{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 500, "global_step": 412, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0048543689320388345, "grad_norm": 6.247678567924481, "learning_rate": 9.999854640567861e-06, "loss": 0.3079, "step": 1 }, { "epoch": 0.009708737864077669, "grad_norm": 4.64975188686189, "learning_rate": 9.999418570723189e-06, "loss": 0.2515, "step": 2 }, { "epoch": 0.014563106796116505, "grad_norm": 7.785908671414252, "learning_rate": 9.998691815820732e-06, "loss": 0.3532, "step": 3 }, { "epoch": 0.019417475728155338, "grad_norm": 5.9611359814479625, "learning_rate": 9.997674418116759e-06, "loss": 0.3818, "step": 4 }, { "epoch": 0.024271844660194174, "grad_norm": 4.157231170406351, "learning_rate": 9.996366436766612e-06, "loss": 0.2384, "step": 5 }, { "epoch": 0.02912621359223301, "grad_norm": 4.757909796367047, "learning_rate": 9.994767947821261e-06, "loss": 0.318, "step": 6 }, { "epoch": 0.03398058252427184, "grad_norm": 4.482147753504881, "learning_rate": 9.992879044222887e-06, "loss": 0.2428, "step": 7 }, { "epoch": 0.038834951456310676, "grad_norm": 3.700661028858978, "learning_rate": 9.99069983579947e-06, "loss": 0.2267, "step": 8 }, { "epoch": 0.043689320388349516, "grad_norm": 4.120140642423019, "learning_rate": 9.988230449258409e-06, "loss": 0.2354, "step": 9 }, { "epoch": 0.04854368932038835, "grad_norm": 3.8181731788087294, "learning_rate": 9.985471028179155e-06, "loss": 0.1599, "step": 10 }, { "epoch": 0.05339805825242718, "grad_norm": 5.079426414640575, "learning_rate": 9.982421733004857e-06, "loss": 0.2488, "step": 11 }, { "epoch": 0.05825242718446602, "grad_norm": 4.728375433201582, "learning_rate": 9.979082741033047e-06, "loss": 0.2433, "step": 12 }, { "epoch": 0.06310679611650485, "grad_norm": 3.485152878413148, "learning_rate": 9.975454246405312e-06, "loss": 0.1986, "step": 13 }, { "epoch": 0.06796116504854369, "grad_norm": 6.421218613593433, "learning_rate": 9.971536460096021e-06, "loss": 0.4593, "step": 14 }, { "epoch": 0.07281553398058252, "grad_norm": 4.6122187535132335, "learning_rate": 9.96732960990005e-06, "loss": 0.2796, "step": 15 }, { "epoch": 0.07766990291262135, "grad_norm": 4.771593821806431, "learning_rate": 9.96283394041954e-06, "loss": 0.2838, "step": 16 }, { "epoch": 0.0825242718446602, "grad_norm": 5.647520887110631, "learning_rate": 9.95804971304968e-06, "loss": 0.2629, "step": 17 }, { "epoch": 0.08737864077669903, "grad_norm": 3.896326412554688, "learning_rate": 9.952977205963496e-06, "loss": 0.2603, "step": 18 }, { "epoch": 0.09223300970873786, "grad_norm": 3.5675602735620866, "learning_rate": 9.94761671409569e-06, "loss": 0.2415, "step": 19 }, { "epoch": 0.0970873786407767, "grad_norm": 4.0379137220851415, "learning_rate": 9.941968549125481e-06, "loss": 0.293, "step": 20 }, { "epoch": 0.10194174757281553, "grad_norm": 4.64613913970608, "learning_rate": 9.936033039458494e-06, "loss": 0.2948, "step": 21 }, { "epoch": 0.10679611650485436, "grad_norm": 3.464915078651549, "learning_rate": 9.929810530207651e-06, "loss": 0.2524, "step": 22 }, { "epoch": 0.11165048543689321, "grad_norm": 3.783232742256657, "learning_rate": 9.923301383173119e-06, "loss": 0.2305, "step": 23 }, { "epoch": 0.11650485436893204, "grad_norm": 3.739820581253542, "learning_rate": 9.916505976821262e-06, "loss": 0.254, "step": 24 }, { "epoch": 0.12135922330097088, "grad_norm": 3.1347766470469813, "learning_rate": 9.909424706262647e-06, "loss": 0.1938, "step": 25 }, { "epoch": 0.1262135922330097, "grad_norm": 4.304760070176075, "learning_rate": 9.902057983229059e-06, "loss": 0.3184, "step": 26 }, { "epoch": 0.13106796116504854, "grad_norm": 3.772144092855404, "learning_rate": 9.894406236049569e-06, "loss": 0.2479, "step": 27 }, { "epoch": 0.13592233009708737, "grad_norm": 4.0895140326117625, "learning_rate": 9.886469909625624e-06, "loss": 0.2747, "step": 28 }, { "epoch": 0.1407766990291262, "grad_norm": 5.715906677385311, "learning_rate": 9.87824946540519e-06, "loss": 0.368, "step": 29 }, { "epoch": 0.14563106796116504, "grad_norm": 4.067187503242232, "learning_rate": 9.869745381355906e-06, "loss": 0.2841, "step": 30 }, { "epoch": 0.15048543689320387, "grad_norm": 4.2009121851915845, "learning_rate": 9.860958151937303e-06, "loss": 0.2679, "step": 31 }, { "epoch": 0.1553398058252427, "grad_norm": 3.6124743886539714, "learning_rate": 9.851888288072053e-06, "loss": 0.2299, "step": 32 }, { "epoch": 0.16019417475728157, "grad_norm": 4.559765429777921, "learning_rate": 9.842536317116262e-06, "loss": 0.3516, "step": 33 }, { "epoch": 0.1650485436893204, "grad_norm": 4.48974315163794, "learning_rate": 9.832902782828801e-06, "loss": 0.276, "step": 34 }, { "epoch": 0.16990291262135923, "grad_norm": 4.094541661305753, "learning_rate": 9.822988245339701e-06, "loss": 0.2946, "step": 35 }, { "epoch": 0.17475728155339806, "grad_norm": 5.182037046662737, "learning_rate": 9.81279328111758e-06, "loss": 0.2791, "step": 36 }, { "epoch": 0.1796116504854369, "grad_norm": 4.088551717879472, "learning_rate": 9.802318482936121e-06, "loss": 0.2831, "step": 37 }, { "epoch": 0.18446601941747573, "grad_norm": 3.483526381278066, "learning_rate": 9.791564459839609e-06, "loss": 0.2294, "step": 38 }, { "epoch": 0.18932038834951456, "grad_norm": 4.559058391577373, "learning_rate": 9.780531837107519e-06, "loss": 0.3326, "step": 39 }, { "epoch": 0.1941747572815534, "grad_norm": 4.665735809876591, "learning_rate": 9.769221256218165e-06, "loss": 0.3116, "step": 40 }, { "epoch": 0.19902912621359223, "grad_norm": 4.217548631938768, "learning_rate": 9.75763337481139e-06, "loss": 0.3462, "step": 41 }, { "epoch": 0.20388349514563106, "grad_norm": 4.437455024874878, "learning_rate": 9.745768866650339e-06, "loss": 0.3759, "step": 42 }, { "epoch": 0.2087378640776699, "grad_norm": 3.3723685716823595, "learning_rate": 9.73362842158228e-06, "loss": 0.2158, "step": 43 }, { "epoch": 0.21359223300970873, "grad_norm": 3.5814753989948835, "learning_rate": 9.721212745498493e-06, "loss": 0.2469, "step": 44 }, { "epoch": 0.21844660194174756, "grad_norm": 4.062627357765731, "learning_rate": 9.70852256029323e-06, "loss": 0.2319, "step": 45 }, { "epoch": 0.22330097087378642, "grad_norm": 4.188867288372569, "learning_rate": 9.695558603821735e-06, "loss": 0.2967, "step": 46 }, { "epoch": 0.22815533980582525, "grad_norm": 3.9173661992328874, "learning_rate": 9.682321629857348e-06, "loss": 0.2598, "step": 47 }, { "epoch": 0.23300970873786409, "grad_norm": 4.13811762281471, "learning_rate": 9.66881240804768e-06, "loss": 0.265, "step": 48 }, { "epoch": 0.23786407766990292, "grad_norm": 4.13576125166871, "learning_rate": 9.655031723869848e-06, "loss": 0.2608, "step": 49 }, { "epoch": 0.24271844660194175, "grad_norm": 4.918133296582067, "learning_rate": 9.64098037858483e-06, "loss": 0.308, "step": 50 }, { "epoch": 0.24757281553398058, "grad_norm": 3.6839102920449003, "learning_rate": 9.626659189190852e-06, "loss": 0.2052, "step": 51 }, { "epoch": 0.2524271844660194, "grad_norm": 4.072089137427962, "learning_rate": 9.612068988375898e-06, "loss": 0.2662, "step": 52 }, { "epoch": 0.25728155339805825, "grad_norm": 5.561646030072696, "learning_rate": 9.597210624469288e-06, "loss": 0.2904, "step": 53 }, { "epoch": 0.2621359223300971, "grad_norm": 3.9641265735200415, "learning_rate": 9.582084961392358e-06, "loss": 0.2236, "step": 54 }, { "epoch": 0.2669902912621359, "grad_norm": 3.816537549324726, "learning_rate": 9.566692878608229e-06, "loss": 0.2746, "step": 55 }, { "epoch": 0.27184466019417475, "grad_norm": 4.597374527618976, "learning_rate": 9.551035271070665e-06, "loss": 0.2868, "step": 56 }, { "epoch": 0.2766990291262136, "grad_norm": 4.332279895369425, "learning_rate": 9.53511304917204e-06, "loss": 0.2961, "step": 57 }, { "epoch": 0.2815533980582524, "grad_norm": 3.9436060015945733, "learning_rate": 9.51892713869041e-06, "loss": 0.2093, "step": 58 }, { "epoch": 0.28640776699029125, "grad_norm": 5.337307413172453, "learning_rate": 9.502478480735678e-06, "loss": 0.3436, "step": 59 }, { "epoch": 0.2912621359223301, "grad_norm": 4.849267457258223, "learning_rate": 9.485768031694872e-06, "loss": 0.3152, "step": 60 }, { "epoch": 0.2961165048543689, "grad_norm": 4.901178385569073, "learning_rate": 9.468796763176549e-06, "loss": 0.3324, "step": 61 }, { "epoch": 0.30097087378640774, "grad_norm": 4.220272072963617, "learning_rate": 9.45156566195429e-06, "loss": 0.2304, "step": 62 }, { "epoch": 0.3058252427184466, "grad_norm": 4.4766268926340835, "learning_rate": 9.43407572990933e-06, "loss": 0.2481, "step": 63 }, { "epoch": 0.3106796116504854, "grad_norm": 4.190554605283616, "learning_rate": 9.416327983972304e-06, "loss": 0.2925, "step": 64 }, { "epoch": 0.3155339805825243, "grad_norm": 4.476339319649827, "learning_rate": 9.398323456064124e-06, "loss": 0.3322, "step": 65 }, { "epoch": 0.32038834951456313, "grad_norm": 4.4653074936996795, "learning_rate": 9.380063193035968e-06, "loss": 0.3156, "step": 66 }, { "epoch": 0.32524271844660196, "grad_norm": 3.8118610747929393, "learning_rate": 9.361548256608421e-06, "loss": 0.2397, "step": 67 }, { "epoch": 0.3300970873786408, "grad_norm": 4.458833109734313, "learning_rate": 9.342779723309746e-06, "loss": 0.4079, "step": 68 }, { "epoch": 0.33495145631067963, "grad_norm": 3.9752115028553394, "learning_rate": 9.323758684413272e-06, "loss": 0.2417, "step": 69 }, { "epoch": 0.33980582524271846, "grad_norm": 3.6581853139335214, "learning_rate": 9.304486245873973e-06, "loss": 0.2252, "step": 70 }, { "epoch": 0.3446601941747573, "grad_norm": 4.476607161813386, "learning_rate": 9.284963528264133e-06, "loss": 0.2311, "step": 71 }, { "epoch": 0.34951456310679613, "grad_norm": 4.027412817527208, "learning_rate": 9.26519166670821e-06, "loss": 0.2501, "step": 72 }, { "epoch": 0.35436893203883496, "grad_norm": 4.481688426750254, "learning_rate": 9.24517181081683e-06, "loss": 0.2482, "step": 73 }, { "epoch": 0.3592233009708738, "grad_norm": 3.4733010960401325, "learning_rate": 9.22490512461995e-06, "loss": 0.2443, "step": 74 }, { "epoch": 0.3640776699029126, "grad_norm": 4.638383830849565, "learning_rate": 9.204392786499168e-06, "loss": 0.3248, "step": 75 }, { "epoch": 0.36893203883495146, "grad_norm": 3.5230252097334955, "learning_rate": 9.183635989119211e-06, "loss": 0.2503, "step": 76 }, { "epoch": 0.3737864077669903, "grad_norm": 3.9535428992415937, "learning_rate": 9.162635939358593e-06, "loss": 0.2357, "step": 77 }, { "epoch": 0.3786407766990291, "grad_norm": 4.204465864050127, "learning_rate": 9.141393858239435e-06, "loss": 0.2342, "step": 78 }, { "epoch": 0.38349514563106796, "grad_norm": 5.009199245522003, "learning_rate": 9.119910980856477e-06, "loss": 0.2807, "step": 79 }, { "epoch": 0.3883495145631068, "grad_norm": 4.171677417785281, "learning_rate": 9.098188556305262e-06, "loss": 0.3293, "step": 80 }, { "epoch": 0.3932038834951456, "grad_norm": 4.333515744894105, "learning_rate": 9.076227847609513e-06, "loss": 0.2562, "step": 81 }, { "epoch": 0.39805825242718446, "grad_norm": 3.253263455860887, "learning_rate": 9.054030131647682e-06, "loss": 0.2133, "step": 82 }, { "epoch": 0.4029126213592233, "grad_norm": 4.004164202940643, "learning_rate": 9.031596699078727e-06, "loss": 0.3433, "step": 83 }, { "epoch": 0.4077669902912621, "grad_norm": 3.987295970205518, "learning_rate": 9.008928854267054e-06, "loss": 0.2404, "step": 84 }, { "epoch": 0.41262135922330095, "grad_norm": 3.972193058734899, "learning_rate": 8.986027915206686e-06, "loss": 0.2362, "step": 85 }, { "epoch": 0.4174757281553398, "grad_norm": 4.480115480045549, "learning_rate": 8.962895213444618e-06, "loss": 0.25, "step": 86 }, { "epoch": 0.4223300970873786, "grad_norm": 3.2773872107660824, "learning_rate": 8.939532094003409e-06, "loss": 0.21, "step": 87 }, { "epoch": 0.42718446601941745, "grad_norm": 4.170869601435682, "learning_rate": 8.91593991530297e-06, "loss": 0.2679, "step": 88 }, { "epoch": 0.4320388349514563, "grad_norm": 5.418004883316298, "learning_rate": 8.892120049081577e-06, "loss": 0.3471, "step": 89 }, { "epoch": 0.4368932038834951, "grad_norm": 4.0315172897232365, "learning_rate": 8.868073880316125e-06, "loss": 0.3055, "step": 90 }, { "epoch": 0.441747572815534, "grad_norm": 3.7308197129881844, "learning_rate": 8.843802807141584e-06, "loss": 0.2481, "step": 91 }, { "epoch": 0.44660194174757284, "grad_norm": 4.517370831808369, "learning_rate": 8.819308240769726e-06, "loss": 0.3017, "step": 92 }, { "epoch": 0.45145631067961167, "grad_norm": 3.740912579474321, "learning_rate": 8.794591605407047e-06, "loss": 0.2474, "step": 93 }, { "epoch": 0.4563106796116505, "grad_norm": 4.71884113693785, "learning_rate": 8.769654338171986e-06, "loss": 0.3281, "step": 94 }, { "epoch": 0.46116504854368934, "grad_norm": 4.188356545579841, "learning_rate": 8.744497889011344e-06, "loss": 0.3008, "step": 95 }, { "epoch": 0.46601941747572817, "grad_norm": 3.537855015745784, "learning_rate": 8.71912372061598e-06, "loss": 0.2885, "step": 96 }, { "epoch": 0.470873786407767, "grad_norm": 3.2150611946582126, "learning_rate": 8.693533308335786e-06, "loss": 0.2235, "step": 97 }, { "epoch": 0.47572815533980584, "grad_norm": 3.895077363034686, "learning_rate": 8.667728140093876e-06, "loss": 0.261, "step": 98 }, { "epoch": 0.48058252427184467, "grad_norm": 4.370221621204338, "learning_rate": 8.641709716300092e-06, "loss": 0.2951, "step": 99 }, { "epoch": 0.4854368932038835, "grad_norm": 4.027597438755747, "learning_rate": 8.615479549763756e-06, "loss": 0.2929, "step": 100 }, { "epoch": 0.49029126213592233, "grad_norm": 3.426639006020909, "learning_rate": 8.589039165605716e-06, "loss": 0.2039, "step": 101 }, { "epoch": 0.49514563106796117, "grad_norm": 3.9582114999287876, "learning_rate": 8.56239010116966e-06, "loss": 0.2727, "step": 102 }, { "epoch": 0.5, "grad_norm": 3.795543145709201, "learning_rate": 8.535533905932739e-06, "loss": 0.2679, "step": 103 }, { "epoch": 0.5048543689320388, "grad_norm": 4.105886040553006, "learning_rate": 8.508472141415468e-06, "loss": 0.2872, "step": 104 }, { "epoch": 0.5097087378640777, "grad_norm": 4.016548475474929, "learning_rate": 8.481206381090934e-06, "loss": 0.2433, "step": 105 }, { "epoch": 0.5145631067961165, "grad_norm": 4.561704312852781, "learning_rate": 8.453738210293316e-06, "loss": 0.2532, "step": 106 }, { "epoch": 0.5194174757281553, "grad_norm": 4.199026706809067, "learning_rate": 8.426069226125695e-06, "loss": 0.2427, "step": 107 }, { "epoch": 0.5242718446601942, "grad_norm": 4.318908888171975, "learning_rate": 8.398201037367202e-06, "loss": 0.2822, "step": 108 }, { "epoch": 0.529126213592233, "grad_norm": 3.3514029501004483, "learning_rate": 8.370135264379475e-06, "loss": 0.251, "step": 109 }, { "epoch": 0.5339805825242718, "grad_norm": 3.5962215545923164, "learning_rate": 8.341873539012443e-06, "loss": 0.2267, "step": 110 }, { "epoch": 0.5388349514563107, "grad_norm": 3.3387107890658934, "learning_rate": 8.313417504509446e-06, "loss": 0.1973, "step": 111 }, { "epoch": 0.5436893203883495, "grad_norm": 3.6320184121677985, "learning_rate": 8.284768815411693e-06, "loss": 0.2699, "step": 112 }, { "epoch": 0.5485436893203883, "grad_norm": 4.387422198268259, "learning_rate": 8.255929137462049e-06, "loss": 0.266, "step": 113 }, { "epoch": 0.5533980582524272, "grad_norm": 4.64122961941939, "learning_rate": 8.226900147508205e-06, "loss": 0.2893, "step": 114 }, { "epoch": 0.558252427184466, "grad_norm": 3.725442272842501, "learning_rate": 8.197683533405156e-06, "loss": 0.2331, "step": 115 }, { "epoch": 0.5631067961165048, "grad_norm": 4.233338213323101, "learning_rate": 8.168280993917078e-06, "loss": 0.2883, "step": 116 }, { "epoch": 0.5679611650485437, "grad_norm": 4.2043046339035275, "learning_rate": 8.138694238618543e-06, "loss": 0.2267, "step": 117 }, { "epoch": 0.5728155339805825, "grad_norm": 4.026146623588584, "learning_rate": 8.108924987795137e-06, "loss": 0.2897, "step": 118 }, { "epoch": 0.5776699029126213, "grad_norm": 3.6164148039844646, "learning_rate": 8.078974972343414e-06, "loss": 0.2533, "step": 119 }, { "epoch": 0.5825242718446602, "grad_norm": 4.192038475806137, "learning_rate": 8.048845933670274e-06, "loss": 0.3124, "step": 120 }, { "epoch": 0.587378640776699, "grad_norm": 3.7059752835243867, "learning_rate": 8.01853962359169e-06, "loss": 0.2705, "step": 121 }, { "epoch": 0.5922330097087378, "grad_norm": 4.400480399277028, "learning_rate": 7.988057804230878e-06, "loss": 0.2367, "step": 122 }, { "epoch": 0.5970873786407767, "grad_norm": 3.282321333437772, "learning_rate": 7.957402247915817e-06, "loss": 0.1912, "step": 123 }, { "epoch": 0.6019417475728155, "grad_norm": 3.744753997591798, "learning_rate": 7.92657473707621e-06, "loss": 0.1912, "step": 124 }, { "epoch": 0.6067961165048543, "grad_norm": 4.169681509927491, "learning_rate": 7.895577064139847e-06, "loss": 0.3216, "step": 125 }, { "epoch": 0.6116504854368932, "grad_norm": 3.9038711056749618, "learning_rate": 7.864411031428379e-06, "loss": 0.2492, "step": 126 }, { "epoch": 0.616504854368932, "grad_norm": 3.322028518058869, "learning_rate": 7.833078451052537e-06, "loss": 0.2131, "step": 127 }, { "epoch": 0.6213592233009708, "grad_norm": 3.947039207000557, "learning_rate": 7.801581144806752e-06, "loss": 0.2765, "step": 128 }, { "epoch": 0.6262135922330098, "grad_norm": 3.9017439615171505, "learning_rate": 7.769920944063244e-06, "loss": 0.225, "step": 129 }, { "epoch": 0.6310679611650486, "grad_norm": 3.9643897061909756, "learning_rate": 7.73809968966554e-06, "loss": 0.2192, "step": 130 }, { "epoch": 0.6359223300970874, "grad_norm": 4.102642002541493, "learning_rate": 7.706119231821423e-06, "loss": 0.3014, "step": 131 }, { "epoch": 0.6407766990291263, "grad_norm": 3.8412144855081554, "learning_rate": 7.673981429995372e-06, "loss": 0.226, "step": 132 }, { "epoch": 0.6456310679611651, "grad_norm": 3.7368346138036928, "learning_rate": 7.641688152800433e-06, "loss": 0.2427, "step": 133 }, { "epoch": 0.6504854368932039, "grad_norm": 4.261154043116193, "learning_rate": 7.609241277889583e-06, "loss": 0.2238, "step": 134 }, { "epoch": 0.6553398058252428, "grad_norm": 4.4391952878407, "learning_rate": 7.5766426918465455e-06, "loss": 0.3092, "step": 135 }, { "epoch": 0.6601941747572816, "grad_norm": 3.4715190603779846, "learning_rate": 7.5438942900761035e-06, "loss": 0.2222, "step": 136 }, { "epoch": 0.6650485436893204, "grad_norm": 3.59258839192787, "learning_rate": 7.51099797669389e-06, "loss": 0.3024, "step": 137 }, { "epoch": 0.6699029126213593, "grad_norm": 4.044503855286348, "learning_rate": 7.477955664415678e-06, "loss": 0.2773, "step": 138 }, { "epoch": 0.6747572815533981, "grad_norm": 3.882557265615038, "learning_rate": 7.444769274446168e-06, "loss": 0.2718, "step": 139 }, { "epoch": 0.6796116504854369, "grad_norm": 4.128705052260471, "learning_rate": 7.411440736367281e-06, "loss": 0.2463, "step": 140 }, { "epoch": 0.6844660194174758, "grad_norm": 3.85487945321752, "learning_rate": 7.377971988025964e-06, "loss": 0.2383, "step": 141 }, { "epoch": 0.6893203883495146, "grad_norm": 3.6549478908232773, "learning_rate": 7.3443649754215175e-06, "loss": 0.1967, "step": 142 }, { "epoch": 0.6941747572815534, "grad_norm": 4.329614090604271, "learning_rate": 7.310621652592449e-06, "loss": 0.2597, "step": 143 }, { "epoch": 0.6990291262135923, "grad_norm": 3.29027958278087, "learning_rate": 7.276743981502856e-06, "loss": 0.2066, "step": 144 }, { "epoch": 0.7038834951456311, "grad_norm": 4.257756854746749, "learning_rate": 7.242733931928352e-06, "loss": 0.2616, "step": 145 }, { "epoch": 0.7087378640776699, "grad_norm": 3.3810738947884493, "learning_rate": 7.208593481341536e-06, "loss": 0.257, "step": 146 }, { "epoch": 0.7135922330097088, "grad_norm": 3.605775685730938, "learning_rate": 7.1743246147970095e-06, "loss": 0.2278, "step": 147 }, { "epoch": 0.7184466019417476, "grad_norm": 4.411396299705449, "learning_rate": 7.139929324815965e-06, "loss": 0.2978, "step": 148 }, { "epoch": 0.7233009708737864, "grad_norm": 2.99318780438867, "learning_rate": 7.105409611270332e-06, "loss": 0.1968, "step": 149 }, { "epoch": 0.7281553398058253, "grad_norm": 3.257896732809592, "learning_rate": 7.070767481266493e-06, "loss": 0.2355, "step": 150 }, { "epoch": 0.7330097087378641, "grad_norm": 3.4514771375738253, "learning_rate": 7.036004949028587e-06, "loss": 0.2058, "step": 151 }, { "epoch": 0.7378640776699029, "grad_norm": 3.4593192091941427, "learning_rate": 7.00112403578139e-06, "loss": 0.232, "step": 152 }, { "epoch": 0.7427184466019418, "grad_norm": 3.7827903841445387, "learning_rate": 6.9661267696328015e-06, "loss": 0.2918, "step": 153 }, { "epoch": 0.7475728155339806, "grad_norm": 3.5625628270167713, "learning_rate": 6.931015185455915e-06, "loss": 0.2448, "step": 154 }, { "epoch": 0.7524271844660194, "grad_norm": 4.665740266194277, "learning_rate": 6.895791324770702e-06, "loss": 0.3402, "step": 155 }, { "epoch": 0.7572815533980582, "grad_norm": 3.8252860517133778, "learning_rate": 6.860457235625322e-06, "loss": 0.2602, "step": 156 }, { "epoch": 0.7621359223300971, "grad_norm": 3.436260748820095, "learning_rate": 6.825014972477024e-06, "loss": 0.2417, "step": 157 }, { "epoch": 0.7669902912621359, "grad_norm": 4.232044892751484, "learning_rate": 6.7894665960727105e-06, "loss": 0.2851, "step": 158 }, { "epoch": 0.7718446601941747, "grad_norm": 4.0964768752721925, "learning_rate": 6.7538141733291e-06, "loss": 0.2594, "step": 159 }, { "epoch": 0.7766990291262136, "grad_norm": 3.9133660665052363, "learning_rate": 6.7180597772125665e-06, "loss": 0.2465, "step": 160 }, { "epoch": 0.7815533980582524, "grad_norm": 3.865991514099758, "learning_rate": 6.682205486618592e-06, "loss": 0.2872, "step": 161 }, { "epoch": 0.7864077669902912, "grad_norm": 4.319914375300806, "learning_rate": 6.646253386250909e-06, "loss": 0.256, "step": 162 }, { "epoch": 0.7912621359223301, "grad_norm": 4.416220089196962, "learning_rate": 6.610205566500272e-06, "loss": 0.3021, "step": 163 }, { "epoch": 0.7961165048543689, "grad_norm": 3.7978015769547997, "learning_rate": 6.574064123322925e-06, "loss": 0.2624, "step": 164 }, { "epoch": 0.8009708737864077, "grad_norm": 3.91268155076918, "learning_rate": 6.537831158118733e-06, "loss": 0.281, "step": 165 }, { "epoch": 0.8058252427184466, "grad_norm": 4.23034808456342, "learning_rate": 6.50150877760899e-06, "loss": 0.3013, "step": 166 }, { "epoch": 0.8106796116504854, "grad_norm": 4.587035934980501, "learning_rate": 6.465099093713944e-06, "loss": 0.2893, "step": 167 }, { "epoch": 0.8155339805825242, "grad_norm": 3.8318953534908164, "learning_rate": 6.42860422342998e-06, "loss": 0.2631, "step": 168 }, { "epoch": 0.8203883495145631, "grad_norm": 4.188496675983887, "learning_rate": 6.392026288706549e-06, "loss": 0.2181, "step": 169 }, { "epoch": 0.8252427184466019, "grad_norm": 3.8308122266509095, "learning_rate": 6.3553674163227786e-06, "loss": 0.2111, "step": 170 }, { "epoch": 0.8300970873786407, "grad_norm": 3.256931877458658, "learning_rate": 6.318629737763818e-06, "loss": 0.2492, "step": 171 }, { "epoch": 0.8349514563106796, "grad_norm": 4.291045875808786, "learning_rate": 6.281815389096903e-06, "loss": 0.2757, "step": 172 }, { "epoch": 0.8398058252427184, "grad_norm": 4.199826287237151, "learning_rate": 6.244926510847162e-06, "loss": 0.2816, "step": 173 }, { "epoch": 0.8446601941747572, "grad_norm": 3.950109271402058, "learning_rate": 6.207965247873151e-06, "loss": 0.2145, "step": 174 }, { "epoch": 0.8495145631067961, "grad_norm": 3.9000596120714994, "learning_rate": 6.1709337492421515e-06, "loss": 0.2168, "step": 175 }, { "epoch": 0.8543689320388349, "grad_norm": 4.055405291995013, "learning_rate": 6.133834168105206e-06, "loss": 0.2969, "step": 176 }, { "epoch": 0.8592233009708737, "grad_norm": 3.769805901751108, "learning_rate": 6.096668661571934e-06, "loss": 0.2892, "step": 177 }, { "epoch": 0.8640776699029126, "grad_norm": 3.723451818829994, "learning_rate": 6.0594393905851065e-06, "loss": 0.2883, "step": 178 }, { "epoch": 0.8689320388349514, "grad_norm": 4.3530471343494925, "learning_rate": 6.0221485197949995e-06, "loss": 0.291, "step": 179 }, { "epoch": 0.8737864077669902, "grad_norm": 4.495474214269869, "learning_rate": 5.9847982174335314e-06, "loss": 0.2926, "step": 180 }, { "epoch": 0.8786407766990292, "grad_norm": 4.289522595112411, "learning_rate": 5.9473906551881985e-06, "loss": 0.3009, "step": 181 }, { "epoch": 0.883495145631068, "grad_norm": 4.126197172937038, "learning_rate": 5.9099280080758085e-06, "loss": 0.2747, "step": 182 }, { "epoch": 0.8883495145631068, "grad_norm": 4.61706122117142, "learning_rate": 5.872412454315999e-06, "loss": 0.2875, "step": 183 }, { "epoch": 0.8932038834951457, "grad_norm": 4.9667921107900215, "learning_rate": 5.834846175204612e-06, "loss": 0.3182, "step": 184 }, { "epoch": 0.8980582524271845, "grad_norm": 4.018360437967008, "learning_rate": 5.797231354986842e-06, "loss": 0.2539, "step": 185 }, { "epoch": 0.9029126213592233, "grad_norm": 3.1301209008749207, "learning_rate": 5.759570180730255e-06, "loss": 0.2328, "step": 186 }, { "epoch": 0.9077669902912622, "grad_norm": 3.535553886489989, "learning_rate": 5.721864842197612e-06, "loss": 0.2215, "step": 187 }, { "epoch": 0.912621359223301, "grad_norm": 4.428224585185658, "learning_rate": 5.684117531719552e-06, "loss": 0.3178, "step": 188 }, { "epoch": 0.9174757281553398, "grad_norm": 4.465401225602881, "learning_rate": 5.646330444067121e-06, "loss": 0.2444, "step": 189 }, { "epoch": 0.9223300970873787, "grad_norm": 3.377118775491171, "learning_rate": 5.608505776324158e-06, "loss": 0.2202, "step": 190 }, { "epoch": 0.9271844660194175, "grad_norm": 3.8188339805747966, "learning_rate": 5.570645727759558e-06, "loss": 0.2906, "step": 191 }, { "epoch": 0.9320388349514563, "grad_norm": 3.274964312559964, "learning_rate": 5.532752499699381e-06, "loss": 0.2617, "step": 192 }, { "epoch": 0.9368932038834952, "grad_norm": 3.5773347833858016, "learning_rate": 5.494828295398874e-06, "loss": 0.2771, "step": 193 }, { "epoch": 0.941747572815534, "grad_norm": 3.6500131278961545, "learning_rate": 5.456875319914355e-06, "loss": 0.2449, "step": 194 }, { "epoch": 0.9466019417475728, "grad_norm": 3.656354634269112, "learning_rate": 5.4188957799750145e-06, "loss": 0.1927, "step": 195 }, { "epoch": 0.9514563106796117, "grad_norm": 3.35625346867669, "learning_rate": 5.380891883854591e-06, "loss": 0.2377, "step": 196 }, { "epoch": 0.9563106796116505, "grad_norm": 3.3081585991438307, "learning_rate": 5.34286584124299e-06, "loss": 0.2373, "step": 197 }, { "epoch": 0.9611650485436893, "grad_norm": 3.4353602958369884, "learning_rate": 5.304819863117796e-06, "loss": 0.2302, "step": 198 }, { "epoch": 0.9660194174757282, "grad_norm": 3.422761026443222, "learning_rate": 5.266756161615719e-06, "loss": 0.2465, "step": 199 }, { "epoch": 0.970873786407767, "grad_norm": 3.9687385194295812, "learning_rate": 5.228676949903974e-06, "loss": 0.2257, "step": 200 }, { "epoch": 0.9757281553398058, "grad_norm": 3.677616580427981, "learning_rate": 5.190584442051594e-06, "loss": 0.263, "step": 201 }, { "epoch": 0.9805825242718447, "grad_norm": 3.5214686067963252, "learning_rate": 5.1524808529007075e-06, "loss": 0.2707, "step": 202 }, { "epoch": 0.9854368932038835, "grad_norm": 3.4133643758495156, "learning_rate": 5.114368397937744e-06, "loss": 0.272, "step": 203 }, { "epoch": 0.9902912621359223, "grad_norm": 3.7286075637715683, "learning_rate": 5.07624929316463e-06, "loss": 0.2595, "step": 204 }, { "epoch": 0.9951456310679612, "grad_norm": 4.315712233586839, "learning_rate": 5.038125754969933e-06, "loss": 0.3029, "step": 205 }, { "epoch": 1.0, "grad_norm": 2.825288032181881, "learning_rate": 5e-06, "loss": 0.14, "step": 206 }, { "epoch": 1.0048543689320388, "grad_norm": 3.1076095063807982, "learning_rate": 4.9618742450300675e-06, "loss": 0.181, "step": 207 }, { "epoch": 1.0097087378640777, "grad_norm": 2.8396255618266384, "learning_rate": 4.923750706835371e-06, "loss": 0.1524, "step": 208 }, { "epoch": 1.0145631067961165, "grad_norm": 3.5716650964736383, "learning_rate": 4.8856316020622564e-06, "loss": 0.1805, "step": 209 }, { "epoch": 1.0194174757281553, "grad_norm": 2.367204341141735, "learning_rate": 4.847519147099294e-06, "loss": 0.1137, "step": 210 }, { "epoch": 1.0242718446601942, "grad_norm": 3.253604267981812, "learning_rate": 4.809415557948407e-06, "loss": 0.1593, "step": 211 }, { "epoch": 1.029126213592233, "grad_norm": 2.6973083592641673, "learning_rate": 4.771323050096028e-06, "loss": 0.1558, "step": 212 }, { "epoch": 1.0339805825242718, "grad_norm": 3.079960651908077, "learning_rate": 4.733243838384282e-06, "loss": 0.1396, "step": 213 }, { "epoch": 1.0388349514563107, "grad_norm": 2.875977868280872, "learning_rate": 4.6951801368822055e-06, "loss": 0.1513, "step": 214 }, { "epoch": 1.0436893203883495, "grad_norm": 3.175751532733471, "learning_rate": 4.6571341587570114e-06, "loss": 0.1379, "step": 215 }, { "epoch": 1.0485436893203883, "grad_norm": 2.5276557807622004, "learning_rate": 4.619108116145411e-06, "loss": 0.1246, "step": 216 }, { "epoch": 1.0533980582524272, "grad_norm": 2.738982516275384, "learning_rate": 4.581104220024988e-06, "loss": 0.1206, "step": 217 }, { "epoch": 1.058252427184466, "grad_norm": 3.5315724373326693, "learning_rate": 4.5431246800856455e-06, "loss": 0.1499, "step": 218 }, { "epoch": 1.0631067961165048, "grad_norm": 3.4470321615664856, "learning_rate": 4.505171704601128e-06, "loss": 0.163, "step": 219 }, { "epoch": 1.0679611650485437, "grad_norm": 2.700730020545396, "learning_rate": 4.467247500300621e-06, "loss": 0.1134, "step": 220 }, { "epoch": 1.0728155339805825, "grad_norm": 3.2655626452961326, "learning_rate": 4.4293542722404435e-06, "loss": 0.1259, "step": 221 }, { "epoch": 1.0776699029126213, "grad_norm": 6.096437215833138, "learning_rate": 4.391494223675843e-06, "loss": 0.1693, "step": 222 }, { "epoch": 1.0825242718446602, "grad_norm": 3.085518434706643, "learning_rate": 4.3536695559328816e-06, "loss": 0.1058, "step": 223 }, { "epoch": 1.087378640776699, "grad_norm": 4.217318866346489, "learning_rate": 4.31588246828045e-06, "loss": 0.1535, "step": 224 }, { "epoch": 1.0922330097087378, "grad_norm": 4.730386658288371, "learning_rate": 4.278135157802389e-06, "loss": 0.1739, "step": 225 }, { "epoch": 1.0970873786407767, "grad_norm": 3.7474266365254985, "learning_rate": 4.240429819269746e-06, "loss": 0.102, "step": 226 }, { "epoch": 1.1019417475728155, "grad_norm": 3.186000595735064, "learning_rate": 4.20276864501316e-06, "loss": 0.0949, "step": 227 }, { "epoch": 1.1067961165048543, "grad_norm": 4.0010808788227346, "learning_rate": 4.165153824795391e-06, "loss": 0.1423, "step": 228 }, { "epoch": 1.1116504854368932, "grad_norm": 3.4881908688849905, "learning_rate": 4.127587545684002e-06, "loss": 0.1231, "step": 229 }, { "epoch": 1.116504854368932, "grad_norm": 3.453501076215586, "learning_rate": 4.090071991924194e-06, "loss": 0.1313, "step": 230 }, { "epoch": 1.1213592233009708, "grad_norm": 3.417475335755339, "learning_rate": 4.052609344811802e-06, "loss": 0.1207, "step": 231 }, { "epoch": 1.1262135922330097, "grad_norm": 4.001575207369683, "learning_rate": 4.015201782566471e-06, "loss": 0.1331, "step": 232 }, { "epoch": 1.1310679611650485, "grad_norm": 3.956735622046391, "learning_rate": 3.977851480205003e-06, "loss": 0.1433, "step": 233 }, { "epoch": 1.1359223300970873, "grad_norm": 2.963338203453741, "learning_rate": 3.940560609414894e-06, "loss": 0.0955, "step": 234 }, { "epoch": 1.1407766990291262, "grad_norm": 3.3826701224860294, "learning_rate": 3.903331338428067e-06, "loss": 0.1204, "step": 235 }, { "epoch": 1.145631067961165, "grad_norm": 3.8835838324244287, "learning_rate": 3.866165831894796e-06, "loss": 0.1529, "step": 236 }, { "epoch": 1.1504854368932038, "grad_norm": 5.100921319397671, "learning_rate": 3.829066250757851e-06, "loss": 0.1197, "step": 237 }, { "epoch": 1.1553398058252426, "grad_norm": 4.4034886498879064, "learning_rate": 3.7920347521268514e-06, "loss": 0.1632, "step": 238 }, { "epoch": 1.1601941747572815, "grad_norm": 2.8258406334223753, "learning_rate": 3.7550734891528413e-06, "loss": 0.1282, "step": 239 }, { "epoch": 1.1650485436893203, "grad_norm": 3.1862106711416014, "learning_rate": 3.7181846109031007e-06, "loss": 0.11, "step": 240 }, { "epoch": 1.1699029126213591, "grad_norm": 3.3062959717568163, "learning_rate": 3.6813702622361858e-06, "loss": 0.132, "step": 241 }, { "epoch": 1.174757281553398, "grad_norm": 3.836762053357835, "learning_rate": 3.6446325836772244e-06, "loss": 0.129, "step": 242 }, { "epoch": 1.1796116504854368, "grad_norm": 3.366776128795921, "learning_rate": 3.6079737112934533e-06, "loss": 0.1131, "step": 243 }, { "epoch": 1.1844660194174756, "grad_norm": 3.371082171285664, "learning_rate": 3.5713957765700224e-06, "loss": 0.1208, "step": 244 }, { "epoch": 1.1893203883495145, "grad_norm": 2.88637185335307, "learning_rate": 3.5349009062860586e-06, "loss": 0.1427, "step": 245 }, { "epoch": 1.1941747572815533, "grad_norm": 3.650529994148201, "learning_rate": 3.4984912223910105e-06, "loss": 0.1248, "step": 246 }, { "epoch": 1.1990291262135921, "grad_norm": 3.398986578475348, "learning_rate": 3.46216884188127e-06, "loss": 0.1216, "step": 247 }, { "epoch": 1.203883495145631, "grad_norm": 3.242168749499786, "learning_rate": 3.425935876677077e-06, "loss": 0.138, "step": 248 }, { "epoch": 1.2087378640776698, "grad_norm": 3.8647346600763606, "learning_rate": 3.38979443349973e-06, "loss": 0.1094, "step": 249 }, { "epoch": 1.2135922330097086, "grad_norm": 4.421012580496002, "learning_rate": 3.3537466137490937e-06, "loss": 0.1289, "step": 250 }, { "epoch": 1.2184466019417475, "grad_norm": 3.0439555973232637, "learning_rate": 3.3177945133814093e-06, "loss": 0.1554, "step": 251 }, { "epoch": 1.2233009708737863, "grad_norm": 3.953190596926767, "learning_rate": 3.2819402227874364e-06, "loss": 0.1516, "step": 252 }, { "epoch": 1.2281553398058254, "grad_norm": 3.514326850079051, "learning_rate": 3.2461858266709017e-06, "loss": 0.1156, "step": 253 }, { "epoch": 1.233009708737864, "grad_norm": 2.800240807825986, "learning_rate": 3.2105334039272924e-06, "loss": 0.1289, "step": 254 }, { "epoch": 1.237864077669903, "grad_norm": 2.989713911706928, "learning_rate": 3.1749850275229777e-06, "loss": 0.1306, "step": 255 }, { "epoch": 1.2427184466019416, "grad_norm": 3.8485117995797338, "learning_rate": 3.1395427643746802e-06, "loss": 0.1422, "step": 256 }, { "epoch": 1.2475728155339807, "grad_norm": 2.856819187298172, "learning_rate": 3.1042086752292995e-06, "loss": 0.103, "step": 257 }, { "epoch": 1.2524271844660193, "grad_norm": 3.5910761866468763, "learning_rate": 3.068984814544087e-06, "loss": 0.162, "step": 258 }, { "epoch": 1.2572815533980584, "grad_norm": 3.5679376514662766, "learning_rate": 3.0338732303671993e-06, "loss": 0.1075, "step": 259 }, { "epoch": 1.262135922330097, "grad_norm": 3.179307171949073, "learning_rate": 2.99887596421861e-06, "loss": 0.1274, "step": 260 }, { "epoch": 1.266990291262136, "grad_norm": 3.7987588145635476, "learning_rate": 2.9639950509714138e-06, "loss": 0.151, "step": 261 }, { "epoch": 1.2718446601941746, "grad_norm": 3.045919745755663, "learning_rate": 2.929232518733507e-06, "loss": 0.1531, "step": 262 }, { "epoch": 1.2766990291262137, "grad_norm": 3.3693086929377594, "learning_rate": 2.8945903887296686e-06, "loss": 0.1465, "step": 263 }, { "epoch": 1.2815533980582523, "grad_norm": 3.49236375510186, "learning_rate": 2.860070675184036e-06, "loss": 0.1139, "step": 264 }, { "epoch": 1.2864077669902914, "grad_norm": 3.2955029024719695, "learning_rate": 2.8256753852029917e-06, "loss": 0.1413, "step": 265 }, { "epoch": 1.29126213592233, "grad_norm": 3.393102058516812, "learning_rate": 2.7914065186584637e-06, "loss": 0.1295, "step": 266 }, { "epoch": 1.296116504854369, "grad_norm": 3.3987352001434044, "learning_rate": 2.757266068071648e-06, "loss": 0.1188, "step": 267 }, { "epoch": 1.3009708737864076, "grad_norm": 4.613865964943307, "learning_rate": 2.7232560184971437e-06, "loss": 0.1803, "step": 268 }, { "epoch": 1.3058252427184467, "grad_norm": 3.2092131895096236, "learning_rate": 2.689378347407553e-06, "loss": 0.1346, "step": 269 }, { "epoch": 1.3106796116504853, "grad_norm": 3.583509166057441, "learning_rate": 2.6556350245784833e-06, "loss": 0.1112, "step": 270 }, { "epoch": 1.3155339805825244, "grad_norm": 3.2408708413710463, "learning_rate": 2.6220280119740376e-06, "loss": 0.13, "step": 271 }, { "epoch": 1.3203883495145632, "grad_norm": 3.0782963890167423, "learning_rate": 2.588559263632719e-06, "loss": 0.1401, "step": 272 }, { "epoch": 1.325242718446602, "grad_norm": 3.957513507362698, "learning_rate": 2.555230725553832e-06, "loss": 0.1006, "step": 273 }, { "epoch": 1.3300970873786409, "grad_norm": 3.1814340451896705, "learning_rate": 2.522044335584322e-06, "loss": 0.1412, "step": 274 }, { "epoch": 1.3349514563106797, "grad_norm": 6.518267289673356, "learning_rate": 2.489002023306112e-06, "loss": 0.1815, "step": 275 }, { "epoch": 1.3398058252427185, "grad_norm": 4.596805280069048, "learning_rate": 2.4561057099238973e-06, "loss": 0.1648, "step": 276 }, { "epoch": 1.3446601941747574, "grad_norm": 4.771581909467749, "learning_rate": 2.423357308153454e-06, "loss": 0.1645, "step": 277 }, { "epoch": 1.3495145631067962, "grad_norm": 3.17704181282022, "learning_rate": 2.390758722110418e-06, "loss": 0.1277, "step": 278 }, { "epoch": 1.354368932038835, "grad_norm": 3.111399705249996, "learning_rate": 2.358311847199567e-06, "loss": 0.1239, "step": 279 }, { "epoch": 1.3592233009708738, "grad_norm": 2.866862935336539, "learning_rate": 2.3260185700046295e-06, "loss": 0.0964, "step": 280 }, { "epoch": 1.3640776699029127, "grad_norm": 3.0986339656435296, "learning_rate": 2.2938807681785764e-06, "loss": 0.1343, "step": 281 }, { "epoch": 1.3689320388349515, "grad_norm": 3.3430689254582635, "learning_rate": 2.2619003103344607e-06, "loss": 0.1328, "step": 282 }, { "epoch": 1.3737864077669903, "grad_norm": 3.1487079094564554, "learning_rate": 2.2300790559367553e-06, "loss": 0.1202, "step": 283 }, { "epoch": 1.3786407766990292, "grad_norm": 3.238532270513983, "learning_rate": 2.1984188551932513e-06, "loss": 0.1235, "step": 284 }, { "epoch": 1.383495145631068, "grad_norm": 4.97423341807088, "learning_rate": 2.166921548947466e-06, "loss": 0.1695, "step": 285 }, { "epoch": 1.3883495145631068, "grad_norm": 3.675539337946243, "learning_rate": 2.1355889685716225e-06, "loss": 0.1531, "step": 286 }, { "epoch": 1.3932038834951457, "grad_norm": 4.288997034109127, "learning_rate": 2.1044229358601543e-06, "loss": 0.1787, "step": 287 }, { "epoch": 1.3980582524271845, "grad_norm": 3.2576349865088865, "learning_rate": 2.0734252629237892e-06, "loss": 0.1298, "step": 288 }, { "epoch": 1.4029126213592233, "grad_norm": 3.223044386138016, "learning_rate": 2.0425977520841837e-06, "loss": 0.1072, "step": 289 }, { "epoch": 1.4077669902912622, "grad_norm": 2.827790393186252, "learning_rate": 2.011942195769122e-06, "loss": 0.0968, "step": 290 }, { "epoch": 1.412621359223301, "grad_norm": 3.1569438578744853, "learning_rate": 1.9814603764083112e-06, "loss": 0.1118, "step": 291 }, { "epoch": 1.4174757281553398, "grad_norm": 3.6256217050622754, "learning_rate": 1.9511540663297284e-06, "loss": 0.1313, "step": 292 }, { "epoch": 1.4223300970873787, "grad_norm": 3.1670340068868037, "learning_rate": 1.921025027656587e-06, "loss": 0.1225, "step": 293 }, { "epoch": 1.4271844660194175, "grad_norm": 3.403811700568661, "learning_rate": 1.8910750122048638e-06, "loss": 0.121, "step": 294 }, { "epoch": 1.4320388349514563, "grad_norm": 3.4107286750978445, "learning_rate": 1.8613057613814584e-06, "loss": 0.1191, "step": 295 }, { "epoch": 1.4368932038834952, "grad_norm": 3.509353618467711, "learning_rate": 1.8317190060829242e-06, "loss": 0.129, "step": 296 }, { "epoch": 1.441747572815534, "grad_norm": 3.7309553747136888, "learning_rate": 1.8023164665948455e-06, "loss": 0.1519, "step": 297 }, { "epoch": 1.4466019417475728, "grad_norm": 3.371018559941889, "learning_rate": 1.773099852491796e-06, "loss": 0.1284, "step": 298 }, { "epoch": 1.4514563106796117, "grad_norm": 3.3374954825617857, "learning_rate": 1.7440708625379503e-06, "loss": 0.1241, "step": 299 }, { "epoch": 1.4563106796116505, "grad_norm": 4.312272200162922, "learning_rate": 1.7152311845883096e-06, "loss": 0.1836, "step": 300 }, { "epoch": 1.4611650485436893, "grad_norm": 3.132725799402524, "learning_rate": 1.686582495490554e-06, "loss": 0.1482, "step": 301 }, { "epoch": 1.4660194174757282, "grad_norm": 3.3818687537371948, "learning_rate": 1.658126460987558e-06, "loss": 0.1178, "step": 302 }, { "epoch": 1.470873786407767, "grad_norm": 4.3184228468810195, "learning_rate": 1.6298647356205255e-06, "loss": 0.178, "step": 303 }, { "epoch": 1.4757281553398058, "grad_norm": 2.8317733082549243, "learning_rate": 1.601798962632799e-06, "loss": 0.1093, "step": 304 }, { "epoch": 1.4805825242718447, "grad_norm": 4.339159909638061, "learning_rate": 1.573930773874306e-06, "loss": 0.1138, "step": 305 }, { "epoch": 1.4854368932038835, "grad_norm": 3.0321303019340218, "learning_rate": 1.5462617897066863e-06, "loss": 0.1286, "step": 306 }, { "epoch": 1.4902912621359223, "grad_norm": 3.046145379255184, "learning_rate": 1.5187936189090668e-06, "loss": 0.1437, "step": 307 }, { "epoch": 1.4951456310679612, "grad_norm": 3.7352753174585795, "learning_rate": 1.491527858584535e-06, "loss": 0.15, "step": 308 }, { "epoch": 1.5, "grad_norm": 3.0786633197480744, "learning_rate": 1.4644660940672628e-06, "loss": 0.1322, "step": 309 }, { "epoch": 1.5048543689320388, "grad_norm": 3.1856158825848624, "learning_rate": 1.4376098988303406e-06, "loss": 0.1159, "step": 310 }, { "epoch": 1.5097087378640777, "grad_norm": 4.138235201110144, "learning_rate": 1.4109608343942855e-06, "loss": 0.1102, "step": 311 }, { "epoch": 1.5145631067961165, "grad_norm": 4.266345177020503, "learning_rate": 1.3845204502362442e-06, "loss": 0.1326, "step": 312 }, { "epoch": 1.5194174757281553, "grad_norm": 3.6631861655006532, "learning_rate": 1.35829028369991e-06, "loss": 0.1365, "step": 313 }, { "epoch": 1.5242718446601942, "grad_norm": 2.796146848602047, "learning_rate": 1.3322718599061252e-06, "loss": 0.1228, "step": 314 }, { "epoch": 1.529126213592233, "grad_norm": 4.323075604128194, "learning_rate": 1.306466691664216e-06, "loss": 0.1469, "step": 315 }, { "epoch": 1.5339805825242718, "grad_norm": 3.791146553197469, "learning_rate": 1.28087627938402e-06, "loss": 0.1284, "step": 316 }, { "epoch": 1.5388349514563107, "grad_norm": 3.4584290863440006, "learning_rate": 1.2555021109886589e-06, "loss": 0.1208, "step": 317 }, { "epoch": 1.5436893203883495, "grad_norm": 3.3754777738094446, "learning_rate": 1.2303456618280141e-06, "loss": 0.134, "step": 318 }, { "epoch": 1.5485436893203883, "grad_norm": 3.0081973970518048, "learning_rate": 1.2054083945929534e-06, "loss": 0.1073, "step": 319 }, { "epoch": 1.5533980582524272, "grad_norm": 2.8464999049520627, "learning_rate": 1.1806917592302763e-06, "loss": 0.1244, "step": 320 }, { "epoch": 1.558252427184466, "grad_norm": 3.651592958305491, "learning_rate": 1.1561971928584158e-06, "loss": 0.1205, "step": 321 }, { "epoch": 1.5631067961165048, "grad_norm": 3.384066329219771, "learning_rate": 1.1319261196838782e-06, "loss": 0.1477, "step": 322 }, { "epoch": 1.5679611650485437, "grad_norm": 3.962602857918603, "learning_rate": 1.1078799509184246e-06, "loss": 0.142, "step": 323 }, { "epoch": 1.5728155339805825, "grad_norm": 4.2134772762813535, "learning_rate": 1.0840600846970333e-06, "loss": 0.1577, "step": 324 }, { "epoch": 1.5776699029126213, "grad_norm": 3.5329896377380403, "learning_rate": 1.0604679059965923e-06, "loss": 0.2112, "step": 325 }, { "epoch": 1.5825242718446602, "grad_norm": 3.5339697498025737, "learning_rate": 1.0371047865553847e-06, "loss": 0.1685, "step": 326 }, { "epoch": 1.587378640776699, "grad_norm": 3.5491468895744065, "learning_rate": 1.0139720847933166e-06, "loss": 0.111, "step": 327 }, { "epoch": 1.5922330097087378, "grad_norm": 4.018795908874112, "learning_rate": 9.91071145732948e-07, "loss": 0.1331, "step": 328 }, { "epoch": 1.5970873786407767, "grad_norm": 4.295446107749891, "learning_rate": 9.684033009212752e-07, "loss": 0.162, "step": 329 }, { "epoch": 1.6019417475728155, "grad_norm": 4.017644694750769, "learning_rate": 9.459698683523205e-07, "loss": 0.1312, "step": 330 }, { "epoch": 1.6067961165048543, "grad_norm": 4.246177768722918, "learning_rate": 9.237721523904891e-07, "loss": 0.2103, "step": 331 }, { "epoch": 1.6116504854368932, "grad_norm": 2.5653252470150174, "learning_rate": 9.018114436947373e-07, "loss": 0.1035, "step": 332 }, { "epoch": 1.616504854368932, "grad_norm": 3.6830525953195803, "learning_rate": 8.80089019143524e-07, "loss": 0.1435, "step": 333 }, { "epoch": 1.6213592233009708, "grad_norm": 3.3368417217901523, "learning_rate": 8.586061417605668e-07, "loss": 0.1244, "step": 334 }, { "epoch": 1.6262135922330097, "grad_norm": 2.979664762954336, "learning_rate": 8.373640606414097e-07, "loss": 0.092, "step": 335 }, { "epoch": 1.6310679611650487, "grad_norm": 4.222876514037551, "learning_rate": 8.163640108807897e-07, "loss": 0.1379, "step": 336 }, { "epoch": 1.6359223300970873, "grad_norm": 2.842862264638519, "learning_rate": 7.956072135008336e-07, "loss": 0.1028, "step": 337 }, { "epoch": 1.6407766990291264, "grad_norm": 4.1715444349980935, "learning_rate": 7.750948753800508e-07, "loss": 0.1305, "step": 338 }, { "epoch": 1.645631067961165, "grad_norm": 3.71407595743837, "learning_rate": 7.548281891831715e-07, "loss": 0.1527, "step": 339 }, { "epoch": 1.650485436893204, "grad_norm": 4.137772721935057, "learning_rate": 7.348083332917927e-07, "loss": 0.1387, "step": 340 }, { "epoch": 1.6553398058252426, "grad_norm": 8.345167893621168, "learning_rate": 7.150364717358699e-07, "loss": 0.1674, "step": 341 }, { "epoch": 1.6601941747572817, "grad_norm": 2.8808093020934713, "learning_rate": 6.955137541260287e-07, "loss": 0.1343, "step": 342 }, { "epoch": 1.6650485436893203, "grad_norm": 3.093208326650529, "learning_rate": 6.762413155867276e-07, "loss": 0.1241, "step": 343 }, { "epoch": 1.6699029126213594, "grad_norm": 3.98939133325456, "learning_rate": 6.572202766902569e-07, "loss": 0.1737, "step": 344 }, { "epoch": 1.674757281553398, "grad_norm": 3.7462129379246107, "learning_rate": 6.384517433915794e-07, "loss": 0.1412, "step": 345 }, { "epoch": 1.679611650485437, "grad_norm": 3.3042462886266493, "learning_rate": 6.199368069640343e-07, "loss": 0.1503, "step": 346 }, { "epoch": 1.6844660194174756, "grad_norm": 3.734930093771564, "learning_rate": 6.016765439358774e-07, "loss": 0.1612, "step": 347 }, { "epoch": 1.6893203883495147, "grad_norm": 3.316716962886949, "learning_rate": 5.836720160276971e-07, "loss": 0.1248, "step": 348 }, { "epoch": 1.6941747572815533, "grad_norm": 3.4128467191242042, "learning_rate": 5.659242700906719e-07, "loss": 0.1122, "step": 349 }, { "epoch": 1.6990291262135924, "grad_norm": 3.1569546121453493, "learning_rate": 5.484343380457124e-07, "loss": 0.1262, "step": 350 }, { "epoch": 1.703883495145631, "grad_norm": 3.1052277068199783, "learning_rate": 5.312032368234527e-07, "loss": 0.1391, "step": 351 }, { "epoch": 1.70873786407767, "grad_norm": 3.266567040448877, "learning_rate": 5.1423196830513e-07, "loss": 0.1211, "step": 352 }, { "epoch": 1.7135922330097086, "grad_norm": 2.9247936466704014, "learning_rate": 4.975215192643246e-07, "loss": 0.1072, "step": 353 }, { "epoch": 1.7184466019417477, "grad_norm": 3.041452400291823, "learning_rate": 4.81072861309591e-07, "loss": 0.0978, "step": 354 }, { "epoch": 1.7233009708737863, "grad_norm": 3.127960800774389, "learning_rate": 4.648869508279613e-07, "loss": 0.1052, "step": 355 }, { "epoch": 1.7281553398058254, "grad_norm": 3.1405916778115643, "learning_rate": 4.4896472892933693e-07, "loss": 0.115, "step": 356 }, { "epoch": 1.733009708737864, "grad_norm": 3.055566866293225, "learning_rate": 4.333071213917722e-07, "loss": 0.099, "step": 357 }, { "epoch": 1.737864077669903, "grad_norm": 3.0696135943962335, "learning_rate": 4.179150386076425e-07, "loss": 0.1335, "step": 358 }, { "epoch": 1.7427184466019416, "grad_norm": 3.709292422749404, "learning_rate": 4.027893755307144e-07, "loss": 0.1504, "step": 359 }, { "epoch": 1.7475728155339807, "grad_norm": 4.481315129511695, "learning_rate": 3.8793101162410417e-07, "loss": 0.1458, "step": 360 }, { "epoch": 1.7524271844660193, "grad_norm": 3.1818272956029174, "learning_rate": 3.733408108091485e-07, "loss": 0.1064, "step": 361 }, { "epoch": 1.7572815533980584, "grad_norm": 3.7843408133363066, "learning_rate": 3.5901962141516975e-07, "loss": 0.1488, "step": 362 }, { "epoch": 1.762135922330097, "grad_norm": 3.6729841150655984, "learning_rate": 3.4496827613015206e-07, "loss": 0.1263, "step": 363 }, { "epoch": 1.766990291262136, "grad_norm": 3.564050424842182, "learning_rate": 3.3118759195232273e-07, "loss": 0.1268, "step": 364 }, { "epoch": 1.7718446601941746, "grad_norm": 3.3751825037513306, "learning_rate": 3.176783701426528e-07, "loss": 0.1274, "step": 365 }, { "epoch": 1.7766990291262137, "grad_norm": 4.73777827269484, "learning_rate": 3.0444139617826605e-07, "loss": 0.1466, "step": 366 }, { "epoch": 1.7815533980582523, "grad_norm": 3.789623333202209, "learning_rate": 2.91477439706771e-07, "loss": 0.165, "step": 367 }, { "epoch": 1.7864077669902914, "grad_norm": 3.345919526336724, "learning_rate": 2.787872545015069e-07, "loss": 0.121, "step": 368 }, { "epoch": 1.79126213592233, "grad_norm": 3.23239065738004, "learning_rate": 2.663715784177201e-07, "loss": 0.1204, "step": 369 }, { "epoch": 1.796116504854369, "grad_norm": 3.867294135630766, "learning_rate": 2.542311333496622e-07, "loss": 0.1557, "step": 370 }, { "epoch": 1.8009708737864076, "grad_norm": 3.8416100779048112, "learning_rate": 2.423666251886114e-07, "loss": 0.1526, "step": 371 }, { "epoch": 1.8058252427184467, "grad_norm": 3.8191639519422957, "learning_rate": 2.307787437818365e-07, "loss": 0.1362, "step": 372 }, { "epoch": 1.8106796116504853, "grad_norm": 3.5324396915575815, "learning_rate": 2.1946816289248163e-07, "loss": 0.128, "step": 373 }, { "epoch": 1.8155339805825244, "grad_norm": 3.937405351211592, "learning_rate": 2.0843554016039326e-07, "loss": 0.1272, "step": 374 }, { "epoch": 1.820388349514563, "grad_norm": 3.6309480792066045, "learning_rate": 1.9768151706388016e-07, "loss": 0.1383, "step": 375 }, { "epoch": 1.825242718446602, "grad_norm": 4.812602376991873, "learning_rate": 1.8720671888242058e-07, "loss": 0.151, "step": 376 }, { "epoch": 1.8300970873786406, "grad_norm": 3.422331358164789, "learning_rate": 1.7701175466029895e-07, "loss": 0.1237, "step": 377 }, { "epoch": 1.8349514563106797, "grad_norm": 3.9942126857073443, "learning_rate": 1.6709721717120042e-07, "loss": 0.2045, "step": 378 }, { "epoch": 1.8398058252427183, "grad_norm": 3.2598726884525226, "learning_rate": 1.574636828837395e-07, "loss": 0.1332, "step": 379 }, { "epoch": 1.8446601941747574, "grad_norm": 2.8617656328542505, "learning_rate": 1.4811171192794628e-07, "loss": 0.1076, "step": 380 }, { "epoch": 1.849514563106796, "grad_norm": 3.46333809211242, "learning_rate": 1.3904184806269705e-07, "loss": 0.1375, "step": 381 }, { "epoch": 1.854368932038835, "grad_norm": 3.50189413524924, "learning_rate": 1.3025461864409395e-07, "loss": 0.1084, "step": 382 }, { "epoch": 1.8592233009708736, "grad_norm": 3.638355557627245, "learning_rate": 1.2175053459481e-07, "loss": 0.139, "step": 383 }, { "epoch": 1.8640776699029127, "grad_norm": 4.119172346052458, "learning_rate": 1.1353009037437523e-07, "loss": 0.1359, "step": 384 }, { "epoch": 1.8689320388349513, "grad_norm": 3.158569389383108, "learning_rate": 1.0559376395043285e-07, "loss": 0.132, "step": 385 }, { "epoch": 1.8737864077669903, "grad_norm": 2.978947917353967, "learning_rate": 9.794201677094162e-08, "loss": 0.1055, "step": 386 }, { "epoch": 1.8786407766990292, "grad_norm": 3.8300006069291466, "learning_rate": 9.05752937373533e-08, "loss": 0.1319, "step": 387 }, { "epoch": 1.883495145631068, "grad_norm": 3.2915388999222124, "learning_rate": 8.34940231787379e-08, "loss": 0.1249, "step": 388 }, { "epoch": 1.8883495145631068, "grad_norm": 3.2273864880240777, "learning_rate": 7.66986168268824e-08, "loss": 0.1158, "step": 389 }, { "epoch": 1.8932038834951457, "grad_norm": 3.9636677519320096, "learning_rate": 7.018946979234997e-08, "loss": 0.1573, "step": 390 }, { "epoch": 1.8980582524271845, "grad_norm": 3.128351850166789, "learning_rate": 6.396696054150719e-08, "loss": 0.0954, "step": 391 }, { "epoch": 1.9029126213592233, "grad_norm": 3.296305880869336, "learning_rate": 5.803145087451945e-08, "loss": 0.1234, "step": 392 }, { "epoch": 1.9077669902912622, "grad_norm": 3.8469136141019553, "learning_rate": 5.238328590431163e-08, "loss": 0.1567, "step": 393 }, { "epoch": 1.912621359223301, "grad_norm": 3.045143901902489, "learning_rate": 4.702279403650534e-08, "loss": 0.1263, "step": 394 }, { "epoch": 1.9174757281553398, "grad_norm": 3.8569105039741527, "learning_rate": 4.195028695032133e-08, "loss": 0.1579, "step": 395 }, { "epoch": 1.9223300970873787, "grad_norm": 4.425431809276777, "learning_rate": 3.716605958046071e-08, "loss": 0.1573, "step": 396 }, { "epoch": 1.9271844660194175, "grad_norm": 3.7669673676489697, "learning_rate": 3.2670390099951985e-08, "loss": 0.148, "step": 397 }, { "epoch": 1.9320388349514563, "grad_norm": 4.986828587513846, "learning_rate": 2.846353990398065e-08, "loss": 0.1716, "step": 398 }, { "epoch": 1.9368932038834952, "grad_norm": 3.3450842341009563, "learning_rate": 2.4545753594688582e-08, "loss": 0.1124, "step": 399 }, { "epoch": 1.941747572815534, "grad_norm": 3.5248076552820087, "learning_rate": 2.0917258966953735e-08, "loss": 0.1189, "step": 400 }, { "epoch": 1.9466019417475728, "grad_norm": 3.279075957571082, "learning_rate": 1.757826699514298e-08, "loss": 0.1543, "step": 401 }, { "epoch": 1.9514563106796117, "grad_norm": 3.7381137731914555, "learning_rate": 1.4528971820846894e-08, "loss": 0.1403, "step": 402 }, { "epoch": 1.9563106796116505, "grad_norm": 2.9335591357898076, "learning_rate": 1.176955074159214e-08, "loss": 0.1196, "step": 403 }, { "epoch": 1.9611650485436893, "grad_norm": 3.735378478280465, "learning_rate": 9.300164200530815e-09, "loss": 0.1035, "step": 404 }, { "epoch": 1.9660194174757282, "grad_norm": 3.921113583618365, "learning_rate": 7.120955777112915e-09, "loss": 0.1387, "step": 405 }, { "epoch": 1.970873786407767, "grad_norm": 3.6009147627703166, "learning_rate": 5.232052178738567e-09, "loss": 0.1197, "step": 406 }, { "epoch": 1.9757281553398058, "grad_norm": 3.4985370424636786, "learning_rate": 3.633563233388926e-09, "loss": 0.1199, "step": 407 }, { "epoch": 1.9805825242718447, "grad_norm": 4.391769239300577, "learning_rate": 2.3255818832423894e-09, "loss": 0.1305, "step": 408 }, { "epoch": 1.9854368932038835, "grad_norm": 3.334284089866996, "learning_rate": 1.3081841792694783e-09, "loss": 0.128, "step": 409 }, { "epoch": 1.9902912621359223, "grad_norm": 3.29948237906008, "learning_rate": 5.814292768108187e-10, "loss": 0.1116, "step": 410 }, { "epoch": 1.9951456310679612, "grad_norm": 3.515868756780877, "learning_rate": 1.453594321393359e-10, "loss": 0.1469, "step": 411 }, { "epoch": 2.0, "grad_norm": 2.4023313688701156, "learning_rate": 0.0, "loss": 0.1017, "step": 412 }, { "epoch": 2.0, "step": 412, "total_flos": 792393179136.0, "train_loss": 0.1997755226471181, "train_runtime": 254.681, "train_samples_per_second": 12.887, "train_steps_per_second": 1.618 } ], "logging_steps": 1, "max_steps": 412, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 50000000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 792393179136.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }