{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.4692168111585623, "eval_steps": 500, "global_step": 2000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00023460840557928115, "grad_norm": 431.5833740234375, "learning_rate": 2.0000000000000002e-07, "loss": 124.3048, "step": 1 }, { "epoch": 0.0004692168111585623, "grad_norm": 282.8776550292969, "learning_rate": 4.0000000000000003e-07, "loss": 121.2244, "step": 2 }, { "epoch": 0.0007038252167378434, "grad_norm": 292.6915283203125, "learning_rate": 6.000000000000001e-07, "loss": 115.3186, "step": 3 }, { "epoch": 0.0009384336223171246, "grad_norm": 256.6849670410156, "learning_rate": 8.000000000000001e-07, "loss": 113.7643, "step": 4 }, { "epoch": 0.0011730420278964057, "grad_norm": 331.59332275390625, "learning_rate": 1.0000000000000002e-06, "loss": 116.3841, "step": 5 }, { "epoch": 0.0014076504334756869, "grad_norm": 247.94737243652344, "learning_rate": 1.2000000000000002e-06, "loss": 109.4528, "step": 6 }, { "epoch": 0.001642258839054968, "grad_norm": 199.04579162597656, "learning_rate": 1.4000000000000001e-06, "loss": 103.2719, "step": 7 }, { "epoch": 0.0018768672446342492, "grad_norm": 249.46322631835938, "learning_rate": 1.6000000000000001e-06, "loss": 103.01, "step": 8 }, { "epoch": 0.0021114756502135304, "grad_norm": 194.32594299316406, "learning_rate": 1.8000000000000001e-06, "loss": 106.7548, "step": 9 }, { "epoch": 0.0023460840557928114, "grad_norm": 159.8208465576172, "learning_rate": 2.0000000000000003e-06, "loss": 94.539, "step": 10 }, { "epoch": 0.0025806924613720928, "grad_norm": 182.28439331054688, "learning_rate": 2.2e-06, "loss": 94.0353, "step": 11 }, { "epoch": 0.0028153008669513737, "grad_norm": 171.6542510986328, "learning_rate": 2.4000000000000003e-06, "loss": 91.4333, "step": 12 }, { "epoch": 0.0030499092725306547, "grad_norm": 162.0957489013672, "learning_rate": 2.6e-06, "loss": 88.0559, "step": 13 }, { "epoch": 0.003284517678109936, "grad_norm": 152.9030303955078, "learning_rate": 2.8000000000000003e-06, "loss": 82.9844, "step": 14 }, { "epoch": 0.003519126083689217, "grad_norm": 125.12821960449219, "learning_rate": 3e-06, "loss": 80.2571, "step": 15 }, { "epoch": 0.0037537344892684984, "grad_norm": 145.99269104003906, "learning_rate": 3.2000000000000003e-06, "loss": 69.783, "step": 16 }, { "epoch": 0.00398834289484778, "grad_norm": 132.161376953125, "learning_rate": 3.4000000000000005e-06, "loss": 68.5376, "step": 17 }, { "epoch": 0.004222951300427061, "grad_norm": 99.72203826904297, "learning_rate": 3.6000000000000003e-06, "loss": 69.3079, "step": 18 }, { "epoch": 0.004457559706006342, "grad_norm": 79.85321044921875, "learning_rate": 3.8000000000000005e-06, "loss": 67.0159, "step": 19 }, { "epoch": 0.004692168111585623, "grad_norm": 77.0258560180664, "learning_rate": 4.000000000000001e-06, "loss": 65.0106, "step": 20 }, { "epoch": 0.004926776517164904, "grad_norm": 73.0287857055664, "learning_rate": 4.2000000000000004e-06, "loss": 64.003, "step": 21 }, { "epoch": 0.0051613849227441855, "grad_norm": 71.51332092285156, "learning_rate": 4.4e-06, "loss": 62.4569, "step": 22 }, { "epoch": 0.0053959933283234665, "grad_norm": 71.87979888916016, "learning_rate": 4.600000000000001e-06, "loss": 58.1717, "step": 23 }, { "epoch": 0.0056306017339027474, "grad_norm": 65.9795913696289, "learning_rate": 4.800000000000001e-06, "loss": 57.3664, "step": 24 }, { "epoch": 0.005865210139482028, "grad_norm": 78.07582092285156, "learning_rate": 5e-06, "loss": 52.3587, "step": 25 }, { "epoch": 0.006099818545061309, "grad_norm": 66.0897445678711, "learning_rate": 5.2e-06, "loss": 48.1227, "step": 26 }, { "epoch": 0.006334426950640591, "grad_norm": 54.82024002075195, "learning_rate": 5.400000000000001e-06, "loss": 46.8902, "step": 27 }, { "epoch": 0.006569035356219872, "grad_norm": 60.46261215209961, "learning_rate": 5.600000000000001e-06, "loss": 47.4436, "step": 28 }, { "epoch": 0.006803643761799153, "grad_norm": 53.08403015136719, "learning_rate": 5.8e-06, "loss": 48.9657, "step": 29 }, { "epoch": 0.007038252167378434, "grad_norm": 48.10612106323242, "learning_rate": 6e-06, "loss": 39.3696, "step": 30 }, { "epoch": 0.007272860572957716, "grad_norm": 41.34337615966797, "learning_rate": 6.200000000000001e-06, "loss": 41.0922, "step": 31 }, { "epoch": 0.007507468978536997, "grad_norm": 49.449913024902344, "learning_rate": 6.4000000000000006e-06, "loss": 53.5898, "step": 32 }, { "epoch": 0.007742077384116278, "grad_norm": 39.08639907836914, "learning_rate": 6.600000000000001e-06, "loss": 46.6142, "step": 33 }, { "epoch": 0.00797668578969556, "grad_norm": 46.23830795288086, "learning_rate": 6.800000000000001e-06, "loss": 54.7222, "step": 34 }, { "epoch": 0.00821129419527484, "grad_norm": 36.233154296875, "learning_rate": 7e-06, "loss": 43.2474, "step": 35 }, { "epoch": 0.008445902600854122, "grad_norm": 42.450660705566406, "learning_rate": 7.2000000000000005e-06, "loss": 40.097, "step": 36 }, { "epoch": 0.008680511006433403, "grad_norm": 43.54088592529297, "learning_rate": 7.4e-06, "loss": 41.2942, "step": 37 }, { "epoch": 0.008915119412012684, "grad_norm": 32.71841812133789, "learning_rate": 7.600000000000001e-06, "loss": 41.1951, "step": 38 }, { "epoch": 0.009149727817591964, "grad_norm": 36.72887420654297, "learning_rate": 7.800000000000002e-06, "loss": 43.0731, "step": 39 }, { "epoch": 0.009384336223171245, "grad_norm": 36.14197540283203, "learning_rate": 8.000000000000001e-06, "loss": 41.3274, "step": 40 }, { "epoch": 0.009618944628750526, "grad_norm": 73.29031372070312, "learning_rate": 8.2e-06, "loss": 43.9427, "step": 41 }, { "epoch": 0.009853553034329807, "grad_norm": 32.026920318603516, "learning_rate": 8.400000000000001e-06, "loss": 40.3668, "step": 42 }, { "epoch": 0.01008816143990909, "grad_norm": 33.73833084106445, "learning_rate": 8.6e-06, "loss": 41.3271, "step": 43 }, { "epoch": 0.010322769845488371, "grad_norm": 29.402469635009766, "learning_rate": 8.8e-06, "loss": 40.8165, "step": 44 }, { "epoch": 0.010557378251067652, "grad_norm": 32.725196838378906, "learning_rate": 9e-06, "loss": 38.1721, "step": 45 }, { "epoch": 0.010791986656646933, "grad_norm": 33.787986755371094, "learning_rate": 9.200000000000002e-06, "loss": 37.2315, "step": 46 }, { "epoch": 0.011026595062226214, "grad_norm": 30.051118850708008, "learning_rate": 9.4e-06, "loss": 40.3238, "step": 47 }, { "epoch": 0.011261203467805495, "grad_norm": 28.415077209472656, "learning_rate": 9.600000000000001e-06, "loss": 41.63, "step": 48 }, { "epoch": 0.011495811873384776, "grad_norm": 32.38840866088867, "learning_rate": 9.800000000000001e-06, "loss": 39.8397, "step": 49 }, { "epoch": 0.011730420278964057, "grad_norm": 29.440380096435547, "learning_rate": 1e-05, "loss": 36.324, "step": 50 }, { "epoch": 0.011965028684543338, "grad_norm": 28.68352699279785, "learning_rate": 1.02e-05, "loss": 38.2148, "step": 51 }, { "epoch": 0.012199637090122619, "grad_norm": 35.46910095214844, "learning_rate": 1.04e-05, "loss": 38.938, "step": 52 }, { "epoch": 0.012434245495701901, "grad_norm": 33.725093841552734, "learning_rate": 1.0600000000000002e-05, "loss": 39.5148, "step": 53 }, { "epoch": 0.012668853901281182, "grad_norm": 31.119285583496094, "learning_rate": 1.0800000000000002e-05, "loss": 39.5953, "step": 54 }, { "epoch": 0.012903462306860463, "grad_norm": 28.087244033813477, "learning_rate": 1.1000000000000001e-05, "loss": 34.854, "step": 55 }, { "epoch": 0.013138070712439744, "grad_norm": 29.026432037353516, "learning_rate": 1.1200000000000001e-05, "loss": 37.7391, "step": 56 }, { "epoch": 0.013372679118019025, "grad_norm": 29.28595733642578, "learning_rate": 1.14e-05, "loss": 38.0498, "step": 57 }, { "epoch": 0.013607287523598306, "grad_norm": 29.428070068359375, "learning_rate": 1.16e-05, "loss": 35.6166, "step": 58 }, { "epoch": 0.013841895929177587, "grad_norm": 34.93647003173828, "learning_rate": 1.18e-05, "loss": 37.0957, "step": 59 }, { "epoch": 0.014076504334756868, "grad_norm": 29.80470848083496, "learning_rate": 1.2e-05, "loss": 35.4115, "step": 60 }, { "epoch": 0.014311112740336149, "grad_norm": 31.742000579833984, "learning_rate": 1.22e-05, "loss": 39.0862, "step": 61 }, { "epoch": 0.014545721145915432, "grad_norm": 25.870052337646484, "learning_rate": 1.2400000000000002e-05, "loss": 32.8247, "step": 62 }, { "epoch": 0.014780329551494713, "grad_norm": 42.16355514526367, "learning_rate": 1.2600000000000001e-05, "loss": 35.4496, "step": 63 }, { "epoch": 0.015014937957073994, "grad_norm": 26.663537979125977, "learning_rate": 1.2800000000000001e-05, "loss": 37.2332, "step": 64 }, { "epoch": 0.015249546362653275, "grad_norm": 29.479616165161133, "learning_rate": 1.3000000000000001e-05, "loss": 37.4796, "step": 65 }, { "epoch": 0.015484154768232556, "grad_norm": 25.485801696777344, "learning_rate": 1.3200000000000002e-05, "loss": 32.5173, "step": 66 }, { "epoch": 0.015718763173811837, "grad_norm": 31.429649353027344, "learning_rate": 1.3400000000000002e-05, "loss": 40.0257, "step": 67 }, { "epoch": 0.01595337157939112, "grad_norm": 28.891958236694336, "learning_rate": 1.3600000000000002e-05, "loss": 43.1546, "step": 68 }, { "epoch": 0.0161879799849704, "grad_norm": 33.310386657714844, "learning_rate": 1.38e-05, "loss": 40.948, "step": 69 }, { "epoch": 0.01642258839054968, "grad_norm": 29.357221603393555, "learning_rate": 1.4e-05, "loss": 34.4769, "step": 70 }, { "epoch": 0.01665719679612896, "grad_norm": 33.23200988769531, "learning_rate": 1.4200000000000001e-05, "loss": 31.9662, "step": 71 }, { "epoch": 0.016891805201708243, "grad_norm": 25.96340560913086, "learning_rate": 1.4400000000000001e-05, "loss": 36.3625, "step": 72 }, { "epoch": 0.017126413607287522, "grad_norm": 31.097774505615234, "learning_rate": 1.46e-05, "loss": 35.0645, "step": 73 }, { "epoch": 0.017361022012866805, "grad_norm": 26.863496780395508, "learning_rate": 1.48e-05, "loss": 37.4287, "step": 74 }, { "epoch": 0.017595630418446084, "grad_norm": 28.706714630126953, "learning_rate": 1.5000000000000002e-05, "loss": 38.8374, "step": 75 }, { "epoch": 0.017830238824025367, "grad_norm": 30.933870315551758, "learning_rate": 1.5200000000000002e-05, "loss": 33.0216, "step": 76 }, { "epoch": 0.01806484722960465, "grad_norm": 31.200035095214844, "learning_rate": 1.54e-05, "loss": 37.5167, "step": 77 }, { "epoch": 0.01829945563518393, "grad_norm": 29.05739402770996, "learning_rate": 1.5600000000000003e-05, "loss": 36.329, "step": 78 }, { "epoch": 0.01853406404076321, "grad_norm": 28.48918914794922, "learning_rate": 1.58e-05, "loss": 40.6949, "step": 79 }, { "epoch": 0.01876867244634249, "grad_norm": 26.435434341430664, "learning_rate": 1.6000000000000003e-05, "loss": 37.8908, "step": 80 }, { "epoch": 0.019003280851921774, "grad_norm": 29.344999313354492, "learning_rate": 1.62e-05, "loss": 36.2096, "step": 81 }, { "epoch": 0.019237889257501053, "grad_norm": 28.4927978515625, "learning_rate": 1.64e-05, "loss": 41.9787, "step": 82 }, { "epoch": 0.019472497663080336, "grad_norm": 23.641250610351562, "learning_rate": 1.66e-05, "loss": 32.8709, "step": 83 }, { "epoch": 0.019707106068659615, "grad_norm": 28.910215377807617, "learning_rate": 1.6800000000000002e-05, "loss": 38.1993, "step": 84 }, { "epoch": 0.019941714474238897, "grad_norm": 25.214174270629883, "learning_rate": 1.7e-05, "loss": 33.2894, "step": 85 }, { "epoch": 0.02017632287981818, "grad_norm": 25.31830406188965, "learning_rate": 1.72e-05, "loss": 36.75, "step": 86 }, { "epoch": 0.02041093128539746, "grad_norm": 24.473800659179688, "learning_rate": 1.7400000000000003e-05, "loss": 33.0156, "step": 87 }, { "epoch": 0.020645539690976742, "grad_norm": 28.74802589416504, "learning_rate": 1.76e-05, "loss": 38.3509, "step": 88 }, { "epoch": 0.02088014809655602, "grad_norm": 27.64483070373535, "learning_rate": 1.7800000000000002e-05, "loss": 37.7107, "step": 89 }, { "epoch": 0.021114756502135304, "grad_norm": 27.966651916503906, "learning_rate": 1.8e-05, "loss": 37.8556, "step": 90 }, { "epoch": 0.021349364907714583, "grad_norm": 27.339460372924805, "learning_rate": 1.8200000000000002e-05, "loss": 33.2062, "step": 91 }, { "epoch": 0.021583973313293866, "grad_norm": 28.445310592651367, "learning_rate": 1.8400000000000003e-05, "loss": 36.2557, "step": 92 }, { "epoch": 0.021818581718873145, "grad_norm": 24.461153030395508, "learning_rate": 1.86e-05, "loss": 34.8494, "step": 93 }, { "epoch": 0.022053190124452428, "grad_norm": 26.196924209594727, "learning_rate": 1.88e-05, "loss": 35.3077, "step": 94 }, { "epoch": 0.02228779853003171, "grad_norm": 27.065690994262695, "learning_rate": 1.9e-05, "loss": 38.7357, "step": 95 }, { "epoch": 0.02252240693561099, "grad_norm": 24.368877410888672, "learning_rate": 1.9200000000000003e-05, "loss": 31.7114, "step": 96 }, { "epoch": 0.022757015341190272, "grad_norm": 23.982168197631836, "learning_rate": 1.94e-05, "loss": 38.5708, "step": 97 }, { "epoch": 0.02299162374676955, "grad_norm": 27.92852210998535, "learning_rate": 1.9600000000000002e-05, "loss": 35.001, "step": 98 }, { "epoch": 0.023226232152348834, "grad_norm": 28.21087646484375, "learning_rate": 1.98e-05, "loss": 31.2187, "step": 99 }, { "epoch": 0.023460840557928114, "grad_norm": 24.320266723632812, "learning_rate": 2e-05, "loss": 30.0096, "step": 100 }, { "epoch": 0.023695448963507396, "grad_norm": 23.05602264404297, "learning_rate": 1.999999715117628e-05, "loss": 32.1651, "step": 101 }, { "epoch": 0.023930057369086676, "grad_norm": 21.590599060058594, "learning_rate": 1.9999988604706727e-05, "loss": 33.8256, "step": 102 }, { "epoch": 0.024164665774665958, "grad_norm": 28.801897048950195, "learning_rate": 1.9999974360596224e-05, "loss": 33.7847, "step": 103 }, { "epoch": 0.024399274180245237, "grad_norm": 26.88731575012207, "learning_rate": 1.999995441885288e-05, "loss": 37.6168, "step": 104 }, { "epoch": 0.02463388258582452, "grad_norm": 27.67681121826172, "learning_rate": 1.9999928779488054e-05, "loss": 29.9823, "step": 105 }, { "epoch": 0.024868490991403803, "grad_norm": 34.293155670166016, "learning_rate": 1.9999897442516364e-05, "loss": 36.3039, "step": 106 }, { "epoch": 0.025103099396983082, "grad_norm": 32.511898040771484, "learning_rate": 1.9999860407955657e-05, "loss": 37.1758, "step": 107 }, { "epoch": 0.025337707802562365, "grad_norm": 22.595829010009766, "learning_rate": 1.9999817675827037e-05, "loss": 31.4094, "step": 108 }, { "epoch": 0.025572316208141644, "grad_norm": 23.185077667236328, "learning_rate": 1.9999769246154852e-05, "loss": 35.253, "step": 109 }, { "epoch": 0.025806924613720927, "grad_norm": 27.340511322021484, "learning_rate": 1.999971511896669e-05, "loss": 36.1269, "step": 110 }, { "epoch": 0.026041533019300206, "grad_norm": 23.837182998657227, "learning_rate": 1.99996552942934e-05, "loss": 36.0081, "step": 111 }, { "epoch": 0.02627614142487949, "grad_norm": 23.664087295532227, "learning_rate": 1.9999589772169062e-05, "loss": 35.2652, "step": 112 }, { "epoch": 0.026510749830458768, "grad_norm": 24.450414657592773, "learning_rate": 1.9999518552631007e-05, "loss": 29.4581, "step": 113 }, { "epoch": 0.02674535823603805, "grad_norm": 28.424457550048828, "learning_rate": 1.9999441635719815e-05, "loss": 37.3262, "step": 114 }, { "epoch": 0.026979966641617333, "grad_norm": 24.942092895507812, "learning_rate": 1.9999359021479314e-05, "loss": 35.6374, "step": 115 }, { "epoch": 0.027214575047196612, "grad_norm": 26.476993560791016, "learning_rate": 1.999927070995657e-05, "loss": 36.8005, "step": 116 }, { "epoch": 0.027449183452775895, "grad_norm": 36.17478561401367, "learning_rate": 1.99991767012019e-05, "loss": 36.0225, "step": 117 }, { "epoch": 0.027683791858355174, "grad_norm": 23.665498733520508, "learning_rate": 1.999907699526887e-05, "loss": 34.7012, "step": 118 }, { "epoch": 0.027918400263934457, "grad_norm": 21.300378799438477, "learning_rate": 1.9998971592214286e-05, "loss": 29.8178, "step": 119 }, { "epoch": 0.028153008669513736, "grad_norm": 26.52481460571289, "learning_rate": 1.9998860492098204e-05, "loss": 38.0044, "step": 120 }, { "epoch": 0.02838761707509302, "grad_norm": 29.960636138916016, "learning_rate": 1.999874369498393e-05, "loss": 30.642, "step": 121 }, { "epoch": 0.028622225480672298, "grad_norm": 26.412534713745117, "learning_rate": 1.9998621200938004e-05, "loss": 33.7752, "step": 122 }, { "epoch": 0.02885683388625158, "grad_norm": 23.515783309936523, "learning_rate": 1.9998493010030214e-05, "loss": 30.8229, "step": 123 }, { "epoch": 0.029091442291830864, "grad_norm": 25.094406127929688, "learning_rate": 1.9998359122333614e-05, "loss": 36.4578, "step": 124 }, { "epoch": 0.029326050697410143, "grad_norm": 25.905460357666016, "learning_rate": 1.9998219537924478e-05, "loss": 34.0601, "step": 125 }, { "epoch": 0.029560659102989426, "grad_norm": 24.258054733276367, "learning_rate": 1.9998074256882335e-05, "loss": 34.8609, "step": 126 }, { "epoch": 0.029795267508568705, "grad_norm": 27.953876495361328, "learning_rate": 1.9997923279289965e-05, "loss": 37.5349, "step": 127 }, { "epoch": 0.030029875914147987, "grad_norm": 21.002426147460938, "learning_rate": 1.999776660523339e-05, "loss": 33.9307, "step": 128 }, { "epoch": 0.030264484319727267, "grad_norm": 21.900981903076172, "learning_rate": 1.9997604234801877e-05, "loss": 33.4759, "step": 129 }, { "epoch": 0.03049909272530655, "grad_norm": 24.311357498168945, "learning_rate": 1.999743616808794e-05, "loss": 37.4562, "step": 130 }, { "epoch": 0.03073370113088583, "grad_norm": 23.89239501953125, "learning_rate": 1.9997262405187333e-05, "loss": 33.9809, "step": 131 }, { "epoch": 0.03096830953646511, "grad_norm": 24.626054763793945, "learning_rate": 1.9997082946199065e-05, "loss": 34.339, "step": 132 }, { "epoch": 0.031202917942044394, "grad_norm": 20.581409454345703, "learning_rate": 1.999689779122538e-05, "loss": 32.135, "step": 133 }, { "epoch": 0.03143752634762367, "grad_norm": 22.102123260498047, "learning_rate": 1.9996706940371778e-05, "loss": 33.9822, "step": 134 }, { "epoch": 0.031672134753202956, "grad_norm": 23.650392532348633, "learning_rate": 1.9996510393746994e-05, "loss": 37.3002, "step": 135 }, { "epoch": 0.03190674315878224, "grad_norm": 26.970800399780273, "learning_rate": 1.999630815146302e-05, "loss": 35.2333, "step": 136 }, { "epoch": 0.032141351564361514, "grad_norm": 29.14348793029785, "learning_rate": 1.9996100213635082e-05, "loss": 39.3281, "step": 137 }, { "epoch": 0.0323759599699408, "grad_norm": 23.962745666503906, "learning_rate": 1.9995886580381657e-05, "loss": 38.0125, "step": 138 }, { "epoch": 0.03261056837552008, "grad_norm": 22.958187103271484, "learning_rate": 1.9995667251824466e-05, "loss": 32.5109, "step": 139 }, { "epoch": 0.03284517678109936, "grad_norm": 25.832698822021484, "learning_rate": 1.999544222808847e-05, "loss": 34.2844, "step": 140 }, { "epoch": 0.03307978518667864, "grad_norm": 20.29319953918457, "learning_rate": 1.9995211509301885e-05, "loss": 28.697, "step": 141 }, { "epoch": 0.03331439359225792, "grad_norm": 23.229026794433594, "learning_rate": 1.9994975095596168e-05, "loss": 31.2405, "step": 142 }, { "epoch": 0.033549001997837204, "grad_norm": 23.235313415527344, "learning_rate": 1.9994732987106014e-05, "loss": 34.8385, "step": 143 }, { "epoch": 0.033783610403416486, "grad_norm": 20.983766555786133, "learning_rate": 1.9994485183969368e-05, "loss": 35.9945, "step": 144 }, { "epoch": 0.03401821880899577, "grad_norm": 24.088333129882812, "learning_rate": 1.9994231686327423e-05, "loss": 32.9007, "step": 145 }, { "epoch": 0.034252827214575045, "grad_norm": 23.99050521850586, "learning_rate": 1.9993972494324615e-05, "loss": 36.486, "step": 146 }, { "epoch": 0.03448743562015433, "grad_norm": 24.30169677734375, "learning_rate": 1.9993707608108616e-05, "loss": 32.3705, "step": 147 }, { "epoch": 0.03472204402573361, "grad_norm": 23.39311408996582, "learning_rate": 1.999343702783035e-05, "loss": 34.4153, "step": 148 }, { "epoch": 0.03495665243131289, "grad_norm": 23.390066146850586, "learning_rate": 1.9993160753643988e-05, "loss": 34.7908, "step": 149 }, { "epoch": 0.03519126083689217, "grad_norm": 22.97186851501465, "learning_rate": 1.9992878785706938e-05, "loss": 32.3291, "step": 150 }, { "epoch": 0.03542586924247145, "grad_norm": 21.663000106811523, "learning_rate": 1.9992591124179856e-05, "loss": 31.834, "step": 151 }, { "epoch": 0.035660477648050734, "grad_norm": 23.7164306640625, "learning_rate": 1.9992297769226646e-05, "loss": 30.0687, "step": 152 }, { "epoch": 0.03589508605363002, "grad_norm": 22.585229873657227, "learning_rate": 1.9991998721014444e-05, "loss": 33.6158, "step": 153 }, { "epoch": 0.0361296944592093, "grad_norm": 23.303850173950195, "learning_rate": 1.9991693979713643e-05, "loss": 31.1519, "step": 154 }, { "epoch": 0.036364302864788575, "grad_norm": 23.895540237426758, "learning_rate": 1.9991383545497868e-05, "loss": 34.0968, "step": 155 }, { "epoch": 0.03659891127036786, "grad_norm": 23.796524047851562, "learning_rate": 1.9991067418543996e-05, "loss": 31.9439, "step": 156 }, { "epoch": 0.03683351967594714, "grad_norm": 22.893789291381836, "learning_rate": 1.9990745599032147e-05, "loss": 32.1632, "step": 157 }, { "epoch": 0.03706812808152642, "grad_norm": 22.034854888916016, "learning_rate": 1.9990418087145684e-05, "loss": 33.7574, "step": 158 }, { "epoch": 0.0373027364871057, "grad_norm": 26.214393615722656, "learning_rate": 1.9990084883071207e-05, "loss": 36.2134, "step": 159 }, { "epoch": 0.03753734489268498, "grad_norm": 22.37685203552246, "learning_rate": 1.9989745986998565e-05, "loss": 29.8898, "step": 160 }, { "epoch": 0.037771953298264264, "grad_norm": 18.590970993041992, "learning_rate": 1.998940139912085e-05, "loss": 31.2681, "step": 161 }, { "epoch": 0.03800656170384355, "grad_norm": 19.251222610473633, "learning_rate": 1.99890511196344e-05, "loss": 29.8065, "step": 162 }, { "epoch": 0.03824117010942283, "grad_norm": 21.652774810791016, "learning_rate": 1.998869514873878e-05, "loss": 36.3952, "step": 163 }, { "epoch": 0.038475778515002106, "grad_norm": 20.042022705078125, "learning_rate": 1.9988333486636823e-05, "loss": 32.2922, "step": 164 }, { "epoch": 0.03871038692058139, "grad_norm": 26.0313720703125, "learning_rate": 1.9987966133534584e-05, "loss": 31.6589, "step": 165 }, { "epoch": 0.03894499532616067, "grad_norm": 28.25917625427246, "learning_rate": 1.9987593089641367e-05, "loss": 30.5943, "step": 166 }, { "epoch": 0.039179603731739954, "grad_norm": 23.369115829467773, "learning_rate": 1.9987214355169726e-05, "loss": 39.2551, "step": 167 }, { "epoch": 0.03941421213731923, "grad_norm": 22.12251091003418, "learning_rate": 1.9986829930335445e-05, "loss": 33.5517, "step": 168 }, { "epoch": 0.03964882054289851, "grad_norm": 21.512773513793945, "learning_rate": 1.998643981535756e-05, "loss": 30.0526, "step": 169 }, { "epoch": 0.039883428948477795, "grad_norm": 20.53412437438965, "learning_rate": 1.9986044010458338e-05, "loss": 30.954, "step": 170 }, { "epoch": 0.04011803735405708, "grad_norm": 20.916120529174805, "learning_rate": 1.99856425158633e-05, "loss": 30.8367, "step": 171 }, { "epoch": 0.04035264575963636, "grad_norm": 22.006301879882812, "learning_rate": 1.9985235331801202e-05, "loss": 33.0308, "step": 172 }, { "epoch": 0.040587254165215636, "grad_norm": 20.944753646850586, "learning_rate": 1.9984822458504043e-05, "loss": 28.5101, "step": 173 }, { "epoch": 0.04082186257079492, "grad_norm": 23.74934196472168, "learning_rate": 1.998440389620706e-05, "loss": 33.4556, "step": 174 }, { "epoch": 0.0410564709763742, "grad_norm": 21.78166389465332, "learning_rate": 1.9983979645148746e-05, "loss": 34.1513, "step": 175 }, { "epoch": 0.041291079381953484, "grad_norm": 25.944128036499023, "learning_rate": 1.998354970557081e-05, "loss": 32.2141, "step": 176 }, { "epoch": 0.04152568778753276, "grad_norm": 22.46167755126953, "learning_rate": 1.9983114077718227e-05, "loss": 37.137, "step": 177 }, { "epoch": 0.04176029619311204, "grad_norm": 23.02762222290039, "learning_rate": 1.99826727618392e-05, "loss": 34.5601, "step": 178 }, { "epoch": 0.041994904598691325, "grad_norm": 27.128936767578125, "learning_rate": 1.9982225758185176e-05, "loss": 31.0189, "step": 179 }, { "epoch": 0.04222951300427061, "grad_norm": 21.224496841430664, "learning_rate": 1.9981773067010838e-05, "loss": 29.7689, "step": 180 }, { "epoch": 0.04246412140984989, "grad_norm": 20.399953842163086, "learning_rate": 1.9981314688574113e-05, "loss": 32.9794, "step": 181 }, { "epoch": 0.042698729815429166, "grad_norm": 22.524303436279297, "learning_rate": 1.9980850623136173e-05, "loss": 32.951, "step": 182 }, { "epoch": 0.04293333822100845, "grad_norm": 21.759521484375, "learning_rate": 1.9980380870961426e-05, "loss": 30.9111, "step": 183 }, { "epoch": 0.04316794662658773, "grad_norm": 22.02227210998535, "learning_rate": 1.9979905432317517e-05, "loss": 31.2464, "step": 184 }, { "epoch": 0.043402555032167014, "grad_norm": 22.50792694091797, "learning_rate": 1.9979424307475338e-05, "loss": 33.6671, "step": 185 }, { "epoch": 0.04363716343774629, "grad_norm": 20.34402084350586, "learning_rate": 1.997893749670901e-05, "loss": 32.7099, "step": 186 }, { "epoch": 0.04387177184332557, "grad_norm": 24.420217514038086, "learning_rate": 1.997844500029591e-05, "loss": 31.201, "step": 187 }, { "epoch": 0.044106380248904856, "grad_norm": 25.829051971435547, "learning_rate": 1.997794681851664e-05, "loss": 33.5262, "step": 188 }, { "epoch": 0.04434098865448414, "grad_norm": 20.745290756225586, "learning_rate": 1.997744295165505e-05, "loss": 31.665, "step": 189 }, { "epoch": 0.04457559706006342, "grad_norm": 20.63484764099121, "learning_rate": 1.9976933399998216e-05, "loss": 34.545, "step": 190 }, { "epoch": 0.0448102054656427, "grad_norm": 24.154470443725586, "learning_rate": 1.9976418163836474e-05, "loss": 33.8355, "step": 191 }, { "epoch": 0.04504481387122198, "grad_norm": 25.40897560119629, "learning_rate": 1.9975897243463383e-05, "loss": 35.2697, "step": 192 }, { "epoch": 0.04527942227680126, "grad_norm": 23.837459564208984, "learning_rate": 1.997537063917574e-05, "loss": 36.9743, "step": 193 }, { "epoch": 0.045514030682380545, "grad_norm": 21.13700294494629, "learning_rate": 1.9974838351273594e-05, "loss": 30.8945, "step": 194 }, { "epoch": 0.04574863908795982, "grad_norm": 22.581939697265625, "learning_rate": 1.997430038006022e-05, "loss": 31.3255, "step": 195 }, { "epoch": 0.0459832474935391, "grad_norm": 23.143539428710938, "learning_rate": 1.9973756725842134e-05, "loss": 31.4369, "step": 196 }, { "epoch": 0.046217855899118386, "grad_norm": 22.182281494140625, "learning_rate": 1.9973207388929096e-05, "loss": 36.9488, "step": 197 }, { "epoch": 0.04645246430469767, "grad_norm": 19.988956451416016, "learning_rate": 1.997265236963409e-05, "loss": 34.7935, "step": 198 }, { "epoch": 0.046687072710276944, "grad_norm": 23.852170944213867, "learning_rate": 1.997209166827335e-05, "loss": 37.9364, "step": 199 }, { "epoch": 0.04692168111585623, "grad_norm": 22.344457626342773, "learning_rate": 1.997152528516635e-05, "loss": 30.1346, "step": 200 }, { "epoch": 0.04715628952143551, "grad_norm": 24.929616928100586, "learning_rate": 1.997095322063579e-05, "loss": 32.1981, "step": 201 }, { "epoch": 0.04739089792701479, "grad_norm": 25.073379516601562, "learning_rate": 1.997037547500761e-05, "loss": 35.1527, "step": 202 }, { "epoch": 0.047625506332594075, "grad_norm": 24.282949447631836, "learning_rate": 1.9969792048610992e-05, "loss": 30.319, "step": 203 }, { "epoch": 0.04786011473817335, "grad_norm": 18.749908447265625, "learning_rate": 1.996920294177835e-05, "loss": 30.319, "step": 204 }, { "epoch": 0.048094723143752634, "grad_norm": 20.830087661743164, "learning_rate": 1.996860815484534e-05, "loss": 32.4696, "step": 205 }, { "epoch": 0.048329331549331916, "grad_norm": 25.1240177154541, "learning_rate": 1.996800768815085e-05, "loss": 32.1921, "step": 206 }, { "epoch": 0.0485639399549112, "grad_norm": 22.43800926208496, "learning_rate": 1.9967401542037e-05, "loss": 33.0743, "step": 207 }, { "epoch": 0.048798548360490475, "grad_norm": 21.863895416259766, "learning_rate": 1.9966789716849157e-05, "loss": 31.2102, "step": 208 }, { "epoch": 0.04903315676606976, "grad_norm": 22.2816104888916, "learning_rate": 1.9966172212935913e-05, "loss": 30.8032, "step": 209 }, { "epoch": 0.04926776517164904, "grad_norm": 23.403141021728516, "learning_rate": 1.99655490306491e-05, "loss": 35.888, "step": 210 }, { "epoch": 0.04950237357722832, "grad_norm": 20.756025314331055, "learning_rate": 1.9964920170343788e-05, "loss": 32.8397, "step": 211 }, { "epoch": 0.049736981982807606, "grad_norm": 21.527809143066406, "learning_rate": 1.9964285632378275e-05, "loss": 33.7593, "step": 212 }, { "epoch": 0.04997159038838688, "grad_norm": 19.328685760498047, "learning_rate": 1.9963645417114103e-05, "loss": 28.9735, "step": 213 }, { "epoch": 0.050206198793966164, "grad_norm": 22.4819278717041, "learning_rate": 1.9962999524916044e-05, "loss": 31.5808, "step": 214 }, { "epoch": 0.05044080719954545, "grad_norm": 22.977081298828125, "learning_rate": 1.99623479561521e-05, "loss": 31.3972, "step": 215 }, { "epoch": 0.05067541560512473, "grad_norm": 19.87923812866211, "learning_rate": 1.996169071119352e-05, "loss": 29.9058, "step": 216 }, { "epoch": 0.050910024010704005, "grad_norm": 27.611042022705078, "learning_rate": 1.996102779041477e-05, "loss": 35.1182, "step": 217 }, { "epoch": 0.05114463241628329, "grad_norm": 25.220476150512695, "learning_rate": 1.9960359194193563e-05, "loss": 30.1968, "step": 218 }, { "epoch": 0.05137924082186257, "grad_norm": 23.080076217651367, "learning_rate": 1.9959684922910844e-05, "loss": 34.2837, "step": 219 }, { "epoch": 0.05161384922744185, "grad_norm": 24.38372802734375, "learning_rate": 1.9959004976950784e-05, "loss": 35.7184, "step": 220 }, { "epoch": 0.051848457633021136, "grad_norm": 20.456083297729492, "learning_rate": 1.9958319356700794e-05, "loss": 27.8895, "step": 221 }, { "epoch": 0.05208306603860041, "grad_norm": 24.88418197631836, "learning_rate": 1.9957628062551516e-05, "loss": 32.2193, "step": 222 }, { "epoch": 0.052317674444179695, "grad_norm": 21.29961395263672, "learning_rate": 1.9956931094896828e-05, "loss": 31.5947, "step": 223 }, { "epoch": 0.05255228284975898, "grad_norm": 18.191116333007812, "learning_rate": 1.9956228454133835e-05, "loss": 31.4188, "step": 224 }, { "epoch": 0.05278689125533826, "grad_norm": 20.037282943725586, "learning_rate": 1.9955520140662876e-05, "loss": 27.884, "step": 225 }, { "epoch": 0.053021499660917536, "grad_norm": 19.644338607788086, "learning_rate": 1.9954806154887527e-05, "loss": 34.4961, "step": 226 }, { "epoch": 0.05325610806649682, "grad_norm": 22.517610549926758, "learning_rate": 1.995408649721459e-05, "loss": 36.9292, "step": 227 }, { "epoch": 0.0534907164720761, "grad_norm": 19.586912155151367, "learning_rate": 1.9953361168054096e-05, "loss": 29.2726, "step": 228 }, { "epoch": 0.053725324877655384, "grad_norm": 21.990755081176758, "learning_rate": 1.9952630167819316e-05, "loss": 35.1309, "step": 229 }, { "epoch": 0.053959933283234666, "grad_norm": 23.024145126342773, "learning_rate": 1.995189349692675e-05, "loss": 35.0152, "step": 230 }, { "epoch": 0.05419454168881394, "grad_norm": 22.104999542236328, "learning_rate": 1.9951151155796128e-05, "loss": 33.8269, "step": 231 }, { "epoch": 0.054429150094393225, "grad_norm": 24.40602684020996, "learning_rate": 1.9950403144850402e-05, "loss": 32.9335, "step": 232 }, { "epoch": 0.05466375849997251, "grad_norm": 19.971405029296875, "learning_rate": 1.994964946451577e-05, "loss": 29.8983, "step": 233 }, { "epoch": 0.05489836690555179, "grad_norm": 20.883941650390625, "learning_rate": 1.994889011522165e-05, "loss": 33.1323, "step": 234 }, { "epoch": 0.055132975311131066, "grad_norm": 22.400903701782227, "learning_rate": 1.994812509740069e-05, "loss": 32.3941, "step": 235 }, { "epoch": 0.05536758371671035, "grad_norm": 23.079769134521484, "learning_rate": 1.9947354411488774e-05, "loss": 37.5756, "step": 236 }, { "epoch": 0.05560219212228963, "grad_norm": 22.917112350463867, "learning_rate": 1.9946578057925012e-05, "loss": 33.779, "step": 237 }, { "epoch": 0.055836800527868914, "grad_norm": 21.586191177368164, "learning_rate": 1.9945796037151736e-05, "loss": 31.7139, "step": 238 }, { "epoch": 0.0560714089334482, "grad_norm": 23.70209503173828, "learning_rate": 1.994500834961452e-05, "loss": 30.3976, "step": 239 }, { "epoch": 0.05630601733902747, "grad_norm": 23.61458396911621, "learning_rate": 1.9944214995762164e-05, "loss": 28.3063, "step": 240 }, { "epoch": 0.056540625744606755, "grad_norm": 24.58729362487793, "learning_rate": 1.9943415976046684e-05, "loss": 30.411, "step": 241 }, { "epoch": 0.05677523415018604, "grad_norm": 23.624574661254883, "learning_rate": 1.994261129092334e-05, "loss": 31.4719, "step": 242 }, { "epoch": 0.05700984255576532, "grad_norm": 25.613861083984375, "learning_rate": 1.9941800940850607e-05, "loss": 29.7329, "step": 243 }, { "epoch": 0.057244450961344596, "grad_norm": 25.626161575317383, "learning_rate": 1.9940984926290204e-05, "loss": 33.7725, "step": 244 }, { "epoch": 0.05747905936692388, "grad_norm": 19.658517837524414, "learning_rate": 1.994016324770706e-05, "loss": 27.1485, "step": 245 }, { "epoch": 0.05771366777250316, "grad_norm": 21.613155364990234, "learning_rate": 1.9939335905569334e-05, "loss": 27.8892, "step": 246 }, { "epoch": 0.057948276178082445, "grad_norm": 21.93730354309082, "learning_rate": 1.9938502900348428e-05, "loss": 29.2441, "step": 247 }, { "epoch": 0.05818288458366173, "grad_norm": 24.169414520263672, "learning_rate": 1.993766423251895e-05, "loss": 28.1374, "step": 248 }, { "epoch": 0.058417492989241, "grad_norm": 23.513721466064453, "learning_rate": 1.9936819902558746e-05, "loss": 34.2501, "step": 249 }, { "epoch": 0.058652101394820286, "grad_norm": 20.153324127197266, "learning_rate": 1.9935969910948887e-05, "loss": 32.3619, "step": 250 }, { "epoch": 0.05888670980039957, "grad_norm": 22.741891860961914, "learning_rate": 1.9935114258173667e-05, "loss": 36.5569, "step": 251 }, { "epoch": 0.05912131820597885, "grad_norm": 21.949562072753906, "learning_rate": 1.993425294472061e-05, "loss": 29.173, "step": 252 }, { "epoch": 0.05935592661155813, "grad_norm": 18.81081771850586, "learning_rate": 1.993338597108045e-05, "loss": 28.4827, "step": 253 }, { "epoch": 0.05959053501713741, "grad_norm": 20.42430877685547, "learning_rate": 1.9932513337747176e-05, "loss": 25.1866, "step": 254 }, { "epoch": 0.05982514342271669, "grad_norm": 23.790294647216797, "learning_rate": 1.993163504521797e-05, "loss": 34.9416, "step": 255 }, { "epoch": 0.060059751828295975, "grad_norm": 22.003854751586914, "learning_rate": 1.993075109399326e-05, "loss": 28.8678, "step": 256 }, { "epoch": 0.06029436023387526, "grad_norm": 20.35602378845215, "learning_rate": 1.9929861484576684e-05, "loss": 32.5479, "step": 257 }, { "epoch": 0.06052896863945453, "grad_norm": 24.7056941986084, "learning_rate": 1.9928966217475115e-05, "loss": 36.8232, "step": 258 }, { "epoch": 0.060763577045033816, "grad_norm": 21.026643753051758, "learning_rate": 1.992806529319864e-05, "loss": 30.6357, "step": 259 }, { "epoch": 0.0609981854506131, "grad_norm": 25.990747451782227, "learning_rate": 1.992715871226058e-05, "loss": 37.9458, "step": 260 }, { "epoch": 0.06123279385619238, "grad_norm": 22.21937370300293, "learning_rate": 1.9926246475177465e-05, "loss": 33.2391, "step": 261 }, { "epoch": 0.06146740226177166, "grad_norm": 20.04498863220215, "learning_rate": 1.9925328582469064e-05, "loss": 29.5912, "step": 262 }, { "epoch": 0.06170201066735094, "grad_norm": 22.946847915649414, "learning_rate": 1.9924405034658358e-05, "loss": 29.7995, "step": 263 }, { "epoch": 0.06193661907293022, "grad_norm": 22.303380966186523, "learning_rate": 1.9923475832271543e-05, "loss": 29.8293, "step": 264 }, { "epoch": 0.062171227478509505, "grad_norm": 25.517898559570312, "learning_rate": 1.9922540975838056e-05, "loss": 32.9712, "step": 265 }, { "epoch": 0.06240583588408879, "grad_norm": 24.175729751586914, "learning_rate": 1.9921600465890543e-05, "loss": 31.9854, "step": 266 }, { "epoch": 0.06264044428966807, "grad_norm": 27.72832679748535, "learning_rate": 1.9920654302964872e-05, "loss": 31.1973, "step": 267 }, { "epoch": 0.06287505269524735, "grad_norm": 22.76962661743164, "learning_rate": 1.9919702487600134e-05, "loss": 30.3488, "step": 268 }, { "epoch": 0.06310966110082662, "grad_norm": 27.34662437438965, "learning_rate": 1.9918745020338636e-05, "loss": 25.23, "step": 269 }, { "epoch": 0.06334426950640591, "grad_norm": 25.117507934570312, "learning_rate": 1.9917781901725918e-05, "loss": 29.5994, "step": 270 }, { "epoch": 0.06357887791198519, "grad_norm": 24.569971084594727, "learning_rate": 1.991681313231072e-05, "loss": 29.0379, "step": 271 }, { "epoch": 0.06381348631756448, "grad_norm": 27.548730850219727, "learning_rate": 1.991583871264502e-05, "loss": 31.148, "step": 272 }, { "epoch": 0.06404809472314375, "grad_norm": 29.802165985107422, "learning_rate": 1.991485864328401e-05, "loss": 28.2412, "step": 273 }, { "epoch": 0.06428270312872303, "grad_norm": 31.180076599121094, "learning_rate": 1.9913872924786092e-05, "loss": 32.4547, "step": 274 }, { "epoch": 0.06451731153430232, "grad_norm": 30.44468116760254, "learning_rate": 1.9912881557712895e-05, "loss": 24.8116, "step": 275 }, { "epoch": 0.0647519199398816, "grad_norm": 37.98418045043945, "learning_rate": 1.9911884542629267e-05, "loss": 26.3557, "step": 276 }, { "epoch": 0.06498652834546088, "grad_norm": 34.06955337524414, "learning_rate": 1.9910881880103276e-05, "loss": 30.7543, "step": 277 }, { "epoch": 0.06522113675104016, "grad_norm": 26.077478408813477, "learning_rate": 1.9909873570706195e-05, "loss": 25.8316, "step": 278 }, { "epoch": 0.06545574515661944, "grad_norm": 19.29450225830078, "learning_rate": 1.990885961501253e-05, "loss": 27.6005, "step": 279 }, { "epoch": 0.06569035356219873, "grad_norm": 20.813711166381836, "learning_rate": 1.9907840013599994e-05, "loss": 28.2587, "step": 280 }, { "epoch": 0.065924961967778, "grad_norm": 21.010986328125, "learning_rate": 1.990681476704952e-05, "loss": 29.5609, "step": 281 }, { "epoch": 0.06615957037335728, "grad_norm": 19.30516815185547, "learning_rate": 1.990578387594526e-05, "loss": 23.5253, "step": 282 }, { "epoch": 0.06639417877893657, "grad_norm": 19.2949275970459, "learning_rate": 1.990474734087458e-05, "loss": 23.9647, "step": 283 }, { "epoch": 0.06662878718451584, "grad_norm": 19.371322631835938, "learning_rate": 1.9903705162428055e-05, "loss": 27.0577, "step": 284 }, { "epoch": 0.06686339559009513, "grad_norm": 22.993587493896484, "learning_rate": 1.9902657341199485e-05, "loss": 34.9216, "step": 285 }, { "epoch": 0.06709800399567441, "grad_norm": 28.293811798095703, "learning_rate": 1.9901603877785885e-05, "loss": 29.8382, "step": 286 }, { "epoch": 0.06733261240125368, "grad_norm": 21.152833938598633, "learning_rate": 1.9900544772787474e-05, "loss": 28.1394, "step": 287 }, { "epoch": 0.06756722080683297, "grad_norm": 28.47956657409668, "learning_rate": 1.9899480026807702e-05, "loss": 32.8374, "step": 288 }, { "epoch": 0.06780182921241225, "grad_norm": 39.76770782470703, "learning_rate": 1.9898409640453216e-05, "loss": 26.3402, "step": 289 }, { "epoch": 0.06803643761799154, "grad_norm": 51.27253341674805, "learning_rate": 1.9897333614333885e-05, "loss": 27.1928, "step": 290 }, { "epoch": 0.06827104602357081, "grad_norm": 32.38995361328125, "learning_rate": 1.9896251949062796e-05, "loss": 28.2412, "step": 291 }, { "epoch": 0.06850565442915009, "grad_norm": 20.61223793029785, "learning_rate": 1.989516464525624e-05, "loss": 26.5446, "step": 292 }, { "epoch": 0.06874026283472938, "grad_norm": 21.443220138549805, "learning_rate": 1.989407170353372e-05, "loss": 28.4287, "step": 293 }, { "epoch": 0.06897487124030866, "grad_norm": 25.599302291870117, "learning_rate": 1.9892973124517967e-05, "loss": 32.2043, "step": 294 }, { "epoch": 0.06920947964588794, "grad_norm": 21.197450637817383, "learning_rate": 1.9891868908834905e-05, "loss": 26.9619, "step": 295 }, { "epoch": 0.06944408805146722, "grad_norm": 23.63831329345703, "learning_rate": 1.9890759057113677e-05, "loss": 30.92, "step": 296 }, { "epoch": 0.0696786964570465, "grad_norm": 24.10389518737793, "learning_rate": 1.988964356998664e-05, "loss": 28.4583, "step": 297 }, { "epoch": 0.06991330486262579, "grad_norm": 25.648609161376953, "learning_rate": 1.9888522448089355e-05, "loss": 32.2215, "step": 298 }, { "epoch": 0.07014791326820506, "grad_norm": 19.82193374633789, "learning_rate": 1.98873956920606e-05, "loss": 26.9303, "step": 299 }, { "epoch": 0.07038252167378434, "grad_norm": 32.87572479248047, "learning_rate": 1.9886263302542366e-05, "loss": 31.3063, "step": 300 }, { "epoch": 0.07061713007936363, "grad_norm": 20.82933235168457, "learning_rate": 1.9885125280179843e-05, "loss": 28.6699, "step": 301 }, { "epoch": 0.0708517384849429, "grad_norm": 21.496910095214844, "learning_rate": 1.9883981625621434e-05, "loss": 28.4289, "step": 302 }, { "epoch": 0.07108634689052219, "grad_norm": 20.648496627807617, "learning_rate": 1.9882832339518757e-05, "loss": 28.9347, "step": 303 }, { "epoch": 0.07132095529610147, "grad_norm": 19.091249465942383, "learning_rate": 1.9881677422526638e-05, "loss": 23.7187, "step": 304 }, { "epoch": 0.07155556370168074, "grad_norm": 22.289745330810547, "learning_rate": 1.98805168753031e-05, "loss": 32.02, "step": 305 }, { "epoch": 0.07179017210726003, "grad_norm": 20.9503231048584, "learning_rate": 1.9879350698509387e-05, "loss": 26.8918, "step": 306 }, { "epoch": 0.07202478051283931, "grad_norm": 20.873220443725586, "learning_rate": 1.9878178892809944e-05, "loss": 25.3484, "step": 307 }, { "epoch": 0.0722593889184186, "grad_norm": 21.3512020111084, "learning_rate": 1.9877001458872424e-05, "loss": 26.0316, "step": 308 }, { "epoch": 0.07249399732399787, "grad_norm": 25.00297737121582, "learning_rate": 1.987581839736769e-05, "loss": 33.4958, "step": 309 }, { "epoch": 0.07272860572957715, "grad_norm": 23.62071418762207, "learning_rate": 1.9874629708969806e-05, "loss": 26.7697, "step": 310 }, { "epoch": 0.07296321413515644, "grad_norm": 22.884790420532227, "learning_rate": 1.9873435394356044e-05, "loss": 25.9037, "step": 311 }, { "epoch": 0.07319782254073572, "grad_norm": 21.248138427734375, "learning_rate": 1.9872235454206885e-05, "loss": 31.0766, "step": 312 }, { "epoch": 0.07343243094631499, "grad_norm": 23.819299697875977, "learning_rate": 1.9871029889206012e-05, "loss": 28.3603, "step": 313 }, { "epoch": 0.07366703935189428, "grad_norm": 22.246938705444336, "learning_rate": 1.9869818700040317e-05, "loss": 26.7285, "step": 314 }, { "epoch": 0.07390164775747356, "grad_norm": 21.261789321899414, "learning_rate": 1.9868601887399882e-05, "loss": 31.1194, "step": 315 }, { "epoch": 0.07413625616305285, "grad_norm": 32.41895294189453, "learning_rate": 1.9867379451978015e-05, "loss": 29.9907, "step": 316 }, { "epoch": 0.07437086456863212, "grad_norm": 26.31590461730957, "learning_rate": 1.986615139447121e-05, "loss": 30.8206, "step": 317 }, { "epoch": 0.0746054729742114, "grad_norm": 21.624916076660156, "learning_rate": 1.9864917715579177e-05, "loss": 26.8594, "step": 318 }, { "epoch": 0.07484008137979069, "grad_norm": 23.374526977539062, "learning_rate": 1.9863678416004813e-05, "loss": 29.2152, "step": 319 }, { "epoch": 0.07507468978536996, "grad_norm": 21.35709571838379, "learning_rate": 1.986243349645424e-05, "loss": 31.6386, "step": 320 }, { "epoch": 0.07530929819094925, "grad_norm": 26.102882385253906, "learning_rate": 1.9861182957636757e-05, "loss": 31.3465, "step": 321 }, { "epoch": 0.07554390659652853, "grad_norm": 23.9254150390625, "learning_rate": 1.9859926800264888e-05, "loss": 27.7903, "step": 322 }, { "epoch": 0.0757785150021078, "grad_norm": 27.501468658447266, "learning_rate": 1.9858665025054334e-05, "loss": 26.5588, "step": 323 }, { "epoch": 0.0760131234076871, "grad_norm": 22.725435256958008, "learning_rate": 1.9857397632724026e-05, "loss": 30.2866, "step": 324 }, { "epoch": 0.07624773181326637, "grad_norm": 21.80025863647461, "learning_rate": 1.9856124623996067e-05, "loss": 29.3064, "step": 325 }, { "epoch": 0.07648234021884566, "grad_norm": 25.63246726989746, "learning_rate": 1.9854845999595776e-05, "loss": 26.5546, "step": 326 }, { "epoch": 0.07671694862442494, "grad_norm": 25.050724029541016, "learning_rate": 1.985356176025167e-05, "loss": 30.3065, "step": 327 }, { "epoch": 0.07695155703000421, "grad_norm": 22.772380828857422, "learning_rate": 1.985227190669546e-05, "loss": 28.9612, "step": 328 }, { "epoch": 0.0771861654355835, "grad_norm": 22.007307052612305, "learning_rate": 1.9850976439662065e-05, "loss": 26.7793, "step": 329 }, { "epoch": 0.07742077384116278, "grad_norm": 18.86005210876465, "learning_rate": 1.984967535988959e-05, "loss": 26.6164, "step": 330 }, { "epoch": 0.07765538224674205, "grad_norm": 20.09914779663086, "learning_rate": 1.984836866811935e-05, "loss": 30.1481, "step": 331 }, { "epoch": 0.07788999065232134, "grad_norm": 22.119327545166016, "learning_rate": 1.9847056365095844e-05, "loss": 28.545, "step": 332 }, { "epoch": 0.07812459905790062, "grad_norm": 25.64582061767578, "learning_rate": 1.9845738451566782e-05, "loss": 32.5418, "step": 333 }, { "epoch": 0.07835920746347991, "grad_norm": 21.01453399658203, "learning_rate": 1.9844414928283066e-05, "loss": 22.802, "step": 334 }, { "epoch": 0.07859381586905918, "grad_norm": 23.31780242919922, "learning_rate": 1.9843085795998787e-05, "loss": 30.5508, "step": 335 }, { "epoch": 0.07882842427463846, "grad_norm": 20.820663452148438, "learning_rate": 1.9841751055471245e-05, "loss": 27.7072, "step": 336 }, { "epoch": 0.07906303268021775, "grad_norm": 21.315439224243164, "learning_rate": 1.9840410707460923e-05, "loss": 30.7911, "step": 337 }, { "epoch": 0.07929764108579702, "grad_norm": 19.943077087402344, "learning_rate": 1.9839064752731505e-05, "loss": 30.1561, "step": 338 }, { "epoch": 0.07953224949137631, "grad_norm": 20.538999557495117, "learning_rate": 1.9837713192049868e-05, "loss": 27.5016, "step": 339 }, { "epoch": 0.07976685789695559, "grad_norm": 22.164779663085938, "learning_rate": 1.9836356026186086e-05, "loss": 30.012, "step": 340 }, { "epoch": 0.08000146630253487, "grad_norm": 22.875011444091797, "learning_rate": 1.983499325591342e-05, "loss": 29.6739, "step": 341 }, { "epoch": 0.08023607470811416, "grad_norm": 17.876928329467773, "learning_rate": 1.9833624882008332e-05, "loss": 24.869, "step": 342 }, { "epoch": 0.08047068311369343, "grad_norm": 21.07624053955078, "learning_rate": 1.9832250905250477e-05, "loss": 28.4965, "step": 343 }, { "epoch": 0.08070529151927272, "grad_norm": 22.576927185058594, "learning_rate": 1.9830871326422687e-05, "loss": 27.7341, "step": 344 }, { "epoch": 0.080939899924852, "grad_norm": 19.67365074157715, "learning_rate": 1.982948614631101e-05, "loss": 24.7356, "step": 345 }, { "epoch": 0.08117450833043127, "grad_norm": 30.276073455810547, "learning_rate": 1.9828095365704663e-05, "loss": 30.1817, "step": 346 }, { "epoch": 0.08140911673601056, "grad_norm": 26.837383270263672, "learning_rate": 1.982669898539607e-05, "loss": 28.9641, "step": 347 }, { "epoch": 0.08164372514158984, "grad_norm": 20.92388153076172, "learning_rate": 1.9825297006180837e-05, "loss": 26.929, "step": 348 }, { "epoch": 0.08187833354716911, "grad_norm": 19.566282272338867, "learning_rate": 1.982388942885776e-05, "loss": 26.4398, "step": 349 }, { "epoch": 0.0821129419527484, "grad_norm": 20.527565002441406, "learning_rate": 1.982247625422883e-05, "loss": 27.9494, "step": 350 }, { "epoch": 0.08234755035832768, "grad_norm": 18.26291275024414, "learning_rate": 1.9821057483099226e-05, "loss": 23.2008, "step": 351 }, { "epoch": 0.08258215876390697, "grad_norm": 19.834766387939453, "learning_rate": 1.981963311627731e-05, "loss": 22.3101, "step": 352 }, { "epoch": 0.08281676716948624, "grad_norm": 20.10218048095703, "learning_rate": 1.9818203154574637e-05, "loss": 26.7334, "step": 353 }, { "epoch": 0.08305137557506552, "grad_norm": 21.212175369262695, "learning_rate": 1.981676759880595e-05, "loss": 28.0859, "step": 354 }, { "epoch": 0.08328598398064481, "grad_norm": 22.15719985961914, "learning_rate": 1.9815326449789177e-05, "loss": 27.9184, "step": 355 }, { "epoch": 0.08352059238622409, "grad_norm": 19.336042404174805, "learning_rate": 1.9813879708345433e-05, "loss": 26.5547, "step": 356 }, { "epoch": 0.08375520079180337, "grad_norm": 22.855344772338867, "learning_rate": 1.9812427375299022e-05, "loss": 30.4064, "step": 357 }, { "epoch": 0.08398980919738265, "grad_norm": 19.654407501220703, "learning_rate": 1.981096945147743e-05, "loss": 27.2333, "step": 358 }, { "epoch": 0.08422441760296193, "grad_norm": 18.426536560058594, "learning_rate": 1.9809505937711332e-05, "loss": 23.162, "step": 359 }, { "epoch": 0.08445902600854122, "grad_norm": 24.413530349731445, "learning_rate": 1.9808036834834588e-05, "loss": 28.7542, "step": 360 }, { "epoch": 0.08469363441412049, "grad_norm": 23.19506072998047, "learning_rate": 1.980656214368424e-05, "loss": 26.1092, "step": 361 }, { "epoch": 0.08492824281969978, "grad_norm": 22.43754005432129, "learning_rate": 1.980508186510051e-05, "loss": 24.9373, "step": 362 }, { "epoch": 0.08516285122527906, "grad_norm": 17.202465057373047, "learning_rate": 1.980359599992682e-05, "loss": 23.83, "step": 363 }, { "epoch": 0.08539745963085833, "grad_norm": 21.220319747924805, "learning_rate": 1.9802104549009754e-05, "loss": 22.0743, "step": 364 }, { "epoch": 0.08563206803643762, "grad_norm": 22.804563522338867, "learning_rate": 1.980060751319909e-05, "loss": 26.1503, "step": 365 }, { "epoch": 0.0858666764420169, "grad_norm": 21.06275749206543, "learning_rate": 1.9799104893347786e-05, "loss": 25.5945, "step": 366 }, { "epoch": 0.08610128484759617, "grad_norm": 20.293331146240234, "learning_rate": 1.979759669031198e-05, "loss": 24.0256, "step": 367 }, { "epoch": 0.08633589325317546, "grad_norm": 19.781330108642578, "learning_rate": 1.9796082904951003e-05, "loss": 28.9123, "step": 368 }, { "epoch": 0.08657050165875474, "grad_norm": 20.07809066772461, "learning_rate": 1.9794563538127347e-05, "loss": 28.388, "step": 369 }, { "epoch": 0.08680511006433403, "grad_norm": 21.06626319885254, "learning_rate": 1.9793038590706695e-05, "loss": 29.5954, "step": 370 }, { "epoch": 0.0870397184699133, "grad_norm": 20.671630859375, "learning_rate": 1.979150806355791e-05, "loss": 32.3933, "step": 371 }, { "epoch": 0.08727432687549258, "grad_norm": 19.616716384887695, "learning_rate": 1.9789971957553033e-05, "loss": 26.2731, "step": 372 }, { "epoch": 0.08750893528107187, "grad_norm": 19.903364181518555, "learning_rate": 1.978843027356728e-05, "loss": 28.7034, "step": 373 }, { "epoch": 0.08774354368665115, "grad_norm": 17.8559627532959, "learning_rate": 1.9786883012479047e-05, "loss": 25.0886, "step": 374 }, { "epoch": 0.08797815209223044, "grad_norm": 24.842384338378906, "learning_rate": 1.9785330175169917e-05, "loss": 20.6416, "step": 375 }, { "epoch": 0.08821276049780971, "grad_norm": 21.595327377319336, "learning_rate": 1.9783771762524632e-05, "loss": 28.1773, "step": 376 }, { "epoch": 0.08844736890338899, "grad_norm": 22.650367736816406, "learning_rate": 1.978220777543113e-05, "loss": 24.8637, "step": 377 }, { "epoch": 0.08868197730896828, "grad_norm": 21.29692268371582, "learning_rate": 1.9780638214780507e-05, "loss": 31.4282, "step": 378 }, { "epoch": 0.08891658571454755, "grad_norm": 21.5135555267334, "learning_rate": 1.977906308146705e-05, "loss": 30.0822, "step": 379 }, { "epoch": 0.08915119412012684, "grad_norm": 21.474199295043945, "learning_rate": 1.977748237638821e-05, "loss": 29.5324, "step": 380 }, { "epoch": 0.08938580252570612, "grad_norm": 19.101497650146484, "learning_rate": 1.977589610044462e-05, "loss": 26.1932, "step": 381 }, { "epoch": 0.0896204109312854, "grad_norm": 18.852598190307617, "learning_rate": 1.977430425454008e-05, "loss": 26.3164, "step": 382 }, { "epoch": 0.08985501933686468, "grad_norm": 22.324665069580078, "learning_rate": 1.9772706839581576e-05, "loss": 26.4111, "step": 383 }, { "epoch": 0.09008962774244396, "grad_norm": 19.309188842773438, "learning_rate": 1.977110385647925e-05, "loss": 27.0768, "step": 384 }, { "epoch": 0.09032423614802323, "grad_norm": 25.099720001220703, "learning_rate": 1.976949530614643e-05, "loss": 28.0478, "step": 385 }, { "epoch": 0.09055884455360252, "grad_norm": 19.74249839782715, "learning_rate": 1.9767881189499606e-05, "loss": 26.8732, "step": 386 }, { "epoch": 0.0907934529591818, "grad_norm": 23.589746475219727, "learning_rate": 1.9766261507458453e-05, "loss": 28.6841, "step": 387 }, { "epoch": 0.09102806136476109, "grad_norm": 20.38739585876465, "learning_rate": 1.97646362609458e-05, "loss": 25.7821, "step": 388 }, { "epoch": 0.09126266977034037, "grad_norm": 18.790794372558594, "learning_rate": 1.9763005450887663e-05, "loss": 21.9868, "step": 389 }, { "epoch": 0.09149727817591964, "grad_norm": 20.038429260253906, "learning_rate": 1.976136907821322e-05, "loss": 31.9285, "step": 390 }, { "epoch": 0.09173188658149893, "grad_norm": 20.783248901367188, "learning_rate": 1.9759727143854808e-05, "loss": 24.8551, "step": 391 }, { "epoch": 0.0919664949870782, "grad_norm": 18.716310501098633, "learning_rate": 1.9758079648747954e-05, "loss": 20.3434, "step": 392 }, { "epoch": 0.0922011033926575, "grad_norm": 23.822965621948242, "learning_rate": 1.9756426593831337e-05, "loss": 27.6708, "step": 393 }, { "epoch": 0.09243571179823677, "grad_norm": 23.208189010620117, "learning_rate": 1.9754767980046813e-05, "loss": 30.8063, "step": 394 }, { "epoch": 0.09267032020381605, "grad_norm": 21.676286697387695, "learning_rate": 1.97531038083394e-05, "loss": 29.7926, "step": 395 }, { "epoch": 0.09290492860939534, "grad_norm": 20.636552810668945, "learning_rate": 1.975143407965728e-05, "loss": 33.4634, "step": 396 }, { "epoch": 0.09313953701497461, "grad_norm": 23.160707473754883, "learning_rate": 1.9749758794951816e-05, "loss": 34.2414, "step": 397 }, { "epoch": 0.09337414542055389, "grad_norm": 23.269365310668945, "learning_rate": 1.9748077955177515e-05, "loss": 30.5943, "step": 398 }, { "epoch": 0.09360875382613318, "grad_norm": 27.627437591552734, "learning_rate": 1.9746391561292068e-05, "loss": 27.4269, "step": 399 }, { "epoch": 0.09384336223171245, "grad_norm": 19.635936737060547, "learning_rate": 1.974469961425632e-05, "loss": 25.3207, "step": 400 }, { "epoch": 0.09407797063729174, "grad_norm": 24.843997955322266, "learning_rate": 1.9743002115034284e-05, "loss": 32.2992, "step": 401 }, { "epoch": 0.09431257904287102, "grad_norm": 18.751489639282227, "learning_rate": 1.9741299064593134e-05, "loss": 25.771, "step": 402 }, { "epoch": 0.0945471874484503, "grad_norm": 19.885005950927734, "learning_rate": 1.9739590463903207e-05, "loss": 27.7761, "step": 403 }, { "epoch": 0.09478179585402959, "grad_norm": 18.07563591003418, "learning_rate": 1.9737876313938004e-05, "loss": 27.5092, "step": 404 }, { "epoch": 0.09501640425960886, "grad_norm": 19.544973373413086, "learning_rate": 1.973615661567419e-05, "loss": 27.3102, "step": 405 }, { "epoch": 0.09525101266518815, "grad_norm": 21.12753677368164, "learning_rate": 1.9734431370091585e-05, "loss": 25.9601, "step": 406 }, { "epoch": 0.09548562107076743, "grad_norm": 23.043542861938477, "learning_rate": 1.9732700578173172e-05, "loss": 27.2974, "step": 407 }, { "epoch": 0.0957202294763467, "grad_norm": 21.51388168334961, "learning_rate": 1.97309642409051e-05, "loss": 29.6562, "step": 408 }, { "epoch": 0.09595483788192599, "grad_norm": 20.847198486328125, "learning_rate": 1.972922235927667e-05, "loss": 27.1574, "step": 409 }, { "epoch": 0.09618944628750527, "grad_norm": 17.851985931396484, "learning_rate": 1.9727474934280345e-05, "loss": 25.1762, "step": 410 }, { "epoch": 0.09642405469308456, "grad_norm": 20.84434700012207, "learning_rate": 1.972572196691175e-05, "loss": 29.2312, "step": 411 }, { "epoch": 0.09665866309866383, "grad_norm": 18.149337768554688, "learning_rate": 1.9723963458169654e-05, "loss": 25.1084, "step": 412 }, { "epoch": 0.09689327150424311, "grad_norm": 19.306795120239258, "learning_rate": 1.9722199409056e-05, "loss": 24.934, "step": 413 }, { "epoch": 0.0971278799098224, "grad_norm": 20.171934127807617, "learning_rate": 1.9720429820575884e-05, "loss": 26.9064, "step": 414 }, { "epoch": 0.09736248831540167, "grad_norm": 18.525020599365234, "learning_rate": 1.9718654693737554e-05, "loss": 30.219, "step": 415 }, { "epoch": 0.09759709672098095, "grad_norm": 27.083660125732422, "learning_rate": 1.9716874029552407e-05, "loss": 27.9512, "step": 416 }, { "epoch": 0.09783170512656024, "grad_norm": 21.84735679626465, "learning_rate": 1.971508782903501e-05, "loss": 29.7077, "step": 417 }, { "epoch": 0.09806631353213952, "grad_norm": 22.765520095825195, "learning_rate": 1.9713296093203076e-05, "loss": 26.6515, "step": 418 }, { "epoch": 0.0983009219377188, "grad_norm": 17.6358642578125, "learning_rate": 1.971149882307747e-05, "loss": 26.4629, "step": 419 }, { "epoch": 0.09853553034329808, "grad_norm": 19.12065315246582, "learning_rate": 1.9709696019682218e-05, "loss": 26.6006, "step": 420 }, { "epoch": 0.09877013874887736, "grad_norm": 24.541372299194336, "learning_rate": 1.970788768404449e-05, "loss": 31.6587, "step": 421 }, { "epoch": 0.09900474715445665, "grad_norm": 24.256654739379883, "learning_rate": 1.9706073817194613e-05, "loss": 27.8286, "step": 422 }, { "epoch": 0.09923935556003592, "grad_norm": 18.337547302246094, "learning_rate": 1.9704254420166063e-05, "loss": 22.9199, "step": 423 }, { "epoch": 0.09947396396561521, "grad_norm": 24.567468643188477, "learning_rate": 1.970242949399547e-05, "loss": 29.5103, "step": 424 }, { "epoch": 0.09970857237119449, "grad_norm": 20.950380325317383, "learning_rate": 1.9700599039722613e-05, "loss": 27.1253, "step": 425 }, { "epoch": 0.09994318077677376, "grad_norm": 20.305992126464844, "learning_rate": 1.9698763058390417e-05, "loss": 23.3065, "step": 426 }, { "epoch": 0.10017778918235305, "grad_norm": 17.229352951049805, "learning_rate": 1.9696921551044963e-05, "loss": 25.2958, "step": 427 }, { "epoch": 0.10041239758793233, "grad_norm": 21.974016189575195, "learning_rate": 1.969507451873548e-05, "loss": 30.1959, "step": 428 }, { "epoch": 0.10064700599351162, "grad_norm": 22.206811904907227, "learning_rate": 1.9693221962514333e-05, "loss": 31.9838, "step": 429 }, { "epoch": 0.1008816143990909, "grad_norm": 20.25482940673828, "learning_rate": 1.969136388343705e-05, "loss": 28.3208, "step": 430 }, { "epoch": 0.10111622280467017, "grad_norm": 19.704286575317383, "learning_rate": 1.9689500282562295e-05, "loss": 25.5264, "step": 431 }, { "epoch": 0.10135083121024946, "grad_norm": 22.75324821472168, "learning_rate": 1.9687631160951885e-05, "loss": 27.9068, "step": 432 }, { "epoch": 0.10158543961582873, "grad_norm": 16.918521881103516, "learning_rate": 1.9685756519670776e-05, "loss": 24.0291, "step": 433 }, { "epoch": 0.10182004802140801, "grad_norm": 17.07303810119629, "learning_rate": 1.968387635978708e-05, "loss": 26.1122, "step": 434 }, { "epoch": 0.1020546564269873, "grad_norm": 20.329771041870117, "learning_rate": 1.9681990682372038e-05, "loss": 24.8199, "step": 435 }, { "epoch": 0.10228926483256658, "grad_norm": 24.341949462890625, "learning_rate": 1.9680099488500047e-05, "loss": 26.3543, "step": 436 }, { "epoch": 0.10252387323814587, "grad_norm": 19.79205322265625, "learning_rate": 1.9678202779248644e-05, "loss": 24.8458, "step": 437 }, { "epoch": 0.10275848164372514, "grad_norm": 19.94573974609375, "learning_rate": 1.96763005556985e-05, "loss": 25.1553, "step": 438 }, { "epoch": 0.10299309004930442, "grad_norm": 23.011817932128906, "learning_rate": 1.9674392818933436e-05, "loss": 29.1014, "step": 439 }, { "epoch": 0.1032276984548837, "grad_norm": 17.704421997070312, "learning_rate": 1.9672479570040425e-05, "loss": 25.3963, "step": 440 }, { "epoch": 0.10346230686046298, "grad_norm": 19.2757568359375, "learning_rate": 1.9670560810109553e-05, "loss": 26.5368, "step": 441 }, { "epoch": 0.10369691526604227, "grad_norm": 17.749189376831055, "learning_rate": 1.9668636540234068e-05, "loss": 26.72, "step": 442 }, { "epoch": 0.10393152367162155, "grad_norm": 26.006433486938477, "learning_rate": 1.9666706761510354e-05, "loss": 25.1048, "step": 443 }, { "epoch": 0.10416613207720082, "grad_norm": 19.343399047851562, "learning_rate": 1.9664771475037933e-05, "loss": 27.8662, "step": 444 }, { "epoch": 0.10440074048278011, "grad_norm": 21.415822982788086, "learning_rate": 1.9662830681919452e-05, "loss": 28.7477, "step": 445 }, { "epoch": 0.10463534888835939, "grad_norm": 21.720603942871094, "learning_rate": 1.9660884383260717e-05, "loss": 24.8964, "step": 446 }, { "epoch": 0.10486995729393868, "grad_norm": 25.18024444580078, "learning_rate": 1.9658932580170657e-05, "loss": 25.4812, "step": 447 }, { "epoch": 0.10510456569951795, "grad_norm": 19.85284996032715, "learning_rate": 1.9656975273761336e-05, "loss": 24.0539, "step": 448 }, { "epoch": 0.10533917410509723, "grad_norm": 19.448362350463867, "learning_rate": 1.9655012465147964e-05, "loss": 24.3216, "step": 449 }, { "epoch": 0.10557378251067652, "grad_norm": 22.12392234802246, "learning_rate": 1.9653044155448882e-05, "loss": 24.8913, "step": 450 }, { "epoch": 0.1058083909162558, "grad_norm": 18.613203048706055, "learning_rate": 1.9651070345785555e-05, "loss": 26.4084, "step": 451 }, { "epoch": 0.10604299932183507, "grad_norm": 21.921953201293945, "learning_rate": 1.96490910372826e-05, "loss": 25.9339, "step": 452 }, { "epoch": 0.10627760772741436, "grad_norm": 22.46790313720703, "learning_rate": 1.964710623106775e-05, "loss": 28.1406, "step": 453 }, { "epoch": 0.10651221613299364, "grad_norm": 18.187896728515625, "learning_rate": 1.9645115928271878e-05, "loss": 21.3514, "step": 454 }, { "epoch": 0.10674682453857293, "grad_norm": 21.937938690185547, "learning_rate": 1.9643120130028993e-05, "loss": 24.0494, "step": 455 }, { "epoch": 0.1069814329441522, "grad_norm": 20.36716651916504, "learning_rate": 1.9641118837476227e-05, "loss": 30.7696, "step": 456 }, { "epoch": 0.10721604134973148, "grad_norm": 17.027313232421875, "learning_rate": 1.9639112051753844e-05, "loss": 26.3128, "step": 457 }, { "epoch": 0.10745064975531077, "grad_norm": 19.719514846801758, "learning_rate": 1.963709977400525e-05, "loss": 25.4713, "step": 458 }, { "epoch": 0.10768525816089004, "grad_norm": 17.73971939086914, "learning_rate": 1.9635082005376957e-05, "loss": 24.3504, "step": 459 }, { "epoch": 0.10791986656646933, "grad_norm": 20.05377960205078, "learning_rate": 1.9633058747018623e-05, "loss": 31.0705, "step": 460 }, { "epoch": 0.10815447497204861, "grad_norm": 22.14566421508789, "learning_rate": 1.963103000008303e-05, "loss": 27.857, "step": 461 }, { "epoch": 0.10838908337762788, "grad_norm": 20.42942237854004, "learning_rate": 1.962899576572609e-05, "loss": 26.7132, "step": 462 }, { "epoch": 0.10862369178320717, "grad_norm": 20.342805862426758, "learning_rate": 1.9626956045106832e-05, "loss": 25.6628, "step": 463 }, { "epoch": 0.10885830018878645, "grad_norm": 21.849864959716797, "learning_rate": 1.9624910839387418e-05, "loss": 32.6506, "step": 464 }, { "epoch": 0.10909290859436573, "grad_norm": 31.23863410949707, "learning_rate": 1.962286014973314e-05, "loss": 30.6292, "step": 465 }, { "epoch": 0.10932751699994502, "grad_norm": 18.13981056213379, "learning_rate": 1.96208039773124e-05, "loss": 23.9867, "step": 466 }, { "epoch": 0.10956212540552429, "grad_norm": 22.848365783691406, "learning_rate": 1.9618742323296742e-05, "loss": 29.7609, "step": 467 }, { "epoch": 0.10979673381110358, "grad_norm": 17.880765914916992, "learning_rate": 1.9616675188860815e-05, "loss": 25.1505, "step": 468 }, { "epoch": 0.11003134221668286, "grad_norm": 19.672121047973633, "learning_rate": 1.9614602575182404e-05, "loss": 26.6369, "step": 469 }, { "epoch": 0.11026595062226213, "grad_norm": 17.53080940246582, "learning_rate": 1.961252448344241e-05, "loss": 24.7876, "step": 470 }, { "epoch": 0.11050055902784142, "grad_norm": 18.64752769470215, "learning_rate": 1.9610440914824854e-05, "loss": 27.5376, "step": 471 }, { "epoch": 0.1107351674334207, "grad_norm": 23.991119384765625, "learning_rate": 1.9608351870516884e-05, "loss": 24.4885, "step": 472 }, { "epoch": 0.11096977583899999, "grad_norm": 20.17178726196289, "learning_rate": 1.9606257351708766e-05, "loss": 26.01, "step": 473 }, { "epoch": 0.11120438424457926, "grad_norm": 18.687419891357422, "learning_rate": 1.9604157359593875e-05, "loss": 23.9007, "step": 474 }, { "epoch": 0.11143899265015854, "grad_norm": 21.227834701538086, "learning_rate": 1.960205189536872e-05, "loss": 30.8146, "step": 475 }, { "epoch": 0.11167360105573783, "grad_norm": 19.500905990600586, "learning_rate": 1.9599940960232912e-05, "loss": 25.4205, "step": 476 }, { "epoch": 0.1119082094613171, "grad_norm": 21.858531951904297, "learning_rate": 1.9597824555389196e-05, "loss": 29.2761, "step": 477 }, { "epoch": 0.1121428178668964, "grad_norm": 22.066579818725586, "learning_rate": 1.9595702682043423e-05, "loss": 25.1049, "step": 478 }, { "epoch": 0.11237742627247567, "grad_norm": 20.985929489135742, "learning_rate": 1.9593575341404557e-05, "loss": 27.6845, "step": 479 }, { "epoch": 0.11261203467805495, "grad_norm": 19.443973541259766, "learning_rate": 1.9591442534684684e-05, "loss": 28.564, "step": 480 }, { "epoch": 0.11284664308363423, "grad_norm": 20.35132598876953, "learning_rate": 1.9589304263099004e-05, "loss": 24.6094, "step": 481 }, { "epoch": 0.11308125148921351, "grad_norm": 22.80177879333496, "learning_rate": 1.958716052786583e-05, "loss": 30.2189, "step": 482 }, { "epoch": 0.11331585989479279, "grad_norm": 22.377323150634766, "learning_rate": 1.9585011330206582e-05, "loss": 27.9021, "step": 483 }, { "epoch": 0.11355046830037208, "grad_norm": 21.27680778503418, "learning_rate": 1.9582856671345796e-05, "loss": 26.8577, "step": 484 }, { "epoch": 0.11378507670595135, "grad_norm": 21.06212043762207, "learning_rate": 1.9580696552511127e-05, "loss": 27.0113, "step": 485 }, { "epoch": 0.11401968511153064, "grad_norm": 29.28482437133789, "learning_rate": 1.957853097493333e-05, "loss": 26.6065, "step": 486 }, { "epoch": 0.11425429351710992, "grad_norm": 19.077058792114258, "learning_rate": 1.957635993984628e-05, "loss": 26.9182, "step": 487 }, { "epoch": 0.11448890192268919, "grad_norm": 19.324413299560547, "learning_rate": 1.957418344848695e-05, "loss": 26.8505, "step": 488 }, { "epoch": 0.11472351032826848, "grad_norm": 20.594776153564453, "learning_rate": 1.9572001502095433e-05, "loss": 24.5885, "step": 489 }, { "epoch": 0.11495811873384776, "grad_norm": 20.365812301635742, "learning_rate": 1.9569814101914918e-05, "loss": 22.4072, "step": 490 }, { "epoch": 0.11519272713942705, "grad_norm": 18.808042526245117, "learning_rate": 1.9567621249191716e-05, "loss": 26.8332, "step": 491 }, { "epoch": 0.11542733554500632, "grad_norm": 25.859338760375977, "learning_rate": 1.9565422945175237e-05, "loss": 31.8854, "step": 492 }, { "epoch": 0.1156619439505856, "grad_norm": 19.925701141357422, "learning_rate": 1.956321919111799e-05, "loss": 27.6729, "step": 493 }, { "epoch": 0.11589655235616489, "grad_norm": 20.502641677856445, "learning_rate": 1.9561009988275602e-05, "loss": 29.1493, "step": 494 }, { "epoch": 0.11613116076174416, "grad_norm": 21.141481399536133, "learning_rate": 1.95587953379068e-05, "loss": 29.9581, "step": 495 }, { "epoch": 0.11636576916732345, "grad_norm": 20.780427932739258, "learning_rate": 1.9556575241273408e-05, "loss": 26.276, "step": 496 }, { "epoch": 0.11660037757290273, "grad_norm": 17.451257705688477, "learning_rate": 1.9554349699640362e-05, "loss": 25.0306, "step": 497 }, { "epoch": 0.116834985978482, "grad_norm": 19.28482437133789, "learning_rate": 1.95521187142757e-05, "loss": 25.3142, "step": 498 }, { "epoch": 0.1170695943840613, "grad_norm": 17.836505889892578, "learning_rate": 1.9549882286450556e-05, "loss": 25.3999, "step": 499 }, { "epoch": 0.11730420278964057, "grad_norm": 24.280311584472656, "learning_rate": 1.954764041743917e-05, "loss": 30.8409, "step": 500 }, { "epoch": 0.11753881119521985, "grad_norm": 17.739395141601562, "learning_rate": 1.9545393108518875e-05, "loss": 27.1383, "step": 501 }, { "epoch": 0.11777341960079914, "grad_norm": 20.994306564331055, "learning_rate": 1.954314036097011e-05, "loss": 28.2874, "step": 502 }, { "epoch": 0.11800802800637841, "grad_norm": 20.256690979003906, "learning_rate": 1.9540882176076413e-05, "loss": 29.7521, "step": 503 }, { "epoch": 0.1182426364119577, "grad_norm": 19.84635353088379, "learning_rate": 1.953861855512442e-05, "loss": 24.7961, "step": 504 }, { "epoch": 0.11847724481753698, "grad_norm": 21.267234802246094, "learning_rate": 1.9536349499403858e-05, "loss": 27.7665, "step": 505 }, { "epoch": 0.11871185322311625, "grad_norm": 19.48050880432129, "learning_rate": 1.9534075010207555e-05, "loss": 24.9658, "step": 506 }, { "epoch": 0.11894646162869554, "grad_norm": 17.958818435668945, "learning_rate": 1.9531795088831443e-05, "loss": 26.1953, "step": 507 }, { "epoch": 0.11918107003427482, "grad_norm": 22.025346755981445, "learning_rate": 1.952950973657453e-05, "loss": 31.9234, "step": 508 }, { "epoch": 0.11941567843985411, "grad_norm": 19.882362365722656, "learning_rate": 1.9527218954738934e-05, "loss": 27.7336, "step": 509 }, { "epoch": 0.11965028684543338, "grad_norm": 22.053369522094727, "learning_rate": 1.9524922744629863e-05, "loss": 26.67, "step": 510 }, { "epoch": 0.11988489525101266, "grad_norm": 21.342832565307617, "learning_rate": 1.952262110755561e-05, "loss": 28.8782, "step": 511 }, { "epoch": 0.12011950365659195, "grad_norm": 18.448299407958984, "learning_rate": 1.9520314044827574e-05, "loss": 27.022, "step": 512 }, { "epoch": 0.12035411206217123, "grad_norm": 16.632490158081055, "learning_rate": 1.9518001557760236e-05, "loss": 22.1151, "step": 513 }, { "epoch": 0.12058872046775052, "grad_norm": 19.081323623657227, "learning_rate": 1.951568364767117e-05, "loss": 26.9975, "step": 514 }, { "epoch": 0.12082332887332979, "grad_norm": 21.02147674560547, "learning_rate": 1.9513360315881042e-05, "loss": 25.7049, "step": 515 }, { "epoch": 0.12105793727890907, "grad_norm": 17.783809661865234, "learning_rate": 1.9511031563713598e-05, "loss": 25.1405, "step": 516 }, { "epoch": 0.12129254568448836, "grad_norm": 26.26138687133789, "learning_rate": 1.9508697392495678e-05, "loss": 25.8984, "step": 517 }, { "epoch": 0.12152715409006763, "grad_norm": 18.09765625, "learning_rate": 1.9506357803557222e-05, "loss": 22.1597, "step": 518 }, { "epoch": 0.12176176249564691, "grad_norm": 18.86961555480957, "learning_rate": 1.9504012798231233e-05, "loss": 28.9602, "step": 519 }, { "epoch": 0.1219963709012262, "grad_norm": 19.105304718017578, "learning_rate": 1.9501662377853814e-05, "loss": 25.1082, "step": 520 }, { "epoch": 0.12223097930680547, "grad_norm": 18.272645950317383, "learning_rate": 1.949930654376416e-05, "loss": 22.9596, "step": 521 }, { "epoch": 0.12246558771238476, "grad_norm": 20.374229431152344, "learning_rate": 1.949694529730454e-05, "loss": 27.1989, "step": 522 }, { "epoch": 0.12270019611796404, "grad_norm": 19.924522399902344, "learning_rate": 1.94945786398203e-05, "loss": 23.1668, "step": 523 }, { "epoch": 0.12293480452354331, "grad_norm": 21.009201049804688, "learning_rate": 1.9492206572659886e-05, "loss": 25.8504, "step": 524 }, { "epoch": 0.1231694129291226, "grad_norm": 19.15546226501465, "learning_rate": 1.948982909717482e-05, "loss": 24.4548, "step": 525 }, { "epoch": 0.12340402133470188, "grad_norm": 18.220369338989258, "learning_rate": 1.9487446214719693e-05, "loss": 26.0887, "step": 526 }, { "epoch": 0.12363862974028117, "grad_norm": 21.281938552856445, "learning_rate": 1.9485057926652198e-05, "loss": 23.7454, "step": 527 }, { "epoch": 0.12387323814586045, "grad_norm": 19.71555519104004, "learning_rate": 1.9482664234333092e-05, "loss": 29.7033, "step": 528 }, { "epoch": 0.12410784655143972, "grad_norm": 21.380229949951172, "learning_rate": 1.9480265139126224e-05, "loss": 24.4421, "step": 529 }, { "epoch": 0.12434245495701901, "grad_norm": 21.019872665405273, "learning_rate": 1.9477860642398504e-05, "loss": 32.4757, "step": 530 }, { "epoch": 0.12457706336259829, "grad_norm": 20.209943771362305, "learning_rate": 1.947545074551993e-05, "loss": 28.447, "step": 531 }, { "epoch": 0.12481167176817758, "grad_norm": 19.44346046447754, "learning_rate": 1.9473035449863586e-05, "loss": 29.0823, "step": 532 }, { "epoch": 0.12504628017375685, "grad_norm": 17.56053352355957, "learning_rate": 1.9470614756805613e-05, "loss": 25.3328, "step": 533 }, { "epoch": 0.12528088857933614, "grad_norm": 20.751220703125, "learning_rate": 1.9468188667725242e-05, "loss": 26.1191, "step": 534 }, { "epoch": 0.1255154969849154, "grad_norm": 19.4117431640625, "learning_rate": 1.9465757184004767e-05, "loss": 26.3118, "step": 535 }, { "epoch": 0.1257501053904947, "grad_norm": 17.267181396484375, "learning_rate": 1.9463320307029567e-05, "loss": 27.9982, "step": 536 }, { "epoch": 0.12598471379607398, "grad_norm": 22.057064056396484, "learning_rate": 1.946087803818809e-05, "loss": 26.7863, "step": 537 }, { "epoch": 0.12621932220165324, "grad_norm": 21.854162216186523, "learning_rate": 1.945843037887185e-05, "loss": 26.9536, "step": 538 }, { "epoch": 0.12645393060723253, "grad_norm": 27.042739868164062, "learning_rate": 1.9455977330475436e-05, "loss": 28.1261, "step": 539 }, { "epoch": 0.12668853901281182, "grad_norm": 24.679052352905273, "learning_rate": 1.9453518894396514e-05, "loss": 29.7268, "step": 540 }, { "epoch": 0.12692314741839109, "grad_norm": 19.01857566833496, "learning_rate": 1.945105507203581e-05, "loss": 28.1393, "step": 541 }, { "epoch": 0.12715775582397038, "grad_norm": 20.190942764282227, "learning_rate": 1.9448585864797123e-05, "loss": 24.8488, "step": 542 }, { "epoch": 0.12739236422954966, "grad_norm": 18.15573501586914, "learning_rate": 1.9446111274087326e-05, "loss": 25.5465, "step": 543 }, { "epoch": 0.12762697263512895, "grad_norm": 23.45258331298828, "learning_rate": 1.9443631301316348e-05, "loss": 26.9974, "step": 544 }, { "epoch": 0.12786158104070822, "grad_norm": 21.43657684326172, "learning_rate": 1.9441145947897193e-05, "loss": 25.6616, "step": 545 }, { "epoch": 0.1280961894462875, "grad_norm": 19.950572967529297, "learning_rate": 1.9438655215245923e-05, "loss": 29.251, "step": 546 }, { "epoch": 0.1283307978518668, "grad_norm": 23.96199607849121, "learning_rate": 1.9436159104781672e-05, "loss": 24.7403, "step": 547 }, { "epoch": 0.12856540625744606, "grad_norm": 17.838638305664062, "learning_rate": 1.9433657617926638e-05, "loss": 25.3674, "step": 548 }, { "epoch": 0.12880001466302535, "grad_norm": 16.370498657226562, "learning_rate": 1.943115075610608e-05, "loss": 27.2959, "step": 549 }, { "epoch": 0.12903462306860464, "grad_norm": 18.291486740112305, "learning_rate": 1.9428638520748317e-05, "loss": 25.2784, "step": 550 }, { "epoch": 0.1292692314741839, "grad_norm": 21.49812889099121, "learning_rate": 1.9426120913284735e-05, "loss": 29.7712, "step": 551 }, { "epoch": 0.1295038398797632, "grad_norm": 19.076705932617188, "learning_rate": 1.942359793514977e-05, "loss": 22.4181, "step": 552 }, { "epoch": 0.12973844828534248, "grad_norm": 23.286556243896484, "learning_rate": 1.9421069587780937e-05, "loss": 33.9745, "step": 553 }, { "epoch": 0.12997305669092177, "grad_norm": 19.158042907714844, "learning_rate": 1.9418535872618793e-05, "loss": 27.1937, "step": 554 }, { "epoch": 0.13020766509650103, "grad_norm": 19.452411651611328, "learning_rate": 1.9415996791106964e-05, "loss": 24.6324, "step": 555 }, { "epoch": 0.13044227350208032, "grad_norm": 22.658613204956055, "learning_rate": 1.9413452344692125e-05, "loss": 28.4174, "step": 556 }, { "epoch": 0.1306768819076596, "grad_norm": 23.751001358032227, "learning_rate": 1.941090253482401e-05, "loss": 30.9022, "step": 557 }, { "epoch": 0.13091149031323887, "grad_norm": 23.302900314331055, "learning_rate": 1.9408347362955414e-05, "loss": 27.1961, "step": 558 }, { "epoch": 0.13114609871881816, "grad_norm": 22.369903564453125, "learning_rate": 1.9405786830542186e-05, "loss": 28.8021, "step": 559 }, { "epoch": 0.13138070712439745, "grad_norm": 18.86091423034668, "learning_rate": 1.9403220939043225e-05, "loss": 25.7824, "step": 560 }, { "epoch": 0.1316153155299767, "grad_norm": 17.9639892578125, "learning_rate": 1.940064968992048e-05, "loss": 22.8918, "step": 561 }, { "epoch": 0.131849923935556, "grad_norm": 22.977291107177734, "learning_rate": 1.939807308463897e-05, "loss": 26.1637, "step": 562 }, { "epoch": 0.1320845323411353, "grad_norm": 18.519723892211914, "learning_rate": 1.9395491124666742e-05, "loss": 26.5833, "step": 563 }, { "epoch": 0.13231914074671455, "grad_norm": 17.81072425842285, "learning_rate": 1.939290381147491e-05, "loss": 24.285, "step": 564 }, { "epoch": 0.13255374915229384, "grad_norm": 19.96721839904785, "learning_rate": 1.9390311146537638e-05, "loss": 23.1013, "step": 565 }, { "epoch": 0.13278835755787313, "grad_norm": 19.204730987548828, "learning_rate": 1.938771313133213e-05, "loss": 23.6908, "step": 566 }, { "epoch": 0.13302296596345242, "grad_norm": 26.817846298217773, "learning_rate": 1.938510976733865e-05, "loss": 30.1518, "step": 567 }, { "epoch": 0.13325757436903168, "grad_norm": 19.717498779296875, "learning_rate": 1.938250105604049e-05, "loss": 26.0769, "step": 568 }, { "epoch": 0.13349218277461097, "grad_norm": 20.368946075439453, "learning_rate": 1.9379886998924016e-05, "loss": 27.618, "step": 569 }, { "epoch": 0.13372679118019026, "grad_norm": 20.598417282104492, "learning_rate": 1.9377267597478618e-05, "loss": 23.3351, "step": 570 }, { "epoch": 0.13396139958576953, "grad_norm": 16.366947174072266, "learning_rate": 1.9374642853196742e-05, "loss": 23.6607, "step": 571 }, { "epoch": 0.13419600799134881, "grad_norm": 18.32000160217285, "learning_rate": 1.937201276757387e-05, "loss": 30.09, "step": 572 }, { "epoch": 0.1344306163969281, "grad_norm": 20.691715240478516, "learning_rate": 1.9369377342108535e-05, "loss": 25.5147, "step": 573 }, { "epoch": 0.13466522480250737, "grad_norm": 18.855663299560547, "learning_rate": 1.9366736578302313e-05, "loss": 27.0345, "step": 574 }, { "epoch": 0.13489983320808666, "grad_norm": 19.18265724182129, "learning_rate": 1.9364090477659808e-05, "loss": 27.0313, "step": 575 }, { "epoch": 0.13513444161366595, "grad_norm": 20.982393264770508, "learning_rate": 1.936143904168869e-05, "loss": 30.1679, "step": 576 }, { "epoch": 0.1353690500192452, "grad_norm": 18.826854705810547, "learning_rate": 1.9358782271899635e-05, "loss": 24.1041, "step": 577 }, { "epoch": 0.1356036584248245, "grad_norm": 18.654190063476562, "learning_rate": 1.9356120169806396e-05, "loss": 26.071, "step": 578 }, { "epoch": 0.1358382668304038, "grad_norm": 18.718461990356445, "learning_rate": 1.935345273692573e-05, "loss": 24.7151, "step": 579 }, { "epoch": 0.13607287523598308, "grad_norm": 21.640722274780273, "learning_rate": 1.9350779974777456e-05, "loss": 27.3017, "step": 580 }, { "epoch": 0.13630748364156234, "grad_norm": 18.774307250976562, "learning_rate": 1.9348101884884415e-05, "loss": 23.5227, "step": 581 }, { "epoch": 0.13654209204714163, "grad_norm": 18.895124435424805, "learning_rate": 1.9345418468772487e-05, "loss": 23.8302, "step": 582 }, { "epoch": 0.13677670045272092, "grad_norm": 20.091785430908203, "learning_rate": 1.9342729727970594e-05, "loss": 30.0384, "step": 583 }, { "epoch": 0.13701130885830018, "grad_norm": 18.230039596557617, "learning_rate": 1.9340035664010676e-05, "loss": 24.4633, "step": 584 }, { "epoch": 0.13724591726387947, "grad_norm": 20.27228355407715, "learning_rate": 1.9337336278427726e-05, "loss": 33.6226, "step": 585 }, { "epoch": 0.13748052566945876, "grad_norm": 20.961721420288086, "learning_rate": 1.9334631572759753e-05, "loss": 27.5617, "step": 586 }, { "epoch": 0.13771513407503802, "grad_norm": 17.337398529052734, "learning_rate": 1.9331921548547804e-05, "loss": 26.3775, "step": 587 }, { "epoch": 0.1379497424806173, "grad_norm": 20.137346267700195, "learning_rate": 1.932920620733595e-05, "loss": 26.5704, "step": 588 }, { "epoch": 0.1381843508861966, "grad_norm": 19.85397720336914, "learning_rate": 1.932648555067131e-05, "loss": 28.35, "step": 589 }, { "epoch": 0.1384189592917759, "grad_norm": 20.81066131591797, "learning_rate": 1.9323759580104006e-05, "loss": 26.6604, "step": 590 }, { "epoch": 0.13865356769735515, "grad_norm": 20.504438400268555, "learning_rate": 1.9321028297187202e-05, "loss": 27.1695, "step": 591 }, { "epoch": 0.13888817610293444, "grad_norm": 19.90978240966797, "learning_rate": 1.931829170347709e-05, "loss": 29.5805, "step": 592 }, { "epoch": 0.13912278450851373, "grad_norm": 20.141109466552734, "learning_rate": 1.9315549800532884e-05, "loss": 22.8776, "step": 593 }, { "epoch": 0.139357392914093, "grad_norm": 22.010330200195312, "learning_rate": 1.9312802589916822e-05, "loss": 31.2169, "step": 594 }, { "epoch": 0.13959200131967228, "grad_norm": 20.30059814453125, "learning_rate": 1.931005007319417e-05, "loss": 25.1421, "step": 595 }, { "epoch": 0.13982660972525157, "grad_norm": 25.250722885131836, "learning_rate": 1.9307292251933215e-05, "loss": 25.0984, "step": 596 }, { "epoch": 0.14006121813083083, "grad_norm": 18.73940086364746, "learning_rate": 1.9304529127705264e-05, "loss": 28.0816, "step": 597 }, { "epoch": 0.14029582653641012, "grad_norm": 20.762832641601562, "learning_rate": 1.930176070208465e-05, "loss": 24.4554, "step": 598 }, { "epoch": 0.1405304349419894, "grad_norm": 19.29817771911621, "learning_rate": 1.929898697664872e-05, "loss": 24.8092, "step": 599 }, { "epoch": 0.14076504334756867, "grad_norm": 22.003440856933594, "learning_rate": 1.929620795297785e-05, "loss": 27.3209, "step": 600 }, { "epoch": 0.14099965175314796, "grad_norm": 17.11868667602539, "learning_rate": 1.9293423632655427e-05, "loss": 24.6122, "step": 601 }, { "epoch": 0.14123426015872725, "grad_norm": 22.8536434173584, "learning_rate": 1.929063401726786e-05, "loss": 29.0044, "step": 602 }, { "epoch": 0.14146886856430654, "grad_norm": 19.160634994506836, "learning_rate": 1.9287839108404573e-05, "loss": 29.0106, "step": 603 }, { "epoch": 0.1417034769698858, "grad_norm": 21.743736267089844, "learning_rate": 1.9285038907658005e-05, "loss": 28.0711, "step": 604 }, { "epoch": 0.1419380853754651, "grad_norm": 21.558292388916016, "learning_rate": 1.9282233416623614e-05, "loss": 28.003, "step": 605 }, { "epoch": 0.14217269378104438, "grad_norm": 22.481693267822266, "learning_rate": 1.9279422636899873e-05, "loss": 28.1764, "step": 606 }, { "epoch": 0.14240730218662365, "grad_norm": 17.3497314453125, "learning_rate": 1.9276606570088255e-05, "loss": 23.8425, "step": 607 }, { "epoch": 0.14264191059220294, "grad_norm": 20.000354766845703, "learning_rate": 1.9273785217793263e-05, "loss": 30.4794, "step": 608 }, { "epoch": 0.14287651899778223, "grad_norm": 18.698883056640625, "learning_rate": 1.9270958581622404e-05, "loss": 23.3829, "step": 609 }, { "epoch": 0.1431111274033615, "grad_norm": 24.699445724487305, "learning_rate": 1.9268126663186195e-05, "loss": 27.3364, "step": 610 }, { "epoch": 0.14334573580894078, "grad_norm": 21.12160873413086, "learning_rate": 1.926528946409816e-05, "loss": 29.0897, "step": 611 }, { "epoch": 0.14358034421452007, "grad_norm": 24.338132858276367, "learning_rate": 1.926244698597484e-05, "loss": 29.1067, "step": 612 }, { "epoch": 0.14381495262009933, "grad_norm": 23.151199340820312, "learning_rate": 1.925959923043578e-05, "loss": 23.4791, "step": 613 }, { "epoch": 0.14404956102567862, "grad_norm": 20.247295379638672, "learning_rate": 1.925674619910352e-05, "loss": 27.5427, "step": 614 }, { "epoch": 0.1442841694312579, "grad_norm": 22.118209838867188, "learning_rate": 1.925388789360363e-05, "loss": 30.2137, "step": 615 }, { "epoch": 0.1445187778368372, "grad_norm": 22.918184280395508, "learning_rate": 1.925102431556466e-05, "loss": 26.2315, "step": 616 }, { "epoch": 0.14475338624241646, "grad_norm": 18.25038719177246, "learning_rate": 1.924815546661819e-05, "loss": 28.4233, "step": 617 }, { "epoch": 0.14498799464799575, "grad_norm": 20.936569213867188, "learning_rate": 1.924528134839877e-05, "loss": 29.1758, "step": 618 }, { "epoch": 0.14522260305357504, "grad_norm": 20.653844833374023, "learning_rate": 1.924240196254399e-05, "loss": 29.7242, "step": 619 }, { "epoch": 0.1454572114591543, "grad_norm": 22.538196563720703, "learning_rate": 1.923951731069441e-05, "loss": 25.8373, "step": 620 }, { "epoch": 0.1456918198647336, "grad_norm": 18.070980072021484, "learning_rate": 1.9236627394493607e-05, "loss": 21.4717, "step": 621 }, { "epoch": 0.14592642827031288, "grad_norm": 18.468753814697266, "learning_rate": 1.9233732215588157e-05, "loss": 27.4155, "step": 622 }, { "epoch": 0.14616103667589214, "grad_norm": 19.604921340942383, "learning_rate": 1.9230831775627626e-05, "loss": 28.7629, "step": 623 }, { "epoch": 0.14639564508147143, "grad_norm": 18.900911331176758, "learning_rate": 1.922792607626458e-05, "loss": 26.086, "step": 624 }, { "epoch": 0.14663025348705072, "grad_norm": 21.62060546875, "learning_rate": 1.9225015119154592e-05, "loss": 21.2521, "step": 625 }, { "epoch": 0.14686486189262998, "grad_norm": 21.521434783935547, "learning_rate": 1.922209890595622e-05, "loss": 30.8013, "step": 626 }, { "epoch": 0.14709947029820927, "grad_norm": 17.868152618408203, "learning_rate": 1.9219177438331013e-05, "loss": 26.9508, "step": 627 }, { "epoch": 0.14733407870378856, "grad_norm": 18.288909912109375, "learning_rate": 1.921625071794353e-05, "loss": 29.4891, "step": 628 }, { "epoch": 0.14756868710936785, "grad_norm": 19.522619247436523, "learning_rate": 1.9213318746461304e-05, "loss": 24.5617, "step": 629 }, { "epoch": 0.14780329551494711, "grad_norm": 18.784847259521484, "learning_rate": 1.9210381525554877e-05, "loss": 28.3092, "step": 630 }, { "epoch": 0.1480379039205264, "grad_norm": 19.295509338378906, "learning_rate": 1.920743905689777e-05, "loss": 32.3017, "step": 631 }, { "epoch": 0.1482725123261057, "grad_norm": 28.63591194152832, "learning_rate": 1.9204491342166495e-05, "loss": 27.3428, "step": 632 }, { "epoch": 0.14850712073168496, "grad_norm": 16.931737899780273, "learning_rate": 1.920153838304056e-05, "loss": 23.553, "step": 633 }, { "epoch": 0.14874172913726424, "grad_norm": 23.63816261291504, "learning_rate": 1.919858018120246e-05, "loss": 27.9172, "step": 634 }, { "epoch": 0.14897633754284353, "grad_norm": 21.69915008544922, "learning_rate": 1.919561673833767e-05, "loss": 29.4645, "step": 635 }, { "epoch": 0.1492109459484228, "grad_norm": 22.09520721435547, "learning_rate": 1.919264805613465e-05, "loss": 23.2699, "step": 636 }, { "epoch": 0.14944555435400209, "grad_norm": 21.936914443969727, "learning_rate": 1.9189674136284863e-05, "loss": 27.1102, "step": 637 }, { "epoch": 0.14968016275958138, "grad_norm": 21.418916702270508, "learning_rate": 1.918669498048273e-05, "loss": 28.6533, "step": 638 }, { "epoch": 0.14991477116516067, "grad_norm": 18.67929458618164, "learning_rate": 1.918371059042568e-05, "loss": 27.9573, "step": 639 }, { "epoch": 0.15014937957073993, "grad_norm": 25.71315574645996, "learning_rate": 1.918072096781411e-05, "loss": 26.8415, "step": 640 }, { "epoch": 0.15038398797631922, "grad_norm": 20.471113204956055, "learning_rate": 1.9177726114351398e-05, "loss": 25.7035, "step": 641 }, { "epoch": 0.1506185963818985, "grad_norm": 21.59760856628418, "learning_rate": 1.9174726031743907e-05, "loss": 24.6044, "step": 642 }, { "epoch": 0.15085320478747777, "grad_norm": 21.41411018371582, "learning_rate": 1.917172072170098e-05, "loss": 24.9393, "step": 643 }, { "epoch": 0.15108781319305706, "grad_norm": 20.00677490234375, "learning_rate": 1.916871018593494e-05, "loss": 26.3719, "step": 644 }, { "epoch": 0.15132242159863635, "grad_norm": 20.1739501953125, "learning_rate": 1.916569442616108e-05, "loss": 26.3096, "step": 645 }, { "epoch": 0.1515570300042156, "grad_norm": 19.752849578857422, "learning_rate": 1.916267344409767e-05, "loss": 30.8781, "step": 646 }, { "epoch": 0.1517916384097949, "grad_norm": 21.119789123535156, "learning_rate": 1.9159647241465966e-05, "loss": 25.2902, "step": 647 }, { "epoch": 0.1520262468153742, "grad_norm": 23.479459762573242, "learning_rate": 1.915661581999019e-05, "loss": 29.3597, "step": 648 }, { "epoch": 0.15226085522095345, "grad_norm": 17.661134719848633, "learning_rate": 1.9153579181397535e-05, "loss": 31.3931, "step": 649 }, { "epoch": 0.15249546362653274, "grad_norm": 17.121347427368164, "learning_rate": 1.9150537327418174e-05, "loss": 24.4874, "step": 650 }, { "epoch": 0.15273007203211203, "grad_norm": 19.85333824157715, "learning_rate": 1.9147490259785247e-05, "loss": 29.6079, "step": 651 }, { "epoch": 0.15296468043769132, "grad_norm": 19.63347625732422, "learning_rate": 1.914443798023487e-05, "loss": 25.6044, "step": 652 }, { "epoch": 0.15319928884327058, "grad_norm": 22.84005355834961, "learning_rate": 1.9141380490506115e-05, "loss": 32.3331, "step": 653 }, { "epoch": 0.15343389724884987, "grad_norm": 18.804941177368164, "learning_rate": 1.9138317792341042e-05, "loss": 26.4921, "step": 654 }, { "epoch": 0.15366850565442916, "grad_norm": 18.68401527404785, "learning_rate": 1.9135249887484663e-05, "loss": 26.1177, "step": 655 }, { "epoch": 0.15390311406000842, "grad_norm": 20.791311264038086, "learning_rate": 1.9132176777684965e-05, "loss": 30.3845, "step": 656 }, { "epoch": 0.1541377224655877, "grad_norm": 19.909109115600586, "learning_rate": 1.912909846469289e-05, "loss": 21.9197, "step": 657 }, { "epoch": 0.154372330871167, "grad_norm": 19.1724853515625, "learning_rate": 1.912601495026236e-05, "loss": 27.0405, "step": 658 }, { "epoch": 0.15460693927674626, "grad_norm": 23.072980880737305, "learning_rate": 1.9122926236150255e-05, "loss": 29.4127, "step": 659 }, { "epoch": 0.15484154768232555, "grad_norm": 19.917863845825195, "learning_rate": 1.9119832324116405e-05, "loss": 30.6651, "step": 660 }, { "epoch": 0.15507615608790484, "grad_norm": 20.822349548339844, "learning_rate": 1.9116733215923623e-05, "loss": 29.6316, "step": 661 }, { "epoch": 0.1553107644934841, "grad_norm": 21.931686401367188, "learning_rate": 1.9113628913337662e-05, "loss": 28.4919, "step": 662 }, { "epoch": 0.1555453728990634, "grad_norm": 17.1589298248291, "learning_rate": 1.911051941812725e-05, "loss": 22.9826, "step": 663 }, { "epoch": 0.15577998130464268, "grad_norm": 18.626649856567383, "learning_rate": 1.9107404732064068e-05, "loss": 28.2451, "step": 664 }, { "epoch": 0.15601458971022197, "grad_norm": 20.826929092407227, "learning_rate": 1.9104284856922754e-05, "loss": 30.2068, "step": 665 }, { "epoch": 0.15624919811580124, "grad_norm": 19.049528121948242, "learning_rate": 1.9101159794480896e-05, "loss": 27.5467, "step": 666 }, { "epoch": 0.15648380652138053, "grad_norm": 20.009126663208008, "learning_rate": 1.9098029546519056e-05, "loss": 22.9298, "step": 667 }, { "epoch": 0.15671841492695981, "grad_norm": 24.307350158691406, "learning_rate": 1.9094894114820733e-05, "loss": 28.8143, "step": 668 }, { "epoch": 0.15695302333253908, "grad_norm": 18.0941104888916, "learning_rate": 1.909175350117238e-05, "loss": 24.8404, "step": 669 }, { "epoch": 0.15718763173811837, "grad_norm": 20.216766357421875, "learning_rate": 1.908860770736342e-05, "loss": 29.1525, "step": 670 }, { "epoch": 0.15742224014369766, "grad_norm": 20.57350730895996, "learning_rate": 1.9085456735186202e-05, "loss": 27.2135, "step": 671 }, { "epoch": 0.15765684854927692, "grad_norm": 21.823911666870117, "learning_rate": 1.908230058643605e-05, "loss": 24.8733, "step": 672 }, { "epoch": 0.1578914569548562, "grad_norm": 17.981571197509766, "learning_rate": 1.9079139262911222e-05, "loss": 26.7219, "step": 673 }, { "epoch": 0.1581260653604355, "grad_norm": 18.15777015686035, "learning_rate": 1.9075972766412926e-05, "loss": 22.9116, "step": 674 }, { "epoch": 0.1583606737660148, "grad_norm": 21.7766056060791, "learning_rate": 1.9072801098745323e-05, "loss": 25.9377, "step": 675 }, { "epoch": 0.15859528217159405, "grad_norm": 22.73971939086914, "learning_rate": 1.9069624261715522e-05, "loss": 27.0426, "step": 676 }, { "epoch": 0.15882989057717334, "grad_norm": 21.441938400268555, "learning_rate": 1.906644225713356e-05, "loss": 29.1334, "step": 677 }, { "epoch": 0.15906449898275263, "grad_norm": 18.61520767211914, "learning_rate": 1.9063255086812445e-05, "loss": 27.0929, "step": 678 }, { "epoch": 0.1592991073883319, "grad_norm": 21.416545867919922, "learning_rate": 1.906006275256811e-05, "loss": 28.3236, "step": 679 }, { "epoch": 0.15953371579391118, "grad_norm": 19.56270980834961, "learning_rate": 1.9056865256219428e-05, "loss": 25.2115, "step": 680 }, { "epoch": 0.15976832419949047, "grad_norm": 21.0888614654541, "learning_rate": 1.9053662599588226e-05, "loss": 26.2015, "step": 681 }, { "epoch": 0.16000293260506973, "grad_norm": 19.77373695373535, "learning_rate": 1.905045478449926e-05, "loss": 26.0859, "step": 682 }, { "epoch": 0.16023754101064902, "grad_norm": 23.981901168823242, "learning_rate": 1.9047241812780238e-05, "loss": 26.812, "step": 683 }, { "epoch": 0.1604721494162283, "grad_norm": 23.524751663208008, "learning_rate": 1.904402368626179e-05, "loss": 31.5626, "step": 684 }, { "epoch": 0.16070675782180757, "grad_norm": 20.045513153076172, "learning_rate": 1.9040800406777492e-05, "loss": 27.4622, "step": 685 }, { "epoch": 0.16094136622738686, "grad_norm": 23.411884307861328, "learning_rate": 1.903757197616386e-05, "loss": 33.0615, "step": 686 }, { "epoch": 0.16117597463296615, "grad_norm": 19.54521369934082, "learning_rate": 1.9034338396260338e-05, "loss": 27.0326, "step": 687 }, { "epoch": 0.16141058303854544, "grad_norm": 20.94941520690918, "learning_rate": 1.9031099668909307e-05, "loss": 24.7255, "step": 688 }, { "epoch": 0.1616451914441247, "grad_norm": 21.519107818603516, "learning_rate": 1.9027855795956073e-05, "loss": 29.0852, "step": 689 }, { "epoch": 0.161879799849704, "grad_norm": 19.443235397338867, "learning_rate": 1.902460677924889e-05, "loss": 22.3174, "step": 690 }, { "epoch": 0.16211440825528328, "grad_norm": 18.922195434570312, "learning_rate": 1.9021352620638926e-05, "loss": 26.5298, "step": 691 }, { "epoch": 0.16234901666086254, "grad_norm": 22.249845504760742, "learning_rate": 1.9018093321980287e-05, "loss": 27.052, "step": 692 }, { "epoch": 0.16258362506644183, "grad_norm": 19.09490394592285, "learning_rate": 1.901482888513001e-05, "loss": 28.0878, "step": 693 }, { "epoch": 0.16281823347202112, "grad_norm": 20.21663475036621, "learning_rate": 1.901155931194805e-05, "loss": 25.9552, "step": 694 }, { "epoch": 0.16305284187760039, "grad_norm": 18.90544891357422, "learning_rate": 1.9008284604297298e-05, "loss": 28.4012, "step": 695 }, { "epoch": 0.16328745028317967, "grad_norm": 18.517690658569336, "learning_rate": 1.9005004764043572e-05, "loss": 23.1841, "step": 696 }, { "epoch": 0.16352205868875896, "grad_norm": 19.75495147705078, "learning_rate": 1.90017197930556e-05, "loss": 28.7446, "step": 697 }, { "epoch": 0.16375666709433823, "grad_norm": 20.52974510192871, "learning_rate": 1.899842969320505e-05, "loss": 28.0876, "step": 698 }, { "epoch": 0.16399127549991752, "grad_norm": 19.313013076782227, "learning_rate": 1.89951344663665e-05, "loss": 27.4145, "step": 699 }, { "epoch": 0.1642258839054968, "grad_norm": 17.355445861816406, "learning_rate": 1.8991834114417454e-05, "loss": 21.7335, "step": 700 }, { "epoch": 0.1644604923110761, "grad_norm": 21.790468215942383, "learning_rate": 1.8988528639238343e-05, "loss": 26.314, "step": 701 }, { "epoch": 0.16469510071665536, "grad_norm": 16.174419403076172, "learning_rate": 1.8985218042712502e-05, "loss": 25.3453, "step": 702 }, { "epoch": 0.16492970912223465, "grad_norm": 18.828357696533203, "learning_rate": 1.89819023267262e-05, "loss": 26.5343, "step": 703 }, { "epoch": 0.16516431752781394, "grad_norm": 24.153043746948242, "learning_rate": 1.8978581493168606e-05, "loss": 24.3492, "step": 704 }, { "epoch": 0.1653989259333932, "grad_norm": 21.787960052490234, "learning_rate": 1.897525554393182e-05, "loss": 25.154, "step": 705 }, { "epoch": 0.1656335343389725, "grad_norm": 16.950136184692383, "learning_rate": 1.897192448091085e-05, "loss": 26.7967, "step": 706 }, { "epoch": 0.16586814274455178, "grad_norm": 22.195117950439453, "learning_rate": 1.896858830600362e-05, "loss": 25.771, "step": 707 }, { "epoch": 0.16610275115013104, "grad_norm": 21.124794006347656, "learning_rate": 1.8965247021110956e-05, "loss": 26.1492, "step": 708 }, { "epoch": 0.16633735955571033, "grad_norm": 20.767465591430664, "learning_rate": 1.8961900628136617e-05, "loss": 24.218, "step": 709 }, { "epoch": 0.16657196796128962, "grad_norm": 18.60675048828125, "learning_rate": 1.895854912898725e-05, "loss": 23.741, "step": 710 }, { "epoch": 0.16680657636686888, "grad_norm": 20.30080223083496, "learning_rate": 1.8955192525572427e-05, "loss": 31.2112, "step": 711 }, { "epoch": 0.16704118477244817, "grad_norm": 18.758079528808594, "learning_rate": 1.8951830819804615e-05, "loss": 22.8206, "step": 712 }, { "epoch": 0.16727579317802746, "grad_norm": 21.13487434387207, "learning_rate": 1.8948464013599204e-05, "loss": 25.9916, "step": 713 }, { "epoch": 0.16751040158360675, "grad_norm": 20.131515502929688, "learning_rate": 1.894509210887448e-05, "loss": 30.6161, "step": 714 }, { "epoch": 0.167745009989186, "grad_norm": 18.77019691467285, "learning_rate": 1.894171510755163e-05, "loss": 31.9273, "step": 715 }, { "epoch": 0.1679796183947653, "grad_norm": 17.463516235351562, "learning_rate": 1.8938333011554754e-05, "loss": 25.9698, "step": 716 }, { "epoch": 0.1682142268003446, "grad_norm": 19.091066360473633, "learning_rate": 1.8934945822810848e-05, "loss": 29.7146, "step": 717 }, { "epoch": 0.16844883520592385, "grad_norm": 20.416582107543945, "learning_rate": 1.8931553543249817e-05, "loss": 26.3439, "step": 718 }, { "epoch": 0.16868344361150314, "grad_norm": 19.577106475830078, "learning_rate": 1.8928156174804462e-05, "loss": 33.1347, "step": 719 }, { "epoch": 0.16891805201708243, "grad_norm": 16.956249237060547, "learning_rate": 1.892475371941048e-05, "loss": 23.329, "step": 720 }, { "epoch": 0.1691526604226617, "grad_norm": 20.874603271484375, "learning_rate": 1.8921346179006475e-05, "loss": 24.3453, "step": 721 }, { "epoch": 0.16938726882824098, "grad_norm": 15.438226699829102, "learning_rate": 1.891793355553394e-05, "loss": 21.8394, "step": 722 }, { "epoch": 0.16962187723382027, "grad_norm": 20.671958923339844, "learning_rate": 1.891451585093727e-05, "loss": 26.517, "step": 723 }, { "epoch": 0.16985648563939956, "grad_norm": 16.086904525756836, "learning_rate": 1.8911093067163746e-05, "loss": 24.9028, "step": 724 }, { "epoch": 0.17009109404497882, "grad_norm": 18.195068359375, "learning_rate": 1.8907665206163557e-05, "loss": 29.9764, "step": 725 }, { "epoch": 0.17032570245055811, "grad_norm": 22.422910690307617, "learning_rate": 1.8904232269889774e-05, "loss": 26.0861, "step": 726 }, { "epoch": 0.1705603108561374, "grad_norm": 18.775405883789062, "learning_rate": 1.8900794260298365e-05, "loss": 23.6909, "step": 727 }, { "epoch": 0.17079491926171667, "grad_norm": 22.083860397338867, "learning_rate": 1.8897351179348187e-05, "loss": 25.4048, "step": 728 }, { "epoch": 0.17102952766729596, "grad_norm": 18.27744483947754, "learning_rate": 1.8893903029000982e-05, "loss": 24.1984, "step": 729 }, { "epoch": 0.17126413607287524, "grad_norm": 22.42286491394043, "learning_rate": 1.889044981122139e-05, "loss": 29.7429, "step": 730 }, { "epoch": 0.1714987444784545, "grad_norm": 16.937294006347656, "learning_rate": 1.8886991527976926e-05, "loss": 24.858, "step": 731 }, { "epoch": 0.1717333528840338, "grad_norm": 18.887409210205078, "learning_rate": 1.8883528181238006e-05, "loss": 22.9065, "step": 732 }, { "epoch": 0.17196796128961309, "grad_norm": 23.969736099243164, "learning_rate": 1.8880059772977917e-05, "loss": 32.1307, "step": 733 }, { "epoch": 0.17220256969519235, "grad_norm": 16.33907699584961, "learning_rate": 1.8876586305172835e-05, "loss": 21.2991, "step": 734 }, { "epoch": 0.17243717810077164, "grad_norm": 18.809139251708984, "learning_rate": 1.8873107779801824e-05, "loss": 26.6684, "step": 735 }, { "epoch": 0.17267178650635093, "grad_norm": 22.116445541381836, "learning_rate": 1.8869624198846824e-05, "loss": 29.7394, "step": 736 }, { "epoch": 0.17290639491193022, "grad_norm": 21.067197799682617, "learning_rate": 1.8866135564292656e-05, "loss": 27.4599, "step": 737 }, { "epoch": 0.17314100331750948, "grad_norm": 20.031543731689453, "learning_rate": 1.886264187812702e-05, "loss": 27.9631, "step": 738 }, { "epoch": 0.17337561172308877, "grad_norm": 20.641456604003906, "learning_rate": 1.8859143142340493e-05, "loss": 27.754, "step": 739 }, { "epoch": 0.17361022012866806, "grad_norm": 21.418542861938477, "learning_rate": 1.8855639358926535e-05, "loss": 26.6936, "step": 740 }, { "epoch": 0.17384482853424732, "grad_norm": 22.52143669128418, "learning_rate": 1.885213052988148e-05, "loss": 27.6761, "step": 741 }, { "epoch": 0.1740794369398266, "grad_norm": 19.081201553344727, "learning_rate": 1.884861665720453e-05, "loss": 25.2811, "step": 742 }, { "epoch": 0.1743140453454059, "grad_norm": 20.586816787719727, "learning_rate": 1.884509774289777e-05, "loss": 24.7653, "step": 743 }, { "epoch": 0.17454865375098516, "grad_norm": 17.56972885131836, "learning_rate": 1.884157378896615e-05, "loss": 25.3754, "step": 744 }, { "epoch": 0.17478326215656445, "grad_norm": 20.187944412231445, "learning_rate": 1.88380447974175e-05, "loss": 32.1297, "step": 745 }, { "epoch": 0.17501787056214374, "grad_norm": 19.749393463134766, "learning_rate": 1.8834510770262507e-05, "loss": 29.8062, "step": 746 }, { "epoch": 0.175252478967723, "grad_norm": 17.69505500793457, "learning_rate": 1.883097170951474e-05, "loss": 30.3229, "step": 747 }, { "epoch": 0.1754870873733023, "grad_norm": 20.860164642333984, "learning_rate": 1.882742761719063e-05, "loss": 27.3335, "step": 748 }, { "epoch": 0.17572169577888158, "grad_norm": 22.791553497314453, "learning_rate": 1.882387849530948e-05, "loss": 27.7496, "step": 749 }, { "epoch": 0.17595630418446087, "grad_norm": 16.754047393798828, "learning_rate": 1.882032434589345e-05, "loss": 22.4578, "step": 750 }, { "epoch": 0.17619091259004013, "grad_norm": 17.998916625976562, "learning_rate": 1.8816765170967563e-05, "loss": 24.4981, "step": 751 }, { "epoch": 0.17642552099561942, "grad_norm": 20.8614559173584, "learning_rate": 1.8813200972559725e-05, "loss": 27.0337, "step": 752 }, { "epoch": 0.1766601294011987, "grad_norm": 20.25900650024414, "learning_rate": 1.8809631752700682e-05, "loss": 29.1059, "step": 753 }, { "epoch": 0.17689473780677797, "grad_norm": 19.50191307067871, "learning_rate": 1.880605751342405e-05, "loss": 21.0887, "step": 754 }, { "epoch": 0.17712934621235726, "grad_norm": 18.398460388183594, "learning_rate": 1.8802478256766306e-05, "loss": 27.2096, "step": 755 }, { "epoch": 0.17736395461793655, "grad_norm": 19.815370559692383, "learning_rate": 1.8798893984766787e-05, "loss": 24.023, "step": 756 }, { "epoch": 0.17759856302351582, "grad_norm": 21.546443939208984, "learning_rate": 1.8795304699467682e-05, "loss": 33.3414, "step": 757 }, { "epoch": 0.1778331714290951, "grad_norm": 21.263551712036133, "learning_rate": 1.8791710402914036e-05, "loss": 27.8837, "step": 758 }, { "epoch": 0.1780677798346744, "grad_norm": 19.972211837768555, "learning_rate": 1.8788111097153758e-05, "loss": 31.6398, "step": 759 }, { "epoch": 0.17830238824025368, "grad_norm": 16.946949005126953, "learning_rate": 1.8784506784237603e-05, "loss": 24.5467, "step": 760 }, { "epoch": 0.17853699664583295, "grad_norm": 18.26791000366211, "learning_rate": 1.878089746621918e-05, "loss": 26.619, "step": 761 }, { "epoch": 0.17877160505141224, "grad_norm": 20.50538444519043, "learning_rate": 1.8777283145154953e-05, "loss": 30.5482, "step": 762 }, { "epoch": 0.17900621345699153, "grad_norm": 17.049285888671875, "learning_rate": 1.8773663823104238e-05, "loss": 24.0901, "step": 763 }, { "epoch": 0.1792408218625708, "grad_norm": 18.086854934692383, "learning_rate": 1.877003950212919e-05, "loss": 26.0022, "step": 764 }, { "epoch": 0.17947543026815008, "grad_norm": 19.732851028442383, "learning_rate": 1.8766410184294824e-05, "loss": 24.3939, "step": 765 }, { "epoch": 0.17971003867372937, "grad_norm": 19.0399112701416, "learning_rate": 1.8762775871668996e-05, "loss": 23.8914, "step": 766 }, { "epoch": 0.17994464707930863, "grad_norm": 19.75922203063965, "learning_rate": 1.875913656632241e-05, "loss": 28.4039, "step": 767 }, { "epoch": 0.18017925548488792, "grad_norm": 19.9813175201416, "learning_rate": 1.8755492270328615e-05, "loss": 28.4576, "step": 768 }, { "epoch": 0.1804138638904672, "grad_norm": 20.594139099121094, "learning_rate": 1.8751842985764e-05, "loss": 23.634, "step": 769 }, { "epoch": 0.18064847229604647, "grad_norm": 18.02235221862793, "learning_rate": 1.8748188714707795e-05, "loss": 25.7891, "step": 770 }, { "epoch": 0.18088308070162576, "grad_norm": 20.605857849121094, "learning_rate": 1.8744529459242083e-05, "loss": 29.0563, "step": 771 }, { "epoch": 0.18111768910720505, "grad_norm": 24.093935012817383, "learning_rate": 1.8740865221451776e-05, "loss": 27.8447, "step": 772 }, { "epoch": 0.18135229751278434, "grad_norm": 22.8870792388916, "learning_rate": 1.8737196003424625e-05, "loss": 30.1572, "step": 773 }, { "epoch": 0.1815869059183636, "grad_norm": 20.581899642944336, "learning_rate": 1.8733521807251222e-05, "loss": 26.7387, "step": 774 }, { "epoch": 0.1818215143239429, "grad_norm": 18.933521270751953, "learning_rate": 1.8729842635024998e-05, "loss": 23.9191, "step": 775 }, { "epoch": 0.18205612272952218, "grad_norm": 18.464311599731445, "learning_rate": 1.872615848884221e-05, "loss": 28.3709, "step": 776 }, { "epoch": 0.18229073113510144, "grad_norm": 16.183368682861328, "learning_rate": 1.872246937080196e-05, "loss": 21.6892, "step": 777 }, { "epoch": 0.18252533954068073, "grad_norm": 24.456289291381836, "learning_rate": 1.8718775283006172e-05, "loss": 28.4723, "step": 778 }, { "epoch": 0.18275994794626002, "grad_norm": 17.869335174560547, "learning_rate": 1.871507622755961e-05, "loss": 25.8923, "step": 779 }, { "epoch": 0.18299455635183928, "grad_norm": 17.21109962463379, "learning_rate": 1.8711372206569864e-05, "loss": 27.0732, "step": 780 }, { "epoch": 0.18322916475741857, "grad_norm": 20.719884872436523, "learning_rate": 1.8707663222147356e-05, "loss": 29.8461, "step": 781 }, { "epoch": 0.18346377316299786, "grad_norm": 17.85472869873047, "learning_rate": 1.8703949276405336e-05, "loss": 25.5378, "step": 782 }, { "epoch": 0.18369838156857712, "grad_norm": 18.765750885009766, "learning_rate": 1.8700230371459878e-05, "loss": 29.0814, "step": 783 }, { "epoch": 0.1839329899741564, "grad_norm": 21.249225616455078, "learning_rate": 1.8696506509429883e-05, "loss": 31.069, "step": 784 }, { "epoch": 0.1841675983797357, "grad_norm": 18.14116096496582, "learning_rate": 1.8692777692437073e-05, "loss": 27.5721, "step": 785 }, { "epoch": 0.184402206785315, "grad_norm": 17.33694076538086, "learning_rate": 1.8689043922606e-05, "loss": 25.5878, "step": 786 }, { "epoch": 0.18463681519089425, "grad_norm": 19.634098052978516, "learning_rate": 1.8685305202064032e-05, "loss": 21.6597, "step": 787 }, { "epoch": 0.18487142359647354, "grad_norm": 21.378475189208984, "learning_rate": 1.8681561532941364e-05, "loss": 25.8157, "step": 788 }, { "epoch": 0.18510603200205283, "grad_norm": 19.534257888793945, "learning_rate": 1.8677812917371006e-05, "loss": 25.6891, "step": 789 }, { "epoch": 0.1853406404076321, "grad_norm": 20.39165687561035, "learning_rate": 1.8674059357488784e-05, "loss": 22.8434, "step": 790 }, { "epoch": 0.18557524881321139, "grad_norm": 20.231882095336914, "learning_rate": 1.8670300855433345e-05, "loss": 27.905, "step": 791 }, { "epoch": 0.18580985721879067, "grad_norm": 19.66605567932129, "learning_rate": 1.8666537413346152e-05, "loss": 22.3171, "step": 792 }, { "epoch": 0.18604446562436994, "grad_norm": 20.53923988342285, "learning_rate": 1.866276903337148e-05, "loss": 27.9006, "step": 793 }, { "epoch": 0.18627907402994923, "grad_norm": 18.2153377532959, "learning_rate": 1.8658995717656422e-05, "loss": 25.0599, "step": 794 }, { "epoch": 0.18651368243552852, "grad_norm": 19.390113830566406, "learning_rate": 1.865521746835088e-05, "loss": 25.7281, "step": 795 }, { "epoch": 0.18674829084110778, "grad_norm": 21.099395751953125, "learning_rate": 1.8651434287607563e-05, "loss": 27.2254, "step": 796 }, { "epoch": 0.18698289924668707, "grad_norm": 17.699785232543945, "learning_rate": 1.8647646177581996e-05, "loss": 23.117, "step": 797 }, { "epoch": 0.18721750765226636, "grad_norm": 19.14929962158203, "learning_rate": 1.864385314043251e-05, "loss": 24.392, "step": 798 }, { "epoch": 0.18745211605784565, "grad_norm": 19.63129997253418, "learning_rate": 1.864005517832025e-05, "loss": 27.3735, "step": 799 }, { "epoch": 0.1876867244634249, "grad_norm": 20.571443557739258, "learning_rate": 1.8636252293409152e-05, "loss": 23.0647, "step": 800 }, { "epoch": 0.1879213328690042, "grad_norm": 19.580738067626953, "learning_rate": 1.863244448786597e-05, "loss": 26.238, "step": 801 }, { "epoch": 0.1881559412745835, "grad_norm": 18.87300682067871, "learning_rate": 1.862863176386026e-05, "loss": 27.3674, "step": 802 }, { "epoch": 0.18839054968016275, "grad_norm": 17.22671127319336, "learning_rate": 1.8624814123564373e-05, "loss": 30.3368, "step": 803 }, { "epoch": 0.18862515808574204, "grad_norm": 25.93787956237793, "learning_rate": 1.8620991569153467e-05, "loss": 29.8232, "step": 804 }, { "epoch": 0.18885976649132133, "grad_norm": 21.736347198486328, "learning_rate": 1.8617164102805504e-05, "loss": 29.2995, "step": 805 }, { "epoch": 0.1890943748969006, "grad_norm": 18.61472511291504, "learning_rate": 1.861333172670123e-05, "loss": 27.0978, "step": 806 }, { "epoch": 0.18932898330247988, "grad_norm": 20.805192947387695, "learning_rate": 1.8609494443024204e-05, "loss": 27.3251, "step": 807 }, { "epoch": 0.18956359170805917, "grad_norm": 18.52741241455078, "learning_rate": 1.860565225396077e-05, "loss": 24.3603, "step": 808 }, { "epoch": 0.18979820011363846, "grad_norm": 18.909889221191406, "learning_rate": 1.8601805161700083e-05, "loss": 26.3065, "step": 809 }, { "epoch": 0.19003280851921772, "grad_norm": 17.21445083618164, "learning_rate": 1.859795316843407e-05, "loss": 25.7021, "step": 810 }, { "epoch": 0.190267416924797, "grad_norm": 21.658124923706055, "learning_rate": 1.8594096276357463e-05, "loss": 28.5216, "step": 811 }, { "epoch": 0.1905020253303763, "grad_norm": 18.74835777282715, "learning_rate": 1.8590234487667784e-05, "loss": 24.433, "step": 812 }, { "epoch": 0.19073663373595556, "grad_norm": 17.362485885620117, "learning_rate": 1.8586367804565343e-05, "loss": 24.7619, "step": 813 }, { "epoch": 0.19097124214153485, "grad_norm": 20.51863670349121, "learning_rate": 1.858249622925324e-05, "loss": 25.6116, "step": 814 }, { "epoch": 0.19120585054711414, "grad_norm": 17.14267921447754, "learning_rate": 1.857861976393737e-05, "loss": 24.0655, "step": 815 }, { "epoch": 0.1914404589526934, "grad_norm": 19.398456573486328, "learning_rate": 1.8574738410826393e-05, "loss": 27.0708, "step": 816 }, { "epoch": 0.1916750673582727, "grad_norm": 16.89520263671875, "learning_rate": 1.8570852172131776e-05, "loss": 23.7436, "step": 817 }, { "epoch": 0.19190967576385198, "grad_norm": 20.418800354003906, "learning_rate": 1.8566961050067755e-05, "loss": 27.603, "step": 818 }, { "epoch": 0.19214428416943125, "grad_norm": 17.72942543029785, "learning_rate": 1.856306504685136e-05, "loss": 25.0395, "step": 819 }, { "epoch": 0.19237889257501053, "grad_norm": 19.351613998413086, "learning_rate": 1.8559164164702394e-05, "loss": 25.9025, "step": 820 }, { "epoch": 0.19261350098058982, "grad_norm": 18.26062774658203, "learning_rate": 1.8555258405843443e-05, "loss": 23.3307, "step": 821 }, { "epoch": 0.19284810938616911, "grad_norm": 17.978919982910156, "learning_rate": 1.8551347772499864e-05, "loss": 29.3456, "step": 822 }, { "epoch": 0.19308271779174838, "grad_norm": 18.568317413330078, "learning_rate": 1.8547432266899806e-05, "loss": 28.2079, "step": 823 }, { "epoch": 0.19331732619732767, "grad_norm": 16.05536651611328, "learning_rate": 1.8543511891274186e-05, "loss": 27.3747, "step": 824 }, { "epoch": 0.19355193460290696, "grad_norm": 16.0697021484375, "learning_rate": 1.853958664785669e-05, "loss": 23.528, "step": 825 }, { "epoch": 0.19378654300848622, "grad_norm": 17.225454330444336, "learning_rate": 1.853565653888379e-05, "loss": 27.9522, "step": 826 }, { "epoch": 0.1940211514140655, "grad_norm": 20.569656372070312, "learning_rate": 1.853172156659472e-05, "loss": 21.7688, "step": 827 }, { "epoch": 0.1942557598196448, "grad_norm": 19.636363983154297, "learning_rate": 1.8527781733231486e-05, "loss": 20.5468, "step": 828 }, { "epoch": 0.19449036822522406, "grad_norm": 22.51970863342285, "learning_rate": 1.852383704103887e-05, "loss": 30.5366, "step": 829 }, { "epoch": 0.19472497663080335, "grad_norm": 18.15575408935547, "learning_rate": 1.8519887492264415e-05, "loss": 30.6569, "step": 830 }, { "epoch": 0.19495958503638264, "grad_norm": 23.936668395996094, "learning_rate": 1.851593308915844e-05, "loss": 25.7686, "step": 831 }, { "epoch": 0.1951941934419619, "grad_norm": 19.920400619506836, "learning_rate": 1.851197383397402e-05, "loss": 27.7317, "step": 832 }, { "epoch": 0.1954288018475412, "grad_norm": 19.049123764038086, "learning_rate": 1.8508009728967e-05, "loss": 32.0667, "step": 833 }, { "epoch": 0.19566341025312048, "grad_norm": 15.88101863861084, "learning_rate": 1.850404077639599e-05, "loss": 22.7056, "step": 834 }, { "epoch": 0.19589801865869977, "grad_norm": 27.70378303527832, "learning_rate": 1.8500066978522357e-05, "loss": 28.2184, "step": 835 }, { "epoch": 0.19613262706427903, "grad_norm": 19.69417953491211, "learning_rate": 1.849608833761023e-05, "loss": 26.322, "step": 836 }, { "epoch": 0.19636723546985832, "grad_norm": 19.271854400634766, "learning_rate": 1.84921048559265e-05, "loss": 24.8422, "step": 837 }, { "epoch": 0.1966018438754376, "grad_norm": 18.781709671020508, "learning_rate": 1.8488116535740815e-05, "loss": 27.156, "step": 838 }, { "epoch": 0.19683645228101687, "grad_norm": 18.68931770324707, "learning_rate": 1.8484123379325573e-05, "loss": 29.9041, "step": 839 }, { "epoch": 0.19707106068659616, "grad_norm": 20.776308059692383, "learning_rate": 1.8480125388955945e-05, "loss": 25.0284, "step": 840 }, { "epoch": 0.19730566909217545, "grad_norm": 21.45889663696289, "learning_rate": 1.8476122566909835e-05, "loss": 30.186, "step": 841 }, { "epoch": 0.1975402774977547, "grad_norm": 20.907794952392578, "learning_rate": 1.8472114915467914e-05, "loss": 26.9774, "step": 842 }, { "epoch": 0.197774885903334, "grad_norm": 21.25614356994629, "learning_rate": 1.8468102436913603e-05, "loss": 30.584, "step": 843 }, { "epoch": 0.1980094943089133, "grad_norm": 21.49897003173828, "learning_rate": 1.8464085133533064e-05, "loss": 26.5806, "step": 844 }, { "epoch": 0.19824410271449255, "grad_norm": 18.37041664123535, "learning_rate": 1.8460063007615218e-05, "loss": 25.2541, "step": 845 }, { "epoch": 0.19847871112007184, "grad_norm": 22.569997787475586, "learning_rate": 1.8456036061451735e-05, "loss": 26.0696, "step": 846 }, { "epoch": 0.19871331952565113, "grad_norm": 17.864656448364258, "learning_rate": 1.8452004297337018e-05, "loss": 24.7645, "step": 847 }, { "epoch": 0.19894792793123042, "grad_norm": 17.917343139648438, "learning_rate": 1.8447967717568234e-05, "loss": 26.4057, "step": 848 }, { "epoch": 0.19918253633680968, "grad_norm": 20.345918655395508, "learning_rate": 1.8443926324445277e-05, "loss": 25.7533, "step": 849 }, { "epoch": 0.19941714474238897, "grad_norm": 18.733922958374023, "learning_rate": 1.8439880120270796e-05, "loss": 24.3955, "step": 850 }, { "epoch": 0.19965175314796826, "grad_norm": 18.680967330932617, "learning_rate": 1.8435829107350167e-05, "loss": 25.0194, "step": 851 }, { "epoch": 0.19988636155354753, "grad_norm": 15.73671817779541, "learning_rate": 1.843177328799152e-05, "loss": 22.8187, "step": 852 }, { "epoch": 0.20012096995912682, "grad_norm": 18.617366790771484, "learning_rate": 1.842771266450572e-05, "loss": 25.826, "step": 853 }, { "epoch": 0.2003555783647061, "grad_norm": 22.079425811767578, "learning_rate": 1.8423647239206363e-05, "loss": 29.4033, "step": 854 }, { "epoch": 0.20059018677028537, "grad_norm": 22.662485122680664, "learning_rate": 1.8419577014409785e-05, "loss": 23.5524, "step": 855 }, { "epoch": 0.20082479517586466, "grad_norm": 17.649452209472656, "learning_rate": 1.8415501992435056e-05, "loss": 26.2037, "step": 856 }, { "epoch": 0.20105940358144395, "grad_norm": 21.12175941467285, "learning_rate": 1.8411422175603985e-05, "loss": 28.6362, "step": 857 }, { "epoch": 0.20129401198702324, "grad_norm": 19.913135528564453, "learning_rate": 1.8407337566241102e-05, "loss": 25.2413, "step": 858 }, { "epoch": 0.2015286203926025, "grad_norm": 20.572158813476562, "learning_rate": 1.840324816667368e-05, "loss": 30.791, "step": 859 }, { "epoch": 0.2017632287981818, "grad_norm": 22.100460052490234, "learning_rate": 1.839915397923171e-05, "loss": 25.8434, "step": 860 }, { "epoch": 0.20199783720376108, "grad_norm": 20.810401916503906, "learning_rate": 1.8395055006247915e-05, "loss": 23.7175, "step": 861 }, { "epoch": 0.20223244560934034, "grad_norm": 15.988489151000977, "learning_rate": 1.8390951250057746e-05, "loss": 23.285, "step": 862 }, { "epoch": 0.20246705401491963, "grad_norm": 18.083354949951172, "learning_rate": 1.838684271299938e-05, "loss": 27.6564, "step": 863 }, { "epoch": 0.20270166242049892, "grad_norm": 19.515363693237305, "learning_rate": 1.8382729397413715e-05, "loss": 29.3327, "step": 864 }, { "epoch": 0.20293627082607818, "grad_norm": 21.09894561767578, "learning_rate": 1.8378611305644372e-05, "loss": 25.3143, "step": 865 }, { "epoch": 0.20317087923165747, "grad_norm": 21.476703643798828, "learning_rate": 1.8374488440037698e-05, "loss": 30.6949, "step": 866 }, { "epoch": 0.20340548763723676, "grad_norm": 17.534025192260742, "learning_rate": 1.8370360802942758e-05, "loss": 22.4875, "step": 867 }, { "epoch": 0.20364009604281602, "grad_norm": 18.725940704345703, "learning_rate": 1.8366228396711327e-05, "loss": 25.6192, "step": 868 }, { "epoch": 0.2038747044483953, "grad_norm": 19.153018951416016, "learning_rate": 1.836209122369791e-05, "loss": 31.2181, "step": 869 }, { "epoch": 0.2041093128539746, "grad_norm": 18.94196891784668, "learning_rate": 1.835794928625972e-05, "loss": 25.2581, "step": 870 }, { "epoch": 0.2043439212595539, "grad_norm": 20.013160705566406, "learning_rate": 1.835380258675669e-05, "loss": 27.6495, "step": 871 }, { "epoch": 0.20457852966513315, "grad_norm": 20.713930130004883, "learning_rate": 1.8349651127551457e-05, "loss": 26.3388, "step": 872 }, { "epoch": 0.20481313807071244, "grad_norm": 20.365718841552734, "learning_rate": 1.8345494911009382e-05, "loss": 28.0179, "step": 873 }, { "epoch": 0.20504774647629173, "grad_norm": 17.88517189025879, "learning_rate": 1.834133393949853e-05, "loss": 23.8237, "step": 874 }, { "epoch": 0.205282354881871, "grad_norm": 20.450613021850586, "learning_rate": 1.833716821538967e-05, "loss": 26.848, "step": 875 }, { "epoch": 0.20551696328745028, "grad_norm": 19.161096572875977, "learning_rate": 1.8332997741056292e-05, "loss": 26.0487, "step": 876 }, { "epoch": 0.20575157169302957, "grad_norm": 24.65115737915039, "learning_rate": 1.8328822518874582e-05, "loss": 24.8998, "step": 877 }, { "epoch": 0.20598618009860883, "grad_norm": 17.91313934326172, "learning_rate": 1.8324642551223437e-05, "loss": 23.8403, "step": 878 }, { "epoch": 0.20622078850418812, "grad_norm": 18.540998458862305, "learning_rate": 1.8320457840484452e-05, "loss": 26.7275, "step": 879 }, { "epoch": 0.2064553969097674, "grad_norm": 19.734079360961914, "learning_rate": 1.8316268389041926e-05, "loss": 27.825, "step": 880 }, { "epoch": 0.20669000531534668, "grad_norm": 17.447471618652344, "learning_rate": 1.8312074199282864e-05, "loss": 23.9531, "step": 881 }, { "epoch": 0.20692461372092597, "grad_norm": 18.354637145996094, "learning_rate": 1.8307875273596968e-05, "loss": 19.3309, "step": 882 }, { "epoch": 0.20715922212650525, "grad_norm": 16.01445770263672, "learning_rate": 1.830367161437664e-05, "loss": 23.3525, "step": 883 }, { "epoch": 0.20739383053208454, "grad_norm": 18.60161590576172, "learning_rate": 1.829946322401697e-05, "loss": 28.5689, "step": 884 }, { "epoch": 0.2076284389376638, "grad_norm": 18.174320220947266, "learning_rate": 1.8295250104915755e-05, "loss": 27.247, "step": 885 }, { "epoch": 0.2078630473432431, "grad_norm": 18.985698699951172, "learning_rate": 1.829103225947348e-05, "loss": 23.809, "step": 886 }, { "epoch": 0.20809765574882239, "grad_norm": 16.983766555786133, "learning_rate": 1.8286809690093325e-05, "loss": 28.8492, "step": 887 }, { "epoch": 0.20833226415440165, "grad_norm": 16.895164489746094, "learning_rate": 1.828258239918116e-05, "loss": 25.7822, "step": 888 }, { "epoch": 0.20856687255998094, "grad_norm": 21.10264015197754, "learning_rate": 1.827835038914555e-05, "loss": 27.4488, "step": 889 }, { "epoch": 0.20880148096556023, "grad_norm": 15.861039161682129, "learning_rate": 1.8274113662397743e-05, "loss": 26.1269, "step": 890 }, { "epoch": 0.2090360893711395, "grad_norm": 16.355131149291992, "learning_rate": 1.8269872221351677e-05, "loss": 22.1805, "step": 891 }, { "epoch": 0.20927069777671878, "grad_norm": 20.815275192260742, "learning_rate": 1.8265626068423977e-05, "loss": 25.8226, "step": 892 }, { "epoch": 0.20950530618229807, "grad_norm": 18.03645896911621, "learning_rate": 1.8261375206033943e-05, "loss": 26.1765, "step": 893 }, { "epoch": 0.20973991458787736, "grad_norm": 20.738994598388672, "learning_rate": 1.825711963660358e-05, "loss": 25.3174, "step": 894 }, { "epoch": 0.20997452299345662, "grad_norm": 19.602617263793945, "learning_rate": 1.825285936255755e-05, "loss": 29.2239, "step": 895 }, { "epoch": 0.2102091313990359, "grad_norm": 22.130678176879883, "learning_rate": 1.824859438632321e-05, "loss": 26.6909, "step": 896 }, { "epoch": 0.2104437398046152, "grad_norm": 21.097965240478516, "learning_rate": 1.8244324710330598e-05, "loss": 24.4423, "step": 897 }, { "epoch": 0.21067834821019446, "grad_norm": 16.322509765625, "learning_rate": 1.824005033701242e-05, "loss": 29.8717, "step": 898 }, { "epoch": 0.21091295661577375, "grad_norm": 18.582996368408203, "learning_rate": 1.8235771268804062e-05, "loss": 24.6697, "step": 899 }, { "epoch": 0.21114756502135304, "grad_norm": 21.427244186401367, "learning_rate": 1.823148750814359e-05, "loss": 25.1944, "step": 900 }, { "epoch": 0.2113821734269323, "grad_norm": 17.954784393310547, "learning_rate": 1.822719905747174e-05, "loss": 26.3605, "step": 901 }, { "epoch": 0.2116167818325116, "grad_norm": 20.397336959838867, "learning_rate": 1.8222905919231916e-05, "loss": 25.864, "step": 902 }, { "epoch": 0.21185139023809088, "grad_norm": 22.43061065673828, "learning_rate": 1.82186080958702e-05, "loss": 25.0052, "step": 903 }, { "epoch": 0.21208599864367014, "grad_norm": 21.116228103637695, "learning_rate": 1.8214305589835343e-05, "loss": 29.1359, "step": 904 }, { "epoch": 0.21232060704924943, "grad_norm": 17.25336265563965, "learning_rate": 1.8209998403578753e-05, "loss": 25.0158, "step": 905 }, { "epoch": 0.21255521545482872, "grad_norm": 16.771961212158203, "learning_rate": 1.8205686539554518e-05, "loss": 23.4766, "step": 906 }, { "epoch": 0.212789823860408, "grad_norm": 22.23583984375, "learning_rate": 1.8201370000219388e-05, "loss": 26.2878, "step": 907 }, { "epoch": 0.21302443226598727, "grad_norm": 18.451658248901367, "learning_rate": 1.8197048788032773e-05, "loss": 26.4687, "step": 908 }, { "epoch": 0.21325904067156656, "grad_norm": 18.847820281982422, "learning_rate": 1.819272290545674e-05, "loss": 30.5105, "step": 909 }, { "epoch": 0.21349364907714585, "grad_norm": 20.652130126953125, "learning_rate": 1.818839235495604e-05, "loss": 28.4453, "step": 910 }, { "epoch": 0.21372825748272511, "grad_norm": 15.388898849487305, "learning_rate": 1.8184057138998056e-05, "loss": 20.2147, "step": 911 }, { "epoch": 0.2139628658883044, "grad_norm": 21.566232681274414, "learning_rate": 1.8179717260052845e-05, "loss": 28.0777, "step": 912 }, { "epoch": 0.2141974742938837, "grad_norm": 17.585697174072266, "learning_rate": 1.8175372720593113e-05, "loss": 24.1623, "step": 913 }, { "epoch": 0.21443208269946296, "grad_norm": 17.526308059692383, "learning_rate": 1.8171023523094235e-05, "loss": 20.9009, "step": 914 }, { "epoch": 0.21466669110504225, "grad_norm": 15.96146297454834, "learning_rate": 1.816666967003422e-05, "loss": 25.3311, "step": 915 }, { "epoch": 0.21490129951062154, "grad_norm": 15.686137199401855, "learning_rate": 1.8162311163893744e-05, "loss": 20.5369, "step": 916 }, { "epoch": 0.2151359079162008, "grad_norm": 17.222177505493164, "learning_rate": 1.8157948007156133e-05, "loss": 24.5487, "step": 917 }, { "epoch": 0.2153705163217801, "grad_norm": 19.083227157592773, "learning_rate": 1.815358020230736e-05, "loss": 28.1987, "step": 918 }, { "epoch": 0.21560512472735938, "grad_norm": 16.980632781982422, "learning_rate": 1.814920775183604e-05, "loss": 26.1201, "step": 919 }, { "epoch": 0.21583973313293867, "grad_norm": 15.543670654296875, "learning_rate": 1.8144830658233442e-05, "loss": 19.1074, "step": 920 }, { "epoch": 0.21607434153851793, "grad_norm": 18.85088539123535, "learning_rate": 1.8140448923993488e-05, "loss": 27.4404, "step": 921 }, { "epoch": 0.21630894994409722, "grad_norm": 19.947216033935547, "learning_rate": 1.8136062551612728e-05, "loss": 29.1329, "step": 922 }, { "epoch": 0.2165435583496765, "grad_norm": 19.69021224975586, "learning_rate": 1.8131671543590362e-05, "loss": 27.7728, "step": 923 }, { "epoch": 0.21677816675525577, "grad_norm": 17.798004150390625, "learning_rate": 1.8127275902428235e-05, "loss": 24.8019, "step": 924 }, { "epoch": 0.21701277516083506, "grad_norm": 17.667295455932617, "learning_rate": 1.812287563063083e-05, "loss": 27.9107, "step": 925 }, { "epoch": 0.21724738356641435, "grad_norm": 25.872089385986328, "learning_rate": 1.811847073070526e-05, "loss": 25.656, "step": 926 }, { "epoch": 0.2174819919719936, "grad_norm": 18.750627517700195, "learning_rate": 1.811406120516129e-05, "loss": 25.7748, "step": 927 }, { "epoch": 0.2177166003775729, "grad_norm": 17.24166488647461, "learning_rate": 1.8109647056511303e-05, "loss": 22.4907, "step": 928 }, { "epoch": 0.2179512087831522, "grad_norm": 18.445301055908203, "learning_rate": 1.8105228287270337e-05, "loss": 25.035, "step": 929 }, { "epoch": 0.21818581718873145, "grad_norm": 17.578439712524414, "learning_rate": 1.810080489995604e-05, "loss": 27.7379, "step": 930 }, { "epoch": 0.21842042559431074, "grad_norm": 19.70942497253418, "learning_rate": 1.8096376897088704e-05, "loss": 26.027, "step": 931 }, { "epoch": 0.21865503399989003, "grad_norm": 18.799476623535156, "learning_rate": 1.8091944281191254e-05, "loss": 26.2257, "step": 932 }, { "epoch": 0.21888964240546932, "grad_norm": 17.426822662353516, "learning_rate": 1.8087507054789234e-05, "loss": 24.1001, "step": 933 }, { "epoch": 0.21912425081104858, "grad_norm": 17.87693977355957, "learning_rate": 1.808306522041082e-05, "loss": 25.0448, "step": 934 }, { "epoch": 0.21935885921662787, "grad_norm": 19.914674758911133, "learning_rate": 1.807861878058682e-05, "loss": 25.8868, "step": 935 }, { "epoch": 0.21959346762220716, "grad_norm": 20.251432418823242, "learning_rate": 1.8074167737850645e-05, "loss": 25.5816, "step": 936 }, { "epoch": 0.21982807602778642, "grad_norm": 19.92068862915039, "learning_rate": 1.8069712094738352e-05, "loss": 28.2295, "step": 937 }, { "epoch": 0.2200626844333657, "grad_norm": 19.777793884277344, "learning_rate": 1.8065251853788605e-05, "loss": 22.8431, "step": 938 }, { "epoch": 0.220297292838945, "grad_norm": 20.91423797607422, "learning_rate": 1.8060787017542692e-05, "loss": 28.9705, "step": 939 }, { "epoch": 0.22053190124452426, "grad_norm": 22.60397720336914, "learning_rate": 1.8056317588544528e-05, "loss": 28.2445, "step": 940 }, { "epoch": 0.22076650965010355, "grad_norm": 19.63265609741211, "learning_rate": 1.8051843569340622e-05, "loss": 28.3339, "step": 941 }, { "epoch": 0.22100111805568284, "grad_norm": 17.915756225585938, "learning_rate": 1.8047364962480124e-05, "loss": 23.8126, "step": 942 }, { "epoch": 0.22123572646126213, "grad_norm": 20.162353515625, "learning_rate": 1.8042881770514777e-05, "loss": 25.3781, "step": 943 }, { "epoch": 0.2214703348668414, "grad_norm": 18.937427520751953, "learning_rate": 1.8038393995998952e-05, "loss": 23.5692, "step": 944 }, { "epoch": 0.22170494327242068, "grad_norm": 18.24896812438965, "learning_rate": 1.8033901641489625e-05, "loss": 28.0195, "step": 945 }, { "epoch": 0.22193955167799997, "grad_norm": 20.53852653503418, "learning_rate": 1.8029404709546376e-05, "loss": 29.9829, "step": 946 }, { "epoch": 0.22217416008357924, "grad_norm": 20.334819793701172, "learning_rate": 1.8024903202731402e-05, "loss": 23.558, "step": 947 }, { "epoch": 0.22240876848915853, "grad_norm": 18.25936508178711, "learning_rate": 1.8020397123609506e-05, "loss": 27.9539, "step": 948 }, { "epoch": 0.22264337689473782, "grad_norm": 18.338268280029297, "learning_rate": 1.801588647474809e-05, "loss": 23.6409, "step": 949 }, { "epoch": 0.22287798530031708, "grad_norm": 18.97005271911621, "learning_rate": 1.8011371258717156e-05, "loss": 27.3525, "step": 950 }, { "epoch": 0.22311259370589637, "grad_norm": 17.781597137451172, "learning_rate": 1.8006851478089324e-05, "loss": 27.0696, "step": 951 }, { "epoch": 0.22334720211147566, "grad_norm": 18.77457046508789, "learning_rate": 1.8002327135439802e-05, "loss": 25.0658, "step": 952 }, { "epoch": 0.22358181051705492, "grad_norm": 17.90547752380371, "learning_rate": 1.7997798233346403e-05, "loss": 27.6982, "step": 953 }, { "epoch": 0.2238164189226342, "grad_norm": 17.146936416625977, "learning_rate": 1.7993264774389536e-05, "loss": 27.0945, "step": 954 }, { "epoch": 0.2240510273282135, "grad_norm": 18.96963882446289, "learning_rate": 1.7988726761152203e-05, "loss": 30.4455, "step": 955 }, { "epoch": 0.2242856357337928, "grad_norm": 25.500608444213867, "learning_rate": 1.7984184196220003e-05, "loss": 28.0769, "step": 956 }, { "epoch": 0.22452024413937205, "grad_norm": 18.998058319091797, "learning_rate": 1.7979637082181137e-05, "loss": 28.5427, "step": 957 }, { "epoch": 0.22475485254495134, "grad_norm": 21.803913116455078, "learning_rate": 1.7975085421626383e-05, "loss": 25.9122, "step": 958 }, { "epoch": 0.22498946095053063, "grad_norm": 21.0700626373291, "learning_rate": 1.7970529217149116e-05, "loss": 28.5547, "step": 959 }, { "epoch": 0.2252240693561099, "grad_norm": 17.663599014282227, "learning_rate": 1.7965968471345303e-05, "loss": 23.5483, "step": 960 }, { "epoch": 0.22545867776168918, "grad_norm": 20.116533279418945, "learning_rate": 1.79614031868135e-05, "loss": 24.1839, "step": 961 }, { "epoch": 0.22569328616726847, "grad_norm": 19.14266014099121, "learning_rate": 1.795683336615484e-05, "loss": 26.7783, "step": 962 }, { "epoch": 0.22592789457284773, "grad_norm": 21.072307586669922, "learning_rate": 1.7952259011973047e-05, "loss": 26.9987, "step": 963 }, { "epoch": 0.22616250297842702, "grad_norm": 16.161823272705078, "learning_rate": 1.7947680126874432e-05, "loss": 24.0632, "step": 964 }, { "epoch": 0.2263971113840063, "grad_norm": 18.606950759887695, "learning_rate": 1.7943096713467873e-05, "loss": 20.6578, "step": 965 }, { "epoch": 0.22663171978958557, "grad_norm": 20.15447425842285, "learning_rate": 1.7938508774364842e-05, "loss": 27.0411, "step": 966 }, { "epoch": 0.22686632819516486, "grad_norm": 20.33567237854004, "learning_rate": 1.7933916312179388e-05, "loss": 25.8725, "step": 967 }, { "epoch": 0.22710093660074415, "grad_norm": 23.825176239013672, "learning_rate": 1.792931932952813e-05, "loss": 27.3914, "step": 968 }, { "epoch": 0.22733554500632344, "grad_norm": 22.150712966918945, "learning_rate": 1.7924717829030266e-05, "loss": 24.8598, "step": 969 }, { "epoch": 0.2275701534119027, "grad_norm": 24.781248092651367, "learning_rate": 1.792011181330757e-05, "loss": 30.7366, "step": 970 }, { "epoch": 0.227804761817482, "grad_norm": 18.983884811401367, "learning_rate": 1.791550128498439e-05, "loss": 27.2533, "step": 971 }, { "epoch": 0.22803937022306128, "grad_norm": 17.5028076171875, "learning_rate": 1.7910886246687633e-05, "loss": 23.714, "step": 972 }, { "epoch": 0.22827397862864054, "grad_norm": 21.31465721130371, "learning_rate": 1.79062667010468e-05, "loss": 28.2269, "step": 973 }, { "epoch": 0.22850858703421983, "grad_norm": 17.528247833251953, "learning_rate": 1.7901642650693935e-05, "loss": 23.0475, "step": 974 }, { "epoch": 0.22874319543979912, "grad_norm": 19.578763961791992, "learning_rate": 1.7897014098263662e-05, "loss": 28.138, "step": 975 }, { "epoch": 0.22897780384537839, "grad_norm": 18.836748123168945, "learning_rate": 1.7892381046393166e-05, "loss": 25.142, "step": 976 }, { "epoch": 0.22921241225095768, "grad_norm": 20.425540924072266, "learning_rate": 1.78877434977222e-05, "loss": 29.1059, "step": 977 }, { "epoch": 0.22944702065653697, "grad_norm": 16.978397369384766, "learning_rate": 1.7883101454893065e-05, "loss": 25.6644, "step": 978 }, { "epoch": 0.22968162906211625, "grad_norm": 22.8728084564209, "learning_rate": 1.7878454920550646e-05, "loss": 24.1054, "step": 979 }, { "epoch": 0.22991623746769552, "grad_norm": 20.04427719116211, "learning_rate": 1.787380389734237e-05, "loss": 24.9831, "step": 980 }, { "epoch": 0.2301508458732748, "grad_norm": 17.18351173400879, "learning_rate": 1.7869148387918226e-05, "loss": 25.5343, "step": 981 }, { "epoch": 0.2303854542788541, "grad_norm": 20.426002502441406, "learning_rate": 1.786448839493076e-05, "loss": 26.8497, "step": 982 }, { "epoch": 0.23062006268443336, "grad_norm": 19.92928695678711, "learning_rate": 1.785982392103507e-05, "loss": 30.4379, "step": 983 }, { "epoch": 0.23085467109001265, "grad_norm": 18.9853458404541, "learning_rate": 1.7855154968888807e-05, "loss": 24.5696, "step": 984 }, { "epoch": 0.23108927949559194, "grad_norm": 16.806995391845703, "learning_rate": 1.7850481541152178e-05, "loss": 26.4, "step": 985 }, { "epoch": 0.2313238879011712, "grad_norm": 19.279024124145508, "learning_rate": 1.7845803640487937e-05, "loss": 25.2143, "step": 986 }, { "epoch": 0.2315584963067505, "grad_norm": 19.811870574951172, "learning_rate": 1.7841121269561386e-05, "loss": 26.0135, "step": 987 }, { "epoch": 0.23179310471232978, "grad_norm": 19.69755744934082, "learning_rate": 1.7836434431040376e-05, "loss": 29.8299, "step": 988 }, { "epoch": 0.23202771311790904, "grad_norm": 18.894323348999023, "learning_rate": 1.7831743127595303e-05, "loss": 24.7837, "step": 989 }, { "epoch": 0.23226232152348833, "grad_norm": 17.86205291748047, "learning_rate": 1.782704736189911e-05, "loss": 27.7895, "step": 990 }, { "epoch": 0.23249692992906762, "grad_norm": 23.459190368652344, "learning_rate": 1.7822347136627264e-05, "loss": 26.6308, "step": 991 }, { "epoch": 0.2327315383346469, "grad_norm": 17.537574768066406, "learning_rate": 1.7817642454457803e-05, "loss": 23.8489, "step": 992 }, { "epoch": 0.23296614674022617, "grad_norm": 18.856229782104492, "learning_rate": 1.7812933318071287e-05, "loss": 22.8176, "step": 993 }, { "epoch": 0.23320075514580546, "grad_norm": 22.899288177490234, "learning_rate": 1.780821973015081e-05, "loss": 27.0757, "step": 994 }, { "epoch": 0.23343536355138475, "grad_norm": 19.937713623046875, "learning_rate": 1.7803501693382007e-05, "loss": 25.3346, "step": 995 }, { "epoch": 0.233669971956964, "grad_norm": 18.127452850341797, "learning_rate": 1.779877921045306e-05, "loss": 26.7951, "step": 996 }, { "epoch": 0.2339045803625433, "grad_norm": 21.278127670288086, "learning_rate": 1.7794052284054662e-05, "loss": 27.2483, "step": 997 }, { "epoch": 0.2341391887681226, "grad_norm": 18.514060974121094, "learning_rate": 1.7789320916880054e-05, "loss": 25.9732, "step": 998 }, { "epoch": 0.23437379717370185, "grad_norm": 18.958101272583008, "learning_rate": 1.7784585111625002e-05, "loss": 25.4732, "step": 999 }, { "epoch": 0.23460840557928114, "grad_norm": 16.49703025817871, "learning_rate": 1.7779844870987797e-05, "loss": 23.5142, "step": 1000 }, { "epoch": 0.23484301398486043, "grad_norm": 19.231876373291016, "learning_rate": 1.777510019766927e-05, "loss": 29.2407, "step": 1001 }, { "epoch": 0.2350776223904397, "grad_norm": 17.34872055053711, "learning_rate": 1.7770351094372756e-05, "loss": 29.8157, "step": 1002 }, { "epoch": 0.23531223079601898, "grad_norm": 21.142436981201172, "learning_rate": 1.7765597563804137e-05, "loss": 31.8342, "step": 1003 }, { "epoch": 0.23554683920159827, "grad_norm": 18.18958854675293, "learning_rate": 1.7760839608671806e-05, "loss": 27.7932, "step": 1004 }, { "epoch": 0.23578144760717756, "grad_norm": 21.198143005371094, "learning_rate": 1.7756077231686674e-05, "loss": 25.5194, "step": 1005 }, { "epoch": 0.23601605601275683, "grad_norm": 19.662567138671875, "learning_rate": 1.7751310435562175e-05, "loss": 25.1686, "step": 1006 }, { "epoch": 0.23625066441833611, "grad_norm": 16.351451873779297, "learning_rate": 1.7746539223014268e-05, "loss": 26.4953, "step": 1007 }, { "epoch": 0.2364852728239154, "grad_norm": 21.722915649414062, "learning_rate": 1.7741763596761412e-05, "loss": 25.8832, "step": 1008 }, { "epoch": 0.23671988122949467, "grad_norm": 24.363201141357422, "learning_rate": 1.77369835595246e-05, "loss": 27.6543, "step": 1009 }, { "epoch": 0.23695448963507396, "grad_norm": 20.568256378173828, "learning_rate": 1.773219911402732e-05, "loss": 31.4105, "step": 1010 }, { "epoch": 0.23718909804065325, "grad_norm": 16.479904174804688, "learning_rate": 1.772741026299559e-05, "loss": 25.5154, "step": 1011 }, { "epoch": 0.2374237064462325, "grad_norm": 19.868349075317383, "learning_rate": 1.7722617009157922e-05, "loss": 30.1869, "step": 1012 }, { "epoch": 0.2376583148518118, "grad_norm": 19.215883255004883, "learning_rate": 1.7717819355245344e-05, "loss": 25.8944, "step": 1013 }, { "epoch": 0.2378929232573911, "grad_norm": 18.197202682495117, "learning_rate": 1.7713017303991388e-05, "loss": 25.6582, "step": 1014 }, { "epoch": 0.23812753166297035, "grad_norm": 24.04545783996582, "learning_rate": 1.77082108581321e-05, "loss": 28.6297, "step": 1015 }, { "epoch": 0.23836214006854964, "grad_norm": 21.048725128173828, "learning_rate": 1.7703400020406017e-05, "loss": 27.4561, "step": 1016 }, { "epoch": 0.23859674847412893, "grad_norm": 23.10136604309082, "learning_rate": 1.7698584793554187e-05, "loss": 30.7092, "step": 1017 }, { "epoch": 0.23883135687970822, "grad_norm": 18.765790939331055, "learning_rate": 1.7693765180320156e-05, "loss": 25.2819, "step": 1018 }, { "epoch": 0.23906596528528748, "grad_norm": 18.55715560913086, "learning_rate": 1.768894118344997e-05, "loss": 26.9803, "step": 1019 }, { "epoch": 0.23930057369086677, "grad_norm": 21.62534523010254, "learning_rate": 1.7684112805692178e-05, "loss": 23.5211, "step": 1020 }, { "epoch": 0.23953518209644606, "grad_norm": 17.762575149536133, "learning_rate": 1.7679280049797806e-05, "loss": 22.6693, "step": 1021 }, { "epoch": 0.23976979050202532, "grad_norm": 16.948486328125, "learning_rate": 1.7674442918520403e-05, "loss": 26.8327, "step": 1022 }, { "epoch": 0.2400043989076046, "grad_norm": 18.778776168823242, "learning_rate": 1.7669601414615984e-05, "loss": 22.4508, "step": 1023 }, { "epoch": 0.2402390073131839, "grad_norm": 17.71686363220215, "learning_rate": 1.7664755540843074e-05, "loss": 23.1321, "step": 1024 }, { "epoch": 0.24047361571876316, "grad_norm": 19.19123649597168, "learning_rate": 1.7659905299962678e-05, "loss": 22.7019, "step": 1025 }, { "epoch": 0.24070822412434245, "grad_norm": 28.459671020507812, "learning_rate": 1.7655050694738297e-05, "loss": 30.431, "step": 1026 }, { "epoch": 0.24094283252992174, "grad_norm": 21.954364776611328, "learning_rate": 1.7650191727935905e-05, "loss": 26.4807, "step": 1027 }, { "epoch": 0.24117744093550103, "grad_norm": 19.026391983032227, "learning_rate": 1.764532840232398e-05, "loss": 28.2343, "step": 1028 }, { "epoch": 0.2414120493410803, "grad_norm": 19.311376571655273, "learning_rate": 1.7640460720673465e-05, "loss": 29.9177, "step": 1029 }, { "epoch": 0.24164665774665958, "grad_norm": 19.148250579833984, "learning_rate": 1.76355886857578e-05, "loss": 26.2228, "step": 1030 }, { "epoch": 0.24188126615223887, "grad_norm": 17.944435119628906, "learning_rate": 1.7630712300352892e-05, "loss": 23.5379, "step": 1031 }, { "epoch": 0.24211587455781813, "grad_norm": 19.919994354248047, "learning_rate": 1.7625831567237143e-05, "loss": 26.1727, "step": 1032 }, { "epoch": 0.24235048296339742, "grad_norm": 25.02779197692871, "learning_rate": 1.7620946489191412e-05, "loss": 26.4958, "step": 1033 }, { "epoch": 0.2425850913689767, "grad_norm": 17.284482955932617, "learning_rate": 1.7616057068999055e-05, "loss": 24.2568, "step": 1034 }, { "epoch": 0.24281969977455597, "grad_norm": 17.073381423950195, "learning_rate": 1.7611163309445876e-05, "loss": 27.8604, "step": 1035 }, { "epoch": 0.24305430818013526, "grad_norm": 18.622249603271484, "learning_rate": 1.7606265213320185e-05, "loss": 28.4347, "step": 1036 }, { "epoch": 0.24328891658571455, "grad_norm": 30.65711212158203, "learning_rate": 1.7601362783412733e-05, "loss": 28.9268, "step": 1037 }, { "epoch": 0.24352352499129382, "grad_norm": 17.578388214111328, "learning_rate": 1.759645602251675e-05, "loss": 25.3722, "step": 1038 }, { "epoch": 0.2437581333968731, "grad_norm": 20.86069679260254, "learning_rate": 1.759154493342795e-05, "loss": 25.6975, "step": 1039 }, { "epoch": 0.2439927418024524, "grad_norm": 23.77337646484375, "learning_rate": 1.758662951894448e-05, "loss": 27.8605, "step": 1040 }, { "epoch": 0.24422735020803168, "grad_norm": 19.361736297607422, "learning_rate": 1.758170978186698e-05, "loss": 28.0678, "step": 1041 }, { "epoch": 0.24446195861361095, "grad_norm": 17.0189266204834, "learning_rate": 1.757678572499854e-05, "loss": 27.0169, "step": 1042 }, { "epoch": 0.24469656701919024, "grad_norm": 16.8466796875, "learning_rate": 1.7571857351144714e-05, "loss": 29.2796, "step": 1043 }, { "epoch": 0.24493117542476953, "grad_norm": 20.564491271972656, "learning_rate": 1.756692466311352e-05, "loss": 27.8682, "step": 1044 }, { "epoch": 0.2451657838303488, "grad_norm": 17.544828414916992, "learning_rate": 1.7561987663715424e-05, "loss": 26.1683, "step": 1045 }, { "epoch": 0.24540039223592808, "grad_norm": 18.49795913696289, "learning_rate": 1.7557046355763356e-05, "loss": 30.4072, "step": 1046 }, { "epoch": 0.24563500064150737, "grad_norm": 16.57126235961914, "learning_rate": 1.75521007420727e-05, "loss": 27.8903, "step": 1047 }, { "epoch": 0.24586960904708663, "grad_norm": 20.235231399536133, "learning_rate": 1.7547150825461292e-05, "loss": 26.9815, "step": 1048 }, { "epoch": 0.24610421745266592, "grad_norm": 16.169898986816406, "learning_rate": 1.754219660874942e-05, "loss": 26.1718, "step": 1049 }, { "epoch": 0.2463388258582452, "grad_norm": 20.087905883789062, "learning_rate": 1.7537238094759818e-05, "loss": 26.3174, "step": 1050 }, { "epoch": 0.24657343426382447, "grad_norm": 20.38924789428711, "learning_rate": 1.753227528631768e-05, "loss": 26.4097, "step": 1051 }, { "epoch": 0.24680804266940376, "grad_norm": 16.530202865600586, "learning_rate": 1.7527308186250635e-05, "loss": 25.2653, "step": 1052 }, { "epoch": 0.24704265107498305, "grad_norm": 18.959341049194336, "learning_rate": 1.7522336797388765e-05, "loss": 28.8701, "step": 1053 }, { "epoch": 0.24727725948056234, "grad_norm": 16.89365005493164, "learning_rate": 1.7517361122564586e-05, "loss": 24.7634, "step": 1054 }, { "epoch": 0.2475118678861416, "grad_norm": 20.277368545532227, "learning_rate": 1.7512381164613064e-05, "loss": 33.0765, "step": 1055 }, { "epoch": 0.2477464762917209, "grad_norm": 18.484113693237305, "learning_rate": 1.750739692637161e-05, "loss": 25.399, "step": 1056 }, { "epoch": 0.24798108469730018, "grad_norm": 22.26426124572754, "learning_rate": 1.7502408410680054e-05, "loss": 32.1583, "step": 1057 }, { "epoch": 0.24821569310287944, "grad_norm": 19.208242416381836, "learning_rate": 1.749741562038069e-05, "loss": 27.1787, "step": 1058 }, { "epoch": 0.24845030150845873, "grad_norm": 19.010093688964844, "learning_rate": 1.7492418558318225e-05, "loss": 24.4621, "step": 1059 }, { "epoch": 0.24868490991403802, "grad_norm": 20.83951187133789, "learning_rate": 1.7487417227339816e-05, "loss": 26.752, "step": 1060 }, { "epoch": 0.24891951831961728, "grad_norm": 23.0755672454834, "learning_rate": 1.7482411630295038e-05, "loss": 24.6309, "step": 1061 }, { "epoch": 0.24915412672519657, "grad_norm": 19.082508087158203, "learning_rate": 1.747740177003591e-05, "loss": 25.4977, "step": 1062 }, { "epoch": 0.24938873513077586, "grad_norm": 18.162084579467773, "learning_rate": 1.7472387649416864e-05, "loss": 28.1857, "step": 1063 }, { "epoch": 0.24962334353635515, "grad_norm": 19.32390785217285, "learning_rate": 1.746736927129478e-05, "loss": 26.6492, "step": 1064 }, { "epoch": 0.24985795194193441, "grad_norm": 22.156248092651367, "learning_rate": 1.746234663852895e-05, "loss": 28.7942, "step": 1065 }, { "epoch": 0.2500925603475137, "grad_norm": 19.47274398803711, "learning_rate": 1.745731975398109e-05, "loss": 25.3306, "step": 1066 }, { "epoch": 0.25032716875309297, "grad_norm": 16.898496627807617, "learning_rate": 1.7452288620515344e-05, "loss": 25.8532, "step": 1067 }, { "epoch": 0.2505617771586723, "grad_norm": 19.957813262939453, "learning_rate": 1.744725324099827e-05, "loss": 25.7071, "step": 1068 }, { "epoch": 0.25079638556425154, "grad_norm": 20.83635711669922, "learning_rate": 1.744221361829886e-05, "loss": 28.3273, "step": 1069 }, { "epoch": 0.2510309939698308, "grad_norm": 16.208614349365234, "learning_rate": 1.7437169755288503e-05, "loss": 24.4942, "step": 1070 }, { "epoch": 0.2512656023754101, "grad_norm": 16.10208511352539, "learning_rate": 1.743212165484102e-05, "loss": 25.42, "step": 1071 }, { "epoch": 0.2515002107809894, "grad_norm": 20.845842361450195, "learning_rate": 1.7427069319832637e-05, "loss": 31.5436, "step": 1072 }, { "epoch": 0.25173481918656865, "grad_norm": 24.669658660888672, "learning_rate": 1.7422012753141998e-05, "loss": 28.4671, "step": 1073 }, { "epoch": 0.25196942759214797, "grad_norm": 18.611894607543945, "learning_rate": 1.7416951957650157e-05, "loss": 27.2563, "step": 1074 }, { "epoch": 0.2522040359977272, "grad_norm": 23.379146575927734, "learning_rate": 1.7411886936240577e-05, "loss": 26.5312, "step": 1075 }, { "epoch": 0.2524386444033065, "grad_norm": 19.6497859954834, "learning_rate": 1.7406817691799127e-05, "loss": 31.3202, "step": 1076 }, { "epoch": 0.2526732528088858, "grad_norm": 21.83441925048828, "learning_rate": 1.7401744227214084e-05, "loss": 25.7228, "step": 1077 }, { "epoch": 0.25290786121446507, "grad_norm": 19.054813385009766, "learning_rate": 1.739666654537613e-05, "loss": 25.3334, "step": 1078 }, { "epoch": 0.25314246962004433, "grad_norm": 15.464221000671387, "learning_rate": 1.7391584649178354e-05, "loss": 21.4914, "step": 1079 }, { "epoch": 0.25337707802562365, "grad_norm": 19.379825592041016, "learning_rate": 1.7386498541516232e-05, "loss": 22.7736, "step": 1080 }, { "epoch": 0.2536116864312029, "grad_norm": 16.694456100463867, "learning_rate": 1.7381408225287658e-05, "loss": 24.6602, "step": 1081 }, { "epoch": 0.25384629483678217, "grad_norm": 19.0427188873291, "learning_rate": 1.7376313703392904e-05, "loss": 29.5526, "step": 1082 }, { "epoch": 0.2540809032423615, "grad_norm": 18.92378044128418, "learning_rate": 1.7371214978734657e-05, "loss": 28.4169, "step": 1083 }, { "epoch": 0.25431551164794075, "grad_norm": 23.089475631713867, "learning_rate": 1.7366112054217992e-05, "loss": 25.669, "step": 1084 }, { "epoch": 0.25455012005352007, "grad_norm": 20.785112380981445, "learning_rate": 1.736100493275037e-05, "loss": 27.9483, "step": 1085 }, { "epoch": 0.25478472845909933, "grad_norm": 19.250518798828125, "learning_rate": 1.735589361724165e-05, "loss": 27.3868, "step": 1086 }, { "epoch": 0.2550193368646786, "grad_norm": 18.20038604736328, "learning_rate": 1.7350778110604078e-05, "loss": 27.3108, "step": 1087 }, { "epoch": 0.2552539452702579, "grad_norm": 18.64410400390625, "learning_rate": 1.7345658415752296e-05, "loss": 24.8151, "step": 1088 }, { "epoch": 0.25548855367583717, "grad_norm": 19.123790740966797, "learning_rate": 1.734053453560332e-05, "loss": 25.0251, "step": 1089 }, { "epoch": 0.25572316208141643, "grad_norm": 18.080673217773438, "learning_rate": 1.7335406473076554e-05, "loss": 23.7052, "step": 1090 }, { "epoch": 0.25595777048699575, "grad_norm": 19.62137794494629, "learning_rate": 1.7330274231093795e-05, "loss": 30.4788, "step": 1091 }, { "epoch": 0.256192378892575, "grad_norm": 18.331079483032227, "learning_rate": 1.7325137812579207e-05, "loss": 25.8886, "step": 1092 }, { "epoch": 0.2564269872981543, "grad_norm": 18.113250732421875, "learning_rate": 1.7319997220459344e-05, "loss": 26.1114, "step": 1093 }, { "epoch": 0.2566615957037336, "grad_norm": 17.43367576599121, "learning_rate": 1.731485245766313e-05, "loss": 27.8105, "step": 1094 }, { "epoch": 0.25689620410931285, "grad_norm": 18.94330596923828, "learning_rate": 1.7309703527121874e-05, "loss": 26.0278, "step": 1095 }, { "epoch": 0.2571308125148921, "grad_norm": 18.972082138061523, "learning_rate": 1.7304550431769255e-05, "loss": 26.0638, "step": 1096 }, { "epoch": 0.25736542092047143, "grad_norm": 19.388044357299805, "learning_rate": 1.729939317454132e-05, "loss": 25.5088, "step": 1097 }, { "epoch": 0.2576000293260507, "grad_norm": 19.914199829101562, "learning_rate": 1.7294231758376495e-05, "loss": 25.433, "step": 1098 }, { "epoch": 0.25783463773162996, "grad_norm": 19.700103759765625, "learning_rate": 1.7289066186215576e-05, "loss": 32.6065, "step": 1099 }, { "epoch": 0.2580692461372093, "grad_norm": 17.16645622253418, "learning_rate": 1.7283896461001718e-05, "loss": 27.1847, "step": 1100 }, { "epoch": 0.25830385454278854, "grad_norm": 16.984638214111328, "learning_rate": 1.7278722585680455e-05, "loss": 25.1967, "step": 1101 }, { "epoch": 0.2585384629483678, "grad_norm": 21.00419044494629, "learning_rate": 1.7273544563199674e-05, "loss": 23.3408, "step": 1102 }, { "epoch": 0.2587730713539471, "grad_norm": 19.72509765625, "learning_rate": 1.726836239650963e-05, "loss": 28.7154, "step": 1103 }, { "epoch": 0.2590076797595264, "grad_norm": 18.377920150756836, "learning_rate": 1.726317608856294e-05, "loss": 26.4688, "step": 1104 }, { "epoch": 0.25924228816510564, "grad_norm": 19.770030975341797, "learning_rate": 1.725798564231458e-05, "loss": 25.6783, "step": 1105 }, { "epoch": 0.25947689657068496, "grad_norm": 17.318618774414062, "learning_rate": 1.725279106072188e-05, "loss": 25.2956, "step": 1106 }, { "epoch": 0.2597115049762642, "grad_norm": 18.047969818115234, "learning_rate": 1.724759234674454e-05, "loss": 23.4146, "step": 1107 }, { "epoch": 0.25994611338184354, "grad_norm": 20.43948745727539, "learning_rate": 1.7242389503344588e-05, "loss": 26.4876, "step": 1108 }, { "epoch": 0.2601807217874228, "grad_norm": 21.476802825927734, "learning_rate": 1.7237182533486435e-05, "loss": 31.4486, "step": 1109 }, { "epoch": 0.26041533019300206, "grad_norm": 21.211374282836914, "learning_rate": 1.7231971440136816e-05, "loss": 27.7296, "step": 1110 }, { "epoch": 0.2606499385985814, "grad_norm": 17.34906578063965, "learning_rate": 1.7226756226264837e-05, "loss": 25.7598, "step": 1111 }, { "epoch": 0.26088454700416064, "grad_norm": 21.262920379638672, "learning_rate": 1.7221536894841943e-05, "loss": 30.715, "step": 1112 }, { "epoch": 0.2611191554097399, "grad_norm": 18.3172550201416, "learning_rate": 1.721631344884192e-05, "loss": 27.2381, "step": 1113 }, { "epoch": 0.2613537638153192, "grad_norm": 18.505748748779297, "learning_rate": 1.721108589124091e-05, "loss": 26.0702, "step": 1114 }, { "epoch": 0.2615883722208985, "grad_norm": 18.567514419555664, "learning_rate": 1.7205854225017384e-05, "loss": 27.8617, "step": 1115 }, { "epoch": 0.26182298062647774, "grad_norm": 18.482242584228516, "learning_rate": 1.7200618453152166e-05, "loss": 28.1014, "step": 1116 }, { "epoch": 0.26205758903205706, "grad_norm": 19.248327255249023, "learning_rate": 1.719537857862841e-05, "loss": 25.3034, "step": 1117 }, { "epoch": 0.2622921974376363, "grad_norm": 17.77419662475586, "learning_rate": 1.7190134604431618e-05, "loss": 30.5025, "step": 1118 }, { "epoch": 0.2625268058432156, "grad_norm": 22.74614143371582, "learning_rate": 1.7184886533549615e-05, "loss": 30.0266, "step": 1119 }, { "epoch": 0.2627614142487949, "grad_norm": 17.69761085510254, "learning_rate": 1.717963436897257e-05, "loss": 21.8996, "step": 1120 }, { "epoch": 0.26299602265437416, "grad_norm": 20.021507263183594, "learning_rate": 1.717437811369298e-05, "loss": 28.1217, "step": 1121 }, { "epoch": 0.2632306310599534, "grad_norm": 17.189027786254883, "learning_rate": 1.7169117770705678e-05, "loss": 25.9656, "step": 1122 }, { "epoch": 0.26346523946553274, "grad_norm": 19.874820709228516, "learning_rate": 1.7163853343007816e-05, "loss": 29.1297, "step": 1123 }, { "epoch": 0.263699847871112, "grad_norm": 21.33209228515625, "learning_rate": 1.715858483359888e-05, "loss": 22.8299, "step": 1124 }, { "epoch": 0.26393445627669126, "grad_norm": 20.279319763183594, "learning_rate": 1.7153312245480685e-05, "loss": 30.1298, "step": 1125 }, { "epoch": 0.2641690646822706, "grad_norm": 19.05644989013672, "learning_rate": 1.7148035581657367e-05, "loss": 26.7719, "step": 1126 }, { "epoch": 0.26440367308784984, "grad_norm": 18.597990036010742, "learning_rate": 1.7142754845135375e-05, "loss": 25.226, "step": 1127 }, { "epoch": 0.2646382814934291, "grad_norm": 18.23499298095703, "learning_rate": 1.7137470038923493e-05, "loss": 25.4509, "step": 1128 }, { "epoch": 0.2648728898990084, "grad_norm": 17.467082977294922, "learning_rate": 1.7132181166032816e-05, "loss": 27.8637, "step": 1129 }, { "epoch": 0.2651074983045877, "grad_norm": 19.06159210205078, "learning_rate": 1.7126888229476757e-05, "loss": 27.5668, "step": 1130 }, { "epoch": 0.265342106710167, "grad_norm": 18.933517456054688, "learning_rate": 1.7121591232271048e-05, "loss": 21.8692, "step": 1131 }, { "epoch": 0.26557671511574626, "grad_norm": 21.09039306640625, "learning_rate": 1.7116290177433724e-05, "loss": 25.0838, "step": 1132 }, { "epoch": 0.2658113235213255, "grad_norm": 21.159608840942383, "learning_rate": 1.7110985067985143e-05, "loss": 28.5125, "step": 1133 }, { "epoch": 0.26604593192690484, "grad_norm": 18.379886627197266, "learning_rate": 1.7105675906947968e-05, "loss": 28.2434, "step": 1134 }, { "epoch": 0.2662805403324841, "grad_norm": 20.091909408569336, "learning_rate": 1.7100362697347175e-05, "loss": 30.2569, "step": 1135 }, { "epoch": 0.26651514873806337, "grad_norm": 19.276090621948242, "learning_rate": 1.709504544221004e-05, "loss": 26.5489, "step": 1136 }, { "epoch": 0.2667497571436427, "grad_norm": 17.88881492614746, "learning_rate": 1.708972414456615e-05, "loss": 24.6481, "step": 1137 }, { "epoch": 0.26698436554922195, "grad_norm": 16.981082916259766, "learning_rate": 1.7084398807447394e-05, "loss": 24.212, "step": 1138 }, { "epoch": 0.2672189739548012, "grad_norm": 17.224529266357422, "learning_rate": 1.7079069433887957e-05, "loss": 28.1946, "step": 1139 }, { "epoch": 0.2674535823603805, "grad_norm": 18.38835334777832, "learning_rate": 1.707373602692433e-05, "loss": 26.3585, "step": 1140 }, { "epoch": 0.2676881907659598, "grad_norm": 20.38790512084961, "learning_rate": 1.7068398589595303e-05, "loss": 21.8149, "step": 1141 }, { "epoch": 0.26792279917153905, "grad_norm": 18.062782287597656, "learning_rate": 1.7063057124941952e-05, "loss": 26.9486, "step": 1142 }, { "epoch": 0.26815740757711837, "grad_norm": 16.584047317504883, "learning_rate": 1.7057711636007666e-05, "loss": 24.5094, "step": 1143 }, { "epoch": 0.26839201598269763, "grad_norm": 23.742170333862305, "learning_rate": 1.705236212583811e-05, "loss": 31.9751, "step": 1144 }, { "epoch": 0.2686266243882769, "grad_norm": 17.675540924072266, "learning_rate": 1.7047008597481245e-05, "loss": 23.3216, "step": 1145 }, { "epoch": 0.2688612327938562, "grad_norm": 17.113847732543945, "learning_rate": 1.7041651053987325e-05, "loss": 25.6455, "step": 1146 }, { "epoch": 0.26909584119943547, "grad_norm": 18.340587615966797, "learning_rate": 1.703628949840889e-05, "loss": 24.3502, "step": 1147 }, { "epoch": 0.26933044960501473, "grad_norm": 20.993770599365234, "learning_rate": 1.7030923933800762e-05, "loss": 27.4827, "step": 1148 }, { "epoch": 0.26956505801059405, "grad_norm": 16.82012367248535, "learning_rate": 1.7025554363220056e-05, "loss": 26.6049, "step": 1149 }, { "epoch": 0.2697996664161733, "grad_norm": 20.909162521362305, "learning_rate": 1.702018078972616e-05, "loss": 26.065, "step": 1150 }, { "epoch": 0.2700342748217526, "grad_norm": 16.54140853881836, "learning_rate": 1.7014803216380746e-05, "loss": 24.0963, "step": 1151 }, { "epoch": 0.2702688832273319, "grad_norm": 21.33189582824707, "learning_rate": 1.700942164624777e-05, "loss": 25.0468, "step": 1152 }, { "epoch": 0.27050349163291115, "grad_norm": 19.085777282714844, "learning_rate": 1.7004036082393457e-05, "loss": 25.1651, "step": 1153 }, { "epoch": 0.2707381000384904, "grad_norm": 19.51226806640625, "learning_rate": 1.6998646527886314e-05, "loss": 24.0467, "step": 1154 }, { "epoch": 0.27097270844406973, "grad_norm": 17.836132049560547, "learning_rate": 1.6993252985797118e-05, "loss": 23.8557, "step": 1155 }, { "epoch": 0.271207316849649, "grad_norm": 19.070903778076172, "learning_rate": 1.6987855459198916e-05, "loss": 25.5101, "step": 1156 }, { "epoch": 0.2714419252552283, "grad_norm": 20.587438583374023, "learning_rate": 1.6982453951167036e-05, "loss": 28.2701, "step": 1157 }, { "epoch": 0.2716765336608076, "grad_norm": 21.16615867614746, "learning_rate": 1.697704846477906e-05, "loss": 27.4898, "step": 1158 }, { "epoch": 0.27191114206638684, "grad_norm": 20.927900314331055, "learning_rate": 1.6971639003114844e-05, "loss": 24.1328, "step": 1159 }, { "epoch": 0.27214575047196615, "grad_norm": 19.898117065429688, "learning_rate": 1.696622556925651e-05, "loss": 26.0336, "step": 1160 }, { "epoch": 0.2723803588775454, "grad_norm": 18.986690521240234, "learning_rate": 1.6960808166288445e-05, "loss": 31.7199, "step": 1161 }, { "epoch": 0.2726149672831247, "grad_norm": 18.726593017578125, "learning_rate": 1.6955386797297292e-05, "loss": 27.0728, "step": 1162 }, { "epoch": 0.272849575688704, "grad_norm": 18.27692985534668, "learning_rate": 1.694996146537195e-05, "loss": 21.5573, "step": 1163 }, { "epoch": 0.27308418409428326, "grad_norm": 17.01279067993164, "learning_rate": 1.6944532173603595e-05, "loss": 22.1166, "step": 1164 }, { "epoch": 0.2733187924998625, "grad_norm": 20.03949737548828, "learning_rate": 1.6939098925085634e-05, "loss": 26.881, "step": 1165 }, { "epoch": 0.27355340090544183, "grad_norm": 21.149063110351562, "learning_rate": 1.6933661722913744e-05, "loss": 25.4725, "step": 1166 }, { "epoch": 0.2737880093110211, "grad_norm": 17.694076538085938, "learning_rate": 1.6928220570185852e-05, "loss": 29.9124, "step": 1167 }, { "epoch": 0.27402261771660036, "grad_norm": 18.45560646057129, "learning_rate": 1.6922775470002135e-05, "loss": 23.2216, "step": 1168 }, { "epoch": 0.2742572261221797, "grad_norm": 23.845495223999023, "learning_rate": 1.6917326425465018e-05, "loss": 32.8299, "step": 1169 }, { "epoch": 0.27449183452775894, "grad_norm": 18.288280487060547, "learning_rate": 1.6911873439679176e-05, "loss": 25.7285, "step": 1170 }, { "epoch": 0.2747264429333382, "grad_norm": 19.205835342407227, "learning_rate": 1.690641651575153e-05, "loss": 26.8059, "step": 1171 }, { "epoch": 0.2749610513389175, "grad_norm": 20.060253143310547, "learning_rate": 1.6900955656791234e-05, "loss": 24.5456, "step": 1172 }, { "epoch": 0.2751956597444968, "grad_norm": 18.27100944519043, "learning_rate": 1.6895490865909704e-05, "loss": 26.2239, "step": 1173 }, { "epoch": 0.27543026815007604, "grad_norm": 18.52873420715332, "learning_rate": 1.689002214622058e-05, "loss": 26.7964, "step": 1174 }, { "epoch": 0.27566487655565536, "grad_norm": 19.88099479675293, "learning_rate": 1.6884549500839745e-05, "loss": 23.7997, "step": 1175 }, { "epoch": 0.2758994849612346, "grad_norm": 17.66244888305664, "learning_rate": 1.687907293288532e-05, "loss": 27.1149, "step": 1176 }, { "epoch": 0.2761340933668139, "grad_norm": 20.12747573852539, "learning_rate": 1.687359244547766e-05, "loss": 24.5733, "step": 1177 }, { "epoch": 0.2763687017723932, "grad_norm": 20.13743782043457, "learning_rate": 1.6868108041739358e-05, "loss": 28.1599, "step": 1178 }, { "epoch": 0.27660331017797246, "grad_norm": 17.714929580688477, "learning_rate": 1.686261972479523e-05, "loss": 23.9496, "step": 1179 }, { "epoch": 0.2768379185835518, "grad_norm": 24.458724975585938, "learning_rate": 1.685712749777232e-05, "loss": 33.5789, "step": 1180 }, { "epoch": 0.27707252698913104, "grad_norm": 16.670307159423828, "learning_rate": 1.6851631363799917e-05, "loss": 23.9419, "step": 1181 }, { "epoch": 0.2773071353947103, "grad_norm": 20.900863647460938, "learning_rate": 1.6846131326009513e-05, "loss": 29.3387, "step": 1182 }, { "epoch": 0.2775417438002896, "grad_norm": 18.15785026550293, "learning_rate": 1.6840627387534846e-05, "loss": 27.0584, "step": 1183 }, { "epoch": 0.2777763522058689, "grad_norm": 22.929101943969727, "learning_rate": 1.683511955151186e-05, "loss": 26.6154, "step": 1184 }, { "epoch": 0.27801096061144814, "grad_norm": 18.888856887817383, "learning_rate": 1.6829607821078724e-05, "loss": 28.5251, "step": 1185 }, { "epoch": 0.27824556901702746, "grad_norm": 20.948585510253906, "learning_rate": 1.6824092199375833e-05, "loss": 26.9368, "step": 1186 }, { "epoch": 0.2784801774226067, "grad_norm": 22.330657958984375, "learning_rate": 1.681857268954579e-05, "loss": 29.2886, "step": 1187 }, { "epoch": 0.278714785828186, "grad_norm": 19.861719131469727, "learning_rate": 1.681304929473342e-05, "loss": 27.7539, "step": 1188 }, { "epoch": 0.2789493942337653, "grad_norm": 18.388803482055664, "learning_rate": 1.6807522018085754e-05, "loss": 27.2224, "step": 1189 }, { "epoch": 0.27918400263934456, "grad_norm": 25.818836212158203, "learning_rate": 1.6801990862752048e-05, "loss": 22.7232, "step": 1190 }, { "epoch": 0.2794186110449238, "grad_norm": 18.367431640625, "learning_rate": 1.679645583188375e-05, "loss": 26.0949, "step": 1191 }, { "epoch": 0.27965321945050314, "grad_norm": 15.79385757446289, "learning_rate": 1.679091692863453e-05, "loss": 22.1828, "step": 1192 }, { "epoch": 0.2798878278560824, "grad_norm": 17.839855194091797, "learning_rate": 1.6785374156160257e-05, "loss": 27.3946, "step": 1193 }, { "epoch": 0.28012243626166167, "grad_norm": 17.536264419555664, "learning_rate": 1.677982751761901e-05, "loss": 22.8647, "step": 1194 }, { "epoch": 0.280357044667241, "grad_norm": 18.55584144592285, "learning_rate": 1.677427701617107e-05, "loss": 24.9361, "step": 1195 }, { "epoch": 0.28059165307282025, "grad_norm": 18.776138305664062, "learning_rate": 1.6768722654978914e-05, "loss": 27.4863, "step": 1196 }, { "epoch": 0.2808262614783995, "grad_norm": 19.02659797668457, "learning_rate": 1.676316443720722e-05, "loss": 28.7766, "step": 1197 }, { "epoch": 0.2810608698839788, "grad_norm": 23.59520149230957, "learning_rate": 1.6757602366022868e-05, "loss": 26.597, "step": 1198 }, { "epoch": 0.2812954782895581, "grad_norm": 17.9226131439209, "learning_rate": 1.675203644459493e-05, "loss": 24.265, "step": 1199 }, { "epoch": 0.28153008669513735, "grad_norm": 19.36151123046875, "learning_rate": 1.6746466676094665e-05, "loss": 27.2071, "step": 1200 }, { "epoch": 0.28176469510071667, "grad_norm": 19.34748077392578, "learning_rate": 1.6740893063695538e-05, "loss": 24.7079, "step": 1201 }, { "epoch": 0.28199930350629593, "grad_norm": 22.448209762573242, "learning_rate": 1.6735315610573197e-05, "loss": 26.8335, "step": 1202 }, { "epoch": 0.2822339119118752, "grad_norm": 18.201303482055664, "learning_rate": 1.6729734319905472e-05, "loss": 24.9512, "step": 1203 }, { "epoch": 0.2824685203174545, "grad_norm": 20.905433654785156, "learning_rate": 1.672414919487239e-05, "loss": 27.589, "step": 1204 }, { "epoch": 0.28270312872303377, "grad_norm": 20.423418045043945, "learning_rate": 1.6718560238656158e-05, "loss": 31.3779, "step": 1205 }, { "epoch": 0.2829377371286131, "grad_norm": 18.592697143554688, "learning_rate": 1.671296745444117e-05, "loss": 26.3203, "step": 1206 }, { "epoch": 0.28317234553419235, "grad_norm": 22.92890167236328, "learning_rate": 1.670737084541399e-05, "loss": 29.19, "step": 1207 }, { "epoch": 0.2834069539397716, "grad_norm": 19.35328483581543, "learning_rate": 1.670177041476337e-05, "loss": 28.8458, "step": 1208 }, { "epoch": 0.28364156234535093, "grad_norm": 18.709197998046875, "learning_rate": 1.6696166165680242e-05, "loss": 25.9926, "step": 1209 }, { "epoch": 0.2838761707509302, "grad_norm": 18.750762939453125, "learning_rate": 1.6690558101357708e-05, "loss": 25.7257, "step": 1210 }, { "epoch": 0.28411077915650945, "grad_norm": 15.728741645812988, "learning_rate": 1.6684946224991042e-05, "loss": 25.5839, "step": 1211 }, { "epoch": 0.28434538756208877, "grad_norm": 20.011981964111328, "learning_rate": 1.66793305397777e-05, "loss": 26.9477, "step": 1212 }, { "epoch": 0.28457999596766803, "grad_norm": 16.874622344970703, "learning_rate": 1.6673711048917294e-05, "loss": 24.3217, "step": 1213 }, { "epoch": 0.2848146043732473, "grad_norm": 18.53583335876465, "learning_rate": 1.6668087755611616e-05, "loss": 25.277, "step": 1214 }, { "epoch": 0.2850492127788266, "grad_norm": 17.771282196044922, "learning_rate": 1.666246066306462e-05, "loss": 23.665, "step": 1215 }, { "epoch": 0.2852838211844059, "grad_norm": 17.11565399169922, "learning_rate": 1.6656829774482423e-05, "loss": 24.3016, "step": 1216 }, { "epoch": 0.28551842958998513, "grad_norm": 18.983566284179688, "learning_rate": 1.6651195093073312e-05, "loss": 25.1257, "step": 1217 }, { "epoch": 0.28575303799556445, "grad_norm": 17.883787155151367, "learning_rate": 1.6645556622047723e-05, "loss": 27.9462, "step": 1218 }, { "epoch": 0.2859876464011437, "grad_norm": 24.55338478088379, "learning_rate": 1.6639914364618263e-05, "loss": 27.1489, "step": 1219 }, { "epoch": 0.286222254806723, "grad_norm": 15.216646194458008, "learning_rate": 1.6634268323999684e-05, "loss": 22.1485, "step": 1220 }, { "epoch": 0.2864568632123023, "grad_norm": 17.750303268432617, "learning_rate": 1.662861850340891e-05, "loss": 23.505, "step": 1221 }, { "epoch": 0.28669147161788155, "grad_norm": 16.142494201660156, "learning_rate": 1.662296490606501e-05, "loss": 27.0192, "step": 1222 }, { "epoch": 0.2869260800234608, "grad_norm": 20.81101417541504, "learning_rate": 1.6617307535189192e-05, "loss": 27.1574, "step": 1223 }, { "epoch": 0.28716068842904013, "grad_norm": 24.0330753326416, "learning_rate": 1.661164639400484e-05, "loss": 28.2045, "step": 1224 }, { "epoch": 0.2873952968346194, "grad_norm": 19.0220890045166, "learning_rate": 1.6605981485737465e-05, "loss": 23.8188, "step": 1225 }, { "epoch": 0.28762990524019866, "grad_norm": 17.169036865234375, "learning_rate": 1.660031281361474e-05, "loss": 25.7264, "step": 1226 }, { "epoch": 0.287864513645778, "grad_norm": 16.9265079498291, "learning_rate": 1.6594640380866462e-05, "loss": 27.1833, "step": 1227 }, { "epoch": 0.28809912205135724, "grad_norm": 18.664775848388672, "learning_rate": 1.658896419072459e-05, "loss": 23.3311, "step": 1228 }, { "epoch": 0.28833373045693655, "grad_norm": 19.34553337097168, "learning_rate": 1.6583284246423223e-05, "loss": 27.4347, "step": 1229 }, { "epoch": 0.2885683388625158, "grad_norm": 22.3277530670166, "learning_rate": 1.6577600551198585e-05, "loss": 27.8418, "step": 1230 }, { "epoch": 0.2888029472680951, "grad_norm": 17.12169647216797, "learning_rate": 1.6571913108289048e-05, "loss": 23.389, "step": 1231 }, { "epoch": 0.2890375556736744, "grad_norm": 21.66016960144043, "learning_rate": 1.6566221920935117e-05, "loss": 26.0965, "step": 1232 }, { "epoch": 0.28927216407925366, "grad_norm": 20.433115005493164, "learning_rate": 1.6560526992379423e-05, "loss": 28.1759, "step": 1233 }, { "epoch": 0.2895067724848329, "grad_norm": 18.77945327758789, "learning_rate": 1.6554828325866744e-05, "loss": 25.3375, "step": 1234 }, { "epoch": 0.28974138089041224, "grad_norm": 19.091787338256836, "learning_rate": 1.6549125924643976e-05, "loss": 24.6942, "step": 1235 }, { "epoch": 0.2899759892959915, "grad_norm": 21.427120208740234, "learning_rate": 1.6543419791960153e-05, "loss": 25.4237, "step": 1236 }, { "epoch": 0.29021059770157076, "grad_norm": 19.616355895996094, "learning_rate": 1.6537709931066412e-05, "loss": 24.896, "step": 1237 }, { "epoch": 0.2904452061071501, "grad_norm": 19.330862045288086, "learning_rate": 1.6531996345216046e-05, "loss": 29.4568, "step": 1238 }, { "epoch": 0.29067981451272934, "grad_norm": 20.286882400512695, "learning_rate": 1.652627903766445e-05, "loss": 27.8883, "step": 1239 }, { "epoch": 0.2909144229183086, "grad_norm": 20.379091262817383, "learning_rate": 1.652055801166914e-05, "loss": 22.138, "step": 1240 }, { "epoch": 0.2911490313238879, "grad_norm": 18.658157348632812, "learning_rate": 1.651483327048976e-05, "loss": 27.2572, "step": 1241 }, { "epoch": 0.2913836397294672, "grad_norm": 17.714738845825195, "learning_rate": 1.6509104817388063e-05, "loss": 26.8458, "step": 1242 }, { "epoch": 0.29161824813504644, "grad_norm": 17.919416427612305, "learning_rate": 1.650337265562792e-05, "loss": 27.2969, "step": 1243 }, { "epoch": 0.29185285654062576, "grad_norm": 18.1213436126709, "learning_rate": 1.649763678847532e-05, "loss": 26.8114, "step": 1244 }, { "epoch": 0.292087464946205, "grad_norm": 20.260168075561523, "learning_rate": 1.649189721919835e-05, "loss": 28.3546, "step": 1245 }, { "epoch": 0.2923220733517843, "grad_norm": 17.19093894958496, "learning_rate": 1.6486153951067217e-05, "loss": 24.9469, "step": 1246 }, { "epoch": 0.2925566817573636, "grad_norm": 18.956491470336914, "learning_rate": 1.6480406987354233e-05, "loss": 26.0585, "step": 1247 }, { "epoch": 0.29279129016294286, "grad_norm": 22.942079544067383, "learning_rate": 1.647465633133382e-05, "loss": 28.3801, "step": 1248 }, { "epoch": 0.2930258985685221, "grad_norm": 21.397174835205078, "learning_rate": 1.646890198628249e-05, "loss": 28.7766, "step": 1249 }, { "epoch": 0.29326050697410144, "grad_norm": 20.435272216796875, "learning_rate": 1.6463143955478873e-05, "loss": 27.7447, "step": 1250 }, { "epoch": 0.2934951153796807, "grad_norm": 16.58888816833496, "learning_rate": 1.6457382242203688e-05, "loss": 26.39, "step": 1251 }, { "epoch": 0.29372972378525997, "grad_norm": 18.772302627563477, "learning_rate": 1.6451616849739757e-05, "loss": 29.2379, "step": 1252 }, { "epoch": 0.2939643321908393, "grad_norm": 18.79940414428711, "learning_rate": 1.6445847781371996e-05, "loss": 28.9031, "step": 1253 }, { "epoch": 0.29419894059641855, "grad_norm": 18.23435401916504, "learning_rate": 1.6440075040387422e-05, "loss": 25.6707, "step": 1254 }, { "epoch": 0.29443354900199786, "grad_norm": 19.322629928588867, "learning_rate": 1.643429863007514e-05, "loss": 27.7664, "step": 1255 }, { "epoch": 0.2946681574075771, "grad_norm": 15.932424545288086, "learning_rate": 1.6428518553726332e-05, "loss": 27.0657, "step": 1256 }, { "epoch": 0.2949027658131564, "grad_norm": 22.710153579711914, "learning_rate": 1.6422734814634297e-05, "loss": 28.5114, "step": 1257 }, { "epoch": 0.2951373742187357, "grad_norm": 15.545011520385742, "learning_rate": 1.6416947416094395e-05, "loss": 24.4315, "step": 1258 }, { "epoch": 0.29537198262431497, "grad_norm": 18.42193603515625, "learning_rate": 1.641115636140409e-05, "loss": 25.2812, "step": 1259 }, { "epoch": 0.29560659102989423, "grad_norm": 18.628982543945312, "learning_rate": 1.6405361653862913e-05, "loss": 28.2736, "step": 1260 }, { "epoch": 0.29584119943547355, "grad_norm": 18.402360916137695, "learning_rate": 1.639956329677249e-05, "loss": 28.2738, "step": 1261 }, { "epoch": 0.2960758078410528, "grad_norm": 22.43109703063965, "learning_rate": 1.6393761293436515e-05, "loss": 23.392, "step": 1262 }, { "epoch": 0.29631041624663207, "grad_norm": 20.10793685913086, "learning_rate": 1.638795564716077e-05, "loss": 24.2544, "step": 1263 }, { "epoch": 0.2965450246522114, "grad_norm": 19.580244064331055, "learning_rate": 1.6382146361253107e-05, "loss": 28.0737, "step": 1264 }, { "epoch": 0.29677963305779065, "grad_norm": 21.935739517211914, "learning_rate": 1.637633343902345e-05, "loss": 25.067, "step": 1265 }, { "epoch": 0.2970142414633699, "grad_norm": 16.285587310791016, "learning_rate": 1.6370516883783798e-05, "loss": 20.2614, "step": 1266 }, { "epoch": 0.2972488498689492, "grad_norm": 20.98285484313965, "learning_rate": 1.636469669884822e-05, "loss": 32.8209, "step": 1267 }, { "epoch": 0.2974834582745285, "grad_norm": 21.392925262451172, "learning_rate": 1.6358872887532852e-05, "loss": 30.8688, "step": 1268 }, { "epoch": 0.29771806668010775, "grad_norm": 23.52781867980957, "learning_rate": 1.6353045453155895e-05, "loss": 27.2569, "step": 1269 }, { "epoch": 0.29795267508568707, "grad_norm": 20.106870651245117, "learning_rate": 1.6347214399037618e-05, "loss": 29.155, "step": 1270 }, { "epoch": 0.29818728349126633, "grad_norm": 20.31974220275879, "learning_rate": 1.6341379728500348e-05, "loss": 27.5592, "step": 1271 }, { "epoch": 0.2984218918968456, "grad_norm": 20.584001541137695, "learning_rate": 1.6335541444868472e-05, "loss": 29.2276, "step": 1272 }, { "epoch": 0.2986565003024249, "grad_norm": 22.092758178710938, "learning_rate": 1.6329699551468445e-05, "loss": 29.796, "step": 1273 }, { "epoch": 0.29889110870800417, "grad_norm": 22.07775115966797, "learning_rate": 1.6323854051628768e-05, "loss": 22.5316, "step": 1274 }, { "epoch": 0.29912571711358343, "grad_norm": 15.07420539855957, "learning_rate": 1.631800494868e-05, "loss": 22.2164, "step": 1275 }, { "epoch": 0.29936032551916275, "grad_norm": 19.09918975830078, "learning_rate": 1.6312152245954754e-05, "loss": 30.3977, "step": 1276 }, { "epoch": 0.299594933924742, "grad_norm": 16.86374855041504, "learning_rate": 1.6306295946787692e-05, "loss": 26.9361, "step": 1277 }, { "epoch": 0.29982954233032133, "grad_norm": 20.88198471069336, "learning_rate": 1.6300436054515538e-05, "loss": 29.0124, "step": 1278 }, { "epoch": 0.3000641507359006, "grad_norm": 17.077686309814453, "learning_rate": 1.6294572572477034e-05, "loss": 26.9369, "step": 1279 }, { "epoch": 0.30029875914147985, "grad_norm": 19.49705696105957, "learning_rate": 1.6288705504013e-05, "loss": 22.9333, "step": 1280 }, { "epoch": 0.30053336754705917, "grad_norm": 17.07882308959961, "learning_rate": 1.6282834852466273e-05, "loss": 25.07, "step": 1281 }, { "epoch": 0.30076797595263843, "grad_norm": 18.270536422729492, "learning_rate": 1.6276960621181753e-05, "loss": 26.5188, "step": 1282 }, { "epoch": 0.3010025843582177, "grad_norm": 20.04899787902832, "learning_rate": 1.627108281350637e-05, "loss": 29.169, "step": 1283 }, { "epoch": 0.301237192763797, "grad_norm": 18.795854568481445, "learning_rate": 1.6265201432789083e-05, "loss": 27.3751, "step": 1284 }, { "epoch": 0.3014718011693763, "grad_norm": 17.57754898071289, "learning_rate": 1.62593164823809e-05, "loss": 25.9834, "step": 1285 }, { "epoch": 0.30170640957495554, "grad_norm": 18.654680252075195, "learning_rate": 1.6253427965634863e-05, "loss": 22.4456, "step": 1286 }, { "epoch": 0.30194101798053485, "grad_norm": 19.426128387451172, "learning_rate": 1.6247535885906033e-05, "loss": 27.9934, "step": 1287 }, { "epoch": 0.3021756263861141, "grad_norm": 18.973527908325195, "learning_rate": 1.6241640246551514e-05, "loss": 23.7639, "step": 1288 }, { "epoch": 0.3024102347916934, "grad_norm": 22.401723861694336, "learning_rate": 1.6235741050930434e-05, "loss": 25.5448, "step": 1289 }, { "epoch": 0.3026448431972727, "grad_norm": 18.790035247802734, "learning_rate": 1.6229838302403944e-05, "loss": 25.4837, "step": 1290 }, { "epoch": 0.30287945160285196, "grad_norm": 16.397035598754883, "learning_rate": 1.6223932004335226e-05, "loss": 26.9401, "step": 1291 }, { "epoch": 0.3031140600084312, "grad_norm": 20.450536727905273, "learning_rate": 1.6218022160089474e-05, "loss": 26.8836, "step": 1292 }, { "epoch": 0.30334866841401054, "grad_norm": 19.351213455200195, "learning_rate": 1.6212108773033915e-05, "loss": 29.1057, "step": 1293 }, { "epoch": 0.3035832768195898, "grad_norm": 20.228601455688477, "learning_rate": 1.6206191846537785e-05, "loss": 23.8222, "step": 1294 }, { "epoch": 0.30381788522516906, "grad_norm": 17.860126495361328, "learning_rate": 1.6200271383972343e-05, "loss": 21.6223, "step": 1295 }, { "epoch": 0.3040524936307484, "grad_norm": 18.685256958007812, "learning_rate": 1.6194347388710853e-05, "loss": 27.1091, "step": 1296 }, { "epoch": 0.30428710203632764, "grad_norm": 19.87862205505371, "learning_rate": 1.618841986412861e-05, "loss": 28.3837, "step": 1297 }, { "epoch": 0.3045217104419069, "grad_norm": 19.095035552978516, "learning_rate": 1.6182488813602898e-05, "loss": 27.9592, "step": 1298 }, { "epoch": 0.3047563188474862, "grad_norm": 17.900976181030273, "learning_rate": 1.6176554240513028e-05, "loss": 25.0849, "step": 1299 }, { "epoch": 0.3049909272530655, "grad_norm": 17.68140983581543, "learning_rate": 1.6170616148240304e-05, "loss": 27.0959, "step": 1300 }, { "epoch": 0.3052255356586448, "grad_norm": 16.864431381225586, "learning_rate": 1.616467454016805e-05, "loss": 21.2966, "step": 1301 }, { "epoch": 0.30546014406422406, "grad_norm": 20.32410430908203, "learning_rate": 1.6158729419681574e-05, "loss": 30.5783, "step": 1302 }, { "epoch": 0.3056947524698033, "grad_norm": 18.319189071655273, "learning_rate": 1.6152780790168204e-05, "loss": 25.3814, "step": 1303 }, { "epoch": 0.30592936087538264, "grad_norm": 19.17436981201172, "learning_rate": 1.6146828655017255e-05, "loss": 23.7264, "step": 1304 }, { "epoch": 0.3061639692809619, "grad_norm": 18.12520408630371, "learning_rate": 1.614087301762005e-05, "loss": 33.2158, "step": 1305 }, { "epoch": 0.30639857768654116, "grad_norm": 17.68740463256836, "learning_rate": 1.6134913881369894e-05, "loss": 24.2458, "step": 1306 }, { "epoch": 0.3066331860921205, "grad_norm": 17.135658264160156, "learning_rate": 1.6128951249662094e-05, "loss": 27.159, "step": 1307 }, { "epoch": 0.30686779449769974, "grad_norm": 16.7636661529541, "learning_rate": 1.6122985125893955e-05, "loss": 28.8869, "step": 1308 }, { "epoch": 0.307102402903279, "grad_norm": 16.99289321899414, "learning_rate": 1.611701551346475e-05, "loss": 25.749, "step": 1309 }, { "epoch": 0.3073370113088583, "grad_norm": 21.777812957763672, "learning_rate": 1.6111042415775772e-05, "loss": 30.7366, "step": 1310 }, { "epoch": 0.3075716197144376, "grad_norm": 19.917545318603516, "learning_rate": 1.6105065836230265e-05, "loss": 23.6511, "step": 1311 }, { "epoch": 0.30780622812001684, "grad_norm": 20.436176300048828, "learning_rate": 1.6099085778233484e-05, "loss": 24.3834, "step": 1312 }, { "epoch": 0.30804083652559616, "grad_norm": 17.89243507385254, "learning_rate": 1.6093102245192645e-05, "loss": 28.1586, "step": 1313 }, { "epoch": 0.3082754449311754, "grad_norm": 20.473411560058594, "learning_rate": 1.6087115240516965e-05, "loss": 28.5588, "step": 1314 }, { "epoch": 0.3085100533367547, "grad_norm": 18.717710494995117, "learning_rate": 1.6081124767617618e-05, "loss": 22.466, "step": 1315 }, { "epoch": 0.308744661742334, "grad_norm": 14.12975788116455, "learning_rate": 1.6075130829907774e-05, "loss": 22.8049, "step": 1316 }, { "epoch": 0.30897927014791327, "grad_norm": 18.268123626708984, "learning_rate": 1.6069133430802565e-05, "loss": 29.2397, "step": 1317 }, { "epoch": 0.3092138785534925, "grad_norm": 17.611019134521484, "learning_rate": 1.6063132573719088e-05, "loss": 25.5929, "step": 1318 }, { "epoch": 0.30944848695907184, "grad_norm": 21.60569953918457, "learning_rate": 1.6057128262076435e-05, "loss": 29.1993, "step": 1319 }, { "epoch": 0.3096830953646511, "grad_norm": 19.86739158630371, "learning_rate": 1.6051120499295637e-05, "loss": 23.9178, "step": 1320 }, { "epoch": 0.30991770377023037, "grad_norm": 18.683271408081055, "learning_rate": 1.6045109288799717e-05, "loss": 30.1167, "step": 1321 }, { "epoch": 0.3101523121758097, "grad_norm": 19.991897583007812, "learning_rate": 1.6039094634013645e-05, "loss": 28.8137, "step": 1322 }, { "epoch": 0.31038692058138895, "grad_norm": 21.778928756713867, "learning_rate": 1.6033076538364355e-05, "loss": 24.0151, "step": 1323 }, { "epoch": 0.3106215289869682, "grad_norm": 20.018632888793945, "learning_rate": 1.6027055005280754e-05, "loss": 24.9902, "step": 1324 }, { "epoch": 0.3108561373925475, "grad_norm": 21.219646453857422, "learning_rate": 1.6021030038193695e-05, "loss": 26.2294, "step": 1325 }, { "epoch": 0.3110907457981268, "grad_norm": 17.42997932434082, "learning_rate": 1.6015001640535996e-05, "loss": 28.3706, "step": 1326 }, { "epoch": 0.3113253542037061, "grad_norm": 17.165334701538086, "learning_rate": 1.6008969815742416e-05, "loss": 30.817, "step": 1327 }, { "epoch": 0.31155996260928537, "grad_norm": 17.171524047851562, "learning_rate": 1.600293456724969e-05, "loss": 25.8914, "step": 1328 }, { "epoch": 0.31179457101486463, "grad_norm": 18.338001251220703, "learning_rate": 1.5996895898496473e-05, "loss": 26.8666, "step": 1329 }, { "epoch": 0.31202917942044395, "grad_norm": 22.342260360717773, "learning_rate": 1.5990853812923403e-05, "loss": 21.4837, "step": 1330 }, { "epoch": 0.3122637878260232, "grad_norm": 19.914350509643555, "learning_rate": 1.5984808313973035e-05, "loss": 31.2699, "step": 1331 }, { "epoch": 0.31249839623160247, "grad_norm": 18.26230239868164, "learning_rate": 1.5978759405089883e-05, "loss": 23.4102, "step": 1332 }, { "epoch": 0.3127330046371818, "grad_norm": 16.521888732910156, "learning_rate": 1.5972707089720406e-05, "loss": 23.9994, "step": 1333 }, { "epoch": 0.31296761304276105, "grad_norm": 20.791542053222656, "learning_rate": 1.5966651371313e-05, "loss": 26.6598, "step": 1334 }, { "epoch": 0.3132022214483403, "grad_norm": 17.61991310119629, "learning_rate": 1.5960592253318e-05, "loss": 28.7387, "step": 1335 }, { "epoch": 0.31343682985391963, "grad_norm": 17.3179931640625, "learning_rate": 1.595452973918767e-05, "loss": 28.4354, "step": 1336 }, { "epoch": 0.3136714382594989, "grad_norm": 17.405609130859375, "learning_rate": 1.5948463832376225e-05, "loss": 23.8404, "step": 1337 }, { "epoch": 0.31390604666507815, "grad_norm": 16.4421329498291, "learning_rate": 1.5942394536339804e-05, "loss": 22.6582, "step": 1338 }, { "epoch": 0.31414065507065747, "grad_norm": 19.29064178466797, "learning_rate": 1.5936321854536473e-05, "loss": 26.1677, "step": 1339 }, { "epoch": 0.31437526347623673, "grad_norm": 18.517045974731445, "learning_rate": 1.593024579042624e-05, "loss": 24.6511, "step": 1340 }, { "epoch": 0.314609871881816, "grad_norm": 19.48556137084961, "learning_rate": 1.592416634747102e-05, "loss": 22.1837, "step": 1341 }, { "epoch": 0.3148444802873953, "grad_norm": 15.818485260009766, "learning_rate": 1.5918083529134678e-05, "loss": 22.8047, "step": 1342 }, { "epoch": 0.3150790886929746, "grad_norm": 21.156221389770508, "learning_rate": 1.5911997338882986e-05, "loss": 28.6127, "step": 1343 }, { "epoch": 0.31531369709855384, "grad_norm": 18.946468353271484, "learning_rate": 1.590590778018364e-05, "loss": 24.7079, "step": 1344 }, { "epoch": 0.31554830550413315, "grad_norm": 19.86614418029785, "learning_rate": 1.5899814856506247e-05, "loss": 25.1197, "step": 1345 }, { "epoch": 0.3157829139097124, "grad_norm": 17.233610153198242, "learning_rate": 1.5893718571322353e-05, "loss": 25.7853, "step": 1346 }, { "epoch": 0.3160175223152917, "grad_norm": 20.208099365234375, "learning_rate": 1.58876189281054e-05, "loss": 29.2005, "step": 1347 }, { "epoch": 0.316252130720871, "grad_norm": 21.779481887817383, "learning_rate": 1.588151593033075e-05, "loss": 28.2304, "step": 1348 }, { "epoch": 0.31648673912645026, "grad_norm": 19.096054077148438, "learning_rate": 1.587540958147568e-05, "loss": 26.6509, "step": 1349 }, { "epoch": 0.3167213475320296, "grad_norm": 17.21601104736328, "learning_rate": 1.5869299885019364e-05, "loss": 27.8963, "step": 1350 }, { "epoch": 0.31695595593760884, "grad_norm": 16.030746459960938, "learning_rate": 1.5863186844442903e-05, "loss": 25.1068, "step": 1351 }, { "epoch": 0.3171905643431881, "grad_norm": 21.81741714477539, "learning_rate": 1.585707046322928e-05, "loss": 28.5656, "step": 1352 }, { "epoch": 0.3174251727487674, "grad_norm": 21.372766494750977, "learning_rate": 1.5850950744863397e-05, "loss": 28.9391, "step": 1353 }, { "epoch": 0.3176597811543467, "grad_norm": 20.329721450805664, "learning_rate": 1.5844827692832065e-05, "loss": 26.8324, "step": 1354 }, { "epoch": 0.31789438955992594, "grad_norm": 17.098405838012695, "learning_rate": 1.5838701310623967e-05, "loss": 24.596, "step": 1355 }, { "epoch": 0.31812899796550526, "grad_norm": 19.970237731933594, "learning_rate": 1.5832571601729707e-05, "loss": 26.2071, "step": 1356 }, { "epoch": 0.3183636063710845, "grad_norm": 19.118600845336914, "learning_rate": 1.582643856964178e-05, "loss": 27.2879, "step": 1357 }, { "epoch": 0.3185982147766638, "grad_norm": 19.101579666137695, "learning_rate": 1.5820302217854567e-05, "loss": 26.0828, "step": 1358 }, { "epoch": 0.3188328231822431, "grad_norm": 17.697235107421875, "learning_rate": 1.5814162549864344e-05, "loss": 26.1887, "step": 1359 }, { "epoch": 0.31906743158782236, "grad_norm": 19.19200897216797, "learning_rate": 1.580801956916928e-05, "loss": 25.2194, "step": 1360 }, { "epoch": 0.3193020399934016, "grad_norm": 18.40789222717285, "learning_rate": 1.580187327926943e-05, "loss": 25.3298, "step": 1361 }, { "epoch": 0.31953664839898094, "grad_norm": 18.715089797973633, "learning_rate": 1.5795723683666734e-05, "loss": 28.0603, "step": 1362 }, { "epoch": 0.3197712568045602, "grad_norm": 18.584714889526367, "learning_rate": 1.578957078586501e-05, "loss": 26.89, "step": 1363 }, { "epoch": 0.32000586521013946, "grad_norm": 18.389698028564453, "learning_rate": 1.578341458936996e-05, "loss": 29.6921, "step": 1364 }, { "epoch": 0.3202404736157188, "grad_norm": 22.419038772583008, "learning_rate": 1.5777255097689176e-05, "loss": 30.3562, "step": 1365 }, { "epoch": 0.32047508202129804, "grad_norm": 18.018484115600586, "learning_rate": 1.5771092314332114e-05, "loss": 26.7455, "step": 1366 }, { "epoch": 0.3207096904268773, "grad_norm": 18.07974624633789, "learning_rate": 1.5764926242810116e-05, "loss": 27.0674, "step": 1367 }, { "epoch": 0.3209442988324566, "grad_norm": 18.324134826660156, "learning_rate": 1.5758756886636385e-05, "loss": 25.0009, "step": 1368 }, { "epoch": 0.3211789072380359, "grad_norm": 25.426300048828125, "learning_rate": 1.5752584249326007e-05, "loss": 26.3721, "step": 1369 }, { "epoch": 0.32141351564361514, "grad_norm": 21.960050582885742, "learning_rate": 1.574640833439593e-05, "loss": 23.4792, "step": 1370 }, { "epoch": 0.32164812404919446, "grad_norm": 18.487686157226562, "learning_rate": 1.5740229145364977e-05, "loss": 25.7327, "step": 1371 }, { "epoch": 0.3218827324547737, "grad_norm": 17.656513214111328, "learning_rate": 1.5734046685753827e-05, "loss": 29.6647, "step": 1372 }, { "epoch": 0.322117340860353, "grad_norm": 19.15076446533203, "learning_rate": 1.5727860959085035e-05, "loss": 26.9973, "step": 1373 }, { "epoch": 0.3223519492659323, "grad_norm": 20.733562469482422, "learning_rate": 1.5721671968883004e-05, "loss": 25.6094, "step": 1374 }, { "epoch": 0.32258655767151156, "grad_norm": 18.7465877532959, "learning_rate": 1.5715479718674e-05, "loss": 26.3333, "step": 1375 }, { "epoch": 0.3228211660770909, "grad_norm": 17.70805549621582, "learning_rate": 1.5709284211986155e-05, "loss": 26.4941, "step": 1376 }, { "epoch": 0.32305577448267014, "grad_norm": 18.477338790893555, "learning_rate": 1.570308545234945e-05, "loss": 25.6351, "step": 1377 }, { "epoch": 0.3232903828882494, "grad_norm": 17.589942932128906, "learning_rate": 1.5696883443295715e-05, "loss": 27.1919, "step": 1378 }, { "epoch": 0.3235249912938287, "grad_norm": 16.593046188354492, "learning_rate": 1.569067818835864e-05, "loss": 22.0843, "step": 1379 }, { "epoch": 0.323759599699408, "grad_norm": 21.963455200195312, "learning_rate": 1.5684469691073755e-05, "loss": 30.254, "step": 1380 }, { "epoch": 0.32399420810498725, "grad_norm": 17.479267120361328, "learning_rate": 1.567825795497845e-05, "loss": 31.6958, "step": 1381 }, { "epoch": 0.32422881651056656, "grad_norm": 31.36265754699707, "learning_rate": 1.567204298361195e-05, "loss": 22.6793, "step": 1382 }, { "epoch": 0.3244634249161458, "grad_norm": 32.67985534667969, "learning_rate": 1.5665824780515325e-05, "loss": 23.1844, "step": 1383 }, { "epoch": 0.3246980333217251, "grad_norm": 21.399192810058594, "learning_rate": 1.5659603349231494e-05, "loss": 23.9762, "step": 1384 }, { "epoch": 0.3249326417273044, "grad_norm": 18.648597717285156, "learning_rate": 1.5653378693305203e-05, "loss": 22.3561, "step": 1385 }, { "epoch": 0.32516725013288367, "grad_norm": 17.178918838500977, "learning_rate": 1.5647150816283044e-05, "loss": 24.5768, "step": 1386 }, { "epoch": 0.32540185853846293, "grad_norm": 21.628843307495117, "learning_rate": 1.564091972171344e-05, "loss": 26.2201, "step": 1387 }, { "epoch": 0.32563646694404225, "grad_norm": 36.997108459472656, "learning_rate": 1.563468541314665e-05, "loss": 21.7775, "step": 1388 }, { "epoch": 0.3258710753496215, "grad_norm": 19.49287986755371, "learning_rate": 1.5628447894134765e-05, "loss": 23.0785, "step": 1389 }, { "epoch": 0.32610568375520077, "grad_norm": 17.167713165283203, "learning_rate": 1.5622207168231697e-05, "loss": 22.5999, "step": 1390 }, { "epoch": 0.3263402921607801, "grad_norm": 18.18600845336914, "learning_rate": 1.5615963238993202e-05, "loss": 27.3601, "step": 1391 }, { "epoch": 0.32657490056635935, "grad_norm": 14.505325317382812, "learning_rate": 1.5609716109976845e-05, "loss": 22.0825, "step": 1392 }, { "epoch": 0.3268095089719386, "grad_norm": 17.523738861083984, "learning_rate": 1.5603465784742017e-05, "loss": 26.7062, "step": 1393 }, { "epoch": 0.32704411737751793, "grad_norm": 17.642032623291016, "learning_rate": 1.5597212266849937e-05, "loss": 25.547, "step": 1394 }, { "epoch": 0.3272787257830972, "grad_norm": 18.04656410217285, "learning_rate": 1.559095555986364e-05, "loss": 23.6604, "step": 1395 }, { "epoch": 0.32751333418867645, "grad_norm": 17.67923355102539, "learning_rate": 1.5584695667347972e-05, "loss": 27.3677, "step": 1396 }, { "epoch": 0.32774794259425577, "grad_norm": 18.205833435058594, "learning_rate": 1.5578432592869602e-05, "loss": 27.0885, "step": 1397 }, { "epoch": 0.32798255099983503, "grad_norm": 20.44559669494629, "learning_rate": 1.5572166339997013e-05, "loss": 25.7911, "step": 1398 }, { "epoch": 0.32821715940541435, "grad_norm": 22.565027236938477, "learning_rate": 1.5565896912300487e-05, "loss": 27.5551, "step": 1399 }, { "epoch": 0.3284517678109936, "grad_norm": 19.292898178100586, "learning_rate": 1.5559624313352132e-05, "loss": 27.4214, "step": 1400 }, { "epoch": 0.3286863762165729, "grad_norm": 19.205474853515625, "learning_rate": 1.5553348546725842e-05, "loss": 26.4496, "step": 1401 }, { "epoch": 0.3289209846221522, "grad_norm": 17.501068115234375, "learning_rate": 1.554706961599734e-05, "loss": 29.6082, "step": 1402 }, { "epoch": 0.32915559302773145, "grad_norm": 18.1934757232666, "learning_rate": 1.554078752474413e-05, "loss": 24.5478, "step": 1403 }, { "epoch": 0.3293902014333107, "grad_norm": 19.419784545898438, "learning_rate": 1.5534502276545534e-05, "loss": 26.9829, "step": 1404 }, { "epoch": 0.32962480983889003, "grad_norm": 20.129655838012695, "learning_rate": 1.552821387498266e-05, "loss": 28.3664, "step": 1405 }, { "epoch": 0.3298594182444693, "grad_norm": 19.243032455444336, "learning_rate": 1.5521922323638416e-05, "loss": 26.8341, "step": 1406 }, { "epoch": 0.33009402665004856, "grad_norm": 17.437408447265625, "learning_rate": 1.5515627626097506e-05, "loss": 26.2258, "step": 1407 }, { "epoch": 0.3303286350556279, "grad_norm": 16.514690399169922, "learning_rate": 1.5509329785946432e-05, "loss": 24.6283, "step": 1408 }, { "epoch": 0.33056324346120713, "grad_norm": 15.776262283325195, "learning_rate": 1.550302880677348e-05, "loss": 24.2255, "step": 1409 }, { "epoch": 0.3307978518667864, "grad_norm": 23.833637237548828, "learning_rate": 1.549672469216872e-05, "loss": 25.9375, "step": 1410 }, { "epoch": 0.3310324602723657, "grad_norm": 23.297142028808594, "learning_rate": 1.549041744572402e-05, "loss": 23.637, "step": 1411 }, { "epoch": 0.331267068677945, "grad_norm": 16.897138595581055, "learning_rate": 1.548410707103303e-05, "loss": 24.2748, "step": 1412 }, { "epoch": 0.33150167708352424, "grad_norm": 24.3472843170166, "learning_rate": 1.547779357169117e-05, "loss": 26.1249, "step": 1413 }, { "epoch": 0.33173628548910356, "grad_norm": 17.559490203857422, "learning_rate": 1.547147695129565e-05, "loss": 26.1864, "step": 1414 }, { "epoch": 0.3319708938946828, "grad_norm": 17.25960350036621, "learning_rate": 1.5465157213445467e-05, "loss": 28.067, "step": 1415 }, { "epoch": 0.3322055023002621, "grad_norm": 20.372108459472656, "learning_rate": 1.5458834361741373e-05, "loss": 24.218, "step": 1416 }, { "epoch": 0.3324401107058414, "grad_norm": 20.120271682739258, "learning_rate": 1.5452508399785914e-05, "loss": 28.4475, "step": 1417 }, { "epoch": 0.33267471911142066, "grad_norm": 16.97324562072754, "learning_rate": 1.54461793311834e-05, "loss": 23.864, "step": 1418 }, { "epoch": 0.3329093275169999, "grad_norm": 17.416810989379883, "learning_rate": 1.543984715953991e-05, "loss": 25.5574, "step": 1419 }, { "epoch": 0.33314393592257924, "grad_norm": 18.301795959472656, "learning_rate": 1.5433511888463288e-05, "loss": 20.6006, "step": 1420 }, { "epoch": 0.3333785443281585, "grad_norm": 17.947986602783203, "learning_rate": 1.5427173521563153e-05, "loss": 26.5998, "step": 1421 }, { "epoch": 0.33361315273373776, "grad_norm": 18.55668830871582, "learning_rate": 1.5420832062450883e-05, "loss": 25.756, "step": 1422 }, { "epoch": 0.3338477611393171, "grad_norm": 18.21746063232422, "learning_rate": 1.5414487514739612e-05, "loss": 26.9847, "step": 1423 }, { "epoch": 0.33408236954489634, "grad_norm": 16.374433517456055, "learning_rate": 1.5408139882044247e-05, "loss": 24.8271, "step": 1424 }, { "epoch": 0.33431697795047566, "grad_norm": 21.413835525512695, "learning_rate": 1.5401789167981438e-05, "loss": 25.3156, "step": 1425 }, { "epoch": 0.3345515863560549, "grad_norm": 20.13751792907715, "learning_rate": 1.5395435376169606e-05, "loss": 29.0333, "step": 1426 }, { "epoch": 0.3347861947616342, "grad_norm": 17.704387664794922, "learning_rate": 1.5389078510228915e-05, "loss": 22.8983, "step": 1427 }, { "epoch": 0.3350208031672135, "grad_norm": 19.692588806152344, "learning_rate": 1.5382718573781277e-05, "loss": 24.6865, "step": 1428 }, { "epoch": 0.33525541157279276, "grad_norm": 18.251798629760742, "learning_rate": 1.537635557045037e-05, "loss": 24.9755, "step": 1429 }, { "epoch": 0.335490019978372, "grad_norm": 20.83839225769043, "learning_rate": 1.5369989503861598e-05, "loss": 25.6819, "step": 1430 }, { "epoch": 0.33572462838395134, "grad_norm": 18.38429069519043, "learning_rate": 1.536362037764213e-05, "loss": 28.3984, "step": 1431 }, { "epoch": 0.3359592367895306, "grad_norm": 21.26182746887207, "learning_rate": 1.5357248195420862e-05, "loss": 24.8866, "step": 1432 }, { "epoch": 0.33619384519510986, "grad_norm": 16.565027236938477, "learning_rate": 1.5350872960828448e-05, "loss": 23.5202, "step": 1433 }, { "epoch": 0.3364284536006892, "grad_norm": 19.617984771728516, "learning_rate": 1.5344494677497265e-05, "loss": 25.7624, "step": 1434 }, { "epoch": 0.33666306200626844, "grad_norm": 19.99993324279785, "learning_rate": 1.5338113349061438e-05, "loss": 29.8618, "step": 1435 }, { "epoch": 0.3368976704118477, "grad_norm": 21.64607810974121, "learning_rate": 1.5331728979156813e-05, "loss": 26.4535, "step": 1436 }, { "epoch": 0.337132278817427, "grad_norm": 20.703067779541016, "learning_rate": 1.5325341571420995e-05, "loss": 26.4389, "step": 1437 }, { "epoch": 0.3373668872230063, "grad_norm": 19.926908493041992, "learning_rate": 1.5318951129493295e-05, "loss": 24.2735, "step": 1438 }, { "epoch": 0.33760149562858555, "grad_norm": 17.84385871887207, "learning_rate": 1.531255765701476e-05, "loss": 26.2129, "step": 1439 }, { "epoch": 0.33783610403416486, "grad_norm": 18.189851760864258, "learning_rate": 1.5306161157628165e-05, "loss": 26.8488, "step": 1440 }, { "epoch": 0.3380707124397441, "grad_norm": 18.136627197265625, "learning_rate": 1.529976163497801e-05, "loss": 27.0014, "step": 1441 }, { "epoch": 0.3383053208453234, "grad_norm": 17.304121017456055, "learning_rate": 1.5293359092710527e-05, "loss": 28.1634, "step": 1442 }, { "epoch": 0.3385399292509027, "grad_norm": 19.09376335144043, "learning_rate": 1.528695353447365e-05, "loss": 23.451, "step": 1443 }, { "epoch": 0.33877453765648197, "grad_norm": 22.653467178344727, "learning_rate": 1.5280544963917037e-05, "loss": 28.5957, "step": 1444 }, { "epoch": 0.33900914606206123, "grad_norm": 19.487205505371094, "learning_rate": 1.5274133384692075e-05, "loss": 23.7564, "step": 1445 }, { "epoch": 0.33924375446764055, "grad_norm": 15.387232780456543, "learning_rate": 1.5267718800451846e-05, "loss": 23.4795, "step": 1446 }, { "epoch": 0.3394783628732198, "grad_norm": 16.328481674194336, "learning_rate": 1.526130121485116e-05, "loss": 24.7525, "step": 1447 }, { "epoch": 0.3397129712787991, "grad_norm": 18.19746971130371, "learning_rate": 1.5254880631546531e-05, "loss": 25.226, "step": 1448 }, { "epoch": 0.3399475796843784, "grad_norm": 19.493446350097656, "learning_rate": 1.5248457054196179e-05, "loss": 31.5969, "step": 1449 }, { "epoch": 0.34018218808995765, "grad_norm": 19.330110549926758, "learning_rate": 1.5242030486460034e-05, "loss": 23.1151, "step": 1450 }, { "epoch": 0.34041679649553697, "grad_norm": 20.09644889831543, "learning_rate": 1.5235600931999725e-05, "loss": 23.8125, "step": 1451 }, { "epoch": 0.34065140490111623, "grad_norm": 21.337249755859375, "learning_rate": 1.5229168394478589e-05, "loss": 32.0706, "step": 1452 }, { "epoch": 0.3408860133066955, "grad_norm": 22.048065185546875, "learning_rate": 1.5222732877561655e-05, "loss": 27.2905, "step": 1453 }, { "epoch": 0.3411206217122748, "grad_norm": 18.16053009033203, "learning_rate": 1.5216294384915658e-05, "loss": 26.6681, "step": 1454 }, { "epoch": 0.34135523011785407, "grad_norm": 21.35779571533203, "learning_rate": 1.520985292020902e-05, "loss": 29.938, "step": 1455 }, { "epoch": 0.34158983852343333, "grad_norm": 15.689915657043457, "learning_rate": 1.5203408487111864e-05, "loss": 25.7252, "step": 1456 }, { "epoch": 0.34182444692901265, "grad_norm": 19.28419303894043, "learning_rate": 1.5196961089296e-05, "loss": 25.404, "step": 1457 }, { "epoch": 0.3420590553345919, "grad_norm": 24.765472412109375, "learning_rate": 1.5190510730434922e-05, "loss": 25.4626, "step": 1458 }, { "epoch": 0.3422936637401712, "grad_norm": 18.476770401000977, "learning_rate": 1.5184057414203826e-05, "loss": 20.6302, "step": 1459 }, { "epoch": 0.3425282721457505, "grad_norm": 21.160953521728516, "learning_rate": 1.5177601144279579e-05, "loss": 24.9152, "step": 1460 }, { "epoch": 0.34276288055132975, "grad_norm": 17.7634334564209, "learning_rate": 1.517114192434074e-05, "loss": 29.534, "step": 1461 }, { "epoch": 0.342997488956909, "grad_norm": 24.3446102142334, "learning_rate": 1.5164679758067537e-05, "loss": 25.207, "step": 1462 }, { "epoch": 0.34323209736248833, "grad_norm": 19.217750549316406, "learning_rate": 1.5158214649141892e-05, "loss": 26.7023, "step": 1463 }, { "epoch": 0.3434667057680676, "grad_norm": 19.73572540283203, "learning_rate": 1.5151746601247395e-05, "loss": 25.7884, "step": 1464 }, { "epoch": 0.34370131417364685, "grad_norm": 22.245384216308594, "learning_rate": 1.514527561806931e-05, "loss": 28.8623, "step": 1465 }, { "epoch": 0.34393592257922617, "grad_norm": 18.246522903442383, "learning_rate": 1.5138801703294572e-05, "loss": 23.488, "step": 1466 }, { "epoch": 0.34417053098480543, "grad_norm": 17.286611557006836, "learning_rate": 1.5132324860611795e-05, "loss": 20.4512, "step": 1467 }, { "epoch": 0.3444051393903847, "grad_norm": 17.767892837524414, "learning_rate": 1.5125845093711256e-05, "loss": 24.6589, "step": 1468 }, { "epoch": 0.344639747795964, "grad_norm": 17.89261817932129, "learning_rate": 1.5119362406284892e-05, "loss": 22.2347, "step": 1469 }, { "epoch": 0.3448743562015433, "grad_norm": 18.01841926574707, "learning_rate": 1.5112876802026316e-05, "loss": 25.8361, "step": 1470 }, { "epoch": 0.34510896460712254, "grad_norm": 19.910533905029297, "learning_rate": 1.5106388284630789e-05, "loss": 24.7846, "step": 1471 }, { "epoch": 0.34534357301270185, "grad_norm": 21.317941665649414, "learning_rate": 1.509989685779525e-05, "loss": 29.9426, "step": 1472 }, { "epoch": 0.3455781814182811, "grad_norm": 16.693756103515625, "learning_rate": 1.5093402525218275e-05, "loss": 27.7801, "step": 1473 }, { "epoch": 0.34581278982386043, "grad_norm": 16.29610252380371, "learning_rate": 1.5086905290600107e-05, "loss": 19.4932, "step": 1474 }, { "epoch": 0.3460473982294397, "grad_norm": 19.797170639038086, "learning_rate": 1.5080405157642648e-05, "loss": 28.2571, "step": 1475 }, { "epoch": 0.34628200663501896, "grad_norm": 17.863800048828125, "learning_rate": 1.5073902130049444e-05, "loss": 21.6356, "step": 1476 }, { "epoch": 0.3465166150405983, "grad_norm": 19.407682418823242, "learning_rate": 1.5067396211525682e-05, "loss": 30.4775, "step": 1477 }, { "epoch": 0.34675122344617754, "grad_norm": 22.26312255859375, "learning_rate": 1.5060887405778212e-05, "loss": 29.103, "step": 1478 }, { "epoch": 0.3469858318517568, "grad_norm": 19.919633865356445, "learning_rate": 1.5054375716515522e-05, "loss": 28.029, "step": 1479 }, { "epoch": 0.3472204402573361, "grad_norm": 18.054658889770508, "learning_rate": 1.504786114744774e-05, "loss": 29.6736, "step": 1480 }, { "epoch": 0.3474550486629154, "grad_norm": 16.461650848388672, "learning_rate": 1.5041343702286643e-05, "loss": 22.2478, "step": 1481 }, { "epoch": 0.34768965706849464, "grad_norm": 18.137012481689453, "learning_rate": 1.5034823384745636e-05, "loss": 24.2746, "step": 1482 }, { "epoch": 0.34792426547407396, "grad_norm": 16.768310546875, "learning_rate": 1.5028300198539767e-05, "loss": 19.2091, "step": 1483 }, { "epoch": 0.3481588738796532, "grad_norm": 16.815082550048828, "learning_rate": 1.5021774147385718e-05, "loss": 24.7041, "step": 1484 }, { "epoch": 0.3483934822852325, "grad_norm": 18.17753791809082, "learning_rate": 1.5015245235001803e-05, "loss": 26.0463, "step": 1485 }, { "epoch": 0.3486280906908118, "grad_norm": 18.54001235961914, "learning_rate": 1.5008713465107966e-05, "loss": 26.3615, "step": 1486 }, { "epoch": 0.34886269909639106, "grad_norm": 18.421743392944336, "learning_rate": 1.5002178841425786e-05, "loss": 25.5161, "step": 1487 }, { "epoch": 0.3490973075019703, "grad_norm": 25.678590774536133, "learning_rate": 1.4995641367678449e-05, "loss": 27.7851, "step": 1488 }, { "epoch": 0.34933191590754964, "grad_norm": 19.947723388671875, "learning_rate": 1.4989101047590781e-05, "loss": 26.7072, "step": 1489 }, { "epoch": 0.3495665243131289, "grad_norm": 19.151973724365234, "learning_rate": 1.498255788488923e-05, "loss": 25.0219, "step": 1490 }, { "epoch": 0.34980113271870816, "grad_norm": 17.414703369140625, "learning_rate": 1.497601188330186e-05, "loss": 25.3072, "step": 1491 }, { "epoch": 0.3500357411242875, "grad_norm": 18.634729385375977, "learning_rate": 1.4969463046558348e-05, "loss": 23.3909, "step": 1492 }, { "epoch": 0.35027034952986674, "grad_norm": 23.10980224609375, "learning_rate": 1.4962911378389987e-05, "loss": 25.4268, "step": 1493 }, { "epoch": 0.350504957935446, "grad_norm": 19.971696853637695, "learning_rate": 1.4956356882529695e-05, "loss": 23.7264, "step": 1494 }, { "epoch": 0.3507395663410253, "grad_norm": 19.842042922973633, "learning_rate": 1.4949799562711989e-05, "loss": 23.503, "step": 1495 }, { "epoch": 0.3509741747466046, "grad_norm": 19.56013298034668, "learning_rate": 1.4943239422672994e-05, "loss": 25.7383, "step": 1496 }, { "epoch": 0.3512087831521839, "grad_norm": 22.278284072875977, "learning_rate": 1.4936676466150456e-05, "loss": 28.4195, "step": 1497 }, { "epoch": 0.35144339155776316, "grad_norm": 17.531326293945312, "learning_rate": 1.4930110696883708e-05, "loss": 28.5798, "step": 1498 }, { "epoch": 0.3516779999633424, "grad_norm": 23.930362701416016, "learning_rate": 1.4923542118613698e-05, "loss": 30.1342, "step": 1499 }, { "epoch": 0.35191260836892174, "grad_norm": 15.73001480102539, "learning_rate": 1.4916970735082967e-05, "loss": 19.509, "step": 1500 }, { "epoch": 0.352147216774501, "grad_norm": 18.887781143188477, "learning_rate": 1.4910396550035662e-05, "loss": 30.406, "step": 1501 }, { "epoch": 0.35238182518008027, "grad_norm": 21.448898315429688, "learning_rate": 1.4903819567217519e-05, "loss": 25.1694, "step": 1502 }, { "epoch": 0.3526164335856596, "grad_norm": 18.807361602783203, "learning_rate": 1.4897239790375871e-05, "loss": 26.9325, "step": 1503 }, { "epoch": 0.35285104199123885, "grad_norm": 27.738988876342773, "learning_rate": 1.4890657223259645e-05, "loss": 26.5018, "step": 1504 }, { "epoch": 0.3530856503968181, "grad_norm": 24.073596954345703, "learning_rate": 1.4884071869619351e-05, "loss": 22.792, "step": 1505 }, { "epoch": 0.3533202588023974, "grad_norm": 19.887222290039062, "learning_rate": 1.48774837332071e-05, "loss": 22.6674, "step": 1506 }, { "epoch": 0.3535548672079767, "grad_norm": 20.410457611083984, "learning_rate": 1.487089281777657e-05, "loss": 26.553, "step": 1507 }, { "epoch": 0.35378947561355595, "grad_norm": 15.818978309631348, "learning_rate": 1.4864299127083035e-05, "loss": 23.3691, "step": 1508 }, { "epoch": 0.35402408401913527, "grad_norm": 20.6457462310791, "learning_rate": 1.4857702664883354e-05, "loss": 29.1533, "step": 1509 }, { "epoch": 0.3542586924247145, "grad_norm": 18.950584411621094, "learning_rate": 1.4851103434935952e-05, "loss": 28.4021, "step": 1510 }, { "epoch": 0.3544933008302938, "grad_norm": 18.607990264892578, "learning_rate": 1.4844501441000839e-05, "loss": 24.495, "step": 1511 }, { "epoch": 0.3547279092358731, "grad_norm": 16.04279136657715, "learning_rate": 1.4837896686839598e-05, "loss": 21.1404, "step": 1512 }, { "epoch": 0.35496251764145237, "grad_norm": 19.893630981445312, "learning_rate": 1.4831289176215384e-05, "loss": 31.3393, "step": 1513 }, { "epoch": 0.35519712604703163, "grad_norm": 22.3310546875, "learning_rate": 1.4824678912892929e-05, "loss": 26.5082, "step": 1514 }, { "epoch": 0.35543173445261095, "grad_norm": 19.156057357788086, "learning_rate": 1.4818065900638522e-05, "loss": 26.8001, "step": 1515 }, { "epoch": 0.3556663428581902, "grad_norm": 19.16181182861328, "learning_rate": 1.4811450143220027e-05, "loss": 24.9041, "step": 1516 }, { "epoch": 0.35590095126376947, "grad_norm": 20.344091415405273, "learning_rate": 1.480483164440687e-05, "loss": 27.4526, "step": 1517 }, { "epoch": 0.3561355596693488, "grad_norm": 24.076208114624023, "learning_rate": 1.4798210407970037e-05, "loss": 28.5511, "step": 1518 }, { "epoch": 0.35637016807492805, "grad_norm": 20.040416717529297, "learning_rate": 1.4791586437682072e-05, "loss": 28.8009, "step": 1519 }, { "epoch": 0.35660477648050737, "grad_norm": 19.871307373046875, "learning_rate": 1.478495973731709e-05, "loss": 26.5992, "step": 1520 }, { "epoch": 0.35683938488608663, "grad_norm": 22.409698486328125, "learning_rate": 1.4778330310650739e-05, "loss": 25.4396, "step": 1521 }, { "epoch": 0.3570739932916659, "grad_norm": 24.36097526550293, "learning_rate": 1.4771698161460237e-05, "loss": 26.8602, "step": 1522 }, { "epoch": 0.3573086016972452, "grad_norm": 20.624250411987305, "learning_rate": 1.4765063293524352e-05, "loss": 25.4355, "step": 1523 }, { "epoch": 0.35754321010282447, "grad_norm": 21.320199966430664, "learning_rate": 1.4758425710623395e-05, "loss": 30.7128, "step": 1524 }, { "epoch": 0.35777781850840373, "grad_norm": 18.548826217651367, "learning_rate": 1.4751785416539228e-05, "loss": 23.5839, "step": 1525 }, { "epoch": 0.35801242691398305, "grad_norm": 18.616769790649414, "learning_rate": 1.4745142415055255e-05, "loss": 26.173, "step": 1526 }, { "epoch": 0.3582470353195623, "grad_norm": 18.58635139465332, "learning_rate": 1.4738496709956425e-05, "loss": 26.2305, "step": 1527 }, { "epoch": 0.3584816437251416, "grad_norm": 18.40369987487793, "learning_rate": 1.4731848305029224e-05, "loss": 26.1854, "step": 1528 }, { "epoch": 0.3587162521307209, "grad_norm": 17.921213150024414, "learning_rate": 1.4725197204061683e-05, "loss": 26.5028, "step": 1529 }, { "epoch": 0.35895086053630015, "grad_norm": 18.529375076293945, "learning_rate": 1.4718543410843362e-05, "loss": 27.3268, "step": 1530 }, { "epoch": 0.3591854689418794, "grad_norm": 20.647045135498047, "learning_rate": 1.471188692916536e-05, "loss": 26.3605, "step": 1531 }, { "epoch": 0.35942007734745873, "grad_norm": 17.74408721923828, "learning_rate": 1.4705227762820301e-05, "loss": 28.2416, "step": 1532 }, { "epoch": 0.359654685753038, "grad_norm": 19.715194702148438, "learning_rate": 1.4698565915602353e-05, "loss": 27.3746, "step": 1533 }, { "epoch": 0.35988929415861726, "grad_norm": 18.311267852783203, "learning_rate": 1.4691901391307189e-05, "loss": 27.919, "step": 1534 }, { "epoch": 0.3601239025641966, "grad_norm": 19.77170181274414, "learning_rate": 1.4685234193732028e-05, "loss": 24.608, "step": 1535 }, { "epoch": 0.36035851096977584, "grad_norm": 22.84170913696289, "learning_rate": 1.4678564326675602e-05, "loss": 23.902, "step": 1536 }, { "epoch": 0.3605931193753551, "grad_norm": 18.549043655395508, "learning_rate": 1.4671891793938167e-05, "loss": 26.0234, "step": 1537 }, { "epoch": 0.3608277277809344, "grad_norm": 17.4027042388916, "learning_rate": 1.4665216599321494e-05, "loss": 31.0177, "step": 1538 }, { "epoch": 0.3610623361865137, "grad_norm": 17.468429565429688, "learning_rate": 1.4658538746628876e-05, "loss": 29.0519, "step": 1539 }, { "epoch": 0.36129694459209294, "grad_norm": 20.621173858642578, "learning_rate": 1.465185823966512e-05, "loss": 30.7098, "step": 1540 }, { "epoch": 0.36153155299767226, "grad_norm": 19.286670684814453, "learning_rate": 1.4645175082236538e-05, "loss": 26.8262, "step": 1541 }, { "epoch": 0.3617661614032515, "grad_norm": 17.99787712097168, "learning_rate": 1.4638489278150965e-05, "loss": 27.1389, "step": 1542 }, { "epoch": 0.3620007698088308, "grad_norm": 18.427213668823242, "learning_rate": 1.4631800831217729e-05, "loss": 23.5259, "step": 1543 }, { "epoch": 0.3622353782144101, "grad_norm": 22.996620178222656, "learning_rate": 1.4625109745247676e-05, "loss": 26.7325, "step": 1544 }, { "epoch": 0.36246998661998936, "grad_norm": 21.828472137451172, "learning_rate": 1.4618416024053146e-05, "loss": 27.7233, "step": 1545 }, { "epoch": 0.3627045950255687, "grad_norm": 18.629419326782227, "learning_rate": 1.461171967144799e-05, "loss": 24.9703, "step": 1546 }, { "epoch": 0.36293920343114794, "grad_norm": 16.24488639831543, "learning_rate": 1.4605020691247554e-05, "loss": 26.0926, "step": 1547 }, { "epoch": 0.3631738118367272, "grad_norm": 17.035419464111328, "learning_rate": 1.459831908726868e-05, "loss": 23.5656, "step": 1548 }, { "epoch": 0.3634084202423065, "grad_norm": 17.893898010253906, "learning_rate": 1.45916148633297e-05, "loss": 24.1892, "step": 1549 }, { "epoch": 0.3636430286478858, "grad_norm": 18.81220245361328, "learning_rate": 1.458490802325045e-05, "loss": 25.9473, "step": 1550 }, { "epoch": 0.36387763705346504, "grad_norm": 17.08363151550293, "learning_rate": 1.457819857085225e-05, "loss": 24.0004, "step": 1551 }, { "epoch": 0.36411224545904436, "grad_norm": 17.612558364868164, "learning_rate": 1.4571486509957913e-05, "loss": 26.5337, "step": 1552 }, { "epoch": 0.3643468538646236, "grad_norm": 18.60142707824707, "learning_rate": 1.456477184439173e-05, "loss": 25.1421, "step": 1553 }, { "epoch": 0.3645814622702029, "grad_norm": 18.362051010131836, "learning_rate": 1.4558054577979482e-05, "loss": 26.7367, "step": 1554 }, { "epoch": 0.3648160706757822, "grad_norm": 18.48832130432129, "learning_rate": 1.4551334714548428e-05, "loss": 24.6771, "step": 1555 }, { "epoch": 0.36505067908136146, "grad_norm": 21.973060607910156, "learning_rate": 1.4544612257927315e-05, "loss": 26.6522, "step": 1556 }, { "epoch": 0.3652852874869407, "grad_norm": 18.536285400390625, "learning_rate": 1.4537887211946356e-05, "loss": 26.8517, "step": 1557 }, { "epoch": 0.36551989589252004, "grad_norm": 20.858154296875, "learning_rate": 1.4531159580437249e-05, "loss": 29.3254, "step": 1558 }, { "epoch": 0.3657545042980993, "grad_norm": 17.865039825439453, "learning_rate": 1.4524429367233159e-05, "loss": 25.8419, "step": 1559 }, { "epoch": 0.36598911270367857, "grad_norm": 20.811195373535156, "learning_rate": 1.4517696576168725e-05, "loss": 29.1635, "step": 1560 }, { "epoch": 0.3662237211092579, "grad_norm": 20.940196990966797, "learning_rate": 1.4510961211080055e-05, "loss": 25.9151, "step": 1561 }, { "epoch": 0.36645832951483714, "grad_norm": 20.061931610107422, "learning_rate": 1.450422327580472e-05, "loss": 25.3558, "step": 1562 }, { "epoch": 0.3666929379204164, "grad_norm": 21.182722091674805, "learning_rate": 1.4497482774181762e-05, "loss": 27.4211, "step": 1563 }, { "epoch": 0.3669275463259957, "grad_norm": 17.556318283081055, "learning_rate": 1.4490739710051679e-05, "loss": 21.4549, "step": 1564 }, { "epoch": 0.367162154731575, "grad_norm": 20.932043075561523, "learning_rate": 1.4483994087256427e-05, "loss": 28.2799, "step": 1565 }, { "epoch": 0.36739676313715425, "grad_norm": 21.720638275146484, "learning_rate": 1.447724590963943e-05, "loss": 26.9323, "step": 1566 }, { "epoch": 0.36763137154273356, "grad_norm": 17.385709762573242, "learning_rate": 1.447049518104556e-05, "loss": 22.4118, "step": 1567 }, { "epoch": 0.3678659799483128, "grad_norm": 18.06804847717285, "learning_rate": 1.4463741905321144e-05, "loss": 23.9471, "step": 1568 }, { "epoch": 0.36810058835389214, "grad_norm": 18.05966567993164, "learning_rate": 1.4456986086313962e-05, "loss": 27.3231, "step": 1569 }, { "epoch": 0.3683351967594714, "grad_norm": 20.81186294555664, "learning_rate": 1.4450227727873238e-05, "loss": 29.572, "step": 1570 }, { "epoch": 0.36856980516505067, "grad_norm": 20.341554641723633, "learning_rate": 1.444346683384965e-05, "loss": 22.5921, "step": 1571 }, { "epoch": 0.36880441357063, "grad_norm": 15.010462760925293, "learning_rate": 1.4436703408095314e-05, "loss": 20.7872, "step": 1572 }, { "epoch": 0.36903902197620925, "grad_norm": 20.50000762939453, "learning_rate": 1.4429937454463791e-05, "loss": 30.9071, "step": 1573 }, { "epoch": 0.3692736303817885, "grad_norm": 19.893735885620117, "learning_rate": 1.4423168976810089e-05, "loss": 25.6117, "step": 1574 }, { "epoch": 0.3695082387873678, "grad_norm": 18.709747314453125, "learning_rate": 1.4416397978990641e-05, "loss": 28.3868, "step": 1575 }, { "epoch": 0.3697428471929471, "grad_norm": 17.957500457763672, "learning_rate": 1.4409624464863326e-05, "loss": 25.7532, "step": 1576 }, { "epoch": 0.36997745559852635, "grad_norm": 21.350412368774414, "learning_rate": 1.4402848438287451e-05, "loss": 28.07, "step": 1577 }, { "epoch": 0.37021206400410567, "grad_norm": 18.64882469177246, "learning_rate": 1.439606990312376e-05, "loss": 26.1743, "step": 1578 }, { "epoch": 0.37044667240968493, "grad_norm": 20.970630645751953, "learning_rate": 1.4389288863234423e-05, "loss": 31.1986, "step": 1579 }, { "epoch": 0.3706812808152642, "grad_norm": 19.53044891357422, "learning_rate": 1.4382505322483038e-05, "loss": 24.6531, "step": 1580 }, { "epoch": 0.3709158892208435, "grad_norm": 18.44399070739746, "learning_rate": 1.4375719284734624e-05, "loss": 28.2109, "step": 1581 }, { "epoch": 0.37115049762642277, "grad_norm": 17.64105987548828, "learning_rate": 1.4368930753855633e-05, "loss": 24.2606, "step": 1582 }, { "epoch": 0.37138510603200203, "grad_norm": 17.614910125732422, "learning_rate": 1.436213973371392e-05, "loss": 24.0481, "step": 1583 }, { "epoch": 0.37161971443758135, "grad_norm": 20.615575790405273, "learning_rate": 1.4355346228178776e-05, "loss": 27.4489, "step": 1584 }, { "epoch": 0.3718543228431606, "grad_norm": 18.18313217163086, "learning_rate": 1.4348550241120902e-05, "loss": 28.5767, "step": 1585 }, { "epoch": 0.3720889312487399, "grad_norm": 16.81735610961914, "learning_rate": 1.4341751776412409e-05, "loss": 23.2263, "step": 1586 }, { "epoch": 0.3723235396543192, "grad_norm": 19.480186462402344, "learning_rate": 1.4334950837926822e-05, "loss": 28.7554, "step": 1587 }, { "epoch": 0.37255814805989845, "grad_norm": 19.161680221557617, "learning_rate": 1.4328147429539074e-05, "loss": 26.2925, "step": 1588 }, { "epoch": 0.3727927564654777, "grad_norm": 17.081140518188477, "learning_rate": 1.4321341555125514e-05, "loss": 29.4249, "step": 1589 }, { "epoch": 0.37302736487105703, "grad_norm": 16.568153381347656, "learning_rate": 1.4314533218563886e-05, "loss": 26.724, "step": 1590 }, { "epoch": 0.3732619732766363, "grad_norm": 21.450719833374023, "learning_rate": 1.4307722423733342e-05, "loss": 25.7524, "step": 1591 }, { "epoch": 0.37349658168221556, "grad_norm": 19.51421356201172, "learning_rate": 1.4300909174514424e-05, "loss": 29.26, "step": 1592 }, { "epoch": 0.3737311900877949, "grad_norm": 17.48053550720215, "learning_rate": 1.429409347478909e-05, "loss": 25.2743, "step": 1593 }, { "epoch": 0.37396579849337414, "grad_norm": 17.518892288208008, "learning_rate": 1.4287275328440684e-05, "loss": 24.6401, "step": 1594 }, { "epoch": 0.37420040689895345, "grad_norm": 18.956527709960938, "learning_rate": 1.4280454739353944e-05, "loss": 24.7979, "step": 1595 }, { "epoch": 0.3744350153045327, "grad_norm": 18.01894760131836, "learning_rate": 1.4273631711415003e-05, "loss": 26.0547, "step": 1596 }, { "epoch": 0.374669623710112, "grad_norm": 17.409658432006836, "learning_rate": 1.426680624851138e-05, "loss": 21.6017, "step": 1597 }, { "epoch": 0.3749042321156913, "grad_norm": 21.23649787902832, "learning_rate": 1.4259978354531985e-05, "loss": 30.0059, "step": 1598 }, { "epoch": 0.37513884052127056, "grad_norm": 17.595455169677734, "learning_rate": 1.4253148033367105e-05, "loss": 22.7107, "step": 1599 }, { "epoch": 0.3753734489268498, "grad_norm": 20.217323303222656, "learning_rate": 1.4246315288908424e-05, "loss": 24.4854, "step": 1600 }, { "epoch": 0.37560805733242913, "grad_norm": 17.911699295043945, "learning_rate": 1.4239480125048997e-05, "loss": 23.5606, "step": 1601 }, { "epoch": 0.3758426657380084, "grad_norm": 19.003408432006836, "learning_rate": 1.4232642545683258e-05, "loss": 25.0854, "step": 1602 }, { "epoch": 0.37607727414358766, "grad_norm": 16.799365997314453, "learning_rate": 1.4225802554707018e-05, "loss": 21.1207, "step": 1603 }, { "epoch": 0.376311882549167, "grad_norm": 16.806913375854492, "learning_rate": 1.4218960156017463e-05, "loss": 29.1366, "step": 1604 }, { "epoch": 0.37654649095474624, "grad_norm": 17.298246383666992, "learning_rate": 1.4212115353513155e-05, "loss": 30.8109, "step": 1605 }, { "epoch": 0.3767810993603255, "grad_norm": 16.86672019958496, "learning_rate": 1.4205268151094012e-05, "loss": 22.4916, "step": 1606 }, { "epoch": 0.3770157077659048, "grad_norm": 18.692577362060547, "learning_rate": 1.419841855266134e-05, "loss": 25.0616, "step": 1607 }, { "epoch": 0.3772503161714841, "grad_norm": 17.54092788696289, "learning_rate": 1.4191566562117786e-05, "loss": 23.323, "step": 1608 }, { "epoch": 0.37748492457706334, "grad_norm": 18.148717880249023, "learning_rate": 1.4184712183367384e-05, "loss": 22.1504, "step": 1609 }, { "epoch": 0.37771953298264266, "grad_norm": 18.711320877075195, "learning_rate": 1.4177855420315511e-05, "loss": 24.1188, "step": 1610 }, { "epoch": 0.3779541413882219, "grad_norm": 18.77186393737793, "learning_rate": 1.4170996276868908e-05, "loss": 26.4326, "step": 1611 }, { "epoch": 0.3781887497938012, "grad_norm": 15.61758804321289, "learning_rate": 1.416413475693568e-05, "loss": 25.5116, "step": 1612 }, { "epoch": 0.3784233581993805, "grad_norm": 18.698827743530273, "learning_rate": 1.4157270864425277e-05, "loss": 26.1846, "step": 1613 }, { "epoch": 0.37865796660495976, "grad_norm": 17.618755340576172, "learning_rate": 1.4150404603248495e-05, "loss": 23.2691, "step": 1614 }, { "epoch": 0.378892575010539, "grad_norm": 17.782896041870117, "learning_rate": 1.4143535977317496e-05, "loss": 21.0934, "step": 1615 }, { "epoch": 0.37912718341611834, "grad_norm": 16.69736099243164, "learning_rate": 1.4136664990545776e-05, "loss": 20.6374, "step": 1616 }, { "epoch": 0.3793617918216976, "grad_norm": 21.17028045654297, "learning_rate": 1.4129791646848186e-05, "loss": 29.0751, "step": 1617 }, { "epoch": 0.3795964002272769, "grad_norm": 18.595653533935547, "learning_rate": 1.4122915950140912e-05, "loss": 31.3797, "step": 1618 }, { "epoch": 0.3798310086328562, "grad_norm": 18.13829803466797, "learning_rate": 1.4116037904341482e-05, "loss": 25.9256, "step": 1619 }, { "epoch": 0.38006561703843544, "grad_norm": 15.836240768432617, "learning_rate": 1.4109157513368768e-05, "loss": 20.8172, "step": 1620 }, { "epoch": 0.38030022544401476, "grad_norm": 20.19683837890625, "learning_rate": 1.4102274781142969e-05, "loss": 28.7397, "step": 1621 }, { "epoch": 0.380534833849594, "grad_norm": 17.121557235717773, "learning_rate": 1.4095389711585625e-05, "loss": 27.5784, "step": 1622 }, { "epoch": 0.3807694422551733, "grad_norm": 20.32291603088379, "learning_rate": 1.4088502308619612e-05, "loss": 27.1695, "step": 1623 }, { "epoch": 0.3810040506607526, "grad_norm": 19.982988357543945, "learning_rate": 1.4081612576169124e-05, "loss": 28.9851, "step": 1624 }, { "epoch": 0.38123865906633186, "grad_norm": 21.558673858642578, "learning_rate": 1.4074720518159684e-05, "loss": 25.9191, "step": 1625 }, { "epoch": 0.3814732674719111, "grad_norm": 17.759984970092773, "learning_rate": 1.406782613851815e-05, "loss": 29.1232, "step": 1626 }, { "epoch": 0.38170787587749044, "grad_norm": 19.891630172729492, "learning_rate": 1.4060929441172693e-05, "loss": 23.9975, "step": 1627 }, { "epoch": 0.3819424842830697, "grad_norm": 17.424238204956055, "learning_rate": 1.405403043005281e-05, "loss": 28.4049, "step": 1628 }, { "epoch": 0.38217709268864897, "grad_norm": 22.01206398010254, "learning_rate": 1.4047129109089315e-05, "loss": 29.4212, "step": 1629 }, { "epoch": 0.3824117010942283, "grad_norm": 17.81673812866211, "learning_rate": 1.4040225482214334e-05, "loss": 25.4416, "step": 1630 }, { "epoch": 0.38264630949980755, "grad_norm": 16.505521774291992, "learning_rate": 1.403331955336131e-05, "loss": 25.2829, "step": 1631 }, { "epoch": 0.3828809179053868, "grad_norm": 20.518959045410156, "learning_rate": 1.4026411326465006e-05, "loss": 26.9719, "step": 1632 }, { "epoch": 0.3831155263109661, "grad_norm": 18.5076847076416, "learning_rate": 1.4019500805461475e-05, "loss": 26.9772, "step": 1633 }, { "epoch": 0.3833501347165454, "grad_norm": 19.255950927734375, "learning_rate": 1.4012587994288097e-05, "loss": 25.9846, "step": 1634 }, { "epoch": 0.38358474312212465, "grad_norm": 19.441789627075195, "learning_rate": 1.400567289688354e-05, "loss": 25.7526, "step": 1635 }, { "epoch": 0.38381935152770397, "grad_norm": 17.147438049316406, "learning_rate": 1.399875551718779e-05, "loss": 22.7405, "step": 1636 }, { "epoch": 0.38405395993328323, "grad_norm": 16.533632278442383, "learning_rate": 1.3991835859142123e-05, "loss": 22.4798, "step": 1637 }, { "epoch": 0.3842885683388625, "grad_norm": 19.592973709106445, "learning_rate": 1.3984913926689113e-05, "loss": 26.5186, "step": 1638 }, { "epoch": 0.3845231767444418, "grad_norm": 20.595441818237305, "learning_rate": 1.397798972377264e-05, "loss": 27.4859, "step": 1639 }, { "epoch": 0.38475778515002107, "grad_norm": 16.933917999267578, "learning_rate": 1.3971063254337866e-05, "loss": 25.8583, "step": 1640 }, { "epoch": 0.38499239355560033, "grad_norm": 23.557519912719727, "learning_rate": 1.3964134522331251e-05, "loss": 25.6478, "step": 1641 }, { "epoch": 0.38522700196117965, "grad_norm": 20.643686294555664, "learning_rate": 1.395720353170054e-05, "loss": 30.1585, "step": 1642 }, { "epoch": 0.3854616103667589, "grad_norm": 20.142303466796875, "learning_rate": 1.3950270286394769e-05, "loss": 26.486, "step": 1643 }, { "epoch": 0.38569621877233823, "grad_norm": 17.32579803466797, "learning_rate": 1.3943334790364258e-05, "loss": 26.0912, "step": 1644 }, { "epoch": 0.3859308271779175, "grad_norm": 16.827028274536133, "learning_rate": 1.3936397047560606e-05, "loss": 24.382, "step": 1645 }, { "epoch": 0.38616543558349675, "grad_norm": 17.119203567504883, "learning_rate": 1.392945706193669e-05, "loss": 21.6294, "step": 1646 }, { "epoch": 0.38640004398907607, "grad_norm": 17.73544692993164, "learning_rate": 1.3922514837446678e-05, "loss": 25.9894, "step": 1647 }, { "epoch": 0.38663465239465533, "grad_norm": 18.760679244995117, "learning_rate": 1.3915570378046e-05, "loss": 28.7429, "step": 1648 }, { "epoch": 0.3868692608002346, "grad_norm": 17.0336971282959, "learning_rate": 1.3908623687691365e-05, "loss": 20.723, "step": 1649 }, { "epoch": 0.3871038692058139, "grad_norm": 18.369260787963867, "learning_rate": 1.3901674770340755e-05, "loss": 21.3094, "step": 1650 }, { "epoch": 0.3873384776113932, "grad_norm": 22.78354835510254, "learning_rate": 1.3894723629953411e-05, "loss": 29.9588, "step": 1651 }, { "epoch": 0.38757308601697243, "grad_norm": 20.10565185546875, "learning_rate": 1.388777027048985e-05, "loss": 29.9266, "step": 1652 }, { "epoch": 0.38780769442255175, "grad_norm": 21.9425106048584, "learning_rate": 1.3880814695911857e-05, "loss": 25.168, "step": 1653 }, { "epoch": 0.388042302828131, "grad_norm": 19.311630249023438, "learning_rate": 1.3873856910182466e-05, "loss": 24.6377, "step": 1654 }, { "epoch": 0.3882769112337103, "grad_norm": 18.72785758972168, "learning_rate": 1.3866896917265983e-05, "loss": 25.796, "step": 1655 }, { "epoch": 0.3885115196392896, "grad_norm": 19.500185012817383, "learning_rate": 1.3859934721127965e-05, "loss": 25.5199, "step": 1656 }, { "epoch": 0.38874612804486885, "grad_norm": 19.18129539489746, "learning_rate": 1.3852970325735225e-05, "loss": 27.7934, "step": 1657 }, { "epoch": 0.3889807364504481, "grad_norm": 19.941051483154297, "learning_rate": 1.3846003735055831e-05, "loss": 24.7717, "step": 1658 }, { "epoch": 0.38921534485602743, "grad_norm": 19.548572540283203, "learning_rate": 1.38390349530591e-05, "loss": 25.1051, "step": 1659 }, { "epoch": 0.3894499532616067, "grad_norm": 21.696826934814453, "learning_rate": 1.3832063983715596e-05, "loss": 28.6587, "step": 1660 }, { "epoch": 0.38968456166718596, "grad_norm": 17.846088409423828, "learning_rate": 1.3825090830997136e-05, "loss": 25.9791, "step": 1661 }, { "epoch": 0.3899191700727653, "grad_norm": 16.82071876525879, "learning_rate": 1.3818115498876778e-05, "loss": 28.6393, "step": 1662 }, { "epoch": 0.39015377847834454, "grad_norm": 18.3749942779541, "learning_rate": 1.3811137991328813e-05, "loss": 20.042, "step": 1663 }, { "epoch": 0.3903883868839238, "grad_norm": 18.64090919494629, "learning_rate": 1.3804158312328784e-05, "loss": 27.1182, "step": 1664 }, { "epoch": 0.3906229952895031, "grad_norm": 18.488039016723633, "learning_rate": 1.3797176465853464e-05, "loss": 26.864, "step": 1665 }, { "epoch": 0.3908576036950824, "grad_norm": 21.86138343811035, "learning_rate": 1.3790192455880864e-05, "loss": 28.6922, "step": 1666 }, { "epoch": 0.3910922121006617, "grad_norm": 16.26580047607422, "learning_rate": 1.3783206286390229e-05, "loss": 26.231, "step": 1667 }, { "epoch": 0.39132682050624096, "grad_norm": 14.054533004760742, "learning_rate": 1.3776217961362028e-05, "loss": 22.9655, "step": 1668 }, { "epoch": 0.3915614289118202, "grad_norm": 22.109912872314453, "learning_rate": 1.3769227484777963e-05, "loss": 28.8768, "step": 1669 }, { "epoch": 0.39179603731739954, "grad_norm": 18.397951126098633, "learning_rate": 1.3762234860620965e-05, "loss": 23.3745, "step": 1670 }, { "epoch": 0.3920306457229788, "grad_norm": 19.854524612426758, "learning_rate": 1.3755240092875177e-05, "loss": 27.3601, "step": 1671 }, { "epoch": 0.39226525412855806, "grad_norm": 21.13009262084961, "learning_rate": 1.374824318552598e-05, "loss": 25.8766, "step": 1672 }, { "epoch": 0.3924998625341374, "grad_norm": 18.129369735717773, "learning_rate": 1.3741244142559957e-05, "loss": 23.9525, "step": 1673 }, { "epoch": 0.39273447093971664, "grad_norm": 17.18474769592285, "learning_rate": 1.3734242967964923e-05, "loss": 28.8326, "step": 1674 }, { "epoch": 0.3929690793452959, "grad_norm": 18.173213958740234, "learning_rate": 1.3727239665729895e-05, "loss": 24.0916, "step": 1675 }, { "epoch": 0.3932036877508752, "grad_norm": 20.1182861328125, "learning_rate": 1.3720234239845112e-05, "loss": 26.2788, "step": 1676 }, { "epoch": 0.3934382961564545, "grad_norm": 22.314010620117188, "learning_rate": 1.3713226694302015e-05, "loss": 22.4395, "step": 1677 }, { "epoch": 0.39367290456203374, "grad_norm": 21.243377685546875, "learning_rate": 1.3706217033093261e-05, "loss": 30.5686, "step": 1678 }, { "epoch": 0.39390751296761306, "grad_norm": 20.148412704467773, "learning_rate": 1.3699205260212702e-05, "loss": 27.0714, "step": 1679 }, { "epoch": 0.3941421213731923, "grad_norm": 22.915143966674805, "learning_rate": 1.3692191379655401e-05, "loss": 28.7876, "step": 1680 }, { "epoch": 0.3943767297787716, "grad_norm": 16.438764572143555, "learning_rate": 1.3685175395417623e-05, "loss": 21.7723, "step": 1681 }, { "epoch": 0.3946113381843509, "grad_norm": 23.206724166870117, "learning_rate": 1.3678157311496825e-05, "loss": 27.7859, "step": 1682 }, { "epoch": 0.39484594658993016, "grad_norm": 18.679975509643555, "learning_rate": 1.3671137131891666e-05, "loss": 24.0357, "step": 1683 }, { "epoch": 0.3950805549955094, "grad_norm": 18.090946197509766, "learning_rate": 1.3664114860601993e-05, "loss": 26.1253, "step": 1684 }, { "epoch": 0.39531516340108874, "grad_norm": 17.388174057006836, "learning_rate": 1.3657090501628855e-05, "loss": 24.2169, "step": 1685 }, { "epoch": 0.395549771806668, "grad_norm": 17.6280460357666, "learning_rate": 1.3650064058974479e-05, "loss": 25.9825, "step": 1686 }, { "epoch": 0.39578438021224727, "grad_norm": 18.764928817749023, "learning_rate": 1.3643035536642285e-05, "loss": 27.8222, "step": 1687 }, { "epoch": 0.3960189886178266, "grad_norm": 18.548873901367188, "learning_rate": 1.363600493863688e-05, "loss": 26.7912, "step": 1688 }, { "epoch": 0.39625359702340585, "grad_norm": 16.924978256225586, "learning_rate": 1.362897226896405e-05, "loss": 26.3054, "step": 1689 }, { "epoch": 0.3964882054289851, "grad_norm": 20.989408493041992, "learning_rate": 1.3621937531630758e-05, "loss": 26.2364, "step": 1690 }, { "epoch": 0.3967228138345644, "grad_norm": 23.0881404876709, "learning_rate": 1.3614900730645153e-05, "loss": 23.593, "step": 1691 }, { "epoch": 0.3969574222401437, "grad_norm": 18.186513900756836, "learning_rate": 1.3607861870016555e-05, "loss": 23.6715, "step": 1692 }, { "epoch": 0.397192030645723, "grad_norm": 18.546342849731445, "learning_rate": 1.360082095375546e-05, "loss": 23.6129, "step": 1693 }, { "epoch": 0.39742663905130227, "grad_norm": 20.808300018310547, "learning_rate": 1.3593777985873535e-05, "loss": 25.2624, "step": 1694 }, { "epoch": 0.39766124745688153, "grad_norm": 16.66359519958496, "learning_rate": 1.3586732970383612e-05, "loss": 27.1144, "step": 1695 }, { "epoch": 0.39789585586246085, "grad_norm": 17.124536514282227, "learning_rate": 1.3579685911299694e-05, "loss": 27.9866, "step": 1696 }, { "epoch": 0.3981304642680401, "grad_norm": 18.269763946533203, "learning_rate": 1.3572636812636943e-05, "loss": 25.8302, "step": 1697 }, { "epoch": 0.39836507267361937, "grad_norm": 19.36003303527832, "learning_rate": 1.3565585678411693e-05, "loss": 26.8186, "step": 1698 }, { "epoch": 0.3985996810791987, "grad_norm": 18.39960479736328, "learning_rate": 1.3558532512641428e-05, "loss": 28.6862, "step": 1699 }, { "epoch": 0.39883428948477795, "grad_norm": 16.478178024291992, "learning_rate": 1.3551477319344795e-05, "loss": 25.415, "step": 1700 }, { "epoch": 0.3990688978903572, "grad_norm": 20.577341079711914, "learning_rate": 1.3544420102541592e-05, "loss": 27.0945, "step": 1701 }, { "epoch": 0.39930350629593653, "grad_norm": 21.716699600219727, "learning_rate": 1.3537360866252773e-05, "loss": 29.2191, "step": 1702 }, { "epoch": 0.3995381147015158, "grad_norm": 19.637311935424805, "learning_rate": 1.3530299614500444e-05, "loss": 29.7047, "step": 1703 }, { "epoch": 0.39977272310709505, "grad_norm": 20.63840103149414, "learning_rate": 1.3523236351307856e-05, "loss": 28.0499, "step": 1704 }, { "epoch": 0.40000733151267437, "grad_norm": 18.016063690185547, "learning_rate": 1.3516171080699407e-05, "loss": 23.3273, "step": 1705 }, { "epoch": 0.40024193991825363, "grad_norm": 17.719999313354492, "learning_rate": 1.3509103806700639e-05, "loss": 26.6645, "step": 1706 }, { "epoch": 0.4004765483238329, "grad_norm": 19.553359985351562, "learning_rate": 1.3502034533338236e-05, "loss": 28.792, "step": 1707 }, { "epoch": 0.4007111567294122, "grad_norm": 22.447250366210938, "learning_rate": 1.3494963264640022e-05, "loss": 28.9882, "step": 1708 }, { "epoch": 0.40094576513499147, "grad_norm": 19.16659164428711, "learning_rate": 1.3487890004634953e-05, "loss": 25.8242, "step": 1709 }, { "epoch": 0.40118037354057073, "grad_norm": 17.529611587524414, "learning_rate": 1.3480814757353129e-05, "loss": 24.8357, "step": 1710 }, { "epoch": 0.40141498194615005, "grad_norm": 17.84787368774414, "learning_rate": 1.347373752682577e-05, "loss": 23.0166, "step": 1711 }, { "epoch": 0.4016495903517293, "grad_norm": 20.625614166259766, "learning_rate": 1.3466658317085237e-05, "loss": 26.7232, "step": 1712 }, { "epoch": 0.4018841987573086, "grad_norm": 17.015348434448242, "learning_rate": 1.3459577132165013e-05, "loss": 27.3365, "step": 1713 }, { "epoch": 0.4021188071628879, "grad_norm": 16.917217254638672, "learning_rate": 1.3452493976099706e-05, "loss": 26.4314, "step": 1714 }, { "epoch": 0.40235341556846715, "grad_norm": 15.928183555603027, "learning_rate": 1.3445408852925051e-05, "loss": 21.6771, "step": 1715 }, { "epoch": 0.40258802397404647, "grad_norm": 20.711132049560547, "learning_rate": 1.34383217666779e-05, "loss": 28.0483, "step": 1716 }, { "epoch": 0.40282263237962573, "grad_norm": 17.34662628173828, "learning_rate": 1.3431232721396223e-05, "loss": 22.333, "step": 1717 }, { "epoch": 0.403057240785205, "grad_norm": 18.205799102783203, "learning_rate": 1.3424141721119109e-05, "loss": 22.6358, "step": 1718 }, { "epoch": 0.4032918491907843, "grad_norm": 17.52741050720215, "learning_rate": 1.3417048769886765e-05, "loss": 27.911, "step": 1719 }, { "epoch": 0.4035264575963636, "grad_norm": 18.473087310791016, "learning_rate": 1.3409953871740497e-05, "loss": 24.2813, "step": 1720 }, { "epoch": 0.40376106600194284, "grad_norm": 21.1733455657959, "learning_rate": 1.3402857030722736e-05, "loss": 31.6663, "step": 1721 }, { "epoch": 0.40399567440752215, "grad_norm": 18.877042770385742, "learning_rate": 1.3395758250877001e-05, "loss": 27.0868, "step": 1722 }, { "epoch": 0.4042302828131014, "grad_norm": 16.752685546875, "learning_rate": 1.3388657536247938e-05, "loss": 25.1043, "step": 1723 }, { "epoch": 0.4044648912186807, "grad_norm": 17.347187042236328, "learning_rate": 1.3381554890881275e-05, "loss": 21.8077, "step": 1724 }, { "epoch": 0.40469949962426, "grad_norm": 19.156017303466797, "learning_rate": 1.3374450318823852e-05, "loss": 25.0451, "step": 1725 }, { "epoch": 0.40493410802983926, "grad_norm": 18.315040588378906, "learning_rate": 1.3367343824123609e-05, "loss": 25.1446, "step": 1726 }, { "epoch": 0.4051687164354185, "grad_norm": 18.040870666503906, "learning_rate": 1.3360235410829569e-05, "loss": 27.8355, "step": 1727 }, { "epoch": 0.40540332484099784, "grad_norm": 17.143627166748047, "learning_rate": 1.3353125082991855e-05, "loss": 24.8442, "step": 1728 }, { "epoch": 0.4056379332465771, "grad_norm": 16.63690948486328, "learning_rate": 1.3346012844661687e-05, "loss": 26.2427, "step": 1729 }, { "epoch": 0.40587254165215636, "grad_norm": 17.843963623046875, "learning_rate": 1.333889869989136e-05, "loss": 21.3012, "step": 1730 }, { "epoch": 0.4061071500577357, "grad_norm": 20.39565086364746, "learning_rate": 1.3331782652734273e-05, "loss": 28.2956, "step": 1731 }, { "epoch": 0.40634175846331494, "grad_norm": 19.73212432861328, "learning_rate": 1.3324664707244892e-05, "loss": 26.8875, "step": 1732 }, { "epoch": 0.4065763668688942, "grad_norm": 18.90621566772461, "learning_rate": 1.3317544867478769e-05, "loss": 26.8829, "step": 1733 }, { "epoch": 0.4068109752744735, "grad_norm": 18.553659439086914, "learning_rate": 1.3310423137492545e-05, "loss": 24.0189, "step": 1734 }, { "epoch": 0.4070455836800528, "grad_norm": 18.88117027282715, "learning_rate": 1.3303299521343925e-05, "loss": 28.6131, "step": 1735 }, { "epoch": 0.40728019208563204, "grad_norm": 22.465707778930664, "learning_rate": 1.3296174023091694e-05, "loss": 27.5338, "step": 1736 }, { "epoch": 0.40751480049121136, "grad_norm": 18.12314224243164, "learning_rate": 1.3289046646795716e-05, "loss": 25.892, "step": 1737 }, { "epoch": 0.4077494088967906, "grad_norm": 15.970794677734375, "learning_rate": 1.3281917396516913e-05, "loss": 24.9648, "step": 1738 }, { "epoch": 0.40798401730236994, "grad_norm": 14.199641227722168, "learning_rate": 1.327478627631728e-05, "loss": 23.0642, "step": 1739 }, { "epoch": 0.4082186257079492, "grad_norm": 18.637535095214844, "learning_rate": 1.3267653290259878e-05, "loss": 29.7303, "step": 1740 }, { "epoch": 0.40845323411352846, "grad_norm": 20.10332489013672, "learning_rate": 1.3260518442408836e-05, "loss": 25.714, "step": 1741 }, { "epoch": 0.4086878425191078, "grad_norm": 16.245044708251953, "learning_rate": 1.3253381736829338e-05, "loss": 21.2089, "step": 1742 }, { "epoch": 0.40892245092468704, "grad_norm": 17.76464080810547, "learning_rate": 1.3246243177587626e-05, "loss": 21.896, "step": 1743 }, { "epoch": 0.4091570593302663, "grad_norm": 18.406675338745117, "learning_rate": 1.3239102768750991e-05, "loss": 27.2485, "step": 1744 }, { "epoch": 0.4093916677358456, "grad_norm": 19.65997886657715, "learning_rate": 1.3231960514387798e-05, "loss": 30.0221, "step": 1745 }, { "epoch": 0.4096262761414249, "grad_norm": 20.705984115600586, "learning_rate": 1.3224816418567448e-05, "loss": 25.8728, "step": 1746 }, { "epoch": 0.40986088454700415, "grad_norm": 17.671485900878906, "learning_rate": 1.3217670485360392e-05, "loss": 23.8054, "step": 1747 }, { "epoch": 0.41009549295258346, "grad_norm": 19.484333038330078, "learning_rate": 1.3210522718838134e-05, "loss": 28.8211, "step": 1748 }, { "epoch": 0.4103301013581627, "grad_norm": 18.455291748046875, "learning_rate": 1.3203373123073217e-05, "loss": 24.1489, "step": 1749 }, { "epoch": 0.410564709763742, "grad_norm": 23.9998722076416, "learning_rate": 1.3196221702139234e-05, "loss": 28.5044, "step": 1750 }, { "epoch": 0.4107993181693213, "grad_norm": 17.03217315673828, "learning_rate": 1.3189068460110805e-05, "loss": 25.1881, "step": 1751 }, { "epoch": 0.41103392657490057, "grad_norm": 18.389328002929688, "learning_rate": 1.3181913401063598e-05, "loss": 22.8258, "step": 1752 }, { "epoch": 0.4112685349804798, "grad_norm": 22.583547592163086, "learning_rate": 1.3174756529074315e-05, "loss": 23.584, "step": 1753 }, { "epoch": 0.41150314338605914, "grad_norm": 18.951448440551758, "learning_rate": 1.316759784822069e-05, "loss": 24.3735, "step": 1754 }, { "epoch": 0.4117377517916384, "grad_norm": 18.697078704833984, "learning_rate": 1.3160437362581484e-05, "loss": 29.3072, "step": 1755 }, { "epoch": 0.41197236019721767, "grad_norm": 20.14912986755371, "learning_rate": 1.3153275076236489e-05, "loss": 26.5218, "step": 1756 }, { "epoch": 0.412206968602797, "grad_norm": 17.55875587463379, "learning_rate": 1.3146110993266528e-05, "loss": 26.2726, "step": 1757 }, { "epoch": 0.41244157700837625, "grad_norm": 21.618595123291016, "learning_rate": 1.3138945117753436e-05, "loss": 22.8236, "step": 1758 }, { "epoch": 0.4126761854139555, "grad_norm": 17.490144729614258, "learning_rate": 1.3131777453780084e-05, "loss": 24.9867, "step": 1759 }, { "epoch": 0.4129107938195348, "grad_norm": 20.0914249420166, "learning_rate": 1.3124608005430347e-05, "loss": 29.3586, "step": 1760 }, { "epoch": 0.4131454022251141, "grad_norm": 19.243867874145508, "learning_rate": 1.311743677678913e-05, "loss": 25.6186, "step": 1761 }, { "epoch": 0.41338001063069335, "grad_norm": 22.693546295166016, "learning_rate": 1.3110263771942339e-05, "loss": 27.2699, "step": 1762 }, { "epoch": 0.41361461903627267, "grad_norm": 18.17862319946289, "learning_rate": 1.3103088994976906e-05, "loss": 27.6011, "step": 1763 }, { "epoch": 0.41384922744185193, "grad_norm": 18.303661346435547, "learning_rate": 1.3095912449980765e-05, "loss": 29.4253, "step": 1764 }, { "epoch": 0.41408383584743125, "grad_norm": 21.696449279785156, "learning_rate": 1.3088734141042858e-05, "loss": 29.6902, "step": 1765 }, { "epoch": 0.4143184442530105, "grad_norm": 16.793624877929688, "learning_rate": 1.3081554072253126e-05, "loss": 25.0247, "step": 1766 }, { "epoch": 0.41455305265858977, "grad_norm": 22.30878448486328, "learning_rate": 1.3074372247702527e-05, "loss": 25.0523, "step": 1767 }, { "epoch": 0.4147876610641691, "grad_norm": 17.67921257019043, "learning_rate": 1.3067188671483009e-05, "loss": 27.4177, "step": 1768 }, { "epoch": 0.41502226946974835, "grad_norm": 21.319303512573242, "learning_rate": 1.3060003347687521e-05, "loss": 26.9568, "step": 1769 }, { "epoch": 0.4152568778753276, "grad_norm": 17.15573501586914, "learning_rate": 1.3052816280410008e-05, "loss": 22.4995, "step": 1770 }, { "epoch": 0.41549148628090693, "grad_norm": 19.473520278930664, "learning_rate": 1.3045627473745404e-05, "loss": 28.3555, "step": 1771 }, { "epoch": 0.4157260946864862, "grad_norm": 16.464387893676758, "learning_rate": 1.3038436931789638e-05, "loss": 22.9646, "step": 1772 }, { "epoch": 0.41596070309206545, "grad_norm": 18.507719039916992, "learning_rate": 1.303124465863963e-05, "loss": 25.4457, "step": 1773 }, { "epoch": 0.41619531149764477, "grad_norm": 23.235395431518555, "learning_rate": 1.3024050658393282e-05, "loss": 26.8739, "step": 1774 }, { "epoch": 0.41642991990322403, "grad_norm": 21.186603546142578, "learning_rate": 1.3016854935149485e-05, "loss": 29.9847, "step": 1775 }, { "epoch": 0.4166645283088033, "grad_norm": 18.932693481445312, "learning_rate": 1.3009657493008106e-05, "loss": 30.7297, "step": 1776 }, { "epoch": 0.4168991367143826, "grad_norm": 17.299917221069336, "learning_rate": 1.300245833606999e-05, "loss": 23.7286, "step": 1777 }, { "epoch": 0.4171337451199619, "grad_norm": 18.863277435302734, "learning_rate": 1.2995257468436967e-05, "loss": 31.8089, "step": 1778 }, { "epoch": 0.41736835352554114, "grad_norm": 19.804237365722656, "learning_rate": 1.2988054894211835e-05, "loss": 25.0566, "step": 1779 }, { "epoch": 0.41760296193112045, "grad_norm": 19.039274215698242, "learning_rate": 1.2980850617498373e-05, "loss": 24.06, "step": 1780 }, { "epoch": 0.4178375703366997, "grad_norm": 18.242084503173828, "learning_rate": 1.297364464240132e-05, "loss": 23.8877, "step": 1781 }, { "epoch": 0.418072178742279, "grad_norm": 23.00545310974121, "learning_rate": 1.2966436973026381e-05, "loss": 25.5417, "step": 1782 }, { "epoch": 0.4183067871478583, "grad_norm": 19.679546356201172, "learning_rate": 1.295922761348024e-05, "loss": 23.2141, "step": 1783 }, { "epoch": 0.41854139555343756, "grad_norm": 18.397817611694336, "learning_rate": 1.2952016567870533e-05, "loss": 25.0951, "step": 1784 }, { "epoch": 0.4187760039590168, "grad_norm": 15.14616870880127, "learning_rate": 1.2944803840305859e-05, "loss": 24.5224, "step": 1785 }, { "epoch": 0.41901061236459614, "grad_norm": 17.052522659301758, "learning_rate": 1.2937589434895778e-05, "loss": 25.4034, "step": 1786 }, { "epoch": 0.4192452207701754, "grad_norm": 17.07750129699707, "learning_rate": 1.29303733557508e-05, "loss": 24.0184, "step": 1787 }, { "epoch": 0.4194798291757547, "grad_norm": 19.03498077392578, "learning_rate": 1.2923155606982396e-05, "loss": 27.5687, "step": 1788 }, { "epoch": 0.419714437581334, "grad_norm": 20.53647804260254, "learning_rate": 1.2915936192702982e-05, "loss": 30.9371, "step": 1789 }, { "epoch": 0.41994904598691324, "grad_norm": 17.418087005615234, "learning_rate": 1.290871511702593e-05, "loss": 23.615, "step": 1790 }, { "epoch": 0.42018365439249256, "grad_norm": 17.713279724121094, "learning_rate": 1.290149238406555e-05, "loss": 20.6656, "step": 1791 }, { "epoch": 0.4204182627980718, "grad_norm": 20.90345001220703, "learning_rate": 1.2894267997937102e-05, "loss": 31.5299, "step": 1792 }, { "epoch": 0.4206528712036511, "grad_norm": 20.74705696105957, "learning_rate": 1.2887041962756785e-05, "loss": 25.4483, "step": 1793 }, { "epoch": 0.4208874796092304, "grad_norm": 22.901325225830078, "learning_rate": 1.2879814282641743e-05, "loss": 25.0312, "step": 1794 }, { "epoch": 0.42112208801480966, "grad_norm": 21.01950454711914, "learning_rate": 1.2872584961710054e-05, "loss": 30.3611, "step": 1795 }, { "epoch": 0.4213566964203889, "grad_norm": 18.81046485900879, "learning_rate": 1.2865354004080722e-05, "loss": 28.4894, "step": 1796 }, { "epoch": 0.42159130482596824, "grad_norm": 18.94498634338379, "learning_rate": 1.2858121413873699e-05, "loss": 24.7385, "step": 1797 }, { "epoch": 0.4218259132315475, "grad_norm": 20.777555465698242, "learning_rate": 1.2850887195209856e-05, "loss": 27.9894, "step": 1798 }, { "epoch": 0.42206052163712676, "grad_norm": 17.64483642578125, "learning_rate": 1.2843651352211002e-05, "loss": 26.33, "step": 1799 }, { "epoch": 0.4222951300427061, "grad_norm": 17.805465698242188, "learning_rate": 1.2836413888999857e-05, "loss": 27.9669, "step": 1800 }, { "epoch": 0.42252973844828534, "grad_norm": 18.05103874206543, "learning_rate": 1.2829174809700078e-05, "loss": 24.2178, "step": 1801 }, { "epoch": 0.4227643468538646, "grad_norm": 21.213306427001953, "learning_rate": 1.2821934118436238e-05, "loss": 30.5138, "step": 1802 }, { "epoch": 0.4229989552594439, "grad_norm": 19.388235092163086, "learning_rate": 1.2814691819333823e-05, "loss": 25.6344, "step": 1803 }, { "epoch": 0.4232335636650232, "grad_norm": 17.299720764160156, "learning_rate": 1.2807447916519238e-05, "loss": 25.9309, "step": 1804 }, { "epoch": 0.42346817207060244, "grad_norm": 17.97735595703125, "learning_rate": 1.280020241411981e-05, "loss": 25.1624, "step": 1805 }, { "epoch": 0.42370278047618176, "grad_norm": 17.334238052368164, "learning_rate": 1.2792955316263767e-05, "loss": 27.807, "step": 1806 }, { "epoch": 0.423937388881761, "grad_norm": 18.816444396972656, "learning_rate": 1.2785706627080255e-05, "loss": 21.6191, "step": 1807 }, { "epoch": 0.4241719972873403, "grad_norm": 17.90091896057129, "learning_rate": 1.2778456350699315e-05, "loss": 26.84, "step": 1808 }, { "epoch": 0.4244066056929196, "grad_norm": 17.902549743652344, "learning_rate": 1.2771204491251901e-05, "loss": 25.6559, "step": 1809 }, { "epoch": 0.42464121409849886, "grad_norm": 19.629880905151367, "learning_rate": 1.2763951052869868e-05, "loss": 25.7127, "step": 1810 }, { "epoch": 0.4248758225040781, "grad_norm": 17.6679744720459, "learning_rate": 1.2756696039685967e-05, "loss": 24.5349, "step": 1811 }, { "epoch": 0.42511043090965744, "grad_norm": 17.339862823486328, "learning_rate": 1.274943945583385e-05, "loss": 23.0179, "step": 1812 }, { "epoch": 0.4253450393152367, "grad_norm": 19.58816146850586, "learning_rate": 1.2742181305448068e-05, "loss": 27.5776, "step": 1813 }, { "epoch": 0.425579647720816, "grad_norm": 19.723331451416016, "learning_rate": 1.2734921592664052e-05, "loss": 26.4162, "step": 1814 }, { "epoch": 0.4258142561263953, "grad_norm": 21.703310012817383, "learning_rate": 1.272766032161813e-05, "loss": 29.1906, "step": 1815 }, { "epoch": 0.42604886453197455, "grad_norm": 21.01654052734375, "learning_rate": 1.2720397496447521e-05, "loss": 30.3172, "step": 1816 }, { "epoch": 0.42628347293755386, "grad_norm": 18.258792877197266, "learning_rate": 1.2713133121290326e-05, "loss": 24.8036, "step": 1817 }, { "epoch": 0.4265180813431331, "grad_norm": 19.27610206604004, "learning_rate": 1.2705867200285532e-05, "loss": 28.9059, "step": 1818 }, { "epoch": 0.4267526897487124, "grad_norm": 19.635671615600586, "learning_rate": 1.2698599737573005e-05, "loss": 23.7937, "step": 1819 }, { "epoch": 0.4269872981542917, "grad_norm": 17.17624282836914, "learning_rate": 1.2691330737293485e-05, "loss": 23.7595, "step": 1820 }, { "epoch": 0.42722190655987097, "grad_norm": 18.853769302368164, "learning_rate": 1.2684060203588592e-05, "loss": 25.3456, "step": 1821 }, { "epoch": 0.42745651496545023, "grad_norm": 19.091995239257812, "learning_rate": 1.267678814060083e-05, "loss": 27.0444, "step": 1822 }, { "epoch": 0.42769112337102955, "grad_norm": 18.39849281311035, "learning_rate": 1.2669514552473548e-05, "loss": 23.3873, "step": 1823 }, { "epoch": 0.4279257317766088, "grad_norm": 19.431528091430664, "learning_rate": 1.2662239443350992e-05, "loss": 25.5199, "step": 1824 }, { "epoch": 0.42816034018218807, "grad_norm": 16.630409240722656, "learning_rate": 1.2654962817378259e-05, "loss": 23.1105, "step": 1825 }, { "epoch": 0.4283949485877674, "grad_norm": 19.07943344116211, "learning_rate": 1.2647684678701313e-05, "loss": 22.7886, "step": 1826 }, { "epoch": 0.42862955699334665, "grad_norm": 19.923826217651367, "learning_rate": 1.264040503146698e-05, "loss": 25.78, "step": 1827 }, { "epoch": 0.4288641653989259, "grad_norm": 18.325042724609375, "learning_rate": 1.2633123879822949e-05, "loss": 21.883, "step": 1828 }, { "epoch": 0.42909877380450523, "grad_norm": 17.50474739074707, "learning_rate": 1.2625841227917761e-05, "loss": 24.6213, "step": 1829 }, { "epoch": 0.4293333822100845, "grad_norm": 23.18111801147461, "learning_rate": 1.2618557079900822e-05, "loss": 32.4489, "step": 1830 }, { "epoch": 0.42956799061566375, "grad_norm": 17.16797637939453, "learning_rate": 1.261127143992237e-05, "loss": 24.5146, "step": 1831 }, { "epoch": 0.42980259902124307, "grad_norm": 18.506027221679688, "learning_rate": 1.2603984312133514e-05, "loss": 24.0377, "step": 1832 }, { "epoch": 0.43003720742682233, "grad_norm": 18.61872673034668, "learning_rate": 1.2596695700686204e-05, "loss": 21.8618, "step": 1833 }, { "epoch": 0.4302718158324016, "grad_norm": 19.478208541870117, "learning_rate": 1.2589405609733227e-05, "loss": 25.1377, "step": 1834 }, { "epoch": 0.4305064242379809, "grad_norm": 17.853769302368164, "learning_rate": 1.2582114043428224e-05, "loss": 23.6681, "step": 1835 }, { "epoch": 0.4307410326435602, "grad_norm": 18.91139030456543, "learning_rate": 1.2574821005925672e-05, "loss": 27.469, "step": 1836 }, { "epoch": 0.4309756410491395, "grad_norm": 16.67847442626953, "learning_rate": 1.256752650138089e-05, "loss": 23.4301, "step": 1837 }, { "epoch": 0.43121024945471875, "grad_norm": 15.9686861038208, "learning_rate": 1.2560230533950021e-05, "loss": 26.0525, "step": 1838 }, { "epoch": 0.431444857860298, "grad_norm": 20.581159591674805, "learning_rate": 1.2552933107790057e-05, "loss": 25.4383, "step": 1839 }, { "epoch": 0.43167946626587733, "grad_norm": 18.36351776123047, "learning_rate": 1.2545634227058813e-05, "loss": 25.9166, "step": 1840 }, { "epoch": 0.4319140746714566, "grad_norm": 17.826866149902344, "learning_rate": 1.2538333895914936e-05, "loss": 23.7657, "step": 1841 }, { "epoch": 0.43214868307703586, "grad_norm": 15.021952629089355, "learning_rate": 1.2531032118517892e-05, "loss": 22.3608, "step": 1842 }, { "epoch": 0.4323832914826152, "grad_norm": 21.93470573425293, "learning_rate": 1.2523728899027977e-05, "loss": 26.8587, "step": 1843 }, { "epoch": 0.43261789988819443, "grad_norm": 17.329692840576172, "learning_rate": 1.251642424160631e-05, "loss": 25.0868, "step": 1844 }, { "epoch": 0.4328525082937737, "grad_norm": 18.79006576538086, "learning_rate": 1.250911815041483e-05, "loss": 27.9862, "step": 1845 }, { "epoch": 0.433087116699353, "grad_norm": 22.31151580810547, "learning_rate": 1.2501810629616285e-05, "loss": 28.4602, "step": 1846 }, { "epoch": 0.4333217251049323, "grad_norm": 19.27683448791504, "learning_rate": 1.2494501683374245e-05, "loss": 27.3227, "step": 1847 }, { "epoch": 0.43355633351051154, "grad_norm": 16.00411033630371, "learning_rate": 1.248719131585309e-05, "loss": 23.8081, "step": 1848 }, { "epoch": 0.43379094191609086, "grad_norm": 20.556659698486328, "learning_rate": 1.2479879531218014e-05, "loss": 24.8675, "step": 1849 }, { "epoch": 0.4340255503216701, "grad_norm": 15.370911598205566, "learning_rate": 1.2472566333635004e-05, "loss": 23.3327, "step": 1850 }, { "epoch": 0.4342601587272494, "grad_norm": 18.91340446472168, "learning_rate": 1.2465251727270869e-05, "loss": 26.1285, "step": 1851 }, { "epoch": 0.4344947671328287, "grad_norm": 17.636377334594727, "learning_rate": 1.2457935716293214e-05, "loss": 22.9292, "step": 1852 }, { "epoch": 0.43472937553840796, "grad_norm": 28.581552505493164, "learning_rate": 1.2450618304870443e-05, "loss": 31.5252, "step": 1853 }, { "epoch": 0.4349639839439872, "grad_norm": 17.36067771911621, "learning_rate": 1.2443299497171757e-05, "loss": 23.6128, "step": 1854 }, { "epoch": 0.43519859234956654, "grad_norm": 20.56843376159668, "learning_rate": 1.2435979297367156e-05, "loss": 21.0434, "step": 1855 }, { "epoch": 0.4354332007551458, "grad_norm": 23.501026153564453, "learning_rate": 1.2428657709627436e-05, "loss": 28.2683, "step": 1856 }, { "epoch": 0.43566780916072506, "grad_norm": 18.360769271850586, "learning_rate": 1.242133473812417e-05, "loss": 24.4329, "step": 1857 }, { "epoch": 0.4359024175663044, "grad_norm": 23.8931827545166, "learning_rate": 1.241401038702974e-05, "loss": 26.4801, "step": 1858 }, { "epoch": 0.43613702597188364, "grad_norm": 19.802011489868164, "learning_rate": 1.2406684660517296e-05, "loss": 22.8557, "step": 1859 }, { "epoch": 0.4363716343774629, "grad_norm": 21.076580047607422, "learning_rate": 1.2399357562760783e-05, "loss": 24.6075, "step": 1860 }, { "epoch": 0.4366062427830422, "grad_norm": 17.52680206298828, "learning_rate": 1.2392029097934917e-05, "loss": 26.9279, "step": 1861 }, { "epoch": 0.4368408511886215, "grad_norm": 19.38756561279297, "learning_rate": 1.2384699270215202e-05, "loss": 23.9578, "step": 1862 }, { "epoch": 0.4370754595942008, "grad_norm": 20.48436164855957, "learning_rate": 1.2377368083777918e-05, "loss": 26.594, "step": 1863 }, { "epoch": 0.43731006799978006, "grad_norm": 18.888957977294922, "learning_rate": 1.2370035542800116e-05, "loss": 25.673, "step": 1864 }, { "epoch": 0.4375446764053593, "grad_norm": 21.988176345825195, "learning_rate": 1.2362701651459615e-05, "loss": 25.1134, "step": 1865 }, { "epoch": 0.43777928481093864, "grad_norm": 16.77631187438965, "learning_rate": 1.2355366413935009e-05, "loss": 26.3679, "step": 1866 }, { "epoch": 0.4380138932165179, "grad_norm": 19.389373779296875, "learning_rate": 1.2348029834405662e-05, "loss": 25.4853, "step": 1867 }, { "epoch": 0.43824850162209716, "grad_norm": 18.508445739746094, "learning_rate": 1.2340691917051695e-05, "loss": 20.7696, "step": 1868 }, { "epoch": 0.4384831100276765, "grad_norm": 18.79261016845703, "learning_rate": 1.2333352666053995e-05, "loss": 25.7315, "step": 1869 }, { "epoch": 0.43871771843325574, "grad_norm": 17.091794967651367, "learning_rate": 1.2326012085594207e-05, "loss": 27.6286, "step": 1870 }, { "epoch": 0.438952326838835, "grad_norm": 16.855690002441406, "learning_rate": 1.2318670179854742e-05, "loss": 20.6894, "step": 1871 }, { "epoch": 0.4391869352444143, "grad_norm": 21.38587760925293, "learning_rate": 1.2311326953018747e-05, "loss": 23.4927, "step": 1872 }, { "epoch": 0.4394215436499936, "grad_norm": 17.91872215270996, "learning_rate": 1.2303982409270144e-05, "loss": 29.5205, "step": 1873 }, { "epoch": 0.43965615205557285, "grad_norm": 20.11161231994629, "learning_rate": 1.229663655279359e-05, "loss": 27.8581, "step": 1874 }, { "epoch": 0.43989076046115216, "grad_norm": 16.223007202148438, "learning_rate": 1.22892893877745e-05, "loss": 23.9033, "step": 1875 }, { "epoch": 0.4401253688667314, "grad_norm": 20.12213897705078, "learning_rate": 1.2281940918399022e-05, "loss": 27.5098, "step": 1876 }, { "epoch": 0.4403599772723107, "grad_norm": 21.297693252563477, "learning_rate": 1.2274591148854058e-05, "loss": 30.0378, "step": 1877 }, { "epoch": 0.44059458567789, "grad_norm": 19.224590301513672, "learning_rate": 1.226724008332725e-05, "loss": 25.1369, "step": 1878 }, { "epoch": 0.44082919408346927, "grad_norm": 18.79509735107422, "learning_rate": 1.2259887726006976e-05, "loss": 25.7605, "step": 1879 }, { "epoch": 0.44106380248904853, "grad_norm": 20.628124237060547, "learning_rate": 1.225253408108235e-05, "loss": 22.7905, "step": 1880 }, { "epoch": 0.44129841089462785, "grad_norm": 19.06997299194336, "learning_rate": 1.2245179152743214e-05, "loss": 28.4228, "step": 1881 }, { "epoch": 0.4415330193002071, "grad_norm": 19.588712692260742, "learning_rate": 1.2237822945180151e-05, "loss": 22.6054, "step": 1882 }, { "epoch": 0.44176762770578637, "grad_norm": 23.141204833984375, "learning_rate": 1.2230465462584473e-05, "loss": 24.4291, "step": 1883 }, { "epoch": 0.4420022361113657, "grad_norm": 18.885282516479492, "learning_rate": 1.2223106709148204e-05, "loss": 24.9074, "step": 1884 }, { "epoch": 0.44223684451694495, "grad_norm": 20.15543556213379, "learning_rate": 1.2215746689064115e-05, "loss": 28.3791, "step": 1885 }, { "epoch": 0.44247145292252427, "grad_norm": 16.328140258789062, "learning_rate": 1.2208385406525674e-05, "loss": 20.4786, "step": 1886 }, { "epoch": 0.44270606132810353, "grad_norm": 16.058095932006836, "learning_rate": 1.2201022865727087e-05, "loss": 23.182, "step": 1887 }, { "epoch": 0.4429406697336828, "grad_norm": 18.633005142211914, "learning_rate": 1.2193659070863269e-05, "loss": 17.9884, "step": 1888 }, { "epoch": 0.4431752781392621, "grad_norm": 16.66940689086914, "learning_rate": 1.2186294026129847e-05, "loss": 23.8337, "step": 1889 }, { "epoch": 0.44340988654484137, "grad_norm": 17.76595687866211, "learning_rate": 1.2178927735723172e-05, "loss": 26.4947, "step": 1890 }, { "epoch": 0.44364449495042063, "grad_norm": 17.25618553161621, "learning_rate": 1.217156020384029e-05, "loss": 24.8425, "step": 1891 }, { "epoch": 0.44387910335599995, "grad_norm": 19.018091201782227, "learning_rate": 1.2164191434678962e-05, "loss": 24.7621, "step": 1892 }, { "epoch": 0.4441137117615792, "grad_norm": 19.138084411621094, "learning_rate": 1.2156821432437651e-05, "loss": 26.2861, "step": 1893 }, { "epoch": 0.4443483201671585, "grad_norm": 21.27809715270996, "learning_rate": 1.2149450201315531e-05, "loss": 24.9332, "step": 1894 }, { "epoch": 0.4445829285727378, "grad_norm": 19.9844970703125, "learning_rate": 1.2142077745512464e-05, "loss": 26.8563, "step": 1895 }, { "epoch": 0.44481753697831705, "grad_norm": 21.508441925048828, "learning_rate": 1.2134704069229018e-05, "loss": 26.3191, "step": 1896 }, { "epoch": 0.4450521453838963, "grad_norm": 17.212339401245117, "learning_rate": 1.2127329176666449e-05, "loss": 22.0332, "step": 1897 }, { "epoch": 0.44528675378947563, "grad_norm": 16.85433006286621, "learning_rate": 1.211995307202672e-05, "loss": 22.6804, "step": 1898 }, { "epoch": 0.4455213621950549, "grad_norm": 16.82377815246582, "learning_rate": 1.2112575759512467e-05, "loss": 23.9389, "step": 1899 }, { "epoch": 0.44575597060063415, "grad_norm": 18.66912078857422, "learning_rate": 1.2105197243327023e-05, "loss": 22.9455, "step": 1900 }, { "epoch": 0.4459905790062135, "grad_norm": 17.098115921020508, "learning_rate": 1.2097817527674412e-05, "loss": 24.8723, "step": 1901 }, { "epoch": 0.44622518741179273, "grad_norm": 16.548629760742188, "learning_rate": 1.2090436616759333e-05, "loss": 22.9255, "step": 1902 }, { "epoch": 0.446459795817372, "grad_norm": 17.953420639038086, "learning_rate": 1.2083054514787168e-05, "loss": 27.7288, "step": 1903 }, { "epoch": 0.4466944042229513, "grad_norm": 16.785892486572266, "learning_rate": 1.2075671225963976e-05, "loss": 26.2094, "step": 1904 }, { "epoch": 0.4469290126285306, "grad_norm": 17.54220962524414, "learning_rate": 1.20682867544965e-05, "loss": 27.6959, "step": 1905 }, { "epoch": 0.44716362103410984, "grad_norm": 27.076534271240234, "learning_rate": 1.206090110459215e-05, "loss": 22.9399, "step": 1906 }, { "epoch": 0.44739822943968915, "grad_norm": 19.795053482055664, "learning_rate": 1.2053514280459006e-05, "loss": 27.7328, "step": 1907 }, { "epoch": 0.4476328378452684, "grad_norm": 19.221464157104492, "learning_rate": 1.2046126286305824e-05, "loss": 25.5769, "step": 1908 }, { "epoch": 0.44786744625084773, "grad_norm": 19.051557540893555, "learning_rate": 1.203873712634202e-05, "loss": 28.2821, "step": 1909 }, { "epoch": 0.448102054656427, "grad_norm": 24.52911949157715, "learning_rate": 1.2031346804777677e-05, "loss": 28.7323, "step": 1910 }, { "epoch": 0.44833666306200626, "grad_norm": 16.25706672668457, "learning_rate": 1.2023955325823538e-05, "loss": 25.5413, "step": 1911 }, { "epoch": 0.4485712714675856, "grad_norm": 18.48362159729004, "learning_rate": 1.2016562693691014e-05, "loss": 24.7135, "step": 1912 }, { "epoch": 0.44880587987316484, "grad_norm": 17.62580108642578, "learning_rate": 1.200916891259216e-05, "loss": 23.7872, "step": 1913 }, { "epoch": 0.4490404882787441, "grad_norm": 19.471786499023438, "learning_rate": 1.200177398673969e-05, "loss": 21.6442, "step": 1914 }, { "epoch": 0.4492750966843234, "grad_norm": 16.398820877075195, "learning_rate": 1.1994377920346976e-05, "loss": 26.5772, "step": 1915 }, { "epoch": 0.4495097050899027, "grad_norm": 19.77499008178711, "learning_rate": 1.1986980717628037e-05, "loss": 23.9664, "step": 1916 }, { "epoch": 0.44974431349548194, "grad_norm": 20.738067626953125, "learning_rate": 1.1979582382797537e-05, "loss": 25.5511, "step": 1917 }, { "epoch": 0.44997892190106126, "grad_norm": 18.273868560791016, "learning_rate": 1.1972182920070785e-05, "loss": 25.8791, "step": 1918 }, { "epoch": 0.4502135303066405, "grad_norm": 17.796810150146484, "learning_rate": 1.1964782333663734e-05, "loss": 26.7156, "step": 1919 }, { "epoch": 0.4504481387122198, "grad_norm": 26.70568084716797, "learning_rate": 1.1957380627792976e-05, "loss": 24.415, "step": 1920 }, { "epoch": 0.4506827471177991, "grad_norm": 19.054975509643555, "learning_rate": 1.1949977806675747e-05, "loss": 26.5219, "step": 1921 }, { "epoch": 0.45091735552337836, "grad_norm": 22.12641143798828, "learning_rate": 1.194257387452991e-05, "loss": 27.8432, "step": 1922 }, { "epoch": 0.4511519639289576, "grad_norm": 15.914046287536621, "learning_rate": 1.1935168835573967e-05, "loss": 26.9221, "step": 1923 }, { "epoch": 0.45138657233453694, "grad_norm": 19.551372528076172, "learning_rate": 1.1927762694027042e-05, "loss": 26.8272, "step": 1924 }, { "epoch": 0.4516211807401162, "grad_norm": 21.46865463256836, "learning_rate": 1.1920355454108902e-05, "loss": 28.1602, "step": 1925 }, { "epoch": 0.45185578914569546, "grad_norm": 18.893993377685547, "learning_rate": 1.1912947120039925e-05, "loss": 27.812, "step": 1926 }, { "epoch": 0.4520903975512748, "grad_norm": 16.350465774536133, "learning_rate": 1.1905537696041118e-05, "loss": 27.5865, "step": 1927 }, { "epoch": 0.45232500595685404, "grad_norm": 17.68035888671875, "learning_rate": 1.1898127186334114e-05, "loss": 27.4256, "step": 1928 }, { "epoch": 0.4525596143624333, "grad_norm": 16.512954711914062, "learning_rate": 1.189071559514116e-05, "loss": 27.3951, "step": 1929 }, { "epoch": 0.4527942227680126, "grad_norm": 16.6551570892334, "learning_rate": 1.1883302926685114e-05, "loss": 22.8846, "step": 1930 }, { "epoch": 0.4530288311735919, "grad_norm": 15.486771583557129, "learning_rate": 1.1875889185189457e-05, "loss": 21.2415, "step": 1931 }, { "epoch": 0.45326343957917115, "grad_norm": 17.983936309814453, "learning_rate": 1.1868474374878279e-05, "loss": 22.6094, "step": 1932 }, { "epoch": 0.45349804798475046, "grad_norm": 17.50263214111328, "learning_rate": 1.1861058499976275e-05, "loss": 25.5077, "step": 1933 }, { "epoch": 0.4537326563903297, "grad_norm": 17.39725685119629, "learning_rate": 1.185364156470875e-05, "loss": 26.9218, "step": 1934 }, { "epoch": 0.45396726479590904, "grad_norm": 19.167438507080078, "learning_rate": 1.1846223573301609e-05, "loss": 26.3241, "step": 1935 }, { "epoch": 0.4542018732014883, "grad_norm": 17.490863800048828, "learning_rate": 1.1838804529981366e-05, "loss": 23.6485, "step": 1936 }, { "epoch": 0.45443648160706757, "grad_norm": 18.38372230529785, "learning_rate": 1.1831384438975131e-05, "loss": 25.7768, "step": 1937 }, { "epoch": 0.4546710900126469, "grad_norm": 18.830913543701172, "learning_rate": 1.1823963304510606e-05, "loss": 25.002, "step": 1938 }, { "epoch": 0.45490569841822615, "grad_norm": 19.42527961730957, "learning_rate": 1.1816541130816097e-05, "loss": 28.9773, "step": 1939 }, { "epoch": 0.4551403068238054, "grad_norm": 18.661489486694336, "learning_rate": 1.1809117922120494e-05, "loss": 25.0485, "step": 1940 }, { "epoch": 0.4553749152293847, "grad_norm": 16.90471839904785, "learning_rate": 1.1801693682653276e-05, "loss": 25.7804, "step": 1941 }, { "epoch": 0.455609523634964, "grad_norm": 17.25708770751953, "learning_rate": 1.1794268416644518e-05, "loss": 27.7902, "step": 1942 }, { "epoch": 0.45584413204054325, "grad_norm": 17.37118911743164, "learning_rate": 1.1786842128324875e-05, "loss": 24.5556, "step": 1943 }, { "epoch": 0.45607874044612257, "grad_norm": 20.41679573059082, "learning_rate": 1.1779414821925584e-05, "loss": 25.5609, "step": 1944 }, { "epoch": 0.4563133488517018, "grad_norm": 18.566511154174805, "learning_rate": 1.177198650167846e-05, "loss": 27.009, "step": 1945 }, { "epoch": 0.4565479572572811, "grad_norm": 17.762836456298828, "learning_rate": 1.1764557171815898e-05, "loss": 24.3669, "step": 1946 }, { "epoch": 0.4567825656628604, "grad_norm": 19.668954849243164, "learning_rate": 1.175712683657087e-05, "loss": 28.5757, "step": 1947 }, { "epoch": 0.45701717406843967, "grad_norm": 18.244508743286133, "learning_rate": 1.174969550017692e-05, "loss": 25.5096, "step": 1948 }, { "epoch": 0.45725178247401893, "grad_norm": 22.393680572509766, "learning_rate": 1.1742263166868155e-05, "loss": 27.5251, "step": 1949 }, { "epoch": 0.45748639087959825, "grad_norm": 18.609975814819336, "learning_rate": 1.1734829840879266e-05, "loss": 24.9024, "step": 1950 }, { "epoch": 0.4577209992851775, "grad_norm": 22.504043579101562, "learning_rate": 1.1727395526445493e-05, "loss": 30.0105, "step": 1951 }, { "epoch": 0.45795560769075677, "grad_norm": 16.437925338745117, "learning_rate": 1.1719960227802649e-05, "loss": 24.6927, "step": 1952 }, { "epoch": 0.4581902160963361, "grad_norm": 15.908896446228027, "learning_rate": 1.1712523949187104e-05, "loss": 21.6472, "step": 1953 }, { "epoch": 0.45842482450191535, "grad_norm": 17.966421127319336, "learning_rate": 1.1705086694835788e-05, "loss": 24.0768, "step": 1954 }, { "epoch": 0.4586594329074946, "grad_norm": 17.18727684020996, "learning_rate": 1.1697648468986189e-05, "loss": 24.1277, "step": 1955 }, { "epoch": 0.45889404131307393, "grad_norm": 17.593313217163086, "learning_rate": 1.1690209275876344e-05, "loss": 25.7303, "step": 1956 }, { "epoch": 0.4591286497186532, "grad_norm": 17.306873321533203, "learning_rate": 1.1682769119744837e-05, "loss": 25.9825, "step": 1957 }, { "epoch": 0.4593632581242325, "grad_norm": 18.315532684326172, "learning_rate": 1.1675328004830815e-05, "loss": 23.7257, "step": 1958 }, { "epoch": 0.45959786652981177, "grad_norm": 16.819637298583984, "learning_rate": 1.1667885935373962e-05, "loss": 24.1208, "step": 1959 }, { "epoch": 0.45983247493539103, "grad_norm": 17.42848014831543, "learning_rate": 1.16604429156145e-05, "loss": 24.8106, "step": 1960 }, { "epoch": 0.46006708334097035, "grad_norm": 16.77956771850586, "learning_rate": 1.1652998949793207e-05, "loss": 24.6213, "step": 1961 }, { "epoch": 0.4603016917465496, "grad_norm": 15.454556465148926, "learning_rate": 1.1645554042151388e-05, "loss": 20.2952, "step": 1962 }, { "epoch": 0.4605363001521289, "grad_norm": 16.41889190673828, "learning_rate": 1.1638108196930891e-05, "loss": 25.5966, "step": 1963 }, { "epoch": 0.4607709085577082, "grad_norm": 20.382070541381836, "learning_rate": 1.1630661418374095e-05, "loss": 29.4352, "step": 1964 }, { "epoch": 0.46100551696328745, "grad_norm": 16.835535049438477, "learning_rate": 1.1623213710723909e-05, "loss": 24.5025, "step": 1965 }, { "epoch": 0.4612401253688667, "grad_norm": 17.68024444580078, "learning_rate": 1.1615765078223781e-05, "loss": 22.217, "step": 1966 }, { "epoch": 0.46147473377444603, "grad_norm": 17.435810089111328, "learning_rate": 1.1608315525117677e-05, "loss": 23.8789, "step": 1967 }, { "epoch": 0.4617093421800253, "grad_norm": 16.171524047851562, "learning_rate": 1.1600865055650084e-05, "loss": 21.0735, "step": 1968 }, { "epoch": 0.46194395058560456, "grad_norm": 18.7513484954834, "learning_rate": 1.1593413674066021e-05, "loss": 25.4337, "step": 1969 }, { "epoch": 0.4621785589911839, "grad_norm": 18.520238876342773, "learning_rate": 1.1585961384611026e-05, "loss": 26.8135, "step": 1970 }, { "epoch": 0.46241316739676314, "grad_norm": 20.34006690979004, "learning_rate": 1.1578508191531146e-05, "loss": 26.7097, "step": 1971 }, { "epoch": 0.4626477758023424, "grad_norm": 16.422767639160156, "learning_rate": 1.1571054099072949e-05, "loss": 25.2379, "step": 1972 }, { "epoch": 0.4628823842079217, "grad_norm": 18.67681121826172, "learning_rate": 1.1563599111483513e-05, "loss": 27.581, "step": 1973 }, { "epoch": 0.463116992613501, "grad_norm": 17.464872360229492, "learning_rate": 1.1556143233010431e-05, "loss": 25.2975, "step": 1974 }, { "epoch": 0.46335160101908024, "grad_norm": 17.245424270629883, "learning_rate": 1.1548686467901793e-05, "loss": 26.1239, "step": 1975 }, { "epoch": 0.46358620942465956, "grad_norm": 20.496488571166992, "learning_rate": 1.1541228820406208e-05, "loss": 25.0632, "step": 1976 }, { "epoch": 0.4638208178302388, "grad_norm": 17.160099029541016, "learning_rate": 1.1533770294772774e-05, "loss": 23.1953, "step": 1977 }, { "epoch": 0.4640554262358181, "grad_norm": 17.450916290283203, "learning_rate": 1.1526310895251105e-05, "loss": 22.3686, "step": 1978 }, { "epoch": 0.4642900346413974, "grad_norm": 19.203880310058594, "learning_rate": 1.1518850626091293e-05, "loss": 24.3, "step": 1979 }, { "epoch": 0.46452464304697666, "grad_norm": 18.010601043701172, "learning_rate": 1.1511389491543942e-05, "loss": 31.1374, "step": 1980 }, { "epoch": 0.4647592514525559, "grad_norm": 19.02227020263672, "learning_rate": 1.1503927495860145e-05, "loss": 24.1358, "step": 1981 }, { "epoch": 0.46499385985813524, "grad_norm": 17.345020294189453, "learning_rate": 1.1496464643291483e-05, "loss": 23.6766, "step": 1982 }, { "epoch": 0.4652284682637145, "grad_norm": 17.361572265625, "learning_rate": 1.1489000938090025e-05, "loss": 25.574, "step": 1983 }, { "epoch": 0.4654630766692938, "grad_norm": 20.594987869262695, "learning_rate": 1.1481536384508325e-05, "loss": 30.1443, "step": 1984 }, { "epoch": 0.4656976850748731, "grad_norm": 19.400001525878906, "learning_rate": 1.1474070986799427e-05, "loss": 24.3897, "step": 1985 }, { "epoch": 0.46593229348045234, "grad_norm": 18.926471710205078, "learning_rate": 1.146660474921685e-05, "loss": 22.8324, "step": 1986 }, { "epoch": 0.46616690188603166, "grad_norm": 19.235002517700195, "learning_rate": 1.145913767601459e-05, "loss": 25.0903, "step": 1987 }, { "epoch": 0.4664015102916109, "grad_norm": 18.7154483795166, "learning_rate": 1.1451669771447125e-05, "loss": 24.9203, "step": 1988 }, { "epoch": 0.4666361186971902, "grad_norm": 18.439363479614258, "learning_rate": 1.1444201039769405e-05, "loss": 27.7058, "step": 1989 }, { "epoch": 0.4668707271027695, "grad_norm": 17.998703002929688, "learning_rate": 1.1436731485236846e-05, "loss": 21.3109, "step": 1990 }, { "epoch": 0.46710533550834876, "grad_norm": 18.056821823120117, "learning_rate": 1.1429261112105338e-05, "loss": 27.9608, "step": 1991 }, { "epoch": 0.467339943913928, "grad_norm": 32.20573043823242, "learning_rate": 1.1421789924631238e-05, "loss": 21.7469, "step": 1992 }, { "epoch": 0.46757455231950734, "grad_norm": 19.388277053833008, "learning_rate": 1.1414317927071366e-05, "loss": 25.7896, "step": 1993 }, { "epoch": 0.4678091607250866, "grad_norm": 16.07781982421875, "learning_rate": 1.1406845123683001e-05, "loss": 25.0008, "step": 1994 }, { "epoch": 0.46804376913066587, "grad_norm": 17.765789031982422, "learning_rate": 1.1399371518723884e-05, "loss": 25.3859, "step": 1995 }, { "epoch": 0.4682783775362452, "grad_norm": 19.490079879760742, "learning_rate": 1.1391897116452206e-05, "loss": 22.8618, "step": 1996 }, { "epoch": 0.46851298594182444, "grad_norm": 21.745744705200195, "learning_rate": 1.1384421921126627e-05, "loss": 25.9734, "step": 1997 }, { "epoch": 0.4687475943474037, "grad_norm": 16.676387786865234, "learning_rate": 1.1376945937006243e-05, "loss": 22.9114, "step": 1998 }, { "epoch": 0.468982202752983, "grad_norm": 18.64183807373047, "learning_rate": 1.136946916835061e-05, "loss": 25.7125, "step": 1999 }, { "epoch": 0.4692168111585623, "grad_norm": 18.373882293701172, "learning_rate": 1.1361991619419725e-05, "loss": 24.5042, "step": 2000 } ], "logging_steps": 1, "max_steps": 4262, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.012750269906502e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }