm": 0.5090706944465637, + "learning_rate": 9.640283640183903e-05, + "loss": 1.7328, + "step": 2443 + }, + { + "epoch": 0.1362242907307285, + "grad_norm": 0.5167303681373596, + "learning_rate": 9.639951938236269e-05, + "loss": 1.7062, + "step": 2444 + }, + { + "epoch": 0.13628002898389163, + "grad_norm": 0.5717843770980835, + "learning_rate": 9.639620089136413e-05, + "loss": 1.8633, + "step": 2445 + }, + { + "epoch": 0.1363357672370548, + "grad_norm": 0.514242947101593, + "learning_rate": 9.63928809289486e-05, + "loss": 1.9126, + "step": 2446 + }, + { + "epoch": 0.13639150549021795, + "grad_norm": 0.5159420371055603, + "learning_rate": 9.638955949522137e-05, + "loss": 1.6795, + "step": 2447 + }, + { + "epoch": 0.13644724374338107, + "grad_norm": 0.4026312828063965, + "learning_rate": 9.638623659028779e-05, + "loss": 1.008, + "step": 2448 + }, + { + "epoch": 0.13650298199654423, + "grad_norm": 0.5365085601806641, + "learning_rate": 9.63829122142532e-05, + "loss": 1.9597, + "step": 2449 + }, + { + "epoch": 0.13655872024970736, + "grad_norm": 0.528103768825531, + "learning_rate": 9.637958636722311e-05, + "loss": 1.8801, + "step": 2450 + }, + { + "epoch": 0.13661445850287052, + "grad_norm": 0.5581492185592651, + "learning_rate": 9.637625904930292e-05, + "loss": 1.6802, + "step": 2451 + }, + { + "epoch": 0.13667019675603367, + "grad_norm": 0.5182628631591797, + "learning_rate": 9.63729302605982e-05, + "loss": 1.8041, + "step": 2452 + }, + { + "epoch": 0.1367259350091968, + "grad_norm": 0.48804765939712524, + "learning_rate": 9.636960000121451e-05, + "loss": 1.7381, + "step": 2453 + }, + { + "epoch": 0.13678167326235996, + "grad_norm": 0.5185055136680603, + "learning_rate": 9.636626827125745e-05, + "loss": 1.8356, + "step": 2454 + }, + { + "epoch": 0.13683741151552312, + "grad_norm": 0.5890060663223267, + "learning_rate": 9.63629350708327e-05, + "loss": 1.8636, + "step": 2455 + }, + { + "epoch": 0.13689314976868625, + "grad_norm": 0.5501379370689392, + "learning_rate": 9.635960040004597e-05, + "loss": 2.0967, + "step": 2456 + }, + { + "epoch": 0.1369488880218494, + "grad_norm": 0.5753256678581238, + "learning_rate": 9.635626425900301e-05, + "loss": 1.8931, + "step": 2457 + }, + { + "epoch": 0.13700462627501253, + "grad_norm": 0.5230208039283752, + "learning_rate": 9.635292664780962e-05, + "loss": 1.6546, + "step": 2458 + }, + { + "epoch": 0.1370603645281757, + "grad_norm": 0.507422149181366, + "learning_rate": 9.634958756657165e-05, + "loss": 1.7135, + "step": 2459 + }, + { + "epoch": 0.13711610278133884, + "grad_norm": 0.48532143235206604, + "learning_rate": 9.634624701539498e-05, + "loss": 1.5297, + "step": 2460 + }, + { + "epoch": 0.13717184103450197, + "grad_norm": 0.5039069652557373, + "learning_rate": 9.63429049943856e-05, + "loss": 1.9089, + "step": 2461 + }, + { + "epoch": 0.13722757928766513, + "grad_norm": 0.5480893850326538, + "learning_rate": 9.633956150364947e-05, + "loss": 1.7987, + "step": 2462 + }, + { + "epoch": 0.13728331754082826, + "grad_norm": 0.5339971780776978, + "learning_rate": 9.633621654329261e-05, + "loss": 1.7035, + "step": 2463 + }, + { + "epoch": 0.13733905579399142, + "grad_norm": 0.5058174133300781, + "learning_rate": 9.633287011342113e-05, + "loss": 1.6676, + "step": 2464 + }, + { + "epoch": 0.13739479404715457, + "grad_norm": 0.5697671175003052, + "learning_rate": 9.632952221414116e-05, + "loss": 1.9683, + "step": 2465 + }, + { + "epoch": 0.1374505323003177, + "grad_norm": 0.5071194767951965, + "learning_rate": 9.632617284555886e-05, + "loss": 1.9232, + "step": 2466 + }, + { + "epoch": 0.13750627055348086, + "grad_norm": 0.5929427742958069, + "learning_rate": 9.632282200778045e-05, + "loss": 1.8352, + "step": 2467 + }, + { + "epoch": 0.137562008806644, + "grad_norm": 0.528889000415802, + "learning_rate": 9.631946970091221e-05, + "loss": 1.7636, + "step": 2468 + }, + { + "epoch": 0.13761774705980714, + "grad_norm": 1.3195804357528687, + "learning_rate": 9.631611592506046e-05, + "loss": 1.7929, + "step": 2469 + }, + { + "epoch": 0.1376734853129703, + "grad_norm": 0.5272727608680725, + "learning_rate": 9.631276068033154e-05, + "loss": 1.89, + "step": 2470 + }, + { + "epoch": 0.13772922356613343, + "grad_norm": 0.5453211665153503, + "learning_rate": 9.630940396683188e-05, + "loss": 1.6766, + "step": 2471 + }, + { + "epoch": 0.1377849618192966, + "grad_norm": 0.5383656620979309, + "learning_rate": 9.630604578466794e-05, + "loss": 1.6168, + "step": 2472 + }, + { + "epoch": 0.13784070007245972, + "grad_norm": 0.5008901953697205, + "learning_rate": 9.63026861339462e-05, + "loss": 1.5592, + "step": 2473 + }, + { + "epoch": 0.13789643832562287, + "grad_norm": 0.5986757874488831, + "learning_rate": 9.629932501477321e-05, + "loss": 2.0793, + "step": 2474 + }, + { + "epoch": 0.13795217657878603, + "grad_norm": 0.5368151664733887, + "learning_rate": 9.629596242725558e-05, + "loss": 1.6693, + "step": 2475 + }, + { + "epoch": 0.13800791483194916, + "grad_norm": 0.5330533385276794, + "learning_rate": 9.629259837149995e-05, + "loss": 1.7398, + "step": 2476 + }, + { + "epoch": 0.13806365308511231, + "grad_norm": 0.5093852877616882, + "learning_rate": 9.6289232847613e-05, + "loss": 1.6665, + "step": 2477 + }, + { + "epoch": 0.13811939133827547, + "grad_norm": 0.5469667911529541, + "learning_rate": 9.628586585570149e-05, + "loss": 1.8411, + "step": 2478 + }, + { + "epoch": 0.1381751295914386, + "grad_norm": 0.5832191705703735, + "learning_rate": 9.628249739587217e-05, + "loss": 1.8821, + "step": 2479 + }, + { + "epoch": 0.13823086784460176, + "grad_norm": 0.5154137015342712, + "learning_rate": 9.627912746823187e-05, + "loss": 1.6075, + "step": 2480 + }, + { + "epoch": 0.13828660609776489, + "grad_norm": 0.5499826669692993, + "learning_rate": 9.627575607288745e-05, + "loss": 1.735, + "step": 2481 + }, + { + "epoch": 0.13834234435092804, + "grad_norm": 0.6152673959732056, + "learning_rate": 9.627238320994589e-05, + "loss": 2.0207, + "step": 2482 + }, + { + "epoch": 0.1383980826040912, + "grad_norm": 0.49340128898620605, + "learning_rate": 9.626900887951412e-05, + "loss": 1.64, + "step": 2483 + }, + { + "epoch": 0.13845382085725433, + "grad_norm": 0.5563956499099731, + "learning_rate": 9.626563308169914e-05, + "loss": 1.9062, + "step": 2484 + }, + { + "epoch": 0.13850955911041749, + "grad_norm": 0.4945386052131653, + "learning_rate": 9.626225581660803e-05, + "loss": 1.4852, + "step": 2485 + }, + { + "epoch": 0.13856529736358061, + "grad_norm": 0.5170808434486389, + "learning_rate": 9.625887708434788e-05, + "loss": 1.7517, + "step": 2486 + }, + { + "epoch": 0.13862103561674377, + "grad_norm": 0.5459514260292053, + "learning_rate": 9.625549688502589e-05, + "loss": 1.6785, + "step": 2487 + }, + { + "epoch": 0.13867677386990693, + "grad_norm": 0.5073458552360535, + "learning_rate": 9.62521152187492e-05, + "loss": 1.7213, + "step": 2488 + }, + { + "epoch": 0.13873251212307006, + "grad_norm": 0.4946017563343048, + "learning_rate": 9.624873208562509e-05, + "loss": 1.6256, + "step": 2489 + }, + { + "epoch": 0.1387882503762332, + "grad_norm": 0.5971960425376892, + "learning_rate": 9.624534748576085e-05, + "loss": 1.9997, + "step": 2490 + }, + { + "epoch": 0.13884398862939634, + "grad_norm": 0.5135798454284668, + "learning_rate": 9.624196141926381e-05, + "loss": 1.6544, + "step": 2491 + }, + { + "epoch": 0.1388997268825595, + "grad_norm": 0.5550069212913513, + "learning_rate": 9.623857388624138e-05, + "loss": 1.8297, + "step": 2492 + }, + { + "epoch": 0.13895546513572266, + "grad_norm": 0.5476080179214478, + "learning_rate": 9.623518488680095e-05, + "loss": 1.9136, + "step": 2493 + }, + { + "epoch": 0.13901120338888578, + "grad_norm": 0.5327604413032532, + "learning_rate": 9.623179442105004e-05, + "loss": 1.7471, + "step": 2494 + }, + { + "epoch": 0.13906694164204894, + "grad_norm": 0.5192773938179016, + "learning_rate": 9.622840248909617e-05, + "loss": 1.6395, + "step": 2495 + }, + { + "epoch": 0.13912267989521207, + "grad_norm": 0.5261735916137695, + "learning_rate": 9.622500909104689e-05, + "loss": 1.6751, + "step": 2496 + }, + { + "epoch": 0.13917841814837523, + "grad_norm": 0.5256398916244507, + "learning_rate": 9.622161422700984e-05, + "loss": 1.7681, + "step": 2497 + }, + { + "epoch": 0.13923415640153838, + "grad_norm": 0.5021438002586365, + "learning_rate": 9.621821789709267e-05, + "loss": 1.6317, + "step": 2498 + }, + { + "epoch": 0.1392898946547015, + "grad_norm": 0.5900087952613831, + "learning_rate": 9.62148201014031e-05, + "loss": 1.8691, + "step": 2499 + }, + { + "epoch": 0.13934563290786467, + "grad_norm": 0.492544025182724, + "learning_rate": 9.621142084004889e-05, + "loss": 1.6061, + "step": 2500 + }, + { + "epoch": 0.13940137116102783, + "grad_norm": 0.5590608716011047, + "learning_rate": 9.620802011313785e-05, + "loss": 1.9551, + "step": 2501 + }, + { + "epoch": 0.13945710941419096, + "grad_norm": 0.5163889527320862, + "learning_rate": 9.620461792077782e-05, + "loss": 1.8419, + "step": 2502 + }, + { + "epoch": 0.1395128476673541, + "grad_norm": 0.5565062165260315, + "learning_rate": 9.620121426307669e-05, + "loss": 1.9454, + "step": 2503 + }, + { + "epoch": 0.13956858592051724, + "grad_norm": 0.5010280013084412, + "learning_rate": 9.619780914014242e-05, + "loss": 1.6189, + "step": 2504 + }, + { + "epoch": 0.1396243241736804, + "grad_norm": 0.5342069268226624, + "learning_rate": 9.619440255208301e-05, + "loss": 1.7667, + "step": 2505 + }, + { + "epoch": 0.13968006242684355, + "grad_norm": 0.5092571377754211, + "learning_rate": 9.619099449900646e-05, + "loss": 1.6797, + "step": 2506 + }, + { + "epoch": 0.13973580068000668, + "grad_norm": 0.5784452557563782, + "learning_rate": 9.618758498102089e-05, + "loss": 1.9559, + "step": 2507 + }, + { + "epoch": 0.13979153893316984, + "grad_norm": 0.5389965176582336, + "learning_rate": 9.618417399823441e-05, + "loss": 1.7971, + "step": 2508 + }, + { + "epoch": 0.13984727718633297, + "grad_norm": 0.5197558999061584, + "learning_rate": 9.618076155075521e-05, + "loss": 1.8631, + "step": 2509 + }, + { + "epoch": 0.13990301543949613, + "grad_norm": 0.5198122262954712, + "learning_rate": 9.617734763869151e-05, + "loss": 1.7487, + "step": 2510 + }, + { + "epoch": 0.13995875369265928, + "grad_norm": 0.515998363494873, + "learning_rate": 9.617393226215157e-05, + "loss": 1.6849, + "step": 2511 + }, + { + "epoch": 0.1400144919458224, + "grad_norm": 0.5627748370170593, + "learning_rate": 9.617051542124371e-05, + "loss": 1.7637, + "step": 2512 + }, + { + "epoch": 0.14007023019898557, + "grad_norm": 0.49436190724372864, + "learning_rate": 9.61670971160763e-05, + "loss": 1.6303, + "step": 2513 + }, + { + "epoch": 0.1401259684521487, + "grad_norm": 0.5101426839828491, + "learning_rate": 9.616367734675772e-05, + "loss": 1.5709, + "step": 2514 + }, + { + "epoch": 0.14018170670531185, + "grad_norm": 0.5416966080665588, + "learning_rate": 9.616025611339647e-05, + "loss": 1.8456, + "step": 2515 + }, + { + "epoch": 0.140237444958475, + "grad_norm": 0.5797568559646606, + "learning_rate": 9.615683341610103e-05, + "loss": 1.7499, + "step": 2516 + }, + { + "epoch": 0.14029318321163814, + "grad_norm": 0.5696927905082703, + "learning_rate": 9.615340925497995e-05, + "loss": 1.6875, + "step": 2517 + }, + { + "epoch": 0.1403489214648013, + "grad_norm": 0.49985361099243164, + "learning_rate": 9.61499836301418e-05, + "loss": 1.6336, + "step": 2518 + }, + { + "epoch": 0.14040465971796443, + "grad_norm": 0.5426433086395264, + "learning_rate": 9.614655654169527e-05, + "loss": 1.8164, + "step": 2519 + }, + { + "epoch": 0.14046039797112758, + "grad_norm": 0.562021017074585, + "learning_rate": 9.6143127989749e-05, + "loss": 1.626, + "step": 2520 + }, + { + "epoch": 0.14051613622429074, + "grad_norm": 0.5873587727546692, + "learning_rate": 9.613969797441173e-05, + "loss": 2.0087, + "step": 2521 + }, + { + "epoch": 0.14057187447745387, + "grad_norm": 0.5239251852035522, + "learning_rate": 9.613626649579229e-05, + "loss": 1.74, + "step": 2522 + }, + { + "epoch": 0.14062761273061702, + "grad_norm": 0.613498330116272, + "learning_rate": 9.613283355399945e-05, + "loss": 1.7088, + "step": 2523 + }, + { + "epoch": 0.14068335098378018, + "grad_norm": 0.5224273800849915, + "learning_rate": 9.61293991491421e-05, + "loss": 1.5665, + "step": 2524 + }, + { + "epoch": 0.1407390892369433, + "grad_norm": 0.5063479542732239, + "learning_rate": 9.612596328132915e-05, + "loss": 1.3456, + "step": 2525 + }, + { + "epoch": 0.14079482749010647, + "grad_norm": 0.5042296648025513, + "learning_rate": 9.61225259506696e-05, + "loss": 1.6111, + "step": 2526 + }, + { + "epoch": 0.1408505657432696, + "grad_norm": 0.5116347670555115, + "learning_rate": 9.611908715727244e-05, + "loss": 1.9546, + "step": 2527 + }, + { + "epoch": 0.14090630399643275, + "grad_norm": 0.5643008351325989, + "learning_rate": 9.611564690124672e-05, + "loss": 1.8488, + "step": 2528 + }, + { + "epoch": 0.1409620422495959, + "grad_norm": 0.5275754332542419, + "learning_rate": 9.611220518270155e-05, + "loss": 1.7367, + "step": 2529 + }, + { + "epoch": 0.14101778050275904, + "grad_norm": 0.523114800453186, + "learning_rate": 9.61087620017461e-05, + "loss": 1.5207, + "step": 2530 + }, + { + "epoch": 0.1410735187559222, + "grad_norm": 0.5141943693161011, + "learning_rate": 9.610531735848953e-05, + "loss": 1.6592, + "step": 2531 + }, + { + "epoch": 0.14112925700908532, + "grad_norm": 0.5485236048698425, + "learning_rate": 9.610187125304111e-05, + "loss": 1.7567, + "step": 2532 + }, + { + "epoch": 0.14118499526224848, + "grad_norm": 0.537264347076416, + "learning_rate": 9.609842368551014e-05, + "loss": 1.7151, + "step": 2533 + }, + { + "epoch": 0.14124073351541164, + "grad_norm": 0.588664174079895, + "learning_rate": 9.609497465600595e-05, + "loss": 1.9591, + "step": 2534 + }, + { + "epoch": 0.14129647176857477, + "grad_norm": 0.5192539691925049, + "learning_rate": 9.60915241646379e-05, + "loss": 1.7296, + "step": 2535 + }, + { + "epoch": 0.14135221002173792, + "grad_norm": 0.543268620967865, + "learning_rate": 9.608807221151543e-05, + "loss": 1.7645, + "step": 2536 + }, + { + "epoch": 0.14140794827490105, + "grad_norm": 0.534324049949646, + "learning_rate": 9.608461879674802e-05, + "loss": 1.8227, + "step": 2537 + }, + { + "epoch": 0.1414636865280642, + "grad_norm": 0.5177492499351501, + "learning_rate": 9.608116392044521e-05, + "loss": 1.6495, + "step": 2538 + }, + { + "epoch": 0.14151942478122737, + "grad_norm": 0.5617666840553284, + "learning_rate": 9.607770758271655e-05, + "loss": 1.9329, + "step": 2539 + }, + { + "epoch": 0.1415751630343905, + "grad_norm": 0.5591059327125549, + "learning_rate": 9.607424978367165e-05, + "loss": 1.8535, + "step": 2540 + }, + { + "epoch": 0.14163090128755365, + "grad_norm": 0.5114865899085999, + "learning_rate": 9.607079052342018e-05, + "loss": 1.6956, + "step": 2541 + }, + { + "epoch": 0.1416866395407168, + "grad_norm": 0.5444316864013672, + "learning_rate": 9.606732980207184e-05, + "loss": 1.6842, + "step": 2542 + }, + { + "epoch": 0.14174237779387994, + "grad_norm": 0.5291377305984497, + "learning_rate": 9.606386761973641e-05, + "loss": 1.778, + "step": 2543 + }, + { + "epoch": 0.1417981160470431, + "grad_norm": 0.5469574332237244, + "learning_rate": 9.606040397652365e-05, + "loss": 1.8492, + "step": 2544 + }, + { + "epoch": 0.14185385430020622, + "grad_norm": 0.5374149084091187, + "learning_rate": 9.605693887254343e-05, + "loss": 1.8428, + "step": 2545 + }, + { + "epoch": 0.14190959255336938, + "grad_norm": 0.5556001663208008, + "learning_rate": 9.605347230790565e-05, + "loss": 1.786, + "step": 2546 + }, + { + "epoch": 0.14196533080653254, + "grad_norm": 0.5268534421920776, + "learning_rate": 9.605000428272023e-05, + "loss": 1.5936, + "step": 2547 + }, + { + "epoch": 0.14202106905969566, + "grad_norm": 0.5348252058029175, + "learning_rate": 9.604653479709717e-05, + "loss": 1.8033, + "step": 2548 + }, + { + "epoch": 0.14207680731285882, + "grad_norm": 0.47919270396232605, + "learning_rate": 9.60430638511465e-05, + "loss": 1.5892, + "step": 2549 + }, + { + "epoch": 0.14213254556602195, + "grad_norm": 0.5066027045249939, + "learning_rate": 9.603959144497827e-05, + "loss": 1.6489, + "step": 2550 + }, + { + "epoch": 0.1421882838191851, + "grad_norm": 0.512729823589325, + "learning_rate": 9.603611757870266e-05, + "loss": 1.4806, + "step": 2551 + }, + { + "epoch": 0.14224402207234826, + "grad_norm": 0.5020458102226257, + "learning_rate": 9.603264225242978e-05, + "loss": 1.7944, + "step": 2552 + }, + { + "epoch": 0.1422997603255114, + "grad_norm": 0.5788121819496155, + "learning_rate": 9.60291654662699e-05, + "loss": 1.828, + "step": 2553 + }, + { + "epoch": 0.14235549857867455, + "grad_norm": 0.5426775217056274, + "learning_rate": 9.602568722033326e-05, + "loss": 1.8621, + "step": 2554 + }, + { + "epoch": 0.14241123683183768, + "grad_norm": 0.5158776044845581, + "learning_rate": 9.602220751473015e-05, + "loss": 1.8829, + "step": 2555 + }, + { + "epoch": 0.14246697508500084, + "grad_norm": 0.48226305842399597, + "learning_rate": 9.601872634957096e-05, + "loss": 1.6547, + "step": 2556 + }, + { + "epoch": 0.142522713338164, + "grad_norm": 0.5081673860549927, + "learning_rate": 9.601524372496608e-05, + "loss": 1.6629, + "step": 2557 + }, + { + "epoch": 0.14257845159132712, + "grad_norm": 0.5080944299697876, + "learning_rate": 9.601175964102596e-05, + "loss": 1.8285, + "step": 2558 + }, + { + "epoch": 0.14263418984449028, + "grad_norm": 0.5221143364906311, + "learning_rate": 9.600827409786107e-05, + "loss": 1.9544, + "step": 2559 + }, + { + "epoch": 0.1426899280976534, + "grad_norm": 0.5045720338821411, + "learning_rate": 9.600478709558199e-05, + "loss": 1.5243, + "step": 2560 + }, + { + "epoch": 0.14274566635081656, + "grad_norm": 0.5300230383872986, + "learning_rate": 9.600129863429929e-05, + "loss": 1.6888, + "step": 2561 + }, + { + "epoch": 0.14280140460397972, + "grad_norm": 0.5262769460678101, + "learning_rate": 9.599780871412359e-05, + "loss": 1.8205, + "step": 2562 + }, + { + "epoch": 0.14285714285714285, + "grad_norm": 0.5437910556793213, + "learning_rate": 9.59943173351656e-05, + "loss": 1.69, + "step": 2563 + }, + { + "epoch": 0.142912881110306, + "grad_norm": 0.5781261324882507, + "learning_rate": 9.599082449753602e-05, + "loss": 1.918, + "step": 2564 + }, + { + "epoch": 0.14296861936346916, + "grad_norm": 0.5519402623176575, + "learning_rate": 9.598733020134562e-05, + "loss": 1.7039, + "step": 2565 + }, + { + "epoch": 0.1430243576166323, + "grad_norm": 0.5874602198600769, + "learning_rate": 9.598383444670526e-05, + "loss": 1.6948, + "step": 2566 + }, + { + "epoch": 0.14308009586979545, + "grad_norm": 0.5131939649581909, + "learning_rate": 9.598033723372575e-05, + "loss": 1.6666, + "step": 2567 + }, + { + "epoch": 0.14313583412295858, + "grad_norm": 0.6441419124603271, + "learning_rate": 9.597683856251804e-05, + "loss": 1.9023, + "step": 2568 + }, + { + "epoch": 0.14319157237612173, + "grad_norm": 0.48139771819114685, + "learning_rate": 9.597333843319309e-05, + "loss": 1.6297, + "step": 2569 + }, + { + "epoch": 0.1432473106292849, + "grad_norm": 0.4975999891757965, + "learning_rate": 9.596983684586186e-05, + "loss": 1.6558, + "step": 2570 + }, + { + "epoch": 0.14330304888244802, + "grad_norm": 0.5479779839515686, + "learning_rate": 9.596633380063544e-05, + "loss": 1.78, + "step": 2571 + }, + { + "epoch": 0.14335878713561118, + "grad_norm": 0.5358686447143555, + "learning_rate": 9.596282929762492e-05, + "loss": 1.848, + "step": 2572 + }, + { + "epoch": 0.1434145253887743, + "grad_norm": 0.5355905890464783, + "learning_rate": 9.595932333694142e-05, + "loss": 1.847, + "step": 2573 + }, + { + "epoch": 0.14347026364193746, + "grad_norm": 0.5640880465507507, + "learning_rate": 9.595581591869616e-05, + "loss": 1.713, + "step": 2574 + }, + { + "epoch": 0.14352600189510062, + "grad_norm": 0.5763548016548157, + "learning_rate": 9.595230704300035e-05, + "loss": 1.9647, + "step": 2575 + }, + { + "epoch": 0.14358174014826375, + "grad_norm": 0.5426276922225952, + "learning_rate": 9.594879670996528e-05, + "loss": 1.7378, + "step": 2576 + }, + { + "epoch": 0.1436374784014269, + "grad_norm": 0.5128087997436523, + "learning_rate": 9.594528491970228e-05, + "loss": 1.7663, + "step": 2577 + }, + { + "epoch": 0.14369321665459003, + "grad_norm": 0.5331497192382812, + "learning_rate": 9.594177167232273e-05, + "loss": 1.6068, + "step": 2578 + }, + { + "epoch": 0.1437489549077532, + "grad_norm": 0.5513312220573425, + "learning_rate": 9.593825696793803e-05, + "loss": 1.6527, + "step": 2579 + }, + { + "epoch": 0.14380469316091635, + "grad_norm": 0.5069592595100403, + "learning_rate": 9.593474080665968e-05, + "loss": 1.5839, + "step": 2580 + }, + { + "epoch": 0.14386043141407948, + "grad_norm": 0.5478212237358093, + "learning_rate": 9.593122318859915e-05, + "loss": 1.8217, + "step": 2581 + }, + { + "epoch": 0.14391616966724263, + "grad_norm": 0.5398098230361938, + "learning_rate": 9.592770411386802e-05, + "loss": 1.8395, + "step": 2582 + }, + { + "epoch": 0.14397190792040576, + "grad_norm": 0.535152792930603, + "learning_rate": 9.592418358257789e-05, + "loss": 1.8477, + "step": 2583 + }, + { + "epoch": 0.14402764617356892, + "grad_norm": 0.5321324467658997, + "learning_rate": 9.592066159484043e-05, + "loss": 1.6152, + "step": 2584 + }, + { + "epoch": 0.14408338442673208, + "grad_norm": 0.525637686252594, + "learning_rate": 9.59171381507673e-05, + "loss": 1.8558, + "step": 2585 + }, + { + "epoch": 0.1441391226798952, + "grad_norm": 0.5971347689628601, + "learning_rate": 9.591361325047028e-05, + "loss": 1.8752, + "step": 2586 + }, + { + "epoch": 0.14419486093305836, + "grad_norm": 0.5029361844062805, + "learning_rate": 9.591008689406114e-05, + "loss": 1.6977, + "step": 2587 + }, + { + "epoch": 0.14425059918622152, + "grad_norm": 0.5642208456993103, + "learning_rate": 9.59065590816517e-05, + "loss": 1.8379, + "step": 2588 + }, + { + "epoch": 0.14430633743938465, + "grad_norm": 0.5269021391868591, + "learning_rate": 9.590302981335387e-05, + "loss": 1.98, + "step": 2589 + }, + { + "epoch": 0.1443620756925478, + "grad_norm": 0.5572815537452698, + "learning_rate": 9.589949908927957e-05, + "loss": 1.7123, + "step": 2590 + }, + { + "epoch": 0.14441781394571093, + "grad_norm": 0.5520729422569275, + "learning_rate": 9.589596690954077e-05, + "loss": 1.8578, + "step": 2591 + }, + { + "epoch": 0.1444735521988741, + "grad_norm": 0.5181688070297241, + "learning_rate": 9.589243327424951e-05, + "loss": 1.7641, + "step": 2592 + }, + { + "epoch": 0.14452929045203725, + "grad_norm": 0.5066071152687073, + "learning_rate": 9.588889818351781e-05, + "loss": 1.6991, + "step": 2593 + }, + { + "epoch": 0.14458502870520037, + "grad_norm": 0.5530059933662415, + "learning_rate": 9.588536163745782e-05, + "loss": 1.7019, + "step": 2594 + }, + { + "epoch": 0.14464076695836353, + "grad_norm": 0.5519603490829468, + "learning_rate": 9.58818236361817e-05, + "loss": 1.6645, + "step": 2595 + }, + { + "epoch": 0.14469650521152666, + "grad_norm": 0.6039948463439941, + "learning_rate": 9.587828417980163e-05, + "loss": 2.0606, + "step": 2596 + }, + { + "epoch": 0.14475224346468982, + "grad_norm": 0.5822129845619202, + "learning_rate": 9.587474326842987e-05, + "loss": 1.8879, + "step": 2597 + }, + { + "epoch": 0.14480798171785297, + "grad_norm": 0.5391368865966797, + "learning_rate": 9.587120090217874e-05, + "loss": 1.6668, + "step": 2598 + }, + { + "epoch": 0.1448637199710161, + "grad_norm": 0.505940854549408, + "learning_rate": 9.586765708116056e-05, + "loss": 1.6322, + "step": 2599 + }, + { + "epoch": 0.14491945822417926, + "grad_norm": 0.5613484978675842, + "learning_rate": 9.586411180548771e-05, + "loss": 1.7002, + "step": 2600 + }, + { + "epoch": 0.1449751964773424, + "grad_norm": 0.5343160629272461, + "learning_rate": 9.586056507527266e-05, + "loss": 1.8232, + "step": 2601 + }, + { + "epoch": 0.14503093473050555, + "grad_norm": 0.5221366286277771, + "learning_rate": 9.585701689062785e-05, + "loss": 1.7799, + "step": 2602 + }, + { + "epoch": 0.1450866729836687, + "grad_norm": 0.503301739692688, + "learning_rate": 9.585346725166584e-05, + "loss": 1.5724, + "step": 2603 + }, + { + "epoch": 0.14514241123683183, + "grad_norm": 0.5650082230567932, + "learning_rate": 9.584991615849921e-05, + "loss": 1.898, + "step": 2604 + }, + { + "epoch": 0.145198149489995, + "grad_norm": 0.4780997633934021, + "learning_rate": 9.584636361124054e-05, + "loss": 1.5643, + "step": 2605 + }, + { + "epoch": 0.14525388774315812, + "grad_norm": 0.5057533979415894, + "learning_rate": 9.584280961000253e-05, + "loss": 1.575, + "step": 2606 + }, + { + "epoch": 0.14530962599632127, + "grad_norm": 0.530737578868866, + "learning_rate": 9.583925415489787e-05, + "loss": 1.7932, + "step": 2607 + }, + { + "epoch": 0.14536536424948443, + "grad_norm": 0.603374719619751, + "learning_rate": 9.583569724603934e-05, + "loss": 2.0627, + "step": 2608 + }, + { + "epoch": 0.14542110250264756, + "grad_norm": 0.5549886226654053, + "learning_rate": 9.583213888353972e-05, + "loss": 1.7767, + "step": 2609 + }, + { + "epoch": 0.14547684075581072, + "grad_norm": 0.6217805743217468, + "learning_rate": 9.582857906751191e-05, + "loss": 2.05, + "step": 2610 + }, + { + "epoch": 0.14553257900897387, + "grad_norm": 0.5606620907783508, + "learning_rate": 9.582501779806874e-05, + "loss": 1.7722, + "step": 2611 + }, + { + "epoch": 0.145588317262137, + "grad_norm": 0.5387722253799438, + "learning_rate": 9.582145507532319e-05, + "loss": 1.6958, + "step": 2612 + }, + { + "epoch": 0.14564405551530016, + "grad_norm": 0.557847797870636, + "learning_rate": 9.581789089938825e-05, + "loss": 1.8401, + "step": 2613 + }, + { + "epoch": 0.1456997937684633, + "grad_norm": 0.5201898217201233, + "learning_rate": 9.581432527037693e-05, + "loss": 1.7684, + "step": 2614 + }, + { + "epoch": 0.14575553202162644, + "grad_norm": 0.5138794183731079, + "learning_rate": 9.581075818840234e-05, + "loss": 1.7435, + "step": 2615 + }, + { + "epoch": 0.1458112702747896, + "grad_norm": 0.5721390247344971, + "learning_rate": 9.58071896535776e-05, + "loss": 1.8191, + "step": 2616 + }, + { + "epoch": 0.14586700852795273, + "grad_norm": 0.5593292117118835, + "learning_rate": 9.580361966601588e-05, + "loss": 1.877, + "step": 2617 + }, + { + "epoch": 0.1459227467811159, + "grad_norm": 0.5009481906890869, + "learning_rate": 9.580004822583038e-05, + "loss": 1.6282, + "step": 2618 + }, + { + "epoch": 0.14597848503427902, + "grad_norm": 0.4969474673271179, + "learning_rate": 9.579647533313439e-05, + "loss": 1.7076, + "step": 2619 + }, + { + "epoch": 0.14603422328744217, + "grad_norm": 0.5316969156265259, + "learning_rate": 9.579290098804122e-05, + "loss": 1.6271, + "step": 2620 + }, + { + "epoch": 0.14608996154060533, + "grad_norm": 0.5574962496757507, + "learning_rate": 9.578932519066422e-05, + "loss": 1.8687, + "step": 2621 + }, + { + "epoch": 0.14614569979376846, + "grad_norm": 0.499491423368454, + "learning_rate": 9.57857479411168e-05, + "loss": 1.6985, + "step": 2622 + }, + { + "epoch": 0.14620143804693161, + "grad_norm": 0.654602587223053, + "learning_rate": 9.57821692395124e-05, + "loss": 1.7291, + "step": 2623 + }, + { + "epoch": 0.14625717630009474, + "grad_norm": 0.5459001660346985, + "learning_rate": 9.577858908596451e-05, + "loss": 1.729, + "step": 2624 + }, + { + "epoch": 0.1463129145532579, + "grad_norm": 0.5157297849655151, + "learning_rate": 9.57750074805867e-05, + "loss": 1.4164, + "step": 2625 + }, + { + "epoch": 0.14636865280642106, + "grad_norm": 0.5205078125, + "learning_rate": 9.577142442349254e-05, + "loss": 1.7282, + "step": 2626 + }, + { + "epoch": 0.14642439105958419, + "grad_norm": 0.563706636428833, + "learning_rate": 9.576783991479565e-05, + "loss": 1.8092, + "step": 2627 + }, + { + "epoch": 0.14648012931274734, + "grad_norm": 0.5385141968727112, + "learning_rate": 9.576425395460973e-05, + "loss": 1.8241, + "step": 2628 + }, + { + "epoch": 0.14653586756591047, + "grad_norm": 0.6100838780403137, + "learning_rate": 9.576066654304849e-05, + "loss": 1.9425, + "step": 2629 + }, + { + "epoch": 0.14659160581907363, + "grad_norm": 0.5153439044952393, + "learning_rate": 9.575707768022572e-05, + "loss": 1.4287, + "step": 2630 + }, + { + "epoch": 0.14664734407223678, + "grad_norm": 0.5562304258346558, + "learning_rate": 9.575348736625523e-05, + "loss": 1.9308, + "step": 2631 + }, + { + "epoch": 0.14670308232539991, + "grad_norm": 0.5785409808158875, + "learning_rate": 9.574989560125087e-05, + "loss": 1.8831, + "step": 2632 + }, + { + "epoch": 0.14675882057856307, + "grad_norm": 0.5315858721733093, + "learning_rate": 9.574630238532658e-05, + "loss": 1.5871, + "step": 2633 + }, + { + "epoch": 0.14681455883172623, + "grad_norm": 0.5748802423477173, + "learning_rate": 9.574270771859628e-05, + "loss": 1.8394, + "step": 2634 + }, + { + "epoch": 0.14687029708488936, + "grad_norm": 0.5130333304405212, + "learning_rate": 9.5739111601174e-05, + "loss": 1.8598, + "step": 2635 + }, + { + "epoch": 0.1469260353380525, + "grad_norm": 0.5098990201950073, + "learning_rate": 9.573551403317378e-05, + "loss": 1.5862, + "step": 2636 + }, + { + "epoch": 0.14698177359121564, + "grad_norm": 0.5426929593086243, + "learning_rate": 9.573191501470971e-05, + "loss": 1.8026, + "step": 2637 + }, + { + "epoch": 0.1470375118443788, + "grad_norm": 0.5652133226394653, + "learning_rate": 9.572831454589592e-05, + "loss": 1.7529, + "step": 2638 + }, + { + "epoch": 0.14709325009754196, + "grad_norm": 0.5370623469352722, + "learning_rate": 9.572471262684662e-05, + "loss": 1.7851, + "step": 2639 + }, + { + "epoch": 0.14714898835070508, + "grad_norm": 0.5871500372886658, + "learning_rate": 9.572110925767601e-05, + "loss": 1.7617, + "step": 2640 + }, + { + "epoch": 0.14720472660386824, + "grad_norm": 0.5181992053985596, + "learning_rate": 9.571750443849841e-05, + "loss": 1.6418, + "step": 2641 + }, + { + "epoch": 0.14726046485703137, + "grad_norm": 0.5635068416595459, + "learning_rate": 9.571389816942811e-05, + "loss": 2.0309, + "step": 2642 + }, + { + "epoch": 0.14731620311019453, + "grad_norm": 0.5830138921737671, + "learning_rate": 9.571029045057948e-05, + "loss": 1.8764, + "step": 2643 + }, + { + "epoch": 0.14737194136335768, + "grad_norm": 0.5109788179397583, + "learning_rate": 9.570668128206697e-05, + "loss": 1.6183, + "step": 2644 + }, + { + "epoch": 0.1474276796165208, + "grad_norm": 0.5681736469268799, + "learning_rate": 9.5703070664005e-05, + "loss": 1.738, + "step": 2645 + }, + { + "epoch": 0.14748341786968397, + "grad_norm": 0.5385489463806152, + "learning_rate": 9.56994585965081e-05, + "loss": 1.7379, + "step": 2646 + }, + { + "epoch": 0.1475391561228471, + "grad_norm": 0.5935365557670593, + "learning_rate": 9.569584507969082e-05, + "loss": 1.6596, + "step": 2647 + }, + { + "epoch": 0.14759489437601025, + "grad_norm": 0.5758340358734131, + "learning_rate": 9.569223011366776e-05, + "loss": 1.7998, + "step": 2648 + }, + { + "epoch": 0.1476506326291734, + "grad_norm": 0.5150250196456909, + "learning_rate": 9.568861369855357e-05, + "loss": 1.5843, + "step": 2649 + }, + { + "epoch": 0.14770637088233654, + "grad_norm": 0.549801230430603, + "learning_rate": 9.568499583446293e-05, + "loss": 1.6966, + "step": 2650 + }, + { + "epoch": 0.1477621091354997, + "grad_norm": 0.5092233419418335, + "learning_rate": 9.568137652151059e-05, + "loss": 1.7318, + "step": 2651 + }, + { + "epoch": 0.14781784738866283, + "grad_norm": 0.5549139976501465, + "learning_rate": 9.567775575981133e-05, + "loss": 1.8252, + "step": 2652 + }, + { + "epoch": 0.14787358564182598, + "grad_norm": 0.5805264115333557, + "learning_rate": 9.567413354947997e-05, + "loss": 1.8455, + "step": 2653 + }, + { + "epoch": 0.14792932389498914, + "grad_norm": 0.5241934657096863, + "learning_rate": 9.56705098906314e-05, + "loss": 1.8003, + "step": 2654 + }, + { + "epoch": 0.14798506214815227, + "grad_norm": 0.5738681554794312, + "learning_rate": 9.566688478338053e-05, + "loss": 1.765, + "step": 2655 + }, + { + "epoch": 0.14804080040131543, + "grad_norm": 0.5123993158340454, + "learning_rate": 9.566325822784232e-05, + "loss": 1.686, + "step": 2656 + }, + { + "epoch": 0.14809653865447858, + "grad_norm": 0.5327409505844116, + "learning_rate": 9.56596302241318e-05, + "loss": 1.9386, + "step": 2657 + }, + { + "epoch": 0.1481522769076417, + "grad_norm": 0.4922872483730316, + "learning_rate": 9.565600077236403e-05, + "loss": 1.6464, + "step": 2658 + }, + { + "epoch": 0.14820801516080487, + "grad_norm": 0.5839138031005859, + "learning_rate": 9.565236987265411e-05, + "loss": 2.0237, + "step": 2659 + }, + { + "epoch": 0.148263753413968, + "grad_norm": 0.5407429933547974, + "learning_rate": 9.564873752511718e-05, + "loss": 1.9181, + "step": 2660 + }, + { + "epoch": 0.14831949166713115, + "grad_norm": 0.5354205369949341, + "learning_rate": 9.564510372986845e-05, + "loss": 1.9004, + "step": 2661 + }, + { + "epoch": 0.1483752299202943, + "grad_norm": 0.517620325088501, + "learning_rate": 9.564146848702316e-05, + "loss": 1.4634, + "step": 2662 + }, + { + "epoch": 0.14843096817345744, + "grad_norm": 0.513761579990387, + "learning_rate": 9.56378317966966e-05, + "loss": 1.7994, + "step": 2663 + }, + { + "epoch": 0.1484867064266206, + "grad_norm": 0.520189642906189, + "learning_rate": 9.56341936590041e-05, + "loss": 1.493, + "step": 2664 + }, + { + "epoch": 0.14854244467978373, + "grad_norm": 0.5256882905960083, + "learning_rate": 9.563055407406104e-05, + "loss": 1.747, + "step": 2665 + }, + { + "epoch": 0.14859818293294688, + "grad_norm": 0.5171797871589661, + "learning_rate": 9.562691304198286e-05, + "loss": 1.7043, + "step": 2666 + }, + { + "epoch": 0.14865392118611004, + "grad_norm": 0.5845912098884583, + "learning_rate": 9.5623270562885e-05, + "loss": 1.8348, + "step": 2667 + }, + { + "epoch": 0.14870965943927317, + "grad_norm": 0.5168249011039734, + "learning_rate": 9.561962663688302e-05, + "loss": 1.5255, + "step": 2668 + }, + { + "epoch": 0.14876539769243632, + "grad_norm": 0.5021228790283203, + "learning_rate": 9.561598126409245e-05, + "loss": 1.5113, + "step": 2669 + }, + { + "epoch": 0.14882113594559945, + "grad_norm": 0.5029981732368469, + "learning_rate": 9.561233444462894e-05, + "loss": 1.5927, + "step": 2670 + }, + { + "epoch": 0.1488768741987626, + "grad_norm": 0.5585193634033203, + "learning_rate": 9.56086861786081e-05, + "loss": 1.9007, + "step": 2671 + }, + { + "epoch": 0.14893261245192577, + "grad_norm": 0.4993244409561157, + "learning_rate": 9.560503646614564e-05, + "loss": 1.5592, + "step": 2672 + }, + { + "epoch": 0.1489883507050889, + "grad_norm": 0.4925285875797272, + "learning_rate": 9.560138530735734e-05, + "loss": 1.5822, + "step": 2673 + }, + { + "epoch": 0.14904408895825205, + "grad_norm": 0.5714946985244751, + "learning_rate": 9.559773270235896e-05, + "loss": 1.703, + "step": 2674 + }, + { + "epoch": 0.14909982721141518, + "grad_norm": 0.5588274598121643, + "learning_rate": 9.559407865126636e-05, + "loss": 1.7473, + "step": 2675 + }, + { + "epoch": 0.14915556546457834, + "grad_norm": 0.5327757000923157, + "learning_rate": 9.559042315419542e-05, + "loss": 1.6382, + "step": 2676 + }, + { + "epoch": 0.1492113037177415, + "grad_norm": 0.5377374887466431, + "learning_rate": 9.558676621126206e-05, + "loss": 1.7602, + "step": 2677 + }, + { + "epoch": 0.14926704197090462, + "grad_norm": 0.5468077659606934, + "learning_rate": 9.558310782258227e-05, + "loss": 1.7686, + "step": 2678 + }, + { + "epoch": 0.14932278022406778, + "grad_norm": 0.5344017744064331, + "learning_rate": 9.557944798827205e-05, + "loss": 1.6661, + "step": 2679 + }, + { + "epoch": 0.14937851847723094, + "grad_norm": 0.5011274218559265, + "learning_rate": 9.557578670844751e-05, + "loss": 1.6757, + "step": 2680 + }, + { + "epoch": 0.14943425673039407, + "grad_norm": 0.5330647826194763, + "learning_rate": 9.557212398322473e-05, + "loss": 1.8146, + "step": 2681 + }, + { + "epoch": 0.14948999498355722, + "grad_norm": 0.5211254954338074, + "learning_rate": 9.556845981271989e-05, + "loss": 1.7437, + "step": 2682 + }, + { + "epoch": 0.14954573323672035, + "grad_norm": 0.603344738483429, + "learning_rate": 9.556479419704918e-05, + "loss": 2.0424, + "step": 2683 + }, + { + "epoch": 0.1496014714898835, + "grad_norm": 0.5117289423942566, + "learning_rate": 9.556112713632885e-05, + "loss": 1.6523, + "step": 2684 + }, + { + "epoch": 0.14965720974304667, + "grad_norm": 0.5624164938926697, + "learning_rate": 9.555745863067522e-05, + "loss": 1.8348, + "step": 2685 + }, + { + "epoch": 0.1497129479962098, + "grad_norm": 0.4994141459465027, + "learning_rate": 9.555378868020461e-05, + "loss": 1.6003, + "step": 2686 + }, + { + "epoch": 0.14976868624937295, + "grad_norm": 0.5267731547355652, + "learning_rate": 9.555011728503343e-05, + "loss": 1.6412, + "step": 2687 + }, + { + "epoch": 0.14982442450253608, + "grad_norm": 0.4905613958835602, + "learning_rate": 9.554644444527812e-05, + "loss": 1.6397, + "step": 2688 + }, + { + "epoch": 0.14988016275569924, + "grad_norm": 0.5710086226463318, + "learning_rate": 9.554277016105512e-05, + "loss": 2.0408, + "step": 2689 + }, + { + "epoch": 0.1499359010088624, + "grad_norm": 0.5375673770904541, + "learning_rate": 9.5539094432481e-05, + "loss": 1.7599, + "step": 2690 + }, + { + "epoch": 0.14999163926202552, + "grad_norm": 0.5491001009941101, + "learning_rate": 9.55354172596723e-05, + "loss": 1.6704, + "step": 2691 + }, + { + "epoch": 0.15004737751518868, + "grad_norm": 0.5431581139564514, + "learning_rate": 9.553173864274567e-05, + "loss": 1.7792, + "step": 2692 + }, + { + "epoch": 0.1501031157683518, + "grad_norm": 0.5338147282600403, + "learning_rate": 9.552805858181775e-05, + "loss": 1.7461, + "step": 2693 + }, + { + "epoch": 0.15015885402151496, + "grad_norm": 0.5207554697990417, + "learning_rate": 9.552437707700526e-05, + "loss": 1.7735, + "step": 2694 + }, + { + "epoch": 0.15021459227467812, + "grad_norm": 0.515975296497345, + "learning_rate": 9.552069412842495e-05, + "loss": 1.6318, + "step": 2695 + }, + { + "epoch": 0.15027033052784125, + "grad_norm": 0.5207625031471252, + "learning_rate": 9.551700973619364e-05, + "loss": 1.665, + "step": 2696 + }, + { + "epoch": 0.1503260687810044, + "grad_norm": 0.5158435702323914, + "learning_rate": 9.551332390042816e-05, + "loss": 1.743, + "step": 2697 + }, + { + "epoch": 0.15038180703416754, + "grad_norm": 0.5647339224815369, + "learning_rate": 9.55096366212454e-05, + "loss": 1.9245, + "step": 2698 + }, + { + "epoch": 0.1504375452873307, + "grad_norm": 0.545265793800354, + "learning_rate": 9.55059478987623e-05, + "loss": 1.5553, + "step": 2699 + }, + { + "epoch": 0.15049328354049385, + "grad_norm": 0.5328176617622375, + "learning_rate": 9.550225773309586e-05, + "loss": 1.4489, + "step": 2700 + }, + { + "epoch": 0.15054902179365698, + "grad_norm": 0.5154641270637512, + "learning_rate": 9.54985661243631e-05, + "loss": 1.9052, + "step": 2701 + }, + { + "epoch": 0.15060476004682014, + "grad_norm": 0.5019435286521912, + "learning_rate": 9.54948730726811e-05, + "loss": 1.5049, + "step": 2702 + }, + { + "epoch": 0.1506604982999833, + "grad_norm": 0.557501494884491, + "learning_rate": 9.549117857816697e-05, + "loss": 1.8818, + "step": 2703 + }, + { + "epoch": 0.15071623655314642, + "grad_norm": 0.5352375507354736, + "learning_rate": 9.548748264093789e-05, + "loss": 1.6683, + "step": 2704 + }, + { + "epoch": 0.15077197480630958, + "grad_norm": 0.5106709599494934, + "learning_rate": 9.548378526111108e-05, + "loss": 1.6966, + "step": 2705 + }, + { + "epoch": 0.1508277130594727, + "grad_norm": 0.5565862655639648, + "learning_rate": 9.54800864388038e-05, + "loss": 1.8303, + "step": 2706 + }, + { + "epoch": 0.15088345131263586, + "grad_norm": 0.5492972135543823, + "learning_rate": 9.547638617413333e-05, + "loss": 1.8624, + "step": 2707 + }, + { + "epoch": 0.15093918956579902, + "grad_norm": 0.50017249584198, + "learning_rate": 9.547268446721702e-05, + "loss": 1.5654, + "step": 2708 + }, + { + "epoch": 0.15099492781896215, + "grad_norm": 0.48998236656188965, + "learning_rate": 9.54689813181723e-05, + "loss": 1.6074, + "step": 2709 + }, + { + "epoch": 0.1510506660721253, + "grad_norm": 0.5397832989692688, + "learning_rate": 9.54652767271166e-05, + "loss": 1.8095, + "step": 2710 + }, + { + "epoch": 0.15110640432528843, + "grad_norm": 0.5553854703903198, + "learning_rate": 9.54615706941674e-05, + "loss": 1.8065, + "step": 2711 + }, + { + "epoch": 0.1511621425784516, + "grad_norm": 0.5286390781402588, + "learning_rate": 9.545786321944223e-05, + "loss": 1.5857, + "step": 2712 + }, + { + "epoch": 0.15121788083161475, + "grad_norm": 0.4900679588317871, + "learning_rate": 9.545415430305869e-05, + "loss": 1.5847, + "step": 2713 + }, + { + "epoch": 0.15127361908477788, + "grad_norm": 0.5456913113594055, + "learning_rate": 9.545044394513439e-05, + "loss": 1.7911, + "step": 2714 + }, + { + "epoch": 0.15132935733794103, + "grad_norm": 0.5544347763061523, + "learning_rate": 9.544673214578698e-05, + "loss": 1.7341, + "step": 2715 + }, + { + "epoch": 0.15138509559110416, + "grad_norm": 0.5260149836540222, + "learning_rate": 9.544301890513423e-05, + "loss": 1.6531, + "step": 2716 + }, + { + "epoch": 0.15144083384426732, + "grad_norm": 0.5473960638046265, + "learning_rate": 9.543930422329386e-05, + "loss": 1.7704, + "step": 2717 + }, + { + "epoch": 0.15149657209743048, + "grad_norm": 0.5335630178451538, + "learning_rate": 9.543558810038368e-05, + "loss": 1.6427, + "step": 2718 + }, + { + "epoch": 0.1515523103505936, + "grad_norm": 0.558547854423523, + "learning_rate": 9.543187053652156e-05, + "loss": 1.9572, + "step": 2719 + }, + { + "epoch": 0.15160804860375676, + "grad_norm": 0.5423372983932495, + "learning_rate": 9.54281515318254e-05, + "loss": 1.6761, + "step": 2720 + }, + { + "epoch": 0.1516637868569199, + "grad_norm": 0.5132402181625366, + "learning_rate": 9.542443108641312e-05, + "loss": 1.8216, + "step": 2721 + }, + { + "epoch": 0.15171952511008305, + "grad_norm": 0.491897314786911, + "learning_rate": 9.542070920040274e-05, + "loss": 1.5411, + "step": 2722 + }, + { + "epoch": 0.1517752633632462, + "grad_norm": 0.5645871758460999, + "learning_rate": 9.541698587391229e-05, + "loss": 1.848, + "step": 2723 + }, + { + "epoch": 0.15183100161640933, + "grad_norm": 0.5238233208656311, + "learning_rate": 9.541326110705983e-05, + "loss": 1.7717, + "step": 2724 + }, + { + "epoch": 0.1518867398695725, + "grad_norm": 0.5333484411239624, + "learning_rate": 9.540953489996354e-05, + "loss": 1.6865, + "step": 2725 + }, + { + "epoch": 0.15194247812273565, + "grad_norm": 0.5394174456596375, + "learning_rate": 9.540580725274153e-05, + "loss": 1.7526, + "step": 2726 + }, + { + "epoch": 0.15199821637589878, + "grad_norm": 0.5119402408599854, + "learning_rate": 9.540207816551206e-05, + "loss": 1.7543, + "step": 2727 + }, + { + "epoch": 0.15205395462906193, + "grad_norm": 0.4968518912792206, + "learning_rate": 9.539834763839337e-05, + "loss": 1.4261, + "step": 2728 + }, + { + "epoch": 0.15210969288222506, + "grad_norm": 0.5909052491188049, + "learning_rate": 9.539461567150378e-05, + "loss": 1.9545, + "step": 2729 + }, + { + "epoch": 0.15216543113538822, + "grad_norm": 0.5353077054023743, + "learning_rate": 9.539088226496167e-05, + "loss": 1.7021, + "step": 2730 + }, + { + "epoch": 0.15222116938855138, + "grad_norm": 0.526706874370575, + "learning_rate": 9.538714741888541e-05, + "loss": 1.7132, + "step": 2731 + }, + { + "epoch": 0.1522769076417145, + "grad_norm": 0.5296183228492737, + "learning_rate": 9.538341113339346e-05, + "loss": 1.6896, + "step": 2732 + }, + { + "epoch": 0.15233264589487766, + "grad_norm": 0.5836046934127808, + "learning_rate": 9.537967340860432e-05, + "loss": 1.7815, + "step": 2733 + }, + { + "epoch": 0.1523883841480408, + "grad_norm": 0.5508841872215271, + "learning_rate": 9.537593424463651e-05, + "loss": 1.8918, + "step": 2734 + }, + { + "epoch": 0.15244412240120395, + "grad_norm": 0.522796630859375, + "learning_rate": 9.537219364160863e-05, + "loss": 1.7225, + "step": 2735 + }, + { + "epoch": 0.1524998606543671, + "grad_norm": 0.48475125432014465, + "learning_rate": 9.536845159963932e-05, + "loss": 1.5232, + "step": 2736 + }, + { + "epoch": 0.15255559890753023, + "grad_norm": 0.5141192674636841, + "learning_rate": 9.536470811884723e-05, + "loss": 1.8193, + "step": 2737 + }, + { + "epoch": 0.1526113371606934, + "grad_norm": 0.5721970796585083, + "learning_rate": 9.536096319935108e-05, + "loss": 1.9167, + "step": 2738 + }, + { + "epoch": 0.15266707541385652, + "grad_norm": 0.53280109167099, + "learning_rate": 9.535721684126967e-05, + "loss": 1.8613, + "step": 2739 + }, + { + "epoch": 0.15272281366701967, + "grad_norm": 0.5099390745162964, + "learning_rate": 9.535346904472177e-05, + "loss": 1.6646, + "step": 2740 + }, + { + "epoch": 0.15277855192018283, + "grad_norm": 0.8719338774681091, + "learning_rate": 9.53497198098263e-05, + "loss": 1.7495, + "step": 2741 + }, + { + "epoch": 0.15283429017334596, + "grad_norm": 0.6453019380569458, + "learning_rate": 9.53459691367021e-05, + "loss": 1.9952, + "step": 2742 + }, + { + "epoch": 0.15289002842650912, + "grad_norm": 0.5782769322395325, + "learning_rate": 9.534221702546814e-05, + "loss": 1.9164, + "step": 2743 + }, + { + "epoch": 0.15294576667967225, + "grad_norm": 0.4970633387565613, + "learning_rate": 9.533846347624343e-05, + "loss": 1.7106, + "step": 2744 + }, + { + "epoch": 0.1530015049328354, + "grad_norm": 0.5226539373397827, + "learning_rate": 9.533470848914698e-05, + "loss": 1.6197, + "step": 2745 + }, + { + "epoch": 0.15305724318599856, + "grad_norm": 0.5139595866203308, + "learning_rate": 9.533095206429792e-05, + "loss": 1.7638, + "step": 2746 + }, + { + "epoch": 0.1531129814391617, + "grad_norm": 0.5007668733596802, + "learning_rate": 9.532719420181535e-05, + "loss": 1.5744, + "step": 2747 + }, + { + "epoch": 0.15316871969232485, + "grad_norm": 0.5414915084838867, + "learning_rate": 9.532343490181845e-05, + "loss": 1.748, + "step": 2748 + }, + { + "epoch": 0.153224457945488, + "grad_norm": 0.6250778436660767, + "learning_rate": 9.531967416442646e-05, + "loss": 1.8845, + "step": 2749 + }, + { + "epoch": 0.15328019619865113, + "grad_norm": 0.5204728245735168, + "learning_rate": 9.531591198975863e-05, + "loss": 1.7691, + "step": 2750 + }, + { + "epoch": 0.1533359344518143, + "grad_norm": 0.5631746649742126, + "learning_rate": 9.531214837793429e-05, + "loss": 1.6964, + "step": 2751 + }, + { + "epoch": 0.15339167270497742, + "grad_norm": 0.49102160334587097, + "learning_rate": 9.530838332907278e-05, + "loss": 1.6693, + "step": 2752 + }, + { + "epoch": 0.15344741095814057, + "grad_norm": 0.5530296564102173, + "learning_rate": 9.530461684329352e-05, + "loss": 1.932, + "step": 2753 + }, + { + "epoch": 0.15350314921130373, + "grad_norm": 0.4979936480522156, + "learning_rate": 9.530084892071596e-05, + "loss": 1.6084, + "step": 2754 + }, + { + "epoch": 0.15355888746446686, + "grad_norm": 0.5499585270881653, + "learning_rate": 9.52970795614596e-05, + "loss": 1.8431, + "step": 2755 + }, + { + "epoch": 0.15361462571763002, + "grad_norm": 0.5399606227874756, + "learning_rate": 9.529330876564398e-05, + "loss": 1.7747, + "step": 2756 + }, + { + "epoch": 0.15367036397079314, + "grad_norm": 0.5473707914352417, + "learning_rate": 9.528953653338867e-05, + "loss": 1.7633, + "step": 2757 + }, + { + "epoch": 0.1537261022239563, + "grad_norm": 0.5312392711639404, + "learning_rate": 9.528576286481332e-05, + "loss": 1.7155, + "step": 2758 + }, + { + "epoch": 0.15378184047711946, + "grad_norm": 0.5812214016914368, + "learning_rate": 9.52819877600376e-05, + "loss": 1.7427, + "step": 2759 + }, + { + "epoch": 0.1538375787302826, + "grad_norm": 0.5881000757217407, + "learning_rate": 9.527821121918126e-05, + "loss": 1.9338, + "step": 2760 + }, + { + "epoch": 0.15389331698344574, + "grad_norm": 0.4990249574184418, + "learning_rate": 9.527443324236403e-05, + "loss": 1.6865, + "step": 2761 + }, + { + "epoch": 0.15394905523660887, + "grad_norm": 0.5099406242370605, + "learning_rate": 9.527065382970576e-05, + "loss": 1.4843, + "step": 2762 + }, + { + "epoch": 0.15400479348977203, + "grad_norm": 0.555368959903717, + "learning_rate": 9.52668729813263e-05, + "loss": 1.7174, + "step": 2763 + }, + { + "epoch": 0.1540605317429352, + "grad_norm": 0.5384423136711121, + "learning_rate": 9.526309069734553e-05, + "loss": 1.8855, + "step": 2764 + }, + { + "epoch": 0.15411626999609832, + "grad_norm": 0.5143032073974609, + "learning_rate": 9.525930697788345e-05, + "loss": 1.7095, + "step": 2765 + }, + { + "epoch": 0.15417200824926147, + "grad_norm": 0.4992869794368744, + "learning_rate": 9.525552182306003e-05, + "loss": 1.5436, + "step": 2766 + }, + { + "epoch": 0.1542277465024246, + "grad_norm": 0.5122644901275635, + "learning_rate": 9.525173523299531e-05, + "loss": 1.8488, + "step": 2767 + }, + { + "epoch": 0.15428348475558776, + "grad_norm": 0.49027514457702637, + "learning_rate": 9.524794720780938e-05, + "loss": 1.6764, + "step": 2768 + }, + { + "epoch": 0.15433922300875091, + "grad_norm": 0.5170779824256897, + "learning_rate": 9.524415774762239e-05, + "loss": 1.7393, + "step": 2769 + }, + { + "epoch": 0.15439496126191404, + "grad_norm": 0.5226306319236755, + "learning_rate": 9.52403668525545e-05, + "loss": 1.6587, + "step": 2770 + }, + { + "epoch": 0.1544506995150772, + "grad_norm": 0.5146019458770752, + "learning_rate": 9.523657452272594e-05, + "loss": 1.5704, + "step": 2771 + }, + { + "epoch": 0.15450643776824036, + "grad_norm": 0.5141226649284363, + "learning_rate": 9.5232780758257e-05, + "loss": 1.6701, + "step": 2772 + }, + { + "epoch": 0.15456217602140349, + "grad_norm": 0.5106475353240967, + "learning_rate": 9.522898555926796e-05, + "loss": 1.7997, + "step": 2773 + }, + { + "epoch": 0.15461791427456664, + "grad_norm": 0.4933443069458008, + "learning_rate": 9.52251889258792e-05, + "loss": 1.4629, + "step": 2774 + }, + { + "epoch": 0.15467365252772977, + "grad_norm": 0.547154426574707, + "learning_rate": 9.522139085821113e-05, + "loss": 1.7481, + "step": 2775 + }, + { + "epoch": 0.15472939078089293, + "grad_norm": 0.5420608520507812, + "learning_rate": 9.521759135638422e-05, + "loss": 1.781, + "step": 2776 + }, + { + "epoch": 0.15478512903405608, + "grad_norm": 0.5556414723396301, + "learning_rate": 9.521379042051894e-05, + "loss": 1.5232, + "step": 2777 + }, + { + "epoch": 0.1548408672872192, + "grad_norm": 0.546357274055481, + "learning_rate": 9.520998805073584e-05, + "loss": 1.663, + "step": 2778 + }, + { + "epoch": 0.15489660554038237, + "grad_norm": 0.5195935964584351, + "learning_rate": 9.52061842471555e-05, + "loss": 1.632, + "step": 2779 + }, + { + "epoch": 0.1549523437935455, + "grad_norm": 0.5412857532501221, + "learning_rate": 9.520237900989858e-05, + "loss": 1.7983, + "step": 2780 + }, + { + "epoch": 0.15500808204670866, + "grad_norm": 0.5480208992958069, + "learning_rate": 9.519857233908574e-05, + "loss": 2.0205, + "step": 2781 + }, + { + "epoch": 0.1550638202998718, + "grad_norm": 0.5754556655883789, + "learning_rate": 9.519476423483771e-05, + "loss": 1.9992, + "step": 2782 + }, + { + "epoch": 0.15511955855303494, + "grad_norm": 0.560160756111145, + "learning_rate": 9.519095469727527e-05, + "loss": 1.8583, + "step": 2783 + }, + { + "epoch": 0.1551752968061981, + "grad_norm": 0.5757945775985718, + "learning_rate": 9.518714372651922e-05, + "loss": 1.9257, + "step": 2784 + }, + { + "epoch": 0.15523103505936123, + "grad_norm": 0.861761212348938, + "learning_rate": 9.518333132269043e-05, + "loss": 1.8291, + "step": 2785 + }, + { + "epoch": 0.15528677331252438, + "grad_norm": 0.5081753134727478, + "learning_rate": 9.517951748590983e-05, + "loss": 1.5859, + "step": 2786 + }, + { + "epoch": 0.15534251156568754, + "grad_norm": 0.5519318580627441, + "learning_rate": 9.517570221629833e-05, + "loss": 1.7556, + "step": 2787 + }, + { + "epoch": 0.15539824981885067, + "grad_norm": 0.5754350423812866, + "learning_rate": 9.517188551397695e-05, + "loss": 1.8201, + "step": 2788 + }, + { + "epoch": 0.15545398807201383, + "grad_norm": 0.5522143840789795, + "learning_rate": 9.516806737906674e-05, + "loss": 1.7392, + "step": 2789 + }, + { + "epoch": 0.15550972632517696, + "grad_norm": 0.5845313668251038, + "learning_rate": 9.516424781168877e-05, + "loss": 1.7216, + "step": 2790 + }, + { + "epoch": 0.1555654645783401, + "grad_norm": 0.57271808385849, + "learning_rate": 9.516042681196419e-05, + "loss": 1.561, + "step": 2791 + }, + { + "epoch": 0.15562120283150327, + "grad_norm": 0.5778896808624268, + "learning_rate": 9.515660438001417e-05, + "loss": 2.061, + "step": 2792 + }, + { + "epoch": 0.1556769410846664, + "grad_norm": 0.5089336633682251, + "learning_rate": 9.515278051595996e-05, + "loss": 1.5716, + "step": 2793 + }, + { + "epoch": 0.15573267933782955, + "grad_norm": 0.5174574255943298, + "learning_rate": 9.514895521992278e-05, + "loss": 1.5369, + "step": 2794 + }, + { + "epoch": 0.1557884175909927, + "grad_norm": 0.5474531650543213, + "learning_rate": 9.5145128492024e-05, + "loss": 1.9497, + "step": 2795 + }, + { + "epoch": 0.15584415584415584, + "grad_norm": 0.5397194027900696, + "learning_rate": 9.514130033238494e-05, + "loss": 1.7145, + "step": 2796 + }, + { + "epoch": 0.155899894097319, + "grad_norm": 0.5489051938056946, + "learning_rate": 9.513747074112705e-05, + "loss": 1.599, + "step": 2797 + }, + { + "epoch": 0.15595563235048213, + "grad_norm": 0.5342767834663391, + "learning_rate": 9.513363971837174e-05, + "loss": 1.6787, + "step": 2798 + }, + { + "epoch": 0.15601137060364528, + "grad_norm": 0.5298926830291748, + "learning_rate": 9.512980726424052e-05, + "loss": 1.6852, + "step": 2799 + }, + { + "epoch": 0.15606710885680844, + "grad_norm": 0.5444782376289368, + "learning_rate": 9.512597337885496e-05, + "loss": 1.6972, + "step": 2800 + }, + { + "epoch": 0.15612284710997157, + "grad_norm": 0.5541877150535583, + "learning_rate": 9.51221380623366e-05, + "loss": 1.6794, + "step": 2801 + }, + { + "epoch": 0.15617858536313473, + "grad_norm": 0.6140812039375305, + "learning_rate": 9.511830131480712e-05, + "loss": 1.6826, + "step": 2802 + }, + { + "epoch": 0.15623432361629785, + "grad_norm": 0.5042434930801392, + "learning_rate": 9.511446313638819e-05, + "loss": 1.6276, + "step": 2803 + }, + { + "epoch": 0.156290061869461, + "grad_norm": 0.5544094443321228, + "learning_rate": 9.51106235272015e-05, + "loss": 1.7685, + "step": 2804 + }, + { + "epoch": 0.15634580012262417, + "grad_norm": 0.49621298909187317, + "learning_rate": 9.510678248736887e-05, + "loss": 1.6194, + "step": 2805 + }, + { + "epoch": 0.1564015383757873, + "grad_norm": 0.5988842248916626, + "learning_rate": 9.510294001701208e-05, + "loss": 1.8121, + "step": 2806 + }, + { + "epoch": 0.15645727662895045, + "grad_norm": 0.5324400067329407, + "learning_rate": 9.509909611625298e-05, + "loss": 1.7674, + "step": 2807 + }, + { + "epoch": 0.15651301488211358, + "grad_norm": 0.5413124561309814, + "learning_rate": 9.509525078521353e-05, + "loss": 1.5738, + "step": 2808 + }, + { + "epoch": 0.15656875313527674, + "grad_norm": 0.5253452658653259, + "learning_rate": 9.509140402401563e-05, + "loss": 1.7126, + "step": 2809 + }, + { + "epoch": 0.1566244913884399, + "grad_norm": 0.5672581791877747, + "learning_rate": 9.508755583278131e-05, + "loss": 1.8056, + "step": 2810 + }, + { + "epoch": 0.15668022964160302, + "grad_norm": 0.49362093210220337, + "learning_rate": 9.508370621163259e-05, + "loss": 1.7569, + "step": 2811 + }, + { + "epoch": 0.15673596789476618, + "grad_norm": 0.5672383308410645, + "learning_rate": 9.507985516069154e-05, + "loss": 2.0115, + "step": 2812 + }, + { + "epoch": 0.1567917061479293, + "grad_norm": 0.576835036277771, + "learning_rate": 9.507600268008034e-05, + "loss": 2.0173, + "step": 2813 + }, + { + "epoch": 0.15684744440109247, + "grad_norm": 0.5514403581619263, + "learning_rate": 9.507214876992116e-05, + "loss": 1.711, + "step": 2814 + }, + { + "epoch": 0.15690318265425562, + "grad_norm": 0.5197775363922119, + "learning_rate": 9.506829343033619e-05, + "loss": 1.7613, + "step": 2815 + }, + { + "epoch": 0.15695892090741875, + "grad_norm": 0.5949315428733826, + "learning_rate": 9.506443666144773e-05, + "loss": 1.9146, + "step": 2816 + }, + { + "epoch": 0.1570146591605819, + "grad_norm": 0.5169588923454285, + "learning_rate": 9.506057846337808e-05, + "loss": 1.5925, + "step": 2817 + }, + { + "epoch": 0.15707039741374507, + "grad_norm": 0.5083977580070496, + "learning_rate": 9.505671883624959e-05, + "loss": 1.7269, + "step": 2818 + }, + { + "epoch": 0.1571261356669082, + "grad_norm": 0.5890203714370728, + "learning_rate": 9.505285778018469e-05, + "loss": 1.9239, + "step": 2819 + }, + { + "epoch": 0.15718187392007135, + "grad_norm": 0.5113581418991089, + "learning_rate": 9.504899529530582e-05, + "loss": 1.4883, + "step": 2820 + }, + { + "epoch": 0.15723761217323448, + "grad_norm": 0.5035502314567566, + "learning_rate": 9.504513138173547e-05, + "loss": 1.5673, + "step": 2821 + }, + { + "epoch": 0.15729335042639764, + "grad_norm": 0.5176184773445129, + "learning_rate": 9.504126603959618e-05, + "loss": 1.492, + "step": 2822 + }, + { + "epoch": 0.1573490886795608, + "grad_norm": 0.5595249533653259, + "learning_rate": 9.503739926901055e-05, + "loss": 1.916, + "step": 2823 + }, + { + "epoch": 0.15740482693272392, + "grad_norm": 0.5306408405303955, + "learning_rate": 9.50335310701012e-05, + "loss": 1.8255, + "step": 2824 + }, + { + "epoch": 0.15746056518588708, + "grad_norm": 0.5166139602661133, + "learning_rate": 9.50296614429908e-05, + "loss": 1.9614, + "step": 2825 + }, + { + "epoch": 0.1575163034390502, + "grad_norm": 0.5143607258796692, + "learning_rate": 9.502579038780207e-05, + "loss": 1.5858, + "step": 2826 + }, + { + "epoch": 0.15757204169221337, + "grad_norm": 0.5186240673065186, + "learning_rate": 9.50219179046578e-05, + "loss": 1.6746, + "step": 2827 + }, + { + "epoch": 0.15762777994537652, + "grad_norm": 0.5193765759468079, + "learning_rate": 9.50180439936808e-05, + "loss": 1.5768, + "step": 2828 + }, + { + "epoch": 0.15768351819853965, + "grad_norm": 0.5847373604774475, + "learning_rate": 9.501416865499391e-05, + "loss": 2.0199, + "step": 2829 + }, + { + "epoch": 0.1577392564517028, + "grad_norm": 0.5198137760162354, + "learning_rate": 9.501029188872004e-05, + "loss": 1.6215, + "step": 2830 + }, + { + "epoch": 0.15779499470486594, + "grad_norm": 0.5044419169425964, + "learning_rate": 9.500641369498214e-05, + "loss": 1.6355, + "step": 2831 + }, + { + "epoch": 0.1578507329580291, + "grad_norm": 0.6085756421089172, + "learning_rate": 9.50025340739032e-05, + "loss": 2.107, + "step": 2832 + }, + { + "epoch": 0.15790647121119225, + "grad_norm": 0.5201433300971985, + "learning_rate": 9.499865302560626e-05, + "loss": 1.5787, + "step": 2833 + }, + { + "epoch": 0.15796220946435538, + "grad_norm": 0.5003561973571777, + "learning_rate": 9.49947705502144e-05, + "loss": 1.6343, + "step": 2834 + }, + { + "epoch": 0.15801794771751854, + "grad_norm": 0.5781692862510681, + "learning_rate": 9.499088664785077e-05, + "loss": 1.8281, + "step": 2835 + }, + { + "epoch": 0.15807368597068167, + "grad_norm": 0.5135318636894226, + "learning_rate": 9.498700131863853e-05, + "loss": 1.7294, + "step": 2836 + }, + { + "epoch": 0.15812942422384482, + "grad_norm": 0.5199892520904541, + "learning_rate": 9.49831145627009e-05, + "loss": 1.6611, + "step": 2837 + }, + { + "epoch": 0.15818516247700798, + "grad_norm": 0.49417805671691895, + "learning_rate": 9.497922638016114e-05, + "loss": 1.4057, + "step": 2838 + }, + { + "epoch": 0.1582409007301711, + "grad_norm": 0.5626333951950073, + "learning_rate": 9.497533677114257e-05, + "loss": 1.7803, + "step": 2839 + }, + { + "epoch": 0.15829663898333426, + "grad_norm": 0.5851137042045593, + "learning_rate": 9.497144573576855e-05, + "loss": 1.7828, + "step": 2840 + }, + { + "epoch": 0.15835237723649742, + "grad_norm": 0.5782892107963562, + "learning_rate": 9.496755327416245e-05, + "loss": 1.9224, + "step": 2841 + }, + { + "epoch": 0.15840811548966055, + "grad_norm": 0.519010603427887, + "learning_rate": 9.496365938644775e-05, + "loss": 1.6932, + "step": 2842 + }, + { + "epoch": 0.1584638537428237, + "grad_norm": 0.588720440864563, + "learning_rate": 9.495976407274794e-05, + "loss": 1.7235, + "step": 2843 + }, + { + "epoch": 0.15851959199598684, + "grad_norm": 0.530684769153595, + "learning_rate": 9.495586733318654e-05, + "loss": 1.7368, + "step": 2844 + }, + { + "epoch": 0.15857533024915, + "grad_norm": 0.5223602652549744, + "learning_rate": 9.495196916788714e-05, + "loss": 1.5822, + "step": 2845 + }, + { + "epoch": 0.15863106850231315, + "grad_norm": 0.5282277464866638, + "learning_rate": 9.494806957697337e-05, + "loss": 1.7119, + "step": 2846 + }, + { + "epoch": 0.15868680675547628, + "grad_norm": 0.5861890912055969, + "learning_rate": 9.49441685605689e-05, + "loss": 1.7597, + "step": 2847 + }, + { + "epoch": 0.15874254500863944, + "grad_norm": 0.6072325110435486, + "learning_rate": 9.494026611879744e-05, + "loss": 2.1445, + "step": 2848 + }, + { + "epoch": 0.15879828326180256, + "grad_norm": 0.5348519086837769, + "learning_rate": 9.493636225178276e-05, + "loss": 1.5885, + "step": 2849 + }, + { + "epoch": 0.15885402151496572, + "grad_norm": 0.5133005976676941, + "learning_rate": 9.493245695964866e-05, + "loss": 1.7934, + "step": 2850 + }, + { + "epoch": 0.15890975976812888, + "grad_norm": 0.5469639897346497, + "learning_rate": 9.492855024251901e-05, + "loss": 1.7025, + "step": 2851 + }, + { + "epoch": 0.158965498021292, + "grad_norm": 0.5326577425003052, + "learning_rate": 9.492464210051771e-05, + "loss": 1.6258, + "step": 2852 + }, + { + "epoch": 0.15902123627445516, + "grad_norm": 0.6941805481910706, + "learning_rate": 9.492073253376865e-05, + "loss": 1.9171, + "step": 2853 + }, + { + "epoch": 0.1590769745276183, + "grad_norm": 0.5997553467750549, + "learning_rate": 9.491682154239589e-05, + "loss": 1.9891, + "step": 2854 + }, + { + "epoch": 0.15913271278078145, + "grad_norm": 0.5727251172065735, + "learning_rate": 9.491290912652344e-05, + "loss": 1.9522, + "step": 2855 + }, + { + "epoch": 0.1591884510339446, + "grad_norm": 0.5947685837745667, + "learning_rate": 9.490899528627536e-05, + "loss": 2.0334, + "step": 2856 + }, + { + "epoch": 0.15924418928710773, + "grad_norm": 0.5425087809562683, + "learning_rate": 9.490508002177579e-05, + "loss": 1.8532, + "step": 2857 + }, + { + "epoch": 0.1592999275402709, + "grad_norm": 0.5523599982261658, + "learning_rate": 9.490116333314889e-05, + "loss": 1.6041, + "step": 2858 + }, + { + "epoch": 0.15935566579343402, + "grad_norm": 0.5558710098266602, + "learning_rate": 9.489724522051888e-05, + "loss": 1.9383, + "step": 2859 + }, + { + "epoch": 0.15941140404659718, + "grad_norm": 0.5611505508422852, + "learning_rate": 9.489332568401004e-05, + "loss": 1.8919, + "step": 2860 + }, + { + "epoch": 0.15946714229976033, + "grad_norm": 0.5016571283340454, + "learning_rate": 9.488940472374663e-05, + "loss": 1.8347, + "step": 2861 + }, + { + "epoch": 0.15952288055292346, + "grad_norm": 0.5290272831916809, + "learning_rate": 9.488548233985305e-05, + "loss": 1.697, + "step": 2862 + }, + { + "epoch": 0.15957861880608662, + "grad_norm": 0.5488302707672119, + "learning_rate": 9.488155853245366e-05, + "loss": 1.9557, + "step": 2863 + }, + { + "epoch": 0.15963435705924978, + "grad_norm": 0.5422006845474243, + "learning_rate": 9.487763330167291e-05, + "loss": 1.6364, + "step": 2864 + }, + { + "epoch": 0.1596900953124129, + "grad_norm": 0.5467256307601929, + "learning_rate": 9.487370664763529e-05, + "loss": 1.7917, + "step": 2865 + }, + { + "epoch": 0.15974583356557606, + "grad_norm": 0.538063108921051, + "learning_rate": 9.486977857046532e-05, + "loss": 1.8552, + "step": 2866 + }, + { + "epoch": 0.1598015718187392, + "grad_norm": 0.5502356886863708, + "learning_rate": 9.486584907028758e-05, + "loss": 1.6089, + "step": 2867 + }, + { + "epoch": 0.15985731007190235, + "grad_norm": 0.526684582233429, + "learning_rate": 9.48619181472267e-05, + "loss": 1.5357, + "step": 2868 + }, + { + "epoch": 0.1599130483250655, + "grad_norm": 0.5427432656288147, + "learning_rate": 9.485798580140735e-05, + "loss": 1.7628, + "step": 2869 + }, + { + "epoch": 0.15996878657822863, + "grad_norm": 0.5465673208236694, + "learning_rate": 9.485405203295421e-05, + "loss": 1.6318, + "step": 2870 + }, + { + "epoch": 0.1600245248313918, + "grad_norm": 0.5261492729187012, + "learning_rate": 9.485011684199207e-05, + "loss": 1.6422, + "step": 2871 + }, + { + "epoch": 0.16008026308455492, + "grad_norm": 0.571042001247406, + "learning_rate": 9.484618022864571e-05, + "loss": 1.5466, + "step": 2872 + }, + { + "epoch": 0.16013600133771808, + "grad_norm": 0.5928837656974792, + "learning_rate": 9.484224219304e-05, + "loss": 2.0925, + "step": 2873 + }, + { + "epoch": 0.16019173959088123, + "grad_norm": 0.4875600337982178, + "learning_rate": 9.48383027352998e-05, + "loss": 1.6183, + "step": 2874 + }, + { + "epoch": 0.16024747784404436, + "grad_norm": 0.5074633955955505, + "learning_rate": 9.483436185555007e-05, + "loss": 1.5593, + "step": 2875 + }, + { + "epoch": 0.16030321609720752, + "grad_norm": 0.553817093372345, + "learning_rate": 9.483041955391578e-05, + "loss": 1.7093, + "step": 2876 + }, + { + "epoch": 0.16035895435037065, + "grad_norm": 0.5676888823509216, + "learning_rate": 9.482647583052196e-05, + "loss": 1.7555, + "step": 2877 + }, + { + "epoch": 0.1604146926035338, + "grad_norm": 0.5311009883880615, + "learning_rate": 9.48225306854937e-05, + "loss": 1.7709, + "step": 2878 + }, + { + "epoch": 0.16047043085669696, + "grad_norm": 0.5391182899475098, + "learning_rate": 9.481858411895608e-05, + "loss": 1.7296, + "step": 2879 + }, + { + "epoch": 0.1605261691098601, + "grad_norm": 0.5432226657867432, + "learning_rate": 9.481463613103429e-05, + "loss": 1.7808, + "step": 2880 + }, + { + "epoch": 0.16058190736302325, + "grad_norm": 0.5264506936073303, + "learning_rate": 9.481068672185353e-05, + "loss": 1.6362, + "step": 2881 + }, + { + "epoch": 0.16063764561618638, + "grad_norm": 0.5308744311332703, + "learning_rate": 9.480673589153904e-05, + "loss": 1.5913, + "step": 2882 + }, + { + "epoch": 0.16069338386934953, + "grad_norm": 0.4966695308685303, + "learning_rate": 9.480278364021614e-05, + "loss": 1.6744, + "step": 2883 + }, + { + "epoch": 0.1607491221225127, + "grad_norm": 0.5250310301780701, + "learning_rate": 9.479882996801017e-05, + "loss": 1.5185, + "step": 2884 + }, + { + "epoch": 0.16080486037567582, + "grad_norm": 0.5288892388343811, + "learning_rate": 9.479487487504649e-05, + "loss": 1.5259, + "step": 2885 + }, + { + "epoch": 0.16086059862883897, + "grad_norm": 0.5666532516479492, + "learning_rate": 9.479091836145057e-05, + "loss": 1.7626, + "step": 2886 + }, + { + "epoch": 0.16091633688200213, + "grad_norm": 0.5458130836486816, + "learning_rate": 9.478696042734785e-05, + "loss": 1.6936, + "step": 2887 + }, + { + "epoch": 0.16097207513516526, + "grad_norm": 0.5105459690093994, + "learning_rate": 9.478300107286389e-05, + "loss": 1.4811, + "step": 2888 + }, + { + "epoch": 0.16102781338832842, + "grad_norm": 0.5251494646072388, + "learning_rate": 9.477904029812422e-05, + "loss": 1.7184, + "step": 2889 + }, + { + "epoch": 0.16108355164149155, + "grad_norm": 0.5484756231307983, + "learning_rate": 9.477507810325448e-05, + "loss": 1.4053, + "step": 2890 + }, + { + "epoch": 0.1611392898946547, + "grad_norm": 0.5894975066184998, + "learning_rate": 9.477111448838031e-05, + "loss": 2.0827, + "step": 2891 + }, + { + "epoch": 0.16119502814781786, + "grad_norm": 0.5738565921783447, + "learning_rate": 9.476714945362745e-05, + "loss": 1.8864, + "step": 2892 + }, + { + "epoch": 0.161250766400981, + "grad_norm": 0.6212289333343506, + "learning_rate": 9.47631829991216e-05, + "loss": 1.9475, + "step": 2893 + }, + { + "epoch": 0.16130650465414414, + "grad_norm": 0.6506125330924988, + "learning_rate": 9.475921512498857e-05, + "loss": 1.9044, + "step": 2894 + }, + { + "epoch": 0.16136224290730727, + "grad_norm": 0.5559994578361511, + "learning_rate": 9.475524583135421e-05, + "loss": 1.5211, + "step": 2895 + }, + { + "epoch": 0.16141798116047043, + "grad_norm": 0.5860363841056824, + "learning_rate": 9.475127511834438e-05, + "loss": 1.7724, + "step": 2896 + }, + { + "epoch": 0.1614737194136336, + "grad_norm": 0.5559065341949463, + "learning_rate": 9.474730298608504e-05, + "loss": 1.8392, + "step": 2897 + }, + { + "epoch": 0.16152945766679672, + "grad_norm": 0.5526688694953918, + "learning_rate": 9.474332943470213e-05, + "loss": 1.7909, + "step": 2898 + }, + { + "epoch": 0.16158519591995987, + "grad_norm": 0.5582461357116699, + "learning_rate": 9.47393544643217e-05, + "loss": 1.9106, + "step": 2899 + }, + { + "epoch": 0.161640934173123, + "grad_norm": 0.5841467380523682, + "learning_rate": 9.473537807506977e-05, + "loss": 1.922, + "step": 2900 + }, + { + "epoch": 0.16169667242628616, + "grad_norm": 0.5061233043670654, + "learning_rate": 9.47314002670725e-05, + "loss": 1.5719, + "step": 2901 + }, + { + "epoch": 0.16175241067944932, + "grad_norm": 0.4959016442298889, + "learning_rate": 9.472742104045599e-05, + "loss": 1.6517, + "step": 2902 + }, + { + "epoch": 0.16180814893261244, + "grad_norm": 0.5075359344482422, + "learning_rate": 9.472344039534646e-05, + "loss": 1.7661, + "step": 2903 + }, + { + "epoch": 0.1618638871857756, + "grad_norm": 0.5135536193847656, + "learning_rate": 9.471945833187018e-05, + "loss": 1.6874, + "step": 2904 + }, + { + "epoch": 0.16191962543893873, + "grad_norm": 0.5618202090263367, + "learning_rate": 9.471547485015341e-05, + "loss": 1.6745, + "step": 2905 + }, + { + "epoch": 0.1619753636921019, + "grad_norm": 0.5325173139572144, + "learning_rate": 9.471148995032247e-05, + "loss": 1.7141, + "step": 2906 + }, + { + "epoch": 0.16203110194526504, + "grad_norm": 0.521827220916748, + "learning_rate": 9.470750363250378e-05, + "loss": 1.595, + "step": 2907 + }, + { + "epoch": 0.16208684019842817, + "grad_norm": 0.5489259362220764, + "learning_rate": 9.470351589682372e-05, + "loss": 1.8687, + "step": 2908 + }, + { + "epoch": 0.16214257845159133, + "grad_norm": 0.5823487043380737, + "learning_rate": 9.469952674340877e-05, + "loss": 1.8964, + "step": 2909 + }, + { + "epoch": 0.16219831670475449, + "grad_norm": 0.5378115773200989, + "learning_rate": 9.469553617238546e-05, + "loss": 1.6171, + "step": 2910 + }, + { + "epoch": 0.16225405495791762, + "grad_norm": 0.500411331653595, + "learning_rate": 9.469154418388034e-05, + "loss": 1.7592, + "step": 2911 + }, + { + "epoch": 0.16230979321108077, + "grad_norm": 0.49383944272994995, + "learning_rate": 9.468755077801999e-05, + "loss": 1.6709, + "step": 2912 + }, + { + "epoch": 0.1623655314642439, + "grad_norm": 0.5428176522254944, + "learning_rate": 9.468355595493109e-05, + "loss": 1.7304, + "step": 2913 + }, + { + "epoch": 0.16242126971740706, + "grad_norm": 0.537581205368042, + "learning_rate": 9.467955971474031e-05, + "loss": 1.7252, + "step": 2914 + }, + { + "epoch": 0.16247700797057021, + "grad_norm": 0.5622221231460571, + "learning_rate": 9.46755620575744e-05, + "loss": 1.7643, + "step": 2915 + }, + { + "epoch": 0.16253274622373334, + "grad_norm": 0.5474369525909424, + "learning_rate": 9.467156298356015e-05, + "loss": 1.7263, + "step": 2916 + }, + { + "epoch": 0.1625884844768965, + "grad_norm": 0.5429725646972656, + "learning_rate": 9.466756249282435e-05, + "loss": 1.7771, + "step": 2917 + }, + { + "epoch": 0.16264422273005963, + "grad_norm": 0.5385332107543945, + "learning_rate": 9.466356058549393e-05, + "loss": 1.7372, + "step": 2918 + }, + { + "epoch": 0.16269996098322279, + "grad_norm": 0.5135955214500427, + "learning_rate": 9.465955726169575e-05, + "loss": 1.7296, + "step": 2919 + }, + { + "epoch": 0.16275569923638594, + "grad_norm": 0.5584880709648132, + "learning_rate": 9.46555525215568e-05, + "loss": 1.7907, + "step": 2920 + }, + { + "epoch": 0.16281143748954907, + "grad_norm": 0.5609123706817627, + "learning_rate": 9.46515463652041e-05, + "loss": 1.8558, + "step": 2921 + }, + { + "epoch": 0.16286717574271223, + "grad_norm": 0.5887969732284546, + "learning_rate": 9.464753879276467e-05, + "loss": 1.8673, + "step": 2922 + }, + { + "epoch": 0.16292291399587536, + "grad_norm": 0.5207127332687378, + "learning_rate": 9.464352980436562e-05, + "loss": 1.8252, + "step": 2923 + }, + { + "epoch": 0.1629786522490385, + "grad_norm": 0.4879356622695923, + "learning_rate": 9.463951940013411e-05, + "loss": 1.564, + "step": 2924 + }, + { + "epoch": 0.16303439050220167, + "grad_norm": 0.5253145098686218, + "learning_rate": 9.46355075801973e-05, + "loss": 1.731, + "step": 2925 + }, + { + "epoch": 0.1630901287553648, + "grad_norm": 0.5216013789176941, + "learning_rate": 9.463149434468244e-05, + "loss": 1.7954, + "step": 2926 + }, + { + "epoch": 0.16314586700852796, + "grad_norm": 0.5162796974182129, + "learning_rate": 9.46274796937168e-05, + "loss": 1.6639, + "step": 2927 + }, + { + "epoch": 0.16320160526169109, + "grad_norm": 0.5164597630500793, + "learning_rate": 9.462346362742767e-05, + "loss": 1.5104, + "step": 2928 + }, + { + "epoch": 0.16325734351485424, + "grad_norm": 0.5458294153213501, + "learning_rate": 9.461944614594248e-05, + "loss": 1.7081, + "step": 2929 + }, + { + "epoch": 0.1633130817680174, + "grad_norm": 0.525484025478363, + "learning_rate": 9.461542724938859e-05, + "loss": 1.8709, + "step": 2930 + }, + { + "epoch": 0.16336882002118053, + "grad_norm": 0.5675646662712097, + "learning_rate": 9.461140693789349e-05, + "loss": 1.7861, + "step": 2931 + }, + { + "epoch": 0.16342455827434368, + "grad_norm": 0.5174034833908081, + "learning_rate": 9.460738521158466e-05, + "loss": 1.745, + "step": 2932 + }, + { + "epoch": 0.16348029652750684, + "grad_norm": 0.5687560439109802, + "learning_rate": 9.460336207058964e-05, + "loss": 1.8071, + "step": 2933 + }, + { + "epoch": 0.16353603478066997, + "grad_norm": 0.5177374482154846, + "learning_rate": 9.459933751503604e-05, + "loss": 1.7359, + "step": 2934 + }, + { + "epoch": 0.16359177303383313, + "grad_norm": 0.5742724537849426, + "learning_rate": 9.459531154505147e-05, + "loss": 1.6545, + "step": 2935 + }, + { + "epoch": 0.16364751128699626, + "grad_norm": 0.555439293384552, + "learning_rate": 9.459128416076365e-05, + "loss": 1.5666, + "step": 2936 + }, + { + "epoch": 0.1637032495401594, + "grad_norm": 0.5305073857307434, + "learning_rate": 9.458725536230027e-05, + "loss": 1.8546, + "step": 2937 + }, + { + "epoch": 0.16375898779332257, + "grad_norm": 0.517587423324585, + "learning_rate": 9.458322514978912e-05, + "loss": 1.6707, + "step": 2938 + }, + { + "epoch": 0.1638147260464857, + "grad_norm": 0.5396296977996826, + "learning_rate": 9.4579193523358e-05, + "loss": 1.6807, + "step": 2939 + }, + { + "epoch": 0.16387046429964885, + "grad_norm": 0.545603334903717, + "learning_rate": 9.457516048313478e-05, + "loss": 1.7966, + "step": 2940 + }, + { + "epoch": 0.16392620255281198, + "grad_norm": 0.5535080432891846, + "learning_rate": 9.457112602924735e-05, + "loss": 1.8103, + "step": 2941 + }, + { + "epoch": 0.16398194080597514, + "grad_norm": 0.5278719663619995, + "learning_rate": 9.456709016182368e-05, + "loss": 1.7992, + "step": 2942 + }, + { + "epoch": 0.1640376790591383, + "grad_norm": 0.5094558000564575, + "learning_rate": 9.456305288099174e-05, + "loss": 1.8232, + "step": 2943 + }, + { + "epoch": 0.16409341731230143, + "grad_norm": 0.5989511013031006, + "learning_rate": 9.45590141868796e-05, + "loss": 1.8106, + "step": 2944 + }, + { + "epoch": 0.16414915556546458, + "grad_norm": 0.5221716165542603, + "learning_rate": 9.455497407961532e-05, + "loss": 1.6316, + "step": 2945 + }, + { + "epoch": 0.1642048938186277, + "grad_norm": 0.4996791481971741, + "learning_rate": 9.455093255932704e-05, + "loss": 1.4846, + "step": 2946 + }, + { + "epoch": 0.16426063207179087, + "grad_norm": 0.5217500329017639, + "learning_rate": 9.454688962614293e-05, + "loss": 1.7717, + "step": 2947 + }, + { + "epoch": 0.16431637032495403, + "grad_norm": 0.5416474938392639, + "learning_rate": 9.45428452801912e-05, + "loss": 1.8829, + "step": 2948 + }, + { + "epoch": 0.16437210857811715, + "grad_norm": 0.5558078289031982, + "learning_rate": 9.453879952160013e-05, + "loss": 1.8933, + "step": 2949 + }, + { + "epoch": 0.1644278468312803, + "grad_norm": 0.5439289808273315, + "learning_rate": 9.4534752350498e-05, + "loss": 1.6009, + "step": 2950 + }, + { + "epoch": 0.16448358508444344, + "grad_norm": 0.5921631455421448, + "learning_rate": 9.45307037670132e-05, + "loss": 1.9932, + "step": 2951 + }, + { + "epoch": 0.1645393233376066, + "grad_norm": 0.5491567850112915, + "learning_rate": 9.452665377127409e-05, + "loss": 1.9729, + "step": 2952 + }, + { + "epoch": 0.16459506159076975, + "grad_norm": 0.6129978895187378, + "learning_rate": 9.452260236340915e-05, + "loss": 1.8995, + "step": 2953 + }, + { + "epoch": 0.16465079984393288, + "grad_norm": 0.6029583215713501, + "learning_rate": 9.451854954354684e-05, + "loss": 1.8313, + "step": 2954 + }, + { + "epoch": 0.16470653809709604, + "grad_norm": 0.5197410583496094, + "learning_rate": 9.451449531181572e-05, + "loss": 1.6307, + "step": 2955 + }, + { + "epoch": 0.1647622763502592, + "grad_norm": 0.5214848518371582, + "learning_rate": 9.451043966834431e-05, + "loss": 1.7253, + "step": 2956 + }, + { + "epoch": 0.16481801460342232, + "grad_norm": 0.48953381180763245, + "learning_rate": 9.450638261326128e-05, + "loss": 1.5122, + "step": 2957 + }, + { + "epoch": 0.16487375285658548, + "grad_norm": 0.5038783550262451, + "learning_rate": 9.450232414669528e-05, + "loss": 1.7602, + "step": 2958 + }, + { + "epoch": 0.1649294911097486, + "grad_norm": 0.5723398327827454, + "learning_rate": 9.449826426877504e-05, + "loss": 1.9841, + "step": 2959 + }, + { + "epoch": 0.16498522936291177, + "grad_norm": 0.5200619101524353, + "learning_rate": 9.44942029796293e-05, + "loss": 1.7965, + "step": 2960 + }, + { + "epoch": 0.16504096761607492, + "grad_norm": 0.6376471519470215, + "learning_rate": 9.449014027938685e-05, + "loss": 2.1267, + "step": 2961 + }, + { + "epoch": 0.16509670586923805, + "grad_norm": 0.5397600531578064, + "learning_rate": 9.448607616817655e-05, + "loss": 1.7952, + "step": 2962 + }, + { + "epoch": 0.1651524441224012, + "grad_norm": 0.5907739996910095, + "learning_rate": 9.448201064612728e-05, + "loss": 1.8026, + "step": 2963 + }, + { + "epoch": 0.16520818237556434, + "grad_norm": 0.5700837969779968, + "learning_rate": 9.447794371336799e-05, + "loss": 2.1377, + "step": 2964 + }, + { + "epoch": 0.1652639206287275, + "grad_norm": 0.5404232740402222, + "learning_rate": 9.447387537002765e-05, + "loss": 1.9586, + "step": 2965 + }, + { + "epoch": 0.16531965888189065, + "grad_norm": 0.5181935429573059, + "learning_rate": 9.446980561623527e-05, + "loss": 1.4828, + "step": 2966 + }, + { + "epoch": 0.16537539713505378, + "grad_norm": 0.6044127941131592, + "learning_rate": 9.446573445211994e-05, + "loss": 1.789, + "step": 2967 + }, + { + "epoch": 0.16543113538821694, + "grad_norm": 0.5353678464889526, + "learning_rate": 9.446166187781077e-05, + "loss": 1.709, + "step": 2968 + }, + { + "epoch": 0.16548687364138007, + "grad_norm": 0.5155282020568848, + "learning_rate": 9.445758789343691e-05, + "loss": 1.6335, + "step": 2969 + }, + { + "epoch": 0.16554261189454322, + "grad_norm": 0.5247118473052979, + "learning_rate": 9.445351249912757e-05, + "loss": 1.6666, + "step": 2970 + }, + { + "epoch": 0.16559835014770638, + "grad_norm": 0.5768206119537354, + "learning_rate": 9.4449435695012e-05, + "loss": 1.9109, + "step": 2971 + }, + { + "epoch": 0.1656540884008695, + "grad_norm": 0.5591040849685669, + "learning_rate": 9.444535748121949e-05, + "loss": 1.781, + "step": 2972 + }, + { + "epoch": 0.16570982665403267, + "grad_norm": 0.5098216533660889, + "learning_rate": 9.444127785787938e-05, + "loss": 1.7213, + "step": 2973 + }, + { + "epoch": 0.1657655649071958, + "grad_norm": 0.5072734355926514, + "learning_rate": 9.443719682512102e-05, + "loss": 1.8224, + "step": 2974 + }, + { + "epoch": 0.16582130316035895, + "grad_norm": 0.5172891020774841, + "learning_rate": 9.443311438307389e-05, + "loss": 1.8449, + "step": 2975 + }, + { + "epoch": 0.1658770414135221, + "grad_norm": 0.557597815990448, + "learning_rate": 9.442903053186743e-05, + "loss": 1.6679, + "step": 2976 + }, + { + "epoch": 0.16593277966668524, + "grad_norm": 0.518157422542572, + "learning_rate": 9.442494527163115e-05, + "loss": 1.6812, + "step": 2977 + }, + { + "epoch": 0.1659885179198484, + "grad_norm": 0.5476084351539612, + "learning_rate": 9.442085860249461e-05, + "loss": 1.7849, + "step": 2978 + }, + { + "epoch": 0.16604425617301155, + "grad_norm": 0.5458279252052307, + "learning_rate": 9.441677052458745e-05, + "loss": 1.8582, + "step": 2979 + }, + { + "epoch": 0.16609999442617468, + "grad_norm": 0.592612624168396, + "learning_rate": 9.441268103803928e-05, + "loss": 2.0226, + "step": 2980 + }, + { + "epoch": 0.16615573267933784, + "grad_norm": 0.5498427748680115, + "learning_rate": 9.440859014297982e-05, + "loss": 1.577, + "step": 2981 + }, + { + "epoch": 0.16621147093250097, + "grad_norm": 0.5673382878303528, + "learning_rate": 9.440449783953883e-05, + "loss": 1.7272, + "step": 2982 + }, + { + "epoch": 0.16626720918566412, + "grad_norm": 0.565617024898529, + "learning_rate": 9.440040412784603e-05, + "loss": 1.7481, + "step": 2983 + }, + { + "epoch": 0.16632294743882728, + "grad_norm": 0.6157540678977966, + "learning_rate": 9.439630900803129e-05, + "loss": 1.9244, + "step": 2984 + }, + { + "epoch": 0.1663786856919904, + "grad_norm": 0.4916851818561554, + "learning_rate": 9.439221248022447e-05, + "loss": 1.5845, + "step": 2985 + }, + { + "epoch": 0.16643442394515356, + "grad_norm": 0.573154091835022, + "learning_rate": 9.43881145445555e-05, + "loss": 1.8841, + "step": 2986 + }, + { + "epoch": 0.1664901621983167, + "grad_norm": 0.5438728332519531, + "learning_rate": 9.438401520115434e-05, + "loss": 1.7537, + "step": 2987 + }, + { + "epoch": 0.16654590045147985, + "grad_norm": 0.5793212652206421, + "learning_rate": 9.4379914450151e-05, + "loss": 1.9331, + "step": 2988 + }, + { + "epoch": 0.166601638704643, + "grad_norm": 0.5194965600967407, + "learning_rate": 9.437581229167551e-05, + "loss": 1.5948, + "step": 2989 + }, + { + "epoch": 0.16665737695780614, + "grad_norm": 0.5872880816459656, + "learning_rate": 9.4371708725858e-05, + "loss": 1.7629, + "step": 2990 + }, + { + "epoch": 0.1667131152109693, + "grad_norm": 0.519842803478241, + "learning_rate": 9.436760375282859e-05, + "loss": 1.766, + "step": 2991 + }, + { + "epoch": 0.16676885346413242, + "grad_norm": 0.5351104736328125, + "learning_rate": 9.436349737271745e-05, + "loss": 1.8319, + "step": 2992 + }, + { + "epoch": 0.16682459171729558, + "grad_norm": 0.5584455728530884, + "learning_rate": 9.435938958565487e-05, + "loss": 1.7975, + "step": 2993 + }, + { + "epoch": 0.16688032997045874, + "grad_norm": 0.4804225564002991, + "learning_rate": 9.435528039177105e-05, + "loss": 1.7058, + "step": 2994 + }, + { + "epoch": 0.16693606822362186, + "grad_norm": 0.5311334133148193, + "learning_rate": 9.435116979119635e-05, + "loss": 1.7305, + "step": 2995 + }, + { + "epoch": 0.16699180647678502, + "grad_norm": 0.5292813777923584, + "learning_rate": 9.434705778406114e-05, + "loss": 1.6901, + "step": 2996 + }, + { + "epoch": 0.16704754472994815, + "grad_norm": 0.5105124711990356, + "learning_rate": 9.434294437049582e-05, + "loss": 1.7462, + "step": 2997 + }, + { + "epoch": 0.1671032829831113, + "grad_norm": 0.5604652762413025, + "learning_rate": 9.433882955063084e-05, + "loss": 1.7997, + "step": 2998 + }, + { + "epoch": 0.16715902123627446, + "grad_norm": 0.555237889289856, + "learning_rate": 9.43347133245967e-05, + "loss": 1.923, + "step": 2999 + }, + { + "epoch": 0.1672147594894376, + "grad_norm": 0.5382326245307922, + "learning_rate": 9.433059569252394e-05, + "loss": 1.7263, + "step": 3000 + }, + { + "epoch": 0.16727049774260075, + "grad_norm": 0.6488143801689148, + "learning_rate": 9.432647665454315e-05, + "loss": 1.5881, + "step": 3001 + }, + { + "epoch": 0.1673262359957639, + "grad_norm": 0.55712890625, + "learning_rate": 9.432235621078497e-05, + "loss": 1.9409, + "step": 3002 + }, + { + "epoch": 0.16738197424892703, + "grad_norm": 0.5540611147880554, + "learning_rate": 9.431823436138005e-05, + "loss": 1.8471, + "step": 3003 + }, + { + "epoch": 0.1674377125020902, + "grad_norm": 0.5297248959541321, + "learning_rate": 9.431411110645915e-05, + "loss": 1.6844, + "step": 3004 + }, + { + "epoch": 0.16749345075525332, + "grad_norm": 0.5368382334709167, + "learning_rate": 9.4309986446153e-05, + "loss": 1.7333, + "step": 3005 + }, + { + "epoch": 0.16754918900841648, + "grad_norm": 0.5433456897735596, + "learning_rate": 9.430586038059244e-05, + "loss": 1.9837, + "step": 3006 + }, + { + "epoch": 0.16760492726157963, + "grad_norm": 0.5077199339866638, + "learning_rate": 9.430173290990829e-05, + "loss": 1.7391, + "step": 3007 + }, + { + "epoch": 0.16766066551474276, + "grad_norm": 0.49970632791519165, + "learning_rate": 9.429760403423148e-05, + "loss": 1.5325, + "step": 3008 + }, + { + "epoch": 0.16771640376790592, + "grad_norm": 0.5068593621253967, + "learning_rate": 9.429347375369295e-05, + "loss": 1.5849, + "step": 3009 + }, + { + "epoch": 0.16777214202106905, + "grad_norm": 0.5405229330062866, + "learning_rate": 9.428934206842365e-05, + "loss": 1.7995, + "step": 3010 + }, + { + "epoch": 0.1678278802742322, + "grad_norm": 0.5368816256523132, + "learning_rate": 9.428520897855469e-05, + "loss": 1.7941, + "step": 3011 + }, + { + "epoch": 0.16788361852739536, + "grad_norm": 0.5910351872444153, + "learning_rate": 9.428107448421708e-05, + "loss": 1.8987, + "step": 3012 + }, + { + "epoch": 0.1679393567805585, + "grad_norm": 0.5387074947357178, + "learning_rate": 9.427693858554196e-05, + "loss": 1.2377, + "step": 3013 + }, + { + "epoch": 0.16799509503372165, + "grad_norm": 0.5382748246192932, + "learning_rate": 9.42728012826605e-05, + "loss": 1.8915, + "step": 3014 + }, + { + "epoch": 0.16805083328688478, + "grad_norm": 0.5706035494804382, + "learning_rate": 9.426866257570391e-05, + "loss": 1.9298, + "step": 3015 + }, + { + "epoch": 0.16810657154004793, + "grad_norm": 0.517613410949707, + "learning_rate": 9.426452246480347e-05, + "loss": 1.6459, + "step": 3016 + }, + { + "epoch": 0.1681623097932111, + "grad_norm": 0.5248231291770935, + "learning_rate": 9.426038095009042e-05, + "loss": 1.8506, + "step": 3017 + }, + { + "epoch": 0.16821804804637422, + "grad_norm": 0.49280843138694763, + "learning_rate": 9.425623803169616e-05, + "loss": 1.5642, + "step": 3018 + }, + { + "epoch": 0.16827378629953738, + "grad_norm": 0.5404548048973083, + "learning_rate": 9.425209370975208e-05, + "loss": 1.7475, + "step": 3019 + }, + { + "epoch": 0.1683295245527005, + "grad_norm": 0.5196406245231628, + "learning_rate": 9.424794798438958e-05, + "loss": 1.8123, + "step": 3020 + }, + { + "epoch": 0.16838526280586366, + "grad_norm": 0.5767018795013428, + "learning_rate": 9.424380085574015e-05, + "loss": 1.9773, + "step": 3021 + }, + { + "epoch": 0.16844100105902682, + "grad_norm": 0.5589628219604492, + "learning_rate": 9.423965232393532e-05, + "loss": 1.8269, + "step": 3022 + }, + { + "epoch": 0.16849673931218995, + "grad_norm": 0.5162323117256165, + "learning_rate": 9.423550238910666e-05, + "loss": 1.7838, + "step": 3023 + }, + { + "epoch": 0.1685524775653531, + "grad_norm": 0.5301263332366943, + "learning_rate": 9.423135105138577e-05, + "loss": 1.7805, + "step": 3024 + }, + { + "epoch": 0.16860821581851626, + "grad_norm": 0.5383440256118774, + "learning_rate": 9.42271983109043e-05, + "loss": 1.8054, + "step": 3025 + }, + { + "epoch": 0.1686639540716794, + "grad_norm": 0.572410523891449, + "learning_rate": 9.422304416779397e-05, + "loss": 1.7666, + "step": 3026 + }, + { + "epoch": 0.16871969232484255, + "grad_norm": 0.5496928691864014, + "learning_rate": 9.421888862218651e-05, + "loss": 1.8725, + "step": 3027 + }, + { + "epoch": 0.16877543057800568, + "grad_norm": 0.5649563670158386, + "learning_rate": 9.421473167421373e-05, + "loss": 1.873, + "step": 3028 + }, + { + "epoch": 0.16883116883116883, + "grad_norm": 0.5560464262962341, + "learning_rate": 9.421057332400744e-05, + "loss": 1.6385, + "step": 3029 + }, + { + "epoch": 0.168886907084332, + "grad_norm": 0.5245364904403687, + "learning_rate": 9.420641357169954e-05, + "loss": 1.758, + "step": 3030 + }, + { + "epoch": 0.16894264533749512, + "grad_norm": 0.5251185297966003, + "learning_rate": 9.420225241742193e-05, + "loss": 1.829, + "step": 3031 + }, + { + "epoch": 0.16899838359065827, + "grad_norm": 0.5360503792762756, + "learning_rate": 9.419808986130661e-05, + "loss": 1.7447, + "step": 3032 + }, + { + "epoch": 0.1690541218438214, + "grad_norm": 0.579368531703949, + "learning_rate": 9.419392590348555e-05, + "loss": 1.7367, + "step": 3033 + }, + { + "epoch": 0.16910986009698456, + "grad_norm": 0.5943927764892578, + "learning_rate": 9.418976054409084e-05, + "loss": 1.8542, + "step": 3034 + }, + { + "epoch": 0.16916559835014772, + "grad_norm": 0.5310322642326355, + "learning_rate": 9.418559378325457e-05, + "loss": 1.5941, + "step": 3035 + }, + { + "epoch": 0.16922133660331085, + "grad_norm": 0.5201945304870605, + "learning_rate": 9.418142562110888e-05, + "loss": 1.6894, + "step": 3036 + }, + { + "epoch": 0.169277074856474, + "grad_norm": 0.49601128697395325, + "learning_rate": 9.417725605778598e-05, + "loss": 1.5647, + "step": 3037 + }, + { + "epoch": 0.16933281310963713, + "grad_norm": 0.5370486378669739, + "learning_rate": 9.417308509341806e-05, + "loss": 1.7843, + "step": 3038 + }, + { + "epoch": 0.1693885513628003, + "grad_norm": 0.5515000820159912, + "learning_rate": 9.416891272813747e-05, + "loss": 1.8156, + "step": 3039 + }, + { + "epoch": 0.16944428961596344, + "grad_norm": 0.5245648622512817, + "learning_rate": 9.416473896207645e-05, + "loss": 1.7029, + "step": 3040 + }, + { + "epoch": 0.16950002786912657, + "grad_norm": 0.6024215817451477, + "learning_rate": 9.416056379536744e-05, + "loss": 1.8892, + "step": 3041 + }, + { + "epoch": 0.16955576612228973, + "grad_norm": 0.5456023812294006, + "learning_rate": 9.415638722814279e-05, + "loss": 1.7344, + "step": 3042 + }, + { + "epoch": 0.16961150437545286, + "grad_norm": 0.47283026576042175, + "learning_rate": 9.415220926053501e-05, + "loss": 1.4281, + "step": 3043 + }, + { + "epoch": 0.16966724262861602, + "grad_norm": 0.5906921029090881, + "learning_rate": 9.414802989267657e-05, + "loss": 1.772, + "step": 3044 + }, + { + "epoch": 0.16972298088177917, + "grad_norm": 0.5549463033676147, + "learning_rate": 9.414384912470002e-05, + "loss": 1.6814, + "step": 3045 + }, + { + "epoch": 0.1697787191349423, + "grad_norm": 0.5007080435752869, + "learning_rate": 9.413966695673795e-05, + "loss": 1.7041, + "step": 3046 + }, + { + "epoch": 0.16983445738810546, + "grad_norm": 0.5527877807617188, + "learning_rate": 9.413548338892301e-05, + "loss": 1.8597, + "step": 3047 + }, + { + "epoch": 0.16989019564126862, + "grad_norm": 0.5755193829536438, + "learning_rate": 9.413129842138786e-05, + "loss": 2.115, + "step": 3048 + }, + { + "epoch": 0.16994593389443174, + "grad_norm": 0.5897433161735535, + "learning_rate": 9.412711205426521e-05, + "loss": 1.5559, + "step": 3049 + }, + { + "epoch": 0.1700016721475949, + "grad_norm": 0.5253439545631409, + "learning_rate": 9.412292428768787e-05, + "loss": 1.8423, + "step": 3050 + }, + { + "epoch": 0.17005741040075803, + "grad_norm": 0.5220539569854736, + "learning_rate": 9.411873512178862e-05, + "loss": 1.6792, + "step": 3051 + }, + { + "epoch": 0.1701131486539212, + "grad_norm": 0.5669887661933899, + "learning_rate": 9.41145445567003e-05, + "loss": 1.8432, + "step": 3052 + }, + { + "epoch": 0.17016888690708434, + "grad_norm": 0.5661007761955261, + "learning_rate": 9.411035259255585e-05, + "loss": 1.9316, + "step": 3053 + }, + { + "epoch": 0.17022462516024747, + "grad_norm": 0.5614895820617676, + "learning_rate": 9.41061592294882e-05, + "loss": 1.8668, + "step": 3054 + }, + { + "epoch": 0.17028036341341063, + "grad_norm": 0.541671872138977, + "learning_rate": 9.410196446763034e-05, + "loss": 1.9025, + "step": 3055 + }, + { + "epoch": 0.17033610166657376, + "grad_norm": 0.54454106092453, + "learning_rate": 9.409776830711528e-05, + "loss": 1.7351, + "step": 3056 + }, + { + "epoch": 0.17039183991973691, + "grad_norm": 0.581135094165802, + "learning_rate": 9.409357074807612e-05, + "loss": 2.0981, + "step": 3057 + }, + { + "epoch": 0.17044757817290007, + "grad_norm": 0.5024539232254028, + "learning_rate": 9.4089371790646e-05, + "loss": 1.74, + "step": 3058 + }, + { + "epoch": 0.1705033164260632, + "grad_norm": 0.527542233467102, + "learning_rate": 9.408517143495806e-05, + "loss": 1.7409, + "step": 3059 + }, + { + "epoch": 0.17055905467922636, + "grad_norm": 0.5976712107658386, + "learning_rate": 9.40809696811455e-05, + "loss": 1.6624, + "step": 3060 + }, + { + "epoch": 0.1706147929323895, + "grad_norm": 0.5328633785247803, + "learning_rate": 9.40767665293416e-05, + "loss": 1.7723, + "step": 3061 + }, + { + "epoch": 0.17067053118555264, + "grad_norm": 0.5550236701965332, + "learning_rate": 9.407256197967965e-05, + "loss": 1.771, + "step": 3062 + }, + { + "epoch": 0.1707262694387158, + "grad_norm": 0.5482365489006042, + "learning_rate": 9.4068356032293e-05, + "loss": 1.5427, + "step": 3063 + }, + { + "epoch": 0.17078200769187893, + "grad_norm": 0.5379420518875122, + "learning_rate": 9.406414868731502e-05, + "loss": 1.7884, + "step": 3064 + }, + { + "epoch": 0.17083774594504209, + "grad_norm": 0.5322206020355225, + "learning_rate": 9.405993994487917e-05, + "loss": 1.7756, + "step": 3065 + }, + { + "epoch": 0.17089348419820521, + "grad_norm": 0.5303000807762146, + "learning_rate": 9.40557298051189e-05, + "loss": 1.7589, + "step": 3066 + }, + { + "epoch": 0.17094922245136837, + "grad_norm": 0.5660407543182373, + "learning_rate": 9.405151826816776e-05, + "loss": 1.7427, + "step": 3067 + }, + { + "epoch": 0.17100496070453153, + "grad_norm": 0.5341696739196777, + "learning_rate": 9.404730533415929e-05, + "loss": 1.8757, + "step": 3068 + }, + { + "epoch": 0.17106069895769466, + "grad_norm": 0.533214271068573, + "learning_rate": 9.40430910032271e-05, + "loss": 1.8219, + "step": 3069 + }, + { + "epoch": 0.1711164372108578, + "grad_norm": 0.6056374311447144, + "learning_rate": 9.403887527550486e-05, + "loss": 1.9808, + "step": 3070 + }, + { + "epoch": 0.17117217546402097, + "grad_norm": 0.5189699530601501, + "learning_rate": 9.403465815112626e-05, + "loss": 1.6841, + "step": 3071 + }, + { + "epoch": 0.1712279137171841, + "grad_norm": 0.5255261659622192, + "learning_rate": 9.403043963022505e-05, + "loss": 1.5559, + "step": 3072 + }, + { + "epoch": 0.17128365197034726, + "grad_norm": 0.8432055115699768, + "learning_rate": 9.4026219712935e-05, + "loss": 1.8316, + "step": 3073 + }, + { + "epoch": 0.17133939022351038, + "grad_norm": 0.5276064276695251, + "learning_rate": 9.402199839938996e-05, + "loss": 1.678, + "step": 3074 + }, + { + "epoch": 0.17139512847667354, + "grad_norm": 0.5075768232345581, + "learning_rate": 9.401777568972379e-05, + "loss": 1.5931, + "step": 3075 + }, + { + "epoch": 0.1714508667298367, + "grad_norm": 0.5471227169036865, + "learning_rate": 9.401355158407042e-05, + "loss": 1.8761, + "step": 3076 + }, + { + "epoch": 0.17150660498299983, + "grad_norm": 0.5062270760536194, + "learning_rate": 9.400932608256381e-05, + "loss": 1.6682, + "step": 3077 + }, + { + "epoch": 0.17156234323616298, + "grad_norm": 0.5492522716522217, + "learning_rate": 9.400509918533798e-05, + "loss": 1.6889, + "step": 3078 + }, + { + "epoch": 0.1716180814893261, + "grad_norm": 0.5703136324882507, + "learning_rate": 9.400087089252695e-05, + "loss": 1.6925, + "step": 3079 + }, + { + "epoch": 0.17167381974248927, + "grad_norm": 0.5027966499328613, + "learning_rate": 9.399664120426484e-05, + "loss": 1.4425, + "step": 3080 + }, + { + "epoch": 0.17172955799565243, + "grad_norm": 0.558413028717041, + "learning_rate": 9.39924101206858e-05, + "loss": 1.6485, + "step": 3081 + }, + { + "epoch": 0.17178529624881556, + "grad_norm": 0.6047654151916504, + "learning_rate": 9.3988177641924e-05, + "loss": 1.835, + "step": 3082 + }, + { + "epoch": 0.1718410345019787, + "grad_norm": 0.5760734677314758, + "learning_rate": 9.398394376811368e-05, + "loss": 1.7104, + "step": 3083 + }, + { + "epoch": 0.17189677275514184, + "grad_norm": 0.5076540112495422, + "learning_rate": 9.397970849938911e-05, + "loss": 1.5808, + "step": 3084 + }, + { + "epoch": 0.171952511008305, + "grad_norm": 0.5645167827606201, + "learning_rate": 9.39754718358846e-05, + "loss": 1.771, + "step": 3085 + }, + { + "epoch": 0.17200824926146815, + "grad_norm": 0.5443428158760071, + "learning_rate": 9.397123377773451e-05, + "loss": 1.8713, + "step": 3086 + }, + { + "epoch": 0.17206398751463128, + "grad_norm": 0.513888418674469, + "learning_rate": 9.396699432507325e-05, + "loss": 1.5279, + "step": 3087 + }, + { + "epoch": 0.17211972576779444, + "grad_norm": 0.5408303141593933, + "learning_rate": 9.396275347803529e-05, + "loss": 1.8924, + "step": 3088 + }, + { + "epoch": 0.1721754640209576, + "grad_norm": 0.5284982323646545, + "learning_rate": 9.395851123675512e-05, + "loss": 1.7562, + "step": 3089 + }, + { + "epoch": 0.17223120227412073, + "grad_norm": 0.5364746451377869, + "learning_rate": 9.395426760136726e-05, + "loss": 1.599, + "step": 3090 + }, + { + "epoch": 0.17228694052728388, + "grad_norm": 0.5527182817459106, + "learning_rate": 9.39500225720063e-05, + "loss": 1.7657, + "step": 3091 + }, + { + "epoch": 0.172342678780447, + "grad_norm": 0.5294612646102905, + "learning_rate": 9.394577614880687e-05, + "loss": 1.684, + "step": 3092 + }, + { + "epoch": 0.17239841703361017, + "grad_norm": 0.5614673495292664, + "learning_rate": 9.394152833190364e-05, + "loss": 1.8619, + "step": 3093 + }, + { + "epoch": 0.17245415528677333, + "grad_norm": 0.5280752182006836, + "learning_rate": 9.393727912143134e-05, + "loss": 1.6454, + "step": 3094 + }, + { + "epoch": 0.17250989353993645, + "grad_norm": 0.5236919522285461, + "learning_rate": 9.39330285175247e-05, + "loss": 1.6498, + "step": 3095 + }, + { + "epoch": 0.1725656317930996, + "grad_norm": 0.5192380547523499, + "learning_rate": 9.392877652031855e-05, + "loss": 1.8345, + "step": 3096 + }, + { + "epoch": 0.17262137004626274, + "grad_norm": 0.5223302841186523, + "learning_rate": 9.392452312994773e-05, + "loss": 1.5056, + "step": 3097 + }, + { + "epoch": 0.1726771082994259, + "grad_norm": 0.5231219530105591, + "learning_rate": 9.392026834654714e-05, + "loss": 1.5868, + "step": 3098 + }, + { + "epoch": 0.17273284655258905, + "grad_norm": 0.5619219541549683, + "learning_rate": 9.39160121702517e-05, + "loss": 1.8988, + "step": 3099 + }, + { + "epoch": 0.17278858480575218, + "grad_norm": 0.5591604709625244, + "learning_rate": 9.391175460119642e-05, + "loss": 1.7228, + "step": 3100 + }, + { + "epoch": 0.17284432305891534, + "grad_norm": 0.5290101766586304, + "learning_rate": 9.39074956395163e-05, + "loss": 1.6436, + "step": 3101 + }, + { + "epoch": 0.17290006131207847, + "grad_norm": 0.5596829056739807, + "learning_rate": 9.390323528534641e-05, + "loss": 1.498, + "step": 3102 + }, + { + "epoch": 0.17295579956524162, + "grad_norm": 0.5178213119506836, + "learning_rate": 9.389897353882188e-05, + "loss": 1.6834, + "step": 3103 + }, + { + "epoch": 0.17301153781840478, + "grad_norm": 0.46845757961273193, + "learning_rate": 9.389471040007784e-05, + "loss": 1.4012, + "step": 3104 + }, + { + "epoch": 0.1730672760715679, + "grad_norm": 0.5671401619911194, + "learning_rate": 9.389044586924953e-05, + "loss": 1.7005, + "step": 3105 + }, + { + "epoch": 0.17312301432473107, + "grad_norm": 0.5250539779663086, + "learning_rate": 9.388617994647218e-05, + "loss": 1.6934, + "step": 3106 + }, + { + "epoch": 0.1731787525778942, + "grad_norm": 0.5091891884803772, + "learning_rate": 9.388191263188107e-05, + "loss": 1.5041, + "step": 3107 + }, + { + "epoch": 0.17323449083105735, + "grad_norm": 0.5298328995704651, + "learning_rate": 9.387764392561153e-05, + "loss": 1.6184, + "step": 3108 + }, + { + "epoch": 0.1732902290842205, + "grad_norm": 0.5605019330978394, + "learning_rate": 9.387337382779894e-05, + "loss": 1.8302, + "step": 3109 + }, + { + "epoch": 0.17334596733738364, + "grad_norm": 0.554153561592102, + "learning_rate": 9.386910233857875e-05, + "loss": 1.6565, + "step": 3110 + }, + { + "epoch": 0.1734017055905468, + "grad_norm": 0.5952569246292114, + "learning_rate": 9.386482945808641e-05, + "loss": 1.5957, + "step": 3111 + }, + { + "epoch": 0.17345744384370995, + "grad_norm": 0.6842632293701172, + "learning_rate": 9.386055518645742e-05, + "loss": 1.7147, + "step": 3112 + }, + { + "epoch": 0.17351318209687308, + "grad_norm": 0.6011619567871094, + "learning_rate": 9.385627952382736e-05, + "loss": 2.0401, + "step": 3113 + }, + { + "epoch": 0.17356892035003624, + "grad_norm": 0.5976441502571106, + "learning_rate": 9.38520024703318e-05, + "loss": 1.9242, + "step": 3114 + }, + { + "epoch": 0.17362465860319937, + "grad_norm": 0.4991317689418793, + "learning_rate": 9.38477240261064e-05, + "loss": 1.689, + "step": 3115 + }, + { + "epoch": 0.17368039685636252, + "grad_norm": 0.5823774337768555, + "learning_rate": 9.384344419128684e-05, + "loss": 1.7896, + "step": 3116 + }, + { + "epoch": 0.17373613510952568, + "grad_norm": 0.584511399269104, + "learning_rate": 9.383916296600886e-05, + "loss": 1.7828, + "step": 3117 + }, + { + "epoch": 0.1737918733626888, + "grad_norm": 0.5839495062828064, + "learning_rate": 9.383488035040821e-05, + "loss": 1.9487, + "step": 3118 + }, + { + "epoch": 0.17384761161585197, + "grad_norm": 0.5381820201873779, + "learning_rate": 9.383059634462077e-05, + "loss": 1.6792, + "step": 3119 + }, + { + "epoch": 0.1739033498690151, + "grad_norm": 0.5147883892059326, + "learning_rate": 9.382631094878234e-05, + "loss": 1.6627, + "step": 3120 + }, + { + "epoch": 0.17395908812217825, + "grad_norm": 0.6467978358268738, + "learning_rate": 9.382202416302885e-05, + "loss": 1.7446, + "step": 3121 + }, + { + "epoch": 0.1740148263753414, + "grad_norm": 0.5035672187805176, + "learning_rate": 9.381773598749626e-05, + "loss": 1.6078, + "step": 3122 + }, + { + "epoch": 0.17407056462850454, + "grad_norm": 0.5837130546569824, + "learning_rate": 9.381344642232056e-05, + "loss": 1.792, + "step": 3123 + }, + { + "epoch": 0.1741263028816677, + "grad_norm": 0.5331088900566101, + "learning_rate": 9.380915546763778e-05, + "loss": 1.788, + "step": 3124 + }, + { + "epoch": 0.17418204113483082, + "grad_norm": 0.5427802801132202, + "learning_rate": 9.380486312358402e-05, + "loss": 1.8515, + "step": 3125 + }, + { + "epoch": 0.17423777938799398, + "grad_norm": 0.4916117489337921, + "learning_rate": 9.380056939029541e-05, + "loss": 1.5184, + "step": 3126 + }, + { + "epoch": 0.17429351764115714, + "grad_norm": 0.559158980846405, + "learning_rate": 9.379627426790812e-05, + "loss": 1.8659, + "step": 3127 + }, + { + "epoch": 0.17434925589432027, + "grad_norm": 0.5941457152366638, + "learning_rate": 9.379197775655833e-05, + "loss": 1.7891, + "step": 3128 + }, + { + "epoch": 0.17440499414748342, + "grad_norm": 0.4794413447380066, + "learning_rate": 9.378767985638235e-05, + "loss": 1.4975, + "step": 3129 + }, + { + "epoch": 0.17446073240064655, + "grad_norm": 0.5934321284294128, + "learning_rate": 9.378338056751647e-05, + "loss": 1.9019, + "step": 3130 + }, + { + "epoch": 0.1745164706538097, + "grad_norm": 0.5290476679801941, + "learning_rate": 9.377907989009702e-05, + "loss": 1.7563, + "step": 3131 + }, + { + "epoch": 0.17457220890697286, + "grad_norm": 0.5909081101417542, + "learning_rate": 9.37747778242604e-05, + "loss": 2.009, + "step": 3132 + }, + { + "epoch": 0.174627947160136, + "grad_norm": 0.5411567687988281, + "learning_rate": 9.377047437014308e-05, + "loss": 1.8264, + "step": 3133 + }, + { + "epoch": 0.17468368541329915, + "grad_norm": 0.5046765208244324, + "learning_rate": 9.376616952788149e-05, + "loss": 1.6131, + "step": 3134 + }, + { + "epoch": 0.1747394236664623, + "grad_norm": 0.528154194355011, + "learning_rate": 9.376186329761219e-05, + "loss": 1.7159, + "step": 3135 + }, + { + "epoch": 0.17479516191962544, + "grad_norm": 0.5536481142044067, + "learning_rate": 9.375755567947173e-05, + "loss": 1.5203, + "step": 3136 + }, + { + "epoch": 0.1748509001727886, + "grad_norm": 0.5683685541152954, + "learning_rate": 9.375324667359673e-05, + "loss": 1.7154, + "step": 3137 + }, + { + "epoch": 0.17490663842595172, + "grad_norm": 0.4969169497489929, + "learning_rate": 9.374893628012384e-05, + "loss": 1.7277, + "step": 3138 + }, + { + "epoch": 0.17496237667911488, + "grad_norm": 0.548058032989502, + "learning_rate": 9.374462449918976e-05, + "loss": 1.7931, + "step": 3139 + }, + { + "epoch": 0.17501811493227803, + "grad_norm": 0.5391299724578857, + "learning_rate": 9.374031133093124e-05, + "loss": 1.8076, + "step": 3140 + }, + { + "epoch": 0.17507385318544116, + "grad_norm": 0.5356679558753967, + "learning_rate": 9.373599677548508e-05, + "loss": 1.7212, + "step": 3141 + }, + { + "epoch": 0.17512959143860432, + "grad_norm": 0.5841724276542664, + "learning_rate": 9.373168083298809e-05, + "loss": 1.9175, + "step": 3142 + }, + { + "epoch": 0.17518532969176745, + "grad_norm": 0.5568740963935852, + "learning_rate": 9.372736350357717e-05, + "loss": 1.842, + "step": 3143 + }, + { + "epoch": 0.1752410679449306, + "grad_norm": 0.5539031028747559, + "learning_rate": 9.372304478738922e-05, + "loss": 1.8881, + "step": 3144 + }, + { + "epoch": 0.17529680619809376, + "grad_norm": 0.5519389510154724, + "learning_rate": 9.371872468456122e-05, + "loss": 1.7381, + "step": 3145 + }, + { + "epoch": 0.1753525444512569, + "grad_norm": 0.5324805378913879, + "learning_rate": 9.371440319523016e-05, + "loss": 1.745, + "step": 3146 + }, + { + "epoch": 0.17540828270442005, + "grad_norm": 0.5449910759925842, + "learning_rate": 9.37100803195331e-05, + "loss": 1.8071, + "step": 3147 + }, + { + "epoch": 0.17546402095758318, + "grad_norm": 0.5846375823020935, + "learning_rate": 9.370575605760716e-05, + "loss": 1.8659, + "step": 3148 + }, + { + "epoch": 0.17551975921074633, + "grad_norm": 0.4958127737045288, + "learning_rate": 9.370143040958943e-05, + "loss": 1.5791, + "step": 3149 + }, + { + "epoch": 0.1755754974639095, + "grad_norm": 0.5119603276252747, + "learning_rate": 9.369710337561714e-05, + "loss": 1.7657, + "step": 3150 + }, + { + "epoch": 0.17563123571707262, + "grad_norm": 0.5698620080947876, + "learning_rate": 9.36927749558275e-05, + "loss": 2.0541, + "step": 3151 + }, + { + "epoch": 0.17568697397023578, + "grad_norm": 0.5704925656318665, + "learning_rate": 9.368844515035779e-05, + "loss": 1.762, + "step": 3152 + }, + { + "epoch": 0.1757427122233989, + "grad_norm": 0.5676224231719971, + "learning_rate": 9.368411395934533e-05, + "loss": 1.5928, + "step": 3153 + }, + { + "epoch": 0.17579845047656206, + "grad_norm": 0.5878868699073792, + "learning_rate": 9.367978138292747e-05, + "loss": 1.9292, + "step": 3154 + }, + { + "epoch": 0.17585418872972522, + "grad_norm": 0.5323675274848938, + "learning_rate": 9.36754474212416e-05, + "loss": 1.8832, + "step": 3155 + }, + { + "epoch": 0.17590992698288835, + "grad_norm": 0.49846091866493225, + "learning_rate": 9.36711120744252e-05, + "loss": 1.4679, + "step": 3156 + }, + { + "epoch": 0.1759656652360515, + "grad_norm": 0.5483475923538208, + "learning_rate": 9.366677534261572e-05, + "loss": 1.7744, + "step": 3157 + }, + { + "epoch": 0.17602140348921466, + "grad_norm": 0.5628114938735962, + "learning_rate": 9.366243722595074e-05, + "loss": 1.8169, + "step": 3158 + }, + { + "epoch": 0.1760771417423778, + "grad_norm": 0.5500927567481995, + "learning_rate": 9.365809772456782e-05, + "loss": 1.8714, + "step": 3159 + }, + { + "epoch": 0.17613287999554095, + "grad_norm": 0.5269673466682434, + "learning_rate": 9.365375683860458e-05, + "loss": 1.797, + "step": 3160 + }, + { + "epoch": 0.17618861824870408, + "grad_norm": 0.5542075037956238, + "learning_rate": 9.36494145681987e-05, + "loss": 1.8027, + "step": 3161 + }, + { + "epoch": 0.17624435650186723, + "grad_norm": 0.5421326756477356, + "learning_rate": 9.364507091348788e-05, + "loss": 1.7254, + "step": 3162 + }, + { + "epoch": 0.1763000947550304, + "grad_norm": 0.4979914128780365, + "learning_rate": 9.364072587460988e-05, + "loss": 1.7505, + "step": 3163 + }, + { + "epoch": 0.17635583300819352, + "grad_norm": 0.5363655686378479, + "learning_rate": 9.363637945170249e-05, + "loss": 1.7651, + "step": 3164 + }, + { + "epoch": 0.17641157126135668, + "grad_norm": 0.5159875750541687, + "learning_rate": 9.363203164490356e-05, + "loss": 1.7096, + "step": 3165 + }, + { + "epoch": 0.1764673095145198, + "grad_norm": 0.590908408164978, + "learning_rate": 9.362768245435098e-05, + "loss": 2.0557, + "step": 3166 + }, + { + "epoch": 0.17652304776768296, + "grad_norm": 0.5476133823394775, + "learning_rate": 9.362333188018269e-05, + "loss": 1.6362, + "step": 3167 + }, + { + "epoch": 0.17657878602084612, + "grad_norm": 0.5187797546386719, + "learning_rate": 9.361897992253665e-05, + "loss": 1.6019, + "step": 3168 + }, + { + "epoch": 0.17663452427400925, + "grad_norm": 0.5152827501296997, + "learning_rate": 9.361462658155089e-05, + "loss": 1.7042, + "step": 3169 + }, + { + "epoch": 0.1766902625271724, + "grad_norm": 0.5961150527000427, + "learning_rate": 9.361027185736346e-05, + "loss": 1.7224, + "step": 3170 + }, + { + "epoch": 0.17674600078033553, + "grad_norm": 0.5234068632125854, + "learning_rate": 9.360591575011245e-05, + "loss": 1.6534, + "step": 3171 + }, + { + "epoch": 0.1768017390334987, + "grad_norm": 0.5417289137840271, + "learning_rate": 9.360155825993607e-05, + "loss": 1.8964, + "step": 3172 + }, + { + "epoch": 0.17685747728666185, + "grad_norm": 0.535892903804779, + "learning_rate": 9.359719938697246e-05, + "loss": 1.7262, + "step": 3173 + }, + { + "epoch": 0.17691321553982498, + "grad_norm": 0.5440612435340881, + "learning_rate": 9.359283913135988e-05, + "loss": 1.7775, + "step": 3174 + }, + { + "epoch": 0.17696895379298813, + "grad_norm": 0.6108183264732361, + "learning_rate": 9.358847749323659e-05, + "loss": 1.9756, + "step": 3175 + }, + { + "epoch": 0.17702469204615126, + "grad_norm": 0.5500672459602356, + "learning_rate": 9.358411447274094e-05, + "loss": 1.7427, + "step": 3176 + }, + { + "epoch": 0.17708043029931442, + "grad_norm": 0.5370178818702698, + "learning_rate": 9.357975007001129e-05, + "loss": 1.8076, + "step": 3177 + }, + { + "epoch": 0.17713616855247757, + "grad_norm": 0.5063850283622742, + "learning_rate": 9.357538428518607e-05, + "loss": 1.6826, + "step": 3178 + }, + { + "epoch": 0.1771919068056407, + "grad_norm": 0.5165611505508423, + "learning_rate": 9.357101711840372e-05, + "loss": 1.6545, + "step": 3179 + }, + { + "epoch": 0.17724764505880386, + "grad_norm": 0.521656334400177, + "learning_rate": 9.356664856980273e-05, + "loss": 1.4337, + "step": 3180 + }, + { + "epoch": 0.17730338331196702, + "grad_norm": 0.527341902256012, + "learning_rate": 9.356227863952168e-05, + "loss": 1.7241, + "step": 3181 + }, + { + "epoch": 0.17735912156513015, + "grad_norm": 0.494210422039032, + "learning_rate": 9.355790732769911e-05, + "loss": 1.5474, + "step": 3182 + }, + { + "epoch": 0.1774148598182933, + "grad_norm": 0.5171836614608765, + "learning_rate": 9.35535346344737e-05, + "loss": 1.5795, + "step": 3183 + }, + { + "epoch": 0.17747059807145643, + "grad_norm": 0.5571975111961365, + "learning_rate": 9.354916055998409e-05, + "loss": 1.8093, + "step": 3184 + }, + { + "epoch": 0.1775263363246196, + "grad_norm": 0.5996416807174683, + "learning_rate": 9.354478510436902e-05, + "loss": 2.0041, + "step": 3185 + }, + { + "epoch": 0.17758207457778274, + "grad_norm": 0.4972604811191559, + "learning_rate": 9.354040826776727e-05, + "loss": 1.7329, + "step": 3186 + }, + { + "epoch": 0.17763781283094587, + "grad_norm": 0.5599552392959595, + "learning_rate": 9.35360300503176e-05, + "loss": 1.7857, + "step": 3187 + }, + { + "epoch": 0.17769355108410903, + "grad_norm": 0.5476880669593811, + "learning_rate": 9.35316504521589e-05, + "loss": 1.7757, + "step": 3188 + }, + { + "epoch": 0.17774928933727216, + "grad_norm": 0.5362497568130493, + "learning_rate": 9.352726947343006e-05, + "loss": 1.7656, + "step": 3189 + }, + { + "epoch": 0.17780502759043532, + "grad_norm": 0.5269262194633484, + "learning_rate": 9.352288711427001e-05, + "loss": 1.7716, + "step": 3190 + }, + { + "epoch": 0.17786076584359847, + "grad_norm": 0.5733572244644165, + "learning_rate": 9.351850337481773e-05, + "loss": 1.7623, + "step": 3191 + }, + { + "epoch": 0.1779165040967616, + "grad_norm": 0.5491241812705994, + "learning_rate": 9.351411825521228e-05, + "loss": 1.7835, + "step": 3192 + }, + { + "epoch": 0.17797224234992476, + "grad_norm": 0.5553460121154785, + "learning_rate": 9.350973175559267e-05, + "loss": 1.9064, + "step": 3193 + }, + { + "epoch": 0.1780279806030879, + "grad_norm": 0.5257185101509094, + "learning_rate": 9.350534387609807e-05, + "loss": 1.7245, + "step": 3194 + }, + { + "epoch": 0.17808371885625104, + "grad_norm": 0.5201014876365662, + "learning_rate": 9.35009546168676e-05, + "loss": 1.6991, + "step": 3195 + }, + { + "epoch": 0.1781394571094142, + "grad_norm": 0.5365905165672302, + "learning_rate": 9.34965639780405e-05, + "loss": 1.747, + "step": 3196 + }, + { + "epoch": 0.17819519536257733, + "grad_norm": 0.5471792221069336, + "learning_rate": 9.349217195975598e-05, + "loss": 1.8114, + "step": 3197 + }, + { + "epoch": 0.1782509336157405, + "grad_norm": 0.5407313704490662, + "learning_rate": 9.348777856215334e-05, + "loss": 1.7719, + "step": 3198 + }, + { + "epoch": 0.17830667186890362, + "grad_norm": 0.5418484807014465, + "learning_rate": 9.348338378537192e-05, + "loss": 1.7989, + "step": 3199 + }, + { + "epoch": 0.17836241012206677, + "grad_norm": 0.5235376954078674, + "learning_rate": 9.347898762955109e-05, + "loss": 1.5998, + "step": 3200 + }, + { + "epoch": 0.17841814837522993, + "grad_norm": 0.5582895874977112, + "learning_rate": 9.347459009483028e-05, + "loss": 1.7352, + "step": 3201 + }, + { + "epoch": 0.17847388662839306, + "grad_norm": 0.5512102246284485, + "learning_rate": 9.347019118134893e-05, + "loss": 1.8595, + "step": 3202 + }, + { + "epoch": 0.17852962488155621, + "grad_norm": 0.5874474048614502, + "learning_rate": 9.346579088924658e-05, + "loss": 1.8312, + "step": 3203 + }, + { + "epoch": 0.17858536313471937, + "grad_norm": 0.5523637533187866, + "learning_rate": 9.346138921866276e-05, + "loss": 1.9124, + "step": 3204 + }, + { + "epoch": 0.1786411013878825, + "grad_norm": 0.5245184898376465, + "learning_rate": 9.345698616973707e-05, + "loss": 1.8279, + "step": 3205 + }, + { + "epoch": 0.17869683964104566, + "grad_norm": 0.5538264513015747, + "learning_rate": 9.345258174260915e-05, + "loss": 1.8218, + "step": 3206 + }, + { + "epoch": 0.1787525778942088, + "grad_norm": 0.5474498271942139, + "learning_rate": 9.344817593741868e-05, + "loss": 1.6772, + "step": 3207 + }, + { + "epoch": 0.17880831614737194, + "grad_norm": 0.5437337756156921, + "learning_rate": 9.344376875430539e-05, + "loss": 1.8402, + "step": 3208 + }, + { + "epoch": 0.1788640544005351, + "grad_norm": 0.6069798469543457, + "learning_rate": 9.343936019340906e-05, + "loss": 2.0245, + "step": 3209 + }, + { + "epoch": 0.17891979265369823, + "grad_norm": 0.5451731085777283, + "learning_rate": 9.343495025486948e-05, + "loss": 1.7243, + "step": 3210 + }, + { + "epoch": 0.17897553090686139, + "grad_norm": 0.5307853817939758, + "learning_rate": 9.343053893882654e-05, + "loss": 1.8062, + "step": 3211 + }, + { + "epoch": 0.17903126916002451, + "grad_norm": 0.5642760992050171, + "learning_rate": 9.34261262454201e-05, + "loss": 1.9111, + "step": 3212 + }, + { + "epoch": 0.17908700741318767, + "grad_norm": 0.5641029477119446, + "learning_rate": 9.342171217479014e-05, + "loss": 1.892, + "step": 3213 + }, + { + "epoch": 0.17914274566635083, + "grad_norm": 0.5118708610534668, + "learning_rate": 9.341729672707664e-05, + "loss": 1.7303, + "step": 3214 + }, + { + "epoch": 0.17919848391951396, + "grad_norm": 0.5048193335533142, + "learning_rate": 9.341287990241962e-05, + "loss": 1.5011, + "step": 3215 + }, + { + "epoch": 0.1792542221726771, + "grad_norm": 0.5508407950401306, + "learning_rate": 9.340846170095917e-05, + "loss": 1.8355, + "step": 3216 + }, + { + "epoch": 0.17930996042584024, + "grad_norm": 0.5779476165771484, + "learning_rate": 9.34040421228354e-05, + "loss": 1.8892, + "step": 3217 + }, + { + "epoch": 0.1793656986790034, + "grad_norm": 0.5211353898048401, + "learning_rate": 9.339962116818848e-05, + "loss": 1.6359, + "step": 3218 + }, + { + "epoch": 0.17942143693216656, + "grad_norm": 0.5479955077171326, + "learning_rate": 9.339519883715862e-05, + "loss": 1.7594, + "step": 3219 + }, + { + "epoch": 0.17947717518532968, + "grad_norm": 0.49651384353637695, + "learning_rate": 9.339077512988606e-05, + "loss": 1.5873, + "step": 3220 + }, + { + "epoch": 0.17953291343849284, + "grad_norm": 0.569810152053833, + "learning_rate": 9.338635004651108e-05, + "loss": 1.6675, + "step": 3221 + }, + { + "epoch": 0.17958865169165597, + "grad_norm": 0.5437332987785339, + "learning_rate": 9.338192358717406e-05, + "loss": 1.8268, + "step": 3222 + }, + { + "epoch": 0.17964438994481913, + "grad_norm": 0.5670780539512634, + "learning_rate": 9.337749575201535e-05, + "loss": 1.6647, + "step": 3223 + }, + { + "epoch": 0.17970012819798228, + "grad_norm": 0.5969633460044861, + "learning_rate": 9.337306654117538e-05, + "loss": 1.7202, + "step": 3224 + }, + { + "epoch": 0.1797558664511454, + "grad_norm": 0.48552221059799194, + "learning_rate": 9.336863595479462e-05, + "loss": 1.4645, + "step": 3225 + }, + { + "epoch": 0.17981160470430857, + "grad_norm": 0.5412662625312805, + "learning_rate": 9.33642039930136e-05, + "loss": 1.8443, + "step": 3226 + }, + { + "epoch": 0.17986734295747173, + "grad_norm": 0.5973519682884216, + "learning_rate": 9.335977065597285e-05, + "loss": 1.98, + "step": 3227 + }, + { + "epoch": 0.17992308121063486, + "grad_norm": 0.5288311243057251, + "learning_rate": 9.335533594381297e-05, + "loss": 1.5549, + "step": 3228 + }, + { + "epoch": 0.179978819463798, + "grad_norm": 0.5504105687141418, + "learning_rate": 9.335089985667463e-05, + "loss": 1.5479, + "step": 3229 + }, + { + "epoch": 0.18003455771696114, + "grad_norm": 0.4889037609100342, + "learning_rate": 9.334646239469848e-05, + "loss": 1.7899, + "step": 3230 + }, + { + "epoch": 0.1800902959701243, + "grad_norm": 0.5372660756111145, + "learning_rate": 9.334202355802528e-05, + "loss": 1.7351, + "step": 3231 + }, + { + "epoch": 0.18014603422328745, + "grad_norm": 0.5164480209350586, + "learning_rate": 9.333758334679581e-05, + "loss": 1.6461, + "step": 3232 + }, + { + "epoch": 0.18020177247645058, + "grad_norm": 0.539726972579956, + "learning_rate": 9.333314176115084e-05, + "loss": 1.6368, + "step": 3233 + }, + { + "epoch": 0.18025751072961374, + "grad_norm": 0.6785762310028076, + "learning_rate": 9.33286988012313e-05, + "loss": 2.0446, + "step": 3234 + }, + { + "epoch": 0.18031324898277687, + "grad_norm": 0.580847442150116, + "learning_rate": 9.332425446717803e-05, + "loss": 1.8455, + "step": 3235 + }, + { + "epoch": 0.18036898723594003, + "grad_norm": 0.5236613154411316, + "learning_rate": 9.331980875913202e-05, + "loss": 1.4925, + "step": 3236 + }, + { + "epoch": 0.18042472548910318, + "grad_norm": 0.5626049637794495, + "learning_rate": 9.331536167723423e-05, + "loss": 1.7695, + "step": 3237 + }, + { + "epoch": 0.1804804637422663, + "grad_norm": 0.5435861349105835, + "learning_rate": 9.331091322162573e-05, + "loss": 1.8594, + "step": 3238 + }, + { + "epoch": 0.18053620199542947, + "grad_norm": 0.5868507027626038, + "learning_rate": 9.330646339244759e-05, + "loss": 1.8194, + "step": 3239 + }, + { + "epoch": 0.1805919402485926, + "grad_norm": 0.5488845705986023, + "learning_rate": 9.330201218984092e-05, + "loss": 1.6584, + "step": 3240 + }, + { + "epoch": 0.18064767850175575, + "grad_norm": 0.5238907933235168, + "learning_rate": 9.329755961394688e-05, + "loss": 1.757, + "step": 3241 + }, + { + "epoch": 0.1807034167549189, + "grad_norm": 0.5120671987533569, + "learning_rate": 9.32931056649067e-05, + "loss": 1.6786, + "step": 3242 + }, + { + "epoch": 0.18075915500808204, + "grad_norm": 0.49454161524772644, + "learning_rate": 9.328865034286161e-05, + "loss": 1.457, + "step": 3243 + }, + { + "epoch": 0.1808148932612452, + "grad_norm": 0.5296444892883301, + "learning_rate": 9.328419364795295e-05, + "loss": 1.691, + "step": 3244 + }, + { + "epoch": 0.18087063151440833, + "grad_norm": 0.5104671120643616, + "learning_rate": 9.327973558032201e-05, + "loss": 1.6702, + "step": 3245 + }, + { + "epoch": 0.18092636976757148, + "grad_norm": 0.5683085322380066, + "learning_rate": 9.32752761401102e-05, + "loss": 1.6912, + "step": 3246 + }, + { + "epoch": 0.18098210802073464, + "grad_norm": 0.5360772609710693, + "learning_rate": 9.327081532745896e-05, + "loss": 1.7894, + "step": 3247 + }, + { + "epoch": 0.18103784627389777, + "grad_norm": 0.6272693872451782, + "learning_rate": 9.326635314250971e-05, + "loss": 2.0331, + "step": 3248 + }, + { + "epoch": 0.18109358452706092, + "grad_norm": 0.5494347810745239, + "learning_rate": 9.326188958540403e-05, + "loss": 1.8261, + "step": 3249 + }, + { + "epoch": 0.18114932278022408, + "grad_norm": 0.5473103523254395, + "learning_rate": 9.325742465628342e-05, + "loss": 1.5244, + "step": 3250 + }, + { + "epoch": 0.1812050610333872, + "grad_norm": 0.5626412034034729, + "learning_rate": 9.325295835528953e-05, + "loss": 1.8512, + "step": 3251 + }, + { + "epoch": 0.18126079928655037, + "grad_norm": 0.5165623426437378, + "learning_rate": 9.324849068256397e-05, + "loss": 1.8405, + "step": 3252 + }, + { + "epoch": 0.1813165375397135, + "grad_norm": 0.5183326601982117, + "learning_rate": 9.324402163824846e-05, + "loss": 1.7193, + "step": 3253 + }, + { + "epoch": 0.18137227579287665, + "grad_norm": 0.5188653469085693, + "learning_rate": 9.323955122248468e-05, + "loss": 1.6715, + "step": 3254 + }, + { + "epoch": 0.1814280140460398, + "grad_norm": 0.5316330194473267, + "learning_rate": 9.323507943541447e-05, + "loss": 1.5796, + "step": 3255 + }, + { + "epoch": 0.18148375229920294, + "grad_norm": 0.5456557869911194, + "learning_rate": 9.323060627717961e-05, + "loss": 1.7856, + "step": 3256 + }, + { + "epoch": 0.1815394905523661, + "grad_norm": 0.5671826004981995, + "learning_rate": 9.322613174792197e-05, + "loss": 1.7715, + "step": 3257 + }, + { + "epoch": 0.18159522880552922, + "grad_norm": 0.5530715584754944, + "learning_rate": 9.322165584778347e-05, + "loss": 1.9437, + "step": 3258 + }, + { + "epoch": 0.18165096705869238, + "grad_norm": 0.5097282528877258, + "learning_rate": 9.321717857690601e-05, + "loss": 1.5789, + "step": 3259 + }, + { + "epoch": 0.18170670531185554, + "grad_norm": 0.5106785297393799, + "learning_rate": 9.321269993543166e-05, + "loss": 1.7718, + "step": 3260 + }, + { + "epoch": 0.18176244356501867, + "grad_norm": 0.5174189209938049, + "learning_rate": 9.320821992350239e-05, + "loss": 1.6088, + "step": 3261 + }, + { + "epoch": 0.18181818181818182, + "grad_norm": 0.5284159779548645, + "learning_rate": 9.320373854126032e-05, + "loss": 1.6355, + "step": 3262 + }, + { + "epoch": 0.18187392007134495, + "grad_norm": 0.5431947708129883, + "learning_rate": 9.319925578884754e-05, + "loss": 1.8282, + "step": 3263 + }, + { + "epoch": 0.1819296583245081, + "grad_norm": 0.5244488716125488, + "learning_rate": 9.319477166640626e-05, + "loss": 1.8765, + "step": 3264 + }, + { + "epoch": 0.18198539657767127, + "grad_norm": 0.5338707566261292, + "learning_rate": 9.319028617407865e-05, + "loss": 1.7684, + "step": 3265 + }, + { + "epoch": 0.1820411348308344, + "grad_norm": 0.5929536819458008, + "learning_rate": 9.318579931200697e-05, + "loss": 1.9083, + "step": 3266 + }, + { + "epoch": 0.18209687308399755, + "grad_norm": 0.5214221477508545, + "learning_rate": 9.318131108033355e-05, + "loss": 1.6844, + "step": 3267 + }, + { + "epoch": 0.18215261133716068, + "grad_norm": 0.5370472073554993, + "learning_rate": 9.31768214792007e-05, + "loss": 1.9451, + "step": 3268 + }, + { + "epoch": 0.18220834959032384, + "grad_norm": 0.5181378722190857, + "learning_rate": 9.31723305087508e-05, + "loss": 1.7534, + "step": 3269 + }, + { + "epoch": 0.182264087843487, + "grad_norm": 0.5766522884368896, + "learning_rate": 9.316783816912629e-05, + "loss": 1.876, + "step": 3270 + }, + { + "epoch": 0.18231982609665012, + "grad_norm": 0.5224177241325378, + "learning_rate": 9.316334446046966e-05, + "loss": 1.7254, + "step": 3271 + }, + { + "epoch": 0.18237556434981328, + "grad_norm": 0.5871415138244629, + "learning_rate": 9.315884938292339e-05, + "loss": 1.6292, + "step": 3272 + }, + { + "epoch": 0.18243130260297644, + "grad_norm": 0.5917293429374695, + "learning_rate": 9.315435293663005e-05, + "loss": 2.0649, + "step": 3273 + }, + { + "epoch": 0.18248704085613957, + "grad_norm": 0.5843697190284729, + "learning_rate": 9.314985512173223e-05, + "loss": 1.8282, + "step": 3274 + }, + { + "epoch": 0.18254277910930272, + "grad_norm": 0.5423409938812256, + "learning_rate": 9.31453559383726e-05, + "loss": 1.7501, + "step": 3275 + }, + { + "epoch": 0.18259851736246585, + "grad_norm": 0.5610026717185974, + "learning_rate": 9.314085538669383e-05, + "loss": 1.7287, + "step": 3276 + }, + { + "epoch": 0.182654255615629, + "grad_norm": 0.5071337223052979, + "learning_rate": 9.313635346683865e-05, + "loss": 1.6779, + "step": 3277 + }, + { + "epoch": 0.18270999386879216, + "grad_norm": 0.5492652058601379, + "learning_rate": 9.313185017894985e-05, + "loss": 1.7884, + "step": 3278 + }, + { + "epoch": 0.1827657321219553, + "grad_norm": 0.4901118874549866, + "learning_rate": 9.312734552317023e-05, + "loss": 1.5747, + "step": 3279 + }, + { + "epoch": 0.18282147037511845, + "grad_norm": 0.515848696231842, + "learning_rate": 9.312283949964267e-05, + "loss": 1.4992, + "step": 3280 + }, + { + "epoch": 0.18287720862828158, + "grad_norm": 0.497324675321579, + "learning_rate": 9.311833210851007e-05, + "loss": 1.5226, + "step": 3281 + }, + { + "epoch": 0.18293294688144474, + "grad_norm": 0.5232150554656982, + "learning_rate": 9.311382334991536e-05, + "loss": 1.6106, + "step": 3282 + }, + { + "epoch": 0.1829886851346079, + "grad_norm": 0.6029054522514343, + "learning_rate": 9.310931322400156e-05, + "loss": 1.9531, + "step": 3283 + }, + { + "epoch": 0.18304442338777102, + "grad_norm": 0.70119708776474, + "learning_rate": 9.310480173091168e-05, + "loss": 1.9566, + "step": 3284 + }, + { + "epoch": 0.18310016164093418, + "grad_norm": 0.5252953767776489, + "learning_rate": 9.31002888707888e-05, + "loss": 1.8004, + "step": 3285 + }, + { + "epoch": 0.1831558998940973, + "grad_norm": 0.5744017958641052, + "learning_rate": 9.309577464377606e-05, + "loss": 1.8203, + "step": 3286 + }, + { + "epoch": 0.18321163814726046, + "grad_norm": 0.5286086797714233, + "learning_rate": 9.309125905001659e-05, + "loss": 1.8127, + "step": 3287 + }, + { + "epoch": 0.18326737640042362, + "grad_norm": 0.5180408954620361, + "learning_rate": 9.308674208965364e-05, + "loss": 1.5432, + "step": 3288 + }, + { + "epoch": 0.18332311465358675, + "grad_norm": 0.568420946598053, + "learning_rate": 9.308222376283045e-05, + "loss": 1.853, + "step": 3289 + }, + { + "epoch": 0.1833788529067499, + "grad_norm": 0.9352191090583801, + "learning_rate": 9.30777040696903e-05, + "loss": 1.531, + "step": 3290 + }, + { + "epoch": 0.18343459115991304, + "grad_norm": 0.5612093210220337, + "learning_rate": 9.307318301037656e-05, + "loss": 2.0149, + "step": 3291 + }, + { + "epoch": 0.1834903294130762, + "grad_norm": 0.5616469979286194, + "learning_rate": 9.306866058503257e-05, + "loss": 1.6388, + "step": 3292 + }, + { + "epoch": 0.18354606766623935, + "grad_norm": 0.5579656958580017, + "learning_rate": 9.306413679380177e-05, + "loss": 1.8719, + "step": 3293 + }, + { + "epoch": 0.18360180591940248, + "grad_norm": 0.5343957543373108, + "learning_rate": 9.305961163682764e-05, + "loss": 1.7592, + "step": 3294 + }, + { + "epoch": 0.18365754417256563, + "grad_norm": 0.5974972248077393, + "learning_rate": 9.305508511425367e-05, + "loss": 1.834, + "step": 3295 + }, + { + "epoch": 0.1837132824257288, + "grad_norm": 0.5827033519744873, + "learning_rate": 9.305055722622344e-05, + "loss": 1.8606, + "step": 3296 + }, + { + "epoch": 0.18376902067889192, + "grad_norm": 0.5568636059761047, + "learning_rate": 9.304602797288054e-05, + "loss": 1.8952, + "step": 3297 + }, + { + "epoch": 0.18382475893205508, + "grad_norm": 0.6066376566886902, + "learning_rate": 9.30414973543686e-05, + "loss": 1.9215, + "step": 3298 + }, + { + "epoch": 0.1838804971852182, + "grad_norm": 0.5111042261123657, + "learning_rate": 9.303696537083132e-05, + "loss": 1.5506, + "step": 3299 + }, + { + "epoch": 0.18393623543838136, + "grad_norm": 0.501711905002594, + "learning_rate": 9.303243202241242e-05, + "loss": 1.5003, + "step": 3300 + }, + { + "epoch": 0.18399197369154452, + "grad_norm": 0.543425977230072, + "learning_rate": 9.302789730925567e-05, + "loss": 1.5837, + "step": 3301 + }, + { + "epoch": 0.18404771194470765, + "grad_norm": 0.5619440674781799, + "learning_rate": 9.30233612315049e-05, + "loss": 1.8285, + "step": 3302 + }, + { + "epoch": 0.1841034501978708, + "grad_norm": 0.5294018387794495, + "learning_rate": 9.301882378930394e-05, + "loss": 1.6032, + "step": 3303 + }, + { + "epoch": 0.18415918845103393, + "grad_norm": 0.6101817488670349, + "learning_rate": 9.301428498279671e-05, + "loss": 1.9998, + "step": 3304 + }, + { + "epoch": 0.1842149267041971, + "grad_norm": 0.5133767127990723, + "learning_rate": 9.300974481212715e-05, + "loss": 1.6816, + "step": 3305 + }, + { + "epoch": 0.18427066495736025, + "grad_norm": 0.5289322137832642, + "learning_rate": 9.300520327743924e-05, + "loss": 1.4649, + "step": 3306 + }, + { + "epoch": 0.18432640321052338, + "grad_norm": 0.5560780763626099, + "learning_rate": 9.300066037887704e-05, + "loss": 1.6704, + "step": 3307 + }, + { + "epoch": 0.18438214146368653, + "grad_norm": 0.5855201482772827, + "learning_rate": 9.29961161165846e-05, + "loss": 1.9368, + "step": 3308 + }, + { + "epoch": 0.18443787971684966, + "grad_norm": 0.5227165818214417, + "learning_rate": 9.299157049070603e-05, + "loss": 1.663, + "step": 3309 + }, + { + "epoch": 0.18449361797001282, + "grad_norm": 0.555633008480072, + "learning_rate": 9.298702350138551e-05, + "loss": 1.6634, + "step": 3310 + }, + { + "epoch": 0.18454935622317598, + "grad_norm": 0.5284892916679382, + "learning_rate": 9.298247514876724e-05, + "loss": 1.7772, + "step": 3311 + }, + { + "epoch": 0.1846050944763391, + "grad_norm": 0.5455605983734131, + "learning_rate": 9.297792543299545e-05, + "loss": 1.7826, + "step": 3312 + }, + { + "epoch": 0.18466083272950226, + "grad_norm": 0.6630359292030334, + "learning_rate": 9.297337435421446e-05, + "loss": 2.0859, + "step": 3313 + }, + { + "epoch": 0.1847165709826654, + "grad_norm": 0.4958614408969879, + "learning_rate": 9.296882191256857e-05, + "loss": 1.6861, + "step": 3314 + }, + { + "epoch": 0.18477230923582855, + "grad_norm": 0.506952702999115, + "learning_rate": 9.29642681082022e-05, + "loss": 1.6616, + "step": 3315 + }, + { + "epoch": 0.1848280474889917, + "grad_norm": 0.5598859190940857, + "learning_rate": 9.295971294125973e-05, + "loss": 1.8831, + "step": 3316 + }, + { + "epoch": 0.18488378574215483, + "grad_norm": 0.5533158183097839, + "learning_rate": 9.295515641188563e-05, + "loss": 1.6373, + "step": 3317 + }, + { + "epoch": 0.184939523995318, + "grad_norm": 0.5264914035797119, + "learning_rate": 9.295059852022443e-05, + "loss": 1.6668, + "step": 3318 + }, + { + "epoch": 0.18499526224848115, + "grad_norm": 0.542248010635376, + "learning_rate": 9.294603926642064e-05, + "loss": 1.5566, + "step": 3319 + }, + { + "epoch": 0.18505100050164427, + "grad_norm": 0.5599246621131897, + "learning_rate": 9.294147865061891e-05, + "loss": 1.8183, + "step": 3320 + }, + { + "epoch": 0.18510673875480743, + "grad_norm": 0.48394709825515747, + "learning_rate": 9.293691667296382e-05, + "loss": 1.4792, + "step": 3321 + }, + { + "epoch": 0.18516247700797056, + "grad_norm": 0.5670637488365173, + "learning_rate": 9.293235333360009e-05, + "loss": 1.8202, + "step": 3322 + }, + { + "epoch": 0.18521821526113372, + "grad_norm": 0.5079344511032104, + "learning_rate": 9.29277886326724e-05, + "loss": 1.698, + "step": 3323 + }, + { + "epoch": 0.18527395351429687, + "grad_norm": 0.6303577423095703, + "learning_rate": 9.292322257032555e-05, + "loss": 1.8882, + "step": 3324 + }, + { + "epoch": 0.18532969176746, + "grad_norm": 0.5548877716064453, + "learning_rate": 9.291865514670435e-05, + "loss": 1.8684, + "step": 3325 + }, + { + "epoch": 0.18538543002062316, + "grad_norm": 0.5407868027687073, + "learning_rate": 9.291408636195364e-05, + "loss": 1.7726, + "step": 3326 + }, + { + "epoch": 0.1854411682737863, + "grad_norm": 0.5434556007385254, + "learning_rate": 9.29095162162183e-05, + "loss": 1.8152, + "step": 3327 + }, + { + "epoch": 0.18549690652694945, + "grad_norm": 0.5405827164649963, + "learning_rate": 9.290494470964332e-05, + "loss": 1.7364, + "step": 3328 + }, + { + "epoch": 0.1855526447801126, + "grad_norm": 0.4682316184043884, + "learning_rate": 9.290037184237362e-05, + "loss": 1.6331, + "step": 3329 + }, + { + "epoch": 0.18560838303327573, + "grad_norm": 0.5418784618377686, + "learning_rate": 9.289579761455426e-05, + "loss": 1.9186, + "step": 3330 + }, + { + "epoch": 0.1856641212864389, + "grad_norm": 0.6001595854759216, + "learning_rate": 9.289122202633029e-05, + "loss": 1.8436, + "step": 3331 + }, + { + "epoch": 0.18571985953960202, + "grad_norm": 0.5514225363731384, + "learning_rate": 9.288664507784686e-05, + "loss": 1.8193, + "step": 3332 + }, + { + "epoch": 0.18577559779276517, + "grad_norm": 0.5329412817955017, + "learning_rate": 9.288206676924906e-05, + "loss": 1.5945, + "step": 3333 + }, + { + "epoch": 0.18583133604592833, + "grad_norm": 0.5613374710083008, + "learning_rate": 9.287748710068214e-05, + "loss": 1.8746, + "step": 3334 + }, + { + "epoch": 0.18588707429909146, + "grad_norm": 0.5720524191856384, + "learning_rate": 9.287290607229131e-05, + "loss": 1.6635, + "step": 3335 + }, + { + "epoch": 0.18594281255225462, + "grad_norm": 0.5446194410324097, + "learning_rate": 9.286832368422187e-05, + "loss": 1.6587, + "step": 3336 + }, + { + "epoch": 0.18599855080541774, + "grad_norm": 0.5358483791351318, + "learning_rate": 9.286373993661916e-05, + "loss": 1.8244, + "step": 3337 + }, + { + "epoch": 0.1860542890585809, + "grad_norm": 0.5477625727653503, + "learning_rate": 9.28591548296285e-05, + "loss": 1.8085, + "step": 3338 + }, + { + "epoch": 0.18611002731174406, + "grad_norm": 0.528417706489563, + "learning_rate": 9.285456836339537e-05, + "loss": 1.7652, + "step": 3339 + }, + { + "epoch": 0.1861657655649072, + "grad_norm": 0.5157662630081177, + "learning_rate": 9.284998053806516e-05, + "loss": 1.7365, + "step": 3340 + }, + { + "epoch": 0.18622150381807034, + "grad_norm": 0.5836164951324463, + "learning_rate": 9.284539135378341e-05, + "loss": 1.8217, + "step": 3341 + }, + { + "epoch": 0.1862772420712335, + "grad_norm": 0.5283136963844299, + "learning_rate": 9.284080081069565e-05, + "loss": 1.7073, + "step": 3342 + }, + { + "epoch": 0.18633298032439663, + "grad_norm": 0.5611073970794678, + "learning_rate": 9.283620890894749e-05, + "loss": 1.6885, + "step": 3343 + }, + { + "epoch": 0.1863887185775598, + "grad_norm": 0.5854252576828003, + "learning_rate": 9.283161564868452e-05, + "loss": 1.8512, + "step": 3344 + }, + { + "epoch": 0.18644445683072292, + "grad_norm": 0.5314401984214783, + "learning_rate": 9.282702103005243e-05, + "loss": 1.8003, + "step": 3345 + }, + { + "epoch": 0.18650019508388607, + "grad_norm": 0.5689622759819031, + "learning_rate": 9.282242505319693e-05, + "loss": 1.7775, + "step": 3346 + }, + { + "epoch": 0.18655593333704923, + "grad_norm": 0.5099941492080688, + "learning_rate": 9.281782771826378e-05, + "loss": 1.4253, + "step": 3347 + }, + { + "epoch": 0.18661167159021236, + "grad_norm": 0.557032585144043, + "learning_rate": 9.281322902539878e-05, + "loss": 1.7682, + "step": 3348 + }, + { + "epoch": 0.18666740984337551, + "grad_norm": 0.5229087471961975, + "learning_rate": 9.280862897474776e-05, + "loss": 1.5904, + "step": 3349 + }, + { + "epoch": 0.18672314809653864, + "grad_norm": 0.5913739800453186, + "learning_rate": 9.280402756645663e-05, + "loss": 1.9147, + "step": 3350 + }, + { + "epoch": 0.1867788863497018, + "grad_norm": 0.5528784990310669, + "learning_rate": 9.279942480067131e-05, + "loss": 1.7212, + "step": 3351 + }, + { + "epoch": 0.18683462460286496, + "grad_norm": 0.5475696921348572, + "learning_rate": 9.279482067753777e-05, + "loss": 1.8177, + "step": 3352 + }, + { + "epoch": 0.18689036285602809, + "grad_norm": 0.5523363947868347, + "learning_rate": 9.279021519720203e-05, + "loss": 1.7726, + "step": 3353 + }, + { + "epoch": 0.18694610110919124, + "grad_norm": 0.4846109449863434, + "learning_rate": 9.278560835981016e-05, + "loss": 1.7335, + "step": 3354 + }, + { + "epoch": 0.18700183936235437, + "grad_norm": 0.5322748422622681, + "learning_rate": 9.278100016550825e-05, + "loss": 1.8071, + "step": 3355 + }, + { + "epoch": 0.18705757761551753, + "grad_norm": 0.5510337352752686, + "learning_rate": 9.277639061444244e-05, + "loss": 1.7673, + "step": 3356 + }, + { + "epoch": 0.18711331586868069, + "grad_norm": 0.5218777060508728, + "learning_rate": 9.277177970675893e-05, + "loss": 1.686, + "step": 3357 + }, + { + "epoch": 0.18716905412184381, + "grad_norm": 0.5483778715133667, + "learning_rate": 9.276716744260392e-05, + "loss": 1.8069, + "step": 3358 + }, + { + "epoch": 0.18722479237500697, + "grad_norm": 0.5690082907676697, + "learning_rate": 9.276255382212373e-05, + "loss": 1.7838, + "step": 3359 + }, + { + "epoch": 0.1872805306281701, + "grad_norm": 0.5564740896224976, + "learning_rate": 9.275793884546465e-05, + "loss": 1.6363, + "step": 3360 + }, + { + "epoch": 0.18733626888133326, + "grad_norm": 0.5689534544944763, + "learning_rate": 9.275332251277305e-05, + "loss": 1.7624, + "step": 3361 + }, + { + "epoch": 0.1873920071344964, + "grad_norm": 0.5340893864631653, + "learning_rate": 9.274870482419533e-05, + "loss": 1.785, + "step": 3362 + }, + { + "epoch": 0.18744774538765954, + "grad_norm": 0.556954562664032, + "learning_rate": 9.274408577987792e-05, + "loss": 1.7629, + "step": 3363 + }, + { + "epoch": 0.1875034836408227, + "grad_norm": 0.5275453329086304, + "learning_rate": 9.273946537996734e-05, + "loss": 1.6675, + "step": 3364 + }, + { + "epoch": 0.18755922189398586, + "grad_norm": 0.5510149598121643, + "learning_rate": 9.273484362461011e-05, + "loss": 1.8703, + "step": 3365 + }, + { + "epoch": 0.18761496014714898, + "grad_norm": 0.5040173530578613, + "learning_rate": 9.273022051395278e-05, + "loss": 1.646, + "step": 3366 + }, + { + "epoch": 0.18767069840031214, + "grad_norm": 0.5532334446907043, + "learning_rate": 9.272559604814201e-05, + "loss": 1.7221, + "step": 3367 + }, + { + "epoch": 0.18772643665347527, + "grad_norm": 0.5305314064025879, + "learning_rate": 9.272097022732443e-05, + "loss": 1.5933, + "step": 3368 + }, + { + "epoch": 0.18778217490663843, + "grad_norm": 0.5466606020927429, + "learning_rate": 9.271634305164675e-05, + "loss": 1.7312, + "step": 3369 + }, + { + "epoch": 0.18783791315980158, + "grad_norm": 0.5373468995094299, + "learning_rate": 9.271171452125575e-05, + "loss": 1.7442, + "step": 3370 + }, + { + "epoch": 0.1878936514129647, + "grad_norm": 0.5270282626152039, + "learning_rate": 9.270708463629815e-05, + "loss": 1.7939, + "step": 3371 + }, + { + "epoch": 0.18794938966612787, + "grad_norm": 0.5657024383544922, + "learning_rate": 9.270245339692086e-05, + "loss": 1.8941, + "step": 3372 + }, + { + "epoch": 0.188005127919291, + "grad_norm": 0.5092267990112305, + "learning_rate": 9.269782080327071e-05, + "loss": 1.6895, + "step": 3373 + }, + { + "epoch": 0.18806086617245416, + "grad_norm": 0.5645020008087158, + "learning_rate": 9.269318685549463e-05, + "loss": 1.6734, + "step": 3374 + }, + { + "epoch": 0.1881166044256173, + "grad_norm": 0.5031103491783142, + "learning_rate": 9.268855155373957e-05, + "loss": 1.848, + "step": 3375 + }, + { + "epoch": 0.18817234267878044, + "grad_norm": 0.5133728981018066, + "learning_rate": 9.268391489815257e-05, + "loss": 1.4297, + "step": 3376 + }, + { + "epoch": 0.1882280809319436, + "grad_norm": 0.5471519231796265, + "learning_rate": 9.267927688888062e-05, + "loss": 1.8073, + "step": 3377 + }, + { + "epoch": 0.18828381918510673, + "grad_norm": 0.545860230922699, + "learning_rate": 9.267463752607089e-05, + "loss": 1.751, + "step": 3378 + }, + { + "epoch": 0.18833955743826988, + "grad_norm": 0.4829151928424835, + "learning_rate": 9.266999680987043e-05, + "loss": 1.498, + "step": 3379 + }, + { + "epoch": 0.18839529569143304, + "grad_norm": 0.5440730452537537, + "learning_rate": 9.266535474042647e-05, + "loss": 1.4733, + "step": 3380 + }, + { + "epoch": 0.18845103394459617, + "grad_norm": 0.7026723623275757, + "learning_rate": 9.266071131788621e-05, + "loss": 1.904, + "step": 3381 + }, + { + "epoch": 0.18850677219775933, + "grad_norm": 0.49864065647125244, + "learning_rate": 9.26560665423969e-05, + "loss": 1.8644, + "step": 3382 + }, + { + "epoch": 0.18856251045092245, + "grad_norm": 0.5199279189109802, + "learning_rate": 9.265142041410589e-05, + "loss": 1.6917, + "step": 3383 + }, + { + "epoch": 0.1886182487040856, + "grad_norm": 0.5546734929084778, + "learning_rate": 9.26467729331605e-05, + "loss": 1.7944, + "step": 3384 + }, + { + "epoch": 0.18867398695724877, + "grad_norm": 0.5777541399002075, + "learning_rate": 9.26421240997081e-05, + "loss": 1.9372, + "step": 3385 + }, + { + "epoch": 0.1887297252104119, + "grad_norm": 0.6016680598258972, + "learning_rate": 9.263747391389615e-05, + "loss": 1.9591, + "step": 3386 + }, + { + "epoch": 0.18878546346357505, + "grad_norm": 0.5046743154525757, + "learning_rate": 9.263282237587213e-05, + "loss": 1.5718, + "step": 3387 + }, + { + "epoch": 0.1888412017167382, + "grad_norm": 0.5458966493606567, + "learning_rate": 9.262816948578354e-05, + "loss": 1.7829, + "step": 3388 + }, + { + "epoch": 0.18889693996990134, + "grad_norm": 0.5983991026878357, + "learning_rate": 9.262351524377797e-05, + "loss": 1.8848, + "step": 3389 + }, + { + "epoch": 0.1889526782230645, + "grad_norm": 0.5047475099563599, + "learning_rate": 9.261885965000298e-05, + "loss": 1.3356, + "step": 3390 + }, + { + "epoch": 0.18900841647622763, + "grad_norm": 0.5353848338127136, + "learning_rate": 9.261420270460628e-05, + "loss": 1.7632, + "step": 3391 + }, + { + "epoch": 0.18906415472939078, + "grad_norm": 0.5097886919975281, + "learning_rate": 9.26095444077355e-05, + "loss": 1.6608, + "step": 3392 + }, + { + "epoch": 0.18911989298255394, + "grad_norm": 0.5497481226921082, + "learning_rate": 9.260488475953842e-05, + "loss": 1.8704, + "step": 3393 + }, + { + "epoch": 0.18917563123571707, + "grad_norm": 0.5084047317504883, + "learning_rate": 9.26002237601628e-05, + "loss": 1.515, + "step": 3394 + }, + { + "epoch": 0.18923136948888022, + "grad_norm": 0.5252576470375061, + "learning_rate": 9.259556140975644e-05, + "loss": 1.448, + "step": 3395 + }, + { + "epoch": 0.18928710774204335, + "grad_norm": 0.5760124325752258, + "learning_rate": 9.259089770846723e-05, + "loss": 1.7052, + "step": 3396 + }, + { + "epoch": 0.1893428459952065, + "grad_norm": 0.5604876279830933, + "learning_rate": 9.258623265644309e-05, + "loss": 1.8782, + "step": 3397 + }, + { + "epoch": 0.18939858424836967, + "grad_norm": 0.5331717133522034, + "learning_rate": 9.258156625383192e-05, + "loss": 1.6754, + "step": 3398 + }, + { + "epoch": 0.1894543225015328, + "grad_norm": 0.5478466153144836, + "learning_rate": 9.257689850078174e-05, + "loss": 1.7709, + "step": 3399 + }, + { + "epoch": 0.18951006075469595, + "grad_norm": 0.5751819014549255, + "learning_rate": 9.257222939744059e-05, + "loss": 1.6806, + "step": 3400 + }, + { + "epoch": 0.18956579900785908, + "grad_norm": 0.557999849319458, + "learning_rate": 9.256755894395652e-05, + "loss": 1.6614, + "step": 3401 + }, + { + "epoch": 0.18962153726102224, + "grad_norm": 0.6242285370826721, + "learning_rate": 9.256288714047767e-05, + "loss": 1.9115, + "step": 3402 + }, + { + "epoch": 0.1896772755141854, + "grad_norm": 0.5403860807418823, + "learning_rate": 9.255821398715221e-05, + "loss": 1.6686, + "step": 3403 + }, + { + "epoch": 0.18973301376734852, + "grad_norm": 0.5129532814025879, + "learning_rate": 9.255353948412833e-05, + "loss": 1.5406, + "step": 3404 + }, + { + "epoch": 0.18978875202051168, + "grad_norm": 0.5771991014480591, + "learning_rate": 9.254886363155429e-05, + "loss": 1.8979, + "step": 3405 + }, + { + "epoch": 0.1898444902736748, + "grad_norm": 0.5569978356361389, + "learning_rate": 9.254418642957835e-05, + "loss": 1.7284, + "step": 3406 + }, + { + "epoch": 0.18990022852683797, + "grad_norm": 0.5016009211540222, + "learning_rate": 9.253950787834889e-05, + "loss": 1.7517, + "step": 3407 + }, + { + "epoch": 0.18995596678000112, + "grad_norm": 0.47752997279167175, + "learning_rate": 9.253482797801425e-05, + "loss": 1.7069, + "step": 3408 + }, + { + "epoch": 0.19001170503316425, + "grad_norm": 0.4722379446029663, + "learning_rate": 9.253014672872285e-05, + "loss": 1.4309, + "step": 3409 + }, + { + "epoch": 0.1900674432863274, + "grad_norm": 0.516113817691803, + "learning_rate": 9.252546413062319e-05, + "loss": 1.6337, + "step": 3410 + }, + { + "epoch": 0.19012318153949057, + "grad_norm": 0.4841940402984619, + "learning_rate": 9.252078018386374e-05, + "loss": 1.4486, + "step": 3411 + }, + { + "epoch": 0.1901789197926537, + "grad_norm": 0.566828191280365, + "learning_rate": 9.251609488859304e-05, + "loss": 1.524, + "step": 3412 + }, + { + "epoch": 0.19023465804581685, + "grad_norm": 0.5277671813964844, + "learning_rate": 9.251140824495972e-05, + "loss": 1.6331, + "step": 3413 + }, + { + "epoch": 0.19029039629897998, + "grad_norm": 0.5212645530700684, + "learning_rate": 9.250672025311237e-05, + "loss": 1.6409, + "step": 3414 + }, + { + "epoch": 0.19034613455214314, + "grad_norm": 0.5892760753631592, + "learning_rate": 9.250203091319968e-05, + "loss": 1.7712, + "step": 3415 + }, + { + "epoch": 0.1904018728053063, + "grad_norm": 0.5454036593437195, + "learning_rate": 9.24973402253704e-05, + "loss": 1.888, + "step": 3416 + }, + { + "epoch": 0.19045761105846942, + "grad_norm": 0.5001441836357117, + "learning_rate": 9.249264818977324e-05, + "loss": 1.6808, + "step": 3417 + }, + { + "epoch": 0.19051334931163258, + "grad_norm": 0.5732707977294922, + "learning_rate": 9.248795480655704e-05, + "loss": 1.8398, + "step": 3418 + }, + { + "epoch": 0.1905690875647957, + "grad_norm": 0.5356916785240173, + "learning_rate": 9.248326007587063e-05, + "loss": 1.7295, + "step": 3419 + }, + { + "epoch": 0.19062482581795887, + "grad_norm": 0.5317162275314331, + "learning_rate": 9.247856399786292e-05, + "loss": 1.7717, + "step": 3420 + }, + { + "epoch": 0.19068056407112202, + "grad_norm": 0.5117460489273071, + "learning_rate": 9.247386657268283e-05, + "loss": 1.5417, + "step": 3421 + }, + { + "epoch": 0.19073630232428515, + "grad_norm": 0.5263468623161316, + "learning_rate": 9.24691678004793e-05, + "loss": 1.8882, + "step": 3422 + }, + { + "epoch": 0.1907920405774483, + "grad_norm": 0.5721904635429382, + "learning_rate": 9.24644676814014e-05, + "loss": 1.8083, + "step": 3423 + }, + { + "epoch": 0.19084777883061144, + "grad_norm": 0.5673632025718689, + "learning_rate": 9.245976621559817e-05, + "loss": 1.8532, + "step": 3424 + }, + { + "epoch": 0.1909035170837746, + "grad_norm": 0.5096221566200256, + "learning_rate": 9.24550634032187e-05, + "loss": 1.5365, + "step": 3425 + }, + { + "epoch": 0.19095925533693775, + "grad_norm": 0.545087456703186, + "learning_rate": 9.245035924441217e-05, + "loss": 1.854, + "step": 3426 + }, + { + "epoch": 0.19101499359010088, + "grad_norm": 0.5424298644065857, + "learning_rate": 9.244565373932774e-05, + "loss": 1.7373, + "step": 3427 + }, + { + "epoch": 0.19107073184326404, + "grad_norm": 0.5558550357818604, + "learning_rate": 9.244094688811465e-05, + "loss": 1.746, + "step": 3428 + }, + { + "epoch": 0.19112647009642716, + "grad_norm": 0.49283209443092346, + "learning_rate": 9.243623869092218e-05, + "loss": 1.3836, + "step": 3429 + }, + { + "epoch": 0.19118220834959032, + "grad_norm": 0.5955911874771118, + "learning_rate": 9.24315291478996e-05, + "loss": 1.8499, + "step": 3430 + }, + { + "epoch": 0.19123794660275348, + "grad_norm": 0.5249252319335938, + "learning_rate": 9.242681825919635e-05, + "loss": 1.6767, + "step": 3431 + }, + { + "epoch": 0.1912936848559166, + "grad_norm": 0.5496412515640259, + "learning_rate": 9.242210602496178e-05, + "loss": 1.7963, + "step": 3432 + }, + { + "epoch": 0.19134942310907976, + "grad_norm": 0.5590277910232544, + "learning_rate": 9.241739244534534e-05, + "loss": 1.7885, + "step": 3433 + }, + { + "epoch": 0.19140516136224292, + "grad_norm": 0.5826262831687927, + "learning_rate": 9.241267752049653e-05, + "loss": 1.7971, + "step": 3434 + }, + { + "epoch": 0.19146089961540605, + "grad_norm": 0.5477822422981262, + "learning_rate": 9.240796125056486e-05, + "loss": 1.7376, + "step": 3435 + }, + { + "epoch": 0.1915166378685692, + "grad_norm": 0.5088443756103516, + "learning_rate": 9.240324363569992e-05, + "loss": 1.6705, + "step": 3436 + }, + { + "epoch": 0.19157237612173234, + "grad_norm": 0.5802351832389832, + "learning_rate": 9.239852467605132e-05, + "loss": 1.8505, + "step": 3437 + }, + { + "epoch": 0.1916281143748955, + "grad_norm": 0.5589656829833984, + "learning_rate": 9.239380437176872e-05, + "loss": 1.7993, + "step": 3438 + }, + { + "epoch": 0.19168385262805865, + "grad_norm": 0.5384811162948608, + "learning_rate": 9.238908272300181e-05, + "loss": 1.803, + "step": 3439 + }, + { + "epoch": 0.19173959088122178, + "grad_norm": 0.5251903533935547, + "learning_rate": 9.238435972990036e-05, + "loss": 1.6364, + "step": 3440 + }, + { + "epoch": 0.19179532913438493, + "grad_norm": 0.5536593794822693, + "learning_rate": 9.237963539261412e-05, + "loss": 1.8069, + "step": 3441 + }, + { + "epoch": 0.19185106738754806, + "grad_norm": 0.49031203985214233, + "learning_rate": 9.237490971129294e-05, + "loss": 1.6969, + "step": 3442 + }, + { + "epoch": 0.19190680564071122, + "grad_norm": 0.5111910700798035, + "learning_rate": 9.23701826860867e-05, + "loss": 1.7135, + "step": 3443 + }, + { + "epoch": 0.19196254389387438, + "grad_norm": 0.5502627491950989, + "learning_rate": 9.236545431714529e-05, + "loss": 1.8724, + "step": 3444 + }, + { + "epoch": 0.1920182821470375, + "grad_norm": 0.5772512555122375, + "learning_rate": 9.236072460461867e-05, + "loss": 1.7944, + "step": 3445 + }, + { + "epoch": 0.19207402040020066, + "grad_norm": 0.6393208503723145, + "learning_rate": 9.235599354865686e-05, + "loss": 1.5557, + "step": 3446 + }, + { + "epoch": 0.1921297586533638, + "grad_norm": 0.5822187066078186, + "learning_rate": 9.235126114940989e-05, + "loss": 1.8263, + "step": 3447 + }, + { + "epoch": 0.19218549690652695, + "grad_norm": 0.5391358733177185, + "learning_rate": 9.234652740702781e-05, + "loss": 1.7186, + "step": 3448 + }, + { + "epoch": 0.1922412351596901, + "grad_norm": 0.4919295907020569, + "learning_rate": 9.23417923216608e-05, + "loss": 1.5176, + "step": 3449 + }, + { + "epoch": 0.19229697341285323, + "grad_norm": 0.547146737575531, + "learning_rate": 9.233705589345902e-05, + "loss": 1.8129, + "step": 3450 + }, + { + "epoch": 0.1923527116660164, + "grad_norm": 0.4958893358707428, + "learning_rate": 9.233231812257265e-05, + "loss": 1.5314, + "step": 3451 + }, + { + "epoch": 0.19240844991917952, + "grad_norm": 0.4873281419277191, + "learning_rate": 9.232757900915197e-05, + "loss": 1.6043, + "step": 3452 + }, + { + "epoch": 0.19246418817234268, + "grad_norm": 0.5672634840011597, + "learning_rate": 9.232283855334727e-05, + "loss": 1.8168, + "step": 3453 + }, + { + "epoch": 0.19251992642550583, + "grad_norm": 0.514673113822937, + "learning_rate": 9.231809675530888e-05, + "loss": 1.7076, + "step": 3454 + }, + { + "epoch": 0.19257566467866896, + "grad_norm": 0.5566558241844177, + "learning_rate": 9.23133536151872e-05, + "loss": 1.8021, + "step": 3455 + }, + { + "epoch": 0.19263140293183212, + "grad_norm": 0.5627939701080322, + "learning_rate": 9.230860913313266e-05, + "loss": 1.659, + "step": 3456 + }, + { + "epoch": 0.19268714118499528, + "grad_norm": 0.5632688403129578, + "learning_rate": 9.23038633092957e-05, + "loss": 1.8172, + "step": 3457 + }, + { + "epoch": 0.1927428794381584, + "grad_norm": 0.5149570107460022, + "learning_rate": 9.229911614382685e-05, + "loss": 1.6086, + "step": 3458 + }, + { + "epoch": 0.19279861769132156, + "grad_norm": 0.5687461495399475, + "learning_rate": 9.229436763687665e-05, + "loss": 1.7102, + "step": 3459 + }, + { + "epoch": 0.1928543559444847, + "grad_norm": 0.527733325958252, + "learning_rate": 9.228961778859572e-05, + "loss": 1.6291, + "step": 3460 + }, + { + "epoch": 0.19291009419764785, + "grad_norm": 0.5713732242584229, + "learning_rate": 9.228486659913467e-05, + "loss": 1.7628, + "step": 3461 + }, + { + "epoch": 0.192965832450811, + "grad_norm": 0.5368852019309998, + "learning_rate": 9.228011406864417e-05, + "loss": 1.6604, + "step": 3462 + }, + { + "epoch": 0.19302157070397413, + "grad_norm": 0.5099670886993408, + "learning_rate": 9.227536019727498e-05, + "loss": 1.6571, + "step": 3463 + }, + { + "epoch": 0.1930773089571373, + "grad_norm": 0.5792325735092163, + "learning_rate": 9.227060498517785e-05, + "loss": 1.6586, + "step": 3464 + }, + { + "epoch": 0.19313304721030042, + "grad_norm": 0.5870433449745178, + "learning_rate": 9.226584843250357e-05, + "loss": 1.6693, + "step": 3465 + }, + { + "epoch": 0.19318878546346357, + "grad_norm": 0.5723249316215515, + "learning_rate": 9.226109053940302e-05, + "loss": 1.8516, + "step": 3466 + }, + { + "epoch": 0.19324452371662673, + "grad_norm": 0.5492411255836487, + "learning_rate": 9.225633130602707e-05, + "loss": 1.8369, + "step": 3467 + }, + { + "epoch": 0.19330026196978986, + "grad_norm": 0.5040132403373718, + "learning_rate": 9.225157073252666e-05, + "loss": 1.7936, + "step": 3468 + }, + { + "epoch": 0.19335600022295302, + "grad_norm": 0.5484923124313354, + "learning_rate": 9.224680881905279e-05, + "loss": 1.8398, + "step": 3469 + }, + { + "epoch": 0.19341173847611615, + "grad_norm": 0.6042559146881104, + "learning_rate": 9.224204556575644e-05, + "loss": 1.8699, + "step": 3470 + }, + { + "epoch": 0.1934674767292793, + "grad_norm": 0.5580307841300964, + "learning_rate": 9.22372809727887e-05, + "loss": 1.6961, + "step": 3471 + }, + { + "epoch": 0.19352321498244246, + "grad_norm": 0.5399236679077148, + "learning_rate": 9.223251504030066e-05, + "loss": 1.6302, + "step": 3472 + }, + { + "epoch": 0.1935789532356056, + "grad_norm": 0.5522669553756714, + "learning_rate": 9.222774776844349e-05, + "loss": 1.765, + "step": 3473 + }, + { + "epoch": 0.19363469148876875, + "grad_norm": 0.5530064105987549, + "learning_rate": 9.222297915736834e-05, + "loss": 1.783, + "step": 3474 + }, + { + "epoch": 0.19369042974193187, + "grad_norm": 0.5082196593284607, + "learning_rate": 9.22182092072265e-05, + "loss": 1.6188, + "step": 3475 + }, + { + "epoch": 0.19374616799509503, + "grad_norm": 0.5311219692230225, + "learning_rate": 9.221343791816918e-05, + "loss": 1.7017, + "step": 3476 + }, + { + "epoch": 0.1938019062482582, + "grad_norm": 0.542589545249939, + "learning_rate": 9.220866529034776e-05, + "loss": 1.7064, + "step": 3477 + }, + { + "epoch": 0.19385764450142132, + "grad_norm": 0.5327942967414856, + "learning_rate": 9.220389132391356e-05, + "loss": 1.7807, + "step": 3478 + }, + { + "epoch": 0.19391338275458447, + "grad_norm": 0.523639976978302, + "learning_rate": 9.219911601901799e-05, + "loss": 1.5785, + "step": 3479 + }, + { + "epoch": 0.19396912100774763, + "grad_norm": 0.5756027102470398, + "learning_rate": 9.21943393758125e-05, + "loss": 2.0297, + "step": 3480 + }, + { + "epoch": 0.19402485926091076, + "grad_norm": 0.5392191410064697, + "learning_rate": 9.218956139444858e-05, + "loss": 1.6824, + "step": 3481 + }, + { + "epoch": 0.19408059751407392, + "grad_norm": 0.536055326461792, + "learning_rate": 9.218478207507775e-05, + "loss": 1.7264, + "step": 3482 + }, + { + "epoch": 0.19413633576723704, + "grad_norm": 0.5701099634170532, + "learning_rate": 9.218000141785158e-05, + "loss": 1.7967, + "step": 3483 + }, + { + "epoch": 0.1941920740204002, + "grad_norm": 0.586493194103241, + "learning_rate": 9.21752194229217e-05, + "loss": 2.0026, + "step": 3484 + }, + { + "epoch": 0.19424781227356336, + "grad_norm": 0.5607553124427795, + "learning_rate": 9.217043609043975e-05, + "loss": 1.8374, + "step": 3485 + }, + { + "epoch": 0.1943035505267265, + "grad_norm": 0.5268848538398743, + "learning_rate": 9.216565142055745e-05, + "loss": 1.6248, + "step": 3486 + }, + { + "epoch": 0.19435928877988964, + "grad_norm": 0.563528299331665, + "learning_rate": 9.216086541342652e-05, + "loss": 1.8659, + "step": 3487 + }, + { + "epoch": 0.19441502703305277, + "grad_norm": 0.5309708714485168, + "learning_rate": 9.215607806919877e-05, + "loss": 1.7026, + "step": 3488 + }, + { + "epoch": 0.19447076528621593, + "grad_norm": 0.5582777857780457, + "learning_rate": 9.2151289388026e-05, + "loss": 1.8766, + "step": 3489 + }, + { + "epoch": 0.1945265035393791, + "grad_norm": 0.5012943744659424, + "learning_rate": 9.214649937006008e-05, + "loss": 1.372, + "step": 3490 + }, + { + "epoch": 0.19458224179254222, + "grad_norm": 0.5534226298332214, + "learning_rate": 9.214170801545294e-05, + "loss": 1.8491, + "step": 3491 + }, + { + "epoch": 0.19463798004570537, + "grad_norm": 0.5312340259552002, + "learning_rate": 9.213691532435654e-05, + "loss": 1.4738, + "step": 3492 + }, + { + "epoch": 0.1946937182988685, + "grad_norm": 0.5233004093170166, + "learning_rate": 9.213212129692284e-05, + "loss": 1.5871, + "step": 3493 + }, + { + "epoch": 0.19474945655203166, + "grad_norm": 0.5227805972099304, + "learning_rate": 9.212732593330389e-05, + "loss": 1.6355, + "step": 3494 + }, + { + "epoch": 0.19480519480519481, + "grad_norm": 0.5237340927124023, + "learning_rate": 9.21225292336518e-05, + "loss": 1.8903, + "step": 3495 + }, + { + "epoch": 0.19486093305835794, + "grad_norm": 0.5420545935630798, + "learning_rate": 9.211773119811867e-05, + "loss": 1.9006, + "step": 3496 + }, + { + "epoch": 0.1949166713115211, + "grad_norm": 0.534702718257904, + "learning_rate": 9.211293182685667e-05, + "loss": 1.5601, + "step": 3497 + }, + { + "epoch": 0.19497240956468423, + "grad_norm": 0.5968030095100403, + "learning_rate": 9.210813112001802e-05, + "loss": 1.7871, + "step": 3498 + }, + { + "epoch": 0.19502814781784739, + "grad_norm": 0.5270916223526001, + "learning_rate": 9.210332907775494e-05, + "loss": 1.69, + "step": 3499 + }, + { + "epoch": 0.19508388607101054, + "grad_norm": 0.5496137142181396, + "learning_rate": 9.209852570021975e-05, + "loss": 1.916, + "step": 3500 + }, + { + "epoch": 0.19513962432417367, + "grad_norm": 0.5198974013328552, + "learning_rate": 9.209372098756476e-05, + "loss": 1.6651, + "step": 3501 + }, + { + "epoch": 0.19519536257733683, + "grad_norm": 0.5615696907043457, + "learning_rate": 9.208891493994239e-05, + "loss": 1.7589, + "step": 3502 + }, + { + "epoch": 0.19525110083049999, + "grad_norm": 0.5367715954780579, + "learning_rate": 9.208410755750501e-05, + "loss": 1.5889, + "step": 3503 + }, + { + "epoch": 0.19530683908366311, + "grad_norm": 0.6133012771606445, + "learning_rate": 9.207929884040511e-05, + "loss": 1.8472, + "step": 3504 + }, + { + "epoch": 0.19536257733682627, + "grad_norm": 0.6582043170928955, + "learning_rate": 9.20744887887952e-05, + "loss": 1.6471, + "step": 3505 + }, + { + "epoch": 0.1954183155899894, + "grad_norm": 0.5180196762084961, + "learning_rate": 9.206967740282783e-05, + "loss": 1.5727, + "step": 3506 + }, + { + "epoch": 0.19547405384315256, + "grad_norm": 0.5526701807975769, + "learning_rate": 9.206486468265555e-05, + "loss": 1.635, + "step": 3507 + }, + { + "epoch": 0.1955297920963157, + "grad_norm": 0.6198756694793701, + "learning_rate": 9.206005062843102e-05, + "loss": 1.7088, + "step": 3508 + }, + { + "epoch": 0.19558553034947884, + "grad_norm": 0.5373274683952332, + "learning_rate": 9.205523524030693e-05, + "loss": 1.7032, + "step": 3509 + }, + { + "epoch": 0.195641268602642, + "grad_norm": 0.5724993944168091, + "learning_rate": 9.205041851843596e-05, + "loss": 1.8822, + "step": 3510 + }, + { + "epoch": 0.19569700685580513, + "grad_norm": 0.5542033314704895, + "learning_rate": 9.20456004629709e-05, + "loss": 1.333, + "step": 3511 + }, + { + "epoch": 0.19575274510896828, + "grad_norm": 0.5784552693367004, + "learning_rate": 9.204078107406454e-05, + "loss": 1.8277, + "step": 3512 + }, + { + "epoch": 0.19580848336213144, + "grad_norm": 0.5339728593826294, + "learning_rate": 9.203596035186969e-05, + "loss": 1.5545, + "step": 3513 + }, + { + "epoch": 0.19586422161529457, + "grad_norm": 0.5574887990951538, + "learning_rate": 9.203113829653927e-05, + "loss": 1.6811, + "step": 3514 + }, + { + "epoch": 0.19591995986845773, + "grad_norm": 0.48576298356056213, + "learning_rate": 9.202631490822622e-05, + "loss": 1.548, + "step": 3515 + }, + { + "epoch": 0.19597569812162086, + "grad_norm": 0.516997218132019, + "learning_rate": 9.202149018708347e-05, + "loss": 1.6624, + "step": 3516 + }, + { + "epoch": 0.196031436374784, + "grad_norm": 0.5537340641021729, + "learning_rate": 9.201666413326408e-05, + "loss": 1.8557, + "step": 3517 + }, + { + "epoch": 0.19608717462794717, + "grad_norm": 0.5295738577842712, + "learning_rate": 9.201183674692107e-05, + "loss": 1.5435, + "step": 3518 + }, + { + "epoch": 0.1961429128811103, + "grad_norm": 0.47536125779151917, + "learning_rate": 9.200700802820754e-05, + "loss": 1.4683, + "step": 3519 + }, + { + "epoch": 0.19619865113427346, + "grad_norm": 0.546451985836029, + "learning_rate": 9.200217797727662e-05, + "loss": 1.8706, + "step": 3520 + }, + { + "epoch": 0.19625438938743658, + "grad_norm": 0.5166674256324768, + "learning_rate": 9.199734659428152e-05, + "loss": 1.5608, + "step": 3521 + }, + { + "epoch": 0.19631012764059974, + "grad_norm": 0.5700700879096985, + "learning_rate": 9.199251387937545e-05, + "loss": 1.7221, + "step": 3522 + }, + { + "epoch": 0.1963658658937629, + "grad_norm": 0.6089435815811157, + "learning_rate": 9.198767983271166e-05, + "loss": 1.7989, + "step": 3523 + }, + { + "epoch": 0.19642160414692603, + "grad_norm": 0.6160342693328857, + "learning_rate": 9.198284445444348e-05, + "loss": 2.0033, + "step": 3524 + }, + { + "epoch": 0.19647734240008918, + "grad_norm": 0.6272563338279724, + "learning_rate": 9.197800774472426e-05, + "loss": 1.9705, + "step": 3525 + }, + { + "epoch": 0.19653308065325234, + "grad_norm": 0.4671235680580139, + "learning_rate": 9.197316970370737e-05, + "loss": 1.0644, + "step": 3526 + }, + { + "epoch": 0.19658881890641547, + "grad_norm": 0.5911363959312439, + "learning_rate": 9.196833033154625e-05, + "loss": 1.662, + "step": 3527 + }, + { + "epoch": 0.19664455715957863, + "grad_norm": 0.552719235420227, + "learning_rate": 9.19634896283944e-05, + "loss": 1.7743, + "step": 3528 + }, + { + "epoch": 0.19670029541274175, + "grad_norm": 0.5252164006233215, + "learning_rate": 9.195864759440531e-05, + "loss": 1.7682, + "step": 3529 + }, + { + "epoch": 0.1967560336659049, + "grad_norm": 0.53560471534729, + "learning_rate": 9.195380422973257e-05, + "loss": 1.6731, + "step": 3530 + }, + { + "epoch": 0.19681177191906807, + "grad_norm": 0.5091952085494995, + "learning_rate": 9.194895953452976e-05, + "loss": 1.4618, + "step": 3531 + }, + { + "epoch": 0.1968675101722312, + "grad_norm": 0.5449403524398804, + "learning_rate": 9.194411350895053e-05, + "loss": 1.7007, + "step": 3532 + }, + { + "epoch": 0.19692324842539435, + "grad_norm": 0.5258320569992065, + "learning_rate": 9.193926615314857e-05, + "loss": 1.8571, + "step": 3533 + }, + { + "epoch": 0.19697898667855748, + "grad_norm": 0.5018019080162048, + "learning_rate": 9.193441746727762e-05, + "loss": 1.4968, + "step": 3534 + }, + { + "epoch": 0.19703472493172064, + "grad_norm": 0.570955753326416, + "learning_rate": 9.192956745149144e-05, + "loss": 1.8938, + "step": 3535 + }, + { + "epoch": 0.1970904631848838, + "grad_norm": 0.595371663570404, + "learning_rate": 9.192471610594384e-05, + "loss": 2.0865, + "step": 3536 + }, + { + "epoch": 0.19714620143804693, + "grad_norm": 0.5452008247375488, + "learning_rate": 9.191986343078868e-05, + "loss": 1.7354, + "step": 3537 + }, + { + "epoch": 0.19720193969121008, + "grad_norm": 0.5002971887588501, + "learning_rate": 9.191500942617988e-05, + "loss": 1.5218, + "step": 3538 + }, + { + "epoch": 0.1972576779443732, + "grad_norm": 0.5388283133506775, + "learning_rate": 9.191015409227134e-05, + "loss": 1.6676, + "step": 3539 + }, + { + "epoch": 0.19731341619753637, + "grad_norm": 0.5798291563987732, + "learning_rate": 9.190529742921707e-05, + "loss": 1.8602, + "step": 3540 + }, + { + "epoch": 0.19736915445069952, + "grad_norm": 0.5622314214706421, + "learning_rate": 9.190043943717111e-05, + "loss": 1.7324, + "step": 3541 + }, + { + "epoch": 0.19742489270386265, + "grad_norm": 0.5845619440078735, + "learning_rate": 9.189558011628749e-05, + "loss": 1.8098, + "step": 3542 + }, + { + "epoch": 0.1974806309570258, + "grad_norm": 0.5707986354827881, + "learning_rate": 9.189071946672033e-05, + "loss": 1.9953, + "step": 3543 + }, + { + "epoch": 0.19753636921018894, + "grad_norm": 0.5030776858329773, + "learning_rate": 9.18858574886238e-05, + "loss": 1.6697, + "step": 3544 + }, + { + "epoch": 0.1975921074633521, + "grad_norm": 0.5452118515968323, + "learning_rate": 9.188099418215208e-05, + "loss": 1.4443, + "step": 3545 + }, + { + "epoch": 0.19764784571651525, + "grad_norm": 0.5277875065803528, + "learning_rate": 9.187612954745942e-05, + "loss": 1.738, + "step": 3546 + }, + { + "epoch": 0.19770358396967838, + "grad_norm": 0.563870906829834, + "learning_rate": 9.187126358470006e-05, + "loss": 1.7746, + "step": 3547 + }, + { + "epoch": 0.19775932222284154, + "grad_norm": 0.5097183585166931, + "learning_rate": 9.186639629402836e-05, + "loss": 1.5869, + "step": 3548 + }, + { + "epoch": 0.1978150604760047, + "grad_norm": 0.5304349660873413, + "learning_rate": 9.186152767559866e-05, + "loss": 1.4967, + "step": 3549 + }, + { + "epoch": 0.19787079872916782, + "grad_norm": 0.5379878878593445, + "learning_rate": 9.185665772956539e-05, + "loss": 1.7457, + "step": 3550 + }, + { + "epoch": 0.19792653698233098, + "grad_norm": 0.5299242734909058, + "learning_rate": 9.185178645608297e-05, + "loss": 1.6194, + "step": 3551 + }, + { + "epoch": 0.1979822752354941, + "grad_norm": 0.5131285190582275, + "learning_rate": 9.184691385530588e-05, + "loss": 1.8616, + "step": 3552 + }, + { + "epoch": 0.19803801348865727, + "grad_norm": 0.5294276475906372, + "learning_rate": 9.184203992738869e-05, + "loss": 1.5835, + "step": 3553 + }, + { + "epoch": 0.19809375174182042, + "grad_norm": 0.544457197189331, + "learning_rate": 9.183716467248593e-05, + "loss": 1.6874, + "step": 3554 + }, + { + "epoch": 0.19814948999498355, + "grad_norm": 0.5258937478065491, + "learning_rate": 9.183228809075223e-05, + "loss": 1.7946, + "step": 3555 + }, + { + "epoch": 0.1982052282481467, + "grad_norm": 0.5388005971908569, + "learning_rate": 9.182741018234228e-05, + "loss": 1.6509, + "step": 3556 + }, + { + "epoch": 0.19826096650130984, + "grad_norm": 0.5726017951965332, + "learning_rate": 9.182253094741073e-05, + "loss": 1.6885, + "step": 3557 + }, + { + "epoch": 0.198316704754473, + "grad_norm": 0.5634879469871521, + "learning_rate": 9.181765038611234e-05, + "loss": 1.7431, + "step": 3558 + }, + { + "epoch": 0.19837244300763615, + "grad_norm": 0.5139129161834717, + "learning_rate": 9.18127684986019e-05, + "loss": 1.763, + "step": 3559 + }, + { + "epoch": 0.19842818126079928, + "grad_norm": 0.5589642524719238, + "learning_rate": 9.180788528503423e-05, + "loss": 1.9388, + "step": 3560 + }, + { + "epoch": 0.19848391951396244, + "grad_norm": 0.538282036781311, + "learning_rate": 9.18030007455642e-05, + "loss": 1.8491, + "step": 3561 + }, + { + "epoch": 0.19853965776712557, + "grad_norm": 0.5197616219520569, + "learning_rate": 9.179811488034671e-05, + "loss": 1.657, + "step": 3562 + }, + { + "epoch": 0.19859539602028872, + "grad_norm": 0.569980800151825, + "learning_rate": 9.17932276895367e-05, + "loss": 1.8632, + "step": 3563 + }, + { + "epoch": 0.19865113427345188, + "grad_norm": 0.6533870100975037, + "learning_rate": 9.17883391732892e-05, + "loss": 2.2768, + "step": 3564 + }, + { + "epoch": 0.198706872526615, + "grad_norm": 0.5272773504257202, + "learning_rate": 9.178344933175922e-05, + "loss": 1.7145, + "step": 3565 + }, + { + "epoch": 0.19876261077977816, + "grad_norm": 0.5350964069366455, + "learning_rate": 9.177855816510184e-05, + "loss": 1.6678, + "step": 3566 + }, + { + "epoch": 0.1988183490329413, + "grad_norm": 0.5308762788772583, + "learning_rate": 9.177366567347216e-05, + "loss": 1.6745, + "step": 3567 + }, + { + "epoch": 0.19887408728610445, + "grad_norm": 0.552905261516571, + "learning_rate": 9.176877185702539e-05, + "loss": 1.7337, + "step": 3568 + }, + { + "epoch": 0.1989298255392676, + "grad_norm": 0.5350809693336487, + "learning_rate": 9.17638767159167e-05, + "loss": 1.754, + "step": 3569 + }, + { + "epoch": 0.19898556379243074, + "grad_norm": 0.5393645167350769, + "learning_rate": 9.175898025030134e-05, + "loss": 1.6508, + "step": 3570 + }, + { + "epoch": 0.1990413020455939, + "grad_norm": 0.5781660079956055, + "learning_rate": 9.175408246033458e-05, + "loss": 1.7258, + "step": 3571 + }, + { + "epoch": 0.19909704029875705, + "grad_norm": 0.5230069160461426, + "learning_rate": 9.17491833461718e-05, + "loss": 1.5918, + "step": 3572 + }, + { + "epoch": 0.19915277855192018, + "grad_norm": 0.54449063539505, + "learning_rate": 9.174428290796833e-05, + "loss": 1.4328, + "step": 3573 + }, + { + "epoch": 0.19920851680508334, + "grad_norm": 0.5652233958244324, + "learning_rate": 9.173938114587957e-05, + "loss": 1.6627, + "step": 3574 + }, + { + "epoch": 0.19926425505824646, + "grad_norm": 0.5487927198410034, + "learning_rate": 9.173447806006102e-05, + "loss": 1.6238, + "step": 3575 + }, + { + "epoch": 0.19931999331140962, + "grad_norm": 0.5450085401535034, + "learning_rate": 9.172957365066815e-05, + "loss": 1.8033, + "step": 3576 + }, + { + "epoch": 0.19937573156457278, + "grad_norm": 0.5951147079467773, + "learning_rate": 9.17246679178565e-05, + "loss": 2.0117, + "step": 3577 + }, + { + "epoch": 0.1994314698177359, + "grad_norm": 0.5555893778800964, + "learning_rate": 9.171976086178164e-05, + "loss": 1.6994, + "step": 3578 + }, + { + "epoch": 0.19948720807089906, + "grad_norm": 0.4888277053833008, + "learning_rate": 9.171485248259924e-05, + "loss": 1.555, + "step": 3579 + }, + { + "epoch": 0.1995429463240622, + "grad_norm": 0.5293035507202148, + "learning_rate": 9.170994278046492e-05, + "loss": 1.7463, + "step": 3580 + }, + { + "epoch": 0.19959868457722535, + "grad_norm": 0.544032096862793, + "learning_rate": 9.17050317555344e-05, + "loss": 1.8112, + "step": 3581 + }, + { + "epoch": 0.1996544228303885, + "grad_norm": 0.5483592748641968, + "learning_rate": 9.170011940796341e-05, + "loss": 1.7906, + "step": 3582 + }, + { + "epoch": 0.19971016108355163, + "grad_norm": 0.6069881319999695, + "learning_rate": 9.16952057379078e-05, + "loss": 2.0624, + "step": 3583 + }, + { + "epoch": 0.1997658993367148, + "grad_norm": 0.5667694211006165, + "learning_rate": 9.169029074552333e-05, + "loss": 1.8233, + "step": 3584 + }, + { + "epoch": 0.19982163758987792, + "grad_norm": 0.5053529739379883, + "learning_rate": 9.168537443096592e-05, + "loss": 1.6512, + "step": 3585 + }, + { + "epoch": 0.19987737584304108, + "grad_norm": 0.5334288477897644, + "learning_rate": 9.168045679439149e-05, + "loss": 1.5675, + "step": 3586 + }, + { + "epoch": 0.19993311409620423, + "grad_norm": 0.61188805103302, + "learning_rate": 9.167553783595597e-05, + "loss": 1.8834, + "step": 3587 + }, + { + "epoch": 0.19998885234936736, + "grad_norm": 0.5691487193107605, + "learning_rate": 9.167061755581539e-05, + "loss": 1.7663, + "step": 3588 + }, + { + "epoch": 0.20004459060253052, + "grad_norm": 0.5586220026016235, + "learning_rate": 9.166569595412575e-05, + "loss": 1.8832, + "step": 3589 + }, + { + "epoch": 0.20010032885569365, + "grad_norm": 0.4987550675868988, + "learning_rate": 9.166077303104319e-05, + "loss": 1.661, + "step": 3590 + }, + { + "epoch": 0.2001560671088568, + "grad_norm": 0.5463746190071106, + "learning_rate": 9.165584878672378e-05, + "loss": 1.6764, + "step": 3591 + }, + { + "epoch": 0.20021180536201996, + "grad_norm": 0.5752919316291809, + "learning_rate": 9.165092322132374e-05, + "loss": 1.6847, + "step": 3592 + }, + { + "epoch": 0.2002675436151831, + "grad_norm": 0.5271925330162048, + "learning_rate": 9.164599633499925e-05, + "loss": 1.7428, + "step": 3593 + }, + { + "epoch": 0.20032328186834625, + "grad_norm": 0.4875536262989044, + "learning_rate": 9.164106812790657e-05, + "loss": 1.3011, + "step": 3594 + }, + { + "epoch": 0.2003790201215094, + "grad_norm": 0.5993346571922302, + "learning_rate": 9.1636138600202e-05, + "loss": 1.8065, + "step": 3595 + }, + { + "epoch": 0.20043475837467253, + "grad_norm": 0.5418604612350464, + "learning_rate": 9.163120775204187e-05, + "loss": 1.6812, + "step": 3596 + }, + { + "epoch": 0.2004904966278357, + "grad_norm": 0.5411487817764282, + "learning_rate": 9.162627558358255e-05, + "loss": 1.8109, + "step": 3597 + }, + { + "epoch": 0.20054623488099882, + "grad_norm": 0.5583702325820923, + "learning_rate": 9.162134209498046e-05, + "loss": 1.8183, + "step": 3598 + }, + { + "epoch": 0.20060197313416198, + "grad_norm": 0.6028481721878052, + "learning_rate": 9.161640728639207e-05, + "loss": 1.8642, + "step": 3599 + }, + { + "epoch": 0.20065771138732513, + "grad_norm": 0.5424187183380127, + "learning_rate": 9.161147115797388e-05, + "loss": 1.8178, + "step": 3600 + }, + { + "epoch": 0.20071344964048826, + "grad_norm": 0.6147588491439819, + "learning_rate": 9.160653370988243e-05, + "loss": 1.7343, + "step": 3601 + }, + { + "epoch": 0.20076918789365142, + "grad_norm": 0.5581020712852478, + "learning_rate": 9.160159494227434e-05, + "loss": 1.713, + "step": 3602 + }, + { + "epoch": 0.20082492614681455, + "grad_norm": 0.5363709330558777, + "learning_rate": 9.15966548553062e-05, + "loss": 1.8839, + "step": 3603 + }, + { + "epoch": 0.2008806643999777, + "grad_norm": 0.5731095671653748, + "learning_rate": 9.159171344913469e-05, + "loss": 1.8919, + "step": 3604 + }, + { + "epoch": 0.20093640265314086, + "grad_norm": 0.5256056785583496, + "learning_rate": 9.158677072391653e-05, + "loss": 1.7236, + "step": 3605 + }, + { + "epoch": 0.200992140906304, + "grad_norm": 0.5467107892036438, + "learning_rate": 9.158182667980846e-05, + "loss": 1.6551, + "step": 3606 + }, + { + "epoch": 0.20104787915946715, + "grad_norm": 0.5082773566246033, + "learning_rate": 9.157688131696729e-05, + "loss": 1.6537, + "step": 3607 + }, + { + "epoch": 0.20110361741263028, + "grad_norm": 0.5320789813995361, + "learning_rate": 9.157193463554986e-05, + "loss": 1.6112, + "step": 3608 + }, + { + "epoch": 0.20115935566579343, + "grad_norm": 0.5658825635910034, + "learning_rate": 9.156698663571305e-05, + "loss": 1.6377, + "step": 3609 + }, + { + "epoch": 0.2012150939189566, + "grad_norm": 0.593096137046814, + "learning_rate": 9.156203731761376e-05, + "loss": 1.7296, + "step": 3610 + }, + { + "epoch": 0.20127083217211972, + "grad_norm": 0.5300352573394775, + "learning_rate": 9.155708668140899e-05, + "loss": 1.4073, + "step": 3611 + }, + { + "epoch": 0.20132657042528287, + "grad_norm": 0.5179193019866943, + "learning_rate": 9.155213472725571e-05, + "loss": 1.5432, + "step": 3612 + }, + { + "epoch": 0.201382308678446, + "grad_norm": 0.5618082880973816, + "learning_rate": 9.154718145531098e-05, + "loss": 1.79, + "step": 3613 + }, + { + "epoch": 0.20143804693160916, + "grad_norm": 0.47643256187438965, + "learning_rate": 9.15422268657319e-05, + "loss": 1.4084, + "step": 3614 + }, + { + "epoch": 0.20149378518477232, + "grad_norm": 0.6415194272994995, + "learning_rate": 9.15372709586756e-05, + "loss": 1.9196, + "step": 3615 + }, + { + "epoch": 0.20154952343793545, + "grad_norm": 0.5599740147590637, + "learning_rate": 9.153231373429922e-05, + "loss": 1.8508, + "step": 3616 + }, + { + "epoch": 0.2016052616910986, + "grad_norm": 0.5777899622917175, + "learning_rate": 9.152735519276002e-05, + "loss": 1.8367, + "step": 3617 + }, + { + "epoch": 0.20166099994426176, + "grad_norm": 0.5653935670852661, + "learning_rate": 9.152239533421523e-05, + "loss": 1.5819, + "step": 3618 + }, + { + "epoch": 0.2017167381974249, + "grad_norm": 0.5558584928512573, + "learning_rate": 9.151743415882215e-05, + "loss": 1.8245, + "step": 3619 + }, + { + "epoch": 0.20177247645058805, + "grad_norm": 0.5481976866722107, + "learning_rate": 9.151247166673811e-05, + "loss": 1.6422, + "step": 3620 + }, + { + "epoch": 0.20182821470375117, + "grad_norm": 0.49504461884498596, + "learning_rate": 9.150750785812052e-05, + "loss": 1.5992, + "step": 3621 + }, + { + "epoch": 0.20188395295691433, + "grad_norm": 0.6056009531021118, + "learning_rate": 9.150254273312677e-05, + "loss": 1.7729, + "step": 3622 + }, + { + "epoch": 0.2019396912100775, + "grad_norm": 0.5418253540992737, + "learning_rate": 9.149757629191436e-05, + "loss": 1.8279, + "step": 3623 + }, + { + "epoch": 0.20199542946324062, + "grad_norm": 0.5427140593528748, + "learning_rate": 9.149260853464077e-05, + "loss": 1.6135, + "step": 3624 + }, + { + "epoch": 0.20205116771640377, + "grad_norm": 0.5552391409873962, + "learning_rate": 9.148763946146354e-05, + "loss": 1.6617, + "step": 3625 + }, + { + "epoch": 0.2021069059695669, + "grad_norm": 0.5886726975440979, + "learning_rate": 9.148266907254031e-05, + "loss": 1.9072, + "step": 3626 + }, + { + "epoch": 0.20216264422273006, + "grad_norm": 0.587967038154602, + "learning_rate": 9.147769736802864e-05, + "loss": 1.7807, + "step": 3627 + }, + { + "epoch": 0.20221838247589322, + "grad_norm": 0.5265384912490845, + "learning_rate": 9.147272434808627e-05, + "loss": 1.5633, + "step": 3628 + }, + { + "epoch": 0.20227412072905634, + "grad_norm": 0.5282620191574097, + "learning_rate": 9.146775001287088e-05, + "loss": 1.579, + "step": 3629 + }, + { + "epoch": 0.2023298589822195, + "grad_norm": 0.5758345723152161, + "learning_rate": 9.146277436254022e-05, + "loss": 1.8881, + "step": 3630 + }, + { + "epoch": 0.20238559723538263, + "grad_norm": 0.5375788807868958, + "learning_rate": 9.145779739725213e-05, + "loss": 1.7915, + "step": 3631 + }, + { + "epoch": 0.2024413354885458, + "grad_norm": 0.5047256350517273, + "learning_rate": 9.14528191171644e-05, + "loss": 1.8006, + "step": 3632 + }, + { + "epoch": 0.20249707374170894, + "grad_norm": 0.5424186587333679, + "learning_rate": 9.144783952243493e-05, + "loss": 1.5753, + "step": 3633 + }, + { + "epoch": 0.20255281199487207, + "grad_norm": 0.5288758277893066, + "learning_rate": 9.144285861322166e-05, + "loss": 1.7276, + "step": 3634 + }, + { + "epoch": 0.20260855024803523, + "grad_norm": 0.638491690158844, + "learning_rate": 9.143787638968254e-05, + "loss": 1.8898, + "step": 3635 + }, + { + "epoch": 0.20266428850119836, + "grad_norm": 0.5804757475852966, + "learning_rate": 9.143289285197558e-05, + "loss": 1.9973, + "step": 3636 + }, + { + "epoch": 0.20272002675436152, + "grad_norm": 0.6197081804275513, + "learning_rate": 9.142790800025883e-05, + "loss": 1.7459, + "step": 3637 + }, + { + "epoch": 0.20277576500752467, + "grad_norm": 0.6034955382347107, + "learning_rate": 9.142292183469039e-05, + "loss": 1.9412, + "step": 3638 + }, + { + "epoch": 0.2028315032606878, + "grad_norm": 0.5404736995697021, + "learning_rate": 9.141793435542836e-05, + "loss": 1.6073, + "step": 3639 + }, + { + "epoch": 0.20288724151385096, + "grad_norm": 0.48670318722724915, + "learning_rate": 9.141294556263096e-05, + "loss": 1.5109, + "step": 3640 + }, + { + "epoch": 0.20294297976701411, + "grad_norm": 0.5840024948120117, + "learning_rate": 9.140795545645636e-05, + "loss": 1.7593, + "step": 3641 + }, + { + "epoch": 0.20299871802017724, + "grad_norm": 0.5371603965759277, + "learning_rate": 9.140296403706284e-05, + "loss": 1.6055, + "step": 3642 + }, + { + "epoch": 0.2030544562733404, + "grad_norm": 1.0509992837905884, + "learning_rate": 9.13979713046087e-05, + "loss": 2.0113, + "step": 3643 + }, + { + "epoch": 0.20311019452650353, + "grad_norm": 0.49479854106903076, + "learning_rate": 9.139297725925229e-05, + "loss": 1.516, + "step": 3644 + }, + { + "epoch": 0.20316593277966669, + "grad_norm": 0.5389636754989624, + "learning_rate": 9.138798190115196e-05, + "loss": 1.9002, + "step": 3645 + }, + { + "epoch": 0.20322167103282984, + "grad_norm": 0.5524114370346069, + "learning_rate": 9.138298523046617e-05, + "loss": 1.6288, + "step": 3646 + }, + { + "epoch": 0.20327740928599297, + "grad_norm": 0.49681249260902405, + "learning_rate": 9.137798724735336e-05, + "loss": 1.4397, + "step": 3647 + }, + { + "epoch": 0.20333314753915613, + "grad_norm": 0.6418421268463135, + "learning_rate": 9.137298795197204e-05, + "loss": 2.1691, + "step": 3648 + }, + { + "epoch": 0.20338888579231926, + "grad_norm": 0.5589434504508972, + "learning_rate": 9.136798734448077e-05, + "loss": 1.781, + "step": 3649 + }, + { + "epoch": 0.20344462404548241, + "grad_norm": 0.5447176694869995, + "learning_rate": 9.136298542503814e-05, + "loss": 1.6205, + "step": 3650 + }, + { + "epoch": 0.20350036229864557, + "grad_norm": 0.5343891978263855, + "learning_rate": 9.135798219380276e-05, + "loss": 1.7727, + "step": 3651 + }, + { + "epoch": 0.2035561005518087, + "grad_norm": 0.5254631638526917, + "learning_rate": 9.135297765093333e-05, + "loss": 1.7057, + "step": 3652 + }, + { + "epoch": 0.20361183880497186, + "grad_norm": 0.5393111109733582, + "learning_rate": 9.134797179658854e-05, + "loss": 1.7132, + "step": 3653 + }, + { + "epoch": 0.20366757705813499, + "grad_norm": 0.5616254806518555, + "learning_rate": 9.134296463092717e-05, + "loss": 1.9128, + "step": 3654 + }, + { + "epoch": 0.20372331531129814, + "grad_norm": 0.5558052659034729, + "learning_rate": 9.133795615410801e-05, + "loss": 1.6986, + "step": 3655 + }, + { + "epoch": 0.2037790535644613, + "grad_norm": 0.5616979002952576, + "learning_rate": 9.13329463662899e-05, + "loss": 1.9381, + "step": 3656 + }, + { + "epoch": 0.20383479181762443, + "grad_norm": 0.5200750827789307, + "learning_rate": 9.132793526763171e-05, + "loss": 1.6176, + "step": 3657 + }, + { + "epoch": 0.20389053007078758, + "grad_norm": 0.5086760520935059, + "learning_rate": 9.132292285829237e-05, + "loss": 1.5035, + "step": 3658 + }, + { + "epoch": 0.20394626832395074, + "grad_norm": 0.5122929215431213, + "learning_rate": 9.131790913843086e-05, + "loss": 1.6288, + "step": 3659 + }, + { + "epoch": 0.20400200657711387, + "grad_norm": 0.5770255923271179, + "learning_rate": 9.131289410820616e-05, + "loss": 1.71, + "step": 3660 + }, + { + "epoch": 0.20405774483027703, + "grad_norm": 0.5811052322387695, + "learning_rate": 9.130787776777734e-05, + "loss": 1.9395, + "step": 3661 + }, + { + "epoch": 0.20411348308344016, + "grad_norm": 0.5475841164588928, + "learning_rate": 9.130286011730347e-05, + "loss": 1.8358, + "step": 3662 + }, + { + "epoch": 0.2041692213366033, + "grad_norm": 0.5167744755744934, + "learning_rate": 9.129784115694369e-05, + "loss": 1.602, + "step": 3663 + }, + { + "epoch": 0.20422495958976647, + "grad_norm": 0.5313771963119507, + "learning_rate": 9.129282088685718e-05, + "loss": 1.7868, + "step": 3664 + }, + { + "epoch": 0.2042806978429296, + "grad_norm": 0.5149242877960205, + "learning_rate": 9.128779930720313e-05, + "loss": 1.6943, + "step": 3665 + }, + { + "epoch": 0.20433643609609276, + "grad_norm": 0.5548785924911499, + "learning_rate": 9.128277641814082e-05, + "loss": 1.9083, + "step": 3666 + }, + { + "epoch": 0.20439217434925588, + "grad_norm": 0.5865716338157654, + "learning_rate": 9.127775221982954e-05, + "loss": 1.9183, + "step": 3667 + }, + { + "epoch": 0.20444791260241904, + "grad_norm": 0.5036227703094482, + "learning_rate": 9.127272671242861e-05, + "loss": 1.6097, + "step": 3668 + }, + { + "epoch": 0.2045036508555822, + "grad_norm": 0.5178596377372742, + "learning_rate": 9.126769989609745e-05, + "loss": 1.7121, + "step": 3669 + }, + { + "epoch": 0.20455938910874533, + "grad_norm": 0.585189938545227, + "learning_rate": 9.126267177099543e-05, + "loss": 1.8327, + "step": 3670 + }, + { + "epoch": 0.20461512736190848, + "grad_norm": 0.5853554606437683, + "learning_rate": 9.125764233728206e-05, + "loss": 1.9047, + "step": 3671 + }, + { + "epoch": 0.2046708656150716, + "grad_norm": 0.5730652213096619, + "learning_rate": 9.125261159511682e-05, + "loss": 1.8311, + "step": 3672 + }, + { + "epoch": 0.20472660386823477, + "grad_norm": 0.5045105814933777, + "learning_rate": 9.124757954465925e-05, + "loss": 1.5241, + "step": 3673 + }, + { + "epoch": 0.20478234212139793, + "grad_norm": 0.5725773572921753, + "learning_rate": 9.124254618606897e-05, + "loss": 1.6949, + "step": 3674 + }, + { + "epoch": 0.20483808037456105, + "grad_norm": 0.5756915211677551, + "learning_rate": 9.123751151950557e-05, + "loss": 1.8553, + "step": 3675 + }, + { + "epoch": 0.2048938186277242, + "grad_norm": 0.5354653000831604, + "learning_rate": 9.123247554512873e-05, + "loss": 1.7906, + "step": 3676 + }, + { + "epoch": 0.20494955688088734, + "grad_norm": 0.5941489934921265, + "learning_rate": 9.122743826309819e-05, + "loss": 1.7721, + "step": 3677 + }, + { + "epoch": 0.2050052951340505, + "grad_norm": 0.5832119584083557, + "learning_rate": 9.122239967357366e-05, + "loss": 1.9673, + "step": 3678 + }, + { + "epoch": 0.20506103338721365, + "grad_norm": 0.6178232431411743, + "learning_rate": 9.121735977671495e-05, + "loss": 2.0516, + "step": 3679 + }, + { + "epoch": 0.20511677164037678, + "grad_norm": 0.5315244197845459, + "learning_rate": 9.121231857268191e-05, + "loss": 1.5958, + "step": 3680 + }, + { + "epoch": 0.20517250989353994, + "grad_norm": 0.5662999153137207, + "learning_rate": 9.120727606163442e-05, + "loss": 1.6989, + "step": 3681 + }, + { + "epoch": 0.2052282481467031, + "grad_norm": 0.49450522661209106, + "learning_rate": 9.120223224373238e-05, + "loss": 1.4492, + "step": 3682 + }, + { + "epoch": 0.20528398639986623, + "grad_norm": 0.572935163974762, + "learning_rate": 9.119718711913575e-05, + "loss": 1.6674, + "step": 3683 + }, + { + "epoch": 0.20533972465302938, + "grad_norm": 0.5418963432312012, + "learning_rate": 9.119214068800456e-05, + "loss": 1.6326, + "step": 3684 + }, + { + "epoch": 0.2053954629061925, + "grad_norm": 0.5970882773399353, + "learning_rate": 9.118709295049883e-05, + "loss": 1.9069, + "step": 3685 + }, + { + "epoch": 0.20545120115935567, + "grad_norm": 0.5530537962913513, + "learning_rate": 9.118204390677863e-05, + "loss": 1.6096, + "step": 3686 + }, + { + "epoch": 0.20550693941251882, + "grad_norm": 0.5641506314277649, + "learning_rate": 9.117699355700412e-05, + "loss": 1.7118, + "step": 3687 + }, + { + "epoch": 0.20556267766568195, + "grad_norm": 0.6086058616638184, + "learning_rate": 9.117194190133545e-05, + "loss": 1.713, + "step": 3688 + }, + { + "epoch": 0.2056184159188451, + "grad_norm": 0.577290952205658, + "learning_rate": 9.116688893993284e-05, + "loss": 1.8858, + "step": 3689 + }, + { + "epoch": 0.20567415417200824, + "grad_norm": 0.5066075325012207, + "learning_rate": 9.116183467295651e-05, + "loss": 1.5922, + "step": 3690 + }, + { + "epoch": 0.2057298924251714, + "grad_norm": 0.5287824273109436, + "learning_rate": 9.115677910056681e-05, + "loss": 1.4441, + "step": 3691 + }, + { + "epoch": 0.20578563067833455, + "grad_norm": 0.62456214427948, + "learning_rate": 9.115172222292401e-05, + "loss": 1.9545, + "step": 3692 + }, + { + "epoch": 0.20584136893149768, + "grad_norm": 0.5801160335540771, + "learning_rate": 9.114666404018853e-05, + "loss": 2.0095, + "step": 3693 + }, + { + "epoch": 0.20589710718466084, + "grad_norm": 0.5162177085876465, + "learning_rate": 9.114160455252074e-05, + "loss": 1.7295, + "step": 3694 + }, + { + "epoch": 0.20595284543782397, + "grad_norm": 0.5912075042724609, + "learning_rate": 9.113654376008115e-05, + "loss": 1.787, + "step": 3695 + }, + { + "epoch": 0.20600858369098712, + "grad_norm": 0.5578693747520447, + "learning_rate": 9.113148166303023e-05, + "loss": 1.6167, + "step": 3696 + }, + { + "epoch": 0.20606432194415028, + "grad_norm": 0.5576518177986145, + "learning_rate": 9.112641826152853e-05, + "loss": 1.7855, + "step": 3697 + }, + { + "epoch": 0.2061200601973134, + "grad_norm": 0.5475178360939026, + "learning_rate": 9.11213535557366e-05, + "loss": 1.7013, + "step": 3698 + }, + { + "epoch": 0.20617579845047657, + "grad_norm": 0.5434138178825378, + "learning_rate": 9.111628754581512e-05, + "loss": 1.7804, + "step": 3699 + }, + { + "epoch": 0.2062315367036397, + "grad_norm": 0.5596892237663269, + "learning_rate": 9.111122023192471e-05, + "loss": 1.8347, + "step": 3700 + }, + { + "epoch": 0.20628727495680285, + "grad_norm": 0.5505380034446716, + "learning_rate": 9.110615161422609e-05, + "loss": 1.878, + "step": 3701 + }, + { + "epoch": 0.206343013209966, + "grad_norm": 0.6178278923034668, + "learning_rate": 9.110108169288001e-05, + "loss": 1.7626, + "step": 3702 + }, + { + "epoch": 0.20639875146312914, + "grad_norm": 0.5460211038589478, + "learning_rate": 9.109601046804726e-05, + "loss": 1.8064, + "step": 3703 + }, + { + "epoch": 0.2064544897162923, + "grad_norm": 0.5765804052352905, + "learning_rate": 9.109093793988865e-05, + "loss": 1.8228, + "step": 3704 + }, + { + "epoch": 0.20651022796945545, + "grad_norm": 0.5335574746131897, + "learning_rate": 9.108586410856508e-05, + "loss": 1.8011, + "step": 3705 + }, + { + "epoch": 0.20656596622261858, + "grad_norm": 0.5536273717880249, + "learning_rate": 9.108078897423743e-05, + "loss": 1.8751, + "step": 3706 + }, + { + "epoch": 0.20662170447578174, + "grad_norm": 0.5405413508415222, + "learning_rate": 9.107571253706668e-05, + "loss": 1.8607, + "step": 3707 + }, + { + "epoch": 0.20667744272894487, + "grad_norm": 0.5240110158920288, + "learning_rate": 9.107063479721383e-05, + "loss": 1.4375, + "step": 3708 + }, + { + "epoch": 0.20673318098210802, + "grad_norm": 0.4756803512573242, + "learning_rate": 9.106555575483988e-05, + "loss": 1.3254, + "step": 3709 + }, + { + "epoch": 0.20678891923527118, + "grad_norm": 0.5738046765327454, + "learning_rate": 9.106047541010593e-05, + "loss": 1.776, + "step": 3710 + }, + { + "epoch": 0.2068446574884343, + "grad_norm": 0.5442799925804138, + "learning_rate": 9.105539376317312e-05, + "loss": 1.7099, + "step": 3711 + }, + { + "epoch": 0.20690039574159746, + "grad_norm": 0.5695345401763916, + "learning_rate": 9.105031081420259e-05, + "loss": 1.6337, + "step": 3712 + }, + { + "epoch": 0.2069561339947606, + "grad_norm": 0.4725694954395294, + "learning_rate": 9.104522656335553e-05, + "loss": 1.4172, + "step": 3713 + }, + { + "epoch": 0.20701187224792375, + "grad_norm": 0.5137088894844055, + "learning_rate": 9.10401410107932e-05, + "loss": 1.6826, + "step": 3714 + }, + { + "epoch": 0.2070676105010869, + "grad_norm": 0.5813738703727722, + "learning_rate": 9.103505415667686e-05, + "loss": 1.9881, + "step": 3715 + }, + { + "epoch": 0.20712334875425004, + "grad_norm": 0.5776458382606506, + "learning_rate": 9.102996600116786e-05, + "loss": 1.8194, + "step": 3716 + }, + { + "epoch": 0.2071790870074132, + "grad_norm": 0.6059629917144775, + "learning_rate": 9.102487654442758e-05, + "loss": 1.9822, + "step": 3717 + }, + { + "epoch": 0.20723482526057632, + "grad_norm": 0.5408186912536621, + "learning_rate": 9.101978578661738e-05, + "loss": 1.8422, + "step": 3718 + }, + { + "epoch": 0.20729056351373948, + "grad_norm": 0.5199152231216431, + "learning_rate": 9.101469372789874e-05, + "loss": 1.6269, + "step": 3719 + }, + { + "epoch": 0.20734630176690264, + "grad_norm": 0.4990878105163574, + "learning_rate": 9.100960036843317e-05, + "loss": 1.6431, + "step": 3720 + }, + { + "epoch": 0.20740204002006576, + "grad_norm": 0.539283812046051, + "learning_rate": 9.100450570838216e-05, + "loss": 1.6332, + "step": 3721 + }, + { + "epoch": 0.20745777827322892, + "grad_norm": 0.4963357150554657, + "learning_rate": 9.09994097479073e-05, + "loss": 1.4083, + "step": 3722 + }, + { + "epoch": 0.20751351652639205, + "grad_norm": 0.5257975459098816, + "learning_rate": 9.099431248717022e-05, + "loss": 1.673, + "step": 3723 + }, + { + "epoch": 0.2075692547795552, + "grad_norm": 0.5869825482368469, + "learning_rate": 9.098921392633255e-05, + "loss": 1.8618, + "step": 3724 + }, + { + "epoch": 0.20762499303271836, + "grad_norm": 0.5818216800689697, + "learning_rate": 9.0984114065556e-05, + "loss": 1.761, + "step": 3725 + }, + { + "epoch": 0.2076807312858815, + "grad_norm": 0.5281986594200134, + "learning_rate": 9.097901290500231e-05, + "loss": 1.5652, + "step": 3726 + }, + { + "epoch": 0.20773646953904465, + "grad_norm": 0.5425719618797302, + "learning_rate": 9.097391044483325e-05, + "loss": 1.6899, + "step": 3727 + }, + { + "epoch": 0.2077922077922078, + "grad_norm": 0.5924318432807922, + "learning_rate": 9.096880668521066e-05, + "loss": 2.0674, + "step": 3728 + }, + { + "epoch": 0.20784794604537093, + "grad_norm": 0.5444379448890686, + "learning_rate": 9.096370162629637e-05, + "loss": 1.8427, + "step": 3729 + }, + { + "epoch": 0.2079036842985341, + "grad_norm": 0.5292965769767761, + "learning_rate": 9.09585952682523e-05, + "loss": 1.6487, + "step": 3730 + }, + { + "epoch": 0.20795942255169722, + "grad_norm": 0.5337923765182495, + "learning_rate": 9.09534876112404e-05, + "loss": 1.7153, + "step": 3731 + }, + { + "epoch": 0.20801516080486038, + "grad_norm": 0.5366414785385132, + "learning_rate": 9.094837865542265e-05, + "loss": 1.7336, + "step": 3732 + }, + { + "epoch": 0.20807089905802353, + "grad_norm": 0.5158184766769409, + "learning_rate": 9.094326840096106e-05, + "loss": 1.4747, + "step": 3733 + }, + { + "epoch": 0.20812663731118666, + "grad_norm": 0.5793300867080688, + "learning_rate": 9.093815684801772e-05, + "loss": 1.67, + "step": 3734 + }, + { + "epoch": 0.20818237556434982, + "grad_norm": 0.57293701171875, + "learning_rate": 9.093304399675474e-05, + "loss": 1.8801, + "step": 3735 + }, + { + "epoch": 0.20823811381751295, + "grad_norm": 0.514213502407074, + "learning_rate": 9.092792984733425e-05, + "loss": 1.5878, + "step": 3736 + }, + { + "epoch": 0.2082938520706761, + "grad_norm": 0.5890586376190186, + "learning_rate": 9.092281439991846e-05, + "loss": 1.9247, + "step": 3737 + }, + { + "epoch": 0.20834959032383926, + "grad_norm": 0.5602766275405884, + "learning_rate": 9.091769765466959e-05, + "loss": 1.7421, + "step": 3738 + }, + { + "epoch": 0.2084053285770024, + "grad_norm": 0.586161196231842, + "learning_rate": 9.091257961174991e-05, + "loss": 2.0567, + "step": 3739 + }, + { + "epoch": 0.20846106683016555, + "grad_norm": 0.5134695768356323, + "learning_rate": 9.090746027132175e-05, + "loss": 1.6464, + "step": 3740 + }, + { + "epoch": 0.20851680508332868, + "grad_norm": 0.5447134375572205, + "learning_rate": 9.090233963354746e-05, + "loss": 1.8313, + "step": 3741 + }, + { + "epoch": 0.20857254333649183, + "grad_norm": 0.5118534564971924, + "learning_rate": 9.089721769858943e-05, + "loss": 1.629, + "step": 3742 + }, + { + "epoch": 0.208628281589655, + "grad_norm": 0.5482544898986816, + "learning_rate": 9.08920944666101e-05, + "loss": 1.6353, + "step": 3743 + }, + { + "epoch": 0.20868401984281812, + "grad_norm": 0.542334258556366, + "learning_rate": 9.088696993777194e-05, + "loss": 1.6882, + "step": 3744 + }, + { + "epoch": 0.20873975809598128, + "grad_norm": 0.527746319770813, + "learning_rate": 9.08818441122375e-05, + "loss": 1.5986, + "step": 3745 + }, + { + "epoch": 0.2087954963491444, + "grad_norm": 0.5480045080184937, + "learning_rate": 9.08767169901693e-05, + "loss": 1.6445, + "step": 3746 + }, + { + "epoch": 0.20885123460230756, + "grad_norm": 0.5573908686637878, + "learning_rate": 9.087158857172999e-05, + "loss": 1.851, + "step": 3747 + }, + { + "epoch": 0.20890697285547072, + "grad_norm": 0.5698862671852112, + "learning_rate": 9.086645885708218e-05, + "loss": 1.6359, + "step": 3748 + }, + { + "epoch": 0.20896271110863385, + "grad_norm": 0.557510256767273, + "learning_rate": 9.086132784638857e-05, + "loss": 1.7563, + "step": 3749 + }, + { + "epoch": 0.209018449361797, + "grad_norm": 0.5576832890510559, + "learning_rate": 9.085619553981187e-05, + "loss": 1.8104, + "step": 3750 + }, + { + "epoch": 0.20907418761496016, + "grad_norm": 0.5342584848403931, + "learning_rate": 9.085106193751485e-05, + "loss": 1.4561, + "step": 3751 + }, + { + "epoch": 0.2091299258681233, + "grad_norm": 0.5547382235527039, + "learning_rate": 9.084592703966033e-05, + "loss": 1.6986, + "step": 3752 + }, + { + "epoch": 0.20918566412128645, + "grad_norm": 0.5614180564880371, + "learning_rate": 9.084079084641115e-05, + "loss": 1.7837, + "step": 3753 + }, + { + "epoch": 0.20924140237444958, + "grad_norm": 0.5065221786499023, + "learning_rate": 9.083565335793021e-05, + "loss": 1.7262, + "step": 3754 + }, + { + "epoch": 0.20929714062761273, + "grad_norm": 0.5504621863365173, + "learning_rate": 9.083051457438043e-05, + "loss": 1.7848, + "step": 3755 + }, + { + "epoch": 0.2093528788807759, + "grad_norm": 0.5882393717765808, + "learning_rate": 9.082537449592479e-05, + "loss": 2.0356, + "step": 3756 + }, + { + "epoch": 0.20940861713393902, + "grad_norm": 0.6157543063163757, + "learning_rate": 9.08202331227263e-05, + "loss": 1.9959, + "step": 3757 + }, + { + "epoch": 0.20946435538710217, + "grad_norm": 0.5493510961532593, + "learning_rate": 9.0815090454948e-05, + "loss": 1.7899, + "step": 3758 + }, + { + "epoch": 0.2095200936402653, + "grad_norm": 0.5107924938201904, + "learning_rate": 9.0809946492753e-05, + "loss": 1.4062, + "step": 3759 + }, + { + "epoch": 0.20957583189342846, + "grad_norm": 0.5571010112762451, + "learning_rate": 9.080480123630444e-05, + "loss": 1.6807, + "step": 3760 + }, + { + "epoch": 0.20963157014659162, + "grad_norm": 0.5510861277580261, + "learning_rate": 9.07996546857655e-05, + "loss": 1.9714, + "step": 3761 + }, + { + "epoch": 0.20968730839975475, + "grad_norm": 0.531609296798706, + "learning_rate": 9.07945068412994e-05, + "loss": 1.7811, + "step": 3762 + }, + { + "epoch": 0.2097430466529179, + "grad_norm": 0.5203907489776611, + "learning_rate": 9.078935770306938e-05, + "loss": 1.7003, + "step": 3763 + }, + { + "epoch": 0.20979878490608103, + "grad_norm": 0.5677714347839355, + "learning_rate": 9.078420727123874e-05, + "loss": 2.0188, + "step": 3764 + }, + { + "epoch": 0.2098545231592442, + "grad_norm": 0.5568066239356995, + "learning_rate": 9.077905554597086e-05, + "loss": 1.7745, + "step": 3765 + }, + { + "epoch": 0.20991026141240735, + "grad_norm": 0.564201831817627, + "learning_rate": 9.077390252742907e-05, + "loss": 1.7723, + "step": 3766 + }, + { + "epoch": 0.20996599966557047, + "grad_norm": 0.569828450679779, + "learning_rate": 9.076874821577683e-05, + "loss": 1.7731, + "step": 3767 + }, + { + "epoch": 0.21002173791873363, + "grad_norm": 0.5601812601089478, + "learning_rate": 9.07635926111776e-05, + "loss": 1.6495, + "step": 3768 + }, + { + "epoch": 0.21007747617189676, + "grad_norm": 0.6098621487617493, + "learning_rate": 9.075843571379488e-05, + "loss": 1.9732, + "step": 3769 + }, + { + "epoch": 0.21013321442505992, + "grad_norm": 0.5688888430595398, + "learning_rate": 9.075327752379221e-05, + "loss": 1.8381, + "step": 3770 + }, + { + "epoch": 0.21018895267822307, + "grad_norm": 0.5635893940925598, + "learning_rate": 9.074811804133318e-05, + "loss": 1.7662, + "step": 3771 + }, + { + "epoch": 0.2102446909313862, + "grad_norm": 0.5132915377616882, + "learning_rate": 9.074295726658144e-05, + "loss": 1.6434, + "step": 3772 + }, + { + "epoch": 0.21030042918454936, + "grad_norm": 0.5504310727119446, + "learning_rate": 9.073779519970065e-05, + "loss": 1.7831, + "step": 3773 + }, + { + "epoch": 0.21035616743771252, + "grad_norm": 0.5861356258392334, + "learning_rate": 9.07326318408545e-05, + "loss": 1.9085, + "step": 3774 + }, + { + "epoch": 0.21041190569087564, + "grad_norm": 0.5746229887008667, + "learning_rate": 9.072746719020676e-05, + "loss": 1.851, + "step": 3775 + }, + { + "epoch": 0.2104676439440388, + "grad_norm": 0.5618278980255127, + "learning_rate": 9.072230124792121e-05, + "loss": 1.9007, + "step": 3776 + }, + { + "epoch": 0.21052338219720193, + "grad_norm": 0.5574671030044556, + "learning_rate": 9.07171340141617e-05, + "loss": 1.7664, + "step": 3777 + }, + { + "epoch": 0.2105791204503651, + "grad_norm": 0.5418394207954407, + "learning_rate": 9.071196548909208e-05, + "loss": 1.5912, + "step": 3778 + }, + { + "epoch": 0.21063485870352824, + "grad_norm": 0.5579066872596741, + "learning_rate": 9.070679567287631e-05, + "loss": 1.8595, + "step": 3779 + }, + { + "epoch": 0.21069059695669137, + "grad_norm": 0.5038254261016846, + "learning_rate": 9.07016245656783e-05, + "loss": 1.5864, + "step": 3780 + }, + { + "epoch": 0.21074633520985453, + "grad_norm": 0.5985908508300781, + "learning_rate": 9.069645216766208e-05, + "loss": 1.8166, + "step": 3781 + }, + { + "epoch": 0.21080207346301766, + "grad_norm": 0.5343535542488098, + "learning_rate": 9.069127847899166e-05, + "loss": 1.7482, + "step": 3782 + }, + { + "epoch": 0.21085781171618082, + "grad_norm": 0.513039231300354, + "learning_rate": 9.068610349983113e-05, + "loss": 1.7065, + "step": 3783 + }, + { + "epoch": 0.21091354996934397, + "grad_norm": 0.5761904716491699, + "learning_rate": 9.068092723034462e-05, + "loss": 1.7781, + "step": 3784 + }, + { + "epoch": 0.2109692882225071, + "grad_norm": 0.5832051634788513, + "learning_rate": 9.067574967069628e-05, + "loss": 1.7871, + "step": 3785 + }, + { + "epoch": 0.21102502647567026, + "grad_norm": 0.9756948947906494, + "learning_rate": 9.067057082105032e-05, + "loss": 1.9512, + "step": 3786 + }, + { + "epoch": 0.2110807647288334, + "grad_norm": 0.5692908763885498, + "learning_rate": 9.066539068157098e-05, + "loss": 1.4585, + "step": 3787 + }, + { + "epoch": 0.21113650298199654, + "grad_norm": 0.5954088568687439, + "learning_rate": 9.066020925242256e-05, + "loss": 1.9236, + "step": 3788 + }, + { + "epoch": 0.2111922412351597, + "grad_norm": 0.5660640597343445, + "learning_rate": 9.065502653376935e-05, + "loss": 1.67, + "step": 3789 + }, + { + "epoch": 0.21124797948832283, + "grad_norm": 0.5779823064804077, + "learning_rate": 9.064984252577573e-05, + "loss": 1.8769, + "step": 3790 + }, + { + "epoch": 0.21130371774148599, + "grad_norm": 0.5380722880363464, + "learning_rate": 9.064465722860611e-05, + "loss": 1.6658, + "step": 3791 + }, + { + "epoch": 0.21135945599464911, + "grad_norm": 0.5925493836402893, + "learning_rate": 9.063947064242495e-05, + "loss": 1.7003, + "step": 3792 + }, + { + "epoch": 0.21141519424781227, + "grad_norm": 0.5475820899009705, + "learning_rate": 9.063428276739671e-05, + "loss": 1.7658, + "step": 3793 + }, + { + "epoch": 0.21147093250097543, + "grad_norm": 0.5608733296394348, + "learning_rate": 9.062909360368595e-05, + "loss": 1.7443, + "step": 3794 + }, + { + "epoch": 0.21152667075413856, + "grad_norm": 0.5024067163467407, + "learning_rate": 9.062390315145723e-05, + "loss": 1.4051, + "step": 3795 + }, + { + "epoch": 0.2115824090073017, + "grad_norm": 0.5922258496284485, + "learning_rate": 9.061871141087515e-05, + "loss": 1.6788, + "step": 3796 + }, + { + "epoch": 0.21163814726046487, + "grad_norm": 0.5388537645339966, + "learning_rate": 9.061351838210434e-05, + "loss": 1.7306, + "step": 3797 + }, + { + "epoch": 0.211693885513628, + "grad_norm": 0.5710194706916809, + "learning_rate": 9.060832406530955e-05, + "loss": 1.7759, + "step": 3798 + }, + { + "epoch": 0.21174962376679116, + "grad_norm": 0.5648775696754456, + "learning_rate": 9.060312846065548e-05, + "loss": 1.8155, + "step": 3799 + }, + { + "epoch": 0.21180536201995429, + "grad_norm": 0.5653148293495178, + "learning_rate": 9.059793156830691e-05, + "loss": 1.9103, + "step": 3800 + }, + { + "epoch": 0.21186110027311744, + "grad_norm": 0.5372900366783142, + "learning_rate": 9.059273338842864e-05, + "loss": 1.6333, + "step": 3801 + }, + { + "epoch": 0.2119168385262806, + "grad_norm": 0.6031267046928406, + "learning_rate": 9.058753392118555e-05, + "loss": 1.9328, + "step": 3802 + }, + { + "epoch": 0.21197257677944373, + "grad_norm": 0.5510583519935608, + "learning_rate": 9.058233316674252e-05, + "loss": 1.6296, + "step": 3803 + }, + { + "epoch": 0.21202831503260688, + "grad_norm": 0.5591006875038147, + "learning_rate": 9.057713112526449e-05, + "loss": 1.6512, + "step": 3804 + }, + { + "epoch": 0.21208405328577, + "grad_norm": 0.5050638318061829, + "learning_rate": 9.057192779691645e-05, + "loss": 1.793, + "step": 3805 + }, + { + "epoch": 0.21213979153893317, + "grad_norm": 0.5485342144966125, + "learning_rate": 9.05667231818634e-05, + "loss": 1.8989, + "step": 3806 + }, + { + "epoch": 0.21219552979209633, + "grad_norm": 0.536729633808136, + "learning_rate": 9.056151728027042e-05, + "loss": 1.7235, + "step": 3807 + }, + { + "epoch": 0.21225126804525946, + "grad_norm": 0.5280648469924927, + "learning_rate": 9.055631009230262e-05, + "loss": 1.779, + "step": 3808 + }, + { + "epoch": 0.2123070062984226, + "grad_norm": 0.5353644490242004, + "learning_rate": 9.05511016181251e-05, + "loss": 1.9023, + "step": 3809 + }, + { + "epoch": 0.21236274455158574, + "grad_norm": 0.5420893430709839, + "learning_rate": 9.054589185790305e-05, + "loss": 1.6484, + "step": 3810 + }, + { + "epoch": 0.2124184828047489, + "grad_norm": 0.49997881054878235, + "learning_rate": 9.054068081180173e-05, + "loss": 1.6866, + "step": 3811 + }, + { + "epoch": 0.21247422105791205, + "grad_norm": 0.540344774723053, + "learning_rate": 9.05354684799864e-05, + "loss": 1.6013, + "step": 3812 + }, + { + "epoch": 0.21252995931107518, + "grad_norm": 0.5512065291404724, + "learning_rate": 9.053025486262231e-05, + "loss": 1.7741, + "step": 3813 + }, + { + "epoch": 0.21258569756423834, + "grad_norm": 0.5562829375267029, + "learning_rate": 9.052503995987488e-05, + "loss": 1.7829, + "step": 3814 + }, + { + "epoch": 0.21264143581740147, + "grad_norm": 0.528271496295929, + "learning_rate": 9.051982377190944e-05, + "loss": 1.6395, + "step": 3815 + }, + { + "epoch": 0.21269717407056463, + "grad_norm": 0.5158810019493103, + "learning_rate": 9.051460629889144e-05, + "loss": 1.4752, + "step": 3816 + }, + { + "epoch": 0.21275291232372778, + "grad_norm": 0.5320451855659485, + "learning_rate": 9.050938754098635e-05, + "loss": 1.7896, + "step": 3817 + }, + { + "epoch": 0.2128086505768909, + "grad_norm": 0.503190279006958, + "learning_rate": 9.050416749835968e-05, + "loss": 1.5488, + "step": 3818 + }, + { + "epoch": 0.21286438883005407, + "grad_norm": 0.561086893081665, + "learning_rate": 9.049894617117696e-05, + "loss": 1.9669, + "step": 3819 + }, + { + "epoch": 0.21292012708321723, + "grad_norm": 0.5414785146713257, + "learning_rate": 9.04937235596038e-05, + "loss": 1.761, + "step": 3820 + }, + { + "epoch": 0.21297586533638035, + "grad_norm": 0.5729870796203613, + "learning_rate": 9.04884996638058e-05, + "loss": 1.7399, + "step": 3821 + }, + { + "epoch": 0.2130316035895435, + "grad_norm": 0.5905429720878601, + "learning_rate": 9.048327448394868e-05, + "loss": 1.863, + "step": 3822 + }, + { + "epoch": 0.21308734184270664, + "grad_norm": 0.5414051413536072, + "learning_rate": 9.047804802019813e-05, + "loss": 1.4662, + "step": 3823 + }, + { + "epoch": 0.2131430800958698, + "grad_norm": 0.5677713751792908, + "learning_rate": 9.047282027271988e-05, + "loss": 1.7569, + "step": 3824 + }, + { + "epoch": 0.21319881834903295, + "grad_norm": 0.5208271145820618, + "learning_rate": 9.046759124167976e-05, + "loss": 1.5647, + "step": 3825 + }, + { + "epoch": 0.21325455660219608, + "grad_norm": 0.5930595397949219, + "learning_rate": 9.046236092724357e-05, + "loss": 1.8287, + "step": 3826 + }, + { + "epoch": 0.21331029485535924, + "grad_norm": 0.5405799150466919, + "learning_rate": 9.045712932957722e-05, + "loss": 1.7175, + "step": 3827 + }, + { + "epoch": 0.21336603310852237, + "grad_norm": 0.5690011382102966, + "learning_rate": 9.045189644884661e-05, + "loss": 1.9759, + "step": 3828 + }, + { + "epoch": 0.21342177136168552, + "grad_norm": 0.5739631652832031, + "learning_rate": 9.04466622852177e-05, + "loss": 1.7102, + "step": 3829 + }, + { + "epoch": 0.21347750961484868, + "grad_norm": 0.5377629399299622, + "learning_rate": 9.044142683885645e-05, + "loss": 1.647, + "step": 3830 + }, + { + "epoch": 0.2135332478680118, + "grad_norm": 0.6439347267150879, + "learning_rate": 9.043619010992897e-05, + "loss": 2.2611, + "step": 3831 + }, + { + "epoch": 0.21358898612117497, + "grad_norm": 0.527803897857666, + "learning_rate": 9.043095209860128e-05, + "loss": 1.7279, + "step": 3832 + }, + { + "epoch": 0.2136447243743381, + "grad_norm": 0.549921452999115, + "learning_rate": 9.042571280503951e-05, + "loss": 1.7293, + "step": 3833 + }, + { + "epoch": 0.21370046262750125, + "grad_norm": 0.5477808713912964, + "learning_rate": 9.042047222940985e-05, + "loss": 1.8327, + "step": 3834 + }, + { + "epoch": 0.2137562008806644, + "grad_norm": 0.6052964329719543, + "learning_rate": 9.041523037187847e-05, + "loss": 1.6961, + "step": 3835 + }, + { + "epoch": 0.21381193913382754, + "grad_norm": 0.5640259385108948, + "learning_rate": 9.04099872326116e-05, + "loss": 1.8019, + "step": 3836 + }, + { + "epoch": 0.2138676773869907, + "grad_norm": 0.5238528251647949, + "learning_rate": 9.040474281177557e-05, + "loss": 1.7182, + "step": 3837 + }, + { + "epoch": 0.21392341564015382, + "grad_norm": 0.561298668384552, + "learning_rate": 9.039949710953665e-05, + "loss": 1.903, + "step": 3838 + }, + { + "epoch": 0.21397915389331698, + "grad_norm": 0.5629448890686035, + "learning_rate": 9.039425012606125e-05, + "loss": 1.6652, + "step": 3839 + }, + { + "epoch": 0.21403489214648014, + "grad_norm": 0.5578324794769287, + "learning_rate": 9.038900186151575e-05, + "loss": 1.8062, + "step": 3840 + }, + { + "epoch": 0.21409063039964327, + "grad_norm": 0.5517327785491943, + "learning_rate": 9.038375231606659e-05, + "loss": 1.7376, + "step": 3841 + }, + { + "epoch": 0.21414636865280642, + "grad_norm": 0.5653707385063171, + "learning_rate": 9.037850148988026e-05, + "loss": 1.7724, + "step": 3842 + }, + { + "epoch": 0.21420210690596958, + "grad_norm": 0.6022188663482666, + "learning_rate": 9.037324938312327e-05, + "loss": 1.9338, + "step": 3843 + }, + { + "epoch": 0.2142578451591327, + "grad_norm": 0.5128300189971924, + "learning_rate": 9.036799599596222e-05, + "loss": 1.6685, + "step": 3844 + }, + { + "epoch": 0.21431358341229587, + "grad_norm": 0.5680099129676819, + "learning_rate": 9.036274132856368e-05, + "loss": 1.6111, + "step": 3845 + }, + { + "epoch": 0.214369321665459, + "grad_norm": 0.5332833528518677, + "learning_rate": 9.035748538109433e-05, + "loss": 1.7406, + "step": 3846 + }, + { + "epoch": 0.21442505991862215, + "grad_norm": 0.5845235586166382, + "learning_rate": 9.035222815372084e-05, + "loss": 2.0365, + "step": 3847 + }, + { + "epoch": 0.2144807981717853, + "grad_norm": 0.536208987236023, + "learning_rate": 9.034696964660996e-05, + "loss": 1.7869, + "step": 3848 + }, + { + "epoch": 0.21453653642494844, + "grad_norm": 0.6078736782073975, + "learning_rate": 9.034170985992843e-05, + "loss": 1.9884, + "step": 3849 + }, + { + "epoch": 0.2145922746781116, + "grad_norm": 0.5227762460708618, + "learning_rate": 9.033644879384307e-05, + "loss": 1.7483, + "step": 3850 + }, + { + "epoch": 0.21464801293127472, + "grad_norm": 0.555255115032196, + "learning_rate": 9.033118644852073e-05, + "loss": 1.7319, + "step": 3851 + }, + { + "epoch": 0.21470375118443788, + "grad_norm": 0.5747233033180237, + "learning_rate": 9.032592282412831e-05, + "loss": 1.806, + "step": 3852 + }, + { + "epoch": 0.21475948943760104, + "grad_norm": 0.5099679231643677, + "learning_rate": 9.032065792083271e-05, + "loss": 1.7784, + "step": 3853 + }, + { + "epoch": 0.21481522769076417, + "grad_norm": 0.583080530166626, + "learning_rate": 9.031539173880095e-05, + "loss": 1.8283, + "step": 3854 + }, + { + "epoch": 0.21487096594392732, + "grad_norm": 0.5755245089530945, + "learning_rate": 9.031012427820003e-05, + "loss": 1.8088, + "step": 3855 + }, + { + "epoch": 0.21492670419709045, + "grad_norm": 0.6300316452980042, + "learning_rate": 9.030485553919696e-05, + "loss": 2.021, + "step": 3856 + }, + { + "epoch": 0.2149824424502536, + "grad_norm": 0.48787984251976013, + "learning_rate": 9.029958552195889e-05, + "loss": 1.7416, + "step": 3857 + }, + { + "epoch": 0.21503818070341676, + "grad_norm": 0.5602289438247681, + "learning_rate": 9.029431422665292e-05, + "loss": 1.7158, + "step": 3858 + }, + { + "epoch": 0.2150939189565799, + "grad_norm": 0.6266565918922424, + "learning_rate": 9.028904165344622e-05, + "loss": 1.904, + "step": 3859 + }, + { + "epoch": 0.21514965720974305, + "grad_norm": 0.5256897211074829, + "learning_rate": 9.028376780250605e-05, + "loss": 1.5227, + "step": 3860 + }, + { + "epoch": 0.21520539546290618, + "grad_norm": 0.5775957107543945, + "learning_rate": 9.027849267399962e-05, + "loss": 1.8613, + "step": 3861 + }, + { + "epoch": 0.21526113371606934, + "grad_norm": 0.5759565830230713, + "learning_rate": 9.027321626809425e-05, + "loss": 1.7657, + "step": 3862 + }, + { + "epoch": 0.2153168719692325, + "grad_norm": 0.5388328433036804, + "learning_rate": 9.026793858495727e-05, + "loss": 1.7117, + "step": 3863 + }, + { + "epoch": 0.21537261022239562, + "grad_norm": 0.5749773383140564, + "learning_rate": 9.026265962475605e-05, + "loss": 1.781, + "step": 3864 + }, + { + "epoch": 0.21542834847555878, + "grad_norm": 0.5567165017127991, + "learning_rate": 9.025737938765801e-05, + "loss": 1.8402, + "step": 3865 + }, + { + "epoch": 0.21548408672872194, + "grad_norm": 0.5531468987464905, + "learning_rate": 9.025209787383062e-05, + "loss": 1.637, + "step": 3866 + }, + { + "epoch": 0.21553982498188506, + "grad_norm": 0.5598788261413574, + "learning_rate": 9.024681508344138e-05, + "loss": 1.7487, + "step": 3867 + }, + { + "epoch": 0.21559556323504822, + "grad_norm": 0.5670254826545715, + "learning_rate": 9.024153101665782e-05, + "loss": 1.8556, + "step": 3868 + }, + { + "epoch": 0.21565130148821135, + "grad_norm": 0.5822195410728455, + "learning_rate": 9.02362456736475e-05, + "loss": 1.8144, + "step": 3869 + }, + { + "epoch": 0.2157070397413745, + "grad_norm": 0.5438206791877747, + "learning_rate": 9.023095905457807e-05, + "loss": 1.7709, + "step": 3870 + }, + { + "epoch": 0.21576277799453766, + "grad_norm": 0.5582990646362305, + "learning_rate": 9.022567115961718e-05, + "loss": 1.7373, + "step": 3871 + }, + { + "epoch": 0.2158185162477008, + "grad_norm": 0.5481442809104919, + "learning_rate": 9.022038198893254e-05, + "loss": 1.642, + "step": 3872 + }, + { + "epoch": 0.21587425450086395, + "grad_norm": 0.5365943312644958, + "learning_rate": 9.021509154269187e-05, + "loss": 1.7393, + "step": 3873 + }, + { + "epoch": 0.21592999275402708, + "grad_norm": 0.5595213174819946, + "learning_rate": 9.0209799821063e-05, + "loss": 1.7803, + "step": 3874 + }, + { + "epoch": 0.21598573100719023, + "grad_norm": 0.5171288251876831, + "learning_rate": 9.020450682421368e-05, + "loss": 1.6007, + "step": 3875 + }, + { + "epoch": 0.2160414692603534, + "grad_norm": 0.5536861419677734, + "learning_rate": 9.019921255231183e-05, + "loss": 1.7964, + "step": 3876 + }, + { + "epoch": 0.21609720751351652, + "grad_norm": 0.5218709707260132, + "learning_rate": 9.019391700552533e-05, + "loss": 1.7572, + "step": 3877 + }, + { + "epoch": 0.21615294576667968, + "grad_norm": 0.5276560187339783, + "learning_rate": 9.018862018402214e-05, + "loss": 1.7768, + "step": 3878 + }, + { + "epoch": 0.2162086840198428, + "grad_norm": 0.509636640548706, + "learning_rate": 9.018332208797023e-05, + "loss": 1.8262, + "step": 3879 + }, + { + "epoch": 0.21626442227300596, + "grad_norm": 0.5426955819129944, + "learning_rate": 9.017802271753763e-05, + "loss": 1.7966, + "step": 3880 + }, + { + "epoch": 0.21632016052616912, + "grad_norm": 0.5915662050247192, + "learning_rate": 9.017272207289241e-05, + "loss": 1.7047, + "step": 3881 + }, + { + "epoch": 0.21637589877933225, + "grad_norm": 0.5025647282600403, + "learning_rate": 9.016742015420264e-05, + "loss": 1.6662, + "step": 3882 + }, + { + "epoch": 0.2164316370324954, + "grad_norm": 0.5097705125808716, + "learning_rate": 9.016211696163651e-05, + "loss": 1.6667, + "step": 3883 + }, + { + "epoch": 0.21648737528565853, + "grad_norm": 0.5540134310722351, + "learning_rate": 9.015681249536219e-05, + "loss": 1.7085, + "step": 3884 + }, + { + "epoch": 0.2165431135388217, + "grad_norm": 0.5509772300720215, + "learning_rate": 9.015150675554791e-05, + "loss": 1.7739, + "step": 3885 + }, + { + "epoch": 0.21659885179198485, + "grad_norm": 0.519534170627594, + "learning_rate": 9.014619974236195e-05, + "loss": 1.5412, + "step": 3886 + }, + { + "epoch": 0.21665459004514798, + "grad_norm": 0.5313923954963684, + "learning_rate": 9.014089145597259e-05, + "loss": 1.6956, + "step": 3887 + }, + { + "epoch": 0.21671032829831113, + "grad_norm": 0.5057397484779358, + "learning_rate": 9.013558189654819e-05, + "loss": 1.6772, + "step": 3888 + }, + { + "epoch": 0.2167660665514743, + "grad_norm": 0.5538941621780396, + "learning_rate": 9.013027106425713e-05, + "loss": 1.7071, + "step": 3889 + }, + { + "epoch": 0.21682180480463742, + "grad_norm": 0.5932080149650574, + "learning_rate": 9.012495895926786e-05, + "loss": 1.9886, + "step": 3890 + }, + { + "epoch": 0.21687754305780058, + "grad_norm": 0.5497404932975769, + "learning_rate": 9.011964558174884e-05, + "loss": 1.6111, + "step": 3891 + }, + { + "epoch": 0.2169332813109637, + "grad_norm": 0.5296292304992676, + "learning_rate": 9.011433093186856e-05, + "loss": 1.7192, + "step": 3892 + }, + { + "epoch": 0.21698901956412686, + "grad_norm": 0.5682234168052673, + "learning_rate": 9.01090150097956e-05, + "loss": 1.727, + "step": 3893 + }, + { + "epoch": 0.21704475781729002, + "grad_norm": 0.49014294147491455, + "learning_rate": 9.010369781569854e-05, + "loss": 1.5865, + "step": 3894 + }, + { + "epoch": 0.21710049607045315, + "grad_norm": 0.5291064381599426, + "learning_rate": 9.009837934974598e-05, + "loss": 1.6708, + "step": 3895 + }, + { + "epoch": 0.2171562343236163, + "grad_norm": 0.5380057096481323, + "learning_rate": 9.009305961210664e-05, + "loss": 1.816, + "step": 3896 + }, + { + "epoch": 0.21721197257677943, + "grad_norm": 0.5304032564163208, + "learning_rate": 9.008773860294921e-05, + "loss": 1.6085, + "step": 3897 + }, + { + "epoch": 0.2172677108299426, + "grad_norm": 0.5649582147598267, + "learning_rate": 9.008241632244243e-05, + "loss": 2.0664, + "step": 3898 + }, + { + "epoch": 0.21732344908310575, + "grad_norm": 0.5284783840179443, + "learning_rate": 9.00770927707551e-05, + "loss": 1.6078, + "step": 3899 + }, + { + "epoch": 0.21737918733626888, + "grad_norm": 0.5097172856330872, + "learning_rate": 9.007176794805606e-05, + "loss": 1.6985, + "step": 3900 + }, + { + "epoch": 0.21743492558943203, + "grad_norm": 0.5433828830718994, + "learning_rate": 9.006644185451416e-05, + "loss": 1.824, + "step": 3901 + }, + { + "epoch": 0.21749066384259516, + "grad_norm": 0.5155694484710693, + "learning_rate": 9.006111449029835e-05, + "loss": 1.674, + "step": 3902 + }, + { + "epoch": 0.21754640209575832, + "grad_norm": 0.4952467978000641, + "learning_rate": 9.005578585557754e-05, + "loss": 1.5491, + "step": 3903 + }, + { + "epoch": 0.21760214034892147, + "grad_norm": 0.5352423191070557, + "learning_rate": 9.005045595052077e-05, + "loss": 1.7583, + "step": 3904 + }, + { + "epoch": 0.2176578786020846, + "grad_norm": 0.5036554336547852, + "learning_rate": 9.004512477529702e-05, + "loss": 1.6147, + "step": 3905 + }, + { + "epoch": 0.21771361685524776, + "grad_norm": 0.5414397120475769, + "learning_rate": 9.003979233007541e-05, + "loss": 1.7576, + "step": 3906 + }, + { + "epoch": 0.2177693551084109, + "grad_norm": 0.51963871717453, + "learning_rate": 9.003445861502502e-05, + "loss": 1.7114, + "step": 3907 + }, + { + "epoch": 0.21782509336157405, + "grad_norm": 0.5667458176612854, + "learning_rate": 9.002912363031504e-05, + "loss": 1.904, + "step": 3908 + }, + { + "epoch": 0.2178808316147372, + "grad_norm": 0.5066022872924805, + "learning_rate": 9.002378737611463e-05, + "loss": 1.5851, + "step": 3909 + }, + { + "epoch": 0.21793656986790033, + "grad_norm": 0.5155694484710693, + "learning_rate": 9.001844985259303e-05, + "loss": 1.6766, + "step": 3910 + }, + { + "epoch": 0.2179923081210635, + "grad_norm": 0.5910778641700745, + "learning_rate": 9.001311105991954e-05, + "loss": 1.6309, + "step": 3911 + }, + { + "epoch": 0.21804804637422665, + "grad_norm": 0.5524371862411499, + "learning_rate": 9.000777099826345e-05, + "loss": 1.5347, + "step": 3912 + }, + { + "epoch": 0.21810378462738977, + "grad_norm": 0.5852683186531067, + "learning_rate": 9.000242966779412e-05, + "loss": 1.7077, + "step": 3913 + }, + { + "epoch": 0.21815952288055293, + "grad_norm": 0.511112630367279, + "learning_rate": 8.999708706868097e-05, + "loss": 1.4288, + "step": 3914 + }, + { + "epoch": 0.21821526113371606, + "grad_norm": 0.553582489490509, + "learning_rate": 8.999174320109343e-05, + "loss": 1.6114, + "step": 3915 + }, + { + "epoch": 0.21827099938687922, + "grad_norm": 0.5207599401473999, + "learning_rate": 8.998639806520092e-05, + "loss": 1.6002, + "step": 3916 + }, + { + "epoch": 0.21832673764004237, + "grad_norm": 0.520836591720581, + "learning_rate": 8.998105166117304e-05, + "loss": 1.7308, + "step": 3917 + }, + { + "epoch": 0.2183824758932055, + "grad_norm": 0.5346881151199341, + "learning_rate": 8.99757039891793e-05, + "loss": 1.7732, + "step": 3918 + }, + { + "epoch": 0.21843821414636866, + "grad_norm": 0.5407224893569946, + "learning_rate": 8.997035504938928e-05, + "loss": 1.6927, + "step": 3919 + }, + { + "epoch": 0.2184939523995318, + "grad_norm": 0.6079891324043274, + "learning_rate": 8.996500484197266e-05, + "loss": 1.7503, + "step": 3920 + }, + { + "epoch": 0.21854969065269494, + "grad_norm": 0.5896045565605164, + "learning_rate": 8.995965336709908e-05, + "loss": 1.8189, + "step": 3921 + }, + { + "epoch": 0.2186054289058581, + "grad_norm": 0.5681061148643494, + "learning_rate": 8.99543006249383e-05, + "loss": 1.9138, + "step": 3922 + }, + { + "epoch": 0.21866116715902123, + "grad_norm": 0.5397033095359802, + "learning_rate": 8.994894661566004e-05, + "loss": 1.6947, + "step": 3923 + }, + { + "epoch": 0.2187169054121844, + "grad_norm": 0.5442162752151489, + "learning_rate": 8.994359133943411e-05, + "loss": 1.7947, + "step": 3924 + }, + { + "epoch": 0.21877264366534752, + "grad_norm": 0.5366693735122681, + "learning_rate": 8.993823479643036e-05, + "loss": 1.8557, + "step": 3925 + }, + { + "epoch": 0.21882838191851067, + "grad_norm": 0.5018730163574219, + "learning_rate": 8.993287698681867e-05, + "loss": 1.6033, + "step": 3926 + }, + { + "epoch": 0.21888412017167383, + "grad_norm": 0.5234804749488831, + "learning_rate": 8.992751791076893e-05, + "loss": 1.6927, + "step": 3927 + }, + { + "epoch": 0.21893985842483696, + "grad_norm": 0.5351289510726929, + "learning_rate": 8.992215756845111e-05, + "loss": 1.6108, + "step": 3928 + }, + { + "epoch": 0.21899559667800012, + "grad_norm": 0.5499307513237, + "learning_rate": 8.991679596003521e-05, + "loss": 1.821, + "step": 3929 + }, + { + "epoch": 0.21905133493116324, + "grad_norm": 0.5461710691452026, + "learning_rate": 8.991143308569129e-05, + "loss": 1.6755, + "step": 3930 + }, + { + "epoch": 0.2191070731843264, + "grad_norm": 0.557220458984375, + "learning_rate": 8.990606894558942e-05, + "loss": 1.7568, + "step": 3931 + }, + { + "epoch": 0.21916281143748956, + "grad_norm": 0.5313843488693237, + "learning_rate": 8.99007035398997e-05, + "loss": 1.5701, + "step": 3932 + }, + { + "epoch": 0.2192185496906527, + "grad_norm": 0.5466028451919556, + "learning_rate": 8.98953368687923e-05, + "loss": 1.7533, + "step": 3933 + }, + { + "epoch": 0.21927428794381584, + "grad_norm": 0.5278179049491882, + "learning_rate": 8.988996893243742e-05, + "loss": 1.6604, + "step": 3934 + }, + { + "epoch": 0.219330026196979, + "grad_norm": 0.5555846095085144, + "learning_rate": 8.988459973100529e-05, + "loss": 1.9101, + "step": 3935 + }, + { + "epoch": 0.21938576445014213, + "grad_norm": 0.5475595593452454, + "learning_rate": 8.987922926466621e-05, + "loss": 1.6784, + "step": 3936 + }, + { + "epoch": 0.21944150270330529, + "grad_norm": 0.5606985092163086, + "learning_rate": 8.98738575335905e-05, + "loss": 1.8496, + "step": 3937 + }, + { + "epoch": 0.21949724095646841, + "grad_norm": 0.5272994041442871, + "learning_rate": 8.986848453794849e-05, + "loss": 1.6477, + "step": 3938 + }, + { + "epoch": 0.21955297920963157, + "grad_norm": 0.5808579325675964, + "learning_rate": 8.986311027791061e-05, + "loss": 1.9312, + "step": 3939 + }, + { + "epoch": 0.21960871746279473, + "grad_norm": 0.5892482399940491, + "learning_rate": 8.985773475364729e-05, + "loss": 1.8278, + "step": 3940 + }, + { + "epoch": 0.21966445571595786, + "grad_norm": 0.5204423069953918, + "learning_rate": 8.9852357965329e-05, + "loss": 1.5689, + "step": 3941 + }, + { + "epoch": 0.219720193969121, + "grad_norm": 0.5408873558044434, + "learning_rate": 8.984697991312629e-05, + "loss": 1.6719, + "step": 3942 + }, + { + "epoch": 0.21977593222228414, + "grad_norm": 0.4690547585487366, + "learning_rate": 8.98416005972097e-05, + "loss": 1.4167, + "step": 3943 + }, + { + "epoch": 0.2198316704754473, + "grad_norm": 0.5128321647644043, + "learning_rate": 8.98362200177498e-05, + "loss": 1.5936, + "step": 3944 + }, + { + "epoch": 0.21988740872861046, + "grad_norm": 0.5651824474334717, + "learning_rate": 8.98308381749173e-05, + "loss": 1.7715, + "step": 3945 + }, + { + "epoch": 0.21994314698177359, + "grad_norm": 0.49932271242141724, + "learning_rate": 8.982545506888282e-05, + "loss": 1.5167, + "step": 3946 + }, + { + "epoch": 0.21999888523493674, + "grad_norm": 0.5488872528076172, + "learning_rate": 8.982007069981711e-05, + "loss": 1.6694, + "step": 3947 + }, + { + "epoch": 0.22005462348809987, + "grad_norm": 0.5529676079750061, + "learning_rate": 8.981468506789093e-05, + "loss": 1.7098, + "step": 3948 + }, + { + "epoch": 0.22011036174126303, + "grad_norm": 0.555151104927063, + "learning_rate": 8.980929817327509e-05, + "loss": 1.8188, + "step": 3949 + }, + { + "epoch": 0.22016609999442618, + "grad_norm": 0.5413922667503357, + "learning_rate": 8.980391001614039e-05, + "loss": 1.6947, + "step": 3950 + }, + { + "epoch": 0.2202218382475893, + "grad_norm": 0.5880113244056702, + "learning_rate": 8.979852059665774e-05, + "loss": 1.8565, + "step": 3951 + }, + { + "epoch": 0.22027757650075247, + "grad_norm": 0.5404399037361145, + "learning_rate": 8.979312991499807e-05, + "loss": 1.6119, + "step": 3952 + }, + { + "epoch": 0.2203333147539156, + "grad_norm": 0.5193542838096619, + "learning_rate": 8.97877379713323e-05, + "loss": 1.5012, + "step": 3953 + }, + { + "epoch": 0.22038905300707876, + "grad_norm": 0.5563862323760986, + "learning_rate": 8.97823447658315e-05, + "loss": 1.7968, + "step": 3954 + }, + { + "epoch": 0.2204447912602419, + "grad_norm": 0.5796663165092468, + "learning_rate": 8.977695029866665e-05, + "loss": 1.6924, + "step": 3955 + }, + { + "epoch": 0.22050052951340504, + "grad_norm": 0.5060169100761414, + "learning_rate": 8.977155457000886e-05, + "loss": 1.6837, + "step": 3956 + }, + { + "epoch": 0.2205562677665682, + "grad_norm": 0.5254307389259338, + "learning_rate": 8.976615758002925e-05, + "loss": 1.5339, + "step": 3957 + }, + { + "epoch": 0.22061200601973135, + "grad_norm": 0.4909488260746002, + "learning_rate": 8.976075932889896e-05, + "loss": 1.406, + "step": 3958 + }, + { + "epoch": 0.22066774427289448, + "grad_norm": 0.521052896976471, + "learning_rate": 8.97553598167892e-05, + "loss": 1.6203, + "step": 3959 + }, + { + "epoch": 0.22072348252605764, + "grad_norm": 0.5382006764411926, + "learning_rate": 8.974995904387123e-05, + "loss": 1.6984, + "step": 3960 + }, + { + "epoch": 0.22077922077922077, + "grad_norm": 0.5354267954826355, + "learning_rate": 8.97445570103163e-05, + "loss": 1.7722, + "step": 3961 + }, + { + "epoch": 0.22083495903238393, + "grad_norm": 0.5725782513618469, + "learning_rate": 8.973915371629577e-05, + "loss": 1.8308, + "step": 3962 + }, + { + "epoch": 0.22089069728554708, + "grad_norm": 0.5183130502700806, + "learning_rate": 8.973374916198096e-05, + "loss": 1.6487, + "step": 3963 + }, + { + "epoch": 0.2209464355387102, + "grad_norm": 0.5026050209999084, + "learning_rate": 8.972834334754331e-05, + "loss": 1.4931, + "step": 3964 + }, + { + "epoch": 0.22100217379187337, + "grad_norm": 0.5589287281036377, + "learning_rate": 8.972293627315424e-05, + "loss": 1.9263, + "step": 3965 + }, + { + "epoch": 0.2210579120450365, + "grad_norm": 0.5776212811470032, + "learning_rate": 8.971752793898522e-05, + "loss": 1.8374, + "step": 3966 + }, + { + "epoch": 0.22111365029819965, + "grad_norm": 0.5569107532501221, + "learning_rate": 8.971211834520779e-05, + "loss": 1.7221, + "step": 3967 + }, + { + "epoch": 0.2211693885513628, + "grad_norm": 0.527186930179596, + "learning_rate": 8.970670749199351e-05, + "loss": 1.713, + "step": 3968 + }, + { + "epoch": 0.22122512680452594, + "grad_norm": 0.5234454274177551, + "learning_rate": 8.970129537951395e-05, + "loss": 1.6519, + "step": 3969 + }, + { + "epoch": 0.2212808650576891, + "grad_norm": 0.5419970154762268, + "learning_rate": 8.969588200794079e-05, + "loss": 1.5816, + "step": 3970 + }, + { + "epoch": 0.22133660331085223, + "grad_norm": 0.5328260660171509, + "learning_rate": 8.969046737744571e-05, + "loss": 1.8442, + "step": 3971 + }, + { + "epoch": 0.22139234156401538, + "grad_norm": 0.5527640581130981, + "learning_rate": 8.968505148820039e-05, + "loss": 1.5886, + "step": 3972 + }, + { + "epoch": 0.22144807981717854, + "grad_norm": 0.5386121869087219, + "learning_rate": 8.967963434037663e-05, + "loss": 1.8938, + "step": 3973 + }, + { + "epoch": 0.22150381807034167, + "grad_norm": 0.60856693983078, + "learning_rate": 8.967421593414622e-05, + "loss": 1.7739, + "step": 3974 + }, + { + "epoch": 0.22155955632350482, + "grad_norm": 0.5383316278457642, + "learning_rate": 8.966879626968099e-05, + "loss": 1.5916, + "step": 3975 + }, + { + "epoch": 0.22161529457666795, + "grad_norm": 0.5469935536384583, + "learning_rate": 8.966337534715284e-05, + "loss": 1.6879, + "step": 3976 + }, + { + "epoch": 0.2216710328298311, + "grad_norm": 0.5624483227729797, + "learning_rate": 8.965795316673366e-05, + "loss": 1.5465, + "step": 3977 + }, + { + "epoch": 0.22172677108299427, + "grad_norm": 0.571090817451477, + "learning_rate": 8.965252972859545e-05, + "loss": 1.8477, + "step": 3978 + }, + { + "epoch": 0.2217825093361574, + "grad_norm": 0.5622638463973999, + "learning_rate": 8.964710503291018e-05, + "loss": 1.7961, + "step": 3979 + }, + { + "epoch": 0.22183824758932055, + "grad_norm": 0.54639732837677, + "learning_rate": 8.964167907984988e-05, + "loss": 1.7795, + "step": 3980 + }, + { + "epoch": 0.2218939858424837, + "grad_norm": 0.5762872099876404, + "learning_rate": 8.963625186958666e-05, + "loss": 1.7824, + "step": 3981 + }, + { + "epoch": 0.22194972409564684, + "grad_norm": 0.5208929777145386, + "learning_rate": 8.963082340229263e-05, + "loss": 1.7521, + "step": 3982 + }, + { + "epoch": 0.22200546234881, + "grad_norm": 0.49496889114379883, + "learning_rate": 8.962539367813993e-05, + "loss": 1.5493, + "step": 3983 + }, + { + "epoch": 0.22206120060197312, + "grad_norm": 0.4936692714691162, + "learning_rate": 8.961996269730078e-05, + "loss": 1.5015, + "step": 3984 + }, + { + "epoch": 0.22211693885513628, + "grad_norm": 0.5555882453918457, + "learning_rate": 8.961453045994742e-05, + "loss": 1.7563, + "step": 3985 + }, + { + "epoch": 0.22217267710829944, + "grad_norm": 0.5514853596687317, + "learning_rate": 8.960909696625213e-05, + "loss": 1.6671, + "step": 3986 + }, + { + "epoch": 0.22222841536146257, + "grad_norm": 0.5259945392608643, + "learning_rate": 8.960366221638721e-05, + "loss": 1.7181, + "step": 3987 + }, + { + "epoch": 0.22228415361462572, + "grad_norm": 0.5564213395118713, + "learning_rate": 8.959822621052502e-05, + "loss": 1.8017, + "step": 3988 + }, + { + "epoch": 0.22233989186778885, + "grad_norm": 0.5879985094070435, + "learning_rate": 8.959278894883797e-05, + "loss": 1.8768, + "step": 3989 + }, + { + "epoch": 0.222395630120952, + "grad_norm": 0.5429808497428894, + "learning_rate": 8.958735043149852e-05, + "loss": 1.6246, + "step": 3990 + }, + { + "epoch": 0.22245136837411517, + "grad_norm": 0.5388792753219604, + "learning_rate": 8.958191065867912e-05, + "loss": 1.8083, + "step": 3991 + }, + { + "epoch": 0.2225071066272783, + "grad_norm": 0.5783261060714722, + "learning_rate": 8.957646963055227e-05, + "loss": 1.9074, + "step": 3992 + }, + { + "epoch": 0.22256284488044145, + "grad_norm": 0.5076984167098999, + "learning_rate": 8.957102734729057e-05, + "loss": 1.6518, + "step": 3993 + }, + { + "epoch": 0.22261858313360458, + "grad_norm": 0.6677889823913574, + "learning_rate": 8.956558380906659e-05, + "loss": 2.3105, + "step": 3994 + }, + { + "epoch": 0.22267432138676774, + "grad_norm": 0.5451659560203552, + "learning_rate": 8.956013901605299e-05, + "loss": 1.7229, + "step": 3995 + }, + { + "epoch": 0.2227300596399309, + "grad_norm": 0.5508718490600586, + "learning_rate": 8.955469296842241e-05, + "loss": 1.641, + "step": 3996 + }, + { + "epoch": 0.22278579789309402, + "grad_norm": 0.5317922234535217, + "learning_rate": 8.95492456663476e-05, + "loss": 1.6717, + "step": 3997 + }, + { + "epoch": 0.22284153614625718, + "grad_norm": 0.5446794033050537, + "learning_rate": 8.954379711000129e-05, + "loss": 1.7382, + "step": 3998 + }, + { + "epoch": 0.2228972743994203, + "grad_norm": 0.5360628962516785, + "learning_rate": 8.95383472995563e-05, + "loss": 1.7489, + "step": 3999 + }, + { + "epoch": 0.22295301265258347, + "grad_norm": 0.5646945238113403, + "learning_rate": 8.953289623518545e-05, + "loss": 1.7241, + "step": 4000 + }, + { + "epoch": 0.22300875090574662, + "grad_norm": 0.5079129338264465, + "learning_rate": 8.952744391706165e-05, + "loss": 1.6683, + "step": 4001 + }, + { + "epoch": 0.22306448915890975, + "grad_norm": 0.5274491906166077, + "learning_rate": 8.952199034535778e-05, + "loss": 1.6086, + "step": 4002 + }, + { + "epoch": 0.2231202274120729, + "grad_norm": 0.5475561618804932, + "learning_rate": 8.95165355202468e-05, + "loss": 1.9497, + "step": 4003 + }, + { + "epoch": 0.22317596566523606, + "grad_norm": 0.5520079135894775, + "learning_rate": 8.951107944190171e-05, + "loss": 1.9735, + "step": 4004 + }, + { + "epoch": 0.2232317039183992, + "grad_norm": 0.5097377300262451, + "learning_rate": 8.950562211049556e-05, + "loss": 1.5424, + "step": 4005 + }, + { + "epoch": 0.22328744217156235, + "grad_norm": 0.5405047535896301, + "learning_rate": 8.950016352620139e-05, + "loss": 1.6966, + "step": 4006 + }, + { + "epoch": 0.22334318042472548, + "grad_norm": 0.5254392027854919, + "learning_rate": 8.949470368919235e-05, + "loss": 1.6651, + "step": 4007 + }, + { + "epoch": 0.22339891867788864, + "grad_norm": 0.5582841634750366, + "learning_rate": 8.948924259964157e-05, + "loss": 1.7668, + "step": 4008 + }, + { + "epoch": 0.2234546569310518, + "grad_norm": 0.5375759601593018, + "learning_rate": 8.948378025772227e-05, + "loss": 1.7271, + "step": 4009 + }, + { + "epoch": 0.22351039518421492, + "grad_norm": 0.5370509028434753, + "learning_rate": 8.947831666360765e-05, + "loss": 1.7851, + "step": 4010 + }, + { + "epoch": 0.22356613343737808, + "grad_norm": 0.5874437093734741, + "learning_rate": 8.947285181747098e-05, + "loss": 1.8569, + "step": 4011 + }, + { + "epoch": 0.2236218716905412, + "grad_norm": 0.566886305809021, + "learning_rate": 8.946738571948562e-05, + "loss": 1.6114, + "step": 4012 + }, + { + "epoch": 0.22367760994370436, + "grad_norm": 0.5747610926628113, + "learning_rate": 8.946191836982489e-05, + "loss": 1.8552, + "step": 4013 + }, + { + "epoch": 0.22373334819686752, + "grad_norm": 0.5414125919342041, + "learning_rate": 8.945644976866219e-05, + "loss": 1.5846, + "step": 4014 + }, + { + "epoch": 0.22378908645003065, + "grad_norm": 0.5818209648132324, + "learning_rate": 8.945097991617096e-05, + "loss": 1.8305, + "step": 4015 + }, + { + "epoch": 0.2238448247031938, + "grad_norm": 0.5896833539009094, + "learning_rate": 8.944550881252465e-05, + "loss": 1.6642, + "step": 4016 + }, + { + "epoch": 0.22390056295635694, + "grad_norm": 0.5750831365585327, + "learning_rate": 8.944003645789678e-05, + "loss": 1.7286, + "step": 4017 + }, + { + "epoch": 0.2239563012095201, + "grad_norm": 0.514319896697998, + "learning_rate": 8.943456285246091e-05, + "loss": 1.6254, + "step": 4018 + }, + { + "epoch": 0.22401203946268325, + "grad_norm": 0.48393240571022034, + "learning_rate": 8.942908799639062e-05, + "loss": 1.4306, + "step": 4019 + }, + { + "epoch": 0.22406777771584638, + "grad_norm": 0.5655490756034851, + "learning_rate": 8.942361188985957e-05, + "loss": 1.8686, + "step": 4020 + }, + { + "epoch": 0.22412351596900953, + "grad_norm": 0.7101614475250244, + "learning_rate": 8.941813453304138e-05, + "loss": 1.6244, + "step": 4021 + }, + { + "epoch": 0.22417925422217266, + "grad_norm": 0.5121461153030396, + "learning_rate": 8.941265592610979e-05, + "loss": 1.5336, + "step": 4022 + }, + { + "epoch": 0.22423499247533582, + "grad_norm": 0.5167136192321777, + "learning_rate": 8.940717606923857e-05, + "loss": 1.5896, + "step": 4023 + }, + { + "epoch": 0.22429073072849898, + "grad_norm": 0.5683619379997253, + "learning_rate": 8.940169496260144e-05, + "loss": 1.8004, + "step": 4024 + }, + { + "epoch": 0.2243464689816621, + "grad_norm": 0.5303056240081787, + "learning_rate": 8.939621260637231e-05, + "loss": 1.6034, + "step": 4025 + }, + { + "epoch": 0.22440220723482526, + "grad_norm": 0.5514824986457825, + "learning_rate": 8.9390729000725e-05, + "loss": 1.7099, + "step": 4026 + }, + { + "epoch": 0.22445794548798842, + "grad_norm": 0.5117455720901489, + "learning_rate": 8.938524414583343e-05, + "loss": 1.8367, + "step": 4027 + }, + { + "epoch": 0.22451368374115155, + "grad_norm": 0.5556350946426392, + "learning_rate": 8.937975804187156e-05, + "loss": 1.6737, + "step": 4028 + }, + { + "epoch": 0.2245694219943147, + "grad_norm": 0.5511283874511719, + "learning_rate": 8.937427068901335e-05, + "loss": 1.7541, + "step": 4029 + }, + { + "epoch": 0.22462516024747783, + "grad_norm": 0.5651305317878723, + "learning_rate": 8.936878208743285e-05, + "loss": 1.7383, + "step": 4030 + }, + { + "epoch": 0.224680898500641, + "grad_norm": 0.5192481875419617, + "learning_rate": 8.93632922373041e-05, + "loss": 1.5392, + "step": 4031 + }, + { + "epoch": 0.22473663675380415, + "grad_norm": 0.5942433476448059, + "learning_rate": 8.935780113880125e-05, + "loss": 1.9703, + "step": 4032 + }, + { + "epoch": 0.22479237500696728, + "grad_norm": 0.5313376188278198, + "learning_rate": 8.93523087920984e-05, + "loss": 1.7827, + "step": 4033 + }, + { + "epoch": 0.22484811326013043, + "grad_norm": 0.5464789271354675, + "learning_rate": 8.934681519736977e-05, + "loss": 1.8036, + "step": 4034 + }, + { + "epoch": 0.22490385151329356, + "grad_norm": 0.5823439955711365, + "learning_rate": 8.934132035478955e-05, + "loss": 1.9969, + "step": 4035 + }, + { + "epoch": 0.22495958976645672, + "grad_norm": 0.5518758296966553, + "learning_rate": 8.933582426453205e-05, + "loss": 1.7836, + "step": 4036 + }, + { + "epoch": 0.22501532801961988, + "grad_norm": 0.529864490032196, + "learning_rate": 8.933032692677153e-05, + "loss": 1.8767, + "step": 4037 + }, + { + "epoch": 0.225071066272783, + "grad_norm": 0.5450250506401062, + "learning_rate": 8.932482834168237e-05, + "loss": 1.6584, + "step": 4038 + }, + { + "epoch": 0.22512680452594616, + "grad_norm": 0.5210989713668823, + "learning_rate": 8.931932850943892e-05, + "loss": 1.6707, + "step": 4039 + }, + { + "epoch": 0.2251825427791093, + "grad_norm": 0.5319432616233826, + "learning_rate": 8.931382743021562e-05, + "loss": 1.5798, + "step": 4040 + }, + { + "epoch": 0.22523828103227245, + "grad_norm": 0.502311110496521, + "learning_rate": 8.930832510418692e-05, + "loss": 1.5718, + "step": 4041 + }, + { + "epoch": 0.2252940192854356, + "grad_norm": 0.5432561635971069, + "learning_rate": 8.930282153152734e-05, + "loss": 1.7996, + "step": 4042 + }, + { + "epoch": 0.22534975753859873, + "grad_norm": 0.5339439511299133, + "learning_rate": 8.92973167124114e-05, + "loss": 1.8783, + "step": 4043 + }, + { + "epoch": 0.2254054957917619, + "grad_norm": 0.5929161310195923, + "learning_rate": 8.92918106470137e-05, + "loss": 1.9278, + "step": 4044 + }, + { + "epoch": 0.22546123404492502, + "grad_norm": 0.5356025695800781, + "learning_rate": 8.928630333550886e-05, + "loss": 1.6555, + "step": 4045 + }, + { + "epoch": 0.22551697229808818, + "grad_norm": 0.6173697113990784, + "learning_rate": 8.928079477807155e-05, + "loss": 1.6326, + "step": 4046 + }, + { + "epoch": 0.22557271055125133, + "grad_norm": 0.5391169786453247, + "learning_rate": 8.927528497487642e-05, + "loss": 1.7983, + "step": 4047 + }, + { + "epoch": 0.22562844880441446, + "grad_norm": 0.541691780090332, + "learning_rate": 8.926977392609826e-05, + "loss": 1.9013, + "step": 4048 + }, + { + "epoch": 0.22568418705757762, + "grad_norm": 0.5518167018890381, + "learning_rate": 8.926426163191182e-05, + "loss": 1.8038, + "step": 4049 + }, + { + "epoch": 0.22573992531074077, + "grad_norm": 0.5680546164512634, + "learning_rate": 8.925874809249193e-05, + "loss": 1.893, + "step": 4050 + }, + { + "epoch": 0.2257956635639039, + "grad_norm": 0.531597912311554, + "learning_rate": 8.925323330801345e-05, + "loss": 1.6987, + "step": 4051 + }, + { + "epoch": 0.22585140181706706, + "grad_norm": 0.5005265474319458, + "learning_rate": 8.924771727865126e-05, + "loss": 1.4703, + "step": 4052 + }, + { + "epoch": 0.2259071400702302, + "grad_norm": 0.4409901201725006, + "learning_rate": 8.924220000458032e-05, + "loss": 1.1188, + "step": 4053 + }, + { + "epoch": 0.22596287832339335, + "grad_norm": 0.5583540797233582, + "learning_rate": 8.92366814859756e-05, + "loss": 1.8899, + "step": 4054 + }, + { + "epoch": 0.2260186165765565, + "grad_norm": 0.5503487586975098, + "learning_rate": 8.923116172301208e-05, + "loss": 1.7006, + "step": 4055 + }, + { + "epoch": 0.22607435482971963, + "grad_norm": 0.5401930212974548, + "learning_rate": 8.922564071586487e-05, + "loss": 1.7435, + "step": 4056 + }, + { + "epoch": 0.2261300930828828, + "grad_norm": 0.5470068454742432, + "learning_rate": 8.922011846470903e-05, + "loss": 1.7926, + "step": 4057 + }, + { + "epoch": 0.22618583133604592, + "grad_norm": 0.5655896663665771, + "learning_rate": 8.921459496971971e-05, + "loss": 1.8028, + "step": 4058 + }, + { + "epoch": 0.22624156958920907, + "grad_norm": 0.520338237285614, + "learning_rate": 8.920907023107208e-05, + "loss": 1.7713, + "step": 4059 + }, + { + "epoch": 0.22629730784237223, + "grad_norm": 0.5628316402435303, + "learning_rate": 8.920354424894133e-05, + "loss": 1.8308, + "step": 4060 + }, + { + "epoch": 0.22635304609553536, + "grad_norm": 0.5436638593673706, + "learning_rate": 8.919801702350272e-05, + "loss": 1.7824, + "step": 4061 + }, + { + "epoch": 0.22640878434869852, + "grad_norm": 0.6150013208389282, + "learning_rate": 8.919248855493156e-05, + "loss": 1.6801, + "step": 4062 + }, + { + "epoch": 0.22646452260186165, + "grad_norm": 0.5413832068443298, + "learning_rate": 8.918695884340318e-05, + "loss": 1.7266, + "step": 4063 + }, + { + "epoch": 0.2265202608550248, + "grad_norm": 0.6004742980003357, + "learning_rate": 8.918142788909294e-05, + "loss": 1.9331, + "step": 4064 + }, + { + "epoch": 0.22657599910818796, + "grad_norm": 0.5428612232208252, + "learning_rate": 8.917589569217624e-05, + "loss": 1.8074, + "step": 4065 + }, + { + "epoch": 0.2266317373613511, + "grad_norm": 0.5653241276741028, + "learning_rate": 8.917036225282855e-05, + "loss": 1.8719, + "step": 4066 + }, + { + "epoch": 0.22668747561451424, + "grad_norm": 0.5411580801010132, + "learning_rate": 8.916482757122535e-05, + "loss": 1.7155, + "step": 4067 + }, + { + "epoch": 0.22674321386767737, + "grad_norm": 0.5733420252799988, + "learning_rate": 8.915929164754215e-05, + "loss": 1.8401, + "step": 4068 + }, + { + "epoch": 0.22679895212084053, + "grad_norm": 0.5870828032493591, + "learning_rate": 8.915375448195455e-05, + "loss": 1.6825, + "step": 4069 + }, + { + "epoch": 0.2268546903740037, + "grad_norm": 0.5373989939689636, + "learning_rate": 8.914821607463814e-05, + "loss": 1.6471, + "step": 4070 + }, + { + "epoch": 0.22691042862716682, + "grad_norm": 0.5650984048843384, + "learning_rate": 8.914267642576857e-05, + "loss": 2.0078, + "step": 4071 + }, + { + "epoch": 0.22696616688032997, + "grad_norm": 0.5647602677345276, + "learning_rate": 8.91371355355215e-05, + "loss": 1.8949, + "step": 4072 + }, + { + "epoch": 0.22702190513349313, + "grad_norm": 0.5225738286972046, + "learning_rate": 8.913159340407269e-05, + "loss": 1.787, + "step": 4073 + }, + { + "epoch": 0.22707764338665626, + "grad_norm": 0.4927429258823395, + "learning_rate": 8.912605003159788e-05, + "loss": 1.6022, + "step": 4074 + }, + { + "epoch": 0.22713338163981941, + "grad_norm": 0.5242977738380432, + "learning_rate": 8.912050541827291e-05, + "loss": 1.6286, + "step": 4075 + }, + { + "epoch": 0.22718911989298254, + "grad_norm": 0.5272535681724548, + "learning_rate": 8.911495956427357e-05, + "loss": 1.8091, + "step": 4076 + }, + { + "epoch": 0.2272448581461457, + "grad_norm": 0.5660970211029053, + "learning_rate": 8.910941246977577e-05, + "loss": 1.7518, + "step": 4077 + }, + { + "epoch": 0.22730059639930886, + "grad_norm": 0.5166184902191162, + "learning_rate": 8.910386413495544e-05, + "loss": 1.7051, + "step": 4078 + }, + { + "epoch": 0.227356334652472, + "grad_norm": 0.5315423607826233, + "learning_rate": 8.909831455998854e-05, + "loss": 1.5667, + "step": 4079 + }, + { + "epoch": 0.22741207290563514, + "grad_norm": 0.5121911764144897, + "learning_rate": 8.909276374505104e-05, + "loss": 1.6594, + "step": 4080 + }, + { + "epoch": 0.22746781115879827, + "grad_norm": 0.5725307464599609, + "learning_rate": 8.908721169031901e-05, + "loss": 1.7931, + "step": 4081 + }, + { + "epoch": 0.22752354941196143, + "grad_norm": 0.6129924058914185, + "learning_rate": 8.908165839596852e-05, + "loss": 2.0539, + "step": 4082 + }, + { + "epoch": 0.22757928766512459, + "grad_norm": 0.6019653677940369, + "learning_rate": 8.907610386217568e-05, + "loss": 2.1055, + "step": 4083 + }, + { + "epoch": 0.22763502591828771, + "grad_norm": 0.5589843392372131, + "learning_rate": 8.907054808911668e-05, + "loss": 1.8536, + "step": 4084 + }, + { + "epoch": 0.22769076417145087, + "grad_norm": 0.5030215382575989, + "learning_rate": 8.906499107696766e-05, + "loss": 1.5868, + "step": 4085 + }, + { + "epoch": 0.227746502424614, + "grad_norm": 0.5388656258583069, + "learning_rate": 8.90594328259049e-05, + "loss": 1.611, + "step": 4086 + }, + { + "epoch": 0.22780224067777716, + "grad_norm": 0.5835996270179749, + "learning_rate": 8.905387333610466e-05, + "loss": 1.3946, + "step": 4087 + }, + { + "epoch": 0.2278579789309403, + "grad_norm": 0.5778213739395142, + "learning_rate": 8.904831260774327e-05, + "loss": 1.9145, + "step": 4088 + }, + { + "epoch": 0.22791371718410344, + "grad_norm": 0.5685307383537292, + "learning_rate": 8.904275064099708e-05, + "loss": 1.8516, + "step": 4089 + }, + { + "epoch": 0.2279694554372666, + "grad_norm": 0.5906243324279785, + "learning_rate": 8.903718743604244e-05, + "loss": 1.7872, + "step": 4090 + }, + { + "epoch": 0.22802519369042973, + "grad_norm": 0.5142653584480286, + "learning_rate": 8.903162299305585e-05, + "loss": 1.5771, + "step": 4091 + }, + { + "epoch": 0.22808093194359289, + "grad_norm": 0.5752720832824707, + "learning_rate": 8.902605731221373e-05, + "loss": 1.7952, + "step": 4092 + }, + { + "epoch": 0.22813667019675604, + "grad_norm": 0.5666948556900024, + "learning_rate": 8.902049039369261e-05, + "loss": 1.7417, + "step": 4093 + }, + { + "epoch": 0.22819240844991917, + "grad_norm": 0.5241186618804932, + "learning_rate": 8.901492223766906e-05, + "loss": 1.6605, + "step": 4094 + }, + { + "epoch": 0.22824814670308233, + "grad_norm": 0.548561155796051, + "learning_rate": 8.900935284431961e-05, + "loss": 1.8027, + "step": 4095 + }, + { + "epoch": 0.22830388495624548, + "grad_norm": 0.5435733795166016, + "learning_rate": 8.900378221382097e-05, + "loss": 1.6941, + "step": 4096 + }, + { + "epoch": 0.2283596232094086, + "grad_norm": 0.5925113558769226, + "learning_rate": 8.899821034634974e-05, + "loss": 1.9182, + "step": 4097 + }, + { + "epoch": 0.22841536146257177, + "grad_norm": 0.5289484262466431, + "learning_rate": 8.899263724208266e-05, + "loss": 1.7512, + "step": 4098 + }, + { + "epoch": 0.2284710997157349, + "grad_norm": 0.5516422390937805, + "learning_rate": 8.898706290119647e-05, + "loss": 1.8606, + "step": 4099 + }, + { + "epoch": 0.22852683796889806, + "grad_norm": 0.5578961372375488, + "learning_rate": 8.898148732386795e-05, + "loss": 1.7136, + "step": 4100 + }, + { + "epoch": 0.2285825762220612, + "grad_norm": 0.5643925666809082, + "learning_rate": 8.897591051027394e-05, + "loss": 1.8315, + "step": 4101 + }, + { + "epoch": 0.22863831447522434, + "grad_norm": 0.4974330961704254, + "learning_rate": 8.89703324605913e-05, + "loss": 1.4505, + "step": 4102 + }, + { + "epoch": 0.2286940527283875, + "grad_norm": 0.5316607356071472, + "learning_rate": 8.896475317499691e-05, + "loss": 1.662, + "step": 4103 + }, + { + "epoch": 0.22874979098155063, + "grad_norm": 0.48880115151405334, + "learning_rate": 8.895917265366773e-05, + "loss": 1.6713, + "step": 4104 + }, + { + "epoch": 0.22880552923471378, + "grad_norm": 0.5647329092025757, + "learning_rate": 8.895359089678075e-05, + "loss": 1.6645, + "step": 4105 + }, + { + "epoch": 0.22886126748787694, + "grad_norm": 0.588045060634613, + "learning_rate": 8.894800790451298e-05, + "loss": 1.7344, + "step": 4106 + }, + { + "epoch": 0.22891700574104007, + "grad_norm": 0.5201917290687561, + "learning_rate": 8.894242367704149e-05, + "loss": 1.7137, + "step": 4107 + }, + { + "epoch": 0.22897274399420323, + "grad_norm": 0.5581889152526855, + "learning_rate": 8.893683821454335e-05, + "loss": 1.689, + "step": 4108 + }, + { + "epoch": 0.22902848224736636, + "grad_norm": 0.533208429813385, + "learning_rate": 8.893125151719574e-05, + "loss": 1.7345, + "step": 4109 + }, + { + "epoch": 0.2290842205005295, + "grad_norm": 0.5409815907478333, + "learning_rate": 8.89256635851758e-05, + "loss": 1.6921, + "step": 4110 + }, + { + "epoch": 0.22913995875369267, + "grad_norm": 0.5371890664100647, + "learning_rate": 8.892007441866076e-05, + "loss": 1.7282, + "step": 4111 + }, + { + "epoch": 0.2291956970068558, + "grad_norm": 0.5628719925880432, + "learning_rate": 8.89144840178279e-05, + "loss": 1.6771, + "step": 4112 + }, + { + "epoch": 0.22925143526001895, + "grad_norm": 0.5631751418113708, + "learning_rate": 8.89088923828545e-05, + "loss": 1.9474, + "step": 4113 + }, + { + "epoch": 0.22930717351318208, + "grad_norm": 0.5464017987251282, + "learning_rate": 8.890329951391787e-05, + "loss": 1.7969, + "step": 4114 + }, + { + "epoch": 0.22936291176634524, + "grad_norm": 0.5662708878517151, + "learning_rate": 8.88977054111954e-05, + "loss": 1.6611, + "step": 4115 + }, + { + "epoch": 0.2294186500195084, + "grad_norm": 0.607832670211792, + "learning_rate": 8.889211007486451e-05, + "loss": 1.6558, + "step": 4116 + }, + { + "epoch": 0.22947438827267153, + "grad_norm": 0.5683878064155579, + "learning_rate": 8.888651350510265e-05, + "loss": 1.712, + "step": 4117 + }, + { + "epoch": 0.22953012652583468, + "grad_norm": 0.5762284398078918, + "learning_rate": 8.888091570208729e-05, + "loss": 1.8012, + "step": 4118 + }, + { + "epoch": 0.22958586477899784, + "grad_norm": 0.5987650752067566, + "learning_rate": 8.887531666599598e-05, + "loss": 2.0303, + "step": 4119 + }, + { + "epoch": 0.22964160303216097, + "grad_norm": 0.5141220092773438, + "learning_rate": 8.88697163970063e-05, + "loss": 1.6133, + "step": 4120 + }, + { + "epoch": 0.22969734128532412, + "grad_norm": 0.5571396946907043, + "learning_rate": 8.886411489529583e-05, + "loss": 1.6117, + "step": 4121 + }, + { + "epoch": 0.22975307953848725, + "grad_norm": 0.5717421770095825, + "learning_rate": 8.885851216104222e-05, + "loss": 1.8159, + "step": 4122 + }, + { + "epoch": 0.2298088177916504, + "grad_norm": 0.5314472913742065, + "learning_rate": 8.885290819442319e-05, + "loss": 1.8198, + "step": 4123 + }, + { + "epoch": 0.22986455604481357, + "grad_norm": 0.5760038495063782, + "learning_rate": 8.884730299561642e-05, + "loss": 1.8839, + "step": 4124 + }, + { + "epoch": 0.2299202942979767, + "grad_norm": 0.5187524557113647, + "learning_rate": 8.88416965647997e-05, + "loss": 1.5981, + "step": 4125 + }, + { + "epoch": 0.22997603255113985, + "grad_norm": 0.5539306998252869, + "learning_rate": 8.883608890215083e-05, + "loss": 1.5802, + "step": 4126 + }, + { + "epoch": 0.23003177080430298, + "grad_norm": 0.5440337061882019, + "learning_rate": 8.883048000784764e-05, + "loss": 1.7884, + "step": 4127 + }, + { + "epoch": 0.23008750905746614, + "grad_norm": 0.6190919876098633, + "learning_rate": 8.882486988206803e-05, + "loss": 1.8968, + "step": 4128 + }, + { + "epoch": 0.2301432473106293, + "grad_norm": 0.5481730103492737, + "learning_rate": 8.881925852498991e-05, + "loss": 1.5026, + "step": 4129 + }, + { + "epoch": 0.23019898556379242, + "grad_norm": 0.5920677185058594, + "learning_rate": 8.881364593679124e-05, + "loss": 2.02, + "step": 4130 + }, + { + "epoch": 0.23025472381695558, + "grad_norm": 0.580629289150238, + "learning_rate": 8.880803211765003e-05, + "loss": 1.8447, + "step": 4131 + }, + { + "epoch": 0.2303104620701187, + "grad_norm": 0.5800060033798218, + "learning_rate": 8.880241706774431e-05, + "loss": 1.8952, + "step": 4132 + }, + { + "epoch": 0.23036620032328187, + "grad_norm": 0.5633650422096252, + "learning_rate": 8.879680078725214e-05, + "loss": 1.79, + "step": 4133 + }, + { + "epoch": 0.23042193857644502, + "grad_norm": 0.503121554851532, + "learning_rate": 8.879118327635165e-05, + "loss": 1.31, + "step": 4134 + }, + { + "epoch": 0.23047767682960815, + "grad_norm": 0.5033895373344421, + "learning_rate": 8.8785564535221e-05, + "loss": 1.388, + "step": 4135 + }, + { + "epoch": 0.2305334150827713, + "grad_norm": 0.5460697412490845, + "learning_rate": 8.877994456403838e-05, + "loss": 1.8455, + "step": 4136 + }, + { + "epoch": 0.23058915333593444, + "grad_norm": 0.5005971193313599, + "learning_rate": 8.877432336298201e-05, + "loss": 1.513, + "step": 4137 + }, + { + "epoch": 0.2306448915890976, + "grad_norm": 0.5267760753631592, + "learning_rate": 8.876870093223019e-05, + "loss": 1.6449, + "step": 4138 + }, + { + "epoch": 0.23070062984226075, + "grad_norm": 0.5714914202690125, + "learning_rate": 8.87630772719612e-05, + "loss": 2.0891, + "step": 4139 + }, + { + "epoch": 0.23075636809542388, + "grad_norm": 0.5814961194992065, + "learning_rate": 8.875745238235341e-05, + "loss": 1.6314, + "step": 4140 + }, + { + "epoch": 0.23081210634858704, + "grad_norm": 0.5237919092178345, + "learning_rate": 8.87518262635852e-05, + "loss": 1.5437, + "step": 4141 + }, + { + "epoch": 0.2308678446017502, + "grad_norm": 0.5390162467956543, + "learning_rate": 8.8746198915835e-05, + "loss": 1.8075, + "step": 4142 + }, + { + "epoch": 0.23092358285491332, + "grad_norm": 0.5281346440315247, + "learning_rate": 8.874057033928128e-05, + "loss": 1.7196, + "step": 4143 + }, + { + "epoch": 0.23097932110807648, + "grad_norm": 0.5769410133361816, + "learning_rate": 8.873494053410254e-05, + "loss": 1.7623, + "step": 4144 + }, + { + "epoch": 0.2310350593612396, + "grad_norm": 0.5773770213127136, + "learning_rate": 8.872930950047733e-05, + "loss": 1.6683, + "step": 4145 + }, + { + "epoch": 0.23109079761440277, + "grad_norm": 0.5479909777641296, + "learning_rate": 8.872367723858422e-05, + "loss": 1.8277, + "step": 4146 + }, + { + "epoch": 0.23114653586756592, + "grad_norm": 0.5558038949966431, + "learning_rate": 8.871804374860185e-05, + "loss": 1.9413, + "step": 4147 + }, + { + "epoch": 0.23120227412072905, + "grad_norm": 0.5571532249450684, + "learning_rate": 8.871240903070888e-05, + "loss": 1.7471, + "step": 4148 + }, + { + "epoch": 0.2312580123738922, + "grad_norm": 0.63371741771698, + "learning_rate": 8.870677308508399e-05, + "loss": 2.0195, + "step": 4149 + }, + { + "epoch": 0.23131375062705534, + "grad_norm": 0.5300304889678955, + "learning_rate": 8.870113591190595e-05, + "loss": 1.5686, + "step": 4150 + }, + { + "epoch": 0.2313694888802185, + "grad_norm": 0.6006084680557251, + "learning_rate": 8.869549751135352e-05, + "loss": 1.7178, + "step": 4151 + }, + { + "epoch": 0.23142522713338165, + "grad_norm": 0.5930531024932861, + "learning_rate": 8.868985788360551e-05, + "loss": 1.6998, + "step": 4152 + }, + { + "epoch": 0.23148096538654478, + "grad_norm": 0.5450523495674133, + "learning_rate": 8.868421702884077e-05, + "loss": 1.5045, + "step": 4153 + }, + { + "epoch": 0.23153670363970794, + "grad_norm": 0.519468367099762, + "learning_rate": 8.867857494723824e-05, + "loss": 1.6035, + "step": 4154 + }, + { + "epoch": 0.23159244189287106, + "grad_norm": 0.5567930936813354, + "learning_rate": 8.867293163897681e-05, + "loss": 1.8108, + "step": 4155 + }, + { + "epoch": 0.23164818014603422, + "grad_norm": 0.5138580799102783, + "learning_rate": 8.866728710423547e-05, + "loss": 1.5952, + "step": 4156 + }, + { + "epoch": 0.23170391839919738, + "grad_norm": 0.5398350954055786, + "learning_rate": 8.866164134319323e-05, + "loss": 1.8621, + "step": 4157 + }, + { + "epoch": 0.2317596566523605, + "grad_norm": 0.5708958506584167, + "learning_rate": 8.865599435602915e-05, + "loss": 1.5408, + "step": 4158 + }, + { + "epoch": 0.23181539490552366, + "grad_norm": 0.62980717420578, + "learning_rate": 8.86503461429223e-05, + "loss": 2.2779, + "step": 4159 + }, + { + "epoch": 0.2318711331586868, + "grad_norm": 0.5782346129417419, + "learning_rate": 8.86446967040518e-05, + "loss": 1.6574, + "step": 4160 + }, + { + "epoch": 0.23192687141184995, + "grad_norm": 0.5406448841094971, + "learning_rate": 8.863904603959686e-05, + "loss": 1.6591, + "step": 4161 + }, + { + "epoch": 0.2319826096650131, + "grad_norm": 0.533285915851593, + "learning_rate": 8.863339414973664e-05, + "loss": 1.7869, + "step": 4162 + }, + { + "epoch": 0.23203834791817624, + "grad_norm": 0.5359031558036804, + "learning_rate": 8.862774103465042e-05, + "loss": 1.8322, + "step": 4163 + }, + { + "epoch": 0.2320940861713394, + "grad_norm": 0.5305787920951843, + "learning_rate": 8.862208669451748e-05, + "loss": 1.5869, + "step": 4164 + }, + { + "epoch": 0.23214982442450255, + "grad_norm": 0.5482218861579895, + "learning_rate": 8.861643112951712e-05, + "loss": 1.9482, + "step": 4165 + }, + { + "epoch": 0.23220556267766568, + "grad_norm": 0.5915202498435974, + "learning_rate": 8.86107743398287e-05, + "loss": 1.9292, + "step": 4166 + }, + { + "epoch": 0.23226130093082883, + "grad_norm": 0.5175179243087769, + "learning_rate": 8.860511632563166e-05, + "loss": 1.5677, + "step": 4167 + }, + { + "epoch": 0.23231703918399196, + "grad_norm": 0.5698404908180237, + "learning_rate": 8.85994570871054e-05, + "loss": 1.8537, + "step": 4168 + }, + { + "epoch": 0.23237277743715512, + "grad_norm": 0.5476871728897095, + "learning_rate": 8.859379662442941e-05, + "loss": 1.7031, + "step": 4169 + }, + { + "epoch": 0.23242851569031828, + "grad_norm": 0.5611745119094849, + "learning_rate": 8.858813493778322e-05, + "loss": 1.9365, + "step": 4170 + }, + { + "epoch": 0.2324842539434814, + "grad_norm": 0.5908852219581604, + "learning_rate": 8.858247202734637e-05, + "loss": 1.7084, + "step": 4171 + }, + { + "epoch": 0.23253999219664456, + "grad_norm": 0.5042490363121033, + "learning_rate": 8.857680789329844e-05, + "loss": 1.6353, + "step": 4172 + }, + { + "epoch": 0.2325957304498077, + "grad_norm": 0.535675048828125, + "learning_rate": 8.85711425358191e-05, + "loss": 1.523, + "step": 4173 + }, + { + "epoch": 0.23265146870297085, + "grad_norm": 0.5372074246406555, + "learning_rate": 8.8565475955088e-05, + "loss": 1.38, + "step": 4174 + }, + { + "epoch": 0.232707206956134, + "grad_norm": 0.554507315158844, + "learning_rate": 8.855980815128486e-05, + "loss": 1.5261, + "step": 4175 + }, + { + "epoch": 0.23276294520929713, + "grad_norm": 0.5450062155723572, + "learning_rate": 8.85541391245894e-05, + "loss": 1.7725, + "step": 4176 + }, + { + "epoch": 0.2328186834624603, + "grad_norm": 0.5121927857398987, + "learning_rate": 8.854846887518147e-05, + "loss": 1.4857, + "step": 4177 + }, + { + "epoch": 0.23287442171562342, + "grad_norm": 0.5284276008605957, + "learning_rate": 8.854279740324086e-05, + "loss": 1.8393, + "step": 4178 + }, + { + "epoch": 0.23293015996878658, + "grad_norm": 0.5464218258857727, + "learning_rate": 8.85371247089474e-05, + "loss": 1.6455, + "step": 4179 + }, + { + "epoch": 0.23298589822194973, + "grad_norm": 0.515756368637085, + "learning_rate": 8.853145079248106e-05, + "loss": 1.6739, + "step": 4180 + }, + { + "epoch": 0.23304163647511286, + "grad_norm": 0.5167007446289062, + "learning_rate": 8.852577565402175e-05, + "loss": 1.6312, + "step": 4181 + }, + { + "epoch": 0.23309737472827602, + "grad_norm": 0.5863040089607239, + "learning_rate": 8.852009929374945e-05, + "loss": 1.8519, + "step": 4182 + }, + { + "epoch": 0.23315311298143915, + "grad_norm": 0.5061371922492981, + "learning_rate": 8.851442171184418e-05, + "loss": 1.6562, + "step": 4183 + }, + { + "epoch": 0.2332088512346023, + "grad_norm": 0.5501469969749451, + "learning_rate": 8.850874290848603e-05, + "loss": 1.7597, + "step": 4184 + }, + { + "epoch": 0.23326458948776546, + "grad_norm": 0.5034657716751099, + "learning_rate": 8.850306288385505e-05, + "loss": 1.7217, + "step": 4185 + }, + { + "epoch": 0.2333203277409286, + "grad_norm": 0.5563570857048035, + "learning_rate": 8.849738163813143e-05, + "loss": 1.7315, + "step": 4186 + }, + { + "epoch": 0.23337606599409175, + "grad_norm": 0.5461295247077942, + "learning_rate": 8.849169917149531e-05, + "loss": 1.7419, + "step": 4187 + }, + { + "epoch": 0.2334318042472549, + "grad_norm": 0.5286983251571655, + "learning_rate": 8.848601548412691e-05, + "loss": 1.8088, + "step": 4188 + }, + { + "epoch": 0.23348754250041803, + "grad_norm": 0.5308994650840759, + "learning_rate": 8.848033057620651e-05, + "loss": 1.6436, + "step": 4189 + }, + { + "epoch": 0.2335432807535812, + "grad_norm": 0.5667473673820496, + "learning_rate": 8.847464444791435e-05, + "loss": 1.6382, + "step": 4190 + }, + { + "epoch": 0.23359901900674432, + "grad_norm": 0.5432576537132263, + "learning_rate": 8.846895709943082e-05, + "loss": 1.8993, + "step": 4191 + }, + { + "epoch": 0.23365475725990748, + "grad_norm": 0.6006546020507812, + "learning_rate": 8.846326853093623e-05, + "loss": 1.7459, + "step": 4192 + }, + { + "epoch": 0.23371049551307063, + "grad_norm": 0.5638506412506104, + "learning_rate": 8.845757874261104e-05, + "loss": 1.618, + "step": 4193 + }, + { + "epoch": 0.23376623376623376, + "grad_norm": 0.5464212894439697, + "learning_rate": 8.845188773463566e-05, + "loss": 1.6731, + "step": 4194 + }, + { + "epoch": 0.23382197201939692, + "grad_norm": 0.5781604051589966, + "learning_rate": 8.84461955071906e-05, + "loss": 1.8368, + "step": 4195 + }, + { + "epoch": 0.23387771027256005, + "grad_norm": 0.5308955907821655, + "learning_rate": 8.844050206045637e-05, + "loss": 1.805, + "step": 4196 + }, + { + "epoch": 0.2339334485257232, + "grad_norm": 0.5154343843460083, + "learning_rate": 8.843480739461356e-05, + "loss": 1.4806, + "step": 4197 + }, + { + "epoch": 0.23398918677888636, + "grad_norm": 0.5477091073989868, + "learning_rate": 8.842911150984272e-05, + "loss": 1.7506, + "step": 4198 + }, + { + "epoch": 0.2340449250320495, + "grad_norm": 0.5401119589805603, + "learning_rate": 8.842341440632454e-05, + "loss": 1.8434, + "step": 4199 + }, + { + "epoch": 0.23410066328521265, + "grad_norm": 0.5683028697967529, + "learning_rate": 8.841771608423967e-05, + "loss": 1.6289, + "step": 4200 + }, + { + "epoch": 0.23415640153837577, + "grad_norm": 0.5980592370033264, + "learning_rate": 8.841201654376883e-05, + "loss": 1.782, + "step": 4201 + }, + { + "epoch": 0.23421213979153893, + "grad_norm": 0.5431941151618958, + "learning_rate": 8.84063157850928e-05, + "loss": 1.7904, + "step": 4202 + }, + { + "epoch": 0.2342678780447021, + "grad_norm": 0.6389545202255249, + "learning_rate": 8.840061380839235e-05, + "loss": 1.5506, + "step": 4203 + }, + { + "epoch": 0.23432361629786522, + "grad_norm": 0.5594901442527771, + "learning_rate": 8.839491061384832e-05, + "loss": 1.7914, + "step": 4204 + }, + { + "epoch": 0.23437935455102837, + "grad_norm": 0.5211427211761475, + "learning_rate": 8.838920620164157e-05, + "loss": 1.5682, + "step": 4205 + }, + { + "epoch": 0.23443509280419153, + "grad_norm": 0.5244554281234741, + "learning_rate": 8.838350057195304e-05, + "loss": 1.6598, + "step": 4206 + }, + { + "epoch": 0.23449083105735466, + "grad_norm": 0.5590394735336304, + "learning_rate": 8.837779372496367e-05, + "loss": 1.6682, + "step": 4207 + }, + { + "epoch": 0.23454656931051782, + "grad_norm": 0.5445299744606018, + "learning_rate": 8.837208566085441e-05, + "loss": 1.8047, + "step": 4208 + }, + { + "epoch": 0.23460230756368095, + "grad_norm": 0.5209025144577026, + "learning_rate": 8.836637637980636e-05, + "loss": 1.6225, + "step": 4209 + }, + { + "epoch": 0.2346580458168441, + "grad_norm": 0.5524556040763855, + "learning_rate": 8.836066588200051e-05, + "loss": 1.7139, + "step": 4210 + }, + { + "epoch": 0.23471378407000726, + "grad_norm": 0.5641475915908813, + "learning_rate": 8.8354954167618e-05, + "loss": 1.7928, + "step": 4211 + }, + { + "epoch": 0.2347695223231704, + "grad_norm": 0.57920241355896, + "learning_rate": 8.834924123683998e-05, + "loss": 1.7035, + "step": 4212 + }, + { + "epoch": 0.23482526057633354, + "grad_norm": 0.5374131202697754, + "learning_rate": 8.834352708984762e-05, + "loss": 1.6887, + "step": 4213 + }, + { + "epoch": 0.23488099882949667, + "grad_norm": 0.5739797353744507, + "learning_rate": 8.833781172682214e-05, + "loss": 1.7476, + "step": 4214 + }, + { + "epoch": 0.23493673708265983, + "grad_norm": 0.5460266470909119, + "learning_rate": 8.833209514794479e-05, + "loss": 1.569, + "step": 4215 + }, + { + "epoch": 0.234992475335823, + "grad_norm": 0.5776944160461426, + "learning_rate": 8.832637735339688e-05, + "loss": 1.6762, + "step": 4216 + }, + { + "epoch": 0.23504821358898612, + "grad_norm": 0.593519926071167, + "learning_rate": 8.832065834335973e-05, + "loss": 1.6699, + "step": 4217 + }, + { + "epoch": 0.23510395184214927, + "grad_norm": 0.5690516233444214, + "learning_rate": 8.831493811801472e-05, + "loss": 1.8292, + "step": 4218 + }, + { + "epoch": 0.2351596900953124, + "grad_norm": 0.5436887741088867, + "learning_rate": 8.830921667754328e-05, + "loss": 1.6958, + "step": 4219 + }, + { + "epoch": 0.23521542834847556, + "grad_norm": 0.54433673620224, + "learning_rate": 8.830349402212683e-05, + "loss": 1.7544, + "step": 4220 + }, + { + "epoch": 0.23527116660163871, + "grad_norm": 0.5694179534912109, + "learning_rate": 8.82977701519469e-05, + "loss": 1.676, + "step": 4221 + }, + { + "epoch": 0.23532690485480184, + "grad_norm": 0.5544805526733398, + "learning_rate": 8.829204506718496e-05, + "loss": 1.7395, + "step": 4222 + }, + { + "epoch": 0.235382643107965, + "grad_norm": 0.586121141910553, + "learning_rate": 8.828631876802263e-05, + "loss": 1.8418, + "step": 4223 + }, + { + "epoch": 0.23543838136112813, + "grad_norm": 0.5376494526863098, + "learning_rate": 8.828059125464148e-05, + "loss": 1.5981, + "step": 4224 + }, + { + "epoch": 0.2354941196142913, + "grad_norm": 0.5764834880828857, + "learning_rate": 8.827486252722316e-05, + "loss": 1.9862, + "step": 4225 + }, + { + "epoch": 0.23554985786745444, + "grad_norm": 0.6348791122436523, + "learning_rate": 8.826913258594937e-05, + "loss": 1.9931, + "step": 4226 + }, + { + "epoch": 0.23560559612061757, + "grad_norm": 0.5736886262893677, + "learning_rate": 8.826340143100182e-05, + "loss": 1.8651, + "step": 4227 + }, + { + "epoch": 0.23566133437378073, + "grad_norm": 0.5940203070640564, + "learning_rate": 8.825766906256228e-05, + "loss": 1.6837, + "step": 4228 + }, + { + "epoch": 0.23571707262694389, + "grad_norm": 0.5036525726318359, + "learning_rate": 8.825193548081252e-05, + "loss": 1.4064, + "step": 4229 + }, + { + "epoch": 0.23577281088010701, + "grad_norm": 0.5096335411071777, + "learning_rate": 8.824620068593439e-05, + "loss": 1.7501, + "step": 4230 + }, + { + "epoch": 0.23582854913327017, + "grad_norm": 0.5474448204040527, + "learning_rate": 8.824046467810976e-05, + "loss": 1.7263, + "step": 4231 + }, + { + "epoch": 0.2358842873864333, + "grad_norm": 0.5364823937416077, + "learning_rate": 8.823472745752055e-05, + "loss": 1.7752, + "step": 4232 + }, + { + "epoch": 0.23594002563959646, + "grad_norm": 0.5261183977127075, + "learning_rate": 8.822898902434873e-05, + "loss": 1.7809, + "step": 4233 + }, + { + "epoch": 0.2359957638927596, + "grad_norm": 0.5040357708930969, + "learning_rate": 8.822324937877624e-05, + "loss": 1.5033, + "step": 4234 + }, + { + "epoch": 0.23605150214592274, + "grad_norm": 0.534517228603363, + "learning_rate": 8.821750852098515e-05, + "loss": 1.735, + "step": 4235 + }, + { + "epoch": 0.2361072403990859, + "grad_norm": 0.5336146950721741, + "learning_rate": 8.821176645115752e-05, + "loss": 1.8211, + "step": 4236 + }, + { + "epoch": 0.23616297865224903, + "grad_norm": 0.5576988458633423, + "learning_rate": 8.820602316947544e-05, + "loss": 1.6501, + "step": 4237 + }, + { + "epoch": 0.23621871690541218, + "grad_norm": 0.6140468716621399, + "learning_rate": 8.820027867612107e-05, + "loss": 1.9297, + "step": 4238 + }, + { + "epoch": 0.23627445515857534, + "grad_norm": 0.6102777123451233, + "learning_rate": 8.819453297127657e-05, + "loss": 1.7881, + "step": 4239 + }, + { + "epoch": 0.23633019341173847, + "grad_norm": 0.5396928787231445, + "learning_rate": 8.818878605512418e-05, + "loss": 1.7629, + "step": 4240 + }, + { + "epoch": 0.23638593166490163, + "grad_norm": 0.5476622581481934, + "learning_rate": 8.818303792784615e-05, + "loss": 1.939, + "step": 4241 + }, + { + "epoch": 0.23644166991806476, + "grad_norm": 0.5725302696228027, + "learning_rate": 8.817728858962478e-05, + "loss": 1.7058, + "step": 4242 + }, + { + "epoch": 0.2364974081712279, + "grad_norm": 0.5522921085357666, + "learning_rate": 8.817153804064241e-05, + "loss": 1.6284, + "step": 4243 + }, + { + "epoch": 0.23655314642439107, + "grad_norm": 0.5554071664810181, + "learning_rate": 8.81657862810814e-05, + "loss": 1.7203, + "step": 4244 + }, + { + "epoch": 0.2366088846775542, + "grad_norm": 0.6202051639556885, + "learning_rate": 8.816003331112419e-05, + "loss": 2.0629, + "step": 4245 + }, + { + "epoch": 0.23666462293071736, + "grad_norm": 0.5647374391555786, + "learning_rate": 8.81542791309532e-05, + "loss": 1.7256, + "step": 4246 + }, + { + "epoch": 0.23672036118388048, + "grad_norm": 0.5261071920394897, + "learning_rate": 8.814852374075093e-05, + "loss": 1.6476, + "step": 4247 + }, + { + "epoch": 0.23677609943704364, + "grad_norm": 0.5051866173744202, + "learning_rate": 8.81427671406999e-05, + "loss": 1.57, + "step": 4248 + }, + { + "epoch": 0.2368318376902068, + "grad_norm": 0.5553388595581055, + "learning_rate": 8.81370093309827e-05, + "loss": 1.497, + "step": 4249 + }, + { + "epoch": 0.23688757594336993, + "grad_norm": 0.6159742474555969, + "learning_rate": 8.813125031178191e-05, + "loss": 1.9324, + "step": 4250 + }, + { + "epoch": 0.23694331419653308, + "grad_norm": 0.5158507227897644, + "learning_rate": 8.812549008328017e-05, + "loss": 1.7841, + "step": 4251 + }, + { + "epoch": 0.23699905244969624, + "grad_norm": 0.5447210073471069, + "learning_rate": 8.811972864566018e-05, + "loss": 1.6966, + "step": 4252 + }, + { + "epoch": 0.23705479070285937, + "grad_norm": 0.5115744471549988, + "learning_rate": 8.811396599910467e-05, + "loss": 1.6449, + "step": 4253 + }, + { + "epoch": 0.23711052895602253, + "grad_norm": 0.5265628695487976, + "learning_rate": 8.810820214379636e-05, + "loss": 1.8372, + "step": 4254 + }, + { + "epoch": 0.23716626720918565, + "grad_norm": 0.5546838045120239, + "learning_rate": 8.810243707991805e-05, + "loss": 1.9996, + "step": 4255 + }, + { + "epoch": 0.2372220054623488, + "grad_norm": 0.5540011525154114, + "learning_rate": 8.809667080765262e-05, + "loss": 1.7619, + "step": 4256 + }, + { + "epoch": 0.23727774371551197, + "grad_norm": 0.5753396153450012, + "learning_rate": 8.809090332718288e-05, + "loss": 1.8621, + "step": 4257 + }, + { + "epoch": 0.2373334819686751, + "grad_norm": 0.5528965592384338, + "learning_rate": 8.808513463869179e-05, + "loss": 1.6625, + "step": 4258 + }, + { + "epoch": 0.23738922022183825, + "grad_norm": 0.5542230010032654, + "learning_rate": 8.80793647423623e-05, + "loss": 1.5929, + "step": 4259 + }, + { + "epoch": 0.23744495847500138, + "grad_norm": 0.6071727275848389, + "learning_rate": 8.807359363837734e-05, + "loss": 1.7551, + "step": 4260 + }, + { + "epoch": 0.23750069672816454, + "grad_norm": 0.5722533464431763, + "learning_rate": 8.806782132691999e-05, + "loss": 1.9474, + "step": 4261 + }, + { + "epoch": 0.2375564349813277, + "grad_norm": 0.5362473130226135, + "learning_rate": 8.806204780817331e-05, + "loss": 1.6914, + "step": 4262 + }, + { + "epoch": 0.23761217323449083, + "grad_norm": 0.519892156124115, + "learning_rate": 8.805627308232036e-05, + "loss": 1.4148, + "step": 4263 + }, + { + "epoch": 0.23766791148765398, + "grad_norm": 0.5315799713134766, + "learning_rate": 8.805049714954434e-05, + "loss": 1.8304, + "step": 4264 + }, + { + "epoch": 0.2377236497408171, + "grad_norm": 0.5093747973442078, + "learning_rate": 8.804472001002839e-05, + "loss": 1.4575, + "step": 4265 + }, + { + "epoch": 0.23777938799398027, + "grad_norm": 0.5335510969161987, + "learning_rate": 8.803894166395574e-05, + "loss": 1.515, + "step": 4266 + }, + { + "epoch": 0.23783512624714342, + "grad_norm": 0.5546256303787231, + "learning_rate": 8.803316211150964e-05, + "loss": 1.657, + "step": 4267 + }, + { + "epoch": 0.23789086450030655, + "grad_norm": 0.5256768465042114, + "learning_rate": 8.802738135287338e-05, + "loss": 1.5228, + "step": 4268 + }, + { + "epoch": 0.2379466027534697, + "grad_norm": 0.5291659235954285, + "learning_rate": 8.802159938823031e-05, + "loss": 1.5667, + "step": 4269 + }, + { + "epoch": 0.23800234100663284, + "grad_norm": 0.5859813094139099, + "learning_rate": 8.801581621776379e-05, + "loss": 1.9385, + "step": 4270 + }, + { + "epoch": 0.238058079259796, + "grad_norm": 0.6084904670715332, + "learning_rate": 8.801003184165722e-05, + "loss": 1.9139, + "step": 4271 + }, + { + "epoch": 0.23811381751295915, + "grad_norm": 0.5245258212089539, + "learning_rate": 8.800424626009407e-05, + "loss": 1.8107, + "step": 4272 + }, + { + "epoch": 0.23816955576612228, + "grad_norm": 0.5182399749755859, + "learning_rate": 8.799845947325777e-05, + "loss": 1.72, + "step": 4273 + }, + { + "epoch": 0.23822529401928544, + "grad_norm": 0.5252156257629395, + "learning_rate": 8.799267148133192e-05, + "loss": 1.6711, + "step": 4274 + }, + { + "epoch": 0.2382810322724486, + "grad_norm": 0.49757280945777893, + "learning_rate": 8.798688228450002e-05, + "loss": 1.5716, + "step": 4275 + }, + { + "epoch": 0.23833677052561172, + "grad_norm": 0.5291200876235962, + "learning_rate": 8.798109188294572e-05, + "loss": 1.6498, + "step": 4276 + }, + { + "epoch": 0.23839250877877488, + "grad_norm": 0.5830451250076294, + "learning_rate": 8.797530027685261e-05, + "loss": 1.8761, + "step": 4277 + }, + { + "epoch": 0.238448247031938, + "grad_norm": 0.5453559756278992, + "learning_rate": 8.796950746640439e-05, + "loss": 1.6984, + "step": 4278 + }, + { + "epoch": 0.23850398528510117, + "grad_norm": 0.5068353414535522, + "learning_rate": 8.796371345178476e-05, + "loss": 1.3414, + "step": 4279 + }, + { + "epoch": 0.23855972353826432, + "grad_norm": 0.5567828416824341, + "learning_rate": 8.79579182331775e-05, + "loss": 1.716, + "step": 4280 + }, + { + "epoch": 0.23861546179142745, + "grad_norm": 0.5418634414672852, + "learning_rate": 8.795212181076638e-05, + "loss": 1.6889, + "step": 4281 + }, + { + "epoch": 0.2386712000445906, + "grad_norm": 0.5291851162910461, + "learning_rate": 8.794632418473522e-05, + "loss": 1.6941, + "step": 4282 + }, + { + "epoch": 0.23872693829775374, + "grad_norm": 0.5776856541633606, + "learning_rate": 8.794052535526792e-05, + "loss": 1.756, + "step": 4283 + }, + { + "epoch": 0.2387826765509169, + "grad_norm": 0.5982547998428345, + "learning_rate": 8.793472532254836e-05, + "loss": 1.8349, + "step": 4284 + }, + { + "epoch": 0.23883841480408005, + "grad_norm": 0.5404837727546692, + "learning_rate": 8.792892408676048e-05, + "loss": 1.6617, + "step": 4285 + }, + { + "epoch": 0.23889415305724318, + "grad_norm": 0.5049643516540527, + "learning_rate": 8.792312164808827e-05, + "loss": 1.5132, + "step": 4286 + }, + { + "epoch": 0.23894989131040634, + "grad_norm": 0.5474380254745483, + "learning_rate": 8.791731800671575e-05, + "loss": 1.7937, + "step": 4287 + }, + { + "epoch": 0.23900562956356947, + "grad_norm": 0.5853757858276367, + "learning_rate": 8.791151316282698e-05, + "loss": 1.8488, + "step": 4288 + }, + { + "epoch": 0.23906136781673262, + "grad_norm": 0.574220597743988, + "learning_rate": 8.790570711660604e-05, + "loss": 1.7211, + "step": 4289 + }, + { + "epoch": 0.23911710606989578, + "grad_norm": 0.580944836139679, + "learning_rate": 8.789989986823707e-05, + "loss": 1.6015, + "step": 4290 + }, + { + "epoch": 0.2391728443230589, + "grad_norm": 0.5716251730918884, + "learning_rate": 8.789409141790426e-05, + "loss": 1.7375, + "step": 4291 + }, + { + "epoch": 0.23922858257622207, + "grad_norm": 0.5204554200172424, + "learning_rate": 8.788828176579182e-05, + "loss": 1.7231, + "step": 4292 + }, + { + "epoch": 0.2392843208293852, + "grad_norm": 0.529961884021759, + "learning_rate": 8.788247091208397e-05, + "loss": 1.7355, + "step": 4293 + }, + { + "epoch": 0.23934005908254835, + "grad_norm": 0.5950244665145874, + "learning_rate": 8.787665885696502e-05, + "loss": 2.0786, + "step": 4294 + }, + { + "epoch": 0.2393957973357115, + "grad_norm": 0.5200558304786682, + "learning_rate": 8.78708456006193e-05, + "loss": 1.6045, + "step": 4295 + }, + { + "epoch": 0.23945153558887464, + "grad_norm": 0.5256621241569519, + "learning_rate": 8.786503114323113e-05, + "loss": 1.6679, + "step": 4296 + }, + { + "epoch": 0.2395072738420378, + "grad_norm": 0.5340785980224609, + "learning_rate": 8.785921548498494e-05, + "loss": 1.6646, + "step": 4297 + }, + { + "epoch": 0.23956301209520095, + "grad_norm": 0.5381552577018738, + "learning_rate": 8.785339862606521e-05, + "loss": 1.7888, + "step": 4298 + }, + { + "epoch": 0.23961875034836408, + "grad_norm": 0.6692368984222412, + "learning_rate": 8.784758056665634e-05, + "loss": 1.9363, + "step": 4299 + }, + { + "epoch": 0.23967448860152724, + "grad_norm": 0.5429602265357971, + "learning_rate": 8.784176130694289e-05, + "loss": 1.8477, + "step": 4300 + }, + { + "epoch": 0.23973022685469036, + "grad_norm": 0.5760909914970398, + "learning_rate": 8.783594084710941e-05, + "loss": 1.9106, + "step": 4301 + }, + { + "epoch": 0.23978596510785352, + "grad_norm": 0.5410770773887634, + "learning_rate": 8.783011918734048e-05, + "loss": 1.7685, + "step": 4302 + }, + { + "epoch": 0.23984170336101668, + "grad_norm": 0.6343144774436951, + "learning_rate": 8.782429632782073e-05, + "loss": 1.6641, + "step": 4303 + }, + { + "epoch": 0.2398974416141798, + "grad_norm": 0.5951781868934631, + "learning_rate": 8.781847226873484e-05, + "loss": 1.8908, + "step": 4304 + }, + { + "epoch": 0.23995317986734296, + "grad_norm": 0.5187268257141113, + "learning_rate": 8.78126470102675e-05, + "loss": 1.5571, + "step": 4305 + }, + { + "epoch": 0.2400089181205061, + "grad_norm": 0.5376867651939392, + "learning_rate": 8.780682055260348e-05, + "loss": 1.514, + "step": 4306 + }, + { + "epoch": 0.24006465637366925, + "grad_norm": 0.5534177422523499, + "learning_rate": 8.780099289592751e-05, + "loss": 1.581, + "step": 4307 + }, + { + "epoch": 0.2401203946268324, + "grad_norm": 0.5672261714935303, + "learning_rate": 8.779516404042446e-05, + "loss": 1.7344, + "step": 4308 + }, + { + "epoch": 0.24017613287999554, + "grad_norm": 0.5509449243545532, + "learning_rate": 8.778933398627915e-05, + "loss": 1.7162, + "step": 4309 + }, + { + "epoch": 0.2402318711331587, + "grad_norm": 0.5842772126197815, + "learning_rate": 8.778350273367653e-05, + "loss": 1.7958, + "step": 4310 + }, + { + "epoch": 0.24028760938632182, + "grad_norm": 0.50345379114151, + "learning_rate": 8.777767028280145e-05, + "loss": 1.4958, + "step": 4311 + }, + { + "epoch": 0.24034334763948498, + "grad_norm": 0.5337620377540588, + "learning_rate": 8.777183663383896e-05, + "loss": 1.6876, + "step": 4312 + }, + { + "epoch": 0.24039908589264813, + "grad_norm": 0.5183177590370178, + "learning_rate": 8.776600178697402e-05, + "loss": 1.7538, + "step": 4313 + }, + { + "epoch": 0.24045482414581126, + "grad_norm": 0.5510264039039612, + "learning_rate": 8.776016574239171e-05, + "loss": 1.7722, + "step": 4314 + }, + { + "epoch": 0.24051056239897442, + "grad_norm": 0.5638562440872192, + "learning_rate": 8.77543285002771e-05, + "loss": 1.8447, + "step": 4315 + }, + { + "epoch": 0.24056630065213755, + "grad_norm": 0.6304780840873718, + "learning_rate": 8.774849006081529e-05, + "loss": 2.111, + "step": 4316 + }, + { + "epoch": 0.2406220389053007, + "grad_norm": 0.5731822848320007, + "learning_rate": 8.774265042419148e-05, + "loss": 1.9022, + "step": 4317 + }, + { + "epoch": 0.24067777715846386, + "grad_norm": 0.5105111002922058, + "learning_rate": 8.773680959059086e-05, + "loss": 1.4723, + "step": 4318 + }, + { + "epoch": 0.240733515411627, + "grad_norm": 0.5694832801818848, + "learning_rate": 8.773096756019866e-05, + "loss": 1.8138, + "step": 4319 + }, + { + "epoch": 0.24078925366479015, + "grad_norm": 0.5039976835250854, + "learning_rate": 8.772512433320014e-05, + "loss": 1.5152, + "step": 4320 + }, + { + "epoch": 0.2408449919179533, + "grad_norm": 0.5481953024864197, + "learning_rate": 8.771927990978063e-05, + "loss": 1.7373, + "step": 4321 + }, + { + "epoch": 0.24090073017111643, + "grad_norm": 0.5046210885047913, + "learning_rate": 8.771343429012549e-05, + "loss": 1.3736, + "step": 4322 + }, + { + "epoch": 0.2409564684242796, + "grad_norm": 0.5144927501678467, + "learning_rate": 8.77075874744201e-05, + "loss": 1.7854, + "step": 4323 + }, + { + "epoch": 0.24101220667744272, + "grad_norm": 0.5863038301467896, + "learning_rate": 8.770173946284987e-05, + "loss": 1.9596, + "step": 4324 + }, + { + "epoch": 0.24106794493060588, + "grad_norm": 0.5546390414237976, + "learning_rate": 8.76958902556003e-05, + "loss": 1.6905, + "step": 4325 + }, + { + "epoch": 0.24112368318376903, + "grad_norm": 0.5615156888961792, + "learning_rate": 8.769003985285686e-05, + "loss": 1.8015, + "step": 4326 + }, + { + "epoch": 0.24117942143693216, + "grad_norm": 0.5112027525901794, + "learning_rate": 8.76841882548051e-05, + "loss": 1.7408, + "step": 4327 + }, + { + "epoch": 0.24123515969009532, + "grad_norm": 0.523891270160675, + "learning_rate": 8.767833546163062e-05, + "loss": 1.6473, + "step": 4328 + }, + { + "epoch": 0.24129089794325845, + "grad_norm": 0.5263711214065552, + "learning_rate": 8.767248147351902e-05, + "loss": 1.724, + "step": 4329 + }, + { + "epoch": 0.2413466361964216, + "grad_norm": 0.5724520683288574, + "learning_rate": 8.766662629065594e-05, + "loss": 1.7469, + "step": 4330 + }, + { + "epoch": 0.24140237444958476, + "grad_norm": 0.5471790432929993, + "learning_rate": 8.76607699132271e-05, + "loss": 1.7262, + "step": 4331 + }, + { + "epoch": 0.2414581127027479, + "grad_norm": 0.6246349215507507, + "learning_rate": 8.76549123414182e-05, + "loss": 2.0055, + "step": 4332 + }, + { + "epoch": 0.24151385095591105, + "grad_norm": 0.5492396354675293, + "learning_rate": 8.764905357541505e-05, + "loss": 1.7602, + "step": 4333 + }, + { + "epoch": 0.24156958920907418, + "grad_norm": 0.5340796113014221, + "learning_rate": 8.76431936154034e-05, + "loss": 1.7666, + "step": 4334 + }, + { + "epoch": 0.24162532746223733, + "grad_norm": 0.5311720967292786, + "learning_rate": 8.763733246156913e-05, + "loss": 1.5892, + "step": 4335 + }, + { + "epoch": 0.2416810657154005, + "grad_norm": 0.5926803350448608, + "learning_rate": 8.763147011409811e-05, + "loss": 1.9398, + "step": 4336 + }, + { + "epoch": 0.24173680396856362, + "grad_norm": 0.5204175710678101, + "learning_rate": 8.762560657317629e-05, + "loss": 1.4019, + "step": 4337 + }, + { + "epoch": 0.24179254222172678, + "grad_norm": 0.5834428071975708, + "learning_rate": 8.761974183898957e-05, + "loss": 1.7063, + "step": 4338 + }, + { + "epoch": 0.2418482804748899, + "grad_norm": 0.5776971578598022, + "learning_rate": 8.7613875911724e-05, + "loss": 1.7957, + "step": 4339 + }, + { + "epoch": 0.24190401872805306, + "grad_norm": 0.5160627365112305, + "learning_rate": 8.760800879156558e-05, + "loss": 1.5686, + "step": 4340 + }, + { + "epoch": 0.24195975698121622, + "grad_norm": 0.5783469676971436, + "learning_rate": 8.760214047870039e-05, + "loss": 2.0046, + "step": 4341 + }, + { + "epoch": 0.24201549523437935, + "grad_norm": 0.5625891089439392, + "learning_rate": 8.759627097331455e-05, + "loss": 1.6902, + "step": 4342 + }, + { + "epoch": 0.2420712334875425, + "grad_norm": 0.5326409935951233, + "learning_rate": 8.759040027559418e-05, + "loss": 1.9046, + "step": 4343 + }, + { + "epoch": 0.24212697174070566, + "grad_norm": 0.5869771838188171, + "learning_rate": 8.758452838572551e-05, + "loss": 1.7593, + "step": 4344 + }, + { + "epoch": 0.2421827099938688, + "grad_norm": 0.6008633971214294, + "learning_rate": 8.75786553038947e-05, + "loss": 2.0021, + "step": 4345 + }, + { + "epoch": 0.24223844824703195, + "grad_norm": 0.48187822103500366, + "learning_rate": 8.757278103028806e-05, + "loss": 1.1718, + "step": 4346 + }, + { + "epoch": 0.24229418650019507, + "grad_norm": 0.5490634441375732, + "learning_rate": 8.756690556509186e-05, + "loss": 1.6083, + "step": 4347 + }, + { + "epoch": 0.24234992475335823, + "grad_norm": 0.5408362746238708, + "learning_rate": 8.756102890849246e-05, + "loss": 1.6982, + "step": 4348 + }, + { + "epoch": 0.2424056630065214, + "grad_norm": 0.5706157684326172, + "learning_rate": 8.75551510606762e-05, + "loss": 1.8505, + "step": 4349 + }, + { + "epoch": 0.24246140125968452, + "grad_norm": 0.573557436466217, + "learning_rate": 8.754927202182953e-05, + "loss": 1.8455, + "step": 4350 + }, + { + "epoch": 0.24251713951284767, + "grad_norm": 0.5338667035102844, + "learning_rate": 8.754339179213886e-05, + "loss": 1.5964, + "step": 4351 + }, + { + "epoch": 0.2425728777660108, + "grad_norm": 0.5258156061172485, + "learning_rate": 8.753751037179073e-05, + "loss": 1.7428, + "step": 4352 + }, + { + "epoch": 0.24262861601917396, + "grad_norm": 0.5279545783996582, + "learning_rate": 8.75316277609716e-05, + "loss": 1.7279, + "step": 4353 + }, + { + "epoch": 0.24268435427233712, + "grad_norm": 0.5074349045753479, + "learning_rate": 8.752574395986806e-05, + "loss": 1.508, + "step": 4354 + }, + { + "epoch": 0.24274009252550025, + "grad_norm": 0.5738914012908936, + "learning_rate": 8.751985896866672e-05, + "loss": 1.8978, + "step": 4355 + }, + { + "epoch": 0.2427958307786634, + "grad_norm": 0.6244510412216187, + "learning_rate": 8.75139727875542e-05, + "loss": 1.94, + "step": 4356 + }, + { + "epoch": 0.24285156903182653, + "grad_norm": 0.5642906427383423, + "learning_rate": 8.75080854167172e-05, + "loss": 1.9239, + "step": 4357 + }, + { + "epoch": 0.2429073072849897, + "grad_norm": 0.5614916086196899, + "learning_rate": 8.75021968563424e-05, + "loss": 1.6965, + "step": 4358 + }, + { + "epoch": 0.24296304553815284, + "grad_norm": 0.5800240635871887, + "learning_rate": 8.749630710661658e-05, + "loss": 1.7979, + "step": 4359 + }, + { + "epoch": 0.24301878379131597, + "grad_norm": 0.5255259871482849, + "learning_rate": 8.749041616772653e-05, + "loss": 1.753, + "step": 4360 + }, + { + "epoch": 0.24307452204447913, + "grad_norm": 0.5205305814743042, + "learning_rate": 8.748452403985905e-05, + "loss": 1.518, + "step": 4361 + }, + { + "epoch": 0.24313026029764226, + "grad_norm": 0.5705804824829102, + "learning_rate": 8.747863072320102e-05, + "loss": 1.7267, + "step": 4362 + }, + { + "epoch": 0.24318599855080542, + "grad_norm": 0.5209723114967346, + "learning_rate": 8.747273621793932e-05, + "loss": 1.6697, + "step": 4363 + }, + { + "epoch": 0.24324173680396857, + "grad_norm": 0.5164801478385925, + "learning_rate": 8.746684052426093e-05, + "loss": 1.628, + "step": 4364 + }, + { + "epoch": 0.2432974750571317, + "grad_norm": 0.6018537282943726, + "learning_rate": 8.74609436423528e-05, + "loss": 1.8611, + "step": 4365 + }, + { + "epoch": 0.24335321331029486, + "grad_norm": 0.5693862438201904, + "learning_rate": 8.745504557240195e-05, + "loss": 1.8587, + "step": 4366 + }, + { + "epoch": 0.24340895156345801, + "grad_norm": 0.5834870338439941, + "learning_rate": 8.744914631459544e-05, + "loss": 1.82, + "step": 4367 + }, + { + "epoch": 0.24346468981662114, + "grad_norm": 0.5055362582206726, + "learning_rate": 8.744324586912033e-05, + "loss": 1.5662, + "step": 4368 + }, + { + "epoch": 0.2435204280697843, + "grad_norm": 0.5283217430114746, + "learning_rate": 8.74373442361638e-05, + "loss": 1.618, + "step": 4369 + }, + { + "epoch": 0.24357616632294743, + "grad_norm": 0.5035987496376038, + "learning_rate": 8.743144141591297e-05, + "loss": 1.6436, + "step": 4370 + }, + { + "epoch": 0.2436319045761106, + "grad_norm": 0.5793476700782776, + "learning_rate": 8.742553740855506e-05, + "loss": 1.9764, + "step": 4371 + }, + { + "epoch": 0.24368764282927374, + "grad_norm": 0.5031444430351257, + "learning_rate": 8.741963221427732e-05, + "loss": 1.4643, + "step": 4372 + }, + { + "epoch": 0.24374338108243687, + "grad_norm": 0.5925171971321106, + "learning_rate": 8.7413725833267e-05, + "loss": 1.7132, + "step": 4373 + }, + { + "epoch": 0.24379911933560003, + "grad_norm": 0.5252764225006104, + "learning_rate": 8.740781826571144e-05, + "loss": 1.613, + "step": 4374 + }, + { + "epoch": 0.24385485758876316, + "grad_norm": 0.5435476899147034, + "learning_rate": 8.740190951179799e-05, + "loss": 1.7225, + "step": 4375 + }, + { + "epoch": 0.24391059584192631, + "grad_norm": 0.5505743026733398, + "learning_rate": 8.739599957171404e-05, + "loss": 1.7796, + "step": 4376 + }, + { + "epoch": 0.24396633409508947, + "grad_norm": 0.5711907148361206, + "learning_rate": 8.7390088445647e-05, + "loss": 1.8918, + "step": 4377 + }, + { + "epoch": 0.2440220723482526, + "grad_norm": 0.617215096950531, + "learning_rate": 8.738417613378439e-05, + "loss": 1.6408, + "step": 4378 + }, + { + "epoch": 0.24407781060141576, + "grad_norm": 0.5194396376609802, + "learning_rate": 8.737826263631363e-05, + "loss": 1.5007, + "step": 4379 + }, + { + "epoch": 0.24413354885457889, + "grad_norm": NaN, + "learning_rate": 8.737826263631363e-05, + "loss": 1.8818, + "step": 4380 + }, + { + "epoch": 0.24418928710774204, + "grad_norm": 0.5449255704879761, + "learning_rate": 8.737234795342234e-05, + "loss": 1.6008, + "step": 4381 + }, + { + "epoch": 0.2442450253609052, + "grad_norm": 0.517254650592804, + "learning_rate": 8.736643208529807e-05, + "loss": 1.5589, + "step": 4382 + }, + { + "epoch": 0.24430076361406833, + "grad_norm": 0.5613778829574585, + "learning_rate": 8.736051503212843e-05, + "loss": 1.8349, + "step": 4383 + }, + { + "epoch": 0.24435650186723148, + "grad_norm": 0.5578374266624451, + "learning_rate": 8.735459679410108e-05, + "loss": 1.6444, + "step": 4384 + }, + { + "epoch": 0.2444122401203946, + "grad_norm": 0.5179364681243896, + "learning_rate": 8.734867737140371e-05, + "loss": 1.5685, + "step": 4385 + }, + { + "epoch": 0.24446797837355777, + "grad_norm": 0.5676231980323792, + "learning_rate": 8.734275676422406e-05, + "loss": 1.7138, + "step": 4386 + }, + { + "epoch": 0.24452371662672093, + "grad_norm": 0.5979743599891663, + "learning_rate": 8.73368349727499e-05, + "loss": 1.8035, + "step": 4387 + }, + { + "epoch": 0.24457945487988406, + "grad_norm": 0.566631555557251, + "learning_rate": 8.733091199716899e-05, + "loss": 1.7692, + "step": 4388 + }, + { + "epoch": 0.2446351931330472, + "grad_norm": 0.5594037175178528, + "learning_rate": 8.732498783766923e-05, + "loss": 1.7145, + "step": 4389 + }, + { + "epoch": 0.24469093138621037, + "grad_norm": 0.47728872299194336, + "learning_rate": 8.731906249443847e-05, + "loss": 1.3759, + "step": 4390 + }, + { + "epoch": 0.2447466696393735, + "grad_norm": 0.5077241063117981, + "learning_rate": 8.731313596766461e-05, + "loss": 1.6403, + "step": 4391 + }, + { + "epoch": 0.24480240789253666, + "grad_norm": 0.51840740442276, + "learning_rate": 8.730720825753567e-05, + "loss": 1.7304, + "step": 4392 + }, + { + "epoch": 0.24485814614569978, + "grad_norm": 0.555458664894104, + "learning_rate": 8.730127936423957e-05, + "loss": 1.7039, + "step": 4393 + }, + { + "epoch": 0.24491388439886294, + "grad_norm": 0.530720591545105, + "learning_rate": 8.729534928796438e-05, + "loss": 1.87, + "step": 4394 + }, + { + "epoch": 0.2449696226520261, + "grad_norm": 0.5183333158493042, + "learning_rate": 8.728941802889816e-05, + "loss": 1.6194, + "step": 4395 + }, + { + "epoch": 0.24502536090518923, + "grad_norm": 0.5418990254402161, + "learning_rate": 8.728348558722901e-05, + "loss": 1.6804, + "step": 4396 + }, + { + "epoch": 0.24508109915835238, + "grad_norm": 0.5377148985862732, + "learning_rate": 8.727755196314507e-05, + "loss": 1.5289, + "step": 4397 + }, + { + "epoch": 0.2451368374115155, + "grad_norm": 0.5729206800460815, + "learning_rate": 8.727161715683452e-05, + "loss": 1.7488, + "step": 4398 + }, + { + "epoch": 0.24519257566467867, + "grad_norm": 0.5957255363464355, + "learning_rate": 8.726568116848559e-05, + "loss": 1.4552, + "step": 4399 + }, + { + "epoch": 0.24524831391784183, + "grad_norm": 0.6279282569885254, + "learning_rate": 8.725974399828653e-05, + "loss": 1.8822, + "step": 4400 + }, + { + "epoch": 0.24530405217100495, + "grad_norm": 0.5379980802536011, + "learning_rate": 8.725380564642563e-05, + "loss": 1.7286, + "step": 4401 + }, + { + "epoch": 0.2453597904241681, + "grad_norm": 0.506988525390625, + "learning_rate": 8.724786611309123e-05, + "loss": 1.5182, + "step": 4402 + }, + { + "epoch": 0.24541552867733124, + "grad_norm": 0.5806999206542969, + "learning_rate": 8.724192539847167e-05, + "loss": 1.7967, + "step": 4403 + }, + { + "epoch": 0.2454712669304944, + "grad_norm": 0.6368009448051453, + "learning_rate": 8.723598350275537e-05, + "loss": 1.8081, + "step": 4404 + }, + { + "epoch": 0.24552700518365755, + "grad_norm": 0.6073201894760132, + "learning_rate": 8.723004042613079e-05, + "loss": 1.8369, + "step": 4405 + }, + { + "epoch": 0.24558274343682068, + "grad_norm": 0.5500373244285583, + "learning_rate": 8.722409616878637e-05, + "loss": 1.6556, + "step": 4406 + }, + { + "epoch": 0.24563848168998384, + "grad_norm": 0.5122720003128052, + "learning_rate": 8.721815073091068e-05, + "loss": 1.5745, + "step": 4407 + }, + { + "epoch": 0.24569421994314697, + "grad_norm": 0.5759167671203613, + "learning_rate": 8.721220411269222e-05, + "loss": 1.8282, + "step": 4408 + }, + { + "epoch": 0.24574995819631013, + "grad_norm": 0.5656915307044983, + "learning_rate": 8.720625631431963e-05, + "loss": 1.6782, + "step": 4409 + }, + { + "epoch": 0.24580569644947328, + "grad_norm": 0.5352250933647156, + "learning_rate": 8.72003073359815e-05, + "loss": 1.7703, + "step": 4410 + }, + { + "epoch": 0.2458614347026364, + "grad_norm": 0.6013755798339844, + "learning_rate": 8.719435717786653e-05, + "loss": 1.4931, + "step": 4411 + }, + { + "epoch": 0.24591717295579957, + "grad_norm": 0.5831592082977295, + "learning_rate": 8.718840584016339e-05, + "loss": 1.8267, + "step": 4412 + }, + { + "epoch": 0.24597291120896272, + "grad_norm": 0.5686485767364502, + "learning_rate": 8.718245332306086e-05, + "loss": 1.7073, + "step": 4413 + }, + { + "epoch": 0.24602864946212585, + "grad_norm": 0.5540615320205688, + "learning_rate": 8.717649962674768e-05, + "loss": 1.7481, + "step": 4414 + }, + { + "epoch": 0.246084387715289, + "grad_norm": 0.4984779953956604, + "learning_rate": 8.71705447514127e-05, + "loss": 1.4674, + "step": 4415 + }, + { + "epoch": 0.24614012596845214, + "grad_norm": 0.5658791065216064, + "learning_rate": 8.716458869724475e-05, + "loss": 1.7044, + "step": 4416 + }, + { + "epoch": 0.2461958642216153, + "grad_norm": 0.6222524046897888, + "learning_rate": 8.715863146443273e-05, + "loss": 1.9216, + "step": 4417 + }, + { + "epoch": 0.24625160247477845, + "grad_norm": 0.5234952569007874, + "learning_rate": 8.715267305316558e-05, + "loss": 1.3814, + "step": 4418 + }, + { + "epoch": 0.24630734072794158, + "grad_norm": 0.5298272371292114, + "learning_rate": 8.714671346363226e-05, + "loss": 1.7245, + "step": 4419 + }, + { + "epoch": 0.24636307898110474, + "grad_norm": 0.5426690578460693, + "learning_rate": 8.714075269602176e-05, + "loss": 1.7225, + "step": 4420 + }, + { + "epoch": 0.24641881723426787, + "grad_norm": 0.5064488649368286, + "learning_rate": 8.713479075052312e-05, + "loss": 1.637, + "step": 4421 + }, + { + "epoch": 0.24647455548743102, + "grad_norm": 0.6294771432876587, + "learning_rate": 8.712882762732543e-05, + "loss": 2.0957, + "step": 4422 + }, + { + "epoch": 0.24653029374059418, + "grad_norm": 0.5518829226493835, + "learning_rate": 8.712286332661783e-05, + "loss": 1.8551, + "step": 4423 + }, + { + "epoch": 0.2465860319937573, + "grad_norm": 0.5775428414344788, + "learning_rate": 8.711689784858943e-05, + "loss": 2.0364, + "step": 4424 + }, + { + "epoch": 0.24664177024692047, + "grad_norm": 0.585757851600647, + "learning_rate": 8.711093119342944e-05, + "loss": 1.9078, + "step": 4425 + }, + { + "epoch": 0.2466975085000836, + "grad_norm": 0.49010977149009705, + "learning_rate": 8.710496336132707e-05, + "loss": 1.7235, + "step": 4426 + }, + { + "epoch": 0.24675324675324675, + "grad_norm": 0.4925966262817383, + "learning_rate": 8.709899435247162e-05, + "loss": 1.5281, + "step": 4427 + }, + { + "epoch": 0.2468089850064099, + "grad_norm": 0.5210297107696533, + "learning_rate": 8.709302416705235e-05, + "loss": 1.6194, + "step": 4428 + }, + { + "epoch": 0.24686472325957304, + "grad_norm": 0.5486511588096619, + "learning_rate": 8.708705280525863e-05, + "loss": 1.8987, + "step": 4429 + }, + { + "epoch": 0.2469204615127362, + "grad_norm": 0.5911165475845337, + "learning_rate": 8.708108026727983e-05, + "loss": 1.8762, + "step": 4430 + }, + { + "epoch": 0.24697619976589932, + "grad_norm": 0.557861864566803, + "learning_rate": 8.707510655330535e-05, + "loss": 1.7246, + "step": 4431 + }, + { + "epoch": 0.24703193801906248, + "grad_norm": 0.5598505139350891, + "learning_rate": 8.706913166352468e-05, + "loss": 1.7012, + "step": 4432 + }, + { + "epoch": 0.24708767627222564, + "grad_norm": 0.523493230342865, + "learning_rate": 8.706315559812725e-05, + "loss": 1.6476, + "step": 4433 + }, + { + "epoch": 0.24714341452538877, + "grad_norm": 0.5727233290672302, + "learning_rate": 8.705717835730263e-05, + "loss": 1.7085, + "step": 4434 + }, + { + "epoch": 0.24719915277855192, + "grad_norm": 0.5231149792671204, + "learning_rate": 8.705119994124038e-05, + "loss": 1.6553, + "step": 4435 + }, + { + "epoch": 0.24725489103171508, + "grad_norm": 0.5807697176933289, + "learning_rate": 8.70452203501301e-05, + "loss": 1.9495, + "step": 4436 + }, + { + "epoch": 0.2473106292848782, + "grad_norm": 0.538212239742279, + "learning_rate": 8.703923958416141e-05, + "loss": 1.6201, + "step": 4437 + }, + { + "epoch": 0.24736636753804137, + "grad_norm": 0.5267363786697388, + "learning_rate": 8.703325764352397e-05, + "loss": 1.6372, + "step": 4438 + }, + { + "epoch": 0.2474221057912045, + "grad_norm": 0.5570881962776184, + "learning_rate": 8.702727452840753e-05, + "loss": 1.7135, + "step": 4439 + }, + { + "epoch": 0.24747784404436765, + "grad_norm": 0.5702007412910461, + "learning_rate": 8.702129023900184e-05, + "loss": 1.7636, + "step": 4440 + }, + { + "epoch": 0.2475335822975308, + "grad_norm": 0.5725893974304199, + "learning_rate": 8.701530477549666e-05, + "loss": 1.7144, + "step": 4441 + }, + { + "epoch": 0.24758932055069394, + "grad_norm": 0.5385577082633972, + "learning_rate": 8.700931813808182e-05, + "loss": 1.7915, + "step": 4442 + }, + { + "epoch": 0.2476450588038571, + "grad_norm": 0.625249981880188, + "learning_rate": 8.700333032694721e-05, + "loss": 1.8956, + "step": 4443 + }, + { + "epoch": 0.24770079705702022, + "grad_norm": 0.6568485498428345, + "learning_rate": 8.69973413422827e-05, + "loss": 2.0, + "step": 4444 + }, + { + "epoch": 0.24775653531018338, + "grad_norm": 0.5595792531967163, + "learning_rate": 8.699135118427821e-05, + "loss": 1.7215, + "step": 4445 + }, + { + "epoch": 0.24781227356334654, + "grad_norm": 0.5085048675537109, + "learning_rate": 8.698535985312376e-05, + "loss": 1.5958, + "step": 4446 + }, + { + "epoch": 0.24786801181650966, + "grad_norm": 0.5155544281005859, + "learning_rate": 8.697936734900932e-05, + "loss": 1.7741, + "step": 4447 + }, + { + "epoch": 0.24792375006967282, + "grad_norm": 0.5145729780197144, + "learning_rate": 8.697337367212496e-05, + "loss": 1.7966, + "step": 4448 + }, + { + "epoch": 0.24797948832283595, + "grad_norm": 0.5527476072311401, + "learning_rate": 8.696737882266076e-05, + "loss": 1.8026, + "step": 4449 + }, + { + "epoch": 0.2480352265759991, + "grad_norm": 0.5763035416603088, + "learning_rate": 8.696138280080684e-05, + "loss": 1.7823, + "step": 4450 + }, + { + "epoch": 0.24809096482916226, + "grad_norm": 0.5513672828674316, + "learning_rate": 8.695538560675334e-05, + "loss": 1.5817, + "step": 4451 + }, + { + "epoch": 0.2481467030823254, + "grad_norm": 0.5553067922592163, + "learning_rate": 8.694938724069048e-05, + "loss": 1.8425, + "step": 4452 + }, + { + "epoch": 0.24820244133548855, + "grad_norm": 0.49385184049606323, + "learning_rate": 8.69433877028085e-05, + "loss": 1.6939, + "step": 4453 + }, + { + "epoch": 0.24825817958865168, + "grad_norm": 0.5889978408813477, + "learning_rate": 8.693738699329765e-05, + "loss": 1.6874, + "step": 4454 + }, + { + "epoch": 0.24831391784181484, + "grad_norm": 0.556433916091919, + "learning_rate": 8.693138511234825e-05, + "loss": 1.7339, + "step": 4455 + }, + { + "epoch": 0.248369656094978, + "grad_norm": 0.5483202338218689, + "learning_rate": 8.692538206015062e-05, + "loss": 1.8301, + "step": 4456 + }, + { + "epoch": 0.24842539434814112, + "grad_norm": 0.5633078813552856, + "learning_rate": 8.691937783689518e-05, + "loss": 1.7435, + "step": 4457 + }, + { + "epoch": 0.24848113260130428, + "grad_norm": 0.5544833540916443, + "learning_rate": 8.691337244277231e-05, + "loss": 1.6348, + "step": 4458 + }, + { + "epoch": 0.24853687085446743, + "grad_norm": 0.5703203082084656, + "learning_rate": 8.69073658779725e-05, + "loss": 1.6839, + "step": 4459 + }, + { + "epoch": 0.24859260910763056, + "grad_norm": 0.5441849231719971, + "learning_rate": 8.690135814268623e-05, + "loss": 1.7292, + "step": 4460 + }, + { + "epoch": 0.24864834736079372, + "grad_norm": 0.5759615302085876, + "learning_rate": 8.689534923710403e-05, + "loss": 1.8113, + "step": 4461 + }, + { + "epoch": 0.24870408561395685, + "grad_norm": 0.568762481212616, + "learning_rate": 8.688933916141647e-05, + "loss": 1.9261, + "step": 4462 + }, + { + "epoch": 0.24875982386712, + "grad_norm": 0.5397505164146423, + "learning_rate": 8.688332791581415e-05, + "loss": 1.8136, + "step": 4463 + }, + { + "epoch": 0.24881556212028316, + "grad_norm": 0.5890788435935974, + "learning_rate": 8.68773155004877e-05, + "loss": 1.6383, + "step": 4464 + }, + { + "epoch": 0.2488713003734463, + "grad_norm": 0.5507654547691345, + "learning_rate": 8.687130191562782e-05, + "loss": 1.7313, + "step": 4465 + }, + { + "epoch": 0.24892703862660945, + "grad_norm": 0.5670168399810791, + "learning_rate": 8.686528716142523e-05, + "loss": 1.7355, + "step": 4466 + }, + { + "epoch": 0.24898277687977258, + "grad_norm": 0.5866429805755615, + "learning_rate": 8.685927123807065e-05, + "loss": 1.7786, + "step": 4467 + }, + { + "epoch": 0.24903851513293573, + "grad_norm": 0.5706139206886292, + "learning_rate": 8.68532541457549e-05, + "loss": 1.8995, + "step": 4468 + }, + { + "epoch": 0.2490942533860989, + "grad_norm": 0.5574220418930054, + "learning_rate": 8.68472358846688e-05, + "loss": 1.86, + "step": 4469 + }, + { + "epoch": 0.24914999163926202, + "grad_norm": 0.5442642569541931, + "learning_rate": 8.684121645500322e-05, + "loss": 1.803, + "step": 4470 + }, + { + "epoch": 0.24920572989242518, + "grad_norm": 0.5070736408233643, + "learning_rate": 8.683519585694903e-05, + "loss": 1.5786, + "step": 4471 + }, + { + "epoch": 0.2492614681455883, + "grad_norm": 0.5622973442077637, + "learning_rate": 8.682917409069721e-05, + "loss": 1.8524, + "step": 4472 + }, + { + "epoch": 0.24931720639875146, + "grad_norm": 0.5547112226486206, + "learning_rate": 8.682315115643872e-05, + "loss": 1.7891, + "step": 4473 + }, + { + "epoch": 0.24937294465191462, + "grad_norm": 0.5251905918121338, + "learning_rate": 8.681712705436455e-05, + "loss": 1.3104, + "step": 4474 + }, + { + "epoch": 0.24942868290507775, + "grad_norm": 0.5507151484489441, + "learning_rate": 8.68111017846658e-05, + "loss": 1.7571, + "step": 4475 + }, + { + "epoch": 0.2494844211582409, + "grad_norm": 0.628353476524353, + "learning_rate": 8.68050753475335e-05, + "loss": 1.7915, + "step": 4476 + }, + { + "epoch": 0.24954015941140403, + "grad_norm": 0.5899398922920227, + "learning_rate": 8.67990477431588e-05, + "loss": 1.7928, + "step": 4477 + }, + { + "epoch": 0.2495958976645672, + "grad_norm": 0.5376555919647217, + "learning_rate": 8.679301897173287e-05, + "loss": 1.6592, + "step": 4478 + }, + { + "epoch": 0.24965163591773035, + "grad_norm": 0.5241808891296387, + "learning_rate": 8.678698903344689e-05, + "loss": 1.6482, + "step": 4479 + }, + { + "epoch": 0.24970737417089348, + "grad_norm": 0.6054913997650146, + "learning_rate": 8.67809579284921e-05, + "loss": 1.7838, + "step": 4480 + }, + { + "epoch": 0.24976311242405663, + "grad_norm": 0.56617671251297, + "learning_rate": 8.677492565705976e-05, + "loss": 1.7705, + "step": 4481 + }, + { + "epoch": 0.2498188506772198, + "grad_norm": 0.549431324005127, + "learning_rate": 8.676889221934121e-05, + "loss": 1.8349, + "step": 4482 + }, + { + "epoch": 0.24987458893038292, + "grad_norm": 0.5290791392326355, + "learning_rate": 8.676285761552775e-05, + "loss": 1.6761, + "step": 4483 + }, + { + "epoch": 0.24993032718354607, + "grad_norm": 0.7188482880592346, + "learning_rate": 8.675682184581081e-05, + "loss": 1.6409, + "step": 4484 + }, + { + "epoch": 0.2499860654367092, + "grad_norm": 0.5338848233222961, + "learning_rate": 8.67507849103818e-05, + "loss": 1.4604, + "step": 4485 + }, + { + "epoch": 0.25004180368987233, + "grad_norm": 0.5384326577186584, + "learning_rate": 8.674474680943215e-05, + "loss": 1.5605, + "step": 4486 + }, + { + "epoch": 0.2500975419430355, + "grad_norm": 0.521425724029541, + "learning_rate": 8.673870754315336e-05, + "loss": 1.625, + "step": 4487 + }, + { + "epoch": 0.25015328019619865, + "grad_norm": 0.5739718079566956, + "learning_rate": 8.673266711173698e-05, + "loss": 1.7826, + "step": 4488 + }, + { + "epoch": 0.2502090184493618, + "grad_norm": 0.5505213141441345, + "learning_rate": 8.672662551537457e-05, + "loss": 1.595, + "step": 4489 + }, + { + "epoch": 0.25026475670252496, + "grad_norm": 0.5271283388137817, + "learning_rate": 8.672058275425772e-05, + "loss": 1.5468, + "step": 4490 + }, + { + "epoch": 0.2503204949556881, + "grad_norm": 0.5678611993789673, + "learning_rate": 8.671453882857808e-05, + "loss": 1.8862, + "step": 4491 + }, + { + "epoch": 0.2503762332088512, + "grad_norm": 0.6000241041183472, + "learning_rate": 8.670849373852734e-05, + "loss": 1.6133, + "step": 4492 + }, + { + "epoch": 0.2504319714620144, + "grad_norm": 0.5662490129470825, + "learning_rate": 8.670244748429719e-05, + "loss": 1.7045, + "step": 4493 + }, + { + "epoch": 0.25048770971517753, + "grad_norm": 0.5680144429206848, + "learning_rate": 8.66964000660794e-05, + "loss": 1.6462, + "step": 4494 + }, + { + "epoch": 0.25054344796834066, + "grad_norm": 0.5490357279777527, + "learning_rate": 8.669035148406577e-05, + "loss": 1.5736, + "step": 4495 + }, + { + "epoch": 0.25059918622150384, + "grad_norm": 0.5800120234489441, + "learning_rate": 8.668430173844808e-05, + "loss": 1.8931, + "step": 4496 + }, + { + "epoch": 0.250654924474667, + "grad_norm": 0.5286765694618225, + "learning_rate": 8.667825082941826e-05, + "loss": 1.6553, + "step": 4497 + }, + { + "epoch": 0.2507106627278301, + "grad_norm": 0.5452672839164734, + "learning_rate": 8.667219875716814e-05, + "loss": 1.7692, + "step": 4498 + }, + { + "epoch": 0.25076640098099323, + "grad_norm": 0.5615769028663635, + "learning_rate": 8.66661455218897e-05, + "loss": 1.8116, + "step": 4499 + }, + { + "epoch": 0.2508221392341564, + "grad_norm": 0.5832181572914124, + "learning_rate": 8.666009112377491e-05, + "loss": 1.938, + "step": 4500 + }, + { + "epoch": 0.25087787748731954, + "grad_norm": 0.5258188247680664, + "learning_rate": 8.665403556301576e-05, + "loss": 1.6026, + "step": 4501 + }, + { + "epoch": 0.2509336157404827, + "grad_norm": 0.6271452307701111, + "learning_rate": 8.664797883980434e-05, + "loss": 1.6589, + "step": 4502 + }, + { + "epoch": 0.25098935399364586, + "grad_norm": 0.5411872267723083, + "learning_rate": 8.664192095433266e-05, + "loss": 1.7016, + "step": 4503 + }, + { + "epoch": 0.251045092246809, + "grad_norm": 0.5610190629959106, + "learning_rate": 8.663586190679291e-05, + "loss": 1.8425, + "step": 4504 + }, + { + "epoch": 0.2511008304999721, + "grad_norm": 0.5276908278465271, + "learning_rate": 8.662980169737723e-05, + "loss": 1.6105, + "step": 4505 + }, + { + "epoch": 0.2511565687531353, + "grad_norm": 0.5493645668029785, + "learning_rate": 8.662374032627778e-05, + "loss": 1.9352, + "step": 4506 + }, + { + "epoch": 0.25121230700629843, + "grad_norm": 0.5296374559402466, + "learning_rate": 8.661767779368683e-05, + "loss": 1.7867, + "step": 4507 + }, + { + "epoch": 0.25126804525946156, + "grad_norm": 0.6600750684738159, + "learning_rate": 8.661161409979665e-05, + "loss": 1.6947, + "step": 4508 + }, + { + "epoch": 0.2513237835126247, + "grad_norm": 0.5515453815460205, + "learning_rate": 8.66055492447995e-05, + "loss": 1.796, + "step": 4509 + }, + { + "epoch": 0.25137952176578787, + "grad_norm": 0.5651318430900574, + "learning_rate": 8.659948322888777e-05, + "loss": 1.6343, + "step": 4510 + }, + { + "epoch": 0.251435260018951, + "grad_norm": 0.5783109664916992, + "learning_rate": 8.659341605225384e-05, + "loss": 1.8057, + "step": 4511 + }, + { + "epoch": 0.25149099827211413, + "grad_norm": 0.5711765885353088, + "learning_rate": 8.65873477150901e-05, + "loss": 1.8123, + "step": 4512 + }, + { + "epoch": 0.2515467365252773, + "grad_norm": 0.5652083158493042, + "learning_rate": 8.658127821758899e-05, + "loss": 1.7952, + "step": 4513 + }, + { + "epoch": 0.25160247477844044, + "grad_norm": 0.5652216076850891, + "learning_rate": 8.657520755994305e-05, + "loss": 1.8295, + "step": 4514 + }, + { + "epoch": 0.2516582130316036, + "grad_norm": 0.5443994998931885, + "learning_rate": 8.656913574234474e-05, + "loss": 1.6294, + "step": 4515 + }, + { + "epoch": 0.25171395128476676, + "grad_norm": 0.5845414400100708, + "learning_rate": 8.656306276498667e-05, + "loss": 1.8597, + "step": 4516 + }, + { + "epoch": 0.2517696895379299, + "grad_norm": 0.5372679233551025, + "learning_rate": 8.655698862806143e-05, + "loss": 1.7067, + "step": 4517 + }, + { + "epoch": 0.251825427791093, + "grad_norm": 0.5330473780632019, + "learning_rate": 8.655091333176165e-05, + "loss": 1.7043, + "step": 4518 + }, + { + "epoch": 0.2518811660442562, + "grad_norm": 0.5988831520080566, + "learning_rate": 8.654483687628002e-05, + "loss": 1.7418, + "step": 4519 + }, + { + "epoch": 0.25193690429741933, + "grad_norm": 0.5914613604545593, + "learning_rate": 8.65387592618092e-05, + "loss": 1.6442, + "step": 4520 + }, + { + "epoch": 0.25199264255058246, + "grad_norm": 0.5800835490226746, + "learning_rate": 8.653268048854201e-05, + "loss": 1.7816, + "step": 4521 + }, + { + "epoch": 0.2520483808037456, + "grad_norm": 0.5335732102394104, + "learning_rate": 8.652660055667117e-05, + "loss": 1.5046, + "step": 4522 + }, + { + "epoch": 0.25210411905690877, + "grad_norm": 0.48013389110565186, + "learning_rate": 8.652051946638953e-05, + "loss": 1.582, + "step": 4523 + }, + { + "epoch": 0.2521598573100719, + "grad_norm": 0.6047071814537048, + "learning_rate": 8.651443721788996e-05, + "loss": 1.6199, + "step": 4524 + }, + { + "epoch": 0.25221559556323503, + "grad_norm": 0.5248143672943115, + "learning_rate": 8.650835381136533e-05, + "loss": 1.5345, + "step": 4525 + }, + { + "epoch": 0.2522713338163982, + "grad_norm": 0.5078330636024475, + "learning_rate": 8.650226924700855e-05, + "loss": 1.6656, + "step": 4526 + }, + { + "epoch": 0.25232707206956134, + "grad_norm": 0.5320603251457214, + "learning_rate": 8.649618352501264e-05, + "loss": 1.598, + "step": 4527 + }, + { + "epoch": 0.25238281032272447, + "grad_norm": 0.49775633215904236, + "learning_rate": 8.649009664557057e-05, + "loss": 1.3941, + "step": 4528 + }, + { + "epoch": 0.25243854857588766, + "grad_norm": 0.5565609931945801, + "learning_rate": 8.648400860887538e-05, + "loss": 1.7144, + "step": 4529 + }, + { + "epoch": 0.2524942868290508, + "grad_norm": 0.5529298782348633, + "learning_rate": 8.647791941512016e-05, + "loss": 1.8223, + "step": 4530 + }, + { + "epoch": 0.2525500250822139, + "grad_norm": 0.5692974328994751, + "learning_rate": 8.6471829064498e-05, + "loss": 1.6577, + "step": 4531 + }, + { + "epoch": 0.25260576333537704, + "grad_norm": 0.49695706367492676, + "learning_rate": 8.646573755720209e-05, + "loss": 1.6222, + "step": 4532 + }, + { + "epoch": 0.2526615015885402, + "grad_norm": 0.5647556781768799, + "learning_rate": 8.645964489342557e-05, + "loss": 1.8348, + "step": 4533 + }, + { + "epoch": 0.25271723984170336, + "grad_norm": 0.5597743391990662, + "learning_rate": 8.645355107336171e-05, + "loss": 1.7095, + "step": 4534 + }, + { + "epoch": 0.2527729780948665, + "grad_norm": 0.5715233683586121, + "learning_rate": 8.644745609720375e-05, + "loss": 1.9243, + "step": 4535 + }, + { + "epoch": 0.25282871634802967, + "grad_norm": 0.5817229747772217, + "learning_rate": 8.644135996514498e-05, + "loss": 1.782, + "step": 4536 + }, + { + "epoch": 0.2528844546011928, + "grad_norm": 0.5697113275527954, + "learning_rate": 8.643526267737873e-05, + "loss": 1.6014, + "step": 4537 + }, + { + "epoch": 0.2529401928543559, + "grad_norm": 0.5716366767883301, + "learning_rate": 8.642916423409839e-05, + "loss": 1.6435, + "step": 4538 + }, + { + "epoch": 0.2529959311075191, + "grad_norm": 0.5631042718887329, + "learning_rate": 8.642306463549736e-05, + "loss": 1.7686, + "step": 4539 + }, + { + "epoch": 0.25305166936068224, + "grad_norm": 0.596517026424408, + "learning_rate": 8.641696388176907e-05, + "loss": 1.8116, + "step": 4540 + }, + { + "epoch": 0.25310740761384537, + "grad_norm": 0.47129639983177185, + "learning_rate": 8.641086197310703e-05, + "loss": 1.4985, + "step": 4541 + }, + { + "epoch": 0.25316314586700855, + "grad_norm": 0.551607072353363, + "learning_rate": 8.640475890970471e-05, + "loss": 1.7948, + "step": 4542 + }, + { + "epoch": 0.2532188841201717, + "grad_norm": 0.559027910232544, + "learning_rate": 8.639865469175572e-05, + "loss": 1.5825, + "step": 4543 + }, + { + "epoch": 0.2532746223733348, + "grad_norm": 0.5063076019287109, + "learning_rate": 8.639254931945362e-05, + "loss": 1.4125, + "step": 4544 + }, + { + "epoch": 0.25333036062649794, + "grad_norm": 0.5271062254905701, + "learning_rate": 8.638644279299202e-05, + "loss": 1.6964, + "step": 4545 + }, + { + "epoch": 0.2533860988796611, + "grad_norm": 0.4922122657299042, + "learning_rate": 8.638033511256462e-05, + "loss": 1.6725, + "step": 4546 + }, + { + "epoch": 0.25344183713282425, + "grad_norm": 0.5734017491340637, + "learning_rate": 8.637422627836509e-05, + "loss": 2.0334, + "step": 4547 + }, + { + "epoch": 0.2534975753859874, + "grad_norm": 0.4978555738925934, + "learning_rate": 8.636811629058718e-05, + "loss": 1.6665, + "step": 4548 + }, + { + "epoch": 0.25355331363915057, + "grad_norm": 0.5637436509132385, + "learning_rate": 8.636200514942467e-05, + "loss": 1.5875, + "step": 4549 + }, + { + "epoch": 0.2536090518923137, + "grad_norm": 0.5382322072982788, + "learning_rate": 8.635589285507135e-05, + "loss": 1.838, + "step": 4550 + }, + { + "epoch": 0.2536647901454768, + "grad_norm": 0.518650233745575, + "learning_rate": 8.634977940772108e-05, + "loss": 1.7802, + "step": 4551 + }, + { + "epoch": 0.25372052839864, + "grad_norm": 0.5153575539588928, + "learning_rate": 8.634366480756774e-05, + "loss": 1.6153, + "step": 4552 + }, + { + "epoch": 0.25377626665180314, + "grad_norm": 0.5355269908905029, + "learning_rate": 8.633754905480527e-05, + "loss": 1.8255, + "step": 4553 + }, + { + "epoch": 0.25383200490496627, + "grad_norm": 0.5261843204498291, + "learning_rate": 8.63314321496276e-05, + "loss": 1.6177, + "step": 4554 + }, + { + "epoch": 0.2538877431581294, + "grad_norm": 0.557314395904541, + "learning_rate": 8.632531409222872e-05, + "loss": 1.8342, + "step": 4555 + }, + { + "epoch": 0.2539434814112926, + "grad_norm": 0.5285095572471619, + "learning_rate": 8.631919488280267e-05, + "loss": 1.6217, + "step": 4556 + }, + { + "epoch": 0.2539992196644557, + "grad_norm": 0.5471826195716858, + "learning_rate": 8.631307452154352e-05, + "loss": 1.5318, + "step": 4557 + }, + { + "epoch": 0.25405495791761884, + "grad_norm": 0.5375044941902161, + "learning_rate": 8.630695300864536e-05, + "loss": 1.7415, + "step": 4558 + }, + { + "epoch": 0.254110696170782, + "grad_norm": 0.566832423210144, + "learning_rate": 8.630083034430232e-05, + "loss": 1.9215, + "step": 4559 + }, + { + "epoch": 0.25416643442394515, + "grad_norm": 0.5262976884841919, + "learning_rate": 8.629470652870861e-05, + "loss": 1.5432, + "step": 4560 + }, + { + "epoch": 0.2542221726771083, + "grad_norm": 0.5495408177375793, + "learning_rate": 8.628858156205842e-05, + "loss": 1.9161, + "step": 4561 + }, + { + "epoch": 0.25427791093027147, + "grad_norm": 0.5776422023773193, + "learning_rate": 8.6282455444546e-05, + "loss": 1.8547, + "step": 4562 + }, + { + "epoch": 0.2543336491834346, + "grad_norm": 0.5136664509773254, + "learning_rate": 8.627632817636563e-05, + "loss": 1.3558, + "step": 4563 + }, + { + "epoch": 0.2543893874365977, + "grad_norm": 0.5449255108833313, + "learning_rate": 8.627019975771165e-05, + "loss": 1.7991, + "step": 4564 + }, + { + "epoch": 0.2544451256897609, + "grad_norm": 0.49720707535743713, + "learning_rate": 8.626407018877837e-05, + "loss": 1.5515, + "step": 4565 + }, + { + "epoch": 0.25450086394292404, + "grad_norm": 0.5493996739387512, + "learning_rate": 8.625793946976026e-05, + "loss": 1.7666, + "step": 4566 + }, + { + "epoch": 0.25455660219608717, + "grad_norm": 0.5458593368530273, + "learning_rate": 8.625180760085167e-05, + "loss": 1.9701, + "step": 4567 + }, + { + "epoch": 0.2546123404492503, + "grad_norm": 0.5866237878799438, + "learning_rate": 8.624567458224713e-05, + "loss": 1.7123, + "step": 4568 + }, + { + "epoch": 0.2546680787024135, + "grad_norm": 0.5610763430595398, + "learning_rate": 8.62395404141411e-05, + "loss": 1.8511, + "step": 4569 + }, + { + "epoch": 0.2547238169555766, + "grad_norm": 0.5264028906822205, + "learning_rate": 8.623340509672817e-05, + "loss": 1.6913, + "step": 4570 + }, + { + "epoch": 0.25477955520873974, + "grad_norm": 0.5024250745773315, + "learning_rate": 8.622726863020285e-05, + "loss": 1.6337, + "step": 4571 + }, + { + "epoch": 0.2548352934619029, + "grad_norm": 0.6130850315093994, + "learning_rate": 8.622113101475982e-05, + "loss": 1.8858, + "step": 4572 + }, + { + "epoch": 0.25489103171506605, + "grad_norm": 0.5543071627616882, + "learning_rate": 8.621499225059369e-05, + "loss": 1.6353, + "step": 4573 + }, + { + "epoch": 0.2549467699682292, + "grad_norm": 0.5286437273025513, + "learning_rate": 8.620885233789914e-05, + "loss": 1.4418, + "step": 4574 + }, + { + "epoch": 0.25500250822139237, + "grad_norm": 0.5485914349555969, + "learning_rate": 8.620271127687092e-05, + "loss": 1.7161, + "step": 4575 + }, + { + "epoch": 0.2550582464745555, + "grad_norm": 0.612994909286499, + "learning_rate": 8.619656906770377e-05, + "loss": 1.8467, + "step": 4576 + }, + { + "epoch": 0.2551139847277186, + "grad_norm": 0.5447350740432739, + "learning_rate": 8.619042571059248e-05, + "loss": 1.7528, + "step": 4577 + }, + { + "epoch": 0.25516972298088175, + "grad_norm": 0.5236079096794128, + "learning_rate": 8.61842812057319e-05, + "loss": 1.5648, + "step": 4578 + }, + { + "epoch": 0.25522546123404494, + "grad_norm": 0.534354567527771, + "learning_rate": 8.617813555331689e-05, + "loss": 1.5093, + "step": 4579 + }, + { + "epoch": 0.25528119948720807, + "grad_norm": 0.5146899819374084, + "learning_rate": 8.617198875354235e-05, + "loss": 1.6445, + "step": 4580 + }, + { + "epoch": 0.2553369377403712, + "grad_norm": 0.5606057047843933, + "learning_rate": 8.616584080660323e-05, + "loss": 1.6225, + "step": 4581 + }, + { + "epoch": 0.2553926759935344, + "grad_norm": 0.557131290435791, + "learning_rate": 8.615969171269449e-05, + "loss": 1.8017, + "step": 4582 + }, + { + "epoch": 0.2554484142466975, + "grad_norm": 0.5046922564506531, + "learning_rate": 8.615354147201116e-05, + "loss": 1.6034, + "step": 4583 + }, + { + "epoch": 0.25550415249986064, + "grad_norm": 0.5313592553138733, + "learning_rate": 8.614739008474829e-05, + "loss": 1.481, + "step": 4584 + }, + { + "epoch": 0.2555598907530238, + "grad_norm": 0.5347174406051636, + "learning_rate": 8.614123755110096e-05, + "loss": 1.6323, + "step": 4585 + }, + { + "epoch": 0.25561562900618695, + "grad_norm": 0.5261495113372803, + "learning_rate": 8.61350838712643e-05, + "loss": 1.4896, + "step": 4586 + }, + { + "epoch": 0.2556713672593501, + "grad_norm": 0.5374502539634705, + "learning_rate": 8.612892904543344e-05, + "loss": 1.6488, + "step": 4587 + }, + { + "epoch": 0.25572710551251326, + "grad_norm": 0.5835258960723877, + "learning_rate": 8.612277307380361e-05, + "loss": 1.7467, + "step": 4588 + }, + { + "epoch": 0.2557828437656764, + "grad_norm": 0.519822359085083, + "learning_rate": 8.611661595657004e-05, + "loss": 1.4627, + "step": 4589 + }, + { + "epoch": 0.2558385820188395, + "grad_norm": 0.5837191343307495, + "learning_rate": 8.611045769392796e-05, + "loss": 1.654, + "step": 4590 + }, + { + "epoch": 0.25589432027200265, + "grad_norm": 0.5844641327857971, + "learning_rate": 8.610429828607271e-05, + "loss": 1.6177, + "step": 4591 + }, + { + "epoch": 0.25595005852516584, + "grad_norm": 0.5927681922912598, + "learning_rate": 8.609813773319963e-05, + "loss": 1.9184, + "step": 4592 + }, + { + "epoch": 0.25600579677832896, + "grad_norm": 0.6149387955665588, + "learning_rate": 8.609197603550409e-05, + "loss": 1.6321, + "step": 4593 + }, + { + "epoch": 0.2560615350314921, + "grad_norm": 0.5619008541107178, + "learning_rate": 8.608581319318148e-05, + "loss": 1.6094, + "step": 4594 + }, + { + "epoch": 0.2561172732846553, + "grad_norm": 0.5645739436149597, + "learning_rate": 8.607964920642728e-05, + "loss": 1.7111, + "step": 4595 + }, + { + "epoch": 0.2561730115378184, + "grad_norm": 0.5264320373535156, + "learning_rate": 8.607348407543699e-05, + "loss": 1.5206, + "step": 4596 + }, + { + "epoch": 0.25622874979098154, + "grad_norm": 0.5533236861228943, + "learning_rate": 8.606731780040608e-05, + "loss": 1.9129, + "step": 4597 + }, + { + "epoch": 0.2562844880441447, + "grad_norm": 0.5276892781257629, + "learning_rate": 8.606115038153015e-05, + "loss": 1.7739, + "step": 4598 + }, + { + "epoch": 0.25634022629730785, + "grad_norm": 0.5314942598342896, + "learning_rate": 8.605498181900477e-05, + "loss": 1.6853, + "step": 4599 + }, + { + "epoch": 0.256395964550471, + "grad_norm": 0.540059506893158, + "learning_rate": 8.604881211302559e-05, + "loss": 1.8345, + "step": 4600 + }, + { + "epoch": 0.2564517028036341, + "grad_norm": 0.5306822657585144, + "learning_rate": 8.604264126378827e-05, + "loss": 1.9012, + "step": 4601 + }, + { + "epoch": 0.2565074410567973, + "grad_norm": 0.5294952988624573, + "learning_rate": 8.603646927148849e-05, + "loss": 1.5109, + "step": 4602 + }, + { + "epoch": 0.2565631793099604, + "grad_norm": 0.5673249959945679, + "learning_rate": 8.603029613632205e-05, + "loss": 1.758, + "step": 4603 + }, + { + "epoch": 0.25661891756312355, + "grad_norm": 0.5006965398788452, + "learning_rate": 8.602412185848466e-05, + "loss": 1.6211, + "step": 4604 + }, + { + "epoch": 0.25667465581628673, + "grad_norm": 0.5873995423316956, + "learning_rate": 8.601794643817216e-05, + "loss": 1.8896, + "step": 4605 + }, + { + "epoch": 0.25673039406944986, + "grad_norm": 0.56819748878479, + "learning_rate": 8.601176987558041e-05, + "loss": 1.6733, + "step": 4606 + }, + { + "epoch": 0.256786132322613, + "grad_norm": 0.5610432624816895, + "learning_rate": 8.600559217090529e-05, + "loss": 1.824, + "step": 4607 + }, + { + "epoch": 0.2568418705757762, + "grad_norm": 0.5451894998550415, + "learning_rate": 8.599941332434269e-05, + "loss": 1.7229, + "step": 4608 + }, + { + "epoch": 0.2568976088289393, + "grad_norm": 0.9107519388198853, + "learning_rate": 8.599323333608861e-05, + "loss": 1.846, + "step": 4609 + }, + { + "epoch": 0.25695334708210243, + "grad_norm": 0.5975711941719055, + "learning_rate": 8.598705220633903e-05, + "loss": 1.7334, + "step": 4610 + }, + { + "epoch": 0.2570090853352656, + "grad_norm": 0.5969035625457764, + "learning_rate": 8.598086993528996e-05, + "loss": 1.9449, + "step": 4611 + }, + { + "epoch": 0.25706482358842875, + "grad_norm": 0.6146485805511475, + "learning_rate": 8.597468652313747e-05, + "loss": 1.8884, + "step": 4612 + }, + { + "epoch": 0.2571205618415919, + "grad_norm": 0.5359372496604919, + "learning_rate": 8.596850197007767e-05, + "loss": 1.6199, + "step": 4613 + }, + { + "epoch": 0.257176300094755, + "grad_norm": 0.5491176247596741, + "learning_rate": 8.596231627630671e-05, + "loss": 1.5702, + "step": 4614 + }, + { + "epoch": 0.2572320383479182, + "grad_norm": 0.5316644310951233, + "learning_rate": 8.595612944202076e-05, + "loss": 1.6538, + "step": 4615 + }, + { + "epoch": 0.2572877766010813, + "grad_norm": 0.5944792032241821, + "learning_rate": 8.5949941467416e-05, + "loss": 1.79, + "step": 4616 + }, + { + "epoch": 0.25734351485424445, + "grad_norm": 0.5629575848579407, + "learning_rate": 8.594375235268872e-05, + "loss": 2.0629, + "step": 4617 + }, + { + "epoch": 0.25739925310740763, + "grad_norm": 0.5681300163269043, + "learning_rate": 8.593756209803518e-05, + "loss": 1.7105, + "step": 4618 + }, + { + "epoch": 0.25745499136057076, + "grad_norm": 0.5259959697723389, + "learning_rate": 8.59313707036517e-05, + "loss": 1.7797, + "step": 4619 + }, + { + "epoch": 0.2575107296137339, + "grad_norm": 0.5173026323318481, + "learning_rate": 8.592517816973462e-05, + "loss": 1.6879, + "step": 4620 + }, + { + "epoch": 0.2575664678668971, + "grad_norm": 0.5310641527175903, + "learning_rate": 8.591898449648035e-05, + "loss": 1.6947, + "step": 4621 + }, + { + "epoch": 0.2576222061200602, + "grad_norm": 0.5746062397956848, + "learning_rate": 8.591278968408532e-05, + "loss": 1.8276, + "step": 4622 + }, + { + "epoch": 0.25767794437322333, + "grad_norm": 0.5601612329483032, + "learning_rate": 8.590659373274599e-05, + "loss": 1.6054, + "step": 4623 + }, + { + "epoch": 0.25773368262638646, + "grad_norm": 0.5777058601379395, + "learning_rate": 8.590039664265885e-05, + "loss": 1.612, + "step": 4624 + }, + { + "epoch": 0.25778942087954965, + "grad_norm": 0.6337921023368835, + "learning_rate": 8.589419841402047e-05, + "loss": 2.1569, + "step": 4625 + }, + { + "epoch": 0.2578451591327128, + "grad_norm": 0.5203370451927185, + "learning_rate": 8.588799904702736e-05, + "loss": 1.4849, + "step": 4626 + }, + { + "epoch": 0.2579008973858759, + "grad_norm": 0.55791175365448, + "learning_rate": 8.588179854187616e-05, + "loss": 1.882, + "step": 4627 + }, + { + "epoch": 0.2579566356390391, + "grad_norm": 0.581343948841095, + "learning_rate": 8.587559689876354e-05, + "loss": 1.7811, + "step": 4628 + }, + { + "epoch": 0.2580123738922022, + "grad_norm": 0.6163395047187805, + "learning_rate": 8.586939411788615e-05, + "loss": 1.8589, + "step": 4629 + }, + { + "epoch": 0.25806811214536535, + "grad_norm": 0.5277383327484131, + "learning_rate": 8.586319019944071e-05, + "loss": 1.5817, + "step": 4630 + }, + { + "epoch": 0.25812385039852853, + "grad_norm": 0.5042583346366882, + "learning_rate": 8.585698514362397e-05, + "loss": 1.4472, + "step": 4631 + }, + { + "epoch": 0.25817958865169166, + "grad_norm": 0.5802309513092041, + "learning_rate": 8.585077895063271e-05, + "loss": 1.9396, + "step": 4632 + }, + { + "epoch": 0.2582353269048548, + "grad_norm": 0.5798273682594299, + "learning_rate": 8.58445716206638e-05, + "loss": 1.6806, + "step": 4633 + }, + { + "epoch": 0.258291065158018, + "grad_norm": 0.5102317333221436, + "learning_rate": 8.583836315391403e-05, + "loss": 1.5884, + "step": 4634 + }, + { + "epoch": 0.2583468034111811, + "grad_norm": 0.6215993165969849, + "learning_rate": 8.583215355058035e-05, + "loss": 2.001, + "step": 4635 + }, + { + "epoch": 0.25840254166434423, + "grad_norm": 0.5116714835166931, + "learning_rate": 8.582594281085967e-05, + "loss": 1.6639, + "step": 4636 + }, + { + "epoch": 0.25845827991750736, + "grad_norm": 0.5677070617675781, + "learning_rate": 8.581973093494897e-05, + "loss": 1.841, + "step": 4637 + }, + { + "epoch": 0.25851401817067055, + "grad_norm": 0.5552488565444946, + "learning_rate": 8.581351792304524e-05, + "loss": 1.6623, + "step": 4638 + }, + { + "epoch": 0.2585697564238337, + "grad_norm": 0.5567041635513306, + "learning_rate": 8.580730377534554e-05, + "loss": 1.5144, + "step": 4639 + }, + { + "epoch": 0.2586254946769968, + "grad_norm": 0.5067396759986877, + "learning_rate": 8.580108849204693e-05, + "loss": 1.4875, + "step": 4640 + }, + { + "epoch": 0.25868123293016, + "grad_norm": 0.5226799845695496, + "learning_rate": 8.579487207334653e-05, + "loss": 1.7197, + "step": 4641 + }, + { + "epoch": 0.2587369711833231, + "grad_norm": 0.5152204036712646, + "learning_rate": 8.578865451944148e-05, + "loss": 1.4488, + "step": 4642 + }, + { + "epoch": 0.25879270943648625, + "grad_norm": 0.5446513295173645, + "learning_rate": 8.578243583052897e-05, + "loss": 1.7116, + "step": 4643 + }, + { + "epoch": 0.25884844768964943, + "grad_norm": 0.5753796696662903, + "learning_rate": 8.577621600680623e-05, + "loss": 1.5765, + "step": 4644 + }, + { + "epoch": 0.25890418594281256, + "grad_norm": 0.53980952501297, + "learning_rate": 8.57699950484705e-05, + "loss": 1.7881, + "step": 4645 + }, + { + "epoch": 0.2589599241959757, + "grad_norm": 0.5444200038909912, + "learning_rate": 8.57637729557191e-05, + "loss": 1.8373, + "step": 4646 + }, + { + "epoch": 0.2590156624491388, + "grad_norm": 0.5415917634963989, + "learning_rate": 8.575754972874931e-05, + "loss": 1.6772, + "step": 4647 + }, + { + "epoch": 0.259071400702302, + "grad_norm": 0.5910305380821228, + "learning_rate": 8.575132536775853e-05, + "loss": 1.8558, + "step": 4648 + }, + { + "epoch": 0.25912713895546513, + "grad_norm": 0.5802417397499084, + "learning_rate": 8.574509987294417e-05, + "loss": 1.9364, + "step": 4649 + }, + { + "epoch": 0.25918287720862826, + "grad_norm": 0.573726236820221, + "learning_rate": 8.573887324450364e-05, + "loss": 1.8956, + "step": 4650 + }, + { + "epoch": 0.25923861546179144, + "grad_norm": 0.5909465551376343, + "learning_rate": 8.573264548263442e-05, + "loss": 1.7338, + "step": 4651 + }, + { + "epoch": 0.2592943537149546, + "grad_norm": 0.6169442534446716, + "learning_rate": 8.572641658753404e-05, + "loss": 1.5941, + "step": 4652 + }, + { + "epoch": 0.2593500919681177, + "grad_norm": 0.5135464668273926, + "learning_rate": 8.572018655940001e-05, + "loss": 1.7035, + "step": 4653 + }, + { + "epoch": 0.2594058302212809, + "grad_norm": 0.5379095077514648, + "learning_rate": 8.571395539842992e-05, + "loss": 1.7387, + "step": 4654 + }, + { + "epoch": 0.259461568474444, + "grad_norm": 0.5439580678939819, + "learning_rate": 8.570772310482141e-05, + "loss": 1.7089, + "step": 4655 + }, + { + "epoch": 0.25951730672760714, + "grad_norm": 0.5132806301116943, + "learning_rate": 8.57014896787721e-05, + "loss": 1.5298, + "step": 4656 + }, + { + "epoch": 0.25957304498077033, + "grad_norm": 0.5612521171569824, + "learning_rate": 8.569525512047969e-05, + "loss": 1.7676, + "step": 4657 + }, + { + "epoch": 0.25962878323393346, + "grad_norm": 0.5397217273712158, + "learning_rate": 8.56890194301419e-05, + "loss": 1.636, + "step": 4658 + }, + { + "epoch": 0.2596845214870966, + "grad_norm": 0.6334729194641113, + "learning_rate": 8.56827826079565e-05, + "loss": 1.8281, + "step": 4659 + }, + { + "epoch": 0.2597402597402597, + "grad_norm": 0.5931346416473389, + "learning_rate": 8.56765446541213e-05, + "loss": 1.7335, + "step": 4660 + }, + { + "epoch": 0.2597959979934229, + "grad_norm": 0.5085331201553345, + "learning_rate": 8.567030556883408e-05, + "loss": 1.8524, + "step": 4661 + }, + { + "epoch": 0.25985173624658603, + "grad_norm": 0.5508363246917725, + "learning_rate": 8.566406535229276e-05, + "loss": 1.7883, + "step": 4662 + }, + { + "epoch": 0.25990747449974916, + "grad_norm": 0.5742567181587219, + "learning_rate": 8.565782400469522e-05, + "loss": 1.7011, + "step": 4663 + }, + { + "epoch": 0.25996321275291234, + "grad_norm": 0.4922592043876648, + "learning_rate": 8.56515815262394e-05, + "loss": 1.4828, + "step": 4664 + }, + { + "epoch": 0.26001895100607547, + "grad_norm": 0.5450266003608704, + "learning_rate": 8.564533791712328e-05, + "loss": 1.7885, + "step": 4665 + }, + { + "epoch": 0.2600746892592386, + "grad_norm": 0.5942632555961609, + "learning_rate": 8.563909317754487e-05, + "loss": 1.9297, + "step": 4666 + }, + { + "epoch": 0.2601304275124018, + "grad_norm": 0.5638509392738342, + "learning_rate": 8.563284730770221e-05, + "loss": 1.9536, + "step": 4667 + }, + { + "epoch": 0.2601861657655649, + "grad_norm": 0.5848171710968018, + "learning_rate": 8.56266003077934e-05, + "loss": 2.003, + "step": 4668 + }, + { + "epoch": 0.26024190401872804, + "grad_norm": 0.5629677176475525, + "learning_rate": 8.562035217801652e-05, + "loss": 2.0024, + "step": 4669 + }, + { + "epoch": 0.26029764227189117, + "grad_norm": 0.5268816351890564, + "learning_rate": 8.561410291856977e-05, + "loss": 1.5865, + "step": 4670 + }, + { + "epoch": 0.26035338052505436, + "grad_norm": 0.545254647731781, + "learning_rate": 8.560785252965131e-05, + "loss": 1.7586, + "step": 4671 + }, + { + "epoch": 0.2604091187782175, + "grad_norm": 0.5406084060668945, + "learning_rate": 8.560160101145937e-05, + "loss": 1.9274, + "step": 4672 + }, + { + "epoch": 0.2604648570313806, + "grad_norm": 0.5519586801528931, + "learning_rate": 8.559534836419224e-05, + "loss": 1.7652, + "step": 4673 + }, + { + "epoch": 0.2605205952845438, + "grad_norm": 0.5398983955383301, + "learning_rate": 8.558909458804818e-05, + "loss": 1.9096, + "step": 4674 + }, + { + "epoch": 0.26057633353770693, + "grad_norm": 0.5414653420448303, + "learning_rate": 8.558283968322555e-05, + "loss": 1.6586, + "step": 4675 + }, + { + "epoch": 0.26063207179087006, + "grad_norm": 0.5628217458724976, + "learning_rate": 8.55765836499227e-05, + "loss": 1.606, + "step": 4676 + }, + { + "epoch": 0.26068781004403324, + "grad_norm": 0.5232682228088379, + "learning_rate": 8.557032648833804e-05, + "loss": 1.698, + "step": 4677 + }, + { + "epoch": 0.26074354829719637, + "grad_norm": 0.588845431804657, + "learning_rate": 8.556406819867001e-05, + "loss": 1.9568, + "step": 4678 + }, + { + "epoch": 0.2607992865503595, + "grad_norm": 0.5363548994064331, + "learning_rate": 8.55578087811171e-05, + "loss": 1.6827, + "step": 4679 + }, + { + "epoch": 0.2608550248035227, + "grad_norm": 0.514584481716156, + "learning_rate": 8.55515482358778e-05, + "loss": 1.631, + "step": 4680 + }, + { + "epoch": 0.2609107630566858, + "grad_norm": 0.5446624159812927, + "learning_rate": 8.554528656315069e-05, + "loss": 1.7978, + "step": 4681 + }, + { + "epoch": 0.26096650130984894, + "grad_norm": 0.5160642266273499, + "learning_rate": 8.55390237631343e-05, + "loss": 1.4935, + "step": 4682 + }, + { + "epoch": 0.26102223956301207, + "grad_norm": 0.5020194053649902, + "learning_rate": 8.553275983602732e-05, + "loss": 1.3459, + "step": 4683 + }, + { + "epoch": 0.26107797781617526, + "grad_norm": 0.5197760462760925, + "learning_rate": 8.552649478202834e-05, + "loss": 1.8008, + "step": 4684 + }, + { + "epoch": 0.2611337160693384, + "grad_norm": 0.5080288648605347, + "learning_rate": 8.55202286013361e-05, + "loss": 1.5853, + "step": 4685 + }, + { + "epoch": 0.2611894543225015, + "grad_norm": 0.5232203602790833, + "learning_rate": 8.551396129414928e-05, + "loss": 1.7352, + "step": 4686 + }, + { + "epoch": 0.2612451925756647, + "grad_norm": 0.5843389630317688, + "learning_rate": 8.550769286066669e-05, + "loss": 1.5833, + "step": 4687 + }, + { + "epoch": 0.2613009308288278, + "grad_norm": 0.5756316184997559, + "learning_rate": 8.55014233010871e-05, + "loss": 1.8692, + "step": 4688 + }, + { + "epoch": 0.26135666908199096, + "grad_norm": 0.5456770658493042, + "learning_rate": 8.549515261560937e-05, + "loss": 1.6987, + "step": 4689 + }, + { + "epoch": 0.26141240733515414, + "grad_norm": 0.5343070030212402, + "learning_rate": 8.548888080443231e-05, + "loss": 1.4492, + "step": 4690 + }, + { + "epoch": 0.26146814558831727, + "grad_norm": 0.546418309211731, + "learning_rate": 8.54826078677549e-05, + "loss": 1.7292, + "step": 4691 + }, + { + "epoch": 0.2615238838414804, + "grad_norm": 0.5571802258491516, + "learning_rate": 8.547633380577604e-05, + "loss": 1.9054, + "step": 4692 + }, + { + "epoch": 0.2615796220946435, + "grad_norm": 0.5529661774635315, + "learning_rate": 8.54700586186947e-05, + "loss": 1.8537, + "step": 4693 + }, + { + "epoch": 0.2616353603478067, + "grad_norm": 0.5503031611442566, + "learning_rate": 8.546378230670992e-05, + "loss": 1.7507, + "step": 4694 + }, + { + "epoch": 0.26169109860096984, + "grad_norm": 0.5290326476097107, + "learning_rate": 8.545750487002073e-05, + "loss": 1.5895, + "step": 4695 + }, + { + "epoch": 0.26174683685413297, + "grad_norm": 0.5247073769569397, + "learning_rate": 8.54512263088262e-05, + "loss": 1.5736, + "step": 4696 + }, + { + "epoch": 0.26180257510729615, + "grad_norm": 0.575093686580658, + "learning_rate": 8.544494662332548e-05, + "loss": 1.5192, + "step": 4697 + }, + { + "epoch": 0.2618583133604593, + "grad_norm": 0.5360473990440369, + "learning_rate": 8.543866581371771e-05, + "loss": 1.7796, + "step": 4698 + }, + { + "epoch": 0.2619140516136224, + "grad_norm": 0.5478860139846802, + "learning_rate": 8.54323838802021e-05, + "loss": 1.756, + "step": 4699 + }, + { + "epoch": 0.2619697898667856, + "grad_norm": 0.5454539060592651, + "learning_rate": 8.542610082297783e-05, + "loss": 1.7589, + "step": 4700 + }, + { + "epoch": 0.2620255281199487, + "grad_norm": 0.5187868475914001, + "learning_rate": 8.541981664224421e-05, + "loss": 1.5043, + "step": 4701 + }, + { + "epoch": 0.26208126637311185, + "grad_norm": 0.5362755060195923, + "learning_rate": 8.54135313382005e-05, + "loss": 1.731, + "step": 4702 + }, + { + "epoch": 0.26213700462627504, + "grad_norm": 0.5599364638328552, + "learning_rate": 8.540724491104606e-05, + "loss": 1.6976, + "step": 4703 + }, + { + "epoch": 0.26219274287943817, + "grad_norm": 0.5924205183982849, + "learning_rate": 8.540095736098026e-05, + "loss": 1.8049, + "step": 4704 + }, + { + "epoch": 0.2622484811326013, + "grad_norm": 0.5288107395172119, + "learning_rate": 8.539466868820247e-05, + "loss": 1.5834, + "step": 4705 + }, + { + "epoch": 0.2623042193857644, + "grad_norm": 0.5498400330543518, + "learning_rate": 8.538837889291218e-05, + "loss": 1.6546, + "step": 4706 + }, + { + "epoch": 0.2623599576389276, + "grad_norm": 0.5080811381340027, + "learning_rate": 8.538208797530883e-05, + "loss": 1.434, + "step": 4707 + }, + { + "epoch": 0.26241569589209074, + "grad_norm": 0.5125556588172913, + "learning_rate": 8.537579593559195e-05, + "loss": 1.6628, + "step": 4708 + }, + { + "epoch": 0.26247143414525387, + "grad_norm": 0.5489838123321533, + "learning_rate": 8.536950277396106e-05, + "loss": 1.5702, + "step": 4709 + }, + { + "epoch": 0.26252717239841705, + "grad_norm": 0.5346508622169495, + "learning_rate": 8.536320849061577e-05, + "loss": 1.7829, + "step": 4710 + }, + { + "epoch": 0.2625829106515802, + "grad_norm": 0.5648466944694519, + "learning_rate": 8.535691308575569e-05, + "loss": 1.8271, + "step": 4711 + }, + { + "epoch": 0.2626386489047433, + "grad_norm": 0.5875536203384399, + "learning_rate": 8.535061655958048e-05, + "loss": 1.888, + "step": 4712 + }, + { + "epoch": 0.2626943871579065, + "grad_norm": 0.5403586626052856, + "learning_rate": 8.534431891228981e-05, + "loss": 1.5633, + "step": 4713 + }, + { + "epoch": 0.2627501254110696, + "grad_norm": 0.5541427135467529, + "learning_rate": 8.533802014408341e-05, + "loss": 1.7778, + "step": 4714 + }, + { + "epoch": 0.26280586366423275, + "grad_norm": 0.5390727519989014, + "learning_rate": 8.533172025516106e-05, + "loss": 1.6732, + "step": 4715 + }, + { + "epoch": 0.2628616019173959, + "grad_norm": 0.5591700077056885, + "learning_rate": 8.532541924572254e-05, + "loss": 1.7714, + "step": 4716 + }, + { + "epoch": 0.26291734017055907, + "grad_norm": 0.5306904911994934, + "learning_rate": 8.531911711596767e-05, + "loss": 1.7311, + "step": 4717 + }, + { + "epoch": 0.2629730784237222, + "grad_norm": 0.5665531158447266, + "learning_rate": 8.531281386609633e-05, + "loss": 1.684, + "step": 4718 + }, + { + "epoch": 0.2630288166768853, + "grad_norm": 0.5404395461082458, + "learning_rate": 8.530650949630844e-05, + "loss": 1.7727, + "step": 4719 + }, + { + "epoch": 0.2630845549300485, + "grad_norm": 0.5549681782722473, + "learning_rate": 8.530020400680392e-05, + "loss": 1.6802, + "step": 4720 + }, + { + "epoch": 0.26314029318321164, + "grad_norm": 0.5529362559318542, + "learning_rate": 8.529389739778272e-05, + "loss": 1.6691, + "step": 4721 + }, + { + "epoch": 0.26319603143637477, + "grad_norm": 0.5257294178009033, + "learning_rate": 8.528758966944489e-05, + "loss": 1.6649, + "step": 4722 + }, + { + "epoch": 0.26325176968953795, + "grad_norm": 0.5499683022499084, + "learning_rate": 8.528128082199046e-05, + "loss": 1.8637, + "step": 4723 + }, + { + "epoch": 0.2633075079427011, + "grad_norm": 0.5676036477088928, + "learning_rate": 8.527497085561949e-05, + "loss": 1.6409, + "step": 4724 + }, + { + "epoch": 0.2633632461958642, + "grad_norm": 0.5784804821014404, + "learning_rate": 8.526865977053211e-05, + "loss": 1.8414, + "step": 4725 + }, + { + "epoch": 0.2634189844490274, + "grad_norm": 0.592461884021759, + "learning_rate": 8.52623475669285e-05, + "loss": 1.725, + "step": 4726 + }, + { + "epoch": 0.2634747227021905, + "grad_norm": 0.5251427888870239, + "learning_rate": 8.52560342450088e-05, + "loss": 1.5888, + "step": 4727 + }, + { + "epoch": 0.26353046095535365, + "grad_norm": 0.5062176585197449, + "learning_rate": 8.524971980497325e-05, + "loss": 1.5588, + "step": 4728 + }, + { + "epoch": 0.2635861992085168, + "grad_norm": 0.5686171054840088, + "learning_rate": 8.524340424702211e-05, + "loss": 1.6186, + "step": 4729 + }, + { + "epoch": 0.26364193746167996, + "grad_norm": 0.5521769523620605, + "learning_rate": 8.523708757135567e-05, + "loss": 1.6917, + "step": 4730 + }, + { + "epoch": 0.2636976757148431, + "grad_norm": 0.5489006042480469, + "learning_rate": 8.523076977817426e-05, + "loss": 1.8079, + "step": 4731 + }, + { + "epoch": 0.2637534139680062, + "grad_norm": 0.5295306444168091, + "learning_rate": 8.522445086767826e-05, + "loss": 1.6814, + "step": 4732 + }, + { + "epoch": 0.2638091522211694, + "grad_norm": 0.5596312284469604, + "learning_rate": 8.521813084006802e-05, + "loss": 1.7971, + "step": 4733 + }, + { + "epoch": 0.26386489047433254, + "grad_norm": 0.535030722618103, + "learning_rate": 8.5211809695544e-05, + "loss": 1.6389, + "step": 4734 + }, + { + "epoch": 0.26392062872749567, + "grad_norm": 0.5560666918754578, + "learning_rate": 8.520548743430673e-05, + "loss": 1.8107, + "step": 4735 + }, + { + "epoch": 0.26397636698065885, + "grad_norm": 0.5749865770339966, + "learning_rate": 8.51991640565566e-05, + "loss": 1.7698, + "step": 4736 + }, + { + "epoch": 0.264032105233822, + "grad_norm": 0.603252649307251, + "learning_rate": 8.519283956249424e-05, + "loss": 1.9701, + "step": 4737 + }, + { + "epoch": 0.2640878434869851, + "grad_norm": 0.562053918838501, + "learning_rate": 8.51865139523202e-05, + "loss": 1.7033, + "step": 4738 + }, + { + "epoch": 0.26414358174014824, + "grad_norm": 0.5553662776947021, + "learning_rate": 8.518018722623509e-05, + "loss": 1.6353, + "step": 4739 + }, + { + "epoch": 0.2641993199933114, + "grad_norm": 0.5916672945022583, + "learning_rate": 8.517385938443955e-05, + "loss": 1.8496, + "step": 4740 + }, + { + "epoch": 0.26425505824647455, + "grad_norm": 0.549395740032196, + "learning_rate": 8.516753042713426e-05, + "loss": 1.612, + "step": 4741 + }, + { + "epoch": 0.2643107964996377, + "grad_norm": 0.5560966730117798, + "learning_rate": 8.516120035451996e-05, + "loss": 1.5978, + "step": 4742 + }, + { + "epoch": 0.26436653475280086, + "grad_norm": 0.5934261679649353, + "learning_rate": 8.515486916679738e-05, + "loss": 1.9667, + "step": 4743 + }, + { + "epoch": 0.264422273005964, + "grad_norm": 0.5441667437553406, + "learning_rate": 8.514853686416732e-05, + "loss": 1.639, + "step": 4744 + }, + { + "epoch": 0.2644780112591271, + "grad_norm": 0.5780582427978516, + "learning_rate": 8.51422034468306e-05, + "loss": 1.6839, + "step": 4745 + }, + { + "epoch": 0.2645337495122903, + "grad_norm": 0.5739880204200745, + "learning_rate": 8.513586891498809e-05, + "loss": 1.6927, + "step": 4746 + }, + { + "epoch": 0.26458948776545343, + "grad_norm": 0.5097702145576477, + "learning_rate": 8.512953326884066e-05, + "loss": 1.5131, + "step": 4747 + }, + { + "epoch": 0.26464522601861656, + "grad_norm": 0.5593822598457336, + "learning_rate": 8.512319650858926e-05, + "loss": 1.8373, + "step": 4748 + }, + { + "epoch": 0.26470096427177975, + "grad_norm": 0.546627938747406, + "learning_rate": 8.511685863443484e-05, + "loss": 1.723, + "step": 4749 + }, + { + "epoch": 0.2647567025249429, + "grad_norm": 0.5196560621261597, + "learning_rate": 8.511051964657842e-05, + "loss": 1.6108, + "step": 4750 + }, + { + "epoch": 0.264812440778106, + "grad_norm": 0.548095166683197, + "learning_rate": 8.510417954522102e-05, + "loss": 1.6268, + "step": 4751 + }, + { + "epoch": 0.26486817903126914, + "grad_norm": 0.5570634007453918, + "learning_rate": 8.509783833056373e-05, + "loss": 1.828, + "step": 4752 + }, + { + "epoch": 0.2649239172844323, + "grad_norm": 0.5177022814750671, + "learning_rate": 8.509149600280762e-05, + "loss": 1.6537, + "step": 4753 + }, + { + "epoch": 0.26497965553759545, + "grad_norm": 0.5529354810714722, + "learning_rate": 8.508515256215389e-05, + "loss": 1.6702, + "step": 4754 + }, + { + "epoch": 0.2650353937907586, + "grad_norm": 0.6287319660186768, + "learning_rate": 8.507880800880364e-05, + "loss": 1.7545, + "step": 4755 + }, + { + "epoch": 0.26509113204392176, + "grad_norm": 0.5878986716270447, + "learning_rate": 8.507246234295814e-05, + "loss": 1.9199, + "step": 4756 + }, + { + "epoch": 0.2651468702970849, + "grad_norm": 0.560119092464447, + "learning_rate": 8.506611556481862e-05, + "loss": 1.645, + "step": 4757 + }, + { + "epoch": 0.265202608550248, + "grad_norm": 0.5107282996177673, + "learning_rate": 8.505976767458636e-05, + "loss": 1.8503, + "step": 4758 + }, + { + "epoch": 0.2652583468034112, + "grad_norm": 0.5514339208602905, + "learning_rate": 8.50534186724627e-05, + "loss": 1.6562, + "step": 4759 + }, + { + "epoch": 0.26531408505657433, + "grad_norm": 0.541807234287262, + "learning_rate": 8.504706855864897e-05, + "loss": 1.7167, + "step": 4760 + }, + { + "epoch": 0.26536982330973746, + "grad_norm": 0.5748420357704163, + "learning_rate": 8.504071733334656e-05, + "loss": 1.955, + "step": 4761 + }, + { + "epoch": 0.2654255615629006, + "grad_norm": 0.5451623201370239, + "learning_rate": 8.503436499675687e-05, + "loss": 1.7336, + "step": 4762 + }, + { + "epoch": 0.2654812998160638, + "grad_norm": 0.5036576986312866, + "learning_rate": 8.502801154908142e-05, + "loss": 1.7619, + "step": 4763 + }, + { + "epoch": 0.2655370380692269, + "grad_norm": 0.5252074003219604, + "learning_rate": 8.502165699052168e-05, + "loss": 1.6425, + "step": 4764 + }, + { + "epoch": 0.26559277632239003, + "grad_norm": 0.5452297925949097, + "learning_rate": 8.501530132127915e-05, + "loss": 1.5942, + "step": 4765 + }, + { + "epoch": 0.2656485145755532, + "grad_norm": 0.5282885432243347, + "learning_rate": 8.500894454155541e-05, + "loss": 1.4847, + "step": 4766 + }, + { + "epoch": 0.26570425282871635, + "grad_norm": 0.6032153367996216, + "learning_rate": 8.500258665155207e-05, + "loss": 1.8069, + "step": 4767 + }, + { + "epoch": 0.2657599910818795, + "grad_norm": 0.6232243776321411, + "learning_rate": 8.499622765147078e-05, + "loss": 1.9243, + "step": 4768 + }, + { + "epoch": 0.26581572933504266, + "grad_norm": 0.5226832032203674, + "learning_rate": 8.498986754151316e-05, + "loss": 1.5832, + "step": 4769 + }, + { + "epoch": 0.2658714675882058, + "grad_norm": 0.653657853603363, + "learning_rate": 8.498350632188097e-05, + "loss": 1.7387, + "step": 4770 + }, + { + "epoch": 0.2659272058413689, + "grad_norm": 0.6087796688079834, + "learning_rate": 8.497714399277592e-05, + "loss": 1.7853, + "step": 4771 + }, + { + "epoch": 0.2659829440945321, + "grad_norm": 0.5050531029701233, + "learning_rate": 8.49707805543998e-05, + "loss": 1.4848, + "step": 4772 + }, + { + "epoch": 0.26603868234769523, + "grad_norm": 0.5245751738548279, + "learning_rate": 8.496441600695441e-05, + "loss": 1.615, + "step": 4773 + }, + { + "epoch": 0.26609442060085836, + "grad_norm": 0.5427295565605164, + "learning_rate": 8.495805035064159e-05, + "loss": 1.8508, + "step": 4774 + }, + { + "epoch": 0.2661501588540215, + "grad_norm": 0.5052759647369385, + "learning_rate": 8.495168358566325e-05, + "loss": 1.6307, + "step": 4775 + }, + { + "epoch": 0.2662058971071847, + "grad_norm": 0.5618288516998291, + "learning_rate": 8.494531571222128e-05, + "loss": 1.7516, + "step": 4776 + }, + { + "epoch": 0.2662616353603478, + "grad_norm": 0.5743941068649292, + "learning_rate": 8.493894673051765e-05, + "loss": 1.9439, + "step": 4777 + }, + { + "epoch": 0.26631737361351093, + "grad_norm": 0.5246620178222656, + "learning_rate": 8.493257664075433e-05, + "loss": 1.7159, + "step": 4778 + }, + { + "epoch": 0.2663731118666741, + "grad_norm": 0.5409666895866394, + "learning_rate": 8.492620544313335e-05, + "loss": 1.6972, + "step": 4779 + }, + { + "epoch": 0.26642885011983725, + "grad_norm": 0.5137554407119751, + "learning_rate": 8.491983313785676e-05, + "loss": 1.6285, + "step": 4780 + }, + { + "epoch": 0.2664845883730004, + "grad_norm": 0.6102763414382935, + "learning_rate": 8.491345972512668e-05, + "loss": 1.7433, + "step": 4781 + }, + { + "epoch": 0.26654032662616356, + "grad_norm": 0.6035791039466858, + "learning_rate": 8.490708520514519e-05, + "loss": 1.8665, + "step": 4782 + }, + { + "epoch": 0.2665960648793267, + "grad_norm": 0.5769240856170654, + "learning_rate": 8.490070957811449e-05, + "loss": 1.7147, + "step": 4783 + }, + { + "epoch": 0.2666518031324898, + "grad_norm": 0.5191882252693176, + "learning_rate": 8.489433284423678e-05, + "loss": 1.5935, + "step": 4784 + }, + { + "epoch": 0.26670754138565295, + "grad_norm": 0.575363039970398, + "learning_rate": 8.488795500371427e-05, + "loss": 1.8616, + "step": 4785 + }, + { + "epoch": 0.26676327963881613, + "grad_norm": 0.5380163788795471, + "learning_rate": 8.488157605674925e-05, + "loss": 1.5693, + "step": 4786 + }, + { + "epoch": 0.26681901789197926, + "grad_norm": 0.5527309775352478, + "learning_rate": 8.487519600354399e-05, + "loss": 1.797, + "step": 4787 + }, + { + "epoch": 0.2668747561451424, + "grad_norm": 0.5432277321815491, + "learning_rate": 8.486881484430085e-05, + "loss": 1.7024, + "step": 4788 + }, + { + "epoch": 0.2669304943983056, + "grad_norm": 0.5643296837806702, + "learning_rate": 8.486243257922221e-05, + "loss": 1.6602, + "step": 4789 + }, + { + "epoch": 0.2669862326514687, + "grad_norm": 0.5539331436157227, + "learning_rate": 8.485604920851049e-05, + "loss": 1.7195, + "step": 4790 + }, + { + "epoch": 0.26704197090463183, + "grad_norm": 0.5279936790466309, + "learning_rate": 8.48496647323681e-05, + "loss": 1.6503, + "step": 4791 + }, + { + "epoch": 0.267097709157795, + "grad_norm": 0.5447912812232971, + "learning_rate": 8.484327915099752e-05, + "loss": 1.7975, + "step": 4792 + }, + { + "epoch": 0.26715344741095814, + "grad_norm": 0.6047879457473755, + "learning_rate": 8.48368924646013e-05, + "loss": 1.8362, + "step": 4793 + }, + { + "epoch": 0.2672091856641213, + "grad_norm": 0.5555823445320129, + "learning_rate": 8.483050467338194e-05, + "loss": 1.7033, + "step": 4794 + }, + { + "epoch": 0.26726492391728446, + "grad_norm": 0.5324097871780396, + "learning_rate": 8.482411577754205e-05, + "loss": 1.828, + "step": 4795 + }, + { + "epoch": 0.2673206621704476, + "grad_norm": 0.5133151412010193, + "learning_rate": 8.481772577728426e-05, + "loss": 1.6922, + "step": 4796 + }, + { + "epoch": 0.2673764004236107, + "grad_norm": 0.5466338396072388, + "learning_rate": 8.48113346728112e-05, + "loss": 1.7228, + "step": 4797 + }, + { + "epoch": 0.26743213867677385, + "grad_norm": 0.5190402269363403, + "learning_rate": 8.480494246432557e-05, + "loss": 1.7192, + "step": 4798 + }, + { + "epoch": 0.26748787692993703, + "grad_norm": 0.4959962069988251, + "learning_rate": 8.47985491520301e-05, + "loss": 1.5593, + "step": 4799 + }, + { + "epoch": 0.26754361518310016, + "grad_norm": 0.5530042052268982, + "learning_rate": 8.479215473612754e-05, + "loss": 1.7545, + "step": 4800 + }, + { + "epoch": 0.2675993534362633, + "grad_norm": 0.6360591650009155, + "learning_rate": 8.478575921682066e-05, + "loss": 1.9369, + "step": 4801 + }, + { + "epoch": 0.26765509168942647, + "grad_norm": 0.5604984164237976, + "learning_rate": 8.477936259431235e-05, + "loss": 1.6485, + "step": 4802 + }, + { + "epoch": 0.2677108299425896, + "grad_norm": 0.568709671497345, + "learning_rate": 8.477296486880541e-05, + "loss": 1.6459, + "step": 4803 + }, + { + "epoch": 0.26776656819575273, + "grad_norm": 0.6228764653205872, + "learning_rate": 8.476656604050277e-05, + "loss": 1.8825, + "step": 4804 + }, + { + "epoch": 0.2678223064489159, + "grad_norm": 0.5803889036178589, + "learning_rate": 8.476016610960736e-05, + "loss": 1.8011, + "step": 4805 + }, + { + "epoch": 0.26787804470207904, + "grad_norm": 0.5778336524963379, + "learning_rate": 8.475376507632215e-05, + "loss": 1.726, + "step": 4806 + }, + { + "epoch": 0.2679337829552422, + "grad_norm": 0.5755890011787415, + "learning_rate": 8.474736294085014e-05, + "loss": 1.6394, + "step": 4807 + }, + { + "epoch": 0.2679895212084053, + "grad_norm": 0.5545676350593567, + "learning_rate": 8.474095970339436e-05, + "loss": 1.7973, + "step": 4808 + }, + { + "epoch": 0.2680452594615685, + "grad_norm": 0.5003368854522705, + "learning_rate": 8.473455536415789e-05, + "loss": 1.6653, + "step": 4809 + }, + { + "epoch": 0.2681009977147316, + "grad_norm": 0.5292695164680481, + "learning_rate": 8.472814992334386e-05, + "loss": 1.7463, + "step": 4810 + }, + { + "epoch": 0.26815673596789474, + "grad_norm": 0.604960560798645, + "learning_rate": 8.472174338115537e-05, + "loss": 1.9016, + "step": 4811 + }, + { + "epoch": 0.26821247422105793, + "grad_norm": 0.5484800338745117, + "learning_rate": 8.471533573779564e-05, + "loss": 1.6117, + "step": 4812 + }, + { + "epoch": 0.26826821247422106, + "grad_norm": 0.5383596420288086, + "learning_rate": 8.470892699346786e-05, + "loss": 1.6871, + "step": 4813 + }, + { + "epoch": 0.2683239507273842, + "grad_norm": 0.5479928851127625, + "learning_rate": 8.470251714837529e-05, + "loss": 1.7255, + "step": 4814 + }, + { + "epoch": 0.26837968898054737, + "grad_norm": 0.5112576484680176, + "learning_rate": 8.46961062027212e-05, + "loss": 1.414, + "step": 4815 + }, + { + "epoch": 0.2684354272337105, + "grad_norm": 0.547825038433075, + "learning_rate": 8.46896941567089e-05, + "loss": 1.835, + "step": 4816 + }, + { + "epoch": 0.26849116548687363, + "grad_norm": 0.5121808648109436, + "learning_rate": 8.468328101054177e-05, + "loss": 1.5269, + "step": 4817 + }, + { + "epoch": 0.2685469037400368, + "grad_norm": 0.5761928558349609, + "learning_rate": 8.467686676442318e-05, + "loss": 1.7195, + "step": 4818 + }, + { + "epoch": 0.26860264199319994, + "grad_norm": 0.547089159488678, + "learning_rate": 8.467045141855656e-05, + "loss": 1.6714, + "step": 4819 + }, + { + "epoch": 0.26865838024636307, + "grad_norm": 0.5228059887886047, + "learning_rate": 8.466403497314537e-05, + "loss": 1.6444, + "step": 4820 + }, + { + "epoch": 0.2687141184995262, + "grad_norm": 0.5589326620101929, + "learning_rate": 8.465761742839307e-05, + "loss": 1.9121, + "step": 4821 + }, + { + "epoch": 0.2687698567526894, + "grad_norm": 0.5607814192771912, + "learning_rate": 8.465119878450324e-05, + "loss": 1.8351, + "step": 4822 + }, + { + "epoch": 0.2688255950058525, + "grad_norm": 0.591454029083252, + "learning_rate": 8.46447790416794e-05, + "loss": 1.8308, + "step": 4823 + }, + { + "epoch": 0.26888133325901564, + "grad_norm": 0.5167153477668762, + "learning_rate": 8.463835820012517e-05, + "loss": 1.6928, + "step": 4824 + }, + { + "epoch": 0.2689370715121788, + "grad_norm": 0.5741368532180786, + "learning_rate": 8.463193626004418e-05, + "loss": 1.8407, + "step": 4825 + }, + { + "epoch": 0.26899280976534196, + "grad_norm": 0.563448965549469, + "learning_rate": 8.462551322164007e-05, + "loss": 1.7246, + "step": 4826 + }, + { + "epoch": 0.2690485480185051, + "grad_norm": 0.5690648555755615, + "learning_rate": 8.461908908511657e-05, + "loss": 1.7408, + "step": 4827 + }, + { + "epoch": 0.26910428627166827, + "grad_norm": 0.5448554754257202, + "learning_rate": 8.461266385067741e-05, + "loss": 1.6012, + "step": 4828 + }, + { + "epoch": 0.2691600245248314, + "grad_norm": 0.5054116249084473, + "learning_rate": 8.460623751852637e-05, + "loss": 1.6175, + "step": 4829 + }, + { + "epoch": 0.2692157627779945, + "grad_norm": 0.5798751711845398, + "learning_rate": 8.459981008886721e-05, + "loss": 1.7742, + "step": 4830 + }, + { + "epoch": 0.26927150103115766, + "grad_norm": 0.5339779257774353, + "learning_rate": 8.459338156190384e-05, + "loss": 1.6737, + "step": 4831 + }, + { + "epoch": 0.26932723928432084, + "grad_norm": 0.5387359261512756, + "learning_rate": 8.45869519378401e-05, + "loss": 1.6606, + "step": 4832 + }, + { + "epoch": 0.26938297753748397, + "grad_norm": 0.646202802658081, + "learning_rate": 8.458052121687987e-05, + "loss": 1.9741, + "step": 4833 + }, + { + "epoch": 0.2694387157906471, + "grad_norm": 0.5640881061553955, + "learning_rate": 8.457408939922715e-05, + "loss": 1.7103, + "step": 4834 + }, + { + "epoch": 0.2694944540438103, + "grad_norm": 0.567292332649231, + "learning_rate": 8.456765648508589e-05, + "loss": 1.7605, + "step": 4835 + }, + { + "epoch": 0.2695501922969734, + "grad_norm": 0.6057398319244385, + "learning_rate": 8.456122247466009e-05, + "loss": 1.6074, + "step": 4836 + }, + { + "epoch": 0.26960593055013654, + "grad_norm": 0.6216564178466797, + "learning_rate": 8.455478736815385e-05, + "loss": 1.6341, + "step": 4837 + }, + { + "epoch": 0.2696616688032997, + "grad_norm": 0.53920978307724, + "learning_rate": 8.454835116577122e-05, + "loss": 1.792, + "step": 4838 + }, + { + "epoch": 0.26971740705646285, + "grad_norm": 0.5827376842498779, + "learning_rate": 8.45419138677163e-05, + "loss": 1.5826, + "step": 4839 + }, + { + "epoch": 0.269773145309626, + "grad_norm": 0.5303118228912354, + "learning_rate": 8.453547547419329e-05, + "loss": 1.7387, + "step": 4840 + }, + { + "epoch": 0.26982888356278917, + "grad_norm": 0.5183376669883728, + "learning_rate": 8.452903598540634e-05, + "loss": 1.532, + "step": 4841 + }, + { + "epoch": 0.2698846218159523, + "grad_norm": 0.5537537336349487, + "learning_rate": 8.452259540155968e-05, + "loss": 1.7955, + "step": 4842 + }, + { + "epoch": 0.2699403600691154, + "grad_norm": 0.5679836273193359, + "learning_rate": 8.451615372285758e-05, + "loss": 1.7329, + "step": 4843 + }, + { + "epoch": 0.26999609832227855, + "grad_norm": 0.5696743726730347, + "learning_rate": 8.450971094950433e-05, + "loss": 1.7294, + "step": 4844 + }, + { + "epoch": 0.27005183657544174, + "grad_norm": 0.5818564295768738, + "learning_rate": 8.450326708170426e-05, + "loss": 2.0301, + "step": 4845 + }, + { + "epoch": 0.27010757482860487, + "grad_norm": 0.5044540762901306, + "learning_rate": 8.449682211966172e-05, + "loss": 1.5171, + "step": 4846 + }, + { + "epoch": 0.270163313081768, + "grad_norm": 0.5692309141159058, + "learning_rate": 8.449037606358111e-05, + "loss": 1.776, + "step": 4847 + }, + { + "epoch": 0.2702190513349312, + "grad_norm": 0.5652437210083008, + "learning_rate": 8.448392891366688e-05, + "loss": 1.8956, + "step": 4848 + }, + { + "epoch": 0.2702747895880943, + "grad_norm": 0.5531434416770935, + "learning_rate": 8.447748067012345e-05, + "loss": 1.7156, + "step": 4849 + }, + { + "epoch": 0.27033052784125744, + "grad_norm": 0.5418469309806824, + "learning_rate": 8.447103133315537e-05, + "loss": 1.6983, + "step": 4850 + }, + { + "epoch": 0.2703862660944206, + "grad_norm": 0.5276792049407959, + "learning_rate": 8.446458090296716e-05, + "loss": 1.6147, + "step": 4851 + }, + { + "epoch": 0.27044200434758375, + "grad_norm": 0.5772181749343872, + "learning_rate": 8.445812937976338e-05, + "loss": 1.677, + "step": 4852 + }, + { + "epoch": 0.2704977426007469, + "grad_norm": 0.5323836803436279, + "learning_rate": 8.445167676374865e-05, + "loss": 1.4833, + "step": 4853 + }, + { + "epoch": 0.27055348085391, + "grad_norm": 0.5478299260139465, + "learning_rate": 8.444522305512757e-05, + "loss": 1.5832, + "step": 4854 + }, + { + "epoch": 0.2706092191070732, + "grad_norm": 0.5325939655303955, + "learning_rate": 8.443876825410488e-05, + "loss": 1.4971, + "step": 4855 + }, + { + "epoch": 0.2706649573602363, + "grad_norm": 0.5912976861000061, + "learning_rate": 8.443231236088524e-05, + "loss": 1.7624, + "step": 4856 + }, + { + "epoch": 0.27072069561339945, + "grad_norm": 0.5368456244468689, + "learning_rate": 8.44258553756734e-05, + "loss": 1.5509, + "step": 4857 + }, + { + "epoch": 0.27077643386656264, + "grad_norm": 0.5713909864425659, + "learning_rate": 8.441939729867415e-05, + "loss": 1.8286, + "step": 4858 + }, + { + "epoch": 0.27083217211972577, + "grad_norm": 0.5259481072425842, + "learning_rate": 8.44129381300923e-05, + "loss": 1.7291, + "step": 4859 + }, + { + "epoch": 0.2708879103728889, + "grad_norm": 0.5365427136421204, + "learning_rate": 8.440647787013268e-05, + "loss": 1.6051, + "step": 4860 + }, + { + "epoch": 0.2709436486260521, + "grad_norm": 0.5223046541213989, + "learning_rate": 8.44000165190002e-05, + "loss": 1.5241, + "step": 4861 + }, + { + "epoch": 0.2709993868792152, + "grad_norm": 0.5721556544303894, + "learning_rate": 8.439355407689975e-05, + "loss": 1.8138, + "step": 4862 + }, + { + "epoch": 0.27105512513237834, + "grad_norm": 0.527158260345459, + "learning_rate": 8.43870905440363e-05, + "loss": 1.5114, + "step": 4863 + }, + { + "epoch": 0.2711108633855415, + "grad_norm": 0.5364054441452026, + "learning_rate": 8.438062592061485e-05, + "loss": 1.5331, + "step": 4864 + }, + { + "epoch": 0.27116660163870465, + "grad_norm": 0.5465856790542603, + "learning_rate": 8.437416020684036e-05, + "loss": 1.5122, + "step": 4865 + }, + { + "epoch": 0.2712223398918678, + "grad_norm": 0.5655773282051086, + "learning_rate": 8.436769340291794e-05, + "loss": 1.8776, + "step": 4866 + }, + { + "epoch": 0.2712780781450309, + "grad_norm": 0.5278435349464417, + "learning_rate": 8.436122550905266e-05, + "loss": 1.6388, + "step": 4867 + }, + { + "epoch": 0.2713338163981941, + "grad_norm": 0.5141345262527466, + "learning_rate": 8.435475652544967e-05, + "loss": 1.5203, + "step": 4868 + }, + { + "epoch": 0.2713895546513572, + "grad_norm": 0.5731988549232483, + "learning_rate": 8.434828645231407e-05, + "loss": 1.8796, + "step": 4869 + }, + { + "epoch": 0.27144529290452035, + "grad_norm": 0.5262272357940674, + "learning_rate": 8.434181528985112e-05, + "loss": 1.711, + "step": 4870 + }, + { + "epoch": 0.27150103115768354, + "grad_norm": 0.5410183668136597, + "learning_rate": 8.4335343038266e-05, + "loss": 1.5739, + "step": 4871 + }, + { + "epoch": 0.27155676941084667, + "grad_norm": 0.5376774072647095, + "learning_rate": 8.432886969776398e-05, + "loss": 1.7037, + "step": 4872 + }, + { + "epoch": 0.2716125076640098, + "grad_norm": 0.4998942017555237, + "learning_rate": 8.432239526855036e-05, + "loss": 1.566, + "step": 4873 + }, + { + "epoch": 0.271668245917173, + "grad_norm": 0.562468945980072, + "learning_rate": 8.431591975083049e-05, + "loss": 1.7742, + "step": 4874 + }, + { + "epoch": 0.2717239841703361, + "grad_norm": 0.5608972907066345, + "learning_rate": 8.430944314480973e-05, + "loss": 1.7467, + "step": 4875 + }, + { + "epoch": 0.27177972242349924, + "grad_norm": 0.6075250506401062, + "learning_rate": 8.430296545069345e-05, + "loss": 1.5414, + "step": 4876 + }, + { + "epoch": 0.27183546067666237, + "grad_norm": 0.5488311052322388, + "learning_rate": 8.429648666868713e-05, + "loss": 1.7401, + "step": 4877 + }, + { + "epoch": 0.27189119892982555, + "grad_norm": 0.5740364193916321, + "learning_rate": 8.429000679899619e-05, + "loss": 1.6739, + "step": 4878 + }, + { + "epoch": 0.2719469371829887, + "grad_norm": 0.5271220207214355, + "learning_rate": 8.428352584182617e-05, + "loss": 1.6982, + "step": 4879 + }, + { + "epoch": 0.2720026754361518, + "grad_norm": 0.5354405045509338, + "learning_rate": 8.42770437973826e-05, + "loss": 1.6927, + "step": 4880 + }, + { + "epoch": 0.272058413689315, + "grad_norm": 0.569052517414093, + "learning_rate": 8.427056066587105e-05, + "loss": 1.6674, + "step": 4881 + }, + { + "epoch": 0.2721141519424781, + "grad_norm": 0.5651227831840515, + "learning_rate": 8.426407644749711e-05, + "loss": 1.8356, + "step": 4882 + }, + { + "epoch": 0.27216989019564125, + "grad_norm": 0.5364747643470764, + "learning_rate": 8.425759114246647e-05, + "loss": 1.749, + "step": 4883 + }, + { + "epoch": 0.27222562844880444, + "grad_norm": 0.48416903614997864, + "learning_rate": 8.425110475098476e-05, + "loss": 1.4771, + "step": 4884 + }, + { + "epoch": 0.27228136670196756, + "grad_norm": 0.5686883926391602, + "learning_rate": 8.42446172732577e-05, + "loss": 1.6603, + "step": 4885 + }, + { + "epoch": 0.2723371049551307, + "grad_norm": 0.5875502824783325, + "learning_rate": 8.423812870949104e-05, + "loss": 1.8797, + "step": 4886 + }, + { + "epoch": 0.2723928432082939, + "grad_norm": 0.5201019644737244, + "learning_rate": 8.423163905989055e-05, + "loss": 1.649, + "step": 4887 + }, + { + "epoch": 0.272448581461457, + "grad_norm": 0.566376268863678, + "learning_rate": 8.422514832466206e-05, + "loss": 1.7182, + "step": 4888 + }, + { + "epoch": 0.27250431971462014, + "grad_norm": 0.5158393979072571, + "learning_rate": 8.421865650401143e-05, + "loss": 1.6317, + "step": 4889 + }, + { + "epoch": 0.27256005796778326, + "grad_norm": 0.5439308881759644, + "learning_rate": 8.421216359814451e-05, + "loss": 1.7071, + "step": 4890 + }, + { + "epoch": 0.27261579622094645, + "grad_norm": 0.5321268439292908, + "learning_rate": 8.420566960726723e-05, + "loss": 1.6561, + "step": 4891 + }, + { + "epoch": 0.2726715344741096, + "grad_norm": 0.4758521616458893, + "learning_rate": 8.419917453158554e-05, + "loss": 1.5538, + "step": 4892 + }, + { + "epoch": 0.2727272727272727, + "grad_norm": 0.4964730441570282, + "learning_rate": 8.419267837130544e-05, + "loss": 1.5957, + "step": 4893 + }, + { + "epoch": 0.2727830109804359, + "grad_norm": 0.555168628692627, + "learning_rate": 8.418618112663292e-05, + "loss": 1.6552, + "step": 4894 + }, + { + "epoch": 0.272838749233599, + "grad_norm": 0.5903061032295227, + "learning_rate": 8.417968279777409e-05, + "loss": 1.8649, + "step": 4895 + }, + { + "epoch": 0.27289448748676215, + "grad_norm": 0.584933876991272, + "learning_rate": 8.417318338493497e-05, + "loss": 1.8317, + "step": 4896 + }, + { + "epoch": 0.27295022573992533, + "grad_norm": 0.6088751554489136, + "learning_rate": 8.416668288832173e-05, + "loss": 1.775, + "step": 4897 + }, + { + "epoch": 0.27300596399308846, + "grad_norm": 0.6300697326660156, + "learning_rate": 8.41601813081405e-05, + "loss": 1.9256, + "step": 4898 + }, + { + "epoch": 0.2730617022462516, + "grad_norm": 0.5516534447669983, + "learning_rate": 8.415367864459751e-05, + "loss": 1.6553, + "step": 4899 + }, + { + "epoch": 0.2731174404994147, + "grad_norm": 0.5985352993011475, + "learning_rate": 8.414717489789894e-05, + "loss": 1.8121, + "step": 4900 + }, + { + "epoch": 0.2731731787525779, + "grad_norm": 0.5280508399009705, + "learning_rate": 8.414067006825108e-05, + "loss": 1.657, + "step": 4901 + }, + { + "epoch": 0.27322891700574103, + "grad_norm": 0.6586048007011414, + "learning_rate": 8.413416415586024e-05, + "loss": 2.2447, + "step": 4902 + }, + { + "epoch": 0.27328465525890416, + "grad_norm": 0.5527061223983765, + "learning_rate": 8.412765716093272e-05, + "loss": 1.5666, + "step": 4903 + }, + { + "epoch": 0.27334039351206735, + "grad_norm": 0.5549877882003784, + "learning_rate": 8.412114908367488e-05, + "loss": 1.5972, + "step": 4904 + }, + { + "epoch": 0.2733961317652305, + "grad_norm": 0.5879062414169312, + "learning_rate": 8.411463992429314e-05, + "loss": 1.8609, + "step": 4905 + }, + { + "epoch": 0.2734518700183936, + "grad_norm": 0.5397518873214722, + "learning_rate": 8.41081296829939e-05, + "loss": 1.8211, + "step": 4906 + }, + { + "epoch": 0.2735076082715568, + "grad_norm": 0.5364968776702881, + "learning_rate": 8.410161835998369e-05, + "loss": 1.7879, + "step": 4907 + }, + { + "epoch": 0.2735633465247199, + "grad_norm": 0.5714520215988159, + "learning_rate": 8.409510595546894e-05, + "loss": 1.9543, + "step": 4908 + }, + { + "epoch": 0.27361908477788305, + "grad_norm": 0.5671858787536621, + "learning_rate": 8.408859246965623e-05, + "loss": 1.8165, + "step": 4909 + }, + { + "epoch": 0.27367482303104623, + "grad_norm": 0.6034393906593323, + "learning_rate": 8.408207790275213e-05, + "loss": 1.8084, + "step": 4910 + }, + { + "epoch": 0.27373056128420936, + "grad_norm": 0.5954535007476807, + "learning_rate": 8.407556225496322e-05, + "loss": 1.782, + "step": 4911 + }, + { + "epoch": 0.2737862995373725, + "grad_norm": 0.5597085952758789, + "learning_rate": 8.406904552649614e-05, + "loss": 1.7673, + "step": 4912 + }, + { + "epoch": 0.2738420377905356, + "grad_norm": 0.7730258107185364, + "learning_rate": 8.406252771755758e-05, + "loss": 1.9742, + "step": 4913 + }, + { + "epoch": 0.2738977760436988, + "grad_norm": 0.5349806547164917, + "learning_rate": 8.405600882835425e-05, + "loss": 1.6226, + "step": 4914 + }, + { + "epoch": 0.27395351429686193, + "grad_norm": 0.5271722674369812, + "learning_rate": 8.404948885909288e-05, + "loss": 1.7948, + "step": 4915 + }, + { + "epoch": 0.27400925255002506, + "grad_norm": 0.6604454517364502, + "learning_rate": 8.404296780998022e-05, + "loss": 1.5653, + "step": 4916 + }, + { + "epoch": 0.27406499080318825, + "grad_norm": 0.5219733119010925, + "learning_rate": 8.403644568122313e-05, + "loss": 1.6596, + "step": 4917 + }, + { + "epoch": 0.2741207290563514, + "grad_norm": 0.5320934653282166, + "learning_rate": 8.402992247302842e-05, + "loss": 1.7119, + "step": 4918 + }, + { + "epoch": 0.2741764673095145, + "grad_norm": 0.5232207179069519, + "learning_rate": 8.402339818560296e-05, + "loss": 1.7161, + "step": 4919 + }, + { + "epoch": 0.2742322055626777, + "grad_norm": 0.5363631844520569, + "learning_rate": 8.401687281915371e-05, + "loss": 1.7174, + "step": 4920 + }, + { + "epoch": 0.2742879438158408, + "grad_norm": 0.5237067937850952, + "learning_rate": 8.401034637388758e-05, + "loss": 1.5517, + "step": 4921 + }, + { + "epoch": 0.27434368206900395, + "grad_norm": 0.5529504418373108, + "learning_rate": 8.400381885001155e-05, + "loss": 1.7067, + "step": 4922 + }, + { + "epoch": 0.2743994203221671, + "grad_norm": 0.5712334513664246, + "learning_rate": 8.399729024773264e-05, + "loss": 1.7333, + "step": 4923 + }, + { + "epoch": 0.27445515857533026, + "grad_norm": 0.5530427098274231, + "learning_rate": 8.39907605672579e-05, + "loss": 1.7721, + "step": 4924 + }, + { + "epoch": 0.2745108968284934, + "grad_norm": 0.5096892714500427, + "learning_rate": 8.398422980879442e-05, + "loss": 1.5788, + "step": 4925 + }, + { + "epoch": 0.2745666350816565, + "grad_norm": 0.5875157713890076, + "learning_rate": 8.39776979725493e-05, + "loss": 1.7782, + "step": 4926 + }, + { + "epoch": 0.2746223733348197, + "grad_norm": 0.5620753169059753, + "learning_rate": 8.397116505872973e-05, + "loss": 1.6911, + "step": 4927 + }, + { + "epoch": 0.27467811158798283, + "grad_norm": 0.5037546157836914, + "learning_rate": 8.396463106754285e-05, + "loss": 1.7944, + "step": 4928 + }, + { + "epoch": 0.27473384984114596, + "grad_norm": 0.5311979055404663, + "learning_rate": 8.395809599919591e-05, + "loss": 1.8542, + "step": 4929 + }, + { + "epoch": 0.27478958809430915, + "grad_norm": 0.5294662714004517, + "learning_rate": 8.395155985389615e-05, + "loss": 1.582, + "step": 4930 + }, + { + "epoch": 0.2748453263474723, + "grad_norm": 0.5880303382873535, + "learning_rate": 8.394502263185087e-05, + "loss": 1.8807, + "step": 4931 + }, + { + "epoch": 0.2749010646006354, + "grad_norm": 0.5946251153945923, + "learning_rate": 8.393848433326736e-05, + "loss": 1.8139, + "step": 4932 + }, + { + "epoch": 0.2749568028537986, + "grad_norm": 0.5572118759155273, + "learning_rate": 8.393194495835304e-05, + "loss": 1.9141, + "step": 4933 + }, + { + "epoch": 0.2750125411069617, + "grad_norm": 0.5573039054870605, + "learning_rate": 8.392540450731522e-05, + "loss": 1.7951, + "step": 4934 + }, + { + "epoch": 0.27506827936012485, + "grad_norm": 0.540758490562439, + "learning_rate": 8.39188629803614e-05, + "loss": 1.7804, + "step": 4935 + }, + { + "epoch": 0.275124017613288, + "grad_norm": 0.5271297693252563, + "learning_rate": 8.3912320377699e-05, + "loss": 1.82, + "step": 4936 + }, + { + "epoch": 0.27517975586645116, + "grad_norm": 0.5359855890274048, + "learning_rate": 8.390577669953552e-05, + "loss": 1.7678, + "step": 4937 + }, + { + "epoch": 0.2752354941196143, + "grad_norm": 0.5025729537010193, + "learning_rate": 8.389923194607849e-05, + "loss": 1.5144, + "step": 4938 + }, + { + "epoch": 0.2752912323727774, + "grad_norm": 0.5402054190635681, + "learning_rate": 8.389268611753546e-05, + "loss": 1.6204, + "step": 4939 + }, + { + "epoch": 0.2753469706259406, + "grad_norm": 0.5499907732009888, + "learning_rate": 8.388613921411404e-05, + "loss": 1.6948, + "step": 4940 + }, + { + "epoch": 0.27540270887910373, + "grad_norm": 0.6044038534164429, + "learning_rate": 8.387959123602185e-05, + "loss": 1.5522, + "step": 4941 + }, + { + "epoch": 0.27545844713226686, + "grad_norm": 0.5463374853134155, + "learning_rate": 8.387304218346656e-05, + "loss": 1.6392, + "step": 4942 + }, + { + "epoch": 0.27551418538543004, + "grad_norm": 0.5164476633071899, + "learning_rate": 8.386649205665586e-05, + "loss": 1.674, + "step": 4943 + }, + { + "epoch": 0.2755699236385932, + "grad_norm": 0.6093559861183167, + "learning_rate": 8.385994085579751e-05, + "loss": 2.0767, + "step": 4944 + }, + { + "epoch": 0.2756256618917563, + "grad_norm": 0.5542387366294861, + "learning_rate": 8.385338858109922e-05, + "loss": 1.8275, + "step": 4945 + }, + { + "epoch": 0.27568140014491943, + "grad_norm": 0.5787892937660217, + "learning_rate": 8.384683523276885e-05, + "loss": 1.5918, + "step": 4946 + }, + { + "epoch": 0.2757371383980826, + "grad_norm": 0.5294553637504578, + "learning_rate": 8.38402808110142e-05, + "loss": 1.6857, + "step": 4947 + }, + { + "epoch": 0.27579287665124574, + "grad_norm": 0.5397957563400269, + "learning_rate": 8.383372531604314e-05, + "loss": 1.6894, + "step": 4948 + }, + { + "epoch": 0.2758486149044089, + "grad_norm": 0.5266357660293579, + "learning_rate": 8.382716874806357e-05, + "loss": 1.7214, + "step": 4949 + }, + { + "epoch": 0.27590435315757206, + "grad_norm": 0.5046342611312866, + "learning_rate": 8.382061110728345e-05, + "loss": 1.4341, + "step": 4950 + }, + { + "epoch": 0.2759600914107352, + "grad_norm": 0.5609323382377625, + "learning_rate": 8.381405239391074e-05, + "loss": 1.7528, + "step": 4951 + }, + { + "epoch": 0.2760158296638983, + "grad_norm": 0.5804145336151123, + "learning_rate": 8.38074926081534e-05, + "loss": 1.8709, + "step": 4952 + }, + { + "epoch": 0.2760715679170615, + "grad_norm": 0.5542110204696655, + "learning_rate": 8.380093175021953e-05, + "loss": 1.8472, + "step": 4953 + }, + { + "epoch": 0.27612730617022463, + "grad_norm": 0.5371457934379578, + "learning_rate": 8.379436982031718e-05, + "loss": 1.5508, + "step": 4954 + }, + { + "epoch": 0.27618304442338776, + "grad_norm": 0.6307567358016968, + "learning_rate": 8.378780681865445e-05, + "loss": 1.7762, + "step": 4955 + }, + { + "epoch": 0.27623878267655094, + "grad_norm": 0.6115426421165466, + "learning_rate": 8.37812427454395e-05, + "loss": 1.8666, + "step": 4956 + }, + { + "epoch": 0.27629452092971407, + "grad_norm": 0.5419024229049683, + "learning_rate": 8.377467760088046e-05, + "loss": 1.6681, + "step": 4957 + }, + { + "epoch": 0.2763502591828772, + "grad_norm": 0.5587498545646667, + "learning_rate": 8.376811138518558e-05, + "loss": 1.8999, + "step": 4958 + }, + { + "epoch": 0.27640599743604033, + "grad_norm": 0.6416218876838684, + "learning_rate": 8.376154409856309e-05, + "loss": 2.1091, + "step": 4959 + }, + { + "epoch": 0.2764617356892035, + "grad_norm": 0.5992975234985352, + "learning_rate": 8.375497574122127e-05, + "loss": 1.837, + "step": 4960 + }, + { + "epoch": 0.27651747394236664, + "grad_norm": 0.5807574987411499, + "learning_rate": 8.374840631336842e-05, + "loss": 1.643, + "step": 4961 + }, + { + "epoch": 0.27657321219552977, + "grad_norm": 0.5473943948745728, + "learning_rate": 8.374183581521288e-05, + "loss": 1.6044, + "step": 4962 + }, + { + "epoch": 0.27662895044869296, + "grad_norm": 0.5294444561004639, + "learning_rate": 8.373526424696305e-05, + "loss": 1.7088, + "step": 4963 + }, + { + "epoch": 0.2766846887018561, + "grad_norm": 0.5424871444702148, + "learning_rate": 8.372869160882733e-05, + "loss": 1.5888, + "step": 4964 + }, + { + "epoch": 0.2767404269550192, + "grad_norm": 0.5405928492546082, + "learning_rate": 8.372211790101414e-05, + "loss": 1.6905, + "step": 4965 + }, + { + "epoch": 0.2767961652081824, + "grad_norm": 0.5668782591819763, + "learning_rate": 8.3715543123732e-05, + "loss": 1.7584, + "step": 4966 + }, + { + "epoch": 0.2768519034613455, + "grad_norm": 0.586342990398407, + "learning_rate": 8.370896727718942e-05, + "loss": 1.7863, + "step": 4967 + }, + { + "epoch": 0.27690764171450866, + "grad_norm": 0.6017349362373352, + "learning_rate": 8.370239036159493e-05, + "loss": 1.8825, + "step": 4968 + }, + { + "epoch": 0.2769633799676718, + "grad_norm": 0.5821561813354492, + "learning_rate": 8.36958123771571e-05, + "loss": 1.9587, + "step": 4969 + }, + { + "epoch": 0.27701911822083497, + "grad_norm": 0.5764045119285583, + "learning_rate": 8.368923332408459e-05, + "loss": 1.8635, + "step": 4970 + }, + { + "epoch": 0.2770748564739981, + "grad_norm": 0.595043957233429, + "learning_rate": 8.368265320258598e-05, + "loss": 1.7843, + "step": 4971 + }, + { + "epoch": 0.27713059472716123, + "grad_norm": 0.5718355774879456, + "learning_rate": 8.367607201287002e-05, + "loss": 1.6231, + "step": 4972 + }, + { + "epoch": 0.2771863329803244, + "grad_norm": 0.5044475793838501, + "learning_rate": 8.366948975514539e-05, + "loss": 1.5014, + "step": 4973 + }, + { + "epoch": 0.27724207123348754, + "grad_norm": 0.5001023411750793, + "learning_rate": 8.366290642962087e-05, + "loss": 1.522, + "step": 4974 + }, + { + "epoch": 0.27729780948665067, + "grad_norm": 0.7615741491317749, + "learning_rate": 8.36563220365052e-05, + "loss": 1.5344, + "step": 4975 + }, + { + "epoch": 0.27735354773981385, + "grad_norm": 0.47964903712272644, + "learning_rate": 8.364973657600724e-05, + "loss": 1.4201, + "step": 4976 + }, + { + "epoch": 0.277409285992977, + "grad_norm": 0.5713698863983154, + "learning_rate": 8.364315004833583e-05, + "loss": 1.7664, + "step": 4977 + }, + { + "epoch": 0.2774650242461401, + "grad_norm": 0.5541187524795532, + "learning_rate": 8.363656245369984e-05, + "loss": 1.75, + "step": 4978 + }, + { + "epoch": 0.2775207624993033, + "grad_norm": 0.543755054473877, + "learning_rate": 8.362997379230822e-05, + "loss": 1.6432, + "step": 4979 + }, + { + "epoch": 0.2775765007524664, + "grad_norm": 0.5810009241104126, + "learning_rate": 8.36233840643699e-05, + "loss": 1.948, + "step": 4980 + }, + { + "epoch": 0.27763223900562956, + "grad_norm": 0.5693858861923218, + "learning_rate": 8.361679327009388e-05, + "loss": 1.8148, + "step": 4981 + }, + { + "epoch": 0.2776879772587927, + "grad_norm": 0.5942829251289368, + "learning_rate": 8.361020140968919e-05, + "loss": 1.9087, + "step": 4982 + }, + { + "epoch": 0.27774371551195587, + "grad_norm": 0.548213541507721, + "learning_rate": 8.360360848336484e-05, + "loss": 1.7628, + "step": 4983 + }, + { + "epoch": 0.277799453765119, + "grad_norm": 0.5708996057510376, + "learning_rate": 8.359701449132998e-05, + "loss": 1.8127, + "step": 4984 + }, + { + "epoch": 0.2778551920182821, + "grad_norm": 0.5608772039413452, + "learning_rate": 8.359041943379369e-05, + "loss": 1.5508, + "step": 4985 + }, + { + "epoch": 0.2779109302714453, + "grad_norm": 0.5337716937065125, + "learning_rate": 8.358382331096514e-05, + "loss": 1.6666, + "step": 4986 + }, + { + "epoch": 0.27796666852460844, + "grad_norm": 0.5663906335830688, + "learning_rate": 8.357722612305353e-05, + "loss": 1.8808, + "step": 4987 + }, + { + "epoch": 0.27802240677777157, + "grad_norm": 0.5678949952125549, + "learning_rate": 8.357062787026805e-05, + "loss": 1.7122, + "step": 4988 + }, + { + "epoch": 0.27807814503093475, + "grad_norm": 0.5173599720001221, + "learning_rate": 8.356402855281802e-05, + "loss": 1.6552, + "step": 4989 + }, + { + "epoch": 0.2781338832840979, + "grad_norm": 0.5319927334785461, + "learning_rate": 8.355742817091268e-05, + "loss": 1.4913, + "step": 4990 + }, + { + "epoch": 0.278189621537261, + "grad_norm": 0.5666325092315674, + "learning_rate": 8.355082672476136e-05, + "loss": 1.7334, + "step": 4991 + }, + { + "epoch": 0.27824535979042414, + "grad_norm": 0.6288278698921204, + "learning_rate": 8.354422421457346e-05, + "loss": 2.005, + "step": 4992 + }, + { + "epoch": 0.2783010980435873, + "grad_norm": 0.4918287992477417, + "learning_rate": 8.353762064055833e-05, + "loss": 1.6484, + "step": 4993 + }, + { + "epoch": 0.27835683629675045, + "grad_norm": 0.6033855676651001, + "learning_rate": 8.353101600292541e-05, + "loss": 1.7403, + "step": 4994 + }, + { + "epoch": 0.2784125745499136, + "grad_norm": 0.5309021472930908, + "learning_rate": 8.352441030188417e-05, + "loss": 1.6779, + "step": 4995 + }, + { + "epoch": 0.27846831280307677, + "grad_norm": 0.5141871571540833, + "learning_rate": 8.351780353764408e-05, + "loss": 1.7298, + "step": 4996 + }, + { + "epoch": 0.2785240510562399, + "grad_norm": 0.5200504064559937, + "learning_rate": 8.351119571041468e-05, + "loss": 1.594, + "step": 4997 + }, + { + "epoch": 0.278579789309403, + "grad_norm": 0.5325762033462524, + "learning_rate": 8.350458682040556e-05, + "loss": 1.7623, + "step": 4998 + }, + { + "epoch": 0.2786355275625662, + "grad_norm": 0.539318859577179, + "learning_rate": 8.349797686782627e-05, + "loss": 1.6779, + "step": 4999 + }, + { + "epoch": 0.27869126581572934, + "grad_norm": 0.5733089447021484, + "learning_rate": 8.349136585288648e-05, + "loss": 1.8159, + "step": 5000 + }, + { + "epoch": 0.27874700406889247, + "grad_norm": 0.5516615509986877, + "learning_rate": 8.348475377579583e-05, + "loss": 1.6049, + "step": 5001 + }, + { + "epoch": 0.27880274232205565, + "grad_norm": 0.5449507236480713, + "learning_rate": 8.3478140636764e-05, + "loss": 1.661, + "step": 5002 + }, + { + "epoch": 0.2788584805752188, + "grad_norm": 0.5257706642150879, + "learning_rate": 8.347152643600076e-05, + "loss": 1.6633, + "step": 5003 + }, + { + "epoch": 0.2789142188283819, + "grad_norm": 0.5481857657432556, + "learning_rate": 8.346491117371584e-05, + "loss": 1.7599, + "step": 5004 + }, + { + "epoch": 0.27896995708154504, + "grad_norm": 0.5461267232894897, + "learning_rate": 8.345829485011906e-05, + "loss": 1.6645, + "step": 5005 + }, + { + "epoch": 0.2790256953347082, + "grad_norm": 0.5450317859649658, + "learning_rate": 8.345167746542024e-05, + "loss": 1.7965, + "step": 5006 + }, + { + "epoch": 0.27908143358787135, + "grad_norm": 0.5598206520080566, + "learning_rate": 8.344505901982926e-05, + "loss": 1.8171, + "step": 5007 + }, + { + "epoch": 0.2791371718410345, + "grad_norm": 0.5036829113960266, + "learning_rate": 8.343843951355599e-05, + "loss": 1.5853, + "step": 5008 + }, + { + "epoch": 0.27919291009419767, + "grad_norm": 0.5530052185058594, + "learning_rate": 8.34318189468104e-05, + "loss": 1.8362, + "step": 5009 + }, + { + "epoch": 0.2792486483473608, + "grad_norm": 0.5920783877372742, + "learning_rate": 8.34251973198024e-05, + "loss": 1.7712, + "step": 5010 + }, + { + "epoch": 0.2793043866005239, + "grad_norm": 0.5592779517173767, + "learning_rate": 8.341857463274204e-05, + "loss": 1.729, + "step": 5011 + }, + { + "epoch": 0.2793601248536871, + "grad_norm": 0.5464910864830017, + "learning_rate": 8.341195088583934e-05, + "loss": 1.9075, + "step": 5012 + }, + { + "epoch": 0.27941586310685024, + "grad_norm": 0.5421869158744812, + "learning_rate": 8.340532607930435e-05, + "loss": 1.6845, + "step": 5013 + }, + { + "epoch": 0.27947160136001337, + "grad_norm": 0.6448494791984558, + "learning_rate": 8.339870021334721e-05, + "loss": 1.677, + "step": 5014 + }, + { + "epoch": 0.2795273396131765, + "grad_norm": 0.551950991153717, + "learning_rate": 8.339207328817801e-05, + "loss": 1.7604, + "step": 5015 + }, + { + "epoch": 0.2795830778663397, + "grad_norm": 0.5297108292579651, + "learning_rate": 8.338544530400694e-05, + "loss": 1.8327, + "step": 5016 + }, + { + "epoch": 0.2796388161195028, + "grad_norm": 0.5589694976806641, + "learning_rate": 8.337881626104418e-05, + "loss": 1.8363, + "step": 5017 + }, + { + "epoch": 0.27969455437266594, + "grad_norm": 0.5295442342758179, + "learning_rate": 8.337218615949999e-05, + "loss": 1.5949, + "step": 5018 + }, + { + "epoch": 0.2797502926258291, + "grad_norm": 0.5680721998214722, + "learning_rate": 8.336555499958463e-05, + "loss": 1.7101, + "step": 5019 + }, + { + "epoch": 0.27980603087899225, + "grad_norm": 0.5222816467285156, + "learning_rate": 8.33589227815084e-05, + "loss": 1.6419, + "step": 5020 + }, + { + "epoch": 0.2798617691321554, + "grad_norm": 0.5572875142097473, + "learning_rate": 8.335228950548164e-05, + "loss": 1.5752, + "step": 5021 + }, + { + "epoch": 0.27991750738531856, + "grad_norm": 0.5234338641166687, + "learning_rate": 8.334565517171471e-05, + "loss": 1.608, + "step": 5022 + }, + { + "epoch": 0.2799732456384817, + "grad_norm": 0.5773409008979797, + "learning_rate": 8.333901978041801e-05, + "loss": 1.8295, + "step": 5023 + }, + { + "epoch": 0.2800289838916448, + "grad_norm": 0.6236357092857361, + "learning_rate": 8.3332383331802e-05, + "loss": 2.1082, + "step": 5024 + }, + { + "epoch": 0.280084722144808, + "grad_norm": 0.5226585865020752, + "learning_rate": 8.332574582607712e-05, + "loss": 1.5637, + "step": 5025 + }, + { + "epoch": 0.28014046039797114, + "grad_norm": 0.5552464723587036, + "learning_rate": 8.331910726345389e-05, + "loss": 1.565, + "step": 5026 + }, + { + "epoch": 0.28019619865113427, + "grad_norm": 0.5889436602592468, + "learning_rate": 8.331246764414282e-05, + "loss": 1.6853, + "step": 5027 + }, + { + "epoch": 0.2802519369042974, + "grad_norm": 0.5935594439506531, + "learning_rate": 8.330582696835453e-05, + "loss": 1.8281, + "step": 5028 + }, + { + "epoch": 0.2803076751574606, + "grad_norm": 0.5328096747398376, + "learning_rate": 8.329918523629958e-05, + "loss": 1.5658, + "step": 5029 + }, + { + "epoch": 0.2803634134106237, + "grad_norm": 0.5282544493675232, + "learning_rate": 8.329254244818862e-05, + "loss": 1.5369, + "step": 5030 + }, + { + "epoch": 0.28041915166378684, + "grad_norm": 0.5771158337593079, + "learning_rate": 8.328589860423234e-05, + "loss": 1.718, + "step": 5031 + }, + { + "epoch": 0.28047488991695, + "grad_norm": 0.5074672698974609, + "learning_rate": 8.327925370464142e-05, + "loss": 1.5096, + "step": 5032 + }, + { + "epoch": 0.28053062817011315, + "grad_norm": 0.5818241834640503, + "learning_rate": 8.32726077496266e-05, + "loss": 1.8082, + "step": 5033 + }, + { + "epoch": 0.2805863664232763, + "grad_norm": 0.5617592930793762, + "learning_rate": 8.326596073939865e-05, + "loss": 1.885, + "step": 5034 + }, + { + "epoch": 0.28064210467643946, + "grad_norm": 0.5317988991737366, + "learning_rate": 8.325931267416837e-05, + "loss": 1.6933, + "step": 5035 + }, + { + "epoch": 0.2806978429296026, + "grad_norm": 0.5429521799087524, + "learning_rate": 8.325266355414663e-05, + "loss": 1.7869, + "step": 5036 + }, + { + "epoch": 0.2807535811827657, + "grad_norm": 0.5846121311187744, + "learning_rate": 8.324601337954427e-05, + "loss": 1.8213, + "step": 5037 + }, + { + "epoch": 0.28080931943592885, + "grad_norm": 0.5202860236167908, + "learning_rate": 8.323936215057219e-05, + "loss": 1.5685, + "step": 5038 + }, + { + "epoch": 0.28086505768909203, + "grad_norm": 0.5208321213722229, + "learning_rate": 8.323270986744136e-05, + "loss": 1.6801, + "step": 5039 + }, + { + "epoch": 0.28092079594225516, + "grad_norm": 0.5601228475570679, + "learning_rate": 8.322605653036273e-05, + "loss": 1.7527, + "step": 5040 + }, + { + "epoch": 0.2809765341954183, + "grad_norm": 0.5703938603401184, + "learning_rate": 8.32194021395473e-05, + "loss": 1.7583, + "step": 5041 + }, + { + "epoch": 0.2810322724485815, + "grad_norm": 0.5135952234268188, + "learning_rate": 8.321274669520613e-05, + "loss": 1.6603, + "step": 5042 + }, + { + "epoch": 0.2810880107017446, + "grad_norm": 0.5345764756202698, + "learning_rate": 8.320609019755025e-05, + "loss": 1.8041, + "step": 5043 + }, + { + "epoch": 0.28114374895490774, + "grad_norm": 0.5866489410400391, + "learning_rate": 8.319943264679082e-05, + "loss": 1.8187, + "step": 5044 + }, + { + "epoch": 0.2811994872080709, + "grad_norm": 0.5317565202713013, + "learning_rate": 8.319277404313895e-05, + "loss": 1.627, + "step": 5045 + }, + { + "epoch": 0.28125522546123405, + "grad_norm": 0.5532716512680054, + "learning_rate": 8.318611438680581e-05, + "loss": 1.7922, + "step": 5046 + }, + { + "epoch": 0.2813109637143972, + "grad_norm": 0.5880955457687378, + "learning_rate": 8.317945367800262e-05, + "loss": 1.9276, + "step": 5047 + }, + { + "epoch": 0.28136670196756036, + "grad_norm": 0.5237969160079956, + "learning_rate": 8.31727919169406e-05, + "loss": 1.6415, + "step": 5048 + }, + { + "epoch": 0.2814224402207235, + "grad_norm": 0.5675956010818481, + "learning_rate": 8.316612910383104e-05, + "loss": 1.7371, + "step": 5049 + }, + { + "epoch": 0.2814781784738866, + "grad_norm": 0.5321084260940552, + "learning_rate": 8.315946523888523e-05, + "loss": 1.5045, + "step": 5050 + }, + { + "epoch": 0.28153391672704975, + "grad_norm": 0.5198732614517212, + "learning_rate": 8.31528003223145e-05, + "loss": 1.7094, + "step": 5051 + }, + { + "epoch": 0.28158965498021293, + "grad_norm": 0.5548423528671265, + "learning_rate": 8.314613435433025e-05, + "loss": 1.7824, + "step": 5052 + }, + { + "epoch": 0.28164539323337606, + "grad_norm": 0.5975722074508667, + "learning_rate": 8.313946733514388e-05, + "loss": 1.6823, + "step": 5053 + }, + { + "epoch": 0.2817011314865392, + "grad_norm": 0.5505688190460205, + "learning_rate": 8.313279926496682e-05, + "loss": 1.6891, + "step": 5054 + }, + { + "epoch": 0.2817568697397024, + "grad_norm": 0.535331666469574, + "learning_rate": 8.312613014401053e-05, + "loss": 1.6879, + "step": 5055 + }, + { + "epoch": 0.2818126079928655, + "grad_norm": 0.5429748296737671, + "learning_rate": 8.311945997248656e-05, + "loss": 1.7741, + "step": 5056 + }, + { + "epoch": 0.28186834624602863, + "grad_norm": 0.5404984354972839, + "learning_rate": 8.31127887506064e-05, + "loss": 1.5888, + "step": 5057 + }, + { + "epoch": 0.2819240844991918, + "grad_norm": 0.6144102811813354, + "learning_rate": 8.310611647858164e-05, + "loss": 1.8173, + "step": 5058 + }, + { + "epoch": 0.28197982275235495, + "grad_norm": 0.5709677934646606, + "learning_rate": 8.30994431566239e-05, + "loss": 1.6492, + "step": 5059 + }, + { + "epoch": 0.2820355610055181, + "grad_norm": 0.5943745374679565, + "learning_rate": 8.309276878494481e-05, + "loss": 1.9265, + "step": 5060 + }, + { + "epoch": 0.28209129925868126, + "grad_norm": 0.5663633942604065, + "learning_rate": 8.308609336375601e-05, + "loss": 1.5966, + "step": 5061 + }, + { + "epoch": 0.2821470375118444, + "grad_norm": 0.5235463380813599, + "learning_rate": 8.307941689326926e-05, + "loss": 1.6598, + "step": 5062 + }, + { + "epoch": 0.2822027757650075, + "grad_norm": 0.5473840832710266, + "learning_rate": 8.307273937369627e-05, + "loss": 1.3741, + "step": 5063 + }, + { + "epoch": 0.28225851401817065, + "grad_norm": 0.6380063891410828, + "learning_rate": 8.30660608052488e-05, + "loss": 1.7855, + "step": 5064 + }, + { + "epoch": 0.28231425227133383, + "grad_norm": 0.5315070748329163, + "learning_rate": 8.305938118813868e-05, + "loss": 1.6285, + "step": 5065 + }, + { + "epoch": 0.28236999052449696, + "grad_norm": 0.571528971195221, + "learning_rate": 8.305270052257773e-05, + "loss": 1.8315, + "step": 5066 + }, + { + "epoch": 0.2824257287776601, + "grad_norm": 0.5939456820487976, + "learning_rate": 8.304601880877784e-05, + "loss": 1.8598, + "step": 5067 + }, + { + "epoch": 0.2824814670308233, + "grad_norm": 0.5018705129623413, + "learning_rate": 8.30393360469509e-05, + "loss": 1.5472, + "step": 5068 + }, + { + "epoch": 0.2825372052839864, + "grad_norm": 0.5844521522521973, + "learning_rate": 8.303265223730885e-05, + "loss": 1.8186, + "step": 5069 + }, + { + "epoch": 0.28259294353714953, + "grad_norm": 0.5360279083251953, + "learning_rate": 8.302596738006367e-05, + "loss": 1.7101, + "step": 5070 + }, + { + "epoch": 0.2826486817903127, + "grad_norm": 0.5614787340164185, + "learning_rate": 8.301928147542736e-05, + "loss": 1.6207, + "step": 5071 + }, + { + "epoch": 0.28270442004347585, + "grad_norm": 0.5616874098777771, + "learning_rate": 8.301259452361197e-05, + "loss": 1.7829, + "step": 5072 + }, + { + "epoch": 0.282760158296639, + "grad_norm": 0.6129429340362549, + "learning_rate": 8.300590652482954e-05, + "loss": 1.844, + "step": 5073 + }, + { + "epoch": 0.2828158965498021, + "grad_norm": 0.5966079831123352, + "learning_rate": 8.29992174792922e-05, + "loss": 1.9242, + "step": 5074 + }, + { + "epoch": 0.2828716348029653, + "grad_norm": 0.5461622476577759, + "learning_rate": 8.299252738721206e-05, + "loss": 1.7337, + "step": 5075 + }, + { + "epoch": 0.2829273730561284, + "grad_norm": 0.5274501442909241, + "learning_rate": 8.298583624880135e-05, + "loss": 1.6531, + "step": 5076 + }, + { + "epoch": 0.28298311130929155, + "grad_norm": 0.6280329823493958, + "learning_rate": 8.29791440642722e-05, + "loss": 1.6198, + "step": 5077 + }, + { + "epoch": 0.28303884956245473, + "grad_norm": 0.5429005026817322, + "learning_rate": 8.297245083383689e-05, + "loss": 1.7574, + "step": 5078 + }, + { + "epoch": 0.28309458781561786, + "grad_norm": 0.586188018321991, + "learning_rate": 8.296575655770768e-05, + "loss": 1.7325, + "step": 5079 + }, + { + "epoch": 0.283150326068781, + "grad_norm": 0.48814016580581665, + "learning_rate": 8.295906123609688e-05, + "loss": 1.6964, + "step": 5080 + }, + { + "epoch": 0.2832060643219442, + "grad_norm": 0.518273651599884, + "learning_rate": 8.295236486921685e-05, + "loss": 1.6128, + "step": 5081 + }, + { + "epoch": 0.2832618025751073, + "grad_norm": 0.5701366066932678, + "learning_rate": 8.29456674572799e-05, + "loss": 1.8898, + "step": 5082 + }, + { + "epoch": 0.28331754082827043, + "grad_norm": 0.522463858127594, + "learning_rate": 8.293896900049846e-05, + "loss": 1.513, + "step": 5083 + }, + { + "epoch": 0.2833732790814336, + "grad_norm": 0.5641170144081116, + "learning_rate": 8.293226949908499e-05, + "loss": 1.658, + "step": 5084 + }, + { + "epoch": 0.28342901733459674, + "grad_norm": 0.5498567223548889, + "learning_rate": 8.292556895325194e-05, + "loss": 1.6148, + "step": 5085 + }, + { + "epoch": 0.2834847555877599, + "grad_norm": 0.5941603183746338, + "learning_rate": 8.29188673632118e-05, + "loss": 1.7469, + "step": 5086 + }, + { + "epoch": 0.283540493840923, + "grad_norm": 0.5746224522590637, + "learning_rate": 8.291216472917714e-05, + "loss": 1.6819, + "step": 5087 + }, + { + "epoch": 0.2835962320940862, + "grad_norm": 0.6701369285583496, + "learning_rate": 8.290546105136048e-05, + "loss": 1.3384, + "step": 5088 + }, + { + "epoch": 0.2836519703472493, + "grad_norm": 0.5807752013206482, + "learning_rate": 8.289875632997446e-05, + "loss": 1.6534, + "step": 5089 + }, + { + "epoch": 0.28370770860041244, + "grad_norm": 0.5432621240615845, + "learning_rate": 8.289205056523168e-05, + "loss": 1.6963, + "step": 5090 + }, + { + "epoch": 0.28376344685357563, + "grad_norm": 0.5509108901023865, + "learning_rate": 8.288534375734486e-05, + "loss": 1.6027, + "step": 5091 + }, + { + "epoch": 0.28381918510673876, + "grad_norm": 0.5456513166427612, + "learning_rate": 8.287863590652666e-05, + "loss": 1.6362, + "step": 5092 + }, + { + "epoch": 0.2838749233599019, + "grad_norm": 0.5441727042198181, + "learning_rate": 8.287192701298982e-05, + "loss": 1.5781, + "step": 5093 + }, + { + "epoch": 0.28393066161306507, + "grad_norm": 0.5558503866195679, + "learning_rate": 8.286521707694712e-05, + "loss": 1.8077, + "step": 5094 + }, + { + "epoch": 0.2839863998662282, + "grad_norm": 0.5933700799942017, + "learning_rate": 8.285850609861134e-05, + "loss": 1.8407, + "step": 5095 + }, + { + "epoch": 0.28404213811939133, + "grad_norm": 0.557685375213623, + "learning_rate": 8.285179407819534e-05, + "loss": 1.579, + "step": 5096 + }, + { + "epoch": 0.28409787637255446, + "grad_norm": 0.5183169841766357, + "learning_rate": 8.284508101591198e-05, + "loss": 1.3955, + "step": 5097 + }, + { + "epoch": 0.28415361462571764, + "grad_norm": 0.5807473659515381, + "learning_rate": 8.283836691197413e-05, + "loss": 1.8429, + "step": 5098 + }, + { + "epoch": 0.28420935287888077, + "grad_norm": 0.6236990690231323, + "learning_rate": 8.283165176659474e-05, + "loss": 1.8281, + "step": 5099 + }, + { + "epoch": 0.2842650911320439, + "grad_norm": 0.5581399202346802, + "learning_rate": 8.282493557998678e-05, + "loss": 1.764, + "step": 5100 + }, + { + "epoch": 0.2843208293852071, + "grad_norm": 0.5508102774620056, + "learning_rate": 8.281821835236325e-05, + "loss": 1.8694, + "step": 5101 + }, + { + "epoch": 0.2843765676383702, + "grad_norm": 0.6012663841247559, + "learning_rate": 8.281150008393718e-05, + "loss": 1.8829, + "step": 5102 + }, + { + "epoch": 0.28443230589153334, + "grad_norm": 0.5453019738197327, + "learning_rate": 8.280478077492163e-05, + "loss": 1.8996, + "step": 5103 + }, + { + "epoch": 0.28448804414469653, + "grad_norm": 0.5334420204162598, + "learning_rate": 8.27980604255297e-05, + "loss": 1.7342, + "step": 5104 + }, + { + "epoch": 0.28454378239785966, + "grad_norm": 0.5454635620117188, + "learning_rate": 8.279133903597451e-05, + "loss": 1.7496, + "step": 5105 + }, + { + "epoch": 0.2845995206510228, + "grad_norm": 0.5557402968406677, + "learning_rate": 8.278461660646925e-05, + "loss": 1.63, + "step": 5106 + }, + { + "epoch": 0.28465525890418597, + "grad_norm": 0.5542622208595276, + "learning_rate": 8.27778931372271e-05, + "loss": 1.6639, + "step": 5107 + }, + { + "epoch": 0.2847109971573491, + "grad_norm": 0.565591037273407, + "learning_rate": 8.277116862846126e-05, + "loss": 1.9303, + "step": 5108 + }, + { + "epoch": 0.28476673541051223, + "grad_norm": 0.6099279522895813, + "learning_rate": 8.276444308038504e-05, + "loss": 1.7833, + "step": 5109 + }, + { + "epoch": 0.28482247366367536, + "grad_norm": 0.6192046999931335, + "learning_rate": 8.27577164932117e-05, + "loss": 1.9167, + "step": 5110 + }, + { + "epoch": 0.28487821191683854, + "grad_norm": 0.5659559965133667, + "learning_rate": 8.275098886715462e-05, + "loss": 1.7716, + "step": 5111 + }, + { + "epoch": 0.28493395017000167, + "grad_norm": 0.6038410067558289, + "learning_rate": 8.274426020242709e-05, + "loss": 1.9078, + "step": 5112 + }, + { + "epoch": 0.2849896884231648, + "grad_norm": 0.5924156904220581, + "learning_rate": 8.273753049924256e-05, + "loss": 1.7014, + "step": 5113 + }, + { + "epoch": 0.285045426676328, + "grad_norm": 0.5436737537384033, + "learning_rate": 8.273079975781442e-05, + "loss": 1.6482, + "step": 5114 + }, + { + "epoch": 0.2851011649294911, + "grad_norm": 0.5460022687911987, + "learning_rate": 8.272406797835614e-05, + "loss": 1.7304, + "step": 5115 + }, + { + "epoch": 0.28515690318265424, + "grad_norm": 0.5954405069351196, + "learning_rate": 8.271733516108125e-05, + "loss": 1.6698, + "step": 5116 + }, + { + "epoch": 0.2852126414358174, + "grad_norm": 0.638888418674469, + "learning_rate": 8.27106013062032e-05, + "loss": 2.0553, + "step": 5117 + }, + { + "epoch": 0.28526837968898056, + "grad_norm": 0.5477131605148315, + "learning_rate": 8.270386641393564e-05, + "loss": 1.5031, + "step": 5118 + }, + { + "epoch": 0.2853241179421437, + "grad_norm": 0.5998544692993164, + "learning_rate": 8.269713048449208e-05, + "loss": 1.9087, + "step": 5119 + }, + { + "epoch": 0.2853798561953068, + "grad_norm": 0.5584544539451599, + "learning_rate": 8.26903935180862e-05, + "loss": 1.8125, + "step": 5120 + }, + { + "epoch": 0.28543559444847, + "grad_norm": 0.5390369892120361, + "learning_rate": 8.268365551493161e-05, + "loss": 1.6459, + "step": 5121 + }, + { + "epoch": 0.2854913327016331, + "grad_norm": 0.5171942710876465, + "learning_rate": 8.267691647524206e-05, + "loss": 1.6801, + "step": 5122 + }, + { + "epoch": 0.28554707095479626, + "grad_norm": 0.4894436299800873, + "learning_rate": 8.26701763992312e-05, + "loss": 1.4172, + "step": 5123 + }, + { + "epoch": 0.28560280920795944, + "grad_norm": 0.5318630337715149, + "learning_rate": 8.266343528711285e-05, + "loss": 1.6956, + "step": 5124 + }, + { + "epoch": 0.28565854746112257, + "grad_norm": 0.513378918170929, + "learning_rate": 8.265669313910077e-05, + "loss": 1.5235, + "step": 5125 + }, + { + "epoch": 0.2857142857142857, + "grad_norm": 0.6027741432189941, + "learning_rate": 8.264994995540878e-05, + "loss": 1.9089, + "step": 5126 + }, + { + "epoch": 0.2857700239674489, + "grad_norm": 0.5300361514091492, + "learning_rate": 8.264320573625075e-05, + "loss": 1.6013, + "step": 5127 + }, + { + "epoch": 0.285825762220612, + "grad_norm": 0.5484519600868225, + "learning_rate": 8.263646048184055e-05, + "loss": 1.6596, + "step": 5128 + }, + { + "epoch": 0.28588150047377514, + "grad_norm": 0.6186813116073608, + "learning_rate": 8.26297141923921e-05, + "loss": 1.7786, + "step": 5129 + }, + { + "epoch": 0.2859372387269383, + "grad_norm": 0.5475611686706543, + "learning_rate": 8.262296686811936e-05, + "loss": 1.6151, + "step": 5130 + }, + { + "epoch": 0.28599297698010145, + "grad_norm": 0.612417995929718, + "learning_rate": 8.261621850923634e-05, + "loss": 1.587, + "step": 5131 + }, + { + "epoch": 0.2860487152332646, + "grad_norm": 0.5619268417358398, + "learning_rate": 8.260946911595701e-05, + "loss": 1.6915, + "step": 5132 + }, + { + "epoch": 0.2861044534864277, + "grad_norm": 0.5510770678520203, + "learning_rate": 8.260271868849547e-05, + "loss": 1.9188, + "step": 5133 + }, + { + "epoch": 0.2861601917395909, + "grad_norm": 0.5569331049919128, + "learning_rate": 8.259596722706575e-05, + "loss": 1.7657, + "step": 5134 + }, + { + "epoch": 0.286215929992754, + "grad_norm": 0.48364466428756714, + "learning_rate": 8.258921473188202e-05, + "loss": 1.3247, + "step": 5135 + }, + { + "epoch": 0.28627166824591715, + "grad_norm": 0.5114015936851501, + "learning_rate": 8.25824612031584e-05, + "loss": 1.6025, + "step": 5136 + }, + { + "epoch": 0.28632740649908034, + "grad_norm": 0.5254806876182556, + "learning_rate": 8.257570664110907e-05, + "loss": 1.7264, + "step": 5137 + }, + { + "epoch": 0.28638314475224347, + "grad_norm": 0.5384583473205566, + "learning_rate": 8.256895104594828e-05, + "loss": 1.802, + "step": 5138 + }, + { + "epoch": 0.2864388830054066, + "grad_norm": 0.5924034118652344, + "learning_rate": 8.256219441789022e-05, + "loss": 1.9493, + "step": 5139 + }, + { + "epoch": 0.2864946212585698, + "grad_norm": 0.5453627705574036, + "learning_rate": 8.255543675714923e-05, + "loss": 1.5655, + "step": 5140 + }, + { + "epoch": 0.2865503595117329, + "grad_norm": 0.535179853439331, + "learning_rate": 8.254867806393957e-05, + "loss": 1.5492, + "step": 5141 + }, + { + "epoch": 0.28660609776489604, + "grad_norm": 0.5418823957443237, + "learning_rate": 8.254191833847564e-05, + "loss": 1.7343, + "step": 5142 + }, + { + "epoch": 0.28666183601805917, + "grad_norm": 0.5330826044082642, + "learning_rate": 8.253515758097179e-05, + "loss": 1.6551, + "step": 5143 + }, + { + "epoch": 0.28671757427122235, + "grad_norm": 0.6033239960670471, + "learning_rate": 8.252839579164243e-05, + "loss": 1.8227, + "step": 5144 + }, + { + "epoch": 0.2867733125243855, + "grad_norm": 0.5882185697555542, + "learning_rate": 8.252163297070201e-05, + "loss": 1.9731, + "step": 5145 + }, + { + "epoch": 0.2868290507775486, + "grad_norm": 0.537185788154602, + "learning_rate": 8.251486911836501e-05, + "loss": 1.5992, + "step": 5146 + }, + { + "epoch": 0.2868847890307118, + "grad_norm": 0.5307870507240295, + "learning_rate": 8.250810423484592e-05, + "loss": 1.5641, + "step": 5147 + }, + { + "epoch": 0.2869405272838749, + "grad_norm": 0.5483027696609497, + "learning_rate": 8.25013383203593e-05, + "loss": 1.759, + "step": 5148 + }, + { + "epoch": 0.28699626553703805, + "grad_norm": 0.5503141283988953, + "learning_rate": 8.249457137511976e-05, + "loss": 1.7229, + "step": 5149 + }, + { + "epoch": 0.28705200379020124, + "grad_norm": 0.5450831651687622, + "learning_rate": 8.248780339934183e-05, + "loss": 1.6758, + "step": 5150 + }, + { + "epoch": 0.28710774204336437, + "grad_norm": 0.5555149912834167, + "learning_rate": 8.248103439324022e-05, + "loss": 1.7173, + "step": 5151 + }, + { + "epoch": 0.2871634802965275, + "grad_norm": 0.5960267186164856, + "learning_rate": 8.247426435702956e-05, + "loss": 1.8327, + "step": 5152 + }, + { + "epoch": 0.2872192185496907, + "grad_norm": 0.5497944951057434, + "learning_rate": 8.246749329092458e-05, + "loss": 1.6373, + "step": 5153 + }, + { + "epoch": 0.2872749568028538, + "grad_norm": 0.6035077571868896, + "learning_rate": 8.246072119514e-05, + "loss": 2.0384, + "step": 5154 + }, + { + "epoch": 0.28733069505601694, + "grad_norm": 0.5685641765594482, + "learning_rate": 8.245394806989062e-05, + "loss": 1.9093, + "step": 5155 + }, + { + "epoch": 0.28738643330918007, + "grad_norm": 0.5542479753494263, + "learning_rate": 8.244717391539124e-05, + "loss": 1.6794, + "step": 5156 + }, + { + "epoch": 0.28744217156234325, + "grad_norm": 0.5434539318084717, + "learning_rate": 8.244039873185664e-05, + "loss": 1.6624, + "step": 5157 + }, + { + "epoch": 0.2874979098155064, + "grad_norm": 0.5240741968154907, + "learning_rate": 8.243362251950177e-05, + "loss": 1.7119, + "step": 5158 + }, + { + "epoch": 0.2875536480686695, + "grad_norm": 0.5400795340538025, + "learning_rate": 8.242684527854148e-05, + "loss": 1.7379, + "step": 5159 + }, + { + "epoch": 0.2876093863218327, + "grad_norm": 0.5450997352600098, + "learning_rate": 8.242006700919072e-05, + "loss": 1.648, + "step": 5160 + }, + { + "epoch": 0.2876651245749958, + "grad_norm": 0.5497955679893494, + "learning_rate": 8.241328771166446e-05, + "loss": 1.8969, + "step": 5161 + }, + { + "epoch": 0.28772086282815895, + "grad_norm": 0.556607186794281, + "learning_rate": 8.24065073861777e-05, + "loss": 1.7941, + "step": 5162 + }, + { + "epoch": 0.28777660108132214, + "grad_norm": 0.5775546431541443, + "learning_rate": 8.239972603294546e-05, + "loss": 1.7996, + "step": 5163 + }, + { + "epoch": 0.28783233933448527, + "grad_norm": 0.5500494241714478, + "learning_rate": 8.239294365218282e-05, + "loss": 1.486, + "step": 5164 + }, + { + "epoch": 0.2878880775876484, + "grad_norm": 0.5263432860374451, + "learning_rate": 8.238616024410486e-05, + "loss": 1.8011, + "step": 5165 + }, + { + "epoch": 0.2879438158408115, + "grad_norm": 0.580796480178833, + "learning_rate": 8.237937580892674e-05, + "loss": 1.7308, + "step": 5166 + }, + { + "epoch": 0.2879995540939747, + "grad_norm": 0.5561580657958984, + "learning_rate": 8.237259034686359e-05, + "loss": 1.7732, + "step": 5167 + }, + { + "epoch": 0.28805529234713784, + "grad_norm": 0.5456521511077881, + "learning_rate": 8.236580385813062e-05, + "loss": 1.6932, + "step": 5168 + }, + { + "epoch": 0.28811103060030097, + "grad_norm": 0.5676544904708862, + "learning_rate": 8.235901634294306e-05, + "loss": 1.8033, + "step": 5169 + }, + { + "epoch": 0.28816676885346415, + "grad_norm": 0.5046932697296143, + "learning_rate": 8.235222780151616e-05, + "loss": 1.5637, + "step": 5170 + }, + { + "epoch": 0.2882225071066273, + "grad_norm": 0.5261063575744629, + "learning_rate": 8.234543823406525e-05, + "loss": 1.5763, + "step": 5171 + }, + { + "epoch": 0.2882782453597904, + "grad_norm": 0.5619118809700012, + "learning_rate": 8.23386476408056e-05, + "loss": 1.7251, + "step": 5172 + }, + { + "epoch": 0.2883339836129536, + "grad_norm": 0.5556089282035828, + "learning_rate": 8.233185602195259e-05, + "loss": 1.7168, + "step": 5173 + }, + { + "epoch": 0.2883897218661167, + "grad_norm": 0.5449663400650024, + "learning_rate": 8.232506337772163e-05, + "loss": 1.7282, + "step": 5174 + }, + { + "epoch": 0.28844546011927985, + "grad_norm": 0.5821020007133484, + "learning_rate": 8.231826970832812e-05, + "loss": 2.0267, + "step": 5175 + }, + { + "epoch": 0.28850119837244304, + "grad_norm": 0.5104268193244934, + "learning_rate": 8.231147501398753e-05, + "loss": 1.4387, + "step": 5176 + }, + { + "epoch": 0.28855693662560616, + "grad_norm": 0.548219621181488, + "learning_rate": 8.230467929491534e-05, + "loss": 1.7042, + "step": 5177 + }, + { + "epoch": 0.2886126748787693, + "grad_norm": 0.5711565017700195, + "learning_rate": 8.229788255132706e-05, + "loss": 1.6752, + "step": 5178 + }, + { + "epoch": 0.2886684131319324, + "grad_norm": 0.526942789554596, + "learning_rate": 8.229108478343827e-05, + "loss": 1.5905, + "step": 5179 + }, + { + "epoch": 0.2887241513850956, + "grad_norm": 0.5535737872123718, + "learning_rate": 8.228428599146453e-05, + "loss": 1.6857, + "step": 5180 + }, + { + "epoch": 0.28877988963825874, + "grad_norm": 0.5093039870262146, + "learning_rate": 8.227748617562147e-05, + "loss": 1.6489, + "step": 5181 + }, + { + "epoch": 0.28883562789142186, + "grad_norm": 0.5642322301864624, + "learning_rate": 8.227068533612475e-05, + "loss": 1.8709, + "step": 5182 + }, + { + "epoch": 0.28889136614458505, + "grad_norm": 0.5547685623168945, + "learning_rate": 8.226388347319004e-05, + "loss": 1.7088, + "step": 5183 + }, + { + "epoch": 0.2889471043977482, + "grad_norm": 0.5316441059112549, + "learning_rate": 8.225708058703305e-05, + "loss": 1.59, + "step": 5184 + }, + { + "epoch": 0.2890028426509113, + "grad_norm": 0.5305221080780029, + "learning_rate": 8.225027667786955e-05, + "loss": 1.4301, + "step": 5185 + }, + { + "epoch": 0.2890585809040745, + "grad_norm": 0.5498524904251099, + "learning_rate": 8.224347174591529e-05, + "loss": 1.533, + "step": 5186 + }, + { + "epoch": 0.2891143191572376, + "grad_norm": 0.5519589781761169, + "learning_rate": 8.22366657913861e-05, + "loss": 1.7171, + "step": 5187 + }, + { + "epoch": 0.28917005741040075, + "grad_norm": 0.5893858075141907, + "learning_rate": 8.222985881449783e-05, + "loss": 1.7751, + "step": 5188 + }, + { + "epoch": 0.2892257956635639, + "grad_norm": 0.5334852933883667, + "learning_rate": 8.222305081546635e-05, + "loss": 1.6905, + "step": 5189 + }, + { + "epoch": 0.28928153391672706, + "grad_norm": 0.5692505836486816, + "learning_rate": 8.221624179450757e-05, + "loss": 1.6461, + "step": 5190 + }, + { + "epoch": 0.2893372721698902, + "grad_norm": 0.5988993644714355, + "learning_rate": 8.220943175183743e-05, + "loss": 2.0131, + "step": 5191 + }, + { + "epoch": 0.2893930104230533, + "grad_norm": 0.6873819231987, + "learning_rate": 8.220262068767191e-05, + "loss": 1.977, + "step": 5192 + }, + { + "epoch": 0.2894487486762165, + "grad_norm": 0.5408362746238708, + "learning_rate": 8.219580860222701e-05, + "loss": 1.6866, + "step": 5193 + }, + { + "epoch": 0.28950448692937963, + "grad_norm": 0.8928006291389465, + "learning_rate": 8.218899549571878e-05, + "loss": 1.6639, + "step": 5194 + }, + { + "epoch": 0.28956022518254276, + "grad_norm": 0.5256812572479248, + "learning_rate": 8.218218136836331e-05, + "loss": 1.435, + "step": 5195 + }, + { + "epoch": 0.28961596343570595, + "grad_norm": 0.5350750684738159, + "learning_rate": 8.217536622037667e-05, + "loss": 1.6317, + "step": 5196 + }, + { + "epoch": 0.2896717016888691, + "grad_norm": 0.5534375309944153, + "learning_rate": 8.2168550051975e-05, + "loss": 1.7473, + "step": 5197 + }, + { + "epoch": 0.2897274399420322, + "grad_norm": 0.5433312058448792, + "learning_rate": 8.216173286337448e-05, + "loss": 1.8094, + "step": 5198 + }, + { + "epoch": 0.2897831781951954, + "grad_norm": 0.5386417508125305, + "learning_rate": 8.215491465479133e-05, + "loss": 1.5757, + "step": 5199 + }, + { + "epoch": 0.2898389164483585, + "grad_norm": 0.6519530415534973, + "learning_rate": 8.214809542644173e-05, + "loss": 1.9404, + "step": 5200 + }, + { + "epoch": 0.28989465470152165, + "grad_norm": 0.6092321872711182, + "learning_rate": 8.214127517854199e-05, + "loss": 1.8751, + "step": 5201 + }, + { + "epoch": 0.2899503929546848, + "grad_norm": 0.5904344320297241, + "learning_rate": 8.213445391130841e-05, + "loss": 1.8278, + "step": 5202 + }, + { + "epoch": 0.29000613120784796, + "grad_norm": 0.6538552045822144, + "learning_rate": 8.212763162495729e-05, + "loss": 1.683, + "step": 5203 + }, + { + "epoch": 0.2900618694610111, + "grad_norm": 0.5683111548423767, + "learning_rate": 8.212080831970503e-05, + "loss": 1.6758, + "step": 5204 + }, + { + "epoch": 0.2901176077141742, + "grad_norm": 0.5633412599563599, + "learning_rate": 8.2113983995768e-05, + "loss": 1.7229, + "step": 5205 + }, + { + "epoch": 0.2901733459673374, + "grad_norm": 0.5722443461418152, + "learning_rate": 8.210715865336263e-05, + "loss": 1.8076, + "step": 5206 + }, + { + "epoch": 0.29022908422050053, + "grad_norm": 0.562892496585846, + "learning_rate": 8.21003322927054e-05, + "loss": 1.672, + "step": 5207 + }, + { + "epoch": 0.29028482247366366, + "grad_norm": 0.5266914367675781, + "learning_rate": 8.209350491401277e-05, + "loss": 1.6009, + "step": 5208 + }, + { + "epoch": 0.29034056072682685, + "grad_norm": 0.576404869556427, + "learning_rate": 8.20866765175013e-05, + "loss": 1.8675, + "step": 5209 + }, + { + "epoch": 0.29039629897999, + "grad_norm": 0.6091673374176025, + "learning_rate": 8.207984710338752e-05, + "loss": 1.7122, + "step": 5210 + }, + { + "epoch": 0.2904520372331531, + "grad_norm": 0.590103030204773, + "learning_rate": 8.207301667188803e-05, + "loss": 1.5629, + "step": 5211 + }, + { + "epoch": 0.29050777548631623, + "grad_norm": 0.5491459369659424, + "learning_rate": 8.206618522321945e-05, + "loss": 1.6373, + "step": 5212 + }, + { + "epoch": 0.2905635137394794, + "grad_norm": 0.5361247062683105, + "learning_rate": 8.205935275759842e-05, + "loss": 1.7587, + "step": 5213 + }, + { + "epoch": 0.29061925199264255, + "grad_norm": 0.5602622628211975, + "learning_rate": 8.205251927524164e-05, + "loss": 1.6596, + "step": 5214 + }, + { + "epoch": 0.2906749902458057, + "grad_norm": 0.5763882994651794, + "learning_rate": 8.204568477636585e-05, + "loss": 1.7195, + "step": 5215 + }, + { + "epoch": 0.29073072849896886, + "grad_norm": 0.5280525088310242, + "learning_rate": 8.203884926118777e-05, + "loss": 1.6929, + "step": 5216 + }, + { + "epoch": 0.290786466752132, + "grad_norm": 0.5279143452644348, + "learning_rate": 8.203201272992419e-05, + "loss": 1.4884, + "step": 5217 + }, + { + "epoch": 0.2908422050052951, + "grad_norm": 0.5360000729560852, + "learning_rate": 8.202517518279193e-05, + "loss": 1.6383, + "step": 5218 + }, + { + "epoch": 0.2908979432584583, + "grad_norm": 0.5178120732307434, + "learning_rate": 8.201833662000781e-05, + "loss": 1.3916, + "step": 5219 + }, + { + "epoch": 0.29095368151162143, + "grad_norm": 0.5441476702690125, + "learning_rate": 8.201149704178875e-05, + "loss": 1.8316, + "step": 5220 + }, + { + "epoch": 0.29100941976478456, + "grad_norm": 0.5272539854049683, + "learning_rate": 8.200465644835165e-05, + "loss": 1.479, + "step": 5221 + }, + { + "epoch": 0.29106515801794774, + "grad_norm": 0.5858429074287415, + "learning_rate": 8.199781483991345e-05, + "loss": 1.8735, + "step": 5222 + }, + { + "epoch": 0.2911208962711109, + "grad_norm": 0.5939355492591858, + "learning_rate": 8.19909722166911e-05, + "loss": 1.8911, + "step": 5223 + }, + { + "epoch": 0.291176634524274, + "grad_norm": 0.6942164301872253, + "learning_rate": 8.198412857890166e-05, + "loss": 1.5865, + "step": 5224 + }, + { + "epoch": 0.29123237277743713, + "grad_norm": 0.5283763408660889, + "learning_rate": 8.197728392676211e-05, + "loss": 1.518, + "step": 5225 + }, + { + "epoch": 0.2912881110306003, + "grad_norm": 0.5898897051811218, + "learning_rate": 8.197043826048957e-05, + "loss": 1.4729, + "step": 5226 + }, + { + "epoch": 0.29134384928376345, + "grad_norm": 0.6161963939666748, + "learning_rate": 8.196359158030113e-05, + "loss": 1.7724, + "step": 5227 + }, + { + "epoch": 0.2913995875369266, + "grad_norm": 0.5693463683128357, + "learning_rate": 8.195674388641393e-05, + "loss": 1.7379, + "step": 5228 + }, + { + "epoch": 0.29145532579008976, + "grad_norm": 0.5397728681564331, + "learning_rate": 8.194989517904513e-05, + "loss": 1.694, + "step": 5229 + }, + { + "epoch": 0.2915110640432529, + "grad_norm": 0.5856531858444214, + "learning_rate": 8.194304545841193e-05, + "loss": 1.7607, + "step": 5230 + }, + { + "epoch": 0.291566802296416, + "grad_norm": 0.5777943730354309, + "learning_rate": 8.19361947247316e-05, + "loss": 1.7321, + "step": 5231 + }, + { + "epoch": 0.2916225405495792, + "grad_norm": 0.5896830558776855, + "learning_rate": 8.192934297822133e-05, + "loss": 1.7183, + "step": 5232 + }, + { + "epoch": 0.29167827880274233, + "grad_norm": 0.6119521260261536, + "learning_rate": 8.192249021909847e-05, + "loss": 1.9229, + "step": 5233 + }, + { + "epoch": 0.29173401705590546, + "grad_norm": 0.5776544213294983, + "learning_rate": 8.191563644758037e-05, + "loss": 1.8151, + "step": 5234 + }, + { + "epoch": 0.2917897553090686, + "grad_norm": 0.510097086429596, + "learning_rate": 8.190878166388435e-05, + "loss": 1.6619, + "step": 5235 + }, + { + "epoch": 0.2918454935622318, + "grad_norm": 0.5378518104553223, + "learning_rate": 8.19019258682278e-05, + "loss": 1.8347, + "step": 5236 + }, + { + "epoch": 0.2919012318153949, + "grad_norm": 0.5934120416641235, + "learning_rate": 8.189506906082818e-05, + "loss": 1.7583, + "step": 5237 + }, + { + "epoch": 0.29195697006855803, + "grad_norm": 0.49861982464790344, + "learning_rate": 8.188821124190293e-05, + "loss": 1.4644, + "step": 5238 + }, + { + "epoch": 0.2920127083217212, + "grad_norm": 0.5318624377250671, + "learning_rate": 8.188135241166953e-05, + "loss": 1.6562, + "step": 5239 + }, + { + "epoch": 0.29206844657488434, + "grad_norm": 0.5517171621322632, + "learning_rate": 8.187449257034552e-05, + "loss": 1.6493, + "step": 5240 + }, + { + "epoch": 0.2921241848280475, + "grad_norm": 0.5400835275650024, + "learning_rate": 8.186763171814845e-05, + "loss": 1.5672, + "step": 5241 + }, + { + "epoch": 0.29217992308121066, + "grad_norm": 0.5250990986824036, + "learning_rate": 8.186076985529589e-05, + "loss": 1.6091, + "step": 5242 + }, + { + "epoch": 0.2922356613343738, + "grad_norm": 0.5855765342712402, + "learning_rate": 8.18539069820055e-05, + "loss": 1.8457, + "step": 5243 + }, + { + "epoch": 0.2922913995875369, + "grad_norm": 0.6245700716972351, + "learning_rate": 8.184704309849487e-05, + "loss": 1.5562, + "step": 5244 + }, + { + "epoch": 0.2923471378407001, + "grad_norm": 0.583342432975769, + "learning_rate": 8.184017820498173e-05, + "loss": 1.8421, + "step": 5245 + }, + { + "epoch": 0.29240287609386323, + "grad_norm": 0.576387345790863, + "learning_rate": 8.183331230168377e-05, + "loss": 1.7761, + "step": 5246 + }, + { + "epoch": 0.29245861434702636, + "grad_norm": 0.5464752316474915, + "learning_rate": 8.182644538881873e-05, + "loss": 1.6677, + "step": 5247 + }, + { + "epoch": 0.2925143526001895, + "grad_norm": 0.602606475353241, + "learning_rate": 8.181957746660445e-05, + "loss": 2.0468, + "step": 5248 + }, + { + "epoch": 0.29257009085335267, + "grad_norm": 0.535839855670929, + "learning_rate": 8.181270853525866e-05, + "loss": 1.5903, + "step": 5249 + }, + { + "epoch": 0.2926258291065158, + "grad_norm": 0.5617656707763672, + "learning_rate": 8.180583859499923e-05, + "loss": 1.6818, + "step": 5250 + }, + { + "epoch": 0.29268156735967893, + "grad_norm": 0.5979596972465515, + "learning_rate": 8.179896764604407e-05, + "loss": 1.7915, + "step": 5251 + }, + { + "epoch": 0.2927373056128421, + "grad_norm": 0.5312914848327637, + "learning_rate": 8.179209568861104e-05, + "loss": 1.4523, + "step": 5252 + }, + { + "epoch": 0.29279304386600524, + "grad_norm": 0.5243698358535767, + "learning_rate": 8.178522272291809e-05, + "loss": 1.5611, + "step": 5253 + }, + { + "epoch": 0.29284878211916837, + "grad_norm": 0.5564961433410645, + "learning_rate": 8.17783487491832e-05, + "loss": 1.7228, + "step": 5254 + }, + { + "epoch": 0.29290452037233156, + "grad_norm": 0.5704841613769531, + "learning_rate": 8.177147376762437e-05, + "loss": 1.8324, + "step": 5255 + }, + { + "epoch": 0.2929602586254947, + "grad_norm": 0.5011201500892639, + "learning_rate": 8.176459777845964e-05, + "loss": 1.6782, + "step": 5256 + }, + { + "epoch": 0.2930159968786578, + "grad_norm": 0.4964855909347534, + "learning_rate": 8.175772078190707e-05, + "loss": 1.4567, + "step": 5257 + }, + { + "epoch": 0.29307173513182094, + "grad_norm": 0.547637403011322, + "learning_rate": 8.175084277818472e-05, + "loss": 1.6129, + "step": 5258 + }, + { + "epoch": 0.2931274733849841, + "grad_norm": 0.5082324743270874, + "learning_rate": 8.174396376751079e-05, + "loss": 1.5253, + "step": 5259 + }, + { + "epoch": 0.29318321163814726, + "grad_norm": 0.535663366317749, + "learning_rate": 8.173708375010342e-05, + "loss": 1.574, + "step": 5260 + }, + { + "epoch": 0.2932389498913104, + "grad_norm": 0.5733945965766907, + "learning_rate": 8.173020272618078e-05, + "loss": 1.8022, + "step": 5261 + }, + { + "epoch": 0.29329468814447357, + "grad_norm": 0.5937253832817078, + "learning_rate": 8.172332069596111e-05, + "loss": 1.952, + "step": 5262 + }, + { + "epoch": 0.2933504263976367, + "grad_norm": 0.5622910261154175, + "learning_rate": 8.171643765966266e-05, + "loss": 1.6838, + "step": 5263 + }, + { + "epoch": 0.29340616465079983, + "grad_norm": 0.5633754730224609, + "learning_rate": 8.170955361750373e-05, + "loss": 1.8205, + "step": 5264 + }, + { + "epoch": 0.293461902903963, + "grad_norm": 0.5639583468437195, + "learning_rate": 8.170266856970264e-05, + "loss": 1.6995, + "step": 5265 + }, + { + "epoch": 0.29351764115712614, + "grad_norm": 0.5767412781715393, + "learning_rate": 8.169578251647775e-05, + "loss": 1.8193, + "step": 5266 + }, + { + "epoch": 0.29357337941028927, + "grad_norm": 0.5323848128318787, + "learning_rate": 8.168889545804743e-05, + "loss": 1.6137, + "step": 5267 + }, + { + "epoch": 0.29362911766345245, + "grad_norm": 0.5105542540550232, + "learning_rate": 8.16820073946301e-05, + "loss": 1.3883, + "step": 5268 + }, + { + "epoch": 0.2936848559166156, + "grad_norm": 0.5348597168922424, + "learning_rate": 8.167511832644423e-05, + "loss": 1.7465, + "step": 5269 + }, + { + "epoch": 0.2937405941697787, + "grad_norm": 0.5634239315986633, + "learning_rate": 8.166822825370828e-05, + "loss": 1.8121, + "step": 5270 + }, + { + "epoch": 0.29379633242294184, + "grad_norm": 0.5704219937324524, + "learning_rate": 8.166133717664075e-05, + "loss": 1.8007, + "step": 5271 + }, + { + "epoch": 0.293852070676105, + "grad_norm": 0.5514686703681946, + "learning_rate": 8.165444509546023e-05, + "loss": 1.7627, + "step": 5272 + }, + { + "epoch": 0.29390780892926816, + "grad_norm": 0.5763065218925476, + "learning_rate": 8.164755201038525e-05, + "loss": 1.8668, + "step": 5273 + }, + { + "epoch": 0.2939635471824313, + "grad_norm": 0.5290045738220215, + "learning_rate": 8.164065792163445e-05, + "loss": 1.6992, + "step": 5274 + }, + { + "epoch": 0.29401928543559447, + "grad_norm": 0.5327118039131165, + "learning_rate": 8.163376282942645e-05, + "loss": 1.6882, + "step": 5275 + }, + { + "epoch": 0.2940750236887576, + "grad_norm": 0.5230002403259277, + "learning_rate": 8.162686673397995e-05, + "loss": 1.6314, + "step": 5276 + }, + { + "epoch": 0.2941307619419207, + "grad_norm": 0.5596842765808105, + "learning_rate": 8.161996963551361e-05, + "loss": 1.8543, + "step": 5277 + }, + { + "epoch": 0.2941865001950839, + "grad_norm": 0.4837280809879303, + "learning_rate": 8.16130715342462e-05, + "loss": 1.407, + "step": 5278 + }, + { + "epoch": 0.29424223844824704, + "grad_norm": 0.5188647508621216, + "learning_rate": 8.160617243039648e-05, + "loss": 1.6469, + "step": 5279 + }, + { + "epoch": 0.29429797670141017, + "grad_norm": 0.5345882177352905, + "learning_rate": 8.159927232418325e-05, + "loss": 1.762, + "step": 5280 + }, + { + "epoch": 0.2943537149545733, + "grad_norm": 0.6385248303413391, + "learning_rate": 8.159237121582532e-05, + "loss": 1.725, + "step": 5281 + }, + { + "epoch": 0.2944094532077365, + "grad_norm": 0.532394289970398, + "learning_rate": 8.158546910554159e-05, + "loss": 1.59, + "step": 5282 + }, + { + "epoch": 0.2944651914608996, + "grad_norm": 0.5918634533882141, + "learning_rate": 8.157856599355093e-05, + "loss": 1.8722, + "step": 5283 + }, + { + "epoch": 0.29452092971406274, + "grad_norm": 0.5643036365509033, + "learning_rate": 8.157166188007228e-05, + "loss": 1.6608, + "step": 5284 + }, + { + "epoch": 0.2945766679672259, + "grad_norm": 0.5480226874351501, + "learning_rate": 8.156475676532458e-05, + "loss": 1.6745, + "step": 5285 + }, + { + "epoch": 0.29463240622038905, + "grad_norm": 0.5562642216682434, + "learning_rate": 8.155785064952683e-05, + "loss": 1.9036, + "step": 5286 + }, + { + "epoch": 0.2946881444735522, + "grad_norm": 0.5737085938453674, + "learning_rate": 8.155094353289807e-05, + "loss": 1.6749, + "step": 5287 + }, + { + "epoch": 0.29474388272671537, + "grad_norm": 0.537407398223877, + "learning_rate": 8.154403541565732e-05, + "loss": 1.5855, + "step": 5288 + }, + { + "epoch": 0.2947996209798785, + "grad_norm": 0.5637186169624329, + "learning_rate": 8.153712629802369e-05, + "loss": 1.6667, + "step": 5289 + }, + { + "epoch": 0.2948553592330416, + "grad_norm": 0.587086021900177, + "learning_rate": 8.153021618021628e-05, + "loss": 1.709, + "step": 5290 + }, + { + "epoch": 0.2949110974862048, + "grad_norm": 0.5255305767059326, + "learning_rate": 8.152330506245425e-05, + "loss": 1.4982, + "step": 5291 + }, + { + "epoch": 0.29496683573936794, + "grad_norm": 0.5582296848297119, + "learning_rate": 8.151639294495678e-05, + "loss": 1.6915, + "step": 5292 + }, + { + "epoch": 0.29502257399253107, + "grad_norm": 0.5476033687591553, + "learning_rate": 8.150947982794307e-05, + "loss": 1.4827, + "step": 5293 + }, + { + "epoch": 0.2950783122456942, + "grad_norm": 0.548763632774353, + "learning_rate": 8.150256571163238e-05, + "loss": 1.805, + "step": 5294 + }, + { + "epoch": 0.2951340504988574, + "grad_norm": 0.58586585521698, + "learning_rate": 8.149565059624398e-05, + "loss": 1.7433, + "step": 5295 + }, + { + "epoch": 0.2951897887520205, + "grad_norm": 0.5618621110916138, + "learning_rate": 8.148873448199717e-05, + "loss": 1.7681, + "step": 5296 + }, + { + "epoch": 0.29524552700518364, + "grad_norm": 0.5388831496238708, + "learning_rate": 8.148181736911129e-05, + "loss": 1.582, + "step": 5297 + }, + { + "epoch": 0.2953012652583468, + "grad_norm": 0.5742696523666382, + "learning_rate": 8.147489925780572e-05, + "loss": 1.8182, + "step": 5298 + }, + { + "epoch": 0.29535700351150995, + "grad_norm": 0.5271889567375183, + "learning_rate": 8.146798014829986e-05, + "loss": 1.4823, + "step": 5299 + }, + { + "epoch": 0.2954127417646731, + "grad_norm": 0.5565046072006226, + "learning_rate": 8.146106004081315e-05, + "loss": 1.6328, + "step": 5300 + }, + { + "epoch": 0.29546848001783627, + "grad_norm": 0.5434616804122925, + "learning_rate": 8.145413893556503e-05, + "loss": 1.5871, + "step": 5301 + }, + { + "epoch": 0.2955242182709994, + "grad_norm": 0.5343239903450012, + "learning_rate": 8.144721683277504e-05, + "loss": 1.6328, + "step": 5302 + }, + { + "epoch": 0.2955799565241625, + "grad_norm": 0.5372942686080933, + "learning_rate": 8.144029373266264e-05, + "loss": 1.6885, + "step": 5303 + }, + { + "epoch": 0.29563569477732565, + "grad_norm": 0.5881915092468262, + "learning_rate": 8.143336963544746e-05, + "loss": 1.8579, + "step": 5304 + }, + { + "epoch": 0.29569143303048884, + "grad_norm": 0.5892425179481506, + "learning_rate": 8.142644454134905e-05, + "loss": 1.8771, + "step": 5305 + }, + { + "epoch": 0.29574717128365197, + "grad_norm": 0.5286465287208557, + "learning_rate": 8.141951845058707e-05, + "loss": 1.6766, + "step": 5306 + }, + { + "epoch": 0.2958029095368151, + "grad_norm": 0.5843679904937744, + "learning_rate": 8.141259136338113e-05, + "loss": 1.7359, + "step": 5307 + }, + { + "epoch": 0.2958586477899783, + "grad_norm": 0.6178736090660095, + "learning_rate": 8.140566327995094e-05, + "loss": 1.9672, + "step": 5308 + }, + { + "epoch": 0.2959143860431414, + "grad_norm": 0.5524381399154663, + "learning_rate": 8.139873420051623e-05, + "loss": 1.5947, + "step": 5309 + }, + { + "epoch": 0.29597012429630454, + "grad_norm": 0.5591756105422974, + "learning_rate": 8.139180412529674e-05, + "loss": 1.7245, + "step": 5310 + }, + { + "epoch": 0.2960258625494677, + "grad_norm": 0.5642113089561462, + "learning_rate": 8.138487305451224e-05, + "loss": 1.7156, + "step": 5311 + }, + { + "epoch": 0.29608160080263085, + "grad_norm": 0.5767959356307983, + "learning_rate": 8.137794098838257e-05, + "loss": 1.78, + "step": 5312 + }, + { + "epoch": 0.296137339055794, + "grad_norm": 0.5422171950340271, + "learning_rate": 8.137100792712755e-05, + "loss": 1.9258, + "step": 5313 + }, + { + "epoch": 0.29619307730895716, + "grad_norm": 0.5860824584960938, + "learning_rate": 8.136407387096704e-05, + "loss": 1.7132, + "step": 5314 + }, + { + "epoch": 0.2962488155621203, + "grad_norm": 0.6460077166557312, + "learning_rate": 8.135713882012102e-05, + "loss": 1.8024, + "step": 5315 + }, + { + "epoch": 0.2963045538152834, + "grad_norm": 0.5744182467460632, + "learning_rate": 8.135020277480934e-05, + "loss": 1.7025, + "step": 5316 + }, + { + "epoch": 0.29636029206844655, + "grad_norm": 0.560867965221405, + "learning_rate": 8.134326573525202e-05, + "loss": 1.7402, + "step": 5317 + }, + { + "epoch": 0.29641603032160974, + "grad_norm": 0.5005339980125427, + "learning_rate": 8.133632770166907e-05, + "loss": 1.585, + "step": 5318 + }, + { + "epoch": 0.29647176857477286, + "grad_norm": 0.5216720700263977, + "learning_rate": 8.13293886742805e-05, + "loss": 1.7313, + "step": 5319 + }, + { + "epoch": 0.296527506827936, + "grad_norm": 0.5353510975837708, + "learning_rate": 8.132244865330638e-05, + "loss": 1.7854, + "step": 5320 + }, + { + "epoch": 0.2965832450810992, + "grad_norm": 0.5222895741462708, + "learning_rate": 8.131550763896682e-05, + "loss": 1.6821, + "step": 5321 + }, + { + "epoch": 0.2966389833342623, + "grad_norm": 0.5571734309196472, + "learning_rate": 8.130856563148193e-05, + "loss": 1.6151, + "step": 5322 + }, + { + "epoch": 0.29669472158742544, + "grad_norm": 0.5494416952133179, + "learning_rate": 8.130162263107189e-05, + "loss": 1.7497, + "step": 5323 + }, + { + "epoch": 0.2967504598405886, + "grad_norm": 0.5263827443122864, + "learning_rate": 8.129467863795688e-05, + "loss": 1.7157, + "step": 5324 + }, + { + "epoch": 0.29680619809375175, + "grad_norm": 0.5756681561470032, + "learning_rate": 8.128773365235711e-05, + "loss": 1.6488, + "step": 5325 + }, + { + "epoch": 0.2968619363469149, + "grad_norm": 0.5204091668128967, + "learning_rate": 8.128078767449287e-05, + "loss": 1.6868, + "step": 5326 + }, + { + "epoch": 0.296917674600078, + "grad_norm": 0.5748211145401001, + "learning_rate": 8.127384070458442e-05, + "loss": 1.9352, + "step": 5327 + }, + { + "epoch": 0.2969734128532412, + "grad_norm": 0.5648884773254395, + "learning_rate": 8.126689274285207e-05, + "loss": 1.9085, + "step": 5328 + }, + { + "epoch": 0.2970291511064043, + "grad_norm": 0.5396182537078857, + "learning_rate": 8.125994378951619e-05, + "loss": 1.715, + "step": 5329 + }, + { + "epoch": 0.29708488935956745, + "grad_norm": 0.5755982398986816, + "learning_rate": 8.125299384479714e-05, + "loss": 1.7472, + "step": 5330 + }, + { + "epoch": 0.29714062761273063, + "grad_norm": 0.5721607804298401, + "learning_rate": 8.124604290891535e-05, + "loss": 1.8646, + "step": 5331 + }, + { + "epoch": 0.29719636586589376, + "grad_norm": 0.5612310171127319, + "learning_rate": 8.123909098209126e-05, + "loss": 1.6506, + "step": 5332 + }, + { + "epoch": 0.2972521041190569, + "grad_norm": 0.5630115866661072, + "learning_rate": 8.123213806454535e-05, + "loss": 1.805, + "step": 5333 + }, + { + "epoch": 0.2973078423722201, + "grad_norm": 0.5319987535476685, + "learning_rate": 8.122518415649808e-05, + "loss": 1.6501, + "step": 5334 + }, + { + "epoch": 0.2973635806253832, + "grad_norm": 0.5346727967262268, + "learning_rate": 8.121822925817006e-05, + "loss": 1.7944, + "step": 5335 + }, + { + "epoch": 0.29741931887854633, + "grad_norm": 0.5356037616729736, + "learning_rate": 8.121127336978183e-05, + "loss": 1.5578, + "step": 5336 + }, + { + "epoch": 0.2974750571317095, + "grad_norm": 0.5593723058700562, + "learning_rate": 8.120431649155396e-05, + "loss": 1.7118, + "step": 5337 + }, + { + "epoch": 0.29753079538487265, + "grad_norm": 0.5361452102661133, + "learning_rate": 8.11973586237071e-05, + "loss": 1.7363, + "step": 5338 + }, + { + "epoch": 0.2975865336380358, + "grad_norm": 0.5503700971603394, + "learning_rate": 8.119039976646192e-05, + "loss": 1.74, + "step": 5339 + }, + { + "epoch": 0.2976422718911989, + "grad_norm": 0.5040326714515686, + "learning_rate": 8.118343992003913e-05, + "loss": 1.5712, + "step": 5340 + }, + { + "epoch": 0.2976980101443621, + "grad_norm": 0.5251342058181763, + "learning_rate": 8.117647908465942e-05, + "loss": 1.5346, + "step": 5341 + }, + { + "epoch": 0.2977537483975252, + "grad_norm": 0.5664347410202026, + "learning_rate": 8.116951726054358e-05, + "loss": 2.0871, + "step": 5342 + }, + { + "epoch": 0.29780948665068835, + "grad_norm": 0.5798686742782593, + "learning_rate": 8.116255444791237e-05, + "loss": 1.5362, + "step": 5343 + }, + { + "epoch": 0.29786522490385153, + "grad_norm": 0.5248550772666931, + "learning_rate": 8.115559064698662e-05, + "loss": 1.5788, + "step": 5344 + }, + { + "epoch": 0.29792096315701466, + "grad_norm": 0.6149808764457703, + "learning_rate": 8.11486258579872e-05, + "loss": 1.7055, + "step": 5345 + }, + { + "epoch": 0.2979767014101778, + "grad_norm": 0.6035127639770508, + "learning_rate": 8.114166008113498e-05, + "loss": 1.8135, + "step": 5346 + }, + { + "epoch": 0.298032439663341, + "grad_norm": 0.5967592000961304, + "learning_rate": 8.113469331665085e-05, + "loss": 1.655, + "step": 5347 + }, + { + "epoch": 0.2980881779165041, + "grad_norm": 0.5948666334152222, + "learning_rate": 8.112772556475579e-05, + "loss": 2.0929, + "step": 5348 + }, + { + "epoch": 0.29814391616966723, + "grad_norm": 0.5955588221549988, + "learning_rate": 8.112075682567075e-05, + "loss": 1.6594, + "step": 5349 + }, + { + "epoch": 0.29819965442283036, + "grad_norm": 0.5304718017578125, + "learning_rate": 8.111378709961676e-05, + "loss": 1.7254, + "step": 5350 + }, + { + "epoch": 0.29825539267599355, + "grad_norm": 0.5426492691040039, + "learning_rate": 8.110681638681485e-05, + "loss": 1.7559, + "step": 5351 + }, + { + "epoch": 0.2983111309291567, + "grad_norm": 0.6616886258125305, + "learning_rate": 8.109984468748608e-05, + "loss": 1.6271, + "step": 5352 + }, + { + "epoch": 0.2983668691823198, + "grad_norm": 0.537685751914978, + "learning_rate": 8.109287200185157e-05, + "loss": 1.6231, + "step": 5353 + }, + { + "epoch": 0.298422607435483, + "grad_norm": 0.5190281867980957, + "learning_rate": 8.108589833013245e-05, + "loss": 1.5838, + "step": 5354 + }, + { + "epoch": 0.2984783456886461, + "grad_norm": 0.5232527852058411, + "learning_rate": 8.107892367254986e-05, + "loss": 1.5132, + "step": 5355 + }, + { + "epoch": 0.29853408394180925, + "grad_norm": 0.5797703266143799, + "learning_rate": 8.107194802932503e-05, + "loss": 1.811, + "step": 5356 + }, + { + "epoch": 0.29858982219497243, + "grad_norm": 0.5324226021766663, + "learning_rate": 8.106497140067916e-05, + "loss": 1.8477, + "step": 5357 + }, + { + "epoch": 0.29864556044813556, + "grad_norm": 0.5274566411972046, + "learning_rate": 8.105799378683353e-05, + "loss": 1.5521, + "step": 5358 + }, + { + "epoch": 0.2987012987012987, + "grad_norm": 0.5862823128700256, + "learning_rate": 8.10510151880094e-05, + "loss": 1.6123, + "step": 5359 + }, + { + "epoch": 0.2987570369544619, + "grad_norm": 0.5503446459770203, + "learning_rate": 8.104403560442813e-05, + "loss": 1.6369, + "step": 5360 + }, + { + "epoch": 0.298812775207625, + "grad_norm": 0.5560075044631958, + "learning_rate": 8.103705503631104e-05, + "loss": 1.762, + "step": 5361 + }, + { + "epoch": 0.29886851346078813, + "grad_norm": 0.5699611306190491, + "learning_rate": 8.103007348387952e-05, + "loss": 1.9896, + "step": 5362 + }, + { + "epoch": 0.29892425171395126, + "grad_norm": 0.5774125456809998, + "learning_rate": 8.102309094735498e-05, + "loss": 1.7463, + "step": 5363 + }, + { + "epoch": 0.29897998996711445, + "grad_norm": 0.5046089887619019, + "learning_rate": 8.101610742695889e-05, + "loss": 1.4381, + "step": 5364 + }, + { + "epoch": 0.2990357282202776, + "grad_norm": 0.5611773133277893, + "learning_rate": 8.100912292291269e-05, + "loss": 1.8118, + "step": 5365 + }, + { + "epoch": 0.2990914664734407, + "grad_norm": 0.5826941132545471, + "learning_rate": 8.100213743543793e-05, + "loss": 1.7309, + "step": 5366 + }, + { + "epoch": 0.2991472047266039, + "grad_norm": 0.5598444938659668, + "learning_rate": 8.099515096475611e-05, + "loss": 1.7422, + "step": 5367 + }, + { + "epoch": 0.299202942979767, + "grad_norm": 0.5191280841827393, + "learning_rate": 8.098816351108881e-05, + "loss": 1.5088, + "step": 5368 + }, + { + "epoch": 0.29925868123293015, + "grad_norm": 0.589454174041748, + "learning_rate": 8.098117507465765e-05, + "loss": 1.4643, + "step": 5369 + }, + { + "epoch": 0.29931441948609333, + "grad_norm": 0.5066042542457581, + "learning_rate": 8.097418565568424e-05, + "loss": 1.3811, + "step": 5370 + }, + { + "epoch": 0.29937015773925646, + "grad_norm": 0.5717688798904419, + "learning_rate": 8.096719525439026e-05, + "loss": 1.5929, + "step": 5371 + }, + { + "epoch": 0.2994258959924196, + "grad_norm": 0.5810229778289795, + "learning_rate": 8.096020387099739e-05, + "loss": 1.5428, + "step": 5372 + }, + { + "epoch": 0.2994816342455827, + "grad_norm": 0.5295297503471375, + "learning_rate": 8.095321150572738e-05, + "loss": 1.5148, + "step": 5373 + }, + { + "epoch": 0.2995373724987459, + "grad_norm": 0.6027771234512329, + "learning_rate": 8.094621815880197e-05, + "loss": 1.898, + "step": 5374 + }, + { + "epoch": 0.29959311075190903, + "grad_norm": 0.5107868909835815, + "learning_rate": 8.093922383044293e-05, + "loss": 1.4073, + "step": 5375 + }, + { + "epoch": 0.29964884900507216, + "grad_norm": 0.5989086031913757, + "learning_rate": 8.09322285208721e-05, + "loss": 1.7551, + "step": 5376 + }, + { + "epoch": 0.29970458725823534, + "grad_norm": 0.5706072449684143, + "learning_rate": 8.092523223031134e-05, + "loss": 1.8272, + "step": 5377 + }, + { + "epoch": 0.2997603255113985, + "grad_norm": 0.5593813061714172, + "learning_rate": 8.091823495898251e-05, + "loss": 1.6346, + "step": 5378 + }, + { + "epoch": 0.2998160637645616, + "grad_norm": 0.5510803461074829, + "learning_rate": 8.091123670710754e-05, + "loss": 1.7025, + "step": 5379 + }, + { + "epoch": 0.2998718020177248, + "grad_norm": 0.5860506892204285, + "learning_rate": 8.090423747490836e-05, + "loss": 1.6895, + "step": 5380 + }, + { + "epoch": 0.2999275402708879, + "grad_norm": 0.5655683875083923, + "learning_rate": 8.089723726260696e-05, + "loss": 1.8338, + "step": 5381 + }, + { + "epoch": 0.29998327852405104, + "grad_norm": 0.5369336605072021, + "learning_rate": 8.089023607042534e-05, + "loss": 1.65, + "step": 5382 + }, + { + "epoch": 0.30003901677721423, + "grad_norm": 0.5484170317649841, + "learning_rate": 8.088323389858552e-05, + "loss": 1.433, + "step": 5383 + }, + { + "epoch": 0.30009475503037736, + "grad_norm": 0.5139251947402954, + "learning_rate": 8.08762307473096e-05, + "loss": 1.3703, + "step": 5384 + }, + { + "epoch": 0.3001504932835405, + "grad_norm": 0.6160516142845154, + "learning_rate": 8.086922661681966e-05, + "loss": 2.1215, + "step": 5385 + }, + { + "epoch": 0.3002062315367036, + "grad_norm": 0.5299053192138672, + "learning_rate": 8.086222150733782e-05, + "loss": 1.5703, + "step": 5386 + }, + { + "epoch": 0.3002619697898668, + "grad_norm": 0.5320441722869873, + "learning_rate": 8.085521541908627e-05, + "loss": 1.5785, + "step": 5387 + }, + { + "epoch": 0.30031770804302993, + "grad_norm": 0.5633600354194641, + "learning_rate": 8.084820835228717e-05, + "loss": 1.799, + "step": 5388 + }, + { + "epoch": 0.30037344629619306, + "grad_norm": 0.5468734502792358, + "learning_rate": 8.084120030716275e-05, + "loss": 1.6782, + "step": 5389 + }, + { + "epoch": 0.30042918454935624, + "grad_norm": 0.5711122751235962, + "learning_rate": 8.083419128393528e-05, + "loss": 1.6544, + "step": 5390 + }, + { + "epoch": 0.30048492280251937, + "grad_norm": 0.5407732129096985, + "learning_rate": 8.082718128282705e-05, + "loss": 1.7962, + "step": 5391 + }, + { + "epoch": 0.3005406610556825, + "grad_norm": 0.5521290898323059, + "learning_rate": 8.082017030406037e-05, + "loss": 1.7551, + "step": 5392 + }, + { + "epoch": 0.3005963993088457, + "grad_norm": 0.5816917419433594, + "learning_rate": 8.081315834785756e-05, + "loss": 1.8789, + "step": 5393 + }, + { + "epoch": 0.3006521375620088, + "grad_norm": 0.5271922945976257, + "learning_rate": 8.080614541444103e-05, + "loss": 1.7545, + "step": 5394 + }, + { + "epoch": 0.30070787581517194, + "grad_norm": 0.543911337852478, + "learning_rate": 8.079913150403318e-05, + "loss": 1.6059, + "step": 5395 + }, + { + "epoch": 0.3007636140683351, + "grad_norm": 0.547044038772583, + "learning_rate": 8.079211661685644e-05, + "loss": 2.0125, + "step": 5396 + }, + { + "epoch": 0.30081935232149826, + "grad_norm": 0.6385172605514526, + "learning_rate": 8.07851007531333e-05, + "loss": 1.8713, + "step": 5397 + }, + { + "epoch": 0.3008750905746614, + "grad_norm": 0.5882077813148499, + "learning_rate": 8.077808391308626e-05, + "loss": 1.6547, + "step": 5398 + }, + { + "epoch": 0.3009308288278245, + "grad_norm": 0.5390593409538269, + "learning_rate": 8.077106609693784e-05, + "loss": 1.5186, + "step": 5399 + }, + { + "epoch": 0.3009865670809877, + "grad_norm": 0.5759447813034058, + "learning_rate": 8.076404730491061e-05, + "loss": 1.8402, + "step": 5400 + }, + { + "epoch": 0.30104230533415083, + "grad_norm": 0.5196195244789124, + "learning_rate": 8.075702753722718e-05, + "loss": 1.656, + "step": 5401 + }, + { + "epoch": 0.30109804358731396, + "grad_norm": 0.5357980728149414, + "learning_rate": 8.075000679411014e-05, + "loss": 1.6743, + "step": 5402 + }, + { + "epoch": 0.30115378184047714, + "grad_norm": 0.5370086431503296, + "learning_rate": 8.074298507578218e-05, + "loss": 1.7567, + "step": 5403 + }, + { + "epoch": 0.30120952009364027, + "grad_norm": 0.5173280835151672, + "learning_rate": 8.073596238246599e-05, + "loss": 1.5783, + "step": 5404 + }, + { + "epoch": 0.3012652583468034, + "grad_norm": 0.5284645557403564, + "learning_rate": 8.072893871438428e-05, + "loss": 1.7135, + "step": 5405 + }, + { + "epoch": 0.3013209965999666, + "grad_norm": 0.5838817954063416, + "learning_rate": 8.072191407175976e-05, + "loss": 1.8845, + "step": 5406 + }, + { + "epoch": 0.3013767348531297, + "grad_norm": 0.5520975589752197, + "learning_rate": 8.071488845481528e-05, + "loss": 1.6139, + "step": 5407 + }, + { + "epoch": 0.30143247310629284, + "grad_norm": 0.5155717730522156, + "learning_rate": 8.07078618637736e-05, + "loss": 1.4973, + "step": 5408 + }, + { + "epoch": 0.30148821135945597, + "grad_norm": 0.5581832528114319, + "learning_rate": 8.070083429885758e-05, + "loss": 1.7224, + "step": 5409 + }, + { + "epoch": 0.30154394961261916, + "grad_norm": 0.5734993815422058, + "learning_rate": 8.069380576029011e-05, + "loss": 1.508, + "step": 5410 + }, + { + "epoch": 0.3015996878657823, + "grad_norm": 0.5819764733314514, + "learning_rate": 8.068677624829406e-05, + "loss": 2.0365, + "step": 5411 + }, + { + "epoch": 0.3016554261189454, + "grad_norm": 0.538995623588562, + "learning_rate": 8.067974576309241e-05, + "loss": 1.8489, + "step": 5412 + }, + { + "epoch": 0.3017111643721086, + "grad_norm": 0.5447677373886108, + "learning_rate": 8.067271430490809e-05, + "loss": 1.7361, + "step": 5413 + }, + { + "epoch": 0.3017669026252717, + "grad_norm": 0.5370633602142334, + "learning_rate": 8.066568187396409e-05, + "loss": 1.5648, + "step": 5414 + }, + { + "epoch": 0.30182264087843486, + "grad_norm": 0.5709346532821655, + "learning_rate": 8.065864847048346e-05, + "loss": 1.7308, + "step": 5415 + }, + { + "epoch": 0.30187837913159804, + "grad_norm": 0.5642514824867249, + "learning_rate": 8.065161409468925e-05, + "loss": 1.9456, + "step": 5416 + }, + { + "epoch": 0.30193411738476117, + "grad_norm": 0.5522916316986084, + "learning_rate": 8.064457874680457e-05, + "loss": 1.8213, + "step": 5417 + }, + { + "epoch": 0.3019898556379243, + "grad_norm": 0.5913909077644348, + "learning_rate": 8.06375424270525e-05, + "loss": 1.8837, + "step": 5418 + }, + { + "epoch": 0.3020455938910874, + "grad_norm": 0.596079409122467, + "learning_rate": 8.063050513565624e-05, + "loss": 1.9783, + "step": 5419 + }, + { + "epoch": 0.3021013321442506, + "grad_norm": 0.5493654012680054, + "learning_rate": 8.062346687283892e-05, + "loss": 1.8092, + "step": 5420 + }, + { + "epoch": 0.30215707039741374, + "grad_norm": 0.5493000745773315, + "learning_rate": 8.06164276388238e-05, + "loss": 1.6994, + "step": 5421 + }, + { + "epoch": 0.30221280865057687, + "grad_norm": 0.4986167550086975, + "learning_rate": 8.060938743383408e-05, + "loss": 1.5504, + "step": 5422 + }, + { + "epoch": 0.30226854690374005, + "grad_norm": 0.5836266875267029, + "learning_rate": 8.060234625809306e-05, + "loss": 1.8898, + "step": 5423 + }, + { + "epoch": 0.3023242851569032, + "grad_norm": 0.5557297468185425, + "learning_rate": 8.059530411182406e-05, + "loss": 1.7518, + "step": 5424 + }, + { + "epoch": 0.3023800234100663, + "grad_norm": 0.5643293261528015, + "learning_rate": 8.058826099525039e-05, + "loss": 1.92, + "step": 5425 + }, + { + "epoch": 0.3024357616632295, + "grad_norm": 0.5600275993347168, + "learning_rate": 8.058121690859541e-05, + "loss": 1.7421, + "step": 5426 + }, + { + "epoch": 0.3024914999163926, + "grad_norm": 0.5405864119529724, + "learning_rate": 8.057417185208254e-05, + "loss": 1.7487, + "step": 5427 + }, + { + "epoch": 0.30254723816955575, + "grad_norm": 0.5578258633613586, + "learning_rate": 8.056712582593519e-05, + "loss": 1.7268, + "step": 5428 + }, + { + "epoch": 0.30260297642271894, + "grad_norm": 0.5377827286720276, + "learning_rate": 8.056007883037682e-05, + "loss": 1.8249, + "step": 5429 + }, + { + "epoch": 0.30265871467588207, + "grad_norm": 0.5574936270713806, + "learning_rate": 8.055303086563095e-05, + "loss": 1.8337, + "step": 5430 + }, + { + "epoch": 0.3027144529290452, + "grad_norm": 0.594794511795044, + "learning_rate": 8.054598193192106e-05, + "loss": 2.0531, + "step": 5431 + }, + { + "epoch": 0.3027701911822083, + "grad_norm": 0.509722888469696, + "learning_rate": 8.053893202947074e-05, + "loss": 1.6712, + "step": 5432 + }, + { + "epoch": 0.3028259294353715, + "grad_norm": 0.5056367516517639, + "learning_rate": 8.053188115850354e-05, + "loss": 1.5738, + "step": 5433 + }, + { + "epoch": 0.30288166768853464, + "grad_norm": 0.5353802442550659, + "learning_rate": 8.052482931924308e-05, + "loss": 1.8257, + "step": 5434 + }, + { + "epoch": 0.30293740594169777, + "grad_norm": 0.535033106803894, + "learning_rate": 8.051777651191299e-05, + "loss": 1.7261, + "step": 5435 + }, + { + "epoch": 0.30299314419486095, + "grad_norm": 0.5537331700325012, + "learning_rate": 8.051072273673698e-05, + "loss": 1.7634, + "step": 5436 + }, + { + "epoch": 0.3030488824480241, + "grad_norm": 0.538147509098053, + "learning_rate": 8.050366799393874e-05, + "loss": 1.5592, + "step": 5437 + }, + { + "epoch": 0.3031046207011872, + "grad_norm": 0.5110997557640076, + "learning_rate": 8.049661228374199e-05, + "loss": 1.7104, + "step": 5438 + }, + { + "epoch": 0.3031603589543504, + "grad_norm": 0.5138676166534424, + "learning_rate": 8.04895556063705e-05, + "loss": 1.7344, + "step": 5439 + }, + { + "epoch": 0.3032160972075135, + "grad_norm": 0.5240350961685181, + "learning_rate": 8.048249796204808e-05, + "loss": 1.6345, + "step": 5440 + }, + { + "epoch": 0.30327183546067665, + "grad_norm": 0.5258268713951111, + "learning_rate": 8.047543935099855e-05, + "loss": 1.542, + "step": 5441 + }, + { + "epoch": 0.3033275737138398, + "grad_norm": 0.5549874901771545, + "learning_rate": 8.046837977344577e-05, + "loss": 1.8106, + "step": 5442 + }, + { + "epoch": 0.30338331196700297, + "grad_norm": 0.5787036418914795, + "learning_rate": 8.046131922961362e-05, + "loss": 1.8995, + "step": 5443 + }, + { + "epoch": 0.3034390502201661, + "grad_norm": 0.5319430828094482, + "learning_rate": 8.045425771972603e-05, + "loss": 1.471, + "step": 5444 + }, + { + "epoch": 0.3034947884733292, + "grad_norm": 0.5467014312744141, + "learning_rate": 8.044719524400694e-05, + "loss": 1.6613, + "step": 5445 + }, + { + "epoch": 0.3035505267264924, + "grad_norm": 0.5461364388465881, + "learning_rate": 8.044013180268034e-05, + "loss": 1.7442, + "step": 5446 + }, + { + "epoch": 0.30360626497965554, + "grad_norm": 0.5711673498153687, + "learning_rate": 8.043306739597024e-05, + "loss": 1.7848, + "step": 5447 + }, + { + "epoch": 0.30366200323281867, + "grad_norm": 0.5382382273674011, + "learning_rate": 8.042600202410066e-05, + "loss": 1.5744, + "step": 5448 + }, + { + "epoch": 0.30371774148598185, + "grad_norm": 0.5482212901115417, + "learning_rate": 8.041893568729573e-05, + "loss": 1.6689, + "step": 5449 + }, + { + "epoch": 0.303773479739145, + "grad_norm": 0.5345839262008667, + "learning_rate": 8.041186838577949e-05, + "loss": 1.6285, + "step": 5450 + }, + { + "epoch": 0.3038292179923081, + "grad_norm": 0.5510614514350891, + "learning_rate": 8.04048001197761e-05, + "loss": 1.5176, + "step": 5451 + }, + { + "epoch": 0.3038849562454713, + "grad_norm": 0.5475590825080872, + "learning_rate": 8.039773088950973e-05, + "loss": 1.6778, + "step": 5452 + }, + { + "epoch": 0.3039406944986344, + "grad_norm": 0.5662024021148682, + "learning_rate": 8.039066069520455e-05, + "loss": 1.9253, + "step": 5453 + }, + { + "epoch": 0.30399643275179755, + "grad_norm": 0.6412192583084106, + "learning_rate": 8.038358953708482e-05, + "loss": 1.8921, + "step": 5454 + }, + { + "epoch": 0.3040521710049607, + "grad_norm": 0.5427385568618774, + "learning_rate": 8.037651741537478e-05, + "loss": 1.6157, + "step": 5455 + }, + { + "epoch": 0.30410790925812387, + "grad_norm": 0.5492942333221436, + "learning_rate": 8.03694443302987e-05, + "loss": 1.6204, + "step": 5456 + }, + { + "epoch": 0.304163647511287, + "grad_norm": 0.5571532249450684, + "learning_rate": 8.036237028208092e-05, + "loss": 1.6984, + "step": 5457 + }, + { + "epoch": 0.3042193857644501, + "grad_norm": 0.5320706963539124, + "learning_rate": 8.035529527094578e-05, + "loss": 1.5733, + "step": 5458 + }, + { + "epoch": 0.3042751240176133, + "grad_norm": 0.5525981187820435, + "learning_rate": 8.034821929711767e-05, + "loss": 1.6158, + "step": 5459 + }, + { + "epoch": 0.30433086227077644, + "grad_norm": 0.5780904293060303, + "learning_rate": 8.034114236082098e-05, + "loss": 1.8269, + "step": 5460 + }, + { + "epoch": 0.30438660052393957, + "grad_norm": 0.5405531525611877, + "learning_rate": 8.033406446228014e-05, + "loss": 1.8742, + "step": 5461 + }, + { + "epoch": 0.30444233877710275, + "grad_norm": 0.5742613077163696, + "learning_rate": 8.032698560171964e-05, + "loss": 1.9496, + "step": 5462 + }, + { + "epoch": 0.3044980770302659, + "grad_norm": 0.49316903948783875, + "learning_rate": 8.031990577936398e-05, + "loss": 1.5899, + "step": 5463 + }, + { + "epoch": 0.304553815283429, + "grad_norm": 0.5170844197273254, + "learning_rate": 8.031282499543769e-05, + "loss": 1.6575, + "step": 5464 + }, + { + "epoch": 0.30460955353659214, + "grad_norm": 0.5051673650741577, + "learning_rate": 8.030574325016532e-05, + "loss": 1.5878, + "step": 5465 + }, + { + "epoch": 0.3046652917897553, + "grad_norm": 0.493794709444046, + "learning_rate": 8.029866054377148e-05, + "loss": 1.5681, + "step": 5466 + }, + { + "epoch": 0.30472103004291845, + "grad_norm": 0.5372213125228882, + "learning_rate": 8.029157687648077e-05, + "loss": 1.6819, + "step": 5467 + }, + { + "epoch": 0.3047767682960816, + "grad_norm": 0.559104323387146, + "learning_rate": 8.028449224851785e-05, + "loss": 1.8688, + "step": 5468 + }, + { + "epoch": 0.30483250654924476, + "grad_norm": 0.558225691318512, + "learning_rate": 8.027740666010741e-05, + "loss": 1.7629, + "step": 5469 + }, + { + "epoch": 0.3048882448024079, + "grad_norm": 0.511577844619751, + "learning_rate": 8.027032011147417e-05, + "loss": 1.594, + "step": 5470 + }, + { + "epoch": 0.304943983055571, + "grad_norm": 0.5308223962783813, + "learning_rate": 8.026323260284286e-05, + "loss": 1.6677, + "step": 5471 + }, + { + "epoch": 0.3049997213087342, + "grad_norm": 0.5670995712280273, + "learning_rate": 8.025614413443824e-05, + "loss": 1.5382, + "step": 5472 + }, + { + "epoch": 0.30505545956189734, + "grad_norm": 0.553377091884613, + "learning_rate": 8.024905470648516e-05, + "loss": 1.59, + "step": 5473 + }, + { + "epoch": 0.30511119781506046, + "grad_norm": 0.5147939324378967, + "learning_rate": 8.024196431920841e-05, + "loss": 1.6797, + "step": 5474 + }, + { + "epoch": 0.30516693606822365, + "grad_norm": 0.5732524394989014, + "learning_rate": 8.023487297283289e-05, + "loss": 1.7703, + "step": 5475 + }, + { + "epoch": 0.3052226743213868, + "grad_norm": 0.5088878870010376, + "learning_rate": 8.022778066758348e-05, + "loss": 1.5239, + "step": 5476 + }, + { + "epoch": 0.3052784125745499, + "grad_norm": 0.5896703600883484, + "learning_rate": 8.02206874036851e-05, + "loss": 1.8356, + "step": 5477 + }, + { + "epoch": 0.30533415082771304, + "grad_norm": 0.5752948522567749, + "learning_rate": 8.021359318136273e-05, + "loss": 1.8527, + "step": 5478 + }, + { + "epoch": 0.3053898890808762, + "grad_norm": 0.5507591366767883, + "learning_rate": 8.020649800084133e-05, + "loss": 1.7682, + "step": 5479 + }, + { + "epoch": 0.30544562733403935, + "grad_norm": 0.5891523957252502, + "learning_rate": 8.019940186234591e-05, + "loss": 1.7112, + "step": 5480 + }, + { + "epoch": 0.3055013655872025, + "grad_norm": 0.5745503306388855, + "learning_rate": 8.019230476610155e-05, + "loss": 1.7824, + "step": 5481 + }, + { + "epoch": 0.30555710384036566, + "grad_norm": 0.6154142022132874, + "learning_rate": 8.018520671233333e-05, + "loss": 1.8217, + "step": 5482 + }, + { + "epoch": 0.3056128420935288, + "grad_norm": 0.5336470603942871, + "learning_rate": 8.017810770126633e-05, + "loss": 1.572, + "step": 5483 + }, + { + "epoch": 0.3056685803466919, + "grad_norm": 0.6083388328552246, + "learning_rate": 8.017100773312572e-05, + "loss": 1.8889, + "step": 5484 + }, + { + "epoch": 0.3057243185998551, + "grad_norm": 0.5398688912391663, + "learning_rate": 8.016390680813664e-05, + "loss": 1.8318, + "step": 5485 + }, + { + "epoch": 0.30578005685301823, + "grad_norm": 0.5180187225341797, + "learning_rate": 8.015680492652432e-05, + "loss": 1.4898, + "step": 5486 + }, + { + "epoch": 0.30583579510618136, + "grad_norm": 0.5112860798835754, + "learning_rate": 8.014970208851395e-05, + "loss": 1.622, + "step": 5487 + }, + { + "epoch": 0.3058915333593445, + "grad_norm": 0.5450818538665771, + "learning_rate": 8.014259829433082e-05, + "loss": 1.5932, + "step": 5488 + }, + { + "epoch": 0.3059472716125077, + "grad_norm": 0.5598384737968445, + "learning_rate": 8.013549354420022e-05, + "loss": 1.7663, + "step": 5489 + }, + { + "epoch": 0.3060030098656708, + "grad_norm": 0.574329137802124, + "learning_rate": 8.012838783834749e-05, + "loss": 1.7812, + "step": 5490 + }, + { + "epoch": 0.30605874811883393, + "grad_norm": 0.5636276006698608, + "learning_rate": 8.012128117699793e-05, + "loss": 1.8031, + "step": 5491 + }, + { + "epoch": 0.3061144863719971, + "grad_norm": 0.5229976177215576, + "learning_rate": 8.011417356037697e-05, + "loss": 1.7483, + "step": 5492 + }, + { + "epoch": 0.30617022462516025, + "grad_norm": 0.5263829231262207, + "learning_rate": 8.010706498870997e-05, + "loss": 1.6449, + "step": 5493 + }, + { + "epoch": 0.3062259628783234, + "grad_norm": 0.5461215376853943, + "learning_rate": 8.009995546222242e-05, + "loss": 1.5837, + "step": 5494 + }, + { + "epoch": 0.30628170113148656, + "grad_norm": 0.541483998298645, + "learning_rate": 8.009284498113979e-05, + "loss": 1.7239, + "step": 5495 + }, + { + "epoch": 0.3063374393846497, + "grad_norm": 0.540389358997345, + "learning_rate": 8.008573354568756e-05, + "loss": 1.6928, + "step": 5496 + }, + { + "epoch": 0.3063931776378128, + "grad_norm": 0.550672709941864, + "learning_rate": 8.007862115609129e-05, + "loss": 1.7299, + "step": 5497 + }, + { + "epoch": 0.306448915890976, + "grad_norm": 0.532590389251709, + "learning_rate": 8.007150781257651e-05, + "loss": 1.6299, + "step": 5498 + }, + { + "epoch": 0.30650465414413913, + "grad_norm": 0.5489155650138855, + "learning_rate": 8.006439351536883e-05, + "loss": 1.6814, + "step": 5499 + }, + { + "epoch": 0.30656039239730226, + "grad_norm": 0.5809459090232849, + "learning_rate": 8.005727826469389e-05, + "loss": 1.7617, + "step": 5500 + }, + { + "epoch": 0.3066161306504654, + "grad_norm": 0.5688945055007935, + "learning_rate": 8.005016206077731e-05, + "loss": 1.913, + "step": 5501 + }, + { + "epoch": 0.3066718689036286, + "grad_norm": 0.5430113673210144, + "learning_rate": 8.004304490384482e-05, + "loss": 1.6782, + "step": 5502 + }, + { + "epoch": 0.3067276071567917, + "grad_norm": 0.5550969243049622, + "learning_rate": 8.003592679412208e-05, + "loss": 1.4965, + "step": 5503 + }, + { + "epoch": 0.30678334540995483, + "grad_norm": 0.5173535943031311, + "learning_rate": 8.00288077318349e-05, + "loss": 1.4724, + "step": 5504 + }, + { + "epoch": 0.306839083663118, + "grad_norm": 0.5464041233062744, + "learning_rate": 8.0021687717209e-05, + "loss": 1.6722, + "step": 5505 + }, + { + "epoch": 0.30689482191628115, + "grad_norm": 0.5555015206336975, + "learning_rate": 8.001456675047019e-05, + "loss": 1.8088, + "step": 5506 + }, + { + "epoch": 0.3069505601694443, + "grad_norm": 0.5883082747459412, + "learning_rate": 8.000744483184433e-05, + "loss": 1.5916, + "step": 5507 + }, + { + "epoch": 0.30700629842260746, + "grad_norm": 0.5937238931655884, + "learning_rate": 8.000032196155726e-05, + "loss": 1.8253, + "step": 5508 + }, + { + "epoch": 0.3070620366757706, + "grad_norm": 0.5752248764038086, + "learning_rate": 7.999319813983492e-05, + "loss": 1.7183, + "step": 5509 + }, + { + "epoch": 0.3071177749289337, + "grad_norm": 0.5927345156669617, + "learning_rate": 7.99860733669032e-05, + "loss": 1.8415, + "step": 5510 + }, + { + "epoch": 0.30717351318209685, + "grad_norm": 0.597845196723938, + "learning_rate": 7.997894764298806e-05, + "loss": 1.8575, + "step": 5511 + }, + { + "epoch": 0.30722925143526003, + "grad_norm": 0.5484491586685181, + "learning_rate": 7.997182096831548e-05, + "loss": 1.6398, + "step": 5512 + }, + { + "epoch": 0.30728498968842316, + "grad_norm": 0.5977261662483215, + "learning_rate": 7.99646933431115e-05, + "loss": 2.0446, + "step": 5513 + }, + { + "epoch": 0.3073407279415863, + "grad_norm": 0.5897913575172424, + "learning_rate": 7.995756476760214e-05, + "loss": 1.7335, + "step": 5514 + }, + { + "epoch": 0.3073964661947495, + "grad_norm": 0.5303786396980286, + "learning_rate": 7.995043524201351e-05, + "loss": 1.6374, + "step": 5515 + }, + { + "epoch": 0.3074522044479126, + "grad_norm": 0.6054732799530029, + "learning_rate": 7.994330476657168e-05, + "loss": 1.8542, + "step": 5516 + }, + { + "epoch": 0.30750794270107573, + "grad_norm": 0.5825492739677429, + "learning_rate": 7.993617334150282e-05, + "loss": 1.74, + "step": 5517 + }, + { + "epoch": 0.3075636809542389, + "grad_norm": 0.5496809482574463, + "learning_rate": 7.992904096703307e-05, + "loss": 1.6844, + "step": 5518 + }, + { + "epoch": 0.30761941920740205, + "grad_norm": 0.5574871301651001, + "learning_rate": 7.992190764338864e-05, + "loss": 1.7397, + "step": 5519 + }, + { + "epoch": 0.3076751574605652, + "grad_norm": 0.5654902458190918, + "learning_rate": 7.991477337079576e-05, + "loss": 1.7361, + "step": 5520 + }, + { + "epoch": 0.30773089571372836, + "grad_norm": 0.5748382806777954, + "learning_rate": 7.990763814948068e-05, + "loss": 1.8819, + "step": 5521 + }, + { + "epoch": 0.3077866339668915, + "grad_norm": 0.5120726823806763, + "learning_rate": 7.99005019796697e-05, + "loss": 1.5405, + "step": 5522 + }, + { + "epoch": 0.3078423722200546, + "grad_norm": 0.5529910326004028, + "learning_rate": 7.989336486158912e-05, + "loss": 1.6712, + "step": 5523 + }, + { + "epoch": 0.30789811047321775, + "grad_norm": 0.5775067210197449, + "learning_rate": 7.988622679546529e-05, + "loss": 2.0319, + "step": 5524 + }, + { + "epoch": 0.30795384872638093, + "grad_norm": 0.5432143211364746, + "learning_rate": 7.987908778152462e-05, + "loss": 1.5891, + "step": 5525 + }, + { + "epoch": 0.30800958697954406, + "grad_norm": 0.5764423608779907, + "learning_rate": 7.987194781999345e-05, + "loss": 1.865, + "step": 5526 + }, + { + "epoch": 0.3080653252327072, + "grad_norm": 0.5256220698356628, + "learning_rate": 7.98648069110983e-05, + "loss": 1.5777, + "step": 5527 + }, + { + "epoch": 0.3081210634858704, + "grad_norm": 0.5597642064094543, + "learning_rate": 7.985766505506559e-05, + "loss": 1.8957, + "step": 5528 + }, + { + "epoch": 0.3081768017390335, + "grad_norm": 0.5411173701286316, + "learning_rate": 7.985052225212181e-05, + "loss": 1.7575, + "step": 5529 + }, + { + "epoch": 0.30823253999219663, + "grad_norm": 0.5252230763435364, + "learning_rate": 7.984337850249352e-05, + "loss": 1.7377, + "step": 5530 + }, + { + "epoch": 0.3082882782453598, + "grad_norm": 0.5985997915267944, + "learning_rate": 7.983623380640729e-05, + "loss": 1.7941, + "step": 5531 + }, + { + "epoch": 0.30834401649852294, + "grad_norm": 0.5696808099746704, + "learning_rate": 7.982908816408963e-05, + "loss": 1.8425, + "step": 5532 + }, + { + "epoch": 0.3083997547516861, + "grad_norm": 0.5184767246246338, + "learning_rate": 7.982194157576723e-05, + "loss": 1.6765, + "step": 5533 + }, + { + "epoch": 0.3084554930048492, + "grad_norm": 0.5509563088417053, + "learning_rate": 7.981479404166672e-05, + "loss": 1.8554, + "step": 5534 + }, + { + "epoch": 0.3085112312580124, + "grad_norm": 0.5477381944656372, + "learning_rate": 7.980764556201478e-05, + "loss": 1.6513, + "step": 5535 + }, + { + "epoch": 0.3085669695111755, + "grad_norm": 0.5575202107429504, + "learning_rate": 7.980049613703811e-05, + "loss": 1.7565, + "step": 5536 + }, + { + "epoch": 0.30862270776433864, + "grad_norm": 0.578071117401123, + "learning_rate": 7.979334576696344e-05, + "loss": 1.6711, + "step": 5537 + }, + { + "epoch": 0.30867844601750183, + "grad_norm": 0.5293973684310913, + "learning_rate": 7.978619445201756e-05, + "loss": 1.8865, + "step": 5538 + }, + { + "epoch": 0.30873418427066496, + "grad_norm": 0.5793629288673401, + "learning_rate": 7.977904219242724e-05, + "loss": 1.9338, + "step": 5539 + }, + { + "epoch": 0.3087899225238281, + "grad_norm": 0.5701123476028442, + "learning_rate": 7.977188898841936e-05, + "loss": 1.778, + "step": 5540 + }, + { + "epoch": 0.30884566077699127, + "grad_norm": 0.5166484117507935, + "learning_rate": 7.976473484022071e-05, + "loss": 1.6528, + "step": 5541 + }, + { + "epoch": 0.3089013990301544, + "grad_norm": 0.5501734018325806, + "learning_rate": 7.975757974805824e-05, + "loss": 1.6939, + "step": 5542 + }, + { + "epoch": 0.30895713728331753, + "grad_norm": 0.5325387716293335, + "learning_rate": 7.975042371215881e-05, + "loss": 1.5085, + "step": 5543 + }, + { + "epoch": 0.3090128755364807, + "grad_norm": 0.5717397928237915, + "learning_rate": 7.974326673274943e-05, + "loss": 1.7745, + "step": 5544 + }, + { + "epoch": 0.30906861378964384, + "grad_norm": 0.5344177484512329, + "learning_rate": 7.973610881005702e-05, + "loss": 1.6344, + "step": 5545 + }, + { + "epoch": 0.30912435204280697, + "grad_norm": 0.5647115707397461, + "learning_rate": 7.972894994430862e-05, + "loss": 1.8173, + "step": 5546 + }, + { + "epoch": 0.3091800902959701, + "grad_norm": 0.5356699824333191, + "learning_rate": 7.972179013573125e-05, + "loss": 1.6173, + "step": 5547 + }, + { + "epoch": 0.3092358285491333, + "grad_norm": 0.5651494860649109, + "learning_rate": 7.971462938455199e-05, + "loss": 1.5781, + "step": 5548 + }, + { + "epoch": 0.3092915668022964, + "grad_norm": 0.5726121664047241, + "learning_rate": 7.970746769099795e-05, + "loss": 1.5528, + "step": 5549 + }, + { + "epoch": 0.30934730505545954, + "grad_norm": 0.6116449236869812, + "learning_rate": 7.970030505529624e-05, + "loss": 1.9145, + "step": 5550 + }, + { + "epoch": 0.3094030433086227, + "grad_norm": 0.5738492012023926, + "learning_rate": 7.969314147767399e-05, + "loss": 1.7875, + "step": 5551 + }, + { + "epoch": 0.30945878156178586, + "grad_norm": 0.5894981026649475, + "learning_rate": 7.968597695835844e-05, + "loss": 1.5879, + "step": 5552 + }, + { + "epoch": 0.309514519814949, + "grad_norm": 0.5126131772994995, + "learning_rate": 7.967881149757678e-05, + "loss": 1.6178, + "step": 5553 + }, + { + "epoch": 0.30957025806811217, + "grad_norm": 0.5616469979286194, + "learning_rate": 7.967164509555624e-05, + "loss": 1.7701, + "step": 5554 + }, + { + "epoch": 0.3096259963212753, + "grad_norm": 0.5041468739509583, + "learning_rate": 7.966447775252415e-05, + "loss": 1.5632, + "step": 5555 + }, + { + "epoch": 0.3096817345744384, + "grad_norm": 0.5093483328819275, + "learning_rate": 7.965730946870775e-05, + "loss": 1.7161, + "step": 5556 + }, + { + "epoch": 0.30973747282760156, + "grad_norm": 0.6104699373245239, + "learning_rate": 7.965014024433443e-05, + "loss": 1.7959, + "step": 5557 + }, + { + "epoch": 0.30979321108076474, + "grad_norm": 0.5576456189155579, + "learning_rate": 7.964297007963151e-05, + "loss": 1.8631, + "step": 5558 + }, + { + "epoch": 0.30984894933392787, + "grad_norm": 0.5558076500892639, + "learning_rate": 7.963579897482642e-05, + "loss": 1.7503, + "step": 5559 + }, + { + "epoch": 0.309904687587091, + "grad_norm": 0.5433835983276367, + "learning_rate": 7.96286269301466e-05, + "loss": 1.6935, + "step": 5560 + }, + { + "epoch": 0.3099604258402542, + "grad_norm": 0.5542037487030029, + "learning_rate": 7.962145394581944e-05, + "loss": 1.7342, + "step": 5561 + }, + { + "epoch": 0.3100161640934173, + "grad_norm": 0.5680848360061646, + "learning_rate": 7.961428002207249e-05, + "loss": 1.6875, + "step": 5562 + }, + { + "epoch": 0.31007190234658044, + "grad_norm": 0.5349116921424866, + "learning_rate": 7.960710515913323e-05, + "loss": 1.6991, + "step": 5563 + }, + { + "epoch": 0.3101276405997436, + "grad_norm": 0.5729091167449951, + "learning_rate": 7.959992935722924e-05, + "loss": 1.8622, + "step": 5564 + }, + { + "epoch": 0.31018337885290675, + "grad_norm": 0.558594286441803, + "learning_rate": 7.959275261658804e-05, + "loss": 1.8244, + "step": 5565 + }, + { + "epoch": 0.3102391171060699, + "grad_norm": 0.5720626711845398, + "learning_rate": 7.958557493743728e-05, + "loss": 1.796, + "step": 5566 + }, + { + "epoch": 0.31029485535923307, + "grad_norm": 0.7089996933937073, + "learning_rate": 7.957839632000457e-05, + "loss": 2.2928, + "step": 5567 + }, + { + "epoch": 0.3103505936123962, + "grad_norm": 0.51308274269104, + "learning_rate": 7.957121676451759e-05, + "loss": 1.5466, + "step": 5568 + }, + { + "epoch": 0.3104063318655593, + "grad_norm": 0.5389419794082642, + "learning_rate": 7.956403627120403e-05, + "loss": 1.7847, + "step": 5569 + }, + { + "epoch": 0.31046207011872246, + "grad_norm": 0.5362538695335388, + "learning_rate": 7.95568548402916e-05, + "loss": 1.752, + "step": 5570 + }, + { + "epoch": 0.31051780837188564, + "grad_norm": 0.5565882921218872, + "learning_rate": 7.954967247200806e-05, + "loss": 1.7436, + "step": 5571 + }, + { + "epoch": 0.31057354662504877, + "grad_norm": 0.5700491070747375, + "learning_rate": 7.95424891665812e-05, + "loss": 1.3893, + "step": 5572 + }, + { + "epoch": 0.3106292848782119, + "grad_norm": 0.5634492635726929, + "learning_rate": 7.953530492423884e-05, + "loss": 1.5228, + "step": 5573 + }, + { + "epoch": 0.3106850231313751, + "grad_norm": 0.5454849004745483, + "learning_rate": 7.95281197452088e-05, + "loss": 1.7454, + "step": 5574 + }, + { + "epoch": 0.3107407613845382, + "grad_norm": 0.5382822751998901, + "learning_rate": 7.952093362971897e-05, + "loss": 1.6264, + "step": 5575 + }, + { + "epoch": 0.31079649963770134, + "grad_norm": 0.5650563836097717, + "learning_rate": 7.951374657799724e-05, + "loss": 1.4175, + "step": 5576 + }, + { + "epoch": 0.3108522378908645, + "grad_norm": 0.570775032043457, + "learning_rate": 7.950655859027154e-05, + "loss": 1.6686, + "step": 5577 + }, + { + "epoch": 0.31090797614402765, + "grad_norm": 0.5498449206352234, + "learning_rate": 7.949936966676984e-05, + "loss": 1.7351, + "step": 5578 + }, + { + "epoch": 0.3109637143971908, + "grad_norm": 0.6256487369537354, + "learning_rate": 7.949217980772012e-05, + "loss": 1.9914, + "step": 5579 + }, + { + "epoch": 0.3110194526503539, + "grad_norm": 0.6062150001525879, + "learning_rate": 7.948498901335042e-05, + "loss": 1.9362, + "step": 5580 + }, + { + "epoch": 0.3110751909035171, + "grad_norm": 0.5351932048797607, + "learning_rate": 7.947779728388878e-05, + "loss": 1.6922, + "step": 5581 + }, + { + "epoch": 0.3111309291566802, + "grad_norm": 0.6049745678901672, + "learning_rate": 7.947060461956329e-05, + "loss": 2.146, + "step": 5582 + }, + { + "epoch": 0.31118666740984335, + "grad_norm": 0.5465789437294006, + "learning_rate": 7.946341102060202e-05, + "loss": 1.7858, + "step": 5583 + }, + { + "epoch": 0.31124240566300654, + "grad_norm": 0.5127213597297668, + "learning_rate": 7.945621648723313e-05, + "loss": 1.6921, + "step": 5584 + }, + { + "epoch": 0.31129814391616967, + "grad_norm": 0.5576222538948059, + "learning_rate": 7.944902101968482e-05, + "loss": 1.7601, + "step": 5585 + }, + { + "epoch": 0.3113538821693328, + "grad_norm": 0.5145538449287415, + "learning_rate": 7.944182461818525e-05, + "loss": 1.6861, + "step": 5586 + }, + { + "epoch": 0.311409620422496, + "grad_norm": 0.5060127973556519, + "learning_rate": 7.943462728296266e-05, + "loss": 1.4954, + "step": 5587 + }, + { + "epoch": 0.3114653586756591, + "grad_norm": 0.5226243138313293, + "learning_rate": 7.942742901424531e-05, + "loss": 1.7086, + "step": 5588 + }, + { + "epoch": 0.31152109692882224, + "grad_norm": 0.5711196064949036, + "learning_rate": 7.942022981226149e-05, + "loss": 1.7788, + "step": 5589 + }, + { + "epoch": 0.3115768351819854, + "grad_norm": 0.511813759803772, + "learning_rate": 7.941302967723951e-05, + "loss": 1.3316, + "step": 5590 + }, + { + "epoch": 0.31163257343514855, + "grad_norm": 0.5399052500724792, + "learning_rate": 7.940582860940771e-05, + "loss": 1.6683, + "step": 5591 + }, + { + "epoch": 0.3116883116883117, + "grad_norm": 0.5305676460266113, + "learning_rate": 7.939862660899448e-05, + "loss": 1.7344, + "step": 5592 + }, + { + "epoch": 0.3117440499414748, + "grad_norm": 0.5254833698272705, + "learning_rate": 7.939142367622823e-05, + "loss": 1.5524, + "step": 5593 + }, + { + "epoch": 0.311799788194638, + "grad_norm": 0.5858429074287415, + "learning_rate": 7.938421981133738e-05, + "loss": 1.7415, + "step": 5594 + }, + { + "epoch": 0.3118555264478011, + "grad_norm": 0.6082313656806946, + "learning_rate": 7.937701501455039e-05, + "loss": 1.5333, + "step": 5595 + }, + { + "epoch": 0.31191126470096425, + "grad_norm": 0.5757048726081848, + "learning_rate": 7.936980928609577e-05, + "loss": 1.8723, + "step": 5596 + }, + { + "epoch": 0.31196700295412744, + "grad_norm": 0.6089504957199097, + "learning_rate": 7.936260262620205e-05, + "loss": 1.8915, + "step": 5597 + }, + { + "epoch": 0.31202274120729057, + "grad_norm": 0.588326096534729, + "learning_rate": 7.935539503509775e-05, + "loss": 1.8353, + "step": 5598 + }, + { + "epoch": 0.3120784794604537, + "grad_norm": 0.5930234789848328, + "learning_rate": 7.934818651301148e-05, + "loss": 1.832, + "step": 5599 + }, + { + "epoch": 0.3121342177136169, + "grad_norm": 0.5394973158836365, + "learning_rate": 7.934097706017185e-05, + "loss": 1.7301, + "step": 5600 + }, + { + "epoch": 0.31218995596678, + "grad_norm": 0.5147609114646912, + "learning_rate": 7.93337666768075e-05, + "loss": 1.7095, + "step": 5601 + }, + { + "epoch": 0.31224569421994314, + "grad_norm": 0.5531661510467529, + "learning_rate": 7.932655536314708e-05, + "loss": 1.6071, + "step": 5602 + }, + { + "epoch": 0.31230143247310627, + "grad_norm": 0.5388891696929932, + "learning_rate": 7.931934311941933e-05, + "loss": 1.5759, + "step": 5603 + }, + { + "epoch": 0.31235717072626945, + "grad_norm": 0.5236558318138123, + "learning_rate": 7.931212994585294e-05, + "loss": 1.5492, + "step": 5604 + }, + { + "epoch": 0.3124129089794326, + "grad_norm": 0.6088682413101196, + "learning_rate": 7.93049158426767e-05, + "loss": 1.7768, + "step": 5605 + }, + { + "epoch": 0.3124686472325957, + "grad_norm": 0.5254512429237366, + "learning_rate": 7.92977008101194e-05, + "loss": 1.6003, + "step": 5606 + }, + { + "epoch": 0.3125243854857589, + "grad_norm": 0.5747987031936646, + "learning_rate": 7.929048484840984e-05, + "loss": 1.7666, + "step": 5607 + }, + { + "epoch": 0.312580123738922, + "grad_norm": 0.5682463645935059, + "learning_rate": 7.928326795777688e-05, + "loss": 1.7861, + "step": 5608 + }, + { + "epoch": 0.31263586199208515, + "grad_norm": 0.5339683890342712, + "learning_rate": 7.927605013844939e-05, + "loss": 1.614, + "step": 5609 + }, + { + "epoch": 0.31269160024524834, + "grad_norm": 0.5913909673690796, + "learning_rate": 7.926883139065627e-05, + "loss": 1.7949, + "step": 5610 + }, + { + "epoch": 0.31274733849841146, + "grad_norm": 0.5656397342681885, + "learning_rate": 7.926161171462648e-05, + "loss": 1.8147, + "step": 5611 + }, + { + "epoch": 0.3128030767515746, + "grad_norm": 0.5707045197486877, + "learning_rate": 7.925439111058897e-05, + "loss": 1.7117, + "step": 5612 + }, + { + "epoch": 0.3128588150047378, + "grad_norm": 0.5682026743888855, + "learning_rate": 7.924716957877275e-05, + "loss": 1.6873, + "step": 5613 + }, + { + "epoch": 0.3129145532579009, + "grad_norm": 0.6239393353462219, + "learning_rate": 7.92399471194068e-05, + "loss": 2.136, + "step": 5614 + }, + { + "epoch": 0.31297029151106404, + "grad_norm": 0.5405849814414978, + "learning_rate": 7.923272373272024e-05, + "loss": 1.7105, + "step": 5615 + }, + { + "epoch": 0.31302602976422716, + "grad_norm": 0.5093609094619751, + "learning_rate": 7.922549941894212e-05, + "loss": 1.7117, + "step": 5616 + }, + { + "epoch": 0.31308176801739035, + "grad_norm": 0.5615028738975525, + "learning_rate": 7.921827417830155e-05, + "loss": 1.7621, + "step": 5617 + }, + { + "epoch": 0.3131375062705535, + "grad_norm": 0.5841954946517944, + "learning_rate": 7.921104801102766e-05, + "loss": 1.7155, + "step": 5618 + }, + { + "epoch": 0.3131932445237166, + "grad_norm": 0.5684096217155457, + "learning_rate": 7.920382091734966e-05, + "loss": 1.5615, + "step": 5619 + }, + { + "epoch": 0.3132489827768798, + "grad_norm": 0.5647116303443909, + "learning_rate": 7.919659289749673e-05, + "loss": 1.6964, + "step": 5620 + }, + { + "epoch": 0.3133047210300429, + "grad_norm": 0.5479496121406555, + "learning_rate": 7.918936395169809e-05, + "loss": 1.6701, + "step": 5621 + }, + { + "epoch": 0.31336045928320605, + "grad_norm": 0.5465035438537598, + "learning_rate": 7.918213408018302e-05, + "loss": 1.8372, + "step": 5622 + }, + { + "epoch": 0.31341619753636923, + "grad_norm": 0.5440232157707214, + "learning_rate": 7.91749032831808e-05, + "loss": 1.6181, + "step": 5623 + }, + { + "epoch": 0.31347193578953236, + "grad_norm": 0.5956066846847534, + "learning_rate": 7.916767156092073e-05, + "loss": 1.8816, + "step": 5624 + }, + { + "epoch": 0.3135276740426955, + "grad_norm": 0.4970141053199768, + "learning_rate": 7.916043891363221e-05, + "loss": 1.331, + "step": 5625 + }, + { + "epoch": 0.3135834122958586, + "grad_norm": 0.5314142107963562, + "learning_rate": 7.915320534154457e-05, + "loss": 1.7526, + "step": 5626 + }, + { + "epoch": 0.3136391505490218, + "grad_norm": 0.5765748620033264, + "learning_rate": 7.914597084488723e-05, + "loss": 1.7204, + "step": 5627 + }, + { + "epoch": 0.31369488880218493, + "grad_norm": 0.5975958704948425, + "learning_rate": 7.913873542388963e-05, + "loss": 1.8833, + "step": 5628 + }, + { + "epoch": 0.31375062705534806, + "grad_norm": 0.5788082480430603, + "learning_rate": 7.913149907878123e-05, + "loss": 1.9049, + "step": 5629 + }, + { + "epoch": 0.31380636530851125, + "grad_norm": 0.6019555330276489, + "learning_rate": 7.912426180979152e-05, + "loss": 2.005, + "step": 5630 + }, + { + "epoch": 0.3138621035616744, + "grad_norm": 0.5763736963272095, + "learning_rate": 7.911702361715006e-05, + "loss": 1.7476, + "step": 5631 + }, + { + "epoch": 0.3139178418148375, + "grad_norm": 0.5758547782897949, + "learning_rate": 7.910978450108634e-05, + "loss": 1.69, + "step": 5632 + }, + { + "epoch": 0.3139735800680007, + "grad_norm": 0.5762767791748047, + "learning_rate": 7.910254446183e-05, + "loss": 1.7354, + "step": 5633 + }, + { + "epoch": 0.3140293183211638, + "grad_norm": 0.5475091338157654, + "learning_rate": 7.909530349961062e-05, + "loss": 1.803, + "step": 5634 + }, + { + "epoch": 0.31408505657432695, + "grad_norm": 0.5797522664070129, + "learning_rate": 7.908806161465785e-05, + "loss": 1.8425, + "step": 5635 + }, + { + "epoch": 0.31414079482749013, + "grad_norm": 0.5494913458824158, + "learning_rate": 7.908081880720137e-05, + "loss": 1.7041, + "step": 5636 + }, + { + "epoch": 0.31419653308065326, + "grad_norm": 0.5253703594207764, + "learning_rate": 7.907357507747087e-05, + "loss": 1.5982, + "step": 5637 + }, + { + "epoch": 0.3142522713338164, + "grad_norm": 0.5663535594940186, + "learning_rate": 7.906633042569607e-05, + "loss": 1.6506, + "step": 5638 + }, + { + "epoch": 0.3143080095869795, + "grad_norm": 0.5768305659294128, + "learning_rate": 7.905908485210674e-05, + "loss": 1.675, + "step": 5639 + }, + { + "epoch": 0.3143637478401427, + "grad_norm": 0.5730108022689819, + "learning_rate": 7.905183835693266e-05, + "loss": 1.6702, + "step": 5640 + }, + { + "epoch": 0.31441948609330583, + "grad_norm": 0.5377948880195618, + "learning_rate": 7.904459094040366e-05, + "loss": 1.8156, + "step": 5641 + }, + { + "epoch": 0.31447522434646896, + "grad_norm": 0.5925690531730652, + "learning_rate": 7.903734260274958e-05, + "loss": 1.8198, + "step": 5642 + }, + { + "epoch": 0.31453096259963215, + "grad_norm": 0.5221425294876099, + "learning_rate": 7.903009334420027e-05, + "loss": 1.6291, + "step": 5643 + }, + { + "epoch": 0.3145867008527953, + "grad_norm": 0.5379535555839539, + "learning_rate": 7.902284316498567e-05, + "loss": 1.6026, + "step": 5644 + }, + { + "epoch": 0.3146424391059584, + "grad_norm": 0.5477253198623657, + "learning_rate": 7.901559206533571e-05, + "loss": 1.9096, + "step": 5645 + }, + { + "epoch": 0.3146981773591216, + "grad_norm": 0.6306549310684204, + "learning_rate": 7.900834004548034e-05, + "loss": 1.9637, + "step": 5646 + }, + { + "epoch": 0.3147539156122847, + "grad_norm": 0.5738115906715393, + "learning_rate": 7.900108710564954e-05, + "loss": 1.8217, + "step": 5647 + }, + { + "epoch": 0.31480965386544785, + "grad_norm": 0.5737825036048889, + "learning_rate": 7.899383324607336e-05, + "loss": 1.7018, + "step": 5648 + }, + { + "epoch": 0.314865392118611, + "grad_norm": 0.5575332641601562, + "learning_rate": 7.898657846698183e-05, + "loss": 1.823, + "step": 5649 + }, + { + "epoch": 0.31492113037177416, + "grad_norm": 0.5665508508682251, + "learning_rate": 7.897932276860502e-05, + "loss": 1.8531, + "step": 5650 + }, + { + "epoch": 0.3149768686249373, + "grad_norm": 0.6147223711013794, + "learning_rate": 7.897206615117307e-05, + "loss": 1.8, + "step": 5651 + }, + { + "epoch": 0.3150326068781004, + "grad_norm": 0.5605811476707458, + "learning_rate": 7.89648086149161e-05, + "loss": 1.8554, + "step": 5652 + }, + { + "epoch": 0.3150883451312636, + "grad_norm": 0.5749962329864502, + "learning_rate": 7.895755016006427e-05, + "loss": 1.9814, + "step": 5653 + }, + { + "epoch": 0.31514408338442673, + "grad_norm": 0.6655054688453674, + "learning_rate": 7.895029078684779e-05, + "loss": 1.6895, + "step": 5654 + }, + { + "epoch": 0.31519982163758986, + "grad_norm": 0.5131604671478271, + "learning_rate": 7.894303049549687e-05, + "loss": 1.4731, + "step": 5655 + }, + { + "epoch": 0.31525555989075305, + "grad_norm": 0.5364745855331421, + "learning_rate": 7.893576928624178e-05, + "loss": 1.819, + "step": 5656 + }, + { + "epoch": 0.3153112981439162, + "grad_norm": 0.563586413860321, + "learning_rate": 7.89285071593128e-05, + "loss": 1.6023, + "step": 5657 + }, + { + "epoch": 0.3153670363970793, + "grad_norm": 0.5618447065353394, + "learning_rate": 7.892124411494022e-05, + "loss": 1.5903, + "step": 5658 + }, + { + "epoch": 0.3154227746502425, + "grad_norm": 0.5073031783103943, + "learning_rate": 7.891398015335442e-05, + "loss": 1.646, + "step": 5659 + }, + { + "epoch": 0.3154785129034056, + "grad_norm": 0.5081502795219421, + "learning_rate": 7.890671527478574e-05, + "loss": 1.3751, + "step": 5660 + }, + { + "epoch": 0.31553425115656875, + "grad_norm": 0.524069607257843, + "learning_rate": 7.88994494794646e-05, + "loss": 1.6491, + "step": 5661 + }, + { + "epoch": 0.3155899894097319, + "grad_norm": 0.5874504446983337, + "learning_rate": 7.88921827676214e-05, + "loss": 1.5753, + "step": 5662 + }, + { + "epoch": 0.31564572766289506, + "grad_norm": 0.5709517002105713, + "learning_rate": 7.888491513948661e-05, + "loss": 1.8023, + "step": 5663 + }, + { + "epoch": 0.3157014659160582, + "grad_norm": 0.5294995903968811, + "learning_rate": 7.887764659529073e-05, + "loss": 1.6754, + "step": 5664 + }, + { + "epoch": 0.3157572041692213, + "grad_norm": 0.5117160677909851, + "learning_rate": 7.887037713526428e-05, + "loss": 1.6262, + "step": 5665 + }, + { + "epoch": 0.3158129424223845, + "grad_norm": 0.49994394183158875, + "learning_rate": 7.88631067596378e-05, + "loss": 1.5649, + "step": 5666 + }, + { + "epoch": 0.31586868067554763, + "grad_norm": 0.486306756734848, + "learning_rate": 7.885583546864184e-05, + "loss": 1.4968, + "step": 5667 + }, + { + "epoch": 0.31592441892871076, + "grad_norm": 0.5242376327514648, + "learning_rate": 7.884856326250703e-05, + "loss": 1.5559, + "step": 5668 + }, + { + "epoch": 0.31598015718187394, + "grad_norm": 0.5692494511604309, + "learning_rate": 7.884129014146397e-05, + "loss": 1.8384, + "step": 5669 + }, + { + "epoch": 0.3160358954350371, + "grad_norm": 0.5784143209457397, + "learning_rate": 7.883401610574336e-05, + "loss": 1.9506, + "step": 5670 + }, + { + "epoch": 0.3160916336882002, + "grad_norm": 0.5659399032592773, + "learning_rate": 7.882674115557587e-05, + "loss": 1.6864, + "step": 5671 + }, + { + "epoch": 0.31614737194136333, + "grad_norm": 0.6336827278137207, + "learning_rate": 7.881946529119223e-05, + "loss": 1.9635, + "step": 5672 + }, + { + "epoch": 0.3162031101945265, + "grad_norm": 0.5327314734458923, + "learning_rate": 7.881218851282317e-05, + "loss": 1.5806, + "step": 5673 + }, + { + "epoch": 0.31625884844768964, + "grad_norm": 0.5700320601463318, + "learning_rate": 7.880491082069949e-05, + "loss": 1.7419, + "step": 5674 + }, + { + "epoch": 0.3163145867008528, + "grad_norm": 0.569348156452179, + "learning_rate": 7.879763221505197e-05, + "loss": 1.7392, + "step": 5675 + }, + { + "epoch": 0.31637032495401596, + "grad_norm": 0.5255264639854431, + "learning_rate": 7.879035269611146e-05, + "loss": 1.6862, + "step": 5676 + }, + { + "epoch": 0.3164260632071791, + "grad_norm": 0.5734140872955322, + "learning_rate": 7.878307226410882e-05, + "loss": 1.8253, + "step": 5677 + }, + { + "epoch": 0.3164818014603422, + "grad_norm": 0.5915566086769104, + "learning_rate": 7.877579091927496e-05, + "loss": 1.7754, + "step": 5678 + }, + { + "epoch": 0.3165375397135054, + "grad_norm": 0.5272923707962036, + "learning_rate": 7.876850866184077e-05, + "loss": 1.7315, + "step": 5679 + }, + { + "epoch": 0.31659327796666853, + "grad_norm": 0.5072640180587769, + "learning_rate": 7.876122549203723e-05, + "loss": 1.5367, + "step": 5680 + }, + { + "epoch": 0.31664901621983166, + "grad_norm": 0.5453153848648071, + "learning_rate": 7.87539414100953e-05, + "loss": 1.7551, + "step": 5681 + }, + { + "epoch": 0.31670475447299484, + "grad_norm": 0.5492895245552063, + "learning_rate": 7.874665641624599e-05, + "loss": 1.7739, + "step": 5682 + }, + { + "epoch": 0.31676049272615797, + "grad_norm": 0.5405164957046509, + "learning_rate": 7.873937051072035e-05, + "loss": 1.747, + "step": 5683 + }, + { + "epoch": 0.3168162309793211, + "grad_norm": 0.5549308061599731, + "learning_rate": 7.873208369374943e-05, + "loss": 1.8224, + "step": 5684 + }, + { + "epoch": 0.31687196923248423, + "grad_norm": 0.5366522669792175, + "learning_rate": 7.872479596556435e-05, + "loss": 1.6589, + "step": 5685 + }, + { + "epoch": 0.3169277074856474, + "grad_norm": 0.527472734451294, + "learning_rate": 7.871750732639621e-05, + "loss": 1.6122, + "step": 5686 + }, + { + "epoch": 0.31698344573881054, + "grad_norm": 0.5421255826950073, + "learning_rate": 7.871021777647618e-05, + "loss": 1.766, + "step": 5687 + }, + { + "epoch": 0.31703918399197367, + "grad_norm": 0.5596272945404053, + "learning_rate": 7.870292731603544e-05, + "loss": 1.765, + "step": 5688 + }, + { + "epoch": 0.31709492224513686, + "grad_norm": 0.5629613995552063, + "learning_rate": 7.869563594530517e-05, + "loss": 1.6374, + "step": 5689 + }, + { + "epoch": 0.3171506604983, + "grad_norm": 0.5471567511558533, + "learning_rate": 7.868834366451665e-05, + "loss": 1.8048, + "step": 5690 + }, + { + "epoch": 0.3172063987514631, + "grad_norm": 0.6505834460258484, + "learning_rate": 7.868105047390113e-05, + "loss": 2.1298, + "step": 5691 + }, + { + "epoch": 0.3172621370046263, + "grad_norm": 0.5665611624717712, + "learning_rate": 7.867375637368993e-05, + "loss": 1.6, + "step": 5692 + }, + { + "epoch": 0.31731787525778943, + "grad_norm": 0.5327755212783813, + "learning_rate": 7.866646136411433e-05, + "loss": 1.7876, + "step": 5693 + }, + { + "epoch": 0.31737361351095256, + "grad_norm": 0.5993742942810059, + "learning_rate": 7.865916544540573e-05, + "loss": 1.7237, + "step": 5694 + }, + { + "epoch": 0.3174293517641157, + "grad_norm": 0.5317041873931885, + "learning_rate": 7.865186861779548e-05, + "loss": 1.5221, + "step": 5695 + }, + { + "epoch": 0.31748509001727887, + "grad_norm": 0.5825653076171875, + "learning_rate": 7.864457088151502e-05, + "loss": 1.7575, + "step": 5696 + }, + { + "epoch": 0.317540828270442, + "grad_norm": 0.5435444116592407, + "learning_rate": 7.863727223679578e-05, + "loss": 1.789, + "step": 5697 + }, + { + "epoch": 0.31759656652360513, + "grad_norm": 0.5559577941894531, + "learning_rate": 7.862997268386924e-05, + "loss": 1.802, + "step": 5698 + }, + { + "epoch": 0.3176523047767683, + "grad_norm": 0.6636247634887695, + "learning_rate": 7.862267222296687e-05, + "loss": 2.0765, + "step": 5699 + }, + { + "epoch": 0.31770804302993144, + "grad_norm": 0.49671420454978943, + "learning_rate": 7.861537085432025e-05, + "loss": 1.5644, + "step": 5700 + }, + { + "epoch": 0.31776378128309457, + "grad_norm": 0.5270445942878723, + "learning_rate": 7.860806857816088e-05, + "loss": 1.7291, + "step": 5701 + }, + { + "epoch": 0.31781951953625776, + "grad_norm": 0.6097070574760437, + "learning_rate": 7.860076539472037e-05, + "loss": 1.9244, + "step": 5702 + }, + { + "epoch": 0.3178752577894209, + "grad_norm": 0.537875235080719, + "learning_rate": 7.859346130423035e-05, + "loss": 1.7579, + "step": 5703 + }, + { + "epoch": 0.317930996042584, + "grad_norm": 0.5384728908538818, + "learning_rate": 7.858615630692244e-05, + "loss": 1.5755, + "step": 5704 + }, + { + "epoch": 0.3179867342957472, + "grad_norm": 0.5751199722290039, + "learning_rate": 7.857885040302833e-05, + "loss": 1.6979, + "step": 5705 + }, + { + "epoch": 0.3180424725489103, + "grad_norm": 0.5749076008796692, + "learning_rate": 7.857154359277972e-05, + "loss": 1.6744, + "step": 5706 + }, + { + "epoch": 0.31809821080207346, + "grad_norm": 0.5693714022636414, + "learning_rate": 7.85642358764083e-05, + "loss": 1.8986, + "step": 5707 + }, + { + "epoch": 0.3181539490552366, + "grad_norm": 0.504147469997406, + "learning_rate": 7.855692725414587e-05, + "loss": 1.5641, + "step": 5708 + }, + { + "epoch": 0.31820968730839977, + "grad_norm": 0.5494616031646729, + "learning_rate": 7.854961772622423e-05, + "loss": 1.6743, + "step": 5709 + }, + { + "epoch": 0.3182654255615629, + "grad_norm": 0.49635690450668335, + "learning_rate": 7.854230729287515e-05, + "loss": 1.5466, + "step": 5710 + }, + { + "epoch": 0.318321163814726, + "grad_norm": 0.569781482219696, + "learning_rate": 7.853499595433049e-05, + "loss": 1.7647, + "step": 5711 + }, + { + "epoch": 0.3183769020678892, + "grad_norm": 0.540679931640625, + "learning_rate": 7.852768371082215e-05, + "loss": 1.6237, + "step": 5712 + }, + { + "epoch": 0.31843264032105234, + "grad_norm": 0.5818458795547485, + "learning_rate": 7.852037056258199e-05, + "loss": 1.9955, + "step": 5713 + }, + { + "epoch": 0.31848837857421547, + "grad_norm": 0.5366159081459045, + "learning_rate": 7.851305650984197e-05, + "loss": 1.5985, + "step": 5714 + }, + { + "epoch": 0.31854411682737865, + "grad_norm": 0.7078673839569092, + "learning_rate": 7.850574155283404e-05, + "loss": 1.6371, + "step": 5715 + }, + { + "epoch": 0.3185998550805418, + "grad_norm": 0.6395692825317383, + "learning_rate": 7.849842569179017e-05, + "loss": 2.0647, + "step": 5716 + }, + { + "epoch": 0.3186555933337049, + "grad_norm": 0.5583460927009583, + "learning_rate": 7.849110892694242e-05, + "loss": 1.8005, + "step": 5717 + }, + { + "epoch": 0.31871133158686804, + "grad_norm": 0.6016951203346252, + "learning_rate": 7.848379125852282e-05, + "loss": 1.9861, + "step": 5718 + }, + { + "epoch": 0.3187670698400312, + "grad_norm": 0.5291598439216614, + "learning_rate": 7.847647268676341e-05, + "loss": 1.6806, + "step": 5719 + }, + { + "epoch": 0.31882280809319435, + "grad_norm": 0.5864149332046509, + "learning_rate": 7.846915321189632e-05, + "loss": 1.7323, + "step": 5720 + }, + { + "epoch": 0.3188785463463575, + "grad_norm": 0.5477664470672607, + "learning_rate": 7.846183283415367e-05, + "loss": 1.7307, + "step": 5721 + }, + { + "epoch": 0.31893428459952067, + "grad_norm": 0.5449158549308777, + "learning_rate": 7.845451155376764e-05, + "loss": 1.679, + "step": 5722 + }, + { + "epoch": 0.3189900228526838, + "grad_norm": 0.5383809804916382, + "learning_rate": 7.844718937097039e-05, + "loss": 1.6991, + "step": 5723 + }, + { + "epoch": 0.3190457611058469, + "grad_norm": 0.4735757112503052, + "learning_rate": 7.843986628599416e-05, + "loss": 1.4701, + "step": 5724 + }, + { + "epoch": 0.3191014993590101, + "grad_norm": 0.5248317122459412, + "learning_rate": 7.843254229907119e-05, + "loss": 1.7293, + "step": 5725 + }, + { + "epoch": 0.31915723761217324, + "grad_norm": 0.5262721180915833, + "learning_rate": 7.842521741043375e-05, + "loss": 1.6067, + "step": 5726 + }, + { + "epoch": 0.31921297586533637, + "grad_norm": 0.5584807991981506, + "learning_rate": 7.841789162031415e-05, + "loss": 1.8573, + "step": 5727 + }, + { + "epoch": 0.31926871411849955, + "grad_norm": 0.5617311596870422, + "learning_rate": 7.84105649289447e-05, + "loss": 1.7482, + "step": 5728 + }, + { + "epoch": 0.3193244523716627, + "grad_norm": 0.5431827902793884, + "learning_rate": 7.840323733655778e-05, + "loss": 1.8564, + "step": 5729 + }, + { + "epoch": 0.3193801906248258, + "grad_norm": 0.5269571542739868, + "learning_rate": 7.839590884338579e-05, + "loss": 1.4677, + "step": 5730 + }, + { + "epoch": 0.31943592887798894, + "grad_norm": 0.5726506114006042, + "learning_rate": 7.838857944966113e-05, + "loss": 1.7656, + "step": 5731 + }, + { + "epoch": 0.3194916671311521, + "grad_norm": 0.5350455641746521, + "learning_rate": 7.838124915561623e-05, + "loss": 1.525, + "step": 5732 + }, + { + "epoch": 0.31954740538431525, + "grad_norm": 0.6093659996986389, + "learning_rate": 7.837391796148359e-05, + "loss": 1.9737, + "step": 5733 + }, + { + "epoch": 0.3196031436374784, + "grad_norm": 0.5513406991958618, + "learning_rate": 7.83665858674957e-05, + "loss": 1.6783, + "step": 5734 + }, + { + "epoch": 0.31965888189064157, + "grad_norm": 0.5465078949928284, + "learning_rate": 7.835925287388511e-05, + "loss": 1.5786, + "step": 5735 + }, + { + "epoch": 0.3197146201438047, + "grad_norm": 0.5756266713142395, + "learning_rate": 7.835191898088435e-05, + "loss": 1.7969, + "step": 5736 + }, + { + "epoch": 0.3197703583969678, + "grad_norm": 0.5218703150749207, + "learning_rate": 7.8344584188726e-05, + "loss": 1.619, + "step": 5737 + }, + { + "epoch": 0.319826096650131, + "grad_norm": 0.5465853810310364, + "learning_rate": 7.833724849764273e-05, + "loss": 1.6193, + "step": 5738 + }, + { + "epoch": 0.31988183490329414, + "grad_norm": 0.596364438533783, + "learning_rate": 7.832991190786716e-05, + "loss": 1.7853, + "step": 5739 + }, + { + "epoch": 0.31993757315645727, + "grad_norm": 0.544185221195221, + "learning_rate": 7.832257441963195e-05, + "loss": 1.8835, + "step": 5740 + }, + { + "epoch": 0.3199933114096204, + "grad_norm": 0.6070075631141663, + "learning_rate": 7.83152360331698e-05, + "loss": 2.1082, + "step": 5741 + }, + { + "epoch": 0.3200490496627836, + "grad_norm": 0.5382431745529175, + "learning_rate": 7.830789674871346e-05, + "loss": 1.7184, + "step": 5742 + }, + { + "epoch": 0.3201047879159467, + "grad_norm": 0.5074361562728882, + "learning_rate": 7.830055656649568e-05, + "loss": 1.5133, + "step": 5743 + }, + { + "epoch": 0.32016052616910984, + "grad_norm": 0.5396546125411987, + "learning_rate": 7.829321548674926e-05, + "loss": 1.6203, + "step": 5744 + }, + { + "epoch": 0.320216264422273, + "grad_norm": 0.5758295059204102, + "learning_rate": 7.8285873509707e-05, + "loss": 1.8658, + "step": 5745 + }, + { + "epoch": 0.32027200267543615, + "grad_norm": 0.506420910358429, + "learning_rate": 7.827853063560175e-05, + "loss": 1.509, + "step": 5746 + }, + { + "epoch": 0.3203277409285993, + "grad_norm": 0.5390977263450623, + "learning_rate": 7.82711868646664e-05, + "loss": 1.8333, + "step": 5747 + }, + { + "epoch": 0.32038347918176246, + "grad_norm": 0.5680609345436096, + "learning_rate": 7.82638421971338e-05, + "loss": 1.6984, + "step": 5748 + }, + { + "epoch": 0.3204392174349256, + "grad_norm": 0.5344312191009521, + "learning_rate": 7.825649663323693e-05, + "loss": 1.6667, + "step": 5749 + }, + { + "epoch": 0.3204949556880887, + "grad_norm": 0.610658586025238, + "learning_rate": 7.824915017320874e-05, + "loss": 1.7763, + "step": 5750 + }, + { + "epoch": 0.3205506939412519, + "grad_norm": 0.5463300943374634, + "learning_rate": 7.824180281728222e-05, + "loss": 1.5632, + "step": 5751 + }, + { + "epoch": 0.32060643219441504, + "grad_norm": 0.5856190919876099, + "learning_rate": 7.823445456569036e-05, + "loss": 1.8129, + "step": 5752 + }, + { + "epoch": 0.32066217044757817, + "grad_norm": 0.7068459987640381, + "learning_rate": 7.822710541866622e-05, + "loss": 1.8126, + "step": 5753 + }, + { + "epoch": 0.3207179087007413, + "grad_norm": 0.6159639954566956, + "learning_rate": 7.821975537644286e-05, + "loss": 1.7802, + "step": 5754 + }, + { + "epoch": 0.3207736469539045, + "grad_norm": 0.583821177482605, + "learning_rate": 7.821240443925341e-05, + "loss": 1.9406, + "step": 5755 + }, + { + "epoch": 0.3208293852070676, + "grad_norm": 0.49633607268333435, + "learning_rate": 7.820505260733098e-05, + "loss": 1.4748, + "step": 5756 + }, + { + "epoch": 0.32088512346023074, + "grad_norm": 0.5159478187561035, + "learning_rate": 7.819769988090873e-05, + "loss": 1.716, + "step": 5757 + }, + { + "epoch": 0.3209408617133939, + "grad_norm": 0.5665544867515564, + "learning_rate": 7.819034626021983e-05, + "loss": 1.8005, + "step": 5758 + }, + { + "epoch": 0.32099659996655705, + "grad_norm": 0.567043125629425, + "learning_rate": 7.818299174549752e-05, + "loss": 1.675, + "step": 5759 + }, + { + "epoch": 0.3210523382197202, + "grad_norm": 0.5980729460716248, + "learning_rate": 7.817563633697503e-05, + "loss": 1.9635, + "step": 5760 + }, + { + "epoch": 0.32110807647288336, + "grad_norm": 0.5714271068572998, + "learning_rate": 7.816828003488563e-05, + "loss": 1.7265, + "step": 5761 + }, + { + "epoch": 0.3211638147260465, + "grad_norm": 0.5386238694190979, + "learning_rate": 7.816092283946261e-05, + "loss": 1.6653, + "step": 5762 + }, + { + "epoch": 0.3212195529792096, + "grad_norm": 0.5798346400260925, + "learning_rate": 7.815356475093931e-05, + "loss": 1.6578, + "step": 5763 + }, + { + "epoch": 0.32127529123237275, + "grad_norm": 0.5155278444290161, + "learning_rate": 7.81462057695491e-05, + "loss": 1.787, + "step": 5764 + }, + { + "epoch": 0.32133102948553594, + "grad_norm": 0.49146315455436707, + "learning_rate": 7.813884589552534e-05, + "loss": 1.5927, + "step": 5765 + }, + { + "epoch": 0.32138676773869906, + "grad_norm": 0.553433895111084, + "learning_rate": 7.813148512910144e-05, + "loss": 1.7973, + "step": 5766 + }, + { + "epoch": 0.3214425059918622, + "grad_norm": 0.5665645003318787, + "learning_rate": 7.812412347051083e-05, + "loss": 1.7949, + "step": 5767 + }, + { + "epoch": 0.3214982442450254, + "grad_norm": 0.5180385708808899, + "learning_rate": 7.811676091998704e-05, + "loss": 1.7011, + "step": 5768 + }, + { + "epoch": 0.3215539824981885, + "grad_norm": 0.581295371055603, + "learning_rate": 7.81093974777635e-05, + "loss": 1.7513, + "step": 5769 + }, + { + "epoch": 0.32160972075135164, + "grad_norm": 0.5677274465560913, + "learning_rate": 7.810203314407377e-05, + "loss": 1.9528, + "step": 5770 + }, + { + "epoch": 0.3216654590045148, + "grad_norm": 0.5377728939056396, + "learning_rate": 7.80946679191514e-05, + "loss": 1.6544, + "step": 5771 + }, + { + "epoch": 0.32172119725767795, + "grad_norm": 0.533319354057312, + "learning_rate": 7.808730180322996e-05, + "loss": 1.6561, + "step": 5772 + }, + { + "epoch": 0.3217769355108411, + "grad_norm": 0.5324406623840332, + "learning_rate": 7.807993479654307e-05, + "loss": 1.6776, + "step": 5773 + }, + { + "epoch": 0.32183267376400426, + "grad_norm": 0.5995755195617676, + "learning_rate": 7.807256689932435e-05, + "loss": 1.6976, + "step": 5774 + }, + { + "epoch": 0.3218884120171674, + "grad_norm": 0.5474086999893188, + "learning_rate": 7.806519811180751e-05, + "loss": 1.4983, + "step": 5775 + }, + { + "epoch": 0.3219441502703305, + "grad_norm": 0.5364895462989807, + "learning_rate": 7.805782843422618e-05, + "loss": 1.7632, + "step": 5776 + }, + { + "epoch": 0.32199988852349365, + "grad_norm": 0.5104418396949768, + "learning_rate": 7.805045786681415e-05, + "loss": 1.6873, + "step": 5777 + }, + { + "epoch": 0.32205562677665683, + "grad_norm": 0.5162766575813293, + "learning_rate": 7.804308640980513e-05, + "loss": 1.6692, + "step": 5778 + }, + { + "epoch": 0.32211136502981996, + "grad_norm": 0.5526577234268188, + "learning_rate": 7.803571406343293e-05, + "loss": 1.631, + "step": 5779 + }, + { + "epoch": 0.3221671032829831, + "grad_norm": 0.4954930245876312, + "learning_rate": 7.802834082793131e-05, + "loss": 1.4774, + "step": 5780 + }, + { + "epoch": 0.3222228415361463, + "grad_norm": 0.5704354643821716, + "learning_rate": 7.802096670353416e-05, + "loss": 1.9247, + "step": 5781 + }, + { + "epoch": 0.3222785797893094, + "grad_norm": 0.5746217966079712, + "learning_rate": 7.80135916904753e-05, + "loss": 1.9075, + "step": 5782 + }, + { + "epoch": 0.32233431804247253, + "grad_norm": 0.5538354516029358, + "learning_rate": 7.800621578898867e-05, + "loss": 1.6338, + "step": 5783 + }, + { + "epoch": 0.3223900562956357, + "grad_norm": 0.5441854596138, + "learning_rate": 7.799883899930815e-05, + "loss": 1.6214, + "step": 5784 + }, + { + "epoch": 0.32244579454879885, + "grad_norm": 0.5677271485328674, + "learning_rate": 7.79914613216677e-05, + "loss": 1.7258, + "step": 5785 + }, + { + "epoch": 0.322501532801962, + "grad_norm": 0.5610553026199341, + "learning_rate": 7.798408275630129e-05, + "loss": 1.6471, + "step": 5786 + }, + { + "epoch": 0.3225572710551251, + "grad_norm": 0.5126567482948303, + "learning_rate": 7.797670330344294e-05, + "loss": 1.7154, + "step": 5787 + }, + { + "epoch": 0.3226130093082883, + "grad_norm": 0.565370500087738, + "learning_rate": 7.796932296332667e-05, + "loss": 1.7534, + "step": 5788 + }, + { + "epoch": 0.3226687475614514, + "grad_norm": 0.5113086104393005, + "learning_rate": 7.796194173618654e-05, + "loss": 1.5581, + "step": 5789 + }, + { + "epoch": 0.32272448581461455, + "grad_norm": 0.543984591960907, + "learning_rate": 7.795455962225669e-05, + "loss": 1.7255, + "step": 5790 + }, + { + "epoch": 0.32278022406777773, + "grad_norm": 0.5158193707466125, + "learning_rate": 7.794717662177115e-05, + "loss": 1.6029, + "step": 5791 + }, + { + "epoch": 0.32283596232094086, + "grad_norm": 0.5405291318893433, + "learning_rate": 7.793979273496414e-05, + "loss": 1.6035, + "step": 5792 + }, + { + "epoch": 0.322891700574104, + "grad_norm": 0.617701530456543, + "learning_rate": 7.793240796206979e-05, + "loss": 1.8577, + "step": 5793 + }, + { + "epoch": 0.3229474388272672, + "grad_norm": 0.4910410940647125, + "learning_rate": 7.79250223033223e-05, + "loss": 1.4227, + "step": 5794 + }, + { + "epoch": 0.3230031770804303, + "grad_norm": 0.5436237454414368, + "learning_rate": 7.791763575895594e-05, + "loss": 1.5865, + "step": 5795 + }, + { + "epoch": 0.32305891533359343, + "grad_norm": 0.5777418613433838, + "learning_rate": 7.791024832920496e-05, + "loss": 1.8056, + "step": 5796 + }, + { + "epoch": 0.3231146535867566, + "grad_norm": 0.5960043668746948, + "learning_rate": 7.79028600143036e-05, + "loss": 1.8124, + "step": 5797 + }, + { + "epoch": 0.32317039183991975, + "grad_norm": 0.5568564534187317, + "learning_rate": 7.789547081448622e-05, + "loss": 1.614, + "step": 5798 + }, + { + "epoch": 0.3232261300930829, + "grad_norm": 0.5896525979042053, + "learning_rate": 7.788808072998715e-05, + "loss": 1.784, + "step": 5799 + }, + { + "epoch": 0.323281868346246, + "grad_norm": 0.5450705885887146, + "learning_rate": 7.788068976104074e-05, + "loss": 1.462, + "step": 5800 + }, + { + "epoch": 0.3233376065994092, + "grad_norm": 0.4870886206626892, + "learning_rate": 7.787329790788142e-05, + "loss": 1.5523, + "step": 5801 + }, + { + "epoch": 0.3233933448525723, + "grad_norm": 0.5481093525886536, + "learning_rate": 7.78659051707436e-05, + "loss": 1.6292, + "step": 5802 + }, + { + "epoch": 0.32344908310573545, + "grad_norm": 0.5144929885864258, + "learning_rate": 7.785851154986174e-05, + "loss": 1.4811, + "step": 5803 + }, + { + "epoch": 0.32350482135889863, + "grad_norm": 0.5884720683097839, + "learning_rate": 7.785111704547032e-05, + "loss": 1.8426, + "step": 5804 + }, + { + "epoch": 0.32356055961206176, + "grad_norm": 0.5478202104568481, + "learning_rate": 7.784372165780386e-05, + "loss": 1.4918, + "step": 5805 + }, + { + "epoch": 0.3236162978652249, + "grad_norm": 0.5706868767738342, + "learning_rate": 7.783632538709688e-05, + "loss": 1.6687, + "step": 5806 + }, + { + "epoch": 0.3236720361183881, + "grad_norm": 0.569288432598114, + "learning_rate": 7.782892823358394e-05, + "loss": 1.7208, + "step": 5807 + }, + { + "epoch": 0.3237277743715512, + "grad_norm": 0.6056145429611206, + "learning_rate": 7.782153019749967e-05, + "loss": 1.9566, + "step": 5808 + }, + { + "epoch": 0.32378351262471433, + "grad_norm": 0.5828245878219604, + "learning_rate": 7.781413127907868e-05, + "loss": 1.7169, + "step": 5809 + }, + { + "epoch": 0.32383925087787746, + "grad_norm": 0.5503557920455933, + "learning_rate": 7.780673147855559e-05, + "loss": 1.7084, + "step": 5810 + }, + { + "epoch": 0.32389498913104064, + "grad_norm": 0.5861828327178955, + "learning_rate": 7.779933079616512e-05, + "loss": 1.6815, + "step": 5811 + }, + { + "epoch": 0.3239507273842038, + "grad_norm": 0.5410308837890625, + "learning_rate": 7.779192923214196e-05, + "loss": 1.6899, + "step": 5812 + }, + { + "epoch": 0.3240064656373669, + "grad_norm": 0.6349414587020874, + "learning_rate": 7.778452678672084e-05, + "loss": 2.0061, + "step": 5813 + }, + { + "epoch": 0.3240622038905301, + "grad_norm": 0.6143296360969543, + "learning_rate": 7.777712346013651e-05, + "loss": 1.6939, + "step": 5814 + }, + { + "epoch": 0.3241179421436932, + "grad_norm": 0.5646039247512817, + "learning_rate": 7.776971925262379e-05, + "loss": 1.4296, + "step": 5815 + }, + { + "epoch": 0.32417368039685635, + "grad_norm": 0.570025622844696, + "learning_rate": 7.776231416441748e-05, + "loss": 1.8693, + "step": 5816 + }, + { + "epoch": 0.32422941865001953, + "grad_norm": 0.4873752295970917, + "learning_rate": 7.775490819575242e-05, + "loss": 1.5215, + "step": 5817 + }, + { + "epoch": 0.32428515690318266, + "grad_norm": 0.5546776652336121, + "learning_rate": 7.774750134686352e-05, + "loss": 1.6002, + "step": 5818 + }, + { + "epoch": 0.3243408951563458, + "grad_norm": 0.5605872273445129, + "learning_rate": 7.774009361798565e-05, + "loss": 1.42, + "step": 5819 + }, + { + "epoch": 0.32439663340950897, + "grad_norm": 0.5118110179901123, + "learning_rate": 7.773268500935372e-05, + "loss": 1.6076, + "step": 5820 + }, + { + "epoch": 0.3244523716626721, + "grad_norm": 0.5516108274459839, + "learning_rate": 7.772527552120273e-05, + "loss": 1.6444, + "step": 5821 + }, + { + "epoch": 0.32450810991583523, + "grad_norm": 0.5176465511322021, + "learning_rate": 7.771786515376765e-05, + "loss": 1.3809, + "step": 5822 + }, + { + "epoch": 0.32456384816899836, + "grad_norm": 0.5901971459388733, + "learning_rate": 7.77104539072835e-05, + "loss": 1.8976, + "step": 5823 + }, + { + "epoch": 0.32461958642216154, + "grad_norm": 0.5981687903404236, + "learning_rate": 7.770304178198531e-05, + "loss": 1.7352, + "step": 5824 + }, + { + "epoch": 0.3246753246753247, + "grad_norm": 0.48600277304649353, + "learning_rate": 7.769562877810816e-05, + "loss": 1.5827, + "step": 5825 + }, + { + "epoch": 0.3247310629284878, + "grad_norm": 0.47773730754852295, + "learning_rate": 7.768821489588713e-05, + "loss": 1.44, + "step": 5826 + }, + { + "epoch": 0.324786801181651, + "grad_norm": 0.5615780353546143, + "learning_rate": 7.768080013555737e-05, + "loss": 1.6719, + "step": 5827 + }, + { + "epoch": 0.3248425394348141, + "grad_norm": 0.5451145172119141, + "learning_rate": 7.767338449735401e-05, + "loss": 1.355, + "step": 5828 + }, + { + "epoch": 0.32489827768797724, + "grad_norm": 0.5609704852104187, + "learning_rate": 7.766596798151224e-05, + "loss": 1.6764, + "step": 5829 + }, + { + "epoch": 0.32495401594114043, + "grad_norm": 0.5926015973091125, + "learning_rate": 7.765855058826727e-05, + "loss": 1.8243, + "step": 5830 + }, + { + "epoch": 0.32500975419430356, + "grad_norm": 0.5234283804893494, + "learning_rate": 7.765113231785435e-05, + "loss": 1.7313, + "step": 5831 + }, + { + "epoch": 0.3250654924474667, + "grad_norm": 0.5433173179626465, + "learning_rate": 7.764371317050873e-05, + "loss": 1.7546, + "step": 5832 + }, + { + "epoch": 0.3251212307006298, + "grad_norm": 0.6074669361114502, + "learning_rate": 7.763629314646568e-05, + "loss": 1.7879, + "step": 5833 + }, + { + "epoch": 0.325176968953793, + "grad_norm": 0.6136168241500854, + "learning_rate": 7.762887224596055e-05, + "loss": 1.8066, + "step": 5834 + }, + { + "epoch": 0.32523270720695613, + "grad_norm": 0.5498754978179932, + "learning_rate": 7.76214504692287e-05, + "loss": 1.6913, + "step": 5835 + }, + { + "epoch": 0.32528844546011926, + "grad_norm": 0.5876418352127075, + "learning_rate": 7.761402781650547e-05, + "loss": 1.7581, + "step": 5836 + }, + { + "epoch": 0.32534418371328244, + "grad_norm": 0.5235028862953186, + "learning_rate": 7.760660428802628e-05, + "loss": 1.5955, + "step": 5837 + }, + { + "epoch": 0.32539992196644557, + "grad_norm": 0.54973304271698, + "learning_rate": 7.759917988402657e-05, + "loss": 1.6833, + "step": 5838 + }, + { + "epoch": 0.3254556602196087, + "grad_norm": 0.6082160472869873, + "learning_rate": 7.759175460474177e-05, + "loss": 1.8303, + "step": 5839 + }, + { + "epoch": 0.3255113984727719, + "grad_norm": 0.5204039812088013, + "learning_rate": 7.758432845040737e-05, + "loss": 1.7216, + "step": 5840 + }, + { + "epoch": 0.325567136725935, + "grad_norm": 0.5268458724021912, + "learning_rate": 7.757690142125893e-05, + "loss": 1.6099, + "step": 5841 + }, + { + "epoch": 0.32562287497909814, + "grad_norm": 0.5118129253387451, + "learning_rate": 7.756947351753196e-05, + "loss": 1.5388, + "step": 5842 + }, + { + "epoch": 0.3256786132322613, + "grad_norm": 0.5349292159080505, + "learning_rate": 7.756204473946203e-05, + "loss": 1.6813, + "step": 5843 + }, + { + "epoch": 0.32573435148542446, + "grad_norm": 0.5555446743965149, + "learning_rate": 7.755461508728472e-05, + "loss": 1.5549, + "step": 5844 + }, + { + "epoch": 0.3257900897385876, + "grad_norm": 0.5379804372787476, + "learning_rate": 7.75471845612357e-05, + "loss": 1.5658, + "step": 5845 + }, + { + "epoch": 0.3258458279917507, + "grad_norm": 0.618511974811554, + "learning_rate": 7.753975316155057e-05, + "loss": 1.8505, + "step": 5846 + }, + { + "epoch": 0.3259015662449139, + "grad_norm": 0.6143367290496826, + "learning_rate": 7.753232088846505e-05, + "loss": 1.953, + "step": 5847 + }, + { + "epoch": 0.325957304498077, + "grad_norm": 0.543201208114624, + "learning_rate": 7.752488774221485e-05, + "loss": 1.9068, + "step": 5848 + }, + { + "epoch": 0.32601304275124016, + "grad_norm": 0.5580254197120667, + "learning_rate": 7.751745372303567e-05, + "loss": 1.6766, + "step": 5849 + }, + { + "epoch": 0.32606878100440334, + "grad_norm": 0.5846728086471558, + "learning_rate": 7.751001883116331e-05, + "loss": 1.874, + "step": 5850 + }, + { + "epoch": 0.32612451925756647, + "grad_norm": 0.5597751140594482, + "learning_rate": 7.750258306683353e-05, + "loss": 1.7491, + "step": 5851 + }, + { + "epoch": 0.3261802575107296, + "grad_norm": 0.49921393394470215, + "learning_rate": 7.749514643028218e-05, + "loss": 1.3701, + "step": 5852 + }, + { + "epoch": 0.3262359957638928, + "grad_norm": 0.5255808234214783, + "learning_rate": 7.748770892174509e-05, + "loss": 1.4772, + "step": 5853 + }, + { + "epoch": 0.3262917340170559, + "grad_norm": 0.5470353960990906, + "learning_rate": 7.748027054145814e-05, + "loss": 1.7885, + "step": 5854 + }, + { + "epoch": 0.32634747227021904, + "grad_norm": 0.575181782245636, + "learning_rate": 7.747283128965723e-05, + "loss": 1.8875, + "step": 5855 + }, + { + "epoch": 0.32640321052338217, + "grad_norm": 0.6346047520637512, + "learning_rate": 7.74653911665783e-05, + "loss": 2.0948, + "step": 5856 + }, + { + "epoch": 0.32645894877654535, + "grad_norm": 0.5814865231513977, + "learning_rate": 7.745795017245729e-05, + "loss": 1.572, + "step": 5857 + }, + { + "epoch": 0.3265146870297085, + "grad_norm": 0.5990648865699768, + "learning_rate": 7.745050830753018e-05, + "loss": 1.7464, + "step": 5858 + }, + { + "epoch": 0.3265704252828716, + "grad_norm": 0.5689359903335571, + "learning_rate": 7.744306557203299e-05, + "loss": 1.9168, + "step": 5859 + }, + { + "epoch": 0.3266261635360348, + "grad_norm": 0.5398204326629639, + "learning_rate": 7.743562196620177e-05, + "loss": 1.6884, + "step": 5860 + }, + { + "epoch": 0.3266819017891979, + "grad_norm": 0.5738016366958618, + "learning_rate": 7.74281774902726e-05, + "loss": 1.815, + "step": 5861 + }, + { + "epoch": 0.32673764004236105, + "grad_norm": 0.5424049496650696, + "learning_rate": 7.742073214448153e-05, + "loss": 1.832, + "step": 5862 + }, + { + "epoch": 0.32679337829552424, + "grad_norm": 0.5409512519836426, + "learning_rate": 7.741328592906474e-05, + "loss": 1.7179, + "step": 5863 + }, + { + "epoch": 0.32684911654868737, + "grad_norm": 0.5621674656867981, + "learning_rate": 7.740583884425833e-05, + "loss": 1.8319, + "step": 5864 + }, + { + "epoch": 0.3269048548018505, + "grad_norm": 0.5400972962379456, + "learning_rate": 7.73983908902985e-05, + "loss": 1.6868, + "step": 5865 + }, + { + "epoch": 0.3269605930550137, + "grad_norm": 0.5927982926368713, + "learning_rate": 7.739094206742146e-05, + "loss": 1.6426, + "step": 5866 + }, + { + "epoch": 0.3270163313081768, + "grad_norm": 0.510775089263916, + "learning_rate": 7.738349237586343e-05, + "loss": 1.6661, + "step": 5867 + }, + { + "epoch": 0.32707206956133994, + "grad_norm": 0.5710152387619019, + "learning_rate": 7.737604181586068e-05, + "loss": 1.7263, + "step": 5868 + }, + { + "epoch": 0.32712780781450307, + "grad_norm": 0.5645250082015991, + "learning_rate": 7.736859038764952e-05, + "loss": 1.7197, + "step": 5869 + }, + { + "epoch": 0.32718354606766625, + "grad_norm": 0.5439823865890503, + "learning_rate": 7.73611380914662e-05, + "loss": 1.7229, + "step": 5870 + }, + { + "epoch": 0.3272392843208294, + "grad_norm": 0.5163010358810425, + "learning_rate": 7.735368492754715e-05, + "loss": 1.5273, + "step": 5871 + }, + { + "epoch": 0.3272950225739925, + "grad_norm": 0.5735363960266113, + "learning_rate": 7.734623089612867e-05, + "loss": 1.7926, + "step": 5872 + }, + { + "epoch": 0.3273507608271557, + "grad_norm": 0.5508522391319275, + "learning_rate": 7.73387759974472e-05, + "loss": 1.492, + "step": 5873 + }, + { + "epoch": 0.3274064990803188, + "grad_norm": 0.6105926632881165, + "learning_rate": 7.733132023173915e-05, + "loss": 1.6155, + "step": 5874 + }, + { + "epoch": 0.32746223733348195, + "grad_norm": 0.5956704020500183, + "learning_rate": 7.732386359924097e-05, + "loss": 1.7757, + "step": 5875 + }, + { + "epoch": 0.32751797558664514, + "grad_norm": 0.6001446843147278, + "learning_rate": 7.731640610018914e-05, + "loss": 1.6669, + "step": 5876 + }, + { + "epoch": 0.32757371383980827, + "grad_norm": 0.6132667660713196, + "learning_rate": 7.730894773482019e-05, + "loss": 1.944, + "step": 5877 + }, + { + "epoch": 0.3276294520929714, + "grad_norm": 0.5684986710548401, + "learning_rate": 7.730148850337062e-05, + "loss": 1.7491, + "step": 5878 + }, + { + "epoch": 0.3276851903461345, + "grad_norm": 0.537605881690979, + "learning_rate": 7.729402840607702e-05, + "loss": 1.7473, + "step": 5879 + }, + { + "epoch": 0.3277409285992977, + "grad_norm": 0.5186078548431396, + "learning_rate": 7.728656744317598e-05, + "loss": 1.7703, + "step": 5880 + }, + { + "epoch": 0.32779666685246084, + "grad_norm": 0.5188151001930237, + "learning_rate": 7.727910561490411e-05, + "loss": 1.6632, + "step": 5881 + }, + { + "epoch": 0.32785240510562397, + "grad_norm": 0.5799871683120728, + "learning_rate": 7.727164292149806e-05, + "loss": 1.7289, + "step": 5882 + }, + { + "epoch": 0.32790814335878715, + "grad_norm": 0.5974400639533997, + "learning_rate": 7.72641793631945e-05, + "loss": 1.9396, + "step": 5883 + }, + { + "epoch": 0.3279638816119503, + "grad_norm": 0.5383574366569519, + "learning_rate": 7.725671494023014e-05, + "loss": 1.6176, + "step": 5884 + }, + { + "epoch": 0.3280196198651134, + "grad_norm": 0.5623538494110107, + "learning_rate": 7.724924965284169e-05, + "loss": 1.7997, + "step": 5885 + }, + { + "epoch": 0.3280753581182766, + "grad_norm": 0.5270793437957764, + "learning_rate": 7.72417835012659e-05, + "loss": 1.762, + "step": 5886 + }, + { + "epoch": 0.3281310963714397, + "grad_norm": 0.4922736585140228, + "learning_rate": 7.72343164857396e-05, + "loss": 1.29, + "step": 5887 + }, + { + "epoch": 0.32818683462460285, + "grad_norm": 0.5568634867668152, + "learning_rate": 7.722684860649953e-05, + "loss": 1.8285, + "step": 5888 + }, + { + "epoch": 0.32824257287776604, + "grad_norm": 0.5732812285423279, + "learning_rate": 7.721937986378261e-05, + "loss": 1.6134, + "step": 5889 + }, + { + "epoch": 0.32829831113092917, + "grad_norm": 0.5091588497161865, + "learning_rate": 7.721191025782563e-05, + "loss": 1.5536, + "step": 5890 + }, + { + "epoch": 0.3283540493840923, + "grad_norm": 0.5646446347236633, + "learning_rate": 7.720443978886551e-05, + "loss": 1.6102, + "step": 5891 + }, + { + "epoch": 0.3284097876372554, + "grad_norm": 0.5230876207351685, + "learning_rate": 7.71969684571392e-05, + "loss": 1.7258, + "step": 5892 + }, + { + "epoch": 0.3284655258904186, + "grad_norm": 0.5695227980613708, + "learning_rate": 7.718949626288359e-05, + "loss": 1.7538, + "step": 5893 + }, + { + "epoch": 0.32852126414358174, + "grad_norm": 0.5724740028381348, + "learning_rate": 7.718202320633572e-05, + "loss": 1.5929, + "step": 5894 + }, + { + "epoch": 0.32857700239674487, + "grad_norm": 0.5088779926300049, + "learning_rate": 7.717454928773253e-05, + "loss": 1.5781, + "step": 5895 + }, + { + "epoch": 0.32863274064990805, + "grad_norm": 0.6324506402015686, + "learning_rate": 7.716707450731109e-05, + "loss": 1.97, + "step": 5896 + }, + { + "epoch": 0.3286884789030712, + "grad_norm": 0.5300724506378174, + "learning_rate": 7.715959886530843e-05, + "loss": 1.6759, + "step": 5897 + }, + { + "epoch": 0.3287442171562343, + "grad_norm": 0.5645179152488708, + "learning_rate": 7.715212236196164e-05, + "loss": 1.6515, + "step": 5898 + }, + { + "epoch": 0.3287999554093975, + "grad_norm": 0.575449526309967, + "learning_rate": 7.714464499750784e-05, + "loss": 1.7267, + "step": 5899 + }, + { + "epoch": 0.3288556936625606, + "grad_norm": 0.5279715657234192, + "learning_rate": 7.713716677218416e-05, + "loss": 1.6431, + "step": 5900 + }, + { + "epoch": 0.32891143191572375, + "grad_norm": 0.5209466814994812, + "learning_rate": 7.712968768622779e-05, + "loss": 1.5909, + "step": 5901 + }, + { + "epoch": 0.3289671701688869, + "grad_norm": 0.5469819903373718, + "learning_rate": 7.712220773987589e-05, + "loss": 1.6273, + "step": 5902 + }, + { + "epoch": 0.32902290842205006, + "grad_norm": 0.5781688690185547, + "learning_rate": 7.71147269333657e-05, + "loss": 1.8497, + "step": 5903 + }, + { + "epoch": 0.3290786466752132, + "grad_norm": 0.5549498200416565, + "learning_rate": 7.710724526693445e-05, + "loss": 1.6606, + "step": 5904 + }, + { + "epoch": 0.3291343849283763, + "grad_norm": 0.5616956949234009, + "learning_rate": 7.709976274081944e-05, + "loss": 1.8094, + "step": 5905 + }, + { + "epoch": 0.3291901231815395, + "grad_norm": 0.5189547538757324, + "learning_rate": 7.709227935525796e-05, + "loss": 1.7477, + "step": 5906 + }, + { + "epoch": 0.32924586143470264, + "grad_norm": 0.5060945749282837, + "learning_rate": 7.708479511048732e-05, + "loss": 1.4591, + "step": 5907 + }, + { + "epoch": 0.32930159968786576, + "grad_norm": 0.5463743209838867, + "learning_rate": 7.707731000674492e-05, + "loss": 1.6762, + "step": 5908 + }, + { + "epoch": 0.32935733794102895, + "grad_norm": 0.5190552473068237, + "learning_rate": 7.70698240442681e-05, + "loss": 1.529, + "step": 5909 + }, + { + "epoch": 0.3294130761941921, + "grad_norm": 0.5391181111335754, + "learning_rate": 7.70623372232943e-05, + "loss": 1.6953, + "step": 5910 + }, + { + "epoch": 0.3294688144473552, + "grad_norm": 0.5780003070831299, + "learning_rate": 7.705484954406092e-05, + "loss": 1.6728, + "step": 5911 + }, + { + "epoch": 0.3295245527005184, + "grad_norm": 0.554817795753479, + "learning_rate": 7.704736100680547e-05, + "loss": 1.6731, + "step": 5912 + }, + { + "epoch": 0.3295802909536815, + "grad_norm": 0.590787410736084, + "learning_rate": 7.703987161176545e-05, + "loss": 1.9063, + "step": 5913 + }, + { + "epoch": 0.32963602920684465, + "grad_norm": 0.5418079495429993, + "learning_rate": 7.703238135917832e-05, + "loss": 1.6984, + "step": 5914 + }, + { + "epoch": 0.3296917674600078, + "grad_norm": 0.5568365454673767, + "learning_rate": 7.702489024928168e-05, + "loss": 1.7057, + "step": 5915 + }, + { + "epoch": 0.32974750571317096, + "grad_norm": 0.5823662281036377, + "learning_rate": 7.701739828231309e-05, + "loss": 1.8851, + "step": 5916 + }, + { + "epoch": 0.3298032439663341, + "grad_norm": 0.588046133518219, + "learning_rate": 7.700990545851014e-05, + "loss": 1.6514, + "step": 5917 + }, + { + "epoch": 0.3298589822194972, + "grad_norm": 0.5833228826522827, + "learning_rate": 7.700241177811048e-05, + "loss": 1.7474, + "step": 5918 + }, + { + "epoch": 0.3299147204726604, + "grad_norm": 0.5376124978065491, + "learning_rate": 7.699491724135175e-05, + "loss": 1.65, + "step": 5919 + }, + { + "epoch": 0.32997045872582353, + "grad_norm": 0.579406201839447, + "learning_rate": 7.698742184847163e-05, + "loss": 1.7039, + "step": 5920 + }, + { + "epoch": 0.33002619697898666, + "grad_norm": 0.5547471046447754, + "learning_rate": 7.697992559970784e-05, + "loss": 1.7428, + "step": 5921 + }, + { + "epoch": 0.33008193523214985, + "grad_norm": 0.5924109816551208, + "learning_rate": 7.697242849529812e-05, + "loss": 1.7935, + "step": 5922 + }, + { + "epoch": 0.330137673485313, + "grad_norm": 0.5609079003334045, + "learning_rate": 7.69649305354802e-05, + "loss": 1.7302, + "step": 5923 + }, + { + "epoch": 0.3301934117384761, + "grad_norm": 0.5709410309791565, + "learning_rate": 7.695743172049192e-05, + "loss": 1.6529, + "step": 5924 + }, + { + "epoch": 0.33024914999163923, + "grad_norm": 0.5341020822525024, + "learning_rate": 7.694993205057108e-05, + "loss": 1.696, + "step": 5925 + }, + { + "epoch": 0.3303048882448024, + "grad_norm": 0.5852230787277222, + "learning_rate": 7.694243152595552e-05, + "loss": 1.6173, + "step": 5926 + }, + { + "epoch": 0.33036062649796555, + "grad_norm": 0.5338337421417236, + "learning_rate": 7.693493014688313e-05, + "loss": 1.4818, + "step": 5927 + }, + { + "epoch": 0.3304163647511287, + "grad_norm": 0.5398749113082886, + "learning_rate": 7.69274279135918e-05, + "loss": 1.631, + "step": 5928 + }, + { + "epoch": 0.33047210300429186, + "grad_norm": 0.5520002245903015, + "learning_rate": 7.691992482631944e-05, + "loss": 1.8426, + "step": 5929 + }, + { + "epoch": 0.330527841257455, + "grad_norm": 0.5498268008232117, + "learning_rate": 7.691242088530401e-05, + "loss": 1.8106, + "step": 5930 + }, + { + "epoch": 0.3305835795106181, + "grad_norm": 0.5437809824943542, + "learning_rate": 7.690491609078351e-05, + "loss": 1.7523, + "step": 5931 + }, + { + "epoch": 0.3306393177637813, + "grad_norm": 0.6089059114456177, + "learning_rate": 7.689741044299595e-05, + "loss": 1.7299, + "step": 5932 + }, + { + "epoch": 0.33069505601694443, + "grad_norm": 0.5289489030838013, + "learning_rate": 7.688990394217933e-05, + "loss": 1.691, + "step": 5933 + }, + { + "epoch": 0.33075079427010756, + "grad_norm": 0.555590033531189, + "learning_rate": 7.688239658857174e-05, + "loss": 1.45, + "step": 5934 + }, + { + "epoch": 0.33080653252327075, + "grad_norm": 0.6252313256263733, + "learning_rate": 7.687488838241128e-05, + "loss": 1.8009, + "step": 5935 + }, + { + "epoch": 0.3308622707764339, + "grad_norm": 0.5846867561340332, + "learning_rate": 7.686737932393605e-05, + "loss": 1.7873, + "step": 5936 + }, + { + "epoch": 0.330918009029597, + "grad_norm": 0.5312223434448242, + "learning_rate": 7.685986941338419e-05, + "loss": 1.6196, + "step": 5937 + }, + { + "epoch": 0.33097374728276013, + "grad_norm": 0.5511593222618103, + "learning_rate": 7.685235865099387e-05, + "loss": 1.7915, + "step": 5938 + }, + { + "epoch": 0.3310294855359233, + "grad_norm": 0.5287107825279236, + "learning_rate": 7.684484703700332e-05, + "loss": 1.6648, + "step": 5939 + }, + { + "epoch": 0.33108522378908645, + "grad_norm": 0.5697956681251526, + "learning_rate": 7.683733457165071e-05, + "loss": 2.0054, + "step": 5940 + }, + { + "epoch": 0.3311409620422496, + "grad_norm": 0.5331019759178162, + "learning_rate": 7.682982125517433e-05, + "loss": 1.7598, + "step": 5941 + }, + { + "epoch": 0.33119670029541276, + "grad_norm": 0.5488009452819824, + "learning_rate": 7.682230708781244e-05, + "loss": 1.4258, + "step": 5942 + }, + { + "epoch": 0.3312524385485759, + "grad_norm": 0.5415595173835754, + "learning_rate": 7.681479206980338e-05, + "loss": 1.766, + "step": 5943 + }, + { + "epoch": 0.331308176801739, + "grad_norm": 0.6208872199058533, + "learning_rate": 7.680727620138542e-05, + "loss": 1.879, + "step": 5944 + }, + { + "epoch": 0.3313639150549022, + "grad_norm": 0.5650165677070618, + "learning_rate": 7.679975948279699e-05, + "loss": 1.4933, + "step": 5945 + }, + { + "epoch": 0.33141965330806533, + "grad_norm": 0.5754852890968323, + "learning_rate": 7.679224191427642e-05, + "loss": 1.6821, + "step": 5946 + }, + { + "epoch": 0.33147539156122846, + "grad_norm": 0.5749027132987976, + "learning_rate": 7.678472349606215e-05, + "loss": 1.8599, + "step": 5947 + }, + { + "epoch": 0.3315311298143916, + "grad_norm": 0.5200157761573792, + "learning_rate": 7.677720422839263e-05, + "loss": 1.6659, + "step": 5948 + }, + { + "epoch": 0.3315868680675548, + "grad_norm": 0.6056989431381226, + "learning_rate": 7.676968411150629e-05, + "loss": 1.9657, + "step": 5949 + }, + { + "epoch": 0.3316426063207179, + "grad_norm": 0.5650584697723389, + "learning_rate": 7.676216314564166e-05, + "loss": 1.9396, + "step": 5950 + }, + { + "epoch": 0.33169834457388103, + "grad_norm": 0.5425543785095215, + "learning_rate": 7.675464133103726e-05, + "loss": 1.6447, + "step": 5951 + }, + { + "epoch": 0.3317540828270442, + "grad_norm": 0.5751011967658997, + "learning_rate": 7.674711866793163e-05, + "loss": 1.7975, + "step": 5952 + }, + { + "epoch": 0.33180982108020735, + "grad_norm": 0.521195113658905, + "learning_rate": 7.673959515656333e-05, + "loss": 1.6343, + "step": 5953 + }, + { + "epoch": 0.3318655593333705, + "grad_norm": 0.5193372964859009, + "learning_rate": 7.673207079717098e-05, + "loss": 1.7215, + "step": 5954 + }, + { + "epoch": 0.33192129758653366, + "grad_norm": 0.4974719285964966, + "learning_rate": 7.672454558999318e-05, + "loss": 1.5058, + "step": 5955 + }, + { + "epoch": 0.3319770358396968, + "grad_norm": 0.610576868057251, + "learning_rate": 7.671701953526863e-05, + "loss": 1.8826, + "step": 5956 + }, + { + "epoch": 0.3320327740928599, + "grad_norm": 0.5185069441795349, + "learning_rate": 7.670949263323599e-05, + "loss": 1.3823, + "step": 5957 + }, + { + "epoch": 0.3320885123460231, + "grad_norm": 0.5048871636390686, + "learning_rate": 7.670196488413397e-05, + "loss": 1.3208, + "step": 5958 + }, + { + "epoch": 0.33214425059918623, + "grad_norm": 0.512177586555481, + "learning_rate": 7.66944362882013e-05, + "loss": 1.4293, + "step": 5959 + }, + { + "epoch": 0.33219998885234936, + "grad_norm": 0.5636778473854065, + "learning_rate": 7.668690684567676e-05, + "loss": 1.5585, + "step": 5960 + }, + { + "epoch": 0.3322557271055125, + "grad_norm": 0.5499832630157471, + "learning_rate": 7.667937655679913e-05, + "loss": 1.5834, + "step": 5961 + }, + { + "epoch": 0.3323114653586757, + "grad_norm": 0.6139015555381775, + "learning_rate": 7.667184542180723e-05, + "loss": 2.0935, + "step": 5962 + }, + { + "epoch": 0.3323672036118388, + "grad_norm": 0.5284989476203918, + "learning_rate": 7.666431344093988e-05, + "loss": 1.6838, + "step": 5963 + }, + { + "epoch": 0.33242294186500193, + "grad_norm": 0.5448603630065918, + "learning_rate": 7.665678061443599e-05, + "loss": 1.6688, + "step": 5964 + }, + { + "epoch": 0.3324786801181651, + "grad_norm": 0.5356377959251404, + "learning_rate": 7.664924694253443e-05, + "loss": 1.6131, + "step": 5965 + }, + { + "epoch": 0.33253441837132824, + "grad_norm": 0.5786362886428833, + "learning_rate": 7.664171242547414e-05, + "loss": 1.859, + "step": 5966 + }, + { + "epoch": 0.3325901566244914, + "grad_norm": 0.5811523199081421, + "learning_rate": 7.663417706349407e-05, + "loss": 1.6848, + "step": 5967 + }, + { + "epoch": 0.33264589487765456, + "grad_norm": 0.5504920482635498, + "learning_rate": 7.662664085683317e-05, + "loss": 1.7, + "step": 5968 + }, + { + "epoch": 0.3327016331308177, + "grad_norm": 0.6110926866531372, + "learning_rate": 7.66191038057305e-05, + "loss": 1.87, + "step": 5969 + }, + { + "epoch": 0.3327573713839808, + "grad_norm": 0.5238990187644958, + "learning_rate": 7.661156591042502e-05, + "loss": 1.6083, + "step": 5970 + }, + { + "epoch": 0.33281310963714394, + "grad_norm": 0.5919533371925354, + "learning_rate": 7.660402717115584e-05, + "loss": 1.6786, + "step": 5971 + }, + { + "epoch": 0.33286884789030713, + "grad_norm": 0.565631091594696, + "learning_rate": 7.659648758816205e-05, + "loss": 1.595, + "step": 5972 + }, + { + "epoch": 0.33292458614347026, + "grad_norm": 0.6189529299736023, + "learning_rate": 7.658894716168271e-05, + "loss": 2.0188, + "step": 5973 + }, + { + "epoch": 0.3329803243966334, + "grad_norm": 0.5532551407814026, + "learning_rate": 7.658140589195701e-05, + "loss": 1.6095, + "step": 5974 + }, + { + "epoch": 0.33303606264979657, + "grad_norm": 0.4914916157722473, + "learning_rate": 7.657386377922409e-05, + "loss": 1.6199, + "step": 5975 + }, + { + "epoch": 0.3330918009029597, + "grad_norm": 0.5677047371864319, + "learning_rate": 7.656632082372315e-05, + "loss": 1.5635, + "step": 5976 + }, + { + "epoch": 0.33314753915612283, + "grad_norm": 0.5638590455055237, + "learning_rate": 7.65587770256934e-05, + "loss": 1.7578, + "step": 5977 + }, + { + "epoch": 0.333203277409286, + "grad_norm": 0.5115950107574463, + "learning_rate": 7.655123238537409e-05, + "loss": 1.4157, + "step": 5978 + }, + { + "epoch": 0.33325901566244914, + "grad_norm": 0.6125264763832092, + "learning_rate": 7.65436869030045e-05, + "loss": 1.8876, + "step": 5979 + }, + { + "epoch": 0.33331475391561227, + "grad_norm": 0.5354574918746948, + "learning_rate": 7.653614057882393e-05, + "loss": 1.7052, + "step": 5980 + }, + { + "epoch": 0.33337049216877546, + "grad_norm": 0.5426600575447083, + "learning_rate": 7.652859341307168e-05, + "loss": 1.7011, + "step": 5981 + }, + { + "epoch": 0.3334262304219386, + "grad_norm": 0.7442419528961182, + "learning_rate": 7.652104540598712e-05, + "loss": 1.7664, + "step": 5982 + }, + { + "epoch": 0.3334819686751017, + "grad_norm": 0.5431948900222778, + "learning_rate": 7.651349655780965e-05, + "loss": 1.5627, + "step": 5983 + }, + { + "epoch": 0.33353770692826484, + "grad_norm": 0.5939268469810486, + "learning_rate": 7.650594686877863e-05, + "loss": 1.8128, + "step": 5984 + }, + { + "epoch": 0.333593445181428, + "grad_norm": 0.540123462677002, + "learning_rate": 7.649839633913352e-05, + "loss": 1.6395, + "step": 5985 + }, + { + "epoch": 0.33364918343459116, + "grad_norm": 0.5777207016944885, + "learning_rate": 7.649084496911378e-05, + "loss": 1.7467, + "step": 5986 + }, + { + "epoch": 0.3337049216877543, + "grad_norm": 0.5720601081848145, + "learning_rate": 7.648329275895889e-05, + "loss": 1.8314, + "step": 5987 + }, + { + "epoch": 0.33376065994091747, + "grad_norm": 0.5010839104652405, + "learning_rate": 7.647573970890837e-05, + "loss": 1.5876, + "step": 5988 + }, + { + "epoch": 0.3338163981940806, + "grad_norm": 0.5364264249801636, + "learning_rate": 7.646818581920173e-05, + "loss": 1.6042, + "step": 5989 + }, + { + "epoch": 0.33387213644724373, + "grad_norm": 0.5355646014213562, + "learning_rate": 7.646063109007858e-05, + "loss": 1.5054, + "step": 5990 + }, + { + "epoch": 0.3339278747004069, + "grad_norm": 0.5173195600509644, + "learning_rate": 7.645307552177847e-05, + "loss": 1.7355, + "step": 5991 + }, + { + "epoch": 0.33398361295357004, + "grad_norm": 0.5141093134880066, + "learning_rate": 7.644551911454103e-05, + "loss": 1.5428, + "step": 5992 + }, + { + "epoch": 0.33403935120673317, + "grad_norm": 0.5739405751228333, + "learning_rate": 7.643796186860595e-05, + "loss": 1.8064, + "step": 5993 + }, + { + "epoch": 0.3340950894598963, + "grad_norm": 0.6502695083618164, + "learning_rate": 7.643040378421282e-05, + "loss": 1.9495, + "step": 5994 + }, + { + "epoch": 0.3341508277130595, + "grad_norm": 0.5652748942375183, + "learning_rate": 7.64228448616014e-05, + "loss": 1.6926, + "step": 5995 + }, + { + "epoch": 0.3342065659662226, + "grad_norm": 0.5500004291534424, + "learning_rate": 7.64152851010114e-05, + "loss": 1.6566, + "step": 5996 + }, + { + "epoch": 0.33426230421938574, + "grad_norm": 0.6248365044593811, + "learning_rate": 7.640772450268255e-05, + "loss": 1.6196, + "step": 5997 + }, + { + "epoch": 0.3343180424725489, + "grad_norm": 0.5509215593338013, + "learning_rate": 7.640016306685467e-05, + "loss": 1.6845, + "step": 5998 + }, + { + "epoch": 0.33437378072571206, + "grad_norm": 0.6251245141029358, + "learning_rate": 7.639260079376753e-05, + "loss": 1.9948, + "step": 5999 + }, + { + "epoch": 0.3344295189788752, + "grad_norm": 0.536384642124176, + "learning_rate": 7.638503768366098e-05, + "loss": 1.6778, + "step": 6000 + }, + { + "epoch": 0.33448525723203837, + "grad_norm": 0.5998651385307312, + "learning_rate": 7.637747373677486e-05, + "loss": 1.6279, + "step": 6001 + }, + { + "epoch": 0.3345409954852015, + "grad_norm": 0.5673259496688843, + "learning_rate": 7.636990895334907e-05, + "loss": 1.7001, + "step": 6002 + }, + { + "epoch": 0.3345967337383646, + "grad_norm": 0.5465088486671448, + "learning_rate": 7.63623433336235e-05, + "loss": 1.7576, + "step": 6003 + }, + { + "epoch": 0.3346524719915278, + "grad_norm": 0.5544756054878235, + "learning_rate": 7.635477687783814e-05, + "loss": 1.844, + "step": 6004 + }, + { + "epoch": 0.33470821024469094, + "grad_norm": 0.5186877846717834, + "learning_rate": 7.634720958623287e-05, + "loss": 1.6125, + "step": 6005 + }, + { + "epoch": 0.33476394849785407, + "grad_norm": 0.5501444935798645, + "learning_rate": 7.633964145904777e-05, + "loss": 1.7169, + "step": 6006 + }, + { + "epoch": 0.3348196867510172, + "grad_norm": 0.5606530904769897, + "learning_rate": 7.633207249652278e-05, + "loss": 1.6944, + "step": 6007 + }, + { + "epoch": 0.3348754250041804, + "grad_norm": 0.49215444922447205, + "learning_rate": 7.6324502698898e-05, + "loss": 1.4025, + "step": 6008 + }, + { + "epoch": 0.3349311632573435, + "grad_norm": 0.555610716342926, + "learning_rate": 7.631693206641346e-05, + "loss": 1.7292, + "step": 6009 + }, + { + "epoch": 0.33498690151050664, + "grad_norm": 0.5174264907836914, + "learning_rate": 7.630936059930927e-05, + "loss": 1.5525, + "step": 6010 + }, + { + "epoch": 0.3350426397636698, + "grad_norm": 0.5901679992675781, + "learning_rate": 7.630178829782558e-05, + "loss": 1.7284, + "step": 6011 + }, + { + "epoch": 0.33509837801683295, + "grad_norm": 0.5459769368171692, + "learning_rate": 7.629421516220249e-05, + "loss": 1.6727, + "step": 6012 + }, + { + "epoch": 0.3351541162699961, + "grad_norm": 0.5339307188987732, + "learning_rate": 7.628664119268023e-05, + "loss": 1.7325, + "step": 6013 + }, + { + "epoch": 0.33520985452315927, + "grad_norm": 0.533289909362793, + "learning_rate": 7.627906638949895e-05, + "loss": 1.5102, + "step": 6014 + }, + { + "epoch": 0.3352655927763224, + "grad_norm": 0.5171735286712646, + "learning_rate": 7.62714907528989e-05, + "loss": 1.5725, + "step": 6015 + }, + { + "epoch": 0.3353213310294855, + "grad_norm": 0.585667610168457, + "learning_rate": 7.626391428312035e-05, + "loss": 1.8119, + "step": 6016 + }, + { + "epoch": 0.33537706928264865, + "grad_norm": 0.504396378993988, + "learning_rate": 7.625633698040357e-05, + "loss": 1.4209, + "step": 6017 + }, + { + "epoch": 0.33543280753581184, + "grad_norm": 0.5608323216438293, + "learning_rate": 7.624875884498886e-05, + "loss": 1.8436, + "step": 6018 + }, + { + "epoch": 0.33548854578897497, + "grad_norm": 0.5625400543212891, + "learning_rate": 7.624117987711656e-05, + "loss": 1.836, + "step": 6019 + }, + { + "epoch": 0.3355442840421381, + "grad_norm": 0.6377468109130859, + "learning_rate": 7.623360007702702e-05, + "loss": 1.7539, + "step": 6020 + }, + { + "epoch": 0.3356000222953013, + "grad_norm": 0.556115984916687, + "learning_rate": 7.622601944496064e-05, + "loss": 1.6686, + "step": 6021 + }, + { + "epoch": 0.3356557605484644, + "grad_norm": 0.49739575386047363, + "learning_rate": 7.621843798115785e-05, + "loss": 1.5361, + "step": 6022 + }, + { + "epoch": 0.33571149880162754, + "grad_norm": 0.5968783497810364, + "learning_rate": 7.621085568585905e-05, + "loss": 1.8225, + "step": 6023 + }, + { + "epoch": 0.3357672370547907, + "grad_norm": 0.575768232345581, + "learning_rate": 7.620327255930474e-05, + "loss": 1.908, + "step": 6024 + }, + { + "epoch": 0.33582297530795385, + "grad_norm": 0.5628235340118408, + "learning_rate": 7.61956886017354e-05, + "loss": 1.6388, + "step": 6025 + }, + { + "epoch": 0.335878713561117, + "grad_norm": 0.5842387676239014, + "learning_rate": 7.618810381339155e-05, + "loss": 1.8774, + "step": 6026 + }, + { + "epoch": 0.33593445181428017, + "grad_norm": 0.5307137370109558, + "learning_rate": 7.618051819451373e-05, + "loss": 1.6372, + "step": 6027 + }, + { + "epoch": 0.3359901900674433, + "grad_norm": 0.5524066090583801, + "learning_rate": 7.617293174534253e-05, + "loss": 1.7415, + "step": 6028 + }, + { + "epoch": 0.3360459283206064, + "grad_norm": 0.5315592885017395, + "learning_rate": 7.616534446611851e-05, + "loss": 1.6005, + "step": 6029 + }, + { + "epoch": 0.33610166657376955, + "grad_norm": 0.5379803776741028, + "learning_rate": 7.615775635708234e-05, + "loss": 1.6998, + "step": 6030 + }, + { + "epoch": 0.33615740482693274, + "grad_norm": 0.593471884727478, + "learning_rate": 7.615016741847463e-05, + "loss": 1.6948, + "step": 6031 + }, + { + "epoch": 0.33621314308009587, + "grad_norm": 0.5759322643280029, + "learning_rate": 7.614257765053609e-05, + "loss": 1.5575, + "step": 6032 + }, + { + "epoch": 0.336268881333259, + "grad_norm": 0.5627144575119019, + "learning_rate": 7.61349870535074e-05, + "loss": 1.7633, + "step": 6033 + }, + { + "epoch": 0.3363246195864222, + "grad_norm": 0.5872805714607239, + "learning_rate": 7.612739562762929e-05, + "loss": 1.8196, + "step": 6034 + }, + { + "epoch": 0.3363803578395853, + "grad_norm": 0.5651592016220093, + "learning_rate": 7.611980337314254e-05, + "loss": 1.7916, + "step": 6035 + }, + { + "epoch": 0.33643609609274844, + "grad_norm": 0.5263227820396423, + "learning_rate": 7.61122102902879e-05, + "loss": 1.6909, + "step": 6036 + }, + { + "epoch": 0.3364918343459116, + "grad_norm": 0.5474349856376648, + "learning_rate": 7.610461637930621e-05, + "loss": 1.7166, + "step": 6037 + }, + { + "epoch": 0.33654757259907475, + "grad_norm": 0.5443328022956848, + "learning_rate": 7.609702164043829e-05, + "loss": 1.6479, + "step": 6038 + }, + { + "epoch": 0.3366033108522379, + "grad_norm": 0.5788392424583435, + "learning_rate": 7.6089426073925e-05, + "loss": 1.7645, + "step": 6039 + }, + { + "epoch": 0.336659049105401, + "grad_norm": 0.5407717823982239, + "learning_rate": 7.608182968000721e-05, + "loss": 1.7543, + "step": 6040 + }, + { + "epoch": 0.3367147873585642, + "grad_norm": 0.5548073649406433, + "learning_rate": 7.607423245892586e-05, + "loss": 1.6023, + "step": 6041 + }, + { + "epoch": 0.3367705256117273, + "grad_norm": 0.5452112555503845, + "learning_rate": 7.606663441092188e-05, + "loss": 1.7298, + "step": 6042 + }, + { + "epoch": 0.33682626386489045, + "grad_norm": 0.5845810770988464, + "learning_rate": 7.605903553623625e-05, + "loss": 1.9093, + "step": 6043 + }, + { + "epoch": 0.33688200211805364, + "grad_norm": 0.5392171740531921, + "learning_rate": 7.605143583510991e-05, + "loss": 1.7111, + "step": 6044 + }, + { + "epoch": 0.33693774037121677, + "grad_norm": 0.51267009973526, + "learning_rate": 7.604383530778396e-05, + "loss": 1.5154, + "step": 6045 + }, + { + "epoch": 0.3369934786243799, + "grad_norm": 0.5741301774978638, + "learning_rate": 7.603623395449937e-05, + "loss": 1.7287, + "step": 6046 + }, + { + "epoch": 0.3370492168775431, + "grad_norm": 0.5356318354606628, + "learning_rate": 7.602863177549724e-05, + "loss": 1.7299, + "step": 6047 + }, + { + "epoch": 0.3371049551307062, + "grad_norm": 0.5820077061653137, + "learning_rate": 7.602102877101869e-05, + "loss": 1.8304, + "step": 6048 + }, + { + "epoch": 0.33716069338386934, + "grad_norm": 0.5404535531997681, + "learning_rate": 7.60134249413048e-05, + "loss": 1.5754, + "step": 6049 + }, + { + "epoch": 0.3372164316370325, + "grad_norm": 0.5398672819137573, + "learning_rate": 7.600582028659675e-05, + "loss": 1.7943, + "step": 6050 + }, + { + "epoch": 0.33727216989019565, + "grad_norm": 0.5376107692718506, + "learning_rate": 7.59982148071357e-05, + "loss": 1.4528, + "step": 6051 + }, + { + "epoch": 0.3373279081433588, + "grad_norm": 0.5899469256401062, + "learning_rate": 7.599060850316287e-05, + "loss": 1.7503, + "step": 6052 + }, + { + "epoch": 0.3373836463965219, + "grad_norm": 0.5668314695358276, + "learning_rate": 7.598300137491946e-05, + "loss": 1.7732, + "step": 6053 + }, + { + "epoch": 0.3374393846496851, + "grad_norm": 0.6154149174690247, + "learning_rate": 7.597539342264675e-05, + "loss": 1.6534, + "step": 6054 + }, + { + "epoch": 0.3374951229028482, + "grad_norm": 0.5487502813339233, + "learning_rate": 7.596778464658599e-05, + "loss": 1.6286, + "step": 6055 + }, + { + "epoch": 0.33755086115601135, + "grad_norm": 0.5876896977424622, + "learning_rate": 7.596017504697851e-05, + "loss": 1.7787, + "step": 6056 + }, + { + "epoch": 0.33760659940917453, + "grad_norm": 0.5587677359580994, + "learning_rate": 7.595256462406564e-05, + "loss": 1.7862, + "step": 6057 + }, + { + "epoch": 0.33766233766233766, + "grad_norm": 0.5694131255149841, + "learning_rate": 7.594495337808873e-05, + "loss": 1.6926, + "step": 6058 + }, + { + "epoch": 0.3377180759155008, + "grad_norm": 0.5591508150100708, + "learning_rate": 7.593734130928918e-05, + "loss": 1.6135, + "step": 6059 + }, + { + "epoch": 0.337773814168664, + "grad_norm": 0.5355261564254761, + "learning_rate": 7.592972841790837e-05, + "loss": 1.5746, + "step": 6060 + }, + { + "epoch": 0.3378295524218271, + "grad_norm": 0.5518434047698975, + "learning_rate": 7.592211470418777e-05, + "loss": 1.6457, + "step": 6061 + }, + { + "epoch": 0.33788529067499024, + "grad_norm": 0.5891780257225037, + "learning_rate": 7.59145001683688e-05, + "loss": 1.7026, + "step": 6062 + }, + { + "epoch": 0.33794102892815336, + "grad_norm": 0.5723276734352112, + "learning_rate": 7.590688481069302e-05, + "loss": 1.8168, + "step": 6063 + }, + { + "epoch": 0.33799676718131655, + "grad_norm": 0.5468711853027344, + "learning_rate": 7.589926863140187e-05, + "loss": 1.607, + "step": 6064 + }, + { + "epoch": 0.3380525054344797, + "grad_norm": 0.6062466502189636, + "learning_rate": 7.589165163073695e-05, + "loss": 1.9372, + "step": 6065 + }, + { + "epoch": 0.3381082436876428, + "grad_norm": 0.5140287280082703, + "learning_rate": 7.588403380893979e-05, + "loss": 1.6545, + "step": 6066 + }, + { + "epoch": 0.338163981940806, + "grad_norm": 0.5543786287307739, + "learning_rate": 7.587641516625197e-05, + "loss": 1.8205, + "step": 6067 + }, + { + "epoch": 0.3382197201939691, + "grad_norm": 0.5844648480415344, + "learning_rate": 7.586879570291514e-05, + "loss": 1.8597, + "step": 6068 + }, + { + "epoch": 0.33827545844713225, + "grad_norm": 0.5109902024269104, + "learning_rate": 7.586117541917095e-05, + "loss": 1.5266, + "step": 6069 + }, + { + "epoch": 0.33833119670029543, + "grad_norm": 0.5208814740180969, + "learning_rate": 7.585355431526104e-05, + "loss": 1.721, + "step": 6070 + }, + { + "epoch": 0.33838693495345856, + "grad_norm": 0.5144614577293396, + "learning_rate": 7.584593239142712e-05, + "loss": 1.624, + "step": 6071 + }, + { + "epoch": 0.3384426732066217, + "grad_norm": 0.5855271220207214, + "learning_rate": 7.583830964791094e-05, + "loss": 1.8765, + "step": 6072 + }, + { + "epoch": 0.3384984114597849, + "grad_norm": 0.5410987138748169, + "learning_rate": 7.58306860849542e-05, + "loss": 1.6027, + "step": 6073 + }, + { + "epoch": 0.338554149712948, + "grad_norm": 0.6230753064155579, + "learning_rate": 7.582306170279872e-05, + "loss": 1.8485, + "step": 6074 + }, + { + "epoch": 0.33860988796611113, + "grad_norm": 0.5517315864562988, + "learning_rate": 7.581543650168628e-05, + "loss": 1.7822, + "step": 6075 + }, + { + "epoch": 0.33866562621927426, + "grad_norm": 0.5739060044288635, + "learning_rate": 7.580781048185871e-05, + "loss": 1.6443, + "step": 6076 + }, + { + "epoch": 0.33872136447243745, + "grad_norm": 0.5618791580200195, + "learning_rate": 7.580018364355785e-05, + "loss": 1.5943, + "step": 6077 + }, + { + "epoch": 0.3387771027256006, + "grad_norm": 0.5723870396614075, + "learning_rate": 7.579255598702562e-05, + "loss": 1.4501, + "step": 6078 + }, + { + "epoch": 0.3388328409787637, + "grad_norm": 0.5427421927452087, + "learning_rate": 7.578492751250386e-05, + "loss": 1.7001, + "step": 6079 + }, + { + "epoch": 0.3388885792319269, + "grad_norm": 0.5765356421470642, + "learning_rate": 7.577729822023455e-05, + "loss": 1.6652, + "step": 6080 + }, + { + "epoch": 0.33894431748509, + "grad_norm": 0.5492302179336548, + "learning_rate": 7.576966811045963e-05, + "loss": 1.6988, + "step": 6081 + }, + { + "epoch": 0.33900005573825315, + "grad_norm": 0.5814895033836365, + "learning_rate": 7.576203718342108e-05, + "loss": 1.9584, + "step": 6082 + }, + { + "epoch": 0.33905579399141633, + "grad_norm": 0.6068232655525208, + "learning_rate": 7.575440543936092e-05, + "loss": 2.0357, + "step": 6083 + }, + { + "epoch": 0.33911153224457946, + "grad_norm": 0.5426899790763855, + "learning_rate": 7.574677287852117e-05, + "loss": 1.6323, + "step": 6084 + }, + { + "epoch": 0.3391672704977426, + "grad_norm": 0.5811708569526672, + "learning_rate": 7.573913950114391e-05, + "loss": 1.538, + "step": 6085 + }, + { + "epoch": 0.3392230087509057, + "grad_norm": 0.5753393769264221, + "learning_rate": 7.573150530747122e-05, + "loss": 1.6013, + "step": 6086 + }, + { + "epoch": 0.3392787470040689, + "grad_norm": 0.5427485108375549, + "learning_rate": 7.572387029774519e-05, + "loss": 1.6444, + "step": 6087 + }, + { + "epoch": 0.33933448525723203, + "grad_norm": 0.5431930422782898, + "learning_rate": 7.571623447220797e-05, + "loss": 1.6733, + "step": 6088 + }, + { + "epoch": 0.33939022351039516, + "grad_norm": 0.555357813835144, + "learning_rate": 7.570859783110176e-05, + "loss": 1.7219, + "step": 6089 + }, + { + "epoch": 0.33944596176355835, + "grad_norm": 0.5578222274780273, + "learning_rate": 7.570096037466869e-05, + "loss": 1.407, + "step": 6090 + }, + { + "epoch": 0.3395017000167215, + "grad_norm": 0.5213090777397156, + "learning_rate": 7.5693322103151e-05, + "loss": 1.4608, + "step": 6091 + }, + { + "epoch": 0.3395574382698846, + "grad_norm": 0.5651876330375671, + "learning_rate": 7.568568301679096e-05, + "loss": 1.6756, + "step": 6092 + }, + { + "epoch": 0.3396131765230478, + "grad_norm": 0.5914562940597534, + "learning_rate": 7.56780431158308e-05, + "loss": 1.7648, + "step": 6093 + }, + { + "epoch": 0.3396689147762109, + "grad_norm": 0.5577222108840942, + "learning_rate": 7.567040240051281e-05, + "loss": 1.6954, + "step": 6094 + }, + { + "epoch": 0.33972465302937405, + "grad_norm": 0.5938786268234253, + "learning_rate": 7.566276087107935e-05, + "loss": 1.8131, + "step": 6095 + }, + { + "epoch": 0.33978039128253723, + "grad_norm": 0.5387003421783447, + "learning_rate": 7.565511852777274e-05, + "loss": 1.6522, + "step": 6096 + }, + { + "epoch": 0.33983612953570036, + "grad_norm": 0.5465493202209473, + "learning_rate": 7.564747537083534e-05, + "loss": 1.6971, + "step": 6097 + }, + { + "epoch": 0.3398918677888635, + "grad_norm": 0.5273247361183167, + "learning_rate": 7.563983140050955e-05, + "loss": 1.6759, + "step": 6098 + }, + { + "epoch": 0.3399476060420266, + "grad_norm": 0.5733767151832581, + "learning_rate": 7.563218661703782e-05, + "loss": 1.7203, + "step": 6099 + }, + { + "epoch": 0.3400033442951898, + "grad_norm": 0.6077031493186951, + "learning_rate": 7.562454102066255e-05, + "loss": 1.9364, + "step": 6100 + }, + { + "epoch": 0.34005908254835293, + "grad_norm": 0.5688176155090332, + "learning_rate": 7.561689461162625e-05, + "loss": 1.6623, + "step": 6101 + }, + { + "epoch": 0.34011482080151606, + "grad_norm": 0.5663187503814697, + "learning_rate": 7.56092473901714e-05, + "loss": 1.567, + "step": 6102 + }, + { + "epoch": 0.34017055905467924, + "grad_norm": 0.6150177121162415, + "learning_rate": 7.560159935654056e-05, + "loss": 1.8714, + "step": 6103 + }, + { + "epoch": 0.3402262973078424, + "grad_norm": 0.5515531301498413, + "learning_rate": 7.559395051097624e-05, + "loss": 1.6713, + "step": 6104 + }, + { + "epoch": 0.3402820355610055, + "grad_norm": 0.687240481376648, + "learning_rate": 7.558630085372105e-05, + "loss": 1.6552, + "step": 6105 + }, + { + "epoch": 0.3403377738141687, + "grad_norm": 0.5493181943893433, + "learning_rate": 7.557865038501756e-05, + "loss": 1.65, + "step": 6106 + }, + { + "epoch": 0.3403935120673318, + "grad_norm": 0.5683436989784241, + "learning_rate": 7.55709991051084e-05, + "loss": 1.8507, + "step": 6107 + }, + { + "epoch": 0.34044925032049494, + "grad_norm": 0.5895001292228699, + "learning_rate": 7.556334701423627e-05, + "loss": 2.0143, + "step": 6108 + }, + { + "epoch": 0.3405049885736581, + "grad_norm": 0.5967059135437012, + "learning_rate": 7.555569411264378e-05, + "loss": 1.9006, + "step": 6109 + }, + { + "epoch": 0.34056072682682126, + "grad_norm": 0.5140407085418701, + "learning_rate": 7.554804040057369e-05, + "loss": 1.4028, + "step": 6110 + }, + { + "epoch": 0.3406164650799844, + "grad_norm": 0.5586955547332764, + "learning_rate": 7.554038587826872e-05, + "loss": 1.6835, + "step": 6111 + }, + { + "epoch": 0.3406722033331475, + "grad_norm": 0.4853399395942688, + "learning_rate": 7.553273054597163e-05, + "loss": 1.5901, + "step": 6112 + }, + { + "epoch": 0.3407279415863107, + "grad_norm": 0.5674946308135986, + "learning_rate": 7.552507440392518e-05, + "loss": 1.8776, + "step": 6113 + }, + { + "epoch": 0.34078367983947383, + "grad_norm": 0.5115534663200378, + "learning_rate": 7.551741745237218e-05, + "loss": 1.4647, + "step": 6114 + }, + { + "epoch": 0.34083941809263696, + "grad_norm": 0.6239203214645386, + "learning_rate": 7.55097596915555e-05, + "loss": 1.8638, + "step": 6115 + }, + { + "epoch": 0.34089515634580014, + "grad_norm": 0.5367839336395264, + "learning_rate": 7.550210112171796e-05, + "loss": 1.7598, + "step": 6116 + }, + { + "epoch": 0.34095089459896327, + "grad_norm": 0.5434908270835876, + "learning_rate": 7.549444174310246e-05, + "loss": 1.8239, + "step": 6117 + }, + { + "epoch": 0.3410066328521264, + "grad_norm": 0.5503940582275391, + "learning_rate": 7.548678155595192e-05, + "loss": 1.7103, + "step": 6118 + }, + { + "epoch": 0.3410623711052896, + "grad_norm": 0.5601882338523865, + "learning_rate": 7.547912056050925e-05, + "loss": 1.8269, + "step": 6119 + }, + { + "epoch": 0.3411181093584527, + "grad_norm": 0.5472147464752197, + "learning_rate": 7.547145875701744e-05, + "loss": 1.7221, + "step": 6120 + }, + { + "epoch": 0.34117384761161584, + "grad_norm": 0.5327697396278381, + "learning_rate": 7.546379614571947e-05, + "loss": 1.6879, + "step": 6121 + }, + { + "epoch": 0.341229585864779, + "grad_norm": 0.5991697311401367, + "learning_rate": 7.545613272685834e-05, + "loss": 1.9402, + "step": 6122 + }, + { + "epoch": 0.34128532411794216, + "grad_norm": 0.5222532749176025, + "learning_rate": 7.544846850067711e-05, + "loss": 1.6331, + "step": 6123 + }, + { + "epoch": 0.3413410623711053, + "grad_norm": 0.5213292837142944, + "learning_rate": 7.544080346741884e-05, + "loss": 1.6547, + "step": 6124 + }, + { + "epoch": 0.3413968006242684, + "grad_norm": 0.516547441482544, + "learning_rate": 7.54331376273266e-05, + "loss": 1.5988, + "step": 6125 + }, + { + "epoch": 0.3414525388774316, + "grad_norm": 0.5505926609039307, + "learning_rate": 7.542547098064351e-05, + "loss": 1.8314, + "step": 6126 + }, + { + "epoch": 0.34150827713059473, + "grad_norm": 0.5631290078163147, + "learning_rate": 7.541780352761275e-05, + "loss": 1.7797, + "step": 6127 + }, + { + "epoch": 0.34156401538375786, + "grad_norm": 0.5578431487083435, + "learning_rate": 7.541013526847745e-05, + "loss": 1.7118, + "step": 6128 + }, + { + "epoch": 0.34161975363692104, + "grad_norm": 0.6077129244804382, + "learning_rate": 7.540246620348079e-05, + "loss": 1.8582, + "step": 6129 + }, + { + "epoch": 0.34167549189008417, + "grad_norm": 0.5378260612487793, + "learning_rate": 7.539479633286604e-05, + "loss": 1.5773, + "step": 6130 + }, + { + "epoch": 0.3417312301432473, + "grad_norm": 0.5147218108177185, + "learning_rate": 7.538712565687637e-05, + "loss": 1.6079, + "step": 6131 + }, + { + "epoch": 0.34178696839641043, + "grad_norm": 0.5637179017066956, + "learning_rate": 7.537945417575513e-05, + "loss": 1.7772, + "step": 6132 + }, + { + "epoch": 0.3418427066495736, + "grad_norm": 0.5718836188316345, + "learning_rate": 7.537178188974556e-05, + "loss": 1.8646, + "step": 6133 + }, + { + "epoch": 0.34189844490273674, + "grad_norm": 0.5593611001968384, + "learning_rate": 7.5364108799091e-05, + "loss": 1.7059, + "step": 6134 + }, + { + "epoch": 0.34195418315589987, + "grad_norm": 0.5491702556610107, + "learning_rate": 7.535643490403478e-05, + "loss": 1.5904, + "step": 6135 + }, + { + "epoch": 0.34200992140906306, + "grad_norm": 0.5673286318778992, + "learning_rate": 7.534876020482032e-05, + "loss": 1.6569, + "step": 6136 + }, + { + "epoch": 0.3420656596622262, + "grad_norm": 0.555279552936554, + "learning_rate": 7.534108470169094e-05, + "loss": 1.947, + "step": 6137 + }, + { + "epoch": 0.3421213979153893, + "grad_norm": 0.5502607226371765, + "learning_rate": 7.533340839489011e-05, + "loss": 1.6199, + "step": 6138 + }, + { + "epoch": 0.3421771361685525, + "grad_norm": 0.5711556673049927, + "learning_rate": 7.532573128466129e-05, + "loss": 1.901, + "step": 6139 + }, + { + "epoch": 0.3422328744217156, + "grad_norm": 0.5685670375823975, + "learning_rate": 7.53180533712479e-05, + "loss": 1.7284, + "step": 6140 + }, + { + "epoch": 0.34228861267487876, + "grad_norm": 0.555075466632843, + "learning_rate": 7.53103746548935e-05, + "loss": 1.8184, + "step": 6141 + }, + { + "epoch": 0.34234435092804194, + "grad_norm": 0.5404545664787292, + "learning_rate": 7.530269513584158e-05, + "loss": 1.6444, + "step": 6142 + }, + { + "epoch": 0.34240008918120507, + "grad_norm": 0.5739527344703674, + "learning_rate": 7.52950148143357e-05, + "loss": 1.5748, + "step": 6143 + }, + { + "epoch": 0.3424558274343682, + "grad_norm": 0.5569913983345032, + "learning_rate": 7.528733369061942e-05, + "loss": 1.8188, + "step": 6144 + }, + { + "epoch": 0.3425115656875313, + "grad_norm": 0.5430577397346497, + "learning_rate": 7.527965176493636e-05, + "loss": 1.5839, + "step": 6145 + }, + { + "epoch": 0.3425673039406945, + "grad_norm": 0.5321673154830933, + "learning_rate": 7.527196903753011e-05, + "loss": 1.3862, + "step": 6146 + }, + { + "epoch": 0.34262304219385764, + "grad_norm": 0.5757884979248047, + "learning_rate": 7.526428550864437e-05, + "loss": 1.5308, + "step": 6147 + }, + { + "epoch": 0.34267878044702077, + "grad_norm": 0.556651771068573, + "learning_rate": 7.525660117852279e-05, + "loss": 1.7377, + "step": 6148 + }, + { + "epoch": 0.34273451870018395, + "grad_norm": 0.5236818790435791, + "learning_rate": 7.524891604740908e-05, + "loss": 1.7305, + "step": 6149 + }, + { + "epoch": 0.3427902569533471, + "grad_norm": 0.5686874985694885, + "learning_rate": 7.524123011554697e-05, + "loss": 1.5379, + "step": 6150 + }, + { + "epoch": 0.3428459952065102, + "grad_norm": 0.5817770957946777, + "learning_rate": 7.52335433831802e-05, + "loss": 1.7069, + "step": 6151 + }, + { + "epoch": 0.3429017334596734, + "grad_norm": 0.5717275738716125, + "learning_rate": 7.522585585055255e-05, + "loss": 1.8944, + "step": 6152 + }, + { + "epoch": 0.3429574717128365, + "grad_norm": 0.5469644665718079, + "learning_rate": 7.521816751790783e-05, + "loss": 1.622, + "step": 6153 + }, + { + "epoch": 0.34301320996599965, + "grad_norm": 0.5735164880752563, + "learning_rate": 7.521047838548988e-05, + "loss": 1.8005, + "step": 6154 + }, + { + "epoch": 0.3430689482191628, + "grad_norm": 0.5070759057998657, + "learning_rate": 7.520278845354254e-05, + "loss": 1.4795, + "step": 6155 + }, + { + "epoch": 0.34312468647232597, + "grad_norm": 0.5179046392440796, + "learning_rate": 7.519509772230968e-05, + "loss": 1.5029, + "step": 6156 + }, + { + "epoch": 0.3431804247254891, + "grad_norm": 0.5747403502464294, + "learning_rate": 7.518740619203523e-05, + "loss": 1.7075, + "step": 6157 + }, + { + "epoch": 0.3432361629786522, + "grad_norm": 0.6233847141265869, + "learning_rate": 7.517971386296309e-05, + "loss": 1.9524, + "step": 6158 + }, + { + "epoch": 0.3432919012318154, + "grad_norm": 0.5195590853691101, + "learning_rate": 7.517202073533727e-05, + "loss": 1.533, + "step": 6159 + }, + { + "epoch": 0.34334763948497854, + "grad_norm": 0.6035041213035583, + "learning_rate": 7.516432680940168e-05, + "loss": 1.7298, + "step": 6160 + }, + { + "epoch": 0.34340337773814167, + "grad_norm": 0.59979248046875, + "learning_rate": 7.515663208540037e-05, + "loss": 1.7295, + "step": 6161 + }, + { + "epoch": 0.34345911599130485, + "grad_norm": 0.5844981074333191, + "learning_rate": 7.514893656357738e-05, + "loss": 1.756, + "step": 6162 + }, + { + "epoch": 0.343514854244468, + "grad_norm": 0.5281308889389038, + "learning_rate": 7.514124024417674e-05, + "loss": 1.7149, + "step": 6163 + }, + { + "epoch": 0.3435705924976311, + "grad_norm": 0.5352674126625061, + "learning_rate": 7.513354312744256e-05, + "loss": 1.7262, + "step": 6164 + }, + { + "epoch": 0.3436263307507943, + "grad_norm": 0.562127411365509, + "learning_rate": 7.512584521361891e-05, + "loss": 1.6434, + "step": 6165 + }, + { + "epoch": 0.3436820690039574, + "grad_norm": 0.5535931587219238, + "learning_rate": 7.511814650294994e-05, + "loss": 1.5353, + "step": 6166 + }, + { + "epoch": 0.34373780725712055, + "grad_norm": 0.543641209602356, + "learning_rate": 7.511044699567981e-05, + "loss": 1.8312, + "step": 6167 + }, + { + "epoch": 0.3437935455102837, + "grad_norm": 0.559559166431427, + "learning_rate": 7.510274669205273e-05, + "loss": 1.6326, + "step": 6168 + }, + { + "epoch": 0.34384928376344687, + "grad_norm": 0.5449449419975281, + "learning_rate": 7.509504559231287e-05, + "loss": 1.7319, + "step": 6169 + }, + { + "epoch": 0.34390502201661, + "grad_norm": 0.5315961837768555, + "learning_rate": 7.508734369670447e-05, + "loss": 1.69, + "step": 6170 + }, + { + "epoch": 0.3439607602697731, + "grad_norm": 0.5506524443626404, + "learning_rate": 7.507964100547181e-05, + "loss": 1.6961, + "step": 6171 + }, + { + "epoch": 0.3440164985229363, + "grad_norm": 0.5587935447692871, + "learning_rate": 7.507193751885915e-05, + "loss": 1.794, + "step": 6172 + }, + { + "epoch": 0.34407223677609944, + "grad_norm": 0.5281456112861633, + "learning_rate": 7.506423323711083e-05, + "loss": 1.637, + "step": 6173 + }, + { + "epoch": 0.34412797502926257, + "grad_norm": 0.5220721960067749, + "learning_rate": 7.505652816047115e-05, + "loss": 1.4696, + "step": 6174 + }, + { + "epoch": 0.34418371328242575, + "grad_norm": 0.565938413143158, + "learning_rate": 7.504882228918449e-05, + "loss": 1.6329, + "step": 6175 + }, + { + "epoch": 0.3442394515355889, + "grad_norm": 0.532490074634552, + "learning_rate": 7.504111562349524e-05, + "loss": 1.5929, + "step": 6176 + }, + { + "epoch": 0.344295189788752, + "grad_norm": 0.5559155941009521, + "learning_rate": 7.503340816364779e-05, + "loss": 1.6935, + "step": 6177 + }, + { + "epoch": 0.3443509280419152, + "grad_norm": 0.5494531989097595, + "learning_rate": 7.502569990988659e-05, + "loss": 1.5508, + "step": 6178 + }, + { + "epoch": 0.3444066662950783, + "grad_norm": 0.48615095019340515, + "learning_rate": 7.50179908624561e-05, + "loss": 1.3464, + "step": 6179 + }, + { + "epoch": 0.34446240454824145, + "grad_norm": 0.543402373790741, + "learning_rate": 7.501028102160082e-05, + "loss": 1.6306, + "step": 6180 + }, + { + "epoch": 0.3445181428014046, + "grad_norm": 0.5688214898109436, + "learning_rate": 7.500257038756522e-05, + "loss": 1.9743, + "step": 6181 + }, + { + "epoch": 0.34457388105456777, + "grad_norm": 0.5336653590202332, + "learning_rate": 7.499485896059389e-05, + "loss": 1.7876, + "step": 6182 + }, + { + "epoch": 0.3446296193077309, + "grad_norm": 0.6009781360626221, + "learning_rate": 7.498714674093134e-05, + "loss": 1.599, + "step": 6183 + }, + { + "epoch": 0.344685357560894, + "grad_norm": 0.5108974575996399, + "learning_rate": 7.497943372882219e-05, + "loss": 1.3671, + "step": 6184 + }, + { + "epoch": 0.3447410958140572, + "grad_norm": 0.5875006914138794, + "learning_rate": 7.497171992451104e-05, + "loss": 1.8846, + "step": 6185 + }, + { + "epoch": 0.34479683406722034, + "grad_norm": 0.5741475820541382, + "learning_rate": 7.496400532824252e-05, + "loss": 1.8147, + "step": 6186 + }, + { + "epoch": 0.34485257232038347, + "grad_norm": 0.5426183938980103, + "learning_rate": 7.495628994026131e-05, + "loss": 1.8584, + "step": 6187 + }, + { + "epoch": 0.34490831057354665, + "grad_norm": 0.5665351152420044, + "learning_rate": 7.49485737608121e-05, + "loss": 1.6254, + "step": 6188 + }, + { + "epoch": 0.3449640488267098, + "grad_norm": 0.6417822241783142, + "learning_rate": 7.494085679013959e-05, + "loss": 1.5997, + "step": 6189 + }, + { + "epoch": 0.3450197870798729, + "grad_norm": 0.580936849117279, + "learning_rate": 7.49331390284885e-05, + "loss": 1.7723, + "step": 6190 + }, + { + "epoch": 0.34507552533303604, + "grad_norm": 0.5405949354171753, + "learning_rate": 7.492542047610362e-05, + "loss": 1.7536, + "step": 6191 + }, + { + "epoch": 0.3451312635861992, + "grad_norm": 0.567459225654602, + "learning_rate": 7.491770113322972e-05, + "loss": 1.5518, + "step": 6192 + }, + { + "epoch": 0.34518700183936235, + "grad_norm": 0.5930157899856567, + "learning_rate": 7.490998100011164e-05, + "loss": 1.8805, + "step": 6193 + }, + { + "epoch": 0.3452427400925255, + "grad_norm": 0.5590851902961731, + "learning_rate": 7.490226007699418e-05, + "loss": 1.7369, + "step": 6194 + }, + { + "epoch": 0.34529847834568866, + "grad_norm": 0.5540249943733215, + "learning_rate": 7.489453836412224e-05, + "loss": 1.7199, + "step": 6195 + }, + { + "epoch": 0.3453542165988518, + "grad_norm": 0.6100202798843384, + "learning_rate": 7.488681586174066e-05, + "loss": 1.8962, + "step": 6196 + }, + { + "epoch": 0.3454099548520149, + "grad_norm": 0.5453261137008667, + "learning_rate": 7.48790925700944e-05, + "loss": 1.6779, + "step": 6197 + }, + { + "epoch": 0.3454656931051781, + "grad_norm": 0.6191526651382446, + "learning_rate": 7.487136848942838e-05, + "loss": 1.837, + "step": 6198 + }, + { + "epoch": 0.34552143135834124, + "grad_norm": 0.5043689608573914, + "learning_rate": 7.486364361998754e-05, + "loss": 1.5438, + "step": 6199 + }, + { + "epoch": 0.34557716961150436, + "grad_norm": 0.5927308797836304, + "learning_rate": 7.485591796201692e-05, + "loss": 1.8893, + "step": 6200 + }, + { + "epoch": 0.34563290786466755, + "grad_norm": 0.5387723445892334, + "learning_rate": 7.484819151576147e-05, + "loss": 1.7063, + "step": 6201 + }, + { + "epoch": 0.3456886461178307, + "grad_norm": 0.5273063778877258, + "learning_rate": 7.48404642814663e-05, + "loss": 1.6052, + "step": 6202 + }, + { + "epoch": 0.3457443843709938, + "grad_norm": 0.5235535502433777, + "learning_rate": 7.48327362593764e-05, + "loss": 1.5859, + "step": 6203 + }, + { + "epoch": 0.34580012262415694, + "grad_norm": 0.5952630043029785, + "learning_rate": 7.48250074497369e-05, + "loss": 1.9669, + "step": 6204 + }, + { + "epoch": 0.3458558608773201, + "grad_norm": 0.5512803196907043, + "learning_rate": 7.48172778527929e-05, + "loss": 1.6103, + "step": 6205 + }, + { + "epoch": 0.34591159913048325, + "grad_norm": 0.5485497117042542, + "learning_rate": 7.480954746878955e-05, + "loss": 1.4648, + "step": 6206 + }, + { + "epoch": 0.3459673373836464, + "grad_norm": 0.5755242109298706, + "learning_rate": 7.480181629797201e-05, + "loss": 1.7882, + "step": 6207 + }, + { + "epoch": 0.34602307563680956, + "grad_norm": 0.586279034614563, + "learning_rate": 7.479408434058545e-05, + "loss": 1.757, + "step": 6208 + }, + { + "epoch": 0.3460788138899727, + "grad_norm": 0.6023716926574707, + "learning_rate": 7.47863515968751e-05, + "loss": 1.6573, + "step": 6209 + }, + { + "epoch": 0.3461345521431358, + "grad_norm": 0.5629722476005554, + "learning_rate": 7.477861806708618e-05, + "loss": 1.8348, + "step": 6210 + }, + { + "epoch": 0.346190290396299, + "grad_norm": 0.64363032579422, + "learning_rate": 7.477088375146397e-05, + "loss": 2.1581, + "step": 6211 + }, + { + "epoch": 0.34624602864946213, + "grad_norm": 0.5952073335647583, + "learning_rate": 7.476314865025376e-05, + "loss": 1.7823, + "step": 6212 + }, + { + "epoch": 0.34630176690262526, + "grad_norm": 0.5444992780685425, + "learning_rate": 7.475541276370083e-05, + "loss": 1.5717, + "step": 6213 + }, + { + "epoch": 0.3463575051557884, + "grad_norm": 0.5698938965797424, + "learning_rate": 7.474767609205057e-05, + "loss": 1.8471, + "step": 6214 + }, + { + "epoch": 0.3464132434089516, + "grad_norm": 0.521270751953125, + "learning_rate": 7.473993863554832e-05, + "loss": 1.5991, + "step": 6215 + }, + { + "epoch": 0.3464689816621147, + "grad_norm": 0.5909140110015869, + "learning_rate": 7.473220039443942e-05, + "loss": 1.8795, + "step": 6216 + }, + { + "epoch": 0.34652471991527783, + "grad_norm": 0.5595431923866272, + "learning_rate": 7.472446136896935e-05, + "loss": 1.5189, + "step": 6217 + }, + { + "epoch": 0.346580458168441, + "grad_norm": 0.5549118518829346, + "learning_rate": 7.471672155938351e-05, + "loss": 1.5113, + "step": 6218 + }, + { + "epoch": 0.34663619642160415, + "grad_norm": 0.5784697532653809, + "learning_rate": 7.470898096592738e-05, + "loss": 1.62, + "step": 6219 + }, + { + "epoch": 0.3466919346747673, + "grad_norm": 0.582065224647522, + "learning_rate": 7.470123958884643e-05, + "loss": 1.7652, + "step": 6220 + }, + { + "epoch": 0.34674767292793046, + "grad_norm": 0.5781643986701965, + "learning_rate": 7.469349742838619e-05, + "loss": 1.816, + "step": 6221 + }, + { + "epoch": 0.3468034111810936, + "grad_norm": 0.5270411968231201, + "learning_rate": 7.468575448479217e-05, + "loss": 1.4521, + "step": 6222 + }, + { + "epoch": 0.3468591494342567, + "grad_norm": 0.5568832159042358, + "learning_rate": 7.467801075830995e-05, + "loss": 1.6393, + "step": 6223 + }, + { + "epoch": 0.3469148876874199, + "grad_norm": 0.6102818846702576, + "learning_rate": 7.467026624918511e-05, + "loss": 1.8486, + "step": 6224 + }, + { + "epoch": 0.34697062594058303, + "grad_norm": 0.6040059328079224, + "learning_rate": 7.466252095766326e-05, + "loss": 1.9639, + "step": 6225 + }, + { + "epoch": 0.34702636419374616, + "grad_norm": 0.5577713847160339, + "learning_rate": 7.465477488399004e-05, + "loss": 1.7672, + "step": 6226 + }, + { + "epoch": 0.3470821024469093, + "grad_norm": 0.6022251844406128, + "learning_rate": 7.464702802841111e-05, + "loss": 1.8587, + "step": 6227 + }, + { + "epoch": 0.3471378407000725, + "grad_norm": 0.6043629050254822, + "learning_rate": 7.463928039117216e-05, + "loss": 1.6798, + "step": 6228 + }, + { + "epoch": 0.3471935789532356, + "grad_norm": 0.5550456643104553, + "learning_rate": 7.463153197251889e-05, + "loss": 1.6258, + "step": 6229 + }, + { + "epoch": 0.34724931720639873, + "grad_norm": 0.5740575790405273, + "learning_rate": 7.462378277269704e-05, + "loss": 1.6253, + "step": 6230 + }, + { + "epoch": 0.3473050554595619, + "grad_norm": 0.5348698496818542, + "learning_rate": 7.461603279195235e-05, + "loss": 1.7417, + "step": 6231 + }, + { + "epoch": 0.34736079371272505, + "grad_norm": 0.5703982710838318, + "learning_rate": 7.460828203053063e-05, + "loss": 1.8448, + "step": 6232 + }, + { + "epoch": 0.3474165319658882, + "grad_norm": 0.5818899869918823, + "learning_rate": 7.460053048867768e-05, + "loss": 1.783, + "step": 6233 + }, + { + "epoch": 0.34747227021905136, + "grad_norm": 0.5640279054641724, + "learning_rate": 7.459277816663934e-05, + "loss": 1.8757, + "step": 6234 + }, + { + "epoch": 0.3475280084722145, + "grad_norm": 0.519883394241333, + "learning_rate": 7.458502506466147e-05, + "loss": 1.622, + "step": 6235 + }, + { + "epoch": 0.3475837467253776, + "grad_norm": 0.5207779407501221, + "learning_rate": 7.457727118298991e-05, + "loss": 1.4801, + "step": 6236 + }, + { + "epoch": 0.34763948497854075, + "grad_norm": 0.5227778553962708, + "learning_rate": 7.456951652187063e-05, + "loss": 1.6797, + "step": 6237 + }, + { + "epoch": 0.34769522323170393, + "grad_norm": 0.6305186748504639, + "learning_rate": 7.456176108154956e-05, + "loss": 2.0804, + "step": 6238 + }, + { + "epoch": 0.34775096148486706, + "grad_norm": 0.6344568133354187, + "learning_rate": 7.45540048622726e-05, + "loss": 1.881, + "step": 6239 + }, + { + "epoch": 0.3478066997380302, + "grad_norm": 0.5849176645278931, + "learning_rate": 7.454624786428576e-05, + "loss": 1.7058, + "step": 6240 + }, + { + "epoch": 0.3478624379911934, + "grad_norm": 0.5511870980262756, + "learning_rate": 7.453849008783507e-05, + "loss": 1.7262, + "step": 6241 + }, + { + "epoch": 0.3479181762443565, + "grad_norm": 0.590895414352417, + "learning_rate": 7.453073153316654e-05, + "loss": 1.7584, + "step": 6242 + }, + { + "epoch": 0.34797391449751963, + "grad_norm": 0.5347367525100708, + "learning_rate": 7.452297220052624e-05, + "loss": 1.7057, + "step": 6243 + }, + { + "epoch": 0.3480296527506828, + "grad_norm": 0.5574136972427368, + "learning_rate": 7.451521209016021e-05, + "loss": 1.8928, + "step": 6244 + }, + { + "epoch": 0.34808539100384595, + "grad_norm": 0.5794700384140015, + "learning_rate": 7.450745120231462e-05, + "loss": 1.9479, + "step": 6245 + }, + { + "epoch": 0.3481411292570091, + "grad_norm": 0.5384243726730347, + "learning_rate": 7.449968953723554e-05, + "loss": 1.678, + "step": 6246 + }, + { + "epoch": 0.34819686751017226, + "grad_norm": 0.560627281665802, + "learning_rate": 7.449192709516916e-05, + "loss": 1.7936, + "step": 6247 + }, + { + "epoch": 0.3482526057633354, + "grad_norm": 0.6408939957618713, + "learning_rate": 7.448416387636166e-05, + "loss": 1.8022, + "step": 6248 + }, + { + "epoch": 0.3483083440164985, + "grad_norm": 0.5532012581825256, + "learning_rate": 7.447639988105922e-05, + "loss": 1.6318, + "step": 6249 + }, + { + "epoch": 0.34836408226966165, + "grad_norm": 0.6528187990188599, + "learning_rate": 7.44686351095081e-05, + "loss": 2.0857, + "step": 6250 + }, + { + "epoch": 0.34841982052282483, + "grad_norm": 0.5271794199943542, + "learning_rate": 7.446086956195452e-05, + "loss": 1.6236, + "step": 6251 + }, + { + "epoch": 0.34847555877598796, + "grad_norm": 0.6053271293640137, + "learning_rate": 7.445310323864478e-05, + "loss": 1.895, + "step": 6252 + }, + { + "epoch": 0.3485312970291511, + "grad_norm": 0.5544027090072632, + "learning_rate": 7.444533613982519e-05, + "loss": 1.6158, + "step": 6253 + }, + { + "epoch": 0.3485870352823143, + "grad_norm": 0.5839915871620178, + "learning_rate": 7.443756826574204e-05, + "loss": 1.7887, + "step": 6254 + }, + { + "epoch": 0.3486427735354774, + "grad_norm": 0.5946133732795715, + "learning_rate": 7.442979961664171e-05, + "loss": 1.7628, + "step": 6255 + }, + { + "epoch": 0.34869851178864053, + "grad_norm": 0.5356269478797913, + "learning_rate": 7.442203019277059e-05, + "loss": 1.6563, + "step": 6256 + }, + { + "epoch": 0.3487542500418037, + "grad_norm": 0.5791853666305542, + "learning_rate": 7.441425999437505e-05, + "loss": 1.7944, + "step": 6257 + }, + { + "epoch": 0.34880998829496684, + "grad_norm": 0.514127254486084, + "learning_rate": 7.440648902170153e-05, + "loss": 1.6007, + "step": 6258 + }, + { + "epoch": 0.34886572654813, + "grad_norm": 0.5857915878295898, + "learning_rate": 7.439871727499648e-05, + "loss": 1.6401, + "step": 6259 + }, + { + "epoch": 0.3489214648012931, + "grad_norm": 0.5310158729553223, + "learning_rate": 7.439094475450638e-05, + "loss": 1.6605, + "step": 6260 + }, + { + "epoch": 0.3489772030544563, + "grad_norm": 0.5631361603736877, + "learning_rate": 7.43831714604777e-05, + "loss": 1.7541, + "step": 6261 + }, + { + "epoch": 0.3490329413076194, + "grad_norm": 0.5697758197784424, + "learning_rate": 7.4375397393157e-05, + "loss": 1.5488, + "step": 6262 + }, + { + "epoch": 0.34908867956078254, + "grad_norm": 0.5197820663452148, + "learning_rate": 7.43676225527908e-05, + "loss": 1.7463, + "step": 6263 + }, + { + "epoch": 0.34914441781394573, + "grad_norm": 0.6369295120239258, + "learning_rate": 7.43598469396257e-05, + "loss": 2.106, + "step": 6264 + }, + { + "epoch": 0.34920015606710886, + "grad_norm": 0.5751513242721558, + "learning_rate": 7.435207055390828e-05, + "loss": 1.8146, + "step": 6265 + }, + { + "epoch": 0.349255894320272, + "grad_norm": 0.5785645246505737, + "learning_rate": 7.434429339588516e-05, + "loss": 1.8598, + "step": 6266 + }, + { + "epoch": 0.34931163257343517, + "grad_norm": 0.5536054968833923, + "learning_rate": 7.4336515465803e-05, + "loss": 1.7508, + "step": 6267 + }, + { + "epoch": 0.3493673708265983, + "grad_norm": 0.5529542565345764, + "learning_rate": 7.432873676390845e-05, + "loss": 1.7749, + "step": 6268 + }, + { + "epoch": 0.34942310907976143, + "grad_norm": 0.5571187734603882, + "learning_rate": 7.432095729044823e-05, + "loss": 1.6954, + "step": 6269 + }, + { + "epoch": 0.3494788473329246, + "grad_norm": 0.5445393323898315, + "learning_rate": 7.431317704566902e-05, + "loss": 1.5363, + "step": 6270 + }, + { + "epoch": 0.34953458558608774, + "grad_norm": 0.5723183155059814, + "learning_rate": 7.430539602981761e-05, + "loss": 1.7007, + "step": 6271 + }, + { + "epoch": 0.34959032383925087, + "grad_norm": 0.5553802847862244, + "learning_rate": 7.429761424314075e-05, + "loss": 1.9324, + "step": 6272 + }, + { + "epoch": 0.349646062092414, + "grad_norm": 0.5308825969696045, + "learning_rate": 7.428983168588522e-05, + "loss": 1.6236, + "step": 6273 + }, + { + "epoch": 0.3497018003455772, + "grad_norm": 0.5892744064331055, + "learning_rate": 7.428204835829787e-05, + "loss": 1.8567, + "step": 6274 + }, + { + "epoch": 0.3497575385987403, + "grad_norm": 0.5890315175056458, + "learning_rate": 7.42742642606255e-05, + "loss": 1.7612, + "step": 6275 + }, + { + "epoch": 0.34981327685190344, + "grad_norm": 0.5714004635810852, + "learning_rate": 7.426647939311499e-05, + "loss": 1.8783, + "step": 6276 + }, + { + "epoch": 0.3498690151050666, + "grad_norm": 0.5221744775772095, + "learning_rate": 7.425869375601324e-05, + "loss": 1.533, + "step": 6277 + }, + { + "epoch": 0.34992475335822976, + "grad_norm": 0.5754460692405701, + "learning_rate": 7.425090734956717e-05, + "loss": 1.7922, + "step": 6278 + }, + { + "epoch": 0.3499804916113929, + "grad_norm": 0.5325612425804138, + "learning_rate": 7.424312017402371e-05, + "loss": 1.5523, + "step": 6279 + }, + { + "epoch": 0.35003622986455607, + "grad_norm": 0.5452947020530701, + "learning_rate": 7.423533222962984e-05, + "loss": 1.7528, + "step": 6280 + }, + { + "epoch": 0.3500919681177192, + "grad_norm": 0.5132524371147156, + "learning_rate": 7.422754351663252e-05, + "loss": 1.6118, + "step": 6281 + }, + { + "epoch": 0.35014770637088233, + "grad_norm": 0.5661509037017822, + "learning_rate": 7.421975403527877e-05, + "loss": 1.7999, + "step": 6282 + }, + { + "epoch": 0.35020344462404546, + "grad_norm": 0.5532317161560059, + "learning_rate": 7.421196378581563e-05, + "loss": 1.8317, + "step": 6283 + }, + { + "epoch": 0.35025918287720864, + "grad_norm": 0.5239238142967224, + "learning_rate": 7.420417276849018e-05, + "loss": 1.6949, + "step": 6284 + }, + { + "epoch": 0.35031492113037177, + "grad_norm": 0.5444215536117554, + "learning_rate": 7.419638098354948e-05, + "loss": 1.666, + "step": 6285 + }, + { + "epoch": 0.3503706593835349, + "grad_norm": 0.5257874131202698, + "learning_rate": 7.418858843124065e-05, + "loss": 1.7663, + "step": 6286 + }, + { + "epoch": 0.3504263976366981, + "grad_norm": 0.5424786806106567, + "learning_rate": 7.418079511181084e-05, + "loss": 1.6048, + "step": 6287 + }, + { + "epoch": 0.3504821358898612, + "grad_norm": 0.5822529196739197, + "learning_rate": 7.417300102550718e-05, + "loss": 1.7153, + "step": 6288 + }, + { + "epoch": 0.35053787414302434, + "grad_norm": 0.6322096586227417, + "learning_rate": 7.416520617257686e-05, + "loss": 2.0466, + "step": 6289 + }, + { + "epoch": 0.3505936123961875, + "grad_norm": 0.6034446358680725, + "learning_rate": 7.41574105532671e-05, + "loss": 1.7793, + "step": 6290 + }, + { + "epoch": 0.35064935064935066, + "grad_norm": 0.5261698365211487, + "learning_rate": 7.414961416782512e-05, + "loss": 1.6958, + "step": 6291 + }, + { + "epoch": 0.3507050889025138, + "grad_norm": 0.5508055090904236, + "learning_rate": 7.414181701649818e-05, + "loss": 1.7336, + "step": 6292 + }, + { + "epoch": 0.35076082715567697, + "grad_norm": 0.5106075406074524, + "learning_rate": 7.413401909953356e-05, + "loss": 1.5585, + "step": 6293 + }, + { + "epoch": 0.3508165654088401, + "grad_norm": 0.5312706232070923, + "learning_rate": 7.412622041717858e-05, + "loss": 1.5692, + "step": 6294 + }, + { + "epoch": 0.3508723036620032, + "grad_norm": 0.5598204135894775, + "learning_rate": 7.411842096968055e-05, + "loss": 1.6424, + "step": 6295 + }, + { + "epoch": 0.35092804191516636, + "grad_norm": 0.5455132126808167, + "learning_rate": 7.411062075728681e-05, + "loss": 1.7084, + "step": 6296 + }, + { + "epoch": 0.35098378016832954, + "grad_norm": 0.5335630774497986, + "learning_rate": 7.410281978024478e-05, + "loss": 1.6269, + "step": 6297 + }, + { + "epoch": 0.35103951842149267, + "grad_norm": 0.5936735272407532, + "learning_rate": 7.409501803880182e-05, + "loss": 1.6821, + "step": 6298 + }, + { + "epoch": 0.3510952566746558, + "grad_norm": 0.626340389251709, + "learning_rate": 7.408721553320536e-05, + "loss": 1.8958, + "step": 6299 + }, + { + "epoch": 0.351150994927819, + "grad_norm": 0.5382502675056458, + "learning_rate": 7.407941226370289e-05, + "loss": 1.6456, + "step": 6300 + }, + { + "epoch": 0.3512067331809821, + "grad_norm": 0.5597545504570007, + "learning_rate": 7.407160823054182e-05, + "loss": 1.7168, + "step": 6301 + }, + { + "epoch": 0.35126247143414524, + "grad_norm": 0.5945395231246948, + "learning_rate": 7.406380343396973e-05, + "loss": 2.0034, + "step": 6302 + }, + { + "epoch": 0.3513182096873084, + "grad_norm": 0.5297150611877441, + "learning_rate": 7.405599787423406e-05, + "loss": 1.5787, + "step": 6303 + }, + { + "epoch": 0.35137394794047155, + "grad_norm": 0.5702363848686218, + "learning_rate": 7.40481915515824e-05, + "loss": 1.8993, + "step": 6304 + }, + { + "epoch": 0.3514296861936347, + "grad_norm": 0.6293717622756958, + "learning_rate": 7.404038446626231e-05, + "loss": 1.9086, + "step": 6305 + }, + { + "epoch": 0.3514854244467978, + "grad_norm": 0.579983651638031, + "learning_rate": 7.403257661852142e-05, + "loss": 1.74, + "step": 6306 + }, + { + "epoch": 0.351541162699961, + "grad_norm": 0.558723509311676, + "learning_rate": 7.40247680086073e-05, + "loss": 1.7519, + "step": 6307 + }, + { + "epoch": 0.3515969009531241, + "grad_norm": 0.5575239062309265, + "learning_rate": 7.401695863676761e-05, + "loss": 1.8393, + "step": 6308 + }, + { + "epoch": 0.35165263920628725, + "grad_norm": 0.5667286515235901, + "learning_rate": 7.400914850325001e-05, + "loss": 1.7958, + "step": 6309 + }, + { + "epoch": 0.35170837745945044, + "grad_norm": 0.5829740762710571, + "learning_rate": 7.400133760830221e-05, + "loss": 1.7113, + "step": 6310 + }, + { + "epoch": 0.35176411571261357, + "grad_norm": 0.5255504846572876, + "learning_rate": 7.399352595217193e-05, + "loss": 1.6819, + "step": 6311 + }, + { + "epoch": 0.3518198539657767, + "grad_norm": 0.5315664410591125, + "learning_rate": 7.39857135351069e-05, + "loss": 1.5692, + "step": 6312 + }, + { + "epoch": 0.3518755922189399, + "grad_norm": 0.5694820880889893, + "learning_rate": 7.397790035735487e-05, + "loss": 1.813, + "step": 6313 + }, + { + "epoch": 0.351931330472103, + "grad_norm": 0.5584225058555603, + "learning_rate": 7.397008641916364e-05, + "loss": 1.6653, + "step": 6314 + }, + { + "epoch": 0.35198706872526614, + "grad_norm": 0.5575059652328491, + "learning_rate": 7.396227172078103e-05, + "loss": 1.7948, + "step": 6315 + }, + { + "epoch": 0.3520428069784293, + "grad_norm": 0.5385696887969971, + "learning_rate": 7.395445626245486e-05, + "loss": 1.6823, + "step": 6316 + }, + { + "epoch": 0.35209854523159245, + "grad_norm": 0.5181571841239929, + "learning_rate": 7.394664004443302e-05, + "loss": 1.4832, + "step": 6317 + }, + { + "epoch": 0.3521542834847556, + "grad_norm": 0.5436875224113464, + "learning_rate": 7.393882306696338e-05, + "loss": 1.5743, + "step": 6318 + }, + { + "epoch": 0.3522100217379187, + "grad_norm": 0.5831631422042847, + "learning_rate": 7.393100533029383e-05, + "loss": 1.7726, + "step": 6319 + }, + { + "epoch": 0.3522657599910819, + "grad_norm": 0.5740854144096375, + "learning_rate": 7.392318683467232e-05, + "loss": 1.5639, + "step": 6320 + }, + { + "epoch": 0.352321498244245, + "grad_norm": 0.5731649994850159, + "learning_rate": 7.391536758034682e-05, + "loss": 1.9563, + "step": 6321 + }, + { + "epoch": 0.35237723649740815, + "grad_norm": 0.6104768514633179, + "learning_rate": 7.390754756756526e-05, + "loss": 1.6392, + "step": 6322 + }, + { + "epoch": 0.35243297475057134, + "grad_norm": 0.5218120813369751, + "learning_rate": 7.389972679657571e-05, + "loss": 1.6262, + "step": 6323 + }, + { + "epoch": 0.35248871300373447, + "grad_norm": 0.5537388324737549, + "learning_rate": 7.389190526762618e-05, + "loss": 1.7317, + "step": 6324 + }, + { + "epoch": 0.3525444512568976, + "grad_norm": 0.577392578125, + "learning_rate": 7.38840829809647e-05, + "loss": 1.7069, + "step": 6325 + }, + { + "epoch": 0.3526001895100608, + "grad_norm": 0.5511906147003174, + "learning_rate": 7.387625993683937e-05, + "loss": 1.6009, + "step": 6326 + }, + { + "epoch": 0.3526559277632239, + "grad_norm": 0.5822625756263733, + "learning_rate": 7.386843613549827e-05, + "loss": 1.7174, + "step": 6327 + }, + { + "epoch": 0.35271166601638704, + "grad_norm": 0.5413920879364014, + "learning_rate": 7.386061157718955e-05, + "loss": 1.5927, + "step": 6328 + }, + { + "epoch": 0.35276740426955017, + "grad_norm": 0.5867698192596436, + "learning_rate": 7.385278626216133e-05, + "loss": 1.7494, + "step": 6329 + }, + { + "epoch": 0.35282314252271335, + "grad_norm": 0.6775004863739014, + "learning_rate": 7.384496019066182e-05, + "loss": 1.8777, + "step": 6330 + }, + { + "epoch": 0.3528788807758765, + "grad_norm": 0.6009215116500854, + "learning_rate": 7.383713336293919e-05, + "loss": 1.7538, + "step": 6331 + }, + { + "epoch": 0.3529346190290396, + "grad_norm": 0.5513560771942139, + "learning_rate": 7.382930577924168e-05, + "loss": 1.6307, + "step": 6332 + }, + { + "epoch": 0.3529903572822028, + "grad_norm": 0.5479623079299927, + "learning_rate": 7.382147743981751e-05, + "loss": 1.6945, + "step": 6333 + }, + { + "epoch": 0.3530460955353659, + "grad_norm": 0.603458046913147, + "learning_rate": 7.381364834491499e-05, + "loss": 1.7531, + "step": 6334 + }, + { + "epoch": 0.35310183378852905, + "grad_norm": 0.951324999332428, + "learning_rate": 7.380581849478236e-05, + "loss": 1.8593, + "step": 6335 + }, + { + "epoch": 0.35315757204169224, + "grad_norm": 0.5293959975242615, + "learning_rate": 7.379798788966798e-05, + "loss": 1.7638, + "step": 6336 + }, + { + "epoch": 0.35321331029485536, + "grad_norm": 0.5229690670967102, + "learning_rate": 7.379015652982016e-05, + "loss": 1.7042, + "step": 6337 + }, + { + "epoch": 0.3532690485480185, + "grad_norm": 0.5152291059494019, + "learning_rate": 7.378232441548729e-05, + "loss": 1.607, + "step": 6338 + }, + { + "epoch": 0.3533247868011817, + "grad_norm": 0.5136567950248718, + "learning_rate": 7.377449154691775e-05, + "loss": 1.7222, + "step": 6339 + }, + { + "epoch": 0.3533805250543448, + "grad_norm": 0.5531160235404968, + "learning_rate": 7.376665792435996e-05, + "loss": 1.6946, + "step": 6340 + }, + { + "epoch": 0.35343626330750794, + "grad_norm": 0.554097592830658, + "learning_rate": 7.375882354806235e-05, + "loss": 1.6551, + "step": 6341 + }, + { + "epoch": 0.35349200156067107, + "grad_norm": 0.5862346887588501, + "learning_rate": 7.375098841827337e-05, + "loss": 1.7594, + "step": 6342 + }, + { + "epoch": 0.35354773981383425, + "grad_norm": 0.5202105641365051, + "learning_rate": 7.374315253524152e-05, + "loss": 1.6205, + "step": 6343 + }, + { + "epoch": 0.3536034780669974, + "grad_norm": 0.5510536432266235, + "learning_rate": 7.373531589921531e-05, + "loss": 1.5776, + "step": 6344 + }, + { + "epoch": 0.3536592163201605, + "grad_norm": 0.5484849214553833, + "learning_rate": 7.372747851044326e-05, + "loss": 1.5603, + "step": 6345 + }, + { + "epoch": 0.3537149545733237, + "grad_norm": 0.55774986743927, + "learning_rate": 7.371964036917394e-05, + "loss": 1.7814, + "step": 6346 + }, + { + "epoch": 0.3537706928264868, + "grad_norm": 0.5338320732116699, + "learning_rate": 7.371180147565592e-05, + "loss": 1.5941, + "step": 6347 + }, + { + "epoch": 0.35382643107964995, + "grad_norm": 0.5263161659240723, + "learning_rate": 7.370396183013779e-05, + "loss": 1.2328, + "step": 6348 + }, + { + "epoch": 0.35388216933281313, + "grad_norm": 0.533647894859314, + "learning_rate": 7.369612143286822e-05, + "loss": 1.7327, + "step": 6349 + }, + { + "epoch": 0.35393790758597626, + "grad_norm": 0.5682227611541748, + "learning_rate": 7.368828028409581e-05, + "loss": 1.8406, + "step": 6350 + }, + { + "epoch": 0.3539936458391394, + "grad_norm": 0.5832127332687378, + "learning_rate": 7.368043838406927e-05, + "loss": 1.7841, + "step": 6351 + }, + { + "epoch": 0.3540493840923025, + "grad_norm": 0.5741327404975891, + "learning_rate": 7.36725957330373e-05, + "loss": 1.787, + "step": 6352 + }, + { + "epoch": 0.3541051223454657, + "grad_norm": 0.5750821828842163, + "learning_rate": 7.366475233124861e-05, + "loss": 1.7946, + "step": 6353 + }, + { + "epoch": 0.35416086059862883, + "grad_norm": 0.5595529079437256, + "learning_rate": 7.365690817895195e-05, + "loss": 1.6904, + "step": 6354 + }, + { + "epoch": 0.35421659885179196, + "grad_norm": 0.5768024921417236, + "learning_rate": 7.364906327639608e-05, + "loss": 1.7634, + "step": 6355 + }, + { + "epoch": 0.35427233710495515, + "grad_norm": 0.5867105722427368, + "learning_rate": 7.364121762382983e-05, + "loss": 1.7406, + "step": 6356 + }, + { + "epoch": 0.3543280753581183, + "grad_norm": 0.5967558026313782, + "learning_rate": 7.363337122150197e-05, + "loss": 1.5078, + "step": 6357 + }, + { + "epoch": 0.3543838136112814, + "grad_norm": 0.5712282061576843, + "learning_rate": 7.36255240696614e-05, + "loss": 1.767, + "step": 6358 + }, + { + "epoch": 0.3544395518644446, + "grad_norm": 0.5473513603210449, + "learning_rate": 7.361767616855692e-05, + "loss": 1.6409, + "step": 6359 + }, + { + "epoch": 0.3544952901176077, + "grad_norm": 0.5412675738334656, + "learning_rate": 7.360982751843747e-05, + "loss": 1.6319, + "step": 6360 + }, + { + "epoch": 0.35455102837077085, + "grad_norm": 0.5327848792076111, + "learning_rate": 7.360197811955194e-05, + "loss": 1.511, + "step": 6361 + }, + { + "epoch": 0.35460676662393403, + "grad_norm": 0.5604977607727051, + "learning_rate": 7.359412797214929e-05, + "loss": 1.7604, + "step": 6362 + }, + { + "epoch": 0.35466250487709716, + "grad_norm": 0.5807721018791199, + "learning_rate": 7.358627707647844e-05, + "loss": 1.5816, + "step": 6363 + }, + { + "epoch": 0.3547182431302603, + "grad_norm": 0.5296190977096558, + "learning_rate": 7.357842543278841e-05, + "loss": 1.2601, + "step": 6364 + }, + { + "epoch": 0.3547739813834234, + "grad_norm": 0.5498451590538025, + "learning_rate": 7.357057304132819e-05, + "loss": 1.8474, + "step": 6365 + }, + { + "epoch": 0.3548297196365866, + "grad_norm": 0.5772817134857178, + "learning_rate": 7.356271990234683e-05, + "loss": 1.7508, + "step": 6366 + }, + { + "epoch": 0.35488545788974973, + "grad_norm": 0.520463764667511, + "learning_rate": 7.355486601609339e-05, + "loss": 1.5589, + "step": 6367 + }, + { + "epoch": 0.35494119614291286, + "grad_norm": 0.5433523058891296, + "learning_rate": 7.354701138281688e-05, + "loss": 1.7982, + "step": 6368 + }, + { + "epoch": 0.35499693439607605, + "grad_norm": 0.587772011756897, + "learning_rate": 7.35391560027665e-05, + "loss": 1.7944, + "step": 6369 + }, + { + "epoch": 0.3550526726492392, + "grad_norm": 0.562419056892395, + "learning_rate": 7.353129987619133e-05, + "loss": 1.8376, + "step": 6370 + }, + { + "epoch": 0.3551084109024023, + "grad_norm": 0.524745523929596, + "learning_rate": 7.352344300334053e-05, + "loss": 1.575, + "step": 6371 + }, + { + "epoch": 0.3551641491555655, + "grad_norm": 0.5049068927764893, + "learning_rate": 7.351558538446326e-05, + "loss": 1.3716, + "step": 6372 + }, + { + "epoch": 0.3552198874087286, + "grad_norm": 0.6006641387939453, + "learning_rate": 7.350772701980872e-05, + "loss": 1.9018, + "step": 6373 + }, + { + "epoch": 0.35527562566189175, + "grad_norm": 0.5516168475151062, + "learning_rate": 7.349986790962613e-05, + "loss": 1.6401, + "step": 6374 + }, + { + "epoch": 0.3553313639150549, + "grad_norm": 0.5250164270401001, + "learning_rate": 7.349200805416478e-05, + "loss": 1.5694, + "step": 6375 + }, + { + "epoch": 0.35538710216821806, + "grad_norm": 0.5079348087310791, + "learning_rate": 7.348414745367387e-05, + "loss": 1.6291, + "step": 6376 + }, + { + "epoch": 0.3554428404213812, + "grad_norm": 0.5634783506393433, + "learning_rate": 7.347628610840274e-05, + "loss": 1.6777, + "step": 6377 + }, + { + "epoch": 0.3554985786745443, + "grad_norm": 0.5921057462692261, + "learning_rate": 7.346842401860069e-05, + "loss": 1.922, + "step": 6378 + }, + { + "epoch": 0.3555543169277075, + "grad_norm": 0.5826466679573059, + "learning_rate": 7.346056118451705e-05, + "loss": 1.7305, + "step": 6379 + }, + { + "epoch": 0.35561005518087063, + "grad_norm": 0.5478690266609192, + "learning_rate": 7.345269760640121e-05, + "loss": 1.7387, + "step": 6380 + }, + { + "epoch": 0.35566579343403376, + "grad_norm": 0.5795879364013672, + "learning_rate": 7.344483328450253e-05, + "loss": 1.6662, + "step": 6381 + }, + { + "epoch": 0.35572153168719695, + "grad_norm": 0.5886217355728149, + "learning_rate": 7.343696821907042e-05, + "loss": 1.8065, + "step": 6382 + }, + { + "epoch": 0.3557772699403601, + "grad_norm": 0.6385563611984253, + "learning_rate": 7.342910241035434e-05, + "loss": 1.7933, + "step": 6383 + }, + { + "epoch": 0.3558330081935232, + "grad_norm": 0.5828480124473572, + "learning_rate": 7.342123585860374e-05, + "loss": 1.6203, + "step": 6384 + }, + { + "epoch": 0.3558887464466864, + "grad_norm": 0.5478693842887878, + "learning_rate": 7.341336856406808e-05, + "loss": 1.6706, + "step": 6385 + }, + { + "epoch": 0.3559444846998495, + "grad_norm": 0.5751214027404785, + "learning_rate": 7.340550052699689e-05, + "loss": 1.8427, + "step": 6386 + }, + { + "epoch": 0.35600022295301265, + "grad_norm": 0.5512586236000061, + "learning_rate": 7.339763174763968e-05, + "loss": 1.7332, + "step": 6387 + }, + { + "epoch": 0.3560559612061758, + "grad_norm": 0.5546371340751648, + "learning_rate": 7.3389762226246e-05, + "loss": 1.5966, + "step": 6388 + }, + { + "epoch": 0.35611169945933896, + "grad_norm": 0.5267236232757568, + "learning_rate": 7.338189196306544e-05, + "loss": 1.8137, + "step": 6389 + }, + { + "epoch": 0.3561674377125021, + "grad_norm": 0.5219095945358276, + "learning_rate": 7.33740209583476e-05, + "loss": 1.6799, + "step": 6390 + }, + { + "epoch": 0.3562231759656652, + "grad_norm": 0.5330881476402283, + "learning_rate": 7.33661492123421e-05, + "loss": 1.6959, + "step": 6391 + }, + { + "epoch": 0.3562789142188284, + "grad_norm": 0.5660157203674316, + "learning_rate": 7.335827672529856e-05, + "loss": 1.7565, + "step": 6392 + }, + { + "epoch": 0.35633465247199153, + "grad_norm": 0.5627869963645935, + "learning_rate": 7.335040349746669e-05, + "loss": 1.7526, + "step": 6393 + }, + { + "epoch": 0.35639039072515466, + "grad_norm": 0.588152289390564, + "learning_rate": 7.334252952909615e-05, + "loss": 1.64, + "step": 6394 + }, + { + "epoch": 0.35644612897831784, + "grad_norm": 0.5885617733001709, + "learning_rate": 7.333465482043667e-05, + "loss": 1.7358, + "step": 6395 + }, + { + "epoch": 0.356501867231481, + "grad_norm": 0.6158447265625, + "learning_rate": 7.3326779371738e-05, + "loss": 1.854, + "step": 6396 + }, + { + "epoch": 0.3565576054846441, + "grad_norm": 0.5353176593780518, + "learning_rate": 7.33189031832499e-05, + "loss": 1.6502, + "step": 6397 + }, + { + "epoch": 0.35661334373780723, + "grad_norm": 0.5986976027488708, + "learning_rate": 7.331102625522212e-05, + "loss": 1.6757, + "step": 6398 + }, + { + "epoch": 0.3566690819909704, + "grad_norm": 0.5034981966018677, + "learning_rate": 7.330314858790453e-05, + "loss": 1.5362, + "step": 6399 + }, + { + "epoch": 0.35672482024413354, + "grad_norm": 0.5768936276435852, + "learning_rate": 7.32952701815469e-05, + "loss": 1.7302, + "step": 6400 + }, + { + "epoch": 0.3567805584972967, + "grad_norm": 0.5493230819702148, + "learning_rate": 7.328739103639916e-05, + "loss": 1.7755, + "step": 6401 + }, + { + "epoch": 0.35683629675045986, + "grad_norm": 0.5121830105781555, + "learning_rate": 7.327951115271113e-05, + "loss": 1.5803, + "step": 6402 + }, + { + "epoch": 0.356892035003623, + "grad_norm": 0.546416699886322, + "learning_rate": 7.327163053073273e-05, + "loss": 1.5991, + "step": 6403 + }, + { + "epoch": 0.3569477732567861, + "grad_norm": 0.5108504891395569, + "learning_rate": 7.32637491707139e-05, + "loss": 1.6789, + "step": 6404 + }, + { + "epoch": 0.3570035115099493, + "grad_norm": 0.5747851729393005, + "learning_rate": 7.32558670729046e-05, + "loss": 1.8266, + "step": 6405 + }, + { + "epoch": 0.35705924976311243, + "grad_norm": 0.587032675743103, + "learning_rate": 7.324798423755476e-05, + "loss": 1.6093, + "step": 6406 + }, + { + "epoch": 0.35711498801627556, + "grad_norm": 0.5485719442367554, + "learning_rate": 7.324010066491442e-05, + "loss": 1.6672, + "step": 6407 + }, + { + "epoch": 0.35717072626943874, + "grad_norm": 0.5325014591217041, + "learning_rate": 7.323221635523358e-05, + "loss": 1.7776, + "step": 6408 + }, + { + "epoch": 0.35722646452260187, + "grad_norm": 0.5524224638938904, + "learning_rate": 7.32243313087623e-05, + "loss": 1.9326, + "step": 6409 + }, + { + "epoch": 0.357282202775765, + "grad_norm": 0.5688652396202087, + "learning_rate": 7.321644552575062e-05, + "loss": 1.8942, + "step": 6410 + }, + { + "epoch": 0.35733794102892813, + "grad_norm": 0.5133098363876343, + "learning_rate": 7.320855900644867e-05, + "loss": 1.6339, + "step": 6411 + }, + { + "epoch": 0.3573936792820913, + "grad_norm": 0.5422292947769165, + "learning_rate": 7.320067175110653e-05, + "loss": 1.681, + "step": 6412 + }, + { + "epoch": 0.35744941753525444, + "grad_norm": 0.5691182613372803, + "learning_rate": 7.319278375997436e-05, + "loss": 1.847, + "step": 6413 + }, + { + "epoch": 0.3575051557884176, + "grad_norm": 0.5584883689880371, + "learning_rate": 7.31848950333023e-05, + "loss": 1.7616, + "step": 6414 + }, + { + "epoch": 0.35756089404158076, + "grad_norm": 0.5878840088844299, + "learning_rate": 7.317700557134056e-05, + "loss": 1.7561, + "step": 6415 + }, + { + "epoch": 0.3576166322947439, + "grad_norm": 0.5363910794258118, + "learning_rate": 7.316911537433933e-05, + "loss": 1.6086, + "step": 6416 + }, + { + "epoch": 0.357672370547907, + "grad_norm": 0.5783511996269226, + "learning_rate": 7.316122444254884e-05, + "loss": 1.7853, + "step": 6417 + }, + { + "epoch": 0.3577281088010702, + "grad_norm": 0.5695887804031372, + "learning_rate": 7.315333277621935e-05, + "loss": 1.5816, + "step": 6418 + }, + { + "epoch": 0.35778384705423333, + "grad_norm": 0.5631670355796814, + "learning_rate": 7.314544037560114e-05, + "loss": 1.5703, + "step": 6419 + }, + { + "epoch": 0.35783958530739646, + "grad_norm": 0.5459564328193665, + "learning_rate": 7.313754724094451e-05, + "loss": 1.6222, + "step": 6420 + }, + { + "epoch": 0.3578953235605596, + "grad_norm": 0.5215150117874146, + "learning_rate": 7.312965337249979e-05, + "loss": 1.7888, + "step": 6421 + }, + { + "epoch": 0.35795106181372277, + "grad_norm": 0.5654617547988892, + "learning_rate": 7.312175877051732e-05, + "loss": 1.7508, + "step": 6422 + }, + { + "epoch": 0.3580068000668859, + "grad_norm": 0.5510186553001404, + "learning_rate": 7.311386343524747e-05, + "loss": 1.8401, + "step": 6423 + }, + { + "epoch": 0.35806253832004903, + "grad_norm": 0.521782398223877, + "learning_rate": 7.310596736694062e-05, + "loss": 1.5428, + "step": 6424 + }, + { + "epoch": 0.3581182765732122, + "grad_norm": 0.5308924317359924, + "learning_rate": 7.309807056584722e-05, + "loss": 1.464, + "step": 6425 + }, + { + "epoch": 0.35817401482637534, + "grad_norm": 0.5567795634269714, + "learning_rate": 7.309017303221768e-05, + "loss": 1.7063, + "step": 6426 + }, + { + "epoch": 0.35822975307953847, + "grad_norm": 0.5558245778083801, + "learning_rate": 7.308227476630249e-05, + "loss": 1.6636, + "step": 6427 + }, + { + "epoch": 0.35828549133270166, + "grad_norm": 0.5258497595787048, + "learning_rate": 7.30743757683521e-05, + "loss": 1.5777, + "step": 6428 + }, + { + "epoch": 0.3583412295858648, + "grad_norm": 0.5101563930511475, + "learning_rate": 7.306647603861706e-05, + "loss": 1.5602, + "step": 6429 + }, + { + "epoch": 0.3583969678390279, + "grad_norm": 0.5508061647415161, + "learning_rate": 7.305857557734789e-05, + "loss": 1.659, + "step": 6430 + }, + { + "epoch": 0.3584527060921911, + "grad_norm": 0.6159545183181763, + "learning_rate": 7.305067438479513e-05, + "loss": 1.9413, + "step": 6431 + }, + { + "epoch": 0.3585084443453542, + "grad_norm": 0.5804408192634583, + "learning_rate": 7.30427724612094e-05, + "loss": 1.7138, + "step": 6432 + }, + { + "epoch": 0.35856418259851736, + "grad_norm": 0.5316668748855591, + "learning_rate": 7.303486980684125e-05, + "loss": 1.7588, + "step": 6433 + }, + { + "epoch": 0.3586199208516805, + "grad_norm": 0.6093178391456604, + "learning_rate": 7.302696642194134e-05, + "loss": 1.8426, + "step": 6434 + }, + { + "epoch": 0.35867565910484367, + "grad_norm": 0.5371636152267456, + "learning_rate": 7.30190623067603e-05, + "loss": 1.5852, + "step": 6435 + }, + { + "epoch": 0.3587313973580068, + "grad_norm": 0.5050824284553528, + "learning_rate": 7.301115746154884e-05, + "loss": 1.5495, + "step": 6436 + }, + { + "epoch": 0.3587871356111699, + "grad_norm": 0.5830590724945068, + "learning_rate": 7.300325188655761e-05, + "loss": 1.8611, + "step": 6437 + }, + { + "epoch": 0.3588428738643331, + "grad_norm": 0.5415953397750854, + "learning_rate": 7.299534558203735e-05, + "loss": 1.6437, + "step": 6438 + }, + { + "epoch": 0.35889861211749624, + "grad_norm": 0.5701804757118225, + "learning_rate": 7.298743854823882e-05, + "loss": 1.8723, + "step": 6439 + }, + { + "epoch": 0.35895435037065937, + "grad_norm": 0.5361306667327881, + "learning_rate": 7.297953078541274e-05, + "loss": 1.518, + "step": 6440 + }, + { + "epoch": 0.35901008862382255, + "grad_norm": 0.5895618796348572, + "learning_rate": 7.297162229380994e-05, + "loss": 1.8528, + "step": 6441 + }, + { + "epoch": 0.3590658268769857, + "grad_norm": 0.5555623173713684, + "learning_rate": 7.29637130736812e-05, + "loss": 1.6619, + "step": 6442 + }, + { + "epoch": 0.3591215651301488, + "grad_norm": 0.5527105331420898, + "learning_rate": 7.295580312527739e-05, + "loss": 1.8209, + "step": 6443 + }, + { + "epoch": 0.35917730338331194, + "grad_norm": 0.5717308521270752, + "learning_rate": 7.294789244884932e-05, + "loss": 1.6109, + "step": 6444 + }, + { + "epoch": 0.3592330416364751, + "grad_norm": 0.5484607815742493, + "learning_rate": 7.293998104464792e-05, + "loss": 1.7449, + "step": 6445 + }, + { + "epoch": 0.35928877988963825, + "grad_norm": 0.5548183917999268, + "learning_rate": 7.293206891292405e-05, + "loss": 1.7952, + "step": 6446 + }, + { + "epoch": 0.3593445181428014, + "grad_norm": 0.5666037201881409, + "learning_rate": 7.292415605392867e-05, + "loss": 1.8784, + "step": 6447 + }, + { + "epoch": 0.35940025639596457, + "grad_norm": 0.5922662615776062, + "learning_rate": 7.291624246791272e-05, + "loss": 1.8764, + "step": 6448 + }, + { + "epoch": 0.3594559946491277, + "grad_norm": 0.5456053018569946, + "learning_rate": 7.290832815512716e-05, + "loss": 1.7389, + "step": 6449 + }, + { + "epoch": 0.3595117329022908, + "grad_norm": 0.5417848229408264, + "learning_rate": 7.290041311582301e-05, + "loss": 1.591, + "step": 6450 + }, + { + "epoch": 0.359567471155454, + "grad_norm": 0.5787496566772461, + "learning_rate": 7.289249735025127e-05, + "loss": 1.765, + "step": 6451 + }, + { + "epoch": 0.35962320940861714, + "grad_norm": 0.5513389110565186, + "learning_rate": 7.288458085866298e-05, + "loss": 1.6685, + "step": 6452 + }, + { + "epoch": 0.35967894766178027, + "grad_norm": 0.5737441182136536, + "learning_rate": 7.287666364130921e-05, + "loss": 1.6956, + "step": 6453 + }, + { + "epoch": 0.35973468591494345, + "grad_norm": 0.6044551134109497, + "learning_rate": 7.286874569844106e-05, + "loss": 1.7829, + "step": 6454 + }, + { + "epoch": 0.3597904241681066, + "grad_norm": 0.5688374638557434, + "learning_rate": 7.286082703030961e-05, + "loss": 1.8747, + "step": 6455 + }, + { + "epoch": 0.3598461624212697, + "grad_norm": 0.5276156067848206, + "learning_rate": 7.285290763716604e-05, + "loss": 1.5944, + "step": 6456 + }, + { + "epoch": 0.35990190067443284, + "grad_norm": 0.5913518667221069, + "learning_rate": 7.284498751926147e-05, + "loss": 1.6307, + "step": 6457 + }, + { + "epoch": 0.359957638927596, + "grad_norm": 0.5470561981201172, + "learning_rate": 7.283706667684709e-05, + "loss": 1.6096, + "step": 6458 + }, + { + "epoch": 0.36001337718075915, + "grad_norm": 0.5165275931358337, + "learning_rate": 7.28291451101741e-05, + "loss": 1.6963, + "step": 6459 + }, + { + "epoch": 0.3600691154339223, + "grad_norm": 0.552894651889801, + "learning_rate": 7.282122281949374e-05, + "loss": 1.7304, + "step": 6460 + }, + { + "epoch": 0.36012485368708547, + "grad_norm": 0.573884129524231, + "learning_rate": 7.281329980505724e-05, + "loss": 1.8304, + "step": 6461 + }, + { + "epoch": 0.3601805919402486, + "grad_norm": 0.5113431811332703, + "learning_rate": 7.280537606711589e-05, + "loss": 1.509, + "step": 6462 + }, + { + "epoch": 0.3602363301934117, + "grad_norm": 0.54507976770401, + "learning_rate": 7.279745160592097e-05, + "loss": 1.765, + "step": 6463 + }, + { + "epoch": 0.3602920684465749, + "grad_norm": 0.5524507761001587, + "learning_rate": 7.278952642172381e-05, + "loss": 1.6604, + "step": 6464 + }, + { + "epoch": 0.36034780669973804, + "grad_norm": 0.5713779926300049, + "learning_rate": 7.278160051477574e-05, + "loss": 1.6273, + "step": 6465 + }, + { + "epoch": 0.36040354495290117, + "grad_norm": 0.5713092684745789, + "learning_rate": 7.277367388532812e-05, + "loss": 1.7693, + "step": 6466 + }, + { + "epoch": 0.3604592832060643, + "grad_norm": 0.5316145420074463, + "learning_rate": 7.276574653363236e-05, + "loss": 1.6402, + "step": 6467 + }, + { + "epoch": 0.3605150214592275, + "grad_norm": 0.5453936457633972, + "learning_rate": 7.275781845993983e-05, + "loss": 1.9642, + "step": 6468 + }, + { + "epoch": 0.3605707597123906, + "grad_norm": 0.5773400068283081, + "learning_rate": 7.274988966450201e-05, + "loss": 1.8417, + "step": 6469 + }, + { + "epoch": 0.36062649796555374, + "grad_norm": 0.5517837405204773, + "learning_rate": 7.274196014757032e-05, + "loss": 1.6307, + "step": 6470 + }, + { + "epoch": 0.3606822362187169, + "grad_norm": 0.5454963445663452, + "learning_rate": 7.273402990939626e-05, + "loss": 1.7725, + "step": 6471 + }, + { + "epoch": 0.36073797447188005, + "grad_norm": 0.5993366837501526, + "learning_rate": 7.272609895023129e-05, + "loss": 1.831, + "step": 6472 + }, + { + "epoch": 0.3607937127250432, + "grad_norm": 0.5621082186698914, + "learning_rate": 7.2718167270327e-05, + "loss": 1.4942, + "step": 6473 + }, + { + "epoch": 0.36084945097820637, + "grad_norm": 0.5455790758132935, + "learning_rate": 7.271023486993488e-05, + "loss": 1.722, + "step": 6474 + }, + { + "epoch": 0.3609051892313695, + "grad_norm": 0.5093836784362793, + "learning_rate": 7.270230174930653e-05, + "loss": 1.5921, + "step": 6475 + }, + { + "epoch": 0.3609609274845326, + "grad_norm": 0.5746651887893677, + "learning_rate": 7.269436790869352e-05, + "loss": 1.7303, + "step": 6476 + }, + { + "epoch": 0.3610166657376958, + "grad_norm": 0.5042871832847595, + "learning_rate": 7.268643334834748e-05, + "loss": 1.4386, + "step": 6477 + }, + { + "epoch": 0.36107240399085894, + "grad_norm": 0.6014384627342224, + "learning_rate": 7.267849806852005e-05, + "loss": 1.7803, + "step": 6478 + }, + { + "epoch": 0.36112814224402207, + "grad_norm": 0.49684464931488037, + "learning_rate": 7.267056206946289e-05, + "loss": 1.6513, + "step": 6479 + }, + { + "epoch": 0.3611838804971852, + "grad_norm": 0.6013120412826538, + "learning_rate": 7.266262535142767e-05, + "loss": 1.718, + "step": 6480 + }, + { + "epoch": 0.3612396187503484, + "grad_norm": 0.5482946038246155, + "learning_rate": 7.26546879146661e-05, + "loss": 1.8295, + "step": 6481 + }, + { + "epoch": 0.3612953570035115, + "grad_norm": 0.5593370199203491, + "learning_rate": 7.264674975942994e-05, + "loss": 1.8042, + "step": 6482 + }, + { + "epoch": 0.36135109525667464, + "grad_norm": 0.5430756211280823, + "learning_rate": 7.26388108859709e-05, + "loss": 1.6976, + "step": 6483 + }, + { + "epoch": 0.3614068335098378, + "grad_norm": 0.5408653020858765, + "learning_rate": 7.263087129454078e-05, + "loss": 1.5425, + "step": 6484 + }, + { + "epoch": 0.36146257176300095, + "grad_norm": 0.5399406552314758, + "learning_rate": 7.262293098539134e-05, + "loss": 1.7552, + "step": 6485 + }, + { + "epoch": 0.3615183100161641, + "grad_norm": 0.5077804923057556, + "learning_rate": 7.261498995877447e-05, + "loss": 1.5728, + "step": 6486 + }, + { + "epoch": 0.36157404826932726, + "grad_norm": 0.5409159660339355, + "learning_rate": 7.260704821494196e-05, + "loss": 1.7926, + "step": 6487 + }, + { + "epoch": 0.3616297865224904, + "grad_norm": 0.4922293424606323, + "learning_rate": 7.259910575414569e-05, + "loss": 1.46, + "step": 6488 + }, + { + "epoch": 0.3616855247756535, + "grad_norm": 0.530104398727417, + "learning_rate": 7.259116257663753e-05, + "loss": 1.4995, + "step": 6489 + }, + { + "epoch": 0.36174126302881665, + "grad_norm": 0.5683631896972656, + "learning_rate": 7.258321868266943e-05, + "loss": 1.6736, + "step": 6490 + }, + { + "epoch": 0.36179700128197984, + "grad_norm": 0.5562074184417725, + "learning_rate": 7.25752740724933e-05, + "loss": 1.6224, + "step": 6491 + }, + { + "epoch": 0.36185273953514296, + "grad_norm": 0.6077651381492615, + "learning_rate": 7.256732874636109e-05, + "loss": 1.7814, + "step": 6492 + }, + { + "epoch": 0.3619084777883061, + "grad_norm": 0.5739646553993225, + "learning_rate": 7.255938270452479e-05, + "loss": 1.7024, + "step": 6493 + }, + { + "epoch": 0.3619642160414693, + "grad_norm": 0.5540484189987183, + "learning_rate": 7.25514359472364e-05, + "loss": 1.5576, + "step": 6494 + }, + { + "epoch": 0.3620199542946324, + "grad_norm": 0.5674034953117371, + "learning_rate": 7.254348847474797e-05, + "loss": 1.8389, + "step": 6495 + }, + { + "epoch": 0.36207569254779554, + "grad_norm": 0.5664230585098267, + "learning_rate": 7.253554028731148e-05, + "loss": 1.7194, + "step": 6496 + }, + { + "epoch": 0.3621314308009587, + "grad_norm": 0.5525626540184021, + "learning_rate": 7.252759138517909e-05, + "loss": 1.3394, + "step": 6497 + }, + { + "epoch": 0.36218716905412185, + "grad_norm": 0.5549319982528687, + "learning_rate": 7.251964176860281e-05, + "loss": 1.6234, + "step": 6498 + }, + { + "epoch": 0.362242907307285, + "grad_norm": 0.5454506874084473, + "learning_rate": 7.25116914378348e-05, + "loss": 1.8937, + "step": 6499 + }, + { + "epoch": 0.36229864556044816, + "grad_norm": 0.5178475379943848, + "learning_rate": 7.25037403931272e-05, + "loss": 1.5599, + "step": 6500 + }, + { + "epoch": 0.3623543838136113, + "grad_norm": 0.5836609601974487, + "learning_rate": 7.249578863473216e-05, + "loss": 1.8547, + "step": 6501 + }, + { + "epoch": 0.3624101220667744, + "grad_norm": 0.5162068605422974, + "learning_rate": 7.248783616290186e-05, + "loss": 1.4538, + "step": 6502 + }, + { + "epoch": 0.36246586031993755, + "grad_norm": 0.5959255695343018, + "learning_rate": 7.24798829778885e-05, + "loss": 1.8237, + "step": 6503 + }, + { + "epoch": 0.36252159857310073, + "grad_norm": 0.5471253395080566, + "learning_rate": 7.247192907994433e-05, + "loss": 1.5705, + "step": 6504 + }, + { + "epoch": 0.36257733682626386, + "grad_norm": 0.5264948010444641, + "learning_rate": 7.246397446932159e-05, + "loss": 1.6597, + "step": 6505 + }, + { + "epoch": 0.362633075079427, + "grad_norm": 0.5829636454582214, + "learning_rate": 7.245601914627255e-05, + "loss": 1.9137, + "step": 6506 + }, + { + "epoch": 0.3626888133325902, + "grad_norm": 0.5371459722518921, + "learning_rate": 7.244806311104952e-05, + "loss": 1.5883, + "step": 6507 + }, + { + "epoch": 0.3627445515857533, + "grad_norm": 0.6225298643112183, + "learning_rate": 7.24401063639048e-05, + "loss": 1.9112, + "step": 6508 + }, + { + "epoch": 0.36280028983891643, + "grad_norm": 0.5452820062637329, + "learning_rate": 7.243214890509073e-05, + "loss": 1.6557, + "step": 6509 + }, + { + "epoch": 0.3628560280920796, + "grad_norm": 0.5052100419998169, + "learning_rate": 7.24241907348597e-05, + "loss": 1.4815, + "step": 6510 + }, + { + "epoch": 0.36291176634524275, + "grad_norm": 0.5527931451797485, + "learning_rate": 7.241623185346409e-05, + "loss": 1.6867, + "step": 6511 + }, + { + "epoch": 0.3629675045984059, + "grad_norm": 0.5412555932998657, + "learning_rate": 7.240827226115629e-05, + "loss": 1.5461, + "step": 6512 + }, + { + "epoch": 0.363023242851569, + "grad_norm": 0.5910593271255493, + "learning_rate": 7.240031195818874e-05, + "loss": 1.7713, + "step": 6513 + }, + { + "epoch": 0.3630789811047322, + "grad_norm": 0.5672844052314758, + "learning_rate": 7.239235094481391e-05, + "loss": 1.3757, + "step": 6514 + }, + { + "epoch": 0.3631347193578953, + "grad_norm": 0.580847442150116, + "learning_rate": 7.238438922128425e-05, + "loss": 1.9571, + "step": 6515 + }, + { + "epoch": 0.36319045761105845, + "grad_norm": 0.642082691192627, + "learning_rate": 7.237642678785228e-05, + "loss": 1.9311, + "step": 6516 + }, + { + "epoch": 0.36324619586422163, + "grad_norm": 0.49659648537635803, + "learning_rate": 7.236846364477052e-05, + "loss": 1.6393, + "step": 6517 + }, + { + "epoch": 0.36330193411738476, + "grad_norm": 0.5082789063453674, + "learning_rate": 7.23604997922915e-05, + "loss": 1.5183, + "step": 6518 + }, + { + "epoch": 0.3633576723705479, + "grad_norm": 0.5978274941444397, + "learning_rate": 7.235253523066781e-05, + "loss": 1.8529, + "step": 6519 + }, + { + "epoch": 0.3634134106237111, + "grad_norm": 0.5323169231414795, + "learning_rate": 7.234456996015202e-05, + "loss": 1.6463, + "step": 6520 + }, + { + "epoch": 0.3634691488768742, + "grad_norm": 0.5250840187072754, + "learning_rate": 7.233660398099675e-05, + "loss": 1.4439, + "step": 6521 + }, + { + "epoch": 0.36352488713003733, + "grad_norm": 0.566667914390564, + "learning_rate": 7.232863729345464e-05, + "loss": 1.5871, + "step": 6522 + }, + { + "epoch": 0.3635806253832005, + "grad_norm": 0.5944371223449707, + "learning_rate": 7.232066989777833e-05, + "loss": 1.978, + "step": 6523 + }, + { + "epoch": 0.36363636363636365, + "grad_norm": 0.556692361831665, + "learning_rate": 7.231270179422051e-05, + "loss": 1.5579, + "step": 6524 + }, + { + "epoch": 0.3636921018895268, + "grad_norm": 0.5578793883323669, + "learning_rate": 7.230473298303388e-05, + "loss": 1.6899, + "step": 6525 + }, + { + "epoch": 0.3637478401426899, + "grad_norm": 0.672099232673645, + "learning_rate": 7.229676346447117e-05, + "loss": 2.1324, + "step": 6526 + }, + { + "epoch": 0.3638035783958531, + "grad_norm": 0.5312888622283936, + "learning_rate": 7.228879323878512e-05, + "loss": 1.453, + "step": 6527 + }, + { + "epoch": 0.3638593166490162, + "grad_norm": 0.5675061345100403, + "learning_rate": 7.22808223062285e-05, + "loss": 1.8623, + "step": 6528 + }, + { + "epoch": 0.36391505490217935, + "grad_norm": 0.49803319573402405, + "learning_rate": 7.227285066705412e-05, + "loss": 1.41, + "step": 6529 + }, + { + "epoch": 0.36397079315534253, + "grad_norm": 0.5489189028739929, + "learning_rate": 7.226487832151476e-05, + "loss": 1.6551, + "step": 6530 + }, + { + "epoch": 0.36402653140850566, + "grad_norm": 0.5769960284233093, + "learning_rate": 7.225690526986326e-05, + "loss": 1.7853, + "step": 6531 + }, + { + "epoch": 0.3640822696616688, + "grad_norm": 0.5400393605232239, + "learning_rate": 7.224893151235251e-05, + "loss": 1.5544, + "step": 6532 + }, + { + "epoch": 0.364138007914832, + "grad_norm": 0.5720942616462708, + "learning_rate": 7.224095704923537e-05, + "loss": 1.9824, + "step": 6533 + }, + { + "epoch": 0.3641937461679951, + "grad_norm": 0.5403176546096802, + "learning_rate": 7.223298188076475e-05, + "loss": 1.5978, + "step": 6534 + }, + { + "epoch": 0.36424948442115823, + "grad_norm": 0.5350765585899353, + "learning_rate": 7.222500600719356e-05, + "loss": 1.5945, + "step": 6535 + }, + { + "epoch": 0.36430522267432136, + "grad_norm": 0.542413592338562, + "learning_rate": 7.221702942877477e-05, + "loss": 1.717, + "step": 6536 + }, + { + "epoch": 0.36436096092748455, + "grad_norm": 0.5472922921180725, + "learning_rate": 7.220905214576134e-05, + "loss": 1.6535, + "step": 6537 + }, + { + "epoch": 0.3644166991806477, + "grad_norm": 0.5479559302330017, + "learning_rate": 7.220107415840626e-05, + "loss": 1.5444, + "step": 6538 + }, + { + "epoch": 0.3644724374338108, + "grad_norm": 0.5131190419197083, + "learning_rate": 7.219309546696255e-05, + "loss": 1.3543, + "step": 6539 + }, + { + "epoch": 0.364528175686974, + "grad_norm": 0.5852962732315063, + "learning_rate": 7.218511607168326e-05, + "loss": 1.7422, + "step": 6540 + }, + { + "epoch": 0.3645839139401371, + "grad_norm": 0.5998173356056213, + "learning_rate": 7.21771359728214e-05, + "loss": 1.9125, + "step": 6541 + }, + { + "epoch": 0.36463965219330025, + "grad_norm": 0.5412231683731079, + "learning_rate": 7.216915517063012e-05, + "loss": 1.8743, + "step": 6542 + }, + { + "epoch": 0.36469539044646343, + "grad_norm": 0.5305824279785156, + "learning_rate": 7.216117366536249e-05, + "loss": 1.476, + "step": 6543 + }, + { + "epoch": 0.36475112869962656, + "grad_norm": 0.586646556854248, + "learning_rate": 7.215319145727161e-05, + "loss": 1.7591, + "step": 6544 + }, + { + "epoch": 0.3648068669527897, + "grad_norm": 0.5975636839866638, + "learning_rate": 7.214520854661071e-05, + "loss": 1.9996, + "step": 6545 + }, + { + "epoch": 0.3648626052059529, + "grad_norm": 0.543255627155304, + "learning_rate": 7.213722493363288e-05, + "loss": 1.6909, + "step": 6546 + }, + { + "epoch": 0.364918343459116, + "grad_norm": 0.5423970222473145, + "learning_rate": 7.212924061859135e-05, + "loss": 1.6429, + "step": 6547 + }, + { + "epoch": 0.36497408171227913, + "grad_norm": 0.5859336256980896, + "learning_rate": 7.212125560173933e-05, + "loss": 1.9055, + "step": 6548 + }, + { + "epoch": 0.36502981996544226, + "grad_norm": 0.5425530672073364, + "learning_rate": 7.211326988333006e-05, + "loss": 1.7073, + "step": 6549 + }, + { + "epoch": 0.36508555821860544, + "grad_norm": 0.580575168132782, + "learning_rate": 7.210528346361678e-05, + "loss": 1.6739, + "step": 6550 + }, + { + "epoch": 0.3651412964717686, + "grad_norm": 0.599686324596405, + "learning_rate": 7.209729634285282e-05, + "loss": 1.7179, + "step": 6551 + }, + { + "epoch": 0.3651970347249317, + "grad_norm": 0.5199704170227051, + "learning_rate": 7.208930852129143e-05, + "loss": 1.7484, + "step": 6552 + }, + { + "epoch": 0.3652527729780949, + "grad_norm": 0.5557204484939575, + "learning_rate": 7.208131999918599e-05, + "loss": 1.6169, + "step": 6553 + }, + { + "epoch": 0.365308511231258, + "grad_norm": 0.5307885408401489, + "learning_rate": 7.20733307767898e-05, + "loss": 1.4029, + "step": 6554 + }, + { + "epoch": 0.36536424948442114, + "grad_norm": 0.5462751388549805, + "learning_rate": 7.206534085435625e-05, + "loss": 1.6399, + "step": 6555 + }, + { + "epoch": 0.36541998773758433, + "grad_norm": 0.5815526247024536, + "learning_rate": 7.205735023213877e-05, + "loss": 1.7943, + "step": 6556 + }, + { + "epoch": 0.36547572599074746, + "grad_norm": 0.5783229470252991, + "learning_rate": 7.204935891039071e-05, + "loss": 1.7919, + "step": 6557 + }, + { + "epoch": 0.3655314642439106, + "grad_norm": 0.5671087503433228, + "learning_rate": 7.204136688936556e-05, + "loss": 1.8125, + "step": 6558 + }, + { + "epoch": 0.3655872024970737, + "grad_norm": 0.5661280751228333, + "learning_rate": 7.203337416931675e-05, + "loss": 1.6377, + "step": 6559 + }, + { + "epoch": 0.3656429407502369, + "grad_norm": 0.5448043942451477, + "learning_rate": 7.202538075049781e-05, + "loss": 1.6929, + "step": 6560 + }, + { + "epoch": 0.36569867900340003, + "grad_norm": 0.5517578125, + "learning_rate": 7.201738663316217e-05, + "loss": 1.7849, + "step": 6561 + }, + { + "epoch": 0.36575441725656316, + "grad_norm": 0.5554426312446594, + "learning_rate": 7.200939181756341e-05, + "loss": 1.3314, + "step": 6562 + }, + { + "epoch": 0.36581015550972634, + "grad_norm": 0.5693673491477966, + "learning_rate": 7.200139630395507e-05, + "loss": 1.8517, + "step": 6563 + }, + { + "epoch": 0.36586589376288947, + "grad_norm": 0.5405746698379517, + "learning_rate": 7.199340009259072e-05, + "loss": 1.58, + "step": 6564 + }, + { + "epoch": 0.3659216320160526, + "grad_norm": 0.633660078048706, + "learning_rate": 7.198540318372394e-05, + "loss": 1.9478, + "step": 6565 + }, + { + "epoch": 0.3659773702692158, + "grad_norm": 0.5665812492370605, + "learning_rate": 7.197740557760834e-05, + "loss": 1.6334, + "step": 6566 + }, + { + "epoch": 0.3660331085223789, + "grad_norm": 0.549199104309082, + "learning_rate": 7.196940727449759e-05, + "loss": 1.4779, + "step": 6567 + }, + { + "epoch": 0.36608884677554204, + "grad_norm": 0.49754953384399414, + "learning_rate": 7.196140827464533e-05, + "loss": 1.5101, + "step": 6568 + }, + { + "epoch": 0.3661445850287052, + "grad_norm": 0.5829338431358337, + "learning_rate": 7.195340857830524e-05, + "loss": 1.7219, + "step": 6569 + }, + { + "epoch": 0.36620032328186836, + "grad_norm": 0.5498637557029724, + "learning_rate": 7.194540818573103e-05, + "loss": 1.6491, + "step": 6570 + }, + { + "epoch": 0.3662560615350315, + "grad_norm": 0.5562663674354553, + "learning_rate": 7.193740709717643e-05, + "loss": 1.7846, + "step": 6571 + }, + { + "epoch": 0.3663117997881946, + "grad_norm": 0.5268211364746094, + "learning_rate": 7.192940531289517e-05, + "loss": 1.5521, + "step": 6572 + }, + { + "epoch": 0.3663675380413578, + "grad_norm": 0.5425642132759094, + "learning_rate": 7.192140283314104e-05, + "loss": 1.7968, + "step": 6573 + }, + { + "epoch": 0.3664232762945209, + "grad_norm": 0.5653149485588074, + "learning_rate": 7.191339965816781e-05, + "loss": 1.6086, + "step": 6574 + }, + { + "epoch": 0.36647901454768406, + "grad_norm": 0.5728870630264282, + "learning_rate": 7.190539578822932e-05, + "loss": 1.8264, + "step": 6575 + }, + { + "epoch": 0.36653475280084724, + "grad_norm": 0.5501007437705994, + "learning_rate": 7.189739122357939e-05, + "loss": 1.8426, + "step": 6576 + }, + { + "epoch": 0.36659049105401037, + "grad_norm": 0.5318872332572937, + "learning_rate": 7.188938596447188e-05, + "loss": 1.7968, + "step": 6577 + }, + { + "epoch": 0.3666462293071735, + "grad_norm": 0.5750231146812439, + "learning_rate": 7.188138001116065e-05, + "loss": 1.6745, + "step": 6578 + }, + { + "epoch": 0.3667019675603367, + "grad_norm": 0.6171157956123352, + "learning_rate": 7.187337336389966e-05, + "loss": 2.0264, + "step": 6579 + }, + { + "epoch": 0.3667577058134998, + "grad_norm": 0.5361387133598328, + "learning_rate": 7.186536602294278e-05, + "loss": 1.5105, + "step": 6580 + }, + { + "epoch": 0.36681344406666294, + "grad_norm": 0.5726244449615479, + "learning_rate": 7.185735798854396e-05, + "loss": 1.6055, + "step": 6581 + }, + { + "epoch": 0.36686918231982607, + "grad_norm": 0.5350404381752014, + "learning_rate": 7.184934926095721e-05, + "loss": 1.7493, + "step": 6582 + }, + { + "epoch": 0.36692492057298925, + "grad_norm": 0.5755828022956848, + "learning_rate": 7.184133984043646e-05, + "loss": 1.6443, + "step": 6583 + }, + { + "epoch": 0.3669806588261524, + "grad_norm": 0.5558964610099792, + "learning_rate": 7.183332972723578e-05, + "loss": 1.816, + "step": 6584 + }, + { + "epoch": 0.3670363970793155, + "grad_norm": 0.5483201146125793, + "learning_rate": 7.182531892160917e-05, + "loss": 1.6545, + "step": 6585 + }, + { + "epoch": 0.3670921353324787, + "grad_norm": 0.5599815249443054, + "learning_rate": 7.18173074238107e-05, + "loss": 1.634, + "step": 6586 + }, + { + "epoch": 0.3671478735856418, + "grad_norm": 0.5529213547706604, + "learning_rate": 7.180929523409443e-05, + "loss": 1.7378, + "step": 6587 + }, + { + "epoch": 0.36720361183880496, + "grad_norm": 0.5131180286407471, + "learning_rate": 7.180128235271449e-05, + "loss": 1.5528, + "step": 6588 + }, + { + "epoch": 0.36725935009196814, + "grad_norm": 0.591602623462677, + "learning_rate": 7.179326877992497e-05, + "loss": 1.7482, + "step": 6589 + }, + { + "epoch": 0.36731508834513127, + "grad_norm": 0.4902382791042328, + "learning_rate": 7.178525451598003e-05, + "loss": 1.4865, + "step": 6590 + }, + { + "epoch": 0.3673708265982944, + "grad_norm": 0.5887609720230103, + "learning_rate": 7.177723956113383e-05, + "loss": 1.9031, + "step": 6591 + }, + { + "epoch": 0.3674265648514576, + "grad_norm": 0.5403375625610352, + "learning_rate": 7.176922391564056e-05, + "loss": 1.6702, + "step": 6592 + }, + { + "epoch": 0.3674823031046207, + "grad_norm": 0.5793707370758057, + "learning_rate": 7.176120757975444e-05, + "loss": 1.6571, + "step": 6593 + }, + { + "epoch": 0.36753804135778384, + "grad_norm": 0.5770851373672485, + "learning_rate": 7.175319055372969e-05, + "loss": 1.7841, + "step": 6594 + }, + { + "epoch": 0.36759377961094697, + "grad_norm": 0.5472514629364014, + "learning_rate": 7.174517283782058e-05, + "loss": 1.6785, + "step": 6595 + }, + { + "epoch": 0.36764951786411015, + "grad_norm": 0.5961628556251526, + "learning_rate": 7.173715443228133e-05, + "loss": 1.6604, + "step": 6596 + }, + { + "epoch": 0.3677052561172733, + "grad_norm": 0.5890954732894897, + "learning_rate": 7.172913533736632e-05, + "loss": 1.7003, + "step": 6597 + }, + { + "epoch": 0.3677609943704364, + "grad_norm": 0.6537253260612488, + "learning_rate": 7.17211155533298e-05, + "loss": 1.9955, + "step": 6598 + }, + { + "epoch": 0.3678167326235996, + "grad_norm": 0.5514366030693054, + "learning_rate": 7.171309508042615e-05, + "loss": 1.5601, + "step": 6599 + }, + { + "epoch": 0.3678724708767627, + "grad_norm": 0.6790293455123901, + "learning_rate": 7.170507391890972e-05, + "loss": 2.1675, + "step": 6600 + }, + { + "epoch": 0.36792820912992585, + "grad_norm": 0.5294934511184692, + "learning_rate": 7.16970520690349e-05, + "loss": 1.6509, + "step": 6601 + }, + { + "epoch": 0.36798394738308904, + "grad_norm": 0.5617215037345886, + "learning_rate": 7.168902953105608e-05, + "loss": 1.7301, + "step": 6602 + }, + { + "epoch": 0.36803968563625217, + "grad_norm": 0.5187042355537415, + "learning_rate": 7.16810063052277e-05, + "loss": 1.4945, + "step": 6603 + }, + { + "epoch": 0.3680954238894153, + "grad_norm": 0.5646756291389465, + "learning_rate": 7.16729823918042e-05, + "loss": 1.8281, + "step": 6604 + }, + { + "epoch": 0.3681511621425784, + "grad_norm": 0.5496782064437866, + "learning_rate": 7.166495779104007e-05, + "loss": 1.6996, + "step": 6605 + }, + { + "epoch": 0.3682069003957416, + "grad_norm": 0.6056029796600342, + "learning_rate": 7.16569325031898e-05, + "loss": 1.9787, + "step": 6606 + }, + { + "epoch": 0.36826263864890474, + "grad_norm": 0.5624659061431885, + "learning_rate": 7.164890652850789e-05, + "loss": 1.7931, + "step": 6607 + }, + { + "epoch": 0.36831837690206787, + "grad_norm": 0.5342402458190918, + "learning_rate": 7.16408798672489e-05, + "loss": 1.664, + "step": 6608 + }, + { + "epoch": 0.36837411515523105, + "grad_norm": 0.5402200818061829, + "learning_rate": 7.163285251966736e-05, + "loss": 1.6754, + "step": 6609 + }, + { + "epoch": 0.3684298534083942, + "grad_norm": 0.5262821316719055, + "learning_rate": 7.162482448601789e-05, + "loss": 1.5501, + "step": 6610 + }, + { + "epoch": 0.3684855916615573, + "grad_norm": 0.5371507406234741, + "learning_rate": 7.161679576655503e-05, + "loss": 1.6168, + "step": 6611 + }, + { + "epoch": 0.3685413299147205, + "grad_norm": 0.5895312428474426, + "learning_rate": 7.160876636153349e-05, + "loss": 1.8576, + "step": 6612 + }, + { + "epoch": 0.3685970681678836, + "grad_norm": 0.5309399962425232, + "learning_rate": 7.160073627120784e-05, + "loss": 1.5803, + "step": 6613 + }, + { + "epoch": 0.36865280642104675, + "grad_norm": 0.564697265625, + "learning_rate": 7.159270549583278e-05, + "loss": 1.2999, + "step": 6614 + }, + { + "epoch": 0.36870854467420994, + "grad_norm": 0.5483527183532715, + "learning_rate": 7.158467403566299e-05, + "loss": 1.559, + "step": 6615 + }, + { + "epoch": 0.36876428292737307, + "grad_norm": 0.47662925720214844, + "learning_rate": 7.15766418909532e-05, + "loss": 1.2871, + "step": 6616 + }, + { + "epoch": 0.3688200211805362, + "grad_norm": 0.5505543947219849, + "learning_rate": 7.156860906195811e-05, + "loss": 1.717, + "step": 6617 + }, + { + "epoch": 0.3688757594336993, + "grad_norm": 0.5837799310684204, + "learning_rate": 7.156057554893251e-05, + "loss": 1.8828, + "step": 6618 + }, + { + "epoch": 0.3689314976868625, + "grad_norm": 0.6020135283470154, + "learning_rate": 7.155254135213117e-05, + "loss": 1.6727, + "step": 6619 + }, + { + "epoch": 0.36898723594002564, + "grad_norm": 0.5805865526199341, + "learning_rate": 7.154450647180886e-05, + "loss": 1.7273, + "step": 6620 + }, + { + "epoch": 0.36904297419318877, + "grad_norm": 0.5338916182518005, + "learning_rate": 7.153647090822043e-05, + "loss": 1.5732, + "step": 6621 + }, + { + "epoch": 0.36909871244635195, + "grad_norm": 0.5388802886009216, + "learning_rate": 7.152843466162069e-05, + "loss": 1.5612, + "step": 6622 + }, + { + "epoch": 0.3691544506995151, + "grad_norm": 0.5497878789901733, + "learning_rate": 7.152039773226456e-05, + "loss": 1.6601, + "step": 6623 + }, + { + "epoch": 0.3692101889526782, + "grad_norm": 0.5147888660430908, + "learning_rate": 7.151236012040685e-05, + "loss": 1.6467, + "step": 6624 + }, + { + "epoch": 0.3692659272058414, + "grad_norm": 0.5906471014022827, + "learning_rate": 7.150432182630252e-05, + "loss": 1.6429, + "step": 6625 + }, + { + "epoch": 0.3693216654590045, + "grad_norm": 0.5193469524383545, + "learning_rate": 7.149628285020648e-05, + "loss": 1.7369, + "step": 6626 + }, + { + "epoch": 0.36937740371216765, + "grad_norm": 0.5903412699699402, + "learning_rate": 7.148824319237367e-05, + "loss": 1.7329, + "step": 6627 + }, + { + "epoch": 0.3694331419653308, + "grad_norm": 0.5230131149291992, + "learning_rate": 7.148020285305907e-05, + "loss": 1.5495, + "step": 6628 + }, + { + "epoch": 0.36948888021849396, + "grad_norm": 0.5554400086402893, + "learning_rate": 7.147216183251768e-05, + "loss": 1.7592, + "step": 6629 + }, + { + "epoch": 0.3695446184716571, + "grad_norm": 0.4992237985134125, + "learning_rate": 7.146412013100451e-05, + "loss": 1.5094, + "step": 6630 + }, + { + "epoch": 0.3696003567248202, + "grad_norm": 0.6239908933639526, + "learning_rate": 7.14560777487746e-05, + "loss": 1.9804, + "step": 6631 + }, + { + "epoch": 0.3696560949779834, + "grad_norm": 0.49736112356185913, + "learning_rate": 7.144803468608298e-05, + "loss": 1.4165, + "step": 6632 + }, + { + "epoch": 0.36971183323114654, + "grad_norm": 0.5291538834571838, + "learning_rate": 7.143999094318477e-05, + "loss": 1.6362, + "step": 6633 + }, + { + "epoch": 0.36976757148430967, + "grad_norm": 0.5881434679031372, + "learning_rate": 7.143194652033505e-05, + "loss": 1.8459, + "step": 6634 + }, + { + "epoch": 0.36982330973747285, + "grad_norm": 0.5663610100746155, + "learning_rate": 7.142390141778895e-05, + "loss": 1.655, + "step": 6635 + }, + { + "epoch": 0.369879047990636, + "grad_norm": 0.6780499219894409, + "learning_rate": 7.141585563580158e-05, + "loss": 1.8284, + "step": 6636 + }, + { + "epoch": 0.3699347862437991, + "grad_norm": 0.544389009475708, + "learning_rate": 7.140780917462814e-05, + "loss": 1.6024, + "step": 6637 + }, + { + "epoch": 0.3699905244969623, + "grad_norm": 0.5259643197059631, + "learning_rate": 7.139976203452383e-05, + "loss": 1.6143, + "step": 6638 + }, + { + "epoch": 0.3700462627501254, + "grad_norm": 0.5904932022094727, + "learning_rate": 7.139171421574383e-05, + "loss": 1.7714, + "step": 6639 + }, + { + "epoch": 0.37010200100328855, + "grad_norm": 0.5398536920547485, + "learning_rate": 7.138366571854338e-05, + "loss": 1.5943, + "step": 6640 + }, + { + "epoch": 0.3701577392564517, + "grad_norm": 0.5698688626289368, + "learning_rate": 7.137561654317772e-05, + "loss": 1.7892, + "step": 6641 + }, + { + "epoch": 0.37021347750961486, + "grad_norm": 0.5498561859130859, + "learning_rate": 7.136756668990213e-05, + "loss": 1.7051, + "step": 6642 + }, + { + "epoch": 0.370269215762778, + "grad_norm": 0.5418841242790222, + "learning_rate": 7.13595161589719e-05, + "loss": 1.6284, + "step": 6643 + }, + { + "epoch": 0.3703249540159411, + "grad_norm": 0.5735422968864441, + "learning_rate": 7.135146495064236e-05, + "loss": 1.5837, + "step": 6644 + }, + { + "epoch": 0.3703806922691043, + "grad_norm": 0.593471348285675, + "learning_rate": 7.134341306516885e-05, + "loss": 1.891, + "step": 6645 + }, + { + "epoch": 0.37043643052226743, + "grad_norm": 0.519626796245575, + "learning_rate": 7.13353605028067e-05, + "loss": 1.676, + "step": 6646 + }, + { + "epoch": 0.37049216877543056, + "grad_norm": 0.59029620885849, + "learning_rate": 7.132730726381134e-05, + "loss": 1.8638, + "step": 6647 + }, + { + "epoch": 0.37054790702859375, + "grad_norm": 0.6374014019966125, + "learning_rate": 7.13192533484381e-05, + "loss": 2.0887, + "step": 6648 + }, + { + "epoch": 0.3706036452817569, + "grad_norm": 0.5250412821769714, + "learning_rate": 7.131119875694246e-05, + "loss": 1.5408, + "step": 6649 + }, + { + "epoch": 0.37065938353492, + "grad_norm": 0.5467897653579712, + "learning_rate": 7.130314348957986e-05, + "loss": 1.4246, + "step": 6650 + }, + { + "epoch": 0.37071512178808314, + "grad_norm": 0.5109268426895142, + "learning_rate": 7.129508754660575e-05, + "loss": 1.4972, + "step": 6651 + }, + { + "epoch": 0.3707708600412463, + "grad_norm": 0.5759547352790833, + "learning_rate": 7.128703092827562e-05, + "loss": 1.9089, + "step": 6652 + }, + { + "epoch": 0.37082659829440945, + "grad_norm": 0.6243898272514343, + "learning_rate": 7.127897363484497e-05, + "loss": 1.9196, + "step": 6653 + }, + { + "epoch": 0.3708823365475726, + "grad_norm": 0.5852481722831726, + "learning_rate": 7.127091566656936e-05, + "loss": 1.7842, + "step": 6654 + }, + { + "epoch": 0.37093807480073576, + "grad_norm": 0.5579434037208557, + "learning_rate": 7.12628570237043e-05, + "loss": 1.6261, + "step": 6655 + }, + { + "epoch": 0.3709938130538989, + "grad_norm": 0.5315961837768555, + "learning_rate": 7.125479770650539e-05, + "loss": 1.6085, + "step": 6656 + }, + { + "epoch": 0.371049551307062, + "grad_norm": 0.5678053498268127, + "learning_rate": 7.124673771522824e-05, + "loss": 1.905, + "step": 6657 + }, + { + "epoch": 0.3711052895602252, + "grad_norm": 0.5308210849761963, + "learning_rate": 7.123867705012843e-05, + "loss": 1.5081, + "step": 6658 + }, + { + "epoch": 0.37116102781338833, + "grad_norm": 0.5750522017478943, + "learning_rate": 7.123061571146161e-05, + "loss": 1.6793, + "step": 6659 + }, + { + "epoch": 0.37121676606655146, + "grad_norm": 0.5785144567489624, + "learning_rate": 7.122255369948346e-05, + "loss": 1.6402, + "step": 6660 + }, + { + "epoch": 0.37127250431971465, + "grad_norm": 0.5107117891311646, + "learning_rate": 7.121449101444964e-05, + "loss": 1.6232, + "step": 6661 + }, + { + "epoch": 0.3713282425728778, + "grad_norm": 0.5365573763847351, + "learning_rate": 7.120642765661584e-05, + "loss": 1.7163, + "step": 6662 + }, + { + "epoch": 0.3713839808260409, + "grad_norm": 0.5924217104911804, + "learning_rate": 7.119836362623781e-05, + "loss": 1.9706, + "step": 6663 + }, + { + "epoch": 0.37143971907920403, + "grad_norm": 0.5683318972587585, + "learning_rate": 7.119029892357128e-05, + "loss": 1.9116, + "step": 6664 + }, + { + "epoch": 0.3714954573323672, + "grad_norm": 0.524502694606781, + "learning_rate": 7.118223354887201e-05, + "loss": 1.5862, + "step": 6665 + }, + { + "epoch": 0.37155119558553035, + "grad_norm": 0.5245027542114258, + "learning_rate": 7.11741675023958e-05, + "loss": 1.5945, + "step": 6666 + }, + { + "epoch": 0.3716069338386935, + "grad_norm": 0.5658608675003052, + "learning_rate": 7.116610078439845e-05, + "loss": 1.5802, + "step": 6667 + }, + { + "epoch": 0.37166267209185666, + "grad_norm": 0.5938420295715332, + "learning_rate": 7.115803339513578e-05, + "loss": 2.005, + "step": 6668 + }, + { + "epoch": 0.3717184103450198, + "grad_norm": 0.5456317663192749, + "learning_rate": 7.114996533486366e-05, + "loss": 1.5013, + "step": 6669 + }, + { + "epoch": 0.3717741485981829, + "grad_norm": 0.5922924280166626, + "learning_rate": 7.114189660383794e-05, + "loss": 2.0418, + "step": 6670 + }, + { + "epoch": 0.3718298868513461, + "grad_norm": 0.5821951627731323, + "learning_rate": 7.113382720231454e-05, + "loss": 1.7955, + "step": 6671 + }, + { + "epoch": 0.37188562510450923, + "grad_norm": 0.5134814381599426, + "learning_rate": 7.112575713054936e-05, + "loss": 1.4315, + "step": 6672 + }, + { + "epoch": 0.37194136335767236, + "grad_norm": 0.5751433968544006, + "learning_rate": 7.111768638879833e-05, + "loss": 1.566, + "step": 6673 + }, + { + "epoch": 0.3719971016108355, + "grad_norm": 0.5614348649978638, + "learning_rate": 7.110961497731742e-05, + "loss": 1.8572, + "step": 6674 + }, + { + "epoch": 0.3720528398639987, + "grad_norm": 0.5680375099182129, + "learning_rate": 7.110154289636259e-05, + "loss": 2.0372, + "step": 6675 + }, + { + "epoch": 0.3721085781171618, + "grad_norm": 0.5367892980575562, + "learning_rate": 7.109347014618985e-05, + "loss": 1.6665, + "step": 6676 + }, + { + "epoch": 0.37216431637032493, + "grad_norm": 0.563017725944519, + "learning_rate": 7.108539672705523e-05, + "loss": 1.747, + "step": 6677 + }, + { + "epoch": 0.3722200546234881, + "grad_norm": 0.5716055631637573, + "learning_rate": 7.107732263921475e-05, + "loss": 1.4182, + "step": 6678 + }, + { + "epoch": 0.37227579287665125, + "grad_norm": 0.514310896396637, + "learning_rate": 7.106924788292448e-05, + "loss": 1.6223, + "step": 6679 + }, + { + "epoch": 0.3723315311298144, + "grad_norm": 0.5039160251617432, + "learning_rate": 7.106117245844054e-05, + "loss": 1.5979, + "step": 6680 + }, + { + "epoch": 0.37238726938297756, + "grad_norm": 0.5815281867980957, + "learning_rate": 7.105309636601898e-05, + "loss": 1.9983, + "step": 6681 + }, + { + "epoch": 0.3724430076361407, + "grad_norm": 0.5450384616851807, + "learning_rate": 7.104501960591595e-05, + "loss": 1.5488, + "step": 6682 + }, + { + "epoch": 0.3724987458893038, + "grad_norm": 0.5386560559272766, + "learning_rate": 7.103694217838761e-05, + "loss": 1.6376, + "step": 6683 + }, + { + "epoch": 0.372554484142467, + "grad_norm": 0.5220578908920288, + "learning_rate": 7.102886408369012e-05, + "loss": 1.4654, + "step": 6684 + }, + { + "epoch": 0.37261022239563013, + "grad_norm": 0.5630038976669312, + "learning_rate": 7.102078532207966e-05, + "loss": 1.7554, + "step": 6685 + }, + { + "epoch": 0.37266596064879326, + "grad_norm": 0.5405006408691406, + "learning_rate": 7.101270589381245e-05, + "loss": 1.8247, + "step": 6686 + }, + { + "epoch": 0.3727216989019564, + "grad_norm": 0.5460960865020752, + "learning_rate": 7.100462579914474e-05, + "loss": 1.7902, + "step": 6687 + }, + { + "epoch": 0.3727774371551196, + "grad_norm": 0.5519078969955444, + "learning_rate": 7.099654503833273e-05, + "loss": 1.7138, + "step": 6688 + }, + { + "epoch": 0.3728331754082827, + "grad_norm": 0.5574856400489807, + "learning_rate": 7.098846361163273e-05, + "loss": 1.6607, + "step": 6689 + }, + { + "epoch": 0.37288891366144583, + "grad_norm": 0.5525651574134827, + "learning_rate": 7.098038151930107e-05, + "loss": 1.8834, + "step": 6690 + }, + { + "epoch": 0.372944651914609, + "grad_norm": 0.5278156399726868, + "learning_rate": 7.097229876159401e-05, + "loss": 1.67, + "step": 6691 + }, + { + "epoch": 0.37300039016777214, + "grad_norm": 0.5362699627876282, + "learning_rate": 7.096421533876792e-05, + "loss": 1.6881, + "step": 6692 + }, + { + "epoch": 0.3730561284209353, + "grad_norm": 0.522748589515686, + "learning_rate": 7.095613125107915e-05, + "loss": 1.6077, + "step": 6693 + }, + { + "epoch": 0.37311186667409846, + "grad_norm": 0.5335802435874939, + "learning_rate": 7.094804649878407e-05, + "loss": 1.6124, + "step": 6694 + }, + { + "epoch": 0.3731676049272616, + "grad_norm": 0.5322664976119995, + "learning_rate": 7.093996108213909e-05, + "loss": 1.735, + "step": 6695 + }, + { + "epoch": 0.3732233431804247, + "grad_norm": 0.5863260626792908, + "learning_rate": 7.093187500140064e-05, + "loss": 1.9465, + "step": 6696 + }, + { + "epoch": 0.37327908143358784, + "grad_norm": 0.5546720623970032, + "learning_rate": 7.092378825682517e-05, + "loss": 1.6817, + "step": 6697 + }, + { + "epoch": 0.37333481968675103, + "grad_norm": 0.5397077798843384, + "learning_rate": 7.091570084866909e-05, + "loss": 1.7072, + "step": 6698 + }, + { + "epoch": 0.37339055793991416, + "grad_norm": 0.5567345023155212, + "learning_rate": 7.090761277718897e-05, + "loss": 1.7315, + "step": 6699 + }, + { + "epoch": 0.3734462961930773, + "grad_norm": 0.5560916662216187, + "learning_rate": 7.089952404264126e-05, + "loss": 1.5599, + "step": 6700 + }, + { + "epoch": 0.37350203444624047, + "grad_norm": 0.5497678518295288, + "learning_rate": 7.089143464528249e-05, + "loss": 1.6328, + "step": 6701 + }, + { + "epoch": 0.3735577726994036, + "grad_norm": 0.5806947946548462, + "learning_rate": 7.088334458536921e-05, + "loss": 1.8025, + "step": 6702 + }, + { + "epoch": 0.37361351095256673, + "grad_norm": 0.6178561449050903, + "learning_rate": 7.087525386315802e-05, + "loss": 1.6715, + "step": 6703 + }, + { + "epoch": 0.3736692492057299, + "grad_norm": 0.5702304244041443, + "learning_rate": 7.086716247890548e-05, + "loss": 1.7321, + "step": 6704 + }, + { + "epoch": 0.37372498745889304, + "grad_norm": 0.5194035172462463, + "learning_rate": 7.08590704328682e-05, + "loss": 1.5648, + "step": 6705 + }, + { + "epoch": 0.37378072571205617, + "grad_norm": 0.5901757478713989, + "learning_rate": 7.085097772530283e-05, + "loss": 1.9348, + "step": 6706 + }, + { + "epoch": 0.37383646396521936, + "grad_norm": 0.7031030654907227, + "learning_rate": 7.084288435646603e-05, + "loss": 1.5634, + "step": 6707 + }, + { + "epoch": 0.3738922022183825, + "grad_norm": 0.5556403398513794, + "learning_rate": 7.083479032661445e-05, + "loss": 1.6525, + "step": 6708 + }, + { + "epoch": 0.3739479404715456, + "grad_norm": 0.5691899061203003, + "learning_rate": 7.082669563600478e-05, + "loss": 1.885, + "step": 6709 + }, + { + "epoch": 0.37400367872470874, + "grad_norm": 0.5547059774398804, + "learning_rate": 7.081860028489377e-05, + "loss": 1.8645, + "step": 6710 + }, + { + "epoch": 0.37405941697787193, + "grad_norm": 0.5635570287704468, + "learning_rate": 7.081050427353814e-05, + "loss": 1.8752, + "step": 6711 + }, + { + "epoch": 0.37411515523103506, + "grad_norm": 0.5423487424850464, + "learning_rate": 7.080240760219465e-05, + "loss": 1.5953, + "step": 6712 + }, + { + "epoch": 0.3741708934841982, + "grad_norm": 0.5141568183898926, + "learning_rate": 7.079431027112006e-05, + "loss": 1.4812, + "step": 6713 + }, + { + "epoch": 0.37422663173736137, + "grad_norm": 0.5988462567329407, + "learning_rate": 7.078621228057121e-05, + "loss": 1.8588, + "step": 6714 + }, + { + "epoch": 0.3742823699905245, + "grad_norm": 0.5320055484771729, + "learning_rate": 7.077811363080489e-05, + "loss": 1.745, + "step": 6715 + }, + { + "epoch": 0.37433810824368763, + "grad_norm": 0.5388814806938171, + "learning_rate": 7.077001432207795e-05, + "loss": 1.511, + "step": 6716 + }, + { + "epoch": 0.3743938464968508, + "grad_norm": 0.537324070930481, + "learning_rate": 7.076191435464725e-05, + "loss": 1.6644, + "step": 6717 + }, + { + "epoch": 0.37444958475001394, + "grad_norm": 0.533687174320221, + "learning_rate": 7.075381372876967e-05, + "loss": 1.73, + "step": 6718 + }, + { + "epoch": 0.37450532300317707, + "grad_norm": 0.5057275295257568, + "learning_rate": 7.074571244470214e-05, + "loss": 1.6284, + "step": 6719 + }, + { + "epoch": 0.3745610612563402, + "grad_norm": 0.6067156195640564, + "learning_rate": 7.073761050270156e-05, + "loss": 1.84, + "step": 6720 + }, + { + "epoch": 0.3746167995095034, + "grad_norm": 0.5253334641456604, + "learning_rate": 7.072950790302487e-05, + "loss": 1.4598, + "step": 6721 + }, + { + "epoch": 0.3746725377626665, + "grad_norm": 0.521193265914917, + "learning_rate": 7.072140464592907e-05, + "loss": 1.5442, + "step": 6722 + }, + { + "epoch": 0.37472827601582964, + "grad_norm": 0.5262565612792969, + "learning_rate": 7.071330073167112e-05, + "loss": 1.6898, + "step": 6723 + }, + { + "epoch": 0.3747840142689928, + "grad_norm": 0.6259338855743408, + "learning_rate": 7.070519616050804e-05, + "loss": 1.731, + "step": 6724 + }, + { + "epoch": 0.37483975252215596, + "grad_norm": 0.5520288348197937, + "learning_rate": 7.069709093269687e-05, + "loss": 1.796, + "step": 6725 + }, + { + "epoch": 0.3748954907753191, + "grad_norm": 0.5660863518714905, + "learning_rate": 7.068898504849462e-05, + "loss": 1.656, + "step": 6726 + }, + { + "epoch": 0.37495122902848227, + "grad_norm": 0.5522897839546204, + "learning_rate": 7.06808785081584e-05, + "loss": 1.6656, + "step": 6727 + }, + { + "epoch": 0.3750069672816454, + "grad_norm": 0.6100639700889587, + "learning_rate": 7.067277131194529e-05, + "loss": 1.7658, + "step": 6728 + }, + { + "epoch": 0.3750627055348085, + "grad_norm": 0.5829086899757385, + "learning_rate": 7.066466346011242e-05, + "loss": 1.6342, + "step": 6729 + }, + { + "epoch": 0.3751184437879717, + "grad_norm": 0.6315231323242188, + "learning_rate": 7.06565549529169e-05, + "loss": 1.7829, + "step": 6730 + }, + { + "epoch": 0.37517418204113484, + "grad_norm": 0.6006489992141724, + "learning_rate": 7.064844579061588e-05, + "loss": 1.8819, + "step": 6731 + }, + { + "epoch": 0.37522992029429797, + "grad_norm": 0.5952304005622864, + "learning_rate": 7.064033597346658e-05, + "loss": 1.6654, + "step": 6732 + }, + { + "epoch": 0.3752856585474611, + "grad_norm": 0.5768652558326721, + "learning_rate": 7.063222550172612e-05, + "loss": 1.6577, + "step": 6733 + }, + { + "epoch": 0.3753413968006243, + "grad_norm": 0.5706788301467896, + "learning_rate": 7.062411437565179e-05, + "loss": 1.7532, + "step": 6734 + }, + { + "epoch": 0.3753971350537874, + "grad_norm": 0.6298890113830566, + "learning_rate": 7.06160025955008e-05, + "loss": 1.7744, + "step": 6735 + }, + { + "epoch": 0.37545287330695054, + "grad_norm": 0.5873239636421204, + "learning_rate": 7.06078901615304e-05, + "loss": 1.9847, + "step": 6736 + }, + { + "epoch": 0.3755086115601137, + "grad_norm": 0.5103023648262024, + "learning_rate": 7.059977707399787e-05, + "loss": 1.4559, + "step": 6737 + }, + { + "epoch": 0.37556434981327685, + "grad_norm": 0.521653950214386, + "learning_rate": 7.059166333316054e-05, + "loss": 1.6796, + "step": 6738 + }, + { + "epoch": 0.37562008806644, + "grad_norm": 0.5209727883338928, + "learning_rate": 7.058354893927568e-05, + "loss": 1.5015, + "step": 6739 + }, + { + "epoch": 0.37567582631960317, + "grad_norm": 0.6425443887710571, + "learning_rate": 7.057543389260068e-05, + "loss": 1.8178, + "step": 6740 + }, + { + "epoch": 0.3757315645727663, + "grad_norm": 0.5647505521774292, + "learning_rate": 7.056731819339286e-05, + "loss": 1.7513, + "step": 6741 + }, + { + "epoch": 0.3757873028259294, + "grad_norm": 0.5992183089256287, + "learning_rate": 7.055920184190964e-05, + "loss": 1.6351, + "step": 6742 + }, + { + "epoch": 0.37584304107909255, + "grad_norm": 0.5495748519897461, + "learning_rate": 7.055108483840839e-05, + "loss": 1.6854, + "step": 6743 + }, + { + "epoch": 0.37589877933225574, + "grad_norm": 0.5780972242355347, + "learning_rate": 7.054296718314656e-05, + "loss": 1.7937, + "step": 6744 + }, + { + "epoch": 0.37595451758541887, + "grad_norm": 0.5518954992294312, + "learning_rate": 7.053484887638158e-05, + "loss": 1.6708, + "step": 6745 + }, + { + "epoch": 0.376010255838582, + "grad_norm": 0.5211352109909058, + "learning_rate": 7.052672991837093e-05, + "loss": 1.6565, + "step": 6746 + }, + { + "epoch": 0.3760659940917452, + "grad_norm": 0.5192275643348694, + "learning_rate": 7.051861030937207e-05, + "loss": 1.5376, + "step": 6747 + }, + { + "epoch": 0.3761217323449083, + "grad_norm": 0.5492019057273865, + "learning_rate": 7.051049004964254e-05, + "loss": 1.7518, + "step": 6748 + }, + { + "epoch": 0.37617747059807144, + "grad_norm": 0.5412474274635315, + "learning_rate": 7.050236913943984e-05, + "loss": 1.5384, + "step": 6749 + }, + { + "epoch": 0.3762332088512346, + "grad_norm": 0.5172974467277527, + "learning_rate": 7.049424757902153e-05, + "loss": 1.6072, + "step": 6750 + }, + { + "epoch": 0.37628894710439775, + "grad_norm": 0.5415205955505371, + "learning_rate": 7.048612536864517e-05, + "loss": 1.8342, + "step": 6751 + }, + { + "epoch": 0.3763446853575609, + "grad_norm": 0.5428817868232727, + "learning_rate": 7.047800250856837e-05, + "loss": 1.6988, + "step": 6752 + }, + { + "epoch": 0.37640042361072407, + "grad_norm": 0.5195114612579346, + "learning_rate": 7.046987899904871e-05, + "loss": 1.4647, + "step": 6753 + }, + { + "epoch": 0.3764561618638872, + "grad_norm": 0.5440792441368103, + "learning_rate": 7.046175484034384e-05, + "loss": 1.5224, + "step": 6754 + }, + { + "epoch": 0.3765119001170503, + "grad_norm": 0.5353301763534546, + "learning_rate": 7.045363003271141e-05, + "loss": 1.664, + "step": 6755 + }, + { + "epoch": 0.37656763837021345, + "grad_norm": 0.5722842812538147, + "learning_rate": 7.044550457640909e-05, + "loss": 1.6422, + "step": 6756 + }, + { + "epoch": 0.37662337662337664, + "grad_norm": 0.5732778906822205, + "learning_rate": 7.043737847169455e-05, + "loss": 2.0161, + "step": 6757 + }, + { + "epoch": 0.37667911487653977, + "grad_norm": 0.5180158019065857, + "learning_rate": 7.042925171882557e-05, + "loss": 1.6388, + "step": 6758 + }, + { + "epoch": 0.3767348531297029, + "grad_norm": 0.530694305896759, + "learning_rate": 7.042112431805979e-05, + "loss": 1.546, + "step": 6759 + }, + { + "epoch": 0.3767905913828661, + "grad_norm": 0.5620813965797424, + "learning_rate": 7.041299626965503e-05, + "loss": 1.6727, + "step": 6760 + }, + { + "epoch": 0.3768463296360292, + "grad_norm": 0.5627542734146118, + "learning_rate": 7.040486757386904e-05, + "loss": 1.7527, + "step": 6761 + }, + { + "epoch": 0.37690206788919234, + "grad_norm": 0.588291347026825, + "learning_rate": 7.039673823095963e-05, + "loss": 1.9415, + "step": 6762 + }, + { + "epoch": 0.3769578061423555, + "grad_norm": 0.5307551026344299, + "learning_rate": 7.03886082411846e-05, + "loss": 1.6316, + "step": 6763 + }, + { + "epoch": 0.37701354439551865, + "grad_norm": 0.5484150648117065, + "learning_rate": 7.038047760480179e-05, + "loss": 1.6363, + "step": 6764 + }, + { + "epoch": 0.3770692826486818, + "grad_norm": 0.5301684737205505, + "learning_rate": 7.037234632206905e-05, + "loss": 1.7243, + "step": 6765 + }, + { + "epoch": 0.3771250209018449, + "grad_norm": 0.5907619595527649, + "learning_rate": 7.036421439324427e-05, + "loss": 1.6807, + "step": 6766 + }, + { + "epoch": 0.3771807591550081, + "grad_norm": 0.5170425772666931, + "learning_rate": 7.035608181858533e-05, + "loss": 1.6641, + "step": 6767 + }, + { + "epoch": 0.3772364974081712, + "grad_norm": 0.5344756245613098, + "learning_rate": 7.034794859835016e-05, + "loss": 1.8226, + "step": 6768 + }, + { + "epoch": 0.37729223566133435, + "grad_norm": 0.5386238098144531, + "learning_rate": 7.033981473279672e-05, + "loss": 1.6291, + "step": 6769 + }, + { + "epoch": 0.37734797391449754, + "grad_norm": 0.5417985916137695, + "learning_rate": 7.033168022218292e-05, + "loss": 1.5797, + "step": 6770 + }, + { + "epoch": 0.37740371216766067, + "grad_norm": 0.5583431124687195, + "learning_rate": 7.032354506676678e-05, + "loss": 1.7165, + "step": 6771 + }, + { + "epoch": 0.3774594504208238, + "grad_norm": 0.5974751114845276, + "learning_rate": 7.031540926680627e-05, + "loss": 1.9454, + "step": 6772 + }, + { + "epoch": 0.377515188673987, + "grad_norm": 0.5629299283027649, + "learning_rate": 7.030727282255944e-05, + "loss": 1.9527, + "step": 6773 + }, + { + "epoch": 0.3775709269271501, + "grad_norm": 0.49648937582969666, + "learning_rate": 7.02991357342843e-05, + "loss": 1.4055, + "step": 6774 + }, + { + "epoch": 0.37762666518031324, + "grad_norm": 0.5776923298835754, + "learning_rate": 7.029099800223895e-05, + "loss": 1.5683, + "step": 6775 + }, + { + "epoch": 0.3776824034334764, + "grad_norm": 0.5667086839675903, + "learning_rate": 7.028285962668144e-05, + "loss": 1.6576, + "step": 6776 + }, + { + "epoch": 0.37773814168663955, + "grad_norm": 0.51173996925354, + "learning_rate": 7.027472060786988e-05, + "loss": 1.6046, + "step": 6777 + }, + { + "epoch": 0.3777938799398027, + "grad_norm": 0.6762179732322693, + "learning_rate": 7.026658094606238e-05, + "loss": 1.8251, + "step": 6778 + }, + { + "epoch": 0.3778496181929658, + "grad_norm": 0.6333464980125427, + "learning_rate": 7.02584406415171e-05, + "loss": 1.9974, + "step": 6779 + }, + { + "epoch": 0.377905356446129, + "grad_norm": 0.5379152297973633, + "learning_rate": 7.02502996944922e-05, + "loss": 1.5211, + "step": 6780 + }, + { + "epoch": 0.3779610946992921, + "grad_norm": 0.5208351016044617, + "learning_rate": 7.024215810524586e-05, + "loss": 1.7317, + "step": 6781 + }, + { + "epoch": 0.37801683295245525, + "grad_norm": 0.5434418320655823, + "learning_rate": 7.023401587403629e-05, + "loss": 1.6749, + "step": 6782 + }, + { + "epoch": 0.37807257120561844, + "grad_norm": 0.5639735460281372, + "learning_rate": 7.022587300112171e-05, + "loss": 1.7105, + "step": 6783 + }, + { + "epoch": 0.37812830945878156, + "grad_norm": 0.600032389163971, + "learning_rate": 7.021772948676037e-05, + "loss": 1.8057, + "step": 6784 + }, + { + "epoch": 0.3781840477119447, + "grad_norm": 0.5152847766876221, + "learning_rate": 7.020958533121051e-05, + "loss": 1.6275, + "step": 6785 + }, + { + "epoch": 0.3782397859651079, + "grad_norm": 0.5553915500640869, + "learning_rate": 7.020144053473044e-05, + "loss": 1.786, + "step": 6786 + }, + { + "epoch": 0.378295524218271, + "grad_norm": 0.5452811121940613, + "learning_rate": 7.019329509757845e-05, + "loss": 1.6452, + "step": 6787 + }, + { + "epoch": 0.37835126247143414, + "grad_norm": 0.5100104212760925, + "learning_rate": 7.01851490200129e-05, + "loss": 1.5128, + "step": 6788 + }, + { + "epoch": 0.37840700072459726, + "grad_norm": 0.6309191584587097, + "learning_rate": 7.017700230229208e-05, + "loss": 1.4683, + "step": 6789 + }, + { + "epoch": 0.37846273897776045, + "grad_norm": 0.5344750881195068, + "learning_rate": 7.01688549446744e-05, + "loss": 1.6131, + "step": 6790 + }, + { + "epoch": 0.3785184772309236, + "grad_norm": 0.5286291837692261, + "learning_rate": 7.016070694741824e-05, + "loss": 1.6499, + "step": 6791 + }, + { + "epoch": 0.3785742154840867, + "grad_norm": 0.5597365498542786, + "learning_rate": 7.015255831078201e-05, + "loss": 1.6677, + "step": 6792 + }, + { + "epoch": 0.3786299537372499, + "grad_norm": 0.5482022166252136, + "learning_rate": 7.01444090350241e-05, + "loss": 1.6498, + "step": 6793 + }, + { + "epoch": 0.378685691990413, + "grad_norm": 0.6198036670684814, + "learning_rate": 7.0136259120403e-05, + "loss": 1.8393, + "step": 6794 + }, + { + "epoch": 0.37874143024357615, + "grad_norm": 0.555736243724823, + "learning_rate": 7.012810856717717e-05, + "loss": 1.5817, + "step": 6795 + }, + { + "epoch": 0.37879716849673933, + "grad_norm": 0.5894885659217834, + "learning_rate": 7.011995737560507e-05, + "loss": 1.736, + "step": 6796 + }, + { + "epoch": 0.37885290674990246, + "grad_norm": 0.5784539580345154, + "learning_rate": 7.011180554594525e-05, + "loss": 1.7195, + "step": 6797 + }, + { + "epoch": 0.3789086450030656, + "grad_norm": 0.5761838555335999, + "learning_rate": 7.010365307845621e-05, + "loss": 1.5784, + "step": 6798 + }, + { + "epoch": 0.3789643832562288, + "grad_norm": 0.5359389185905457, + "learning_rate": 7.00954999733965e-05, + "loss": 1.4703, + "step": 6799 + }, + { + "epoch": 0.3790201215093919, + "grad_norm": 0.5606504678726196, + "learning_rate": 7.008734623102471e-05, + "loss": 1.7026, + "step": 6800 + }, + { + "epoch": 0.37907585976255503, + "grad_norm": 0.5452861785888672, + "learning_rate": 7.007919185159942e-05, + "loss": 1.6358, + "step": 6801 + }, + { + "epoch": 0.37913159801571816, + "grad_norm": 0.533334493637085, + "learning_rate": 7.007103683537922e-05, + "loss": 1.5224, + "step": 6802 + }, + { + "epoch": 0.37918733626888135, + "grad_norm": 0.5216323137283325, + "learning_rate": 7.006288118262277e-05, + "loss": 1.5611, + "step": 6803 + }, + { + "epoch": 0.3792430745220445, + "grad_norm": 0.6083248853683472, + "learning_rate": 7.005472489358868e-05, + "loss": 1.9112, + "step": 6804 + }, + { + "epoch": 0.3792988127752076, + "grad_norm": 0.5337701439857483, + "learning_rate": 7.004656796853565e-05, + "loss": 1.678, + "step": 6805 + }, + { + "epoch": 0.3793545510283708, + "grad_norm": 0.5296239256858826, + "learning_rate": 7.003841040772237e-05, + "loss": 1.6372, + "step": 6806 + }, + { + "epoch": 0.3794102892815339, + "grad_norm": 0.5512758493423462, + "learning_rate": 7.003025221140754e-05, + "loss": 1.7838, + "step": 6807 + }, + { + "epoch": 0.37946602753469705, + "grad_norm": 0.5666672587394714, + "learning_rate": 7.00220933798499e-05, + "loss": 1.8518, + "step": 6808 + }, + { + "epoch": 0.37952176578786023, + "grad_norm": 0.5516249537467957, + "learning_rate": 7.001393391330819e-05, + "loss": 1.4928, + "step": 6809 + }, + { + "epoch": 0.37957750404102336, + "grad_norm": 0.5139819979667664, + "learning_rate": 7.000577381204118e-05, + "loss": 1.5464, + "step": 6810 + }, + { + "epoch": 0.3796332422941865, + "grad_norm": 0.5297854542732239, + "learning_rate": 6.999761307630767e-05, + "loss": 1.4929, + "step": 6811 + }, + { + "epoch": 0.3796889805473496, + "grad_norm": 0.5862724184989929, + "learning_rate": 6.998945170636647e-05, + "loss": 1.8435, + "step": 6812 + }, + { + "epoch": 0.3797447188005128, + "grad_norm": 0.5517110228538513, + "learning_rate": 6.998128970247641e-05, + "loss": 1.5962, + "step": 6813 + }, + { + "epoch": 0.37980045705367593, + "grad_norm": 0.5306249260902405, + "learning_rate": 6.997312706489634e-05, + "loss": 1.4978, + "step": 6814 + }, + { + "epoch": 0.37985619530683906, + "grad_norm": 0.5715779662132263, + "learning_rate": 6.996496379388512e-05, + "loss": 1.7663, + "step": 6815 + }, + { + "epoch": 0.37991193356000225, + "grad_norm": 0.5692317485809326, + "learning_rate": 6.995679988970167e-05, + "loss": 1.9011, + "step": 6816 + }, + { + "epoch": 0.3799676718131654, + "grad_norm": 0.5604211091995239, + "learning_rate": 6.994863535260488e-05, + "loss": 1.5928, + "step": 6817 + }, + { + "epoch": 0.3800234100663285, + "grad_norm": 0.5591232776641846, + "learning_rate": 6.994047018285368e-05, + "loss": 1.6347, + "step": 6818 + }, + { + "epoch": 0.3800791483194917, + "grad_norm": 0.515835702419281, + "learning_rate": 6.993230438070702e-05, + "loss": 1.4441, + "step": 6819 + }, + { + "epoch": 0.3801348865726548, + "grad_norm": 0.5194911360740662, + "learning_rate": 6.99241379464239e-05, + "loss": 1.6603, + "step": 6820 + }, + { + "epoch": 0.38019062482581795, + "grad_norm": 0.49259036779403687, + "learning_rate": 6.991597088026327e-05, + "loss": 1.5785, + "step": 6821 + }, + { + "epoch": 0.38024636307898113, + "grad_norm": 0.5865880846977234, + "learning_rate": 6.990780318248416e-05, + "loss": 1.7017, + "step": 6822 + }, + { + "epoch": 0.38030210133214426, + "grad_norm": 0.532753050327301, + "learning_rate": 6.989963485334562e-05, + "loss": 1.7205, + "step": 6823 + }, + { + "epoch": 0.3803578395853074, + "grad_norm": 0.6024113297462463, + "learning_rate": 6.989146589310667e-05, + "loss": 1.8499, + "step": 6824 + }, + { + "epoch": 0.3804135778384705, + "grad_norm": 0.5912168622016907, + "learning_rate": 6.988329630202641e-05, + "loss": 1.7783, + "step": 6825 + }, + { + "epoch": 0.3804693160916337, + "grad_norm": 0.5647505521774292, + "learning_rate": 6.98751260803639e-05, + "loss": 1.6106, + "step": 6826 + }, + { + "epoch": 0.38052505434479683, + "grad_norm": 0.5149972438812256, + "learning_rate": 6.98669552283783e-05, + "loss": 1.652, + "step": 6827 + }, + { + "epoch": 0.38058079259795996, + "grad_norm": 0.5642407536506653, + "learning_rate": 6.98587837463287e-05, + "loss": 1.6075, + "step": 6828 + }, + { + "epoch": 0.38063653085112314, + "grad_norm": 0.6054338812828064, + "learning_rate": 6.985061163447426e-05, + "loss": 1.7205, + "step": 6829 + }, + { + "epoch": 0.3806922691042863, + "grad_norm": 0.5490162372589111, + "learning_rate": 6.984243889307415e-05, + "loss": 1.605, + "step": 6830 + }, + { + "epoch": 0.3807480073574494, + "grad_norm": 0.5481693744659424, + "learning_rate": 6.983426552238756e-05, + "loss": 1.6532, + "step": 6831 + }, + { + "epoch": 0.3808037456106126, + "grad_norm": 0.5470540523529053, + "learning_rate": 6.982609152267374e-05, + "loss": 1.856, + "step": 6832 + }, + { + "epoch": 0.3808594838637757, + "grad_norm": 0.5047014355659485, + "learning_rate": 6.981791689419186e-05, + "loss": 1.5632, + "step": 6833 + }, + { + "epoch": 0.38091522211693885, + "grad_norm": 0.5213363766670227, + "learning_rate": 6.980974163720123e-05, + "loss": 1.648, + "step": 6834 + }, + { + "epoch": 0.380970960370102, + "grad_norm": 0.5108797550201416, + "learning_rate": 6.980156575196107e-05, + "loss": 1.7048, + "step": 6835 + }, + { + "epoch": 0.38102669862326516, + "grad_norm": 0.5571927428245544, + "learning_rate": 6.979338923873073e-05, + "loss": 1.7984, + "step": 6836 + }, + { + "epoch": 0.3810824368764283, + "grad_norm": 0.5656031966209412, + "learning_rate": 6.978521209776945e-05, + "loss": 1.6214, + "step": 6837 + }, + { + "epoch": 0.3811381751295914, + "grad_norm": 0.5520498752593994, + "learning_rate": 6.977703432933661e-05, + "loss": 1.5048, + "step": 6838 + }, + { + "epoch": 0.3811939133827546, + "grad_norm": 0.5377273559570312, + "learning_rate": 6.976885593369155e-05, + "loss": 1.4111, + "step": 6839 + }, + { + "epoch": 0.38124965163591773, + "grad_norm": 0.5396257042884827, + "learning_rate": 6.976067691109365e-05, + "loss": 1.6715, + "step": 6840 + }, + { + "epoch": 0.38130538988908086, + "grad_norm": 0.5259842872619629, + "learning_rate": 6.975249726180227e-05, + "loss": 1.586, + "step": 6841 + }, + { + "epoch": 0.38136112814224404, + "grad_norm": 0.5793870091438293, + "learning_rate": 6.974431698607686e-05, + "loss": 1.8532, + "step": 6842 + }, + { + "epoch": 0.3814168663954072, + "grad_norm": 0.6075243353843689, + "learning_rate": 6.973613608417683e-05, + "loss": 1.8658, + "step": 6843 + }, + { + "epoch": 0.3814726046485703, + "grad_norm": 0.5244048833847046, + "learning_rate": 6.972795455636163e-05, + "loss": 1.5298, + "step": 6844 + }, + { + "epoch": 0.3815283429017335, + "grad_norm": 0.5625903010368347, + "learning_rate": 6.971977240289073e-05, + "loss": 1.7494, + "step": 6845 + }, + { + "epoch": 0.3815840811548966, + "grad_norm": 0.5776612758636475, + "learning_rate": 6.971158962402362e-05, + "loss": 1.9495, + "step": 6846 + }, + { + "epoch": 0.38163981940805974, + "grad_norm": 0.5811514258384705, + "learning_rate": 6.970340622001983e-05, + "loss": 1.6167, + "step": 6847 + }, + { + "epoch": 0.3816955576612229, + "grad_norm": 0.5879440307617188, + "learning_rate": 6.969522219113886e-05, + "loss": 1.7636, + "step": 6848 + }, + { + "epoch": 0.38175129591438606, + "grad_norm": 0.6386079788208008, + "learning_rate": 6.968703753764027e-05, + "loss": 1.779, + "step": 6849 + }, + { + "epoch": 0.3818070341675492, + "grad_norm": 0.5324746966362, + "learning_rate": 6.967885225978365e-05, + "loss": 1.5693, + "step": 6850 + }, + { + "epoch": 0.3818627724207123, + "grad_norm": 0.6155705451965332, + "learning_rate": 6.967066635782855e-05, + "loss": 1.8075, + "step": 6851 + }, + { + "epoch": 0.3819185106738755, + "grad_norm": 0.5880451202392578, + "learning_rate": 6.966247983203462e-05, + "loss": 1.8192, + "step": 6852 + }, + { + "epoch": 0.38197424892703863, + "grad_norm": 0.5279741287231445, + "learning_rate": 6.965429268266147e-05, + "loss": 1.5787, + "step": 6853 + }, + { + "epoch": 0.38202998718020176, + "grad_norm": 0.5816035270690918, + "learning_rate": 6.964610490996874e-05, + "loss": 1.7935, + "step": 6854 + }, + { + "epoch": 0.38208572543336494, + "grad_norm": 0.5708805918693542, + "learning_rate": 6.963791651421612e-05, + "loss": 1.6204, + "step": 6855 + }, + { + "epoch": 0.38214146368652807, + "grad_norm": 0.5362871885299683, + "learning_rate": 6.962972749566326e-05, + "loss": 1.6198, + "step": 6856 + }, + { + "epoch": 0.3821972019396912, + "grad_norm": 0.5008870363235474, + "learning_rate": 6.962153785456991e-05, + "loss": 1.3949, + "step": 6857 + }, + { + "epoch": 0.38225294019285433, + "grad_norm": 0.5772041082382202, + "learning_rate": 6.961334759119577e-05, + "loss": 1.7137, + "step": 6858 + }, + { + "epoch": 0.3823086784460175, + "grad_norm": 0.5443426966667175, + "learning_rate": 6.960515670580061e-05, + "loss": 1.809, + "step": 6859 + }, + { + "epoch": 0.38236441669918064, + "grad_norm": 0.6082087755203247, + "learning_rate": 6.959696519864418e-05, + "loss": 1.8777, + "step": 6860 + }, + { + "epoch": 0.38242015495234377, + "grad_norm": 0.5430213809013367, + "learning_rate": 6.958877306998627e-05, + "loss": 1.7168, + "step": 6861 + }, + { + "epoch": 0.38247589320550696, + "grad_norm": 0.5611394047737122, + "learning_rate": 6.95805803200867e-05, + "loss": 1.7136, + "step": 6862 + }, + { + "epoch": 0.3825316314586701, + "grad_norm": 0.5467121005058289, + "learning_rate": 6.957238694920527e-05, + "loss": 1.7348, + "step": 6863 + }, + { + "epoch": 0.3825873697118332, + "grad_norm": 0.5907519459724426, + "learning_rate": 6.956419295760184e-05, + "loss": 1.8087, + "step": 6864 + }, + { + "epoch": 0.3826431079649964, + "grad_norm": 0.4940342307090759, + "learning_rate": 6.95559983455363e-05, + "loss": 1.226, + "step": 6865 + }, + { + "epoch": 0.3826988462181595, + "grad_norm": 0.525205135345459, + "learning_rate": 6.954780311326849e-05, + "loss": 1.6166, + "step": 6866 + }, + { + "epoch": 0.38275458447132266, + "grad_norm": 0.5510271191596985, + "learning_rate": 6.953960726105835e-05, + "loss": 1.6143, + "step": 6867 + }, + { + "epoch": 0.38281032272448584, + "grad_norm": 0.5778586268424988, + "learning_rate": 6.953141078916578e-05, + "loss": 1.8417, + "step": 6868 + }, + { + "epoch": 0.38286606097764897, + "grad_norm": 0.5931724309921265, + "learning_rate": 6.952321369785075e-05, + "loss": 1.6908, + "step": 6869 + }, + { + "epoch": 0.3829217992308121, + "grad_norm": 0.5995519161224365, + "learning_rate": 6.951501598737318e-05, + "loss": 1.9328, + "step": 6870 + }, + { + "epoch": 0.38297753748397523, + "grad_norm": 0.5441159009933472, + "learning_rate": 6.95068176579931e-05, + "loss": 1.7226, + "step": 6871 + }, + { + "epoch": 0.3830332757371384, + "grad_norm": 0.5795645117759705, + "learning_rate": 6.94986187099705e-05, + "loss": 1.8162, + "step": 6872 + }, + { + "epoch": 0.38308901399030154, + "grad_norm": 0.5668213367462158, + "learning_rate": 6.949041914356541e-05, + "loss": 1.5981, + "step": 6873 + }, + { + "epoch": 0.38314475224346467, + "grad_norm": 0.6034721732139587, + "learning_rate": 6.948221895903784e-05, + "loss": 1.688, + "step": 6874 + }, + { + "epoch": 0.38320049049662785, + "grad_norm": 0.5386607050895691, + "learning_rate": 6.94740181566479e-05, + "loss": 1.6411, + "step": 6875 + }, + { + "epoch": 0.383256228749791, + "grad_norm": 0.5482555627822876, + "learning_rate": 6.946581673665561e-05, + "loss": 1.3411, + "step": 6876 + }, + { + "epoch": 0.3833119670029541, + "grad_norm": 0.5288286805152893, + "learning_rate": 6.945761469932114e-05, + "loss": 1.5896, + "step": 6877 + }, + { + "epoch": 0.3833677052561173, + "grad_norm": 0.5721820592880249, + "learning_rate": 6.944941204490456e-05, + "loss": 1.7555, + "step": 6878 + }, + { + "epoch": 0.3834234435092804, + "grad_norm": 0.5338029861450195, + "learning_rate": 6.944120877366604e-05, + "loss": 1.8117, + "step": 6879 + }, + { + "epoch": 0.38347918176244356, + "grad_norm": 0.5430106520652771, + "learning_rate": 6.943300488586572e-05, + "loss": 1.5363, + "step": 6880 + }, + { + "epoch": 0.3835349200156067, + "grad_norm": 0.5485236644744873, + "learning_rate": 6.942480038176379e-05, + "loss": 1.4549, + "step": 6881 + }, + { + "epoch": 0.38359065826876987, + "grad_norm": 0.5767553448677063, + "learning_rate": 6.941659526162045e-05, + "loss": 1.5041, + "step": 6882 + }, + { + "epoch": 0.383646396521933, + "grad_norm": 0.5788490176200867, + "learning_rate": 6.940838952569589e-05, + "loss": 1.8509, + "step": 6883 + }, + { + "epoch": 0.3837021347750961, + "grad_norm": 0.5562904477119446, + "learning_rate": 6.94001831742504e-05, + "loss": 1.6337, + "step": 6884 + }, + { + "epoch": 0.3837578730282593, + "grad_norm": 0.5514802932739258, + "learning_rate": 6.939197620754419e-05, + "loss": 1.6887, + "step": 6885 + }, + { + "epoch": 0.38381361128142244, + "grad_norm": 0.6278872489929199, + "learning_rate": 6.938376862583757e-05, + "loss": 1.6762, + "step": 6886 + }, + { + "epoch": 0.38386934953458557, + "grad_norm": 0.5348507761955261, + "learning_rate": 6.937556042939083e-05, + "loss": 1.5778, + "step": 6887 + }, + { + "epoch": 0.38392508778774875, + "grad_norm": 0.555674135684967, + "learning_rate": 6.936735161846429e-05, + "loss": 1.6806, + "step": 6888 + }, + { + "epoch": 0.3839808260409119, + "grad_norm": 0.5161069631576538, + "learning_rate": 6.935914219331825e-05, + "loss": 1.5607, + "step": 6889 + }, + { + "epoch": 0.384036564294075, + "grad_norm": 0.5375397205352783, + "learning_rate": 6.93509321542131e-05, + "loss": 1.6835, + "step": 6890 + }, + { + "epoch": 0.3840923025472382, + "grad_norm": 0.4695841073989868, + "learning_rate": 6.934272150140921e-05, + "loss": 1.3228, + "step": 6891 + }, + { + "epoch": 0.3841480408004013, + "grad_norm": 0.5479111075401306, + "learning_rate": 6.933451023516697e-05, + "loss": 1.6331, + "step": 6892 + }, + { + "epoch": 0.38420377905356445, + "grad_norm": 0.5705395936965942, + "learning_rate": 6.932629835574679e-05, + "loss": 1.7666, + "step": 6893 + }, + { + "epoch": 0.3842595173067276, + "grad_norm": 0.5568275451660156, + "learning_rate": 6.93180858634091e-05, + "loss": 1.5809, + "step": 6894 + }, + { + "epoch": 0.38431525555989077, + "grad_norm": 0.6088882088661194, + "learning_rate": 6.930987275841439e-05, + "loss": 1.7695, + "step": 6895 + }, + { + "epoch": 0.3843709938130539, + "grad_norm": 0.5949798822402954, + "learning_rate": 6.930165904102305e-05, + "loss": 1.8917, + "step": 6896 + }, + { + "epoch": 0.384426732066217, + "grad_norm": 0.557823657989502, + "learning_rate": 6.929344471149566e-05, + "loss": 1.8922, + "step": 6897 + }, + { + "epoch": 0.3844824703193802, + "grad_norm": 0.5406614542007446, + "learning_rate": 6.928522977009268e-05, + "loss": 1.6488, + "step": 6898 + }, + { + "epoch": 0.38453820857254334, + "grad_norm": 0.5692750811576843, + "learning_rate": 6.927701421707466e-05, + "loss": 1.6886, + "step": 6899 + }, + { + "epoch": 0.38459394682570647, + "grad_norm": 0.5827295780181885, + "learning_rate": 6.926879805270212e-05, + "loss": 1.6532, + "step": 6900 + }, + { + "epoch": 0.38464968507886965, + "grad_norm": 0.5955531001091003, + "learning_rate": 6.926058127723568e-05, + "loss": 1.6202, + "step": 6901 + }, + { + "epoch": 0.3847054233320328, + "grad_norm": 0.5544630885124207, + "learning_rate": 6.925236389093588e-05, + "loss": 1.1835, + "step": 6902 + }, + { + "epoch": 0.3847611615851959, + "grad_norm": 0.6354855298995972, + "learning_rate": 6.924414589406335e-05, + "loss": 1.9214, + "step": 6903 + }, + { + "epoch": 0.38481689983835904, + "grad_norm": 0.6088757514953613, + "learning_rate": 6.923592728687871e-05, + "loss": 1.8236, + "step": 6904 + }, + { + "epoch": 0.3848726380915222, + "grad_norm": 0.5689512491226196, + "learning_rate": 6.922770806964263e-05, + "loss": 1.5128, + "step": 6905 + }, + { + "epoch": 0.38492837634468535, + "grad_norm": 0.5286409854888916, + "learning_rate": 6.921948824261573e-05, + "loss": 1.5956, + "step": 6906 + }, + { + "epoch": 0.3849841145978485, + "grad_norm": 0.5316895842552185, + "learning_rate": 6.921126780605873e-05, + "loss": 1.5846, + "step": 6907 + }, + { + "epoch": 0.38503985285101167, + "grad_norm": 0.5461425185203552, + "learning_rate": 6.920304676023233e-05, + "loss": 1.6645, + "step": 6908 + }, + { + "epoch": 0.3850955911041748, + "grad_norm": 0.5628203749656677, + "learning_rate": 6.919482510539723e-05, + "loss": 1.6028, + "step": 6909 + }, + { + "epoch": 0.3851513293573379, + "grad_norm": 0.5715482234954834, + "learning_rate": 6.918660284181421e-05, + "loss": 1.7378, + "step": 6910 + }, + { + "epoch": 0.3852070676105011, + "grad_norm": 0.6020052433013916, + "learning_rate": 6.9178379969744e-05, + "loss": 1.8591, + "step": 6911 + }, + { + "epoch": 0.38526280586366424, + "grad_norm": 0.5738694071769714, + "learning_rate": 6.917015648944741e-05, + "loss": 1.527, + "step": 6912 + }, + { + "epoch": 0.38531854411682737, + "grad_norm": 0.5757240653038025, + "learning_rate": 6.916193240118522e-05, + "loss": 1.6982, + "step": 6913 + }, + { + "epoch": 0.38537428236999055, + "grad_norm": 0.5647144913673401, + "learning_rate": 6.915370770521825e-05, + "loss": 1.6709, + "step": 6914 + }, + { + "epoch": 0.3854300206231537, + "grad_norm": 0.5539698004722595, + "learning_rate": 6.914548240180736e-05, + "loss": 1.8178, + "step": 6915 + }, + { + "epoch": 0.3854857588763168, + "grad_norm": 0.5621739625930786, + "learning_rate": 6.913725649121337e-05, + "loss": 1.8038, + "step": 6916 + }, + { + "epoch": 0.38554149712947994, + "grad_norm": 0.5707613229751587, + "learning_rate": 6.91290299736972e-05, + "loss": 1.7155, + "step": 6917 + }, + { + "epoch": 0.3855972353826431, + "grad_norm": 0.5707844495773315, + "learning_rate": 6.912080284951972e-05, + "loss": 1.7316, + "step": 6918 + }, + { + "epoch": 0.38565297363580625, + "grad_norm": 0.5531010627746582, + "learning_rate": 6.911257511894188e-05, + "loss": 1.7607, + "step": 6919 + }, + { + "epoch": 0.3857087118889694, + "grad_norm": 0.6005899906158447, + "learning_rate": 6.910434678222457e-05, + "loss": 1.8731, + "step": 6920 + }, + { + "epoch": 0.38576445014213256, + "grad_norm": 0.5527727603912354, + "learning_rate": 6.909611783962877e-05, + "loss": 1.3704, + "step": 6921 + }, + { + "epoch": 0.3858201883952957, + "grad_norm": 0.5586572885513306, + "learning_rate": 6.908788829141544e-05, + "loss": 1.6253, + "step": 6922 + }, + { + "epoch": 0.3858759266484588, + "grad_norm": 0.6035952568054199, + "learning_rate": 6.907965813784558e-05, + "loss": 1.9226, + "step": 6923 + }, + { + "epoch": 0.385931664901622, + "grad_norm": 0.5370834469795227, + "learning_rate": 6.907142737918023e-05, + "loss": 1.5934, + "step": 6924 + }, + { + "epoch": 0.38598740315478514, + "grad_norm": 0.5954363346099854, + "learning_rate": 6.906319601568038e-05, + "loss": 1.8197, + "step": 6925 + }, + { + "epoch": 0.38604314140794826, + "grad_norm": 0.5880860686302185, + "learning_rate": 6.90549640476071e-05, + "loss": 1.9775, + "step": 6926 + }, + { + "epoch": 0.3860988796611114, + "grad_norm": 0.6047815084457397, + "learning_rate": 6.904673147522147e-05, + "loss": 1.9008, + "step": 6927 + }, + { + "epoch": 0.3861546179142746, + "grad_norm": 0.6101181507110596, + "learning_rate": 6.903849829878457e-05, + "loss": 1.9632, + "step": 6928 + }, + { + "epoch": 0.3862103561674377, + "grad_norm": 0.5670501589775085, + "learning_rate": 6.903026451855748e-05, + "loss": 1.7489, + "step": 6929 + }, + { + "epoch": 0.38626609442060084, + "grad_norm": 0.6123764514923096, + "learning_rate": 6.902203013480137e-05, + "loss": 1.7719, + "step": 6930 + }, + { + "epoch": 0.386321832673764, + "grad_norm": 0.53583824634552, + "learning_rate": 6.901379514777739e-05, + "loss": 1.5504, + "step": 6931 + }, + { + "epoch": 0.38637757092692715, + "grad_norm": 0.5257768630981445, + "learning_rate": 6.900555955774666e-05, + "loss": 1.6045, + "step": 6932 + }, + { + "epoch": 0.3864333091800903, + "grad_norm": 0.5276762843132019, + "learning_rate": 6.899732336497038e-05, + "loss": 1.7366, + "step": 6933 + }, + { + "epoch": 0.38648904743325346, + "grad_norm": 0.555980384349823, + "learning_rate": 6.898908656970979e-05, + "loss": 1.3954, + "step": 6934 + }, + { + "epoch": 0.3865447856864166, + "grad_norm": 0.5937703847885132, + "learning_rate": 6.898084917222609e-05, + "loss": 1.791, + "step": 6935 + }, + { + "epoch": 0.3866005239395797, + "grad_norm": 0.5324926376342773, + "learning_rate": 6.89726111727805e-05, + "loss": 1.7835, + "step": 6936 + }, + { + "epoch": 0.3866562621927429, + "grad_norm": 0.569644033908844, + "learning_rate": 6.896437257163432e-05, + "loss": 1.651, + "step": 6937 + }, + { + "epoch": 0.38671200044590603, + "grad_norm": 0.5893319249153137, + "learning_rate": 6.89561333690488e-05, + "loss": 1.8836, + "step": 6938 + }, + { + "epoch": 0.38676773869906916, + "grad_norm": 0.5247541666030884, + "learning_rate": 6.894789356528526e-05, + "loss": 1.5643, + "step": 6939 + }, + { + "epoch": 0.3868234769522323, + "grad_norm": 0.5343844890594482, + "learning_rate": 6.893965316060501e-05, + "loss": 1.6483, + "step": 6940 + }, + { + "epoch": 0.3868792152053955, + "grad_norm": 0.5714672803878784, + "learning_rate": 6.893141215526938e-05, + "loss": 1.5949, + "step": 6941 + }, + { + "epoch": 0.3869349534585586, + "grad_norm": 0.5850149989128113, + "learning_rate": 6.892317054953975e-05, + "loss": 1.7971, + "step": 6942 + }, + { + "epoch": 0.38699069171172173, + "grad_norm": 0.570669412612915, + "learning_rate": 6.891492834367746e-05, + "loss": 1.8339, + "step": 6943 + }, + { + "epoch": 0.3870464299648849, + "grad_norm": 0.5296490788459778, + "learning_rate": 6.890668553794392e-05, + "loss": 1.6175, + "step": 6944 + }, + { + "epoch": 0.38710216821804805, + "grad_norm": 0.5491392612457275, + "learning_rate": 6.889844213260057e-05, + "loss": 1.7679, + "step": 6945 + }, + { + "epoch": 0.3871579064712112, + "grad_norm": 0.5886465907096863, + "learning_rate": 6.88901981279088e-05, + "loss": 1.5769, + "step": 6946 + }, + { + "epoch": 0.38721364472437436, + "grad_norm": 0.5220004916191101, + "learning_rate": 6.88819535241301e-05, + "loss": 1.4678, + "step": 6947 + }, + { + "epoch": 0.3872693829775375, + "grad_norm": 0.5555586814880371, + "learning_rate": 6.887370832152592e-05, + "loss": 1.6784, + "step": 6948 + }, + { + "epoch": 0.3873251212307006, + "grad_norm": 0.5332651138305664, + "learning_rate": 6.886546252035775e-05, + "loss": 1.6139, + "step": 6949 + }, + { + "epoch": 0.38738085948386375, + "grad_norm": 0.5473794341087341, + "learning_rate": 6.88572161208871e-05, + "loss": 1.8137, + "step": 6950 + }, + { + "epoch": 0.38743659773702693, + "grad_norm": 0.5803813934326172, + "learning_rate": 6.88489691233755e-05, + "loss": 1.5237, + "step": 6951 + }, + { + "epoch": 0.38749233599019006, + "grad_norm": 0.5329601168632507, + "learning_rate": 6.884072152808451e-05, + "loss": 1.686, + "step": 6952 + }, + { + "epoch": 0.3875480742433532, + "grad_norm": 0.5633809566497803, + "learning_rate": 6.883247333527567e-05, + "loss": 1.9771, + "step": 6953 + }, + { + "epoch": 0.3876038124965164, + "grad_norm": 0.6174986958503723, + "learning_rate": 6.882422454521058e-05, + "loss": 1.7549, + "step": 6954 + }, + { + "epoch": 0.3876595507496795, + "grad_norm": 0.5496551394462585, + "learning_rate": 6.881597515815084e-05, + "loss": 1.7045, + "step": 6955 + }, + { + "epoch": 0.38771528900284263, + "grad_norm": 0.5577127933502197, + "learning_rate": 6.880772517435807e-05, + "loss": 1.5901, + "step": 6956 + }, + { + "epoch": 0.3877710272560058, + "grad_norm": 0.5230315327644348, + "learning_rate": 6.879947459409393e-05, + "loss": 1.5849, + "step": 6957 + }, + { + "epoch": 0.38782676550916895, + "grad_norm": 0.5241686105728149, + "learning_rate": 6.879122341762003e-05, + "loss": 1.8152, + "step": 6958 + }, + { + "epoch": 0.3878825037623321, + "grad_norm": 0.5810775756835938, + "learning_rate": 6.878297164519812e-05, + "loss": 1.7573, + "step": 6959 + }, + { + "epoch": 0.38793824201549526, + "grad_norm": 0.5543670058250427, + "learning_rate": 6.877471927708985e-05, + "loss": 1.7487, + "step": 6960 + }, + { + "epoch": 0.3879939802686584, + "grad_norm": 0.5780448317527771, + "learning_rate": 6.876646631355693e-05, + "loss": 1.8512, + "step": 6961 + }, + { + "epoch": 0.3880497185218215, + "grad_norm": 0.6595468521118164, + "learning_rate": 6.875821275486113e-05, + "loss": 2.1185, + "step": 6962 + }, + { + "epoch": 0.38810545677498465, + "grad_norm": 0.5663919448852539, + "learning_rate": 6.874995860126419e-05, + "loss": 1.6607, + "step": 6963 + }, + { + "epoch": 0.38816119502814783, + "grad_norm": 0.6084817051887512, + "learning_rate": 6.874170385302789e-05, + "loss": 1.4841, + "step": 6964 + }, + { + "epoch": 0.38821693328131096, + "grad_norm": 0.5507417321205139, + "learning_rate": 6.8733448510414e-05, + "loss": 1.7557, + "step": 6965 + }, + { + "epoch": 0.3882726715344741, + "grad_norm": 0.5766531825065613, + "learning_rate": 6.872519257368437e-05, + "loss": 1.7722, + "step": 6966 + }, + { + "epoch": 0.3883284097876373, + "grad_norm": 0.5653195381164551, + "learning_rate": 6.871693604310077e-05, + "loss": 1.8058, + "step": 6967 + }, + { + "epoch": 0.3883841480408004, + "grad_norm": 0.6037474274635315, + "learning_rate": 6.87086789189251e-05, + "loss": 1.8542, + "step": 6968 + }, + { + "epoch": 0.38843988629396353, + "grad_norm": 0.5463787317276001, + "learning_rate": 6.870042120141923e-05, + "loss": 1.7221, + "step": 6969 + }, + { + "epoch": 0.3884956245471267, + "grad_norm": 0.5135644674301147, + "learning_rate": 6.869216289084503e-05, + "loss": 1.5492, + "step": 6970 + }, + { + "epoch": 0.38855136280028985, + "grad_norm": 0.5640287399291992, + "learning_rate": 6.86839039874644e-05, + "loss": 1.4507, + "step": 6971 + }, + { + "epoch": 0.388607101053453, + "grad_norm": 0.5661764144897461, + "learning_rate": 6.867564449153925e-05, + "loss": 1.7683, + "step": 6972 + }, + { + "epoch": 0.3886628393066161, + "grad_norm": 0.5671542882919312, + "learning_rate": 6.866738440333157e-05, + "loss": 1.7076, + "step": 6973 + }, + { + "epoch": 0.3887185775597793, + "grad_norm": 0.5259964466094971, + "learning_rate": 6.865912372310328e-05, + "loss": 1.542, + "step": 6974 + }, + { + "epoch": 0.3887743158129424, + "grad_norm": 0.5321882963180542, + "learning_rate": 6.865086245111638e-05, + "loss": 1.6909, + "step": 6975 + }, + { + "epoch": 0.38883005406610555, + "grad_norm": 0.5812041759490967, + "learning_rate": 6.864260058763286e-05, + "loss": 1.8409, + "step": 6976 + }, + { + "epoch": 0.38888579231926873, + "grad_norm": 0.5516645312309265, + "learning_rate": 6.863433813291477e-05, + "loss": 1.5931, + "step": 6977 + }, + { + "epoch": 0.38894153057243186, + "grad_norm": 0.612776517868042, + "learning_rate": 6.86260750872241e-05, + "loss": 1.7741, + "step": 6978 + }, + { + "epoch": 0.388997268825595, + "grad_norm": 0.5400133728981018, + "learning_rate": 6.861781145082293e-05, + "loss": 1.6731, + "step": 6979 + }, + { + "epoch": 0.3890530070787582, + "grad_norm": 0.5253887176513672, + "learning_rate": 6.860954722397332e-05, + "loss": 1.6809, + "step": 6980 + }, + { + "epoch": 0.3891087453319213, + "grad_norm": 0.5338975191116333, + "learning_rate": 6.860128240693737e-05, + "loss": 1.7078, + "step": 6981 + }, + { + "epoch": 0.38916448358508443, + "grad_norm": 0.6083932518959045, + "learning_rate": 6.85930169999772e-05, + "loss": 1.7694, + "step": 6982 + }, + { + "epoch": 0.3892202218382476, + "grad_norm": 0.5741243958473206, + "learning_rate": 6.858475100335496e-05, + "loss": 1.7516, + "step": 6983 + }, + { + "epoch": 0.38927596009141074, + "grad_norm": 0.5835102200508118, + "learning_rate": 6.857648441733275e-05, + "loss": 1.7409, + "step": 6984 + }, + { + "epoch": 0.3893316983445739, + "grad_norm": 0.5485714673995972, + "learning_rate": 6.856821724217276e-05, + "loss": 1.7237, + "step": 6985 + }, + { + "epoch": 0.389387436597737, + "grad_norm": 0.5908092856407166, + "learning_rate": 6.855994947813719e-05, + "loss": 1.8842, + "step": 6986 + }, + { + "epoch": 0.3894431748509002, + "grad_norm": 0.5635112524032593, + "learning_rate": 6.855168112548823e-05, + "loss": 1.8356, + "step": 6987 + }, + { + "epoch": 0.3894989131040633, + "grad_norm": 0.6175239086151123, + "learning_rate": 6.85434121844881e-05, + "loss": 2.1173, + "step": 6988 + }, + { + "epoch": 0.38955465135722644, + "grad_norm": 0.5377556085586548, + "learning_rate": 6.853514265539907e-05, + "loss": 1.6531, + "step": 6989 + }, + { + "epoch": 0.38961038961038963, + "grad_norm": 0.5529573559761047, + "learning_rate": 6.852687253848337e-05, + "loss": 1.7125, + "step": 6990 + }, + { + "epoch": 0.38966612786355276, + "grad_norm": 0.5733687877655029, + "learning_rate": 6.85186018340033e-05, + "loss": 1.8723, + "step": 6991 + }, + { + "epoch": 0.3897218661167159, + "grad_norm": 0.5605233311653137, + "learning_rate": 6.851033054222115e-05, + "loss": 1.9066, + "step": 6992 + }, + { + "epoch": 0.38977760436987907, + "grad_norm": 0.5196309089660645, + "learning_rate": 6.850205866339923e-05, + "loss": 1.6027, + "step": 6993 + }, + { + "epoch": 0.3898333426230422, + "grad_norm": 0.5691904425621033, + "learning_rate": 6.849378619779989e-05, + "loss": 1.7806, + "step": 6994 + }, + { + "epoch": 0.38988908087620533, + "grad_norm": 0.5791077017784119, + "learning_rate": 6.848551314568548e-05, + "loss": 1.8153, + "step": 6995 + }, + { + "epoch": 0.38994481912936846, + "grad_norm": 0.5611302256584167, + "learning_rate": 6.847723950731837e-05, + "loss": 1.7705, + "step": 6996 + }, + { + "epoch": 0.39000055738253164, + "grad_norm": 0.6004642248153687, + "learning_rate": 6.846896528296094e-05, + "loss": 1.6717, + "step": 6997 + }, + { + "epoch": 0.39005629563569477, + "grad_norm": 0.5229793787002563, + "learning_rate": 6.846069047287562e-05, + "loss": 1.6567, + "step": 6998 + }, + { + "epoch": 0.3901120338888579, + "grad_norm": 0.5206711888313293, + "learning_rate": 6.845241507732483e-05, + "loss": 1.3903, + "step": 6999 + }, + { + "epoch": 0.3901677721420211, + "grad_norm": 0.6022440791130066, + "learning_rate": 6.844413909657104e-05, + "loss": 1.8607, + "step": 7000 + }, + { + "epoch": 0.3902235103951842, + "grad_norm": 0.5634634494781494, + "learning_rate": 6.843586253087666e-05, + "loss": 1.6199, + "step": 7001 + }, + { + "epoch": 0.39027924864834734, + "grad_norm": 0.5622709393501282, + "learning_rate": 6.842758538050422e-05, + "loss": 1.5923, + "step": 7002 + }, + { + "epoch": 0.39033498690151053, + "grad_norm": 0.5336858034133911, + "learning_rate": 6.841930764571623e-05, + "loss": 1.6086, + "step": 7003 + }, + { + "epoch": 0.39039072515467366, + "grad_norm": 0.6216438412666321, + "learning_rate": 6.841102932677517e-05, + "loss": 1.8973, + "step": 7004 + }, + { + "epoch": 0.3904464634078368, + "grad_norm": 0.5596641898155212, + "learning_rate": 6.840275042394363e-05, + "loss": 1.4897, + "step": 7005 + }, + { + "epoch": 0.39050220166099997, + "grad_norm": 0.5638755559921265, + "learning_rate": 6.839447093748413e-05, + "loss": 1.7267, + "step": 7006 + }, + { + "epoch": 0.3905579399141631, + "grad_norm": 0.5759851932525635, + "learning_rate": 6.838619086765925e-05, + "loss": 1.9025, + "step": 7007 + }, + { + "epoch": 0.39061367816732623, + "grad_norm": 0.5657535791397095, + "learning_rate": 6.83779102147316e-05, + "loss": 1.6509, + "step": 7008 + }, + { + "epoch": 0.39066941642048936, + "grad_norm": 0.5276607275009155, + "learning_rate": 6.83696289789638e-05, + "loss": 1.6244, + "step": 7009 + }, + { + "epoch": 0.39072515467365254, + "grad_norm": 0.6091243624687195, + "learning_rate": 6.836134716061845e-05, + "loss": 1.7403, + "step": 7010 + }, + { + "epoch": 0.39078089292681567, + "grad_norm": 0.5518734455108643, + "learning_rate": 6.835306475995823e-05, + "loss": 1.6201, + "step": 7011 + }, + { + "epoch": 0.3908366311799788, + "grad_norm": 0.5169443488121033, + "learning_rate": 6.834478177724581e-05, + "loss": 1.5593, + "step": 7012 + }, + { + "epoch": 0.390892369433142, + "grad_norm": 0.5405734181404114, + "learning_rate": 6.833649821274386e-05, + "loss": 1.6275, + "step": 7013 + }, + { + "epoch": 0.3909481076863051, + "grad_norm": 0.639498233795166, + "learning_rate": 6.83282140667151e-05, + "loss": 1.9288, + "step": 7014 + }, + { + "epoch": 0.39100384593946824, + "grad_norm": 0.5509902238845825, + "learning_rate": 6.831992933942225e-05, + "loss": 1.6756, + "step": 7015 + }, + { + "epoch": 0.3910595841926314, + "grad_norm": 0.6026686429977417, + "learning_rate": 6.831164403112806e-05, + "loss": 1.8422, + "step": 7016 + }, + { + "epoch": 0.39111532244579456, + "grad_norm": 0.4942910969257355, + "learning_rate": 6.830335814209527e-05, + "loss": 1.407, + "step": 7017 + }, + { + "epoch": 0.3911710606989577, + "grad_norm": 0.5921064615249634, + "learning_rate": 6.829507167258671e-05, + "loss": 1.7507, + "step": 7018 + }, + { + "epoch": 0.3912267989521208, + "grad_norm": 0.5901893377304077, + "learning_rate": 6.828678462286511e-05, + "loss": 1.9612, + "step": 7019 + }, + { + "epoch": 0.391282537205284, + "grad_norm": 0.5834552049636841, + "learning_rate": 6.827849699319333e-05, + "loss": 1.8656, + "step": 7020 + }, + { + "epoch": 0.3913382754584471, + "grad_norm": 0.5791158080101013, + "learning_rate": 6.827020878383418e-05, + "loss": 1.6849, + "step": 7021 + }, + { + "epoch": 0.39139401371161026, + "grad_norm": 0.6698895692825317, + "learning_rate": 6.826191999505056e-05, + "loss": 1.9619, + "step": 7022 + }, + { + "epoch": 0.39144975196477344, + "grad_norm": 0.5854638814926147, + "learning_rate": 6.82536306271053e-05, + "loss": 1.6066, + "step": 7023 + }, + { + "epoch": 0.39150549021793657, + "grad_norm": 0.5511733293533325, + "learning_rate": 6.82453406802613e-05, + "loss": 1.8761, + "step": 7024 + }, + { + "epoch": 0.3915612284710997, + "grad_norm": 0.5574920177459717, + "learning_rate": 6.823705015478148e-05, + "loss": 1.494, + "step": 7025 + }, + { + "epoch": 0.3916169667242629, + "grad_norm": 0.5293987989425659, + "learning_rate": 6.822875905092876e-05, + "loss": 1.4918, + "step": 7026 + }, + { + "epoch": 0.391672704977426, + "grad_norm": 0.5626353621482849, + "learning_rate": 6.822046736896607e-05, + "loss": 1.7521, + "step": 7027 + }, + { + "epoch": 0.39172844323058914, + "grad_norm": 0.5664160847663879, + "learning_rate": 6.821217510915639e-05, + "loss": 1.5782, + "step": 7028 + }, + { + "epoch": 0.3917841814837523, + "grad_norm": 0.5288576483726501, + "learning_rate": 6.820388227176271e-05, + "loss": 1.4754, + "step": 7029 + }, + { + "epoch": 0.39183991973691545, + "grad_norm": 0.5488860607147217, + "learning_rate": 6.819558885704801e-05, + "loss": 1.6245, + "step": 7030 + }, + { + "epoch": 0.3918956579900786, + "grad_norm": 0.5747123956680298, + "learning_rate": 6.818729486527533e-05, + "loss": 1.7134, + "step": 7031 + }, + { + "epoch": 0.3919513962432417, + "grad_norm": 0.5334782600402832, + "learning_rate": 6.817900029670769e-05, + "loss": 1.6473, + "step": 7032 + }, + { + "epoch": 0.3920071344964049, + "grad_norm": 0.5332539081573486, + "learning_rate": 6.817070515160815e-05, + "loss": 1.4961, + "step": 7033 + }, + { + "epoch": 0.392062872749568, + "grad_norm": 0.5700680017471313, + "learning_rate": 6.816240943023977e-05, + "loss": 1.8336, + "step": 7034 + }, + { + "epoch": 0.39211861100273115, + "grad_norm": 0.5893431901931763, + "learning_rate": 6.815411313286568e-05, + "loss": 1.8517, + "step": 7035 + }, + { + "epoch": 0.39217434925589434, + "grad_norm": 0.5954105854034424, + "learning_rate": 6.814581625974897e-05, + "loss": 1.8405, + "step": 7036 + }, + { + "epoch": 0.39223008750905747, + "grad_norm": 0.5694375038146973, + "learning_rate": 6.813751881115275e-05, + "loss": 1.7636, + "step": 7037 + }, + { + "epoch": 0.3922858257622206, + "grad_norm": 0.6035060286521912, + "learning_rate": 6.812922078734019e-05, + "loss": 1.8142, + "step": 7038 + }, + { + "epoch": 0.3923415640153838, + "grad_norm": 0.6111207008361816, + "learning_rate": 6.812092218857444e-05, + "loss": 1.7048, + "step": 7039 + }, + { + "epoch": 0.3923973022685469, + "grad_norm": 0.5596774220466614, + "learning_rate": 6.811262301511869e-05, + "loss": 1.652, + "step": 7040 + }, + { + "epoch": 0.39245304052171004, + "grad_norm": 0.5244095921516418, + "learning_rate": 6.810432326723615e-05, + "loss": 1.325, + "step": 7041 + }, + { + "epoch": 0.39250877877487317, + "grad_norm": 0.5797486305236816, + "learning_rate": 6.809602294519004e-05, + "loss": 1.7832, + "step": 7042 + }, + { + "epoch": 0.39256451702803635, + "grad_norm": 0.5226321816444397, + "learning_rate": 6.808772204924357e-05, + "loss": 1.6449, + "step": 7043 + }, + { + "epoch": 0.3926202552811995, + "grad_norm": 0.5220246911048889, + "learning_rate": 6.807942057966003e-05, + "loss": 1.6308, + "step": 7044 + }, + { + "epoch": 0.3926759935343626, + "grad_norm": 0.7185441255569458, + "learning_rate": 6.807111853670268e-05, + "loss": 1.6675, + "step": 7045 + }, + { + "epoch": 0.3927317317875258, + "grad_norm": 0.6072642803192139, + "learning_rate": 6.806281592063481e-05, + "loss": 1.8951, + "step": 7046 + }, + { + "epoch": 0.3927874700406889, + "grad_norm": 0.5583004355430603, + "learning_rate": 6.805451273171972e-05, + "loss": 1.686, + "step": 7047 + }, + { + "epoch": 0.39284320829385205, + "grad_norm": 0.5066385865211487, + "learning_rate": 6.804620897022076e-05, + "loss": 1.407, + "step": 7048 + }, + { + "epoch": 0.39289894654701524, + "grad_norm": 0.5519012212753296, + "learning_rate": 6.803790463640127e-05, + "loss": 1.8137, + "step": 7049 + }, + { + "epoch": 0.39295468480017837, + "grad_norm": 0.5573792457580566, + "learning_rate": 6.802959973052461e-05, + "loss": 1.7861, + "step": 7050 + }, + { + "epoch": 0.3930104230533415, + "grad_norm": 0.5672924518585205, + "learning_rate": 6.802129425285417e-05, + "loss": 1.6572, + "step": 7051 + }, + { + "epoch": 0.3930661613065047, + "grad_norm": 0.5737549066543579, + "learning_rate": 6.801298820365333e-05, + "loss": 1.7467, + "step": 7052 + }, + { + "epoch": 0.3931218995596678, + "grad_norm": 0.5474954843521118, + "learning_rate": 6.800468158318554e-05, + "loss": 1.7429, + "step": 7053 + }, + { + "epoch": 0.39317763781283094, + "grad_norm": 0.549497127532959, + "learning_rate": 6.799637439171424e-05, + "loss": 1.764, + "step": 7054 + }, + { + "epoch": 0.39323337606599407, + "grad_norm": 0.5415019392967224, + "learning_rate": 6.798806662950286e-05, + "loss": 1.4691, + "step": 7055 + }, + { + "epoch": 0.39328911431915725, + "grad_norm": 0.5431099534034729, + "learning_rate": 6.797975829681487e-05, + "loss": 1.5577, + "step": 7056 + }, + { + "epoch": 0.3933448525723204, + "grad_norm": 0.549314558506012, + "learning_rate": 6.79714493939138e-05, + "loss": 1.7471, + "step": 7057 + }, + { + "epoch": 0.3934005908254835, + "grad_norm": 0.5444470047950745, + "learning_rate": 6.796313992106313e-05, + "loss": 1.765, + "step": 7058 + }, + { + "epoch": 0.3934563290786467, + "grad_norm": 0.57083660364151, + "learning_rate": 6.795482987852638e-05, + "loss": 1.9101, + "step": 7059 + }, + { + "epoch": 0.3935120673318098, + "grad_norm": 0.5475842952728271, + "learning_rate": 6.794651926656711e-05, + "loss": 1.8193, + "step": 7060 + }, + { + "epoch": 0.39356780558497295, + "grad_norm": 0.5259652733802795, + "learning_rate": 6.793820808544891e-05, + "loss": 1.3794, + "step": 7061 + }, + { + "epoch": 0.39362354383813614, + "grad_norm": 0.5105850100517273, + "learning_rate": 6.792989633543531e-05, + "loss": 1.5634, + "step": 7062 + }, + { + "epoch": 0.39367928209129927, + "grad_norm": 0.5771433711051941, + "learning_rate": 6.792158401678994e-05, + "loss": 1.6858, + "step": 7063 + }, + { + "epoch": 0.3937350203444624, + "grad_norm": 0.5675138235092163, + "learning_rate": 6.791327112977644e-05, + "loss": 1.8272, + "step": 7064 + }, + { + "epoch": 0.3937907585976255, + "grad_norm": 0.5633112788200378, + "learning_rate": 6.790495767465839e-05, + "loss": 1.7226, + "step": 7065 + }, + { + "epoch": 0.3938464968507887, + "grad_norm": 0.5350648760795593, + "learning_rate": 6.789664365169947e-05, + "loss": 1.5082, + "step": 7066 + }, + { + "epoch": 0.39390223510395184, + "grad_norm": 0.5656428337097168, + "learning_rate": 6.788832906116338e-05, + "loss": 1.4914, + "step": 7067 + }, + { + "epoch": 0.39395797335711497, + "grad_norm": 0.5312878489494324, + "learning_rate": 6.78800139033138e-05, + "loss": 1.5864, + "step": 7068 + }, + { + "epoch": 0.39401371161027815, + "grad_norm": 0.6321331262588501, + "learning_rate": 6.787169817841442e-05, + "loss": 1.9452, + "step": 7069 + }, + { + "epoch": 0.3940694498634413, + "grad_norm": 0.5593883991241455, + "learning_rate": 6.786338188672896e-05, + "loss": 1.7637, + "step": 7070 + }, + { + "epoch": 0.3941251881166044, + "grad_norm": 0.5405465960502625, + "learning_rate": 6.785506502852118e-05, + "loss": 1.6875, + "step": 7071 + }, + { + "epoch": 0.3941809263697676, + "grad_norm": 0.5527162551879883, + "learning_rate": 6.784674760405482e-05, + "loss": 1.6496, + "step": 7072 + }, + { + "epoch": 0.3942366646229307, + "grad_norm": 0.5357568264007568, + "learning_rate": 6.78384296135937e-05, + "loss": 1.7234, + "step": 7073 + }, + { + "epoch": 0.39429240287609385, + "grad_norm": 0.5588380694389343, + "learning_rate": 6.783011105740162e-05, + "loss": 1.9166, + "step": 7074 + }, + { + "epoch": 0.39434814112925703, + "grad_norm": 0.7392244338989258, + "learning_rate": 6.782179193574234e-05, + "loss": 1.6746, + "step": 7075 + }, + { + "epoch": 0.39440387938242016, + "grad_norm": 0.5365987420082092, + "learning_rate": 6.781347224887974e-05, + "loss": 1.6615, + "step": 7076 + }, + { + "epoch": 0.3944596176355833, + "grad_norm": 0.5493837594985962, + "learning_rate": 6.780515199707766e-05, + "loss": 1.7271, + "step": 7077 + }, + { + "epoch": 0.3945153558887464, + "grad_norm": 0.5309239029884338, + "learning_rate": 6.779683118059997e-05, + "loss": 1.5172, + "step": 7078 + }, + { + "epoch": 0.3945710941419096, + "grad_norm": 0.5167561769485474, + "learning_rate": 6.778850979971057e-05, + "loss": 1.5777, + "step": 7079 + }, + { + "epoch": 0.39462683239507274, + "grad_norm": 0.5119823217391968, + "learning_rate": 6.778018785467332e-05, + "loss": 1.5685, + "step": 7080 + }, + { + "epoch": 0.39468257064823586, + "grad_norm": 0.5578561425209045, + "learning_rate": 6.777186534575222e-05, + "loss": 1.6626, + "step": 7081 + }, + { + "epoch": 0.39473830890139905, + "grad_norm": 0.535065233707428, + "learning_rate": 6.776354227321114e-05, + "loss": 1.5554, + "step": 7082 + }, + { + "epoch": 0.3947940471545622, + "grad_norm": 0.5996119976043701, + "learning_rate": 6.775521863731408e-05, + "loss": 1.613, + "step": 7083 + }, + { + "epoch": 0.3948497854077253, + "grad_norm": 0.5490982532501221, + "learning_rate": 6.7746894438325e-05, + "loss": 1.6554, + "step": 7084 + }, + { + "epoch": 0.3949055236608885, + "grad_norm": 0.5607420802116394, + "learning_rate": 6.773856967650789e-05, + "loss": 1.7542, + "step": 7085 + }, + { + "epoch": 0.3949612619140516, + "grad_norm": 0.594559907913208, + "learning_rate": 6.773024435212678e-05, + "loss": 1.8008, + "step": 7086 + }, + { + "epoch": 0.39501700016721475, + "grad_norm": 0.5436771512031555, + "learning_rate": 6.77219184654457e-05, + "loss": 1.6853, + "step": 7087 + }, + { + "epoch": 0.3950727384203779, + "grad_norm": 0.6430955529212952, + "learning_rate": 6.771359201672868e-05, + "loss": 1.877, + "step": 7088 + }, + { + "epoch": 0.39512847667354106, + "grad_norm": 0.5667055249214172, + "learning_rate": 6.770526500623982e-05, + "loss": 1.5347, + "step": 7089 + }, + { + "epoch": 0.3951842149267042, + "grad_norm": 0.5299628376960754, + "learning_rate": 6.769693743424317e-05, + "loss": 1.6611, + "step": 7090 + }, + { + "epoch": 0.3952399531798673, + "grad_norm": 0.6088326573371887, + "learning_rate": 6.768860930100285e-05, + "loss": 1.991, + "step": 7091 + }, + { + "epoch": 0.3952956914330305, + "grad_norm": 0.5899388790130615, + "learning_rate": 6.768028060678296e-05, + "loss": 1.8402, + "step": 7092 + }, + { + "epoch": 0.39535142968619363, + "grad_norm": 0.5693525075912476, + "learning_rate": 6.767195135184765e-05, + "loss": 1.6969, + "step": 7093 + }, + { + "epoch": 0.39540716793935676, + "grad_norm": 0.5347588658332825, + "learning_rate": 6.766362153646111e-05, + "loss": 1.6525, + "step": 7094 + }, + { + "epoch": 0.39546290619251995, + "grad_norm": 0.5795377492904663, + "learning_rate": 6.765529116088745e-05, + "loss": 1.7744, + "step": 7095 + }, + { + "epoch": 0.3955186444456831, + "grad_norm": 0.5230005979537964, + "learning_rate": 6.764696022539091e-05, + "loss": 1.6068, + "step": 7096 + }, + { + "epoch": 0.3955743826988462, + "grad_norm": 0.5676483511924744, + "learning_rate": 6.763862873023567e-05, + "loss": 1.6501, + "step": 7097 + }, + { + "epoch": 0.3956301209520094, + "grad_norm": 0.5104279518127441, + "learning_rate": 6.763029667568597e-05, + "loss": 1.5805, + "step": 7098 + }, + { + "epoch": 0.3956858592051725, + "grad_norm": 0.575018048286438, + "learning_rate": 6.762196406200604e-05, + "loss": 1.7185, + "step": 7099 + }, + { + "epoch": 0.39574159745833565, + "grad_norm": 0.5459030270576477, + "learning_rate": 6.761363088946017e-05, + "loss": 1.7264, + "step": 7100 + }, + { + "epoch": 0.3957973357114988, + "grad_norm": 0.5303768515586853, + "learning_rate": 6.760529715831262e-05, + "loss": 1.6626, + "step": 7101 + }, + { + "epoch": 0.39585307396466196, + "grad_norm": 0.5729551911354065, + "learning_rate": 6.759696286882769e-05, + "loss": 1.827, + "step": 7102 + }, + { + "epoch": 0.3959088122178251, + "grad_norm": 0.578536331653595, + "learning_rate": 6.758862802126969e-05, + "loss": 1.8003, + "step": 7103 + }, + { + "epoch": 0.3959645504709882, + "grad_norm": 0.5476341247558594, + "learning_rate": 6.758029261590296e-05, + "loss": 1.7641, + "step": 7104 + }, + { + "epoch": 0.3960202887241514, + "grad_norm": 0.5585542917251587, + "learning_rate": 6.757195665299186e-05, + "loss": 1.6907, + "step": 7105 + }, + { + "epoch": 0.39607602697731453, + "grad_norm": 0.5314999222755432, + "learning_rate": 6.756362013280072e-05, + "loss": 1.5457, + "step": 7106 + }, + { + "epoch": 0.39613176523047766, + "grad_norm": 0.5275375247001648, + "learning_rate": 6.755528305559398e-05, + "loss": 1.6021, + "step": 7107 + }, + { + "epoch": 0.39618750348364085, + "grad_norm": 0.5544595122337341, + "learning_rate": 6.7546945421636e-05, + "loss": 1.5837, + "step": 7108 + }, + { + "epoch": 0.396243241736804, + "grad_norm": 0.6334085464477539, + "learning_rate": 6.753860723119122e-05, + "loss": 2.096, + "step": 7109 + }, + { + "epoch": 0.3962989799899671, + "grad_norm": 0.5980644822120667, + "learning_rate": 6.753026848452407e-05, + "loss": 1.9298, + "step": 7110 + }, + { + "epoch": 0.39635471824313023, + "grad_norm": 0.5179347991943359, + "learning_rate": 6.752192918189902e-05, + "loss": 1.702, + "step": 7111 + }, + { + "epoch": 0.3964104564962934, + "grad_norm": 0.5576172471046448, + "learning_rate": 6.751358932358052e-05, + "loss": 1.6217, + "step": 7112 + }, + { + "epoch": 0.39646619474945655, + "grad_norm": 0.5886361002922058, + "learning_rate": 6.750524890983309e-05, + "loss": 1.9734, + "step": 7113 + }, + { + "epoch": 0.3965219330026197, + "grad_norm": 0.573229193687439, + "learning_rate": 6.749690794092125e-05, + "loss": 1.9415, + "step": 7114 + }, + { + "epoch": 0.39657767125578286, + "grad_norm": 1.0474965572357178, + "learning_rate": 6.748856641710948e-05, + "loss": 2.0009, + "step": 7115 + }, + { + "epoch": 0.396633409508946, + "grad_norm": 0.5304273366928101, + "learning_rate": 6.748022433866236e-05, + "loss": 1.7601, + "step": 7116 + }, + { + "epoch": 0.3966891477621091, + "grad_norm": 0.5350653529167175, + "learning_rate": 6.747188170584444e-05, + "loss": 1.7173, + "step": 7117 + }, + { + "epoch": 0.3967448860152723, + "grad_norm": 0.5216551423072815, + "learning_rate": 6.746353851892028e-05, + "loss": 1.7054, + "step": 7118 + }, + { + "epoch": 0.39680062426843543, + "grad_norm": 0.5482343435287476, + "learning_rate": 6.745519477815451e-05, + "loss": 1.6456, + "step": 7119 + }, + { + "epoch": 0.39685636252159856, + "grad_norm": 0.5794587135314941, + "learning_rate": 6.744685048381174e-05, + "loss": 1.7264, + "step": 7120 + }, + { + "epoch": 0.39691210077476174, + "grad_norm": 0.5834348797798157, + "learning_rate": 6.743850563615659e-05, + "loss": 1.7025, + "step": 7121 + }, + { + "epoch": 0.3969678390279249, + "grad_norm": 0.5380405187606812, + "learning_rate": 6.743016023545373e-05, + "loss": 1.5742, + "step": 7122 + }, + { + "epoch": 0.397023577281088, + "grad_norm": 0.5725619792938232, + "learning_rate": 6.742181428196777e-05, + "loss": 1.8845, + "step": 7123 + }, + { + "epoch": 0.39707931553425113, + "grad_norm": 0.5491376519203186, + "learning_rate": 6.741346777596347e-05, + "loss": 1.6998, + "step": 7124 + }, + { + "epoch": 0.3971350537874143, + "grad_norm": 0.5111629962921143, + "learning_rate": 6.74051207177055e-05, + "loss": 1.4712, + "step": 7125 + }, + { + "epoch": 0.39719079204057745, + "grad_norm": 0.5327715277671814, + "learning_rate": 6.739677310745856e-05, + "loss": 1.4259, + "step": 7126 + }, + { + "epoch": 0.3972465302937406, + "grad_norm": 0.585437536239624, + "learning_rate": 6.738842494548742e-05, + "loss": 1.6437, + "step": 7127 + }, + { + "epoch": 0.39730226854690376, + "grad_norm": 0.4905366599559784, + "learning_rate": 6.738007623205682e-05, + "loss": 1.537, + "step": 7128 + }, + { + "epoch": 0.3973580068000669, + "grad_norm": 0.578807532787323, + "learning_rate": 6.737172696743155e-05, + "loss": 1.7359, + "step": 7129 + }, + { + "epoch": 0.39741374505323, + "grad_norm": 0.5269452333450317, + "learning_rate": 6.736337715187638e-05, + "loss": 1.632, + "step": 7130 + }, + { + "epoch": 0.3974694833063932, + "grad_norm": 0.6212645769119263, + "learning_rate": 6.735502678565611e-05, + "loss": 1.6633, + "step": 7131 + }, + { + "epoch": 0.39752522155955633, + "grad_norm": 0.5281040668487549, + "learning_rate": 6.734667586903557e-05, + "loss": 1.6349, + "step": 7132 + }, + { + "epoch": 0.39758095981271946, + "grad_norm": 0.6241141557693481, + "learning_rate": 6.733832440227963e-05, + "loss": 1.8522, + "step": 7133 + }, + { + "epoch": 0.3976366980658826, + "grad_norm": 0.5351576805114746, + "learning_rate": 6.732997238565311e-05, + "loss": 1.8608, + "step": 7134 + }, + { + "epoch": 0.3976924363190458, + "grad_norm": 0.6173853278160095, + "learning_rate": 6.732161981942093e-05, + "loss": 1.7628, + "step": 7135 + }, + { + "epoch": 0.3977481745722089, + "grad_norm": 0.5938517451286316, + "learning_rate": 6.731326670384794e-05, + "loss": 1.7216, + "step": 7136 + }, + { + "epoch": 0.39780391282537203, + "grad_norm": 0.5863813161849976, + "learning_rate": 6.730491303919907e-05, + "loss": 1.6816, + "step": 7137 + }, + { + "epoch": 0.3978596510785352, + "grad_norm": 0.6825369596481323, + "learning_rate": 6.729655882573928e-05, + "loss": 1.9808, + "step": 7138 + }, + { + "epoch": 0.39791538933169834, + "grad_norm": 0.5284822583198547, + "learning_rate": 6.728820406373346e-05, + "loss": 1.8237, + "step": 7139 + }, + { + "epoch": 0.3979711275848615, + "grad_norm": 0.554270327091217, + "learning_rate": 6.727984875344663e-05, + "loss": 1.61, + "step": 7140 + }, + { + "epoch": 0.39802686583802466, + "grad_norm": 0.6326965093612671, + "learning_rate": 6.727149289514373e-05, + "loss": 2.1011, + "step": 7141 + }, + { + "epoch": 0.3980826040911878, + "grad_norm": 0.5701342225074768, + "learning_rate": 6.72631364890898e-05, + "loss": 1.6724, + "step": 7142 + }, + { + "epoch": 0.3981383423443509, + "grad_norm": 0.5414735078811646, + "learning_rate": 6.725477953554979e-05, + "loss": 1.5425, + "step": 7143 + }, + { + "epoch": 0.3981940805975141, + "grad_norm": 0.5954646468162537, + "learning_rate": 6.72464220347888e-05, + "loss": 1.6308, + "step": 7144 + }, + { + "epoch": 0.39824981885067723, + "grad_norm": 0.6013423204421997, + "learning_rate": 6.723806398707185e-05, + "loss": 1.8022, + "step": 7145 + }, + { + "epoch": 0.39830555710384036, + "grad_norm": 0.5645208954811096, + "learning_rate": 6.722970539266403e-05, + "loss": 1.4448, + "step": 7146 + }, + { + "epoch": 0.3983612953570035, + "grad_norm": 0.6153306365013123, + "learning_rate": 6.72213462518304e-05, + "loss": 1.7358, + "step": 7147 + }, + { + "epoch": 0.39841703361016667, + "grad_norm": 0.5638027191162109, + "learning_rate": 6.721298656483608e-05, + "loss": 1.4709, + "step": 7148 + }, + { + "epoch": 0.3984727718633298, + "grad_norm": 0.5619633197784424, + "learning_rate": 6.720462633194618e-05, + "loss": 1.6085, + "step": 7149 + }, + { + "epoch": 0.39852851011649293, + "grad_norm": 0.5597891211509705, + "learning_rate": 6.719626555342585e-05, + "loss": 1.8059, + "step": 7150 + }, + { + "epoch": 0.3985842483696561, + "grad_norm": 0.5170794725418091, + "learning_rate": 6.718790422954021e-05, + "loss": 1.7492, + "step": 7151 + }, + { + "epoch": 0.39863998662281924, + "grad_norm": 0.5071738362312317, + "learning_rate": 6.717954236055449e-05, + "loss": 1.6074, + "step": 7152 + }, + { + "epoch": 0.39869572487598237, + "grad_norm": 0.5328095555305481, + "learning_rate": 6.717117994673384e-05, + "loss": 1.3657, + "step": 7153 + }, + { + "epoch": 0.39875146312914556, + "grad_norm": 0.5484116673469543, + "learning_rate": 6.716281698834346e-05, + "loss": 1.6112, + "step": 7154 + }, + { + "epoch": 0.3988072013823087, + "grad_norm": 0.5871725678443909, + "learning_rate": 6.715445348564862e-05, + "loss": 1.9087, + "step": 7155 + }, + { + "epoch": 0.3988629396354718, + "grad_norm": 0.5913428068161011, + "learning_rate": 6.714608943891452e-05, + "loss": 2.0278, + "step": 7156 + }, + { + "epoch": 0.39891867788863494, + "grad_norm": 0.5644116997718811, + "learning_rate": 6.713772484840645e-05, + "loss": 1.63, + "step": 7157 + }, + { + "epoch": 0.3989744161417981, + "grad_norm": 0.5353809595108032, + "learning_rate": 6.712935971438962e-05, + "loss": 1.6313, + "step": 7158 + }, + { + "epoch": 0.39903015439496126, + "grad_norm": 0.5755419731140137, + "learning_rate": 6.712099403712942e-05, + "loss": 1.7367, + "step": 7159 + }, + { + "epoch": 0.3990858926481244, + "grad_norm": 0.5571795105934143, + "learning_rate": 6.711262781689109e-05, + "loss": 1.8337, + "step": 7160 + }, + { + "epoch": 0.39914163090128757, + "grad_norm": 0.5910276174545288, + "learning_rate": 6.710426105394e-05, + "loss": 1.8474, + "step": 7161 + }, + { + "epoch": 0.3991973691544507, + "grad_norm": 0.5713383555412292, + "learning_rate": 6.709589374854144e-05, + "loss": 1.4712, + "step": 7162 + }, + { + "epoch": 0.3992531074076138, + "grad_norm": 0.6179262399673462, + "learning_rate": 6.708752590096082e-05, + "loss": 1.6399, + "step": 7163 + }, + { + "epoch": 0.399308845660777, + "grad_norm": 0.5618530511856079, + "learning_rate": 6.707915751146351e-05, + "loss": 1.6822, + "step": 7164 + }, + { + "epoch": 0.39936458391394014, + "grad_norm": 0.5299525260925293, + "learning_rate": 6.70707885803149e-05, + "loss": 1.4796, + "step": 7165 + }, + { + "epoch": 0.39942032216710327, + "grad_norm": 0.5534185767173767, + "learning_rate": 6.706241910778041e-05, + "loss": 1.844, + "step": 7166 + }, + { + "epoch": 0.39947606042026645, + "grad_norm": 0.5665568709373474, + "learning_rate": 6.705404909412547e-05, + "loss": 1.787, + "step": 7167 + }, + { + "epoch": 0.3995317986734296, + "grad_norm": 0.6122377514839172, + "learning_rate": 6.704567853961552e-05, + "loss": 1.7695, + "step": 7168 + }, + { + "epoch": 0.3995875369265927, + "grad_norm": 0.5161054730415344, + "learning_rate": 6.703730744451601e-05, + "loss": 1.5939, + "step": 7169 + }, + { + "epoch": 0.39964327517975584, + "grad_norm": 0.569864809513092, + "learning_rate": 6.702893580909247e-05, + "loss": 1.7385, + "step": 7170 + }, + { + "epoch": 0.399699013432919, + "grad_norm": 0.5484759211540222, + "learning_rate": 6.702056363361036e-05, + "loss": 1.6495, + "step": 7171 + }, + { + "epoch": 0.39975475168608215, + "grad_norm": 0.5385055541992188, + "learning_rate": 6.701219091833522e-05, + "loss": 1.8867, + "step": 7172 + }, + { + "epoch": 0.3998104899392453, + "grad_norm": 0.5519033074378967, + "learning_rate": 6.700381766353255e-05, + "loss": 1.7746, + "step": 7173 + }, + { + "epoch": 0.39986622819240847, + "grad_norm": 0.6148980259895325, + "learning_rate": 6.699544386946795e-05, + "loss": 1.8656, + "step": 7174 + }, + { + "epoch": 0.3999219664455716, + "grad_norm": 0.569527268409729, + "learning_rate": 6.698706953640693e-05, + "loss": 1.6071, + "step": 7175 + }, + { + "epoch": 0.3999777046987347, + "grad_norm": 0.5626715421676636, + "learning_rate": 6.697869466461513e-05, + "loss": 1.8849, + "step": 7176 + }, + { + "epoch": 0.4000334429518979, + "grad_norm": 0.5838245153427124, + "learning_rate": 6.69703192543581e-05, + "loss": 1.7764, + "step": 7177 + }, + { + "epoch": 0.40008918120506104, + "grad_norm": 0.552139937877655, + "learning_rate": 6.696194330590151e-05, + "loss": 1.6598, + "step": 7178 + }, + { + "epoch": 0.40014491945822417, + "grad_norm": 0.5443406105041504, + "learning_rate": 6.695356681951099e-05, + "loss": 1.6139, + "step": 7179 + }, + { + "epoch": 0.4002006577113873, + "grad_norm": 0.5214937329292297, + "learning_rate": 6.694518979545214e-05, + "loss": 1.6783, + "step": 7180 + }, + { + "epoch": 0.4002563959645505, + "grad_norm": 0.5553892254829407, + "learning_rate": 6.69368122339907e-05, + "loss": 1.6699, + "step": 7181 + }, + { + "epoch": 0.4003121342177136, + "grad_norm": 0.5150647163391113, + "learning_rate": 6.692843413539229e-05, + "loss": 1.532, + "step": 7182 + }, + { + "epoch": 0.40036787247087674, + "grad_norm": 0.5763303637504578, + "learning_rate": 6.692005549992268e-05, + "loss": 1.9554, + "step": 7183 + }, + { + "epoch": 0.4004236107240399, + "grad_norm": 0.5533180832862854, + "learning_rate": 6.691167632784754e-05, + "loss": 1.4465, + "step": 7184 + }, + { + "epoch": 0.40047934897720305, + "grad_norm": 0.5495351552963257, + "learning_rate": 6.690329661943265e-05, + "loss": 1.6263, + "step": 7185 + }, + { + "epoch": 0.4005350872303662, + "grad_norm": 0.5440528988838196, + "learning_rate": 6.689491637494371e-05, + "loss": 1.8053, + "step": 7186 + }, + { + "epoch": 0.40059082548352937, + "grad_norm": 0.5240649580955505, + "learning_rate": 6.688653559464655e-05, + "loss": 1.6647, + "step": 7187 + }, + { + "epoch": 0.4006465637366925, + "grad_norm": 0.5496859550476074, + "learning_rate": 6.687815427880694e-05, + "loss": 1.7904, + "step": 7188 + }, + { + "epoch": 0.4007023019898556, + "grad_norm": 0.5740963816642761, + "learning_rate": 6.686977242769067e-05, + "loss": 1.8628, + "step": 7189 + }, + { + "epoch": 0.4007580402430188, + "grad_norm": 0.5899214148521423, + "learning_rate": 6.686139004156358e-05, + "loss": 1.6146, + "step": 7190 + }, + { + "epoch": 0.40081377849618194, + "grad_norm": 0.5265205502510071, + "learning_rate": 6.68530071206915e-05, + "loss": 1.683, + "step": 7191 + }, + { + "epoch": 0.40086951674934507, + "grad_norm": 0.560076892375946, + "learning_rate": 6.684462366534032e-05, + "loss": 1.6757, + "step": 7192 + }, + { + "epoch": 0.4009252550025082, + "grad_norm": 0.5472216010093689, + "learning_rate": 6.683623967577586e-05, + "loss": 1.7725, + "step": 7193 + }, + { + "epoch": 0.4009809932556714, + "grad_norm": 0.5014883875846863, + "learning_rate": 6.682785515226407e-05, + "loss": 1.4681, + "step": 7194 + }, + { + "epoch": 0.4010367315088345, + "grad_norm": 0.5076844692230225, + "learning_rate": 6.681947009507079e-05, + "loss": 1.4126, + "step": 7195 + }, + { + "epoch": 0.40109246976199764, + "grad_norm": 0.5327789187431335, + "learning_rate": 6.681108450446202e-05, + "loss": 1.6593, + "step": 7196 + }, + { + "epoch": 0.4011482080151608, + "grad_norm": 0.6164959073066711, + "learning_rate": 6.680269838070364e-05, + "loss": 1.9668, + "step": 7197 + }, + { + "epoch": 0.40120394626832395, + "grad_norm": 0.5150039792060852, + "learning_rate": 6.679431172406163e-05, + "loss": 1.4285, + "step": 7198 + }, + { + "epoch": 0.4012596845214871, + "grad_norm": 0.5839514136314392, + "learning_rate": 6.678592453480198e-05, + "loss": 1.8469, + "step": 7199 + }, + { + "epoch": 0.40131542277465027, + "grad_norm": 0.6449024677276611, + "learning_rate": 6.677753681319066e-05, + "loss": 2.1511, + "step": 7200 + }, + { + "epoch": 0.4013711610278134, + "grad_norm": 0.5425246357917786, + "learning_rate": 6.676914855949372e-05, + "loss": 1.8045, + "step": 7201 + }, + { + "epoch": 0.4014268992809765, + "grad_norm": 0.5886958241462708, + "learning_rate": 6.676075977397715e-05, + "loss": 1.7844, + "step": 7202 + }, + { + "epoch": 0.40148263753413965, + "grad_norm": 0.5560657382011414, + "learning_rate": 6.675237045690699e-05, + "loss": 1.7289, + "step": 7203 + }, + { + "epoch": 0.40153837578730284, + "grad_norm": 0.5133156776428223, + "learning_rate": 6.674398060854931e-05, + "loss": 1.4584, + "step": 7204 + }, + { + "epoch": 0.40159411404046597, + "grad_norm": 0.5923200845718384, + "learning_rate": 6.67355902291702e-05, + "loss": 1.8035, + "step": 7205 + }, + { + "epoch": 0.4016498522936291, + "grad_norm": 0.5706618428230286, + "learning_rate": 6.672719931903574e-05, + "loss": 1.781, + "step": 7206 + }, + { + "epoch": 0.4017055905467923, + "grad_norm": 0.548729419708252, + "learning_rate": 6.671880787841204e-05, + "loss": 1.7033, + "step": 7207 + }, + { + "epoch": 0.4017613287999554, + "grad_norm": 0.5980433225631714, + "learning_rate": 6.671041590756524e-05, + "loss": 1.7048, + "step": 7208 + }, + { + "epoch": 0.40181706705311854, + "grad_norm": 0.5054447054862976, + "learning_rate": 6.670202340676149e-05, + "loss": 1.6601, + "step": 7209 + }, + { + "epoch": 0.4018728053062817, + "grad_norm": 0.5414553880691528, + "learning_rate": 6.669363037626689e-05, + "loss": 1.619, + "step": 7210 + }, + { + "epoch": 0.40192854355944485, + "grad_norm": 0.5375347137451172, + "learning_rate": 6.66852368163477e-05, + "loss": 1.6898, + "step": 7211 + }, + { + "epoch": 0.401984281812608, + "grad_norm": 0.5620880722999573, + "learning_rate": 6.667684272727007e-05, + "loss": 1.4842, + "step": 7212 + }, + { + "epoch": 0.40204002006577116, + "grad_norm": 0.5257782936096191, + "learning_rate": 6.666844810930021e-05, + "loss": 1.5747, + "step": 7213 + }, + { + "epoch": 0.4020957583189343, + "grad_norm": 0.586007297039032, + "learning_rate": 6.666005296270439e-05, + "loss": 1.9183, + "step": 7214 + }, + { + "epoch": 0.4021514965720974, + "grad_norm": 0.5531460642814636, + "learning_rate": 6.66516572877488e-05, + "loss": 1.708, + "step": 7215 + }, + { + "epoch": 0.40220723482526055, + "grad_norm": 0.544386625289917, + "learning_rate": 6.664326108469974e-05, + "loss": 1.5666, + "step": 7216 + }, + { + "epoch": 0.40226297307842374, + "grad_norm": 0.5806384682655334, + "learning_rate": 6.663486435382347e-05, + "loss": 1.8389, + "step": 7217 + }, + { + "epoch": 0.40231871133158686, + "grad_norm": 0.6060808300971985, + "learning_rate": 6.66264670953863e-05, + "loss": 1.91, + "step": 7218 + }, + { + "epoch": 0.40237444958475, + "grad_norm": 0.5704980492591858, + "learning_rate": 6.661806930965452e-05, + "loss": 1.6892, + "step": 7219 + }, + { + "epoch": 0.4024301878379132, + "grad_norm": 0.5570072531700134, + "learning_rate": 6.660967099689448e-05, + "loss": 1.6718, + "step": 7220 + }, + { + "epoch": 0.4024859260910763, + "grad_norm": 0.5326122641563416, + "learning_rate": 6.66012721573725e-05, + "loss": 1.7055, + "step": 7221 + }, + { + "epoch": 0.40254166434423944, + "grad_norm": 0.5099365711212158, + "learning_rate": 6.659287279135499e-05, + "loss": 1.6732, + "step": 7222 + }, + { + "epoch": 0.4025974025974026, + "grad_norm": 0.5786659717559814, + "learning_rate": 6.658447289910827e-05, + "loss": 1.4223, + "step": 7223 + }, + { + "epoch": 0.40265314085056575, + "grad_norm": 0.5925951600074768, + "learning_rate": 6.657607248089879e-05, + "loss": 1.8696, + "step": 7224 + }, + { + "epoch": 0.4027088791037289, + "grad_norm": 0.5589519739151001, + "learning_rate": 6.65676715369929e-05, + "loss": 1.5046, + "step": 7225 + }, + { + "epoch": 0.402764617356892, + "grad_norm": 0.5450175404548645, + "learning_rate": 6.655927006765709e-05, + "loss": 1.6517, + "step": 7226 + }, + { + "epoch": 0.4028203556100552, + "grad_norm": 0.563928484916687, + "learning_rate": 6.655086807315778e-05, + "loss": 1.8544, + "step": 7227 + }, + { + "epoch": 0.4028760938632183, + "grad_norm": 0.5899096131324768, + "learning_rate": 6.654246555376144e-05, + "loss": 1.7556, + "step": 7228 + }, + { + "epoch": 0.40293183211638145, + "grad_norm": 0.5601338744163513, + "learning_rate": 6.653406250973451e-05, + "loss": 1.7469, + "step": 7229 + }, + { + "epoch": 0.40298757036954463, + "grad_norm": 0.5789577960968018, + "learning_rate": 6.652565894134355e-05, + "loss": 1.6428, + "step": 7230 + }, + { + "epoch": 0.40304330862270776, + "grad_norm": 0.5229625701904297, + "learning_rate": 6.651725484885503e-05, + "loss": 1.4699, + "step": 7231 + }, + { + "epoch": 0.4030990468758709, + "grad_norm": 0.5528407096862793, + "learning_rate": 6.650885023253548e-05, + "loss": 1.8881, + "step": 7232 + }, + { + "epoch": 0.4031547851290341, + "grad_norm": 0.5682995319366455, + "learning_rate": 6.650044509265147e-05, + "loss": 1.8263, + "step": 7233 + }, + { + "epoch": 0.4032105233821972, + "grad_norm": 0.5219863057136536, + "learning_rate": 6.649203942946954e-05, + "loss": 1.5232, + "step": 7234 + }, + { + "epoch": 0.40326626163536033, + "grad_norm": 0.5359931588172913, + "learning_rate": 6.648363324325627e-05, + "loss": 1.5617, + "step": 7235 + }, + { + "epoch": 0.4033219998885235, + "grad_norm": 0.5631711483001709, + "learning_rate": 6.647522653427825e-05, + "loss": 1.7428, + "step": 7236 + }, + { + "epoch": 0.40337773814168665, + "grad_norm": 0.5994919538497925, + "learning_rate": 6.646681930280211e-05, + "loss": 1.5538, + "step": 7237 + }, + { + "epoch": 0.4034334763948498, + "grad_norm": 0.5310835242271423, + "learning_rate": 6.645841154909448e-05, + "loss": 1.5501, + "step": 7238 + }, + { + "epoch": 0.4034892146480129, + "grad_norm": 0.7443162798881531, + "learning_rate": 6.6450003273422e-05, + "loss": 1.7322, + "step": 7239 + }, + { + "epoch": 0.4035449529011761, + "grad_norm": 0.5354825258255005, + "learning_rate": 6.644159447605131e-05, + "loss": 1.6913, + "step": 7240 + }, + { + "epoch": 0.4036006911543392, + "grad_norm": 0.5255858898162842, + "learning_rate": 6.64331851572491e-05, + "loss": 1.6574, + "step": 7241 + }, + { + "epoch": 0.40365642940750235, + "grad_norm": 0.531148374080658, + "learning_rate": 6.642477531728207e-05, + "loss": 1.5934, + "step": 7242 + }, + { + "epoch": 0.40371216766066553, + "grad_norm": 0.5981380939483643, + "learning_rate": 6.641636495641694e-05, + "loss": 1.8274, + "step": 7243 + }, + { + "epoch": 0.40376790591382866, + "grad_norm": 0.5403674840927124, + "learning_rate": 6.640795407492043e-05, + "loss": 1.4047, + "step": 7244 + }, + { + "epoch": 0.4038236441669918, + "grad_norm": 0.5610218048095703, + "learning_rate": 6.639954267305928e-05, + "loss": 1.8228, + "step": 7245 + }, + { + "epoch": 0.403879382420155, + "grad_norm": 0.5543003678321838, + "learning_rate": 6.639113075110025e-05, + "loss": 1.8899, + "step": 7246 + }, + { + "epoch": 0.4039351206733181, + "grad_norm": 0.5696173906326294, + "learning_rate": 6.63827183093101e-05, + "loss": 1.6491, + "step": 7247 + }, + { + "epoch": 0.40399085892648123, + "grad_norm": 0.5595298409461975, + "learning_rate": 6.637430534795567e-05, + "loss": 1.7502, + "step": 7248 + }, + { + "epoch": 0.40404659717964436, + "grad_norm": 0.5707483291625977, + "learning_rate": 6.636589186730373e-05, + "loss": 1.6643, + "step": 7249 + }, + { + "epoch": 0.40410233543280755, + "grad_norm": 0.5698502063751221, + "learning_rate": 6.635747786762113e-05, + "loss": 1.5516, + "step": 7250 + }, + { + "epoch": 0.4041580736859707, + "grad_norm": 0.5298511385917664, + "learning_rate": 6.63490633491747e-05, + "loss": 1.5581, + "step": 7251 + }, + { + "epoch": 0.4042138119391338, + "grad_norm": 0.5572474598884583, + "learning_rate": 6.63406483122313e-05, + "loss": 1.7449, + "step": 7252 + }, + { + "epoch": 0.404269550192297, + "grad_norm": 0.5807195901870728, + "learning_rate": 6.633223275705781e-05, + "loss": 1.6806, + "step": 7253 + }, + { + "epoch": 0.4043252884454601, + "grad_norm": 0.5467732548713684, + "learning_rate": 6.632381668392111e-05, + "loss": 1.742, + "step": 7254 + }, + { + "epoch": 0.40438102669862325, + "grad_norm": 0.5687143206596375, + "learning_rate": 6.631540009308813e-05, + "loss": 1.7586, + "step": 7255 + }, + { + "epoch": 0.40443676495178643, + "grad_norm": 0.5853325128555298, + "learning_rate": 6.630698298482578e-05, + "loss": 1.8601, + "step": 7256 + }, + { + "epoch": 0.40449250320494956, + "grad_norm": 0.5176242589950562, + "learning_rate": 6.629856535940101e-05, + "loss": 1.5131, + "step": 7257 + }, + { + "epoch": 0.4045482414581127, + "grad_norm": 0.5749338865280151, + "learning_rate": 6.629014721708076e-05, + "loss": 1.6167, + "step": 7258 + }, + { + "epoch": 0.4046039797112759, + "grad_norm": 0.6350910663604736, + "learning_rate": 6.628172855813203e-05, + "loss": 1.6698, + "step": 7259 + }, + { + "epoch": 0.404659717964439, + "grad_norm": 0.538773238658905, + "learning_rate": 6.627330938282182e-05, + "loss": 1.7449, + "step": 7260 + }, + { + "epoch": 0.40471545621760213, + "grad_norm": 0.5643429160118103, + "learning_rate": 6.62648896914171e-05, + "loss": 1.6906, + "step": 7261 + }, + { + "epoch": 0.40477119447076526, + "grad_norm": 0.5482378005981445, + "learning_rate": 6.62564694841849e-05, + "loss": 1.651, + "step": 7262 + }, + { + "epoch": 0.40482693272392845, + "grad_norm": 0.556492805480957, + "learning_rate": 6.624804876139227e-05, + "loss": 1.6232, + "step": 7263 + }, + { + "epoch": 0.4048826709770916, + "grad_norm": 0.5243347883224487, + "learning_rate": 6.623962752330627e-05, + "loss": 1.5745, + "step": 7264 + }, + { + "epoch": 0.4049384092302547, + "grad_norm": 0.5533580780029297, + "learning_rate": 6.623120577019396e-05, + "loss": 1.621, + "step": 7265 + }, + { + "epoch": 0.4049941474834179, + "grad_norm": 0.6168079376220703, + "learning_rate": 6.622278350232246e-05, + "loss": 1.8571, + "step": 7266 + }, + { + "epoch": 0.405049885736581, + "grad_norm": 0.5359664559364319, + "learning_rate": 6.621436071995884e-05, + "loss": 1.5815, + "step": 7267 + }, + { + "epoch": 0.40510562398974415, + "grad_norm": 0.6080171465873718, + "learning_rate": 6.620593742337022e-05, + "loss": 1.7069, + "step": 7268 + }, + { + "epoch": 0.40516136224290733, + "grad_norm": 0.5019293427467346, + "learning_rate": 6.619751361282377e-05, + "loss": 1.5408, + "step": 7269 + }, + { + "epoch": 0.40521710049607046, + "grad_norm": 0.5557806491851807, + "learning_rate": 6.618908928858663e-05, + "loss": 1.7405, + "step": 7270 + }, + { + "epoch": 0.4052728387492336, + "grad_norm": 0.5392197370529175, + "learning_rate": 6.618066445092595e-05, + "loss": 1.5968, + "step": 7271 + }, + { + "epoch": 0.4053285770023967, + "grad_norm": 0.621353030204773, + "learning_rate": 6.617223910010896e-05, + "loss": 1.8194, + "step": 7272 + }, + { + "epoch": 0.4053843152555599, + "grad_norm": 0.5642111301422119, + "learning_rate": 6.61638132364028e-05, + "loss": 1.4983, + "step": 7273 + }, + { + "epoch": 0.40544005350872303, + "grad_norm": 0.5767485499382019, + "learning_rate": 6.615538686007476e-05, + "loss": 1.6838, + "step": 7274 + }, + { + "epoch": 0.40549579176188616, + "grad_norm": 0.5635485649108887, + "learning_rate": 6.614695997139202e-05, + "loss": 1.87, + "step": 7275 + }, + { + "epoch": 0.40555153001504934, + "grad_norm": 0.617825448513031, + "learning_rate": 6.613853257062186e-05, + "loss": 1.839, + "step": 7276 + }, + { + "epoch": 0.4056072682682125, + "grad_norm": 0.5892661213874817, + "learning_rate": 6.613010465803153e-05, + "loss": 1.7833, + "step": 7277 + }, + { + "epoch": 0.4056630065213756, + "grad_norm": 0.6038499474525452, + "learning_rate": 6.612167623388834e-05, + "loss": 1.8361, + "step": 7278 + }, + { + "epoch": 0.4057187447745388, + "grad_norm": 0.5470013618469238, + "learning_rate": 6.611324729845958e-05, + "loss": 1.8218, + "step": 7279 + }, + { + "epoch": 0.4057744830277019, + "grad_norm": 0.5531765818595886, + "learning_rate": 6.610481785201254e-05, + "loss": 1.6214, + "step": 7280 + }, + { + "epoch": 0.40583022128086504, + "grad_norm": 0.5488517880439758, + "learning_rate": 6.60963878948146e-05, + "loss": 1.5644, + "step": 7281 + }, + { + "epoch": 0.40588595953402823, + "grad_norm": 0.5389445424079895, + "learning_rate": 6.608795742713306e-05, + "loss": 1.6407, + "step": 7282 + }, + { + "epoch": 0.40594169778719136, + "grad_norm": 0.5432456731796265, + "learning_rate": 6.607952644923534e-05, + "loss": 1.6906, + "step": 7283 + }, + { + "epoch": 0.4059974360403545, + "grad_norm": 0.5381740927696228, + "learning_rate": 6.607109496138877e-05, + "loss": 1.5545, + "step": 7284 + }, + { + "epoch": 0.4060531742935176, + "grad_norm": 0.5759360194206238, + "learning_rate": 6.606266296386078e-05, + "loss": 1.3279, + "step": 7285 + }, + { + "epoch": 0.4061089125466808, + "grad_norm": 0.5859653949737549, + "learning_rate": 6.605423045691875e-05, + "loss": 1.6515, + "step": 7286 + }, + { + "epoch": 0.40616465079984393, + "grad_norm": 0.5650625228881836, + "learning_rate": 6.604579744083015e-05, + "loss": 1.7375, + "step": 7287 + }, + { + "epoch": 0.40622038905300706, + "grad_norm": 0.5053606629371643, + "learning_rate": 6.60373639158624e-05, + "loss": 1.3345, + "step": 7288 + }, + { + "epoch": 0.40627612730617024, + "grad_norm": 0.559548020362854, + "learning_rate": 6.602892988228299e-05, + "loss": 1.5881, + "step": 7289 + }, + { + "epoch": 0.40633186555933337, + "grad_norm": 0.5711749196052551, + "learning_rate": 6.602049534035937e-05, + "loss": 1.6593, + "step": 7290 + }, + { + "epoch": 0.4063876038124965, + "grad_norm": 0.5415685176849365, + "learning_rate": 6.601206029035904e-05, + "loss": 1.7801, + "step": 7291 + }, + { + "epoch": 0.4064433420656597, + "grad_norm": 0.5906074643135071, + "learning_rate": 6.60036247325495e-05, + "loss": 1.8566, + "step": 7292 + }, + { + "epoch": 0.4064990803188228, + "grad_norm": 0.5831937789916992, + "learning_rate": 6.599518866719831e-05, + "loss": 1.6081, + "step": 7293 + }, + { + "epoch": 0.40655481857198594, + "grad_norm": 0.5068337917327881, + "learning_rate": 6.5986752094573e-05, + "loss": 1.5883, + "step": 7294 + }, + { + "epoch": 0.4066105568251491, + "grad_norm": 0.5402857065200806, + "learning_rate": 6.59783150149411e-05, + "loss": 1.7286, + "step": 7295 + }, + { + "epoch": 0.40666629507831226, + "grad_norm": 0.5793524980545044, + "learning_rate": 6.596987742857024e-05, + "loss": 1.782, + "step": 7296 + }, + { + "epoch": 0.4067220333314754, + "grad_norm": 0.5685024261474609, + "learning_rate": 6.596143933572795e-05, + "loss": 1.6989, + "step": 7297 + }, + { + "epoch": 0.4067777715846385, + "grad_norm": 0.5885668396949768, + "learning_rate": 6.595300073668188e-05, + "loss": 1.7724, + "step": 7298 + }, + { + "epoch": 0.4068335098378017, + "grad_norm": 0.5693629384040833, + "learning_rate": 6.594456163169963e-05, + "loss": 1.7927, + "step": 7299 + }, + { + "epoch": 0.40688924809096483, + "grad_norm": 0.6024751663208008, + "learning_rate": 6.593612202104885e-05, + "loss": 1.9269, + "step": 7300 + }, + { + "epoch": 0.40694498634412796, + "grad_norm": 0.5218265652656555, + "learning_rate": 6.59276819049972e-05, + "loss": 1.6254, + "step": 7301 + }, + { + "epoch": 0.40700072459729114, + "grad_norm": 0.6775539517402649, + "learning_rate": 6.591924128381234e-05, + "loss": 2.2446, + "step": 7302 + }, + { + "epoch": 0.40705646285045427, + "grad_norm": 0.5457693338394165, + "learning_rate": 6.591080015776196e-05, + "loss": 1.7268, + "step": 7303 + }, + { + "epoch": 0.4071122011036174, + "grad_norm": 0.5545173287391663, + "learning_rate": 6.590235852711377e-05, + "loss": 1.5403, + "step": 7304 + }, + { + "epoch": 0.4071679393567806, + "grad_norm": 0.5415998697280884, + "learning_rate": 6.589391639213549e-05, + "loss": 1.7487, + "step": 7305 + }, + { + "epoch": 0.4072236776099437, + "grad_norm": 0.535123884677887, + "learning_rate": 6.588547375309484e-05, + "loss": 1.8118, + "step": 7306 + }, + { + "epoch": 0.40727941586310684, + "grad_norm": 0.5559954643249512, + "learning_rate": 6.587703061025959e-05, + "loss": 1.7792, + "step": 7307 + }, + { + "epoch": 0.40733515411626997, + "grad_norm": 0.5952346920967102, + "learning_rate": 6.586858696389748e-05, + "loss": 1.8367, + "step": 7308 + }, + { + "epoch": 0.40739089236943316, + "grad_norm": 0.5658838152885437, + "learning_rate": 6.586014281427632e-05, + "loss": 1.8874, + "step": 7309 + }, + { + "epoch": 0.4074466306225963, + "grad_norm": 0.5443295240402222, + "learning_rate": 6.585169816166392e-05, + "loss": 1.6405, + "step": 7310 + }, + { + "epoch": 0.4075023688757594, + "grad_norm": 0.5414347648620605, + "learning_rate": 6.584325300632806e-05, + "loss": 1.7544, + "step": 7311 + }, + { + "epoch": 0.4075581071289226, + "grad_norm": 0.5387737154960632, + "learning_rate": 6.583480734853658e-05, + "loss": 1.6416, + "step": 7312 + }, + { + "epoch": 0.4076138453820857, + "grad_norm": 0.5518178343772888, + "learning_rate": 6.582636118855735e-05, + "loss": 1.7322, + "step": 7313 + }, + { + "epoch": 0.40766958363524886, + "grad_norm": 0.5452878475189209, + "learning_rate": 6.58179145266582e-05, + "loss": 1.7432, + "step": 7314 + }, + { + "epoch": 0.40772532188841204, + "grad_norm": 0.5074037313461304, + "learning_rate": 6.580946736310704e-05, + "loss": 1.6643, + "step": 7315 + }, + { + "epoch": 0.40778106014157517, + "grad_norm": 0.5745427012443542, + "learning_rate": 6.580101969817175e-05, + "loss": 1.8664, + "step": 7316 + }, + { + "epoch": 0.4078367983947383, + "grad_norm": 0.5891657471656799, + "learning_rate": 6.579257153212024e-05, + "loss": 1.8217, + "step": 7317 + }, + { + "epoch": 0.4078925366479015, + "grad_norm": 0.5395662188529968, + "learning_rate": 6.578412286522044e-05, + "loss": 1.5422, + "step": 7318 + }, + { + "epoch": 0.4079482749010646, + "grad_norm": 0.5738537907600403, + "learning_rate": 6.57756736977403e-05, + "loss": 1.753, + "step": 7319 + }, + { + "epoch": 0.40800401315422774, + "grad_norm": 0.5593982338905334, + "learning_rate": 6.576722402994775e-05, + "loss": 1.5805, + "step": 7320 + }, + { + "epoch": 0.40805975140739087, + "grad_norm": 0.6101201772689819, + "learning_rate": 6.575877386211077e-05, + "loss": 1.742, + "step": 7321 + }, + { + "epoch": 0.40811548966055405, + "grad_norm": 0.5429602265357971, + "learning_rate": 6.57503231944974e-05, + "loss": 1.7166, + "step": 7322 + }, + { + "epoch": 0.4081712279137172, + "grad_norm": 0.5799590349197388, + "learning_rate": 6.574187202737558e-05, + "loss": 1.8698, + "step": 7323 + }, + { + "epoch": 0.4082269661668803, + "grad_norm": 0.5671953558921814, + "learning_rate": 6.573342036101339e-05, + "loss": 1.5871, + "step": 7324 + }, + { + "epoch": 0.4082827044200435, + "grad_norm": 0.5521631836891174, + "learning_rate": 6.572496819567882e-05, + "loss": 1.6091, + "step": 7325 + }, + { + "epoch": 0.4083384426732066, + "grad_norm": 0.6058674454689026, + "learning_rate": 6.571651553163994e-05, + "loss": 1.9233, + "step": 7326 + }, + { + "epoch": 0.40839418092636975, + "grad_norm": 0.5595351457595825, + "learning_rate": 6.570806236916481e-05, + "loss": 1.681, + "step": 7327 + }, + { + "epoch": 0.40844991917953294, + "grad_norm": 0.5565963983535767, + "learning_rate": 6.569960870852156e-05, + "loss": 1.8081, + "step": 7328 + }, + { + "epoch": 0.40850565743269607, + "grad_norm": 0.5626837015151978, + "learning_rate": 6.569115454997823e-05, + "loss": 1.7268, + "step": 7329 + }, + { + "epoch": 0.4085613956858592, + "grad_norm": 0.5642188787460327, + "learning_rate": 6.568269989380296e-05, + "loss": 1.9007, + "step": 7330 + }, + { + "epoch": 0.4086171339390223, + "grad_norm": 0.5992141962051392, + "learning_rate": 6.56742447402639e-05, + "loss": 1.8163, + "step": 7331 + }, + { + "epoch": 0.4086728721921855, + "grad_norm": 0.5469499826431274, + "learning_rate": 6.566578908962918e-05, + "loss": 1.6564, + "step": 7332 + }, + { + "epoch": 0.40872861044534864, + "grad_norm": 0.5719706416130066, + "learning_rate": 6.565733294216697e-05, + "loss": 1.3752, + "step": 7333 + }, + { + "epoch": 0.40878434869851177, + "grad_norm": 0.5726919174194336, + "learning_rate": 6.564887629814543e-05, + "loss": 1.629, + "step": 7334 + }, + { + "epoch": 0.40884008695167495, + "grad_norm": 0.6024767160415649, + "learning_rate": 6.56404191578328e-05, + "loss": 1.6818, + "step": 7335 + }, + { + "epoch": 0.4088958252048381, + "grad_norm": 0.5598945021629333, + "learning_rate": 6.563196152149725e-05, + "loss": 1.6562, + "step": 7336 + }, + { + "epoch": 0.4089515634580012, + "grad_norm": 0.6022909283638, + "learning_rate": 6.562350338940704e-05, + "loss": 1.6497, + "step": 7337 + }, + { + "epoch": 0.4090073017111644, + "grad_norm": 0.5557130575180054, + "learning_rate": 6.561504476183037e-05, + "loss": 1.5777, + "step": 7338 + }, + { + "epoch": 0.4090630399643275, + "grad_norm": 0.556742787361145, + "learning_rate": 6.560658563903553e-05, + "loss": 1.6048, + "step": 7339 + }, + { + "epoch": 0.40911877821749065, + "grad_norm": 0.6215361952781677, + "learning_rate": 6.559812602129078e-05, + "loss": 1.85, + "step": 7340 + }, + { + "epoch": 0.40917451647065384, + "grad_norm": 0.5431729555130005, + "learning_rate": 6.558966590886443e-05, + "loss": 1.7366, + "step": 7341 + }, + { + "epoch": 0.40923025472381697, + "grad_norm": 0.5173145532608032, + "learning_rate": 6.558120530202476e-05, + "loss": 1.5962, + "step": 7342 + }, + { + "epoch": 0.4092859929769801, + "grad_norm": 0.558746874332428, + "learning_rate": 6.55727442010401e-05, + "loss": 1.6842, + "step": 7343 + }, + { + "epoch": 0.4093417312301432, + "grad_norm": 0.5484337210655212, + "learning_rate": 6.55642826061788e-05, + "loss": 1.8824, + "step": 7344 + }, + { + "epoch": 0.4093974694833064, + "grad_norm": 0.5415590405464172, + "learning_rate": 6.55558205177092e-05, + "loss": 1.7393, + "step": 7345 + }, + { + "epoch": 0.40945320773646954, + "grad_norm": 0.5736859440803528, + "learning_rate": 6.554735793589967e-05, + "loss": 1.6012, + "step": 7346 + }, + { + "epoch": 0.40950894598963267, + "grad_norm": 0.5511910319328308, + "learning_rate": 6.553889486101857e-05, + "loss": 1.6051, + "step": 7347 + }, + { + "epoch": 0.40956468424279585, + "grad_norm": 0.5481744408607483, + "learning_rate": 6.553043129333436e-05, + "loss": 1.6571, + "step": 7348 + }, + { + "epoch": 0.409620422495959, + "grad_norm": 0.7418869733810425, + "learning_rate": 6.55219672331154e-05, + "loss": 1.6247, + "step": 7349 + }, + { + "epoch": 0.4096761607491221, + "grad_norm": 0.5882282257080078, + "learning_rate": 6.551350268063015e-05, + "loss": 1.7125, + "step": 7350 + }, + { + "epoch": 0.4097318990022853, + "grad_norm": 0.6087817549705505, + "learning_rate": 6.550503763614702e-05, + "loss": 1.9143, + "step": 7351 + }, + { + "epoch": 0.4097876372554484, + "grad_norm": 0.5106980800628662, + "learning_rate": 6.549657209993452e-05, + "loss": 1.4884, + "step": 7352 + }, + { + "epoch": 0.40984337550861155, + "grad_norm": 0.5542812347412109, + "learning_rate": 6.548810607226109e-05, + "loss": 1.6739, + "step": 7353 + }, + { + "epoch": 0.4098991137617747, + "grad_norm": 0.6260994672775269, + "learning_rate": 6.547963955339526e-05, + "loss": 1.8902, + "step": 7354 + }, + { + "epoch": 0.40995485201493786, + "grad_norm": 0.5681547522544861, + "learning_rate": 6.547117254360549e-05, + "loss": 1.8688, + "step": 7355 + }, + { + "epoch": 0.410010590268101, + "grad_norm": 0.5453806519508362, + "learning_rate": 6.546270504316033e-05, + "loss": 1.7046, + "step": 7356 + }, + { + "epoch": 0.4100663285212641, + "grad_norm": 0.5230925679206848, + "learning_rate": 6.545423705232834e-05, + "loss": 1.6008, + "step": 7357 + }, + { + "epoch": 0.4101220667744273, + "grad_norm": 0.5534452795982361, + "learning_rate": 6.544576857137804e-05, + "loss": 1.806, + "step": 7358 + }, + { + "epoch": 0.41017780502759044, + "grad_norm": 0.586466908454895, + "learning_rate": 6.543729960057803e-05, + "loss": 1.8252, + "step": 7359 + }, + { + "epoch": 0.41023354328075357, + "grad_norm": 0.5712817311286926, + "learning_rate": 6.542883014019686e-05, + "loss": 1.6653, + "step": 7360 + }, + { + "epoch": 0.41028928153391675, + "grad_norm": 0.5666759014129639, + "learning_rate": 6.542036019050318e-05, + "loss": 1.7503, + "step": 7361 + }, + { + "epoch": 0.4103450197870799, + "grad_norm": 0.6092966198921204, + "learning_rate": 6.541188975176557e-05, + "loss": 2.0138, + "step": 7362 + }, + { + "epoch": 0.410400758040243, + "grad_norm": 0.5910922884941101, + "learning_rate": 6.540341882425267e-05, + "loss": 1.8193, + "step": 7363 + }, + { + "epoch": 0.4104564962934062, + "grad_norm": 0.5653868317604065, + "learning_rate": 6.539494740823313e-05, + "loss": 1.6905, + "step": 7364 + }, + { + "epoch": 0.4105122345465693, + "grad_norm": 0.5556957721710205, + "learning_rate": 6.538647550397563e-05, + "loss": 1.5966, + "step": 7365 + }, + { + "epoch": 0.41056797279973245, + "grad_norm": 0.6585522294044495, + "learning_rate": 6.537800311174882e-05, + "loss": 1.9665, + "step": 7366 + }, + { + "epoch": 0.4106237110528956, + "grad_norm": 0.5647701621055603, + "learning_rate": 6.536953023182143e-05, + "loss": 1.7119, + "step": 7367 + }, + { + "epoch": 0.41067944930605876, + "grad_norm": 0.5993644595146179, + "learning_rate": 6.536105686446214e-05, + "loss": 1.8307, + "step": 7368 + }, + { + "epoch": 0.4107351875592219, + "grad_norm": 0.5878274440765381, + "learning_rate": 6.535258300993969e-05, + "loss": 1.6834, + "step": 7369 + }, + { + "epoch": 0.410790925812385, + "grad_norm": 0.5731014609336853, + "learning_rate": 6.534410866852283e-05, + "loss": 1.7639, + "step": 7370 + }, + { + "epoch": 0.4108466640655482, + "grad_norm": 0.558718204498291, + "learning_rate": 6.533563384048029e-05, + "loss": 1.68, + "step": 7371 + }, + { + "epoch": 0.41090240231871134, + "grad_norm": 0.5906892418861389, + "learning_rate": 6.532715852608087e-05, + "loss": 1.6856, + "step": 7372 + }, + { + "epoch": 0.41095814057187446, + "grad_norm": 0.5575792193412781, + "learning_rate": 6.531868272559333e-05, + "loss": 1.6829, + "step": 7373 + }, + { + "epoch": 0.41101387882503765, + "grad_norm": 0.5349531769752502, + "learning_rate": 6.531020643928649e-05, + "loss": 1.666, + "step": 7374 + }, + { + "epoch": 0.4110696170782008, + "grad_norm": 0.5200047492980957, + "learning_rate": 6.530172966742918e-05, + "loss": 1.5504, + "step": 7375 + }, + { + "epoch": 0.4111253553313639, + "grad_norm": 0.599875271320343, + "learning_rate": 6.529325241029022e-05, + "loss": 1.8604, + "step": 7376 + }, + { + "epoch": 0.41118109358452704, + "grad_norm": 0.5267208814620972, + "learning_rate": 6.528477466813845e-05, + "loss": 1.5969, + "step": 7377 + }, + { + "epoch": 0.4112368318376902, + "grad_norm": 0.5209345817565918, + "learning_rate": 6.527629644124273e-05, + "loss": 1.5824, + "step": 7378 + }, + { + "epoch": 0.41129257009085335, + "grad_norm": 0.5929481983184814, + "learning_rate": 6.526781772987197e-05, + "loss": 1.9316, + "step": 7379 + }, + { + "epoch": 0.4113483083440165, + "grad_norm": 0.5629690885543823, + "learning_rate": 6.525933853429505e-05, + "loss": 1.6927, + "step": 7380 + }, + { + "epoch": 0.41140404659717966, + "grad_norm": 0.5802732110023499, + "learning_rate": 6.525085885478089e-05, + "loss": 1.7149, + "step": 7381 + }, + { + "epoch": 0.4114597848503428, + "grad_norm": 0.5767194032669067, + "learning_rate": 6.524237869159838e-05, + "loss": 1.6511, + "step": 7382 + }, + { + "epoch": 0.4115155231035059, + "grad_norm": 0.5414605140686035, + "learning_rate": 6.523389804501651e-05, + "loss": 1.5401, + "step": 7383 + }, + { + "epoch": 0.4115712613566691, + "grad_norm": 0.5376063585281372, + "learning_rate": 6.52254169153042e-05, + "loss": 1.6796, + "step": 7384 + }, + { + "epoch": 0.41162699960983223, + "grad_norm": 0.5899385809898376, + "learning_rate": 6.521693530273045e-05, + "loss": 1.7729, + "step": 7385 + }, + { + "epoch": 0.41168273786299536, + "grad_norm": 0.5602531433105469, + "learning_rate": 6.520845320756421e-05, + "loss": 1.6136, + "step": 7386 + }, + { + "epoch": 0.41173847611615855, + "grad_norm": 0.5425115823745728, + "learning_rate": 6.519997063007452e-05, + "loss": 1.5817, + "step": 7387 + }, + { + "epoch": 0.4117942143693217, + "grad_norm": 0.5449849963188171, + "learning_rate": 6.51914875705304e-05, + "loss": 1.6962, + "step": 7388 + }, + { + "epoch": 0.4118499526224848, + "grad_norm": 0.5851723551750183, + "learning_rate": 6.518300402920084e-05, + "loss": 2.035, + "step": 7389 + }, + { + "epoch": 0.41190569087564793, + "grad_norm": 0.5257713794708252, + "learning_rate": 6.517452000635493e-05, + "loss": 1.1806, + "step": 7390 + }, + { + "epoch": 0.4119614291288111, + "grad_norm": 0.5605010390281677, + "learning_rate": 6.516603550226171e-05, + "loss": 1.7513, + "step": 7391 + }, + { + "epoch": 0.41201716738197425, + "grad_norm": 0.6154865026473999, + "learning_rate": 6.515755051719026e-05, + "loss": 1.8616, + "step": 7392 + }, + { + "epoch": 0.4120729056351374, + "grad_norm": 0.5920423269271851, + "learning_rate": 6.51490650514097e-05, + "loss": 1.7594, + "step": 7393 + }, + { + "epoch": 0.41212864388830056, + "grad_norm": 0.545600414276123, + "learning_rate": 6.514057910518913e-05, + "loss": 1.5641, + "step": 7394 + }, + { + "epoch": 0.4121843821414637, + "grad_norm": 0.5568488836288452, + "learning_rate": 6.513209267879765e-05, + "loss": 1.6398, + "step": 7395 + }, + { + "epoch": 0.4122401203946268, + "grad_norm": 0.5209145545959473, + "learning_rate": 6.512360577250443e-05, + "loss": 1.4485, + "step": 7396 + }, + { + "epoch": 0.41229585864779, + "grad_norm": 0.5175876021385193, + "learning_rate": 6.511511838657859e-05, + "loss": 1.6851, + "step": 7397 + }, + { + "epoch": 0.41235159690095313, + "grad_norm": 0.5393850803375244, + "learning_rate": 6.510663052128934e-05, + "loss": 1.6724, + "step": 7398 + }, + { + "epoch": 0.41240733515411626, + "grad_norm": 0.5579698085784912, + "learning_rate": 6.509814217690582e-05, + "loss": 1.7999, + "step": 7399 + }, + { + "epoch": 0.4124630734072794, + "grad_norm": 0.5217966437339783, + "learning_rate": 6.508965335369729e-05, + "loss": 1.5216, + "step": 7400 + }, + { + "epoch": 0.4125188116604426, + "grad_norm": 0.5507352352142334, + "learning_rate": 6.508116405193292e-05, + "loss": 1.5396, + "step": 7401 + }, + { + "epoch": 0.4125745499136057, + "grad_norm": 0.5592759847640991, + "learning_rate": 6.507267427188197e-05, + "loss": 1.7238, + "step": 7402 + }, + { + "epoch": 0.41263028816676883, + "grad_norm": 0.5734774470329285, + "learning_rate": 6.506418401381365e-05, + "loss": 1.7004, + "step": 7403 + }, + { + "epoch": 0.412686026419932, + "grad_norm": 0.5572485327720642, + "learning_rate": 6.505569327799726e-05, + "loss": 1.5875, + "step": 7404 + }, + { + "epoch": 0.41274176467309515, + "grad_norm": 0.5783054232597351, + "learning_rate": 6.504720206470205e-05, + "loss": 1.806, + "step": 7405 + }, + { + "epoch": 0.4127975029262583, + "grad_norm": 0.5762080550193787, + "learning_rate": 6.503871037419731e-05, + "loss": 1.6241, + "step": 7406 + }, + { + "epoch": 0.41285324117942146, + "grad_norm": 0.5752031207084656, + "learning_rate": 6.50302182067524e-05, + "loss": 1.5105, + "step": 7407 + }, + { + "epoch": 0.4129089794325846, + "grad_norm": 0.5618080496788025, + "learning_rate": 6.502172556263656e-05, + "loss": 1.6661, + "step": 7408 + }, + { + "epoch": 0.4129647176857477, + "grad_norm": 0.5460039377212524, + "learning_rate": 6.501323244211919e-05, + "loss": 1.5414, + "step": 7409 + }, + { + "epoch": 0.4130204559389109, + "grad_norm": 0.5536362528800964, + "learning_rate": 6.500473884546962e-05, + "loss": 1.7312, + "step": 7410 + }, + { + "epoch": 0.41307619419207403, + "grad_norm": 0.5220944285392761, + "learning_rate": 6.499624477295722e-05, + "loss": 1.4628, + "step": 7411 + }, + { + "epoch": 0.41313193244523716, + "grad_norm": 0.5702623128890991, + "learning_rate": 6.498775022485134e-05, + "loss": 1.7568, + "step": 7412 + }, + { + "epoch": 0.4131876706984003, + "grad_norm": 0.5831007361412048, + "learning_rate": 6.497925520142143e-05, + "loss": 1.8805, + "step": 7413 + }, + { + "epoch": 0.4132434089515635, + "grad_norm": 0.5719270706176758, + "learning_rate": 6.497075970293688e-05, + "loss": 1.8406, + "step": 7414 + }, + { + "epoch": 0.4132991472047266, + "grad_norm": 0.5721832513809204, + "learning_rate": 6.496226372966711e-05, + "loss": 1.8577, + "step": 7415 + }, + { + "epoch": 0.41335488545788973, + "grad_norm": 0.5381945967674255, + "learning_rate": 6.495376728188159e-05, + "loss": 1.5441, + "step": 7416 + }, + { + "epoch": 0.4134106237110529, + "grad_norm": 0.5105479955673218, + "learning_rate": 6.494527035984974e-05, + "loss": 1.7383, + "step": 7417 + }, + { + "epoch": 0.41346636196421604, + "grad_norm": 0.5516504049301147, + "learning_rate": 6.493677296384106e-05, + "loss": 1.7542, + "step": 7418 + }, + { + "epoch": 0.4135221002173792, + "grad_norm": 0.5726693868637085, + "learning_rate": 6.492827509412501e-05, + "loss": 1.887, + "step": 7419 + }, + { + "epoch": 0.41357783847054236, + "grad_norm": 0.5425702333450317, + "learning_rate": 6.491977675097114e-05, + "loss": 1.6247, + "step": 7420 + }, + { + "epoch": 0.4136335767237055, + "grad_norm": 0.7511564493179321, + "learning_rate": 6.491127793464893e-05, + "loss": 1.7428, + "step": 7421 + }, + { + "epoch": 0.4136893149768686, + "grad_norm": 0.5151875019073486, + "learning_rate": 6.490277864542792e-05, + "loss": 1.6937, + "step": 7422 + }, + { + "epoch": 0.41374505323003175, + "grad_norm": 0.5558873414993286, + "learning_rate": 6.489427888357765e-05, + "loss": 1.7254, + "step": 7423 + }, + { + "epoch": 0.41380079148319493, + "grad_norm": 0.5704571008682251, + "learning_rate": 6.488577864936771e-05, + "loss": 1.6893, + "step": 7424 + }, + { + "epoch": 0.41385652973635806, + "grad_norm": 0.5515883564949036, + "learning_rate": 6.487727794306765e-05, + "loss": 1.5928, + "step": 7425 + }, + { + "epoch": 0.4139122679895212, + "grad_norm": 0.5346539616584778, + "learning_rate": 6.48687767649471e-05, + "loss": 1.5923, + "step": 7426 + }, + { + "epoch": 0.41396800624268437, + "grad_norm": 0.48073434829711914, + "learning_rate": 6.48602751152756e-05, + "loss": 1.5783, + "step": 7427 + }, + { + "epoch": 0.4140237444958475, + "grad_norm": 0.5613585114479065, + "learning_rate": 6.485177299432284e-05, + "loss": 1.7081, + "step": 7428 + }, + { + "epoch": 0.41407948274901063, + "grad_norm": 0.5521184206008911, + "learning_rate": 6.484327040235844e-05, + "loss": 1.8141, + "step": 7429 + }, + { + "epoch": 0.4141352210021738, + "grad_norm": 0.5570716857910156, + "learning_rate": 6.483476733965202e-05, + "loss": 1.8114, + "step": 7430 + }, + { + "epoch": 0.41419095925533694, + "grad_norm": 0.5927569270133972, + "learning_rate": 6.48262638064733e-05, + "loss": 1.8538, + "step": 7431 + }, + { + "epoch": 0.4142466975085001, + "grad_norm": 0.6198796629905701, + "learning_rate": 6.48177598030919e-05, + "loss": 1.8671, + "step": 7432 + }, + { + "epoch": 0.41430243576166326, + "grad_norm": 0.562487781047821, + "learning_rate": 6.480925532977758e-05, + "loss": 1.6247, + "step": 7433 + }, + { + "epoch": 0.4143581740148264, + "grad_norm": 0.5455536246299744, + "learning_rate": 6.480075038680002e-05, + "loss": 1.6946, + "step": 7434 + }, + { + "epoch": 0.4144139122679895, + "grad_norm": 0.6041662096977234, + "learning_rate": 6.479224497442897e-05, + "loss": 1.9345, + "step": 7435 + }, + { + "epoch": 0.41446965052115264, + "grad_norm": 0.5616452693939209, + "learning_rate": 6.478373909293412e-05, + "loss": 1.8108, + "step": 7436 + }, + { + "epoch": 0.41452538877431583, + "grad_norm": 0.5593286752700806, + "learning_rate": 6.477523274258528e-05, + "loss": 1.6404, + "step": 7437 + }, + { + "epoch": 0.41458112702747896, + "grad_norm": 0.5919610261917114, + "learning_rate": 6.47667259236522e-05, + "loss": 1.8287, + "step": 7438 + }, + { + "epoch": 0.4146368652806421, + "grad_norm": 0.6362894177436829, + "learning_rate": 6.475821863640467e-05, + "loss": 1.8535, + "step": 7439 + }, + { + "epoch": 0.41469260353380527, + "grad_norm": 0.4930521547794342, + "learning_rate": 6.474971088111248e-05, + "loss": 1.3973, + "step": 7440 + }, + { + "epoch": 0.4147483417869684, + "grad_norm": 0.5308540463447571, + "learning_rate": 6.474120265804549e-05, + "loss": 1.5271, + "step": 7441 + }, + { + "epoch": 0.41480408004013153, + "grad_norm": 0.5587360262870789, + "learning_rate": 6.473269396747346e-05, + "loss": 1.6953, + "step": 7442 + }, + { + "epoch": 0.4148598182932947, + "grad_norm": 0.5565241575241089, + "learning_rate": 6.47241848096663e-05, + "loss": 1.7807, + "step": 7443 + }, + { + "epoch": 0.41491555654645784, + "grad_norm": 0.6130486130714417, + "learning_rate": 6.471567518489383e-05, + "loss": 2.0551, + "step": 7444 + }, + { + "epoch": 0.41497129479962097, + "grad_norm": 0.5374565720558167, + "learning_rate": 6.470716509342594e-05, + "loss": 1.6525, + "step": 7445 + }, + { + "epoch": 0.4150270330527841, + "grad_norm": 0.5470364093780518, + "learning_rate": 6.469865453553254e-05, + "loss": 1.7753, + "step": 7446 + }, + { + "epoch": 0.4150827713059473, + "grad_norm": 0.5423111319541931, + "learning_rate": 6.46901435114835e-05, + "loss": 1.6718, + "step": 7447 + }, + { + "epoch": 0.4151385095591104, + "grad_norm": 0.630453884601593, + "learning_rate": 6.468163202154877e-05, + "loss": 1.7607, + "step": 7448 + }, + { + "epoch": 0.41519424781227354, + "grad_norm": 0.5870693325996399, + "learning_rate": 6.467312006599828e-05, + "loss": 1.8854, + "step": 7449 + }, + { + "epoch": 0.4152499860654367, + "grad_norm": 0.6026604771614075, + "learning_rate": 6.466460764510196e-05, + "loss": 1.6298, + "step": 7450 + }, + { + "epoch": 0.41530572431859986, + "grad_norm": 0.5341464281082153, + "learning_rate": 6.465609475912977e-05, + "loss": 1.5961, + "step": 7451 + }, + { + "epoch": 0.415361462571763, + "grad_norm": 0.5364176630973816, + "learning_rate": 6.464758140835173e-05, + "loss": 1.6091, + "step": 7452 + }, + { + "epoch": 0.41541720082492617, + "grad_norm": 0.5682061910629272, + "learning_rate": 6.463906759303779e-05, + "loss": 1.6807, + "step": 7453 + }, + { + "epoch": 0.4154729390780893, + "grad_norm": 0.5520201325416565, + "learning_rate": 6.463055331345798e-05, + "loss": 1.8693, + "step": 7454 + }, + { + "epoch": 0.4155286773312524, + "grad_norm": 0.5386977195739746, + "learning_rate": 6.462203856988233e-05, + "loss": 1.5473, + "step": 7455 + }, + { + "epoch": 0.4155844155844156, + "grad_norm": 0.5517452955245972, + "learning_rate": 6.461352336258088e-05, + "loss": 1.5523, + "step": 7456 + }, + { + "epoch": 0.41564015383757874, + "grad_norm": 0.6362208127975464, + "learning_rate": 6.460500769182365e-05, + "loss": 1.6515, + "step": 7457 + }, + { + "epoch": 0.41569589209074187, + "grad_norm": 0.5483435392379761, + "learning_rate": 6.459649155788075e-05, + "loss": 1.6962, + "step": 7458 + }, + { + "epoch": 0.415751630343905, + "grad_norm": 0.5627394914627075, + "learning_rate": 6.458797496102222e-05, + "loss": 1.5808, + "step": 7459 + }, + { + "epoch": 0.4158073685970682, + "grad_norm": 0.5749256610870361, + "learning_rate": 6.45794579015182e-05, + "loss": 1.6652, + "step": 7460 + }, + { + "epoch": 0.4158631068502313, + "grad_norm": 0.561033308506012, + "learning_rate": 6.457094037963877e-05, + "loss": 1.5447, + "step": 7461 + }, + { + "epoch": 0.41591884510339444, + "grad_norm": 0.6188123822212219, + "learning_rate": 6.456242239565405e-05, + "loss": 1.8373, + "step": 7462 + }, + { + "epoch": 0.4159745833565576, + "grad_norm": 0.5495220422744751, + "learning_rate": 6.455390394983422e-05, + "loss": 1.7338, + "step": 7463 + }, + { + "epoch": 0.41603032160972075, + "grad_norm": 0.5390871167182922, + "learning_rate": 6.454538504244938e-05, + "loss": 1.5552, + "step": 7464 + }, + { + "epoch": 0.4160860598628839, + "grad_norm": 0.5653820633888245, + "learning_rate": 6.453686567376976e-05, + "loss": 1.692, + "step": 7465 + }, + { + "epoch": 0.41614179811604707, + "grad_norm": 0.5153915286064148, + "learning_rate": 6.45283458440655e-05, + "loss": 1.6676, + "step": 7466 + }, + { + "epoch": 0.4161975363692102, + "grad_norm": 0.5695963501930237, + "learning_rate": 6.451982555360682e-05, + "loss": 1.6982, + "step": 7467 + }, + { + "epoch": 0.4162532746223733, + "grad_norm": 0.6078826785087585, + "learning_rate": 6.451130480266395e-05, + "loss": 1.762, + "step": 7468 + }, + { + "epoch": 0.41630901287553645, + "grad_norm": 0.5621688961982727, + "learning_rate": 6.450278359150708e-05, + "loss": 1.5914, + "step": 7469 + }, + { + "epoch": 0.41636475112869964, + "grad_norm": 0.5914077162742615, + "learning_rate": 6.449426192040649e-05, + "loss": 1.909, + "step": 7470 + }, + { + "epoch": 0.41642048938186277, + "grad_norm": 0.5638688802719116, + "learning_rate": 6.448573978963239e-05, + "loss": 1.8037, + "step": 7471 + }, + { + "epoch": 0.4164762276350259, + "grad_norm": 0.569990336894989, + "learning_rate": 6.44772171994551e-05, + "loss": 1.5707, + "step": 7472 + }, + { + "epoch": 0.4165319658881891, + "grad_norm": 0.5680502653121948, + "learning_rate": 6.446869415014488e-05, + "loss": 1.6062, + "step": 7473 + }, + { + "epoch": 0.4165877041413522, + "grad_norm": 0.5565951466560364, + "learning_rate": 6.446017064197205e-05, + "loss": 1.7973, + "step": 7474 + }, + { + "epoch": 0.41664344239451534, + "grad_norm": 0.5711973905563354, + "learning_rate": 6.445164667520691e-05, + "loss": 1.751, + "step": 7475 + }, + { + "epoch": 0.4166991806476785, + "grad_norm": 0.5332829356193542, + "learning_rate": 6.44431222501198e-05, + "loss": 1.5348, + "step": 7476 + }, + { + "epoch": 0.41675491890084165, + "grad_norm": 0.5311811566352844, + "learning_rate": 6.443459736698105e-05, + "loss": 1.7648, + "step": 7477 + }, + { + "epoch": 0.4168106571540048, + "grad_norm": 0.5389667749404907, + "learning_rate": 6.442607202606104e-05, + "loss": 1.5702, + "step": 7478 + }, + { + "epoch": 0.41686639540716797, + "grad_norm": 0.5450131297111511, + "learning_rate": 6.441754622763015e-05, + "loss": 1.5624, + "step": 7479 + }, + { + "epoch": 0.4169221336603311, + "grad_norm": 0.6195186376571655, + "learning_rate": 6.440901997195871e-05, + "loss": 1.8265, + "step": 7480 + }, + { + "epoch": 0.4169778719134942, + "grad_norm": 0.5652611255645752, + "learning_rate": 6.440049325931721e-05, + "loss": 1.6908, + "step": 7481 + }, + { + "epoch": 0.41703361016665735, + "grad_norm": 0.5675498843193054, + "learning_rate": 6.4391966089976e-05, + "loss": 1.8279, + "step": 7482 + }, + { + "epoch": 0.41708934841982054, + "grad_norm": 0.5133779048919678, + "learning_rate": 6.438343846420556e-05, + "loss": 1.4909, + "step": 7483 + }, + { + "epoch": 0.41714508667298367, + "grad_norm": 0.5815598964691162, + "learning_rate": 6.437491038227628e-05, + "loss": 1.6886, + "step": 7484 + }, + { + "epoch": 0.4172008249261468, + "grad_norm": 0.5756742358207703, + "learning_rate": 6.43663818444587e-05, + "loss": 1.5501, + "step": 7485 + }, + { + "epoch": 0.41725656317931, + "grad_norm": 0.5238984227180481, + "learning_rate": 6.435785285102321e-05, + "loss": 1.5227, + "step": 7486 + }, + { + "epoch": 0.4173123014324731, + "grad_norm": 0.6538522839546204, + "learning_rate": 6.434932340224036e-05, + "loss": 1.8644, + "step": 7487 + }, + { + "epoch": 0.41736803968563624, + "grad_norm": 0.5802149772644043, + "learning_rate": 6.434079349838062e-05, + "loss": 1.823, + "step": 7488 + }, + { + "epoch": 0.4174237779387994, + "grad_norm": 0.5617754459381104, + "learning_rate": 6.433226313971455e-05, + "loss": 1.6917, + "step": 7489 + }, + { + "epoch": 0.41747951619196255, + "grad_norm": 0.5967627763748169, + "learning_rate": 6.432373232651261e-05, + "loss": 1.8103, + "step": 7490 + }, + { + "epoch": 0.4175352544451257, + "grad_norm": 0.5762447714805603, + "learning_rate": 6.431520105904543e-05, + "loss": 1.6457, + "step": 7491 + }, + { + "epoch": 0.4175909926982888, + "grad_norm": 0.5717265009880066, + "learning_rate": 6.430666933758353e-05, + "loss": 1.7308, + "step": 7492 + }, + { + "epoch": 0.417646730951452, + "grad_norm": 0.5314132571220398, + "learning_rate": 6.429813716239747e-05, + "loss": 1.5346, + "step": 7493 + }, + { + "epoch": 0.4177024692046151, + "grad_norm": 0.5187550187110901, + "learning_rate": 6.42896045337579e-05, + "loss": 1.541, + "step": 7494 + }, + { + "epoch": 0.41775820745777825, + "grad_norm": 0.524467945098877, + "learning_rate": 6.428107145193535e-05, + "loss": 1.6209, + "step": 7495 + }, + { + "epoch": 0.41781394571094144, + "grad_norm": 0.5283476710319519, + "learning_rate": 6.427253791720051e-05, + "loss": 1.6333, + "step": 7496 + }, + { + "epoch": 0.41786968396410457, + "grad_norm": 0.5059264302253723, + "learning_rate": 6.426400392982396e-05, + "loss": 1.4312, + "step": 7497 + }, + { + "epoch": 0.4179254222172677, + "grad_norm": 0.5070070028305054, + "learning_rate": 6.425546949007639e-05, + "loss": 1.4918, + "step": 7498 + }, + { + "epoch": 0.4179811604704309, + "grad_norm": 0.5226110219955444, + "learning_rate": 6.424693459822842e-05, + "loss": 1.6224, + "step": 7499 + }, + { + "epoch": 0.418036898723594, + "grad_norm": 0.5620803833007812, + "learning_rate": 6.423839925455077e-05, + "loss": 1.815, + "step": 7500 + }, + { + "epoch": 0.41809263697675714, + "grad_norm": 0.5102522969245911, + "learning_rate": 6.422986345931411e-05, + "loss": 1.6608, + "step": 7501 + }, + { + "epoch": 0.4181483752299203, + "grad_norm": 0.5353087782859802, + "learning_rate": 6.422132721278915e-05, + "loss": 1.5651, + "step": 7502 + }, + { + "epoch": 0.41820411348308345, + "grad_norm": 0.6161815524101257, + "learning_rate": 6.421279051524658e-05, + "loss": 1.6941, + "step": 7503 + }, + { + "epoch": 0.4182598517362466, + "grad_norm": 0.6280367970466614, + "learning_rate": 6.420425336695719e-05, + "loss": 1.8122, + "step": 7504 + }, + { + "epoch": 0.4183155899894097, + "grad_norm": 0.5285361409187317, + "learning_rate": 6.419571576819168e-05, + "loss": 1.59, + "step": 7505 + }, + { + "epoch": 0.4183713282425729, + "grad_norm": 0.5601312518119812, + "learning_rate": 6.418717771922084e-05, + "loss": 1.6675, + "step": 7506 + }, + { + "epoch": 0.418427066495736, + "grad_norm": 0.6108425855636597, + "learning_rate": 6.417863922031544e-05, + "loss": 1.9184, + "step": 7507 + }, + { + "epoch": 0.41848280474889915, + "grad_norm": 0.5752027034759521, + "learning_rate": 6.417010027174627e-05, + "loss": 1.7789, + "step": 7508 + }, + { + "epoch": 0.41853854300206234, + "grad_norm": 0.5731359720230103, + "learning_rate": 6.416156087378415e-05, + "loss": 1.6246, + "step": 7509 + }, + { + "epoch": 0.41859428125522546, + "grad_norm": 0.5547140836715698, + "learning_rate": 6.415302102669987e-05, + "loss": 1.5967, + "step": 7510 + }, + { + "epoch": 0.4186500195083886, + "grad_norm": 0.5709370970726013, + "learning_rate": 6.414448073076429e-05, + "loss": 1.6613, + "step": 7511 + }, + { + "epoch": 0.4187057577615518, + "grad_norm": 0.5591392517089844, + "learning_rate": 6.413593998624824e-05, + "loss": 1.709, + "step": 7512 + }, + { + "epoch": 0.4187614960147149, + "grad_norm": 0.5560973286628723, + "learning_rate": 6.41273987934226e-05, + "loss": 1.6281, + "step": 7513 + }, + { + "epoch": 0.41881723426787804, + "grad_norm": 0.5822799205780029, + "learning_rate": 6.411885715255823e-05, + "loss": 1.7274, + "step": 7514 + }, + { + "epoch": 0.41887297252104116, + "grad_norm": 0.5955770611763, + "learning_rate": 6.411031506392605e-05, + "loss": 1.6704, + "step": 7515 + }, + { + "epoch": 0.41892871077420435, + "grad_norm": 0.5852923393249512, + "learning_rate": 6.410177252779692e-05, + "loss": 1.7526, + "step": 7516 + }, + { + "epoch": 0.4189844490273675, + "grad_norm": 0.5543795228004456, + "learning_rate": 6.409322954444179e-05, + "loss": 1.5793, + "step": 7517 + }, + { + "epoch": 0.4190401872805306, + "grad_norm": 0.5983227491378784, + "learning_rate": 6.408468611413159e-05, + "loss": 1.8319, + "step": 7518 + }, + { + "epoch": 0.4190959255336938, + "grad_norm": 0.5510286688804626, + "learning_rate": 6.407614223713727e-05, + "loss": 1.6506, + "step": 7519 + }, + { + "epoch": 0.4191516637868569, + "grad_norm": 0.5010602474212646, + "learning_rate": 6.40675979137298e-05, + "loss": 1.5807, + "step": 7520 + }, + { + "epoch": 0.41920740204002005, + "grad_norm": 0.5825363397598267, + "learning_rate": 6.405905314418013e-05, + "loss": 1.6839, + "step": 7521 + }, + { + "epoch": 0.41926314029318323, + "grad_norm": 0.5282953977584839, + "learning_rate": 6.405050792875926e-05, + "loss": 1.5602, + "step": 7522 + }, + { + "epoch": 0.41931887854634636, + "grad_norm": 0.5378554463386536, + "learning_rate": 6.40419622677382e-05, + "loss": 1.5204, + "step": 7523 + }, + { + "epoch": 0.4193746167995095, + "grad_norm": 0.548743486404419, + "learning_rate": 6.403341616138797e-05, + "loss": 1.7654, + "step": 7524 + }, + { + "epoch": 0.4194303550526727, + "grad_norm": 0.5437180399894714, + "learning_rate": 6.40248696099796e-05, + "loss": 1.7341, + "step": 7525 + }, + { + "epoch": 0.4194860933058358, + "grad_norm": 0.7081752419471741, + "learning_rate": 6.401632261378414e-05, + "loss": 1.3932, + "step": 7526 + }, + { + "epoch": 0.41954183155899893, + "grad_norm": 0.6215348243713379, + "learning_rate": 6.400777517307265e-05, + "loss": 1.9211, + "step": 7527 + }, + { + "epoch": 0.41959756981216206, + "grad_norm": 0.5972661375999451, + "learning_rate": 6.39992272881162e-05, + "loss": 1.848, + "step": 7528 + }, + { + "epoch": 0.41965330806532525, + "grad_norm": 0.5357066988945007, + "learning_rate": 6.399067895918587e-05, + "loss": 1.6233, + "step": 7529 + }, + { + "epoch": 0.4197090463184884, + "grad_norm": 0.5154542922973633, + "learning_rate": 6.39821301865528e-05, + "loss": 1.578, + "step": 7530 + }, + { + "epoch": 0.4197647845716515, + "grad_norm": 0.524694561958313, + "learning_rate": 6.397358097048806e-05, + "loss": 1.6923, + "step": 7531 + }, + { + "epoch": 0.4198205228248147, + "grad_norm": 0.5902459025382996, + "learning_rate": 6.39650313112628e-05, + "loss": 1.7314, + "step": 7532 + }, + { + "epoch": 0.4198762610779778, + "grad_norm": 0.5320487022399902, + "learning_rate": 6.39564812091482e-05, + "loss": 1.6396, + "step": 7533 + }, + { + "epoch": 0.41993199933114095, + "grad_norm": 0.5881032943725586, + "learning_rate": 6.394793066441534e-05, + "loss": 1.8865, + "step": 7534 + }, + { + "epoch": 0.41998773758430413, + "grad_norm": 0.5616896748542786, + "learning_rate": 6.393937967733548e-05, + "loss": 1.8735, + "step": 7535 + }, + { + "epoch": 0.42004347583746726, + "grad_norm": 0.5341779589653015, + "learning_rate": 6.393082824817974e-05, + "loss": 1.635, + "step": 7536 + }, + { + "epoch": 0.4200992140906304, + "grad_norm": 0.5636286735534668, + "learning_rate": 6.392227637721937e-05, + "loss": 1.797, + "step": 7537 + }, + { + "epoch": 0.4201549523437935, + "grad_norm": 0.5334611535072327, + "learning_rate": 6.391372406472557e-05, + "loss": 1.6705, + "step": 7538 + }, + { + "epoch": 0.4202106905969567, + "grad_norm": 0.588848888874054, + "learning_rate": 6.390517131096955e-05, + "loss": 1.7877, + "step": 7539 + }, + { + "epoch": 0.42026642885011983, + "grad_norm": 0.5427910685539246, + "learning_rate": 6.389661811622258e-05, + "loss": 1.5672, + "step": 7540 + }, + { + "epoch": 0.42032216710328296, + "grad_norm": 0.6046989560127258, + "learning_rate": 6.388806448075591e-05, + "loss": 1.8186, + "step": 7541 + }, + { + "epoch": 0.42037790535644615, + "grad_norm": 0.5373850464820862, + "learning_rate": 6.38795104048408e-05, + "loss": 1.5539, + "step": 7542 + }, + { + "epoch": 0.4204336436096093, + "grad_norm": 0.5726231336593628, + "learning_rate": 6.387095588874854e-05, + "loss": 1.6383, + "step": 7543 + }, + { + "epoch": 0.4204893818627724, + "grad_norm": 0.5964796543121338, + "learning_rate": 6.386240093275044e-05, + "loss": 1.9338, + "step": 7544 + }, + { + "epoch": 0.4205451201159356, + "grad_norm": 0.5379793047904968, + "learning_rate": 6.385384553711779e-05, + "loss": 1.5479, + "step": 7545 + }, + { + "epoch": 0.4206008583690987, + "grad_norm": 0.5321194529533386, + "learning_rate": 6.384528970212196e-05, + "loss": 1.6119, + "step": 7546 + }, + { + "epoch": 0.42065659662226185, + "grad_norm": 0.6583168506622314, + "learning_rate": 6.383673342803424e-05, + "loss": 1.7555, + "step": 7547 + }, + { + "epoch": 0.42071233487542503, + "grad_norm": 0.5755535364151001, + "learning_rate": 6.382817671512603e-05, + "loss": 1.629, + "step": 7548 + }, + { + "epoch": 0.42076807312858816, + "grad_norm": 0.614747941493988, + "learning_rate": 6.381961956366865e-05, + "loss": 2.0066, + "step": 7549 + }, + { + "epoch": 0.4208238113817513, + "grad_norm": 0.5643095374107361, + "learning_rate": 6.381106197393353e-05, + "loss": 1.7497, + "step": 7550 + }, + { + "epoch": 0.4208795496349144, + "grad_norm": 0.5332757234573364, + "learning_rate": 6.380250394619205e-05, + "loss": 1.4505, + "step": 7551 + }, + { + "epoch": 0.4209352878880776, + "grad_norm": 0.5462849736213684, + "learning_rate": 6.379394548071563e-05, + "loss": 1.7164, + "step": 7552 + }, + { + "epoch": 0.42099102614124073, + "grad_norm": 0.5277321338653564, + "learning_rate": 6.378538657777565e-05, + "loss": 1.4521, + "step": 7553 + }, + { + "epoch": 0.42104676439440386, + "grad_norm": 0.5687193274497986, + "learning_rate": 6.37768272376436e-05, + "loss": 1.6832, + "step": 7554 + }, + { + "epoch": 0.42110250264756705, + "grad_norm": 0.5538173913955688, + "learning_rate": 6.376826746059092e-05, + "loss": 1.5916, + "step": 7555 + }, + { + "epoch": 0.4211582409007302, + "grad_norm": 0.5794023871421814, + "learning_rate": 6.375970724688906e-05, + "loss": 1.5985, + "step": 7556 + }, + { + "epoch": 0.4212139791538933, + "grad_norm": 0.534807026386261, + "learning_rate": 6.375114659680951e-05, + "loss": 1.5822, + "step": 7557 + }, + { + "epoch": 0.4212697174070565, + "grad_norm": 0.5474613308906555, + "learning_rate": 6.374258551062378e-05, + "loss": 1.7155, + "step": 7558 + }, + { + "epoch": 0.4213254556602196, + "grad_norm": 0.558594286441803, + "learning_rate": 6.373402398860336e-05, + "loss": 1.7239, + "step": 7559 + }, + { + "epoch": 0.42138119391338275, + "grad_norm": 0.6263135671615601, + "learning_rate": 6.372546203101977e-05, + "loss": 1.8782, + "step": 7560 + }, + { + "epoch": 0.4214369321665459, + "grad_norm": 0.5759534239768982, + "learning_rate": 6.371689963814455e-05, + "loss": 1.798, + "step": 7561 + }, + { + "epoch": 0.42149267041970906, + "grad_norm": 0.582333505153656, + "learning_rate": 6.370833681024924e-05, + "loss": 1.679, + "step": 7562 + }, + { + "epoch": 0.4215484086728722, + "grad_norm": 0.5175591707229614, + "learning_rate": 6.369977354760541e-05, + "loss": 1.6172, + "step": 7563 + }, + { + "epoch": 0.4216041469260353, + "grad_norm": 0.6253464818000793, + "learning_rate": 6.369120985048464e-05, + "loss": 1.8897, + "step": 7564 + }, + { + "epoch": 0.4216598851791985, + "grad_norm": 0.6171419024467468, + "learning_rate": 6.368264571915854e-05, + "loss": 1.9296, + "step": 7565 + }, + { + "epoch": 0.42171562343236163, + "grad_norm": 0.5854969620704651, + "learning_rate": 6.367408115389868e-05, + "loss": 1.8127, + "step": 7566 + }, + { + "epoch": 0.42177136168552476, + "grad_norm": 0.5167074203491211, + "learning_rate": 6.366551615497669e-05, + "loss": 1.4419, + "step": 7567 + }, + { + "epoch": 0.42182709993868794, + "grad_norm": 0.5605902075767517, + "learning_rate": 6.36569507226642e-05, + "loss": 1.5106, + "step": 7568 + }, + { + "epoch": 0.4218828381918511, + "grad_norm": 0.5542864799499512, + "learning_rate": 6.364838485723286e-05, + "loss": 1.6104, + "step": 7569 + }, + { + "epoch": 0.4219385764450142, + "grad_norm": 0.5589380860328674, + "learning_rate": 6.363981855895433e-05, + "loss": 1.8112, + "step": 7570 + }, + { + "epoch": 0.4219943146981774, + "grad_norm": 0.5342586040496826, + "learning_rate": 6.363125182810028e-05, + "loss": 1.668, + "step": 7571 + }, + { + "epoch": 0.4220500529513405, + "grad_norm": 0.5474408268928528, + "learning_rate": 6.36226846649424e-05, + "loss": 1.477, + "step": 7572 + }, + { + "epoch": 0.42210579120450364, + "grad_norm": 0.549768328666687, + "learning_rate": 6.361411706975237e-05, + "loss": 1.6127, + "step": 7573 + }, + { + "epoch": 0.4221615294576668, + "grad_norm": 0.5820984244346619, + "learning_rate": 6.360554904280196e-05, + "loss": 1.7687, + "step": 7574 + }, + { + "epoch": 0.42221726771082996, + "grad_norm": 0.5574761033058167, + "learning_rate": 6.359698058436282e-05, + "loss": 1.7282, + "step": 7575 + }, + { + "epoch": 0.4222730059639931, + "grad_norm": 0.5506951808929443, + "learning_rate": 6.358841169470676e-05, + "loss": 1.6214, + "step": 7576 + }, + { + "epoch": 0.4223287442171562, + "grad_norm": 0.5659124851226807, + "learning_rate": 6.35798423741055e-05, + "loss": 1.6966, + "step": 7577 + }, + { + "epoch": 0.4223844824703194, + "grad_norm": 0.5484572052955627, + "learning_rate": 6.357127262283081e-05, + "loss": 1.6683, + "step": 7578 + }, + { + "epoch": 0.42244022072348253, + "grad_norm": 0.4761580526828766, + "learning_rate": 6.356270244115448e-05, + "loss": 1.3579, + "step": 7579 + }, + { + "epoch": 0.42249595897664566, + "grad_norm": 0.5656337738037109, + "learning_rate": 6.355413182934831e-05, + "loss": 1.7506, + "step": 7580 + }, + { + "epoch": 0.42255169722980884, + "grad_norm": 0.6253755688667297, + "learning_rate": 6.35455607876841e-05, + "loss": 1.5443, + "step": 7581 + }, + { + "epoch": 0.42260743548297197, + "grad_norm": 0.5522517561912537, + "learning_rate": 6.353698931643368e-05, + "loss": 1.7318, + "step": 7582 + }, + { + "epoch": 0.4226631737361351, + "grad_norm": 0.5824682712554932, + "learning_rate": 6.352841741586888e-05, + "loss": 1.9499, + "step": 7583 + }, + { + "epoch": 0.42271891198929823, + "grad_norm": 0.6166448593139648, + "learning_rate": 6.351984508626155e-05, + "loss": 1.6598, + "step": 7584 + }, + { + "epoch": 0.4227746502424614, + "grad_norm": 0.6640730500221252, + "learning_rate": 6.351127232788357e-05, + "loss": 1.9022, + "step": 7585 + }, + { + "epoch": 0.42283038849562454, + "grad_norm": 0.5395544171333313, + "learning_rate": 6.350269914100681e-05, + "loss": 1.8523, + "step": 7586 + }, + { + "epoch": 0.42288612674878767, + "grad_norm": 0.597951352596283, + "learning_rate": 6.349412552590317e-05, + "loss": 1.7423, + "step": 7587 + }, + { + "epoch": 0.42294186500195086, + "grad_norm": 0.5310340523719788, + "learning_rate": 6.348555148284452e-05, + "loss": 1.6669, + "step": 7588 + }, + { + "epoch": 0.422997603255114, + "grad_norm": 0.563275933265686, + "learning_rate": 6.347697701210281e-05, + "loss": 1.8138, + "step": 7589 + }, + { + "epoch": 0.4230533415082771, + "grad_norm": 0.5225051641464233, + "learning_rate": 6.346840211394998e-05, + "loss": 1.5228, + "step": 7590 + }, + { + "epoch": 0.4231090797614403, + "grad_norm": 0.5949013233184814, + "learning_rate": 6.345982678865795e-05, + "loss": 1.8378, + "step": 7591 + }, + { + "epoch": 0.4231648180146034, + "grad_norm": 0.6444050073623657, + "learning_rate": 6.345125103649869e-05, + "loss": 1.9561, + "step": 7592 + }, + { + "epoch": 0.42322055626776656, + "grad_norm": 0.538077712059021, + "learning_rate": 6.344267485774417e-05, + "loss": 1.6172, + "step": 7593 + }, + { + "epoch": 0.42327629452092974, + "grad_norm": 0.5770418047904968, + "learning_rate": 6.34340982526664e-05, + "loss": 1.7064, + "step": 7594 + }, + { + "epoch": 0.42333203277409287, + "grad_norm": 0.5491243600845337, + "learning_rate": 6.342552122153734e-05, + "loss": 1.5869, + "step": 7595 + }, + { + "epoch": 0.423387771027256, + "grad_norm": 0.5911741852760315, + "learning_rate": 6.3416943764629e-05, + "loss": 1.4539, + "step": 7596 + }, + { + "epoch": 0.42344350928041913, + "grad_norm": 0.5493375062942505, + "learning_rate": 6.340836588221347e-05, + "loss": 1.2324, + "step": 7597 + }, + { + "epoch": 0.4234992475335823, + "grad_norm": 0.5272154808044434, + "learning_rate": 6.339978757456274e-05, + "loss": 1.7336, + "step": 7598 + }, + { + "epoch": 0.42355498578674544, + "grad_norm": 0.6132648587226868, + "learning_rate": 6.339120884194886e-05, + "loss": 1.8399, + "step": 7599 + }, + { + "epoch": 0.42361072403990857, + "grad_norm": 0.6002299189567566, + "learning_rate": 6.338262968464394e-05, + "loss": 1.7355, + "step": 7600 + }, + { + "epoch": 0.42366646229307175, + "grad_norm": 0.5747309327125549, + "learning_rate": 6.337405010292e-05, + "loss": 1.5466, + "step": 7601 + }, + { + "epoch": 0.4237222005462349, + "grad_norm": 0.6044133901596069, + "learning_rate": 6.336547009704919e-05, + "loss": 1.894, + "step": 7602 + }, + { + "epoch": 0.423777938799398, + "grad_norm": 0.6029581427574158, + "learning_rate": 6.335688966730358e-05, + "loss": 1.7874, + "step": 7603 + }, + { + "epoch": 0.4238336770525612, + "grad_norm": 0.5374162197113037, + "learning_rate": 6.334830881395533e-05, + "loss": 1.4537, + "step": 7604 + }, + { + "epoch": 0.4238894153057243, + "grad_norm": 0.5794885158538818, + "learning_rate": 6.333972753727653e-05, + "loss": 1.6731, + "step": 7605 + }, + { + "epoch": 0.42394515355888746, + "grad_norm": 0.6136147379875183, + "learning_rate": 6.333114583753936e-05, + "loss": 2.0005, + "step": 7606 + }, + { + "epoch": 0.4240008918120506, + "grad_norm": 0.6465775370597839, + "learning_rate": 6.332256371501597e-05, + "loss": 1.7024, + "step": 7607 + }, + { + "epoch": 0.42405663006521377, + "grad_norm": 0.4953748285770416, + "learning_rate": 6.331398116997851e-05, + "loss": 1.4046, + "step": 7608 + }, + { + "epoch": 0.4241123683183769, + "grad_norm": 0.5147947669029236, + "learning_rate": 6.330539820269921e-05, + "loss": 1.7066, + "step": 7609 + }, + { + "epoch": 0.42416810657154, + "grad_norm": 0.5854727029800415, + "learning_rate": 6.329681481345026e-05, + "loss": 1.7871, + "step": 7610 + }, + { + "epoch": 0.4242238448247032, + "grad_norm": 0.5421152710914612, + "learning_rate": 6.328823100250386e-05, + "loss": 1.6782, + "step": 7611 + }, + { + "epoch": 0.42427958307786634, + "grad_norm": 0.5201201438903809, + "learning_rate": 6.327964677013224e-05, + "loss": 1.6405, + "step": 7612 + }, + { + "epoch": 0.42433532133102947, + "grad_norm": 0.5656992197036743, + "learning_rate": 6.327106211660769e-05, + "loss": 1.798, + "step": 7613 + }, + { + "epoch": 0.42439105958419265, + "grad_norm": 0.5751951336860657, + "learning_rate": 6.326247704220239e-05, + "loss": 1.6055, + "step": 7614 + }, + { + "epoch": 0.4244467978373558, + "grad_norm": 0.546371579170227, + "learning_rate": 6.325389154718865e-05, + "loss": 1.7596, + "step": 7615 + }, + { + "epoch": 0.4245025360905189, + "grad_norm": 0.5406731367111206, + "learning_rate": 6.324530563183875e-05, + "loss": 1.6401, + "step": 7616 + }, + { + "epoch": 0.4245582743436821, + "grad_norm": 0.5809882879257202, + "learning_rate": 6.323671929642498e-05, + "loss": 1.868, + "step": 7617 + }, + { + "epoch": 0.4246140125968452, + "grad_norm": 0.540643572807312, + "learning_rate": 6.322813254121964e-05, + "loss": 1.715, + "step": 7618 + }, + { + "epoch": 0.42466975085000835, + "grad_norm": 0.5267550945281982, + "learning_rate": 6.321954536649508e-05, + "loss": 1.5837, + "step": 7619 + }, + { + "epoch": 0.4247254891031715, + "grad_norm": 0.5602602958679199, + "learning_rate": 6.32109577725236e-05, + "loss": 1.7406, + "step": 7620 + }, + { + "epoch": 0.42478122735633467, + "grad_norm": 0.5607280731201172, + "learning_rate": 6.320236975957757e-05, + "loss": 1.6099, + "step": 7621 + }, + { + "epoch": 0.4248369656094978, + "grad_norm": 0.5364249348640442, + "learning_rate": 6.319378132792935e-05, + "loss": 1.5277, + "step": 7622 + }, + { + "epoch": 0.4248927038626609, + "grad_norm": 0.5527327656745911, + "learning_rate": 6.318519247785131e-05, + "loss": 1.7702, + "step": 7623 + }, + { + "epoch": 0.4249484421158241, + "grad_norm": 0.5770801901817322, + "learning_rate": 6.317660320961585e-05, + "loss": 1.6098, + "step": 7624 + }, + { + "epoch": 0.42500418036898724, + "grad_norm": 0.5606113076210022, + "learning_rate": 6.316801352349534e-05, + "loss": 1.6451, + "step": 7625 + }, + { + "epoch": 0.42505991862215037, + "grad_norm": 0.6124593615531921, + "learning_rate": 6.315942341976223e-05, + "loss": 1.9987, + "step": 7626 + }, + { + "epoch": 0.42511565687531355, + "grad_norm": 0.5524605512619019, + "learning_rate": 6.315083289868892e-05, + "loss": 1.6352, + "step": 7627 + }, + { + "epoch": 0.4251713951284767, + "grad_norm": 0.5734837651252747, + "learning_rate": 6.314224196054787e-05, + "loss": 1.8757, + "step": 7628 + }, + { + "epoch": 0.4252271333816398, + "grad_norm": 0.64513099193573, + "learning_rate": 6.313365060561153e-05, + "loss": 2.0665, + "step": 7629 + }, + { + "epoch": 0.42528287163480294, + "grad_norm": 0.5457690954208374, + "learning_rate": 6.312505883415238e-05, + "loss": 1.6602, + "step": 7630 + }, + { + "epoch": 0.4253386098879661, + "grad_norm": 0.6007886528968811, + "learning_rate": 6.311646664644288e-05, + "loss": 1.7241, + "step": 7631 + }, + { + "epoch": 0.42539434814112925, + "grad_norm": 0.5715931057929993, + "learning_rate": 6.310787404275553e-05, + "loss": 1.7581, + "step": 7632 + }, + { + "epoch": 0.4254500863942924, + "grad_norm": 0.5710930228233337, + "learning_rate": 6.309928102336284e-05, + "loss": 1.7147, + "step": 7633 + }, + { + "epoch": 0.42550582464745557, + "grad_norm": 0.5583118796348572, + "learning_rate": 6.309068758853732e-05, + "loss": 1.6103, + "step": 7634 + }, + { + "epoch": 0.4255615629006187, + "grad_norm": 0.5537952184677124, + "learning_rate": 6.308209373855154e-05, + "loss": 1.6947, + "step": 7635 + }, + { + "epoch": 0.4256173011537818, + "grad_norm": 0.5451967716217041, + "learning_rate": 6.3073499473678e-05, + "loss": 1.6384, + "step": 7636 + }, + { + "epoch": 0.425673039406945, + "grad_norm": 0.5317254066467285, + "learning_rate": 6.30649047941893e-05, + "loss": 1.5643, + "step": 7637 + }, + { + "epoch": 0.42572877766010814, + "grad_norm": 0.5423393845558167, + "learning_rate": 6.305630970035796e-05, + "loss": 1.5257, + "step": 7638 + }, + { + "epoch": 0.42578451591327127, + "grad_norm": 0.5897427797317505, + "learning_rate": 6.304771419245663e-05, + "loss": 1.8738, + "step": 7639 + }, + { + "epoch": 0.42584025416643445, + "grad_norm": 0.5559675097465515, + "learning_rate": 6.303911827075786e-05, + "loss": 1.8562, + "step": 7640 + }, + { + "epoch": 0.4258959924195976, + "grad_norm": 0.5857858061790466, + "learning_rate": 6.303052193553429e-05, + "loss": 1.7146, + "step": 7641 + }, + { + "epoch": 0.4259517306727607, + "grad_norm": 0.6495271325111389, + "learning_rate": 6.302192518705853e-05, + "loss": 1.7639, + "step": 7642 + }, + { + "epoch": 0.42600746892592384, + "grad_norm": 0.5638108253479004, + "learning_rate": 6.301332802560325e-05, + "loss": 1.5804, + "step": 7643 + }, + { + "epoch": 0.426063207179087, + "grad_norm": 0.5066633224487305, + "learning_rate": 6.300473045144107e-05, + "loss": 1.4344, + "step": 7644 + }, + { + "epoch": 0.42611894543225015, + "grad_norm": 0.5637665390968323, + "learning_rate": 6.299613246484464e-05, + "loss": 1.6573, + "step": 7645 + }, + { + "epoch": 0.4261746836854133, + "grad_norm": 0.5206940174102783, + "learning_rate": 6.298753406608668e-05, + "loss": 1.5995, + "step": 7646 + }, + { + "epoch": 0.42623042193857646, + "grad_norm": 0.5374553799629211, + "learning_rate": 6.297893525543986e-05, + "loss": 1.7107, + "step": 7647 + }, + { + "epoch": 0.4262861601917396, + "grad_norm": 0.5552041530609131, + "learning_rate": 6.297033603317689e-05, + "loss": 1.6734, + "step": 7648 + }, + { + "epoch": 0.4263418984449027, + "grad_norm": 0.5269225239753723, + "learning_rate": 6.296173639957045e-05, + "loss": 1.64, + "step": 7649 + }, + { + "epoch": 0.4263976366980659, + "grad_norm": 0.5553382635116577, + "learning_rate": 6.295313635489335e-05, + "loss": 1.3837, + "step": 7650 + }, + { + "epoch": 0.42645337495122904, + "grad_norm": 0.5205674171447754, + "learning_rate": 6.294453589941826e-05, + "loss": 1.6142, + "step": 7651 + }, + { + "epoch": 0.42650911320439217, + "grad_norm": 0.6198689937591553, + "learning_rate": 6.2935935033418e-05, + "loss": 1.7297, + "step": 7652 + }, + { + "epoch": 0.4265648514575553, + "grad_norm": 0.556909441947937, + "learning_rate": 6.292733375716526e-05, + "loss": 1.7119, + "step": 7653 + }, + { + "epoch": 0.4266205897107185, + "grad_norm": 0.5496246218681335, + "learning_rate": 6.291873207093287e-05, + "loss": 1.6478, + "step": 7654 + }, + { + "epoch": 0.4266763279638816, + "grad_norm": 0.5758047103881836, + "learning_rate": 6.291012997499362e-05, + "loss": 1.8439, + "step": 7655 + }, + { + "epoch": 0.42673206621704474, + "grad_norm": 0.5833730697631836, + "learning_rate": 6.290152746962034e-05, + "loss": 1.6251, + "step": 7656 + }, + { + "epoch": 0.4267878044702079, + "grad_norm": 0.509559690952301, + "learning_rate": 6.289292455508582e-05, + "loss": 1.6364, + "step": 7657 + }, + { + "epoch": 0.42684354272337105, + "grad_norm": 0.5244433879852295, + "learning_rate": 6.28843212316629e-05, + "loss": 1.4855, + "step": 7658 + }, + { + "epoch": 0.4268992809765342, + "grad_norm": 0.5262942314147949, + "learning_rate": 6.287571749962444e-05, + "loss": 1.6034, + "step": 7659 + }, + { + "epoch": 0.42695501922969736, + "grad_norm": 0.592850923538208, + "learning_rate": 6.286711335924326e-05, + "loss": 2.0333, + "step": 7660 + }, + { + "epoch": 0.4270107574828605, + "grad_norm": 0.5585233569145203, + "learning_rate": 6.28585088107923e-05, + "loss": 1.7037, + "step": 7661 + }, + { + "epoch": 0.4270664957360236, + "grad_norm": 0.5201496481895447, + "learning_rate": 6.284990385454439e-05, + "loss": 1.5226, + "step": 7662 + }, + { + "epoch": 0.4271222339891868, + "grad_norm": 0.5410779714584351, + "learning_rate": 6.284129849077247e-05, + "loss": 1.6186, + "step": 7663 + }, + { + "epoch": 0.42717797224234993, + "grad_norm": 0.5643417835235596, + "learning_rate": 6.283269271974941e-05, + "loss": 1.7211, + "step": 7664 + }, + { + "epoch": 0.42723371049551306, + "grad_norm": 0.5603637099266052, + "learning_rate": 6.282408654174818e-05, + "loss": 1.6978, + "step": 7665 + }, + { + "epoch": 0.4272894487486762, + "grad_norm": 0.5303884744644165, + "learning_rate": 6.281547995704168e-05, + "loss": 1.5544, + "step": 7666 + }, + { + "epoch": 0.4273451870018394, + "grad_norm": 0.5895907282829285, + "learning_rate": 6.280687296590287e-05, + "loss": 1.697, + "step": 7667 + }, + { + "epoch": 0.4274009252550025, + "grad_norm": 0.566055953502655, + "learning_rate": 6.279826556860472e-05, + "loss": 1.6596, + "step": 7668 + }, + { + "epoch": 0.42745666350816564, + "grad_norm": 0.5401179790496826, + "learning_rate": 6.278965776542021e-05, + "loss": 1.7029, + "step": 7669 + }, + { + "epoch": 0.4275124017613288, + "grad_norm": 0.6178464889526367, + "learning_rate": 6.278104955662234e-05, + "loss": 1.7344, + "step": 7670 + }, + { + "epoch": 0.42756814001449195, + "grad_norm": 0.5440572500228882, + "learning_rate": 6.277244094248407e-05, + "loss": 1.7182, + "step": 7671 + }, + { + "epoch": 0.4276238782676551, + "grad_norm": 0.5953531265258789, + "learning_rate": 6.276383192327846e-05, + "loss": 1.7045, + "step": 7672 + }, + { + "epoch": 0.42767961652081826, + "grad_norm": 0.5182901620864868, + "learning_rate": 6.27552224992785e-05, + "loss": 1.5657, + "step": 7673 + }, + { + "epoch": 0.4277353547739814, + "grad_norm": 0.5608685612678528, + "learning_rate": 6.274661267075728e-05, + "loss": 1.701, + "step": 7674 + }, + { + "epoch": 0.4277910930271445, + "grad_norm": 0.5933842658996582, + "learning_rate": 6.27380024379878e-05, + "loss": 1.804, + "step": 7675 + }, + { + "epoch": 0.42784683128030765, + "grad_norm": 0.586521327495575, + "learning_rate": 6.272939180124317e-05, + "loss": 1.7744, + "step": 7676 + }, + { + "epoch": 0.42790256953347083, + "grad_norm": 0.6096509695053101, + "learning_rate": 6.272078076079644e-05, + "loss": 1.9837, + "step": 7677 + }, + { + "epoch": 0.42795830778663396, + "grad_norm": 0.6212565302848816, + "learning_rate": 6.27121693169207e-05, + "loss": 1.8042, + "step": 7678 + }, + { + "epoch": 0.4280140460397971, + "grad_norm": 0.5542432069778442, + "learning_rate": 6.270355746988908e-05, + "loss": 1.6222, + "step": 7679 + }, + { + "epoch": 0.4280697842929603, + "grad_norm": 0.5913196802139282, + "learning_rate": 6.269494521997467e-05, + "loss": 1.6313, + "step": 7680 + }, + { + "epoch": 0.4281255225461234, + "grad_norm": 0.5573778748512268, + "learning_rate": 6.268633256745063e-05, + "loss": 1.7364, + "step": 7681 + }, + { + "epoch": 0.42818126079928653, + "grad_norm": 0.5151004195213318, + "learning_rate": 6.267771951259009e-05, + "loss": 1.8938, + "step": 7682 + }, + { + "epoch": 0.4282369990524497, + "grad_norm": 0.5424497127532959, + "learning_rate": 6.26691060556662e-05, + "loss": 1.706, + "step": 7683 + }, + { + "epoch": 0.42829273730561285, + "grad_norm": 0.5353766083717346, + "learning_rate": 6.266049219695211e-05, + "loss": 1.6015, + "step": 7684 + }, + { + "epoch": 0.428348475558776, + "grad_norm": 0.5848101377487183, + "learning_rate": 6.265187793672105e-05, + "loss": 1.9252, + "step": 7685 + }, + { + "epoch": 0.42840421381193916, + "grad_norm": 0.5816083550453186, + "learning_rate": 6.264326327524617e-05, + "loss": 1.7076, + "step": 7686 + }, + { + "epoch": 0.4284599520651023, + "grad_norm": 0.595378577709198, + "learning_rate": 6.263464821280071e-05, + "loss": 1.8343, + "step": 7687 + }, + { + "epoch": 0.4285156903182654, + "grad_norm": 0.5391969084739685, + "learning_rate": 6.262603274965786e-05, + "loss": 1.5771, + "step": 7688 + }, + { + "epoch": 0.42857142857142855, + "grad_norm": 0.5316036939620972, + "learning_rate": 6.261741688609087e-05, + "loss": 1.6646, + "step": 7689 + }, + { + "epoch": 0.42862716682459173, + "grad_norm": 0.5671446323394775, + "learning_rate": 6.260880062237299e-05, + "loss": 1.8235, + "step": 7690 + }, + { + "epoch": 0.42868290507775486, + "grad_norm": 0.5752628445625305, + "learning_rate": 6.260018395877747e-05, + "loss": 1.7776, + "step": 7691 + }, + { + "epoch": 0.428738643330918, + "grad_norm": 0.5416520833969116, + "learning_rate": 6.259156689557757e-05, + "loss": 1.5817, + "step": 7692 + }, + { + "epoch": 0.4287943815840812, + "grad_norm": 0.5795433521270752, + "learning_rate": 6.258294943304656e-05, + "loss": 1.6236, + "step": 7693 + }, + { + "epoch": 0.4288501198372443, + "grad_norm": 0.5906192064285278, + "learning_rate": 6.257433157145779e-05, + "loss": 1.8114, + "step": 7694 + }, + { + "epoch": 0.42890585809040743, + "grad_norm": 0.589847207069397, + "learning_rate": 6.256571331108454e-05, + "loss": 1.7796, + "step": 7695 + }, + { + "epoch": 0.4289615963435706, + "grad_norm": 0.5236275792121887, + "learning_rate": 6.25570946522001e-05, + "loss": 1.4089, + "step": 7696 + }, + { + "epoch": 0.42901733459673375, + "grad_norm": 0.5735291838645935, + "learning_rate": 6.254847559507783e-05, + "loss": 1.8332, + "step": 7697 + }, + { + "epoch": 0.4290730728498969, + "grad_norm": 0.5835584998130798, + "learning_rate": 6.253985613999111e-05, + "loss": 1.7905, + "step": 7698 + }, + { + "epoch": 0.42912881110306, + "grad_norm": 0.5706406831741333, + "learning_rate": 6.253123628721324e-05, + "loss": 1.7185, + "step": 7699 + }, + { + "epoch": 0.4291845493562232, + "grad_norm": 0.6053869724273682, + "learning_rate": 6.252261603701762e-05, + "loss": 1.6092, + "step": 7700 + }, + { + "epoch": 0.4292402876093863, + "grad_norm": 0.559517502784729, + "learning_rate": 6.251399538967764e-05, + "loss": 1.6353, + "step": 7701 + }, + { + "epoch": 0.42929602586254945, + "grad_norm": 0.5170453190803528, + "learning_rate": 6.250537434546668e-05, + "loss": 1.5933, + "step": 7702 + }, + { + "epoch": 0.42935176411571263, + "grad_norm": 0.5452066659927368, + "learning_rate": 6.249675290465817e-05, + "loss": 1.5875, + "step": 7703 + }, + { + "epoch": 0.42940750236887576, + "grad_norm": 0.5306586623191833, + "learning_rate": 6.248813106752551e-05, + "loss": 1.4277, + "step": 7704 + }, + { + "epoch": 0.4294632406220389, + "grad_norm": 0.601926863193512, + "learning_rate": 6.247950883434214e-05, + "loss": 1.667, + "step": 7705 + }, + { + "epoch": 0.4295189788752021, + "grad_norm": 0.6103541254997253, + "learning_rate": 6.24708862053815e-05, + "loss": 1.6387, + "step": 7706 + }, + { + "epoch": 0.4295747171283652, + "grad_norm": 0.5850464701652527, + "learning_rate": 6.246226318091708e-05, + "loss": 1.5703, + "step": 7707 + }, + { + "epoch": 0.42963045538152833, + "grad_norm": 0.564311683177948, + "learning_rate": 6.245363976122232e-05, + "loss": 1.4084, + "step": 7708 + }, + { + "epoch": 0.4296861936346915, + "grad_norm": 0.5692956447601318, + "learning_rate": 6.244501594657073e-05, + "loss": 1.6056, + "step": 7709 + }, + { + "epoch": 0.42974193188785464, + "grad_norm": 0.48438626527786255, + "learning_rate": 6.243639173723577e-05, + "loss": 1.3122, + "step": 7710 + }, + { + "epoch": 0.4297976701410178, + "grad_norm": 0.5293724536895752, + "learning_rate": 6.2427767133491e-05, + "loss": 1.5922, + "step": 7711 + }, + { + "epoch": 0.4298534083941809, + "grad_norm": 0.5632352232933044, + "learning_rate": 6.241914213560988e-05, + "loss": 1.7423, + "step": 7712 + }, + { + "epoch": 0.4299091466473441, + "grad_norm": 0.5172026753425598, + "learning_rate": 6.241051674386602e-05, + "loss": 1.4298, + "step": 7713 + }, + { + "epoch": 0.4299648849005072, + "grad_norm": 0.5803625583648682, + "learning_rate": 6.24018909585329e-05, + "loss": 1.6772, + "step": 7714 + }, + { + "epoch": 0.43002062315367034, + "grad_norm": 0.530988335609436, + "learning_rate": 6.239326477988413e-05, + "loss": 1.7007, + "step": 7715 + }, + { + "epoch": 0.43007636140683353, + "grad_norm": 0.5132483243942261, + "learning_rate": 6.238463820819325e-05, + "loss": 1.5829, + "step": 7716 + }, + { + "epoch": 0.43013209965999666, + "grad_norm": 0.6094499230384827, + "learning_rate": 6.237601124373385e-05, + "loss": 1.7885, + "step": 7717 + }, + { + "epoch": 0.4301878379131598, + "grad_norm": 0.5744908452033997, + "learning_rate": 6.236738388677952e-05, + "loss": 1.7993, + "step": 7718 + }, + { + "epoch": 0.43024357616632297, + "grad_norm": 0.6198621392250061, + "learning_rate": 6.23587561376039e-05, + "loss": 1.8437, + "step": 7719 + }, + { + "epoch": 0.4302993144194861, + "grad_norm": 0.5478682518005371, + "learning_rate": 6.235012799648057e-05, + "loss": 1.7246, + "step": 7720 + }, + { + "epoch": 0.43035505267264923, + "grad_norm": 0.5738255381584167, + "learning_rate": 6.23414994636832e-05, + "loss": 1.7322, + "step": 7721 + }, + { + "epoch": 0.43041079092581236, + "grad_norm": 0.6019119024276733, + "learning_rate": 6.233287053948543e-05, + "loss": 1.6743, + "step": 7722 + }, + { + "epoch": 0.43046652917897554, + "grad_norm": 0.5403818488121033, + "learning_rate": 6.23242412241609e-05, + "loss": 1.5439, + "step": 7723 + }, + { + "epoch": 0.43052226743213867, + "grad_norm": 0.5892661213874817, + "learning_rate": 6.23156115179833e-05, + "loss": 2.0254, + "step": 7724 + }, + { + "epoch": 0.4305780056853018, + "grad_norm": 0.6273830533027649, + "learning_rate": 6.230698142122629e-05, + "loss": 1.6787, + "step": 7725 + }, + { + "epoch": 0.430633743938465, + "grad_norm": 0.5560447573661804, + "learning_rate": 6.229835093416361e-05, + "loss": 1.711, + "step": 7726 + }, + { + "epoch": 0.4306894821916281, + "grad_norm": 0.5284225344657898, + "learning_rate": 6.228972005706893e-05, + "loss": 1.5921, + "step": 7727 + }, + { + "epoch": 0.43074522044479124, + "grad_norm": 0.5550575852394104, + "learning_rate": 6.228108879021599e-05, + "loss": 1.5798, + "step": 7728 + }, + { + "epoch": 0.43080095869795443, + "grad_norm": 0.5931698083877563, + "learning_rate": 6.22724571338785e-05, + "loss": 2.0899, + "step": 7729 + }, + { + "epoch": 0.43085669695111756, + "grad_norm": 0.5341006517410278, + "learning_rate": 6.226382508833026e-05, + "loss": 1.6937, + "step": 7730 + }, + { + "epoch": 0.4309124352042807, + "grad_norm": 0.5837813019752502, + "learning_rate": 6.225519265384495e-05, + "loss": 1.7363, + "step": 7731 + }, + { + "epoch": 0.43096817345744387, + "grad_norm": 0.5665456056594849, + "learning_rate": 6.22465598306964e-05, + "loss": 1.6438, + "step": 7732 + }, + { + "epoch": 0.431023911710607, + "grad_norm": 0.7508494257926941, + "learning_rate": 6.223792661915838e-05, + "loss": 1.6701, + "step": 7733 + }, + { + "epoch": 0.43107964996377013, + "grad_norm": 0.5742450952529907, + "learning_rate": 6.222929301950466e-05, + "loss": 1.6195, + "step": 7734 + }, + { + "epoch": 0.43113538821693326, + "grad_norm": 0.5885428190231323, + "learning_rate": 6.222065903200908e-05, + "loss": 1.852, + "step": 7735 + }, + { + "epoch": 0.43119112647009644, + "grad_norm": 0.6054401993751526, + "learning_rate": 6.221202465694545e-05, + "loss": 1.9739, + "step": 7736 + }, + { + "epoch": 0.43124686472325957, + "grad_norm": 0.5252482891082764, + "learning_rate": 6.22033898945876e-05, + "loss": 1.5755, + "step": 7737 + }, + { + "epoch": 0.4313026029764227, + "grad_norm": 0.5708329677581787, + "learning_rate": 6.219475474520936e-05, + "loss": 1.7666, + "step": 7738 + }, + { + "epoch": 0.4313583412295859, + "grad_norm": 0.5406473278999329, + "learning_rate": 6.218611920908461e-05, + "loss": 1.6721, + "step": 7739 + }, + { + "epoch": 0.431414079482749, + "grad_norm": 0.5870915055274963, + "learning_rate": 6.21774832864872e-05, + "loss": 1.635, + "step": 7740 + }, + { + "epoch": 0.43146981773591214, + "grad_norm": 0.5580663681030273, + "learning_rate": 6.216884697769104e-05, + "loss": 1.7878, + "step": 7741 + }, + { + "epoch": 0.4315255559890753, + "grad_norm": 0.6071598529815674, + "learning_rate": 6.216021028296999e-05, + "loss": 1.817, + "step": 7742 + }, + { + "epoch": 0.43158129424223846, + "grad_norm": 0.5742529630661011, + "learning_rate": 6.215157320259798e-05, + "loss": 1.6086, + "step": 7743 + }, + { + "epoch": 0.4316370324954016, + "grad_norm": 0.5802901387214661, + "learning_rate": 6.214293573684889e-05, + "loss": 1.7647, + "step": 7744 + }, + { + "epoch": 0.4316927707485647, + "grad_norm": 0.6176155209541321, + "learning_rate": 6.21342978859967e-05, + "loss": 2.0043, + "step": 7745 + }, + { + "epoch": 0.4317485090017279, + "grad_norm": 0.6097760200500488, + "learning_rate": 6.212565965031532e-05, + "loss": 1.7955, + "step": 7746 + }, + { + "epoch": 0.431804247254891, + "grad_norm": 0.5612444877624512, + "learning_rate": 6.211702103007871e-05, + "loss": 1.6242, + "step": 7747 + }, + { + "epoch": 0.43185998550805416, + "grad_norm": 0.6074878573417664, + "learning_rate": 6.210838202556085e-05, + "loss": 1.5951, + "step": 7748 + }, + { + "epoch": 0.43191572376121734, + "grad_norm": 0.5827562808990479, + "learning_rate": 6.209974263703569e-05, + "loss": 1.849, + "step": 7749 + }, + { + "epoch": 0.43197146201438047, + "grad_norm": 0.5888208746910095, + "learning_rate": 6.209110286477727e-05, + "loss": 1.7899, + "step": 7750 + }, + { + "epoch": 0.4320272002675436, + "grad_norm": 0.5709846019744873, + "learning_rate": 6.208246270905952e-05, + "loss": 1.8588, + "step": 7751 + }, + { + "epoch": 0.4320829385207068, + "grad_norm": 0.5687053203582764, + "learning_rate": 6.207382217015655e-05, + "loss": 1.7115, + "step": 7752 + }, + { + "epoch": 0.4321386767738699, + "grad_norm": 0.5730668306350708, + "learning_rate": 6.206518124834231e-05, + "loss": 1.7556, + "step": 7753 + }, + { + "epoch": 0.43219441502703304, + "grad_norm": 0.48593658208847046, + "learning_rate": 6.205653994389087e-05, + "loss": 1.4447, + "step": 7754 + }, + { + "epoch": 0.4322501532801962, + "grad_norm": 0.5364407896995544, + "learning_rate": 6.204789825707626e-05, + "loss": 1.7097, + "step": 7755 + }, + { + "epoch": 0.43230589153335935, + "grad_norm": 0.5474497079849243, + "learning_rate": 6.203925618817258e-05, + "loss": 1.6242, + "step": 7756 + }, + { + "epoch": 0.4323616297865225, + "grad_norm": 0.5366718173027039, + "learning_rate": 6.203061373745388e-05, + "loss": 1.6055, + "step": 7757 + }, + { + "epoch": 0.4324173680396856, + "grad_norm": 0.6138222813606262, + "learning_rate": 6.202197090519428e-05, + "loss": 1.6537, + "step": 7758 + }, + { + "epoch": 0.4324731062928488, + "grad_norm": 0.5678575038909912, + "learning_rate": 6.201332769166782e-05, + "loss": 1.5895, + "step": 7759 + }, + { + "epoch": 0.4325288445460119, + "grad_norm": 0.5866283178329468, + "learning_rate": 6.200468409714866e-05, + "loss": 1.6663, + "step": 7760 + }, + { + "epoch": 0.43258458279917505, + "grad_norm": 0.5652245879173279, + "learning_rate": 6.199604012191093e-05, + "loss": 1.6446, + "step": 7761 + }, + { + "epoch": 0.43264032105233824, + "grad_norm": 0.5838261842727661, + "learning_rate": 6.198739576622872e-05, + "loss": 1.8155, + "step": 7762 + }, + { + "epoch": 0.43269605930550137, + "grad_norm": 0.537699818611145, + "learning_rate": 6.197875103037623e-05, + "loss": 1.6124, + "step": 7763 + }, + { + "epoch": 0.4327517975586645, + "grad_norm": 0.6197475790977478, + "learning_rate": 6.197010591462758e-05, + "loss": 1.72, + "step": 7764 + }, + { + "epoch": 0.4328075358118277, + "grad_norm": 0.5581753253936768, + "learning_rate": 6.196146041925697e-05, + "loss": 1.6948, + "step": 7765 + }, + { + "epoch": 0.4328632740649908, + "grad_norm": 0.5555060505867004, + "learning_rate": 6.195281454453858e-05, + "loss": 1.5966, + "step": 7766 + }, + { + "epoch": 0.43291901231815394, + "grad_norm": 0.5592203140258789, + "learning_rate": 6.19441682907466e-05, + "loss": 1.8594, + "step": 7767 + }, + { + "epoch": 0.43297475057131707, + "grad_norm": 0.5492338538169861, + "learning_rate": 6.193552165815525e-05, + "loss": 1.707, + "step": 7768 + }, + { + "epoch": 0.43303048882448025, + "grad_norm": 0.5119403600692749, + "learning_rate": 6.192687464703873e-05, + "loss": 1.3713, + "step": 7769 + }, + { + "epoch": 0.4330862270776434, + "grad_norm": 0.6076398491859436, + "learning_rate": 6.191822725767129e-05, + "loss": 1.7667, + "step": 7770 + }, + { + "epoch": 0.4331419653308065, + "grad_norm": 0.5796701312065125, + "learning_rate": 6.190957949032716e-05, + "loss": 1.688, + "step": 7771 + }, + { + "epoch": 0.4331977035839697, + "grad_norm": 0.5363877415657043, + "learning_rate": 6.190093134528061e-05, + "loss": 1.6081, + "step": 7772 + }, + { + "epoch": 0.4332534418371328, + "grad_norm": 0.5938536524772644, + "learning_rate": 6.189228282280592e-05, + "loss": 1.7503, + "step": 7773 + }, + { + "epoch": 0.43330918009029595, + "grad_norm": 0.5643225312232971, + "learning_rate": 6.188363392317734e-05, + "loss": 1.7848, + "step": 7774 + }, + { + "epoch": 0.43336491834345914, + "grad_norm": 0.5852196216583252, + "learning_rate": 6.187498464666917e-05, + "loss": 1.8112, + "step": 7775 + }, + { + "epoch": 0.43342065659662227, + "grad_norm": 0.5774117112159729, + "learning_rate": 6.186633499355576e-05, + "loss": 1.5268, + "step": 7776 + }, + { + "epoch": 0.4334763948497854, + "grad_norm": 0.5480836033821106, + "learning_rate": 6.185768496411135e-05, + "loss": 1.6839, + "step": 7777 + }, + { + "epoch": 0.4335321331029486, + "grad_norm": 0.5210850834846497, + "learning_rate": 6.184903455861032e-05, + "loss": 1.592, + "step": 7778 + }, + { + "epoch": 0.4335878713561117, + "grad_norm": 0.532539427280426, + "learning_rate": 6.1840383777327e-05, + "loss": 1.7992, + "step": 7779 + }, + { + "epoch": 0.43364360960927484, + "grad_norm": 0.5546075105667114, + "learning_rate": 6.183173262053575e-05, + "loss": 1.76, + "step": 7780 + }, + { + "epoch": 0.43369934786243797, + "grad_norm": 0.5634498000144958, + "learning_rate": 6.182308108851091e-05, + "loss": 1.5548, + "step": 7781 + }, + { + "epoch": 0.43375508611560115, + "grad_norm": 0.5091983079910278, + "learning_rate": 6.18144291815269e-05, + "loss": 1.4981, + "step": 7782 + }, + { + "epoch": 0.4338108243687643, + "grad_norm": 0.550807535648346, + "learning_rate": 6.180577689985805e-05, + "loss": 1.6661, + "step": 7783 + }, + { + "epoch": 0.4338665626219274, + "grad_norm": 0.5441664457321167, + "learning_rate": 6.179712424377879e-05, + "loss": 1.6262, + "step": 7784 + }, + { + "epoch": 0.4339223008750906, + "grad_norm": 0.620506227016449, + "learning_rate": 6.178847121356353e-05, + "loss": 1.9091, + "step": 7785 + }, + { + "epoch": 0.4339780391282537, + "grad_norm": 0.6028100252151489, + "learning_rate": 6.17798178094867e-05, + "loss": 1.7357, + "step": 7786 + }, + { + "epoch": 0.43403377738141685, + "grad_norm": 0.549159049987793, + "learning_rate": 6.177116403182274e-05, + "loss": 1.6313, + "step": 7787 + }, + { + "epoch": 0.43408951563458004, + "grad_norm": 0.5400141477584839, + "learning_rate": 6.176250988084608e-05, + "loss": 1.605, + "step": 7788 + }, + { + "epoch": 0.43414525388774317, + "grad_norm": 0.5363699793815613, + "learning_rate": 6.17538553568312e-05, + "loss": 1.5072, + "step": 7789 + }, + { + "epoch": 0.4342009921409063, + "grad_norm": 0.5816105604171753, + "learning_rate": 6.174520046005253e-05, + "loss": 1.769, + "step": 7790 + }, + { + "epoch": 0.4342567303940694, + "grad_norm": 0.5653383731842041, + "learning_rate": 6.17365451907846e-05, + "loss": 1.6427, + "step": 7791 + }, + { + "epoch": 0.4343124686472326, + "grad_norm": 0.5933492183685303, + "learning_rate": 6.172788954930188e-05, + "loss": 1.7614, + "step": 7792 + }, + { + "epoch": 0.43436820690039574, + "grad_norm": 0.5355760455131531, + "learning_rate": 6.171923353587888e-05, + "loss": 1.7932, + "step": 7793 + }, + { + "epoch": 0.43442394515355887, + "grad_norm": 0.5630636811256409, + "learning_rate": 6.171057715079012e-05, + "loss": 1.5032, + "step": 7794 + }, + { + "epoch": 0.43447968340672205, + "grad_norm": 0.5832585692405701, + "learning_rate": 6.170192039431013e-05, + "loss": 1.7822, + "step": 7795 + }, + { + "epoch": 0.4345354216598852, + "grad_norm": 0.4809796214103699, + "learning_rate": 6.169326326671346e-05, + "loss": 1.4389, + "step": 7796 + }, + { + "epoch": 0.4345911599130483, + "grad_norm": 0.5459611415863037, + "learning_rate": 6.168460576827465e-05, + "loss": 1.6287, + "step": 7797 + }, + { + "epoch": 0.4346468981662115, + "grad_norm": 0.5732072591781616, + "learning_rate": 6.167594789926827e-05, + "loss": 1.9769, + "step": 7798 + }, + { + "epoch": 0.4347026364193746, + "grad_norm": 0.5578893423080444, + "learning_rate": 6.16672896599689e-05, + "loss": 1.8077, + "step": 7799 + }, + { + "epoch": 0.43475837467253775, + "grad_norm": 0.5882522463798523, + "learning_rate": 6.165863105065113e-05, + "loss": 1.7451, + "step": 7800 + }, + { + "epoch": 0.43481411292570094, + "grad_norm": 0.6155940890312195, + "learning_rate": 6.164997207158954e-05, + "loss": 1.809, + "step": 7801 + }, + { + "epoch": 0.43486985117886406, + "grad_norm": 0.5675914883613586, + "learning_rate": 6.164131272305878e-05, + "loss": 1.7839, + "step": 7802 + }, + { + "epoch": 0.4349255894320272, + "grad_norm": 0.5673891305923462, + "learning_rate": 6.163265300533345e-05, + "loss": 1.6121, + "step": 7803 + }, + { + "epoch": 0.4349813276851903, + "grad_norm": 0.5579030513763428, + "learning_rate": 6.162399291868819e-05, + "loss": 1.7024, + "step": 7804 + }, + { + "epoch": 0.4350370659383535, + "grad_norm": 0.5674803256988525, + "learning_rate": 6.161533246339764e-05, + "loss": 1.702, + "step": 7805 + }, + { + "epoch": 0.43509280419151664, + "grad_norm": 0.5546411275863647, + "learning_rate": 6.160667163973648e-05, + "loss": 1.7928, + "step": 7806 + }, + { + "epoch": 0.43514854244467976, + "grad_norm": 0.6025899648666382, + "learning_rate": 6.159801044797936e-05, + "loss": 1.7094, + "step": 7807 + }, + { + "epoch": 0.43520428069784295, + "grad_norm": 0.5264720916748047, + "learning_rate": 6.158934888840095e-05, + "loss": 1.4788, + "step": 7808 + }, + { + "epoch": 0.4352600189510061, + "grad_norm": 0.6098587512969971, + "learning_rate": 6.158068696127601e-05, + "loss": 1.789, + "step": 7809 + }, + { + "epoch": 0.4353157572041692, + "grad_norm": 0.5427471995353699, + "learning_rate": 6.157202466687916e-05, + "loss": 1.7309, + "step": 7810 + }, + { + "epoch": 0.4353714954573324, + "grad_norm": 0.5572206974029541, + "learning_rate": 6.156336200548517e-05, + "loss": 1.7018, + "step": 7811 + }, + { + "epoch": 0.4354272337104955, + "grad_norm": 0.5554936528205872, + "learning_rate": 6.155469897736874e-05, + "loss": 1.6621, + "step": 7812 + }, + { + "epoch": 0.43548297196365865, + "grad_norm": 0.5617427229881287, + "learning_rate": 6.154603558280466e-05, + "loss": 1.7123, + "step": 7813 + }, + { + "epoch": 0.4355387102168218, + "grad_norm": 0.572582483291626, + "learning_rate": 6.153737182206762e-05, + "loss": 1.7392, + "step": 7814 + }, + { + "epoch": 0.43559444846998496, + "grad_norm": 0.5278533101081848, + "learning_rate": 6.152870769543245e-05, + "loss": 1.5766, + "step": 7815 + }, + { + "epoch": 0.4356501867231481, + "grad_norm": 0.5663198232650757, + "learning_rate": 6.152004320317385e-05, + "loss": 1.6999, + "step": 7816 + }, + { + "epoch": 0.4357059249763112, + "grad_norm": 0.5262326598167419, + "learning_rate": 6.151137834556666e-05, + "loss": 1.569, + "step": 7817 + }, + { + "epoch": 0.4357616632294744, + "grad_norm": 0.6140465140342712, + "learning_rate": 6.150271312288566e-05, + "loss": 1.9939, + "step": 7818 + }, + { + "epoch": 0.43581740148263753, + "grad_norm": 0.5997401475906372, + "learning_rate": 6.149404753540567e-05, + "loss": 1.7254, + "step": 7819 + }, + { + "epoch": 0.43587313973580066, + "grad_norm": 0.6437683701515198, + "learning_rate": 6.14853815834015e-05, + "loss": 2.0098, + "step": 7820 + }, + { + "epoch": 0.43592887798896385, + "grad_norm": 0.6912010312080383, + "learning_rate": 6.1476715267148e-05, + "loss": 2.1957, + "step": 7821 + }, + { + "epoch": 0.435984616242127, + "grad_norm": 0.5197498202323914, + "learning_rate": 6.146804858692001e-05, + "loss": 1.614, + "step": 7822 + }, + { + "epoch": 0.4360403544952901, + "grad_norm": 0.5308524370193481, + "learning_rate": 6.145938154299237e-05, + "loss": 1.5681, + "step": 7823 + }, + { + "epoch": 0.4360960927484533, + "grad_norm": 0.5914180278778076, + "learning_rate": 6.145071413563996e-05, + "loss": 1.8961, + "step": 7824 + }, + { + "epoch": 0.4361518310016164, + "grad_norm": 0.583292543888092, + "learning_rate": 6.144204636513767e-05, + "loss": 1.7469, + "step": 7825 + }, + { + "epoch": 0.43620756925477955, + "grad_norm": 0.6572228074073792, + "learning_rate": 6.143337823176038e-05, + "loss": 1.8796, + "step": 7826 + }, + { + "epoch": 0.4362633075079427, + "grad_norm": 0.5719166994094849, + "learning_rate": 6.142470973578299e-05, + "loss": 1.8995, + "step": 7827 + }, + { + "epoch": 0.43631904576110586, + "grad_norm": 0.561431348323822, + "learning_rate": 6.141604087748043e-05, + "loss": 1.544, + "step": 7828 + }, + { + "epoch": 0.436374784014269, + "grad_norm": 0.5519416928291321, + "learning_rate": 6.14073716571276e-05, + "loss": 1.7948, + "step": 7829 + }, + { + "epoch": 0.4364305222674321, + "grad_norm": 0.5517488718032837, + "learning_rate": 6.139870207499945e-05, + "loss": 1.6391, + "step": 7830 + }, + { + "epoch": 0.4364862605205953, + "grad_norm": 0.5172828435897827, + "learning_rate": 6.139003213137092e-05, + "loss": 1.7099, + "step": 7831 + }, + { + "epoch": 0.43654199877375843, + "grad_norm": 0.5379384756088257, + "learning_rate": 6.1381361826517e-05, + "loss": 1.5748, + "step": 7832 + }, + { + "epoch": 0.43659773702692156, + "grad_norm": 0.5668090581893921, + "learning_rate": 6.137269116071263e-05, + "loss": 1.6389, + "step": 7833 + }, + { + "epoch": 0.43665347528008475, + "grad_norm": 0.5936790704727173, + "learning_rate": 6.13640201342328e-05, + "loss": 1.7916, + "step": 7834 + }, + { + "epoch": 0.4367092135332479, + "grad_norm": 0.5564102530479431, + "learning_rate": 6.135534874735253e-05, + "loss": 1.6772, + "step": 7835 + }, + { + "epoch": 0.436764951786411, + "grad_norm": 0.6297538876533508, + "learning_rate": 6.134667700034678e-05, + "loss": 1.6905, + "step": 7836 + }, + { + "epoch": 0.43682069003957413, + "grad_norm": 0.5488330125808716, + "learning_rate": 6.13380048934906e-05, + "loss": 1.4808, + "step": 7837 + }, + { + "epoch": 0.4368764282927373, + "grad_norm": 0.5490309000015259, + "learning_rate": 6.132933242705899e-05, + "loss": 1.4744, + "step": 7838 + }, + { + "epoch": 0.43693216654590045, + "grad_norm": 0.5560508370399475, + "learning_rate": 6.132065960132705e-05, + "loss": 1.5957, + "step": 7839 + }, + { + "epoch": 0.4369879047990636, + "grad_norm": 0.6161486506462097, + "learning_rate": 6.131198641656976e-05, + "loss": 1.7756, + "step": 7840 + }, + { + "epoch": 0.43704364305222676, + "grad_norm": 0.5948550701141357, + "learning_rate": 6.130331287306224e-05, + "loss": 1.8239, + "step": 7841 + }, + { + "epoch": 0.4370993813053899, + "grad_norm": 0.5820697546005249, + "learning_rate": 6.129463897107951e-05, + "loss": 1.5446, + "step": 7842 + }, + { + "epoch": 0.437155119558553, + "grad_norm": 0.5708462595939636, + "learning_rate": 6.128596471089669e-05, + "loss": 1.7479, + "step": 7843 + }, + { + "epoch": 0.4372108578117162, + "grad_norm": 0.543056309223175, + "learning_rate": 6.127729009278889e-05, + "loss": 1.5951, + "step": 7844 + }, + { + "epoch": 0.43726659606487933, + "grad_norm": 0.5421169400215149, + "learning_rate": 6.126861511703119e-05, + "loss": 1.7609, + "step": 7845 + }, + { + "epoch": 0.43732233431804246, + "grad_norm": 0.5461887121200562, + "learning_rate": 6.125993978389871e-05, + "loss": 1.559, + "step": 7846 + }, + { + "epoch": 0.43737807257120564, + "grad_norm": 0.5687921643257141, + "learning_rate": 6.12512640936666e-05, + "loss": 1.8498, + "step": 7847 + }, + { + "epoch": 0.4374338108243688, + "grad_norm": 0.571535050868988, + "learning_rate": 6.124258804660999e-05, + "loss": 1.6316, + "step": 7848 + }, + { + "epoch": 0.4374895490775319, + "grad_norm": 0.5363306999206543, + "learning_rate": 6.123391164300404e-05, + "loss": 1.5648, + "step": 7849 + }, + { + "epoch": 0.43754528733069503, + "grad_norm": 0.5810931324958801, + "learning_rate": 6.12252348831239e-05, + "loss": 1.6624, + "step": 7850 + }, + { + "epoch": 0.4376010255838582, + "grad_norm": 0.54121994972229, + "learning_rate": 6.121655776724475e-05, + "loss": 1.617, + "step": 7851 + }, + { + "epoch": 0.43765676383702135, + "grad_norm": 0.54410719871521, + "learning_rate": 6.120788029564181e-05, + "loss": 1.6805, + "step": 7852 + }, + { + "epoch": 0.4377125020901845, + "grad_norm": 0.5891941785812378, + "learning_rate": 6.119920246859024e-05, + "loss": 1.51, + "step": 7853 + }, + { + "epoch": 0.43776824034334766, + "grad_norm": 0.625268280506134, + "learning_rate": 6.119052428636529e-05, + "loss": 1.9405, + "step": 7854 + }, + { + "epoch": 0.4378239785965108, + "grad_norm": 0.5463603138923645, + "learning_rate": 6.118184574924212e-05, + "loss": 1.6922, + "step": 7855 + }, + { + "epoch": 0.4378797168496739, + "grad_norm": 0.6116244196891785, + "learning_rate": 6.1173166857496e-05, + "loss": 1.7829, + "step": 7856 + }, + { + "epoch": 0.4379354551028371, + "grad_norm": 0.60081547498703, + "learning_rate": 6.116448761140218e-05, + "loss": 1.9078, + "step": 7857 + }, + { + "epoch": 0.43799119335600023, + "grad_norm": 0.5881320238113403, + "learning_rate": 6.11558080112359e-05, + "loss": 1.4085, + "step": 7858 + }, + { + "epoch": 0.43804693160916336, + "grad_norm": 0.5768188238143921, + "learning_rate": 6.114712805727244e-05, + "loss": 1.8526, + "step": 7859 + }, + { + "epoch": 0.4381026698623265, + "grad_norm": 0.530643105506897, + "learning_rate": 6.113844774978706e-05, + "loss": 1.6052, + "step": 7860 + }, + { + "epoch": 0.4381584081154897, + "grad_norm": 0.5398595929145813, + "learning_rate": 6.112976708905508e-05, + "loss": 1.7706, + "step": 7861 + }, + { + "epoch": 0.4382141463686528, + "grad_norm": 0.5204975008964539, + "learning_rate": 6.112108607535176e-05, + "loss": 1.6883, + "step": 7862 + }, + { + "epoch": 0.43826988462181593, + "grad_norm": 0.7956941723823547, + "learning_rate": 6.111240470895245e-05, + "loss": 1.4164, + "step": 7863 + }, + { + "epoch": 0.4383256228749791, + "grad_norm": 0.5599929094314575, + "learning_rate": 6.110372299013243e-05, + "loss": 1.7575, + "step": 7864 + }, + { + "epoch": 0.43838136112814224, + "grad_norm": 0.5534434914588928, + "learning_rate": 6.109504091916707e-05, + "loss": 1.825, + "step": 7865 + }, + { + "epoch": 0.4384370993813054, + "grad_norm": 0.5528411269187927, + "learning_rate": 6.108635849633169e-05, + "loss": 1.5657, + "step": 7866 + }, + { + "epoch": 0.43849283763446856, + "grad_norm": 0.5750871300697327, + "learning_rate": 6.107767572190168e-05, + "loss": 2.019, + "step": 7867 + }, + { + "epoch": 0.4385485758876317, + "grad_norm": 0.5783527493476868, + "learning_rate": 6.106899259615236e-05, + "loss": 1.5383, + "step": 7868 + }, + { + "epoch": 0.4386043141407948, + "grad_norm": 0.5577226877212524, + "learning_rate": 6.106030911935913e-05, + "loss": 1.8226, + "step": 7869 + }, + { + "epoch": 0.438660052393958, + "grad_norm": 0.5514130592346191, + "learning_rate": 6.105162529179738e-05, + "loss": 1.8757, + "step": 7870 + }, + { + "epoch": 0.43871579064712113, + "grad_norm": 0.5459834337234497, + "learning_rate": 6.104294111374252e-05, + "loss": 1.6836, + "step": 7871 + }, + { + "epoch": 0.43877152890028426, + "grad_norm": 0.5836615562438965, + "learning_rate": 6.103425658546995e-05, + "loss": 1.7928, + "step": 7872 + }, + { + "epoch": 0.4388272671534474, + "grad_norm": 0.552156925201416, + "learning_rate": 6.1025571707255104e-05, + "loss": 1.7313, + "step": 7873 + }, + { + "epoch": 0.43888300540661057, + "grad_norm": 0.5519532561302185, + "learning_rate": 6.10168864793734e-05, + "loss": 1.7947, + "step": 7874 + }, + { + "epoch": 0.4389387436597737, + "grad_norm": 0.5163867473602295, + "learning_rate": 6.100820090210028e-05, + "loss": 1.5192, + "step": 7875 + }, + { + "epoch": 0.43899448191293683, + "grad_norm": 0.5566312074661255, + "learning_rate": 6.099951497571123e-05, + "loss": 1.5993, + "step": 7876 + }, + { + "epoch": 0.4390502201661, + "grad_norm": 0.5464503765106201, + "learning_rate": 6.099082870048168e-05, + "loss": 1.8421, + "step": 7877 + }, + { + "epoch": 0.43910595841926314, + "grad_norm": 0.5337437987327576, + "learning_rate": 6.098214207668713e-05, + "loss": 1.5466, + "step": 7878 + }, + { + "epoch": 0.43916169667242627, + "grad_norm": 0.6034952402114868, + "learning_rate": 6.097345510460307e-05, + "loss": 1.8151, + "step": 7879 + }, + { + "epoch": 0.43921743492558946, + "grad_norm": 0.5526003241539001, + "learning_rate": 6.0964767784504995e-05, + "loss": 1.6425, + "step": 7880 + }, + { + "epoch": 0.4392731731787526, + "grad_norm": 0.575605571269989, + "learning_rate": 6.09560801166684e-05, + "loss": 1.7276, + "step": 7881 + }, + { + "epoch": 0.4393289114319157, + "grad_norm": 0.6006867289543152, + "learning_rate": 6.094739210136883e-05, + "loss": 1.7726, + "step": 7882 + }, + { + "epoch": 0.43938464968507884, + "grad_norm": 0.5347257852554321, + "learning_rate": 6.093870373888181e-05, + "loss": 1.6228, + "step": 7883 + }, + { + "epoch": 0.439440387938242, + "grad_norm": 0.5642088651657104, + "learning_rate": 6.093001502948289e-05, + "loss": 1.7197, + "step": 7884 + }, + { + "epoch": 0.43949612619140516, + "grad_norm": 0.5518479943275452, + "learning_rate": 6.0921325973447604e-05, + "loss": 1.5778, + "step": 7885 + }, + { + "epoch": 0.4395518644445683, + "grad_norm": 0.6168820261955261, + "learning_rate": 6.091263657105155e-05, + "loss": 1.7891, + "step": 7886 + }, + { + "epoch": 0.43960760269773147, + "grad_norm": 0.5440758466720581, + "learning_rate": 6.090394682257029e-05, + "loss": 1.5781, + "step": 7887 + }, + { + "epoch": 0.4396633409508946, + "grad_norm": 0.5412326455116272, + "learning_rate": 6.08952567282794e-05, + "loss": 1.683, + "step": 7888 + }, + { + "epoch": 0.43971907920405773, + "grad_norm": 0.563556969165802, + "learning_rate": 6.0886566288454496e-05, + "loss": 1.5673, + "step": 7889 + }, + { + "epoch": 0.4397748174572209, + "grad_norm": 0.5224372148513794, + "learning_rate": 6.0877875503371176e-05, + "loss": 1.7352, + "step": 7890 + }, + { + "epoch": 0.43983055571038404, + "grad_norm": 0.5953571796417236, + "learning_rate": 6.086918437330508e-05, + "loss": 1.7736, + "step": 7891 + }, + { + "epoch": 0.43988629396354717, + "grad_norm": 0.5646018385887146, + "learning_rate": 6.086049289853182e-05, + "loss": 1.7542, + "step": 7892 + }, + { + "epoch": 0.43994203221671035, + "grad_norm": 0.6011926531791687, + "learning_rate": 6.0851801079327056e-05, + "loss": 1.7245, + "step": 7893 + }, + { + "epoch": 0.4399977704698735, + "grad_norm": 0.4823513627052307, + "learning_rate": 6.0843108915966415e-05, + "loss": 1.4047, + "step": 7894 + }, + { + "epoch": 0.4400535087230366, + "grad_norm": 0.6140894889831543, + "learning_rate": 6.083441640872558e-05, + "loss": 2.0188, + "step": 7895 + }, + { + "epoch": 0.44010924697619974, + "grad_norm": 0.5411475896835327, + "learning_rate": 6.082572355788023e-05, + "loss": 1.5408, + "step": 7896 + }, + { + "epoch": 0.4401649852293629, + "grad_norm": 0.6488401293754578, + "learning_rate": 6.081703036370606e-05, + "loss": 2.0136, + "step": 7897 + }, + { + "epoch": 0.44022072348252606, + "grad_norm": 0.7427087426185608, + "learning_rate": 6.080833682647874e-05, + "loss": 1.6615, + "step": 7898 + }, + { + "epoch": 0.4402764617356892, + "grad_norm": 0.6195456385612488, + "learning_rate": 6.0799642946473986e-05, + "loss": 1.5859, + "step": 7899 + }, + { + "epoch": 0.44033219998885237, + "grad_norm": 0.5988082885742188, + "learning_rate": 6.079094872396754e-05, + "loss": 1.7462, + "step": 7900 + }, + { + "epoch": 0.4403879382420155, + "grad_norm": 0.6001728177070618, + "learning_rate": 6.0782254159235116e-05, + "loss": 1.736, + "step": 7901 + }, + { + "epoch": 0.4404436764951786, + "grad_norm": 0.5472791790962219, + "learning_rate": 6.0773559252552446e-05, + "loss": 1.372, + "step": 7902 + }, + { + "epoch": 0.4404994147483418, + "grad_norm": 0.5791669487953186, + "learning_rate": 6.0764864004195286e-05, + "loss": 1.7732, + "step": 7903 + }, + { + "epoch": 0.44055515300150494, + "grad_norm": 0.5353814363479614, + "learning_rate": 6.075616841443943e-05, + "loss": 1.8002, + "step": 7904 + }, + { + "epoch": 0.44061089125466807, + "grad_norm": 0.5734871029853821, + "learning_rate": 6.07474724835606e-05, + "loss": 1.7832, + "step": 7905 + }, + { + "epoch": 0.4406666295078312, + "grad_norm": 0.6158138513565063, + "learning_rate": 6.0738776211834615e-05, + "loss": 1.9006, + "step": 7906 + }, + { + "epoch": 0.4407223677609944, + "grad_norm": 0.5585591793060303, + "learning_rate": 6.073007959953726e-05, + "loss": 1.8046, + "step": 7907 + }, + { + "epoch": 0.4407781060141575, + "grad_norm": 0.5921459794044495, + "learning_rate": 6.0721382646944326e-05, + "loss": 1.8318, + "step": 7908 + }, + { + "epoch": 0.44083384426732064, + "grad_norm": 0.5314304828643799, + "learning_rate": 6.0712685354331654e-05, + "loss": 1.4663, + "step": 7909 + }, + { + "epoch": 0.4408895825204838, + "grad_norm": 0.5642038583755493, + "learning_rate": 6.0703987721975076e-05, + "loss": 1.6231, + "step": 7910 + }, + { + "epoch": 0.44094532077364695, + "grad_norm": 0.598506510257721, + "learning_rate": 6.0695289750150394e-05, + "loss": 1.6668, + "step": 7911 + }, + { + "epoch": 0.4410010590268101, + "grad_norm": 0.5824127197265625, + "learning_rate": 6.068659143913349e-05, + "loss": 1.7711, + "step": 7912 + }, + { + "epoch": 0.44105679727997327, + "grad_norm": 0.5553746223449707, + "learning_rate": 6.0677892789200216e-05, + "loss": 1.7025, + "step": 7913 + }, + { + "epoch": 0.4411125355331364, + "grad_norm": 0.5868836641311646, + "learning_rate": 6.066919380062643e-05, + "loss": 1.7495, + "step": 7914 + }, + { + "epoch": 0.4411682737862995, + "grad_norm": 0.5977121591567993, + "learning_rate": 6.066049447368802e-05, + "loss": 1.5988, + "step": 7915 + }, + { + "epoch": 0.4412240120394627, + "grad_norm": 0.6062576770782471, + "learning_rate": 6.065179480866089e-05, + "loss": 1.7006, + "step": 7916 + }, + { + "epoch": 0.44127975029262584, + "grad_norm": 0.5636418461799622, + "learning_rate": 6.064309480582093e-05, + "loss": 1.6275, + "step": 7917 + }, + { + "epoch": 0.44133548854578897, + "grad_norm": 0.5832415223121643, + "learning_rate": 6.0634394465444056e-05, + "loss": 1.8278, + "step": 7918 + }, + { + "epoch": 0.4413912267989521, + "grad_norm": 0.5471083521842957, + "learning_rate": 6.062569378780621e-05, + "loss": 1.724, + "step": 7919 + }, + { + "epoch": 0.4414469650521153, + "grad_norm": 0.5676271915435791, + "learning_rate": 6.061699277318328e-05, + "loss": 1.706, + "step": 7920 + }, + { + "epoch": 0.4415027033052784, + "grad_norm": 0.5920431613922119, + "learning_rate": 6.060829142185125e-05, + "loss": 1.7118, + "step": 7921 + }, + { + "epoch": 0.44155844155844154, + "grad_norm": 0.6104030609130859, + "learning_rate": 6.059958973408607e-05, + "loss": 1.908, + "step": 7922 + }, + { + "epoch": 0.4416141798116047, + "grad_norm": 0.5903329849243164, + "learning_rate": 6.05908877101637e-05, + "loss": 1.7077, + "step": 7923 + }, + { + "epoch": 0.44166991806476785, + "grad_norm": 0.5489821434020996, + "learning_rate": 6.058218535036013e-05, + "loss": 1.6519, + "step": 7924 + }, + { + "epoch": 0.441725656317931, + "grad_norm": 0.5121790170669556, + "learning_rate": 6.057348265495133e-05, + "loss": 1.4665, + "step": 7925 + }, + { + "epoch": 0.44178139457109417, + "grad_norm": 0.5221953392028809, + "learning_rate": 6.0564779624213316e-05, + "loss": 1.6157, + "step": 7926 + }, + { + "epoch": 0.4418371328242573, + "grad_norm": 0.5600380897521973, + "learning_rate": 6.055607625842208e-05, + "loss": 1.5828, + "step": 7927 + }, + { + "epoch": 0.4418928710774204, + "grad_norm": 0.5320744514465332, + "learning_rate": 6.0547372557853655e-05, + "loss": 1.6772, + "step": 7928 + }, + { + "epoch": 0.44194860933058355, + "grad_norm": 0.5403137803077698, + "learning_rate": 6.053866852278406e-05, + "loss": 1.7394, + "step": 7929 + }, + { + "epoch": 0.44200434758374674, + "grad_norm": 0.591922402381897, + "learning_rate": 6.052996415348936e-05, + "loss": 1.8231, + "step": 7930 + }, + { + "epoch": 0.44206008583690987, + "grad_norm": 0.5516440868377686, + "learning_rate": 6.052125945024558e-05, + "loss": 1.6415, + "step": 7931 + }, + { + "epoch": 0.442115824090073, + "grad_norm": 0.5129381418228149, + "learning_rate": 6.05125544133288e-05, + "loss": 1.5515, + "step": 7932 + }, + { + "epoch": 0.4421715623432362, + "grad_norm": 0.5778689980506897, + "learning_rate": 6.050384904301508e-05, + "loss": 1.7348, + "step": 7933 + }, + { + "epoch": 0.4422273005963993, + "grad_norm": 0.5508379340171814, + "learning_rate": 6.049514333958052e-05, + "loss": 1.6601, + "step": 7934 + }, + { + "epoch": 0.44228303884956244, + "grad_norm": 0.5481617450714111, + "learning_rate": 6.048643730330119e-05, + "loss": 1.5493, + "step": 7935 + }, + { + "epoch": 0.4423387771027256, + "grad_norm": 0.5237631797790527, + "learning_rate": 6.0477730934453226e-05, + "loss": 1.5092, + "step": 7936 + }, + { + "epoch": 0.44239451535588875, + "grad_norm": 0.5657276511192322, + "learning_rate": 6.046902423331271e-05, + "loss": 1.4483, + "step": 7937 + }, + { + "epoch": 0.4424502536090519, + "grad_norm": 0.5502325892448425, + "learning_rate": 6.046031720015579e-05, + "loss": 1.6987, + "step": 7938 + }, + { + "epoch": 0.44250599186221506, + "grad_norm": 0.6082862615585327, + "learning_rate": 6.045160983525859e-05, + "loss": 1.8988, + "step": 7939 + }, + { + "epoch": 0.4425617301153782, + "grad_norm": 0.5569537878036499, + "learning_rate": 6.044290213889727e-05, + "loss": 1.696, + "step": 7940 + }, + { + "epoch": 0.4426174683685413, + "grad_norm": 0.518162190914154, + "learning_rate": 6.0434194111347985e-05, + "loss": 1.5279, + "step": 7941 + }, + { + "epoch": 0.44267320662170445, + "grad_norm": 0.5695126056671143, + "learning_rate": 6.042548575288689e-05, + "loss": 1.7109, + "step": 7942 + }, + { + "epoch": 0.44272894487486764, + "grad_norm": 0.49009808897972107, + "learning_rate": 6.0416777063790184e-05, + "loss": 1.4709, + "step": 7943 + }, + { + "epoch": 0.44278468312803076, + "grad_norm": 0.5802407264709473, + "learning_rate": 6.040806804433403e-05, + "loss": 1.6943, + "step": 7944 + }, + { + "epoch": 0.4428404213811939, + "grad_norm": 0.5507357716560364, + "learning_rate": 6.0399358694794647e-05, + "loss": 1.3918, + "step": 7945 + }, + { + "epoch": 0.4428961596343571, + "grad_norm": 0.5855342745780945, + "learning_rate": 6.039064901544824e-05, + "loss": 1.8103, + "step": 7946 + }, + { + "epoch": 0.4429518978875202, + "grad_norm": 0.5658082365989685, + "learning_rate": 6.038193900657102e-05, + "loss": 1.7597, + "step": 7947 + }, + { + "epoch": 0.44300763614068334, + "grad_norm": 0.5863122344017029, + "learning_rate": 6.037322866843923e-05, + "loss": 1.7671, + "step": 7948 + }, + { + "epoch": 0.4430633743938465, + "grad_norm": 0.5610207915306091, + "learning_rate": 6.036451800132912e-05, + "loss": 1.7487, + "step": 7949 + }, + { + "epoch": 0.44311911264700965, + "grad_norm": 0.5848312377929688, + "learning_rate": 6.03558070055169e-05, + "loss": 1.7112, + "step": 7950 + }, + { + "epoch": 0.4431748509001728, + "grad_norm": 0.5728501081466675, + "learning_rate": 6.0347095681278876e-05, + "loss": 1.7736, + "step": 7951 + }, + { + "epoch": 0.4432305891533359, + "grad_norm": 0.5987431406974792, + "learning_rate": 6.033838402889131e-05, + "loss": 1.7693, + "step": 7952 + }, + { + "epoch": 0.4432863274064991, + "grad_norm": 0.5747002959251404, + "learning_rate": 6.032967204863048e-05, + "loss": 1.6216, + "step": 7953 + }, + { + "epoch": 0.4433420656596622, + "grad_norm": 0.5476230382919312, + "learning_rate": 6.0320959740772666e-05, + "loss": 1.7631, + "step": 7954 + }, + { + "epoch": 0.44339780391282535, + "grad_norm": 0.5305277109146118, + "learning_rate": 6.031224710559419e-05, + "loss": 1.6809, + "step": 7955 + }, + { + "epoch": 0.44345354216598853, + "grad_norm": 0.5442744493484497, + "learning_rate": 6.0303534143371374e-05, + "loss": 1.5357, + "step": 7956 + }, + { + "epoch": 0.44350928041915166, + "grad_norm": 0.5553621053695679, + "learning_rate": 6.029482085438051e-05, + "loss": 1.6955, + "step": 7957 + }, + { + "epoch": 0.4435650186723148, + "grad_norm": 0.5430163741111755, + "learning_rate": 6.028610723889797e-05, + "loss": 1.762, + "step": 7958 + }, + { + "epoch": 0.443620756925478, + "grad_norm": 0.5217944979667664, + "learning_rate": 6.027739329720006e-05, + "loss": 1.4594, + "step": 7959 + }, + { + "epoch": 0.4436764951786411, + "grad_norm": 0.5763014554977417, + "learning_rate": 6.026867902956317e-05, + "loss": 1.7942, + "step": 7960 + }, + { + "epoch": 0.44373223343180423, + "grad_norm": 0.533718466758728, + "learning_rate": 6.025996443626364e-05, + "loss": 1.6659, + "step": 7961 + }, + { + "epoch": 0.4437879716849674, + "grad_norm": 0.5921129584312439, + "learning_rate": 6.0251249517577854e-05, + "loss": 1.9042, + "step": 7962 + }, + { + "epoch": 0.44384370993813055, + "grad_norm": 0.5379483103752136, + "learning_rate": 6.024253427378222e-05, + "loss": 1.6772, + "step": 7963 + }, + { + "epoch": 0.4438994481912937, + "grad_norm": 0.5350393652915955, + "learning_rate": 6.0233818705153114e-05, + "loss": 1.5868, + "step": 7964 + }, + { + "epoch": 0.4439551864444568, + "grad_norm": 0.5462901592254639, + "learning_rate": 6.022510281196695e-05, + "loss": 1.6118, + "step": 7965 + }, + { + "epoch": 0.44401092469762, + "grad_norm": 0.5518479943275452, + "learning_rate": 6.021638659450013e-05, + "loss": 1.4902, + "step": 7966 + }, + { + "epoch": 0.4440666629507831, + "grad_norm": 0.5284306406974792, + "learning_rate": 6.020767005302909e-05, + "loss": 1.5573, + "step": 7967 + }, + { + "epoch": 0.44412240120394625, + "grad_norm": 0.6189160346984863, + "learning_rate": 6.0198953187830277e-05, + "loss": 1.9599, + "step": 7968 + }, + { + "epoch": 0.44417813945710943, + "grad_norm": 0.5723422765731812, + "learning_rate": 6.019023599918014e-05, + "loss": 1.7111, + "step": 7969 + }, + { + "epoch": 0.44423387771027256, + "grad_norm": 0.5545480251312256, + "learning_rate": 6.018151848735511e-05, + "loss": 1.6214, + "step": 7970 + }, + { + "epoch": 0.4442896159634357, + "grad_norm": 0.5693395733833313, + "learning_rate": 6.01728006526317e-05, + "loss": 1.8074, + "step": 7971 + }, + { + "epoch": 0.4443453542165989, + "grad_norm": 0.5313411951065063, + "learning_rate": 6.0164082495286354e-05, + "loss": 1.6405, + "step": 7972 + }, + { + "epoch": 0.444401092469762, + "grad_norm": 0.5680732727050781, + "learning_rate": 6.015536401559556e-05, + "loss": 1.4973, + "step": 7973 + }, + { + "epoch": 0.44445683072292513, + "grad_norm": 0.6219733357429504, + "learning_rate": 6.014664521383584e-05, + "loss": 1.8733, + "step": 7974 + }, + { + "epoch": 0.44451256897608826, + "grad_norm": 0.5903530716896057, + "learning_rate": 6.0137926090283694e-05, + "loss": 1.6334, + "step": 7975 + }, + { + "epoch": 0.44456830722925145, + "grad_norm": 0.6504166722297668, + "learning_rate": 6.0129206645215655e-05, + "loss": 1.7995, + "step": 7976 + }, + { + "epoch": 0.4446240454824146, + "grad_norm": 0.6121776103973389, + "learning_rate": 6.012048687890821e-05, + "loss": 1.8132, + "step": 7977 + }, + { + "epoch": 0.4446797837355777, + "grad_norm": 0.6290067434310913, + "learning_rate": 6.011176679163796e-05, + "loss": 1.9482, + "step": 7978 + }, + { + "epoch": 0.4447355219887409, + "grad_norm": 0.6563844084739685, + "learning_rate": 6.010304638368139e-05, + "loss": 1.8485, + "step": 7979 + }, + { + "epoch": 0.444791260241904, + "grad_norm": 0.5514439940452576, + "learning_rate": 6.009432565531511e-05, + "loss": 1.6343, + "step": 7980 + }, + { + "epoch": 0.44484699849506715, + "grad_norm": 0.5945736765861511, + "learning_rate": 6.008560460681567e-05, + "loss": 1.721, + "step": 7981 + }, + { + "epoch": 0.44490273674823033, + "grad_norm": 0.5428782105445862, + "learning_rate": 6.007688323845966e-05, + "loss": 1.5152, + "step": 7982 + }, + { + "epoch": 0.44495847500139346, + "grad_norm": 0.5975694060325623, + "learning_rate": 6.006816155052366e-05, + "loss": 1.7975, + "step": 7983 + }, + { + "epoch": 0.4450142132545566, + "grad_norm": 0.5683627724647522, + "learning_rate": 6.005943954328429e-05, + "loss": 1.7401, + "step": 7984 + }, + { + "epoch": 0.4450699515077198, + "grad_norm": 0.552085280418396, + "learning_rate": 6.005071721701814e-05, + "loss": 1.5525, + "step": 7985 + }, + { + "epoch": 0.4451256897608829, + "grad_norm": 0.5957344770431519, + "learning_rate": 6.004199457200184e-05, + "loss": 1.8248, + "step": 7986 + }, + { + "epoch": 0.44518142801404603, + "grad_norm": 0.5816213488578796, + "learning_rate": 6.003327160851201e-05, + "loss": 1.5985, + "step": 7987 + }, + { + "epoch": 0.44523716626720916, + "grad_norm": 0.5090708136558533, + "learning_rate": 6.002454832682532e-05, + "loss": 1.4312, + "step": 7988 + }, + { + "epoch": 0.44529290452037235, + "grad_norm": 0.5570594668388367, + "learning_rate": 6.00158247272184e-05, + "loss": 1.6288, + "step": 7989 + }, + { + "epoch": 0.4453486427735355, + "grad_norm": 0.4970921576023102, + "learning_rate": 6.00071008099679e-05, + "loss": 1.2663, + "step": 7990 + }, + { + "epoch": 0.4454043810266986, + "grad_norm": 0.5791414976119995, + "learning_rate": 5.999837657535052e-05, + "loss": 1.8037, + "step": 7991 + }, + { + "epoch": 0.4454601192798618, + "grad_norm": 0.5636151432991028, + "learning_rate": 5.998965202364294e-05, + "loss": 1.6298, + "step": 7992 + }, + { + "epoch": 0.4455158575330249, + "grad_norm": 0.5829344987869263, + "learning_rate": 5.998092715512183e-05, + "loss": 1.6349, + "step": 7993 + }, + { + "epoch": 0.44557159578618805, + "grad_norm": 0.556348979473114, + "learning_rate": 5.9972201970063904e-05, + "loss": 1.5642, + "step": 7994 + }, + { + "epoch": 0.44562733403935123, + "grad_norm": 0.5365790724754333, + "learning_rate": 5.996347646874587e-05, + "loss": 1.6421, + "step": 7995 + }, + { + "epoch": 0.44568307229251436, + "grad_norm": 0.576501190662384, + "learning_rate": 5.9954750651444455e-05, + "loss": 1.6171, + "step": 7996 + }, + { + "epoch": 0.4457388105456775, + "grad_norm": 0.5861379504203796, + "learning_rate": 5.9946024518436406e-05, + "loss": 1.6702, + "step": 7997 + }, + { + "epoch": 0.4457945487988406, + "grad_norm": 0.5348252058029175, + "learning_rate": 5.9937298069998424e-05, + "loss": 1.4339, + "step": 7998 + }, + { + "epoch": 0.4458502870520038, + "grad_norm": 0.5516197085380554, + "learning_rate": 5.99285713064073e-05, + "loss": 1.738, + "step": 7999 + }, + { + "epoch": 0.44590602530516693, + "grad_norm": 0.58391934633255, + "learning_rate": 5.991984422793977e-05, + "loss": 1.4481, + "step": 8000 + }, + { + "epoch": 0.44596176355833006, + "grad_norm": 0.5707566738128662, + "learning_rate": 5.9911116834872624e-05, + "loss": 1.7051, + "step": 8001 + }, + { + "epoch": 0.44601750181149324, + "grad_norm": 0.5384584069252014, + "learning_rate": 5.990238912748265e-05, + "loss": 1.7542, + "step": 8002 + }, + { + "epoch": 0.4460732400646564, + "grad_norm": 0.5866785645484924, + "learning_rate": 5.989366110604662e-05, + "loss": 1.8245, + "step": 8003 + }, + { + "epoch": 0.4461289783178195, + "grad_norm": 0.5644246935844421, + "learning_rate": 5.988493277084134e-05, + "loss": 1.7637, + "step": 8004 + }, + { + "epoch": 0.4461847165709827, + "grad_norm": 0.5331970453262329, + "learning_rate": 5.9876204122143634e-05, + "loss": 1.6303, + "step": 8005 + }, + { + "epoch": 0.4462404548241458, + "grad_norm": 0.5923652648925781, + "learning_rate": 5.98674751602303e-05, + "loss": 1.8505, + "step": 8006 + }, + { + "epoch": 0.44629619307730894, + "grad_norm": 0.5415480136871338, + "learning_rate": 5.985874588537819e-05, + "loss": 1.6483, + "step": 8007 + }, + { + "epoch": 0.44635193133047213, + "grad_norm": 0.5634106397628784, + "learning_rate": 5.985001629786415e-05, + "loss": 1.5566, + "step": 8008 + }, + { + "epoch": 0.44640766958363526, + "grad_norm": 0.5723522901535034, + "learning_rate": 5.9841286397965014e-05, + "loss": 1.7409, + "step": 8009 + }, + { + "epoch": 0.4464634078367984, + "grad_norm": 0.5537884831428528, + "learning_rate": 5.983255618595767e-05, + "loss": 1.712, + "step": 8010 + }, + { + "epoch": 0.4465191460899615, + "grad_norm": 0.5915796160697937, + "learning_rate": 5.982382566211895e-05, + "loss": 1.7699, + "step": 8011 + }, + { + "epoch": 0.4465748843431247, + "grad_norm": 0.6134962439537048, + "learning_rate": 5.981509482672576e-05, + "loss": 1.862, + "step": 8012 + }, + { + "epoch": 0.44663062259628783, + "grad_norm": 0.4997968077659607, + "learning_rate": 5.980636368005499e-05, + "loss": 1.5174, + "step": 8013 + }, + { + "epoch": 0.44668636084945096, + "grad_norm": 0.5801420211791992, + "learning_rate": 5.979763222238354e-05, + "loss": 1.8425, + "step": 8014 + }, + { + "epoch": 0.44674209910261414, + "grad_norm": 0.5159302949905396, + "learning_rate": 5.978890045398833e-05, + "loss": 1.7243, + "step": 8015 + }, + { + "epoch": 0.44679783735577727, + "grad_norm": 0.59089195728302, + "learning_rate": 5.978016837514625e-05, + "loss": 1.8003, + "step": 8016 + }, + { + "epoch": 0.4468535756089404, + "grad_norm": 0.5666080713272095, + "learning_rate": 5.9771435986134274e-05, + "loss": 1.648, + "step": 8017 + }, + { + "epoch": 0.4469093138621036, + "grad_norm": 0.5891024470329285, + "learning_rate": 5.9762703287229304e-05, + "loss": 1.5867, + "step": 8018 + }, + { + "epoch": 0.4469650521152667, + "grad_norm": 0.5871114730834961, + "learning_rate": 5.975397027870831e-05, + "loss": 1.656, + "step": 8019 + }, + { + "epoch": 0.44702079036842984, + "grad_norm": 0.6023023724555969, + "learning_rate": 5.974523696084825e-05, + "loss": 1.6628, + "step": 8020 + }, + { + "epoch": 0.447076528621593, + "grad_norm": 0.5608631372451782, + "learning_rate": 5.97365033339261e-05, + "loss": 1.4316, + "step": 8021 + }, + { + "epoch": 0.44713226687475616, + "grad_norm": 0.5549430251121521, + "learning_rate": 5.972776939821883e-05, + "loss": 1.4696, + "step": 8022 + }, + { + "epoch": 0.4471880051279193, + "grad_norm": 0.5799054503440857, + "learning_rate": 5.971903515400342e-05, + "loss": 1.7885, + "step": 8023 + }, + { + "epoch": 0.4472437433810824, + "grad_norm": 0.5215498208999634, + "learning_rate": 5.971030060155689e-05, + "loss": 1.6956, + "step": 8024 + }, + { + "epoch": 0.4472994816342456, + "grad_norm": 0.5385097861289978, + "learning_rate": 5.970156574115623e-05, + "loss": 1.5434, + "step": 8025 + }, + { + "epoch": 0.44735521988740873, + "grad_norm": 0.5320507287979126, + "learning_rate": 5.969283057307847e-05, + "loss": 1.5207, + "step": 8026 + }, + { + "epoch": 0.44741095814057186, + "grad_norm": 0.53661048412323, + "learning_rate": 5.9684095097600645e-05, + "loss": 1.6211, + "step": 8027 + }, + { + "epoch": 0.44746669639373504, + "grad_norm": 0.5779610872268677, + "learning_rate": 5.967535931499979e-05, + "loss": 1.7282, + "step": 8028 + }, + { + "epoch": 0.44752243464689817, + "grad_norm": 0.5973451137542725, + "learning_rate": 5.966662322555294e-05, + "loss": 1.822, + "step": 8029 + }, + { + "epoch": 0.4475781729000613, + "grad_norm": 0.6070274710655212, + "learning_rate": 5.965788682953717e-05, + "loss": 1.6235, + "step": 8030 + }, + { + "epoch": 0.4476339111532245, + "grad_norm": 0.5565271377563477, + "learning_rate": 5.9649150127229534e-05, + "loss": 1.8248, + "step": 8031 + }, + { + "epoch": 0.4476896494063876, + "grad_norm": 0.5610112547874451, + "learning_rate": 5.964041311890711e-05, + "loss": 1.5738, + "step": 8032 + }, + { + "epoch": 0.44774538765955074, + "grad_norm": 0.5636839270591736, + "learning_rate": 5.9631675804846985e-05, + "loss": 1.5644, + "step": 8033 + }, + { + "epoch": 0.44780112591271387, + "grad_norm": 0.5381824970245361, + "learning_rate": 5.962293818532628e-05, + "loss": 1.6785, + "step": 8034 + }, + { + "epoch": 0.44785686416587706, + "grad_norm": 0.5614325404167175, + "learning_rate": 5.9614200260622066e-05, + "loss": 1.7991, + "step": 8035 + }, + { + "epoch": 0.4479126024190402, + "grad_norm": 0.527214527130127, + "learning_rate": 5.960546203101148e-05, + "loss": 1.6311, + "step": 8036 + }, + { + "epoch": 0.4479683406722033, + "grad_norm": 0.5667834877967834, + "learning_rate": 5.959672349677163e-05, + "loss": 1.4416, + "step": 8037 + }, + { + "epoch": 0.4480240789253665, + "grad_norm": 0.5953390002250671, + "learning_rate": 5.9587984658179676e-05, + "loss": 1.8168, + "step": 8038 + }, + { + "epoch": 0.4480798171785296, + "grad_norm": 0.5339275598526001, + "learning_rate": 5.957924551551275e-05, + "loss": 1.6999, + "step": 8039 + }, + { + "epoch": 0.44813555543169276, + "grad_norm": 0.5568943619728088, + "learning_rate": 5.9570506069048e-05, + "loss": 1.7066, + "step": 8040 + }, + { + "epoch": 0.44819129368485594, + "grad_norm": 0.5787097215652466, + "learning_rate": 5.95617663190626e-05, + "loss": 1.6468, + "step": 8041 + }, + { + "epoch": 0.44824703193801907, + "grad_norm": 0.5685398578643799, + "learning_rate": 5.955302626583374e-05, + "loss": 1.8804, + "step": 8042 + }, + { + "epoch": 0.4483027701911822, + "grad_norm": 0.5303986668586731, + "learning_rate": 5.9544285909638566e-05, + "loss": 1.4389, + "step": 8043 + }, + { + "epoch": 0.4483585084443453, + "grad_norm": 0.5936418771743774, + "learning_rate": 5.953554525075429e-05, + "loss": 1.9128, + "step": 8044 + }, + { + "epoch": 0.4484142466975085, + "grad_norm": 0.5271584391593933, + "learning_rate": 5.952680428945812e-05, + "loss": 1.5926, + "step": 8045 + }, + { + "epoch": 0.44846998495067164, + "grad_norm": 0.5615208148956299, + "learning_rate": 5.951806302602725e-05, + "loss": 1.6805, + "step": 8046 + }, + { + "epoch": 0.44852572320383477, + "grad_norm": 0.5467960834503174, + "learning_rate": 5.950932146073893e-05, + "loss": 1.6863, + "step": 8047 + }, + { + "epoch": 0.44858146145699795, + "grad_norm": 0.5716736912727356, + "learning_rate": 5.950057959387038e-05, + "loss": 1.695, + "step": 8048 + }, + { + "epoch": 0.4486371997101611, + "grad_norm": 0.5174785852432251, + "learning_rate": 5.9491837425698816e-05, + "loss": 1.3978, + "step": 8049 + }, + { + "epoch": 0.4486929379633242, + "grad_norm": 0.5112467408180237, + "learning_rate": 5.948309495650153e-05, + "loss": 1.3862, + "step": 8050 + }, + { + "epoch": 0.4487486762164874, + "grad_norm": 0.6070237755775452, + "learning_rate": 5.947435218655576e-05, + "loss": 1.744, + "step": 8051 + }, + { + "epoch": 0.4488044144696505, + "grad_norm": 0.5886159539222717, + "learning_rate": 5.946560911613877e-05, + "loss": 1.9782, + "step": 8052 + }, + { + "epoch": 0.44886015272281365, + "grad_norm": 0.6077089309692383, + "learning_rate": 5.945686574552785e-05, + "loss": 1.6861, + "step": 8053 + }, + { + "epoch": 0.44891589097597684, + "grad_norm": 0.5767019391059875, + "learning_rate": 5.944812207500029e-05, + "loss": 1.8577, + "step": 8054 + }, + { + "epoch": 0.44897162922913997, + "grad_norm": 0.5735483765602112, + "learning_rate": 5.943937810483338e-05, + "loss": 1.8143, + "step": 8055 + }, + { + "epoch": 0.4490273674823031, + "grad_norm": 0.5384686589241028, + "learning_rate": 5.943063383530444e-05, + "loss": 1.7183, + "step": 8056 + }, + { + "epoch": 0.4490831057354662, + "grad_norm": 0.5415961146354675, + "learning_rate": 5.942188926669077e-05, + "loss": 1.5619, + "step": 8057 + }, + { + "epoch": 0.4491388439886294, + "grad_norm": 0.5548281669616699, + "learning_rate": 5.941314439926969e-05, + "loss": 1.8049, + "step": 8058 + }, + { + "epoch": 0.44919458224179254, + "grad_norm": 0.5731210112571716, + "learning_rate": 5.940439923331857e-05, + "loss": 1.9301, + "step": 8059 + }, + { + "epoch": 0.44925032049495567, + "grad_norm": 0.5715717673301697, + "learning_rate": 5.939565376911475e-05, + "loss": 1.6145, + "step": 8060 + }, + { + "epoch": 0.44930605874811885, + "grad_norm": 0.5775079131126404, + "learning_rate": 5.938690800693556e-05, + "loss": 1.7435, + "step": 8061 + }, + { + "epoch": 0.449361797001282, + "grad_norm": 0.5366044044494629, + "learning_rate": 5.937816194705838e-05, + "loss": 1.7497, + "step": 8062 + }, + { + "epoch": 0.4494175352544451, + "grad_norm": 0.5498981475830078, + "learning_rate": 5.936941558976058e-05, + "loss": 1.6565, + "step": 8063 + }, + { + "epoch": 0.4494732735076083, + "grad_norm": 0.541826605796814, + "learning_rate": 5.936066893531954e-05, + "loss": 1.6147, + "step": 8064 + }, + { + "epoch": 0.4495290117607714, + "grad_norm": 0.5456510186195374, + "learning_rate": 5.9351921984012657e-05, + "loss": 1.652, + "step": 8065 + }, + { + "epoch": 0.44958475001393455, + "grad_norm": 0.5831677317619324, + "learning_rate": 5.934317473611734e-05, + "loss": 1.7302, + "step": 8066 + }, + { + "epoch": 0.4496404882670977, + "grad_norm": 0.55061274766922, + "learning_rate": 5.9334427191911e-05, + "loss": 1.6976, + "step": 8067 + }, + { + "epoch": 0.44969622652026087, + "grad_norm": 0.5210010409355164, + "learning_rate": 5.932567935167104e-05, + "loss": 1.5901, + "step": 8068 + }, + { + "epoch": 0.449751964773424, + "grad_norm": 0.5638371706008911, + "learning_rate": 5.931693121567492e-05, + "loss": 1.7005, + "step": 8069 + }, + { + "epoch": 0.4498077030265871, + "grad_norm": 0.5460227131843567, + "learning_rate": 5.930818278420005e-05, + "loss": 1.8827, + "step": 8070 + }, + { + "epoch": 0.4498634412797503, + "grad_norm": 0.5335036516189575, + "learning_rate": 5.9299434057523894e-05, + "loss": 1.6689, + "step": 8071 + }, + { + "epoch": 0.44991917953291344, + "grad_norm": 0.45309698581695557, + "learning_rate": 5.929068503592391e-05, + "loss": 1.1558, + "step": 8072 + }, + { + "epoch": 0.44997491778607657, + "grad_norm": 0.5678838491439819, + "learning_rate": 5.9281935719677574e-05, + "loss": 1.7916, + "step": 8073 + }, + { + "epoch": 0.45003065603923975, + "grad_norm": 0.6037769913673401, + "learning_rate": 5.927318610906234e-05, + "loss": 1.6458, + "step": 8074 + }, + { + "epoch": 0.4500863942924029, + "grad_norm": 0.5376781821250916, + "learning_rate": 5.9264436204355724e-05, + "loss": 1.754, + "step": 8075 + }, + { + "epoch": 0.450142132545566, + "grad_norm": 0.5493988394737244, + "learning_rate": 5.92556860058352e-05, + "loss": 1.7992, + "step": 8076 + }, + { + "epoch": 0.4501978707987292, + "grad_norm": 0.5373069643974304, + "learning_rate": 5.9246935513778276e-05, + "loss": 1.6756, + "step": 8077 + }, + { + "epoch": 0.4502536090518923, + "grad_norm": 0.5574460625648499, + "learning_rate": 5.923818472846248e-05, + "loss": 1.6423, + "step": 8078 + }, + { + "epoch": 0.45030934730505545, + "grad_norm": 0.5568375587463379, + "learning_rate": 5.922943365016531e-05, + "loss": 1.7708, + "step": 8079 + }, + { + "epoch": 0.4503650855582186, + "grad_norm": 0.551171064376831, + "learning_rate": 5.922068227916433e-05, + "loss": 1.7107, + "step": 8080 + }, + { + "epoch": 0.45042082381138177, + "grad_norm": 0.5870986580848694, + "learning_rate": 5.9211930615737066e-05, + "loss": 1.801, + "step": 8081 + }, + { + "epoch": 0.4504765620645449, + "grad_norm": 0.5700268745422363, + "learning_rate": 5.920317866016108e-05, + "loss": 1.6317, + "step": 8082 + }, + { + "epoch": 0.450532300317708, + "grad_norm": 0.5469490885734558, + "learning_rate": 5.919442641271391e-05, + "loss": 1.6841, + "step": 8083 + }, + { + "epoch": 0.4505880385708712, + "grad_norm": 0.5380752682685852, + "learning_rate": 5.9185673873673154e-05, + "loss": 1.3761, + "step": 8084 + }, + { + "epoch": 0.45064377682403434, + "grad_norm": 0.6156383156776428, + "learning_rate": 5.917692104331637e-05, + "loss": 1.9012, + "step": 8085 + }, + { + "epoch": 0.45069951507719747, + "grad_norm": 0.6044989824295044, + "learning_rate": 5.916816792192116e-05, + "loss": 1.8825, + "step": 8086 + }, + { + "epoch": 0.45075525333036065, + "grad_norm": 0.5541858673095703, + "learning_rate": 5.915941450976512e-05, + "loss": 1.6097, + "step": 8087 + }, + { + "epoch": 0.4508109915835238, + "grad_norm": 0.5468337535858154, + "learning_rate": 5.9150660807125844e-05, + "loss": 1.7299, + "step": 8088 + }, + { + "epoch": 0.4508667298366869, + "grad_norm": 0.6255477070808411, + "learning_rate": 5.9141906814280975e-05, + "loss": 1.818, + "step": 8089 + }, + { + "epoch": 0.45092246808985004, + "grad_norm": 0.5574450492858887, + "learning_rate": 5.9133152531508106e-05, + "loss": 1.8804, + "step": 8090 + }, + { + "epoch": 0.4509782063430132, + "grad_norm": 0.5240482091903687, + "learning_rate": 5.91243979590849e-05, + "loss": 1.6162, + "step": 8091 + }, + { + "epoch": 0.45103394459617635, + "grad_norm": 0.5322662591934204, + "learning_rate": 5.911564309728899e-05, + "loss": 1.7833, + "step": 8092 + }, + { + "epoch": 0.4510896828493395, + "grad_norm": 0.5365003347396851, + "learning_rate": 5.910688794639803e-05, + "loss": 1.5982, + "step": 8093 + }, + { + "epoch": 0.45114542110250266, + "grad_norm": 0.5948169827461243, + "learning_rate": 5.909813250668967e-05, + "loss": 1.8386, + "step": 8094 + }, + { + "epoch": 0.4512011593556658, + "grad_norm": 0.5501197576522827, + "learning_rate": 5.9089376778441606e-05, + "loss": 1.748, + "step": 8095 + }, + { + "epoch": 0.4512568976088289, + "grad_norm": 0.5238162875175476, + "learning_rate": 5.908062076193149e-05, + "loss": 1.4871, + "step": 8096 + }, + { + "epoch": 0.4513126358619921, + "grad_norm": 0.515355110168457, + "learning_rate": 5.907186445743704e-05, + "loss": 1.4985, + "step": 8097 + }, + { + "epoch": 0.45136837411515524, + "grad_norm": 0.5451371073722839, + "learning_rate": 5.9063107865235936e-05, + "loss": 1.7953, + "step": 8098 + }, + { + "epoch": 0.45142411236831836, + "grad_norm": 0.5602155327796936, + "learning_rate": 5.90543509856059e-05, + "loss": 1.4848, + "step": 8099 + }, + { + "epoch": 0.45147985062148155, + "grad_norm": 0.6136230826377869, + "learning_rate": 5.904559381882463e-05, + "loss": 1.8602, + "step": 8100 + }, + { + "epoch": 0.4515355888746447, + "grad_norm": 0.5416921973228455, + "learning_rate": 5.9036836365169865e-05, + "loss": 1.7242, + "step": 8101 + }, + { + "epoch": 0.4515913271278078, + "grad_norm": 0.5299700498580933, + "learning_rate": 5.9028078624919344e-05, + "loss": 1.4976, + "step": 8102 + }, + { + "epoch": 0.45164706538097094, + "grad_norm": 0.5295999050140381, + "learning_rate": 5.901932059835081e-05, + "loss": 1.667, + "step": 8103 + }, + { + "epoch": 0.4517028036341341, + "grad_norm": 0.5291856527328491, + "learning_rate": 5.9010562285742e-05, + "loss": 1.5909, + "step": 8104 + }, + { + "epoch": 0.45175854188729725, + "grad_norm": 0.5456459522247314, + "learning_rate": 5.9001803687370696e-05, + "loss": 1.6947, + "step": 8105 + }, + { + "epoch": 0.4518142801404604, + "grad_norm": 0.534061074256897, + "learning_rate": 5.8993044803514674e-05, + "loss": 1.4796, + "step": 8106 + }, + { + "epoch": 0.45187001839362356, + "grad_norm": 0.5795206427574158, + "learning_rate": 5.8984285634451695e-05, + "loss": 1.8176, + "step": 8107 + }, + { + "epoch": 0.4519257566467867, + "grad_norm": 0.5638490915298462, + "learning_rate": 5.897552618045956e-05, + "loss": 1.6067, + "step": 8108 + }, + { + "epoch": 0.4519814948999498, + "grad_norm": 0.5725950002670288, + "learning_rate": 5.896676644181607e-05, + "loss": 1.6761, + "step": 8109 + }, + { + "epoch": 0.452037233153113, + "grad_norm": 0.6189979314804077, + "learning_rate": 5.8958006418799005e-05, + "loss": 1.8323, + "step": 8110 + }, + { + "epoch": 0.45209297140627613, + "grad_norm": 0.550565779209137, + "learning_rate": 5.894924611168622e-05, + "loss": 1.865, + "step": 8111 + }, + { + "epoch": 0.45214870965943926, + "grad_norm": 0.563420832157135, + "learning_rate": 5.894048552075554e-05, + "loss": 1.8, + "step": 8112 + }, + { + "epoch": 0.4522044479126024, + "grad_norm": 0.5111345052719116, + "learning_rate": 5.893172464628477e-05, + "loss": 1.4806, + "step": 8113 + }, + { + "epoch": 0.4522601861657656, + "grad_norm": 0.566088855266571, + "learning_rate": 5.8922963488551775e-05, + "loss": 1.7427, + "step": 8114 + }, + { + "epoch": 0.4523159244189287, + "grad_norm": 0.5696318745613098, + "learning_rate": 5.89142020478344e-05, + "loss": 1.8576, + "step": 8115 + }, + { + "epoch": 0.45237166267209183, + "grad_norm": 0.5730637907981873, + "learning_rate": 5.890544032441051e-05, + "loss": 1.6966, + "step": 8116 + }, + { + "epoch": 0.452427400925255, + "grad_norm": 0.5427675247192383, + "learning_rate": 5.889667831855797e-05, + "loss": 1.639, + "step": 8117 + }, + { + "epoch": 0.45248313917841815, + "grad_norm": 0.6031304001808167, + "learning_rate": 5.888791603055467e-05, + "loss": 1.7707, + "step": 8118 + }, + { + "epoch": 0.4525388774315813, + "grad_norm": 0.5573417544364929, + "learning_rate": 5.887915346067851e-05, + "loss": 1.8751, + "step": 8119 + }, + { + "epoch": 0.45259461568474446, + "grad_norm": 0.5398233532905579, + "learning_rate": 5.8870390609207337e-05, + "loss": 1.5854, + "step": 8120 + }, + { + "epoch": 0.4526503539379076, + "grad_norm": 0.554905354976654, + "learning_rate": 5.886162747641912e-05, + "loss": 1.6138, + "step": 8121 + }, + { + "epoch": 0.4527060921910707, + "grad_norm": 0.5116898417472839, + "learning_rate": 5.885286406259174e-05, + "loss": 1.4997, + "step": 8122 + }, + { + "epoch": 0.4527618304442339, + "grad_norm": 0.5095398426055908, + "learning_rate": 5.884410036800312e-05, + "loss": 1.372, + "step": 8123 + }, + { + "epoch": 0.45281756869739703, + "grad_norm": 0.5345844626426697, + "learning_rate": 5.883533639293119e-05, + "loss": 1.7398, + "step": 8124 + }, + { + "epoch": 0.45287330695056016, + "grad_norm": 0.5889625549316406, + "learning_rate": 5.882657213765393e-05, + "loss": 1.8826, + "step": 8125 + }, + { + "epoch": 0.4529290452037233, + "grad_norm": 0.5907882452011108, + "learning_rate": 5.881780760244926e-05, + "loss": 1.8187, + "step": 8126 + }, + { + "epoch": 0.4529847834568865, + "grad_norm": 0.5326589941978455, + "learning_rate": 5.8809042787595135e-05, + "loss": 1.5317, + "step": 8127 + }, + { + "epoch": 0.4530405217100496, + "grad_norm": 0.6067203283309937, + "learning_rate": 5.880027769336953e-05, + "loss": 1.9912, + "step": 8128 + }, + { + "epoch": 0.45309625996321273, + "grad_norm": 0.5273611545562744, + "learning_rate": 5.879151232005044e-05, + "loss": 1.7771, + "step": 8129 + }, + { + "epoch": 0.4531519982163759, + "grad_norm": 0.5791671872138977, + "learning_rate": 5.8782746667915824e-05, + "loss": 1.9728, + "step": 8130 + }, + { + "epoch": 0.45320773646953905, + "grad_norm": 0.5748934149742126, + "learning_rate": 5.877398073724368e-05, + "loss": 1.7932, + "step": 8131 + }, + { + "epoch": 0.4532634747227022, + "grad_norm": 0.5750080943107605, + "learning_rate": 5.876521452831205e-05, + "loss": 1.6562, + "step": 8132 + }, + { + "epoch": 0.45331921297586536, + "grad_norm": 0.5455517172813416, + "learning_rate": 5.87564480413989e-05, + "loss": 1.6491, + "step": 8133 + }, + { + "epoch": 0.4533749512290285, + "grad_norm": 0.5786875486373901, + "learning_rate": 5.8747681276782294e-05, + "loss": 1.6799, + "step": 8134 + }, + { + "epoch": 0.4534306894821916, + "grad_norm": 0.5193260908126831, + "learning_rate": 5.8738914234740225e-05, + "loss": 1.7299, + "step": 8135 + }, + { + "epoch": 0.45348642773535475, + "grad_norm": 0.5477581024169922, + "learning_rate": 5.8730146915550745e-05, + "loss": 1.529, + "step": 8136 + }, + { + "epoch": 0.45354216598851793, + "grad_norm": 0.5622334480285645, + "learning_rate": 5.872137931949191e-05, + "loss": 1.7301, + "step": 8137 + }, + { + "epoch": 0.45359790424168106, + "grad_norm": 0.5410364866256714, + "learning_rate": 5.871261144684177e-05, + "loss": 1.7159, + "step": 8138 + }, + { + "epoch": 0.4536536424948442, + "grad_norm": 0.5440908670425415, + "learning_rate": 5.870384329787839e-05, + "loss": 1.6208, + "step": 8139 + }, + { + "epoch": 0.4537093807480074, + "grad_norm": 0.5730171799659729, + "learning_rate": 5.8695074872879855e-05, + "loss": 1.7554, + "step": 8140 + }, + { + "epoch": 0.4537651190011705, + "grad_norm": 0.5274659991264343, + "learning_rate": 5.868630617212424e-05, + "loss": 1.6493, + "step": 8141 + }, + { + "epoch": 0.45382085725433363, + "grad_norm": 0.5639094114303589, + "learning_rate": 5.867753719588963e-05, + "loss": 1.8717, + "step": 8142 + }, + { + "epoch": 0.4538765955074968, + "grad_norm": 0.5402084589004517, + "learning_rate": 5.8668767944454136e-05, + "loss": 1.7959, + "step": 8143 + }, + { + "epoch": 0.45393233376065995, + "grad_norm": 0.5999549627304077, + "learning_rate": 5.865999841809586e-05, + "loss": 1.7492, + "step": 8144 + }, + { + "epoch": 0.4539880720138231, + "grad_norm": 0.5832345485687256, + "learning_rate": 5.865122861709295e-05, + "loss": 1.7432, + "step": 8145 + }, + { + "epoch": 0.45404381026698626, + "grad_norm": 0.500333309173584, + "learning_rate": 5.864245854172349e-05, + "loss": 1.5536, + "step": 8146 + }, + { + "epoch": 0.4540995485201494, + "grad_norm": 0.5283179879188538, + "learning_rate": 5.8633688192265645e-05, + "loss": 1.5528, + "step": 8147 + }, + { + "epoch": 0.4541552867733125, + "grad_norm": 0.5074849128723145, + "learning_rate": 5.862491756899753e-05, + "loss": 1.5251, + "step": 8148 + }, + { + "epoch": 0.45421102502647565, + "grad_norm": 0.5706311464309692, + "learning_rate": 5.8616146672197326e-05, + "loss": 1.5709, + "step": 8149 + }, + { + "epoch": 0.45426676327963883, + "grad_norm": 0.570326566696167, + "learning_rate": 5.8607375502143183e-05, + "loss": 1.6585, + "step": 8150 + }, + { + "epoch": 0.45432250153280196, + "grad_norm": 0.7040314674377441, + "learning_rate": 5.859860405911328e-05, + "loss": 2.0239, + "step": 8151 + }, + { + "epoch": 0.4543782397859651, + "grad_norm": 0.5602174401283264, + "learning_rate": 5.858983234338579e-05, + "loss": 1.5565, + "step": 8152 + }, + { + "epoch": 0.4544339780391283, + "grad_norm": 0.596564531326294, + "learning_rate": 5.858106035523888e-05, + "loss": 1.8482, + "step": 8153 + }, + { + "epoch": 0.4544897162922914, + "grad_norm": 0.5571820735931396, + "learning_rate": 5.85722880949508e-05, + "loss": 1.6401, + "step": 8154 + }, + { + "epoch": 0.45454545454545453, + "grad_norm": 0.5759769678115845, + "learning_rate": 5.8563515562799695e-05, + "loss": 1.8876, + "step": 8155 + }, + { + "epoch": 0.4546011927986177, + "grad_norm": 0.526823103427887, + "learning_rate": 5.855474275906381e-05, + "loss": 1.4215, + "step": 8156 + }, + { + "epoch": 0.45465693105178084, + "grad_norm": 0.5801699161529541, + "learning_rate": 5.854596968402136e-05, + "loss": 1.8225, + "step": 8157 + }, + { + "epoch": 0.454712669304944, + "grad_norm": 0.548812747001648, + "learning_rate": 5.8537196337950596e-05, + "loss": 1.6582, + "step": 8158 + }, + { + "epoch": 0.4547684075581071, + "grad_norm": 0.5647279024124146, + "learning_rate": 5.8528422721129726e-05, + "loss": 1.6121, + "step": 8159 + }, + { + "epoch": 0.4548241458112703, + "grad_norm": 0.5501880645751953, + "learning_rate": 5.8519648833837013e-05, + "loss": 1.5704, + "step": 8160 + }, + { + "epoch": 0.4548798840644334, + "grad_norm": 0.5714605450630188, + "learning_rate": 5.851087467635071e-05, + "loss": 1.918, + "step": 8161 + }, + { + "epoch": 0.45493562231759654, + "grad_norm": 0.5872429609298706, + "learning_rate": 5.8502100248949085e-05, + "loss": 1.7381, + "step": 8162 + }, + { + "epoch": 0.45499136057075973, + "grad_norm": 0.5113133788108826, + "learning_rate": 5.8493325551910405e-05, + "loss": 1.6602, + "step": 8163 + }, + { + "epoch": 0.45504709882392286, + "grad_norm": 0.5724974274635315, + "learning_rate": 5.848455058551298e-05, + "loss": 1.7762, + "step": 8164 + }, + { + "epoch": 0.455102837077086, + "grad_norm": 0.5925339460372925, + "learning_rate": 5.8475775350035056e-05, + "loss": 1.8456, + "step": 8165 + }, + { + "epoch": 0.45515857533024917, + "grad_norm": 0.567402720451355, + "learning_rate": 5.846699984575497e-05, + "loss": 1.6512, + "step": 8166 + }, + { + "epoch": 0.4552143135834123, + "grad_norm": 0.53789883852005, + "learning_rate": 5.8458224072951005e-05, + "loss": 1.675, + "step": 8167 + }, + { + "epoch": 0.45527005183657543, + "grad_norm": 0.563400149345398, + "learning_rate": 5.844944803190149e-05, + "loss": 1.4973, + "step": 8168 + }, + { + "epoch": 0.4553257900897386, + "grad_norm": 0.5786770582199097, + "learning_rate": 5.844067172288474e-05, + "loss": 1.6223, + "step": 8169 + }, + { + "epoch": 0.45538152834290174, + "grad_norm": 0.5910102725028992, + "learning_rate": 5.843189514617911e-05, + "loss": 1.7822, + "step": 8170 + }, + { + "epoch": 0.45543726659606487, + "grad_norm": 0.5599364638328552, + "learning_rate": 5.8423118302062915e-05, + "loss": 1.7511, + "step": 8171 + }, + { + "epoch": 0.455493004849228, + "grad_norm": 0.5284358263015747, + "learning_rate": 5.841434119081453e-05, + "loss": 1.6494, + "step": 8172 + }, + { + "epoch": 0.4555487431023912, + "grad_norm": 0.5970794558525085, + "learning_rate": 5.840556381271229e-05, + "loss": 1.6952, + "step": 8173 + }, + { + "epoch": 0.4556044813555543, + "grad_norm": 0.5448065400123596, + "learning_rate": 5.839678616803458e-05, + "loss": 1.5907, + "step": 8174 + }, + { + "epoch": 0.45566021960871744, + "grad_norm": 0.5598198771476746, + "learning_rate": 5.838800825705977e-05, + "loss": 1.6862, + "step": 8175 + }, + { + "epoch": 0.4557159578618806, + "grad_norm": 0.5819631218910217, + "learning_rate": 5.837923008006623e-05, + "loss": 1.7354, + "step": 8176 + }, + { + "epoch": 0.45577169611504376, + "grad_norm": 0.5947074890136719, + "learning_rate": 5.837045163733239e-05, + "loss": 1.7971, + "step": 8177 + }, + { + "epoch": 0.4558274343682069, + "grad_norm": 0.541515588760376, + "learning_rate": 5.8361672929136614e-05, + "loss": 1.4939, + "step": 8178 + }, + { + "epoch": 0.45588317262137007, + "grad_norm": 0.670753002166748, + "learning_rate": 5.835289395575731e-05, + "loss": 1.8816, + "step": 8179 + }, + { + "epoch": 0.4559389108745332, + "grad_norm": 0.5665016174316406, + "learning_rate": 5.8344114717472943e-05, + "loss": 1.6907, + "step": 8180 + }, + { + "epoch": 0.4559946491276963, + "grad_norm": 0.5885823369026184, + "learning_rate": 5.833533521456188e-05, + "loss": 1.6905, + "step": 8181 + }, + { + "epoch": 0.45605038738085946, + "grad_norm": 0.5672965049743652, + "learning_rate": 5.832655544730259e-05, + "loss": 1.5996, + "step": 8182 + }, + { + "epoch": 0.45610612563402264, + "grad_norm": 0.5488877296447754, + "learning_rate": 5.831777541597351e-05, + "loss": 1.6316, + "step": 8183 + }, + { + "epoch": 0.45616186388718577, + "grad_norm": 0.541111409664154, + "learning_rate": 5.8308995120853096e-05, + "loss": 1.7246, + "step": 8184 + }, + { + "epoch": 0.4562176021403489, + "grad_norm": 0.5794996619224548, + "learning_rate": 5.830021456221979e-05, + "loss": 1.8438, + "step": 8185 + }, + { + "epoch": 0.4562733403935121, + "grad_norm": 0.4965246021747589, + "learning_rate": 5.829143374035209e-05, + "loss": 1.2569, + "step": 8186 + }, + { + "epoch": 0.4563290786466752, + "grad_norm": 0.5464833974838257, + "learning_rate": 5.8282652655528426e-05, + "loss": 1.6355, + "step": 8187 + }, + { + "epoch": 0.45638481689983834, + "grad_norm": 0.617215096950531, + "learning_rate": 5.827387130802733e-05, + "loss": 1.7473, + "step": 8188 + }, + { + "epoch": 0.4564405551530015, + "grad_norm": 0.6064026355743408, + "learning_rate": 5.826508969812726e-05, + "loss": 1.817, + "step": 8189 + }, + { + "epoch": 0.45649629340616465, + "grad_norm": 0.6004077792167664, + "learning_rate": 5.825630782610676e-05, + "loss": 1.8728, + "step": 8190 + }, + { + "epoch": 0.4565520316593278, + "grad_norm": 0.6301288604736328, + "learning_rate": 5.82475256922443e-05, + "loss": 1.8616, + "step": 8191 + }, + { + "epoch": 0.45660776991249097, + "grad_norm": 0.540440022945404, + "learning_rate": 5.8238743296818396e-05, + "loss": 1.7224, + "step": 8192 + }, + { + "epoch": 0.4566635081656541, + "grad_norm": 0.5390138626098633, + "learning_rate": 5.8229960640107617e-05, + "loss": 1.556, + "step": 8193 + }, + { + "epoch": 0.4567192464188172, + "grad_norm": 0.5261824131011963, + "learning_rate": 5.822117772239045e-05, + "loss": 1.6086, + "step": 8194 + }, + { + "epoch": 0.45677498467198036, + "grad_norm": 0.543070375919342, + "learning_rate": 5.821239454394547e-05, + "loss": 1.5987, + "step": 8195 + }, + { + "epoch": 0.45683072292514354, + "grad_norm": 0.6048296689987183, + "learning_rate": 5.8203611105051204e-05, + "loss": 1.7936, + "step": 8196 + }, + { + "epoch": 0.45688646117830667, + "grad_norm": 0.5308238863945007, + "learning_rate": 5.819482740598624e-05, + "loss": 1.5304, + "step": 8197 + }, + { + "epoch": 0.4569421994314698, + "grad_norm": 0.5806917548179626, + "learning_rate": 5.8186043447029125e-05, + "loss": 1.6869, + "step": 8198 + }, + { + "epoch": 0.456997937684633, + "grad_norm": 0.5387137532234192, + "learning_rate": 5.8177259228458444e-05, + "loss": 1.7673, + "step": 8199 + }, + { + "epoch": 0.4570536759377961, + "grad_norm": 0.5830815434455872, + "learning_rate": 5.816847475055277e-05, + "loss": 1.9119, + "step": 8200 + }, + { + "epoch": 0.45710941419095924, + "grad_norm": 0.5564570426940918, + "learning_rate": 5.8159690013590695e-05, + "loss": 1.5385, + "step": 8201 + }, + { + "epoch": 0.4571651524441224, + "grad_norm": 0.5688846707344055, + "learning_rate": 5.815090501785083e-05, + "loss": 1.5954, + "step": 8202 + }, + { + "epoch": 0.45722089069728555, + "grad_norm": 0.6317092776298523, + "learning_rate": 5.814211976361179e-05, + "loss": 1.9886, + "step": 8203 + }, + { + "epoch": 0.4572766289504487, + "grad_norm": 0.5649227499961853, + "learning_rate": 5.813333425115218e-05, + "loss": 1.6259, + "step": 8204 + }, + { + "epoch": 0.4573323672036118, + "grad_norm": 0.5452385544776917, + "learning_rate": 5.812454848075063e-05, + "loss": 1.7129, + "step": 8205 + }, + { + "epoch": 0.457388105456775, + "grad_norm": 0.5575756430625916, + "learning_rate": 5.8115762452685774e-05, + "loss": 1.7543, + "step": 8206 + }, + { + "epoch": 0.4574438437099381, + "grad_norm": 0.5120208263397217, + "learning_rate": 5.810697616723624e-05, + "loss": 1.5619, + "step": 8207 + }, + { + "epoch": 0.45749958196310125, + "grad_norm": 0.5111353397369385, + "learning_rate": 5.809818962468069e-05, + "loss": 1.5594, + "step": 8208 + }, + { + "epoch": 0.45755532021626444, + "grad_norm": 0.5274066925048828, + "learning_rate": 5.8089402825297776e-05, + "loss": 1.5727, + "step": 8209 + }, + { + "epoch": 0.45761105846942757, + "grad_norm": 0.531512439250946, + "learning_rate": 5.80806157693662e-05, + "loss": 1.6845, + "step": 8210 + }, + { + "epoch": 0.4576667967225907, + "grad_norm": 0.587890088558197, + "learning_rate": 5.807182845716458e-05, + "loss": 1.8239, + "step": 8211 + }, + { + "epoch": 0.4577225349757539, + "grad_norm": 0.543900191783905, + "learning_rate": 5.8063040888971635e-05, + "loss": 1.9671, + "step": 8212 + }, + { + "epoch": 0.457778273228917, + "grad_norm": 0.5269332528114319, + "learning_rate": 5.8054253065066024e-05, + "loss": 1.5801, + "step": 8213 + }, + { + "epoch": 0.45783401148208014, + "grad_norm": 0.5568074584007263, + "learning_rate": 5.8045464985726474e-05, + "loss": 1.5843, + "step": 8214 + }, + { + "epoch": 0.4578897497352433, + "grad_norm": 0.5887969136238098, + "learning_rate": 5.803667665123168e-05, + "loss": 1.9532, + "step": 8215 + }, + { + "epoch": 0.45794548798840645, + "grad_norm": 0.6071587204933167, + "learning_rate": 5.802788806186038e-05, + "loss": 1.9501, + "step": 8216 + }, + { + "epoch": 0.4580012262415696, + "grad_norm": 0.5481032133102417, + "learning_rate": 5.801909921789126e-05, + "loss": 1.7435, + "step": 8217 + }, + { + "epoch": 0.4580569644947327, + "grad_norm": 0.6313177347183228, + "learning_rate": 5.801031011960306e-05, + "loss": 1.928, + "step": 8218 + }, + { + "epoch": 0.4581127027478959, + "grad_norm": 0.5789720416069031, + "learning_rate": 5.800152076727454e-05, + "loss": 1.8, + "step": 8219 + }, + { + "epoch": 0.458168441001059, + "grad_norm": 0.5438299775123596, + "learning_rate": 5.799273116118443e-05, + "loss": 1.6805, + "step": 8220 + }, + { + "epoch": 0.45822417925422215, + "grad_norm": 0.5296357870101929, + "learning_rate": 5.798394130161149e-05, + "loss": 1.4218, + "step": 8221 + }, + { + "epoch": 0.45827991750738534, + "grad_norm": 0.6217812895774841, + "learning_rate": 5.7975151188834475e-05, + "loss": 1.7633, + "step": 8222 + }, + { + "epoch": 0.45833565576054847, + "grad_norm": 0.6416480541229248, + "learning_rate": 5.796636082313217e-05, + "loss": 2.0147, + "step": 8223 + }, + { + "epoch": 0.4583913940137116, + "grad_norm": 0.5263529419898987, + "learning_rate": 5.795757020478334e-05, + "loss": 1.5335, + "step": 8224 + }, + { + "epoch": 0.4584471322668748, + "grad_norm": 0.565466046333313, + "learning_rate": 5.794877933406679e-05, + "loss": 1.778, + "step": 8225 + }, + { + "epoch": 0.4585028705200379, + "grad_norm": 0.5382056832313538, + "learning_rate": 5.79399882112613e-05, + "loss": 1.678, + "step": 8226 + }, + { + "epoch": 0.45855860877320104, + "grad_norm": 0.5097582340240479, + "learning_rate": 5.7931196836645675e-05, + "loss": 1.5224, + "step": 8227 + }, + { + "epoch": 0.45861434702636417, + "grad_norm": 0.5619562268257141, + "learning_rate": 5.792240521049872e-05, + "loss": 1.9743, + "step": 8228 + }, + { + "epoch": 0.45867008527952735, + "grad_norm": 0.57401442527771, + "learning_rate": 5.791361333309926e-05, + "loss": 1.6526, + "step": 8229 + }, + { + "epoch": 0.4587258235326905, + "grad_norm": 0.557773232460022, + "learning_rate": 5.790482120472615e-05, + "loss": 1.7427, + "step": 8230 + }, + { + "epoch": 0.4587815617858536, + "grad_norm": 0.5370197296142578, + "learning_rate": 5.789602882565818e-05, + "loss": 1.5028, + "step": 8231 + }, + { + "epoch": 0.4588373000390168, + "grad_norm": 0.559916079044342, + "learning_rate": 5.788723619617422e-05, + "loss": 1.6115, + "step": 8232 + }, + { + "epoch": 0.4588930382921799, + "grad_norm": 0.5461910367012024, + "learning_rate": 5.787844331655311e-05, + "loss": 1.5789, + "step": 8233 + }, + { + "epoch": 0.45894877654534305, + "grad_norm": 0.5319302082061768, + "learning_rate": 5.786965018707371e-05, + "loss": 1.66, + "step": 8234 + }, + { + "epoch": 0.45900451479850624, + "grad_norm": 0.5757958292961121, + "learning_rate": 5.786085680801488e-05, + "loss": 1.9192, + "step": 8235 + }, + { + "epoch": 0.45906025305166936, + "grad_norm": 0.523041844367981, + "learning_rate": 5.785206317965553e-05, + "loss": 1.5435, + "step": 8236 + }, + { + "epoch": 0.4591159913048325, + "grad_norm": 0.5196270942687988, + "learning_rate": 5.7843269302274506e-05, + "loss": 1.2152, + "step": 8237 + }, + { + "epoch": 0.4591717295579957, + "grad_norm": 0.5284752249717712, + "learning_rate": 5.7834475176150715e-05, + "loss": 1.6407, + "step": 8238 + }, + { + "epoch": 0.4592274678111588, + "grad_norm": 0.5639576315879822, + "learning_rate": 5.782568080156303e-05, + "loss": 1.8297, + "step": 8239 + }, + { + "epoch": 0.45928320606432194, + "grad_norm": 0.5723278522491455, + "learning_rate": 5.781688617879039e-05, + "loss": 1.7981, + "step": 8240 + }, + { + "epoch": 0.45933894431748507, + "grad_norm": 0.5638182759284973, + "learning_rate": 5.780809130811169e-05, + "loss": 1.6244, + "step": 8241 + }, + { + "epoch": 0.45939468257064825, + "grad_norm": 0.5704604983329773, + "learning_rate": 5.779929618980586e-05, + "loss": 1.6348, + "step": 8242 + }, + { + "epoch": 0.4594504208238114, + "grad_norm": 0.5768876671791077, + "learning_rate": 5.779050082415184e-05, + "loss": 1.7342, + "step": 8243 + }, + { + "epoch": 0.4595061590769745, + "grad_norm": 0.5308094620704651, + "learning_rate": 5.778170521142854e-05, + "loss": 1.6838, + "step": 8244 + }, + { + "epoch": 0.4595618973301377, + "grad_norm": 0.6009156703948975, + "learning_rate": 5.777290935191493e-05, + "loss": 1.72, + "step": 8245 + }, + { + "epoch": 0.4596176355833008, + "grad_norm": 0.5695474743843079, + "learning_rate": 5.776411324588995e-05, + "loss": 1.6783, + "step": 8246 + }, + { + "epoch": 0.45967337383646395, + "grad_norm": 0.5541953444480896, + "learning_rate": 5.775531689363256e-05, + "loss": 1.5248, + "step": 8247 + }, + { + "epoch": 0.45972911208962713, + "grad_norm": 0.5543676614761353, + "learning_rate": 5.7746520295421736e-05, + "loss": 1.5673, + "step": 8248 + }, + { + "epoch": 0.45978485034279026, + "grad_norm": 0.6300926804542542, + "learning_rate": 5.773772345153648e-05, + "loss": 1.9275, + "step": 8249 + }, + { + "epoch": 0.4598405885959534, + "grad_norm": 0.580083429813385, + "learning_rate": 5.772892636225572e-05, + "loss": 1.583, + "step": 8250 + }, + { + "epoch": 0.4598963268491165, + "grad_norm": 0.6072207689285278, + "learning_rate": 5.7720129027858496e-05, + "loss": 1.6752, + "step": 8251 + }, + { + "epoch": 0.4599520651022797, + "grad_norm": 0.575436532497406, + "learning_rate": 5.771133144862377e-05, + "loss": 1.5191, + "step": 8252 + }, + { + "epoch": 0.46000780335544283, + "grad_norm": 0.5946778655052185, + "learning_rate": 5.770253362483059e-05, + "loss": 1.7338, + "step": 8253 + }, + { + "epoch": 0.46006354160860596, + "grad_norm": 0.5782346129417419, + "learning_rate": 5.769373555675794e-05, + "loss": 1.9825, + "step": 8254 + }, + { + "epoch": 0.46011927986176915, + "grad_norm": 0.6065311431884766, + "learning_rate": 5.7684937244684856e-05, + "loss": 1.8879, + "step": 8255 + }, + { + "epoch": 0.4601750181149323, + "grad_norm": 0.5789337158203125, + "learning_rate": 5.767613868889038e-05, + "loss": 1.5408, + "step": 8256 + }, + { + "epoch": 0.4602307563680954, + "grad_norm": 0.5640459060668945, + "learning_rate": 5.766733988965354e-05, + "loss": 1.7434, + "step": 8257 + }, + { + "epoch": 0.4602864946212586, + "grad_norm": 0.5351431965827942, + "learning_rate": 5.765854084725337e-05, + "loss": 1.7586, + "step": 8258 + }, + { + "epoch": 0.4603422328744217, + "grad_norm": 0.6039308905601501, + "learning_rate": 5.764974156196895e-05, + "loss": 1.8, + "step": 8259 + }, + { + "epoch": 0.46039797112758485, + "grad_norm": 0.5545447468757629, + "learning_rate": 5.764094203407933e-05, + "loss": 1.5867, + "step": 8260 + }, + { + "epoch": 0.46045370938074803, + "grad_norm": 0.5933241248130798, + "learning_rate": 5.763214226386355e-05, + "loss": 1.8117, + "step": 8261 + }, + { + "epoch": 0.46050944763391116, + "grad_norm": 0.6593655943870544, + "learning_rate": 5.7623342251600745e-05, + "loss": 1.6466, + "step": 8262 + }, + { + "epoch": 0.4605651858870743, + "grad_norm": 0.5840887427330017, + "learning_rate": 5.761454199756996e-05, + "loss": 1.6135, + "step": 8263 + }, + { + "epoch": 0.4606209241402374, + "grad_norm": 0.5381019711494446, + "learning_rate": 5.7605741502050314e-05, + "loss": 1.6211, + "step": 8264 + }, + { + "epoch": 0.4606766623934006, + "grad_norm": 0.6085990071296692, + "learning_rate": 5.759694076532087e-05, + "loss": 1.795, + "step": 8265 + }, + { + "epoch": 0.46073240064656373, + "grad_norm": 0.5574647784233093, + "learning_rate": 5.758813978766077e-05, + "loss": 1.4925, + "step": 8266 + }, + { + "epoch": 0.46078813889972686, + "grad_norm": 0.6263840794563293, + "learning_rate": 5.75793385693491e-05, + "loss": 1.8677, + "step": 8267 + }, + { + "epoch": 0.46084387715289005, + "grad_norm": 0.543647289276123, + "learning_rate": 5.7570537110665026e-05, + "loss": 1.7692, + "step": 8268 + }, + { + "epoch": 0.4608996154060532, + "grad_norm": 0.6330240368843079, + "learning_rate": 5.7561735411887644e-05, + "loss": 1.8521, + "step": 8269 + }, + { + "epoch": 0.4609553536592163, + "grad_norm": 0.5961319208145142, + "learning_rate": 5.75529334732961e-05, + "loss": 1.8511, + "step": 8270 + }, + { + "epoch": 0.4610110919123795, + "grad_norm": 0.5653590559959412, + "learning_rate": 5.754413129516956e-05, + "loss": 1.6472, + "step": 8271 + }, + { + "epoch": 0.4610668301655426, + "grad_norm": 0.5134671330451965, + "learning_rate": 5.753532887778714e-05, + "loss": 1.5722, + "step": 8272 + }, + { + "epoch": 0.46112256841870575, + "grad_norm": 0.5468015074729919, + "learning_rate": 5.7526526221428036e-05, + "loss": 1.6829, + "step": 8273 + }, + { + "epoch": 0.4611783066718689, + "grad_norm": 0.5542712211608887, + "learning_rate": 5.751772332637137e-05, + "loss": 1.6583, + "step": 8274 + }, + { + "epoch": 0.46123404492503206, + "grad_norm": 0.554300844669342, + "learning_rate": 5.75089201928964e-05, + "loss": 1.7805, + "step": 8275 + }, + { + "epoch": 0.4612897831781952, + "grad_norm": 0.5648434162139893, + "learning_rate": 5.750011682128222e-05, + "loss": 1.8315, + "step": 8276 + }, + { + "epoch": 0.4613455214313583, + "grad_norm": 0.5622681975364685, + "learning_rate": 5.7491313211808095e-05, + "loss": 1.6431, + "step": 8277 + }, + { + "epoch": 0.4614012596845215, + "grad_norm": 0.5813915133476257, + "learning_rate": 5.748250936475318e-05, + "loss": 1.9023, + "step": 8278 + }, + { + "epoch": 0.46145699793768463, + "grad_norm": 0.5567924380302429, + "learning_rate": 5.747370528039668e-05, + "loss": 1.7468, + "step": 8279 + }, + { + "epoch": 0.46151273619084776, + "grad_norm": 0.5861298441886902, + "learning_rate": 5.7464900959017844e-05, + "loss": 1.7059, + "step": 8280 + }, + { + "epoch": 0.46156847444401095, + "grad_norm": 0.642804741859436, + "learning_rate": 5.745609640089585e-05, + "loss": 1.8385, + "step": 8281 + }, + { + "epoch": 0.4616242126971741, + "grad_norm": 0.5455397963523865, + "learning_rate": 5.744729160630998e-05, + "loss": 1.5585, + "step": 8282 + }, + { + "epoch": 0.4616799509503372, + "grad_norm": 0.5456379055976868, + "learning_rate": 5.743848657553943e-05, + "loss": 1.6787, + "step": 8283 + }, + { + "epoch": 0.4617356892035004, + "grad_norm": 0.6248784065246582, + "learning_rate": 5.742968130886346e-05, + "loss": 1.9457, + "step": 8284 + }, + { + "epoch": 0.4617914274566635, + "grad_norm": 0.5508323311805725, + "learning_rate": 5.74208758065613e-05, + "loss": 1.7643, + "step": 8285 + }, + { + "epoch": 0.46184716570982665, + "grad_norm": 0.5070561170578003, + "learning_rate": 5.741207006891224e-05, + "loss": 1.414, + "step": 8286 + }, + { + "epoch": 0.4619029039629898, + "grad_norm": 0.5954271554946899, + "learning_rate": 5.740326409619552e-05, + "loss": 1.7004, + "step": 8287 + }, + { + "epoch": 0.46195864221615296, + "grad_norm": 0.5585724115371704, + "learning_rate": 5.739445788869043e-05, + "loss": 1.7653, + "step": 8288 + }, + { + "epoch": 0.4620143804693161, + "grad_norm": 0.5526925325393677, + "learning_rate": 5.738565144667626e-05, + "loss": 1.7572, + "step": 8289 + }, + { + "epoch": 0.4620701187224792, + "grad_norm": 0.5708301663398743, + "learning_rate": 5.737684477043228e-05, + "loss": 1.8134, + "step": 8290 + }, + { + "epoch": 0.4621258569756424, + "grad_norm": 0.5142967104911804, + "learning_rate": 5.736803786023779e-05, + "loss": 1.4841, + "step": 8291 + }, + { + "epoch": 0.46218159522880553, + "grad_norm": 0.6403586864471436, + "learning_rate": 5.7359230716372105e-05, + "loss": 1.9146, + "step": 8292 + }, + { + "epoch": 0.46223733348196866, + "grad_norm": 0.5327916145324707, + "learning_rate": 5.735042333911452e-05, + "loss": 1.6559, + "step": 8293 + }, + { + "epoch": 0.46229307173513184, + "grad_norm": 0.5524441599845886, + "learning_rate": 5.734161572874437e-05, + "loss": 1.6659, + "step": 8294 + }, + { + "epoch": 0.462348809988295, + "grad_norm": 0.5722818970680237, + "learning_rate": 5.7332807885540976e-05, + "loss": 1.7702, + "step": 8295 + }, + { + "epoch": 0.4624045482414581, + "grad_norm": 0.5551111698150635, + "learning_rate": 5.7323999809783656e-05, + "loss": 1.6766, + "step": 8296 + }, + { + "epoch": 0.46246028649462123, + "grad_norm": 0.5412301421165466, + "learning_rate": 5.731519150175179e-05, + "loss": 1.6475, + "step": 8297 + }, + { + "epoch": 0.4625160247477844, + "grad_norm": 0.5476828813552856, + "learning_rate": 5.730638296172467e-05, + "loss": 1.643, + "step": 8298 + }, + { + "epoch": 0.46257176300094754, + "grad_norm": 0.5418581366539001, + "learning_rate": 5.7297574189981705e-05, + "loss": 1.5904, + "step": 8299 + }, + { + "epoch": 0.4626275012541107, + "grad_norm": 0.5094223022460938, + "learning_rate": 5.7288765186802204e-05, + "loss": 1.6782, + "step": 8300 + }, + { + "epoch": 0.46268323950727386, + "grad_norm": 0.5535764694213867, + "learning_rate": 5.72799559524656e-05, + "loss": 1.7858, + "step": 8301 + }, + { + "epoch": 0.462738977760437, + "grad_norm": 0.5554370284080505, + "learning_rate": 5.7271146487251224e-05, + "loss": 1.757, + "step": 8302 + }, + { + "epoch": 0.4627947160136001, + "grad_norm": 0.5177475810050964, + "learning_rate": 5.726233679143849e-05, + "loss": 1.7816, + "step": 8303 + }, + { + "epoch": 0.4628504542667633, + "grad_norm": 0.5340207815170288, + "learning_rate": 5.725352686530676e-05, + "loss": 1.742, + "step": 8304 + }, + { + "epoch": 0.46290619251992643, + "grad_norm": 0.5540534257888794, + "learning_rate": 5.724471670913545e-05, + "loss": 1.7751, + "step": 8305 + }, + { + "epoch": 0.46296193077308956, + "grad_norm": 0.539763331413269, + "learning_rate": 5.7235906323203956e-05, + "loss": 1.6988, + "step": 8306 + }, + { + "epoch": 0.46301766902625274, + "grad_norm": 0.5649262070655823, + "learning_rate": 5.7227095707791714e-05, + "loss": 1.6722, + "step": 8307 + }, + { + "epoch": 0.46307340727941587, + "grad_norm": 0.583903968334198, + "learning_rate": 5.721828486317814e-05, + "loss": 1.8056, + "step": 8308 + }, + { + "epoch": 0.463129145532579, + "grad_norm": 0.5246012210845947, + "learning_rate": 5.7209473789642644e-05, + "loss": 1.4819, + "step": 8309 + }, + { + "epoch": 0.46318488378574213, + "grad_norm": 0.5652540922164917, + "learning_rate": 5.720066248746468e-05, + "loss": 1.7022, + "step": 8310 + }, + { + "epoch": 0.4632406220389053, + "grad_norm": 0.5494220852851868, + "learning_rate": 5.7191850956923675e-05, + "loss": 1.5258, + "step": 8311 + }, + { + "epoch": 0.46329636029206844, + "grad_norm": 0.5923638343811035, + "learning_rate": 5.7183039198299105e-05, + "loss": 1.7439, + "step": 8312 + }, + { + "epoch": 0.46335209854523157, + "grad_norm": 0.6051487922668457, + "learning_rate": 5.717422721187039e-05, + "loss": 1.8911, + "step": 8313 + }, + { + "epoch": 0.46340783679839476, + "grad_norm": 0.5064337253570557, + "learning_rate": 5.7165414997917045e-05, + "loss": 1.6547, + "step": 8314 + }, + { + "epoch": 0.4634635750515579, + "grad_norm": 0.6165828704833984, + "learning_rate": 5.715660255671848e-05, + "loss": 1.8988, + "step": 8315 + }, + { + "epoch": 0.463519313304721, + "grad_norm": 0.5490414500236511, + "learning_rate": 5.714778988855422e-05, + "loss": 1.8075, + "step": 8316 + }, + { + "epoch": 0.4635750515578842, + "grad_norm": 0.5493695139884949, + "learning_rate": 5.713897699370376e-05, + "loss": 1.6288, + "step": 8317 + }, + { + "epoch": 0.46363078981104733, + "grad_norm": 0.5596882700920105, + "learning_rate": 5.713016387244656e-05, + "loss": 1.6575, + "step": 8318 + }, + { + "epoch": 0.46368652806421046, + "grad_norm": 0.562776505947113, + "learning_rate": 5.7121350525062126e-05, + "loss": 1.7129, + "step": 8319 + }, + { + "epoch": 0.4637422663173736, + "grad_norm": 0.6399055123329163, + "learning_rate": 5.7112536951829975e-05, + "loss": 1.7888, + "step": 8320 + }, + { + "epoch": 0.46379800457053677, + "grad_norm": 0.5227872729301453, + "learning_rate": 5.710372315302963e-05, + "loss": 1.6324, + "step": 8321 + }, + { + "epoch": 0.4638537428236999, + "grad_norm": 0.5664421319961548, + "learning_rate": 5.70949091289406e-05, + "loss": 1.5484, + "step": 8322 + }, + { + "epoch": 0.46390948107686303, + "grad_norm": 0.5465877652168274, + "learning_rate": 5.708609487984242e-05, + "loss": 1.5863, + "step": 8323 + }, + { + "epoch": 0.4639652193300262, + "grad_norm": 0.562119722366333, + "learning_rate": 5.707728040601462e-05, + "loss": 1.7411, + "step": 8324 + }, + { + "epoch": 0.46402095758318934, + "grad_norm": 0.569681704044342, + "learning_rate": 5.706846570773676e-05, + "loss": 1.6488, + "step": 8325 + }, + { + "epoch": 0.46407669583635247, + "grad_norm": 0.6219793558120728, + "learning_rate": 5.7059650785288354e-05, + "loss": 1.7995, + "step": 8326 + }, + { + "epoch": 0.46413243408951566, + "grad_norm": 0.5750408172607422, + "learning_rate": 5.705083563894902e-05, + "loss": 1.8457, + "step": 8327 + }, + { + "epoch": 0.4641881723426788, + "grad_norm": 0.5338056683540344, + "learning_rate": 5.7042020268998265e-05, + "loss": 1.665, + "step": 8328 + }, + { + "epoch": 0.4642439105958419, + "grad_norm": 0.5091413259506226, + "learning_rate": 5.703320467571569e-05, + "loss": 1.5915, + "step": 8329 + }, + { + "epoch": 0.4642996488490051, + "grad_norm": 0.567847490310669, + "learning_rate": 5.7024388859380875e-05, + "loss": 1.6417, + "step": 8330 + }, + { + "epoch": 0.4643553871021682, + "grad_norm": 0.591010332107544, + "learning_rate": 5.701557282027339e-05, + "loss": 1.8457, + "step": 8331 + }, + { + "epoch": 0.46441112535533136, + "grad_norm": 0.5327983498573303, + "learning_rate": 5.700675655867285e-05, + "loss": 1.6806, + "step": 8332 + }, + { + "epoch": 0.4644668636084945, + "grad_norm": 0.5359470844268799, + "learning_rate": 5.6997940074858835e-05, + "loss": 1.5137, + "step": 8333 + }, + { + "epoch": 0.46452260186165767, + "grad_norm": 0.5727723240852356, + "learning_rate": 5.698912336911097e-05, + "loss": 1.737, + "step": 8334 + }, + { + "epoch": 0.4645783401148208, + "grad_norm": 0.5366725325584412, + "learning_rate": 5.6980306441708854e-05, + "loss": 1.5039, + "step": 8335 + }, + { + "epoch": 0.4646340783679839, + "grad_norm": 0.5799429416656494, + "learning_rate": 5.6971489292932126e-05, + "loss": 1.7687, + "step": 8336 + }, + { + "epoch": 0.4646898166211471, + "grad_norm": 0.6180622577667236, + "learning_rate": 5.69626719230604e-05, + "loss": 1.8375, + "step": 8337 + }, + { + "epoch": 0.46474555487431024, + "grad_norm": 0.5698204636573792, + "learning_rate": 5.6953854332373314e-05, + "loss": 1.6076, + "step": 8338 + }, + { + "epoch": 0.46480129312747337, + "grad_norm": 0.5486071109771729, + "learning_rate": 5.6945036521150495e-05, + "loss": 1.75, + "step": 8339 + }, + { + "epoch": 0.46485703138063655, + "grad_norm": 0.5504134893417358, + "learning_rate": 5.693621848967163e-05, + "loss": 1.753, + "step": 8340 + }, + { + "epoch": 0.4649127696337997, + "grad_norm": 0.5678994059562683, + "learning_rate": 5.6927400238216354e-05, + "loss": 1.845, + "step": 8341 + }, + { + "epoch": 0.4649685078869628, + "grad_norm": 0.5259969234466553, + "learning_rate": 5.6918581767064325e-05, + "loss": 1.5699, + "step": 8342 + }, + { + "epoch": 0.46502424614012594, + "grad_norm": 0.5243310928344727, + "learning_rate": 5.690976307649523e-05, + "loss": 1.5899, + "step": 8343 + }, + { + "epoch": 0.4650799843932891, + "grad_norm": 0.5647771954536438, + "learning_rate": 5.6900944166788725e-05, + "loss": 1.7661, + "step": 8344 + }, + { + "epoch": 0.46513572264645225, + "grad_norm": 0.6884542107582092, + "learning_rate": 5.689212503822452e-05, + "loss": 1.5225, + "step": 8345 + }, + { + "epoch": 0.4651914608996154, + "grad_norm": 0.5403727889060974, + "learning_rate": 5.688330569108228e-05, + "loss": 1.5896, + "step": 8346 + }, + { + "epoch": 0.46524719915277857, + "grad_norm": 0.5732728838920593, + "learning_rate": 5.6874486125641726e-05, + "loss": 1.5632, + "step": 8347 + }, + { + "epoch": 0.4653029374059417, + "grad_norm": 0.5338377356529236, + "learning_rate": 5.686566634218254e-05, + "loss": 1.679, + "step": 8348 + }, + { + "epoch": 0.4653586756591048, + "grad_norm": 0.6053128242492676, + "learning_rate": 5.685684634098447e-05, + "loss": 2.0888, + "step": 8349 + }, + { + "epoch": 0.465414413912268, + "grad_norm": 0.5830248594284058, + "learning_rate": 5.684802612232719e-05, + "loss": 1.7972, + "step": 8350 + }, + { + "epoch": 0.46547015216543114, + "grad_norm": 0.6264218688011169, + "learning_rate": 5.683920568649047e-05, + "loss": 1.8225, + "step": 8351 + }, + { + "epoch": 0.46552589041859427, + "grad_norm": 0.6199706196784973, + "learning_rate": 5.6830385033753995e-05, + "loss": 1.6771, + "step": 8352 + }, + { + "epoch": 0.46558162867175745, + "grad_norm": 0.5402054190635681, + "learning_rate": 5.682156416439755e-05, + "loss": 1.3349, + "step": 8353 + }, + { + "epoch": 0.4656373669249206, + "grad_norm": 0.5562443733215332, + "learning_rate": 5.681274307870085e-05, + "loss": 1.606, + "step": 8354 + }, + { + "epoch": 0.4656931051780837, + "grad_norm": 0.6087068915367126, + "learning_rate": 5.680392177694366e-05, + "loss": 1.7091, + "step": 8355 + }, + { + "epoch": 0.46574884343124684, + "grad_norm": 0.5770891904830933, + "learning_rate": 5.679510025940575e-05, + "loss": 1.7989, + "step": 8356 + }, + { + "epoch": 0.46580458168441, + "grad_norm": 0.5513335466384888, + "learning_rate": 5.6786278526366875e-05, + "loss": 1.5115, + "step": 8357 + }, + { + "epoch": 0.46586031993757315, + "grad_norm": 0.5334859490394592, + "learning_rate": 5.677745657810681e-05, + "loss": 1.5391, + "step": 8358 + }, + { + "epoch": 0.4659160581907363, + "grad_norm": 0.51854008436203, + "learning_rate": 5.6768634414905344e-05, + "loss": 1.4878, + "step": 8359 + }, + { + "epoch": 0.46597179644389947, + "grad_norm": 0.5759007930755615, + "learning_rate": 5.675981203704226e-05, + "loss": 1.7812, + "step": 8360 + }, + { + "epoch": 0.4660275346970626, + "grad_norm": 0.5255948305130005, + "learning_rate": 5.675098944479733e-05, + "loss": 1.6782, + "step": 8361 + }, + { + "epoch": 0.4660832729502257, + "grad_norm": 0.5190218091011047, + "learning_rate": 5.67421666384504e-05, + "loss": 1.4408, + "step": 8362 + }, + { + "epoch": 0.4661390112033889, + "grad_norm": 0.5538722276687622, + "learning_rate": 5.673334361828124e-05, + "loss": 1.6993, + "step": 8363 + }, + { + "epoch": 0.46619474945655204, + "grad_norm": 0.5251713991165161, + "learning_rate": 5.672452038456969e-05, + "loss": 1.5929, + "step": 8364 + }, + { + "epoch": 0.46625048770971517, + "grad_norm": 0.5203914642333984, + "learning_rate": 5.671569693759554e-05, + "loss": 1.5579, + "step": 8365 + }, + { + "epoch": 0.4663062259628783, + "grad_norm": 0.4919300675392151, + "learning_rate": 5.670687327763866e-05, + "loss": 1.5625, + "step": 8366 + }, + { + "epoch": 0.4663619642160415, + "grad_norm": 0.5500087141990662, + "learning_rate": 5.6698049404978845e-05, + "loss": 1.6695, + "step": 8367 + }, + { + "epoch": 0.4664177024692046, + "grad_norm": 0.5846395492553711, + "learning_rate": 5.6689225319895966e-05, + "loss": 1.884, + "step": 8368 + }, + { + "epoch": 0.46647344072236774, + "grad_norm": 0.5971377491950989, + "learning_rate": 5.668040102266987e-05, + "loss": 1.9091, + "step": 8369 + }, + { + "epoch": 0.4665291789755309, + "grad_norm": 0.5873506665229797, + "learning_rate": 5.6671576513580385e-05, + "loss": 1.7085, + "step": 8370 + }, + { + "epoch": 0.46658491722869405, + "grad_norm": 0.551792323589325, + "learning_rate": 5.66627517929074e-05, + "loss": 1.5626, + "step": 8371 + }, + { + "epoch": 0.4666406554818572, + "grad_norm": 0.5586331486701965, + "learning_rate": 5.665392686093076e-05, + "loss": 1.7621, + "step": 8372 + }, + { + "epoch": 0.46669639373502037, + "grad_norm": 0.6477528810501099, + "learning_rate": 5.664510171793038e-05, + "loss": 1.9983, + "step": 8373 + }, + { + "epoch": 0.4667521319881835, + "grad_norm": 0.5568731427192688, + "learning_rate": 5.6636276364186105e-05, + "loss": 1.5046, + "step": 8374 + }, + { + "epoch": 0.4668078702413466, + "grad_norm": 0.5492534637451172, + "learning_rate": 5.6627450799977844e-05, + "loss": 1.6931, + "step": 8375 + }, + { + "epoch": 0.4668636084945098, + "grad_norm": 0.5230808854103088, + "learning_rate": 5.661862502558547e-05, + "loss": 1.5232, + "step": 8376 + }, + { + "epoch": 0.46691934674767294, + "grad_norm": 0.5762078762054443, + "learning_rate": 5.660979904128891e-05, + "loss": 1.8327, + "step": 8377 + }, + { + "epoch": 0.46697508500083607, + "grad_norm": 0.5496635437011719, + "learning_rate": 5.660097284736805e-05, + "loss": 1.5354, + "step": 8378 + }, + { + "epoch": 0.4670308232539992, + "grad_norm": 0.5177884101867676, + "learning_rate": 5.6592146444102826e-05, + "loss": 1.4303, + "step": 8379 + }, + { + "epoch": 0.4670865615071624, + "grad_norm": 0.6022128462791443, + "learning_rate": 5.658331983177315e-05, + "loss": 1.9321, + "step": 8380 + }, + { + "epoch": 0.4671422997603255, + "grad_norm": 0.5913931131362915, + "learning_rate": 5.657449301065895e-05, + "loss": 1.9125, + "step": 8381 + }, + { + "epoch": 0.46719803801348864, + "grad_norm": 0.4976262152194977, + "learning_rate": 5.656566598104017e-05, + "loss": 1.6072, + "step": 8382 + }, + { + "epoch": 0.4672537762666518, + "grad_norm": 0.5472914576530457, + "learning_rate": 5.655683874319675e-05, + "loss": 1.719, + "step": 8383 + }, + { + "epoch": 0.46730951451981495, + "grad_norm": 0.5451732277870178, + "learning_rate": 5.6548011297408634e-05, + "loss": 1.6492, + "step": 8384 + }, + { + "epoch": 0.4673652527729781, + "grad_norm": 0.5876046419143677, + "learning_rate": 5.653918364395575e-05, + "loss": 1.7208, + "step": 8385 + }, + { + "epoch": 0.46742099102614126, + "grad_norm": 0.5409192442893982, + "learning_rate": 5.653035578311812e-05, + "loss": 1.6186, + "step": 8386 + }, + { + "epoch": 0.4674767292793044, + "grad_norm": 0.5066797733306885, + "learning_rate": 5.652152771517566e-05, + "loss": 1.2929, + "step": 8387 + }, + { + "epoch": 0.4675324675324675, + "grad_norm": 0.5531768202781677, + "learning_rate": 5.651269944040838e-05, + "loss": 1.7447, + "step": 8388 + }, + { + "epoch": 0.46758820578563065, + "grad_norm": 0.5745431780815125, + "learning_rate": 5.650387095909623e-05, + "loss": 1.7896, + "step": 8389 + }, + { + "epoch": 0.46764394403879384, + "grad_norm": 0.5450076460838318, + "learning_rate": 5.649504227151922e-05, + "loss": 1.5537, + "step": 8390 + }, + { + "epoch": 0.46769968229195696, + "grad_norm": 0.5614714622497559, + "learning_rate": 5.648621337795733e-05, + "loss": 1.5894, + "step": 8391 + }, + { + "epoch": 0.4677554205451201, + "grad_norm": 0.6122470498085022, + "learning_rate": 5.647738427869058e-05, + "loss": 1.8336, + "step": 8392 + }, + { + "epoch": 0.4678111587982833, + "grad_norm": 0.598466157913208, + "learning_rate": 5.6468554973998955e-05, + "loss": 1.799, + "step": 8393 + }, + { + "epoch": 0.4678668970514464, + "grad_norm": 0.5752211213111877, + "learning_rate": 5.645972546416248e-05, + "loss": 1.7678, + "step": 8394 + }, + { + "epoch": 0.46792263530460954, + "grad_norm": 0.5438199043273926, + "learning_rate": 5.6450895749461194e-05, + "loss": 1.6982, + "step": 8395 + }, + { + "epoch": 0.4679783735577727, + "grad_norm": 0.5414747595787048, + "learning_rate": 5.64420658301751e-05, + "loss": 1.5794, + "step": 8396 + }, + { + "epoch": 0.46803411181093585, + "grad_norm": 0.5446813702583313, + "learning_rate": 5.643323570658424e-05, + "loss": 1.4545, + "step": 8397 + }, + { + "epoch": 0.468089850064099, + "grad_norm": 0.5998760461807251, + "learning_rate": 5.642440537896863e-05, + "loss": 1.6886, + "step": 8398 + }, + { + "epoch": 0.46814558831726216, + "grad_norm": 0.5757097005844116, + "learning_rate": 5.6415574847608365e-05, + "loss": 1.6932, + "step": 8399 + }, + { + "epoch": 0.4682013265704253, + "grad_norm": 0.5681119561195374, + "learning_rate": 5.640674411278345e-05, + "loss": 1.6357, + "step": 8400 + }, + { + "epoch": 0.4682570648235884, + "grad_norm": 0.5782068371772766, + "learning_rate": 5.6397913174773986e-05, + "loss": 1.4748, + "step": 8401 + }, + { + "epoch": 0.46831280307675155, + "grad_norm": 0.5838581323623657, + "learning_rate": 5.638908203386001e-05, + "loss": 1.6619, + "step": 8402 + }, + { + "epoch": 0.46836854132991473, + "grad_norm": 0.5535818934440613, + "learning_rate": 5.638025069032159e-05, + "loss": 1.7486, + "step": 8403 + }, + { + "epoch": 0.46842427958307786, + "grad_norm": 0.5350418090820312, + "learning_rate": 5.637141914443883e-05, + "loss": 1.6243, + "step": 8404 + }, + { + "epoch": 0.468480017836241, + "grad_norm": 0.5376988053321838, + "learning_rate": 5.6362587396491805e-05, + "loss": 1.6984, + "step": 8405 + }, + { + "epoch": 0.4685357560894042, + "grad_norm": 0.593912661075592, + "learning_rate": 5.63537554467606e-05, + "loss": 1.6001, + "step": 8406 + }, + { + "epoch": 0.4685914943425673, + "grad_norm": 0.5185176730155945, + "learning_rate": 5.634492329552531e-05, + "loss": 1.4702, + "step": 8407 + }, + { + "epoch": 0.46864723259573043, + "grad_norm": 0.5814734101295471, + "learning_rate": 5.6336090943066063e-05, + "loss": 1.8799, + "step": 8408 + }, + { + "epoch": 0.4687029708488936, + "grad_norm": 0.5562795400619507, + "learning_rate": 5.632725838966294e-05, + "loss": 1.7107, + "step": 8409 + }, + { + "epoch": 0.46875870910205675, + "grad_norm": 0.5342075824737549, + "learning_rate": 5.631842563559608e-05, + "loss": 1.6502, + "step": 8410 + }, + { + "epoch": 0.4688144473552199, + "grad_norm": 0.5376294255256653, + "learning_rate": 5.630959268114558e-05, + "loss": 1.6374, + "step": 8411 + }, + { + "epoch": 0.46887018560838306, + "grad_norm": 0.5461024641990662, + "learning_rate": 5.630075952659162e-05, + "loss": 1.7209, + "step": 8412 + }, + { + "epoch": 0.4689259238615462, + "grad_norm": 0.5888074040412903, + "learning_rate": 5.629192617221427e-05, + "loss": 1.7923, + "step": 8413 + }, + { + "epoch": 0.4689816621147093, + "grad_norm": 0.5504298210144043, + "learning_rate": 5.6283092618293734e-05, + "loss": 1.6201, + "step": 8414 + }, + { + "epoch": 0.46903740036787245, + "grad_norm": 0.5408875942230225, + "learning_rate": 5.627425886511012e-05, + "loss": 1.5646, + "step": 8415 + }, + { + "epoch": 0.46909313862103563, + "grad_norm": 0.5847890377044678, + "learning_rate": 5.626542491294359e-05, + "loss": 1.7076, + "step": 8416 + }, + { + "epoch": 0.46914887687419876, + "grad_norm": 0.5354915261268616, + "learning_rate": 5.6256590762074315e-05, + "loss": 1.5801, + "step": 8417 + }, + { + "epoch": 0.4692046151273619, + "grad_norm": 0.5805383324623108, + "learning_rate": 5.624775641278247e-05, + "loss": 1.8075, + "step": 8418 + }, + { + "epoch": 0.4692603533805251, + "grad_norm": 0.5791111588478088, + "learning_rate": 5.6238921865348204e-05, + "loss": 1.8437, + "step": 8419 + }, + { + "epoch": 0.4693160916336882, + "grad_norm": 0.5863295793533325, + "learning_rate": 5.623008712005172e-05, + "loss": 1.7371, + "step": 8420 + }, + { + "epoch": 0.46937182988685133, + "grad_norm": 0.5539514422416687, + "learning_rate": 5.62212521771732e-05, + "loss": 1.646, + "step": 8421 + }, + { + "epoch": 0.4694275681400145, + "grad_norm": 0.5049216151237488, + "learning_rate": 5.6212417036992826e-05, + "loss": 1.447, + "step": 8422 + }, + { + "epoch": 0.46948330639317765, + "grad_norm": 0.5240146517753601, + "learning_rate": 5.620358169979082e-05, + "loss": 1.729, + "step": 8423 + }, + { + "epoch": 0.4695390446463408, + "grad_norm": 0.5284691452980042, + "learning_rate": 5.619474616584734e-05, + "loss": 1.5096, + "step": 8424 + }, + { + "epoch": 0.4695947828995039, + "grad_norm": 0.5499683618545532, + "learning_rate": 5.618591043544266e-05, + "loss": 1.5803, + "step": 8425 + }, + { + "epoch": 0.4696505211526671, + "grad_norm": 0.588737964630127, + "learning_rate": 5.617707450885695e-05, + "loss": 1.6776, + "step": 8426 + }, + { + "epoch": 0.4697062594058302, + "grad_norm": 0.5827232599258423, + "learning_rate": 5.6168238386370466e-05, + "loss": 1.6402, + "step": 8427 + }, + { + "epoch": 0.46976199765899335, + "grad_norm": 0.5729832649230957, + "learning_rate": 5.615940206826341e-05, + "loss": 1.7642, + "step": 8428 + }, + { + "epoch": 0.46981773591215653, + "grad_norm": 0.5644805431365967, + "learning_rate": 5.6150565554816035e-05, + "loss": 1.7081, + "step": 8429 + }, + { + "epoch": 0.46987347416531966, + "grad_norm": 0.5413994193077087, + "learning_rate": 5.6141728846308586e-05, + "loss": 1.7756, + "step": 8430 + }, + { + "epoch": 0.4699292124184828, + "grad_norm": 0.5305155515670776, + "learning_rate": 5.6132891943021304e-05, + "loss": 1.5193, + "step": 8431 + }, + { + "epoch": 0.469984950671646, + "grad_norm": 0.5325213074684143, + "learning_rate": 5.612405484523444e-05, + "loss": 1.5169, + "step": 8432 + }, + { + "epoch": 0.4700406889248091, + "grad_norm": 0.5783179998397827, + "learning_rate": 5.6115217553228274e-05, + "loss": 1.6159, + "step": 8433 + }, + { + "epoch": 0.47009642717797223, + "grad_norm": 0.5537718534469604, + "learning_rate": 5.610638006728306e-05, + "loss": 1.6027, + "step": 8434 + }, + { + "epoch": 0.4701521654311354, + "grad_norm": 0.6395325660705566, + "learning_rate": 5.609754238767907e-05, + "loss": 1.3854, + "step": 8435 + }, + { + "epoch": 0.47020790368429854, + "grad_norm": 0.5301234126091003, + "learning_rate": 5.608870451469659e-05, + "loss": 1.6888, + "step": 8436 + }, + { + "epoch": 0.4702636419374617, + "grad_norm": 0.5246771574020386, + "learning_rate": 5.607986644861588e-05, + "loss": 1.5963, + "step": 8437 + }, + { + "epoch": 0.4703193801906248, + "grad_norm": 0.5331987738609314, + "learning_rate": 5.607102818971729e-05, + "loss": 1.7791, + "step": 8438 + }, + { + "epoch": 0.470375118443788, + "grad_norm": 0.5587426424026489, + "learning_rate": 5.6062189738281056e-05, + "loss": 1.744, + "step": 8439 + }, + { + "epoch": 0.4704308566969511, + "grad_norm": 0.5236651301383972, + "learning_rate": 5.6053351094587526e-05, + "loss": 1.4963, + "step": 8440 + }, + { + "epoch": 0.47048659495011425, + "grad_norm": 0.5496351718902588, + "learning_rate": 5.604451225891698e-05, + "loss": 1.491, + "step": 8441 + }, + { + "epoch": 0.47054233320327743, + "grad_norm": 0.5666020512580872, + "learning_rate": 5.603567323154975e-05, + "loss": 1.6241, + "step": 8442 + }, + { + "epoch": 0.47059807145644056, + "grad_norm": 0.5503633618354797, + "learning_rate": 5.602683401276615e-05, + "loss": 1.6522, + "step": 8443 + }, + { + "epoch": 0.4706538097096037, + "grad_norm": 0.5833953022956848, + "learning_rate": 5.601799460284654e-05, + "loss": 1.7361, + "step": 8444 + }, + { + "epoch": 0.47070954796276687, + "grad_norm": 0.5664584636688232, + "learning_rate": 5.60091550020712e-05, + "loss": 1.6558, + "step": 8445 + }, + { + "epoch": 0.47076528621593, + "grad_norm": 0.5645166635513306, + "learning_rate": 5.60003152107205e-05, + "loss": 1.7492, + "step": 8446 + }, + { + "epoch": 0.47082102446909313, + "grad_norm": 0.5689491629600525, + "learning_rate": 5.599147522907481e-05, + "loss": 1.6956, + "step": 8447 + }, + { + "epoch": 0.47087676272225626, + "grad_norm": 0.6192054152488708, + "learning_rate": 5.598263505741443e-05, + "loss": 1.5153, + "step": 8448 + }, + { + "epoch": 0.47093250097541944, + "grad_norm": 0.5669271945953369, + "learning_rate": 5.597379469601978e-05, + "loss": 1.5719, + "step": 8449 + }, + { + "epoch": 0.4709882392285826, + "grad_norm": 0.5729002952575684, + "learning_rate": 5.5964954145171145e-05, + "loss": 1.7169, + "step": 8450 + }, + { + "epoch": 0.4710439774817457, + "grad_norm": 0.532015323638916, + "learning_rate": 5.595611340514898e-05, + "loss": 1.6197, + "step": 8451 + }, + { + "epoch": 0.4710997157349089, + "grad_norm": 0.5148784518241882, + "learning_rate": 5.594727247623361e-05, + "loss": 1.611, + "step": 8452 + }, + { + "epoch": 0.471155453988072, + "grad_norm": 0.5674019455909729, + "learning_rate": 5.593843135870545e-05, + "loss": 1.6694, + "step": 8453 + }, + { + "epoch": 0.47121119224123514, + "grad_norm": 0.5392388701438904, + "learning_rate": 5.592959005284485e-05, + "loss": 1.5342, + "step": 8454 + }, + { + "epoch": 0.47126693049439833, + "grad_norm": 0.5939937829971313, + "learning_rate": 5.592074855893223e-05, + "loss": 1.7698, + "step": 8455 + }, + { + "epoch": 0.47132266874756146, + "grad_norm": 0.603952169418335, + "learning_rate": 5.591190687724799e-05, + "loss": 1.885, + "step": 8456 + }, + { + "epoch": 0.4713784070007246, + "grad_norm": 0.5169516801834106, + "learning_rate": 5.590306500807253e-05, + "loss": 1.4436, + "step": 8457 + }, + { + "epoch": 0.47143414525388777, + "grad_norm": 0.5573791265487671, + "learning_rate": 5.589422295168626e-05, + "loss": 1.6708, + "step": 8458 + }, + { + "epoch": 0.4714898835070509, + "grad_norm": 0.5594834685325623, + "learning_rate": 5.5885380708369606e-05, + "loss": 1.6496, + "step": 8459 + }, + { + "epoch": 0.47154562176021403, + "grad_norm": 0.5771753787994385, + "learning_rate": 5.5876538278403e-05, + "loss": 1.7612, + "step": 8460 + }, + { + "epoch": 0.47160136001337716, + "grad_norm": 0.5862414240837097, + "learning_rate": 5.586769566206686e-05, + "loss": 1.9365, + "step": 8461 + }, + { + "epoch": 0.47165709826654034, + "grad_norm": 0.5807836055755615, + "learning_rate": 5.585885285964163e-05, + "loss": 1.623, + "step": 8462 + }, + { + "epoch": 0.47171283651970347, + "grad_norm": 0.5933867692947388, + "learning_rate": 5.5850009871407716e-05, + "loss": 1.8284, + "step": 8463 + }, + { + "epoch": 0.4717685747728666, + "grad_norm": 0.5377753973007202, + "learning_rate": 5.584116669764563e-05, + "loss": 1.462, + "step": 8464 + }, + { + "epoch": 0.4718243130260298, + "grad_norm": 0.5384745597839355, + "learning_rate": 5.583232333863577e-05, + "loss": 1.5878, + "step": 8465 + }, + { + "epoch": 0.4718800512791929, + "grad_norm": 0.5296236872673035, + "learning_rate": 5.582347979465864e-05, + "loss": 1.6045, + "step": 8466 + }, + { + "epoch": 0.47193578953235604, + "grad_norm": 0.6247029304504395, + "learning_rate": 5.581463606599467e-05, + "loss": 1.6802, + "step": 8467 + }, + { + "epoch": 0.4719915277855192, + "grad_norm": 0.5652837157249451, + "learning_rate": 5.580579215292435e-05, + "loss": 1.6555, + "step": 8468 + }, + { + "epoch": 0.47204726603868236, + "grad_norm": 0.5700575709342957, + "learning_rate": 5.5796948055728147e-05, + "loss": 1.8245, + "step": 8469 + }, + { + "epoch": 0.4721030042918455, + "grad_norm": 0.5366250276565552, + "learning_rate": 5.578810377468656e-05, + "loss": 1.8156, + "step": 8470 + }, + { + "epoch": 0.4721587425450086, + "grad_norm": 0.5650043487548828, + "learning_rate": 5.577925931008007e-05, + "loss": 1.6757, + "step": 8471 + }, + { + "epoch": 0.4722144807981718, + "grad_norm": 0.5967742204666138, + "learning_rate": 5.577041466218915e-05, + "loss": 1.939, + "step": 8472 + }, + { + "epoch": 0.4722702190513349, + "grad_norm": 0.5320480465888977, + "learning_rate": 5.576156983129435e-05, + "loss": 1.5016, + "step": 8473 + }, + { + "epoch": 0.47232595730449806, + "grad_norm": 0.5365233421325684, + "learning_rate": 5.5752724817676125e-05, + "loss": 1.5794, + "step": 8474 + }, + { + "epoch": 0.47238169555766124, + "grad_norm": 0.5704277753829956, + "learning_rate": 5.5743879621615026e-05, + "loss": 1.5467, + "step": 8475 + }, + { + "epoch": 0.47243743381082437, + "grad_norm": 0.5679128170013428, + "learning_rate": 5.5735034243391537e-05, + "loss": 1.6893, + "step": 8476 + }, + { + "epoch": 0.4724931720639875, + "grad_norm": 0.5593464970588684, + "learning_rate": 5.572618868328621e-05, + "loss": 1.6293, + "step": 8477 + }, + { + "epoch": 0.4725489103171507, + "grad_norm": 0.527761697769165, + "learning_rate": 5.5717342941579555e-05, + "loss": 1.6616, + "step": 8478 + }, + { + "epoch": 0.4726046485703138, + "grad_norm": 0.5714175701141357, + "learning_rate": 5.570849701855213e-05, + "loss": 1.7797, + "step": 8479 + }, + { + "epoch": 0.47266038682347694, + "grad_norm": 0.5801485180854797, + "learning_rate": 5.569965091448446e-05, + "loss": 1.6934, + "step": 8480 + }, + { + "epoch": 0.4727161250766401, + "grad_norm": 0.6128066778182983, + "learning_rate": 5.5690804629657076e-05, + "loss": 1.8593, + "step": 8481 + }, + { + "epoch": 0.47277186332980325, + "grad_norm": 0.6358544230461121, + "learning_rate": 5.568195816435057e-05, + "loss": 1.8292, + "step": 8482 + }, + { + "epoch": 0.4728276015829664, + "grad_norm": 0.5209305882453918, + "learning_rate": 5.567311151884547e-05, + "loss": 1.6183, + "step": 8483 + }, + { + "epoch": 0.4728833398361295, + "grad_norm": 0.5640316605567932, + "learning_rate": 5.566426469342235e-05, + "loss": 1.7618, + "step": 8484 + }, + { + "epoch": 0.4729390780892927, + "grad_norm": 0.5284755825996399, + "learning_rate": 5.565541768836178e-05, + "loss": 1.6473, + "step": 8485 + }, + { + "epoch": 0.4729948163424558, + "grad_norm": 0.5737931728363037, + "learning_rate": 5.564657050394434e-05, + "loss": 1.9419, + "step": 8486 + }, + { + "epoch": 0.47305055459561896, + "grad_norm": 0.5647780299186707, + "learning_rate": 5.563772314045059e-05, + "loss": 1.6413, + "step": 8487 + }, + { + "epoch": 0.47310629284878214, + "grad_norm": 0.5379336476325989, + "learning_rate": 5.562887559816116e-05, + "loss": 1.5344, + "step": 8488 + }, + { + "epoch": 0.47316203110194527, + "grad_norm": 0.5728521943092346, + "learning_rate": 5.562002787735657e-05, + "loss": 1.6937, + "step": 8489 + }, + { + "epoch": 0.4732177693551084, + "grad_norm": 0.5722839832305908, + "learning_rate": 5.561117997831751e-05, + "loss": 1.6869, + "step": 8490 + }, + { + "epoch": 0.4732735076082716, + "grad_norm": 0.5436987280845642, + "learning_rate": 5.56023319013245e-05, + "loss": 1.3939, + "step": 8491 + }, + { + "epoch": 0.4733292458614347, + "grad_norm": 0.5408251285552979, + "learning_rate": 5.559348364665822e-05, + "loss": 1.5309, + "step": 8492 + }, + { + "epoch": 0.47338498411459784, + "grad_norm": 0.5417353510856628, + "learning_rate": 5.5584635214599225e-05, + "loss": 1.5592, + "step": 8493 + }, + { + "epoch": 0.47344072236776097, + "grad_norm": 0.5821628570556641, + "learning_rate": 5.557578660542816e-05, + "loss": 1.5603, + "step": 8494 + }, + { + "epoch": 0.47349646062092415, + "grad_norm": 0.5318421721458435, + "learning_rate": 5.5566937819425656e-05, + "loss": 1.5251, + "step": 8495 + }, + { + "epoch": 0.4735521988740873, + "grad_norm": 0.5154527425765991, + "learning_rate": 5.5558088856872346e-05, + "loss": 1.572, + "step": 8496 + }, + { + "epoch": 0.4736079371272504, + "grad_norm": 0.5686662197113037, + "learning_rate": 5.554923971804887e-05, + "loss": 1.5153, + "step": 8497 + }, + { + "epoch": 0.4736636753804136, + "grad_norm": 0.5712747573852539, + "learning_rate": 5.554039040323586e-05, + "loss": 1.7534, + "step": 8498 + }, + { + "epoch": 0.4737194136335767, + "grad_norm": 0.5434257388114929, + "learning_rate": 5.5531540912713974e-05, + "loss": 1.6791, + "step": 8499 + }, + { + "epoch": 0.47377515188673985, + "grad_norm": 0.5522347092628479, + "learning_rate": 5.552269124676386e-05, + "loss": 1.7779, + "step": 8500 + }, + { + "epoch": 0.47383089013990304, + "grad_norm": 0.5155788064002991, + "learning_rate": 5.551384140566618e-05, + "loss": 1.4377, + "step": 8501 + }, + { + "epoch": 0.47388662839306617, + "grad_norm": 0.5739377737045288, + "learning_rate": 5.550499138970158e-05, + "loss": 1.8262, + "step": 8502 + }, + { + "epoch": 0.4739423666462293, + "grad_norm": 0.5527716875076294, + "learning_rate": 5.5496141199150766e-05, + "loss": 1.3705, + "step": 8503 + }, + { + "epoch": 0.4739981048993925, + "grad_norm": 0.5810341238975525, + "learning_rate": 5.548729083429439e-05, + "loss": 1.7927, + "step": 8504 + }, + { + "epoch": 0.4740538431525556, + "grad_norm": 0.5541203618049622, + "learning_rate": 5.547844029541316e-05, + "loss": 1.7237, + "step": 8505 + }, + { + "epoch": 0.47410958140571874, + "grad_norm": 0.5816789865493774, + "learning_rate": 5.546958958278773e-05, + "loss": 1.6761, + "step": 8506 + }, + { + "epoch": 0.47416531965888187, + "grad_norm": 0.5344805121421814, + "learning_rate": 5.546073869669881e-05, + "loss": 1.7347, + "step": 8507 + }, + { + "epoch": 0.47422105791204505, + "grad_norm": 0.5249469876289368, + "learning_rate": 5.5451887637427104e-05, + "loss": 1.5048, + "step": 8508 + }, + { + "epoch": 0.4742767961652082, + "grad_norm": 0.5707089900970459, + "learning_rate": 5.544303640525328e-05, + "loss": 1.811, + "step": 8509 + }, + { + "epoch": 0.4743325344183713, + "grad_norm": 0.5320430397987366, + "learning_rate": 5.5434185000458114e-05, + "loss": 1.7104, + "step": 8510 + }, + { + "epoch": 0.4743882726715345, + "grad_norm": 0.5608380436897278, + "learning_rate": 5.5425333423322255e-05, + "loss": 1.7893, + "step": 8511 + }, + { + "epoch": 0.4744440109246976, + "grad_norm": 0.5271068811416626, + "learning_rate": 5.5416481674126474e-05, + "loss": 1.7735, + "step": 8512 + }, + { + "epoch": 0.47449974917786075, + "grad_norm": 0.5395051836967468, + "learning_rate": 5.540762975315147e-05, + "loss": 1.7249, + "step": 8513 + }, + { + "epoch": 0.47455548743102394, + "grad_norm": 0.5892390012741089, + "learning_rate": 5.539877766067798e-05, + "loss": 1.7148, + "step": 8514 + }, + { + "epoch": 0.47461122568418707, + "grad_norm": 0.5333415269851685, + "learning_rate": 5.538992539698672e-05, + "loss": 1.6184, + "step": 8515 + }, + { + "epoch": 0.4746669639373502, + "grad_norm": 0.6480614542961121, + "learning_rate": 5.538107296235847e-05, + "loss": 1.6898, + "step": 8516 + }, + { + "epoch": 0.4747227021905133, + "grad_norm": 0.5696564316749573, + "learning_rate": 5.5372220357073955e-05, + "loss": 1.7039, + "step": 8517 + }, + { + "epoch": 0.4747784404436765, + "grad_norm": 0.5047008991241455, + "learning_rate": 5.536336758141394e-05, + "loss": 1.5221, + "step": 8518 + }, + { + "epoch": 0.47483417869683964, + "grad_norm": 0.6112247705459595, + "learning_rate": 5.535451463565916e-05, + "loss": 1.7282, + "step": 8519 + }, + { + "epoch": 0.47488991695000277, + "grad_norm": 0.5554122924804688, + "learning_rate": 5.5345661520090394e-05, + "loss": 1.6662, + "step": 8520 + }, + { + "epoch": 0.47494565520316595, + "grad_norm": 0.5461030602455139, + "learning_rate": 5.533680823498844e-05, + "loss": 1.6679, + "step": 8521 + }, + { + "epoch": 0.4750013934563291, + "grad_norm": 0.5860038995742798, + "learning_rate": 5.5327954780634004e-05, + "loss": 1.769, + "step": 8522 + }, + { + "epoch": 0.4750571317094922, + "grad_norm": 0.6236945390701294, + "learning_rate": 5.531910115730794e-05, + "loss": 1.9089, + "step": 8523 + }, + { + "epoch": 0.4751128699626554, + "grad_norm": 0.545220673084259, + "learning_rate": 5.531024736529099e-05, + "loss": 1.7743, + "step": 8524 + }, + { + "epoch": 0.4751686082158185, + "grad_norm": 0.6534609198570251, + "learning_rate": 5.5301393404863954e-05, + "loss": 1.9673, + "step": 8525 + }, + { + "epoch": 0.47522434646898165, + "grad_norm": 0.5649281740188599, + "learning_rate": 5.529253927630762e-05, + "loss": 1.6666, + "step": 8526 + }, + { + "epoch": 0.47528008472214484, + "grad_norm": 0.5315033197402954, + "learning_rate": 5.5283684979902815e-05, + "loss": 1.678, + "step": 8527 + }, + { + "epoch": 0.47533582297530796, + "grad_norm": 0.5951296091079712, + "learning_rate": 5.5274830515930306e-05, + "loss": 1.6429, + "step": 8528 + }, + { + "epoch": 0.4753915612284711, + "grad_norm": 0.5288706421852112, + "learning_rate": 5.526597588467095e-05, + "loss": 1.65, + "step": 8529 + }, + { + "epoch": 0.4754472994816342, + "grad_norm": 0.5894261002540588, + "learning_rate": 5.525712108640553e-05, + "loss": 1.6486, + "step": 8530 + }, + { + "epoch": 0.4755030377347974, + "grad_norm": 0.5475479960441589, + "learning_rate": 5.524826612141488e-05, + "loss": 1.5981, + "step": 8531 + }, + { + "epoch": 0.47555877598796054, + "grad_norm": 0.5496692657470703, + "learning_rate": 5.523941098997983e-05, + "loss": 1.6958, + "step": 8532 + }, + { + "epoch": 0.47561451424112366, + "grad_norm": 0.6038063168525696, + "learning_rate": 5.5230555692381214e-05, + "loss": 1.7152, + "step": 8533 + }, + { + "epoch": 0.47567025249428685, + "grad_norm": 0.5410369038581848, + "learning_rate": 5.5221700228899866e-05, + "loss": 1.5163, + "step": 8534 + }, + { + "epoch": 0.47572599074745, + "grad_norm": 0.5673332214355469, + "learning_rate": 5.521284459981662e-05, + "loss": 1.6854, + "step": 8535 + }, + { + "epoch": 0.4757817290006131, + "grad_norm": 0.5714686512947083, + "learning_rate": 5.520398880541235e-05, + "loss": 1.6205, + "step": 8536 + }, + { + "epoch": 0.4758374672537763, + "grad_norm": 0.6370970606803894, + "learning_rate": 5.519513284596789e-05, + "loss": 1.8303, + "step": 8537 + }, + { + "epoch": 0.4758932055069394, + "grad_norm": 0.5482840538024902, + "learning_rate": 5.518627672176412e-05, + "loss": 1.5506, + "step": 8538 + }, + { + "epoch": 0.47594894376010255, + "grad_norm": 0.5282999277114868, + "learning_rate": 5.5177420433081874e-05, + "loss": 1.2786, + "step": 8539 + }, + { + "epoch": 0.4760046820132657, + "grad_norm": 0.5575840473175049, + "learning_rate": 5.516856398020205e-05, + "loss": 1.5573, + "step": 8540 + }, + { + "epoch": 0.47606042026642886, + "grad_norm": 0.5926665663719177, + "learning_rate": 5.5159707363405485e-05, + "loss": 1.7721, + "step": 8541 + }, + { + "epoch": 0.476116158519592, + "grad_norm": 0.5172202587127686, + "learning_rate": 5.515085058297313e-05, + "loss": 1.4076, + "step": 8542 + }, + { + "epoch": 0.4761718967727551, + "grad_norm": 0.581986665725708, + "learning_rate": 5.514199363918578e-05, + "loss": 1.7104, + "step": 8543 + }, + { + "epoch": 0.4762276350259183, + "grad_norm": 0.5978564023971558, + "learning_rate": 5.51331365323244e-05, + "loss": 1.8326, + "step": 8544 + }, + { + "epoch": 0.47628337327908143, + "grad_norm": 0.5649850368499756, + "learning_rate": 5.5124279262669856e-05, + "loss": 1.6206, + "step": 8545 + }, + { + "epoch": 0.47633911153224456, + "grad_norm": 0.6205348372459412, + "learning_rate": 5.511542183050305e-05, + "loss": 1.7466, + "step": 8546 + }, + { + "epoch": 0.47639484978540775, + "grad_norm": 0.5095716714859009, + "learning_rate": 5.5106564236104884e-05, + "loss": 1.5614, + "step": 8547 + }, + { + "epoch": 0.4764505880385709, + "grad_norm": 0.5600999593734741, + "learning_rate": 5.509770647975626e-05, + "loss": 1.825, + "step": 8548 + }, + { + "epoch": 0.476506326291734, + "grad_norm": 0.5659551620483398, + "learning_rate": 5.508884856173813e-05, + "loss": 1.8289, + "step": 8549 + }, + { + "epoch": 0.4765620645448972, + "grad_norm": 0.524356484413147, + "learning_rate": 5.507999048233138e-05, + "loss": 1.591, + "step": 8550 + }, + { + "epoch": 0.4766178027980603, + "grad_norm": 0.5709447860717773, + "learning_rate": 5.507113224181696e-05, + "loss": 1.6152, + "step": 8551 + }, + { + "epoch": 0.47667354105122345, + "grad_norm": 0.5852453112602234, + "learning_rate": 5.506227384047579e-05, + "loss": 1.7522, + "step": 8552 + }, + { + "epoch": 0.4767292793043866, + "grad_norm": 0.6322617530822754, + "learning_rate": 5.50534152785888e-05, + "loss": 1.8002, + "step": 8553 + }, + { + "epoch": 0.47678501755754976, + "grad_norm": 0.6037564277648926, + "learning_rate": 5.504455655643694e-05, + "loss": 1.7472, + "step": 8554 + }, + { + "epoch": 0.4768407558107129, + "grad_norm": 0.6172270774841309, + "learning_rate": 5.503569767430118e-05, + "loss": 1.7638, + "step": 8555 + }, + { + "epoch": 0.476896494063876, + "grad_norm": 0.5917114615440369, + "learning_rate": 5.502683863246243e-05, + "loss": 1.7726, + "step": 8556 + }, + { + "epoch": 0.4769522323170392, + "grad_norm": 0.5618294477462769, + "learning_rate": 5.5017979431201675e-05, + "loss": 1.5519, + "step": 8557 + }, + { + "epoch": 0.47700797057020233, + "grad_norm": 0.5710815191268921, + "learning_rate": 5.500912007079987e-05, + "loss": 1.6896, + "step": 8558 + }, + { + "epoch": 0.47706370882336546, + "grad_norm": 0.5609897971153259, + "learning_rate": 5.5000260551537975e-05, + "loss": 1.7455, + "step": 8559 + }, + { + "epoch": 0.47711944707652865, + "grad_norm": 0.5565608739852905, + "learning_rate": 5.499140087369697e-05, + "loss": 1.5399, + "step": 8560 + }, + { + "epoch": 0.4771751853296918, + "grad_norm": 0.5751162767410278, + "learning_rate": 5.4982541037557823e-05, + "loss": 1.5373, + "step": 8561 + }, + { + "epoch": 0.4772309235828549, + "grad_norm": 0.5089201927185059, + "learning_rate": 5.4973681043401534e-05, + "loss": 1.2027, + "step": 8562 + }, + { + "epoch": 0.47728666183601803, + "grad_norm": 0.5925856232643127, + "learning_rate": 5.496482089150908e-05, + "loss": 1.9377, + "step": 8563 + }, + { + "epoch": 0.4773424000891812, + "grad_norm": 0.5660269260406494, + "learning_rate": 5.495596058216147e-05, + "loss": 1.4814, + "step": 8564 + }, + { + "epoch": 0.47739813834234435, + "grad_norm": 0.5554754734039307, + "learning_rate": 5.494710011563966e-05, + "loss": 1.6303, + "step": 8565 + }, + { + "epoch": 0.4774538765955075, + "grad_norm": 0.6004930138587952, + "learning_rate": 5.49382394922247e-05, + "loss": 1.6204, + "step": 8566 + }, + { + "epoch": 0.47750961484867066, + "grad_norm": 0.5308135747909546, + "learning_rate": 5.4929378712197556e-05, + "loss": 1.5949, + "step": 8567 + }, + { + "epoch": 0.4775653531018338, + "grad_norm": 0.5763102769851685, + "learning_rate": 5.4920517775839276e-05, + "loss": 1.7625, + "step": 8568 + }, + { + "epoch": 0.4776210913549969, + "grad_norm": 0.572308361530304, + "learning_rate": 5.491165668343085e-05, + "loss": 1.7809, + "step": 8569 + }, + { + "epoch": 0.4776768296081601, + "grad_norm": 0.6404359340667725, + "learning_rate": 5.4902795435253306e-05, + "loss": 2.0053, + "step": 8570 + }, + { + "epoch": 0.47773256786132323, + "grad_norm": 0.5613745450973511, + "learning_rate": 5.489393403158769e-05, + "loss": 1.8136, + "step": 8571 + }, + { + "epoch": 0.47778830611448636, + "grad_norm": 0.5631322860717773, + "learning_rate": 5.488507247271502e-05, + "loss": 1.9469, + "step": 8572 + }, + { + "epoch": 0.47784404436764955, + "grad_norm": 0.5425231456756592, + "learning_rate": 5.487621075891632e-05, + "loss": 1.7089, + "step": 8573 + }, + { + "epoch": 0.4778997826208127, + "grad_norm": 0.6085340976715088, + "learning_rate": 5.4867348890472646e-05, + "loss": 1.8108, + "step": 8574 + }, + { + "epoch": 0.4779555208739758, + "grad_norm": 0.5472151637077332, + "learning_rate": 5.485848686766506e-05, + "loss": 1.5179, + "step": 8575 + }, + { + "epoch": 0.47801125912713893, + "grad_norm": 0.5451512336730957, + "learning_rate": 5.484962469077458e-05, + "loss": 1.6112, + "step": 8576 + }, + { + "epoch": 0.4780669973803021, + "grad_norm": 0.5663710236549377, + "learning_rate": 5.4840762360082286e-05, + "loss": 1.6932, + "step": 8577 + }, + { + "epoch": 0.47812273563346525, + "grad_norm": 0.5614507794380188, + "learning_rate": 5.483189987586924e-05, + "loss": 1.7001, + "step": 8578 + }, + { + "epoch": 0.4781784738866284, + "grad_norm": 0.5428431034088135, + "learning_rate": 5.4823037238416506e-05, + "loss": 1.7767, + "step": 8579 + }, + { + "epoch": 0.47823421213979156, + "grad_norm": 0.5602681636810303, + "learning_rate": 5.481417444800512e-05, + "loss": 1.6749, + "step": 8580 + }, + { + "epoch": 0.4782899503929547, + "grad_norm": 0.5648148655891418, + "learning_rate": 5.480531150491622e-05, + "loss": 1.723, + "step": 8581 + }, + { + "epoch": 0.4783456886461178, + "grad_norm": 0.5764549970626831, + "learning_rate": 5.4796448409430845e-05, + "loss": 1.8049, + "step": 8582 + }, + { + "epoch": 0.478401426899281, + "grad_norm": 0.5871893167495728, + "learning_rate": 5.478758516183009e-05, + "loss": 1.979, + "step": 8583 + }, + { + "epoch": 0.47845716515244413, + "grad_norm": 0.5481773018836975, + "learning_rate": 5.477872176239506e-05, + "loss": 1.738, + "step": 8584 + }, + { + "epoch": 0.47851290340560726, + "grad_norm": 0.5214368104934692, + "learning_rate": 5.4769858211406824e-05, + "loss": 1.5133, + "step": 8585 + }, + { + "epoch": 0.4785686416587704, + "grad_norm": 0.5468040704727173, + "learning_rate": 5.4760994509146514e-05, + "loss": 1.6054, + "step": 8586 + }, + { + "epoch": 0.4786243799119336, + "grad_norm": 0.5729833841323853, + "learning_rate": 5.475213065589518e-05, + "loss": 1.4712, + "step": 8587 + }, + { + "epoch": 0.4786801181650967, + "grad_norm": 0.558814525604248, + "learning_rate": 5.4743266651934e-05, + "loss": 1.4907, + "step": 8588 + }, + { + "epoch": 0.47873585641825983, + "grad_norm": 0.5633212924003601, + "learning_rate": 5.4734402497544044e-05, + "loss": 1.4832, + "step": 8589 + }, + { + "epoch": 0.478791594671423, + "grad_norm": 0.6136720180511475, + "learning_rate": 5.472553819300645e-05, + "loss": 1.6588, + "step": 8590 + }, + { + "epoch": 0.47884733292458614, + "grad_norm": 0.537601113319397, + "learning_rate": 5.471667373860234e-05, + "loss": 1.6905, + "step": 8591 + }, + { + "epoch": 0.4789030711777493, + "grad_norm": 0.5937305688858032, + "learning_rate": 5.4707809134612844e-05, + "loss": 1.7177, + "step": 8592 + }, + { + "epoch": 0.47895880943091246, + "grad_norm": 0.6321950554847717, + "learning_rate": 5.469894438131906e-05, + "loss": 1.8388, + "step": 8593 + }, + { + "epoch": 0.4790145476840756, + "grad_norm": 0.5728781223297119, + "learning_rate": 5.469007947900219e-05, + "loss": 1.9354, + "step": 8594 + }, + { + "epoch": 0.4790702859372387, + "grad_norm": 0.5851932764053345, + "learning_rate": 5.468121442794333e-05, + "loss": 1.6465, + "step": 8595 + }, + { + "epoch": 0.4791260241904019, + "grad_norm": 0.5869148969650269, + "learning_rate": 5.467234922842363e-05, + "loss": 1.8636, + "step": 8596 + }, + { + "epoch": 0.47918176244356503, + "grad_norm": 0.5678532719612122, + "learning_rate": 5.4663483880724275e-05, + "loss": 1.7346, + "step": 8597 + }, + { + "epoch": 0.47923750069672816, + "grad_norm": 0.5783692598342896, + "learning_rate": 5.46546183851264e-05, + "loss": 1.8068, + "step": 8598 + }, + { + "epoch": 0.4792932389498913, + "grad_norm": 0.5361393690109253, + "learning_rate": 5.464575274191116e-05, + "loss": 1.4534, + "step": 8599 + }, + { + "epoch": 0.47934897720305447, + "grad_norm": 0.5204313397407532, + "learning_rate": 5.4636886951359726e-05, + "loss": 1.5212, + "step": 8600 + }, + { + "epoch": 0.4794047154562176, + "grad_norm": 0.5215826630592346, + "learning_rate": 5.4628021013753284e-05, + "loss": 1.6756, + "step": 8601 + }, + { + "epoch": 0.47946045370938073, + "grad_norm": 0.5335747599601746, + "learning_rate": 5.461915492937299e-05, + "loss": 1.7895, + "step": 8602 + }, + { + "epoch": 0.4795161919625439, + "grad_norm": 0.5702705979347229, + "learning_rate": 5.461028869850004e-05, + "loss": 1.7024, + "step": 8603 + }, + { + "epoch": 0.47957193021570704, + "grad_norm": 0.5771311521530151, + "learning_rate": 5.4601422321415606e-05, + "loss": 1.7879, + "step": 8604 + }, + { + "epoch": 0.47962766846887017, + "grad_norm": 0.5826980471611023, + "learning_rate": 5.459255579840089e-05, + "loss": 1.6198, + "step": 8605 + }, + { + "epoch": 0.47968340672203336, + "grad_norm": 0.5219647288322449, + "learning_rate": 5.458368912973707e-05, + "loss": 1.6159, + "step": 8606 + }, + { + "epoch": 0.4797391449751965, + "grad_norm": 0.5676286220550537, + "learning_rate": 5.4574822315705366e-05, + "loss": 1.6843, + "step": 8607 + }, + { + "epoch": 0.4797948832283596, + "grad_norm": 0.5792801380157471, + "learning_rate": 5.456595535658696e-05, + "loss": 1.8092, + "step": 8608 + }, + { + "epoch": 0.47985062148152274, + "grad_norm": 0.5464149713516235, + "learning_rate": 5.455708825266308e-05, + "loss": 1.7726, + "step": 8609 + }, + { + "epoch": 0.47990635973468593, + "grad_norm": 0.597957968711853, + "learning_rate": 5.4548221004214936e-05, + "loss": 1.7107, + "step": 8610 + }, + { + "epoch": 0.47996209798784906, + "grad_norm": 0.5609841346740723, + "learning_rate": 5.453935361152374e-05, + "loss": 1.5578, + "step": 8611 + }, + { + "epoch": 0.4800178362410122, + "grad_norm": 0.5753505229949951, + "learning_rate": 5.45304860748707e-05, + "loss": 1.8959, + "step": 8612 + }, + { + "epoch": 0.48007357449417537, + "grad_norm": 0.5798444747924805, + "learning_rate": 5.4521618394537056e-05, + "loss": 1.9346, + "step": 8613 + }, + { + "epoch": 0.4801293127473385, + "grad_norm": 0.536660373210907, + "learning_rate": 5.451275057080405e-05, + "loss": 1.6191, + "step": 8614 + }, + { + "epoch": 0.48018505100050163, + "grad_norm": 0.5759127736091614, + "learning_rate": 5.4503882603952905e-05, + "loss": 1.6555, + "step": 8615 + }, + { + "epoch": 0.4802407892536648, + "grad_norm": 0.5895690321922302, + "learning_rate": 5.449501449426487e-05, + "loss": 1.7481, + "step": 8616 + }, + { + "epoch": 0.48029652750682794, + "grad_norm": 0.5727548003196716, + "learning_rate": 5.448614624202117e-05, + "loss": 1.7338, + "step": 8617 + }, + { + "epoch": 0.48035226575999107, + "grad_norm": 0.5720645189285278, + "learning_rate": 5.447727784750308e-05, + "loss": 1.7127, + "step": 8618 + }, + { + "epoch": 0.48040800401315426, + "grad_norm": 0.5797655582427979, + "learning_rate": 5.446840931099182e-05, + "loss": 1.733, + "step": 8619 + }, + { + "epoch": 0.4804637422663174, + "grad_norm": 0.5146819949150085, + "learning_rate": 5.445954063276869e-05, + "loss": 1.5931, + "step": 8620 + }, + { + "epoch": 0.4805194805194805, + "grad_norm": 0.5465497970581055, + "learning_rate": 5.445067181311492e-05, + "loss": 1.6994, + "step": 8621 + }, + { + "epoch": 0.48057521877264364, + "grad_norm": 0.5129651427268982, + "learning_rate": 5.4441802852311795e-05, + "loss": 1.5357, + "step": 8622 + }, + { + "epoch": 0.4806309570258068, + "grad_norm": 0.5457690954208374, + "learning_rate": 5.443293375064058e-05, + "loss": 1.5543, + "step": 8623 + }, + { + "epoch": 0.48068669527896996, + "grad_norm": 0.5993552207946777, + "learning_rate": 5.4424064508382556e-05, + "loss": 1.902, + "step": 8624 + }, + { + "epoch": 0.4807424335321331, + "grad_norm": 0.5725103616714478, + "learning_rate": 5.4415195125819e-05, + "loss": 1.7444, + "step": 8625 + }, + { + "epoch": 0.48079817178529627, + "grad_norm": 0.5666811466217041, + "learning_rate": 5.440632560323118e-05, + "loss": 1.6553, + "step": 8626 + }, + { + "epoch": 0.4808539100384594, + "grad_norm": 0.5566148161888123, + "learning_rate": 5.439745594090042e-05, + "loss": 1.3808, + "step": 8627 + }, + { + "epoch": 0.4809096482916225, + "grad_norm": 0.5133042335510254, + "learning_rate": 5.438858613910799e-05, + "loss": 1.5705, + "step": 8628 + }, + { + "epoch": 0.4809653865447857, + "grad_norm": 0.6130719780921936, + "learning_rate": 5.43797161981352e-05, + "loss": 1.9702, + "step": 8629 + }, + { + "epoch": 0.48102112479794884, + "grad_norm": 0.5869434475898743, + "learning_rate": 5.4370846118263354e-05, + "loss": 1.8149, + "step": 8630 + }, + { + "epoch": 0.48107686305111197, + "grad_norm": 0.5676392316818237, + "learning_rate": 5.436197589977374e-05, + "loss": 1.5798, + "step": 8631 + }, + { + "epoch": 0.4811326013042751, + "grad_norm": 0.5470464825630188, + "learning_rate": 5.435310554294769e-05, + "loss": 1.6549, + "step": 8632 + }, + { + "epoch": 0.4811883395574383, + "grad_norm": 0.5741833448410034, + "learning_rate": 5.434423504806651e-05, + "loss": 1.7124, + "step": 8633 + }, + { + "epoch": 0.4812440778106014, + "grad_norm": 0.5436912178993225, + "learning_rate": 5.433536441541152e-05, + "loss": 1.568, + "step": 8634 + }, + { + "epoch": 0.48129981606376454, + "grad_norm": 0.5380058884620667, + "learning_rate": 5.432649364526403e-05, + "loss": 1.4785, + "step": 8635 + }, + { + "epoch": 0.4813555543169277, + "grad_norm": 0.5699672102928162, + "learning_rate": 5.4317622737905413e-05, + "loss": 1.4929, + "step": 8636 + }, + { + "epoch": 0.48141129257009085, + "grad_norm": 0.565059244632721, + "learning_rate": 5.4308751693616975e-05, + "loss": 1.7861, + "step": 8637 + }, + { + "epoch": 0.481467030823254, + "grad_norm": 0.5427149534225464, + "learning_rate": 5.429988051268006e-05, + "loss": 1.6655, + "step": 8638 + }, + { + "epoch": 0.48152276907641717, + "grad_norm": 0.5943994522094727, + "learning_rate": 5.429100919537597e-05, + "loss": 1.8461, + "step": 8639 + }, + { + "epoch": 0.4815785073295803, + "grad_norm": 0.5920754671096802, + "learning_rate": 5.4282137741986125e-05, + "loss": 1.9077, + "step": 8640 + }, + { + "epoch": 0.4816342455827434, + "grad_norm": 0.5471158623695374, + "learning_rate": 5.427326615279182e-05, + "loss": 1.6468, + "step": 8641 + }, + { + "epoch": 0.4816899838359066, + "grad_norm": 0.5595037341117859, + "learning_rate": 5.426439442807444e-05, + "loss": 1.7315, + "step": 8642 + }, + { + "epoch": 0.48174572208906974, + "grad_norm": 0.5808396935462952, + "learning_rate": 5.4255522568115314e-05, + "loss": 1.8597, + "step": 8643 + }, + { + "epoch": 0.48180146034223287, + "grad_norm": 0.5106577277183533, + "learning_rate": 5.424665057319584e-05, + "loss": 1.4579, + "step": 8644 + }, + { + "epoch": 0.481857198595396, + "grad_norm": 0.5588060617446899, + "learning_rate": 5.4237778443597366e-05, + "loss": 1.7045, + "step": 8645 + }, + { + "epoch": 0.4819129368485592, + "grad_norm": 0.5763769149780273, + "learning_rate": 5.4228906179601256e-05, + "loss": 1.7194, + "step": 8646 + }, + { + "epoch": 0.4819686751017223, + "grad_norm": 0.5877617597579956, + "learning_rate": 5.42200337814889e-05, + "loss": 1.8115, + "step": 8647 + }, + { + "epoch": 0.48202441335488544, + "grad_norm": 0.588557779788971, + "learning_rate": 5.421116124954169e-05, + "loss": 1.7122, + "step": 8648 + }, + { + "epoch": 0.4820801516080486, + "grad_norm": 0.5687382221221924, + "learning_rate": 5.4202288584040996e-05, + "loss": 1.6734, + "step": 8649 + }, + { + "epoch": 0.48213588986121175, + "grad_norm": 0.5797961950302124, + "learning_rate": 5.4193415785268195e-05, + "loss": 1.9098, + "step": 8650 + }, + { + "epoch": 0.4821916281143749, + "grad_norm": 0.5459732413291931, + "learning_rate": 5.418454285350472e-05, + "loss": 1.5751, + "step": 8651 + }, + { + "epoch": 0.48224736636753807, + "grad_norm": 0.6237668991088867, + "learning_rate": 5.4175669789031904e-05, + "loss": 1.9574, + "step": 8652 + }, + { + "epoch": 0.4823031046207012, + "grad_norm": 0.5237795114517212, + "learning_rate": 5.4166796592131216e-05, + "loss": 1.6274, + "step": 8653 + }, + { + "epoch": 0.4823588428738643, + "grad_norm": 0.8351784348487854, + "learning_rate": 5.415792326308403e-05, + "loss": 1.6101, + "step": 8654 + }, + { + "epoch": 0.48241458112702745, + "grad_norm": 0.553855836391449, + "learning_rate": 5.414904980217177e-05, + "loss": 1.7006, + "step": 8655 + }, + { + "epoch": 0.48247031938019064, + "grad_norm": 0.5128687620162964, + "learning_rate": 5.414017620967582e-05, + "loss": 1.5782, + "step": 8656 + }, + { + "epoch": 0.48252605763335377, + "grad_norm": 0.5743347406387329, + "learning_rate": 5.4131302485877635e-05, + "loss": 1.8762, + "step": 8657 + }, + { + "epoch": 0.4825817958865169, + "grad_norm": 0.5579991936683655, + "learning_rate": 5.412242863105862e-05, + "loss": 1.6882, + "step": 8658 + }, + { + "epoch": 0.4826375341396801, + "grad_norm": 0.5496572256088257, + "learning_rate": 5.41135546455002e-05, + "loss": 1.6909, + "step": 8659 + }, + { + "epoch": 0.4826932723928432, + "grad_norm": 0.5845061540603638, + "learning_rate": 5.410468052948381e-05, + "loss": 1.8966, + "step": 8660 + }, + { + "epoch": 0.48274901064600634, + "grad_norm": 0.5628004670143127, + "learning_rate": 5.409580628329088e-05, + "loss": 1.6114, + "step": 8661 + }, + { + "epoch": 0.4828047488991695, + "grad_norm": 0.52235347032547, + "learning_rate": 5.408693190720288e-05, + "loss": 1.4296, + "step": 8662 + }, + { + "epoch": 0.48286048715233265, + "grad_norm": 0.5655858516693115, + "learning_rate": 5.40780574015012e-05, + "loss": 1.7761, + "step": 8663 + }, + { + "epoch": 0.4829162254054958, + "grad_norm": 0.5697308778762817, + "learning_rate": 5.406918276646733e-05, + "loss": 1.7426, + "step": 8664 + }, + { + "epoch": 0.48297196365865896, + "grad_norm": 0.5626512169837952, + "learning_rate": 5.40603080023827e-05, + "loss": 1.5949, + "step": 8665 + }, + { + "epoch": 0.4830277019118221, + "grad_norm": 0.6178479194641113, + "learning_rate": 5.405143310952878e-05, + "loss": 1.9571, + "step": 8666 + }, + { + "epoch": 0.4830834401649852, + "grad_norm": 0.6123231053352356, + "learning_rate": 5.4042558088187014e-05, + "loss": 1.9154, + "step": 8667 + }, + { + "epoch": 0.48313917841814835, + "grad_norm": 0.5526097416877747, + "learning_rate": 5.40336829386389e-05, + "loss": 1.5508, + "step": 8668 + }, + { + "epoch": 0.48319491667131154, + "grad_norm": 0.5456022620201111, + "learning_rate": 5.4024807661165855e-05, + "loss": 1.5887, + "step": 8669 + }, + { + "epoch": 0.48325065492447467, + "grad_norm": 0.49078524112701416, + "learning_rate": 5.4015932256049386e-05, + "loss": 1.5876, + "step": 8670 + }, + { + "epoch": 0.4833063931776378, + "grad_norm": 0.5714897513389587, + "learning_rate": 5.4007056723570956e-05, + "loss": 1.8633, + "step": 8671 + }, + { + "epoch": 0.483362131430801, + "grad_norm": 0.6069988012313843, + "learning_rate": 5.399818106401206e-05, + "loss": 1.7922, + "step": 8672 + }, + { + "epoch": 0.4834178696839641, + "grad_norm": 0.5466931462287903, + "learning_rate": 5.3989305277654156e-05, + "loss": 1.7496, + "step": 8673 + }, + { + "epoch": 0.48347360793712724, + "grad_norm": 0.562350869178772, + "learning_rate": 5.398042936477875e-05, + "loss": 1.6191, + "step": 8674 + }, + { + "epoch": 0.4835293461902904, + "grad_norm": 0.5562702417373657, + "learning_rate": 5.397155332566736e-05, + "loss": 1.8695, + "step": 8675 + }, + { + "epoch": 0.48358508444345355, + "grad_norm": 0.598784863948822, + "learning_rate": 5.3962677160601426e-05, + "loss": 1.5275, + "step": 8676 + }, + { + "epoch": 0.4836408226966167, + "grad_norm": 0.5225400924682617, + "learning_rate": 5.395380086986249e-05, + "loss": 1.4847, + "step": 8677 + }, + { + "epoch": 0.4836965609497798, + "grad_norm": 0.58516925573349, + "learning_rate": 5.3944924453732014e-05, + "loss": 1.652, + "step": 8678 + }, + { + "epoch": 0.483752299202943, + "grad_norm": 0.5312181115150452, + "learning_rate": 5.3936047912491574e-05, + "loss": 1.356, + "step": 8679 + }, + { + "epoch": 0.4838080374561061, + "grad_norm": 0.5645095109939575, + "learning_rate": 5.3927171246422615e-05, + "loss": 1.7965, + "step": 8680 + }, + { + "epoch": 0.48386377570926925, + "grad_norm": 0.5576086044311523, + "learning_rate": 5.39182944558067e-05, + "loss": 1.6595, + "step": 8681 + }, + { + "epoch": 0.48391951396243243, + "grad_norm": 0.5667631030082703, + "learning_rate": 5.390941754092532e-05, + "loss": 1.6973, + "step": 8682 + }, + { + "epoch": 0.48397525221559556, + "grad_norm": 0.5693982243537903, + "learning_rate": 5.3900540502060015e-05, + "loss": 1.6383, + "step": 8683 + }, + { + "epoch": 0.4840309904687587, + "grad_norm": 0.5972820520401001, + "learning_rate": 5.3891663339492306e-05, + "loss": 1.73, + "step": 8684 + }, + { + "epoch": 0.4840867287219219, + "grad_norm": 0.5453163385391235, + "learning_rate": 5.388278605350372e-05, + "loss": 1.5295, + "step": 8685 + }, + { + "epoch": 0.484142466975085, + "grad_norm": 0.5659864544868469, + "learning_rate": 5.38739086443758e-05, + "loss": 1.6765, + "step": 8686 + }, + { + "epoch": 0.48419820522824814, + "grad_norm": 0.5438006520271301, + "learning_rate": 5.386503111239008e-05, + "loss": 1.5357, + "step": 8687 + }, + { + "epoch": 0.4842539434814113, + "grad_norm": 0.5650402903556824, + "learning_rate": 5.385615345782813e-05, + "loss": 1.7396, + "step": 8688 + }, + { + "epoch": 0.48430968173457445, + "grad_norm": 0.5356137156486511, + "learning_rate": 5.3847275680971454e-05, + "loss": 1.7116, + "step": 8689 + }, + { + "epoch": 0.4843654199877376, + "grad_norm": 0.5687363743782043, + "learning_rate": 5.383839778210163e-05, + "loss": 1.6747, + "step": 8690 + }, + { + "epoch": 0.4844211582409007, + "grad_norm": 0.5704367756843567, + "learning_rate": 5.38295197615002e-05, + "loss": 1.5563, + "step": 8691 + }, + { + "epoch": 0.4844768964940639, + "grad_norm": 0.6154001355171204, + "learning_rate": 5.382064161944874e-05, + "loss": 2.1129, + "step": 8692 + }, + { + "epoch": 0.484532634747227, + "grad_norm": 0.5885458588600159, + "learning_rate": 5.3811763356228804e-05, + "loss": 1.6652, + "step": 8693 + }, + { + "epoch": 0.48458837300039015, + "grad_norm": 0.5427495837211609, + "learning_rate": 5.3802884972121955e-05, + "loss": 1.7085, + "step": 8694 + }, + { + "epoch": 0.48464411125355333, + "grad_norm": 0.5415340065956116, + "learning_rate": 5.379400646740977e-05, + "loss": 1.7126, + "step": 8695 + }, + { + "epoch": 0.48469984950671646, + "grad_norm": 0.50815749168396, + "learning_rate": 5.3785127842373814e-05, + "loss": 1.7257, + "step": 8696 + }, + { + "epoch": 0.4847555877598796, + "grad_norm": 0.5710844397544861, + "learning_rate": 5.3776249097295696e-05, + "loss": 1.6778, + "step": 8697 + }, + { + "epoch": 0.4848113260130428, + "grad_norm": 0.5827280282974243, + "learning_rate": 5.376737023245695e-05, + "loss": 1.717, + "step": 8698 + }, + { + "epoch": 0.4848670642662059, + "grad_norm": 0.6222889423370361, + "learning_rate": 5.375849124813919e-05, + "loss": 1.9998, + "step": 8699 + }, + { + "epoch": 0.48492280251936903, + "grad_norm": 0.5893861651420593, + "learning_rate": 5.3749612144623995e-05, + "loss": 1.9211, + "step": 8700 + }, + { + "epoch": 0.48497854077253216, + "grad_norm": 0.5538213849067688, + "learning_rate": 5.374073292219297e-05, + "loss": 1.7934, + "step": 8701 + }, + { + "epoch": 0.48503427902569535, + "grad_norm": 0.5892875790596008, + "learning_rate": 5.3731853581127714e-05, + "loss": 1.8932, + "step": 8702 + }, + { + "epoch": 0.4850900172788585, + "grad_norm": 0.5553523302078247, + "learning_rate": 5.3722974121709815e-05, + "loss": 1.7465, + "step": 8703 + }, + { + "epoch": 0.4851457555320216, + "grad_norm": 0.57076096534729, + "learning_rate": 5.371409454422087e-05, + "loss": 1.7025, + "step": 8704 + }, + { + "epoch": 0.4852014937851848, + "grad_norm": 0.5483660101890564, + "learning_rate": 5.370521484894252e-05, + "loss": 1.6435, + "step": 8705 + }, + { + "epoch": 0.4852572320383479, + "grad_norm": 0.5742903351783752, + "learning_rate": 5.3696335036156345e-05, + "loss": 1.7067, + "step": 8706 + }, + { + "epoch": 0.48531297029151105, + "grad_norm": 0.5819395184516907, + "learning_rate": 5.368745510614399e-05, + "loss": 1.6528, + "step": 8707 + }, + { + "epoch": 0.48536870854467423, + "grad_norm": 0.5477610230445862, + "learning_rate": 5.367857505918704e-05, + "loss": 1.8253, + "step": 8708 + }, + { + "epoch": 0.48542444679783736, + "grad_norm": 0.6026375889778137, + "learning_rate": 5.3669694895567145e-05, + "loss": 1.8483, + "step": 8709 + }, + { + "epoch": 0.4854801850510005, + "grad_norm": 0.49743878841400146, + "learning_rate": 5.366081461556593e-05, + "loss": 1.4705, + "step": 8710 + }, + { + "epoch": 0.4855359233041637, + "grad_norm": 0.5510653853416443, + "learning_rate": 5.365193421946502e-05, + "loss": 1.4843, + "step": 8711 + }, + { + "epoch": 0.4855916615573268, + "grad_norm": 0.5583814978599548, + "learning_rate": 5.3643053707546034e-05, + "loss": 1.6045, + "step": 8712 + }, + { + "epoch": 0.48564739981048993, + "grad_norm": 0.5511784553527832, + "learning_rate": 5.363417308009062e-05, + "loss": 1.7184, + "step": 8713 + }, + { + "epoch": 0.48570313806365306, + "grad_norm": 0.5590716600418091, + "learning_rate": 5.362529233738045e-05, + "loss": 1.6326, + "step": 8714 + }, + { + "epoch": 0.48575887631681625, + "grad_norm": 0.564095139503479, + "learning_rate": 5.361641147969713e-05, + "loss": 1.6036, + "step": 8715 + }, + { + "epoch": 0.4858146145699794, + "grad_norm": 0.6147303581237793, + "learning_rate": 5.3607530507322334e-05, + "loss": 1.8542, + "step": 8716 + }, + { + "epoch": 0.4858703528231425, + "grad_norm": 0.556438684463501, + "learning_rate": 5.3598649420537675e-05, + "loss": 1.6413, + "step": 8717 + }, + { + "epoch": 0.4859260910763057, + "grad_norm": 0.5851439237594604, + "learning_rate": 5.358976821962487e-05, + "loss": 1.7414, + "step": 8718 + }, + { + "epoch": 0.4859818293294688, + "grad_norm": 0.5886179804801941, + "learning_rate": 5.358088690486553e-05, + "loss": 1.623, + "step": 8719 + }, + { + "epoch": 0.48603756758263195, + "grad_norm": 0.5328960418701172, + "learning_rate": 5.357200547654134e-05, + "loss": 1.4861, + "step": 8720 + }, + { + "epoch": 0.48609330583579513, + "grad_norm": 0.5452643036842346, + "learning_rate": 5.356312393493396e-05, + "loss": 1.763, + "step": 8721 + }, + { + "epoch": 0.48614904408895826, + "grad_norm": 0.5395748019218445, + "learning_rate": 5.3554242280325064e-05, + "loss": 1.4284, + "step": 8722 + }, + { + "epoch": 0.4862047823421214, + "grad_norm": 0.6557826399803162, + "learning_rate": 5.354536051299634e-05, + "loss": 1.8725, + "step": 8723 + }, + { + "epoch": 0.4862605205952845, + "grad_norm": 0.5590106248855591, + "learning_rate": 5.353647863322943e-05, + "loss": 1.6673, + "step": 8724 + }, + { + "epoch": 0.4863162588484477, + "grad_norm": 0.560207188129425, + "learning_rate": 5.3527596641306034e-05, + "loss": 1.7026, + "step": 8725 + }, + { + "epoch": 0.48637199710161083, + "grad_norm": 0.54021817445755, + "learning_rate": 5.3518714537507855e-05, + "loss": 1.3786, + "step": 8726 + }, + { + "epoch": 0.48642773535477396, + "grad_norm": 0.5303489565849304, + "learning_rate": 5.350983232211657e-05, + "loss": 1.5461, + "step": 8727 + }, + { + "epoch": 0.48648347360793714, + "grad_norm": 0.5234289169311523, + "learning_rate": 5.350094999541385e-05, + "loss": 1.8215, + "step": 8728 + }, + { + "epoch": 0.4865392118611003, + "grad_norm": 0.6171209216117859, + "learning_rate": 5.349206755768142e-05, + "loss": 1.6419, + "step": 8729 + }, + { + "epoch": 0.4865949501142634, + "grad_norm": 0.5630922317504883, + "learning_rate": 5.3483185009200955e-05, + "loss": 1.7303, + "step": 8730 + }, + { + "epoch": 0.4866506883674266, + "grad_norm": 0.5881733298301697, + "learning_rate": 5.347430235025419e-05, + "loss": 1.8506, + "step": 8731 + }, + { + "epoch": 0.4867064266205897, + "grad_norm": 0.5110684633255005, + "learning_rate": 5.34654195811228e-05, + "loss": 1.4549, + "step": 8732 + }, + { + "epoch": 0.48676216487375285, + "grad_norm": 0.5621329545974731, + "learning_rate": 5.345653670208851e-05, + "loss": 1.6001, + "step": 8733 + }, + { + "epoch": 0.48681790312691603, + "grad_norm": 0.5230090022087097, + "learning_rate": 5.344765371343302e-05, + "loss": 1.7102, + "step": 8734 + }, + { + "epoch": 0.48687364138007916, + "grad_norm": 0.5325090289115906, + "learning_rate": 5.343877061543806e-05, + "loss": 1.5661, + "step": 8735 + }, + { + "epoch": 0.4869293796332423, + "grad_norm": 0.5863301753997803, + "learning_rate": 5.342988740838535e-05, + "loss": 1.9036, + "step": 8736 + }, + { + "epoch": 0.4869851178864054, + "grad_norm": 0.5872917175292969, + "learning_rate": 5.342100409255659e-05, + "loss": 1.8516, + "step": 8737 + }, + { + "epoch": 0.4870408561395686, + "grad_norm": 0.5677287578582764, + "learning_rate": 5.341212066823355e-05, + "loss": 1.5462, + "step": 8738 + }, + { + "epoch": 0.48709659439273173, + "grad_norm": 0.5717810392379761, + "learning_rate": 5.340323713569792e-05, + "loss": 1.7118, + "step": 8739 + }, + { + "epoch": 0.48715233264589486, + "grad_norm": 0.5940883159637451, + "learning_rate": 5.339435349523148e-05, + "loss": 1.8225, + "step": 8740 + }, + { + "epoch": 0.48720807089905804, + "grad_norm": 0.6162937879562378, + "learning_rate": 5.33854697471159e-05, + "loss": 1.9512, + "step": 8741 + }, + { + "epoch": 0.4872638091522212, + "grad_norm": 0.5418954491615295, + "learning_rate": 5.337658589163299e-05, + "loss": 1.6836, + "step": 8742 + }, + { + "epoch": 0.4873195474053843, + "grad_norm": 0.5783557295799255, + "learning_rate": 5.3367701929064426e-05, + "loss": 1.709, + "step": 8743 + }, + { + "epoch": 0.4873752856585475, + "grad_norm": 0.5385530591011047, + "learning_rate": 5.3358817859692025e-05, + "loss": 1.5885, + "step": 8744 + }, + { + "epoch": 0.4874310239117106, + "grad_norm": 0.5666008591651917, + "learning_rate": 5.334993368379748e-05, + "loss": 1.6946, + "step": 8745 + }, + { + "epoch": 0.48748676216487374, + "grad_norm": 0.549767255783081, + "learning_rate": 5.3341049401662594e-05, + "loss": 1.5776, + "step": 8746 + }, + { + "epoch": 0.4875425004180369, + "grad_norm": 0.5610424280166626, + "learning_rate": 5.333216501356909e-05, + "loss": 1.6057, + "step": 8747 + }, + { + "epoch": 0.48759823867120006, + "grad_norm": 0.5643283724784851, + "learning_rate": 5.332328051979873e-05, + "loss": 1.7629, + "step": 8748 + }, + { + "epoch": 0.4876539769243632, + "grad_norm": 0.5474547743797302, + "learning_rate": 5.3314395920633306e-05, + "loss": 1.7972, + "step": 8749 + }, + { + "epoch": 0.4877097151775263, + "grad_norm": 0.56900554895401, + "learning_rate": 5.330551121635454e-05, + "loss": 1.7521, + "step": 8750 + }, + { + "epoch": 0.4877654534306895, + "grad_norm": 0.6560434103012085, + "learning_rate": 5.329662640724426e-05, + "loss": 1.4613, + "step": 8751 + }, + { + "epoch": 0.48782119168385263, + "grad_norm": 0.5190215110778809, + "learning_rate": 5.32877414935842e-05, + "loss": 1.4367, + "step": 8752 + }, + { + "epoch": 0.48787692993701576, + "grad_norm": 0.5503537058830261, + "learning_rate": 5.3278856475656144e-05, + "loss": 1.649, + "step": 8753 + }, + { + "epoch": 0.48793266819017894, + "grad_norm": 0.5634624361991882, + "learning_rate": 5.326997135374189e-05, + "loss": 1.9406, + "step": 8754 + }, + { + "epoch": 0.48798840644334207, + "grad_norm": 0.5632345676422119, + "learning_rate": 5.3261086128123206e-05, + "loss": 1.6661, + "step": 8755 + }, + { + "epoch": 0.4880441446965052, + "grad_norm": 0.6362982392311096, + "learning_rate": 5.3252200799081875e-05, + "loss": 1.9258, + "step": 8756 + }, + { + "epoch": 0.4880998829496684, + "grad_norm": 0.5737461447715759, + "learning_rate": 5.3243315366899694e-05, + "loss": 1.6868, + "step": 8757 + }, + { + "epoch": 0.4881556212028315, + "grad_norm": 0.5335796475410461, + "learning_rate": 5.3234429831858466e-05, + "loss": 1.4586, + "step": 8758 + }, + { + "epoch": 0.48821135945599464, + "grad_norm": 0.5574231743812561, + "learning_rate": 5.3225544194239984e-05, + "loss": 1.6262, + "step": 8759 + }, + { + "epoch": 0.48826709770915777, + "grad_norm": 0.5251532196998596, + "learning_rate": 5.3216658454326043e-05, + "loss": 1.5789, + "step": 8760 + }, + { + "epoch": 0.48832283596232096, + "grad_norm": 0.5983790159225464, + "learning_rate": 5.3207772612398444e-05, + "loss": 1.8751, + "step": 8761 + }, + { + "epoch": 0.4883785742154841, + "grad_norm": 0.5940685272216797, + "learning_rate": 5.319888666873902e-05, + "loss": 1.5181, + "step": 8762 + }, + { + "epoch": 0.4884343124686472, + "grad_norm": 0.5403158664703369, + "learning_rate": 5.319000062362953e-05, + "loss": 1.6698, + "step": 8763 + }, + { + "epoch": 0.4884900507218104, + "grad_norm": 0.5441331267356873, + "learning_rate": 5.318111447735186e-05, + "loss": 1.6822, + "step": 8764 + }, + { + "epoch": 0.4885457889749735, + "grad_norm": 0.6151909232139587, + "learning_rate": 5.317222823018775e-05, + "loss": 1.8201, + "step": 8765 + }, + { + "epoch": 0.48860152722813666, + "grad_norm": 0.5616387724876404, + "learning_rate": 5.316334188241908e-05, + "loss": 1.705, + "step": 8766 + }, + { + "epoch": 0.48865726548129984, + "grad_norm": 0.570561408996582, + "learning_rate": 5.3154455434327634e-05, + "loss": 1.7352, + "step": 8767 + }, + { + "epoch": 0.48871300373446297, + "grad_norm": 0.5549841523170471, + "learning_rate": 5.314556888619527e-05, + "loss": 1.7109, + "step": 8768 + }, + { + "epoch": 0.4887687419876261, + "grad_norm": 0.6028071045875549, + "learning_rate": 5.313668223830378e-05, + "loss": 1.7114, + "step": 8769 + }, + { + "epoch": 0.4888244802407892, + "grad_norm": 0.563991129398346, + "learning_rate": 5.312779549093503e-05, + "loss": 1.5484, + "step": 8770 + }, + { + "epoch": 0.4888802184939524, + "grad_norm": 0.5773816108703613, + "learning_rate": 5.3118908644370834e-05, + "loss": 1.7072, + "step": 8771 + }, + { + "epoch": 0.48893595674711554, + "grad_norm": 0.5592569708824158, + "learning_rate": 5.3110021698893053e-05, + "loss": 1.7843, + "step": 8772 + }, + { + "epoch": 0.48899169500027867, + "grad_norm": 0.5349111557006836, + "learning_rate": 5.310113465478351e-05, + "loss": 1.5887, + "step": 8773 + }, + { + "epoch": 0.48904743325344185, + "grad_norm": 0.5708144903182983, + "learning_rate": 5.309224751232406e-05, + "loss": 1.5671, + "step": 8774 + }, + { + "epoch": 0.489103171506605, + "grad_norm": 0.5695350766181946, + "learning_rate": 5.308336027179655e-05, + "loss": 1.8061, + "step": 8775 + }, + { + "epoch": 0.4891589097597681, + "grad_norm": 0.5757440328598022, + "learning_rate": 5.307447293348281e-05, + "loss": 1.7021, + "step": 8776 + }, + { + "epoch": 0.4892146480129313, + "grad_norm": 0.5219387412071228, + "learning_rate": 5.306558549766473e-05, + "loss": 1.5089, + "step": 8777 + }, + { + "epoch": 0.4892703862660944, + "grad_norm": 0.5836179256439209, + "learning_rate": 5.305669796462415e-05, + "loss": 1.764, + "step": 8778 + }, + { + "epoch": 0.48932612451925755, + "grad_norm": 0.5617983341217041, + "learning_rate": 5.3047810334642935e-05, + "loss": 1.751, + "step": 8779 + }, + { + "epoch": 0.48938186277242074, + "grad_norm": 0.5990623831748962, + "learning_rate": 5.303892260800294e-05, + "loss": 1.7939, + "step": 8780 + }, + { + "epoch": 0.48943760102558387, + "grad_norm": 0.5625554323196411, + "learning_rate": 5.303003478498605e-05, + "loss": 1.8436, + "step": 8781 + }, + { + "epoch": 0.489493339278747, + "grad_norm": 0.6201027631759644, + "learning_rate": 5.3021146865874117e-05, + "loss": 1.7894, + "step": 8782 + }, + { + "epoch": 0.4895490775319101, + "grad_norm": 0.5482053160667419, + "learning_rate": 5.301225885094902e-05, + "loss": 1.7486, + "step": 8783 + }, + { + "epoch": 0.4896048157850733, + "grad_norm": 0.5940152406692505, + "learning_rate": 5.300337074049262e-05, + "loss": 1.7971, + "step": 8784 + }, + { + "epoch": 0.48966055403823644, + "grad_norm": 0.49621883034706116, + "learning_rate": 5.299448253478683e-05, + "loss": 1.6085, + "step": 8785 + }, + { + "epoch": 0.48971629229139957, + "grad_norm": 0.5509806275367737, + "learning_rate": 5.29855942341135e-05, + "loss": 1.8445, + "step": 8786 + }, + { + "epoch": 0.48977203054456275, + "grad_norm": 0.5669719576835632, + "learning_rate": 5.297670583875454e-05, + "loss": 1.7854, + "step": 8787 + }, + { + "epoch": 0.4898277687977259, + "grad_norm": 0.5512406826019287, + "learning_rate": 5.296781734899182e-05, + "loss": 1.4982, + "step": 8788 + }, + { + "epoch": 0.489883507050889, + "grad_norm": 0.56741863489151, + "learning_rate": 5.295892876510723e-05, + "loss": 1.7415, + "step": 8789 + }, + { + "epoch": 0.4899392453040522, + "grad_norm": 0.5425149202346802, + "learning_rate": 5.295004008738268e-05, + "loss": 1.5488, + "step": 8790 + }, + { + "epoch": 0.4899949835572153, + "grad_norm": 0.5617731213569641, + "learning_rate": 5.294115131610006e-05, + "loss": 1.7582, + "step": 8791 + }, + { + "epoch": 0.49005072181037845, + "grad_norm": 0.5693073868751526, + "learning_rate": 5.293226245154127e-05, + "loss": 1.5738, + "step": 8792 + }, + { + "epoch": 0.4901064600635416, + "grad_norm": 0.6429868340492249, + "learning_rate": 5.292337349398821e-05, + "loss": 1.7709, + "step": 8793 + }, + { + "epoch": 0.49016219831670477, + "grad_norm": 0.568608283996582, + "learning_rate": 5.291448444372279e-05, + "loss": 1.5022, + "step": 8794 + }, + { + "epoch": 0.4902179365698679, + "grad_norm": 0.5543949604034424, + "learning_rate": 5.29055953010269e-05, + "loss": 1.7136, + "step": 8795 + }, + { + "epoch": 0.490273674823031, + "grad_norm": 0.5077717900276184, + "learning_rate": 5.289670606618248e-05, + "loss": 1.5791, + "step": 8796 + }, + { + "epoch": 0.4903294130761942, + "grad_norm": 0.5588290691375732, + "learning_rate": 5.288781673947143e-05, + "loss": 1.7905, + "step": 8797 + }, + { + "epoch": 0.49038515132935734, + "grad_norm": 0.5637931823730469, + "learning_rate": 5.2878927321175676e-05, + "loss": 1.7184, + "step": 8798 + }, + { + "epoch": 0.49044088958252047, + "grad_norm": 0.5664627552032471, + "learning_rate": 5.2870037811577125e-05, + "loss": 1.5013, + "step": 8799 + }, + { + "epoch": 0.49049662783568365, + "grad_norm": 0.5796491503715515, + "learning_rate": 5.28611482109577e-05, + "loss": 1.7939, + "step": 8800 + }, + { + "epoch": 0.4905523660888468, + "grad_norm": 0.556143045425415, + "learning_rate": 5.2852258519599365e-05, + "loss": 1.5717, + "step": 8801 + }, + { + "epoch": 0.4906081043420099, + "grad_norm": 0.5120705366134644, + "learning_rate": 5.284336873778398e-05, + "loss": 1.5725, + "step": 8802 + }, + { + "epoch": 0.4906638425951731, + "grad_norm": 0.5616738200187683, + "learning_rate": 5.2834478865793545e-05, + "loss": 1.5918, + "step": 8803 + }, + { + "epoch": 0.4907195808483362, + "grad_norm": 0.5868408679962158, + "learning_rate": 5.282558890390995e-05, + "loss": 1.7262, + "step": 8804 + }, + { + "epoch": 0.49077531910149935, + "grad_norm": 0.5609720945358276, + "learning_rate": 5.281669885241517e-05, + "loss": 1.6374, + "step": 8805 + }, + { + "epoch": 0.4908310573546625, + "grad_norm": 0.5879573225975037, + "learning_rate": 5.280780871159111e-05, + "loss": 1.7363, + "step": 8806 + }, + { + "epoch": 0.49088679560782567, + "grad_norm": 0.5944104790687561, + "learning_rate": 5.279891848171974e-05, + "loss": 1.8078, + "step": 8807 + }, + { + "epoch": 0.4909425338609888, + "grad_norm": 0.5318206548690796, + "learning_rate": 5.2790028163082985e-05, + "loss": 1.5397, + "step": 8808 + }, + { + "epoch": 0.4909982721141519, + "grad_norm": 0.542536199092865, + "learning_rate": 5.2781137755962794e-05, + "loss": 1.6362, + "step": 8809 + }, + { + "epoch": 0.4910540103673151, + "grad_norm": 0.5784698128700256, + "learning_rate": 5.2772247260641136e-05, + "loss": 1.765, + "step": 8810 + }, + { + "epoch": 0.49110974862047824, + "grad_norm": 0.5454279184341431, + "learning_rate": 5.276335667739998e-05, + "loss": 1.7014, + "step": 8811 + }, + { + "epoch": 0.49116548687364137, + "grad_norm": 0.519689679145813, + "learning_rate": 5.275446600652123e-05, + "loss": 1.7533, + "step": 8812 + }, + { + "epoch": 0.49122122512680455, + "grad_norm": 0.7089325785636902, + "learning_rate": 5.2745575248286895e-05, + "loss": 2.1051, + "step": 8813 + }, + { + "epoch": 0.4912769633799677, + "grad_norm": 0.5588321089744568, + "learning_rate": 5.273668440297892e-05, + "loss": 1.6069, + "step": 8814 + }, + { + "epoch": 0.4913327016331308, + "grad_norm": 0.5273601412773132, + "learning_rate": 5.272779347087925e-05, + "loss": 1.4399, + "step": 8815 + }, + { + "epoch": 0.49138843988629394, + "grad_norm": 0.5443345904350281, + "learning_rate": 5.27189024522699e-05, + "loss": 1.5401, + "step": 8816 + }, + { + "epoch": 0.4914441781394571, + "grad_norm": 0.5727609395980835, + "learning_rate": 5.271001134743281e-05, + "loss": 1.6588, + "step": 8817 + }, + { + "epoch": 0.49149991639262025, + "grad_norm": 0.5712710618972778, + "learning_rate": 5.270112015664997e-05, + "loss": 1.7393, + "step": 8818 + }, + { + "epoch": 0.4915556546457834, + "grad_norm": 0.5474506616592407, + "learning_rate": 5.2692228880203333e-05, + "loss": 1.6144, + "step": 8819 + }, + { + "epoch": 0.49161139289894656, + "grad_norm": 0.5622429251670837, + "learning_rate": 5.2683337518374906e-05, + "loss": 1.6107, + "step": 8820 + }, + { + "epoch": 0.4916671311521097, + "grad_norm": 0.5528522729873657, + "learning_rate": 5.267444607144665e-05, + "loss": 1.5545, + "step": 8821 + }, + { + "epoch": 0.4917228694052728, + "grad_norm": 0.5275382995605469, + "learning_rate": 5.2665554539700554e-05, + "loss": 1.6128, + "step": 8822 + }, + { + "epoch": 0.491778607658436, + "grad_norm": 0.6423818469047546, + "learning_rate": 5.265666292341861e-05, + "loss": 2.064, + "step": 8823 + }, + { + "epoch": 0.49183434591159914, + "grad_norm": 0.5372768640518188, + "learning_rate": 5.26477712228828e-05, + "loss": 1.2805, + "step": 8824 + }, + { + "epoch": 0.49189008416476226, + "grad_norm": 0.600679337978363, + "learning_rate": 5.2638879438375144e-05, + "loss": 1.8211, + "step": 8825 + }, + { + "epoch": 0.49194582241792545, + "grad_norm": 0.5628047585487366, + "learning_rate": 5.2629987570177606e-05, + "loss": 1.6321, + "step": 8826 + }, + { + "epoch": 0.4920015606710886, + "grad_norm": 0.600486695766449, + "learning_rate": 5.262109561857221e-05, + "loss": 1.782, + "step": 8827 + }, + { + "epoch": 0.4920572989242517, + "grad_norm": 0.5375781655311584, + "learning_rate": 5.261220358384091e-05, + "loss": 1.5132, + "step": 8828 + }, + { + "epoch": 0.49211303717741484, + "grad_norm": 0.5441939830780029, + "learning_rate": 5.260331146626578e-05, + "loss": 1.4457, + "step": 8829 + }, + { + "epoch": 0.492168775430578, + "grad_norm": 0.5390109419822693, + "learning_rate": 5.259441926612877e-05, + "loss": 1.6268, + "step": 8830 + }, + { + "epoch": 0.49222451368374115, + "grad_norm": 0.5406618714332581, + "learning_rate": 5.2585526983711916e-05, + "loss": 1.5747, + "step": 8831 + }, + { + "epoch": 0.4922802519369043, + "grad_norm": 0.5526447296142578, + "learning_rate": 5.2576634619297216e-05, + "loss": 1.6989, + "step": 8832 + }, + { + "epoch": 0.49233599019006746, + "grad_norm": 0.5135407447814941, + "learning_rate": 5.256774217316669e-05, + "loss": 1.4546, + "step": 8833 + }, + { + "epoch": 0.4923917284432306, + "grad_norm": 0.5286427736282349, + "learning_rate": 5.255884964560235e-05, + "loss": 1.6071, + "step": 8834 + }, + { + "epoch": 0.4924474666963937, + "grad_norm": 0.5706698894500732, + "learning_rate": 5.254995703688621e-05, + "loss": 1.7096, + "step": 8835 + }, + { + "epoch": 0.4925032049495569, + "grad_norm": 0.5597012042999268, + "learning_rate": 5.2541064347300306e-05, + "loss": 1.6175, + "step": 8836 + }, + { + "epoch": 0.49255894320272003, + "grad_norm": 0.4902280271053314, + "learning_rate": 5.253217157712666e-05, + "loss": 1.2836, + "step": 8837 + }, + { + "epoch": 0.49261468145588316, + "grad_norm": 0.598961591720581, + "learning_rate": 5.2523278726647304e-05, + "loss": 1.7038, + "step": 8838 + }, + { + "epoch": 0.4926704197090463, + "grad_norm": 1.2628682851791382, + "learning_rate": 5.251438579614425e-05, + "loss": 1.8079, + "step": 8839 + }, + { + "epoch": 0.4927261579622095, + "grad_norm": 0.5793728232383728, + "learning_rate": 5.250549278589955e-05, + "loss": 1.8102, + "step": 8840 + }, + { + "epoch": 0.4927818962153726, + "grad_norm": 0.5742671489715576, + "learning_rate": 5.249659969619519e-05, + "loss": 1.6611, + "step": 8841 + }, + { + "epoch": 0.49283763446853573, + "grad_norm": 0.5438802242279053, + "learning_rate": 5.248770652731327e-05, + "loss": 1.5826, + "step": 8842 + }, + { + "epoch": 0.4928933727216989, + "grad_norm": 0.553573727607727, + "learning_rate": 5.247881327953581e-05, + "loss": 1.5787, + "step": 8843 + }, + { + "epoch": 0.49294911097486205, + "grad_norm": 0.5531934499740601, + "learning_rate": 5.246991995314484e-05, + "loss": 1.7769, + "step": 8844 + }, + { + "epoch": 0.4930048492280252, + "grad_norm": 0.5669671893119812, + "learning_rate": 5.24610265484224e-05, + "loss": 1.6973, + "step": 8845 + }, + { + "epoch": 0.49306058748118836, + "grad_norm": 0.5406858921051025, + "learning_rate": 5.2452133065650565e-05, + "loss": 1.4484, + "step": 8846 + }, + { + "epoch": 0.4931163257343515, + "grad_norm": 0.6136825084686279, + "learning_rate": 5.2443239505111354e-05, + "loss": 1.7145, + "step": 8847 + }, + { + "epoch": 0.4931720639875146, + "grad_norm": 0.5375277400016785, + "learning_rate": 5.243434586708682e-05, + "loss": 1.5229, + "step": 8848 + }, + { + "epoch": 0.4932278022406778, + "grad_norm": 0.5452854633331299, + "learning_rate": 5.2425452151859045e-05, + "loss": 1.4448, + "step": 8849 + }, + { + "epoch": 0.49328354049384093, + "grad_norm": 0.5728045701980591, + "learning_rate": 5.241655835971006e-05, + "loss": 1.8291, + "step": 8850 + }, + { + "epoch": 0.49333927874700406, + "grad_norm": 0.5290676951408386, + "learning_rate": 5.240766449092194e-05, + "loss": 1.53, + "step": 8851 + }, + { + "epoch": 0.4933950170001672, + "grad_norm": 0.6011704206466675, + "learning_rate": 5.239877054577673e-05, + "loss": 1.7215, + "step": 8852 + }, + { + "epoch": 0.4934507552533304, + "grad_norm": 0.5930907130241394, + "learning_rate": 5.2389876524556526e-05, + "loss": 1.8231, + "step": 8853 + }, + { + "epoch": 0.4935064935064935, + "grad_norm": 0.5788987874984741, + "learning_rate": 5.2380982427543346e-05, + "loss": 1.7529, + "step": 8854 + }, + { + "epoch": 0.49356223175965663, + "grad_norm": 0.5591574311256409, + "learning_rate": 5.23720882550193e-05, + "loss": 1.5894, + "step": 8855 + }, + { + "epoch": 0.4936179700128198, + "grad_norm": 0.6035146117210388, + "learning_rate": 5.2363194007266435e-05, + "loss": 1.811, + "step": 8856 + }, + { + "epoch": 0.49367370826598295, + "grad_norm": 0.5160028338432312, + "learning_rate": 5.2354299684566856e-05, + "loss": 1.6787, + "step": 8857 + }, + { + "epoch": 0.4937294465191461, + "grad_norm": 0.5431737899780273, + "learning_rate": 5.2345405287202596e-05, + "loss": 1.4917, + "step": 8858 + }, + { + "epoch": 0.49378518477230926, + "grad_norm": 0.5381173491477966, + "learning_rate": 5.233651081545577e-05, + "loss": 1.6775, + "step": 8859 + }, + { + "epoch": 0.4938409230254724, + "grad_norm": 0.6041108965873718, + "learning_rate": 5.232761626960844e-05, + "loss": 1.6414, + "step": 8860 + }, + { + "epoch": 0.4938966612786355, + "grad_norm": 0.6218950152397156, + "learning_rate": 5.231872164994268e-05, + "loss": 1.6513, + "step": 8861 + }, + { + "epoch": 0.49395239953179865, + "grad_norm": 0.5222500562667847, + "learning_rate": 5.230982695674059e-05, + "loss": 1.7083, + "step": 8862 + }, + { + "epoch": 0.49400813778496183, + "grad_norm": 0.5420836806297302, + "learning_rate": 5.230093219028427e-05, + "loss": 1.5971, + "step": 8863 + }, + { + "epoch": 0.49406387603812496, + "grad_norm": 0.5384796857833862, + "learning_rate": 5.229203735085579e-05, + "loss": 1.5896, + "step": 8864 + }, + { + "epoch": 0.4941196142912881, + "grad_norm": 0.6375717520713806, + "learning_rate": 5.2283142438737245e-05, + "loss": 1.8503, + "step": 8865 + }, + { + "epoch": 0.4941753525444513, + "grad_norm": 0.5303763151168823, + "learning_rate": 5.227424745421074e-05, + "loss": 1.6416, + "step": 8866 + }, + { + "epoch": 0.4942310907976144, + "grad_norm": 0.5153331756591797, + "learning_rate": 5.2265352397558354e-05, + "loss": 1.3659, + "step": 8867 + }, + { + "epoch": 0.49428682905077753, + "grad_norm": 0.5397130846977234, + "learning_rate": 5.225645726906222e-05, + "loss": 1.5523, + "step": 8868 + }, + { + "epoch": 0.4943425673039407, + "grad_norm": 0.5596987009048462, + "learning_rate": 5.224756206900439e-05, + "loss": 1.7921, + "step": 8869 + }, + { + "epoch": 0.49439830555710385, + "grad_norm": 0.5709193348884583, + "learning_rate": 5.2238666797667026e-05, + "loss": 1.6013, + "step": 8870 + }, + { + "epoch": 0.494454043810267, + "grad_norm": 0.5561599731445312, + "learning_rate": 5.2229771455332176e-05, + "loss": 1.4794, + "step": 8871 + }, + { + "epoch": 0.49450978206343016, + "grad_norm": 0.5445564985275269, + "learning_rate": 5.2220876042281995e-05, + "loss": 1.5029, + "step": 8872 + }, + { + "epoch": 0.4945655203165933, + "grad_norm": 0.5647691488265991, + "learning_rate": 5.2211980558798565e-05, + "loss": 1.7888, + "step": 8873 + }, + { + "epoch": 0.4946212585697564, + "grad_norm": 0.5487396717071533, + "learning_rate": 5.220308500516401e-05, + "loss": 1.6931, + "step": 8874 + }, + { + "epoch": 0.49467699682291955, + "grad_norm": 0.5969203114509583, + "learning_rate": 5.219418938166044e-05, + "loss": 1.6718, + "step": 8875 + }, + { + "epoch": 0.49473273507608273, + "grad_norm": 0.564508855342865, + "learning_rate": 5.218529368856997e-05, + "loss": 1.6968, + "step": 8876 + }, + { + "epoch": 0.49478847332924586, + "grad_norm": 0.5070094466209412, + "learning_rate": 5.217639792617475e-05, + "loss": 1.5859, + "step": 8877 + }, + { + "epoch": 0.494844211582409, + "grad_norm": 0.5474216341972351, + "learning_rate": 5.216750209475685e-05, + "loss": 1.7858, + "step": 8878 + }, + { + "epoch": 0.4948999498355722, + "grad_norm": 0.4998477101325989, + "learning_rate": 5.2158606194598436e-05, + "loss": 1.4827, + "step": 8879 + }, + { + "epoch": 0.4949556880887353, + "grad_norm": 0.5660443305969238, + "learning_rate": 5.214971022598162e-05, + "loss": 1.7799, + "step": 8880 + }, + { + "epoch": 0.49501142634189843, + "grad_norm": 0.5911859273910522, + "learning_rate": 5.2140814189188514e-05, + "loss": 1.6708, + "step": 8881 + }, + { + "epoch": 0.4950671645950616, + "grad_norm": 0.5817141532897949, + "learning_rate": 5.213191808450127e-05, + "loss": 1.6558, + "step": 8882 + }, + { + "epoch": 0.49512290284822474, + "grad_norm": 0.5510105490684509, + "learning_rate": 5.212302191220203e-05, + "loss": 1.5644, + "step": 8883 + }, + { + "epoch": 0.4951786411013879, + "grad_norm": 0.6024221181869507, + "learning_rate": 5.21141256725729e-05, + "loss": 1.7236, + "step": 8884 + }, + { + "epoch": 0.495234379354551, + "grad_norm": 0.5197804570198059, + "learning_rate": 5.210522936589604e-05, + "loss": 1.5429, + "step": 8885 + }, + { + "epoch": 0.4952901176077142, + "grad_norm": 0.5537724494934082, + "learning_rate": 5.209633299245357e-05, + "loss": 1.7254, + "step": 8886 + }, + { + "epoch": 0.4953458558608773, + "grad_norm": 0.5095260739326477, + "learning_rate": 5.208743655252763e-05, + "loss": 1.4012, + "step": 8887 + }, + { + "epoch": 0.49540159411404044, + "grad_norm": 0.5599790811538696, + "learning_rate": 5.207854004640038e-05, + "loss": 1.7249, + "step": 8888 + }, + { + "epoch": 0.49545733236720363, + "grad_norm": 0.555938184261322, + "learning_rate": 5.206964347435396e-05, + "loss": 1.6312, + "step": 8889 + }, + { + "epoch": 0.49551307062036676, + "grad_norm": 0.5438600182533264, + "learning_rate": 5.206074683667053e-05, + "loss": 1.7241, + "step": 8890 + }, + { + "epoch": 0.4955688088735299, + "grad_norm": 0.5477585792541504, + "learning_rate": 5.2051850133632206e-05, + "loss": 1.6946, + "step": 8891 + }, + { + "epoch": 0.49562454712669307, + "grad_norm": 0.5788122415542603, + "learning_rate": 5.204295336552117e-05, + "loss": 1.503, + "step": 8892 + }, + { + "epoch": 0.4956802853798562, + "grad_norm": 0.5613676309585571, + "learning_rate": 5.203405653261956e-05, + "loss": 1.5574, + "step": 8893 + }, + { + "epoch": 0.49573602363301933, + "grad_norm": 0.5826630592346191, + "learning_rate": 5.202515963520953e-05, + "loss": 1.85, + "step": 8894 + }, + { + "epoch": 0.4957917618861825, + "grad_norm": 0.5635188817977905, + "learning_rate": 5.2016262673573246e-05, + "loss": 1.3931, + "step": 8895 + }, + { + "epoch": 0.49584750013934564, + "grad_norm": 0.5745763182640076, + "learning_rate": 5.200736564799288e-05, + "loss": 1.7307, + "step": 8896 + }, + { + "epoch": 0.49590323839250877, + "grad_norm": 0.5301480889320374, + "learning_rate": 5.199846855875057e-05, + "loss": 1.4952, + "step": 8897 + }, + { + "epoch": 0.4959589766456719, + "grad_norm": 0.561489999294281, + "learning_rate": 5.19895714061285e-05, + "loss": 1.5023, + "step": 8898 + }, + { + "epoch": 0.4960147148988351, + "grad_norm": 0.5963059663772583, + "learning_rate": 5.198067419040881e-05, + "loss": 1.7862, + "step": 8899 + }, + { + "epoch": 0.4960704531519982, + "grad_norm": 0.5533133149147034, + "learning_rate": 5.197177691187368e-05, + "loss": 1.6099, + "step": 8900 + }, + { + "epoch": 0.49612619140516134, + "grad_norm": 0.5286788940429688, + "learning_rate": 5.196287957080529e-05, + "loss": 1.5929, + "step": 8901 + }, + { + "epoch": 0.4961819296583245, + "grad_norm": 0.5352204442024231, + "learning_rate": 5.195398216748579e-05, + "loss": 1.5723, + "step": 8902 + }, + { + "epoch": 0.49623766791148766, + "grad_norm": 0.5606736540794373, + "learning_rate": 5.194508470219739e-05, + "loss": 1.6633, + "step": 8903 + }, + { + "epoch": 0.4962934061646508, + "grad_norm": 0.5791866779327393, + "learning_rate": 5.193618717522224e-05, + "loss": 1.6933, + "step": 8904 + }, + { + "epoch": 0.49634914441781397, + "grad_norm": 0.5928483009338379, + "learning_rate": 5.192728958684252e-05, + "loss": 1.8085, + "step": 8905 + }, + { + "epoch": 0.4964048826709771, + "grad_norm": 0.545987606048584, + "learning_rate": 5.1918391937340405e-05, + "loss": 1.6682, + "step": 8906 + }, + { + "epoch": 0.49646062092414023, + "grad_norm": 0.5828558206558228, + "learning_rate": 5.190949422699808e-05, + "loss": 1.7887, + "step": 8907 + }, + { + "epoch": 0.49651635917730336, + "grad_norm": 0.5636189579963684, + "learning_rate": 5.1900596456097736e-05, + "loss": 1.6192, + "step": 8908 + }, + { + "epoch": 0.49657209743046654, + "grad_norm": 0.5548069477081299, + "learning_rate": 5.189169862492156e-05, + "loss": 1.482, + "step": 8909 + }, + { + "epoch": 0.49662783568362967, + "grad_norm": 0.5686978697776794, + "learning_rate": 5.188280073375173e-05, + "loss": 1.5428, + "step": 8910 + }, + { + "epoch": 0.4966835739367928, + "grad_norm": 0.5715393424034119, + "learning_rate": 5.187390278287043e-05, + "loss": 1.751, + "step": 8911 + }, + { + "epoch": 0.496739312189956, + "grad_norm": 0.5473306775093079, + "learning_rate": 5.1865004772559876e-05, + "loss": 1.6317, + "step": 8912 + }, + { + "epoch": 0.4967950504431191, + "grad_norm": 0.5280557870864868, + "learning_rate": 5.1856106703102225e-05, + "loss": 1.382, + "step": 8913 + }, + { + "epoch": 0.49685078869628224, + "grad_norm": 0.566477358341217, + "learning_rate": 5.18472085747797e-05, + "loss": 1.6059, + "step": 8914 + }, + { + "epoch": 0.4969065269494454, + "grad_norm": 0.618401288986206, + "learning_rate": 5.183831038787449e-05, + "loss": 1.7905, + "step": 8915 + }, + { + "epoch": 0.49696226520260856, + "grad_norm": 0.555980384349823, + "learning_rate": 5.18294121426688e-05, + "loss": 1.7827, + "step": 8916 + }, + { + "epoch": 0.4970180034557717, + "grad_norm": 0.5835009813308716, + "learning_rate": 5.1820513839444804e-05, + "loss": 1.5225, + "step": 8917 + }, + { + "epoch": 0.49707374170893487, + "grad_norm": 0.5366058945655823, + "learning_rate": 5.181161547848474e-05, + "loss": 1.584, + "step": 8918 + }, + { + "epoch": 0.497129479962098, + "grad_norm": 0.5382677316665649, + "learning_rate": 5.1802717060070795e-05, + "loss": 1.7048, + "step": 8919 + }, + { + "epoch": 0.4971852182152611, + "grad_norm": 0.5656511783599854, + "learning_rate": 5.1793818584485166e-05, + "loss": 1.7254, + "step": 8920 + }, + { + "epoch": 0.49724095646842426, + "grad_norm": 0.4968765377998352, + "learning_rate": 5.178492005201007e-05, + "loss": 1.4276, + "step": 8921 + }, + { + "epoch": 0.49729669472158744, + "grad_norm": 0.599624514579773, + "learning_rate": 5.177602146292773e-05, + "loss": 1.7886, + "step": 8922 + }, + { + "epoch": 0.49735243297475057, + "grad_norm": 0.5555099844932556, + "learning_rate": 5.176712281752033e-05, + "loss": 1.5135, + "step": 8923 + }, + { + "epoch": 0.4974081712279137, + "grad_norm": 0.5166276693344116, + "learning_rate": 5.17582241160701e-05, + "loss": 1.284, + "step": 8924 + }, + { + "epoch": 0.4974639094810769, + "grad_norm": 0.5706877708435059, + "learning_rate": 5.1749325358859255e-05, + "loss": 1.5666, + "step": 8925 + }, + { + "epoch": 0.49751964773424, + "grad_norm": 0.6055343747138977, + "learning_rate": 5.1740426546170003e-05, + "loss": 1.7793, + "step": 8926 + }, + { + "epoch": 0.49757538598740314, + "grad_norm": 0.551367998123169, + "learning_rate": 5.1731527678284575e-05, + "loss": 1.7579, + "step": 8927 + }, + { + "epoch": 0.4976311242405663, + "grad_norm": 0.6338830590248108, + "learning_rate": 5.172262875548518e-05, + "loss": 1.691, + "step": 8928 + }, + { + "epoch": 0.49768686249372945, + "grad_norm": 0.5556480884552002, + "learning_rate": 5.171372977805405e-05, + "loss": 1.5507, + "step": 8929 + }, + { + "epoch": 0.4977426007468926, + "grad_norm": 0.5841500163078308, + "learning_rate": 5.17048307462734e-05, + "loss": 1.8044, + "step": 8930 + }, + { + "epoch": 0.4977983390000557, + "grad_norm": 0.5762627124786377, + "learning_rate": 5.169593166042547e-05, + "loss": 1.6068, + "step": 8931 + }, + { + "epoch": 0.4978540772532189, + "grad_norm": 0.5406793355941772, + "learning_rate": 5.1687032520792464e-05, + "loss": 1.6587, + "step": 8932 + }, + { + "epoch": 0.497909815506382, + "grad_norm": 0.5948076248168945, + "learning_rate": 5.1678133327656616e-05, + "loss": 1.7269, + "step": 8933 + }, + { + "epoch": 0.49796555375954515, + "grad_norm": 0.5559920072555542, + "learning_rate": 5.166923408130016e-05, + "loss": 1.7147, + "step": 8934 + }, + { + "epoch": 0.49802129201270834, + "grad_norm": 0.5676483511924744, + "learning_rate": 5.166033478200536e-05, + "loss": 1.5815, + "step": 8935 + }, + { + "epoch": 0.49807703026587147, + "grad_norm": 0.5557644367218018, + "learning_rate": 5.1651435430054396e-05, + "loss": 1.7004, + "step": 8936 + }, + { + "epoch": 0.4981327685190346, + "grad_norm": 0.5279107093811035, + "learning_rate": 5.164253602572954e-05, + "loss": 1.5522, + "step": 8937 + }, + { + "epoch": 0.4981885067721978, + "grad_norm": 0.5402976870536804, + "learning_rate": 5.1633636569313014e-05, + "loss": 1.6626, + "step": 8938 + }, + { + "epoch": 0.4982442450253609, + "grad_norm": 0.5484632849693298, + "learning_rate": 5.1624737061087056e-05, + "loss": 1.5598, + "step": 8939 + }, + { + "epoch": 0.49829998327852404, + "grad_norm": 0.5460349321365356, + "learning_rate": 5.161583750133392e-05, + "loss": 1.6661, + "step": 8940 + }, + { + "epoch": 0.4983557215316872, + "grad_norm": 0.5012972950935364, + "learning_rate": 5.160693789033583e-05, + "loss": 1.3436, + "step": 8941 + }, + { + "epoch": 0.49841145978485035, + "grad_norm": 0.5560734272003174, + "learning_rate": 5.159803822837506e-05, + "loss": 1.5994, + "step": 8942 + }, + { + "epoch": 0.4984671980380135, + "grad_norm": 0.5721739530563354, + "learning_rate": 5.1589138515733805e-05, + "loss": 1.8826, + "step": 8943 + }, + { + "epoch": 0.4985229362911766, + "grad_norm": 0.548629105091095, + "learning_rate": 5.158023875269436e-05, + "loss": 1.465, + "step": 8944 + }, + { + "epoch": 0.4985786745443398, + "grad_norm": 0.5386154651641846, + "learning_rate": 5.157133893953895e-05, + "loss": 1.624, + "step": 8945 + }, + { + "epoch": 0.4986344127975029, + "grad_norm": 0.6287878155708313, + "learning_rate": 5.156243907654983e-05, + "loss": 1.6433, + "step": 8946 + }, + { + "epoch": 0.49869015105066605, + "grad_norm": 0.6134181022644043, + "learning_rate": 5.155353916400925e-05, + "loss": 1.7598, + "step": 8947 + }, + { + "epoch": 0.49874588930382924, + "grad_norm": 0.5654070377349854, + "learning_rate": 5.154463920219947e-05, + "loss": 1.7002, + "step": 8948 + }, + { + "epoch": 0.49880162755699237, + "grad_norm": 0.5511396527290344, + "learning_rate": 5.153573919140274e-05, + "loss": 1.5513, + "step": 8949 + }, + { + "epoch": 0.4988573658101555, + "grad_norm": 0.5892798900604248, + "learning_rate": 5.1526839131901315e-05, + "loss": 1.8855, + "step": 8950 + }, + { + "epoch": 0.4989131040633187, + "grad_norm": 0.6024952530860901, + "learning_rate": 5.151793902397747e-05, + "loss": 1.591, + "step": 8951 + }, + { + "epoch": 0.4989688423164818, + "grad_norm": 0.545107901096344, + "learning_rate": 5.150903886791343e-05, + "loss": 1.54, + "step": 8952 + }, + { + "epoch": 0.49902458056964494, + "grad_norm": 0.5680729746818542, + "learning_rate": 5.150013866399147e-05, + "loss": 1.417, + "step": 8953 + }, + { + "epoch": 0.49908031882280807, + "grad_norm": 0.5475823879241943, + "learning_rate": 5.149123841249387e-05, + "loss": 1.5283, + "step": 8954 + }, + { + "epoch": 0.49913605707597125, + "grad_norm": 0.6003718376159668, + "learning_rate": 5.148233811370289e-05, + "loss": 1.9128, + "step": 8955 + }, + { + "epoch": 0.4991917953291344, + "grad_norm": 0.5217127203941345, + "learning_rate": 5.1473437767900766e-05, + "loss": 1.5466, + "step": 8956 + }, + { + "epoch": 0.4992475335822975, + "grad_norm": 0.5930051803588867, + "learning_rate": 5.1464537375369816e-05, + "loss": 1.7227, + "step": 8957 + }, + { + "epoch": 0.4993032718354607, + "grad_norm": 0.5506693124771118, + "learning_rate": 5.145563693639226e-05, + "loss": 1.5488, + "step": 8958 + }, + { + "epoch": 0.4993590100886238, + "grad_norm": 0.5341318845748901, + "learning_rate": 5.144673645125039e-05, + "loss": 1.6493, + "step": 8959 + }, + { + "epoch": 0.49941474834178695, + "grad_norm": 0.5735641717910767, + "learning_rate": 5.143783592022646e-05, + "loss": 1.6502, + "step": 8960 + }, + { + "epoch": 0.49947048659495014, + "grad_norm": 0.5525271892547607, + "learning_rate": 5.142893534360278e-05, + "loss": 1.389, + "step": 8961 + }, + { + "epoch": 0.49952622484811326, + "grad_norm": 0.6138321161270142, + "learning_rate": 5.1420034721661594e-05, + "loss": 1.882, + "step": 8962 + }, + { + "epoch": 0.4995819631012764, + "grad_norm": 0.5286270380020142, + "learning_rate": 5.1411134054685185e-05, + "loss": 1.6304, + "step": 8963 + }, + { + "epoch": 0.4996377013544396, + "grad_norm": 0.5324103832244873, + "learning_rate": 5.140223334295584e-05, + "loss": 1.7474, + "step": 8964 + }, + { + "epoch": 0.4996934396076027, + "grad_norm": 0.598732590675354, + "learning_rate": 5.139333258675582e-05, + "loss": 1.7623, + "step": 8965 + }, + { + "epoch": 0.49974917786076584, + "grad_norm": 0.5680933594703674, + "learning_rate": 5.138443178636742e-05, + "loss": 1.5633, + "step": 8966 + }, + { + "epoch": 0.49980491611392897, + "grad_norm": 0.5769996047019958, + "learning_rate": 5.13755309420729e-05, + "loss": 1.6215, + "step": 8967 + }, + { + "epoch": 0.49986065436709215, + "grad_norm": 0.5486459732055664, + "learning_rate": 5.1366630054154576e-05, + "loss": 1.6782, + "step": 8968 + }, + { + "epoch": 0.4999163926202553, + "grad_norm": 0.6276679635047913, + "learning_rate": 5.1357729122894706e-05, + "loss": 1.7972, + "step": 8969 + }, + { + "epoch": 0.4999721308734184, + "grad_norm": 0.5534047484397888, + "learning_rate": 5.134882814857559e-05, + "loss": 1.5217, + "step": 8970 + }, + { + "epoch": 0.5000278691265816, + "grad_norm": 0.7427502274513245, + "learning_rate": 5.1339927131479503e-05, + "loss": 1.7474, + "step": 8971 + }, + { + "epoch": 0.5000836073797447, + "grad_norm": 0.5830016136169434, + "learning_rate": 5.133102607188874e-05, + "loss": 1.7703, + "step": 8972 + }, + { + "epoch": 0.5001393456329079, + "grad_norm": 0.5821530818939209, + "learning_rate": 5.132212497008559e-05, + "loss": 1.6809, + "step": 8973 + }, + { + "epoch": 0.500195083886071, + "grad_norm": 0.5597349405288696, + "learning_rate": 5.1313223826352365e-05, + "loss": 1.6982, + "step": 8974 + }, + { + "epoch": 0.5002508221392341, + "grad_norm": 0.5627524256706238, + "learning_rate": 5.1304322640971315e-05, + "loss": 1.5646, + "step": 8975 + }, + { + "epoch": 0.5003065603923973, + "grad_norm": 0.568310558795929, + "learning_rate": 5.1295421414224754e-05, + "loss": 1.6019, + "step": 8976 + }, + { + "epoch": 0.5003622986455605, + "grad_norm": 0.5768476128578186, + "learning_rate": 5.128652014639499e-05, + "loss": 1.6455, + "step": 8977 + }, + { + "epoch": 0.5004180368987236, + "grad_norm": 0.5494751930236816, + "learning_rate": 5.1277618837764294e-05, + "loss": 1.5586, + "step": 8978 + }, + { + "epoch": 0.5004737751518867, + "grad_norm": 0.5893326997756958, + "learning_rate": 5.126871748861499e-05, + "loss": 1.8271, + "step": 8979 + }, + { + "epoch": 0.5005295134050499, + "grad_norm": 0.5742121934890747, + "learning_rate": 5.125981609922935e-05, + "loss": 1.7673, + "step": 8980 + }, + { + "epoch": 0.500585251658213, + "grad_norm": 0.5225714445114136, + "learning_rate": 5.1250914669889714e-05, + "loss": 1.5127, + "step": 8981 + }, + { + "epoch": 0.5006409899113762, + "grad_norm": 0.5902960300445557, + "learning_rate": 5.124201320087833e-05, + "loss": 1.7471, + "step": 8982 + }, + { + "epoch": 0.5006967281645394, + "grad_norm": 0.5950215458869934, + "learning_rate": 5.1233111692477555e-05, + "loss": 1.6188, + "step": 8983 + }, + { + "epoch": 0.5007524664177024, + "grad_norm": 0.5525108575820923, + "learning_rate": 5.122421014496965e-05, + "loss": 1.6802, + "step": 8984 + }, + { + "epoch": 0.5008082046708656, + "grad_norm": 0.5543337464332581, + "learning_rate": 5.1215308558636944e-05, + "loss": 1.5793, + "step": 8985 + }, + { + "epoch": 0.5008639429240288, + "grad_norm": 0.5265454053878784, + "learning_rate": 5.1206406933761716e-05, + "loss": 1.3947, + "step": 8986 + }, + { + "epoch": 0.5009196811771919, + "grad_norm": 0.6150608658790588, + "learning_rate": 5.119750527062632e-05, + "loss": 1.9244, + "step": 8987 + }, + { + "epoch": 0.5009754194303551, + "grad_norm": 0.5269333124160767, + "learning_rate": 5.1188603569513025e-05, + "loss": 1.6002, + "step": 8988 + }, + { + "epoch": 0.5010311576835182, + "grad_norm": 0.6029527187347412, + "learning_rate": 5.117970183070416e-05, + "loss": 1.8124, + "step": 8989 + }, + { + "epoch": 0.5010868959366813, + "grad_norm": 0.5682185292243958, + "learning_rate": 5.1170800054482035e-05, + "loss": 1.6561, + "step": 8990 + }, + { + "epoch": 0.5011426341898445, + "grad_norm": 0.5897371172904968, + "learning_rate": 5.116189824112896e-05, + "loss": 1.7734, + "step": 8991 + }, + { + "epoch": 0.5011983724430077, + "grad_norm": 0.5152097940444946, + "learning_rate": 5.115299639092723e-05, + "loss": 1.4226, + "step": 8992 + }, + { + "epoch": 0.5012541106961708, + "grad_norm": 0.546345591545105, + "learning_rate": 5.114409450415919e-05, + "loss": 1.4967, + "step": 8993 + }, + { + "epoch": 0.501309848949334, + "grad_norm": 0.5303710103034973, + "learning_rate": 5.113519258110715e-05, + "loss": 1.6527, + "step": 8994 + }, + { + "epoch": 0.501365587202497, + "grad_norm": 0.5513923764228821, + "learning_rate": 5.1126290622053405e-05, + "loss": 1.7632, + "step": 8995 + }, + { + "epoch": 0.5014213254556602, + "grad_norm": 0.5321218371391296, + "learning_rate": 5.1117388627280305e-05, + "loss": 1.5339, + "step": 8996 + }, + { + "epoch": 0.5014770637088234, + "grad_norm": 0.5597907900810242, + "learning_rate": 5.1108486597070125e-05, + "loss": 1.6767, + "step": 8997 + }, + { + "epoch": 0.5015328019619865, + "grad_norm": 0.5612991452217102, + "learning_rate": 5.109958453170524e-05, + "loss": 1.7141, + "step": 8998 + }, + { + "epoch": 0.5015885402151496, + "grad_norm": 0.549898087978363, + "learning_rate": 5.109068243146793e-05, + "loss": 1.393, + "step": 8999 + }, + { + "epoch": 0.5016442784683128, + "grad_norm": 0.5984362959861755, + "learning_rate": 5.1081780296640535e-05, + "loss": 1.8804, + "step": 9000 + }, + { + "epoch": 0.5017000167214759, + "grad_norm": 0.567398190498352, + "learning_rate": 5.107287812750538e-05, + "loss": 1.6947, + "step": 9001 + }, + { + "epoch": 0.5017557549746391, + "grad_norm": 0.5649966597557068, + "learning_rate": 5.106397592434478e-05, + "loss": 1.6008, + "step": 9002 + }, + { + "epoch": 0.5018114932278023, + "grad_norm": 0.5383644700050354, + "learning_rate": 5.105507368744108e-05, + "loss": 1.6802, + "step": 9003 + }, + { + "epoch": 0.5018672314809653, + "grad_norm": 0.5765425562858582, + "learning_rate": 5.1046171417076584e-05, + "loss": 1.653, + "step": 9004 + }, + { + "epoch": 0.5019229697341285, + "grad_norm": 0.5408610105514526, + "learning_rate": 5.103726911353363e-05, + "loss": 1.7098, + "step": 9005 + }, + { + "epoch": 0.5019787079872917, + "grad_norm": 0.5842016339302063, + "learning_rate": 5.1028366777094536e-05, + "loss": 1.9008, + "step": 9006 + }, + { + "epoch": 0.5020344462404548, + "grad_norm": 0.5333168506622314, + "learning_rate": 5.101946440804166e-05, + "loss": 1.4168, + "step": 9007 + }, + { + "epoch": 0.502090184493618, + "grad_norm": 0.5522457957267761, + "learning_rate": 5.101056200665731e-05, + "loss": 1.7717, + "step": 9008 + }, + { + "epoch": 0.5021459227467812, + "grad_norm": 0.5111657381057739, + "learning_rate": 5.100165957322384e-05, + "loss": 1.4358, + "step": 9009 + }, + { + "epoch": 0.5022016609999442, + "grad_norm": 0.5850957632064819, + "learning_rate": 5.099275710802355e-05, + "loss": 1.7202, + "step": 9010 + }, + { + "epoch": 0.5022573992531074, + "grad_norm": 0.5885518789291382, + "learning_rate": 5.09838546113388e-05, + "loss": 1.8804, + "step": 9011 + }, + { + "epoch": 0.5023131375062706, + "grad_norm": 0.5729745626449585, + "learning_rate": 5.097495208345191e-05, + "loss": 1.7409, + "step": 9012 + }, + { + "epoch": 0.5023688757594337, + "grad_norm": 0.5428875088691711, + "learning_rate": 5.096604952464524e-05, + "loss": 1.6353, + "step": 9013 + }, + { + "epoch": 0.5024246140125969, + "grad_norm": 0.598082423210144, + "learning_rate": 5.095714693520111e-05, + "loss": 1.8436, + "step": 9014 + }, + { + "epoch": 0.50248035226576, + "grad_norm": 0.5146722197532654, + "learning_rate": 5.094824431540184e-05, + "loss": 1.5617, + "step": 9015 + }, + { + "epoch": 0.5025360905189231, + "grad_norm": 0.5724582076072693, + "learning_rate": 5.093934166552981e-05, + "loss": 1.7339, + "step": 9016 + }, + { + "epoch": 0.5025918287720863, + "grad_norm": 0.5695306658744812, + "learning_rate": 5.0930438985867326e-05, + "loss": 1.892, + "step": 9017 + }, + { + "epoch": 0.5026475670252494, + "grad_norm": 0.5484499931335449, + "learning_rate": 5.0921536276696745e-05, + "loss": 1.6645, + "step": 9018 + }, + { + "epoch": 0.5027033052784126, + "grad_norm": 0.561751127243042, + "learning_rate": 5.09126335383004e-05, + "loss": 1.8816, + "step": 9019 + }, + { + "epoch": 0.5027590435315757, + "grad_norm": 0.5813974142074585, + "learning_rate": 5.090373077096067e-05, + "loss": 1.8134, + "step": 9020 + }, + { + "epoch": 0.5028147817847388, + "grad_norm": 0.5623780488967896, + "learning_rate": 5.089482797495984e-05, + "loss": 1.625, + "step": 9021 + }, + { + "epoch": 0.502870520037902, + "grad_norm": 0.5759438872337341, + "learning_rate": 5.0885925150580295e-05, + "loss": 1.8258, + "step": 9022 + }, + { + "epoch": 0.5029262582910652, + "grad_norm": 0.5717414617538452, + "learning_rate": 5.0877022298104356e-05, + "loss": 1.5994, + "step": 9023 + }, + { + "epoch": 0.5029819965442283, + "grad_norm": 0.5251317620277405, + "learning_rate": 5.08681194178144e-05, + "loss": 1.4209, + "step": 9024 + }, + { + "epoch": 0.5030377347973914, + "grad_norm": 0.628030002117157, + "learning_rate": 5.0859216509992743e-05, + "loss": 2.1234, + "step": 9025 + }, + { + "epoch": 0.5030934730505546, + "grad_norm": 0.6082812547683716, + "learning_rate": 5.085031357492177e-05, + "loss": 1.6014, + "step": 9026 + }, + { + "epoch": 0.5031492113037177, + "grad_norm": 0.5856479406356812, + "learning_rate": 5.0841410612883786e-05, + "loss": 1.6218, + "step": 9027 + }, + { + "epoch": 0.5032049495568809, + "grad_norm": 0.5050733089447021, + "learning_rate": 5.083250762416116e-05, + "loss": 1.4808, + "step": 9028 + }, + { + "epoch": 0.5032606878100441, + "grad_norm": 0.5920116901397705, + "learning_rate": 5.082360460903627e-05, + "loss": 1.7044, + "step": 9029 + }, + { + "epoch": 0.5033164260632071, + "grad_norm": 0.588408350944519, + "learning_rate": 5.0814701567791436e-05, + "loss": 1.923, + "step": 9030 + }, + { + "epoch": 0.5033721643163703, + "grad_norm": 0.5859766602516174, + "learning_rate": 5.0805798500709e-05, + "loss": 1.888, + "step": 9031 + }, + { + "epoch": 0.5034279025695335, + "grad_norm": 0.5343489646911621, + "learning_rate": 5.0796895408071344e-05, + "loss": 1.7227, + "step": 9032 + }, + { + "epoch": 0.5034836408226966, + "grad_norm": 0.574579656124115, + "learning_rate": 5.0787992290160827e-05, + "loss": 1.7073, + "step": 9033 + }, + { + "epoch": 0.5035393790758598, + "grad_norm": 0.5644822716712952, + "learning_rate": 5.0779089147259774e-05, + "loss": 1.6084, + "step": 9034 + }, + { + "epoch": 0.503595117329023, + "grad_norm": 0.5493994355201721, + "learning_rate": 5.077018597965056e-05, + "loss": 1.6793, + "step": 9035 + }, + { + "epoch": 0.503650855582186, + "grad_norm": 0.5413119196891785, + "learning_rate": 5.076128278761554e-05, + "loss": 1.6211, + "step": 9036 + }, + { + "epoch": 0.5037065938353492, + "grad_norm": 0.5473475456237793, + "learning_rate": 5.075237957143706e-05, + "loss": 1.5416, + "step": 9037 + }, + { + "epoch": 0.5037623320885124, + "grad_norm": 0.5547932982444763, + "learning_rate": 5.0743476331397474e-05, + "loss": 1.7137, + "step": 9038 + }, + { + "epoch": 0.5038180703416755, + "grad_norm": 0.5651285648345947, + "learning_rate": 5.073457306777919e-05, + "loss": 1.2725, + "step": 9039 + }, + { + "epoch": 0.5038738085948387, + "grad_norm": 0.559619128704071, + "learning_rate": 5.0725669780864505e-05, + "loss": 1.7186, + "step": 9040 + }, + { + "epoch": 0.5039295468480017, + "grad_norm": 0.5500231385231018, + "learning_rate": 5.0716766470935806e-05, + "loss": 1.5712, + "step": 9041 + }, + { + "epoch": 0.5039852851011649, + "grad_norm": 0.5345457792282104, + "learning_rate": 5.070786313827547e-05, + "loss": 1.4333, + "step": 9042 + }, + { + "epoch": 0.5040410233543281, + "grad_norm": 0.5673493146896362, + "learning_rate": 5.069895978316582e-05, + "loss": 1.7388, + "step": 9043 + }, + { + "epoch": 0.5040967616074912, + "grad_norm": 0.5534777641296387, + "learning_rate": 5.0690056405889255e-05, + "loss": 1.5896, + "step": 9044 + }, + { + "epoch": 0.5041524998606544, + "grad_norm": 0.542965292930603, + "learning_rate": 5.068115300672812e-05, + "loss": 1.4889, + "step": 9045 + }, + { + "epoch": 0.5042082381138175, + "grad_norm": 0.6177462339401245, + "learning_rate": 5.0672249585964796e-05, + "loss": 1.6881, + "step": 9046 + }, + { + "epoch": 0.5042639763669806, + "grad_norm": 0.581512987613678, + "learning_rate": 5.0663346143881617e-05, + "loss": 1.9196, + "step": 9047 + }, + { + "epoch": 0.5043197146201438, + "grad_norm": 0.5823097825050354, + "learning_rate": 5.065444268076097e-05, + "loss": 1.8109, + "step": 9048 + }, + { + "epoch": 0.504375452873307, + "grad_norm": 0.6185294389724731, + "learning_rate": 5.0645539196885214e-05, + "loss": 1.7364, + "step": 9049 + }, + { + "epoch": 0.5044311911264701, + "grad_norm": 0.5381544828414917, + "learning_rate": 5.0636635692536724e-05, + "loss": 1.4389, + "step": 9050 + }, + { + "epoch": 0.5044869293796332, + "grad_norm": 0.547680675983429, + "learning_rate": 5.062773216799786e-05, + "loss": 1.5368, + "step": 9051 + }, + { + "epoch": 0.5045426676327964, + "grad_norm": 0.5290063619613647, + "learning_rate": 5.0618828623550996e-05, + "loss": 1.561, + "step": 9052 + }, + { + "epoch": 0.5045984058859595, + "grad_norm": 0.6034530997276306, + "learning_rate": 5.060992505947849e-05, + "loss": 1.6605, + "step": 9053 + }, + { + "epoch": 0.5046541441391227, + "grad_norm": 0.5535921454429626, + "learning_rate": 5.0601021476062714e-05, + "loss": 1.6417, + "step": 9054 + }, + { + "epoch": 0.5047098823922859, + "grad_norm": 0.5762230157852173, + "learning_rate": 5.059211787358607e-05, + "loss": 1.8285, + "step": 9055 + }, + { + "epoch": 0.5047656206454489, + "grad_norm": 0.5755069255828857, + "learning_rate": 5.058321425233087e-05, + "loss": 1.8365, + "step": 9056 + }, + { + "epoch": 0.5048213588986121, + "grad_norm": 0.5716124773025513, + "learning_rate": 5.0574310612579515e-05, + "loss": 1.7859, + "step": 9057 + }, + { + "epoch": 0.5048770971517753, + "grad_norm": 0.5171856880187988, + "learning_rate": 5.056540695461437e-05, + "loss": 1.6426, + "step": 9058 + }, + { + "epoch": 0.5049328354049384, + "grad_norm": 0.5806797742843628, + "learning_rate": 5.0556503278717836e-05, + "loss": 1.9062, + "step": 9059 + }, + { + "epoch": 0.5049885736581016, + "grad_norm": 0.556565523147583, + "learning_rate": 5.0547599585172245e-05, + "loss": 1.7185, + "step": 9060 + }, + { + "epoch": 0.5050443119112648, + "grad_norm": 0.5945353507995605, + "learning_rate": 5.053869587426e-05, + "loss": 1.5759, + "step": 9061 + }, + { + "epoch": 0.5051000501644278, + "grad_norm": 0.581937313079834, + "learning_rate": 5.052979214626346e-05, + "loss": 1.7592, + "step": 9062 + }, + { + "epoch": 0.505155788417591, + "grad_norm": 0.5184255838394165, + "learning_rate": 5.0520888401464994e-05, + "loss": 1.4266, + "step": 9063 + }, + { + "epoch": 0.5052115266707541, + "grad_norm": 0.568466305732727, + "learning_rate": 5.051198464014698e-05, + "loss": 1.852, + "step": 9064 + }, + { + "epoch": 0.5052672649239173, + "grad_norm": 0.5698969960212708, + "learning_rate": 5.0503080862591824e-05, + "loss": 1.6573, + "step": 9065 + }, + { + "epoch": 0.5053230031770805, + "grad_norm": 0.6118015050888062, + "learning_rate": 5.049417706908185e-05, + "loss": 1.9084, + "step": 9066 + }, + { + "epoch": 0.5053787414302435, + "grad_norm": 0.5635191798210144, + "learning_rate": 5.0485273259899465e-05, + "loss": 1.6099, + "step": 9067 + }, + { + "epoch": 0.5054344796834067, + "grad_norm": 0.6044256091117859, + "learning_rate": 5.0476369435327066e-05, + "loss": 1.7669, + "step": 9068 + }, + { + "epoch": 0.5054902179365699, + "grad_norm": 0.5191871523857117, + "learning_rate": 5.046746559564698e-05, + "loss": 1.6294, + "step": 9069 + }, + { + "epoch": 0.505545956189733, + "grad_norm": 0.5460189580917358, + "learning_rate": 5.045856174114161e-05, + "loss": 1.4943, + "step": 9070 + }, + { + "epoch": 0.5056016944428962, + "grad_norm": 0.5360379219055176, + "learning_rate": 5.044965787209333e-05, + "loss": 1.4914, + "step": 9071 + }, + { + "epoch": 0.5056574326960593, + "grad_norm": 0.5588350296020508, + "learning_rate": 5.044075398878456e-05, + "loss": 1.5848, + "step": 9072 + }, + { + "epoch": 0.5057131709492224, + "grad_norm": 0.5703949928283691, + "learning_rate": 5.0431850091497614e-05, + "loss": 1.8014, + "step": 9073 + }, + { + "epoch": 0.5057689092023856, + "grad_norm": 0.5233216285705566, + "learning_rate": 5.042294618051492e-05, + "loss": 1.5506, + "step": 9074 + }, + { + "epoch": 0.5058246474555488, + "grad_norm": 0.603326141834259, + "learning_rate": 5.041404225611882e-05, + "loss": 1.7151, + "step": 9075 + }, + { + "epoch": 0.5058803857087119, + "grad_norm": 0.5280753374099731, + "learning_rate": 5.040513831859172e-05, + "loss": 1.6034, + "step": 9076 + }, + { + "epoch": 0.505936123961875, + "grad_norm": 0.5462760925292969, + "learning_rate": 5.0396234368215986e-05, + "loss": 1.7025, + "step": 9077 + }, + { + "epoch": 0.5059918622150382, + "grad_norm": 0.5069268345832825, + "learning_rate": 5.0387330405274027e-05, + "loss": 1.6266, + "step": 9078 + }, + { + "epoch": 0.5060476004682013, + "grad_norm": 0.619596004486084, + "learning_rate": 5.0378426430048185e-05, + "loss": 1.9665, + "step": 9079 + }, + { + "epoch": 0.5061033387213645, + "grad_norm": 0.6080803275108337, + "learning_rate": 5.036952244282087e-05, + "loss": 1.7505, + "step": 9080 + }, + { + "epoch": 0.5061590769745277, + "grad_norm": 0.5581051111221313, + "learning_rate": 5.036061844387447e-05, + "loss": 1.3145, + "step": 9081 + }, + { + "epoch": 0.5062148152276907, + "grad_norm": 0.6103323698043823, + "learning_rate": 5.035171443349135e-05, + "loss": 1.8727, + "step": 9082 + }, + { + "epoch": 0.5062705534808539, + "grad_norm": 0.5805239081382751, + "learning_rate": 5.034281041195389e-05, + "loss": 1.8522, + "step": 9083 + }, + { + "epoch": 0.5063262917340171, + "grad_norm": 0.5124911665916443, + "learning_rate": 5.0333906379544485e-05, + "loss": 1.4206, + "step": 9084 + }, + { + "epoch": 0.5063820299871802, + "grad_norm": 0.5628135204315186, + "learning_rate": 5.0325002336545525e-05, + "loss": 1.6741, + "step": 9085 + }, + { + "epoch": 0.5064377682403434, + "grad_norm": 0.6049720644950867, + "learning_rate": 5.031609828323938e-05, + "loss": 1.6622, + "step": 9086 + }, + { + "epoch": 0.5064935064935064, + "grad_norm": 0.5559591054916382, + "learning_rate": 5.030719421990845e-05, + "loss": 1.6901, + "step": 9087 + }, + { + "epoch": 0.5065492447466696, + "grad_norm": 0.5482590198516846, + "learning_rate": 5.029829014683509e-05, + "loss": 1.5533, + "step": 9088 + }, + { + "epoch": 0.5066049829998328, + "grad_norm": 0.617445170879364, + "learning_rate": 5.0289386064301715e-05, + "loss": 2.0952, + "step": 9089 + }, + { + "epoch": 0.5066607212529959, + "grad_norm": 0.5329674482345581, + "learning_rate": 5.0280481972590696e-05, + "loss": 1.5283, + "step": 9090 + }, + { + "epoch": 0.5067164595061591, + "grad_norm": 0.5704628825187683, + "learning_rate": 5.027157787198443e-05, + "loss": 1.5935, + "step": 9091 + }, + { + "epoch": 0.5067721977593223, + "grad_norm": 0.5466018319129944, + "learning_rate": 5.0262673762765314e-05, + "loss": 1.6714, + "step": 9092 + }, + { + "epoch": 0.5068279360124853, + "grad_norm": 0.581349790096283, + "learning_rate": 5.0253769645215684e-05, + "loss": 1.6966, + "step": 9093 + }, + { + "epoch": 0.5068836742656485, + "grad_norm": 0.5872965455055237, + "learning_rate": 5.024486551961799e-05, + "loss": 1.8099, + "step": 9094 + }, + { + "epoch": 0.5069394125188117, + "grad_norm": 0.5728545188903809, + "learning_rate": 5.0235961386254584e-05, + "loss": 1.8034, + "step": 9095 + }, + { + "epoch": 0.5069951507719748, + "grad_norm": 0.6576269268989563, + "learning_rate": 5.022705724540785e-05, + "loss": 1.761, + "step": 9096 + }, + { + "epoch": 0.507050889025138, + "grad_norm": 0.49354177713394165, + "learning_rate": 5.0218153097360174e-05, + "loss": 1.5518, + "step": 9097 + }, + { + "epoch": 0.5071066272783011, + "grad_norm": 0.5540168881416321, + "learning_rate": 5.0209248942393975e-05, + "loss": 1.6151, + "step": 9098 + }, + { + "epoch": 0.5071623655314642, + "grad_norm": 0.5904643535614014, + "learning_rate": 5.020034478079161e-05, + "loss": 1.6079, + "step": 9099 + }, + { + "epoch": 0.5072181037846274, + "grad_norm": 0.52375328540802, + "learning_rate": 5.0191440612835484e-05, + "loss": 1.4861, + "step": 9100 + }, + { + "epoch": 0.5072738420377906, + "grad_norm": 0.5494303703308105, + "learning_rate": 5.018253643880797e-05, + "loss": 1.6863, + "step": 9101 + }, + { + "epoch": 0.5073295802909537, + "grad_norm": 0.5974358320236206, + "learning_rate": 5.017363225899147e-05, + "loss": 1.5901, + "step": 9102 + }, + { + "epoch": 0.5073853185441168, + "grad_norm": 0.5655843615531921, + "learning_rate": 5.0164728073668354e-05, + "loss": 1.6177, + "step": 9103 + }, + { + "epoch": 0.50744105679728, + "grad_norm": 0.5226239562034607, + "learning_rate": 5.0155823883121025e-05, + "loss": 1.5947, + "step": 9104 + }, + { + "epoch": 0.5074967950504431, + "grad_norm": 0.5766085982322693, + "learning_rate": 5.014691968763189e-05, + "loss": 1.6997, + "step": 9105 + }, + { + "epoch": 0.5075525333036063, + "grad_norm": 0.5901437997817993, + "learning_rate": 5.0138015487483305e-05, + "loss": 1.7778, + "step": 9106 + }, + { + "epoch": 0.5076082715567695, + "grad_norm": 0.5961461663246155, + "learning_rate": 5.012911128295768e-05, + "loss": 1.6958, + "step": 9107 + }, + { + "epoch": 0.5076640098099325, + "grad_norm": 0.5779803991317749, + "learning_rate": 5.012020707433739e-05, + "loss": 1.7133, + "step": 9108 + }, + { + "epoch": 0.5077197480630957, + "grad_norm": 0.5328028202056885, + "learning_rate": 5.011130286190483e-05, + "loss": 1.3029, + "step": 9109 + }, + { + "epoch": 0.5077754863162588, + "grad_norm": 0.5509020686149597, + "learning_rate": 5.0102398645942404e-05, + "loss": 1.6388, + "step": 9110 + }, + { + "epoch": 0.507831224569422, + "grad_norm": 0.5838056802749634, + "learning_rate": 5.009349442673249e-05, + "loss": 1.6256, + "step": 9111 + }, + { + "epoch": 0.5078869628225852, + "grad_norm": 0.560120701789856, + "learning_rate": 5.008459020455747e-05, + "loss": 1.7203, + "step": 9112 + }, + { + "epoch": 0.5079427010757482, + "grad_norm": 0.5297266840934753, + "learning_rate": 5.007568597969975e-05, + "loss": 1.6371, + "step": 9113 + }, + { + "epoch": 0.5079984393289114, + "grad_norm": 0.5594682097434998, + "learning_rate": 5.00667817524417e-05, + "loss": 1.7731, + "step": 9114 + }, + { + "epoch": 0.5080541775820746, + "grad_norm": 0.5355550050735474, + "learning_rate": 5.005787752306573e-05, + "loss": 1.7304, + "step": 9115 + }, + { + "epoch": 0.5081099158352377, + "grad_norm": 0.5299372673034668, + "learning_rate": 5.0048973291854215e-05, + "loss": 1.6358, + "step": 9116 + }, + { + "epoch": 0.5081656540884009, + "grad_norm": 0.5633680820465088, + "learning_rate": 5.004006905908956e-05, + "loss": 1.6261, + "step": 9117 + }, + { + "epoch": 0.508221392341564, + "grad_norm": 0.621525764465332, + "learning_rate": 5.0031164825054154e-05, + "loss": 1.7944, + "step": 9118 + }, + { + "epoch": 0.5082771305947271, + "grad_norm": 0.5595192313194275, + "learning_rate": 5.0022260590030365e-05, + "loss": 1.6483, + "step": 9119 + }, + { + "epoch": 0.5083328688478903, + "grad_norm": 0.6154051423072815, + "learning_rate": 5.0013356354300625e-05, + "loss": 1.7028, + "step": 9120 + }, + { + "epoch": 0.5083886071010535, + "grad_norm": 0.5414613485336304, + "learning_rate": 5.000445211814727e-05, + "loss": 1.7512, + "step": 9121 + }, + { + "epoch": 0.5084443453542166, + "grad_norm": 0.5534652471542358, + "learning_rate": 4.9995547881852745e-05, + "loss": 1.6766, + "step": 9122 + }, + { + "epoch": 0.5085000836073797, + "grad_norm": 0.5453454256057739, + "learning_rate": 4.9986643645699387e-05, + "loss": 1.3173, + "step": 9123 + }, + { + "epoch": 0.5085558218605429, + "grad_norm": 0.6073355674743652, + "learning_rate": 4.997773940996964e-05, + "loss": 1.7782, + "step": 9124 + }, + { + "epoch": 0.508611560113706, + "grad_norm": 0.5917234420776367, + "learning_rate": 4.9968835174945864e-05, + "loss": 1.566, + "step": 9125 + }, + { + "epoch": 0.5086672983668692, + "grad_norm": 0.5518240928649902, + "learning_rate": 4.995993094091044e-05, + "loss": 1.61, + "step": 9126 + }, + { + "epoch": 0.5087230366200324, + "grad_norm": 0.5641380548477173, + "learning_rate": 4.995102670814579e-05, + "loss": 1.3672, + "step": 9127 + }, + { + "epoch": 0.5087787748731954, + "grad_norm": 0.5821805596351624, + "learning_rate": 4.9942122476934286e-05, + "loss": 1.8647, + "step": 9128 + }, + { + "epoch": 0.5088345131263586, + "grad_norm": 0.536016047000885, + "learning_rate": 4.9933218247558316e-05, + "loss": 1.4283, + "step": 9129 + }, + { + "epoch": 0.5088902513795218, + "grad_norm": 0.5962494015693665, + "learning_rate": 4.992431402030026e-05, + "loss": 1.7816, + "step": 9130 + }, + { + "epoch": 0.5089459896326849, + "grad_norm": 0.5421521067619324, + "learning_rate": 4.9915409795442553e-05, + "loss": 1.5547, + "step": 9131 + }, + { + "epoch": 0.5090017278858481, + "grad_norm": 0.5603907108306885, + "learning_rate": 4.990650557326752e-05, + "loss": 1.6848, + "step": 9132 + }, + { + "epoch": 0.5090574661390111, + "grad_norm": 0.5411096215248108, + "learning_rate": 4.98976013540576e-05, + "loss": 1.5241, + "step": 9133 + }, + { + "epoch": 0.5091132043921743, + "grad_norm": 0.5356809496879578, + "learning_rate": 4.988869713809518e-05, + "loss": 1.3605, + "step": 9134 + }, + { + "epoch": 0.5091689426453375, + "grad_norm": 0.5351254940032959, + "learning_rate": 4.9879792925662624e-05, + "loss": 1.663, + "step": 9135 + }, + { + "epoch": 0.5092246808985006, + "grad_norm": 0.5317051410675049, + "learning_rate": 4.987088871704234e-05, + "loss": 1.7112, + "step": 9136 + }, + { + "epoch": 0.5092804191516638, + "grad_norm": 0.5253128409385681, + "learning_rate": 4.9861984512516706e-05, + "loss": 1.5613, + "step": 9137 + }, + { + "epoch": 0.509336157404827, + "grad_norm": 0.5916141271591187, + "learning_rate": 4.985308031236811e-05, + "loss": 1.7832, + "step": 9138 + }, + { + "epoch": 0.50939189565799, + "grad_norm": 0.5364113450050354, + "learning_rate": 4.984417611687899e-05, + "loss": 1.6785, + "step": 9139 + }, + { + "epoch": 0.5094476339111532, + "grad_norm": 0.5543467402458191, + "learning_rate": 4.983527192633165e-05, + "loss": 1.6664, + "step": 9140 + }, + { + "epoch": 0.5095033721643164, + "grad_norm": 0.5683530569076538, + "learning_rate": 4.982636774100855e-05, + "loss": 1.5922, + "step": 9141 + }, + { + "epoch": 0.5095591104174795, + "grad_norm": 0.5523553490638733, + "learning_rate": 4.981746356119204e-05, + "loss": 1.51, + "step": 9142 + }, + { + "epoch": 0.5096148486706427, + "grad_norm": 0.5828970074653625, + "learning_rate": 4.980855938716454e-05, + "loss": 1.661, + "step": 9143 + }, + { + "epoch": 0.5096705869238058, + "grad_norm": 0.556447446346283, + "learning_rate": 4.97996552192084e-05, + "loss": 1.5701, + "step": 9144 + }, + { + "epoch": 0.5097263251769689, + "grad_norm": 0.5221887826919556, + "learning_rate": 4.979075105760603e-05, + "loss": 1.389, + "step": 9145 + }, + { + "epoch": 0.5097820634301321, + "grad_norm": 0.528141438961029, + "learning_rate": 4.978184690263983e-05, + "loss": 1.585, + "step": 9146 + }, + { + "epoch": 0.5098378016832953, + "grad_norm": 0.5802522897720337, + "learning_rate": 4.9772942754592156e-05, + "loss": 1.7289, + "step": 9147 + }, + { + "epoch": 0.5098935399364584, + "grad_norm": 0.6549295783042908, + "learning_rate": 4.976403861374545e-05, + "loss": 1.6774, + "step": 9148 + }, + { + "epoch": 0.5099492781896215, + "grad_norm": 0.5203224420547485, + "learning_rate": 4.975513448038202e-05, + "loss": 1.4913, + "step": 9149 + }, + { + "epoch": 0.5100050164427847, + "grad_norm": 0.5493060946464539, + "learning_rate": 4.974623035478432e-05, + "loss": 1.8086, + "step": 9150 + }, + { + "epoch": 0.5100607546959478, + "grad_norm": 0.5371272563934326, + "learning_rate": 4.9737326237234704e-05, + "loss": 1.48, + "step": 9151 + }, + { + "epoch": 0.510116492949111, + "grad_norm": 0.5722330212593079, + "learning_rate": 4.972842212801557e-05, + "loss": 1.6754, + "step": 9152 + }, + { + "epoch": 0.5101722312022742, + "grad_norm": 0.5680810809135437, + "learning_rate": 4.9719518027409315e-05, + "loss": 1.6418, + "step": 9153 + }, + { + "epoch": 0.5102279694554372, + "grad_norm": 0.5572932362556458, + "learning_rate": 4.9710613935698296e-05, + "loss": 1.5825, + "step": 9154 + }, + { + "epoch": 0.5102837077086004, + "grad_norm": 0.56486976146698, + "learning_rate": 4.970170985316493e-05, + "loss": 1.7214, + "step": 9155 + }, + { + "epoch": 0.5103394459617635, + "grad_norm": 0.5949878692626953, + "learning_rate": 4.969280578009157e-05, + "loss": 1.6079, + "step": 9156 + }, + { + "epoch": 0.5103951842149267, + "grad_norm": 0.5963469743728638, + "learning_rate": 4.9683901716760645e-05, + "loss": 1.7796, + "step": 9157 + }, + { + "epoch": 0.5104509224680899, + "grad_norm": 0.518810510635376, + "learning_rate": 4.967499766345449e-05, + "loss": 1.5331, + "step": 9158 + }, + { + "epoch": 0.510506660721253, + "grad_norm": 0.5369781255722046, + "learning_rate": 4.966609362045552e-05, + "loss": 1.5991, + "step": 9159 + }, + { + "epoch": 0.5105623989744161, + "grad_norm": 0.603927731513977, + "learning_rate": 4.9657189588046125e-05, + "loss": 1.6963, + "step": 9160 + }, + { + "epoch": 0.5106181372275793, + "grad_norm": 0.512532651424408, + "learning_rate": 4.964828556650867e-05, + "loss": 1.4591, + "step": 9161 + }, + { + "epoch": 0.5106738754807424, + "grad_norm": 0.5606699585914612, + "learning_rate": 4.9639381556125545e-05, + "loss": 1.7269, + "step": 9162 + }, + { + "epoch": 0.5107296137339056, + "grad_norm": 0.5832485556602478, + "learning_rate": 4.963047755717914e-05, + "loss": 1.7202, + "step": 9163 + }, + { + "epoch": 0.5107853519870688, + "grad_norm": 0.549618661403656, + "learning_rate": 4.962157356995181e-05, + "loss": 1.543, + "step": 9164 + }, + { + "epoch": 0.5108410902402318, + "grad_norm": 0.6027174592018127, + "learning_rate": 4.9612669594725985e-05, + "loss": 1.506, + "step": 9165 + }, + { + "epoch": 0.510896828493395, + "grad_norm": 0.5265709161758423, + "learning_rate": 4.960376563178402e-05, + "loss": 1.4054, + "step": 9166 + }, + { + "epoch": 0.5109525667465582, + "grad_norm": 0.6092290282249451, + "learning_rate": 4.95948616814083e-05, + "loss": 1.8014, + "step": 9167 + }, + { + "epoch": 0.5110083049997213, + "grad_norm": 0.581297755241394, + "learning_rate": 4.958595774388119e-05, + "loss": 1.6825, + "step": 9168 + }, + { + "epoch": 0.5110640432528845, + "grad_norm": 0.5989497303962708, + "learning_rate": 4.9577053819485106e-05, + "loss": 1.8822, + "step": 9169 + }, + { + "epoch": 0.5111197815060476, + "grad_norm": 0.5412517786026001, + "learning_rate": 4.95681499085024e-05, + "loss": 1.5337, + "step": 9170 + }, + { + "epoch": 0.5111755197592107, + "grad_norm": 0.5634650588035583, + "learning_rate": 4.9559246011215445e-05, + "loss": 1.6926, + "step": 9171 + }, + { + "epoch": 0.5112312580123739, + "grad_norm": 0.56587815284729, + "learning_rate": 4.955034212790667e-05, + "loss": 1.8106, + "step": 9172 + }, + { + "epoch": 0.5112869962655371, + "grad_norm": 0.5138219594955444, + "learning_rate": 4.954143825885839e-05, + "loss": 1.5418, + "step": 9173 + }, + { + "epoch": 0.5113427345187002, + "grad_norm": 0.5837535262107849, + "learning_rate": 4.9532534404353045e-05, + "loss": 1.7995, + "step": 9174 + }, + { + "epoch": 0.5113984727718633, + "grad_norm": 0.5723191499710083, + "learning_rate": 4.952363056467295e-05, + "loss": 1.7018, + "step": 9175 + }, + { + "epoch": 0.5114542110250265, + "grad_norm": 0.5086800456047058, + "learning_rate": 4.951472674010054e-05, + "loss": 1.4375, + "step": 9176 + }, + { + "epoch": 0.5115099492781896, + "grad_norm": 0.5769858360290527, + "learning_rate": 4.9505822930918154e-05, + "loss": 1.856, + "step": 9177 + }, + { + "epoch": 0.5115656875313528, + "grad_norm": 0.5059775114059448, + "learning_rate": 4.9496919137408194e-05, + "loss": 1.5449, + "step": 9178 + }, + { + "epoch": 0.5116214257845159, + "grad_norm": 0.5650221705436707, + "learning_rate": 4.948801535985302e-05, + "loss": 1.5744, + "step": 9179 + }, + { + "epoch": 0.511677164037679, + "grad_norm": 0.6061702966690063, + "learning_rate": 4.947911159853502e-05, + "loss": 1.5903, + "step": 9180 + }, + { + "epoch": 0.5117329022908422, + "grad_norm": 0.6307567358016968, + "learning_rate": 4.947020785373657e-05, + "loss": 1.6904, + "step": 9181 + }, + { + "epoch": 0.5117886405440053, + "grad_norm": 0.5376378297805786, + "learning_rate": 4.9461304125740006e-05, + "loss": 1.6402, + "step": 9182 + }, + { + "epoch": 0.5118443787971685, + "grad_norm": 0.5407423973083496, + "learning_rate": 4.945240041482777e-05, + "loss": 1.6268, + "step": 9183 + }, + { + "epoch": 0.5119001170503317, + "grad_norm": 0.575613260269165, + "learning_rate": 4.9443496721282176e-05, + "loss": 1.7676, + "step": 9184 + }, + { + "epoch": 0.5119558553034947, + "grad_norm": 0.5587126612663269, + "learning_rate": 4.943459304538562e-05, + "loss": 1.787, + "step": 9185 + }, + { + "epoch": 0.5120115935566579, + "grad_norm": 0.5674868226051331, + "learning_rate": 4.94256893874205e-05, + "loss": 1.4734, + "step": 9186 + }, + { + "epoch": 0.5120673318098211, + "grad_norm": 0.5866878032684326, + "learning_rate": 4.941678574766915e-05, + "loss": 1.6512, + "step": 9187 + }, + { + "epoch": 0.5121230700629842, + "grad_norm": 0.5577338337898254, + "learning_rate": 4.9407882126413964e-05, + "loss": 1.6187, + "step": 9188 + }, + { + "epoch": 0.5121788083161474, + "grad_norm": 0.551834225654602, + "learning_rate": 4.939897852393729e-05, + "loss": 1.7205, + "step": 9189 + }, + { + "epoch": 0.5122345465693106, + "grad_norm": 0.5380664467811584, + "learning_rate": 4.939007494052153e-05, + "loss": 1.7667, + "step": 9190 + }, + { + "epoch": 0.5122902848224736, + "grad_norm": 0.5532002449035645, + "learning_rate": 4.938117137644901e-05, + "loss": 1.6104, + "step": 9191 + }, + { + "epoch": 0.5123460230756368, + "grad_norm": 0.532942533493042, + "learning_rate": 4.937226783200214e-05, + "loss": 1.5063, + "step": 9192 + }, + { + "epoch": 0.5124017613288, + "grad_norm": 0.6073448657989502, + "learning_rate": 4.936336430746328e-05, + "loss": 1.8014, + "step": 9193 + }, + { + "epoch": 0.5124574995819631, + "grad_norm": 0.6055412292480469, + "learning_rate": 4.935446080311479e-05, + "loss": 2.0275, + "step": 9194 + }, + { + "epoch": 0.5125132378351263, + "grad_norm": 0.5389105081558228, + "learning_rate": 4.934555731923905e-05, + "loss": 1.4672, + "step": 9195 + }, + { + "epoch": 0.5125689760882894, + "grad_norm": 0.5867198705673218, + "learning_rate": 4.9336653856118395e-05, + "loss": 1.9117, + "step": 9196 + }, + { + "epoch": 0.5126247143414525, + "grad_norm": 0.5566348433494568, + "learning_rate": 4.932775041403521e-05, + "loss": 1.7259, + "step": 9197 + }, + { + "epoch": 0.5126804525946157, + "grad_norm": 0.5522982478141785, + "learning_rate": 4.93188469932719e-05, + "loss": 1.6182, + "step": 9198 + }, + { + "epoch": 0.5127361908477789, + "grad_norm": 0.5474398136138916, + "learning_rate": 4.9309943594110743e-05, + "loss": 1.6146, + "step": 9199 + }, + { + "epoch": 0.512791929100942, + "grad_norm": 0.5723056793212891, + "learning_rate": 4.93010402168342e-05, + "loss": 1.5467, + "step": 9200 + }, + { + "epoch": 0.5128476673541051, + "grad_norm": 0.5831982493400574, + "learning_rate": 4.9292136861724544e-05, + "loss": 1.7189, + "step": 9201 + }, + { + "epoch": 0.5129034056072682, + "grad_norm": 0.5088267922401428, + "learning_rate": 4.9283233529064205e-05, + "loss": 1.6331, + "step": 9202 + }, + { + "epoch": 0.5129591438604314, + "grad_norm": 0.5105864405632019, + "learning_rate": 4.9274330219135506e-05, + "loss": 1.3119, + "step": 9203 + }, + { + "epoch": 0.5130148821135946, + "grad_norm": 0.5990265011787415, + "learning_rate": 4.926542693222083e-05, + "loss": 1.7628, + "step": 9204 + }, + { + "epoch": 0.5130706203667577, + "grad_norm": 0.5516785383224487, + "learning_rate": 4.925652366860253e-05, + "loss": 1.8385, + "step": 9205 + }, + { + "epoch": 0.5131263586199208, + "grad_norm": 0.5530927777290344, + "learning_rate": 4.9247620428562954e-05, + "loss": 1.5642, + "step": 9206 + }, + { + "epoch": 0.513182096873084, + "grad_norm": 0.553615152835846, + "learning_rate": 4.9238717212384485e-05, + "loss": 1.5955, + "step": 9207 + }, + { + "epoch": 0.5132378351262471, + "grad_norm": 0.553424060344696, + "learning_rate": 4.922981402034945e-05, + "loss": 1.4373, + "step": 9208 + }, + { + "epoch": 0.5132935733794103, + "grad_norm": 0.52947598695755, + "learning_rate": 4.922091085274025e-05, + "loss": 1.5492, + "step": 9209 + }, + { + "epoch": 0.5133493116325735, + "grad_norm": 0.5600340366363525, + "learning_rate": 4.9212007709839185e-05, + "loss": 1.7274, + "step": 9210 + }, + { + "epoch": 0.5134050498857365, + "grad_norm": 0.525035560131073, + "learning_rate": 4.9203104591928654e-05, + "loss": 1.6216, + "step": 9211 + }, + { + "epoch": 0.5134607881388997, + "grad_norm": 0.5979744791984558, + "learning_rate": 4.919420149929101e-05, + "loss": 1.7127, + "step": 9212 + }, + { + "epoch": 0.5135165263920629, + "grad_norm": 0.5735787153244019, + "learning_rate": 4.918529843220858e-05, + "loss": 1.8044, + "step": 9213 + }, + { + "epoch": 0.513572264645226, + "grad_norm": 0.544146716594696, + "learning_rate": 4.917639539096375e-05, + "loss": 1.7176, + "step": 9214 + }, + { + "epoch": 0.5136280028983892, + "grad_norm": 0.6068428158760071, + "learning_rate": 4.9167492375838844e-05, + "loss": 1.8507, + "step": 9215 + }, + { + "epoch": 0.5136837411515524, + "grad_norm": 0.5296306014060974, + "learning_rate": 4.915858938711624e-05, + "loss": 1.4948, + "step": 9216 + }, + { + "epoch": 0.5137394794047154, + "grad_norm": 0.5465298891067505, + "learning_rate": 4.914968642507824e-05, + "loss": 1.7211, + "step": 9217 + }, + { + "epoch": 0.5137952176578786, + "grad_norm": 0.5519313812255859, + "learning_rate": 4.9140783490007255e-05, + "loss": 1.6642, + "step": 9218 + }, + { + "epoch": 0.5138509559110418, + "grad_norm": 0.5677876472473145, + "learning_rate": 4.9131880582185614e-05, + "loss": 1.7359, + "step": 9219 + }, + { + "epoch": 0.5139066941642049, + "grad_norm": 0.5681816339492798, + "learning_rate": 4.912297770189565e-05, + "loss": 1.6898, + "step": 9220 + }, + { + "epoch": 0.513962432417368, + "grad_norm": 0.5291382670402527, + "learning_rate": 4.911407484941973e-05, + "loss": 1.6172, + "step": 9221 + }, + { + "epoch": 0.5140181706705312, + "grad_norm": 0.5665237307548523, + "learning_rate": 4.910517202504017e-05, + "loss": 1.6677, + "step": 9222 + }, + { + "epoch": 0.5140739089236943, + "grad_norm": 0.5834330320358276, + "learning_rate": 4.909626922903934e-05, + "loss": 1.8476, + "step": 9223 + }, + { + "epoch": 0.5141296471768575, + "grad_norm": 0.5709316730499268, + "learning_rate": 4.90873664616996e-05, + "loss": 1.9254, + "step": 9224 + }, + { + "epoch": 0.5141853854300206, + "grad_norm": 0.5521526336669922, + "learning_rate": 4.907846372330325e-05, + "loss": 2.0271, + "step": 9225 + }, + { + "epoch": 0.5142411236831838, + "grad_norm": 0.6235350370407104, + "learning_rate": 4.906956101413269e-05, + "loss": 1.8016, + "step": 9226 + }, + { + "epoch": 0.5142968619363469, + "grad_norm": 0.5495184659957886, + "learning_rate": 4.90606583344702e-05, + "loss": 1.7529, + "step": 9227 + }, + { + "epoch": 0.51435260018951, + "grad_norm": 0.5534826517105103, + "learning_rate": 4.905175568459817e-05, + "loss": 1.7477, + "step": 9228 + }, + { + "epoch": 0.5144083384426732, + "grad_norm": 0.5249108076095581, + "learning_rate": 4.904285306479891e-05, + "loss": 1.627, + "step": 9229 + }, + { + "epoch": 0.5144640766958364, + "grad_norm": 0.49146464467048645, + "learning_rate": 4.903395047535477e-05, + "loss": 1.459, + "step": 9230 + }, + { + "epoch": 0.5145198149489995, + "grad_norm": 0.5858702659606934, + "learning_rate": 4.90250479165481e-05, + "loss": 1.6794, + "step": 9231 + }, + { + "epoch": 0.5145755532021626, + "grad_norm": 0.5300642848014832, + "learning_rate": 4.901614538866121e-05, + "loss": 1.5589, + "step": 9232 + }, + { + "epoch": 0.5146312914553258, + "grad_norm": 0.6229625344276428, + "learning_rate": 4.900724289197647e-05, + "loss": 1.9199, + "step": 9233 + }, + { + "epoch": 0.5146870297084889, + "grad_norm": 0.565897524356842, + "learning_rate": 4.899834042677617e-05, + "loss": 1.8075, + "step": 9234 + }, + { + "epoch": 0.5147427679616521, + "grad_norm": 0.5347508192062378, + "learning_rate": 4.898943799334271e-05, + "loss": 1.4777, + "step": 9235 + }, + { + "epoch": 0.5147985062148153, + "grad_norm": 0.6027230024337769, + "learning_rate": 4.8980535591958346e-05, + "loss": 1.8581, + "step": 9236 + }, + { + "epoch": 0.5148542444679783, + "grad_norm": 0.603020429611206, + "learning_rate": 4.897163322290546e-05, + "loss": 1.9628, + "step": 9237 + }, + { + "epoch": 0.5149099827211415, + "grad_norm": 0.5772542357444763, + "learning_rate": 4.896273088646639e-05, + "loss": 1.5789, + "step": 9238 + }, + { + "epoch": 0.5149657209743047, + "grad_norm": 0.537726879119873, + "learning_rate": 4.8953828582923435e-05, + "loss": 1.6334, + "step": 9239 + }, + { + "epoch": 0.5150214592274678, + "grad_norm": 0.5418381094932556, + "learning_rate": 4.894492631255895e-05, + "loss": 1.7236, + "step": 9240 + }, + { + "epoch": 0.515077197480631, + "grad_norm": 0.5719316601753235, + "learning_rate": 4.8936024075655234e-05, + "loss": 1.8026, + "step": 9241 + }, + { + "epoch": 0.5151329357337942, + "grad_norm": 0.5505056381225586, + "learning_rate": 4.892712187249465e-05, + "loss": 1.7085, + "step": 9242 + }, + { + "epoch": 0.5151886739869572, + "grad_norm": 0.5943016409873962, + "learning_rate": 4.891821970335948e-05, + "loss": 1.8545, + "step": 9243 + }, + { + "epoch": 0.5152444122401204, + "grad_norm": 0.5240996479988098, + "learning_rate": 4.8909317568532074e-05, + "loss": 1.5689, + "step": 9244 + }, + { + "epoch": 0.5153001504932836, + "grad_norm": 0.5402621030807495, + "learning_rate": 4.890041546829478e-05, + "loss": 1.6177, + "step": 9245 + }, + { + "epoch": 0.5153558887464467, + "grad_norm": 0.5427978038787842, + "learning_rate": 4.889151340292988e-05, + "loss": 1.6859, + "step": 9246 + }, + { + "epoch": 0.5154116269996099, + "grad_norm": 0.5826436281204224, + "learning_rate": 4.888261137271972e-05, + "loss": 1.7225, + "step": 9247 + }, + { + "epoch": 0.5154673652527729, + "grad_norm": 0.5483592748641968, + "learning_rate": 4.8873709377946607e-05, + "loss": 1.8317, + "step": 9248 + }, + { + "epoch": 0.5155231035059361, + "grad_norm": 0.5138580799102783, + "learning_rate": 4.886480741889285e-05, + "loss": 1.3468, + "step": 9249 + }, + { + "epoch": 0.5155788417590993, + "grad_norm": 0.5693102478981018, + "learning_rate": 4.8855905495840824e-05, + "loss": 1.8712, + "step": 9250 + }, + { + "epoch": 0.5156345800122624, + "grad_norm": 0.5839586853981018, + "learning_rate": 4.8847003609072766e-05, + "loss": 1.7937, + "step": 9251 + }, + { + "epoch": 0.5156903182654256, + "grad_norm": 0.5809890627861023, + "learning_rate": 4.883810175887106e-05, + "loss": 1.6511, + "step": 9252 + }, + { + "epoch": 0.5157460565185887, + "grad_norm": 0.5595370531082153, + "learning_rate": 4.882919994551797e-05, + "loss": 1.6945, + "step": 9253 + }, + { + "epoch": 0.5158017947717518, + "grad_norm": 0.5431410074234009, + "learning_rate": 4.882029816929585e-05, + "loss": 1.555, + "step": 9254 + }, + { + "epoch": 0.515857533024915, + "grad_norm": 0.516463577747345, + "learning_rate": 4.881139643048698e-05, + "loss": 1.5392, + "step": 9255 + }, + { + "epoch": 0.5159132712780782, + "grad_norm": 0.5569630265235901, + "learning_rate": 4.8802494729373684e-05, + "loss": 1.5023, + "step": 9256 + }, + { + "epoch": 0.5159690095312413, + "grad_norm": 0.6542758941650391, + "learning_rate": 4.879359306623829e-05, + "loss": 1.7664, + "step": 9257 + }, + { + "epoch": 0.5160247477844044, + "grad_norm": 0.5755527019500732, + "learning_rate": 4.878469144136306e-05, + "loss": 1.7523, + "step": 9258 + }, + { + "epoch": 0.5160804860375676, + "grad_norm": 0.603937029838562, + "learning_rate": 4.8775789855030366e-05, + "loss": 1.7377, + "step": 9259 + }, + { + "epoch": 0.5161362242907307, + "grad_norm": 0.6183059215545654, + "learning_rate": 4.876688830752245e-05, + "loss": 1.9714, + "step": 9260 + }, + { + "epoch": 0.5161919625438939, + "grad_norm": 0.5435531139373779, + "learning_rate": 4.8757986799121685e-05, + "loss": 1.5455, + "step": 9261 + }, + { + "epoch": 0.5162477007970571, + "grad_norm": 0.5262885689735413, + "learning_rate": 4.87490853301103e-05, + "loss": 1.547, + "step": 9262 + }, + { + "epoch": 0.5163034390502201, + "grad_norm": 0.5731160640716553, + "learning_rate": 4.874018390077065e-05, + "loss": 1.7112, + "step": 9263 + }, + { + "epoch": 0.5163591773033833, + "grad_norm": 0.5427829623222351, + "learning_rate": 4.8731282511385025e-05, + "loss": 1.5646, + "step": 9264 + }, + { + "epoch": 0.5164149155565465, + "grad_norm": 0.5715686678886414, + "learning_rate": 4.872238116223571e-05, + "loss": 1.7205, + "step": 9265 + }, + { + "epoch": 0.5164706538097096, + "grad_norm": 0.5412135124206543, + "learning_rate": 4.871347985360503e-05, + "loss": 1.641, + "step": 9266 + }, + { + "epoch": 0.5165263920628728, + "grad_norm": 0.5642713308334351, + "learning_rate": 4.870457858577526e-05, + "loss": 1.7817, + "step": 9267 + }, + { + "epoch": 0.516582130316036, + "grad_norm": 0.6018970608711243, + "learning_rate": 4.869567735902871e-05, + "loss": 2.0283, + "step": 9268 + }, + { + "epoch": 0.516637868569199, + "grad_norm": 0.5858074426651001, + "learning_rate": 4.8686776173647653e-05, + "loss": 1.7466, + "step": 9269 + }, + { + "epoch": 0.5166936068223622, + "grad_norm": 0.5206944942474365, + "learning_rate": 4.867787502991441e-05, + "loss": 1.4493, + "step": 9270 + }, + { + "epoch": 0.5167493450755253, + "grad_norm": 0.5470089912414551, + "learning_rate": 4.866897392811126e-05, + "loss": 1.6095, + "step": 9271 + }, + { + "epoch": 0.5168050833286885, + "grad_norm": 0.5739067196846008, + "learning_rate": 4.866007286852051e-05, + "loss": 1.6357, + "step": 9272 + }, + { + "epoch": 0.5168608215818516, + "grad_norm": 0.567419171333313, + "learning_rate": 4.865117185142443e-05, + "loss": 1.6251, + "step": 9273 + }, + { + "epoch": 0.5169165598350147, + "grad_norm": 0.5760751366615295, + "learning_rate": 4.8642270877105305e-05, + "loss": 1.6139, + "step": 9274 + }, + { + "epoch": 0.5169722980881779, + "grad_norm": 0.5624504089355469, + "learning_rate": 4.863336994584542e-05, + "loss": 1.7346, + "step": 9275 + }, + { + "epoch": 0.5170280363413411, + "grad_norm": 0.5871464610099792, + "learning_rate": 4.8624469057927116e-05, + "loss": 1.8586, + "step": 9276 + }, + { + "epoch": 0.5170837745945042, + "grad_norm": 0.5720483064651489, + "learning_rate": 4.861556821363259e-05, + "loss": 1.6571, + "step": 9277 + }, + { + "epoch": 0.5171395128476673, + "grad_norm": 0.6062625646591187, + "learning_rate": 4.860666741324419e-05, + "loss": 1.6364, + "step": 9278 + }, + { + "epoch": 0.5171952511008305, + "grad_norm": 0.5324755907058716, + "learning_rate": 4.8597766657044166e-05, + "loss": 1.5787, + "step": 9279 + }, + { + "epoch": 0.5172509893539936, + "grad_norm": 0.5596499443054199, + "learning_rate": 4.8588865945314826e-05, + "loss": 1.7362, + "step": 9280 + }, + { + "epoch": 0.5173067276071568, + "grad_norm": 0.5920062065124512, + "learning_rate": 4.857996527833841e-05, + "loss": 1.9419, + "step": 9281 + }, + { + "epoch": 0.51736246586032, + "grad_norm": 0.574780285358429, + "learning_rate": 4.857106465639723e-05, + "loss": 1.8925, + "step": 9282 + }, + { + "epoch": 0.517418204113483, + "grad_norm": 0.5297632813453674, + "learning_rate": 4.8562164079773545e-05, + "loss": 1.5802, + "step": 9283 + }, + { + "epoch": 0.5174739423666462, + "grad_norm": 0.6014637351036072, + "learning_rate": 4.855326354874962e-05, + "loss": 1.651, + "step": 9284 + }, + { + "epoch": 0.5175296806198094, + "grad_norm": 0.5652185082435608, + "learning_rate": 4.8544363063607764e-05, + "loss": 1.5509, + "step": 9285 + }, + { + "epoch": 0.5175854188729725, + "grad_norm": 0.5464864373207092, + "learning_rate": 4.8535462624630196e-05, + "loss": 1.5164, + "step": 9286 + }, + { + "epoch": 0.5176411571261357, + "grad_norm": 0.5614228248596191, + "learning_rate": 4.852656223209925e-05, + "loss": 1.4815, + "step": 9287 + }, + { + "epoch": 0.5176968953792989, + "grad_norm": 0.5757022500038147, + "learning_rate": 4.8517661886297124e-05, + "loss": 1.6221, + "step": 9288 + }, + { + "epoch": 0.5177526336324619, + "grad_norm": 0.5105504393577576, + "learning_rate": 4.850876158750613e-05, + "loss": 1.5974, + "step": 9289 + }, + { + "epoch": 0.5178083718856251, + "grad_norm": 0.5799221992492676, + "learning_rate": 4.849986133600854e-05, + "loss": 1.7308, + "step": 9290 + }, + { + "epoch": 0.5178641101387883, + "grad_norm": 0.6229887008666992, + "learning_rate": 4.849096113208658e-05, + "loss": 1.828, + "step": 9291 + }, + { + "epoch": 0.5179198483919514, + "grad_norm": 0.6005191206932068, + "learning_rate": 4.848206097602256e-05, + "loss": 1.7686, + "step": 9292 + }, + { + "epoch": 0.5179755866451146, + "grad_norm": 0.6147307753562927, + "learning_rate": 4.8473160868098697e-05, + "loss": 1.8687, + "step": 9293 + }, + { + "epoch": 0.5180313248982776, + "grad_norm": 0.5599120259284973, + "learning_rate": 4.8464260808597276e-05, + "loss": 1.4875, + "step": 9294 + }, + { + "epoch": 0.5180870631514408, + "grad_norm": 0.63963782787323, + "learning_rate": 4.8455360797800534e-05, + "loss": 1.7863, + "step": 9295 + }, + { + "epoch": 0.518142801404604, + "grad_norm": 0.5774217247962952, + "learning_rate": 4.844646083599075e-05, + "loss": 1.842, + "step": 9296 + }, + { + "epoch": 0.5181985396577671, + "grad_norm": 0.5250087380409241, + "learning_rate": 4.843756092345018e-05, + "loss": 1.4797, + "step": 9297 + }, + { + "epoch": 0.5182542779109303, + "grad_norm": 0.6038861274719238, + "learning_rate": 4.8428661060461055e-05, + "loss": 1.6694, + "step": 9298 + }, + { + "epoch": 0.5183100161640934, + "grad_norm": 0.5457639098167419, + "learning_rate": 4.8419761247305655e-05, + "loss": 1.611, + "step": 9299 + }, + { + "epoch": 0.5183657544172565, + "grad_norm": 0.5245123505592346, + "learning_rate": 4.8410861484266206e-05, + "loss": 1.4735, + "step": 9300 + }, + { + "epoch": 0.5184214926704197, + "grad_norm": 0.5180814266204834, + "learning_rate": 4.8401961771624946e-05, + "loss": 1.5019, + "step": 9301 + }, + { + "epoch": 0.5184772309235829, + "grad_norm": 0.5676085352897644, + "learning_rate": 4.839306210966418e-05, + "loss": 1.7617, + "step": 9302 + }, + { + "epoch": 0.518532969176746, + "grad_norm": 0.6066186428070068, + "learning_rate": 4.838416249866608e-05, + "loss": 1.8268, + "step": 9303 + }, + { + "epoch": 0.5185887074299091, + "grad_norm": 0.5835402607917786, + "learning_rate": 4.837526293891295e-05, + "loss": 1.816, + "step": 9304 + }, + { + "epoch": 0.5186444456830723, + "grad_norm": 0.520706057548523, + "learning_rate": 4.8366363430687e-05, + "loss": 1.6345, + "step": 9305 + }, + { + "epoch": 0.5187001839362354, + "grad_norm": 0.54007488489151, + "learning_rate": 4.8357463974270474e-05, + "loss": 1.5671, + "step": 9306 + }, + { + "epoch": 0.5187559221893986, + "grad_norm": 0.5502505302429199, + "learning_rate": 4.834856456994561e-05, + "loss": 1.5713, + "step": 9307 + }, + { + "epoch": 0.5188116604425618, + "grad_norm": 0.5642566084861755, + "learning_rate": 4.8339665217994654e-05, + "loss": 1.6636, + "step": 9308 + }, + { + "epoch": 0.5188673986957248, + "grad_norm": 0.5338882207870483, + "learning_rate": 4.833076591869984e-05, + "loss": 1.6706, + "step": 9309 + }, + { + "epoch": 0.518923136948888, + "grad_norm": 0.5252307057380676, + "learning_rate": 4.832186667234338e-05, + "loss": 1.6778, + "step": 9310 + }, + { + "epoch": 0.5189788752020512, + "grad_norm": 0.5578994750976562, + "learning_rate": 4.831296747920756e-05, + "loss": 1.7534, + "step": 9311 + }, + { + "epoch": 0.5190346134552143, + "grad_norm": 0.5512505173683167, + "learning_rate": 4.8304068339574536e-05, + "loss": 1.5795, + "step": 9312 + }, + { + "epoch": 0.5190903517083775, + "grad_norm": 0.5381572842597961, + "learning_rate": 4.829516925372662e-05, + "loss": 1.5837, + "step": 9313 + }, + { + "epoch": 0.5191460899615407, + "grad_norm": 0.5063994526863098, + "learning_rate": 4.828627022194596e-05, + "loss": 1.3961, + "step": 9314 + }, + { + "epoch": 0.5192018282147037, + "grad_norm": 0.5659567713737488, + "learning_rate": 4.827737124451482e-05, + "loss": 1.6917, + "step": 9315 + }, + { + "epoch": 0.5192575664678669, + "grad_norm": 0.6182090640068054, + "learning_rate": 4.8268472321715437e-05, + "loss": 1.4865, + "step": 9316 + }, + { + "epoch": 0.51931330472103, + "grad_norm": 0.5523496270179749, + "learning_rate": 4.825957345383e-05, + "loss": 1.6661, + "step": 9317 + }, + { + "epoch": 0.5193690429741932, + "grad_norm": 0.5721933245658875, + "learning_rate": 4.8250674641140763e-05, + "loss": 1.8197, + "step": 9318 + }, + { + "epoch": 0.5194247812273564, + "grad_norm": 0.5994561910629272, + "learning_rate": 4.8241775883929914e-05, + "loss": 1.6962, + "step": 9319 + }, + { + "epoch": 0.5194805194805194, + "grad_norm": 0.5856831073760986, + "learning_rate": 4.82328771824797e-05, + "loss": 1.7966, + "step": 9320 + }, + { + "epoch": 0.5195362577336826, + "grad_norm": 0.5815552473068237, + "learning_rate": 4.822397853707228e-05, + "loss": 1.7016, + "step": 9321 + }, + { + "epoch": 0.5195919959868458, + "grad_norm": 0.566786527633667, + "learning_rate": 4.821507994798993e-05, + "loss": 1.4905, + "step": 9322 + }, + { + "epoch": 0.5196477342400089, + "grad_norm": 0.5902820229530334, + "learning_rate": 4.820618141551485e-05, + "loss": 1.6682, + "step": 9323 + }, + { + "epoch": 0.5197034724931721, + "grad_norm": 0.5534100532531738, + "learning_rate": 4.819728293992922e-05, + "loss": 1.6271, + "step": 9324 + }, + { + "epoch": 0.5197592107463352, + "grad_norm": 0.5736867189407349, + "learning_rate": 4.8188384521515276e-05, + "loss": 1.8624, + "step": 9325 + }, + { + "epoch": 0.5198149489994983, + "grad_norm": 0.5427315831184387, + "learning_rate": 4.817948616055521e-05, + "loss": 1.6311, + "step": 9326 + }, + { + "epoch": 0.5198706872526615, + "grad_norm": 0.5504226684570312, + "learning_rate": 4.817058785733123e-05, + "loss": 1.706, + "step": 9327 + }, + { + "epoch": 0.5199264255058247, + "grad_norm": 0.560772180557251, + "learning_rate": 4.8161689612125524e-05, + "loss": 1.5919, + "step": 9328 + }, + { + "epoch": 0.5199821637589878, + "grad_norm": 0.5797060132026672, + "learning_rate": 4.8152791425220304e-05, + "loss": 1.6905, + "step": 9329 + }, + { + "epoch": 0.5200379020121509, + "grad_norm": 0.5403047800064087, + "learning_rate": 4.814389329689778e-05, + "loss": 1.6947, + "step": 9330 + }, + { + "epoch": 0.5200936402653141, + "grad_norm": 0.5620684027671814, + "learning_rate": 4.8134995227440136e-05, + "loss": 1.6495, + "step": 9331 + }, + { + "epoch": 0.5201493785184772, + "grad_norm": 0.563530683517456, + "learning_rate": 4.8126097217129576e-05, + "loss": 1.6507, + "step": 9332 + }, + { + "epoch": 0.5202051167716404, + "grad_norm": 0.5273337960243225, + "learning_rate": 4.811719926624828e-05, + "loss": 1.6496, + "step": 9333 + }, + { + "epoch": 0.5202608550248036, + "grad_norm": 0.5833011865615845, + "learning_rate": 4.8108301375078445e-05, + "loss": 1.7513, + "step": 9334 + }, + { + "epoch": 0.5203165932779666, + "grad_norm": 0.5634909868240356, + "learning_rate": 4.809940354390227e-05, + "loss": 1.5815, + "step": 9335 + }, + { + "epoch": 0.5203723315311298, + "grad_norm": 0.6327871084213257, + "learning_rate": 4.809050577300191e-05, + "loss": 1.8808, + "step": 9336 + }, + { + "epoch": 0.520428069784293, + "grad_norm": 0.5909899473190308, + "learning_rate": 4.8081608062659614e-05, + "loss": 1.5373, + "step": 9337 + }, + { + "epoch": 0.5204838080374561, + "grad_norm": 0.5492987632751465, + "learning_rate": 4.807271041315749e-05, + "loss": 1.7677, + "step": 9338 + }, + { + "epoch": 0.5205395462906193, + "grad_norm": 0.5624071955680847, + "learning_rate": 4.806381282477778e-05, + "loss": 1.7192, + "step": 9339 + }, + { + "epoch": 0.5205952845437823, + "grad_norm": 0.5824905037879944, + "learning_rate": 4.8054915297802616e-05, + "loss": 1.6621, + "step": 9340 + }, + { + "epoch": 0.5206510227969455, + "grad_norm": 0.6446887254714966, + "learning_rate": 4.8046017832514206e-05, + "loss": 1.8134, + "step": 9341 + }, + { + "epoch": 0.5207067610501087, + "grad_norm": 0.5947240591049194, + "learning_rate": 4.803712042919473e-05, + "loss": 1.811, + "step": 9342 + }, + { + "epoch": 0.5207624993032718, + "grad_norm": 0.6278781890869141, + "learning_rate": 4.8028223088126336e-05, + "loss": 1.6691, + "step": 9343 + }, + { + "epoch": 0.520818237556435, + "grad_norm": 0.5742304921150208, + "learning_rate": 4.8019325809591216e-05, + "loss": 1.8073, + "step": 9344 + }, + { + "epoch": 0.5208739758095982, + "grad_norm": 0.626422107219696, + "learning_rate": 4.8010428593871517e-05, + "loss": 1.5679, + "step": 9345 + }, + { + "epoch": 0.5209297140627612, + "grad_norm": 0.5343272089958191, + "learning_rate": 4.8001531441249457e-05, + "loss": 1.4528, + "step": 9346 + }, + { + "epoch": 0.5209854523159244, + "grad_norm": 0.7227659225463867, + "learning_rate": 4.7992634352007125e-05, + "loss": 1.5618, + "step": 9347 + }, + { + "epoch": 0.5210411905690876, + "grad_norm": 0.5783427953720093, + "learning_rate": 4.7983737326426746e-05, + "loss": 1.7091, + "step": 9348 + }, + { + "epoch": 0.5210969288222507, + "grad_norm": 0.5899874567985535, + "learning_rate": 4.7974840364790476e-05, + "loss": 1.7043, + "step": 9349 + }, + { + "epoch": 0.5211526670754139, + "grad_norm": 0.5830110907554626, + "learning_rate": 4.7965943467380446e-05, + "loss": 1.5431, + "step": 9350 + }, + { + "epoch": 0.521208405328577, + "grad_norm": 0.5403499603271484, + "learning_rate": 4.7957046634478846e-05, + "loss": 1.5314, + "step": 9351 + }, + { + "epoch": 0.5212641435817401, + "grad_norm": 0.6497839093208313, + "learning_rate": 4.7948149866367806e-05, + "loss": 1.9862, + "step": 9352 + }, + { + "epoch": 0.5213198818349033, + "grad_norm": 0.5488117337226868, + "learning_rate": 4.7939253163329496e-05, + "loss": 1.6921, + "step": 9353 + }, + { + "epoch": 0.5213756200880665, + "grad_norm": 0.6064301133155823, + "learning_rate": 4.7930356525646046e-05, + "loss": 1.5896, + "step": 9354 + }, + { + "epoch": 0.5214313583412296, + "grad_norm": 0.5546178221702576, + "learning_rate": 4.792145995359962e-05, + "loss": 1.7059, + "step": 9355 + }, + { + "epoch": 0.5214870965943927, + "grad_norm": 0.5294743180274963, + "learning_rate": 4.791256344747238e-05, + "loss": 1.5835, + "step": 9356 + }, + { + "epoch": 0.5215428348475559, + "grad_norm": 0.5221080780029297, + "learning_rate": 4.790366700754644e-05, + "loss": 1.5472, + "step": 9357 + }, + { + "epoch": 0.521598573100719, + "grad_norm": 0.555313229560852, + "learning_rate": 4.789477063410399e-05, + "loss": 1.7969, + "step": 9358 + }, + { + "epoch": 0.5216543113538822, + "grad_norm": 0.5328066349029541, + "learning_rate": 4.788587432742711e-05, + "loss": 1.6338, + "step": 9359 + }, + { + "epoch": 0.5217100496070454, + "grad_norm": 0.5458719730377197, + "learning_rate": 4.787697808779798e-05, + "loss": 1.7335, + "step": 9360 + }, + { + "epoch": 0.5217657878602084, + "grad_norm": 0.5909193158149719, + "learning_rate": 4.7868081915498734e-05, + "loss": 1.9916, + "step": 9361 + }, + { + "epoch": 0.5218215261133716, + "grad_norm": 0.5532034039497375, + "learning_rate": 4.785918581081148e-05, + "loss": 1.6839, + "step": 9362 + }, + { + "epoch": 0.5218772643665347, + "grad_norm": 0.5652511119842529, + "learning_rate": 4.7850289774018404e-05, + "loss": 1.6613, + "step": 9363 + }, + { + "epoch": 0.5219330026196979, + "grad_norm": 0.5659765005111694, + "learning_rate": 4.784139380540157e-05, + "loss": 1.4462, + "step": 9364 + }, + { + "epoch": 0.5219887408728611, + "grad_norm": 0.6014359593391418, + "learning_rate": 4.7832497905243164e-05, + "loss": 1.826, + "step": 9365 + }, + { + "epoch": 0.5220444791260241, + "grad_norm": 0.5442059636116028, + "learning_rate": 4.782360207382527e-05, + "loss": 1.6403, + "step": 9366 + }, + { + "epoch": 0.5221002173791873, + "grad_norm": 0.571991503238678, + "learning_rate": 4.781470631143003e-05, + "loss": 1.6031, + "step": 9367 + }, + { + "epoch": 0.5221559556323505, + "grad_norm": 0.6860571503639221, + "learning_rate": 4.780581061833958e-05, + "loss": 1.7744, + "step": 9368 + }, + { + "epoch": 0.5222116938855136, + "grad_norm": 0.5633348226547241, + "learning_rate": 4.7796914994836003e-05, + "loss": 1.7062, + "step": 9369 + }, + { + "epoch": 0.5222674321386768, + "grad_norm": 0.5520535111427307, + "learning_rate": 4.778801944120146e-05, + "loss": 1.6158, + "step": 9370 + }, + { + "epoch": 0.52232317039184, + "grad_norm": 0.5730091333389282, + "learning_rate": 4.7779123957718016e-05, + "loss": 1.8501, + "step": 9371 + }, + { + "epoch": 0.522378908645003, + "grad_norm": 0.5603798031806946, + "learning_rate": 4.777022854466784e-05, + "loss": 1.677, + "step": 9372 + }, + { + "epoch": 0.5224346468981662, + "grad_norm": 0.5554346442222595, + "learning_rate": 4.7761333202332986e-05, + "loss": 1.6819, + "step": 9373 + }, + { + "epoch": 0.5224903851513294, + "grad_norm": 0.5741342306137085, + "learning_rate": 4.7752437930995605e-05, + "loss": 1.8114, + "step": 9374 + }, + { + "epoch": 0.5225461234044925, + "grad_norm": 0.5575484037399292, + "learning_rate": 4.7743542730937794e-05, + "loss": 1.6216, + "step": 9375 + }, + { + "epoch": 0.5226018616576557, + "grad_norm": 0.5593728423118591, + "learning_rate": 4.7734647602441644e-05, + "loss": 1.5714, + "step": 9376 + }, + { + "epoch": 0.5226575999108188, + "grad_norm": 0.5570329427719116, + "learning_rate": 4.7725752545789276e-05, + "loss": 1.7383, + "step": 9377 + }, + { + "epoch": 0.5227133381639819, + "grad_norm": 0.5562308430671692, + "learning_rate": 4.771685756126276e-05, + "loss": 1.4746, + "step": 9378 + }, + { + "epoch": 0.5227690764171451, + "grad_norm": 0.5393458008766174, + "learning_rate": 4.7707962649144225e-05, + "loss": 1.762, + "step": 9379 + }, + { + "epoch": 0.5228248146703083, + "grad_norm": 0.5442481637001038, + "learning_rate": 4.769906780971575e-05, + "loss": 1.6694, + "step": 9380 + }, + { + "epoch": 0.5228805529234714, + "grad_norm": 0.5860007405281067, + "learning_rate": 4.769017304325941e-05, + "loss": 1.6952, + "step": 9381 + }, + { + "epoch": 0.5229362911766345, + "grad_norm": 0.6174299716949463, + "learning_rate": 4.768127835005733e-05, + "loss": 1.8446, + "step": 9382 + }, + { + "epoch": 0.5229920294297977, + "grad_norm": 0.5522156953811646, + "learning_rate": 4.767238373039157e-05, + "loss": 1.5253, + "step": 9383 + }, + { + "epoch": 0.5230477676829608, + "grad_norm": 0.5956835150718689, + "learning_rate": 4.7663489184544246e-05, + "loss": 1.7674, + "step": 9384 + }, + { + "epoch": 0.523103505936124, + "grad_norm": 0.5649197101593018, + "learning_rate": 4.7654594712797415e-05, + "loss": 1.6636, + "step": 9385 + }, + { + "epoch": 0.523159244189287, + "grad_norm": 0.5424702167510986, + "learning_rate": 4.7645700315433155e-05, + "loss": 1.6065, + "step": 9386 + }, + { + "epoch": 0.5232149824424502, + "grad_norm": 0.5742893218994141, + "learning_rate": 4.763680599273357e-05, + "loss": 1.8092, + "step": 9387 + }, + { + "epoch": 0.5232707206956134, + "grad_norm": 0.565175473690033, + "learning_rate": 4.76279117449807e-05, + "loss": 1.5921, + "step": 9388 + }, + { + "epoch": 0.5233264589487765, + "grad_norm": 0.599720299243927, + "learning_rate": 4.761901757245667e-05, + "loss": 1.7831, + "step": 9389 + }, + { + "epoch": 0.5233821972019397, + "grad_norm": 0.600030243396759, + "learning_rate": 4.7610123475443486e-05, + "loss": 1.7594, + "step": 9390 + }, + { + "epoch": 0.5234379354551029, + "grad_norm": 0.5445983409881592, + "learning_rate": 4.7601229454223275e-05, + "loss": 1.635, + "step": 9391 + }, + { + "epoch": 0.5234936737082659, + "grad_norm": 1.3782683610916138, + "learning_rate": 4.759233550907807e-05, + "loss": 1.6621, + "step": 9392 + }, + { + "epoch": 0.5235494119614291, + "grad_norm": 0.58378005027771, + "learning_rate": 4.7583441640289946e-05, + "loss": 1.6687, + "step": 9393 + }, + { + "epoch": 0.5236051502145923, + "grad_norm": 0.5960495471954346, + "learning_rate": 4.757454784814097e-05, + "loss": 1.7393, + "step": 9394 + }, + { + "epoch": 0.5236608884677554, + "grad_norm": 0.6179077625274658, + "learning_rate": 4.756565413291318e-05, + "loss": 1.7908, + "step": 9395 + }, + { + "epoch": 0.5237166267209186, + "grad_norm": 0.5232189297676086, + "learning_rate": 4.755676049488867e-05, + "loss": 1.6024, + "step": 9396 + }, + { + "epoch": 0.5237723649740817, + "grad_norm": 0.5634143352508545, + "learning_rate": 4.7547866934349447e-05, + "loss": 1.7352, + "step": 9397 + }, + { + "epoch": 0.5238281032272448, + "grad_norm": 0.5540798306465149, + "learning_rate": 4.753897345157762e-05, + "loss": 1.6196, + "step": 9398 + }, + { + "epoch": 0.523883841480408, + "grad_norm": 0.5112434029579163, + "learning_rate": 4.753008004685517e-05, + "loss": 1.5433, + "step": 9399 + }, + { + "epoch": 0.5239395797335712, + "grad_norm": 0.5160391926765442, + "learning_rate": 4.752118672046419e-05, + "loss": 1.4725, + "step": 9400 + }, + { + "epoch": 0.5239953179867343, + "grad_norm": 0.5671103000640869, + "learning_rate": 4.751229347268673e-05, + "loss": 1.6878, + "step": 9401 + }, + { + "epoch": 0.5240510562398975, + "grad_norm": 0.5739786028862, + "learning_rate": 4.750340030380481e-05, + "loss": 1.4368, + "step": 9402 + }, + { + "epoch": 0.5241067944930606, + "grad_norm": 0.5829623937606812, + "learning_rate": 4.749450721410048e-05, + "loss": 1.8745, + "step": 9403 + }, + { + "epoch": 0.5241625327462237, + "grad_norm": 0.5581690669059753, + "learning_rate": 4.748561420385577e-05, + "loss": 1.8433, + "step": 9404 + }, + { + "epoch": 0.5242182709993869, + "grad_norm": 0.5548933148384094, + "learning_rate": 4.747672127335272e-05, + "loss": 1.6408, + "step": 9405 + }, + { + "epoch": 0.5242740092525501, + "grad_norm": 0.5583091378211975, + "learning_rate": 4.746782842287335e-05, + "loss": 1.74, + "step": 9406 + }, + { + "epoch": 0.5243297475057132, + "grad_norm": 0.6239990592002869, + "learning_rate": 4.7458935652699686e-05, + "loss": 1.7131, + "step": 9407 + }, + { + "epoch": 0.5243854857588763, + "grad_norm": 0.5649636387825012, + "learning_rate": 4.7450042963113794e-05, + "loss": 1.6917, + "step": 9408 + }, + { + "epoch": 0.5244412240120394, + "grad_norm": 0.5509878993034363, + "learning_rate": 4.744115035439766e-05, + "loss": 1.5985, + "step": 9409 + }, + { + "epoch": 0.5244969622652026, + "grad_norm": 0.5211341977119446, + "learning_rate": 4.743225782683333e-05, + "loss": 1.3233, + "step": 9410 + }, + { + "epoch": 0.5245527005183658, + "grad_norm": 0.5903692245483398, + "learning_rate": 4.74233653807028e-05, + "loss": 1.7022, + "step": 9411 + }, + { + "epoch": 0.5246084387715289, + "grad_norm": 0.5562416911125183, + "learning_rate": 4.7414473016288096e-05, + "loss": 1.5126, + "step": 9412 + }, + { + "epoch": 0.524664177024692, + "grad_norm": 0.5590984225273132, + "learning_rate": 4.740558073387124e-05, + "loss": 1.736, + "step": 9413 + }, + { + "epoch": 0.5247199152778552, + "grad_norm": 0.5605709552764893, + "learning_rate": 4.7396688533734224e-05, + "loss": 1.7664, + "step": 9414 + }, + { + "epoch": 0.5247756535310183, + "grad_norm": 0.56081622838974, + "learning_rate": 4.7387796416159094e-05, + "loss": 1.6379, + "step": 9415 + }, + { + "epoch": 0.5248313917841815, + "grad_norm": 0.5936822891235352, + "learning_rate": 4.7378904381427805e-05, + "loss": 1.6248, + "step": 9416 + }, + { + "epoch": 0.5248871300373447, + "grad_norm": 0.5852161049842834, + "learning_rate": 4.7370012429822405e-05, + "loss": 1.8269, + "step": 9417 + }, + { + "epoch": 0.5249428682905077, + "grad_norm": 0.5660523772239685, + "learning_rate": 4.736112056162486e-05, + "loss": 1.6686, + "step": 9418 + }, + { + "epoch": 0.5249986065436709, + "grad_norm": 0.5601064562797546, + "learning_rate": 4.7352228777117195e-05, + "loss": 1.6043, + "step": 9419 + }, + { + "epoch": 0.5250543447968341, + "grad_norm": 0.531576931476593, + "learning_rate": 4.73433370765814e-05, + "loss": 1.3681, + "step": 9420 + }, + { + "epoch": 0.5251100830499972, + "grad_norm": 0.609130322933197, + "learning_rate": 4.733444546029946e-05, + "loss": 1.8752, + "step": 9421 + }, + { + "epoch": 0.5251658213031604, + "grad_norm": 0.5157068371772766, + "learning_rate": 4.7325553928553375e-05, + "loss": 1.6649, + "step": 9422 + }, + { + "epoch": 0.5252215595563235, + "grad_norm": 0.42130622267723083, + "learning_rate": 4.73166624816251e-05, + "loss": 0.7808, + "step": 9423 + }, + { + "epoch": 0.5252772978094866, + "grad_norm": 0.5316475629806519, + "learning_rate": 4.7307771119796685e-05, + "loss": 1.9264, + "step": 9424 + }, + { + "epoch": 0.5253330360626498, + "grad_norm": 0.5346727967262268, + "learning_rate": 4.729887984335004e-05, + "loss": 1.4697, + "step": 9425 + }, + { + "epoch": 0.525388774315813, + "grad_norm": 0.5731312036514282, + "learning_rate": 4.728998865256718e-05, + "loss": 1.7123, + "step": 9426 + }, + { + "epoch": 0.5254445125689761, + "grad_norm": 0.5310966968536377, + "learning_rate": 4.728109754773011e-05, + "loss": 1.6069, + "step": 9427 + }, + { + "epoch": 0.5255002508221392, + "grad_norm": 0.5562901496887207, + "learning_rate": 4.727220652912074e-05, + "loss": 1.5449, + "step": 9428 + }, + { + "epoch": 0.5255559890753024, + "grad_norm": 0.5125192403793335, + "learning_rate": 4.72633155970211e-05, + "loss": 1.3929, + "step": 9429 + }, + { + "epoch": 0.5256117273284655, + "grad_norm": 0.5134342908859253, + "learning_rate": 4.725442475171312e-05, + "loss": 1.5311, + "step": 9430 + }, + { + "epoch": 0.5256674655816287, + "grad_norm": 0.56780606508255, + "learning_rate": 4.724553399347879e-05, + "loss": 1.8386, + "step": 9431 + }, + { + "epoch": 0.5257232038347918, + "grad_norm": 0.527378499507904, + "learning_rate": 4.723664332260004e-05, + "loss": 1.4743, + "step": 9432 + }, + { + "epoch": 0.525778942087955, + "grad_norm": 0.5406578779220581, + "learning_rate": 4.722775273935886e-05, + "loss": 1.5645, + "step": 9433 + }, + { + "epoch": 0.5258346803411181, + "grad_norm": 0.5987953543663025, + "learning_rate": 4.721886224403722e-05, + "loss": 1.8844, + "step": 9434 + }, + { + "epoch": 0.5258904185942812, + "grad_norm": 0.6220631003379822, + "learning_rate": 4.720997183691703e-05, + "loss": 1.6094, + "step": 9435 + }, + { + "epoch": 0.5259461568474444, + "grad_norm": 0.5748035311698914, + "learning_rate": 4.720108151828028e-05, + "loss": 1.6859, + "step": 9436 + }, + { + "epoch": 0.5260018951006076, + "grad_norm": 0.6056424379348755, + "learning_rate": 4.71921912884089e-05, + "loss": 1.8112, + "step": 9437 + }, + { + "epoch": 0.5260576333537706, + "grad_norm": 0.5912368893623352, + "learning_rate": 4.7183301147584854e-05, + "loss": 1.783, + "step": 9438 + }, + { + "epoch": 0.5261133716069338, + "grad_norm": 0.5289324522018433, + "learning_rate": 4.717441109609006e-05, + "loss": 1.5162, + "step": 9439 + }, + { + "epoch": 0.526169109860097, + "grad_norm": 0.5573659539222717, + "learning_rate": 4.716552113420646e-05, + "loss": 1.5676, + "step": 9440 + }, + { + "epoch": 0.5262248481132601, + "grad_norm": 0.5835697054862976, + "learning_rate": 4.715663126221603e-05, + "loss": 1.812, + "step": 9441 + }, + { + "epoch": 0.5262805863664233, + "grad_norm": 0.617939293384552, + "learning_rate": 4.714774148040065e-05, + "loss": 1.8001, + "step": 9442 + }, + { + "epoch": 0.5263363246195865, + "grad_norm": 0.59937584400177, + "learning_rate": 4.713885178904231e-05, + "loss": 1.8504, + "step": 9443 + }, + { + "epoch": 0.5263920628727495, + "grad_norm": 0.5530192852020264, + "learning_rate": 4.7129962188422886e-05, + "loss": 1.7862, + "step": 9444 + }, + { + "epoch": 0.5264478011259127, + "grad_norm": 0.5564062595367432, + "learning_rate": 4.712107267882434e-05, + "loss": 1.6889, + "step": 9445 + }, + { + "epoch": 0.5265035393790759, + "grad_norm": 0.5669463276863098, + "learning_rate": 4.7112183260528584e-05, + "loss": 1.4817, + "step": 9446 + }, + { + "epoch": 0.526559277632239, + "grad_norm": 0.5424147248268127, + "learning_rate": 4.710329393381753e-05, + "loss": 1.7066, + "step": 9447 + }, + { + "epoch": 0.5266150158854022, + "grad_norm": 0.5391395092010498, + "learning_rate": 4.709440469897312e-05, + "loss": 1.4955, + "step": 9448 + }, + { + "epoch": 0.5266707541385653, + "grad_norm": 0.5175044536590576, + "learning_rate": 4.708551555627723e-05, + "loss": 1.6005, + "step": 9449 + }, + { + "epoch": 0.5267264923917284, + "grad_norm": 0.5783989429473877, + "learning_rate": 4.707662650601182e-05, + "loss": 1.6138, + "step": 9450 + }, + { + "epoch": 0.5267822306448916, + "grad_norm": 0.6266419887542725, + "learning_rate": 4.706773754845874e-05, + "loss": 1.8049, + "step": 9451 + }, + { + "epoch": 0.5268379688980548, + "grad_norm": 0.5239512920379639, + "learning_rate": 4.705884868389994e-05, + "loss": 1.4986, + "step": 9452 + }, + { + "epoch": 0.5268937071512179, + "grad_norm": 0.504352867603302, + "learning_rate": 4.704995991261733e-05, + "loss": 1.6794, + "step": 9453 + }, + { + "epoch": 0.526949445404381, + "grad_norm": 0.5516874194145203, + "learning_rate": 4.704107123489277e-05, + "loss": 1.544, + "step": 9454 + }, + { + "epoch": 0.5270051836575441, + "grad_norm": 0.5346981883049011, + "learning_rate": 4.70321826510082e-05, + "loss": 1.556, + "step": 9455 + }, + { + "epoch": 0.5270609219107073, + "grad_norm": 0.5733329057693481, + "learning_rate": 4.702329416124548e-05, + "loss": 1.5109, + "step": 9456 + }, + { + "epoch": 0.5271166601638705, + "grad_norm": 0.5586609244346619, + "learning_rate": 4.701440576588652e-05, + "loss": 1.6984, + "step": 9457 + }, + { + "epoch": 0.5271723984170336, + "grad_norm": 0.6048542261123657, + "learning_rate": 4.700551746521318e-05, + "loss": 1.6543, + "step": 9458 + }, + { + "epoch": 0.5272281366701967, + "grad_norm": 0.5741638541221619, + "learning_rate": 4.699662925950738e-05, + "loss": 1.5402, + "step": 9459 + }, + { + "epoch": 0.5272838749233599, + "grad_norm": 0.5675785541534424, + "learning_rate": 4.6987741149051e-05, + "loss": 1.6698, + "step": 9460 + }, + { + "epoch": 0.527339613176523, + "grad_norm": 0.5488637685775757, + "learning_rate": 4.69788531341259e-05, + "loss": 1.7072, + "step": 9461 + }, + { + "epoch": 0.5273953514296862, + "grad_norm": 0.5417453646659851, + "learning_rate": 4.6969965215013964e-05, + "loss": 1.443, + "step": 9462 + }, + { + "epoch": 0.5274510896828494, + "grad_norm": 0.5321457982063293, + "learning_rate": 4.696107739199707e-05, + "loss": 1.498, + "step": 9463 + }, + { + "epoch": 0.5275068279360124, + "grad_norm": 0.5696976780891418, + "learning_rate": 4.695218966535708e-05, + "loss": 1.7932, + "step": 9464 + }, + { + "epoch": 0.5275625661891756, + "grad_norm": 0.5530003905296326, + "learning_rate": 4.6943302035375864e-05, + "loss": 1.5405, + "step": 9465 + }, + { + "epoch": 0.5276183044423388, + "grad_norm": 0.5903899669647217, + "learning_rate": 4.693441450233527e-05, + "loss": 1.6725, + "step": 9466 + }, + { + "epoch": 0.5276740426955019, + "grad_norm": 0.5503592491149902, + "learning_rate": 4.69255270665172e-05, + "loss": 1.7555, + "step": 9467 + }, + { + "epoch": 0.5277297809486651, + "grad_norm": 0.5256405472755432, + "learning_rate": 4.6916639728203465e-05, + "loss": 1.5811, + "step": 9468 + }, + { + "epoch": 0.5277855192018283, + "grad_norm": 0.5961898565292358, + "learning_rate": 4.6907752487675954e-05, + "loss": 1.7571, + "step": 9469 + }, + { + "epoch": 0.5278412574549913, + "grad_norm": 0.6401336193084717, + "learning_rate": 4.68988653452165e-05, + "loss": 1.8604, + "step": 9470 + }, + { + "epoch": 0.5278969957081545, + "grad_norm": 0.5445451140403748, + "learning_rate": 4.688997830110695e-05, + "loss": 1.7073, + "step": 9471 + }, + { + "epoch": 0.5279527339613177, + "grad_norm": 0.5979543924331665, + "learning_rate": 4.688109135562918e-05, + "loss": 1.8051, + "step": 9472 + }, + { + "epoch": 0.5280084722144808, + "grad_norm": 0.5162997841835022, + "learning_rate": 4.6872204509064984e-05, + "loss": 1.4152, + "step": 9473 + }, + { + "epoch": 0.528064210467644, + "grad_norm": 0.5626786351203918, + "learning_rate": 4.686331776169624e-05, + "loss": 1.8541, + "step": 9474 + }, + { + "epoch": 0.5281199487208071, + "grad_norm": 0.5397034883499146, + "learning_rate": 4.685443111380474e-05, + "loss": 1.5225, + "step": 9475 + }, + { + "epoch": 0.5281756869739702, + "grad_norm": 0.549978494644165, + "learning_rate": 4.6845544565672385e-05, + "loss": 1.8114, + "step": 9476 + }, + { + "epoch": 0.5282314252271334, + "grad_norm": 0.564751148223877, + "learning_rate": 4.683665811758093e-05, + "loss": 1.698, + "step": 9477 + }, + { + "epoch": 0.5282871634802965, + "grad_norm": 0.5972959399223328, + "learning_rate": 4.6827771769812247e-05, + "loss": 1.9423, + "step": 9478 + }, + { + "epoch": 0.5283429017334597, + "grad_norm": 0.5752547979354858, + "learning_rate": 4.681888552264816e-05, + "loss": 1.8993, + "step": 9479 + }, + { + "epoch": 0.5283986399866228, + "grad_norm": 0.5367037057876587, + "learning_rate": 4.680999937637047e-05, + "loss": 1.4992, + "step": 9480 + }, + { + "epoch": 0.5284543782397859, + "grad_norm": 0.5151523947715759, + "learning_rate": 4.6801113331261e-05, + "loss": 1.469, + "step": 9481 + }, + { + "epoch": 0.5285101164929491, + "grad_norm": 0.5293115973472595, + "learning_rate": 4.679222738760156e-05, + "loss": 1.5147, + "step": 9482 + }, + { + "epoch": 0.5285658547461123, + "grad_norm": 0.5823219418525696, + "learning_rate": 4.6783341545673975e-05, + "loss": 1.7303, + "step": 9483 + }, + { + "epoch": 0.5286215929992754, + "grad_norm": 0.5544847846031189, + "learning_rate": 4.677445580576003e-05, + "loss": 1.4783, + "step": 9484 + }, + { + "epoch": 0.5286773312524385, + "grad_norm": 0.5406891107559204, + "learning_rate": 4.676557016814154e-05, + "loss": 1.6925, + "step": 9485 + }, + { + "epoch": 0.5287330695056017, + "grad_norm": 0.5609269738197327, + "learning_rate": 4.675668463310032e-05, + "loss": 1.562, + "step": 9486 + }, + { + "epoch": 0.5287888077587648, + "grad_norm": 0.5836624503135681, + "learning_rate": 4.674779920091814e-05, + "loss": 1.8974, + "step": 9487 + }, + { + "epoch": 0.528844546011928, + "grad_norm": 0.6158092617988586, + "learning_rate": 4.673891387187682e-05, + "loss": 1.6163, + "step": 9488 + }, + { + "epoch": 0.5289002842650912, + "grad_norm": 0.5655474066734314, + "learning_rate": 4.673002864625813e-05, + "loss": 1.7773, + "step": 9489 + }, + { + "epoch": 0.5289560225182542, + "grad_norm": 0.572187066078186, + "learning_rate": 4.6721143524343874e-05, + "loss": 1.6477, + "step": 9490 + }, + { + "epoch": 0.5290117607714174, + "grad_norm": 0.5250730514526367, + "learning_rate": 4.671225850641582e-05, + "loss": 1.3446, + "step": 9491 + }, + { + "epoch": 0.5290674990245806, + "grad_norm": 0.576943039894104, + "learning_rate": 4.670337359275574e-05, + "loss": 1.864, + "step": 9492 + }, + { + "epoch": 0.5291232372777437, + "grad_norm": 0.6366379857063293, + "learning_rate": 4.6694488783645466e-05, + "loss": 1.9024, + "step": 9493 + }, + { + "epoch": 0.5291789755309069, + "grad_norm": 0.5497097969055176, + "learning_rate": 4.6685604079366706e-05, + "loss": 1.7019, + "step": 9494 + }, + { + "epoch": 0.52923471378407, + "grad_norm": 0.5463730692863464, + "learning_rate": 4.667671948020128e-05, + "loss": 1.545, + "step": 9495 + }, + { + "epoch": 0.5292904520372331, + "grad_norm": 0.5959593653678894, + "learning_rate": 4.666783498643093e-05, + "loss": 1.4809, + "step": 9496 + }, + { + "epoch": 0.5293461902903963, + "grad_norm": 0.6760483384132385, + "learning_rate": 4.665895059833741e-05, + "loss": 1.3123, + "step": 9497 + }, + { + "epoch": 0.5294019285435595, + "grad_norm": 0.5294803977012634, + "learning_rate": 4.6650066316202525e-05, + "loss": 1.5795, + "step": 9498 + }, + { + "epoch": 0.5294576667967226, + "grad_norm": 0.5938780903816223, + "learning_rate": 4.6641182140307986e-05, + "loss": 1.7409, + "step": 9499 + }, + { + "epoch": 0.5295134050498858, + "grad_norm": 0.5527142882347107, + "learning_rate": 4.663229807093558e-05, + "loss": 1.5922, + "step": 9500 + }, + { + "epoch": 0.5295691433030488, + "grad_norm": 0.5486581325531006, + "learning_rate": 4.662341410836703e-05, + "loss": 1.6494, + "step": 9501 + }, + { + "epoch": 0.529624881556212, + "grad_norm": 0.548119068145752, + "learning_rate": 4.661453025288411e-05, + "loss": 1.5342, + "step": 9502 + }, + { + "epoch": 0.5296806198093752, + "grad_norm": 0.5932400822639465, + "learning_rate": 4.660564650476854e-05, + "loss": 1.6725, + "step": 9503 + }, + { + "epoch": 0.5297363580625383, + "grad_norm": 0.614427387714386, + "learning_rate": 4.6596762864302076e-05, + "loss": 1.9948, + "step": 9504 + }, + { + "epoch": 0.5297920963157015, + "grad_norm": 0.5420172810554504, + "learning_rate": 4.658787933176646e-05, + "loss": 1.4934, + "step": 9505 + }, + { + "epoch": 0.5298478345688646, + "grad_norm": 0.5479914546012878, + "learning_rate": 4.657899590744341e-05, + "loss": 1.627, + "step": 9506 + }, + { + "epoch": 0.5299035728220277, + "grad_norm": 0.5667080879211426, + "learning_rate": 4.6570112591614664e-05, + "loss": 1.5898, + "step": 9507 + }, + { + "epoch": 0.5299593110751909, + "grad_norm": 0.5239989161491394, + "learning_rate": 4.656122938456195e-05, + "loss": 1.4714, + "step": 9508 + }, + { + "epoch": 0.5300150493283541, + "grad_norm": 0.5880669951438904, + "learning_rate": 4.6552346286567e-05, + "loss": 1.6165, + "step": 9509 + }, + { + "epoch": 0.5300707875815172, + "grad_norm": 0.6253079175949097, + "learning_rate": 4.65434632979115e-05, + "loss": 1.8067, + "step": 9510 + }, + { + "epoch": 0.5301265258346803, + "grad_norm": 0.5400813817977905, + "learning_rate": 4.6534580418877205e-05, + "loss": 1.5718, + "step": 9511 + }, + { + "epoch": 0.5301822640878435, + "grad_norm": 0.5349458456039429, + "learning_rate": 4.652569764974582e-05, + "loss": 1.5877, + "step": 9512 + }, + { + "epoch": 0.5302380023410066, + "grad_norm": 0.5760993957519531, + "learning_rate": 4.651681499079904e-05, + "loss": 1.7207, + "step": 9513 + }, + { + "epoch": 0.5302937405941698, + "grad_norm": 0.48260366916656494, + "learning_rate": 4.6507932442318596e-05, + "loss": 1.1782, + "step": 9514 + }, + { + "epoch": 0.530349478847333, + "grad_norm": 0.5174147486686707, + "learning_rate": 4.649905000458616e-05, + "loss": 1.2772, + "step": 9515 + }, + { + "epoch": 0.530405217100496, + "grad_norm": 0.543880820274353, + "learning_rate": 4.6490167677883457e-05, + "loss": 1.6083, + "step": 9516 + }, + { + "epoch": 0.5304609553536592, + "grad_norm": 0.5448428392410278, + "learning_rate": 4.648128546249216e-05, + "loss": 1.687, + "step": 9517 + }, + { + "epoch": 0.5305166936068224, + "grad_norm": 0.5626906752586365, + "learning_rate": 4.6472403358693964e-05, + "loss": 1.5031, + "step": 9518 + }, + { + "epoch": 0.5305724318599855, + "grad_norm": 0.5578361749649048, + "learning_rate": 4.646352136677058e-05, + "loss": 1.7177, + "step": 9519 + }, + { + "epoch": 0.5306281701131487, + "grad_norm": 0.5288956165313721, + "learning_rate": 4.645463948700368e-05, + "loss": 1.4941, + "step": 9520 + }, + { + "epoch": 0.5306839083663119, + "grad_norm": 0.5862405896186829, + "learning_rate": 4.644575771967495e-05, + "loss": 1.5097, + "step": 9521 + }, + { + "epoch": 0.5307396466194749, + "grad_norm": 0.5509393811225891, + "learning_rate": 4.6436876065066046e-05, + "loss": 1.6904, + "step": 9522 + }, + { + "epoch": 0.5307953848726381, + "grad_norm": 0.5741393566131592, + "learning_rate": 4.642799452345867e-05, + "loss": 1.7481, + "step": 9523 + }, + { + "epoch": 0.5308511231258012, + "grad_norm": 0.5851439833641052, + "learning_rate": 4.6419113095134485e-05, + "loss": 1.8227, + "step": 9524 + }, + { + "epoch": 0.5309068613789644, + "grad_norm": 0.5458952784538269, + "learning_rate": 4.641023178037514e-05, + "loss": 1.5991, + "step": 9525 + }, + { + "epoch": 0.5309625996321276, + "grad_norm": 0.5807502269744873, + "learning_rate": 4.6401350579462337e-05, + "loss": 1.7392, + "step": 9526 + }, + { + "epoch": 0.5310183378852906, + "grad_norm": 0.5653144121170044, + "learning_rate": 4.6392469492677685e-05, + "loss": 1.9319, + "step": 9527 + }, + { + "epoch": 0.5310740761384538, + "grad_norm": 0.559446394443512, + "learning_rate": 4.63835885203029e-05, + "loss": 1.4941, + "step": 9528 + }, + { + "epoch": 0.531129814391617, + "grad_norm": 0.6032963991165161, + "learning_rate": 4.637470766261956e-05, + "loss": 1.8894, + "step": 9529 + }, + { + "epoch": 0.5311855526447801, + "grad_norm": 0.546187698841095, + "learning_rate": 4.636582691990937e-05, + "loss": 1.5257, + "step": 9530 + }, + { + "epoch": 0.5312412908979433, + "grad_norm": 0.552087664604187, + "learning_rate": 4.6356946292453984e-05, + "loss": 1.6217, + "step": 9531 + }, + { + "epoch": 0.5312970291511064, + "grad_norm": 0.5413661599159241, + "learning_rate": 4.6348065780535e-05, + "loss": 1.4773, + "step": 9532 + }, + { + "epoch": 0.5313527674042695, + "grad_norm": 0.5477663278579712, + "learning_rate": 4.633918538443409e-05, + "loss": 1.5962, + "step": 9533 + }, + { + "epoch": 0.5314085056574327, + "grad_norm": 0.5874429941177368, + "learning_rate": 4.633030510443287e-05, + "loss": 1.9244, + "step": 9534 + }, + { + "epoch": 0.5314642439105959, + "grad_norm": 0.5683996677398682, + "learning_rate": 4.632142494081298e-05, + "loss": 1.5354, + "step": 9535 + }, + { + "epoch": 0.531519982163759, + "grad_norm": 0.5978541374206543, + "learning_rate": 4.631254489385602e-05, + "loss": 1.7756, + "step": 9536 + }, + { + "epoch": 0.5315757204169221, + "grad_norm": 0.5998654365539551, + "learning_rate": 4.630366496384365e-05, + "loss": 1.7578, + "step": 9537 + }, + { + "epoch": 0.5316314586700853, + "grad_norm": 0.6490985751152039, + "learning_rate": 4.629478515105749e-05, + "loss": 1.8384, + "step": 9538 + }, + { + "epoch": 0.5316871969232484, + "grad_norm": 0.5708163380622864, + "learning_rate": 4.6285905455779136e-05, + "loss": 1.7661, + "step": 9539 + }, + { + "epoch": 0.5317429351764116, + "grad_norm": 0.5977619886398315, + "learning_rate": 4.6277025878290204e-05, + "loss": 1.965, + "step": 9540 + }, + { + "epoch": 0.5317986734295748, + "grad_norm": 0.5742282271385193, + "learning_rate": 4.6268146418872305e-05, + "loss": 1.7107, + "step": 9541 + }, + { + "epoch": 0.5318544116827378, + "grad_norm": 0.5834643840789795, + "learning_rate": 4.625926707780705e-05, + "loss": 1.7749, + "step": 9542 + }, + { + "epoch": 0.531910149935901, + "grad_norm": 0.5550711154937744, + "learning_rate": 4.625038785537602e-05, + "loss": 1.6059, + "step": 9543 + }, + { + "epoch": 0.5319658881890642, + "grad_norm": 0.5790189504623413, + "learning_rate": 4.6241508751860816e-05, + "loss": 1.8484, + "step": 9544 + }, + { + "epoch": 0.5320216264422273, + "grad_norm": 0.5297401547431946, + "learning_rate": 4.623262976754307e-05, + "loss": 1.6221, + "step": 9545 + }, + { + "epoch": 0.5320773646953905, + "grad_norm": 0.5399177074432373, + "learning_rate": 4.622375090270432e-05, + "loss": 1.6821, + "step": 9546 + }, + { + "epoch": 0.5321331029485535, + "grad_norm": 0.5894103050231934, + "learning_rate": 4.621487215762619e-05, + "loss": 1.8067, + "step": 9547 + }, + { + "epoch": 0.5321888412017167, + "grad_norm": 0.5290741920471191, + "learning_rate": 4.620599353259023e-05, + "loss": 1.4202, + "step": 9548 + }, + { + "epoch": 0.5322445794548799, + "grad_norm": 0.6190316081047058, + "learning_rate": 4.619711502787805e-05, + "loss": 1.832, + "step": 9549 + }, + { + "epoch": 0.532300317708043, + "grad_norm": 0.5280694365501404, + "learning_rate": 4.618823664377121e-05, + "loss": 1.6861, + "step": 9550 + }, + { + "epoch": 0.5323560559612062, + "grad_norm": 0.5568878054618835, + "learning_rate": 4.6179358380551255e-05, + "loss": 1.6477, + "step": 9551 + }, + { + "epoch": 0.5324117942143693, + "grad_norm": 0.6240448951721191, + "learning_rate": 4.617048023849981e-05, + "loss": 1.8258, + "step": 9552 + }, + { + "epoch": 0.5324675324675324, + "grad_norm": 0.6594541072845459, + "learning_rate": 4.616160221789837e-05, + "loss": 2.1279, + "step": 9553 + }, + { + "epoch": 0.5325232707206956, + "grad_norm": 0.5653007626533508, + "learning_rate": 4.615272431902857e-05, + "loss": 1.8833, + "step": 9554 + }, + { + "epoch": 0.5325790089738588, + "grad_norm": 0.5489795207977295, + "learning_rate": 4.614384654217189e-05, + "loss": 1.5675, + "step": 9555 + }, + { + "epoch": 0.5326347472270219, + "grad_norm": 0.5744782090187073, + "learning_rate": 4.6134968887609915e-05, + "loss": 1.7209, + "step": 9556 + }, + { + "epoch": 0.532690485480185, + "grad_norm": 0.5887755751609802, + "learning_rate": 4.6126091355624215e-05, + "loss": 1.8778, + "step": 9557 + }, + { + "epoch": 0.5327462237333482, + "grad_norm": 0.5370951890945435, + "learning_rate": 4.611721394649629e-05, + "loss": 1.6063, + "step": 9558 + }, + { + "epoch": 0.5328019619865113, + "grad_norm": 0.5396353006362915, + "learning_rate": 4.610833666050771e-05, + "loss": 1.7225, + "step": 9559 + }, + { + "epoch": 0.5328577002396745, + "grad_norm": 0.5278332233428955, + "learning_rate": 4.609945949794e-05, + "loss": 1.6031, + "step": 9560 + }, + { + "epoch": 0.5329134384928377, + "grad_norm": 0.5371220707893372, + "learning_rate": 4.60905824590747e-05, + "loss": 1.519, + "step": 9561 + }, + { + "epoch": 0.5329691767460008, + "grad_norm": 0.5495018362998962, + "learning_rate": 4.60817055441933e-05, + "loss": 1.5729, + "step": 9562 + }, + { + "epoch": 0.5330249149991639, + "grad_norm": 0.5440717339515686, + "learning_rate": 4.607282875357738e-05, + "loss": 1.4728, + "step": 9563 + }, + { + "epoch": 0.5330806532523271, + "grad_norm": 0.502078115940094, + "learning_rate": 4.606395208750844e-05, + "loss": 1.4295, + "step": 9564 + }, + { + "epoch": 0.5331363915054902, + "grad_norm": 0.629677414894104, + "learning_rate": 4.605507554626798e-05, + "loss": 1.836, + "step": 9565 + }, + { + "epoch": 0.5331921297586534, + "grad_norm": 0.5432531237602234, + "learning_rate": 4.6046199130137536e-05, + "loss": 1.6115, + "step": 9566 + }, + { + "epoch": 0.5332478680118166, + "grad_norm": 0.5538272261619568, + "learning_rate": 4.6037322839398586e-05, + "loss": 1.5308, + "step": 9567 + }, + { + "epoch": 0.5333036062649796, + "grad_norm": 0.6601541042327881, + "learning_rate": 4.602844667433267e-05, + "loss": 1.6254, + "step": 9568 + }, + { + "epoch": 0.5333593445181428, + "grad_norm": 0.6120070219039917, + "learning_rate": 4.601957063522125e-05, + "loss": 1.7533, + "step": 9569 + }, + { + "epoch": 0.5334150827713059, + "grad_norm": 0.6346586346626282, + "learning_rate": 4.601069472234584e-05, + "loss": 1.8627, + "step": 9570 + }, + { + "epoch": 0.5334708210244691, + "grad_norm": 0.606587827205658, + "learning_rate": 4.6001818935987954e-05, + "loss": 1.8637, + "step": 9571 + }, + { + "epoch": 0.5335265592776323, + "grad_norm": 0.6264762282371521, + "learning_rate": 4.599294327642905e-05, + "loss": 1.8194, + "step": 9572 + }, + { + "epoch": 0.5335822975307953, + "grad_norm": 0.5685368180274963, + "learning_rate": 4.598406774395063e-05, + "loss": 1.7858, + "step": 9573 + }, + { + "epoch": 0.5336380357839585, + "grad_norm": 0.5685484409332275, + "learning_rate": 4.597519233883416e-05, + "loss": 1.8332, + "step": 9574 + }, + { + "epoch": 0.5336937740371217, + "grad_norm": 0.5560395121574402, + "learning_rate": 4.596631706136113e-05, + "loss": 1.7374, + "step": 9575 + }, + { + "epoch": 0.5337495122902848, + "grad_norm": 0.5584644079208374, + "learning_rate": 4.595744191181299e-05, + "loss": 1.6939, + "step": 9576 + }, + { + "epoch": 0.533805250543448, + "grad_norm": 0.5306901335716248, + "learning_rate": 4.5948566890471226e-05, + "loss": 1.5649, + "step": 9577 + }, + { + "epoch": 0.5338609887966111, + "grad_norm": 0.5599258542060852, + "learning_rate": 4.593969199761732e-05, + "loss": 1.6355, + "step": 9578 + }, + { + "epoch": 0.5339167270497742, + "grad_norm": 0.5288627743721008, + "learning_rate": 4.593081723353267e-05, + "loss": 1.5703, + "step": 9579 + }, + { + "epoch": 0.5339724653029374, + "grad_norm": 0.5489224791526794, + "learning_rate": 4.592194259849882e-05, + "loss": 1.6562, + "step": 9580 + }, + { + "epoch": 0.5340282035561006, + "grad_norm": 0.5630218386650085, + "learning_rate": 4.591306809279714e-05, + "loss": 1.3497, + "step": 9581 + }, + { + "epoch": 0.5340839418092637, + "grad_norm": 0.5344558954238892, + "learning_rate": 4.590419371670912e-05, + "loss": 1.6694, + "step": 9582 + }, + { + "epoch": 0.5341396800624268, + "grad_norm": 0.5834851861000061, + "learning_rate": 4.5895319470516204e-05, + "loss": 1.823, + "step": 9583 + }, + { + "epoch": 0.53419541831559, + "grad_norm": 0.5720002055168152, + "learning_rate": 4.5886445354499814e-05, + "loss": 1.6351, + "step": 9584 + }, + { + "epoch": 0.5342511565687531, + "grad_norm": 0.6013414859771729, + "learning_rate": 4.58775713689414e-05, + "loss": 1.6793, + "step": 9585 + }, + { + "epoch": 0.5343068948219163, + "grad_norm": 0.5077610611915588, + "learning_rate": 4.5868697514122384e-05, + "loss": 1.5092, + "step": 9586 + }, + { + "epoch": 0.5343626330750795, + "grad_norm": 0.5603808164596558, + "learning_rate": 4.5859823790324194e-05, + "loss": 1.7538, + "step": 9587 + }, + { + "epoch": 0.5344183713282425, + "grad_norm": 0.5666378736495972, + "learning_rate": 4.5850950197828247e-05, + "loss": 1.7059, + "step": 9588 + }, + { + "epoch": 0.5344741095814057, + "grad_norm": 0.6286757588386536, + "learning_rate": 4.5842076736915974e-05, + "loss": 1.9543, + "step": 9589 + }, + { + "epoch": 0.5345298478345689, + "grad_norm": 0.5461648106575012, + "learning_rate": 4.583320340786879e-05, + "loss": 1.5304, + "step": 9590 + }, + { + "epoch": 0.534585586087732, + "grad_norm": 0.5395976901054382, + "learning_rate": 4.58243302109681e-05, + "loss": 1.6066, + "step": 9591 + }, + { + "epoch": 0.5346413243408952, + "grad_norm": 0.557267963886261, + "learning_rate": 4.581545714649531e-05, + "loss": 1.5607, + "step": 9592 + }, + { + "epoch": 0.5346970625940582, + "grad_norm": 0.5258218050003052, + "learning_rate": 4.5806584214731816e-05, + "loss": 1.5174, + "step": 9593 + }, + { + "epoch": 0.5347528008472214, + "grad_norm": 0.5536956787109375, + "learning_rate": 4.579771141595903e-05, + "loss": 1.5984, + "step": 9594 + }, + { + "epoch": 0.5348085391003846, + "grad_norm": 0.591376781463623, + "learning_rate": 4.578883875045833e-05, + "loss": 1.7833, + "step": 9595 + }, + { + "epoch": 0.5348642773535477, + "grad_norm": 0.5513203144073486, + "learning_rate": 4.5779966218511094e-05, + "loss": 1.8074, + "step": 9596 + }, + { + "epoch": 0.5349200156067109, + "grad_norm": 0.5725258588790894, + "learning_rate": 4.5771093820398756e-05, + "loss": 1.6128, + "step": 9597 + }, + { + "epoch": 0.5349757538598741, + "grad_norm": 0.6103070378303528, + "learning_rate": 4.576222155640265e-05, + "loss": 1.9675, + "step": 9598 + }, + { + "epoch": 0.5350314921130371, + "grad_norm": 0.5657504796981812, + "learning_rate": 4.5753349426804176e-05, + "loss": 1.7877, + "step": 9599 + }, + { + "epoch": 0.5350872303662003, + "grad_norm": 0.5394463539123535, + "learning_rate": 4.574447743188469e-05, + "loss": 1.7376, + "step": 9600 + }, + { + "epoch": 0.5351429686193635, + "grad_norm": 0.582391619682312, + "learning_rate": 4.573560557192558e-05, + "loss": 1.5553, + "step": 9601 + }, + { + "epoch": 0.5351987068725266, + "grad_norm": 0.5822402238845825, + "learning_rate": 4.572673384720819e-05, + "loss": 1.5464, + "step": 9602 + }, + { + "epoch": 0.5352544451256898, + "grad_norm": 0.5555740594863892, + "learning_rate": 4.571786225801388e-05, + "loss": 1.7513, + "step": 9603 + }, + { + "epoch": 0.5353101833788529, + "grad_norm": 0.5371900200843811, + "learning_rate": 4.570899080462404e-05, + "loss": 1.658, + "step": 9604 + }, + { + "epoch": 0.535365921632016, + "grad_norm": 0.6092341542243958, + "learning_rate": 4.570011948731996e-05, + "loss": 1.7345, + "step": 9605 + }, + { + "epoch": 0.5354216598851792, + "grad_norm": 0.5381090044975281, + "learning_rate": 4.569124830638304e-05, + "loss": 1.5001, + "step": 9606 + }, + { + "epoch": 0.5354773981383424, + "grad_norm": 0.6168373227119446, + "learning_rate": 4.568237726209459e-05, + "loss": 1.8614, + "step": 9607 + }, + { + "epoch": 0.5355331363915055, + "grad_norm": 0.5389047265052795, + "learning_rate": 4.567350635473596e-05, + "loss": 1.5247, + "step": 9608 + }, + { + "epoch": 0.5355888746446686, + "grad_norm": 0.5485653877258301, + "learning_rate": 4.56646355845885e-05, + "loss": 1.4937, + "step": 9609 + }, + { + "epoch": 0.5356446128978318, + "grad_norm": 0.5548982620239258, + "learning_rate": 4.565576495193351e-05, + "loss": 1.6458, + "step": 9610 + }, + { + "epoch": 0.5357003511509949, + "grad_norm": 0.5642284750938416, + "learning_rate": 4.564689445705233e-05, + "loss": 1.6966, + "step": 9611 + }, + { + "epoch": 0.5357560894041581, + "grad_norm": 0.5454595685005188, + "learning_rate": 4.563802410022627e-05, + "loss": 1.5728, + "step": 9612 + }, + { + "epoch": 0.5358118276573213, + "grad_norm": 0.5459495782852173, + "learning_rate": 4.562915388173668e-05, + "loss": 1.5377, + "step": 9613 + }, + { + "epoch": 0.5358675659104843, + "grad_norm": 0.5787219405174255, + "learning_rate": 4.562028380186481e-05, + "loss": 1.6114, + "step": 9614 + }, + { + "epoch": 0.5359233041636475, + "grad_norm": 0.550297200679779, + "learning_rate": 4.561141386089201e-05, + "loss": 1.2671, + "step": 9615 + }, + { + "epoch": 0.5359790424168106, + "grad_norm": 0.5597065687179565, + "learning_rate": 4.560254405909959e-05, + "loss": 1.5903, + "step": 9616 + }, + { + "epoch": 0.5360347806699738, + "grad_norm": 0.5175857543945312, + "learning_rate": 4.559367439676882e-05, + "loss": 1.5522, + "step": 9617 + }, + { + "epoch": 0.536090518923137, + "grad_norm": 0.5799580216407776, + "learning_rate": 4.558480487418102e-05, + "loss": 1.6349, + "step": 9618 + }, + { + "epoch": 0.5361462571763, + "grad_norm": 0.536422610282898, + "learning_rate": 4.557593549161746e-05, + "loss": 1.7025, + "step": 9619 + }, + { + "epoch": 0.5362019954294632, + "grad_norm": 0.534331738948822, + "learning_rate": 4.556706624935944e-05, + "loss": 1.5889, + "step": 9620 + }, + { + "epoch": 0.5362577336826264, + "grad_norm": 0.5340269804000854, + "learning_rate": 4.555819714768822e-05, + "loss": 1.5922, + "step": 9621 + }, + { + "epoch": 0.5363134719357895, + "grad_norm": 0.5497701168060303, + "learning_rate": 4.554932818688508e-05, + "loss": 1.4581, + "step": 9622 + }, + { + "epoch": 0.5363692101889527, + "grad_norm": 0.6451365947723389, + "learning_rate": 4.554045936723132e-05, + "loss": 1.8858, + "step": 9623 + }, + { + "epoch": 0.5364249484421159, + "grad_norm": 0.5696703195571899, + "learning_rate": 4.553159068900818e-05, + "loss": 1.6621, + "step": 9624 + }, + { + "epoch": 0.5364806866952789, + "grad_norm": 0.5307613611221313, + "learning_rate": 4.552272215249694e-05, + "loss": 1.6915, + "step": 9625 + }, + { + "epoch": 0.5365364249484421, + "grad_norm": 0.5900824666023254, + "learning_rate": 4.551385375797884e-05, + "loss": 1.6064, + "step": 9626 + }, + { + "epoch": 0.5365921632016053, + "grad_norm": 0.579522967338562, + "learning_rate": 4.5504985505735154e-05, + "loss": 1.721, + "step": 9627 + }, + { + "epoch": 0.5366479014547684, + "grad_norm": 0.5785220861434937, + "learning_rate": 4.5496117396047107e-05, + "loss": 1.6382, + "step": 9628 + }, + { + "epoch": 0.5367036397079316, + "grad_norm": 0.5899390578269958, + "learning_rate": 4.5487249429195946e-05, + "loss": 1.8254, + "step": 9629 + }, + { + "epoch": 0.5367593779610947, + "grad_norm": 0.6377177238464355, + "learning_rate": 4.5478381605462955e-05, + "loss": 1.9322, + "step": 9630 + }, + { + "epoch": 0.5368151162142578, + "grad_norm": 0.6333304047584534, + "learning_rate": 4.54695139251293e-05, + "loss": 1.6886, + "step": 9631 + }, + { + "epoch": 0.536870854467421, + "grad_norm": 0.5392901301383972, + "learning_rate": 4.546064638847628e-05, + "loss": 1.6018, + "step": 9632 + }, + { + "epoch": 0.5369265927205842, + "grad_norm": 0.5325821042060852, + "learning_rate": 4.545177899578507e-05, + "loss": 1.6915, + "step": 9633 + }, + { + "epoch": 0.5369823309737473, + "grad_norm": 0.5551168918609619, + "learning_rate": 4.544291174733692e-05, + "loss": 1.6215, + "step": 9634 + }, + { + "epoch": 0.5370380692269104, + "grad_norm": 0.6074517965316772, + "learning_rate": 4.543404464341304e-05, + "loss": 1.5721, + "step": 9635 + }, + { + "epoch": 0.5370938074800736, + "grad_norm": 0.5474486947059631, + "learning_rate": 4.5425177684294645e-05, + "loss": 1.6407, + "step": 9636 + }, + { + "epoch": 0.5371495457332367, + "grad_norm": 0.5517297387123108, + "learning_rate": 4.541631087026294e-05, + "loss": 1.6858, + "step": 9637 + }, + { + "epoch": 0.5372052839863999, + "grad_norm": 0.5288307666778564, + "learning_rate": 4.5407444201599115e-05, + "loss": 1.4761, + "step": 9638 + }, + { + "epoch": 0.537261022239563, + "grad_norm": 0.4987405836582184, + "learning_rate": 4.539857767858441e-05, + "loss": 1.6962, + "step": 9639 + }, + { + "epoch": 0.5373167604927261, + "grad_norm": 0.5545489192008972, + "learning_rate": 4.538971130149997e-05, + "loss": 1.5394, + "step": 9640 + }, + { + "epoch": 0.5373724987458893, + "grad_norm": 0.5300205945968628, + "learning_rate": 4.538084507062702e-05, + "loss": 1.629, + "step": 9641 + }, + { + "epoch": 0.5374282369990524, + "grad_norm": 0.5651752352714539, + "learning_rate": 4.537197898624673e-05, + "loss": 1.5614, + "step": 9642 + }, + { + "epoch": 0.5374839752522156, + "grad_norm": 0.56346195936203, + "learning_rate": 4.536311304864028e-05, + "loss": 1.532, + "step": 9643 + }, + { + "epoch": 0.5375397135053788, + "grad_norm": 0.5524798035621643, + "learning_rate": 4.5354247258088854e-05, + "loss": 1.5766, + "step": 9644 + }, + { + "epoch": 0.5375954517585418, + "grad_norm": 0.5094345808029175, + "learning_rate": 4.534538161487362e-05, + "loss": 1.727, + "step": 9645 + }, + { + "epoch": 0.537651190011705, + "grad_norm": 0.5881072282791138, + "learning_rate": 4.533651611927574e-05, + "loss": 1.6667, + "step": 9646 + }, + { + "epoch": 0.5377069282648682, + "grad_norm": 0.5255770087242126, + "learning_rate": 4.532765077157637e-05, + "loss": 1.6659, + "step": 9647 + }, + { + "epoch": 0.5377626665180313, + "grad_norm": 0.6107676029205322, + "learning_rate": 4.5318785572056674e-05, + "loss": 1.6792, + "step": 9648 + }, + { + "epoch": 0.5378184047711945, + "grad_norm": 0.596538245677948, + "learning_rate": 4.530992052099782e-05, + "loss": 1.5461, + "step": 9649 + }, + { + "epoch": 0.5378741430243577, + "grad_norm": 0.5855775475502014, + "learning_rate": 4.530105561868094e-05, + "loss": 1.6144, + "step": 9650 + }, + { + "epoch": 0.5379298812775207, + "grad_norm": 0.5489295721054077, + "learning_rate": 4.529219086538718e-05, + "loss": 1.7566, + "step": 9651 + }, + { + "epoch": 0.5379856195306839, + "grad_norm": 0.5393614172935486, + "learning_rate": 4.528332626139767e-05, + "loss": 1.6659, + "step": 9652 + }, + { + "epoch": 0.5380413577838471, + "grad_norm": 0.5832717418670654, + "learning_rate": 4.527446180699356e-05, + "loss": 1.7152, + "step": 9653 + }, + { + "epoch": 0.5380970960370102, + "grad_norm": 0.5892272591590881, + "learning_rate": 4.526559750245597e-05, + "loss": 1.7, + "step": 9654 + }, + { + "epoch": 0.5381528342901734, + "grad_norm": 0.5694185495376587, + "learning_rate": 4.5256733348066e-05, + "loss": 1.5537, + "step": 9655 + }, + { + "epoch": 0.5382085725433365, + "grad_norm": 0.5511647462844849, + "learning_rate": 4.524786934410483e-05, + "loss": 1.5007, + "step": 9656 + }, + { + "epoch": 0.5382643107964996, + "grad_norm": 0.5417333245277405, + "learning_rate": 4.5239005490853505e-05, + "loss": 1.7346, + "step": 9657 + }, + { + "epoch": 0.5383200490496628, + "grad_norm": 0.5600014328956604, + "learning_rate": 4.523014178859319e-05, + "loss": 1.5088, + "step": 9658 + }, + { + "epoch": 0.538375787302826, + "grad_norm": 0.5783017873764038, + "learning_rate": 4.522127823760495e-05, + "loss": 1.6899, + "step": 9659 + }, + { + "epoch": 0.538431525555989, + "grad_norm": 0.5410140156745911, + "learning_rate": 4.5212414838169905e-05, + "loss": 1.564, + "step": 9660 + }, + { + "epoch": 0.5384872638091522, + "grad_norm": 0.5686094164848328, + "learning_rate": 4.520355159056917e-05, + "loss": 1.7485, + "step": 9661 + }, + { + "epoch": 0.5385430020623153, + "grad_norm": 0.5296582579612732, + "learning_rate": 4.519468849508379e-05, + "loss": 1.4511, + "step": 9662 + }, + { + "epoch": 0.5385987403154785, + "grad_norm": 0.5661003589630127, + "learning_rate": 4.5185825551994884e-05, + "loss": 1.7853, + "step": 9663 + }, + { + "epoch": 0.5386544785686417, + "grad_norm": 0.5485278964042664, + "learning_rate": 4.5176962761583505e-05, + "loss": 1.6016, + "step": 9664 + }, + { + "epoch": 0.5387102168218048, + "grad_norm": 0.6073358654975891, + "learning_rate": 4.5168100124130787e-05, + "loss": 1.8608, + "step": 9665 + }, + { + "epoch": 0.5387659550749679, + "grad_norm": 0.6006177663803101, + "learning_rate": 4.515923763991772e-05, + "loss": 1.6971, + "step": 9666 + }, + { + "epoch": 0.5388216933281311, + "grad_norm": 0.6587806344032288, + "learning_rate": 4.515037530922542e-05, + "loss": 2.0262, + "step": 9667 + }, + { + "epoch": 0.5388774315812942, + "grad_norm": 0.5338617563247681, + "learning_rate": 4.5141513132334956e-05, + "loss": 1.5727, + "step": 9668 + }, + { + "epoch": 0.5389331698344574, + "grad_norm": 0.5626280307769775, + "learning_rate": 4.513265110952736e-05, + "loss": 1.7543, + "step": 9669 + }, + { + "epoch": 0.5389889080876206, + "grad_norm": 0.5913511514663696, + "learning_rate": 4.5123789241083696e-05, + "loss": 1.7567, + "step": 9670 + }, + { + "epoch": 0.5390446463407836, + "grad_norm": 0.5821614265441895, + "learning_rate": 4.5114927527285e-05, + "loss": 1.8279, + "step": 9671 + }, + { + "epoch": 0.5391003845939468, + "grad_norm": 0.5600893497467041, + "learning_rate": 4.510606596841233e-05, + "loss": 1.7168, + "step": 9672 + }, + { + "epoch": 0.53915612284711, + "grad_norm": 0.57114577293396, + "learning_rate": 4.5097204564746705e-05, + "loss": 1.8184, + "step": 9673 + }, + { + "epoch": 0.5392118611002731, + "grad_norm": 0.6253485679626465, + "learning_rate": 4.5088343316569156e-05, + "loss": 1.5677, + "step": 9674 + }, + { + "epoch": 0.5392675993534363, + "grad_norm": 0.5010294318199158, + "learning_rate": 4.507948222416074e-05, + "loss": 1.423, + "step": 9675 + }, + { + "epoch": 0.5393233376065995, + "grad_norm": 0.5963042974472046, + "learning_rate": 4.507062128780245e-05, + "loss": 1.7762, + "step": 9676 + }, + { + "epoch": 0.5393790758597625, + "grad_norm": 0.5247800946235657, + "learning_rate": 4.506176050777532e-05, + "loss": 1.5931, + "step": 9677 + }, + { + "epoch": 0.5394348141129257, + "grad_norm": 0.5738952159881592, + "learning_rate": 4.505289988436034e-05, + "loss": 1.8376, + "step": 9678 + }, + { + "epoch": 0.5394905523660889, + "grad_norm": 0.5756804347038269, + "learning_rate": 4.504403941783855e-05, + "loss": 1.695, + "step": 9679 + }, + { + "epoch": 0.539546290619252, + "grad_norm": 0.5405778884887695, + "learning_rate": 4.503517910849093e-05, + "loss": 1.7173, + "step": 9680 + }, + { + "epoch": 0.5396020288724152, + "grad_norm": 0.501308023929596, + "learning_rate": 4.502631895659846e-05, + "loss": 1.3706, + "step": 9681 + }, + { + "epoch": 0.5396577671255783, + "grad_norm": 0.5409435629844666, + "learning_rate": 4.501745896244219e-05, + "loss": 1.6029, + "step": 9682 + }, + { + "epoch": 0.5397135053787414, + "grad_norm": 0.6150081157684326, + "learning_rate": 4.500859912630303e-05, + "loss": 1.8895, + "step": 9683 + }, + { + "epoch": 0.5397692436319046, + "grad_norm": 0.5330567359924316, + "learning_rate": 4.499973944846204e-05, + "loss": 1.5352, + "step": 9684 + }, + { + "epoch": 0.5398249818850677, + "grad_norm": 0.5629265308380127, + "learning_rate": 4.499087992920015e-05, + "loss": 1.5303, + "step": 9685 + }, + { + "epoch": 0.5398807201382309, + "grad_norm": 0.6040432453155518, + "learning_rate": 4.4982020568798344e-05, + "loss": 1.9174, + "step": 9686 + }, + { + "epoch": 0.539936458391394, + "grad_norm": 0.5688749551773071, + "learning_rate": 4.497316136753759e-05, + "loss": 1.858, + "step": 9687 + }, + { + "epoch": 0.5399921966445571, + "grad_norm": 0.5480324029922485, + "learning_rate": 4.496430232569884e-05, + "loss": 1.6544, + "step": 9688 + }, + { + "epoch": 0.5400479348977203, + "grad_norm": 0.5562218427658081, + "learning_rate": 4.4955443443563064e-05, + "loss": 1.6606, + "step": 9689 + }, + { + "epoch": 0.5401036731508835, + "grad_norm": 0.5424361824989319, + "learning_rate": 4.49465847214112e-05, + "loss": 1.5377, + "step": 9690 + }, + { + "epoch": 0.5401594114040466, + "grad_norm": 0.6881382465362549, + "learning_rate": 4.4937726159524235e-05, + "loss": 1.6281, + "step": 9691 + }, + { + "epoch": 0.5402151496572097, + "grad_norm": 0.5246618390083313, + "learning_rate": 4.492886775818305e-05, + "loss": 1.6659, + "step": 9692 + }, + { + "epoch": 0.5402708879103729, + "grad_norm": 0.5500891804695129, + "learning_rate": 4.492000951766862e-05, + "loss": 1.5169, + "step": 9693 + }, + { + "epoch": 0.540326626163536, + "grad_norm": 0.5503033399581909, + "learning_rate": 4.4911151438261885e-05, + "loss": 1.4738, + "step": 9694 + }, + { + "epoch": 0.5403823644166992, + "grad_norm": 0.5710744857788086, + "learning_rate": 4.4902293520243746e-05, + "loss": 1.7376, + "step": 9695 + }, + { + "epoch": 0.5404381026698624, + "grad_norm": 0.5603642463684082, + "learning_rate": 4.489343576389514e-05, + "loss": 1.7419, + "step": 9696 + }, + { + "epoch": 0.5404938409230254, + "grad_norm": 0.60004723072052, + "learning_rate": 4.488457816949697e-05, + "loss": 1.4912, + "step": 9697 + }, + { + "epoch": 0.5405495791761886, + "grad_norm": 0.5611134171485901, + "learning_rate": 4.487572073733017e-05, + "loss": 1.8182, + "step": 9698 + }, + { + "epoch": 0.5406053174293518, + "grad_norm": 0.5735024809837341, + "learning_rate": 4.48668634676756e-05, + "loss": 1.7492, + "step": 9699 + }, + { + "epoch": 0.5406610556825149, + "grad_norm": 0.5404465794563293, + "learning_rate": 4.4858006360814215e-05, + "loss": 1.7785, + "step": 9700 + }, + { + "epoch": 0.5407167939356781, + "grad_norm": 0.5365709066390991, + "learning_rate": 4.484914941702689e-05, + "loss": 1.6768, + "step": 9701 + }, + { + "epoch": 0.5407725321888412, + "grad_norm": 0.5550958514213562, + "learning_rate": 4.484029263659451e-05, + "loss": 1.6993, + "step": 9702 + }, + { + "epoch": 0.5408282704420043, + "grad_norm": 0.5951088666915894, + "learning_rate": 4.4831436019797976e-05, + "loss": 1.882, + "step": 9703 + }, + { + "epoch": 0.5408840086951675, + "grad_norm": 0.5994411110877991, + "learning_rate": 4.482257956691814e-05, + "loss": 1.8899, + "step": 9704 + }, + { + "epoch": 0.5409397469483307, + "grad_norm": 0.5515292882919312, + "learning_rate": 4.48137232782359e-05, + "loss": 1.576, + "step": 9705 + }, + { + "epoch": 0.5409954852014938, + "grad_norm": 0.5630680322647095, + "learning_rate": 4.480486715403212e-05, + "loss": 1.7682, + "step": 9706 + }, + { + "epoch": 0.541051223454657, + "grad_norm": 0.608163058757782, + "learning_rate": 4.479601119458765e-05, + "loss": 1.8614, + "step": 9707 + }, + { + "epoch": 0.54110696170782, + "grad_norm": 0.5568028688430786, + "learning_rate": 4.478715540018339e-05, + "loss": 1.9185, + "step": 9708 + }, + { + "epoch": 0.5411626999609832, + "grad_norm": 0.5182965993881226, + "learning_rate": 4.477829977110014e-05, + "loss": 1.5266, + "step": 9709 + }, + { + "epoch": 0.5412184382141464, + "grad_norm": 0.5429890751838684, + "learning_rate": 4.4769444307618804e-05, + "loss": 1.5938, + "step": 9710 + }, + { + "epoch": 0.5412741764673095, + "grad_norm": 0.5619489550590515, + "learning_rate": 4.476058901002018e-05, + "loss": 1.7021, + "step": 9711 + }, + { + "epoch": 0.5413299147204726, + "grad_norm": 0.6017050743103027, + "learning_rate": 4.475173387858513e-05, + "loss": 1.7607, + "step": 9712 + }, + { + "epoch": 0.5413856529736358, + "grad_norm": 0.536908745765686, + "learning_rate": 4.4742878913594485e-05, + "loss": 1.6063, + "step": 9713 + }, + { + "epoch": 0.5414413912267989, + "grad_norm": 0.5397683382034302, + "learning_rate": 4.4734024115329066e-05, + "loss": 1.5175, + "step": 9714 + }, + { + "epoch": 0.5414971294799621, + "grad_norm": 0.6045666337013245, + "learning_rate": 4.4725169484069706e-05, + "loss": 1.9511, + "step": 9715 + }, + { + "epoch": 0.5415528677331253, + "grad_norm": 0.5848411321640015, + "learning_rate": 4.47163150200972e-05, + "loss": 1.7098, + "step": 9716 + }, + { + "epoch": 0.5416086059862883, + "grad_norm": 0.5425751209259033, + "learning_rate": 4.4707460723692396e-05, + "loss": 1.6926, + "step": 9717 + }, + { + "epoch": 0.5416643442394515, + "grad_norm": 0.5430467128753662, + "learning_rate": 4.469860659513606e-05, + "loss": 1.5529, + "step": 9718 + }, + { + "epoch": 0.5417200824926147, + "grad_norm": 0.5357252359390259, + "learning_rate": 4.468975263470902e-05, + "loss": 1.5383, + "step": 9719 + }, + { + "epoch": 0.5417758207457778, + "grad_norm": 0.6040672659873962, + "learning_rate": 4.468089884269207e-05, + "loss": 1.437, + "step": 9720 + }, + { + "epoch": 0.541831558998941, + "grad_norm": 0.5664768218994141, + "learning_rate": 4.467204521936599e-05, + "loss": 1.5692, + "step": 9721 + }, + { + "epoch": 0.5418872972521042, + "grad_norm": 0.5839176774024963, + "learning_rate": 4.466319176501159e-05, + "loss": 1.7301, + "step": 9722 + }, + { + "epoch": 0.5419430355052672, + "grad_norm": 0.6070646643638611, + "learning_rate": 4.465433847990961e-05, + "loss": 1.806, + "step": 9723 + }, + { + "epoch": 0.5419987737584304, + "grad_norm": 0.6136497855186462, + "learning_rate": 4.464548536434086e-05, + "loss": 1.8704, + "step": 9724 + }, + { + "epoch": 0.5420545120115936, + "grad_norm": 0.5477949976921082, + "learning_rate": 4.463663241858607e-05, + "loss": 1.5875, + "step": 9725 + }, + { + "epoch": 0.5421102502647567, + "grad_norm": 0.5016915798187256, + "learning_rate": 4.462777964292605e-05, + "loss": 1.504, + "step": 9726 + }, + { + "epoch": 0.5421659885179199, + "grad_norm": 0.588592529296875, + "learning_rate": 4.461892703764154e-05, + "loss": 1.7438, + "step": 9727 + }, + { + "epoch": 0.542221726771083, + "grad_norm": 0.6035858392715454, + "learning_rate": 4.461007460301328e-05, + "loss": 1.8666, + "step": 9728 + }, + { + "epoch": 0.5422774650242461, + "grad_norm": 0.5583263635635376, + "learning_rate": 4.4601222339322045e-05, + "loss": 1.456, + "step": 9729 + }, + { + "epoch": 0.5423332032774093, + "grad_norm": 0.5258424878120422, + "learning_rate": 4.459237024684855e-05, + "loss": 1.4502, + "step": 9730 + }, + { + "epoch": 0.5423889415305724, + "grad_norm": 0.59454345703125, + "learning_rate": 4.458351832587354e-05, + "loss": 1.9578, + "step": 9731 + }, + { + "epoch": 0.5424446797837356, + "grad_norm": 0.5876555442810059, + "learning_rate": 4.457466657667775e-05, + "loss": 1.867, + "step": 9732 + }, + { + "epoch": 0.5425004180368987, + "grad_norm": 0.5531097650527954, + "learning_rate": 4.456581499954189e-05, + "loss": 1.8218, + "step": 9733 + }, + { + "epoch": 0.5425561562900618, + "grad_norm": 0.578526496887207, + "learning_rate": 4.4556963594746724e-05, + "loss": 1.7565, + "step": 9734 + }, + { + "epoch": 0.542611894543225, + "grad_norm": 0.5239474177360535, + "learning_rate": 4.4548112362572915e-05, + "loss": 1.5784, + "step": 9735 + }, + { + "epoch": 0.5426676327963882, + "grad_norm": 0.5566216707229614, + "learning_rate": 4.45392613033012e-05, + "loss": 1.6293, + "step": 9736 + }, + { + "epoch": 0.5427233710495513, + "grad_norm": 0.5767298340797424, + "learning_rate": 4.453041041721228e-05, + "loss": 1.8317, + "step": 9737 + }, + { + "epoch": 0.5427791093027144, + "grad_norm": 0.5398491621017456, + "learning_rate": 4.452155970458686e-05, + "loss": 1.7089, + "step": 9738 + }, + { + "epoch": 0.5428348475558776, + "grad_norm": 0.5698423385620117, + "learning_rate": 4.451270916570562e-05, + "loss": 1.7275, + "step": 9739 + }, + { + "epoch": 0.5428905858090407, + "grad_norm": 0.534481942653656, + "learning_rate": 4.450385880084924e-05, + "loss": 1.6992, + "step": 9740 + }, + { + "epoch": 0.5429463240622039, + "grad_norm": 0.5307855606079102, + "learning_rate": 4.4495008610298435e-05, + "loss": 1.6468, + "step": 9741 + }, + { + "epoch": 0.5430020623153671, + "grad_norm": 0.572459876537323, + "learning_rate": 4.448615859433383e-05, + "loss": 1.7285, + "step": 9742 + }, + { + "epoch": 0.5430578005685301, + "grad_norm": 0.5302841067314148, + "learning_rate": 4.447730875323617e-05, + "loss": 1.5839, + "step": 9743 + }, + { + "epoch": 0.5431135388216933, + "grad_norm": 0.5929808616638184, + "learning_rate": 4.446845908728604e-05, + "loss": 1.8845, + "step": 9744 + }, + { + "epoch": 0.5431692770748565, + "grad_norm": 0.569716215133667, + "learning_rate": 4.445960959676414e-05, + "loss": 1.8191, + "step": 9745 + }, + { + "epoch": 0.5432250153280196, + "grad_norm": 0.590050995349884, + "learning_rate": 4.4450760281951134e-05, + "loss": 1.8001, + "step": 9746 + }, + { + "epoch": 0.5432807535811828, + "grad_norm": 0.5911651849746704, + "learning_rate": 4.444191114312765e-05, + "loss": 1.8329, + "step": 9747 + }, + { + "epoch": 0.543336491834346, + "grad_norm": 0.5420973896980286, + "learning_rate": 4.4433062180574356e-05, + "loss": 1.4827, + "step": 9748 + }, + { + "epoch": 0.543392230087509, + "grad_norm": 0.5806952118873596, + "learning_rate": 4.442421339457185e-05, + "loss": 1.5864, + "step": 9749 + }, + { + "epoch": 0.5434479683406722, + "grad_norm": 0.5456143021583557, + "learning_rate": 4.44153647854008e-05, + "loss": 1.5616, + "step": 9750 + }, + { + "epoch": 0.5435037065938354, + "grad_norm": 0.6005389094352722, + "learning_rate": 4.44065163533418e-05, + "loss": 1.773, + "step": 9751 + }, + { + "epoch": 0.5435594448469985, + "grad_norm": 0.6176022291183472, + "learning_rate": 4.43976680986755e-05, + "loss": 1.8526, + "step": 9752 + }, + { + "epoch": 0.5436151831001617, + "grad_norm": 0.5599396824836731, + "learning_rate": 4.438882002168251e-05, + "loss": 1.5885, + "step": 9753 + }, + { + "epoch": 0.5436709213533247, + "grad_norm": 0.5520609617233276, + "learning_rate": 4.437997212264343e-05, + "loss": 1.5476, + "step": 9754 + }, + { + "epoch": 0.5437266596064879, + "grad_norm": 0.5556759834289551, + "learning_rate": 4.437112440183887e-05, + "loss": 1.8489, + "step": 9755 + }, + { + "epoch": 0.5437823978596511, + "grad_norm": 0.5187088847160339, + "learning_rate": 4.436227685954942e-05, + "loss": 1.4991, + "step": 9756 + }, + { + "epoch": 0.5438381361128142, + "grad_norm": 0.5788566470146179, + "learning_rate": 4.4353429496055685e-05, + "loss": 1.6384, + "step": 9757 + }, + { + "epoch": 0.5438938743659774, + "grad_norm": 0.5231850147247314, + "learning_rate": 4.4344582311638234e-05, + "loss": 1.5669, + "step": 9758 + }, + { + "epoch": 0.5439496126191405, + "grad_norm": 0.5520696043968201, + "learning_rate": 4.4335735306577645e-05, + "loss": 1.8168, + "step": 9759 + }, + { + "epoch": 0.5440053508723036, + "grad_norm": 0.5291838049888611, + "learning_rate": 4.432688848115455e-05, + "loss": 1.449, + "step": 9760 + }, + { + "epoch": 0.5440610891254668, + "grad_norm": 0.5278047323226929, + "learning_rate": 4.431804183564944e-05, + "loss": 1.7658, + "step": 9761 + }, + { + "epoch": 0.54411682737863, + "grad_norm": 0.5484183430671692, + "learning_rate": 4.430919537034293e-05, + "loss": 1.6033, + "step": 9762 + }, + { + "epoch": 0.5441725656317931, + "grad_norm": 0.5881717801094055, + "learning_rate": 4.430034908551556e-05, + "loss": 1.5546, + "step": 9763 + }, + { + "epoch": 0.5442283038849562, + "grad_norm": 0.5577450394630432, + "learning_rate": 4.429150298144789e-05, + "loss": 1.6856, + "step": 9764 + }, + { + "epoch": 0.5442840421381194, + "grad_norm": 0.5595176219940186, + "learning_rate": 4.428265705842045e-05, + "loss": 1.7699, + "step": 9765 + }, + { + "epoch": 0.5443397803912825, + "grad_norm": 0.5696182250976562, + "learning_rate": 4.42738113167138e-05, + "loss": 1.5959, + "step": 9766 + }, + { + "epoch": 0.5443955186444457, + "grad_norm": 0.5747469067573547, + "learning_rate": 4.426496575660848e-05, + "loss": 1.7393, + "step": 9767 + }, + { + "epoch": 0.5444512568976089, + "grad_norm": 0.551275372505188, + "learning_rate": 4.425612037838498e-05, + "loss": 1.7109, + "step": 9768 + }, + { + "epoch": 0.5445069951507719, + "grad_norm": 0.5111570358276367, + "learning_rate": 4.424727518232389e-05, + "loss": 1.5678, + "step": 9769 + }, + { + "epoch": 0.5445627334039351, + "grad_norm": 0.5441057682037354, + "learning_rate": 4.4238430168705655e-05, + "loss": 1.6594, + "step": 9770 + }, + { + "epoch": 0.5446184716570983, + "grad_norm": 0.5695107579231262, + "learning_rate": 4.422958533781084e-05, + "loss": 1.6752, + "step": 9771 + }, + { + "epoch": 0.5446742099102614, + "grad_norm": 0.5917108058929443, + "learning_rate": 4.422074068991994e-05, + "loss": 1.6174, + "step": 9772 + }, + { + "epoch": 0.5447299481634246, + "grad_norm": 0.577524721622467, + "learning_rate": 4.4211896225313446e-05, + "loss": 1.666, + "step": 9773 + }, + { + "epoch": 0.5447856864165878, + "grad_norm": 0.566038191318512, + "learning_rate": 4.420305194427186e-05, + "loss": 1.7369, + "step": 9774 + }, + { + "epoch": 0.5448414246697508, + "grad_norm": 0.5815591216087341, + "learning_rate": 4.4194207847075655e-05, + "loss": 1.6213, + "step": 9775 + }, + { + "epoch": 0.544897162922914, + "grad_norm": 0.6219716668128967, + "learning_rate": 4.4185363934005346e-05, + "loss": 1.8705, + "step": 9776 + }, + { + "epoch": 0.5449529011760771, + "grad_norm": 0.5532581806182861, + "learning_rate": 4.417652020534137e-05, + "loss": 1.8517, + "step": 9777 + }, + { + "epoch": 0.5450086394292403, + "grad_norm": 0.5168758034706116, + "learning_rate": 4.416767666136422e-05, + "loss": 1.4589, + "step": 9778 + }, + { + "epoch": 0.5450643776824035, + "grad_norm": 0.5540144443511963, + "learning_rate": 4.415883330235438e-05, + "loss": 1.6545, + "step": 9779 + }, + { + "epoch": 0.5451201159355665, + "grad_norm": 0.5852721333503723, + "learning_rate": 4.4149990128592275e-05, + "loss": 1.951, + "step": 9780 + }, + { + "epoch": 0.5451758541887297, + "grad_norm": 0.5823214650154114, + "learning_rate": 4.41411471403584e-05, + "loss": 1.7445, + "step": 9781 + }, + { + "epoch": 0.5452315924418929, + "grad_norm": 0.7067981958389282, + "learning_rate": 4.413230433793315e-05, + "loss": 1.8898, + "step": 9782 + }, + { + "epoch": 0.545287330695056, + "grad_norm": 0.5201447010040283, + "learning_rate": 4.4123461721597016e-05, + "loss": 1.7319, + "step": 9783 + }, + { + "epoch": 0.5453430689482192, + "grad_norm": 0.5641838908195496, + "learning_rate": 4.41146192916304e-05, + "loss": 1.7698, + "step": 9784 + }, + { + "epoch": 0.5453988072013823, + "grad_norm": 0.6753969192504883, + "learning_rate": 4.4105777048313734e-05, + "loss": 1.8118, + "step": 9785 + }, + { + "epoch": 0.5454545454545454, + "grad_norm": 0.5199365019798279, + "learning_rate": 4.409693499192748e-05, + "loss": 1.6101, + "step": 9786 + }, + { + "epoch": 0.5455102837077086, + "grad_norm": 0.5644820928573608, + "learning_rate": 4.408809312275202e-05, + "loss": 1.55, + "step": 9787 + }, + { + "epoch": 0.5455660219608718, + "grad_norm": 0.5578990578651428, + "learning_rate": 4.407925144106778e-05, + "loss": 1.7077, + "step": 9788 + }, + { + "epoch": 0.5456217602140349, + "grad_norm": 0.5619536638259888, + "learning_rate": 4.4070409947155164e-05, + "loss": 1.736, + "step": 9789 + }, + { + "epoch": 0.545677498467198, + "grad_norm": 0.5421947836875916, + "learning_rate": 4.406156864129458e-05, + "loss": 1.5738, + "step": 9790 + }, + { + "epoch": 0.5457332367203612, + "grad_norm": 0.5277280211448669, + "learning_rate": 4.40527275237664e-05, + "loss": 1.6053, + "step": 9791 + }, + { + "epoch": 0.5457889749735243, + "grad_norm": 0.5307068228721619, + "learning_rate": 4.404388659485102e-05, + "loss": 1.3866, + "step": 9792 + }, + { + "epoch": 0.5458447132266875, + "grad_norm": 0.6040915250778198, + "learning_rate": 4.403504585482886e-05, + "loss": 1.8915, + "step": 9793 + }, + { + "epoch": 0.5459004514798507, + "grad_norm": 0.592362105846405, + "learning_rate": 4.402620530398024e-05, + "loss": 1.7637, + "step": 9794 + }, + { + "epoch": 0.5459561897330137, + "grad_norm": 0.5996968150138855, + "learning_rate": 4.401736494258559e-05, + "loss": 1.6987, + "step": 9795 + }, + { + "epoch": 0.5460119279861769, + "grad_norm": 0.5434197187423706, + "learning_rate": 4.400852477092521e-05, + "loss": 1.4462, + "step": 9796 + }, + { + "epoch": 0.5460676662393401, + "grad_norm": 0.5243266224861145, + "learning_rate": 4.399968478927949e-05, + "loss": 1.5191, + "step": 9797 + }, + { + "epoch": 0.5461234044925032, + "grad_norm": 0.5348801016807556, + "learning_rate": 4.399084499792882e-05, + "loss": 1.6671, + "step": 9798 + }, + { + "epoch": 0.5461791427456664, + "grad_norm": 0.5467276573181152, + "learning_rate": 4.398200539715348e-05, + "loss": 1.6921, + "step": 9799 + }, + { + "epoch": 0.5462348809988294, + "grad_norm": 0.5606840252876282, + "learning_rate": 4.397316598723385e-05, + "loss": 1.7919, + "step": 9800 + }, + { + "epoch": 0.5462906192519926, + "grad_norm": 0.6401974558830261, + "learning_rate": 4.396432676845026e-05, + "loss": 1.8814, + "step": 9801 + }, + { + "epoch": 0.5463463575051558, + "grad_norm": 0.5535458326339722, + "learning_rate": 4.395548774108304e-05, + "loss": 1.5737, + "step": 9802 + }, + { + "epoch": 0.5464020957583189, + "grad_norm": 0.5207072496414185, + "learning_rate": 4.3946648905412486e-05, + "loss": 1.6611, + "step": 9803 + }, + { + "epoch": 0.5464578340114821, + "grad_norm": 0.5882294178009033, + "learning_rate": 4.393781026171894e-05, + "loss": 1.7487, + "step": 9804 + }, + { + "epoch": 0.5465135722646453, + "grad_norm": 0.5833045244216919, + "learning_rate": 4.392897181028273e-05, + "loss": 1.5144, + "step": 9805 + }, + { + "epoch": 0.5465693105178083, + "grad_norm": 0.5518405437469482, + "learning_rate": 4.392013355138411e-05, + "loss": 1.4697, + "step": 9806 + }, + { + "epoch": 0.5466250487709715, + "grad_norm": 0.530725359916687, + "learning_rate": 4.391129548530343e-05, + "loss": 1.5778, + "step": 9807 + }, + { + "epoch": 0.5466807870241347, + "grad_norm": 0.5344696640968323, + "learning_rate": 4.390245761232094e-05, + "loss": 1.692, + "step": 9808 + }, + { + "epoch": 0.5467365252772978, + "grad_norm": 0.5627099275588989, + "learning_rate": 4.389361993271696e-05, + "loss": 1.6905, + "step": 9809 + }, + { + "epoch": 0.546792263530461, + "grad_norm": 0.5395922660827637, + "learning_rate": 4.388478244677174e-05, + "loss": 1.6399, + "step": 9810 + }, + { + "epoch": 0.5468480017836241, + "grad_norm": 0.5499055981636047, + "learning_rate": 4.387594515476555e-05, + "loss": 1.6705, + "step": 9811 + }, + { + "epoch": 0.5469037400367872, + "grad_norm": 0.5418950319290161, + "learning_rate": 4.386710805697871e-05, + "loss": 1.2681, + "step": 9812 + }, + { + "epoch": 0.5469594782899504, + "grad_norm": 0.6052936315536499, + "learning_rate": 4.385827115369142e-05, + "loss": 1.7306, + "step": 9813 + }, + { + "epoch": 0.5470152165431136, + "grad_norm": 0.5980737805366516, + "learning_rate": 4.3849434445183977e-05, + "loss": 1.7266, + "step": 9814 + }, + { + "epoch": 0.5470709547962767, + "grad_norm": 0.610704243183136, + "learning_rate": 4.38405979317366e-05, + "loss": 1.7676, + "step": 9815 + }, + { + "epoch": 0.5471266930494398, + "grad_norm": 0.5389671921730042, + "learning_rate": 4.383176161362956e-05, + "loss": 1.5504, + "step": 9816 + }, + { + "epoch": 0.547182431302603, + "grad_norm": 0.540878415107727, + "learning_rate": 4.382292549114306e-05, + "loss": 1.5915, + "step": 9817 + }, + { + "epoch": 0.5472381695557661, + "grad_norm": 0.5596631765365601, + "learning_rate": 4.381408956455734e-05, + "loss": 1.7682, + "step": 9818 + }, + { + "epoch": 0.5472939078089293, + "grad_norm": 0.5934588313102722, + "learning_rate": 4.380525383415267e-05, + "loss": 1.7587, + "step": 9819 + }, + { + "epoch": 0.5473496460620925, + "grad_norm": 0.5937252044677734, + "learning_rate": 4.3796418300209194e-05, + "loss": 1.8327, + "step": 9820 + }, + { + "epoch": 0.5474053843152555, + "grad_norm": 0.5708996057510376, + "learning_rate": 4.378758296300719e-05, + "loss": 1.7339, + "step": 9821 + }, + { + "epoch": 0.5474611225684187, + "grad_norm": 0.5516582727432251, + "learning_rate": 4.377874782282681e-05, + "loss": 1.7792, + "step": 9822 + }, + { + "epoch": 0.5475168608215818, + "grad_norm": 0.5492805242538452, + "learning_rate": 4.376991287994829e-05, + "loss": 1.5596, + "step": 9823 + }, + { + "epoch": 0.547572599074745, + "grad_norm": 0.5498988628387451, + "learning_rate": 4.376107813465181e-05, + "loss": 1.5048, + "step": 9824 + }, + { + "epoch": 0.5476283373279082, + "grad_norm": 0.5600182414054871, + "learning_rate": 4.3752243587217546e-05, + "loss": 1.6238, + "step": 9825 + }, + { + "epoch": 0.5476840755810712, + "grad_norm": 0.6144223213195801, + "learning_rate": 4.37434092379257e-05, + "loss": 1.5942, + "step": 9826 + }, + { + "epoch": 0.5477398138342344, + "grad_norm": 0.580475389957428, + "learning_rate": 4.3734575087056425e-05, + "loss": 1.6875, + "step": 9827 + }, + { + "epoch": 0.5477955520873976, + "grad_norm": 0.5507834553718567, + "learning_rate": 4.372574113488991e-05, + "loss": 1.4169, + "step": 9828 + }, + { + "epoch": 0.5478512903405607, + "grad_norm": 0.6568073034286499, + "learning_rate": 4.371690738170628e-05, + "loss": 1.7524, + "step": 9829 + }, + { + "epoch": 0.5479070285937239, + "grad_norm": 0.5925707817077637, + "learning_rate": 4.370807382778573e-05, + "loss": 1.859, + "step": 9830 + }, + { + "epoch": 0.547962766846887, + "grad_norm": 0.5850409269332886, + "learning_rate": 4.36992404734084e-05, + "loss": 1.4963, + "step": 9831 + }, + { + "epoch": 0.5480185051000501, + "grad_norm": 0.5406137108802795, + "learning_rate": 4.3690407318854416e-05, + "loss": 1.4895, + "step": 9832 + }, + { + "epoch": 0.5480742433532133, + "grad_norm": 0.5430670380592346, + "learning_rate": 4.3681574364403936e-05, + "loss": 1.6322, + "step": 9833 + }, + { + "epoch": 0.5481299816063765, + "grad_norm": 0.5720853805541992, + "learning_rate": 4.367274161033707e-05, + "loss": 1.5524, + "step": 9834 + }, + { + "epoch": 0.5481857198595396, + "grad_norm": 0.5545953512191772, + "learning_rate": 4.366390905693396e-05, + "loss": 1.5659, + "step": 9835 + }, + { + "epoch": 0.5482414581127028, + "grad_norm": 0.5208585858345032, + "learning_rate": 4.36550767044747e-05, + "loss": 1.5188, + "step": 9836 + }, + { + "epoch": 0.5482971963658659, + "grad_norm": 0.5306513905525208, + "learning_rate": 4.36462445532394e-05, + "loss": 1.6353, + "step": 9837 + }, + { + "epoch": 0.548352934619029, + "grad_norm": 0.5258748531341553, + "learning_rate": 4.3637412603508206e-05, + "loss": 1.6311, + "step": 9838 + }, + { + "epoch": 0.5484086728721922, + "grad_norm": 0.5057768821716309, + "learning_rate": 4.3628580855561176e-05, + "loss": 1.5426, + "step": 9839 + }, + { + "epoch": 0.5484644111253554, + "grad_norm": 0.5385904312133789, + "learning_rate": 4.361974930967842e-05, + "loss": 1.7261, + "step": 9840 + }, + { + "epoch": 0.5485201493785185, + "grad_norm": 0.5567389726638794, + "learning_rate": 4.361091796614001e-05, + "loss": 1.6934, + "step": 9841 + }, + { + "epoch": 0.5485758876316816, + "grad_norm": 0.5337814092636108, + "learning_rate": 4.360208682522603e-05, + "loss": 1.6504, + "step": 9842 + }, + { + "epoch": 0.5486316258848448, + "grad_norm": 0.5739735960960388, + "learning_rate": 4.3593255887216555e-05, + "loss": 1.5194, + "step": 9843 + }, + { + "epoch": 0.5486873641380079, + "grad_norm": 0.5616000890731812, + "learning_rate": 4.358442515239164e-05, + "loss": 1.7104, + "step": 9844 + }, + { + "epoch": 0.5487431023911711, + "grad_norm": 0.5667536854743958, + "learning_rate": 4.357559462103138e-05, + "loss": 1.547, + "step": 9845 + }, + { + "epoch": 0.5487988406443342, + "grad_norm": 0.5744796991348267, + "learning_rate": 4.3566764293415776e-05, + "loss": 1.675, + "step": 9846 + }, + { + "epoch": 0.5488545788974973, + "grad_norm": 0.5584723353385925, + "learning_rate": 4.355793416982492e-05, + "loss": 1.6043, + "step": 9847 + }, + { + "epoch": 0.5489103171506605, + "grad_norm": 0.5384577512741089, + "learning_rate": 4.354910425053881e-05, + "loss": 1.7647, + "step": 9848 + }, + { + "epoch": 0.5489660554038236, + "grad_norm": 0.5378496646881104, + "learning_rate": 4.3540274535837524e-05, + "loss": 1.5597, + "step": 9849 + }, + { + "epoch": 0.5490217936569868, + "grad_norm": 0.5346800088882446, + "learning_rate": 4.353144502600105e-05, + "loss": 1.6489, + "step": 9850 + }, + { + "epoch": 0.54907753191015, + "grad_norm": 0.5737703442573547, + "learning_rate": 4.3522615721309436e-05, + "loss": 1.7917, + "step": 9851 + }, + { + "epoch": 0.549133270163313, + "grad_norm": 0.5731632113456726, + "learning_rate": 4.3513786622042685e-05, + "loss": 1.7261, + "step": 9852 + }, + { + "epoch": 0.5491890084164762, + "grad_norm": 0.5530697107315063, + "learning_rate": 4.35049577284808e-05, + "loss": 1.6477, + "step": 9853 + }, + { + "epoch": 0.5492447466696394, + "grad_norm": 0.5312392711639404, + "learning_rate": 4.3496129040903795e-05, + "loss": 1.5079, + "step": 9854 + }, + { + "epoch": 0.5493004849228025, + "grad_norm": 0.5439527630805969, + "learning_rate": 4.348730055959164e-05, + "loss": 1.6616, + "step": 9855 + }, + { + "epoch": 0.5493562231759657, + "grad_norm": 0.6246342062950134, + "learning_rate": 4.3478472284824346e-05, + "loss": 1.8967, + "step": 9856 + }, + { + "epoch": 0.5494119614291288, + "grad_norm": 0.5579057335853577, + "learning_rate": 4.3469644216881893e-05, + "loss": 1.8138, + "step": 9857 + }, + { + "epoch": 0.5494676996822919, + "grad_norm": 0.5730265378952026, + "learning_rate": 4.346081635604425e-05, + "loss": 1.6882, + "step": 9858 + }, + { + "epoch": 0.5495234379354551, + "grad_norm": 0.6028726696968079, + "learning_rate": 4.34519887025914e-05, + "loss": 1.8155, + "step": 9859 + }, + { + "epoch": 0.5495791761886183, + "grad_norm": 0.5326104164123535, + "learning_rate": 4.3443161256803264e-05, + "loss": 1.5754, + "step": 9860 + }, + { + "epoch": 0.5496349144417814, + "grad_norm": 0.5944668650627136, + "learning_rate": 4.343433401895984e-05, + "loss": 1.6735, + "step": 9861 + }, + { + "epoch": 0.5496906526949445, + "grad_norm": 0.5546173453330994, + "learning_rate": 4.342550698934106e-05, + "loss": 1.5815, + "step": 9862 + }, + { + "epoch": 0.5497463909481077, + "grad_norm": 0.5735986232757568, + "learning_rate": 4.3416680168226855e-05, + "loss": 1.5027, + "step": 9863 + }, + { + "epoch": 0.5498021292012708, + "grad_norm": 0.5421950817108154, + "learning_rate": 4.340785355589718e-05, + "loss": 1.6578, + "step": 9864 + }, + { + "epoch": 0.549857867454434, + "grad_norm": 0.5298879146575928, + "learning_rate": 4.339902715263195e-05, + "loss": 1.4347, + "step": 9865 + }, + { + "epoch": 0.5499136057075972, + "grad_norm": 0.574774444103241, + "learning_rate": 4.339020095871111e-05, + "loss": 1.6696, + "step": 9866 + }, + { + "epoch": 0.5499693439607602, + "grad_norm": 0.5394953489303589, + "learning_rate": 4.338137497441454e-05, + "loss": 1.6238, + "step": 9867 + }, + { + "epoch": 0.5500250822139234, + "grad_norm": 0.574478030204773, + "learning_rate": 4.337254920002218e-05, + "loss": 1.6317, + "step": 9868 + }, + { + "epoch": 0.5500808204670865, + "grad_norm": 0.5428669452667236, + "learning_rate": 4.336372363581391e-05, + "loss": 1.4349, + "step": 9869 + }, + { + "epoch": 0.5501365587202497, + "grad_norm": 0.49491697549819946, + "learning_rate": 4.3354898282069624e-05, + "loss": 1.4318, + "step": 9870 + }, + { + "epoch": 0.5501922969734129, + "grad_norm": 0.5415276288986206, + "learning_rate": 4.3346073139069245e-05, + "loss": 1.7328, + "step": 9871 + }, + { + "epoch": 0.550248035226576, + "grad_norm": 0.5677903890609741, + "learning_rate": 4.3337248207092604e-05, + "loss": 1.6179, + "step": 9872 + }, + { + "epoch": 0.5503037734797391, + "grad_norm": 0.544323742389679, + "learning_rate": 4.332842348641962e-05, + "loss": 1.7354, + "step": 9873 + }, + { + "epoch": 0.5503595117329023, + "grad_norm": 0.5574266910552979, + "learning_rate": 4.331959897733015e-05, + "loss": 1.4075, + "step": 9874 + }, + { + "epoch": 0.5504152499860654, + "grad_norm": 0.566932201385498, + "learning_rate": 4.3310774680104045e-05, + "loss": 1.7368, + "step": 9875 + }, + { + "epoch": 0.5504709882392286, + "grad_norm": 0.5502132773399353, + "learning_rate": 4.330195059502116e-05, + "loss": 1.6125, + "step": 9876 + }, + { + "epoch": 0.5505267264923918, + "grad_norm": 0.5705932974815369, + "learning_rate": 4.329312672236136e-05, + "loss": 1.5961, + "step": 9877 + }, + { + "epoch": 0.5505824647455548, + "grad_norm": 0.5607555508613586, + "learning_rate": 4.328430306240447e-05, + "loss": 1.7871, + "step": 9878 + }, + { + "epoch": 0.550638202998718, + "grad_norm": 0.5171093344688416, + "learning_rate": 4.327547961543032e-05, + "loss": 1.6864, + "step": 9879 + }, + { + "epoch": 0.5506939412518812, + "grad_norm": 0.5639234185218811, + "learning_rate": 4.3266656381718776e-05, + "loss": 1.503, + "step": 9880 + }, + { + "epoch": 0.5507496795050443, + "grad_norm": 0.5581746697425842, + "learning_rate": 4.325783336154961e-05, + "loss": 1.6596, + "step": 9881 + }, + { + "epoch": 0.5508054177582075, + "grad_norm": 0.5529181957244873, + "learning_rate": 4.324901055520266e-05, + "loss": 1.5023, + "step": 9882 + }, + { + "epoch": 0.5508611560113706, + "grad_norm": 0.5628426671028137, + "learning_rate": 4.324018796295776e-05, + "loss": 1.6991, + "step": 9883 + }, + { + "epoch": 0.5509168942645337, + "grad_norm": 0.6470309495925903, + "learning_rate": 4.323136558509466e-05, + "loss": 1.5738, + "step": 9884 + }, + { + "epoch": 0.5509726325176969, + "grad_norm": 0.5868264436721802, + "learning_rate": 4.3222543421893205e-05, + "loss": 1.8939, + "step": 9885 + }, + { + "epoch": 0.5510283707708601, + "grad_norm": 0.5328113436698914, + "learning_rate": 4.3213721473633136e-05, + "loss": 1.3017, + "step": 9886 + }, + { + "epoch": 0.5510841090240232, + "grad_norm": 0.5659006237983704, + "learning_rate": 4.320489974059426e-05, + "loss": 1.6982, + "step": 9887 + }, + { + "epoch": 0.5511398472771863, + "grad_norm": 0.5908814072608948, + "learning_rate": 4.3196078223056346e-05, + "loss": 1.75, + "step": 9888 + }, + { + "epoch": 0.5511955855303495, + "grad_norm": 0.5215436220169067, + "learning_rate": 4.3187256921299155e-05, + "loss": 1.6721, + "step": 9889 + }, + { + "epoch": 0.5512513237835126, + "grad_norm": 0.5671520233154297, + "learning_rate": 4.317843583560246e-05, + "loss": 1.6611, + "step": 9890 + }, + { + "epoch": 0.5513070620366758, + "grad_norm": 0.568788468837738, + "learning_rate": 4.316961496624601e-05, + "loss": 1.5042, + "step": 9891 + }, + { + "epoch": 0.5513628002898389, + "grad_norm": 0.5743429064750671, + "learning_rate": 4.316079431350956e-05, + "loss": 1.5001, + "step": 9892 + }, + { + "epoch": 0.551418538543002, + "grad_norm": 0.5083088278770447, + "learning_rate": 4.3151973877672815e-05, + "loss": 1.3369, + "step": 9893 + }, + { + "epoch": 0.5514742767961652, + "grad_norm": 0.5570357441902161, + "learning_rate": 4.314315365901555e-05, + "loss": 1.7525, + "step": 9894 + }, + { + "epoch": 0.5515300150493283, + "grad_norm": 0.5853736400604248, + "learning_rate": 4.3134333657817464e-05, + "loss": 1.7689, + "step": 9895 + }, + { + "epoch": 0.5515857533024915, + "grad_norm": 0.5641288161277771, + "learning_rate": 4.312551387435827e-05, + "loss": 1.8022, + "step": 9896 + }, + { + "epoch": 0.5516414915556547, + "grad_norm": 0.5889329314231873, + "learning_rate": 4.311669430891773e-05, + "loss": 1.7209, + "step": 9897 + }, + { + "epoch": 0.5516972298088177, + "grad_norm": 0.5651081800460815, + "learning_rate": 4.310787496177548e-05, + "loss": 1.6729, + "step": 9898 + }, + { + "epoch": 0.5517529680619809, + "grad_norm": 0.5457670092582703, + "learning_rate": 4.309905583321128e-05, + "loss": 1.4496, + "step": 9899 + }, + { + "epoch": 0.5518087063151441, + "grad_norm": 0.5131945013999939, + "learning_rate": 4.309023692350478e-05, + "loss": 1.5063, + "step": 9900 + }, + { + "epoch": 0.5518644445683072, + "grad_norm": 0.5401031374931335, + "learning_rate": 4.3081418232935687e-05, + "loss": 1.5095, + "step": 9901 + }, + { + "epoch": 0.5519201828214704, + "grad_norm": 0.6112632155418396, + "learning_rate": 4.3072599761783664e-05, + "loss": 1.7476, + "step": 9902 + }, + { + "epoch": 0.5519759210746336, + "grad_norm": 0.5150609612464905, + "learning_rate": 4.306378151032838e-05, + "loss": 1.3913, + "step": 9903 + }, + { + "epoch": 0.5520316593277966, + "grad_norm": 0.5849746465682983, + "learning_rate": 4.3054963478849517e-05, + "loss": 1.6125, + "step": 9904 + }, + { + "epoch": 0.5520873975809598, + "grad_norm": 0.6250925064086914, + "learning_rate": 4.30461456676267e-05, + "loss": 1.8131, + "step": 9905 + }, + { + "epoch": 0.552143135834123, + "grad_norm": 0.49495401978492737, + "learning_rate": 4.303732807693963e-05, + "loss": 1.4352, + "step": 9906 + }, + { + "epoch": 0.5521988740872861, + "grad_norm": 0.6217641234397888, + "learning_rate": 4.3028510707067885e-05, + "loss": 1.9657, + "step": 9907 + }, + { + "epoch": 0.5522546123404493, + "grad_norm": 0.6217669248580933, + "learning_rate": 4.3019693558291144e-05, + "loss": 1.8648, + "step": 9908 + }, + { + "epoch": 0.5523103505936124, + "grad_norm": 0.5340979099273682, + "learning_rate": 4.301087663088904e-05, + "loss": 1.4133, + "step": 9909 + }, + { + "epoch": 0.5523660888467755, + "grad_norm": 0.5489256381988525, + "learning_rate": 4.300205992514117e-05, + "loss": 1.8159, + "step": 9910 + }, + { + "epoch": 0.5524218270999387, + "grad_norm": 0.5621556639671326, + "learning_rate": 4.299324344132717e-05, + "loss": 1.7179, + "step": 9911 + }, + { + "epoch": 0.5524775653531019, + "grad_norm": 0.5325203537940979, + "learning_rate": 4.298442717972662e-05, + "loss": 1.6968, + "step": 9912 + }, + { + "epoch": 0.552533303606265, + "grad_norm": 0.5561079978942871, + "learning_rate": 4.297561114061915e-05, + "loss": 1.6225, + "step": 9913 + }, + { + "epoch": 0.5525890418594281, + "grad_norm": 0.566832423210144, + "learning_rate": 4.2966795324284324e-05, + "loss": 1.4759, + "step": 9914 + }, + { + "epoch": 0.5526447801125912, + "grad_norm": 0.647016167640686, + "learning_rate": 4.295797973100174e-05, + "loss": 1.456, + "step": 9915 + }, + { + "epoch": 0.5527005183657544, + "grad_norm": 0.5589674711227417, + "learning_rate": 4.2949164361051e-05, + "loss": 1.625, + "step": 9916 + }, + { + "epoch": 0.5527562566189176, + "grad_norm": 0.5907155275344849, + "learning_rate": 4.294034921471164e-05, + "loss": 1.3695, + "step": 9917 + }, + { + "epoch": 0.5528119948720807, + "grad_norm": 0.6016174554824829, + "learning_rate": 4.2931534292263264e-05, + "loss": 1.748, + "step": 9918 + }, + { + "epoch": 0.5528677331252438, + "grad_norm": 0.593099057674408, + "learning_rate": 4.292271959398539e-05, + "loss": 1.7037, + "step": 9919 + }, + { + "epoch": 0.552923471378407, + "grad_norm": 0.6433031558990479, + "learning_rate": 4.2913905120157596e-05, + "loss": 1.9699, + "step": 9920 + }, + { + "epoch": 0.5529792096315701, + "grad_norm": 0.5927780270576477, + "learning_rate": 4.290509087105942e-05, + "loss": 1.7382, + "step": 9921 + }, + { + "epoch": 0.5530349478847333, + "grad_norm": 0.5874158143997192, + "learning_rate": 4.289627684697037e-05, + "loss": 1.5503, + "step": 9922 + }, + { + "epoch": 0.5530906861378965, + "grad_norm": 0.5684481263160706, + "learning_rate": 4.288746304817004e-05, + "loss": 1.3335, + "step": 9923 + }, + { + "epoch": 0.5531464243910595, + "grad_norm": 0.6145278811454773, + "learning_rate": 4.287864947493788e-05, + "loss": 1.9235, + "step": 9924 + }, + { + "epoch": 0.5532021626442227, + "grad_norm": 0.5604020953178406, + "learning_rate": 4.286983612755345e-05, + "loss": 1.7431, + "step": 9925 + }, + { + "epoch": 0.5532579008973859, + "grad_norm": 0.5660736560821533, + "learning_rate": 4.2861023006296245e-05, + "loss": 1.6642, + "step": 9926 + }, + { + "epoch": 0.553313639150549, + "grad_norm": 0.5653099417686462, + "learning_rate": 4.285221011144578e-05, + "loss": 1.5847, + "step": 9927 + }, + { + "epoch": 0.5533693774037122, + "grad_norm": 0.5528052449226379, + "learning_rate": 4.284339744328152e-05, + "loss": 1.6667, + "step": 9928 + }, + { + "epoch": 0.5534251156568754, + "grad_norm": 0.5655755996704102, + "learning_rate": 4.283458500208297e-05, + "loss": 1.6661, + "step": 9929 + }, + { + "epoch": 0.5534808539100384, + "grad_norm": 0.5706286430358887, + "learning_rate": 4.282577278812962e-05, + "loss": 1.57, + "step": 9930 + }, + { + "epoch": 0.5535365921632016, + "grad_norm": 0.5573133230209351, + "learning_rate": 4.28169608017009e-05, + "loss": 1.6694, + "step": 9931 + }, + { + "epoch": 0.5535923304163648, + "grad_norm": 0.5579492449760437, + "learning_rate": 4.2808149043076337e-05, + "loss": 1.8431, + "step": 9932 + }, + { + "epoch": 0.5536480686695279, + "grad_norm": 0.5701257586479187, + "learning_rate": 4.279933751253533e-05, + "loss": 1.7697, + "step": 9933 + }, + { + "epoch": 0.553703806922691, + "grad_norm": 0.586942195892334, + "learning_rate": 4.279052621035738e-05, + "loss": 1.6883, + "step": 9934 + }, + { + "epoch": 0.5537595451758542, + "grad_norm": 0.6071811318397522, + "learning_rate": 4.2781715136821874e-05, + "loss": 1.88, + "step": 9935 + }, + { + "epoch": 0.5538152834290173, + "grad_norm": 0.6040579080581665, + "learning_rate": 4.277290429220829e-05, + "loss": 1.9303, + "step": 9936 + }, + { + "epoch": 0.5538710216821805, + "grad_norm": 0.554654598236084, + "learning_rate": 4.276409367679605e-05, + "loss": 1.7339, + "step": 9937 + }, + { + "epoch": 0.5539267599353436, + "grad_norm": 0.5604990720748901, + "learning_rate": 4.275528329086457e-05, + "loss": 1.8366, + "step": 9938 + }, + { + "epoch": 0.5539824981885068, + "grad_norm": 0.5396780967712402, + "learning_rate": 4.274647313469326e-05, + "loss": 1.5683, + "step": 9939 + }, + { + "epoch": 0.5540382364416699, + "grad_norm": 0.5582244396209717, + "learning_rate": 4.273766320856152e-05, + "loss": 1.7331, + "step": 9940 + }, + { + "epoch": 0.554093974694833, + "grad_norm": 0.5684306621551514, + "learning_rate": 4.2728853512748774e-05, + "loss": 1.6732, + "step": 9941 + }, + { + "epoch": 0.5541497129479962, + "grad_norm": 0.5707295536994934, + "learning_rate": 4.272004404753441e-05, + "loss": 1.7369, + "step": 9942 + }, + { + "epoch": 0.5542054512011594, + "grad_norm": 0.5841218829154968, + "learning_rate": 4.271123481319779e-05, + "loss": 1.5369, + "step": 9943 + }, + { + "epoch": 0.5542611894543225, + "grad_norm": 0.5583487749099731, + "learning_rate": 4.2702425810018314e-05, + "loss": 1.9257, + "step": 9944 + }, + { + "epoch": 0.5543169277074856, + "grad_norm": 0.6115777492523193, + "learning_rate": 4.269361703827533e-05, + "loss": 1.6092, + "step": 9945 + }, + { + "epoch": 0.5543726659606488, + "grad_norm": 0.5527899861335754, + "learning_rate": 4.268480849824824e-05, + "loss": 1.5267, + "step": 9946 + }, + { + "epoch": 0.5544284042138119, + "grad_norm": 0.5732879638671875, + "learning_rate": 4.2676000190216355e-05, + "loss": 1.7716, + "step": 9947 + }, + { + "epoch": 0.5544841424669751, + "grad_norm": 0.5747142434120178, + "learning_rate": 4.266719211445903e-05, + "loss": 1.5671, + "step": 9948 + }, + { + "epoch": 0.5545398807201383, + "grad_norm": 0.5483896136283875, + "learning_rate": 4.265838427125565e-05, + "loss": 1.68, + "step": 9949 + }, + { + "epoch": 0.5545956189733013, + "grad_norm": 0.5686975121498108, + "learning_rate": 4.2649576660885484e-05, + "loss": 1.6753, + "step": 9950 + }, + { + "epoch": 0.5546513572264645, + "grad_norm": 0.5398499965667725, + "learning_rate": 4.264076928362791e-05, + "loss": 1.4447, + "step": 9951 + }, + { + "epoch": 0.5547070954796277, + "grad_norm": 0.5364631414413452, + "learning_rate": 4.2631962139762216e-05, + "loss": 1.6929, + "step": 9952 + }, + { + "epoch": 0.5547628337327908, + "grad_norm": 0.6317248940467834, + "learning_rate": 4.262315522956774e-05, + "loss": 1.3731, + "step": 9953 + }, + { + "epoch": 0.554818571985954, + "grad_norm": 0.5127749443054199, + "learning_rate": 4.261434855332376e-05, + "loss": 1.4813, + "step": 9954 + }, + { + "epoch": 0.5548743102391172, + "grad_norm": 0.5657464861869812, + "learning_rate": 4.2605542111309574e-05, + "loss": 1.7245, + "step": 9955 + }, + { + "epoch": 0.5549300484922802, + "grad_norm": 0.5313467979431152, + "learning_rate": 4.25967359038045e-05, + "loss": 1.6008, + "step": 9956 + }, + { + "epoch": 0.5549857867454434, + "grad_norm": 0.5843843817710876, + "learning_rate": 4.258792993108777e-05, + "loss": 1.483, + "step": 9957 + }, + { + "epoch": 0.5550415249986066, + "grad_norm": 0.5298835635185242, + "learning_rate": 4.257912419343872e-05, + "loss": 1.7526, + "step": 9958 + }, + { + "epoch": 0.5550972632517697, + "grad_norm": 0.5512775182723999, + "learning_rate": 4.257031869113656e-05, + "loss": 1.593, + "step": 9959 + }, + { + "epoch": 0.5551530015049329, + "grad_norm": 0.5587732791900635, + "learning_rate": 4.256151342446059e-05, + "loss": 1.6164, + "step": 9960 + }, + { + "epoch": 0.5552087397580959, + "grad_norm": 0.5447744727134705, + "learning_rate": 4.255270839369003e-05, + "loss": 1.4945, + "step": 9961 + }, + { + "epoch": 0.5552644780112591, + "grad_norm": 0.6091803908348083, + "learning_rate": 4.254390359910414e-05, + "loss": 1.7595, + "step": 9962 + }, + { + "epoch": 0.5553202162644223, + "grad_norm": 0.5939117074012756, + "learning_rate": 4.2535099040982174e-05, + "loss": 1.6638, + "step": 9963 + }, + { + "epoch": 0.5553759545175854, + "grad_norm": 0.5523215532302856, + "learning_rate": 4.252629471960332e-05, + "loss": 1.6403, + "step": 9964 + }, + { + "epoch": 0.5554316927707486, + "grad_norm": 0.5710287690162659, + "learning_rate": 4.251749063524684e-05, + "loss": 1.7287, + "step": 9965 + }, + { + "epoch": 0.5554874310239117, + "grad_norm": 0.5372434854507446, + "learning_rate": 4.2508686788191917e-05, + "loss": 1.4819, + "step": 9966 + }, + { + "epoch": 0.5555431692770748, + "grad_norm": 0.5489197373390198, + "learning_rate": 4.249988317871777e-05, + "loss": 1.6855, + "step": 9967 + }, + { + "epoch": 0.555598907530238, + "grad_norm": 0.56691974401474, + "learning_rate": 4.249107980710362e-05, + "loss": 1.6364, + "step": 9968 + }, + { + "epoch": 0.5556546457834012, + "grad_norm": 0.5599048733711243, + "learning_rate": 4.2482276673628626e-05, + "loss": 1.6847, + "step": 9969 + }, + { + "epoch": 0.5557103840365643, + "grad_norm": 0.5381473302841187, + "learning_rate": 4.247347377857199e-05, + "loss": 1.5898, + "step": 9970 + }, + { + "epoch": 0.5557661222897274, + "grad_norm": 0.5331934094429016, + "learning_rate": 4.2464671122212876e-05, + "loss": 1.7209, + "step": 9971 + }, + { + "epoch": 0.5558218605428906, + "grad_norm": 0.593131959438324, + "learning_rate": 4.245586870483047e-05, + "loss": 1.9442, + "step": 9972 + }, + { + "epoch": 0.5558775987960537, + "grad_norm": 0.5709297060966492, + "learning_rate": 4.2447066526703914e-05, + "loss": 1.6745, + "step": 9973 + }, + { + "epoch": 0.5559333370492169, + "grad_norm": 0.5793182849884033, + "learning_rate": 4.2438264588112354e-05, + "loss": 1.7414, + "step": 9974 + }, + { + "epoch": 0.5559890753023801, + "grad_norm": 0.5524191856384277, + "learning_rate": 4.242946288933499e-05, + "loss": 1.654, + "step": 9975 + }, + { + "epoch": 0.5560448135555431, + "grad_norm": 0.5401830077171326, + "learning_rate": 4.2420661430650895e-05, + "loss": 1.8102, + "step": 9976 + }, + { + "epoch": 0.5561005518087063, + "grad_norm": 0.5864329934120178, + "learning_rate": 4.241186021233925e-05, + "loss": 1.6475, + "step": 9977 + }, + { + "epoch": 0.5561562900618695, + "grad_norm": 0.688472330570221, + "learning_rate": 4.240305923467914e-05, + "loss": 2.1339, + "step": 9978 + }, + { + "epoch": 0.5562120283150326, + "grad_norm": 0.5475722551345825, + "learning_rate": 4.239425849794971e-05, + "loss": 1.6901, + "step": 9979 + }, + { + "epoch": 0.5562677665681958, + "grad_norm": 0.5240103602409363, + "learning_rate": 4.238545800243005e-05, + "loss": 1.3724, + "step": 9980 + }, + { + "epoch": 0.556323504821359, + "grad_norm": 0.5475266575813293, + "learning_rate": 4.237665774839926e-05, + "loss": 1.6478, + "step": 9981 + }, + { + "epoch": 0.556379243074522, + "grad_norm": 0.5561927556991577, + "learning_rate": 4.236785773613646e-05, + "loss": 1.8298, + "step": 9982 + }, + { + "epoch": 0.5564349813276852, + "grad_norm": 0.568395733833313, + "learning_rate": 4.2359057965920684e-05, + "loss": 1.5858, + "step": 9983 + }, + { + "epoch": 0.5564907195808483, + "grad_norm": 0.5727097988128662, + "learning_rate": 4.235025843803108e-05, + "loss": 1.7207, + "step": 9984 + }, + { + "epoch": 0.5565464578340115, + "grad_norm": 0.5476745963096619, + "learning_rate": 4.234145915274663e-05, + "loss": 1.6093, + "step": 9985 + }, + { + "epoch": 0.5566021960871746, + "grad_norm": 0.5828372240066528, + "learning_rate": 4.233266011034648e-05, + "loss": 1.6445, + "step": 9986 + }, + { + "epoch": 0.5566579343403377, + "grad_norm": 0.532822847366333, + "learning_rate": 4.232386131110963e-05, + "loss": 1.5421, + "step": 9987 + }, + { + "epoch": 0.5567136725935009, + "grad_norm": 0.6059979200363159, + "learning_rate": 4.231506275531514e-05, + "loss": 1.7904, + "step": 9988 + }, + { + "epoch": 0.5567694108466641, + "grad_norm": 0.5532347559928894, + "learning_rate": 4.230626444324207e-05, + "loss": 1.8607, + "step": 9989 + }, + { + "epoch": 0.5568251490998272, + "grad_norm": 0.5815007090568542, + "learning_rate": 4.2297466375169425e-05, + "loss": 1.6841, + "step": 9990 + }, + { + "epoch": 0.5568808873529904, + "grad_norm": 0.5533902049064636, + "learning_rate": 4.2288668551376246e-05, + "loss": 1.5424, + "step": 9991 + }, + { + "epoch": 0.5569366256061535, + "grad_norm": 0.5605874061584473, + "learning_rate": 4.2279870972141516e-05, + "loss": 1.7097, + "step": 9992 + }, + { + "epoch": 0.5569923638593166, + "grad_norm": 0.6050384640693665, + "learning_rate": 4.227107363774429e-05, + "loss": 1.6374, + "step": 9993 + }, + { + "epoch": 0.5570481021124798, + "grad_norm": 0.5556758046150208, + "learning_rate": 4.226227654846354e-05, + "loss": 1.6, + "step": 9994 + }, + { + "epoch": 0.557103840365643, + "grad_norm": 0.544030487537384, + "learning_rate": 4.2253479704578255e-05, + "loss": 1.5008, + "step": 9995 + }, + { + "epoch": 0.557159578618806, + "grad_norm": 0.5751504898071289, + "learning_rate": 4.224468310636745e-05, + "loss": 1.6418, + "step": 9996 + }, + { + "epoch": 0.5572153168719692, + "grad_norm": 0.5826640725135803, + "learning_rate": 4.223588675411007e-05, + "loss": 1.8126, + "step": 9997 + }, + { + "epoch": 0.5572710551251324, + "grad_norm": 0.5713084936141968, + "learning_rate": 4.222709064808509e-05, + "loss": 1.7107, + "step": 9998 + }, + { + "epoch": 0.5573267933782955, + "grad_norm": 0.5925366878509521, + "learning_rate": 4.221829478857148e-05, + "loss": 1.6814, + "step": 9999 + }, + { + "epoch": 0.5573825316314587, + "grad_norm": 0.5469158291816711, + "learning_rate": 4.220949917584817e-05, + "loss": 1.7406, + "step": 10000 + }, + { + "epoch": 0.5574382698846219, + "grad_norm": 0.5660231709480286, + "learning_rate": 4.2200703810194155e-05, + "loss": 1.6824, + "step": 10001 + }, + { + "epoch": 0.5574940081377849, + "grad_norm": 0.6542315483093262, + "learning_rate": 4.219190869188831e-05, + "loss": 1.6746, + "step": 10002 + }, + { + "epoch": 0.5575497463909481, + "grad_norm": 0.5918342471122742, + "learning_rate": 4.2183113821209625e-05, + "loss": 1.9145, + "step": 10003 + }, + { + "epoch": 0.5576054846441113, + "grad_norm": 0.5502055883407593, + "learning_rate": 4.2174319198436976e-05, + "loss": 1.6127, + "step": 10004 + }, + { + "epoch": 0.5576612228972744, + "grad_norm": 0.523463249206543, + "learning_rate": 4.216552482384931e-05, + "loss": 1.6454, + "step": 10005 + }, + { + "epoch": 0.5577169611504376, + "grad_norm": 0.6080988645553589, + "learning_rate": 4.215673069772551e-05, + "loss": 1.7028, + "step": 10006 + }, + { + "epoch": 0.5577726994036006, + "grad_norm": 0.5708165764808655, + "learning_rate": 4.214793682034448e-05, + "loss": 1.7396, + "step": 10007 + }, + { + "epoch": 0.5578284376567638, + "grad_norm": 0.657543420791626, + "learning_rate": 4.213914319198512e-05, + "loss": 1.9985, + "step": 10008 + }, + { + "epoch": 0.557884175909927, + "grad_norm": 0.5319724082946777, + "learning_rate": 4.213034981292629e-05, + "loss": 1.5067, + "step": 10009 + }, + { + "epoch": 0.5579399141630901, + "grad_norm": 0.5601934790611267, + "learning_rate": 4.212155668344691e-05, + "loss": 1.5677, + "step": 10010 + }, + { + "epoch": 0.5579956524162533, + "grad_norm": 0.5320611596107483, + "learning_rate": 4.211276380382579e-05, + "loss": 1.5929, + "step": 10011 + }, + { + "epoch": 0.5580513906694164, + "grad_norm": 0.5682796239852905, + "learning_rate": 4.210397117434183e-05, + "loss": 1.5922, + "step": 10012 + }, + { + "epoch": 0.5581071289225795, + "grad_norm": 0.531771183013916, + "learning_rate": 4.2095178795273864e-05, + "loss": 1.6061, + "step": 10013 + }, + { + "epoch": 0.5581628671757427, + "grad_norm": 0.5384634733200073, + "learning_rate": 4.208638666690074e-05, + "loss": 1.6108, + "step": 10014 + }, + { + "epoch": 0.5582186054289059, + "grad_norm": 0.5733115077018738, + "learning_rate": 4.207759478950129e-05, + "loss": 1.6811, + "step": 10015 + }, + { + "epoch": 0.558274343682069, + "grad_norm": 0.5614367127418518, + "learning_rate": 4.2068803163354344e-05, + "loss": 1.5484, + "step": 10016 + }, + { + "epoch": 0.5583300819352321, + "grad_norm": 0.5718212723731995, + "learning_rate": 4.206001178873872e-05, + "loss": 1.6159, + "step": 10017 + }, + { + "epoch": 0.5583858201883953, + "grad_norm": 0.577841579914093, + "learning_rate": 4.205122066593321e-05, + "loss": 1.7111, + "step": 10018 + }, + { + "epoch": 0.5584415584415584, + "grad_norm": 0.5670404434204102, + "learning_rate": 4.204242979521665e-05, + "loss": 1.6692, + "step": 10019 + }, + { + "epoch": 0.5584972966947216, + "grad_norm": 0.5312654376029968, + "learning_rate": 4.203363917686784e-05, + "loss": 1.5002, + "step": 10020 + }, + { + "epoch": 0.5585530349478848, + "grad_norm": 0.5269418358802795, + "learning_rate": 4.202484881116553e-05, + "loss": 1.5218, + "step": 10021 + }, + { + "epoch": 0.5586087732010478, + "grad_norm": 0.5869148969650269, + "learning_rate": 4.201605869838852e-05, + "loss": 1.6535, + "step": 10022 + }, + { + "epoch": 0.558664511454211, + "grad_norm": 0.5673363208770752, + "learning_rate": 4.2007268838815575e-05, + "loss": 1.7252, + "step": 10023 + }, + { + "epoch": 0.5587202497073742, + "grad_norm": 0.5675745606422424, + "learning_rate": 4.199847923272547e-05, + "loss": 1.7039, + "step": 10024 + }, + { + "epoch": 0.5587759879605373, + "grad_norm": 0.6065249443054199, + "learning_rate": 4.198968988039695e-05, + "loss": 1.8148, + "step": 10025 + }, + { + "epoch": 0.5588317262137005, + "grad_norm": 0.5471330285072327, + "learning_rate": 4.198090078210874e-05, + "loss": 1.6482, + "step": 10026 + }, + { + "epoch": 0.5588874644668637, + "grad_norm": 0.5834773182868958, + "learning_rate": 4.1972111938139636e-05, + "loss": 1.7497, + "step": 10027 + }, + { + "epoch": 0.5589432027200267, + "grad_norm": 0.5758984684944153, + "learning_rate": 4.196332334876831e-05, + "loss": 1.7287, + "step": 10028 + }, + { + "epoch": 0.5589989409731899, + "grad_norm": 0.6321014165878296, + "learning_rate": 4.195453501427353e-05, + "loss": 1.8665, + "step": 10029 + }, + { + "epoch": 0.559054679226353, + "grad_norm": 0.6041330099105835, + "learning_rate": 4.194574693493398e-05, + "loss": 2.0083, + "step": 10030 + }, + { + "epoch": 0.5591104174795162, + "grad_norm": 0.5616350173950195, + "learning_rate": 4.19369591110284e-05, + "loss": 1.4786, + "step": 10031 + }, + { + "epoch": 0.5591661557326794, + "grad_norm": 0.5436341166496277, + "learning_rate": 4.192817154283544e-05, + "loss": 1.5979, + "step": 10032 + }, + { + "epoch": 0.5592218939858424, + "grad_norm": 0.5548772811889648, + "learning_rate": 4.1919384230633804e-05, + "loss": 1.612, + "step": 10033 + }, + { + "epoch": 0.5592776322390056, + "grad_norm": 0.49860692024230957, + "learning_rate": 4.191059717470223e-05, + "loss": 1.1854, + "step": 10034 + }, + { + "epoch": 0.5593333704921688, + "grad_norm": 0.5409103035926819, + "learning_rate": 4.19018103753193e-05, + "loss": 1.6482, + "step": 10035 + }, + { + "epoch": 0.5593891087453319, + "grad_norm": 0.5163053274154663, + "learning_rate": 4.1893023832763786e-05, + "loss": 1.5681, + "step": 10036 + }, + { + "epoch": 0.5594448469984951, + "grad_norm": 0.5453513860702515, + "learning_rate": 4.1884237547314244e-05, + "loss": 1.5808, + "step": 10037 + }, + { + "epoch": 0.5595005852516582, + "grad_norm": 0.52850741147995, + "learning_rate": 4.1875451519249386e-05, + "loss": 1.4751, + "step": 10038 + }, + { + "epoch": 0.5595563235048213, + "grad_norm": 0.5223550200462341, + "learning_rate": 4.186666574884783e-05, + "loss": 1.4774, + "step": 10039 + }, + { + "epoch": 0.5596120617579845, + "grad_norm": 0.5033788084983826, + "learning_rate": 4.1857880236388217e-05, + "loss": 1.546, + "step": 10040 + }, + { + "epoch": 0.5596678000111477, + "grad_norm": 0.5803878903388977, + "learning_rate": 4.184909498214918e-05, + "loss": 1.7583, + "step": 10041 + }, + { + "epoch": 0.5597235382643108, + "grad_norm": 0.5489541888237, + "learning_rate": 4.1840309986409316e-05, + "loss": 1.4077, + "step": 10042 + }, + { + "epoch": 0.559779276517474, + "grad_norm": 0.5916313529014587, + "learning_rate": 4.1831525249447255e-05, + "loss": 1.7512, + "step": 10043 + }, + { + "epoch": 0.5598350147706371, + "grad_norm": 0.610925018787384, + "learning_rate": 4.182274077154157e-05, + "loss": 1.8438, + "step": 10044 + }, + { + "epoch": 0.5598907530238002, + "grad_norm": 0.5416461229324341, + "learning_rate": 4.181395655297088e-05, + "loss": 1.7325, + "step": 10045 + }, + { + "epoch": 0.5599464912769634, + "grad_norm": 0.5306708812713623, + "learning_rate": 4.180517259401377e-05, + "loss": 1.662, + "step": 10046 + }, + { + "epoch": 0.5600022295301266, + "grad_norm": 0.5335866808891296, + "learning_rate": 4.179638889494879e-05, + "loss": 1.7033, + "step": 10047 + }, + { + "epoch": 0.5600579677832896, + "grad_norm": 0.5430575013160706, + "learning_rate": 4.1787605456054546e-05, + "loss": 1.4528, + "step": 10048 + }, + { + "epoch": 0.5601137060364528, + "grad_norm": 0.5668299794197083, + "learning_rate": 4.177882227760956e-05, + "loss": 1.6722, + "step": 10049 + }, + { + "epoch": 0.560169444289616, + "grad_norm": 0.5457166433334351, + "learning_rate": 4.17700393598924e-05, + "loss": 1.534, + "step": 10050 + }, + { + "epoch": 0.5602251825427791, + "grad_norm": 0.5463144183158875, + "learning_rate": 4.176125670318161e-05, + "loss": 1.7221, + "step": 10051 + }, + { + "epoch": 0.5602809207959423, + "grad_norm": 0.5175307989120483, + "learning_rate": 4.1752474307755706e-05, + "loss": 1.4255, + "step": 10052 + }, + { + "epoch": 0.5603366590491053, + "grad_norm": 0.5423510670661926, + "learning_rate": 4.174369217389326e-05, + "loss": 1.6083, + "step": 10053 + }, + { + "epoch": 0.5603923973022685, + "grad_norm": 0.5733422040939331, + "learning_rate": 4.173491030187274e-05, + "loss": 1.4492, + "step": 10054 + }, + { + "epoch": 0.5604481355554317, + "grad_norm": 0.5978653430938721, + "learning_rate": 4.172612869197269e-05, + "loss": 1.9517, + "step": 10055 + }, + { + "epoch": 0.5605038738085948, + "grad_norm": 0.6374850869178772, + "learning_rate": 4.171734734447158e-05, + "loss": 1.5612, + "step": 10056 + }, + { + "epoch": 0.560559612061758, + "grad_norm": 0.5653359889984131, + "learning_rate": 4.1708566259647944e-05, + "loss": 1.6853, + "step": 10057 + }, + { + "epoch": 0.5606153503149212, + "grad_norm": 0.5681639313697815, + "learning_rate": 4.1699785437780226e-05, + "loss": 1.6625, + "step": 10058 + }, + { + "epoch": 0.5606710885680842, + "grad_norm": 0.5495839715003967, + "learning_rate": 4.169100487914691e-05, + "loss": 1.6534, + "step": 10059 + }, + { + "epoch": 0.5607268268212474, + "grad_norm": 0.6118134260177612, + "learning_rate": 4.168222458402651e-05, + "loss": 1.7264, + "step": 10060 + }, + { + "epoch": 0.5607825650744106, + "grad_norm": 0.5823867321014404, + "learning_rate": 4.167344455269741e-05, + "loss": 1.6749, + "step": 10061 + }, + { + "epoch": 0.5608383033275737, + "grad_norm": 0.5473729968070984, + "learning_rate": 4.166466478543814e-05, + "loss": 1.5746, + "step": 10062 + }, + { + "epoch": 0.5608940415807369, + "grad_norm": 0.5540270805358887, + "learning_rate": 4.1655885282527075e-05, + "loss": 1.4935, + "step": 10063 + }, + { + "epoch": 0.5609497798339, + "grad_norm": 0.5212602019309998, + "learning_rate": 4.164710604424269e-05, + "loss": 1.422, + "step": 10064 + }, + { + "epoch": 0.5610055180870631, + "grad_norm": 0.5885487198829651, + "learning_rate": 4.1638327070863404e-05, + "loss": 1.7145, + "step": 10065 + }, + { + "epoch": 0.5610612563402263, + "grad_norm": 0.5488985776901245, + "learning_rate": 4.162954836266762e-05, + "loss": 1.565, + "step": 10066 + }, + { + "epoch": 0.5611169945933895, + "grad_norm": 0.563651978969574, + "learning_rate": 4.1620769919933775e-05, + "loss": 1.653, + "step": 10067 + }, + { + "epoch": 0.5611727328465526, + "grad_norm": 0.5442456007003784, + "learning_rate": 4.161199174294025e-05, + "loss": 1.7342, + "step": 10068 + }, + { + "epoch": 0.5612284710997157, + "grad_norm": 0.555916428565979, + "learning_rate": 4.1603213831965435e-05, + "loss": 1.7592, + "step": 10069 + }, + { + "epoch": 0.5612842093528789, + "grad_norm": 0.556006908416748, + "learning_rate": 4.1594436187287714e-05, + "loss": 1.6228, + "step": 10070 + }, + { + "epoch": 0.561339947606042, + "grad_norm": 0.5912269949913025, + "learning_rate": 4.15856588091855e-05, + "loss": 1.789, + "step": 10071 + }, + { + "epoch": 0.5613956858592052, + "grad_norm": 0.5295083522796631, + "learning_rate": 4.157688169793709e-05, + "loss": 1.4986, + "step": 10072 + }, + { + "epoch": 0.5614514241123684, + "grad_norm": 0.5145447254180908, + "learning_rate": 4.15681048538209e-05, + "loss": 1.326, + "step": 10073 + }, + { + "epoch": 0.5615071623655314, + "grad_norm": 0.6136693954467773, + "learning_rate": 4.155932827711527e-05, + "loss": 2.1994, + "step": 10074 + }, + { + "epoch": 0.5615629006186946, + "grad_norm": 0.649308443069458, + "learning_rate": 4.155055196809852e-05, + "loss": 1.9845, + "step": 10075 + }, + { + "epoch": 0.5616186388718577, + "grad_norm": 0.5622665286064148, + "learning_rate": 4.154177592704901e-05, + "loss": 1.6813, + "step": 10076 + }, + { + "epoch": 0.5616743771250209, + "grad_norm": 0.5435896515846252, + "learning_rate": 4.153300015424505e-05, + "loss": 1.6458, + "step": 10077 + }, + { + "epoch": 0.5617301153781841, + "grad_norm": 0.5368431806564331, + "learning_rate": 4.1524224649964935e-05, + "loss": 1.4892, + "step": 10078 + }, + { + "epoch": 0.5617858536313471, + "grad_norm": 0.5401378870010376, + "learning_rate": 4.1515449414487034e-05, + "loss": 1.5534, + "step": 10079 + }, + { + "epoch": 0.5618415918845103, + "grad_norm": 0.5672016143798828, + "learning_rate": 4.1506674448089586e-05, + "loss": 1.7606, + "step": 10080 + }, + { + "epoch": 0.5618973301376735, + "grad_norm": 0.6083208322525024, + "learning_rate": 4.149789975105092e-05, + "loss": 1.7784, + "step": 10081 + }, + { + "epoch": 0.5619530683908366, + "grad_norm": 0.5388506650924683, + "learning_rate": 4.1489125323649294e-05, + "loss": 1.7375, + "step": 10082 + }, + { + "epoch": 0.5620088066439998, + "grad_norm": 0.6294654011726379, + "learning_rate": 4.1480351166163e-05, + "loss": 1.5098, + "step": 10083 + }, + { + "epoch": 0.562064544897163, + "grad_norm": 0.5356112718582153, + "learning_rate": 4.1471577278870285e-05, + "loss": 1.6152, + "step": 10084 + }, + { + "epoch": 0.562120283150326, + "grad_norm": 0.566550612449646, + "learning_rate": 4.14628036620494e-05, + "loss": 1.5779, + "step": 10085 + }, + { + "epoch": 0.5621760214034892, + "grad_norm": 0.5861518979072571, + "learning_rate": 4.145403031597865e-05, + "loss": 1.5938, + "step": 10086 + }, + { + "epoch": 0.5622317596566524, + "grad_norm": 0.5656233429908752, + "learning_rate": 4.144525724093619e-05, + "loss": 1.5921, + "step": 10087 + }, + { + "epoch": 0.5622874979098155, + "grad_norm": 0.555738091468811, + "learning_rate": 4.143648443720033e-05, + "loss": 1.6272, + "step": 10088 + }, + { + "epoch": 0.5623432361629787, + "grad_norm": 0.6210994124412537, + "learning_rate": 4.1427711905049215e-05, + "loss": 1.9088, + "step": 10089 + }, + { + "epoch": 0.5623989744161418, + "grad_norm": 0.5784873366355896, + "learning_rate": 4.1418939644761125e-05, + "loss": 1.6455, + "step": 10090 + }, + { + "epoch": 0.5624547126693049, + "grad_norm": 0.5760608911514282, + "learning_rate": 4.141016765661423e-05, + "loss": 1.71, + "step": 10091 + }, + { + "epoch": 0.5625104509224681, + "grad_norm": 0.5815902948379517, + "learning_rate": 4.1401395940886725e-05, + "loss": 1.6911, + "step": 10092 + }, + { + "epoch": 0.5625661891756313, + "grad_norm": 0.5799475312232971, + "learning_rate": 4.139262449785683e-05, + "loss": 1.7185, + "step": 10093 + }, + { + "epoch": 0.5626219274287944, + "grad_norm": 0.572181224822998, + "learning_rate": 4.1383853327802686e-05, + "loss": 1.5143, + "step": 10094 + }, + { + "epoch": 0.5626776656819575, + "grad_norm": 0.593944787979126, + "learning_rate": 4.137508243100249e-05, + "loss": 1.7856, + "step": 10095 + }, + { + "epoch": 0.5627334039351207, + "grad_norm": 0.5817708373069763, + "learning_rate": 4.136631180773437e-05, + "loss": 1.7438, + "step": 10096 + }, + { + "epoch": 0.5627891421882838, + "grad_norm": 0.559810221195221, + "learning_rate": 4.1357541458276535e-05, + "loss": 1.5218, + "step": 10097 + }, + { + "epoch": 0.562844880441447, + "grad_norm": 0.5834983587265015, + "learning_rate": 4.134877138290706e-05, + "loss": 1.7985, + "step": 10098 + }, + { + "epoch": 0.5629006186946102, + "grad_norm": 0.5739032030105591, + "learning_rate": 4.134000158190413e-05, + "loss": 1.6318, + "step": 10099 + }, + { + "epoch": 0.5629563569477732, + "grad_norm": 0.5493670105934143, + "learning_rate": 4.133123205554587e-05, + "loss": 1.5959, + "step": 10100 + }, + { + "epoch": 0.5630120952009364, + "grad_norm": 0.5687856674194336, + "learning_rate": 4.132246280411038e-05, + "loss": 1.7061, + "step": 10101 + }, + { + "epoch": 0.5630678334540995, + "grad_norm": 0.5455751419067383, + "learning_rate": 4.131369382787578e-05, + "loss": 1.5649, + "step": 10102 + }, + { + "epoch": 0.5631235717072627, + "grad_norm": 0.5812469124794006, + "learning_rate": 4.130492512712016e-05, + "loss": 1.7403, + "step": 10103 + }, + { + "epoch": 0.5631793099604259, + "grad_norm": 0.5267177224159241, + "learning_rate": 4.129615670212161e-05, + "loss": 1.4974, + "step": 10104 + }, + { + "epoch": 0.5632350482135889, + "grad_norm": 0.5732220411300659, + "learning_rate": 4.1287388553158235e-05, + "loss": 1.6699, + "step": 10105 + }, + { + "epoch": 0.5632907864667521, + "grad_norm": 0.5401387810707092, + "learning_rate": 4.1278620680508096e-05, + "loss": 1.5078, + "step": 10106 + }, + { + "epoch": 0.5633465247199153, + "grad_norm": 0.5950440764427185, + "learning_rate": 4.126985308444927e-05, + "loss": 1.7493, + "step": 10107 + }, + { + "epoch": 0.5634022629730784, + "grad_norm": 0.5888415575027466, + "learning_rate": 4.1261085765259786e-05, + "loss": 1.5739, + "step": 10108 + }, + { + "epoch": 0.5634580012262416, + "grad_norm": 0.5839027166366577, + "learning_rate": 4.1252318723217724e-05, + "loss": 1.6441, + "step": 10109 + }, + { + "epoch": 0.5635137394794048, + "grad_norm": 0.517785906791687, + "learning_rate": 4.1243551958601103e-05, + "loss": 1.5001, + "step": 10110 + }, + { + "epoch": 0.5635694777325678, + "grad_norm": 0.5795639753341675, + "learning_rate": 4.123478547168795e-05, + "loss": 1.6376, + "step": 10111 + }, + { + "epoch": 0.563625215985731, + "grad_norm": 0.5699589252471924, + "learning_rate": 4.122601926275632e-05, + "loss": 1.723, + "step": 10112 + }, + { + "epoch": 0.5636809542388942, + "grad_norm": 0.5570908188819885, + "learning_rate": 4.121725333208418e-05, + "loss": 1.4783, + "step": 10113 + }, + { + "epoch": 0.5637366924920573, + "grad_norm": 0.641866147518158, + "learning_rate": 4.1208487679949574e-05, + "loss": 1.6867, + "step": 10114 + }, + { + "epoch": 0.5637924307452205, + "grad_norm": 0.5656890869140625, + "learning_rate": 4.119972230663047e-05, + "loss": 1.6556, + "step": 10115 + }, + { + "epoch": 0.5638481689983836, + "grad_norm": 0.5093350410461426, + "learning_rate": 4.119095721240488e-05, + "loss": 1.4309, + "step": 10116 + }, + { + "epoch": 0.5639039072515467, + "grad_norm": 0.590333104133606, + "learning_rate": 4.118219239755076e-05, + "loss": 1.7376, + "step": 10117 + }, + { + "epoch": 0.5639596455047099, + "grad_norm": 0.5829031467437744, + "learning_rate": 4.117342786234608e-05, + "loss": 1.6084, + "step": 10118 + }, + { + "epoch": 0.5640153837578731, + "grad_norm": 0.5385381579399109, + "learning_rate": 4.116466360706881e-05, + "loss": 1.6276, + "step": 10119 + }, + { + "epoch": 0.5640711220110362, + "grad_norm": 0.5832441449165344, + "learning_rate": 4.1155899631996883e-05, + "loss": 1.7219, + "step": 10120 + }, + { + "epoch": 0.5641268602641993, + "grad_norm": 0.59648197889328, + "learning_rate": 4.114713593740828e-05, + "loss": 1.6228, + "step": 10121 + }, + { + "epoch": 0.5641825985173625, + "grad_norm": 0.5410522818565369, + "learning_rate": 4.113837252358089e-05, + "loss": 1.6936, + "step": 10122 + }, + { + "epoch": 0.5642383367705256, + "grad_norm": 0.5790727138519287, + "learning_rate": 4.1129609390792675e-05, + "loss": 1.7324, + "step": 10123 + }, + { + "epoch": 0.5642940750236888, + "grad_norm": 0.5365089774131775, + "learning_rate": 4.112084653932151e-05, + "loss": 1.5449, + "step": 10124 + }, + { + "epoch": 0.5643498132768519, + "grad_norm": 0.5550824999809265, + "learning_rate": 4.111208396944533e-05, + "loss": 1.6333, + "step": 10125 + }, + { + "epoch": 0.564405551530015, + "grad_norm": 0.5916097164154053, + "learning_rate": 4.110332168144204e-05, + "loss": 1.7363, + "step": 10126 + }, + { + "epoch": 0.5644612897831782, + "grad_norm": 0.5079007744789124, + "learning_rate": 4.10945596755895e-05, + "loss": 1.4916, + "step": 10127 + }, + { + "epoch": 0.5645170280363413, + "grad_norm": 0.5717905163764954, + "learning_rate": 4.108579795216562e-05, + "loss": 1.7816, + "step": 10128 + }, + { + "epoch": 0.5645727662895045, + "grad_norm": 0.5530692338943481, + "learning_rate": 4.107703651144824e-05, + "loss": 1.6816, + "step": 10129 + }, + { + "epoch": 0.5646285045426677, + "grad_norm": 0.5110148787498474, + "learning_rate": 4.106827535371523e-05, + "loss": 1.5643, + "step": 10130 + }, + { + "epoch": 0.5646842427958307, + "grad_norm": 0.5846538543701172, + "learning_rate": 4.105951447924447e-05, + "loss": 1.8457, + "step": 10131 + }, + { + "epoch": 0.5647399810489939, + "grad_norm": 0.6359025239944458, + "learning_rate": 4.105075388831378e-05, + "loss": 1.8374, + "step": 10132 + }, + { + "epoch": 0.5647957193021571, + "grad_norm": 0.5842446684837341, + "learning_rate": 4.1041993581201e-05, + "loss": 1.9171, + "step": 10133 + }, + { + "epoch": 0.5648514575553202, + "grad_norm": 0.5989353060722351, + "learning_rate": 4.103323355818395e-05, + "loss": 1.8695, + "step": 10134 + }, + { + "epoch": 0.5649071958084834, + "grad_norm": 0.5007326006889343, + "learning_rate": 4.102447381954046e-05, + "loss": 1.5685, + "step": 10135 + }, + { + "epoch": 0.5649629340616465, + "grad_norm": 0.544731855392456, + "learning_rate": 4.1015714365548316e-05, + "loss": 1.7752, + "step": 10136 + }, + { + "epoch": 0.5650186723148096, + "grad_norm": 0.4942627251148224, + "learning_rate": 4.1006955196485324e-05, + "loss": 1.3801, + "step": 10137 + }, + { + "epoch": 0.5650744105679728, + "grad_norm": 0.5270852446556091, + "learning_rate": 4.099819631262931e-05, + "loss": 1.6352, + "step": 10138 + }, + { + "epoch": 0.565130148821136, + "grad_norm": 0.5775606632232666, + "learning_rate": 4.0989437714258e-05, + "loss": 1.7102, + "step": 10139 + }, + { + "epoch": 0.5651858870742991, + "grad_norm": 0.5705950260162354, + "learning_rate": 4.09806794016492e-05, + "loss": 1.7768, + "step": 10140 + }, + { + "epoch": 0.5652416253274622, + "grad_norm": 0.5659387111663818, + "learning_rate": 4.097192137508066e-05, + "loss": 1.5619, + "step": 10141 + }, + { + "epoch": 0.5652973635806254, + "grad_norm": 0.5292123556137085, + "learning_rate": 4.096316363483014e-05, + "loss": 1.5905, + "step": 10142 + }, + { + "epoch": 0.5653531018337885, + "grad_norm": 0.6031396985054016, + "learning_rate": 4.095440618117538e-05, + "loss": 1.5628, + "step": 10143 + }, + { + "epoch": 0.5654088400869517, + "grad_norm": 0.5399644374847412, + "learning_rate": 4.094564901439411e-05, + "loss": 1.7393, + "step": 10144 + }, + { + "epoch": 0.5654645783401149, + "grad_norm": 0.5706971287727356, + "learning_rate": 4.0936892134764076e-05, + "loss": 1.6748, + "step": 10145 + }, + { + "epoch": 0.565520316593278, + "grad_norm": 0.6021378040313721, + "learning_rate": 4.0928135542562964e-05, + "loss": 1.7082, + "step": 10146 + }, + { + "epoch": 0.5655760548464411, + "grad_norm": 0.4986594617366791, + "learning_rate": 4.0919379238068526e-05, + "loss": 1.0838, + "step": 10147 + }, + { + "epoch": 0.5656317930996042, + "grad_norm": 0.5753964185714722, + "learning_rate": 4.0910623221558405e-05, + "loss": 1.552, + "step": 10148 + }, + { + "epoch": 0.5656875313527674, + "grad_norm": 0.5776475071907043, + "learning_rate": 4.0901867493310354e-05, + "loss": 1.8034, + "step": 10149 + }, + { + "epoch": 0.5657432696059306, + "grad_norm": 0.5469151735305786, + "learning_rate": 4.089311205360199e-05, + "loss": 1.7206, + "step": 10150 + }, + { + "epoch": 0.5657990078590937, + "grad_norm": 0.5828034281730652, + "learning_rate": 4.0884356902711016e-05, + "loss": 1.6696, + "step": 10151 + }, + { + "epoch": 0.5658547461122568, + "grad_norm": 0.5706288814544678, + "learning_rate": 4.087560204091511e-05, + "loss": 1.6162, + "step": 10152 + }, + { + "epoch": 0.56591048436542, + "grad_norm": 0.65047687292099, + "learning_rate": 4.08668474684919e-05, + "loss": 1.9385, + "step": 10153 + }, + { + "epoch": 0.5659662226185831, + "grad_norm": 0.5484048128128052, + "learning_rate": 4.085809318571905e-05, + "loss": 1.7144, + "step": 10154 + }, + { + "epoch": 0.5660219608717463, + "grad_norm": 0.5408827066421509, + "learning_rate": 4.084933919287417e-05, + "loss": 1.4162, + "step": 10155 + }, + { + "epoch": 0.5660776991249095, + "grad_norm": 0.5536865592002869, + "learning_rate": 4.084058549023488e-05, + "loss": 1.6541, + "step": 10156 + }, + { + "epoch": 0.5661334373780725, + "grad_norm": 0.5546683073043823, + "learning_rate": 4.0831832078078845e-05, + "loss": 1.5955, + "step": 10157 + }, + { + "epoch": 0.5661891756312357, + "grad_norm": 0.6069309711456299, + "learning_rate": 4.082307895668364e-05, + "loss": 1.9304, + "step": 10158 + }, + { + "epoch": 0.5662449138843989, + "grad_norm": 0.6290032267570496, + "learning_rate": 4.0814326126326864e-05, + "loss": 1.91, + "step": 10159 + }, + { + "epoch": 0.566300652137562, + "grad_norm": 0.5626652240753174, + "learning_rate": 4.080557358728609e-05, + "loss": 1.848, + "step": 10160 + }, + { + "epoch": 0.5663563903907252, + "grad_norm": 0.5320069789886475, + "learning_rate": 4.079682133983894e-05, + "loss": 1.6209, + "step": 10161 + }, + { + "epoch": 0.5664121286438883, + "grad_norm": 0.5245012044906616, + "learning_rate": 4.0788069384262946e-05, + "loss": 1.4589, + "step": 10162 + }, + { + "epoch": 0.5664678668970514, + "grad_norm": 0.5692093968391418, + "learning_rate": 4.077931772083566e-05, + "loss": 1.7792, + "step": 10163 + }, + { + "epoch": 0.5665236051502146, + "grad_norm": 0.5256657600402832, + "learning_rate": 4.0770566349834696e-05, + "loss": 1.5378, + "step": 10164 + }, + { + "epoch": 0.5665793434033778, + "grad_norm": 0.5258059501647949, + "learning_rate": 4.076181527153753e-05, + "loss": 1.543, + "step": 10165 + }, + { + "epoch": 0.5666350816565409, + "grad_norm": 0.5840742588043213, + "learning_rate": 4.0753064486221736e-05, + "loss": 1.6944, + "step": 10166 + }, + { + "epoch": 0.566690819909704, + "grad_norm": 0.5648197531700134, + "learning_rate": 4.0744313994164804e-05, + "loss": 1.6907, + "step": 10167 + }, + { + "epoch": 0.5667465581628672, + "grad_norm": 0.6014297008514404, + "learning_rate": 4.0735563795644294e-05, + "loss": 1.6311, + "step": 10168 + }, + { + "epoch": 0.5668022964160303, + "grad_norm": 0.5499513745307922, + "learning_rate": 4.072681389093767e-05, + "loss": 1.5288, + "step": 10169 + }, + { + "epoch": 0.5668580346691935, + "grad_norm": 0.5218088626861572, + "learning_rate": 4.071806428032244e-05, + "loss": 1.5348, + "step": 10170 + }, + { + "epoch": 0.5669137729223566, + "grad_norm": 0.5808815956115723, + "learning_rate": 4.07093149640761e-05, + "loss": 1.9325, + "step": 10171 + }, + { + "epoch": 0.5669695111755197, + "grad_norm": 0.6530500054359436, + "learning_rate": 4.0700565942476104e-05, + "loss": 1.93, + "step": 10172 + }, + { + "epoch": 0.5670252494286829, + "grad_norm": 0.5505321025848389, + "learning_rate": 4.069181721579997e-05, + "loss": 1.6544, + "step": 10173 + }, + { + "epoch": 0.567080987681846, + "grad_norm": 0.5787295699119568, + "learning_rate": 4.068306878432509e-05, + "loss": 1.6509, + "step": 10174 + }, + { + "epoch": 0.5671367259350092, + "grad_norm": 0.6493069529533386, + "learning_rate": 4.067432064832898e-05, + "loss": 2.02, + "step": 10175 + }, + { + "epoch": 0.5671924641881724, + "grad_norm": 0.5896463394165039, + "learning_rate": 4.066557280808901e-05, + "loss": 1.7404, + "step": 10176 + }, + { + "epoch": 0.5672482024413354, + "grad_norm": 0.5523368716239929, + "learning_rate": 4.065682526388266e-05, + "loss": 1.7042, + "step": 10177 + }, + { + "epoch": 0.5673039406944986, + "grad_norm": 0.5077149271965027, + "learning_rate": 4.064807801598735e-05, + "loss": 1.5399, + "step": 10178 + }, + { + "epoch": 0.5673596789476618, + "grad_norm": 0.5975422263145447, + "learning_rate": 4.063933106468047e-05, + "loss": 1.5696, + "step": 10179 + }, + { + "epoch": 0.5674154172008249, + "grad_norm": 0.5238234400749207, + "learning_rate": 4.063058441023944e-05, + "loss": 1.5354, + "step": 10180 + }, + { + "epoch": 0.5674711554539881, + "grad_norm": 0.5576155781745911, + "learning_rate": 4.062183805294164e-05, + "loss": 1.6381, + "step": 10181 + }, + { + "epoch": 0.5675268937071513, + "grad_norm": 0.5786839723587036, + "learning_rate": 4.0613091993064464e-05, + "loss": 1.6276, + "step": 10182 + }, + { + "epoch": 0.5675826319603143, + "grad_norm": 0.5902144312858582, + "learning_rate": 4.0604346230885257e-05, + "loss": 1.7498, + "step": 10183 + }, + { + "epoch": 0.5676383702134775, + "grad_norm": 0.647559642791748, + "learning_rate": 4.0595600766681425e-05, + "loss": 1.63, + "step": 10184 + }, + { + "epoch": 0.5676941084666407, + "grad_norm": 0.5559741854667664, + "learning_rate": 4.0586855600730314e-05, + "loss": 1.6698, + "step": 10185 + }, + { + "epoch": 0.5677498467198038, + "grad_norm": 0.5404937267303467, + "learning_rate": 4.057811073330925e-05, + "loss": 1.4475, + "step": 10186 + }, + { + "epoch": 0.567805584972967, + "grad_norm": 0.6052438616752625, + "learning_rate": 4.056936616469559e-05, + "loss": 1.5655, + "step": 10187 + }, + { + "epoch": 0.5678613232261301, + "grad_norm": 0.5823904275894165, + "learning_rate": 4.056062189516664e-05, + "loss": 1.7327, + "step": 10188 + }, + { + "epoch": 0.5679170614792932, + "grad_norm": 0.5970086455345154, + "learning_rate": 4.055187792499971e-05, + "loss": 1.8365, + "step": 10189 + }, + { + "epoch": 0.5679727997324564, + "grad_norm": 0.530210018157959, + "learning_rate": 4.054313425447217e-05, + "loss": 1.5606, + "step": 10190 + }, + { + "epoch": 0.5680285379856196, + "grad_norm": 0.5752225518226624, + "learning_rate": 4.053439088386124e-05, + "loss": 1.5273, + "step": 10191 + }, + { + "epoch": 0.5680842762387827, + "grad_norm": 0.6104926466941833, + "learning_rate": 4.0525647813444254e-05, + "loss": 1.6909, + "step": 10192 + }, + { + "epoch": 0.5681400144919458, + "grad_norm": 0.6021226048469543, + "learning_rate": 4.0516905043498474e-05, + "loss": 1.8376, + "step": 10193 + }, + { + "epoch": 0.5681957527451089, + "grad_norm": 0.5418221950531006, + "learning_rate": 4.0508162574301195e-05, + "loss": 1.4, + "step": 10194 + }, + { + "epoch": 0.5682514909982721, + "grad_norm": 0.5655646324157715, + "learning_rate": 4.049942040612964e-05, + "loss": 1.6005, + "step": 10195 + }, + { + "epoch": 0.5683072292514353, + "grad_norm": 0.5451434254646301, + "learning_rate": 4.049067853926108e-05, + "loss": 1.6205, + "step": 10196 + }, + { + "epoch": 0.5683629675045984, + "grad_norm": 0.585850715637207, + "learning_rate": 4.048193697397276e-05, + "loss": 1.7273, + "step": 10197 + }, + { + "epoch": 0.5684187057577615, + "grad_norm": 0.6063744425773621, + "learning_rate": 4.0473195710541886e-05, + "loss": 1.7355, + "step": 10198 + }, + { + "epoch": 0.5684744440109247, + "grad_norm": 0.5964711308479309, + "learning_rate": 4.046445474924573e-05, + "loss": 1.8361, + "step": 10199 + }, + { + "epoch": 0.5685301822640878, + "grad_norm": 0.5515483021736145, + "learning_rate": 4.0455714090361446e-05, + "loss": 1.6124, + "step": 10200 + }, + { + "epoch": 0.568585920517251, + "grad_norm": 0.5965580344200134, + "learning_rate": 4.044697373416628e-05, + "loss": 1.8331, + "step": 10201 + }, + { + "epoch": 0.5686416587704142, + "grad_norm": 0.618015706539154, + "learning_rate": 4.04382336809374e-05, + "loss": 1.7974, + "step": 10202 + }, + { + "epoch": 0.5686973970235772, + "grad_norm": 0.5886608958244324, + "learning_rate": 4.0429493930952e-05, + "loss": 1.7206, + "step": 10203 + }, + { + "epoch": 0.5687531352767404, + "grad_norm": 0.6158391237258911, + "learning_rate": 4.042075448448726e-05, + "loss": 1.6667, + "step": 10204 + }, + { + "epoch": 0.5688088735299036, + "grad_norm": 0.6388469338417053, + "learning_rate": 4.041201534182033e-05, + "loss": 1.5124, + "step": 10205 + }, + { + "epoch": 0.5688646117830667, + "grad_norm": 0.575337290763855, + "learning_rate": 4.040327650322838e-05, + "loss": 1.756, + "step": 10206 + }, + { + "epoch": 0.5689203500362299, + "grad_norm": 0.5659148693084717, + "learning_rate": 4.039453796898853e-05, + "loss": 1.7316, + "step": 10207 + }, + { + "epoch": 0.5689760882893931, + "grad_norm": 0.5717800259590149, + "learning_rate": 4.038579973937796e-05, + "loss": 1.6193, + "step": 10208 + }, + { + "epoch": 0.5690318265425561, + "grad_norm": 0.5925152897834778, + "learning_rate": 4.037706181467373e-05, + "loss": 1.8098, + "step": 10209 + }, + { + "epoch": 0.5690875647957193, + "grad_norm": 0.5946084856987, + "learning_rate": 4.036832419515301e-05, + "loss": 1.792, + "step": 10210 + }, + { + "epoch": 0.5691433030488825, + "grad_norm": 0.5962294340133667, + "learning_rate": 4.03595868810929e-05, + "loss": 1.716, + "step": 10211 + }, + { + "epoch": 0.5691990413020456, + "grad_norm": 0.5260846614837646, + "learning_rate": 4.035084987277048e-05, + "loss": 1.5782, + "step": 10212 + }, + { + "epoch": 0.5692547795552088, + "grad_norm": 0.5939358472824097, + "learning_rate": 4.034211317046285e-05, + "loss": 1.7408, + "step": 10213 + }, + { + "epoch": 0.5693105178083719, + "grad_norm": 0.5185898542404175, + "learning_rate": 4.033337677444707e-05, + "loss": 1.5208, + "step": 10214 + }, + { + "epoch": 0.569366256061535, + "grad_norm": 0.5650632381439209, + "learning_rate": 4.0324640685000206e-05, + "loss": 1.7486, + "step": 10215 + }, + { + "epoch": 0.5694219943146982, + "grad_norm": 0.5693777799606323, + "learning_rate": 4.0315904902399367e-05, + "loss": 1.8807, + "step": 10216 + }, + { + "epoch": 0.5694777325678613, + "grad_norm": 0.5746406316757202, + "learning_rate": 4.030716942692153e-05, + "loss": 1.7639, + "step": 10217 + }, + { + "epoch": 0.5695334708210245, + "grad_norm": 0.5026817917823792, + "learning_rate": 4.0298434258843775e-05, + "loss": 1.52, + "step": 10218 + }, + { + "epoch": 0.5695892090741876, + "grad_norm": 0.5377751588821411, + "learning_rate": 4.028969939844312e-05, + "loss": 1.7166, + "step": 10219 + }, + { + "epoch": 0.5696449473273507, + "grad_norm": 0.5900459289550781, + "learning_rate": 4.0280964845996597e-05, + "loss": 1.7338, + "step": 10220 + }, + { + "epoch": 0.5697006855805139, + "grad_norm": 0.5911110639572144, + "learning_rate": 4.027223060178119e-05, + "loss": 1.7374, + "step": 10221 + }, + { + "epoch": 0.5697564238336771, + "grad_norm": 0.49996447563171387, + "learning_rate": 4.0263496666073907e-05, + "loss": 1.4187, + "step": 10222 + }, + { + "epoch": 0.5698121620868402, + "grad_norm": 0.5100619792938232, + "learning_rate": 4.025476303915176e-05, + "loss": 1.4252, + "step": 10223 + }, + { + "epoch": 0.5698679003400033, + "grad_norm": 0.6046686768531799, + "learning_rate": 4.024602972129169e-05, + "loss": 1.8751, + "step": 10224 + }, + { + "epoch": 0.5699236385931665, + "grad_norm": 0.5467636585235596, + "learning_rate": 4.0237296712770714e-05, + "loss": 1.7274, + "step": 10225 + }, + { + "epoch": 0.5699793768463296, + "grad_norm": 0.5854259729385376, + "learning_rate": 4.022856401386573e-05, + "loss": 1.7434, + "step": 10226 + }, + { + "epoch": 0.5700351150994928, + "grad_norm": 0.5991394519805908, + "learning_rate": 4.0219831624853754e-05, + "loss": 1.7, + "step": 10227 + }, + { + "epoch": 0.570090853352656, + "grad_norm": 0.5040337443351746, + "learning_rate": 4.021109954601169e-05, + "loss": 1.3809, + "step": 10228 + }, + { + "epoch": 0.570146591605819, + "grad_norm": 0.5473932027816772, + "learning_rate": 4.020236777761646e-05, + "loss": 1.7109, + "step": 10229 + }, + { + "epoch": 0.5702023298589822, + "grad_norm": 0.5707757472991943, + "learning_rate": 4.0193636319945025e-05, + "loss": 1.8791, + "step": 10230 + }, + { + "epoch": 0.5702580681121454, + "grad_norm": 0.5629134178161621, + "learning_rate": 4.018490517327425e-05, + "loss": 1.904, + "step": 10231 + }, + { + "epoch": 0.5703138063653085, + "grad_norm": 0.5864009261131287, + "learning_rate": 4.0176174337881076e-05, + "loss": 1.7688, + "step": 10232 + }, + { + "epoch": 0.5703695446184717, + "grad_norm": 0.5961767435073853, + "learning_rate": 4.0167443814042344e-05, + "loss": 1.7515, + "step": 10233 + }, + { + "epoch": 0.5704252828716349, + "grad_norm": 0.5666062235832214, + "learning_rate": 4.0158713602035004e-05, + "loss": 1.7589, + "step": 10234 + }, + { + "epoch": 0.5704810211247979, + "grad_norm": 0.5441728234291077, + "learning_rate": 4.014998370213586e-05, + "loss": 1.7212, + "step": 10235 + }, + { + "epoch": 0.5705367593779611, + "grad_norm": 0.6179669499397278, + "learning_rate": 4.0141254114621815e-05, + "loss": 1.6665, + "step": 10236 + }, + { + "epoch": 0.5705924976311243, + "grad_norm": 0.5338011980056763, + "learning_rate": 4.0132524839769716e-05, + "loss": 1.7351, + "step": 10237 + }, + { + "epoch": 0.5706482358842874, + "grad_norm": 0.5339807868003845, + "learning_rate": 4.0123795877856385e-05, + "loss": 1.6007, + "step": 10238 + }, + { + "epoch": 0.5707039741374506, + "grad_norm": 0.5658773183822632, + "learning_rate": 4.011506722915867e-05, + "loss": 1.706, + "step": 10239 + }, + { + "epoch": 0.5707597123906136, + "grad_norm": 0.591503918170929, + "learning_rate": 4.01063388939534e-05, + "loss": 1.9076, + "step": 10240 + }, + { + "epoch": 0.5708154506437768, + "grad_norm": 0.4976126253604889, + "learning_rate": 4.009761087251735e-05, + "loss": 1.3349, + "step": 10241 + }, + { + "epoch": 0.57087118889694, + "grad_norm": 0.5694444179534912, + "learning_rate": 4.008888316512738e-05, + "loss": 1.7024, + "step": 10242 + }, + { + "epoch": 0.5709269271501031, + "grad_norm": 0.6095151305198669, + "learning_rate": 4.0080155772060225e-05, + "loss": 1.8915, + "step": 10243 + }, + { + "epoch": 0.5709826654032663, + "grad_norm": 0.5910167694091797, + "learning_rate": 4.007142869359272e-05, + "loss": 1.6265, + "step": 10244 + }, + { + "epoch": 0.5710384036564294, + "grad_norm": 0.5558249950408936, + "learning_rate": 4.006270193000158e-05, + "loss": 1.6305, + "step": 10245 + }, + { + "epoch": 0.5710941419095925, + "grad_norm": 0.5426621437072754, + "learning_rate": 4.005397548156362e-05, + "loss": 1.7311, + "step": 10246 + }, + { + "epoch": 0.5711498801627557, + "grad_norm": 0.5525389313697815, + "learning_rate": 4.004524934855555e-05, + "loss": 1.7237, + "step": 10247 + }, + { + "epoch": 0.5712056184159189, + "grad_norm": 0.5233203172683716, + "learning_rate": 4.0036523531254136e-05, + "loss": 1.6268, + "step": 10248 + }, + { + "epoch": 0.571261356669082, + "grad_norm": 0.5712999105453491, + "learning_rate": 4.0027798029936114e-05, + "loss": 1.6511, + "step": 10249 + }, + { + "epoch": 0.5713170949222451, + "grad_norm": 0.5465791821479797, + "learning_rate": 4.001907284487818e-05, + "loss": 1.554, + "step": 10250 + }, + { + "epoch": 0.5713728331754083, + "grad_norm": 0.5340691208839417, + "learning_rate": 4.0010347976357085e-05, + "loss": 1.6915, + "step": 10251 + }, + { + "epoch": 0.5714285714285714, + "grad_norm": 0.5902113914489746, + "learning_rate": 4.000162342464948e-05, + "loss": 1.8803, + "step": 10252 + }, + { + "epoch": 0.5714843096817346, + "grad_norm": 0.5747789144515991, + "learning_rate": 3.9992899190032104e-05, + "loss": 1.7181, + "step": 10253 + }, + { + "epoch": 0.5715400479348978, + "grad_norm": 0.574839174747467, + "learning_rate": 3.998417527278162e-05, + "loss": 1.8356, + "step": 10254 + }, + { + "epoch": 0.5715957861880608, + "grad_norm": 0.5555924773216248, + "learning_rate": 3.997545167317469e-05, + "loss": 1.6524, + "step": 10255 + }, + { + "epoch": 0.571651524441224, + "grad_norm": 0.5201401114463806, + "learning_rate": 3.9966728391488e-05, + "loss": 1.4982, + "step": 10256 + }, + { + "epoch": 0.5717072626943872, + "grad_norm": 0.5710572004318237, + "learning_rate": 3.995800542799818e-05, + "loss": 1.6855, + "step": 10257 + }, + { + "epoch": 0.5717630009475503, + "grad_norm": 0.5481722354888916, + "learning_rate": 3.9949282782981886e-05, + "loss": 1.6136, + "step": 10258 + }, + { + "epoch": 0.5718187392007135, + "grad_norm": 0.5805692672729492, + "learning_rate": 3.994056045671572e-05, + "loss": 1.8276, + "step": 10259 + }, + { + "epoch": 0.5718744774538767, + "grad_norm": 0.5870146155357361, + "learning_rate": 3.993183844947635e-05, + "loss": 1.8052, + "step": 10260 + }, + { + "epoch": 0.5719302157070397, + "grad_norm": 0.5496461391448975, + "learning_rate": 3.992311676154035e-05, + "loss": 1.7339, + "step": 10261 + }, + { + "epoch": 0.5719859539602029, + "grad_norm": 0.5844667553901672, + "learning_rate": 3.991439539318434e-05, + "loss": 1.593, + "step": 10262 + }, + { + "epoch": 0.572041692213366, + "grad_norm": 0.5758823156356812, + "learning_rate": 3.99056743446849e-05, + "loss": 1.5935, + "step": 10263 + }, + { + "epoch": 0.5720974304665292, + "grad_norm": 0.5993025302886963, + "learning_rate": 3.9896953616318614e-05, + "loss": 1.7039, + "step": 10264 + }, + { + "epoch": 0.5721531687196924, + "grad_norm": 0.5562222003936768, + "learning_rate": 3.988823320836207e-05, + "loss": 1.718, + "step": 10265 + }, + { + "epoch": 0.5722089069728554, + "grad_norm": 0.5475729703903198, + "learning_rate": 3.9879513121091795e-05, + "loss": 1.6327, + "step": 10266 + }, + { + "epoch": 0.5722646452260186, + "grad_norm": 0.5502913594245911, + "learning_rate": 3.987079335478435e-05, + "loss": 1.7032, + "step": 10267 + }, + { + "epoch": 0.5723203834791818, + "grad_norm": 0.5649488568305969, + "learning_rate": 3.986207390971631e-05, + "loss": 1.6994, + "step": 10268 + }, + { + "epoch": 0.5723761217323449, + "grad_norm": 0.5440324544906616, + "learning_rate": 3.985335478616415e-05, + "loss": 1.6933, + "step": 10269 + }, + { + "epoch": 0.572431859985508, + "grad_norm": 0.5091212391853333, + "learning_rate": 3.984463598440444e-05, + "loss": 1.3312, + "step": 10270 + }, + { + "epoch": 0.5724875982386712, + "grad_norm": 0.5522047877311707, + "learning_rate": 3.983591750471366e-05, + "loss": 1.5176, + "step": 10271 + }, + { + "epoch": 0.5725433364918343, + "grad_norm": 0.5953494906425476, + "learning_rate": 3.982719934736832e-05, + "loss": 1.6718, + "step": 10272 + }, + { + "epoch": 0.5725990747449975, + "grad_norm": 0.5262237191200256, + "learning_rate": 3.981848151264489e-05, + "loss": 1.6548, + "step": 10273 + }, + { + "epoch": 0.5726548129981607, + "grad_norm": 0.54544997215271, + "learning_rate": 3.9809764000819875e-05, + "loss": 1.6723, + "step": 10274 + }, + { + "epoch": 0.5727105512513238, + "grad_norm": 0.5449570417404175, + "learning_rate": 3.980104681216974e-05, + "loss": 1.673, + "step": 10275 + }, + { + "epoch": 0.5727662895044869, + "grad_norm": 0.602749228477478, + "learning_rate": 3.979232994697091e-05, + "loss": 1.2947, + "step": 10276 + }, + { + "epoch": 0.5728220277576501, + "grad_norm": 0.6310192942619324, + "learning_rate": 3.97836134054999e-05, + "loss": 1.6502, + "step": 10277 + }, + { + "epoch": 0.5728777660108132, + "grad_norm": 0.5666201114654541, + "learning_rate": 3.9774897188033064e-05, + "loss": 1.8275, + "step": 10278 + }, + { + "epoch": 0.5729335042639764, + "grad_norm": 0.5859840512275696, + "learning_rate": 3.97661812948469e-05, + "loss": 1.7393, + "step": 10279 + }, + { + "epoch": 0.5729892425171396, + "grad_norm": 0.6887635588645935, + "learning_rate": 3.975746572621778e-05, + "loss": 1.6816, + "step": 10280 + }, + { + "epoch": 0.5730449807703026, + "grad_norm": 0.5669187903404236, + "learning_rate": 3.9748750482422145e-05, + "loss": 1.5666, + "step": 10281 + }, + { + "epoch": 0.5731007190234658, + "grad_norm": 0.5395673513412476, + "learning_rate": 3.974003556373637e-05, + "loss": 1.611, + "step": 10282 + }, + { + "epoch": 0.573156457276629, + "grad_norm": 0.5382205247879028, + "learning_rate": 3.973132097043685e-05, + "loss": 1.6061, + "step": 10283 + }, + { + "epoch": 0.5732121955297921, + "grad_norm": 0.5802567601203918, + "learning_rate": 3.972260670279996e-05, + "loss": 1.7779, + "step": 10284 + }, + { + "epoch": 0.5732679337829553, + "grad_norm": 0.5593720078468323, + "learning_rate": 3.971389276110204e-05, + "loss": 1.6468, + "step": 10285 + }, + { + "epoch": 0.5733236720361183, + "grad_norm": 0.5882350206375122, + "learning_rate": 3.970517914561951e-05, + "loss": 1.6013, + "step": 10286 + }, + { + "epoch": 0.5733794102892815, + "grad_norm": 0.5444415807723999, + "learning_rate": 3.969646585662864e-05, + "loss": 1.7013, + "step": 10287 + }, + { + "epoch": 0.5734351485424447, + "grad_norm": 0.5615072846412659, + "learning_rate": 3.9687752894405804e-05, + "loss": 1.7675, + "step": 10288 + }, + { + "epoch": 0.5734908867956078, + "grad_norm": Infinity, + "learning_rate": 3.9687752894405804e-05, + "loss": 1.5965, + "step": 10289 + }, + { + "epoch": 0.573546625048771, + "grad_norm": 0.5616545677185059, + "learning_rate": 3.967904025922734e-05, + "loss": 1.6883, + "step": 10290 + }, + { + "epoch": 0.5736023633019341, + "grad_norm": 0.571757972240448, + "learning_rate": 3.9670327951369537e-05, + "loss": 1.6156, + "step": 10291 + }, + { + "epoch": 0.5736581015550972, + "grad_norm": 0.5675120949745178, + "learning_rate": 3.9661615971108706e-05, + "loss": 1.6129, + "step": 10292 + }, + { + "epoch": 0.5737138398082604, + "grad_norm": 0.6117345094680786, + "learning_rate": 3.965290431872113e-05, + "loss": 1.7097, + "step": 10293 + }, + { + "epoch": 0.5737695780614236, + "grad_norm": 0.6245883107185364, + "learning_rate": 3.9644192994483095e-05, + "loss": 1.9848, + "step": 10294 + }, + { + "epoch": 0.5738253163145867, + "grad_norm": 0.5811381936073303, + "learning_rate": 3.96354819986709e-05, + "loss": 1.7762, + "step": 10295 + }, + { + "epoch": 0.5738810545677498, + "grad_norm": 0.5340662002563477, + "learning_rate": 3.9626771331560766e-05, + "loss": 1.5887, + "step": 10296 + }, + { + "epoch": 0.573936792820913, + "grad_norm": 0.6120584011077881, + "learning_rate": 3.961806099342899e-05, + "loss": 1.8988, + "step": 10297 + }, + { + "epoch": 0.5739925310740761, + "grad_norm": 0.5624459385871887, + "learning_rate": 3.960935098455177e-05, + "loss": 1.7073, + "step": 10298 + }, + { + "epoch": 0.5740482693272393, + "grad_norm": 0.5729663968086243, + "learning_rate": 3.9600641305205365e-05, + "loss": 1.5212, + "step": 10299 + }, + { + "epoch": 0.5741040075804025, + "grad_norm": 0.552730917930603, + "learning_rate": 3.959193195566598e-05, + "loss": 1.4532, + "step": 10300 + }, + { + "epoch": 0.5741597458335655, + "grad_norm": 0.5537503361701965, + "learning_rate": 3.958322293620982e-05, + "loss": 1.7352, + "step": 10301 + }, + { + "epoch": 0.5742154840867287, + "grad_norm": 0.5406333804130554, + "learning_rate": 3.957451424711312e-05, + "loss": 1.7068, + "step": 10302 + }, + { + "epoch": 0.5742712223398919, + "grad_norm": 0.5790851712226868, + "learning_rate": 3.956580588865202e-05, + "loss": 1.8338, + "step": 10303 + }, + { + "epoch": 0.574326960593055, + "grad_norm": 0.5130342245101929, + "learning_rate": 3.955709786110274e-05, + "loss": 1.3051, + "step": 10304 + }, + { + "epoch": 0.5743826988462182, + "grad_norm": 0.5465152263641357, + "learning_rate": 3.954839016474141e-05, + "loss": 1.4312, + "step": 10305 + }, + { + "epoch": 0.5744384370993814, + "grad_norm": 0.565580427646637, + "learning_rate": 3.953968279984422e-05, + "loss": 1.6097, + "step": 10306 + }, + { + "epoch": 0.5744941753525444, + "grad_norm": 0.5684987902641296, + "learning_rate": 3.95309757666873e-05, + "loss": 1.7451, + "step": 10307 + }, + { + "epoch": 0.5745499136057076, + "grad_norm": 0.5432803630828857, + "learning_rate": 3.952226906554679e-05, + "loss": 1.8016, + "step": 10308 + }, + { + "epoch": 0.5746056518588707, + "grad_norm": 0.5711129903793335, + "learning_rate": 3.9513562696698826e-05, + "loss": 1.6584, + "step": 10309 + }, + { + "epoch": 0.5746613901120339, + "grad_norm": 0.5580195784568787, + "learning_rate": 3.9504856660419495e-05, + "loss": 1.5651, + "step": 10310 + }, + { + "epoch": 0.5747171283651971, + "grad_norm": 0.5921227931976318, + "learning_rate": 3.949615095698494e-05, + "loss": 1.7212, + "step": 10311 + }, + { + "epoch": 0.5747728666183601, + "grad_norm": 0.5192678570747375, + "learning_rate": 3.948744558667121e-05, + "loss": 1.3938, + "step": 10312 + }, + { + "epoch": 0.5748286048715233, + "grad_norm": 0.5308910012245178, + "learning_rate": 3.9478740549754444e-05, + "loss": 1.6182, + "step": 10313 + }, + { + "epoch": 0.5748843431246865, + "grad_norm": 0.5796390771865845, + "learning_rate": 3.947003584651065e-05, + "loss": 1.5559, + "step": 10314 + }, + { + "epoch": 0.5749400813778496, + "grad_norm": 0.620233952999115, + "learning_rate": 3.946133147721594e-05, + "loss": 1.8528, + "step": 10315 + }, + { + "epoch": 0.5749958196310128, + "grad_norm": 0.5096827149391174, + "learning_rate": 3.945262744214636e-05, + "loss": 1.3252, + "step": 10316 + }, + { + "epoch": 0.575051557884176, + "grad_norm": 0.5851264595985413, + "learning_rate": 3.9443923741577935e-05, + "loss": 1.6752, + "step": 10317 + }, + { + "epoch": 0.575107296137339, + "grad_norm": 0.5834670662879944, + "learning_rate": 3.943522037578671e-05, + "loss": 1.8702, + "step": 10318 + }, + { + "epoch": 0.5751630343905022, + "grad_norm": 0.5740618705749512, + "learning_rate": 3.942651734504869e-05, + "loss": 1.7431, + "step": 10319 + }, + { + "epoch": 0.5752187726436654, + "grad_norm": 0.5476807951927185, + "learning_rate": 3.9417814649639893e-05, + "loss": 1.7095, + "step": 10320 + }, + { + "epoch": 0.5752745108968285, + "grad_norm": 0.5697437524795532, + "learning_rate": 3.9409112289836305e-05, + "loss": 1.7306, + "step": 10321 + }, + { + "epoch": 0.5753302491499916, + "grad_norm": 0.5896326899528503, + "learning_rate": 3.9400410265913936e-05, + "loss": 1.5845, + "step": 10322 + }, + { + "epoch": 0.5753859874031548, + "grad_norm": 0.5682885050773621, + "learning_rate": 3.939170857814876e-05, + "loss": 1.7804, + "step": 10323 + }, + { + "epoch": 0.5754417256563179, + "grad_norm": 0.5711153745651245, + "learning_rate": 3.9383007226816726e-05, + "loss": 1.6929, + "step": 10324 + }, + { + "epoch": 0.5754974639094811, + "grad_norm": 0.5820274353027344, + "learning_rate": 3.937430621219382e-05, + "loss": 1.7542, + "step": 10325 + }, + { + "epoch": 0.5755532021626443, + "grad_norm": 0.5988385081291199, + "learning_rate": 3.936560553455595e-05, + "loss": 1.7471, + "step": 10326 + }, + { + "epoch": 0.5756089404158073, + "grad_norm": 0.5577500462532043, + "learning_rate": 3.935690519417906e-05, + "loss": 1.7389, + "step": 10327 + }, + { + "epoch": 0.5756646786689705, + "grad_norm": 0.5570036768913269, + "learning_rate": 3.934820519133912e-05, + "loss": 1.6225, + "step": 10328 + }, + { + "epoch": 0.5757204169221337, + "grad_norm": 0.6182720065116882, + "learning_rate": 3.933950552631198e-05, + "loss": 1.1692, + "step": 10329 + }, + { + "epoch": 0.5757761551752968, + "grad_norm": 0.5024303793907166, + "learning_rate": 3.9330806199373595e-05, + "loss": 1.697, + "step": 10330 + }, + { + "epoch": 0.57583189342846, + "grad_norm": 0.544809103012085, + "learning_rate": 3.9322107210799795e-05, + "loss": 1.6768, + "step": 10331 + }, + { + "epoch": 0.575887631681623, + "grad_norm": 0.5746915340423584, + "learning_rate": 3.931340856086652e-05, + "loss": 1.7127, + "step": 10332 + }, + { + "epoch": 0.5759433699347862, + "grad_norm": 0.5670152306556702, + "learning_rate": 3.930471024984961e-05, + "loss": 1.7439, + "step": 10333 + }, + { + "epoch": 0.5759991081879494, + "grad_norm": 0.5794965624809265, + "learning_rate": 3.929601227802494e-05, + "loss": 1.622, + "step": 10334 + }, + { + "epoch": 0.5760548464411125, + "grad_norm": 0.5243938565254211, + "learning_rate": 3.928731464566836e-05, + "loss": 1.5308, + "step": 10335 + }, + { + "epoch": 0.5761105846942757, + "grad_norm": 0.6057234406471252, + "learning_rate": 3.927861735305568e-05, + "loss": 1.7297, + "step": 10336 + }, + { + "epoch": 0.5761663229474389, + "grad_norm": 0.5918848514556885, + "learning_rate": 3.926992040046277e-05, + "loss": 1.8108, + "step": 10337 + }, + { + "epoch": 0.5762220612006019, + "grad_norm": 0.557761549949646, + "learning_rate": 3.926122378816539e-05, + "loss": 1.4936, + "step": 10338 + }, + { + "epoch": 0.5762777994537651, + "grad_norm": 0.5680163502693176, + "learning_rate": 3.925252751643942e-05, + "loss": 1.5076, + "step": 10339 + }, + { + "epoch": 0.5763335377069283, + "grad_norm": 0.516508162021637, + "learning_rate": 3.924383158556059e-05, + "loss": 1.7351, + "step": 10340 + }, + { + "epoch": 0.5763892759600914, + "grad_norm": 0.5683130025863647, + "learning_rate": 3.9235135995804705e-05, + "loss": 1.6554, + "step": 10341 + }, + { + "epoch": 0.5764450142132546, + "grad_norm": 0.5636241436004639, + "learning_rate": 3.9226440747447565e-05, + "loss": 1.624, + "step": 10342 + }, + { + "epoch": 0.5765007524664177, + "grad_norm": 0.53886479139328, + "learning_rate": 3.9217745840764895e-05, + "loss": 1.5321, + "step": 10343 + }, + { + "epoch": 0.5765564907195808, + "grad_norm": 0.5719546675682068, + "learning_rate": 3.920905127603247e-05, + "loss": 1.5408, + "step": 10344 + }, + { + "epoch": 0.576612228972744, + "grad_norm": 0.5249210596084595, + "learning_rate": 3.920035705352602e-05, + "loss": 1.587, + "step": 10345 + }, + { + "epoch": 0.5766679672259072, + "grad_norm": 0.563533365726471, + "learning_rate": 3.9191663173521284e-05, + "loss": 1.7007, + "step": 10346 + }, + { + "epoch": 0.5767237054790703, + "grad_norm": 0.5978162288665771, + "learning_rate": 3.918296963629395e-05, + "loss": 1.7961, + "step": 10347 + }, + { + "epoch": 0.5767794437322334, + "grad_norm": 0.5723155736923218, + "learning_rate": 3.9174276442119766e-05, + "loss": 1.5591, + "step": 10348 + }, + { + "epoch": 0.5768351819853966, + "grad_norm": 0.5694242715835571, + "learning_rate": 3.916558359127443e-05, + "loss": 1.6161, + "step": 10349 + }, + { + "epoch": 0.5768909202385597, + "grad_norm": 0.5386130213737488, + "learning_rate": 3.9156891084033596e-05, + "loss": 1.6975, + "step": 10350 + }, + { + "epoch": 0.5769466584917229, + "grad_norm": 0.5643964409828186, + "learning_rate": 3.9148198920672975e-05, + "loss": 1.7234, + "step": 10351 + }, + { + "epoch": 0.5770023967448861, + "grad_norm": 0.551584005355835, + "learning_rate": 3.913950710146819e-05, + "loss": 1.5164, + "step": 10352 + }, + { + "epoch": 0.5770581349980491, + "grad_norm": 0.60798180103302, + "learning_rate": 3.913081562669492e-05, + "loss": 1.7445, + "step": 10353 + }, + { + "epoch": 0.5771138732512123, + "grad_norm": 0.5259472131729126, + "learning_rate": 3.9122124496628836e-05, + "loss": 1.5357, + "step": 10354 + }, + { + "epoch": 0.5771696115043754, + "grad_norm": 0.5704507231712341, + "learning_rate": 3.911343371154551e-05, + "loss": 1.8522, + "step": 10355 + }, + { + "epoch": 0.5772253497575386, + "grad_norm": 0.6215217113494873, + "learning_rate": 3.9104743271720624e-05, + "loss": 2.0213, + "step": 10356 + }, + { + "epoch": 0.5772810880107018, + "grad_norm": 0.5803076028823853, + "learning_rate": 3.909605317742972e-05, + "loss": 1.8434, + "step": 10357 + }, + { + "epoch": 0.5773368262638648, + "grad_norm": 0.5362025499343872, + "learning_rate": 3.908736342894846e-05, + "loss": 1.5575, + "step": 10358 + }, + { + "epoch": 0.577392564517028, + "grad_norm": 0.5348682999610901, + "learning_rate": 3.90786740265524e-05, + "loss": 1.6087, + "step": 10359 + }, + { + "epoch": 0.5774483027701912, + "grad_norm": 0.5173177719116211, + "learning_rate": 3.9069984970517124e-05, + "loss": 1.6299, + "step": 10360 + }, + { + "epoch": 0.5775040410233543, + "grad_norm": 0.5550698637962341, + "learning_rate": 3.90612962611182e-05, + "loss": 1.7779, + "step": 10361 + }, + { + "epoch": 0.5775597792765175, + "grad_norm": 0.5339301824569702, + "learning_rate": 3.905260789863118e-05, + "loss": 1.4732, + "step": 10362 + }, + { + "epoch": 0.5776155175296807, + "grad_norm": 0.611870288848877, + "learning_rate": 3.9043919883331615e-05, + "loss": 1.7523, + "step": 10363 + }, + { + "epoch": 0.5776712557828437, + "grad_norm": 0.5385359525680542, + "learning_rate": 3.903523221549502e-05, + "loss": 1.617, + "step": 10364 + }, + { + "epoch": 0.5777269940360069, + "grad_norm": 0.5916758179664612, + "learning_rate": 3.902654489539695e-05, + "loss": 2.0081, + "step": 10365 + }, + { + "epoch": 0.5777827322891701, + "grad_norm": 0.5239583253860474, + "learning_rate": 3.901785792331287e-05, + "loss": 1.6251, + "step": 10366 + }, + { + "epoch": 0.5778384705423332, + "grad_norm": 0.5588314533233643, + "learning_rate": 3.9009171299518324e-05, + "loss": 1.6483, + "step": 10367 + }, + { + "epoch": 0.5778942087954964, + "grad_norm": 0.5109575986862183, + "learning_rate": 3.9000485024288784e-05, + "loss": 1.3879, + "step": 10368 + }, + { + "epoch": 0.5779499470486595, + "grad_norm": 0.5284083485603333, + "learning_rate": 3.899179909789972e-05, + "loss": 1.548, + "step": 10369 + }, + { + "epoch": 0.5780056853018226, + "grad_norm": 0.6521651744842529, + "learning_rate": 3.898311352062662e-05, + "loss": 1.9616, + "step": 10370 + }, + { + "epoch": 0.5780614235549858, + "grad_norm": 0.607297956943512, + "learning_rate": 3.8974428292744914e-05, + "loss": 1.7795, + "step": 10371 + }, + { + "epoch": 0.578117161808149, + "grad_norm": 0.5658968687057495, + "learning_rate": 3.896574341453007e-05, + "loss": 1.6974, + "step": 10372 + }, + { + "epoch": 0.5781729000613121, + "grad_norm": 0.5024977922439575, + "learning_rate": 3.895705888625748e-05, + "loss": 1.4682, + "step": 10373 + }, + { + "epoch": 0.5782286383144752, + "grad_norm": 0.5308341383934021, + "learning_rate": 3.894837470820262e-05, + "loss": 1.4336, + "step": 10374 + }, + { + "epoch": 0.5782843765676384, + "grad_norm": 0.5695244073867798, + "learning_rate": 3.8939690880640885e-05, + "loss": 1.6593, + "step": 10375 + }, + { + "epoch": 0.5783401148208015, + "grad_norm": 0.5992659330368042, + "learning_rate": 3.893100740384766e-05, + "loss": 1.6772, + "step": 10376 + }, + { + "epoch": 0.5783958530739647, + "grad_norm": 0.5644543766975403, + "learning_rate": 3.8922324278098356e-05, + "loss": 1.7087, + "step": 10377 + }, + { + "epoch": 0.5784515913271278, + "grad_norm": 0.5220384001731873, + "learning_rate": 3.891364150366832e-05, + "loss": 1.4623, + "step": 10378 + }, + { + "epoch": 0.5785073295802909, + "grad_norm": 0.5461076498031616, + "learning_rate": 3.890495908083293e-05, + "loss": 1.6518, + "step": 10379 + }, + { + "epoch": 0.5785630678334541, + "grad_norm": 0.5484482049942017, + "learning_rate": 3.889627700986759e-05, + "loss": 1.5737, + "step": 10380 + }, + { + "epoch": 0.5786188060866172, + "grad_norm": 0.5702036023139954, + "learning_rate": 3.8887595291047564e-05, + "loss": 1.5644, + "step": 10381 + }, + { + "epoch": 0.5786745443397804, + "grad_norm": 0.5962613224983215, + "learning_rate": 3.887891392464825e-05, + "loss": 1.8534, + "step": 10382 + }, + { + "epoch": 0.5787302825929436, + "grad_norm": 0.6296350359916687, + "learning_rate": 3.8870232910944924e-05, + "loss": 1.8821, + "step": 10383 + }, + { + "epoch": 0.5787860208461066, + "grad_norm": 0.5504742860794067, + "learning_rate": 3.886155225021294e-05, + "loss": 1.8454, + "step": 10384 + }, + { + "epoch": 0.5788417590992698, + "grad_norm": 0.5213546752929688, + "learning_rate": 3.885287194272757e-05, + "loss": 1.4968, + "step": 10385 + }, + { + "epoch": 0.578897497352433, + "grad_norm": 0.5692139267921448, + "learning_rate": 3.884419198876411e-05, + "loss": 1.7601, + "step": 10386 + }, + { + "epoch": 0.5789532356055961, + "grad_norm": 0.5776494145393372, + "learning_rate": 3.8835512388597836e-05, + "loss": 1.7149, + "step": 10387 + }, + { + "epoch": 0.5790089738587593, + "grad_norm": 0.5485444068908691, + "learning_rate": 3.8826833142504006e-05, + "loss": 1.6867, + "step": 10388 + }, + { + "epoch": 0.5790647121119225, + "grad_norm": 0.5601508021354675, + "learning_rate": 3.881815425075791e-05, + "loss": 1.6042, + "step": 10389 + }, + { + "epoch": 0.5791204503650855, + "grad_norm": 0.5325314998626709, + "learning_rate": 3.880947571363474e-05, + "loss": 1.7868, + "step": 10390 + }, + { + "epoch": 0.5791761886182487, + "grad_norm": 0.5936904549598694, + "learning_rate": 3.880079753140978e-05, + "loss": 1.8606, + "step": 10391 + }, + { + "epoch": 0.5792319268714119, + "grad_norm": 0.5427181720733643, + "learning_rate": 3.87921197043582e-05, + "loss": 1.5603, + "step": 10392 + }, + { + "epoch": 0.579287665124575, + "grad_norm": 0.5596809387207031, + "learning_rate": 3.878344223275524e-05, + "loss": 1.9158, + "step": 10393 + }, + { + "epoch": 0.5793434033777382, + "grad_norm": 0.5559753179550171, + "learning_rate": 3.877476511687611e-05, + "loss": 1.62, + "step": 10394 + }, + { + "epoch": 0.5793991416309013, + "grad_norm": 0.5727944374084473, + "learning_rate": 3.8766088356995976e-05, + "loss": 1.5055, + "step": 10395 + }, + { + "epoch": 0.5794548798840644, + "grad_norm": 0.6167700290679932, + "learning_rate": 3.875741195339003e-05, + "loss": 1.7256, + "step": 10396 + }, + { + "epoch": 0.5795106181372276, + "grad_norm": 0.5643514394760132, + "learning_rate": 3.874873590633341e-05, + "loss": 1.6768, + "step": 10397 + }, + { + "epoch": 0.5795663563903908, + "grad_norm": 0.5504075884819031, + "learning_rate": 3.874006021610131e-05, + "loss": 1.676, + "step": 10398 + }, + { + "epoch": 0.5796220946435539, + "grad_norm": 0.5333808064460754, + "learning_rate": 3.8731384882968824e-05, + "loss": 1.5099, + "step": 10399 + }, + { + "epoch": 0.579677832896717, + "grad_norm": 0.5340782999992371, + "learning_rate": 3.872270990721112e-05, + "loss": 1.7212, + "step": 10400 + }, + { + "epoch": 0.5797335711498801, + "grad_norm": 0.5497784614562988, + "learning_rate": 3.8714035289103314e-05, + "loss": 1.66, + "step": 10401 + }, + { + "epoch": 0.5797893094030433, + "grad_norm": 0.5847936868667603, + "learning_rate": 3.8705361028920494e-05, + "loss": 1.7655, + "step": 10402 + }, + { + "epoch": 0.5798450476562065, + "grad_norm": 0.5303927659988403, + "learning_rate": 3.869668712693778e-05, + "loss": 1.5689, + "step": 10403 + }, + { + "epoch": 0.5799007859093696, + "grad_norm": 0.5461509823799133, + "learning_rate": 3.868801358343025e-05, + "loss": 1.6214, + "step": 10404 + }, + { + "epoch": 0.5799565241625327, + "grad_norm": 0.5522668957710266, + "learning_rate": 3.8679340398672953e-05, + "loss": 1.5918, + "step": 10405 + }, + { + "epoch": 0.5800122624156959, + "grad_norm": 0.5287279486656189, + "learning_rate": 3.867066757294101e-05, + "loss": 1.5958, + "step": 10406 + }, + { + "epoch": 0.580068000668859, + "grad_norm": 0.5924019813537598, + "learning_rate": 3.866199510650941e-05, + "loss": 1.6475, + "step": 10407 + }, + { + "epoch": 0.5801237389220222, + "grad_norm": 0.5650224685668945, + "learning_rate": 3.865332299965323e-05, + "loss": 1.6921, + "step": 10408 + }, + { + "epoch": 0.5801794771751854, + "grad_norm": 0.5323730707168579, + "learning_rate": 3.864465125264749e-05, + "loss": 1.5513, + "step": 10409 + }, + { + "epoch": 0.5802352154283484, + "grad_norm": 0.5714460611343384, + "learning_rate": 3.8635979865767205e-05, + "loss": 1.6684, + "step": 10410 + }, + { + "epoch": 0.5802909536815116, + "grad_norm": 0.5639826059341431, + "learning_rate": 3.862730883928738e-05, + "loss": 1.6376, + "step": 10411 + }, + { + "epoch": 0.5803466919346748, + "grad_norm": 0.5803040266036987, + "learning_rate": 3.8618638173483014e-05, + "loss": 1.8236, + "step": 10412 + }, + { + "epoch": 0.5804024301878379, + "grad_norm": 0.566265344619751, + "learning_rate": 3.860996786862909e-05, + "loss": 1.4877, + "step": 10413 + }, + { + "epoch": 0.5804581684410011, + "grad_norm": 0.5610904097557068, + "learning_rate": 3.860129792500056e-05, + "loss": 1.6582, + "step": 10414 + }, + { + "epoch": 0.5805139066941643, + "grad_norm": 0.5860254764556885, + "learning_rate": 3.859262834287243e-05, + "loss": 1.6139, + "step": 10415 + }, + { + "epoch": 0.5805696449473273, + "grad_norm": 0.5870318412780762, + "learning_rate": 3.8583959122519585e-05, + "loss": 1.6614, + "step": 10416 + }, + { + "epoch": 0.5806253832004905, + "grad_norm": 0.5830135941505432, + "learning_rate": 3.8575290264217036e-05, + "loss": 1.7069, + "step": 10417 + }, + { + "epoch": 0.5806811214536537, + "grad_norm": 0.5582641959190369, + "learning_rate": 3.8566621768239634e-05, + "loss": 1.604, + "step": 10418 + }, + { + "epoch": 0.5807368597068168, + "grad_norm": 0.6204952001571655, + "learning_rate": 3.855795363486233e-05, + "loss": 1.9387, + "step": 10419 + }, + { + "epoch": 0.58079259795998, + "grad_norm": 0.5565268993377686, + "learning_rate": 3.854928586436005e-05, + "loss": 1.8071, + "step": 10420 + }, + { + "epoch": 0.5808483362131431, + "grad_norm": 0.5894541144371033, + "learning_rate": 3.854061845700764e-05, + "loss": 1.7062, + "step": 10421 + }, + { + "epoch": 0.5809040744663062, + "grad_norm": 0.5459067821502686, + "learning_rate": 3.853195141308001e-05, + "loss": 1.6668, + "step": 10422 + }, + { + "epoch": 0.5809598127194694, + "grad_norm": 0.5536026954650879, + "learning_rate": 3.852328473285201e-05, + "loss": 1.6721, + "step": 10423 + }, + { + "epoch": 0.5810155509726325, + "grad_norm": 0.5301326513290405, + "learning_rate": 3.851461841659851e-05, + "loss": 1.503, + "step": 10424 + }, + { + "epoch": 0.5810712892257957, + "grad_norm": 0.5645812153816223, + "learning_rate": 3.850595246459434e-05, + "loss": 1.6078, + "step": 10425 + }, + { + "epoch": 0.5811270274789588, + "grad_norm": 0.5299369692802429, + "learning_rate": 3.849728687711435e-05, + "loss": 1.4543, + "step": 10426 + }, + { + "epoch": 0.5811827657321219, + "grad_norm": 0.5582391619682312, + "learning_rate": 3.8488621654433356e-05, + "loss": 1.4153, + "step": 10427 + }, + { + "epoch": 0.5812385039852851, + "grad_norm": 0.5766590237617493, + "learning_rate": 3.8479956796826164e-05, + "loss": 1.8426, + "step": 10428 + }, + { + "epoch": 0.5812942422384483, + "grad_norm": 0.5900693535804749, + "learning_rate": 3.8471292304567586e-05, + "loss": 1.9991, + "step": 10429 + }, + { + "epoch": 0.5813499804916114, + "grad_norm": 0.5874468088150024, + "learning_rate": 3.8462628177932386e-05, + "loss": 1.7196, + "step": 10430 + }, + { + "epoch": 0.5814057187447745, + "grad_norm": 0.5636804699897766, + "learning_rate": 3.845396441719537e-05, + "loss": 1.6985, + "step": 10431 + }, + { + "epoch": 0.5814614569979377, + "grad_norm": 0.5602846145629883, + "learning_rate": 3.844530102263126e-05, + "loss": 1.729, + "step": 10432 + }, + { + "epoch": 0.5815171952511008, + "grad_norm": 0.5678505301475525, + "learning_rate": 3.843663799451483e-05, + "loss": 1.602, + "step": 10433 + }, + { + "epoch": 0.581572933504264, + "grad_norm": 0.5459701418876648, + "learning_rate": 3.842797533312085e-05, + "loss": 1.6195, + "step": 10434 + }, + { + "epoch": 0.5816286717574272, + "grad_norm": 0.5326259732246399, + "learning_rate": 3.841931303872401e-05, + "loss": 1.5695, + "step": 10435 + }, + { + "epoch": 0.5816844100105902, + "grad_norm": 0.5516942143440247, + "learning_rate": 3.841065111159905e-05, + "loss": 1.5744, + "step": 10436 + }, + { + "epoch": 0.5817401482637534, + "grad_norm": 0.5589244365692139, + "learning_rate": 3.8401989552020654e-05, + "loss": 1.5559, + "step": 10437 + }, + { + "epoch": 0.5817958865169166, + "grad_norm": 0.5421091318130493, + "learning_rate": 3.839332836026353e-05, + "loss": 1.5991, + "step": 10438 + }, + { + "epoch": 0.5818516247700797, + "grad_norm": 0.5204689502716064, + "learning_rate": 3.838466753660237e-05, + "loss": 1.3576, + "step": 10439 + }, + { + "epoch": 0.5819073630232429, + "grad_norm": 0.6035448312759399, + "learning_rate": 3.837600708131181e-05, + "loss": 1.7927, + "step": 10440 + }, + { + "epoch": 0.581963101276406, + "grad_norm": 0.5337579250335693, + "learning_rate": 3.836734699466656e-05, + "loss": 1.6014, + "step": 10441 + }, + { + "epoch": 0.5820188395295691, + "grad_norm": 0.604854166507721, + "learning_rate": 3.835868727694122e-05, + "loss": 1.7221, + "step": 10442 + }, + { + "epoch": 0.5820745777827323, + "grad_norm": 0.5534946918487549, + "learning_rate": 3.835002792841047e-05, + "loss": 1.5634, + "step": 10443 + }, + { + "epoch": 0.5821303160358955, + "grad_norm": 0.5689296126365662, + "learning_rate": 3.834136894934888e-05, + "loss": 1.6135, + "step": 10444 + }, + { + "epoch": 0.5821860542890586, + "grad_norm": 0.5645999312400818, + "learning_rate": 3.833271034003111e-05, + "loss": 1.3717, + "step": 10445 + }, + { + "epoch": 0.5822417925422217, + "grad_norm": 0.6080798506736755, + "learning_rate": 3.832405210073174e-05, + "loss": 1.5761, + "step": 10446 + }, + { + "epoch": 0.5822975307953848, + "grad_norm": 0.5378057360649109, + "learning_rate": 3.831539423172536e-05, + "loss": 1.6861, + "step": 10447 + }, + { + "epoch": 0.582353269048548, + "grad_norm": 0.576270341873169, + "learning_rate": 3.8306736733286555e-05, + "loss": 1.6967, + "step": 10448 + }, + { + "epoch": 0.5824090073017112, + "grad_norm": 0.6018567681312561, + "learning_rate": 3.829807960568988e-05, + "loss": 1.9025, + "step": 10449 + }, + { + "epoch": 0.5824647455548743, + "grad_norm": 0.6117346286773682, + "learning_rate": 3.8289422849209896e-05, + "loss": 1.8112, + "step": 10450 + }, + { + "epoch": 0.5825204838080374, + "grad_norm": 0.5422847270965576, + "learning_rate": 3.8280766464121134e-05, + "loss": 1.5044, + "step": 10451 + }, + { + "epoch": 0.5825762220612006, + "grad_norm": 0.5537722110748291, + "learning_rate": 3.827211045069813e-05, + "loss": 1.6428, + "step": 10452 + }, + { + "epoch": 0.5826319603143637, + "grad_norm": 0.6170569062232971, + "learning_rate": 3.826345480921542e-05, + "loss": 1.7481, + "step": 10453 + }, + { + "epoch": 0.5826876985675269, + "grad_norm": 0.5351431369781494, + "learning_rate": 3.825479953994748e-05, + "loss": 1.6192, + "step": 10454 + }, + { + "epoch": 0.5827434368206901, + "grad_norm": 0.5633178353309631, + "learning_rate": 3.824614464316883e-05, + "loss": 1.6705, + "step": 10455 + }, + { + "epoch": 0.5827991750738531, + "grad_norm": 0.5995389223098755, + "learning_rate": 3.8237490119153934e-05, + "loss": 1.7806, + "step": 10456 + }, + { + "epoch": 0.5828549133270163, + "grad_norm": 0.5304275751113892, + "learning_rate": 3.822883596817728e-05, + "loss": 1.5233, + "step": 10457 + }, + { + "epoch": 0.5829106515801795, + "grad_norm": 0.5443453788757324, + "learning_rate": 3.822018219051331e-05, + "loss": 1.6379, + "step": 10458 + }, + { + "epoch": 0.5829663898333426, + "grad_norm": 0.5200064778327942, + "learning_rate": 3.821152878643647e-05, + "loss": 1.5846, + "step": 10459 + }, + { + "epoch": 0.5830221280865058, + "grad_norm": 0.5608554482460022, + "learning_rate": 3.820287575622122e-05, + "loss": 1.5801, + "step": 10460 + }, + { + "epoch": 0.583077866339669, + "grad_norm": 0.5903092622756958, + "learning_rate": 3.8194223100141965e-05, + "loss": 1.6576, + "step": 10461 + }, + { + "epoch": 0.583133604592832, + "grad_norm": 0.5784822106361389, + "learning_rate": 3.818557081847313e-05, + "loss": 1.8402, + "step": 10462 + }, + { + "epoch": 0.5831893428459952, + "grad_norm": 0.5177431702613831, + "learning_rate": 3.81769189114891e-05, + "loss": 1.2378, + "step": 10463 + }, + { + "epoch": 0.5832450810991584, + "grad_norm": 0.5646283626556396, + "learning_rate": 3.8168267379464263e-05, + "loss": 1.6343, + "step": 10464 + }, + { + "epoch": 0.5833008193523215, + "grad_norm": 0.5550134778022766, + "learning_rate": 3.815961622267301e-05, + "loss": 1.6733, + "step": 10465 + }, + { + "epoch": 0.5833565576054847, + "grad_norm": 0.6027835011482239, + "learning_rate": 3.8150965441389674e-05, + "loss": 1.6899, + "step": 10466 + }, + { + "epoch": 0.5834122958586478, + "grad_norm": 0.5438368916511536, + "learning_rate": 3.814231503588867e-05, + "loss": 1.6729, + "step": 10467 + }, + { + "epoch": 0.5834680341118109, + "grad_norm": 0.5765901803970337, + "learning_rate": 3.8133665006444255e-05, + "loss": 1.794, + "step": 10468 + }, + { + "epoch": 0.5835237723649741, + "grad_norm": 0.6034119725227356, + "learning_rate": 3.812501535333083e-05, + "loss": 1.9005, + "step": 10469 + }, + { + "epoch": 0.5835795106181372, + "grad_norm": 0.5628261566162109, + "learning_rate": 3.811636607682267e-05, + "loss": 1.75, + "step": 10470 + }, + { + "epoch": 0.5836352488713004, + "grad_norm": 0.6064727902412415, + "learning_rate": 3.810771717719409e-05, + "loss": 1.83, + "step": 10471 + }, + { + "epoch": 0.5836909871244635, + "grad_norm": 0.5413762331008911, + "learning_rate": 3.80990686547194e-05, + "loss": 1.6382, + "step": 10472 + }, + { + "epoch": 0.5837467253776266, + "grad_norm": 0.5523511171340942, + "learning_rate": 3.809042050967285e-05, + "loss": 1.4951, + "step": 10473 + }, + { + "epoch": 0.5838024636307898, + "grad_norm": 0.5516862273216248, + "learning_rate": 3.808177274232873e-05, + "loss": 1.5714, + "step": 10474 + }, + { + "epoch": 0.583858201883953, + "grad_norm": 0.5366679430007935, + "learning_rate": 3.807312535296127e-05, + "loss": 1.6896, + "step": 10475 + }, + { + "epoch": 0.5839139401371161, + "grad_norm": 0.5850146412849426, + "learning_rate": 3.806447834184477e-05, + "loss": 1.6643, + "step": 10476 + }, + { + "epoch": 0.5839696783902792, + "grad_norm": 0.5514613389968872, + "learning_rate": 3.8055831709253396e-05, + "loss": 1.6747, + "step": 10477 + }, + { + "epoch": 0.5840254166434424, + "grad_norm": 0.5313770771026611, + "learning_rate": 3.804718545546142e-05, + "loss": 1.7009, + "step": 10478 + }, + { + "epoch": 0.5840811548966055, + "grad_norm": 0.5248450040817261, + "learning_rate": 3.803853958074303e-05, + "loss": 1.4489, + "step": 10479 + }, + { + "epoch": 0.5841368931497687, + "grad_norm": 0.8921785950660706, + "learning_rate": 3.802989408537242e-05, + "loss": 1.5598, + "step": 10480 + }, + { + "epoch": 0.5841926314029319, + "grad_norm": 0.5542730689048767, + "learning_rate": 3.802124896962379e-05, + "loss": 1.6924, + "step": 10481 + }, + { + "epoch": 0.584248369656095, + "grad_norm": 0.5227362513542175, + "learning_rate": 3.801260423377129e-05, + "loss": 1.479, + "step": 10482 + }, + { + "epoch": 0.5843041079092581, + "grad_norm": 0.5378886461257935, + "learning_rate": 3.8003959878089104e-05, + "loss": 1.5304, + "step": 10483 + }, + { + "epoch": 0.5843598461624213, + "grad_norm": 0.554295003414154, + "learning_rate": 3.7995315902851354e-05, + "loss": 1.4134, + "step": 10484 + }, + { + "epoch": 0.5844155844155844, + "grad_norm": 0.5478252172470093, + "learning_rate": 3.798667230833218e-05, + "loss": 1.8024, + "step": 10485 + }, + { + "epoch": 0.5844713226687476, + "grad_norm": 0.5450767874717712, + "learning_rate": 3.797802909480574e-05, + "loss": 1.7916, + "step": 10486 + }, + { + "epoch": 0.5845270609219108, + "grad_norm": 0.6002693176269531, + "learning_rate": 3.796938626254612e-05, + "loss": 1.6446, + "step": 10487 + }, + { + "epoch": 0.5845827991750738, + "grad_norm": 0.5589439272880554, + "learning_rate": 3.796074381182743e-05, + "loss": 1.5499, + "step": 10488 + }, + { + "epoch": 0.584638537428237, + "grad_norm": 0.5932784676551819, + "learning_rate": 3.795210174292374e-05, + "loss": 1.661, + "step": 10489 + }, + { + "epoch": 0.5846942756814002, + "grad_norm": 0.7987622618675232, + "learning_rate": 3.794346005610914e-05, + "loss": 1.9696, + "step": 10490 + }, + { + "epoch": 0.5847500139345633, + "grad_norm": 0.5644296407699585, + "learning_rate": 3.7934818751657706e-05, + "loss": 1.6024, + "step": 10491 + }, + { + "epoch": 0.5848057521877265, + "grad_norm": 0.5474801659584045, + "learning_rate": 3.792617782984346e-05, + "loss": 1.5879, + "step": 10492 + }, + { + "epoch": 0.5848614904408895, + "grad_norm": 0.5493007302284241, + "learning_rate": 3.791753729094048e-05, + "loss": 1.5693, + "step": 10493 + }, + { + "epoch": 0.5849172286940527, + "grad_norm": 0.5822592973709106, + "learning_rate": 3.790889713522274e-05, + "loss": 1.7629, + "step": 10494 + }, + { + "epoch": 0.5849729669472159, + "grad_norm": 0.5798677206039429, + "learning_rate": 3.7900257362964314e-05, + "loss": 1.8306, + "step": 10495 + }, + { + "epoch": 0.585028705200379, + "grad_norm": 0.5388454794883728, + "learning_rate": 3.7891617974439165e-05, + "loss": 1.6657, + "step": 10496 + }, + { + "epoch": 0.5850844434535422, + "grad_norm": 0.5188543796539307, + "learning_rate": 3.7882978969921296e-05, + "loss": 1.6045, + "step": 10497 + }, + { + "epoch": 0.5851401817067053, + "grad_norm": 0.5407771468162537, + "learning_rate": 3.78743403496847e-05, + "loss": 1.6769, + "step": 10498 + }, + { + "epoch": 0.5851959199598684, + "grad_norm": 0.5791205763816833, + "learning_rate": 3.7865702114003314e-05, + "loss": 1.5448, + "step": 10499 + }, + { + "epoch": 0.5852516582130316, + "grad_norm": 0.574635922908783, + "learning_rate": 3.785706426315113e-05, + "loss": 1.8509, + "step": 10500 + }, + { + "epoch": 0.5853073964661948, + "grad_norm": 0.5714727640151978, + "learning_rate": 3.7848426797402034e-05, + "loss": 1.856, + "step": 10501 + }, + { + "epoch": 0.5853631347193579, + "grad_norm": 0.558771014213562, + "learning_rate": 3.783978971703003e-05, + "loss": 1.6842, + "step": 10502 + }, + { + "epoch": 0.585418872972521, + "grad_norm": 0.6013060808181763, + "learning_rate": 3.783115302230897e-05, + "loss": 1.8741, + "step": 10503 + }, + { + "epoch": 0.5854746112256842, + "grad_norm": 0.5288045406341553, + "learning_rate": 3.7822516713512795e-05, + "loss": 1.669, + "step": 10504 + }, + { + "epoch": 0.5855303494788473, + "grad_norm": 0.5664896368980408, + "learning_rate": 3.78138807909154e-05, + "loss": 1.7707, + "step": 10505 + }, + { + "epoch": 0.5855860877320105, + "grad_norm": 0.6236469745635986, + "learning_rate": 3.7805245254790646e-05, + "loss": 2.0792, + "step": 10506 + }, + { + "epoch": 0.5856418259851737, + "grad_norm": 0.5737569332122803, + "learning_rate": 3.779661010541242e-05, + "loss": 1.7686, + "step": 10507 + }, + { + "epoch": 0.5856975642383367, + "grad_norm": 0.5788602232933044, + "learning_rate": 3.778797534305456e-05, + "loss": 1.751, + "step": 10508 + }, + { + "epoch": 0.5857533024914999, + "grad_norm": 0.5300620794296265, + "learning_rate": 3.777934096799094e-05, + "loss": 1.7072, + "step": 10509 + }, + { + "epoch": 0.5858090407446631, + "grad_norm": 0.5347722768783569, + "learning_rate": 3.777070698049535e-05, + "loss": 1.4512, + "step": 10510 + }, + { + "epoch": 0.5858647789978262, + "grad_norm": 0.5386114716529846, + "learning_rate": 3.7762073380841634e-05, + "loss": 1.6386, + "step": 10511 + }, + { + "epoch": 0.5859205172509894, + "grad_norm": 0.545583963394165, + "learning_rate": 3.775344016930361e-05, + "loss": 1.4614, + "step": 10512 + }, + { + "epoch": 0.5859762555041526, + "grad_norm": 0.540080726146698, + "learning_rate": 3.774480734615506e-05, + "loss": 1.3026, + "step": 10513 + }, + { + "epoch": 0.5860319937573156, + "grad_norm": 0.5793723464012146, + "learning_rate": 3.7736174911669776e-05, + "loss": 1.664, + "step": 10514 + }, + { + "epoch": 0.5860877320104788, + "grad_norm": 0.5617543458938599, + "learning_rate": 3.77275428661215e-05, + "loss": 1.7944, + "step": 10515 + }, + { + "epoch": 0.5861434702636419, + "grad_norm": 0.5727483630180359, + "learning_rate": 3.7718911209784026e-05, + "loss": 1.6576, + "step": 10516 + }, + { + "epoch": 0.5861992085168051, + "grad_norm": 0.614232063293457, + "learning_rate": 3.771027994293109e-05, + "loss": 1.968, + "step": 10517 + }, + { + "epoch": 0.5862549467699683, + "grad_norm": 0.5104675889015198, + "learning_rate": 3.7701649065836394e-05, + "loss": 1.754, + "step": 10518 + }, + { + "epoch": 0.5863106850231313, + "grad_norm": 0.5460989475250244, + "learning_rate": 3.769301857877372e-05, + "loss": 1.4775, + "step": 10519 + }, + { + "epoch": 0.5863664232762945, + "grad_norm": 0.5603992342948914, + "learning_rate": 3.768438848201671e-05, + "loss": 1.6659, + "step": 10520 + }, + { + "epoch": 0.5864221615294577, + "grad_norm": 0.5435361862182617, + "learning_rate": 3.767575877583912e-05, + "loss": 1.6178, + "step": 10521 + }, + { + "epoch": 0.5864778997826208, + "grad_norm": 0.5277562737464905, + "learning_rate": 3.7667129460514585e-05, + "loss": 1.5179, + "step": 10522 + }, + { + "epoch": 0.586533638035784, + "grad_norm": 0.5214918851852417, + "learning_rate": 3.76585005363168e-05, + "loss": 1.6504, + "step": 10523 + }, + { + "epoch": 0.5865893762889471, + "grad_norm": 0.5323712229728699, + "learning_rate": 3.764987200351944e-05, + "loss": 1.468, + "step": 10524 + }, + { + "epoch": 0.5866451145421102, + "grad_norm": 0.5450025796890259, + "learning_rate": 3.764124386239611e-05, + "loss": 1.6458, + "step": 10525 + }, + { + "epoch": 0.5867008527952734, + "grad_norm": 0.5709915161132812, + "learning_rate": 3.7632616113220495e-05, + "loss": 1.7088, + "step": 10526 + }, + { + "epoch": 0.5867565910484366, + "grad_norm": 0.5776938199996948, + "learning_rate": 3.762398875626616e-05, + "loss": 1.5763, + "step": 10527 + }, + { + "epoch": 0.5868123293015997, + "grad_norm": 0.5697132349014282, + "learning_rate": 3.761536179180678e-05, + "loss": 1.639, + "step": 10528 + }, + { + "epoch": 0.5868680675547628, + "grad_norm": 0.5992898941040039, + "learning_rate": 3.760673522011588e-05, + "loss": 1.6822, + "step": 10529 + }, + { + "epoch": 0.586923805807926, + "grad_norm": 0.5981577634811401, + "learning_rate": 3.7598109041467094e-05, + "loss": 1.7807, + "step": 10530 + }, + { + "epoch": 0.5869795440610891, + "grad_norm": 0.5266358852386475, + "learning_rate": 3.758948325613399e-05, + "loss": 1.6093, + "step": 10531 + }, + { + "epoch": 0.5870352823142523, + "grad_norm": 0.5778212547302246, + "learning_rate": 3.758085786439011e-05, + "loss": 1.6115, + "step": 10532 + }, + { + "epoch": 0.5870910205674155, + "grad_norm": 0.5699662566184998, + "learning_rate": 3.757223286650902e-05, + "loss": 1.6165, + "step": 10533 + }, + { + "epoch": 0.5871467588205785, + "grad_norm": 0.6047526597976685, + "learning_rate": 3.756360826276424e-05, + "loss": 1.7445, + "step": 10534 + }, + { + "epoch": 0.5872024970737417, + "grad_norm": 0.5751059651374817, + "learning_rate": 3.75549840534293e-05, + "loss": 1.6591, + "step": 10535 + }, + { + "epoch": 0.5872582353269049, + "grad_norm": 0.5245922207832336, + "learning_rate": 3.7546360238777694e-05, + "loss": 1.6325, + "step": 10536 + }, + { + "epoch": 0.587313973580068, + "grad_norm": 0.5294795632362366, + "learning_rate": 3.753773681908292e-05, + "loss": 1.6007, + "step": 10537 + }, + { + "epoch": 0.5873697118332312, + "grad_norm": 0.5342444181442261, + "learning_rate": 3.75291137946185e-05, + "loss": 1.6943, + "step": 10538 + }, + { + "epoch": 0.5874254500863942, + "grad_norm": 0.5659368634223938, + "learning_rate": 3.7520491165657875e-05, + "loss": 1.538, + "step": 10539 + }, + { + "epoch": 0.5874811883395574, + "grad_norm": 0.5024417638778687, + "learning_rate": 3.751186893247452e-05, + "loss": 1.7185, + "step": 10540 + }, + { + "epoch": 0.5875369265927206, + "grad_norm": 0.553939700126648, + "learning_rate": 3.750324709534185e-05, + "loss": 1.6519, + "step": 10541 + }, + { + "epoch": 0.5875926648458837, + "grad_norm": 0.5790380239486694, + "learning_rate": 3.749462565453333e-05, + "loss": 1.783, + "step": 10542 + }, + { + "epoch": 0.5876484030990469, + "grad_norm": 0.5356141328811646, + "learning_rate": 3.748600461032238e-05, + "loss": 1.4267, + "step": 10543 + }, + { + "epoch": 0.58770414135221, + "grad_norm": 0.5545246601104736, + "learning_rate": 3.7477383962982374e-05, + "loss": 1.6198, + "step": 10544 + }, + { + "epoch": 0.5877598796053731, + "grad_norm": 0.5444962978363037, + "learning_rate": 3.746876371278678e-05, + "loss": 1.501, + "step": 10545 + }, + { + "epoch": 0.5878156178585363, + "grad_norm": 0.5676127076148987, + "learning_rate": 3.74601438600089e-05, + "loss": 1.7348, + "step": 10546 + }, + { + "epoch": 0.5878713561116995, + "grad_norm": 0.5442788004875183, + "learning_rate": 3.745152440492217e-05, + "loss": 1.6013, + "step": 10547 + }, + { + "epoch": 0.5879270943648626, + "grad_norm": 0.543764054775238, + "learning_rate": 3.744290534779991e-05, + "loss": 1.5797, + "step": 10548 + }, + { + "epoch": 0.5879828326180258, + "grad_norm": 0.5701844692230225, + "learning_rate": 3.7434286688915474e-05, + "loss": 1.6181, + "step": 10549 + }, + { + "epoch": 0.5880385708711889, + "grad_norm": 0.558018147945404, + "learning_rate": 3.742566842854222e-05, + "loss": 1.7129, + "step": 10550 + }, + { + "epoch": 0.588094309124352, + "grad_norm": 0.617866575717926, + "learning_rate": 3.741705056695344e-05, + "loss": 1.8679, + "step": 10551 + }, + { + "epoch": 0.5881500473775152, + "grad_norm": 0.5197618007659912, + "learning_rate": 3.7408433104422455e-05, + "loss": 1.2723, + "step": 10552 + }, + { + "epoch": 0.5882057856306784, + "grad_norm": 0.6245566606521606, + "learning_rate": 3.739981604122254e-05, + "loss": 1.8093, + "step": 10553 + }, + { + "epoch": 0.5882615238838415, + "grad_norm": 0.5682582855224609, + "learning_rate": 3.739119937762703e-05, + "loss": 1.7748, + "step": 10554 + }, + { + "epoch": 0.5883172621370046, + "grad_norm": 0.5899463891983032, + "learning_rate": 3.738258311390913e-05, + "loss": 1.874, + "step": 10555 + }, + { + "epoch": 0.5883730003901678, + "grad_norm": 0.587677001953125, + "learning_rate": 3.737396725034214e-05, + "loss": 1.7739, + "step": 10556 + }, + { + "epoch": 0.5884287386433309, + "grad_norm": 0.5093933939933777, + "learning_rate": 3.7365351787199305e-05, + "loss": 1.3497, + "step": 10557 + }, + { + "epoch": 0.5884844768964941, + "grad_norm": 0.5440930128097534, + "learning_rate": 3.7356736724753834e-05, + "loss": 1.5436, + "step": 10558 + }, + { + "epoch": 0.5885402151496573, + "grad_norm": 0.531604528427124, + "learning_rate": 3.734812206327897e-05, + "loss": 1.5924, + "step": 10559 + }, + { + "epoch": 0.5885959534028203, + "grad_norm": 0.593714714050293, + "learning_rate": 3.73395078030479e-05, + "loss": 1.9695, + "step": 10560 + }, + { + "epoch": 0.5886516916559835, + "grad_norm": 0.5461561679840088, + "learning_rate": 3.733089394433383e-05, + "loss": 1.5767, + "step": 10561 + }, + { + "epoch": 0.5887074299091466, + "grad_norm": 0.5576294660568237, + "learning_rate": 3.732228048740992e-05, + "loss": 1.6256, + "step": 10562 + }, + { + "epoch": 0.5887631681623098, + "grad_norm": 0.5713305473327637, + "learning_rate": 3.731366743254937e-05, + "loss": 1.7033, + "step": 10563 + }, + { + "epoch": 0.588818906415473, + "grad_norm": 0.5811915397644043, + "learning_rate": 3.730505478002533e-05, + "loss": 1.8645, + "step": 10564 + }, + { + "epoch": 0.588874644668636, + "grad_norm": 0.5555295348167419, + "learning_rate": 3.7296442530110934e-05, + "loss": 1.6798, + "step": 10565 + }, + { + "epoch": 0.5889303829217992, + "grad_norm": 0.6551502346992493, + "learning_rate": 3.728783068307931e-05, + "loss": 1.9067, + "step": 10566 + }, + { + "epoch": 0.5889861211749624, + "grad_norm": 0.6149044036865234, + "learning_rate": 3.727921923920358e-05, + "loss": 1.7204, + "step": 10567 + }, + { + "epoch": 0.5890418594281255, + "grad_norm": 0.635021448135376, + "learning_rate": 3.7270608198756854e-05, + "loss": 1.8126, + "step": 10568 + }, + { + "epoch": 0.5890975976812887, + "grad_norm": 0.813902735710144, + "learning_rate": 3.726199756201221e-05, + "loss": 1.5697, + "step": 10569 + }, + { + "epoch": 0.5891533359344518, + "grad_norm": 0.6003322005271912, + "learning_rate": 3.7253387329242726e-05, + "loss": 1.6158, + "step": 10570 + }, + { + "epoch": 0.5892090741876149, + "grad_norm": 0.5682037472724915, + "learning_rate": 3.7244777500721504e-05, + "loss": 1.6502, + "step": 10571 + }, + { + "epoch": 0.5892648124407781, + "grad_norm": 0.6143748164176941, + "learning_rate": 3.723616807672155e-05, + "loss": 1.9357, + "step": 10572 + }, + { + "epoch": 0.5893205506939413, + "grad_norm": 0.5592736005783081, + "learning_rate": 3.722755905751594e-05, + "loss": 1.7127, + "step": 10573 + }, + { + "epoch": 0.5893762889471044, + "grad_norm": 0.5672972798347473, + "learning_rate": 3.7218950443377676e-05, + "loss": 1.6027, + "step": 10574 + }, + { + "epoch": 0.5894320272002675, + "grad_norm": 0.5966082215309143, + "learning_rate": 3.7210342234579785e-05, + "loss": 1.8543, + "step": 10575 + }, + { + "epoch": 0.5894877654534307, + "grad_norm": 0.5324078798294067, + "learning_rate": 3.720173443139528e-05, + "loss": 1.6043, + "step": 10576 + }, + { + "epoch": 0.5895435037065938, + "grad_norm": 0.5152407884597778, + "learning_rate": 3.7193127034097144e-05, + "loss": 1.4774, + "step": 10577 + }, + { + "epoch": 0.589599241959757, + "grad_norm": 0.5895288586616516, + "learning_rate": 3.718452004295835e-05, + "loss": 1.8391, + "step": 10578 + }, + { + "epoch": 0.5896549802129202, + "grad_norm": 0.5626966953277588, + "learning_rate": 3.717591345825183e-05, + "loss": 1.8092, + "step": 10579 + }, + { + "epoch": 0.5897107184660833, + "grad_norm": 0.5412726402282715, + "learning_rate": 3.7167307280250607e-05, + "loss": 1.5544, + "step": 10580 + }, + { + "epoch": 0.5897664567192464, + "grad_norm": 0.5498217940330505, + "learning_rate": 3.7158701509227544e-05, + "loss": 1.8257, + "step": 10581 + }, + { + "epoch": 0.5898221949724096, + "grad_norm": 0.5844752788543701, + "learning_rate": 3.715009614545561e-05, + "loss": 1.8018, + "step": 10582 + }, + { + "epoch": 0.5898779332255727, + "grad_norm": 0.5298795700073242, + "learning_rate": 3.714149118920772e-05, + "loss": 1.6239, + "step": 10583 + }, + { + "epoch": 0.5899336714787359, + "grad_norm": 0.5541282296180725, + "learning_rate": 3.713288664075674e-05, + "loss": 1.7372, + "step": 10584 + }, + { + "epoch": 0.589989409731899, + "grad_norm": 0.5731157064437866, + "learning_rate": 3.7124282500375597e-05, + "loss": 1.7206, + "step": 10585 + }, + { + "epoch": 0.5900451479850621, + "grad_norm": 0.5772982239723206, + "learning_rate": 3.711567876833712e-05, + "loss": 1.8214, + "step": 10586 + }, + { + "epoch": 0.5901008862382253, + "grad_norm": 0.6069211959838867, + "learning_rate": 3.710707544491421e-05, + "loss": 1.9289, + "step": 10587 + }, + { + "epoch": 0.5901566244913884, + "grad_norm": 0.582378089427948, + "learning_rate": 3.709847253037967e-05, + "loss": 1.6522, + "step": 10588 + }, + { + "epoch": 0.5902123627445516, + "grad_norm": 0.5845189690589905, + "learning_rate": 3.7089870025006374e-05, + "loss": 1.7481, + "step": 10589 + }, + { + "epoch": 0.5902681009977148, + "grad_norm": 0.5751447677612305, + "learning_rate": 3.708126792906714e-05, + "loss": 1.4827, + "step": 10590 + }, + { + "epoch": 0.5903238392508778, + "grad_norm": 0.5446940660476685, + "learning_rate": 3.707266624283475e-05, + "loss": 1.6345, + "step": 10591 + }, + { + "epoch": 0.590379577504041, + "grad_norm": 0.5264309048652649, + "learning_rate": 3.706406496658204e-05, + "loss": 1.675, + "step": 10592 + }, + { + "epoch": 0.5904353157572042, + "grad_norm": 0.5321794748306274, + "learning_rate": 3.705546410058175e-05, + "loss": 1.6043, + "step": 10593 + }, + { + "epoch": 0.5904910540103673, + "grad_norm": 0.568670928478241, + "learning_rate": 3.704686364510667e-05, + "loss": 1.799, + "step": 10594 + }, + { + "epoch": 0.5905467922635305, + "grad_norm": 0.5585296154022217, + "learning_rate": 3.703826360042954e-05, + "loss": 1.6559, + "step": 10595 + }, + { + "epoch": 0.5906025305166936, + "grad_norm": 0.5437737107276917, + "learning_rate": 3.702966396682312e-05, + "loss": 1.7088, + "step": 10596 + }, + { + "epoch": 0.5906582687698567, + "grad_norm": 0.5538874268531799, + "learning_rate": 3.702106474456016e-05, + "loss": 1.845, + "step": 10597 + }, + { + "epoch": 0.5907140070230199, + "grad_norm": 0.5787869095802307, + "learning_rate": 3.701246593391332e-05, + "loss": 1.6807, + "step": 10598 + }, + { + "epoch": 0.5907697452761831, + "grad_norm": 0.5712507963180542, + "learning_rate": 3.7003867535155365e-05, + "loss": 1.6427, + "step": 10599 + }, + { + "epoch": 0.5908254835293462, + "grad_norm": 0.5915331244468689, + "learning_rate": 3.699526954855895e-05, + "loss": 1.7423, + "step": 10600 + }, + { + "epoch": 0.5908812217825093, + "grad_norm": 0.5464789271354675, + "learning_rate": 3.6986671974396755e-05, + "loss": 1.5484, + "step": 10601 + }, + { + "epoch": 0.5909369600356725, + "grad_norm": 0.58048015832901, + "learning_rate": 3.697807481294146e-05, + "loss": 1.694, + "step": 10602 + }, + { + "epoch": 0.5909926982888356, + "grad_norm": 0.5703095197677612, + "learning_rate": 3.696947806446571e-05, + "loss": 1.7923, + "step": 10603 + }, + { + "epoch": 0.5910484365419988, + "grad_norm": 0.5519693493843079, + "learning_rate": 3.696088172924215e-05, + "loss": 1.506, + "step": 10604 + }, + { + "epoch": 0.591104174795162, + "grad_norm": 0.6527479887008667, + "learning_rate": 3.695228580754337e-05, + "loss": 1.6042, + "step": 10605 + }, + { + "epoch": 0.591159913048325, + "grad_norm": 0.58185213804245, + "learning_rate": 3.6943690299642055e-05, + "loss": 1.5731, + "step": 10606 + }, + { + "epoch": 0.5912156513014882, + "grad_norm": 0.5212710499763489, + "learning_rate": 3.693509520581072e-05, + "loss": 1.3331, + "step": 10607 + }, + { + "epoch": 0.5912713895546513, + "grad_norm": 0.5953770279884338, + "learning_rate": 3.6926500526322e-05, + "loss": 1.7033, + "step": 10608 + }, + { + "epoch": 0.5913271278078145, + "grad_norm": 0.5897699594497681, + "learning_rate": 3.6917906261448473e-05, + "loss": 1.8765, + "step": 10609 + }, + { + "epoch": 0.5913828660609777, + "grad_norm": 0.5852439999580383, + "learning_rate": 3.6909312411462675e-05, + "loss": 1.6823, + "step": 10610 + }, + { + "epoch": 0.5914386043141407, + "grad_norm": 0.5378084182739258, + "learning_rate": 3.6900718976637174e-05, + "loss": 1.6476, + "step": 10611 + }, + { + "epoch": 0.5914943425673039, + "grad_norm": 0.5815349221229553, + "learning_rate": 3.6892125957244484e-05, + "loss": 1.7493, + "step": 10612 + }, + { + "epoch": 0.5915500808204671, + "grad_norm": 0.5775283575057983, + "learning_rate": 3.688353335355714e-05, + "loss": 1.5932, + "step": 10613 + }, + { + "epoch": 0.5916058190736302, + "grad_norm": 0.5364789962768555, + "learning_rate": 3.687494116584763e-05, + "loss": 1.6508, + "step": 10614 + }, + { + "epoch": 0.5916615573267934, + "grad_norm": 0.5703774690628052, + "learning_rate": 3.6866349394388465e-05, + "loss": 1.6409, + "step": 10615 + }, + { + "epoch": 0.5917172955799566, + "grad_norm": 0.575446367263794, + "learning_rate": 3.6857758039452135e-05, + "loss": 1.6912, + "step": 10616 + }, + { + "epoch": 0.5917730338331196, + "grad_norm": 0.5789859294891357, + "learning_rate": 3.6849167101311086e-05, + "loss": 1.646, + "step": 10617 + }, + { + "epoch": 0.5918287720862828, + "grad_norm": 0.5376462340354919, + "learning_rate": 3.68405765802378e-05, + "loss": 1.5624, + "step": 10618 + }, + { + "epoch": 0.591884510339446, + "grad_norm": 0.5628196001052856, + "learning_rate": 3.683198647650468e-05, + "loss": 1.7411, + "step": 10619 + }, + { + "epoch": 0.5919402485926091, + "grad_norm": 0.566883385181427, + "learning_rate": 3.6823396790384176e-05, + "loss": 1.6677, + "step": 10620 + }, + { + "epoch": 0.5919959868457723, + "grad_norm": 0.570627748966217, + "learning_rate": 3.681480752214871e-05, + "loss": 1.6784, + "step": 10621 + }, + { + "epoch": 0.5920517250989354, + "grad_norm": 0.5927448868751526, + "learning_rate": 3.6806218672070644e-05, + "loss": 2.0557, + "step": 10622 + }, + { + "epoch": 0.5921074633520985, + "grad_norm": 0.5723655223846436, + "learning_rate": 3.6797630240422445e-05, + "loss": 1.637, + "step": 10623 + }, + { + "epoch": 0.5921632016052617, + "grad_norm": 0.5774400234222412, + "learning_rate": 3.67890422274764e-05, + "loss": 1.6871, + "step": 10624 + }, + { + "epoch": 0.5922189398584249, + "grad_norm": 0.560175359249115, + "learning_rate": 3.678045463350493e-05, + "loss": 1.5928, + "step": 10625 + }, + { + "epoch": 0.592274678111588, + "grad_norm": 0.5461480021476746, + "learning_rate": 3.677186745878036e-05, + "loss": 1.5871, + "step": 10626 + }, + { + "epoch": 0.5923304163647511, + "grad_norm": 0.5419283509254456, + "learning_rate": 3.676328070357503e-05, + "loss": 1.5642, + "step": 10627 + }, + { + "epoch": 0.5923861546179143, + "grad_norm": 0.5696420669555664, + "learning_rate": 3.6754694368161264e-05, + "loss": 1.711, + "step": 10628 + }, + { + "epoch": 0.5924418928710774, + "grad_norm": 0.5280278921127319, + "learning_rate": 3.6746108452811344e-05, + "loss": 1.2255, + "step": 10629 + }, + { + "epoch": 0.5924976311242406, + "grad_norm": 0.5472394227981567, + "learning_rate": 3.6737522957797635e-05, + "loss": 1.5926, + "step": 10630 + }, + { + "epoch": 0.5925533693774037, + "grad_norm": 0.6041975617408752, + "learning_rate": 3.6728937883392326e-05, + "loss": 2.0771, + "step": 10631 + }, + { + "epoch": 0.5926091076305668, + "grad_norm": 0.5683224201202393, + "learning_rate": 3.672035322986777e-05, + "loss": 1.7859, + "step": 10632 + }, + { + "epoch": 0.59266484588373, + "grad_norm": 0.5793581604957581, + "learning_rate": 3.671176899749614e-05, + "loss": 1.6532, + "step": 10633 + }, + { + "epoch": 0.5927205841368931, + "grad_norm": 0.5718412399291992, + "learning_rate": 3.670318518654975e-05, + "loss": 1.5604, + "step": 10634 + }, + { + "epoch": 0.5927763223900563, + "grad_norm": 0.5807404518127441, + "learning_rate": 3.66946017973008e-05, + "loss": 1.6858, + "step": 10635 + }, + { + "epoch": 0.5928320606432195, + "grad_norm": 0.5799666047096252, + "learning_rate": 3.668601883002149e-05, + "loss": 1.4864, + "step": 10636 + }, + { + "epoch": 0.5928877988963825, + "grad_norm": 0.6206822395324707, + "learning_rate": 3.667743628498406e-05, + "loss": 1.7848, + "step": 10637 + }, + { + "epoch": 0.5929435371495457, + "grad_norm": 0.5985648036003113, + "learning_rate": 3.6668854162460667e-05, + "loss": 1.7601, + "step": 10638 + }, + { + "epoch": 0.5929992754027089, + "grad_norm": 0.579348087310791, + "learning_rate": 3.666027246272349e-05, + "loss": 1.8047, + "step": 10639 + }, + { + "epoch": 0.593055013655872, + "grad_norm": 0.5877785682678223, + "learning_rate": 3.665169118604468e-05, + "loss": 1.6072, + "step": 10640 + }, + { + "epoch": 0.5931107519090352, + "grad_norm": 0.579860508441925, + "learning_rate": 3.6643110332696404e-05, + "loss": 1.768, + "step": 10641 + }, + { + "epoch": 0.5931664901621984, + "grad_norm": 0.5771205425262451, + "learning_rate": 3.663452990295081e-05, + "loss": 1.7465, + "step": 10642 + }, + { + "epoch": 0.5932222284153614, + "grad_norm": 0.5102217197418213, + "learning_rate": 3.662594989707999e-05, + "loss": 1.5842, + "step": 10643 + }, + { + "epoch": 0.5932779666685246, + "grad_norm": 0.6734121441841125, + "learning_rate": 3.661737031535608e-05, + "loss": 2.1065, + "step": 10644 + }, + { + "epoch": 0.5933337049216878, + "grad_norm": 0.5396010279655457, + "learning_rate": 3.660879115805114e-05, + "loss": 1.6108, + "step": 10645 + }, + { + "epoch": 0.5933894431748509, + "grad_norm": 0.5581656694412231, + "learning_rate": 3.6600212425437275e-05, + "loss": 1.6259, + "step": 10646 + }, + { + "epoch": 0.5934451814280141, + "grad_norm": 0.5051550269126892, + "learning_rate": 3.659163411778654e-05, + "loss": 1.5076, + "step": 10647 + }, + { + "epoch": 0.5935009196811772, + "grad_norm": 0.6038596034049988, + "learning_rate": 3.658305623537098e-05, + "loss": 1.8803, + "step": 10648 + }, + { + "epoch": 0.5935566579343403, + "grad_norm": 0.5228748917579651, + "learning_rate": 3.6574478778462676e-05, + "loss": 1.4336, + "step": 10649 + }, + { + "epoch": 0.5936123961875035, + "grad_norm": 0.5188995599746704, + "learning_rate": 3.6565901747333616e-05, + "loss": 1.5946, + "step": 10650 + }, + { + "epoch": 0.5936681344406667, + "grad_norm": 0.6071973443031311, + "learning_rate": 3.655732514225584e-05, + "loss": 1.9025, + "step": 10651 + }, + { + "epoch": 0.5937238726938298, + "grad_norm": 0.5159845948219299, + "learning_rate": 3.654874896350132e-05, + "loss": 1.5769, + "step": 10652 + }, + { + "epoch": 0.5937796109469929, + "grad_norm": 0.5195660591125488, + "learning_rate": 3.654017321134206e-05, + "loss": 1.5514, + "step": 10653 + }, + { + "epoch": 0.593835349200156, + "grad_norm": 0.5409337878227234, + "learning_rate": 3.653159788605004e-05, + "loss": 1.4165, + "step": 10654 + }, + { + "epoch": 0.5938910874533192, + "grad_norm": 0.5055655241012573, + "learning_rate": 3.652302298789718e-05, + "loss": 1.4697, + "step": 10655 + }, + { + "epoch": 0.5939468257064824, + "grad_norm": 0.5607792735099792, + "learning_rate": 3.65144485171555e-05, + "loss": 1.6819, + "step": 10656 + }, + { + "epoch": 0.5940025639596455, + "grad_norm": 0.6190406680107117, + "learning_rate": 3.6505874474096844e-05, + "loss": 1.8052, + "step": 10657 + }, + { + "epoch": 0.5940583022128086, + "grad_norm": 0.6234287619590759, + "learning_rate": 3.649730085899321e-05, + "loss": 2.0106, + "step": 10658 + }, + { + "epoch": 0.5941140404659718, + "grad_norm": 0.5554551482200623, + "learning_rate": 3.648872767211643e-05, + "loss": 1.3272, + "step": 10659 + }, + { + "epoch": 0.5941697787191349, + "grad_norm": 0.5771641731262207, + "learning_rate": 3.648015491373845e-05, + "loss": 1.6486, + "step": 10660 + }, + { + "epoch": 0.5942255169722981, + "grad_norm": 0.5576834082603455, + "learning_rate": 3.6471582584131135e-05, + "loss": 1.6681, + "step": 10661 + }, + { + "epoch": 0.5942812552254613, + "grad_norm": 0.5702229142189026, + "learning_rate": 3.6463010683566336e-05, + "loss": 1.7256, + "step": 10662 + }, + { + "epoch": 0.5943369934786243, + "grad_norm": 0.5582361817359924, + "learning_rate": 3.645443921231592e-05, + "loss": 1.5431, + "step": 10663 + }, + { + "epoch": 0.5943927317317875, + "grad_norm": 0.5515589714050293, + "learning_rate": 3.644586817065171e-05, + "loss": 1.6071, + "step": 10664 + }, + { + "epoch": 0.5944484699849507, + "grad_norm": 0.6197267174720764, + "learning_rate": 3.643729755884554e-05, + "loss": 1.6828, + "step": 10665 + }, + { + "epoch": 0.5945042082381138, + "grad_norm": 0.5776437520980835, + "learning_rate": 3.6428727377169195e-05, + "loss": 1.4355, + "step": 10666 + }, + { + "epoch": 0.594559946491277, + "grad_norm": 0.5944076776504517, + "learning_rate": 3.642015762589451e-05, + "loss": 1.8823, + "step": 10667 + }, + { + "epoch": 0.5946156847444402, + "grad_norm": 0.5644761919975281, + "learning_rate": 3.6411588305293255e-05, + "loss": 1.6855, + "step": 10668 + }, + { + "epoch": 0.5946714229976032, + "grad_norm": 0.5875162482261658, + "learning_rate": 3.640301941563717e-05, + "loss": 1.6565, + "step": 10669 + }, + { + "epoch": 0.5947271612507664, + "grad_norm": 0.5691081881523132, + "learning_rate": 3.639445095719807e-05, + "loss": 1.7644, + "step": 10670 + }, + { + "epoch": 0.5947828995039296, + "grad_norm": 0.5673412084579468, + "learning_rate": 3.638588293024763e-05, + "loss": 1.595, + "step": 10671 + }, + { + "epoch": 0.5948386377570927, + "grad_norm": 0.5375627875328064, + "learning_rate": 3.637731533505762e-05, + "loss": 1.7064, + "step": 10672 + }, + { + "epoch": 0.5948943760102559, + "grad_norm": 0.563486635684967, + "learning_rate": 3.6368748171899734e-05, + "loss": 1.6056, + "step": 10673 + }, + { + "epoch": 0.594950114263419, + "grad_norm": 0.5447495579719543, + "learning_rate": 3.636018144104567e-05, + "loss": 1.6079, + "step": 10674 + }, + { + "epoch": 0.5950058525165821, + "grad_norm": 0.6056522727012634, + "learning_rate": 3.6351615142767146e-05, + "loss": 1.7554, + "step": 10675 + }, + { + "epoch": 0.5950615907697453, + "grad_norm": 0.5688165426254272, + "learning_rate": 3.634304927733581e-05, + "loss": 1.6637, + "step": 10676 + }, + { + "epoch": 0.5951173290229084, + "grad_norm": 0.5747976303100586, + "learning_rate": 3.633448384502333e-05, + "loss": 1.4985, + "step": 10677 + }, + { + "epoch": 0.5951730672760716, + "grad_norm": 0.5755765438079834, + "learning_rate": 3.632591884610133e-05, + "loss": 1.5359, + "step": 10678 + }, + { + "epoch": 0.5952288055292347, + "grad_norm": 0.6509361863136292, + "learning_rate": 3.631735428084148e-05, + "loss": 1.9455, + "step": 10679 + }, + { + "epoch": 0.5952845437823978, + "grad_norm": 0.5636258721351624, + "learning_rate": 3.630879014951536e-05, + "loss": 1.5867, + "step": 10680 + }, + { + "epoch": 0.595340282035561, + "grad_norm": 0.5509964227676392, + "learning_rate": 3.6300226452394584e-05, + "loss": 1.6271, + "step": 10681 + }, + { + "epoch": 0.5953960202887242, + "grad_norm": 0.5601130723953247, + "learning_rate": 3.629166318975078e-05, + "loss": 1.7173, + "step": 10682 + }, + { + "epoch": 0.5954517585418873, + "grad_norm": 0.5896451473236084, + "learning_rate": 3.628310036185546e-05, + "loss": 1.7909, + "step": 10683 + }, + { + "epoch": 0.5955074967950504, + "grad_norm": 0.5564537644386292, + "learning_rate": 3.6274537968980255e-05, + "loss": 1.6348, + "step": 10684 + }, + { + "epoch": 0.5955632350482136, + "grad_norm": 0.5651112794876099, + "learning_rate": 3.6265976011396655e-05, + "loss": 1.7643, + "step": 10685 + }, + { + "epoch": 0.5956189733013767, + "grad_norm": 0.5091538429260254, + "learning_rate": 3.625741448937622e-05, + "loss": 1.5047, + "step": 10686 + }, + { + "epoch": 0.5956747115545399, + "grad_norm": 0.6056941747665405, + "learning_rate": 3.6248853403190484e-05, + "loss": 1.7784, + "step": 10687 + }, + { + "epoch": 0.5957304498077031, + "grad_norm": 0.5621974468231201, + "learning_rate": 3.624029275311094e-05, + "loss": 1.6646, + "step": 10688 + }, + { + "epoch": 0.5957861880608661, + "grad_norm": 0.6054074168205261, + "learning_rate": 3.6231732539409095e-05, + "loss": 1.8714, + "step": 10689 + }, + { + "epoch": 0.5958419263140293, + "grad_norm": 0.5782527923583984, + "learning_rate": 3.6223172762356404e-05, + "loss": 1.7925, + "step": 10690 + }, + { + "epoch": 0.5958976645671925, + "grad_norm": 0.5137213468551636, + "learning_rate": 3.621461342222436e-05, + "loss": 1.5877, + "step": 10691 + }, + { + "epoch": 0.5959534028203556, + "grad_norm": 0.6089626550674438, + "learning_rate": 3.62060545192844e-05, + "loss": 2.0101, + "step": 10692 + }, + { + "epoch": 0.5960091410735188, + "grad_norm": 0.6029727458953857, + "learning_rate": 3.6197496053807954e-05, + "loss": 1.8824, + "step": 10693 + }, + { + "epoch": 0.596064879326682, + "grad_norm": 0.597644031047821, + "learning_rate": 3.6188938026066476e-05, + "loss": 1.8954, + "step": 10694 + }, + { + "epoch": 0.596120617579845, + "grad_norm": 0.5832270383834839, + "learning_rate": 3.618038043633135e-05, + "loss": 1.8127, + "step": 10695 + }, + { + "epoch": 0.5961763558330082, + "grad_norm": 0.533963680267334, + "learning_rate": 3.617182328487399e-05, + "loss": 1.7617, + "step": 10696 + }, + { + "epoch": 0.5962320940861714, + "grad_norm": 0.5463215708732605, + "learning_rate": 3.616326657196577e-05, + "loss": 1.7745, + "step": 10697 + }, + { + "epoch": 0.5962878323393345, + "grad_norm": 0.5657750368118286, + "learning_rate": 3.615471029787807e-05, + "loss": 1.7582, + "step": 10698 + }, + { + "epoch": 0.5963435705924977, + "grad_norm": 0.6177558898925781, + "learning_rate": 3.614615446288222e-05, + "loss": 1.7778, + "step": 10699 + }, + { + "epoch": 0.5963993088456607, + "grad_norm": 0.5581892728805542, + "learning_rate": 3.6137599067249566e-05, + "loss": 1.4981, + "step": 10700 + }, + { + "epoch": 0.5964550470988239, + "grad_norm": 0.5763764381408691, + "learning_rate": 3.612904411125147e-05, + "loss": 1.7714, + "step": 10701 + }, + { + "epoch": 0.5965107853519871, + "grad_norm": 0.5390127897262573, + "learning_rate": 3.6120489595159214e-05, + "loss": 1.5728, + "step": 10702 + }, + { + "epoch": 0.5965665236051502, + "grad_norm": 0.563076376914978, + "learning_rate": 3.611193551924411e-05, + "loss": 1.6069, + "step": 10703 + }, + { + "epoch": 0.5966222618583134, + "grad_norm": 0.5416215658187866, + "learning_rate": 3.610338188377743e-05, + "loss": 1.4952, + "step": 10704 + }, + { + "epoch": 0.5966780001114765, + "grad_norm": 0.6353267431259155, + "learning_rate": 3.609482868903046e-05, + "loss": 1.8509, + "step": 10705 + }, + { + "epoch": 0.5967337383646396, + "grad_norm": 0.5492638349533081, + "learning_rate": 3.6086275935274446e-05, + "loss": 1.5773, + "step": 10706 + }, + { + "epoch": 0.5967894766178028, + "grad_norm": 0.5659378170967102, + "learning_rate": 3.607772362278063e-05, + "loss": 1.5693, + "step": 10707 + }, + { + "epoch": 0.596845214870966, + "grad_norm": 0.582631528377533, + "learning_rate": 3.606917175182027e-05, + "loss": 1.5673, + "step": 10708 + }, + { + "epoch": 0.596900953124129, + "grad_norm": 0.5583199858665466, + "learning_rate": 3.606062032266453e-05, + "loss": 1.8263, + "step": 10709 + }, + { + "epoch": 0.5969566913772922, + "grad_norm": 0.5515373945236206, + "learning_rate": 3.605206933558467e-05, + "loss": 1.4876, + "step": 10710 + }, + { + "epoch": 0.5970124296304554, + "grad_norm": 0.5634705424308777, + "learning_rate": 3.6043518790851824e-05, + "loss": 1.5723, + "step": 10711 + }, + { + "epoch": 0.5970681678836185, + "grad_norm": 0.5301898121833801, + "learning_rate": 3.60349686887372e-05, + "loss": 1.6389, + "step": 10712 + }, + { + "epoch": 0.5971239061367817, + "grad_norm": 0.5615551471710205, + "learning_rate": 3.602641902951196e-05, + "loss": 1.7281, + "step": 10713 + }, + { + "epoch": 0.5971796443899449, + "grad_norm": 0.5689008235931396, + "learning_rate": 3.601786981344722e-05, + "loss": 1.7753, + "step": 10714 + }, + { + "epoch": 0.5972353826431079, + "grad_norm": 0.5843450427055359, + "learning_rate": 3.600932104081414e-05, + "loss": 1.75, + "step": 10715 + }, + { + "epoch": 0.5972911208962711, + "grad_norm": 0.5649077892303467, + "learning_rate": 3.6000772711883805e-05, + "loss": 1.7143, + "step": 10716 + }, + { + "epoch": 0.5973468591494343, + "grad_norm": 0.5699289441108704, + "learning_rate": 3.599222482692737e-05, + "loss": 1.831, + "step": 10717 + }, + { + "epoch": 0.5974025974025974, + "grad_norm": 0.5822247266769409, + "learning_rate": 3.598367738621586e-05, + "loss": 1.6298, + "step": 10718 + }, + { + "epoch": 0.5974583356557606, + "grad_norm": 0.5153210163116455, + "learning_rate": 3.5975130390020396e-05, + "loss": 1.4701, + "step": 10719 + }, + { + "epoch": 0.5975140739089237, + "grad_norm": 0.5386978983879089, + "learning_rate": 3.596658383861203e-05, + "loss": 1.5741, + "step": 10720 + }, + { + "epoch": 0.5975698121620868, + "grad_norm": 0.586660623550415, + "learning_rate": 3.5958037732261804e-05, + "loss": 1.737, + "step": 10721 + }, + { + "epoch": 0.59762555041525, + "grad_norm": 0.5435377359390259, + "learning_rate": 3.594949207124075e-05, + "loss": 1.5736, + "step": 10722 + }, + { + "epoch": 0.5976812886684131, + "grad_norm": 0.5378552079200745, + "learning_rate": 3.594094685581989e-05, + "loss": 1.5723, + "step": 10723 + }, + { + "epoch": 0.5977370269215763, + "grad_norm": 0.5955055356025696, + "learning_rate": 3.5932402086270225e-05, + "loss": 1.5994, + "step": 10724 + }, + { + "epoch": 0.5977927651747394, + "grad_norm": 0.6412666440010071, + "learning_rate": 3.592385776286274e-05, + "loss": 1.9002, + "step": 10725 + }, + { + "epoch": 0.5978485034279025, + "grad_norm": 0.5329419374465942, + "learning_rate": 3.5915313885868405e-05, + "loss": 1.4599, + "step": 10726 + }, + { + "epoch": 0.5979042416810657, + "grad_norm": 0.5248754024505615, + "learning_rate": 3.590677045555822e-05, + "loss": 1.4763, + "step": 10727 + }, + { + "epoch": 0.5979599799342289, + "grad_norm": 0.5744431614875793, + "learning_rate": 3.589822747220308e-05, + "loss": 1.6913, + "step": 10728 + }, + { + "epoch": 0.598015718187392, + "grad_norm": 0.5648195743560791, + "learning_rate": 3.588968493607398e-05, + "loss": 1.6534, + "step": 10729 + }, + { + "epoch": 0.5980714564405551, + "grad_norm": 0.52918541431427, + "learning_rate": 3.588114284744177e-05, + "loss": 1.6151, + "step": 10730 + }, + { + "epoch": 0.5981271946937183, + "grad_norm": 0.5425333976745605, + "learning_rate": 3.587260120657742e-05, + "loss": 1.4861, + "step": 10731 + }, + { + "epoch": 0.5981829329468814, + "grad_norm": 0.6288706660270691, + "learning_rate": 3.5864060013751775e-05, + "loss": 1.984, + "step": 10732 + }, + { + "epoch": 0.5982386712000446, + "grad_norm": 0.6068618297576904, + "learning_rate": 3.585551926923572e-05, + "loss": 2.0094, + "step": 10733 + }, + { + "epoch": 0.5982944094532078, + "grad_norm": 0.546398401260376, + "learning_rate": 3.5846978973300146e-05, + "loss": 1.6148, + "step": 10734 + }, + { + "epoch": 0.5983501477063708, + "grad_norm": 0.5468116998672485, + "learning_rate": 3.5838439126215863e-05, + "loss": 1.6965, + "step": 10735 + }, + { + "epoch": 0.598405885959534, + "grad_norm": 0.5598884224891663, + "learning_rate": 3.582989972825374e-05, + "loss": 1.5948, + "step": 10736 + }, + { + "epoch": 0.5984616242126972, + "grad_norm": 0.6028941869735718, + "learning_rate": 3.5821360779684564e-05, + "loss": 1.8262, + "step": 10737 + }, + { + "epoch": 0.5985173624658603, + "grad_norm": 0.6217941045761108, + "learning_rate": 3.581282228077916e-05, + "loss": 1.9408, + "step": 10738 + }, + { + "epoch": 0.5985731007190235, + "grad_norm": 0.5594194531440735, + "learning_rate": 3.580428423180833e-05, + "loss": 1.7485, + "step": 10739 + }, + { + "epoch": 0.5986288389721867, + "grad_norm": 0.5369617938995361, + "learning_rate": 3.5795746633042825e-05, + "loss": 1.5062, + "step": 10740 + }, + { + "epoch": 0.5986845772253497, + "grad_norm": 0.5273184180259705, + "learning_rate": 3.578720948475343e-05, + "loss": 1.6942, + "step": 10741 + }, + { + "epoch": 0.5987403154785129, + "grad_norm": 0.5254104137420654, + "learning_rate": 3.5778672787210866e-05, + "loss": 1.5236, + "step": 10742 + }, + { + "epoch": 0.5987960537316761, + "grad_norm": 0.578599214553833, + "learning_rate": 3.5770136540685915e-05, + "loss": 1.7426, + "step": 10743 + }, + { + "epoch": 0.5988517919848392, + "grad_norm": 0.6897125840187073, + "learning_rate": 3.576160074544923e-05, + "loss": 1.724, + "step": 10744 + }, + { + "epoch": 0.5989075302380024, + "grad_norm": 0.5394157767295837, + "learning_rate": 3.575306540177157e-05, + "loss": 1.6856, + "step": 10745 + }, + { + "epoch": 0.5989632684911654, + "grad_norm": 0.5963736176490784, + "learning_rate": 3.5744530509923624e-05, + "loss": 1.6754, + "step": 10746 + }, + { + "epoch": 0.5990190067443286, + "grad_norm": 0.5288623571395874, + "learning_rate": 3.5735996070176036e-05, + "loss": 1.4265, + "step": 10747 + }, + { + "epoch": 0.5990747449974918, + "grad_norm": 0.6559962034225464, + "learning_rate": 3.57274620827995e-05, + "loss": 1.6428, + "step": 10748 + }, + { + "epoch": 0.5991304832506549, + "grad_norm": 0.563292920589447, + "learning_rate": 3.571892854806464e-05, + "loss": 1.5636, + "step": 10749 + }, + { + "epoch": 0.5991862215038181, + "grad_norm": 0.5565873980522156, + "learning_rate": 3.5710395466242126e-05, + "loss": 1.6054, + "step": 10750 + }, + { + "epoch": 0.5992419597569812, + "grad_norm": 0.5816026329994202, + "learning_rate": 3.570186283760254e-05, + "loss": 1.753, + "step": 10751 + }, + { + "epoch": 0.5992976980101443, + "grad_norm": 0.5431708693504333, + "learning_rate": 3.569333066241648e-05, + "loss": 1.4766, + "step": 10752 + }, + { + "epoch": 0.5993534362633075, + "grad_norm": 0.5268303751945496, + "learning_rate": 3.568479894095458e-05, + "loss": 1.5641, + "step": 10753 + }, + { + "epoch": 0.5994091745164707, + "grad_norm": 0.5448703169822693, + "learning_rate": 3.567626767348739e-05, + "loss": 1.528, + "step": 10754 + }, + { + "epoch": 0.5994649127696338, + "grad_norm": 0.5704829096794128, + "learning_rate": 3.5667736860285485e-05, + "loss": 1.8203, + "step": 10755 + }, + { + "epoch": 0.599520651022797, + "grad_norm": 0.5476005673408508, + "learning_rate": 3.5659206501619385e-05, + "loss": 1.6485, + "step": 10756 + }, + { + "epoch": 0.5995763892759601, + "grad_norm": 0.5662007927894592, + "learning_rate": 3.565067659775966e-05, + "loss": 1.7586, + "step": 10757 + }, + { + "epoch": 0.5996321275291232, + "grad_norm": 0.5654915571212769, + "learning_rate": 3.56421471489768e-05, + "loss": 1.607, + "step": 10758 + }, + { + "epoch": 0.5996878657822864, + "grad_norm": 0.5372860431671143, + "learning_rate": 3.563361815554131e-05, + "loss": 1.7169, + "step": 10759 + }, + { + "epoch": 0.5997436040354496, + "grad_norm": 0.528947114944458, + "learning_rate": 3.5625089617723716e-05, + "loss": 1.5978, + "step": 10760 + }, + { + "epoch": 0.5997993422886126, + "grad_norm": 0.5702643990516663, + "learning_rate": 3.5616561535794445e-05, + "loss": 1.8016, + "step": 10761 + }, + { + "epoch": 0.5998550805417758, + "grad_norm": 0.5951703190803528, + "learning_rate": 3.5608033910023995e-05, + "loss": 1.6588, + "step": 10762 + }, + { + "epoch": 0.599910818794939, + "grad_norm": 0.5421859622001648, + "learning_rate": 3.55995067406828e-05, + "loss": 1.8786, + "step": 10763 + }, + { + "epoch": 0.5999665570481021, + "grad_norm": 0.553703248500824, + "learning_rate": 3.5590980028041274e-05, + "loss": 1.7054, + "step": 10764 + }, + { + "epoch": 0.6000222953012653, + "grad_norm": 0.515870988368988, + "learning_rate": 3.558245377236987e-05, + "loss": 1.4711, + "step": 10765 + }, + { + "epoch": 0.6000780335544285, + "grad_norm": 0.547909140586853, + "learning_rate": 3.557392797393896e-05, + "loss": 1.6006, + "step": 10766 + }, + { + "epoch": 0.6001337718075915, + "grad_norm": 0.5588516592979431, + "learning_rate": 3.556540263301896e-05, + "loss": 1.7297, + "step": 10767 + }, + { + "epoch": 0.6001895100607547, + "grad_norm": 0.5475988388061523, + "learning_rate": 3.55568777498802e-05, + "loss": 1.684, + "step": 10768 + }, + { + "epoch": 0.6002452483139178, + "grad_norm": 0.577996551990509, + "learning_rate": 3.554835332479311e-05, + "loss": 1.5644, + "step": 10769 + }, + { + "epoch": 0.600300986567081, + "grad_norm": 0.5774939656257629, + "learning_rate": 3.553982935802795e-05, + "loss": 1.7492, + "step": 10770 + }, + { + "epoch": 0.6003567248202442, + "grad_norm": 0.6069820523262024, + "learning_rate": 3.5531305849855115e-05, + "loss": 1.7471, + "step": 10771 + }, + { + "epoch": 0.6004124630734072, + "grad_norm": 0.5596128106117249, + "learning_rate": 3.552278280054491e-05, + "loss": 1.6402, + "step": 10772 + }, + { + "epoch": 0.6004682013265704, + "grad_norm": 0.5300867557525635, + "learning_rate": 3.551426021036761e-05, + "loss": 1.5077, + "step": 10773 + }, + { + "epoch": 0.6005239395797336, + "grad_norm": 0.6160181760787964, + "learning_rate": 3.550573807959353e-05, + "loss": 1.8933, + "step": 10774 + }, + { + "epoch": 0.6005796778328967, + "grad_norm": 0.5664730072021484, + "learning_rate": 3.549721640849293e-05, + "loss": 1.5747, + "step": 10775 + }, + { + "epoch": 0.6006354160860599, + "grad_norm": 0.5451174974441528, + "learning_rate": 3.548869519733606e-05, + "loss": 1.7253, + "step": 10776 + }, + { + "epoch": 0.600691154339223, + "grad_norm": 0.5766503214836121, + "learning_rate": 3.5480174446393175e-05, + "loss": 1.6655, + "step": 10777 + }, + { + "epoch": 0.6007468925923861, + "grad_norm": 0.6216641068458557, + "learning_rate": 3.5471654155934485e-05, + "loss": 1.3522, + "step": 10778 + }, + { + "epoch": 0.6008026308455493, + "grad_norm": 0.5925215482711792, + "learning_rate": 3.546313432623025e-05, + "loss": 1.8613, + "step": 10779 + }, + { + "epoch": 0.6008583690987125, + "grad_norm": 0.5722919702529907, + "learning_rate": 3.545461495755061e-05, + "loss": 1.6849, + "step": 10780 + }, + { + "epoch": 0.6009141073518756, + "grad_norm": 0.5494630932807922, + "learning_rate": 3.54460960501658e-05, + "loss": 1.7203, + "step": 10781 + }, + { + "epoch": 0.6009698456050387, + "grad_norm": 0.5340242385864258, + "learning_rate": 3.5437577604345964e-05, + "loss": 1.4293, + "step": 10782 + }, + { + "epoch": 0.6010255838582019, + "grad_norm": 0.5879470705986023, + "learning_rate": 3.542905962036126e-05, + "loss": 1.7313, + "step": 10783 + }, + { + "epoch": 0.601081322111365, + "grad_norm": 0.5412936210632324, + "learning_rate": 3.542054209848182e-05, + "loss": 1.7252, + "step": 10784 + }, + { + "epoch": 0.6011370603645282, + "grad_norm": 0.5653871893882751, + "learning_rate": 3.5412025038977774e-05, + "loss": 1.7057, + "step": 10785 + }, + { + "epoch": 0.6011927986176914, + "grad_norm": 0.5855697989463806, + "learning_rate": 3.540350844211927e-05, + "loss": 1.813, + "step": 10786 + }, + { + "epoch": 0.6012485368708544, + "grad_norm": 0.5583329796791077, + "learning_rate": 3.539499230817634e-05, + "loss": 1.765, + "step": 10787 + }, + { + "epoch": 0.6013042751240176, + "grad_norm": 0.5965836644172668, + "learning_rate": 3.538647663741913e-05, + "loss": 1.6828, + "step": 10788 + }, + { + "epoch": 0.6013600133771808, + "grad_norm": 0.6070554852485657, + "learning_rate": 3.5377961430117665e-05, + "loss": 1.8815, + "step": 10789 + }, + { + "epoch": 0.6014157516303439, + "grad_norm": 0.6031116247177124, + "learning_rate": 3.5369446686542016e-05, + "loss": 1.8932, + "step": 10790 + }, + { + "epoch": 0.6014714898835071, + "grad_norm": 0.6014582514762878, + "learning_rate": 3.5360932406962214e-05, + "loss": 1.8328, + "step": 10791 + }, + { + "epoch": 0.6015272281366701, + "grad_norm": 0.5309771299362183, + "learning_rate": 3.5352418591648285e-05, + "loss": 1.4607, + "step": 10792 + }, + { + "epoch": 0.6015829663898333, + "grad_norm": 0.5593672394752502, + "learning_rate": 3.534390524087024e-05, + "loss": 1.7778, + "step": 10793 + }, + { + "epoch": 0.6016387046429965, + "grad_norm": 0.541955292224884, + "learning_rate": 3.5335392354898055e-05, + "loss": 1.6689, + "step": 10794 + }, + { + "epoch": 0.6016944428961596, + "grad_norm": 0.5780551433563232, + "learning_rate": 3.532687993400175e-05, + "loss": 1.6137, + "step": 10795 + }, + { + "epoch": 0.6017501811493228, + "grad_norm": 0.5650581121444702, + "learning_rate": 3.5318367978451234e-05, + "loss": 1.5538, + "step": 10796 + }, + { + "epoch": 0.601805919402486, + "grad_norm": 0.5644901990890503, + "learning_rate": 3.530985648851649e-05, + "loss": 1.7932, + "step": 10797 + }, + { + "epoch": 0.601861657655649, + "grad_norm": 0.5749223828315735, + "learning_rate": 3.530134546446747e-05, + "loss": 1.7293, + "step": 10798 + }, + { + "epoch": 0.6019173959088122, + "grad_norm": 0.6107510328292847, + "learning_rate": 3.529283490657406e-05, + "loss": 1.6503, + "step": 10799 + }, + { + "epoch": 0.6019731341619754, + "grad_norm": 0.6036887168884277, + "learning_rate": 3.5284324815106184e-05, + "loss": 1.7405, + "step": 10800 + }, + { + "epoch": 0.6020288724151385, + "grad_norm": 0.6208280920982361, + "learning_rate": 3.527581519033372e-05, + "loss": 1.9516, + "step": 10801 + }, + { + "epoch": 0.6020846106683017, + "grad_norm": 0.5419480204582214, + "learning_rate": 3.5267306032526556e-05, + "loss": 1.518, + "step": 10802 + }, + { + "epoch": 0.6021403489214648, + "grad_norm": 0.594589352607727, + "learning_rate": 3.525879734195453e-05, + "loss": 1.9563, + "step": 10803 + }, + { + "epoch": 0.6021960871746279, + "grad_norm": 0.553704023361206, + "learning_rate": 3.525028911888751e-05, + "loss": 1.4931, + "step": 10804 + }, + { + "epoch": 0.6022518254277911, + "grad_norm": 0.5537152886390686, + "learning_rate": 3.5241781363595344e-05, + "loss": 1.6004, + "step": 10805 + }, + { + "epoch": 0.6023075636809543, + "grad_norm": 0.5621123909950256, + "learning_rate": 3.523327407634781e-05, + "loss": 1.5503, + "step": 10806 + }, + { + "epoch": 0.6023633019341174, + "grad_norm": 0.6001083254814148, + "learning_rate": 3.5224767257414734e-05, + "loss": 1.8868, + "step": 10807 + }, + { + "epoch": 0.6024190401872805, + "grad_norm": 0.5669860243797302, + "learning_rate": 3.521626090706589e-05, + "loss": 1.7416, + "step": 10808 + }, + { + "epoch": 0.6024747784404437, + "grad_norm": 0.5396543741226196, + "learning_rate": 3.5207755025571066e-05, + "loss": 1.6226, + "step": 10809 + }, + { + "epoch": 0.6025305166936068, + "grad_norm": 0.5446880459785461, + "learning_rate": 3.519924961319999e-05, + "loss": 1.5139, + "step": 10810 + }, + { + "epoch": 0.60258625494677, + "grad_norm": 0.5307889580726624, + "learning_rate": 3.519074467022241e-05, + "loss": 1.5466, + "step": 10811 + }, + { + "epoch": 0.6026419931999332, + "grad_norm": 0.5402228832244873, + "learning_rate": 3.518224019690811e-05, + "loss": 1.5498, + "step": 10812 + }, + { + "epoch": 0.6026977314530962, + "grad_norm": 0.5594295859336853, + "learning_rate": 3.517373619352672e-05, + "loss": 1.5064, + "step": 10813 + }, + { + "epoch": 0.6027534697062594, + "grad_norm": 0.5983800292015076, + "learning_rate": 3.516523266034799e-05, + "loss": 1.9771, + "step": 10814 + }, + { + "epoch": 0.6028092079594225, + "grad_norm": 0.5792510509490967, + "learning_rate": 3.515672959764158e-05, + "loss": 1.5936, + "step": 10815 + }, + { + "epoch": 0.6028649462125857, + "grad_norm": 0.5335869789123535, + "learning_rate": 3.514822700567718e-05, + "loss": 1.7219, + "step": 10816 + }, + { + "epoch": 0.6029206844657489, + "grad_norm": 0.5837699174880981, + "learning_rate": 3.5139724884724406e-05, + "loss": 1.6883, + "step": 10817 + }, + { + "epoch": 0.6029764227189119, + "grad_norm": 0.5807821154594421, + "learning_rate": 3.5131223235052927e-05, + "loss": 1.8162, + "step": 10818 + }, + { + "epoch": 0.6030321609720751, + "grad_norm": 0.5589340329170227, + "learning_rate": 3.512272205693236e-05, + "loss": 1.7268, + "step": 10819 + }, + { + "epoch": 0.6030878992252383, + "grad_norm": 0.6129077672958374, + "learning_rate": 3.511422135063229e-05, + "loss": 1.7887, + "step": 10820 + }, + { + "epoch": 0.6031436374784014, + "grad_norm": 0.5553536415100098, + "learning_rate": 3.5105721116422364e-05, + "loss": 1.5031, + "step": 10821 + }, + { + "epoch": 0.6031993757315646, + "grad_norm": 0.6441968083381653, + "learning_rate": 3.509722135457209e-05, + "loss": 1.486, + "step": 10822 + }, + { + "epoch": 0.6032551139847278, + "grad_norm": 0.5330159068107605, + "learning_rate": 3.5088722065351074e-05, + "loss": 1.6346, + "step": 10823 + }, + { + "epoch": 0.6033108522378908, + "grad_norm": 0.5661835670471191, + "learning_rate": 3.508022324902888e-05, + "loss": 1.6415, + "step": 10824 + }, + { + "epoch": 0.603366590491054, + "grad_norm": 0.6099451184272766, + "learning_rate": 3.507172490587499e-05, + "loss": 1.8652, + "step": 10825 + }, + { + "epoch": 0.6034223287442172, + "grad_norm": 0.5531985759735107, + "learning_rate": 3.5063227036158956e-05, + "loss": 1.6726, + "step": 10826 + }, + { + "epoch": 0.6034780669973803, + "grad_norm": 0.5670011639595032, + "learning_rate": 3.5054729640150274e-05, + "loss": 1.6772, + "step": 10827 + }, + { + "epoch": 0.6035338052505435, + "grad_norm": 0.5749963521957397, + "learning_rate": 3.504623271811843e-05, + "loss": 1.714, + "step": 10828 + }, + { + "epoch": 0.6035895435037066, + "grad_norm": 0.5688133835792542, + "learning_rate": 3.5037736270332886e-05, + "loss": 1.6752, + "step": 10829 + }, + { + "epoch": 0.6036452817568697, + "grad_norm": 0.5335734486579895, + "learning_rate": 3.502924029706312e-05, + "loss": 1.3809, + "step": 10830 + }, + { + "epoch": 0.6037010200100329, + "grad_norm": 0.5560937523841858, + "learning_rate": 3.502074479857858e-05, + "loss": 1.6847, + "step": 10831 + }, + { + "epoch": 0.6037567582631961, + "grad_norm": 0.5606946349143982, + "learning_rate": 3.501224977514867e-05, + "loss": 1.7664, + "step": 10832 + }, + { + "epoch": 0.6038124965163592, + "grad_norm": 0.5246312022209167, + "learning_rate": 3.500375522704281e-05, + "loss": 1.631, + "step": 10833 + }, + { + "epoch": 0.6038682347695223, + "grad_norm": 0.5628395676612854, + "learning_rate": 3.49952611545304e-05, + "loss": 1.6952, + "step": 10834 + }, + { + "epoch": 0.6039239730226855, + "grad_norm": 0.5548897385597229, + "learning_rate": 3.498676755788083e-05, + "loss": 1.5307, + "step": 10835 + }, + { + "epoch": 0.6039797112758486, + "grad_norm": 0.5087965130805969, + "learning_rate": 3.497827443736344e-05, + "loss": 1.4216, + "step": 10836 + }, + { + "epoch": 0.6040354495290118, + "grad_norm": 0.5709730982780457, + "learning_rate": 3.496978179324761e-05, + "loss": 1.7554, + "step": 10837 + }, + { + "epoch": 0.6040911877821749, + "grad_norm": 0.5632007122039795, + "learning_rate": 3.49612896258027e-05, + "loss": 1.677, + "step": 10838 + }, + { + "epoch": 0.604146926035338, + "grad_norm": 0.5664843320846558, + "learning_rate": 3.4952797935297955e-05, + "loss": 1.8422, + "step": 10839 + }, + { + "epoch": 0.6042026642885012, + "grad_norm": 0.5658974051475525, + "learning_rate": 3.494430672200276e-05, + "loss": 1.6821, + "step": 10840 + }, + { + "epoch": 0.6042584025416643, + "grad_norm": 0.5238000750541687, + "learning_rate": 3.493581598618636e-05, + "loss": 1.635, + "step": 10841 + }, + { + "epoch": 0.6043141407948275, + "grad_norm": 0.5444875359535217, + "learning_rate": 3.4927325728118055e-05, + "loss": 1.7191, + "step": 10842 + }, + { + "epoch": 0.6043698790479907, + "grad_norm": 0.5294889211654663, + "learning_rate": 3.491883594806709e-05, + "loss": 1.637, + "step": 10843 + }, + { + "epoch": 0.6044256173011537, + "grad_norm": 0.5691200494766235, + "learning_rate": 3.4910346646302716e-05, + "loss": 1.6545, + "step": 10844 + }, + { + "epoch": 0.6044813555543169, + "grad_norm": 0.6108242869377136, + "learning_rate": 3.4901857823094184e-05, + "loss": 1.7508, + "step": 10845 + }, + { + "epoch": 0.6045370938074801, + "grad_norm": 0.5625608563423157, + "learning_rate": 3.489336947871067e-05, + "loss": 1.5451, + "step": 10846 + }, + { + "epoch": 0.6045928320606432, + "grad_norm": 0.5418411493301392, + "learning_rate": 3.488488161342143e-05, + "loss": 1.4548, + "step": 10847 + }, + { + "epoch": 0.6046485703138064, + "grad_norm": 0.6216863393783569, + "learning_rate": 3.487639422749559e-05, + "loss": 1.926, + "step": 10848 + }, + { + "epoch": 0.6047043085669696, + "grad_norm": 0.6217368245124817, + "learning_rate": 3.486790732120235e-05, + "loss": 1.8622, + "step": 10849 + }, + { + "epoch": 0.6047600468201326, + "grad_norm": 0.525329053401947, + "learning_rate": 3.485942089481089e-05, + "loss": 1.6005, + "step": 10850 + }, + { + "epoch": 0.6048157850732958, + "grad_norm": 0.5369617938995361, + "learning_rate": 3.4850934948590295e-05, + "loss": 1.6028, + "step": 10851 + }, + { + "epoch": 0.604871523326459, + "grad_norm": 0.584526538848877, + "learning_rate": 3.484244948280974e-05, + "loss": 1.8607, + "step": 10852 + }, + { + "epoch": 0.6049272615796221, + "grad_norm": 0.5628748536109924, + "learning_rate": 3.4833964497738305e-05, + "loss": 1.6398, + "step": 10853 + }, + { + "epoch": 0.6049829998327853, + "grad_norm": 0.5512056946754456, + "learning_rate": 3.482547999364509e-05, + "loss": 1.6174, + "step": 10854 + }, + { + "epoch": 0.6050387380859484, + "grad_norm": 0.5609381794929504, + "learning_rate": 3.481699597079916e-05, + "loss": 1.742, + "step": 10855 + }, + { + "epoch": 0.6050944763391115, + "grad_norm": 0.5258693099021912, + "learning_rate": 3.480851242946961e-05, + "loss": 1.626, + "step": 10856 + }, + { + "epoch": 0.6051502145922747, + "grad_norm": 0.5588704347610474, + "learning_rate": 3.4800029369925476e-05, + "loss": 1.4834, + "step": 10857 + }, + { + "epoch": 0.6052059528454379, + "grad_norm": 0.6147596836090088, + "learning_rate": 3.4791546792435785e-05, + "loss": 1.9472, + "step": 10858 + }, + { + "epoch": 0.605261691098601, + "grad_norm": 0.5736888647079468, + "learning_rate": 3.478306469726957e-05, + "loss": 1.8025, + "step": 10859 + }, + { + "epoch": 0.6053174293517641, + "grad_norm": 0.5551031231880188, + "learning_rate": 3.4774583084695804e-05, + "loss": 1.7116, + "step": 10860 + }, + { + "epoch": 0.6053731676049272, + "grad_norm": 0.5682637095451355, + "learning_rate": 3.476610195498351e-05, + "loss": 1.5637, + "step": 10861 + }, + { + "epoch": 0.6054289058580904, + "grad_norm": 0.5585805773735046, + "learning_rate": 3.4757621308401625e-05, + "loss": 1.7162, + "step": 10862 + }, + { + "epoch": 0.6054846441112536, + "grad_norm": 0.7432271242141724, + "learning_rate": 3.474914114521912e-05, + "loss": 1.8017, + "step": 10863 + }, + { + "epoch": 0.6055403823644167, + "grad_norm": 0.5110836029052734, + "learning_rate": 3.474066146570496e-05, + "loss": 1.5233, + "step": 10864 + }, + { + "epoch": 0.6055961206175798, + "grad_norm": 0.5634505748748779, + "learning_rate": 3.4732182270128026e-05, + "loss": 1.7133, + "step": 10865 + }, + { + "epoch": 0.605651858870743, + "grad_norm": 0.5704511404037476, + "learning_rate": 3.472370355875727e-05, + "loss": 1.6873, + "step": 10866 + }, + { + "epoch": 0.6057075971239061, + "grad_norm": 0.5130916833877563, + "learning_rate": 3.471522533186157e-05, + "loss": 1.4978, + "step": 10867 + }, + { + "epoch": 0.6057633353770693, + "grad_norm": 0.5763922333717346, + "learning_rate": 3.470674758970981e-05, + "loss": 1.7908, + "step": 10868 + }, + { + "epoch": 0.6058190736302325, + "grad_norm": 0.5909677147865295, + "learning_rate": 3.4698270332570835e-05, + "loss": 1.8559, + "step": 10869 + }, + { + "epoch": 0.6058748118833955, + "grad_norm": 0.5599098205566406, + "learning_rate": 3.468979356071351e-05, + "loss": 1.8091, + "step": 10870 + }, + { + "epoch": 0.6059305501365587, + "grad_norm": 0.5690943598747253, + "learning_rate": 3.468131727440669e-05, + "loss": 1.6181, + "step": 10871 + }, + { + "epoch": 0.6059862883897219, + "grad_norm": 0.5756849646568298, + "learning_rate": 3.467284147391914e-05, + "loss": 1.8721, + "step": 10872 + }, + { + "epoch": 0.606042026642885, + "grad_norm": 0.5114251971244812, + "learning_rate": 3.466436615951973e-05, + "loss": 1.3427, + "step": 10873 + }, + { + "epoch": 0.6060977648960482, + "grad_norm": 0.5647757053375244, + "learning_rate": 3.465589133147718e-05, + "loss": 1.6981, + "step": 10874 + }, + { + "epoch": 0.6061535031492113, + "grad_norm": 0.6103023290634155, + "learning_rate": 3.464741699006031e-05, + "loss": 1.3025, + "step": 10875 + }, + { + "epoch": 0.6062092414023744, + "grad_norm": 0.5083357095718384, + "learning_rate": 3.4638943135537864e-05, + "loss": 1.5597, + "step": 10876 + }, + { + "epoch": 0.6062649796555376, + "grad_norm": 0.5760177373886108, + "learning_rate": 3.463046976817857e-05, + "loss": 1.6599, + "step": 10877 + }, + { + "epoch": 0.6063207179087008, + "grad_norm": 0.5807527899742126, + "learning_rate": 3.462199688825119e-05, + "loss": 1.7096, + "step": 10878 + }, + { + "epoch": 0.6063764561618639, + "grad_norm": 0.5611261129379272, + "learning_rate": 3.461352449602439e-05, + "loss": 1.6227, + "step": 10879 + }, + { + "epoch": 0.606432194415027, + "grad_norm": 0.5763663053512573, + "learning_rate": 3.4605052591766884e-05, + "loss": 1.9214, + "step": 10880 + }, + { + "epoch": 0.6064879326681902, + "grad_norm": 0.572849452495575, + "learning_rate": 3.459658117574733e-05, + "loss": 1.6082, + "step": 10881 + }, + { + "epoch": 0.6065436709213533, + "grad_norm": 0.6065723896026611, + "learning_rate": 3.458811024823444e-05, + "loss": 1.5039, + "step": 10882 + }, + { + "epoch": 0.6065994091745165, + "grad_norm": 0.5590231418609619, + "learning_rate": 3.4579639809496835e-05, + "loss": 1.5629, + "step": 10883 + }, + { + "epoch": 0.6066551474276796, + "grad_norm": 0.535981297492981, + "learning_rate": 3.4571169859803135e-05, + "loss": 1.5471, + "step": 10884 + }, + { + "epoch": 0.6067108856808427, + "grad_norm": 0.5847405195236206, + "learning_rate": 3.4562700399421985e-05, + "loss": 1.7089, + "step": 10885 + }, + { + "epoch": 0.6067666239340059, + "grad_norm": 0.5974164605140686, + "learning_rate": 3.455423142862196e-05, + "loss": 1.7032, + "step": 10886 + }, + { + "epoch": 0.606822362187169, + "grad_norm": 0.5608033537864685, + "learning_rate": 3.4545762947671676e-05, + "loss": 1.6528, + "step": 10887 + }, + { + "epoch": 0.6068781004403322, + "grad_norm": 0.5671756863594055, + "learning_rate": 3.453729495683967e-05, + "loss": 1.641, + "step": 10888 + }, + { + "epoch": 0.6069338386934954, + "grad_norm": 0.5884689688682556, + "learning_rate": 3.4528827456394506e-05, + "loss": 1.77, + "step": 10889 + }, + { + "epoch": 0.6069895769466584, + "grad_norm": 0.5784920454025269, + "learning_rate": 3.452036044660476e-05, + "loss": 1.7991, + "step": 10890 + }, + { + "epoch": 0.6070453151998216, + "grad_norm": 0.5790646076202393, + "learning_rate": 3.451189392773891e-05, + "loss": 1.592, + "step": 10891 + }, + { + "epoch": 0.6071010534529848, + "grad_norm": 0.576714038848877, + "learning_rate": 3.45034279000655e-05, + "loss": 1.4394, + "step": 10892 + }, + { + "epoch": 0.6071567917061479, + "grad_norm": 0.6155091524124146, + "learning_rate": 3.449496236385298e-05, + "loss": 1.7956, + "step": 10893 + }, + { + "epoch": 0.6072125299593111, + "grad_norm": 0.571345329284668, + "learning_rate": 3.448649731936988e-05, + "loss": 1.6404, + "step": 10894 + }, + { + "epoch": 0.6072682682124743, + "grad_norm": 0.5463574528694153, + "learning_rate": 3.4478032766884615e-05, + "loss": 1.6412, + "step": 10895 + }, + { + "epoch": 0.6073240064656373, + "grad_norm": 0.5688880085945129, + "learning_rate": 3.446956870666565e-05, + "loss": 1.699, + "step": 10896 + }, + { + "epoch": 0.6073797447188005, + "grad_norm": 0.5384257435798645, + "learning_rate": 3.446110513898143e-05, + "loss": 1.6323, + "step": 10897 + }, + { + "epoch": 0.6074354829719637, + "grad_norm": 0.5217699408531189, + "learning_rate": 3.445264206410034e-05, + "loss": 1.727, + "step": 10898 + }, + { + "epoch": 0.6074912212251268, + "grad_norm": 0.5378054976463318, + "learning_rate": 3.444417948229083e-05, + "loss": 1.4174, + "step": 10899 + }, + { + "epoch": 0.60754695947829, + "grad_norm": 0.5939854383468628, + "learning_rate": 3.443571739382121e-05, + "loss": 1.7969, + "step": 10900 + }, + { + "epoch": 0.6076026977314531, + "grad_norm": 0.6069276332855225, + "learning_rate": 3.44272557989599e-05, + "loss": 1.7629, + "step": 10901 + }, + { + "epoch": 0.6076584359846162, + "grad_norm": 0.5685117244720459, + "learning_rate": 3.4418794697975254e-05, + "loss": 1.6894, + "step": 10902 + }, + { + "epoch": 0.6077141742377794, + "grad_norm": 0.5635547041893005, + "learning_rate": 3.4410334091135586e-05, + "loss": 1.6697, + "step": 10903 + }, + { + "epoch": 0.6077699124909426, + "grad_norm": 0.5866085290908813, + "learning_rate": 3.440187397870923e-05, + "loss": 1.7436, + "step": 10904 + }, + { + "epoch": 0.6078256507441057, + "grad_norm": 0.599195659160614, + "learning_rate": 3.4393414360964486e-05, + "loss": 1.921, + "step": 10905 + }, + { + "epoch": 0.6078813889972688, + "grad_norm": 0.5734924674034119, + "learning_rate": 3.438495523816966e-05, + "loss": 1.5432, + "step": 10906 + }, + { + "epoch": 0.6079371272504319, + "grad_norm": 0.5457361340522766, + "learning_rate": 3.437649661059298e-05, + "loss": 1.4088, + "step": 10907 + }, + { + "epoch": 0.6079928655035951, + "grad_norm": 0.6204760074615479, + "learning_rate": 3.436803847850275e-05, + "loss": 1.964, + "step": 10908 + }, + { + "epoch": 0.6080486037567583, + "grad_norm": 0.5474656224250793, + "learning_rate": 3.4359580842167205e-05, + "loss": 1.8181, + "step": 10909 + }, + { + "epoch": 0.6081043420099214, + "grad_norm": 0.5399399399757385, + "learning_rate": 3.435112370185456e-05, + "loss": 1.5749, + "step": 10910 + }, + { + "epoch": 0.6081600802630845, + "grad_norm": 0.5384534001350403, + "learning_rate": 3.434266705783305e-05, + "loss": 1.5584, + "step": 10911 + }, + { + "epoch": 0.6082158185162477, + "grad_norm": 0.5624092221260071, + "learning_rate": 3.4334210910370833e-05, + "loss": 1.4784, + "step": 10912 + }, + { + "epoch": 0.6082715567694108, + "grad_norm": 0.5896902084350586, + "learning_rate": 3.4325755259736114e-05, + "loss": 1.748, + "step": 10913 + }, + { + "epoch": 0.608327295022574, + "grad_norm": 0.5084818601608276, + "learning_rate": 3.4317300106197045e-05, + "loss": 1.4765, + "step": 10914 + }, + { + "epoch": 0.6083830332757372, + "grad_norm": 0.5438110828399658, + "learning_rate": 3.430884545002178e-05, + "loss": 1.5289, + "step": 10915 + }, + { + "epoch": 0.6084387715289002, + "grad_norm": 0.5773879885673523, + "learning_rate": 3.430039129147846e-05, + "loss": 1.7349, + "step": 10916 + }, + { + "epoch": 0.6084945097820634, + "grad_norm": 0.5718106031417847, + "learning_rate": 3.4291937630835184e-05, + "loss": 1.8119, + "step": 10917 + }, + { + "epoch": 0.6085502480352266, + "grad_norm": 0.5841074585914612, + "learning_rate": 3.428348446836008e-05, + "loss": 1.4698, + "step": 10918 + }, + { + "epoch": 0.6086059862883897, + "grad_norm": 0.5340185165405273, + "learning_rate": 3.42750318043212e-05, + "loss": 1.7174, + "step": 10919 + }, + { + "epoch": 0.6086617245415529, + "grad_norm": 0.5589284300804138, + "learning_rate": 3.4266579638986637e-05, + "loss": 1.7808, + "step": 10920 + }, + { + "epoch": 0.6087174627947161, + "grad_norm": 0.5883926153182983, + "learning_rate": 3.4258127972624423e-05, + "loss": 1.5736, + "step": 10921 + }, + { + "epoch": 0.6087732010478791, + "grad_norm": 0.525952160358429, + "learning_rate": 3.424967680550261e-05, + "loss": 1.3187, + "step": 10922 + }, + { + "epoch": 0.6088289393010423, + "grad_norm": 0.6014953851699829, + "learning_rate": 3.424122613788923e-05, + "loss": 1.6827, + "step": 10923 + }, + { + "epoch": 0.6088846775542055, + "grad_norm": 0.5605544447898865, + "learning_rate": 3.423277597005226e-05, + "loss": 1.548, + "step": 10924 + }, + { + "epoch": 0.6089404158073686, + "grad_norm": 0.5829630494117737, + "learning_rate": 3.422432630225974e-05, + "loss": 1.7789, + "step": 10925 + }, + { + "epoch": 0.6089961540605318, + "grad_norm": 0.5912023186683655, + "learning_rate": 3.421587713477957e-05, + "loss": 1.6069, + "step": 10926 + }, + { + "epoch": 0.6090518923136949, + "grad_norm": 0.5478500127792358, + "learning_rate": 3.4207428467879774e-05, + "loss": 1.4861, + "step": 10927 + }, + { + "epoch": 0.609107630566858, + "grad_norm": 0.5500767827033997, + "learning_rate": 3.419898030182825e-05, + "loss": 1.5054, + "step": 10928 + }, + { + "epoch": 0.6091633688200212, + "grad_norm": 0.6093530654907227, + "learning_rate": 3.4190532636892955e-05, + "loss": 1.9566, + "step": 10929 + }, + { + "epoch": 0.6092191070731843, + "grad_norm": 0.5310298204421997, + "learning_rate": 3.418208547334181e-05, + "loss": 1.4754, + "step": 10930 + }, + { + "epoch": 0.6092748453263475, + "grad_norm": 0.5761799216270447, + "learning_rate": 3.417363881144267e-05, + "loss": 1.4885, + "step": 10931 + }, + { + "epoch": 0.6093305835795106, + "grad_norm": 0.5826595425605774, + "learning_rate": 3.416519265146343e-05, + "loss": 1.5243, + "step": 10932 + }, + { + "epoch": 0.6093863218326737, + "grad_norm": 0.5796806216239929, + "learning_rate": 3.415674699367195e-05, + "loss": 1.5245, + "step": 10933 + }, + { + "epoch": 0.6094420600858369, + "grad_norm": 0.584348738193512, + "learning_rate": 3.414830183833608e-05, + "loss": 1.6732, + "step": 10934 + }, + { + "epoch": 0.6094977983390001, + "grad_norm": 0.5404664874076843, + "learning_rate": 3.413985718572368e-05, + "loss": 1.6273, + "step": 10935 + }, + { + "epoch": 0.6095535365921632, + "grad_norm": 0.5560908317565918, + "learning_rate": 3.413141303610252e-05, + "loss": 1.7216, + "step": 10936 + }, + { + "epoch": 0.6096092748453263, + "grad_norm": 0.5780743956565857, + "learning_rate": 3.412296938974043e-05, + "loss": 1.6605, + "step": 10937 + }, + { + "epoch": 0.6096650130984895, + "grad_norm": 0.5821511745452881, + "learning_rate": 3.4114526246905176e-05, + "loss": 1.6557, + "step": 10938 + }, + { + "epoch": 0.6097207513516526, + "grad_norm": 0.6239771246910095, + "learning_rate": 3.410608360786454e-05, + "loss": 1.6936, + "step": 10939 + }, + { + "epoch": 0.6097764896048158, + "grad_norm": 0.5467875003814697, + "learning_rate": 3.4097641472886245e-05, + "loss": 1.5873, + "step": 10940 + }, + { + "epoch": 0.609832227857979, + "grad_norm": 0.5692501068115234, + "learning_rate": 3.408919984223804e-05, + "loss": 1.636, + "step": 10941 + }, + { + "epoch": 0.609887966111142, + "grad_norm": 0.553924560546875, + "learning_rate": 3.408075871618767e-05, + "loss": 1.5813, + "step": 10942 + }, + { + "epoch": 0.6099437043643052, + "grad_norm": 0.601086437702179, + "learning_rate": 3.407231809500281e-05, + "loss": 1.8607, + "step": 10943 + }, + { + "epoch": 0.6099994426174684, + "grad_norm": 0.57811039686203, + "learning_rate": 3.406387797895116e-05, + "loss": 1.6621, + "step": 10944 + }, + { + "epoch": 0.6100551808706315, + "grad_norm": 0.5589052438735962, + "learning_rate": 3.405543836830038e-05, + "loss": 1.8064, + "step": 10945 + }, + { + "epoch": 0.6101109191237947, + "grad_norm": 0.5751338005065918, + "learning_rate": 3.404699926331814e-05, + "loss": 1.6508, + "step": 10946 + }, + { + "epoch": 0.6101666573769579, + "grad_norm": 0.5896758437156677, + "learning_rate": 3.403856066427207e-05, + "loss": 1.8309, + "step": 10947 + }, + { + "epoch": 0.6102223956301209, + "grad_norm": 0.5646328330039978, + "learning_rate": 3.403012257142977e-05, + "loss": 1.6079, + "step": 10948 + }, + { + "epoch": 0.6102781338832841, + "grad_norm": 0.5370541214942932, + "learning_rate": 3.4021684985058914e-05, + "loss": 1.5691, + "step": 10949 + }, + { + "epoch": 0.6103338721364473, + "grad_norm": 0.5964412093162537, + "learning_rate": 3.4013247905427e-05, + "loss": 1.7893, + "step": 10950 + }, + { + "epoch": 0.6103896103896104, + "grad_norm": 0.5477089285850525, + "learning_rate": 3.4004811332801705e-05, + "loss": 1.708, + "step": 10951 + }, + { + "epoch": 0.6104453486427736, + "grad_norm": 0.7580403089523315, + "learning_rate": 3.39963752674505e-05, + "loss": 1.9378, + "step": 10952 + }, + { + "epoch": 0.6105010868959366, + "grad_norm": 0.5177296996116638, + "learning_rate": 3.398793970964098e-05, + "loss": 1.7007, + "step": 10953 + }, + { + "epoch": 0.6105568251490998, + "grad_norm": 0.5849555134773254, + "learning_rate": 3.397950465964065e-05, + "loss": 1.6816, + "step": 10954 + }, + { + "epoch": 0.610612563402263, + "grad_norm": 0.5685425996780396, + "learning_rate": 3.3971070117717016e-05, + "loss": 1.8814, + "step": 10955 + }, + { + "epoch": 0.6106683016554261, + "grad_norm": 0.6520184278488159, + "learning_rate": 3.39626360841376e-05, + "loss": 1.7222, + "step": 10956 + }, + { + "epoch": 0.6107240399085893, + "grad_norm": 0.579638659954071, + "learning_rate": 3.395420255916986e-05, + "loss": 1.6526, + "step": 10957 + }, + { + "epoch": 0.6107797781617524, + "grad_norm": 0.5428391098976135, + "learning_rate": 3.3945769543081264e-05, + "loss": 1.5243, + "step": 10958 + }, + { + "epoch": 0.6108355164149155, + "grad_norm": 0.5601480603218079, + "learning_rate": 3.3937337036139236e-05, + "loss": 1.6196, + "step": 10959 + }, + { + "epoch": 0.6108912546680787, + "grad_norm": 0.6202312111854553, + "learning_rate": 3.392890503861124e-05, + "loss": 1.5272, + "step": 10960 + }, + { + "epoch": 0.6109469929212419, + "grad_norm": 0.5722497701644897, + "learning_rate": 3.3920473550764676e-05, + "loss": 1.6407, + "step": 10961 + }, + { + "epoch": 0.611002731174405, + "grad_norm": 0.5435575246810913, + "learning_rate": 3.3912042572866934e-05, + "loss": 1.618, + "step": 10962 + }, + { + "epoch": 0.6110584694275681, + "grad_norm": 0.6046878695487976, + "learning_rate": 3.390361210518542e-05, + "loss": 1.7345, + "step": 10963 + }, + { + "epoch": 0.6111142076807313, + "grad_norm": 0.5520839095115662, + "learning_rate": 3.389518214798746e-05, + "loss": 1.5911, + "step": 10964 + }, + { + "epoch": 0.6111699459338944, + "grad_norm": 0.502733588218689, + "learning_rate": 3.388675270154045e-05, + "loss": 1.4994, + "step": 10965 + }, + { + "epoch": 0.6112256841870576, + "grad_norm": 0.5726004242897034, + "learning_rate": 3.3878323766111675e-05, + "loss": 1.5398, + "step": 10966 + }, + { + "epoch": 0.6112814224402208, + "grad_norm": 0.8424298763275146, + "learning_rate": 3.3869895341968463e-05, + "loss": 1.501, + "step": 10967 + }, + { + "epoch": 0.6113371606933838, + "grad_norm": 0.5562017560005188, + "learning_rate": 3.386146742937815e-05, + "loss": 1.5948, + "step": 10968 + }, + { + "epoch": 0.611392898946547, + "grad_norm": 0.5517137050628662, + "learning_rate": 3.385304002860799e-05, + "loss": 1.5442, + "step": 10969 + }, + { + "epoch": 0.6114486371997102, + "grad_norm": 0.5374296307563782, + "learning_rate": 3.384461313992526e-05, + "loss": 1.743, + "step": 10970 + }, + { + "epoch": 0.6115043754528733, + "grad_norm": 0.6051550507545471, + "learning_rate": 3.38361867635972e-05, + "loss": 1.8001, + "step": 10971 + }, + { + "epoch": 0.6115601137060365, + "grad_norm": 0.5788960456848145, + "learning_rate": 3.382776089989107e-05, + "loss": 1.8217, + "step": 10972 + }, + { + "epoch": 0.6116158519591997, + "grad_norm": 0.5100364089012146, + "learning_rate": 3.3819335549074064e-05, + "loss": 1.5457, + "step": 10973 + }, + { + "epoch": 0.6116715902123627, + "grad_norm": 0.5339128971099854, + "learning_rate": 3.3810910711413376e-05, + "loss": 1.571, + "step": 10974 + }, + { + "epoch": 0.6117273284655259, + "grad_norm": 0.5776057839393616, + "learning_rate": 3.380248638717625e-05, + "loss": 1.579, + "step": 10975 + }, + { + "epoch": 0.611783066718689, + "grad_norm": 0.7491598725318909, + "learning_rate": 3.379406257662977e-05, + "loss": 1.5398, + "step": 10976 + }, + { + "epoch": 0.6118388049718522, + "grad_norm": 0.5306689739227295, + "learning_rate": 3.378563928004118e-05, + "loss": 1.7963, + "step": 10977 + }, + { + "epoch": 0.6118945432250154, + "grad_norm": 0.6286993026733398, + "learning_rate": 3.377721649767755e-05, + "loss": 1.7298, + "step": 10978 + }, + { + "epoch": 0.6119502814781784, + "grad_norm": 0.5252998471260071, + "learning_rate": 3.376879422980605e-05, + "loss": 1.6033, + "step": 10979 + }, + { + "epoch": 0.6120060197313416, + "grad_norm": 0.5619044899940491, + "learning_rate": 3.3760372476693744e-05, + "loss": 1.5339, + "step": 10980 + }, + { + "epoch": 0.6120617579845048, + "grad_norm": 0.5480098128318787, + "learning_rate": 3.375195123860774e-05, + "loss": 1.4833, + "step": 10981 + }, + { + "epoch": 0.6121174962376679, + "grad_norm": 0.5810719728469849, + "learning_rate": 3.374353051581513e-05, + "loss": 1.7522, + "step": 10982 + }, + { + "epoch": 0.612173234490831, + "grad_norm": 0.6109387874603271, + "learning_rate": 3.373511030858292e-05, + "loss": 1.7102, + "step": 10983 + }, + { + "epoch": 0.6122289727439942, + "grad_norm": 0.556450605392456, + "learning_rate": 3.372669061717821e-05, + "loss": 1.6045, + "step": 10984 + }, + { + "epoch": 0.6122847109971573, + "grad_norm": 0.5535019636154175, + "learning_rate": 3.3718271441867964e-05, + "loss": 1.7434, + "step": 10985 + }, + { + "epoch": 0.6123404492503205, + "grad_norm": 0.5736287832260132, + "learning_rate": 3.370985278291923e-05, + "loss": 1.5278, + "step": 10986 + }, + { + "epoch": 0.6123961875034837, + "grad_norm": 0.5478652715682983, + "learning_rate": 3.3701434640599e-05, + "loss": 1.4593, + "step": 10987 + }, + { + "epoch": 0.6124519257566468, + "grad_norm": 0.5607852935791016, + "learning_rate": 3.369301701517422e-05, + "loss": 1.616, + "step": 10988 + }, + { + "epoch": 0.6125076640098099, + "grad_norm": 0.6062629222869873, + "learning_rate": 3.3684599906911885e-05, + "loss": 1.7739, + "step": 10989 + }, + { + "epoch": 0.6125634022629731, + "grad_norm": 0.6138796806335449, + "learning_rate": 3.36761833160789e-05, + "loss": 1.7103, + "step": 10990 + }, + { + "epoch": 0.6126191405161362, + "grad_norm": 0.5835701823234558, + "learning_rate": 3.3667767242942215e-05, + "loss": 1.6394, + "step": 10991 + }, + { + "epoch": 0.6126748787692994, + "grad_norm": 0.5834316611289978, + "learning_rate": 3.3659351687768714e-05, + "loss": 1.6211, + "step": 10992 + }, + { + "epoch": 0.6127306170224626, + "grad_norm": 0.5939779877662659, + "learning_rate": 3.3650936650825305e-05, + "loss": 1.9074, + "step": 10993 + }, + { + "epoch": 0.6127863552756256, + "grad_norm": 0.5545198321342468, + "learning_rate": 3.364252213237887e-05, + "loss": 1.7556, + "step": 10994 + }, + { + "epoch": 0.6128420935287888, + "grad_norm": 0.536385715007782, + "learning_rate": 3.363410813269627e-05, + "loss": 1.6704, + "step": 10995 + }, + { + "epoch": 0.612897831781952, + "grad_norm": 0.5516625046730042, + "learning_rate": 3.362569465204434e-05, + "loss": 1.629, + "step": 10996 + }, + { + "epoch": 0.6129535700351151, + "grad_norm": 0.5734841227531433, + "learning_rate": 3.361728169068989e-05, + "loss": 1.5543, + "step": 10997 + }, + { + "epoch": 0.6130093082882783, + "grad_norm": 0.48854759335517883, + "learning_rate": 3.360886924889977e-05, + "loss": 1.484, + "step": 10998 + }, + { + "epoch": 0.6130650465414413, + "grad_norm": 0.5883350372314453, + "learning_rate": 3.360045732694074e-05, + "loss": 1.5407, + "step": 10999 + }, + { + "epoch": 0.6131207847946045, + "grad_norm": 0.5424591898918152, + "learning_rate": 3.3592045925079575e-05, + "loss": 1.801, + "step": 11000 + }, + { + "epoch": 0.6131765230477677, + "grad_norm": 0.5398431420326233, + "learning_rate": 3.3583635043583075e-05, + "loss": 1.7198, + "step": 11001 + }, + { + "epoch": 0.6132322613009308, + "grad_norm": 0.5736198425292969, + "learning_rate": 3.357522468271793e-05, + "loss": 1.8192, + "step": 11002 + }, + { + "epoch": 0.613287999554094, + "grad_norm": 0.5277306437492371, + "learning_rate": 3.356681484275091e-05, + "loss": 1.5158, + "step": 11003 + }, + { + "epoch": 0.6133437378072571, + "grad_norm": 0.539786696434021, + "learning_rate": 3.3558405523948703e-05, + "loss": 1.5025, + "step": 11004 + }, + { + "epoch": 0.6133994760604202, + "grad_norm": 0.5373875498771667, + "learning_rate": 3.354999672657802e-05, + "loss": 1.4258, + "step": 11005 + }, + { + "epoch": 0.6134552143135834, + "grad_norm": 0.6097363829612732, + "learning_rate": 3.354158845090553e-05, + "loss": 1.5761, + "step": 11006 + }, + { + "epoch": 0.6135109525667466, + "grad_norm": 0.576100766658783, + "learning_rate": 3.3533180697197886e-05, + "loss": 1.8187, + "step": 11007 + }, + { + "epoch": 0.6135666908199097, + "grad_norm": 0.5665978789329529, + "learning_rate": 3.352477346572176e-05, + "loss": 1.655, + "step": 11008 + }, + { + "epoch": 0.6136224290730729, + "grad_norm": 0.5619946122169495, + "learning_rate": 3.351636675674373e-05, + "loss": 1.7595, + "step": 11009 + }, + { + "epoch": 0.613678167326236, + "grad_norm": 0.5662100911140442, + "learning_rate": 3.350796057053048e-05, + "loss": 1.7159, + "step": 11010 + }, + { + "epoch": 0.6137339055793991, + "grad_norm": 0.5565624237060547, + "learning_rate": 3.349955490734854e-05, + "loss": 1.6548, + "step": 11011 + }, + { + "epoch": 0.6137896438325623, + "grad_norm": 0.5969928503036499, + "learning_rate": 3.349114976746451e-05, + "loss": 1.6303, + "step": 11012 + }, + { + "epoch": 0.6138453820857255, + "grad_norm": 0.552580714225769, + "learning_rate": 3.348274515114498e-05, + "loss": 1.6347, + "step": 11013 + }, + { + "epoch": 0.6139011203388886, + "grad_norm": 0.4925132393836975, + "learning_rate": 3.3474341058656453e-05, + "loss": 1.3515, + "step": 11014 + }, + { + "epoch": 0.6139568585920517, + "grad_norm": 0.5885698795318604, + "learning_rate": 3.346593749026549e-05, + "loss": 1.8692, + "step": 11015 + }, + { + "epoch": 0.6140125968452149, + "grad_norm": 0.5670897364616394, + "learning_rate": 3.345753444623858e-05, + "loss": 1.6248, + "step": 11016 + }, + { + "epoch": 0.614068335098378, + "grad_norm": 0.5874050259590149, + "learning_rate": 3.344913192684224e-05, + "loss": 1.6746, + "step": 11017 + }, + { + "epoch": 0.6141240733515412, + "grad_norm": 0.5586856603622437, + "learning_rate": 3.344072993234292e-05, + "loss": 1.6177, + "step": 11018 + }, + { + "epoch": 0.6141798116047044, + "grad_norm": 0.5451282858848572, + "learning_rate": 3.343232846300709e-05, + "loss": 1.6588, + "step": 11019 + }, + { + "epoch": 0.6142355498578674, + "grad_norm": 0.5075144171714783, + "learning_rate": 3.3423927519101225e-05, + "loss": 1.257, + "step": 11020 + }, + { + "epoch": 0.6142912881110306, + "grad_norm": 0.569128692150116, + "learning_rate": 3.3415527100891734e-05, + "loss": 1.5108, + "step": 11021 + }, + { + "epoch": 0.6143470263641937, + "grad_norm": 0.6079961061477661, + "learning_rate": 3.3407127208645026e-05, + "loss": 1.8459, + "step": 11022 + }, + { + "epoch": 0.6144027646173569, + "grad_norm": 0.5876660943031311, + "learning_rate": 3.33987278426275e-05, + "loss": 1.9795, + "step": 11023 + }, + { + "epoch": 0.6144585028705201, + "grad_norm": 0.5557812452316284, + "learning_rate": 3.339032900310554e-05, + "loss": 1.5239, + "step": 11024 + }, + { + "epoch": 0.6145142411236831, + "grad_norm": 0.7021792531013489, + "learning_rate": 3.338193069034549e-05, + "loss": 2.0899, + "step": 11025 + }, + { + "epoch": 0.6145699793768463, + "grad_norm": 0.5470578074455261, + "learning_rate": 3.33735329046137e-05, + "loss": 1.7312, + "step": 11026 + }, + { + "epoch": 0.6146257176300095, + "grad_norm": 0.5664429664611816, + "learning_rate": 3.336513564617654e-05, + "loss": 1.5185, + "step": 11027 + }, + { + "epoch": 0.6146814558831726, + "grad_norm": 0.6334248185157776, + "learning_rate": 3.3356738915300255e-05, + "loss": 1.8831, + "step": 11028 + }, + { + "epoch": 0.6147371941363358, + "grad_norm": 0.5621626377105713, + "learning_rate": 3.33483427122512e-05, + "loss": 1.7854, + "step": 11029 + }, + { + "epoch": 0.614792932389499, + "grad_norm": 0.5289725065231323, + "learning_rate": 3.333994703729562e-05, + "loss": 1.5749, + "step": 11030 + }, + { + "epoch": 0.614848670642662, + "grad_norm": 0.5943875312805176, + "learning_rate": 3.333155189069978e-05, + "loss": 1.7339, + "step": 11031 + }, + { + "epoch": 0.6149044088958252, + "grad_norm": 0.5255435109138489, + "learning_rate": 3.332315727272994e-05, + "loss": 1.6177, + "step": 11032 + }, + { + "epoch": 0.6149601471489884, + "grad_norm": 0.5951310396194458, + "learning_rate": 3.331476318365231e-05, + "loss": 1.8444, + "step": 11033 + }, + { + "epoch": 0.6150158854021515, + "grad_norm": 0.5913835763931274, + "learning_rate": 3.330636962373312e-05, + "loss": 1.5832, + "step": 11034 + }, + { + "epoch": 0.6150716236553146, + "grad_norm": 0.5857747197151184, + "learning_rate": 3.329797659323853e-05, + "loss": 1.7523, + "step": 11035 + }, + { + "epoch": 0.6151273619084778, + "grad_norm": 0.5293170213699341, + "learning_rate": 3.3289584092434785e-05, + "loss": 1.5468, + "step": 11036 + }, + { + "epoch": 0.6151831001616409, + "grad_norm": 0.5425816178321838, + "learning_rate": 3.328119212158797e-05, + "loss": 1.6177, + "step": 11037 + }, + { + "epoch": 0.6152388384148041, + "grad_norm": 0.53827965259552, + "learning_rate": 3.327280068096429e-05, + "loss": 1.585, + "step": 11038 + }, + { + "epoch": 0.6152945766679673, + "grad_norm": 0.5500679612159729, + "learning_rate": 3.326440977082981e-05, + "loss": 1.5652, + "step": 11039 + }, + { + "epoch": 0.6153503149211303, + "grad_norm": 0.5159964561462402, + "learning_rate": 3.325601939145069e-05, + "loss": 1.6, + "step": 11040 + }, + { + "epoch": 0.6154060531742935, + "grad_norm": 0.5599196553230286, + "learning_rate": 3.3247629543093025e-05, + "loss": 1.7046, + "step": 11041 + }, + { + "epoch": 0.6154617914274567, + "grad_norm": 0.5590962767601013, + "learning_rate": 3.323924022602287e-05, + "loss": 1.7124, + "step": 11042 + }, + { + "epoch": 0.6155175296806198, + "grad_norm": 0.5326443910598755, + "learning_rate": 3.32308514405063e-05, + "loss": 1.4437, + "step": 11043 + }, + { + "epoch": 0.615573267933783, + "grad_norm": 0.6075683832168579, + "learning_rate": 3.322246318680934e-05, + "loss": 1.809, + "step": 11044 + }, + { + "epoch": 0.615629006186946, + "grad_norm": 0.5951778888702393, + "learning_rate": 3.321407546519802e-05, + "loss": 1.6689, + "step": 11045 + }, + { + "epoch": 0.6156847444401092, + "grad_norm": 0.5833475589752197, + "learning_rate": 3.320568827593837e-05, + "loss": 1.7449, + "step": 11046 + }, + { + "epoch": 0.6157404826932724, + "grad_norm": 0.562238872051239, + "learning_rate": 3.319730161929637e-05, + "loss": 1.6372, + "step": 11047 + }, + { + "epoch": 0.6157962209464355, + "grad_norm": 0.5967754125595093, + "learning_rate": 3.318891549553801e-05, + "loss": 1.6837, + "step": 11048 + }, + { + "epoch": 0.6158519591995987, + "grad_norm": 0.5980004072189331, + "learning_rate": 3.318052990492921e-05, + "loss": 1.7888, + "step": 11049 + }, + { + "epoch": 0.6159076974527619, + "grad_norm": 0.53914874792099, + "learning_rate": 3.317214484773596e-05, + "loss": 1.6178, + "step": 11050 + }, + { + "epoch": 0.6159634357059249, + "grad_norm": 0.606036365032196, + "learning_rate": 3.316376032422415e-05, + "loss": 1.9799, + "step": 11051 + }, + { + "epoch": 0.6160191739590881, + "grad_norm": 0.6011738181114197, + "learning_rate": 3.315537633465968e-05, + "loss": 1.7318, + "step": 11052 + }, + { + "epoch": 0.6160749122122513, + "grad_norm": 0.4829182028770447, + "learning_rate": 3.3146992879308505e-05, + "loss": 1.2948, + "step": 11053 + }, + { + "epoch": 0.6161306504654144, + "grad_norm": 0.5873551368713379, + "learning_rate": 3.3138609958436414e-05, + "loss": 1.7205, + "step": 11054 + }, + { + "epoch": 0.6161863887185776, + "grad_norm": 0.5033444762229919, + "learning_rate": 3.3130227572309334e-05, + "loss": 1.4926, + "step": 11055 + }, + { + "epoch": 0.6162421269717407, + "grad_norm": 0.5444531440734863, + "learning_rate": 3.3121845721193065e-05, + "loss": 1.5604, + "step": 11056 + }, + { + "epoch": 0.6162978652249038, + "grad_norm": 0.585561990737915, + "learning_rate": 3.311346440535346e-05, + "loss": 1.737, + "step": 11057 + }, + { + "epoch": 0.616353603478067, + "grad_norm": 0.6604238748550415, + "learning_rate": 3.31050836250563e-05, + "loss": 1.2615, + "step": 11058 + }, + { + "epoch": 0.6164093417312302, + "grad_norm": 0.5413322448730469, + "learning_rate": 3.3096703380567376e-05, + "loss": 1.6531, + "step": 11059 + }, + { + "epoch": 0.6164650799843933, + "grad_norm": 0.5525966882705688, + "learning_rate": 3.3088323672152474e-05, + "loss": 1.7572, + "step": 11060 + }, + { + "epoch": 0.6165208182375564, + "grad_norm": 0.62772136926651, + "learning_rate": 3.307994450007733e-05, + "loss": 1.7705, + "step": 11061 + }, + { + "epoch": 0.6165765564907196, + "grad_norm": 0.5861853957176208, + "learning_rate": 3.3071565864607723e-05, + "loss": 1.7726, + "step": 11062 + }, + { + "epoch": 0.6166322947438827, + "grad_norm": 0.5600711107254028, + "learning_rate": 3.3063187766009316e-05, + "loss": 1.4762, + "step": 11063 + }, + { + "epoch": 0.6166880329970459, + "grad_norm": 0.5767860412597656, + "learning_rate": 3.305481020454787e-05, + "loss": 1.7204, + "step": 11064 + }, + { + "epoch": 0.6167437712502091, + "grad_norm": 0.5620105862617493, + "learning_rate": 3.304643318048903e-05, + "loss": 1.5623, + "step": 11065 + }, + { + "epoch": 0.6167995095033721, + "grad_norm": 0.5560240745544434, + "learning_rate": 3.303805669409848e-05, + "loss": 1.7162, + "step": 11066 + }, + { + "epoch": 0.6168552477565353, + "grad_norm": 0.5894601345062256, + "learning_rate": 3.30296807456419e-05, + "loss": 1.666, + "step": 11067 + }, + { + "epoch": 0.6169109860096984, + "grad_norm": 0.5420163869857788, + "learning_rate": 3.3021305335384886e-05, + "loss": 1.3855, + "step": 11068 + }, + { + "epoch": 0.6169667242628616, + "grad_norm": 0.6015777587890625, + "learning_rate": 3.3012930463593084e-05, + "loss": 1.8732, + "step": 11069 + }, + { + "epoch": 0.6170224625160248, + "grad_norm": 0.5890399217605591, + "learning_rate": 3.300455613053207e-05, + "loss": 1.5905, + "step": 11070 + }, + { + "epoch": 0.6170782007691878, + "grad_norm": 0.5790014863014221, + "learning_rate": 3.299618233646745e-05, + "loss": 1.5319, + "step": 11071 + }, + { + "epoch": 0.617133939022351, + "grad_norm": 0.5821947455406189, + "learning_rate": 3.29878090816648e-05, + "loss": 1.7873, + "step": 11072 + }, + { + "epoch": 0.6171896772755142, + "grad_norm": 0.5517497658729553, + "learning_rate": 3.297943636638965e-05, + "loss": 1.8069, + "step": 11073 + }, + { + "epoch": 0.6172454155286773, + "grad_norm": 0.509792149066925, + "learning_rate": 3.297106419090754e-05, + "loss": 1.3797, + "step": 11074 + }, + { + "epoch": 0.6173011537818405, + "grad_norm": 0.5943223834037781, + "learning_rate": 3.296269255548399e-05, + "loss": 1.8426, + "step": 11075 + }, + { + "epoch": 0.6173568920350037, + "grad_norm": 0.5859249830245972, + "learning_rate": 3.2954321460384506e-05, + "loss": 1.5177, + "step": 11076 + }, + { + "epoch": 0.6174126302881667, + "grad_norm": 0.5453793406486511, + "learning_rate": 3.294595090587455e-05, + "loss": 1.641, + "step": 11077 + }, + { + "epoch": 0.6174683685413299, + "grad_norm": 0.5777225494384766, + "learning_rate": 3.293758089221959e-05, + "loss": 1.6019, + "step": 11078 + }, + { + "epoch": 0.6175241067944931, + "grad_norm": 0.6105305552482605, + "learning_rate": 3.292921141968511e-05, + "loss": 1.5064, + "step": 11079 + }, + { + "epoch": 0.6175798450476562, + "grad_norm": 0.5501500964164734, + "learning_rate": 3.292084248853649e-05, + "loss": 1.7632, + "step": 11080 + }, + { + "epoch": 0.6176355833008194, + "grad_norm": 0.546392560005188, + "learning_rate": 3.291247409903919e-05, + "loss": 1.5724, + "step": 11081 + }, + { + "epoch": 0.6176913215539825, + "grad_norm": 0.6007018685340881, + "learning_rate": 3.290410625145857e-05, + "loss": 1.8628, + "step": 11082 + }, + { + "epoch": 0.6177470598071456, + "grad_norm": 0.5350911617279053, + "learning_rate": 3.289573894606003e-05, + "loss": 1.5649, + "step": 11083 + }, + { + "epoch": 0.6178027980603088, + "grad_norm": 0.5646401047706604, + "learning_rate": 3.288737218310892e-05, + "loss": 1.5843, + "step": 11084 + }, + { + "epoch": 0.617858536313472, + "grad_norm": 0.5566853880882263, + "learning_rate": 3.287900596287059e-05, + "loss": 1.6214, + "step": 11085 + }, + { + "epoch": 0.6179142745666351, + "grad_norm": 0.659518837928772, + "learning_rate": 3.2870640285610375e-05, + "loss": 1.9879, + "step": 11086 + }, + { + "epoch": 0.6179700128197982, + "grad_norm": 0.5458612442016602, + "learning_rate": 3.286227515159357e-05, + "loss": 1.6907, + "step": 11087 + }, + { + "epoch": 0.6180257510729614, + "grad_norm": 0.5440777540206909, + "learning_rate": 3.28539105610855e-05, + "loss": 1.7293, + "step": 11088 + }, + { + "epoch": 0.6180814893261245, + "grad_norm": 0.5791444182395935, + "learning_rate": 3.284554651435138e-05, + "loss": 1.7966, + "step": 11089 + }, + { + "epoch": 0.6181372275792877, + "grad_norm": 0.5879372358322144, + "learning_rate": 3.2837183011656533e-05, + "loss": 1.7938, + "step": 11090 + }, + { + "epoch": 0.6181929658324508, + "grad_norm": 0.5607120394706726, + "learning_rate": 3.2828820053266176e-05, + "loss": 1.6818, + "step": 11091 + }, + { + "epoch": 0.6182487040856139, + "grad_norm": 0.5742748379707336, + "learning_rate": 3.2820457639445525e-05, + "loss": 1.7102, + "step": 11092 + }, + { + "epoch": 0.6183044423387771, + "grad_norm": 0.584244966506958, + "learning_rate": 3.28120957704598e-05, + "loss": 1.7051, + "step": 11093 + }, + { + "epoch": 0.6183601805919402, + "grad_norm": 0.5676624178886414, + "learning_rate": 3.280373444657417e-05, + "loss": 1.6841, + "step": 11094 + }, + { + "epoch": 0.6184159188451034, + "grad_norm": 0.6396898031234741, + "learning_rate": 3.279537366805384e-05, + "loss": 2.0282, + "step": 11095 + }, + { + "epoch": 0.6184716570982666, + "grad_norm": 0.5480191111564636, + "learning_rate": 3.278701343516393e-05, + "loss": 1.6552, + "step": 11096 + }, + { + "epoch": 0.6185273953514296, + "grad_norm": 0.5784115195274353, + "learning_rate": 3.27786537481696e-05, + "loss": 1.7273, + "step": 11097 + }, + { + "epoch": 0.6185831336045928, + "grad_norm": 0.5261921286582947, + "learning_rate": 3.277029460733598e-05, + "loss": 1.6164, + "step": 11098 + }, + { + "epoch": 0.618638871857756, + "grad_norm": 0.6365436315536499, + "learning_rate": 3.276193601292815e-05, + "loss": 1.9246, + "step": 11099 + }, + { + "epoch": 0.6186946101109191, + "grad_norm": 0.539184033870697, + "learning_rate": 3.275357796521121e-05, + "loss": 1.5328, + "step": 11100 + }, + { + "epoch": 0.6187503483640823, + "grad_norm": 0.5453305840492249, + "learning_rate": 3.274522046445021e-05, + "loss": 1.7782, + "step": 11101 + }, + { + "epoch": 0.6188060866172455, + "grad_norm": 0.5231083035469055, + "learning_rate": 3.273686351091023e-05, + "loss": 1.5018, + "step": 11102 + }, + { + "epoch": 0.6188618248704085, + "grad_norm": 0.5448489189147949, + "learning_rate": 3.272850710485628e-05, + "loss": 1.6596, + "step": 11103 + }, + { + "epoch": 0.6189175631235717, + "grad_norm": 0.5277993083000183, + "learning_rate": 3.2720151246553366e-05, + "loss": 1.4884, + "step": 11104 + }, + { + "epoch": 0.6189733013767349, + "grad_norm": 0.5456802845001221, + "learning_rate": 3.271179593626654e-05, + "loss": 1.5642, + "step": 11105 + }, + { + "epoch": 0.619029039629898, + "grad_norm": 0.5369241833686829, + "learning_rate": 3.270344117426073e-05, + "loss": 1.7674, + "step": 11106 + }, + { + "epoch": 0.6190847778830612, + "grad_norm": 0.5577540397644043, + "learning_rate": 3.269508696080093e-05, + "loss": 1.5923, + "step": 11107 + }, + { + "epoch": 0.6191405161362243, + "grad_norm": 0.5356347560882568, + "learning_rate": 3.268673329615207e-05, + "loss": 1.5301, + "step": 11108 + }, + { + "epoch": 0.6191962543893874, + "grad_norm": 0.5975854396820068, + "learning_rate": 3.267838018057909e-05, + "loss": 1.5344, + "step": 11109 + }, + { + "epoch": 0.6192519926425506, + "grad_norm": 0.5814411044120789, + "learning_rate": 3.2670027614346896e-05, + "loss": 1.8432, + "step": 11110 + }, + { + "epoch": 0.6193077308957138, + "grad_norm": 0.559992253780365, + "learning_rate": 3.2661675597720384e-05, + "loss": 1.6279, + "step": 11111 + }, + { + "epoch": 0.6193634691488769, + "grad_norm": 0.5477424263954163, + "learning_rate": 3.265332413096444e-05, + "loss": 1.5426, + "step": 11112 + }, + { + "epoch": 0.61941920740204, + "grad_norm": 0.5477100014686584, + "learning_rate": 3.26449732143439e-05, + "loss": 1.709, + "step": 11113 + }, + { + "epoch": 0.6194749456552031, + "grad_norm": 0.5695294141769409, + "learning_rate": 3.263662284812365e-05, + "loss": 1.6154, + "step": 11114 + }, + { + "epoch": 0.6195306839083663, + "grad_norm": 0.5602665543556213, + "learning_rate": 3.262827303256846e-05, + "loss": 1.4069, + "step": 11115 + }, + { + "epoch": 0.6195864221615295, + "grad_norm": 0.5472245216369629, + "learning_rate": 3.261992376794318e-05, + "loss": 1.6916, + "step": 11116 + }, + { + "epoch": 0.6196421604146926, + "grad_norm": 0.5716364979743958, + "learning_rate": 3.2611575054512584e-05, + "loss": 1.829, + "step": 11117 + }, + { + "epoch": 0.6196978986678557, + "grad_norm": 0.5174562931060791, + "learning_rate": 3.2603226892541437e-05, + "loss": 1.4311, + "step": 11118 + }, + { + "epoch": 0.6197536369210189, + "grad_norm": 0.5370128750801086, + "learning_rate": 3.2594879282294524e-05, + "loss": 1.7092, + "step": 11119 + }, + { + "epoch": 0.619809375174182, + "grad_norm": 0.5618498921394348, + "learning_rate": 3.258653222403654e-05, + "loss": 1.5921, + "step": 11120 + }, + { + "epoch": 0.6198651134273452, + "grad_norm": 0.54872065782547, + "learning_rate": 3.257818571803224e-05, + "loss": 1.6191, + "step": 11121 + }, + { + "epoch": 0.6199208516805084, + "grad_norm": 0.5251935720443726, + "learning_rate": 3.25698397645463e-05, + "loss": 1.3492, + "step": 11122 + }, + { + "epoch": 0.6199765899336714, + "grad_norm": 0.5758818984031677, + "learning_rate": 3.2561494363843416e-05, + "loss": 1.7222, + "step": 11123 + }, + { + "epoch": 0.6200323281868346, + "grad_norm": 0.5772950649261475, + "learning_rate": 3.255314951618827e-05, + "loss": 1.5677, + "step": 11124 + }, + { + "epoch": 0.6200880664399978, + "grad_norm": 0.5665372014045715, + "learning_rate": 3.2544805221845485e-05, + "loss": 1.4315, + "step": 11125 + }, + { + "epoch": 0.6201438046931609, + "grad_norm": 0.5531750321388245, + "learning_rate": 3.253646148107973e-05, + "loss": 1.4994, + "step": 11126 + }, + { + "epoch": 0.6201995429463241, + "grad_norm": 0.5572689771652222, + "learning_rate": 3.2528118294155576e-05, + "loss": 1.4227, + "step": 11127 + }, + { + "epoch": 0.6202552811994873, + "grad_norm": 0.577793538570404, + "learning_rate": 3.251977566133766e-05, + "loss": 1.8407, + "step": 11128 + }, + { + "epoch": 0.6203110194526503, + "grad_norm": 0.6016719341278076, + "learning_rate": 3.251143358289053e-05, + "loss": 1.8582, + "step": 11129 + }, + { + "epoch": 0.6203667577058135, + "grad_norm": 0.5398997068405151, + "learning_rate": 3.2503092059078754e-05, + "loss": 1.6491, + "step": 11130 + }, + { + "epoch": 0.6204224959589767, + "grad_norm": 0.5354841947555542, + "learning_rate": 3.2494751090166907e-05, + "loss": 1.6451, + "step": 11131 + }, + { + "epoch": 0.6204782342121398, + "grad_norm": 0.5381180047988892, + "learning_rate": 3.2486410676419467e-05, + "loss": 1.563, + "step": 11132 + }, + { + "epoch": 0.620533972465303, + "grad_norm": 0.5650672912597656, + "learning_rate": 3.247807081810099e-05, + "loss": 1.7636, + "step": 11133 + }, + { + "epoch": 0.6205897107184661, + "grad_norm": 0.5720324516296387, + "learning_rate": 3.246973151547594e-05, + "loss": 1.6853, + "step": 11134 + }, + { + "epoch": 0.6206454489716292, + "grad_norm": 0.6177263855934143, + "learning_rate": 3.2461392768808796e-05, + "loss": 1.7606, + "step": 11135 + }, + { + "epoch": 0.6207011872247924, + "grad_norm": 0.547572672367096, + "learning_rate": 3.245305457836402e-05, + "loss": 1.6584, + "step": 11136 + }, + { + "epoch": 0.6207569254779555, + "grad_norm": 0.5631645917892456, + "learning_rate": 3.244471694440604e-05, + "loss": 1.6822, + "step": 11137 + }, + { + "epoch": 0.6208126637311187, + "grad_norm": 0.5759522914886475, + "learning_rate": 3.243637986719929e-05, + "loss": 1.7112, + "step": 11138 + }, + { + "epoch": 0.6208684019842818, + "grad_norm": 0.557873547077179, + "learning_rate": 3.2428043347008154e-05, + "loss": 1.731, + "step": 11139 + }, + { + "epoch": 0.6209241402374449, + "grad_norm": 0.5248095393180847, + "learning_rate": 3.241970738409707e-05, + "loss": 1.6321, + "step": 11140 + }, + { + "epoch": 0.6209798784906081, + "grad_norm": 0.5478214025497437, + "learning_rate": 3.241137197873032e-05, + "loss": 1.5864, + "step": 11141 + }, + { + "epoch": 0.6210356167437713, + "grad_norm": 0.6157545447349548, + "learning_rate": 3.2403037131172324e-05, + "loss": 1.8697, + "step": 11142 + }, + { + "epoch": 0.6210913549969344, + "grad_norm": 0.5615748167037964, + "learning_rate": 3.239470284168739e-05, + "loss": 1.7243, + "step": 11143 + }, + { + "epoch": 0.6211470932500975, + "grad_norm": 0.6518558859825134, + "learning_rate": 3.238636911053984e-05, + "loss": 1.953, + "step": 11144 + }, + { + "epoch": 0.6212028315032607, + "grad_norm": 0.518277108669281, + "learning_rate": 3.237803593799397e-05, + "loss": 1.7371, + "step": 11145 + }, + { + "epoch": 0.6212585697564238, + "grad_norm": 0.5324394106864929, + "learning_rate": 3.2369703324314046e-05, + "loss": 1.6465, + "step": 11146 + }, + { + "epoch": 0.621314308009587, + "grad_norm": 0.5850804448127747, + "learning_rate": 3.236137126976435e-05, + "loss": 1.7146, + "step": 11147 + }, + { + "epoch": 0.6213700462627502, + "grad_norm": 0.5877463221549988, + "learning_rate": 3.23530397746091e-05, + "loss": 1.8071, + "step": 11148 + }, + { + "epoch": 0.6214257845159132, + "grad_norm": 0.582880973815918, + "learning_rate": 3.234470883911255e-05, + "loss": 1.6476, + "step": 11149 + }, + { + "epoch": 0.6214815227690764, + "grad_norm": 0.5952877402305603, + "learning_rate": 3.2336378463538907e-05, + "loss": 1.7425, + "step": 11150 + }, + { + "epoch": 0.6215372610222396, + "grad_norm": 0.5596649646759033, + "learning_rate": 3.232804864815234e-05, + "loss": 1.5382, + "step": 11151 + }, + { + "epoch": 0.6215929992754027, + "grad_norm": 0.5372732281684875, + "learning_rate": 3.2319719393217055e-05, + "loss": 1.5486, + "step": 11152 + }, + { + "epoch": 0.6216487375285659, + "grad_norm": 0.6073440909385681, + "learning_rate": 3.231139069899717e-05, + "loss": 1.8761, + "step": 11153 + }, + { + "epoch": 0.621704475781729, + "grad_norm": 0.6037800312042236, + "learning_rate": 3.230306256575685e-05, + "loss": 1.8006, + "step": 11154 + }, + { + "epoch": 0.6217602140348921, + "grad_norm": 0.5567789673805237, + "learning_rate": 3.2294734993760196e-05, + "loss": 1.681, + "step": 11155 + }, + { + "epoch": 0.6218159522880553, + "grad_norm": 0.5184069275856018, + "learning_rate": 3.228640798327131e-05, + "loss": 1.6012, + "step": 11156 + }, + { + "epoch": 0.6218716905412185, + "grad_norm": 0.5890794992446899, + "learning_rate": 3.227808153455431e-05, + "loss": 1.8304, + "step": 11157 + }, + { + "epoch": 0.6219274287943816, + "grad_norm": 0.5692599415779114, + "learning_rate": 3.226975564787322e-05, + "loss": 1.699, + "step": 11158 + }, + { + "epoch": 0.6219831670475447, + "grad_norm": 0.5787486433982849, + "learning_rate": 3.226143032349211e-05, + "loss": 1.5854, + "step": 11159 + }, + { + "epoch": 0.6220389053007078, + "grad_norm": 0.6033738851547241, + "learning_rate": 3.225310556167501e-05, + "loss": 1.8011, + "step": 11160 + }, + { + "epoch": 0.622094643553871, + "grad_norm": 0.5922840237617493, + "learning_rate": 3.2244781362685937e-05, + "loss": 1.8349, + "step": 11161 + }, + { + "epoch": 0.6221503818070342, + "grad_norm": 0.5423793792724609, + "learning_rate": 3.223645772678887e-05, + "loss": 1.6352, + "step": 11162 + }, + { + "epoch": 0.6222061200601973, + "grad_norm": 0.5888994336128235, + "learning_rate": 3.2228134654247785e-05, + "loss": 1.7301, + "step": 11163 + }, + { + "epoch": 0.6222618583133604, + "grad_norm": 0.5580011010169983, + "learning_rate": 3.2219812145326675e-05, + "loss": 1.939, + "step": 11164 + }, + { + "epoch": 0.6223175965665236, + "grad_norm": 0.5396100878715515, + "learning_rate": 3.221149020028944e-05, + "loss": 1.5153, + "step": 11165 + }, + { + "epoch": 0.6223733348196867, + "grad_norm": 0.5858661532402039, + "learning_rate": 3.2203168819400045e-05, + "loss": 1.7389, + "step": 11166 + }, + { + "epoch": 0.6224290730728499, + "grad_norm": 0.5977375507354736, + "learning_rate": 3.219484800292234e-05, + "loss": 1.6778, + "step": 11167 + }, + { + "epoch": 0.6224848113260131, + "grad_norm": 0.5393698215484619, + "learning_rate": 3.2186527751120264e-05, + "loss": 1.5979, + "step": 11168 + }, + { + "epoch": 0.6225405495791762, + "grad_norm": 0.5956501960754395, + "learning_rate": 3.2178208064257666e-05, + "loss": 1.6583, + "step": 11169 + }, + { + "epoch": 0.6225962878323393, + "grad_norm": 0.5951047539710999, + "learning_rate": 3.2169888942598395e-05, + "loss": 1.8095, + "step": 11170 + }, + { + "epoch": 0.6226520260855025, + "grad_norm": 0.5699685215950012, + "learning_rate": 3.2161570386406305e-05, + "loss": 1.7863, + "step": 11171 + }, + { + "epoch": 0.6227077643386656, + "grad_norm": 0.5904039144515991, + "learning_rate": 3.2153252395945176e-05, + "loss": 1.5287, + "step": 11172 + }, + { + "epoch": 0.6227635025918288, + "grad_norm": 0.5787484645843506, + "learning_rate": 3.214493497147885e-05, + "loss": 1.5626, + "step": 11173 + }, + { + "epoch": 0.622819240844992, + "grad_norm": 0.5047122836112976, + "learning_rate": 3.2136618113271055e-05, + "loss": 1.3227, + "step": 11174 + }, + { + "epoch": 0.622874979098155, + "grad_norm": 0.5570552349090576, + "learning_rate": 3.2128301821585616e-05, + "loss": 1.4615, + "step": 11175 + }, + { + "epoch": 0.6229307173513182, + "grad_norm": 0.5824396014213562, + "learning_rate": 3.2119986096686215e-05, + "loss": 1.5484, + "step": 11176 + }, + { + "epoch": 0.6229864556044814, + "grad_norm": 0.5634551048278809, + "learning_rate": 3.211167093883661e-05, + "loss": 1.3652, + "step": 11177 + }, + { + "epoch": 0.6230421938576445, + "grad_norm": 0.5389364957809448, + "learning_rate": 3.2103356348300525e-05, + "loss": 1.7177, + "step": 11178 + }, + { + "epoch": 0.6230979321108077, + "grad_norm": 0.5723541975021362, + "learning_rate": 3.2095042325341626e-05, + "loss": 1.6482, + "step": 11179 + }, + { + "epoch": 0.6231536703639708, + "grad_norm": 0.5335341691970825, + "learning_rate": 3.2086728870223594e-05, + "loss": 1.6545, + "step": 11180 + }, + { + "epoch": 0.6232094086171339, + "grad_norm": 0.6035029292106628, + "learning_rate": 3.207841598321007e-05, + "loss": 1.9482, + "step": 11181 + }, + { + "epoch": 0.6232651468702971, + "grad_norm": 0.5398215055465698, + "learning_rate": 3.207010366456469e-05, + "loss": 1.4994, + "step": 11182 + }, + { + "epoch": 0.6233208851234602, + "grad_norm": 0.5689934492111206, + "learning_rate": 3.206179191455111e-05, + "loss": 1.6828, + "step": 11183 + }, + { + "epoch": 0.6233766233766234, + "grad_norm": 0.5845012068748474, + "learning_rate": 3.2053480733432886e-05, + "loss": 1.66, + "step": 11184 + }, + { + "epoch": 0.6234323616297865, + "grad_norm": 0.6214088797569275, + "learning_rate": 3.204517012147363e-05, + "loss": 1.7498, + "step": 11185 + }, + { + "epoch": 0.6234880998829496, + "grad_norm": 0.5731697678565979, + "learning_rate": 3.2036860078936886e-05, + "loss": 1.7147, + "step": 11186 + }, + { + "epoch": 0.6235438381361128, + "grad_norm": 0.5301964282989502, + "learning_rate": 3.2028550606086216e-05, + "loss": 1.5002, + "step": 11187 + }, + { + "epoch": 0.623599576389276, + "grad_norm": 0.5406346321105957, + "learning_rate": 3.202024170318513e-05, + "loss": 1.6626, + "step": 11188 + }, + { + "epoch": 0.6236553146424391, + "grad_norm": 0.5429883599281311, + "learning_rate": 3.201193337049714e-05, + "loss": 1.6432, + "step": 11189 + }, + { + "epoch": 0.6237110528956022, + "grad_norm": 0.5684347748756409, + "learning_rate": 3.2003625608285776e-05, + "loss": 1.6593, + "step": 11190 + }, + { + "epoch": 0.6237667911487654, + "grad_norm": 0.6120270490646362, + "learning_rate": 3.199531841681445e-05, + "loss": 1.7227, + "step": 11191 + }, + { + "epoch": 0.6238225294019285, + "grad_norm": 0.5948870778083801, + "learning_rate": 3.198701179634668e-05, + "loss": 1.663, + "step": 11192 + }, + { + "epoch": 0.6238782676550917, + "grad_norm": 0.5670180320739746, + "learning_rate": 3.197870574714584e-05, + "loss": 1.3727, + "step": 11193 + }, + { + "epoch": 0.6239340059082549, + "grad_norm": 0.5460881590843201, + "learning_rate": 3.197040026947541e-05, + "loss": 1.7794, + "step": 11194 + }, + { + "epoch": 0.623989744161418, + "grad_norm": 0.5323398113250732, + "learning_rate": 3.196209536359874e-05, + "loss": 1.7328, + "step": 11195 + }, + { + "epoch": 0.6240454824145811, + "grad_norm": 0.5424444675445557, + "learning_rate": 3.195379102977925e-05, + "loss": 1.621, + "step": 11196 + }, + { + "epoch": 0.6241012206677443, + "grad_norm": 0.5800326466560364, + "learning_rate": 3.19454872682803e-05, + "loss": 1.6368, + "step": 11197 + }, + { + "epoch": 0.6241569589209074, + "grad_norm": 0.5419188737869263, + "learning_rate": 3.193718407936521e-05, + "loss": 1.4724, + "step": 11198 + }, + { + "epoch": 0.6242126971740706, + "grad_norm": 0.5642205476760864, + "learning_rate": 3.192888146329734e-05, + "loss": 1.5669, + "step": 11199 + }, + { + "epoch": 0.6242684354272338, + "grad_norm": 0.6043959856033325, + "learning_rate": 3.192057942033997e-05, + "loss": 1.904, + "step": 11200 + }, + { + "epoch": 0.6243241736803968, + "grad_norm": 0.5266156196594238, + "learning_rate": 3.191227795075644e-05, + "loss": 1.4223, + "step": 11201 + }, + { + "epoch": 0.62437991193356, + "grad_norm": 0.5283826589584351, + "learning_rate": 3.190397705480997e-05, + "loss": 1.6111, + "step": 11202 + }, + { + "epoch": 0.6244356501867232, + "grad_norm": 0.6343064308166504, + "learning_rate": 3.189567673276385e-05, + "loss": 2.0359, + "step": 11203 + }, + { + "epoch": 0.6244913884398863, + "grad_norm": 0.5972675085067749, + "learning_rate": 3.1887376984881315e-05, + "loss": 1.6094, + "step": 11204 + }, + { + "epoch": 0.6245471266930495, + "grad_norm": 0.5392424464225769, + "learning_rate": 3.187907781142556e-05, + "loss": 1.581, + "step": 11205 + }, + { + "epoch": 0.6246028649462125, + "grad_norm": 0.5838165283203125, + "learning_rate": 3.187077921265983e-05, + "loss": 1.4707, + "step": 11206 + }, + { + "epoch": 0.6246586031993757, + "grad_norm": 0.5730239152908325, + "learning_rate": 3.186248118884726e-05, + "loss": 1.6216, + "step": 11207 + }, + { + "epoch": 0.6247143414525389, + "grad_norm": 0.5531439185142517, + "learning_rate": 3.185418374025104e-05, + "loss": 1.5112, + "step": 11208 + }, + { + "epoch": 0.624770079705702, + "grad_norm": 0.5780851244926453, + "learning_rate": 3.184588686713432e-05, + "loss": 1.8131, + "step": 11209 + }, + { + "epoch": 0.6248258179588652, + "grad_norm": 0.6342042684555054, + "learning_rate": 3.183759056976022e-05, + "loss": 1.6177, + "step": 11210 + }, + { + "epoch": 0.6248815562120283, + "grad_norm": 0.5741910338401794, + "learning_rate": 3.1829294848391867e-05, + "loss": 1.8943, + "step": 11211 + }, + { + "epoch": 0.6249372944651914, + "grad_norm": 0.5274877548217773, + "learning_rate": 3.182099970329232e-05, + "loss": 1.4587, + "step": 11212 + }, + { + "epoch": 0.6249930327183546, + "grad_norm": 0.573377251625061, + "learning_rate": 3.181270513472469e-05, + "loss": 1.7161, + "step": 11213 + }, + { + "epoch": 0.6250487709715178, + "grad_norm": 0.5359188318252563, + "learning_rate": 3.1804411142952e-05, + "loss": 1.6094, + "step": 11214 + }, + { + "epoch": 0.6251045092246809, + "grad_norm": 0.5997651219367981, + "learning_rate": 3.179611772823729e-05, + "loss": 1.8517, + "step": 11215 + }, + { + "epoch": 0.625160247477844, + "grad_norm": 0.536719024181366, + "learning_rate": 3.178782489084362e-05, + "loss": 1.4891, + "step": 11216 + }, + { + "epoch": 0.6252159857310072, + "grad_norm": 0.5246587991714478, + "learning_rate": 3.177953263103394e-05, + "loss": 1.5387, + "step": 11217 + }, + { + "epoch": 0.6252717239841703, + "grad_norm": 0.6258318424224854, + "learning_rate": 3.177124094907127e-05, + "loss": 1.8772, + "step": 11218 + }, + { + "epoch": 0.6253274622373335, + "grad_norm": 0.5783872604370117, + "learning_rate": 3.176294984521852e-05, + "loss": 1.6118, + "step": 11219 + }, + { + "epoch": 0.6253832004904967, + "grad_norm": 0.5509163737297058, + "learning_rate": 3.175465931973871e-05, + "loss": 1.5575, + "step": 11220 + }, + { + "epoch": 0.6254389387436597, + "grad_norm": 0.5583782196044922, + "learning_rate": 3.174636937289471e-05, + "loss": 1.8273, + "step": 11221 + }, + { + "epoch": 0.6254946769968229, + "grad_norm": 0.5733713507652283, + "learning_rate": 3.173808000494944e-05, + "loss": 1.7487, + "step": 11222 + }, + { + "epoch": 0.6255504152499861, + "grad_norm": 0.5729860067367554, + "learning_rate": 3.1729791216165814e-05, + "loss": 1.7391, + "step": 11223 + }, + { + "epoch": 0.6256061535031492, + "grad_norm": 0.6327353715896606, + "learning_rate": 3.172150300680669e-05, + "loss": 1.9217, + "step": 11224 + }, + { + "epoch": 0.6256618917563124, + "grad_norm": 0.6311041116714478, + "learning_rate": 3.171321537713491e-05, + "loss": 1.9327, + "step": 11225 + }, + { + "epoch": 0.6257176300094756, + "grad_norm": 0.5261319279670715, + "learning_rate": 3.1704928327413307e-05, + "loss": 1.6966, + "step": 11226 + }, + { + "epoch": 0.6257733682626386, + "grad_norm": 0.583069384098053, + "learning_rate": 3.169664185790474e-05, + "loss": 1.664, + "step": 11227 + }, + { + "epoch": 0.6258291065158018, + "grad_norm": 0.5649895668029785, + "learning_rate": 3.1688355968871945e-05, + "loss": 1.5542, + "step": 11228 + }, + { + "epoch": 0.6258848447689649, + "grad_norm": 0.5580496191978455, + "learning_rate": 3.1680070660577746e-05, + "loss": 1.6896, + "step": 11229 + }, + { + "epoch": 0.6259405830221281, + "grad_norm": 0.6010125875473022, + "learning_rate": 3.1671785933284906e-05, + "loss": 1.6811, + "step": 11230 + }, + { + "epoch": 0.6259963212752913, + "grad_norm": 0.5710118412971497, + "learning_rate": 3.166350178725615e-05, + "loss": 1.7108, + "step": 11231 + }, + { + "epoch": 0.6260520595284543, + "grad_norm": 0.5758123397827148, + "learning_rate": 3.16552182227542e-05, + "loss": 1.6537, + "step": 11232 + }, + { + "epoch": 0.6261077977816175, + "grad_norm": 0.5612704753875732, + "learning_rate": 3.164693524004178e-05, + "loss": 1.5966, + "step": 11233 + }, + { + "epoch": 0.6261635360347807, + "grad_norm": 0.5761590600013733, + "learning_rate": 3.1638652839381544e-05, + "loss": 1.8528, + "step": 11234 + }, + { + "epoch": 0.6262192742879438, + "grad_norm": 0.5486272573471069, + "learning_rate": 3.1630371021036214e-05, + "loss": 1.7224, + "step": 11235 + }, + { + "epoch": 0.626275012541107, + "grad_norm": 0.5285595059394836, + "learning_rate": 3.16220897852684e-05, + "loss": 1.5045, + "step": 11236 + }, + { + "epoch": 0.6263307507942701, + "grad_norm": 0.533839225769043, + "learning_rate": 3.1613809132340756e-05, + "loss": 1.6119, + "step": 11237 + }, + { + "epoch": 0.6263864890474332, + "grad_norm": 0.6031431555747986, + "learning_rate": 3.1605529062515884e-05, + "loss": 1.7967, + "step": 11238 + }, + { + "epoch": 0.6264422273005964, + "grad_norm": 0.5195392370223999, + "learning_rate": 3.1597249576056384e-05, + "loss": 1.4543, + "step": 11239 + }, + { + "epoch": 0.6264979655537596, + "grad_norm": 0.5455713868141174, + "learning_rate": 3.1588970673224826e-05, + "loss": 1.6086, + "step": 11240 + }, + { + "epoch": 0.6265537038069227, + "grad_norm": 0.5660552382469177, + "learning_rate": 3.158069235428377e-05, + "loss": 1.8036, + "step": 11241 + }, + { + "epoch": 0.6266094420600858, + "grad_norm": 0.5812910199165344, + "learning_rate": 3.157241461949578e-05, + "loss": 1.5898, + "step": 11242 + }, + { + "epoch": 0.626665180313249, + "grad_norm": 0.556128978729248, + "learning_rate": 3.1564137469123336e-05, + "loss": 1.5166, + "step": 11243 + }, + { + "epoch": 0.6267209185664121, + "grad_norm": 0.5934070348739624, + "learning_rate": 3.155586090342898e-05, + "loss": 1.9267, + "step": 11244 + }, + { + "epoch": 0.6267766568195753, + "grad_norm": 0.5680559873580933, + "learning_rate": 3.1547584922675163e-05, + "loss": 1.7181, + "step": 11245 + }, + { + "epoch": 0.6268323950727385, + "grad_norm": 0.6229578256607056, + "learning_rate": 3.1539309527124394e-05, + "loss": 1.7861, + "step": 11246 + }, + { + "epoch": 0.6268881333259015, + "grad_norm": 0.549788236618042, + "learning_rate": 3.153103471703907e-05, + "loss": 1.7002, + "step": 11247 + }, + { + "epoch": 0.6269438715790647, + "grad_norm": 0.5750143527984619, + "learning_rate": 3.1522760492681647e-05, + "loss": 1.6348, + "step": 11248 + }, + { + "epoch": 0.6269996098322279, + "grad_norm": 0.5771127939224243, + "learning_rate": 3.151448685431454e-05, + "loss": 1.6681, + "step": 11249 + }, + { + "epoch": 0.627055348085391, + "grad_norm": 0.5842124223709106, + "learning_rate": 3.150621380220011e-05, + "loss": 1.6242, + "step": 11250 + }, + { + "epoch": 0.6271110863385542, + "grad_norm": 0.5503714084625244, + "learning_rate": 3.149794133660079e-05, + "loss": 1.5461, + "step": 11251 + }, + { + "epoch": 0.6271668245917172, + "grad_norm": 0.5330989956855774, + "learning_rate": 3.148966945777886e-05, + "loss": 1.6535, + "step": 11252 + }, + { + "epoch": 0.6272225628448804, + "grad_norm": 0.5222387909889221, + "learning_rate": 3.148139816599672e-05, + "loss": 1.5138, + "step": 11253 + }, + { + "epoch": 0.6272783010980436, + "grad_norm": 0.5381698608398438, + "learning_rate": 3.147312746151664e-05, + "loss": 1.546, + "step": 11254 + }, + { + "epoch": 0.6273340393512067, + "grad_norm": 0.6186235547065735, + "learning_rate": 3.1464857344600935e-05, + "loss": 1.6739, + "step": 11255 + }, + { + "epoch": 0.6273897776043699, + "grad_norm": 0.5606537461280823, + "learning_rate": 3.145658781551191e-05, + "loss": 1.5668, + "step": 11256 + }, + { + "epoch": 0.627445515857533, + "grad_norm": 0.5646564364433289, + "learning_rate": 3.144831887451178e-05, + "loss": 1.545, + "step": 11257 + }, + { + "epoch": 0.6275012541106961, + "grad_norm": 0.595557689666748, + "learning_rate": 3.144005052186283e-05, + "loss": 1.6925, + "step": 11258 + }, + { + "epoch": 0.6275569923638593, + "grad_norm": 0.5523800253868103, + "learning_rate": 3.1431782757827256e-05, + "loss": 1.5535, + "step": 11259 + }, + { + "epoch": 0.6276127306170225, + "grad_norm": 0.559516191482544, + "learning_rate": 3.142351558266726e-05, + "loss": 1.5023, + "step": 11260 + }, + { + "epoch": 0.6276684688701856, + "grad_norm": 0.5421967506408691, + "learning_rate": 3.1415248996645056e-05, + "loss": 1.4871, + "step": 11261 + }, + { + "epoch": 0.6277242071233488, + "grad_norm": 0.6028934717178345, + "learning_rate": 3.1406983000022795e-05, + "loss": 1.79, + "step": 11262 + }, + { + "epoch": 0.6277799453765119, + "grad_norm": 0.5425928235054016, + "learning_rate": 3.1398717593062635e-05, + "loss": 1.7054, + "step": 11263 + }, + { + "epoch": 0.627835683629675, + "grad_norm": 0.6035993099212646, + "learning_rate": 3.139045277602669e-05, + "loss": 1.7227, + "step": 11264 + }, + { + "epoch": 0.6278914218828382, + "grad_norm": 0.6094220876693726, + "learning_rate": 3.138218854917709e-05, + "loss": 1.7799, + "step": 11265 + }, + { + "epoch": 0.6279471601360014, + "grad_norm": 0.6169310808181763, + "learning_rate": 3.137392491277592e-05, + "loss": 1.8094, + "step": 11266 + }, + { + "epoch": 0.6280028983891645, + "grad_norm": 0.47607964277267456, + "learning_rate": 3.1365661867085236e-05, + "loss": 1.2856, + "step": 11267 + }, + { + "epoch": 0.6280586366423276, + "grad_norm": 0.6014509797096252, + "learning_rate": 3.135739941236714e-05, + "loss": 1.8226, + "step": 11268 + }, + { + "epoch": 0.6281143748954908, + "grad_norm": 0.5377684235572815, + "learning_rate": 3.134913754888362e-05, + "loss": 1.4785, + "step": 11269 + }, + { + "epoch": 0.6281701131486539, + "grad_norm": 0.5159873366355896, + "learning_rate": 3.134087627689672e-05, + "loss": 1.7147, + "step": 11270 + }, + { + "epoch": 0.6282258514018171, + "grad_norm": 0.523975133895874, + "learning_rate": 3.133261559666843e-05, + "loss": 1.6772, + "step": 11271 + }, + { + "epoch": 0.6282815896549803, + "grad_norm": 0.5608593821525574, + "learning_rate": 3.132435550846076e-05, + "loss": 1.5868, + "step": 11272 + }, + { + "epoch": 0.6283373279081433, + "grad_norm": 0.6289455890655518, + "learning_rate": 3.1316096012535626e-05, + "loss": 1.8946, + "step": 11273 + }, + { + "epoch": 0.6283930661613065, + "grad_norm": 0.5686862468719482, + "learning_rate": 3.130783710915498e-05, + "loss": 1.6757, + "step": 11274 + }, + { + "epoch": 0.6284488044144696, + "grad_norm": 0.55696702003479, + "learning_rate": 3.129957879858078e-05, + "loss": 1.4474, + "step": 11275 + }, + { + "epoch": 0.6285045426676328, + "grad_norm": 0.5241310596466064, + "learning_rate": 3.1291321081074884e-05, + "loss": 1.5844, + "step": 11276 + }, + { + "epoch": 0.628560280920796, + "grad_norm": 0.5064421892166138, + "learning_rate": 3.1283063956899244e-05, + "loss": 1.4043, + "step": 11277 + }, + { + "epoch": 0.628616019173959, + "grad_norm": 0.5911862850189209, + "learning_rate": 3.127480742631565e-05, + "loss": 1.7536, + "step": 11278 + }, + { + "epoch": 0.6286717574271222, + "grad_norm": 0.619687557220459, + "learning_rate": 3.126655148958602e-05, + "loss": 2.0976, + "step": 11279 + }, + { + "epoch": 0.6287274956802854, + "grad_norm": 0.573886513710022, + "learning_rate": 3.125829614697213e-05, + "loss": 1.6716, + "step": 11280 + }, + { + "epoch": 0.6287832339334485, + "grad_norm": 0.5493733882904053, + "learning_rate": 3.125004139873582e-05, + "loss": 1.7497, + "step": 11281 + }, + { + "epoch": 0.6288389721866117, + "grad_norm": 0.5901930332183838, + "learning_rate": 3.1241787245138884e-05, + "loss": 1.7312, + "step": 11282 + }, + { + "epoch": 0.6288947104397749, + "grad_norm": 0.5369457602500916, + "learning_rate": 3.123353368644307e-05, + "loss": 1.5331, + "step": 11283 + }, + { + "epoch": 0.6289504486929379, + "grad_norm": 0.5471475124359131, + "learning_rate": 3.1225280722910175e-05, + "loss": 1.6681, + "step": 11284 + }, + { + "epoch": 0.6290061869461011, + "grad_norm": 0.6188231706619263, + "learning_rate": 3.12170283548019e-05, + "loss": 1.7812, + "step": 11285 + }, + { + "epoch": 0.6290619251992643, + "grad_norm": 0.5695561170578003, + "learning_rate": 3.120877658237998e-05, + "loss": 1.7624, + "step": 11286 + }, + { + "epoch": 0.6291176634524274, + "grad_norm": 0.5495535135269165, + "learning_rate": 3.120052540590609e-05, + "loss": 1.5895, + "step": 11287 + }, + { + "epoch": 0.6291734017055906, + "grad_norm": 0.5273025035858154, + "learning_rate": 3.1192274825641935e-05, + "loss": 1.5756, + "step": 11288 + }, + { + "epoch": 0.6292291399587537, + "grad_norm": 0.6200233697891235, + "learning_rate": 3.118402484184917e-05, + "loss": 1.9689, + "step": 11289 + }, + { + "epoch": 0.6292848782119168, + "grad_norm": 0.527696967124939, + "learning_rate": 3.1175775454789424e-05, + "loss": 1.422, + "step": 11290 + }, + { + "epoch": 0.62934061646508, + "grad_norm": 0.5265816450119019, + "learning_rate": 3.1167526664724346e-05, + "loss": 1.5129, + "step": 11291 + }, + { + "epoch": 0.6293963547182432, + "grad_norm": 0.5591835379600525, + "learning_rate": 3.11592784719155e-05, + "loss": 1.5274, + "step": 11292 + }, + { + "epoch": 0.6294520929714063, + "grad_norm": 0.5992676615715027, + "learning_rate": 3.1151030876624486e-05, + "loss": 1.7378, + "step": 11293 + }, + { + "epoch": 0.6295078312245694, + "grad_norm": 0.5295802354812622, + "learning_rate": 3.1142783879112914e-05, + "loss": 1.6353, + "step": 11294 + }, + { + "epoch": 0.6295635694777326, + "grad_norm": 0.5344937443733215, + "learning_rate": 3.113453747964225e-05, + "loss": 1.6101, + "step": 11295 + }, + { + "epoch": 0.6296193077308957, + "grad_norm": 0.5788000822067261, + "learning_rate": 3.112629167847409e-05, + "loss": 1.6695, + "step": 11296 + }, + { + "epoch": 0.6296750459840589, + "grad_norm": 0.5490555763244629, + "learning_rate": 3.11180464758699e-05, + "loss": 1.4184, + "step": 11297 + }, + { + "epoch": 0.629730784237222, + "grad_norm": 0.5981817841529846, + "learning_rate": 3.1109801872091205e-05, + "loss": 1.7076, + "step": 11298 + }, + { + "epoch": 0.6297865224903851, + "grad_norm": 0.5663672685623169, + "learning_rate": 3.1101557867399444e-05, + "loss": 1.8046, + "step": 11299 + }, + { + "epoch": 0.6298422607435483, + "grad_norm": 0.5466318726539612, + "learning_rate": 3.109331446205608e-05, + "loss": 1.6712, + "step": 11300 + }, + { + "epoch": 0.6298979989967114, + "grad_norm": 0.5660746693611145, + "learning_rate": 3.108507165632256e-05, + "loss": 1.7935, + "step": 11301 + }, + { + "epoch": 0.6299537372498746, + "grad_norm": 0.539685070514679, + "learning_rate": 3.1076829450460266e-05, + "loss": 1.4931, + "step": 11302 + }, + { + "epoch": 0.6300094755030378, + "grad_norm": 0.561718761920929, + "learning_rate": 3.106858784473064e-05, + "loss": 1.5466, + "step": 11303 + }, + { + "epoch": 0.6300652137562008, + "grad_norm": 0.5737816095352173, + "learning_rate": 3.1060346839395e-05, + "loss": 1.5863, + "step": 11304 + }, + { + "epoch": 0.630120952009364, + "grad_norm": 0.5613131523132324, + "learning_rate": 3.105210643471476e-05, + "loss": 1.5272, + "step": 11305 + }, + { + "epoch": 0.6301766902625272, + "grad_norm": 0.571135938167572, + "learning_rate": 3.10438666309512e-05, + "loss": 1.6595, + "step": 11306 + }, + { + "epoch": 0.6302324285156903, + "grad_norm": 0.5821939706802368, + "learning_rate": 3.103562742836569e-05, + "loss": 1.7253, + "step": 11307 + }, + { + "epoch": 0.6302881667688535, + "grad_norm": 0.5542194843292236, + "learning_rate": 3.1027388827219506e-05, + "loss": 1.7749, + "step": 11308 + }, + { + "epoch": 0.6303439050220166, + "grad_norm": 0.5321241021156311, + "learning_rate": 3.1019150827773925e-05, + "loss": 1.6484, + "step": 11309 + }, + { + "epoch": 0.6303996432751797, + "grad_norm": 0.5949715971946716, + "learning_rate": 3.1010913430290224e-05, + "loss": 1.6021, + "step": 11310 + }, + { + "epoch": 0.6304553815283429, + "grad_norm": 0.550311267375946, + "learning_rate": 3.100267663502962e-05, + "loss": 1.3745, + "step": 11311 + }, + { + "epoch": 0.6305111197815061, + "grad_norm": 0.5823655724525452, + "learning_rate": 3.099444044225336e-05, + "loss": 1.6346, + "step": 11312 + }, + { + "epoch": 0.6305668580346692, + "grad_norm": 0.5521398186683655, + "learning_rate": 3.0986204852222626e-05, + "loss": 1.7061, + "step": 11313 + }, + { + "epoch": 0.6306225962878323, + "grad_norm": 0.5518872737884521, + "learning_rate": 3.097796986519863e-05, + "loss": 1.7118, + "step": 11314 + }, + { + "epoch": 0.6306783345409955, + "grad_norm": 0.6041616797447205, + "learning_rate": 3.096973548144252e-05, + "loss": 1.5219, + "step": 11315 + }, + { + "epoch": 0.6307340727941586, + "grad_norm": 0.632793128490448, + "learning_rate": 3.096150170121545e-05, + "loss": 1.8662, + "step": 11316 + }, + { + "epoch": 0.6307898110473218, + "grad_norm": 0.5445522665977478, + "learning_rate": 3.0953268524778544e-05, + "loss": 1.6059, + "step": 11317 + }, + { + "epoch": 0.630845549300485, + "grad_norm": 0.5500385165214539, + "learning_rate": 3.09450359523929e-05, + "loss": 1.7426, + "step": 11318 + }, + { + "epoch": 0.630901287553648, + "grad_norm": 0.5449601411819458, + "learning_rate": 3.093680398431962e-05, + "loss": 1.6988, + "step": 11319 + }, + { + "epoch": 0.6309570258068112, + "grad_norm": 0.5738338232040405, + "learning_rate": 3.0928572620819786e-05, + "loss": 1.6672, + "step": 11320 + }, + { + "epoch": 0.6310127640599743, + "grad_norm": 0.5188368558883667, + "learning_rate": 3.092034186215441e-05, + "loss": 1.3523, + "step": 11321 + }, + { + "epoch": 0.6310685023131375, + "grad_norm": 0.5617424845695496, + "learning_rate": 3.091211170858457e-05, + "loss": 1.6872, + "step": 11322 + }, + { + "epoch": 0.6311242405663007, + "grad_norm": 0.5671687722206116, + "learning_rate": 3.0903882160371246e-05, + "loss": 1.7043, + "step": 11323 + }, + { + "epoch": 0.6311799788194637, + "grad_norm": 0.5423902869224548, + "learning_rate": 3.089565321777546e-05, + "loss": 1.7498, + "step": 11324 + }, + { + "epoch": 0.6312357170726269, + "grad_norm": 0.5642695426940918, + "learning_rate": 3.088742488105814e-05, + "loss": 1.6361, + "step": 11325 + }, + { + "epoch": 0.6312914553257901, + "grad_norm": 0.5880917906761169, + "learning_rate": 3.0879197150480274e-05, + "loss": 1.707, + "step": 11326 + }, + { + "epoch": 0.6313471935789532, + "grad_norm": 0.6160138249397278, + "learning_rate": 3.0870970026302813e-05, + "loss": 1.8144, + "step": 11327 + }, + { + "epoch": 0.6314029318321164, + "grad_norm": 0.5911991000175476, + "learning_rate": 3.0862743508786626e-05, + "loss": 1.8036, + "step": 11328 + }, + { + "epoch": 0.6314586700852796, + "grad_norm": 0.5307081937789917, + "learning_rate": 3.0854517598192666e-05, + "loss": 1.666, + "step": 11329 + }, + { + "epoch": 0.6315144083384426, + "grad_norm": 0.5666818618774414, + "learning_rate": 3.084629229478175e-05, + "loss": 1.6637, + "step": 11330 + }, + { + "epoch": 0.6315701465916058, + "grad_norm": 0.5223289728164673, + "learning_rate": 3.083806759881479e-05, + "loss": 1.597, + "step": 11331 + }, + { + "epoch": 0.631625884844769, + "grad_norm": 0.5430996417999268, + "learning_rate": 3.0829843510552604e-05, + "loss": 1.6464, + "step": 11332 + }, + { + "epoch": 0.6316816230979321, + "grad_norm": 0.555894672870636, + "learning_rate": 3.0821620030256e-05, + "loss": 1.5438, + "step": 11333 + }, + { + "epoch": 0.6317373613510953, + "grad_norm": 0.5556870698928833, + "learning_rate": 3.0813397158185806e-05, + "loss": 1.7269, + "step": 11334 + }, + { + "epoch": 0.6317930996042584, + "grad_norm": 0.5671871900558472, + "learning_rate": 3.0805174894602775e-05, + "loss": 1.6349, + "step": 11335 + }, + { + "epoch": 0.6318488378574215, + "grad_norm": 0.5389631986618042, + "learning_rate": 3.0796953239767693e-05, + "loss": 1.6013, + "step": 11336 + }, + { + "epoch": 0.6319045761105847, + "grad_norm": 0.543947160243988, + "learning_rate": 3.078873219394127e-05, + "loss": 1.7542, + "step": 11337 + }, + { + "epoch": 0.6319603143637479, + "grad_norm": 0.587973415851593, + "learning_rate": 3.078051175738429e-05, + "loss": 1.8181, + "step": 11338 + }, + { + "epoch": 0.632016052616911, + "grad_norm": 0.5861559510231018, + "learning_rate": 3.0772291930357386e-05, + "loss": 1.6423, + "step": 11339 + }, + { + "epoch": 0.6320717908700741, + "grad_norm": 0.5492725968360901, + "learning_rate": 3.076407271312129e-05, + "loss": 1.5643, + "step": 11340 + }, + { + "epoch": 0.6321275291232373, + "grad_norm": 0.5426955819129944, + "learning_rate": 3.075585410593666e-05, + "loss": 1.609, + "step": 11341 + }, + { + "epoch": 0.6321832673764004, + "grad_norm": 0.5526770353317261, + "learning_rate": 3.074763610906413e-05, + "loss": 1.9504, + "step": 11342 + }, + { + "epoch": 0.6322390056295636, + "grad_norm": 0.6021462082862854, + "learning_rate": 3.073941872276434e-05, + "loss": 1.704, + "step": 11343 + }, + { + "epoch": 0.6322947438827267, + "grad_norm": 0.6182892322540283, + "learning_rate": 3.073120194729788e-05, + "loss": 1.8544, + "step": 11344 + }, + { + "epoch": 0.6323504821358898, + "grad_norm": 0.5577238202095032, + "learning_rate": 3.072298578292534e-05, + "loss": 1.6185, + "step": 11345 + }, + { + "epoch": 0.632406220389053, + "grad_norm": 0.5607499480247498, + "learning_rate": 3.071477022990734e-05, + "loss": 1.764, + "step": 11346 + }, + { + "epoch": 0.6324619586422161, + "grad_norm": 0.5537651777267456, + "learning_rate": 3.070655528850435e-05, + "loss": 1.6142, + "step": 11347 + }, + { + "epoch": 0.6325176968953793, + "grad_norm": 0.5657694935798645, + "learning_rate": 3.0698340958976943e-05, + "loss": 1.6187, + "step": 11348 + }, + { + "epoch": 0.6325734351485425, + "grad_norm": 0.551733672618866, + "learning_rate": 3.069012724158563e-05, + "loss": 1.5745, + "step": 11349 + }, + { + "epoch": 0.6326291734017055, + "grad_norm": 0.5896459221839905, + "learning_rate": 3.068191413659091e-05, + "loss": 1.9964, + "step": 11350 + }, + { + "epoch": 0.6326849116548687, + "grad_norm": 0.5522114634513855, + "learning_rate": 3.067370164425322e-05, + "loss": 1.5707, + "step": 11351 + }, + { + "epoch": 0.6327406499080319, + "grad_norm": 0.6097670793533325, + "learning_rate": 3.066548976483304e-05, + "loss": 1.8577, + "step": 11352 + }, + { + "epoch": 0.632796388161195, + "grad_norm": 0.6086198091506958, + "learning_rate": 3.06572784985908e-05, + "loss": 1.6431, + "step": 11353 + }, + { + "epoch": 0.6328521264143582, + "grad_norm": 0.5401943325996399, + "learning_rate": 3.0649067845786895e-05, + "loss": 1.5172, + "step": 11354 + }, + { + "epoch": 0.6329078646675214, + "grad_norm": 0.5912280678749084, + "learning_rate": 3.0640857806681764e-05, + "loss": 1.8141, + "step": 11355 + }, + { + "epoch": 0.6329636029206844, + "grad_norm": 0.577514111995697, + "learning_rate": 3.0632648381535725e-05, + "loss": 1.679, + "step": 11356 + }, + { + "epoch": 0.6330193411738476, + "grad_norm": 0.5429527163505554, + "learning_rate": 3.062443957060918e-05, + "loss": 1.5311, + "step": 11357 + }, + { + "epoch": 0.6330750794270108, + "grad_norm": 0.5673772096633911, + "learning_rate": 3.061623137416243e-05, + "loss": 1.6186, + "step": 11358 + }, + { + "epoch": 0.6331308176801739, + "grad_norm": 0.5661761164665222, + "learning_rate": 3.060802379245581e-05, + "loss": 1.7088, + "step": 11359 + }, + { + "epoch": 0.6331865559333371, + "grad_norm": 0.5400183796882629, + "learning_rate": 3.059981682574961e-05, + "loss": 1.5318, + "step": 11360 + }, + { + "epoch": 0.6332422941865002, + "grad_norm": 0.5342452526092529, + "learning_rate": 3.059161047430411e-05, + "loss": 1.5, + "step": 11361 + }, + { + "epoch": 0.6332980324396633, + "grad_norm": 0.5756200551986694, + "learning_rate": 3.058340473837958e-05, + "loss": 1.6703, + "step": 11362 + }, + { + "epoch": 0.6333537706928265, + "grad_norm": 0.5399934649467468, + "learning_rate": 3.057519961823622e-05, + "loss": 1.42, + "step": 11363 + }, + { + "epoch": 0.6334095089459897, + "grad_norm": 0.6465393304824829, + "learning_rate": 3.05669951141343e-05, + "loss": 1.8826, + "step": 11364 + }, + { + "epoch": 0.6334652471991528, + "grad_norm": 0.6080984473228455, + "learning_rate": 3.055879122633397e-05, + "loss": 1.7671, + "step": 11365 + }, + { + "epoch": 0.6335209854523159, + "grad_norm": 0.6007773280143738, + "learning_rate": 3.055058795509544e-05, + "loss": 1.7308, + "step": 11366 + }, + { + "epoch": 0.633576723705479, + "grad_norm": 0.6644430756568909, + "learning_rate": 3.0542385300678875e-05, + "loss": 1.8272, + "step": 11367 + }, + { + "epoch": 0.6336324619586422, + "grad_norm": 0.4975641369819641, + "learning_rate": 3.053418326334438e-05, + "loss": 1.3861, + "step": 11368 + }, + { + "epoch": 0.6336882002118054, + "grad_norm": 0.6592350006103516, + "learning_rate": 3.052598184335212e-05, + "loss": 2.0965, + "step": 11369 + }, + { + "epoch": 0.6337439384649685, + "grad_norm": 0.4995543360710144, + "learning_rate": 3.0517781040962163e-05, + "loss": 1.5337, + "step": 11370 + }, + { + "epoch": 0.6337996767181316, + "grad_norm": 0.548430860042572, + "learning_rate": 3.0509580856434595e-05, + "loss": 1.6827, + "step": 11371 + }, + { + "epoch": 0.6338554149712948, + "grad_norm": 0.5827524662017822, + "learning_rate": 3.0501381290029506e-05, + "loss": 1.6712, + "step": 11372 + }, + { + "epoch": 0.6339111532244579, + "grad_norm": 0.5682417750358582, + "learning_rate": 3.049318234200689e-05, + "loss": 1.7436, + "step": 11373 + }, + { + "epoch": 0.6339668914776211, + "grad_norm": 0.5213860273361206, + "learning_rate": 3.048498401262683e-05, + "loss": 1.5253, + "step": 11374 + }, + { + "epoch": 0.6340226297307843, + "grad_norm": 0.5296808481216431, + "learning_rate": 3.0476786302149274e-05, + "loss": 1.6458, + "step": 11375 + }, + { + "epoch": 0.6340783679839473, + "grad_norm": 0.5561826229095459, + "learning_rate": 3.0468589210834237e-05, + "loss": 1.8774, + "step": 11376 + }, + { + "epoch": 0.6341341062371105, + "grad_norm": 0.619141697883606, + "learning_rate": 3.046039273894167e-05, + "loss": 1.7102, + "step": 11377 + }, + { + "epoch": 0.6341898444902737, + "grad_norm": 0.5776034593582153, + "learning_rate": 3.045219688673152e-05, + "loss": 1.8709, + "step": 11378 + }, + { + "epoch": 0.6342455827434368, + "grad_norm": 0.5861794948577881, + "learning_rate": 3.044400165446372e-05, + "loss": 1.6028, + "step": 11379 + }, + { + "epoch": 0.6343013209966, + "grad_norm": 0.5809794068336487, + "learning_rate": 3.043580704239815e-05, + "loss": 1.6706, + "step": 11380 + }, + { + "epoch": 0.6343570592497632, + "grad_norm": 0.4941370189189911, + "learning_rate": 3.0427613050794745e-05, + "loss": 1.3136, + "step": 11381 + }, + { + "epoch": 0.6344127975029262, + "grad_norm": 0.5624459385871887, + "learning_rate": 3.0419419679913307e-05, + "loss": 1.7069, + "step": 11382 + }, + { + "epoch": 0.6344685357560894, + "grad_norm": 0.6081975698471069, + "learning_rate": 3.0411226930013735e-05, + "loss": 1.9564, + "step": 11383 + }, + { + "epoch": 0.6345242740092526, + "grad_norm": 0.5885438919067383, + "learning_rate": 3.0403034801355828e-05, + "loss": 1.655, + "step": 11384 + }, + { + "epoch": 0.6345800122624157, + "grad_norm": 0.5063520073890686, + "learning_rate": 3.0394843294199395e-05, + "loss": 1.4787, + "step": 11385 + }, + { + "epoch": 0.6346357505155789, + "grad_norm": 0.5593530535697937, + "learning_rate": 3.038665240880424e-05, + "loss": 1.6266, + "step": 11386 + }, + { + "epoch": 0.634691488768742, + "grad_norm": 0.5777801275253296, + "learning_rate": 3.0378462145430102e-05, + "loss": 1.8088, + "step": 11387 + }, + { + "epoch": 0.6347472270219051, + "grad_norm": 0.5216872692108154, + "learning_rate": 3.0370272504336762e-05, + "loss": 1.5096, + "step": 11388 + }, + { + "epoch": 0.6348029652750683, + "grad_norm": 0.5875978469848633, + "learning_rate": 3.0362083485783897e-05, + "loss": 1.9104, + "step": 11389 + }, + { + "epoch": 0.6348587035282314, + "grad_norm": 0.6326603889465332, + "learning_rate": 3.035389509003128e-05, + "loss": 1.8119, + "step": 11390 + }, + { + "epoch": 0.6349144417813946, + "grad_norm": 0.5737482309341431, + "learning_rate": 3.0345707317338545e-05, + "loss": 1.7255, + "step": 11391 + }, + { + "epoch": 0.6349701800345577, + "grad_norm": 0.5858984589576721, + "learning_rate": 3.0337520167965383e-05, + "loss": 1.6893, + "step": 11392 + }, + { + "epoch": 0.6350259182877208, + "grad_norm": 0.5381850600242615, + "learning_rate": 3.0329333642171454e-05, + "loss": 1.6162, + "step": 11393 + }, + { + "epoch": 0.635081656540884, + "grad_norm": 0.597037672996521, + "learning_rate": 3.032114774021636e-05, + "loss": 1.6565, + "step": 11394 + }, + { + "epoch": 0.6351373947940472, + "grad_norm": 0.5514940023422241, + "learning_rate": 3.031296246235974e-05, + "loss": 1.6259, + "step": 11395 + }, + { + "epoch": 0.6351931330472103, + "grad_norm": 0.5908069014549255, + "learning_rate": 3.0304777808861152e-05, + "loss": 1.8429, + "step": 11396 + }, + { + "epoch": 0.6352488713003734, + "grad_norm": 0.5402722954750061, + "learning_rate": 3.0296593779980177e-05, + "loss": 1.5404, + "step": 11397 + }, + { + "epoch": 0.6353046095535366, + "grad_norm": 0.6599807739257812, + "learning_rate": 3.028841037597639e-05, + "loss": 1.6664, + "step": 11398 + }, + { + "epoch": 0.6353603478066997, + "grad_norm": 0.5322889685630798, + "learning_rate": 3.0280227597109272e-05, + "loss": 1.4491, + "step": 11399 + }, + { + "epoch": 0.6354160860598629, + "grad_norm": 0.5631368160247803, + "learning_rate": 3.0272045443638386e-05, + "loss": 1.7172, + "step": 11400 + }, + { + "epoch": 0.6354718243130261, + "grad_norm": 0.5631436705589294, + "learning_rate": 3.0263863915823182e-05, + "loss": 1.6882, + "step": 11401 + }, + { + "epoch": 0.6355275625661891, + "grad_norm": 0.5329986810684204, + "learning_rate": 3.0255683013923154e-05, + "loss": 1.5914, + "step": 11402 + }, + { + "epoch": 0.6355833008193523, + "grad_norm": 0.5338492393493652, + "learning_rate": 3.0247502738197735e-05, + "loss": 1.5801, + "step": 11403 + }, + { + "epoch": 0.6356390390725155, + "grad_norm": 0.6237903237342834, + "learning_rate": 3.0239323088906357e-05, + "loss": 1.6125, + "step": 11404 + }, + { + "epoch": 0.6356947773256786, + "grad_norm": 0.5942304134368896, + "learning_rate": 3.0231144066308463e-05, + "loss": 1.8681, + "step": 11405 + }, + { + "epoch": 0.6357505155788418, + "grad_norm": 0.5691540241241455, + "learning_rate": 3.0222965670663394e-05, + "loss": 1.6304, + "step": 11406 + }, + { + "epoch": 0.635806253832005, + "grad_norm": 0.5843005776405334, + "learning_rate": 3.021478790223057e-05, + "loss": 1.6737, + "step": 11407 + }, + { + "epoch": 0.635861992085168, + "grad_norm": 0.5377256274223328, + "learning_rate": 3.0206610761269293e-05, + "loss": 1.3904, + "step": 11408 + }, + { + "epoch": 0.6359177303383312, + "grad_norm": 0.5730248093605042, + "learning_rate": 3.0198434248038933e-05, + "loss": 1.5715, + "step": 11409 + }, + { + "epoch": 0.6359734685914944, + "grad_norm": 0.5647515654563904, + "learning_rate": 3.0190258362798783e-05, + "loss": 1.5383, + "step": 11410 + }, + { + "epoch": 0.6360292068446575, + "grad_norm": 0.5440086722373962, + "learning_rate": 3.0182083105808134e-05, + "loss": 1.4719, + "step": 11411 + }, + { + "epoch": 0.6360849450978207, + "grad_norm": 0.5645092725753784, + "learning_rate": 3.017390847732628e-05, + "loss": 1.7294, + "step": 11412 + }, + { + "epoch": 0.6361406833509837, + "grad_norm": 0.5475958585739136, + "learning_rate": 3.016573447761244e-05, + "loss": 1.6529, + "step": 11413 + }, + { + "epoch": 0.6361964216041469, + "grad_norm": 0.5536510944366455, + "learning_rate": 3.015756110692587e-05, + "loss": 1.3404, + "step": 11414 + }, + { + "epoch": 0.6362521598573101, + "grad_norm": 0.6730042099952698, + "learning_rate": 3.0149388365525756e-05, + "loss": 1.726, + "step": 11415 + }, + { + "epoch": 0.6363078981104732, + "grad_norm": 0.5912729501724243, + "learning_rate": 3.0141216253671334e-05, + "loss": 1.7075, + "step": 11416 + }, + { + "epoch": 0.6363636363636364, + "grad_norm": 0.5724123120307922, + "learning_rate": 3.013304477162171e-05, + "loss": 1.4312, + "step": 11417 + }, + { + "epoch": 0.6364193746167995, + "grad_norm": 0.558233380317688, + "learning_rate": 3.0124873919636098e-05, + "loss": 1.6381, + "step": 11418 + }, + { + "epoch": 0.6364751128699626, + "grad_norm": 0.5994689464569092, + "learning_rate": 3.0116703697973604e-05, + "loss": 1.669, + "step": 11419 + }, + { + "epoch": 0.6365308511231258, + "grad_norm": 0.5841171741485596, + "learning_rate": 3.0108534106893336e-05, + "loss": 1.7477, + "step": 11420 + }, + { + "epoch": 0.636586589376289, + "grad_norm": 0.5982357263565063, + "learning_rate": 3.01003651466544e-05, + "loss": 1.6329, + "step": 11421 + }, + { + "epoch": 0.636642327629452, + "grad_norm": 0.5657229423522949, + "learning_rate": 3.009219681751585e-05, + "loss": 1.65, + "step": 11422 + }, + { + "epoch": 0.6366980658826152, + "grad_norm": 0.5730195045471191, + "learning_rate": 3.008402911973675e-05, + "loss": 1.6053, + "step": 11423 + }, + { + "epoch": 0.6367538041357784, + "grad_norm": 0.5259706974029541, + "learning_rate": 3.0075862053576115e-05, + "loss": 1.4455, + "step": 11424 + }, + { + "epoch": 0.6368095423889415, + "grad_norm": 0.5402256846427917, + "learning_rate": 3.006769561929298e-05, + "loss": 1.6209, + "step": 11425 + }, + { + "epoch": 0.6368652806421047, + "grad_norm": 0.5747603178024292, + "learning_rate": 3.005952981714633e-05, + "loss": 1.5629, + "step": 11426 + }, + { + "epoch": 0.6369210188952679, + "grad_norm": 0.5934039354324341, + "learning_rate": 3.0051364647395132e-05, + "loss": 1.6286, + "step": 11427 + }, + { + "epoch": 0.6369767571484309, + "grad_norm": 0.5477046370506287, + "learning_rate": 3.004320011029834e-05, + "loss": 1.3619, + "step": 11428 + }, + { + "epoch": 0.6370324954015941, + "grad_norm": 0.6017884016036987, + "learning_rate": 3.003503620611488e-05, + "loss": 1.8033, + "step": 11429 + }, + { + "epoch": 0.6370882336547573, + "grad_norm": 0.5695460438728333, + "learning_rate": 3.0026872935103658e-05, + "loss": 1.7917, + "step": 11430 + }, + { + "epoch": 0.6371439719079204, + "grad_norm": 0.5401207208633423, + "learning_rate": 3.00187102975236e-05, + "loss": 1.5718, + "step": 11431 + }, + { + "epoch": 0.6371997101610836, + "grad_norm": 0.5520731806755066, + "learning_rate": 3.0010548293633527e-05, + "loss": 1.6192, + "step": 11432 + }, + { + "epoch": 0.6372554484142468, + "grad_norm": 0.5545134544372559, + "learning_rate": 3.0002386923692344e-05, + "loss": 1.7251, + "step": 11433 + }, + { + "epoch": 0.6373111866674098, + "grad_norm": 0.5655757784843445, + "learning_rate": 2.9994226187958823e-05, + "loss": 1.6958, + "step": 11434 + }, + { + "epoch": 0.637366924920573, + "grad_norm": 0.7290306091308594, + "learning_rate": 2.9986066086691828e-05, + "loss": 1.688, + "step": 11435 + }, + { + "epoch": 0.6374226631737361, + "grad_norm": 0.5409923195838928, + "learning_rate": 2.997790662015012e-05, + "loss": 1.4879, + "step": 11436 + }, + { + "epoch": 0.6374784014268993, + "grad_norm": 0.5542522668838501, + "learning_rate": 2.9969747788592472e-05, + "loss": 1.7174, + "step": 11437 + }, + { + "epoch": 0.6375341396800625, + "grad_norm": 0.5595596432685852, + "learning_rate": 2.996158959227765e-05, + "loss": 1.6473, + "step": 11438 + }, + { + "epoch": 0.6375898779332255, + "grad_norm": 0.5823233127593994, + "learning_rate": 2.995343203146436e-05, + "loss": 1.8093, + "step": 11439 + }, + { + "epoch": 0.6376456161863887, + "grad_norm": 0.5893445014953613, + "learning_rate": 2.994527510641134e-05, + "loss": 1.5227, + "step": 11440 + }, + { + "epoch": 0.6377013544395519, + "grad_norm": 0.5489947199821472, + "learning_rate": 2.993711881737725e-05, + "loss": 1.5738, + "step": 11441 + }, + { + "epoch": 0.637757092692715, + "grad_norm": 0.5400989055633545, + "learning_rate": 2.9928963164620806e-05, + "loss": 1.6712, + "step": 11442 + }, + { + "epoch": 0.6378128309458782, + "grad_norm": 0.5572450160980225, + "learning_rate": 2.992080814840059e-05, + "loss": 1.3923, + "step": 11443 + }, + { + "epoch": 0.6378685691990413, + "grad_norm": 0.6122034192085266, + "learning_rate": 2.991265376897529e-05, + "loss": 1.7614, + "step": 11444 + }, + { + "epoch": 0.6379243074522044, + "grad_norm": 0.5644296407699585, + "learning_rate": 2.99045000266035e-05, + "loss": 1.6199, + "step": 11445 + }, + { + "epoch": 0.6379800457053676, + "grad_norm": 0.5942640900611877, + "learning_rate": 2.9896346921543796e-05, + "loss": 1.9717, + "step": 11446 + }, + { + "epoch": 0.6380357839585308, + "grad_norm": 0.6068518757820129, + "learning_rate": 2.9888194454054762e-05, + "loss": 1.7399, + "step": 11447 + }, + { + "epoch": 0.6380915222116939, + "grad_norm": 0.6198694705963135, + "learning_rate": 2.988004262439493e-05, + "loss": 1.7467, + "step": 11448 + }, + { + "epoch": 0.638147260464857, + "grad_norm": 0.6115100383758545, + "learning_rate": 2.9871891432822858e-05, + "loss": 1.8546, + "step": 11449 + }, + { + "epoch": 0.6382029987180202, + "grad_norm": 0.540266752243042, + "learning_rate": 2.9863740879597006e-05, + "loss": 1.5476, + "step": 11450 + }, + { + "epoch": 0.6382587369711833, + "grad_norm": 0.5491194725036621, + "learning_rate": 2.98555909649759e-05, + "loss": 1.5871, + "step": 11451 + }, + { + "epoch": 0.6383144752243465, + "grad_norm": 0.5302134156227112, + "learning_rate": 2.9847441689218014e-05, + "loss": 1.592, + "step": 11452 + }, + { + "epoch": 0.6383702134775097, + "grad_norm": 0.5229141116142273, + "learning_rate": 2.9839293052581767e-05, + "loss": 1.4722, + "step": 11453 + }, + { + "epoch": 0.6384259517306727, + "grad_norm": 0.5786263942718506, + "learning_rate": 2.983114505532561e-05, + "loss": 1.5706, + "step": 11454 + }, + { + "epoch": 0.6384816899838359, + "grad_norm": 0.5235024690628052, + "learning_rate": 2.9822997697707927e-05, + "loss": 1.6502, + "step": 11455 + }, + { + "epoch": 0.6385374282369991, + "grad_norm": 0.5675355792045593, + "learning_rate": 2.981485097998711e-05, + "loss": 1.7896, + "step": 11456 + }, + { + "epoch": 0.6385931664901622, + "grad_norm": 0.5436956882476807, + "learning_rate": 2.9806704902421555e-05, + "loss": 1.5343, + "step": 11457 + }, + { + "epoch": 0.6386489047433254, + "grad_norm": 0.5603477358818054, + "learning_rate": 2.9798559465269564e-05, + "loss": 1.6853, + "step": 11458 + }, + { + "epoch": 0.6387046429964884, + "grad_norm": 0.5103815197944641, + "learning_rate": 2.9790414668789514e-05, + "loss": 1.3626, + "step": 11459 + }, + { + "epoch": 0.6387603812496516, + "grad_norm": 0.6653990149497986, + "learning_rate": 2.978227051323965e-05, + "loss": 1.7424, + "step": 11460 + }, + { + "epoch": 0.6388161195028148, + "grad_norm": 0.5415511131286621, + "learning_rate": 2.9774126998878305e-05, + "loss": 1.586, + "step": 11461 + }, + { + "epoch": 0.6388718577559779, + "grad_norm": 0.5623989701271057, + "learning_rate": 2.976598412596372e-05, + "loss": 1.7159, + "step": 11462 + }, + { + "epoch": 0.6389275960091411, + "grad_norm": 0.47628477215766907, + "learning_rate": 2.975784189475414e-05, + "loss": 1.1537, + "step": 11463 + }, + { + "epoch": 0.6389833342623042, + "grad_norm": 0.6199833750724792, + "learning_rate": 2.974970030550781e-05, + "loss": 1.8564, + "step": 11464 + }, + { + "epoch": 0.6390390725154673, + "grad_norm": 0.5712960362434387, + "learning_rate": 2.9741559358482908e-05, + "loss": 1.474, + "step": 11465 + }, + { + "epoch": 0.6390948107686305, + "grad_norm": 0.5492451190948486, + "learning_rate": 2.973341905393764e-05, + "loss": 1.6722, + "step": 11466 + }, + { + "epoch": 0.6391505490217937, + "grad_norm": 0.5948915481567383, + "learning_rate": 2.972527939213013e-05, + "loss": 1.499, + "step": 11467 + }, + { + "epoch": 0.6392062872749568, + "grad_norm": 0.5698557496070862, + "learning_rate": 2.9717140373318587e-05, + "loss": 1.7276, + "step": 11468 + }, + { + "epoch": 0.63926202552812, + "grad_norm": 0.5909801721572876, + "learning_rate": 2.9709001997761053e-05, + "loss": 1.7654, + "step": 11469 + }, + { + "epoch": 0.6393177637812831, + "grad_norm": 0.5476438999176025, + "learning_rate": 2.970086426571569e-05, + "loss": 1.634, + "step": 11470 + }, + { + "epoch": 0.6393735020344462, + "grad_norm": 0.5444782972335815, + "learning_rate": 2.969272717744057e-05, + "loss": 1.6631, + "step": 11471 + }, + { + "epoch": 0.6394292402876094, + "grad_norm": 0.5920711159706116, + "learning_rate": 2.9684590733193728e-05, + "loss": 1.9441, + "step": 11472 + }, + { + "epoch": 0.6394849785407726, + "grad_norm": 0.5431917309761047, + "learning_rate": 2.9676454933233238e-05, + "loss": 1.5584, + "step": 11473 + }, + { + "epoch": 0.6395407167939356, + "grad_norm": 0.5913118720054626, + "learning_rate": 2.9668319777817088e-05, + "loss": 1.6103, + "step": 11474 + }, + { + "epoch": 0.6395964550470988, + "grad_norm": 0.5852524042129517, + "learning_rate": 2.966018526720331e-05, + "loss": 1.7739, + "step": 11475 + }, + { + "epoch": 0.639652193300262, + "grad_norm": 0.5839758515357971, + "learning_rate": 2.965205140164984e-05, + "loss": 1.8033, + "step": 11476 + }, + { + "epoch": 0.6397079315534251, + "grad_norm": 0.5499829649925232, + "learning_rate": 2.9643918181414676e-05, + "loss": 1.5886, + "step": 11477 + }, + { + "epoch": 0.6397636698065883, + "grad_norm": 0.5322203636169434, + "learning_rate": 2.963578560675575e-05, + "loss": 1.3883, + "step": 11478 + }, + { + "epoch": 0.6398194080597515, + "grad_norm": 0.5608605146408081, + "learning_rate": 2.962765367793096e-05, + "loss": 1.764, + "step": 11479 + }, + { + "epoch": 0.6398751463129145, + "grad_norm": 0.4977636933326721, + "learning_rate": 2.9619522395198228e-05, + "loss": 1.2644, + "step": 11480 + }, + { + "epoch": 0.6399308845660777, + "grad_norm": 0.580485999584198, + "learning_rate": 2.9611391758815416e-05, + "loss": 1.6284, + "step": 11481 + }, + { + "epoch": 0.6399866228192408, + "grad_norm": 0.5771294832229614, + "learning_rate": 2.9603261769040368e-05, + "loss": 1.5244, + "step": 11482 + }, + { + "epoch": 0.640042361072404, + "grad_norm": 0.5638933777809143, + "learning_rate": 2.9595132426130968e-05, + "loss": 1.662, + "step": 11483 + }, + { + "epoch": 0.6400980993255672, + "grad_norm": 0.590519368648529, + "learning_rate": 2.9587003730344965e-05, + "loss": 1.7329, + "step": 11484 + }, + { + "epoch": 0.6401538375787302, + "grad_norm": 0.5339858531951904, + "learning_rate": 2.9578875681940223e-05, + "loss": 1.5648, + "step": 11485 + }, + { + "epoch": 0.6402095758318934, + "grad_norm": 0.5530378818511963, + "learning_rate": 2.9570748281174443e-05, + "loss": 1.639, + "step": 11486 + }, + { + "epoch": 0.6402653140850566, + "grad_norm": 0.5428372621536255, + "learning_rate": 2.9562621528305445e-05, + "loss": 1.5573, + "step": 11487 + }, + { + "epoch": 0.6403210523382197, + "grad_norm": 0.5383026003837585, + "learning_rate": 2.9554495423590924e-05, + "loss": 1.6015, + "step": 11488 + }, + { + "epoch": 0.6403767905913829, + "grad_norm": 0.5547573566436768, + "learning_rate": 2.9546369967288594e-05, + "loss": 1.6447, + "step": 11489 + }, + { + "epoch": 0.640432528844546, + "grad_norm": 0.5519043207168579, + "learning_rate": 2.9538245159656174e-05, + "loss": 1.5088, + "step": 11490 + }, + { + "epoch": 0.6404882670977091, + "grad_norm": 0.5677748322486877, + "learning_rate": 2.9530121000951294e-05, + "loss": 1.6811, + "step": 11491 + }, + { + "epoch": 0.6405440053508723, + "grad_norm": 0.5701718926429749, + "learning_rate": 2.952199749143165e-05, + "loss": 1.5924, + "step": 11492 + }, + { + "epoch": 0.6405997436040355, + "grad_norm": 0.5985507369041443, + "learning_rate": 2.9513874631354833e-05, + "loss": 1.5902, + "step": 11493 + }, + { + "epoch": 0.6406554818571986, + "grad_norm": 0.5509946346282959, + "learning_rate": 2.9505752420978495e-05, + "loss": 1.4045, + "step": 11494 + }, + { + "epoch": 0.6407112201103617, + "grad_norm": 0.5370048880577087, + "learning_rate": 2.9497630860560178e-05, + "loss": 1.4327, + "step": 11495 + }, + { + "epoch": 0.6407669583635249, + "grad_norm": 0.5271995663642883, + "learning_rate": 2.9489509950357476e-05, + "loss": 1.5244, + "step": 11496 + }, + { + "epoch": 0.640822696616688, + "grad_norm": 0.5988388061523438, + "learning_rate": 2.9481389690627943e-05, + "loss": 1.7219, + "step": 11497 + }, + { + "epoch": 0.6408784348698512, + "grad_norm": 0.5371741652488708, + "learning_rate": 2.947327008162909e-05, + "loss": 1.5458, + "step": 11498 + }, + { + "epoch": 0.6409341731230144, + "grad_norm": 0.6004182696342468, + "learning_rate": 2.946515112361844e-05, + "loss": 1.8704, + "step": 11499 + }, + { + "epoch": 0.6409899113761774, + "grad_norm": 0.5374881029129028, + "learning_rate": 2.945703281685346e-05, + "loss": 1.6822, + "step": 11500 + }, + { + "epoch": 0.6410456496293406, + "grad_norm": 0.571029007434845, + "learning_rate": 2.944891516159163e-05, + "loss": 1.7695, + "step": 11501 + }, + { + "epoch": 0.6411013878825038, + "grad_norm": 0.5365399122238159, + "learning_rate": 2.9440798158090377e-05, + "loss": 1.4151, + "step": 11502 + }, + { + "epoch": 0.6411571261356669, + "grad_norm": 0.574303388595581, + "learning_rate": 2.9432681806607143e-05, + "loss": 1.7826, + "step": 11503 + }, + { + "epoch": 0.6412128643888301, + "grad_norm": 0.571097195148468, + "learning_rate": 2.9424566107399342e-05, + "loss": 1.6817, + "step": 11504 + }, + { + "epoch": 0.6412686026419931, + "grad_norm": 0.5556220412254333, + "learning_rate": 2.9416451060724325e-05, + "loss": 1.7257, + "step": 11505 + }, + { + "epoch": 0.6413243408951563, + "grad_norm": 0.5598143935203552, + "learning_rate": 2.9408336666839488e-05, + "loss": 1.5757, + "step": 11506 + }, + { + "epoch": 0.6413800791483195, + "grad_norm": 0.6592652201652527, + "learning_rate": 2.940022292600213e-05, + "loss": 1.8345, + "step": 11507 + }, + { + "epoch": 0.6414358174014826, + "grad_norm": 0.5990983843803406, + "learning_rate": 2.9392109838469594e-05, + "loss": 1.7728, + "step": 11508 + }, + { + "epoch": 0.6414915556546458, + "grad_norm": 0.5551927089691162, + "learning_rate": 2.938399740449922e-05, + "loss": 1.4375, + "step": 11509 + }, + { + "epoch": 0.641547293907809, + "grad_norm": 0.5568867325782776, + "learning_rate": 2.937588562434821e-05, + "loss": 1.6464, + "step": 11510 + }, + { + "epoch": 0.641603032160972, + "grad_norm": 0.569223940372467, + "learning_rate": 2.936777449827388e-05, + "loss": 1.8679, + "step": 11511 + }, + { + "epoch": 0.6416587704141352, + "grad_norm": 0.6105400323867798, + "learning_rate": 2.935966402653344e-05, + "loss": 1.8918, + "step": 11512 + }, + { + "epoch": 0.6417145086672984, + "grad_norm": 0.5622360706329346, + "learning_rate": 2.9351554209384125e-05, + "loss": 1.6716, + "step": 11513 + }, + { + "epoch": 0.6417702469204615, + "grad_norm": 0.5488218069076538, + "learning_rate": 2.9343445047083117e-05, + "loss": 1.7824, + "step": 11514 + }, + { + "epoch": 0.6418259851736247, + "grad_norm": 0.547471284866333, + "learning_rate": 2.933533653988759e-05, + "loss": 1.557, + "step": 11515 + }, + { + "epoch": 0.6418817234267878, + "grad_norm": 0.5255625247955322, + "learning_rate": 2.932722868805472e-05, + "loss": 1.498, + "step": 11516 + }, + { + "epoch": 0.6419374616799509, + "grad_norm": 0.5560644268989563, + "learning_rate": 2.93191214918416e-05, + "loss": 1.628, + "step": 11517 + }, + { + "epoch": 0.6419931999331141, + "grad_norm": 0.5956060886383057, + "learning_rate": 2.93110149515054e-05, + "loss": 1.5985, + "step": 11518 + }, + { + "epoch": 0.6420489381862773, + "grad_norm": 0.5386204719543457, + "learning_rate": 2.9302909067303152e-05, + "loss": 1.5679, + "step": 11519 + }, + { + "epoch": 0.6421046764394404, + "grad_norm": 0.5531619787216187, + "learning_rate": 2.929480383949198e-05, + "loss": 1.8117, + "step": 11520 + }, + { + "epoch": 0.6421604146926035, + "grad_norm": 0.5731996297836304, + "learning_rate": 2.9286699268328887e-05, + "loss": 1.6363, + "step": 11521 + }, + { + "epoch": 0.6422161529457667, + "grad_norm": 0.5966832041740417, + "learning_rate": 2.9278595354070937e-05, + "loss": 1.7658, + "step": 11522 + }, + { + "epoch": 0.6422718911989298, + "grad_norm": 0.5194985866546631, + "learning_rate": 2.9270492096975134e-05, + "loss": 1.4656, + "step": 11523 + }, + { + "epoch": 0.642327629452093, + "grad_norm": 0.5613593459129333, + "learning_rate": 2.9262389497298454e-05, + "loss": 1.5639, + "step": 11524 + }, + { + "epoch": 0.6423833677052562, + "grad_norm": 0.6349266171455383, + "learning_rate": 2.9254287555297876e-05, + "loss": 1.9102, + "step": 11525 + }, + { + "epoch": 0.6424391059584192, + "grad_norm": 0.523147702217102, + "learning_rate": 2.9246186271230337e-05, + "loss": 1.72, + "step": 11526 + }, + { + "epoch": 0.6424948442115824, + "grad_norm": 0.65010005235672, + "learning_rate": 2.9238085645352776e-05, + "loss": 1.729, + "step": 11527 + }, + { + "epoch": 0.6425505824647455, + "grad_norm": 0.5469678640365601, + "learning_rate": 2.9229985677922062e-05, + "loss": 1.6568, + "step": 11528 + }, + { + "epoch": 0.6426063207179087, + "grad_norm": 0.5617852210998535, + "learning_rate": 2.9221886369195116e-05, + "loss": 1.4062, + "step": 11529 + }, + { + "epoch": 0.6426620589710719, + "grad_norm": 0.500699520111084, + "learning_rate": 2.9213787719428805e-05, + "loss": 1.5071, + "step": 11530 + }, + { + "epoch": 0.6427177972242349, + "grad_norm": 0.5502698421478271, + "learning_rate": 2.9205689728879936e-05, + "loss": 1.572, + "step": 11531 + }, + { + "epoch": 0.6427735354773981, + "grad_norm": 0.6290270090103149, + "learning_rate": 2.919759239780537e-05, + "loss": 1.3922, + "step": 11532 + }, + { + "epoch": 0.6428292737305613, + "grad_norm": 0.5990520715713501, + "learning_rate": 2.9189495726461868e-05, + "loss": 1.6264, + "step": 11533 + }, + { + "epoch": 0.6428850119837244, + "grad_norm": 0.5172905921936035, + "learning_rate": 2.918139971510624e-05, + "loss": 1.4878, + "step": 11534 + }, + { + "epoch": 0.6429407502368876, + "grad_norm": 0.5496329069137573, + "learning_rate": 2.917330436399522e-05, + "loss": 1.6821, + "step": 11535 + }, + { + "epoch": 0.6429964884900508, + "grad_norm": 0.5884643793106079, + "learning_rate": 2.9165209673385563e-05, + "loss": 1.8271, + "step": 11536 + }, + { + "epoch": 0.6430522267432138, + "grad_norm": 0.5393579602241516, + "learning_rate": 2.9157115643533993e-05, + "loss": 1.4832, + "step": 11537 + }, + { + "epoch": 0.643107964996377, + "grad_norm": 0.5137203335762024, + "learning_rate": 2.914902227469718e-05, + "loss": 1.5079, + "step": 11538 + }, + { + "epoch": 0.6431637032495402, + "grad_norm": 0.5596064329147339, + "learning_rate": 2.9140929567131815e-05, + "loss": 1.5945, + "step": 11539 + }, + { + "epoch": 0.6432194415027033, + "grad_norm": 0.5552858114242554, + "learning_rate": 2.9132837521094535e-05, + "loss": 1.598, + "step": 11540 + }, + { + "epoch": 0.6432751797558665, + "grad_norm": 0.5611785650253296, + "learning_rate": 2.9124746136841996e-05, + "loss": 1.6551, + "step": 11541 + }, + { + "epoch": 0.6433309180090296, + "grad_norm": 0.601570188999176, + "learning_rate": 2.911665541463079e-05, + "loss": 1.5584, + "step": 11542 + }, + { + "epoch": 0.6433866562621927, + "grad_norm": 0.5507310032844543, + "learning_rate": 2.9108565354717522e-05, + "loss": 1.7545, + "step": 11543 + }, + { + "epoch": 0.6434423945153559, + "grad_norm": 0.5532577633857727, + "learning_rate": 2.910047595735877e-05, + "loss": 1.5668, + "step": 11544 + }, + { + "epoch": 0.6434981327685191, + "grad_norm": 0.5722034573554993, + "learning_rate": 2.9092387222811045e-05, + "loss": 1.7969, + "step": 11545 + }, + { + "epoch": 0.6435538710216822, + "grad_norm": 0.5793879628181458, + "learning_rate": 2.9084299151330906e-05, + "loss": 1.7327, + "step": 11546 + }, + { + "epoch": 0.6436096092748453, + "grad_norm": 0.6248428821563721, + "learning_rate": 2.9076211743174854e-05, + "loss": 1.7837, + "step": 11547 + }, + { + "epoch": 0.6436653475280085, + "grad_norm": 0.5645349621772766, + "learning_rate": 2.9068124998599362e-05, + "loss": 1.6744, + "step": 11548 + }, + { + "epoch": 0.6437210857811716, + "grad_norm": 0.5263849496841431, + "learning_rate": 2.9060038917860928e-05, + "loss": 1.6584, + "step": 11549 + }, + { + "epoch": 0.6437768240343348, + "grad_norm": 0.5999687910079956, + "learning_rate": 2.9051953501215928e-05, + "loss": 1.6557, + "step": 11550 + }, + { + "epoch": 0.6438325622874979, + "grad_norm": 0.5746318101882935, + "learning_rate": 2.9043868748920868e-05, + "loss": 1.7061, + "step": 11551 + }, + { + "epoch": 0.643888300540661, + "grad_norm": 0.553269624710083, + "learning_rate": 2.903578466123209e-05, + "loss": 1.7217, + "step": 11552 + }, + { + "epoch": 0.6439440387938242, + "grad_norm": 0.5399090647697449, + "learning_rate": 2.902770123840599e-05, + "loss": 1.6482, + "step": 11553 + }, + { + "epoch": 0.6439997770469873, + "grad_norm": 0.5580053925514221, + "learning_rate": 2.901961848069894e-05, + "loss": 1.5762, + "step": 11554 + }, + { + "epoch": 0.6440555153001505, + "grad_norm": 0.5592229962348938, + "learning_rate": 2.9011536388367256e-05, + "loss": 1.5193, + "step": 11555 + }, + { + "epoch": 0.6441112535533137, + "grad_norm": 0.5572046041488647, + "learning_rate": 2.900345496166729e-05, + "loss": 1.6022, + "step": 11556 + }, + { + "epoch": 0.6441669918064767, + "grad_norm": 0.6023865938186646, + "learning_rate": 2.8995374200855275e-05, + "loss": 1.748, + "step": 11557 + }, + { + "epoch": 0.6442227300596399, + "grad_norm": 0.5624969005584717, + "learning_rate": 2.8987294106187567e-05, + "loss": 1.4763, + "step": 11558 + }, + { + "epoch": 0.6442784683128031, + "grad_norm": 0.55375736951828, + "learning_rate": 2.8979214677920353e-05, + "loss": 1.6101, + "step": 11559 + }, + { + "epoch": 0.6443342065659662, + "grad_norm": 0.5634573101997375, + "learning_rate": 2.8971135916309895e-05, + "loss": 1.7446, + "step": 11560 + }, + { + "epoch": 0.6443899448191294, + "grad_norm": 0.6170838475227356, + "learning_rate": 2.8963057821612394e-05, + "loss": 1.8012, + "step": 11561 + }, + { + "epoch": 0.6444456830722926, + "grad_norm": 0.5855227112770081, + "learning_rate": 2.8954980394084046e-05, + "loss": 1.4746, + "step": 11562 + }, + { + "epoch": 0.6445014213254556, + "grad_norm": 0.5456474423408508, + "learning_rate": 2.8946903633981038e-05, + "loss": 1.5389, + "step": 11563 + }, + { + "epoch": 0.6445571595786188, + "grad_norm": 0.6640143394470215, + "learning_rate": 2.8938827541559482e-05, + "loss": 1.9017, + "step": 11564 + }, + { + "epoch": 0.644612897831782, + "grad_norm": 0.5690329074859619, + "learning_rate": 2.893075211707552e-05, + "loss": 1.668, + "step": 11565 + }, + { + "epoch": 0.6446686360849451, + "grad_norm": 0.6500377655029297, + "learning_rate": 2.8922677360785255e-05, + "loss": 1.9912, + "step": 11566 + }, + { + "epoch": 0.6447243743381083, + "grad_norm": 0.532332181930542, + "learning_rate": 2.8914603272944784e-05, + "loss": 1.4963, + "step": 11567 + }, + { + "epoch": 0.6447801125912714, + "grad_norm": 0.5918958187103271, + "learning_rate": 2.890652985381015e-05, + "loss": 1.6432, + "step": 11568 + }, + { + "epoch": 0.6448358508444345, + "grad_norm": 0.6097450256347656, + "learning_rate": 2.8898457103637412e-05, + "loss": 1.65, + "step": 11569 + }, + { + "epoch": 0.6448915890975977, + "grad_norm": 0.5675815939903259, + "learning_rate": 2.8890385022682603e-05, + "loss": 1.6351, + "step": 11570 + }, + { + "epoch": 0.6449473273507609, + "grad_norm": 0.6037099957466125, + "learning_rate": 2.8882313611201684e-05, + "loss": 2.0205, + "step": 11571 + }, + { + "epoch": 0.645003065603924, + "grad_norm": 0.6402329206466675, + "learning_rate": 2.887424286945065e-05, + "loss": 1.8547, + "step": 11572 + }, + { + "epoch": 0.6450588038570871, + "grad_norm": 0.5856971740722656, + "learning_rate": 2.8866172797685463e-05, + "loss": 1.733, + "step": 11573 + }, + { + "epoch": 0.6451145421102502, + "grad_norm": 0.613845705986023, + "learning_rate": 2.8858103396162055e-05, + "loss": 1.7774, + "step": 11574 + }, + { + "epoch": 0.6451702803634134, + "grad_norm": 0.5045792460441589, + "learning_rate": 2.8850034665136345e-05, + "loss": 1.4179, + "step": 11575 + }, + { + "epoch": 0.6452260186165766, + "grad_norm": 0.589607834815979, + "learning_rate": 2.8841966604864218e-05, + "loss": 1.7132, + "step": 11576 + }, + { + "epoch": 0.6452817568697397, + "grad_norm": 0.5298007726669312, + "learning_rate": 2.8833899215601567e-05, + "loss": 1.6576, + "step": 11577 + }, + { + "epoch": 0.6453374951229028, + "grad_norm": 0.5419639348983765, + "learning_rate": 2.8825832497604215e-05, + "loss": 1.5273, + "step": 11578 + }, + { + "epoch": 0.645393233376066, + "grad_norm": 0.503090500831604, + "learning_rate": 2.8817766451127997e-05, + "loss": 1.3098, + "step": 11579 + }, + { + "epoch": 0.6454489716292291, + "grad_norm": 0.5862603187561035, + "learning_rate": 2.880970107642873e-05, + "loss": 1.7311, + "step": 11580 + }, + { + "epoch": 0.6455047098823923, + "grad_norm": 0.5508575439453125, + "learning_rate": 2.8801636373762193e-05, + "loss": 1.5223, + "step": 11581 + }, + { + "epoch": 0.6455604481355555, + "grad_norm": 0.5836048126220703, + "learning_rate": 2.879357234338418e-05, + "loss": 1.7109, + "step": 11582 + }, + { + "epoch": 0.6456161863887185, + "grad_norm": 0.665833592414856, + "learning_rate": 2.878550898555036e-05, + "loss": 1.811, + "step": 11583 + }, + { + "epoch": 0.6456719246418817, + "grad_norm": 0.5850480794906616, + "learning_rate": 2.8777446300516552e-05, + "loss": 1.6823, + "step": 11584 + }, + { + "epoch": 0.6457276628950449, + "grad_norm": 0.5332453846931458, + "learning_rate": 2.876938428853839e-05, + "loss": 1.576, + "step": 11585 + }, + { + "epoch": 0.645783401148208, + "grad_norm": 0.5579224228858948, + "learning_rate": 2.8761322949871582e-05, + "loss": 1.6211, + "step": 11586 + }, + { + "epoch": 0.6458391394013712, + "grad_norm": 0.6172266602516174, + "learning_rate": 2.8753262284771776e-05, + "loss": 1.8955, + "step": 11587 + }, + { + "epoch": 0.6458948776545343, + "grad_norm": 0.5603342652320862, + "learning_rate": 2.874520229349461e-05, + "loss": 1.6045, + "step": 11588 + }, + { + "epoch": 0.6459506159076974, + "grad_norm": 0.596922755241394, + "learning_rate": 2.8737142976295723e-05, + "loss": 1.3921, + "step": 11589 + }, + { + "epoch": 0.6460063541608606, + "grad_norm": 0.5799021124839783, + "learning_rate": 2.8729084333430673e-05, + "loss": 1.6893, + "step": 11590 + }, + { + "epoch": 0.6460620924140238, + "grad_norm": 0.6304532289505005, + "learning_rate": 2.8721026365155046e-05, + "loss": 1.6962, + "step": 11591 + }, + { + "epoch": 0.6461178306671869, + "grad_norm": 0.5298161506652832, + "learning_rate": 2.8712969071724405e-05, + "loss": 1.5756, + "step": 11592 + }, + { + "epoch": 0.64617356892035, + "grad_norm": 0.5427919030189514, + "learning_rate": 2.8704912453394266e-05, + "loss": 1.5104, + "step": 11593 + }, + { + "epoch": 0.6462293071735132, + "grad_norm": 0.5470585823059082, + "learning_rate": 2.8696856510420146e-05, + "loss": 1.6283, + "step": 11594 + }, + { + "epoch": 0.6462850454266763, + "grad_norm": 0.55455082654953, + "learning_rate": 2.8688801243057532e-05, + "loss": 1.7311, + "step": 11595 + }, + { + "epoch": 0.6463407836798395, + "grad_norm": 0.5554984211921692, + "learning_rate": 2.868074665156191e-05, + "loss": 1.695, + "step": 11596 + }, + { + "epoch": 0.6463965219330026, + "grad_norm": 0.5633205771446228, + "learning_rate": 2.867269273618869e-05, + "loss": 1.6918, + "step": 11597 + }, + { + "epoch": 0.6464522601861658, + "grad_norm": 0.5851027965545654, + "learning_rate": 2.8664639497193303e-05, + "loss": 1.865, + "step": 11598 + }, + { + "epoch": 0.6465079984393289, + "grad_norm": 0.526494026184082, + "learning_rate": 2.865658693483116e-05, + "loss": 1.5144, + "step": 11599 + }, + { + "epoch": 0.646563736692492, + "grad_norm": 0.5389431118965149, + "learning_rate": 2.8648535049357637e-05, + "loss": 1.5973, + "step": 11600 + }, + { + "epoch": 0.6466194749456552, + "grad_norm": 0.5754119753837585, + "learning_rate": 2.86404838410281e-05, + "loss": 1.763, + "step": 11601 + }, + { + "epoch": 0.6466752131988184, + "grad_norm": 0.5695751309394836, + "learning_rate": 2.863243331009787e-05, + "loss": 1.5489, + "step": 11602 + }, + { + "epoch": 0.6467309514519815, + "grad_norm": 0.5716252326965332, + "learning_rate": 2.86243834568223e-05, + "loss": 1.8196, + "step": 11603 + }, + { + "epoch": 0.6467866897051446, + "grad_norm": 0.5450440049171448, + "learning_rate": 2.8616334281456643e-05, + "loss": 1.7187, + "step": 11604 + }, + { + "epoch": 0.6468424279583078, + "grad_norm": 0.5670022964477539, + "learning_rate": 2.8608285784256182e-05, + "loss": 1.6422, + "step": 11605 + }, + { + "epoch": 0.6468981662114709, + "grad_norm": 0.5809680819511414, + "learning_rate": 2.8600237965476172e-05, + "loss": 1.6867, + "step": 11606 + }, + { + "epoch": 0.6469539044646341, + "grad_norm": 0.5372865796089172, + "learning_rate": 2.8592190825371845e-05, + "loss": 1.561, + "step": 11607 + }, + { + "epoch": 0.6470096427177973, + "grad_norm": 0.557598888874054, + "learning_rate": 2.8584144364198428e-05, + "loss": 1.7218, + "step": 11608 + }, + { + "epoch": 0.6470653809709603, + "grad_norm": 0.57530277967453, + "learning_rate": 2.8576098582211054e-05, + "loss": 1.5977, + "step": 11609 + }, + { + "epoch": 0.6471211192241235, + "grad_norm": 0.5730135440826416, + "learning_rate": 2.856805347966496e-05, + "loss": 1.6856, + "step": 11610 + }, + { + "epoch": 0.6471768574772867, + "grad_norm": 0.5707370042800903, + "learning_rate": 2.8560009056815235e-05, + "loss": 1.6719, + "step": 11611 + }, + { + "epoch": 0.6472325957304498, + "grad_norm": 0.5852611064910889, + "learning_rate": 2.855196531391702e-05, + "loss": 1.5255, + "step": 11612 + }, + { + "epoch": 0.647288333983613, + "grad_norm": 0.5563340783119202, + "learning_rate": 2.8543922251225408e-05, + "loss": 1.543, + "step": 11613 + }, + { + "epoch": 0.6473440722367761, + "grad_norm": 0.6254847645759583, + "learning_rate": 2.8535879868995487e-05, + "loss": 1.9824, + "step": 11614 + }, + { + "epoch": 0.6473998104899392, + "grad_norm": 0.5794035196304321, + "learning_rate": 2.8527838167482336e-05, + "loss": 1.9843, + "step": 11615 + }, + { + "epoch": 0.6474555487431024, + "grad_norm": 0.565477728843689, + "learning_rate": 2.851979714694094e-05, + "loss": 1.6633, + "step": 11616 + }, + { + "epoch": 0.6475112869962656, + "grad_norm": 0.5635069608688354, + "learning_rate": 2.8511756807626345e-05, + "loss": 1.7438, + "step": 11617 + }, + { + "epoch": 0.6475670252494287, + "grad_norm": 0.5621711015701294, + "learning_rate": 2.850371714979354e-05, + "loss": 1.4934, + "step": 11618 + }, + { + "epoch": 0.6476227635025918, + "grad_norm": 0.5810402035713196, + "learning_rate": 2.8495678173697494e-05, + "loss": 1.7621, + "step": 11619 + }, + { + "epoch": 0.6476785017557549, + "grad_norm": 0.5873593091964722, + "learning_rate": 2.8487639879593153e-05, + "loss": 1.6058, + "step": 11620 + }, + { + "epoch": 0.6477342400089181, + "grad_norm": 0.604656994342804, + "learning_rate": 2.847960226773545e-05, + "loss": 1.8631, + "step": 11621 + }, + { + "epoch": 0.6477899782620813, + "grad_norm": 0.5500726699829102, + "learning_rate": 2.8471565338379313e-05, + "loss": 1.5498, + "step": 11622 + }, + { + "epoch": 0.6478457165152444, + "grad_norm": 0.5837782621383667, + "learning_rate": 2.8463529091779583e-05, + "loss": 1.5045, + "step": 11623 + }, + { + "epoch": 0.6479014547684075, + "grad_norm": 0.5583280920982361, + "learning_rate": 2.8455493528191145e-05, + "loss": 1.606, + "step": 11624 + }, + { + "epoch": 0.6479571930215707, + "grad_norm": 0.5514859557151794, + "learning_rate": 2.844745864786884e-05, + "loss": 1.7629, + "step": 11625 + }, + { + "epoch": 0.6480129312747338, + "grad_norm": 0.5777311325073242, + "learning_rate": 2.8439424451067487e-05, + "loss": 1.644, + "step": 11626 + }, + { + "epoch": 0.648068669527897, + "grad_norm": 0.5456623435020447, + "learning_rate": 2.843139093804188e-05, + "loss": 1.6939, + "step": 11627 + }, + { + "epoch": 0.6481244077810602, + "grad_norm": 0.5963661074638367, + "learning_rate": 2.8423358109046806e-05, + "loss": 1.7068, + "step": 11628 + }, + { + "epoch": 0.6481801460342232, + "grad_norm": 0.5352113246917725, + "learning_rate": 2.8415325964337026e-05, + "loss": 1.6281, + "step": 11629 + }, + { + "epoch": 0.6482358842873864, + "grad_norm": 0.5343273878097534, + "learning_rate": 2.8407294504167236e-05, + "loss": 1.4476, + "step": 11630 + }, + { + "epoch": 0.6482916225405496, + "grad_norm": 0.5758916139602661, + "learning_rate": 2.839926372879218e-05, + "loss": 1.7469, + "step": 11631 + }, + { + "epoch": 0.6483473607937127, + "grad_norm": 0.5887387990951538, + "learning_rate": 2.839123363846653e-05, + "loss": 1.635, + "step": 11632 + }, + { + "epoch": 0.6484030990468759, + "grad_norm": 0.5245947241783142, + "learning_rate": 2.838320423344496e-05, + "loss": 1.6089, + "step": 11633 + }, + { + "epoch": 0.6484588373000391, + "grad_norm": 0.579623281955719, + "learning_rate": 2.8375175513982144e-05, + "loss": 1.6684, + "step": 11634 + }, + { + "epoch": 0.6485145755532021, + "grad_norm": 0.5545833110809326, + "learning_rate": 2.8367147480332635e-05, + "loss": 1.6369, + "step": 11635 + }, + { + "epoch": 0.6485703138063653, + "grad_norm": 0.5932074785232544, + "learning_rate": 2.8359120132751116e-05, + "loss": 1.7348, + "step": 11636 + }, + { + "epoch": 0.6486260520595285, + "grad_norm": 0.5304184556007385, + "learning_rate": 2.835109347149212e-05, + "loss": 1.5308, + "step": 11637 + }, + { + "epoch": 0.6486817903126916, + "grad_norm": 0.5450805425643921, + "learning_rate": 2.834306749681021e-05, + "loss": 1.6735, + "step": 11638 + }, + { + "epoch": 0.6487375285658548, + "grad_norm": 0.5163072347640991, + "learning_rate": 2.8335042208959932e-05, + "loss": 1.3315, + "step": 11639 + }, + { + "epoch": 0.6487932668190179, + "grad_norm": 0.5149058103561401, + "learning_rate": 2.8327017608195804e-05, + "loss": 1.4162, + "step": 11640 + }, + { + "epoch": 0.648849005072181, + "grad_norm": 0.5630050897598267, + "learning_rate": 2.831899369477233e-05, + "loss": 1.407, + "step": 11641 + }, + { + "epoch": 0.6489047433253442, + "grad_norm": 0.5516093969345093, + "learning_rate": 2.8310970468943947e-05, + "loss": 1.4329, + "step": 11642 + }, + { + "epoch": 0.6489604815785073, + "grad_norm": 0.5966786742210388, + "learning_rate": 2.830294793096513e-05, + "loss": 1.7362, + "step": 11643 + }, + { + "epoch": 0.6490162198316705, + "grad_norm": 0.5372209548950195, + "learning_rate": 2.8294926081090296e-05, + "loss": 1.8945, + "step": 11644 + }, + { + "epoch": 0.6490719580848336, + "grad_norm": 0.5281509160995483, + "learning_rate": 2.8286904919573858e-05, + "loss": 1.6381, + "step": 11645 + }, + { + "epoch": 0.6491276963379967, + "grad_norm": 0.5646560788154602, + "learning_rate": 2.8278884446670205e-05, + "loss": 1.5749, + "step": 11646 + }, + { + "epoch": 0.6491834345911599, + "grad_norm": 0.5708281993865967, + "learning_rate": 2.827086466263369e-05, + "loss": 1.6901, + "step": 11647 + }, + { + "epoch": 0.6492391728443231, + "grad_norm": 0.5605478882789612, + "learning_rate": 2.8262845567718676e-05, + "loss": 1.588, + "step": 11648 + }, + { + "epoch": 0.6492949110974862, + "grad_norm": 0.5626661777496338, + "learning_rate": 2.8254827162179453e-05, + "loss": 1.5874, + "step": 11649 + }, + { + "epoch": 0.6493506493506493, + "grad_norm": 0.5522568225860596, + "learning_rate": 2.8246809446270323e-05, + "loss": 1.5423, + "step": 11650 + }, + { + "epoch": 0.6494063876038125, + "grad_norm": 0.5682557225227356, + "learning_rate": 2.8238792420245564e-05, + "loss": 1.4861, + "step": 11651 + }, + { + "epoch": 0.6494621258569756, + "grad_norm": 0.5430989265441895, + "learning_rate": 2.823077608435944e-05, + "loss": 1.4421, + "step": 11652 + }, + { + "epoch": 0.6495178641101388, + "grad_norm": 0.5792363286018372, + "learning_rate": 2.822276043886617e-05, + "loss": 1.5598, + "step": 11653 + }, + { + "epoch": 0.649573602363302, + "grad_norm": 0.6064366102218628, + "learning_rate": 2.8214745484019972e-05, + "loss": 1.485, + "step": 11654 + }, + { + "epoch": 0.649629340616465, + "grad_norm": 0.5442171692848206, + "learning_rate": 2.820673122007505e-05, + "loss": 1.4355, + "step": 11655 + }, + { + "epoch": 0.6496850788696282, + "grad_norm": 0.6010521054267883, + "learning_rate": 2.8198717647285534e-05, + "loss": 1.6034, + "step": 11656 + }, + { + "epoch": 0.6497408171227914, + "grad_norm": 0.5923758745193481, + "learning_rate": 2.8190704765905573e-05, + "loss": 1.7005, + "step": 11657 + }, + { + "epoch": 0.6497965553759545, + "grad_norm": 0.5728440284729004, + "learning_rate": 2.8182692576189306e-05, + "loss": 1.6823, + "step": 11658 + }, + { + "epoch": 0.6498522936291177, + "grad_norm": 0.5419698357582092, + "learning_rate": 2.817468107839083e-05, + "loss": 1.6961, + "step": 11659 + }, + { + "epoch": 0.6499080318822809, + "grad_norm": 0.5518703460693359, + "learning_rate": 2.816667027276424e-05, + "loss": 1.6161, + "step": 11660 + }, + { + "epoch": 0.6499637701354439, + "grad_norm": 0.5387782454490662, + "learning_rate": 2.8158660159563527e-05, + "loss": 1.6064, + "step": 11661 + }, + { + "epoch": 0.6500195083886071, + "grad_norm": 0.5789139866828918, + "learning_rate": 2.815065073904281e-05, + "loss": 1.6869, + "step": 11662 + }, + { + "epoch": 0.6500752466417703, + "grad_norm": 0.5399966239929199, + "learning_rate": 2.8142642011456045e-05, + "loss": 1.6542, + "step": 11663 + }, + { + "epoch": 0.6501309848949334, + "grad_norm": 0.5608077645301819, + "learning_rate": 2.8134633977057235e-05, + "loss": 1.6167, + "step": 11664 + }, + { + "epoch": 0.6501867231480966, + "grad_norm": 0.5759866237640381, + "learning_rate": 2.812662663610035e-05, + "loss": 1.6651, + "step": 11665 + }, + { + "epoch": 0.6502424614012596, + "grad_norm": 0.5594897270202637, + "learning_rate": 2.8118619988839338e-05, + "loss": 1.3785, + "step": 11666 + }, + { + "epoch": 0.6502981996544228, + "grad_norm": 0.53223717212677, + "learning_rate": 2.811061403552815e-05, + "loss": 1.5593, + "step": 11667 + }, + { + "epoch": 0.650353937907586, + "grad_norm": 0.579182505607605, + "learning_rate": 2.8102608776420614e-05, + "loss": 1.7187, + "step": 11668 + }, + { + "epoch": 0.6504096761607491, + "grad_norm": 0.5530314445495605, + "learning_rate": 2.8094604211770693e-05, + "loss": 1.5669, + "step": 11669 + }, + { + "epoch": 0.6504654144139123, + "grad_norm": 0.6045119166374207, + "learning_rate": 2.8086600341832197e-05, + "loss": 1.7421, + "step": 11670 + }, + { + "epoch": 0.6505211526670754, + "grad_norm": 0.509285032749176, + "learning_rate": 2.807859716685899e-05, + "loss": 1.4496, + "step": 11671 + }, + { + "epoch": 0.6505768909202385, + "grad_norm": 0.5628162622451782, + "learning_rate": 2.8070594687104835e-05, + "loss": 1.5671, + "step": 11672 + }, + { + "epoch": 0.6506326291734017, + "grad_norm": 0.5559877157211304, + "learning_rate": 2.806259290282357e-05, + "loss": 1.6659, + "step": 11673 + }, + { + "epoch": 0.6506883674265649, + "grad_norm": 0.5760934352874756, + "learning_rate": 2.8054591814268984e-05, + "loss": 1.5014, + "step": 11674 + }, + { + "epoch": 0.650744105679728, + "grad_norm": 0.5483234524726868, + "learning_rate": 2.804659142169477e-05, + "loss": 1.7134, + "step": 11675 + }, + { + "epoch": 0.6507998439328911, + "grad_norm": 0.6183010339736938, + "learning_rate": 2.803859172535468e-05, + "loss": 1.8295, + "step": 11676 + }, + { + "epoch": 0.6508555821860543, + "grad_norm": 0.5524032711982727, + "learning_rate": 2.8030592725502412e-05, + "loss": 1.553, + "step": 11677 + }, + { + "epoch": 0.6509113204392174, + "grad_norm": 0.5912196040153503, + "learning_rate": 2.8022594422391663e-05, + "loss": 1.5796, + "step": 11678 + }, + { + "epoch": 0.6509670586923806, + "grad_norm": 0.5911765098571777, + "learning_rate": 2.8014596816276073e-05, + "loss": 1.6964, + "step": 11679 + }, + { + "epoch": 0.6510227969455438, + "grad_norm": 0.5506945848464966, + "learning_rate": 2.800659990740929e-05, + "loss": 1.523, + "step": 11680 + }, + { + "epoch": 0.6510785351987068, + "grad_norm": 0.5004502534866333, + "learning_rate": 2.7998603696044952e-05, + "loss": 1.385, + "step": 11681 + }, + { + "epoch": 0.65113427345187, + "grad_norm": 0.5972052216529846, + "learning_rate": 2.79906081824366e-05, + "loss": 1.4586, + "step": 11682 + }, + { + "epoch": 0.6511900117050332, + "grad_norm": 0.5466043949127197, + "learning_rate": 2.798261336683784e-05, + "loss": 1.5598, + "step": 11683 + }, + { + "epoch": 0.6512457499581963, + "grad_norm": 0.5743733644485474, + "learning_rate": 2.7974619249502208e-05, + "loss": 1.6281, + "step": 11684 + }, + { + "epoch": 0.6513014882113595, + "grad_norm": 0.5645943284034729, + "learning_rate": 2.7966625830683235e-05, + "loss": 1.6654, + "step": 11685 + }, + { + "epoch": 0.6513572264645227, + "grad_norm": 0.6178829073905945, + "learning_rate": 2.7958633110634457e-05, + "loss": 1.6944, + "step": 11686 + }, + { + "epoch": 0.6514129647176857, + "grad_norm": 0.5012251734733582, + "learning_rate": 2.7950641089609274e-05, + "loss": 1.3509, + "step": 11687 + }, + { + "epoch": 0.6514687029708489, + "grad_norm": 0.6008442640304565, + "learning_rate": 2.7942649767861252e-05, + "loss": 1.8239, + "step": 11688 + }, + { + "epoch": 0.651524441224012, + "grad_norm": 0.562760055065155, + "learning_rate": 2.7934659145643747e-05, + "loss": 1.7763, + "step": 11689 + }, + { + "epoch": 0.6515801794771752, + "grad_norm": 0.572251558303833, + "learning_rate": 2.792666922321021e-05, + "loss": 1.5611, + "step": 11690 + }, + { + "epoch": 0.6516359177303384, + "grad_norm": 0.5346998572349548, + "learning_rate": 2.7918680000814025e-05, + "loss": 1.6913, + "step": 11691 + }, + { + "epoch": 0.6516916559835014, + "grad_norm": 0.571090817451477, + "learning_rate": 2.7910691478708567e-05, + "loss": 1.7309, + "step": 11692 + }, + { + "epoch": 0.6517473942366646, + "grad_norm": 0.6278156042098999, + "learning_rate": 2.7902703657147206e-05, + "loss": 1.9031, + "step": 11693 + }, + { + "epoch": 0.6518031324898278, + "grad_norm": 0.5592220425605774, + "learning_rate": 2.789471653638321e-05, + "loss": 1.6664, + "step": 11694 + }, + { + "epoch": 0.6518588707429909, + "grad_norm": 0.5627824664115906, + "learning_rate": 2.7886730116669963e-05, + "loss": 1.7134, + "step": 11695 + }, + { + "epoch": 0.651914608996154, + "grad_norm": 0.5618991851806641, + "learning_rate": 2.787874439826068e-05, + "loss": 1.6886, + "step": 11696 + }, + { + "epoch": 0.6519703472493172, + "grad_norm": 0.5403565168380737, + "learning_rate": 2.7870759381408686e-05, + "loss": 1.5477, + "step": 11697 + }, + { + "epoch": 0.6520260855024803, + "grad_norm": 0.5511575937271118, + "learning_rate": 2.7862775066367124e-05, + "loss": 1.5624, + "step": 11698 + }, + { + "epoch": 0.6520818237556435, + "grad_norm": 0.6034442782402039, + "learning_rate": 2.7854791453389295e-05, + "loss": 1.8036, + "step": 11699 + }, + { + "epoch": 0.6521375620088067, + "grad_norm": 0.5496557950973511, + "learning_rate": 2.7846808542728386e-05, + "loss": 1.639, + "step": 11700 + }, + { + "epoch": 0.6521933002619698, + "grad_norm": 0.5528457760810852, + "learning_rate": 2.783882633463753e-05, + "loss": 1.553, + "step": 11701 + }, + { + "epoch": 0.6522490385151329, + "grad_norm": 0.49106788635253906, + "learning_rate": 2.7830844829369896e-05, + "loss": 1.2438, + "step": 11702 + }, + { + "epoch": 0.6523047767682961, + "grad_norm": 0.5681769251823425, + "learning_rate": 2.7822864027178596e-05, + "loss": 1.5023, + "step": 11703 + }, + { + "epoch": 0.6523605150214592, + "grad_norm": 0.6085399985313416, + "learning_rate": 2.781488392831676e-05, + "loss": 1.5908, + "step": 11704 + }, + { + "epoch": 0.6524162532746224, + "grad_norm": 0.5347082614898682, + "learning_rate": 2.7806904533037455e-05, + "loss": 1.6314, + "step": 11705 + }, + { + "epoch": 0.6524719915277856, + "grad_norm": 0.5232277512550354, + "learning_rate": 2.7798925841593743e-05, + "loss": 1.4394, + "step": 11706 + }, + { + "epoch": 0.6525277297809486, + "grad_norm": 0.5716795921325684, + "learning_rate": 2.779094785423868e-05, + "loss": 1.8412, + "step": 11707 + }, + { + "epoch": 0.6525834680341118, + "grad_norm": 0.5647847056388855, + "learning_rate": 2.7782970571225243e-05, + "loss": 1.592, + "step": 11708 + }, + { + "epoch": 0.652639206287275, + "grad_norm": 0.5854530930519104, + "learning_rate": 2.777499399280645e-05, + "loss": 1.8748, + "step": 11709 + }, + { + "epoch": 0.6526949445404381, + "grad_norm": 0.5178894400596619, + "learning_rate": 2.7767018119235262e-05, + "loss": 1.5548, + "step": 11710 + }, + { + "epoch": 0.6527506827936013, + "grad_norm": 0.5811799168586731, + "learning_rate": 2.7759042950764635e-05, + "loss": 1.6619, + "step": 11711 + }, + { + "epoch": 0.6528064210467643, + "grad_norm": 0.5538857579231262, + "learning_rate": 2.7751068487647508e-05, + "loss": 1.5367, + "step": 11712 + }, + { + "epoch": 0.6528621592999275, + "grad_norm": 0.5820496082305908, + "learning_rate": 2.774309473013673e-05, + "loss": 1.7765, + "step": 11713 + }, + { + "epoch": 0.6529178975530907, + "grad_norm": 0.5591105222702026, + "learning_rate": 2.7735121678485265e-05, + "loss": 1.445, + "step": 11714 + }, + { + "epoch": 0.6529736358062538, + "grad_norm": 0.5089815855026245, + "learning_rate": 2.7727149332945902e-05, + "loss": 1.4578, + "step": 11715 + }, + { + "epoch": 0.653029374059417, + "grad_norm": 0.5578038096427917, + "learning_rate": 2.7719177693771505e-05, + "loss": 1.2704, + "step": 11716 + }, + { + "epoch": 0.6530851123125802, + "grad_norm": 0.5787779092788696, + "learning_rate": 2.7711206761214882e-05, + "loss": 1.5699, + "step": 11717 + }, + { + "epoch": 0.6531408505657432, + "grad_norm": 0.6014275550842285, + "learning_rate": 2.770323653552883e-05, + "loss": 1.8262, + "step": 11718 + }, + { + "epoch": 0.6531965888189064, + "grad_norm": 0.5510164499282837, + "learning_rate": 2.769526701696613e-05, + "loss": 1.6857, + "step": 11719 + }, + { + "epoch": 0.6532523270720696, + "grad_norm": 0.5538983345031738, + "learning_rate": 2.7687298205779488e-05, + "loss": 1.6479, + "step": 11720 + }, + { + "epoch": 0.6533080653252327, + "grad_norm": 0.5758739709854126, + "learning_rate": 2.7679330102221684e-05, + "loss": 1.5931, + "step": 11721 + }, + { + "epoch": 0.6533638035783959, + "grad_norm": 0.5778799057006836, + "learning_rate": 2.7671362706545377e-05, + "loss": 1.6227, + "step": 11722 + }, + { + "epoch": 0.653419541831559, + "grad_norm": 0.5738372206687927, + "learning_rate": 2.7663396019003275e-05, + "loss": 1.6291, + "step": 11723 + }, + { + "epoch": 0.6534752800847221, + "grad_norm": 0.5328623652458191, + "learning_rate": 2.7655430039847986e-05, + "loss": 1.3945, + "step": 11724 + }, + { + "epoch": 0.6535310183378853, + "grad_norm": 0.574098527431488, + "learning_rate": 2.7647464769332186e-05, + "loss": 1.6416, + "step": 11725 + }, + { + "epoch": 0.6535867565910485, + "grad_norm": 0.5825911164283752, + "learning_rate": 2.7639500207708513e-05, + "loss": 1.5359, + "step": 11726 + }, + { + "epoch": 0.6536424948442116, + "grad_norm": 0.5495928525924683, + "learning_rate": 2.7631536355229494e-05, + "loss": 1.8041, + "step": 11727 + }, + { + "epoch": 0.6536982330973747, + "grad_norm": 0.5315799117088318, + "learning_rate": 2.7623573212147723e-05, + "loss": 1.3771, + "step": 11728 + }, + { + "epoch": 0.6537539713505379, + "grad_norm": 0.5464669466018677, + "learning_rate": 2.7615610778715757e-05, + "loss": 1.5428, + "step": 11729 + }, + { + "epoch": 0.653809709603701, + "grad_norm": 0.5899285674095154, + "learning_rate": 2.76076490551861e-05, + "loss": 1.7209, + "step": 11730 + }, + { + "epoch": 0.6538654478568642, + "grad_norm": 0.544582188129425, + "learning_rate": 2.7599688041811257e-05, + "loss": 1.7189, + "step": 11731 + }, + { + "epoch": 0.6539211861100274, + "grad_norm": 0.5615865588188171, + "learning_rate": 2.759172773884371e-05, + "loss": 1.6597, + "step": 11732 + }, + { + "epoch": 0.6539769243631904, + "grad_norm": 0.5366857051849365, + "learning_rate": 2.7583768146535925e-05, + "loss": 1.5292, + "step": 11733 + }, + { + "epoch": 0.6540326626163536, + "grad_norm": 0.563675582408905, + "learning_rate": 2.7575809265140305e-05, + "loss": 1.6176, + "step": 11734 + }, + { + "epoch": 0.6540884008695167, + "grad_norm": 0.5570533275604248, + "learning_rate": 2.756785109490927e-05, + "loss": 1.7055, + "step": 11735 + }, + { + "epoch": 0.6541441391226799, + "grad_norm": 0.548004150390625, + "learning_rate": 2.7559893636095212e-05, + "loss": 1.5861, + "step": 11736 + }, + { + "epoch": 0.6541998773758431, + "grad_norm": 0.5964729189872742, + "learning_rate": 2.755193688895049e-05, + "loss": 1.8638, + "step": 11737 + }, + { + "epoch": 0.6542556156290061, + "grad_norm": 0.5480014085769653, + "learning_rate": 2.754398085372747e-05, + "loss": 1.4608, + "step": 11738 + }, + { + "epoch": 0.6543113538821693, + "grad_norm": 0.5882792472839355, + "learning_rate": 2.7536025530678407e-05, + "loss": 1.7498, + "step": 11739 + }, + { + "epoch": 0.6543670921353325, + "grad_norm": 0.5270636081695557, + "learning_rate": 2.752807092005568e-05, + "loss": 1.4097, + "step": 11740 + }, + { + "epoch": 0.6544228303884956, + "grad_norm": 0.5782089829444885, + "learning_rate": 2.75201170221115e-05, + "loss": 1.6588, + "step": 11741 + }, + { + "epoch": 0.6544785686416588, + "grad_norm": 0.6418783664703369, + "learning_rate": 2.7512163837098155e-05, + "loss": 1.8219, + "step": 11742 + }, + { + "epoch": 0.654534306894822, + "grad_norm": 0.5354815125465393, + "learning_rate": 2.750421136526785e-05, + "loss": 1.4547, + "step": 11743 + }, + { + "epoch": 0.654590045147985, + "grad_norm": 0.566822350025177, + "learning_rate": 2.74962596068728e-05, + "loss": 1.6586, + "step": 11744 + }, + { + "epoch": 0.6546457834011482, + "grad_norm": 0.6059299111366272, + "learning_rate": 2.748830856216521e-05, + "loss": 1.8293, + "step": 11745 + }, + { + "epoch": 0.6547015216543114, + "grad_norm": 0.5582495331764221, + "learning_rate": 2.7480358231397184e-05, + "loss": 1.651, + "step": 11746 + }, + { + "epoch": 0.6547572599074745, + "grad_norm": 0.6115778088569641, + "learning_rate": 2.747240861482093e-05, + "loss": 1.4241, + "step": 11747 + }, + { + "epoch": 0.6548129981606376, + "grad_norm": 0.6121757626533508, + "learning_rate": 2.7464459712688516e-05, + "loss": 1.8573, + "step": 11748 + }, + { + "epoch": 0.6548687364138008, + "grad_norm": 0.5520625114440918, + "learning_rate": 2.745651152525205e-05, + "loss": 1.7483, + "step": 11749 + }, + { + "epoch": 0.6549244746669639, + "grad_norm": 0.5481840968132019, + "learning_rate": 2.744856405276359e-05, + "loss": 1.5745, + "step": 11750 + }, + { + "epoch": 0.6549802129201271, + "grad_norm": 0.575197696685791, + "learning_rate": 2.744061729547521e-05, + "loss": 1.6733, + "step": 11751 + }, + { + "epoch": 0.6550359511732903, + "grad_norm": 0.5682066082954407, + "learning_rate": 2.743267125363893e-05, + "loss": 1.6021, + "step": 11752 + }, + { + "epoch": 0.6550916894264533, + "grad_norm": 0.6352496147155762, + "learning_rate": 2.7424725927506722e-05, + "loss": 1.5939, + "step": 11753 + }, + { + "epoch": 0.6551474276796165, + "grad_norm": 0.5162918567657471, + "learning_rate": 2.741678131733058e-05, + "loss": 1.5034, + "step": 11754 + }, + { + "epoch": 0.6552031659327797, + "grad_norm": 0.5746167302131653, + "learning_rate": 2.740883742336247e-05, + "loss": 1.6453, + "step": 11755 + }, + { + "epoch": 0.6552589041859428, + "grad_norm": 0.5538302063941956, + "learning_rate": 2.7400894245854326e-05, + "loss": 1.7042, + "step": 11756 + }, + { + "epoch": 0.655314642439106, + "grad_norm": 0.5114599466323853, + "learning_rate": 2.7392951785058046e-05, + "loss": 1.5452, + "step": 11757 + }, + { + "epoch": 0.655370380692269, + "grad_norm": 0.5948389768600464, + "learning_rate": 2.7385010041225534e-05, + "loss": 1.7493, + "step": 11758 + }, + { + "epoch": 0.6554261189454322, + "grad_norm": 0.48783570528030396, + "learning_rate": 2.737706901460866e-05, + "loss": 1.3269, + "step": 11759 + }, + { + "epoch": 0.6554818571985954, + "grad_norm": 0.5941017270088196, + "learning_rate": 2.7369128705459246e-05, + "loss": 1.7478, + "step": 11760 + }, + { + "epoch": 0.6555375954517585, + "grad_norm": 0.5333529710769653, + "learning_rate": 2.736118911402912e-05, + "loss": 1.6844, + "step": 11761 + }, + { + "epoch": 0.6555933337049217, + "grad_norm": 0.6064323782920837, + "learning_rate": 2.735325024057007e-05, + "loss": 1.8216, + "step": 11762 + }, + { + "epoch": 0.6556490719580849, + "grad_norm": 0.6015443205833435, + "learning_rate": 2.7345312085333897e-05, + "loss": 1.7156, + "step": 11763 + }, + { + "epoch": 0.6557048102112479, + "grad_norm": 0.5998244285583496, + "learning_rate": 2.7337374648572354e-05, + "loss": 1.7078, + "step": 11764 + }, + { + "epoch": 0.6557605484644111, + "grad_norm": 0.5969440937042236, + "learning_rate": 2.7329437930537115e-05, + "loss": 1.798, + "step": 11765 + }, + { + "epoch": 0.6558162867175743, + "grad_norm": 0.48716482520103455, + "learning_rate": 2.7321501931479966e-05, + "loss": 1.3555, + "step": 11766 + }, + { + "epoch": 0.6558720249707374, + "grad_norm": 0.5743377208709717, + "learning_rate": 2.7313566651652532e-05, + "loss": 1.4993, + "step": 11767 + }, + { + "epoch": 0.6559277632239006, + "grad_norm": 0.5310671329498291, + "learning_rate": 2.7305632091306488e-05, + "loss": 1.6846, + "step": 11768 + }, + { + "epoch": 0.6559835014770637, + "grad_norm": 0.5764484405517578, + "learning_rate": 2.729769825069348e-05, + "loss": 1.7928, + "step": 11769 + }, + { + "epoch": 0.6560392397302268, + "grad_norm": 0.5921671986579895, + "learning_rate": 2.7289765130065126e-05, + "loss": 1.6052, + "step": 11770 + }, + { + "epoch": 0.65609497798339, + "grad_norm": 0.5272278785705566, + "learning_rate": 2.728183272967303e-05, + "loss": 1.6509, + "step": 11771 + }, + { + "epoch": 0.6561507162365532, + "grad_norm": 0.5755944848060608, + "learning_rate": 2.7273901049768697e-05, + "loss": 1.7614, + "step": 11772 + }, + { + "epoch": 0.6562064544897163, + "grad_norm": 0.5172051787376404, + "learning_rate": 2.7265970090603764e-05, + "loss": 1.441, + "step": 11773 + }, + { + "epoch": 0.6562621927428794, + "grad_norm": 0.6681126356124878, + "learning_rate": 2.725803985242969e-05, + "loss": 1.7769, + "step": 11774 + }, + { + "epoch": 0.6563179309960426, + "grad_norm": 0.5718099474906921, + "learning_rate": 2.7250110335497996e-05, + "loss": 1.7925, + "step": 11775 + }, + { + "epoch": 0.6563736692492057, + "grad_norm": 0.6293430924415588, + "learning_rate": 2.7242181540060163e-05, + "loss": 1.8628, + "step": 11776 + }, + { + "epoch": 0.6564294075023689, + "grad_norm": 0.5449262857437134, + "learning_rate": 2.7234253466367643e-05, + "loss": 1.5689, + "step": 11777 + }, + { + "epoch": 0.6564851457555321, + "grad_norm": 0.5448122620582581, + "learning_rate": 2.7226326114671895e-05, + "loss": 1.5135, + "step": 11778 + }, + { + "epoch": 0.6565408840086951, + "grad_norm": 0.5253317356109619, + "learning_rate": 2.7218399485224278e-05, + "loss": 1.5069, + "step": 11779 + }, + { + "epoch": 0.6565966222618583, + "grad_norm": 0.5427688956260681, + "learning_rate": 2.721047357827621e-05, + "loss": 1.6105, + "step": 11780 + }, + { + "epoch": 0.6566523605150214, + "grad_norm": 0.5660583972930908, + "learning_rate": 2.7202548394079037e-05, + "loss": 1.7517, + "step": 11781 + }, + { + "epoch": 0.6567080987681846, + "grad_norm": 0.5620884895324707, + "learning_rate": 2.7194623932884133e-05, + "loss": 1.5322, + "step": 11782 + }, + { + "epoch": 0.6567638370213478, + "grad_norm": 0.6195741891860962, + "learning_rate": 2.718670019494276e-05, + "loss": 1.6235, + "step": 11783 + }, + { + "epoch": 0.6568195752745108, + "grad_norm": 0.578835666179657, + "learning_rate": 2.717877718050626e-05, + "loss": 1.6345, + "step": 11784 + }, + { + "epoch": 0.656875313527674, + "grad_norm": 0.561337411403656, + "learning_rate": 2.7170854889825914e-05, + "loss": 1.7114, + "step": 11785 + }, + { + "epoch": 0.6569310517808372, + "grad_norm": 0.5934423804283142, + "learning_rate": 2.716293332315293e-05, + "loss": 1.7212, + "step": 11786 + }, + { + "epoch": 0.6569867900340003, + "grad_norm": 0.5505562424659729, + "learning_rate": 2.7155012480738546e-05, + "loss": 1.6627, + "step": 11787 + }, + { + "epoch": 0.6570425282871635, + "grad_norm": 0.5922462940216064, + "learning_rate": 2.714709236283397e-05, + "loss": 1.7468, + "step": 11788 + }, + { + "epoch": 0.6570982665403267, + "grad_norm": 0.5288242101669312, + "learning_rate": 2.7139172969690385e-05, + "loss": 1.5715, + "step": 11789 + }, + { + "epoch": 0.6571540047934897, + "grad_norm": 0.5881549715995789, + "learning_rate": 2.7131254301558965e-05, + "loss": 1.6476, + "step": 11790 + }, + { + "epoch": 0.6572097430466529, + "grad_norm": 0.5649522542953491, + "learning_rate": 2.7123336358690786e-05, + "loss": 1.5052, + "step": 11791 + }, + { + "epoch": 0.6572654812998161, + "grad_norm": 0.6090741157531738, + "learning_rate": 2.711541914133704e-05, + "loss": 1.673, + "step": 11792 + }, + { + "epoch": 0.6573212195529792, + "grad_norm": 0.5936515927314758, + "learning_rate": 2.710750264974875e-05, + "loss": 1.7664, + "step": 11793 + }, + { + "epoch": 0.6573769578061424, + "grad_norm": 0.5199238657951355, + "learning_rate": 2.7099586884177004e-05, + "loss": 1.6937, + "step": 11794 + }, + { + "epoch": 0.6574326960593055, + "grad_norm": 0.5748278498649597, + "learning_rate": 2.709167184487284e-05, + "loss": 1.6415, + "step": 11795 + }, + { + "epoch": 0.6574884343124686, + "grad_norm": 0.6542965173721313, + "learning_rate": 2.7083757532087285e-05, + "loss": 2.0278, + "step": 11796 + }, + { + "epoch": 0.6575441725656318, + "grad_norm": 0.5692175626754761, + "learning_rate": 2.7075843946071343e-05, + "loss": 1.7187, + "step": 11797 + }, + { + "epoch": 0.657599910818795, + "grad_norm": 0.5671214461326599, + "learning_rate": 2.7067931087075936e-05, + "loss": 1.5879, + "step": 11798 + }, + { + "epoch": 0.6576556490719581, + "grad_norm": 0.5661264657974243, + "learning_rate": 2.7060018955352094e-05, + "loss": 1.6877, + "step": 11799 + }, + { + "epoch": 0.6577113873251212, + "grad_norm": 0.5358115434646606, + "learning_rate": 2.7052107551150685e-05, + "loss": 1.5547, + "step": 11800 + }, + { + "epoch": 0.6577671255782844, + "grad_norm": 0.6027678847312927, + "learning_rate": 2.7044196874722627e-05, + "loss": 1.5204, + "step": 11801 + }, + { + "epoch": 0.6578228638314475, + "grad_norm": 0.5381132364273071, + "learning_rate": 2.7036286926318798e-05, + "loss": 1.7442, + "step": 11802 + }, + { + "epoch": 0.6578786020846107, + "grad_norm": 0.5434688329696655, + "learning_rate": 2.7028377706190068e-05, + "loss": 1.4083, + "step": 11803 + }, + { + "epoch": 0.6579343403377738, + "grad_norm": 0.5840322375297546, + "learning_rate": 2.7020469214587274e-05, + "loss": 1.8607, + "step": 11804 + }, + { + "epoch": 0.6579900785909369, + "grad_norm": 0.554832935333252, + "learning_rate": 2.7012561451761203e-05, + "loss": 1.6151, + "step": 11805 + }, + { + "epoch": 0.6580458168441001, + "grad_norm": 0.564648449420929, + "learning_rate": 2.700465441796266e-05, + "loss": 1.6476, + "step": 11806 + }, + { + "epoch": 0.6581015550972632, + "grad_norm": 0.5735161900520325, + "learning_rate": 2.6996748113442394e-05, + "loss": 1.3972, + "step": 11807 + }, + { + "epoch": 0.6581572933504264, + "grad_norm": 0.5288743376731873, + "learning_rate": 2.6988842538451187e-05, + "loss": 1.597, + "step": 11808 + }, + { + "epoch": 0.6582130316035896, + "grad_norm": 0.5484468936920166, + "learning_rate": 2.6980937693239695e-05, + "loss": 1.5462, + "step": 11809 + }, + { + "epoch": 0.6582687698567526, + "grad_norm": 0.5598819851875305, + "learning_rate": 2.697303357805866e-05, + "loss": 1.6007, + "step": 11810 + }, + { + "epoch": 0.6583245081099158, + "grad_norm": 0.5698304772377014, + "learning_rate": 2.696513019315877e-05, + "loss": 1.6685, + "step": 11811 + }, + { + "epoch": 0.658380246363079, + "grad_norm": 0.5363532900810242, + "learning_rate": 2.6957227538790625e-05, + "loss": 1.4725, + "step": 11812 + }, + { + "epoch": 0.6584359846162421, + "grad_norm": 0.5554176568984985, + "learning_rate": 2.694932561520488e-05, + "loss": 1.4386, + "step": 11813 + }, + { + "epoch": 0.6584917228694053, + "grad_norm": 0.5538124442100525, + "learning_rate": 2.694142442265212e-05, + "loss": 1.8516, + "step": 11814 + }, + { + "epoch": 0.6585474611225685, + "grad_norm": 0.5798441171646118, + "learning_rate": 2.6933523961382946e-05, + "loss": 1.7817, + "step": 11815 + }, + { + "epoch": 0.6586031993757315, + "grad_norm": 0.5579670667648315, + "learning_rate": 2.6925624231647916e-05, + "loss": 1.6708, + "step": 11816 + }, + { + "epoch": 0.6586589376288947, + "grad_norm": 0.6054978966712952, + "learning_rate": 2.691772523369752e-05, + "loss": 1.6924, + "step": 11817 + }, + { + "epoch": 0.6587146758820579, + "grad_norm": 0.5623806118965149, + "learning_rate": 2.6909826967782338e-05, + "loss": 1.5783, + "step": 11818 + }, + { + "epoch": 0.658770414135221, + "grad_norm": 0.5320571660995483, + "learning_rate": 2.6901929434152802e-05, + "loss": 1.5426, + "step": 11819 + }, + { + "epoch": 0.6588261523883842, + "grad_norm": 0.6053674817085266, + "learning_rate": 2.6894032633059392e-05, + "loss": 1.67, + "step": 11820 + }, + { + "epoch": 0.6588818906415473, + "grad_norm": 0.5375155210494995, + "learning_rate": 2.688613656475255e-05, + "loss": 1.4324, + "step": 11821 + }, + { + "epoch": 0.6589376288947104, + "grad_norm": 0.5696715116500854, + "learning_rate": 2.687824122948269e-05, + "loss": 1.5658, + "step": 11822 + }, + { + "epoch": 0.6589933671478736, + "grad_norm": 0.5656219124794006, + "learning_rate": 2.687034662750023e-05, + "loss": 1.7141, + "step": 11823 + }, + { + "epoch": 0.6590491054010368, + "grad_norm": 0.5286223292350769, + "learning_rate": 2.6862452759055478e-05, + "loss": 1.51, + "step": 11824 + }, + { + "epoch": 0.6591048436541999, + "grad_norm": 0.5871027708053589, + "learning_rate": 2.6854559624398868e-05, + "loss": 1.7183, + "step": 11825 + }, + { + "epoch": 0.659160581907363, + "grad_norm": 0.5437431931495667, + "learning_rate": 2.6846667223780658e-05, + "loss": 1.6043, + "step": 11826 + }, + { + "epoch": 0.6592163201605261, + "grad_norm": 0.5970200300216675, + "learning_rate": 2.683877555745117e-05, + "loss": 1.6279, + "step": 11827 + }, + { + "epoch": 0.6592720584136893, + "grad_norm": 0.5312990546226501, + "learning_rate": 2.683088462566068e-05, + "loss": 1.5773, + "step": 11828 + }, + { + "epoch": 0.6593277966668525, + "grad_norm": 0.5490882992744446, + "learning_rate": 2.682299442865945e-05, + "loss": 1.5818, + "step": 11829 + }, + { + "epoch": 0.6593835349200156, + "grad_norm": 0.5834240913391113, + "learning_rate": 2.6815104966697718e-05, + "loss": 1.7962, + "step": 11830 + }, + { + "epoch": 0.6594392731731787, + "grad_norm": 0.5726290345191956, + "learning_rate": 2.680721624002566e-05, + "loss": 1.6222, + "step": 11831 + }, + { + "epoch": 0.6594950114263419, + "grad_norm": 0.5791205167770386, + "learning_rate": 2.6799328248893485e-05, + "loss": 1.781, + "step": 11832 + }, + { + "epoch": 0.659550749679505, + "grad_norm": 0.5636252164840698, + "learning_rate": 2.6791440993551343e-05, + "loss": 1.5622, + "step": 11833 + }, + { + "epoch": 0.6596064879326682, + "grad_norm": 0.5404438972473145, + "learning_rate": 2.6783554474249407e-05, + "loss": 1.6885, + "step": 11834 + }, + { + "epoch": 0.6596622261858314, + "grad_norm": 0.5758154988288879, + "learning_rate": 2.677566869123771e-05, + "loss": 1.7058, + "step": 11835 + }, + { + "epoch": 0.6597179644389944, + "grad_norm": 0.5790137648582458, + "learning_rate": 2.676778364476642e-05, + "loss": 1.6399, + "step": 11836 + }, + { + "epoch": 0.6597737026921576, + "grad_norm": 0.548075258731842, + "learning_rate": 2.6759899335085602e-05, + "loss": 1.6838, + "step": 11837 + }, + { + "epoch": 0.6598294409453208, + "grad_norm": 0.60141521692276, + "learning_rate": 2.6752015762445254e-05, + "loss": 1.7896, + "step": 11838 + }, + { + "epoch": 0.6598851791984839, + "grad_norm": 0.4708482623100281, + "learning_rate": 2.674413292709542e-05, + "loss": 1.2567, + "step": 11839 + }, + { + "epoch": 0.6599409174516471, + "grad_norm": 0.5700356960296631, + "learning_rate": 2.6736250829286103e-05, + "loss": 1.5649, + "step": 11840 + }, + { + "epoch": 0.6599966557048103, + "grad_norm": 0.5416743755340576, + "learning_rate": 2.6728369469267266e-05, + "loss": 1.5569, + "step": 11841 + }, + { + "epoch": 0.6600523939579733, + "grad_norm": 0.5961542129516602, + "learning_rate": 2.6720488847288873e-05, + "loss": 1.534, + "step": 11842 + }, + { + "epoch": 0.6601081322111365, + "grad_norm": 0.5858752727508545, + "learning_rate": 2.6712608963600843e-05, + "loss": 1.722, + "step": 11843 + }, + { + "epoch": 0.6601638704642997, + "grad_norm": 0.564729630947113, + "learning_rate": 2.67047298184531e-05, + "loss": 1.5489, + "step": 11844 + }, + { + "epoch": 0.6602196087174628, + "grad_norm": 0.6010147929191589, + "learning_rate": 2.6696851412095492e-05, + "loss": 1.8072, + "step": 11845 + }, + { + "epoch": 0.660275346970626, + "grad_norm": 0.5355246663093567, + "learning_rate": 2.6688973744777884e-05, + "loss": 1.454, + "step": 11846 + }, + { + "epoch": 0.6603310852237891, + "grad_norm": 0.5350586175918579, + "learning_rate": 2.6681096816750117e-05, + "loss": 1.663, + "step": 11847 + }, + { + "epoch": 0.6603868234769522, + "grad_norm": 0.5176247358322144, + "learning_rate": 2.6673220628262e-05, + "loss": 1.4612, + "step": 11848 + }, + { + "epoch": 0.6604425617301154, + "grad_norm": 0.5709378123283386, + "learning_rate": 2.6665345179563345e-05, + "loss": 1.5046, + "step": 11849 + }, + { + "epoch": 0.6604982999832785, + "grad_norm": 0.5571310520172119, + "learning_rate": 2.6657470470903845e-05, + "loss": 1.7277, + "step": 11850 + }, + { + "epoch": 0.6605540382364417, + "grad_norm": 0.5337514281272888, + "learning_rate": 2.6649596502533323e-05, + "loss": 1.6117, + "step": 11851 + }, + { + "epoch": 0.6606097764896048, + "grad_norm": 0.5532556772232056, + "learning_rate": 2.6641723274701447e-05, + "loss": 1.7025, + "step": 11852 + }, + { + "epoch": 0.6606655147427679, + "grad_norm": 0.49335777759552, + "learning_rate": 2.6633850787657915e-05, + "loss": 1.3906, + "step": 11853 + }, + { + "epoch": 0.6607212529959311, + "grad_norm": 0.5451174974441528, + "learning_rate": 2.6625979041652406e-05, + "loss": 1.721, + "step": 11854 + }, + { + "epoch": 0.6607769912490943, + "grad_norm": 0.5025902986526489, + "learning_rate": 2.6618108036934554e-05, + "loss": 1.4738, + "step": 11855 + }, + { + "epoch": 0.6608327295022574, + "grad_norm": 0.5471557974815369, + "learning_rate": 2.6610237773754015e-05, + "loss": 1.6252, + "step": 11856 + }, + { + "epoch": 0.6608884677554205, + "grad_norm": 0.57525235414505, + "learning_rate": 2.6602368252360345e-05, + "loss": 1.6125, + "step": 11857 + }, + { + "epoch": 0.6609442060085837, + "grad_norm": 0.5472937226295471, + "learning_rate": 2.6594499473003125e-05, + "loss": 1.6452, + "step": 11858 + }, + { + "epoch": 0.6609999442617468, + "grad_norm": 0.5961613655090332, + "learning_rate": 2.658663143593193e-05, + "loss": 1.5554, + "step": 11859 + }, + { + "epoch": 0.66105568251491, + "grad_norm": 0.543452799320221, + "learning_rate": 2.6578764141396282e-05, + "loss": 1.6729, + "step": 11860 + }, + { + "epoch": 0.6611114207680732, + "grad_norm": 0.5469802021980286, + "learning_rate": 2.6570897589645654e-05, + "loss": 1.6435, + "step": 11861 + }, + { + "epoch": 0.6611671590212362, + "grad_norm": 0.5711193680763245, + "learning_rate": 2.656303178092957e-05, + "loss": 1.6829, + "step": 11862 + }, + { + "epoch": 0.6612228972743994, + "grad_norm": 0.5289133787155151, + "learning_rate": 2.6555166715497492e-05, + "loss": 1.6514, + "step": 11863 + }, + { + "epoch": 0.6612786355275626, + "grad_norm": 0.5423325896263123, + "learning_rate": 2.6547302393598804e-05, + "loss": 1.6465, + "step": 11864 + }, + { + "epoch": 0.6613343737807257, + "grad_norm": 0.5673478245735168, + "learning_rate": 2.6539438815482955e-05, + "loss": 1.6402, + "step": 11865 + }, + { + "epoch": 0.6613901120338889, + "grad_norm": 0.5566899180412292, + "learning_rate": 2.653157598139932e-05, + "loss": 1.6084, + "step": 11866 + }, + { + "epoch": 0.661445850287052, + "grad_norm": 0.5686150193214417, + "learning_rate": 2.652371389159727e-05, + "loss": 1.846, + "step": 11867 + }, + { + "epoch": 0.6615015885402151, + "grad_norm": 0.5833027362823486, + "learning_rate": 2.6515852546326124e-05, + "loss": 1.8253, + "step": 11868 + }, + { + "epoch": 0.6615573267933783, + "grad_norm": 0.5765178799629211, + "learning_rate": 2.6507991945835227e-05, + "loss": 1.7235, + "step": 11869 + }, + { + "epoch": 0.6616130650465415, + "grad_norm": 0.558733344078064, + "learning_rate": 2.6500132090373873e-05, + "loss": 1.6533, + "step": 11870 + }, + { + "epoch": 0.6616688032997046, + "grad_norm": 0.5753670334815979, + "learning_rate": 2.649227298019129e-05, + "loss": 1.711, + "step": 11871 + }, + { + "epoch": 0.6617245415528678, + "grad_norm": 0.5563479065895081, + "learning_rate": 2.6484414615536757e-05, + "loss": 1.6361, + "step": 11872 + }, + { + "epoch": 0.6617802798060308, + "grad_norm": 0.5799263715744019, + "learning_rate": 2.6476556996659484e-05, + "loss": 1.6981, + "step": 11873 + }, + { + "epoch": 0.661836018059194, + "grad_norm": 0.5460615754127502, + "learning_rate": 2.646870012380867e-05, + "loss": 1.5684, + "step": 11874 + }, + { + "epoch": 0.6618917563123572, + "grad_norm": 0.5564395189285278, + "learning_rate": 2.646084399723351e-05, + "loss": 1.5542, + "step": 11875 + }, + { + "epoch": 0.6619474945655203, + "grad_norm": 0.5553494691848755, + "learning_rate": 2.6452988617183106e-05, + "loss": 1.7904, + "step": 11876 + }, + { + "epoch": 0.6620032328186835, + "grad_norm": 0.557140052318573, + "learning_rate": 2.6445133983906643e-05, + "loss": 1.607, + "step": 11877 + }, + { + "epoch": 0.6620589710718466, + "grad_norm": 0.63083416223526, + "learning_rate": 2.643728009765318e-05, + "loss": 1.6927, + "step": 11878 + }, + { + "epoch": 0.6621147093250097, + "grad_norm": 0.5608395934104919, + "learning_rate": 2.642942695867181e-05, + "loss": 1.7663, + "step": 11879 + }, + { + "epoch": 0.6621704475781729, + "grad_norm": 0.603378176689148, + "learning_rate": 2.6421574567211595e-05, + "loss": 1.7458, + "step": 11880 + }, + { + "epoch": 0.6622261858313361, + "grad_norm": 0.5721191167831421, + "learning_rate": 2.6413722923521555e-05, + "loss": 1.6295, + "step": 11881 + }, + { + "epoch": 0.6622819240844992, + "grad_norm": 0.5742847919464111, + "learning_rate": 2.6405872027850732e-05, + "loss": 1.5865, + "step": 11882 + }, + { + "epoch": 0.6623376623376623, + "grad_norm": 0.593904972076416, + "learning_rate": 2.6398021880448066e-05, + "loss": 1.6666, + "step": 11883 + }, + { + "epoch": 0.6623934005908255, + "grad_norm": 0.5501095056533813, + "learning_rate": 2.6390172481562537e-05, + "loss": 1.7405, + "step": 11884 + }, + { + "epoch": 0.6624491388439886, + "grad_norm": 0.5565217733383179, + "learning_rate": 2.6382323831443078e-05, + "loss": 1.6778, + "step": 11885 + }, + { + "epoch": 0.6625048770971518, + "grad_norm": 0.5937246680259705, + "learning_rate": 2.6374475930338625e-05, + "loss": 1.6827, + "step": 11886 + }, + { + "epoch": 0.662560615350315, + "grad_norm": 0.6125547289848328, + "learning_rate": 2.6366628778498017e-05, + "loss": 1.8122, + "step": 11887 + }, + { + "epoch": 0.662616353603478, + "grad_norm": 0.568310022354126, + "learning_rate": 2.6358782376170164e-05, + "loss": 1.724, + "step": 11888 + }, + { + "epoch": 0.6626720918566412, + "grad_norm": 0.5387205481529236, + "learning_rate": 2.6350936723603923e-05, + "loss": 1.5148, + "step": 11889 + }, + { + "epoch": 0.6627278301098044, + "grad_norm": 0.5455870032310486, + "learning_rate": 2.634309182104806e-05, + "loss": 1.7194, + "step": 11890 + }, + { + "epoch": 0.6627835683629675, + "grad_norm": 0.5351374745368958, + "learning_rate": 2.63352476687514e-05, + "loss": 1.667, + "step": 11891 + }, + { + "epoch": 0.6628393066161307, + "grad_norm": 0.5790825486183167, + "learning_rate": 2.6327404266962707e-05, + "loss": 1.6988, + "step": 11892 + }, + { + "epoch": 0.6628950448692938, + "grad_norm": 0.5976444482803345, + "learning_rate": 2.6319561615930732e-05, + "loss": 1.4099, + "step": 11893 + }, + { + "epoch": 0.6629507831224569, + "grad_norm": 0.5867549180984497, + "learning_rate": 2.6311719715904193e-05, + "loss": 1.7522, + "step": 11894 + }, + { + "epoch": 0.6630065213756201, + "grad_norm": 0.5726478099822998, + "learning_rate": 2.630387856713179e-05, + "loss": 1.5786, + "step": 11895 + }, + { + "epoch": 0.6630622596287832, + "grad_norm": 0.5656641721725464, + "learning_rate": 2.6296038169862226e-05, + "loss": 1.5653, + "step": 11896 + }, + { + "epoch": 0.6631179978819464, + "grad_norm": 0.5478425025939941, + "learning_rate": 2.6288198524344106e-05, + "loss": 1.6283, + "step": 11897 + }, + { + "epoch": 0.6631737361351095, + "grad_norm": 0.6097078919410706, + "learning_rate": 2.6280359630826078e-05, + "loss": 1.6296, + "step": 11898 + }, + { + "epoch": 0.6632294743882726, + "grad_norm": 0.5414223074913025, + "learning_rate": 2.6272521489556746e-05, + "loss": 1.5074, + "step": 11899 + }, + { + "epoch": 0.6632852126414358, + "grad_norm": 0.5565434694290161, + "learning_rate": 2.62646841007847e-05, + "loss": 1.4944, + "step": 11900 + }, + { + "epoch": 0.663340950894599, + "grad_norm": 0.5831652879714966, + "learning_rate": 2.6256847464758495e-05, + "loss": 1.7095, + "step": 11901 + }, + { + "epoch": 0.6633966891477621, + "grad_norm": 0.5691834092140198, + "learning_rate": 2.6249011581726625e-05, + "loss": 1.6111, + "step": 11902 + }, + { + "epoch": 0.6634524274009252, + "grad_norm": 0.5959990620613098, + "learning_rate": 2.6241176451937664e-05, + "loss": 1.7611, + "step": 11903 + }, + { + "epoch": 0.6635081656540884, + "grad_norm": 0.5408827662467957, + "learning_rate": 2.623334207564005e-05, + "loss": 1.6979, + "step": 11904 + }, + { + "epoch": 0.6635639039072515, + "grad_norm": 0.5845001935958862, + "learning_rate": 2.6225508453082247e-05, + "loss": 1.8504, + "step": 11905 + }, + { + "epoch": 0.6636196421604147, + "grad_norm": 0.5302397012710571, + "learning_rate": 2.6217675584512713e-05, + "loss": 1.4962, + "step": 11906 + }, + { + "epoch": 0.6636753804135779, + "grad_norm": 0.5679298043251038, + "learning_rate": 2.620984347017984e-05, + "loss": 1.5897, + "step": 11907 + }, + { + "epoch": 0.663731118666741, + "grad_norm": 0.5457496643066406, + "learning_rate": 2.6202012110332046e-05, + "loss": 1.565, + "step": 11908 + }, + { + "epoch": 0.6637868569199041, + "grad_norm": 0.5777455568313599, + "learning_rate": 2.619418150521766e-05, + "loss": 1.8616, + "step": 11909 + }, + { + "epoch": 0.6638425951730673, + "grad_norm": 0.5581088066101074, + "learning_rate": 2.6186351655085036e-05, + "loss": 1.7539, + "step": 11910 + }, + { + "epoch": 0.6638983334262304, + "grad_norm": 0.5956060886383057, + "learning_rate": 2.6178522560182496e-05, + "loss": 1.5453, + "step": 11911 + }, + { + "epoch": 0.6639540716793936, + "grad_norm": 0.5325225591659546, + "learning_rate": 2.6170694220758352e-05, + "loss": 1.6533, + "step": 11912 + }, + { + "epoch": 0.6640098099325568, + "grad_norm": 0.523888885974884, + "learning_rate": 2.6162866637060812e-05, + "loss": 1.5123, + "step": 11913 + }, + { + "epoch": 0.6640655481857198, + "grad_norm": 0.5633407235145569, + "learning_rate": 2.6155039809338178e-05, + "loss": 1.7104, + "step": 11914 + }, + { + "epoch": 0.664121286438883, + "grad_norm": 0.5729668736457825, + "learning_rate": 2.6147213737838682e-05, + "loss": 1.6117, + "step": 11915 + }, + { + "epoch": 0.6641770246920462, + "grad_norm": 0.6129339933395386, + "learning_rate": 2.6139388422810468e-05, + "loss": 1.9683, + "step": 11916 + }, + { + "epoch": 0.6642327629452093, + "grad_norm": 0.5193238854408264, + "learning_rate": 2.613156386450174e-05, + "loss": 1.5635, + "step": 11917 + }, + { + "epoch": 0.6642885011983725, + "grad_norm": 0.5500721335411072, + "learning_rate": 2.6123740063160646e-05, + "loss": 1.6013, + "step": 11918 + }, + { + "epoch": 0.6643442394515355, + "grad_norm": 0.5810501575469971, + "learning_rate": 2.6115917019035326e-05, + "loss": 1.6931, + "step": 11919 + }, + { + "epoch": 0.6643999777046987, + "grad_norm": 0.5327263474464417, + "learning_rate": 2.6108094732373823e-05, + "loss": 1.397, + "step": 11920 + }, + { + "epoch": 0.6644557159578619, + "grad_norm": 0.5560159087181091, + "learning_rate": 2.610027320342428e-05, + "loss": 1.5599, + "step": 11921 + }, + { + "epoch": 0.664511454211025, + "grad_norm": 0.5466412901878357, + "learning_rate": 2.6092452432434745e-05, + "loss": 1.5155, + "step": 11922 + }, + { + "epoch": 0.6645671924641882, + "grad_norm": 0.5591964721679688, + "learning_rate": 2.6084632419653206e-05, + "loss": 1.6088, + "step": 11923 + }, + { + "epoch": 0.6646229307173513, + "grad_norm": 0.5819532871246338, + "learning_rate": 2.6076813165327692e-05, + "loss": 1.6295, + "step": 11924 + }, + { + "epoch": 0.6646786689705144, + "grad_norm": 0.5858190059661865, + "learning_rate": 2.606899466970618e-05, + "loss": 1.7028, + "step": 11925 + }, + { + "epoch": 0.6647344072236776, + "grad_norm": 0.593717634677887, + "learning_rate": 2.6061176933036636e-05, + "loss": 1.7271, + "step": 11926 + }, + { + "epoch": 0.6647901454768408, + "grad_norm": 0.5807863473892212, + "learning_rate": 2.6053359955566997e-05, + "loss": 1.6711, + "step": 11927 + }, + { + "epoch": 0.6648458837300039, + "grad_norm": 0.5966163873672485, + "learning_rate": 2.604554373754513e-05, + "loss": 1.6863, + "step": 11928 + }, + { + "epoch": 0.664901621983167, + "grad_norm": 0.6047829389572144, + "learning_rate": 2.6037728279218986e-05, + "loss": 1.6041, + "step": 11929 + }, + { + "epoch": 0.6649573602363302, + "grad_norm": 0.5634847283363342, + "learning_rate": 2.6029913580836372e-05, + "loss": 1.5647, + "step": 11930 + }, + { + "epoch": 0.6650130984894933, + "grad_norm": 0.5834475159645081, + "learning_rate": 2.6022099642645147e-05, + "loss": 1.489, + "step": 11931 + }, + { + "epoch": 0.6650688367426565, + "grad_norm": 0.6043350100517273, + "learning_rate": 2.6014286464893116e-05, + "loss": 1.7557, + "step": 11932 + }, + { + "epoch": 0.6651245749958197, + "grad_norm": 0.5589107871055603, + "learning_rate": 2.600647404782808e-05, + "loss": 1.5685, + "step": 11933 + }, + { + "epoch": 0.6651803132489827, + "grad_norm": 0.5879253149032593, + "learning_rate": 2.5998662391697805e-05, + "loss": 1.8277, + "step": 11934 + }, + { + "epoch": 0.6652360515021459, + "grad_norm": 0.6046743988990784, + "learning_rate": 2.599085149674999e-05, + "loss": 1.7789, + "step": 11935 + }, + { + "epoch": 0.6652917897553091, + "grad_norm": 0.5767287611961365, + "learning_rate": 2.5983041363232418e-05, + "loss": 1.8216, + "step": 11936 + }, + { + "epoch": 0.6653475280084722, + "grad_norm": 0.627777636051178, + "learning_rate": 2.5975231991392725e-05, + "loss": 1.7176, + "step": 11937 + }, + { + "epoch": 0.6654032662616354, + "grad_norm": 0.5515438318252563, + "learning_rate": 2.5967423381478616e-05, + "loss": 1.656, + "step": 11938 + }, + { + "epoch": 0.6654590045147986, + "grad_norm": 0.5708695650100708, + "learning_rate": 2.5959615533737685e-05, + "loss": 1.4709, + "step": 11939 + }, + { + "epoch": 0.6655147427679616, + "grad_norm": 0.5571765899658203, + "learning_rate": 2.5951808448417602e-05, + "loss": 1.6504, + "step": 11940 + }, + { + "epoch": 0.6655704810211248, + "grad_norm": 0.5637586712837219, + "learning_rate": 2.5944002125765964e-05, + "loss": 1.5995, + "step": 11941 + }, + { + "epoch": 0.6656262192742879, + "grad_norm": 0.5670571327209473, + "learning_rate": 2.5936196566030302e-05, + "loss": 1.8318, + "step": 11942 + }, + { + "epoch": 0.6656819575274511, + "grad_norm": 0.5566664338111877, + "learning_rate": 2.5928391769458183e-05, + "loss": 1.5158, + "step": 11943 + }, + { + "epoch": 0.6657376957806143, + "grad_norm": 0.5441628694534302, + "learning_rate": 2.592058773629713e-05, + "loss": 1.5724, + "step": 11944 + }, + { + "epoch": 0.6657934340337773, + "grad_norm": 0.5653737187385559, + "learning_rate": 2.591278446679466e-05, + "loss": 1.6876, + "step": 11945 + }, + { + "epoch": 0.6658491722869405, + "grad_norm": 0.554476797580719, + "learning_rate": 2.5904981961198187e-05, + "loss": 1.6439, + "step": 11946 + }, + { + "epoch": 0.6659049105401037, + "grad_norm": 0.5171441435813904, + "learning_rate": 2.5897180219755223e-05, + "loss": 1.4966, + "step": 11947 + }, + { + "epoch": 0.6659606487932668, + "grad_norm": 0.5593156814575195, + "learning_rate": 2.5889379242713197e-05, + "loss": 1.6051, + "step": 11948 + }, + { + "epoch": 0.66601638704643, + "grad_norm": 0.5688751339912415, + "learning_rate": 2.588157903031947e-05, + "loss": 1.768, + "step": 11949 + }, + { + "epoch": 0.6660721252995931, + "grad_norm": 0.5453287959098816, + "learning_rate": 2.5873779582821428e-05, + "loss": 1.6705, + "step": 11950 + }, + { + "epoch": 0.6661278635527562, + "grad_norm": 0.5424460172653198, + "learning_rate": 2.5865980900466436e-05, + "loss": 1.7035, + "step": 11951 + }, + { + "epoch": 0.6661836018059194, + "grad_norm": 0.5378473997116089, + "learning_rate": 2.5858182983501817e-05, + "loss": 1.6159, + "step": 11952 + }, + { + "epoch": 0.6662393400590826, + "grad_norm": 0.5400096774101257, + "learning_rate": 2.5850385832174896e-05, + "loss": 1.5236, + "step": 11953 + }, + { + "epoch": 0.6662950783122457, + "grad_norm": 0.5049753189086914, + "learning_rate": 2.58425894467329e-05, + "loss": 1.5456, + "step": 11954 + }, + { + "epoch": 0.6663508165654088, + "grad_norm": 0.6285840272903442, + "learning_rate": 2.5834793827423155e-05, + "loss": 1.8465, + "step": 11955 + }, + { + "epoch": 0.666406554818572, + "grad_norm": 0.5433966517448425, + "learning_rate": 2.582699897449284e-05, + "loss": 1.7157, + "step": 11956 + }, + { + "epoch": 0.6664622930717351, + "grad_norm": 0.5678963661193848, + "learning_rate": 2.5819204888189173e-05, + "loss": 1.5398, + "step": 11957 + }, + { + "epoch": 0.6665180313248983, + "grad_norm": 0.5653471350669861, + "learning_rate": 2.5811411568759346e-05, + "loss": 1.4759, + "step": 11958 + }, + { + "epoch": 0.6665737695780615, + "grad_norm": 0.5493046045303345, + "learning_rate": 2.5803619016450518e-05, + "loss": 1.6772, + "step": 11959 + }, + { + "epoch": 0.6666295078312245, + "grad_norm": 0.5423870086669922, + "learning_rate": 2.579582723150984e-05, + "loss": 1.6816, + "step": 11960 + }, + { + "epoch": 0.6666852460843877, + "grad_norm": 0.5807955861091614, + "learning_rate": 2.578803621418436e-05, + "loss": 1.7645, + "step": 11961 + }, + { + "epoch": 0.6667409843375509, + "grad_norm": 0.5688575506210327, + "learning_rate": 2.5780245964721244e-05, + "loss": 1.6954, + "step": 11962 + }, + { + "epoch": 0.666796722590714, + "grad_norm": 0.500732958316803, + "learning_rate": 2.5772456483367497e-05, + "loss": 1.4321, + "step": 11963 + }, + { + "epoch": 0.6668524608438772, + "grad_norm": 0.5536085367202759, + "learning_rate": 2.5764667770370195e-05, + "loss": 1.5843, + "step": 11964 + }, + { + "epoch": 0.6669081990970402, + "grad_norm": 0.5987438559532166, + "learning_rate": 2.5756879825976287e-05, + "loss": 1.6635, + "step": 11965 + }, + { + "epoch": 0.6669639373502034, + "grad_norm": 0.5400751233100891, + "learning_rate": 2.5749092650432828e-05, + "loss": 1.5231, + "step": 11966 + }, + { + "epoch": 0.6670196756033666, + "grad_norm": 0.5186768770217896, + "learning_rate": 2.5741306243986773e-05, + "loss": 1.5618, + "step": 11967 + }, + { + "epoch": 0.6670754138565297, + "grad_norm": 0.5389026403427124, + "learning_rate": 2.5733520606885024e-05, + "loss": 1.6768, + "step": 11968 + }, + { + "epoch": 0.6671311521096929, + "grad_norm": 0.6083009839057922, + "learning_rate": 2.5725735739374523e-05, + "loss": 1.9559, + "step": 11969 + }, + { + "epoch": 0.667186890362856, + "grad_norm": 0.5317343473434448, + "learning_rate": 2.5717951641702155e-05, + "loss": 1.1981, + "step": 11970 + }, + { + "epoch": 0.6672426286160191, + "grad_norm": 0.5438907742500305, + "learning_rate": 2.5710168314114802e-05, + "loss": 1.5034, + "step": 11971 + }, + { + "epoch": 0.6672983668691823, + "grad_norm": 0.5268614888191223, + "learning_rate": 2.570238575685926e-05, + "loss": 1.5647, + "step": 11972 + }, + { + "epoch": 0.6673541051223455, + "grad_norm": 0.5814064145088196, + "learning_rate": 2.5694603970182384e-05, + "loss": 1.9909, + "step": 11973 + }, + { + "epoch": 0.6674098433755086, + "grad_norm": 0.5964480638504028, + "learning_rate": 2.568682295433099e-05, + "loss": 1.7471, + "step": 11974 + }, + { + "epoch": 0.6674655816286718, + "grad_norm": 0.5062904357910156, + "learning_rate": 2.5679042709551793e-05, + "loss": 1.376, + "step": 11975 + }, + { + "epoch": 0.6675213198818349, + "grad_norm": 0.5355701446533203, + "learning_rate": 2.5671263236091557e-05, + "loss": 1.6064, + "step": 11976 + }, + { + "epoch": 0.667577058134998, + "grad_norm": 0.5466346144676208, + "learning_rate": 2.5663484534197014e-05, + "loss": 1.6715, + "step": 11977 + }, + { + "epoch": 0.6676327963881612, + "grad_norm": 0.5518960952758789, + "learning_rate": 2.5655706604114844e-05, + "loss": 1.5901, + "step": 11978 + }, + { + "epoch": 0.6676885346413244, + "grad_norm": 0.547706127166748, + "learning_rate": 2.5647929446091746e-05, + "loss": 1.5659, + "step": 11979 + }, + { + "epoch": 0.6677442728944875, + "grad_norm": 0.5523556470870972, + "learning_rate": 2.5640153060374293e-05, + "loss": 1.7662, + "step": 11980 + }, + { + "epoch": 0.6678000111476506, + "grad_norm": 0.5731891989707947, + "learning_rate": 2.563237744720921e-05, + "loss": 1.5056, + "step": 11981 + }, + { + "epoch": 0.6678557494008138, + "grad_norm": 0.5777943134307861, + "learning_rate": 2.5624602606843017e-05, + "loss": 1.5221, + "step": 11982 + }, + { + "epoch": 0.6679114876539769, + "grad_norm": 0.5800961852073669, + "learning_rate": 2.561682853952231e-05, + "loss": 1.6958, + "step": 11983 + }, + { + "epoch": 0.6679672259071401, + "grad_norm": 0.5744274854660034, + "learning_rate": 2.560905524549364e-05, + "loss": 1.7868, + "step": 11984 + }, + { + "epoch": 0.6680229641603033, + "grad_norm": 0.5199480056762695, + "learning_rate": 2.5601282725003522e-05, + "loss": 1.3076, + "step": 11985 + }, + { + "epoch": 0.6680787024134663, + "grad_norm": 0.6389720439910889, + "learning_rate": 2.5593510978298486e-05, + "loss": 1.9535, + "step": 11986 + }, + { + "epoch": 0.6681344406666295, + "grad_norm": 0.5399093627929688, + "learning_rate": 2.5585740005624947e-05, + "loss": 1.5529, + "step": 11987 + }, + { + "epoch": 0.6681901789197926, + "grad_norm": 0.5350346565246582, + "learning_rate": 2.5577969807229422e-05, + "loss": 1.5102, + "step": 11988 + }, + { + "epoch": 0.6682459171729558, + "grad_norm": 0.5301445126533508, + "learning_rate": 2.557020038335829e-05, + "loss": 1.5665, + "step": 11989 + }, + { + "epoch": 0.668301655426119, + "grad_norm": 0.5629336833953857, + "learning_rate": 2.5562431734257987e-05, + "loss": 1.5837, + "step": 11990 + }, + { + "epoch": 0.668357393679282, + "grad_norm": 0.6423056125640869, + "learning_rate": 2.5554663860174823e-05, + "loss": 1.673, + "step": 11991 + }, + { + "epoch": 0.6684131319324452, + "grad_norm": 0.5791043639183044, + "learning_rate": 2.5546896761355216e-05, + "loss": 1.6438, + "step": 11992 + }, + { + "epoch": 0.6684688701856084, + "grad_norm": 0.5836037397384644, + "learning_rate": 2.5539130438045494e-05, + "loss": 1.6323, + "step": 11993 + }, + { + "epoch": 0.6685246084387715, + "grad_norm": 0.56341153383255, + "learning_rate": 2.5531364890491916e-05, + "loss": 1.6362, + "step": 11994 + }, + { + "epoch": 0.6685803466919347, + "grad_norm": 0.5776152014732361, + "learning_rate": 2.5523600118940784e-05, + "loss": 1.7689, + "step": 11995 + }, + { + "epoch": 0.6686360849450979, + "grad_norm": 0.5938311815261841, + "learning_rate": 2.551583612363835e-05, + "loss": 1.7699, + "step": 11996 + }, + { + "epoch": 0.6686918231982609, + "grad_norm": 0.5410308837890625, + "learning_rate": 2.550807290483086e-05, + "loss": 1.6291, + "step": 11997 + }, + { + "epoch": 0.6687475614514241, + "grad_norm": 0.5281055569648743, + "learning_rate": 2.5500310462764458e-05, + "loss": 1.4974, + "step": 11998 + }, + { + "epoch": 0.6688032997045873, + "grad_norm": 0.5797048211097717, + "learning_rate": 2.549254879768539e-05, + "loss": 1.742, + "step": 11999 + }, + { + "epoch": 0.6688590379577504, + "grad_norm": 0.5304363369941711, + "learning_rate": 2.54847879098398e-05, + "loss": 1.6044, + "step": 12000 + }, + { + "epoch": 0.6689147762109136, + "grad_norm": 0.5916433334350586, + "learning_rate": 2.5477027799473786e-05, + "loss": 1.6588, + "step": 12001 + }, + { + "epoch": 0.6689705144640767, + "grad_norm": 0.56605064868927, + "learning_rate": 2.5469268466833474e-05, + "loss": 1.5768, + "step": 12002 + }, + { + "epoch": 0.6690262527172398, + "grad_norm": 0.5318643450737, + "learning_rate": 2.5461509912164937e-05, + "loss": 1.7623, + "step": 12003 + }, + { + "epoch": 0.669081990970403, + "grad_norm": 0.5695320963859558, + "learning_rate": 2.5453752135714237e-05, + "loss": 1.6399, + "step": 12004 + }, + { + "epoch": 0.6691377292235662, + "grad_norm": 0.526165783405304, + "learning_rate": 2.5445995137727428e-05, + "loss": 1.6047, + "step": 12005 + }, + { + "epoch": 0.6691934674767293, + "grad_norm": 0.5636263489723206, + "learning_rate": 2.5438238918450453e-05, + "loss": 1.6891, + "step": 12006 + }, + { + "epoch": 0.6692492057298924, + "grad_norm": 0.6026769876480103, + "learning_rate": 2.5430483478129374e-05, + "loss": 1.6847, + "step": 12007 + }, + { + "epoch": 0.6693049439830556, + "grad_norm": 0.5717709064483643, + "learning_rate": 2.5422728817010088e-05, + "loss": 1.7936, + "step": 12008 + }, + { + "epoch": 0.6693606822362187, + "grad_norm": 0.5113479495048523, + "learning_rate": 2.5414974935338553e-05, + "loss": 1.5723, + "step": 12009 + }, + { + "epoch": 0.6694164204893819, + "grad_norm": 0.5642980337142944, + "learning_rate": 2.540722183336066e-05, + "loss": 1.9559, + "step": 12010 + }, + { + "epoch": 0.669472158742545, + "grad_norm": 0.5360389947891235, + "learning_rate": 2.5399469511322316e-05, + "loss": 1.5012, + "step": 12011 + }, + { + "epoch": 0.6695278969957081, + "grad_norm": 0.5451308488845825, + "learning_rate": 2.5391717969469387e-05, + "loss": 1.7371, + "step": 12012 + }, + { + "epoch": 0.6695836352488713, + "grad_norm": 0.5800293684005737, + "learning_rate": 2.5383967208047642e-05, + "loss": 1.5257, + "step": 12013 + }, + { + "epoch": 0.6696393735020344, + "grad_norm": 0.5658344030380249, + "learning_rate": 2.5376217227302985e-05, + "loss": 1.5169, + "step": 12014 + }, + { + "epoch": 0.6696951117551976, + "grad_norm": 0.5860779881477356, + "learning_rate": 2.5368468027481125e-05, + "loss": 1.763, + "step": 12015 + }, + { + "epoch": 0.6697508500083608, + "grad_norm": 0.5342041850090027, + "learning_rate": 2.5360719608827843e-05, + "loss": 1.5319, + "step": 12016 + }, + { + "epoch": 0.6698065882615238, + "grad_norm": 0.5477134585380554, + "learning_rate": 2.535297197158889e-05, + "loss": 1.5549, + "step": 12017 + }, + { + "epoch": 0.669862326514687, + "grad_norm": 0.5928038358688354, + "learning_rate": 2.5345225116009952e-05, + "loss": 1.6838, + "step": 12018 + }, + { + "epoch": 0.6699180647678502, + "grad_norm": 0.5327808260917664, + "learning_rate": 2.5337479042336755e-05, + "loss": 1.4308, + "step": 12019 + }, + { + "epoch": 0.6699738030210133, + "grad_norm": 0.61540687084198, + "learning_rate": 2.5329733750814903e-05, + "loss": 1.7362, + "step": 12020 + }, + { + "epoch": 0.6700295412741765, + "grad_norm": 0.5844860672950745, + "learning_rate": 2.532198924169006e-05, + "loss": 1.7953, + "step": 12021 + }, + { + "epoch": 0.6700852795273397, + "grad_norm": 0.6544490456581116, + "learning_rate": 2.531424551520784e-05, + "loss": 1.9502, + "step": 12022 + }, + { + "epoch": 0.6701410177805027, + "grad_norm": 0.5588658452033997, + "learning_rate": 2.5306502571613843e-05, + "loss": 1.5504, + "step": 12023 + }, + { + "epoch": 0.6701967560336659, + "grad_norm": 0.5695081949234009, + "learning_rate": 2.5298760411153567e-05, + "loss": 1.5688, + "step": 12024 + }, + { + "epoch": 0.6702524942868291, + "grad_norm": 0.5447390675544739, + "learning_rate": 2.5291019034072616e-05, + "loss": 1.6796, + "step": 12025 + }, + { + "epoch": 0.6703082325399922, + "grad_norm": 0.6449052095413208, + "learning_rate": 2.52832784406165e-05, + "loss": 1.8635, + "step": 12026 + }, + { + "epoch": 0.6703639707931554, + "grad_norm": 0.5398309230804443, + "learning_rate": 2.5275538631030658e-05, + "loss": 1.5262, + "step": 12027 + }, + { + "epoch": 0.6704197090463185, + "grad_norm": 0.5473873615264893, + "learning_rate": 2.5267799605560584e-05, + "loss": 1.7629, + "step": 12028 + }, + { + "epoch": 0.6704754472994816, + "grad_norm": 0.5728017687797546, + "learning_rate": 2.5260061364451703e-05, + "loss": 1.7794, + "step": 12029 + }, + { + "epoch": 0.6705311855526448, + "grad_norm": 0.5419506430625916, + "learning_rate": 2.5252323907949448e-05, + "loss": 1.5772, + "step": 12030 + }, + { + "epoch": 0.670586923805808, + "grad_norm": 0.5533862113952637, + "learning_rate": 2.5244587236299177e-05, + "loss": 1.7015, + "step": 12031 + }, + { + "epoch": 0.670642662058971, + "grad_norm": 0.5854989290237427, + "learning_rate": 2.5236851349746245e-05, + "loss": 1.5979, + "step": 12032 + }, + { + "epoch": 0.6706984003121342, + "grad_norm": 0.6313944458961487, + "learning_rate": 2.5229116248536044e-05, + "loss": 1.6631, + "step": 12033 + }, + { + "epoch": 0.6707541385652973, + "grad_norm": 0.5602930784225464, + "learning_rate": 2.5221381932913835e-05, + "loss": 1.5784, + "step": 12034 + }, + { + "epoch": 0.6708098768184605, + "grad_norm": 0.5706256628036499, + "learning_rate": 2.5213648403124918e-05, + "loss": 1.5644, + "step": 12035 + }, + { + "epoch": 0.6708656150716237, + "grad_norm": 0.6049339175224304, + "learning_rate": 2.520591565941456e-05, + "loss": 1.7091, + "step": 12036 + }, + { + "epoch": 0.6709213533247868, + "grad_norm": 0.49709540605545044, + "learning_rate": 2.5198183702028e-05, + "loss": 1.4581, + "step": 12037 + }, + { + "epoch": 0.6709770915779499, + "grad_norm": 0.5363261103630066, + "learning_rate": 2.5190452531210463e-05, + "loss": 1.4818, + "step": 12038 + }, + { + "epoch": 0.6710328298311131, + "grad_norm": 0.5210326910018921, + "learning_rate": 2.5182722147207088e-05, + "loss": 1.5246, + "step": 12039 + }, + { + "epoch": 0.6710885680842762, + "grad_norm": 0.5645127892494202, + "learning_rate": 2.517499255026311e-05, + "loss": 1.5696, + "step": 12040 + }, + { + "epoch": 0.6711443063374394, + "grad_norm": 0.5957170128822327, + "learning_rate": 2.5167263740623607e-05, + "loss": 1.4597, + "step": 12041 + }, + { + "epoch": 0.6712000445906026, + "grad_norm": 0.5939059853553772, + "learning_rate": 2.5159535718533717e-05, + "loss": 1.6307, + "step": 12042 + }, + { + "epoch": 0.6712557828437656, + "grad_norm": 0.6196640133857727, + "learning_rate": 2.5151808484238525e-05, + "loss": 1.6608, + "step": 12043 + }, + { + "epoch": 0.6713115210969288, + "grad_norm": 0.5694495439529419, + "learning_rate": 2.5144082037983085e-05, + "loss": 1.6391, + "step": 12044 + }, + { + "epoch": 0.671367259350092, + "grad_norm": 0.5964381098747253, + "learning_rate": 2.513635638001247e-05, + "loss": 1.6466, + "step": 12045 + }, + { + "epoch": 0.6714229976032551, + "grad_norm": 0.5447733402252197, + "learning_rate": 2.5128631510571643e-05, + "loss": 1.6352, + "step": 12046 + }, + { + "epoch": 0.6714787358564183, + "grad_norm": 0.5714775919914246, + "learning_rate": 2.5120907429905617e-05, + "loss": 1.6743, + "step": 12047 + }, + { + "epoch": 0.6715344741095814, + "grad_norm": 0.5910129547119141, + "learning_rate": 2.511318413825935e-05, + "loss": 1.7514, + "step": 12048 + }, + { + "epoch": 0.6715902123627445, + "grad_norm": 0.5670276284217834, + "learning_rate": 2.5105461635877797e-05, + "loss": 1.2842, + "step": 12049 + }, + { + "epoch": 0.6716459506159077, + "grad_norm": 0.5352841019630432, + "learning_rate": 2.509773992300582e-05, + "loss": 1.5662, + "step": 12050 + }, + { + "epoch": 0.6717016888690709, + "grad_norm": 0.5886231064796448, + "learning_rate": 2.5090018999888365e-05, + "loss": 1.7842, + "step": 12051 + }, + { + "epoch": 0.671757427122234, + "grad_norm": 0.5294016599655151, + "learning_rate": 2.508229886677029e-05, + "loss": 1.5996, + "step": 12052 + }, + { + "epoch": 0.6718131653753971, + "grad_norm": 0.5378506779670715, + "learning_rate": 2.507457952389639e-05, + "loss": 1.7818, + "step": 12053 + }, + { + "epoch": 0.6718689036285603, + "grad_norm": 0.5751243233680725, + "learning_rate": 2.506686097151151e-05, + "loss": 1.8029, + "step": 12054 + }, + { + "epoch": 0.6719246418817234, + "grad_norm": 0.6077497005462646, + "learning_rate": 2.5059143209860425e-05, + "loss": 1.8815, + "step": 12055 + }, + { + "epoch": 0.6719803801348866, + "grad_norm": 0.5650768876075745, + "learning_rate": 2.5051426239187918e-05, + "loss": 1.6726, + "step": 12056 + }, + { + "epoch": 0.6720361183880497, + "grad_norm": 0.5476177334785461, + "learning_rate": 2.5043710059738702e-05, + "loss": 1.5366, + "step": 12057 + }, + { + "epoch": 0.6720918566412128, + "grad_norm": 0.58171147108078, + "learning_rate": 2.503599467175747e-05, + "loss": 1.8958, + "step": 12058 + }, + { + "epoch": 0.672147594894376, + "grad_norm": 0.562774121761322, + "learning_rate": 2.5028280075488973e-05, + "loss": 1.7533, + "step": 12059 + }, + { + "epoch": 0.6722033331475391, + "grad_norm": 0.542335569858551, + "learning_rate": 2.5020566271177824e-05, + "loss": 1.608, + "step": 12060 + }, + { + "epoch": 0.6722590714007023, + "grad_norm": 0.5780958533287048, + "learning_rate": 2.501285325906867e-05, + "loss": 1.5929, + "step": 12061 + }, + { + "epoch": 0.6723148096538655, + "grad_norm": 0.553331196308136, + "learning_rate": 2.500514103940613e-05, + "loss": 1.7366, + "step": 12062 + }, + { + "epoch": 0.6723705479070285, + "grad_norm": 0.5768744349479675, + "learning_rate": 2.499742961243478e-05, + "loss": 1.9978, + "step": 12063 + }, + { + "epoch": 0.6724262861601917, + "grad_norm": 0.580155074596405, + "learning_rate": 2.4989718978399207e-05, + "loss": 1.6921, + "step": 12064 + }, + { + "epoch": 0.6724820244133549, + "grad_norm": 0.5232993364334106, + "learning_rate": 2.4982009137543894e-05, + "loss": 1.5997, + "step": 12065 + }, + { + "epoch": 0.672537762666518, + "grad_norm": 0.5684017539024353, + "learning_rate": 2.4974300090113422e-05, + "loss": 1.7996, + "step": 12066 + }, + { + "epoch": 0.6725935009196812, + "grad_norm": 0.5195304751396179, + "learning_rate": 2.4966591836352222e-05, + "loss": 1.5594, + "step": 12067 + }, + { + "epoch": 0.6726492391728444, + "grad_norm": 0.6149779558181763, + "learning_rate": 2.495888437650477e-05, + "loss": 1.7468, + "step": 12068 + }, + { + "epoch": 0.6727049774260074, + "grad_norm": 0.5937604904174805, + "learning_rate": 2.495117771081551e-05, + "loss": 1.8914, + "step": 12069 + }, + { + "epoch": 0.6727607156791706, + "grad_norm": 0.5604000091552734, + "learning_rate": 2.494347183952885e-05, + "loss": 1.6262, + "step": 12070 + }, + { + "epoch": 0.6728164539323338, + "grad_norm": 0.5344957113265991, + "learning_rate": 2.493576676288919e-05, + "loss": 1.511, + "step": 12071 + }, + { + "epoch": 0.6728721921854969, + "grad_norm": 0.5278180837631226, + "learning_rate": 2.4928062481140856e-05, + "loss": 1.4848, + "step": 12072 + }, + { + "epoch": 0.6729279304386601, + "grad_norm": 0.5628829598426819, + "learning_rate": 2.4920358994528198e-05, + "loss": 1.7329, + "step": 12073 + }, + { + "epoch": 0.6729836686918232, + "grad_norm": 0.6097002625465393, + "learning_rate": 2.4912656303295535e-05, + "loss": 1.7582, + "step": 12074 + }, + { + "epoch": 0.6730394069449863, + "grad_norm": 0.5815702080726624, + "learning_rate": 2.4904954407687153e-05, + "loss": 1.8324, + "step": 12075 + }, + { + "epoch": 0.6730951451981495, + "grad_norm": 0.5267353653907776, + "learning_rate": 2.4897253307947272e-05, + "loss": 1.5541, + "step": 12076 + }, + { + "epoch": 0.6731508834513127, + "grad_norm": 0.5497151613235474, + "learning_rate": 2.4889553004320177e-05, + "loss": 1.6382, + "step": 12077 + }, + { + "epoch": 0.6732066217044758, + "grad_norm": 0.5231025815010071, + "learning_rate": 2.488185349705007e-05, + "loss": 1.6186, + "step": 12078 + }, + { + "epoch": 0.673262359957639, + "grad_norm": 0.5598129630088806, + "learning_rate": 2.487415478638111e-05, + "loss": 1.6038, + "step": 12079 + }, + { + "epoch": 0.673318098210802, + "grad_norm": 0.5685511827468872, + "learning_rate": 2.4866456872557458e-05, + "loss": 1.6577, + "step": 12080 + }, + { + "epoch": 0.6733738364639652, + "grad_norm": 0.5880294442176819, + "learning_rate": 2.4858759755823258e-05, + "loss": 1.563, + "step": 12081 + }, + { + "epoch": 0.6734295747171284, + "grad_norm": 0.5600868463516235, + "learning_rate": 2.485106343642264e-05, + "loss": 1.6662, + "step": 12082 + }, + { + "epoch": 0.6734853129702915, + "grad_norm": 0.5627442002296448, + "learning_rate": 2.4843367914599637e-05, + "loss": 1.7301, + "step": 12083 + }, + { + "epoch": 0.6735410512234546, + "grad_norm": 0.5312789082527161, + "learning_rate": 2.4835673190598306e-05, + "loss": 1.4877, + "step": 12084 + }, + { + "epoch": 0.6735967894766178, + "grad_norm": 0.5254043936729431, + "learning_rate": 2.482797926466275e-05, + "loss": 1.6383, + "step": 12085 + }, + { + "epoch": 0.6736525277297809, + "grad_norm": 0.5575996041297913, + "learning_rate": 2.482028613703691e-05, + "loss": 1.7706, + "step": 12086 + }, + { + "epoch": 0.6737082659829441, + "grad_norm": 0.614926278591156, + "learning_rate": 2.481259380796478e-05, + "loss": 1.5105, + "step": 12087 + }, + { + "epoch": 0.6737640042361073, + "grad_norm": 0.5587199926376343, + "learning_rate": 2.480490227769032e-05, + "loss": 1.7255, + "step": 12088 + }, + { + "epoch": 0.6738197424892703, + "grad_norm": 0.5892671346664429, + "learning_rate": 2.4797211546457465e-05, + "loss": 1.7097, + "step": 12089 + }, + { + "epoch": 0.6738754807424335, + "grad_norm": 0.6368154883384705, + "learning_rate": 2.4789521614510143e-05, + "loss": 1.8793, + "step": 12090 + }, + { + "epoch": 0.6739312189955967, + "grad_norm": 0.5571451187133789, + "learning_rate": 2.478183248209216e-05, + "loss": 1.7683, + "step": 12091 + }, + { + "epoch": 0.6739869572487598, + "grad_norm": 0.5345653891563416, + "learning_rate": 2.4774144149447465e-05, + "loss": 1.3473, + "step": 12092 + }, + { + "epoch": 0.674042695501923, + "grad_norm": 0.649505078792572, + "learning_rate": 2.4766456616819818e-05, + "loss": 1.9293, + "step": 12093 + }, + { + "epoch": 0.6740984337550862, + "grad_norm": 0.5354018807411194, + "learning_rate": 2.4758769884453043e-05, + "loss": 1.5863, + "step": 12094 + }, + { + "epoch": 0.6741541720082492, + "grad_norm": 0.6080323457717896, + "learning_rate": 2.4751083952590926e-05, + "loss": 1.7642, + "step": 12095 + }, + { + "epoch": 0.6742099102614124, + "grad_norm": 0.5298397541046143, + "learning_rate": 2.474339882147721e-05, + "loss": 1.4794, + "step": 12096 + }, + { + "epoch": 0.6742656485145756, + "grad_norm": 0.5831593871116638, + "learning_rate": 2.4735714491355643e-05, + "loss": 1.584, + "step": 12097 + }, + { + "epoch": 0.6743213867677387, + "grad_norm": 0.6232854723930359, + "learning_rate": 2.47280309624699e-05, + "loss": 1.828, + "step": 12098 + }, + { + "epoch": 0.6743771250209019, + "grad_norm": 0.5947305560112, + "learning_rate": 2.4720348235063666e-05, + "loss": 1.7087, + "step": 12099 + }, + { + "epoch": 0.674432863274065, + "grad_norm": 0.5919405221939087, + "learning_rate": 2.4712666309380595e-05, + "loss": 1.7922, + "step": 12100 + }, + { + "epoch": 0.6744886015272281, + "grad_norm": 0.5434198975563049, + "learning_rate": 2.470498518566433e-05, + "loss": 1.3383, + "step": 12101 + }, + { + "epoch": 0.6745443397803913, + "grad_norm": 0.5246424674987793, + "learning_rate": 2.469730486415842e-05, + "loss": 1.4675, + "step": 12102 + }, + { + "epoch": 0.6746000780335544, + "grad_norm": 0.5592208504676819, + "learning_rate": 2.468962534510649e-05, + "loss": 1.7807, + "step": 12103 + }, + { + "epoch": 0.6746558162867176, + "grad_norm": 0.5231202244758606, + "learning_rate": 2.46819466287521e-05, + "loss": 1.5491, + "step": 12104 + }, + { + "epoch": 0.6747115545398807, + "grad_norm": 0.5387272834777832, + "learning_rate": 2.467426871533873e-05, + "loss": 1.7326, + "step": 12105 + }, + { + "epoch": 0.6747672927930438, + "grad_norm": 0.6031918525695801, + "learning_rate": 2.466659160510989e-05, + "loss": 1.7699, + "step": 12106 + }, + { + "epoch": 0.674823031046207, + "grad_norm": 0.548579752445221, + "learning_rate": 2.4658915298309066e-05, + "loss": 1.7571, + "step": 12107 + }, + { + "epoch": 0.6748787692993702, + "grad_norm": 0.5778599381446838, + "learning_rate": 2.4651239795179713e-05, + "loss": 1.636, + "step": 12108 + }, + { + "epoch": 0.6749345075525333, + "grad_norm": 0.5563526153564453, + "learning_rate": 2.4643565095965204e-05, + "loss": 1.4918, + "step": 12109 + }, + { + "epoch": 0.6749902458056964, + "grad_norm": 0.5569801330566406, + "learning_rate": 2.4635891200908996e-05, + "loss": 1.6423, + "step": 12110 + }, + { + "epoch": 0.6750459840588596, + "grad_norm": 0.546291172504425, + "learning_rate": 2.4628218110254452e-05, + "loss": 1.644, + "step": 12111 + }, + { + "epoch": 0.6751017223120227, + "grad_norm": 0.5411151051521301, + "learning_rate": 2.462054582424488e-05, + "loss": 1.5569, + "step": 12112 + }, + { + "epoch": 0.6751574605651859, + "grad_norm": 0.5745245218276978, + "learning_rate": 2.4612874343123626e-05, + "loss": 1.5434, + "step": 12113 + }, + { + "epoch": 0.6752131988183491, + "grad_norm": 0.5502985715866089, + "learning_rate": 2.460520366713398e-05, + "loss": 1.6833, + "step": 12114 + }, + { + "epoch": 0.6752689370715121, + "grad_norm": 0.6116489768028259, + "learning_rate": 2.4597533796519206e-05, + "loss": 1.7659, + "step": 12115 + }, + { + "epoch": 0.6753246753246753, + "grad_norm": 0.5902003049850464, + "learning_rate": 2.4589864731522578e-05, + "loss": 1.6773, + "step": 12116 + }, + { + "epoch": 0.6753804135778385, + "grad_norm": 0.7062128186225891, + "learning_rate": 2.4582196472387255e-05, + "loss": 1.7786, + "step": 12117 + }, + { + "epoch": 0.6754361518310016, + "grad_norm": 0.5624451637268066, + "learning_rate": 2.4574529019356494e-05, + "loss": 1.7779, + "step": 12118 + }, + { + "epoch": 0.6754918900841648, + "grad_norm": 0.5526938438415527, + "learning_rate": 2.4566862372673415e-05, + "loss": 1.7638, + "step": 12119 + }, + { + "epoch": 0.675547628337328, + "grad_norm": 0.589867353439331, + "learning_rate": 2.4559196532581174e-05, + "loss": 1.6782, + "step": 12120 + }, + { + "epoch": 0.675603366590491, + "grad_norm": 0.5674148201942444, + "learning_rate": 2.4551531499322895e-05, + "loss": 1.5979, + "step": 12121 + }, + { + "epoch": 0.6756591048436542, + "grad_norm": 0.5661038756370544, + "learning_rate": 2.4543867273141658e-05, + "loss": 1.5279, + "step": 12122 + }, + { + "epoch": 0.6757148430968174, + "grad_norm": 0.5659511089324951, + "learning_rate": 2.4536203854280553e-05, + "loss": 1.5487, + "step": 12123 + }, + { + "epoch": 0.6757705813499805, + "grad_norm": 0.5999061465263367, + "learning_rate": 2.452854124298257e-05, + "loss": 1.6329, + "step": 12124 + }, + { + "epoch": 0.6758263196031437, + "grad_norm": 0.5986047983169556, + "learning_rate": 2.4520879439490763e-05, + "loss": 1.8838, + "step": 12125 + }, + { + "epoch": 0.6758820578563067, + "grad_norm": 0.6163796186447144, + "learning_rate": 2.45132184440481e-05, + "loss": 1.8276, + "step": 12126 + }, + { + "epoch": 0.6759377961094699, + "grad_norm": 0.6057443618774414, + "learning_rate": 2.4505558256897564e-05, + "loss": 1.748, + "step": 12127 + }, + { + "epoch": 0.6759935343626331, + "grad_norm": 0.5554170608520508, + "learning_rate": 2.449789887828205e-05, + "loss": 1.5513, + "step": 12128 + }, + { + "epoch": 0.6760492726157962, + "grad_norm": 0.5506255030632019, + "learning_rate": 2.4490240308444507e-05, + "loss": 1.5345, + "step": 12129 + }, + { + "epoch": 0.6761050108689594, + "grad_norm": 0.5533109307289124, + "learning_rate": 2.448258254762783e-05, + "loss": 1.754, + "step": 12130 + }, + { + "epoch": 0.6761607491221225, + "grad_norm": 0.5812035202980042, + "learning_rate": 2.447492559607484e-05, + "loss": 1.5279, + "step": 12131 + }, + { + "epoch": 0.6762164873752856, + "grad_norm": 0.5917302370071411, + "learning_rate": 2.4467269454028386e-05, + "loss": 1.8167, + "step": 12132 + }, + { + "epoch": 0.6762722256284488, + "grad_norm": 0.5987018346786499, + "learning_rate": 2.4459614121731283e-05, + "loss": 1.6938, + "step": 12133 + }, + { + "epoch": 0.676327963881612, + "grad_norm": 0.5785610675811768, + "learning_rate": 2.445195959942632e-05, + "loss": 1.6087, + "step": 12134 + }, + { + "epoch": 0.6763837021347751, + "grad_norm": 0.5947317481040955, + "learning_rate": 2.4444305887356218e-05, + "loss": 1.8278, + "step": 12135 + }, + { + "epoch": 0.6764394403879382, + "grad_norm": 0.562552273273468, + "learning_rate": 2.4436652985763742e-05, + "loss": 1.6288, + "step": 12136 + }, + { + "epoch": 0.6764951786411014, + "grad_norm": 0.5087525248527527, + "learning_rate": 2.4429000894891606e-05, + "loss": 1.4703, + "step": 12137 + }, + { + "epoch": 0.6765509168942645, + "grad_norm": 0.523859977722168, + "learning_rate": 2.4421349614982464e-05, + "loss": 1.435, + "step": 12138 + }, + { + "epoch": 0.6766066551474277, + "grad_norm": 0.5445376038551331, + "learning_rate": 2.441369914627897e-05, + "loss": 1.5009, + "step": 12139 + }, + { + "epoch": 0.6766623934005909, + "grad_norm": 0.555959939956665, + "learning_rate": 2.4406049489023763e-05, + "loss": 1.6002, + "step": 12140 + }, + { + "epoch": 0.6767181316537539, + "grad_norm": 0.6597177982330322, + "learning_rate": 2.439840064345944e-05, + "loss": 2.0263, + "step": 12141 + }, + { + "epoch": 0.6767738699069171, + "grad_norm": 0.5682998299598694, + "learning_rate": 2.4390752609828603e-05, + "loss": 1.5754, + "step": 12142 + }, + { + "epoch": 0.6768296081600803, + "grad_norm": 0.5617828369140625, + "learning_rate": 2.4383105388373745e-05, + "loss": 1.6967, + "step": 12143 + }, + { + "epoch": 0.6768853464132434, + "grad_norm": 0.544691801071167, + "learning_rate": 2.4375458979337463e-05, + "loss": 1.4722, + "step": 12144 + }, + { + "epoch": 0.6769410846664066, + "grad_norm": 0.5128159523010254, + "learning_rate": 2.4367813382962203e-05, + "loss": 1.567, + "step": 12145 + }, + { + "epoch": 0.6769968229195698, + "grad_norm": 0.5488656163215637, + "learning_rate": 2.436016859949046e-05, + "loss": 1.7543, + "step": 12146 + }, + { + "epoch": 0.6770525611727328, + "grad_norm": 0.5271493196487427, + "learning_rate": 2.435252462916467e-05, + "loss": 1.5287, + "step": 12147 + }, + { + "epoch": 0.677108299425896, + "grad_norm": 0.5668809413909912, + "learning_rate": 2.4344881472227264e-05, + "loss": 1.6324, + "step": 12148 + }, + { + "epoch": 0.6771640376790591, + "grad_norm": 0.6095489263534546, + "learning_rate": 2.4337239128920662e-05, + "loss": 1.8157, + "step": 12149 + }, + { + "epoch": 0.6772197759322223, + "grad_norm": 0.5673229098320007, + "learning_rate": 2.4329597599487192e-05, + "loss": 1.7171, + "step": 12150 + }, + { + "epoch": 0.6772755141853855, + "grad_norm": 0.5574488043785095, + "learning_rate": 2.432195688416921e-05, + "loss": 1.816, + "step": 12151 + }, + { + "epoch": 0.6773312524385485, + "grad_norm": 0.5575489401817322, + "learning_rate": 2.431431698320905e-05, + "loss": 1.594, + "step": 12152 + }, + { + "epoch": 0.6773869906917117, + "grad_norm": 0.5522165894508362, + "learning_rate": 2.4306677896849018e-05, + "loss": 1.6131, + "step": 12153 + }, + { + "epoch": 0.6774427289448749, + "grad_norm": 0.5478757619857788, + "learning_rate": 2.4299039625331315e-05, + "loss": 1.5579, + "step": 12154 + }, + { + "epoch": 0.677498467198038, + "grad_norm": 0.5960223078727722, + "learning_rate": 2.4291402168898252e-05, + "loss": 1.7149, + "step": 12155 + }, + { + "epoch": 0.6775542054512012, + "grad_norm": 0.5895914435386658, + "learning_rate": 2.4283765527792034e-05, + "loss": 1.7342, + "step": 12156 + }, + { + "epoch": 0.6776099437043643, + "grad_norm": 0.5667082071304321, + "learning_rate": 2.4276129702254826e-05, + "loss": 1.5972, + "step": 12157 + }, + { + "epoch": 0.6776656819575274, + "grad_norm": 0.6155690550804138, + "learning_rate": 2.4268494692528798e-05, + "loss": 1.8824, + "step": 12158 + }, + { + "epoch": 0.6777214202106906, + "grad_norm": 0.5950416922569275, + "learning_rate": 2.4260860498856098e-05, + "loss": 1.6597, + "step": 12159 + }, + { + "epoch": 0.6777771584638538, + "grad_norm": 0.5567697882652283, + "learning_rate": 2.425322712147885e-05, + "loss": 1.5585, + "step": 12160 + }, + { + "epoch": 0.6778328967170169, + "grad_norm": 0.5798008441925049, + "learning_rate": 2.4245594560639084e-05, + "loss": 1.5505, + "step": 12161 + }, + { + "epoch": 0.67788863497018, + "grad_norm": 0.5718047022819519, + "learning_rate": 2.4237962816578918e-05, + "loss": 1.5679, + "step": 12162 + }, + { + "epoch": 0.6779443732233432, + "grad_norm": 0.597363293170929, + "learning_rate": 2.4230331889540393e-05, + "loss": 1.7587, + "step": 12163 + }, + { + "epoch": 0.6780001114765063, + "grad_norm": 0.6661909818649292, + "learning_rate": 2.4222701779765467e-05, + "loss": 1.3722, + "step": 12164 + }, + { + "epoch": 0.6780558497296695, + "grad_norm": 0.574291467666626, + "learning_rate": 2.4215072487496153e-05, + "loss": 1.6003, + "step": 12165 + }, + { + "epoch": 0.6781115879828327, + "grad_norm": 0.5555253624916077, + "learning_rate": 2.4207444012974402e-05, + "loss": 1.8517, + "step": 12166 + }, + { + "epoch": 0.6781673262359957, + "grad_norm": 0.5446553826332092, + "learning_rate": 2.4199816356442166e-05, + "loss": 1.5125, + "step": 12167 + }, + { + "epoch": 0.6782230644891589, + "grad_norm": 0.5693860054016113, + "learning_rate": 2.419218951814131e-05, + "loss": 1.7082, + "step": 12168 + }, + { + "epoch": 0.6782788027423221, + "grad_norm": 0.5330381989479065, + "learning_rate": 2.4184563498313712e-05, + "loss": 1.6407, + "step": 12169 + }, + { + "epoch": 0.6783345409954852, + "grad_norm": 0.5500601530075073, + "learning_rate": 2.4176938297201286e-05, + "loss": 1.6078, + "step": 12170 + }, + { + "epoch": 0.6783902792486484, + "grad_norm": 0.5614216923713684, + "learning_rate": 2.4169313915045795e-05, + "loss": 1.6395, + "step": 12171 + }, + { + "epoch": 0.6784460175018114, + "grad_norm": 0.548337459564209, + "learning_rate": 2.4161690352089067e-05, + "loss": 1.6889, + "step": 12172 + }, + { + "epoch": 0.6785017557549746, + "grad_norm": 0.535300076007843, + "learning_rate": 2.4154067608572874e-05, + "loss": 1.663, + "step": 12173 + }, + { + "epoch": 0.6785574940081378, + "grad_norm": 0.5819778442382812, + "learning_rate": 2.414644568473896e-05, + "loss": 1.8053, + "step": 12174 + }, + { + "epoch": 0.6786132322613009, + "grad_norm": 0.5482204556465149, + "learning_rate": 2.413882458082907e-05, + "loss": 1.6296, + "step": 12175 + }, + { + "epoch": 0.6786689705144641, + "grad_norm": 0.5731914043426514, + "learning_rate": 2.4131204297084875e-05, + "loss": 1.6391, + "step": 12176 + }, + { + "epoch": 0.6787247087676272, + "grad_norm": 0.6898718476295471, + "learning_rate": 2.4123584833748042e-05, + "loss": 1.702, + "step": 12177 + }, + { + "epoch": 0.6787804470207903, + "grad_norm": 0.5492184162139893, + "learning_rate": 2.4115966191060236e-05, + "loss": 1.7373, + "step": 12178 + }, + { + "epoch": 0.6788361852739535, + "grad_norm": 0.5639967322349548, + "learning_rate": 2.4108348369263084e-05, + "loss": 1.6233, + "step": 12179 + }, + { + "epoch": 0.6788919235271167, + "grad_norm": 0.5644584894180298, + "learning_rate": 2.4100731368598123e-05, + "loss": 1.6422, + "step": 12180 + }, + { + "epoch": 0.6789476617802798, + "grad_norm": 0.5759285092353821, + "learning_rate": 2.409311518930698e-05, + "loss": 1.6933, + "step": 12181 + }, + { + "epoch": 0.679003400033443, + "grad_norm": 0.5666438937187195, + "learning_rate": 2.4085499831631197e-05, + "loss": 1.6532, + "step": 12182 + }, + { + "epoch": 0.6790591382866061, + "grad_norm": 0.5786770582199097, + "learning_rate": 2.4077885295812248e-05, + "loss": 1.7707, + "step": 12183 + }, + { + "epoch": 0.6791148765397692, + "grad_norm": 0.5363991260528564, + "learning_rate": 2.4070271582091642e-05, + "loss": 1.6073, + "step": 12184 + }, + { + "epoch": 0.6791706147929324, + "grad_norm": 0.5650521516799927, + "learning_rate": 2.406265869071084e-05, + "loss": 1.6806, + "step": 12185 + }, + { + "epoch": 0.6792263530460956, + "grad_norm": 0.5003963708877563, + "learning_rate": 2.4055046621911294e-05, + "loss": 1.4209, + "step": 12186 + }, + { + "epoch": 0.6792820912992587, + "grad_norm": 0.6042050123214722, + "learning_rate": 2.4047435375934363e-05, + "loss": 1.7709, + "step": 12187 + }, + { + "epoch": 0.6793378295524218, + "grad_norm": 0.5666334629058838, + "learning_rate": 2.4039824953021488e-05, + "loss": 1.6503, + "step": 12188 + }, + { + "epoch": 0.679393567805585, + "grad_norm": 0.5441558957099915, + "learning_rate": 2.403221535341403e-05, + "loss": 1.6457, + "step": 12189 + }, + { + "epoch": 0.6794493060587481, + "grad_norm": 0.5805729031562805, + "learning_rate": 2.402460657735327e-05, + "loss": 1.6228, + "step": 12190 + }, + { + "epoch": 0.6795050443119113, + "grad_norm": 0.5899102687835693, + "learning_rate": 2.401699862508055e-05, + "loss": 1.8148, + "step": 12191 + }, + { + "epoch": 0.6795607825650745, + "grad_norm": 0.5872830152511597, + "learning_rate": 2.4009391496837143e-05, + "loss": 1.8663, + "step": 12192 + }, + { + "epoch": 0.6796165208182375, + "grad_norm": 0.6101430058479309, + "learning_rate": 2.4001785192864313e-05, + "loss": 1.9342, + "step": 12193 + }, + { + "epoch": 0.6796722590714007, + "grad_norm": 0.5709355473518372, + "learning_rate": 2.3994179713403265e-05, + "loss": 1.5368, + "step": 12194 + }, + { + "epoch": 0.6797279973245638, + "grad_norm": 0.5578945875167847, + "learning_rate": 2.398657505869519e-05, + "loss": 1.4992, + "step": 12195 + }, + { + "epoch": 0.679783735577727, + "grad_norm": 0.5690076351165771, + "learning_rate": 2.3978971228981323e-05, + "loss": 1.5838, + "step": 12196 + }, + { + "epoch": 0.6798394738308902, + "grad_norm": 0.5869070291519165, + "learning_rate": 2.397136822450276e-05, + "loss": 1.8293, + "step": 12197 + }, + { + "epoch": 0.6798952120840532, + "grad_norm": 0.617962121963501, + "learning_rate": 2.3963766045500634e-05, + "loss": 1.6752, + "step": 12198 + }, + { + "epoch": 0.6799509503372164, + "grad_norm": 0.5052658915519714, + "learning_rate": 2.3956164692216054e-05, + "loss": 1.3596, + "step": 12199 + }, + { + "epoch": 0.6800066885903796, + "grad_norm": 0.6124083995819092, + "learning_rate": 2.394856416489008e-05, + "loss": 1.7068, + "step": 12200 + }, + { + "epoch": 0.6800624268435427, + "grad_norm": 0.5866329669952393, + "learning_rate": 2.3940964463763778e-05, + "loss": 1.7651, + "step": 12201 + }, + { + "epoch": 0.6801181650967059, + "grad_norm": 0.5338658094406128, + "learning_rate": 2.393336558907811e-05, + "loss": 1.4577, + "step": 12202 + }, + { + "epoch": 0.680173903349869, + "grad_norm": 0.5513985753059387, + "learning_rate": 2.3925767541074147e-05, + "loss": 1.6466, + "step": 12203 + }, + { + "epoch": 0.6802296416030321, + "grad_norm": 0.5717636346817017, + "learning_rate": 2.3918170319992793e-05, + "loss": 1.6213, + "step": 12204 + }, + { + "epoch": 0.6802853798561953, + "grad_norm": 0.5736023187637329, + "learning_rate": 2.391057392607503e-05, + "loss": 1.8441, + "step": 12205 + }, + { + "epoch": 0.6803411181093585, + "grad_norm": 0.6372126936912537, + "learning_rate": 2.3902978359561713e-05, + "loss": 1.5251, + "step": 12206 + }, + { + "epoch": 0.6803968563625216, + "grad_norm": 0.5528156757354736, + "learning_rate": 2.3895383620693785e-05, + "loss": 1.7265, + "step": 12207 + }, + { + "epoch": 0.6804525946156847, + "grad_norm": 0.5714967250823975, + "learning_rate": 2.3887789709712107e-05, + "loss": 1.7238, + "step": 12208 + }, + { + "epoch": 0.6805083328688479, + "grad_norm": 0.6046301126480103, + "learning_rate": 2.388019662685747e-05, + "loss": 1.7441, + "step": 12209 + }, + { + "epoch": 0.680564071122011, + "grad_norm": 0.5244828462600708, + "learning_rate": 2.3872604372370717e-05, + "loss": 1.5733, + "step": 12210 + }, + { + "epoch": 0.6806198093751742, + "grad_norm": 0.5506595373153687, + "learning_rate": 2.386501294649261e-05, + "loss": 1.8439, + "step": 12211 + }, + { + "epoch": 0.6806755476283374, + "grad_norm": 0.5664464235305786, + "learning_rate": 2.3857422349463944e-05, + "loss": 1.6925, + "step": 12212 + }, + { + "epoch": 0.6807312858815004, + "grad_norm": 0.5245766043663025, + "learning_rate": 2.384983258152537e-05, + "loss": 1.7101, + "step": 12213 + }, + { + "epoch": 0.6807870241346636, + "grad_norm": 0.5500200986862183, + "learning_rate": 2.3842243642917666e-05, + "loss": 1.6757, + "step": 12214 + }, + { + "epoch": 0.6808427623878268, + "grad_norm": 0.540712296962738, + "learning_rate": 2.38346555338815e-05, + "loss": 1.5788, + "step": 12215 + }, + { + "epoch": 0.6808985006409899, + "grad_norm": 0.5923953652381897, + "learning_rate": 2.382706825465749e-05, + "loss": 1.5688, + "step": 12216 + }, + { + "epoch": 0.6809542388941531, + "grad_norm": 0.559162437915802, + "learning_rate": 2.3819481805486275e-05, + "loss": 1.4546, + "step": 12217 + }, + { + "epoch": 0.6810099771473161, + "grad_norm": 0.5854106545448303, + "learning_rate": 2.3811896186608457e-05, + "loss": 1.6903, + "step": 12218 + }, + { + "epoch": 0.6810657154004793, + "grad_norm": 0.5242003798484802, + "learning_rate": 2.3804311398264617e-05, + "loss": 1.4833, + "step": 12219 + }, + { + "epoch": 0.6811214536536425, + "grad_norm": 0.5815067291259766, + "learning_rate": 2.379672744069527e-05, + "loss": 1.6484, + "step": 12220 + }, + { + "epoch": 0.6811771919068056, + "grad_norm": 0.5998220443725586, + "learning_rate": 2.3789144314140938e-05, + "loss": 1.7253, + "step": 12221 + }, + { + "epoch": 0.6812329301599688, + "grad_norm": 0.5479490756988525, + "learning_rate": 2.378156201884217e-05, + "loss": 1.7107, + "step": 12222 + }, + { + "epoch": 0.681288668413132, + "grad_norm": 0.5347844362258911, + "learning_rate": 2.377398055503936e-05, + "loss": 1.4336, + "step": 12223 + }, + { + "epoch": 0.681344406666295, + "grad_norm": 0.5410118699073792, + "learning_rate": 2.376639992297299e-05, + "loss": 1.4867, + "step": 12224 + }, + { + "epoch": 0.6814001449194582, + "grad_norm": 0.5688346028327942, + "learning_rate": 2.3758820122883456e-05, + "loss": 1.7883, + "step": 12225 + }, + { + "epoch": 0.6814558831726214, + "grad_norm": 0.5206215381622314, + "learning_rate": 2.375124115501115e-05, + "loss": 1.7039, + "step": 12226 + }, + { + "epoch": 0.6815116214257845, + "grad_norm": 0.5235037803649902, + "learning_rate": 2.3743663019596456e-05, + "loss": 1.592, + "step": 12227 + }, + { + "epoch": 0.6815673596789477, + "grad_norm": 0.6111394762992859, + "learning_rate": 2.3736085716879647e-05, + "loss": 1.7615, + "step": 12228 + }, + { + "epoch": 0.6816230979321108, + "grad_norm": 0.5806996822357178, + "learning_rate": 2.3728509247101106e-05, + "loss": 1.5715, + "step": 12229 + }, + { + "epoch": 0.6816788361852739, + "grad_norm": 0.5856095552444458, + "learning_rate": 2.3720933610501062e-05, + "loss": 1.6945, + "step": 12230 + }, + { + "epoch": 0.6817345744384371, + "grad_norm": 0.563182532787323, + "learning_rate": 2.37133588073198e-05, + "loss": 1.5869, + "step": 12231 + }, + { + "epoch": 0.6817903126916003, + "grad_norm": 0.5626211166381836, + "learning_rate": 2.3705784837797502e-05, + "loss": 1.5898, + "step": 12232 + }, + { + "epoch": 0.6818460509447634, + "grad_norm": 0.6541900634765625, + "learning_rate": 2.3698211702174423e-05, + "loss": 1.6013, + "step": 12233 + }, + { + "epoch": 0.6819017891979265, + "grad_norm": 0.6194508075714111, + "learning_rate": 2.3690639400690735e-05, + "loss": 1.6214, + "step": 12234 + }, + { + "epoch": 0.6819575274510897, + "grad_norm": 0.5775251984596252, + "learning_rate": 2.368306793358655e-05, + "loss": 1.6553, + "step": 12235 + }, + { + "epoch": 0.6820132657042528, + "grad_norm": 0.570357620716095, + "learning_rate": 2.3675497301102017e-05, + "loss": 1.8637, + "step": 12236 + }, + { + "epoch": 0.682069003957416, + "grad_norm": 0.5307665467262268, + "learning_rate": 2.3667927503477222e-05, + "loss": 1.3013, + "step": 12237 + }, + { + "epoch": 0.6821247422105792, + "grad_norm": 0.6126335263252258, + "learning_rate": 2.3660358540952265e-05, + "loss": 1.7682, + "step": 12238 + }, + { + "epoch": 0.6821804804637422, + "grad_norm": 0.5725120902061462, + "learning_rate": 2.3652790413767122e-05, + "loss": 1.7248, + "step": 12239 + }, + { + "epoch": 0.6822362187169054, + "grad_norm": 0.5724482536315918, + "learning_rate": 2.3645223122161868e-05, + "loss": 1.6372, + "step": 12240 + }, + { + "epoch": 0.6822919569700685, + "grad_norm": 0.5620321035385132, + "learning_rate": 2.3637656666376505e-05, + "loss": 1.5107, + "step": 12241 + }, + { + "epoch": 0.6823476952232317, + "grad_norm": 0.6563616394996643, + "learning_rate": 2.3630091046650944e-05, + "loss": 1.9183, + "step": 12242 + }, + { + "epoch": 0.6824034334763949, + "grad_norm": 0.5810117125511169, + "learning_rate": 2.3622526263225152e-05, + "loss": 1.7131, + "step": 12243 + }, + { + "epoch": 0.682459171729558, + "grad_norm": 0.5808402895927429, + "learning_rate": 2.3614962316339033e-05, + "loss": 1.8323, + "step": 12244 + }, + { + "epoch": 0.6825149099827211, + "grad_norm": 0.5127190351486206, + "learning_rate": 2.3607399206232493e-05, + "loss": 1.46, + "step": 12245 + }, + { + "epoch": 0.6825706482358843, + "grad_norm": 0.5926672220230103, + "learning_rate": 2.359983693314535e-05, + "loss": 1.6821, + "step": 12246 + }, + { + "epoch": 0.6826263864890474, + "grad_norm": 0.5927006602287292, + "learning_rate": 2.359227549731744e-05, + "loss": 1.5697, + "step": 12247 + }, + { + "epoch": 0.6826821247422106, + "grad_norm": 0.5811200141906738, + "learning_rate": 2.358471489898862e-05, + "loss": 1.5941, + "step": 12248 + }, + { + "epoch": 0.6827378629953738, + "grad_norm": 0.5455745458602905, + "learning_rate": 2.3577155138398616e-05, + "loss": 1.6352, + "step": 12249 + }, + { + "epoch": 0.6827936012485368, + "grad_norm": 0.5447341203689575, + "learning_rate": 2.3569596215787187e-05, + "loss": 1.4396, + "step": 12250 + }, + { + "epoch": 0.6828493395017, + "grad_norm": 0.619299590587616, + "learning_rate": 2.356203813139407e-05, + "loss": 1.645, + "step": 12251 + }, + { + "epoch": 0.6829050777548632, + "grad_norm": 0.5267062783241272, + "learning_rate": 2.3554480885458964e-05, + "loss": 1.4556, + "step": 12252 + }, + { + "epoch": 0.6829608160080263, + "grad_norm": 0.5284720063209534, + "learning_rate": 2.354692447822155e-05, + "loss": 1.4566, + "step": 12253 + }, + { + "epoch": 0.6830165542611895, + "grad_norm": 0.5493966937065125, + "learning_rate": 2.3539368909921423e-05, + "loss": 1.6032, + "step": 12254 + }, + { + "epoch": 0.6830722925143526, + "grad_norm": 0.5600801110267639, + "learning_rate": 2.3531814180798277e-05, + "loss": 1.5002, + "step": 12255 + }, + { + "epoch": 0.6831280307675157, + "grad_norm": 0.5507102608680725, + "learning_rate": 2.3524260291091642e-05, + "loss": 1.8472, + "step": 12256 + }, + { + "epoch": 0.6831837690206789, + "grad_norm": 0.5536506772041321, + "learning_rate": 2.3516707241041132e-05, + "loss": 1.7751, + "step": 12257 + }, + { + "epoch": 0.6832395072738421, + "grad_norm": 0.5619939565658569, + "learning_rate": 2.350915503088622e-05, + "loss": 1.6577, + "step": 12258 + }, + { + "epoch": 0.6832952455270052, + "grad_norm": 0.5918766260147095, + "learning_rate": 2.3501603660866473e-05, + "loss": 1.8244, + "step": 12259 + }, + { + "epoch": 0.6833509837801683, + "grad_norm": 0.5610700845718384, + "learning_rate": 2.3494053131221383e-05, + "loss": 1.7442, + "step": 12260 + }, + { + "epoch": 0.6834067220333315, + "grad_norm": 0.5872762799263, + "learning_rate": 2.3486503442190373e-05, + "loss": 1.5471, + "step": 12261 + }, + { + "epoch": 0.6834624602864946, + "grad_norm": 0.5529700517654419, + "learning_rate": 2.347895459401288e-05, + "loss": 1.5732, + "step": 12262 + }, + { + "epoch": 0.6835181985396578, + "grad_norm": 0.5814720988273621, + "learning_rate": 2.3471406586928323e-05, + "loss": 1.642, + "step": 12263 + }, + { + "epoch": 0.6835739367928209, + "grad_norm": 0.5444031953811646, + "learning_rate": 2.34638594211761e-05, + "loss": 1.603, + "step": 12264 + }, + { + "epoch": 0.683629675045984, + "grad_norm": 0.5756646990776062, + "learning_rate": 2.3456313096995498e-05, + "loss": 1.7664, + "step": 12265 + }, + { + "epoch": 0.6836854132991472, + "grad_norm": 0.5543645620346069, + "learning_rate": 2.34487676146259e-05, + "loss": 1.4581, + "step": 12266 + }, + { + "epoch": 0.6837411515523103, + "grad_norm": 0.590130090713501, + "learning_rate": 2.344122297430661e-05, + "loss": 1.6216, + "step": 12267 + }, + { + "epoch": 0.6837968898054735, + "grad_norm": 0.5462613105773926, + "learning_rate": 2.343367917627686e-05, + "loss": 1.641, + "step": 12268 + }, + { + "epoch": 0.6838526280586367, + "grad_norm": 0.5439698100090027, + "learning_rate": 2.3426136220775917e-05, + "loss": 1.5376, + "step": 12269 + }, + { + "epoch": 0.6839083663117997, + "grad_norm": 0.557994544506073, + "learning_rate": 2.3418594108042996e-05, + "loss": 1.4804, + "step": 12270 + }, + { + "epoch": 0.6839641045649629, + "grad_norm": 0.5578276515007019, + "learning_rate": 2.3411052838317306e-05, + "loss": 1.6446, + "step": 12271 + }, + { + "epoch": 0.6840198428181261, + "grad_norm": 0.5396918654441833, + "learning_rate": 2.340351241183798e-05, + "loss": 1.6575, + "step": 12272 + }, + { + "epoch": 0.6840755810712892, + "grad_norm": 0.548381507396698, + "learning_rate": 2.339597282884415e-05, + "loss": 1.4676, + "step": 12273 + }, + { + "epoch": 0.6841313193244524, + "grad_norm": 0.5647532343864441, + "learning_rate": 2.3388434089574985e-05, + "loss": 1.6655, + "step": 12274 + }, + { + "epoch": 0.6841870575776156, + "grad_norm": 0.5372335910797119, + "learning_rate": 2.3380896194269518e-05, + "loss": 1.5272, + "step": 12275 + }, + { + "epoch": 0.6842427958307786, + "grad_norm": 0.6535205245018005, + "learning_rate": 2.337335914316683e-05, + "loss": 1.8014, + "step": 12276 + }, + { + "epoch": 0.6842985340839418, + "grad_norm": 0.579191267490387, + "learning_rate": 2.3365822936505938e-05, + "loss": 1.7232, + "step": 12277 + }, + { + "epoch": 0.684354272337105, + "grad_norm": 0.5299929976463318, + "learning_rate": 2.3358287574525878e-05, + "loss": 1.4039, + "step": 12278 + }, + { + "epoch": 0.6844100105902681, + "grad_norm": 0.5980880856513977, + "learning_rate": 2.335075305746558e-05, + "loss": 1.6005, + "step": 12279 + }, + { + "epoch": 0.6844657488434313, + "grad_norm": 0.5642344951629639, + "learning_rate": 2.3343219385564003e-05, + "loss": 1.5314, + "step": 12280 + }, + { + "epoch": 0.6845214870965944, + "grad_norm": 0.5406617522239685, + "learning_rate": 2.333568655906013e-05, + "loss": 1.5298, + "step": 12281 + }, + { + "epoch": 0.6845772253497575, + "grad_norm": 0.5585936307907104, + "learning_rate": 2.332815457819279e-05, + "loss": 1.6174, + "step": 12282 + }, + { + "epoch": 0.6846329636029207, + "grad_norm": 0.6313422322273254, + "learning_rate": 2.332062344320088e-05, + "loss": 1.4918, + "step": 12283 + }, + { + "epoch": 0.6846887018560839, + "grad_norm": 0.6248939037322998, + "learning_rate": 2.3313093154323246e-05, + "loss": 1.8133, + "step": 12284 + }, + { + "epoch": 0.684744440109247, + "grad_norm": 0.5743393301963806, + "learning_rate": 2.3305563711798694e-05, + "loss": 1.7663, + "step": 12285 + }, + { + "epoch": 0.6848001783624101, + "grad_norm": 0.532964825630188, + "learning_rate": 2.3298035115866052e-05, + "loss": 1.6054, + "step": 12286 + }, + { + "epoch": 0.6848559166155732, + "grad_norm": 0.587245523929596, + "learning_rate": 2.3290507366764025e-05, + "loss": 1.7638, + "step": 12287 + }, + { + "epoch": 0.6849116548687364, + "grad_norm": 0.5927528142929077, + "learning_rate": 2.3282980464731378e-05, + "loss": 1.8447, + "step": 12288 + }, + { + "epoch": 0.6849673931218996, + "grad_norm": 0.5583227276802063, + "learning_rate": 2.3275454410006825e-05, + "loss": 1.5922, + "step": 12289 + }, + { + "epoch": 0.6850231313750627, + "grad_norm": 0.5567259192466736, + "learning_rate": 2.326792920282906e-05, + "loss": 1.5335, + "step": 12290 + }, + { + "epoch": 0.6850788696282258, + "grad_norm": 0.5991070866584778, + "learning_rate": 2.3260404843436685e-05, + "loss": 1.7828, + "step": 12291 + }, + { + "epoch": 0.685134607881389, + "grad_norm": 0.5784618854522705, + "learning_rate": 2.325288133206838e-05, + "loss": 1.7622, + "step": 12292 + }, + { + "epoch": 0.6851903461345521, + "grad_norm": 0.6060516834259033, + "learning_rate": 2.3245358668962754e-05, + "loss": 1.6446, + "step": 12293 + }, + { + "epoch": 0.6852460843877153, + "grad_norm": 0.5378335118293762, + "learning_rate": 2.323783685435834e-05, + "loss": 1.1563, + "step": 12294 + }, + { + "epoch": 0.6853018226408785, + "grad_norm": 0.5524575710296631, + "learning_rate": 2.323031588849371e-05, + "loss": 1.4075, + "step": 12295 + }, + { + "epoch": 0.6853575608940415, + "grad_norm": 0.5505098700523376, + "learning_rate": 2.322279577160738e-05, + "loss": 1.5879, + "step": 12296 + }, + { + "epoch": 0.6854132991472047, + "grad_norm": 0.5956327319145203, + "learning_rate": 2.3215276503937867e-05, + "loss": 1.8357, + "step": 12297 + }, + { + "epoch": 0.6854690374003679, + "grad_norm": 0.5103068351745605, + "learning_rate": 2.3207758085723597e-05, + "loss": 1.4444, + "step": 12298 + }, + { + "epoch": 0.685524775653531, + "grad_norm": 0.5405187010765076, + "learning_rate": 2.3200240517203015e-05, + "loss": 1.6139, + "step": 12299 + }, + { + "epoch": 0.6855805139066942, + "grad_norm": 0.5659931898117065, + "learning_rate": 2.3192723798614584e-05, + "loss": 1.7099, + "step": 12300 + }, + { + "epoch": 0.6856362521598574, + "grad_norm": 0.553611159324646, + "learning_rate": 2.318520793019664e-05, + "loss": 1.602, + "step": 12301 + }, + { + "epoch": 0.6856919904130204, + "grad_norm": 0.5447365045547485, + "learning_rate": 2.317769291218756e-05, + "loss": 1.6749, + "step": 12302 + }, + { + "epoch": 0.6857477286661836, + "grad_norm": 0.5491530299186707, + "learning_rate": 2.3170178744825676e-05, + "loss": 1.7086, + "step": 12303 + }, + { + "epoch": 0.6858034669193468, + "grad_norm": 0.5359060764312744, + "learning_rate": 2.316266542834931e-05, + "loss": 1.4932, + "step": 12304 + }, + { + "epoch": 0.6858592051725099, + "grad_norm": 0.5571125745773315, + "learning_rate": 2.3155152962996708e-05, + "loss": 1.6363, + "step": 12305 + }, + { + "epoch": 0.685914943425673, + "grad_norm": 0.581794023513794, + "learning_rate": 2.3147641349006116e-05, + "loss": 1.7378, + "step": 12306 + }, + { + "epoch": 0.6859706816788362, + "grad_norm": 0.6025446057319641, + "learning_rate": 2.3140130586615823e-05, + "loss": 1.3766, + "step": 12307 + }, + { + "epoch": 0.6860264199319993, + "grad_norm": 0.5985897183418274, + "learning_rate": 2.313262067606396e-05, + "loss": 1.9187, + "step": 12308 + }, + { + "epoch": 0.6860821581851625, + "grad_norm": 0.6531051993370056, + "learning_rate": 2.3125111617588717e-05, + "loss": 1.7144, + "step": 12309 + }, + { + "epoch": 0.6861378964383256, + "grad_norm": 0.5455422401428223, + "learning_rate": 2.311760341142825e-05, + "loss": 1.7483, + "step": 12310 + }, + { + "epoch": 0.6861936346914888, + "grad_norm": 0.5412722826004028, + "learning_rate": 2.3110096057820668e-05, + "loss": 1.6752, + "step": 12311 + }, + { + "epoch": 0.6862493729446519, + "grad_norm": 0.5647415518760681, + "learning_rate": 2.310258955700408e-05, + "loss": 1.5869, + "step": 12312 + }, + { + "epoch": 0.686305111197815, + "grad_norm": 0.5701124668121338, + "learning_rate": 2.3095083909216504e-05, + "loss": 1.6082, + "step": 12313 + }, + { + "epoch": 0.6863608494509782, + "grad_norm": 0.534731388092041, + "learning_rate": 2.3087579114696e-05, + "loss": 1.6087, + "step": 12314 + }, + { + "epoch": 0.6864165877041414, + "grad_norm": 0.5065962076187134, + "learning_rate": 2.3080075173680577e-05, + "loss": 1.178, + "step": 12315 + }, + { + "epoch": 0.6864723259573045, + "grad_norm": 0.6015399098396301, + "learning_rate": 2.3072572086408233e-05, + "loss": 1.6732, + "step": 12316 + }, + { + "epoch": 0.6865280642104676, + "grad_norm": 0.5849504470825195, + "learning_rate": 2.3065069853116872e-05, + "loss": 1.6694, + "step": 12317 + }, + { + "epoch": 0.6865838024636308, + "grad_norm": 0.5738614201545715, + "learning_rate": 2.3057568474044473e-05, + "loss": 1.6295, + "step": 12318 + }, + { + "epoch": 0.6866395407167939, + "grad_norm": 0.5688014030456543, + "learning_rate": 2.305006794942893e-05, + "loss": 1.7854, + "step": 12319 + }, + { + "epoch": 0.6866952789699571, + "grad_norm": 0.5481501817703247, + "learning_rate": 2.3042568279508087e-05, + "loss": 1.5614, + "step": 12320 + }, + { + "epoch": 0.6867510172231203, + "grad_norm": 0.636509895324707, + "learning_rate": 2.3035069464519805e-05, + "loss": 1.8107, + "step": 12321 + }, + { + "epoch": 0.6868067554762833, + "grad_norm": 0.5459586977958679, + "learning_rate": 2.3027571504701902e-05, + "loss": 1.4073, + "step": 12322 + }, + { + "epoch": 0.6868624937294465, + "grad_norm": 0.5219615697860718, + "learning_rate": 2.302007440029219e-05, + "loss": 1.4108, + "step": 12323 + }, + { + "epoch": 0.6869182319826097, + "grad_norm": 0.5494387745857239, + "learning_rate": 2.3012578151528398e-05, + "loss": 1.7426, + "step": 12324 + }, + { + "epoch": 0.6869739702357728, + "grad_norm": 0.5496208667755127, + "learning_rate": 2.3005082758648256e-05, + "loss": 1.6956, + "step": 12325 + }, + { + "epoch": 0.687029708488936, + "grad_norm": 0.5529760122299194, + "learning_rate": 2.299758822188954e-05, + "loss": 1.4693, + "step": 12326 + }, + { + "epoch": 0.6870854467420991, + "grad_norm": 0.5550394654273987, + "learning_rate": 2.2990094541489866e-05, + "loss": 1.9276, + "step": 12327 + }, + { + "epoch": 0.6871411849952622, + "grad_norm": 0.5335902571678162, + "learning_rate": 2.298260171768692e-05, + "loss": 1.4048, + "step": 12328 + }, + { + "epoch": 0.6871969232484254, + "grad_norm": 0.6344630122184753, + "learning_rate": 2.2975109750718323e-05, + "loss": 1.8137, + "step": 12329 + }, + { + "epoch": 0.6872526615015886, + "grad_norm": 0.5269440412521362, + "learning_rate": 2.2967618640821698e-05, + "loss": 1.5533, + "step": 12330 + }, + { + "epoch": 0.6873083997547517, + "grad_norm": 0.649878978729248, + "learning_rate": 2.296012838823458e-05, + "loss": 1.8408, + "step": 12331 + }, + { + "epoch": 0.6873641380079148, + "grad_norm": 0.5460097789764404, + "learning_rate": 2.2952638993194515e-05, + "loss": 1.6803, + "step": 12332 + }, + { + "epoch": 0.6874198762610779, + "grad_norm": 0.5708609223365784, + "learning_rate": 2.2945150455939084e-05, + "loss": 1.5447, + "step": 12333 + }, + { + "epoch": 0.6874756145142411, + "grad_norm": 0.5807245373725891, + "learning_rate": 2.2937662776705728e-05, + "loss": 1.7161, + "step": 12334 + }, + { + "epoch": 0.6875313527674043, + "grad_norm": 0.5651794075965881, + "learning_rate": 2.2930175955731914e-05, + "loss": 1.5177, + "step": 12335 + }, + { + "epoch": 0.6875870910205674, + "grad_norm": 0.6334015727043152, + "learning_rate": 2.2922689993255093e-05, + "loss": 1.9024, + "step": 12336 + }, + { + "epoch": 0.6876428292737305, + "grad_norm": 0.593908965587616, + "learning_rate": 2.2915204889512678e-05, + "loss": 1.7149, + "step": 12337 + }, + { + "epoch": 0.6876985675268937, + "grad_norm": 0.5945553183555603, + "learning_rate": 2.2907720644742064e-05, + "loss": 1.8041, + "step": 12338 + }, + { + "epoch": 0.6877543057800568, + "grad_norm": 0.5217798948287964, + "learning_rate": 2.2900237259180575e-05, + "loss": 1.5429, + "step": 12339 + }, + { + "epoch": 0.68781004403322, + "grad_norm": 0.5226582288742065, + "learning_rate": 2.2892754733065558e-05, + "loss": 1.6162, + "step": 12340 + }, + { + "epoch": 0.6878657822863832, + "grad_norm": 0.5856578946113586, + "learning_rate": 2.2885273066634312e-05, + "loss": 1.5418, + "step": 12341 + }, + { + "epoch": 0.6879215205395462, + "grad_norm": 0.5848087668418884, + "learning_rate": 2.287779226012413e-05, + "loss": 1.5795, + "step": 12342 + }, + { + "epoch": 0.6879772587927094, + "grad_norm": 0.5924365520477295, + "learning_rate": 2.287031231377221e-05, + "loss": 1.5287, + "step": 12343 + }, + { + "epoch": 0.6880329970458726, + "grad_norm": 0.5729358792304993, + "learning_rate": 2.2862833227815834e-05, + "loss": 1.8508, + "step": 12344 + }, + { + "epoch": 0.6880887352990357, + "grad_norm": 0.5354797840118408, + "learning_rate": 2.2855355002492173e-05, + "loss": 1.8116, + "step": 12345 + }, + { + "epoch": 0.6881444735521989, + "grad_norm": 0.5971417427062988, + "learning_rate": 2.2847877638038378e-05, + "loss": 1.911, + "step": 12346 + }, + { + "epoch": 0.6882002118053621, + "grad_norm": 0.6175577044487, + "learning_rate": 2.2840401134691593e-05, + "loss": 1.9441, + "step": 12347 + }, + { + "epoch": 0.6882559500585251, + "grad_norm": 0.5977439880371094, + "learning_rate": 2.283292549268893e-05, + "loss": 1.6979, + "step": 12348 + }, + { + "epoch": 0.6883116883116883, + "grad_norm": 0.5494217872619629, + "learning_rate": 2.2825450712267495e-05, + "loss": 1.4911, + "step": 12349 + }, + { + "epoch": 0.6883674265648515, + "grad_norm": 0.5619058609008789, + "learning_rate": 2.2817976793664286e-05, + "loss": 1.7359, + "step": 12350 + }, + { + "epoch": 0.6884231648180146, + "grad_norm": 0.6751987338066101, + "learning_rate": 2.2810503737116395e-05, + "loss": 1.5864, + "step": 12351 + }, + { + "epoch": 0.6884789030711778, + "grad_norm": 0.5647567510604858, + "learning_rate": 2.2803031542860814e-05, + "loss": 1.6317, + "step": 12352 + }, + { + "epoch": 0.688534641324341, + "grad_norm": 0.5837883353233337, + "learning_rate": 2.2795560211134488e-05, + "loss": 1.7449, + "step": 12353 + }, + { + "epoch": 0.688590379577504, + "grad_norm": 0.5777410864830017, + "learning_rate": 2.2788089742174374e-05, + "loss": 1.8073, + "step": 12354 + }, + { + "epoch": 0.6886461178306672, + "grad_norm": 0.5158605575561523, + "learning_rate": 2.27806201362174e-05, + "loss": 1.4452, + "step": 12355 + }, + { + "epoch": 0.6887018560838304, + "grad_norm": 0.5918664336204529, + "learning_rate": 2.2773151393500475e-05, + "loss": 1.5739, + "step": 12356 + }, + { + "epoch": 0.6887575943369935, + "grad_norm": 0.5540437698364258, + "learning_rate": 2.2765683514260426e-05, + "loss": 1.6514, + "step": 12357 + }, + { + "epoch": 0.6888133325901566, + "grad_norm": 0.556175708770752, + "learning_rate": 2.2758216498734086e-05, + "loss": 1.7062, + "step": 12358 + }, + { + "epoch": 0.6888690708433197, + "grad_norm": 0.5426061153411865, + "learning_rate": 2.275075034715833e-05, + "loss": 1.731, + "step": 12359 + }, + { + "epoch": 0.6889248090964829, + "grad_norm": 0.5565474033355713, + "learning_rate": 2.2743285059769876e-05, + "loss": 1.445, + "step": 12360 + }, + { + "epoch": 0.6889805473496461, + "grad_norm": 0.5506940484046936, + "learning_rate": 2.2735820636805504e-05, + "loss": 1.6502, + "step": 12361 + }, + { + "epoch": 0.6890362856028092, + "grad_norm": 0.563405454158783, + "learning_rate": 2.2728357078501943e-05, + "loss": 1.728, + "step": 12362 + }, + { + "epoch": 0.6890920238559723, + "grad_norm": 0.5887188911437988, + "learning_rate": 2.2720894385095887e-05, + "loss": 1.7767, + "step": 12363 + }, + { + "epoch": 0.6891477621091355, + "grad_norm": 0.5309818983078003, + "learning_rate": 2.2713432556824033e-05, + "loss": 1.4704, + "step": 12364 + }, + { + "epoch": 0.6892035003622986, + "grad_norm": 0.5519055128097534, + "learning_rate": 2.2705971593922985e-05, + "loss": 1.5619, + "step": 12365 + }, + { + "epoch": 0.6892592386154618, + "grad_norm": 0.6391844749450684, + "learning_rate": 2.269851149662939e-05, + "loss": 1.6688, + "step": 12366 + }, + { + "epoch": 0.689314976868625, + "grad_norm": 0.5843481421470642, + "learning_rate": 2.269105226517983e-05, + "loss": 1.73, + "step": 12367 + }, + { + "epoch": 0.689370715121788, + "grad_norm": 0.5808287262916565, + "learning_rate": 2.2683593899810884e-05, + "loss": 1.713, + "step": 12368 + }, + { + "epoch": 0.6894264533749512, + "grad_norm": 0.5973604321479797, + "learning_rate": 2.2676136400759036e-05, + "loss": 1.746, + "step": 12369 + }, + { + "epoch": 0.6894821916281144, + "grad_norm": 0.5638074278831482, + "learning_rate": 2.2668679768260853e-05, + "loss": 1.4742, + "step": 12370 + }, + { + "epoch": 0.6895379298812775, + "grad_norm": 0.5505542755126953, + "learning_rate": 2.2661224002552816e-05, + "loss": 1.5458, + "step": 12371 + }, + { + "epoch": 0.6895936681344407, + "grad_norm": 0.5930557250976562, + "learning_rate": 2.2653769103871337e-05, + "loss": 1.723, + "step": 12372 + }, + { + "epoch": 0.6896494063876039, + "grad_norm": 0.5452224016189575, + "learning_rate": 2.2646315072452862e-05, + "loss": 1.5082, + "step": 12373 + }, + { + "epoch": 0.6897051446407669, + "grad_norm": 0.574612557888031, + "learning_rate": 2.2638861908533788e-05, + "loss": 1.8428, + "step": 12374 + }, + { + "epoch": 0.6897608828939301, + "grad_norm": 0.5554018616676331, + "learning_rate": 2.2631409612350512e-05, + "loss": 1.6155, + "step": 12375 + }, + { + "epoch": 0.6898166211470933, + "grad_norm": 0.5662262439727783, + "learning_rate": 2.262395818413931e-05, + "loss": 1.5198, + "step": 12376 + }, + { + "epoch": 0.6898723594002564, + "grad_norm": 0.6049961447715759, + "learning_rate": 2.261650762413656e-05, + "loss": 1.7388, + "step": 12377 + }, + { + "epoch": 0.6899280976534196, + "grad_norm": 0.5534675717353821, + "learning_rate": 2.2609057932578554e-05, + "loss": 1.4587, + "step": 12378 + }, + { + "epoch": 0.6899838359065827, + "grad_norm": 0.5847275257110596, + "learning_rate": 2.260160910970151e-05, + "loss": 1.4442, + "step": 12379 + }, + { + "epoch": 0.6900395741597458, + "grad_norm": 0.551920473575592, + "learning_rate": 2.2594161155741683e-05, + "loss": 1.613, + "step": 12380 + }, + { + "epoch": 0.690095312412909, + "grad_norm": 0.5585432052612305, + "learning_rate": 2.2586714070935272e-05, + "loss": 1.6245, + "step": 12381 + }, + { + "epoch": 0.6901510506660721, + "grad_norm": 0.5355674624443054, + "learning_rate": 2.257926785551848e-05, + "loss": 1.5427, + "step": 12382 + }, + { + "epoch": 0.6902067889192353, + "grad_norm": 0.5962349772453308, + "learning_rate": 2.2571822509727426e-05, + "loss": 1.6541, + "step": 12383 + }, + { + "epoch": 0.6902625271723984, + "grad_norm": 0.5941932201385498, + "learning_rate": 2.2564378033798217e-05, + "loss": 1.6218, + "step": 12384 + }, + { + "epoch": 0.6903182654255615, + "grad_norm": 0.5653877258300781, + "learning_rate": 2.255693442796702e-05, + "loss": 1.7158, + "step": 12385 + }, + { + "epoch": 0.6903740036787247, + "grad_norm": 0.5377355813980103, + "learning_rate": 2.254949169246983e-05, + "loss": 1.5469, + "step": 12386 + }, + { + "epoch": 0.6904297419318879, + "grad_norm": 0.5659373998641968, + "learning_rate": 2.254204982754273e-05, + "loss": 1.6359, + "step": 12387 + }, + { + "epoch": 0.690485480185051, + "grad_norm": 0.5379758477210999, + "learning_rate": 2.2534608833421712e-05, + "loss": 1.5418, + "step": 12388 + }, + { + "epoch": 0.6905412184382141, + "grad_norm": 0.6035560965538025, + "learning_rate": 2.252716871034276e-05, + "loss": 1.7552, + "step": 12389 + }, + { + "epoch": 0.6905969566913773, + "grad_norm": 0.5235888957977295, + "learning_rate": 2.2519729458541865e-05, + "loss": 1.4821, + "step": 12390 + }, + { + "epoch": 0.6906526949445404, + "grad_norm": 0.5545063018798828, + "learning_rate": 2.2512291078254914e-05, + "loss": 1.497, + "step": 12391 + }, + { + "epoch": 0.6907084331977036, + "grad_norm": 0.5761866569519043, + "learning_rate": 2.250485356971782e-05, + "loss": 1.7174, + "step": 12392 + }, + { + "epoch": 0.6907641714508668, + "grad_norm": 0.6089950799942017, + "learning_rate": 2.249741693316647e-05, + "loss": 1.8879, + "step": 12393 + }, + { + "epoch": 0.6908199097040298, + "grad_norm": 0.5526731014251709, + "learning_rate": 2.2489981168836717e-05, + "loss": 1.7202, + "step": 12394 + }, + { + "epoch": 0.690875647957193, + "grad_norm": 0.5309497117996216, + "learning_rate": 2.2482546276964327e-05, + "loss": 1.6372, + "step": 12395 + }, + { + "epoch": 0.6909313862103562, + "grad_norm": 0.5908359885215759, + "learning_rate": 2.2475112257785157e-05, + "loss": 1.6641, + "step": 12396 + }, + { + "epoch": 0.6909871244635193, + "grad_norm": 0.5748770833015442, + "learning_rate": 2.246767911153496e-05, + "loss": 1.6881, + "step": 12397 + }, + { + "epoch": 0.6910428627166825, + "grad_norm": 0.543129026889801, + "learning_rate": 2.246024683844944e-05, + "loss": 1.5398, + "step": 12398 + }, + { + "epoch": 0.6910986009698457, + "grad_norm": 0.5681257843971252, + "learning_rate": 2.2452815438764318e-05, + "loss": 1.814, + "step": 12399 + }, + { + "epoch": 0.6911543392230087, + "grad_norm": 0.5826138854026794, + "learning_rate": 2.2445384912715284e-05, + "loss": 1.8071, + "step": 12400 + }, + { + "epoch": 0.6912100774761719, + "grad_norm": 0.5727596879005432, + "learning_rate": 2.2437955260538e-05, + "loss": 1.6608, + "step": 12401 + }, + { + "epoch": 0.6912658157293351, + "grad_norm": 0.6145783066749573, + "learning_rate": 2.2430526482468045e-05, + "loss": 1.862, + "step": 12402 + }, + { + "epoch": 0.6913215539824982, + "grad_norm": 0.5567439794540405, + "learning_rate": 2.2423098578741065e-05, + "loss": 1.4627, + "step": 12403 + }, + { + "epoch": 0.6913772922356614, + "grad_norm": 0.5916569828987122, + "learning_rate": 2.2415671549592632e-05, + "loss": 1.7114, + "step": 12404 + }, + { + "epoch": 0.6914330304888244, + "grad_norm": 0.6020697951316833, + "learning_rate": 2.2408245395258248e-05, + "loss": 1.6241, + "step": 12405 + }, + { + "epoch": 0.6914887687419876, + "grad_norm": 0.5648030042648315, + "learning_rate": 2.2400820115973453e-05, + "loss": 1.6638, + "step": 12406 + }, + { + "epoch": 0.6915445069951508, + "grad_norm": 0.5384600758552551, + "learning_rate": 2.239339571197373e-05, + "loss": 1.4791, + "step": 12407 + }, + { + "epoch": 0.6916002452483139, + "grad_norm": 0.5968599915504456, + "learning_rate": 2.2385972183494552e-05, + "loss": 1.7044, + "step": 12408 + }, + { + "epoch": 0.6916559835014771, + "grad_norm": 0.5620965361595154, + "learning_rate": 2.237854953077132e-05, + "loss": 1.5771, + "step": 12409 + }, + { + "epoch": 0.6917117217546402, + "grad_norm": 0.5662969946861267, + "learning_rate": 2.2371127754039433e-05, + "loss": 1.523, + "step": 12410 + }, + { + "epoch": 0.6917674600078033, + "grad_norm": 0.5784090161323547, + "learning_rate": 2.236370685353433e-05, + "loss": 1.7749, + "step": 12411 + }, + { + "epoch": 0.6918231982609665, + "grad_norm": 0.5956070423126221, + "learning_rate": 2.2356286829491284e-05, + "loss": 1.7331, + "step": 12412 + }, + { + "epoch": 0.6918789365141297, + "grad_norm": 0.5325424075126648, + "learning_rate": 2.2348867682145653e-05, + "loss": 1.299, + "step": 12413 + }, + { + "epoch": 0.6919346747672928, + "grad_norm": 0.6309555768966675, + "learning_rate": 2.2341449411732724e-05, + "loss": 1.7712, + "step": 12414 + }, + { + "epoch": 0.6919904130204559, + "grad_norm": 0.5682843327522278, + "learning_rate": 2.2334032018487772e-05, + "loss": 1.8, + "step": 12415 + }, + { + "epoch": 0.6920461512736191, + "grad_norm": 0.5643319487571716, + "learning_rate": 2.2326615502646002e-05, + "loss": 1.7482, + "step": 12416 + }, + { + "epoch": 0.6921018895267822, + "grad_norm": 0.6528568267822266, + "learning_rate": 2.2319199864442648e-05, + "loss": 1.867, + "step": 12417 + }, + { + "epoch": 0.6921576277799454, + "grad_norm": 0.5698180198669434, + "learning_rate": 2.2311785104112876e-05, + "loss": 1.627, + "step": 12418 + }, + { + "epoch": 0.6922133660331086, + "grad_norm": 0.5689524412155151, + "learning_rate": 2.230437122189185e-05, + "loss": 1.5884, + "step": 12419 + }, + { + "epoch": 0.6922691042862716, + "grad_norm": 0.5394712686538696, + "learning_rate": 2.2296958218014712e-05, + "loss": 1.5532, + "step": 12420 + }, + { + "epoch": 0.6923248425394348, + "grad_norm": 0.5593292713165283, + "learning_rate": 2.22895460927165e-05, + "loss": 1.5991, + "step": 12421 + }, + { + "epoch": 0.692380580792598, + "grad_norm": 0.5734406113624573, + "learning_rate": 2.2282134846232343e-05, + "loss": 1.6068, + "step": 12422 + }, + { + "epoch": 0.6924363190457611, + "grad_norm": 0.5365568399429321, + "learning_rate": 2.227472447879728e-05, + "loss": 1.4699, + "step": 12423 + }, + { + "epoch": 0.6924920572989243, + "grad_norm": 0.5808716416358948, + "learning_rate": 2.2267314990646294e-05, + "loss": 1.7881, + "step": 12424 + }, + { + "epoch": 0.6925477955520875, + "grad_norm": 0.5327333807945251, + "learning_rate": 2.225990638201438e-05, + "loss": 1.4128, + "step": 12425 + }, + { + "epoch": 0.6926035338052505, + "grad_norm": 0.6283466219902039, + "learning_rate": 2.2252498653136493e-05, + "loss": 1.6069, + "step": 12426 + }, + { + "epoch": 0.6926592720584137, + "grad_norm": 0.5366610884666443, + "learning_rate": 2.22450918042476e-05, + "loss": 1.6399, + "step": 12427 + }, + { + "epoch": 0.6927150103115768, + "grad_norm": 0.548111081123352, + "learning_rate": 2.2237685835582527e-05, + "loss": 1.5405, + "step": 12428 + }, + { + "epoch": 0.69277074856474, + "grad_norm": 0.5569949150085449, + "learning_rate": 2.2230280747376216e-05, + "loss": 1.7644, + "step": 12429 + }, + { + "epoch": 0.6928264868179032, + "grad_norm": 0.5301342010498047, + "learning_rate": 2.2222876539863508e-05, + "loss": 1.5258, + "step": 12430 + }, + { + "epoch": 0.6928822250710662, + "grad_norm": 0.5644490122795105, + "learning_rate": 2.221547321327918e-05, + "loss": 1.8579, + "step": 12431 + }, + { + "epoch": 0.6929379633242294, + "grad_norm": 0.529535710811615, + "learning_rate": 2.2208070767858057e-05, + "loss": 1.5001, + "step": 12432 + }, + { + "epoch": 0.6929937015773926, + "grad_norm": 0.5771368145942688, + "learning_rate": 2.2200669203834885e-05, + "loss": 1.6712, + "step": 12433 + }, + { + "epoch": 0.6930494398305557, + "grad_norm": 0.5676137208938599, + "learning_rate": 2.2193268521444428e-05, + "loss": 1.631, + "step": 12434 + }, + { + "epoch": 0.6931051780837189, + "grad_norm": 0.6103230714797974, + "learning_rate": 2.2185868720921342e-05, + "loss": 1.7087, + "step": 12435 + }, + { + "epoch": 0.693160916336882, + "grad_norm": 0.6129918694496155, + "learning_rate": 2.217846980250032e-05, + "loss": 1.7335, + "step": 12436 + }, + { + "epoch": 0.6932166545900451, + "grad_norm": 0.6118063926696777, + "learning_rate": 2.2171071766416064e-05, + "loss": 1.8468, + "step": 12437 + }, + { + "epoch": 0.6932723928432083, + "grad_norm": 0.5562924146652222, + "learning_rate": 2.2163674612903135e-05, + "loss": 1.5575, + "step": 12438 + }, + { + "epoch": 0.6933281310963715, + "grad_norm": 0.6027613282203674, + "learning_rate": 2.215627834219615e-05, + "loss": 1.7773, + "step": 12439 + }, + { + "epoch": 0.6933838693495346, + "grad_norm": 0.5739839673042297, + "learning_rate": 2.2148882954529676e-05, + "loss": 1.7082, + "step": 12440 + }, + { + "epoch": 0.6934396076026977, + "grad_norm": 0.5857069492340088, + "learning_rate": 2.2141488450138277e-05, + "loss": 1.7633, + "step": 12441 + }, + { + "epoch": 0.6934953458558609, + "grad_norm": 0.5265825986862183, + "learning_rate": 2.2134094829256408e-05, + "loss": 1.4418, + "step": 12442 + }, + { + "epoch": 0.693551084109024, + "grad_norm": 0.5409064888954163, + "learning_rate": 2.2126702092118572e-05, + "loss": 1.6666, + "step": 12443 + }, + { + "epoch": 0.6936068223621872, + "grad_norm": 0.5915992259979248, + "learning_rate": 2.2119310238959268e-05, + "loss": 1.8063, + "step": 12444 + }, + { + "epoch": 0.6936625606153504, + "grad_norm": 0.5871009826660156, + "learning_rate": 2.2111919270012866e-05, + "loss": 1.8061, + "step": 12445 + }, + { + "epoch": 0.6937182988685134, + "grad_norm": 0.5730018019676208, + "learning_rate": 2.2104529185513806e-05, + "loss": 1.7359, + "step": 12446 + }, + { + "epoch": 0.6937740371216766, + "grad_norm": 0.5645169019699097, + "learning_rate": 2.2097139985696404e-05, + "loss": 1.7572, + "step": 12447 + }, + { + "epoch": 0.6938297753748398, + "grad_norm": 0.5949046015739441, + "learning_rate": 2.208975167079505e-05, + "loss": 1.8654, + "step": 12448 + }, + { + "epoch": 0.6938855136280029, + "grad_norm": 0.5888786911964417, + "learning_rate": 2.2082364241044068e-05, + "loss": 1.625, + "step": 12449 + }, + { + "epoch": 0.6939412518811661, + "grad_norm": 0.5714291930198669, + "learning_rate": 2.2074977696677703e-05, + "loss": 1.685, + "step": 12450 + }, + { + "epoch": 0.6939969901343291, + "grad_norm": 0.5251734256744385, + "learning_rate": 2.2067592037930224e-05, + "loss": 1.6458, + "step": 12451 + }, + { + "epoch": 0.6940527283874923, + "grad_norm": 0.5464848279953003, + "learning_rate": 2.2060207265035876e-05, + "loss": 1.6008, + "step": 12452 + }, + { + "epoch": 0.6941084666406555, + "grad_norm": 0.5456926226615906, + "learning_rate": 2.205282337822887e-05, + "loss": 1.4996, + "step": 12453 + }, + { + "epoch": 0.6941642048938186, + "grad_norm": 0.5967133641242981, + "learning_rate": 2.2045440377743325e-05, + "loss": 1.8717, + "step": 12454 + }, + { + "epoch": 0.6942199431469818, + "grad_norm": 0.5450711846351624, + "learning_rate": 2.2038058263813443e-05, + "loss": 1.7107, + "step": 12455 + }, + { + "epoch": 0.694275681400145, + "grad_norm": 0.5266870856285095, + "learning_rate": 2.203067703667334e-05, + "loss": 1.4656, + "step": 12456 + }, + { + "epoch": 0.694331419653308, + "grad_norm": 0.6569809317588806, + "learning_rate": 2.202329669655708e-05, + "loss": 1.8354, + "step": 12457 + }, + { + "epoch": 0.6943871579064712, + "grad_norm": 0.5468927621841431, + "learning_rate": 2.2015917243698725e-05, + "loss": 1.6724, + "step": 12458 + }, + { + "epoch": 0.6944428961596344, + "grad_norm": 0.6082443594932556, + "learning_rate": 2.2008538678332314e-05, + "loss": 1.7463, + "step": 12459 + }, + { + "epoch": 0.6944986344127975, + "grad_norm": 0.5773779153823853, + "learning_rate": 2.200116100069188e-05, + "loss": 1.743, + "step": 12460 + }, + { + "epoch": 0.6945543726659607, + "grad_norm": 0.5488123297691345, + "learning_rate": 2.1993784211011353e-05, + "loss": 1.6518, + "step": 12461 + }, + { + "epoch": 0.6946101109191238, + "grad_norm": 0.5357816219329834, + "learning_rate": 2.1986408309524682e-05, + "loss": 1.4703, + "step": 12462 + }, + { + "epoch": 0.6946658491722869, + "grad_norm": 0.5495067238807678, + "learning_rate": 2.197903329646585e-05, + "loss": 1.6126, + "step": 12463 + }, + { + "epoch": 0.6947215874254501, + "grad_norm": 0.5771341323852539, + "learning_rate": 2.1971659172068688e-05, + "loss": 1.8363, + "step": 12464 + }, + { + "epoch": 0.6947773256786133, + "grad_norm": 0.5454638004302979, + "learning_rate": 2.196428593656708e-05, + "loss": 1.3474, + "step": 12465 + }, + { + "epoch": 0.6948330639317764, + "grad_norm": 0.6014922857284546, + "learning_rate": 2.1956913590194867e-05, + "loss": 1.7261, + "step": 12466 + }, + { + "epoch": 0.6948888021849395, + "grad_norm": 0.5554134249687195, + "learning_rate": 2.1949542133185864e-05, + "loss": 1.6184, + "step": 12467 + }, + { + "epoch": 0.6949445404381027, + "grad_norm": 0.6078512072563171, + "learning_rate": 2.194217156577383e-05, + "loss": 1.6595, + "step": 12468 + }, + { + "epoch": 0.6950002786912658, + "grad_norm": 0.5782285928726196, + "learning_rate": 2.1934801888192496e-05, + "loss": 1.4192, + "step": 12469 + }, + { + "epoch": 0.695056016944429, + "grad_norm": 0.6169813275337219, + "learning_rate": 2.1927433100675652e-05, + "loss": 1.9271, + "step": 12470 + }, + { + "epoch": 0.6951117551975922, + "grad_norm": 0.5804049968719482, + "learning_rate": 2.1920065203456946e-05, + "loss": 1.8332, + "step": 12471 + }, + { + "epoch": 0.6951674934507552, + "grad_norm": 0.6012964248657227, + "learning_rate": 2.191269819677007e-05, + "loss": 1.8357, + "step": 12472 + }, + { + "epoch": 0.6952232317039184, + "grad_norm": 0.6622440814971924, + "learning_rate": 2.1905332080848606e-05, + "loss": 1.9264, + "step": 12473 + }, + { + "epoch": 0.6952789699570815, + "grad_norm": 0.544611394405365, + "learning_rate": 2.1897966855926227e-05, + "loss": 1.7122, + "step": 12474 + }, + { + "epoch": 0.6953347082102447, + "grad_norm": 0.5682854652404785, + "learning_rate": 2.189060252223651e-05, + "loss": 1.5732, + "step": 12475 + }, + { + "epoch": 0.6953904464634079, + "grad_norm": 0.5614532232284546, + "learning_rate": 2.1883239080012973e-05, + "loss": 1.6042, + "step": 12476 + }, + { + "epoch": 0.6954461847165709, + "grad_norm": 0.55224609375, + "learning_rate": 2.1875876529489165e-05, + "loss": 1.5583, + "step": 12477 + }, + { + "epoch": 0.6955019229697341, + "grad_norm": 0.5405192971229553, + "learning_rate": 2.1868514870898572e-05, + "loss": 1.6155, + "step": 12478 + }, + { + "epoch": 0.6955576612228973, + "grad_norm": 0.5644908547401428, + "learning_rate": 2.186115410447469e-05, + "loss": 1.506, + "step": 12479 + }, + { + "epoch": 0.6956133994760604, + "grad_norm": 0.5841819047927856, + "learning_rate": 2.1853794230450903e-05, + "loss": 1.5715, + "step": 12480 + }, + { + "epoch": 0.6956691377292236, + "grad_norm": 0.5464922785758972, + "learning_rate": 2.1846435249060677e-05, + "loss": 1.6175, + "step": 12481 + }, + { + "epoch": 0.6957248759823867, + "grad_norm": 0.5380191802978516, + "learning_rate": 2.18390771605374e-05, + "loss": 1.4722, + "step": 12482 + }, + { + "epoch": 0.6957806142355498, + "grad_norm": 0.6160181760787964, + "learning_rate": 2.1831719965114383e-05, + "loss": 1.6391, + "step": 12483 + }, + { + "epoch": 0.695836352488713, + "grad_norm": 0.551240861415863, + "learning_rate": 2.1824363663024976e-05, + "loss": 1.6116, + "step": 12484 + }, + { + "epoch": 0.6958920907418762, + "grad_norm": 0.555523157119751, + "learning_rate": 2.181700825450248e-05, + "loss": 1.7712, + "step": 12485 + }, + { + "epoch": 0.6959478289950393, + "grad_norm": 0.5367977619171143, + "learning_rate": 2.1809653739780182e-05, + "loss": 1.5029, + "step": 12486 + }, + { + "epoch": 0.6960035672482024, + "grad_norm": 0.5227271914482117, + "learning_rate": 2.180230011909129e-05, + "loss": 1.5279, + "step": 12487 + }, + { + "epoch": 0.6960593055013656, + "grad_norm": 0.5195460915565491, + "learning_rate": 2.1794947392669013e-05, + "loss": 1.4994, + "step": 12488 + }, + { + "epoch": 0.6961150437545287, + "grad_norm": 0.6149149537086487, + "learning_rate": 2.1787595560746593e-05, + "loss": 1.7903, + "step": 12489 + }, + { + "epoch": 0.6961707820076919, + "grad_norm": 0.587485671043396, + "learning_rate": 2.178024462355714e-05, + "loss": 1.5443, + "step": 12490 + }, + { + "epoch": 0.6962265202608551, + "grad_norm": 0.550566554069519, + "learning_rate": 2.1772894581333792e-05, + "loss": 1.5959, + "step": 12491 + }, + { + "epoch": 0.6962822585140181, + "grad_norm": 0.5332329869270325, + "learning_rate": 2.176554543430965e-05, + "loss": 1.4327, + "step": 12492 + }, + { + "epoch": 0.6963379967671813, + "grad_norm": 0.5670337677001953, + "learning_rate": 2.175819718271781e-05, + "loss": 1.7718, + "step": 12493 + }, + { + "epoch": 0.6963937350203445, + "grad_norm": 0.5738561153411865, + "learning_rate": 2.1750849826791275e-05, + "loss": 1.5627, + "step": 12494 + }, + { + "epoch": 0.6964494732735076, + "grad_norm": 0.5175594687461853, + "learning_rate": 2.1743503366763058e-05, + "loss": 1.6201, + "step": 12495 + }, + { + "epoch": 0.6965052115266708, + "grad_norm": 0.5937666296958923, + "learning_rate": 2.173615780286621e-05, + "loss": 1.6484, + "step": 12496 + }, + { + "epoch": 0.6965609497798338, + "grad_norm": 0.5607738494873047, + "learning_rate": 2.172881313533362e-05, + "loss": 1.5867, + "step": 12497 + }, + { + "epoch": 0.696616688032997, + "grad_norm": 0.5806588530540466, + "learning_rate": 2.1721469364398274e-05, + "loss": 1.6964, + "step": 12498 + }, + { + "epoch": 0.6966724262861602, + "grad_norm": 0.5884150862693787, + "learning_rate": 2.1714126490292998e-05, + "loss": 1.4694, + "step": 12499 + }, + { + "epoch": 0.6967281645393233, + "grad_norm": 0.5738844275474548, + "learning_rate": 2.1706784513250734e-05, + "loss": 1.679, + "step": 12500 + }, + { + "epoch": 0.6967839027924865, + "grad_norm": 0.5930630564689636, + "learning_rate": 2.1699443433504326e-05, + "loss": 1.8925, + "step": 12501 + }, + { + "epoch": 0.6968396410456497, + "grad_norm": 0.5870788097381592, + "learning_rate": 2.1692103251286544e-05, + "loss": 1.5665, + "step": 12502 + }, + { + "epoch": 0.6968953792988127, + "grad_norm": 0.5544155836105347, + "learning_rate": 2.1684763966830208e-05, + "loss": 1.5741, + "step": 12503 + }, + { + "epoch": 0.6969511175519759, + "grad_norm": 0.5461851358413696, + "learning_rate": 2.167742558036806e-05, + "loss": 1.6109, + "step": 12504 + }, + { + "epoch": 0.6970068558051391, + "grad_norm": 0.5209200382232666, + "learning_rate": 2.1670088092132866e-05, + "loss": 1.5966, + "step": 12505 + }, + { + "epoch": 0.6970625940583022, + "grad_norm": 0.5700559020042419, + "learning_rate": 2.1662751502357265e-05, + "loss": 1.7803, + "step": 12506 + }, + { + "epoch": 0.6971183323114654, + "grad_norm": 0.5122175216674805, + "learning_rate": 2.1655415811273988e-05, + "loss": 1.366, + "step": 12507 + }, + { + "epoch": 0.6971740705646285, + "grad_norm": 0.5897361636161804, + "learning_rate": 2.1648081019115675e-05, + "loss": 1.7152, + "step": 12508 + }, + { + "epoch": 0.6972298088177916, + "grad_norm": 0.5518897771835327, + "learning_rate": 2.1640747126114915e-05, + "loss": 1.6061, + "step": 12509 + }, + { + "epoch": 0.6972855470709548, + "grad_norm": 0.5426011085510254, + "learning_rate": 2.163341413250431e-05, + "loss": 1.455, + "step": 12510 + }, + { + "epoch": 0.697341285324118, + "grad_norm": 0.5575090646743774, + "learning_rate": 2.1626082038516415e-05, + "loss": 1.554, + "step": 12511 + }, + { + "epoch": 0.6973970235772811, + "grad_norm": 0.5110504627227783, + "learning_rate": 2.161875084438379e-05, + "loss": 1.4238, + "step": 12512 + }, + { + "epoch": 0.6974527618304442, + "grad_norm": 0.5228980779647827, + "learning_rate": 2.1611420550338894e-05, + "loss": 1.6579, + "step": 12513 + }, + { + "epoch": 0.6975085000836074, + "grad_norm": 0.5784720778465271, + "learning_rate": 2.1604091156614204e-05, + "loss": 1.7723, + "step": 12514 + }, + { + "epoch": 0.6975642383367705, + "grad_norm": 0.546317994594574, + "learning_rate": 2.1596762663442218e-05, + "loss": 1.5309, + "step": 12515 + }, + { + "epoch": 0.6976199765899337, + "grad_norm": 0.5592935085296631, + "learning_rate": 2.1589435071055296e-05, + "loss": 1.6055, + "step": 12516 + }, + { + "epoch": 0.6976757148430969, + "grad_norm": 0.5744695067405701, + "learning_rate": 2.1582108379685856e-05, + "loss": 1.8028, + "step": 12517 + }, + { + "epoch": 0.69773145309626, + "grad_norm": 0.5620167255401611, + "learning_rate": 2.1574782589566244e-05, + "loss": 1.6126, + "step": 12518 + }, + { + "epoch": 0.6977871913494231, + "grad_norm": 0.5813114047050476, + "learning_rate": 2.1567457700928822e-05, + "loss": 1.6897, + "step": 12519 + }, + { + "epoch": 0.6978429296025862, + "grad_norm": 0.5728158950805664, + "learning_rate": 2.1560133714005848e-05, + "loss": 1.5911, + "step": 12520 + }, + { + "epoch": 0.6978986678557494, + "grad_norm": 0.5162991881370544, + "learning_rate": 2.1552810629029596e-05, + "loss": 1.7061, + "step": 12521 + }, + { + "epoch": 0.6979544061089126, + "grad_norm": 0.5759060978889465, + "learning_rate": 2.154548844623237e-05, + "loss": 1.5237, + "step": 12522 + }, + { + "epoch": 0.6980101443620756, + "grad_norm": 0.5483187437057495, + "learning_rate": 2.1538167165846333e-05, + "loss": 1.7261, + "step": 12523 + }, + { + "epoch": 0.6980658826152388, + "grad_norm": 0.56321120262146, + "learning_rate": 2.1530846788103686e-05, + "loss": 1.7511, + "step": 12524 + }, + { + "epoch": 0.698121620868402, + "grad_norm": 0.5477744936943054, + "learning_rate": 2.1523527313236598e-05, + "loss": 1.6178, + "step": 12525 + }, + { + "epoch": 0.6981773591215651, + "grad_norm": 0.5206699371337891, + "learning_rate": 2.1516208741477207e-05, + "loss": 1.436, + "step": 12526 + }, + { + "epoch": 0.6982330973747283, + "grad_norm": 0.5443151593208313, + "learning_rate": 2.1508891073057587e-05, + "loss": 1.4729, + "step": 12527 + }, + { + "epoch": 0.6982888356278915, + "grad_norm": 0.6137494444847107, + "learning_rate": 2.1501574308209828e-05, + "loss": 1.9092, + "step": 12528 + }, + { + "epoch": 0.6983445738810545, + "grad_norm": 0.6065635085105896, + "learning_rate": 2.1494258447165973e-05, + "loss": 1.6061, + "step": 12529 + }, + { + "epoch": 0.6984003121342177, + "grad_norm": 0.6359501481056213, + "learning_rate": 2.1486943490158034e-05, + "loss": 1.828, + "step": 12530 + }, + { + "epoch": 0.6984560503873809, + "grad_norm": 0.5409738421440125, + "learning_rate": 2.1479629437418032e-05, + "loss": 1.8147, + "step": 12531 + }, + { + "epoch": 0.698511788640544, + "grad_norm": 0.5747645497322083, + "learning_rate": 2.1472316289177856e-05, + "loss": 1.6662, + "step": 12532 + }, + { + "epoch": 0.6985675268937072, + "grad_norm": 0.5804151892662048, + "learning_rate": 2.1465004045669505e-05, + "loss": 1.5294, + "step": 12533 + }, + { + "epoch": 0.6986232651468703, + "grad_norm": 0.574507474899292, + "learning_rate": 2.145769270712487e-05, + "loss": 1.7331, + "step": 12534 + }, + { + "epoch": 0.6986790034000334, + "grad_norm": 0.5345951318740845, + "learning_rate": 2.1450382273775788e-05, + "loss": 1.5622, + "step": 12535 + }, + { + "epoch": 0.6987347416531966, + "grad_norm": 0.6589462161064148, + "learning_rate": 2.144307274585413e-05, + "loss": 1.418, + "step": 12536 + }, + { + "epoch": 0.6987904799063598, + "grad_norm": 0.5831825137138367, + "learning_rate": 2.14357641235917e-05, + "loss": 1.5661, + "step": 12537 + }, + { + "epoch": 0.6988462181595229, + "grad_norm": 0.5969269275665283, + "learning_rate": 2.1428456407220315e-05, + "loss": 1.8971, + "step": 12538 + }, + { + "epoch": 0.698901956412686, + "grad_norm": 0.5822701454162598, + "learning_rate": 2.142114959697169e-05, + "loss": 1.5624, + "step": 12539 + }, + { + "epoch": 0.6989576946658492, + "grad_norm": 0.5579544901847839, + "learning_rate": 2.1413843693077552e-05, + "loss": 1.7243, + "step": 12540 + }, + { + "epoch": 0.6990134329190123, + "grad_norm": 0.5481868982315063, + "learning_rate": 2.140653869576966e-05, + "loss": 1.5812, + "step": 12541 + }, + { + "epoch": 0.6990691711721755, + "grad_norm": 0.5613032579421997, + "learning_rate": 2.1399234605279634e-05, + "loss": 1.6288, + "step": 12542 + }, + { + "epoch": 0.6991249094253386, + "grad_norm": 0.5468133091926575, + "learning_rate": 2.1391931421839127e-05, + "loss": 1.6193, + "step": 12543 + }, + { + "epoch": 0.6991806476785017, + "grad_norm": 0.5905917882919312, + "learning_rate": 2.1384629145679765e-05, + "loss": 1.8533, + "step": 12544 + }, + { + "epoch": 0.6992363859316649, + "grad_norm": 0.5613247752189636, + "learning_rate": 2.137732777703314e-05, + "loss": 1.8032, + "step": 12545 + }, + { + "epoch": 0.699292124184828, + "grad_norm": 0.5663119554519653, + "learning_rate": 2.137002731613078e-05, + "loss": 1.8345, + "step": 12546 + }, + { + "epoch": 0.6993478624379912, + "grad_norm": 0.5337582230567932, + "learning_rate": 2.1362727763204216e-05, + "loss": 1.6405, + "step": 12547 + }, + { + "epoch": 0.6994036006911544, + "grad_norm": 0.5438380241394043, + "learning_rate": 2.1355429118484986e-05, + "loss": 1.4639, + "step": 12548 + }, + { + "epoch": 0.6994593389443174, + "grad_norm": 0.5389162302017212, + "learning_rate": 2.1348131382204527e-05, + "loss": 1.6657, + "step": 12549 + }, + { + "epoch": 0.6995150771974806, + "grad_norm": 0.574306845664978, + "learning_rate": 2.1340834554594287e-05, + "loss": 1.7891, + "step": 12550 + }, + { + "epoch": 0.6995708154506438, + "grad_norm": 0.653531014919281, + "learning_rate": 2.1333538635885674e-05, + "loss": 1.9755, + "step": 12551 + }, + { + "epoch": 0.6996265537038069, + "grad_norm": 0.54327791929245, + "learning_rate": 2.13262436263101e-05, + "loss": 1.4889, + "step": 12552 + }, + { + "epoch": 0.6996822919569701, + "grad_norm": 0.5144495964050293, + "learning_rate": 2.131894952609888e-05, + "loss": 1.3855, + "step": 12553 + }, + { + "epoch": 0.6997380302101333, + "grad_norm": 0.6167160272598267, + "learning_rate": 2.131165633548336e-05, + "loss": 1.8536, + "step": 12554 + }, + { + "epoch": 0.6997937684632963, + "grad_norm": 0.5398876070976257, + "learning_rate": 2.1304364054694835e-05, + "loss": 1.6022, + "step": 12555 + }, + { + "epoch": 0.6998495067164595, + "grad_norm": 0.5648753046989441, + "learning_rate": 2.129707268396458e-05, + "loss": 1.812, + "step": 12556 + }, + { + "epoch": 0.6999052449696227, + "grad_norm": 0.5736165642738342, + "learning_rate": 2.1289782223523848e-05, + "loss": 1.7548, + "step": 12557 + }, + { + "epoch": 0.6999609832227858, + "grad_norm": 0.5434161424636841, + "learning_rate": 2.1282492673603788e-05, + "loss": 1.5542, + "step": 12558 + }, + { + "epoch": 0.700016721475949, + "grad_norm": 0.5680014491081238, + "learning_rate": 2.1275204034435647e-05, + "loss": 1.7433, + "step": 12559 + }, + { + "epoch": 0.7000724597291121, + "grad_norm": 0.6389971375465393, + "learning_rate": 2.1267916306250573e-05, + "loss": 1.7956, + "step": 12560 + }, + { + "epoch": 0.7001281979822752, + "grad_norm": 0.5255822539329529, + "learning_rate": 2.126062948927966e-05, + "loss": 1.1928, + "step": 12561 + }, + { + "epoch": 0.7001839362354384, + "grad_norm": 0.5520752668380737, + "learning_rate": 2.1253343583754016e-05, + "loss": 1.6835, + "step": 12562 + }, + { + "epoch": 0.7002396744886016, + "grad_norm": 0.6200222373008728, + "learning_rate": 2.124605858990471e-05, + "loss": 1.7763, + "step": 12563 + }, + { + "epoch": 0.7002954127417647, + "grad_norm": 0.5540696382522583, + "learning_rate": 2.1238774507962795e-05, + "loss": 1.5703, + "step": 12564 + }, + { + "epoch": 0.7003511509949278, + "grad_norm": 0.5841526389122009, + "learning_rate": 2.123149133815925e-05, + "loss": 1.7078, + "step": 12565 + }, + { + "epoch": 0.7004068892480909, + "grad_norm": 0.568084716796875, + "learning_rate": 2.1224209080725042e-05, + "loss": 1.6979, + "step": 12566 + }, + { + "epoch": 0.7004626275012541, + "grad_norm": 0.5143046379089355, + "learning_rate": 2.1216927735891183e-05, + "loss": 1.3949, + "step": 12567 + }, + { + "epoch": 0.7005183657544173, + "grad_norm": 0.5790497064590454, + "learning_rate": 2.1209647303888546e-05, + "loss": 1.6486, + "step": 12568 + }, + { + "epoch": 0.7005741040075804, + "grad_norm": 0.5869383811950684, + "learning_rate": 2.1202367784948036e-05, + "loss": 1.7111, + "step": 12569 + }, + { + "epoch": 0.7006298422607435, + "grad_norm": 0.5924579501152039, + "learning_rate": 2.119508917930052e-05, + "loss": 1.5828, + "step": 12570 + }, + { + "epoch": 0.7006855805139067, + "grad_norm": 0.5691964030265808, + "learning_rate": 2.1187811487176845e-05, + "loss": 1.499, + "step": 12571 + }, + { + "epoch": 0.7007413187670698, + "grad_norm": 0.6078161001205444, + "learning_rate": 2.1180534708807787e-05, + "loss": 1.6988, + "step": 12572 + }, + { + "epoch": 0.700797057020233, + "grad_norm": 0.539812445640564, + "learning_rate": 2.117325884442412e-05, + "loss": 1.3717, + "step": 12573 + }, + { + "epoch": 0.7008527952733962, + "grad_norm": 0.5669495463371277, + "learning_rate": 2.1165983894256647e-05, + "loss": 1.5043, + "step": 12574 + }, + { + "epoch": 0.7009085335265592, + "grad_norm": 0.5549720525741577, + "learning_rate": 2.1158709858536037e-05, + "loss": 1.602, + "step": 12575 + }, + { + "epoch": 0.7009642717797224, + "grad_norm": 0.5545222759246826, + "learning_rate": 2.115143673749299e-05, + "loss": 1.6733, + "step": 12576 + }, + { + "epoch": 0.7010200100328856, + "grad_norm": 0.6436394453048706, + "learning_rate": 2.114416453135817e-05, + "loss": 1.8525, + "step": 12577 + }, + { + "epoch": 0.7010757482860487, + "grad_norm": 0.5488054156303406, + "learning_rate": 2.1136893240362226e-05, + "loss": 1.7004, + "step": 12578 + }, + { + "epoch": 0.7011314865392119, + "grad_norm": 0.5736593008041382, + "learning_rate": 2.112962286473573e-05, + "loss": 1.5932, + "step": 12579 + }, + { + "epoch": 0.701187224792375, + "grad_norm": 0.5578902363777161, + "learning_rate": 2.1122353404709274e-05, + "loss": 1.5578, + "step": 12580 + }, + { + "epoch": 0.7012429630455381, + "grad_norm": 0.5767555236816406, + "learning_rate": 2.1115084860513395e-05, + "loss": 1.8148, + "step": 12581 + }, + { + "epoch": 0.7012987012987013, + "grad_norm": 0.6967010498046875, + "learning_rate": 2.1107817232378618e-05, + "loss": 1.7272, + "step": 12582 + }, + { + "epoch": 0.7013544395518645, + "grad_norm": 0.5739030838012695, + "learning_rate": 2.110055052053544e-05, + "loss": 1.6468, + "step": 12583 + }, + { + "epoch": 0.7014101778050276, + "grad_norm": 0.5442588925361633, + "learning_rate": 2.1093284725214268e-05, + "loss": 1.5593, + "step": 12584 + }, + { + "epoch": 0.7014659160581908, + "grad_norm": 0.5849565863609314, + "learning_rate": 2.1086019846645582e-05, + "loss": 1.6528, + "step": 12585 + }, + { + "epoch": 0.7015216543113539, + "grad_norm": 0.6619828343391418, + "learning_rate": 2.1078755885059786e-05, + "loss": 1.9402, + "step": 12586 + }, + { + "epoch": 0.701577392564517, + "grad_norm": 0.5421179533004761, + "learning_rate": 2.1071492840687218e-05, + "loss": 1.6465, + "step": 12587 + }, + { + "epoch": 0.7016331308176802, + "grad_norm": 0.5201606154441833, + "learning_rate": 2.1064230713758225e-05, + "loss": 1.5343, + "step": 12588 + }, + { + "epoch": 0.7016888690708433, + "grad_norm": 0.5774264931678772, + "learning_rate": 2.1056969504503134e-05, + "loss": 1.7163, + "step": 12589 + }, + { + "epoch": 0.7017446073240065, + "grad_norm": 0.5549290776252747, + "learning_rate": 2.104970921315223e-05, + "loss": 1.6034, + "step": 12590 + }, + { + "epoch": 0.7018003455771696, + "grad_norm": 0.5619807243347168, + "learning_rate": 2.1042449839935747e-05, + "loss": 1.7492, + "step": 12591 + }, + { + "epoch": 0.7018560838303327, + "grad_norm": 0.6009867787361145, + "learning_rate": 2.1035191385083895e-05, + "loss": 1.8769, + "step": 12592 + }, + { + "epoch": 0.7019118220834959, + "grad_norm": 0.5830333232879639, + "learning_rate": 2.1027933848826942e-05, + "loss": 1.7465, + "step": 12593 + }, + { + "epoch": 0.7019675603366591, + "grad_norm": 0.6390556693077087, + "learning_rate": 2.1020677231394982e-05, + "loss": 1.7793, + "step": 12594 + }, + { + "epoch": 0.7020232985898222, + "grad_norm": 0.583836555480957, + "learning_rate": 2.1013421533018184e-05, + "loss": 1.5743, + "step": 12595 + }, + { + "epoch": 0.7020790368429853, + "grad_norm": 0.5856710076332092, + "learning_rate": 2.1006166753926648e-05, + "loss": 1.6089, + "step": 12596 + }, + { + "epoch": 0.7021347750961485, + "grad_norm": 0.5670978426933289, + "learning_rate": 2.0998912894350477e-05, + "loss": 1.6831, + "step": 12597 + }, + { + "epoch": 0.7021905133493116, + "grad_norm": 0.610052764415741, + "learning_rate": 2.0991659954519682e-05, + "loss": 1.787, + "step": 12598 + }, + { + "epoch": 0.7022462516024748, + "grad_norm": 0.5299352407455444, + "learning_rate": 2.0984407934664287e-05, + "loss": 1.5232, + "step": 12599 + }, + { + "epoch": 0.702301989855638, + "grad_norm": 0.5819052457809448, + "learning_rate": 2.097715683501433e-05, + "loss": 1.7159, + "step": 12600 + }, + { + "epoch": 0.702357728108801, + "grad_norm": 0.5537623167037964, + "learning_rate": 2.0969906655799732e-05, + "loss": 1.6153, + "step": 12601 + }, + { + "epoch": 0.7024134663619642, + "grad_norm": 0.5379827618598938, + "learning_rate": 2.0962657397250433e-05, + "loss": 1.5843, + "step": 12602 + }, + { + "epoch": 0.7024692046151274, + "grad_norm": 0.628884494304657, + "learning_rate": 2.0955409059596348e-05, + "loss": 1.6255, + "step": 12603 + }, + { + "epoch": 0.7025249428682905, + "grad_norm": 0.5172703266143799, + "learning_rate": 2.094816164306736e-05, + "loss": 1.5451, + "step": 12604 + }, + { + "epoch": 0.7025806811214537, + "grad_norm": 0.5739989876747131, + "learning_rate": 2.094091514789328e-05, + "loss": 1.4511, + "step": 12605 + }, + { + "epoch": 0.7026364193746168, + "grad_norm": 0.5497764945030212, + "learning_rate": 2.093366957430395e-05, + "loss": 1.5672, + "step": 12606 + }, + { + "epoch": 0.7026921576277799, + "grad_norm": 0.5838956832885742, + "learning_rate": 2.092642492252915e-05, + "loss": 1.636, + "step": 12607 + }, + { + "epoch": 0.7027478958809431, + "grad_norm": 0.624302327632904, + "learning_rate": 2.0919181192798644e-05, + "loss": 1.7725, + "step": 12608 + }, + { + "epoch": 0.7028036341341063, + "grad_norm": 0.5599181056022644, + "learning_rate": 2.091193838534217e-05, + "loss": 1.467, + "step": 12609 + }, + { + "epoch": 0.7028593723872694, + "grad_norm": 0.5655273199081421, + "learning_rate": 2.090469650038938e-05, + "loss": 1.5876, + "step": 12610 + }, + { + "epoch": 0.7029151106404325, + "grad_norm": 0.5795032978057861, + "learning_rate": 2.089745553817e-05, + "loss": 1.698, + "step": 12611 + }, + { + "epoch": 0.7029708488935956, + "grad_norm": 0.5137896537780762, + "learning_rate": 2.0890215498913668e-05, + "loss": 1.5782, + "step": 12612 + }, + { + "epoch": 0.7030265871467588, + "grad_norm": 0.569449245929718, + "learning_rate": 2.0882976382849962e-05, + "loss": 1.7965, + "step": 12613 + }, + { + "epoch": 0.703082325399922, + "grad_norm": 0.6196072101593018, + "learning_rate": 2.0875738190208483e-05, + "loss": 1.6878, + "step": 12614 + }, + { + "epoch": 0.7031380636530851, + "grad_norm": 0.578255295753479, + "learning_rate": 2.0868500921218775e-05, + "loss": 1.5877, + "step": 12615 + }, + { + "epoch": 0.7031938019062483, + "grad_norm": 0.5548200607299805, + "learning_rate": 2.0861264576110395e-05, + "loss": 1.54, + "step": 12616 + }, + { + "epoch": 0.7032495401594114, + "grad_norm": 0.591273844242096, + "learning_rate": 2.085402915511277e-05, + "loss": 1.9004, + "step": 12617 + }, + { + "epoch": 0.7033052784125745, + "grad_norm": 0.5834256410598755, + "learning_rate": 2.0846794658455433e-05, + "loss": 1.7008, + "step": 12618 + }, + { + "epoch": 0.7033610166657377, + "grad_norm": 0.5561612248420715, + "learning_rate": 2.0839561086367802e-05, + "loss": 1.6724, + "step": 12619 + }, + { + "epoch": 0.7034167549189009, + "grad_norm": 0.6206260323524475, + "learning_rate": 2.0832328439079268e-05, + "loss": 1.4036, + "step": 12620 + }, + { + "epoch": 0.703472493172064, + "grad_norm": 0.6796298027038574, + "learning_rate": 2.082509671681921e-05, + "loss": 1.6769, + "step": 12621 + }, + { + "epoch": 0.7035282314252271, + "grad_norm": 0.578867495059967, + "learning_rate": 2.0817865919816988e-05, + "loss": 1.7971, + "step": 12622 + }, + { + "epoch": 0.7035839696783903, + "grad_norm": 0.5739205479621887, + "learning_rate": 2.081063604830193e-05, + "loss": 1.7429, + "step": 12623 + }, + { + "epoch": 0.7036397079315534, + "grad_norm": 0.5878620147705078, + "learning_rate": 2.0803407102503293e-05, + "loss": 1.6767, + "step": 12624 + }, + { + "epoch": 0.7036954461847166, + "grad_norm": 0.5952854156494141, + "learning_rate": 2.0796179082650336e-05, + "loss": 1.8749, + "step": 12625 + }, + { + "epoch": 0.7037511844378798, + "grad_norm": 0.5622190833091736, + "learning_rate": 2.0788951988972345e-05, + "loss": 1.6783, + "step": 12626 + }, + { + "epoch": 0.7038069226910428, + "grad_norm": 0.514674186706543, + "learning_rate": 2.0781725821698466e-05, + "loss": 1.3523, + "step": 12627 + }, + { + "epoch": 0.703862660944206, + "grad_norm": 0.5285819172859192, + "learning_rate": 2.0774500581057892e-05, + "loss": 1.5957, + "step": 12628 + }, + { + "epoch": 0.7039183991973692, + "grad_norm": 0.6194326877593994, + "learning_rate": 2.076727626727976e-05, + "loss": 1.7849, + "step": 12629 + }, + { + "epoch": 0.7039741374505323, + "grad_norm": 0.588029682636261, + "learning_rate": 2.0760052880593213e-05, + "loss": 1.7172, + "step": 12630 + }, + { + "epoch": 0.7040298757036955, + "grad_norm": 0.5699478983879089, + "learning_rate": 2.0752830421227277e-05, + "loss": 1.72, + "step": 12631 + }, + { + "epoch": 0.7040856139568586, + "grad_norm": 0.5345055460929871, + "learning_rate": 2.0745608889411044e-05, + "loss": 1.5975, + "step": 12632 + }, + { + "epoch": 0.7041413522100217, + "grad_norm": 0.5528733134269714, + "learning_rate": 2.0738388285373533e-05, + "loss": 1.6038, + "step": 12633 + }, + { + "epoch": 0.7041970904631849, + "grad_norm": 0.5432607531547546, + "learning_rate": 2.0731168609343737e-05, + "loss": 1.5777, + "step": 12634 + }, + { + "epoch": 0.704252828716348, + "grad_norm": 0.5677303671836853, + "learning_rate": 2.072394986155064e-05, + "loss": 1.7384, + "step": 12635 + }, + { + "epoch": 0.7043085669695112, + "grad_norm": 0.5520053505897522, + "learning_rate": 2.071673204222313e-05, + "loss": 1.5779, + "step": 12636 + }, + { + "epoch": 0.7043643052226743, + "grad_norm": 0.5608752965927124, + "learning_rate": 2.070951515159016e-05, + "loss": 1.6983, + "step": 12637 + }, + { + "epoch": 0.7044200434758374, + "grad_norm": 0.5688676238059998, + "learning_rate": 2.0702299189880613e-05, + "loss": 1.8005, + "step": 12638 + }, + { + "epoch": 0.7044757817290006, + "grad_norm": 0.5453701019287109, + "learning_rate": 2.0695084157323303e-05, + "loss": 1.5594, + "step": 12639 + }, + { + "epoch": 0.7045315199821638, + "grad_norm": 0.5923493504524231, + "learning_rate": 2.0687870054147062e-05, + "loss": 1.7295, + "step": 12640 + }, + { + "epoch": 0.7045872582353269, + "grad_norm": 0.5711904764175415, + "learning_rate": 2.068065688058068e-05, + "loss": 1.7237, + "step": 12641 + }, + { + "epoch": 0.70464299648849, + "grad_norm": 0.5311852097511292, + "learning_rate": 2.067344463685294e-05, + "loss": 1.3802, + "step": 12642 + }, + { + "epoch": 0.7046987347416532, + "grad_norm": 0.6140351295471191, + "learning_rate": 2.0666233323192515e-05, + "loss": 1.6697, + "step": 12643 + }, + { + "epoch": 0.7047544729948163, + "grad_norm": 0.5683553218841553, + "learning_rate": 2.0659022939828154e-05, + "loss": 1.604, + "step": 12644 + }, + { + "epoch": 0.7048102112479795, + "grad_norm": 0.5510280132293701, + "learning_rate": 2.0651813486988535e-05, + "loss": 1.7428, + "step": 12645 + }, + { + "epoch": 0.7048659495011427, + "grad_norm": 0.5744211077690125, + "learning_rate": 2.0644604964902264e-05, + "loss": 1.7455, + "step": 12646 + }, + { + "epoch": 0.7049216877543057, + "grad_norm": 0.5572615265846252, + "learning_rate": 2.063739737379797e-05, + "loss": 1.5011, + "step": 12647 + }, + { + "epoch": 0.7049774260074689, + "grad_norm": 0.5855537056922913, + "learning_rate": 2.063019071390423e-05, + "loss": 1.7493, + "step": 12648 + }, + { + "epoch": 0.7050331642606321, + "grad_norm": 0.5825347304344177, + "learning_rate": 2.062298498544963e-05, + "loss": 1.741, + "step": 12649 + }, + { + "epoch": 0.7050889025137952, + "grad_norm": 0.5738754868507385, + "learning_rate": 2.0615780188662642e-05, + "loss": 1.6665, + "step": 12650 + }, + { + "epoch": 0.7051446407669584, + "grad_norm": 0.5652052760124207, + "learning_rate": 2.0608576323771767e-05, + "loss": 1.4688, + "step": 12651 + }, + { + "epoch": 0.7052003790201216, + "grad_norm": 0.5375339388847351, + "learning_rate": 2.0601373391005525e-05, + "loss": 1.584, + "step": 12652 + }, + { + "epoch": 0.7052561172732846, + "grad_norm": 0.5722372531890869, + "learning_rate": 2.0594171390592294e-05, + "loss": 1.729, + "step": 12653 + }, + { + "epoch": 0.7053118555264478, + "grad_norm": 0.5661969184875488, + "learning_rate": 2.0586970322760498e-05, + "loss": 1.7496, + "step": 12654 + }, + { + "epoch": 0.705367593779611, + "grad_norm": 0.5383875966072083, + "learning_rate": 2.057977018773851e-05, + "loss": 1.5804, + "step": 12655 + }, + { + "epoch": 0.7054233320327741, + "grad_norm": 0.5743109583854675, + "learning_rate": 2.057257098575471e-05, + "loss": 1.5512, + "step": 12656 + }, + { + "epoch": 0.7054790702859373, + "grad_norm": 0.622540295124054, + "learning_rate": 2.0565372717037356e-05, + "loss": 1.7573, + "step": 12657 + }, + { + "epoch": 0.7055348085391003, + "grad_norm": 0.629591166973114, + "learning_rate": 2.0558175381814766e-05, + "loss": 1.9962, + "step": 12658 + }, + { + "epoch": 0.7055905467922635, + "grad_norm": 0.5481202006340027, + "learning_rate": 2.0550978980315194e-05, + "loss": 1.6104, + "step": 12659 + }, + { + "epoch": 0.7056462850454267, + "grad_norm": 0.5914950370788574, + "learning_rate": 2.0543783512766873e-05, + "loss": 1.6372, + "step": 12660 + }, + { + "epoch": 0.7057020232985898, + "grad_norm": 0.553175687789917, + "learning_rate": 2.0536588979398013e-05, + "loss": 1.5143, + "step": 12661 + }, + { + "epoch": 0.705757761551753, + "grad_norm": 0.5907781720161438, + "learning_rate": 2.0529395380436727e-05, + "loss": 1.7892, + "step": 12662 + }, + { + "epoch": 0.7058134998049161, + "grad_norm": 0.5549091696739197, + "learning_rate": 2.052220271611124e-05, + "loss": 1.6492, + "step": 12663 + }, + { + "epoch": 0.7058692380580792, + "grad_norm": 0.5427672266960144, + "learning_rate": 2.051501098664959e-05, + "loss": 1.6053, + "step": 12664 + }, + { + "epoch": 0.7059249763112424, + "grad_norm": 0.5447436571121216, + "learning_rate": 2.050782019227988e-05, + "loss": 1.475, + "step": 12665 + }, + { + "epoch": 0.7059807145644056, + "grad_norm": 0.5734901428222656, + "learning_rate": 2.0500630333230168e-05, + "loss": 1.7296, + "step": 12666 + }, + { + "epoch": 0.7060364528175687, + "grad_norm": 0.580880343914032, + "learning_rate": 2.0493441409728466e-05, + "loss": 1.7089, + "step": 12667 + }, + { + "epoch": 0.7060921910707318, + "grad_norm": 0.5470337271690369, + "learning_rate": 2.0486253422002784e-05, + "loss": 1.5953, + "step": 12668 + }, + { + "epoch": 0.706147929323895, + "grad_norm": 0.5712233781814575, + "learning_rate": 2.047906637028103e-05, + "loss": 1.7162, + "step": 12669 + }, + { + "epoch": 0.7062036675770581, + "grad_norm": 0.6004396080970764, + "learning_rate": 2.047188025479119e-05, + "loss": 1.5502, + "step": 12670 + }, + { + "epoch": 0.7062594058302213, + "grad_norm": 0.5722224116325378, + "learning_rate": 2.046469507576117e-05, + "loss": 1.9175, + "step": 12671 + }, + { + "epoch": 0.7063151440833845, + "grad_norm": 0.5458431839942932, + "learning_rate": 2.0457510833418796e-05, + "loss": 1.6203, + "step": 12672 + }, + { + "epoch": 0.7063708823365475, + "grad_norm": 0.5887515544891357, + "learning_rate": 2.045032752799194e-05, + "loss": 1.7017, + "step": 12673 + }, + { + "epoch": 0.7064266205897107, + "grad_norm": 0.580519437789917, + "learning_rate": 2.0443145159708405e-05, + "loss": 1.7859, + "step": 12674 + }, + { + "epoch": 0.7064823588428739, + "grad_norm": 0.5798778533935547, + "learning_rate": 2.0435963728795992e-05, + "loss": 1.7632, + "step": 12675 + }, + { + "epoch": 0.706538097096037, + "grad_norm": 0.5585095286369324, + "learning_rate": 2.0428783235482424e-05, + "loss": 1.5312, + "step": 12676 + }, + { + "epoch": 0.7065938353492002, + "grad_norm": 0.5716522336006165, + "learning_rate": 2.042160367999542e-05, + "loss": 1.5461, + "step": 12677 + }, + { + "epoch": 0.7066495736023634, + "grad_norm": 0.5700616240501404, + "learning_rate": 2.041442506256273e-05, + "loss": 1.7262, + "step": 12678 + }, + { + "epoch": 0.7067053118555264, + "grad_norm": 0.5960610508918762, + "learning_rate": 2.0407247383411966e-05, + "loss": 1.7994, + "step": 12679 + }, + { + "epoch": 0.7067610501086896, + "grad_norm": 0.5809378027915955, + "learning_rate": 2.0400070642770775e-05, + "loss": 1.7502, + "step": 12680 + }, + { + "epoch": 0.7068167883618527, + "grad_norm": 0.6252628564834595, + "learning_rate": 2.0392894840866767e-05, + "loss": 1.8929, + "step": 12681 + }, + { + "epoch": 0.7068725266150159, + "grad_norm": 0.6130125522613525, + "learning_rate": 2.0385719977927526e-05, + "loss": 1.8354, + "step": 12682 + }, + { + "epoch": 0.7069282648681791, + "grad_norm": 0.5739142894744873, + "learning_rate": 2.0378546054180568e-05, + "loss": 1.7345, + "step": 12683 + }, + { + "epoch": 0.7069840031213421, + "grad_norm": 0.5880386829376221, + "learning_rate": 2.0371373069853424e-05, + "loss": 1.9439, + "step": 12684 + }, + { + "epoch": 0.7070397413745053, + "grad_norm": 0.5849983096122742, + "learning_rate": 2.036420102517358e-05, + "loss": 1.5638, + "step": 12685 + }, + { + "epoch": 0.7070954796276685, + "grad_norm": 0.545464277267456, + "learning_rate": 2.035702992036849e-05, + "loss": 1.5163, + "step": 12686 + }, + { + "epoch": 0.7071512178808316, + "grad_norm": 0.5759094953536987, + "learning_rate": 2.0349859755665595e-05, + "loss": 1.6277, + "step": 12687 + }, + { + "epoch": 0.7072069561339948, + "grad_norm": 0.5686140060424805, + "learning_rate": 2.0342690531292248e-05, + "loss": 1.4882, + "step": 12688 + }, + { + "epoch": 0.7072626943871579, + "grad_norm": 0.549177348613739, + "learning_rate": 2.0335522247475874e-05, + "loss": 1.611, + "step": 12689 + }, + { + "epoch": 0.707318432640321, + "grad_norm": 0.6295575499534607, + "learning_rate": 2.0328354904443764e-05, + "loss": 1.8073, + "step": 12690 + }, + { + "epoch": 0.7073741708934842, + "grad_norm": 0.5919781923294067, + "learning_rate": 2.0321188502423232e-05, + "loss": 1.6561, + "step": 12691 + }, + { + "epoch": 0.7074299091466474, + "grad_norm": 0.5448305606842041, + "learning_rate": 2.0314023041641568e-05, + "loss": 1.7064, + "step": 12692 + }, + { + "epoch": 0.7074856473998105, + "grad_norm": 0.5615071058273315, + "learning_rate": 2.030685852232601e-05, + "loss": 1.511, + "step": 12693 + }, + { + "epoch": 0.7075413856529736, + "grad_norm": 0.5193641781806946, + "learning_rate": 2.0299694944703796e-05, + "loss": 1.4849, + "step": 12694 + }, + { + "epoch": 0.7075971239061368, + "grad_norm": 0.5853648781776428, + "learning_rate": 2.0292532309002054e-05, + "loss": 1.5751, + "step": 12695 + }, + { + "epoch": 0.7076528621592999, + "grad_norm": 0.559391975402832, + "learning_rate": 2.0285370615448002e-05, + "loss": 1.5558, + "step": 12696 + }, + { + "epoch": 0.7077086004124631, + "grad_norm": 0.6228542923927307, + "learning_rate": 2.027820986426876e-05, + "loss": 1.3527, + "step": 12697 + }, + { + "epoch": 0.7077643386656263, + "grad_norm": 0.5739468932151794, + "learning_rate": 2.0271050055691393e-05, + "loss": 1.4686, + "step": 12698 + }, + { + "epoch": 0.7078200769187893, + "grad_norm": 0.5727941393852234, + "learning_rate": 2.026389118994299e-05, + "loss": 1.6368, + "step": 12699 + }, + { + "epoch": 0.7078758151719525, + "grad_norm": 0.5730375051498413, + "learning_rate": 2.0256733267250583e-05, + "loss": 1.6877, + "step": 12700 + }, + { + "epoch": 0.7079315534251157, + "grad_norm": 0.5445471405982971, + "learning_rate": 2.02495762878412e-05, + "loss": 1.5749, + "step": 12701 + }, + { + "epoch": 0.7079872916782788, + "grad_norm": 0.5488109588623047, + "learning_rate": 2.024242025194178e-05, + "loss": 1.5247, + "step": 12702 + }, + { + "epoch": 0.708043029931442, + "grad_norm": 0.5618939399719238, + "learning_rate": 2.0235265159779277e-05, + "loss": 1.7531, + "step": 12703 + }, + { + "epoch": 0.708098768184605, + "grad_norm": 0.5433917045593262, + "learning_rate": 2.022811101158066e-05, + "loss": 1.7212, + "step": 12704 + }, + { + "epoch": 0.7081545064377682, + "grad_norm": 0.5437905788421631, + "learning_rate": 2.0220957807572756e-05, + "loss": 1.6991, + "step": 12705 + }, + { + "epoch": 0.7082102446909314, + "grad_norm": 0.5957657098770142, + "learning_rate": 2.0213805547982446e-05, + "loss": 1.6026, + "step": 12706 + }, + { + "epoch": 0.7082659829440945, + "grad_norm": 0.5926949381828308, + "learning_rate": 2.020665423303656e-05, + "loss": 1.8268, + "step": 12707 + }, + { + "epoch": 0.7083217211972577, + "grad_norm": 0.5730268359184265, + "learning_rate": 2.0199503862961917e-05, + "loss": 1.6651, + "step": 12708 + }, + { + "epoch": 0.7083774594504209, + "grad_norm": 0.5360450744628906, + "learning_rate": 2.019235443798524e-05, + "loss": 1.6086, + "step": 12709 + }, + { + "epoch": 0.7084331977035839, + "grad_norm": 0.5588325262069702, + "learning_rate": 2.0185205958333275e-05, + "loss": 1.6118, + "step": 12710 + }, + { + "epoch": 0.7084889359567471, + "grad_norm": 0.5698480606079102, + "learning_rate": 2.0178058424232776e-05, + "loss": 1.6655, + "step": 12711 + }, + { + "epoch": 0.7085446742099103, + "grad_norm": 0.5079599618911743, + "learning_rate": 2.017091183591037e-05, + "loss": 1.4887, + "step": 12712 + }, + { + "epoch": 0.7086004124630734, + "grad_norm": 0.5740954875946045, + "learning_rate": 2.0163766193592753e-05, + "loss": 1.7438, + "step": 12713 + }, + { + "epoch": 0.7086561507162366, + "grad_norm": 0.5531185865402222, + "learning_rate": 2.0156621497506472e-05, + "loss": 1.4655, + "step": 12714 + }, + { + "epoch": 0.7087118889693997, + "grad_norm": 0.5318362712860107, + "learning_rate": 2.0149477747878194e-05, + "loss": 1.6594, + "step": 12715 + }, + { + "epoch": 0.7087676272225628, + "grad_norm": 0.5267673134803772, + "learning_rate": 2.0142334944934426e-05, + "loss": 1.583, + "step": 12716 + }, + { + "epoch": 0.708823365475726, + "grad_norm": 0.5608228445053101, + "learning_rate": 2.013519308890171e-05, + "loss": 1.5247, + "step": 12717 + }, + { + "epoch": 0.7088791037288892, + "grad_norm": 0.5941587090492249, + "learning_rate": 2.0128052180006546e-05, + "loss": 1.6722, + "step": 12718 + }, + { + "epoch": 0.7089348419820523, + "grad_norm": 0.5631396174430847, + "learning_rate": 2.0120912218475396e-05, + "loss": 1.6948, + "step": 12719 + }, + { + "epoch": 0.7089905802352154, + "grad_norm": 0.578289270401001, + "learning_rate": 2.011377320453473e-05, + "loss": 1.6412, + "step": 12720 + }, + { + "epoch": 0.7090463184883786, + "grad_norm": 0.5368520021438599, + "learning_rate": 2.0106635138410883e-05, + "loss": 1.6345, + "step": 12721 + }, + { + "epoch": 0.7091020567415417, + "grad_norm": 0.5559724569320679, + "learning_rate": 2.0099498020330303e-05, + "loss": 1.6459, + "step": 12722 + }, + { + "epoch": 0.7091577949947049, + "grad_norm": 0.5772035717964172, + "learning_rate": 2.0092361850519336e-05, + "loss": 1.5565, + "step": 12723 + }, + { + "epoch": 0.7092135332478681, + "grad_norm": 0.653834879398346, + "learning_rate": 2.0085226629204256e-05, + "loss": 1.6026, + "step": 12724 + }, + { + "epoch": 0.7092692715010311, + "grad_norm": 0.6090754270553589, + "learning_rate": 2.0078092356611372e-05, + "loss": 1.6818, + "step": 12725 + }, + { + "epoch": 0.7093250097541943, + "grad_norm": 0.5616610646247864, + "learning_rate": 2.0070959032966942e-05, + "loss": 1.6622, + "step": 12726 + }, + { + "epoch": 0.7093807480073574, + "grad_norm": 0.6165484189987183, + "learning_rate": 2.0063826658497203e-05, + "loss": 1.8945, + "step": 12727 + }, + { + "epoch": 0.7094364862605206, + "grad_norm": 0.5442148447036743, + "learning_rate": 2.0056695233428335e-05, + "loss": 1.4223, + "step": 12728 + }, + { + "epoch": 0.7094922245136838, + "grad_norm": 0.5319198966026306, + "learning_rate": 2.0049564757986488e-05, + "loss": 1.5615, + "step": 12729 + }, + { + "epoch": 0.7095479627668468, + "grad_norm": 0.6317080855369568, + "learning_rate": 2.0042435232397867e-05, + "loss": 1.9871, + "step": 12730 + }, + { + "epoch": 0.70960370102001, + "grad_norm": 0.5435596704483032, + "learning_rate": 2.0035306656888515e-05, + "loss": 1.4064, + "step": 12731 + }, + { + "epoch": 0.7096594392731732, + "grad_norm": 0.5366087555885315, + "learning_rate": 2.0028179031684523e-05, + "loss": 1.6376, + "step": 12732 + }, + { + "epoch": 0.7097151775263363, + "grad_norm": 0.593706488609314, + "learning_rate": 2.002105235701195e-05, + "loss": 1.7685, + "step": 12733 + }, + { + "epoch": 0.7097709157794995, + "grad_norm": 0.61496901512146, + "learning_rate": 2.0013926633096825e-05, + "loss": 1.6685, + "step": 12734 + }, + { + "epoch": 0.7098266540326627, + "grad_norm": 0.49844062328338623, + "learning_rate": 2.0006801860165098e-05, + "loss": 1.5448, + "step": 12735 + }, + { + "epoch": 0.7098823922858257, + "grad_norm": 0.610573947429657, + "learning_rate": 1.9999678038442727e-05, + "loss": 1.8328, + "step": 12736 + }, + { + "epoch": 0.7099381305389889, + "grad_norm": 0.5731762051582336, + "learning_rate": 1.9992555168155687e-05, + "loss": 1.3826, + "step": 12737 + }, + { + "epoch": 0.7099938687921521, + "grad_norm": 0.5378715991973877, + "learning_rate": 1.998543324952982e-05, + "loss": 1.4891, + "step": 12738 + }, + { + "epoch": 0.7100496070453152, + "grad_norm": 0.5719186067581177, + "learning_rate": 1.997831228279104e-05, + "loss": 1.6531, + "step": 12739 + }, + { + "epoch": 0.7101053452984784, + "grad_norm": 0.5602190494537354, + "learning_rate": 1.9971192268165116e-05, + "loss": 1.7154, + "step": 12740 + }, + { + "epoch": 0.7101610835516415, + "grad_norm": 0.5402939915657043, + "learning_rate": 1.9964073205877924e-05, + "loss": 1.5835, + "step": 12741 + }, + { + "epoch": 0.7102168218048046, + "grad_norm": 0.6443590521812439, + "learning_rate": 1.99569550961552e-05, + "loss": 1.8135, + "step": 12742 + }, + { + "epoch": 0.7102725600579678, + "grad_norm": 0.563509464263916, + "learning_rate": 1.9949837939222693e-05, + "loss": 1.6409, + "step": 12743 + }, + { + "epoch": 0.710328298311131, + "grad_norm": 0.4864160716533661, + "learning_rate": 1.994272173530612e-05, + "loss": 1.0639, + "step": 12744 + }, + { + "epoch": 0.710384036564294, + "grad_norm": 0.5689197182655334, + "learning_rate": 1.993560648463117e-05, + "loss": 1.7668, + "step": 12745 + }, + { + "epoch": 0.7104397748174572, + "grad_norm": 0.6037869453430176, + "learning_rate": 1.9928492187423514e-05, + "loss": 1.4886, + "step": 12746 + }, + { + "epoch": 0.7104955130706204, + "grad_norm": 0.6127498149871826, + "learning_rate": 1.9921378843908716e-05, + "loss": 1.9898, + "step": 12747 + }, + { + "epoch": 0.7105512513237835, + "grad_norm": 0.5575817227363586, + "learning_rate": 1.991426645431243e-05, + "loss": 1.6636, + "step": 12748 + }, + { + "epoch": 0.7106069895769467, + "grad_norm": 0.5344414114952087, + "learning_rate": 1.9907155018860217e-05, + "loss": 1.6165, + "step": 12749 + }, + { + "epoch": 0.7106627278301098, + "grad_norm": 0.5407127737998962, + "learning_rate": 1.9900044537777586e-05, + "loss": 1.6894, + "step": 12750 + }, + { + "epoch": 0.7107184660832729, + "grad_norm": 0.531772792339325, + "learning_rate": 1.9892935011290037e-05, + "loss": 1.4837, + "step": 12751 + }, + { + "epoch": 0.7107742043364361, + "grad_norm": 0.5555554628372192, + "learning_rate": 1.9885826439623052e-05, + "loss": 1.6393, + "step": 12752 + }, + { + "epoch": 0.7108299425895992, + "grad_norm": 0.5575926899909973, + "learning_rate": 1.9878718823002097e-05, + "loss": 1.6043, + "step": 12753 + }, + { + "epoch": 0.7108856808427624, + "grad_norm": 0.5810105204582214, + "learning_rate": 1.9871612161652542e-05, + "loss": 1.6273, + "step": 12754 + }, + { + "epoch": 0.7109414190959256, + "grad_norm": 0.5523950457572937, + "learning_rate": 1.9864506455799768e-05, + "loss": 1.6094, + "step": 12755 + }, + { + "epoch": 0.7109971573490886, + "grad_norm": 0.572114109992981, + "learning_rate": 1.9857401705669186e-05, + "loss": 1.7298, + "step": 12756 + }, + { + "epoch": 0.7110528956022518, + "grad_norm": 0.5734782814979553, + "learning_rate": 1.9850297911486067e-05, + "loss": 1.649, + "step": 12757 + }, + { + "epoch": 0.711108633855415, + "grad_norm": 0.5278222560882568, + "learning_rate": 1.98431950734757e-05, + "loss": 1.4049, + "step": 12758 + }, + { + "epoch": 0.7111643721085781, + "grad_norm": 0.5516873002052307, + "learning_rate": 1.983609319186337e-05, + "loss": 1.5951, + "step": 12759 + }, + { + "epoch": 0.7112201103617413, + "grad_norm": 0.5528345108032227, + "learning_rate": 1.982899226687431e-05, + "loss": 1.7238, + "step": 12760 + }, + { + "epoch": 0.7112758486149044, + "grad_norm": 0.589545726776123, + "learning_rate": 1.9821892298733686e-05, + "loss": 1.7273, + "step": 12761 + }, + { + "epoch": 0.7113315868680675, + "grad_norm": 0.5374835729598999, + "learning_rate": 1.9814793287666673e-05, + "loss": 1.7202, + "step": 12762 + }, + { + "epoch": 0.7113873251212307, + "grad_norm": 0.5903745889663696, + "learning_rate": 1.9807695233898455e-05, + "loss": 1.6107, + "step": 12763 + }, + { + "epoch": 0.7114430633743939, + "grad_norm": 0.578032910823822, + "learning_rate": 1.98005981376541e-05, + "loss": 1.5467, + "step": 12764 + }, + { + "epoch": 0.711498801627557, + "grad_norm": 0.5979136824607849, + "learning_rate": 1.9793501999158708e-05, + "loss": 1.7664, + "step": 12765 + }, + { + "epoch": 0.7115545398807201, + "grad_norm": 0.5675146579742432, + "learning_rate": 1.9786406818637286e-05, + "loss": 1.6013, + "step": 12766 + }, + { + "epoch": 0.7116102781338833, + "grad_norm": 0.5453364253044128, + "learning_rate": 1.977931259631492e-05, + "loss": 1.4807, + "step": 12767 + }, + { + "epoch": 0.7116660163870464, + "grad_norm": 0.622312605381012, + "learning_rate": 1.977221933241654e-05, + "loss": 1.9146, + "step": 12768 + }, + { + "epoch": 0.7117217546402096, + "grad_norm": 0.5752536058425903, + "learning_rate": 1.9765127027167117e-05, + "loss": 1.4818, + "step": 12769 + }, + { + "epoch": 0.7117774928933728, + "grad_norm": 0.5456924438476562, + "learning_rate": 1.9758035680791593e-05, + "loss": 1.6821, + "step": 12770 + }, + { + "epoch": 0.7118332311465358, + "grad_norm": 0.594129741191864, + "learning_rate": 1.975094529351485e-05, + "loss": 1.5839, + "step": 12771 + }, + { + "epoch": 0.711888969399699, + "grad_norm": 0.5474662780761719, + "learning_rate": 1.9743855865561772e-05, + "loss": 1.7335, + "step": 12772 + }, + { + "epoch": 0.7119447076528621, + "grad_norm": 0.5566896200180054, + "learning_rate": 1.9736767397157147e-05, + "loss": 1.4159, + "step": 12773 + }, + { + "epoch": 0.7120004459060253, + "grad_norm": 0.5809720754623413, + "learning_rate": 1.9729679888525847e-05, + "loss": 1.6998, + "step": 12774 + }, + { + "epoch": 0.7120561841591885, + "grad_norm": 0.5639328956604004, + "learning_rate": 1.9722593339892605e-05, + "loss": 1.6072, + "step": 12775 + }, + { + "epoch": 0.7121119224123516, + "grad_norm": 0.5665844082832336, + "learning_rate": 1.971550775148216e-05, + "loss": 1.4811, + "step": 12776 + }, + { + "epoch": 0.7121676606655147, + "grad_norm": 0.5987708568572998, + "learning_rate": 1.9708423123519242e-05, + "loss": 1.7223, + "step": 12777 + }, + { + "epoch": 0.7122233989186779, + "grad_norm": 0.5482421517372131, + "learning_rate": 1.9701339456228534e-05, + "loss": 1.7612, + "step": 12778 + }, + { + "epoch": 0.712279137171841, + "grad_norm": 0.5657587051391602, + "learning_rate": 1.96942567498347e-05, + "loss": 1.7783, + "step": 12779 + }, + { + "epoch": 0.7123348754250042, + "grad_norm": 0.5460767149925232, + "learning_rate": 1.968717500456233e-05, + "loss": 1.5199, + "step": 12780 + }, + { + "epoch": 0.7123906136781674, + "grad_norm": 0.5805169343948364, + "learning_rate": 1.9680094220636018e-05, + "loss": 1.6642, + "step": 12781 + }, + { + "epoch": 0.7124463519313304, + "grad_norm": 0.5397613048553467, + "learning_rate": 1.967301439828037e-05, + "loss": 1.5273, + "step": 12782 + }, + { + "epoch": 0.7125020901844936, + "grad_norm": 0.5457704067230225, + "learning_rate": 1.966593553771987e-05, + "loss": 1.484, + "step": 12783 + }, + { + "epoch": 0.7125578284376568, + "grad_norm": 0.5834569334983826, + "learning_rate": 1.965885763917904e-05, + "loss": 1.798, + "step": 12784 + }, + { + "epoch": 0.7126135666908199, + "grad_norm": 0.5535709857940674, + "learning_rate": 1.9651780702882338e-05, + "loss": 1.4035, + "step": 12785 + }, + { + "epoch": 0.7126693049439831, + "grad_norm": 0.535655677318573, + "learning_rate": 1.964470472905423e-05, + "loss": 1.5595, + "step": 12786 + }, + { + "epoch": 0.7127250431971462, + "grad_norm": 0.5838567614555359, + "learning_rate": 1.9637629717919094e-05, + "loss": 1.6134, + "step": 12787 + }, + { + "epoch": 0.7127807814503093, + "grad_norm": 0.6011456847190857, + "learning_rate": 1.963055566970129e-05, + "loss": 1.9148, + "step": 12788 + }, + { + "epoch": 0.7128365197034725, + "grad_norm": 0.5572181344032288, + "learning_rate": 1.9623482584625237e-05, + "loss": 1.3516, + "step": 12789 + }, + { + "epoch": 0.7128922579566357, + "grad_norm": 0.5829541087150574, + "learning_rate": 1.9616410462915186e-05, + "loss": 1.6736, + "step": 12790 + }, + { + "epoch": 0.7129479962097988, + "grad_norm": 0.5342071652412415, + "learning_rate": 1.960933930479545e-05, + "loss": 1.6827, + "step": 12791 + }, + { + "epoch": 0.713003734462962, + "grad_norm": 0.5617251396179199, + "learning_rate": 1.9602269110490273e-05, + "loss": 1.7693, + "step": 12792 + }, + { + "epoch": 0.7130594727161251, + "grad_norm": 0.6102042198181152, + "learning_rate": 1.9595199880223912e-05, + "loss": 1.7255, + "step": 12793 + }, + { + "epoch": 0.7131152109692882, + "grad_norm": 0.5527377724647522, + "learning_rate": 1.9588131614220522e-05, + "loss": 1.5599, + "step": 12794 + }, + { + "epoch": 0.7131709492224514, + "grad_norm": 0.5990374684333801, + "learning_rate": 1.958106431270429e-05, + "loss": 1.7379, + "step": 12795 + }, + { + "epoch": 0.7132266874756145, + "grad_norm": 0.5425254702568054, + "learning_rate": 1.957399797589933e-05, + "loss": 1.6852, + "step": 12796 + }, + { + "epoch": 0.7132824257287776, + "grad_norm": 0.5994154810905457, + "learning_rate": 1.956693260402977e-05, + "loss": 1.8283, + "step": 12797 + }, + { + "epoch": 0.7133381639819408, + "grad_norm": 0.5741962790489197, + "learning_rate": 1.955986819731968e-05, + "loss": 1.8184, + "step": 12798 + }, + { + "epoch": 0.7133939022351039, + "grad_norm": 0.5813300609588623, + "learning_rate": 1.9552804755993065e-05, + "loss": 1.8002, + "step": 12799 + }, + { + "epoch": 0.7134496404882671, + "grad_norm": 0.534512460231781, + "learning_rate": 1.9545742280273993e-05, + "loss": 1.4038, + "step": 12800 + }, + { + "epoch": 0.7135053787414303, + "grad_norm": 0.5778892636299133, + "learning_rate": 1.9538680770386398e-05, + "loss": 1.6931, + "step": 12801 + }, + { + "epoch": 0.7135611169945933, + "grad_norm": 0.5787971615791321, + "learning_rate": 1.9531620226554248e-05, + "loss": 1.7565, + "step": 12802 + }, + { + "epoch": 0.7136168552477565, + "grad_norm": 0.5496509671211243, + "learning_rate": 1.9524560649001462e-05, + "loss": 1.7543, + "step": 12803 + }, + { + "epoch": 0.7136725935009197, + "grad_norm": 0.6067994832992554, + "learning_rate": 1.951750203795193e-05, + "loss": 1.7114, + "step": 12804 + }, + { + "epoch": 0.7137283317540828, + "grad_norm": 0.5479700565338135, + "learning_rate": 1.9510444393629525e-05, + "loss": 1.4792, + "step": 12805 + }, + { + "epoch": 0.713784070007246, + "grad_norm": 0.5829119086265564, + "learning_rate": 1.9503387716258038e-05, + "loss": 1.6419, + "step": 12806 + }, + { + "epoch": 0.7138398082604092, + "grad_norm": 0.529517650604248, + "learning_rate": 1.9496332006061262e-05, + "loss": 1.5288, + "step": 12807 + }, + { + "epoch": 0.7138955465135722, + "grad_norm": 0.5489634871482849, + "learning_rate": 1.9489277263263028e-05, + "loss": 1.7274, + "step": 12808 + }, + { + "epoch": 0.7139512847667354, + "grad_norm": 0.6540934443473816, + "learning_rate": 1.9482223488087016e-05, + "loss": 2.0038, + "step": 12809 + }, + { + "epoch": 0.7140070230198986, + "grad_norm": 0.5693274736404419, + "learning_rate": 1.9475170680756938e-05, + "loss": 1.6409, + "step": 12810 + }, + { + "epoch": 0.7140627612730617, + "grad_norm": 0.6074066758155823, + "learning_rate": 1.9468118841496476e-05, + "loss": 1.8189, + "step": 12811 + }, + { + "epoch": 0.7141184995262249, + "grad_norm": 0.5593070983886719, + "learning_rate": 1.9461067970529286e-05, + "loss": 1.5253, + "step": 12812 + }, + { + "epoch": 0.714174237779388, + "grad_norm": 0.5670613646507263, + "learning_rate": 1.9454018068078948e-05, + "loss": 1.5391, + "step": 12813 + }, + { + "epoch": 0.7142299760325511, + "grad_norm": 0.5611968040466309, + "learning_rate": 1.944696913436905e-05, + "loss": 1.7251, + "step": 12814 + }, + { + "epoch": 0.7142857142857143, + "grad_norm": 0.5555674433708191, + "learning_rate": 1.9439921169623183e-05, + "loss": 1.6815, + "step": 12815 + }, + { + "epoch": 0.7143414525388775, + "grad_norm": 0.5796941518783569, + "learning_rate": 1.943287417406482e-05, + "loss": 1.5858, + "step": 12816 + }, + { + "epoch": 0.7143971907920406, + "grad_norm": 0.5309176445007324, + "learning_rate": 1.9425828147917475e-05, + "loss": 1.6417, + "step": 12817 + }, + { + "epoch": 0.7144529290452037, + "grad_norm": 0.6035979986190796, + "learning_rate": 1.9418783091404597e-05, + "loss": 1.7085, + "step": 12818 + }, + { + "epoch": 0.7145086672983668, + "grad_norm": 0.5622169375419617, + "learning_rate": 1.941173900474964e-05, + "loss": 1.7192, + "step": 12819 + }, + { + "epoch": 0.71456440555153, + "grad_norm": 0.6361518502235413, + "learning_rate": 1.940469588817596e-05, + "loss": 1.7091, + "step": 12820 + }, + { + "epoch": 0.7146201438046932, + "grad_norm": 0.6154270172119141, + "learning_rate": 1.9397653741906947e-05, + "loss": 1.7204, + "step": 12821 + }, + { + "epoch": 0.7146758820578563, + "grad_norm": 0.6581857800483704, + "learning_rate": 1.939061256616593e-05, + "loss": 1.8386, + "step": 12822 + }, + { + "epoch": 0.7147316203110194, + "grad_norm": 0.5279804468154907, + "learning_rate": 1.9383572361176216e-05, + "loss": 1.4818, + "step": 12823 + }, + { + "epoch": 0.7147873585641826, + "grad_norm": 0.5774812698364258, + "learning_rate": 1.93765331271611e-05, + "loss": 1.6351, + "step": 12824 + }, + { + "epoch": 0.7148430968173457, + "grad_norm": 0.5667797327041626, + "learning_rate": 1.9369494864343768e-05, + "loss": 1.7558, + "step": 12825 + }, + { + "epoch": 0.7148988350705089, + "grad_norm": 0.5321443676948547, + "learning_rate": 1.9362457572947508e-05, + "loss": 1.4818, + "step": 12826 + }, + { + "epoch": 0.7149545733236721, + "grad_norm": 0.5456085801124573, + "learning_rate": 1.935542125319545e-05, + "loss": 1.5985, + "step": 12827 + }, + { + "epoch": 0.7150103115768351, + "grad_norm": 0.5820759534835815, + "learning_rate": 1.9348385905310757e-05, + "loss": 1.6352, + "step": 12828 + }, + { + "epoch": 0.7150660498299983, + "grad_norm": 0.610159695148468, + "learning_rate": 1.934135152951655e-05, + "loss": 1.6083, + "step": 12829 + }, + { + "epoch": 0.7151217880831615, + "grad_norm": 0.6192707419395447, + "learning_rate": 1.9334318126035922e-05, + "loss": 1.6754, + "step": 12830 + }, + { + "epoch": 0.7151775263363246, + "grad_norm": 0.5779080986976624, + "learning_rate": 1.9327285695091946e-05, + "loss": 1.695, + "step": 12831 + }, + { + "epoch": 0.7152332645894878, + "grad_norm": 0.652459979057312, + "learning_rate": 1.932025423690762e-05, + "loss": 1.9642, + "step": 12832 + }, + { + "epoch": 0.715289002842651, + "grad_norm": 0.5195798277854919, + "learning_rate": 1.9313223751705935e-05, + "loss": 1.3916, + "step": 12833 + }, + { + "epoch": 0.715344741095814, + "grad_norm": 0.5294322967529297, + "learning_rate": 1.9306194239709906e-05, + "loss": 1.4148, + "step": 12834 + }, + { + "epoch": 0.7154004793489772, + "grad_norm": 0.5848262906074524, + "learning_rate": 1.9299165701142426e-05, + "loss": 1.3771, + "step": 12835 + }, + { + "epoch": 0.7154562176021404, + "grad_norm": 0.5794307589530945, + "learning_rate": 1.9292138136226413e-05, + "loss": 1.6937, + "step": 12836 + }, + { + "epoch": 0.7155119558553035, + "grad_norm": 0.5708346366882324, + "learning_rate": 1.928511154518473e-05, + "loss": 1.6335, + "step": 12837 + }, + { + "epoch": 0.7155676941084667, + "grad_norm": 0.6344782710075378, + "learning_rate": 1.927808592824026e-05, + "loss": 1.7754, + "step": 12838 + }, + { + "epoch": 0.7156234323616298, + "grad_norm": 0.5648434162139893, + "learning_rate": 1.9271061285615755e-05, + "loss": 1.607, + "step": 12839 + }, + { + "epoch": 0.7156791706147929, + "grad_norm": 0.5946949124336243, + "learning_rate": 1.926403761753401e-05, + "loss": 1.6942, + "step": 12840 + }, + { + "epoch": 0.7157349088679561, + "grad_norm": 0.6035356521606445, + "learning_rate": 1.925701492421782e-05, + "loss": 1.7635, + "step": 12841 + }, + { + "epoch": 0.7157906471211192, + "grad_norm": 0.5887398719787598, + "learning_rate": 1.924999320588986e-05, + "loss": 1.5762, + "step": 12842 + }, + { + "epoch": 0.7158463853742824, + "grad_norm": 0.6360691785812378, + "learning_rate": 1.924297246277283e-05, + "loss": 1.8578, + "step": 12843 + }, + { + "epoch": 0.7159021236274455, + "grad_norm": 0.5708274841308594, + "learning_rate": 1.9235952695089388e-05, + "loss": 1.5414, + "step": 12844 + }, + { + "epoch": 0.7159578618806086, + "grad_norm": 0.6127935647964478, + "learning_rate": 1.9228933903062173e-05, + "loss": 1.4997, + "step": 12845 + }, + { + "epoch": 0.7160136001337718, + "grad_norm": 0.5536811947822571, + "learning_rate": 1.9221916086913756e-05, + "loss": 1.6019, + "step": 12846 + }, + { + "epoch": 0.716069338386935, + "grad_norm": 0.55485600233078, + "learning_rate": 1.9214899246866707e-05, + "loss": 1.4985, + "step": 12847 + }, + { + "epoch": 0.7161250766400981, + "grad_norm": 0.6536714434623718, + "learning_rate": 1.9207883383143566e-05, + "loss": 1.9859, + "step": 12848 + }, + { + "epoch": 0.7161808148932612, + "grad_norm": 0.6306371688842773, + "learning_rate": 1.9200868495966827e-05, + "loss": 1.8885, + "step": 12849 + }, + { + "epoch": 0.7162365531464244, + "grad_norm": 0.6592320799827576, + "learning_rate": 1.9193854585558996e-05, + "loss": 1.8515, + "step": 12850 + }, + { + "epoch": 0.7162922913995875, + "grad_norm": 0.5459424257278442, + "learning_rate": 1.9186841652142446e-05, + "loss": 1.6183, + "step": 12851 + }, + { + "epoch": 0.7163480296527507, + "grad_norm": 0.5748673677444458, + "learning_rate": 1.917982969593966e-05, + "loss": 1.5724, + "step": 12852 + }, + { + "epoch": 0.7164037679059139, + "grad_norm": 0.5920608043670654, + "learning_rate": 1.9172818717172964e-05, + "loss": 1.7062, + "step": 12853 + }, + { + "epoch": 0.7164595061590769, + "grad_norm": 0.5399507880210876, + "learning_rate": 1.9165808716064727e-05, + "loss": 1.6388, + "step": 12854 + }, + { + "epoch": 0.7165152444122401, + "grad_norm": 0.5645083785057068, + "learning_rate": 1.9158799692837258e-05, + "loss": 1.5902, + "step": 12855 + }, + { + "epoch": 0.7165709826654033, + "grad_norm": 0.5651130676269531, + "learning_rate": 1.9151791647712848e-05, + "loss": 1.5341, + "step": 12856 + }, + { + "epoch": 0.7166267209185664, + "grad_norm": 0.5224648118019104, + "learning_rate": 1.9144784580913765e-05, + "loss": 1.5641, + "step": 12857 + }, + { + "epoch": 0.7166824591717296, + "grad_norm": 0.5261692404747009, + "learning_rate": 1.91377784926622e-05, + "loss": 1.4185, + "step": 12858 + }, + { + "epoch": 0.7167381974248928, + "grad_norm": 0.6022654175758362, + "learning_rate": 1.9130773383180344e-05, + "loss": 1.6281, + "step": 12859 + }, + { + "epoch": 0.7167939356780558, + "grad_norm": 0.5448938012123108, + "learning_rate": 1.912376925269041e-05, + "loss": 1.4896, + "step": 12860 + }, + { + "epoch": 0.716849673931219, + "grad_norm": 0.5428690910339355, + "learning_rate": 1.911676610141448e-05, + "loss": 1.6033, + "step": 12861 + }, + { + "epoch": 0.7169054121843822, + "grad_norm": 0.6159693598747253, + "learning_rate": 1.9109763929574665e-05, + "loss": 1.5138, + "step": 12862 + }, + { + "epoch": 0.7169611504375453, + "grad_norm": 0.5566955208778381, + "learning_rate": 1.910276273739304e-05, + "loss": 1.728, + "step": 12863 + }, + { + "epoch": 0.7170168886907085, + "grad_norm": 0.6169360876083374, + "learning_rate": 1.909576252509165e-05, + "loss": 1.8363, + "step": 12864 + }, + { + "epoch": 0.7170726269438715, + "grad_norm": 0.5535723567008972, + "learning_rate": 1.9088763292892468e-05, + "loss": 1.6138, + "step": 12865 + }, + { + "epoch": 0.7171283651970347, + "grad_norm": 0.6125819683074951, + "learning_rate": 1.908176504101748e-05, + "loss": 1.6805, + "step": 12866 + }, + { + "epoch": 0.7171841034501979, + "grad_norm": 0.5870202779769897, + "learning_rate": 1.9074767769688674e-05, + "loss": 1.5874, + "step": 12867 + }, + { + "epoch": 0.717239841703361, + "grad_norm": 0.5767966508865356, + "learning_rate": 1.9067771479127905e-05, + "loss": 1.7405, + "step": 12868 + }, + { + "epoch": 0.7172955799565242, + "grad_norm": 0.5747946500778198, + "learning_rate": 1.9060776169557083e-05, + "loss": 1.9751, + "step": 12869 + }, + { + "epoch": 0.7173513182096873, + "grad_norm": 0.5575464963912964, + "learning_rate": 1.9053781841198044e-05, + "loss": 1.701, + "step": 12870 + }, + { + "epoch": 0.7174070564628504, + "grad_norm": 0.5241334438323975, + "learning_rate": 1.9046788494272638e-05, + "loss": 1.5356, + "step": 12871 + }, + { + "epoch": 0.7174627947160136, + "grad_norm": 0.5647209882736206, + "learning_rate": 1.903979612900262e-05, + "loss": 1.6373, + "step": 12872 + }, + { + "epoch": 0.7175185329691768, + "grad_norm": 0.5827178359031677, + "learning_rate": 1.903280474560975e-05, + "loss": 1.919, + "step": 12873 + }, + { + "epoch": 0.7175742712223399, + "grad_norm": 0.5812021493911743, + "learning_rate": 1.902581434431576e-05, + "loss": 1.6801, + "step": 12874 + }, + { + "epoch": 0.717630009475503, + "grad_norm": 0.5697082281112671, + "learning_rate": 1.9018824925342353e-05, + "loss": 1.7047, + "step": 12875 + }, + { + "epoch": 0.7176857477286662, + "grad_norm": 0.5812304019927979, + "learning_rate": 1.9011836488911207e-05, + "loss": 1.5699, + "step": 12876 + }, + { + "epoch": 0.7177414859818293, + "grad_norm": 0.5891488790512085, + "learning_rate": 1.9004849035243894e-05, + "loss": 1.8281, + "step": 12877 + }, + { + "epoch": 0.7177972242349925, + "grad_norm": 0.6002638339996338, + "learning_rate": 1.8997862564562092e-05, + "loss": 1.6098, + "step": 12878 + }, + { + "epoch": 0.7178529624881557, + "grad_norm": 0.5769315958023071, + "learning_rate": 1.8990877077087315e-05, + "loss": 1.6627, + "step": 12879 + }, + { + "epoch": 0.7179087007413187, + "grad_norm": 0.5559478998184204, + "learning_rate": 1.8983892573041124e-05, + "loss": 1.5231, + "step": 12880 + }, + { + "epoch": 0.7179644389944819, + "grad_norm": 0.599773645401001, + "learning_rate": 1.897690905264502e-05, + "loss": 1.5775, + "step": 12881 + }, + { + "epoch": 0.7180201772476451, + "grad_norm": 0.5190117955207825, + "learning_rate": 1.8969926516120486e-05, + "loss": 1.5025, + "step": 12882 + }, + { + "epoch": 0.7180759155008082, + "grad_norm": 0.5551081895828247, + "learning_rate": 1.8962944963688982e-05, + "loss": 1.6357, + "step": 12883 + }, + { + "epoch": 0.7181316537539714, + "grad_norm": 0.5973671078681946, + "learning_rate": 1.8955964395571875e-05, + "loss": 1.617, + "step": 12884 + }, + { + "epoch": 0.7181873920071346, + "grad_norm": 0.6069487929344177, + "learning_rate": 1.894898481199059e-05, + "loss": 1.7125, + "step": 12885 + }, + { + "epoch": 0.7182431302602976, + "grad_norm": 0.5540785193443298, + "learning_rate": 1.8942006213166486e-05, + "loss": 1.5926, + "step": 12886 + }, + { + "epoch": 0.7182988685134608, + "grad_norm": 0.552204966545105, + "learning_rate": 1.8935028599320846e-05, + "loss": 1.5145, + "step": 12887 + }, + { + "epoch": 0.7183546067666239, + "grad_norm": 0.6157098412513733, + "learning_rate": 1.8928051970674975e-05, + "loss": 1.7493, + "step": 12888 + }, + { + "epoch": 0.7184103450197871, + "grad_norm": 0.5683028697967529, + "learning_rate": 1.892107632745014e-05, + "loss": 1.5814, + "step": 12889 + }, + { + "epoch": 0.7184660832729503, + "grad_norm": 0.5874137282371521, + "learning_rate": 1.8914101669867572e-05, + "loss": 1.5899, + "step": 12890 + }, + { + "epoch": 0.7185218215261133, + "grad_norm": 0.5777448415756226, + "learning_rate": 1.8907127998148444e-05, + "loss": 1.6587, + "step": 12891 + }, + { + "epoch": 0.7185775597792765, + "grad_norm": 0.5604439973831177, + "learning_rate": 1.8900155312513913e-05, + "loss": 1.4609, + "step": 12892 + }, + { + "epoch": 0.7186332980324397, + "grad_norm": 0.5519274473190308, + "learning_rate": 1.8893183613185163e-05, + "loss": 1.715, + "step": 12893 + }, + { + "epoch": 0.7186890362856028, + "grad_norm": 0.5561261177062988, + "learning_rate": 1.8886212900383248e-05, + "loss": 1.5037, + "step": 12894 + }, + { + "epoch": 0.718744774538766, + "grad_norm": 0.5496982932090759, + "learning_rate": 1.887924317432925e-05, + "loss": 1.3882, + "step": 12895 + }, + { + "epoch": 0.7188005127919291, + "grad_norm": 0.5935930013656616, + "learning_rate": 1.887227443524422e-05, + "loss": 1.6411, + "step": 12896 + }, + { + "epoch": 0.7188562510450922, + "grad_norm": 0.6104579567909241, + "learning_rate": 1.886530668334917e-05, + "loss": 1.7263, + "step": 12897 + }, + { + "epoch": 0.7189119892982554, + "grad_norm": 0.544337272644043, + "learning_rate": 1.8858339918865046e-05, + "loss": 1.5848, + "step": 12898 + }, + { + "epoch": 0.7189677275514186, + "grad_norm": 0.6195954084396362, + "learning_rate": 1.885137414201281e-05, + "loss": 1.8026, + "step": 12899 + }, + { + "epoch": 0.7190234658045817, + "grad_norm": 0.5602339506149292, + "learning_rate": 1.884440935301338e-05, + "loss": 1.6852, + "step": 12900 + }, + { + "epoch": 0.7190792040577448, + "grad_norm": 0.5330663919448853, + "learning_rate": 1.883744555208764e-05, + "loss": 1.5815, + "step": 12901 + }, + { + "epoch": 0.719134942310908, + "grad_norm": 0.5787651538848877, + "learning_rate": 1.8830482739456452e-05, + "loss": 1.6217, + "step": 12902 + }, + { + "epoch": 0.7191906805640711, + "grad_norm": 0.5768993496894836, + "learning_rate": 1.8823520915340583e-05, + "loss": 1.7787, + "step": 12903 + }, + { + "epoch": 0.7192464188172343, + "grad_norm": 0.5117707848548889, + "learning_rate": 1.8816560079960892e-05, + "loss": 1.2857, + "step": 12904 + }, + { + "epoch": 0.7193021570703975, + "grad_norm": 0.5444961786270142, + "learning_rate": 1.8809600233538087e-05, + "loss": 1.6263, + "step": 12905 + }, + { + "epoch": 0.7193578953235605, + "grad_norm": 0.5877333283424377, + "learning_rate": 1.8802641376292914e-05, + "loss": 1.3656, + "step": 12906 + }, + { + "epoch": 0.7194136335767237, + "grad_norm": 0.7059000134468079, + "learning_rate": 1.8795683508446055e-05, + "loss": 1.7087, + "step": 12907 + }, + { + "epoch": 0.7194693718298869, + "grad_norm": 0.6280462145805359, + "learning_rate": 1.878872663021819e-05, + "loss": 1.7132, + "step": 12908 + }, + { + "epoch": 0.71952511008305, + "grad_norm": 0.5358414649963379, + "learning_rate": 1.8781770741829956e-05, + "loss": 1.6527, + "step": 12909 + }, + { + "epoch": 0.7195808483362132, + "grad_norm": 0.5640277862548828, + "learning_rate": 1.8774815843501904e-05, + "loss": 1.7389, + "step": 12910 + }, + { + "epoch": 0.7196365865893762, + "grad_norm": 0.5553831458091736, + "learning_rate": 1.8767861935454673e-05, + "loss": 1.5739, + "step": 12911 + }, + { + "epoch": 0.7196923248425394, + "grad_norm": 0.5298663973808289, + "learning_rate": 1.8760909017908746e-05, + "loss": 1.3315, + "step": 12912 + }, + { + "epoch": 0.7197480630957026, + "grad_norm": 0.5556603670120239, + "learning_rate": 1.875395709108465e-05, + "loss": 1.634, + "step": 12913 + }, + { + "epoch": 0.7198038013488657, + "grad_norm": 0.5391923189163208, + "learning_rate": 1.874700615520286e-05, + "loss": 1.6764, + "step": 12914 + }, + { + "epoch": 0.7198595396020289, + "grad_norm": 0.5856571197509766, + "learning_rate": 1.8740056210483815e-05, + "loss": 1.7273, + "step": 12915 + }, + { + "epoch": 0.719915277855192, + "grad_norm": 0.5557060837745667, + "learning_rate": 1.873310725714795e-05, + "loss": 1.6144, + "step": 12916 + }, + { + "epoch": 0.7199710161083551, + "grad_norm": 0.5560556650161743, + "learning_rate": 1.8726159295415603e-05, + "loss": 1.6216, + "step": 12917 + }, + { + "epoch": 0.7200267543615183, + "grad_norm": 0.6109077334403992, + "learning_rate": 1.8719212325507123e-05, + "loss": 1.44, + "step": 12918 + }, + { + "epoch": 0.7200824926146815, + "grad_norm": 0.5736623406410217, + "learning_rate": 1.871226634764289e-05, + "loss": 1.7272, + "step": 12919 + }, + { + "epoch": 0.7201382308678446, + "grad_norm": 0.535057783126831, + "learning_rate": 1.870532136204313e-05, + "loss": 1.4406, + "step": 12920 + }, + { + "epoch": 0.7201939691210077, + "grad_norm": 0.570833683013916, + "learning_rate": 1.8698377368928115e-05, + "loss": 1.6393, + "step": 12921 + }, + { + "epoch": 0.7202497073741709, + "grad_norm": 0.567415177822113, + "learning_rate": 1.8691434368518067e-05, + "loss": 1.7118, + "step": 12922 + }, + { + "epoch": 0.720305445627334, + "grad_norm": 0.5809144377708435, + "learning_rate": 1.8684492361033196e-05, + "loss": 1.7196, + "step": 12923 + }, + { + "epoch": 0.7203611838804972, + "grad_norm": 0.6149061322212219, + "learning_rate": 1.8677551346693633e-05, + "loss": 1.5354, + "step": 12924 + }, + { + "epoch": 0.7204169221336604, + "grad_norm": 0.5699290037155151, + "learning_rate": 1.867061132571951e-05, + "loss": 1.7636, + "step": 12925 + }, + { + "epoch": 0.7204726603868234, + "grad_norm": 0.5781373977661133, + "learning_rate": 1.8663672298330942e-05, + "loss": 1.6949, + "step": 12926 + }, + { + "epoch": 0.7205283986399866, + "grad_norm": 0.5494027733802795, + "learning_rate": 1.865673426474798e-05, + "loss": 1.684, + "step": 12927 + }, + { + "epoch": 0.7205841368931498, + "grad_norm": 0.5682995915412903, + "learning_rate": 1.864979722519068e-05, + "loss": 1.6678, + "step": 12928 + }, + { + "epoch": 0.7206398751463129, + "grad_norm": 0.5997836589813232, + "learning_rate": 1.8642861179878994e-05, + "loss": 1.7897, + "step": 12929 + }, + { + "epoch": 0.7206956133994761, + "grad_norm": 0.6006888151168823, + "learning_rate": 1.8635926129032964e-05, + "loss": 1.7266, + "step": 12930 + }, + { + "epoch": 0.7207513516526393, + "grad_norm": 0.5405071377754211, + "learning_rate": 1.8628992072872476e-05, + "loss": 1.606, + "step": 12931 + }, + { + "epoch": 0.7208070899058023, + "grad_norm": 0.5881284475326538, + "learning_rate": 1.862205901161745e-05, + "loss": 1.7615, + "step": 12932 + }, + { + "epoch": 0.7208628281589655, + "grad_norm": 0.5610661506652832, + "learning_rate": 1.8615126945487766e-05, + "loss": 1.8626, + "step": 12933 + }, + { + "epoch": 0.7209185664121286, + "grad_norm": 0.6191084980964661, + "learning_rate": 1.8608195874703266e-05, + "loss": 1.871, + "step": 12934 + }, + { + "epoch": 0.7209743046652918, + "grad_norm": 0.5465794205665588, + "learning_rate": 1.8601265799483786e-05, + "loss": 1.4462, + "step": 12935 + }, + { + "epoch": 0.721030042918455, + "grad_norm": 0.5514585375785828, + "learning_rate": 1.8594336720049055e-05, + "loss": 1.4693, + "step": 12936 + }, + { + "epoch": 0.721085781171618, + "grad_norm": 0.49483048915863037, + "learning_rate": 1.8587408636618887e-05, + "loss": 1.3201, + "step": 12937 + }, + { + "epoch": 0.7211415194247812, + "grad_norm": 0.5280016660690308, + "learning_rate": 1.8580481549412953e-05, + "loss": 1.5373, + "step": 12938 + }, + { + "epoch": 0.7211972576779444, + "grad_norm": 0.5409990549087524, + "learning_rate": 1.857355545865096e-05, + "loss": 1.5566, + "step": 12939 + }, + { + "epoch": 0.7212529959311075, + "grad_norm": 0.6028059124946594, + "learning_rate": 1.856663036455255e-05, + "loss": 1.9095, + "step": 12940 + }, + { + "epoch": 0.7213087341842707, + "grad_norm": 0.5442488789558411, + "learning_rate": 1.8559706267337362e-05, + "loss": 1.7033, + "step": 12941 + }, + { + "epoch": 0.7213644724374338, + "grad_norm": 0.5725643038749695, + "learning_rate": 1.8552783167224995e-05, + "loss": 1.7649, + "step": 12942 + }, + { + "epoch": 0.7214202106905969, + "grad_norm": 0.5693257451057434, + "learning_rate": 1.8545861064434984e-05, + "loss": 1.6757, + "step": 12943 + }, + { + "epoch": 0.7214759489437601, + "grad_norm": 0.5688108801841736, + "learning_rate": 1.853893995918685e-05, + "loss": 1.5795, + "step": 12944 + }, + { + "epoch": 0.7215316871969233, + "grad_norm": 0.500092089176178, + "learning_rate": 1.8532019851700143e-05, + "loss": 1.3856, + "step": 12945 + }, + { + "epoch": 0.7215874254500864, + "grad_norm": 0.5776916146278381, + "learning_rate": 1.852510074219428e-05, + "loss": 1.83, + "step": 12946 + }, + { + "epoch": 0.7216431637032495, + "grad_norm": 0.5361211895942688, + "learning_rate": 1.851818263088871e-05, + "loss": 1.3333, + "step": 12947 + }, + { + "epoch": 0.7216989019564127, + "grad_norm": 0.5286733508110046, + "learning_rate": 1.851126551800283e-05, + "loss": 1.2956, + "step": 12948 + }, + { + "epoch": 0.7217546402095758, + "grad_norm": 0.5599008798599243, + "learning_rate": 1.8504349403756038e-05, + "loss": 1.5162, + "step": 12949 + }, + { + "epoch": 0.721810378462739, + "grad_norm": 0.5262306928634644, + "learning_rate": 1.8497434288367633e-05, + "loss": 1.5998, + "step": 12950 + }, + { + "epoch": 0.7218661167159022, + "grad_norm": 0.5595152378082275, + "learning_rate": 1.8490520172056942e-05, + "loss": 1.6553, + "step": 12951 + }, + { + "epoch": 0.7219218549690652, + "grad_norm": 0.5566936731338501, + "learning_rate": 1.8483607055043233e-05, + "loss": 1.5902, + "step": 12952 + }, + { + "epoch": 0.7219775932222284, + "grad_norm": 0.5860758423805237, + "learning_rate": 1.847669493754576e-05, + "loss": 1.6285, + "step": 12953 + }, + { + "epoch": 0.7220333314753916, + "grad_norm": 0.5415453314781189, + "learning_rate": 1.8469783819783735e-05, + "loss": 1.625, + "step": 12954 + }, + { + "epoch": 0.7220890697285547, + "grad_norm": 0.5949093103408813, + "learning_rate": 1.8462873701976314e-05, + "loss": 1.7366, + "step": 12955 + }, + { + "epoch": 0.7221448079817179, + "grad_norm": 0.5670189261436462, + "learning_rate": 1.8455964584342693e-05, + "loss": 1.608, + "step": 12956 + }, + { + "epoch": 0.722200546234881, + "grad_norm": 0.5760493278503418, + "learning_rate": 1.8449056467101945e-05, + "loss": 1.7061, + "step": 12957 + }, + { + "epoch": 0.7222562844880441, + "grad_norm": 0.6208779215812683, + "learning_rate": 1.8442149350473172e-05, + "loss": 1.5652, + "step": 12958 + }, + { + "epoch": 0.7223120227412073, + "grad_norm": 0.5377376079559326, + "learning_rate": 1.843524323467542e-05, + "loss": 1.6385, + "step": 12959 + }, + { + "epoch": 0.7223677609943704, + "grad_norm": 0.6057771444320679, + "learning_rate": 1.8428338119927724e-05, + "loss": 1.7745, + "step": 12960 + }, + { + "epoch": 0.7224234992475336, + "grad_norm": 0.5822296142578125, + "learning_rate": 1.8421434006449084e-05, + "loss": 1.6446, + "step": 12961 + }, + { + "epoch": 0.7224792375006968, + "grad_norm": 0.5849522948265076, + "learning_rate": 1.8414530894458403e-05, + "loss": 1.6425, + "step": 12962 + }, + { + "epoch": 0.7225349757538598, + "grad_norm": 0.5624440312385559, + "learning_rate": 1.8407628784174686e-05, + "loss": 1.6815, + "step": 12963 + }, + { + "epoch": 0.722590714007023, + "grad_norm": 0.5463077425956726, + "learning_rate": 1.8400727675816765e-05, + "loss": 1.6791, + "step": 12964 + }, + { + "epoch": 0.7226464522601862, + "grad_norm": 0.6184215545654297, + "learning_rate": 1.8393827569603528e-05, + "loss": 1.8262, + "step": 12965 + }, + { + "epoch": 0.7227021905133493, + "grad_norm": 0.6199098825454712, + "learning_rate": 1.8386928465753807e-05, + "loss": 1.7666, + "step": 12966 + }, + { + "epoch": 0.7227579287665125, + "grad_norm": 0.6008428335189819, + "learning_rate": 1.838003036448639e-05, + "loss": 1.5913, + "step": 12967 + }, + { + "epoch": 0.7228136670196756, + "grad_norm": 0.5535486936569214, + "learning_rate": 1.8373133266020078e-05, + "loss": 1.6933, + "step": 12968 + }, + { + "epoch": 0.7228694052728387, + "grad_norm": 0.5395800471305847, + "learning_rate": 1.836623717057356e-05, + "loss": 1.6757, + "step": 12969 + }, + { + "epoch": 0.7229251435260019, + "grad_norm": 0.5903302431106567, + "learning_rate": 1.8359342078365544e-05, + "loss": 1.605, + "step": 12970 + }, + { + "epoch": 0.7229808817791651, + "grad_norm": 0.6031521558761597, + "learning_rate": 1.8352447989614758e-05, + "loss": 1.6577, + "step": 12971 + }, + { + "epoch": 0.7230366200323282, + "grad_norm": 0.500883162021637, + "learning_rate": 1.834555490453978e-05, + "loss": 1.5251, + "step": 12972 + }, + { + "epoch": 0.7230923582854913, + "grad_norm": 0.604284942150116, + "learning_rate": 1.8338662823359248e-05, + "loss": 1.6013, + "step": 12973 + }, + { + "epoch": 0.7231480965386545, + "grad_norm": 0.554581344127655, + "learning_rate": 1.8331771746291728e-05, + "loss": 1.5824, + "step": 12974 + }, + { + "epoch": 0.7232038347918176, + "grad_norm": 0.5634434819221497, + "learning_rate": 1.8324881673555788e-05, + "loss": 1.7972, + "step": 12975 + }, + { + "epoch": 0.7232595730449808, + "grad_norm": 0.550441563129425, + "learning_rate": 1.831799260536991e-05, + "loss": 1.6554, + "step": 12976 + }, + { + "epoch": 0.723315311298144, + "grad_norm": 0.5207143425941467, + "learning_rate": 1.8311104541952567e-05, + "loss": 1.3969, + "step": 12977 + }, + { + "epoch": 0.723371049551307, + "grad_norm": 0.558920681476593, + "learning_rate": 1.8304217483522263e-05, + "loss": 1.5403, + "step": 12978 + }, + { + "epoch": 0.7234267878044702, + "grad_norm": 0.5989134311676025, + "learning_rate": 1.8297331430297365e-05, + "loss": 1.7002, + "step": 12979 + }, + { + "epoch": 0.7234825260576333, + "grad_norm": 0.5259067416191101, + "learning_rate": 1.829044638249629e-05, + "loss": 1.4977, + "step": 12980 + }, + { + "epoch": 0.7235382643107965, + "grad_norm": 0.527930498123169, + "learning_rate": 1.8283562340337342e-05, + "loss": 1.5423, + "step": 12981 + }, + { + "epoch": 0.7235940025639597, + "grad_norm": 0.5931378602981567, + "learning_rate": 1.8276679304038912e-05, + "loss": 1.7416, + "step": 12982 + }, + { + "epoch": 0.7236497408171227, + "grad_norm": 0.5570964813232422, + "learning_rate": 1.826979727381924e-05, + "loss": 1.6216, + "step": 12983 + }, + { + "epoch": 0.7237054790702859, + "grad_norm": 0.5443962812423706, + "learning_rate": 1.8262916249896595e-05, + "loss": 1.4643, + "step": 12984 + }, + { + "epoch": 0.7237612173234491, + "grad_norm": 0.5586367249488831, + "learning_rate": 1.825603623248921e-05, + "loss": 1.7197, + "step": 12985 + }, + { + "epoch": 0.7238169555766122, + "grad_norm": 0.5415465831756592, + "learning_rate": 1.8249157221815273e-05, + "loss": 1.5418, + "step": 12986 + }, + { + "epoch": 0.7238726938297754, + "grad_norm": 0.6045337915420532, + "learning_rate": 1.8242279218092968e-05, + "loss": 1.2166, + "step": 12987 + }, + { + "epoch": 0.7239284320829386, + "grad_norm": 0.5467269420623779, + "learning_rate": 1.8235402221540367e-05, + "loss": 1.6258, + "step": 12988 + }, + { + "epoch": 0.7239841703361016, + "grad_norm": 0.5268842577934265, + "learning_rate": 1.8228526232375643e-05, + "loss": 1.6773, + "step": 12989 + }, + { + "epoch": 0.7240399085892648, + "grad_norm": 0.5661937594413757, + "learning_rate": 1.822165125081681e-05, + "loss": 1.6878, + "step": 12990 + }, + { + "epoch": 0.724095646842428, + "grad_norm": 0.554506242275238, + "learning_rate": 1.8214777277081917e-05, + "loss": 1.732, + "step": 12991 + }, + { + "epoch": 0.7241513850955911, + "grad_norm": 0.6218104958534241, + "learning_rate": 1.8207904311388973e-05, + "loss": 1.6358, + "step": 12992 + }, + { + "epoch": 0.7242071233487543, + "grad_norm": 0.5697388648986816, + "learning_rate": 1.8201032353955937e-05, + "loss": 1.7553, + "step": 12993 + }, + { + "epoch": 0.7242628616019174, + "grad_norm": 0.5874882936477661, + "learning_rate": 1.8194161405000777e-05, + "loss": 1.7667, + "step": 12994 + }, + { + "epoch": 0.7243185998550805, + "grad_norm": 0.5762251615524292, + "learning_rate": 1.8187291464741357e-05, + "loss": 1.5637, + "step": 12995 + }, + { + "epoch": 0.7243743381082437, + "grad_norm": 0.5835250020027161, + "learning_rate": 1.8180422533395552e-05, + "loss": 1.7027, + "step": 12996 + }, + { + "epoch": 0.7244300763614069, + "grad_norm": 0.5812956690788269, + "learning_rate": 1.817355461118126e-05, + "loss": 1.4391, + "step": 12997 + }, + { + "epoch": 0.72448581461457, + "grad_norm": 0.5332396030426025, + "learning_rate": 1.8166687698316236e-05, + "loss": 1.5179, + "step": 12998 + }, + { + "epoch": 0.7245415528677331, + "grad_norm": 0.6374024152755737, + "learning_rate": 1.815982179501828e-05, + "loss": 1.9367, + "step": 12999 + }, + { + "epoch": 0.7245972911208963, + "grad_norm": 0.5459944605827332, + "learning_rate": 1.815295690150513e-05, + "loss": 1.4403, + "step": 13000 + }, + { + "epoch": 0.7246530293740594, + "grad_norm": 0.5092973709106445, + "learning_rate": 1.814609301799453e-05, + "loss": 1.611, + "step": 13001 + }, + { + "epoch": 0.7247087676272226, + "grad_norm": 0.5163784623146057, + "learning_rate": 1.8139230144704116e-05, + "loss": 1.5506, + "step": 13002 + }, + { + "epoch": 0.7247645058803857, + "grad_norm": 0.5897939205169678, + "learning_rate": 1.8132368281851547e-05, + "loss": 1.7454, + "step": 13003 + }, + { + "epoch": 0.7248202441335488, + "grad_norm": 0.5630401372909546, + "learning_rate": 1.8125507429654488e-05, + "loss": 1.7844, + "step": 13004 + }, + { + "epoch": 0.724875982386712, + "grad_norm": 0.6095412969589233, + "learning_rate": 1.8118647588330472e-05, + "loss": 1.4738, + "step": 13005 + }, + { + "epoch": 0.7249317206398751, + "grad_norm": 0.5806434154510498, + "learning_rate": 1.8111788758097092e-05, + "loss": 1.7141, + "step": 13006 + }, + { + "epoch": 0.7249874588930383, + "grad_norm": 0.5746235251426697, + "learning_rate": 1.8104930939171814e-05, + "loss": 1.4829, + "step": 13007 + }, + { + "epoch": 0.7250431971462015, + "grad_norm": 0.5625148415565491, + "learning_rate": 1.809807413177221e-05, + "loss": 1.5404, + "step": 13008 + }, + { + "epoch": 0.7250989353993645, + "grad_norm": 0.6030070781707764, + "learning_rate": 1.8091218336115667e-05, + "loss": 1.6544, + "step": 13009 + }, + { + "epoch": 0.7251546736525277, + "grad_norm": 0.5468196272850037, + "learning_rate": 1.8084363552419643e-05, + "loss": 1.6339, + "step": 13010 + }, + { + "epoch": 0.7252104119056909, + "grad_norm": 0.5445948839187622, + "learning_rate": 1.807750978090152e-05, + "loss": 1.5828, + "step": 13011 + }, + { + "epoch": 0.725266150158854, + "grad_norm": 0.5647769570350647, + "learning_rate": 1.807065702177867e-05, + "loss": 1.5901, + "step": 13012 + }, + { + "epoch": 0.7253218884120172, + "grad_norm": 0.54178386926651, + "learning_rate": 1.8063805275268437e-05, + "loss": 1.7264, + "step": 13013 + }, + { + "epoch": 0.7253776266651804, + "grad_norm": 0.5340712070465088, + "learning_rate": 1.8056954541588063e-05, + "loss": 1.559, + "step": 13014 + }, + { + "epoch": 0.7254333649183434, + "grad_norm": 0.6358417272567749, + "learning_rate": 1.8050104820954883e-05, + "loss": 1.857, + "step": 13015 + }, + { + "epoch": 0.7254891031715066, + "grad_norm": 0.627558171749115, + "learning_rate": 1.8043256113586078e-05, + "loss": 1.9097, + "step": 13016 + }, + { + "epoch": 0.7255448414246698, + "grad_norm": 0.562868595123291, + "learning_rate": 1.8036408419698873e-05, + "loss": 1.6233, + "step": 13017 + }, + { + "epoch": 0.7256005796778329, + "grad_norm": 0.5979735851287842, + "learning_rate": 1.802956173951043e-05, + "loss": 1.7397, + "step": 13018 + }, + { + "epoch": 0.725656317930996, + "grad_norm": 0.5467450022697449, + "learning_rate": 1.8022716073237887e-05, + "loss": 1.5947, + "step": 13019 + }, + { + "epoch": 0.7257120561841592, + "grad_norm": 0.49903130531311035, + "learning_rate": 1.8015871421098373e-05, + "loss": 1.4622, + "step": 13020 + }, + { + "epoch": 0.7257677944373223, + "grad_norm": 0.5474138855934143, + "learning_rate": 1.8009027783308914e-05, + "loss": 1.7291, + "step": 13021 + }, + { + "epoch": 0.7258235326904855, + "grad_norm": 0.563923716545105, + "learning_rate": 1.8002185160086575e-05, + "loss": 1.5213, + "step": 13022 + }, + { + "epoch": 0.7258792709436487, + "grad_norm": 0.594559907913208, + "learning_rate": 1.7995343551648365e-05, + "loss": 1.7677, + "step": 13023 + }, + { + "epoch": 0.7259350091968118, + "grad_norm": 0.5416660308837891, + "learning_rate": 1.798850295821125e-05, + "loss": 1.4572, + "step": 13024 + }, + { + "epoch": 0.7259907474499749, + "grad_norm": 0.5499664545059204, + "learning_rate": 1.7981663379992187e-05, + "loss": 1.6194, + "step": 13025 + }, + { + "epoch": 0.726046485703138, + "grad_norm": 0.5548843145370483, + "learning_rate": 1.797482481720808e-05, + "loss": 1.5044, + "step": 13026 + }, + { + "epoch": 0.7261022239563012, + "grad_norm": 0.5904132127761841, + "learning_rate": 1.796798727007583e-05, + "loss": 1.5585, + "step": 13027 + }, + { + "epoch": 0.7261579622094644, + "grad_norm": 0.585654079914093, + "learning_rate": 1.7961150738812244e-05, + "loss": 1.6835, + "step": 13028 + }, + { + "epoch": 0.7262137004626275, + "grad_norm": 0.5477873682975769, + "learning_rate": 1.7954315223634143e-05, + "loss": 1.7269, + "step": 13029 + }, + { + "epoch": 0.7262694387157906, + "grad_norm": 0.5600523948669434, + "learning_rate": 1.794748072475836e-05, + "loss": 1.6663, + "step": 13030 + }, + { + "epoch": 0.7263251769689538, + "grad_norm": 0.6076684594154358, + "learning_rate": 1.7940647242401586e-05, + "loss": 1.7742, + "step": 13031 + }, + { + "epoch": 0.7263809152221169, + "grad_norm": 0.5797076225280762, + "learning_rate": 1.7933814776780583e-05, + "loss": 1.7405, + "step": 13032 + }, + { + "epoch": 0.7264366534752801, + "grad_norm": 0.5418017506599426, + "learning_rate": 1.7926983328111978e-05, + "loss": 1.6648, + "step": 13033 + }, + { + "epoch": 0.7264923917284433, + "grad_norm": 0.5510844588279724, + "learning_rate": 1.7920152896612503e-05, + "loss": 1.6446, + "step": 13034 + }, + { + "epoch": 0.7265481299816063, + "grad_norm": 0.5720747113227844, + "learning_rate": 1.7913323482498718e-05, + "loss": 1.7264, + "step": 13035 + }, + { + "epoch": 0.7266038682347695, + "grad_norm": 0.561935544013977, + "learning_rate": 1.7906495085987236e-05, + "loss": 1.5724, + "step": 13036 + }, + { + "epoch": 0.7266596064879327, + "grad_norm": 0.5294128060340881, + "learning_rate": 1.789966770729461e-05, + "loss": 1.6304, + "step": 13037 + }, + { + "epoch": 0.7267153447410958, + "grad_norm": 0.5671653151512146, + "learning_rate": 1.789284134663737e-05, + "loss": 1.6261, + "step": 13038 + }, + { + "epoch": 0.726771082994259, + "grad_norm": 0.5587400794029236, + "learning_rate": 1.788601600423202e-05, + "loss": 1.6302, + "step": 13039 + }, + { + "epoch": 0.7268268212474222, + "grad_norm": 0.5392343997955322, + "learning_rate": 1.787919168029497e-05, + "loss": 1.5139, + "step": 13040 + }, + { + "epoch": 0.7268825595005852, + "grad_norm": 0.5418177247047424, + "learning_rate": 1.787236837504272e-05, + "loss": 1.5585, + "step": 13041 + }, + { + "epoch": 0.7269382977537484, + "grad_norm": 0.5475856065750122, + "learning_rate": 1.786554608869161e-05, + "loss": 1.5051, + "step": 13042 + }, + { + "epoch": 0.7269940360069116, + "grad_norm": 0.5837298631668091, + "learning_rate": 1.785872482145802e-05, + "loss": 1.8636, + "step": 13043 + }, + { + "epoch": 0.7270497742600747, + "grad_norm": 0.517890453338623, + "learning_rate": 1.7851904573558276e-05, + "loss": 1.5822, + "step": 13044 + }, + { + "epoch": 0.7271055125132379, + "grad_norm": 0.5840612649917603, + "learning_rate": 1.784508534520869e-05, + "loss": 1.5041, + "step": 13045 + }, + { + "epoch": 0.727161250766401, + "grad_norm": 0.5422665476799011, + "learning_rate": 1.7838267136625535e-05, + "loss": 1.7019, + "step": 13046 + }, + { + "epoch": 0.7272169890195641, + "grad_norm": 0.577457845211029, + "learning_rate": 1.7831449948025015e-05, + "loss": 1.7343, + "step": 13047 + }, + { + "epoch": 0.7272727272727273, + "grad_norm": 0.603726327419281, + "learning_rate": 1.7824633779623347e-05, + "loss": 1.9108, + "step": 13048 + }, + { + "epoch": 0.7273284655258904, + "grad_norm": 0.5421007871627808, + "learning_rate": 1.78178186316367e-05, + "loss": 1.559, + "step": 13049 + }, + { + "epoch": 0.7273842037790536, + "grad_norm": 0.5838912129402161, + "learning_rate": 1.7811004504281208e-05, + "loss": 1.8311, + "step": 13050 + }, + { + "epoch": 0.7274399420322167, + "grad_norm": 0.5752909779548645, + "learning_rate": 1.7804191397772984e-05, + "loss": 1.585, + "step": 13051 + }, + { + "epoch": 0.7274956802853798, + "grad_norm": 0.5657978653907776, + "learning_rate": 1.7797379312328088e-05, + "loss": 1.4848, + "step": 13052 + }, + { + "epoch": 0.727551418538543, + "grad_norm": 0.5181905031204224, + "learning_rate": 1.7790568248162586e-05, + "loss": 1.5032, + "step": 13053 + }, + { + "epoch": 0.7276071567917062, + "grad_norm": 0.5629306435585022, + "learning_rate": 1.7783758205492452e-05, + "loss": 1.728, + "step": 13054 + }, + { + "epoch": 0.7276628950448693, + "grad_norm": 0.5550503134727478, + "learning_rate": 1.777694918453365e-05, + "loss": 1.4794, + "step": 13055 + }, + { + "epoch": 0.7277186332980324, + "grad_norm": 0.5529603362083435, + "learning_rate": 1.777014118550218e-05, + "loss": 1.5339, + "step": 13056 + }, + { + "epoch": 0.7277743715511956, + "grad_norm": 0.6003782153129578, + "learning_rate": 1.7763334208613908e-05, + "loss": 1.8527, + "step": 13057 + }, + { + "epoch": 0.7278301098043587, + "grad_norm": 0.5447100400924683, + "learning_rate": 1.775652825408472e-05, + "loss": 1.4837, + "step": 13058 + }, + { + "epoch": 0.7278858480575219, + "grad_norm": 0.5227007269859314, + "learning_rate": 1.7749723322130462e-05, + "loss": 1.4804, + "step": 13059 + }, + { + "epoch": 0.7279415863106851, + "grad_norm": 0.6335617899894714, + "learning_rate": 1.7742919412966964e-05, + "loss": 1.8064, + "step": 13060 + }, + { + "epoch": 0.7279973245638481, + "grad_norm": 0.5494779348373413, + "learning_rate": 1.7736116526809975e-05, + "loss": 1.6725, + "step": 13061 + }, + { + "epoch": 0.7280530628170113, + "grad_norm": 0.5667814612388611, + "learning_rate": 1.7729314663875257e-05, + "loss": 1.4949, + "step": 13062 + }, + { + "epoch": 0.7281088010701745, + "grad_norm": 0.5563710331916809, + "learning_rate": 1.7722513824378527e-05, + "loss": 1.4885, + "step": 13063 + }, + { + "epoch": 0.7281645393233376, + "grad_norm": 0.559414267539978, + "learning_rate": 1.7715714008535472e-05, + "loss": 1.653, + "step": 13064 + }, + { + "epoch": 0.7282202775765008, + "grad_norm": 0.5678215026855469, + "learning_rate": 1.770891521656175e-05, + "loss": 1.6643, + "step": 13065 + }, + { + "epoch": 0.728276015829664, + "grad_norm": 0.589455246925354, + "learning_rate": 1.7702117448672933e-05, + "loss": 1.8701, + "step": 13066 + }, + { + "epoch": 0.728331754082827, + "grad_norm": 0.5894622802734375, + "learning_rate": 1.7695320705084677e-05, + "loss": 1.8521, + "step": 13067 + }, + { + "epoch": 0.7283874923359902, + "grad_norm": 0.5983284711837769, + "learning_rate": 1.7688524986012484e-05, + "loss": 1.67, + "step": 13068 + }, + { + "epoch": 0.7284432305891534, + "grad_norm": 0.5873123407363892, + "learning_rate": 1.7681730291671888e-05, + "loss": 1.6678, + "step": 13069 + }, + { + "epoch": 0.7284989688423165, + "grad_norm": 0.6033545732498169, + "learning_rate": 1.7674936622278377e-05, + "loss": 1.6773, + "step": 13070 + }, + { + "epoch": 0.7285547070954796, + "grad_norm": 0.5835305452346802, + "learning_rate": 1.7668143978047408e-05, + "loss": 1.6948, + "step": 13071 + }, + { + "epoch": 0.7286104453486427, + "grad_norm": 0.6241502165794373, + "learning_rate": 1.7661352359194423e-05, + "loss": 1.9477, + "step": 13072 + }, + { + "epoch": 0.7286661836018059, + "grad_norm": 0.5314739346504211, + "learning_rate": 1.7654561765934772e-05, + "loss": 1.1618, + "step": 13073 + }, + { + "epoch": 0.7287219218549691, + "grad_norm": 0.5321511626243591, + "learning_rate": 1.7647772198483842e-05, + "loss": 1.5494, + "step": 13074 + }, + { + "epoch": 0.7287776601081322, + "grad_norm": 0.5920379161834717, + "learning_rate": 1.7640983657056948e-05, + "loss": 1.6923, + "step": 13075 + }, + { + "epoch": 0.7288333983612953, + "grad_norm": 0.5376768708229065, + "learning_rate": 1.7634196141869386e-05, + "loss": 1.6827, + "step": 13076 + }, + { + "epoch": 0.7288891366144585, + "grad_norm": 0.6414303183555603, + "learning_rate": 1.7627409653136417e-05, + "loss": 1.7496, + "step": 13077 + }, + { + "epoch": 0.7289448748676216, + "grad_norm": 0.5750012397766113, + "learning_rate": 1.7620624191073266e-05, + "loss": 1.5867, + "step": 13078 + }, + { + "epoch": 0.7290006131207848, + "grad_norm": 0.5717658996582031, + "learning_rate": 1.761383975589515e-05, + "loss": 1.8191, + "step": 13079 + }, + { + "epoch": 0.729056351373948, + "grad_norm": 0.6010684967041016, + "learning_rate": 1.7607056347817196e-05, + "loss": 1.8822, + "step": 13080 + }, + { + "epoch": 0.729112089627111, + "grad_norm": 0.6027198433876038, + "learning_rate": 1.7600273967054535e-05, + "loss": 1.7475, + "step": 13081 + }, + { + "epoch": 0.7291678278802742, + "grad_norm": 0.5768362879753113, + "learning_rate": 1.759349261382231e-05, + "loss": 1.6764, + "step": 13082 + }, + { + "epoch": 0.7292235661334374, + "grad_norm": 0.5655965209007263, + "learning_rate": 1.7586712288335543e-05, + "loss": 1.6163, + "step": 13083 + }, + { + "epoch": 0.7292793043866005, + "grad_norm": 0.525158166885376, + "learning_rate": 1.7579932990809277e-05, + "loss": 1.5605, + "step": 13084 + }, + { + "epoch": 0.7293350426397637, + "grad_norm": 0.5401511192321777, + "learning_rate": 1.7573154721458518e-05, + "loss": 1.458, + "step": 13085 + }, + { + "epoch": 0.7293907808929269, + "grad_norm": 0.499323308467865, + "learning_rate": 1.7566377480498246e-05, + "loss": 1.5316, + "step": 13086 + }, + { + "epoch": 0.7294465191460899, + "grad_norm": 0.5240613222122192, + "learning_rate": 1.755960126814336e-05, + "loss": 1.3185, + "step": 13087 + }, + { + "epoch": 0.7295022573992531, + "grad_norm": 0.5412852168083191, + "learning_rate": 1.755282608460878e-05, + "loss": 1.59, + "step": 13088 + }, + { + "epoch": 0.7295579956524163, + "grad_norm": 0.5833172798156738, + "learning_rate": 1.754605193010938e-05, + "loss": 1.7575, + "step": 13089 + }, + { + "epoch": 0.7296137339055794, + "grad_norm": 0.5948725342750549, + "learning_rate": 1.7539278804859993e-05, + "loss": 1.988, + "step": 13090 + }, + { + "epoch": 0.7296694721587426, + "grad_norm": 0.592042863368988, + "learning_rate": 1.7532506709075436e-05, + "loss": 1.6315, + "step": 13091 + }, + { + "epoch": 0.7297252104119057, + "grad_norm": 0.5844925045967102, + "learning_rate": 1.7525735642970438e-05, + "loss": 1.8533, + "step": 13092 + }, + { + "epoch": 0.7297809486650688, + "grad_norm": 0.59089195728302, + "learning_rate": 1.7518965606759797e-05, + "loss": 1.7435, + "step": 13093 + }, + { + "epoch": 0.729836686918232, + "grad_norm": 0.60077303647995, + "learning_rate": 1.7512196600658175e-05, + "loss": 1.6991, + "step": 13094 + }, + { + "epoch": 0.7298924251713951, + "grad_norm": 0.5530768632888794, + "learning_rate": 1.750542862488026e-05, + "loss": 1.6129, + "step": 13095 + }, + { + "epoch": 0.7299481634245583, + "grad_norm": 0.6510162949562073, + "learning_rate": 1.7498661679640693e-05, + "loss": 1.555, + "step": 13096 + }, + { + "epoch": 0.7300039016777214, + "grad_norm": 0.5623936653137207, + "learning_rate": 1.749189576515408e-05, + "loss": 1.5851, + "step": 13097 + }, + { + "epoch": 0.7300596399308845, + "grad_norm": 0.5465413331985474, + "learning_rate": 1.7485130881635014e-05, + "loss": 1.6828, + "step": 13098 + }, + { + "epoch": 0.7301153781840477, + "grad_norm": 0.5557692646980286, + "learning_rate": 1.747836702929801e-05, + "loss": 1.5023, + "step": 13099 + }, + { + "epoch": 0.7301711164372109, + "grad_norm": 0.6196216940879822, + "learning_rate": 1.7471604208357584e-05, + "loss": 1.7822, + "step": 13100 + }, + { + "epoch": 0.730226854690374, + "grad_norm": 0.5655481219291687, + "learning_rate": 1.746484241902822e-05, + "loss": 1.5506, + "step": 13101 + }, + { + "epoch": 0.7302825929435371, + "grad_norm": 0.5573101043701172, + "learning_rate": 1.7458081661524363e-05, + "loss": 1.7494, + "step": 13102 + }, + { + "epoch": 0.7303383311967003, + "grad_norm": 0.5817492008209229, + "learning_rate": 1.745132193606042e-05, + "loss": 1.6126, + "step": 13103 + }, + { + "epoch": 0.7303940694498634, + "grad_norm": 0.5593802332878113, + "learning_rate": 1.7444563242850774e-05, + "loss": 1.6587, + "step": 13104 + }, + { + "epoch": 0.7304498077030266, + "grad_norm": 0.5610882639884949, + "learning_rate": 1.743780558210979e-05, + "loss": 1.7012, + "step": 13105 + }, + { + "epoch": 0.7305055459561898, + "grad_norm": 0.5741089582443237, + "learning_rate": 1.743104895405175e-05, + "loss": 1.6279, + "step": 13106 + }, + { + "epoch": 0.7305612842093528, + "grad_norm": 0.5729717016220093, + "learning_rate": 1.742429335889092e-05, + "loss": 1.6917, + "step": 13107 + }, + { + "epoch": 0.730617022462516, + "grad_norm": 0.5948959589004517, + "learning_rate": 1.7417538796841615e-05, + "loss": 1.5668, + "step": 13108 + }, + { + "epoch": 0.7306727607156792, + "grad_norm": 0.5032156705856323, + "learning_rate": 1.741078526811799e-05, + "loss": 1.3751, + "step": 13109 + }, + { + "epoch": 0.7307284989688423, + "grad_norm": 0.5447957515716553, + "learning_rate": 1.7404032772934246e-05, + "loss": 1.5854, + "step": 13110 + }, + { + "epoch": 0.7307842372220055, + "grad_norm": 0.5654783248901367, + "learning_rate": 1.7397281311504544e-05, + "loss": 1.646, + "step": 13111 + }, + { + "epoch": 0.7308399754751687, + "grad_norm": 0.602711021900177, + "learning_rate": 1.7390530884043e-05, + "loss": 1.796, + "step": 13112 + }, + { + "epoch": 0.7308957137283317, + "grad_norm": 0.5649969577789307, + "learning_rate": 1.738378149076368e-05, + "loss": 1.5496, + "step": 13113 + }, + { + "epoch": 0.7309514519814949, + "grad_norm": 0.5492765307426453, + "learning_rate": 1.7377033131880638e-05, + "loss": 1.5582, + "step": 13114 + }, + { + "epoch": 0.7310071902346581, + "grad_norm": 0.7160940170288086, + "learning_rate": 1.7370285807607905e-05, + "loss": 1.5616, + "step": 13115 + }, + { + "epoch": 0.7310629284878212, + "grad_norm": 0.5868720412254333, + "learning_rate": 1.736353951815946e-05, + "loss": 1.6777, + "step": 13116 + }, + { + "epoch": 0.7311186667409844, + "grad_norm": 0.6325905323028564, + "learning_rate": 1.7356794263749275e-05, + "loss": 1.5789, + "step": 13117 + }, + { + "epoch": 0.7311744049941474, + "grad_norm": 0.573526918888092, + "learning_rate": 1.735005004459122e-05, + "loss": 1.4678, + "step": 13118 + }, + { + "epoch": 0.7312301432473106, + "grad_norm": 0.5424122214317322, + "learning_rate": 1.7343306860899243e-05, + "loss": 1.6012, + "step": 13119 + }, + { + "epoch": 0.7312858815004738, + "grad_norm": 0.5311015844345093, + "learning_rate": 1.733656471288716e-05, + "loss": 1.3831, + "step": 13120 + }, + { + "epoch": 0.7313416197536369, + "grad_norm": 0.7135401368141174, + "learning_rate": 1.73298236007688e-05, + "loss": 1.5432, + "step": 13121 + }, + { + "epoch": 0.7313973580068001, + "grad_norm": 0.5333171486854553, + "learning_rate": 1.732308352475796e-05, + "loss": 1.6044, + "step": 13122 + }, + { + "epoch": 0.7314530962599632, + "grad_norm": 0.5196841359138489, + "learning_rate": 1.7316344485068392e-05, + "loss": 1.4039, + "step": 13123 + }, + { + "epoch": 0.7315088345131263, + "grad_norm": 0.5499348044395447, + "learning_rate": 1.7309606481913826e-05, + "loss": 1.6396, + "step": 13124 + }, + { + "epoch": 0.7315645727662895, + "grad_norm": 0.5782787203788757, + "learning_rate": 1.730286951550792e-05, + "loss": 1.7854, + "step": 13125 + }, + { + "epoch": 0.7316203110194527, + "grad_norm": 0.5685500502586365, + "learning_rate": 1.7296133586064382e-05, + "loss": 1.8116, + "step": 13126 + }, + { + "epoch": 0.7316760492726158, + "grad_norm": 0.5851349234580994, + "learning_rate": 1.7289398693796795e-05, + "loss": 1.8243, + "step": 13127 + }, + { + "epoch": 0.7317317875257789, + "grad_norm": 0.5307192206382751, + "learning_rate": 1.7282664838918766e-05, + "loss": 1.4941, + "step": 13128 + }, + { + "epoch": 0.7317875257789421, + "grad_norm": 0.5350309014320374, + "learning_rate": 1.7275932021643853e-05, + "loss": 1.4587, + "step": 13129 + }, + { + "epoch": 0.7318432640321052, + "grad_norm": 0.5509794354438782, + "learning_rate": 1.726920024218558e-05, + "loss": 1.7593, + "step": 13130 + }, + { + "epoch": 0.7318990022852684, + "grad_norm": 0.6042940020561218, + "learning_rate": 1.726246950075746e-05, + "loss": 1.7246, + "step": 13131 + }, + { + "epoch": 0.7319547405384316, + "grad_norm": 0.5225052237510681, + "learning_rate": 1.7255739797572916e-05, + "loss": 1.4019, + "step": 13132 + }, + { + "epoch": 0.7320104787915946, + "grad_norm": 0.5401765704154968, + "learning_rate": 1.72490111328454e-05, + "loss": 1.4506, + "step": 13133 + }, + { + "epoch": 0.7320662170447578, + "grad_norm": 0.5437548160552979, + "learning_rate": 1.7242283506788292e-05, + "loss": 1.4996, + "step": 13134 + }, + { + "epoch": 0.732121955297921, + "grad_norm": 0.6444903612136841, + "learning_rate": 1.7235556919614964e-05, + "loss": 1.8975, + "step": 13135 + }, + { + "epoch": 0.7321776935510841, + "grad_norm": 0.5493695735931396, + "learning_rate": 1.722883137153874e-05, + "loss": 1.7209, + "step": 13136 + }, + { + "epoch": 0.7322334318042473, + "grad_norm": 0.5016687512397766, + "learning_rate": 1.7222106862772912e-05, + "loss": 1.3764, + "step": 13137 + }, + { + "epoch": 0.7322891700574105, + "grad_norm": 0.5542362928390503, + "learning_rate": 1.7215383393530767e-05, + "loss": 1.4915, + "step": 13138 + }, + { + "epoch": 0.7323449083105735, + "grad_norm": 0.571007251739502, + "learning_rate": 1.7208660964025498e-05, + "loss": 1.6684, + "step": 13139 + }, + { + "epoch": 0.7324006465637367, + "grad_norm": 0.5865726470947266, + "learning_rate": 1.720193957447031e-05, + "loss": 1.6384, + "step": 13140 + }, + { + "epoch": 0.7324563848168998, + "grad_norm": 0.5695785880088806, + "learning_rate": 1.719521922507838e-05, + "loss": 1.7146, + "step": 13141 + }, + { + "epoch": 0.732512123070063, + "grad_norm": 0.5801404118537903, + "learning_rate": 1.7188499916062823e-05, + "loss": 1.6765, + "step": 13142 + }, + { + "epoch": 0.7325678613232262, + "grad_norm": 0.5730370879173279, + "learning_rate": 1.718178164763677e-05, + "loss": 1.7715, + "step": 13143 + }, + { + "epoch": 0.7326235995763892, + "grad_norm": 0.6010292172431946, + "learning_rate": 1.717506442001322e-05, + "loss": 1.8965, + "step": 13144 + }, + { + "epoch": 0.7326793378295524, + "grad_norm": 0.5768089890480042, + "learning_rate": 1.716834823340528e-05, + "loss": 1.6592, + "step": 13145 + }, + { + "epoch": 0.7327350760827156, + "grad_norm": 0.5558800101280212, + "learning_rate": 1.7161633088025892e-05, + "loss": 1.6016, + "step": 13146 + }, + { + "epoch": 0.7327908143358787, + "grad_norm": 0.5557398200035095, + "learning_rate": 1.715491898408804e-05, + "loss": 1.5946, + "step": 13147 + }, + { + "epoch": 0.7328465525890419, + "grad_norm": 0.5502184629440308, + "learning_rate": 1.7148205921804665e-05, + "loss": 1.5196, + "step": 13148 + }, + { + "epoch": 0.732902290842205, + "grad_norm": 0.5514625906944275, + "learning_rate": 1.7141493901388657e-05, + "loss": 1.5667, + "step": 13149 + }, + { + "epoch": 0.7329580290953681, + "grad_norm": 0.5282281041145325, + "learning_rate": 1.71347829230529e-05, + "loss": 1.3212, + "step": 13150 + }, + { + "epoch": 0.7330137673485313, + "grad_norm": 0.5706415176391602, + "learning_rate": 1.7128072987010173e-05, + "loss": 1.8084, + "step": 13151 + }, + { + "epoch": 0.7330695056016945, + "grad_norm": 0.5897558331489563, + "learning_rate": 1.7121364093473352e-05, + "loss": 1.9594, + "step": 13152 + }, + { + "epoch": 0.7331252438548576, + "grad_norm": 0.5287189483642578, + "learning_rate": 1.7114656242655153e-05, + "loss": 1.6426, + "step": 13153 + }, + { + "epoch": 0.7331809821080207, + "grad_norm": 0.5570682287216187, + "learning_rate": 1.7107949434768317e-05, + "loss": 1.4455, + "step": 13154 + }, + { + "epoch": 0.7332367203611839, + "grad_norm": 0.529339075088501, + "learning_rate": 1.710124367002555e-05, + "loss": 1.5018, + "step": 13155 + }, + { + "epoch": 0.733292458614347, + "grad_norm": 0.584701657295227, + "learning_rate": 1.7094538948639527e-05, + "loss": 1.6713, + "step": 13156 + }, + { + "epoch": 0.7333481968675102, + "grad_norm": 0.5863745808601379, + "learning_rate": 1.7087835270822893e-05, + "loss": 1.6141, + "step": 13157 + }, + { + "epoch": 0.7334039351206734, + "grad_norm": 0.6347394585609436, + "learning_rate": 1.708113263678821e-05, + "loss": 1.7676, + "step": 13158 + }, + { + "epoch": 0.7334596733738364, + "grad_norm": 0.5613558292388916, + "learning_rate": 1.7074431046748075e-05, + "loss": 1.5305, + "step": 13159 + }, + { + "epoch": 0.7335154116269996, + "grad_norm": 0.559970498085022, + "learning_rate": 1.7067730500915015e-05, + "loss": 1.5329, + "step": 13160 + }, + { + "epoch": 0.7335711498801628, + "grad_norm": 0.6007326245307922, + "learning_rate": 1.7061030999501538e-05, + "loss": 1.8066, + "step": 13161 + }, + { + "epoch": 0.7336268881333259, + "grad_norm": 0.5830183029174805, + "learning_rate": 1.705433254272011e-05, + "loss": 1.6414, + "step": 13162 + }, + { + "epoch": 0.7336826263864891, + "grad_norm": 0.5798273682594299, + "learning_rate": 1.7047635130783163e-05, + "loss": 1.6874, + "step": 13163 + }, + { + "epoch": 0.7337383646396521, + "grad_norm": 0.576889157295227, + "learning_rate": 1.704093876390312e-05, + "loss": 1.8305, + "step": 13164 + }, + { + "epoch": 0.7337941028928153, + "grad_norm": 0.5485324263572693, + "learning_rate": 1.7034243442292326e-05, + "loss": 1.5281, + "step": 13165 + }, + { + "epoch": 0.7338498411459785, + "grad_norm": 0.5446223616600037, + "learning_rate": 1.702754916616312e-05, + "loss": 1.4261, + "step": 13166 + }, + { + "epoch": 0.7339055793991416, + "grad_norm": 0.558986485004425, + "learning_rate": 1.702085593572781e-05, + "loss": 1.4768, + "step": 13167 + }, + { + "epoch": 0.7339613176523048, + "grad_norm": 0.6452115178108215, + "learning_rate": 1.701416375119867e-05, + "loss": 1.8325, + "step": 13168 + }, + { + "epoch": 0.734017055905468, + "grad_norm": 0.6113860607147217, + "learning_rate": 1.7007472612787957e-05, + "loss": 1.8015, + "step": 13169 + }, + { + "epoch": 0.734072794158631, + "grad_norm": 0.526680588722229, + "learning_rate": 1.7000782520707815e-05, + "loss": 1.5654, + "step": 13170 + }, + { + "epoch": 0.7341285324117942, + "grad_norm": 0.5179544687271118, + "learning_rate": 1.6994093475170485e-05, + "loss": 1.5492, + "step": 13171 + }, + { + "epoch": 0.7341842706649574, + "grad_norm": 0.5642718076705933, + "learning_rate": 1.6987405476388056e-05, + "loss": 1.753, + "step": 13172 + }, + { + "epoch": 0.7342400089181205, + "grad_norm": 0.5657768845558167, + "learning_rate": 1.6980718524572648e-05, + "loss": 1.68, + "step": 13173 + }, + { + "epoch": 0.7342957471712837, + "grad_norm": 0.5769280195236206, + "learning_rate": 1.6974032619936338e-05, + "loss": 1.6085, + "step": 13174 + }, + { + "epoch": 0.7343514854244468, + "grad_norm": 0.5651370882987976, + "learning_rate": 1.6967347762691154e-05, + "loss": 1.6717, + "step": 13175 + }, + { + "epoch": 0.7344072236776099, + "grad_norm": 0.5511763691902161, + "learning_rate": 1.6960663953049123e-05, + "loss": 1.5811, + "step": 13176 + }, + { + "epoch": 0.7344629619307731, + "grad_norm": 0.5351390242576599, + "learning_rate": 1.6953981191222162e-05, + "loss": 1.6795, + "step": 13177 + }, + { + "epoch": 0.7345187001839363, + "grad_norm": 0.5856584906578064, + "learning_rate": 1.6947299477422284e-05, + "loss": 1.7929, + "step": 13178 + }, + { + "epoch": 0.7345744384370994, + "grad_norm": 0.5638580322265625, + "learning_rate": 1.6940618811861335e-05, + "loss": 1.6411, + "step": 13179 + }, + { + "epoch": 0.7346301766902625, + "grad_norm": 0.519822895526886, + "learning_rate": 1.6933939194751215e-05, + "loss": 1.5319, + "step": 13180 + }, + { + "epoch": 0.7346859149434257, + "grad_norm": 0.5416386723518372, + "learning_rate": 1.6927260626303748e-05, + "loss": 1.5279, + "step": 13181 + }, + { + "epoch": 0.7347416531965888, + "grad_norm": 0.6365106105804443, + "learning_rate": 1.6920583106730748e-05, + "loss": 1.8239, + "step": 13182 + }, + { + "epoch": 0.734797391449752, + "grad_norm": 0.6207970380783081, + "learning_rate": 1.6913906636244005e-05, + "loss": 1.7993, + "step": 13183 + }, + { + "epoch": 0.7348531297029152, + "grad_norm": 0.5355508923530579, + "learning_rate": 1.690723121505522e-05, + "loss": 1.5527, + "step": 13184 + }, + { + "epoch": 0.7349088679560782, + "grad_norm": 0.5439286231994629, + "learning_rate": 1.6900556843376115e-05, + "loss": 1.6684, + "step": 13185 + }, + { + "epoch": 0.7349646062092414, + "grad_norm": 0.5732739567756653, + "learning_rate": 1.6893883521418362e-05, + "loss": 1.5172, + "step": 13186 + }, + { + "epoch": 0.7350203444624045, + "grad_norm": 0.6353051066398621, + "learning_rate": 1.6887211249393608e-05, + "loss": 1.6473, + "step": 13187 + }, + { + "epoch": 0.7350760827155677, + "grad_norm": 0.6798067092895508, + "learning_rate": 1.6880540027513448e-05, + "loss": 1.8738, + "step": 13188 + }, + { + "epoch": 0.7351318209687309, + "grad_norm": 0.6208623051643372, + "learning_rate": 1.687386985598946e-05, + "loss": 1.8411, + "step": 13189 + }, + { + "epoch": 0.7351875592218939, + "grad_norm": 0.5615735650062561, + "learning_rate": 1.6867200735033196e-05, + "loss": 1.5319, + "step": 13190 + }, + { + "epoch": 0.7352432974750571, + "grad_norm": 0.5641026496887207, + "learning_rate": 1.6860532664856133e-05, + "loss": 1.5069, + "step": 13191 + }, + { + "epoch": 0.7352990357282203, + "grad_norm": 0.5726016163825989, + "learning_rate": 1.6853865645669752e-05, + "loss": 1.6411, + "step": 13192 + }, + { + "epoch": 0.7353547739813834, + "grad_norm": 0.5372188687324524, + "learning_rate": 1.6847199677685505e-05, + "loss": 1.6466, + "step": 13193 + }, + { + "epoch": 0.7354105122345466, + "grad_norm": 0.5255815386772156, + "learning_rate": 1.6840534761114786e-05, + "loss": 1.4866, + "step": 13194 + }, + { + "epoch": 0.7354662504877097, + "grad_norm": 0.5993079543113708, + "learning_rate": 1.683387089616899e-05, + "loss": 1.903, + "step": 13195 + }, + { + "epoch": 0.7355219887408728, + "grad_norm": 0.588141918182373, + "learning_rate": 1.68272080830594e-05, + "loss": 1.8349, + "step": 13196 + }, + { + "epoch": 0.735577726994036, + "grad_norm": 0.5988585948944092, + "learning_rate": 1.6820546321997395e-05, + "loss": 1.7329, + "step": 13197 + }, + { + "epoch": 0.7356334652471992, + "grad_norm": 0.5887940526008606, + "learning_rate": 1.6813885613194195e-05, + "loss": 1.6086, + "step": 13198 + }, + { + "epoch": 0.7356892035003623, + "grad_norm": 0.5614736080169678, + "learning_rate": 1.6807225956861054e-05, + "loss": 1.5956, + "step": 13199 + }, + { + "epoch": 0.7357449417535254, + "grad_norm": 0.5350954532623291, + "learning_rate": 1.6800567353209178e-05, + "loss": 1.5, + "step": 13200 + }, + { + "epoch": 0.7358006800066886, + "grad_norm": 0.5915472507476807, + "learning_rate": 1.6793909802449737e-05, + "loss": 1.764, + "step": 13201 + }, + { + "epoch": 0.7358564182598517, + "grad_norm": 0.5408633351325989, + "learning_rate": 1.6787253304793892e-05, + "loss": 1.5798, + "step": 13202 + }, + { + "epoch": 0.7359121565130149, + "grad_norm": 0.5959146618843079, + "learning_rate": 1.6780597860452695e-05, + "loss": 1.7875, + "step": 13203 + }, + { + "epoch": 0.7359678947661781, + "grad_norm": 0.6157255172729492, + "learning_rate": 1.6773943469637282e-05, + "loss": 1.7364, + "step": 13204 + }, + { + "epoch": 0.7360236330193412, + "grad_norm": 0.5907375812530518, + "learning_rate": 1.676729013255865e-05, + "loss": 1.5179, + "step": 13205 + }, + { + "epoch": 0.7360793712725043, + "grad_norm": 0.571946918964386, + "learning_rate": 1.6760637849427812e-05, + "loss": 1.6597, + "step": 13206 + }, + { + "epoch": 0.7361351095256675, + "grad_norm": 0.594362199306488, + "learning_rate": 1.675398662045574e-05, + "loss": 1.7935, + "step": 13207 + }, + { + "epoch": 0.7361908477788306, + "grad_norm": 0.5478150844573975, + "learning_rate": 1.6747336445853373e-05, + "loss": 1.5229, + "step": 13208 + }, + { + "epoch": 0.7362465860319938, + "grad_norm": 0.5203835368156433, + "learning_rate": 1.6740687325831638e-05, + "loss": 1.4077, + "step": 13209 + }, + { + "epoch": 0.7363023242851569, + "grad_norm": 0.5903517007827759, + "learning_rate": 1.673403926060137e-05, + "loss": 1.641, + "step": 13210 + }, + { + "epoch": 0.73635806253832, + "grad_norm": 0.5217337608337402, + "learning_rate": 1.672739225037342e-05, + "loss": 1.3975, + "step": 13211 + }, + { + "epoch": 0.7364138007914832, + "grad_norm": 0.5792795419692993, + "learning_rate": 1.6720746295358596e-05, + "loss": 1.8485, + "step": 13212 + }, + { + "epoch": 0.7364695390446463, + "grad_norm": 0.5703185200691223, + "learning_rate": 1.6714101395767673e-05, + "loss": 1.7343, + "step": 13213 + }, + { + "epoch": 0.7365252772978095, + "grad_norm": 0.5775966644287109, + "learning_rate": 1.670745755181138e-05, + "loss": 1.5785, + "step": 13214 + }, + { + "epoch": 0.7365810155509727, + "grad_norm": 0.5719923973083496, + "learning_rate": 1.670081476370042e-05, + "loss": 1.7871, + "step": 13215 + }, + { + "epoch": 0.7366367538041357, + "grad_norm": 0.5493507981300354, + "learning_rate": 1.669417303164549e-05, + "loss": 1.707, + "step": 13216 + }, + { + "epoch": 0.7366924920572989, + "grad_norm": 0.5433780550956726, + "learning_rate": 1.6687532355857183e-05, + "loss": 1.5654, + "step": 13217 + }, + { + "epoch": 0.7367482303104621, + "grad_norm": 0.5848167538642883, + "learning_rate": 1.668089273654611e-05, + "loss": 1.7403, + "step": 13218 + }, + { + "epoch": 0.7368039685636252, + "grad_norm": 0.5769858956336975, + "learning_rate": 1.6674254173922893e-05, + "loss": 1.8995, + "step": 13219 + }, + { + "epoch": 0.7368597068167884, + "grad_norm": 0.572632372379303, + "learning_rate": 1.666761666819801e-05, + "loss": 1.4678, + "step": 13220 + }, + { + "epoch": 0.7369154450699515, + "grad_norm": 0.592958927154541, + "learning_rate": 1.6660980219582e-05, + "loss": 1.5932, + "step": 13221 + }, + { + "epoch": 0.7369711833231146, + "grad_norm": 0.5782008171081543, + "learning_rate": 1.665434482828529e-05, + "loss": 1.8013, + "step": 13222 + }, + { + "epoch": 0.7370269215762778, + "grad_norm": 0.5540836453437805, + "learning_rate": 1.664771049451837e-05, + "loss": 1.4329, + "step": 13223 + }, + { + "epoch": 0.737082659829441, + "grad_norm": 0.5827534198760986, + "learning_rate": 1.6641077218491606e-05, + "loss": 1.4933, + "step": 13224 + }, + { + "epoch": 0.7371383980826041, + "grad_norm": 0.5785440802574158, + "learning_rate": 1.6634445000415372e-05, + "loss": 1.7321, + "step": 13225 + }, + { + "epoch": 0.7371941363357672, + "grad_norm": 0.5536699891090393, + "learning_rate": 1.662781384050001e-05, + "loss": 1.5427, + "step": 13226 + }, + { + "epoch": 0.7372498745889304, + "grad_norm": 0.5601542592048645, + "learning_rate": 1.662118373895582e-05, + "loss": 1.6237, + "step": 13227 + }, + { + "epoch": 0.7373056128420935, + "grad_norm": 0.5668201446533203, + "learning_rate": 1.6614554695993084e-05, + "loss": 1.7387, + "step": 13228 + }, + { + "epoch": 0.7373613510952567, + "grad_norm": 0.558070182800293, + "learning_rate": 1.660792671182199e-05, + "loss": 1.6295, + "step": 13229 + }, + { + "epoch": 0.7374170893484199, + "grad_norm": 0.6125143766403198, + "learning_rate": 1.6601299786652807e-05, + "loss": 1.6571, + "step": 13230 + }, + { + "epoch": 0.737472827601583, + "grad_norm": 0.5656547546386719, + "learning_rate": 1.6594673920695647e-05, + "loss": 1.7502, + "step": 13231 + }, + { + "epoch": 0.7375285658547461, + "grad_norm": 0.6245994567871094, + "learning_rate": 1.658804911416067e-05, + "loss": 1.7857, + "step": 13232 + }, + { + "epoch": 0.7375843041079092, + "grad_norm": 0.5701721906661987, + "learning_rate": 1.6581425367257963e-05, + "loss": 1.5482, + "step": 13233 + }, + { + "epoch": 0.7376400423610724, + "grad_norm": 0.5576661229133606, + "learning_rate": 1.65748026801976e-05, + "loss": 1.6569, + "step": 13234 + }, + { + "epoch": 0.7376957806142356, + "grad_norm": 0.546334445476532, + "learning_rate": 1.656818105318963e-05, + "loss": 1.8769, + "step": 13235 + }, + { + "epoch": 0.7377515188673986, + "grad_norm": 0.5302374362945557, + "learning_rate": 1.6561560486444023e-05, + "loss": 1.5192, + "step": 13236 + }, + { + "epoch": 0.7378072571205618, + "grad_norm": 0.5588144063949585, + "learning_rate": 1.6554940980170757e-05, + "loss": 1.5064, + "step": 13237 + }, + { + "epoch": 0.737862995373725, + "grad_norm": 0.5656217932701111, + "learning_rate": 1.6548322534579765e-05, + "loss": 1.5538, + "step": 13238 + }, + { + "epoch": 0.7379187336268881, + "grad_norm": 0.5525779724121094, + "learning_rate": 1.6541705149880943e-05, + "loss": 1.5847, + "step": 13239 + }, + { + "epoch": 0.7379744718800513, + "grad_norm": 0.5362941026687622, + "learning_rate": 1.6535088826284158e-05, + "loss": 1.6449, + "step": 13240 + }, + { + "epoch": 0.7380302101332145, + "grad_norm": 0.531810998916626, + "learning_rate": 1.652847356399924e-05, + "loss": 1.608, + "step": 13241 + }, + { + "epoch": 0.7380859483863775, + "grad_norm": 0.5702958106994629, + "learning_rate": 1.6521859363236008e-05, + "loss": 1.5354, + "step": 13242 + }, + { + "epoch": 0.7381416866395407, + "grad_norm": 0.5588272213935852, + "learning_rate": 1.651524622420419e-05, + "loss": 1.658, + "step": 13243 + }, + { + "epoch": 0.7381974248927039, + "grad_norm": 0.5959174633026123, + "learning_rate": 1.6508634147113515e-05, + "loss": 1.6284, + "step": 13244 + }, + { + "epoch": 0.738253163145867, + "grad_norm": 0.5471432209014893, + "learning_rate": 1.6502023132173733e-05, + "loss": 1.7111, + "step": 13245 + }, + { + "epoch": 0.7383089013990302, + "grad_norm": 0.5873154401779175, + "learning_rate": 1.6495413179594448e-05, + "loss": 1.6066, + "step": 13246 + }, + { + "epoch": 0.7383646396521933, + "grad_norm": 0.5228626728057861, + "learning_rate": 1.648880428958533e-05, + "loss": 1.409, + "step": 13247 + }, + { + "epoch": 0.7384203779053564, + "grad_norm": 0.6058785319328308, + "learning_rate": 1.6482196462355925e-05, + "loss": 1.6826, + "step": 13248 + }, + { + "epoch": 0.7384761161585196, + "grad_norm": 0.5443040728569031, + "learning_rate": 1.6475589698115856e-05, + "loss": 1.2258, + "step": 13249 + }, + { + "epoch": 0.7385318544116828, + "grad_norm": 0.5611996054649353, + "learning_rate": 1.6468983997074606e-05, + "loss": 1.6302, + "step": 13250 + }, + { + "epoch": 0.7385875926648459, + "grad_norm": 0.5696637630462646, + "learning_rate": 1.6462379359441683e-05, + "loss": 1.4842, + "step": 13251 + }, + { + "epoch": 0.738643330918009, + "grad_norm": 0.7141457796096802, + "learning_rate": 1.6455775785426548e-05, + "loss": 1.771, + "step": 13252 + }, + { + "epoch": 0.7386990691711722, + "grad_norm": 0.5674689412117004, + "learning_rate": 1.6449173275238634e-05, + "loss": 1.7011, + "step": 13253 + }, + { + "epoch": 0.7387548074243353, + "grad_norm": 0.5802819728851318, + "learning_rate": 1.644257182908734e-05, + "loss": 1.7596, + "step": 13254 + }, + { + "epoch": 0.7388105456774985, + "grad_norm": 0.5873621106147766, + "learning_rate": 1.6435971447181982e-05, + "loss": 1.626, + "step": 13255 + }, + { + "epoch": 0.7388662839306616, + "grad_norm": 0.585585355758667, + "learning_rate": 1.642937212973195e-05, + "loss": 1.5525, + "step": 13256 + }, + { + "epoch": 0.7389220221838247, + "grad_norm": 0.5948177576065063, + "learning_rate": 1.642277387694649e-05, + "loss": 1.5693, + "step": 13257 + }, + { + "epoch": 0.7389777604369879, + "grad_norm": 0.5636075139045715, + "learning_rate": 1.6416176689034873e-05, + "loss": 1.6173, + "step": 13258 + }, + { + "epoch": 0.739033498690151, + "grad_norm": 0.5540120005607605, + "learning_rate": 1.6409580566206324e-05, + "loss": 1.6737, + "step": 13259 + }, + { + "epoch": 0.7390892369433142, + "grad_norm": 0.5813601016998291, + "learning_rate": 1.6402985508670032e-05, + "loss": 1.8666, + "step": 13260 + }, + { + "epoch": 0.7391449751964774, + "grad_norm": 0.5551378130912781, + "learning_rate": 1.639639151663518e-05, + "loss": 1.8081, + "step": 13261 + }, + { + "epoch": 0.7392007134496404, + "grad_norm": 0.5455393195152283, + "learning_rate": 1.638979859031084e-05, + "loss": 1.7515, + "step": 13262 + }, + { + "epoch": 0.7392564517028036, + "grad_norm": 0.6024508476257324, + "learning_rate": 1.638320672990613e-05, + "loss": 1.8197, + "step": 13263 + }, + { + "epoch": 0.7393121899559668, + "grad_norm": 0.5206683874130249, + "learning_rate": 1.6376615935630106e-05, + "loss": 1.4308, + "step": 13264 + }, + { + "epoch": 0.7393679282091299, + "grad_norm": 0.5082628130912781, + "learning_rate": 1.6370026207691786e-05, + "loss": 1.4348, + "step": 13265 + }, + { + "epoch": 0.7394236664622931, + "grad_norm": 0.5659313201904297, + "learning_rate": 1.636343754630015e-05, + "loss": 1.7006, + "step": 13266 + }, + { + "epoch": 0.7394794047154563, + "grad_norm": 0.5450108647346497, + "learning_rate": 1.6356849951664172e-05, + "loss": 1.5063, + "step": 13267 + }, + { + "epoch": 0.7395351429686193, + "grad_norm": 0.5550732016563416, + "learning_rate": 1.6350263423992774e-05, + "loss": 1.6295, + "step": 13268 + }, + { + "epoch": 0.7395908812217825, + "grad_norm": 0.6069827675819397, + "learning_rate": 1.634367796349481e-05, + "loss": 1.7564, + "step": 13269 + }, + { + "epoch": 0.7396466194749457, + "grad_norm": 0.5506473779678345, + "learning_rate": 1.6337093570379153e-05, + "loss": 1.6458, + "step": 13270 + }, + { + "epoch": 0.7397023577281088, + "grad_norm": 0.5603538751602173, + "learning_rate": 1.6330510244854612e-05, + "loss": 1.5231, + "step": 13271 + }, + { + "epoch": 0.739758095981272, + "grad_norm": 0.6235647201538086, + "learning_rate": 1.632392798712999e-05, + "loss": 1.9289, + "step": 13272 + }, + { + "epoch": 0.7398138342344351, + "grad_norm": 0.5420436263084412, + "learning_rate": 1.631734679741404e-05, + "loss": 1.515, + "step": 13273 + }, + { + "epoch": 0.7398695724875982, + "grad_norm": 0.5445640683174133, + "learning_rate": 1.631076667591543e-05, + "loss": 1.5093, + "step": 13274 + }, + { + "epoch": 0.7399253107407614, + "grad_norm": 0.5499640107154846, + "learning_rate": 1.6304187622842916e-05, + "loss": 1.7421, + "step": 13275 + }, + { + "epoch": 0.7399810489939246, + "grad_norm": 0.5200676321983337, + "learning_rate": 1.6297609638405093e-05, + "loss": 1.4374, + "step": 13276 + }, + { + "epoch": 0.7400367872470877, + "grad_norm": 0.5372708439826965, + "learning_rate": 1.629103272281059e-05, + "loss": 1.591, + "step": 13277 + }, + { + "epoch": 0.7400925255002508, + "grad_norm": 0.58269864320755, + "learning_rate": 1.6284456876267994e-05, + "loss": 1.8288, + "step": 13278 + }, + { + "epoch": 0.7401482637534139, + "grad_norm": 0.5352569818496704, + "learning_rate": 1.6277882098985852e-05, + "loss": 1.4758, + "step": 13279 + }, + { + "epoch": 0.7402040020065771, + "grad_norm": 0.591149628162384, + "learning_rate": 1.6271308391172696e-05, + "loss": 1.7342, + "step": 13280 + }, + { + "epoch": 0.7402597402597403, + "grad_norm": 0.6212684512138367, + "learning_rate": 1.626473575303695e-05, + "loss": 1.7038, + "step": 13281 + }, + { + "epoch": 0.7403154785129034, + "grad_norm": 0.6295444369316101, + "learning_rate": 1.6258164184787123e-05, + "loss": 1.5131, + "step": 13282 + }, + { + "epoch": 0.7403712167660665, + "grad_norm": 0.5664548277854919, + "learning_rate": 1.6251593686631588e-05, + "loss": 1.6506, + "step": 13283 + }, + { + "epoch": 0.7404269550192297, + "grad_norm": 0.5600103139877319, + "learning_rate": 1.6245024258778733e-05, + "loss": 1.7275, + "step": 13284 + }, + { + "epoch": 0.7404826932723928, + "grad_norm": 0.5680475831031799, + "learning_rate": 1.6238455901436905e-05, + "loss": 1.4691, + "step": 13285 + }, + { + "epoch": 0.740538431525556, + "grad_norm": 0.5569763779640198, + "learning_rate": 1.6231888614814416e-05, + "loss": 1.6232, + "step": 13286 + }, + { + "epoch": 0.7405941697787192, + "grad_norm": 0.5917499661445618, + "learning_rate": 1.622532239911955e-05, + "loss": 1.6881, + "step": 13287 + }, + { + "epoch": 0.7406499080318822, + "grad_norm": 0.5224557518959045, + "learning_rate": 1.6218757254560523e-05, + "loss": 1.496, + "step": 13288 + }, + { + "epoch": 0.7407056462850454, + "grad_norm": 0.5698574781417847, + "learning_rate": 1.6212193181345554e-05, + "loss": 1.7215, + "step": 13289 + }, + { + "epoch": 0.7407613845382086, + "grad_norm": 0.567707896232605, + "learning_rate": 1.6205630179682825e-05, + "loss": 1.6221, + "step": 13290 + }, + { + "epoch": 0.7408171227913717, + "grad_norm": 0.5405696630477905, + "learning_rate": 1.619906824978047e-05, + "loss": 1.6172, + "step": 13291 + }, + { + "epoch": 0.7408728610445349, + "grad_norm": 0.5634341239929199, + "learning_rate": 1.6192507391846597e-05, + "loss": 1.5224, + "step": 13292 + }, + { + "epoch": 0.740928599297698, + "grad_norm": 0.6389575004577637, + "learning_rate": 1.618594760608928e-05, + "loss": 2.1171, + "step": 13293 + }, + { + "epoch": 0.7409843375508611, + "grad_norm": 0.5640349388122559, + "learning_rate": 1.6179388892716568e-05, + "loss": 1.4332, + "step": 13294 + }, + { + "epoch": 0.7410400758040243, + "grad_norm": 0.5597231388092041, + "learning_rate": 1.617283125193644e-05, + "loss": 1.7089, + "step": 13295 + }, + { + "epoch": 0.7410958140571875, + "grad_norm": 0.5188087224960327, + "learning_rate": 1.6166274683956872e-05, + "loss": 1.425, + "step": 13296 + }, + { + "epoch": 0.7411515523103506, + "grad_norm": 0.5404828190803528, + "learning_rate": 1.6159719188985813e-05, + "loss": 1.599, + "step": 13297 + }, + { + "epoch": 0.7412072905635138, + "grad_norm": 0.5605739951133728, + "learning_rate": 1.615316476723116e-05, + "loss": 1.713, + "step": 13298 + }, + { + "epoch": 0.7412630288166769, + "grad_norm": 0.5415946841239929, + "learning_rate": 1.6146611418900777e-05, + "loss": 1.5347, + "step": 13299 + }, + { + "epoch": 0.74131876706984, + "grad_norm": 0.5645654201507568, + "learning_rate": 1.6140059144202497e-05, + "loss": 1.7316, + "step": 13300 + }, + { + "epoch": 0.7413745053230032, + "grad_norm": 0.5823950171470642, + "learning_rate": 1.6133507943344144e-05, + "loss": 1.8572, + "step": 13301 + }, + { + "epoch": 0.7414302435761663, + "grad_norm": 0.5628172159194946, + "learning_rate": 1.612695781653345e-05, + "loss": 1.6987, + "step": 13302 + }, + { + "epoch": 0.7414859818293295, + "grad_norm": 0.5878089070320129, + "learning_rate": 1.6120408763978156e-05, + "loss": 1.6614, + "step": 13303 + }, + { + "epoch": 0.7415417200824926, + "grad_norm": 0.5398010611534119, + "learning_rate": 1.6113860785885966e-05, + "loss": 1.4362, + "step": 13304 + }, + { + "epoch": 0.7415974583356557, + "grad_norm": 0.5680728554725647, + "learning_rate": 1.6107313882464542e-05, + "loss": 1.5918, + "step": 13305 + }, + { + "epoch": 0.7416531965888189, + "grad_norm": 0.5598174333572388, + "learning_rate": 1.6100768053921534e-05, + "loss": 1.6136, + "step": 13306 + }, + { + "epoch": 0.7417089348419821, + "grad_norm": 0.5566685199737549, + "learning_rate": 1.609422330046448e-05, + "loss": 1.3586, + "step": 13307 + }, + { + "epoch": 0.7417646730951452, + "grad_norm": 0.5482991933822632, + "learning_rate": 1.608767962230101e-05, + "loss": 1.6597, + "step": 13308 + }, + { + "epoch": 0.7418204113483083, + "grad_norm": 0.5422983169555664, + "learning_rate": 1.6081137019638603e-05, + "loss": 1.3816, + "step": 13309 + }, + { + "epoch": 0.7418761496014715, + "grad_norm": 0.592792272567749, + "learning_rate": 1.6074595492684774e-05, + "loss": 1.9714, + "step": 13310 + }, + { + "epoch": 0.7419318878546346, + "grad_norm": 0.5382637977600098, + "learning_rate": 1.6068055041646973e-05, + "loss": 1.647, + "step": 13311 + }, + { + "epoch": 0.7419876261077978, + "grad_norm": 0.549544095993042, + "learning_rate": 1.606151566673263e-05, + "loss": 1.5836, + "step": 13312 + }, + { + "epoch": 0.742043364360961, + "grad_norm": 0.5724050402641296, + "learning_rate": 1.6054977368149154e-05, + "loss": 1.6138, + "step": 13313 + }, + { + "epoch": 0.742099102614124, + "grad_norm": 0.5999428629875183, + "learning_rate": 1.6048440146103866e-05, + "loss": 1.9437, + "step": 13314 + }, + { + "epoch": 0.7421548408672872, + "grad_norm": 0.6062003970146179, + "learning_rate": 1.6041904000804103e-05, + "loss": 1.6194, + "step": 13315 + }, + { + "epoch": 0.7422105791204504, + "grad_norm": 0.5726443529129028, + "learning_rate": 1.603536893245715e-05, + "loss": 1.7029, + "step": 13316 + }, + { + "epoch": 0.7422663173736135, + "grad_norm": 0.6113731265068054, + "learning_rate": 1.6028834941270277e-05, + "loss": 1.6231, + "step": 13317 + }, + { + "epoch": 0.7423220556267767, + "grad_norm": 0.5550969839096069, + "learning_rate": 1.602230202745069e-05, + "loss": 1.4641, + "step": 13318 + }, + { + "epoch": 0.7423777938799399, + "grad_norm": 0.5901103019714355, + "learning_rate": 1.601577019120558e-05, + "loss": 1.5502, + "step": 13319 + }, + { + "epoch": 0.7424335321331029, + "grad_norm": 0.5575149655342102, + "learning_rate": 1.600923943274211e-05, + "loss": 1.437, + "step": 13320 + }, + { + "epoch": 0.7424892703862661, + "grad_norm": 0.5528237819671631, + "learning_rate": 1.6002709752267375e-05, + "loss": 1.4918, + "step": 13321 + }, + { + "epoch": 0.7425450086394293, + "grad_norm": 0.5548231601715088, + "learning_rate": 1.5996181149988467e-05, + "loss": 1.7844, + "step": 13322 + }, + { + "epoch": 0.7426007468925924, + "grad_norm": 0.5276260375976562, + "learning_rate": 1.598965362611243e-05, + "loss": 1.5067, + "step": 13323 + }, + { + "epoch": 0.7426564851457556, + "grad_norm": 0.5183296799659729, + "learning_rate": 1.5983127180846298e-05, + "loss": 1.454, + "step": 13324 + }, + { + "epoch": 0.7427122233989186, + "grad_norm": 0.6147708892822266, + "learning_rate": 1.597660181439703e-05, + "loss": 1.7211, + "step": 13325 + }, + { + "epoch": 0.7427679616520818, + "grad_norm": 0.5286272168159485, + "learning_rate": 1.5970077526971582e-05, + "loss": 1.4562, + "step": 13326 + }, + { + "epoch": 0.742823699905245, + "grad_norm": 0.5524761080741882, + "learning_rate": 1.596355431877689e-05, + "loss": 1.8089, + "step": 13327 + }, + { + "epoch": 0.7428794381584081, + "grad_norm": 0.581933856010437, + "learning_rate": 1.5957032190019787e-05, + "loss": 1.6357, + "step": 13328 + }, + { + "epoch": 0.7429351764115713, + "grad_norm": 0.5518571138381958, + "learning_rate": 1.5950511140907142e-05, + "loss": 1.5216, + "step": 13329 + }, + { + "epoch": 0.7429909146647344, + "grad_norm": 0.569599449634552, + "learning_rate": 1.5943991171645762e-05, + "loss": 1.6905, + "step": 13330 + }, + { + "epoch": 0.7430466529178975, + "grad_norm": 0.5589736700057983, + "learning_rate": 1.5937472282442416e-05, + "loss": 1.6697, + "step": 13331 + }, + { + "epoch": 0.7431023911710607, + "grad_norm": 0.6014086008071899, + "learning_rate": 1.5930954473503874e-05, + "loss": 1.7427, + "step": 13332 + }, + { + "epoch": 0.7431581294242239, + "grad_norm": 0.5605618357658386, + "learning_rate": 1.5924437745036784e-05, + "loss": 1.6212, + "step": 13333 + }, + { + "epoch": 0.743213867677387, + "grad_norm": 0.525735080242157, + "learning_rate": 1.5917922097247882e-05, + "loss": 1.4751, + "step": 13334 + }, + { + "epoch": 0.7432696059305501, + "grad_norm": 0.6295618414878845, + "learning_rate": 1.5911407530343768e-05, + "loss": 1.9724, + "step": 13335 + }, + { + "epoch": 0.7433253441837133, + "grad_norm": 0.5409222841262817, + "learning_rate": 1.590489404453106e-05, + "loss": 1.3127, + "step": 13336 + }, + { + "epoch": 0.7433810824368764, + "grad_norm": 0.5514601469039917, + "learning_rate": 1.5898381640016318e-05, + "loss": 1.6791, + "step": 13337 + }, + { + "epoch": 0.7434368206900396, + "grad_norm": 0.6076371669769287, + "learning_rate": 1.5891870317006093e-05, + "loss": 1.6209, + "step": 13338 + }, + { + "epoch": 0.7434925589432028, + "grad_norm": 0.5812973976135254, + "learning_rate": 1.5885360075706886e-05, + "loss": 1.6723, + "step": 13339 + }, + { + "epoch": 0.7435482971963658, + "grad_norm": 0.5968800187110901, + "learning_rate": 1.587885091632514e-05, + "loss": 1.8016, + "step": 13340 + }, + { + "epoch": 0.743604035449529, + "grad_norm": 0.5531649589538574, + "learning_rate": 1.5872342839067306e-05, + "loss": 1.6212, + "step": 13341 + }, + { + "epoch": 0.7436597737026922, + "grad_norm": 0.5633963942527771, + "learning_rate": 1.5865835844139776e-05, + "loss": 1.735, + "step": 13342 + }, + { + "epoch": 0.7437155119558553, + "grad_norm": 0.5534663796424866, + "learning_rate": 1.585932993174892e-05, + "loss": 1.6558, + "step": 13343 + }, + { + "epoch": 0.7437712502090185, + "grad_norm": 0.5312620997428894, + "learning_rate": 1.585282510210106e-05, + "loss": 1.4825, + "step": 13344 + }, + { + "epoch": 0.7438269884621816, + "grad_norm": 0.6024535894393921, + "learning_rate": 1.58463213554025e-05, + "loss": 1.7989, + "step": 13345 + }, + { + "epoch": 0.7438827267153447, + "grad_norm": 0.5507554411888123, + "learning_rate": 1.583981869185951e-05, + "loss": 1.6123, + "step": 13346 + }, + { + "epoch": 0.7439384649685079, + "grad_norm": 0.5958787798881531, + "learning_rate": 1.5833317111678285e-05, + "loss": 1.7726, + "step": 13347 + }, + { + "epoch": 0.743994203221671, + "grad_norm": 0.5509111285209656, + "learning_rate": 1.5826816615065042e-05, + "loss": 1.6517, + "step": 13348 + }, + { + "epoch": 0.7440499414748342, + "grad_norm": 0.5578701496124268, + "learning_rate": 1.5820317202225926e-05, + "loss": 1.6328, + "step": 13349 + }, + { + "epoch": 0.7441056797279973, + "grad_norm": 0.5589818954467773, + "learning_rate": 1.5813818873367076e-05, + "loss": 1.632, + "step": 13350 + }, + { + "epoch": 0.7441614179811604, + "grad_norm": 0.5828130841255188, + "learning_rate": 1.5807321628694567e-05, + "loss": 1.5918, + "step": 13351 + }, + { + "epoch": 0.7442171562343236, + "grad_norm": 0.5889452695846558, + "learning_rate": 1.5800825468414452e-05, + "loss": 1.8415, + "step": 13352 + }, + { + "epoch": 0.7442728944874868, + "grad_norm": 0.624024510383606, + "learning_rate": 1.5794330392732787e-05, + "loss": 1.6525, + "step": 13353 + }, + { + "epoch": 0.7443286327406499, + "grad_norm": 0.5891615748405457, + "learning_rate": 1.5787836401855503e-05, + "loss": 1.7335, + "step": 13354 + }, + { + "epoch": 0.744384370993813, + "grad_norm": 0.5748935341835022, + "learning_rate": 1.578134349598858e-05, + "loss": 1.6273, + "step": 13355 + }, + { + "epoch": 0.7444401092469762, + "grad_norm": 0.5996773838996887, + "learning_rate": 1.577485167533794e-05, + "loss": 1.7174, + "step": 13356 + }, + { + "epoch": 0.7444958475001393, + "grad_norm": 0.5693355202674866, + "learning_rate": 1.576836094010945e-05, + "loss": 1.621, + "step": 13357 + }, + { + "epoch": 0.7445515857533025, + "grad_norm": 0.5534161329269409, + "learning_rate": 1.5761871290508983e-05, + "loss": 1.4205, + "step": 13358 + }, + { + "epoch": 0.7446073240064657, + "grad_norm": 0.5653291940689087, + "learning_rate": 1.5755382726742308e-05, + "loss": 1.6063, + "step": 13359 + }, + { + "epoch": 0.7446630622596287, + "grad_norm": 0.5330468416213989, + "learning_rate": 1.5748895249015266e-05, + "loss": 1.6184, + "step": 13360 + }, + { + "epoch": 0.7447188005127919, + "grad_norm": 0.6169772744178772, + "learning_rate": 1.5742408857533546e-05, + "loss": 1.6787, + "step": 13361 + }, + { + "epoch": 0.7447745387659551, + "grad_norm": 0.5544992089271545, + "learning_rate": 1.573592355250289e-05, + "loss": 1.5111, + "step": 13362 + }, + { + "epoch": 0.7448302770191182, + "grad_norm": 0.62140953540802, + "learning_rate": 1.572943933412896e-05, + "loss": 1.7729, + "step": 13363 + }, + { + "epoch": 0.7448860152722814, + "grad_norm": 0.5693691372871399, + "learning_rate": 1.5722956202617408e-05, + "loss": 1.5573, + "step": 13364 + }, + { + "epoch": 0.7449417535254446, + "grad_norm": 0.5448788404464722, + "learning_rate": 1.5716474158173845e-05, + "loss": 1.5506, + "step": 13365 + }, + { + "epoch": 0.7449974917786076, + "grad_norm": 0.5135059952735901, + "learning_rate": 1.5709993201003827e-05, + "loss": 1.4187, + "step": 13366 + }, + { + "epoch": 0.7450532300317708, + "grad_norm": 0.5643311738967896, + "learning_rate": 1.570351333131289e-05, + "loss": 1.6344, + "step": 13367 + }, + { + "epoch": 0.745108968284934, + "grad_norm": 0.5740456581115723, + "learning_rate": 1.5697034549306554e-05, + "loss": 1.6753, + "step": 13368 + }, + { + "epoch": 0.7451647065380971, + "grad_norm": 0.5633687973022461, + "learning_rate": 1.569055685519028e-05, + "loss": 1.8055, + "step": 13369 + }, + { + "epoch": 0.7452204447912603, + "grad_norm": 0.5269423127174377, + "learning_rate": 1.5684080249169507e-05, + "loss": 1.426, + "step": 13370 + }, + { + "epoch": 0.7452761830444233, + "grad_norm": 0.6111160516738892, + "learning_rate": 1.5677604731449635e-05, + "loss": 1.832, + "step": 13371 + }, + { + "epoch": 0.7453319212975865, + "grad_norm": 0.5429782271385193, + "learning_rate": 1.5671130302236038e-05, + "loss": 1.511, + "step": 13372 + }, + { + "epoch": 0.7453876595507497, + "grad_norm": 0.6169877052307129, + "learning_rate": 1.5664656961734025e-05, + "loss": 1.8098, + "step": 13373 + }, + { + "epoch": 0.7454433978039128, + "grad_norm": 0.5550345182418823, + "learning_rate": 1.5658184710148897e-05, + "loss": 1.6672, + "step": 13374 + }, + { + "epoch": 0.745499136057076, + "grad_norm": 0.6161905527114868, + "learning_rate": 1.565171354768593e-05, + "loss": 1.9259, + "step": 13375 + }, + { + "epoch": 0.7455548743102391, + "grad_norm": 0.5543949007987976, + "learning_rate": 1.5645243474550346e-05, + "loss": 1.6948, + "step": 13376 + }, + { + "epoch": 0.7456106125634022, + "grad_norm": 0.5576022863388062, + "learning_rate": 1.5638774490947332e-05, + "loss": 1.6303, + "step": 13377 + }, + { + "epoch": 0.7456663508165654, + "grad_norm": 0.5574358105659485, + "learning_rate": 1.563230659708206e-05, + "loss": 1.56, + "step": 13378 + }, + { + "epoch": 0.7457220890697286, + "grad_norm": 0.5838919281959534, + "learning_rate": 1.562583979315965e-05, + "loss": 1.79, + "step": 13379 + }, + { + "epoch": 0.7457778273228917, + "grad_norm": 0.5559114813804626, + "learning_rate": 1.5619374079385175e-05, + "loss": 1.6725, + "step": 13380 + }, + { + "epoch": 0.7458335655760548, + "grad_norm": 0.5833230018615723, + "learning_rate": 1.5612909455963703e-05, + "loss": 1.8324, + "step": 13381 + }, + { + "epoch": 0.745889303829218, + "grad_norm": 0.59188312292099, + "learning_rate": 1.560644592310025e-05, + "loss": 1.5773, + "step": 13382 + }, + { + "epoch": 0.7459450420823811, + "grad_norm": 0.5672659277915955, + "learning_rate": 1.5599983480999802e-05, + "loss": 1.4419, + "step": 13383 + }, + { + "epoch": 0.7460007803355443, + "grad_norm": 0.5613914728164673, + "learning_rate": 1.559352212986733e-05, + "loss": 1.6136, + "step": 13384 + }, + { + "epoch": 0.7460565185887075, + "grad_norm": 0.5510649681091309, + "learning_rate": 1.5587061869907704e-05, + "loss": 1.5806, + "step": 13385 + }, + { + "epoch": 0.7461122568418705, + "grad_norm": 0.5434938073158264, + "learning_rate": 1.5580602701325865e-05, + "loss": 1.6182, + "step": 13386 + }, + { + "epoch": 0.7461679950950337, + "grad_norm": 0.5438975691795349, + "learning_rate": 1.5574144624326607e-05, + "loss": 1.4877, + "step": 13387 + }, + { + "epoch": 0.7462237333481969, + "grad_norm": 0.5524957180023193, + "learning_rate": 1.5567687639114776e-05, + "loss": 1.4704, + "step": 13388 + }, + { + "epoch": 0.74627947160136, + "grad_norm": 0.5521454811096191, + "learning_rate": 1.5561231745895127e-05, + "loss": 1.6477, + "step": 13389 + }, + { + "epoch": 0.7463352098545232, + "grad_norm": 0.6323177218437195, + "learning_rate": 1.5554776944872422e-05, + "loss": 1.8731, + "step": 13390 + }, + { + "epoch": 0.7463909481076864, + "grad_norm": 0.5329812169075012, + "learning_rate": 1.5548323236251378e-05, + "loss": 1.4527, + "step": 13391 + }, + { + "epoch": 0.7464466863608494, + "grad_norm": 0.5540409088134766, + "learning_rate": 1.5541870620236622e-05, + "loss": 1.7002, + "step": 13392 + }, + { + "epoch": 0.7465024246140126, + "grad_norm": 0.5764815807342529, + "learning_rate": 1.5535419097032854e-05, + "loss": 1.7703, + "step": 13393 + }, + { + "epoch": 0.7465581628671757, + "grad_norm": 0.5406001806259155, + "learning_rate": 1.5528968666844634e-05, + "loss": 1.7067, + "step": 13394 + }, + { + "epoch": 0.7466139011203389, + "grad_norm": 0.5606533288955688, + "learning_rate": 1.552251932987655e-05, + "loss": 1.5557, + "step": 13395 + }, + { + "epoch": 0.7466696393735021, + "grad_norm": 0.5777366757392883, + "learning_rate": 1.5516071086333138e-05, + "loss": 1.6904, + "step": 13396 + }, + { + "epoch": 0.7467253776266651, + "grad_norm": 0.6230834722518921, + "learning_rate": 1.5509623936418892e-05, + "loss": 1.6019, + "step": 13397 + }, + { + "epoch": 0.7467811158798283, + "grad_norm": 0.5899634957313538, + "learning_rate": 1.5503177880338298e-05, + "loss": 1.8989, + "step": 13398 + }, + { + "epoch": 0.7468368541329915, + "grad_norm": 0.5678186416625977, + "learning_rate": 1.5496732918295755e-05, + "loss": 1.7319, + "step": 13399 + }, + { + "epoch": 0.7468925923861546, + "grad_norm": 0.587462842464447, + "learning_rate": 1.5490289050495676e-05, + "loss": 1.8259, + "step": 13400 + }, + { + "epoch": 0.7469483306393178, + "grad_norm": 0.5820348858833313, + "learning_rate": 1.5483846277142423e-05, + "loss": 1.658, + "step": 13401 + }, + { + "epoch": 0.7470040688924809, + "grad_norm": 0.5110056400299072, + "learning_rate": 1.5477404598440327e-05, + "loss": 1.3426, + "step": 13402 + }, + { + "epoch": 0.747059807145644, + "grad_norm": 0.6571440696716309, + "learning_rate": 1.547096401459367e-05, + "loss": 1.5072, + "step": 13403 + }, + { + "epoch": 0.7471155453988072, + "grad_norm": 0.6007630228996277, + "learning_rate": 1.5464524525806717e-05, + "loss": 1.7707, + "step": 13404 + }, + { + "epoch": 0.7471712836519704, + "grad_norm": 0.5080630779266357, + "learning_rate": 1.5458086132283712e-05, + "loss": 1.5782, + "step": 13405 + }, + { + "epoch": 0.7472270219051335, + "grad_norm": 0.5876208543777466, + "learning_rate": 1.54516488342288e-05, + "loss": 1.5931, + "step": 13406 + }, + { + "epoch": 0.7472827601582966, + "grad_norm": 0.5827615261077881, + "learning_rate": 1.5445212631846157e-05, + "loss": 1.7915, + "step": 13407 + }, + { + "epoch": 0.7473384984114598, + "grad_norm": 0.570421576499939, + "learning_rate": 1.5438777525339902e-05, + "loss": 1.6272, + "step": 13408 + }, + { + "epoch": 0.7473942366646229, + "grad_norm": 0.5399143099784851, + "learning_rate": 1.5432343514914123e-05, + "loss": 1.4453, + "step": 13409 + }, + { + "epoch": 0.7474499749177861, + "grad_norm": 0.5795050859451294, + "learning_rate": 1.5425910600772868e-05, + "loss": 1.4543, + "step": 13410 + }, + { + "epoch": 0.7475057131709493, + "grad_norm": 0.542121946811676, + "learning_rate": 1.5419478783120127e-05, + "loss": 1.5641, + "step": 13411 + }, + { + "epoch": 0.7475614514241123, + "grad_norm": 0.5423764586448669, + "learning_rate": 1.541304806215993e-05, + "loss": 1.5104, + "step": 13412 + }, + { + "epoch": 0.7476171896772755, + "grad_norm": 0.5753214359283447, + "learning_rate": 1.5406618438096172e-05, + "loss": 1.8031, + "step": 13413 + }, + { + "epoch": 0.7476729279304387, + "grad_norm": 0.5540892481803894, + "learning_rate": 1.540018991113279e-05, + "loss": 1.8608, + "step": 13414 + }, + { + "epoch": 0.7477286661836018, + "grad_norm": 0.5682497620582581, + "learning_rate": 1.5393762481473644e-05, + "loss": 1.6909, + "step": 13415 + }, + { + "epoch": 0.747784404436765, + "grad_norm": 0.529656708240509, + "learning_rate": 1.5387336149322594e-05, + "loss": 1.7286, + "step": 13416 + }, + { + "epoch": 0.747840142689928, + "grad_norm": 0.5613870024681091, + "learning_rate": 1.5380910914883445e-05, + "loss": 1.6818, + "step": 13417 + }, + { + "epoch": 0.7478958809430912, + "grad_norm": 0.5584611296653748, + "learning_rate": 1.5374486778359932e-05, + "loss": 1.6994, + "step": 13418 + }, + { + "epoch": 0.7479516191962544, + "grad_norm": 0.5976415872573853, + "learning_rate": 1.5368063739955845e-05, + "loss": 1.8279, + "step": 13419 + }, + { + "epoch": 0.7480073574494175, + "grad_norm": 0.5717959403991699, + "learning_rate": 1.5361641799874843e-05, + "loss": 1.5076, + "step": 13420 + }, + { + "epoch": 0.7480630957025807, + "grad_norm": 0.5503527522087097, + "learning_rate": 1.5355220958320604e-05, + "loss": 1.604, + "step": 13421 + }, + { + "epoch": 0.7481188339557439, + "grad_norm": 0.5726061463356018, + "learning_rate": 1.5348801215496773e-05, + "loss": 1.8152, + "step": 13422 + }, + { + "epoch": 0.7481745722089069, + "grad_norm": 0.5453668236732483, + "learning_rate": 1.5342382571606928e-05, + "loss": 1.6422, + "step": 13423 + }, + { + "epoch": 0.7482303104620701, + "grad_norm": 0.5500398278236389, + "learning_rate": 1.533596502685466e-05, + "loss": 1.5407, + "step": 13424 + }, + { + "epoch": 0.7482860487152333, + "grad_norm": 0.5172477960586548, + "learning_rate": 1.532954858144346e-05, + "loss": 1.4653, + "step": 13425 + }, + { + "epoch": 0.7483417869683964, + "grad_norm": 0.5574005842208862, + "learning_rate": 1.532313323557683e-05, + "loss": 1.5693, + "step": 13426 + }, + { + "epoch": 0.7483975252215596, + "grad_norm": 0.5705146193504333, + "learning_rate": 1.531671898945824e-05, + "loss": 1.5493, + "step": 13427 + }, + { + "epoch": 0.7484532634747227, + "grad_norm": 0.5598993301391602, + "learning_rate": 1.5310305843291106e-05, + "loss": 1.3341, + "step": 13428 + }, + { + "epoch": 0.7485090017278858, + "grad_norm": 0.5688292384147644, + "learning_rate": 1.5303893797278813e-05, + "loss": 1.6766, + "step": 13429 + }, + { + "epoch": 0.748564739981049, + "grad_norm": 0.5565484166145325, + "learning_rate": 1.5297482851624718e-05, + "loss": 1.7853, + "step": 13430 + }, + { + "epoch": 0.7486204782342122, + "grad_norm": 0.5675035119056702, + "learning_rate": 1.529107300653215e-05, + "loss": 1.6365, + "step": 13431 + }, + { + "epoch": 0.7486762164873753, + "grad_norm": 0.5844092965126038, + "learning_rate": 1.528466426220437e-05, + "loss": 1.6628, + "step": 13432 + }, + { + "epoch": 0.7487319547405384, + "grad_norm": 0.5560231804847717, + "learning_rate": 1.527825661884463e-05, + "loss": 1.5994, + "step": 13433 + }, + { + "epoch": 0.7487876929937016, + "grad_norm": 0.5227312445640564, + "learning_rate": 1.527185007665615e-05, + "loss": 1.4491, + "step": 13434 + }, + { + "epoch": 0.7488434312468647, + "grad_norm": 0.5424653887748718, + "learning_rate": 1.526544463584211e-05, + "loss": 1.7824, + "step": 13435 + }, + { + "epoch": 0.7488991695000279, + "grad_norm": 0.586765468120575, + "learning_rate": 1.525904029660566e-05, + "loss": 1.5596, + "step": 13436 + }, + { + "epoch": 0.7489549077531911, + "grad_norm": 0.5893957614898682, + "learning_rate": 1.5252637059149866e-05, + "loss": 1.7777, + "step": 13437 + }, + { + "epoch": 0.7490106460063541, + "grad_norm": 0.5714499950408936, + "learning_rate": 1.5246234923677866e-05, + "loss": 1.6985, + "step": 13438 + }, + { + "epoch": 0.7490663842595173, + "grad_norm": 0.620743453502655, + "learning_rate": 1.5239833890392652e-05, + "loss": 1.9387, + "step": 13439 + }, + { + "epoch": 0.7491221225126804, + "grad_norm": 0.5654244422912598, + "learning_rate": 1.523343395949724e-05, + "loss": 1.5936, + "step": 13440 + }, + { + "epoch": 0.7491778607658436, + "grad_norm": 0.5660731792449951, + "learning_rate": 1.52270351311946e-05, + "loss": 1.6402, + "step": 13441 + }, + { + "epoch": 0.7492335990190068, + "grad_norm": 0.5458896160125732, + "learning_rate": 1.5220637405687659e-05, + "loss": 1.599, + "step": 13442 + }, + { + "epoch": 0.7492893372721698, + "grad_norm": 0.5200908184051514, + "learning_rate": 1.5214240783179345e-05, + "loss": 1.5019, + "step": 13443 + }, + { + "epoch": 0.749345075525333, + "grad_norm": 0.5807740092277527, + "learning_rate": 1.5207845263872466e-05, + "loss": 1.6836, + "step": 13444 + }, + { + "epoch": 0.7494008137784962, + "grad_norm": 0.6102779507637024, + "learning_rate": 1.5201450847969911e-05, + "loss": 1.6637, + "step": 13445 + }, + { + "epoch": 0.7494565520316593, + "grad_norm": 0.5772900581359863, + "learning_rate": 1.5195057535674434e-05, + "loss": 1.7797, + "step": 13446 + }, + { + "epoch": 0.7495122902848225, + "grad_norm": 0.6321548223495483, + "learning_rate": 1.5188665327188805e-05, + "loss": 1.7168, + "step": 13447 + }, + { + "epoch": 0.7495680285379857, + "grad_norm": 0.5762151479721069, + "learning_rate": 1.5182274222715747e-05, + "loss": 1.4862, + "step": 13448 + }, + { + "epoch": 0.7496237667911487, + "grad_norm": 0.5636744499206543, + "learning_rate": 1.5175884222457948e-05, + "loss": 1.6067, + "step": 13449 + }, + { + "epoch": 0.7496795050443119, + "grad_norm": 0.5497311949729919, + "learning_rate": 1.5169495326618077e-05, + "loss": 1.5944, + "step": 13450 + }, + { + "epoch": 0.7497352432974751, + "grad_norm": 0.5859318971633911, + "learning_rate": 1.5163107535398724e-05, + "loss": 1.7657, + "step": 13451 + }, + { + "epoch": 0.7497909815506382, + "grad_norm": 0.5736318826675415, + "learning_rate": 1.5156720849002487e-05, + "loss": 1.4466, + "step": 13452 + }, + { + "epoch": 0.7498467198038014, + "grad_norm": 0.6058290600776672, + "learning_rate": 1.5150335267631915e-05, + "loss": 1.6204, + "step": 13453 + }, + { + "epoch": 0.7499024580569645, + "grad_norm": 0.568292498588562, + "learning_rate": 1.514395079148952e-05, + "loss": 1.8471, + "step": 13454 + }, + { + "epoch": 0.7499581963101276, + "grad_norm": 0.566444993019104, + "learning_rate": 1.5137567420777783e-05, + "loss": 1.567, + "step": 13455 + }, + { + "epoch": 0.7500139345632908, + "grad_norm": 0.5849542617797852, + "learning_rate": 1.513118515569914e-05, + "loss": 1.6508, + "step": 13456 + }, + { + "epoch": 0.750069672816454, + "grad_norm": 0.5593271255493164, + "learning_rate": 1.5124803996456021e-05, + "loss": 1.6505, + "step": 13457 + }, + { + "epoch": 0.750125411069617, + "grad_norm": 0.5788416862487793, + "learning_rate": 1.5118423943250771e-05, + "loss": 1.7703, + "step": 13458 + }, + { + "epoch": 0.7501811493227802, + "grad_norm": 0.6123077869415283, + "learning_rate": 1.511204499628574e-05, + "loss": 1.8, + "step": 13459 + }, + { + "epoch": 0.7502368875759434, + "grad_norm": 0.5456638336181641, + "learning_rate": 1.5105667155763231e-05, + "loss": 1.597, + "step": 13460 + }, + { + "epoch": 0.7502926258291065, + "grad_norm": 0.5396011471748352, + "learning_rate": 1.5099290421885509e-05, + "loss": 1.56, + "step": 13461 + }, + { + "epoch": 0.7503483640822697, + "grad_norm": 0.5928915143013, + "learning_rate": 1.5092914794854824e-05, + "loss": 1.7026, + "step": 13462 + }, + { + "epoch": 0.7504041023354328, + "grad_norm": 0.5351876020431519, + "learning_rate": 1.5086540274873328e-05, + "loss": 1.7195, + "step": 13463 + }, + { + "epoch": 0.7504598405885959, + "grad_norm": 0.561486005783081, + "learning_rate": 1.5080166862143253e-05, + "loss": 1.5934, + "step": 13464 + }, + { + "epoch": 0.7505155788417591, + "grad_norm": 0.5588828325271606, + "learning_rate": 1.5073794556866666e-05, + "loss": 1.4999, + "step": 13465 + }, + { + "epoch": 0.7505713170949222, + "grad_norm": 0.6039292812347412, + "learning_rate": 1.5067423359245686e-05, + "loss": 1.836, + "step": 13466 + }, + { + "epoch": 0.7506270553480854, + "grad_norm": 0.5354037284851074, + "learning_rate": 1.5061053269482362e-05, + "loss": 1.7677, + "step": 13467 + }, + { + "epoch": 0.7506827936012486, + "grad_norm": 0.5810551643371582, + "learning_rate": 1.505468428777872e-05, + "loss": 1.5995, + "step": 13468 + }, + { + "epoch": 0.7507385318544116, + "grad_norm": 0.5635651350021362, + "learning_rate": 1.5048316414336766e-05, + "loss": 1.7743, + "step": 13469 + }, + { + "epoch": 0.7507942701075748, + "grad_norm": 0.5567081570625305, + "learning_rate": 1.50419496493584e-05, + "loss": 1.4866, + "step": 13470 + }, + { + "epoch": 0.750850008360738, + "grad_norm": 0.5657464861869812, + "learning_rate": 1.5035583993045604e-05, + "loss": 1.601, + "step": 13471 + }, + { + "epoch": 0.7509057466139011, + "grad_norm": 0.5875218510627747, + "learning_rate": 1.5029219445600212e-05, + "loss": 1.8084, + "step": 13472 + }, + { + "epoch": 0.7509614848670643, + "grad_norm": 0.5419088006019592, + "learning_rate": 1.5022856007224084e-05, + "loss": 1.498, + "step": 13473 + }, + { + "epoch": 0.7510172231202275, + "grad_norm": 0.5150018334388733, + "learning_rate": 1.5016493678119031e-05, + "loss": 1.4284, + "step": 13474 + }, + { + "epoch": 0.7510729613733905, + "grad_norm": 0.5912177562713623, + "learning_rate": 1.5010132458486832e-05, + "loss": 1.8732, + "step": 13475 + }, + { + "epoch": 0.7511286996265537, + "grad_norm": 0.5249746441841125, + "learning_rate": 1.5003772348529243e-05, + "loss": 1.4964, + "step": 13476 + }, + { + "epoch": 0.7511844378797169, + "grad_norm": 0.5486159920692444, + "learning_rate": 1.4997413348447937e-05, + "loss": 1.5421, + "step": 13477 + }, + { + "epoch": 0.75124017613288, + "grad_norm": 0.5511107444763184, + "learning_rate": 1.4991055458444597e-05, + "loss": 1.664, + "step": 13478 + }, + { + "epoch": 0.7512959143860432, + "grad_norm": 0.5520987510681152, + "learning_rate": 1.4984698678720865e-05, + "loss": 1.4636, + "step": 13479 + }, + { + "epoch": 0.7513516526392063, + "grad_norm": 0.553927481174469, + "learning_rate": 1.4978343009478335e-05, + "loss": 1.5685, + "step": 13480 + }, + { + "epoch": 0.7514073908923694, + "grad_norm": 0.5070444345474243, + "learning_rate": 1.4971988450918578e-05, + "loss": 1.4127, + "step": 13481 + }, + { + "epoch": 0.7514631291455326, + "grad_norm": 0.5468535423278809, + "learning_rate": 1.4965635003243117e-05, + "loss": 1.6098, + "step": 13482 + }, + { + "epoch": 0.7515188673986958, + "grad_norm": 0.5456457138061523, + "learning_rate": 1.4959282666653468e-05, + "loss": 1.6879, + "step": 13483 + }, + { + "epoch": 0.7515746056518589, + "grad_norm": 0.54702228307724, + "learning_rate": 1.4952931441351054e-05, + "loss": 1.5991, + "step": 13484 + }, + { + "epoch": 0.751630343905022, + "grad_norm": 0.5564615726470947, + "learning_rate": 1.4946581327537312e-05, + "loss": 1.5979, + "step": 13485 + }, + { + "epoch": 0.7516860821581851, + "grad_norm": 0.5617123246192932, + "learning_rate": 1.4940232325413638e-05, + "loss": 1.672, + "step": 13486 + }, + { + "epoch": 0.7517418204113483, + "grad_norm": 0.6110641956329346, + "learning_rate": 1.4933884435181383e-05, + "loss": 1.7764, + "step": 13487 + }, + { + "epoch": 0.7517975586645115, + "grad_norm": 0.5776284337043762, + "learning_rate": 1.4927537657041879e-05, + "loss": 1.6431, + "step": 13488 + }, + { + "epoch": 0.7518532969176746, + "grad_norm": 0.5718814730644226, + "learning_rate": 1.4921191991196365e-05, + "loss": 1.5381, + "step": 13489 + }, + { + "epoch": 0.7519090351708377, + "grad_norm": 0.616912841796875, + "learning_rate": 1.4914847437846147e-05, + "loss": 1.7817, + "step": 13490 + }, + { + "epoch": 0.7519647734240009, + "grad_norm": 0.5536419153213501, + "learning_rate": 1.4908503997192391e-05, + "loss": 1.6046, + "step": 13491 + }, + { + "epoch": 0.752020511677164, + "grad_norm": 0.5831686854362488, + "learning_rate": 1.4902161669436287e-05, + "loss": 1.8871, + "step": 13492 + }, + { + "epoch": 0.7520762499303272, + "grad_norm": 0.6020655632019043, + "learning_rate": 1.4895820454778986e-05, + "loss": 1.6076, + "step": 13493 + }, + { + "epoch": 0.7521319881834904, + "grad_norm": 0.5684720873832703, + "learning_rate": 1.4889480353421586e-05, + "loss": 1.5878, + "step": 13494 + }, + { + "epoch": 0.7521877264366534, + "grad_norm": 0.5338294506072998, + "learning_rate": 1.4883141365565178e-05, + "loss": 1.5914, + "step": 13495 + }, + { + "epoch": 0.7522434646898166, + "grad_norm": 0.5656914710998535, + "learning_rate": 1.4876803491410746e-05, + "loss": 1.5741, + "step": 13496 + }, + { + "epoch": 0.7522992029429798, + "grad_norm": 0.6254673004150391, + "learning_rate": 1.487046673115936e-05, + "loss": 1.6547, + "step": 13497 + }, + { + "epoch": 0.7523549411961429, + "grad_norm": 0.5721585750579834, + "learning_rate": 1.4864131085011934e-05, + "loss": 1.6673, + "step": 13498 + }, + { + "epoch": 0.7524106794493061, + "grad_norm": 0.589742124080658, + "learning_rate": 1.4857796553169412e-05, + "loss": 1.4904, + "step": 13499 + }, + { + "epoch": 0.7524664177024692, + "grad_norm": 0.5777998566627502, + "learning_rate": 1.4851463135832689e-05, + "loss": 1.6627, + "step": 13500 + }, + { + "epoch": 0.7525221559556323, + "grad_norm": 0.5200433135032654, + "learning_rate": 1.4845130833202625e-05, + "loss": 1.4796, + "step": 13501 + }, + { + "epoch": 0.7525778942087955, + "grad_norm": 0.5812724232673645, + "learning_rate": 1.4838799645480061e-05, + "loss": 1.4919, + "step": 13502 + }, + { + "epoch": 0.7526336324619587, + "grad_norm": 0.6124995946884155, + "learning_rate": 1.4832469572865754e-05, + "loss": 1.7236, + "step": 13503 + }, + { + "epoch": 0.7526893707151218, + "grad_norm": 0.5346381664276123, + "learning_rate": 1.4826140615560469e-05, + "loss": 1.56, + "step": 13504 + }, + { + "epoch": 0.752745108968285, + "grad_norm": 0.6158668994903564, + "learning_rate": 1.4819812773764924e-05, + "loss": 1.7928, + "step": 13505 + }, + { + "epoch": 0.7528008472214481, + "grad_norm": 0.5613118410110474, + "learning_rate": 1.4813486047679808e-05, + "loss": 1.7989, + "step": 13506 + }, + { + "epoch": 0.7528565854746112, + "grad_norm": 0.5942383408546448, + "learning_rate": 1.4807160437505756e-05, + "loss": 1.8563, + "step": 13507 + }, + { + "epoch": 0.7529123237277744, + "grad_norm": 0.5570755004882812, + "learning_rate": 1.4800835943443392e-05, + "loss": 1.6341, + "step": 13508 + }, + { + "epoch": 0.7529680619809375, + "grad_norm": 0.5737524032592773, + "learning_rate": 1.4794512565693303e-05, + "loss": 1.5606, + "step": 13509 + }, + { + "epoch": 0.7530238002341006, + "grad_norm": 0.5694605112075806, + "learning_rate": 1.4788190304455996e-05, + "loss": 1.6136, + "step": 13510 + }, + { + "epoch": 0.7530795384872638, + "grad_norm": 0.5719156265258789, + "learning_rate": 1.4781869159931994e-05, + "loss": 1.6516, + "step": 13511 + }, + { + "epoch": 0.7531352767404269, + "grad_norm": 0.5556133389472961, + "learning_rate": 1.4775549132321764e-05, + "loss": 1.6058, + "step": 13512 + }, + { + "epoch": 0.7531910149935901, + "grad_norm": 0.5758563280105591, + "learning_rate": 1.4769230221825741e-05, + "loss": 1.6085, + "step": 13513 + }, + { + "epoch": 0.7532467532467533, + "grad_norm": 0.5548908710479736, + "learning_rate": 1.4762912428644348e-05, + "loss": 1.5802, + "step": 13514 + }, + { + "epoch": 0.7533024914999163, + "grad_norm": 0.5532346963882446, + "learning_rate": 1.4756595752977892e-05, + "loss": 1.5401, + "step": 13515 + }, + { + "epoch": 0.7533582297530795, + "grad_norm": NaN, + "learning_rate": 1.4756595752977892e-05, + "loss": 1.6784, + "step": 13516 + }, + { + "epoch": 0.7534139680062427, + "grad_norm": 0.5984622240066528, + "learning_rate": 1.4750280195026767e-05, + "loss": 1.782, + "step": 13517 + }, + { + "epoch": 0.7534697062594058, + "grad_norm": 0.5604650378227234, + "learning_rate": 1.4743965754991217e-05, + "loss": 1.4861, + "step": 13518 + }, + { + "epoch": 0.753525444512569, + "grad_norm": 0.5935846567153931, + "learning_rate": 1.4737652433071513e-05, + "loss": 1.8707, + "step": 13519 + }, + { + "epoch": 0.7535811827657322, + "grad_norm": 0.5540009140968323, + "learning_rate": 1.4731340229467888e-05, + "loss": 1.606, + "step": 13520 + }, + { + "epoch": 0.7536369210188952, + "grad_norm": 0.5764244794845581, + "learning_rate": 1.4725029144380515e-05, + "loss": 1.7317, + "step": 13521 + }, + { + "epoch": 0.7536926592720584, + "grad_norm": 0.5727776288986206, + "learning_rate": 1.4718719178009567e-05, + "loss": 1.5096, + "step": 13522 + }, + { + "epoch": 0.7537483975252216, + "grad_norm": 0.6232305765151978, + "learning_rate": 1.471241033055511e-05, + "loss": 1.5065, + "step": 13523 + }, + { + "epoch": 0.7538041357783847, + "grad_norm": 0.5429270267486572, + "learning_rate": 1.4706102602217291e-05, + "loss": 1.5696, + "step": 13524 + }, + { + "epoch": 0.7538598740315479, + "grad_norm": 0.5457437634468079, + "learning_rate": 1.4699795993196103e-05, + "loss": 1.7403, + "step": 13525 + }, + { + "epoch": 0.753915612284711, + "grad_norm": 0.5556396245956421, + "learning_rate": 1.4693490503691571e-05, + "loss": 1.6232, + "step": 13526 + }, + { + "epoch": 0.7539713505378741, + "grad_norm": 0.5786697864532471, + "learning_rate": 1.4687186133903668e-05, + "loss": 1.732, + "step": 13527 + }, + { + "epoch": 0.7540270887910373, + "grad_norm": 0.5584318041801453, + "learning_rate": 1.4680882884032332e-05, + "loss": 1.4731, + "step": 13528 + }, + { + "epoch": 0.7540828270442005, + "grad_norm": 0.5617906451225281, + "learning_rate": 1.4674580754277483e-05, + "loss": 1.6842, + "step": 13529 + }, + { + "epoch": 0.7541385652973636, + "grad_norm": 0.5737243890762329, + "learning_rate": 1.4668279744838958e-05, + "loss": 1.6571, + "step": 13530 + }, + { + "epoch": 0.7541943035505267, + "grad_norm": 0.5647205710411072, + "learning_rate": 1.4661979855916602e-05, + "loss": 1.5902, + "step": 13531 + }, + { + "epoch": 0.7542500418036898, + "grad_norm": 0.5912965536117554, + "learning_rate": 1.4655681087710205e-05, + "loss": 1.799, + "step": 13532 + }, + { + "epoch": 0.754305780056853, + "grad_norm": 0.5538866519927979, + "learning_rate": 1.4649383440419534e-05, + "loss": 1.477, + "step": 13533 + }, + { + "epoch": 0.7543615183100162, + "grad_norm": 0.5638540983200073, + "learning_rate": 1.4643086914244314e-05, + "loss": 1.6655, + "step": 13534 + }, + { + "epoch": 0.7544172565631793, + "grad_norm": 0.5820828676223755, + "learning_rate": 1.463679150938423e-05, + "loss": 1.7415, + "step": 13535 + }, + { + "epoch": 0.7544729948163424, + "grad_norm": 0.5478092432022095, + "learning_rate": 1.4630497226038953e-05, + "loss": 1.5266, + "step": 13536 + }, + { + "epoch": 0.7545287330695056, + "grad_norm": 0.555873453617096, + "learning_rate": 1.462420406440807e-05, + "loss": 1.5921, + "step": 13537 + }, + { + "epoch": 0.7545844713226687, + "grad_norm": 0.5451073050498962, + "learning_rate": 1.4617912024691177e-05, + "loss": 1.5367, + "step": 13538 + }, + { + "epoch": 0.7546402095758319, + "grad_norm": 0.838469386100769, + "learning_rate": 1.4611621107087826e-05, + "loss": 1.3466, + "step": 13539 + }, + { + "epoch": 0.7546959478289951, + "grad_norm": 0.5384388566017151, + "learning_rate": 1.4605331311797526e-05, + "loss": 1.5763, + "step": 13540 + }, + { + "epoch": 0.7547516860821581, + "grad_norm": 0.6133666634559631, + "learning_rate": 1.4599042639019767e-05, + "loss": 2.1011, + "step": 13541 + }, + { + "epoch": 0.7548074243353213, + "grad_norm": 0.5743862390518188, + "learning_rate": 1.4592755088953935e-05, + "loss": 1.7852, + "step": 13542 + }, + { + "epoch": 0.7548631625884845, + "grad_norm": 0.5554697513580322, + "learning_rate": 1.4586468661799512e-05, + "loss": 1.7704, + "step": 13543 + }, + { + "epoch": 0.7549189008416476, + "grad_norm": 0.5402542948722839, + "learning_rate": 1.458018335775581e-05, + "loss": 1.6328, + "step": 13544 + }, + { + "epoch": 0.7549746390948108, + "grad_norm": 0.5552062392234802, + "learning_rate": 1.4573899177022176e-05, + "loss": 1.4073, + "step": 13545 + }, + { + "epoch": 0.755030377347974, + "grad_norm": 0.5201606154441833, + "learning_rate": 1.4567616119797916e-05, + "loss": 1.4983, + "step": 13546 + }, + { + "epoch": 0.755086115601137, + "grad_norm": 0.6160169243812561, + "learning_rate": 1.4561334186282288e-05, + "loss": 1.7044, + "step": 13547 + }, + { + "epoch": 0.7551418538543002, + "grad_norm": 0.572885274887085, + "learning_rate": 1.4555053376674532e-05, + "loss": 1.5564, + "step": 13548 + }, + { + "epoch": 0.7551975921074634, + "grad_norm": 0.5509326457977295, + "learning_rate": 1.4548773691173794e-05, + "loss": 1.5752, + "step": 13549 + }, + { + "epoch": 0.7552533303606265, + "grad_norm": 0.5369094610214233, + "learning_rate": 1.4542495129979294e-05, + "loss": 1.5379, + "step": 13550 + }, + { + "epoch": 0.7553090686137897, + "grad_norm": 0.5564013719558716, + "learning_rate": 1.4536217693290094e-05, + "loss": 1.6103, + "step": 13551 + }, + { + "epoch": 0.7553648068669528, + "grad_norm": 0.5279716849327087, + "learning_rate": 1.4529941381305307e-05, + "loss": 1.2465, + "step": 13552 + }, + { + "epoch": 0.7554205451201159, + "grad_norm": 0.6001760363578796, + "learning_rate": 1.4523666194223972e-05, + "loss": 1.8333, + "step": 13553 + }, + { + "epoch": 0.7554762833732791, + "grad_norm": 0.5822129845619202, + "learning_rate": 1.4517392132245105e-05, + "loss": 1.6442, + "step": 13554 + }, + { + "epoch": 0.7555320216264422, + "grad_norm": 0.5734686851501465, + "learning_rate": 1.4511119195567696e-05, + "loss": 1.5921, + "step": 13555 + }, + { + "epoch": 0.7555877598796054, + "grad_norm": 0.6088379621505737, + "learning_rate": 1.4504847384390657e-05, + "loss": 1.833, + "step": 13556 + }, + { + "epoch": 0.7556434981327685, + "grad_norm": 0.5933637619018555, + "learning_rate": 1.4498576698912902e-05, + "loss": 1.8395, + "step": 13557 + }, + { + "epoch": 0.7556992363859316, + "grad_norm": 0.5619442462921143, + "learning_rate": 1.4492307139333316e-05, + "loss": 1.4357, + "step": 13558 + }, + { + "epoch": 0.7557549746390948, + "grad_norm": 0.5386919379234314, + "learning_rate": 1.448603870585072e-05, + "loss": 1.511, + "step": 13559 + }, + { + "epoch": 0.755810712892258, + "grad_norm": 0.5765253305435181, + "learning_rate": 1.447977139866391e-05, + "loss": 1.5333, + "step": 13560 + }, + { + "epoch": 0.7558664511454211, + "grad_norm": 0.5310157537460327, + "learning_rate": 1.447350521797166e-05, + "loss": 1.3624, + "step": 13561 + }, + { + "epoch": 0.7559221893985842, + "grad_norm": 0.5235006809234619, + "learning_rate": 1.4467240163972706e-05, + "loss": 1.3457, + "step": 13562 + }, + { + "epoch": 0.7559779276517474, + "grad_norm": 0.5245125889778137, + "learning_rate": 1.4460976236865703e-05, + "loss": 1.1391, + "step": 13563 + }, + { + "epoch": 0.7560336659049105, + "grad_norm": 0.5855050683021545, + "learning_rate": 1.4454713436849333e-05, + "loss": 1.7568, + "step": 13564 + }, + { + "epoch": 0.7560894041580737, + "grad_norm": 0.5477002263069153, + "learning_rate": 1.4448451764122206e-05, + "loss": 1.6173, + "step": 13565 + }, + { + "epoch": 0.7561451424112369, + "grad_norm": 0.5755841135978699, + "learning_rate": 1.4442191218882911e-05, + "loss": 1.7494, + "step": 13566 + }, + { + "epoch": 0.7562008806643999, + "grad_norm": 0.5701185464859009, + "learning_rate": 1.4435931801329994e-05, + "loss": 1.6753, + "step": 13567 + }, + { + "epoch": 0.7562566189175631, + "grad_norm": 0.6093330383300781, + "learning_rate": 1.4429673511661962e-05, + "loss": 1.7557, + "step": 13568 + }, + { + "epoch": 0.7563123571707263, + "grad_norm": 0.5922994017601013, + "learning_rate": 1.4423416350077318e-05, + "loss": 1.6739, + "step": 13569 + }, + { + "epoch": 0.7563680954238894, + "grad_norm": 0.5818817615509033, + "learning_rate": 1.4417160316774465e-05, + "loss": 1.824, + "step": 13570 + }, + { + "epoch": 0.7564238336770526, + "grad_norm": 0.5563713908195496, + "learning_rate": 1.4410905411951824e-05, + "loss": 1.5959, + "step": 13571 + }, + { + "epoch": 0.7564795719302158, + "grad_norm": 0.5510568022727966, + "learning_rate": 1.4404651635807764e-05, + "loss": 1.6415, + "step": 13572 + }, + { + "epoch": 0.7565353101833788, + "grad_norm": 0.5633411407470703, + "learning_rate": 1.4398398988540623e-05, + "loss": 1.3973, + "step": 13573 + }, + { + "epoch": 0.756591048436542, + "grad_norm": 0.5479226112365723, + "learning_rate": 1.4392147470348704e-05, + "loss": 1.5665, + "step": 13574 + }, + { + "epoch": 0.7566467866897052, + "grad_norm": 0.5947529673576355, + "learning_rate": 1.4385897081430233e-05, + "loss": 1.4084, + "step": 13575 + }, + { + "epoch": 0.7567025249428683, + "grad_norm": 0.5711276531219482, + "learning_rate": 1.4379647821983488e-05, + "loss": 1.6453, + "step": 13576 + }, + { + "epoch": 0.7567582631960315, + "grad_norm": 0.5438666939735413, + "learning_rate": 1.4373399692206618e-05, + "loss": 1.7396, + "step": 13577 + }, + { + "epoch": 0.7568140014491945, + "grad_norm": 0.5963262319564819, + "learning_rate": 1.4367152692297797e-05, + "loss": 1.8246, + "step": 13578 + }, + { + "epoch": 0.7568697397023577, + "grad_norm": 0.5485786199569702, + "learning_rate": 1.4360906822455134e-05, + "loss": 1.5035, + "step": 13579 + }, + { + "epoch": 0.7569254779555209, + "grad_norm": 0.5633838176727295, + "learning_rate": 1.4354662082876718e-05, + "loss": 1.6054, + "step": 13580 + }, + { + "epoch": 0.756981216208684, + "grad_norm": 0.5588928461074829, + "learning_rate": 1.434841847376061e-05, + "loss": 1.5249, + "step": 13581 + }, + { + "epoch": 0.7570369544618472, + "grad_norm": 0.5531945824623108, + "learning_rate": 1.434217599530479e-05, + "loss": 1.6811, + "step": 13582 + }, + { + "epoch": 0.7570926927150103, + "grad_norm": 0.5261382460594177, + "learning_rate": 1.4335934647707244e-05, + "loss": 1.5311, + "step": 13583 + }, + { + "epoch": 0.7571484309681734, + "grad_norm": 0.5691108703613281, + "learning_rate": 1.432969443116592e-05, + "loss": 1.2596, + "step": 13584 + }, + { + "epoch": 0.7572041692213366, + "grad_norm": 0.5955578088760376, + "learning_rate": 1.4323455345878717e-05, + "loss": 1.737, + "step": 13585 + }, + { + "epoch": 0.7572599074744998, + "grad_norm": 0.5733932852745056, + "learning_rate": 1.4317217392043496e-05, + "loss": 1.6467, + "step": 13586 + }, + { + "epoch": 0.7573156457276629, + "grad_norm": 0.5477440357208252, + "learning_rate": 1.4310980569858096e-05, + "loss": 1.6087, + "step": 13587 + }, + { + "epoch": 0.757371383980826, + "grad_norm": 0.5244430303573608, + "learning_rate": 1.4304744879520333e-05, + "loss": 1.495, + "step": 13588 + }, + { + "epoch": 0.7574271222339892, + "grad_norm": 0.5610432028770447, + "learning_rate": 1.429851032122792e-05, + "loss": 1.5276, + "step": 13589 + }, + { + "epoch": 0.7574828604871523, + "grad_norm": 0.5067460536956787, + "learning_rate": 1.4292276895178608e-05, + "loss": 1.3332, + "step": 13590 + }, + { + "epoch": 0.7575385987403155, + "grad_norm": 0.5795394778251648, + "learning_rate": 1.4286044601570086e-05, + "loss": 1.6538, + "step": 13591 + }, + { + "epoch": 0.7575943369934787, + "grad_norm": 0.5770653486251831, + "learning_rate": 1.4279813440599999e-05, + "loss": 1.6558, + "step": 13592 + }, + { + "epoch": 0.7576500752466417, + "grad_norm": 0.6013298630714417, + "learning_rate": 1.4273583412465968e-05, + "loss": 1.9873, + "step": 13593 + }, + { + "epoch": 0.7577058134998049, + "grad_norm": 0.554816484451294, + "learning_rate": 1.4267354517365572e-05, + "loss": 1.5415, + "step": 13594 + }, + { + "epoch": 0.7577615517529681, + "grad_norm": 0.5791512727737427, + "learning_rate": 1.4261126755496368e-05, + "loss": 1.7035, + "step": 13595 + }, + { + "epoch": 0.7578172900061312, + "grad_norm": 0.5591641068458557, + "learning_rate": 1.4254900127055843e-05, + "loss": 1.5896, + "step": 13596 + }, + { + "epoch": 0.7578730282592944, + "grad_norm": 0.5369632840156555, + "learning_rate": 1.424867463224147e-05, + "loss": 1.5107, + "step": 13597 + }, + { + "epoch": 0.7579287665124576, + "grad_norm": 0.6140280365943909, + "learning_rate": 1.4242450271250696e-05, + "loss": 1.7632, + "step": 13598 + }, + { + "epoch": 0.7579845047656206, + "grad_norm": 0.5376614332199097, + "learning_rate": 1.4236227044280914e-05, + "loss": 1.4528, + "step": 13599 + }, + { + "epoch": 0.7580402430187838, + "grad_norm": 0.5407631397247314, + "learning_rate": 1.4230004951529513e-05, + "loss": 1.5148, + "step": 13600 + }, + { + "epoch": 0.7580959812719469, + "grad_norm": 0.5585989952087402, + "learning_rate": 1.4223783993193767e-05, + "loss": 1.6172, + "step": 13601 + }, + { + "epoch": 0.7581517195251101, + "grad_norm": 0.6118331551551819, + "learning_rate": 1.4217564169471038e-05, + "loss": 1.9368, + "step": 13602 + }, + { + "epoch": 0.7582074577782733, + "grad_norm": 0.555669903755188, + "learning_rate": 1.421134548055853e-05, + "loss": 1.6861, + "step": 13603 + }, + { + "epoch": 0.7582631960314363, + "grad_norm": 0.5365854501724243, + "learning_rate": 1.4205127926653483e-05, + "loss": 1.5603, + "step": 13604 + }, + { + "epoch": 0.7583189342845995, + "grad_norm": 0.603866457939148, + "learning_rate": 1.4198911507953077e-05, + "loss": 1.7819, + "step": 13605 + }, + { + "epoch": 0.7583746725377627, + "grad_norm": 0.5609720945358276, + "learning_rate": 1.4192696224654467e-05, + "loss": 1.7878, + "step": 13606 + }, + { + "epoch": 0.7584304107909258, + "grad_norm": 0.5774200558662415, + "learning_rate": 1.418648207695477e-05, + "loss": 1.7785, + "step": 13607 + }, + { + "epoch": 0.758486149044089, + "grad_norm": 0.5633645057678223, + "learning_rate": 1.4180269065051043e-05, + "loss": 1.6062, + "step": 13608 + }, + { + "epoch": 0.7585418872972521, + "grad_norm": 0.595280647277832, + "learning_rate": 1.4174057189140339e-05, + "loss": 1.663, + "step": 13609 + }, + { + "epoch": 0.7585976255504152, + "grad_norm": 0.5903527736663818, + "learning_rate": 1.4167846449419659e-05, + "loss": 1.5436, + "step": 13610 + }, + { + "epoch": 0.7586533638035784, + "grad_norm": 0.5782942771911621, + "learning_rate": 1.4161636846085973e-05, + "loss": 2.0576, + "step": 13611 + }, + { + "epoch": 0.7587091020567416, + "grad_norm": 0.5964334607124329, + "learning_rate": 1.4155428379336216e-05, + "loss": 1.5829, + "step": 13612 + }, + { + "epoch": 0.7587648403099047, + "grad_norm": 0.5553979277610779, + "learning_rate": 1.4149221049367283e-05, + "loss": 1.7045, + "step": 13613 + }, + { + "epoch": 0.7588205785630678, + "grad_norm": 0.5777998566627502, + "learning_rate": 1.4143014856376053e-05, + "loss": 1.7569, + "step": 13614 + }, + { + "epoch": 0.758876316816231, + "grad_norm": 0.5861302018165588, + "learning_rate": 1.4136809800559308e-05, + "loss": 1.592, + "step": 13615 + }, + { + "epoch": 0.7589320550693941, + "grad_norm": 0.61280357837677, + "learning_rate": 1.4130605882113862e-05, + "loss": 1.7016, + "step": 13616 + }, + { + "epoch": 0.7589877933225573, + "grad_norm": 0.5595108270645142, + "learning_rate": 1.4124403101236466e-05, + "loss": 1.8053, + "step": 13617 + }, + { + "epoch": 0.7590435315757205, + "grad_norm": 0.5404929518699646, + "learning_rate": 1.411820145812383e-05, + "loss": 1.3909, + "step": 13618 + }, + { + "epoch": 0.7590992698288835, + "grad_norm": 0.5916149616241455, + "learning_rate": 1.4112000952972643e-05, + "loss": 1.6921, + "step": 13619 + }, + { + "epoch": 0.7591550080820467, + "grad_norm": 0.6086878776550293, + "learning_rate": 1.4105801585979545e-05, + "loss": 1.7093, + "step": 13620 + }, + { + "epoch": 0.7592107463352099, + "grad_norm": 0.5869114995002747, + "learning_rate": 1.4099603357341152e-05, + "loss": 1.7623, + "step": 13621 + }, + { + "epoch": 0.759266484588373, + "grad_norm": 0.5688807964324951, + "learning_rate": 1.4093406267254017e-05, + "loss": 1.5728, + "step": 13622 + }, + { + "epoch": 0.7593222228415362, + "grad_norm": 0.5534716844558716, + "learning_rate": 1.4087210315914684e-05, + "loss": 1.653, + "step": 13623 + }, + { + "epoch": 0.7593779610946992, + "grad_norm": 0.5276861190795898, + "learning_rate": 1.4081015503519651e-05, + "loss": 1.6385, + "step": 13624 + }, + { + "epoch": 0.7594336993478624, + "grad_norm": 0.5419962406158447, + "learning_rate": 1.4074821830265388e-05, + "loss": 1.5487, + "step": 13625 + }, + { + "epoch": 0.7594894376010256, + "grad_norm": 0.5207490921020508, + "learning_rate": 1.406862929634833e-05, + "loss": 1.4538, + "step": 13626 + }, + { + "epoch": 0.7595451758541887, + "grad_norm": 0.7052216529846191, + "learning_rate": 1.4062437901964825e-05, + "loss": 1.5614, + "step": 13627 + }, + { + "epoch": 0.7596009141073519, + "grad_norm": 0.5324676036834717, + "learning_rate": 1.4056247647311294e-05, + "loss": 1.382, + "step": 13628 + }, + { + "epoch": 0.759656652360515, + "grad_norm": 0.5526208281517029, + "learning_rate": 1.4050058532584003e-05, + "loss": 1.5966, + "step": 13629 + }, + { + "epoch": 0.7597123906136781, + "grad_norm": 0.5500971674919128, + "learning_rate": 1.4043870557979255e-05, + "loss": 1.5784, + "step": 13630 + }, + { + "epoch": 0.7597681288668413, + "grad_norm": 0.5780391693115234, + "learning_rate": 1.4037683723693296e-05, + "loss": 1.409, + "step": 13631 + }, + { + "epoch": 0.7598238671200045, + "grad_norm": 0.577774703502655, + "learning_rate": 1.403149802992233e-05, + "loss": 1.5705, + "step": 13632 + }, + { + "epoch": 0.7598796053731676, + "grad_norm": 0.5978648066520691, + "learning_rate": 1.4025313476862551e-05, + "loss": 1.8538, + "step": 13633 + }, + { + "epoch": 0.7599353436263308, + "grad_norm": 0.5553382039070129, + "learning_rate": 1.4019130064710068e-05, + "loss": 1.3479, + "step": 13634 + }, + { + "epoch": 0.7599910818794939, + "grad_norm": 0.5762467384338379, + "learning_rate": 1.4012947793660996e-05, + "loss": 1.6895, + "step": 13635 + }, + { + "epoch": 0.760046820132657, + "grad_norm": 0.602973461151123, + "learning_rate": 1.4006766663911397e-05, + "loss": 1.5507, + "step": 13636 + }, + { + "epoch": 0.7601025583858202, + "grad_norm": 0.5446701049804688, + "learning_rate": 1.4000586675657312e-05, + "loss": 1.4995, + "step": 13637 + }, + { + "epoch": 0.7601582966389834, + "grad_norm": 0.5432769656181335, + "learning_rate": 1.399440782909472e-05, + "loss": 1.6442, + "step": 13638 + }, + { + "epoch": 0.7602140348921465, + "grad_norm": 0.5659343004226685, + "learning_rate": 1.3988230124419589e-05, + "loss": 1.6857, + "step": 13639 + }, + { + "epoch": 0.7602697731453096, + "grad_norm": 0.5553669333457947, + "learning_rate": 1.3982053561827846e-05, + "loss": 1.6515, + "step": 13640 + }, + { + "epoch": 0.7603255113984728, + "grad_norm": 0.6063775420188904, + "learning_rate": 1.3975878141515352e-05, + "loss": 1.7898, + "step": 13641 + }, + { + "epoch": 0.7603812496516359, + "grad_norm": 0.5545953512191772, + "learning_rate": 1.3969703863677969e-05, + "loss": 1.5781, + "step": 13642 + }, + { + "epoch": 0.7604369879047991, + "grad_norm": 0.6215736269950867, + "learning_rate": 1.396353072851151e-05, + "loss": 1.7786, + "step": 13643 + }, + { + "epoch": 0.7604927261579623, + "grad_norm": 0.5639563798904419, + "learning_rate": 1.3957358736211745e-05, + "loss": 1.6052, + "step": 13644 + }, + { + "epoch": 0.7605484644111253, + "grad_norm": 0.5856985449790955, + "learning_rate": 1.3951187886974416e-05, + "loss": 1.7038, + "step": 13645 + }, + { + "epoch": 0.7606042026642885, + "grad_norm": 0.5552805662155151, + "learning_rate": 1.3945018180995234e-05, + "loss": 1.6561, + "step": 13646 + }, + { + "epoch": 0.7606599409174516, + "grad_norm": 0.5644158720970154, + "learning_rate": 1.3938849618469868e-05, + "loss": 1.6025, + "step": 13647 + }, + { + "epoch": 0.7607156791706148, + "grad_norm": 0.5574057698249817, + "learning_rate": 1.3932682199593933e-05, + "loss": 1.7453, + "step": 13648 + }, + { + "epoch": 0.760771417423778, + "grad_norm": 0.5566650629043579, + "learning_rate": 1.3926515924563027e-05, + "loss": 1.6144, + "step": 13649 + }, + { + "epoch": 0.760827155676941, + "grad_norm": 0.5857501029968262, + "learning_rate": 1.3920350793572717e-05, + "loss": 1.6279, + "step": 13650 + }, + { + "epoch": 0.7608828939301042, + "grad_norm": 0.5910730361938477, + "learning_rate": 1.391418680681852e-05, + "loss": 1.6013, + "step": 13651 + }, + { + "epoch": 0.7609386321832674, + "grad_norm": 0.6606738567352295, + "learning_rate": 1.3908023964495937e-05, + "loss": 1.7508, + "step": 13652 + }, + { + "epoch": 0.7609943704364305, + "grad_norm": 0.5536946058273315, + "learning_rate": 1.390186226680037e-05, + "loss": 1.7573, + "step": 13653 + }, + { + "epoch": 0.7610501086895937, + "grad_norm": 0.5876284837722778, + "learning_rate": 1.38957017139273e-05, + "loss": 1.8013, + "step": 13654 + }, + { + "epoch": 0.7611058469427568, + "grad_norm": 0.5489315390586853, + "learning_rate": 1.3889542306072052e-05, + "loss": 1.5425, + "step": 13655 + }, + { + "epoch": 0.7611615851959199, + "grad_norm": 0.6121096014976501, + "learning_rate": 1.388338404342998e-05, + "loss": 1.694, + "step": 13656 + }, + { + "epoch": 0.7612173234490831, + "grad_norm": 0.5223791599273682, + "learning_rate": 1.3877226926196397e-05, + "loss": 1.6321, + "step": 13657 + }, + { + "epoch": 0.7612730617022463, + "grad_norm": 0.5644776225090027, + "learning_rate": 1.3871070954566561e-05, + "loss": 1.7296, + "step": 13658 + }, + { + "epoch": 0.7613287999554094, + "grad_norm": 0.5516535639762878, + "learning_rate": 1.3864916128735727e-05, + "loss": 1.5889, + "step": 13659 + }, + { + "epoch": 0.7613845382085725, + "grad_norm": 0.5555848479270935, + "learning_rate": 1.3858762448899037e-05, + "loss": 1.6957, + "step": 13660 + }, + { + "epoch": 0.7614402764617357, + "grad_norm": 0.559370756149292, + "learning_rate": 1.3852609915251719e-05, + "loss": 1.504, + "step": 13661 + }, + { + "epoch": 0.7614960147148988, + "grad_norm": 0.5376693606376648, + "learning_rate": 1.3846458527988842e-05, + "loss": 1.5899, + "step": 13662 + }, + { + "epoch": 0.761551752968062, + "grad_norm": 0.5808365345001221, + "learning_rate": 1.3840308287305509e-05, + "loss": 1.8645, + "step": 13663 + }, + { + "epoch": 0.7616074912212252, + "grad_norm": 0.5773041844367981, + "learning_rate": 1.3834159193396778e-05, + "loss": 1.7324, + "step": 13664 + }, + { + "epoch": 0.7616632294743882, + "grad_norm": 0.6116316914558411, + "learning_rate": 1.382801124645765e-05, + "loss": 1.8378, + "step": 13665 + }, + { + "epoch": 0.7617189677275514, + "grad_norm": 0.5963553786277771, + "learning_rate": 1.3821864446683125e-05, + "loss": 1.7662, + "step": 13666 + }, + { + "epoch": 0.7617747059807146, + "grad_norm": 0.5584465265274048, + "learning_rate": 1.3815718794268112e-05, + "loss": 1.5952, + "step": 13667 + }, + { + "epoch": 0.7618304442338777, + "grad_norm": 0.5512256622314453, + "learning_rate": 1.3809574289407529e-05, + "loss": 1.5949, + "step": 13668 + }, + { + "epoch": 0.7618861824870409, + "grad_norm": 0.5420078635215759, + "learning_rate": 1.3803430932296247e-05, + "loss": 1.7301, + "step": 13669 + }, + { + "epoch": 0.761941920740204, + "grad_norm": 0.5526279211044312, + "learning_rate": 1.3797288723129093e-05, + "loss": 1.6325, + "step": 13670 + }, + { + "epoch": 0.7619976589933671, + "grad_norm": 0.5725477337837219, + "learning_rate": 1.3791147662100867e-05, + "loss": 1.7894, + "step": 13671 + }, + { + "epoch": 0.7620533972465303, + "grad_norm": 0.5640320181846619, + "learning_rate": 1.378500774940632e-05, + "loss": 1.6614, + "step": 13672 + }, + { + "epoch": 0.7621091354996934, + "grad_norm": 0.5445780754089355, + "learning_rate": 1.3778868985240195e-05, + "loss": 1.2925, + "step": 13673 + }, + { + "epoch": 0.7621648737528566, + "grad_norm": 0.5337774753570557, + "learning_rate": 1.3772731369797154e-05, + "loss": 1.4987, + "step": 13674 + }, + { + "epoch": 0.7622206120060198, + "grad_norm": 0.5738458633422852, + "learning_rate": 1.3766594903271845e-05, + "loss": 1.6826, + "step": 13675 + }, + { + "epoch": 0.7622763502591828, + "grad_norm": 0.563511312007904, + "learning_rate": 1.3760459585858897e-05, + "loss": 1.7222, + "step": 13676 + }, + { + "epoch": 0.762332088512346, + "grad_norm": 0.5649859309196472, + "learning_rate": 1.3754325417752878e-05, + "loss": 1.6004, + "step": 13677 + }, + { + "epoch": 0.7623878267655092, + "grad_norm": 0.5031634569168091, + "learning_rate": 1.374819239914834e-05, + "loss": 1.3402, + "step": 13678 + }, + { + "epoch": 0.7624435650186723, + "grad_norm": 0.6033832430839539, + "learning_rate": 1.3742060530239753e-05, + "loss": 1.7393, + "step": 13679 + }, + { + "epoch": 0.7624993032718355, + "grad_norm": 0.5838034152984619, + "learning_rate": 1.3735929811221637e-05, + "loss": 1.7233, + "step": 13680 + }, + { + "epoch": 0.7625550415249986, + "grad_norm": 0.5297046303749084, + "learning_rate": 1.372980024228837e-05, + "loss": 1.3896, + "step": 13681 + }, + { + "epoch": 0.7626107797781617, + "grad_norm": 0.6580976843833923, + "learning_rate": 1.3723671823634376e-05, + "loss": 1.8186, + "step": 13682 + }, + { + "epoch": 0.7626665180313249, + "grad_norm": 0.7035778164863586, + "learning_rate": 1.3717544555454009e-05, + "loss": 1.721, + "step": 13683 + }, + { + "epoch": 0.7627222562844881, + "grad_norm": 0.5296900272369385, + "learning_rate": 1.3711418437941582e-05, + "loss": 1.462, + "step": 13684 + }, + { + "epoch": 0.7627779945376512, + "grad_norm": 0.5588696002960205, + "learning_rate": 1.3705293471291403e-05, + "loss": 1.5209, + "step": 13685 + }, + { + "epoch": 0.7628337327908143, + "grad_norm": 0.5136246085166931, + "learning_rate": 1.3699169655697669e-05, + "loss": 1.5621, + "step": 13686 + }, + { + "epoch": 0.7628894710439775, + "grad_norm": 0.560178279876709, + "learning_rate": 1.3693046991354658e-05, + "loss": 1.7407, + "step": 13687 + }, + { + "epoch": 0.7629452092971406, + "grad_norm": 0.5490294694900513, + "learning_rate": 1.3686925478456497e-05, + "loss": 1.6656, + "step": 13688 + }, + { + "epoch": 0.7630009475503038, + "grad_norm": 0.5643256902694702, + "learning_rate": 1.3680805117197344e-05, + "loss": 1.4874, + "step": 13689 + }, + { + "epoch": 0.763056685803467, + "grad_norm": 0.5297697186470032, + "learning_rate": 1.367468590777129e-05, + "loss": 1.6193, + "step": 13690 + }, + { + "epoch": 0.76311242405663, + "grad_norm": 0.5320075750350952, + "learning_rate": 1.366856785037241e-05, + "loss": 1.5072, + "step": 13691 + }, + { + "epoch": 0.7631681623097932, + "grad_norm": 0.5761438012123108, + "learning_rate": 1.3662450945194743e-05, + "loss": 1.5143, + "step": 13692 + }, + { + "epoch": 0.7632239005629563, + "grad_norm": 0.5583884119987488, + "learning_rate": 1.3656335192432258e-05, + "loss": 1.6937, + "step": 13693 + }, + { + "epoch": 0.7632796388161195, + "grad_norm": 0.5506449937820435, + "learning_rate": 1.3650220592278923e-05, + "loss": 1.6081, + "step": 13694 + }, + { + "epoch": 0.7633353770692827, + "grad_norm": 0.5765452980995178, + "learning_rate": 1.3644107144928658e-05, + "loss": 1.5314, + "step": 13695 + }, + { + "epoch": 0.7633911153224457, + "grad_norm": 0.6005212068557739, + "learning_rate": 1.3637994850575341e-05, + "loss": 1.6142, + "step": 13696 + }, + { + "epoch": 0.7634468535756089, + "grad_norm": 0.5738573670387268, + "learning_rate": 1.3631883709412823e-05, + "loss": 1.683, + "step": 13697 + }, + { + "epoch": 0.7635025918287721, + "grad_norm": 0.5588680505752563, + "learning_rate": 1.3625773721634915e-05, + "loss": 1.6197, + "step": 13698 + }, + { + "epoch": 0.7635583300819352, + "grad_norm": 0.5157375931739807, + "learning_rate": 1.3619664887435402e-05, + "loss": 1.6233, + "step": 13699 + }, + { + "epoch": 0.7636140683350984, + "grad_norm": 0.5695037245750427, + "learning_rate": 1.3613557207007988e-05, + "loss": 1.5264, + "step": 13700 + }, + { + "epoch": 0.7636698065882616, + "grad_norm": 0.5643973350524902, + "learning_rate": 1.3607450680546397e-05, + "loss": 1.5529, + "step": 13701 + }, + { + "epoch": 0.7637255448414246, + "grad_norm": 0.5982683897018433, + "learning_rate": 1.3601345308244284e-05, + "loss": 1.8334, + "step": 13702 + }, + { + "epoch": 0.7637812830945878, + "grad_norm": 0.5559334754943848, + "learning_rate": 1.359524109029528e-05, + "loss": 1.3872, + "step": 13703 + }, + { + "epoch": 0.763837021347751, + "grad_norm": 0.591163694858551, + "learning_rate": 1.3589138026892988e-05, + "loss": 1.7196, + "step": 13704 + }, + { + "epoch": 0.7638927596009141, + "grad_norm": 0.5622092485427856, + "learning_rate": 1.3583036118230924e-05, + "loss": 1.7068, + "step": 13705 + }, + { + "epoch": 0.7639484978540773, + "grad_norm": 0.5617137551307678, + "learning_rate": 1.3576935364502653e-05, + "loss": 1.6201, + "step": 13706 + }, + { + "epoch": 0.7640042361072404, + "grad_norm": 0.6120706796646118, + "learning_rate": 1.3570835765901612e-05, + "loss": 1.697, + "step": 13707 + }, + { + "epoch": 0.7640599743604035, + "grad_norm": 0.562481164932251, + "learning_rate": 1.3564737322621274e-05, + "loss": 1.6438, + "step": 13708 + }, + { + "epoch": 0.7641157126135667, + "grad_norm": 0.5552496314048767, + "learning_rate": 1.355864003485503e-05, + "loss": 1.7532, + "step": 13709 + }, + { + "epoch": 0.7641714508667299, + "grad_norm": 0.5245192646980286, + "learning_rate": 1.3552543902796256e-05, + "loss": 1.3265, + "step": 13710 + }, + { + "epoch": 0.764227189119893, + "grad_norm": 0.5369590520858765, + "learning_rate": 1.35464489266383e-05, + "loss": 1.509, + "step": 13711 + }, + { + "epoch": 0.7642829273730561, + "grad_norm": 0.5913751721382141, + "learning_rate": 1.3540355106574416e-05, + "loss": 1.663, + "step": 13712 + }, + { + "epoch": 0.7643386656262193, + "grad_norm": 0.5683638453483582, + "learning_rate": 1.3534262442797923e-05, + "loss": 1.6732, + "step": 13713 + }, + { + "epoch": 0.7643944038793824, + "grad_norm": 0.5665015578269958, + "learning_rate": 1.3528170935502005e-05, + "loss": 1.5886, + "step": 13714 + }, + { + "epoch": 0.7644501421325456, + "grad_norm": 0.528668224811554, + "learning_rate": 1.3522080584879854e-05, + "loss": 1.5023, + "step": 13715 + }, + { + "epoch": 0.7645058803857087, + "grad_norm": 0.5553814172744751, + "learning_rate": 1.3515991391124627e-05, + "loss": 1.5308, + "step": 13716 + }, + { + "epoch": 0.7645616186388718, + "grad_norm": 0.6319010257720947, + "learning_rate": 1.3509903354429437e-05, + "loss": 1.7049, + "step": 13717 + }, + { + "epoch": 0.764617356892035, + "grad_norm": 0.5890353918075562, + "learning_rate": 1.3503816474987379e-05, + "loss": 1.6599, + "step": 13718 + }, + { + "epoch": 0.7646730951451981, + "grad_norm": 0.5836519598960876, + "learning_rate": 1.3497730752991455e-05, + "loss": 1.8447, + "step": 13719 + }, + { + "epoch": 0.7647288333983613, + "grad_norm": 0.5459491610527039, + "learning_rate": 1.3491646188634689e-05, + "loss": 1.6414, + "step": 13720 + }, + { + "epoch": 0.7647845716515245, + "grad_norm": 0.5694407224655151, + "learning_rate": 1.348556278211005e-05, + "loss": 1.5857, + "step": 13721 + }, + { + "epoch": 0.7648403099046875, + "grad_norm": 0.5732302069664001, + "learning_rate": 1.3479480533610468e-05, + "loss": 1.7178, + "step": 13722 + }, + { + "epoch": 0.7648960481578507, + "grad_norm": 0.6317426562309265, + "learning_rate": 1.3473399443328826e-05, + "loss": 1.864, + "step": 13723 + }, + { + "epoch": 0.7649517864110139, + "grad_norm": 0.5422190427780151, + "learning_rate": 1.3467319511457993e-05, + "loss": 1.6681, + "step": 13724 + }, + { + "epoch": 0.765007524664177, + "grad_norm": 0.5311571955680847, + "learning_rate": 1.34612407381908e-05, + "loss": 1.5217, + "step": 13725 + }, + { + "epoch": 0.7650632629173402, + "grad_norm": 0.5102006196975708, + "learning_rate": 1.3455163123719999e-05, + "loss": 1.3252, + "step": 13726 + }, + { + "epoch": 0.7651190011705034, + "grad_norm": 0.5632702112197876, + "learning_rate": 1.344908666823836e-05, + "loss": 1.5403, + "step": 13727 + }, + { + "epoch": 0.7651747394236664, + "grad_norm": 0.5720388293266296, + "learning_rate": 1.3443011371938574e-05, + "loss": 1.7533, + "step": 13728 + }, + { + "epoch": 0.7652304776768296, + "grad_norm": 0.5603064298629761, + "learning_rate": 1.3436937235013331e-05, + "loss": 1.7345, + "step": 13729 + }, + { + "epoch": 0.7652862159299928, + "grad_norm": 0.5317055583000183, + "learning_rate": 1.3430864257655273e-05, + "loss": 1.5839, + "step": 13730 + }, + { + "epoch": 0.7653419541831559, + "grad_norm": 0.5410267114639282, + "learning_rate": 1.3424792440056966e-05, + "loss": 1.4791, + "step": 13731 + }, + { + "epoch": 0.765397692436319, + "grad_norm": 0.5275070071220398, + "learning_rate": 1.3418721782411015e-05, + "loss": 1.5329, + "step": 13732 + }, + { + "epoch": 0.7654534306894822, + "grad_norm": 0.5779644250869751, + "learning_rate": 1.3412652284909916e-05, + "loss": 1.7906, + "step": 13733 + }, + { + "epoch": 0.7655091689426453, + "grad_norm": 0.6660231947898865, + "learning_rate": 1.3406583947746166e-05, + "loss": 1.952, + "step": 13734 + }, + { + "epoch": 0.7655649071958085, + "grad_norm": 0.5571669936180115, + "learning_rate": 1.340051677111222e-05, + "loss": 1.6007, + "step": 13735 + }, + { + "epoch": 0.7656206454489717, + "grad_norm": 0.5619083046913147, + "learning_rate": 1.3394450755200488e-05, + "loss": 1.6623, + "step": 13736 + }, + { + "epoch": 0.7656763837021348, + "grad_norm": 0.5739771127700806, + "learning_rate": 1.3388385900203371e-05, + "loss": 1.7574, + "step": 13737 + }, + { + "epoch": 0.7657321219552979, + "grad_norm": 0.5774732232093811, + "learning_rate": 1.3382322206313164e-05, + "loss": 1.5834, + "step": 13738 + }, + { + "epoch": 0.765787860208461, + "grad_norm": 0.5748267769813538, + "learning_rate": 1.337625967372223e-05, + "loss": 1.7372, + "step": 13739 + }, + { + "epoch": 0.7658435984616242, + "grad_norm": 0.5925459265708923, + "learning_rate": 1.3370198302622794e-05, + "loss": 1.8107, + "step": 13740 + }, + { + "epoch": 0.7658993367147874, + "grad_norm": 0.5471937656402588, + "learning_rate": 1.3364138093207096e-05, + "loss": 1.4694, + "step": 13741 + }, + { + "epoch": 0.7659550749679505, + "grad_norm": 0.6107663512229919, + "learning_rate": 1.3358079045667338e-05, + "loss": 1.6048, + "step": 13742 + }, + { + "epoch": 0.7660108132211136, + "grad_norm": 0.5694422125816345, + "learning_rate": 1.3352021160195676e-05, + "loss": 1.5999, + "step": 13743 + }, + { + "epoch": 0.7660665514742768, + "grad_norm": 0.5657966732978821, + "learning_rate": 1.3345964436984249e-05, + "loss": 1.5563, + "step": 13744 + }, + { + "epoch": 0.7661222897274399, + "grad_norm": 0.5410760045051575, + "learning_rate": 1.3339908876225105e-05, + "loss": 1.4062, + "step": 13745 + }, + { + "epoch": 0.7661780279806031, + "grad_norm": 0.6214928030967712, + "learning_rate": 1.3333854478110309e-05, + "loss": 1.5772, + "step": 13746 + }, + { + "epoch": 0.7662337662337663, + "grad_norm": 0.6026737689971924, + "learning_rate": 1.3327801242831867e-05, + "loss": 1.7012, + "step": 13747 + }, + { + "epoch": 0.7662895044869293, + "grad_norm": 0.5919846892356873, + "learning_rate": 1.332174917058176e-05, + "loss": 1.5764, + "step": 13748 + }, + { + "epoch": 0.7663452427400925, + "grad_norm": 0.5703722238540649, + "learning_rate": 1.3315698261551917e-05, + "loss": 1.4723, + "step": 13749 + }, + { + "epoch": 0.7664009809932557, + "grad_norm": 0.5685303807258606, + "learning_rate": 1.3309648515934241e-05, + "loss": 1.6053, + "step": 13750 + }, + { + "epoch": 0.7664567192464188, + "grad_norm": 0.5829964876174927, + "learning_rate": 1.3303599933920613e-05, + "loss": 1.5209, + "step": 13751 + }, + { + "epoch": 0.766512457499582, + "grad_norm": 0.5797625184059143, + "learning_rate": 1.3297552515702822e-05, + "loss": 1.8081, + "step": 13752 + }, + { + "epoch": 0.7665681957527452, + "grad_norm": 0.6179783940315247, + "learning_rate": 1.3291506261472675e-05, + "loss": 1.754, + "step": 13753 + }, + { + "epoch": 0.7666239340059082, + "grad_norm": 0.5700926184654236, + "learning_rate": 1.3285461171421925e-05, + "loss": 1.622, + "step": 13754 + }, + { + "epoch": 0.7666796722590714, + "grad_norm": 0.5579239130020142, + "learning_rate": 1.3279417245742286e-05, + "loss": 1.6621, + "step": 13755 + }, + { + "epoch": 0.7667354105122346, + "grad_norm": 0.5812460780143738, + "learning_rate": 1.327337448462545e-05, + "loss": 1.6559, + "step": 13756 + }, + { + "epoch": 0.7667911487653977, + "grad_norm": 0.5232528448104858, + "learning_rate": 1.3267332888263013e-05, + "loss": 1.631, + "step": 13757 + }, + { + "epoch": 0.7668468870185609, + "grad_norm": 0.5652537941932678, + "learning_rate": 1.3261292456846647e-05, + "loss": 1.6011, + "step": 13758 + }, + { + "epoch": 0.766902625271724, + "grad_norm": 0.5638788938522339, + "learning_rate": 1.3255253190567863e-05, + "loss": 1.7915, + "step": 13759 + }, + { + "epoch": 0.7669583635248871, + "grad_norm": 0.5904683470726013, + "learning_rate": 1.3249215089618211e-05, + "loss": 1.6165, + "step": 13760 + }, + { + "epoch": 0.7670141017780503, + "grad_norm": 0.5620837211608887, + "learning_rate": 1.3243178154189184e-05, + "loss": 1.5416, + "step": 13761 + }, + { + "epoch": 0.7670698400312134, + "grad_norm": 0.5649104118347168, + "learning_rate": 1.323714238447224e-05, + "loss": 1.678, + "step": 13762 + }, + { + "epoch": 0.7671255782843766, + "grad_norm": 0.6296602487564087, + "learning_rate": 1.3231107780658814e-05, + "loss": 1.6428, + "step": 13763 + }, + { + "epoch": 0.7671813165375397, + "grad_norm": 0.5722455978393555, + "learning_rate": 1.3225074342940235e-05, + "loss": 1.6772, + "step": 13764 + }, + { + "epoch": 0.7672370547907028, + "grad_norm": 0.5544499158859253, + "learning_rate": 1.321904207150792e-05, + "loss": 1.4968, + "step": 13765 + }, + { + "epoch": 0.767292793043866, + "grad_norm": 0.5880872011184692, + "learning_rate": 1.321301096655313e-05, + "loss": 1.67, + "step": 13766 + }, + { + "epoch": 0.7673485312970292, + "grad_norm": 0.5740914940834045, + "learning_rate": 1.3206981028267145e-05, + "loss": 1.6711, + "step": 13767 + }, + { + "epoch": 0.7674042695501923, + "grad_norm": 0.5627743601799011, + "learning_rate": 1.3200952256841204e-05, + "loss": 1.7168, + "step": 13768 + }, + { + "epoch": 0.7674600078033554, + "grad_norm": 0.5852112174034119, + "learning_rate": 1.3194924652466507e-05, + "loss": 1.5528, + "step": 13769 + }, + { + "epoch": 0.7675157460565186, + "grad_norm": 0.5481190085411072, + "learning_rate": 1.3188898215334228e-05, + "loss": 1.668, + "step": 13770 + }, + { + "epoch": 0.7675714843096817, + "grad_norm": 0.5531885027885437, + "learning_rate": 1.3182872945635455e-05, + "loss": 1.5727, + "step": 13771 + }, + { + "epoch": 0.7676272225628449, + "grad_norm": 0.5442955493927002, + "learning_rate": 1.317684884356129e-05, + "loss": 1.6687, + "step": 13772 + }, + { + "epoch": 0.7676829608160081, + "grad_norm": 0.5647032260894775, + "learning_rate": 1.3170825909302792e-05, + "loss": 1.7627, + "step": 13773 + }, + { + "epoch": 0.7677386990691711, + "grad_norm": 0.5629161596298218, + "learning_rate": 1.3164804143050963e-05, + "loss": 1.4726, + "step": 13774 + }, + { + "epoch": 0.7677944373223343, + "grad_norm": 0.5685316920280457, + "learning_rate": 1.3158783544996789e-05, + "loss": 1.4011, + "step": 13775 + }, + { + "epoch": 0.7678501755754975, + "grad_norm": 0.5748550295829773, + "learning_rate": 1.3152764115331195e-05, + "loss": 1.5873, + "step": 13776 + }, + { + "epoch": 0.7679059138286606, + "grad_norm": 0.5731246471405029, + "learning_rate": 1.3146745854245108e-05, + "loss": 1.5637, + "step": 13777 + }, + { + "epoch": 0.7679616520818238, + "grad_norm": 0.5486955046653748, + "learning_rate": 1.3140728761929356e-05, + "loss": 1.6605, + "step": 13778 + }, + { + "epoch": 0.768017390334987, + "grad_norm": 0.5804146528244019, + "learning_rate": 1.313471283857478e-05, + "loss": 1.7208, + "step": 13779 + }, + { + "epoch": 0.76807312858815, + "grad_norm": 0.5566115379333496, + "learning_rate": 1.3128698084372182e-05, + "loss": 1.8526, + "step": 13780 + }, + { + "epoch": 0.7681288668413132, + "grad_norm": 0.5542247295379639, + "learning_rate": 1.31226844995123e-05, + "loss": 1.4398, + "step": 13781 + }, + { + "epoch": 0.7681846050944764, + "grad_norm": 0.556767463684082, + "learning_rate": 1.3116672084185872e-05, + "loss": 1.6531, + "step": 13782 + }, + { + "epoch": 0.7682403433476395, + "grad_norm": 0.5431240797042847, + "learning_rate": 1.3110660838583533e-05, + "loss": 1.6007, + "step": 13783 + }, + { + "epoch": 0.7682960816008026, + "grad_norm": 0.5814715027809143, + "learning_rate": 1.3104650762895975e-05, + "loss": 1.4798, + "step": 13784 + }, + { + "epoch": 0.7683518198539657, + "grad_norm": 0.5413219332695007, + "learning_rate": 1.3098641857313777e-05, + "loss": 1.5713, + "step": 13785 + }, + { + "epoch": 0.7684075581071289, + "grad_norm": 0.6077486872673035, + "learning_rate": 1.3092634122027497e-05, + "loss": 1.7747, + "step": 13786 + }, + { + "epoch": 0.7684632963602921, + "grad_norm": 0.5583086609840393, + "learning_rate": 1.3086627557227687e-05, + "loss": 1.6071, + "step": 13787 + }, + { + "epoch": 0.7685190346134552, + "grad_norm": 0.5888667702674866, + "learning_rate": 1.3080622163104827e-05, + "loss": 1.823, + "step": 13788 + }, + { + "epoch": 0.7685747728666183, + "grad_norm": 0.5727972984313965, + "learning_rate": 1.3074617939849393e-05, + "loss": 1.5356, + "step": 13789 + }, + { + "epoch": 0.7686305111197815, + "grad_norm": 0.5865001082420349, + "learning_rate": 1.3068614887651759e-05, + "loss": 1.6255, + "step": 13790 + }, + { + "epoch": 0.7686862493729446, + "grad_norm": 0.578157901763916, + "learning_rate": 1.3062613006702361e-05, + "loss": 1.7089, + "step": 13791 + }, + { + "epoch": 0.7687419876261078, + "grad_norm": 0.5981795191764832, + "learning_rate": 1.3056612297191505e-05, + "loss": 1.9307, + "step": 13792 + }, + { + "epoch": 0.768797725879271, + "grad_norm": 0.58543461561203, + "learning_rate": 1.3050612759309515e-05, + "loss": 1.5325, + "step": 13793 + }, + { + "epoch": 0.768853464132434, + "grad_norm": 0.5604169964790344, + "learning_rate": 1.3044614393246662e-05, + "loss": 1.5726, + "step": 13794 + }, + { + "epoch": 0.7689092023855972, + "grad_norm": 0.5601847767829895, + "learning_rate": 1.3038617199193171e-05, + "loss": 1.5083, + "step": 13795 + }, + { + "epoch": 0.7689649406387604, + "grad_norm": 0.552564799785614, + "learning_rate": 1.3032621177339255e-05, + "loss": 1.6135, + "step": 13796 + }, + { + "epoch": 0.7690206788919235, + "grad_norm": 0.5546259880065918, + "learning_rate": 1.3026626327875052e-05, + "loss": 1.5547, + "step": 13797 + }, + { + "epoch": 0.7690764171450867, + "grad_norm": 0.540576696395874, + "learning_rate": 1.3020632650990688e-05, + "loss": 1.5781, + "step": 13798 + }, + { + "epoch": 0.7691321553982499, + "grad_norm": 0.5935271382331848, + "learning_rate": 1.301464014687625e-05, + "loss": 1.7391, + "step": 13799 + }, + { + "epoch": 0.7691878936514129, + "grad_norm": 0.5803846120834351, + "learning_rate": 1.300864881572179e-05, + "loss": 1.6353, + "step": 13800 + }, + { + "epoch": 0.7692436319045761, + "grad_norm": 0.5862022042274475, + "learning_rate": 1.3002658657717314e-05, + "loss": 1.7033, + "step": 13801 + }, + { + "epoch": 0.7692993701577393, + "grad_norm": 0.6239582896232605, + "learning_rate": 1.2996669673052797e-05, + "loss": 1.7809, + "step": 13802 + }, + { + "epoch": 0.7693551084109024, + "grad_norm": 0.5111715793609619, + "learning_rate": 1.2990681861918186e-05, + "loss": 1.3578, + "step": 13803 + }, + { + "epoch": 0.7694108466640656, + "grad_norm": 0.5416402220726013, + "learning_rate": 1.2984695224503351e-05, + "loss": 1.607, + "step": 13804 + }, + { + "epoch": 0.7694665849172287, + "grad_norm": 0.5554835796356201, + "learning_rate": 1.2978709760998176e-05, + "loss": 1.5583, + "step": 13805 + }, + { + "epoch": 0.7695223231703918, + "grad_norm": 0.5633331537246704, + "learning_rate": 1.2972725471592473e-05, + "loss": 1.6499, + "step": 13806 + }, + { + "epoch": 0.769578061423555, + "grad_norm": 0.5715453028678894, + "learning_rate": 1.2966742356476036e-05, + "loss": 1.8379, + "step": 13807 + }, + { + "epoch": 0.7696337996767181, + "grad_norm": 0.5345661044120789, + "learning_rate": 1.2960760415838625e-05, + "loss": 1.4554, + "step": 13808 + }, + { + "epoch": 0.7696895379298813, + "grad_norm": 0.5594824552536011, + "learning_rate": 1.2954779649869914e-05, + "loss": 1.6364, + "step": 13809 + }, + { + "epoch": 0.7697452761830444, + "grad_norm": 0.6407233476638794, + "learning_rate": 1.294880005875963e-05, + "loss": 1.8723, + "step": 13810 + }, + { + "epoch": 0.7698010144362075, + "grad_norm": 0.5817638635635376, + "learning_rate": 1.2942821642697372e-05, + "loss": 1.7793, + "step": 13811 + }, + { + "epoch": 0.7698567526893707, + "grad_norm": 0.5345514416694641, + "learning_rate": 1.293684440187275e-05, + "loss": 1.3296, + "step": 13812 + }, + { + "epoch": 0.7699124909425339, + "grad_norm": 0.6158250570297241, + "learning_rate": 1.2930868336475332e-05, + "loss": 1.8778, + "step": 13813 + }, + { + "epoch": 0.769968229195697, + "grad_norm": 0.6545181274414062, + "learning_rate": 1.2924893446694647e-05, + "loss": 1.8938, + "step": 13814 + }, + { + "epoch": 0.7700239674488601, + "grad_norm": 0.6429218649864197, + "learning_rate": 1.2918919732720186e-05, + "loss": 2.1305, + "step": 13815 + }, + { + "epoch": 0.7700797057020233, + "grad_norm": 0.6089257001876831, + "learning_rate": 1.291294719474137e-05, + "loss": 1.7058, + "step": 13816 + }, + { + "epoch": 0.7701354439551864, + "grad_norm": 0.5691222548484802, + "learning_rate": 1.2906975832947665e-05, + "loss": 1.7782, + "step": 13817 + }, + { + "epoch": 0.7701911822083496, + "grad_norm": 0.5711841583251953, + "learning_rate": 1.2901005647528402e-05, + "loss": 1.4945, + "step": 13818 + }, + { + "epoch": 0.7702469204615128, + "grad_norm": 0.5910068154335022, + "learning_rate": 1.2895036638672937e-05, + "loss": 1.7357, + "step": 13819 + }, + { + "epoch": 0.7703026587146758, + "grad_norm": 0.5314319133758545, + "learning_rate": 1.2889068806570575e-05, + "loss": 1.5099, + "step": 13820 + }, + { + "epoch": 0.770358396967839, + "grad_norm": 0.5431066155433655, + "learning_rate": 1.288310215141058e-05, + "loss": 1.6854, + "step": 13821 + }, + { + "epoch": 0.7704141352210022, + "grad_norm": 0.6121734976768494, + "learning_rate": 1.287713667338219e-05, + "loss": 1.9443, + "step": 13822 + }, + { + "epoch": 0.7704698734741653, + "grad_norm": 0.5128597617149353, + "learning_rate": 1.2871172372674573e-05, + "loss": 1.3639, + "step": 13823 + }, + { + "epoch": 0.7705256117273285, + "grad_norm": 0.5147601962089539, + "learning_rate": 1.286520924947689e-05, + "loss": 1.3894, + "step": 13824 + }, + { + "epoch": 0.7705813499804917, + "grad_norm": 0.5614168047904968, + "learning_rate": 1.2859247303978255e-05, + "loss": 1.6414, + "step": 13825 + }, + { + "epoch": 0.7706370882336547, + "grad_norm": 0.540399968624115, + "learning_rate": 1.2853286536367753e-05, + "loss": 1.5018, + "step": 13826 + }, + { + "epoch": 0.7706928264868179, + "grad_norm": 0.5493924021720886, + "learning_rate": 1.2847326946834426e-05, + "loss": 1.8156, + "step": 13827 + }, + { + "epoch": 0.7707485647399811, + "grad_norm": 0.5494512915611267, + "learning_rate": 1.2841368535567267e-05, + "loss": 1.5758, + "step": 13828 + }, + { + "epoch": 0.7708043029931442, + "grad_norm": 0.566554605960846, + "learning_rate": 1.2835411302755262e-05, + "loss": 1.4204, + "step": 13829 + }, + { + "epoch": 0.7708600412463074, + "grad_norm": 0.5874374508857727, + "learning_rate": 1.2829455248587319e-05, + "loss": 1.7024, + "step": 13830 + }, + { + "epoch": 0.7709157794994704, + "grad_norm": 0.5894142389297485, + "learning_rate": 1.2823500373252329e-05, + "loss": 1.534, + "step": 13831 + }, + { + "epoch": 0.7709715177526336, + "grad_norm": 0.5818924903869629, + "learning_rate": 1.2817546676939158e-05, + "loss": 1.7682, + "step": 13832 + }, + { + "epoch": 0.7710272560057968, + "grad_norm": 0.5268850326538086, + "learning_rate": 1.281159415983661e-05, + "loss": 1.4134, + "step": 13833 + }, + { + "epoch": 0.7710829942589599, + "grad_norm": 0.5993547439575195, + "learning_rate": 1.2805642822133478e-05, + "loss": 1.5439, + "step": 13834 + }, + { + "epoch": 0.7711387325121231, + "grad_norm": 0.5826319456100464, + "learning_rate": 1.2799692664018498e-05, + "loss": 1.7694, + "step": 13835 + }, + { + "epoch": 0.7711944707652862, + "grad_norm": 0.5974748134613037, + "learning_rate": 1.2793743685680388e-05, + "loss": 1.7029, + "step": 13836 + }, + { + "epoch": 0.7712502090184493, + "grad_norm": 0.5868716835975647, + "learning_rate": 1.2787795887307784e-05, + "loss": 1.8878, + "step": 13837 + }, + { + "epoch": 0.7713059472716125, + "grad_norm": 0.5850960612297058, + "learning_rate": 1.278184926908933e-05, + "loss": 1.7172, + "step": 13838 + }, + { + "epoch": 0.7713616855247757, + "grad_norm": 0.5551589131355286, + "learning_rate": 1.2775903831213625e-05, + "loss": 1.6341, + "step": 13839 + }, + { + "epoch": 0.7714174237779388, + "grad_norm": 0.5528069138526917, + "learning_rate": 1.2769959573869217e-05, + "loss": 1.7551, + "step": 13840 + }, + { + "epoch": 0.7714731620311019, + "grad_norm": 0.5707437992095947, + "learning_rate": 1.2764016497244641e-05, + "loss": 1.6185, + "step": 13841 + }, + { + "epoch": 0.7715289002842651, + "grad_norm": 0.6060401797294617, + "learning_rate": 1.275807460152833e-05, + "loss": 1.7512, + "step": 13842 + }, + { + "epoch": 0.7715846385374282, + "grad_norm": 0.6141118407249451, + "learning_rate": 1.275213388690879e-05, + "loss": 1.6764, + "step": 13843 + }, + { + "epoch": 0.7716403767905914, + "grad_norm": 0.5402005910873413, + "learning_rate": 1.2746194353574375e-05, + "loss": 1.5101, + "step": 13844 + }, + { + "epoch": 0.7716961150437546, + "grad_norm": 0.503443717956543, + "learning_rate": 1.2740256001713468e-05, + "loss": 1.3814, + "step": 13845 + }, + { + "epoch": 0.7717518532969176, + "grad_norm": 0.5166171789169312, + "learning_rate": 1.2734318831514408e-05, + "loss": 1.1882, + "step": 13846 + }, + { + "epoch": 0.7718075915500808, + "grad_norm": 0.528704047203064, + "learning_rate": 1.2728382843165477e-05, + "loss": 1.615, + "step": 13847 + }, + { + "epoch": 0.771863329803244, + "grad_norm": 0.5474404096603394, + "learning_rate": 1.272244803685495e-05, + "loss": 1.6113, + "step": 13848 + }, + { + "epoch": 0.7719190680564071, + "grad_norm": 0.5809311866760254, + "learning_rate": 1.2716514412771008e-05, + "loss": 1.5951, + "step": 13849 + }, + { + "epoch": 0.7719748063095703, + "grad_norm": 0.5877264142036438, + "learning_rate": 1.2710581971101854e-05, + "loss": 1.5873, + "step": 13850 + }, + { + "epoch": 0.7720305445627335, + "grad_norm": 0.6127954125404358, + "learning_rate": 1.2704650712035632e-05, + "loss": 1.7727, + "step": 13851 + }, + { + "epoch": 0.7720862828158965, + "grad_norm": 0.5746996402740479, + "learning_rate": 1.2698720635760435e-05, + "loss": 1.7201, + "step": 13852 + }, + { + "epoch": 0.7721420210690597, + "grad_norm": 0.5272437930107117, + "learning_rate": 1.2692791742464343e-05, + "loss": 1.5452, + "step": 13853 + }, + { + "epoch": 0.7721977593222228, + "grad_norm": 0.5763612985610962, + "learning_rate": 1.2686864032335376e-05, + "loss": 1.7422, + "step": 13854 + }, + { + "epoch": 0.772253497575386, + "grad_norm": 0.5544466376304626, + "learning_rate": 1.2680937505561552e-05, + "loss": 1.5116, + "step": 13855 + }, + { + "epoch": 0.7723092358285492, + "grad_norm": 0.5890754461288452, + "learning_rate": 1.267501216233079e-05, + "loss": 1.7639, + "step": 13856 + }, + { + "epoch": 0.7723649740817122, + "grad_norm": 0.5503895282745361, + "learning_rate": 1.266908800283102e-05, + "loss": 1.7836, + "step": 13857 + }, + { + "epoch": 0.7724207123348754, + "grad_norm": 0.5393791198730469, + "learning_rate": 1.2663165027250124e-05, + "loss": 1.5314, + "step": 13858 + }, + { + "epoch": 0.7724764505880386, + "grad_norm": 0.6032135486602783, + "learning_rate": 1.2657243235775945e-05, + "loss": 1.738, + "step": 13859 + }, + { + "epoch": 0.7725321888412017, + "grad_norm": 0.5893515944480896, + "learning_rate": 1.2651322628596285e-05, + "loss": 1.8642, + "step": 13860 + }, + { + "epoch": 0.7725879270943649, + "grad_norm": 0.5650129914283752, + "learning_rate": 1.2645403205898914e-05, + "loss": 1.7399, + "step": 13861 + }, + { + "epoch": 0.772643665347528, + "grad_norm": 0.5308829545974731, + "learning_rate": 1.2639484967871578e-05, + "loss": 1.5345, + "step": 13862 + }, + { + "epoch": 0.7726994036006911, + "grad_norm": 0.5386495590209961, + "learning_rate": 1.2633567914701939e-05, + "loss": 1.5579, + "step": 13863 + }, + { + "epoch": 0.7727551418538543, + "grad_norm": 0.5876171588897705, + "learning_rate": 1.2627652046577659e-05, + "loss": 1.686, + "step": 13864 + }, + { + "epoch": 0.7728108801070175, + "grad_norm": 0.5936629176139832, + "learning_rate": 1.2621737363686365e-05, + "loss": 1.5364, + "step": 13865 + }, + { + "epoch": 0.7728666183601806, + "grad_norm": 0.5996050238609314, + "learning_rate": 1.2615823866215626e-05, + "loss": 1.8273, + "step": 13866 + }, + { + "epoch": 0.7729223566133437, + "grad_norm": 0.6248884797096252, + "learning_rate": 1.260991155435301e-05, + "loss": 1.6975, + "step": 13867 + }, + { + "epoch": 0.7729780948665069, + "grad_norm": 0.5924556255340576, + "learning_rate": 1.2604000428285967e-05, + "loss": 1.6625, + "step": 13868 + }, + { + "epoch": 0.77303383311967, + "grad_norm": 0.5752199292182922, + "learning_rate": 1.2598090488202025e-05, + "loss": 1.6419, + "step": 13869 + }, + { + "epoch": 0.7730895713728332, + "grad_norm": 0.5989288687705994, + "learning_rate": 1.2592181734288572e-05, + "loss": 1.8036, + "step": 13870 + }, + { + "epoch": 0.7731453096259964, + "grad_norm": 0.5582593679428101, + "learning_rate": 1.2586274166733009e-05, + "loss": 1.6237, + "step": 13871 + }, + { + "epoch": 0.7732010478791594, + "grad_norm": 0.5653522610664368, + "learning_rate": 1.2580367785722697e-05, + "loss": 1.6326, + "step": 13872 + }, + { + "epoch": 0.7732567861323226, + "grad_norm": 0.5593123435974121, + "learning_rate": 1.257446259144494e-05, + "loss": 1.5155, + "step": 13873 + }, + { + "epoch": 0.7733125243854858, + "grad_norm": 0.5426331162452698, + "learning_rate": 1.2568558584087048e-05, + "loss": 1.4979, + "step": 13874 + }, + { + "epoch": 0.7733682626386489, + "grad_norm": 0.5261883735656738, + "learning_rate": 1.2562655763836217e-05, + "loss": 1.4564, + "step": 13875 + }, + { + "epoch": 0.7734240008918121, + "grad_norm": 0.5568323731422424, + "learning_rate": 1.2556754130879666e-05, + "loss": 1.5123, + "step": 13876 + }, + { + "epoch": 0.7734797391449751, + "grad_norm": 0.5774717926979065, + "learning_rate": 1.2550853685404573e-05, + "loss": 1.7825, + "step": 13877 + }, + { + "epoch": 0.7735354773981383, + "grad_norm": 0.5544146299362183, + "learning_rate": 1.2544954427598066e-05, + "loss": 1.5749, + "step": 13878 + }, + { + "epoch": 0.7735912156513015, + "grad_norm": 0.5266306400299072, + "learning_rate": 1.25390563576472e-05, + "loss": 1.6941, + "step": 13879 + }, + { + "epoch": 0.7736469539044646, + "grad_norm": 0.605617880821228, + "learning_rate": 1.253315947573907e-05, + "loss": 1.6413, + "step": 13880 + }, + { + "epoch": 0.7737026921576278, + "grad_norm": 0.5538267493247986, + "learning_rate": 1.2527263782060689e-05, + "loss": 1.6178, + "step": 13881 + }, + { + "epoch": 0.773758430410791, + "grad_norm": 0.6117134690284729, + "learning_rate": 1.2521369276799e-05, + "loss": 1.7388, + "step": 13882 + }, + { + "epoch": 0.773814168663954, + "grad_norm": 0.6116869449615479, + "learning_rate": 1.2515475960140966e-05, + "loss": 1.8371, + "step": 13883 + }, + { + "epoch": 0.7738699069171172, + "grad_norm": 0.5542810559272766, + "learning_rate": 1.2509583832273486e-05, + "loss": 1.4842, + "step": 13884 + }, + { + "epoch": 0.7739256451702804, + "grad_norm": 0.6455458402633667, + "learning_rate": 1.2503692893383424e-05, + "loss": 1.836, + "step": 13885 + }, + { + "epoch": 0.7739813834234435, + "grad_norm": 0.5932666063308716, + "learning_rate": 1.24978031436576e-05, + "loss": 1.5868, + "step": 13886 + }, + { + "epoch": 0.7740371216766067, + "grad_norm": 0.5318253040313721, + "learning_rate": 1.2491914583282805e-05, + "loss": 1.5224, + "step": 13887 + }, + { + "epoch": 0.7740928599297698, + "grad_norm": 0.5483694076538086, + "learning_rate": 1.2486027212445812e-05, + "loss": 1.6178, + "step": 13888 + }, + { + "epoch": 0.7741485981829329, + "grad_norm": 0.5445347428321838, + "learning_rate": 1.2480141031333299e-05, + "loss": 1.5006, + "step": 13889 + }, + { + "epoch": 0.7742043364360961, + "grad_norm": 0.5520989298820496, + "learning_rate": 1.2474256040131955e-05, + "loss": 1.6473, + "step": 13890 + }, + { + "epoch": 0.7742600746892593, + "grad_norm": 0.5939954519271851, + "learning_rate": 1.246837223902842e-05, + "loss": 1.7462, + "step": 13891 + }, + { + "epoch": 0.7743158129424224, + "grad_norm": 0.5705162286758423, + "learning_rate": 1.246248962820929e-05, + "loss": 1.5555, + "step": 13892 + }, + { + "epoch": 0.7743715511955855, + "grad_norm": 0.5511966943740845, + "learning_rate": 1.2456608207861147e-05, + "loss": 1.4746, + "step": 13893 + }, + { + "epoch": 0.7744272894487487, + "grad_norm": 0.560956597328186, + "learning_rate": 1.2450727978170473e-05, + "loss": 1.6586, + "step": 13894 + }, + { + "epoch": 0.7744830277019118, + "grad_norm": 0.5590883493423462, + "learning_rate": 1.2444848939323805e-05, + "loss": 1.7492, + "step": 13895 + }, + { + "epoch": 0.774538765955075, + "grad_norm": 0.5555147528648376, + "learning_rate": 1.243897109150755e-05, + "loss": 1.5381, + "step": 13896 + }, + { + "epoch": 0.7745945042082382, + "grad_norm": 0.5215170383453369, + "learning_rate": 1.2433094434908143e-05, + "loss": 1.4131, + "step": 13897 + }, + { + "epoch": 0.7746502424614012, + "grad_norm": 0.5432319045066833, + "learning_rate": 1.2427218969711945e-05, + "loss": 1.3415, + "step": 13898 + }, + { + "epoch": 0.7747059807145644, + "grad_norm": 0.6142305731773376, + "learning_rate": 1.2421344696105298e-05, + "loss": 1.6424, + "step": 13899 + }, + { + "epoch": 0.7747617189677275, + "grad_norm": 0.5684335827827454, + "learning_rate": 1.2415471614274515e-05, + "loss": 1.8077, + "step": 13900 + }, + { + "epoch": 0.7748174572208907, + "grad_norm": 0.5752829313278198, + "learning_rate": 1.2409599724405807e-05, + "loss": 1.6892, + "step": 13901 + }, + { + "epoch": 0.7748731954740539, + "grad_norm": 0.5764576196670532, + "learning_rate": 1.2403729026685462e-05, + "loss": 1.722, + "step": 13902 + }, + { + "epoch": 0.7749289337272169, + "grad_norm": 0.5339565873146057, + "learning_rate": 1.2397859521299615e-05, + "loss": 1.5116, + "step": 13903 + }, + { + "epoch": 0.7749846719803801, + "grad_norm": 0.6000561714172363, + "learning_rate": 1.2391991208434439e-05, + "loss": 1.6784, + "step": 13904 + }, + { + "epoch": 0.7750404102335433, + "grad_norm": 0.592254638671875, + "learning_rate": 1.2386124088276007e-05, + "loss": 1.7135, + "step": 13905 + }, + { + "epoch": 0.7750961484867064, + "grad_norm": 0.5584617853164673, + "learning_rate": 1.2380258161010427e-05, + "loss": 1.6567, + "step": 13906 + }, + { + "epoch": 0.7751518867398696, + "grad_norm": 0.5328884124755859, + "learning_rate": 1.2374393426823733e-05, + "loss": 1.5234, + "step": 13907 + }, + { + "epoch": 0.7752076249930328, + "grad_norm": 0.5227957367897034, + "learning_rate": 1.2368529885901898e-05, + "loss": 1.4218, + "step": 13908 + }, + { + "epoch": 0.7752633632461958, + "grad_norm": 0.5832966566085815, + "learning_rate": 1.2362667538430883e-05, + "loss": 1.6467, + "step": 13909 + }, + { + "epoch": 0.775319101499359, + "grad_norm": 0.5582821369171143, + "learning_rate": 1.2356806384596614e-05, + "loss": 1.5709, + "step": 13910 + }, + { + "epoch": 0.7753748397525222, + "grad_norm": 0.5849579572677612, + "learning_rate": 1.235094642458497e-05, + "loss": 1.7064, + "step": 13911 + }, + { + "epoch": 0.7754305780056853, + "grad_norm": 0.64003586769104, + "learning_rate": 1.23450876585818e-05, + "loss": 1.7045, + "step": 13912 + }, + { + "epoch": 0.7754863162588485, + "grad_norm": 0.5383117198944092, + "learning_rate": 1.2339230086772907e-05, + "loss": 1.5096, + "step": 13913 + }, + { + "epoch": 0.7755420545120116, + "grad_norm": 0.5988223552703857, + "learning_rate": 1.2333373709344065e-05, + "loss": 1.8464, + "step": 13914 + }, + { + "epoch": 0.7755977927651747, + "grad_norm": 0.522731602191925, + "learning_rate": 1.2327518526480992e-05, + "loss": 1.4544, + "step": 13915 + }, + { + "epoch": 0.7756535310183379, + "grad_norm": 0.5857813358306885, + "learning_rate": 1.2321664538369382e-05, + "loss": 1.851, + "step": 13916 + }, + { + "epoch": 0.7757092692715011, + "grad_norm": 0.560541570186615, + "learning_rate": 1.231581174519489e-05, + "loss": 1.732, + "step": 13917 + }, + { + "epoch": 0.7757650075246642, + "grad_norm": 0.564007580280304, + "learning_rate": 1.2309960147143134e-05, + "loss": 1.6381, + "step": 13918 + }, + { + "epoch": 0.7758207457778273, + "grad_norm": 0.5471463203430176, + "learning_rate": 1.2304109744399716e-05, + "loss": 1.5694, + "step": 13919 + }, + { + "epoch": 0.7758764840309905, + "grad_norm": 0.5344834327697754, + "learning_rate": 1.2298260537150119e-05, + "loss": 1.7807, + "step": 13920 + }, + { + "epoch": 0.7759322222841536, + "grad_norm": 0.5642966628074646, + "learning_rate": 1.2292412525579916e-05, + "loss": 1.7266, + "step": 13921 + }, + { + "epoch": 0.7759879605373168, + "grad_norm": 0.5271955132484436, + "learning_rate": 1.228656570987452e-05, + "loss": 1.4124, + "step": 13922 + }, + { + "epoch": 0.7760436987904799, + "grad_norm": 0.5498999357223511, + "learning_rate": 1.2280720090219372e-05, + "loss": 1.5466, + "step": 13923 + }, + { + "epoch": 0.776099437043643, + "grad_norm": 0.595337450504303, + "learning_rate": 1.2274875666799867e-05, + "loss": 1.8677, + "step": 13924 + }, + { + "epoch": 0.7761551752968062, + "grad_norm": 0.581565260887146, + "learning_rate": 1.2269032439801353e-05, + "loss": 1.862, + "step": 13925 + }, + { + "epoch": 0.7762109135499693, + "grad_norm": 0.623028576374054, + "learning_rate": 1.226319040940916e-05, + "loss": 1.9658, + "step": 13926 + }, + { + "epoch": 0.7762666518031325, + "grad_norm": 0.5315784215927124, + "learning_rate": 1.2257349575808513e-05, + "loss": 1.488, + "step": 13927 + }, + { + "epoch": 0.7763223900562957, + "grad_norm": 0.5710899233818054, + "learning_rate": 1.2251509939184713e-05, + "loss": 1.8711, + "step": 13928 + }, + { + "epoch": 0.7763781283094587, + "grad_norm": 0.5678262710571289, + "learning_rate": 1.2245671499722916e-05, + "loss": 1.6375, + "step": 13929 + }, + { + "epoch": 0.7764338665626219, + "grad_norm": 0.6168885231018066, + "learning_rate": 1.2239834257608312e-05, + "loss": 1.9096, + "step": 13930 + }, + { + "epoch": 0.7764896048157851, + "grad_norm": 0.6101101636886597, + "learning_rate": 1.2233998213025977e-05, + "loss": 1.7417, + "step": 13931 + }, + { + "epoch": 0.7765453430689482, + "grad_norm": 0.5685074329376221, + "learning_rate": 1.2228163366161038e-05, + "loss": 1.6114, + "step": 13932 + }, + { + "epoch": 0.7766010813221114, + "grad_norm": 0.5775470733642578, + "learning_rate": 1.2222329717198556e-05, + "loss": 1.6181, + "step": 13933 + }, + { + "epoch": 0.7766568195752745, + "grad_norm": 0.53831946849823, + "learning_rate": 1.2216497266323495e-05, + "loss": 1.6174, + "step": 13934 + }, + { + "epoch": 0.7767125578284376, + "grad_norm": 0.5419134497642517, + "learning_rate": 1.2210666013720845e-05, + "loss": 1.5781, + "step": 13935 + }, + { + "epoch": 0.7767682960816008, + "grad_norm": 0.5791894793510437, + "learning_rate": 1.2204835959575545e-05, + "loss": 1.6628, + "step": 13936 + }, + { + "epoch": 0.776824034334764, + "grad_norm": 0.5430119037628174, + "learning_rate": 1.219900710407249e-05, + "loss": 1.506, + "step": 13937 + }, + { + "epoch": 0.7768797725879271, + "grad_norm": 0.542615532875061, + "learning_rate": 1.219317944739653e-05, + "loss": 1.8301, + "step": 13938 + }, + { + "epoch": 0.7769355108410902, + "grad_norm": 0.5840906500816345, + "learning_rate": 1.2187352989732493e-05, + "loss": 1.6372, + "step": 13939 + }, + { + "epoch": 0.7769912490942534, + "grad_norm": 0.5867896676063538, + "learning_rate": 1.2181527731265169e-05, + "loss": 1.5859, + "step": 13940 + }, + { + "epoch": 0.7770469873474165, + "grad_norm": 0.5682836771011353, + "learning_rate": 1.2175703672179273e-05, + "loss": 1.756, + "step": 13941 + }, + { + "epoch": 0.7771027256005797, + "grad_norm": 0.6265798807144165, + "learning_rate": 1.2169880812659529e-05, + "loss": 1.682, + "step": 13942 + }, + { + "epoch": 0.7771584638537429, + "grad_norm": 0.5579496026039124, + "learning_rate": 1.21640591528906e-05, + "loss": 1.5255, + "step": 13943 + }, + { + "epoch": 0.777214202106906, + "grad_norm": 0.5834450125694275, + "learning_rate": 1.2158238693057112e-05, + "loss": 1.724, + "step": 13944 + }, + { + "epoch": 0.7772699403600691, + "grad_norm": 0.5844115614891052, + "learning_rate": 1.2152419433343676e-05, + "loss": 1.6637, + "step": 13945 + }, + { + "epoch": 0.7773256786132322, + "grad_norm": 0.5828450322151184, + "learning_rate": 1.2146601373934801e-05, + "loss": 1.732, + "step": 13946 + }, + { + "epoch": 0.7773814168663954, + "grad_norm": 0.5758583545684814, + "learning_rate": 1.2140784515015058e-05, + "loss": 1.6216, + "step": 13947 + }, + { + "epoch": 0.7774371551195586, + "grad_norm": 0.6091346740722656, + "learning_rate": 1.213496885676888e-05, + "loss": 1.9204, + "step": 13948 + }, + { + "epoch": 0.7774928933727216, + "grad_norm": 0.5350582003593445, + "learning_rate": 1.212915439938072e-05, + "loss": 1.4757, + "step": 13949 + }, + { + "epoch": 0.7775486316258848, + "grad_norm": 0.5768659114837646, + "learning_rate": 1.2123341143034988e-05, + "loss": 1.7228, + "step": 13950 + }, + { + "epoch": 0.777604369879048, + "grad_norm": 0.5592014193534851, + "learning_rate": 1.211752908791603e-05, + "loss": 1.6262, + "step": 13951 + }, + { + "epoch": 0.7776601081322111, + "grad_norm": 0.610351026058197, + "learning_rate": 1.2111718234208197e-05, + "loss": 1.7301, + "step": 13952 + }, + { + "epoch": 0.7777158463853743, + "grad_norm": 0.5659115314483643, + "learning_rate": 1.2105908582095731e-05, + "loss": 1.6193, + "step": 13953 + }, + { + "epoch": 0.7777715846385375, + "grad_norm": 0.5750666260719299, + "learning_rate": 1.2100100131762932e-05, + "loss": 1.8068, + "step": 13954 + }, + { + "epoch": 0.7778273228917005, + "grad_norm": 0.5514704585075378, + "learning_rate": 1.2094292883393976e-05, + "loss": 1.5966, + "step": 13955 + }, + { + "epoch": 0.7778830611448637, + "grad_norm": 0.5872873067855835, + "learning_rate": 1.2088486837173051e-05, + "loss": 1.8582, + "step": 13956 + }, + { + "epoch": 0.7779387993980269, + "grad_norm": 0.5862222909927368, + "learning_rate": 1.2082681993284261e-05, + "loss": 1.7307, + "step": 13957 + }, + { + "epoch": 0.77799453765119, + "grad_norm": 0.5620829463005066, + "learning_rate": 1.2076878351911736e-05, + "loss": 1.7103, + "step": 13958 + }, + { + "epoch": 0.7780502759043532, + "grad_norm": 0.5808737874031067, + "learning_rate": 1.2071075913239538e-05, + "loss": 1.7988, + "step": 13959 + }, + { + "epoch": 0.7781060141575163, + "grad_norm": 0.5587299466133118, + "learning_rate": 1.206527467745166e-05, + "loss": 1.7373, + "step": 13960 + }, + { + "epoch": 0.7781617524106794, + "grad_norm": 0.607959508895874, + "learning_rate": 1.2059474644732088e-05, + "loss": 1.7231, + "step": 13961 + }, + { + "epoch": 0.7782174906638426, + "grad_norm": 0.569949209690094, + "learning_rate": 1.2053675815264776e-05, + "loss": 1.6934, + "step": 13962 + }, + { + "epoch": 0.7782732289170058, + "grad_norm": 0.5692344307899475, + "learning_rate": 1.2047878189233625e-05, + "loss": 1.7624, + "step": 13963 + }, + { + "epoch": 0.7783289671701689, + "grad_norm": 0.5457063317298889, + "learning_rate": 1.2042081766822499e-05, + "loss": 1.6195, + "step": 13964 + }, + { + "epoch": 0.778384705423332, + "grad_norm": 0.6106131076812744, + "learning_rate": 1.2036286548215231e-05, + "loss": 1.8619, + "step": 13965 + }, + { + "epoch": 0.7784404436764952, + "grad_norm": 0.590175986289978, + "learning_rate": 1.2030492533595623e-05, + "loss": 1.7022, + "step": 13966 + }, + { + "epoch": 0.7784961819296583, + "grad_norm": 0.6062188744544983, + "learning_rate": 1.2024699723147403e-05, + "loss": 1.6003, + "step": 13967 + }, + { + "epoch": 0.7785519201828215, + "grad_norm": 0.5541261434555054, + "learning_rate": 1.2018908117054295e-05, + "loss": 1.488, + "step": 13968 + }, + { + "epoch": 0.7786076584359846, + "grad_norm": 0.5979520082473755, + "learning_rate": 1.2013117715499972e-05, + "loss": 1.7595, + "step": 13969 + }, + { + "epoch": 0.7786633966891477, + "grad_norm": 0.5797428488731384, + "learning_rate": 1.2007328518668082e-05, + "loss": 1.6972, + "step": 13970 + }, + { + "epoch": 0.7787191349423109, + "grad_norm": 0.5980271697044373, + "learning_rate": 1.2001540526742234e-05, + "loss": 1.6437, + "step": 13971 + }, + { + "epoch": 0.778774873195474, + "grad_norm": 0.5568384528160095, + "learning_rate": 1.199575373990594e-05, + "loss": 1.455, + "step": 13972 + }, + { + "epoch": 0.7788306114486372, + "grad_norm": 0.5588963627815247, + "learning_rate": 1.198996815834279e-05, + "loss": 1.6241, + "step": 13973 + }, + { + "epoch": 0.7788863497018004, + "grad_norm": 0.5465938448905945, + "learning_rate": 1.1984183782236219e-05, + "loss": 1.7752, + "step": 13974 + }, + { + "epoch": 0.7789420879549634, + "grad_norm": 0.5582731366157532, + "learning_rate": 1.197840061176969e-05, + "loss": 1.5402, + "step": 13975 + }, + { + "epoch": 0.7789978262081266, + "grad_norm": 0.6088888049125671, + "learning_rate": 1.1972618647126616e-05, + "loss": 1.6849, + "step": 13976 + }, + { + "epoch": 0.7790535644612898, + "grad_norm": 0.5533426403999329, + "learning_rate": 1.1966837888490361e-05, + "loss": 1.6473, + "step": 13977 + }, + { + "epoch": 0.7791093027144529, + "grad_norm": 0.5501806139945984, + "learning_rate": 1.1961058336044274e-05, + "loss": 1.5457, + "step": 13978 + }, + { + "epoch": 0.7791650409676161, + "grad_norm": 0.5428063273429871, + "learning_rate": 1.1955279989971607e-05, + "loss": 1.5844, + "step": 13979 + }, + { + "epoch": 0.7792207792207793, + "grad_norm": 0.5709086060523987, + "learning_rate": 1.1949502850455669e-05, + "loss": 1.6657, + "step": 13980 + }, + { + "epoch": 0.7792765174739423, + "grad_norm": 0.5452801585197449, + "learning_rate": 1.1943726917679637e-05, + "loss": 1.5395, + "step": 13981 + }, + { + "epoch": 0.7793322557271055, + "grad_norm": 0.5536159873008728, + "learning_rate": 1.1937952191826723e-05, + "loss": 1.4989, + "step": 13982 + }, + { + "epoch": 0.7793879939802687, + "grad_norm": 0.5623399019241333, + "learning_rate": 1.1932178673080014e-05, + "loss": 1.692, + "step": 13983 + }, + { + "epoch": 0.7794437322334318, + "grad_norm": 0.6092471480369568, + "learning_rate": 1.1926406361622661e-05, + "loss": 1.7339, + "step": 13984 + }, + { + "epoch": 0.779499470486595, + "grad_norm": 0.5527442693710327, + "learning_rate": 1.192063525763773e-05, + "loss": 1.7289, + "step": 13985 + }, + { + "epoch": 0.7795552087397581, + "grad_norm": 0.6212316155433655, + "learning_rate": 1.1914865361308213e-05, + "loss": 1.6664, + "step": 13986 + }, + { + "epoch": 0.7796109469929212, + "grad_norm": 0.6183369755744934, + "learning_rate": 1.1909096672817121e-05, + "loss": 1.8228, + "step": 13987 + }, + { + "epoch": 0.7796666852460844, + "grad_norm": 0.5724116563796997, + "learning_rate": 1.1903329192347395e-05, + "loss": 1.7243, + "step": 13988 + }, + { + "epoch": 0.7797224234992476, + "grad_norm": 0.5382424592971802, + "learning_rate": 1.1897562920081945e-05, + "loss": 1.4968, + "step": 13989 + }, + { + "epoch": 0.7797781617524107, + "grad_norm": 0.5783862471580505, + "learning_rate": 1.1891797856203651e-05, + "loss": 1.6693, + "step": 13990 + }, + { + "epoch": 0.7798339000055738, + "grad_norm": 0.5656108856201172, + "learning_rate": 1.188603400089534e-05, + "loss": 1.6512, + "step": 13991 + }, + { + "epoch": 0.7798896382587369, + "grad_norm": 0.5719448924064636, + "learning_rate": 1.1880271354339822e-05, + "loss": 1.6319, + "step": 13992 + }, + { + "epoch": 0.7799453765119001, + "grad_norm": 0.5753348469734192, + "learning_rate": 1.1874509916719834e-05, + "loss": 1.6541, + "step": 13993 + }, + { + "epoch": 0.7800011147650633, + "grad_norm": 0.5586207509040833, + "learning_rate": 1.1868749688218106e-05, + "loss": 1.6669, + "step": 13994 + }, + { + "epoch": 0.7800568530182264, + "grad_norm": 0.6782849431037903, + "learning_rate": 1.186299066901731e-05, + "loss": 2.0342, + "step": 13995 + }, + { + "epoch": 0.7801125912713895, + "grad_norm": 0.5908063650131226, + "learning_rate": 1.18572328593001e-05, + "loss": 1.7769, + "step": 13996 + }, + { + "epoch": 0.7801683295245527, + "grad_norm": 0.5401486158370972, + "learning_rate": 1.185147625924909e-05, + "loss": 1.5211, + "step": 13997 + }, + { + "epoch": 0.7802240677777158, + "grad_norm": 0.5483136177062988, + "learning_rate": 1.1845720869046805e-05, + "loss": 1.4663, + "step": 13998 + }, + { + "epoch": 0.780279806030879, + "grad_norm": 0.6039329171180725, + "learning_rate": 1.1839966688875825e-05, + "loss": 1.6968, + "step": 13999 + }, + { + "epoch": 0.7803355442840422, + "grad_norm": 0.5703708529472351, + "learning_rate": 1.1834213718918602e-05, + "loss": 1.6897, + "step": 14000 + }, + { + "epoch": 0.7803912825372052, + "grad_norm": 0.5920760035514832, + "learning_rate": 1.1828461959357595e-05, + "loss": 1.7622, + "step": 14001 + }, + { + "epoch": 0.7804470207903684, + "grad_norm": 0.5369116067886353, + "learning_rate": 1.182271141037522e-05, + "loss": 1.5367, + "step": 14002 + }, + { + "epoch": 0.7805027590435316, + "grad_norm": 0.5805405974388123, + "learning_rate": 1.1816962072153848e-05, + "loss": 1.8351, + "step": 14003 + }, + { + "epoch": 0.7805584972966947, + "grad_norm": 0.5652420520782471, + "learning_rate": 1.1811213944875832e-05, + "loss": 1.5502, + "step": 14004 + }, + { + "epoch": 0.7806142355498579, + "grad_norm": 0.5290706753730774, + "learning_rate": 1.1805467028723426e-05, + "loss": 1.5114, + "step": 14005 + }, + { + "epoch": 0.7806699738030211, + "grad_norm": 0.5578330755233765, + "learning_rate": 1.1799721323878943e-05, + "loss": 1.5488, + "step": 14006 + }, + { + "epoch": 0.7807257120561841, + "grad_norm": 0.557753324508667, + "learning_rate": 1.1793976830524567e-05, + "loss": 1.5781, + "step": 14007 + }, + { + "epoch": 0.7807814503093473, + "grad_norm": 0.5453119277954102, + "learning_rate": 1.1788233548842486e-05, + "loss": 1.6267, + "step": 14008 + }, + { + "epoch": 0.7808371885625105, + "grad_norm": 0.5647554993629456, + "learning_rate": 1.1782491479014846e-05, + "loss": 1.7858, + "step": 14009 + }, + { + "epoch": 0.7808929268156736, + "grad_norm": 0.553887665271759, + "learning_rate": 1.1776750621223754e-05, + "loss": 1.394, + "step": 14010 + }, + { + "epoch": 0.7809486650688368, + "grad_norm": 0.6797167658805847, + "learning_rate": 1.1771010975651287e-05, + "loss": 1.8826, + "step": 14011 + }, + { + "epoch": 0.7810044033219999, + "grad_norm": 0.568385660648346, + "learning_rate": 1.176527254247945e-05, + "loss": 1.6163, + "step": 14012 + }, + { + "epoch": 0.781060141575163, + "grad_norm": 0.566242516040802, + "learning_rate": 1.1759535321890247e-05, + "loss": 1.6258, + "step": 14013 + }, + { + "epoch": 0.7811158798283262, + "grad_norm": 0.5936616659164429, + "learning_rate": 1.1753799314065622e-05, + "loss": 1.7727, + "step": 14014 + }, + { + "epoch": 0.7811716180814893, + "grad_norm": 0.5442579984664917, + "learning_rate": 1.1748064519187507e-05, + "loss": 1.5458, + "step": 14015 + }, + { + "epoch": 0.7812273563346525, + "grad_norm": 0.6045543551445007, + "learning_rate": 1.1742330937437729e-05, + "loss": 1.5589, + "step": 14016 + }, + { + "epoch": 0.7812830945878156, + "grad_norm": 0.5740007162094116, + "learning_rate": 1.1736598568998175e-05, + "loss": 1.752, + "step": 14017 + }, + { + "epoch": 0.7813388328409787, + "grad_norm": 0.5655611753463745, + "learning_rate": 1.1730867414050634e-05, + "loss": 1.8233, + "step": 14018 + }, + { + "epoch": 0.7813945710941419, + "grad_norm": 0.5489192605018616, + "learning_rate": 1.1725137472776842e-05, + "loss": 1.3202, + "step": 14019 + }, + { + "epoch": 0.7814503093473051, + "grad_norm": 0.6361293792724609, + "learning_rate": 1.1719408745358534e-05, + "loss": 1.7173, + "step": 14020 + }, + { + "epoch": 0.7815060476004682, + "grad_norm": 0.5393735766410828, + "learning_rate": 1.1713681231977387e-05, + "loss": 1.6645, + "step": 14021 + }, + { + "epoch": 0.7815617858536313, + "grad_norm": 0.5540429353713989, + "learning_rate": 1.1707954932815046e-05, + "loss": 1.6041, + "step": 14022 + }, + { + "epoch": 0.7816175241067945, + "grad_norm": 0.5488499402999878, + "learning_rate": 1.1702229848053131e-05, + "loss": 1.6196, + "step": 14023 + }, + { + "epoch": 0.7816732623599576, + "grad_norm": 0.6127748489379883, + "learning_rate": 1.1696505977873167e-05, + "loss": 1.9201, + "step": 14024 + }, + { + "epoch": 0.7817290006131208, + "grad_norm": 0.5382614731788635, + "learning_rate": 1.1690783322456734e-05, + "loss": 1.596, + "step": 14025 + }, + { + "epoch": 0.781784738866284, + "grad_norm": 0.564821183681488, + "learning_rate": 1.1685061881985282e-05, + "loss": 1.6196, + "step": 14026 + }, + { + "epoch": 0.781840477119447, + "grad_norm": 0.5664968490600586, + "learning_rate": 1.1679341656640275e-05, + "loss": 1.7333, + "step": 14027 + }, + { + "epoch": 0.7818962153726102, + "grad_norm": 0.5671424269676208, + "learning_rate": 1.1673622646603127e-05, + "loss": 1.6193, + "step": 14028 + }, + { + "epoch": 0.7819519536257734, + "grad_norm": 0.5720041394233704, + "learning_rate": 1.1667904852055212e-05, + "loss": 1.6827, + "step": 14029 + }, + { + "epoch": 0.7820076918789365, + "grad_norm": 0.5713546276092529, + "learning_rate": 1.1662188273177877e-05, + "loss": 1.5779, + "step": 14030 + }, + { + "epoch": 0.7820634301320997, + "grad_norm": 0.5552577376365662, + "learning_rate": 1.1656472910152376e-05, + "loss": 1.5118, + "step": 14031 + }, + { + "epoch": 0.7821191683852629, + "grad_norm": 0.5922068357467651, + "learning_rate": 1.1650758763160025e-05, + "loss": 1.7555, + "step": 14032 + }, + { + "epoch": 0.7821749066384259, + "grad_norm": 0.6121614575386047, + "learning_rate": 1.1645045832381995e-05, + "loss": 1.8431, + "step": 14033 + }, + { + "epoch": 0.7822306448915891, + "grad_norm": 0.5433709025382996, + "learning_rate": 1.1639334117999496e-05, + "loss": 1.523, + "step": 14034 + }, + { + "epoch": 0.7822863831447523, + "grad_norm": 0.5548751950263977, + "learning_rate": 1.163362362019365e-05, + "loss": 1.6873, + "step": 14035 + }, + { + "epoch": 0.7823421213979154, + "grad_norm": 0.6262120008468628, + "learning_rate": 1.162791433914558e-05, + "loss": 1.7052, + "step": 14036 + }, + { + "epoch": 0.7823978596510786, + "grad_norm": 0.5512871742248535, + "learning_rate": 1.1622206275036352e-05, + "loss": 1.8216, + "step": 14037 + }, + { + "epoch": 0.7824535979042416, + "grad_norm": 0.5779017210006714, + "learning_rate": 1.1616499428046974e-05, + "loss": 1.5163, + "step": 14038 + }, + { + "epoch": 0.7825093361574048, + "grad_norm": 0.5814633965492249, + "learning_rate": 1.1610793798358433e-05, + "loss": 1.5863, + "step": 14039 + }, + { + "epoch": 0.782565074410568, + "grad_norm": 0.5750308632850647, + "learning_rate": 1.1605089386151695e-05, + "loss": 1.5654, + "step": 14040 + }, + { + "epoch": 0.7826208126637311, + "grad_norm": 0.5587421655654907, + "learning_rate": 1.1599386191607675e-05, + "loss": 1.6553, + "step": 14041 + }, + { + "epoch": 0.7826765509168943, + "grad_norm": 0.5279087424278259, + "learning_rate": 1.1593684214907207e-05, + "loss": 1.5521, + "step": 14042 + }, + { + "epoch": 0.7827322891700574, + "grad_norm": 0.5872433185577393, + "learning_rate": 1.1587983456231166e-05, + "loss": 1.6284, + "step": 14043 + }, + { + "epoch": 0.7827880274232205, + "grad_norm": 0.5682265162467957, + "learning_rate": 1.158228391576035e-05, + "loss": 1.29, + "step": 14044 + }, + { + "epoch": 0.7828437656763837, + "grad_norm": 0.548341691493988, + "learning_rate": 1.1576585593675477e-05, + "loss": 1.5505, + "step": 14045 + }, + { + "epoch": 0.7828995039295469, + "grad_norm": 0.5533690452575684, + "learning_rate": 1.1570888490157289e-05, + "loss": 1.369, + "step": 14046 + }, + { + "epoch": 0.78295524218271, + "grad_norm": 0.6491280794143677, + "learning_rate": 1.156519260538646e-05, + "loss": 1.7068, + "step": 14047 + }, + { + "epoch": 0.7830109804358731, + "grad_norm": 0.5396941304206848, + "learning_rate": 1.155949793954363e-05, + "loss": 1.5027, + "step": 14048 + }, + { + "epoch": 0.7830667186890363, + "grad_norm": 0.6212543845176697, + "learning_rate": 1.1553804492809417e-05, + "loss": 1.9128, + "step": 14049 + }, + { + "epoch": 0.7831224569421994, + "grad_norm": 0.5530951619148254, + "learning_rate": 1.1548112265364336e-05, + "loss": 1.7097, + "step": 14050 + }, + { + "epoch": 0.7831781951953626, + "grad_norm": 0.5900622606277466, + "learning_rate": 1.154242125738898e-05, + "loss": 1.78, + "step": 14051 + }, + { + "epoch": 0.7832339334485258, + "grad_norm": 0.6479026079177856, + "learning_rate": 1.1536731469063777e-05, + "loss": 2.0257, + "step": 14052 + }, + { + "epoch": 0.7832896717016888, + "grad_norm": 0.5552021861076355, + "learning_rate": 1.15310429005692e-05, + "loss": 1.5198, + "step": 14053 + }, + { + "epoch": 0.783345409954852, + "grad_norm": 0.6861423850059509, + "learning_rate": 1.1525355552085648e-05, + "loss": 1.2568, + "step": 14054 + }, + { + "epoch": 0.7834011482080152, + "grad_norm": 0.5832570791244507, + "learning_rate": 1.15196694237935e-05, + "loss": 1.6483, + "step": 14055 + }, + { + "epoch": 0.7834568864611783, + "grad_norm": 0.5791754722595215, + "learning_rate": 1.1513984515873094e-05, + "loss": 1.5516, + "step": 14056 + }, + { + "epoch": 0.7835126247143415, + "grad_norm": 0.6173155307769775, + "learning_rate": 1.150830082850468e-05, + "loss": 1.8275, + "step": 14057 + }, + { + "epoch": 0.7835683629675047, + "grad_norm": 0.5452615022659302, + "learning_rate": 1.1502618361868572e-05, + "loss": 1.5679, + "step": 14058 + }, + { + "epoch": 0.7836241012206677, + "grad_norm": 0.5976300835609436, + "learning_rate": 1.149693711614494e-05, + "loss": 1.6907, + "step": 14059 + }, + { + "epoch": 0.7836798394738309, + "grad_norm": 0.7489990592002869, + "learning_rate": 1.1491257091513974e-05, + "loss": 1.4673, + "step": 14060 + }, + { + "epoch": 0.783735577726994, + "grad_norm": 0.5231119990348816, + "learning_rate": 1.1485578288155813e-05, + "loss": 1.4492, + "step": 14061 + }, + { + "epoch": 0.7837913159801572, + "grad_norm": 0.5623896718025208, + "learning_rate": 1.1479900706250552e-05, + "loss": 1.6429, + "step": 14062 + }, + { + "epoch": 0.7838470542333204, + "grad_norm": 0.5758726000785828, + "learning_rate": 1.1474224345978268e-05, + "loss": 1.6883, + "step": 14063 + }, + { + "epoch": 0.7839027924864834, + "grad_norm": 0.617182195186615, + "learning_rate": 1.1468549207518953e-05, + "loss": 1.6511, + "step": 14064 + }, + { + "epoch": 0.7839585307396466, + "grad_norm": 0.5945354700088501, + "learning_rate": 1.1462875291052604e-05, + "loss": 1.7315, + "step": 14065 + }, + { + "epoch": 0.7840142689928098, + "grad_norm": 0.5089705586433411, + "learning_rate": 1.1457202596759165e-05, + "loss": 1.2648, + "step": 14066 + }, + { + "epoch": 0.7840700072459729, + "grad_norm": 0.5625550746917725, + "learning_rate": 1.1451531124818548e-05, + "loss": 1.5514, + "step": 14067 + }, + { + "epoch": 0.784125745499136, + "grad_norm": 0.5699339509010315, + "learning_rate": 1.1445860875410586e-05, + "loss": 1.5198, + "step": 14068 + }, + { + "epoch": 0.7841814837522992, + "grad_norm": 0.568102240562439, + "learning_rate": 1.1440191848715143e-05, + "loss": 1.6896, + "step": 14069 + }, + { + "epoch": 0.7842372220054623, + "grad_norm": 0.5320776700973511, + "learning_rate": 1.1434524044912009e-05, + "loss": 1.4559, + "step": 14070 + }, + { + "epoch": 0.7842929602586255, + "grad_norm": 0.5914183855056763, + "learning_rate": 1.1428857464180908e-05, + "loss": 1.6122, + "step": 14071 + }, + { + "epoch": 0.7843486985117887, + "grad_norm": 0.5802083015441895, + "learning_rate": 1.1423192106701563e-05, + "loss": 1.7864, + "step": 14072 + }, + { + "epoch": 0.7844044367649518, + "grad_norm": 0.6148181557655334, + "learning_rate": 1.1417527972653647e-05, + "loss": 1.6808, + "step": 14073 + }, + { + "epoch": 0.7844601750181149, + "grad_norm": 0.5611074566841125, + "learning_rate": 1.1411865062216792e-05, + "loss": 1.7022, + "step": 14074 + }, + { + "epoch": 0.7845159132712781, + "grad_norm": 0.5848512649536133, + "learning_rate": 1.140620337557059e-05, + "loss": 1.5988, + "step": 14075 + }, + { + "epoch": 0.7845716515244412, + "grad_norm": 0.5921863913536072, + "learning_rate": 1.1400542912894602e-05, + "loss": 1.5858, + "step": 14076 + }, + { + "epoch": 0.7846273897776044, + "grad_norm": 0.5781610012054443, + "learning_rate": 1.1394883674368356e-05, + "loss": 1.795, + "step": 14077 + }, + { + "epoch": 0.7846831280307676, + "grad_norm": 0.5733685493469238, + "learning_rate": 1.1389225660171299e-05, + "loss": 1.7813, + "step": 14078 + }, + { + "epoch": 0.7847388662839306, + "grad_norm": 0.5941674709320068, + "learning_rate": 1.1383568870482891e-05, + "loss": 1.6134, + "step": 14079 + }, + { + "epoch": 0.7847946045370938, + "grad_norm": 0.5456043481826782, + "learning_rate": 1.137791330548253e-05, + "loss": 1.6329, + "step": 14080 + }, + { + "epoch": 0.784850342790257, + "grad_norm": 0.5724867582321167, + "learning_rate": 1.1372258965349575e-05, + "loss": 1.6439, + "step": 14081 + }, + { + "epoch": 0.7849060810434201, + "grad_norm": 0.5601940155029297, + "learning_rate": 1.1366605850263368e-05, + "loss": 1.5401, + "step": 14082 + }, + { + "epoch": 0.7849618192965833, + "grad_norm": 0.6222748756408691, + "learning_rate": 1.1360953960403142e-05, + "loss": 1.7608, + "step": 14083 + }, + { + "epoch": 0.7850175575497463, + "grad_norm": 0.5868781208992004, + "learning_rate": 1.1355303295948205e-05, + "loss": 1.7358, + "step": 14084 + }, + { + "epoch": 0.7850732958029095, + "grad_norm": 0.5608435869216919, + "learning_rate": 1.1349653857077718e-05, + "loss": 1.7373, + "step": 14085 + }, + { + "epoch": 0.7851290340560727, + "grad_norm": 0.5700390338897705, + "learning_rate": 1.1344005643970863e-05, + "loss": 1.6794, + "step": 14086 + }, + { + "epoch": 0.7851847723092358, + "grad_norm": 0.5813573002815247, + "learning_rate": 1.1338358656806769e-05, + "loss": 1.7308, + "step": 14087 + }, + { + "epoch": 0.785240510562399, + "grad_norm": 0.557304859161377, + "learning_rate": 1.133271289576453e-05, + "loss": 1.602, + "step": 14088 + }, + { + "epoch": 0.7852962488155621, + "grad_norm": 0.6621891260147095, + "learning_rate": 1.1327068361023202e-05, + "loss": 1.803, + "step": 14089 + }, + { + "epoch": 0.7853519870687252, + "grad_norm": 0.586766242980957, + "learning_rate": 1.132142505276177e-05, + "loss": 1.4317, + "step": 14090 + }, + { + "epoch": 0.7854077253218884, + "grad_norm": 0.5434842705726624, + "learning_rate": 1.1315782971159227e-05, + "loss": 1.6327, + "step": 14091 + }, + { + "epoch": 0.7854634635750516, + "grad_norm": 0.5822570323944092, + "learning_rate": 1.1310142116394506e-05, + "loss": 1.7124, + "step": 14092 + }, + { + "epoch": 0.7855192018282147, + "grad_norm": 0.5885120630264282, + "learning_rate": 1.1304502488646513e-05, + "loss": 1.7282, + "step": 14093 + }, + { + "epoch": 0.7855749400813778, + "grad_norm": 0.5187118649482727, + "learning_rate": 1.1298864088094058e-05, + "loss": 1.3171, + "step": 14094 + }, + { + "epoch": 0.785630678334541, + "grad_norm": 0.5518853068351746, + "learning_rate": 1.1293226914916006e-05, + "loss": 1.52, + "step": 14095 + }, + { + "epoch": 0.7856864165877041, + "grad_norm": 0.5994083285331726, + "learning_rate": 1.128759096929114e-05, + "loss": 1.6558, + "step": 14096 + }, + { + "epoch": 0.7857421548408673, + "grad_norm": 0.5273770689964294, + "learning_rate": 1.1281956251398157e-05, + "loss": 1.6298, + "step": 14097 + }, + { + "epoch": 0.7857978930940305, + "grad_norm": 0.5608893036842346, + "learning_rate": 1.1276322761415786e-05, + "loss": 1.4396, + "step": 14098 + }, + { + "epoch": 0.7858536313471935, + "grad_norm": 0.6453974843025208, + "learning_rate": 1.127069049952268e-05, + "loss": 2.072, + "step": 14099 + }, + { + "epoch": 0.7859093696003567, + "grad_norm": 0.5457696914672852, + "learning_rate": 1.1265059465897465e-05, + "loss": 1.6547, + "step": 14100 + }, + { + "epoch": 0.7859651078535199, + "grad_norm": 0.5690119862556458, + "learning_rate": 1.1259429660718723e-05, + "loss": 1.6223, + "step": 14101 + }, + { + "epoch": 0.786020846106683, + "grad_norm": 0.5498533248901367, + "learning_rate": 1.1253801084164995e-05, + "loss": 1.632, + "step": 14102 + }, + { + "epoch": 0.7860765843598462, + "grad_norm": 0.6033128499984741, + "learning_rate": 1.1248173736414808e-05, + "loss": 1.7907, + "step": 14103 + }, + { + "epoch": 0.7861323226130094, + "grad_norm": 0.5408663749694824, + "learning_rate": 1.1242547617646598e-05, + "loss": 1.7747, + "step": 14104 + }, + { + "epoch": 0.7861880608661724, + "grad_norm": 0.556079089641571, + "learning_rate": 1.1236922728038807e-05, + "loss": 1.5891, + "step": 14105 + }, + { + "epoch": 0.7862437991193356, + "grad_norm": 0.5124304890632629, + "learning_rate": 1.1231299067769818e-05, + "loss": 1.5138, + "step": 14106 + }, + { + "epoch": 0.7862995373724987, + "grad_norm": 0.551034152507782, + "learning_rate": 1.122567663701799e-05, + "loss": 1.5725, + "step": 14107 + }, + { + "epoch": 0.7863552756256619, + "grad_norm": 0.5727046728134155, + "learning_rate": 1.122005543596164e-05, + "loss": 1.8054, + "step": 14108 + }, + { + "epoch": 0.7864110138788251, + "grad_norm": 0.5518726706504822, + "learning_rate": 1.1214435464779006e-05, + "loss": 1.6492, + "step": 14109 + }, + { + "epoch": 0.7864667521319881, + "grad_norm": 0.530637264251709, + "learning_rate": 1.1208816723648364e-05, + "loss": 1.5806, + "step": 14110 + }, + { + "epoch": 0.7865224903851513, + "grad_norm": 0.5481143593788147, + "learning_rate": 1.1203199212747878e-05, + "loss": 1.691, + "step": 14111 + }, + { + "epoch": 0.7865782286383145, + "grad_norm": 0.5416361689567566, + "learning_rate": 1.1197582932255712e-05, + "loss": 1.7296, + "step": 14112 + }, + { + "epoch": 0.7866339668914776, + "grad_norm": 0.577296793460846, + "learning_rate": 1.119196788234998e-05, + "loss": 1.5213, + "step": 14113 + }, + { + "epoch": 0.7866897051446408, + "grad_norm": 0.5732555985450745, + "learning_rate": 1.1186354063208759e-05, + "loss": 1.6295, + "step": 14114 + }, + { + "epoch": 0.786745443397804, + "grad_norm": 0.525271475315094, + "learning_rate": 1.1180741475010104e-05, + "loss": 1.5283, + "step": 14115 + }, + { + "epoch": 0.786801181650967, + "grad_norm": 0.5291435718536377, + "learning_rate": 1.1175130117931987e-05, + "loss": 1.3781, + "step": 14116 + }, + { + "epoch": 0.7868569199041302, + "grad_norm": 0.5415179133415222, + "learning_rate": 1.1169519992152372e-05, + "loss": 1.554, + "step": 14117 + }, + { + "epoch": 0.7869126581572934, + "grad_norm": 0.567564070224762, + "learning_rate": 1.1163911097849189e-05, + "loss": 1.5795, + "step": 14118 + }, + { + "epoch": 0.7869683964104565, + "grad_norm": 0.5729326009750366, + "learning_rate": 1.1158303435200324e-05, + "loss": 1.7236, + "step": 14119 + }, + { + "epoch": 0.7870241346636196, + "grad_norm": 0.5714365243911743, + "learning_rate": 1.115269700438359e-05, + "loss": 1.7392, + "step": 14120 + }, + { + "epoch": 0.7870798729167828, + "grad_norm": 0.5530888438224792, + "learning_rate": 1.114709180557682e-05, + "loss": 1.6407, + "step": 14121 + }, + { + "epoch": 0.7871356111699459, + "grad_norm": 0.5813184380531311, + "learning_rate": 1.1141487838957787e-05, + "loss": 1.6539, + "step": 14122 + }, + { + "epoch": 0.7871913494231091, + "grad_norm": 0.573197066783905, + "learning_rate": 1.1135885104704186e-05, + "loss": 1.3411, + "step": 14123 + }, + { + "epoch": 0.7872470876762723, + "grad_norm": 0.5426301956176758, + "learning_rate": 1.1130283602993718e-05, + "loss": 1.6036, + "step": 14124 + }, + { + "epoch": 0.7873028259294353, + "grad_norm": 0.5949573516845703, + "learning_rate": 1.1124683334004021e-05, + "loss": 1.8074, + "step": 14125 + }, + { + "epoch": 0.7873585641825985, + "grad_norm": 0.587485134601593, + "learning_rate": 1.1119084297912729e-05, + "loss": 1.893, + "step": 14126 + }, + { + "epoch": 0.7874143024357617, + "grad_norm": 0.5607683062553406, + "learning_rate": 1.1113486494897363e-05, + "loss": 1.5241, + "step": 14127 + }, + { + "epoch": 0.7874700406889248, + "grad_norm": 0.533374547958374, + "learning_rate": 1.1107889925135495e-05, + "loss": 1.4693, + "step": 14128 + }, + { + "epoch": 0.787525778942088, + "grad_norm": 0.6041263341903687, + "learning_rate": 1.1102294588804613e-05, + "loss": 1.8778, + "step": 14129 + }, + { + "epoch": 0.787581517195251, + "grad_norm": 0.5453782081604004, + "learning_rate": 1.1096700486082146e-05, + "loss": 1.5998, + "step": 14130 + }, + { + "epoch": 0.7876372554484142, + "grad_norm": 0.5560128688812256, + "learning_rate": 1.1091107617145519e-05, + "loss": 1.473, + "step": 14131 + }, + { + "epoch": 0.7876929937015774, + "grad_norm": 0.5424692630767822, + "learning_rate": 1.10855159821721e-05, + "loss": 1.4516, + "step": 14132 + }, + { + "epoch": 0.7877487319547405, + "grad_norm": 0.5891462564468384, + "learning_rate": 1.1079925581339229e-05, + "loss": 1.8915, + "step": 14133 + }, + { + "epoch": 0.7878044702079037, + "grad_norm": 0.5774295330047607, + "learning_rate": 1.1074336414824215e-05, + "loss": 1.5509, + "step": 14134 + }, + { + "epoch": 0.7878602084610669, + "grad_norm": 0.5502496957778931, + "learning_rate": 1.1068748482804264e-05, + "loss": 1.4576, + "step": 14135 + }, + { + "epoch": 0.7879159467142299, + "grad_norm": 0.5660259127616882, + "learning_rate": 1.106316178545666e-05, + "loss": 1.8418, + "step": 14136 + }, + { + "epoch": 0.7879716849673931, + "grad_norm": 0.5616737604141235, + "learning_rate": 1.105757632295853e-05, + "loss": 1.6923, + "step": 14137 + }, + { + "epoch": 0.7880274232205563, + "grad_norm": 0.559689998626709, + "learning_rate": 1.1051992095487029e-05, + "loss": 1.6677, + "step": 14138 + }, + { + "epoch": 0.7880831614737194, + "grad_norm": 0.6023997664451599, + "learning_rate": 1.1046409103219251e-05, + "loss": 2.0795, + "step": 14139 + }, + { + "epoch": 0.7881388997268826, + "grad_norm": 0.5657042264938354, + "learning_rate": 1.1040827346332272e-05, + "loss": 1.572, + "step": 14140 + }, + { + "epoch": 0.7881946379800457, + "grad_norm": 0.5904360413551331, + "learning_rate": 1.103524682500311e-05, + "loss": 1.7121, + "step": 14141 + }, + { + "epoch": 0.7882503762332088, + "grad_norm": 0.6427820920944214, + "learning_rate": 1.1029667539408723e-05, + "loss": 1.8675, + "step": 14142 + }, + { + "epoch": 0.788306114486372, + "grad_norm": 0.5739613771438599, + "learning_rate": 1.102408948972607e-05, + "loss": 1.7795, + "step": 14143 + }, + { + "epoch": 0.7883618527395352, + "grad_norm": 0.5235968232154846, + "learning_rate": 1.1018512676132054e-05, + "loss": 1.3756, + "step": 14144 + }, + { + "epoch": 0.7884175909926983, + "grad_norm": 0.5444537997245789, + "learning_rate": 1.101293709880355e-05, + "loss": 1.5751, + "step": 14145 + }, + { + "epoch": 0.7884733292458614, + "grad_norm": 0.5618844628334045, + "learning_rate": 1.1007362757917344e-05, + "loss": 1.5829, + "step": 14146 + }, + { + "epoch": 0.7885290674990246, + "grad_norm": 0.5503376722335815, + "learning_rate": 1.1001789653650264e-05, + "loss": 1.6555, + "step": 14147 + }, + { + "epoch": 0.7885848057521877, + "grad_norm": 0.5950319170951843, + "learning_rate": 1.0996217786179052e-05, + "loss": 1.8102, + "step": 14148 + }, + { + "epoch": 0.7886405440053509, + "grad_norm": 0.5576203465461731, + "learning_rate": 1.099064715568039e-05, + "loss": 1.6791, + "step": 14149 + }, + { + "epoch": 0.7886962822585141, + "grad_norm": 0.569321870803833, + "learning_rate": 1.0985077762330963e-05, + "loss": 1.6076, + "step": 14150 + }, + { + "epoch": 0.7887520205116771, + "grad_norm": 0.5832285284996033, + "learning_rate": 1.0979509606307398e-05, + "loss": 1.6604, + "step": 14151 + }, + { + "epoch": 0.7888077587648403, + "grad_norm": 0.5698609948158264, + "learning_rate": 1.0973942687786293e-05, + "loss": 1.588, + "step": 14152 + }, + { + "epoch": 0.7888634970180034, + "grad_norm": 0.5445098876953125, + "learning_rate": 1.0968377006944158e-05, + "loss": 1.4434, + "step": 14153 + }, + { + "epoch": 0.7889192352711666, + "grad_norm": 0.5489819645881653, + "learning_rate": 1.0962812563957552e-05, + "loss": 1.5954, + "step": 14154 + }, + { + "epoch": 0.7889749735243298, + "grad_norm": 0.5446029901504517, + "learning_rate": 1.095724935900294e-05, + "loss": 1.359, + "step": 14155 + }, + { + "epoch": 0.7890307117774928, + "grad_norm": 0.5374274849891663, + "learning_rate": 1.0951687392256738e-05, + "loss": 1.5071, + "step": 14156 + }, + { + "epoch": 0.789086450030656, + "grad_norm": 0.5869937539100647, + "learning_rate": 1.0946126663895335e-05, + "loss": 1.7058, + "step": 14157 + }, + { + "epoch": 0.7891421882838192, + "grad_norm": 0.549609899520874, + "learning_rate": 1.0940567174095101e-05, + "loss": 1.6391, + "step": 14158 + }, + { + "epoch": 0.7891979265369823, + "grad_norm": 0.5412814617156982, + "learning_rate": 1.0935008923032336e-05, + "loss": 1.3799, + "step": 14159 + }, + { + "epoch": 0.7892536647901455, + "grad_norm": 0.5886615514755249, + "learning_rate": 1.0929451910883343e-05, + "loss": 1.5895, + "step": 14160 + }, + { + "epoch": 0.7893094030433087, + "grad_norm": 0.559424638748169, + "learning_rate": 1.0923896137824308e-05, + "loss": 1.3587, + "step": 14161 + }, + { + "epoch": 0.7893651412964717, + "grad_norm": 0.6307703256607056, + "learning_rate": 1.0918341604031491e-05, + "loss": 1.6722, + "step": 14162 + }, + { + "epoch": 0.7894208795496349, + "grad_norm": 0.5167428255081177, + "learning_rate": 1.0912788309680999e-05, + "loss": 1.3863, + "step": 14163 + }, + { + "epoch": 0.7894766178027981, + "grad_norm": 0.5647063851356506, + "learning_rate": 1.0907236254948967e-05, + "loss": 1.6009, + "step": 14164 + }, + { + "epoch": 0.7895323560559612, + "grad_norm": 0.5547575354576111, + "learning_rate": 1.0901685440011471e-05, + "loss": 1.5707, + "step": 14165 + }, + { + "epoch": 0.7895880943091244, + "grad_norm": 0.5227721333503723, + "learning_rate": 1.089613586504456e-05, + "loss": 1.4619, + "step": 14166 + }, + { + "epoch": 0.7896438325622875, + "grad_norm": 0.5079346895217896, + "learning_rate": 1.0890587530224239e-05, + "loss": 1.5639, + "step": 14167 + }, + { + "epoch": 0.7896995708154506, + "grad_norm": 0.5701187252998352, + "learning_rate": 1.088504043572643e-05, + "loss": 1.7238, + "step": 14168 + }, + { + "epoch": 0.7897553090686138, + "grad_norm": 0.5453519821166992, + "learning_rate": 1.0879494581727112e-05, + "loss": 1.5679, + "step": 14169 + }, + { + "epoch": 0.789811047321777, + "grad_norm": 0.5493216514587402, + "learning_rate": 1.087394996840212e-05, + "loss": 1.6117, + "step": 14170 + }, + { + "epoch": 0.7898667855749401, + "grad_norm": 0.5504185557365417, + "learning_rate": 1.0868406595927327e-05, + "loss": 1.5702, + "step": 14171 + }, + { + "epoch": 0.7899225238281032, + "grad_norm": 0.5828469395637512, + "learning_rate": 1.0862864464478501e-05, + "loss": 1.8501, + "step": 14172 + }, + { + "epoch": 0.7899782620812664, + "grad_norm": 0.5702177882194519, + "learning_rate": 1.0857323574231443e-05, + "loss": 1.7125, + "step": 14173 + }, + { + "epoch": 0.7900340003344295, + "grad_norm": 0.6009947061538696, + "learning_rate": 1.0851783925361875e-05, + "loss": 1.8166, + "step": 14174 + }, + { + "epoch": 0.7900897385875927, + "grad_norm": 0.5664753317832947, + "learning_rate": 1.0846245518045457e-05, + "loss": 1.5777, + "step": 14175 + }, + { + "epoch": 0.7901454768407558, + "grad_norm": 0.5617591738700867, + "learning_rate": 1.0840708352457851e-05, + "loss": 1.8449, + "step": 14176 + }, + { + "epoch": 0.7902012150939189, + "grad_norm": 0.5748462080955505, + "learning_rate": 1.0835172428774659e-05, + "loss": 1.8072, + "step": 14177 + }, + { + "epoch": 0.7902569533470821, + "grad_norm": 0.5637654066085815, + "learning_rate": 1.0829637747171468e-05, + "loss": 1.4591, + "step": 14178 + }, + { + "epoch": 0.7903126916002452, + "grad_norm": 0.5314264297485352, + "learning_rate": 1.0824104307823756e-05, + "loss": 1.5205, + "step": 14179 + }, + { + "epoch": 0.7903684298534084, + "grad_norm": 0.5520778894424438, + "learning_rate": 1.081857211090706e-05, + "loss": 1.5751, + "step": 14180 + }, + { + "epoch": 0.7904241681065716, + "grad_norm": 0.5554165244102478, + "learning_rate": 1.0813041156596826e-05, + "loss": 1.445, + "step": 14181 + }, + { + "epoch": 0.7904799063597346, + "grad_norm": 0.5123404264450073, + "learning_rate": 1.080751144506844e-05, + "loss": 1.3204, + "step": 14182 + }, + { + "epoch": 0.7905356446128978, + "grad_norm": 0.5553086400032043, + "learning_rate": 1.0801982976497283e-05, + "loss": 1.6754, + "step": 14183 + }, + { + "epoch": 0.790591382866061, + "grad_norm": 0.6091317534446716, + "learning_rate": 1.0796455751058682e-05, + "loss": 1.685, + "step": 14184 + }, + { + "epoch": 0.7906471211192241, + "grad_norm": 0.5874457955360413, + "learning_rate": 1.0790929768927932e-05, + "loss": 1.6895, + "step": 14185 + }, + { + "epoch": 0.7907028593723873, + "grad_norm": 0.5442774295806885, + "learning_rate": 1.0785405030280305e-05, + "loss": 1.512, + "step": 14186 + }, + { + "epoch": 0.7907585976255505, + "grad_norm": 0.5660844445228577, + "learning_rate": 1.077988153529096e-05, + "loss": 1.6243, + "step": 14187 + }, + { + "epoch": 0.7908143358787135, + "grad_norm": 0.5658431649208069, + "learning_rate": 1.0774359284135133e-05, + "loss": 1.5732, + "step": 14188 + }, + { + "epoch": 0.7908700741318767, + "grad_norm": 0.5881638526916504, + "learning_rate": 1.0768838276987914e-05, + "loss": 1.7611, + "step": 14189 + }, + { + "epoch": 0.7909258123850399, + "grad_norm": 0.5711503624916077, + "learning_rate": 1.0763318514024412e-05, + "loss": 1.5442, + "step": 14190 + }, + { + "epoch": 0.790981550638203, + "grad_norm": 0.5731552243232727, + "learning_rate": 1.0757799995419677e-05, + "loss": 1.7336, + "step": 14191 + }, + { + "epoch": 0.7910372888913662, + "grad_norm": 0.5885837078094482, + "learning_rate": 1.0752282721348733e-05, + "loss": 1.794, + "step": 14192 + }, + { + "epoch": 0.7910930271445293, + "grad_norm": 0.5574288368225098, + "learning_rate": 1.0746766691986565e-05, + "loss": 1.7035, + "step": 14193 + }, + { + "epoch": 0.7911487653976924, + "grad_norm": 0.5461791753768921, + "learning_rate": 1.0741251907508065e-05, + "loss": 1.5022, + "step": 14194 + }, + { + "epoch": 0.7912045036508556, + "grad_norm": 0.5729514360427856, + "learning_rate": 1.0735738368088188e-05, + "loss": 1.6407, + "step": 14195 + }, + { + "epoch": 0.7912602419040188, + "grad_norm": 0.5560081005096436, + "learning_rate": 1.073022607390175e-05, + "loss": 1.5304, + "step": 14196 + }, + { + "epoch": 0.7913159801571819, + "grad_norm": 0.6013069748878479, + "learning_rate": 1.0724715025123599e-05, + "loss": 1.6339, + "step": 14197 + }, + { + "epoch": 0.791371718410345, + "grad_norm": 0.5798637866973877, + "learning_rate": 1.0719205221928464e-05, + "loss": 1.7463, + "step": 14198 + }, + { + "epoch": 0.7914274566635081, + "grad_norm": 0.5300682187080383, + "learning_rate": 1.0713696664491134e-05, + "loss": 1.5111, + "step": 14199 + }, + { + "epoch": 0.7914831949166713, + "grad_norm": 0.5579528212547302, + "learning_rate": 1.0708189352986304e-05, + "loss": 1.5489, + "step": 14200 + }, + { + "epoch": 0.7915389331698345, + "grad_norm": 0.5883510112762451, + "learning_rate": 1.0702683287588606e-05, + "loss": 1.7422, + "step": 14201 + }, + { + "epoch": 0.7915946714229976, + "grad_norm": 0.5935243964195251, + "learning_rate": 1.0697178468472674e-05, + "loss": 1.6753, + "step": 14202 + }, + { + "epoch": 0.7916504096761607, + "grad_norm": 0.5785866379737854, + "learning_rate": 1.0691674895813092e-05, + "loss": 1.5724, + "step": 14203 + }, + { + "epoch": 0.7917061479293239, + "grad_norm": 0.5762687921524048, + "learning_rate": 1.0686172569784415e-05, + "loss": 1.6701, + "step": 14204 + }, + { + "epoch": 0.791761886182487, + "grad_norm": 0.5559493899345398, + "learning_rate": 1.0680671490561095e-05, + "loss": 1.6701, + "step": 14205 + }, + { + "epoch": 0.7918176244356502, + "grad_norm": 0.571079432964325, + "learning_rate": 1.0675171658317645e-05, + "loss": 1.6881, + "step": 14206 + }, + { + "epoch": 0.7918733626888134, + "grad_norm": 0.5778709053993225, + "learning_rate": 1.0669673073228482e-05, + "loss": 1.7261, + "step": 14207 + }, + { + "epoch": 0.7919291009419764, + "grad_norm": 0.6055009961128235, + "learning_rate": 1.0664175735467963e-05, + "loss": 1.8894, + "step": 14208 + }, + { + "epoch": 0.7919848391951396, + "grad_norm": 0.541527509689331, + "learning_rate": 1.0658679645210445e-05, + "loss": 1.4879, + "step": 14209 + }, + { + "epoch": 0.7920405774483028, + "grad_norm": 0.5720058679580688, + "learning_rate": 1.065318480263024e-05, + "loss": 1.7824, + "step": 14210 + }, + { + "epoch": 0.7920963157014659, + "grad_norm": 0.5170486569404602, + "learning_rate": 1.06476912079016e-05, + "loss": 1.4463, + "step": 14211 + }, + { + "epoch": 0.7921520539546291, + "grad_norm": 0.5375114679336548, + "learning_rate": 1.0642198861198771e-05, + "loss": 1.6579, + "step": 14212 + }, + { + "epoch": 0.7922077922077922, + "grad_norm": 0.5250227451324463, + "learning_rate": 1.0636707762695891e-05, + "loss": 1.6839, + "step": 14213 + }, + { + "epoch": 0.7922635304609553, + "grad_norm": 0.5751910209655762, + "learning_rate": 1.0631217912567165e-05, + "loss": 1.7319, + "step": 14214 + }, + { + "epoch": 0.7923192687141185, + "grad_norm": 0.5820494890213013, + "learning_rate": 1.0625729310986659e-05, + "loss": 1.7223, + "step": 14215 + }, + { + "epoch": 0.7923750069672817, + "grad_norm": 0.6259032487869263, + "learning_rate": 1.0620241958128451e-05, + "loss": 1.6946, + "step": 14216 + }, + { + "epoch": 0.7924307452204448, + "grad_norm": 0.5648552775382996, + "learning_rate": 1.061475585416657e-05, + "loss": 1.7499, + "step": 14217 + }, + { + "epoch": 0.792486483473608, + "grad_norm": 0.5858311653137207, + "learning_rate": 1.0609270999275e-05, + "loss": 1.6454, + "step": 14218 + }, + { + "epoch": 0.7925422217267711, + "grad_norm": 0.5872727632522583, + "learning_rate": 1.0603787393627701e-05, + "loss": 1.7257, + "step": 14219 + }, + { + "epoch": 0.7925979599799342, + "grad_norm": 0.6232999563217163, + "learning_rate": 1.0598305037398543e-05, + "loss": 1.5123, + "step": 14220 + }, + { + "epoch": 0.7926536982330974, + "grad_norm": 0.5462108254432678, + "learning_rate": 1.0592823930761454e-05, + "loss": 1.5896, + "step": 14221 + }, + { + "epoch": 0.7927094364862605, + "grad_norm": 0.5950632691383362, + "learning_rate": 1.0587344073890209e-05, + "loss": 1.6032, + "step": 14222 + }, + { + "epoch": 0.7927651747394237, + "grad_norm": 0.5734551548957825, + "learning_rate": 1.058186546695864e-05, + "loss": 1.685, + "step": 14223 + }, + { + "epoch": 0.7928209129925868, + "grad_norm": 0.5197454690933228, + "learning_rate": 1.0576388110140444e-05, + "loss": 1.4667, + "step": 14224 + }, + { + "epoch": 0.7928766512457499, + "grad_norm": 0.5591278672218323, + "learning_rate": 1.0570912003609374e-05, + "loss": 1.7501, + "step": 14225 + }, + { + "epoch": 0.7929323894989131, + "grad_norm": 0.602046012878418, + "learning_rate": 1.0565437147539104e-05, + "loss": 1.6845, + "step": 14226 + }, + { + "epoch": 0.7929881277520763, + "grad_norm": 0.6184342503547668, + "learning_rate": 1.055996354210323e-05, + "loss": 1.6876, + "step": 14227 + }, + { + "epoch": 0.7930438660052394, + "grad_norm": 0.5796352028846741, + "learning_rate": 1.0554491187475363e-05, + "loss": 1.6564, + "step": 14228 + }, + { + "epoch": 0.7930996042584025, + "grad_norm": 0.5525890588760376, + "learning_rate": 1.0549020083829053e-05, + "loss": 1.5664, + "step": 14229 + }, + { + "epoch": 0.7931553425115657, + "grad_norm": 0.641735315322876, + "learning_rate": 1.0543550231337824e-05, + "loss": 1.6195, + "step": 14230 + }, + { + "epoch": 0.7932110807647288, + "grad_norm": 0.563994288444519, + "learning_rate": 1.0538081630175106e-05, + "loss": 1.8589, + "step": 14231 + }, + { + "epoch": 0.793266819017892, + "grad_norm": 0.5552716851234436, + "learning_rate": 1.0532614280514374e-05, + "loss": 1.5969, + "step": 14232 + }, + { + "epoch": 0.7933225572710552, + "grad_norm": 0.6517505049705505, + "learning_rate": 1.0527148182529023e-05, + "loss": 1.914, + "step": 14233 + }, + { + "epoch": 0.7933782955242182, + "grad_norm": 0.588067352771759, + "learning_rate": 1.0521683336392374e-05, + "loss": 1.5224, + "step": 14234 + }, + { + "epoch": 0.7934340337773814, + "grad_norm": 0.5851812958717346, + "learning_rate": 1.0516219742277755e-05, + "loss": 1.7211, + "step": 14235 + }, + { + "epoch": 0.7934897720305446, + "grad_norm": 0.5404538512229919, + "learning_rate": 1.051075740035844e-05, + "loss": 1.193, + "step": 14236 + }, + { + "epoch": 0.7935455102837077, + "grad_norm": 0.625626266002655, + "learning_rate": 1.050529631080766e-05, + "loss": 1.7133, + "step": 14237 + }, + { + "epoch": 0.7936012485368709, + "grad_norm": 0.5095002055168152, + "learning_rate": 1.0499836473798624e-05, + "loss": 1.4363, + "step": 14238 + }, + { + "epoch": 0.793656986790034, + "grad_norm": 0.5581433773040771, + "learning_rate": 1.0494377889504448e-05, + "loss": 1.4707, + "step": 14239 + }, + { + "epoch": 0.7937127250431971, + "grad_norm": 0.5656692981719971, + "learning_rate": 1.0488920558098298e-05, + "loss": 1.5554, + "step": 14240 + }, + { + "epoch": 0.7937684632963603, + "grad_norm": 0.5666208267211914, + "learning_rate": 1.0483464479753207e-05, + "loss": 1.7977, + "step": 14241 + }, + { + "epoch": 0.7938242015495235, + "grad_norm": 0.525331437587738, + "learning_rate": 1.0478009654642229e-05, + "loss": 1.5221, + "step": 14242 + }, + { + "epoch": 0.7938799398026866, + "grad_norm": 0.5352795124053955, + "learning_rate": 1.047255608293835e-05, + "loss": 1.4287, + "step": 14243 + }, + { + "epoch": 0.7939356780558497, + "grad_norm": 0.5808674693107605, + "learning_rate": 1.0467103764814534e-05, + "loss": 1.5659, + "step": 14244 + }, + { + "epoch": 0.7939914163090128, + "grad_norm": 0.7119161486625671, + "learning_rate": 1.0461652700443708e-05, + "loss": 1.8926, + "step": 14245 + }, + { + "epoch": 0.794047154562176, + "grad_norm": 0.5350673198699951, + "learning_rate": 1.0456202889998706e-05, + "loss": 1.5393, + "step": 14246 + }, + { + "epoch": 0.7941028928153392, + "grad_norm": 0.5706144571304321, + "learning_rate": 1.0450754333652423e-05, + "loss": 1.7159, + "step": 14247 + }, + { + "epoch": 0.7941586310685023, + "grad_norm": 0.5782610774040222, + "learning_rate": 1.0445307031577606e-05, + "loss": 1.7552, + "step": 14248 + }, + { + "epoch": 0.7942143693216654, + "grad_norm": 0.5863004326820374, + "learning_rate": 1.0439860983947031e-05, + "loss": 1.7994, + "step": 14249 + }, + { + "epoch": 0.7942701075748286, + "grad_norm": 0.5793316960334778, + "learning_rate": 1.0434416190933415e-05, + "loss": 1.6273, + "step": 14250 + }, + { + "epoch": 0.7943258458279917, + "grad_norm": 0.5680450797080994, + "learning_rate": 1.0428972652709435e-05, + "loss": 1.7099, + "step": 14251 + }, + { + "epoch": 0.7943815840811549, + "grad_norm": 0.5190421342849731, + "learning_rate": 1.0423530369447736e-05, + "loss": 1.4654, + "step": 14252 + }, + { + "epoch": 0.7944373223343181, + "grad_norm": 0.6031879186630249, + "learning_rate": 1.0418089341320902e-05, + "loss": 1.4411, + "step": 14253 + }, + { + "epoch": 0.7944930605874811, + "grad_norm": 0.5635674595832825, + "learning_rate": 1.0412649568501487e-05, + "loss": 1.6224, + "step": 14254 + }, + { + "epoch": 0.7945487988406443, + "grad_norm": 0.56245356798172, + "learning_rate": 1.0407211051162024e-05, + "loss": 1.5888, + "step": 14255 + }, + { + "epoch": 0.7946045370938075, + "grad_norm": 0.5387111902236938, + "learning_rate": 1.0401773789474994e-05, + "loss": 1.6535, + "step": 14256 + }, + { + "epoch": 0.7946602753469706, + "grad_norm": 0.5577722191810608, + "learning_rate": 1.0396337783612797e-05, + "loss": 1.4711, + "step": 14257 + }, + { + "epoch": 0.7947160136001338, + "grad_norm": 0.6203587651252747, + "learning_rate": 1.0390903033747879e-05, + "loss": 1.838, + "step": 14258 + }, + { + "epoch": 0.794771751853297, + "grad_norm": 0.5994099378585815, + "learning_rate": 1.0385469540052589e-05, + "loss": 1.7793, + "step": 14259 + }, + { + "epoch": 0.79482749010646, + "grad_norm": 0.5388332009315491, + "learning_rate": 1.0380037302699225e-05, + "loss": 1.6085, + "step": 14260 + }, + { + "epoch": 0.7948832283596232, + "grad_norm": 0.5807412266731262, + "learning_rate": 1.0374606321860076e-05, + "loss": 1.8404, + "step": 14261 + }, + { + "epoch": 0.7949389666127864, + "grad_norm": 0.5289828777313232, + "learning_rate": 1.0369176597707386e-05, + "loss": 1.4937, + "step": 14262 + }, + { + "epoch": 0.7949947048659495, + "grad_norm": 0.5667517781257629, + "learning_rate": 1.0363748130413358e-05, + "loss": 1.7009, + "step": 14263 + }, + { + "epoch": 0.7950504431191127, + "grad_norm": 0.5320255160331726, + "learning_rate": 1.0358320920150132e-05, + "loss": 1.5766, + "step": 14264 + }, + { + "epoch": 0.7951061813722758, + "grad_norm": 0.5835577845573425, + "learning_rate": 1.0352894967089833e-05, + "loss": 1.6995, + "step": 14265 + }, + { + "epoch": 0.7951619196254389, + "grad_norm": 0.6064572334289551, + "learning_rate": 1.0347470271404569e-05, + "loss": 1.7647, + "step": 14266 + }, + { + "epoch": 0.7952176578786021, + "grad_norm": 0.5594108700752258, + "learning_rate": 1.0342046833266339e-05, + "loss": 1.3858, + "step": 14267 + }, + { + "epoch": 0.7952733961317652, + "grad_norm": 0.5946968793869019, + "learning_rate": 1.033662465284717e-05, + "loss": 1.7127, + "step": 14268 + }, + { + "epoch": 0.7953291343849284, + "grad_norm": 0.5593485236167908, + "learning_rate": 1.033120373031901e-05, + "loss": 1.5011, + "step": 14269 + }, + { + "epoch": 0.7953848726380915, + "grad_norm": 0.5262752771377563, + "learning_rate": 1.0325784065853783e-05, + "loss": 1.5378, + "step": 14270 + }, + { + "epoch": 0.7954406108912546, + "grad_norm": 0.5922139883041382, + "learning_rate": 1.0320365659623377e-05, + "loss": 1.7753, + "step": 14271 + }, + { + "epoch": 0.7954963491444178, + "grad_norm": 0.5745583176612854, + "learning_rate": 1.0314948511799605e-05, + "loss": 1.7533, + "step": 14272 + }, + { + "epoch": 0.795552087397581, + "grad_norm": 0.608664870262146, + "learning_rate": 1.0309532622554308e-05, + "loss": 1.7726, + "step": 14273 + }, + { + "epoch": 0.7956078256507441, + "grad_norm": 0.5508156418800354, + "learning_rate": 1.0304117992059215e-05, + "loss": 1.7032, + "step": 14274 + }, + { + "epoch": 0.7956635639039072, + "grad_norm": 0.5590789318084717, + "learning_rate": 1.0298704620486055e-05, + "loss": 1.648, + "step": 14275 + }, + { + "epoch": 0.7957193021570704, + "grad_norm": 0.6094940304756165, + "learning_rate": 1.0293292508006507e-05, + "loss": 1.8069, + "step": 14276 + }, + { + "epoch": 0.7957750404102335, + "grad_norm": 0.5808109045028687, + "learning_rate": 1.028788165479222e-05, + "loss": 1.643, + "step": 14277 + }, + { + "epoch": 0.7958307786633967, + "grad_norm": 0.5147292613983154, + "learning_rate": 1.0282472061014797e-05, + "loss": 1.4351, + "step": 14278 + }, + { + "epoch": 0.7958865169165599, + "grad_norm": 0.5710453391075134, + "learning_rate": 1.0277063726845781e-05, + "loss": 1.6967, + "step": 14279 + }, + { + "epoch": 0.795942255169723, + "grad_norm": 0.5748862624168396, + "learning_rate": 1.02716566524567e-05, + "loss": 1.7828, + "step": 14280 + }, + { + "epoch": 0.7959979934228861, + "grad_norm": 0.5527694225311279, + "learning_rate": 1.0266250838019036e-05, + "loss": 1.5625, + "step": 14281 + }, + { + "epoch": 0.7960537316760493, + "grad_norm": 0.558049738407135, + "learning_rate": 1.026084628370425e-05, + "loss": 1.607, + "step": 14282 + }, + { + "epoch": 0.7961094699292124, + "grad_norm": 0.6232607364654541, + "learning_rate": 1.0255442989683694e-05, + "loss": 1.8911, + "step": 14283 + }, + { + "epoch": 0.7961652081823756, + "grad_norm": 0.598755419254303, + "learning_rate": 1.0250040956128776e-05, + "loss": 1.6691, + "step": 14284 + }, + { + "epoch": 0.7962209464355388, + "grad_norm": 0.5317803025245667, + "learning_rate": 1.0244640183210814e-05, + "loss": 1.6303, + "step": 14285 + }, + { + "epoch": 0.7962766846887018, + "grad_norm": 0.5924306511878967, + "learning_rate": 1.0239240671101063e-05, + "loss": 1.7553, + "step": 14286 + }, + { + "epoch": 0.796332422941865, + "grad_norm": 0.5458486676216125, + "learning_rate": 1.0233842419970773e-05, + "loss": 1.58, + "step": 14287 + }, + { + "epoch": 0.7963881611950282, + "grad_norm": 0.5232000350952148, + "learning_rate": 1.0228445429991151e-05, + "loss": 1.5677, + "step": 14288 + }, + { + "epoch": 0.7964438994481913, + "grad_norm": 0.6367863416671753, + "learning_rate": 1.0223049701333371e-05, + "loss": 1.8649, + "step": 14289 + }, + { + "epoch": 0.7964996377013545, + "grad_norm": 0.5690382719039917, + "learning_rate": 1.0217655234168522e-05, + "loss": 1.7821, + "step": 14290 + }, + { + "epoch": 0.7965553759545175, + "grad_norm": 0.591062605381012, + "learning_rate": 1.0212262028667686e-05, + "loss": 1.7406, + "step": 14291 + }, + { + "epoch": 0.7966111142076807, + "grad_norm": 0.5326418876647949, + "learning_rate": 1.0206870085001952e-05, + "loss": 1.6126, + "step": 14292 + }, + { + "epoch": 0.7966668524608439, + "grad_norm": 0.5550294518470764, + "learning_rate": 1.0201479403342273e-05, + "loss": 1.5392, + "step": 14293 + }, + { + "epoch": 0.796722590714007, + "grad_norm": 0.5567722916603088, + "learning_rate": 1.0196089983859624e-05, + "loss": 1.4339, + "step": 14294 + }, + { + "epoch": 0.7967783289671702, + "grad_norm": 0.5251907110214233, + "learning_rate": 1.0190701826724929e-05, + "loss": 1.6336, + "step": 14295 + }, + { + "epoch": 0.7968340672203333, + "grad_norm": 0.5811560750007629, + "learning_rate": 1.0185314932109069e-05, + "loss": 1.5615, + "step": 14296 + }, + { + "epoch": 0.7968898054734964, + "grad_norm": 0.5523189306259155, + "learning_rate": 1.01799293001829e-05, + "loss": 1.4878, + "step": 14297 + }, + { + "epoch": 0.7969455437266596, + "grad_norm": 0.5699687004089355, + "learning_rate": 1.0174544931117175e-05, + "loss": 1.6865, + "step": 14298 + }, + { + "epoch": 0.7970012819798228, + "grad_norm": 0.5722973942756653, + "learning_rate": 1.0169161825082718e-05, + "loss": 1.6865, + "step": 14299 + }, + { + "epoch": 0.7970570202329859, + "grad_norm": 0.5504626631736755, + "learning_rate": 1.0163779982250199e-05, + "loss": 1.6237, + "step": 14300 + }, + { + "epoch": 0.797112758486149, + "grad_norm": 0.6280822157859802, + "learning_rate": 1.015839940279032e-05, + "loss": 1.7827, + "step": 14301 + }, + { + "epoch": 0.7971684967393122, + "grad_norm": 0.6179702281951904, + "learning_rate": 1.015302008687372e-05, + "loss": 1.4354, + "step": 14302 + }, + { + "epoch": 0.7972242349924753, + "grad_norm": 0.5778931975364685, + "learning_rate": 1.0147642034670996e-05, + "loss": 1.6831, + "step": 14303 + }, + { + "epoch": 0.7972799732456385, + "grad_norm": 0.5538243055343628, + "learning_rate": 1.0142265246352728e-05, + "loss": 1.7572, + "step": 14304 + }, + { + "epoch": 0.7973357114988017, + "grad_norm": 0.5653696656227112, + "learning_rate": 1.0136889722089404e-05, + "loss": 1.6094, + "step": 14305 + }, + { + "epoch": 0.7973914497519647, + "grad_norm": 0.6097986698150635, + "learning_rate": 1.0131515462051521e-05, + "loss": 1.9664, + "step": 14306 + }, + { + "epoch": 0.7974471880051279, + "grad_norm": 0.573856770992279, + "learning_rate": 1.0126142466409517e-05, + "loss": 1.7449, + "step": 14307 + }, + { + "epoch": 0.7975029262582911, + "grad_norm": 0.5199556946754456, + "learning_rate": 1.0120770735333807e-05, + "loss": 1.4495, + "step": 14308 + }, + { + "epoch": 0.7975586645114542, + "grad_norm": 0.5416279435157776, + "learning_rate": 1.0115400268994713e-05, + "loss": 1.5221, + "step": 14309 + }, + { + "epoch": 0.7976144027646174, + "grad_norm": 0.5629909634590149, + "learning_rate": 1.0110031067562592e-05, + "loss": 1.4912, + "step": 14310 + }, + { + "epoch": 0.7976701410177806, + "grad_norm": 0.5700094699859619, + "learning_rate": 1.010466313120772e-05, + "loss": 1.7532, + "step": 14311 + }, + { + "epoch": 0.7977258792709436, + "grad_norm": 0.5885013937950134, + "learning_rate": 1.0099296460100322e-05, + "loss": 1.7185, + "step": 14312 + }, + { + "epoch": 0.7977816175241068, + "grad_norm": 0.5609301328659058, + "learning_rate": 1.0093931054410594e-05, + "loss": 1.5657, + "step": 14313 + }, + { + "epoch": 0.7978373557772699, + "grad_norm": 0.5494312047958374, + "learning_rate": 1.008856691430871e-05, + "loss": 1.6364, + "step": 14314 + }, + { + "epoch": 0.7978930940304331, + "grad_norm": 0.5229134559631348, + "learning_rate": 1.0083204039964794e-05, + "loss": 1.5217, + "step": 14315 + }, + { + "epoch": 0.7979488322835963, + "grad_norm": 0.573517918586731, + "learning_rate": 1.0077842431548906e-05, + "loss": 1.7008, + "step": 14316 + }, + { + "epoch": 0.7980045705367593, + "grad_norm": 0.5787200927734375, + "learning_rate": 1.0072482089231078e-05, + "loss": 1.5748, + "step": 14317 + }, + { + "epoch": 0.7980603087899225, + "grad_norm": 0.5575430989265442, + "learning_rate": 1.006712301318135e-05, + "loss": 1.6165, + "step": 14318 + }, + { + "epoch": 0.7981160470430857, + "grad_norm": 0.49361756443977356, + "learning_rate": 1.0061765203569639e-05, + "loss": 1.1837, + "step": 14319 + }, + { + "epoch": 0.7981717852962488, + "grad_norm": 0.5558135509490967, + "learning_rate": 1.0056408660565885e-05, + "loss": 1.7098, + "step": 14320 + }, + { + "epoch": 0.798227523549412, + "grad_norm": 0.6294339895248413, + "learning_rate": 1.0051053384339959e-05, + "loss": 1.8916, + "step": 14321 + }, + { + "epoch": 0.7982832618025751, + "grad_norm": 0.544558048248291, + "learning_rate": 1.0045699375061701e-05, + "loss": 1.6068, + "step": 14322 + }, + { + "epoch": 0.7983390000557382, + "grad_norm": 0.6012967228889465, + "learning_rate": 1.0040346632900921e-05, + "loss": 1.5894, + "step": 14323 + }, + { + "epoch": 0.7983947383089014, + "grad_norm": 0.5851178765296936, + "learning_rate": 1.0034995158027343e-05, + "loss": 1.634, + "step": 14324 + }, + { + "epoch": 0.7984504765620646, + "grad_norm": 0.5557059049606323, + "learning_rate": 1.0029644950610728e-05, + "loss": 1.6313, + "step": 14325 + }, + { + "epoch": 0.7985062148152277, + "grad_norm": 0.5574374198913574, + "learning_rate": 1.0024296010820721e-05, + "loss": 1.5917, + "step": 14326 + }, + { + "epoch": 0.7985619530683908, + "grad_norm": 0.5546873807907104, + "learning_rate": 1.0018948338826972e-05, + "loss": 1.6068, + "step": 14327 + }, + { + "epoch": 0.798617691321554, + "grad_norm": 0.5635491013526917, + "learning_rate": 1.0013601934799072e-05, + "loss": 1.7385, + "step": 14328 + }, + { + "epoch": 0.7986734295747171, + "grad_norm": 0.5756046175956726, + "learning_rate": 1.0008256798906585e-05, + "loss": 1.6175, + "step": 14329 + }, + { + "epoch": 0.7987291678278803, + "grad_norm": 0.5956593155860901, + "learning_rate": 1.0002912931319036e-05, + "loss": 1.623, + "step": 14330 + }, + { + "epoch": 0.7987849060810435, + "grad_norm": 0.5440784096717834, + "learning_rate": 9.997570332205875e-06, + "loss": 1.4983, + "step": 14331 + }, + { + "epoch": 0.7988406443342065, + "grad_norm": 0.5485489964485168, + "learning_rate": 9.992229001736553e-06, + "loss": 1.435, + "step": 14332 + }, + { + "epoch": 0.7988963825873697, + "grad_norm": 0.5302622318267822, + "learning_rate": 9.986888940080468e-06, + "loss": 1.4607, + "step": 14333 + }, + { + "epoch": 0.7989521208405329, + "grad_norm": 0.5820941925048828, + "learning_rate": 9.981550147406987e-06, + "loss": 1.556, + "step": 14334 + }, + { + "epoch": 0.799007859093696, + "grad_norm": 0.5871179103851318, + "learning_rate": 9.976212623885384e-06, + "loss": 1.668, + "step": 14335 + }, + { + "epoch": 0.7990635973468592, + "grad_norm": 0.5687511563301086, + "learning_rate": 9.970876369684973e-06, + "loss": 1.6566, + "step": 14336 + }, + { + "epoch": 0.7991193356000222, + "grad_norm": 0.5481507182121277, + "learning_rate": 9.96554138497499e-06, + "loss": 1.2366, + "step": 14337 + }, + { + "epoch": 0.7991750738531854, + "grad_norm": 0.6357203722000122, + "learning_rate": 9.960207669924603e-06, + "loss": 1.916, + "step": 14338 + }, + { + "epoch": 0.7992308121063486, + "grad_norm": NaN, + "learning_rate": 9.960207669924603e-06, + "loss": 1.5393, + "step": 14339 + }, + { + "epoch": 0.7992865503595117, + "grad_norm": 0.5581541657447815, + "learning_rate": 9.954875224702986e-06, + "loss": 1.5587, + "step": 14340 + }, + { + "epoch": 0.7993422886126749, + "grad_norm": 0.5387499332427979, + "learning_rate": 9.949544049479247e-06, + "loss": 1.4697, + "step": 14341 + }, + { + "epoch": 0.799398026865838, + "grad_norm": 0.49244141578674316, + "learning_rate": 9.94421414442247e-06, + "loss": 1.3914, + "step": 14342 + }, + { + "epoch": 0.7994537651190011, + "grad_norm": 0.5456081628799438, + "learning_rate": 9.938885509701657e-06, + "loss": 1.4728, + "step": 14343 + }, + { + "epoch": 0.7995095033721643, + "grad_norm": 0.5390294790267944, + "learning_rate": 9.933558145485833e-06, + "loss": 1.3721, + "step": 14344 + }, + { + "epoch": 0.7995652416253275, + "grad_norm": 0.5985755920410156, + "learning_rate": 9.928232051943953e-06, + "loss": 1.7802, + "step": 14345 + }, + { + "epoch": 0.7996209798784906, + "grad_norm": 0.5658624172210693, + "learning_rate": 9.922907229244904e-06, + "loss": 1.4227, + "step": 14346 + }, + { + "epoch": 0.7996767181316538, + "grad_norm": 0.5901734232902527, + "learning_rate": 9.917583677557574e-06, + "loss": 1.6922, + "step": 14347 + }, + { + "epoch": 0.7997324563848169, + "grad_norm": 0.5785011649131775, + "learning_rate": 9.912261397050792e-06, + "loss": 1.5325, + "step": 14348 + }, + { + "epoch": 0.79978819463798, + "grad_norm": 0.5889132618904114, + "learning_rate": 9.906940387893354e-06, + "loss": 1.7558, + "step": 14349 + }, + { + "epoch": 0.7998439328911432, + "grad_norm": 0.581152617931366, + "learning_rate": 9.901620650254017e-06, + "loss": 1.3819, + "step": 14350 + }, + { + "epoch": 0.7998996711443064, + "grad_norm": 0.548949122428894, + "learning_rate": 9.896302184301465e-06, + "loss": 1.7104, + "step": 14351 + }, + { + "epoch": 0.7999554093974695, + "grad_norm": 0.5606316924095154, + "learning_rate": 9.890984990204404e-06, + "loss": 1.7376, + "step": 14352 + }, + { + "epoch": 0.8000111476506326, + "grad_norm": 0.6483362317085266, + "learning_rate": 9.885669068131437e-06, + "loss": 2.0308, + "step": 14353 + }, + { + "epoch": 0.8000668859037958, + "grad_norm": 0.5594815611839294, + "learning_rate": 9.880354418251165e-06, + "loss": 1.4996, + "step": 14354 + }, + { + "epoch": 0.8001226241569589, + "grad_norm": 0.5642004609107971, + "learning_rate": 9.875041040732136e-06, + "loss": 1.6186, + "step": 14355 + }, + { + "epoch": 0.8001783624101221, + "grad_norm": 0.5526056289672852, + "learning_rate": 9.869728935742862e-06, + "loss": 1.4683, + "step": 14356 + }, + { + "epoch": 0.8002341006632853, + "grad_norm": 0.6208131313323975, + "learning_rate": 9.864418103451828e-06, + "loss": 1.8107, + "step": 14357 + }, + { + "epoch": 0.8002898389164483, + "grad_norm": 0.5653442740440369, + "learning_rate": 9.859108544027423e-06, + "loss": 1.6458, + "step": 14358 + }, + { + "epoch": 0.8003455771696115, + "grad_norm": 0.5809319615364075, + "learning_rate": 9.853800257638063e-06, + "loss": 1.6334, + "step": 14359 + }, + { + "epoch": 0.8004013154227746, + "grad_norm": 0.543079137802124, + "learning_rate": 9.848493244452089e-06, + "loss": 1.6904, + "step": 14360 + }, + { + "epoch": 0.8004570536759378, + "grad_norm": 0.5740684270858765, + "learning_rate": 9.843187504637824e-06, + "loss": 1.6743, + "step": 14361 + }, + { + "epoch": 0.800512791929101, + "grad_norm": 0.5502151846885681, + "learning_rate": 9.837883038363494e-06, + "loss": 1.6923, + "step": 14362 + }, + { + "epoch": 0.800568530182264, + "grad_norm": 0.6467139720916748, + "learning_rate": 9.832579845797362e-06, + "loss": 1.858, + "step": 14363 + }, + { + "epoch": 0.8006242684354272, + "grad_norm": 0.5684570670127869, + "learning_rate": 9.82727792710762e-06, + "loss": 1.6314, + "step": 14364 + }, + { + "epoch": 0.8006800066885904, + "grad_norm": 0.5606323480606079, + "learning_rate": 9.821977282462387e-06, + "loss": 1.5115, + "step": 14365 + }, + { + "epoch": 0.8007357449417535, + "grad_norm": 0.5373196005821228, + "learning_rate": 9.81667791202978e-06, + "loss": 1.5325, + "step": 14366 + }, + { + "epoch": 0.8007914831949167, + "grad_norm": 0.5519532561302185, + "learning_rate": 9.811379815977866e-06, + "loss": 1.4287, + "step": 14367 + }, + { + "epoch": 0.8008472214480798, + "grad_norm": 0.5695307850837708, + "learning_rate": 9.80608299447468e-06, + "loss": 1.7301, + "step": 14368 + }, + { + "epoch": 0.8009029597012429, + "grad_norm": 0.5454866290092468, + "learning_rate": 9.80078744768817e-06, + "loss": 1.4684, + "step": 14369 + }, + { + "epoch": 0.8009586979544061, + "grad_norm": 0.5738468766212463, + "learning_rate": 9.795493175786318e-06, + "loss": 1.6985, + "step": 14370 + }, + { + "epoch": 0.8010144362075693, + "grad_norm": 0.5349743962287903, + "learning_rate": 9.790200178937026e-06, + "loss": 1.5258, + "step": 14371 + }, + { + "epoch": 0.8010701744607324, + "grad_norm": 0.5547036528587341, + "learning_rate": 9.784908457308128e-06, + "loss": 1.6424, + "step": 14372 + }, + { + "epoch": 0.8011259127138955, + "grad_norm": 0.5633455514907837, + "learning_rate": 9.779618011067471e-06, + "loss": 1.5519, + "step": 14373 + }, + { + "epoch": 0.8011816509670587, + "grad_norm": 0.5618358254432678, + "learning_rate": 9.774328840382824e-06, + "loss": 1.5504, + "step": 14374 + }, + { + "epoch": 0.8012373892202218, + "grad_norm": 0.5330274105072021, + "learning_rate": 9.769040945421948e-06, + "loss": 1.5899, + "step": 14375 + }, + { + "epoch": 0.801293127473385, + "grad_norm": 0.5382915735244751, + "learning_rate": 9.76375432635252e-06, + "loss": 1.6959, + "step": 14376 + }, + { + "epoch": 0.8013488657265482, + "grad_norm": 0.541482150554657, + "learning_rate": 9.758468983342194e-06, + "loss": 1.6766, + "step": 14377 + }, + { + "epoch": 0.8014046039797112, + "grad_norm": 0.55217045545578, + "learning_rate": 9.753184916558633e-06, + "loss": 1.4319, + "step": 14378 + }, + { + "epoch": 0.8014603422328744, + "grad_norm": 0.5737308859825134, + "learning_rate": 9.747902126169383e-06, + "loss": 1.8583, + "step": 14379 + }, + { + "epoch": 0.8015160804860376, + "grad_norm": 0.5124214291572571, + "learning_rate": 9.74262061234199e-06, + "loss": 1.4291, + "step": 14380 + }, + { + "epoch": 0.8015718187392007, + "grad_norm": 0.5909250378608704, + "learning_rate": 9.737340375243953e-06, + "loss": 1.6524, + "step": 14381 + }, + { + "epoch": 0.8016275569923639, + "grad_norm": 0.5784448981285095, + "learning_rate": 9.732061415042732e-06, + "loss": 1.7465, + "step": 14382 + }, + { + "epoch": 0.801683295245527, + "grad_norm": 0.5897037982940674, + "learning_rate": 9.726783731905759e-06, + "loss": 1.6151, + "step": 14383 + }, + { + "epoch": 0.8017390334986901, + "grad_norm": 0.5656660795211792, + "learning_rate": 9.721507326000383e-06, + "loss": 1.5089, + "step": 14384 + }, + { + "epoch": 0.8017947717518533, + "grad_norm": 0.5050958395004272, + "learning_rate": 9.716232197493957e-06, + "loss": 1.3962, + "step": 14385 + }, + { + "epoch": 0.8018505100050164, + "grad_norm": 0.5602197647094727, + "learning_rate": 9.710958346553772e-06, + "loss": 1.6131, + "step": 14386 + }, + { + "epoch": 0.8019062482581796, + "grad_norm": 0.5962628722190857, + "learning_rate": 9.705685773347101e-06, + "loss": 1.5955, + "step": 14387 + }, + { + "epoch": 0.8019619865113428, + "grad_norm": 0.5173510313034058, + "learning_rate": 9.70041447804112e-06, + "loss": 1.4416, + "step": 14388 + }, + { + "epoch": 0.8020177247645058, + "grad_norm": 0.5978318452835083, + "learning_rate": 9.69514446080304e-06, + "loss": 1.4565, + "step": 14389 + }, + { + "epoch": 0.802073463017669, + "grad_norm": 0.5639249086380005, + "learning_rate": 9.689875721799995e-06, + "loss": 1.6088, + "step": 14390 + }, + { + "epoch": 0.8021292012708322, + "grad_norm": 0.5586134195327759, + "learning_rate": 9.684608261199058e-06, + "loss": 1.6619, + "step": 14391 + }, + { + "epoch": 0.8021849395239953, + "grad_norm": 0.6344155669212341, + "learning_rate": 9.679342079167291e-06, + "loss": 1.884, + "step": 14392 + }, + { + "epoch": 0.8022406777771585, + "grad_norm": 0.5842048525810242, + "learning_rate": 9.674077175871709e-06, + "loss": 1.6299, + "step": 14393 + }, + { + "epoch": 0.8022964160303216, + "grad_norm": 0.5197391510009766, + "learning_rate": 9.668813551479295e-06, + "loss": 1.5954, + "step": 14394 + }, + { + "epoch": 0.8023521542834847, + "grad_norm": 0.5479873418807983, + "learning_rate": 9.66355120615694e-06, + "loss": 1.6079, + "step": 14395 + }, + { + "epoch": 0.8024078925366479, + "grad_norm": 0.544422447681427, + "learning_rate": 9.65829014007158e-06, + "loss": 1.5324, + "step": 14396 + }, + { + "epoch": 0.8024636307898111, + "grad_norm": 0.5572550892829895, + "learning_rate": 9.653030353390058e-06, + "loss": 1.919, + "step": 14397 + }, + { + "epoch": 0.8025193690429742, + "grad_norm": 0.5628582835197449, + "learning_rate": 9.647771846279162e-06, + "loss": 1.5565, + "step": 14398 + }, + { + "epoch": 0.8025751072961373, + "grad_norm": 0.562232255935669, + "learning_rate": 9.642514618905673e-06, + "loss": 1.429, + "step": 14399 + }, + { + "epoch": 0.8026308455493005, + "grad_norm": 0.588840663433075, + "learning_rate": 9.637258671436317e-06, + "loss": 1.6777, + "step": 14400 + }, + { + "epoch": 0.8026865838024636, + "grad_norm": 0.542707085609436, + "learning_rate": 9.632004004037804e-06, + "loss": 1.4368, + "step": 14401 + }, + { + "epoch": 0.8027423220556268, + "grad_norm": 0.5453609824180603, + "learning_rate": 9.626750616876745e-06, + "loss": 1.4163, + "step": 14402 + }, + { + "epoch": 0.80279806030879, + "grad_norm": 0.5559371113777161, + "learning_rate": 9.621498510119754e-06, + "loss": 1.5634, + "step": 14403 + }, + { + "epoch": 0.802853798561953, + "grad_norm": 0.5142374038696289, + "learning_rate": 9.616247683933428e-06, + "loss": 1.4767, + "step": 14404 + }, + { + "epoch": 0.8029095368151162, + "grad_norm": 0.5711025595664978, + "learning_rate": 9.610998138484262e-06, + "loss": 1.753, + "step": 14405 + }, + { + "epoch": 0.8029652750682793, + "grad_norm": 0.5574143528938293, + "learning_rate": 9.605749873938752e-06, + "loss": 1.6291, + "step": 14406 + }, + { + "epoch": 0.8030210133214425, + "grad_norm": 0.5474604368209839, + "learning_rate": 9.600502890463341e-06, + "loss": 1.658, + "step": 14407 + }, + { + "epoch": 0.8030767515746057, + "grad_norm": 0.6181548833847046, + "learning_rate": 9.595257188224433e-06, + "loss": 1.8136, + "step": 14408 + }, + { + "epoch": 0.8031324898277687, + "grad_norm": 0.5687413215637207, + "learning_rate": 9.590012767388402e-06, + "loss": 1.3871, + "step": 14409 + }, + { + "epoch": 0.8031882280809319, + "grad_norm": 0.5563036799430847, + "learning_rate": 9.584769628121548e-06, + "loss": 1.4633, + "step": 14410 + }, + { + "epoch": 0.8032439663340951, + "grad_norm": 0.5676126480102539, + "learning_rate": 9.579527770590163e-06, + "loss": 1.7256, + "step": 14411 + }, + { + "epoch": 0.8032997045872582, + "grad_norm": 0.5939561128616333, + "learning_rate": 9.574287194960491e-06, + "loss": 1.5641, + "step": 14412 + }, + { + "epoch": 0.8033554428404214, + "grad_norm": 0.5618433356285095, + "learning_rate": 9.569047901398742e-06, + "loss": 1.5298, + "step": 14413 + }, + { + "epoch": 0.8034111810935846, + "grad_norm": 0.5444064736366272, + "learning_rate": 9.56380989007104e-06, + "loss": 1.5445, + "step": 14414 + }, + { + "epoch": 0.8034669193467476, + "grad_norm": 0.5717688202857971, + "learning_rate": 9.558573161143542e-06, + "loss": 1.7519, + "step": 14415 + }, + { + "epoch": 0.8035226575999108, + "grad_norm": 0.5950873494148254, + "learning_rate": 9.553337714782324e-06, + "loss": 1.7039, + "step": 14416 + }, + { + "epoch": 0.803578395853074, + "grad_norm": 0.5963200330734253, + "learning_rate": 9.548103551153403e-06, + "loss": 1.6528, + "step": 14417 + }, + { + "epoch": 0.8036341341062371, + "grad_norm": 0.5930481553077698, + "learning_rate": 9.542870670422787e-06, + "loss": 1.6934, + "step": 14418 + }, + { + "epoch": 0.8036898723594003, + "grad_norm": 0.5762895941734314, + "learning_rate": 9.537639072756432e-06, + "loss": 1.5557, + "step": 14419 + }, + { + "epoch": 0.8037456106125634, + "grad_norm": 0.5235835909843445, + "learning_rate": 9.532408758320267e-06, + "loss": 1.5267, + "step": 14420 + }, + { + "epoch": 0.8038013488657265, + "grad_norm": 0.5825777649879456, + "learning_rate": 9.527179727280122e-06, + "loss": 1.8426, + "step": 14421 + }, + { + "epoch": 0.8038570871188897, + "grad_norm": 0.5870946645736694, + "learning_rate": 9.52195197980188e-06, + "loss": 1.8076, + "step": 14422 + }, + { + "epoch": 0.8039128253720529, + "grad_norm": 0.5672115683555603, + "learning_rate": 9.516725516051333e-06, + "loss": 1.6287, + "step": 14423 + }, + { + "epoch": 0.803968563625216, + "grad_norm": 0.5582349896430969, + "learning_rate": 9.5115003361942e-06, + "loss": 1.6721, + "step": 14424 + }, + { + "epoch": 0.8040243018783791, + "grad_norm": 0.5517037510871887, + "learning_rate": 9.506276440396223e-06, + "loss": 1.6215, + "step": 14425 + }, + { + "epoch": 0.8040800401315423, + "grad_norm": 0.5543230772018433, + "learning_rate": 9.501053828823053e-06, + "loss": 1.7268, + "step": 14426 + }, + { + "epoch": 0.8041357783847054, + "grad_norm": 0.6084774732589722, + "learning_rate": 9.495832501640344e-06, + "loss": 1.7804, + "step": 14427 + }, + { + "epoch": 0.8041915166378686, + "grad_norm": 0.5827273726463318, + "learning_rate": 9.490612459013664e-06, + "loss": 1.6868, + "step": 14428 + }, + { + "epoch": 0.8042472548910317, + "grad_norm": 0.5763819217681885, + "learning_rate": 9.485393701108552e-06, + "loss": 1.4381, + "step": 14429 + }, + { + "epoch": 0.8043029931441948, + "grad_norm": 0.5460847616195679, + "learning_rate": 9.480176228090566e-06, + "loss": 1.6462, + "step": 14430 + }, + { + "epoch": 0.804358731397358, + "grad_norm": 0.5776088833808899, + "learning_rate": 9.47496004012513e-06, + "loss": 1.6948, + "step": 14431 + }, + { + "epoch": 0.8044144696505211, + "grad_norm": 0.5703887343406677, + "learning_rate": 9.469745137377678e-06, + "loss": 1.5765, + "step": 14432 + }, + { + "epoch": 0.8044702079036843, + "grad_norm": 0.5882792472839355, + "learning_rate": 9.464531520013608e-06, + "loss": 1.463, + "step": 14433 + }, + { + "epoch": 0.8045259461568475, + "grad_norm": 0.5276558995246887, + "learning_rate": 9.459319188198262e-06, + "loss": 1.4668, + "step": 14434 + }, + { + "epoch": 0.8045816844100105, + "grad_norm": 0.5833683609962463, + "learning_rate": 9.454108142096951e-06, + "loss": 1.7968, + "step": 14435 + }, + { + "epoch": 0.8046374226631737, + "grad_norm": 0.5308690667152405, + "learning_rate": 9.448898381874904e-06, + "loss": 1.5935, + "step": 14436 + }, + { + "epoch": 0.8046931609163369, + "grad_norm": 0.6034372448921204, + "learning_rate": 9.4436899076974e-06, + "loss": 1.8367, + "step": 14437 + }, + { + "epoch": 0.8047488991695, + "grad_norm": 0.5395357012748718, + "learning_rate": 9.438482719729579e-06, + "loss": 1.726, + "step": 14438 + }, + { + "epoch": 0.8048046374226632, + "grad_norm": 0.5694220662117004, + "learning_rate": 9.43327681813661e-06, + "loss": 1.7836, + "step": 14439 + }, + { + "epoch": 0.8048603756758264, + "grad_norm": 0.5619423389434814, + "learning_rate": 9.428072203083554e-06, + "loss": 1.7362, + "step": 14440 + }, + { + "epoch": 0.8049161139289894, + "grad_norm": 0.5950040817260742, + "learning_rate": 9.422868874735507e-06, + "loss": 1.8533, + "step": 14441 + }, + { + "epoch": 0.8049718521821526, + "grad_norm": 0.5778230428695679, + "learning_rate": 9.417666833257493e-06, + "loss": 1.5445, + "step": 14442 + }, + { + "epoch": 0.8050275904353158, + "grad_norm": 0.5824107527732849, + "learning_rate": 9.412466078814463e-06, + "loss": 1.7809, + "step": 14443 + }, + { + "epoch": 0.8050833286884789, + "grad_norm": 0.5468677282333374, + "learning_rate": 9.407266611571368e-06, + "loss": 1.547, + "step": 14444 + }, + { + "epoch": 0.8051390669416421, + "grad_norm": 0.5690337419509888, + "learning_rate": 9.402068431693101e-06, + "loss": 1.5924, + "step": 14445 + }, + { + "epoch": 0.8051948051948052, + "grad_norm": 0.5694676637649536, + "learning_rate": 9.396871539344537e-06, + "loss": 1.5457, + "step": 14446 + }, + { + "epoch": 0.8052505434479683, + "grad_norm": 0.5355550050735474, + "learning_rate": 9.391675934690447e-06, + "loss": 1.3105, + "step": 14447 + }, + { + "epoch": 0.8053062817011315, + "grad_norm": 0.6325549483299255, + "learning_rate": 9.386481617895648e-06, + "loss": 1.9536, + "step": 14448 + }, + { + "epoch": 0.8053620199542947, + "grad_norm": 0.5932197570800781, + "learning_rate": 9.381288589124876e-06, + "loss": 1.5554, + "step": 14449 + }, + { + "epoch": 0.8054177582074578, + "grad_norm": 0.5165389180183411, + "learning_rate": 9.376096848542788e-06, + "loss": 1.3512, + "step": 14450 + }, + { + "epoch": 0.8054734964606209, + "grad_norm": 0.5656865835189819, + "learning_rate": 9.370906396314055e-06, + "loss": 1.5164, + "step": 14451 + }, + { + "epoch": 0.805529234713784, + "grad_norm": 0.5801335573196411, + "learning_rate": 9.365717232603283e-06, + "loss": 1.4119, + "step": 14452 + }, + { + "epoch": 0.8055849729669472, + "grad_norm": 0.5520214438438416, + "learning_rate": 9.360529357575066e-06, + "loss": 1.5208, + "step": 14453 + }, + { + "epoch": 0.8056407112201104, + "grad_norm": 0.5672596096992493, + "learning_rate": 9.3553427713939e-06, + "loss": 1.5729, + "step": 14454 + }, + { + "epoch": 0.8056964494732735, + "grad_norm": 0.534829318523407, + "learning_rate": 9.350157474224268e-06, + "loss": 1.615, + "step": 14455 + }, + { + "epoch": 0.8057521877264366, + "grad_norm": 0.5782783627510071, + "learning_rate": 9.344973466230667e-06, + "loss": 1.5061, + "step": 14456 + }, + { + "epoch": 0.8058079259795998, + "grad_norm": 0.5374855399131775, + "learning_rate": 9.339790747577453e-06, + "loss": 1.2955, + "step": 14457 + }, + { + "epoch": 0.8058636642327629, + "grad_norm": 0.5761247277259827, + "learning_rate": 9.334609318429016e-06, + "loss": 1.6353, + "step": 14458 + }, + { + "epoch": 0.8059194024859261, + "grad_norm": 0.5449190735816956, + "learning_rate": 9.329429178949678e-06, + "loss": 1.7109, + "step": 14459 + }, + { + "epoch": 0.8059751407390893, + "grad_norm": 0.5729144215583801, + "learning_rate": 9.324250329303713e-06, + "loss": 1.4907, + "step": 14460 + }, + { + "epoch": 0.8060308789922523, + "grad_norm": 0.5700400471687317, + "learning_rate": 9.31907276965539e-06, + "loss": 1.6438, + "step": 14461 + }, + { + "epoch": 0.8060866172454155, + "grad_norm": 0.5756001472473145, + "learning_rate": 9.313896500168867e-06, + "loss": 1.6177, + "step": 14462 + }, + { + "epoch": 0.8061423554985787, + "grad_norm": 0.5858460664749146, + "learning_rate": 9.308721521008357e-06, + "loss": 1.7162, + "step": 14463 + }, + { + "epoch": 0.8061980937517418, + "grad_norm": 0.5806597471237183, + "learning_rate": 9.303547832337934e-06, + "loss": 1.8492, + "step": 14464 + }, + { + "epoch": 0.806253832004905, + "grad_norm": 0.5977433323860168, + "learning_rate": 9.298375434321716e-06, + "loss": 1.7473, + "step": 14465 + }, + { + "epoch": 0.8063095702580682, + "grad_norm": 0.5730159282684326, + "learning_rate": 9.293204327123694e-06, + "loss": 1.5024, + "step": 14466 + }, + { + "epoch": 0.8063653085112312, + "grad_norm": 0.5740247368812561, + "learning_rate": 9.288034510907912e-06, + "loss": 1.6197, + "step": 14467 + }, + { + "epoch": 0.8064210467643944, + "grad_norm": 0.5691631436347961, + "learning_rate": 9.282865985838313e-06, + "loss": 1.7008, + "step": 14468 + }, + { + "epoch": 0.8064767850175576, + "grad_norm": 0.5945144295692444, + "learning_rate": 9.277698752078801e-06, + "loss": 1.8471, + "step": 14469 + }, + { + "epoch": 0.8065325232707207, + "grad_norm": 0.5495025515556335, + "learning_rate": 9.272532809793254e-06, + "loss": 1.5663, + "step": 14470 + }, + { + "epoch": 0.8065882615238839, + "grad_norm": 0.5286274552345276, + "learning_rate": 9.267368159145506e-06, + "loss": 1.4549, + "step": 14471 + }, + { + "epoch": 0.806643999777047, + "grad_norm": 0.5482826232910156, + "learning_rate": 9.262204800299373e-06, + "loss": 1.4818, + "step": 14472 + }, + { + "epoch": 0.8066997380302101, + "grad_norm": 0.5395148992538452, + "learning_rate": 9.257042733418552e-06, + "loss": 1.5863, + "step": 14473 + }, + { + "epoch": 0.8067554762833733, + "grad_norm": 0.5677280426025391, + "learning_rate": 9.251881958666802e-06, + "loss": 1.461, + "step": 14474 + }, + { + "epoch": 0.8068112145365364, + "grad_norm": 0.5757277011871338, + "learning_rate": 9.246722476207797e-06, + "loss": 1.4981, + "step": 14475 + }, + { + "epoch": 0.8068669527896996, + "grad_norm": 0.5508648157119751, + "learning_rate": 9.24156428620513e-06, + "loss": 1.6121, + "step": 14476 + }, + { + "epoch": 0.8069226910428627, + "grad_norm": 0.5794610977172852, + "learning_rate": 9.236407388822405e-06, + "loss": 1.5065, + "step": 14477 + }, + { + "epoch": 0.8069784292960258, + "grad_norm": 0.5588470101356506, + "learning_rate": 9.23125178422317e-06, + "loss": 1.47, + "step": 14478 + }, + { + "epoch": 0.807034167549189, + "grad_norm": 0.5367100834846497, + "learning_rate": 9.226097472570943e-06, + "loss": 1.4377, + "step": 14479 + }, + { + "epoch": 0.8070899058023522, + "grad_norm": 0.5730358362197876, + "learning_rate": 9.220944454029162e-06, + "loss": 1.6211, + "step": 14480 + }, + { + "epoch": 0.8071456440555153, + "grad_norm": 0.541301429271698, + "learning_rate": 9.215792728761253e-06, + "loss": 1.5581, + "step": 14481 + }, + { + "epoch": 0.8072013823086784, + "grad_norm": 0.5392494201660156, + "learning_rate": 9.210642296930638e-06, + "loss": 1.5311, + "step": 14482 + }, + { + "epoch": 0.8072571205618416, + "grad_norm": 0.5902514457702637, + "learning_rate": 9.205493158700618e-06, + "loss": 1.6832, + "step": 14483 + }, + { + "epoch": 0.8073128588150047, + "grad_norm": 0.5396768450737, + "learning_rate": 9.200345314234504e-06, + "loss": 1.5659, + "step": 14484 + }, + { + "epoch": 0.8073685970681679, + "grad_norm": 0.5860647559165955, + "learning_rate": 9.195198763695557e-06, + "loss": 1.5639, + "step": 14485 + }, + { + "epoch": 0.8074243353213311, + "grad_norm": 0.6074658632278442, + "learning_rate": 9.190053507246999e-06, + "loss": 1.7787, + "step": 14486 + }, + { + "epoch": 0.8074800735744941, + "grad_norm": 0.5613250136375427, + "learning_rate": 9.184909545052017e-06, + "loss": 1.5598, + "step": 14487 + }, + { + "epoch": 0.8075358118276573, + "grad_norm": 0.5493916273117065, + "learning_rate": 9.17976687727371e-06, + "loss": 1.5103, + "step": 14488 + }, + { + "epoch": 0.8075915500808205, + "grad_norm": 0.578508734703064, + "learning_rate": 9.174625504075225e-06, + "loss": 1.7456, + "step": 14489 + }, + { + "epoch": 0.8076472883339836, + "grad_norm": 0.5659584999084473, + "learning_rate": 9.169485425619578e-06, + "loss": 1.7104, + "step": 14490 + }, + { + "epoch": 0.8077030265871468, + "grad_norm": 0.6089297533035278, + "learning_rate": 9.164346642069804e-06, + "loss": 1.814, + "step": 14491 + }, + { + "epoch": 0.80775876484031, + "grad_norm": 0.5530262589454651, + "learning_rate": 9.159209153588849e-06, + "loss": 1.6125, + "step": 14492 + }, + { + "epoch": 0.807814503093473, + "grad_norm": 0.5667465329170227, + "learning_rate": 9.154072960339666e-06, + "loss": 1.627, + "step": 14493 + }, + { + "epoch": 0.8078702413466362, + "grad_norm": 0.6102772951126099, + "learning_rate": 9.148938062485157e-06, + "loss": 1.5063, + "step": 14494 + }, + { + "epoch": 0.8079259795997994, + "grad_norm": 0.6273038983345032, + "learning_rate": 9.143804460188143e-06, + "loss": 1.6385, + "step": 14495 + }, + { + "epoch": 0.8079817178529625, + "grad_norm": 0.554091215133667, + "learning_rate": 9.138672153611439e-06, + "loss": 1.6554, + "step": 14496 + }, + { + "epoch": 0.8080374561061257, + "grad_norm": 0.5899942517280579, + "learning_rate": 9.133541142917823e-06, + "loss": 1.7165, + "step": 14497 + }, + { + "epoch": 0.8080931943592887, + "grad_norm": 0.6665770411491394, + "learning_rate": 9.128411428270018e-06, + "loss": 2.0642, + "step": 14498 + }, + { + "epoch": 0.8081489326124519, + "grad_norm": 0.5284276008605957, + "learning_rate": 9.123283009830686e-06, + "loss": 1.6783, + "step": 14499 + }, + { + "epoch": 0.8082046708656151, + "grad_norm": 0.5691483616828918, + "learning_rate": 9.118155887762496e-06, + "loss": 1.6466, + "step": 14500 + }, + { + "epoch": 0.8082604091187782, + "grad_norm": 0.5701718330383301, + "learning_rate": 9.113030062228063e-06, + "loss": 1.4418, + "step": 14501 + }, + { + "epoch": 0.8083161473719414, + "grad_norm": 0.5520241856575012, + "learning_rate": 9.107905533389915e-06, + "loss": 1.4944, + "step": 14502 + }, + { + "epoch": 0.8083718856251045, + "grad_norm": 0.5629130601882935, + "learning_rate": 9.102782301410584e-06, + "loss": 1.6503, + "step": 14503 + }, + { + "epoch": 0.8084276238782676, + "grad_norm": 0.5741170644760132, + "learning_rate": 9.097660366452548e-06, + "loss": 1.7528, + "step": 14504 + }, + { + "epoch": 0.8084833621314308, + "grad_norm": 0.5423370003700256, + "learning_rate": 9.092539728678262e-06, + "loss": 1.7108, + "step": 14505 + }, + { + "epoch": 0.808539100384594, + "grad_norm": 0.5521060228347778, + "learning_rate": 9.087420388250101e-06, + "loss": 1.5113, + "step": 14506 + }, + { + "epoch": 0.808594838637757, + "grad_norm": 0.6263614892959595, + "learning_rate": 9.082302345330413e-06, + "loss": 1.9957, + "step": 14507 + }, + { + "epoch": 0.8086505768909202, + "grad_norm": 0.5271081328392029, + "learning_rate": 9.077185600081551e-06, + "loss": 1.4357, + "step": 14508 + }, + { + "epoch": 0.8087063151440834, + "grad_norm": 0.5640679597854614, + "learning_rate": 9.072070152665758e-06, + "loss": 1.7057, + "step": 14509 + }, + { + "epoch": 0.8087620533972465, + "grad_norm": 0.5805985927581787, + "learning_rate": 9.066956003245264e-06, + "loss": 1.737, + "step": 14510 + }, + { + "epoch": 0.8088177916504097, + "grad_norm": 0.5537278056144714, + "learning_rate": 9.06184315198228e-06, + "loss": 1.5738, + "step": 14511 + }, + { + "epoch": 0.8088735299035729, + "grad_norm": 0.5141084790229797, + "learning_rate": 9.056731599038948e-06, + "loss": 1.4052, + "step": 14512 + }, + { + "epoch": 0.8089292681567359, + "grad_norm": 0.6007054448127747, + "learning_rate": 9.051621344577371e-06, + "loss": 1.9542, + "step": 14513 + }, + { + "epoch": 0.8089850064098991, + "grad_norm": 0.5462144017219543, + "learning_rate": 9.046512388759598e-06, + "loss": 1.6902, + "step": 14514 + }, + { + "epoch": 0.8090407446630623, + "grad_norm": 0.5487377047538757, + "learning_rate": 9.041404731747705e-06, + "loss": 1.7517, + "step": 14515 + }, + { + "epoch": 0.8090964829162254, + "grad_norm": 0.6560800075531006, + "learning_rate": 9.036298373703638e-06, + "loss": 1.7549, + "step": 14516 + }, + { + "epoch": 0.8091522211693886, + "grad_norm": 0.5306289196014404, + "learning_rate": 9.03119331478935e-06, + "loss": 1.596, + "step": 14517 + }, + { + "epoch": 0.8092079594225517, + "grad_norm": 0.5258604884147644, + "learning_rate": 9.026089555166745e-06, + "loss": 1.5824, + "step": 14518 + }, + { + "epoch": 0.8092636976757148, + "grad_norm": 0.5263345837593079, + "learning_rate": 9.020987094997691e-06, + "loss": 1.5729, + "step": 14519 + }, + { + "epoch": 0.809319435928878, + "grad_norm": 0.6098785400390625, + "learning_rate": 9.015885934444007e-06, + "loss": 1.7344, + "step": 14520 + }, + { + "epoch": 0.8093751741820411, + "grad_norm": 0.5672189593315125, + "learning_rate": 9.010786073667455e-06, + "loss": 1.6726, + "step": 14521 + }, + { + "epoch": 0.8094309124352043, + "grad_norm": 0.5683502554893494, + "learning_rate": 9.005687512829786e-06, + "loss": 1.7196, + "step": 14522 + }, + { + "epoch": 0.8094866506883674, + "grad_norm": 0.5518867373466492, + "learning_rate": 9.0005902520927e-06, + "loss": 1.6435, + "step": 14523 + }, + { + "epoch": 0.8095423889415305, + "grad_norm": 0.5819790959358215, + "learning_rate": 8.995494291617856e-06, + "loss": 1.7616, + "step": 14524 + }, + { + "epoch": 0.8095981271946937, + "grad_norm": 0.5913581252098083, + "learning_rate": 8.990399631566837e-06, + "loss": 1.6495, + "step": 14525 + }, + { + "epoch": 0.8096538654478569, + "grad_norm": 0.5639625787734985, + "learning_rate": 8.985306272101252e-06, + "loss": 1.6081, + "step": 14526 + }, + { + "epoch": 0.80970960370102, + "grad_norm": 0.5754690170288086, + "learning_rate": 8.980214213382632e-06, + "loss": 1.4755, + "step": 14527 + }, + { + "epoch": 0.8097653419541831, + "grad_norm": 0.5814158916473389, + "learning_rate": 8.975123455572443e-06, + "loss": 1.5668, + "step": 14528 + }, + { + "epoch": 0.8098210802073463, + "grad_norm": 0.4973066449165344, + "learning_rate": 8.970033998832145e-06, + "loss": 1.2416, + "step": 14529 + }, + { + "epoch": 0.8098768184605094, + "grad_norm": 0.586467444896698, + "learning_rate": 8.964945843323147e-06, + "loss": 1.8587, + "step": 14530 + }, + { + "epoch": 0.8099325567136726, + "grad_norm": 0.5752747058868408, + "learning_rate": 8.959858989206827e-06, + "loss": 1.6583, + "step": 14531 + }, + { + "epoch": 0.8099882949668358, + "grad_norm": 0.5636700391769409, + "learning_rate": 8.954773436644492e-06, + "loss": 1.6193, + "step": 14532 + }, + { + "epoch": 0.8100440332199988, + "grad_norm": 0.596447229385376, + "learning_rate": 8.949689185797416e-06, + "loss": 1.7473, + "step": 14533 + }, + { + "epoch": 0.810099771473162, + "grad_norm": 0.5715921521186829, + "learning_rate": 8.944606236826885e-06, + "loss": 1.6444, + "step": 14534 + }, + { + "epoch": 0.8101555097263252, + "grad_norm": 0.5635936260223389, + "learning_rate": 8.939524589894067e-06, + "loss": 1.7083, + "step": 14535 + }, + { + "epoch": 0.8102112479794883, + "grad_norm": 0.5593386888504028, + "learning_rate": 8.934444245160123e-06, + "loss": 1.6985, + "step": 14536 + }, + { + "epoch": 0.8102669862326515, + "grad_norm": 0.5133383274078369, + "learning_rate": 8.929365202786183e-06, + "loss": 1.487, + "step": 14537 + }, + { + "epoch": 0.8103227244858147, + "grad_norm": 0.5615258812904358, + "learning_rate": 8.924287462933328e-06, + "loss": 1.4259, + "step": 14538 + }, + { + "epoch": 0.8103784627389777, + "grad_norm": 0.5180845260620117, + "learning_rate": 8.919211025762581e-06, + "loss": 1.4425, + "step": 14539 + }, + { + "epoch": 0.8104342009921409, + "grad_norm": 0.5557456612586975, + "learning_rate": 8.914135891434927e-06, + "loss": 1.467, + "step": 14540 + }, + { + "epoch": 0.8104899392453041, + "grad_norm": 0.5708995461463928, + "learning_rate": 8.909062060111357e-06, + "loss": 1.6551, + "step": 14541 + }, + { + "epoch": 0.8105456774984672, + "grad_norm": 0.5808879733085632, + "learning_rate": 8.903989531952755e-06, + "loss": 1.6874, + "step": 14542 + }, + { + "epoch": 0.8106014157516304, + "grad_norm": 0.5360985398292542, + "learning_rate": 8.89891830711999e-06, + "loss": 1.5656, + "step": 14543 + }, + { + "epoch": 0.8106571540047934, + "grad_norm": 0.556928813457489, + "learning_rate": 8.893848385773911e-06, + "loss": 1.6318, + "step": 14544 + }, + { + "epoch": 0.8107128922579566, + "grad_norm": 0.5977469682693481, + "learning_rate": 8.88877976807529e-06, + "loss": 1.7456, + "step": 14545 + }, + { + "epoch": 0.8107686305111198, + "grad_norm": 0.6153261661529541, + "learning_rate": 8.883712454184894e-06, + "loss": 1.7037, + "step": 14546 + }, + { + "epoch": 0.8108243687642829, + "grad_norm": 0.5547722578048706, + "learning_rate": 8.8786464442634e-06, + "loss": 1.6516, + "step": 14547 + }, + { + "epoch": 0.8108801070174461, + "grad_norm": 0.6243407726287842, + "learning_rate": 8.873581738471486e-06, + "loss": 1.8242, + "step": 14548 + }, + { + "epoch": 0.8109358452706092, + "grad_norm": 0.571435809135437, + "learning_rate": 8.868518336969779e-06, + "loss": 1.6742, + "step": 14549 + }, + { + "epoch": 0.8109915835237723, + "grad_norm": 0.5933339595794678, + "learning_rate": 8.863456239918866e-06, + "loss": 1.7067, + "step": 14550 + }, + { + "epoch": 0.8110473217769355, + "grad_norm": 0.5834755301475525, + "learning_rate": 8.858395447479257e-06, + "loss": 1.5587, + "step": 14551 + }, + { + "epoch": 0.8111030600300987, + "grad_norm": 0.6342363953590393, + "learning_rate": 8.853335959811482e-06, + "loss": 1.8265, + "step": 14552 + }, + { + "epoch": 0.8111587982832618, + "grad_norm": 0.5746006965637207, + "learning_rate": 8.848277777076003e-06, + "loss": 1.6465, + "step": 14553 + }, + { + "epoch": 0.811214536536425, + "grad_norm": 0.5476809740066528, + "learning_rate": 8.843220899433207e-06, + "loss": 1.6282, + "step": 14554 + }, + { + "epoch": 0.8112702747895881, + "grad_norm": 0.5748486518859863, + "learning_rate": 8.838165327043485e-06, + "loss": 1.6087, + "step": 14555 + }, + { + "epoch": 0.8113260130427512, + "grad_norm": 0.5710524320602417, + "learning_rate": 8.833111060067172e-06, + "loss": 1.5522, + "step": 14556 + }, + { + "epoch": 0.8113817512959144, + "grad_norm": 0.5666594505310059, + "learning_rate": 8.828058098664566e-06, + "loss": 1.5523, + "step": 14557 + }, + { + "epoch": 0.8114374895490776, + "grad_norm": 0.5782667994499207, + "learning_rate": 8.823006442995895e-06, + "loss": 1.6946, + "step": 14558 + }, + { + "epoch": 0.8114932278022406, + "grad_norm": 0.5868912935256958, + "learning_rate": 8.817956093221369e-06, + "loss": 1.7758, + "step": 14559 + }, + { + "epoch": 0.8115489660554038, + "grad_norm": 0.5910466313362122, + "learning_rate": 8.81290704950119e-06, + "loss": 1.8656, + "step": 14560 + }, + { + "epoch": 0.811604704308567, + "grad_norm": 0.5408613085746765, + "learning_rate": 8.807859311995454e-06, + "loss": 1.4917, + "step": 14561 + }, + { + "epoch": 0.8116604425617301, + "grad_norm": 0.6216923594474792, + "learning_rate": 8.802812880864252e-06, + "loss": 1.808, + "step": 14562 + }, + { + "epoch": 0.8117161808148933, + "grad_norm": 0.5523777008056641, + "learning_rate": 8.797767756267628e-06, + "loss": 1.4685, + "step": 14563 + }, + { + "epoch": 0.8117719190680565, + "grad_norm": 0.5775405764579773, + "learning_rate": 8.792723938365599e-06, + "loss": 1.6824, + "step": 14564 + }, + { + "epoch": 0.8118276573212195, + "grad_norm": 0.5495176911354065, + "learning_rate": 8.787681427318095e-06, + "loss": 1.5778, + "step": 14565 + }, + { + "epoch": 0.8118833955743827, + "grad_norm": 0.5674751400947571, + "learning_rate": 8.782640223285043e-06, + "loss": 1.7507, + "step": 14566 + }, + { + "epoch": 0.8119391338275458, + "grad_norm": 0.5787277221679688, + "learning_rate": 8.777600326426356e-06, + "loss": 1.647, + "step": 14567 + }, + { + "epoch": 0.811994872080709, + "grad_norm": 0.6019443273544312, + "learning_rate": 8.77256173690183e-06, + "loss": 1.6628, + "step": 14568 + }, + { + "epoch": 0.8120506103338722, + "grad_norm": 0.5538434386253357, + "learning_rate": 8.767524454871273e-06, + "loss": 1.4677, + "step": 14569 + }, + { + "epoch": 0.8121063485870352, + "grad_norm": 0.5707783102989197, + "learning_rate": 8.762488480494435e-06, + "loss": 1.6471, + "step": 14570 + }, + { + "epoch": 0.8121620868401984, + "grad_norm": 0.576706051826477, + "learning_rate": 8.757453813931032e-06, + "loss": 1.5768, + "step": 14571 + }, + { + "epoch": 0.8122178250933616, + "grad_norm": 0.5679410696029663, + "learning_rate": 8.752420455340749e-06, + "loss": 1.6616, + "step": 14572 + }, + { + "epoch": 0.8122735633465247, + "grad_norm": 0.5615427494049072, + "learning_rate": 8.747388404883183e-06, + "loss": 1.659, + "step": 14573 + }, + { + "epoch": 0.8123293015996879, + "grad_norm": 0.5732202529907227, + "learning_rate": 8.742357662717943e-06, + "loss": 1.5695, + "step": 14574 + }, + { + "epoch": 0.812385039852851, + "grad_norm": 0.5816728472709656, + "learning_rate": 8.737328229004565e-06, + "loss": 1.6397, + "step": 14575 + }, + { + "epoch": 0.8124407781060141, + "grad_norm": 0.5549823045730591, + "learning_rate": 8.732300103902568e-06, + "loss": 1.639, + "step": 14576 + }, + { + "epoch": 0.8124965163591773, + "grad_norm": 0.6017770171165466, + "learning_rate": 8.72727328757138e-06, + "loss": 1.6974, + "step": 14577 + }, + { + "epoch": 0.8125522546123405, + "grad_norm": 0.5807628631591797, + "learning_rate": 8.722247780170461e-06, + "loss": 1.5893, + "step": 14578 + }, + { + "epoch": 0.8126079928655036, + "grad_norm": 0.5604943633079529, + "learning_rate": 8.717223581859191e-06, + "loss": 1.7204, + "step": 14579 + }, + { + "epoch": 0.8126637311186667, + "grad_norm": 0.529071569442749, + "learning_rate": 8.71220069279688e-06, + "loss": 1.6458, + "step": 14580 + }, + { + "epoch": 0.8127194693718299, + "grad_norm": 0.5336666703224182, + "learning_rate": 8.707179113142839e-06, + "loss": 1.3501, + "step": 14581 + }, + { + "epoch": 0.812775207624993, + "grad_norm": 0.5635989308357239, + "learning_rate": 8.702158843056319e-06, + "loss": 1.694, + "step": 14582 + }, + { + "epoch": 0.8128309458781562, + "grad_norm": 0.5581356287002563, + "learning_rate": 8.697139882696548e-06, + "loss": 1.5596, + "step": 14583 + }, + { + "epoch": 0.8128866841313194, + "grad_norm": 0.5320961475372314, + "learning_rate": 8.692122232222683e-06, + "loss": 1.7084, + "step": 14584 + }, + { + "epoch": 0.8129424223844824, + "grad_norm": 0.5928415060043335, + "learning_rate": 8.68710589179384e-06, + "loss": 1.4451, + "step": 14585 + }, + { + "epoch": 0.8129981606376456, + "grad_norm": 0.5560922622680664, + "learning_rate": 8.682090861569153e-06, + "loss": 1.4804, + "step": 14586 + }, + { + "epoch": 0.8130538988908088, + "grad_norm": 0.5927940011024475, + "learning_rate": 8.677077141707635e-06, + "loss": 1.6313, + "step": 14587 + }, + { + "epoch": 0.8131096371439719, + "grad_norm": 0.511622965335846, + "learning_rate": 8.672064732368301e-06, + "loss": 1.4384, + "step": 14588 + }, + { + "epoch": 0.8131653753971351, + "grad_norm": 0.6018781661987305, + "learning_rate": 8.667053633710109e-06, + "loss": 1.7108, + "step": 14589 + }, + { + "epoch": 0.8132211136502983, + "grad_norm": 0.5497088432312012, + "learning_rate": 8.662043845892004e-06, + "loss": 1.4508, + "step": 14590 + }, + { + "epoch": 0.8132768519034613, + "grad_norm": 0.5855251550674438, + "learning_rate": 8.65703536907284e-06, + "loss": 1.7348, + "step": 14591 + }, + { + "epoch": 0.8133325901566245, + "grad_norm": 0.628377377986908, + "learning_rate": 8.652028203411455e-06, + "loss": 1.6383, + "step": 14592 + }, + { + "epoch": 0.8133883284097876, + "grad_norm": 0.6113680601119995, + "learning_rate": 8.647022349066686e-06, + "loss": 1.8188, + "step": 14593 + }, + { + "epoch": 0.8134440666629508, + "grad_norm": 0.536659300327301, + "learning_rate": 8.64201780619725e-06, + "loss": 1.5536, + "step": 14594 + }, + { + "epoch": 0.813499804916114, + "grad_norm": 0.5933912396430969, + "learning_rate": 8.637014574961872e-06, + "loss": 1.68, + "step": 14595 + }, + { + "epoch": 0.813555543169277, + "grad_norm": 0.5632370114326477, + "learning_rate": 8.632012655519234e-06, + "loss": 1.4752, + "step": 14596 + }, + { + "epoch": 0.8136112814224402, + "grad_norm": 0.5764100551605225, + "learning_rate": 8.62701204802796e-06, + "loss": 1.6428, + "step": 14597 + }, + { + "epoch": 0.8136670196756034, + "grad_norm": 0.5657497048377991, + "learning_rate": 8.622012752646652e-06, + "loss": 1.6523, + "step": 14598 + }, + { + "epoch": 0.8137227579287665, + "grad_norm": 0.6426599621772766, + "learning_rate": 8.617014769533843e-06, + "loss": 1.8712, + "step": 14599 + }, + { + "epoch": 0.8137784961819297, + "grad_norm": 0.5723824501037598, + "learning_rate": 8.612018098848041e-06, + "loss": 1.6655, + "step": 14600 + }, + { + "epoch": 0.8138342344350928, + "grad_norm": 0.5591287612915039, + "learning_rate": 8.607022740747716e-06, + "loss": 1.7306, + "step": 14601 + }, + { + "epoch": 0.8138899726882559, + "grad_norm": 0.5826481580734253, + "learning_rate": 8.602028695391307e-06, + "loss": 1.5182, + "step": 14602 + }, + { + "epoch": 0.8139457109414191, + "grad_norm": 0.5714852809906006, + "learning_rate": 8.597035962937156e-06, + "loss": 1.5408, + "step": 14603 + }, + { + "epoch": 0.8140014491945823, + "grad_norm": 0.5411056876182556, + "learning_rate": 8.592044543543643e-06, + "loss": 1.5651, + "step": 14604 + }, + { + "epoch": 0.8140571874477454, + "grad_norm": 0.586496114730835, + "learning_rate": 8.587054437369057e-06, + "loss": 1.7391, + "step": 14605 + }, + { + "epoch": 0.8141129257009085, + "grad_norm": 0.5315595865249634, + "learning_rate": 8.582065644571647e-06, + "loss": 1.5022, + "step": 14606 + }, + { + "epoch": 0.8141686639540717, + "grad_norm": 0.5513681769371033, + "learning_rate": 8.577078165309621e-06, + "loss": 1.6308, + "step": 14607 + }, + { + "epoch": 0.8142244022072348, + "grad_norm": 0.6040627956390381, + "learning_rate": 8.572091999741172e-06, + "loss": 1.825, + "step": 14608 + }, + { + "epoch": 0.814280140460398, + "grad_norm": 0.5821855664253235, + "learning_rate": 8.567107148024434e-06, + "loss": 1.5367, + "step": 14609 + }, + { + "epoch": 0.8143358787135612, + "grad_norm": 0.5883117318153381, + "learning_rate": 8.562123610317457e-06, + "loss": 1.7769, + "step": 14610 + }, + { + "epoch": 0.8143916169667242, + "grad_norm": 0.5612747669219971, + "learning_rate": 8.557141386778334e-06, + "loss": 1.4503, + "step": 14611 + }, + { + "epoch": 0.8144473552198874, + "grad_norm": 0.5363609194755554, + "learning_rate": 8.552160477565075e-06, + "loss": 1.3287, + "step": 14612 + }, + { + "epoch": 0.8145030934730506, + "grad_norm": 0.5557144284248352, + "learning_rate": 8.547180882835609e-06, + "loss": 1.8482, + "step": 14613 + }, + { + "epoch": 0.8145588317262137, + "grad_norm": 0.5327957272529602, + "learning_rate": 8.542202602747884e-06, + "loss": 1.4672, + "step": 14614 + }, + { + "epoch": 0.8146145699793769, + "grad_norm": 0.5746212601661682, + "learning_rate": 8.537225637459773e-06, + "loss": 1.7671, + "step": 14615 + }, + { + "epoch": 0.8146703082325399, + "grad_norm": 0.5310134887695312, + "learning_rate": 8.532249987129132e-06, + "loss": 1.6654, + "step": 14616 + }, + { + "epoch": 0.8147260464857031, + "grad_norm": 0.574122965335846, + "learning_rate": 8.527275651913735e-06, + "loss": 1.7017, + "step": 14617 + }, + { + "epoch": 0.8147817847388663, + "grad_norm": 0.5795066952705383, + "learning_rate": 8.522302631971341e-06, + "loss": 1.6954, + "step": 14618 + }, + { + "epoch": 0.8148375229920294, + "grad_norm": 0.5737940669059753, + "learning_rate": 8.517330927459704e-06, + "loss": 1.6882, + "step": 14619 + }, + { + "epoch": 0.8148932612451926, + "grad_norm": 0.5952860116958618, + "learning_rate": 8.512360538536452e-06, + "loss": 1.6532, + "step": 14620 + }, + { + "epoch": 0.8149489994983558, + "grad_norm": 0.5542854070663452, + "learning_rate": 8.507391465359238e-06, + "loss": 1.6373, + "step": 14621 + }, + { + "epoch": 0.8150047377515188, + "grad_norm": 0.5282446146011353, + "learning_rate": 8.502423708085644e-06, + "loss": 1.5834, + "step": 14622 + }, + { + "epoch": 0.815060476004682, + "grad_norm": 0.576572835445404, + "learning_rate": 8.497457266873233e-06, + "loss": 1.5779, + "step": 14623 + }, + { + "epoch": 0.8151162142578452, + "grad_norm": 0.5445130467414856, + "learning_rate": 8.492492141879493e-06, + "loss": 1.7272, + "step": 14624 + }, + { + "epoch": 0.8151719525110083, + "grad_norm": 0.5699845552444458, + "learning_rate": 8.487528333261896e-06, + "loss": 1.597, + "step": 14625 + }, + { + "epoch": 0.8152276907641715, + "grad_norm": 0.5669733285903931, + "learning_rate": 8.482565841177864e-06, + "loss": 1.7181, + "step": 14626 + }, + { + "epoch": 0.8152834290173346, + "grad_norm": 0.5513604283332825, + "learning_rate": 8.477604665784782e-06, + "loss": 1.4208, + "step": 14627 + }, + { + "epoch": 0.8153391672704977, + "grad_norm": 0.5793091654777527, + "learning_rate": 8.47264480724e-06, + "loss": 1.6251, + "step": 14628 + }, + { + "epoch": 0.8153949055236609, + "grad_norm": 0.6061859130859375, + "learning_rate": 8.467686265700775e-06, + "loss": 1.5518, + "step": 14629 + }, + { + "epoch": 0.8154506437768241, + "grad_norm": 0.5648293495178223, + "learning_rate": 8.462729041324407e-06, + "loss": 1.751, + "step": 14630 + }, + { + "epoch": 0.8155063820299872, + "grad_norm": 0.5499643683433533, + "learning_rate": 8.45777313426811e-06, + "loss": 1.4874, + "step": 14631 + }, + { + "epoch": 0.8155621202831503, + "grad_norm": 0.5458365082740784, + "learning_rate": 8.452818544689023e-06, + "loss": 1.5309, + "step": 14632 + }, + { + "epoch": 0.8156178585363135, + "grad_norm": 0.5470486283302307, + "learning_rate": 8.447865272744299e-06, + "loss": 1.598, + "step": 14633 + }, + { + "epoch": 0.8156735967894766, + "grad_norm": 0.5594566464424133, + "learning_rate": 8.442913318591022e-06, + "loss": 1.6158, + "step": 14634 + }, + { + "epoch": 0.8157293350426398, + "grad_norm": 0.5831910371780396, + "learning_rate": 8.437962682386252e-06, + "loss": 1.6812, + "step": 14635 + }, + { + "epoch": 0.815785073295803, + "grad_norm": 0.5766580104827881, + "learning_rate": 8.433013364286957e-06, + "loss": 1.5881, + "step": 14636 + }, + { + "epoch": 0.815840811548966, + "grad_norm": 0.612402081489563, + "learning_rate": 8.428065364450138e-06, + "loss": 1.7401, + "step": 14637 + }, + { + "epoch": 0.8158965498021292, + "grad_norm": 0.5256620645523071, + "learning_rate": 8.423118683032715e-06, + "loss": 1.6026, + "step": 14638 + }, + { + "epoch": 0.8159522880552923, + "grad_norm": 0.5555899143218994, + "learning_rate": 8.418173320191547e-06, + "loss": 1.764, + "step": 14639 + }, + { + "epoch": 0.8160080263084555, + "grad_norm": 0.626512348651886, + "learning_rate": 8.413229276083484e-06, + "loss": 1.813, + "step": 14640 + }, + { + "epoch": 0.8160637645616187, + "grad_norm": 0.5965732932090759, + "learning_rate": 8.408286550865318e-06, + "loss": 1.7731, + "step": 14641 + }, + { + "epoch": 0.8161195028147817, + "grad_norm": 0.5264768004417419, + "learning_rate": 8.40334514469382e-06, + "loss": 1.606, + "step": 14642 + }, + { + "epoch": 0.8161752410679449, + "grad_norm": 0.5863091349601746, + "learning_rate": 8.398405057725678e-06, + "loss": 1.6438, + "step": 14643 + }, + { + "epoch": 0.8162309793211081, + "grad_norm": 0.6372930407524109, + "learning_rate": 8.393466290117557e-06, + "loss": 1.5923, + "step": 14644 + }, + { + "epoch": 0.8162867175742712, + "grad_norm": 0.574329674243927, + "learning_rate": 8.388528842026128e-06, + "loss": 1.5047, + "step": 14645 + }, + { + "epoch": 0.8163424558274344, + "grad_norm": 0.5910654664039612, + "learning_rate": 8.38359271360794e-06, + "loss": 1.669, + "step": 14646 + }, + { + "epoch": 0.8163981940805976, + "grad_norm": 0.5745288133621216, + "learning_rate": 8.378657905019555e-06, + "loss": 1.6667, + "step": 14647 + }, + { + "epoch": 0.8164539323337606, + "grad_norm": 0.5561100244522095, + "learning_rate": 8.373724416417467e-06, + "loss": 1.8452, + "step": 14648 + }, + { + "epoch": 0.8165096705869238, + "grad_norm": 0.634443461894989, + "learning_rate": 8.368792247958157e-06, + "loss": 1.755, + "step": 14649 + }, + { + "epoch": 0.816565408840087, + "grad_norm": 0.5481244921684265, + "learning_rate": 8.363861399798018e-06, + "loss": 1.6841, + "step": 14650 + }, + { + "epoch": 0.8166211470932501, + "grad_norm": 0.5906131863594055, + "learning_rate": 8.358931872093439e-06, + "loss": 1.6548, + "step": 14651 + }, + { + "epoch": 0.8166768853464133, + "grad_norm": 0.5448386073112488, + "learning_rate": 8.354003665000754e-06, + "loss": 1.6098, + "step": 14652 + }, + { + "epoch": 0.8167326235995764, + "grad_norm": 0.5544820427894592, + "learning_rate": 8.349076778676262e-06, + "loss": 1.4819, + "step": 14653 + }, + { + "epoch": 0.8167883618527395, + "grad_norm": 0.5842088460922241, + "learning_rate": 8.34415121327623e-06, + "loss": 2.0069, + "step": 14654 + }, + { + "epoch": 0.8168441001059027, + "grad_norm": 0.5592513084411621, + "learning_rate": 8.33922696895682e-06, + "loss": 1.6903, + "step": 14655 + }, + { + "epoch": 0.8168998383590659, + "grad_norm": 0.5489197969436646, + "learning_rate": 8.334304045874247e-06, + "loss": 1.5395, + "step": 14656 + }, + { + "epoch": 0.816955576612229, + "grad_norm": 0.5454195737838745, + "learning_rate": 8.329382444184636e-06, + "loss": 1.6031, + "step": 14657 + }, + { + "epoch": 0.8170113148653921, + "grad_norm": 0.5950064063072205, + "learning_rate": 8.32446216404404e-06, + "loss": 1.6411, + "step": 14658 + }, + { + "epoch": 0.8170670531185553, + "grad_norm": 0.5340271592140198, + "learning_rate": 8.319543205608522e-06, + "loss": 1.5835, + "step": 14659 + }, + { + "epoch": 0.8171227913717184, + "grad_norm": 0.5560121536254883, + "learning_rate": 8.31462556903408e-06, + "loss": 1.6486, + "step": 14660 + }, + { + "epoch": 0.8171785296248816, + "grad_norm": 0.5711260437965393, + "learning_rate": 8.309709254476682e-06, + "loss": 1.6764, + "step": 14661 + }, + { + "epoch": 0.8172342678780447, + "grad_norm": 0.5732410550117493, + "learning_rate": 8.304794262092208e-06, + "loss": 1.6329, + "step": 14662 + }, + { + "epoch": 0.8172900061312078, + "grad_norm": 0.5843484401702881, + "learning_rate": 8.299880592036579e-06, + "loss": 2.0122, + "step": 14663 + }, + { + "epoch": 0.817345744384371, + "grad_norm": 0.5985366702079773, + "learning_rate": 8.294968244465618e-06, + "loss": 1.7526, + "step": 14664 + }, + { + "epoch": 0.8174014826375341, + "grad_norm": 0.5528346300125122, + "learning_rate": 8.290057219535097e-06, + "loss": 1.7203, + "step": 14665 + }, + { + "epoch": 0.8174572208906973, + "grad_norm": 0.5621989965438843, + "learning_rate": 8.28514751740077e-06, + "loss": 1.5719, + "step": 14666 + }, + { + "epoch": 0.8175129591438605, + "grad_norm": 0.532791793346405, + "learning_rate": 8.280239138218354e-06, + "loss": 1.6364, + "step": 14667 + }, + { + "epoch": 0.8175686973970235, + "grad_norm": 0.5551378726959229, + "learning_rate": 8.275332082143522e-06, + "loss": 1.4977, + "step": 14668 + }, + { + "epoch": 0.8176244356501867, + "grad_norm": 0.5460422039031982, + "learning_rate": 8.270426349331872e-06, + "loss": 1.5391, + "step": 14669 + }, + { + "epoch": 0.8176801739033499, + "grad_norm": 0.5884209871292114, + "learning_rate": 8.265521939938987e-06, + "loss": 1.8799, + "step": 14670 + }, + { + "epoch": 0.817735912156513, + "grad_norm": 0.5831186175346375, + "learning_rate": 8.260618854120439e-06, + "loss": 1.637, + "step": 14671 + }, + { + "epoch": 0.8177916504096762, + "grad_norm": 0.5479006767272949, + "learning_rate": 8.25571709203169e-06, + "loss": 1.5, + "step": 14672 + }, + { + "epoch": 0.8178473886628393, + "grad_norm": 0.5728062987327576, + "learning_rate": 8.250816653828208e-06, + "loss": 1.5887, + "step": 14673 + }, + { + "epoch": 0.8179031269160024, + "grad_norm": 0.5844617486000061, + "learning_rate": 8.245917539665409e-06, + "loss": 1.7618, + "step": 14674 + }, + { + "epoch": 0.8179588651691656, + "grad_norm": 0.6304042935371399, + "learning_rate": 8.241019749698675e-06, + "loss": 1.9131, + "step": 14675 + }, + { + "epoch": 0.8180146034223288, + "grad_norm": 0.560624897480011, + "learning_rate": 8.236123284083314e-06, + "loss": 1.4943, + "step": 14676 + }, + { + "epoch": 0.8180703416754919, + "grad_norm": 0.6337041854858398, + "learning_rate": 8.231228142974606e-06, + "loss": 1.9758, + "step": 14677 + }, + { + "epoch": 0.818126079928655, + "grad_norm": 0.58197021484375, + "learning_rate": 8.226334326527834e-06, + "loss": 1.6154, + "step": 14678 + }, + { + "epoch": 0.8181818181818182, + "grad_norm": 0.6239030957221985, + "learning_rate": 8.221441834898175e-06, + "loss": 1.6926, + "step": 14679 + }, + { + "epoch": 0.8182375564349813, + "grad_norm": 0.5664547085762024, + "learning_rate": 8.216550668240803e-06, + "loss": 1.7325, + "step": 14680 + }, + { + "epoch": 0.8182932946881445, + "grad_norm": 0.5848506093025208, + "learning_rate": 8.211660826710804e-06, + "loss": 1.6233, + "step": 14681 + }, + { + "epoch": 0.8183490329413077, + "grad_norm": 0.5485044717788696, + "learning_rate": 8.206772310463295e-06, + "loss": 1.5409, + "step": 14682 + }, + { + "epoch": 0.8184047711944707, + "grad_norm": 0.6160194873809814, + "learning_rate": 8.201885119653308e-06, + "loss": 1.9611, + "step": 14683 + }, + { + "epoch": 0.8184605094476339, + "grad_norm": 0.5616006851196289, + "learning_rate": 8.196999254435816e-06, + "loss": 1.7156, + "step": 14684 + }, + { + "epoch": 0.818516247700797, + "grad_norm": 0.6323941946029663, + "learning_rate": 8.192114714965776e-06, + "loss": 1.7105, + "step": 14685 + }, + { + "epoch": 0.8185719859539602, + "grad_norm": 0.6214513778686523, + "learning_rate": 8.187231501398102e-06, + "loss": 1.7029, + "step": 14686 + }, + { + "epoch": 0.8186277242071234, + "grad_norm": 0.5549011826515198, + "learning_rate": 8.18234961388767e-06, + "loss": 1.3432, + "step": 14687 + }, + { + "epoch": 0.8186834624602864, + "grad_norm": 0.5615776181221008, + "learning_rate": 8.17746905258927e-06, + "loss": 1.6022, + "step": 14688 + }, + { + "epoch": 0.8187392007134496, + "grad_norm": 0.5588061213493347, + "learning_rate": 8.172589817657721e-06, + "loss": 1.4637, + "step": 14689 + }, + { + "epoch": 0.8187949389666128, + "grad_norm": 0.5842549800872803, + "learning_rate": 8.167711909247766e-06, + "loss": 1.7603, + "step": 14690 + }, + { + "epoch": 0.8188506772197759, + "grad_norm": 0.6246482729911804, + "learning_rate": 8.16283532751408e-06, + "loss": 1.8689, + "step": 14691 + }, + { + "epoch": 0.8189064154729391, + "grad_norm": 0.5793601274490356, + "learning_rate": 8.157960072611326e-06, + "loss": 1.5218, + "step": 14692 + }, + { + "epoch": 0.8189621537261023, + "grad_norm": 0.6303258538246155, + "learning_rate": 8.153086144694122e-06, + "loss": 1.676, + "step": 14693 + }, + { + "epoch": 0.8190178919792653, + "grad_norm": 0.6256571412086487, + "learning_rate": 8.148213543917055e-06, + "loss": 1.7805, + "step": 14694 + }, + { + "epoch": 0.8190736302324285, + "grad_norm": 0.6186008453369141, + "learning_rate": 8.143342270434629e-06, + "loss": 1.524, + "step": 14695 + }, + { + "epoch": 0.8191293684855917, + "grad_norm": 0.519763171672821, + "learning_rate": 8.138472324401335e-06, + "loss": 1.3755, + "step": 14696 + }, + { + "epoch": 0.8191851067387548, + "grad_norm": 0.5263442993164062, + "learning_rate": 8.133603705971649e-06, + "loss": 1.5122, + "step": 14697 + }, + { + "epoch": 0.819240844991918, + "grad_norm": 0.5439835786819458, + "learning_rate": 8.128736415299948e-06, + "loss": 1.4538, + "step": 14698 + }, + { + "epoch": 0.8192965832450811, + "grad_norm": 0.6475786566734314, + "learning_rate": 8.1238704525406e-06, + "loss": 1.8112, + "step": 14699 + }, + { + "epoch": 0.8193523214982442, + "grad_norm": 0.6076223254203796, + "learning_rate": 8.119005817847924e-06, + "loss": 1.6804, + "step": 14700 + }, + { + "epoch": 0.8194080597514074, + "grad_norm": 0.5878423452377319, + "learning_rate": 8.114142511376215e-06, + "loss": 1.7354, + "step": 14701 + }, + { + "epoch": 0.8194637980045706, + "grad_norm": 0.5754333138465881, + "learning_rate": 8.109280533279684e-06, + "loss": 1.6038, + "step": 14702 + }, + { + "epoch": 0.8195195362577337, + "grad_norm": 0.6017590165138245, + "learning_rate": 8.104419883712517e-06, + "loss": 1.7552, + "step": 14703 + }, + { + "epoch": 0.8195752745108968, + "grad_norm": 0.5602265000343323, + "learning_rate": 8.099560562828911e-06, + "loss": 1.5637, + "step": 14704 + }, + { + "epoch": 0.81963101276406, + "grad_norm": 0.513415515422821, + "learning_rate": 8.094702570782936e-06, + "loss": 1.495, + "step": 14705 + }, + { + "epoch": 0.8196867510172231, + "grad_norm": 0.5594004392623901, + "learning_rate": 8.089845907728682e-06, + "loss": 1.7242, + "step": 14706 + }, + { + "epoch": 0.8197424892703863, + "grad_norm": 0.5501028299331665, + "learning_rate": 8.084990573820133e-06, + "loss": 1.4354, + "step": 14707 + }, + { + "epoch": 0.8197982275235494, + "grad_norm": 0.5331346392631531, + "learning_rate": 8.080136569211322e-06, + "loss": 1.7557, + "step": 14708 + }, + { + "epoch": 0.8198539657767125, + "grad_norm": 0.5430104732513428, + "learning_rate": 8.075283894056178e-06, + "loss": 1.6358, + "step": 14709 + }, + { + "epoch": 0.8199097040298757, + "grad_norm": 0.5166445970535278, + "learning_rate": 8.070432548508578e-06, + "loss": 1.572, + "step": 14710 + }, + { + "epoch": 0.8199654422830388, + "grad_norm": 0.5667523741722107, + "learning_rate": 8.065582532722394e-06, + "loss": 1.6363, + "step": 14711 + }, + { + "epoch": 0.820021180536202, + "grad_norm": 0.5528684258460999, + "learning_rate": 8.060733846851432e-06, + "loss": 1.4092, + "step": 14712 + }, + { + "epoch": 0.8200769187893652, + "grad_norm": 0.5996767282485962, + "learning_rate": 8.055886491049486e-06, + "loss": 1.8248, + "step": 14713 + }, + { + "epoch": 0.8201326570425282, + "grad_norm": 0.5381787419319153, + "learning_rate": 8.051040465470245e-06, + "loss": 1.517, + "step": 14714 + }, + { + "epoch": 0.8201883952956914, + "grad_norm": 0.5631827712059021, + "learning_rate": 8.046195770267428e-06, + "loss": 1.7852, + "step": 14715 + }, + { + "epoch": 0.8202441335488546, + "grad_norm": 0.5505089163780212, + "learning_rate": 8.041352405594692e-06, + "loss": 1.615, + "step": 14716 + }, + { + "epoch": 0.8202998718020177, + "grad_norm": 0.5934506058692932, + "learning_rate": 8.03651037160561e-06, + "loss": 1.6671, + "step": 14717 + }, + { + "epoch": 0.8203556100551809, + "grad_norm": 0.5772705674171448, + "learning_rate": 8.031669668453752e-06, + "loss": 1.682, + "step": 14718 + }, + { + "epoch": 0.8204113483083441, + "grad_norm": 0.5619063973426819, + "learning_rate": 8.026830296292636e-06, + "loss": 1.762, + "step": 14719 + }, + { + "epoch": 0.8204670865615071, + "grad_norm": 0.5829328894615173, + "learning_rate": 8.021992255275763e-06, + "loss": 1.73, + "step": 14720 + }, + { + "epoch": 0.8205228248146703, + "grad_norm": 0.5251481533050537, + "learning_rate": 8.017155545556527e-06, + "loss": 1.6057, + "step": 14721 + }, + { + "epoch": 0.8205785630678335, + "grad_norm": 0.5804221630096436, + "learning_rate": 8.012320167288334e-06, + "loss": 1.4836, + "step": 14722 + }, + { + "epoch": 0.8206343013209966, + "grad_norm": 0.5928997993469238, + "learning_rate": 8.007486120624559e-06, + "loss": 1.8501, + "step": 14723 + }, + { + "epoch": 0.8206900395741598, + "grad_norm": 0.5831340551376343, + "learning_rate": 8.002653405718485e-06, + "loss": 1.6392, + "step": 14724 + }, + { + "epoch": 0.8207457778273229, + "grad_norm": 0.5551106929779053, + "learning_rate": 7.997822022723378e-06, + "loss": 1.5372, + "step": 14725 + }, + { + "epoch": 0.820801516080486, + "grad_norm": 0.5780943036079407, + "learning_rate": 7.992991971792469e-06, + "loss": 1.6999, + "step": 14726 + }, + { + "epoch": 0.8208572543336492, + "grad_norm": 0.5924753546714783, + "learning_rate": 7.988163253078952e-06, + "loss": 1.6596, + "step": 14727 + }, + { + "epoch": 0.8209129925868124, + "grad_norm": 0.5651062726974487, + "learning_rate": 7.98333586673593e-06, + "loss": 1.4913, + "step": 14728 + }, + { + "epoch": 0.8209687308399755, + "grad_norm": 0.5695908069610596, + "learning_rate": 7.978509812916513e-06, + "loss": 1.7483, + "step": 14729 + }, + { + "epoch": 0.8210244690931386, + "grad_norm": 0.575892984867096, + "learning_rate": 7.973685091773792e-06, + "loss": 1.5914, + "step": 14730 + }, + { + "epoch": 0.8210802073463017, + "grad_norm": 0.5623947381973267, + "learning_rate": 7.968861703460728e-06, + "loss": 1.5902, + "step": 14731 + }, + { + "epoch": 0.8211359455994649, + "grad_norm": 0.5500161647796631, + "learning_rate": 7.964039648130328e-06, + "loss": 1.6152, + "step": 14732 + }, + { + "epoch": 0.8211916838526281, + "grad_norm": 0.5211798548698425, + "learning_rate": 7.95921892593548e-06, + "loss": 1.3945, + "step": 14733 + }, + { + "epoch": 0.8212474221057912, + "grad_norm": 0.5861966609954834, + "learning_rate": 7.954399537029106e-06, + "loss": 1.5801, + "step": 14734 + }, + { + "epoch": 0.8213031603589543, + "grad_norm": 0.5749439001083374, + "learning_rate": 7.94958148156405e-06, + "loss": 1.56, + "step": 14735 + }, + { + "epoch": 0.8213588986121175, + "grad_norm": 0.5986553430557251, + "learning_rate": 7.94476475969308e-06, + "loss": 1.6339, + "step": 14736 + }, + { + "epoch": 0.8214146368652806, + "grad_norm": 0.5730953216552734, + "learning_rate": 7.939949371568977e-06, + "loss": 1.7142, + "step": 14737 + }, + { + "epoch": 0.8214703751184438, + "grad_norm": 0.5454463362693787, + "learning_rate": 7.935135317344455e-06, + "loss": 1.5694, + "step": 14738 + }, + { + "epoch": 0.821526113371607, + "grad_norm": 0.5606818795204163, + "learning_rate": 7.930322597172191e-06, + "loss": 1.5784, + "step": 14739 + }, + { + "epoch": 0.82158185162477, + "grad_norm": 0.5257277488708496, + "learning_rate": 7.925511211204795e-06, + "loss": 1.6162, + "step": 14740 + }, + { + "epoch": 0.8216375898779332, + "grad_norm": 0.5445712208747864, + "learning_rate": 7.92070115959488e-06, + "loss": 1.6094, + "step": 14741 + }, + { + "epoch": 0.8216933281310964, + "grad_norm": 0.5786468386650085, + "learning_rate": 7.915892442494994e-06, + "loss": 1.6552, + "step": 14742 + }, + { + "epoch": 0.8217490663842595, + "grad_norm": 0.5710452795028687, + "learning_rate": 7.911085060057621e-06, + "loss": 1.7177, + "step": 14743 + }, + { + "epoch": 0.8218048046374227, + "grad_norm": 0.6072984933853149, + "learning_rate": 7.906279012435237e-06, + "loss": 1.8521, + "step": 14744 + }, + { + "epoch": 0.8218605428905859, + "grad_norm": 0.5253605842590332, + "learning_rate": 7.901474299780258e-06, + "loss": 1.3688, + "step": 14745 + }, + { + "epoch": 0.8219162811437489, + "grad_norm": 0.6044268012046814, + "learning_rate": 7.89667092224508e-06, + "loss": 1.7278, + "step": 14746 + }, + { + "epoch": 0.8219720193969121, + "grad_norm": 0.5338749885559082, + "learning_rate": 7.891868879982001e-06, + "loss": 1.5499, + "step": 14747 + }, + { + "epoch": 0.8220277576500753, + "grad_norm": 0.5516805648803711, + "learning_rate": 7.887068173143325e-06, + "loss": 1.5249, + "step": 14748 + }, + { + "epoch": 0.8220834959032384, + "grad_norm": 0.5159933567047119, + "learning_rate": 7.882268801881337e-06, + "loss": 1.4663, + "step": 14749 + }, + { + "epoch": 0.8221392341564016, + "grad_norm": 0.5163145661354065, + "learning_rate": 7.877470766348206e-06, + "loss": 1.3222, + "step": 14750 + }, + { + "epoch": 0.8221949724095647, + "grad_norm": 0.5524355173110962, + "learning_rate": 7.872674066696112e-06, + "loss": 1.6223, + "step": 14751 + }, + { + "epoch": 0.8222507106627278, + "grad_norm": 0.5480507016181946, + "learning_rate": 7.867878703077175e-06, + "loss": 1.6545, + "step": 14752 + }, + { + "epoch": 0.822306448915891, + "grad_norm": 0.5572043061256409, + "learning_rate": 7.86308467564349e-06, + "loss": 1.5277, + "step": 14753 + }, + { + "epoch": 0.8223621871690541, + "grad_norm": 0.6016210317611694, + "learning_rate": 7.858291984547072e-06, + "loss": 1.6744, + "step": 14754 + }, + { + "epoch": 0.8224179254222173, + "grad_norm": 0.5957650542259216, + "learning_rate": 7.85350062993992e-06, + "loss": 1.7234, + "step": 14755 + }, + { + "epoch": 0.8224736636753804, + "grad_norm": 0.5599290728569031, + "learning_rate": 7.848710611974019e-06, + "loss": 1.6461, + "step": 14756 + }, + { + "epoch": 0.8225294019285435, + "grad_norm": 0.5692183971405029, + "learning_rate": 7.843921930801245e-06, + "loss": 1.427, + "step": 14757 + }, + { + "epoch": 0.8225851401817067, + "grad_norm": 0.5449408888816833, + "learning_rate": 7.839134586573493e-06, + "loss": 1.5931, + "step": 14758 + }, + { + "epoch": 0.8226408784348699, + "grad_norm": 0.5386254787445068, + "learning_rate": 7.834348579442553e-06, + "loss": 1.6162, + "step": 14759 + }, + { + "epoch": 0.822696616688033, + "grad_norm": 0.5870130658149719, + "learning_rate": 7.829563909560256e-06, + "loss": 1.6442, + "step": 14760 + }, + { + "epoch": 0.8227523549411961, + "grad_norm": 0.5991342663764954, + "learning_rate": 7.824780577078311e-06, + "loss": 1.7833, + "step": 14761 + }, + { + "epoch": 0.8228080931943593, + "grad_norm": 0.5483075380325317, + "learning_rate": 7.81999858214843e-06, + "loss": 1.7263, + "step": 14762 + }, + { + "epoch": 0.8228638314475224, + "grad_norm": 0.5456960797309875, + "learning_rate": 7.815217924922264e-06, + "loss": 1.6074, + "step": 14763 + }, + { + "epoch": 0.8229195697006856, + "grad_norm": 0.5569692850112915, + "learning_rate": 7.81043860555143e-06, + "loss": 1.7478, + "step": 14764 + }, + { + "epoch": 0.8229753079538488, + "grad_norm": 0.5834555625915527, + "learning_rate": 7.805660624187516e-06, + "loss": 1.6435, + "step": 14765 + }, + { + "epoch": 0.8230310462070118, + "grad_norm": 0.5573313236236572, + "learning_rate": 7.80088398098201e-06, + "loss": 1.5407, + "step": 14766 + }, + { + "epoch": 0.823086784460175, + "grad_norm": 0.557045578956604, + "learning_rate": 7.796108676086445e-06, + "loss": 1.7211, + "step": 14767 + }, + { + "epoch": 0.8231425227133382, + "grad_norm": 0.5935823321342468, + "learning_rate": 7.791334709652254e-06, + "loss": 1.6505, + "step": 14768 + }, + { + "epoch": 0.8231982609665013, + "grad_norm": 0.6052401661872864, + "learning_rate": 7.786562081830817e-06, + "loss": 1.6837, + "step": 14769 + }, + { + "epoch": 0.8232539992196645, + "grad_norm": 0.5678144693374634, + "learning_rate": 7.781790792773514e-06, + "loss": 1.642, + "step": 14770 + }, + { + "epoch": 0.8233097374728277, + "grad_norm": 0.5625177025794983, + "learning_rate": 7.777020842631656e-06, + "loss": 1.6248, + "step": 14771 + }, + { + "epoch": 0.8233654757259907, + "grad_norm": 0.5575246214866638, + "learning_rate": 7.772252231556531e-06, + "loss": 1.7027, + "step": 14772 + }, + { + "epoch": 0.8234212139791539, + "grad_norm": 0.5748698711395264, + "learning_rate": 7.76748495969935e-06, + "loss": 1.5712, + "step": 14773 + }, + { + "epoch": 0.8234769522323171, + "grad_norm": 0.5593873262405396, + "learning_rate": 7.762719027211308e-06, + "loss": 1.3786, + "step": 14774 + }, + { + "epoch": 0.8235326904854802, + "grad_norm": 0.5477203130722046, + "learning_rate": 7.75795443424357e-06, + "loss": 1.5349, + "step": 14775 + }, + { + "epoch": 0.8235884287386434, + "grad_norm": 0.6124054193496704, + "learning_rate": 7.753191180947223e-06, + "loss": 1.7259, + "step": 14776 + }, + { + "epoch": 0.8236441669918064, + "grad_norm": 0.6015963554382324, + "learning_rate": 7.74842926747334e-06, + "loss": 1.5049, + "step": 14777 + }, + { + "epoch": 0.8236999052449696, + "grad_norm": 0.5595274567604065, + "learning_rate": 7.743668693972927e-06, + "loss": 1.5613, + "step": 14778 + }, + { + "epoch": 0.8237556434981328, + "grad_norm": 0.575369119644165, + "learning_rate": 7.738909460596994e-06, + "loss": 1.744, + "step": 14779 + }, + { + "epoch": 0.8238113817512959, + "grad_norm": 0.5448950529098511, + "learning_rate": 7.734151567496434e-06, + "loss": 1.5413, + "step": 14780 + }, + { + "epoch": 0.823867120004459, + "grad_norm": 0.5308200716972351, + "learning_rate": 7.729395014822149e-06, + "loss": 1.6224, + "step": 14781 + }, + { + "epoch": 0.8239228582576222, + "grad_norm": 0.5744593143463135, + "learning_rate": 7.724639802725025e-06, + "loss": 1.7152, + "step": 14782 + }, + { + "epoch": 0.8239785965107853, + "grad_norm": 0.552858293056488, + "learning_rate": 7.71988593135583e-06, + "loss": 1.7338, + "step": 14783 + }, + { + "epoch": 0.8240343347639485, + "grad_norm": 0.567445695400238, + "learning_rate": 7.715133400865342e-06, + "loss": 1.735, + "step": 14784 + }, + { + "epoch": 0.8240900730171117, + "grad_norm": 0.5928866267204285, + "learning_rate": 7.710382211404288e-06, + "loss": 1.7797, + "step": 14785 + }, + { + "epoch": 0.8241458112702748, + "grad_norm": 0.5809508562088013, + "learning_rate": 7.705632363123355e-06, + "loss": 1.7308, + "step": 14786 + }, + { + "epoch": 0.8242015495234379, + "grad_norm": 0.5642045736312866, + "learning_rate": 7.700883856173164e-06, + "loss": 1.4567, + "step": 14787 + }, + { + "epoch": 0.8242572877766011, + "grad_norm": 0.5252789855003357, + "learning_rate": 7.696136690704309e-06, + "loss": 1.3691, + "step": 14788 + }, + { + "epoch": 0.8243130260297642, + "grad_norm": 0.6067389845848083, + "learning_rate": 7.691390866867348e-06, + "loss": 1.578, + "step": 14789 + }, + { + "epoch": 0.8243687642829274, + "grad_norm": 0.5476150512695312, + "learning_rate": 7.686646384812802e-06, + "loss": 1.5294, + "step": 14790 + }, + { + "epoch": 0.8244245025360906, + "grad_norm": 0.5800880193710327, + "learning_rate": 7.68190324469113e-06, + "loss": 1.6699, + "step": 14791 + }, + { + "epoch": 0.8244802407892536, + "grad_norm": 0.6214286088943481, + "learning_rate": 7.677161446652736e-06, + "loss": 1.6154, + "step": 14792 + }, + { + "epoch": 0.8245359790424168, + "grad_norm": 0.61076819896698, + "learning_rate": 7.672420990848033e-06, + "loss": 1.7302, + "step": 14793 + }, + { + "epoch": 0.82459171729558, + "grad_norm": 0.5480033755302429, + "learning_rate": 7.667681877427363e-06, + "loss": 1.5814, + "step": 14794 + }, + { + "epoch": 0.8246474555487431, + "grad_norm": 0.5674887299537659, + "learning_rate": 7.662944106540998e-06, + "loss": 1.6489, + "step": 14795 + }, + { + "epoch": 0.8247031938019063, + "grad_norm": 0.6398147940635681, + "learning_rate": 7.658207678339202e-06, + "loss": 1.8268, + "step": 14796 + }, + { + "epoch": 0.8247589320550694, + "grad_norm": 0.5531885623931885, + "learning_rate": 7.653472592972188e-06, + "loss": 1.6168, + "step": 14797 + }, + { + "epoch": 0.8248146703082325, + "grad_norm": 0.5649216175079346, + "learning_rate": 7.648738850590137e-06, + "loss": 1.5265, + "step": 14798 + }, + { + "epoch": 0.8248704085613957, + "grad_norm": 0.5621973276138306, + "learning_rate": 7.644006451343156e-06, + "loss": 1.774, + "step": 14799 + }, + { + "epoch": 0.8249261468145588, + "grad_norm": 0.5101774334907532, + "learning_rate": 7.639275395381324e-06, + "loss": 1.5918, + "step": 14800 + }, + { + "epoch": 0.824981885067722, + "grad_norm": 0.5356602072715759, + "learning_rate": 7.63454568285472e-06, + "loss": 1.5562, + "step": 14801 + }, + { + "epoch": 0.8250376233208851, + "grad_norm": 0.58839350938797, + "learning_rate": 7.629817313913306e-06, + "loss": 1.6387, + "step": 14802 + }, + { + "epoch": 0.8250933615740482, + "grad_norm": 0.5281109809875488, + "learning_rate": 7.625090288707054e-06, + "loss": 1.5421, + "step": 14803 + }, + { + "epoch": 0.8251490998272114, + "grad_norm": 0.5732079744338989, + "learning_rate": 7.620364607385877e-06, + "loss": 1.6407, + "step": 14804 + }, + { + "epoch": 0.8252048380803746, + "grad_norm": 0.5893906354904175, + "learning_rate": 7.61564027009965e-06, + "loss": 1.7231, + "step": 14805 + }, + { + "epoch": 0.8252605763335377, + "grad_norm": 0.5752212405204773, + "learning_rate": 7.610917276998192e-06, + "loss": 1.4615, + "step": 14806 + }, + { + "epoch": 0.8253163145867008, + "grad_norm": 0.5605239272117615, + "learning_rate": 7.606195628231272e-06, + "loss": 1.6183, + "step": 14807 + }, + { + "epoch": 0.825372052839864, + "grad_norm": 0.5010392069816589, + "learning_rate": 7.6014753239486815e-06, + "loss": 1.4315, + "step": 14808 + }, + { + "epoch": 0.8254277910930271, + "grad_norm": 0.6002615690231323, + "learning_rate": 7.596756364300084e-06, + "loss": 1.7067, + "step": 14809 + }, + { + "epoch": 0.8254835293461903, + "grad_norm": 0.6006166934967041, + "learning_rate": 7.592038749435143e-06, + "loss": 1.7114, + "step": 14810 + }, + { + "epoch": 0.8255392675993535, + "grad_norm": 0.5413761138916016, + "learning_rate": 7.587322479503478e-06, + "loss": 1.5799, + "step": 14811 + }, + { + "epoch": 0.8255950058525166, + "grad_norm": 0.5678083896636963, + "learning_rate": 7.582607554654669e-06, + "loss": 1.6757, + "step": 14812 + }, + { + "epoch": 0.8256507441056797, + "grad_norm": 0.5252918601036072, + "learning_rate": 7.577893975038231e-06, + "loss": 1.6212, + "step": 14813 + }, + { + "epoch": 0.8257064823588429, + "grad_norm": 0.5357844233512878, + "learning_rate": 7.573181740803659e-06, + "loss": 1.5161, + "step": 14814 + }, + { + "epoch": 0.825762220612006, + "grad_norm": 0.4912710189819336, + "learning_rate": 7.568470852100396e-06, + "loss": 1.2616, + "step": 14815 + }, + { + "epoch": 0.8258179588651692, + "grad_norm": 0.5815874934196472, + "learning_rate": 7.563761309077838e-06, + "loss": 1.7431, + "step": 14816 + }, + { + "epoch": 0.8258736971183324, + "grad_norm": 0.5636022090911865, + "learning_rate": 7.559053111885372e-06, + "loss": 1.5336, + "step": 14817 + }, + { + "epoch": 0.8259294353714954, + "grad_norm": 0.5679888129234314, + "learning_rate": 7.5543462606722624e-06, + "loss": 1.5636, + "step": 14818 + }, + { + "epoch": 0.8259851736246586, + "grad_norm": 0.5726489424705505, + "learning_rate": 7.5496407555878276e-06, + "loss": 1.6993, + "step": 14819 + }, + { + "epoch": 0.8260409118778218, + "grad_norm": 0.5466410517692566, + "learning_rate": 7.544936596781299e-06, + "loss": 1.4985, + "step": 14820 + }, + { + "epoch": 0.8260966501309849, + "grad_norm": 0.5589420795440674, + "learning_rate": 7.54023378440184e-06, + "loss": 1.4959, + "step": 14821 + }, + { + "epoch": 0.8261523883841481, + "grad_norm": 0.5536938309669495, + "learning_rate": 7.535532318598609e-06, + "loss": 1.5709, + "step": 14822 + }, + { + "epoch": 0.8262081266373111, + "grad_norm": 0.5842770338058472, + "learning_rate": 7.530832199520705e-06, + "loss": 1.8395, + "step": 14823 + }, + { + "epoch": 0.8262638648904743, + "grad_norm": 0.6140356659889221, + "learning_rate": 7.5261334273172e-06, + "loss": 1.7728, + "step": 14824 + }, + { + "epoch": 0.8263196031436375, + "grad_norm": 0.6124187111854553, + "learning_rate": 7.5214360021371e-06, + "loss": 1.6189, + "step": 14825 + }, + { + "epoch": 0.8263753413968006, + "grad_norm": 0.5564613938331604, + "learning_rate": 7.516739924129362e-06, + "loss": 1.4719, + "step": 14826 + }, + { + "epoch": 0.8264310796499638, + "grad_norm": 0.5939016938209534, + "learning_rate": 7.512045193442968e-06, + "loss": 1.6933, + "step": 14827 + }, + { + "epoch": 0.826486817903127, + "grad_norm": 0.6369741559028625, + "learning_rate": 7.507351810226765e-06, + "loss": 1.9048, + "step": 14828 + }, + { + "epoch": 0.82654255615629, + "grad_norm": 0.5417369604110718, + "learning_rate": 7.502659774629612e-06, + "loss": 1.6225, + "step": 14829 + }, + { + "epoch": 0.8265982944094532, + "grad_norm": 0.5475333333015442, + "learning_rate": 7.4979690868003165e-06, + "loss": 1.6123, + "step": 14830 + }, + { + "epoch": 0.8266540326626164, + "grad_norm": 0.6035535931587219, + "learning_rate": 7.493279746887649e-06, + "loss": 1.5044, + "step": 14831 + }, + { + "epoch": 0.8267097709157795, + "grad_norm": 0.5344101190567017, + "learning_rate": 7.488591755040303e-06, + "loss": 1.4167, + "step": 14832 + }, + { + "epoch": 0.8267655091689426, + "grad_norm": 0.5738053321838379, + "learning_rate": 7.483905111406958e-06, + "loss": 1.565, + "step": 14833 + }, + { + "epoch": 0.8268212474221058, + "grad_norm": 0.5430249571800232, + "learning_rate": 7.479219816136279e-06, + "loss": 1.503, + "step": 14834 + }, + { + "epoch": 0.8268769856752689, + "grad_norm": 0.5295128226280212, + "learning_rate": 7.474535869376819e-06, + "loss": 1.4863, + "step": 14835 + }, + { + "epoch": 0.8269327239284321, + "grad_norm": 0.5527878403663635, + "learning_rate": 7.46985327127715e-06, + "loss": 1.5387, + "step": 14836 + }, + { + "epoch": 0.8269884621815953, + "grad_norm": 0.5978548526763916, + "learning_rate": 7.465172021985761e-06, + "loss": 1.6446, + "step": 14837 + }, + { + "epoch": 0.8270442004347583, + "grad_norm": 0.5778266191482544, + "learning_rate": 7.46049212165113e-06, + "loss": 1.3285, + "step": 14838 + }, + { + "epoch": 0.8270999386879215, + "grad_norm": 0.5653694868087769, + "learning_rate": 7.45581357042166e-06, + "loss": 1.6796, + "step": 14839 + }, + { + "epoch": 0.8271556769410847, + "grad_norm": 0.5550215244293213, + "learning_rate": 7.451136368445727e-06, + "loss": 1.513, + "step": 14840 + }, + { + "epoch": 0.8272114151942478, + "grad_norm": 0.5472756624221802, + "learning_rate": 7.446460515871678e-06, + "loss": 1.4862, + "step": 14841 + }, + { + "epoch": 0.827267153447411, + "grad_norm": 0.5686060786247253, + "learning_rate": 7.441786012847795e-06, + "loss": 1.6166, + "step": 14842 + }, + { + "epoch": 0.8273228917005742, + "grad_norm": 0.5672643184661865, + "learning_rate": 7.437112859522339e-06, + "loss": 1.7089, + "step": 14843 + }, + { + "epoch": 0.8273786299537372, + "grad_norm": 0.5945203900337219, + "learning_rate": 7.4324410560434825e-06, + "loss": 1.6842, + "step": 14844 + }, + { + "epoch": 0.8274343682069004, + "grad_norm": 0.5317419171333313, + "learning_rate": 7.42777060255942e-06, + "loss": 1.7236, + "step": 14845 + }, + { + "epoch": 0.8274901064600635, + "grad_norm": 0.5510501265525818, + "learning_rate": 7.423101499218272e-06, + "loss": 1.7382, + "step": 14846 + }, + { + "epoch": 0.8275458447132267, + "grad_norm": 0.5681928396224976, + "learning_rate": 7.4184337461680905e-06, + "loss": 1.5124, + "step": 14847 + }, + { + "epoch": 0.8276015829663899, + "grad_norm": 0.5582361817359924, + "learning_rate": 7.4137673435569266e-06, + "loss": 1.5824, + "step": 14848 + }, + { + "epoch": 0.8276573212195529, + "grad_norm": 0.5670194029808044, + "learning_rate": 7.409102291532766e-06, + "loss": 1.5791, + "step": 14849 + }, + { + "epoch": 0.8277130594727161, + "grad_norm": 0.5458555817604065, + "learning_rate": 7.404438590243568e-06, + "loss": 1.69, + "step": 14850 + }, + { + "epoch": 0.8277687977258793, + "grad_norm": 0.588135838508606, + "learning_rate": 7.399776239837208e-06, + "loss": 1.9097, + "step": 14851 + }, + { + "epoch": 0.8278245359790424, + "grad_norm": 0.5528299808502197, + "learning_rate": 7.395115240461581e-06, + "loss": 1.6214, + "step": 14852 + }, + { + "epoch": 0.8278802742322056, + "grad_norm": 0.616841197013855, + "learning_rate": 7.390455592264506e-06, + "loss": 1.8655, + "step": 14853 + }, + { + "epoch": 0.8279360124853687, + "grad_norm": 0.5567806959152222, + "learning_rate": 7.385797295393732e-06, + "loss": 1.6002, + "step": 14854 + }, + { + "epoch": 0.8279917507385318, + "grad_norm": 0.5780771374702454, + "learning_rate": 7.381140349997018e-06, + "loss": 1.7274, + "step": 14855 + }, + { + "epoch": 0.828047488991695, + "grad_norm": 0.6161444783210754, + "learning_rate": 7.376484756222041e-06, + "loss": 1.8171, + "step": 14856 + }, + { + "epoch": 0.8281032272448582, + "grad_norm": 0.6308067440986633, + "learning_rate": 7.371830514216471e-06, + "loss": 1.6465, + "step": 14857 + }, + { + "epoch": 0.8281589654980213, + "grad_norm": 0.5672606229782104, + "learning_rate": 7.3671776241278856e-06, + "loss": 1.5607, + "step": 14858 + }, + { + "epoch": 0.8282147037511844, + "grad_norm": 0.5984612107276917, + "learning_rate": 7.362526086103844e-06, + "loss": 1.7207, + "step": 14859 + }, + { + "epoch": 0.8282704420043476, + "grad_norm": 0.5337589979171753, + "learning_rate": 7.357875900291905e-06, + "loss": 1.5266, + "step": 14860 + }, + { + "epoch": 0.8283261802575107, + "grad_norm": 0.5842846035957336, + "learning_rate": 7.353227066839513e-06, + "loss": 1.6808, + "step": 14861 + }, + { + "epoch": 0.8283819185106739, + "grad_norm": 0.5503394603729248, + "learning_rate": 7.348579585894111e-06, + "loss": 1.5349, + "step": 14862 + }, + { + "epoch": 0.8284376567638371, + "grad_norm": 0.5789114236831665, + "learning_rate": 7.3439334576030864e-06, + "loss": 1.7059, + "step": 14863 + }, + { + "epoch": 0.8284933950170001, + "grad_norm": 0.5610846877098083, + "learning_rate": 7.339288682113804e-06, + "loss": 1.7997, + "step": 14864 + }, + { + "epoch": 0.8285491332701633, + "grad_norm": 0.5403236746788025, + "learning_rate": 7.334645259573541e-06, + "loss": 1.4615, + "step": 14865 + }, + { + "epoch": 0.8286048715233265, + "grad_norm": 0.5676838755607605, + "learning_rate": 7.330003190129575e-06, + "loss": 1.6691, + "step": 14866 + }, + { + "epoch": 0.8286606097764896, + "grad_norm": 0.5780337452888489, + "learning_rate": 7.325362473929126e-06, + "loss": 1.6924, + "step": 14867 + }, + { + "epoch": 0.8287163480296528, + "grad_norm": 0.5940248966217041, + "learning_rate": 7.320723111119371e-06, + "loss": 1.8302, + "step": 14868 + }, + { + "epoch": 0.8287720862828158, + "grad_norm": 0.5656587481498718, + "learning_rate": 7.316085101847453e-06, + "loss": 1.5856, + "step": 14869 + }, + { + "epoch": 0.828827824535979, + "grad_norm": 0.5414813160896301, + "learning_rate": 7.311448446260422e-06, + "loss": 1.5342, + "step": 14870 + }, + { + "epoch": 0.8288835627891422, + "grad_norm": 0.5124301910400391, + "learning_rate": 7.306813144505381e-06, + "loss": 1.4847, + "step": 14871 + }, + { + "epoch": 0.8289393010423053, + "grad_norm": 0.6682723164558411, + "learning_rate": 7.3021791967292976e-06, + "loss": 1.8871, + "step": 14872 + }, + { + "epoch": 0.8289950392954685, + "grad_norm": 0.5085262060165405, + "learning_rate": 7.297546603079147e-06, + "loss": 1.5112, + "step": 14873 + }, + { + "epoch": 0.8290507775486317, + "grad_norm": 0.5488193035125732, + "learning_rate": 7.292915363701841e-06, + "loss": 1.2755, + "step": 14874 + }, + { + "epoch": 0.8291065158017947, + "grad_norm": 0.5370182991027832, + "learning_rate": 7.288285478744261e-06, + "loss": 1.5412, + "step": 14875 + }, + { + "epoch": 0.8291622540549579, + "grad_norm": 0.5484380125999451, + "learning_rate": 7.283656948353251e-06, + "loss": 1.7214, + "step": 14876 + }, + { + "epoch": 0.8292179923081211, + "grad_norm": 0.5984296202659607, + "learning_rate": 7.2790297726755716e-06, + "loss": 1.9109, + "step": 14877 + }, + { + "epoch": 0.8292737305612842, + "grad_norm": 0.5639859437942505, + "learning_rate": 7.274403951857994e-06, + "loss": 1.5359, + "step": 14878 + }, + { + "epoch": 0.8293294688144474, + "grad_norm": 0.5411209464073181, + "learning_rate": 7.2697794860472235e-06, + "loss": 1.6992, + "step": 14879 + }, + { + "epoch": 0.8293852070676105, + "grad_norm": 0.5661779046058655, + "learning_rate": 7.265156375389909e-06, + "loss": 1.6467, + "step": 14880 + }, + { + "epoch": 0.8294409453207736, + "grad_norm": 0.5306726098060608, + "learning_rate": 7.260534620032667e-06, + "loss": 1.7689, + "step": 14881 + }, + { + "epoch": 0.8294966835739368, + "grad_norm": 0.5563758611679077, + "learning_rate": 7.255914220122078e-06, + "loss": 1.7601, + "step": 14882 + }, + { + "epoch": 0.8295524218271, + "grad_norm": 0.5583815574645996, + "learning_rate": 7.25129517580469e-06, + "loss": 1.731, + "step": 14883 + }, + { + "epoch": 0.8296081600802631, + "grad_norm": 0.5571249723434448, + "learning_rate": 7.246677487226966e-06, + "loss": 1.6389, + "step": 14884 + }, + { + "epoch": 0.8296638983334262, + "grad_norm": 0.5696853399276733, + "learning_rate": 7.242061154535346e-06, + "loss": 1.6421, + "step": 14885 + }, + { + "epoch": 0.8297196365865894, + "grad_norm": 0.5597503781318665, + "learning_rate": 7.237446177876278e-06, + "loss": 1.4844, + "step": 14886 + }, + { + "epoch": 0.8297753748397525, + "grad_norm": 0.5343501567840576, + "learning_rate": 7.23283255739608e-06, + "loss": 1.478, + "step": 14887 + }, + { + "epoch": 0.8298311130929157, + "grad_norm": 0.5455690026283264, + "learning_rate": 7.228220293241084e-06, + "loss": 1.7255, + "step": 14888 + }, + { + "epoch": 0.8298868513460789, + "grad_norm": 0.5314241051673889, + "learning_rate": 7.223609385557567e-06, + "loss": 1.4374, + "step": 14889 + }, + { + "epoch": 0.8299425895992419, + "grad_norm": 0.589161217212677, + "learning_rate": 7.2189998344917635e-06, + "loss": 1.5534, + "step": 14890 + }, + { + "epoch": 0.8299983278524051, + "grad_norm": 0.5816118121147156, + "learning_rate": 7.214391640189844e-06, + "loss": 1.683, + "step": 14891 + }, + { + "epoch": 0.8300540661055682, + "grad_norm": 0.5937685966491699, + "learning_rate": 7.209784802797964e-06, + "loss": 1.6317, + "step": 14892 + }, + { + "epoch": 0.8301098043587314, + "grad_norm": 0.5852888822555542, + "learning_rate": 7.20517932246223e-06, + "loss": 1.8489, + "step": 14893 + }, + { + "epoch": 0.8301655426118946, + "grad_norm": 0.5392382740974426, + "learning_rate": 7.200575199328691e-06, + "loss": 1.6475, + "step": 14894 + }, + { + "epoch": 0.8302212808650576, + "grad_norm": 0.5379775166511536, + "learning_rate": 7.195972433543386e-06, + "loss": 1.5613, + "step": 14895 + }, + { + "epoch": 0.8302770191182208, + "grad_norm": 0.5524624586105347, + "learning_rate": 7.191371025252242e-06, + "loss": 1.5859, + "step": 14896 + }, + { + "epoch": 0.830332757371384, + "grad_norm": 0.5549662113189697, + "learning_rate": 7.186770974601242e-06, + "loss": 1.7449, + "step": 14897 + }, + { + "epoch": 0.8303884956245471, + "grad_norm": 0.9866027235984802, + "learning_rate": 7.182172281736244e-06, + "loss": 1.6864, + "step": 14898 + }, + { + "epoch": 0.8304442338777103, + "grad_norm": 0.5486053228378296, + "learning_rate": 7.177574946803084e-06, + "loss": 1.752, + "step": 14899 + }, + { + "epoch": 0.8304999721308735, + "grad_norm": 0.5818338990211487, + "learning_rate": 7.172978969947586e-06, + "loss": 1.5253, + "step": 14900 + }, + { + "epoch": 0.8305557103840365, + "grad_norm": 0.5546401739120483, + "learning_rate": 7.168384351315488e-06, + "loss": 1.7083, + "step": 14901 + }, + { + "epoch": 0.8306114486371997, + "grad_norm": 0.5562866926193237, + "learning_rate": 7.163791091052524e-06, + "loss": 1.5918, + "step": 14902 + }, + { + "epoch": 0.8306671868903629, + "grad_norm": 0.5581058859825134, + "learning_rate": 7.1591991893043384e-06, + "loss": 1.673, + "step": 14903 + }, + { + "epoch": 0.830722925143526, + "grad_norm": 0.6358676552772522, + "learning_rate": 7.1546086462165816e-06, + "loss": 1.837, + "step": 14904 + }, + { + "epoch": 0.8307786633966892, + "grad_norm": 0.5933240652084351, + "learning_rate": 7.150019461934843e-06, + "loss": 1.7407, + "step": 14905 + }, + { + "epoch": 0.8308344016498523, + "grad_norm": 0.5273723006248474, + "learning_rate": 7.145431636604644e-06, + "loss": 1.4998, + "step": 14906 + }, + { + "epoch": 0.8308901399030154, + "grad_norm": 0.5660163164138794, + "learning_rate": 7.140845170371496e-06, + "loss": 1.5029, + "step": 14907 + }, + { + "epoch": 0.8309458781561786, + "grad_norm": 0.5751037001609802, + "learning_rate": 7.136260063380851e-06, + "loss": 1.5846, + "step": 14908 + }, + { + "epoch": 0.8310016164093418, + "grad_norm": 0.601863443851471, + "learning_rate": 7.131676315778135e-06, + "loss": 1.749, + "step": 14909 + }, + { + "epoch": 0.8310573546625049, + "grad_norm": 0.586399495601654, + "learning_rate": 7.1270939277087e-06, + "loss": 1.6114, + "step": 14910 + }, + { + "epoch": 0.831113092915668, + "grad_norm": 0.5683432221412659, + "learning_rate": 7.122512899317862e-06, + "loss": 1.7493, + "step": 14911 + }, + { + "epoch": 0.8311688311688312, + "grad_norm": 0.5420761704444885, + "learning_rate": 7.11793323075095e-06, + "loss": 1.5338, + "step": 14912 + }, + { + "epoch": 0.8312245694219943, + "grad_norm": 0.5505176186561584, + "learning_rate": 7.113354922153159e-06, + "loss": 1.6078, + "step": 14913 + }, + { + "epoch": 0.8312803076751575, + "grad_norm": 0.6434391140937805, + "learning_rate": 7.108777973669706e-06, + "loss": 1.8323, + "step": 14914 + }, + { + "epoch": 0.8313360459283206, + "grad_norm": 0.5409782528877258, + "learning_rate": 7.104202385445741e-06, + "loss": 1.6329, + "step": 14915 + }, + { + "epoch": 0.8313917841814837, + "grad_norm": 0.5738489627838135, + "learning_rate": 7.099628157626392e-06, + "loss": 1.5872, + "step": 14916 + }, + { + "epoch": 0.8314475224346469, + "grad_norm": 0.5797942876815796, + "learning_rate": 7.095055290356694e-06, + "loss": 1.6175, + "step": 14917 + }, + { + "epoch": 0.83150326068781, + "grad_norm": 0.5602861642837524, + "learning_rate": 7.090483783781693e-06, + "loss": 1.5957, + "step": 14918 + }, + { + "epoch": 0.8315589989409732, + "grad_norm": 0.5227814316749573, + "learning_rate": 7.085913638046366e-06, + "loss": 1.3375, + "step": 14919 + }, + { + "epoch": 0.8316147371941364, + "grad_norm": 0.5705005526542664, + "learning_rate": 7.081344853295652e-06, + "loss": 1.6729, + "step": 14920 + }, + { + "epoch": 0.8316704754472994, + "grad_norm": 0.6214076280593872, + "learning_rate": 7.076777429674458e-06, + "loss": 1.5751, + "step": 14921 + }, + { + "epoch": 0.8317262137004626, + "grad_norm": 0.5561441779136658, + "learning_rate": 7.072211367327603e-06, + "loss": 1.6183, + "step": 14922 + }, + { + "epoch": 0.8317819519536258, + "grad_norm": 0.5700360536575317, + "learning_rate": 7.0676466663999355e-06, + "loss": 1.5727, + "step": 14923 + }, + { + "epoch": 0.8318376902067889, + "grad_norm": 0.5978094339370728, + "learning_rate": 7.063083327036191e-06, + "loss": 1.8146, + "step": 14924 + }, + { + "epoch": 0.8318934284599521, + "grad_norm": 0.6397820711135864, + "learning_rate": 7.058521349381109e-06, + "loss": 1.8472, + "step": 14925 + }, + { + "epoch": 0.8319491667131153, + "grad_norm": 0.5918593406677246, + "learning_rate": 7.0539607335793565e-06, + "loss": 1.5908, + "step": 14926 + }, + { + "epoch": 0.8320049049662783, + "grad_norm": 0.6069926619529724, + "learning_rate": 7.04940147977558e-06, + "loss": 1.7789, + "step": 14927 + }, + { + "epoch": 0.8320606432194415, + "grad_norm": 0.5574516654014587, + "learning_rate": 7.044843588114386e-06, + "loss": 1.7592, + "step": 14928 + }, + { + "epoch": 0.8321163814726047, + "grad_norm": 0.6075261831283569, + "learning_rate": 7.04028705874028e-06, + "loss": 1.8732, + "step": 14929 + }, + { + "epoch": 0.8321721197257678, + "grad_norm": 0.5926170945167542, + "learning_rate": 7.035731891797803e-06, + "loss": 1.7596, + "step": 14930 + }, + { + "epoch": 0.832227857978931, + "grad_norm": 0.5655992031097412, + "learning_rate": 7.031178087431428e-06, + "loss": 1.738, + "step": 14931 + }, + { + "epoch": 0.8322835962320941, + "grad_norm": 0.5602476000785828, + "learning_rate": 7.026625645785551e-06, + "loss": 1.5169, + "step": 14932 + }, + { + "epoch": 0.8323393344852572, + "grad_norm": 0.5783279538154602, + "learning_rate": 7.022074567004549e-06, + "loss": 1.7271, + "step": 14933 + }, + { + "epoch": 0.8323950727384204, + "grad_norm": 0.5969105362892151, + "learning_rate": 7.017524851232765e-06, + "loss": 1.6145, + "step": 14934 + }, + { + "epoch": 0.8324508109915836, + "grad_norm": 0.5629395842552185, + "learning_rate": 7.012976498614498e-06, + "loss": 1.6458, + "step": 14935 + }, + { + "epoch": 0.8325065492447467, + "grad_norm": 0.595198929309845, + "learning_rate": 7.008429509293979e-06, + "loss": 1.5222, + "step": 14936 + }, + { + "epoch": 0.8325622874979098, + "grad_norm": 0.6046950817108154, + "learning_rate": 7.003883883415402e-06, + "loss": 1.6804, + "step": 14937 + }, + { + "epoch": 0.8326180257510729, + "grad_norm": 0.5445270538330078, + "learning_rate": 6.9993396211229635e-06, + "loss": 1.4962, + "step": 14938 + }, + { + "epoch": 0.8326737640042361, + "grad_norm": 0.6198094487190247, + "learning_rate": 6.994796722560754e-06, + "loss": 1.9543, + "step": 14939 + }, + { + "epoch": 0.8327295022573993, + "grad_norm": 0.542130708694458, + "learning_rate": 6.990255187872851e-06, + "loss": 1.6622, + "step": 14940 + }, + { + "epoch": 0.8327852405105624, + "grad_norm": 0.5684085488319397, + "learning_rate": 6.985715017203293e-06, + "loss": 1.4973, + "step": 14941 + }, + { + "epoch": 0.8328409787637255, + "grad_norm": 0.5942514538764954, + "learning_rate": 6.981176210696077e-06, + "loss": 1.7641, + "step": 14942 + }, + { + "epoch": 0.8328967170168887, + "grad_norm": 0.592943549156189, + "learning_rate": 6.97663876849512e-06, + "loss": 1.6925, + "step": 14943 + }, + { + "epoch": 0.8329524552700518, + "grad_norm": 0.5728437304496765, + "learning_rate": 6.972102690744325e-06, + "loss": 1.7473, + "step": 14944 + }, + { + "epoch": 0.833008193523215, + "grad_norm": 0.5813961029052734, + "learning_rate": 6.967567977587586e-06, + "loss": 1.7243, + "step": 14945 + }, + { + "epoch": 0.8330639317763782, + "grad_norm": 0.5490429401397705, + "learning_rate": 6.963034629168685e-06, + "loss": 1.4805, + "step": 14946 + }, + { + "epoch": 0.8331196700295412, + "grad_norm": 0.4701632857322693, + "learning_rate": 6.958502645631409e-06, + "loss": 0.9261, + "step": 14947 + }, + { + "epoch": 0.8331754082827044, + "grad_norm": 0.570267379283905, + "learning_rate": 6.953972027119466e-06, + "loss": 1.5988, + "step": 14948 + }, + { + "epoch": 0.8332311465358676, + "grad_norm": 0.5397829413414001, + "learning_rate": 6.949442773776571e-06, + "loss": 1.399, + "step": 14949 + }, + { + "epoch": 0.8332868847890307, + "grad_norm": 0.5675944685935974, + "learning_rate": 6.944914885746334e-06, + "loss": 1.6314, + "step": 14950 + }, + { + "epoch": 0.8333426230421939, + "grad_norm": 0.5543584227561951, + "learning_rate": 6.940388363172373e-06, + "loss": 1.5388, + "step": 14951 + }, + { + "epoch": 0.833398361295357, + "grad_norm": 0.5559143424034119, + "learning_rate": 6.93586320619824e-06, + "loss": 1.5226, + "step": 14952 + }, + { + "epoch": 0.8334540995485201, + "grad_norm": 0.5080550312995911, + "learning_rate": 6.931339414967441e-06, + "loss": 1.4901, + "step": 14953 + }, + { + "epoch": 0.8335098378016833, + "grad_norm": 0.5370514392852783, + "learning_rate": 6.926816989623464e-06, + "loss": 1.5107, + "step": 14954 + }, + { + "epoch": 0.8335655760548465, + "grad_norm": 0.6255368590354919, + "learning_rate": 6.922295930309691e-06, + "loss": 1.5848, + "step": 14955 + }, + { + "epoch": 0.8336213143080096, + "grad_norm": 0.5875033736228943, + "learning_rate": 6.917776237169543e-06, + "loss": 1.5865, + "step": 14956 + }, + { + "epoch": 0.8336770525611727, + "grad_norm": 0.5647172927856445, + "learning_rate": 6.91325791034636e-06, + "loss": 1.6705, + "step": 14957 + }, + { + "epoch": 0.8337327908143359, + "grad_norm": 0.5676584839820862, + "learning_rate": 6.908740949983411e-06, + "loss": 1.5818, + "step": 14958 + }, + { + "epoch": 0.833788529067499, + "grad_norm": 0.5705934166908264, + "learning_rate": 6.904225356223954e-06, + "loss": 1.6364, + "step": 14959 + }, + { + "epoch": 0.8338442673206622, + "grad_norm": 0.5556856393814087, + "learning_rate": 6.899711129211206e-06, + "loss": 1.5349, + "step": 14960 + }, + { + "epoch": 0.8339000055738253, + "grad_norm": 0.560831606388092, + "learning_rate": 6.895198269088343e-06, + "loss": 1.6409, + "step": 14961 + }, + { + "epoch": 0.8339557438269884, + "grad_norm": 0.5645913481712341, + "learning_rate": 6.890686775998462e-06, + "loss": 1.8578, + "step": 14962 + }, + { + "epoch": 0.8340114820801516, + "grad_norm": 0.5440537333488464, + "learning_rate": 6.8861766500846356e-06, + "loss": 1.4316, + "step": 14963 + }, + { + "epoch": 0.8340672203333147, + "grad_norm": 0.5634580254554749, + "learning_rate": 6.88166789148994e-06, + "loss": 1.6223, + "step": 14964 + }, + { + "epoch": 0.8341229585864779, + "grad_norm": 0.6253748536109924, + "learning_rate": 6.877160500357327e-06, + "loss": 1.5812, + "step": 14965 + }, + { + "epoch": 0.8341786968396411, + "grad_norm": 0.5785320997238159, + "learning_rate": 6.872654476829765e-06, + "loss": 1.6649, + "step": 14966 + }, + { + "epoch": 0.8342344350928041, + "grad_norm": 0.5737482905387878, + "learning_rate": 6.868149821050152e-06, + "loss": 1.6446, + "step": 14967 + }, + { + "epoch": 0.8342901733459673, + "grad_norm": 0.554928183555603, + "learning_rate": 6.8636465331613555e-06, + "loss": 1.702, + "step": 14968 + }, + { + "epoch": 0.8343459115991305, + "grad_norm": 0.5656299591064453, + "learning_rate": 6.859144613306185e-06, + "loss": 1.8365, + "step": 14969 + }, + { + "epoch": 0.8344016498522936, + "grad_norm": 0.6206011176109314, + "learning_rate": 6.8546440616274024e-06, + "loss": 1.6186, + "step": 14970 + }, + { + "epoch": 0.8344573881054568, + "grad_norm": 0.6015493869781494, + "learning_rate": 6.850144878267784e-06, + "loss": 1.6608, + "step": 14971 + }, + { + "epoch": 0.83451312635862, + "grad_norm": 0.6501861214637756, + "learning_rate": 6.84564706336997e-06, + "loss": 1.4615, + "step": 14972 + }, + { + "epoch": 0.834568864611783, + "grad_norm": 0.5718386173248291, + "learning_rate": 6.841150617076636e-06, + "loss": 1.7102, + "step": 14973 + }, + { + "epoch": 0.8346246028649462, + "grad_norm": 0.5772673487663269, + "learning_rate": 6.836655539530351e-06, + "loss": 1.5415, + "step": 14974 + }, + { + "epoch": 0.8346803411181094, + "grad_norm": 0.5746707916259766, + "learning_rate": 6.832161830873718e-06, + "loss": 1.6088, + "step": 14975 + }, + { + "epoch": 0.8347360793712725, + "grad_norm": 0.534925103187561, + "learning_rate": 6.827669491249211e-06, + "loss": 1.5481, + "step": 14976 + }, + { + "epoch": 0.8347918176244357, + "grad_norm": 0.6033921837806702, + "learning_rate": 6.823178520799317e-06, + "loss": 1.6031, + "step": 14977 + }, + { + "epoch": 0.8348475558775988, + "grad_norm": 0.5789549350738525, + "learning_rate": 6.8186889196664605e-06, + "loss": 1.647, + "step": 14978 + }, + { + "epoch": 0.8349032941307619, + "grad_norm": 0.5535509586334229, + "learning_rate": 6.814200687993028e-06, + "loss": 1.5902, + "step": 14979 + }, + { + "epoch": 0.8349590323839251, + "grad_norm": 0.5693678855895996, + "learning_rate": 6.809713825921371e-06, + "loss": 1.5765, + "step": 14980 + }, + { + "epoch": 0.8350147706370883, + "grad_norm": 0.5999974012374878, + "learning_rate": 6.80522833359375e-06, + "loss": 1.6666, + "step": 14981 + }, + { + "epoch": 0.8350705088902514, + "grad_norm": 0.5667532086372375, + "learning_rate": 6.800744211152454e-06, + "loss": 1.7652, + "step": 14982 + }, + { + "epoch": 0.8351262471434145, + "grad_norm": 0.562842607498169, + "learning_rate": 6.796261458739695e-06, + "loss": 1.6158, + "step": 14983 + }, + { + "epoch": 0.8351819853965776, + "grad_norm": 0.5929235219955444, + "learning_rate": 6.791780076497617e-06, + "loss": 1.6253, + "step": 14984 + }, + { + "epoch": 0.8352377236497408, + "grad_norm": 0.6288977861404419, + "learning_rate": 6.787300064568353e-06, + "loss": 1.7899, + "step": 14985 + }, + { + "epoch": 0.835293461902904, + "grad_norm": 0.5721529126167297, + "learning_rate": 6.7828214230939825e-06, + "loss": 1.8485, + "step": 14986 + }, + { + "epoch": 0.8353492001560671, + "grad_norm": 0.5428566932678223, + "learning_rate": 6.778344152216553e-06, + "loss": 1.5262, + "step": 14987 + }, + { + "epoch": 0.8354049384092302, + "grad_norm": 0.6128736734390259, + "learning_rate": 6.7738682520780415e-06, + "loss": 1.6569, + "step": 14988 + }, + { + "epoch": 0.8354606766623934, + "grad_norm": 0.5812713503837585, + "learning_rate": 6.7693937228203885e-06, + "loss": 1.7483, + "step": 14989 + }, + { + "epoch": 0.8355164149155565, + "grad_norm": 0.6197991371154785, + "learning_rate": 6.764920564585536e-06, + "loss": 1.708, + "step": 14990 + }, + { + "epoch": 0.8355721531687197, + "grad_norm": 0.613953173160553, + "learning_rate": 6.760448777515316e-06, + "loss": 1.9626, + "step": 14991 + }, + { + "epoch": 0.8356278914218829, + "grad_norm": 0.5072037577629089, + "learning_rate": 6.755978361751553e-06, + "loss": 1.2251, + "step": 14992 + }, + { + "epoch": 0.835683629675046, + "grad_norm": 0.6177765130996704, + "learning_rate": 6.7515093174360275e-06, + "loss": 1.7765, + "step": 14993 + }, + { + "epoch": 0.8357393679282091, + "grad_norm": 0.5812098979949951, + "learning_rate": 6.7470416447104834e-06, + "loss": 1.777, + "step": 14994 + }, + { + "epoch": 0.8357951061813723, + "grad_norm": 0.5786961913108826, + "learning_rate": 6.742575343716584e-06, + "loss": 1.695, + "step": 14995 + }, + { + "epoch": 0.8358508444345354, + "grad_norm": 0.6079100966453552, + "learning_rate": 6.738110414595977e-06, + "loss": 1.6019, + "step": 14996 + }, + { + "epoch": 0.8359065826876986, + "grad_norm": 0.5513747334480286, + "learning_rate": 6.733646857490294e-06, + "loss": 1.4083, + "step": 14997 + }, + { + "epoch": 0.8359623209408618, + "grad_norm": 0.5464707016944885, + "learning_rate": 6.729184672541061e-06, + "loss": 1.5974, + "step": 14998 + }, + { + "epoch": 0.8360180591940248, + "grad_norm": 0.5555058121681213, + "learning_rate": 6.7247238598898145e-06, + "loss": 1.5756, + "step": 14999 + }, + { + "epoch": 0.836073797447188, + "grad_norm": 0.636162519454956, + "learning_rate": 6.720264419677996e-06, + "loss": 1.8554, + "step": 15000 + }, + { + "epoch": 0.8361295357003512, + "grad_norm": 0.5476662516593933, + "learning_rate": 6.715806352047072e-06, + "loss": 1.5994, + "step": 15001 + }, + { + "epoch": 0.8361852739535143, + "grad_norm": 0.5730222463607788, + "learning_rate": 6.711349657138394e-06, + "loss": 1.6864, + "step": 15002 + }, + { + "epoch": 0.8362410122066775, + "grad_norm": 0.594792902469635, + "learning_rate": 6.706894335093311e-06, + "loss": 1.7365, + "step": 15003 + }, + { + "epoch": 0.8362967504598406, + "grad_norm": 0.5853808522224426, + "learning_rate": 6.702440386053127e-06, + "loss": 1.8279, + "step": 15004 + }, + { + "epoch": 0.8363524887130037, + "grad_norm": 0.5967854261398315, + "learning_rate": 6.697987810159095e-06, + "loss": 1.5776, + "step": 15005 + }, + { + "epoch": 0.8364082269661669, + "grad_norm": 0.5882403254508972, + "learning_rate": 6.6935366075524305e-06, + "loss": 1.7631, + "step": 15006 + }, + { + "epoch": 0.83646396521933, + "grad_norm": 0.5702071189880371, + "learning_rate": 6.689086778374265e-06, + "loss": 1.757, + "step": 15007 + }, + { + "epoch": 0.8365197034724932, + "grad_norm": 0.5262090563774109, + "learning_rate": 6.684638322765774e-06, + "loss": 1.5883, + "step": 15008 + }, + { + "epoch": 0.8365754417256563, + "grad_norm": 0.5453174114227295, + "learning_rate": 6.680191240867995e-06, + "loss": 1.5605, + "step": 15009 + }, + { + "epoch": 0.8366311799788194, + "grad_norm": 0.5476326942443848, + "learning_rate": 6.675745532821975e-06, + "loss": 1.2555, + "step": 15010 + }, + { + "epoch": 0.8366869182319826, + "grad_norm": 0.5776779651641846, + "learning_rate": 6.671301198768715e-06, + "loss": 1.7833, + "step": 15011 + }, + { + "epoch": 0.8367426564851458, + "grad_norm": 0.5358211994171143, + "learning_rate": 6.666858238849155e-06, + "loss": 1.4817, + "step": 15012 + }, + { + "epoch": 0.8367983947383089, + "grad_norm": 0.6029189229011536, + "learning_rate": 6.662416653204212e-06, + "loss": 1.8673, + "step": 15013 + }, + { + "epoch": 0.836854132991472, + "grad_norm": 0.5805032253265381, + "learning_rate": 6.657976441974722e-06, + "loss": 1.5881, + "step": 15014 + }, + { + "epoch": 0.8369098712446352, + "grad_norm": 0.561822772026062, + "learning_rate": 6.653537605301513e-06, + "loss": 1.6088, + "step": 15015 + }, + { + "epoch": 0.8369656094977983, + "grad_norm": 0.6312741637229919, + "learning_rate": 6.6491001433253875e-06, + "loss": 2.0219, + "step": 15016 + }, + { + "epoch": 0.8370213477509615, + "grad_norm": 0.5362054705619812, + "learning_rate": 6.6446640561870335e-06, + "loss": 1.6178, + "step": 15017 + }, + { + "epoch": 0.8370770860041247, + "grad_norm": 0.6213870048522949, + "learning_rate": 6.64022934402716e-06, + "loss": 1.7283, + "step": 15018 + }, + { + "epoch": 0.8371328242572877, + "grad_norm": 0.5578364133834839, + "learning_rate": 6.635796006986411e-06, + "loss": 1.8185, + "step": 15019 + }, + { + "epoch": 0.8371885625104509, + "grad_norm": 0.5122633576393127, + "learning_rate": 6.631364045205391e-06, + "loss": 1.3608, + "step": 15020 + }, + { + "epoch": 0.8372443007636141, + "grad_norm": 0.5539398789405823, + "learning_rate": 6.62693345882463e-06, + "loss": 1.6448, + "step": 15021 + }, + { + "epoch": 0.8373000390167772, + "grad_norm": 0.5195080041885376, + "learning_rate": 6.622504247984651e-06, + "loss": 1.5787, + "step": 15022 + }, + { + "epoch": 0.8373557772699404, + "grad_norm": 0.5909291505813599, + "learning_rate": 6.618076412825952e-06, + "loss": 1.6616, + "step": 15023 + }, + { + "epoch": 0.8374115155231036, + "grad_norm": 0.5663995146751404, + "learning_rate": 6.613649953488921e-06, + "loss": 1.7556, + "step": 15024 + }, + { + "epoch": 0.8374672537762666, + "grad_norm": 0.5626013875007629, + "learning_rate": 6.6092248701139556e-06, + "loss": 1.7979, + "step": 15025 + }, + { + "epoch": 0.8375229920294298, + "grad_norm": 0.5691468119621277, + "learning_rate": 6.60480116284139e-06, + "loss": 1.3892, + "step": 15026 + }, + { + "epoch": 0.837578730282593, + "grad_norm": 0.536590039730072, + "learning_rate": 6.6003788318115265e-06, + "loss": 1.554, + "step": 15027 + }, + { + "epoch": 0.8376344685357561, + "grad_norm": 0.5234001278877258, + "learning_rate": 6.595957877164604e-06, + "loss": 1.3891, + "step": 15028 + }, + { + "epoch": 0.8376902067889193, + "grad_norm": 0.5402917265892029, + "learning_rate": 6.591538299040833e-06, + "loss": 1.6932, + "step": 15029 + }, + { + "epoch": 0.8377459450420823, + "grad_norm": 0.6079432368278503, + "learning_rate": 6.587120097580379e-06, + "loss": 1.6175, + "step": 15030 + }, + { + "epoch": 0.8378016832952455, + "grad_norm": 0.5843925476074219, + "learning_rate": 6.582703272923363e-06, + "loss": 1.7834, + "step": 15031 + }, + { + "epoch": 0.8378574215484087, + "grad_norm": 0.5867448449134827, + "learning_rate": 6.578287825209866e-06, + "loss": 1.6085, + "step": 15032 + }, + { + "epoch": 0.8379131598015718, + "grad_norm": 0.5778144598007202, + "learning_rate": 6.573873754579896e-06, + "loss": 1.562, + "step": 15033 + }, + { + "epoch": 0.837968898054735, + "grad_norm": 0.5780001282691956, + "learning_rate": 6.569461061173476e-06, + "loss": 1.7156, + "step": 15034 + }, + { + "epoch": 0.8380246363078981, + "grad_norm": 0.5731835961341858, + "learning_rate": 6.5650497451305246e-06, + "loss": 1.7941, + "step": 15035 + }, + { + "epoch": 0.8380803745610612, + "grad_norm": 0.5535814166069031, + "learning_rate": 6.560639806590951e-06, + "loss": 1.5525, + "step": 15036 + }, + { + "epoch": 0.8381361128142244, + "grad_norm": 0.634691596031189, + "learning_rate": 6.556231245694611e-06, + "loss": 1.8809, + "step": 15037 + }, + { + "epoch": 0.8381918510673876, + "grad_norm": 0.581288754940033, + "learning_rate": 6.5518240625813246e-06, + "loss": 1.7528, + "step": 15038 + }, + { + "epoch": 0.8382475893205507, + "grad_norm": 0.5855739712715149, + "learning_rate": 6.547418257390869e-06, + "loss": 1.7202, + "step": 15039 + }, + { + "epoch": 0.8383033275737138, + "grad_norm": 0.5641582012176514, + "learning_rate": 6.543013830262951e-06, + "loss": 1.5567, + "step": 15040 + }, + { + "epoch": 0.838359065826877, + "grad_norm": 0.5455724596977234, + "learning_rate": 6.538610781337246e-06, + "loss": 1.4171, + "step": 15041 + }, + { + "epoch": 0.8384148040800401, + "grad_norm": 0.5321260690689087, + "learning_rate": 6.534209110753436e-06, + "loss": 1.5516, + "step": 15042 + }, + { + "epoch": 0.8384705423332033, + "grad_norm": 0.6176903247833252, + "learning_rate": 6.529808818651079e-06, + "loss": 1.5619, + "step": 15043 + }, + { + "epoch": 0.8385262805863665, + "grad_norm": 0.5510743856430054, + "learning_rate": 6.525409905169733e-06, + "loss": 1.5283, + "step": 15044 + }, + { + "epoch": 0.8385820188395295, + "grad_norm": 0.553101122379303, + "learning_rate": 6.5210123704489144e-06, + "loss": 1.6015, + "step": 15045 + }, + { + "epoch": 0.8386377570926927, + "grad_norm": 0.6012181639671326, + "learning_rate": 6.516616214628096e-06, + "loss": 1.8035, + "step": 15046 + }, + { + "epoch": 0.8386934953458559, + "grad_norm": 0.5681309103965759, + "learning_rate": 6.512221437846672e-06, + "loss": 1.5109, + "step": 15047 + }, + { + "epoch": 0.838749233599019, + "grad_norm": 0.5924879908561707, + "learning_rate": 6.507828040244018e-06, + "loss": 1.7845, + "step": 15048 + }, + { + "epoch": 0.8388049718521822, + "grad_norm": 0.5429763197898865, + "learning_rate": 6.503436021959508e-06, + "loss": 1.625, + "step": 15049 + }, + { + "epoch": 0.8388607101053454, + "grad_norm": 0.5881600379943848, + "learning_rate": 6.499045383132396e-06, + "loss": 1.6112, + "step": 15050 + }, + { + "epoch": 0.8389164483585084, + "grad_norm": 0.5217443704605103, + "learning_rate": 6.494656123901932e-06, + "loss": 1.4907, + "step": 15051 + }, + { + "epoch": 0.8389721866116716, + "grad_norm": 0.580059289932251, + "learning_rate": 6.490268244407321e-06, + "loss": 1.2179, + "step": 15052 + }, + { + "epoch": 0.8390279248648347, + "grad_norm": 0.5654399991035461, + "learning_rate": 6.485881744787736e-06, + "loss": 1.6479, + "step": 15053 + }, + { + "epoch": 0.8390836631179979, + "grad_norm": 0.5799293518066406, + "learning_rate": 6.481496625182271e-06, + "loss": 1.6279, + "step": 15054 + }, + { + "epoch": 0.839139401371161, + "grad_norm": 0.5369434952735901, + "learning_rate": 6.477112885729997e-06, + "loss": 1.4366, + "step": 15055 + }, + { + "epoch": 0.8391951396243241, + "grad_norm": 0.5435557961463928, + "learning_rate": 6.472730526569942e-06, + "loss": 1.4023, + "step": 15056 + }, + { + "epoch": 0.8392508778774873, + "grad_norm": 0.5399908423423767, + "learning_rate": 6.468349547841102e-06, + "loss": 1.6455, + "step": 15057 + }, + { + "epoch": 0.8393066161306505, + "grad_norm": 0.583627462387085, + "learning_rate": 6.463969949682413e-06, + "loss": 1.7753, + "step": 15058 + }, + { + "epoch": 0.8393623543838136, + "grad_norm": 0.595605731010437, + "learning_rate": 6.459591732232739e-06, + "loss": 1.7581, + "step": 15059 + }, + { + "epoch": 0.8394180926369768, + "grad_norm": 0.5331535935401917, + "learning_rate": 6.4552148956309845e-06, + "loss": 1.6923, + "step": 15060 + }, + { + "epoch": 0.8394738308901399, + "grad_norm": 0.494249165058136, + "learning_rate": 6.450839440015921e-06, + "loss": 1.3142, + "step": 15061 + }, + { + "epoch": 0.839529569143303, + "grad_norm": 0.5518122911453247, + "learning_rate": 6.446465365526316e-06, + "loss": 1.4404, + "step": 15062 + }, + { + "epoch": 0.8395853073964662, + "grad_norm": 0.5549556612968445, + "learning_rate": 6.442092672300898e-06, + "loss": 1.5676, + "step": 15063 + }, + { + "epoch": 0.8396410456496294, + "grad_norm": 0.5494826436042786, + "learning_rate": 6.437721360478338e-06, + "loss": 1.6463, + "step": 15064 + }, + { + "epoch": 0.8396967839027925, + "grad_norm": 0.5314594507217407, + "learning_rate": 6.433351430197282e-06, + "loss": 1.6032, + "step": 15065 + }, + { + "epoch": 0.8397525221559556, + "grad_norm": 0.5597966909408569, + "learning_rate": 6.428982881596296e-06, + "loss": 1.7303, + "step": 15066 + }, + { + "epoch": 0.8398082604091188, + "grad_norm": 0.5992987751960754, + "learning_rate": 6.42461571481393e-06, + "loss": 1.771, + "step": 15067 + }, + { + "epoch": 0.8398639986622819, + "grad_norm": 0.5551838874816895, + "learning_rate": 6.420249929988709e-06, + "loss": 1.6365, + "step": 15068 + }, + { + "epoch": 0.8399197369154451, + "grad_norm": 0.6186457872390747, + "learning_rate": 6.415885527259064e-06, + "loss": 1.7606, + "step": 15069 + }, + { + "epoch": 0.8399754751686083, + "grad_norm": 0.5746279954910278, + "learning_rate": 6.411522506763412e-06, + "loss": 1.4675, + "step": 15070 + }, + { + "epoch": 0.8400312134217713, + "grad_norm": 0.5870872139930725, + "learning_rate": 6.407160868640133e-06, + "loss": 1.7661, + "step": 15071 + }, + { + "epoch": 0.8400869516749345, + "grad_norm": 0.558394193649292, + "learning_rate": 6.402800613027554e-06, + "loss": 1.5774, + "step": 15072 + }, + { + "epoch": 0.8401426899280977, + "grad_norm": 0.5370978713035583, + "learning_rate": 6.398441740063943e-06, + "loss": 1.46, + "step": 15073 + }, + { + "epoch": 0.8401984281812608, + "grad_norm": 0.5619174838066101, + "learning_rate": 6.394084249887533e-06, + "loss": 1.5676, + "step": 15074 + }, + { + "epoch": 0.840254166434424, + "grad_norm": 0.5572698712348938, + "learning_rate": 6.389728142636553e-06, + "loss": 1.5891, + "step": 15075 + }, + { + "epoch": 0.840309904687587, + "grad_norm": 0.5868242979049683, + "learning_rate": 6.3853734184491195e-06, + "loss": 1.5158, + "step": 15076 + }, + { + "epoch": 0.8403656429407502, + "grad_norm": 0.5599640011787415, + "learning_rate": 6.381020077463351e-06, + "loss": 1.4915, + "step": 15077 + }, + { + "epoch": 0.8404213811939134, + "grad_norm": 0.58631831407547, + "learning_rate": 6.376668119817308e-06, + "loss": 1.9049, + "step": 15078 + }, + { + "epoch": 0.8404771194470765, + "grad_norm": 0.5880148410797119, + "learning_rate": 6.37231754564902e-06, + "loss": 1.5713, + "step": 15079 + }, + { + "epoch": 0.8405328577002397, + "grad_norm": 0.5282483696937561, + "learning_rate": 6.367968355096449e-06, + "loss": 1.5207, + "step": 15080 + }, + { + "epoch": 0.8405885959534029, + "grad_norm": 0.6356255412101746, + "learning_rate": 6.363620548297522e-06, + "loss": 1.8841, + "step": 15081 + }, + { + "epoch": 0.8406443342065659, + "grad_norm": 0.5985350608825684, + "learning_rate": 6.359274125390135e-06, + "loss": 1.7406, + "step": 15082 + }, + { + "epoch": 0.8407000724597291, + "grad_norm": 0.6167718768119812, + "learning_rate": 6.3549290865121294e-06, + "loss": 1.7603, + "step": 15083 + }, + { + "epoch": 0.8407558107128923, + "grad_norm": 0.5391794443130493, + "learning_rate": 6.350585431801314e-06, + "loss": 1.5523, + "step": 15084 + }, + { + "epoch": 0.8408115489660554, + "grad_norm": 0.5297492146492004, + "learning_rate": 6.346243161395421e-06, + "loss": 1.5157, + "step": 15085 + }, + { + "epoch": 0.8408672872192186, + "grad_norm": 0.5875098705291748, + "learning_rate": 6.341902275432188e-06, + "loss": 1.685, + "step": 15086 + }, + { + "epoch": 0.8409230254723817, + "grad_norm": 0.5708257555961609, + "learning_rate": 6.337562774049266e-06, + "loss": 1.6276, + "step": 15087 + }, + { + "epoch": 0.8409787637255448, + "grad_norm": 0.5539237856864929, + "learning_rate": 6.333224657384279e-06, + "loss": 1.5399, + "step": 15088 + }, + { + "epoch": 0.841034501978708, + "grad_norm": 0.5507051944732666, + "learning_rate": 6.328887925574812e-06, + "loss": 1.6095, + "step": 15089 + }, + { + "epoch": 0.8410902402318712, + "grad_norm": 0.5970490574836731, + "learning_rate": 6.324552578758403e-06, + "loss": 1.6613, + "step": 15090 + }, + { + "epoch": 0.8411459784850343, + "grad_norm": 0.5925393104553223, + "learning_rate": 6.3202186170725485e-06, + "loss": 1.8106, + "step": 15091 + }, + { + "epoch": 0.8412017167381974, + "grad_norm": 0.5829653739929199, + "learning_rate": 6.315886040654679e-06, + "loss": 1.6608, + "step": 15092 + }, + { + "epoch": 0.8412574549913606, + "grad_norm": 0.6200035810470581, + "learning_rate": 6.311554849642198e-06, + "loss": 1.6227, + "step": 15093 + }, + { + "epoch": 0.8413131932445237, + "grad_norm": 0.5908560156822205, + "learning_rate": 6.307225044172493e-06, + "loss": 1.7769, + "step": 15094 + }, + { + "epoch": 0.8413689314976869, + "grad_norm": 0.5397213101387024, + "learning_rate": 6.302896624382859e-06, + "loss": 1.6509, + "step": 15095 + }, + { + "epoch": 0.8414246697508501, + "grad_norm": 0.5733935832977295, + "learning_rate": 6.298569590410569e-06, + "loss": 1.8361, + "step": 15096 + }, + { + "epoch": 0.8414804080040131, + "grad_norm": 0.5369426608085632, + "learning_rate": 6.294243942392852e-06, + "loss": 1.426, + "step": 15097 + }, + { + "epoch": 0.8415361462571763, + "grad_norm": 0.5744366645812988, + "learning_rate": 6.28991968046691e-06, + "loss": 1.6749, + "step": 15098 + }, + { + "epoch": 0.8415918845103394, + "grad_norm": 0.5129631161689758, + "learning_rate": 6.285596804769856e-06, + "loss": 1.442, + "step": 15099 + }, + { + "epoch": 0.8416476227635026, + "grad_norm": 0.6413232088088989, + "learning_rate": 6.281275315438784e-06, + "loss": 1.6696, + "step": 15100 + }, + { + "epoch": 0.8417033610166658, + "grad_norm": 0.5749282836914062, + "learning_rate": 6.276955212610785e-06, + "loss": 1.6203, + "step": 15101 + }, + { + "epoch": 0.8417590992698288, + "grad_norm": 0.5394002795219421, + "learning_rate": 6.272636496422835e-06, + "loss": 1.5446, + "step": 15102 + }, + { + "epoch": 0.841814837522992, + "grad_norm": 0.5376508831977844, + "learning_rate": 6.2683191670119105e-06, + "loss": 1.7728, + "step": 15103 + }, + { + "epoch": 0.8418705757761552, + "grad_norm": 0.5614270567893982, + "learning_rate": 6.264003224514925e-06, + "loss": 1.7175, + "step": 15104 + }, + { + "epoch": 0.8419263140293183, + "grad_norm": 0.5553098917007446, + "learning_rate": 6.259688669068764e-06, + "loss": 1.6456, + "step": 15105 + }, + { + "epoch": 0.8419820522824815, + "grad_norm": 0.5312615036964417, + "learning_rate": 6.255375500810251e-06, + "loss": 1.429, + "step": 15106 + }, + { + "epoch": 0.8420377905356446, + "grad_norm": 0.5330777168273926, + "learning_rate": 6.251063719876177e-06, + "loss": 1.4268, + "step": 15107 + }, + { + "epoch": 0.8420935287888077, + "grad_norm": 0.5949349999427795, + "learning_rate": 6.246753326403287e-06, + "loss": 1.6279, + "step": 15108 + }, + { + "epoch": 0.8421492670419709, + "grad_norm": 0.5401760339736938, + "learning_rate": 6.242444320528279e-06, + "loss": 1.5042, + "step": 15109 + }, + { + "epoch": 0.8422050052951341, + "grad_norm": 0.5791640281677246, + "learning_rate": 6.238136702387831e-06, + "loss": 1.6186, + "step": 15110 + }, + { + "epoch": 0.8422607435482972, + "grad_norm": 0.5404651165008545, + "learning_rate": 6.233830472118507e-06, + "loss": 1.5597, + "step": 15111 + }, + { + "epoch": 0.8423164818014603, + "grad_norm": 0.5574688911437988, + "learning_rate": 6.229525629856936e-06, + "loss": 1.5839, + "step": 15112 + }, + { + "epoch": 0.8423722200546235, + "grad_norm": 0.555789053440094, + "learning_rate": 6.225222175739598e-06, + "loss": 1.5685, + "step": 15113 + }, + { + "epoch": 0.8424279583077866, + "grad_norm": 0.5716651082038879, + "learning_rate": 6.220920109902989e-06, + "loss": 1.7948, + "step": 15114 + }, + { + "epoch": 0.8424836965609498, + "grad_norm": 0.5621392726898193, + "learning_rate": 6.216619432483539e-06, + "loss": 1.5943, + "step": 15115 + }, + { + "epoch": 0.842539434814113, + "grad_norm": 0.5896852016448975, + "learning_rate": 6.21232014361765e-06, + "loss": 1.6435, + "step": 15116 + }, + { + "epoch": 0.842595173067276, + "grad_norm": 0.5524661540985107, + "learning_rate": 6.20802224344168e-06, + "loss": 1.712, + "step": 15117 + }, + { + "epoch": 0.8426509113204392, + "grad_norm": 0.568313479423523, + "learning_rate": 6.203725732091891e-06, + "loss": 1.8713, + "step": 15118 + }, + { + "epoch": 0.8427066495736024, + "grad_norm": 0.5936497449874878, + "learning_rate": 6.199430609704598e-06, + "loss": 1.7247, + "step": 15119 + }, + { + "epoch": 0.8427623878267655, + "grad_norm": 0.48076698184013367, + "learning_rate": 6.19513687641598e-06, + "loss": 1.093, + "step": 15120 + }, + { + "epoch": 0.8428181260799287, + "grad_norm": 0.5699744820594788, + "learning_rate": 6.190844532362222e-06, + "loss": 1.6697, + "step": 15121 + }, + { + "epoch": 0.8428738643330917, + "grad_norm": 0.5501531958580017, + "learning_rate": 6.186553577679449e-06, + "loss": 1.6949, + "step": 15122 + }, + { + "epoch": 0.8429296025862549, + "grad_norm": 0.6222522258758545, + "learning_rate": 6.182264012503741e-06, + "loss": 1.8087, + "step": 15123 + }, + { + "epoch": 0.8429853408394181, + "grad_norm": 0.6549838781356812, + "learning_rate": 6.177975836971161e-06, + "loss": 1.6954, + "step": 15124 + }, + { + "epoch": 0.8430410790925812, + "grad_norm": 0.6259307265281677, + "learning_rate": 6.173689051217674e-06, + "loss": 1.6088, + "step": 15125 + }, + { + "epoch": 0.8430968173457444, + "grad_norm": 0.5921953916549683, + "learning_rate": 6.169403655379235e-06, + "loss": 1.5706, + "step": 15126 + }, + { + "epoch": 0.8431525555989076, + "grad_norm": 0.5394318103790283, + "learning_rate": 6.165119649591783e-06, + "loss": 1.4777, + "step": 15127 + }, + { + "epoch": 0.8432082938520706, + "grad_norm": 0.5984581708908081, + "learning_rate": 6.160837033991152e-06, + "loss": 1.676, + "step": 15128 + }, + { + "epoch": 0.8432640321052338, + "grad_norm": 0.5852010250091553, + "learning_rate": 6.156555808713166e-06, + "loss": 1.6371, + "step": 15129 + }, + { + "epoch": 0.843319770358397, + "grad_norm": 0.5490121245384216, + "learning_rate": 6.1522759738936066e-06, + "loss": 1.4938, + "step": 15130 + }, + { + "epoch": 0.8433755086115601, + "grad_norm": 0.5940157771110535, + "learning_rate": 6.147997529668214e-06, + "loss": 1.7965, + "step": 15131 + }, + { + "epoch": 0.8434312468647233, + "grad_norm": 0.5224518179893494, + "learning_rate": 6.143720476172654e-06, + "loss": 1.4601, + "step": 15132 + }, + { + "epoch": 0.8434869851178864, + "grad_norm": 0.5169552564620972, + "learning_rate": 6.139444813542583e-06, + "loss": 1.4532, + "step": 15133 + }, + { + "epoch": 0.8435427233710495, + "grad_norm": 0.5963098406791687, + "learning_rate": 6.135170541913599e-06, + "loss": 1.7473, + "step": 15134 + }, + { + "epoch": 0.8435984616242127, + "grad_norm": 0.590155303478241, + "learning_rate": 6.130897661421248e-06, + "loss": 1.7668, + "step": 15135 + }, + { + "epoch": 0.8436541998773759, + "grad_norm": 0.5155788064002991, + "learning_rate": 6.1266261722010666e-06, + "loss": 1.4973, + "step": 15136 + }, + { + "epoch": 0.843709938130539, + "grad_norm": 0.5276482105255127, + "learning_rate": 6.12235607438848e-06, + "loss": 1.4502, + "step": 15137 + }, + { + "epoch": 0.8437656763837021, + "grad_norm": 0.6681525707244873, + "learning_rate": 6.118087368118952e-06, + "loss": 1.7002, + "step": 15138 + }, + { + "epoch": 0.8438214146368653, + "grad_norm": 0.5738222002983093, + "learning_rate": 6.113820053527836e-06, + "loss": 1.8362, + "step": 15139 + }, + { + "epoch": 0.8438771528900284, + "grad_norm": 0.5899402499198914, + "learning_rate": 6.109554130750472e-06, + "loss": 1.8748, + "step": 15140 + }, + { + "epoch": 0.8439328911431916, + "grad_norm": 0.537513792514801, + "learning_rate": 6.105289599922154e-06, + "loss": 1.6823, + "step": 15141 + }, + { + "epoch": 0.8439886293963548, + "grad_norm": 0.4960184693336487, + "learning_rate": 6.1010264611781275e-06, + "loss": 1.2737, + "step": 15142 + }, + { + "epoch": 0.8440443676495178, + "grad_norm": 0.5494456887245178, + "learning_rate": 6.096764714653602e-06, + "loss": 1.5777, + "step": 15143 + }, + { + "epoch": 0.844100105902681, + "grad_norm": 0.6477494239807129, + "learning_rate": 6.092504360483703e-06, + "loss": 1.9725, + "step": 15144 + }, + { + "epoch": 0.8441558441558441, + "grad_norm": 0.4952775537967682, + "learning_rate": 6.088245398803588e-06, + "loss": 1.2087, + "step": 15145 + }, + { + "epoch": 0.8442115824090073, + "grad_norm": 0.5322543382644653, + "learning_rate": 6.0839878297483e-06, + "loss": 1.6881, + "step": 15146 + }, + { + "epoch": 0.8442673206621705, + "grad_norm": 0.534050464630127, + "learning_rate": 6.0797316534528636e-06, + "loss": 1.5091, + "step": 15147 + }, + { + "epoch": 0.8443230589153335, + "grad_norm": 0.5191200375556946, + "learning_rate": 6.075476870052271e-06, + "loss": 1.5777, + "step": 15148 + }, + { + "epoch": 0.8443787971684967, + "grad_norm": 0.5721346735954285, + "learning_rate": 6.071223479681454e-06, + "loss": 1.7263, + "step": 15149 + }, + { + "epoch": 0.8444345354216599, + "grad_norm": 0.5471512675285339, + "learning_rate": 6.0669714824753144e-06, + "loss": 1.6941, + "step": 15150 + }, + { + "epoch": 0.844490273674823, + "grad_norm": 0.5731834769248962, + "learning_rate": 6.062720878568684e-06, + "loss": 1.6013, + "step": 15151 + }, + { + "epoch": 0.8445460119279862, + "grad_norm": 0.5664587616920471, + "learning_rate": 6.058471668096361e-06, + "loss": 1.6914, + "step": 15152 + }, + { + "epoch": 0.8446017501811494, + "grad_norm": 0.5806335806846619, + "learning_rate": 6.054223851193141e-06, + "loss": 1.7909, + "step": 15153 + }, + { + "epoch": 0.8446574884343124, + "grad_norm": 0.5735641717910767, + "learning_rate": 6.049977427993714e-06, + "loss": 1.6129, + "step": 15154 + }, + { + "epoch": 0.8447132266874756, + "grad_norm": 0.5994248986244202, + "learning_rate": 6.045732398632753e-06, + "loss": 1.6981, + "step": 15155 + }, + { + "epoch": 0.8447689649406388, + "grad_norm": 0.5608644485473633, + "learning_rate": 6.0414887632448845e-06, + "loss": 1.6413, + "step": 15156 + }, + { + "epoch": 0.8448247031938019, + "grad_norm": 0.5737500786781311, + "learning_rate": 6.037246521964712e-06, + "loss": 1.5987, + "step": 15157 + }, + { + "epoch": 0.8448804414469651, + "grad_norm": 0.5404165387153625, + "learning_rate": 6.03300567492675e-06, + "loss": 1.625, + "step": 15158 + }, + { + "epoch": 0.8449361797001282, + "grad_norm": 0.5718837380409241, + "learning_rate": 6.028766222265498e-06, + "loss": 1.4054, + "step": 15159 + }, + { + "epoch": 0.8449919179532913, + "grad_norm": 0.5695325136184692, + "learning_rate": 6.024528164115417e-06, + "loss": 1.6633, + "step": 15160 + }, + { + "epoch": 0.8450476562064545, + "grad_norm": 0.6172574162483215, + "learning_rate": 6.020291500610903e-06, + "loss": 1.62, + "step": 15161 + }, + { + "epoch": 0.8451033944596177, + "grad_norm": 0.5405846238136292, + "learning_rate": 6.016056231886335e-06, + "loss": 1.5042, + "step": 15162 + }, + { + "epoch": 0.8451591327127808, + "grad_norm": 0.557936429977417, + "learning_rate": 6.011822358075997e-06, + "loss": 1.6623, + "step": 15163 + }, + { + "epoch": 0.8452148709659439, + "grad_norm": 0.5977124571800232, + "learning_rate": 6.007589879314207e-06, + "loss": 1.5602, + "step": 15164 + }, + { + "epoch": 0.8452706092191071, + "grad_norm": 0.5428844094276428, + "learning_rate": 6.003358795735164e-06, + "loss": 1.4476, + "step": 15165 + }, + { + "epoch": 0.8453263474722702, + "grad_norm": 0.5770780444145203, + "learning_rate": 5.999129107473062e-06, + "loss": 1.7579, + "step": 15166 + }, + { + "epoch": 0.8453820857254334, + "grad_norm": 0.5842610001564026, + "learning_rate": 5.994900814662041e-06, + "loss": 1.49, + "step": 15167 + }, + { + "epoch": 0.8454378239785965, + "grad_norm": 0.5725298523902893, + "learning_rate": 5.990673917436196e-06, + "loss": 1.6362, + "step": 15168 + }, + { + "epoch": 0.8454935622317596, + "grad_norm": 0.558623731136322, + "learning_rate": 5.986448415929597e-06, + "loss": 1.573, + "step": 15169 + }, + { + "epoch": 0.8455493004849228, + "grad_norm": 0.5286862254142761, + "learning_rate": 5.982224310276214e-06, + "loss": 1.5352, + "step": 15170 + }, + { + "epoch": 0.8456050387380859, + "grad_norm": 0.5825233459472656, + "learning_rate": 5.97800160061005e-06, + "loss": 1.7468, + "step": 15171 + }, + { + "epoch": 0.8456607769912491, + "grad_norm": 0.5374108552932739, + "learning_rate": 5.973780287065006e-06, + "loss": 1.5021, + "step": 15172 + }, + { + "epoch": 0.8457165152444123, + "grad_norm": 0.5852628350257874, + "learning_rate": 5.969560369774957e-06, + "loss": 1.6955, + "step": 15173 + }, + { + "epoch": 0.8457722534975753, + "grad_norm": 0.5365518927574158, + "learning_rate": 5.96534184887374e-06, + "loss": 1.5456, + "step": 15174 + }, + { + "epoch": 0.8458279917507385, + "grad_norm": 0.5182381272315979, + "learning_rate": 5.961124724495137e-06, + "loss": 1.4469, + "step": 15175 + }, + { + "epoch": 0.8458837300039017, + "grad_norm": 0.6150214076042175, + "learning_rate": 5.956908996772909e-06, + "loss": 1.5972, + "step": 15176 + }, + { + "epoch": 0.8459394682570648, + "grad_norm": 0.5836634635925293, + "learning_rate": 5.9526946658407245e-06, + "loss": 1.8852, + "step": 15177 + }, + { + "epoch": 0.845995206510228, + "grad_norm": 0.5743767619132996, + "learning_rate": 5.948481731832239e-06, + "loss": 1.4465, + "step": 15178 + }, + { + "epoch": 0.8460509447633912, + "grad_norm": 0.5668880343437195, + "learning_rate": 5.9442701948811015e-06, + "loss": 1.5702, + "step": 15179 + }, + { + "epoch": 0.8461066830165542, + "grad_norm": 0.5709795951843262, + "learning_rate": 5.940060055120838e-06, + "loss": 1.7079, + "step": 15180 + }, + { + "epoch": 0.8461624212697174, + "grad_norm": 0.5624746680259705, + "learning_rate": 5.935851312684981e-06, + "loss": 1.5781, + "step": 15181 + }, + { + "epoch": 0.8462181595228806, + "grad_norm": 0.5586860775947571, + "learning_rate": 5.9316439677070066e-06, + "loss": 1.645, + "step": 15182 + }, + { + "epoch": 0.8462738977760437, + "grad_norm": 0.5692182183265686, + "learning_rate": 5.927438020320364e-06, + "loss": 1.5638, + "step": 15183 + }, + { + "epoch": 0.8463296360292069, + "grad_norm": 0.5767751336097717, + "learning_rate": 5.923233470658412e-06, + "loss": 1.7303, + "step": 15184 + }, + { + "epoch": 0.84638537428237, + "grad_norm": 0.5157864093780518, + "learning_rate": 5.919030318854513e-06, + "loss": 1.2655, + "step": 15185 + }, + { + "epoch": 0.8464411125355331, + "grad_norm": 0.6971840858459473, + "learning_rate": 5.914828565041958e-06, + "loss": 1.6171, + "step": 15186 + }, + { + "epoch": 0.8464968507886963, + "grad_norm": 0.5945658087730408, + "learning_rate": 5.910628209354008e-06, + "loss": 1.8041, + "step": 15187 + }, + { + "epoch": 0.8465525890418595, + "grad_norm": 0.5842046141624451, + "learning_rate": 5.906429251923884e-06, + "loss": 1.6288, + "step": 15188 + }, + { + "epoch": 0.8466083272950226, + "grad_norm": 0.5760061144828796, + "learning_rate": 5.9022316928847185e-06, + "loss": 1.4974, + "step": 15189 + }, + { + "epoch": 0.8466640655481857, + "grad_norm": 0.5655816793441772, + "learning_rate": 5.898035532369678e-06, + "loss": 1.652, + "step": 15190 + }, + { + "epoch": 0.8467198038013488, + "grad_norm": 0.5635972619056702, + "learning_rate": 5.89384077051181e-06, + "loss": 1.7512, + "step": 15191 + }, + { + "epoch": 0.846775542054512, + "grad_norm": 0.5724639892578125, + "learning_rate": 5.8896474074441545e-06, + "loss": 1.4862, + "step": 15192 + }, + { + "epoch": 0.8468312803076752, + "grad_norm": 0.5514636635780334, + "learning_rate": 5.885455443299698e-06, + "loss": 1.7256, + "step": 15193 + }, + { + "epoch": 0.8468870185608383, + "grad_norm": 0.6052865386009216, + "learning_rate": 5.8812648782113955e-06, + "loss": 1.8113, + "step": 15194 + }, + { + "epoch": 0.8469427568140014, + "grad_norm": 0.5689749717712402, + "learning_rate": 5.877075712312147e-06, + "loss": 1.7658, + "step": 15195 + }, + { + "epoch": 0.8469984950671646, + "grad_norm": 0.5780896544456482, + "learning_rate": 5.872887945734784e-06, + "loss": 1.5032, + "step": 15196 + }, + { + "epoch": 0.8470542333203277, + "grad_norm": 0.5639193654060364, + "learning_rate": 5.8687015786121565e-06, + "loss": 1.6255, + "step": 15197 + }, + { + "epoch": 0.8471099715734909, + "grad_norm": 0.6532199382781982, + "learning_rate": 5.8645166110769976e-06, + "loss": 2.0318, + "step": 15198 + }, + { + "epoch": 0.8471657098266541, + "grad_norm": 0.5265516638755798, + "learning_rate": 5.860333043262045e-06, + "loss": 1.5605, + "step": 15199 + }, + { + "epoch": 0.8472214480798171, + "grad_norm": 0.6008475422859192, + "learning_rate": 5.8561508752999815e-06, + "loss": 1.7965, + "step": 15200 + }, + { + "epoch": 0.8472771863329803, + "grad_norm": 0.6126861572265625, + "learning_rate": 5.851970107323435e-06, + "loss": 1.6465, + "step": 15201 + }, + { + "epoch": 0.8473329245861435, + "grad_norm": 0.5757130980491638, + "learning_rate": 5.847790739465003e-06, + "loss": 1.6753, + "step": 15202 + }, + { + "epoch": 0.8473886628393066, + "grad_norm": 0.543804407119751, + "learning_rate": 5.84361277185721e-06, + "loss": 1.5499, + "step": 15203 + }, + { + "epoch": 0.8474444010924698, + "grad_norm": 0.6240707635879517, + "learning_rate": 5.839436204632564e-06, + "loss": 1.9306, + "step": 15204 + }, + { + "epoch": 0.847500139345633, + "grad_norm": 0.5344946980476379, + "learning_rate": 5.83526103792355e-06, + "loss": 1.4509, + "step": 15205 + }, + { + "epoch": 0.847555877598796, + "grad_norm": 0.5294502973556519, + "learning_rate": 5.8310872718625456e-06, + "loss": 1.5115, + "step": 15206 + }, + { + "epoch": 0.8476116158519592, + "grad_norm": 0.5593866109848022, + "learning_rate": 5.826914906581932e-06, + "loss": 1.7621, + "step": 15207 + }, + { + "epoch": 0.8476673541051224, + "grad_norm": 0.5948423147201538, + "learning_rate": 5.822743942214026e-06, + "loss": 1.6684, + "step": 15208 + }, + { + "epoch": 0.8477230923582855, + "grad_norm": 0.5644746422767639, + "learning_rate": 5.818574378891123e-06, + "loss": 1.784, + "step": 15209 + }, + { + "epoch": 0.8477788306114487, + "grad_norm": 0.561109721660614, + "learning_rate": 5.814406216745438e-06, + "loss": 1.5706, + "step": 15210 + }, + { + "epoch": 0.8478345688646118, + "grad_norm": 0.5108320713043213, + "learning_rate": 5.8102394559091556e-06, + "loss": 1.541, + "step": 15211 + }, + { + "epoch": 0.8478903071177749, + "grad_norm": 0.5673696398735046, + "learning_rate": 5.8060740965144525e-06, + "loss": 1.6359, + "step": 15212 + }, + { + "epoch": 0.8479460453709381, + "grad_norm": 0.5839824080467224, + "learning_rate": 5.8019101386934e-06, + "loss": 1.599, + "step": 15213 + }, + { + "epoch": 0.8480017836241012, + "grad_norm": 0.6167586445808411, + "learning_rate": 5.797747582578078e-06, + "loss": 1.7939, + "step": 15214 + }, + { + "epoch": 0.8480575218772644, + "grad_norm": 0.5187019109725952, + "learning_rate": 5.793586428300468e-06, + "loss": 1.3147, + "step": 15215 + }, + { + "epoch": 0.8481132601304275, + "grad_norm": 0.523949146270752, + "learning_rate": 5.7894266759925705e-06, + "loss": 1.4693, + "step": 15216 + }, + { + "epoch": 0.8481689983835906, + "grad_norm": 0.5620637536048889, + "learning_rate": 5.785268325786286e-06, + "loss": 1.5794, + "step": 15217 + }, + { + "epoch": 0.8482247366367538, + "grad_norm": 0.5765520334243774, + "learning_rate": 5.781111377813498e-06, + "loss": 1.7335, + "step": 15218 + }, + { + "epoch": 0.848280474889917, + "grad_norm": 0.5613219738006592, + "learning_rate": 5.776955832206044e-06, + "loss": 1.7115, + "step": 15219 + }, + { + "epoch": 0.84833621314308, + "grad_norm": 0.5151294469833374, + "learning_rate": 5.7728016890957136e-06, + "loss": 1.626, + "step": 15220 + }, + { + "epoch": 0.8483919513962432, + "grad_norm": 0.547092080116272, + "learning_rate": 5.768648948614258e-06, + "loss": 1.5939, + "step": 15221 + }, + { + "epoch": 0.8484476896494064, + "grad_norm": 0.5229447484016418, + "learning_rate": 5.764497610893355e-06, + "loss": 1.3716, + "step": 15222 + }, + { + "epoch": 0.8485034279025695, + "grad_norm": 0.5841200351715088, + "learning_rate": 5.7603476760646924e-06, + "loss": 1.6838, + "step": 15223 + }, + { + "epoch": 0.8485591661557327, + "grad_norm": 0.5877189040184021, + "learning_rate": 5.756199144259861e-06, + "loss": 1.6622, + "step": 15224 + }, + { + "epoch": 0.8486149044088959, + "grad_norm": 0.5866639614105225, + "learning_rate": 5.752052015610432e-06, + "loss": 1.626, + "step": 15225 + }, + { + "epoch": 0.8486706426620589, + "grad_norm": 0.5326880216598511, + "learning_rate": 5.7479062902479285e-06, + "loss": 1.4526, + "step": 15226 + }, + { + "epoch": 0.8487263809152221, + "grad_norm": 0.5623133182525635, + "learning_rate": 5.743761968303835e-06, + "loss": 1.4646, + "step": 15227 + }, + { + "epoch": 0.8487821191683853, + "grad_norm": 0.5249256491661072, + "learning_rate": 5.739619049909584e-06, + "loss": 1.4568, + "step": 15228 + }, + { + "epoch": 0.8488378574215484, + "grad_norm": 0.5421143174171448, + "learning_rate": 5.735477535196554e-06, + "loss": 1.539, + "step": 15229 + }, + { + "epoch": 0.8488935956747116, + "grad_norm": 0.49832555651664734, + "learning_rate": 5.7313374242960845e-06, + "loss": 1.3992, + "step": 15230 + }, + { + "epoch": 0.8489493339278747, + "grad_norm": 0.5837661027908325, + "learning_rate": 5.727198717339511e-06, + "loss": 1.7422, + "step": 15231 + }, + { + "epoch": 0.8490050721810378, + "grad_norm": 0.6013142466545105, + "learning_rate": 5.723061414458053e-06, + "loss": 1.6997, + "step": 15232 + }, + { + "epoch": 0.849060810434201, + "grad_norm": 0.594485878944397, + "learning_rate": 5.718925515782936e-06, + "loss": 1.854, + "step": 15233 + }, + { + "epoch": 0.8491165486873642, + "grad_norm": 0.5698985457420349, + "learning_rate": 5.71479102144532e-06, + "loss": 1.6647, + "step": 15234 + }, + { + "epoch": 0.8491722869405273, + "grad_norm": 0.5398910045623779, + "learning_rate": 5.710657931576347e-06, + "loss": 1.6021, + "step": 15235 + }, + { + "epoch": 0.8492280251936905, + "grad_norm": 0.6242139935493469, + "learning_rate": 5.70652624630707e-06, + "loss": 1.7062, + "step": 15236 + }, + { + "epoch": 0.8492837634468535, + "grad_norm": 0.5674960017204285, + "learning_rate": 5.70239596576852e-06, + "loss": 1.6983, + "step": 15237 + }, + { + "epoch": 0.8493395017000167, + "grad_norm": 0.5780263543128967, + "learning_rate": 5.698267090091719e-06, + "loss": 1.6402, + "step": 15238 + }, + { + "epoch": 0.8493952399531799, + "grad_norm": 0.5564453601837158, + "learning_rate": 5.694139619407574e-06, + "loss": 1.5863, + "step": 15239 + }, + { + "epoch": 0.849450978206343, + "grad_norm": 0.5647628903388977, + "learning_rate": 5.690013553847013e-06, + "loss": 1.6958, + "step": 15240 + }, + { + "epoch": 0.8495067164595062, + "grad_norm": 0.5931124687194824, + "learning_rate": 5.685888893540858e-06, + "loss": 1.6198, + "step": 15241 + }, + { + "epoch": 0.8495624547126693, + "grad_norm": 0.5776707530021667, + "learning_rate": 5.681765638619957e-06, + "loss": 1.5416, + "step": 15242 + }, + { + "epoch": 0.8496181929658324, + "grad_norm": 0.5682428479194641, + "learning_rate": 5.677643789215042e-06, + "loss": 1.6824, + "step": 15243 + }, + { + "epoch": 0.8496739312189956, + "grad_norm": 0.5195711255073547, + "learning_rate": 5.673523345456855e-06, + "loss": 1.4865, + "step": 15244 + }, + { + "epoch": 0.8497296694721588, + "grad_norm": 0.5705044269561768, + "learning_rate": 5.669404307476067e-06, + "loss": 1.6201, + "step": 15245 + }, + { + "epoch": 0.8497854077253219, + "grad_norm": 0.5956353545188904, + "learning_rate": 5.665286675403303e-06, + "loss": 1.8477, + "step": 15246 + }, + { + "epoch": 0.849841145978485, + "grad_norm": 0.5652217864990234, + "learning_rate": 5.661170449369168e-06, + "loss": 1.5675, + "step": 15247 + }, + { + "epoch": 0.8498968842316482, + "grad_norm": 0.566508412361145, + "learning_rate": 5.657055629504176e-06, + "loss": 1.6843, + "step": 15248 + }, + { + "epoch": 0.8499526224848113, + "grad_norm": 0.5447408556938171, + "learning_rate": 5.6529422159388615e-06, + "loss": 1.5339, + "step": 15249 + }, + { + "epoch": 0.8500083607379745, + "grad_norm": 0.5511146783828735, + "learning_rate": 5.648830208803646e-06, + "loss": 1.4031, + "step": 15250 + }, + { + "epoch": 0.8500640989911377, + "grad_norm": 0.5858672857284546, + "learning_rate": 5.644719608228954e-06, + "loss": 1.7687, + "step": 15251 + }, + { + "epoch": 0.8501198372443007, + "grad_norm": 0.7188095450401306, + "learning_rate": 5.640610414345149e-06, + "loss": 1.4767, + "step": 15252 + }, + { + "epoch": 0.8501755754974639, + "grad_norm": 0.5778825879096985, + "learning_rate": 5.636502627282542e-06, + "loss": 1.713, + "step": 15253 + }, + { + "epoch": 0.8502313137506271, + "grad_norm": 0.5594868659973145, + "learning_rate": 5.6323962471714286e-06, + "loss": 1.7735, + "step": 15254 + }, + { + "epoch": 0.8502870520037902, + "grad_norm": 0.5119555592536926, + "learning_rate": 5.628291274142017e-06, + "loss": 1.4571, + "step": 15255 + }, + { + "epoch": 0.8503427902569534, + "grad_norm": 0.5971197485923767, + "learning_rate": 5.624187708324497e-06, + "loss": 1.7026, + "step": 15256 + }, + { + "epoch": 0.8503985285101165, + "grad_norm": 0.5353764891624451, + "learning_rate": 5.620085549849013e-06, + "loss": 1.5978, + "step": 15257 + }, + { + "epoch": 0.8504542667632796, + "grad_norm": 0.5506916642189026, + "learning_rate": 5.6159847988456694e-06, + "loss": 1.4557, + "step": 15258 + }, + { + "epoch": 0.8505100050164428, + "grad_norm": 0.5897876620292664, + "learning_rate": 5.611885455444504e-06, + "loss": 1.7215, + "step": 15259 + }, + { + "epoch": 0.8505657432696059, + "grad_norm": 0.5640243291854858, + "learning_rate": 5.6077875197755316e-06, + "loss": 1.7734, + "step": 15260 + }, + { + "epoch": 0.8506214815227691, + "grad_norm": 0.5391086339950562, + "learning_rate": 5.60369099196873e-06, + "loss": 1.5654, + "step": 15261 + }, + { + "epoch": 0.8506772197759322, + "grad_norm": 0.5349490642547607, + "learning_rate": 5.59959587215399e-06, + "loss": 1.4452, + "step": 15262 + }, + { + "epoch": 0.8507329580290953, + "grad_norm": 0.5481526255607605, + "learning_rate": 5.595502160461186e-06, + "loss": 1.5936, + "step": 15263 + }, + { + "epoch": 0.8507886962822585, + "grad_norm": 0.6109682321548462, + "learning_rate": 5.591409857020175e-06, + "loss": 1.6409, + "step": 15264 + }, + { + "epoch": 0.8508444345354217, + "grad_norm": 0.5805014371871948, + "learning_rate": 5.587318961960714e-06, + "loss": 1.5613, + "step": 15265 + }, + { + "epoch": 0.8509001727885848, + "grad_norm": 0.5603240728378296, + "learning_rate": 5.583229475412561e-06, + "loss": 1.5431, + "step": 15266 + }, + { + "epoch": 0.850955911041748, + "grad_norm": 0.5892546772956848, + "learning_rate": 5.579141397505383e-06, + "loss": 1.7616, + "step": 15267 + }, + { + "epoch": 0.8510116492949111, + "grad_norm": 0.5216774940490723, + "learning_rate": 5.575054728368867e-06, + "loss": 1.3921, + "step": 15268 + }, + { + "epoch": 0.8510673875480742, + "grad_norm": 0.6074888706207275, + "learning_rate": 5.570969468132592e-06, + "loss": 1.4879, + "step": 15269 + }, + { + "epoch": 0.8511231258012374, + "grad_norm": 0.5761826634407043, + "learning_rate": 5.566885616926127e-06, + "loss": 1.5854, + "step": 15270 + }, + { + "epoch": 0.8511788640544006, + "grad_norm": 0.604915976524353, + "learning_rate": 5.562803174878983e-06, + "loss": 1.664, + "step": 15271 + }, + { + "epoch": 0.8512346023075636, + "grad_norm": 0.5562587976455688, + "learning_rate": 5.558722142120637e-06, + "loss": 1.7785, + "step": 15272 + }, + { + "epoch": 0.8512903405607268, + "grad_norm": 0.5488361120223999, + "learning_rate": 5.554642518780529e-06, + "loss": 1.6459, + "step": 15273 + }, + { + "epoch": 0.85134607881389, + "grad_norm": 0.5539646744728088, + "learning_rate": 5.550564304987999e-06, + "loss": 1.5275, + "step": 15274 + }, + { + "epoch": 0.8514018170670531, + "grad_norm": 0.5942704677581787, + "learning_rate": 5.546487500872432e-06, + "loss": 1.6295, + "step": 15275 + }, + { + "epoch": 0.8514575553202163, + "grad_norm": 0.5667029023170471, + "learning_rate": 5.542412106563094e-06, + "loss": 1.6804, + "step": 15276 + }, + { + "epoch": 0.8515132935733795, + "grad_norm": 0.5751008987426758, + "learning_rate": 5.538338122189235e-06, + "loss": 1.8148, + "step": 15277 + }, + { + "epoch": 0.8515690318265425, + "grad_norm": 0.581994354724884, + "learning_rate": 5.534265547880063e-06, + "loss": 1.7574, + "step": 15278 + }, + { + "epoch": 0.8516247700797057, + "grad_norm": 0.5172850489616394, + "learning_rate": 5.530194383764731e-06, + "loss": 1.3945, + "step": 15279 + }, + { + "epoch": 0.8516805083328689, + "grad_norm": 0.6292058825492859, + "learning_rate": 5.526124629972368e-06, + "loss": 1.8844, + "step": 15280 + }, + { + "epoch": 0.851736246586032, + "grad_norm": 0.5667592883110046, + "learning_rate": 5.522056286632021e-06, + "loss": 1.7102, + "step": 15281 + }, + { + "epoch": 0.8517919848391952, + "grad_norm": 0.5740981101989746, + "learning_rate": 5.517989353872727e-06, + "loss": 1.5469, + "step": 15282 + }, + { + "epoch": 0.8518477230923582, + "grad_norm": 0.5140419006347656, + "learning_rate": 5.513923831823459e-06, + "loss": 1.3507, + "step": 15283 + }, + { + "epoch": 0.8519034613455214, + "grad_norm": 0.6327999830245972, + "learning_rate": 5.509859720613159e-06, + "loss": 1.8035, + "step": 15284 + }, + { + "epoch": 0.8519591995986846, + "grad_norm": 0.6091687679290771, + "learning_rate": 5.505797020370706e-06, + "loss": 1.7747, + "step": 15285 + }, + { + "epoch": 0.8520149378518477, + "grad_norm": 0.5747889280319214, + "learning_rate": 5.50173573122496e-06, + "loss": 1.7629, + "step": 15286 + }, + { + "epoch": 0.8520706761050109, + "grad_norm": 0.5787854790687561, + "learning_rate": 5.497675853304718e-06, + "loss": 1.7322, + "step": 15287 + }, + { + "epoch": 0.852126414358174, + "grad_norm": 0.5640000104904175, + "learning_rate": 5.493617386738725e-06, + "loss": 1.6233, + "step": 15288 + }, + { + "epoch": 0.8521821526113371, + "grad_norm": 0.5153630375862122, + "learning_rate": 5.489560331655691e-06, + "loss": 1.1728, + "step": 15289 + }, + { + "epoch": 0.8522378908645003, + "grad_norm": 0.6024267673492432, + "learning_rate": 5.485504688184306e-06, + "loss": 1.8366, + "step": 15290 + }, + { + "epoch": 0.8522936291176635, + "grad_norm": 0.5728671550750732, + "learning_rate": 5.481450456453163e-06, + "loss": 1.7631, + "step": 15291 + }, + { + "epoch": 0.8523493673708266, + "grad_norm": 0.6010458469390869, + "learning_rate": 5.477397636590853e-06, + "loss": 1.4881, + "step": 15292 + }, + { + "epoch": 0.8524051056239897, + "grad_norm": 0.5556822419166565, + "learning_rate": 5.473346228725901e-06, + "loss": 1.7177, + "step": 15293 + }, + { + "epoch": 0.8524608438771529, + "grad_norm": 0.6074588298797607, + "learning_rate": 5.469296232986815e-06, + "loss": 1.7936, + "step": 15294 + }, + { + "epoch": 0.852516582130316, + "grad_norm": 0.5758323073387146, + "learning_rate": 5.4652476495020035e-06, + "loss": 1.846, + "step": 15295 + }, + { + "epoch": 0.8525723203834792, + "grad_norm": 0.5471615195274353, + "learning_rate": 5.461200478399886e-06, + "loss": 1.5868, + "step": 15296 + }, + { + "epoch": 0.8526280586366424, + "grad_norm": 0.5678038001060486, + "learning_rate": 5.45715471980881e-06, + "loss": 1.6317, + "step": 15297 + }, + { + "epoch": 0.8526837968898054, + "grad_norm": 0.5739495158195496, + "learning_rate": 5.4531103738570785e-06, + "loss": 1.8102, + "step": 15298 + }, + { + "epoch": 0.8527395351429686, + "grad_norm": 0.5679243803024292, + "learning_rate": 5.4490674406729724e-06, + "loss": 1.4936, + "step": 15299 + }, + { + "epoch": 0.8527952733961318, + "grad_norm": 0.528080403804779, + "learning_rate": 5.445025920384678e-06, + "loss": 1.5057, + "step": 15300 + }, + { + "epoch": 0.8528510116492949, + "grad_norm": 0.5866766571998596, + "learning_rate": 5.4409858131204085e-06, + "loss": 1.5193, + "step": 15301 + }, + { + "epoch": 0.8529067499024581, + "grad_norm": 0.5619071125984192, + "learning_rate": 5.436947119008262e-06, + "loss": 1.6733, + "step": 15302 + }, + { + "epoch": 0.8529624881556213, + "grad_norm": 0.531623125076294, + "learning_rate": 5.432909838176331e-06, + "loss": 1.5138, + "step": 15303 + }, + { + "epoch": 0.8530182264087843, + "grad_norm": 0.5578266382217407, + "learning_rate": 5.4288739707526574e-06, + "loss": 1.5927, + "step": 15304 + }, + { + "epoch": 0.8530739646619475, + "grad_norm": 0.5856972336769104, + "learning_rate": 5.424839516865232e-06, + "loss": 1.9848, + "step": 15305 + }, + { + "epoch": 0.8531297029151106, + "grad_norm": 0.6632283329963684, + "learning_rate": 5.4208064766420154e-06, + "loss": 1.8113, + "step": 15306 + }, + { + "epoch": 0.8531854411682738, + "grad_norm": 0.5741599202156067, + "learning_rate": 5.416774850210893e-06, + "loss": 1.5934, + "step": 15307 + }, + { + "epoch": 0.853241179421437, + "grad_norm": 0.5223631858825684, + "learning_rate": 5.412744637699735e-06, + "loss": 1.6988, + "step": 15308 + }, + { + "epoch": 0.8532969176746, + "grad_norm": 0.6060996651649475, + "learning_rate": 5.408715839236356e-06, + "loss": 1.7733, + "step": 15309 + }, + { + "epoch": 0.8533526559277632, + "grad_norm": 0.5588971376419067, + "learning_rate": 5.404688454948525e-06, + "loss": 1.5969, + "step": 15310 + }, + { + "epoch": 0.8534083941809264, + "grad_norm": 0.6880512833595276, + "learning_rate": 5.400662484963964e-06, + "loss": 2.1357, + "step": 15311 + }, + { + "epoch": 0.8534641324340895, + "grad_norm": 0.5473765134811401, + "learning_rate": 5.3966379294103646e-06, + "loss": 1.5925, + "step": 15312 + }, + { + "epoch": 0.8535198706872527, + "grad_norm": 0.5176913738250732, + "learning_rate": 5.392614788415357e-06, + "loss": 1.4044, + "step": 15313 + }, + { + "epoch": 0.8535756089404158, + "grad_norm": 0.6218048930168152, + "learning_rate": 5.388593062106523e-06, + "loss": 1.986, + "step": 15314 + }, + { + "epoch": 0.8536313471935789, + "grad_norm": 0.5660545825958252, + "learning_rate": 5.384572750611405e-06, + "loss": 1.6102, + "step": 15315 + }, + { + "epoch": 0.8536870854467421, + "grad_norm": 0.5434587597846985, + "learning_rate": 5.38055385405753e-06, + "loss": 1.5741, + "step": 15316 + }, + { + "epoch": 0.8537428236999053, + "grad_norm": 0.5917388796806335, + "learning_rate": 5.376536372572327e-06, + "loss": 1.7797, + "step": 15317 + }, + { + "epoch": 0.8537985619530684, + "grad_norm": 0.5587685704231262, + "learning_rate": 5.372520306283219e-06, + "loss": 1.6347, + "step": 15318 + }, + { + "epoch": 0.8538543002062315, + "grad_norm": 0.5779635906219482, + "learning_rate": 5.368505655317574e-06, + "loss": 1.6654, + "step": 15319 + }, + { + "epoch": 0.8539100384593947, + "grad_norm": 0.5655465126037598, + "learning_rate": 5.364492419802713e-06, + "loss": 1.6386, + "step": 15320 + }, + { + "epoch": 0.8539657767125578, + "grad_norm": 0.5569277405738831, + "learning_rate": 5.360480599865908e-06, + "loss": 1.5141, + "step": 15321 + }, + { + "epoch": 0.854021514965721, + "grad_norm": 0.5451422333717346, + "learning_rate": 5.3564701956343835e-06, + "loss": 1.6536, + "step": 15322 + }, + { + "epoch": 0.8540772532188842, + "grad_norm": 0.5646899342536926, + "learning_rate": 5.3524612072353434e-06, + "loss": 1.5392, + "step": 15323 + }, + { + "epoch": 0.8541329914720472, + "grad_norm": 0.5931175947189331, + "learning_rate": 5.3484536347959135e-06, + "loss": 1.622, + "step": 15324 + }, + { + "epoch": 0.8541887297252104, + "grad_norm": 0.5813482403755188, + "learning_rate": 5.34444747844321e-06, + "loss": 1.6824, + "step": 15325 + }, + { + "epoch": 0.8542444679783736, + "grad_norm": 0.5609878897666931, + "learning_rate": 5.340442738304252e-06, + "loss": 1.7105, + "step": 15326 + }, + { + "epoch": 0.8543002062315367, + "grad_norm": 0.5926048159599304, + "learning_rate": 5.336439414506089e-06, + "loss": 1.8319, + "step": 15327 + }, + { + "epoch": 0.8543559444846999, + "grad_norm": 0.6210368275642395, + "learning_rate": 5.332437507175647e-06, + "loss": 1.6904, + "step": 15328 + }, + { + "epoch": 0.8544116827378629, + "grad_norm": 0.5832761526107788, + "learning_rate": 5.3284370164398575e-06, + "loss": 1.7488, + "step": 15329 + }, + { + "epoch": 0.8544674209910261, + "grad_norm": 0.5563054084777832, + "learning_rate": 5.324437942425598e-06, + "loss": 1.5471, + "step": 15330 + }, + { + "epoch": 0.8545231592441893, + "grad_norm": 0.5379578471183777, + "learning_rate": 5.320440285259687e-06, + "loss": 1.5594, + "step": 15331 + }, + { + "epoch": 0.8545788974973524, + "grad_norm": 0.5721989870071411, + "learning_rate": 5.316444045068919e-06, + "loss": 1.3393, + "step": 15332 + }, + { + "epoch": 0.8546346357505156, + "grad_norm": 0.5492073893547058, + "learning_rate": 5.3124492219800145e-06, + "loss": 1.523, + "step": 15333 + }, + { + "epoch": 0.8546903740036788, + "grad_norm": 0.5965925455093384, + "learning_rate": 5.308455816119673e-06, + "loss": 1.9166, + "step": 15334 + }, + { + "epoch": 0.8547461122568418, + "grad_norm": 0.5864201188087463, + "learning_rate": 5.304463827614548e-06, + "loss": 1.8974, + "step": 15335 + }, + { + "epoch": 0.854801850510005, + "grad_norm": 0.5345680117607117, + "learning_rate": 5.300473256591232e-06, + "loss": 1.5165, + "step": 15336 + }, + { + "epoch": 0.8548575887631682, + "grad_norm": 0.5684088468551636, + "learning_rate": 5.296484103176291e-06, + "loss": 1.5878, + "step": 15337 + }, + { + "epoch": 0.8549133270163313, + "grad_norm": 0.5782109498977661, + "learning_rate": 5.292496367496231e-06, + "loss": 1.5214, + "step": 15338 + }, + { + "epoch": 0.8549690652694945, + "grad_norm": 0.6083633303642273, + "learning_rate": 5.288510049677536e-06, + "loss": 1.6509, + "step": 15339 + }, + { + "epoch": 0.8550248035226576, + "grad_norm": 0.5428735613822937, + "learning_rate": 5.284525149846609e-06, + "loss": 1.4928, + "step": 15340 + }, + { + "epoch": 0.8550805417758207, + "grad_norm": 0.5942511558532715, + "learning_rate": 5.2805416681298184e-06, + "loss": 1.5425, + "step": 15341 + }, + { + "epoch": 0.8551362800289839, + "grad_norm": 0.540432333946228, + "learning_rate": 5.276559604653536e-06, + "loss": 1.3634, + "step": 15342 + }, + { + "epoch": 0.8551920182821471, + "grad_norm": 0.5534170269966125, + "learning_rate": 5.272578959544017e-06, + "loss": 1.5259, + "step": 15343 + }, + { + "epoch": 0.8552477565353102, + "grad_norm": 0.5999718904495239, + "learning_rate": 5.268599732927521e-06, + "loss": 1.5523, + "step": 15344 + }, + { + "epoch": 0.8553034947884733, + "grad_norm": 0.5599328279495239, + "learning_rate": 5.26462192493023e-06, + "loss": 1.6618, + "step": 15345 + }, + { + "epoch": 0.8553592330416365, + "grad_norm": 0.6114493012428284, + "learning_rate": 5.2606455356783215e-06, + "loss": 1.8076, + "step": 15346 + }, + { + "epoch": 0.8554149712947996, + "grad_norm": 0.5662743449211121, + "learning_rate": 5.256670565297878e-06, + "loss": 1.7027, + "step": 15347 + }, + { + "epoch": 0.8554707095479628, + "grad_norm": 0.6383835673332214, + "learning_rate": 5.25269701391497e-06, + "loss": 1.7644, + "step": 15348 + }, + { + "epoch": 0.855526447801126, + "grad_norm": 0.5854325294494629, + "learning_rate": 5.24872488165562e-06, + "loss": 1.6903, + "step": 15349 + }, + { + "epoch": 0.855582186054289, + "grad_norm": 0.5545699596405029, + "learning_rate": 5.244754168645793e-06, + "loss": 1.6964, + "step": 15350 + }, + { + "epoch": 0.8556379243074522, + "grad_norm": 0.5679833889007568, + "learning_rate": 5.240784875011439e-06, + "loss": 1.6683, + "step": 15351 + }, + { + "epoch": 0.8556936625606153, + "grad_norm": 0.5067540407180786, + "learning_rate": 5.236817000878402e-06, + "loss": 1.3393, + "step": 15352 + }, + { + "epoch": 0.8557494008137785, + "grad_norm": 0.5773850679397583, + "learning_rate": 5.232850546372564e-06, + "loss": 1.6366, + "step": 15353 + }, + { + "epoch": 0.8558051390669417, + "grad_norm": 0.5768328905105591, + "learning_rate": 5.228885511619686e-06, + "loss": 1.6016, + "step": 15354 + }, + { + "epoch": 0.8558608773201047, + "grad_norm": 0.5299201011657715, + "learning_rate": 5.2249218967455215e-06, + "loss": 1.3442, + "step": 15355 + }, + { + "epoch": 0.8559166155732679, + "grad_norm": 0.5551941394805908, + "learning_rate": 5.220959701875783e-06, + "loss": 1.7464, + "step": 15356 + }, + { + "epoch": 0.8559723538264311, + "grad_norm": 0.5491567850112915, + "learning_rate": 5.216998927136118e-06, + "loss": 1.5449, + "step": 15357 + }, + { + "epoch": 0.8560280920795942, + "grad_norm": 0.5426344275474548, + "learning_rate": 5.213039572652162e-06, + "loss": 1.5248, + "step": 15358 + }, + { + "epoch": 0.8560838303327574, + "grad_norm": 0.5670163631439209, + "learning_rate": 5.209081638549446e-06, + "loss": 1.7179, + "step": 15359 + }, + { + "epoch": 0.8561395685859206, + "grad_norm": 0.5363210439682007, + "learning_rate": 5.205125124953514e-06, + "loss": 1.5125, + "step": 15360 + }, + { + "epoch": 0.8561953068390836, + "grad_norm": 0.5416868329048157, + "learning_rate": 5.201170031989844e-06, + "loss": 1.6392, + "step": 15361 + }, + { + "epoch": 0.8562510450922468, + "grad_norm": 0.5665026307106018, + "learning_rate": 5.197216359783863e-06, + "loss": 1.709, + "step": 15362 + }, + { + "epoch": 0.85630678334541, + "grad_norm": 0.5239731669425964, + "learning_rate": 5.19326410846096e-06, + "loss": 1.5904, + "step": 15363 + }, + { + "epoch": 0.8563625215985731, + "grad_norm": 0.6031737923622131, + "learning_rate": 5.18931327814648e-06, + "loss": 1.6574, + "step": 15364 + }, + { + "epoch": 0.8564182598517363, + "grad_norm": 0.5324326157569885, + "learning_rate": 5.185363868965726e-06, + "loss": 1.6079, + "step": 15365 + }, + { + "epoch": 0.8564739981048994, + "grad_norm": 0.5542480945587158, + "learning_rate": 5.181415881043933e-06, + "loss": 1.6236, + "step": 15366 + }, + { + "epoch": 0.8565297363580625, + "grad_norm": 0.5819278955459595, + "learning_rate": 5.177469314506317e-06, + "loss": 1.7752, + "step": 15367 + }, + { + "epoch": 0.8565854746112257, + "grad_norm": 0.6743700504302979, + "learning_rate": 5.173524169478045e-06, + "loss": 1.4805, + "step": 15368 + }, + { + "epoch": 0.8566412128643889, + "grad_norm": 0.5446099042892456, + "learning_rate": 5.1695804460842264e-06, + "loss": 1.4595, + "step": 15369 + }, + { + "epoch": 0.856696951117552, + "grad_norm": 0.6102388501167297, + "learning_rate": 5.165638144449936e-06, + "loss": 1.714, + "step": 15370 + }, + { + "epoch": 0.8567526893707151, + "grad_norm": 0.5492424964904785, + "learning_rate": 5.161697264700205e-06, + "loss": 1.5827, + "step": 15371 + }, + { + "epoch": 0.8568084276238783, + "grad_norm": 0.5956559181213379, + "learning_rate": 5.1577578069600174e-06, + "loss": 1.6936, + "step": 15372 + }, + { + "epoch": 0.8568641658770414, + "grad_norm": 0.5352222323417664, + "learning_rate": 5.153819771354296e-06, + "loss": 1.5163, + "step": 15373 + }, + { + "epoch": 0.8569199041302046, + "grad_norm": 0.5325025320053101, + "learning_rate": 5.14988315800794e-06, + "loss": 1.3902, + "step": 15374 + }, + { + "epoch": 0.8569756423833677, + "grad_norm": 0.5189099311828613, + "learning_rate": 5.145947967045794e-06, + "loss": 1.443, + "step": 15375 + }, + { + "epoch": 0.8570313806365308, + "grad_norm": 0.5611141324043274, + "learning_rate": 5.142014198592665e-06, + "loss": 1.8804, + "step": 15376 + }, + { + "epoch": 0.857087118889694, + "grad_norm": 0.5646120309829712, + "learning_rate": 5.138081852773313e-06, + "loss": 1.5493, + "step": 15377 + }, + { + "epoch": 0.8571428571428571, + "grad_norm": 0.6324902176856995, + "learning_rate": 5.134150929712417e-06, + "loss": 1.8992, + "step": 15378 + }, + { + "epoch": 0.8571985953960203, + "grad_norm": 0.549885094165802, + "learning_rate": 5.130221429534693e-06, + "loss": 1.6225, + "step": 15379 + }, + { + "epoch": 0.8572543336491835, + "grad_norm": 0.623681902885437, + "learning_rate": 5.126293352364725e-06, + "loss": 1.7471, + "step": 15380 + }, + { + "epoch": 0.8573100719023465, + "grad_norm": 0.5811004638671875, + "learning_rate": 5.1223666983271025e-06, + "loss": 1.6856, + "step": 15381 + }, + { + "epoch": 0.8573658101555097, + "grad_norm": 0.5791736841201782, + "learning_rate": 5.118441467546348e-06, + "loss": 1.5704, + "step": 15382 + }, + { + "epoch": 0.8574215484086729, + "grad_norm": 0.5922284722328186, + "learning_rate": 5.114517660146956e-06, + "loss": 1.6813, + "step": 15383 + }, + { + "epoch": 0.857477286661836, + "grad_norm": 0.5538209080696106, + "learning_rate": 5.110595276253377e-06, + "loss": 1.54, + "step": 15384 + }, + { + "epoch": 0.8575330249149992, + "grad_norm": 0.5606957674026489, + "learning_rate": 5.106674315989968e-06, + "loss": 1.4813, + "step": 15385 + }, + { + "epoch": 0.8575887631681623, + "grad_norm": 0.56087327003479, + "learning_rate": 5.102754779481122e-06, + "loss": 1.7306, + "step": 15386 + }, + { + "epoch": 0.8576445014213254, + "grad_norm": 0.5657017230987549, + "learning_rate": 5.09883666685112e-06, + "loss": 1.5453, + "step": 15387 + }, + { + "epoch": 0.8577002396744886, + "grad_norm": 0.5775014758110046, + "learning_rate": 5.094919978224222e-06, + "loss": 1.5683, + "step": 15388 + }, + { + "epoch": 0.8577559779276518, + "grad_norm": 0.5717271566390991, + "learning_rate": 5.091004713724651e-06, + "loss": 1.706, + "step": 15389 + }, + { + "epoch": 0.8578117161808149, + "grad_norm": 0.5753965377807617, + "learning_rate": 5.087090873476569e-06, + "loss": 1.7164, + "step": 15390 + }, + { + "epoch": 0.857867454433978, + "grad_norm": 0.5357929468154907, + "learning_rate": 5.083178457604115e-06, + "loss": 1.4208, + "step": 15391 + }, + { + "epoch": 0.8579231926871412, + "grad_norm": 0.554488480091095, + "learning_rate": 5.079267466231352e-06, + "loss": 1.5262, + "step": 15392 + }, + { + "epoch": 0.8579789309403043, + "grad_norm": 0.5660421848297119, + "learning_rate": 5.075357899482314e-06, + "loss": 1.6433, + "step": 15393 + }, + { + "epoch": 0.8580346691934675, + "grad_norm": 0.5593205094337463, + "learning_rate": 5.071449757480995e-06, + "loss": 1.4153, + "step": 15394 + }, + { + "epoch": 0.8580904074466307, + "grad_norm": 0.5544254779815674, + "learning_rate": 5.067543040351341e-06, + "loss": 1.7719, + "step": 15395 + }, + { + "epoch": 0.8581461456997937, + "grad_norm": 0.5616485476493835, + "learning_rate": 5.063637748217248e-06, + "loss": 1.6683, + "step": 15396 + }, + { + "epoch": 0.8582018839529569, + "grad_norm": 0.6132542490959167, + "learning_rate": 5.059733881202567e-06, + "loss": 1.8132, + "step": 15397 + }, + { + "epoch": 0.85825762220612, + "grad_norm": 0.5480258464813232, + "learning_rate": 5.055831439431114e-06, + "loss": 1.4149, + "step": 15398 + }, + { + "epoch": 0.8583133604592832, + "grad_norm": 0.605096161365509, + "learning_rate": 5.051930423026641e-06, + "loss": 1.7472, + "step": 15399 + }, + { + "epoch": 0.8583690987124464, + "grad_norm": 0.5746431946754456, + "learning_rate": 5.048030832112865e-06, + "loss": 1.7392, + "step": 15400 + }, + { + "epoch": 0.8584248369656095, + "grad_norm": 0.5519094467163086, + "learning_rate": 5.044132666813461e-06, + "loss": 1.6323, + "step": 15401 + }, + { + "epoch": 0.8584805752187726, + "grad_norm": 0.5745964646339417, + "learning_rate": 5.040235927252063e-06, + "loss": 1.7079, + "step": 15402 + }, + { + "epoch": 0.8585363134719358, + "grad_norm": 0.6268486380577087, + "learning_rate": 5.036340613552254e-06, + "loss": 1.7767, + "step": 15403 + }, + { + "epoch": 0.8585920517250989, + "grad_norm": 0.56236332654953, + "learning_rate": 5.032446725837547e-06, + "loss": 1.487, + "step": 15404 + }, + { + "epoch": 0.8586477899782621, + "grad_norm": 0.5816671848297119, + "learning_rate": 5.028554264231472e-06, + "loss": 1.5984, + "step": 15405 + }, + { + "epoch": 0.8587035282314253, + "grad_norm": 0.5292980670928955, + "learning_rate": 5.02466322885744e-06, + "loss": 1.5717, + "step": 15406 + }, + { + "epoch": 0.8587592664845883, + "grad_norm": 0.545213520526886, + "learning_rate": 5.02077361983887e-06, + "loss": 1.3869, + "step": 15407 + }, + { + "epoch": 0.8588150047377515, + "grad_norm": 0.5650976896286011, + "learning_rate": 5.0168854372991125e-06, + "loss": 1.4508, + "step": 15408 + }, + { + "epoch": 0.8588707429909147, + "grad_norm": 0.607316792011261, + "learning_rate": 5.012998681361475e-06, + "loss": 1.617, + "step": 15409 + }, + { + "epoch": 0.8589264812440778, + "grad_norm": 0.5596630573272705, + "learning_rate": 5.0091133521492415e-06, + "loss": 1.6986, + "step": 15410 + }, + { + "epoch": 0.858982219497241, + "grad_norm": 0.5784112811088562, + "learning_rate": 5.005229449785598e-06, + "loss": 1.4624, + "step": 15411 + }, + { + "epoch": 0.8590379577504041, + "grad_norm": 0.5670730471611023, + "learning_rate": 5.001346974393755e-06, + "loss": 1.6463, + "step": 15412 + }, + { + "epoch": 0.8590936960035672, + "grad_norm": 0.6688535809516907, + "learning_rate": 4.997465926096817e-06, + "loss": 1.6815, + "step": 15413 + }, + { + "epoch": 0.8591494342567304, + "grad_norm": 0.5701976418495178, + "learning_rate": 4.993586305017878e-06, + "loss": 1.575, + "step": 15414 + }, + { + "epoch": 0.8592051725098936, + "grad_norm": 0.5505329966545105, + "learning_rate": 4.9897081112799725e-06, + "loss": 1.5276, + "step": 15415 + }, + { + "epoch": 0.8592609107630567, + "grad_norm": 0.5370540618896484, + "learning_rate": 4.985831345006103e-06, + "loss": 1.6019, + "step": 15416 + }, + { + "epoch": 0.8593166490162198, + "grad_norm": 0.5617567896842957, + "learning_rate": 4.981956006319216e-06, + "loss": 1.5506, + "step": 15417 + }, + { + "epoch": 0.859372387269383, + "grad_norm": 0.5740174651145935, + "learning_rate": 4.978082095342207e-06, + "loss": 1.6915, + "step": 15418 + }, + { + "epoch": 0.8594281255225461, + "grad_norm": 0.5496030449867249, + "learning_rate": 4.974209612197933e-06, + "loss": 1.7283, + "step": 15419 + }, + { + "epoch": 0.8594838637757093, + "grad_norm": 0.5726914405822754, + "learning_rate": 4.970338557009219e-06, + "loss": 1.575, + "step": 15420 + }, + { + "epoch": 0.8595396020288724, + "grad_norm": 0.5253758430480957, + "learning_rate": 4.9664689298988155e-06, + "loss": 1.4879, + "step": 15421 + }, + { + "epoch": 0.8595953402820355, + "grad_norm": 0.5366917252540588, + "learning_rate": 4.962600730989459e-06, + "loss": 1.5325, + "step": 15422 + }, + { + "epoch": 0.8596510785351987, + "grad_norm": 0.554969847202301, + "learning_rate": 4.958733960403822e-06, + "loss": 1.7003, + "step": 15423 + }, + { + "epoch": 0.8597068167883618, + "grad_norm": 0.559771716594696, + "learning_rate": 4.954868618264541e-06, + "loss": 1.6402, + "step": 15424 + }, + { + "epoch": 0.859762555041525, + "grad_norm": 0.5611486434936523, + "learning_rate": 4.95100470469419e-06, + "loss": 1.5105, + "step": 15425 + }, + { + "epoch": 0.8598182932946882, + "grad_norm": 0.5651686191558838, + "learning_rate": 4.947142219815315e-06, + "loss": 1.6836, + "step": 15426 + }, + { + "epoch": 0.8598740315478512, + "grad_norm": 0.5484427809715271, + "learning_rate": 4.943281163750413e-06, + "loss": 1.4754, + "step": 15427 + }, + { + "epoch": 0.8599297698010144, + "grad_norm": 0.588737964630127, + "learning_rate": 4.9394215366219296e-06, + "loss": 1.7882, + "step": 15428 + }, + { + "epoch": 0.8599855080541776, + "grad_norm": 0.5918551087379456, + "learning_rate": 4.9355633385522905e-06, + "loss": 1.8442, + "step": 15429 + }, + { + "epoch": 0.8600412463073407, + "grad_norm": 0.594916045665741, + "learning_rate": 4.931706569663813e-06, + "loss": 1.6857, + "step": 15430 + }, + { + "epoch": 0.8600969845605039, + "grad_norm": 0.5604150295257568, + "learning_rate": 4.9278512300788556e-06, + "loss": 1.5753, + "step": 15431 + }, + { + "epoch": 0.8601527228136671, + "grad_norm": 0.5494148135185242, + "learning_rate": 4.92399731991966e-06, + "loss": 1.5379, + "step": 15432 + }, + { + "epoch": 0.8602084610668301, + "grad_norm": 0.5493863224983215, + "learning_rate": 4.92014483930846e-06, + "loss": 1.6328, + "step": 15433 + }, + { + "epoch": 0.8602641993199933, + "grad_norm": 0.5823617577552795, + "learning_rate": 4.916293788367432e-06, + "loss": 1.6785, + "step": 15434 + }, + { + "epoch": 0.8603199375731565, + "grad_norm": 0.5982986092567444, + "learning_rate": 4.912444167218705e-06, + "loss": 1.8026, + "step": 15435 + }, + { + "epoch": 0.8603756758263196, + "grad_norm": 0.5928519368171692, + "learning_rate": 4.908595975984387e-06, + "loss": 1.5967, + "step": 15436 + }, + { + "epoch": 0.8604314140794828, + "grad_norm": 0.5546932220458984, + "learning_rate": 4.904749214786475e-06, + "loss": 1.3421, + "step": 15437 + }, + { + "epoch": 0.8604871523326459, + "grad_norm": 0.5764714479446411, + "learning_rate": 4.900903883747021e-06, + "loss": 1.7279, + "step": 15438 + }, + { + "epoch": 0.860542890585809, + "grad_norm": 0.6450945734977722, + "learning_rate": 4.897059982987939e-06, + "loss": 1.6473, + "step": 15439 + }, + { + "epoch": 0.8605986288389722, + "grad_norm": 0.5633136630058289, + "learning_rate": 4.893217512631143e-06, + "loss": 1.7516, + "step": 15440 + }, + { + "epoch": 0.8606543670921354, + "grad_norm": 0.5991867780685425, + "learning_rate": 4.889376472798502e-06, + "loss": 1.8468, + "step": 15441 + }, + { + "epoch": 0.8607101053452985, + "grad_norm": 0.5585817694664001, + "learning_rate": 4.8855368636118175e-06, + "loss": 1.6379, + "step": 15442 + }, + { + "epoch": 0.8607658435984616, + "grad_norm": 0.5958824157714844, + "learning_rate": 4.881698685192887e-06, + "loss": 1.6127, + "step": 15443 + }, + { + "epoch": 0.8608215818516247, + "grad_norm": 0.5530955791473389, + "learning_rate": 4.877861937663397e-06, + "loss": 1.487, + "step": 15444 + }, + { + "epoch": 0.8608773201047879, + "grad_norm": 0.5415002107620239, + "learning_rate": 4.874026621145055e-06, + "loss": 1.4375, + "step": 15445 + }, + { + "epoch": 0.8609330583579511, + "grad_norm": 0.5727704763412476, + "learning_rate": 4.870192735759482e-06, + "loss": 1.7431, + "step": 15446 + }, + { + "epoch": 0.8609887966111142, + "grad_norm": 0.5700619220733643, + "learning_rate": 4.866360281628268e-06, + "loss": 1.5807, + "step": 15447 + }, + { + "epoch": 0.8610445348642773, + "grad_norm": 0.5800610184669495, + "learning_rate": 4.862529258872961e-06, + "loss": 1.8166, + "step": 15448 + }, + { + "epoch": 0.8611002731174405, + "grad_norm": 0.5496475696563721, + "learning_rate": 4.858699667615057e-06, + "loss": 1.4941, + "step": 15449 + }, + { + "epoch": 0.8611560113706036, + "grad_norm": 0.6145876049995422, + "learning_rate": 4.8548715079760166e-06, + "loss": 1.8157, + "step": 15450 + }, + { + "epoch": 0.8612117496237668, + "grad_norm": 0.587644100189209, + "learning_rate": 4.85104478007723e-06, + "loss": 1.641, + "step": 15451 + }, + { + "epoch": 0.86126748787693, + "grad_norm": 0.5685145258903503, + "learning_rate": 4.847219484040055e-06, + "loss": 1.7062, + "step": 15452 + }, + { + "epoch": 0.861323226130093, + "grad_norm": 0.5452786087989807, + "learning_rate": 4.843395619985836e-06, + "loss": 1.5513, + "step": 15453 + }, + { + "epoch": 0.8613789643832562, + "grad_norm": 0.5764070749282837, + "learning_rate": 4.839573188035818e-06, + "loss": 1.7844, + "step": 15454 + }, + { + "epoch": 0.8614347026364194, + "grad_norm": 0.5676529407501221, + "learning_rate": 4.835752188311249e-06, + "loss": 1.6284, + "step": 15455 + }, + { + "epoch": 0.8614904408895825, + "grad_norm": 0.5460330843925476, + "learning_rate": 4.8319326209332715e-06, + "loss": 1.7408, + "step": 15456 + }, + { + "epoch": 0.8615461791427457, + "grad_norm": 0.571887731552124, + "learning_rate": 4.828114486023061e-06, + "loss": 1.6529, + "step": 15457 + }, + { + "epoch": 0.8616019173959089, + "grad_norm": 0.5191607475280762, + "learning_rate": 4.824297783701681e-06, + "loss": 1.429, + "step": 15458 + }, + { + "epoch": 0.8616576556490719, + "grad_norm": 0.5630595088005066, + "learning_rate": 4.82048251409018e-06, + "loss": 1.7355, + "step": 15459 + }, + { + "epoch": 0.8617133939022351, + "grad_norm": 0.5613915920257568, + "learning_rate": 4.816668677309566e-06, + "loss": 1.6579, + "step": 15460 + }, + { + "epoch": 0.8617691321553983, + "grad_norm": 0.5973622798919678, + "learning_rate": 4.812856273480776e-06, + "loss": 1.8092, + "step": 15461 + }, + { + "epoch": 0.8618248704085614, + "grad_norm": 0.5976740121841431, + "learning_rate": 4.80904530272474e-06, + "loss": 1.6346, + "step": 15462 + }, + { + "epoch": 0.8618806086617246, + "grad_norm": 0.559171736240387, + "learning_rate": 4.805235765162286e-06, + "loss": 1.4948, + "step": 15463 + }, + { + "epoch": 0.8619363469148877, + "grad_norm": 0.5460478663444519, + "learning_rate": 4.801427660914265e-06, + "loss": 1.5347, + "step": 15464 + }, + { + "epoch": 0.8619920851680508, + "grad_norm": 0.6621419787406921, + "learning_rate": 4.797620990101431e-06, + "loss": 1.9691, + "step": 15465 + }, + { + "epoch": 0.862047823421214, + "grad_norm": 0.6295529007911682, + "learning_rate": 4.793815752844505e-06, + "loss": 1.7786, + "step": 15466 + }, + { + "epoch": 0.8621035616743771, + "grad_norm": 0.5284590125083923, + "learning_rate": 4.7900119492641726e-06, + "loss": 1.4825, + "step": 15467 + }, + { + "epoch": 0.8621592999275403, + "grad_norm": 0.5299116969108582, + "learning_rate": 4.786209579481072e-06, + "loss": 1.445, + "step": 15468 + }, + { + "epoch": 0.8622150381807034, + "grad_norm": 0.5334445834159851, + "learning_rate": 4.782408643615799e-06, + "loss": 1.4002, + "step": 15469 + }, + { + "epoch": 0.8622707764338665, + "grad_norm": 0.5246026515960693, + "learning_rate": 4.77860914178887e-06, + "loss": 1.4445, + "step": 15470 + }, + { + "epoch": 0.8623265146870297, + "grad_norm": 0.6295610070228577, + "learning_rate": 4.774811074120805e-06, + "loss": 1.6644, + "step": 15471 + }, + { + "epoch": 0.8623822529401929, + "grad_norm": 0.5478858351707458, + "learning_rate": 4.771014440732052e-06, + "loss": 1.62, + "step": 15472 + }, + { + "epoch": 0.862437991193356, + "grad_norm": 0.5671639442443848, + "learning_rate": 4.76721924174302e-06, + "loss": 1.7278, + "step": 15473 + }, + { + "epoch": 0.8624937294465191, + "grad_norm": 0.5437140464782715, + "learning_rate": 4.763425477274064e-06, + "loss": 1.4852, + "step": 15474 + }, + { + "epoch": 0.8625494676996823, + "grad_norm": 0.6082166433334351, + "learning_rate": 4.759633147445508e-06, + "loss": 1.7785, + "step": 15475 + }, + { + "epoch": 0.8626052059528454, + "grad_norm": 0.5816795229911804, + "learning_rate": 4.755842252377629e-06, + "loss": 1.7309, + "step": 15476 + }, + { + "epoch": 0.8626609442060086, + "grad_norm": 0.5319193601608276, + "learning_rate": 4.752052792190625e-06, + "loss": 1.6361, + "step": 15477 + }, + { + "epoch": 0.8627166824591718, + "grad_norm": 0.5771275758743286, + "learning_rate": 4.748264767004701e-06, + "loss": 1.7223, + "step": 15478 + }, + { + "epoch": 0.8627724207123348, + "grad_norm": 0.5817843079566956, + "learning_rate": 4.744478176939976e-06, + "loss": 1.8503, + "step": 15479 + }, + { + "epoch": 0.862828158965498, + "grad_norm": 0.6019348502159119, + "learning_rate": 4.740693022116549e-06, + "loss": 1.8527, + "step": 15480 + }, + { + "epoch": 0.8628838972186612, + "grad_norm": 0.5442162156105042, + "learning_rate": 4.736909302654469e-06, + "loss": 1.5862, + "step": 15481 + }, + { + "epoch": 0.8629396354718243, + "grad_norm": 0.5274694561958313, + "learning_rate": 4.7331270186737055e-06, + "loss": 1.3339, + "step": 15482 + }, + { + "epoch": 0.8629953737249875, + "grad_norm": 0.5995909571647644, + "learning_rate": 4.729346170294247e-06, + "loss": 1.6642, + "step": 15483 + }, + { + "epoch": 0.8630511119781507, + "grad_norm": 0.5429494976997375, + "learning_rate": 4.725566757635969e-06, + "loss": 1.4468, + "step": 15484 + }, + { + "epoch": 0.8631068502313137, + "grad_norm": 0.5837387442588806, + "learning_rate": 4.721788780818748e-06, + "loss": 1.6472, + "step": 15485 + }, + { + "epoch": 0.8631625884844769, + "grad_norm": 0.5596417784690857, + "learning_rate": 4.718012239962399e-06, + "loss": 1.5244, + "step": 15486 + }, + { + "epoch": 0.8632183267376401, + "grad_norm": 0.6326264142990112, + "learning_rate": 4.714237135186689e-06, + "loss": 2.0101, + "step": 15487 + }, + { + "epoch": 0.8632740649908032, + "grad_norm": 0.5334985852241516, + "learning_rate": 4.710463466611348e-06, + "loss": 1.5559, + "step": 15488 + }, + { + "epoch": 0.8633298032439664, + "grad_norm": 0.5594983100891113, + "learning_rate": 4.706691234356031e-06, + "loss": 1.485, + "step": 15489 + }, + { + "epoch": 0.8633855414971294, + "grad_norm": 0.5688342452049255, + "learning_rate": 4.702920438540409e-06, + "loss": 1.6059, + "step": 15490 + }, + { + "epoch": 0.8634412797502926, + "grad_norm": 0.5246999859809875, + "learning_rate": 4.699151079284042e-06, + "loss": 1.5789, + "step": 15491 + }, + { + "epoch": 0.8634970180034558, + "grad_norm": 0.5973978638648987, + "learning_rate": 4.695383156706484e-06, + "loss": 1.675, + "step": 15492 + }, + { + "epoch": 0.8635527562566189, + "grad_norm": 0.5514283776283264, + "learning_rate": 4.691616670927224e-06, + "loss": 1.5333, + "step": 15493 + }, + { + "epoch": 0.863608494509782, + "grad_norm": 0.5539659261703491, + "learning_rate": 4.68785162206572e-06, + "loss": 1.4639, + "step": 15494 + }, + { + "epoch": 0.8636642327629452, + "grad_norm": 0.5989444255828857, + "learning_rate": 4.684088010241377e-06, + "loss": 1.79, + "step": 15495 + }, + { + "epoch": 0.8637199710161083, + "grad_norm": 0.5403555035591125, + "learning_rate": 4.680325835573551e-06, + "loss": 1.6528, + "step": 15496 + }, + { + "epoch": 0.8637757092692715, + "grad_norm": 0.5443036556243896, + "learning_rate": 4.676565098181551e-06, + "loss": 1.7418, + "step": 15497 + }, + { + "epoch": 0.8638314475224347, + "grad_norm": 0.6038947701454163, + "learning_rate": 4.6728057981846596e-06, + "loss": 1.8748, + "step": 15498 + }, + { + "epoch": 0.8638871857755978, + "grad_norm": 0.5979270935058594, + "learning_rate": 4.669047935702087e-06, + "loss": 1.599, + "step": 15499 + }, + { + "epoch": 0.8639429240287609, + "grad_norm": 0.5527109503746033, + "learning_rate": 4.665291510853015e-06, + "loss": 1.6501, + "step": 15500 + }, + { + "epoch": 0.8639986622819241, + "grad_norm": 0.5590683817863464, + "learning_rate": 4.661536523756576e-06, + "loss": 1.7524, + "step": 15501 + }, + { + "epoch": 0.8640544005350872, + "grad_norm": 0.5427082777023315, + "learning_rate": 4.6577829745318714e-06, + "loss": 1.5037, + "step": 15502 + }, + { + "epoch": 0.8641101387882504, + "grad_norm": 0.6110124588012695, + "learning_rate": 4.654030863297915e-06, + "loss": 1.6441, + "step": 15503 + }, + { + "epoch": 0.8641658770414136, + "grad_norm": 0.5651621222496033, + "learning_rate": 4.650280190173717e-06, + "loss": 1.593, + "step": 15504 + }, + { + "epoch": 0.8642216152945766, + "grad_norm": 0.5888461470603943, + "learning_rate": 4.6465309552782224e-06, + "loss": 1.7073, + "step": 15505 + }, + { + "epoch": 0.8642773535477398, + "grad_norm": 0.5709715485572815, + "learning_rate": 4.642783158730335e-06, + "loss": 1.6903, + "step": 15506 + }, + { + "epoch": 0.864333091800903, + "grad_norm": 0.6093868017196655, + "learning_rate": 4.639036800648927e-06, + "loss": 1.8398, + "step": 15507 + }, + { + "epoch": 0.8643888300540661, + "grad_norm": 0.5452781915664673, + "learning_rate": 4.635291881152776e-06, + "loss": 1.5834, + "step": 15508 + }, + { + "epoch": 0.8644445683072293, + "grad_norm": 0.6487130522727966, + "learning_rate": 4.631548400360697e-06, + "loss": 1.6087, + "step": 15509 + }, + { + "epoch": 0.8645003065603925, + "grad_norm": 0.5405240058898926, + "learning_rate": 4.627806358391374e-06, + "loss": 1.5439, + "step": 15510 + }, + { + "epoch": 0.8645560448135555, + "grad_norm": 0.5847694873809814, + "learning_rate": 4.624065755363494e-06, + "loss": 1.7105, + "step": 15511 + }, + { + "epoch": 0.8646117830667187, + "grad_norm": 0.5682114362716675, + "learning_rate": 4.620326591395685e-06, + "loss": 1.5566, + "step": 15512 + }, + { + "epoch": 0.8646675213198818, + "grad_norm": 0.5714296698570251, + "learning_rate": 4.616588866606542e-06, + "loss": 1.6774, + "step": 15513 + }, + { + "epoch": 0.864723259573045, + "grad_norm": 0.573913037776947, + "learning_rate": 4.612852581114602e-06, + "loss": 1.4555, + "step": 15514 + }, + { + "epoch": 0.8647789978262082, + "grad_norm": 0.5963373780250549, + "learning_rate": 4.609117735038332e-06, + "loss": 1.6735, + "step": 15515 + }, + { + "epoch": 0.8648347360793712, + "grad_norm": 0.5759990811347961, + "learning_rate": 4.605384328496221e-06, + "loss": 1.8024, + "step": 15516 + }, + { + "epoch": 0.8648904743325344, + "grad_norm": 0.5373070240020752, + "learning_rate": 4.60165236160664e-06, + "loss": 1.4956, + "step": 15517 + }, + { + "epoch": 0.8649462125856976, + "grad_norm": 0.609135091304779, + "learning_rate": 4.597921834487956e-06, + "loss": 1.8077, + "step": 15518 + }, + { + "epoch": 0.8650019508388607, + "grad_norm": 0.5510380268096924, + "learning_rate": 4.59419274725848e-06, + "loss": 1.5009, + "step": 15519 + }, + { + "epoch": 0.8650576890920239, + "grad_norm": 0.5822418928146362, + "learning_rate": 4.590465100036473e-06, + "loss": 1.6073, + "step": 15520 + }, + { + "epoch": 0.865113427345187, + "grad_norm": 0.5392298698425293, + "learning_rate": 4.586738892940173e-06, + "loss": 1.594, + "step": 15521 + }, + { + "epoch": 0.8651691655983501, + "grad_norm": 0.5079191327095032, + "learning_rate": 4.58301412608772e-06, + "loss": 1.2062, + "step": 15522 + }, + { + "epoch": 0.8652249038515133, + "grad_norm": 0.5669457316398621, + "learning_rate": 4.579290799597263e-06, + "loss": 1.5692, + "step": 15523 + }, + { + "epoch": 0.8652806421046765, + "grad_norm": 0.590228796005249, + "learning_rate": 4.57556891358688e-06, + "loss": 1.7171, + "step": 15524 + }, + { + "epoch": 0.8653363803578396, + "grad_norm": 0.5493983030319214, + "learning_rate": 4.571848468174611e-06, + "loss": 1.475, + "step": 15525 + }, + { + "epoch": 0.8653921186110027, + "grad_norm": 0.5402043461799622, + "learning_rate": 4.568129463478443e-06, + "loss": 1.5265, + "step": 15526 + }, + { + "epoch": 0.8654478568641659, + "grad_norm": 0.5576213002204895, + "learning_rate": 4.564411899616322e-06, + "loss": 1.5385, + "step": 15527 + }, + { + "epoch": 0.865503595117329, + "grad_norm": 0.5966400504112244, + "learning_rate": 4.560695776706159e-06, + "loss": 1.8107, + "step": 15528 + }, + { + "epoch": 0.8655593333704922, + "grad_norm": 0.5934291481971741, + "learning_rate": 4.556981094865781e-06, + "loss": 1.8119, + "step": 15529 + }, + { + "epoch": 0.8656150716236554, + "grad_norm": 0.6066737771034241, + "learning_rate": 4.553267854213017e-06, + "loss": 1.8444, + "step": 15530 + }, + { + "epoch": 0.8656708098768184, + "grad_norm": 0.5464828014373779, + "learning_rate": 4.5495560548656224e-06, + "loss": 1.3499, + "step": 15531 + }, + { + "epoch": 0.8657265481299816, + "grad_norm": 0.5383492112159729, + "learning_rate": 4.545845696941314e-06, + "loss": 1.6111, + "step": 15532 + }, + { + "epoch": 0.8657822863831448, + "grad_norm": 0.5318053960800171, + "learning_rate": 4.542136780557776e-06, + "loss": 1.6156, + "step": 15533 + }, + { + "epoch": 0.8658380246363079, + "grad_norm": 0.5948800444602966, + "learning_rate": 4.538429305832597e-06, + "loss": 1.7633, + "step": 15534 + }, + { + "epoch": 0.8658937628894711, + "grad_norm": 0.5563294887542725, + "learning_rate": 4.534723272883407e-06, + "loss": 1.7511, + "step": 15535 + }, + { + "epoch": 0.8659495011426341, + "grad_norm": 0.5767949223518372, + "learning_rate": 4.5310186818277035e-06, + "loss": 1.7555, + "step": 15536 + }, + { + "epoch": 0.8660052393957973, + "grad_norm": 0.5797931551933289, + "learning_rate": 4.527315532782983e-06, + "loss": 1.5834, + "step": 15537 + }, + { + "epoch": 0.8660609776489605, + "grad_norm": 0.6480404734611511, + "learning_rate": 4.523613825866685e-06, + "loss": 1.9246, + "step": 15538 + }, + { + "epoch": 0.8661167159021236, + "grad_norm": 0.5480387210845947, + "learning_rate": 4.519913561196215e-06, + "loss": 1.5153, + "step": 15539 + }, + { + "epoch": 0.8661724541552868, + "grad_norm": 0.5448498129844666, + "learning_rate": 4.51621473888893e-06, + "loss": 1.5956, + "step": 15540 + }, + { + "epoch": 0.86622819240845, + "grad_norm": 0.5855646729469299, + "learning_rate": 4.512517359062107e-06, + "loss": 1.649, + "step": 15541 + }, + { + "epoch": 0.866283930661613, + "grad_norm": 0.572676956653595, + "learning_rate": 4.508821421833037e-06, + "loss": 1.5356, + "step": 15542 + }, + { + "epoch": 0.8663396689147762, + "grad_norm": 0.5771461725234985, + "learning_rate": 4.505126927318915e-06, + "loss": 1.7055, + "step": 15543 + }, + { + "epoch": 0.8663954071679394, + "grad_norm": 0.5787577629089355, + "learning_rate": 4.501433875636912e-06, + "loss": 1.6176, + "step": 15544 + }, + { + "epoch": 0.8664511454211025, + "grad_norm": 0.568511962890625, + "learning_rate": 4.497742266904148e-06, + "loss": 1.6723, + "step": 15545 + }, + { + "epoch": 0.8665068836742656, + "grad_norm": 0.6242843866348267, + "learning_rate": 4.494052101237706e-06, + "loss": 1.712, + "step": 15546 + }, + { + "epoch": 0.8665626219274288, + "grad_norm": 0.5609937906265259, + "learning_rate": 4.490363378754625e-06, + "loss": 1.5149, + "step": 15547 + }, + { + "epoch": 0.8666183601805919, + "grad_norm": 0.6083208322525024, + "learning_rate": 4.486676099571863e-06, + "loss": 1.7661, + "step": 15548 + }, + { + "epoch": 0.8666740984337551, + "grad_norm": 0.6923094987869263, + "learning_rate": 4.4829902638063746e-06, + "loss": 1.6221, + "step": 15549 + }, + { + "epoch": 0.8667298366869183, + "grad_norm": 0.5632875561714172, + "learning_rate": 4.479305871575057e-06, + "loss": 1.7164, + "step": 15550 + }, + { + "epoch": 0.8667855749400813, + "grad_norm": 0.5461005568504333, + "learning_rate": 4.475622922994749e-06, + "loss": 1.4664, + "step": 15551 + }, + { + "epoch": 0.8668413131932445, + "grad_norm": 0.5477694869041443, + "learning_rate": 4.471941418182257e-06, + "loss": 1.5011, + "step": 15552 + }, + { + "epoch": 0.8668970514464077, + "grad_norm": 0.5656465291976929, + "learning_rate": 4.468261357254339e-06, + "loss": 1.8066, + "step": 15553 + }, + { + "epoch": 0.8669527896995708, + "grad_norm": 0.5492956638336182, + "learning_rate": 4.46458274032771e-06, + "loss": 1.5738, + "step": 15554 + }, + { + "epoch": 0.867008527952734, + "grad_norm": 0.5633922815322876, + "learning_rate": 4.460905567519019e-06, + "loss": 1.749, + "step": 15555 + }, + { + "epoch": 0.8670642662058972, + "grad_norm": 0.5624592304229736, + "learning_rate": 4.457229838944888e-06, + "loss": 1.6565, + "step": 15556 + }, + { + "epoch": 0.8671200044590602, + "grad_norm": 0.5875877141952515, + "learning_rate": 4.453555554721894e-06, + "loss": 1.7361, + "step": 15557 + }, + { + "epoch": 0.8671757427122234, + "grad_norm": 0.5672153830528259, + "learning_rate": 4.449882714966569e-06, + "loss": 1.6593, + "step": 15558 + }, + { + "epoch": 0.8672314809653865, + "grad_norm": 0.5771555304527283, + "learning_rate": 4.446211319795385e-06, + "loss": 1.6871, + "step": 15559 + }, + { + "epoch": 0.8672872192185497, + "grad_norm": 0.5882150530815125, + "learning_rate": 4.442541369324782e-06, + "loss": 1.7918, + "step": 15560 + }, + { + "epoch": 0.8673429574717129, + "grad_norm": 0.5746208429336548, + "learning_rate": 4.438872863671156e-06, + "loss": 1.6794, + "step": 15561 + }, + { + "epoch": 0.8673986957248759, + "grad_norm": 0.616490364074707, + "learning_rate": 4.435205802950832e-06, + "loss": 1.7128, + "step": 15562 + }, + { + "epoch": 0.8674544339780391, + "grad_norm": 0.5822766423225403, + "learning_rate": 4.431540187280126e-06, + "loss": 1.7655, + "step": 15563 + }, + { + "epoch": 0.8675101722312023, + "grad_norm": 0.5353412628173828, + "learning_rate": 4.427876016775273e-06, + "loss": 1.5178, + "step": 15564 + }, + { + "epoch": 0.8675659104843654, + "grad_norm": 0.5344415903091431, + "learning_rate": 4.424213291552498e-06, + "loss": 1.435, + "step": 15565 + }, + { + "epoch": 0.8676216487375286, + "grad_norm": 0.5679115653038025, + "learning_rate": 4.420552011727952e-06, + "loss": 1.6849, + "step": 15566 + }, + { + "epoch": 0.8676773869906917, + "grad_norm": 0.5594514012336731, + "learning_rate": 4.416892177417736e-06, + "loss": 1.428, + "step": 15567 + }, + { + "epoch": 0.8677331252438548, + "grad_norm": 0.7073445320129395, + "learning_rate": 4.413233788737953e-06, + "loss": 2.1306, + "step": 15568 + }, + { + "epoch": 0.867788863497018, + "grad_norm": 0.5675196051597595, + "learning_rate": 4.409576845804591e-06, + "loss": 1.6757, + "step": 15569 + }, + { + "epoch": 0.8678446017501812, + "grad_norm": 0.584666907787323, + "learning_rate": 4.405921348733644e-06, + "loss": 1.6635, + "step": 15570 + }, + { + "epoch": 0.8679003400033443, + "grad_norm": 0.6141462922096252, + "learning_rate": 4.402267297641044e-06, + "loss": 1.6816, + "step": 15571 + }, + { + "epoch": 0.8679560782565074, + "grad_norm": 0.6230907440185547, + "learning_rate": 4.398614692642666e-06, + "loss": 1.7229, + "step": 15572 + }, + { + "epoch": 0.8680118165096706, + "grad_norm": 0.5699254870414734, + "learning_rate": 4.394963533854362e-06, + "loss": 1.5502, + "step": 15573 + }, + { + "epoch": 0.8680675547628337, + "grad_norm": 0.5758548974990845, + "learning_rate": 4.391313821391918e-06, + "loss": 1.6453, + "step": 15574 + }, + { + "epoch": 0.8681232930159969, + "grad_norm": 0.527561366558075, + "learning_rate": 4.387665555371079e-06, + "loss": 1.4136, + "step": 15575 + }, + { + "epoch": 0.8681790312691601, + "grad_norm": 0.5711715817451477, + "learning_rate": 4.384018735907547e-06, + "loss": 1.7267, + "step": 15576 + }, + { + "epoch": 0.8682347695223231, + "grad_norm": 0.5088726282119751, + "learning_rate": 4.380373363116985e-06, + "loss": 1.313, + "step": 15577 + }, + { + "epoch": 0.8682905077754863, + "grad_norm": 0.5771408081054688, + "learning_rate": 4.376729437114996e-06, + "loss": 1.7581, + "step": 15578 + }, + { + "epoch": 0.8683462460286495, + "grad_norm": 0.5671499967575073, + "learning_rate": 4.373086958017147e-06, + "loss": 1.7934, + "step": 15579 + }, + { + "epoch": 0.8684019842818126, + "grad_norm": 0.5877515077590942, + "learning_rate": 4.3694459259389696e-06, + "loss": 1.5457, + "step": 15580 + }, + { + "epoch": 0.8684577225349758, + "grad_norm": 0.5331607460975647, + "learning_rate": 4.3658063409959095e-06, + "loss": 1.5551, + "step": 15581 + }, + { + "epoch": 0.8685134607881388, + "grad_norm": 0.557798445224762, + "learning_rate": 4.3621682033034075e-06, + "loss": 1.6441, + "step": 15582 + }, + { + "epoch": 0.868569199041302, + "grad_norm": 0.515790581703186, + "learning_rate": 4.358531512976849e-06, + "loss": 1.3928, + "step": 15583 + }, + { + "epoch": 0.8686249372944652, + "grad_norm": 0.5497269630432129, + "learning_rate": 4.354896270131553e-06, + "loss": 1.6283, + "step": 15584 + }, + { + "epoch": 0.8686806755476283, + "grad_norm": 0.6632587909698486, + "learning_rate": 4.351262474882822e-06, + "loss": 2.1723, + "step": 15585 + }, + { + "epoch": 0.8687364138007915, + "grad_norm": 0.543668270111084, + "learning_rate": 4.347630127345897e-06, + "loss": 1.6998, + "step": 15586 + }, + { + "epoch": 0.8687921520539547, + "grad_norm": 0.5417209267616272, + "learning_rate": 4.343999227635981e-06, + "loss": 1.5729, + "step": 15587 + }, + { + "epoch": 0.8688478903071177, + "grad_norm": 0.6380163431167603, + "learning_rate": 4.340369775868203e-06, + "loss": 1.9269, + "step": 15588 + }, + { + "epoch": 0.8689036285602809, + "grad_norm": 0.5393193364143372, + "learning_rate": 4.336741772157688e-06, + "loss": 1.6061, + "step": 15589 + }, + { + "epoch": 0.8689593668134441, + "grad_norm": 0.5712205767631531, + "learning_rate": 4.333115216619482e-06, + "loss": 1.6895, + "step": 15590 + }, + { + "epoch": 0.8690151050666072, + "grad_norm": 0.5683231353759766, + "learning_rate": 4.329490109368611e-06, + "loss": 1.6801, + "step": 15591 + }, + { + "epoch": 0.8690708433197704, + "grad_norm": 0.5479118227958679, + "learning_rate": 4.325866450520044e-06, + "loss": 1.4233, + "step": 15592 + }, + { + "epoch": 0.8691265815729335, + "grad_norm": 0.5884711146354675, + "learning_rate": 4.322244240188672e-06, + "loss": 1.6267, + "step": 15593 + }, + { + "epoch": 0.8691823198260966, + "grad_norm": 0.5951160192489624, + "learning_rate": 4.318623478489414e-06, + "loss": 1.8838, + "step": 15594 + }, + { + "epoch": 0.8692380580792598, + "grad_norm": 0.5782709717750549, + "learning_rate": 4.315004165537073e-06, + "loss": 1.7112, + "step": 15595 + }, + { + "epoch": 0.869293796332423, + "grad_norm": 0.535774290561676, + "learning_rate": 4.311386301446435e-06, + "loss": 1.513, + "step": 15596 + }, + { + "epoch": 0.8693495345855861, + "grad_norm": 0.5398627519607544, + "learning_rate": 4.307769886332236e-06, + "loss": 1.6379, + "step": 15597 + }, + { + "epoch": 0.8694052728387492, + "grad_norm": 0.5375766754150391, + "learning_rate": 4.304154920309178e-06, + "loss": 1.4164, + "step": 15598 + }, + { + "epoch": 0.8694610110919124, + "grad_norm": 0.5592421889305115, + "learning_rate": 4.3005414034919086e-06, + "loss": 1.5725, + "step": 15599 + }, + { + "epoch": 0.8695167493450755, + "grad_norm": 0.5812150239944458, + "learning_rate": 4.296929335995009e-06, + "loss": 1.6476, + "step": 15600 + }, + { + "epoch": 0.8695724875982387, + "grad_norm": 0.5794095396995544, + "learning_rate": 4.2933187179330424e-06, + "loss": 1.8728, + "step": 15601 + }, + { + "epoch": 0.8696282258514019, + "grad_norm": 0.5979856252670288, + "learning_rate": 4.2897095494205176e-06, + "loss": 1.7015, + "step": 15602 + }, + { + "epoch": 0.8696839641045649, + "grad_norm": 0.5352218151092529, + "learning_rate": 4.2861018305718984e-06, + "loss": 1.7217, + "step": 15603 + }, + { + "epoch": 0.8697397023577281, + "grad_norm": 0.6218880414962769, + "learning_rate": 4.282495561501598e-06, + "loss": 1.8056, + "step": 15604 + }, + { + "epoch": 0.8697954406108912, + "grad_norm": 0.5992869138717651, + "learning_rate": 4.278890742323988e-06, + "loss": 1.8375, + "step": 15605 + }, + { + "epoch": 0.8698511788640544, + "grad_norm": 0.5773003101348877, + "learning_rate": 4.275287373153403e-06, + "loss": 1.5903, + "step": 15606 + }, + { + "epoch": 0.8699069171172176, + "grad_norm": 0.5959195494651794, + "learning_rate": 4.271685454104091e-06, + "loss": 1.6892, + "step": 15607 + }, + { + "epoch": 0.8699626553703806, + "grad_norm": 0.5282344222068787, + "learning_rate": 4.26808498529031e-06, + "loss": 1.5293, + "step": 15608 + }, + { + "epoch": 0.8700183936235438, + "grad_norm": 0.539767861366272, + "learning_rate": 4.264485966826231e-06, + "loss": 1.6881, + "step": 15609 + }, + { + "epoch": 0.870074131876707, + "grad_norm": 0.5524450540542603, + "learning_rate": 4.260888398826008e-06, + "loss": 1.5591, + "step": 15610 + }, + { + "epoch": 0.8701298701298701, + "grad_norm": 0.6019861102104187, + "learning_rate": 4.257292281403724e-06, + "loss": 1.4014, + "step": 15611 + }, + { + "epoch": 0.8701856083830333, + "grad_norm": 0.5807546973228455, + "learning_rate": 4.25369761467343e-06, + "loss": 1.6571, + "step": 15612 + }, + { + "epoch": 0.8702413466361965, + "grad_norm": 0.5696931481361389, + "learning_rate": 4.250104398749138e-06, + "loss": 1.5419, + "step": 15613 + }, + { + "epoch": 0.8702970848893595, + "grad_norm": 0.5705064535140991, + "learning_rate": 4.246512633744781e-06, + "loss": 1.7289, + "step": 15614 + }, + { + "epoch": 0.8703528231425227, + "grad_norm": 0.5957085490226746, + "learning_rate": 4.242922319774284e-06, + "loss": 1.6259, + "step": 15615 + }, + { + "epoch": 0.8704085613956859, + "grad_norm": 0.5796871781349182, + "learning_rate": 4.239333456951511e-06, + "loss": 1.7026, + "step": 15616 + }, + { + "epoch": 0.870464299648849, + "grad_norm": 0.5609190464019775, + "learning_rate": 4.235746045390276e-06, + "loss": 1.673, + "step": 15617 + }, + { + "epoch": 0.8705200379020122, + "grad_norm": 0.5441182255744934, + "learning_rate": 4.232160085204362e-06, + "loss": 1.4717, + "step": 15618 + }, + { + "epoch": 0.8705757761551753, + "grad_norm": 0.5815683007240295, + "learning_rate": 4.228575576507471e-06, + "loss": 1.5752, + "step": 15619 + }, + { + "epoch": 0.8706315144083384, + "grad_norm": 0.5537039041519165, + "learning_rate": 4.224992519413307e-06, + "loss": 1.8164, + "step": 15620 + }, + { + "epoch": 0.8706872526615016, + "grad_norm": 0.5365816354751587, + "learning_rate": 4.221410914035489e-06, + "loss": 1.6512, + "step": 15621 + }, + { + "epoch": 0.8707429909146648, + "grad_norm": 0.6044591665267944, + "learning_rate": 4.217830760487607e-06, + "loss": 1.8409, + "step": 15622 + }, + { + "epoch": 0.8707987291678279, + "grad_norm": 0.5398228764533997, + "learning_rate": 4.2142520588832055e-06, + "loss": 1.4412, + "step": 15623 + }, + { + "epoch": 0.870854467420991, + "grad_norm": 0.6193695068359375, + "learning_rate": 4.210674809335785e-06, + "loss": 1.7831, + "step": 15624 + }, + { + "epoch": 0.8709102056741542, + "grad_norm": 0.5912129282951355, + "learning_rate": 4.207099011958793e-06, + "loss": 1.8052, + "step": 15625 + }, + { + "epoch": 0.8709659439273173, + "grad_norm": 0.5548464059829712, + "learning_rate": 4.20352466686561e-06, + "loss": 1.6564, + "step": 15626 + }, + { + "epoch": 0.8710216821804805, + "grad_norm": 0.5471537113189697, + "learning_rate": 4.19995177416963e-06, + "loss": 1.4838, + "step": 15627 + }, + { + "epoch": 0.8710774204336436, + "grad_norm": 0.573521614074707, + "learning_rate": 4.19638033398414e-06, + "loss": 1.7513, + "step": 15628 + }, + { + "epoch": 0.8711331586868067, + "grad_norm": 0.5943538546562195, + "learning_rate": 4.192810346422415e-06, + "loss": 1.6848, + "step": 15629 + }, + { + "epoch": 0.8711888969399699, + "grad_norm": 0.6194045543670654, + "learning_rate": 4.189241811597666e-06, + "loss": 1.7092, + "step": 15630 + }, + { + "epoch": 0.871244635193133, + "grad_norm": 0.5906783938407898, + "learning_rate": 4.185674729623074e-06, + "loss": 1.7318, + "step": 15631 + }, + { + "epoch": 0.8713003734462962, + "grad_norm": 0.5606653094291687, + "learning_rate": 4.182109100611775e-06, + "loss": 1.6107, + "step": 15632 + }, + { + "epoch": 0.8713561116994594, + "grad_norm": 0.6594774127006531, + "learning_rate": 4.178544924676825e-06, + "loss": 1.6532, + "step": 15633 + }, + { + "epoch": 0.8714118499526224, + "grad_norm": 0.5248673558235168, + "learning_rate": 4.174982201931271e-06, + "loss": 1.2978, + "step": 15634 + }, + { + "epoch": 0.8714675882057856, + "grad_norm": 0.5331790447235107, + "learning_rate": 4.171420932488107e-06, + "loss": 1.4143, + "step": 15635 + }, + { + "epoch": 0.8715233264589488, + "grad_norm": 0.5229520201683044, + "learning_rate": 4.1678611164602755e-06, + "loss": 1.515, + "step": 15636 + }, + { + "epoch": 0.8715790647121119, + "grad_norm": 0.5970715880393982, + "learning_rate": 4.1643027539606635e-06, + "loss": 1.7191, + "step": 15637 + }, + { + "epoch": 0.8716348029652751, + "grad_norm": 0.5556305646896362, + "learning_rate": 4.160745845102127e-06, + "loss": 1.5287, + "step": 15638 + }, + { + "epoch": 0.8716905412184383, + "grad_norm": 0.5826808214187622, + "learning_rate": 4.157190389997484e-06, + "loss": 1.6858, + "step": 15639 + }, + { + "epoch": 0.8717462794716013, + "grad_norm": 0.6512157917022705, + "learning_rate": 4.153636388759469e-06, + "loss": 1.8478, + "step": 15640 + }, + { + "epoch": 0.8718020177247645, + "grad_norm": 0.5063778162002563, + "learning_rate": 4.150083841500807e-06, + "loss": 1.3555, + "step": 15641 + }, + { + "epoch": 0.8718577559779277, + "grad_norm": 0.5749867558479309, + "learning_rate": 4.1465327483341585e-06, + "loss": 1.7335, + "step": 15642 + }, + { + "epoch": 0.8719134942310908, + "grad_norm": 0.5315744280815125, + "learning_rate": 4.142983109372145e-06, + "loss": 1.4399, + "step": 15643 + }, + { + "epoch": 0.871969232484254, + "grad_norm": 0.5689708590507507, + "learning_rate": 4.139434924727359e-06, + "loss": 1.5743, + "step": 15644 + }, + { + "epoch": 0.8720249707374171, + "grad_norm": 0.6701650023460388, + "learning_rate": 4.135888194512289e-06, + "loss": 1.9219, + "step": 15645 + }, + { + "epoch": 0.8720807089905802, + "grad_norm": 0.5429824590682983, + "learning_rate": 4.132342918839455e-06, + "loss": 1.5456, + "step": 15646 + }, + { + "epoch": 0.8721364472437434, + "grad_norm": 0.5863592624664307, + "learning_rate": 4.128799097821268e-06, + "loss": 1.5484, + "step": 15647 + }, + { + "epoch": 0.8721921854969066, + "grad_norm": 0.581322431564331, + "learning_rate": 4.125256731570132e-06, + "loss": 1.6531, + "step": 15648 + }, + { + "epoch": 0.8722479237500697, + "grad_norm": 0.518942654132843, + "learning_rate": 4.121715820198379e-06, + "loss": 1.3986, + "step": 15649 + }, + { + "epoch": 0.8723036620032328, + "grad_norm": 0.5346654057502747, + "learning_rate": 4.11817636381831e-06, + "loss": 1.4709, + "step": 15650 + }, + { + "epoch": 0.8723594002563959, + "grad_norm": 0.5923715233802795, + "learning_rate": 4.114638362542189e-06, + "loss": 1.6281, + "step": 15651 + }, + { + "epoch": 0.8724151385095591, + "grad_norm": 0.5403051376342773, + "learning_rate": 4.111101816482193e-06, + "loss": 1.5158, + "step": 15652 + }, + { + "epoch": 0.8724708767627223, + "grad_norm": 0.5560429692268372, + "learning_rate": 4.107566725750512e-06, + "loss": 1.598, + "step": 15653 + }, + { + "epoch": 0.8725266150158854, + "grad_norm": 0.5674578547477722, + "learning_rate": 4.10403309045923e-06, + "loss": 1.5373, + "step": 15654 + }, + { + "epoch": 0.8725823532690485, + "grad_norm": 0.5468437671661377, + "learning_rate": 4.100500910720434e-06, + "loss": 1.5468, + "step": 15655 + }, + { + "epoch": 0.8726380915222117, + "grad_norm": 0.6030481457710266, + "learning_rate": 4.096970186646132e-06, + "loss": 1.742, + "step": 15656 + }, + { + "epoch": 0.8726938297753748, + "grad_norm": 0.6235069036483765, + "learning_rate": 4.093440918348302e-06, + "loss": 1.5131, + "step": 15657 + }, + { + "epoch": 0.872749568028538, + "grad_norm": 0.5454466938972473, + "learning_rate": 4.089913105938881e-06, + "loss": 1.345, + "step": 15658 + }, + { + "epoch": 0.8728053062817012, + "grad_norm": 0.5781631469726562, + "learning_rate": 4.086386749529736e-06, + "loss": 1.6515, + "step": 15659 + }, + { + "epoch": 0.8728610445348642, + "grad_norm": 0.5574864149093628, + "learning_rate": 4.082861849232706e-06, + "loss": 1.668, + "step": 15660 + }, + { + "epoch": 0.8729167827880274, + "grad_norm": 0.5793167352676392, + "learning_rate": 4.079338405159583e-06, + "loss": 1.6234, + "step": 15661 + }, + { + "epoch": 0.8729725210411906, + "grad_norm": 0.5928291082382202, + "learning_rate": 4.075816417422113e-06, + "loss": 1.6388, + "step": 15662 + }, + { + "epoch": 0.8730282592943537, + "grad_norm": 0.5603934526443481, + "learning_rate": 4.072295886131983e-06, + "loss": 1.5423, + "step": 15663 + }, + { + "epoch": 0.8730839975475169, + "grad_norm": 0.5271645188331604, + "learning_rate": 4.068776811400854e-06, + "loss": 1.4875, + "step": 15664 + }, + { + "epoch": 0.87313973580068, + "grad_norm": 0.5508955717086792, + "learning_rate": 4.065259193340337e-06, + "loss": 1.5053, + "step": 15665 + }, + { + "epoch": 0.8731954740538431, + "grad_norm": 0.5733965039253235, + "learning_rate": 4.061743032061971e-06, + "loss": 1.7788, + "step": 15666 + }, + { + "epoch": 0.8732512123070063, + "grad_norm": 0.5469422936439514, + "learning_rate": 4.058228327677277e-06, + "loss": 1.4898, + "step": 15667 + }, + { + "epoch": 0.8733069505601695, + "grad_norm": 0.6071850657463074, + "learning_rate": 4.054715080297722e-06, + "loss": 1.5606, + "step": 15668 + }, + { + "epoch": 0.8733626888133326, + "grad_norm": 0.5945049524307251, + "learning_rate": 4.051203290034722e-06, + "loss": 1.8127, + "step": 15669 + }, + { + "epoch": 0.8734184270664958, + "grad_norm": 0.5678067207336426, + "learning_rate": 4.047692956999665e-06, + "loss": 1.6833, + "step": 15670 + }, + { + "epoch": 0.8734741653196589, + "grad_norm": 0.5792582631111145, + "learning_rate": 4.044184081303848e-06, + "loss": 1.6853, + "step": 15671 + }, + { + "epoch": 0.873529903572822, + "grad_norm": 0.5871610045433044, + "learning_rate": 4.04067666305859e-06, + "loss": 1.7173, + "step": 15672 + }, + { + "epoch": 0.8735856418259852, + "grad_norm": 0.5663048624992371, + "learning_rate": 4.037170702375098e-06, + "loss": 1.6507, + "step": 15673 + }, + { + "epoch": 0.8736413800791483, + "grad_norm": 0.5291358828544617, + "learning_rate": 4.033666199364572e-06, + "loss": 1.4363, + "step": 15674 + }, + { + "epoch": 0.8736971183323115, + "grad_norm": 0.5455508232116699, + "learning_rate": 4.030163154138144e-06, + "loss": 1.6504, + "step": 15675 + }, + { + "epoch": 0.8737528565854746, + "grad_norm": 0.5902119874954224, + "learning_rate": 4.026661566806927e-06, + "loss": 1.5737, + "step": 15676 + }, + { + "epoch": 0.8738085948386377, + "grad_norm": 0.5301883220672607, + "learning_rate": 4.023161437481965e-06, + "loss": 1.438, + "step": 15677 + }, + { + "epoch": 0.8738643330918009, + "grad_norm": 0.5470799803733826, + "learning_rate": 4.01966276627424e-06, + "loss": 1.5465, + "step": 15678 + }, + { + "epoch": 0.8739200713449641, + "grad_norm": 0.5275294184684753, + "learning_rate": 4.0161655532947485e-06, + "loss": 1.5558, + "step": 15679 + }, + { + "epoch": 0.8739758095981272, + "grad_norm": 0.524453341960907, + "learning_rate": 4.012669798654372e-06, + "loss": 1.3105, + "step": 15680 + }, + { + "epoch": 0.8740315478512903, + "grad_norm": 0.5739786028862, + "learning_rate": 4.009175502463985e-06, + "loss": 1.6766, + "step": 15681 + }, + { + "epoch": 0.8740872861044535, + "grad_norm": 0.5472451448440552, + "learning_rate": 4.005682664834409e-06, + "loss": 1.6375, + "step": 15682 + }, + { + "epoch": 0.8741430243576166, + "grad_norm": 0.5441928505897522, + "learning_rate": 4.002191285876411e-06, + "loss": 1.5017, + "step": 15683 + }, + { + "epoch": 0.8741987626107798, + "grad_norm": 0.5375933051109314, + "learning_rate": 3.998701365700724e-06, + "loss": 1.6714, + "step": 15684 + }, + { + "epoch": 0.874254500863943, + "grad_norm": 0.5806841254234314, + "learning_rate": 3.995212904418022e-06, + "loss": 1.6666, + "step": 15685 + }, + { + "epoch": 0.874310239117106, + "grad_norm": 0.6031893491744995, + "learning_rate": 3.991725902138932e-06, + "loss": 1.6705, + "step": 15686 + }, + { + "epoch": 0.8743659773702692, + "grad_norm": 0.5578137040138245, + "learning_rate": 3.988240358974054e-06, + "loss": 1.5875, + "step": 15687 + }, + { + "epoch": 0.8744217156234324, + "grad_norm": 0.5403085947036743, + "learning_rate": 3.98475627503393e-06, + "loss": 1.4768, + "step": 15688 + }, + { + "epoch": 0.8744774538765955, + "grad_norm": 0.5489023923873901, + "learning_rate": 3.98127365042904e-06, + "loss": 1.6493, + "step": 15689 + }, + { + "epoch": 0.8745331921297587, + "grad_norm": 0.5725310444831848, + "learning_rate": 3.977792485269849e-06, + "loss": 1.7767, + "step": 15690 + }, + { + "epoch": 0.8745889303829218, + "grad_norm": 0.6043734550476074, + "learning_rate": 3.974312779666756e-06, + "loss": 1.8401, + "step": 15691 + }, + { + "epoch": 0.8746446686360849, + "grad_norm": 0.5540077686309814, + "learning_rate": 3.970834533730106e-06, + "loss": 1.7548, + "step": 15692 + }, + { + "epoch": 0.8747004068892481, + "grad_norm": 0.5910173058509827, + "learning_rate": 3.967357747570216e-06, + "loss": 1.7338, + "step": 15693 + }, + { + "epoch": 0.8747561451424113, + "grad_norm": 0.5365675091743469, + "learning_rate": 3.963882421297354e-06, + "loss": 1.5358, + "step": 15694 + }, + { + "epoch": 0.8748118833955744, + "grad_norm": 0.582892656326294, + "learning_rate": 3.960408555021727e-06, + "loss": 1.6326, + "step": 15695 + }, + { + "epoch": 0.8748676216487375, + "grad_norm": 0.5828142762184143, + "learning_rate": 3.956936148853518e-06, + "loss": 1.6002, + "step": 15696 + }, + { + "epoch": 0.8749233599019006, + "grad_norm": 0.5471785664558411, + "learning_rate": 3.953465202902834e-06, + "loss": 1.4552, + "step": 15697 + }, + { + "epoch": 0.8749790981550638, + "grad_norm": 0.5770442485809326, + "learning_rate": 3.949995717279775e-06, + "loss": 1.7802, + "step": 15698 + }, + { + "epoch": 0.875034836408227, + "grad_norm": 0.5750591158866882, + "learning_rate": 3.94652769209436e-06, + "loss": 1.7097, + "step": 15699 + }, + { + "epoch": 0.8750905746613901, + "grad_norm": 0.6036392450332642, + "learning_rate": 3.943061127456571e-06, + "loss": 1.7576, + "step": 15700 + }, + { + "epoch": 0.8751463129145532, + "grad_norm": 0.5749990940093994, + "learning_rate": 3.939596023476355e-06, + "loss": 1.6516, + "step": 15701 + }, + { + "epoch": 0.8752020511677164, + "grad_norm": 0.5418144464492798, + "learning_rate": 3.936132380263596e-06, + "loss": 1.7933, + "step": 15702 + }, + { + "epoch": 0.8752577894208795, + "grad_norm": 0.5709229707717896, + "learning_rate": 3.9326701979281624e-06, + "loss": 1.6893, + "step": 15703 + }, + { + "epoch": 0.8753135276740427, + "grad_norm": 0.5903497934341431, + "learning_rate": 3.929209476579821e-06, + "loss": 1.6717, + "step": 15704 + }, + { + "epoch": 0.8753692659272059, + "grad_norm": 0.5490012764930725, + "learning_rate": 3.925750216328361e-06, + "loss": 1.5763, + "step": 15705 + }, + { + "epoch": 0.875425004180369, + "grad_norm": 0.5839686989784241, + "learning_rate": 3.922292417283463e-06, + "loss": 1.7637, + "step": 15706 + }, + { + "epoch": 0.8754807424335321, + "grad_norm": 0.5329456329345703, + "learning_rate": 3.918836079554794e-06, + "loss": 1.4888, + "step": 15707 + }, + { + "epoch": 0.8755364806866953, + "grad_norm": 0.5600573420524597, + "learning_rate": 3.915381203251977e-06, + "loss": 1.4943, + "step": 15708 + }, + { + "epoch": 0.8755922189398584, + "grad_norm": 0.57575923204422, + "learning_rate": 3.911927788484576e-06, + "loss": 1.709, + "step": 15709 + }, + { + "epoch": 0.8756479571930216, + "grad_norm": 0.562798023223877, + "learning_rate": 3.908475835362124e-06, + "loss": 1.6748, + "step": 15710 + }, + { + "epoch": 0.8757036954461848, + "grad_norm": 0.5573869347572327, + "learning_rate": 3.905025343994073e-06, + "loss": 1.6158, + "step": 15711 + }, + { + "epoch": 0.8757594336993478, + "grad_norm": 0.5720036029815674, + "learning_rate": 3.901576314489869e-06, + "loss": 1.6543, + "step": 15712 + }, + { + "epoch": 0.875815171952511, + "grad_norm": 0.5650816559791565, + "learning_rate": 3.89812874695889e-06, + "loss": 1.617, + "step": 15713 + }, + { + "epoch": 0.8758709102056742, + "grad_norm": 0.5559343695640564, + "learning_rate": 3.894682641510477e-06, + "loss": 1.5324, + "step": 15714 + }, + { + "epoch": 0.8759266484588373, + "grad_norm": 0.5646649599075317, + "learning_rate": 3.891237998253916e-06, + "loss": 1.6526, + "step": 15715 + }, + { + "epoch": 0.8759823867120005, + "grad_norm": 0.5795676708221436, + "learning_rate": 3.887794817298452e-06, + "loss": 1.5923, + "step": 15716 + }, + { + "epoch": 0.8760381249651636, + "grad_norm": 0.5817763209342957, + "learning_rate": 3.884353098753296e-06, + "loss": 1.6028, + "step": 15717 + }, + { + "epoch": 0.8760938632183267, + "grad_norm": 0.5391849279403687, + "learning_rate": 3.880912842727574e-06, + "loss": 1.6405, + "step": 15718 + }, + { + "epoch": 0.8761496014714899, + "grad_norm": 0.5393145680427551, + "learning_rate": 3.877474049330404e-06, + "loss": 1.5182, + "step": 15719 + }, + { + "epoch": 0.876205339724653, + "grad_norm": 0.6242254972457886, + "learning_rate": 3.8740367186708485e-06, + "loss": 1.4649, + "step": 15720 + }, + { + "epoch": 0.8762610779778162, + "grad_norm": 0.5560100674629211, + "learning_rate": 3.870600850857914e-06, + "loss": 1.5252, + "step": 15721 + }, + { + "epoch": 0.8763168162309793, + "grad_norm": 0.637604296207428, + "learning_rate": 3.86716644600057e-06, + "loss": 1.7815, + "step": 15722 + }, + { + "epoch": 0.8763725544841424, + "grad_norm": 0.5911380648612976, + "learning_rate": 3.8637335042077225e-06, + "loss": 1.6557, + "step": 15723 + }, + { + "epoch": 0.8764282927373056, + "grad_norm": 0.5707426071166992, + "learning_rate": 3.86030202558827e-06, + "loss": 1.7001, + "step": 15724 + }, + { + "epoch": 0.8764840309904688, + "grad_norm": 0.6083332896232605, + "learning_rate": 3.856872010251017e-06, + "loss": 1.7792, + "step": 15725 + }, + { + "epoch": 0.8765397692436319, + "grad_norm": 0.5518040657043457, + "learning_rate": 3.853443458304751e-06, + "loss": 1.6699, + "step": 15726 + }, + { + "epoch": 0.876595507496795, + "grad_norm": 0.5586187839508057, + "learning_rate": 3.8500163698582e-06, + "loss": 1.5898, + "step": 15727 + }, + { + "epoch": 0.8766512457499582, + "grad_norm": 0.5967614650726318, + "learning_rate": 3.846590745020062e-06, + "loss": 1.5957, + "step": 15728 + }, + { + "epoch": 0.8767069840031213, + "grad_norm": 0.5749884843826294, + "learning_rate": 3.843166583898983e-06, + "loss": 1.6312, + "step": 15729 + }, + { + "epoch": 0.8767627222562845, + "grad_norm": 0.590756893157959, + "learning_rate": 3.839743886603525e-06, + "loss": 1.7032, + "step": 15730 + }, + { + "epoch": 0.8768184605094477, + "grad_norm": 0.6230370998382568, + "learning_rate": 3.836322653242275e-06, + "loss": 1.8931, + "step": 15731 + }, + { + "epoch": 0.8768741987626107, + "grad_norm": 0.5485255122184753, + "learning_rate": 3.832902883923711e-06, + "loss": 1.4354, + "step": 15732 + }, + { + "epoch": 0.8769299370157739, + "grad_norm": 0.5545439720153809, + "learning_rate": 3.829484578756298e-06, + "loss": 1.5042, + "step": 15733 + }, + { + "epoch": 0.8769856752689371, + "grad_norm": 0.5984395742416382, + "learning_rate": 3.826067737848438e-06, + "loss": 1.4766, + "step": 15734 + }, + { + "epoch": 0.8770414135221002, + "grad_norm": 0.5562477707862854, + "learning_rate": 3.822652361308493e-06, + "loss": 1.568, + "step": 15735 + }, + { + "epoch": 0.8770971517752634, + "grad_norm": 0.56642085313797, + "learning_rate": 3.819238449244794e-06, + "loss": 1.7266, + "step": 15736 + }, + { + "epoch": 0.8771528900284266, + "grad_norm": 0.5441727638244629, + "learning_rate": 3.815826001765593e-06, + "loss": 1.6284, + "step": 15737 + }, + { + "epoch": 0.8772086282815896, + "grad_norm": 0.5654782056808472, + "learning_rate": 3.812415018979115e-06, + "loss": 1.5299, + "step": 15738 + }, + { + "epoch": 0.8772643665347528, + "grad_norm": 0.5549350380897522, + "learning_rate": 3.8090055009935454e-06, + "loss": 1.6306, + "step": 15739 + }, + { + "epoch": 0.877320104787916, + "grad_norm": 0.8221239447593689, + "learning_rate": 3.805597447917003e-06, + "loss": 1.4984, + "step": 15740 + }, + { + "epoch": 0.8773758430410791, + "grad_norm": 0.5463032722473145, + "learning_rate": 3.8021908598575795e-06, + "loss": 1.5862, + "step": 15741 + }, + { + "epoch": 0.8774315812942423, + "grad_norm": 0.5700477957725525, + "learning_rate": 3.7987857369233103e-06, + "loss": 1.7315, + "step": 15742 + }, + { + "epoch": 0.8774873195474053, + "grad_norm": 0.5568161606788635, + "learning_rate": 3.7953820792221984e-06, + "loss": 1.6165, + "step": 15743 + }, + { + "epoch": 0.8775430578005685, + "grad_norm": 0.5700830221176147, + "learning_rate": 3.7919798868621626e-06, + "loss": 1.4986, + "step": 15744 + }, + { + "epoch": 0.8775987960537317, + "grad_norm": 0.5636020302772522, + "learning_rate": 3.788579159951111e-06, + "loss": 1.6291, + "step": 15745 + }, + { + "epoch": 0.8776545343068948, + "grad_norm": 0.5664473176002502, + "learning_rate": 3.7851798985969023e-06, + "loss": 1.5745, + "step": 15746 + }, + { + "epoch": 0.877710272560058, + "grad_norm": 0.6242087483406067, + "learning_rate": 3.781782102907333e-06, + "loss": 1.6791, + "step": 15747 + }, + { + "epoch": 0.8777660108132211, + "grad_norm": 0.5981343388557434, + "learning_rate": 3.778385772990173e-06, + "loss": 1.666, + "step": 15748 + }, + { + "epoch": 0.8778217490663842, + "grad_norm": 0.5430866479873657, + "learning_rate": 3.7749909089531076e-06, + "loss": 1.5475, + "step": 15749 + }, + { + "epoch": 0.8778774873195474, + "grad_norm": 0.5824033617973328, + "learning_rate": 3.7715975109038406e-06, + "loss": 1.8361, + "step": 15750 + }, + { + "epoch": 0.8779332255727106, + "grad_norm": 0.5778290033340454, + "learning_rate": 3.7682055789499626e-06, + "loss": 1.6891, + "step": 15751 + }, + { + "epoch": 0.8779889638258737, + "grad_norm": 0.5397013425827026, + "learning_rate": 3.7648151131990494e-06, + "loss": 1.5066, + "step": 15752 + }, + { + "epoch": 0.8780447020790368, + "grad_norm": 0.5605987906455994, + "learning_rate": 3.7614261137586314e-06, + "loss": 1.6471, + "step": 15753 + }, + { + "epoch": 0.8781004403322, + "grad_norm": 0.5682454705238342, + "learning_rate": 3.7580385807361894e-06, + "loss": 1.5962, + "step": 15754 + }, + { + "epoch": 0.8781561785853631, + "grad_norm": 0.5730165839195251, + "learning_rate": 3.7546525142391654e-06, + "loss": 1.5955, + "step": 15755 + }, + { + "epoch": 0.8782119168385263, + "grad_norm": 0.5778536796569824, + "learning_rate": 3.751267914374912e-06, + "loss": 1.6844, + "step": 15756 + }, + { + "epoch": 0.8782676550916895, + "grad_norm": 0.5479168891906738, + "learning_rate": 3.74788478125081e-06, + "loss": 1.4976, + "step": 15757 + }, + { + "epoch": 0.8783233933448525, + "grad_norm": 0.5362728238105774, + "learning_rate": 3.7445031149741294e-06, + "loss": 1.4495, + "step": 15758 + }, + { + "epoch": 0.8783791315980157, + "grad_norm": 0.5761111974716187, + "learning_rate": 3.741122915652118e-06, + "loss": 1.7237, + "step": 15759 + }, + { + "epoch": 0.8784348698511789, + "grad_norm": 0.5565175414085388, + "learning_rate": 3.737744183391978e-06, + "loss": 1.5868, + "step": 15760 + }, + { + "epoch": 0.878490608104342, + "grad_norm": 0.5846210718154907, + "learning_rate": 3.734366918300869e-06, + "loss": 1.6997, + "step": 15761 + }, + { + "epoch": 0.8785463463575052, + "grad_norm": 0.5782837271690369, + "learning_rate": 3.7309911204858995e-06, + "loss": 1.8069, + "step": 15762 + }, + { + "epoch": 0.8786020846106684, + "grad_norm": 0.616163432598114, + "learning_rate": 3.727616790054117e-06, + "loss": 1.7699, + "step": 15763 + }, + { + "epoch": 0.8786578228638314, + "grad_norm": 0.549358069896698, + "learning_rate": 3.7242439271125474e-06, + "loss": 1.6868, + "step": 15764 + }, + { + "epoch": 0.8787135611169946, + "grad_norm": 0.5625343322753906, + "learning_rate": 3.720872531768149e-06, + "loss": 1.6907, + "step": 15765 + }, + { + "epoch": 0.8787692993701577, + "grad_norm": 0.5563330054283142, + "learning_rate": 3.7175026041278483e-06, + "loss": 1.7177, + "step": 15766 + }, + { + "epoch": 0.8788250376233209, + "grad_norm": 0.585578203201294, + "learning_rate": 3.71413414429852e-06, + "loss": 1.6994, + "step": 15767 + }, + { + "epoch": 0.878880775876484, + "grad_norm": 0.5387508273124695, + "learning_rate": 3.7107671523869903e-06, + "loss": 1.5811, + "step": 15768 + }, + { + "epoch": 0.8789365141296471, + "grad_norm": 0.5487370491027832, + "learning_rate": 3.7074016285000512e-06, + "loss": 1.6197, + "step": 15769 + }, + { + "epoch": 0.8789922523828103, + "grad_norm": 0.5552342534065247, + "learning_rate": 3.7040375727444233e-06, + "loss": 1.657, + "step": 15770 + }, + { + "epoch": 0.8790479906359735, + "grad_norm": 0.6588811278343201, + "learning_rate": 3.700674985226793e-06, + "loss": 1.8687, + "step": 15771 + }, + { + "epoch": 0.8791037288891366, + "grad_norm": 0.5783315300941467, + "learning_rate": 3.6973138660538144e-06, + "loss": 1.6434, + "step": 15772 + }, + { + "epoch": 0.8791594671422998, + "grad_norm": 0.5899311304092407, + "learning_rate": 3.693954215332074e-06, + "loss": 1.6503, + "step": 15773 + }, + { + "epoch": 0.8792152053954629, + "grad_norm": 0.5716587901115417, + "learning_rate": 3.6905960331681256e-06, + "loss": 1.8172, + "step": 15774 + }, + { + "epoch": 0.879270943648626, + "grad_norm": 0.5669835805892944, + "learning_rate": 3.687239319668462e-06, + "loss": 1.7368, + "step": 15775 + }, + { + "epoch": 0.8793266819017892, + "grad_norm": 0.544732391834259, + "learning_rate": 3.683884074939553e-06, + "loss": 1.5331, + "step": 15776 + }, + { + "epoch": 0.8793824201549524, + "grad_norm": 0.5805574059486389, + "learning_rate": 3.6805302990877976e-06, + "loss": 1.6661, + "step": 15777 + }, + { + "epoch": 0.8794381584081155, + "grad_norm": 0.5763493776321411, + "learning_rate": 3.6771779922195547e-06, + "loss": 1.608, + "step": 15778 + }, + { + "epoch": 0.8794938966612786, + "grad_norm": 0.6213945150375366, + "learning_rate": 3.6738271544411453e-06, + "loss": 1.9745, + "step": 15779 + }, + { + "epoch": 0.8795496349144418, + "grad_norm": 0.5570361018180847, + "learning_rate": 3.6704777858588444e-06, + "loss": 1.6281, + "step": 15780 + }, + { + "epoch": 0.8796053731676049, + "grad_norm": 0.5684201717376709, + "learning_rate": 3.6671298865788685e-06, + "loss": 1.6116, + "step": 15781 + }, + { + "epoch": 0.8796611114207681, + "grad_norm": 0.6011030077934265, + "learning_rate": 3.6637834567073815e-06, + "loss": 1.7403, + "step": 15782 + }, + { + "epoch": 0.8797168496739313, + "grad_norm": 0.5654848217964172, + "learning_rate": 3.6604384963505433e-06, + "loss": 1.617, + "step": 15783 + }, + { + "epoch": 0.8797725879270943, + "grad_norm": 0.6074404716491699, + "learning_rate": 3.6570950056144026e-06, + "loss": 1.5354, + "step": 15784 + }, + { + "epoch": 0.8798283261802575, + "grad_norm": 0.5351618528366089, + "learning_rate": 3.6537529846050134e-06, + "loss": 1.5775, + "step": 15785 + }, + { + "epoch": 0.8798840644334207, + "grad_norm": 0.583764910697937, + "learning_rate": 3.650412433428363e-06, + "loss": 1.7492, + "step": 15786 + }, + { + "epoch": 0.8799398026865838, + "grad_norm": 0.5557485818862915, + "learning_rate": 3.6470733521903945e-06, + "loss": 1.6341, + "step": 15787 + }, + { + "epoch": 0.879995540939747, + "grad_norm": 0.5981559157371521, + "learning_rate": 3.643735740997012e-06, + "loss": 1.7935, + "step": 15788 + }, + { + "epoch": 0.88005127919291, + "grad_norm": 0.6121543049812317, + "learning_rate": 3.640399599954042e-06, + "loss": 1.7948, + "step": 15789 + }, + { + "epoch": 0.8801070174460732, + "grad_norm": 0.5926955342292786, + "learning_rate": 3.6370649291673055e-06, + "loss": 1.7953, + "step": 15790 + }, + { + "epoch": 0.8801627556992364, + "grad_norm": 0.5853786468505859, + "learning_rate": 3.6337317287425565e-06, + "loss": 1.6587, + "step": 15791 + }, + { + "epoch": 0.8802184939523995, + "grad_norm": 0.5548514723777771, + "learning_rate": 3.6303999987854996e-06, + "loss": 1.6646, + "step": 15792 + }, + { + "epoch": 0.8802742322055627, + "grad_norm": 0.5534593462944031, + "learning_rate": 3.6270697394018007e-06, + "loss": 1.6545, + "step": 15793 + }, + { + "epoch": 0.8803299704587259, + "grad_norm": 0.5391322374343872, + "learning_rate": 3.62374095069708e-06, + "loss": 1.5467, + "step": 15794 + }, + { + "epoch": 0.8803857087118889, + "grad_norm": 0.5490776300430298, + "learning_rate": 3.6204136327769088e-06, + "loss": 1.641, + "step": 15795 + }, + { + "epoch": 0.8804414469650521, + "grad_norm": 0.6054949164390564, + "learning_rate": 3.6170877857467977e-06, + "loss": 1.7804, + "step": 15796 + }, + { + "epoch": 0.8804971852182153, + "grad_norm": 0.5534854531288147, + "learning_rate": 3.613763409712234e-06, + "loss": 1.7916, + "step": 15797 + }, + { + "epoch": 0.8805529234713784, + "grad_norm": 0.5776894092559814, + "learning_rate": 3.610440504778645e-06, + "loss": 1.6742, + "step": 15798 + }, + { + "epoch": 0.8806086617245416, + "grad_norm": 0.5657996535301208, + "learning_rate": 3.607119071051407e-06, + "loss": 1.7098, + "step": 15799 + }, + { + "epoch": 0.8806643999777047, + "grad_norm": 0.6018683314323425, + "learning_rate": 3.603799108635869e-06, + "loss": 1.4523, + "step": 15800 + }, + { + "epoch": 0.8807201382308678, + "grad_norm": 0.5693888068199158, + "learning_rate": 3.600480617637314e-06, + "loss": 1.655, + "step": 15801 + }, + { + "epoch": 0.880775876484031, + "grad_norm": 0.5557105541229248, + "learning_rate": 3.597163598160991e-06, + "loss": 1.4806, + "step": 15802 + }, + { + "epoch": 0.8808316147371942, + "grad_norm": 0.5904127359390259, + "learning_rate": 3.593848050312082e-06, + "loss": 1.7873, + "step": 15803 + }, + { + "epoch": 0.8808873529903573, + "grad_norm": 0.6123230457305908, + "learning_rate": 3.5905339741957535e-06, + "loss": 1.6772, + "step": 15804 + }, + { + "epoch": 0.8809430912435204, + "grad_norm": 0.5287997722625732, + "learning_rate": 3.5872213699170932e-06, + "loss": 1.3347, + "step": 15805 + }, + { + "epoch": 0.8809988294966836, + "grad_norm": 0.5872935652732849, + "learning_rate": 3.5839102375811674e-06, + "loss": 1.6325, + "step": 15806 + }, + { + "epoch": 0.8810545677498467, + "grad_norm": 0.6141674518585205, + "learning_rate": 3.5806005772929975e-06, + "loss": 1.7944, + "step": 15807 + }, + { + "epoch": 0.8811103060030099, + "grad_norm": 0.568565309047699, + "learning_rate": 3.5772923891575107e-06, + "loss": 1.6031, + "step": 15808 + }, + { + "epoch": 0.8811660442561731, + "grad_norm": 0.5713023543357849, + "learning_rate": 3.5739856732796674e-06, + "loss": 1.6244, + "step": 15809 + }, + { + "epoch": 0.8812217825093361, + "grad_norm": 0.6083016991615295, + "learning_rate": 3.570680429764306e-06, + "loss": 1.819, + "step": 15810 + }, + { + "epoch": 0.8812775207624993, + "grad_norm": 0.511864185333252, + "learning_rate": 3.5673766587162593e-06, + "loss": 1.4932, + "step": 15811 + }, + { + "epoch": 0.8813332590156624, + "grad_norm": 0.5721727609634399, + "learning_rate": 3.564074360240305e-06, + "loss": 1.5483, + "step": 15812 + }, + { + "epoch": 0.8813889972688256, + "grad_norm": 0.5577667355537415, + "learning_rate": 3.560773534441175e-06, + "loss": 1.4245, + "step": 15813 + }, + { + "epoch": 0.8814447355219888, + "grad_norm": 0.5569271445274353, + "learning_rate": 3.5574741814235534e-06, + "loss": 1.9034, + "step": 15814 + }, + { + "epoch": 0.8815004737751518, + "grad_norm": 0.5723382234573364, + "learning_rate": 3.5541763012920613e-06, + "loss": 1.5504, + "step": 15815 + }, + { + "epoch": 0.881556212028315, + "grad_norm": 0.5648158192634583, + "learning_rate": 3.5508798941513045e-06, + "loss": 1.5131, + "step": 15816 + }, + { + "epoch": 0.8816119502814782, + "grad_norm": 0.5506287217140198, + "learning_rate": 3.5475849601058154e-06, + "loss": 1.5225, + "step": 15817 + }, + { + "epoch": 0.8816676885346413, + "grad_norm": 0.565623939037323, + "learning_rate": 3.5442914992600995e-06, + "loss": 1.5951, + "step": 15818 + }, + { + "epoch": 0.8817234267878045, + "grad_norm": 0.5612080097198486, + "learning_rate": 3.5409995117185957e-06, + "loss": 1.6046, + "step": 15819 + }, + { + "epoch": 0.8817791650409676, + "grad_norm": 0.5668306946754456, + "learning_rate": 3.5377089975857148e-06, + "loss": 1.6479, + "step": 15820 + }, + { + "epoch": 0.8818349032941307, + "grad_norm": 0.5489674806594849, + "learning_rate": 3.5344199569658233e-06, + "loss": 1.467, + "step": 15821 + }, + { + "epoch": 0.8818906415472939, + "grad_norm": 0.5955537557601929, + "learning_rate": 3.5311323899632044e-06, + "loss": 1.7529, + "step": 15822 + }, + { + "epoch": 0.8819463798004571, + "grad_norm": 0.5681952834129333, + "learning_rate": 3.5278462966821357e-06, + "loss": 1.5552, + "step": 15823 + }, + { + "epoch": 0.8820021180536202, + "grad_norm": 0.5572336912155151, + "learning_rate": 3.524561677226834e-06, + "loss": 1.4434, + "step": 15824 + }, + { + "epoch": 0.8820578563067833, + "grad_norm": 0.5786949992179871, + "learning_rate": 3.521278531701461e-06, + "loss": 1.4434, + "step": 15825 + }, + { + "epoch": 0.8821135945599465, + "grad_norm": 0.5569239854812622, + "learning_rate": 3.517996860210143e-06, + "loss": 1.489, + "step": 15826 + }, + { + "epoch": 0.8821693328131096, + "grad_norm": 0.5697907209396362, + "learning_rate": 3.5147166628569594e-06, + "loss": 1.5887, + "step": 15827 + }, + { + "epoch": 0.8822250710662728, + "grad_norm": 0.5942627191543579, + "learning_rate": 3.511437939745943e-06, + "loss": 1.7832, + "step": 15828 + }, + { + "epoch": 0.882280809319436, + "grad_norm": 0.5396826267242432, + "learning_rate": 3.508160690981055e-06, + "loss": 1.5757, + "step": 15829 + }, + { + "epoch": 0.882336547572599, + "grad_norm": 0.5690128803253174, + "learning_rate": 3.5048849166662456e-06, + "loss": 1.5776, + "step": 15830 + }, + { + "epoch": 0.8823922858257622, + "grad_norm": 0.5711696147918701, + "learning_rate": 3.501610616905404e-06, + "loss": 1.582, + "step": 15831 + }, + { + "epoch": 0.8824480240789254, + "grad_norm": 0.6206567287445068, + "learning_rate": 3.4983377918023698e-06, + "loss": 1.6043, + "step": 15832 + }, + { + "epoch": 0.8825037623320885, + "grad_norm": 0.5381189584732056, + "learning_rate": 3.4950664414609425e-06, + "loss": 1.6977, + "step": 15833 + }, + { + "epoch": 0.8825595005852517, + "grad_norm": 0.5752723813056946, + "learning_rate": 3.4917965659848506e-06, + "loss": 1.5686, + "step": 15834 + }, + { + "epoch": 0.8826152388384148, + "grad_norm": 0.5566213726997375, + "learning_rate": 3.4885281654778224e-06, + "loss": 1.4928, + "step": 15835 + }, + { + "epoch": 0.8826709770915779, + "grad_norm": 0.6104714274406433, + "learning_rate": 3.485261240043497e-06, + "loss": 1.8674, + "step": 15836 + }, + { + "epoch": 0.8827267153447411, + "grad_norm": 0.5847084522247314, + "learning_rate": 3.4819957897854805e-06, + "loss": 1.5629, + "step": 15837 + }, + { + "epoch": 0.8827824535979042, + "grad_norm": 0.5710684061050415, + "learning_rate": 3.4787318148073455e-06, + "loss": 1.7014, + "step": 15838 + }, + { + "epoch": 0.8828381918510674, + "grad_norm": 0.5992119312286377, + "learning_rate": 3.4754693152125928e-06, + "loss": 1.8721, + "step": 15839 + }, + { + "epoch": 0.8828939301042306, + "grad_norm": 0.5555844902992249, + "learning_rate": 3.4722082911047116e-06, + "loss": 1.72, + "step": 15840 + }, + { + "epoch": 0.8829496683573936, + "grad_norm": 0.5531332492828369, + "learning_rate": 3.4689487425870916e-06, + "loss": 1.5737, + "step": 15841 + }, + { + "epoch": 0.8830054066105568, + "grad_norm": 0.6133163571357727, + "learning_rate": 3.4656906697631276e-06, + "loss": 1.7312, + "step": 15842 + }, + { + "epoch": 0.88306114486372, + "grad_norm": 0.6038590669631958, + "learning_rate": 3.462434072736143e-06, + "loss": 1.7947, + "step": 15843 + }, + { + "epoch": 0.8831168831168831, + "grad_norm": 0.5830754041671753, + "learning_rate": 3.4591789516094095e-06, + "loss": 1.7457, + "step": 15844 + }, + { + "epoch": 0.8831726213700463, + "grad_norm": 0.5233110189437866, + "learning_rate": 3.455925306486174e-06, + "loss": 1.5253, + "step": 15845 + }, + { + "epoch": 0.8832283596232094, + "grad_norm": 0.5506311058998108, + "learning_rate": 3.452673137469614e-06, + "loss": 1.5557, + "step": 15846 + }, + { + "epoch": 0.8832840978763725, + "grad_norm": 0.5962168574333191, + "learning_rate": 3.4494224446628863e-06, + "loss": 1.8283, + "step": 15847 + }, + { + "epoch": 0.8833398361295357, + "grad_norm": 0.5320143699645996, + "learning_rate": 3.4461732281690585e-06, + "loss": 1.5048, + "step": 15848 + }, + { + "epoch": 0.8833955743826989, + "grad_norm": 0.5182924270629883, + "learning_rate": 3.4429254880911867e-06, + "loss": 1.3804, + "step": 15849 + }, + { + "epoch": 0.883451312635862, + "grad_norm": 0.5459631681442261, + "learning_rate": 3.4396792245322716e-06, + "loss": 1.5334, + "step": 15850 + }, + { + "epoch": 0.8835070508890251, + "grad_norm": 0.5541400909423828, + "learning_rate": 3.4364344375952652e-06, + "loss": 1.6218, + "step": 15851 + }, + { + "epoch": 0.8835627891421883, + "grad_norm": 0.5123451352119446, + "learning_rate": 3.4331911273830784e-06, + "loss": 1.4603, + "step": 15852 + }, + { + "epoch": 0.8836185273953514, + "grad_norm": 0.48906397819519043, + "learning_rate": 3.4299492939985633e-06, + "loss": 1.3335, + "step": 15853 + }, + { + "epoch": 0.8836742656485146, + "grad_norm": 0.5606974959373474, + "learning_rate": 3.4267089375445425e-06, + "loss": 1.5551, + "step": 15854 + }, + { + "epoch": 0.8837300039016778, + "grad_norm": 0.6333062052726746, + "learning_rate": 3.423470058123762e-06, + "loss": 1.9433, + "step": 15855 + }, + { + "epoch": 0.8837857421548408, + "grad_norm": 0.5507806539535522, + "learning_rate": 3.4202326558389563e-06, + "loss": 1.6007, + "step": 15856 + }, + { + "epoch": 0.883841480408004, + "grad_norm": 0.608963131904602, + "learning_rate": 3.4169967307927875e-06, + "loss": 1.7967, + "step": 15857 + }, + { + "epoch": 0.8838972186611671, + "grad_norm": 0.5400906801223755, + "learning_rate": 3.41376228308789e-06, + "loss": 1.607, + "step": 15858 + }, + { + "epoch": 0.8839529569143303, + "grad_norm": 0.5906161665916443, + "learning_rate": 3.410529312826838e-06, + "loss": 1.6588, + "step": 15859 + }, + { + "epoch": 0.8840086951674935, + "grad_norm": 0.5629030466079712, + "learning_rate": 3.4072978201121485e-06, + "loss": 1.8458, + "step": 15860 + }, + { + "epoch": 0.8840644334206565, + "grad_norm": 0.5807666778564453, + "learning_rate": 3.404067805046335e-06, + "loss": 1.7582, + "step": 15861 + }, + { + "epoch": 0.8841201716738197, + "grad_norm": 0.5578849911689758, + "learning_rate": 3.4008392677318034e-06, + "loss": 1.633, + "step": 15862 + }, + { + "epoch": 0.8841759099269829, + "grad_norm": 0.5812610387802124, + "learning_rate": 3.3976122082709672e-06, + "loss": 1.5867, + "step": 15863 + }, + { + "epoch": 0.884231648180146, + "grad_norm": 0.5540379285812378, + "learning_rate": 3.394386626766155e-06, + "loss": 1.5209, + "step": 15864 + }, + { + "epoch": 0.8842873864333092, + "grad_norm": 0.5712565779685974, + "learning_rate": 3.3911625233196685e-06, + "loss": 1.6386, + "step": 15865 + }, + { + "epoch": 0.8843431246864724, + "grad_norm": 0.5131077766418457, + "learning_rate": 3.3879398980337707e-06, + "loss": 1.5442, + "step": 15866 + }, + { + "epoch": 0.8843988629396354, + "grad_norm": 0.5460878014564514, + "learning_rate": 3.3847187510106403e-06, + "loss": 1.6252, + "step": 15867 + }, + { + "epoch": 0.8844546011927986, + "grad_norm": 0.5852480530738831, + "learning_rate": 3.381499082352446e-06, + "loss": 1.5251, + "step": 15868 + }, + { + "epoch": 0.8845103394459618, + "grad_norm": 0.5823503136634827, + "learning_rate": 3.3782808921613005e-06, + "loss": 1.6025, + "step": 15869 + }, + { + "epoch": 0.8845660776991249, + "grad_norm": 0.6018304824829102, + "learning_rate": 3.3750641805392557e-06, + "loss": 1.7369, + "step": 15870 + }, + { + "epoch": 0.8846218159522881, + "grad_norm": 0.5926112532615662, + "learning_rate": 3.3718489475883354e-06, + "loss": 1.7343, + "step": 15871 + }, + { + "epoch": 0.8846775542054512, + "grad_norm": 0.5472990870475769, + "learning_rate": 3.3686351934105076e-06, + "loss": 1.5965, + "step": 15872 + }, + { + "epoch": 0.8847332924586143, + "grad_norm": 0.5900512337684631, + "learning_rate": 3.3654229181076968e-06, + "loss": 1.677, + "step": 15873 + }, + { + "epoch": 0.8847890307117775, + "grad_norm": 0.5639572739601135, + "learning_rate": 3.362212121781766e-06, + "loss": 1.5953, + "step": 15874 + }, + { + "epoch": 0.8848447689649407, + "grad_norm": 0.5574104189872742, + "learning_rate": 3.35900280453455e-06, + "loss": 1.5175, + "step": 15875 + }, + { + "epoch": 0.8849005072181038, + "grad_norm": 0.5839914679527283, + "learning_rate": 3.355794966467829e-06, + "loss": 1.7415, + "step": 15876 + }, + { + "epoch": 0.884956245471267, + "grad_norm": 0.5679370164871216, + "learning_rate": 3.3525886076833326e-06, + "loss": 1.7925, + "step": 15877 + }, + { + "epoch": 0.8850119837244301, + "grad_norm": 0.6027814745903015, + "learning_rate": 3.349383728282757e-06, + "loss": 1.7262, + "step": 15878 + }, + { + "epoch": 0.8850677219775932, + "grad_norm": 0.5443357825279236, + "learning_rate": 3.3461803283677373e-06, + "loss": 1.5908, + "step": 15879 + }, + { + "epoch": 0.8851234602307564, + "grad_norm": 0.5994856357574463, + "learning_rate": 3.3429784080398762e-06, + "loss": 1.6122, + "step": 15880 + }, + { + "epoch": 0.8851791984839195, + "grad_norm": 0.5735911726951599, + "learning_rate": 3.339777967400698e-06, + "loss": 1.7489, + "step": 15881 + }, + { + "epoch": 0.8852349367370826, + "grad_norm": 0.5670081973075867, + "learning_rate": 3.3365790065517156e-06, + "loss": 1.5237, + "step": 15882 + }, + { + "epoch": 0.8852906749902458, + "grad_norm": 0.5890611410140991, + "learning_rate": 3.3333815255943867e-06, + "loss": 1.7946, + "step": 15883 + }, + { + "epoch": 0.8853464132434089, + "grad_norm": 0.5700726509094238, + "learning_rate": 3.3301855246301026e-06, + "loss": 1.7742, + "step": 15884 + }, + { + "epoch": 0.8854021514965721, + "grad_norm": 0.5722408890724182, + "learning_rate": 3.3269910037602436e-06, + "loss": 1.6423, + "step": 15885 + }, + { + "epoch": 0.8854578897497353, + "grad_norm": 0.5584518909454346, + "learning_rate": 3.3237979630860892e-06, + "loss": 1.5558, + "step": 15886 + }, + { + "epoch": 0.8855136280028983, + "grad_norm": 0.5754905343055725, + "learning_rate": 3.3206064027089367e-06, + "loss": 1.6937, + "step": 15887 + }, + { + "epoch": 0.8855693662560615, + "grad_norm": 0.5797026753425598, + "learning_rate": 3.3174163227299826e-06, + "loss": 1.776, + "step": 15888 + }, + { + "epoch": 0.8856251045092247, + "grad_norm": 0.5771031379699707, + "learning_rate": 3.314227723250407e-06, + "loss": 1.7548, + "step": 15889 + }, + { + "epoch": 0.8856808427623878, + "grad_norm": 0.5617585778236389, + "learning_rate": 3.3110406043713296e-06, + "loss": 1.8775, + "step": 15890 + }, + { + "epoch": 0.885736581015551, + "grad_norm": 0.578700840473175, + "learning_rate": 3.307854966193824e-06, + "loss": 1.7155, + "step": 15891 + }, + { + "epoch": 0.8857923192687142, + "grad_norm": 0.5871515870094299, + "learning_rate": 3.304670808818938e-06, + "loss": 1.6435, + "step": 15892 + }, + { + "epoch": 0.8858480575218772, + "grad_norm": 0.5839070081710815, + "learning_rate": 3.3014881323476242e-06, + "loss": 1.4476, + "step": 15893 + }, + { + "epoch": 0.8859037957750404, + "grad_norm": 0.6002477407455444, + "learning_rate": 3.2983069368808516e-06, + "loss": 1.8098, + "step": 15894 + }, + { + "epoch": 0.8859595340282036, + "grad_norm": 0.5426203608512878, + "learning_rate": 3.295127222519484e-06, + "loss": 1.4949, + "step": 15895 + }, + { + "epoch": 0.8860152722813667, + "grad_norm": 0.5917392373085022, + "learning_rate": 3.291948989364374e-06, + "loss": 1.5185, + "step": 15896 + }, + { + "epoch": 0.8860710105345299, + "grad_norm": 0.5681447386741638, + "learning_rate": 3.2887722375163133e-06, + "loss": 1.7169, + "step": 15897 + }, + { + "epoch": 0.886126748787693, + "grad_norm": 0.5620180368423462, + "learning_rate": 3.2855969670760543e-06, + "loss": 1.5604, + "step": 15898 + }, + { + "epoch": 0.8861824870408561, + "grad_norm": 0.5336468815803528, + "learning_rate": 3.282423178144306e-06, + "loss": 1.7701, + "step": 15899 + }, + { + "epoch": 0.8862382252940193, + "grad_norm": 0.5509390234947205, + "learning_rate": 3.2792508708216986e-06, + "loss": 1.6685, + "step": 15900 + }, + { + "epoch": 0.8862939635471825, + "grad_norm": 0.5617192387580872, + "learning_rate": 3.276080045208857e-06, + "loss": 1.6324, + "step": 15901 + }, + { + "epoch": 0.8863497018003456, + "grad_norm": 0.5366843342781067, + "learning_rate": 3.272910701406334e-06, + "loss": 1.5295, + "step": 15902 + }, + { + "epoch": 0.8864054400535087, + "grad_norm": 0.5649051666259766, + "learning_rate": 3.2697428395146444e-06, + "loss": 1.6449, + "step": 15903 + }, + { + "epoch": 0.8864611783066718, + "grad_norm": 0.5743849873542786, + "learning_rate": 3.2665764596342575e-06, + "loss": 1.6511, + "step": 15904 + }, + { + "epoch": 0.886516916559835, + "grad_norm": 0.6004202961921692, + "learning_rate": 3.2634115618655926e-06, + "loss": 1.4201, + "step": 15905 + }, + { + "epoch": 0.8865726548129982, + "grad_norm": 0.5800164937973022, + "learning_rate": 3.2602481463090252e-06, + "loss": 1.708, + "step": 15906 + }, + { + "epoch": 0.8866283930661613, + "grad_norm": 0.6020044088363647, + "learning_rate": 3.2570862130648696e-06, + "loss": 1.8314, + "step": 15907 + }, + { + "epoch": 0.8866841313193244, + "grad_norm": 0.5905942916870117, + "learning_rate": 3.2539257622334062e-06, + "loss": 1.7611, + "step": 15908 + }, + { + "epoch": 0.8867398695724876, + "grad_norm": 0.6396439671516418, + "learning_rate": 3.2507667939148722e-06, + "loss": 1.7406, + "step": 15909 + }, + { + "epoch": 0.8867956078256507, + "grad_norm": 0.5652817487716675, + "learning_rate": 3.247609308209443e-06, + "loss": 1.5265, + "step": 15910 + }, + { + "epoch": 0.8868513460788139, + "grad_norm": 0.5868328809738159, + "learning_rate": 3.2444533052172766e-06, + "loss": 1.661, + "step": 15911 + }, + { + "epoch": 0.8869070843319771, + "grad_norm": 0.5335938930511475, + "learning_rate": 3.241298785038427e-06, + "loss": 1.5103, + "step": 15912 + }, + { + "epoch": 0.8869628225851401, + "grad_norm": 0.576056718826294, + "learning_rate": 3.2381457477729747e-06, + "loss": 1.6671, + "step": 15913 + }, + { + "epoch": 0.8870185608383033, + "grad_norm": 0.5416059494018555, + "learning_rate": 3.2349941935208905e-06, + "loss": 1.7058, + "step": 15914 + }, + { + "epoch": 0.8870742990914665, + "grad_norm": 0.5886712074279785, + "learning_rate": 3.231844122382133e-06, + "loss": 1.7952, + "step": 15915 + }, + { + "epoch": 0.8871300373446296, + "grad_norm": 0.5932267308235168, + "learning_rate": 3.2286955344565993e-06, + "loss": 1.6081, + "step": 15916 + }, + { + "epoch": 0.8871857755977928, + "grad_norm": 0.5687417984008789, + "learning_rate": 3.2255484298441497e-06, + "loss": 1.7535, + "step": 15917 + }, + { + "epoch": 0.887241513850956, + "grad_norm": 0.5745554566383362, + "learning_rate": 3.222402808644598e-06, + "loss": 1.4049, + "step": 15918 + }, + { + "epoch": 0.887297252104119, + "grad_norm": 0.5646759271621704, + "learning_rate": 3.219258670957681e-06, + "loss": 1.4825, + "step": 15919 + }, + { + "epoch": 0.8873529903572822, + "grad_norm": 0.5413823127746582, + "learning_rate": 3.216116016883147e-06, + "loss": 1.4344, + "step": 15920 + }, + { + "epoch": 0.8874087286104454, + "grad_norm": 0.5760074257850647, + "learning_rate": 3.2129748465206335e-06, + "loss": 1.6976, + "step": 15921 + }, + { + "epoch": 0.8874644668636085, + "grad_norm": 0.6001960039138794, + "learning_rate": 3.209835159969771e-06, + "loss": 1.6668, + "step": 15922 + }, + { + "epoch": 0.8875202051167717, + "grad_norm": 0.6348347067832947, + "learning_rate": 3.20669695733013e-06, + "loss": 1.8659, + "step": 15923 + }, + { + "epoch": 0.8875759433699348, + "grad_norm": 0.5959821939468384, + "learning_rate": 3.2035602387012367e-06, + "loss": 1.7998, + "step": 15924 + }, + { + "epoch": 0.8876316816230979, + "grad_norm": 0.5767197012901306, + "learning_rate": 3.2004250041825834e-06, + "loss": 1.6054, + "step": 15925 + }, + { + "epoch": 0.8876874198762611, + "grad_norm": 0.5905073285102844, + "learning_rate": 3.1972912538735745e-06, + "loss": 1.6876, + "step": 15926 + }, + { + "epoch": 0.8877431581294242, + "grad_norm": 0.5631966590881348, + "learning_rate": 3.1941589878736135e-06, + "loss": 1.6825, + "step": 15927 + }, + { + "epoch": 0.8877988963825874, + "grad_norm": 0.5464244484901428, + "learning_rate": 3.191028206282032e-06, + "loss": 1.6847, + "step": 15928 + }, + { + "epoch": 0.8878546346357505, + "grad_norm": 0.5480577945709229, + "learning_rate": 3.187898909198117e-06, + "loss": 1.5833, + "step": 15929 + }, + { + "epoch": 0.8879103728889136, + "grad_norm": 0.5566979050636292, + "learning_rate": 3.1847710967211174e-06, + "loss": 1.5762, + "step": 15930 + }, + { + "epoch": 0.8879661111420768, + "grad_norm": 0.6020669937133789, + "learning_rate": 3.181644768950226e-06, + "loss": 1.6475, + "step": 15931 + }, + { + "epoch": 0.88802184939524, + "grad_norm": 0.5540771484375, + "learning_rate": 3.178519925984602e-06, + "loss": 1.6052, + "step": 15932 + }, + { + "epoch": 0.888077587648403, + "grad_norm": 0.5560112595558167, + "learning_rate": 3.175396567923328e-06, + "loss": 1.571, + "step": 15933 + }, + { + "epoch": 0.8881333259015662, + "grad_norm": 0.540611743927002, + "learning_rate": 3.172274694865468e-06, + "loss": 1.6819, + "step": 15934 + }, + { + "epoch": 0.8881890641547294, + "grad_norm": 0.5594174861907959, + "learning_rate": 3.169154306910033e-06, + "loss": 1.704, + "step": 15935 + }, + { + "epoch": 0.8882448024078925, + "grad_norm": 0.5895832777023315, + "learning_rate": 3.166035404155976e-06, + "loss": 1.6457, + "step": 15936 + }, + { + "epoch": 0.8883005406610557, + "grad_norm": 0.5945568680763245, + "learning_rate": 3.1629179867022298e-06, + "loss": 1.7127, + "step": 15937 + }, + { + "epoch": 0.8883562789142189, + "grad_norm": 0.581678032875061, + "learning_rate": 3.159802054647626e-06, + "loss": 1.5, + "step": 15938 + }, + { + "epoch": 0.8884120171673819, + "grad_norm": 0.6420979499816895, + "learning_rate": 3.156687608091019e-06, + "loss": 1.6278, + "step": 15939 + }, + { + "epoch": 0.8884677554205451, + "grad_norm": 0.5576969385147095, + "learning_rate": 3.1535746471311578e-06, + "loss": 1.7275, + "step": 15940 + }, + { + "epoch": 0.8885234936737083, + "grad_norm": 0.5767509341239929, + "learning_rate": 3.1504631718667744e-06, + "loss": 1.6617, + "step": 15941 + }, + { + "epoch": 0.8885792319268714, + "grad_norm": 0.6448524594306946, + "learning_rate": 3.1473531823965507e-06, + "loss": 1.7402, + "step": 15942 + }, + { + "epoch": 0.8886349701800346, + "grad_norm": 0.5689535140991211, + "learning_rate": 3.144244678819114e-06, + "loss": 1.45, + "step": 15943 + }, + { + "epoch": 0.8886907084331978, + "grad_norm": 0.5715149641036987, + "learning_rate": 3.1411376612330514e-06, + "loss": 1.4243, + "step": 15944 + }, + { + "epoch": 0.8887464466863608, + "grad_norm": 0.6064462661743164, + "learning_rate": 3.138032129736884e-06, + "loss": 1.7704, + "step": 15945 + }, + { + "epoch": 0.888802184939524, + "grad_norm": 0.5543216466903687, + "learning_rate": 3.1349280844291286e-06, + "loss": 1.6739, + "step": 15946 + }, + { + "epoch": 0.8888579231926872, + "grad_norm": 0.5677141547203064, + "learning_rate": 3.131825525408205e-06, + "loss": 1.5555, + "step": 15947 + }, + { + "epoch": 0.8889136614458503, + "grad_norm": 0.5624781847000122, + "learning_rate": 3.1287244527725135e-06, + "loss": 1.512, + "step": 15948 + }, + { + "epoch": 0.8889693996990135, + "grad_norm": 0.5779447555541992, + "learning_rate": 3.125624866620408e-06, + "loss": 1.658, + "step": 15949 + }, + { + "epoch": 0.8890251379521765, + "grad_norm": 0.5259407758712769, + "learning_rate": 3.122526767050177e-06, + "loss": 1.4094, + "step": 15950 + }, + { + "epoch": 0.8890808762053397, + "grad_norm": 0.5897923707962036, + "learning_rate": 3.119430154160097e-06, + "loss": 1.6805, + "step": 15951 + }, + { + "epoch": 0.8891366144585029, + "grad_norm": 0.5360985398292542, + "learning_rate": 3.1163350280483505e-06, + "loss": 1.7003, + "step": 15952 + }, + { + "epoch": 0.889192352711666, + "grad_norm": 0.5847355127334595, + "learning_rate": 3.113241388813104e-06, + "loss": 1.5728, + "step": 15953 + }, + { + "epoch": 0.8892480909648292, + "grad_norm": 0.5840595364570618, + "learning_rate": 3.110149236552473e-06, + "loss": 1.6875, + "step": 15954 + }, + { + "epoch": 0.8893038292179923, + "grad_norm": 0.6066023707389832, + "learning_rate": 3.107058571364524e-06, + "loss": 1.4887, + "step": 15955 + }, + { + "epoch": 0.8893595674711554, + "grad_norm": 0.5420007705688477, + "learning_rate": 3.103969393347267e-06, + "loss": 1.6033, + "step": 15956 + }, + { + "epoch": 0.8894153057243186, + "grad_norm": 0.5636321902275085, + "learning_rate": 3.1008817025986847e-06, + "loss": 1.4675, + "step": 15957 + }, + { + "epoch": 0.8894710439774818, + "grad_norm": 0.584204375743866, + "learning_rate": 3.097795499216699e-06, + "loss": 1.7095, + "step": 15958 + }, + { + "epoch": 0.8895267822306449, + "grad_norm": 0.5510618090629578, + "learning_rate": 3.094710783299171e-06, + "loss": 1.5529, + "step": 15959 + }, + { + "epoch": 0.889582520483808, + "grad_norm": 0.5739907622337341, + "learning_rate": 3.0916275549439432e-06, + "loss": 1.8335, + "step": 15960 + }, + { + "epoch": 0.8896382587369712, + "grad_norm": 0.6414487361907959, + "learning_rate": 3.0885458142487944e-06, + "loss": 1.7716, + "step": 15961 + }, + { + "epoch": 0.8896939969901343, + "grad_norm": 0.5211830139160156, + "learning_rate": 3.085465561311457e-06, + "loss": 1.3397, + "step": 15962 + }, + { + "epoch": 0.8897497352432975, + "grad_norm": 0.5396595597267151, + "learning_rate": 3.0823867962296305e-06, + "loss": 1.6436, + "step": 15963 + }, + { + "epoch": 0.8898054734964607, + "grad_norm": 0.5453661680221558, + "learning_rate": 3.0793095191009314e-06, + "loss": 1.7821, + "step": 15964 + }, + { + "epoch": 0.8898612117496237, + "grad_norm": 0.5480706691741943, + "learning_rate": 3.0762337300229817e-06, + "loss": 1.7467, + "step": 15965 + }, + { + "epoch": 0.8899169500027869, + "grad_norm": 0.5457361340522766, + "learning_rate": 3.0731594290933085e-06, + "loss": 1.5924, + "step": 15966 + }, + { + "epoch": 0.8899726882559501, + "grad_norm": 0.5531290173530579, + "learning_rate": 3.0700866164094123e-06, + "loss": 1.5698, + "step": 15967 + }, + { + "epoch": 0.8900284265091132, + "grad_norm": 0.5527978539466858, + "learning_rate": 3.0670152920687478e-06, + "loss": 1.6342, + "step": 15968 + }, + { + "epoch": 0.8900841647622764, + "grad_norm": 0.5642292499542236, + "learning_rate": 3.063945456168721e-06, + "loss": 1.7048, + "step": 15969 + }, + { + "epoch": 0.8901399030154395, + "grad_norm": 0.5974380373954773, + "learning_rate": 3.060877108806698e-06, + "loss": 1.8074, + "step": 15970 + }, + { + "epoch": 0.8901956412686026, + "grad_norm": 0.5607271194458008, + "learning_rate": 3.0578102500799623e-06, + "loss": 1.5402, + "step": 15971 + }, + { + "epoch": 0.8902513795217658, + "grad_norm": 0.6231569051742554, + "learning_rate": 3.054744880085808e-06, + "loss": 1.7861, + "step": 15972 + }, + { + "epoch": 0.8903071177749289, + "grad_norm": 0.5548269748687744, + "learning_rate": 3.0516809989214302e-06, + "loss": 1.5309, + "step": 15973 + }, + { + "epoch": 0.8903628560280921, + "grad_norm": 0.5717900991439819, + "learning_rate": 3.048618606684006e-06, + "loss": 1.6472, + "step": 15974 + }, + { + "epoch": 0.8904185942812552, + "grad_norm": 0.560154139995575, + "learning_rate": 3.045557703470647e-06, + "loss": 1.4459, + "step": 15975 + }, + { + "epoch": 0.8904743325344183, + "grad_norm": 0.5667665600776672, + "learning_rate": 3.0424982893784426e-06, + "loss": 1.481, + "step": 15976 + }, + { + "epoch": 0.8905300707875815, + "grad_norm": 0.5854259133338928, + "learning_rate": 3.0394403645044144e-06, + "loss": 1.6715, + "step": 15977 + }, + { + "epoch": 0.8905858090407447, + "grad_norm": 0.6453731656074524, + "learning_rate": 3.0363839289455297e-06, + "loss": 1.8429, + "step": 15978 + }, + { + "epoch": 0.8906415472939078, + "grad_norm": 0.6137635111808777, + "learning_rate": 3.033328982798733e-06, + "loss": 1.7792, + "step": 15979 + }, + { + "epoch": 0.890697285547071, + "grad_norm": 0.5792522430419922, + "learning_rate": 3.0302755261609028e-06, + "loss": 1.6636, + "step": 15980 + }, + { + "epoch": 0.8907530238002341, + "grad_norm": 0.5616828203201294, + "learning_rate": 3.0272235591288833e-06, + "loss": 1.6162, + "step": 15981 + }, + { + "epoch": 0.8908087620533972, + "grad_norm": 0.5925399661064148, + "learning_rate": 3.0241730817994583e-06, + "loss": 1.9301, + "step": 15982 + }, + { + "epoch": 0.8908645003065604, + "grad_norm": 0.5702762603759766, + "learning_rate": 3.0211240942693786e-06, + "loss": 1.5951, + "step": 15983 + }, + { + "epoch": 0.8909202385597236, + "grad_norm": 0.5429912805557251, + "learning_rate": 3.0180765966353443e-06, + "loss": 1.5957, + "step": 15984 + }, + { + "epoch": 0.8909759768128866, + "grad_norm": 0.5492966175079346, + "learning_rate": 3.015030588993989e-06, + "loss": 1.5814, + "step": 15985 + }, + { + "epoch": 0.8910317150660498, + "grad_norm": 0.5768184661865234, + "learning_rate": 3.0119860714419247e-06, + "loss": 1.5555, + "step": 15986 + }, + { + "epoch": 0.891087453319213, + "grad_norm": 0.5543115735054016, + "learning_rate": 3.008943044075696e-06, + "loss": 1.6901, + "step": 15987 + }, + { + "epoch": 0.8911431915723761, + "grad_norm": 0.5564537048339844, + "learning_rate": 3.005901506991826e-06, + "loss": 1.7219, + "step": 15988 + }, + { + "epoch": 0.8911989298255393, + "grad_norm": 0.6506380438804626, + "learning_rate": 3.0028614602867656e-06, + "loss": 1.9941, + "step": 15989 + }, + { + "epoch": 0.8912546680787025, + "grad_norm": 0.5839443802833557, + "learning_rate": 2.999822904056915e-06, + "loss": 1.7898, + "step": 15990 + }, + { + "epoch": 0.8913104063318655, + "grad_norm": 0.5792399644851685, + "learning_rate": 2.996785838398669e-06, + "loss": 1.7062, + "step": 15991 + }, + { + "epoch": 0.8913661445850287, + "grad_norm": 0.5519151091575623, + "learning_rate": 2.9937502634083183e-06, + "loss": 1.6367, + "step": 15992 + }, + { + "epoch": 0.8914218828381919, + "grad_norm": 0.5507789254188538, + "learning_rate": 2.990716179182146e-06, + "loss": 1.7481, + "step": 15993 + }, + { + "epoch": 0.891477621091355, + "grad_norm": 0.5409170389175415, + "learning_rate": 2.9876835858163698e-06, + "loss": 1.5891, + "step": 15994 + }, + { + "epoch": 0.8915333593445182, + "grad_norm": 0.5614409446716309, + "learning_rate": 2.984652483407169e-06, + "loss": 1.7217, + "step": 15995 + }, + { + "epoch": 0.8915890975976812, + "grad_norm": 0.6166634559631348, + "learning_rate": 2.981622872050682e-06, + "loss": 1.7456, + "step": 15996 + }, + { + "epoch": 0.8916448358508444, + "grad_norm": 0.5857463479042053, + "learning_rate": 2.978594751842967e-06, + "loss": 1.5291, + "step": 15997 + }, + { + "epoch": 0.8917005741040076, + "grad_norm": 0.599435031414032, + "learning_rate": 2.9755681228800902e-06, + "loss": 1.5079, + "step": 15998 + }, + { + "epoch": 0.8917563123571707, + "grad_norm": 0.5585033893585205, + "learning_rate": 2.972542985258009e-06, + "loss": 1.6639, + "step": 15999 + }, + { + "epoch": 0.8918120506103339, + "grad_norm": 0.6204033493995667, + "learning_rate": 2.9695193390726793e-06, + "loss": 1.776, + "step": 16000 + }, + { + "epoch": 0.891867788863497, + "grad_norm": 0.5450143218040466, + "learning_rate": 2.9664971844199863e-06, + "loss": 1.4699, + "step": 16001 + }, + { + "epoch": 0.8919235271166601, + "grad_norm": 0.5746825337409973, + "learning_rate": 2.9634765213957803e-06, + "loss": 1.7631, + "step": 16002 + }, + { + "epoch": 0.8919792653698233, + "grad_norm": 0.5068110227584839, + "learning_rate": 2.9604573500958633e-06, + "loss": 1.4175, + "step": 16003 + }, + { + "epoch": 0.8920350036229865, + "grad_norm": 0.539305567741394, + "learning_rate": 2.9574396706159746e-06, + "loss": 1.5931, + "step": 16004 + }, + { + "epoch": 0.8920907418761496, + "grad_norm": 0.5833491086959839, + "learning_rate": 2.9544234830518213e-06, + "loss": 1.7791, + "step": 16005 + }, + { + "epoch": 0.8921464801293127, + "grad_norm": 0.5791546702384949, + "learning_rate": 2.9514087874990604e-06, + "loss": 1.7419, + "step": 16006 + }, + { + "epoch": 0.8922022183824759, + "grad_norm": 0.6205574870109558, + "learning_rate": 2.9483955840532984e-06, + "loss": 1.7437, + "step": 16007 + }, + { + "epoch": 0.892257956635639, + "grad_norm": 0.5531277656555176, + "learning_rate": 2.945383872810098e-06, + "loss": 1.5056, + "step": 16008 + }, + { + "epoch": 0.8923136948888022, + "grad_norm": 0.5632871985435486, + "learning_rate": 2.942373653864977e-06, + "loss": 1.6407, + "step": 16009 + }, + { + "epoch": 0.8923694331419654, + "grad_norm": 0.5692397356033325, + "learning_rate": 2.939364927313404e-06, + "loss": 1.6579, + "step": 16010 + }, + { + "epoch": 0.8924251713951284, + "grad_norm": 0.5485531091690063, + "learning_rate": 2.9363576932507854e-06, + "loss": 1.4188, + "step": 16011 + }, + { + "epoch": 0.8924809096482916, + "grad_norm": 0.5531525015830994, + "learning_rate": 2.9333519517725004e-06, + "loss": 1.583, + "step": 16012 + }, + { + "epoch": 0.8925366479014548, + "grad_norm": 0.5605869293212891, + "learning_rate": 2.9303477029738793e-06, + "loss": 1.6154, + "step": 16013 + }, + { + "epoch": 0.8925923861546179, + "grad_norm": 0.600347638130188, + "learning_rate": 2.927344946950189e-06, + "loss": 1.7656, + "step": 16014 + }, + { + "epoch": 0.8926481244077811, + "grad_norm": 0.599833071231842, + "learning_rate": 2.9243436837966708e-06, + "loss": 1.8014, + "step": 16015 + }, + { + "epoch": 0.8927038626609443, + "grad_norm": 0.5680908560752869, + "learning_rate": 2.9213439136084875e-06, + "loss": 1.7021, + "step": 16016 + }, + { + "epoch": 0.8927596009141073, + "grad_norm": 0.5389718413352966, + "learning_rate": 2.9183456364808013e-06, + "loss": 1.7614, + "step": 16017 + }, + { + "epoch": 0.8928153391672705, + "grad_norm": 0.5132433176040649, + "learning_rate": 2.9153488525086814e-06, + "loss": 1.6005, + "step": 16018 + }, + { + "epoch": 0.8928710774204336, + "grad_norm": 0.5869194865226746, + "learning_rate": 2.9123535617871734e-06, + "loss": 1.6781, + "step": 16019 + }, + { + "epoch": 0.8929268156735968, + "grad_norm": 0.5567715167999268, + "learning_rate": 2.909359764411268e-06, + "loss": 1.5218, + "step": 16020 + }, + { + "epoch": 0.89298255392676, + "grad_norm": 0.5885666012763977, + "learning_rate": 2.9063674604759118e-06, + "loss": 1.7996, + "step": 16021 + }, + { + "epoch": 0.893038292179923, + "grad_norm": 0.5397041440010071, + "learning_rate": 2.903376650076017e-06, + "loss": 1.5145, + "step": 16022 + }, + { + "epoch": 0.8930940304330862, + "grad_norm": 0.5613077878952026, + "learning_rate": 2.9003873333064035e-06, + "loss": 1.7649, + "step": 16023 + }, + { + "epoch": 0.8931497686862494, + "grad_norm": 0.6617479920387268, + "learning_rate": 2.897399510261911e-06, + "loss": 2.0282, + "step": 16024 + }, + { + "epoch": 0.8932055069394125, + "grad_norm": 0.5322519540786743, + "learning_rate": 2.8944131810372754e-06, + "loss": 1.4677, + "step": 16025 + }, + { + "epoch": 0.8932612451925757, + "grad_norm": 0.5965158939361572, + "learning_rate": 2.891428345727204e-06, + "loss": 1.885, + "step": 16026 + }, + { + "epoch": 0.8933169834457388, + "grad_norm": 0.5451410412788391, + "learning_rate": 2.8884450044263654e-06, + "loss": 1.8177, + "step": 16027 + }, + { + "epoch": 0.8933727216989019, + "grad_norm": 0.5512980818748474, + "learning_rate": 2.885463157229368e-06, + "loss": 1.7025, + "step": 16028 + }, + { + "epoch": 0.8934284599520651, + "grad_norm": 0.5658778548240662, + "learning_rate": 2.882482804230796e-06, + "loss": 1.5729, + "step": 16029 + }, + { + "epoch": 0.8934841982052283, + "grad_norm": 0.5971152186393738, + "learning_rate": 2.8795039455251417e-06, + "loss": 1.619, + "step": 16030 + }, + { + "epoch": 0.8935399364583914, + "grad_norm": 0.5880569219589233, + "learning_rate": 2.8765265812068955e-06, + "loss": 1.6816, + "step": 16031 + }, + { + "epoch": 0.8935956747115545, + "grad_norm": 0.5676398873329163, + "learning_rate": 2.8735507113704765e-06, + "loss": 1.4816, + "step": 16032 + }, + { + "epoch": 0.8936514129647177, + "grad_norm": 0.5465163588523865, + "learning_rate": 2.870576336110259e-06, + "loss": 1.6472, + "step": 16033 + }, + { + "epoch": 0.8937071512178808, + "grad_norm": 0.5322096943855286, + "learning_rate": 2.867603455520579e-06, + "loss": 1.5764, + "step": 16034 + }, + { + "epoch": 0.893762889471044, + "grad_norm": 0.5871340036392212, + "learning_rate": 2.8646320696957163e-06, + "loss": 1.5398, + "step": 16035 + }, + { + "epoch": 0.8938186277242072, + "grad_norm": 0.5516924262046814, + "learning_rate": 2.8616621787299182e-06, + "loss": 1.5303, + "step": 16036 + }, + { + "epoch": 0.8938743659773702, + "grad_norm": 0.5902751088142395, + "learning_rate": 2.8586937827173475e-06, + "loss": 1.6509, + "step": 16037 + }, + { + "epoch": 0.8939301042305334, + "grad_norm": 0.5504544973373413, + "learning_rate": 2.8557268817521577e-06, + "loss": 1.4169, + "step": 16038 + }, + { + "epoch": 0.8939858424836966, + "grad_norm": 0.540054976940155, + "learning_rate": 2.8527614759284393e-06, + "loss": 1.6065, + "step": 16039 + }, + { + "epoch": 0.8940415807368597, + "grad_norm": 0.5828325152397156, + "learning_rate": 2.8497975653402398e-06, + "loss": 1.498, + "step": 16040 + }, + { + "epoch": 0.8940973189900229, + "grad_norm": 0.5389959216117859, + "learning_rate": 2.846835150081567e-06, + "loss": 1.5735, + "step": 16041 + }, + { + "epoch": 0.894153057243186, + "grad_norm": 0.5519946217536926, + "learning_rate": 2.8438742302463463e-06, + "loss": 1.4585, + "step": 16042 + }, + { + "epoch": 0.8942087954963491, + "grad_norm": 0.5483652949333191, + "learning_rate": 2.8409148059285074e-06, + "loss": 1.5987, + "step": 16043 + }, + { + "epoch": 0.8942645337495123, + "grad_norm": 0.587627112865448, + "learning_rate": 2.8379568772218925e-06, + "loss": 1.6512, + "step": 16044 + }, + { + "epoch": 0.8943202720026754, + "grad_norm": 0.5679745674133301, + "learning_rate": 2.8350004442203093e-06, + "loss": 1.5096, + "step": 16045 + }, + { + "epoch": 0.8943760102558386, + "grad_norm": 0.5471773147583008, + "learning_rate": 2.832045507017517e-06, + "loss": 1.6152, + "step": 16046 + }, + { + "epoch": 0.8944317485090018, + "grad_norm": 0.55399489402771, + "learning_rate": 2.8290920657072395e-06, + "loss": 1.6592, + "step": 16047 + }, + { + "epoch": 0.8944874867621648, + "grad_norm": 0.5755215883255005, + "learning_rate": 2.826140120383136e-06, + "loss": 1.6614, + "step": 16048 + }, + { + "epoch": 0.894543225015328, + "grad_norm": 0.5865688920021057, + "learning_rate": 2.823189671138815e-06, + "loss": 1.7733, + "step": 16049 + }, + { + "epoch": 0.8945989632684912, + "grad_norm": 0.5821816921234131, + "learning_rate": 2.8202407180678734e-06, + "loss": 1.8013, + "step": 16050 + }, + { + "epoch": 0.8946547015216543, + "grad_norm": 0.557863712310791, + "learning_rate": 2.8172932612638094e-06, + "loss": 1.6324, + "step": 16051 + }, + { + "epoch": 0.8947104397748175, + "grad_norm": 0.5792876482009888, + "learning_rate": 2.8143473008201083e-06, + "loss": 1.5339, + "step": 16052 + }, + { + "epoch": 0.8947661780279806, + "grad_norm": 0.5538420677185059, + "learning_rate": 2.8114028368302016e-06, + "loss": 1.4765, + "step": 16053 + }, + { + "epoch": 0.8948219162811437, + "grad_norm": 0.5834795236587524, + "learning_rate": 2.8084598693874696e-06, + "loss": 1.5913, + "step": 16054 + }, + { + "epoch": 0.8948776545343069, + "grad_norm": 0.5423466563224792, + "learning_rate": 2.8055183985852495e-06, + "loss": 1.4893, + "step": 16055 + }, + { + "epoch": 0.8949333927874701, + "grad_norm": 0.5582904815673828, + "learning_rate": 2.8025784245168165e-06, + "loss": 1.6404, + "step": 16056 + }, + { + "epoch": 0.8949891310406332, + "grad_norm": 0.5539766550064087, + "learning_rate": 2.799639947275412e-06, + "loss": 1.6021, + "step": 16057 + }, + { + "epoch": 0.8950448692937963, + "grad_norm": 0.5408018827438354, + "learning_rate": 2.79670296695424e-06, + "loss": 1.5734, + "step": 16058 + }, + { + "epoch": 0.8951006075469595, + "grad_norm": 0.56126469373703, + "learning_rate": 2.7937674836464256e-06, + "loss": 1.7043, + "step": 16059 + }, + { + "epoch": 0.8951563458001226, + "grad_norm": 0.5632897615432739, + "learning_rate": 2.7908334974450835e-06, + "loss": 1.5945, + "step": 16060 + }, + { + "epoch": 0.8952120840532858, + "grad_norm": 0.5938173532485962, + "learning_rate": 2.78790100844325e-06, + "loss": 1.8713, + "step": 16061 + }, + { + "epoch": 0.895267822306449, + "grad_norm": 0.5657972693443298, + "learning_rate": 2.7849700167339397e-06, + "loss": 1.5255, + "step": 16062 + }, + { + "epoch": 0.895323560559612, + "grad_norm": 0.5954453945159912, + "learning_rate": 2.7820405224100898e-06, + "loss": 1.5041, + "step": 16063 + }, + { + "epoch": 0.8953792988127752, + "grad_norm": 0.5433526039123535, + "learning_rate": 2.7791125255646146e-06, + "loss": 1.7677, + "step": 16064 + }, + { + "epoch": 0.8954350370659383, + "grad_norm": 0.5708447694778442, + "learning_rate": 2.7761860262903728e-06, + "loss": 1.7189, + "step": 16065 + }, + { + "epoch": 0.8954907753191015, + "grad_norm": 0.558793842792511, + "learning_rate": 2.7732610246801737e-06, + "loss": 1.5225, + "step": 16066 + }, + { + "epoch": 0.8955465135722647, + "grad_norm": 0.5685842037200928, + "learning_rate": 2.7703375208267877e-06, + "loss": 1.7542, + "step": 16067 + }, + { + "epoch": 0.8956022518254277, + "grad_norm": 0.5649571418762207, + "learning_rate": 2.767415514822924e-06, + "loss": 1.5417, + "step": 16068 + }, + { + "epoch": 0.8956579900785909, + "grad_norm": 0.5796234011650085, + "learning_rate": 2.7644950067612694e-06, + "loss": 1.7285, + "step": 16069 + }, + { + "epoch": 0.8957137283317541, + "grad_norm": 0.595861554145813, + "learning_rate": 2.7615759967344167e-06, + "loss": 1.6136, + "step": 16070 + }, + { + "epoch": 0.8957694665849172, + "grad_norm": 0.608975350856781, + "learning_rate": 2.758658484834958e-06, + "loss": 2.0667, + "step": 16071 + }, + { + "epoch": 0.8958252048380804, + "grad_norm": 0.5649267435073853, + "learning_rate": 2.7557424711554146e-06, + "loss": 1.5887, + "step": 16072 + }, + { + "epoch": 0.8958809430912436, + "grad_norm": 0.5669053792953491, + "learning_rate": 2.7528279557882675e-06, + "loss": 1.7353, + "step": 16073 + }, + { + "epoch": 0.8959366813444066, + "grad_norm": 0.5819360613822937, + "learning_rate": 2.7499149388259536e-06, + "loss": 1.6566, + "step": 16074 + }, + { + "epoch": 0.8959924195975698, + "grad_norm": 0.5492451190948486, + "learning_rate": 2.7470034203608384e-06, + "loss": 1.536, + "step": 16075 + }, + { + "epoch": 0.896048157850733, + "grad_norm": 0.539772629737854, + "learning_rate": 2.7440934004852816e-06, + "loss": 1.563, + "step": 16076 + }, + { + "epoch": 0.8961038961038961, + "grad_norm": 0.5729084610939026, + "learning_rate": 2.7411848792915585e-06, + "loss": 1.8413, + "step": 16077 + }, + { + "epoch": 0.8961596343570593, + "grad_norm": 0.5888326168060303, + "learning_rate": 2.7382778568719127e-06, + "loss": 1.7377, + "step": 16078 + }, + { + "epoch": 0.8962153726102224, + "grad_norm": 0.6055900454521179, + "learning_rate": 2.7353723333185365e-06, + "loss": 1.5769, + "step": 16079 + }, + { + "epoch": 0.8962711108633855, + "grad_norm": 0.5950702428817749, + "learning_rate": 2.7324683087235736e-06, + "loss": 1.1935, + "step": 16080 + }, + { + "epoch": 0.8963268491165487, + "grad_norm": 0.5498350858688354, + "learning_rate": 2.7295657831791387e-06, + "loss": 1.5682, + "step": 16081 + }, + { + "epoch": 0.8963825873697119, + "grad_norm": 0.5495039224624634, + "learning_rate": 2.7266647567772643e-06, + "loss": 1.4302, + "step": 16082 + }, + { + "epoch": 0.896438325622875, + "grad_norm": 0.5697756409645081, + "learning_rate": 2.7237652296099646e-06, + "loss": 1.7366, + "step": 16083 + }, + { + "epoch": 0.8964940638760381, + "grad_norm": 0.5656793713569641, + "learning_rate": 2.7208672017691893e-06, + "loss": 1.5471, + "step": 16084 + }, + { + "epoch": 0.8965498021292013, + "grad_norm": 0.6022312045097351, + "learning_rate": 2.717970673346848e-06, + "loss": 1.8768, + "step": 16085 + }, + { + "epoch": 0.8966055403823644, + "grad_norm": 0.581227719783783, + "learning_rate": 2.715075644434806e-06, + "loss": 1.725, + "step": 16086 + }, + { + "epoch": 0.8966612786355276, + "grad_norm": 0.5306532979011536, + "learning_rate": 2.7121821151248726e-06, + "loss": 1.4072, + "step": 16087 + }, + { + "epoch": 0.8967170168886907, + "grad_norm": 0.5724023580551147, + "learning_rate": 2.70929008550882e-06, + "loss": 1.6065, + "step": 16088 + }, + { + "epoch": 0.8967727551418538, + "grad_norm": 0.5894409418106079, + "learning_rate": 2.706399555678357e-06, + "loss": 1.5687, + "step": 16089 + }, + { + "epoch": 0.896828493395017, + "grad_norm": 0.6361358165740967, + "learning_rate": 2.7035105257251614e-06, + "loss": 1.7931, + "step": 16090 + }, + { + "epoch": 0.8968842316481801, + "grad_norm": 0.538797914981842, + "learning_rate": 2.7006229957408537e-06, + "loss": 1.4986, + "step": 16091 + }, + { + "epoch": 0.8969399699013433, + "grad_norm": 0.6297140121459961, + "learning_rate": 2.6977369658170105e-06, + "loss": 1.5404, + "step": 16092 + }, + { + "epoch": 0.8969957081545065, + "grad_norm": 0.5619019865989685, + "learning_rate": 2.6948524360451588e-06, + "loss": 1.6416, + "step": 16093 + }, + { + "epoch": 0.8970514464076695, + "grad_norm": 0.5399261713027954, + "learning_rate": 2.6919694065167756e-06, + "loss": 1.3168, + "step": 16094 + }, + { + "epoch": 0.8971071846608327, + "grad_norm": 0.5137415528297424, + "learning_rate": 2.6890878773233097e-06, + "loss": 1.3254, + "step": 16095 + }, + { + "epoch": 0.8971629229139959, + "grad_norm": 0.5602340698242188, + "learning_rate": 2.686207848556127e-06, + "loss": 1.7026, + "step": 16096 + }, + { + "epoch": 0.897218661167159, + "grad_norm": 0.5822181701660156, + "learning_rate": 2.683329320306571e-06, + "loss": 1.8391, + "step": 16097 + }, + { + "epoch": 0.8972743994203222, + "grad_norm": 0.6048908829689026, + "learning_rate": 2.6804522926659358e-06, + "loss": 1.7414, + "step": 16098 + }, + { + "epoch": 0.8973301376734854, + "grad_norm": 0.5519444942474365, + "learning_rate": 2.677576765725459e-06, + "loss": 1.8649, + "step": 16099 + }, + { + "epoch": 0.8973858759266484, + "grad_norm": 0.5473284721374512, + "learning_rate": 2.674702739576351e-06, + "loss": 1.6357, + "step": 16100 + }, + { + "epoch": 0.8974416141798116, + "grad_norm": 0.6029911041259766, + "learning_rate": 2.6718302143097283e-06, + "loss": 1.6912, + "step": 16101 + }, + { + "epoch": 0.8974973524329748, + "grad_norm": 0.5273539423942566, + "learning_rate": 2.668959190016723e-06, + "loss": 1.4666, + "step": 16102 + }, + { + "epoch": 0.8975530906861379, + "grad_norm": 0.5469059944152832, + "learning_rate": 2.666089666788363e-06, + "loss": 1.5336, + "step": 16103 + }, + { + "epoch": 0.897608828939301, + "grad_norm": 0.5588993430137634, + "learning_rate": 2.6632216447156686e-06, + "loss": 1.3672, + "step": 16104 + }, + { + "epoch": 0.8976645671924642, + "grad_norm": 0.676473081111908, + "learning_rate": 2.6603551238895853e-06, + "loss": 2.1044, + "step": 16105 + }, + { + "epoch": 0.8977203054456273, + "grad_norm": 0.6686132550239563, + "learning_rate": 2.6574901044010337e-06, + "loss": 1.8391, + "step": 16106 + }, + { + "epoch": 0.8977760436987905, + "grad_norm": 0.5427836179733276, + "learning_rate": 2.654626586340875e-06, + "loss": 1.4328, + "step": 16107 + }, + { + "epoch": 0.8978317819519537, + "grad_norm": 0.5965200662612915, + "learning_rate": 2.651764569799908e-06, + "loss": 1.6311, + "step": 16108 + }, + { + "epoch": 0.8978875202051168, + "grad_norm": 0.5406008362770081, + "learning_rate": 2.648904054868917e-06, + "loss": 1.7373, + "step": 16109 + }, + { + "epoch": 0.8979432584582799, + "grad_norm": 0.5878314971923828, + "learning_rate": 2.646045041638606e-06, + "loss": 1.779, + "step": 16110 + }, + { + "epoch": 0.897998996711443, + "grad_norm": 0.6186338663101196, + "learning_rate": 2.6431875301996645e-06, + "loss": 1.683, + "step": 16111 + }, + { + "epoch": 0.8980547349646062, + "grad_norm": 0.5795671939849854, + "learning_rate": 2.6403315206426917e-06, + "loss": 1.5908, + "step": 16112 + }, + { + "epoch": 0.8981104732177694, + "grad_norm": 0.5506584048271179, + "learning_rate": 2.6374770130582815e-06, + "loss": 1.7345, + "step": 16113 + }, + { + "epoch": 0.8981662114709325, + "grad_norm": 0.5616600513458252, + "learning_rate": 2.6346240075369677e-06, + "loss": 1.6287, + "step": 16114 + }, + { + "epoch": 0.8982219497240956, + "grad_norm": 0.5344184637069702, + "learning_rate": 2.631772504169211e-06, + "loss": 1.5898, + "step": 16115 + }, + { + "epoch": 0.8982776879772588, + "grad_norm": 0.627220869064331, + "learning_rate": 2.6289225030454555e-06, + "loss": 1.8715, + "step": 16116 + }, + { + "epoch": 0.8983334262304219, + "grad_norm": 0.5454089045524597, + "learning_rate": 2.626074004256085e-06, + "loss": 1.6249, + "step": 16117 + }, + { + "epoch": 0.8983891644835851, + "grad_norm": 0.5851393938064575, + "learning_rate": 2.6232270078914378e-06, + "loss": 1.7873, + "step": 16118 + }, + { + "epoch": 0.8984449027367483, + "grad_norm": 0.5392501950263977, + "learning_rate": 2.620381514041803e-06, + "loss": 1.4625, + "step": 16119 + }, + { + "epoch": 0.8985006409899113, + "grad_norm": 0.5707475543022156, + "learning_rate": 2.617537522797431e-06, + "loss": 1.7089, + "step": 16120 + }, + { + "epoch": 0.8985563792430745, + "grad_norm": 0.5721530318260193, + "learning_rate": 2.61469503424851e-06, + "loss": 1.8189, + "step": 16121 + }, + { + "epoch": 0.8986121174962377, + "grad_norm": 0.5983375310897827, + "learning_rate": 2.611854048485185e-06, + "loss": 1.8311, + "step": 16122 + }, + { + "epoch": 0.8986678557494008, + "grad_norm": 0.5735673308372498, + "learning_rate": 2.6090145655975505e-06, + "loss": 1.6892, + "step": 16123 + }, + { + "epoch": 0.898723594002564, + "grad_norm": 0.5582413673400879, + "learning_rate": 2.6061765856756737e-06, + "loss": 1.7123, + "step": 16124 + }, + { + "epoch": 0.8987793322557271, + "grad_norm": 0.6058027148246765, + "learning_rate": 2.603340108809543e-06, + "loss": 1.7274, + "step": 16125 + }, + { + "epoch": 0.8988350705088902, + "grad_norm": 0.5493965744972229, + "learning_rate": 2.600505135089132e-06, + "loss": 1.6002, + "step": 16126 + }, + { + "epoch": 0.8988908087620534, + "grad_norm": 0.561474084854126, + "learning_rate": 2.5976716646043286e-06, + "loss": 1.7723, + "step": 16127 + }, + { + "epoch": 0.8989465470152166, + "grad_norm": 0.5366647243499756, + "learning_rate": 2.594839697445017e-06, + "loss": 1.4776, + "step": 16128 + }, + { + "epoch": 0.8990022852683797, + "grad_norm": 0.5751245021820068, + "learning_rate": 2.592009233700993e-06, + "loss": 1.7196, + "step": 16129 + }, + { + "epoch": 0.8990580235215428, + "grad_norm": 0.5932884812355042, + "learning_rate": 2.5891802734620273e-06, + "loss": 1.7536, + "step": 16130 + }, + { + "epoch": 0.899113761774706, + "grad_norm": 0.5735995769500732, + "learning_rate": 2.5863528168178385e-06, + "loss": 1.7116, + "step": 16131 + }, + { + "epoch": 0.8991695000278691, + "grad_norm": 0.573340892791748, + "learning_rate": 2.583526863858099e-06, + "loss": 1.6725, + "step": 16132 + }, + { + "epoch": 0.8992252382810323, + "grad_norm": 0.6185228824615479, + "learning_rate": 2.5807024146724368e-06, + "loss": 1.9008, + "step": 16133 + }, + { + "epoch": 0.8992809765341954, + "grad_norm": 0.5922132134437561, + "learning_rate": 2.5778794693504136e-06, + "loss": 1.6693, + "step": 16134 + }, + { + "epoch": 0.8993367147873585, + "grad_norm": 0.5708510279655457, + "learning_rate": 2.575058027981564e-06, + "loss": 1.5989, + "step": 16135 + }, + { + "epoch": 0.8993924530405217, + "grad_norm": 0.542935848236084, + "learning_rate": 2.5722380906553655e-06, + "loss": 1.6231, + "step": 16136 + }, + { + "epoch": 0.8994481912936848, + "grad_norm": 0.5564297437667847, + "learning_rate": 2.5694196574612585e-06, + "loss": 1.5986, + "step": 16137 + }, + { + "epoch": 0.899503929546848, + "grad_norm": 0.5666566491127014, + "learning_rate": 2.5666027284886095e-06, + "loss": 1.6638, + "step": 16138 + }, + { + "epoch": 0.8995596678000112, + "grad_norm": 0.543543815612793, + "learning_rate": 2.56378730382677e-06, + "loss": 1.5928, + "step": 16139 + }, + { + "epoch": 0.8996154060531742, + "grad_norm": 0.5925387144088745, + "learning_rate": 2.560973383565035e-06, + "loss": 1.8026, + "step": 16140 + }, + { + "epoch": 0.8996711443063374, + "grad_norm": 0.5771430730819702, + "learning_rate": 2.558160967792622e-06, + "loss": 1.6094, + "step": 16141 + }, + { + "epoch": 0.8997268825595006, + "grad_norm": 0.5323361158370972, + "learning_rate": 2.5553500565987433e-06, + "loss": 1.5472, + "step": 16142 + }, + { + "epoch": 0.8997826208126637, + "grad_norm": 0.5811231136322021, + "learning_rate": 2.5525406500725378e-06, + "loss": 1.5912, + "step": 16143 + }, + { + "epoch": 0.8998383590658269, + "grad_norm": 0.5251652598381042, + "learning_rate": 2.5497327483031075e-06, + "loss": 1.5085, + "step": 16144 + }, + { + "epoch": 0.8998940973189901, + "grad_norm": 0.4739479720592499, + "learning_rate": 2.546926351379497e-06, + "loss": 1.0702, + "step": 16145 + }, + { + "epoch": 0.8999498355721531, + "grad_norm": 0.5963080525398254, + "learning_rate": 2.544121459390714e-06, + "loss": 1.78, + "step": 16146 + }, + { + "epoch": 0.9000055738253163, + "grad_norm": 0.6176660060882568, + "learning_rate": 2.5413180724257192e-06, + "loss": 1.7871, + "step": 16147 + }, + { + "epoch": 0.9000613120784795, + "grad_norm": 0.5905717611312866, + "learning_rate": 2.5385161905734036e-06, + "loss": 1.626, + "step": 16148 + }, + { + "epoch": 0.9001170503316426, + "grad_norm": 0.5534247756004333, + "learning_rate": 2.5357158139226347e-06, + "loss": 1.6934, + "step": 16149 + }, + { + "epoch": 0.9001727885848058, + "grad_norm": 0.5321455001831055, + "learning_rate": 2.5329169425622247e-06, + "loss": 1.5418, + "step": 16150 + }, + { + "epoch": 0.900228526837969, + "grad_norm": 0.6282263994216919, + "learning_rate": 2.530119576580936e-06, + "loss": 1.8433, + "step": 16151 + }, + { + "epoch": 0.900284265091132, + "grad_norm": 0.5648069381713867, + "learning_rate": 2.5273237160674924e-06, + "loss": 1.665, + "step": 16152 + }, + { + "epoch": 0.9003400033442952, + "grad_norm": 0.565209150314331, + "learning_rate": 2.5245293611105393e-06, + "loss": 1.4747, + "step": 16153 + }, + { + "epoch": 0.9003957415974584, + "grad_norm": 0.5891183614730835, + "learning_rate": 2.5217365117987334e-06, + "loss": 1.648, + "step": 16154 + }, + { + "epoch": 0.9004514798506215, + "grad_norm": 0.5333722233772278, + "learning_rate": 2.5189451682206157e-06, + "loss": 1.3829, + "step": 16155 + }, + { + "epoch": 0.9005072181037846, + "grad_norm": 0.6240305304527283, + "learning_rate": 2.5161553304647256e-06, + "loss": 1.8415, + "step": 16156 + }, + { + "epoch": 0.9005629563569477, + "grad_norm": 0.5713739395141602, + "learning_rate": 2.513366998619543e-06, + "loss": 1.7705, + "step": 16157 + }, + { + "epoch": 0.9006186946101109, + "grad_norm": 0.5766152143478394, + "learning_rate": 2.5105801727734857e-06, + "loss": 1.8471, + "step": 16158 + }, + { + "epoch": 0.9006744328632741, + "grad_norm": 0.5578577518463135, + "learning_rate": 2.5077948530149554e-06, + "loss": 1.5019, + "step": 16159 + }, + { + "epoch": 0.9007301711164372, + "grad_norm": 0.6112489700317383, + "learning_rate": 2.5050110394322533e-06, + "loss": 1.5259, + "step": 16160 + }, + { + "epoch": 0.9007859093696003, + "grad_norm": 0.5936005115509033, + "learning_rate": 2.502228732113704e-06, + "loss": 1.7377, + "step": 16161 + }, + { + "epoch": 0.9008416476227635, + "grad_norm": 0.5542739629745483, + "learning_rate": 2.499447931147525e-06, + "loss": 1.6652, + "step": 16162 + }, + { + "epoch": 0.9008973858759266, + "grad_norm": 0.5677976608276367, + "learning_rate": 2.4966686366219127e-06, + "loss": 1.5852, + "step": 16163 + }, + { + "epoch": 0.9009531241290898, + "grad_norm": 0.5147234797477722, + "learning_rate": 2.493890848624991e-06, + "loss": 1.5853, + "step": 16164 + }, + { + "epoch": 0.901008862382253, + "grad_norm": 0.5458986759185791, + "learning_rate": 2.491114567244884e-06, + "loss": 1.6512, + "step": 16165 + }, + { + "epoch": 0.901064600635416, + "grad_norm": 0.5613119006156921, + "learning_rate": 2.488339792569633e-06, + "loss": 1.6572, + "step": 16166 + }, + { + "epoch": 0.9011203388885792, + "grad_norm": 0.5735984444618225, + "learning_rate": 2.4855665246872216e-06, + "loss": 1.6004, + "step": 16167 + }, + { + "epoch": 0.9011760771417424, + "grad_norm": 0.5594103336334229, + "learning_rate": 2.4827947636856142e-06, + "loss": 1.6282, + "step": 16168 + }, + { + "epoch": 0.9012318153949055, + "grad_norm": 0.572628378868103, + "learning_rate": 2.480024509652712e-06, + "loss": 1.6305, + "step": 16169 + }, + { + "epoch": 0.9012875536480687, + "grad_norm": 0.567187488079071, + "learning_rate": 2.477255762676367e-06, + "loss": 1.6547, + "step": 16170 + }, + { + "epoch": 0.9013432919012319, + "grad_norm": 0.5400233268737793, + "learning_rate": 2.474488522844398e-06, + "loss": 1.7767, + "step": 16171 + }, + { + "epoch": 0.9013990301543949, + "grad_norm": 0.5454822778701782, + "learning_rate": 2.4717227902445573e-06, + "loss": 1.5718, + "step": 16172 + }, + { + "epoch": 0.9014547684075581, + "grad_norm": 0.6007751226425171, + "learning_rate": 2.4689585649645685e-06, + "loss": 1.8284, + "step": 16173 + }, + { + "epoch": 0.9015105066607213, + "grad_norm": 0.5879939794540405, + "learning_rate": 2.4661958470920844e-06, + "loss": 1.7134, + "step": 16174 + }, + { + "epoch": 0.9015662449138844, + "grad_norm": 0.5395904779434204, + "learning_rate": 2.4634346367147233e-06, + "loss": 1.4603, + "step": 16175 + }, + { + "epoch": 0.9016219831670476, + "grad_norm": 0.5363257527351379, + "learning_rate": 2.4606749339200595e-06, + "loss": 1.3745, + "step": 16176 + }, + { + "epoch": 0.9016777214202107, + "grad_norm": 0.5916034579277039, + "learning_rate": 2.4579167387956127e-06, + "loss": 1.5152, + "step": 16177 + }, + { + "epoch": 0.9017334596733738, + "grad_norm": 0.5937188267707825, + "learning_rate": 2.4551600514288674e-06, + "loss": 1.8504, + "step": 16178 + }, + { + "epoch": 0.901789197926537, + "grad_norm": 0.5348295569419861, + "learning_rate": 2.4524048719072214e-06, + "loss": 1.5154, + "step": 16179 + }, + { + "epoch": 0.9018449361797001, + "grad_norm": 0.6616393327713013, + "learning_rate": 2.449651200318087e-06, + "loss": 1.481, + "step": 16180 + }, + { + "epoch": 0.9019006744328633, + "grad_norm": 0.5949798226356506, + "learning_rate": 2.446899036748773e-06, + "loss": 1.5498, + "step": 16181 + }, + { + "epoch": 0.9019564126860264, + "grad_norm": 0.5386583209037781, + "learning_rate": 2.444148381286565e-06, + "loss": 1.5103, + "step": 16182 + }, + { + "epoch": 0.9020121509391895, + "grad_norm": 0.559246301651001, + "learning_rate": 2.441399234018704e-06, + "loss": 1.6951, + "step": 16183 + }, + { + "epoch": 0.9020678891923527, + "grad_norm": 0.5879007577896118, + "learning_rate": 2.4386515950323705e-06, + "loss": 1.7548, + "step": 16184 + }, + { + "epoch": 0.9021236274455159, + "grad_norm": 0.5575884580612183, + "learning_rate": 2.4359054644147117e-06, + "loss": 1.5964, + "step": 16185 + }, + { + "epoch": 0.902179365698679, + "grad_norm": 0.6214359402656555, + "learning_rate": 2.433160842252802e-06, + "loss": 1.7819, + "step": 16186 + }, + { + "epoch": 0.9022351039518421, + "grad_norm": 0.5600733160972595, + "learning_rate": 2.4304177286337102e-06, + "loss": 1.5818, + "step": 16187 + }, + { + "epoch": 0.9022908422050053, + "grad_norm": 0.5444473624229431, + "learning_rate": 2.4276761236444125e-06, + "loss": 1.6073, + "step": 16188 + }, + { + "epoch": 0.9023465804581684, + "grad_norm": 0.5482627153396606, + "learning_rate": 2.4249360273718714e-06, + "loss": 1.696, + "step": 16189 + }, + { + "epoch": 0.9024023187113316, + "grad_norm": 0.5775576829910278, + "learning_rate": 2.4221974399029625e-06, + "loss": 1.7948, + "step": 16190 + }, + { + "epoch": 0.9024580569644948, + "grad_norm": 0.5745429992675781, + "learning_rate": 2.4194603613245546e-06, + "loss": 1.5173, + "step": 16191 + }, + { + "epoch": 0.9025137952176578, + "grad_norm": 0.6044434309005737, + "learning_rate": 2.4167247917234626e-06, + "loss": 1.8802, + "step": 16192 + }, + { + "epoch": 0.902569533470821, + "grad_norm": 0.5430091619491577, + "learning_rate": 2.413990731186422e-06, + "loss": 1.5677, + "step": 16193 + }, + { + "epoch": 0.9026252717239842, + "grad_norm": 0.5700405836105347, + "learning_rate": 2.4112581798001464e-06, + "loss": 1.5949, + "step": 16194 + }, + { + "epoch": 0.9026810099771473, + "grad_norm": 0.5866665244102478, + "learning_rate": 2.4085271376513065e-06, + "loss": 1.9555, + "step": 16195 + }, + { + "epoch": 0.9027367482303105, + "grad_norm": 0.5908649563789368, + "learning_rate": 2.405797604826504e-06, + "loss": 1.7255, + "step": 16196 + }, + { + "epoch": 0.9027924864834737, + "grad_norm": 0.5687332153320312, + "learning_rate": 2.4030695814123094e-06, + "loss": 1.6104, + "step": 16197 + }, + { + "epoch": 0.9028482247366367, + "grad_norm": 0.5401330590248108, + "learning_rate": 2.4003430674952366e-06, + "loss": 1.6265, + "step": 16198 + }, + { + "epoch": 0.9029039629897999, + "grad_norm": 0.5473314523696899, + "learning_rate": 2.3976180631617605e-06, + "loss": 1.5713, + "step": 16199 + }, + { + "epoch": 0.9029597012429631, + "grad_norm": 0.5788750648498535, + "learning_rate": 2.394894568498296e-06, + "loss": 1.6233, + "step": 16200 + }, + { + "epoch": 0.9030154394961262, + "grad_norm": 0.5692962408065796, + "learning_rate": 2.392172583591218e-06, + "loss": 1.7263, + "step": 16201 + }, + { + "epoch": 0.9030711777492894, + "grad_norm": 0.5532717704772949, + "learning_rate": 2.3894521085268516e-06, + "loss": 1.6395, + "step": 16202 + }, + { + "epoch": 0.9031269160024524, + "grad_norm": 0.5175745487213135, + "learning_rate": 2.3867331433914787e-06, + "loss": 1.4497, + "step": 16203 + }, + { + "epoch": 0.9031826542556156, + "grad_norm": 0.5720580816268921, + "learning_rate": 2.3840156882713293e-06, + "loss": 1.688, + "step": 16204 + }, + { + "epoch": 0.9032383925087788, + "grad_norm": 0.5270658135414124, + "learning_rate": 2.3812997432525687e-06, + "loss": 1.6415, + "step": 16205 + }, + { + "epoch": 0.9032941307619419, + "grad_norm": 0.505079448223114, + "learning_rate": 2.3785853084213604e-06, + "loss": 1.5103, + "step": 16206 + }, + { + "epoch": 0.9033498690151051, + "grad_norm": 0.6018316745758057, + "learning_rate": 2.3758723838637643e-06, + "loss": 1.7707, + "step": 16207 + }, + { + "epoch": 0.9034056072682682, + "grad_norm": 0.5867494940757751, + "learning_rate": 2.373160969665833e-06, + "loss": 1.6635, + "step": 16208 + }, + { + "epoch": 0.9034613455214313, + "grad_norm": 0.6046900749206543, + "learning_rate": 2.370451065913548e-06, + "loss": 1.7736, + "step": 16209 + }, + { + "epoch": 0.9035170837745945, + "grad_norm": 0.5086727738380432, + "learning_rate": 2.367742672692852e-06, + "loss": 1.4639, + "step": 16210 + }, + { + "epoch": 0.9035728220277577, + "grad_norm": 0.5750524997711182, + "learning_rate": 2.3650357900896536e-06, + "loss": 1.6669, + "step": 16211 + }, + { + "epoch": 0.9036285602809208, + "grad_norm": 0.614326000213623, + "learning_rate": 2.362330418189779e-06, + "loss": 1.8263, + "step": 16212 + }, + { + "epoch": 0.9036842985340839, + "grad_norm": 0.5382913947105408, + "learning_rate": 2.359626557079042e-06, + "loss": 1.5759, + "step": 16213 + }, + { + "epoch": 0.9037400367872471, + "grad_norm": 0.5230354070663452, + "learning_rate": 2.3569242068431863e-06, + "loss": 1.4883, + "step": 16214 + }, + { + "epoch": 0.9037957750404102, + "grad_norm": 0.6069961190223694, + "learning_rate": 2.354223367567926e-06, + "loss": 1.7013, + "step": 16215 + }, + { + "epoch": 0.9038515132935734, + "grad_norm": 0.5895886421203613, + "learning_rate": 2.351524039338887e-06, + "loss": 1.737, + "step": 16216 + }, + { + "epoch": 0.9039072515467366, + "grad_norm": 0.5959450006484985, + "learning_rate": 2.3488262222417067e-06, + "loss": 1.7467, + "step": 16217 + }, + { + "epoch": 0.9039629897998996, + "grad_norm": 0.5692031979560852, + "learning_rate": 2.346129916361939e-06, + "loss": 1.6631, + "step": 16218 + }, + { + "epoch": 0.9040187280530628, + "grad_norm": 0.564283549785614, + "learning_rate": 2.3434351217850815e-06, + "loss": 1.7187, + "step": 16219 + }, + { + "epoch": 0.904074466306226, + "grad_norm": 0.5690788626670837, + "learning_rate": 2.340741838596605e-06, + "loss": 1.5157, + "step": 16220 + }, + { + "epoch": 0.9041302045593891, + "grad_norm": 0.5721325278282166, + "learning_rate": 2.3380500668819193e-06, + "loss": 1.5417, + "step": 16221 + }, + { + "epoch": 0.9041859428125523, + "grad_norm": 0.5627867579460144, + "learning_rate": 2.3353598067264114e-06, + "loss": 1.6474, + "step": 16222 + }, + { + "epoch": 0.9042416810657155, + "grad_norm": 0.5417048335075378, + "learning_rate": 2.3326710582153687e-06, + "loss": 1.5528, + "step": 16223 + }, + { + "epoch": 0.9042974193188785, + "grad_norm": 0.5965459942817688, + "learning_rate": 2.3299838214340898e-06, + "loss": 1.7656, + "step": 16224 + }, + { + "epoch": 0.9043531575720417, + "grad_norm": 0.5772057175636292, + "learning_rate": 2.3272980964677947e-06, + "loss": 1.5688, + "step": 16225 + }, + { + "epoch": 0.9044088958252048, + "grad_norm": 0.5504265427589417, + "learning_rate": 2.324613883401644e-06, + "loss": 1.4842, + "step": 16226 + }, + { + "epoch": 0.904464634078368, + "grad_norm": 0.5558382868766785, + "learning_rate": 2.3219311823207748e-06, + "loss": 1.5161, + "step": 16227 + }, + { + "epoch": 0.9045203723315312, + "grad_norm": 0.5796585083007812, + "learning_rate": 2.3192499933102683e-06, + "loss": 1.6988, + "step": 16228 + }, + { + "epoch": 0.9045761105846942, + "grad_norm": 0.5768376588821411, + "learning_rate": 2.316570316455152e-06, + "loss": 1.5747, + "step": 16229 + }, + { + "epoch": 0.9046318488378574, + "grad_norm": 0.5504205226898193, + "learning_rate": 2.313892151840419e-06, + "loss": 1.5106, + "step": 16230 + }, + { + "epoch": 0.9046875870910206, + "grad_norm": 0.5408338308334351, + "learning_rate": 2.311215499550984e-06, + "loss": 1.5141, + "step": 16231 + }, + { + "epoch": 0.9047433253441837, + "grad_norm": 0.5853996872901917, + "learning_rate": 2.3085403596717623e-06, + "loss": 1.6803, + "step": 16232 + }, + { + "epoch": 0.9047990635973469, + "grad_norm": 0.5850360989570618, + "learning_rate": 2.3058667322875705e-06, + "loss": 1.718, + "step": 16233 + }, + { + "epoch": 0.90485480185051, + "grad_norm": 0.5884479284286499, + "learning_rate": 2.303194617483212e-06, + "loss": 1.7267, + "step": 16234 + }, + { + "epoch": 0.9049105401036731, + "grad_norm": 0.6016861200332642, + "learning_rate": 2.3005240153434306e-06, + "loss": 1.8153, + "step": 16235 + }, + { + "epoch": 0.9049662783568363, + "grad_norm": 0.5232079029083252, + "learning_rate": 2.2978549259529137e-06, + "loss": 1.5595, + "step": 16236 + }, + { + "epoch": 0.9050220166099995, + "grad_norm": 0.5585784912109375, + "learning_rate": 2.2951873493963274e-06, + "loss": 1.6735, + "step": 16237 + }, + { + "epoch": 0.9050777548631626, + "grad_norm": 0.5651165246963501, + "learning_rate": 2.292521285758248e-06, + "loss": 1.4991, + "step": 16238 + }, + { + "epoch": 0.9051334931163257, + "grad_norm": 0.5494994521141052, + "learning_rate": 2.2898567351232524e-06, + "loss": 1.5668, + "step": 16239 + }, + { + "epoch": 0.9051892313694889, + "grad_norm": 0.6000809669494629, + "learning_rate": 2.2871936975758234e-06, + "loss": 1.8032, + "step": 16240 + }, + { + "epoch": 0.905244969622652, + "grad_norm": 0.5880887508392334, + "learning_rate": 2.2845321732004267e-06, + "loss": 1.8109, + "step": 16241 + }, + { + "epoch": 0.9053007078758152, + "grad_norm": 0.5565019845962524, + "learning_rate": 2.2818721620814665e-06, + "loss": 1.6465, + "step": 16242 + }, + { + "epoch": 0.9053564461289784, + "grad_norm": 0.5996361374855042, + "learning_rate": 2.2792136643033036e-06, + "loss": 1.9135, + "step": 16243 + }, + { + "epoch": 0.9054121843821414, + "grad_norm": 0.5298063158988953, + "learning_rate": 2.2765566799502647e-06, + "loss": 1.4893, + "step": 16244 + }, + { + "epoch": 0.9054679226353046, + "grad_norm": 0.5619958639144897, + "learning_rate": 2.273901209106588e-06, + "loss": 1.6798, + "step": 16245 + }, + { + "epoch": 0.9055236608884678, + "grad_norm": 0.5738300681114197, + "learning_rate": 2.2712472518565065e-06, + "loss": 1.6062, + "step": 16246 + }, + { + "epoch": 0.9055793991416309, + "grad_norm": 0.5136476755142212, + "learning_rate": 2.268594808284186e-06, + "loss": 1.3619, + "step": 16247 + }, + { + "epoch": 0.9056351373947941, + "grad_norm": 0.6152523159980774, + "learning_rate": 2.2659438784737476e-06, + "loss": 1.8227, + "step": 16248 + }, + { + "epoch": 0.9056908756479571, + "grad_norm": 0.5871201753616333, + "learning_rate": 2.263294462509247e-06, + "loss": 1.7411, + "step": 16249 + }, + { + "epoch": 0.9057466139011203, + "grad_norm": 0.5907616019248962, + "learning_rate": 2.260646560474733e-06, + "loss": 1.694, + "step": 16250 + }, + { + "epoch": 0.9058023521542835, + "grad_norm": 0.5849599838256836, + "learning_rate": 2.2580001724541723e-06, + "loss": 1.6663, + "step": 16251 + }, + { + "epoch": 0.9058580904074466, + "grad_norm": 0.579804539680481, + "learning_rate": 2.2553552985314864e-06, + "loss": 1.7592, + "step": 16252 + }, + { + "epoch": 0.9059138286606098, + "grad_norm": 0.5680350661277771, + "learning_rate": 2.2527119387905582e-06, + "loss": 1.5501, + "step": 16253 + }, + { + "epoch": 0.905969566913773, + "grad_norm": 0.6235656142234802, + "learning_rate": 2.2500700933152264e-06, + "loss": 1.4766, + "step": 16254 + }, + { + "epoch": 0.906025305166936, + "grad_norm": 0.5397202968597412, + "learning_rate": 2.2474297621892628e-06, + "loss": 1.4374, + "step": 16255 + }, + { + "epoch": 0.9060810434200992, + "grad_norm": 0.5390480756759644, + "learning_rate": 2.244790945496422e-06, + "loss": 1.4, + "step": 16256 + }, + { + "epoch": 0.9061367816732624, + "grad_norm": 0.5564383268356323, + "learning_rate": 2.242153643320366e-06, + "loss": 1.5911, + "step": 16257 + }, + { + "epoch": 0.9061925199264255, + "grad_norm": 0.5558486580848694, + "learning_rate": 2.2395178557447605e-06, + "loss": 1.6573, + "step": 16258 + }, + { + "epoch": 0.9062482581795887, + "grad_norm": 0.5499858856201172, + "learning_rate": 2.2368835828531774e-06, + "loss": 1.6426, + "step": 16259 + }, + { + "epoch": 0.9063039964327518, + "grad_norm": 0.5473018288612366, + "learning_rate": 2.234250824729173e-06, + "loss": 1.6886, + "step": 16260 + }, + { + "epoch": 0.9063597346859149, + "grad_norm": 0.5679814219474792, + "learning_rate": 2.2316195814562345e-06, + "loss": 1.5702, + "step": 16261 + }, + { + "epoch": 0.9064154729390781, + "grad_norm": 0.574245274066925, + "learning_rate": 2.228989853117819e-06, + "loss": 1.6387, + "step": 16262 + }, + { + "epoch": 0.9064712111922413, + "grad_norm": 0.556791365146637, + "learning_rate": 2.226361639797325e-06, + "loss": 1.5259, + "step": 16263 + }, + { + "epoch": 0.9065269494454044, + "grad_norm": 0.5897510051727295, + "learning_rate": 2.2237349415780873e-06, + "loss": 1.6076, + "step": 16264 + }, + { + "epoch": 0.9065826876985675, + "grad_norm": 0.5262135863304138, + "learning_rate": 2.2211097585434324e-06, + "loss": 1.6696, + "step": 16265 + }, + { + "epoch": 0.9066384259517307, + "grad_norm": 0.5264698266983032, + "learning_rate": 2.2184860907766e-06, + "loss": 1.6529, + "step": 16266 + }, + { + "epoch": 0.9066941642048938, + "grad_norm": 0.5501774549484253, + "learning_rate": 2.215863938360807e-06, + "loss": 1.5219, + "step": 16267 + }, + { + "epoch": 0.906749902458057, + "grad_norm": 0.5458822250366211, + "learning_rate": 2.2132433013792087e-06, + "loss": 1.5906, + "step": 16268 + }, + { + "epoch": 0.9068056407112202, + "grad_norm": 0.5708175301551819, + "learning_rate": 2.2106241799149165e-06, + "loss": 1.6548, + "step": 16269 + }, + { + "epoch": 0.9068613789643832, + "grad_norm": 0.5546550750732422, + "learning_rate": 2.208006574050997e-06, + "loss": 1.6273, + "step": 16270 + }, + { + "epoch": 0.9069171172175464, + "grad_norm": 0.5719642043113708, + "learning_rate": 2.2053904838704564e-06, + "loss": 1.6253, + "step": 16271 + }, + { + "epoch": 0.9069728554707095, + "grad_norm": 0.5788507461547852, + "learning_rate": 2.2027759094562726e-06, + "loss": 1.5816, + "step": 16272 + }, + { + "epoch": 0.9070285937238727, + "grad_norm": 0.6040105819702148, + "learning_rate": 2.200162850891352e-06, + "loss": 1.8245, + "step": 16273 + }, + { + "epoch": 0.9070843319770359, + "grad_norm": 0.5602688789367676, + "learning_rate": 2.1975513082585885e-06, + "loss": 1.6826, + "step": 16274 + }, + { + "epoch": 0.9071400702301989, + "grad_norm": 0.5587949752807617, + "learning_rate": 2.194941281640772e-06, + "loss": 1.4705, + "step": 16275 + }, + { + "epoch": 0.9071958084833621, + "grad_norm": 0.6179760098457336, + "learning_rate": 2.192332771120703e-06, + "loss": 1.8863, + "step": 16276 + }, + { + "epoch": 0.9072515467365253, + "grad_norm": 0.5368984341621399, + "learning_rate": 2.189725776781104e-06, + "loss": 1.5036, + "step": 16277 + }, + { + "epoch": 0.9073072849896884, + "grad_norm": 0.5557940006256104, + "learning_rate": 2.187120298704648e-06, + "loss": 1.7201, + "step": 16278 + }, + { + "epoch": 0.9073630232428516, + "grad_norm": 0.5269171595573425, + "learning_rate": 2.184516336973963e-06, + "loss": 1.4208, + "step": 16279 + }, + { + "epoch": 0.9074187614960147, + "grad_norm": 0.5811324119567871, + "learning_rate": 2.1819138916716386e-06, + "loss": 1.6301, + "step": 16280 + }, + { + "epoch": 0.9074744997491778, + "grad_norm": 0.5921099781990051, + "learning_rate": 2.179312962880209e-06, + "loss": 1.756, + "step": 16281 + }, + { + "epoch": 0.907530238002341, + "grad_norm": 0.5625371932983398, + "learning_rate": 2.1767135506821636e-06, + "loss": 1.5911, + "step": 16282 + }, + { + "epoch": 0.9075859762555042, + "grad_norm": 0.5526474714279175, + "learning_rate": 2.1741156551599196e-06, + "loss": 1.6621, + "step": 16283 + }, + { + "epoch": 0.9076417145086673, + "grad_norm": 0.5928450226783752, + "learning_rate": 2.1715192763959e-06, + "loss": 1.6103, + "step": 16284 + }, + { + "epoch": 0.9076974527618304, + "grad_norm": 0.5777646899223328, + "learning_rate": 2.1689244144724173e-06, + "loss": 1.8086, + "step": 16285 + }, + { + "epoch": 0.9077531910149936, + "grad_norm": 0.5837210416793823, + "learning_rate": 2.1663310694717832e-06, + "loss": 1.7998, + "step": 16286 + }, + { + "epoch": 0.9078089292681567, + "grad_norm": 0.5362181663513184, + "learning_rate": 2.163739241476237e-06, + "loss": 1.4457, + "step": 16287 + }, + { + "epoch": 0.9078646675213199, + "grad_norm": 0.5136518478393555, + "learning_rate": 2.1611489305679743e-06, + "loss": 1.3774, + "step": 16288 + }, + { + "epoch": 0.9079204057744831, + "grad_norm": 0.5325779318809509, + "learning_rate": 2.1585601368291574e-06, + "loss": 1.5493, + "step": 16289 + }, + { + "epoch": 0.9079761440276461, + "grad_norm": 0.6524935364723206, + "learning_rate": 2.155972860341865e-06, + "loss": 1.6492, + "step": 16290 + }, + { + "epoch": 0.9080318822808093, + "grad_norm": 0.5504276156425476, + "learning_rate": 2.1533871011881757e-06, + "loss": 1.5392, + "step": 16291 + }, + { + "epoch": 0.9080876205339725, + "grad_norm": 0.5825825929641724, + "learning_rate": 2.150802859450074e-06, + "loss": 1.6312, + "step": 16292 + }, + { + "epoch": 0.9081433587871356, + "grad_norm": 0.5898470878601074, + "learning_rate": 2.1482201352095275e-06, + "loss": 1.7963, + "step": 16293 + }, + { + "epoch": 0.9081990970402988, + "grad_norm": 0.5645402669906616, + "learning_rate": 2.1456389285484437e-06, + "loss": 1.529, + "step": 16294 + }, + { + "epoch": 0.9082548352934618, + "grad_norm": 0.5600345134735107, + "learning_rate": 2.143059239548678e-06, + "loss": 1.4003, + "step": 16295 + }, + { + "epoch": 0.908310573546625, + "grad_norm": 0.5579517483711243, + "learning_rate": 2.140481068292061e-06, + "loss": 1.6012, + "step": 16296 + }, + { + "epoch": 0.9083663117997882, + "grad_norm": 0.5682119727134705, + "learning_rate": 2.137904414860331e-06, + "loss": 1.6037, + "step": 16297 + }, + { + "epoch": 0.9084220500529513, + "grad_norm": 0.6124076843261719, + "learning_rate": 2.135329279335224e-06, + "loss": 1.5799, + "step": 16298 + }, + { + "epoch": 0.9084777883061145, + "grad_norm": 0.5528500080108643, + "learning_rate": 2.132755661798397e-06, + "loss": 1.5622, + "step": 16299 + }, + { + "epoch": 0.9085335265592777, + "grad_norm": 0.6142159104347229, + "learning_rate": 2.1301835623314836e-06, + "loss": 1.6835, + "step": 16300 + }, + { + "epoch": 0.9085892648124407, + "grad_norm": 0.5384484529495239, + "learning_rate": 2.127612981016036e-06, + "loss": 1.6256, + "step": 16301 + }, + { + "epoch": 0.9086450030656039, + "grad_norm": 0.5860117077827454, + "learning_rate": 2.1250439179335946e-06, + "loss": 1.8222, + "step": 16302 + }, + { + "epoch": 0.9087007413187671, + "grad_norm": 0.6375497579574585, + "learning_rate": 2.122476373165633e-06, + "loss": 1.7279, + "step": 16303 + }, + { + "epoch": 0.9087564795719302, + "grad_norm": 0.6110420227050781, + "learning_rate": 2.1199103467935744e-06, + "loss": 1.6672, + "step": 16304 + }, + { + "epoch": 0.9088122178250934, + "grad_norm": 0.572277843952179, + "learning_rate": 2.117345838898793e-06, + "loss": 1.6559, + "step": 16305 + }, + { + "epoch": 0.9088679560782565, + "grad_norm": 0.5324705243110657, + "learning_rate": 2.1147828495626298e-06, + "loss": 1.5189, + "step": 16306 + }, + { + "epoch": 0.9089236943314196, + "grad_norm": 0.5452579259872437, + "learning_rate": 2.112221378866369e-06, + "loss": 1.6515, + "step": 16307 + }, + { + "epoch": 0.9089794325845828, + "grad_norm": 0.652783989906311, + "learning_rate": 2.109661426891241e-06, + "loss": 1.6793, + "step": 16308 + }, + { + "epoch": 0.909035170837746, + "grad_norm": 0.5870492458343506, + "learning_rate": 2.107102993718424e-06, + "loss": 1.6749, + "step": 16309 + }, + { + "epoch": 0.9090909090909091, + "grad_norm": 0.5540602803230286, + "learning_rate": 2.1045460794290704e-06, + "loss": 1.6496, + "step": 16310 + }, + { + "epoch": 0.9091466473440722, + "grad_norm": 0.5487245917320251, + "learning_rate": 2.101990684104266e-06, + "loss": 1.6938, + "step": 16311 + }, + { + "epoch": 0.9092023855972354, + "grad_norm": 0.5633036494255066, + "learning_rate": 2.0994368078250503e-06, + "loss": 1.7482, + "step": 16312 + }, + { + "epoch": 0.9092581238503985, + "grad_norm": 0.5988346338272095, + "learning_rate": 2.0968844506724204e-06, + "loss": 2.0318, + "step": 16313 + }, + { + "epoch": 0.9093138621035617, + "grad_norm": 0.5486369729042053, + "learning_rate": 2.094333612727317e-06, + "loss": 1.63, + "step": 16314 + }, + { + "epoch": 0.9093696003567249, + "grad_norm": 0.5369518995285034, + "learning_rate": 2.091784294070653e-06, + "loss": 1.6674, + "step": 16315 + }, + { + "epoch": 0.909425338609888, + "grad_norm": 0.5641408562660217, + "learning_rate": 2.0892364947832534e-06, + "loss": 1.6477, + "step": 16316 + }, + { + "epoch": 0.9094810768630511, + "grad_norm": 0.6651021838188171, + "learning_rate": 2.0866902149459466e-06, + "loss": 1.5441, + "step": 16317 + }, + { + "epoch": 0.9095368151162142, + "grad_norm": 0.5467895865440369, + "learning_rate": 2.0841454546394633e-06, + "loss": 1.527, + "step": 16318 + }, + { + "epoch": 0.9095925533693774, + "grad_norm": 0.5849424004554749, + "learning_rate": 2.0816022139445167e-06, + "loss": 1.7746, + "step": 16319 + }, + { + "epoch": 0.9096482916225406, + "grad_norm": 0.5678523778915405, + "learning_rate": 2.07906049294177e-06, + "loss": 1.6312, + "step": 16320 + }, + { + "epoch": 0.9097040298757036, + "grad_norm": 0.574133574962616, + "learning_rate": 2.0765202917118198e-06, + "loss": 1.6555, + "step": 16321 + }, + { + "epoch": 0.9097597681288668, + "grad_norm": 0.6076043844223022, + "learning_rate": 2.0739816103352404e-06, + "loss": 1.4457, + "step": 16322 + }, + { + "epoch": 0.90981550638203, + "grad_norm": 0.6198605895042419, + "learning_rate": 2.071444448892529e-06, + "loss": 1.8818, + "step": 16323 + }, + { + "epoch": 0.9098712446351931, + "grad_norm": 0.5919679999351501, + "learning_rate": 2.0689088074641593e-06, + "loss": 1.6588, + "step": 16324 + }, + { + "epoch": 0.9099269828883563, + "grad_norm": 0.5595120787620544, + "learning_rate": 2.0663746861305457e-06, + "loss": 1.5367, + "step": 16325 + }, + { + "epoch": 0.9099827211415195, + "grad_norm": 0.5503993034362793, + "learning_rate": 2.0638420849720565e-06, + "loss": 1.5971, + "step": 16326 + }, + { + "epoch": 0.9100384593946825, + "grad_norm": 0.5758650302886963, + "learning_rate": 2.061311004069e-06, + "loss": 1.7707, + "step": 16327 + }, + { + "epoch": 0.9100941976478457, + "grad_norm": 0.5886837244033813, + "learning_rate": 2.058781443501662e-06, + "loss": 1.7856, + "step": 16328 + }, + { + "epoch": 0.9101499359010089, + "grad_norm": 0.5453135371208191, + "learning_rate": 2.056253403350267e-06, + "loss": 1.4072, + "step": 16329 + }, + { + "epoch": 0.910205674154172, + "grad_norm": 0.5898021459579468, + "learning_rate": 2.0537268836949784e-06, + "loss": 1.6138, + "step": 16330 + }, + { + "epoch": 0.9102614124073352, + "grad_norm": 0.5901027321815491, + "learning_rate": 2.051201884615922e-06, + "loss": 1.7281, + "step": 16331 + }, + { + "epoch": 0.9103171506604983, + "grad_norm": 0.5659447312355042, + "learning_rate": 2.048678406193183e-06, + "loss": 1.8754, + "step": 16332 + }, + { + "epoch": 0.9103728889136614, + "grad_norm": 0.5723013877868652, + "learning_rate": 2.046156448506786e-06, + "loss": 1.6788, + "step": 16333 + }, + { + "epoch": 0.9104286271668246, + "grad_norm": 0.5516445636749268, + "learning_rate": 2.0436360116367236e-06, + "loss": 1.5839, + "step": 16334 + }, + { + "epoch": 0.9104843654199878, + "grad_norm": 0.5594833493232727, + "learning_rate": 2.0411170956629143e-06, + "loss": 1.6303, + "step": 16335 + }, + { + "epoch": 0.9105401036731509, + "grad_norm": 0.5574612617492676, + "learning_rate": 2.0385997006652614e-06, + "loss": 1.6719, + "step": 16336 + }, + { + "epoch": 0.910595841926314, + "grad_norm": 0.6043298244476318, + "learning_rate": 2.0360838267235837e-06, + "loss": 1.6495, + "step": 16337 + }, + { + "epoch": 0.9106515801794772, + "grad_norm": 0.5330505967140198, + "learning_rate": 2.0335694739176793e-06, + "loss": 1.6592, + "step": 16338 + }, + { + "epoch": 0.9107073184326403, + "grad_norm": 0.6119699478149414, + "learning_rate": 2.0310566423272893e-06, + "loss": 1.6613, + "step": 16339 + }, + { + "epoch": 0.9107630566858035, + "grad_norm": 0.5507022142410278, + "learning_rate": 2.0285453320321003e-06, + "loss": 1.4194, + "step": 16340 + }, + { + "epoch": 0.9108187949389666, + "grad_norm": 0.5497919321060181, + "learning_rate": 2.0260355431117707e-06, + "loss": 1.4815, + "step": 16341 + }, + { + "epoch": 0.9108745331921297, + "grad_norm": 0.5851951241493225, + "learning_rate": 2.02352727564587e-06, + "loss": 1.6783, + "step": 16342 + }, + { + "epoch": 0.9109302714452929, + "grad_norm": 0.5943406820297241, + "learning_rate": 2.0210205297139794e-06, + "loss": 1.8243, + "step": 16343 + }, + { + "epoch": 0.910986009698456, + "grad_norm": 0.5871433019638062, + "learning_rate": 2.0185153053955684e-06, + "loss": 1.6776, + "step": 16344 + }, + { + "epoch": 0.9110417479516192, + "grad_norm": 0.5993211269378662, + "learning_rate": 2.0160116027701014e-06, + "loss": 1.8912, + "step": 16345 + }, + { + "epoch": 0.9110974862047824, + "grad_norm": 0.5340527892112732, + "learning_rate": 2.0135094219169814e-06, + "loss": 1.5518, + "step": 16346 + }, + { + "epoch": 0.9111532244579454, + "grad_norm": 0.5467515587806702, + "learning_rate": 2.0110087629155614e-06, + "loss": 1.623, + "step": 16347 + }, + { + "epoch": 0.9112089627111086, + "grad_norm": 0.518818199634552, + "learning_rate": 2.0085096258451563e-06, + "loss": 1.4222, + "step": 16348 + }, + { + "epoch": 0.9112647009642718, + "grad_norm": 0.5602338314056396, + "learning_rate": 2.0060120107850078e-06, + "loss": 1.3592, + "step": 16349 + }, + { + "epoch": 0.9113204392174349, + "grad_norm": 0.5352469682693481, + "learning_rate": 2.0035159178143358e-06, + "loss": 1.4282, + "step": 16350 + }, + { + "epoch": 0.9113761774705981, + "grad_norm": 0.556150496006012, + "learning_rate": 2.0010213470123e-06, + "loss": 1.6585, + "step": 16351 + }, + { + "epoch": 0.9114319157237613, + "grad_norm": 0.560319185256958, + "learning_rate": 1.998528298458019e-06, + "loss": 1.548, + "step": 16352 + }, + { + "epoch": 0.9114876539769243, + "grad_norm": 0.5751150250434875, + "learning_rate": 1.9960367722305416e-06, + "loss": 1.5965, + "step": 16353 + }, + { + "epoch": 0.9115433922300875, + "grad_norm": 0.5204324722290039, + "learning_rate": 1.993546768408899e-06, + "loss": 1.6278, + "step": 16354 + }, + { + "epoch": 0.9115991304832507, + "grad_norm": 0.5589833855628967, + "learning_rate": 1.9910582870720616e-06, + "loss": 1.5308, + "step": 16355 + }, + { + "epoch": 0.9116548687364138, + "grad_norm": 0.5939486026763916, + "learning_rate": 1.9885713282989383e-06, + "loss": 1.7062, + "step": 16356 + }, + { + "epoch": 0.911710606989577, + "grad_norm": 0.5556850433349609, + "learning_rate": 1.98608589216841e-06, + "loss": 1.5839, + "step": 16357 + }, + { + "epoch": 0.9117663452427401, + "grad_norm": 0.5494816899299622, + "learning_rate": 1.983601978759292e-06, + "loss": 1.5855, + "step": 16358 + }, + { + "epoch": 0.9118220834959032, + "grad_norm": 0.5849503874778748, + "learning_rate": 1.9811195881503707e-06, + "loss": 1.5939, + "step": 16359 + }, + { + "epoch": 0.9118778217490664, + "grad_norm": 0.6211272478103638, + "learning_rate": 1.978638720420356e-06, + "loss": 1.8301, + "step": 16360 + }, + { + "epoch": 0.9119335600022296, + "grad_norm": 0.6557322144508362, + "learning_rate": 1.976159375647946e-06, + "loss": 1.6721, + "step": 16361 + }, + { + "epoch": 0.9119892982553927, + "grad_norm": 0.6447960138320923, + "learning_rate": 1.973681553911766e-06, + "loss": 1.4492, + "step": 16362 + }, + { + "epoch": 0.9120450365085558, + "grad_norm": 0.5334677696228027, + "learning_rate": 1.971205255290387e-06, + "loss": 1.3443, + "step": 16363 + }, + { + "epoch": 0.9121007747617189, + "grad_norm": 0.5457823276519775, + "learning_rate": 1.9687304798623465e-06, + "loss": 1.6671, + "step": 16364 + }, + { + "epoch": 0.9121565130148821, + "grad_norm": 0.569832980632782, + "learning_rate": 1.966257227706142e-06, + "loss": 1.8718, + "step": 16365 + }, + { + "epoch": 0.9122122512680453, + "grad_norm": 0.6242331266403198, + "learning_rate": 1.9637854989001947e-06, + "loss": 1.8048, + "step": 16366 + }, + { + "epoch": 0.9122679895212084, + "grad_norm": 0.588097870349884, + "learning_rate": 1.9613152935229082e-06, + "loss": 1.7361, + "step": 16367 + }, + { + "epoch": 0.9123237277743715, + "grad_norm": 0.5257436037063599, + "learning_rate": 1.9588466116526092e-06, + "loss": 1.5224, + "step": 16368 + }, + { + "epoch": 0.9123794660275347, + "grad_norm": 0.5604174733161926, + "learning_rate": 1.9563794533676016e-06, + "loss": 1.6835, + "step": 16369 + }, + { + "epoch": 0.9124352042806978, + "grad_norm": 0.5166577696800232, + "learning_rate": 1.9539138187461225e-06, + "loss": 1.5155, + "step": 16370 + }, + { + "epoch": 0.912490942533861, + "grad_norm": 0.5879610776901245, + "learning_rate": 1.9514497078663653e-06, + "loss": 1.6996, + "step": 16371 + }, + { + "epoch": 0.9125466807870242, + "grad_norm": 0.5442944765090942, + "learning_rate": 1.9489871208064835e-06, + "loss": 1.6456, + "step": 16372 + }, + { + "epoch": 0.9126024190401872, + "grad_norm": 0.6130040287971497, + "learning_rate": 1.9465260576445708e-06, + "loss": 1.8207, + "step": 16373 + }, + { + "epoch": 0.9126581572933504, + "grad_norm": 0.5738656520843506, + "learning_rate": 1.944066518458687e-06, + "loss": 1.8296, + "step": 16374 + }, + { + "epoch": 0.9127138955465136, + "grad_norm": 0.5759257078170776, + "learning_rate": 1.941608503326825e-06, + "loss": 1.942, + "step": 16375 + }, + { + "epoch": 0.9127696337996767, + "grad_norm": 0.6239985227584839, + "learning_rate": 1.939152012326939e-06, + "loss": 1.792, + "step": 16376 + }, + { + "epoch": 0.9128253720528399, + "grad_norm": 0.6275523900985718, + "learning_rate": 1.936697045536934e-06, + "loss": 1.8032, + "step": 16377 + }, + { + "epoch": 0.912881110306003, + "grad_norm": 0.6044204831123352, + "learning_rate": 1.93424360303468e-06, + "loss": 1.9287, + "step": 16378 + }, + { + "epoch": 0.9129368485591661, + "grad_norm": 0.5985537171363831, + "learning_rate": 1.9317916848979657e-06, + "loss": 1.8145, + "step": 16379 + }, + { + "epoch": 0.9129925868123293, + "grad_norm": 0.5529384613037109, + "learning_rate": 1.929341291204567e-06, + "loss": 1.4588, + "step": 16380 + }, + { + "epoch": 0.9130483250654925, + "grad_norm": 0.608033299446106, + "learning_rate": 1.926892422032195e-06, + "loss": 1.8245, + "step": 16381 + }, + { + "epoch": 0.9131040633186556, + "grad_norm": 0.5728061199188232, + "learning_rate": 1.9244450774585033e-06, + "loss": 1.687, + "step": 16382 + }, + { + "epoch": 0.9131598015718188, + "grad_norm": 0.5595676302909851, + "learning_rate": 1.9219992575611133e-06, + "loss": 1.7481, + "step": 16383 + }, + { + "epoch": 0.9132155398249819, + "grad_norm": 0.5918931365013123, + "learning_rate": 1.9195549624175967e-06, + "loss": 1.7939, + "step": 16384 + }, + { + "epoch": 0.913271278078145, + "grad_norm": 0.5507239103317261, + "learning_rate": 1.9171121921054747e-06, + "loss": 1.5386, + "step": 16385 + }, + { + "epoch": 0.9133270163313082, + "grad_norm": 0.5711354613304138, + "learning_rate": 1.914670946702196e-06, + "loss": 1.6413, + "step": 16386 + }, + { + "epoch": 0.9133827545844713, + "grad_norm": 0.5676741600036621, + "learning_rate": 1.912231226285205e-06, + "loss": 1.4792, + "step": 16387 + }, + { + "epoch": 0.9134384928376345, + "grad_norm": 0.6302747130393982, + "learning_rate": 1.9097930309318724e-06, + "loss": 1.5589, + "step": 16388 + }, + { + "epoch": 0.9134942310907976, + "grad_norm": 0.5529274344444275, + "learning_rate": 1.9073563607195145e-06, + "loss": 1.4047, + "step": 16389 + }, + { + "epoch": 0.9135499693439607, + "grad_norm": 0.562939465045929, + "learning_rate": 1.9049212157254138e-06, + "loss": 1.5307, + "step": 16390 + }, + { + "epoch": 0.9136057075971239, + "grad_norm": 0.5679606795310974, + "learning_rate": 1.9024875960267975e-06, + "loss": 1.6551, + "step": 16391 + }, + { + "epoch": 0.9136614458502871, + "grad_norm": 0.5608037114143372, + "learning_rate": 1.900055501700848e-06, + "loss": 1.5454, + "step": 16392 + }, + { + "epoch": 0.9137171841034502, + "grad_norm": 0.5579122304916382, + "learning_rate": 1.8976249328247042e-06, + "loss": 1.8315, + "step": 16393 + }, + { + "epoch": 0.9137729223566133, + "grad_norm": 0.5809940099716187, + "learning_rate": 1.8951958894754264e-06, + "loss": 1.6967, + "step": 16394 + }, + { + "epoch": 0.9138286606097765, + "grad_norm": 0.5494776368141174, + "learning_rate": 1.892768371730075e-06, + "loss": 1.5542, + "step": 16395 + }, + { + "epoch": 0.9138843988629396, + "grad_norm": 0.5633254051208496, + "learning_rate": 1.8903423796656216e-06, + "loss": 1.6167, + "step": 16396 + }, + { + "epoch": 0.9139401371161028, + "grad_norm": 0.6057842373847961, + "learning_rate": 1.8879179133590107e-06, + "loss": 1.5031, + "step": 16397 + }, + { + "epoch": 0.913995875369266, + "grad_norm": 0.5395832061767578, + "learning_rate": 1.8854949728871308e-06, + "loss": 1.526, + "step": 16398 + }, + { + "epoch": 0.914051613622429, + "grad_norm": 0.5238010883331299, + "learning_rate": 1.88307355832682e-06, + "loss": 1.5379, + "step": 16399 + }, + { + "epoch": 0.9141073518755922, + "grad_norm": 0.5353637337684631, + "learning_rate": 1.8806536697548838e-06, + "loss": 1.6934, + "step": 16400 + }, + { + "epoch": 0.9141630901287554, + "grad_norm": 0.5515512228012085, + "learning_rate": 1.878235307248044e-06, + "loss": 1.601, + "step": 16401 + }, + { + "epoch": 0.9142188283819185, + "grad_norm": 0.5203688740730286, + "learning_rate": 1.875818470883023e-06, + "loss": 1.4037, + "step": 16402 + }, + { + "epoch": 0.9142745666350817, + "grad_norm": 0.5910791754722595, + "learning_rate": 1.8734031607364532e-06, + "loss": 1.5897, + "step": 16403 + }, + { + "epoch": 0.9143303048882448, + "grad_norm": 0.6479304432868958, + "learning_rate": 1.8709893768849406e-06, + "loss": 1.5717, + "step": 16404 + }, + { + "epoch": 0.9143860431414079, + "grad_norm": 0.5512206554412842, + "learning_rate": 1.868577119405024e-06, + "loss": 1.4539, + "step": 16405 + }, + { + "epoch": 0.9144417813945711, + "grad_norm": 0.5331587791442871, + "learning_rate": 1.8661663883732195e-06, + "loss": 1.5421, + "step": 16406 + }, + { + "epoch": 0.9144975196477343, + "grad_norm": 0.5025634169578552, + "learning_rate": 1.8637571838659828e-06, + "loss": 1.1721, + "step": 16407 + }, + { + "epoch": 0.9145532579008974, + "grad_norm": 0.5516257882118225, + "learning_rate": 1.8613495059597086e-06, + "loss": 1.6126, + "step": 16408 + }, + { + "epoch": 0.9146089961540605, + "grad_norm": 0.5576212406158447, + "learning_rate": 1.8589433547307633e-06, + "loss": 1.7637, + "step": 16409 + }, + { + "epoch": 0.9146647344072236, + "grad_norm": 0.5739085078239441, + "learning_rate": 1.8565387302554527e-06, + "loss": 1.7126, + "step": 16410 + }, + { + "epoch": 0.9147204726603868, + "grad_norm": 0.5299978852272034, + "learning_rate": 1.8541356326100433e-06, + "loss": 1.4304, + "step": 16411 + }, + { + "epoch": 0.91477621091355, + "grad_norm": 0.5288132429122925, + "learning_rate": 1.8517340618707247e-06, + "loss": 1.2973, + "step": 16412 + }, + { + "epoch": 0.9148319491667131, + "grad_norm": 0.5455918312072754, + "learning_rate": 1.8493340181136908e-06, + "loss": 1.5642, + "step": 16413 + }, + { + "epoch": 0.9148876874198762, + "grad_norm": 0.5809057950973511, + "learning_rate": 1.846935501415048e-06, + "loss": 1.6875, + "step": 16414 + }, + { + "epoch": 0.9149434256730394, + "grad_norm": 0.5612070560455322, + "learning_rate": 1.8445385118508517e-06, + "loss": 1.6338, + "step": 16415 + }, + { + "epoch": 0.9149991639262025, + "grad_norm": 0.5714902877807617, + "learning_rate": 1.8421430494971248e-06, + "loss": 1.6241, + "step": 16416 + }, + { + "epoch": 0.9150549021793657, + "grad_norm": 0.5890349745750427, + "learning_rate": 1.839749114429845e-06, + "loss": 1.7354, + "step": 16417 + }, + { + "epoch": 0.9151106404325289, + "grad_norm": 0.5912462472915649, + "learning_rate": 1.8373567067249298e-06, + "loss": 1.7374, + "step": 16418 + }, + { + "epoch": 0.915166378685692, + "grad_norm": 0.5817426443099976, + "learning_rate": 1.834965826458257e-06, + "loss": 1.7834, + "step": 16419 + }, + { + "epoch": 0.9152221169388551, + "grad_norm": 0.5936219692230225, + "learning_rate": 1.8325764737056328e-06, + "loss": 1.8441, + "step": 16420 + }, + { + "epoch": 0.9152778551920183, + "grad_norm": 0.5384576320648193, + "learning_rate": 1.8301886485428632e-06, + "loss": 1.5443, + "step": 16421 + }, + { + "epoch": 0.9153335934451814, + "grad_norm": 0.5196239948272705, + "learning_rate": 1.8278023510456543e-06, + "loss": 1.3697, + "step": 16422 + }, + { + "epoch": 0.9153893316983446, + "grad_norm": 0.5763368010520935, + "learning_rate": 1.82541758128969e-06, + "loss": 1.6132, + "step": 16423 + }, + { + "epoch": 0.9154450699515078, + "grad_norm": 0.5932090878486633, + "learning_rate": 1.823034339350599e-06, + "loss": 1.7383, + "step": 16424 + }, + { + "epoch": 0.9155008082046708, + "grad_norm": 0.534191906452179, + "learning_rate": 1.8206526253039702e-06, + "loss": 1.5158, + "step": 16425 + }, + { + "epoch": 0.915556546457834, + "grad_norm": 0.556568443775177, + "learning_rate": 1.8182724392253437e-06, + "loss": 1.5575, + "step": 16426 + }, + { + "epoch": 0.9156122847109972, + "grad_norm": 0.570776641368866, + "learning_rate": 1.815893781190181e-06, + "loss": 1.8494, + "step": 16427 + }, + { + "epoch": 0.9156680229641603, + "grad_norm": 0.5521082282066345, + "learning_rate": 1.81351665127395e-06, + "loss": 1.489, + "step": 16428 + }, + { + "epoch": 0.9157237612173235, + "grad_norm": 0.5504701137542725, + "learning_rate": 1.811141049552012e-06, + "loss": 1.5362, + "step": 16429 + }, + { + "epoch": 0.9157794994704866, + "grad_norm": 0.6085372567176819, + "learning_rate": 1.8087669760997295e-06, + "loss": 1.6659, + "step": 16430 + }, + { + "epoch": 0.9158352377236497, + "grad_norm": 0.587598979473114, + "learning_rate": 1.8063944309923752e-06, + "loss": 1.6386, + "step": 16431 + }, + { + "epoch": 0.9158909759768129, + "grad_norm": 0.5368753671646118, + "learning_rate": 1.804023414305206e-06, + "loss": 1.6515, + "step": 16432 + }, + { + "epoch": 0.915946714229976, + "grad_norm": 0.5684150457382202, + "learning_rate": 1.8016539261134113e-06, + "loss": 1.4344, + "step": 16433 + }, + { + "epoch": 0.9160024524831392, + "grad_norm": 0.551999568939209, + "learning_rate": 1.7992859664921424e-06, + "loss": 1.5954, + "step": 16434 + }, + { + "epoch": 0.9160581907363023, + "grad_norm": 0.571282148361206, + "learning_rate": 1.7969195355164836e-06, + "loss": 1.7711, + "step": 16435 + }, + { + "epoch": 0.9161139289894654, + "grad_norm": 0.5832626819610596, + "learning_rate": 1.794554633261497e-06, + "loss": 1.635, + "step": 16436 + }, + { + "epoch": 0.9161696672426286, + "grad_norm": 0.6278531551361084, + "learning_rate": 1.7921912598021895e-06, + "loss": 1.8298, + "step": 16437 + }, + { + "epoch": 0.9162254054957918, + "grad_norm": 0.5460119247436523, + "learning_rate": 1.7898294152134899e-06, + "loss": 1.511, + "step": 16438 + }, + { + "epoch": 0.9162811437489549, + "grad_norm": 0.5607736706733704, + "learning_rate": 1.7874690995703213e-06, + "loss": 1.6774, + "step": 16439 + }, + { + "epoch": 0.916336882002118, + "grad_norm": 0.5553047060966492, + "learning_rate": 1.785110312947541e-06, + "loss": 1.6264, + "step": 16440 + }, + { + "epoch": 0.9163926202552812, + "grad_norm": 0.5573118329048157, + "learning_rate": 1.7827530554199445e-06, + "loss": 1.5843, + "step": 16441 + }, + { + "epoch": 0.9164483585084443, + "grad_norm": 0.5777952075004578, + "learning_rate": 1.7803973270622943e-06, + "loss": 1.5035, + "step": 16442 + }, + { + "epoch": 0.9165040967616075, + "grad_norm": 0.5638415813446045, + "learning_rate": 1.7780431279493027e-06, + "loss": 1.6238, + "step": 16443 + }, + { + "epoch": 0.9165598350147707, + "grad_norm": 0.5762361288070679, + "learning_rate": 1.7756904581556265e-06, + "loss": 1.5588, + "step": 16444 + }, + { + "epoch": 0.9166155732679337, + "grad_norm": 0.5966445207595825, + "learning_rate": 1.77333931775589e-06, + "loss": 1.6715, + "step": 16445 + }, + { + "epoch": 0.9166713115210969, + "grad_norm": 0.5778394341468811, + "learning_rate": 1.7709897068246385e-06, + "loss": 1.626, + "step": 16446 + }, + { + "epoch": 0.9167270497742601, + "grad_norm": 0.5755835175514221, + "learning_rate": 1.7686416254364068e-06, + "loss": 1.622, + "step": 16447 + }, + { + "epoch": 0.9167827880274232, + "grad_norm": 0.5625899434089661, + "learning_rate": 1.7662950736656524e-06, + "loss": 1.5325, + "step": 16448 + }, + { + "epoch": 0.9168385262805864, + "grad_norm": 0.5442537069320679, + "learning_rate": 1.7639500515867934e-06, + "loss": 1.6706, + "step": 16449 + }, + { + "epoch": 0.9168942645337496, + "grad_norm": 0.5656050443649292, + "learning_rate": 1.7616065592742038e-06, + "loss": 1.4834, + "step": 16450 + }, + { + "epoch": 0.9169500027869126, + "grad_norm": 0.5210759043693542, + "learning_rate": 1.7592645968022015e-06, + "loss": 1.5534, + "step": 16451 + }, + { + "epoch": 0.9170057410400758, + "grad_norm": 0.5299588441848755, + "learning_rate": 1.7569241642450774e-06, + "loss": 1.5757, + "step": 16452 + }, + { + "epoch": 0.917061479293239, + "grad_norm": 0.5570264458656311, + "learning_rate": 1.754585261677022e-06, + "loss": 1.7064, + "step": 16453 + }, + { + "epoch": 0.9171172175464021, + "grad_norm": 0.5452120304107666, + "learning_rate": 1.7522478891722483e-06, + "loss": 1.5926, + "step": 16454 + }, + { + "epoch": 0.9171729557995653, + "grad_norm": 0.574564516544342, + "learning_rate": 1.7499120468048635e-06, + "loss": 1.6621, + "step": 16455 + }, + { + "epoch": 0.9172286940527283, + "grad_norm": 0.5752410292625427, + "learning_rate": 1.747577734648953e-06, + "loss": 1.6868, + "step": 16456 + }, + { + "epoch": 0.9172844323058915, + "grad_norm": 0.5618624687194824, + "learning_rate": 1.7452449527785353e-06, + "loss": 1.5867, + "step": 16457 + }, + { + "epoch": 0.9173401705590547, + "grad_norm": 0.5668958425521851, + "learning_rate": 1.7429137012676066e-06, + "loss": 1.7146, + "step": 16458 + }, + { + "epoch": 0.9173959088122178, + "grad_norm": 0.5456563234329224, + "learning_rate": 1.7405839801901026e-06, + "loss": 1.5809, + "step": 16459 + }, + { + "epoch": 0.917451647065381, + "grad_norm": 0.5776280164718628, + "learning_rate": 1.7382557896199025e-06, + "loss": 1.6357, + "step": 16460 + }, + { + "epoch": 0.9175073853185441, + "grad_norm": 0.5580477118492126, + "learning_rate": 1.7359291296308365e-06, + "loss": 1.522, + "step": 16461 + }, + { + "epoch": 0.9175631235717072, + "grad_norm": 0.5477070212364197, + "learning_rate": 1.7336040002967069e-06, + "loss": 1.5754, + "step": 16462 + }, + { + "epoch": 0.9176188618248704, + "grad_norm": 0.536621630191803, + "learning_rate": 1.7312804016912433e-06, + "loss": 1.514, + "step": 16463 + }, + { + "epoch": 0.9176746000780336, + "grad_norm": 0.5977050065994263, + "learning_rate": 1.7289583338881365e-06, + "loss": 1.7679, + "step": 16464 + }, + { + "epoch": 0.9177303383311967, + "grad_norm": 0.5983988642692566, + "learning_rate": 1.7266377969610281e-06, + "loss": 1.8285, + "step": 16465 + }, + { + "epoch": 0.9177860765843598, + "grad_norm": 0.5651358962059021, + "learning_rate": 1.7243187909835257e-06, + "loss": 1.6595, + "step": 16466 + }, + { + "epoch": 0.917841814837523, + "grad_norm": 0.556364893913269, + "learning_rate": 1.7220013160291592e-06, + "loss": 1.5281, + "step": 16467 + }, + { + "epoch": 0.9178975530906861, + "grad_norm": 0.5568684935569763, + "learning_rate": 1.7196853721714313e-06, + "loss": 1.677, + "step": 16468 + }, + { + "epoch": 0.9179532913438493, + "grad_norm": 0.5776600241661072, + "learning_rate": 1.7173709594837884e-06, + "loss": 1.8137, + "step": 16469 + }, + { + "epoch": 0.9180090295970125, + "grad_norm": 0.5296235680580139, + "learning_rate": 1.7150580780396387e-06, + "loss": 1.6009, + "step": 16470 + }, + { + "epoch": 0.9180647678501755, + "grad_norm": 0.5891937613487244, + "learning_rate": 1.7127467279123232e-06, + "loss": 1.7379, + "step": 16471 + }, + { + "epoch": 0.9181205061033387, + "grad_norm": 0.5940790176391602, + "learning_rate": 1.7104369091751337e-06, + "loss": 1.5403, + "step": 16472 + }, + { + "epoch": 0.9181762443565019, + "grad_norm": 0.5478262305259705, + "learning_rate": 1.7081286219013559e-06, + "loss": 1.5477, + "step": 16473 + }, + { + "epoch": 0.918231982609665, + "grad_norm": 0.56959068775177, + "learning_rate": 1.7058218661641645e-06, + "loss": 1.5801, + "step": 16474 + }, + { + "epoch": 0.9182877208628282, + "grad_norm": 0.5889841318130493, + "learning_rate": 1.7035166420367344e-06, + "loss": 1.6562, + "step": 16475 + }, + { + "epoch": 0.9183434591159914, + "grad_norm": 0.5901776552200317, + "learning_rate": 1.7012129495921681e-06, + "loss": 1.5919, + "step": 16476 + }, + { + "epoch": 0.9183991973691544, + "grad_norm": 0.5541892647743225, + "learning_rate": 1.6989107889035238e-06, + "loss": 1.6926, + "step": 16477 + }, + { + "epoch": 0.9184549356223176, + "grad_norm": 0.5845743417739868, + "learning_rate": 1.696610160043821e-06, + "loss": 1.6333, + "step": 16478 + }, + { + "epoch": 0.9185106738754807, + "grad_norm": 0.5838524699211121, + "learning_rate": 1.6943110630860016e-06, + "loss": 1.6626, + "step": 16479 + }, + { + "epoch": 0.9185664121286439, + "grad_norm": 0.5719736814498901, + "learning_rate": 1.6920134981030122e-06, + "loss": 1.6502, + "step": 16480 + }, + { + "epoch": 0.9186221503818071, + "grad_norm": 0.5804576873779297, + "learning_rate": 1.6897174651676895e-06, + "loss": 1.6908, + "step": 16481 + }, + { + "epoch": 0.9186778886349701, + "grad_norm": 0.5853901505470276, + "learning_rate": 1.6874229643528583e-06, + "loss": 1.7559, + "step": 16482 + }, + { + "epoch": 0.9187336268881333, + "grad_norm": 0.5708677172660828, + "learning_rate": 1.6851299957312883e-06, + "loss": 1.8367, + "step": 16483 + }, + { + "epoch": 0.9187893651412965, + "grad_norm": 0.5577463507652283, + "learning_rate": 1.6828385593757047e-06, + "loss": 1.6753, + "step": 16484 + }, + { + "epoch": 0.9188451033944596, + "grad_norm": 0.5763183832168579, + "learning_rate": 1.6805486553587712e-06, + "loss": 1.713, + "step": 16485 + }, + { + "epoch": 0.9189008416476228, + "grad_norm": 0.5715948343276978, + "learning_rate": 1.6782602837531136e-06, + "loss": 1.6826, + "step": 16486 + }, + { + "epoch": 0.9189565799007859, + "grad_norm": 0.5386956930160522, + "learning_rate": 1.6759734446313014e-06, + "loss": 1.5478, + "step": 16487 + }, + { + "epoch": 0.919012318153949, + "grad_norm": 0.5436660051345825, + "learning_rate": 1.6736881380658654e-06, + "loss": 1.6034, + "step": 16488 + }, + { + "epoch": 0.9190680564071122, + "grad_norm": 0.5543313026428223, + "learning_rate": 1.6714043641292864e-06, + "loss": 1.4609, + "step": 16489 + }, + { + "epoch": 0.9191237946602754, + "grad_norm": 0.5309345722198486, + "learning_rate": 1.669122122893968e-06, + "loss": 1.3554, + "step": 16490 + }, + { + "epoch": 0.9191795329134385, + "grad_norm": 0.5759702324867249, + "learning_rate": 1.6668414144323186e-06, + "loss": 1.4837, + "step": 16491 + }, + { + "epoch": 0.9192352711666016, + "grad_norm": 0.5658862590789795, + "learning_rate": 1.6645622388166638e-06, + "loss": 1.7913, + "step": 16492 + }, + { + "epoch": 0.9192910094197648, + "grad_norm": 0.5941377878189087, + "learning_rate": 1.662284596119268e-06, + "loss": 1.9116, + "step": 16493 + }, + { + "epoch": 0.9193467476729279, + "grad_norm": 0.5891839265823364, + "learning_rate": 1.660008486412379e-06, + "loss": 1.6278, + "step": 16494 + }, + { + "epoch": 0.9194024859260911, + "grad_norm": 0.521165668964386, + "learning_rate": 1.6577339097681832e-06, + "loss": 1.4077, + "step": 16495 + }, + { + "epoch": 0.9194582241792543, + "grad_norm": 0.531406581401825, + "learning_rate": 1.655460866258818e-06, + "loss": 1.4824, + "step": 16496 + }, + { + "epoch": 0.9195139624324173, + "grad_norm": 0.5666982531547546, + "learning_rate": 1.6531893559563526e-06, + "loss": 1.6222, + "step": 16497 + }, + { + "epoch": 0.9195697006855805, + "grad_norm": 0.5837276577949524, + "learning_rate": 1.6509193789328413e-06, + "loss": 1.6781, + "step": 16498 + }, + { + "epoch": 0.9196254389387437, + "grad_norm": 0.5440641641616821, + "learning_rate": 1.648650935260282e-06, + "loss": 1.4755, + "step": 16499 + }, + { + "epoch": 0.9196811771919068, + "grad_norm": 0.588312566280365, + "learning_rate": 1.6463840250106e-06, + "loss": 1.755, + "step": 16500 + }, + { + "epoch": 0.91973691544507, + "grad_norm": 0.5434694886207581, + "learning_rate": 1.644118648255699e-06, + "loss": 1.5966, + "step": 16501 + }, + { + "epoch": 0.919792653698233, + "grad_norm": 0.6122984290122986, + "learning_rate": 1.6418548050674166e-06, + "loss": 1.5313, + "step": 16502 + }, + { + "epoch": 0.9198483919513962, + "grad_norm": 0.5978482961654663, + "learning_rate": 1.6395924955175502e-06, + "loss": 1.9343, + "step": 16503 + }, + { + "epoch": 0.9199041302045594, + "grad_norm": 0.5809456706047058, + "learning_rate": 1.6373317196778592e-06, + "loss": 1.7741, + "step": 16504 + }, + { + "epoch": 0.9199598684577225, + "grad_norm": 0.575381875038147, + "learning_rate": 1.6350724776200199e-06, + "loss": 1.8046, + "step": 16505 + }, + { + "epoch": 0.9200156067108857, + "grad_norm": 0.6297763586044312, + "learning_rate": 1.632814769415708e-06, + "loss": 1.8731, + "step": 16506 + }, + { + "epoch": 0.9200713449640489, + "grad_norm": 0.5816977620124817, + "learning_rate": 1.6305585951365e-06, + "loss": 1.7025, + "step": 16507 + }, + { + "epoch": 0.9201270832172119, + "grad_norm": 0.5675135254859924, + "learning_rate": 1.6283039548539658e-06, + "loss": 1.7016, + "step": 16508 + }, + { + "epoch": 0.9201828214703751, + "grad_norm": 0.6639918088912964, + "learning_rate": 1.6260508486395986e-06, + "loss": 2.1694, + "step": 16509 + }, + { + "epoch": 0.9202385597235383, + "grad_norm": 0.5344813466072083, + "learning_rate": 1.6237992765648636e-06, + "loss": 1.526, + "step": 16510 + }, + { + "epoch": 0.9202942979767014, + "grad_norm": 0.5808811783790588, + "learning_rate": 1.6215492387011643e-06, + "loss": 1.6928, + "step": 16511 + }, + { + "epoch": 0.9203500362298646, + "grad_norm": 0.5614989995956421, + "learning_rate": 1.6193007351198553e-06, + "loss": 1.4855, + "step": 16512 + }, + { + "epoch": 0.9204057744830277, + "grad_norm": 0.5616374015808105, + "learning_rate": 1.6170537658922457e-06, + "loss": 1.5693, + "step": 16513 + }, + { + "epoch": 0.9204615127361908, + "grad_norm": 0.6297098994255066, + "learning_rate": 1.6148083310895956e-06, + "loss": 1.9811, + "step": 16514 + }, + { + "epoch": 0.920517250989354, + "grad_norm": 0.5860701203346252, + "learning_rate": 1.612564430783131e-06, + "loss": 1.7147, + "step": 16515 + }, + { + "epoch": 0.9205729892425172, + "grad_norm": 0.587976336479187, + "learning_rate": 1.6103220650439898e-06, + "loss": 1.5628, + "step": 16516 + }, + { + "epoch": 0.9206287274956803, + "grad_norm": 0.6221239566802979, + "learning_rate": 1.6080812339433094e-06, + "loss": 1.6205, + "step": 16517 + }, + { + "epoch": 0.9206844657488434, + "grad_norm": 0.583825945854187, + "learning_rate": 1.6058419375521494e-06, + "loss": 1.6176, + "step": 16518 + }, + { + "epoch": 0.9207402040020066, + "grad_norm": 0.6152258515357971, + "learning_rate": 1.6036041759415254e-06, + "loss": 1.7232, + "step": 16519 + }, + { + "epoch": 0.9207959422551697, + "grad_norm": 0.5814340114593506, + "learning_rate": 1.601367949182403e-06, + "loss": 1.4445, + "step": 16520 + }, + { + "epoch": 0.9208516805083329, + "grad_norm": 0.5321704149246216, + "learning_rate": 1.599133257345703e-06, + "loss": 1.4912, + "step": 16521 + }, + { + "epoch": 0.9209074187614961, + "grad_norm": 0.5516023635864258, + "learning_rate": 1.5969001005023077e-06, + "loss": 1.5366, + "step": 16522 + }, + { + "epoch": 0.9209631570146591, + "grad_norm": 0.6178098320960999, + "learning_rate": 1.594668478723027e-06, + "loss": 1.7946, + "step": 16523 + }, + { + "epoch": 0.9210188952678223, + "grad_norm": 0.5458576679229736, + "learning_rate": 1.5924383920786323e-06, + "loss": 1.5214, + "step": 16524 + }, + { + "epoch": 0.9210746335209854, + "grad_norm": 0.5953642129898071, + "learning_rate": 1.5902098406398724e-06, + "loss": 1.8999, + "step": 16525 + }, + { + "epoch": 0.9211303717741486, + "grad_norm": 0.5081036686897278, + "learning_rate": 1.5879828244773965e-06, + "loss": 1.3326, + "step": 16526 + }, + { + "epoch": 0.9211861100273118, + "grad_norm": 0.5677838325500488, + "learning_rate": 1.585757343661848e-06, + "loss": 1.6633, + "step": 16527 + }, + { + "epoch": 0.9212418482804748, + "grad_norm": 0.5805388689041138, + "learning_rate": 1.5835333982637978e-06, + "loss": 1.6892, + "step": 16528 + }, + { + "epoch": 0.921297586533638, + "grad_norm": 0.5271235108375549, + "learning_rate": 1.581310988353779e-06, + "loss": 1.4578, + "step": 16529 + }, + { + "epoch": 0.9213533247868012, + "grad_norm": 0.5820759534835815, + "learning_rate": 1.579090114002285e-06, + "loss": 1.7048, + "step": 16530 + }, + { + "epoch": 0.9214090630399643, + "grad_norm": 0.6028430461883545, + "learning_rate": 1.5768707752797263e-06, + "loss": 1.724, + "step": 16531 + }, + { + "epoch": 0.9214648012931275, + "grad_norm": 0.5903018712997437, + "learning_rate": 1.574652972256513e-06, + "loss": 1.8385, + "step": 16532 + }, + { + "epoch": 0.9215205395462907, + "grad_norm": 0.5569248199462891, + "learning_rate": 1.5724367050029608e-06, + "loss": 1.5621, + "step": 16533 + }, + { + "epoch": 0.9215762777994537, + "grad_norm": 0.6074315905570984, + "learning_rate": 1.5702219735893643e-06, + "loss": 1.5684, + "step": 16534 + }, + { + "epoch": 0.9216320160526169, + "grad_norm": 0.582641065120697, + "learning_rate": 1.5680087780859609e-06, + "loss": 1.8214, + "step": 16535 + }, + { + "epoch": 0.9216877543057801, + "grad_norm": 0.5743795037269592, + "learning_rate": 1.565797118562945e-06, + "loss": 1.4727, + "step": 16536 + }, + { + "epoch": 0.9217434925589432, + "grad_norm": 0.5716885924339294, + "learning_rate": 1.5635869950904547e-06, + "loss": 1.8936, + "step": 16537 + }, + { + "epoch": 0.9217992308121064, + "grad_norm": 0.5845539569854736, + "learning_rate": 1.5613784077385785e-06, + "loss": 1.7389, + "step": 16538 + }, + { + "epoch": 0.9218549690652695, + "grad_norm": 0.5926645994186401, + "learning_rate": 1.5591713565773602e-06, + "loss": 1.902, + "step": 16539 + }, + { + "epoch": 0.9219107073184326, + "grad_norm": 0.6809507608413696, + "learning_rate": 1.556965841676794e-06, + "loss": 1.8112, + "step": 16540 + }, + { + "epoch": 0.9219664455715958, + "grad_norm": 0.5653813481330872, + "learning_rate": 1.5547618631068407e-06, + "loss": 1.5137, + "step": 16541 + }, + { + "epoch": 0.922022183824759, + "grad_norm": 0.5626515746116638, + "learning_rate": 1.5525594209373717e-06, + "loss": 1.5703, + "step": 16542 + }, + { + "epoch": 0.922077922077922, + "grad_norm": 0.5312036871910095, + "learning_rate": 1.5503585152382538e-06, + "loss": 1.5157, + "step": 16543 + }, + { + "epoch": 0.9221336603310852, + "grad_norm": 0.5704143643379211, + "learning_rate": 1.5481591460792921e-06, + "loss": 1.7501, + "step": 16544 + }, + { + "epoch": 0.9221893985842484, + "grad_norm": 0.5714554786682129, + "learning_rate": 1.5459613135302198e-06, + "loss": 1.3828, + "step": 16545 + }, + { + "epoch": 0.9222451368374115, + "grad_norm": 0.5901116132736206, + "learning_rate": 1.5437650176607477e-06, + "loss": 1.8228, + "step": 16546 + }, + { + "epoch": 0.9223008750905747, + "grad_norm": 0.5710008144378662, + "learning_rate": 1.5415702585405312e-06, + "loss": 1.7252, + "step": 16547 + }, + { + "epoch": 0.9223566133437378, + "grad_norm": 0.6171746850013733, + "learning_rate": 1.5393770362391813e-06, + "loss": 1.735, + "step": 16548 + }, + { + "epoch": 0.9224123515969009, + "grad_norm": 0.5631168484687805, + "learning_rate": 1.537185350826237e-06, + "loss": 1.6412, + "step": 16549 + }, + { + "epoch": 0.9224680898500641, + "grad_norm": 0.5849908590316772, + "learning_rate": 1.5349952023712144e-06, + "loss": 1.7825, + "step": 16550 + }, + { + "epoch": 0.9225238281032272, + "grad_norm": 0.5402557253837585, + "learning_rate": 1.5328065909435807e-06, + "loss": 1.535, + "step": 16551 + }, + { + "epoch": 0.9225795663563904, + "grad_norm": 0.5642532706260681, + "learning_rate": 1.5306195166127357e-06, + "loss": 1.7134, + "step": 16552 + }, + { + "epoch": 0.9226353046095536, + "grad_norm": 0.5910566449165344, + "learning_rate": 1.5284339794480406e-06, + "loss": 1.7493, + "step": 16553 + }, + { + "epoch": 0.9226910428627166, + "grad_norm": 0.546161413192749, + "learning_rate": 1.5262499795188124e-06, + "loss": 1.6107, + "step": 16554 + }, + { + "epoch": 0.9227467811158798, + "grad_norm": 0.5336690545082092, + "learning_rate": 1.5240675168943118e-06, + "loss": 1.3162, + "step": 16555 + }, + { + "epoch": 0.922802519369043, + "grad_norm": 0.5863358974456787, + "learning_rate": 1.521886591643762e-06, + "loss": 1.8181, + "step": 16556 + }, + { + "epoch": 0.9228582576222061, + "grad_norm": 0.5708210468292236, + "learning_rate": 1.5197072038363125e-06, + "loss": 1.7267, + "step": 16557 + }, + { + "epoch": 0.9229139958753693, + "grad_norm": 0.5650946497917175, + "learning_rate": 1.5175293535411028e-06, + "loss": 1.4564, + "step": 16558 + }, + { + "epoch": 0.9229697341285324, + "grad_norm": 0.5419399738311768, + "learning_rate": 1.5153530408271832e-06, + "loss": 1.5022, + "step": 16559 + }, + { + "epoch": 0.9230254723816955, + "grad_norm": 0.5661548972129822, + "learning_rate": 1.5131782657635763e-06, + "loss": 1.6439, + "step": 16560 + }, + { + "epoch": 0.9230812106348587, + "grad_norm": 0.5467028021812439, + "learning_rate": 1.51100502841926e-06, + "loss": 1.8417, + "step": 16561 + }, + { + "epoch": 0.9231369488880219, + "grad_norm": 0.5810919404029846, + "learning_rate": 1.5088333288631573e-06, + "loss": 1.6319, + "step": 16562 + }, + { + "epoch": 0.923192687141185, + "grad_norm": 0.5900965929031372, + "learning_rate": 1.5066631671641406e-06, + "loss": 1.6145, + "step": 16563 + }, + { + "epoch": 0.9232484253943481, + "grad_norm": 0.6063122153282166, + "learning_rate": 1.5044945433910274e-06, + "loss": 1.6342, + "step": 16564 + }, + { + "epoch": 0.9233041636475113, + "grad_norm": 0.5637290477752686, + "learning_rate": 1.5023274576125956e-06, + "loss": 1.5479, + "step": 16565 + }, + { + "epoch": 0.9233599019006744, + "grad_norm": 0.5472915172576904, + "learning_rate": 1.5001619098975795e-06, + "loss": 1.6262, + "step": 16566 + }, + { + "epoch": 0.9234156401538376, + "grad_norm": 0.5457784533500671, + "learning_rate": 1.4979979003146572e-06, + "loss": 1.4897, + "step": 16567 + }, + { + "epoch": 0.9234713784070008, + "grad_norm": 0.5658400654792786, + "learning_rate": 1.4958354289324462e-06, + "loss": 1.6279, + "step": 16568 + }, + { + "epoch": 0.9235271166601638, + "grad_norm": 0.5519348978996277, + "learning_rate": 1.4936744958195415e-06, + "loss": 1.5064, + "step": 16569 + }, + { + "epoch": 0.923582854913327, + "grad_norm": 0.6148653626441956, + "learning_rate": 1.4915151010444716e-06, + "loss": 1.7816, + "step": 16570 + }, + { + "epoch": 0.9236385931664901, + "grad_norm": 0.579528272151947, + "learning_rate": 1.489357244675721e-06, + "loss": 1.701, + "step": 16571 + }, + { + "epoch": 0.9236943314196533, + "grad_norm": 0.5673269033432007, + "learning_rate": 1.4872009267817177e-06, + "loss": 1.6186, + "step": 16572 + }, + { + "epoch": 0.9237500696728165, + "grad_norm": 0.5438182353973389, + "learning_rate": 1.485046147430852e-06, + "loss": 1.684, + "step": 16573 + }, + { + "epoch": 0.9238058079259795, + "grad_norm": 0.5174392461776733, + "learning_rate": 1.4828929066914632e-06, + "loss": 1.5003, + "step": 16574 + }, + { + "epoch": 0.9238615461791427, + "grad_norm": 0.6033009886741638, + "learning_rate": 1.4807412046318303e-06, + "loss": 1.684, + "step": 16575 + }, + { + "epoch": 0.9239172844323059, + "grad_norm": 0.5328043103218079, + "learning_rate": 1.4785910413202042e-06, + "loss": 1.5795, + "step": 16576 + }, + { + "epoch": 0.923973022685469, + "grad_norm": 0.5500699281692505, + "learning_rate": 1.4764424168247747e-06, + "loss": 1.5598, + "step": 16577 + }, + { + "epoch": 0.9240287609386322, + "grad_norm": 0.5959620475769043, + "learning_rate": 1.4742953312136765e-06, + "loss": 1.4809, + "step": 16578 + }, + { + "epoch": 0.9240844991917954, + "grad_norm": 0.5720731019973755, + "learning_rate": 1.4721497845550048e-06, + "loss": 1.5731, + "step": 16579 + }, + { + "epoch": 0.9241402374449584, + "grad_norm": 0.5862687826156616, + "learning_rate": 1.4700057769168053e-06, + "loss": 1.7021, + "step": 16580 + }, + { + "epoch": 0.9241959756981216, + "grad_norm": 0.6171941161155701, + "learning_rate": 1.4678633083670734e-06, + "loss": 1.7689, + "step": 16581 + }, + { + "epoch": 0.9242517139512848, + "grad_norm": 0.4975408613681793, + "learning_rate": 1.4657223789737606e-06, + "loss": 1.0948, + "step": 16582 + }, + { + "epoch": 0.9243074522044479, + "grad_norm": 0.5937922596931458, + "learning_rate": 1.4635829888047459e-06, + "loss": 1.6724, + "step": 16583 + }, + { + "epoch": 0.9243631904576111, + "grad_norm": 0.5575575232505798, + "learning_rate": 1.4614451379279081e-06, + "loss": 1.3943, + "step": 16584 + }, + { + "epoch": 0.9244189287107742, + "grad_norm": 0.5398813486099243, + "learning_rate": 1.459308826411021e-06, + "loss": 1.5175, + "step": 16585 + }, + { + "epoch": 0.9244746669639373, + "grad_norm": 0.561843752861023, + "learning_rate": 1.457174054321847e-06, + "loss": 1.6664, + "step": 16586 + }, + { + "epoch": 0.9245304052171005, + "grad_norm": 0.5843443274497986, + "learning_rate": 1.4550408217280875e-06, + "loss": 1.7089, + "step": 16587 + }, + { + "epoch": 0.9245861434702637, + "grad_norm": 0.6158113479614258, + "learning_rate": 1.4529091286973995e-06, + "loss": 1.7767, + "step": 16588 + }, + { + "epoch": 0.9246418817234268, + "grad_norm": 0.5882505178451538, + "learning_rate": 1.4507789752973844e-06, + "loss": 1.5851, + "step": 16589 + }, + { + "epoch": 0.92469761997659, + "grad_norm": 0.6174805164337158, + "learning_rate": 1.4486503615955993e-06, + "loss": 1.6937, + "step": 16590 + }, + { + "epoch": 0.9247533582297531, + "grad_norm": 0.571028470993042, + "learning_rate": 1.4465232876595457e-06, + "loss": 1.7255, + "step": 16591 + }, + { + "epoch": 0.9248090964829162, + "grad_norm": 0.5297460556030273, + "learning_rate": 1.4443977535566922e-06, + "loss": 1.4131, + "step": 16592 + }, + { + "epoch": 0.9248648347360794, + "grad_norm": 0.5910332202911377, + "learning_rate": 1.4422737593544455e-06, + "loss": 1.802, + "step": 16593 + }, + { + "epoch": 0.9249205729892425, + "grad_norm": 0.5692709684371948, + "learning_rate": 1.4401513051201521e-06, + "loss": 1.5824, + "step": 16594 + }, + { + "epoch": 0.9249763112424056, + "grad_norm": 0.5456255078315735, + "learning_rate": 1.4380303909211413e-06, + "loss": 1.5499, + "step": 16595 + }, + { + "epoch": 0.9250320494955688, + "grad_norm": 0.54347825050354, + "learning_rate": 1.435911016824676e-06, + "loss": 1.5213, + "step": 16596 + }, + { + "epoch": 0.9250877877487319, + "grad_norm": 0.5416505336761475, + "learning_rate": 1.4337931828979633e-06, + "loss": 1.7629, + "step": 16597 + }, + { + "epoch": 0.9251435260018951, + "grad_norm": 0.5668787360191345, + "learning_rate": 1.4316768892081667e-06, + "loss": 1.53, + "step": 16598 + }, + { + "epoch": 0.9251992642550583, + "grad_norm": 0.5617362260818481, + "learning_rate": 1.42956213582241e-06, + "loss": 1.6082, + "step": 16599 + }, + { + "epoch": 0.9252550025082213, + "grad_norm": 0.5775700807571411, + "learning_rate": 1.427448922807756e-06, + "loss": 1.6629, + "step": 16600 + }, + { + "epoch": 0.9253107407613845, + "grad_norm": 0.5427951812744141, + "learning_rate": 1.425337250231218e-06, + "loss": 1.6067, + "step": 16601 + }, + { + "epoch": 0.9253664790145477, + "grad_norm": 0.6276479363441467, + "learning_rate": 1.4232271181597757e-06, + "loss": 1.8957, + "step": 16602 + }, + { + "epoch": 0.9254222172677108, + "grad_norm": 0.5605406165122986, + "learning_rate": 1.4211185266603589e-06, + "loss": 1.6444, + "step": 16603 + }, + { + "epoch": 0.925477955520874, + "grad_norm": 0.5391684174537659, + "learning_rate": 1.4190114757998141e-06, + "loss": 1.6003, + "step": 16604 + }, + { + "epoch": 0.9255336937740372, + "grad_norm": 0.5512267351150513, + "learning_rate": 1.4169059656449824e-06, + "loss": 1.5485, + "step": 16605 + }, + { + "epoch": 0.9255894320272002, + "grad_norm": 0.5149703025817871, + "learning_rate": 1.4148019962626323e-06, + "loss": 1.4721, + "step": 16606 + }, + { + "epoch": 0.9256451702803634, + "grad_norm": 0.569707453250885, + "learning_rate": 1.4126995677195e-06, + "loss": 1.7393, + "step": 16607 + }, + { + "epoch": 0.9257009085335266, + "grad_norm": 0.5579036474227905, + "learning_rate": 1.410598680082248e-06, + "loss": 1.7286, + "step": 16608 + }, + { + "epoch": 0.9257566467866897, + "grad_norm": 0.5913406014442444, + "learning_rate": 1.4084993334175012e-06, + "loss": 1.7772, + "step": 16609 + }, + { + "epoch": 0.9258123850398529, + "grad_norm": 0.5493654012680054, + "learning_rate": 1.4064015277918618e-06, + "loss": 1.4551, + "step": 16610 + }, + { + "epoch": 0.925868123293016, + "grad_norm": 0.5319018959999084, + "learning_rate": 1.4043052632718378e-06, + "loss": 1.6318, + "step": 16611 + }, + { + "epoch": 0.9259238615461791, + "grad_norm": 0.5780298113822937, + "learning_rate": 1.4022105399239206e-06, + "loss": 1.5872, + "step": 16612 + }, + { + "epoch": 0.9259795997993423, + "grad_norm": 0.5337649583816528, + "learning_rate": 1.4001173578145398e-06, + "loss": 1.5583, + "step": 16613 + }, + { + "epoch": 0.9260353380525055, + "grad_norm": 0.5670482516288757, + "learning_rate": 1.3980257170100763e-06, + "loss": 1.635, + "step": 16614 + }, + { + "epoch": 0.9260910763056686, + "grad_norm": 0.5582801103591919, + "learning_rate": 1.3959356175768768e-06, + "loss": 1.4499, + "step": 16615 + }, + { + "epoch": 0.9261468145588317, + "grad_norm": 0.5150138735771179, + "learning_rate": 1.3938470595812103e-06, + "loss": 1.2255, + "step": 16616 + }, + { + "epoch": 0.9262025528119948, + "grad_norm": 0.5473129153251648, + "learning_rate": 1.391760043089324e-06, + "loss": 1.5682, + "step": 16617 + }, + { + "epoch": 0.926258291065158, + "grad_norm": 0.6057248115539551, + "learning_rate": 1.3896745681674039e-06, + "loss": 1.8535, + "step": 16618 + }, + { + "epoch": 0.9263140293183212, + "grad_norm": 0.5713788270950317, + "learning_rate": 1.3875906348815914e-06, + "loss": 1.5544, + "step": 16619 + }, + { + "epoch": 0.9263697675714843, + "grad_norm": 0.5901215076446533, + "learning_rate": 1.3855082432979672e-06, + "loss": 1.5231, + "step": 16620 + }, + { + "epoch": 0.9264255058246474, + "grad_norm": 0.5600011944770813, + "learning_rate": 1.383427393482578e-06, + "loss": 1.6676, + "step": 16621 + }, + { + "epoch": 0.9264812440778106, + "grad_norm": 0.5697068572044373, + "learning_rate": 1.381348085501427e-06, + "loss": 1.5498, + "step": 16622 + }, + { + "epoch": 0.9265369823309737, + "grad_norm": 0.5958000421524048, + "learning_rate": 1.3792703194204448e-06, + "loss": 1.7304, + "step": 16623 + }, + { + "epoch": 0.9265927205841369, + "grad_norm": 0.5966675281524658, + "learning_rate": 1.3771940953055284e-06, + "loss": 1.73, + "step": 16624 + }, + { + "epoch": 0.9266484588373001, + "grad_norm": 0.5797795057296753, + "learning_rate": 1.3751194132225253e-06, + "loss": 1.653, + "step": 16625 + }, + { + "epoch": 0.9267041970904631, + "grad_norm": 0.5479815602302551, + "learning_rate": 1.3730462732372328e-06, + "loss": 1.467, + "step": 16626 + }, + { + "epoch": 0.9267599353436263, + "grad_norm": 0.565971851348877, + "learning_rate": 1.370974675415393e-06, + "loss": 1.7548, + "step": 16627 + }, + { + "epoch": 0.9268156735967895, + "grad_norm": 0.5931971073150635, + "learning_rate": 1.3689046198227086e-06, + "loss": 1.8312, + "step": 16628 + }, + { + "epoch": 0.9268714118499526, + "grad_norm": 0.5479225516319275, + "learning_rate": 1.366836106524838e-06, + "loss": 1.6967, + "step": 16629 + }, + { + "epoch": 0.9269271501031158, + "grad_norm": 0.5402050614356995, + "learning_rate": 1.3647691355873737e-06, + "loss": 1.4939, + "step": 16630 + }, + { + "epoch": 0.926982888356279, + "grad_norm": 0.5199860334396362, + "learning_rate": 1.3627037070758686e-06, + "loss": 1.4178, + "step": 16631 + }, + { + "epoch": 0.927038626609442, + "grad_norm": 0.5571439266204834, + "learning_rate": 1.3606398210558202e-06, + "loss": 1.5338, + "step": 16632 + }, + { + "epoch": 0.9270943648626052, + "grad_norm": 0.5534048080444336, + "learning_rate": 1.3585774775926985e-06, + "loss": 1.6177, + "step": 16633 + }, + { + "epoch": 0.9271501031157684, + "grad_norm": 0.5392510294914246, + "learning_rate": 1.3565166767519012e-06, + "loss": 1.6417, + "step": 16634 + }, + { + "epoch": 0.9272058413689315, + "grad_norm": 0.5554952621459961, + "learning_rate": 1.3544574185987702e-06, + "loss": 1.5803, + "step": 16635 + }, + { + "epoch": 0.9272615796220947, + "grad_norm": 0.5348825454711914, + "learning_rate": 1.3523997031986424e-06, + "loss": 1.5008, + "step": 16636 + }, + { + "epoch": 0.9273173178752578, + "grad_norm": 0.5562388300895691, + "learning_rate": 1.350343530616749e-06, + "loss": 1.5865, + "step": 16637 + }, + { + "epoch": 0.9273730561284209, + "grad_norm": 0.606353759765625, + "learning_rate": 1.3482889009183153e-06, + "loss": 1.8265, + "step": 16638 + }, + { + "epoch": 0.9274287943815841, + "grad_norm": 0.5765892863273621, + "learning_rate": 1.3462358141685005e-06, + "loss": 1.7269, + "step": 16639 + }, + { + "epoch": 0.9274845326347472, + "grad_norm": 0.5677004456520081, + "learning_rate": 1.3441842704324136e-06, + "loss": 1.686, + "step": 16640 + }, + { + "epoch": 0.9275402708879104, + "grad_norm": 0.5988342761993408, + "learning_rate": 1.3421342697751249e-06, + "loss": 1.7519, + "step": 16641 + }, + { + "epoch": 0.9275960091410735, + "grad_norm": 0.5709552764892578, + "learning_rate": 1.3400858122616323e-06, + "loss": 1.8219, + "step": 16642 + }, + { + "epoch": 0.9276517473942366, + "grad_norm": 0.6109775900840759, + "learning_rate": 1.338038897956917e-06, + "loss": 1.6694, + "step": 16643 + }, + { + "epoch": 0.9277074856473998, + "grad_norm": 0.5375047326087952, + "learning_rate": 1.3359935269258828e-06, + "loss": 1.396, + "step": 16644 + }, + { + "epoch": 0.927763223900563, + "grad_norm": 0.6010435223579407, + "learning_rate": 1.333949699233411e-06, + "loss": 1.7887, + "step": 16645 + }, + { + "epoch": 0.9278189621537261, + "grad_norm": 0.6132597923278809, + "learning_rate": 1.3319074149443057e-06, + "loss": 1.6942, + "step": 16646 + }, + { + "epoch": 0.9278747004068892, + "grad_norm": 0.5798476934432983, + "learning_rate": 1.3298666741233424e-06, + "loss": 1.7105, + "step": 16647 + }, + { + "epoch": 0.9279304386600524, + "grad_norm": 0.5826559066772461, + "learning_rate": 1.3278274768352473e-06, + "loss": 1.6445, + "step": 16648 + }, + { + "epoch": 0.9279861769132155, + "grad_norm": 0.5752706527709961, + "learning_rate": 1.3257898231446797e-06, + "loss": 1.6324, + "step": 16649 + }, + { + "epoch": 0.9280419151663787, + "grad_norm": 0.5526127815246582, + "learning_rate": 1.3237537131162714e-06, + "loss": 1.611, + "step": 16650 + }, + { + "epoch": 0.9280976534195419, + "grad_norm": 0.5751146078109741, + "learning_rate": 1.3217191468145928e-06, + "loss": 1.6696, + "step": 16651 + }, + { + "epoch": 0.9281533916727049, + "grad_norm": 0.5594660639762878, + "learning_rate": 1.3196861243041758e-06, + "loss": 1.4856, + "step": 16652 + }, + { + "epoch": 0.9282091299258681, + "grad_norm": 0.5656089186668396, + "learning_rate": 1.3176546456494742e-06, + "loss": 1.7154, + "step": 16653 + }, + { + "epoch": 0.9282648681790313, + "grad_norm": 0.563431978225708, + "learning_rate": 1.3156247109149366e-06, + "loss": 1.6028, + "step": 16654 + }, + { + "epoch": 0.9283206064321944, + "grad_norm": 0.5688559412956238, + "learning_rate": 1.3135963201649393e-06, + "loss": 1.5997, + "step": 16655 + }, + { + "epoch": 0.9283763446853576, + "grad_norm": 0.560697078704834, + "learning_rate": 1.3115694734638028e-06, + "loss": 1.5001, + "step": 16656 + }, + { + "epoch": 0.9284320829385208, + "grad_norm": 0.510688841342926, + "learning_rate": 1.3095441708758037e-06, + "loss": 1.2605, + "step": 16657 + }, + { + "epoch": 0.9284878211916838, + "grad_norm": 0.5209299921989441, + "learning_rate": 1.307520412465185e-06, + "loss": 1.3539, + "step": 16658 + }, + { + "epoch": 0.928543559444847, + "grad_norm": 0.49172842502593994, + "learning_rate": 1.3054981982961234e-06, + "loss": 1.4482, + "step": 16659 + }, + { + "epoch": 0.9285992976980102, + "grad_norm": 0.5374777913093567, + "learning_rate": 1.303477528432745e-06, + "loss": 1.5341, + "step": 16660 + }, + { + "epoch": 0.9286550359511733, + "grad_norm": 0.5938795804977417, + "learning_rate": 1.301458402939132e-06, + "loss": 1.6272, + "step": 16661 + }, + { + "epoch": 0.9287107742043365, + "grad_norm": 0.5304864048957825, + "learning_rate": 1.2994408218793385e-06, + "loss": 1.4829, + "step": 16662 + }, + { + "epoch": 0.9287665124574995, + "grad_norm": 0.576808512210846, + "learning_rate": 1.297424785317336e-06, + "loss": 1.6001, + "step": 16663 + }, + { + "epoch": 0.9288222507106627, + "grad_norm": 0.6030658483505249, + "learning_rate": 1.2954102933170564e-06, + "loss": 1.7221, + "step": 16664 + }, + { + "epoch": 0.9288779889638259, + "grad_norm": 0.562144935131073, + "learning_rate": 1.2933973459423987e-06, + "loss": 1.6743, + "step": 16665 + }, + { + "epoch": 0.928933727216989, + "grad_norm": 0.5682948231697083, + "learning_rate": 1.2913859432572007e-06, + "loss": 1.741, + "step": 16666 + }, + { + "epoch": 0.9289894654701522, + "grad_norm": 0.571731448173523, + "learning_rate": 1.2893760853252501e-06, + "loss": 1.7181, + "step": 16667 + }, + { + "epoch": 0.9290452037233153, + "grad_norm": 0.5321506261825562, + "learning_rate": 1.2873677722102795e-06, + "loss": 1.36, + "step": 16668 + }, + { + "epoch": 0.9291009419764784, + "grad_norm": 0.5522253513336182, + "learning_rate": 1.285361003975999e-06, + "loss": 1.4247, + "step": 16669 + }, + { + "epoch": 0.9291566802296416, + "grad_norm": 0.5712013840675354, + "learning_rate": 1.2833557806860407e-06, + "loss": 1.4759, + "step": 16670 + }, + { + "epoch": 0.9292124184828048, + "grad_norm": 0.6068529486656189, + "learning_rate": 1.2813521024039987e-06, + "loss": 1.738, + "step": 16671 + }, + { + "epoch": 0.9292681567359679, + "grad_norm": 0.5316171646118164, + "learning_rate": 1.2793499691934107e-06, + "loss": 1.509, + "step": 16672 + }, + { + "epoch": 0.929323894989131, + "grad_norm": 0.5690956711769104, + "learning_rate": 1.2773493811177817e-06, + "loss": 1.555, + "step": 16673 + }, + { + "epoch": 0.9293796332422942, + "grad_norm": 0.5570046305656433, + "learning_rate": 1.2753503382405662e-06, + "loss": 1.5637, + "step": 16674 + }, + { + "epoch": 0.9294353714954573, + "grad_norm": 0.5495041608810425, + "learning_rate": 1.2733528406251471e-06, + "loss": 1.627, + "step": 16675 + }, + { + "epoch": 0.9294911097486205, + "grad_norm": 0.5016968250274658, + "learning_rate": 1.2713568883348848e-06, + "loss": 1.1211, + "step": 16676 + }, + { + "epoch": 0.9295468480017837, + "grad_norm": 0.5415257811546326, + "learning_rate": 1.2693624814330674e-06, + "loss": 1.5907, + "step": 16677 + }, + { + "epoch": 0.9296025862549467, + "grad_norm": 0.5632084012031555, + "learning_rate": 1.267369619982961e-06, + "loss": 1.6616, + "step": 16678 + }, + { + "epoch": 0.9296583245081099, + "grad_norm": 0.5344038009643555, + "learning_rate": 1.2653783040477486e-06, + "loss": 1.6527, + "step": 16679 + }, + { + "epoch": 0.9297140627612731, + "grad_norm": 0.5634905695915222, + "learning_rate": 1.2633885336906015e-06, + "loss": 1.7218, + "step": 16680 + }, + { + "epoch": 0.9297698010144362, + "grad_norm": 0.5764480233192444, + "learning_rate": 1.2614003089746196e-06, + "loss": 1.617, + "step": 16681 + }, + { + "epoch": 0.9298255392675994, + "grad_norm": 0.5850197076797485, + "learning_rate": 1.2594136299628467e-06, + "loss": 1.8366, + "step": 16682 + }, + { + "epoch": 0.9298812775207626, + "grad_norm": 0.5194596648216248, + "learning_rate": 1.2574284967182992e-06, + "loss": 1.4348, + "step": 16683 + }, + { + "epoch": 0.9299370157739256, + "grad_norm": 0.5815238952636719, + "learning_rate": 1.2554449093039267e-06, + "loss": 1.7107, + "step": 16684 + }, + { + "epoch": 0.9299927540270888, + "grad_norm": 0.5676091909408569, + "learning_rate": 1.253462867782651e-06, + "loss": 1.6215, + "step": 16685 + }, + { + "epoch": 0.9300484922802519, + "grad_norm": 0.5642685890197754, + "learning_rate": 1.2514823722173108e-06, + "loss": 1.6611, + "step": 16686 + }, + { + "epoch": 0.9301042305334151, + "grad_norm": 0.5569720268249512, + "learning_rate": 1.249503422670728e-06, + "loss": 1.568, + "step": 16687 + }, + { + "epoch": 0.9301599687865783, + "grad_norm": 0.5640183091163635, + "learning_rate": 1.2475260192056638e-06, + "loss": 1.752, + "step": 16688 + }, + { + "epoch": 0.9302157070397413, + "grad_norm": 0.5582478642463684, + "learning_rate": 1.2455501618848285e-06, + "loss": 1.6086, + "step": 16689 + }, + { + "epoch": 0.9302714452929045, + "grad_norm": 0.5712947249412537, + "learning_rate": 1.243575850770884e-06, + "loss": 1.7463, + "step": 16690 + }, + { + "epoch": 0.9303271835460677, + "grad_norm": 0.5544520616531372, + "learning_rate": 1.2416030859264406e-06, + "loss": 1.5899, + "step": 16691 + }, + { + "epoch": 0.9303829217992308, + "grad_norm": 0.5443426370620728, + "learning_rate": 1.2396318674140651e-06, + "loss": 1.6088, + "step": 16692 + }, + { + "epoch": 0.930438660052394, + "grad_norm": 0.5617956519126892, + "learning_rate": 1.2376621952962851e-06, + "loss": 1.6877, + "step": 16693 + }, + { + "epoch": 0.9304943983055571, + "grad_norm": 0.5678000450134277, + "learning_rate": 1.2356940696355401e-06, + "loss": 1.6779, + "step": 16694 + }, + { + "epoch": 0.9305501365587202, + "grad_norm": 0.5771474242210388, + "learning_rate": 1.2337274904942796e-06, + "loss": 1.7652, + "step": 16695 + }, + { + "epoch": 0.9306058748118834, + "grad_norm": 0.6152870059013367, + "learning_rate": 1.231762457934843e-06, + "loss": 1.7286, + "step": 16696 + }, + { + "epoch": 0.9306616130650466, + "grad_norm": 0.5356496572494507, + "learning_rate": 1.2297989720195747e-06, + "loss": 1.5344, + "step": 16697 + }, + { + "epoch": 0.9307173513182097, + "grad_norm": 0.5202732086181641, + "learning_rate": 1.2278370328107192e-06, + "loss": 1.4956, + "step": 16698 + }, + { + "epoch": 0.9307730895713728, + "grad_norm": 0.5313246250152588, + "learning_rate": 1.2258766403705157e-06, + "loss": 1.5858, + "step": 16699 + }, + { + "epoch": 0.930828827824536, + "grad_norm": 0.5500717759132385, + "learning_rate": 1.2239177947611423e-06, + "loss": 1.713, + "step": 16700 + }, + { + "epoch": 0.9308845660776991, + "grad_norm": 0.6000309586524963, + "learning_rate": 1.221960496044705e-06, + "loss": 1.8718, + "step": 16701 + }, + { + "epoch": 0.9309403043308623, + "grad_norm": 0.5714352130889893, + "learning_rate": 1.2200047442832817e-06, + "loss": 1.724, + "step": 16702 + }, + { + "epoch": 0.9309960425840255, + "grad_norm": 0.5956761837005615, + "learning_rate": 1.2180505395389064e-06, + "loss": 1.7801, + "step": 16703 + }, + { + "epoch": 0.9310517808371885, + "grad_norm": 0.6166582107543945, + "learning_rate": 1.2160978818735514e-06, + "loss": 1.7699, + "step": 16704 + }, + { + "epoch": 0.9311075190903517, + "grad_norm": 0.5781773924827576, + "learning_rate": 1.2141467713491284e-06, + "loss": 1.6572, + "step": 16705 + }, + { + "epoch": 0.9311632573435149, + "grad_norm": 0.555993914604187, + "learning_rate": 1.212197208027538e-06, + "loss": 1.6102, + "step": 16706 + }, + { + "epoch": 0.931218995596678, + "grad_norm": 0.5200090408325195, + "learning_rate": 1.2102491919706027e-06, + "loss": 1.3241, + "step": 16707 + }, + { + "epoch": 0.9312747338498412, + "grad_norm": 0.6023423075675964, + "learning_rate": 1.2083027232400957e-06, + "loss": 1.7006, + "step": 16708 + }, + { + "epoch": 0.9313304721030042, + "grad_norm": 0.5306578278541565, + "learning_rate": 1.2063578018977507e-06, + "loss": 1.3477, + "step": 16709 + }, + { + "epoch": 0.9313862103561674, + "grad_norm": 0.5822689533233643, + "learning_rate": 1.2044144280052517e-06, + "loss": 1.7295, + "step": 16710 + }, + { + "epoch": 0.9314419486093306, + "grad_norm": 0.5724120736122131, + "learning_rate": 1.2024726016242272e-06, + "loss": 1.6229, + "step": 16711 + }, + { + "epoch": 0.9314976868624937, + "grad_norm": 0.5296499729156494, + "learning_rate": 1.2005323228162612e-06, + "loss": 1.2124, + "step": 16712 + }, + { + "epoch": 0.9315534251156569, + "grad_norm": 0.5773170590400696, + "learning_rate": 1.198593591642888e-06, + "loss": 1.5589, + "step": 16713 + }, + { + "epoch": 0.93160916336882, + "grad_norm": 0.5271617770195007, + "learning_rate": 1.196656408165603e-06, + "loss": 1.4937, + "step": 16714 + }, + { + "epoch": 0.9316649016219831, + "grad_norm": 0.551253616809845, + "learning_rate": 1.1947207724458232e-06, + "loss": 1.3918, + "step": 16715 + }, + { + "epoch": 0.9317206398751463, + "grad_norm": 0.576744019985199, + "learning_rate": 1.1927866845449499e-06, + "loss": 1.6976, + "step": 16716 + }, + { + "epoch": 0.9317763781283095, + "grad_norm": 0.5563866496086121, + "learning_rate": 1.190854144524317e-06, + "loss": 1.6336, + "step": 16717 + }, + { + "epoch": 0.9318321163814726, + "grad_norm": 0.613950252532959, + "learning_rate": 1.188923152445215e-06, + "loss": 1.8903, + "step": 16718 + }, + { + "epoch": 0.9318878546346357, + "grad_norm": 0.5719265341758728, + "learning_rate": 1.1869937083688831e-06, + "loss": 1.7302, + "step": 16719 + }, + { + "epoch": 0.9319435928877989, + "grad_norm": 0.5954426527023315, + "learning_rate": 1.1850658123565007e-06, + "loss": 1.6667, + "step": 16720 + }, + { + "epoch": 0.931999331140962, + "grad_norm": 0.5922693610191345, + "learning_rate": 1.183139464469235e-06, + "loss": 1.8157, + "step": 16721 + }, + { + "epoch": 0.9320550693941252, + "grad_norm": 0.5756450891494751, + "learning_rate": 1.1812146647681543e-06, + "loss": 1.4797, + "step": 16722 + }, + { + "epoch": 0.9321108076472884, + "grad_norm": 0.5641850233078003, + "learning_rate": 1.1792914133143208e-06, + "loss": 1.7114, + "step": 16723 + }, + { + "epoch": 0.9321665459004514, + "grad_norm": 0.5602290034294128, + "learning_rate": 1.177369710168702e-06, + "loss": 1.4327, + "step": 16724 + }, + { + "epoch": 0.9322222841536146, + "grad_norm": 0.5762725472450256, + "learning_rate": 1.1754495553922718e-06, + "loss": 1.7566, + "step": 16725 + }, + { + "epoch": 0.9322780224067778, + "grad_norm": 0.5456225872039795, + "learning_rate": 1.17353094904592e-06, + "loss": 1.5927, + "step": 16726 + }, + { + "epoch": 0.9323337606599409, + "grad_norm": 0.5576876401901245, + "learning_rate": 1.1716138911904816e-06, + "loss": 1.7087, + "step": 16727 + }, + { + "epoch": 0.9323894989131041, + "grad_norm": 0.49490100145339966, + "learning_rate": 1.169698381886758e-06, + "loss": 1.1584, + "step": 16728 + }, + { + "epoch": 0.9324452371662673, + "grad_norm": 0.5619612336158752, + "learning_rate": 1.1677844211955058e-06, + "loss": 1.6593, + "step": 16729 + }, + { + "epoch": 0.9325009754194303, + "grad_norm": 0.5875867605209351, + "learning_rate": 1.1658720091774211e-06, + "loss": 1.6306, + "step": 16730 + }, + { + "epoch": 0.9325567136725935, + "grad_norm": 0.5866366028785706, + "learning_rate": 1.1639611458931498e-06, + "loss": 1.616, + "step": 16731 + }, + { + "epoch": 0.9326124519257566, + "grad_norm": 0.5573495626449585, + "learning_rate": 1.1620518314032935e-06, + "loss": 1.701, + "step": 16732 + }, + { + "epoch": 0.9326681901789198, + "grad_norm": 0.5777599215507507, + "learning_rate": 1.1601440657684204e-06, + "loss": 1.727, + "step": 16733 + }, + { + "epoch": 0.932723928432083, + "grad_norm": 0.5743429064750671, + "learning_rate": 1.1582378490490154e-06, + "loss": 1.5478, + "step": 16734 + }, + { + "epoch": 0.932779666685246, + "grad_norm": 0.5656700730323792, + "learning_rate": 1.1563331813055356e-06, + "loss": 1.6477, + "step": 16735 + }, + { + "epoch": 0.9328354049384092, + "grad_norm": 0.583740770816803, + "learning_rate": 1.1544300625983884e-06, + "loss": 1.7011, + "step": 16736 + }, + { + "epoch": 0.9328911431915724, + "grad_norm": 0.5600483417510986, + "learning_rate": 1.1525284929879364e-06, + "loss": 1.7284, + "step": 16737 + }, + { + "epoch": 0.9329468814447355, + "grad_norm": 0.5471096038818359, + "learning_rate": 1.1506284725344763e-06, + "loss": 1.5, + "step": 16738 + }, + { + "epoch": 0.9330026196978987, + "grad_norm": 0.6244087815284729, + "learning_rate": 1.1487300012982649e-06, + "loss": 1.6443, + "step": 16739 + }, + { + "epoch": 0.9330583579510618, + "grad_norm": 0.541283905506134, + "learning_rate": 1.1468330793395266e-06, + "loss": 1.5057, + "step": 16740 + }, + { + "epoch": 0.9331140962042249, + "grad_norm": 0.5932419896125793, + "learning_rate": 1.144937706718402e-06, + "loss": 1.4323, + "step": 16741 + }, + { + "epoch": 0.9331698344573881, + "grad_norm": 0.564828634262085, + "learning_rate": 1.1430438834950096e-06, + "loss": 1.5609, + "step": 16742 + }, + { + "epoch": 0.9332255727105513, + "grad_norm": 0.5578659176826477, + "learning_rate": 1.1411516097294073e-06, + "loss": 1.6138, + "step": 16743 + }, + { + "epoch": 0.9332813109637144, + "grad_norm": 0.5417086482048035, + "learning_rate": 1.1392608854816133e-06, + "loss": 1.4596, + "step": 16744 + }, + { + "epoch": 0.9333370492168775, + "grad_norm": 0.5894051790237427, + "learning_rate": 1.1373717108115857e-06, + "loss": 1.635, + "step": 16745 + }, + { + "epoch": 0.9333927874700407, + "grad_norm": 0.5652799010276794, + "learning_rate": 1.1354840857792315e-06, + "loss": 1.5789, + "step": 16746 + }, + { + "epoch": 0.9334485257232038, + "grad_norm": 0.5355352759361267, + "learning_rate": 1.133598010444431e-06, + "loss": 1.5497, + "step": 16747 + }, + { + "epoch": 0.933504263976367, + "grad_norm": 0.5300465226173401, + "learning_rate": 1.1317134848669864e-06, + "loss": 1.6279, + "step": 16748 + }, + { + "epoch": 0.9335600022295302, + "grad_norm": 0.5907360315322876, + "learning_rate": 1.1298305091066664e-06, + "loss": 1.5749, + "step": 16749 + }, + { + "epoch": 0.9336157404826932, + "grad_norm": 0.5717518329620361, + "learning_rate": 1.1279490832231954e-06, + "loss": 1.7361, + "step": 16750 + }, + { + "epoch": 0.9336714787358564, + "grad_norm": 0.5456339716911316, + "learning_rate": 1.1260692072762313e-06, + "loss": 1.7525, + "step": 16751 + }, + { + "epoch": 0.9337272169890196, + "grad_norm": 0.5922035574913025, + "learning_rate": 1.1241908813253987e-06, + "loss": 1.731, + "step": 16752 + }, + { + "epoch": 0.9337829552421827, + "grad_norm": 0.5281246304512024, + "learning_rate": 1.1223141054302665e-06, + "loss": 1.6132, + "step": 16753 + }, + { + "epoch": 0.9338386934953459, + "grad_norm": 0.6618608236312866, + "learning_rate": 1.120438879650354e-06, + "loss": 1.8055, + "step": 16754 + }, + { + "epoch": 0.933894431748509, + "grad_norm": 0.6179165244102478, + "learning_rate": 1.11856520404513e-06, + "loss": 1.4531, + "step": 16755 + }, + { + "epoch": 0.9339501700016721, + "grad_norm": 0.5813210010528564, + "learning_rate": 1.116693078674025e-06, + "loss": 1.7555, + "step": 16756 + }, + { + "epoch": 0.9340059082548353, + "grad_norm": 0.5596987009048462, + "learning_rate": 1.1148225035963966e-06, + "loss": 1.6048, + "step": 16757 + }, + { + "epoch": 0.9340616465079984, + "grad_norm": 0.5552729368209839, + "learning_rate": 1.1129534788715812e-06, + "loss": 1.5587, + "step": 16758 + }, + { + "epoch": 0.9341173847611616, + "grad_norm": 0.5551490187644958, + "learning_rate": 1.1110860045588589e-06, + "loss": 1.6526, + "step": 16759 + }, + { + "epoch": 0.9341731230143248, + "grad_norm": 0.6028414964675903, + "learning_rate": 1.109220080717438e-06, + "loss": 1.8698, + "step": 16760 + }, + { + "epoch": 0.9342288612674878, + "grad_norm": 0.5633191466331482, + "learning_rate": 1.1073557074065044e-06, + "loss": 1.5642, + "step": 16761 + }, + { + "epoch": 0.934284599520651, + "grad_norm": 0.6233230233192444, + "learning_rate": 1.105492884685183e-06, + "loss": 1.6282, + "step": 16762 + }, + { + "epoch": 0.9343403377738142, + "grad_norm": 0.5539950132369995, + "learning_rate": 1.10363161261256e-06, + "loss": 1.4938, + "step": 16763 + }, + { + "epoch": 0.9343960760269773, + "grad_norm": 0.5945073366165161, + "learning_rate": 1.1017718912476493e-06, + "loss": 1.6369, + "step": 16764 + }, + { + "epoch": 0.9344518142801405, + "grad_norm": 0.5230268836021423, + "learning_rate": 1.0999137206494314e-06, + "loss": 1.447, + "step": 16765 + }, + { + "epoch": 0.9345075525333036, + "grad_norm": 0.5577611923217773, + "learning_rate": 1.0980571008768592e-06, + "loss": 1.6531, + "step": 16766 + }, + { + "epoch": 0.9345632907864667, + "grad_norm": 0.5691031813621521, + "learning_rate": 1.0962020319887856e-06, + "loss": 1.6529, + "step": 16767 + }, + { + "epoch": 0.9346190290396299, + "grad_norm": 0.5706901550292969, + "learning_rate": 1.0943485140440578e-06, + "loss": 1.7453, + "step": 16768 + }, + { + "epoch": 0.9346747672927931, + "grad_norm": 0.611893355846405, + "learning_rate": 1.092496547101457e-06, + "loss": 1.9268, + "step": 16769 + }, + { + "epoch": 0.9347305055459562, + "grad_norm": 0.563347578048706, + "learning_rate": 1.0906461312197135e-06, + "loss": 1.5568, + "step": 16770 + }, + { + "epoch": 0.9347862437991193, + "grad_norm": 0.5679728984832764, + "learning_rate": 1.0887972664575141e-06, + "loss": 1.5729, + "step": 16771 + }, + { + "epoch": 0.9348419820522825, + "grad_norm": 0.5481329560279846, + "learning_rate": 1.0869499528734895e-06, + "loss": 1.6663, + "step": 16772 + }, + { + "epoch": 0.9348977203054456, + "grad_norm": 0.5482124090194702, + "learning_rate": 1.0851041905262372e-06, + "loss": 1.6167, + "step": 16773 + }, + { + "epoch": 0.9349534585586088, + "grad_norm": 0.5514622926712036, + "learning_rate": 1.0832599794742826e-06, + "loss": 1.5327, + "step": 16774 + }, + { + "epoch": 0.935009196811772, + "grad_norm": 0.5569831132888794, + "learning_rate": 1.0814173197761178e-06, + "loss": 1.8459, + "step": 16775 + }, + { + "epoch": 0.935064935064935, + "grad_norm": 0.5289499759674072, + "learning_rate": 1.0795762114901742e-06, + "loss": 1.6765, + "step": 16776 + }, + { + "epoch": 0.9351206733180982, + "grad_norm": 0.5781850814819336, + "learning_rate": 1.0777366546748547e-06, + "loss": 1.6937, + "step": 16777 + }, + { + "epoch": 0.9351764115712613, + "grad_norm": 0.5425864458084106, + "learning_rate": 1.075898649388496e-06, + "loss": 1.5319, + "step": 16778 + }, + { + "epoch": 0.9352321498244245, + "grad_norm": 0.527653157711029, + "learning_rate": 1.0740621956893736e-06, + "loss": 1.5061, + "step": 16779 + }, + { + "epoch": 0.9352878880775877, + "grad_norm": 0.5545275807380676, + "learning_rate": 1.072227293635747e-06, + "loss": 1.623, + "step": 16780 + }, + { + "epoch": 0.9353436263307507, + "grad_norm": 0.546058714389801, + "learning_rate": 1.0703939432857969e-06, + "loss": 1.657, + "step": 16781 + }, + { + "epoch": 0.9353993645839139, + "grad_norm": 0.5665484666824341, + "learning_rate": 1.0685621446976823e-06, + "loss": 1.6301, + "step": 16782 + }, + { + "epoch": 0.9354551028370771, + "grad_norm": 0.5558667182922363, + "learning_rate": 1.0667318979294739e-06, + "loss": 1.738, + "step": 16783 + }, + { + "epoch": 0.9355108410902402, + "grad_norm": 0.5884390473365784, + "learning_rate": 1.0649032030392304e-06, + "loss": 1.7667, + "step": 16784 + }, + { + "epoch": 0.9355665793434034, + "grad_norm": 0.5583817958831787, + "learning_rate": 1.0630760600849555e-06, + "loss": 1.5402, + "step": 16785 + }, + { + "epoch": 0.9356223175965666, + "grad_norm": 0.5457566976547241, + "learning_rate": 1.0612504691245807e-06, + "loss": 1.6312, + "step": 16786 + }, + { + "epoch": 0.9356780558497296, + "grad_norm": 0.5825153589248657, + "learning_rate": 1.059426430216004e-06, + "loss": 1.6652, + "step": 16787 + }, + { + "epoch": 0.9357337941028928, + "grad_norm": 0.6148772835731506, + "learning_rate": 1.0576039434170848e-06, + "loss": 1.3273, + "step": 16788 + }, + { + "epoch": 0.935789532356056, + "grad_norm": 0.5664966702461243, + "learning_rate": 1.0557830087856102e-06, + "loss": 1.6496, + "step": 16789 + }, + { + "epoch": 0.9358452706092191, + "grad_norm": 0.5659354329109192, + "learning_rate": 1.0539636263793394e-06, + "loss": 1.872, + "step": 16790 + }, + { + "epoch": 0.9359010088623823, + "grad_norm": 0.5623767375946045, + "learning_rate": 1.0521457962559545e-06, + "loss": 1.7581, + "step": 16791 + }, + { + "epoch": 0.9359567471155454, + "grad_norm": 0.5644464492797852, + "learning_rate": 1.050329518473131e-06, + "loss": 1.7107, + "step": 16792 + }, + { + "epoch": 0.9360124853687085, + "grad_norm": 0.5334804058074951, + "learning_rate": 1.0485147930884565e-06, + "loss": 1.5497, + "step": 16793 + }, + { + "epoch": 0.9360682236218717, + "grad_norm": 0.5793955326080322, + "learning_rate": 1.0467016201594849e-06, + "loss": 1.6007, + "step": 16794 + }, + { + "epoch": 0.9361239618750349, + "grad_norm": 0.5724888443946838, + "learning_rate": 1.0448899997437144e-06, + "loss": 1.7443, + "step": 16795 + }, + { + "epoch": 0.936179700128198, + "grad_norm": 0.6698756217956543, + "learning_rate": 1.0430799318986162e-06, + "loss": 2.0844, + "step": 16796 + }, + { + "epoch": 0.9362354383813611, + "grad_norm": 0.5882816910743713, + "learning_rate": 1.0412714166815773e-06, + "loss": 1.6163, + "step": 16797 + }, + { + "epoch": 0.9362911766345243, + "grad_norm": 0.5869001746177673, + "learning_rate": 1.0394644541499576e-06, + "loss": 1.7549, + "step": 16798 + }, + { + "epoch": 0.9363469148876874, + "grad_norm": 0.5883141756057739, + "learning_rate": 1.0376590443610723e-06, + "loss": 1.5603, + "step": 16799 + }, + { + "epoch": 0.9364026531408506, + "grad_norm": 0.6060160994529724, + "learning_rate": 1.0358551873721645e-06, + "loss": 1.7288, + "step": 16800 + }, + { + "epoch": 0.9364583913940137, + "grad_norm": 0.5904092788696289, + "learning_rate": 1.034052883240455e-06, + "loss": 1.6673, + "step": 16801 + }, + { + "epoch": 0.9365141296471768, + "grad_norm": 0.5603213310241699, + "learning_rate": 1.0322521320230927e-06, + "loss": 1.7246, + "step": 16802 + }, + { + "epoch": 0.93656986790034, + "grad_norm": 0.5533449649810791, + "learning_rate": 1.030452933777193e-06, + "loss": 1.6787, + "step": 16803 + }, + { + "epoch": 0.9366256061535031, + "grad_norm": 0.5495796799659729, + "learning_rate": 1.028655288559821e-06, + "loss": 1.4616, + "step": 16804 + }, + { + "epoch": 0.9366813444066663, + "grad_norm": 0.5743607878684998, + "learning_rate": 1.0268591964279707e-06, + "loss": 1.5618, + "step": 16805 + }, + { + "epoch": 0.9367370826598295, + "grad_norm": 0.5496140718460083, + "learning_rate": 1.025064657438618e-06, + "loss": 1.5928, + "step": 16806 + }, + { + "epoch": 0.9367928209129925, + "grad_norm": 0.5219504833221436, + "learning_rate": 1.0232716716486678e-06, + "loss": 1.4486, + "step": 16807 + }, + { + "epoch": 0.9368485591661557, + "grad_norm": 0.5510823130607605, + "learning_rate": 1.0214802391149914e-06, + "loss": 1.6045, + "step": 16808 + }, + { + "epoch": 0.9369042974193189, + "grad_norm": 0.5275538563728333, + "learning_rate": 1.0196903598943874e-06, + "loss": 1.5062, + "step": 16809 + }, + { + "epoch": 0.936960035672482, + "grad_norm": 0.5535945296287537, + "learning_rate": 1.0179020340436385e-06, + "loss": 1.5983, + "step": 16810 + }, + { + "epoch": 0.9370157739256452, + "grad_norm": 0.5571825504302979, + "learning_rate": 1.016115261619449e-06, + "loss": 1.5915, + "step": 16811 + }, + { + "epoch": 0.9370715121788084, + "grad_norm": 0.5676726698875427, + "learning_rate": 1.0143300426784906e-06, + "loss": 1.6147, + "step": 16812 + }, + { + "epoch": 0.9371272504319714, + "grad_norm": 0.576204776763916, + "learning_rate": 1.0125463772773735e-06, + "loss": 1.726, + "step": 16813 + }, + { + "epoch": 0.9371829886851346, + "grad_norm": 0.5400001406669617, + "learning_rate": 1.010764265472669e-06, + "loss": 1.589, + "step": 16814 + }, + { + "epoch": 0.9372387269382978, + "grad_norm": 0.5573274493217468, + "learning_rate": 1.0089837073208985e-06, + "loss": 1.764, + "step": 16815 + }, + { + "epoch": 0.9372944651914609, + "grad_norm": 0.5726682543754578, + "learning_rate": 1.0072047028785224e-06, + "loss": 1.651, + "step": 16816 + }, + { + "epoch": 0.937350203444624, + "grad_norm": 0.5456724762916565, + "learning_rate": 1.0054272522019626e-06, + "loss": 1.5316, + "step": 16817 + }, + { + "epoch": 0.9374059416977872, + "grad_norm": 0.5308707356452942, + "learning_rate": 1.0036513553476012e-06, + "loss": 1.475, + "step": 16818 + }, + { + "epoch": 0.9374616799509503, + "grad_norm": 0.5439468622207642, + "learning_rate": 1.0018770123717436e-06, + "loss": 1.3326, + "step": 16819 + }, + { + "epoch": 0.9375174182041135, + "grad_norm": 0.5625535249710083, + "learning_rate": 1.0001042233306723e-06, + "loss": 1.5274, + "step": 16820 + }, + { + "epoch": 0.9375731564572767, + "grad_norm": 0.5665705800056458, + "learning_rate": 9.983329882806037e-07, + "loss": 1.484, + "step": 16821 + }, + { + "epoch": 0.9376288947104398, + "grad_norm": 0.5897991061210632, + "learning_rate": 9.965633072777147e-07, + "loss": 1.5763, + "step": 16822 + }, + { + "epoch": 0.9376846329636029, + "grad_norm": 0.5494163632392883, + "learning_rate": 9.947951803781274e-07, + "loss": 1.5261, + "step": 16823 + }, + { + "epoch": 0.9377403712167661, + "grad_norm": 0.5441389679908752, + "learning_rate": 9.93028607637908e-07, + "loss": 1.6338, + "step": 16824 + }, + { + "epoch": 0.9377961094699292, + "grad_norm": 0.5666918754577637, + "learning_rate": 9.91263589113106e-07, + "loss": 1.6033, + "step": 16825 + }, + { + "epoch": 0.9378518477230924, + "grad_norm": 0.5893945693969727, + "learning_rate": 9.895001248596714e-07, + "loss": 1.6361, + "step": 16826 + }, + { + "epoch": 0.9379075859762555, + "grad_norm": 0.5792770981788635, + "learning_rate": 9.877382149335478e-07, + "loss": 1.6824, + "step": 16827 + }, + { + "epoch": 0.9379633242294186, + "grad_norm": 0.5937860012054443, + "learning_rate": 9.859778593906023e-07, + "loss": 1.9127, + "step": 16828 + }, + { + "epoch": 0.9380190624825818, + "grad_norm": 0.5455308556556702, + "learning_rate": 9.842190582866672e-07, + "loss": 1.4649, + "step": 16829 + }, + { + "epoch": 0.9380748007357449, + "grad_norm": 0.5718119740486145, + "learning_rate": 9.824618116775264e-07, + "loss": 1.6229, + "step": 16830 + }, + { + "epoch": 0.9381305389889081, + "grad_norm": 0.5994406938552856, + "learning_rate": 9.807061196189016e-07, + "loss": 1.8311, + "step": 16831 + }, + { + "epoch": 0.9381862772420713, + "grad_norm": 0.5260912775993347, + "learning_rate": 9.78951982166476e-07, + "loss": 1.3583, + "step": 16832 + }, + { + "epoch": 0.9382420154952343, + "grad_norm": 0.5482512712478638, + "learning_rate": 9.771993993758831e-07, + "loss": 1.5562, + "step": 16833 + }, + { + "epoch": 0.9382977537483975, + "grad_norm": 0.5522276759147644, + "learning_rate": 9.754483713027063e-07, + "loss": 1.644, + "step": 16834 + }, + { + "epoch": 0.9383534920015607, + "grad_norm": 0.5632951855659485, + "learning_rate": 9.73698898002462e-07, + "loss": 1.5279, + "step": 16835 + }, + { + "epoch": 0.9384092302547238, + "grad_norm": 0.5413833260536194, + "learning_rate": 9.719509795306559e-07, + "loss": 1.6109, + "step": 16836 + }, + { + "epoch": 0.938464968507887, + "grad_norm": 0.5463613271713257, + "learning_rate": 9.702046159427104e-07, + "loss": 1.4811, + "step": 16837 + }, + { + "epoch": 0.9385207067610501, + "grad_norm": 0.6515476703643799, + "learning_rate": 9.684598072940089e-07, + "loss": 1.9212, + "step": 16838 + }, + { + "epoch": 0.9385764450142132, + "grad_norm": 0.5356936454772949, + "learning_rate": 9.667165536398904e-07, + "loss": 1.4313, + "step": 16839 + }, + { + "epoch": 0.9386321832673764, + "grad_norm": 0.545353353023529, + "learning_rate": 9.64974855035633e-07, + "loss": 1.5254, + "step": 16840 + }, + { + "epoch": 0.9386879215205396, + "grad_norm": 0.5675305724143982, + "learning_rate": 9.632347115364871e-07, + "loss": 1.7144, + "step": 16841 + }, + { + "epoch": 0.9387436597737027, + "grad_norm": 0.539758026599884, + "learning_rate": 9.61496123197625e-07, + "loss": 1.604, + "step": 16842 + }, + { + "epoch": 0.9387993980268659, + "grad_norm": 0.5914060473442078, + "learning_rate": 9.597590900741916e-07, + "loss": 1.7027, + "step": 16843 + }, + { + "epoch": 0.938855136280029, + "grad_norm": 0.5827062129974365, + "learning_rate": 9.58023612221287e-07, + "loss": 1.6507, + "step": 16844 + }, + { + "epoch": 0.9389108745331921, + "grad_norm": 0.5714417695999146, + "learning_rate": 9.562896896939288e-07, + "loss": 1.6674, + "step": 16845 + }, + { + "epoch": 0.9389666127863553, + "grad_norm": 0.6030182242393494, + "learning_rate": 9.545573225471171e-07, + "loss": 1.7702, + "step": 16846 + }, + { + "epoch": 0.9390223510395185, + "grad_norm": 0.5809786915779114, + "learning_rate": 9.528265108357915e-07, + "loss": 1.9243, + "step": 16847 + }, + { + "epoch": 0.9390780892926816, + "grad_norm": 0.59272301197052, + "learning_rate": 9.510972546148522e-07, + "loss": 1.8476, + "step": 16848 + }, + { + "epoch": 0.9391338275458447, + "grad_norm": 0.6118817925453186, + "learning_rate": 9.493695539391278e-07, + "loss": 1.6859, + "step": 16849 + }, + { + "epoch": 0.9391895657990078, + "grad_norm": 0.5756952166557312, + "learning_rate": 9.476434088634078e-07, + "loss": 1.5396, + "step": 16850 + }, + { + "epoch": 0.939245304052171, + "grad_norm": 0.55875164270401, + "learning_rate": 9.459188194424595e-07, + "loss": 1.6498, + "step": 16851 + }, + { + "epoch": 0.9393010423053342, + "grad_norm": 0.5629695057868958, + "learning_rate": 9.441957857309502e-07, + "loss": 1.6658, + "step": 16852 + }, + { + "epoch": 0.9393567805584973, + "grad_norm": 0.51868736743927, + "learning_rate": 9.424743077835363e-07, + "loss": 1.2825, + "step": 16853 + }, + { + "epoch": 0.9394125188116604, + "grad_norm": 0.5891311168670654, + "learning_rate": 9.407543856548185e-07, + "loss": 1.8969, + "step": 16854 + }, + { + "epoch": 0.9394682570648236, + "grad_norm": 0.5700414776802063, + "learning_rate": 9.390360193993309e-07, + "loss": 1.6525, + "step": 16855 + }, + { + "epoch": 0.9395239953179867, + "grad_norm": 0.581132173538208, + "learning_rate": 9.373192090715799e-07, + "loss": 1.7488, + "step": 16856 + }, + { + "epoch": 0.9395797335711499, + "grad_norm": 0.5358730554580688, + "learning_rate": 9.356039547260054e-07, + "loss": 1.4556, + "step": 16857 + }, + { + "epoch": 0.9396354718243131, + "grad_norm": 0.587860107421875, + "learning_rate": 9.338902564170027e-07, + "loss": 1.6622, + "step": 16858 + }, + { + "epoch": 0.9396912100774761, + "grad_norm": 0.5048412680625916, + "learning_rate": 9.321781141989339e-07, + "loss": 1.3895, + "step": 16859 + }, + { + "epoch": 0.9397469483306393, + "grad_norm": 0.572661280632019, + "learning_rate": 9.304675281260889e-07, + "loss": 1.6764, + "step": 16860 + }, + { + "epoch": 0.9398026865838025, + "grad_norm": 0.5400744080543518, + "learning_rate": 9.287584982527131e-07, + "loss": 1.4854, + "step": 16861 + }, + { + "epoch": 0.9398584248369656, + "grad_norm": 0.5804818868637085, + "learning_rate": 9.270510246330188e-07, + "loss": 1.6977, + "step": 16862 + }, + { + "epoch": 0.9399141630901288, + "grad_norm": 0.5581326484680176, + "learning_rate": 9.253451073211517e-07, + "loss": 1.5387, + "step": 16863 + }, + { + "epoch": 0.939969901343292, + "grad_norm": 0.5778710842132568, + "learning_rate": 9.236407463712071e-07, + "loss": 1.6416, + "step": 16864 + }, + { + "epoch": 0.940025639596455, + "grad_norm": 0.6114763617515564, + "learning_rate": 9.219379418372476e-07, + "loss": 1.722, + "step": 16865 + }, + { + "epoch": 0.9400813778496182, + "grad_norm": 0.5990073084831238, + "learning_rate": 9.202366937732687e-07, + "loss": 1.5153, + "step": 16866 + }, + { + "epoch": 0.9401371161027814, + "grad_norm": 0.5689799785614014, + "learning_rate": 9.185370022332274e-07, + "loss": 1.6314, + "step": 16867 + }, + { + "epoch": 0.9401928543559445, + "grad_norm": 0.6560726165771484, + "learning_rate": 9.168388672710248e-07, + "loss": 1.9229, + "step": 16868 + }, + { + "epoch": 0.9402485926091076, + "grad_norm": 0.5391461253166199, + "learning_rate": 9.151422889405237e-07, + "loss": 1.6497, + "step": 16869 + }, + { + "epoch": 0.9403043308622708, + "grad_norm": 0.5034330487251282, + "learning_rate": 9.134472672955252e-07, + "loss": 1.4396, + "step": 16870 + }, + { + "epoch": 0.9403600691154339, + "grad_norm": 0.5862897634506226, + "learning_rate": 9.117538023897809e-07, + "loss": 1.6452, + "step": 16871 + }, + { + "epoch": 0.9404158073685971, + "grad_norm": 0.5404767394065857, + "learning_rate": 9.100618942770034e-07, + "loss": 1.6783, + "step": 16872 + }, + { + "epoch": 0.9404715456217602, + "grad_norm": 0.558737576007843, + "learning_rate": 9.083715430108497e-07, + "loss": 1.4322, + "step": 16873 + }, + { + "epoch": 0.9405272838749233, + "grad_norm": 0.5557568073272705, + "learning_rate": 9.06682748644927e-07, + "loss": 1.6379, + "step": 16874 + }, + { + "epoch": 0.9405830221280865, + "grad_norm": 0.5563536882400513, + "learning_rate": 9.049955112327923e-07, + "loss": 1.7436, + "step": 16875 + }, + { + "epoch": 0.9406387603812496, + "grad_norm": 0.5667238831520081, + "learning_rate": 9.033098308279475e-07, + "loss": 1.5094, + "step": 16876 + }, + { + "epoch": 0.9406944986344128, + "grad_norm": 0.5954780578613281, + "learning_rate": 9.016257074838775e-07, + "loss": 1.5522, + "step": 16877 + }, + { + "epoch": 0.940750236887576, + "grad_norm": 0.5526831150054932, + "learning_rate": 8.999431412539672e-07, + "loss": 1.5814, + "step": 16878 + }, + { + "epoch": 0.940805975140739, + "grad_norm": 0.5897734761238098, + "learning_rate": 8.982621321915852e-07, + "loss": 1.7722, + "step": 16879 + }, + { + "epoch": 0.9408617133939022, + "grad_norm": 0.5578067302703857, + "learning_rate": 8.965826803500499e-07, + "loss": 1.2975, + "step": 16880 + }, + { + "epoch": 0.9409174516470654, + "grad_norm": 0.5925698280334473, + "learning_rate": 8.949047857826242e-07, + "loss": 1.7634, + "step": 16881 + }, + { + "epoch": 0.9409731899002285, + "grad_norm": 0.6634193062782288, + "learning_rate": 8.932284485425102e-07, + "loss": 1.6529, + "step": 16882 + }, + { + "epoch": 0.9410289281533917, + "grad_norm": 0.5800929069519043, + "learning_rate": 8.915536686828763e-07, + "loss": 1.6217, + "step": 16883 + }, + { + "epoch": 0.9410846664065549, + "grad_norm": 0.6004784107208252, + "learning_rate": 8.898804462568355e-07, + "loss": 1.8195, + "step": 16884 + }, + { + "epoch": 0.9411404046597179, + "grad_norm": 0.5862502455711365, + "learning_rate": 8.882087813174622e-07, + "loss": 1.6975, + "step": 16885 + }, + { + "epoch": 0.9411961429128811, + "grad_norm": 0.5823085904121399, + "learning_rate": 8.865386739177639e-07, + "loss": 1.6651, + "step": 16886 + }, + { + "epoch": 0.9412518811660443, + "grad_norm": 0.5541600584983826, + "learning_rate": 8.848701241106982e-07, + "loss": 1.8084, + "step": 16887 + }, + { + "epoch": 0.9413076194192074, + "grad_norm": 0.5641975998878479, + "learning_rate": 8.832031319492007e-07, + "loss": 1.5518, + "step": 16888 + }, + { + "epoch": 0.9413633576723706, + "grad_norm": 0.5984840393066406, + "learning_rate": 8.815376974861289e-07, + "loss": 1.6356, + "step": 16889 + }, + { + "epoch": 0.9414190959255337, + "grad_norm": 0.5587028861045837, + "learning_rate": 8.798738207742963e-07, + "loss": 1.6015, + "step": 16890 + }, + { + "epoch": 0.9414748341786968, + "grad_norm": 0.5777599811553955, + "learning_rate": 8.782115018664771e-07, + "loss": 1.5823, + "step": 16891 + }, + { + "epoch": 0.94153057243186, + "grad_norm": 0.5491505265235901, + "learning_rate": 8.765507408153906e-07, + "loss": 1.5989, + "step": 16892 + }, + { + "epoch": 0.9415863106850232, + "grad_norm": 0.5884366631507874, + "learning_rate": 8.748915376737054e-07, + "loss": 1.8058, + "step": 16893 + }, + { + "epoch": 0.9416420489381863, + "grad_norm": 0.5464414358139038, + "learning_rate": 8.732338924940353e-07, + "loss": 1.617, + "step": 16894 + }, + { + "epoch": 0.9416977871913494, + "grad_norm": 0.5510953068733215, + "learning_rate": 8.715778053289603e-07, + "loss": 1.554, + "step": 16895 + }, + { + "epoch": 0.9417535254445125, + "grad_norm": 0.5908687710762024, + "learning_rate": 8.69923276231005e-07, + "loss": 1.5602, + "step": 16896 + }, + { + "epoch": 0.9418092636976757, + "grad_norm": 0.5835829973220825, + "learning_rate": 8.682703052526331e-07, + "loss": 1.7909, + "step": 16897 + }, + { + "epoch": 0.9418650019508389, + "grad_norm": 0.5421337485313416, + "learning_rate": 8.666188924462637e-07, + "loss": 1.5703, + "step": 16898 + }, + { + "epoch": 0.941920740204002, + "grad_norm": 0.6531662344932556, + "learning_rate": 8.649690378642772e-07, + "loss": 1.4395, + "step": 16899 + }, + { + "epoch": 0.9419764784571651, + "grad_norm": 0.520761251449585, + "learning_rate": 8.633207415590039e-07, + "loss": 1.478, + "step": 16900 + }, + { + "epoch": 0.9420322167103283, + "grad_norm": 0.5745235085487366, + "learning_rate": 8.61674003582702e-07, + "loss": 1.8977, + "step": 16901 + }, + { + "epoch": 0.9420879549634914, + "grad_norm": 0.5429668426513672, + "learning_rate": 8.60028823987602e-07, + "loss": 1.522, + "step": 16902 + }, + { + "epoch": 0.9421436932166546, + "grad_norm": 0.5769269466400146, + "learning_rate": 8.583852028258899e-07, + "loss": 1.6179, + "step": 16903 + }, + { + "epoch": 0.9421994314698178, + "grad_norm": 0.5333672761917114, + "learning_rate": 8.567431401496795e-07, + "loss": 1.3213, + "step": 16904 + }, + { + "epoch": 0.9422551697229808, + "grad_norm": 0.5411314964294434, + "learning_rate": 8.551026360110458e-07, + "loss": 1.421, + "step": 16905 + }, + { + "epoch": 0.942310907976144, + "grad_norm": 0.5387500524520874, + "learning_rate": 8.534636904620308e-07, + "loss": 1.5467, + "step": 16906 + }, + { + "epoch": 0.9423666462293072, + "grad_norm": 0.5943649411201477, + "learning_rate": 8.518263035546037e-07, + "loss": 1.7246, + "step": 16907 + }, + { + "epoch": 0.9424223844824703, + "grad_norm": 0.5774201154708862, + "learning_rate": 8.501904753406898e-07, + "loss": 1.5566, + "step": 16908 + }, + { + "epoch": 0.9424781227356335, + "grad_norm": 0.5977226495742798, + "learning_rate": 8.485562058721641e-07, + "loss": 1.5759, + "step": 16909 + }, + { + "epoch": 0.9425338609887967, + "grad_norm": 0.5736502408981323, + "learning_rate": 8.469234952008687e-07, + "loss": 1.6642, + "step": 16910 + }, + { + "epoch": 0.9425895992419597, + "grad_norm": 0.5714553594589233, + "learning_rate": 8.452923433785787e-07, + "loss": 1.6105, + "step": 16911 + }, + { + "epoch": 0.9426453374951229, + "grad_norm": 0.5020471811294556, + "learning_rate": 8.436627504570249e-07, + "loss": 1.455, + "step": 16912 + }, + { + "epoch": 0.9427010757482861, + "grad_norm": 0.5730252265930176, + "learning_rate": 8.420347164878828e-07, + "loss": 1.5826, + "step": 16913 + }, + { + "epoch": 0.9427568140014492, + "grad_norm": 0.56931471824646, + "learning_rate": 8.404082415227887e-07, + "loss": 1.5373, + "step": 16914 + }, + { + "epoch": 0.9428125522546124, + "grad_norm": 0.5473915338516235, + "learning_rate": 8.387833256133292e-07, + "loss": 1.5081, + "step": 16915 + }, + { + "epoch": 0.9428682905077755, + "grad_norm": 0.5750105977058411, + "learning_rate": 8.371599688110299e-07, + "loss": 1.7214, + "step": 16916 + }, + { + "epoch": 0.9429240287609386, + "grad_norm": 0.5435006022453308, + "learning_rate": 8.355381711673771e-07, + "loss": 1.571, + "step": 16917 + }, + { + "epoch": 0.9429797670141018, + "grad_norm": 0.525737464427948, + "learning_rate": 8.339179327338076e-07, + "loss": 1.4953, + "step": 16918 + }, + { + "epoch": 0.9430355052672649, + "grad_norm": 0.5566396117210388, + "learning_rate": 8.322992535617025e-07, + "loss": 1.7961, + "step": 16919 + }, + { + "epoch": 0.9430912435204281, + "grad_norm": 0.6126981973648071, + "learning_rate": 8.306821337023929e-07, + "loss": 1.8401, + "step": 16920 + }, + { + "epoch": 0.9431469817735912, + "grad_norm": 0.5546177625656128, + "learning_rate": 8.290665732071711e-07, + "loss": 1.4785, + "step": 16921 + }, + { + "epoch": 0.9432027200267543, + "grad_norm": 0.5737544298171997, + "learning_rate": 8.274525721272741e-07, + "loss": 1.7048, + "step": 16922 + }, + { + "epoch": 0.9432584582799175, + "grad_norm": 0.5518257021903992, + "learning_rate": 8.258401305138885e-07, + "loss": 1.508, + "step": 16923 + }, + { + "epoch": 0.9433141965330807, + "grad_norm": 0.5299418568611145, + "learning_rate": 8.242292484181402e-07, + "loss": 1.4915, + "step": 16924 + }, + { + "epoch": 0.9433699347862438, + "grad_norm": 0.5615280270576477, + "learning_rate": 8.226199258911327e-07, + "loss": 1.6707, + "step": 16925 + }, + { + "epoch": 0.9434256730394069, + "grad_norm": 0.5303876996040344, + "learning_rate": 8.210121629838918e-07, + "loss": 1.5004, + "step": 16926 + }, + { + "epoch": 0.9434814112925701, + "grad_norm": 0.5471112728118896, + "learning_rate": 8.194059597474158e-07, + "loss": 1.5514, + "step": 16927 + }, + { + "epoch": 0.9435371495457332, + "grad_norm": 0.6098458766937256, + "learning_rate": 8.178013162326359e-07, + "loss": 1.7864, + "step": 16928 + }, + { + "epoch": 0.9435928877988964, + "grad_norm": 0.5647457838058472, + "learning_rate": 8.161982324904505e-07, + "loss": 1.64, + "step": 16929 + }, + { + "epoch": 0.9436486260520596, + "grad_norm": 0.835615873336792, + "learning_rate": 8.14596708571691e-07, + "loss": 1.6564, + "step": 16930 + }, + { + "epoch": 0.9437043643052226, + "grad_norm": 0.5723029375076294, + "learning_rate": 8.129967445271558e-07, + "loss": 1.6213, + "step": 16931 + }, + { + "epoch": 0.9437601025583858, + "grad_norm": 0.6130080223083496, + "learning_rate": 8.11398340407582e-07, + "loss": 1.7619, + "step": 16932 + }, + { + "epoch": 0.943815840811549, + "grad_norm": 0.5904813408851624, + "learning_rate": 8.09801496263668e-07, + "loss": 1.7034, + "step": 16933 + }, + { + "epoch": 0.9438715790647121, + "grad_norm": 0.5444279909133911, + "learning_rate": 8.08206212146051e-07, + "loss": 1.632, + "step": 16934 + }, + { + "epoch": 0.9439273173178753, + "grad_norm": 0.5795121192932129, + "learning_rate": 8.066124881053183e-07, + "loss": 1.6041, + "step": 16935 + }, + { + "epoch": 0.9439830555710385, + "grad_norm": 0.5348795652389526, + "learning_rate": 8.05020324192024e-07, + "loss": 1.5342, + "step": 16936 + }, + { + "epoch": 0.9440387938242015, + "grad_norm": 0.605394721031189, + "learning_rate": 8.03429720456661e-07, + "loss": 1.8362, + "step": 16937 + }, + { + "epoch": 0.9440945320773647, + "grad_norm": 0.5863170027732849, + "learning_rate": 8.018406769496722e-07, + "loss": 1.7253, + "step": 16938 + }, + { + "epoch": 0.9441502703305279, + "grad_norm": 0.5727696418762207, + "learning_rate": 8.002531937214452e-07, + "loss": 1.7858, + "step": 16939 + }, + { + "epoch": 0.944206008583691, + "grad_norm": 0.607088565826416, + "learning_rate": 7.986672708223341e-07, + "loss": 1.6108, + "step": 16940 + }, + { + "epoch": 0.9442617468368542, + "grad_norm": 0.5421030521392822, + "learning_rate": 7.970829083026377e-07, + "loss": 1.4481, + "step": 16941 + }, + { + "epoch": 0.9443174850900172, + "grad_norm": 0.6223423480987549, + "learning_rate": 7.955001062125988e-07, + "loss": 1.8286, + "step": 16942 + }, + { + "epoch": 0.9443732233431804, + "grad_norm": 0.5516008138656616, + "learning_rate": 7.93918864602411e-07, + "loss": 1.6667, + "step": 16943 + }, + { + "epoch": 0.9444289615963436, + "grad_norm": 0.5771745443344116, + "learning_rate": 7.923391835222227e-07, + "loss": 1.6067, + "step": 16944 + }, + { + "epoch": 0.9444846998495067, + "grad_norm": 0.6209045648574829, + "learning_rate": 7.90761063022144e-07, + "loss": 1.7842, + "step": 16945 + }, + { + "epoch": 0.9445404381026699, + "grad_norm": 0.5578152537345886, + "learning_rate": 7.891845031522072e-07, + "loss": 1.7356, + "step": 16946 + }, + { + "epoch": 0.944596176355833, + "grad_norm": 0.551343560218811, + "learning_rate": 7.876095039624165e-07, + "loss": 1.3916, + "step": 16947 + }, + { + "epoch": 0.9446519146089961, + "grad_norm": 0.550447404384613, + "learning_rate": 7.860360655027377e-07, + "loss": 1.732, + "step": 16948 + }, + { + "epoch": 0.9447076528621593, + "grad_norm": 0.5752705931663513, + "learning_rate": 7.844641878230474e-07, + "loss": 1.6551, + "step": 16949 + }, + { + "epoch": 0.9447633911153225, + "grad_norm": 0.5619220733642578, + "learning_rate": 7.828938709732059e-07, + "loss": 1.4815, + "step": 16950 + }, + { + "epoch": 0.9448191293684856, + "grad_norm": 0.5495359301567078, + "learning_rate": 7.813251150030176e-07, + "loss": 1.5795, + "step": 16951 + }, + { + "epoch": 0.9448748676216487, + "grad_norm": 0.5434496402740479, + "learning_rate": 7.797579199622318e-07, + "loss": 1.7019, + "step": 16952 + }, + { + "epoch": 0.9449306058748119, + "grad_norm": 0.574411153793335, + "learning_rate": 7.78192285900553e-07, + "loss": 1.5984, + "step": 16953 + }, + { + "epoch": 0.944986344127975, + "grad_norm": 0.5779029726982117, + "learning_rate": 7.76628212867625e-07, + "loss": 1.6128, + "step": 16954 + }, + { + "epoch": 0.9450420823811382, + "grad_norm": 0.5680252313613892, + "learning_rate": 7.750657009130635e-07, + "loss": 1.7367, + "step": 16955 + }, + { + "epoch": 0.9450978206343014, + "grad_norm": 0.5338242053985596, + "learning_rate": 7.735047500864179e-07, + "loss": 1.4785, + "step": 16956 + }, + { + "epoch": 0.9451535588874644, + "grad_norm": 0.5744556784629822, + "learning_rate": 7.719453604371874e-07, + "loss": 1.5787, + "step": 16957 + }, + { + "epoch": 0.9452092971406276, + "grad_norm": 0.6012402176856995, + "learning_rate": 7.703875320148323e-07, + "loss": 1.9061, + "step": 16958 + }, + { + "epoch": 0.9452650353937908, + "grad_norm": 0.5857225060462952, + "learning_rate": 7.688312648687579e-07, + "loss": 1.681, + "step": 16959 + }, + { + "epoch": 0.9453207736469539, + "grad_norm": 0.5835810303688049, + "learning_rate": 7.672765590483133e-07, + "loss": 1.6794, + "step": 16960 + }, + { + "epoch": 0.9453765119001171, + "grad_norm": 0.5841832160949707, + "learning_rate": 7.657234146028092e-07, + "loss": 1.6617, + "step": 16961 + }, + { + "epoch": 0.9454322501532803, + "grad_norm": 0.5425101518630981, + "learning_rate": 7.641718315815116e-07, + "loss": 1.5476, + "step": 16962 + }, + { + "epoch": 0.9454879884064433, + "grad_norm": 0.6066599488258362, + "learning_rate": 7.626218100336091e-07, + "loss": 1.9378, + "step": 16963 + }, + { + "epoch": 0.9455437266596065, + "grad_norm": 0.5384292006492615, + "learning_rate": 7.610733500082789e-07, + "loss": 1.3775, + "step": 16964 + }, + { + "epoch": 0.9455994649127696, + "grad_norm": 0.5869914889335632, + "learning_rate": 7.595264515546097e-07, + "loss": 1.6954, + "step": 16965 + }, + { + "epoch": 0.9456552031659328, + "grad_norm": 0.5561032295227051, + "learning_rate": 7.579811147216731e-07, + "loss": 1.6822, + "step": 16966 + }, + { + "epoch": 0.945710941419096, + "grad_norm": 0.5475266575813293, + "learning_rate": 7.564373395584745e-07, + "loss": 1.6487, + "step": 16967 + }, + { + "epoch": 0.945766679672259, + "grad_norm": 0.5417787432670593, + "learning_rate": 7.548951261139747e-07, + "loss": 1.552, + "step": 16968 + }, + { + "epoch": 0.9458224179254222, + "grad_norm": 0.5482089519500732, + "learning_rate": 7.53354474437079e-07, + "loss": 1.5766, + "step": 16969 + }, + { + "epoch": 0.9458781561785854, + "grad_norm": 0.542628288269043, + "learning_rate": 7.51815384576654e-07, + "loss": 1.519, + "step": 16970 + }, + { + "epoch": 0.9459338944317485, + "grad_norm": 0.5261123180389404, + "learning_rate": 7.502778565815105e-07, + "loss": 1.4053, + "step": 16971 + }, + { + "epoch": 0.9459896326849117, + "grad_norm": 0.58245849609375, + "learning_rate": 7.48741890500404e-07, + "loss": 1.5938, + "step": 16972 + }, + { + "epoch": 0.9460453709380748, + "grad_norm": 0.6295725107192993, + "learning_rate": 7.472074863820511e-07, + "loss": 1.7217, + "step": 16973 + }, + { + "epoch": 0.9461011091912379, + "grad_norm": 0.5577417016029358, + "learning_rate": 7.456746442751129e-07, + "loss": 1.5028, + "step": 16974 + }, + { + "epoch": 0.9461568474444011, + "grad_norm": 0.5512625575065613, + "learning_rate": 7.441433642282059e-07, + "loss": 1.5843, + "step": 16975 + }, + { + "epoch": 0.9462125856975643, + "grad_norm": 0.5793192982673645, + "learning_rate": 7.426136462898859e-07, + "loss": 1.456, + "step": 16976 + }, + { + "epoch": 0.9462683239507274, + "grad_norm": 0.5469534993171692, + "learning_rate": 7.410854905086695e-07, + "loss": 1.654, + "step": 16977 + }, + { + "epoch": 0.9463240622038905, + "grad_norm": 0.5659774541854858, + "learning_rate": 7.395588969330292e-07, + "loss": 1.5899, + "step": 16978 + }, + { + "epoch": 0.9463798004570537, + "grad_norm": 0.566008985042572, + "learning_rate": 7.38033865611365e-07, + "loss": 1.6535, + "step": 16979 + }, + { + "epoch": 0.9464355387102168, + "grad_norm": 0.5535767674446106, + "learning_rate": 7.365103965920439e-07, + "loss": 1.5952, + "step": 16980 + }, + { + "epoch": 0.94649127696338, + "grad_norm": 0.5583308339118958, + "learning_rate": 7.349884899233994e-07, + "loss": 1.6768, + "step": 16981 + }, + { + "epoch": 0.9465470152165432, + "grad_norm": 0.6059837937355042, + "learning_rate": 7.334681456536818e-07, + "loss": 1.7187, + "step": 16982 + }, + { + "epoch": 0.9466027534697062, + "grad_norm": 0.5808477997779846, + "learning_rate": 7.319493638311082e-07, + "loss": 1.6883, + "step": 16983 + }, + { + "epoch": 0.9466584917228694, + "grad_norm": 0.48394033312797546, + "learning_rate": 7.304321445038453e-07, + "loss": 1.2998, + "step": 16984 + }, + { + "epoch": 0.9467142299760326, + "grad_norm": 0.5622145533561707, + "learning_rate": 7.289164877200216e-07, + "loss": 1.7541, + "step": 16985 + }, + { + "epoch": 0.9467699682291957, + "grad_norm": 0.5846502780914307, + "learning_rate": 7.27402393527693e-07, + "loss": 1.6901, + "step": 16986 + }, + { + "epoch": 0.9468257064823589, + "grad_norm": 0.5269169807434082, + "learning_rate": 7.258898619748767e-07, + "loss": 1.3803, + "step": 16987 + }, + { + "epoch": 0.9468814447355219, + "grad_norm": 0.5600767135620117, + "learning_rate": 7.243788931095508e-07, + "loss": 1.6025, + "step": 16988 + }, + { + "epoch": 0.9469371829886851, + "grad_norm": 0.5525202751159668, + "learning_rate": 7.228694869796271e-07, + "loss": 1.5792, + "step": 16989 + }, + { + "epoch": 0.9469929212418483, + "grad_norm": 0.5616320967674255, + "learning_rate": 7.21361643632984e-07, + "loss": 1.8059, + "step": 16990 + }, + { + "epoch": 0.9470486594950114, + "grad_norm": 0.6212959885597229, + "learning_rate": 7.198553631174221e-07, + "loss": 1.9646, + "step": 16991 + }, + { + "epoch": 0.9471043977481746, + "grad_norm": 0.5984450578689575, + "learning_rate": 7.183506454807365e-07, + "loss": 1.7726, + "step": 16992 + }, + { + "epoch": 0.9471601360013377, + "grad_norm": 0.5685959458351135, + "learning_rate": 7.168474907706335e-07, + "loss": 1.645, + "step": 16993 + }, + { + "epoch": 0.9472158742545008, + "grad_norm": 0.5834311842918396, + "learning_rate": 7.153458990347861e-07, + "loss": 1.4872, + "step": 16994 + }, + { + "epoch": 0.947271612507664, + "grad_norm": 0.5570898652076721, + "learning_rate": 7.138458703208173e-07, + "loss": 1.6738, + "step": 16995 + }, + { + "epoch": 0.9473273507608272, + "grad_norm": 0.5605740547180176, + "learning_rate": 7.123474046763002e-07, + "loss": 1.7239, + "step": 16996 + }, + { + "epoch": 0.9473830890139903, + "grad_norm": 0.5445290803909302, + "learning_rate": 7.108505021487577e-07, + "loss": 1.6759, + "step": 16997 + }, + { + "epoch": 0.9474388272671534, + "grad_norm": 0.5455150008201599, + "learning_rate": 7.093551627856576e-07, + "loss": 1.5727, + "step": 16998 + }, + { + "epoch": 0.9474945655203166, + "grad_norm": 0.5549116134643555, + "learning_rate": 7.078613866344286e-07, + "loss": 1.6551, + "step": 16999 + }, + { + "epoch": 0.9475503037734797, + "grad_norm": 0.5562629103660583, + "learning_rate": 7.063691737424494e-07, + "loss": 1.4096, + "step": 17000 + }, + { + "epoch": 0.9476060420266429, + "grad_norm": 0.5963786244392395, + "learning_rate": 7.048785241570321e-07, + "loss": 1.5989, + "step": 17001 + }, + { + "epoch": 0.9476617802798061, + "grad_norm": 0.5290612578392029, + "learning_rate": 7.033894379254557e-07, + "loss": 1.4911, + "step": 17002 + }, + { + "epoch": 0.9477175185329691, + "grad_norm": 0.5972602963447571, + "learning_rate": 7.019019150949546e-07, + "loss": 1.6911, + "step": 17003 + }, + { + "epoch": 0.9477732567861323, + "grad_norm": 0.5170223116874695, + "learning_rate": 7.00415955712691e-07, + "loss": 1.3522, + "step": 17004 + }, + { + "epoch": 0.9478289950392955, + "grad_norm": 0.5839651823043823, + "learning_rate": 6.989315598257995e-07, + "loss": 1.6699, + "step": 17005 + }, + { + "epoch": 0.9478847332924586, + "grad_norm": 0.5812819004058838, + "learning_rate": 6.974487274813479e-07, + "loss": 1.6929, + "step": 17006 + }, + { + "epoch": 0.9479404715456218, + "grad_norm": 0.5574496388435364, + "learning_rate": 6.959674587263765e-07, + "loss": 1.6404, + "step": 17007 + }, + { + "epoch": 0.947996209798785, + "grad_norm": 0.5795475244522095, + "learning_rate": 6.944877536078531e-07, + "loss": 1.5798, + "step": 17008 + }, + { + "epoch": 0.948051948051948, + "grad_norm": 0.5303933024406433, + "learning_rate": 6.93009612172707e-07, + "loss": 1.4725, + "step": 17009 + }, + { + "epoch": 0.9481076863051112, + "grad_norm": 0.5569559335708618, + "learning_rate": 6.915330344678117e-07, + "loss": 1.5175, + "step": 17010 + }, + { + "epoch": 0.9481634245582743, + "grad_norm": 0.6014468669891357, + "learning_rate": 6.900580205400076e-07, + "loss": 1.7627, + "step": 17011 + }, + { + "epoch": 0.9482191628114375, + "grad_norm": 0.5283464193344116, + "learning_rate": 6.885845704360627e-07, + "loss": 1.494, + "step": 17012 + }, + { + "epoch": 0.9482749010646007, + "grad_norm": 0.5729781985282898, + "learning_rate": 6.871126842027064e-07, + "loss": 1.5726, + "step": 17013 + }, + { + "epoch": 0.9483306393177637, + "grad_norm": 0.5762726664543152, + "learning_rate": 6.856423618866237e-07, + "loss": 1.7376, + "step": 17014 + }, + { + "epoch": 0.9483863775709269, + "grad_norm": 0.6001695990562439, + "learning_rate": 6.841736035344437e-07, + "loss": 1.6236, + "step": 17015 + }, + { + "epoch": 0.9484421158240901, + "grad_norm": 0.5503683090209961, + "learning_rate": 6.82706409192746e-07, + "loss": 1.583, + "step": 17016 + }, + { + "epoch": 0.9484978540772532, + "grad_norm": 0.5634928941726685, + "learning_rate": 6.812407789080599e-07, + "loss": 1.5396, + "step": 17017 + }, + { + "epoch": 0.9485535923304164, + "grad_norm": 0.5767964124679565, + "learning_rate": 6.797767127268706e-07, + "loss": 1.5526, + "step": 17018 + }, + { + "epoch": 0.9486093305835795, + "grad_norm": 0.5399457812309265, + "learning_rate": 6.783142106956075e-07, + "loss": 1.5421, + "step": 17019 + }, + { + "epoch": 0.9486650688367426, + "grad_norm": 0.5682318806648254, + "learning_rate": 6.768532728606502e-07, + "loss": 1.6919, + "step": 17020 + }, + { + "epoch": 0.9487208070899058, + "grad_norm": 0.5837402939796448, + "learning_rate": 6.753938992683339e-07, + "loss": 1.7134, + "step": 17021 + }, + { + "epoch": 0.948776545343069, + "grad_norm": 0.6359543204307556, + "learning_rate": 6.739360899649383e-07, + "loss": 1.7222, + "step": 17022 + }, + { + "epoch": 0.9488322835962321, + "grad_norm": 0.5625662803649902, + "learning_rate": 6.724798449967041e-07, + "loss": 1.631, + "step": 17023 + }, + { + "epoch": 0.9488880218493952, + "grad_norm": 0.6394003033638, + "learning_rate": 6.710251644097998e-07, + "loss": 1.8997, + "step": 17024 + }, + { + "epoch": 0.9489437601025584, + "grad_norm": 0.5707859992980957, + "learning_rate": 6.695720482503776e-07, + "loss": 1.7108, + "step": 17025 + }, + { + "epoch": 0.9489994983557215, + "grad_norm": 0.6031056046485901, + "learning_rate": 6.681204965645171e-07, + "loss": 1.7563, + "step": 17026 + }, + { + "epoch": 0.9490552366088847, + "grad_norm": 0.5597089529037476, + "learning_rate": 6.666705093982428e-07, + "loss": 1.6225, + "step": 17027 + }, + { + "epoch": 0.9491109748620479, + "grad_norm": 0.5538654327392578, + "learning_rate": 6.652220867975456e-07, + "loss": 1.5518, + "step": 17028 + }, + { + "epoch": 0.949166713115211, + "grad_norm": 0.5561701059341431, + "learning_rate": 6.637752288083666e-07, + "loss": 1.6425, + "step": 17029 + }, + { + "epoch": 0.9492224513683741, + "grad_norm": 0.5365672707557678, + "learning_rate": 6.623299354765911e-07, + "loss": 1.45, + "step": 17030 + }, + { + "epoch": 0.9492781896215373, + "grad_norm": 0.5727249383926392, + "learning_rate": 6.608862068480437e-07, + "loss": 1.4817, + "step": 17031 + }, + { + "epoch": 0.9493339278747004, + "grad_norm": 0.5486777424812317, + "learning_rate": 6.594440429685156e-07, + "loss": 1.4503, + "step": 17032 + }, + { + "epoch": 0.9493896661278636, + "grad_norm": 0.5862206220626831, + "learning_rate": 6.58003443883759e-07, + "loss": 1.7839, + "step": 17033 + }, + { + "epoch": 0.9494454043810266, + "grad_norm": 0.6015295386314392, + "learning_rate": 6.56564409639443e-07, + "loss": 1.8742, + "step": 17034 + }, + { + "epoch": 0.9495011426341898, + "grad_norm": 0.5946756601333618, + "learning_rate": 6.551269402812088e-07, + "loss": 1.7448, + "step": 17035 + }, + { + "epoch": 0.949556880887353, + "grad_norm": 0.5743675827980042, + "learning_rate": 6.536910358546477e-07, + "loss": 1.5972, + "step": 17036 + }, + { + "epoch": 0.9496126191405161, + "grad_norm": 0.6118848919868469, + "learning_rate": 6.522566964053068e-07, + "loss": 1.8572, + "step": 17037 + }, + { + "epoch": 0.9496683573936793, + "grad_norm": 0.5464027523994446, + "learning_rate": 6.508239219786605e-07, + "loss": 1.4599, + "step": 17038 + }, + { + "epoch": 0.9497240956468425, + "grad_norm": 0.537115752696991, + "learning_rate": 6.493927126201504e-07, + "loss": 1.5872, + "step": 17039 + }, + { + "epoch": 0.9497798339000055, + "grad_norm": 0.5763193368911743, + "learning_rate": 6.479630683751736e-07, + "loss": 1.6558, + "step": 17040 + }, + { + "epoch": 0.9498355721531687, + "grad_norm": 0.504616916179657, + "learning_rate": 6.465349892890659e-07, + "loss": 1.4328, + "step": 17041 + }, + { + "epoch": 0.9498913104063319, + "grad_norm": 0.5546362400054932, + "learning_rate": 6.451084754071135e-07, + "loss": 1.5492, + "step": 17042 + }, + { + "epoch": 0.949947048659495, + "grad_norm": 0.5468747019767761, + "learning_rate": 6.436835267745634e-07, + "loss": 1.567, + "step": 17043 + }, + { + "epoch": 0.9500027869126582, + "grad_norm": 0.5787795186042786, + "learning_rate": 6.422601434366071e-07, + "loss": 1.667, + "step": 17044 + }, + { + "epoch": 0.9500585251658213, + "grad_norm": 0.5407884120941162, + "learning_rate": 6.408383254383809e-07, + "loss": 1.4466, + "step": 17045 + }, + { + "epoch": 0.9501142634189844, + "grad_norm": 0.6134397387504578, + "learning_rate": 6.394180728249821e-07, + "loss": 1.9481, + "step": 17046 + }, + { + "epoch": 0.9501700016721476, + "grad_norm": 0.5420237183570862, + "learning_rate": 6.379993856414468e-07, + "loss": 1.6337, + "step": 17047 + }, + { + "epoch": 0.9502257399253108, + "grad_norm": 0.6651062369346619, + "learning_rate": 6.365822639327723e-07, + "loss": 1.55, + "step": 17048 + }, + { + "epoch": 0.9502814781784739, + "grad_norm": 0.5766616463661194, + "learning_rate": 6.351667077439006e-07, + "loss": 1.5785, + "step": 17049 + }, + { + "epoch": 0.950337216431637, + "grad_norm": 0.5712983012199402, + "learning_rate": 6.337527171197177e-07, + "loss": 1.7686, + "step": 17050 + }, + { + "epoch": 0.9503929546848002, + "grad_norm": 0.5250173211097717, + "learning_rate": 6.32340292105077e-07, + "loss": 1.4871, + "step": 17051 + }, + { + "epoch": 0.9504486929379633, + "grad_norm": 0.5313369035720825, + "learning_rate": 6.309294327447756e-07, + "loss": 1.3882, + "step": 17052 + }, + { + "epoch": 0.9505044311911265, + "grad_norm": 0.6166152954101562, + "learning_rate": 6.295201390835448e-07, + "loss": 1.7842, + "step": 17053 + }, + { + "epoch": 0.9505601694442897, + "grad_norm": 0.5496584177017212, + "learning_rate": 6.281124111660875e-07, + "loss": 1.5399, + "step": 17054 + }, + { + "epoch": 0.9506159076974527, + "grad_norm": 0.5371002554893494, + "learning_rate": 6.267062490370401e-07, + "loss": 1.4698, + "step": 17055 + }, + { + "epoch": 0.9506716459506159, + "grad_norm": 0.6396268010139465, + "learning_rate": 6.253016527410116e-07, + "loss": 2.0197, + "step": 17056 + }, + { + "epoch": 0.950727384203779, + "grad_norm": 0.5591143369674683, + "learning_rate": 6.238986223225384e-07, + "loss": 1.6629, + "step": 17057 + }, + { + "epoch": 0.9507831224569422, + "grad_norm": 0.5616872310638428, + "learning_rate": 6.22497157826113e-07, + "loss": 1.758, + "step": 17058 + }, + { + "epoch": 0.9508388607101054, + "grad_norm": 0.5787703990936279, + "learning_rate": 6.210972592961938e-07, + "loss": 1.6158, + "step": 17059 + }, + { + "epoch": 0.9508945989632684, + "grad_norm": 0.5783166885375977, + "learning_rate": 6.19698926777168e-07, + "loss": 1.7162, + "step": 17060 + }, + { + "epoch": 0.9509503372164316, + "grad_norm": 0.6991276741027832, + "learning_rate": 6.183021603133887e-07, + "loss": 1.8092, + "step": 17061 + }, + { + "epoch": 0.9510060754695948, + "grad_norm": 0.5244433879852295, + "learning_rate": 6.169069599491428e-07, + "loss": 1.4472, + "step": 17062 + }, + { + "epoch": 0.9510618137227579, + "grad_norm": 0.6047583818435669, + "learning_rate": 6.155133257286893e-07, + "loss": 1.598, + "step": 17063 + }, + { + "epoch": 0.9511175519759211, + "grad_norm": 0.564811110496521, + "learning_rate": 6.141212576962207e-07, + "loss": 1.5263, + "step": 17064 + }, + { + "epoch": 0.9511732902290843, + "grad_norm": 0.5758123397827148, + "learning_rate": 6.12730755895885e-07, + "loss": 1.7322, + "step": 17065 + }, + { + "epoch": 0.9512290284822473, + "grad_norm": 0.5987499952316284, + "learning_rate": 6.113418203717858e-07, + "loss": 1.6605, + "step": 17066 + }, + { + "epoch": 0.9512847667354105, + "grad_norm": 0.607015073299408, + "learning_rate": 6.0995445116796e-07, + "loss": 1.8248, + "step": 17067 + }, + { + "epoch": 0.9513405049885737, + "grad_norm": 0.5862894058227539, + "learning_rate": 6.085686483284225e-07, + "loss": 1.4618, + "step": 17068 + }, + { + "epoch": 0.9513962432417368, + "grad_norm": 0.5554474592208862, + "learning_rate": 6.071844118971104e-07, + "loss": 1.6171, + "step": 17069 + }, + { + "epoch": 0.9514519814949, + "grad_norm": 0.5716840624809265, + "learning_rate": 6.058017419179384e-07, + "loss": 1.6565, + "step": 17070 + }, + { + "epoch": 0.9515077197480631, + "grad_norm": 0.522499680519104, + "learning_rate": 6.044206384347384e-07, + "loss": 1.5644, + "step": 17071 + }, + { + "epoch": 0.9515634580012262, + "grad_norm": 0.5786073803901672, + "learning_rate": 6.030411014913196e-07, + "loss": 1.6023, + "step": 17072 + }, + { + "epoch": 0.9516191962543894, + "grad_norm": 0.5461097955703735, + "learning_rate": 6.016631311314358e-07, + "loss": 1.3485, + "step": 17073 + }, + { + "epoch": 0.9516749345075526, + "grad_norm": 0.580531656742096, + "learning_rate": 6.0028672739878e-07, + "loss": 1.6505, + "step": 17074 + }, + { + "epoch": 0.9517306727607157, + "grad_norm": 0.5400432348251343, + "learning_rate": 5.989118903370172e-07, + "loss": 1.5776, + "step": 17075 + }, + { + "epoch": 0.9517864110138788, + "grad_norm": 0.5756409764289856, + "learning_rate": 5.975386199897348e-07, + "loss": 1.6576, + "step": 17076 + }, + { + "epoch": 0.951842149267042, + "grad_norm": 0.6007011532783508, + "learning_rate": 5.961669164004924e-07, + "loss": 1.5698, + "step": 17077 + }, + { + "epoch": 0.9518978875202051, + "grad_norm": 0.5606570839881897, + "learning_rate": 5.94796779612794e-07, + "loss": 1.5342, + "step": 17078 + }, + { + "epoch": 0.9519536257733683, + "grad_norm": 0.5706213116645813, + "learning_rate": 5.934282096700827e-07, + "loss": 1.7001, + "step": 17079 + }, + { + "epoch": 0.9520093640265314, + "grad_norm": 0.6424241065979004, + "learning_rate": 5.920612066157738e-07, + "loss": 1.3442, + "step": 17080 + }, + { + "epoch": 0.9520651022796945, + "grad_norm": 0.5613848567008972, + "learning_rate": 5.906957704932104e-07, + "loss": 1.55, + "step": 17081 + }, + { + "epoch": 0.9521208405328577, + "grad_norm": 0.6065196394920349, + "learning_rate": 5.893319013457077e-07, + "loss": 1.8351, + "step": 17082 + }, + { + "epoch": 0.9521765787860208, + "grad_norm": 0.575497567653656, + "learning_rate": 5.879695992165091e-07, + "loss": 1.6878, + "step": 17083 + }, + { + "epoch": 0.952232317039184, + "grad_norm": 0.6075579524040222, + "learning_rate": 5.866088641488188e-07, + "loss": 1.7578, + "step": 17084 + }, + { + "epoch": 0.9522880552923472, + "grad_norm": 0.5950081944465637, + "learning_rate": 5.852496961858023e-07, + "loss": 1.8184, + "step": 17085 + }, + { + "epoch": 0.9523437935455102, + "grad_norm": 0.5427230000495911, + "learning_rate": 5.838920953705584e-07, + "loss": 1.4511, + "step": 17086 + }, + { + "epoch": 0.9523995317986734, + "grad_norm": 0.595068097114563, + "learning_rate": 5.825360617461362e-07, + "loss": 1.6303, + "step": 17087 + }, + { + "epoch": 0.9524552700518366, + "grad_norm": 0.5383949279785156, + "learning_rate": 5.811815953555456e-07, + "loss": 1.6204, + "step": 17088 + }, + { + "epoch": 0.9525110083049997, + "grad_norm": 0.5752375721931458, + "learning_rate": 5.798286962417465e-07, + "loss": 1.7111, + "step": 17089 + }, + { + "epoch": 0.9525667465581629, + "grad_norm": 0.5788770914077759, + "learning_rate": 5.784773644476438e-07, + "loss": 1.6455, + "step": 17090 + }, + { + "epoch": 0.952622484811326, + "grad_norm": 0.5657581090927124, + "learning_rate": 5.771276000160808e-07, + "loss": 1.4845, + "step": 17091 + }, + { + "epoch": 0.9526782230644891, + "grad_norm": 0.5722523927688599, + "learning_rate": 5.757794029898844e-07, + "loss": 1.7556, + "step": 17092 + }, + { + "epoch": 0.9527339613176523, + "grad_norm": 0.5416318774223328, + "learning_rate": 5.744327734118037e-07, + "loss": 1.5055, + "step": 17093 + }, + { + "epoch": 0.9527896995708155, + "grad_norm": 0.5927363038063049, + "learning_rate": 5.730877113245381e-07, + "loss": 1.7597, + "step": 17094 + }, + { + "epoch": 0.9528454378239786, + "grad_norm": 0.6073784828186035, + "learning_rate": 5.717442167707531e-07, + "loss": 1.6878, + "step": 17095 + }, + { + "epoch": 0.9529011760771418, + "grad_norm": 0.5661188960075378, + "learning_rate": 5.704022897930594e-07, + "loss": 1.5908, + "step": 17096 + }, + { + "epoch": 0.9529569143303049, + "grad_norm": 0.5860098004341125, + "learning_rate": 5.690619304340061e-07, + "loss": 1.7469, + "step": 17097 + }, + { + "epoch": 0.953012652583468, + "grad_norm": 0.5996899008750916, + "learning_rate": 5.677231387361093e-07, + "loss": 1.8152, + "step": 17098 + }, + { + "epoch": 0.9530683908366312, + "grad_norm": 0.5388041734695435, + "learning_rate": 5.663859147418183e-07, + "loss": 1.6877, + "step": 17099 + }, + { + "epoch": 0.9531241290897944, + "grad_norm": 0.6276445984840393, + "learning_rate": 5.650502584935546e-07, + "loss": 1.964, + "step": 17100 + }, + { + "epoch": 0.9531798673429575, + "grad_norm": 0.5559234619140625, + "learning_rate": 5.63716170033668e-07, + "loss": 1.6014, + "step": 17101 + }, + { + "epoch": 0.9532356055961206, + "grad_norm": 0.6018325686454773, + "learning_rate": 5.623836494044687e-07, + "loss": 1.805, + "step": 17102 + }, + { + "epoch": 0.9532913438492837, + "grad_norm": 0.5577319860458374, + "learning_rate": 5.610526966482232e-07, + "loss": 1.463, + "step": 17103 + }, + { + "epoch": 0.9533470821024469, + "grad_norm": 0.6154071092605591, + "learning_rate": 5.597233118071365e-07, + "loss": 1.8894, + "step": 17104 + }, + { + "epoch": 0.9534028203556101, + "grad_norm": 0.585364580154419, + "learning_rate": 5.583954949233638e-07, + "loss": 1.6705, + "step": 17105 + }, + { + "epoch": 0.9534585586087732, + "grad_norm": 0.5592061877250671, + "learning_rate": 5.57069246039027e-07, + "loss": 1.6637, + "step": 17106 + }, + { + "epoch": 0.9535142968619363, + "grad_norm": 0.533197283744812, + "learning_rate": 5.557445651961812e-07, + "loss": 1.5197, + "step": 17107 + }, + { + "epoch": 0.9535700351150995, + "grad_norm": 0.5449912548065186, + "learning_rate": 5.544214524368374e-07, + "loss": 1.5722, + "step": 17108 + }, + { + "epoch": 0.9536257733682626, + "grad_norm": 0.6087771654129028, + "learning_rate": 5.530999078029563e-07, + "loss": 1.7963, + "step": 17109 + }, + { + "epoch": 0.9536815116214258, + "grad_norm": 0.55324387550354, + "learning_rate": 5.517799313364491e-07, + "loss": 1.5337, + "step": 17110 + }, + { + "epoch": 0.953737249874589, + "grad_norm": 0.5788394808769226, + "learning_rate": 5.504615230791821e-07, + "loss": 1.7755, + "step": 17111 + }, + { + "epoch": 0.953792988127752, + "grad_norm": 0.5552836060523987, + "learning_rate": 5.491446830729663e-07, + "loss": 1.7108, + "step": 17112 + }, + { + "epoch": 0.9538487263809152, + "grad_norm": 0.5873304605484009, + "learning_rate": 5.478294113595573e-07, + "loss": 1.7004, + "step": 17113 + }, + { + "epoch": 0.9539044646340784, + "grad_norm": 0.7041929960250854, + "learning_rate": 5.465157079806771e-07, + "loss": 1.7245, + "step": 17114 + }, + { + "epoch": 0.9539602028872415, + "grad_norm": 0.5417248606681824, + "learning_rate": 5.452035729779869e-07, + "loss": 1.5044, + "step": 17115 + }, + { + "epoch": 0.9540159411404047, + "grad_norm": 0.5634655952453613, + "learning_rate": 5.438930063930925e-07, + "loss": 1.5727, + "step": 17116 + }, + { + "epoch": 0.9540716793935679, + "grad_norm": 0.5923795104026794, + "learning_rate": 5.42584008267566e-07, + "loss": 1.7628, + "step": 17117 + }, + { + "epoch": 0.9541274176467309, + "grad_norm": 0.5859149694442749, + "learning_rate": 5.412765786429186e-07, + "loss": 1.644, + "step": 17118 + }, + { + "epoch": 0.9541831558998941, + "grad_norm": 0.5265727639198303, + "learning_rate": 5.399707175606117e-07, + "loss": 1.456, + "step": 17119 + }, + { + "epoch": 0.9542388941530573, + "grad_norm": 0.5537406206130981, + "learning_rate": 5.386664250620621e-07, + "loss": 1.5407, + "step": 17120 + }, + { + "epoch": 0.9542946324062204, + "grad_norm": 0.5547535419464111, + "learning_rate": 5.373637011886312e-07, + "loss": 1.7538, + "step": 17121 + }, + { + "epoch": 0.9543503706593836, + "grad_norm": 0.5436185598373413, + "learning_rate": 5.36062545981647e-07, + "loss": 1.6037, + "step": 17122 + }, + { + "epoch": 0.9544061089125467, + "grad_norm": 0.6028372645378113, + "learning_rate": 5.347629594823544e-07, + "loss": 1.6391, + "step": 17123 + }, + { + "epoch": 0.9544618471657098, + "grad_norm": 0.555198073387146, + "learning_rate": 5.334649417319815e-07, + "loss": 1.692, + "step": 17124 + }, + { + "epoch": 0.954517585418873, + "grad_norm": 0.5775254964828491, + "learning_rate": 5.321684927716897e-07, + "loss": 1.6215, + "step": 17125 + }, + { + "epoch": 0.9545733236720361, + "grad_norm": 0.561040997505188, + "learning_rate": 5.308736126425962e-07, + "loss": 1.7474, + "step": 17126 + }, + { + "epoch": 0.9546290619251993, + "grad_norm": 0.5487300753593445, + "learning_rate": 5.295803013857681e-07, + "loss": 1.6767, + "step": 17127 + }, + { + "epoch": 0.9546848001783624, + "grad_norm": 0.5460517406463623, + "learning_rate": 5.282885590422171e-07, + "loss": 1.4194, + "step": 17128 + }, + { + "epoch": 0.9547405384315255, + "grad_norm": 0.5349060893058777, + "learning_rate": 5.269983856529159e-07, + "loss": 1.4386, + "step": 17129 + }, + { + "epoch": 0.9547962766846887, + "grad_norm": 0.535463809967041, + "learning_rate": 5.257097812587763e-07, + "loss": 1.6629, + "step": 17130 + }, + { + "epoch": 0.9548520149378519, + "grad_norm": 0.5883685350418091, + "learning_rate": 5.244227459006656e-07, + "loss": 1.6166, + "step": 17131 + }, + { + "epoch": 0.954907753191015, + "grad_norm": 0.5415738821029663, + "learning_rate": 5.231372796194068e-07, + "loss": 1.588, + "step": 17132 + }, + { + "epoch": 0.9549634914441781, + "grad_norm": 0.5167189240455627, + "learning_rate": 5.218533824557614e-07, + "loss": 1.4972, + "step": 17133 + }, + { + "epoch": 0.9550192296973413, + "grad_norm": 0.5703948140144348, + "learning_rate": 5.205710544504527e-07, + "loss": 1.6878, + "step": 17134 + }, + { + "epoch": 0.9550749679505044, + "grad_norm": 0.5150492191314697, + "learning_rate": 5.19290295644137e-07, + "loss": 1.4775, + "step": 17135 + }, + { + "epoch": 0.9551307062036676, + "grad_norm": 0.5545765161514282, + "learning_rate": 5.180111060774429e-07, + "loss": 1.6239, + "step": 17136 + }, + { + "epoch": 0.9551864444568308, + "grad_norm": 0.5277937650680542, + "learning_rate": 5.167334857909434e-07, + "loss": 1.6065, + "step": 17137 + }, + { + "epoch": 0.9552421827099938, + "grad_norm": 0.5491108298301697, + "learning_rate": 5.15457434825145e-07, + "loss": 1.6714, + "step": 17138 + }, + { + "epoch": 0.955297920963157, + "grad_norm": 0.6350153684616089, + "learning_rate": 5.141829532205211e-07, + "loss": 2.0025, + "step": 17139 + }, + { + "epoch": 0.9553536592163202, + "grad_norm": 0.57353276014328, + "learning_rate": 5.129100410174947e-07, + "loss": 1.6201, + "step": 17140 + }, + { + "epoch": 0.9554093974694833, + "grad_norm": 0.580916166305542, + "learning_rate": 5.116386982564336e-07, + "loss": 1.5489, + "step": 17141 + }, + { + "epoch": 0.9554651357226465, + "grad_norm": 0.5787146091461182, + "learning_rate": 5.103689249776555e-07, + "loss": 1.5875, + "step": 17142 + }, + { + "epoch": 0.9555208739758096, + "grad_norm": 0.5643471479415894, + "learning_rate": 5.091007212214227e-07, + "loss": 1.6044, + "step": 17143 + }, + { + "epoch": 0.9555766122289727, + "grad_norm": 0.6052595973014832, + "learning_rate": 5.078340870279697e-07, + "loss": 1.7169, + "step": 17144 + }, + { + "epoch": 0.9556323504821359, + "grad_norm": 0.5392379760742188, + "learning_rate": 5.065690224374587e-07, + "loss": 1.2724, + "step": 17145 + }, + { + "epoch": 0.9556880887352991, + "grad_norm": 0.5751489996910095, + "learning_rate": 5.053055274900131e-07, + "loss": 1.6387, + "step": 17146 + }, + { + "epoch": 0.9557438269884622, + "grad_norm": 0.6253306269645691, + "learning_rate": 5.040436022256956e-07, + "loss": 2.1196, + "step": 17147 + }, + { + "epoch": 0.9557995652416253, + "grad_norm": 0.5502660274505615, + "learning_rate": 5.027832466845462e-07, + "loss": 1.5834, + "step": 17148 + }, + { + "epoch": 0.9558553034947884, + "grad_norm": 0.5606353282928467, + "learning_rate": 5.015244609065106e-07, + "loss": 1.5055, + "step": 17149 + }, + { + "epoch": 0.9559110417479516, + "grad_norm": 0.5353908538818359, + "learning_rate": 5.002672449315293e-07, + "loss": 1.4226, + "step": 17150 + }, + { + "epoch": 0.9559667800011148, + "grad_norm": 0.5819185972213745, + "learning_rate": 4.990115987994648e-07, + "loss": 1.7643, + "step": 17151 + }, + { + "epoch": 0.9560225182542779, + "grad_norm": 0.5204069018363953, + "learning_rate": 4.977575225501463e-07, + "loss": 1.418, + "step": 17152 + }, + { + "epoch": 0.956078256507441, + "grad_norm": 0.5813349485397339, + "learning_rate": 4.965050162233365e-07, + "loss": 1.7449, + "step": 17153 + }, + { + "epoch": 0.9561339947606042, + "grad_norm": 0.5545005798339844, + "learning_rate": 4.952540798587646e-07, + "loss": 1.8759, + "step": 17154 + }, + { + "epoch": 0.9561897330137673, + "grad_norm": 0.5863983631134033, + "learning_rate": 4.94004713496099e-07, + "loss": 1.8904, + "step": 17155 + }, + { + "epoch": 0.9562454712669305, + "grad_norm": 0.5897269248962402, + "learning_rate": 4.927569171749635e-07, + "loss": 1.4976, + "step": 17156 + }, + { + "epoch": 0.9563012095200937, + "grad_norm": 0.5661434531211853, + "learning_rate": 4.915106909349321e-07, + "loss": 1.6972, + "step": 17157 + }, + { + "epoch": 0.9563569477732567, + "grad_norm": 0.5706937313079834, + "learning_rate": 4.902660348155285e-07, + "loss": 1.6761, + "step": 17158 + }, + { + "epoch": 0.9564126860264199, + "grad_norm": 0.5610705614089966, + "learning_rate": 4.890229488562215e-07, + "loss": 1.6926, + "step": 17159 + }, + { + "epoch": 0.9564684242795831, + "grad_norm": 0.5586698055267334, + "learning_rate": 4.877814330964458e-07, + "loss": 1.5531, + "step": 17160 + }, + { + "epoch": 0.9565241625327462, + "grad_norm": 0.5700247883796692, + "learning_rate": 4.865414875755537e-07, + "loss": 1.7092, + "step": 17161 + }, + { + "epoch": 0.9565799007859094, + "grad_norm": 0.5655803084373474, + "learning_rate": 4.85303112332891e-07, + "loss": 1.6221, + "step": 17162 + }, + { + "epoch": 0.9566356390390726, + "grad_norm": 0.5784798264503479, + "learning_rate": 4.840663074077212e-07, + "loss": 1.7214, + "step": 17163 + }, + { + "epoch": 0.9566913772922356, + "grad_norm": 0.5506024360656738, + "learning_rate": 4.828310728392682e-07, + "loss": 1.5189, + "step": 17164 + }, + { + "epoch": 0.9567471155453988, + "grad_norm": 0.5768864154815674, + "learning_rate": 4.815974086667119e-07, + "loss": 1.6799, + "step": 17165 + }, + { + "epoch": 0.956802853798562, + "grad_norm": 0.5469486117362976, + "learning_rate": 4.80365314929171e-07, + "loss": 1.7674, + "step": 17166 + }, + { + "epoch": 0.9568585920517251, + "grad_norm": 0.6864200830459595, + "learning_rate": 4.791347916657252e-07, + "loss": 1.8631, + "step": 17167 + }, + { + "epoch": 0.9569143303048883, + "grad_norm": 0.6033056974411011, + "learning_rate": 4.779058389153934e-07, + "loss": 1.6842, + "step": 17168 + }, + { + "epoch": 0.9569700685580514, + "grad_norm": 0.5971852540969849, + "learning_rate": 4.766784567171556e-07, + "loss": 1.9205, + "step": 17169 + }, + { + "epoch": 0.9570258068112145, + "grad_norm": 0.5592812895774841, + "learning_rate": 4.754526451099417e-07, + "loss": 1.7295, + "step": 17170 + }, + { + "epoch": 0.9570815450643777, + "grad_norm": 0.5669441819190979, + "learning_rate": 4.7422840413261504e-07, + "loss": 1.5759, + "step": 17171 + }, + { + "epoch": 0.9571372833175408, + "grad_norm": 0.6172444820404053, + "learning_rate": 4.7300573382401123e-07, + "loss": 1.8294, + "step": 17172 + }, + { + "epoch": 0.957193021570704, + "grad_norm": 0.5782250761985779, + "learning_rate": 4.717846342228993e-07, + "loss": 1.6738, + "step": 17173 + }, + { + "epoch": 0.9572487598238671, + "grad_norm": 0.4995215833187103, + "learning_rate": 4.705651053680149e-07, + "loss": 1.4396, + "step": 17174 + }, + { + "epoch": 0.9573044980770302, + "grad_norm": 0.5729857683181763, + "learning_rate": 4.693471472980271e-07, + "loss": 1.6577, + "step": 17175 + }, + { + "epoch": 0.9573602363301934, + "grad_norm": 0.5761178135871887, + "learning_rate": 4.6813076005156054e-07, + "loss": 1.6601, + "step": 17176 + }, + { + "epoch": 0.9574159745833566, + "grad_norm": 0.591345489025116, + "learning_rate": 4.6691594366719547e-07, + "loss": 1.769, + "step": 17177 + }, + { + "epoch": 0.9574717128365197, + "grad_norm": 0.5400246977806091, + "learning_rate": 4.6570269818346224e-07, + "loss": 1.394, + "step": 17178 + }, + { + "epoch": 0.9575274510896828, + "grad_norm": 0.5980721712112427, + "learning_rate": 4.644910236388356e-07, + "loss": 1.6643, + "step": 17179 + }, + { + "epoch": 0.957583189342846, + "grad_norm": 0.5853055715560913, + "learning_rate": 4.6328092007173475e-07, + "loss": 1.8785, + "step": 17180 + }, + { + "epoch": 0.9576389275960091, + "grad_norm": 0.6245357990264893, + "learning_rate": 4.620723875205513e-07, + "loss": 1.8076, + "step": 17181 + }, + { + "epoch": 0.9576946658491723, + "grad_norm": 0.4698905944824219, + "learning_rate": 4.608654260236045e-07, + "loss": 1.1926, + "step": 17182 + }, + { + "epoch": 0.9577504041023355, + "grad_norm": 0.5433370471000671, + "learning_rate": 4.596600356191694e-07, + "loss": 1.4759, + "step": 17183 + }, + { + "epoch": 0.9578061423554985, + "grad_norm": 0.5955995321273804, + "learning_rate": 4.5845621634548195e-07, + "loss": 1.6676, + "step": 17184 + }, + { + "epoch": 0.9578618806086617, + "grad_norm": 0.5686216950416565, + "learning_rate": 4.5725396824071177e-07, + "loss": 1.6399, + "step": 17185 + }, + { + "epoch": 0.9579176188618249, + "grad_norm": 0.5718632340431213, + "learning_rate": 4.560532913429949e-07, + "loss": 1.7609, + "step": 17186 + }, + { + "epoch": 0.957973357114988, + "grad_norm": 0.5449936389923096, + "learning_rate": 4.5485418569040095e-07, + "loss": 1.5248, + "step": 17187 + }, + { + "epoch": 0.9580290953681512, + "grad_norm": 0.570787250995636, + "learning_rate": 4.536566513209717e-07, + "loss": 1.7189, + "step": 17188 + }, + { + "epoch": 0.9580848336213144, + "grad_norm": 0.5979569554328918, + "learning_rate": 4.524606882726767e-07, + "loss": 1.7432, + "step": 17189 + }, + { + "epoch": 0.9581405718744774, + "grad_norm": 0.5879902243614197, + "learning_rate": 4.512662965834413e-07, + "loss": 1.7686, + "step": 17190 + }, + { + "epoch": 0.9581963101276406, + "grad_norm": 0.5947943925857544, + "learning_rate": 4.500734762911518e-07, + "loss": 1.7781, + "step": 17191 + }, + { + "epoch": 0.9582520483808038, + "grad_norm": 0.6514115929603577, + "learning_rate": 4.4888222743363906e-07, + "loss": 2.2384, + "step": 17192 + }, + { + "epoch": 0.9583077866339669, + "grad_norm": 0.5053853988647461, + "learning_rate": 4.476925500486784e-07, + "loss": 1.6351, + "step": 17193 + }, + { + "epoch": 0.9583635248871301, + "grad_norm": 0.5630142688751221, + "learning_rate": 4.4650444417400075e-07, + "loss": 1.4533, + "step": 17194 + }, + { + "epoch": 0.9584192631402931, + "grad_norm": 0.6217920780181885, + "learning_rate": 4.4531790984727594e-07, + "loss": 1.6649, + "step": 17195 + }, + { + "epoch": 0.9584750013934563, + "grad_norm": 0.5543999671936035, + "learning_rate": 4.441329471061517e-07, + "loss": 1.7243, + "step": 17196 + }, + { + "epoch": 0.9585307396466195, + "grad_norm": 0.6299118399620056, + "learning_rate": 4.42949555988198e-07, + "loss": 1.8475, + "step": 17197 + }, + { + "epoch": 0.9585864778997826, + "grad_norm": 0.5300838947296143, + "learning_rate": 4.4176773653094583e-07, + "loss": 1.4875, + "step": 17198 + }, + { + "epoch": 0.9586422161529458, + "grad_norm": 0.6004483699798584, + "learning_rate": 4.4058748877188196e-07, + "loss": 1.821, + "step": 17199 + }, + { + "epoch": 0.9586979544061089, + "grad_norm": 0.5626548528671265, + "learning_rate": 4.3940881274842637e-07, + "loss": 1.6276, + "step": 17200 + }, + { + "epoch": 0.958753692659272, + "grad_norm": 0.5802615284919739, + "learning_rate": 4.3823170849796593e-07, + "loss": 1.4243, + "step": 17201 + }, + { + "epoch": 0.9588094309124352, + "grad_norm": 0.571747899055481, + "learning_rate": 4.370561760578262e-07, + "loss": 1.7216, + "step": 17202 + }, + { + "epoch": 0.9588651691655984, + "grad_norm": 0.5820655226707458, + "learning_rate": 4.358822154652997e-07, + "loss": 1.5975, + "step": 17203 + }, + { + "epoch": 0.9589209074187615, + "grad_norm": 0.5650625824928284, + "learning_rate": 4.347098267576066e-07, + "loss": 1.468, + "step": 17204 + }, + { + "epoch": 0.9589766456719246, + "grad_norm": 0.6469852924346924, + "learning_rate": 4.3353900997193384e-07, + "loss": 1.586, + "step": 17205 + }, + { + "epoch": 0.9590323839250878, + "grad_norm": 0.5440933108329773, + "learning_rate": 4.323697651454073e-07, + "loss": 1.4871, + "step": 17206 + }, + { + "epoch": 0.9590881221782509, + "grad_norm": 0.639417827129364, + "learning_rate": 4.3120209231511946e-07, + "loss": 1.6051, + "step": 17207 + }, + { + "epoch": 0.9591438604314141, + "grad_norm": 0.5535564422607422, + "learning_rate": 4.300359915180907e-07, + "loss": 1.5162, + "step": 17208 + }, + { + "epoch": 0.9591995986845773, + "grad_norm": 0.7195184826850891, + "learning_rate": 4.288714627913082e-07, + "loss": 1.6967, + "step": 17209 + }, + { + "epoch": 0.9592553369377403, + "grad_norm": 0.5364476442337036, + "learning_rate": 4.277085061716979e-07, + "loss": 1.6838, + "step": 17210 + }, + { + "epoch": 0.9593110751909035, + "grad_norm": 0.558215320110321, + "learning_rate": 4.265471216961525e-07, + "loss": 1.5101, + "step": 17211 + }, + { + "epoch": 0.9593668134440667, + "grad_norm": 0.6101508140563965, + "learning_rate": 4.2538730940150373e-07, + "loss": 1.8355, + "step": 17212 + }, + { + "epoch": 0.9594225516972298, + "grad_norm": 0.5373988747596741, + "learning_rate": 4.242290693245221e-07, + "loss": 1.4289, + "step": 17213 + }, + { + "epoch": 0.959478289950393, + "grad_norm": 0.5482228398323059, + "learning_rate": 4.2307240150195047e-07, + "loss": 1.6346, + "step": 17214 + }, + { + "epoch": 0.9595340282035562, + "grad_norm": 0.6059067845344543, + "learning_rate": 4.219173059704651e-07, + "loss": 1.6333, + "step": 17215 + }, + { + "epoch": 0.9595897664567192, + "grad_norm": 0.5706430077552795, + "learning_rate": 4.207637827667088e-07, + "loss": 1.6506, + "step": 17216 + }, + { + "epoch": 0.9596455047098824, + "grad_norm": 0.5996609926223755, + "learning_rate": 4.196118319272524e-07, + "loss": 1.6314, + "step": 17217 + }, + { + "epoch": 0.9597012429630455, + "grad_norm": 0.549426257610321, + "learning_rate": 4.1846145348863883e-07, + "loss": 1.3523, + "step": 17218 + }, + { + "epoch": 0.9597569812162087, + "grad_norm": 0.5231605768203735, + "learning_rate": 4.173126474873501e-07, + "loss": 1.4213, + "step": 17219 + }, + { + "epoch": 0.9598127194693719, + "grad_norm": 0.5310205817222595, + "learning_rate": 4.1616541395981256e-07, + "loss": 1.4499, + "step": 17220 + }, + { + "epoch": 0.9598684577225349, + "grad_norm": 0.7105188369750977, + "learning_rate": 4.1501975294240824e-07, + "loss": 1.9351, + "step": 17221 + }, + { + "epoch": 0.9599241959756981, + "grad_norm": 0.5943854451179504, + "learning_rate": 4.1387566447148585e-07, + "loss": 1.6842, + "step": 17222 + }, + { + "epoch": 0.9599799342288613, + "grad_norm": 0.5623593926429749, + "learning_rate": 4.127331485833219e-07, + "loss": 1.6548, + "step": 17223 + }, + { + "epoch": 0.9600356724820244, + "grad_norm": 0.580953061580658, + "learning_rate": 4.1159220531414297e-07, + "loss": 1.7442, + "step": 17224 + }, + { + "epoch": 0.9600914107351876, + "grad_norm": 0.6038072109222412, + "learning_rate": 4.104528347001368e-07, + "loss": 1.6952, + "step": 17225 + }, + { + "epoch": 0.9601471489883507, + "grad_norm": 0.5870489478111267, + "learning_rate": 4.0931503677744676e-07, + "loss": 1.5481, + "step": 17226 + }, + { + "epoch": 0.9602028872415138, + "grad_norm": 0.5754347443580627, + "learning_rate": 4.0817881158214946e-07, + "loss": 1.7855, + "step": 17227 + }, + { + "epoch": 0.960258625494677, + "grad_norm": 0.583094596862793, + "learning_rate": 4.070441591502716e-07, + "loss": 1.5109, + "step": 17228 + }, + { + "epoch": 0.9603143637478402, + "grad_norm": 0.5574551820755005, + "learning_rate": 4.0591107951781227e-07, + "loss": 1.6554, + "step": 17229 + }, + { + "epoch": 0.9603701020010033, + "grad_norm": 0.5949016809463501, + "learning_rate": 4.047795727207038e-07, + "loss": 1.7827, + "step": 17230 + }, + { + "epoch": 0.9604258402541664, + "grad_norm": 0.7539557218551636, + "learning_rate": 4.03649638794823e-07, + "loss": 1.6885, + "step": 17231 + }, + { + "epoch": 0.9604815785073296, + "grad_norm": 0.5546339750289917, + "learning_rate": 4.0252127777600236e-07, + "loss": 1.6805, + "step": 17232 + }, + { + "epoch": 0.9605373167604927, + "grad_norm": 0.5417783856391907, + "learning_rate": 4.01394489700041e-07, + "loss": 1.552, + "step": 17233 + }, + { + "epoch": 0.9605930550136559, + "grad_norm": 0.56772780418396, + "learning_rate": 4.0026927460266594e-07, + "loss": 1.6936, + "step": 17234 + }, + { + "epoch": 0.9606487932668191, + "grad_norm": 0.5507760047912598, + "learning_rate": 3.9914563251956525e-07, + "loss": 1.5903, + "step": 17235 + }, + { + "epoch": 0.9607045315199821, + "grad_norm": 0.6138635873794556, + "learning_rate": 3.98023563486366e-07, + "loss": 1.8814, + "step": 17236 + }, + { + "epoch": 0.9607602697731453, + "grad_norm": 0.5589078664779663, + "learning_rate": 3.96903067538662e-07, + "loss": 1.4595, + "step": 17237 + }, + { + "epoch": 0.9608160080263085, + "grad_norm": 0.5237577557563782, + "learning_rate": 3.9578414471199145e-07, + "loss": 1.4028, + "step": 17238 + }, + { + "epoch": 0.9608717462794716, + "grad_norm": 0.5533643960952759, + "learning_rate": 3.946667950418259e-07, + "loss": 1.3832, + "step": 17239 + }, + { + "epoch": 0.9609274845326348, + "grad_norm": 0.5483295917510986, + "learning_rate": 3.935510185636149e-07, + "loss": 1.5302, + "step": 17240 + }, + { + "epoch": 0.9609832227857978, + "grad_norm": 0.5572713613510132, + "learning_rate": 3.924368153127411e-07, + "loss": 1.5696, + "step": 17241 + }, + { + "epoch": 0.961038961038961, + "grad_norm": 0.5555443167686462, + "learning_rate": 3.913241853245375e-07, + "loss": 1.5546, + "step": 17242 + }, + { + "epoch": 0.9610946992921242, + "grad_norm": 0.5994016528129578, + "learning_rate": 3.902131286342925e-07, + "loss": 1.8268, + "step": 17243 + }, + { + "epoch": 0.9611504375452873, + "grad_norm": 0.5812157392501831, + "learning_rate": 3.891036452772445e-07, + "loss": 1.7141, + "step": 17244 + }, + { + "epoch": 0.9612061757984505, + "grad_norm": 0.5765419602394104, + "learning_rate": 3.879957352885766e-07, + "loss": 1.6503, + "step": 17245 + }, + { + "epoch": 0.9612619140516137, + "grad_norm": 0.542682409286499, + "learning_rate": 3.868893987034272e-07, + "loss": 1.6333, + "step": 17246 + }, + { + "epoch": 0.9613176523047767, + "grad_norm": 0.5937307476997375, + "learning_rate": 3.8578463555687396e-07, + "loss": 1.8458, + "step": 17247 + }, + { + "epoch": 0.9613733905579399, + "grad_norm": 0.6144217252731323, + "learning_rate": 3.8468144588396647e-07, + "loss": 1.7948, + "step": 17248 + }, + { + "epoch": 0.9614291288111031, + "grad_norm": 0.5792607665061951, + "learning_rate": 3.8357982971968796e-07, + "loss": 1.6938, + "step": 17249 + }, + { + "epoch": 0.9614848670642662, + "grad_norm": 0.5988001227378845, + "learning_rate": 3.824797870989716e-07, + "loss": 1.7462, + "step": 17250 + }, + { + "epoch": 0.9615406053174294, + "grad_norm": 0.5512014627456665, + "learning_rate": 3.8138131805670606e-07, + "loss": 1.5328, + "step": 17251 + }, + { + "epoch": 0.9615963435705925, + "grad_norm": 0.5704134702682495, + "learning_rate": 3.8028442262773026e-07, + "loss": 1.8171, + "step": 17252 + }, + { + "epoch": 0.9616520818237556, + "grad_norm": 0.5572457313537598, + "learning_rate": 3.7918910084682734e-07, + "loss": 1.6913, + "step": 17253 + }, + { + "epoch": 0.9617078200769188, + "grad_norm": 0.5451191067695618, + "learning_rate": 3.780953527487363e-07, + "loss": 1.6028, + "step": 17254 + }, + { + "epoch": 0.961763558330082, + "grad_norm": 0.5607072114944458, + "learning_rate": 3.77003178368146e-07, + "loss": 1.6237, + "step": 17255 + }, + { + "epoch": 0.961819296583245, + "grad_norm": 0.5849952101707458, + "learning_rate": 3.759125777396899e-07, + "loss": 1.6616, + "step": 17256 + }, + { + "epoch": 0.9618750348364082, + "grad_norm": 0.598247230052948, + "learning_rate": 3.7482355089796253e-07, + "loss": 1.5478, + "step": 17257 + }, + { + "epoch": 0.9619307730895714, + "grad_norm": 0.5605067610740662, + "learning_rate": 3.737360978774973e-07, + "loss": 1.6128, + "step": 17258 + }, + { + "epoch": 0.9619865113427345, + "grad_norm": 0.5875841379165649, + "learning_rate": 3.726502187127834e-07, + "loss": 1.5874, + "step": 17259 + }, + { + "epoch": 0.9620422495958977, + "grad_norm": 0.5789545774459839, + "learning_rate": 3.7156591343824874e-07, + "loss": 1.6423, + "step": 17260 + }, + { + "epoch": 0.9620979878490609, + "grad_norm": 0.5922415852546692, + "learning_rate": 3.7048318208829924e-07, + "loss": 1.4805, + "step": 17261 + }, + { + "epoch": 0.9621537261022239, + "grad_norm": 0.5667035579681396, + "learning_rate": 3.694020246972574e-07, + "loss": 1.646, + "step": 17262 + }, + { + "epoch": 0.9622094643553871, + "grad_norm": 0.6190335154533386, + "learning_rate": 3.6832244129941796e-07, + "loss": 1.8116, + "step": 17263 + }, + { + "epoch": 0.9622652026085502, + "grad_norm": 0.535043478012085, + "learning_rate": 3.6724443192902026e-07, + "loss": 1.5197, + "step": 17264 + }, + { + "epoch": 0.9623209408617134, + "grad_norm": 0.5469433665275574, + "learning_rate": 3.6616799662024246e-07, + "loss": 1.5514, + "step": 17265 + }, + { + "epoch": 0.9623766791148766, + "grad_norm": 0.5909947752952576, + "learning_rate": 3.6509313540724067e-07, + "loss": 1.6777, + "step": 17266 + }, + { + "epoch": 0.9624324173680396, + "grad_norm": 0.5609679818153381, + "learning_rate": 3.6401984832408754e-07, + "loss": 1.644, + "step": 17267 + }, + { + "epoch": 0.9624881556212028, + "grad_norm": 0.567853569984436, + "learning_rate": 3.629481354048281e-07, + "loss": 1.6234, + "step": 17268 + }, + { + "epoch": 0.962543893874366, + "grad_norm": 0.5747160911560059, + "learning_rate": 3.6187799668344626e-07, + "loss": 1.4791, + "step": 17269 + }, + { + "epoch": 0.9625996321275291, + "grad_norm": 0.5874738693237305, + "learning_rate": 3.608094321938871e-07, + "loss": 1.8732, + "step": 17270 + }, + { + "epoch": 0.9626553703806923, + "grad_norm": 0.6413251161575317, + "learning_rate": 3.5974244197004016e-07, + "loss": 1.686, + "step": 17271 + }, + { + "epoch": 0.9627111086338555, + "grad_norm": 0.5412811040878296, + "learning_rate": 3.5867702604573395e-07, + "loss": 1.4681, + "step": 17272 + }, + { + "epoch": 0.9627668468870185, + "grad_norm": 0.5562384724617004, + "learning_rate": 3.5761318445476367e-07, + "loss": 1.6921, + "step": 17273 + }, + { + "epoch": 0.9628225851401817, + "grad_norm": 0.5652821660041809, + "learning_rate": 3.56550917230869e-07, + "loss": 1.821, + "step": 17274 + }, + { + "epoch": 0.9628783233933449, + "grad_norm": 0.5868329405784607, + "learning_rate": 3.554902244077396e-07, + "loss": 1.4901, + "step": 17275 + }, + { + "epoch": 0.962934061646508, + "grad_norm": 0.5646710395812988, + "learning_rate": 3.5443110601901533e-07, + "loss": 1.3337, + "step": 17276 + }, + { + "epoch": 0.9629897998996712, + "grad_norm": 0.5524607300758362, + "learning_rate": 3.5337356209827477e-07, + "loss": 1.5836, + "step": 17277 + }, + { + "epoch": 0.9630455381528343, + "grad_norm": 0.5268007516860962, + "learning_rate": 3.523175926790745e-07, + "loss": 1.3261, + "step": 17278 + }, + { + "epoch": 0.9631012764059974, + "grad_norm": 0.569468080997467, + "learning_rate": 3.512631977948877e-07, + "loss": 1.7087, + "step": 17279 + }, + { + "epoch": 0.9631570146591606, + "grad_norm": 0.5644505023956299, + "learning_rate": 3.5021037747915987e-07, + "loss": 1.6478, + "step": 17280 + }, + { + "epoch": 0.9632127529123238, + "grad_norm": 0.585853099822998, + "learning_rate": 3.4915913176528094e-07, + "loss": 1.8982, + "step": 17281 + }, + { + "epoch": 0.9632684911654869, + "grad_norm": 0.55772465467453, + "learning_rate": 3.481094606865909e-07, + "loss": 1.5759, + "step": 17282 + }, + { + "epoch": 0.96332422941865, + "grad_norm": 0.6021003723144531, + "learning_rate": 3.470613642763798e-07, + "loss": 1.6012, + "step": 17283 + }, + { + "epoch": 0.9633799676718132, + "grad_norm": 0.5937752723693848, + "learning_rate": 3.460148425678822e-07, + "loss": 1.7879, + "step": 17284 + }, + { + "epoch": 0.9634357059249763, + "grad_norm": 0.5817155838012695, + "learning_rate": 3.449698955942937e-07, + "loss": 1.6797, + "step": 17285 + }, + { + "epoch": 0.9634914441781395, + "grad_norm": 0.5915647745132446, + "learning_rate": 3.4392652338875453e-07, + "loss": 1.6003, + "step": 17286 + }, + { + "epoch": 0.9635471824313026, + "grad_norm": 0.5529605150222778, + "learning_rate": 3.428847259843437e-07, + "loss": 1.4621, + "step": 17287 + }, + { + "epoch": 0.9636029206844657, + "grad_norm": 0.5803284049034119, + "learning_rate": 3.418445034141127e-07, + "loss": 1.6383, + "step": 17288 + }, + { + "epoch": 0.9636586589376289, + "grad_norm": 0.5789690017700195, + "learning_rate": 3.408058557110461e-07, + "loss": 1.5645, + "step": 17289 + }, + { + "epoch": 0.963714397190792, + "grad_norm": 0.6098388433456421, + "learning_rate": 3.3976878290808423e-07, + "loss": 1.7982, + "step": 17290 + }, + { + "epoch": 0.9637701354439552, + "grad_norm": 0.5684050917625427, + "learning_rate": 3.3873328503811195e-07, + "loss": 1.5192, + "step": 17291 + }, + { + "epoch": 0.9638258736971184, + "grad_norm": 0.5353776216506958, + "learning_rate": 3.3769936213398635e-07, + "loss": 1.4408, + "step": 17292 + }, + { + "epoch": 0.9638816119502814, + "grad_norm": 0.5815197229385376, + "learning_rate": 3.366670142284756e-07, + "loss": 1.6641, + "step": 17293 + }, + { + "epoch": 0.9639373502034446, + "grad_norm": 0.5491476655006409, + "learning_rate": 3.356362413543313e-07, + "loss": 1.5355, + "step": 17294 + }, + { + "epoch": 0.9639930884566078, + "grad_norm": 0.587035059928894, + "learning_rate": 3.346070435442439e-07, + "loss": 1.7866, + "step": 17295 + }, + { + "epoch": 0.9640488267097709, + "grad_norm": 0.5887094140052795, + "learning_rate": 3.3357942083085405e-07, + "loss": 1.725, + "step": 17296 + }, + { + "epoch": 0.9641045649629341, + "grad_norm": 0.57686448097229, + "learning_rate": 3.325533732467523e-07, + "loss": 1.6818, + "step": 17297 + }, + { + "epoch": 0.9641603032160972, + "grad_norm": 0.5542997717857361, + "learning_rate": 3.315289008244682e-07, + "loss": 1.634, + "step": 17298 + }, + { + "epoch": 0.9642160414692603, + "grad_norm": 0.5543830394744873, + "learning_rate": 3.3050600359650354e-07, + "loss": 1.6775, + "step": 17299 + }, + { + "epoch": 0.9642717797224235, + "grad_norm": 0.6240384578704834, + "learning_rate": 3.2948468159529343e-07, + "loss": 1.7811, + "step": 17300 + }, + { + "epoch": 0.9643275179755867, + "grad_norm": 0.6050795912742615, + "learning_rate": 3.2846493485323426e-07, + "loss": 1.6629, + "step": 17301 + }, + { + "epoch": 0.9643832562287498, + "grad_norm": 0.5383679270744324, + "learning_rate": 3.274467634026557e-07, + "loss": 1.5419, + "step": 17302 + }, + { + "epoch": 0.964438994481913, + "grad_norm": 0.5714291930198669, + "learning_rate": 3.2643016727585964e-07, + "loss": 1.4743, + "step": 17303 + }, + { + "epoch": 0.9644947327350761, + "grad_norm": 0.5695536136627197, + "learning_rate": 3.2541514650508144e-07, + "loss": 1.7358, + "step": 17304 + }, + { + "epoch": 0.9645504709882392, + "grad_norm": 0.6092671155929565, + "learning_rate": 3.24401701122512e-07, + "loss": 1.7541, + "step": 17305 + }, + { + "epoch": 0.9646062092414024, + "grad_norm": 0.5745135545730591, + "learning_rate": 3.233898311602923e-07, + "loss": 1.6517, + "step": 17306 + }, + { + "epoch": 0.9646619474945656, + "grad_norm": 0.5422305464744568, + "learning_rate": 3.223795366505133e-07, + "loss": 1.3316, + "step": 17307 + }, + { + "epoch": 0.9647176857477286, + "grad_norm": 0.5784045457839966, + "learning_rate": 3.213708176252106e-07, + "loss": 1.8486, + "step": 17308 + }, + { + "epoch": 0.9647734240008918, + "grad_norm": 0.6055980920791626, + "learning_rate": 3.2036367411638066e-07, + "loss": 1.6671, + "step": 17309 + }, + { + "epoch": 0.9648291622540549, + "grad_norm": 0.5514237284660339, + "learning_rate": 3.193581061559592e-07, + "loss": 1.636, + "step": 17310 + }, + { + "epoch": 0.9648849005072181, + "grad_norm": 0.5304876565933228, + "learning_rate": 3.1835411377584833e-07, + "loss": 1.6163, + "step": 17311 + }, + { + "epoch": 0.9649406387603813, + "grad_norm": 0.5696273446083069, + "learning_rate": 3.1735169700787823e-07, + "loss": 1.7554, + "step": 17312 + }, + { + "epoch": 0.9649963770135443, + "grad_norm": 0.5528146624565125, + "learning_rate": 3.1635085588384016e-07, + "loss": 1.5399, + "step": 17313 + }, + { + "epoch": 0.9650521152667075, + "grad_norm": 0.5657849907875061, + "learning_rate": 3.1535159043547533e-07, + "loss": 1.5671, + "step": 17314 + }, + { + "epoch": 0.9651078535198707, + "grad_norm": 0.6009482145309448, + "learning_rate": 3.143539006944807e-07, + "loss": 1.6985, + "step": 17315 + }, + { + "epoch": 0.9651635917730338, + "grad_norm": 0.5508155822753906, + "learning_rate": 3.1335778669249196e-07, + "loss": 1.3725, + "step": 17316 + }, + { + "epoch": 0.965219330026197, + "grad_norm": 0.5842600464820862, + "learning_rate": 3.1236324846110055e-07, + "loss": 1.7234, + "step": 17317 + }, + { + "epoch": 0.9652750682793602, + "grad_norm": 0.551836371421814, + "learning_rate": 3.113702860318479e-07, + "loss": 1.5436, + "step": 17318 + }, + { + "epoch": 0.9653308065325232, + "grad_norm": 0.5550974011421204, + "learning_rate": 3.1037889943622555e-07, + "loss": 1.7209, + "step": 17319 + }, + { + "epoch": 0.9653865447856864, + "grad_norm": 0.5945010781288147, + "learning_rate": 3.093890887056694e-07, + "loss": 1.6455, + "step": 17320 + }, + { + "epoch": 0.9654422830388496, + "grad_norm": 0.5163649320602417, + "learning_rate": 3.0840085387158214e-07, + "loss": 1.4525, + "step": 17321 + }, + { + "epoch": 0.9654980212920127, + "grad_norm": 0.5646975040435791, + "learning_rate": 3.074141949652942e-07, + "loss": 1.6845, + "step": 17322 + }, + { + "epoch": 0.9655537595451759, + "grad_norm": 0.548812747001648, + "learning_rate": 3.064291120180973e-07, + "loss": 1.6338, + "step": 17323 + }, + { + "epoch": 0.965609497798339, + "grad_norm": 0.5883470177650452, + "learning_rate": 3.0544560506123865e-07, + "loss": 1.788, + "step": 17324 + }, + { + "epoch": 0.9656652360515021, + "grad_norm": 0.5733928680419922, + "learning_rate": 3.0446367412590435e-07, + "loss": 1.6008, + "step": 17325 + }, + { + "epoch": 0.9657209743046653, + "grad_norm": 0.5432400703430176, + "learning_rate": 3.034833192432418e-07, + "loss": 1.4603, + "step": 17326 + }, + { + "epoch": 0.9657767125578285, + "grad_norm": 0.5912125110626221, + "learning_rate": 3.0250454044433164e-07, + "loss": 1.5596, + "step": 17327 + }, + { + "epoch": 0.9658324508109916, + "grad_norm": 0.552674412727356, + "learning_rate": 3.015273377602268e-07, + "loss": 1.4737, + "step": 17328 + }, + { + "epoch": 0.9658881890641547, + "grad_norm": 0.5554338097572327, + "learning_rate": 3.0055171122190806e-07, + "loss": 1.6263, + "step": 17329 + }, + { + "epoch": 0.9659439273173179, + "grad_norm": 0.5979476571083069, + "learning_rate": 2.995776608603229e-07, + "loss": 1.6034, + "step": 17330 + }, + { + "epoch": 0.965999665570481, + "grad_norm": 0.5567131042480469, + "learning_rate": 2.986051867063577e-07, + "loss": 1.4754, + "step": 17331 + }, + { + "epoch": 0.9660554038236442, + "grad_norm": 0.5886350274085999, + "learning_rate": 2.976342887908601e-07, + "loss": 1.6227, + "step": 17332 + }, + { + "epoch": 0.9661111420768073, + "grad_norm": 0.6296853423118591, + "learning_rate": 2.9666496714461645e-07, + "loss": 1.9817, + "step": 17333 + }, + { + "epoch": 0.9661668803299704, + "grad_norm": 0.5914571285247803, + "learning_rate": 2.956972217983689e-07, + "loss": 1.6725, + "step": 17334 + }, + { + "epoch": 0.9662226185831336, + "grad_norm": 0.5795911550521851, + "learning_rate": 2.947310527828151e-07, + "loss": 1.6861, + "step": 17335 + }, + { + "epoch": 0.9662783568362967, + "grad_norm": 0.5560477375984192, + "learning_rate": 2.937664601285861e-07, + "loss": 1.5534, + "step": 17336 + }, + { + "epoch": 0.9663340950894599, + "grad_norm": 0.5729761123657227, + "learning_rate": 2.928034438662797e-07, + "loss": 1.7596, + "step": 17337 + }, + { + "epoch": 0.9663898333426231, + "grad_norm": 0.5408196449279785, + "learning_rate": 2.9184200402643247e-07, + "loss": 1.6954, + "step": 17338 + }, + { + "epoch": 0.9664455715957861, + "grad_norm": 0.5803601741790771, + "learning_rate": 2.9088214063953677e-07, + "loss": 1.6415, + "step": 17339 + }, + { + "epoch": 0.9665013098489493, + "grad_norm": 0.6737496852874756, + "learning_rate": 2.8992385373603494e-07, + "loss": 2.1054, + "step": 17340 + }, + { + "epoch": 0.9665570481021125, + "grad_norm": 0.5710918307304382, + "learning_rate": 2.8896714334631925e-07, + "loss": 1.5307, + "step": 17341 + }, + { + "epoch": 0.9666127863552756, + "grad_norm": 0.5659196376800537, + "learning_rate": 2.880120095007377e-07, + "loss": 1.6503, + "step": 17342 + }, + { + "epoch": 0.9666685246084388, + "grad_norm": 0.6507548093795776, + "learning_rate": 2.8705845222956607e-07, + "loss": 1.9174, + "step": 17343 + }, + { + "epoch": 0.966724262861602, + "grad_norm": 0.5305619239807129, + "learning_rate": 2.861064715630579e-07, + "loss": 1.422, + "step": 17344 + }, + { + "epoch": 0.966780001114765, + "grad_norm": 0.5292493104934692, + "learning_rate": 2.8515606753139466e-07, + "loss": 1.5975, + "step": 17345 + }, + { + "epoch": 0.9668357393679282, + "grad_norm": 0.5302406549453735, + "learning_rate": 2.8420724016473e-07, + "loss": 1.6251, + "step": 17346 + }, + { + "epoch": 0.9668914776210914, + "grad_norm": 0.5781571269035339, + "learning_rate": 2.8325998949314536e-07, + "loss": 1.6007, + "step": 17347 + }, + { + "epoch": 0.9669472158742545, + "grad_norm": 0.5614532828330994, + "learning_rate": 2.823143155466834e-07, + "loss": 1.5968, + "step": 17348 + }, + { + "epoch": 0.9670029541274177, + "grad_norm": 0.5478951334953308, + "learning_rate": 2.8137021835534237e-07, + "loss": 1.6994, + "step": 17349 + }, + { + "epoch": 0.9670586923805808, + "grad_norm": 0.5577452778816223, + "learning_rate": 2.8042769794905387e-07, + "loss": 1.6549, + "step": 17350 + }, + { + "epoch": 0.9671144306337439, + "grad_norm": 0.6483974456787109, + "learning_rate": 2.794867543577162e-07, + "loss": 1.5995, + "step": 17351 + }, + { + "epoch": 0.9671701688869071, + "grad_norm": 0.5784814953804016, + "learning_rate": 2.7854738761116663e-07, + "loss": 1.6002, + "step": 17352 + }, + { + "epoch": 0.9672259071400703, + "grad_norm": 0.5991257429122925, + "learning_rate": 2.776095977391979e-07, + "loss": 1.9395, + "step": 17353 + }, + { + "epoch": 0.9672816453932334, + "grad_norm": 0.5878704190254211, + "learning_rate": 2.766733847715475e-07, + "loss": 1.6846, + "step": 17354 + }, + { + "epoch": 0.9673373836463965, + "grad_norm": 0.5203773975372314, + "learning_rate": 2.7573874873791373e-07, + "loss": 1.4772, + "step": 17355 + }, + { + "epoch": 0.9673931218995596, + "grad_norm": 0.5572613477706909, + "learning_rate": 2.7480568966793407e-07, + "loss": 1.5267, + "step": 17356 + }, + { + "epoch": 0.9674488601527228, + "grad_norm": 0.5624637603759766, + "learning_rate": 2.7387420759120154e-07, + "loss": 1.6162, + "step": 17357 + }, + { + "epoch": 0.967504598405886, + "grad_norm": 0.5390849709510803, + "learning_rate": 2.7294430253725357e-07, + "loss": 1.237, + "step": 17358 + }, + { + "epoch": 0.9675603366590491, + "grad_norm": 0.556024968624115, + "learning_rate": 2.7201597453558325e-07, + "loss": 1.5605, + "step": 17359 + }, + { + "epoch": 0.9676160749122122, + "grad_norm": 0.6136623024940491, + "learning_rate": 2.710892236156337e-07, + "loss": 1.6469, + "step": 17360 + }, + { + "epoch": 0.9676718131653754, + "grad_norm": 0.567143976688385, + "learning_rate": 2.7016404980679253e-07, + "loss": 1.759, + "step": 17361 + }, + { + "epoch": 0.9677275514185385, + "grad_norm": 0.5562999844551086, + "learning_rate": 2.6924045313840296e-07, + "loss": 1.6129, + "step": 17362 + }, + { + "epoch": 0.9677832896717017, + "grad_norm": 0.5915812253952026, + "learning_rate": 2.6831843363975815e-07, + "loss": 1.5556, + "step": 17363 + }, + { + "epoch": 0.9678390279248649, + "grad_norm": 0.5475921630859375, + "learning_rate": 2.673979913400959e-07, + "loss": 1.5573, + "step": 17364 + }, + { + "epoch": 0.9678947661780279, + "grad_norm": 0.5704444050788879, + "learning_rate": 2.664791262686095e-07, + "loss": 1.6159, + "step": 17365 + }, + { + "epoch": 0.9679505044311911, + "grad_norm": 0.6007750034332275, + "learning_rate": 2.655618384544367e-07, + "loss": 1.7405, + "step": 17366 + }, + { + "epoch": 0.9680062426843543, + "grad_norm": 0.5656429529190063, + "learning_rate": 2.6464612792666544e-07, + "loss": 1.3257, + "step": 17367 + }, + { + "epoch": 0.9680619809375174, + "grad_norm": 0.5513545274734497, + "learning_rate": 2.637319947143502e-07, + "loss": 1.5611, + "step": 17368 + }, + { + "epoch": 0.9681177191906806, + "grad_norm": 0.5818155407905579, + "learning_rate": 2.6281943884646776e-07, + "loss": 1.795, + "step": 17369 + }, + { + "epoch": 0.9681734574438438, + "grad_norm": 0.5847978591918945, + "learning_rate": 2.6190846035196725e-07, + "loss": 1.7284, + "step": 17370 + }, + { + "epoch": 0.9682291956970068, + "grad_norm": 0.5976824760437012, + "learning_rate": 2.609990592597422e-07, + "loss": 1.8973, + "step": 17371 + }, + { + "epoch": 0.96828493395017, + "grad_norm": 0.5374826788902283, + "learning_rate": 2.600912355986196e-07, + "loss": 1.2629, + "step": 17372 + }, + { + "epoch": 0.9683406722033332, + "grad_norm": 0.558891773223877, + "learning_rate": 2.591849893974041e-07, + "loss": 1.6609, + "step": 17373 + }, + { + "epoch": 0.9683964104564963, + "grad_norm": 0.6174675822257996, + "learning_rate": 2.582803206848283e-07, + "loss": 1.7628, + "step": 17374 + }, + { + "epoch": 0.9684521487096595, + "grad_norm": 0.5313951373100281, + "learning_rate": 2.5737722948959155e-07, + "loss": 1.3498, + "step": 17375 + }, + { + "epoch": 0.9685078869628226, + "grad_norm": 0.5710331797599792, + "learning_rate": 2.5647571584032635e-07, + "loss": 1.6097, + "step": 17376 + }, + { + "epoch": 0.9685636252159857, + "grad_norm": 0.5484393239021301, + "learning_rate": 2.555757797656266e-07, + "loss": 1.4861, + "step": 17377 + }, + { + "epoch": 0.9686193634691489, + "grad_norm": 0.5933155417442322, + "learning_rate": 2.546774212940306e-07, + "loss": 1.6977, + "step": 17378 + }, + { + "epoch": 0.968675101722312, + "grad_norm": 0.5880883932113647, + "learning_rate": 2.537806404540377e-07, + "loss": 1.5545, + "step": 17379 + }, + { + "epoch": 0.9687308399754752, + "grad_norm": 0.5858535170555115, + "learning_rate": 2.528854372740752e-07, + "loss": 1.827, + "step": 17380 + }, + { + "epoch": 0.9687865782286383, + "grad_norm": 0.5468205213546753, + "learning_rate": 2.5199181178254814e-07, + "loss": 1.4785, + "step": 17381 + }, + { + "epoch": 0.9688423164818014, + "grad_norm": 0.6168578267097473, + "learning_rate": 2.510997640077839e-07, + "loss": 1.6028, + "step": 17382 + }, + { + "epoch": 0.9688980547349646, + "grad_norm": 0.5611661076545715, + "learning_rate": 2.50209293978082e-07, + "loss": 1.6416, + "step": 17383 + }, + { + "epoch": 0.9689537929881278, + "grad_norm": 0.5268359184265137, + "learning_rate": 2.493204017216755e-07, + "loss": 1.5737, + "step": 17384 + }, + { + "epoch": 0.9690095312412909, + "grad_norm": 0.5682333111763, + "learning_rate": 2.4843308726676396e-07, + "loss": 1.6412, + "step": 17385 + }, + { + "epoch": 0.969065269494454, + "grad_norm": 0.572048008441925, + "learning_rate": 2.475473506414805e-07, + "loss": 1.6683, + "step": 17386 + }, + { + "epoch": 0.9691210077476172, + "grad_norm": 0.5893365740776062, + "learning_rate": 2.466631918739193e-07, + "loss": 1.6574, + "step": 17387 + }, + { + "epoch": 0.9691767460007803, + "grad_norm": 0.5543003082275391, + "learning_rate": 2.45780610992119e-07, + "loss": 1.7983, + "step": 17388 + }, + { + "epoch": 0.9692324842539435, + "grad_norm": 0.6202488541603088, + "learning_rate": 2.44899608024074e-07, + "loss": 1.8562, + "step": 17389 + }, + { + "epoch": 0.9692882225071067, + "grad_norm": 0.5069781541824341, + "learning_rate": 2.4402018299771736e-07, + "loss": 1.2506, + "step": 17390 + }, + { + "epoch": 0.9693439607602697, + "grad_norm": 0.5632750391960144, + "learning_rate": 2.4314233594094904e-07, + "loss": 1.6392, + "step": 17391 + }, + { + "epoch": 0.9693996990134329, + "grad_norm": 0.5373238325119019, + "learning_rate": 2.422660668815968e-07, + "loss": 1.6612, + "step": 17392 + }, + { + "epoch": 0.9694554372665961, + "grad_norm": 0.561794102191925, + "learning_rate": 2.4139137584745507e-07, + "loss": 1.6994, + "step": 17393 + }, + { + "epoch": 0.9695111755197592, + "grad_norm": 0.5513629913330078, + "learning_rate": 2.4051826286627386e-07, + "loss": 1.5613, + "step": 17394 + }, + { + "epoch": 0.9695669137729224, + "grad_norm": 0.5551432967185974, + "learning_rate": 2.396467279657255e-07, + "loss": 1.5602, + "step": 17395 + }, + { + "epoch": 0.9696226520260856, + "grad_norm": 0.5925288200378418, + "learning_rate": 2.387767711734712e-07, + "loss": 1.6979, + "step": 17396 + }, + { + "epoch": 0.9696783902792486, + "grad_norm": 0.5694093704223633, + "learning_rate": 2.379083925170833e-07, + "loss": 1.5671, + "step": 17397 + }, + { + "epoch": 0.9697341285324118, + "grad_norm": 0.5563808083534241, + "learning_rate": 2.3704159202410647e-07, + "loss": 1.728, + "step": 17398 + }, + { + "epoch": 0.969789866785575, + "grad_norm": 0.5637340545654297, + "learning_rate": 2.361763697220354e-07, + "loss": 1.612, + "step": 17399 + }, + { + "epoch": 0.9698456050387381, + "grad_norm": 0.5685291886329651, + "learning_rate": 2.3531272563830364e-07, + "loss": 1.7587, + "step": 17400 + }, + { + "epoch": 0.9699013432919013, + "grad_norm": 0.5889203548431396, + "learning_rate": 2.3445065980031156e-07, + "loss": 1.6518, + "step": 17401 + }, + { + "epoch": 0.9699570815450643, + "grad_norm": 0.5768680572509766, + "learning_rate": 2.335901722353817e-07, + "loss": 1.7213, + "step": 17402 + }, + { + "epoch": 0.9700128197982275, + "grad_norm": 0.5813074707984924, + "learning_rate": 2.3273126297082003e-07, + "loss": 1.5702, + "step": 17403 + }, + { + "epoch": 0.9700685580513907, + "grad_norm": 0.6021438241004944, + "learning_rate": 2.3187393203385476e-07, + "loss": 1.7451, + "step": 17404 + }, + { + "epoch": 0.9701242963045538, + "grad_norm": 0.5626713633537292, + "learning_rate": 2.310181794516808e-07, + "loss": 1.7603, + "step": 17405 + }, + { + "epoch": 0.970180034557717, + "grad_norm": 0.5951448082923889, + "learning_rate": 2.301640052514431e-07, + "loss": 1.701, + "step": 17406 + }, + { + "epoch": 0.9702357728108801, + "grad_norm": 0.5505704879760742, + "learning_rate": 2.2931140946021445e-07, + "loss": 1.5951, + "step": 17407 + }, + { + "epoch": 0.9702915110640432, + "grad_norm": 0.5228086113929749, + "learning_rate": 2.2846039210505653e-07, + "loss": 1.5476, + "step": 17408 + }, + { + "epoch": 0.9703472493172064, + "grad_norm": 0.563837468624115, + "learning_rate": 2.2761095321293667e-07, + "loss": 1.5117, + "step": 17409 + }, + { + "epoch": 0.9704029875703696, + "grad_norm": 0.5393516421318054, + "learning_rate": 2.2676309281080555e-07, + "loss": 1.5716, + "step": 17410 + }, + { + "epoch": 0.9704587258235327, + "grad_norm": 0.6021537184715271, + "learning_rate": 2.2591681092555827e-07, + "loss": 1.7473, + "step": 17411 + }, + { + "epoch": 0.9705144640766958, + "grad_norm": 0.6440083384513855, + "learning_rate": 2.2507210758401787e-07, + "loss": 1.954, + "step": 17412 + }, + { + "epoch": 0.970570202329859, + "grad_norm": 0.60943603515625, + "learning_rate": 2.2422898281299064e-07, + "loss": 1.4049, + "step": 17413 + }, + { + "epoch": 0.9706259405830221, + "grad_norm": 0.5589292049407959, + "learning_rate": 2.233874366391997e-07, + "loss": 1.6264, + "step": 17414 + }, + { + "epoch": 0.9706816788361853, + "grad_norm": 0.5627011656761169, + "learning_rate": 2.2254746908934588e-07, + "loss": 1.4372, + "step": 17415 + }, + { + "epoch": 0.9707374170893485, + "grad_norm": 0.5047675967216492, + "learning_rate": 2.2170908019006344e-07, + "loss": 1.4728, + "step": 17416 + }, + { + "epoch": 0.9707931553425115, + "grad_norm": 0.5784826278686523, + "learning_rate": 2.2087226996794218e-07, + "loss": 1.7119, + "step": 17417 + }, + { + "epoch": 0.9708488935956747, + "grad_norm": 0.5366753339767456, + "learning_rate": 2.200370384495165e-07, + "loss": 1.5581, + "step": 17418 + }, + { + "epoch": 0.9709046318488379, + "grad_norm": 0.5521515011787415, + "learning_rate": 2.1920338566128185e-07, + "loss": 1.4902, + "step": 17419 + }, + { + "epoch": 0.970960370102001, + "grad_norm": 0.5769363045692444, + "learning_rate": 2.1837131162967263e-07, + "loss": 1.5332, + "step": 17420 + }, + { + "epoch": 0.9710161083551642, + "grad_norm": 0.5594366788864136, + "learning_rate": 2.1754081638107326e-07, + "loss": 1.7266, + "step": 17421 + }, + { + "epoch": 0.9710718466083273, + "grad_norm": 0.5942495465278625, + "learning_rate": 2.1671189994183493e-07, + "loss": 1.7387, + "step": 17422 + }, + { + "epoch": 0.9711275848614904, + "grad_norm": 0.5742723345756531, + "learning_rate": 2.1588456233823662e-07, + "loss": 1.6106, + "step": 17423 + }, + { + "epoch": 0.9711833231146536, + "grad_norm": 0.5840983986854553, + "learning_rate": 2.1505880359651842e-07, + "loss": 1.6707, + "step": 17424 + }, + { + "epoch": 0.9712390613678167, + "grad_norm": 0.5570304989814758, + "learning_rate": 2.1423462374286496e-07, + "loss": 1.5115, + "step": 17425 + }, + { + "epoch": 0.9712947996209799, + "grad_norm": 0.5448031425476074, + "learning_rate": 2.1341202280342198e-07, + "loss": 1.4976, + "step": 17426 + }, + { + "epoch": 0.971350537874143, + "grad_norm": 0.5733084082603455, + "learning_rate": 2.125910008042742e-07, + "loss": 1.6415, + "step": 17427 + }, + { + "epoch": 0.9714062761273061, + "grad_norm": 0.6293667554855347, + "learning_rate": 2.1177155777145075e-07, + "loss": 1.8922, + "step": 17428 + }, + { + "epoch": 0.9714620143804693, + "grad_norm": 0.6087853908538818, + "learning_rate": 2.1095369373095864e-07, + "loss": 1.7416, + "step": 17429 + }, + { + "epoch": 0.9715177526336325, + "grad_norm": 0.5907488465309143, + "learning_rate": 2.1013740870872157e-07, + "loss": 1.6385, + "step": 17430 + }, + { + "epoch": 0.9715734908867956, + "grad_norm": 0.5491884350776672, + "learning_rate": 2.0932270273062993e-07, + "loss": 1.6032, + "step": 17431 + }, + { + "epoch": 0.9716292291399587, + "grad_norm": 0.6580973267555237, + "learning_rate": 2.0850957582252418e-07, + "loss": 1.8481, + "step": 17432 + }, + { + "epoch": 0.9716849673931219, + "grad_norm": 0.5719611644744873, + "learning_rate": 2.0769802801018923e-07, + "loss": 1.6074, + "step": 17433 + }, + { + "epoch": 0.971740705646285, + "grad_norm": 0.5376779437065125, + "learning_rate": 2.0688805931936006e-07, + "loss": 1.6911, + "step": 17434 + }, + { + "epoch": 0.9717964438994482, + "grad_norm": 0.6207929849624634, + "learning_rate": 2.0607966977573278e-07, + "loss": 1.805, + "step": 17435 + }, + { + "epoch": 0.9718521821526114, + "grad_norm": 0.5388861298561096, + "learning_rate": 2.052728594049369e-07, + "loss": 1.5898, + "step": 17436 + }, + { + "epoch": 0.9719079204057745, + "grad_norm": 0.528306782245636, + "learning_rate": 2.0446762823256304e-07, + "loss": 1.556, + "step": 17437 + }, + { + "epoch": 0.9719636586589376, + "grad_norm": 0.5542298555374146, + "learning_rate": 2.0366397628414634e-07, + "loss": 1.7866, + "step": 17438 + }, + { + "epoch": 0.9720193969121008, + "grad_norm": 0.5751318335533142, + "learning_rate": 2.0286190358517753e-07, + "loss": 1.6995, + "step": 17439 + }, + { + "epoch": 0.9720751351652639, + "grad_norm": 0.5305642485618591, + "learning_rate": 2.020614101610918e-07, + "loss": 1.2878, + "step": 17440 + }, + { + "epoch": 0.9721308734184271, + "grad_norm": 0.5757197737693787, + "learning_rate": 2.0126249603727998e-07, + "loss": 1.5829, + "step": 17441 + }, + { + "epoch": 0.9721866116715903, + "grad_norm": 0.546352744102478, + "learning_rate": 2.0046516123906623e-07, + "loss": 1.535, + "step": 17442 + }, + { + "epoch": 0.9722423499247533, + "grad_norm": 0.586355447769165, + "learning_rate": 1.9966940579175253e-07, + "loss": 1.5099, + "step": 17443 + }, + { + "epoch": 0.9722980881779165, + "grad_norm": 0.578485906124115, + "learning_rate": 1.988752297205687e-07, + "loss": 1.5699, + "step": 17444 + }, + { + "epoch": 0.9723538264310797, + "grad_norm": 0.5449104309082031, + "learning_rate": 1.980826330507002e-07, + "loss": 1.4562, + "step": 17445 + }, + { + "epoch": 0.9724095646842428, + "grad_norm": 0.5530482530593872, + "learning_rate": 1.9729161580728794e-07, + "loss": 1.5444, + "step": 17446 + }, + { + "epoch": 0.972465302937406, + "grad_norm": 0.5506795048713684, + "learning_rate": 1.9650217801540637e-07, + "loss": 1.7887, + "step": 17447 + }, + { + "epoch": 0.972521041190569, + "grad_norm": 0.5185830593109131, + "learning_rate": 1.9571431970011322e-07, + "loss": 1.3856, + "step": 17448 + }, + { + "epoch": 0.9725767794437322, + "grad_norm": 0.5770006775856018, + "learning_rate": 1.9492804088637739e-07, + "loss": 1.621, + "step": 17449 + }, + { + "epoch": 0.9726325176968954, + "grad_norm": 0.5605840086936951, + "learning_rate": 1.9414334159914006e-07, + "loss": 1.5547, + "step": 17450 + }, + { + "epoch": 0.9726882559500585, + "grad_norm": 0.5712602138519287, + "learning_rate": 1.9336022186328683e-07, + "loss": 1.7351, + "step": 17451 + }, + { + "epoch": 0.9727439942032217, + "grad_norm": 0.5153247117996216, + "learning_rate": 1.9257868170365346e-07, + "loss": 1.4511, + "step": 17452 + }, + { + "epoch": 0.9727997324563848, + "grad_norm": 0.6056563258171082, + "learning_rate": 1.9179872114503118e-07, + "loss": 1.5941, + "step": 17453 + }, + { + "epoch": 0.9728554707095479, + "grad_norm": 0.5411661863327026, + "learning_rate": 1.9102034021215022e-07, + "loss": 1.5145, + "step": 17454 + }, + { + "epoch": 0.9729112089627111, + "grad_norm": 0.6172816157341003, + "learning_rate": 1.9024353892969639e-07, + "loss": 1.8374, + "step": 17455 + }, + { + "epoch": 0.9729669472158743, + "grad_norm": 0.5759900808334351, + "learning_rate": 1.8946831732231107e-07, + "loss": 1.6687, + "step": 17456 + }, + { + "epoch": 0.9730226854690374, + "grad_norm": 0.5865177512168884, + "learning_rate": 1.886946754145691e-07, + "loss": 1.7319, + "step": 17457 + }, + { + "epoch": 0.9730784237222005, + "grad_norm": 0.5775735378265381, + "learning_rate": 1.879226132310119e-07, + "loss": 1.7592, + "step": 17458 + }, + { + "epoch": 0.9731341619753637, + "grad_norm": 0.6052709817886353, + "learning_rate": 1.8715213079612548e-07, + "loss": 1.7894, + "step": 17459 + }, + { + "epoch": 0.9731899002285268, + "grad_norm": 0.5581001043319702, + "learning_rate": 1.8638322813435138e-07, + "loss": 1.751, + "step": 17460 + }, + { + "epoch": 0.97324563848169, + "grad_norm": 0.6055797338485718, + "learning_rate": 1.85615905270059e-07, + "loss": 1.8523, + "step": 17461 + }, + { + "epoch": 0.9733013767348532, + "grad_norm": 0.5984184741973877, + "learning_rate": 1.8485016222759555e-07, + "loss": 1.7618, + "step": 17462 + }, + { + "epoch": 0.9733571149880162, + "grad_norm": 0.5603173971176147, + "learning_rate": 1.8408599903124156e-07, + "loss": 1.5608, + "step": 17463 + }, + { + "epoch": 0.9734128532411794, + "grad_norm": 0.5484486222267151, + "learning_rate": 1.8332341570523326e-07, + "loss": 1.2819, + "step": 17464 + }, + { + "epoch": 0.9734685914943426, + "grad_norm": 0.6000778079032898, + "learning_rate": 1.8256241227375682e-07, + "loss": 1.7922, + "step": 17465 + }, + { + "epoch": 0.9735243297475057, + "grad_norm": 0.5797109603881836, + "learning_rate": 1.8180298876094294e-07, + "loss": 1.6168, + "step": 17466 + }, + { + "epoch": 0.9735800680006689, + "grad_norm": 0.5316083431243896, + "learning_rate": 1.810451451908779e-07, + "loss": 1.6254, + "step": 17467 + }, + { + "epoch": 0.9736358062538321, + "grad_norm": 0.5724085569381714, + "learning_rate": 1.8028888158759806e-07, + "loss": 1.3905, + "step": 17468 + }, + { + "epoch": 0.9736915445069951, + "grad_norm": 0.5840455293655396, + "learning_rate": 1.7953419797508418e-07, + "loss": 1.7984, + "step": 17469 + }, + { + "epoch": 0.9737472827601583, + "grad_norm": 0.5562770366668701, + "learning_rate": 1.7878109437727275e-07, + "loss": 1.5176, + "step": 17470 + }, + { + "epoch": 0.9738030210133214, + "grad_norm": 0.5368590354919434, + "learning_rate": 1.780295708180446e-07, + "loss": 1.5487, + "step": 17471 + }, + { + "epoch": 0.9738587592664846, + "grad_norm": 0.5613184571266174, + "learning_rate": 1.772796273212418e-07, + "loss": 1.1495, + "step": 17472 + }, + { + "epoch": 0.9739144975196478, + "grad_norm": 0.5388922691345215, + "learning_rate": 1.7653126391063422e-07, + "loss": 1.4882, + "step": 17473 + }, + { + "epoch": 0.9739702357728108, + "grad_norm": 0.6021110415458679, + "learning_rate": 1.757844806099751e-07, + "loss": 1.449, + "step": 17474 + }, + { + "epoch": 0.974025974025974, + "grad_norm": 0.5156201720237732, + "learning_rate": 1.750392774429288e-07, + "loss": 1.6215, + "step": 17475 + }, + { + "epoch": 0.9740817122791372, + "grad_norm": 0.56586092710495, + "learning_rate": 1.7429565443313755e-07, + "loss": 1.6578, + "step": 17476 + }, + { + "epoch": 0.9741374505323003, + "grad_norm": 0.5326628088951111, + "learning_rate": 1.735536116041825e-07, + "loss": 1.4979, + "step": 17477 + }, + { + "epoch": 0.9741931887854635, + "grad_norm": 0.5309004187583923, + "learning_rate": 1.7281314897960587e-07, + "loss": 1.406, + "step": 17478 + }, + { + "epoch": 0.9742489270386266, + "grad_norm": 0.6239014267921448, + "learning_rate": 1.7207426658287783e-07, + "loss": 1.8241, + "step": 17479 + }, + { + "epoch": 0.9743046652917897, + "grad_norm": 0.5447794198989868, + "learning_rate": 1.7133696443743518e-07, + "loss": 1.4602, + "step": 17480 + }, + { + "epoch": 0.9743604035449529, + "grad_norm": 0.5595765113830566, + "learning_rate": 1.7060124256667032e-07, + "loss": 1.4693, + "step": 17481 + }, + { + "epoch": 0.9744161417981161, + "grad_norm": 0.5369855165481567, + "learning_rate": 1.6986710099390347e-07, + "loss": 1.5575, + "step": 17482 + }, + { + "epoch": 0.9744718800512792, + "grad_norm": 0.5491763353347778, + "learning_rate": 1.6913453974242155e-07, + "loss": 1.3921, + "step": 17483 + }, + { + "epoch": 0.9745276183044423, + "grad_norm": 0.5946828126907349, + "learning_rate": 1.6840355883546154e-07, + "loss": 1.8316, + "step": 17484 + }, + { + "epoch": 0.9745833565576055, + "grad_norm": 0.5701006650924683, + "learning_rate": 1.6767415829619936e-07, + "loss": 1.7087, + "step": 17485 + }, + { + "epoch": 0.9746390948107686, + "grad_norm": 0.6235036849975586, + "learning_rate": 1.6694633814777204e-07, + "loss": 1.8712, + "step": 17486 + }, + { + "epoch": 0.9746948330639318, + "grad_norm": 0.5734260678291321, + "learning_rate": 1.662200984132556e-07, + "loss": 1.6848, + "step": 17487 + }, + { + "epoch": 0.974750571317095, + "grad_norm": 0.551760196685791, + "learning_rate": 1.6549543911569265e-07, + "loss": 1.5194, + "step": 17488 + }, + { + "epoch": 0.974806309570258, + "grad_norm": 0.545562744140625, + "learning_rate": 1.6477236027805376e-07, + "loss": 1.6262, + "step": 17489 + }, + { + "epoch": 0.9748620478234212, + "grad_norm": 0.5627488493919373, + "learning_rate": 1.6405086192328168e-07, + "loss": 1.6148, + "step": 17490 + }, + { + "epoch": 0.9749177860765844, + "grad_norm": 0.6104137897491455, + "learning_rate": 1.63330944074247e-07, + "loss": 1.8156, + "step": 17491 + }, + { + "epoch": 0.9749735243297475, + "grad_norm": 0.6106162667274475, + "learning_rate": 1.6261260675379254e-07, + "loss": 1.5922, + "step": 17492 + }, + { + "epoch": 0.9750292625829107, + "grad_norm": 0.5650972723960876, + "learning_rate": 1.6189584998468897e-07, + "loss": 1.6144, + "step": 17493 + }, + { + "epoch": 0.9750850008360737, + "grad_norm": 0.5150385499000549, + "learning_rate": 1.6118067378967373e-07, + "loss": 1.4621, + "step": 17494 + }, + { + "epoch": 0.9751407390892369, + "grad_norm": 0.5290409326553345, + "learning_rate": 1.604670781914286e-07, + "loss": 1.6115, + "step": 17495 + }, + { + "epoch": 0.9751964773424001, + "grad_norm": 0.5764357447624207, + "learning_rate": 1.5975506321257995e-07, + "loss": 1.7181, + "step": 17496 + }, + { + "epoch": 0.9752522155955632, + "grad_norm": 0.5669819712638855, + "learning_rate": 1.5904462887571526e-07, + "loss": 1.6811, + "step": 17497 + }, + { + "epoch": 0.9753079538487264, + "grad_norm": 0.5643836855888367, + "learning_rate": 1.5833577520336652e-07, + "loss": 1.6505, + "step": 17498 + }, + { + "epoch": 0.9753636921018896, + "grad_norm": 0.5744938254356384, + "learning_rate": 1.5762850221799908e-07, + "loss": 1.5923, + "step": 17499 + }, + { + "epoch": 0.9754194303550526, + "grad_norm": 0.547427773475647, + "learning_rate": 1.5692280994206166e-07, + "loss": 1.5352, + "step": 17500 + }, + { + "epoch": 0.9754751686082158, + "grad_norm": 0.5454980731010437, + "learning_rate": 1.5621869839792525e-07, + "loss": 1.6762, + "step": 17501 + }, + { + "epoch": 0.975530906861379, + "grad_norm": 0.5904503464698792, + "learning_rate": 1.5551616760792198e-07, + "loss": 1.6437, + "step": 17502 + }, + { + "epoch": 0.9755866451145421, + "grad_norm": 0.605842113494873, + "learning_rate": 1.5481521759433403e-07, + "loss": 1.8254, + "step": 17503 + }, + { + "epoch": 0.9756423833677053, + "grad_norm": 0.5653247833251953, + "learning_rate": 1.5411584837938808e-07, + "loss": 1.7997, + "step": 17504 + }, + { + "epoch": 0.9756981216208684, + "grad_norm": 0.5315133333206177, + "learning_rate": 1.5341805998526638e-07, + "loss": 1.4193, + "step": 17505 + }, + { + "epoch": 0.9757538598740315, + "grad_norm": 0.5977218151092529, + "learning_rate": 1.527218524341012e-07, + "loss": 1.8292, + "step": 17506 + }, + { + "epoch": 0.9758095981271947, + "grad_norm": 0.5664666295051575, + "learning_rate": 1.520272257479638e-07, + "loss": 1.6791, + "step": 17507 + }, + { + "epoch": 0.9758653363803579, + "grad_norm": 0.571151852607727, + "learning_rate": 1.5133417994889208e-07, + "loss": 1.6145, + "step": 17508 + }, + { + "epoch": 0.975921074633521, + "grad_norm": 0.559502899646759, + "learning_rate": 1.5064271505886297e-07, + "loss": 1.5854, + "step": 17509 + }, + { + "epoch": 0.9759768128866841, + "grad_norm": 0.6255260705947876, + "learning_rate": 1.4995283109980329e-07, + "loss": 1.7567, + "step": 17510 + }, + { + "epoch": 0.9760325511398473, + "grad_norm": 0.526515781879425, + "learning_rate": 1.4926452809359004e-07, + "loss": 1.4395, + "step": 17511 + }, + { + "epoch": 0.9760882893930104, + "grad_norm": 0.5295319557189941, + "learning_rate": 1.4857780606206685e-07, + "loss": 1.6581, + "step": 17512 + }, + { + "epoch": 0.9761440276461736, + "grad_norm": 0.6067336797714233, + "learning_rate": 1.4789266502699406e-07, + "loss": 1.6412, + "step": 17513 + }, + { + "epoch": 0.9761997658993368, + "grad_norm": 0.6037614941596985, + "learning_rate": 1.4720910501010432e-07, + "loss": 1.7759, + "step": 17514 + }, + { + "epoch": 0.9762555041524998, + "grad_norm": 0.5151894092559814, + "learning_rate": 1.4652712603308583e-07, + "loss": 1.4624, + "step": 17515 + }, + { + "epoch": 0.976311242405663, + "grad_norm": 0.5613059997558594, + "learning_rate": 1.4584672811756017e-07, + "loss": 1.7039, + "step": 17516 + }, + { + "epoch": 0.9763669806588261, + "grad_norm": 0.5775642991065979, + "learning_rate": 1.4516791128510453e-07, + "loss": 1.5521, + "step": 17517 + }, + { + "epoch": 0.9764227189119893, + "grad_norm": 0.5726396441459656, + "learning_rate": 1.444906755572517e-07, + "loss": 1.688, + "step": 17518 + }, + { + "epoch": 0.9764784571651525, + "grad_norm": 0.516624927520752, + "learning_rate": 1.438150209554734e-07, + "loss": 1.3975, + "step": 17519 + }, + { + "epoch": 0.9765341954183155, + "grad_norm": 0.5717558264732361, + "learning_rate": 1.4314094750120244e-07, + "loss": 1.686, + "step": 17520 + }, + { + "epoch": 0.9765899336714787, + "grad_norm": 0.5908404588699341, + "learning_rate": 1.424684552158162e-07, + "loss": 1.7495, + "step": 17521 + }, + { + "epoch": 0.9766456719246419, + "grad_norm": 0.5669304728507996, + "learning_rate": 1.4179754412064205e-07, + "loss": 1.6879, + "step": 17522 + }, + { + "epoch": 0.976701410177805, + "grad_norm": 0.5616547465324402, + "learning_rate": 1.4112821423695188e-07, + "loss": 1.643, + "step": 17523 + }, + { + "epoch": 0.9767571484309682, + "grad_norm": 0.5882663726806641, + "learning_rate": 1.4046046558598424e-07, + "loss": 1.7498, + "step": 17524 + }, + { + "epoch": 0.9768128866841314, + "grad_norm": 0.6003211140632629, + "learning_rate": 1.397942981889e-07, + "loss": 1.4685, + "step": 17525 + }, + { + "epoch": 0.9768686249372944, + "grad_norm": 0.5155422687530518, + "learning_rate": 1.3912971206684333e-07, + "loss": 1.5475, + "step": 17526 + }, + { + "epoch": 0.9769243631904576, + "grad_norm": 0.557610273361206, + "learning_rate": 1.3846670724088073e-07, + "loss": 1.6087, + "step": 17527 + }, + { + "epoch": 0.9769801014436208, + "grad_norm": 0.591092586517334, + "learning_rate": 1.3780528373203984e-07, + "loss": 1.8259, + "step": 17528 + }, + { + "epoch": 0.9770358396967839, + "grad_norm": 0.5666201114654541, + "learning_rate": 1.3714544156129828e-07, + "loss": 1.5683, + "step": 17529 + }, + { + "epoch": 0.977091577949947, + "grad_norm": 0.6234301924705505, + "learning_rate": 1.3648718074958378e-07, + "loss": 1.84, + "step": 17530 + }, + { + "epoch": 0.9771473162031102, + "grad_norm": 0.5640621185302734, + "learning_rate": 1.3583050131777408e-07, + "loss": 1.6083, + "step": 17531 + }, + { + "epoch": 0.9772030544562733, + "grad_norm": 0.5728961229324341, + "learning_rate": 1.3517540328669143e-07, + "loss": 1.6145, + "step": 17532 + }, + { + "epoch": 0.9772587927094365, + "grad_norm": 0.5581539273262024, + "learning_rate": 1.3452188667711364e-07, + "loss": 1.6176, + "step": 17533 + }, + { + "epoch": 0.9773145309625997, + "grad_norm": 0.5683838129043579, + "learning_rate": 1.33869951509763e-07, + "loss": 1.6213, + "step": 17534 + }, + { + "epoch": 0.9773702692157628, + "grad_norm": 0.5717304944992065, + "learning_rate": 1.3321959780531747e-07, + "loss": 1.476, + "step": 17535 + }, + { + "epoch": 0.9774260074689259, + "grad_norm": 0.5545562505722046, + "learning_rate": 1.3257082558440493e-07, + "loss": 1.5191, + "step": 17536 + }, + { + "epoch": 0.9774817457220891, + "grad_norm": 0.5551288723945618, + "learning_rate": 1.319236348675923e-07, + "loss": 1.5931, + "step": 17537 + }, + { + "epoch": 0.9775374839752522, + "grad_norm": 0.5903578996658325, + "learning_rate": 1.312780256754187e-07, + "loss": 1.5943, + "step": 17538 + }, + { + "epoch": 0.9775932222284154, + "grad_norm": 0.5859331488609314, + "learning_rate": 1.306339980283511e-07, + "loss": 1.6834, + "step": 17539 + }, + { + "epoch": 0.9776489604815785, + "grad_norm": 0.5414606332778931, + "learning_rate": 1.29991551946812e-07, + "loss": 1.6299, + "step": 17540 + }, + { + "epoch": 0.9777046987347416, + "grad_norm": 0.5341433882713318, + "learning_rate": 1.2935068745117962e-07, + "loss": 1.5637, + "step": 17541 + }, + { + "epoch": 0.9777604369879048, + "grad_norm": 0.5732452273368835, + "learning_rate": 1.28711404561771e-07, + "loss": 1.7262, + "step": 17542 + }, + { + "epoch": 0.9778161752410679, + "grad_norm": 0.5421660542488098, + "learning_rate": 1.2807370329887546e-07, + "loss": 1.6842, + "step": 17543 + }, + { + "epoch": 0.9778719134942311, + "grad_norm": 0.5894938707351685, + "learning_rate": 1.2743758368270464e-07, + "loss": 1.7178, + "step": 17544 + }, + { + "epoch": 0.9779276517473943, + "grad_norm": 0.5124488472938538, + "learning_rate": 1.268030457334368e-07, + "loss": 1.4419, + "step": 17545 + }, + { + "epoch": 0.9779833900005573, + "grad_norm": 0.5062386989593506, + "learning_rate": 1.261700894711948e-07, + "loss": 1.5456, + "step": 17546 + }, + { + "epoch": 0.9780391282537205, + "grad_norm": 0.5608654022216797, + "learning_rate": 1.2553871491605697e-07, + "loss": 1.6811, + "step": 17547 + }, + { + "epoch": 0.9780948665068837, + "grad_norm": 0.5316845774650574, + "learning_rate": 1.249089220880406e-07, + "loss": 1.5014, + "step": 17548 + }, + { + "epoch": 0.9781506047600468, + "grad_norm": 0.5972026586532593, + "learning_rate": 1.2428071100711869e-07, + "loss": 1.6858, + "step": 17549 + }, + { + "epoch": 0.97820634301321, + "grad_norm": 0.5620047450065613, + "learning_rate": 1.2365408169321968e-07, + "loss": 1.5579, + "step": 17550 + }, + { + "epoch": 0.9782620812663732, + "grad_norm": 0.5669444799423218, + "learning_rate": 1.2302903416621103e-07, + "loss": 1.5839, + "step": 17551 + }, + { + "epoch": 0.9783178195195362, + "grad_norm": 0.5622949600219727, + "learning_rate": 1.2240556844592133e-07, + "loss": 1.5508, + "step": 17552 + }, + { + "epoch": 0.9783735577726994, + "grad_norm": 0.57085782289505, + "learning_rate": 1.217836845521181e-07, + "loss": 1.7075, + "step": 17553 + }, + { + "epoch": 0.9784292960258626, + "grad_norm": 0.6361119747161865, + "learning_rate": 1.2116338250452995e-07, + "loss": 1.8348, + "step": 17554 + }, + { + "epoch": 0.9784850342790257, + "grad_norm": 0.6325366497039795, + "learning_rate": 1.2054466232282457e-07, + "loss": 1.9305, + "step": 17555 + }, + { + "epoch": 0.9785407725321889, + "grad_norm": 0.5608697533607483, + "learning_rate": 1.199275240266251e-07, + "loss": 1.5773, + "step": 17556 + }, + { + "epoch": 0.978596510785352, + "grad_norm": 0.5455080270767212, + "learning_rate": 1.1931196763549924e-07, + "loss": 1.493, + "step": 17557 + }, + { + "epoch": 0.9786522490385151, + "grad_norm": 0.5164167881011963, + "learning_rate": 1.1869799316897579e-07, + "loss": 1.4702, + "step": 17558 + }, + { + "epoch": 0.9787079872916783, + "grad_norm": 0.5904884338378906, + "learning_rate": 1.1808560064652807e-07, + "loss": 1.7745, + "step": 17559 + }, + { + "epoch": 0.9787637255448415, + "grad_norm": 0.5712197422981262, + "learning_rate": 1.1747479008756835e-07, + "loss": 1.6221, + "step": 17560 + }, + { + "epoch": 0.9788194637980046, + "grad_norm": 0.5632557272911072, + "learning_rate": 1.1686556151147554e-07, + "loss": 1.5683, + "step": 17561 + }, + { + "epoch": 0.9788752020511677, + "grad_norm": 0.5834195017814636, + "learning_rate": 1.1625791493756755e-07, + "loss": 1.5488, + "step": 17562 + }, + { + "epoch": 0.9789309403043308, + "grad_norm": 0.573235034942627, + "learning_rate": 1.1565185038511229e-07, + "loss": 1.6573, + "step": 17563 + }, + { + "epoch": 0.978986678557494, + "grad_norm": 0.6115302443504333, + "learning_rate": 1.150473678733388e-07, + "loss": 1.8614, + "step": 17564 + }, + { + "epoch": 0.9790424168106572, + "grad_norm": 0.5387873649597168, + "learning_rate": 1.1444446742141512e-07, + "loss": 1.281, + "step": 17565 + }, + { + "epoch": 0.9790981550638203, + "grad_norm": 0.555159866809845, + "learning_rate": 1.1384314904845372e-07, + "loss": 1.7311, + "step": 17566 + }, + { + "epoch": 0.9791538933169834, + "grad_norm": 0.5555679798126221, + "learning_rate": 1.1324341277353378e-07, + "loss": 1.5461, + "step": 17567 + }, + { + "epoch": 0.9792096315701466, + "grad_norm": 0.5714148283004761, + "learning_rate": 1.1264525861567344e-07, + "loss": 1.6261, + "step": 17568 + }, + { + "epoch": 0.9792653698233097, + "grad_norm": 0.5695425868034363, + "learning_rate": 1.1204868659384082e-07, + "loss": 1.5654, + "step": 17569 + }, + { + "epoch": 0.9793211080764729, + "grad_norm": 0.5962039828300476, + "learning_rate": 1.1145369672695971e-07, + "loss": 1.4733, + "step": 17570 + }, + { + "epoch": 0.9793768463296361, + "grad_norm": 0.5857483744621277, + "learning_rate": 1.1086028903389833e-07, + "loss": 1.724, + "step": 17571 + }, + { + "epoch": 0.9794325845827991, + "grad_norm": 0.597956120967865, + "learning_rate": 1.1026846353346943e-07, + "loss": 1.6512, + "step": 17572 + }, + { + "epoch": 0.9794883228359623, + "grad_norm": 0.5775173902511597, + "learning_rate": 1.096782202444524e-07, + "loss": 1.7214, + "step": 17573 + }, + { + "epoch": 0.9795440610891255, + "grad_norm": 0.5533824563026428, + "learning_rate": 1.0908955918556007e-07, + "loss": 1.6191, + "step": 17574 + }, + { + "epoch": 0.9795997993422886, + "grad_norm": 0.5322213768959045, + "learning_rate": 1.0850248037546085e-07, + "loss": 1.5329, + "step": 17575 + }, + { + "epoch": 0.9796555375954518, + "grad_norm": 0.5811262726783752, + "learning_rate": 1.0791698383277315e-07, + "loss": 1.6629, + "step": 17576 + }, + { + "epoch": 0.979711275848615, + "grad_norm": 0.6128361225128174, + "learning_rate": 1.0733306957607104e-07, + "loss": 1.6974, + "step": 17577 + }, + { + "epoch": 0.979767014101778, + "grad_norm": 0.5672536492347717, + "learning_rate": 1.06750737623873e-07, + "loss": 1.6688, + "step": 17578 + }, + { + "epoch": 0.9798227523549412, + "grad_norm": 0.5492042303085327, + "learning_rate": 1.0616998799463651e-07, + "loss": 1.7467, + "step": 17579 + }, + { + "epoch": 0.9798784906081044, + "grad_norm": 0.5600057244300842, + "learning_rate": 1.0559082070679127e-07, + "loss": 1.8833, + "step": 17580 + }, + { + "epoch": 0.9799342288612675, + "grad_norm": 0.5473673939704895, + "learning_rate": 1.0501323577870037e-07, + "loss": 1.5387, + "step": 17581 + }, + { + "epoch": 0.9799899671144306, + "grad_norm": 0.5802236795425415, + "learning_rate": 1.0443723322868248e-07, + "loss": 1.6262, + "step": 17582 + }, + { + "epoch": 0.9800457053675938, + "grad_norm": 0.5640122294425964, + "learning_rate": 1.0386281307500079e-07, + "loss": 1.5699, + "step": 17583 + }, + { + "epoch": 0.9801014436207569, + "grad_norm": 0.5737574696540833, + "learning_rate": 1.0328997533587958e-07, + "loss": 1.6014, + "step": 17584 + }, + { + "epoch": 0.9801571818739201, + "grad_norm": 0.5717910528182983, + "learning_rate": 1.0271872002948213e-07, + "loss": 1.7115, + "step": 17585 + }, + { + "epoch": 0.9802129201270832, + "grad_norm": 0.5819235444068909, + "learning_rate": 1.0214904717392171e-07, + "loss": 1.6098, + "step": 17586 + }, + { + "epoch": 0.9802686583802463, + "grad_norm": 0.5310031175613403, + "learning_rate": 1.0158095678727275e-07, + "loss": 1.4817, + "step": 17587 + }, + { + "epoch": 0.9803243966334095, + "grad_norm": 0.5269623398780823, + "learning_rate": 1.0101444888754308e-07, + "loss": 1.4595, + "step": 17588 + }, + { + "epoch": 0.9803801348865726, + "grad_norm": 0.6050212979316711, + "learning_rate": 1.004495234927072e-07, + "loss": 1.6758, + "step": 17589 + }, + { + "epoch": 0.9804358731397358, + "grad_norm": 0.6110159754753113, + "learning_rate": 9.988618062068411e-08, + "loss": 1.9659, + "step": 17590 + }, + { + "epoch": 0.980491611392899, + "grad_norm": 0.6562373042106628, + "learning_rate": 9.93244202893262e-08, + "loss": 1.8171, + "step": 17591 + }, + { + "epoch": 0.980547349646062, + "grad_norm": 0.5384320020675659, + "learning_rate": 9.87642425164581e-08, + "loss": 1.6474, + "step": 17592 + }, + { + "epoch": 0.9806030878992252, + "grad_norm": 0.5735446214675903, + "learning_rate": 9.820564731984339e-08, + "loss": 1.7013, + "step": 17593 + }, + { + "epoch": 0.9806588261523884, + "grad_norm": 0.6070604920387268, + "learning_rate": 9.764863471719565e-08, + "loss": 1.7987, + "step": 17594 + }, + { + "epoch": 0.9807145644055515, + "grad_norm": 0.5484580993652344, + "learning_rate": 9.70932047261841e-08, + "loss": 1.6046, + "step": 17595 + }, + { + "epoch": 0.9807703026587147, + "grad_norm": 0.581143856048584, + "learning_rate": 9.653935736442244e-08, + "loss": 1.7104, + "step": 17596 + }, + { + "epoch": 0.9808260409118779, + "grad_norm": 0.5306569933891296, + "learning_rate": 9.598709264947436e-08, + "loss": 1.4238, + "step": 17597 + }, + { + "epoch": 0.9808817791650409, + "grad_norm": 0.5836363434791565, + "learning_rate": 9.543641059885922e-08, + "loss": 1.8799, + "step": 17598 + }, + { + "epoch": 0.9809375174182041, + "grad_norm": 0.5329042673110962, + "learning_rate": 9.48873112300297e-08, + "loss": 1.4658, + "step": 17599 + }, + { + "epoch": 0.9809932556713673, + "grad_norm": 0.5836918354034424, + "learning_rate": 9.433979456041631e-08, + "loss": 1.5968, + "step": 17600 + }, + { + "epoch": 0.9810489939245304, + "grad_norm": 0.5990757942199707, + "learning_rate": 9.379386060736628e-08, + "loss": 1.655, + "step": 17601 + }, + { + "epoch": 0.9811047321776936, + "grad_norm": 0.5767358541488647, + "learning_rate": 9.324950938820465e-08, + "loss": 1.6373, + "step": 17602 + }, + { + "epoch": 0.9811604704308567, + "grad_norm": 0.5505197644233704, + "learning_rate": 9.270674092019537e-08, + "loss": 1.5491, + "step": 17603 + }, + { + "epoch": 0.9812162086840198, + "grad_norm": 0.5758749842643738, + "learning_rate": 9.216555522054692e-08, + "loss": 1.5259, + "step": 17604 + }, + { + "epoch": 0.981271946937183, + "grad_norm": 0.5435932278633118, + "learning_rate": 9.162595230642334e-08, + "loss": 1.589, + "step": 17605 + }, + { + "epoch": 0.9813276851903462, + "grad_norm": 0.5337393283843994, + "learning_rate": 9.108793219493872e-08, + "loss": 1.5886, + "step": 17606 + }, + { + "epoch": 0.9813834234435093, + "grad_norm": 0.554614782333374, + "learning_rate": 9.055149490315163e-08, + "loss": 1.4713, + "step": 17607 + }, + { + "epoch": 0.9814391616966724, + "grad_norm": 0.5531981587409973, + "learning_rate": 9.001664044808733e-08, + "loss": 1.5119, + "step": 17608 + }, + { + "epoch": 0.9814948999498355, + "grad_norm": 0.5442023277282715, + "learning_rate": 8.94833688466934e-08, + "loss": 1.5986, + "step": 17609 + }, + { + "epoch": 0.9815506382029987, + "grad_norm": 0.5532471537590027, + "learning_rate": 8.895168011588961e-08, + "loss": 1.6371, + "step": 17610 + }, + { + "epoch": 0.9816063764561619, + "grad_norm": 0.5365181565284729, + "learning_rate": 8.842157427254027e-08, + "loss": 1.4524, + "step": 17611 + }, + { + "epoch": 0.981662114709325, + "grad_norm": 0.5608639717102051, + "learning_rate": 8.78930513334486e-08, + "loss": 1.5316, + "step": 17612 + }, + { + "epoch": 0.9817178529624881, + "grad_norm": 0.6386743783950806, + "learning_rate": 8.736611131538452e-08, + "loss": 1.6934, + "step": 17613 + }, + { + "epoch": 0.9817735912156513, + "grad_norm": 0.5726924538612366, + "learning_rate": 8.684075423505688e-08, + "loss": 1.676, + "step": 17614 + }, + { + "epoch": 0.9818293294688144, + "grad_norm": 0.5828086733818054, + "learning_rate": 8.631698010912459e-08, + "loss": 1.5567, + "step": 17615 + }, + { + "epoch": 0.9818850677219776, + "grad_norm": 0.5307722091674805, + "learning_rate": 8.579478895420212e-08, + "loss": 1.5866, + "step": 17616 + }, + { + "epoch": 0.9819408059751408, + "grad_norm": 0.5634893774986267, + "learning_rate": 8.527418078684845e-08, + "loss": 1.729, + "step": 17617 + }, + { + "epoch": 0.9819965442283038, + "grad_norm": 0.566849946975708, + "learning_rate": 8.475515562357816e-08, + "loss": 1.5519, + "step": 17618 + }, + { + "epoch": 0.982052282481467, + "grad_norm": 0.5177443623542786, + "learning_rate": 8.423771348084474e-08, + "loss": 1.3238, + "step": 17619 + }, + { + "epoch": 0.9821080207346302, + "grad_norm": 0.5961422324180603, + "learning_rate": 8.372185437506285e-08, + "loss": 1.6958, + "step": 17620 + }, + { + "epoch": 0.9821637589877933, + "grad_norm": 0.5936393141746521, + "learning_rate": 8.320757832259163e-08, + "loss": 1.5099, + "step": 17621 + }, + { + "epoch": 0.9822194972409565, + "grad_norm": 0.5952803492546082, + "learning_rate": 8.269488533974024e-08, + "loss": 1.8139, + "step": 17622 + }, + { + "epoch": 0.9822752354941197, + "grad_norm": 0.594485878944397, + "learning_rate": 8.21837754427679e-08, + "loss": 1.7761, + "step": 17623 + }, + { + "epoch": 0.9823309737472827, + "grad_norm": 0.5753436088562012, + "learning_rate": 8.167424864788942e-08, + "loss": 1.5626, + "step": 17624 + }, + { + "epoch": 0.9823867120004459, + "grad_norm": 0.5214491486549377, + "learning_rate": 8.1166304971253e-08, + "loss": 1.29, + "step": 17625 + }, + { + "epoch": 0.9824424502536091, + "grad_norm": 0.5985666513442993, + "learning_rate": 8.065994442897906e-08, + "loss": 1.779, + "step": 17626 + }, + { + "epoch": 0.9824981885067722, + "grad_norm": 0.5855262279510498, + "learning_rate": 8.015516703712145e-08, + "loss": 1.5287, + "step": 17627 + }, + { + "epoch": 0.9825539267599354, + "grad_norm": 0.5555679798126221, + "learning_rate": 7.965197281168957e-08, + "loss": 1.6058, + "step": 17628 + }, + { + "epoch": 0.9826096650130985, + "grad_norm": 0.5779415965080261, + "learning_rate": 7.915036176864288e-08, + "loss": 1.5269, + "step": 17629 + }, + { + "epoch": 0.9826654032662616, + "grad_norm": 0.5492480993270874, + "learning_rate": 7.865033392388533e-08, + "loss": 1.6304, + "step": 17630 + }, + { + "epoch": 0.9827211415194248, + "grad_norm": 0.5686248540878296, + "learning_rate": 7.815188929327644e-08, + "loss": 1.6169, + "step": 17631 + }, + { + "epoch": 0.9827768797725879, + "grad_norm": 0.5415977835655212, + "learning_rate": 7.76550278926258e-08, + "loss": 1.4114, + "step": 17632 + }, + { + "epoch": 0.9828326180257511, + "grad_norm": 0.6027060747146606, + "learning_rate": 7.715974973769302e-08, + "loss": 1.5866, + "step": 17633 + }, + { + "epoch": 0.9828883562789142, + "grad_norm": 0.5264376401901245, + "learning_rate": 7.666605484417666e-08, + "loss": 1.4801, + "step": 17634 + }, + { + "epoch": 0.9829440945320773, + "grad_norm": 0.5663968324661255, + "learning_rate": 7.617394322774752e-08, + "loss": 1.5682, + "step": 17635 + }, + { + "epoch": 0.9829998327852405, + "grad_norm": 0.5683836340904236, + "learning_rate": 7.568341490399866e-08, + "loss": 1.7344, + "step": 17636 + }, + { + "epoch": 0.9830555710384037, + "grad_norm": 0.5963418483734131, + "learning_rate": 7.519446988849543e-08, + "loss": 1.6406, + "step": 17637 + }, + { + "epoch": 0.9831113092915668, + "grad_norm": 0.5845539569854736, + "learning_rate": 7.470710819674209e-08, + "loss": 1.6992, + "step": 17638 + }, + { + "epoch": 0.9831670475447299, + "grad_norm": 0.5363653898239136, + "learning_rate": 7.422132984419294e-08, + "loss": 1.5221, + "step": 17639 + }, + { + "epoch": 0.9832227857978931, + "grad_norm": 0.6009367108345032, + "learning_rate": 7.373713484625789e-08, + "loss": 1.9106, + "step": 17640 + }, + { + "epoch": 0.9832785240510562, + "grad_norm": 0.6247106790542603, + "learning_rate": 7.325452321828574e-08, + "loss": 2.0823, + "step": 17641 + }, + { + "epoch": 0.9833342623042194, + "grad_norm": 0.5325173735618591, + "learning_rate": 7.277349497559205e-08, + "loss": 1.5629, + "step": 17642 + }, + { + "epoch": 0.9833900005573826, + "grad_norm": 0.5428493618965149, + "learning_rate": 7.229405013342572e-08, + "loss": 1.4567, + "step": 17643 + }, + { + "epoch": 0.9834457388105456, + "grad_norm": 0.5612325072288513, + "learning_rate": 7.18161887069968e-08, + "loss": 1.6365, + "step": 17644 + }, + { + "epoch": 0.9835014770637088, + "grad_norm": 0.5935699343681335, + "learning_rate": 7.133991071145429e-08, + "loss": 1.6963, + "step": 17645 + }, + { + "epoch": 0.983557215316872, + "grad_norm": 0.6116538047790527, + "learning_rate": 7.086521616190279e-08, + "loss": 1.8795, + "step": 17646 + }, + { + "epoch": 0.9836129535700351, + "grad_norm": 0.5670484900474548, + "learning_rate": 7.039210507340244e-08, + "loss": 1.7972, + "step": 17647 + }, + { + "epoch": 0.9836686918231983, + "grad_norm": 0.5587061643600464, + "learning_rate": 6.992057746095237e-08, + "loss": 1.6461, + "step": 17648 + }, + { + "epoch": 0.9837244300763615, + "grad_norm": 0.5563431978225708, + "learning_rate": 6.945063333951285e-08, + "loss": 1.5296, + "step": 17649 + }, + { + "epoch": 0.9837801683295245, + "grad_norm": 0.5587682723999023, + "learning_rate": 6.898227272398305e-08, + "loss": 1.7309, + "step": 17650 + }, + { + "epoch": 0.9838359065826877, + "grad_norm": 0.5581985712051392, + "learning_rate": 6.851549562921223e-08, + "loss": 1.4404, + "step": 17651 + }, + { + "epoch": 0.9838916448358509, + "grad_norm": 0.5164779424667358, + "learning_rate": 6.805030207001629e-08, + "loss": 1.515, + "step": 17652 + }, + { + "epoch": 0.983947383089014, + "grad_norm": 0.5820528864860535, + "learning_rate": 6.758669206113899e-08, + "loss": 1.7107, + "step": 17653 + }, + { + "epoch": 0.9840031213421772, + "grad_norm": 0.5570393800735474, + "learning_rate": 6.71246656172797e-08, + "loss": 1.7174, + "step": 17654 + }, + { + "epoch": 0.9840588595953402, + "grad_norm": 0.5851088762283325, + "learning_rate": 6.666422275310446e-08, + "loss": 1.7076, + "step": 17655 + }, + { + "epoch": 0.9841145978485034, + "grad_norm": 0.5754079818725586, + "learning_rate": 6.620536348320716e-08, + "loss": 1.5258, + "step": 17656 + }, + { + "epoch": 0.9841703361016666, + "grad_norm": 0.561769425868988, + "learning_rate": 6.574808782214282e-08, + "loss": 1.6819, + "step": 17657 + }, + { + "epoch": 0.9842260743548297, + "grad_norm": 0.5445395708084106, + "learning_rate": 6.529239578440539e-08, + "loss": 1.5465, + "step": 17658 + }, + { + "epoch": 0.9842818126079929, + "grad_norm": 0.5681195855140686, + "learning_rate": 6.483828738446107e-08, + "loss": 1.7137, + "step": 17659 + }, + { + "epoch": 0.984337550861156, + "grad_norm": 0.5304739475250244, + "learning_rate": 6.438576263669838e-08, + "loss": 1.4516, + "step": 17660 + }, + { + "epoch": 0.9843932891143191, + "grad_norm": 0.5998936295509338, + "learning_rate": 6.393482155547803e-08, + "loss": 1.5397, + "step": 17661 + }, + { + "epoch": 0.9844490273674823, + "grad_norm": 0.5229600667953491, + "learning_rate": 6.34854641550997e-08, + "loss": 1.6758, + "step": 17662 + }, + { + "epoch": 0.9845047656206455, + "grad_norm": 0.5354757905006409, + "learning_rate": 6.303769044980757e-08, + "loss": 1.4918, + "step": 17663 + }, + { + "epoch": 0.9845605038738086, + "grad_norm": 0.5705389380455017, + "learning_rate": 6.259150045381245e-08, + "loss": 1.7168, + "step": 17664 + }, + { + "epoch": 0.9846162421269717, + "grad_norm": 0.5588167309761047, + "learning_rate": 6.214689418125308e-08, + "loss": 1.562, + "step": 17665 + }, + { + "epoch": 0.9846719803801349, + "grad_norm": 0.502700924873352, + "learning_rate": 6.170387164624036e-08, + "loss": 1.4466, + "step": 17666 + }, + { + "epoch": 0.984727718633298, + "grad_norm": 0.5499680042266846, + "learning_rate": 6.126243286281863e-08, + "loss": 1.3996, + "step": 17667 + }, + { + "epoch": 0.9847834568864612, + "grad_norm": 0.551371157169342, + "learning_rate": 6.082257784499335e-08, + "loss": 1.4558, + "step": 17668 + }, + { + "epoch": 0.9848391951396244, + "grad_norm": 0.5390509963035583, + "learning_rate": 6.038430660670891e-08, + "loss": 1.5282, + "step": 17669 + }, + { + "epoch": 0.9848949333927874, + "grad_norm": 0.5301749110221863, + "learning_rate": 5.99476191618653e-08, + "loss": 1.5312, + "step": 17670 + }, + { + "epoch": 0.9849506716459506, + "grad_norm": 0.5372301340103149, + "learning_rate": 5.9512515524312586e-08, + "loss": 1.6531, + "step": 17671 + }, + { + "epoch": 0.9850064098991138, + "grad_norm": 0.5120816230773926, + "learning_rate": 5.9078995707845255e-08, + "loss": 1.3456, + "step": 17672 + }, + { + "epoch": 0.9850621481522769, + "grad_norm": 0.5552569031715393, + "learning_rate": 5.864705972622453e-08, + "loss": 1.581, + "step": 17673 + }, + { + "epoch": 0.9851178864054401, + "grad_norm": 0.5756086707115173, + "learning_rate": 5.8216707593133915e-08, + "loss": 1.5573, + "step": 17674 + }, + { + "epoch": 0.9851736246586033, + "grad_norm": 0.5051289200782776, + "learning_rate": 5.77879393222347e-08, + "loss": 1.4311, + "step": 17675 + }, + { + "epoch": 0.9852293629117663, + "grad_norm": 0.6823752522468567, + "learning_rate": 5.7360754927110464e-08, + "loss": 1.5767, + "step": 17676 + }, + { + "epoch": 0.9852851011649295, + "grad_norm": 0.5909570455551147, + "learning_rate": 5.693515442132258e-08, + "loss": 1.7955, + "step": 17677 + }, + { + "epoch": 0.9853408394180926, + "grad_norm": 0.5723685026168823, + "learning_rate": 5.651113781836581e-08, + "loss": 1.5223, + "step": 17678 + }, + { + "epoch": 0.9853965776712558, + "grad_norm": 0.5648658275604248, + "learning_rate": 5.6088705131679407e-08, + "loss": 1.6272, + "step": 17679 + }, + { + "epoch": 0.985452315924419, + "grad_norm": 0.5270441770553589, + "learning_rate": 5.5667856374669314e-08, + "loss": 1.5475, + "step": 17680 + }, + { + "epoch": 0.985508054177582, + "grad_norm": 0.6145524382591248, + "learning_rate": 5.524859156068041e-08, + "loss": 1.7325, + "step": 17681 + }, + { + "epoch": 0.9855637924307452, + "grad_norm": 0.5308423638343811, + "learning_rate": 5.483091070300761e-08, + "loss": 1.4162, + "step": 17682 + }, + { + "epoch": 0.9856195306839084, + "grad_norm": 0.5819408297538757, + "learning_rate": 5.441481381489588e-08, + "loss": 1.5781, + "step": 17683 + }, + { + "epoch": 0.9856752689370715, + "grad_norm": 0.5704575777053833, + "learning_rate": 5.4000300909540224e-08, + "loss": 1.6112, + "step": 17684 + }, + { + "epoch": 0.9857310071902347, + "grad_norm": 0.5668299794197083, + "learning_rate": 5.358737200009678e-08, + "loss": 1.4819, + "step": 17685 + }, + { + "epoch": 0.9857867454433978, + "grad_norm": 0.5464116930961609, + "learning_rate": 5.3176027099649526e-08, + "loss": 1.6226, + "step": 17686 + }, + { + "epoch": 0.9858424836965609, + "grad_norm": 0.5709362030029297, + "learning_rate": 5.276626622124914e-08, + "loss": 1.6784, + "step": 17687 + }, + { + "epoch": 0.9858982219497241, + "grad_norm": 0.5686623454093933, + "learning_rate": 5.2358089377890776e-08, + "loss": 1.8073, + "step": 17688 + }, + { + "epoch": 0.9859539602028873, + "grad_norm": 0.583076536655426, + "learning_rate": 5.195149658251963e-08, + "loss": 1.6573, + "step": 17689 + }, + { + "epoch": 0.9860096984560504, + "grad_norm": 0.530877947807312, + "learning_rate": 5.15464878480254e-08, + "loss": 1.473, + "step": 17690 + }, + { + "epoch": 0.9860654367092135, + "grad_norm": 0.5617296695709229, + "learning_rate": 5.114306318726447e-08, + "loss": 1.6588, + "step": 17691 + }, + { + "epoch": 0.9861211749623767, + "grad_norm": 0.5920813083648682, + "learning_rate": 5.074122261301551e-08, + "loss": 1.6358, + "step": 17692 + }, + { + "epoch": 0.9861769132155398, + "grad_norm": 0.6091045141220093, + "learning_rate": 5.034096613803496e-08, + "loss": 1.8155, + "step": 17693 + }, + { + "epoch": 0.986232651468703, + "grad_norm": 0.527067244052887, + "learning_rate": 4.9942293775012696e-08, + "loss": 1.4193, + "step": 17694 + }, + { + "epoch": 0.9862883897218662, + "grad_norm": 0.5787523984909058, + "learning_rate": 4.954520553658859e-08, + "loss": 1.7525, + "step": 17695 + }, + { + "epoch": 0.9863441279750292, + "grad_norm": 0.530201256275177, + "learning_rate": 4.914970143536368e-08, + "loss": 1.4906, + "step": 17696 + }, + { + "epoch": 0.9863998662281924, + "grad_norm": 0.5512275695800781, + "learning_rate": 4.875578148387794e-08, + "loss": 1.789, + "step": 17697 + }, + { + "epoch": 0.9864556044813556, + "grad_norm": 0.5669159889221191, + "learning_rate": 4.8363445694615814e-08, + "loss": 1.7271, + "step": 17698 + }, + { + "epoch": 0.9865113427345187, + "grad_norm": 0.6101011633872986, + "learning_rate": 4.797269408002847e-08, + "loss": 1.9038, + "step": 17699 + }, + { + "epoch": 0.9865670809876819, + "grad_norm": 0.5837644934654236, + "learning_rate": 4.758352665251153e-08, + "loss": 1.6516, + "step": 17700 + }, + { + "epoch": 0.9866228192408449, + "grad_norm": 0.5508288741111755, + "learning_rate": 4.719594342439959e-08, + "loss": 1.6106, + "step": 17701 + }, + { + "epoch": 0.9866785574940081, + "grad_norm": 0.5630781650543213, + "learning_rate": 4.680994440798836e-08, + "loss": 1.5687, + "step": 17702 + }, + { + "epoch": 0.9867342957471713, + "grad_norm": 0.6122694611549377, + "learning_rate": 4.642552961551805e-08, + "loss": 1.7888, + "step": 17703 + }, + { + "epoch": 0.9867900340003344, + "grad_norm": 0.5711543560028076, + "learning_rate": 4.604269905917891e-08, + "loss": 1.4133, + "step": 17704 + }, + { + "epoch": 0.9868457722534976, + "grad_norm": 0.5705737471580505, + "learning_rate": 4.5661452751111223e-08, + "loss": 1.7083, + "step": 17705 + }, + { + "epoch": 0.9869015105066608, + "grad_norm": 0.5657354593276978, + "learning_rate": 4.5281790703410875e-08, + "loss": 1.6912, + "step": 17706 + }, + { + "epoch": 0.9869572487598238, + "grad_norm": 0.5302325487136841, + "learning_rate": 4.490371292811824e-08, + "loss": 1.115, + "step": 17707 + }, + { + "epoch": 0.987012987012987, + "grad_norm": 0.5923711061477661, + "learning_rate": 4.452721943721816e-08, + "loss": 1.6267, + "step": 17708 + }, + { + "epoch": 0.9870687252661502, + "grad_norm": 0.6066462993621826, + "learning_rate": 4.4152310242656646e-08, + "loss": 1.8893, + "step": 17709 + }, + { + "epoch": 0.9871244635193133, + "grad_norm": 0.5526143312454224, + "learning_rate": 4.377898535631863e-08, + "loss": 1.7032, + "step": 17710 + }, + { + "epoch": 0.9871802017724765, + "grad_norm": 0.5796599388122559, + "learning_rate": 4.3407244790050207e-08, + "loss": 1.5622, + "step": 17711 + }, + { + "epoch": 0.9872359400256396, + "grad_norm": 0.5357824563980103, + "learning_rate": 4.303708855563082e-08, + "loss": 1.5024, + "step": 17712 + }, + { + "epoch": 0.9872916782788027, + "grad_norm": 0.5754384398460388, + "learning_rate": 4.26685166648122e-08, + "loss": 1.6252, + "step": 17713 + }, + { + "epoch": 0.9873474165319659, + "grad_norm": 0.5639127492904663, + "learning_rate": 4.230152912927387e-08, + "loss": 1.5022, + "step": 17714 + }, + { + "epoch": 0.9874031547851291, + "grad_norm": 0.5203130841255188, + "learning_rate": 4.193612596065655e-08, + "loss": 1.3451, + "step": 17715 + }, + { + "epoch": 0.9874588930382922, + "grad_norm": 0.5642319321632385, + "learning_rate": 4.1572307170550936e-08, + "loss": 1.4555, + "step": 17716 + }, + { + "epoch": 0.9875146312914553, + "grad_norm": 0.553350031375885, + "learning_rate": 4.121007277049227e-08, + "loss": 1.4166, + "step": 17717 + }, + { + "epoch": 0.9875703695446185, + "grad_norm": 0.5548847317695618, + "learning_rate": 4.084942277197135e-08, + "loss": 1.5581, + "step": 17718 + }, + { + "epoch": 0.9876261077977816, + "grad_norm": 0.5544130802154541, + "learning_rate": 4.049035718642347e-08, + "loss": 1.6954, + "step": 17719 + }, + { + "epoch": 0.9876818460509448, + "grad_norm": 0.5522232055664062, + "learning_rate": 4.013287602523952e-08, + "loss": 1.5224, + "step": 17720 + }, + { + "epoch": 0.987737584304108, + "grad_norm": 0.5449672937393188, + "learning_rate": 3.9776979299749326e-08, + "loss": 1.6119, + "step": 17721 + }, + { + "epoch": 0.987793322557271, + "grad_norm": 0.5824279189109802, + "learning_rate": 3.9422667021249414e-08, + "loss": 1.9024, + "step": 17722 + }, + { + "epoch": 0.9878490608104342, + "grad_norm": 0.5748085975646973, + "learning_rate": 3.906993920097524e-08, + "loss": 1.7866, + "step": 17723 + }, + { + "epoch": 0.9879047990635973, + "grad_norm": 0.5287823677062988, + "learning_rate": 3.871879585010674e-08, + "loss": 1.4668, + "step": 17724 + }, + { + "epoch": 0.9879605373167605, + "grad_norm": 0.5538375973701477, + "learning_rate": 3.8369236979779455e-08, + "loss": 1.5639, + "step": 17725 + }, + { + "epoch": 0.9880162755699237, + "grad_norm": 0.5878131985664368, + "learning_rate": 3.8021262601090066e-08, + "loss": 1.6867, + "step": 17726 + }, + { + "epoch": 0.9880720138230867, + "grad_norm": 0.5977593064308167, + "learning_rate": 3.767487272506309e-08, + "loss": 1.4791, + "step": 17727 + }, + { + "epoch": 0.9881277520762499, + "grad_norm": 0.6099099516868591, + "learning_rate": 3.7330067362689736e-08, + "loss": 1.482, + "step": 17728 + }, + { + "epoch": 0.9881834903294131, + "grad_norm": 0.5905750393867493, + "learning_rate": 3.698684652490569e-08, + "loss": 1.7269, + "step": 17729 + }, + { + "epoch": 0.9882392285825762, + "grad_norm": 0.5845779180526733, + "learning_rate": 3.664521022259671e-08, + "loss": 1.8449, + "step": 17730 + }, + { + "epoch": 0.9882949668357394, + "grad_norm": 0.5942860245704651, + "learning_rate": 3.630515846658744e-08, + "loss": 1.8374, + "step": 17731 + }, + { + "epoch": 0.9883507050889025, + "grad_norm": 0.5766461491584778, + "learning_rate": 3.5966691267674824e-08, + "loss": 1.5831, + "step": 17732 + }, + { + "epoch": 0.9884064433420656, + "grad_norm": 0.5644928812980652, + "learning_rate": 3.5629808636589154e-08, + "loss": 1.541, + "step": 17733 + }, + { + "epoch": 0.9884621815952288, + "grad_norm": 0.4986118674278259, + "learning_rate": 3.529451058401079e-08, + "loss": 1.3535, + "step": 17734 + }, + { + "epoch": 0.988517919848392, + "grad_norm": 0.5393011569976807, + "learning_rate": 3.4960797120581204e-08, + "loss": 1.6024, + "step": 17735 + }, + { + "epoch": 0.9885736581015551, + "grad_norm": 0.5787156224250793, + "learning_rate": 3.4628668256875273e-08, + "loss": 1.532, + "step": 17736 + }, + { + "epoch": 0.9886293963547182, + "grad_norm": 0.5874704122543335, + "learning_rate": 3.429812400342902e-08, + "loss": 1.7255, + "step": 17737 + }, + { + "epoch": 0.9886851346078814, + "grad_norm": 0.5697699785232544, + "learning_rate": 3.396916437072295e-08, + "loss": 1.6464, + "step": 17738 + }, + { + "epoch": 0.9887408728610445, + "grad_norm": 0.5763781666755676, + "learning_rate": 3.3641789369198706e-08, + "loss": 1.6756, + "step": 17739 + }, + { + "epoch": 0.9887966111142077, + "grad_norm": 0.6000750660896301, + "learning_rate": 3.3315999009231324e-08, + "loss": 1.7003, + "step": 17740 + }, + { + "epoch": 0.9888523493673709, + "grad_norm": 0.5382059812545776, + "learning_rate": 3.299179330115143e-08, + "loss": 1.5417, + "step": 17741 + }, + { + "epoch": 0.988908087620534, + "grad_norm": 0.5685963034629822, + "learning_rate": 3.266917225524524e-08, + "loss": 1.8359, + "step": 17742 + }, + { + "epoch": 0.9889638258736971, + "grad_norm": 0.5986034870147705, + "learning_rate": 3.234813588174346e-08, + "loss": 1.7218, + "step": 17743 + }, + { + "epoch": 0.9890195641268603, + "grad_norm": 0.581881046295166, + "learning_rate": 3.202868419082683e-08, + "loss": 1.8224, + "step": 17744 + }, + { + "epoch": 0.9890753023800234, + "grad_norm": 0.5866140127182007, + "learning_rate": 3.1710817192631693e-08, + "loss": 2.0053, + "step": 17745 + }, + { + "epoch": 0.9891310406331866, + "grad_norm": 0.5924258232116699, + "learning_rate": 3.139453489722777e-08, + "loss": 1.4328, + "step": 17746 + }, + { + "epoch": 0.9891867788863496, + "grad_norm": 0.6319179534912109, + "learning_rate": 3.1079837314657025e-08, + "loss": 1.8279, + "step": 17747 + }, + { + "epoch": 0.9892425171395128, + "grad_norm": 0.5618653893470764, + "learning_rate": 3.076672445488926e-08, + "loss": 1.6699, + "step": 17748 + }, + { + "epoch": 0.989298255392676, + "grad_norm": 0.5731929540634155, + "learning_rate": 3.045519632786653e-08, + "loss": 1.4811, + "step": 17749 + }, + { + "epoch": 0.9893539936458391, + "grad_norm": 0.5121474862098694, + "learning_rate": 3.014525294345871e-08, + "loss": 1.2753, + "step": 17750 + }, + { + "epoch": 0.9894097318990023, + "grad_norm": 0.5540692210197449, + "learning_rate": 2.983689431149683e-08, + "loss": 1.6277, + "step": 17751 + }, + { + "epoch": 0.9894654701521655, + "grad_norm": 0.6145097613334656, + "learning_rate": 2.9530120441761956e-08, + "loss": 1.5578, + "step": 17752 + }, + { + "epoch": 0.9895212084053285, + "grad_norm": 0.5538742542266846, + "learning_rate": 2.9224931343990737e-08, + "loss": 1.4695, + "step": 17753 + }, + { + "epoch": 0.9895769466584917, + "grad_norm": 0.590013325214386, + "learning_rate": 2.8921327027847667e-08, + "loss": 1.9163, + "step": 17754 + }, + { + "epoch": 0.9896326849116549, + "grad_norm": 0.5824711322784424, + "learning_rate": 2.8619307502975035e-08, + "loss": 1.5151, + "step": 17755 + }, + { + "epoch": 0.989688423164818, + "grad_norm": 0.5580297708511353, + "learning_rate": 2.831887277893741e-08, + "loss": 1.7624, + "step": 17756 + }, + { + "epoch": 0.9897441614179812, + "grad_norm": 0.5867076516151428, + "learning_rate": 2.8020022865277163e-08, + "loss": 1.6216, + "step": 17757 + }, + { + "epoch": 0.9897998996711443, + "grad_norm": 0.5542786121368408, + "learning_rate": 2.7722757771458942e-08, + "loss": 1.7067, + "step": 17758 + }, + { + "epoch": 0.9898556379243074, + "grad_norm": 0.577502429485321, + "learning_rate": 2.7427077506919642e-08, + "loss": 1.6443, + "step": 17759 + }, + { + "epoch": 0.9899113761774706, + "grad_norm": 0.5390874743461609, + "learning_rate": 2.7132982081029544e-08, + "loss": 1.6573, + "step": 17760 + }, + { + "epoch": 0.9899671144306338, + "grad_norm": 0.6351310014724731, + "learning_rate": 2.684047150312563e-08, + "loss": 1.8253, + "step": 17761 + }, + { + "epoch": 0.9900228526837969, + "grad_norm": 0.5603695511817932, + "learning_rate": 2.6549545782472708e-08, + "loss": 1.581, + "step": 17762 + }, + { + "epoch": 0.99007859093696, + "grad_norm": 0.5148984789848328, + "learning_rate": 2.6260204928302278e-08, + "loss": 1.7049, + "step": 17763 + }, + { + "epoch": 0.9901343291901232, + "grad_norm": 0.5745189785957336, + "learning_rate": 2.597244894979589e-08, + "loss": 1.6109, + "step": 17764 + }, + { + "epoch": 0.9901900674432863, + "grad_norm": 0.592917799949646, + "learning_rate": 2.5686277856074026e-08, + "loss": 1.6352, + "step": 17765 + }, + { + "epoch": 0.9902458056964495, + "grad_norm": 0.5276328921318054, + "learning_rate": 2.5401691656207206e-08, + "loss": 1.4389, + "step": 17766 + }, + { + "epoch": 0.9903015439496127, + "grad_norm": 0.5520426034927368, + "learning_rate": 2.5118690359232644e-08, + "loss": 1.8776, + "step": 17767 + }, + { + "epoch": 0.9903572822027757, + "grad_norm": 0.5455012917518616, + "learning_rate": 2.4837273974115395e-08, + "loss": 1.6979, + "step": 17768 + }, + { + "epoch": 0.9904130204559389, + "grad_norm": 0.5926978588104248, + "learning_rate": 2.4557442509787198e-08, + "loss": 1.6877, + "step": 17769 + }, + { + "epoch": 0.990468758709102, + "grad_norm": 0.6039942502975464, + "learning_rate": 2.427919597511874e-08, + "loss": 1.7037, + "step": 17770 + }, + { + "epoch": 0.9905244969622652, + "grad_norm": 0.5855873823165894, + "learning_rate": 2.4002534378936293e-08, + "loss": 1.7178, + "step": 17771 + }, + { + "epoch": 0.9905802352154284, + "grad_norm": 0.5336987972259521, + "learning_rate": 2.3727457730010616e-08, + "loss": 1.6152, + "step": 17772 + }, + { + "epoch": 0.9906359734685914, + "grad_norm": 0.5844517946243286, + "learning_rate": 2.3453966037068066e-08, + "loss": 1.7571, + "step": 17773 + }, + { + "epoch": 0.9906917117217546, + "grad_norm": 0.6293264031410217, + "learning_rate": 2.318205930878503e-08, + "loss": 1.9999, + "step": 17774 + }, + { + "epoch": 0.9907474499749178, + "grad_norm": 0.5782108902931213, + "learning_rate": 2.2911737553782398e-08, + "loss": 1.6135, + "step": 17775 + }, + { + "epoch": 0.9908031882280809, + "grad_norm": 0.5384835600852966, + "learning_rate": 2.2643000780631086e-08, + "loss": 1.5198, + "step": 17776 + }, + { + "epoch": 0.9908589264812441, + "grad_norm": 0.5698707699775696, + "learning_rate": 2.2375848997857608e-08, + "loss": 1.653, + "step": 17777 + }, + { + "epoch": 0.9909146647344073, + "grad_norm": 0.6240308284759521, + "learning_rate": 2.2110282213927413e-08, + "loss": 1.77, + "step": 17778 + }, + { + "epoch": 0.9909704029875703, + "grad_norm": 0.585132360458374, + "learning_rate": 2.1846300437272648e-08, + "loss": 1.5992, + "step": 17779 + }, + { + "epoch": 0.9910261412407335, + "grad_norm": 0.6754236817359924, + "learning_rate": 2.1583903676258842e-08, + "loss": 1.8138, + "step": 17780 + }, + { + "epoch": 0.9910818794938967, + "grad_norm": 0.5370476245880127, + "learning_rate": 2.132309193921267e-08, + "loss": 1.4731, + "step": 17781 + }, + { + "epoch": 0.9911376177470598, + "grad_norm": 0.5317405462265015, + "learning_rate": 2.1063865234399738e-08, + "loss": 1.4826, + "step": 17782 + }, + { + "epoch": 0.991193356000223, + "grad_norm": 0.562485933303833, + "learning_rate": 2.080622357004125e-08, + "loss": 1.5009, + "step": 17783 + }, + { + "epoch": 0.9912490942533861, + "grad_norm": 0.5830033421516418, + "learning_rate": 2.0550166954308448e-08, + "loss": 1.6499, + "step": 17784 + }, + { + "epoch": 0.9913048325065492, + "grad_norm": 0.6019043922424316, + "learning_rate": 2.0295695395328164e-08, + "loss": 1.608, + "step": 17785 + }, + { + "epoch": 0.9913605707597124, + "grad_norm": 0.5869892835617065, + "learning_rate": 2.0042808901166166e-08, + "loss": 1.7485, + "step": 17786 + }, + { + "epoch": 0.9914163090128756, + "grad_norm": 0.5672516822814941, + "learning_rate": 1.979150747984382e-08, + "loss": 1.6374, + "step": 17787 + }, + { + "epoch": 0.9914720472660387, + "grad_norm": 0.5829968452453613, + "learning_rate": 1.954179113932697e-08, + "loss": 1.6544, + "step": 17788 + }, + { + "epoch": 0.9915277855192018, + "grad_norm": 0.5749821066856384, + "learning_rate": 1.9293659887542613e-08, + "loss": 1.7181, + "step": 17789 + }, + { + "epoch": 0.991583523772365, + "grad_norm": 0.5573068857192993, + "learning_rate": 1.904711373235113e-08, + "loss": 1.6068, + "step": 17790 + }, + { + "epoch": 0.9916392620255281, + "grad_norm": 0.5727934837341309, + "learning_rate": 1.8802152681579587e-08, + "loss": 1.6995, + "step": 17791 + }, + { + "epoch": 0.9916950002786913, + "grad_norm": 0.53313148021698, + "learning_rate": 1.8558776742988448e-08, + "loss": 1.3236, + "step": 17792 + }, + { + "epoch": 0.9917507385318544, + "grad_norm": 0.6228346228599548, + "learning_rate": 1.8316985924304864e-08, + "loss": 1.7792, + "step": 17793 + }, + { + "epoch": 0.9918064767850175, + "grad_norm": 0.5533289313316345, + "learning_rate": 1.8076780233194923e-08, + "loss": 1.6207, + "step": 17794 + }, + { + "epoch": 0.9918622150381807, + "grad_norm": 0.5599698424339294, + "learning_rate": 1.7838159677269206e-08, + "loss": 1.6762, + "step": 17795 + }, + { + "epoch": 0.9919179532913438, + "grad_norm": 0.6013026237487793, + "learning_rate": 1.7601124264104985e-08, + "loss": 1.6446, + "step": 17796 + }, + { + "epoch": 0.991973691544507, + "grad_norm": 0.5470018982887268, + "learning_rate": 1.7365674001212918e-08, + "loss": 1.6751, + "step": 17797 + }, + { + "epoch": 0.9920294297976702, + "grad_norm": 0.540104329586029, + "learning_rate": 1.7131808896064805e-08, + "loss": 1.3628, + "step": 17798 + }, + { + "epoch": 0.9920851680508332, + "grad_norm": 0.5892403721809387, + "learning_rate": 1.6899528956071387e-08, + "loss": 1.7296, + "step": 17799 + }, + { + "epoch": 0.9921409063039964, + "grad_norm": 0.556348979473114, + "learning_rate": 1.6668834188610096e-08, + "loss": 1.5786, + "step": 17800 + }, + { + "epoch": 0.9921966445571596, + "grad_norm": 0.5606974363327026, + "learning_rate": 1.6439724600986196e-08, + "loss": 1.5854, + "step": 17801 + }, + { + "epoch": 0.9922523828103227, + "grad_norm": 0.5659820437431335, + "learning_rate": 1.62122002004661e-08, + "loss": 1.5773, + "step": 17802 + }, + { + "epoch": 0.9923081210634859, + "grad_norm": 0.6099393963813782, + "learning_rate": 1.5986260994277358e-08, + "loss": 1.7926, + "step": 17803 + }, + { + "epoch": 0.992363859316649, + "grad_norm": 0.6045954823493958, + "learning_rate": 1.5761906989569808e-08, + "loss": 1.7704, + "step": 17804 + }, + { + "epoch": 0.9924195975698121, + "grad_norm": 0.5326430797576904, + "learning_rate": 1.5539138193471082e-08, + "loss": 1.5083, + "step": 17805 + }, + { + "epoch": 0.9924753358229753, + "grad_norm": 0.5619720816612244, + "learning_rate": 1.5317954613042197e-08, + "loss": 1.6763, + "step": 17806 + }, + { + "epoch": 0.9925310740761385, + "grad_norm": 0.603206992149353, + "learning_rate": 1.509835625529421e-08, + "loss": 2.0011, + "step": 17807 + }, + { + "epoch": 0.9925868123293016, + "grad_norm": 0.5108258724212646, + "learning_rate": 1.4880343127193774e-08, + "loss": 1.2496, + "step": 17808 + }, + { + "epoch": 0.9926425505824648, + "grad_norm": 0.5849392414093018, + "learning_rate": 1.4663915235657577e-08, + "loss": 1.6381, + "step": 17809 + }, + { + "epoch": 0.9926982888356279, + "grad_norm": 0.5737783312797546, + "learning_rate": 1.4449072587546797e-08, + "loss": 1.7707, + "step": 17810 + }, + { + "epoch": 0.992754027088791, + "grad_norm": 0.5545682907104492, + "learning_rate": 1.4235815189672652e-08, + "loss": 1.7729, + "step": 17811 + }, + { + "epoch": 0.9928097653419542, + "grad_norm": 0.5413428544998169, + "learning_rate": 1.4024143048801952e-08, + "loss": 1.5435, + "step": 17812 + }, + { + "epoch": 0.9928655035951174, + "grad_norm": 0.5803634524345398, + "learning_rate": 1.3814056171651546e-08, + "loss": 1.6541, + "step": 17813 + }, + { + "epoch": 0.9929212418482805, + "grad_norm": 0.5304771065711975, + "learning_rate": 1.3605554564871669e-08, + "loss": 1.4937, + "step": 17814 + }, + { + "epoch": 0.9929769801014436, + "grad_norm": 0.5582455396652222, + "learning_rate": 1.3398638235090355e-08, + "loss": 1.5573, + "step": 17815 + }, + { + "epoch": 0.9930327183546067, + "grad_norm": 0.5911871194839478, + "learning_rate": 1.3193307188857917e-08, + "loss": 1.7921, + "step": 17816 + }, + { + "epoch": 0.9930884566077699, + "grad_norm": 0.5655099749565125, + "learning_rate": 1.2989561432691366e-08, + "loss": 1.6022, + "step": 17817 + }, + { + "epoch": 0.9931441948609331, + "grad_norm": 0.5436229109764099, + "learning_rate": 1.2787400973052199e-08, + "loss": 1.234, + "step": 17818 + }, + { + "epoch": 0.9931999331140962, + "grad_norm": 0.5562745928764343, + "learning_rate": 1.2586825816351954e-08, + "loss": 1.5633, + "step": 17819 + }, + { + "epoch": 0.9932556713672593, + "grad_norm": 0.5429986119270325, + "learning_rate": 1.238783596894666e-08, + "loss": 1.496, + "step": 17820 + }, + { + "epoch": 0.9933114096204225, + "grad_norm": 0.5741674304008484, + "learning_rate": 1.2190431437153483e-08, + "loss": 1.628, + "step": 17821 + }, + { + "epoch": 0.9933671478735856, + "grad_norm": 0.5536769032478333, + "learning_rate": 1.1994612227234081e-08, + "loss": 1.6507, + "step": 17822 + }, + { + "epoch": 0.9934228861267488, + "grad_norm": 0.5863866806030273, + "learning_rate": 1.1800378345389051e-08, + "loss": 1.8845, + "step": 17823 + }, + { + "epoch": 0.993478624379912, + "grad_norm": 0.5925377607345581, + "learning_rate": 1.1607729797791233e-08, + "loss": 1.7482, + "step": 17824 + }, + { + "epoch": 0.993534362633075, + "grad_norm": 0.5730286836624146, + "learning_rate": 1.1416666590535752e-08, + "loss": 1.6669, + "step": 17825 + }, + { + "epoch": 0.9935901008862382, + "grad_norm": 0.5881670713424683, + "learning_rate": 1.1227188729695525e-08, + "loss": 1.8451, + "step": 17826 + }, + { + "epoch": 0.9936458391394014, + "grad_norm": 0.5761116147041321, + "learning_rate": 1.1039296221276863e-08, + "loss": 1.8348, + "step": 17827 + }, + { + "epoch": 0.9937015773925645, + "grad_norm": 0.5753434896469116, + "learning_rate": 1.0852989071230557e-08, + "loss": 1.5636, + "step": 17828 + }, + { + "epoch": 0.9937573156457277, + "grad_norm": 0.584956705570221, + "learning_rate": 1.0668267285474099e-08, + "loss": 1.7154, + "step": 17829 + }, + { + "epoch": 0.9938130538988909, + "grad_norm": 0.5855661630630493, + "learning_rate": 1.0485130869858362e-08, + "loss": 1.6266, + "step": 17830 + }, + { + "epoch": 0.9938687921520539, + "grad_norm": 0.5252522230148315, + "learning_rate": 1.0303579830195364e-08, + "loss": 1.4427, + "step": 17831 + }, + { + "epoch": 0.9939245304052171, + "grad_norm": 0.548348605632782, + "learning_rate": 1.0123614172247164e-08, + "loss": 1.5355, + "step": 17832 + }, + { + "epoch": 0.9939802686583803, + "grad_norm": 0.5975556373596191, + "learning_rate": 9.945233901709206e-09, + "loss": 1.7237, + "step": 17833 + }, + { + "epoch": 0.9940360069115434, + "grad_norm": 0.558417558670044, + "learning_rate": 9.768439024254727e-09, + "loss": 1.636, + "step": 17834 + }, + { + "epoch": 0.9940917451647066, + "grad_norm": 0.5559073686599731, + "learning_rate": 9.593229545473704e-09, + "loss": 1.624, + "step": 17835 + }, + { + "epoch": 0.9941474834178697, + "grad_norm": 0.5781221985816956, + "learning_rate": 9.419605470939452e-09, + "loss": 1.7618, + "step": 17836 + }, + { + "epoch": 0.9942032216710328, + "grad_norm": 0.5527158975601196, + "learning_rate": 9.247566806147579e-09, + "loss": 1.6754, + "step": 17837 + }, + { + "epoch": 0.994258959924196, + "grad_norm": 0.5695816278457642, + "learning_rate": 9.077113556554829e-09, + "loss": 1.5919, + "step": 17838 + }, + { + "epoch": 0.9943146981773591, + "grad_norm": 0.5489197373390198, + "learning_rate": 8.908245727567988e-09, + "loss": 1.6583, + "step": 17839 + }, + { + "epoch": 0.9943704364305223, + "grad_norm": 0.6120737791061401, + "learning_rate": 8.740963324543883e-09, + "loss": 1.906, + "step": 17840 + }, + { + "epoch": 0.9944261746836854, + "grad_norm": 0.5744720101356506, + "learning_rate": 8.575266352789379e-09, + "loss": 1.6375, + "step": 17841 + }, + { + "epoch": 0.9944819129368485, + "grad_norm": 0.5566824078559875, + "learning_rate": 8.411154817550283e-09, + "loss": 1.6561, + "step": 17842 + }, + { + "epoch": 0.9945376511900117, + "grad_norm": 0.6282997131347656, + "learning_rate": 8.248628724044637e-09, + "loss": 1.7869, + "step": 17843 + }, + { + "epoch": 0.9945933894431749, + "grad_norm": 0.5376906991004944, + "learning_rate": 8.087688077418332e-09, + "loss": 1.5893, + "step": 17844 + }, + { + "epoch": 0.994649127696338, + "grad_norm": 0.5853403210639954, + "learning_rate": 7.92833288277839e-09, + "loss": 1.629, + "step": 17845 + }, + { + "epoch": 0.9947048659495011, + "grad_norm": 0.5313374400138855, + "learning_rate": 7.770563145181874e-09, + "loss": 1.66, + "step": 17846 + }, + { + "epoch": 0.9947606042026643, + "grad_norm": 0.5778084397315979, + "learning_rate": 7.614378869619244e-09, + "loss": 1.6057, + "step": 17847 + }, + { + "epoch": 0.9948163424558274, + "grad_norm": 0.6288685202598572, + "learning_rate": 7.45978006105874e-09, + "loss": 1.7555, + "step": 17848 + }, + { + "epoch": 0.9948720807089906, + "grad_norm": 0.5758605599403381, + "learning_rate": 7.306766724396452e-09, + "loss": 1.3339, + "step": 17849 + }, + { + "epoch": 0.9949278189621538, + "grad_norm": 0.6046236753463745, + "learning_rate": 7.1553388644840515e-09, + "loss": 1.7004, + "step": 17850 + }, + { + "epoch": 0.9949835572153168, + "grad_norm": 0.5758521556854248, + "learning_rate": 7.005496486128804e-09, + "loss": 1.571, + "step": 17851 + }, + { + "epoch": 0.99503929546848, + "grad_norm": 0.5523056387901306, + "learning_rate": 6.857239594076914e-09, + "loss": 1.6759, + "step": 17852 + }, + { + "epoch": 0.9950950337216432, + "grad_norm": 0.5698785185813904, + "learning_rate": 6.710568193035727e-09, + "loss": 1.7104, + "step": 17853 + }, + { + "epoch": 0.9951507719748063, + "grad_norm": 0.5591890811920166, + "learning_rate": 6.5654822876515255e-09, + "loss": 1.7512, + "step": 17854 + }, + { + "epoch": 0.9952065102279695, + "grad_norm": 0.579388439655304, + "learning_rate": 6.421981882531736e-09, + "loss": 1.7223, + "step": 17855 + }, + { + "epoch": 0.9952622484811326, + "grad_norm": 0.5567805767059326, + "learning_rate": 6.280066982222721e-09, + "loss": 1.7547, + "step": 17856 + }, + { + "epoch": 0.9953179867342957, + "grad_norm": 0.5671547651290894, + "learning_rate": 6.139737591226436e-09, + "loss": 1.4622, + "step": 17857 + }, + { + "epoch": 0.9953737249874589, + "grad_norm": 0.5701755881309509, + "learning_rate": 6.000993713989322e-09, + "loss": 1.7235, + "step": 17858 + }, + { + "epoch": 0.9954294632406221, + "grad_norm": 0.5654506087303162, + "learning_rate": 5.863835354918967e-09, + "loss": 1.7357, + "step": 17859 + }, + { + "epoch": 0.9954852014937852, + "grad_norm": 0.5632920265197754, + "learning_rate": 5.7282625183618936e-09, + "loss": 1.4926, + "step": 17860 + }, + { + "epoch": 0.9955409397469484, + "grad_norm": 0.5621775388717651, + "learning_rate": 5.594275208614663e-09, + "loss": 1.8364, + "step": 17861 + }, + { + "epoch": 0.9955966780001114, + "grad_norm": 0.5905541181564331, + "learning_rate": 5.461873429929432e-09, + "loss": 1.6545, + "step": 17862 + }, + { + "epoch": 0.9956524162532746, + "grad_norm": 0.570364236831665, + "learning_rate": 5.331057186508392e-09, + "loss": 1.8837, + "step": 17863 + }, + { + "epoch": 0.9957081545064378, + "grad_norm": 0.5538524389266968, + "learning_rate": 5.201826482498229e-09, + "loss": 1.6242, + "step": 17864 + }, + { + "epoch": 0.9957638927596009, + "grad_norm": 0.6024903655052185, + "learning_rate": 5.0741813219956634e-09, + "loss": 1.6272, + "step": 17865 + }, + { + "epoch": 0.995819631012764, + "grad_norm": 0.5529265403747559, + "learning_rate": 4.94812170904746e-09, + "loss": 1.656, + "step": 17866 + }, + { + "epoch": 0.9958753692659272, + "grad_norm": 0.5587241053581238, + "learning_rate": 4.82364764765042e-09, + "loss": 1.6829, + "step": 17867 + }, + { + "epoch": 0.9959311075190903, + "grad_norm": 0.6123833060264587, + "learning_rate": 4.700759141756939e-09, + "loss": 1.8201, + "step": 17868 + }, + { + "epoch": 0.9959868457722535, + "grad_norm": 0.5877248048782349, + "learning_rate": 4.579456195269449e-09, + "loss": 1.9657, + "step": 17869 + }, + { + "epoch": 0.9960425840254167, + "grad_norm": 0.6264537572860718, + "learning_rate": 4.4597388120182215e-09, + "loss": 1.8972, + "step": 17870 + }, + { + "epoch": 0.9960983222785798, + "grad_norm": 0.5811901688575745, + "learning_rate": 4.341606995816871e-09, + "loss": 1.5479, + "step": 17871 + }, + { + "epoch": 0.9961540605317429, + "grad_norm": 0.5497073531150818, + "learning_rate": 4.225060750401299e-09, + "loss": 1.6797, + "step": 17872 + }, + { + "epoch": 0.9962097987849061, + "grad_norm": 0.5911428332328796, + "learning_rate": 4.110100079474099e-09, + "loss": 1.658, + "step": 17873 + }, + { + "epoch": 0.9962655370380692, + "grad_norm": 0.5555235743522644, + "learning_rate": 3.996724986676803e-09, + "loss": 1.6017, + "step": 17874 + }, + { + "epoch": 0.9963212752912324, + "grad_norm": 0.5350549221038818, + "learning_rate": 3.884935475606533e-09, + "loss": 1.5619, + "step": 17875 + }, + { + "epoch": 0.9963770135443956, + "grad_norm": 0.5625602602958679, + "learning_rate": 3.7747315498049e-09, + "loss": 1.633, + "step": 17876 + }, + { + "epoch": 0.9964327517975586, + "grad_norm": 0.5179721713066101, + "learning_rate": 3.6661132127746577e-09, + "loss": 1.3805, + "step": 17877 + }, + { + "epoch": 0.9964884900507218, + "grad_norm": 0.518448531627655, + "learning_rate": 3.5590804679574986e-09, + "loss": 1.5279, + "step": 17878 + }, + { + "epoch": 0.996544228303885, + "grad_norm": 0.5527274012565613, + "learning_rate": 3.453633318745153e-09, + "loss": 1.6911, + "step": 17879 + }, + { + "epoch": 0.9965999665570481, + "grad_norm": 0.515629768371582, + "learning_rate": 3.349771768479393e-09, + "loss": 1.522, + "step": 17880 + }, + { + "epoch": 0.9966557048102113, + "grad_norm": 0.5573046803474426, + "learning_rate": 3.247495820463131e-09, + "loss": 1.7007, + "step": 17881 + }, + { + "epoch": 0.9967114430633744, + "grad_norm": 0.5546225309371948, + "learning_rate": 3.1468054779326684e-09, + "loss": 1.6738, + "step": 17882 + }, + { + "epoch": 0.9967671813165375, + "grad_norm": 0.6161512136459351, + "learning_rate": 3.0477007440854464e-09, + "loss": 1.7663, + "step": 17883 + }, + { + "epoch": 0.9968229195697007, + "grad_norm": 0.5987143516540527, + "learning_rate": 2.950181622063397e-09, + "loss": 1.6182, + "step": 17884 + }, + { + "epoch": 0.9968786578228638, + "grad_norm": 0.5967904329299927, + "learning_rate": 2.854248114958491e-09, + "loss": 1.4883, + "step": 17885 + }, + { + "epoch": 0.996934396076027, + "grad_norm": 0.5350334644317627, + "learning_rate": 2.7599002258127393e-09, + "loss": 1.5116, + "step": 17886 + }, + { + "epoch": 0.9969901343291901, + "grad_norm": 0.575527012348175, + "learning_rate": 2.6671379576181934e-09, + "loss": 1.7701, + "step": 17887 + }, + { + "epoch": 0.9970458725823532, + "grad_norm": 0.595644474029541, + "learning_rate": 2.5759613133169435e-09, + "loss": 1.758, + "step": 17888 + }, + { + "epoch": 0.9971016108355164, + "grad_norm": 0.5721838474273682, + "learning_rate": 2.4863702958011213e-09, + "loss": 1.4548, + "step": 17889 + }, + { + "epoch": 0.9971573490886796, + "grad_norm": 0.5691001415252686, + "learning_rate": 2.3983649079128977e-09, + "loss": 1.7625, + "step": 17890 + }, + { + "epoch": 0.9972130873418427, + "grad_norm": 0.5790197253227234, + "learning_rate": 2.3119451524389323e-09, + "loss": 1.7275, + "step": 17891 + }, + { + "epoch": 0.9972688255950058, + "grad_norm": 0.5473052263259888, + "learning_rate": 2.227111032127027e-09, + "loss": 1.5049, + "step": 17892 + }, + { + "epoch": 0.997324563848169, + "grad_norm": 0.5797288417816162, + "learning_rate": 2.143862549663922e-09, + "loss": 1.78, + "step": 17893 + }, + { + "epoch": 0.9973803021013321, + "grad_norm": 0.5797807574272156, + "learning_rate": 2.0621997076863964e-09, + "loss": 1.7308, + "step": 17894 + }, + { + "epoch": 0.9974360403544953, + "grad_norm": 0.5804511308670044, + "learning_rate": 1.982122508792372e-09, + "loss": 1.5949, + "step": 17895 + }, + { + "epoch": 0.9974917786076585, + "grad_norm": 0.5463127493858337, + "learning_rate": 1.9036309555131582e-09, + "loss": 1.6167, + "step": 17896 + }, + { + "epoch": 0.9975475168608215, + "grad_norm": 0.5459886789321899, + "learning_rate": 1.8267250503412048e-09, + "loss": 1.6487, + "step": 17897 + }, + { + "epoch": 0.9976032551139847, + "grad_norm": 0.5647213459014893, + "learning_rate": 1.7514047957190027e-09, + "loss": 1.7007, + "step": 17898 + }, + { + "epoch": 0.9976589933671479, + "grad_norm": 0.5954081416130066, + "learning_rate": 1.6776701940335315e-09, + "loss": 1.8813, + "step": 17899 + }, + { + "epoch": 0.997714731620311, + "grad_norm": 0.5660445690155029, + "learning_rate": 1.6055212476162595e-09, + "loss": 1.4914, + "step": 17900 + }, + { + "epoch": 0.9977704698734742, + "grad_norm": 0.5751714110374451, + "learning_rate": 1.5349579587653484e-09, + "loss": 1.7087, + "step": 17901 + }, + { + "epoch": 0.9978262081266374, + "grad_norm": 0.5353075265884399, + "learning_rate": 1.4659803297123465e-09, + "loss": 1.6502, + "step": 17902 + }, + { + "epoch": 0.9978819463798004, + "grad_norm": 0.5637602210044861, + "learning_rate": 1.398588362649944e-09, + "loss": 1.693, + "step": 17903 + }, + { + "epoch": 0.9979376846329636, + "grad_norm": 0.5660296678543091, + "learning_rate": 1.3327820597097695e-09, + "loss": 1.7254, + "step": 17904 + }, + { + "epoch": 0.9979934228861268, + "grad_norm": 0.5764157772064209, + "learning_rate": 1.268561422979042e-09, + "loss": 1.8097, + "step": 17905 + }, + { + "epoch": 0.9980491611392899, + "grad_norm": 0.5623731017112732, + "learning_rate": 1.2059264545005721e-09, + "loss": 1.5276, + "step": 17906 + }, + { + "epoch": 0.9981048993924531, + "grad_norm": 0.5733487606048584, + "learning_rate": 1.1448771562561078e-09, + "loss": 1.5952, + "step": 17907 + }, + { + "epoch": 0.9981606376456161, + "grad_norm": 0.5872202515602112, + "learning_rate": 1.0854135301774372e-09, + "loss": 1.7756, + "step": 17908 + }, + { + "epoch": 0.9982163758987793, + "grad_norm": 0.5693990588188171, + "learning_rate": 1.0275355781630415e-09, + "loss": 1.6389, + "step": 17909 + }, + { + "epoch": 0.9982721141519425, + "grad_norm": 0.5961620211601257, + "learning_rate": 9.712433020392375e-10, + "loss": 1.6831, + "step": 17910 + }, + { + "epoch": 0.9983278524051056, + "grad_norm": 0.5362070202827454, + "learning_rate": 9.165367035879335e-10, + "loss": 1.5888, + "step": 17911 + }, + { + "epoch": 0.9983835906582688, + "grad_norm": 0.5927963852882385, + "learning_rate": 8.634157845521796e-10, + "loss": 1.701, + "step": 17912 + }, + { + "epoch": 0.998439328911432, + "grad_norm": 0.5628186464309692, + "learning_rate": 8.118805466139634e-10, + "loss": 1.4631, + "step": 17913 + }, + { + "epoch": 0.998495067164595, + "grad_norm": 0.5345197319984436, + "learning_rate": 7.619309914108641e-10, + "loss": 1.6177, + "step": 17914 + }, + { + "epoch": 0.9985508054177582, + "grad_norm": 0.5351245999336243, + "learning_rate": 7.135671205193983e-10, + "loss": 1.5327, + "step": 17915 + }, + { + "epoch": 0.9986065436709214, + "grad_norm": 0.5982441306114197, + "learning_rate": 6.667889354772249e-10, + "loss": 1.7842, + "step": 17916 + }, + { + "epoch": 0.9986622819240845, + "grad_norm": 0.5954335927963257, + "learning_rate": 6.215964377720429e-10, + "loss": 1.8974, + "step": 17917 + }, + { + "epoch": 0.9987180201772476, + "grad_norm": 0.5718487501144409, + "learning_rate": 5.779896288304887e-10, + "loss": 1.7538, + "step": 17918 + }, + { + "epoch": 0.9987737584304108, + "grad_norm": 0.6256338357925415, + "learning_rate": 5.359685100403411e-10, + "loss": 1.6867, + "step": 17919 + }, + { + "epoch": 0.9988294966835739, + "grad_norm": 0.578621506690979, + "learning_rate": 4.955330827283167e-10, + "loss": 1.5661, + "step": 17920 + }, + { + "epoch": 0.9988852349367371, + "grad_norm": 0.5479393005371094, + "learning_rate": 4.566833481822741e-10, + "loss": 1.5337, + "step": 17921 + }, + { + "epoch": 0.9989409731899003, + "grad_norm": 0.5969484448432922, + "learning_rate": 4.1941930763456094e-10, + "loss": 1.6745, + "step": 17922 + }, + { + "epoch": 0.9989967114430633, + "grad_norm": 0.5723933577537537, + "learning_rate": 3.8374096226201363e-10, + "loss": 1.6886, + "step": 17923 + }, + { + "epoch": 0.9990524496962265, + "grad_norm": 0.6094542145729065, + "learning_rate": 3.4964831320261074e-10, + "loss": 1.7712, + "step": 17924 + }, + { + "epoch": 0.9991081879493897, + "grad_norm": 0.5740577578544617, + "learning_rate": 3.1714136153326856e-10, + "loss": 1.7366, + "step": 17925 + }, + { + "epoch": 0.9991639262025528, + "grad_norm": 0.5772085189819336, + "learning_rate": 2.8622010828094347e-10, + "loss": 1.6816, + "step": 17926 + }, + { + "epoch": 0.999219664455716, + "grad_norm": 0.5197486281394958, + "learning_rate": 2.5688455443928504e-10, + "loss": 1.4507, + "step": 17927 + }, + { + "epoch": 0.9992754027088792, + "grad_norm": 0.5529182553291321, + "learning_rate": 2.291347009242273e-10, + "loss": 1.5333, + "step": 17928 + }, + { + "epoch": 0.9993311409620422, + "grad_norm": 0.6028139591217041, + "learning_rate": 2.029705486239486e-10, + "loss": 1.6289, + "step": 17929 + }, + { + "epoch": 0.9993868792152054, + "grad_norm": 0.5496512055397034, + "learning_rate": 1.7839209836556513e-10, + "loss": 1.5401, + "step": 17930 + }, + { + "epoch": 0.9994426174683685, + "grad_norm": 0.5949000120162964, + "learning_rate": 1.5539935093178414e-10, + "loss": 1.6467, + "step": 17931 + }, + { + "epoch": 0.9994983557215317, + "grad_norm": 0.5672999620437622, + "learning_rate": 1.339923070498017e-10, + "loss": 1.7435, + "step": 17932 + }, + { + "epoch": 0.9995540939746949, + "grad_norm": 0.6153858304023743, + "learning_rate": 1.1417096739685385e-10, + "loss": 1.7012, + "step": 17933 + }, + { + "epoch": 0.9996098322278579, + "grad_norm": 0.6022427082061768, + "learning_rate": 9.593533260021659e-11, + "loss": 1.7907, + "step": 17934 + }, + { + "epoch": 0.9996655704810211, + "grad_norm": 0.5764996409416199, + "learning_rate": 7.928540324275702e-11, + "loss": 1.8255, + "step": 17935 + }, + { + "epoch": 0.9997213087341843, + "grad_norm": 0.517230749130249, + "learning_rate": 6.422117985183107e-11, + "loss": 1.5038, + "step": 17936 + }, + { + "epoch": 0.9997770469873474, + "grad_norm": 0.5824159979820251, + "learning_rate": 5.074266290483465e-11, + "loss": 1.6391, + "step": 17937 + }, + { + "epoch": 0.9998327852405106, + "grad_norm": 0.5506365895271301, + "learning_rate": 3.88498528236525e-11, + "loss": 1.5529, + "step": 17938 + }, + { + "epoch": 0.9998885234936737, + "grad_norm": 0.5669583082199097, + "learning_rate": 2.8542749996862682e-11, + "loss": 1.6723, + "step": 17939 + }, + { + "epoch": 0.9999442617468368, + "grad_norm": 0.540381133556366, + "learning_rate": 1.982135474087876e-11, + "loss": 1.5116, + "step": 17940 + }, + { + "epoch": 1.0, + "grad_norm": 0.5757983922958374, + "learning_rate": 1.268566733325649e-11, + "loss": 1.6776, + "step": 17941 + } + ], + "logging_steps": 1, + "max_steps": 17941, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 3000, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 1.3384173522285232e+19, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +}