{ "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": 5.378143407634127, "learning_rate": 9.999854640567861e-06, "loss": 0.3464, "step": 1 }, { "epoch": 0.009708737864077669, "grad_norm": 4.894296929528875, "learning_rate": 9.999418570723189e-06, "loss": 0.3255, "step": 2 }, { "epoch": 0.014563106796116505, "grad_norm": 7.351759486789586, "learning_rate": 9.998691815820732e-06, "loss": 0.4611, "step": 3 }, { "epoch": 0.019417475728155338, "grad_norm": 5.271446077550997, "learning_rate": 9.997674418116759e-06, "loss": 0.4408, "step": 4 }, { "epoch": 0.024271844660194174, "grad_norm": 3.612464756117011, "learning_rate": 9.996366436766612e-06, "loss": 0.3053, "step": 5 }, { "epoch": 0.02912621359223301, "grad_norm": 4.572942668158758, "learning_rate": 9.994767947821261e-06, "loss": 0.3871, "step": 6 }, { "epoch": 0.03398058252427184, "grad_norm": 4.011088042824444, "learning_rate": 9.992879044222887e-06, "loss": 0.2683, "step": 7 }, { "epoch": 0.038834951456310676, "grad_norm": 3.770696527596648, "learning_rate": 9.99069983579947e-06, "loss": 0.299, "step": 8 }, { "epoch": 0.043689320388349516, "grad_norm": 3.99445466882808, "learning_rate": 9.988230449258409e-06, "loss": 0.2953, "step": 9 }, { "epoch": 0.04854368932038835, "grad_norm": 3.305857445393283, "learning_rate": 9.985471028179155e-06, "loss": 0.2231, "step": 10 }, { "epoch": 0.05339805825242718, "grad_norm": 4.4807917263811765, "learning_rate": 9.982421733004857e-06, "loss": 0.3227, "step": 11 }, { "epoch": 0.05825242718446602, "grad_norm": 3.8723393421519368, "learning_rate": 9.979082741033047e-06, "loss": 0.2654, "step": 12 }, { "epoch": 0.06310679611650485, "grad_norm": 3.972191046860092, "learning_rate": 9.975454246405312e-06, "loss": 0.2567, "step": 13 }, { "epoch": 0.06796116504854369, "grad_norm": 5.326392755632004, "learning_rate": 9.971536460096021e-06, "loss": 0.4939, "step": 14 }, { "epoch": 0.07281553398058252, "grad_norm": 3.911942426386476, "learning_rate": 9.96732960990005e-06, "loss": 0.2872, "step": 15 }, { "epoch": 0.07766990291262135, "grad_norm": 3.8227075161218576, "learning_rate": 9.96283394041954e-06, "loss": 0.2827, "step": 16 }, { "epoch": 0.0825242718446602, "grad_norm": 4.917122259212616, "learning_rate": 9.95804971304968e-06, "loss": 0.3229, "step": 17 }, { "epoch": 0.08737864077669903, "grad_norm": 3.5881520748906803, "learning_rate": 9.952977205963496e-06, "loss": 0.2462, "step": 18 }, { "epoch": 0.09223300970873786, "grad_norm": 3.2615635933708305, "learning_rate": 9.94761671409569e-06, "loss": 0.2877, "step": 19 }, { "epoch": 0.0970873786407767, "grad_norm": 3.580768122545938, "learning_rate": 9.941968549125481e-06, "loss": 0.3244, "step": 20 }, { "epoch": 0.10194174757281553, "grad_norm": 3.5694832101684346, "learning_rate": 9.936033039458494e-06, "loss": 0.3041, "step": 21 }, { "epoch": 0.10679611650485436, "grad_norm": 3.7251131637258914, "learning_rate": 9.929810530207651e-06, "loss": 0.3085, "step": 22 }, { "epoch": 0.11165048543689321, "grad_norm": 3.1294125258938346, "learning_rate": 9.923301383173119e-06, "loss": 0.2735, "step": 23 }, { "epoch": 0.11650485436893204, "grad_norm": 3.498762097373417, "learning_rate": 9.916505976821262e-06, "loss": 0.2977, "step": 24 }, { "epoch": 0.12135922330097088, "grad_norm": 3.4347462789997016, "learning_rate": 9.909424706262647e-06, "loss": 0.2773, "step": 25 }, { "epoch": 0.1262135922330097, "grad_norm": 4.042734295116432, "learning_rate": 9.902057983229059e-06, "loss": 0.3298, "step": 26 }, { "epoch": 0.13106796116504854, "grad_norm": 3.402243403849008, "learning_rate": 9.894406236049569e-06, "loss": 0.2786, "step": 27 }, { "epoch": 0.13592233009708737, "grad_norm": 3.932743924163005, "learning_rate": 9.886469909625624e-06, "loss": 0.3188, "step": 28 }, { "epoch": 0.1407766990291262, "grad_norm": 3.905197044703144, "learning_rate": 9.87824946540519e-06, "loss": 0.3535, "step": 29 }, { "epoch": 0.14563106796116504, "grad_norm": 3.609206552249489, "learning_rate": 9.869745381355906e-06, "loss": 0.2909, "step": 30 }, { "epoch": 0.15048543689320387, "grad_norm": 3.414831784710911, "learning_rate": 9.860958151937303e-06, "loss": 0.2574, "step": 31 }, { "epoch": 0.1553398058252427, "grad_norm": 3.5579321291929116, "learning_rate": 9.851888288072053e-06, "loss": 0.2459, "step": 32 }, { "epoch": 0.16019417475728157, "grad_norm": 4.162641219147627, "learning_rate": 9.842536317116262e-06, "loss": 0.3588, "step": 33 }, { "epoch": 0.1650485436893204, "grad_norm": 4.68580370285394, "learning_rate": 9.832902782828801e-06, "loss": 0.3702, "step": 34 }, { "epoch": 0.16990291262135923, "grad_norm": 4.193004613941464, "learning_rate": 9.822988245339701e-06, "loss": 0.381, "step": 35 }, { "epoch": 0.17475728155339806, "grad_norm": 4.355494846026111, "learning_rate": 9.81279328111758e-06, "loss": 0.3122, "step": 36 }, { "epoch": 0.1796116504854369, "grad_norm": 3.9624635452437906, "learning_rate": 9.802318482936121e-06, "loss": 0.3228, "step": 37 }, { "epoch": 0.18446601941747573, "grad_norm": 4.016385482613762, "learning_rate": 9.791564459839609e-06, "loss": 0.3008, "step": 38 }, { "epoch": 0.18932038834951456, "grad_norm": 4.060884878117307, "learning_rate": 9.780531837107519e-06, "loss": 0.3423, "step": 39 }, { "epoch": 0.1941747572815534, "grad_norm": 3.9972439902223775, "learning_rate": 9.769221256218165e-06, "loss": 0.3306, "step": 40 }, { "epoch": 0.19902912621359223, "grad_norm": 3.792327487947346, "learning_rate": 9.75763337481139e-06, "loss": 0.3476, "step": 41 }, { "epoch": 0.20388349514563106, "grad_norm": 3.6416741800021715, "learning_rate": 9.745768866650339e-06, "loss": 0.3449, "step": 42 }, { "epoch": 0.2087378640776699, "grad_norm": 3.4964559729684797, "learning_rate": 9.73362842158228e-06, "loss": 0.2669, "step": 43 }, { "epoch": 0.21359223300970873, "grad_norm": 3.441263103573181, "learning_rate": 9.721212745498493e-06, "loss": 0.2742, "step": 44 }, { "epoch": 0.21844660194174756, "grad_norm": 3.917275363205342, "learning_rate": 9.70852256029323e-06, "loss": 0.2954, "step": 45 }, { "epoch": 0.22330097087378642, "grad_norm": 4.181842792733697, "learning_rate": 9.695558603821735e-06, "loss": 0.3589, "step": 46 }, { "epoch": 0.22815533980582525, "grad_norm": 3.4511140959192277, "learning_rate": 9.682321629857348e-06, "loss": 0.324, "step": 47 }, { "epoch": 0.23300970873786409, "grad_norm": 3.789785520542004, "learning_rate": 9.66881240804768e-06, "loss": 0.308, "step": 48 }, { "epoch": 0.23786407766990292, "grad_norm": 4.598754296184572, "learning_rate": 9.655031723869848e-06, "loss": 0.3861, "step": 49 }, { "epoch": 0.24271844660194175, "grad_norm": 5.1330458881850225, "learning_rate": 9.64098037858483e-06, "loss": 0.3893, "step": 50 }, { "epoch": 0.24757281553398058, "grad_norm": 3.3657145440506264, "learning_rate": 9.626659189190852e-06, "loss": 0.263, "step": 51 }, { "epoch": 0.2524271844660194, "grad_norm": 3.554083897905739, "learning_rate": 9.612068988375898e-06, "loss": 0.3167, "step": 52 }, { "epoch": 0.25728155339805825, "grad_norm": 4.500513509448257, "learning_rate": 9.597210624469288e-06, "loss": 0.3181, "step": 53 }, { "epoch": 0.2621359223300971, "grad_norm": 3.34099829795081, "learning_rate": 9.582084961392358e-06, "loss": 0.2965, "step": 54 }, { "epoch": 0.2669902912621359, "grad_norm": 3.466575422333381, "learning_rate": 9.566692878608229e-06, "loss": 0.3219, "step": 55 }, { "epoch": 0.27184466019417475, "grad_norm": 4.250464552549045, "learning_rate": 9.551035271070665e-06, "loss": 0.3541, "step": 56 }, { "epoch": 0.2766990291262136, "grad_norm": 3.6232412587871043, "learning_rate": 9.53511304917204e-06, "loss": 0.3005, "step": 57 }, { "epoch": 0.2815533980582524, "grad_norm": 3.571200047447214, "learning_rate": 9.51892713869041e-06, "loss": 0.2616, "step": 58 }, { "epoch": 0.28640776699029125, "grad_norm": 4.347354232094379, "learning_rate": 9.502478480735678e-06, "loss": 0.3722, "step": 59 }, { "epoch": 0.2912621359223301, "grad_norm": 3.87730169839573, "learning_rate": 9.485768031694872e-06, "loss": 0.3117, "step": 60 }, { "epoch": 0.2961165048543689, "grad_norm": 4.274501416159858, "learning_rate": 9.468796763176549e-06, "loss": 0.3849, "step": 61 }, { "epoch": 0.30097087378640774, "grad_norm": 3.246374985365425, "learning_rate": 9.45156566195429e-06, "loss": 0.2522, "step": 62 }, { "epoch": 0.3058252427184466, "grad_norm": 3.696747350462723, "learning_rate": 9.43407572990933e-06, "loss": 0.293, "step": 63 }, { "epoch": 0.3106796116504854, "grad_norm": 3.9338713829165584, "learning_rate": 9.416327983972304e-06, "loss": 0.3201, "step": 64 }, { "epoch": 0.3155339805825243, "grad_norm": 4.0017810616141425, "learning_rate": 9.398323456064124e-06, "loss": 0.3799, "step": 65 }, { "epoch": 0.32038834951456313, "grad_norm": 3.8342637859675444, "learning_rate": 9.380063193035968e-06, "loss": 0.292, "step": 66 }, { "epoch": 0.32524271844660196, "grad_norm": 3.827573439920934, "learning_rate": 9.361548256608421e-06, "loss": 0.2921, "step": 67 }, { "epoch": 0.3300970873786408, "grad_norm": 3.9845442576869092, "learning_rate": 9.342779723309746e-06, "loss": 0.4174, "step": 68 }, { "epoch": 0.33495145631067963, "grad_norm": 3.1026015714842954, "learning_rate": 9.323758684413272e-06, "loss": 0.235, "step": 69 }, { "epoch": 0.33980582524271846, "grad_norm": 3.7750036783126393, "learning_rate": 9.304486245873973e-06, "loss": 0.3227, "step": 70 }, { "epoch": 0.3446601941747573, "grad_norm": 3.943387424903264, "learning_rate": 9.284963528264133e-06, "loss": 0.3371, "step": 71 }, { "epoch": 0.34951456310679613, "grad_norm": 3.8381884344953825, "learning_rate": 9.26519166670821e-06, "loss": 0.2894, "step": 72 }, { "epoch": 0.35436893203883496, "grad_norm": 3.544434059167168, "learning_rate": 9.24517181081683e-06, "loss": 0.2685, "step": 73 }, { "epoch": 0.3592233009708738, "grad_norm": 3.378961777033687, "learning_rate": 9.22490512461995e-06, "loss": 0.2781, "step": 74 }, { "epoch": 0.3640776699029126, "grad_norm": 4.331788711997835, "learning_rate": 9.204392786499168e-06, "loss": 0.3451, "step": 75 }, { "epoch": 0.36893203883495146, "grad_norm": 3.4925860733450476, "learning_rate": 9.183635989119211e-06, "loss": 0.2746, "step": 76 }, { "epoch": 0.3737864077669903, "grad_norm": 3.794077796789663, "learning_rate": 9.162635939358593e-06, "loss": 0.279, "step": 77 }, { "epoch": 0.3786407766990291, "grad_norm": 4.069630918475093, "learning_rate": 9.141393858239435e-06, "loss": 0.3196, "step": 78 }, { "epoch": 0.38349514563106796, "grad_norm": 3.7846293915199527, "learning_rate": 9.119910980856477e-06, "loss": 0.3348, "step": 79 }, { "epoch": 0.3883495145631068, "grad_norm": 3.267156149708633, "learning_rate": 9.098188556305262e-06, "loss": 0.3272, "step": 80 }, { "epoch": 0.3932038834951456, "grad_norm": 3.3968613462591133, "learning_rate": 9.076227847609513e-06, "loss": 0.2808, "step": 81 }, { "epoch": 0.39805825242718446, "grad_norm": 3.011208559175575, "learning_rate": 9.054030131647682e-06, "loss": 0.2372, "step": 82 }, { "epoch": 0.4029126213592233, "grad_norm": 4.051616797054234, "learning_rate": 9.031596699078727e-06, "loss": 0.4596, "step": 83 }, { "epoch": 0.4077669902912621, "grad_norm": 3.6075025150149225, "learning_rate": 9.008928854267054e-06, "loss": 0.2939, "step": 84 }, { "epoch": 0.41262135922330095, "grad_norm": 4.135509053101431, "learning_rate": 8.986027915206686e-06, "loss": 0.2967, "step": 85 }, { "epoch": 0.4174757281553398, "grad_norm": 3.7862374826186826, "learning_rate": 8.962895213444618e-06, "loss": 0.2671, "step": 86 }, { "epoch": 0.4223300970873786, "grad_norm": 3.0878348574553676, "learning_rate": 8.939532094003409e-06, "loss": 0.2706, "step": 87 }, { "epoch": 0.42718446601941745, "grad_norm": 3.7265938482807037, "learning_rate": 8.91593991530297e-06, "loss": 0.316, "step": 88 }, { "epoch": 0.4320388349514563, "grad_norm": 4.630457617713916, "learning_rate": 8.892120049081577e-06, "loss": 0.3866, "step": 89 }, { "epoch": 0.4368932038834951, "grad_norm": 3.9288103295473937, "learning_rate": 8.868073880316125e-06, "loss": 0.3674, "step": 90 }, { "epoch": 0.441747572815534, "grad_norm": 3.6634831334676816, "learning_rate": 8.843802807141584e-06, "loss": 0.2437, "step": 91 }, { "epoch": 0.44660194174757284, "grad_norm": 3.9345830082103834, "learning_rate": 8.819308240769726e-06, "loss": 0.3072, "step": 92 }, { "epoch": 0.45145631067961167, "grad_norm": 3.696277061427197, "learning_rate": 8.794591605407047e-06, "loss": 0.3546, "step": 93 }, { "epoch": 0.4563106796116505, "grad_norm": 4.6325972388154035, "learning_rate": 8.769654338171986e-06, "loss": 0.3703, "step": 94 }, { "epoch": 0.46116504854368934, "grad_norm": 3.720951674003812, "learning_rate": 8.744497889011344e-06, "loss": 0.3023, "step": 95 }, { "epoch": 0.46601941747572817, "grad_norm": 3.4941267371150158, "learning_rate": 8.71912372061598e-06, "loss": 0.3681, "step": 96 }, { "epoch": 0.470873786407767, "grad_norm": 3.59440313295267, "learning_rate": 8.693533308335786e-06, "loss": 0.2995, "step": 97 }, { "epoch": 0.47572815533980584, "grad_norm": 3.699310247730822, "learning_rate": 8.667728140093876e-06, "loss": 0.3316, "step": 98 }, { "epoch": 0.48058252427184467, "grad_norm": 4.114605116349415, "learning_rate": 8.641709716300092e-06, "loss": 0.3059, "step": 99 }, { "epoch": 0.4854368932038835, "grad_norm": 3.656975878650179, "learning_rate": 8.615479549763756e-06, "loss": 0.3385, "step": 100 }, { "epoch": 0.49029126213592233, "grad_norm": 3.3815288817303313, "learning_rate": 8.589039165605716e-06, "loss": 0.2678, "step": 101 }, { "epoch": 0.49514563106796117, "grad_norm": 3.638304857763173, "learning_rate": 8.56239010116966e-06, "loss": 0.3167, "step": 102 }, { "epoch": 0.5, "grad_norm": 3.6323757635548635, "learning_rate": 8.535533905932739e-06, "loss": 0.2918, "step": 103 }, { "epoch": 0.5048543689320388, "grad_norm": 4.183379717690887, "learning_rate": 8.508472141415468e-06, "loss": 0.3186, "step": 104 }, { "epoch": 0.5097087378640777, "grad_norm": 4.154343055084759, "learning_rate": 8.481206381090934e-06, "loss": 0.2626, "step": 105 }, { "epoch": 0.5145631067961165, "grad_norm": 3.5786841796945685, "learning_rate": 8.453738210293316e-06, "loss": 0.2824, "step": 106 }, { "epoch": 0.5194174757281553, "grad_norm": 4.168143564101458, "learning_rate": 8.426069226125695e-06, "loss": 0.3458, "step": 107 }, { "epoch": 0.5242718446601942, "grad_norm": 4.126139154772882, "learning_rate": 8.398201037367202e-06, "loss": 0.3052, "step": 108 }, { "epoch": 0.529126213592233, "grad_norm": 3.237923851122716, "learning_rate": 8.370135264379475e-06, "loss": 0.2874, "step": 109 }, { "epoch": 0.5339805825242718, "grad_norm": 3.1249087177275308, "learning_rate": 8.341873539012443e-06, "loss": 0.2394, "step": 110 }, { "epoch": 0.5388349514563107, "grad_norm": 5.074364305711858, "learning_rate": 8.313417504509446e-06, "loss": 0.2302, "step": 111 }, { "epoch": 0.5436893203883495, "grad_norm": 3.3253330575964495, "learning_rate": 8.284768815411693e-06, "loss": 0.2861, "step": 112 }, { "epoch": 0.5485436893203883, "grad_norm": 4.360168763243382, "learning_rate": 8.255929137462049e-06, "loss": 0.3128, "step": 113 }, { "epoch": 0.5533980582524272, "grad_norm": 4.27399461394767, "learning_rate": 8.226900147508205e-06, "loss": 0.3279, "step": 114 }, { "epoch": 0.558252427184466, "grad_norm": 3.3681041810207755, "learning_rate": 8.197683533405156e-06, "loss": 0.2547, "step": 115 }, { "epoch": 0.5631067961165048, "grad_norm": 4.055671521702825, "learning_rate": 8.168280993917078e-06, "loss": 0.3092, "step": 116 }, { "epoch": 0.5679611650485437, "grad_norm": 4.248189965027739, "learning_rate": 8.138694238618543e-06, "loss": 0.3236, "step": 117 }, { "epoch": 0.5728155339805825, "grad_norm": 3.612343188062059, "learning_rate": 8.108924987795137e-06, "loss": 0.3403, "step": 118 }, { "epoch": 0.5776699029126213, "grad_norm": 4.111961208705483, "learning_rate": 8.078974972343414e-06, "loss": 0.3044, "step": 119 }, { "epoch": 0.5825242718446602, "grad_norm": 4.120026736966224, "learning_rate": 8.048845933670274e-06, "loss": 0.2845, "step": 120 }, { "epoch": 0.587378640776699, "grad_norm": 3.4954482548295878, "learning_rate": 8.01853962359169e-06, "loss": 0.2441, "step": 121 }, { "epoch": 0.5922330097087378, "grad_norm": 3.9071335972909744, "learning_rate": 7.988057804230878e-06, "loss": 0.2879, "step": 122 }, { "epoch": 0.5970873786407767, "grad_norm": 2.957098675744294, "learning_rate": 7.957402247915817e-06, "loss": 0.2138, "step": 123 }, { "epoch": 0.6019417475728155, "grad_norm": 3.140479418310476, "learning_rate": 7.92657473707621e-06, "loss": 0.2111, "step": 124 }, { "epoch": 0.6067961165048543, "grad_norm": 3.0799814234459526, "learning_rate": 7.895577064139847e-06, "loss": 0.2861, "step": 125 }, { "epoch": 0.6116504854368932, "grad_norm": 3.627717678753021, "learning_rate": 7.864411031428379e-06, "loss": 0.2902, "step": 126 }, { "epoch": 0.616504854368932, "grad_norm": 3.2781356561377173, "learning_rate": 7.833078451052537e-06, "loss": 0.2605, "step": 127 }, { "epoch": 0.6213592233009708, "grad_norm": 3.4215884348866066, "learning_rate": 7.801581144806752e-06, "loss": 0.3316, "step": 128 }, { "epoch": 0.6262135922330098, "grad_norm": 3.8424343189726944, "learning_rate": 7.769920944063244e-06, "loss": 0.2814, "step": 129 }, { "epoch": 0.6310679611650486, "grad_norm": 3.675388135381745, "learning_rate": 7.73809968966554e-06, "loss": 0.2795, "step": 130 }, { "epoch": 0.6359223300970874, "grad_norm": 3.374157334994161, "learning_rate": 7.706119231821423e-06, "loss": 0.2682, "step": 131 }, { "epoch": 0.6407766990291263, "grad_norm": 3.6605583885523747, "learning_rate": 7.673981429995372e-06, "loss": 0.2905, "step": 132 }, { "epoch": 0.6456310679611651, "grad_norm": 3.5259822612580742, "learning_rate": 7.641688152800433e-06, "loss": 0.2976, "step": 133 }, { "epoch": 0.6504854368932039, "grad_norm": 4.18102995202913, "learning_rate": 7.609241277889583e-06, "loss": 0.3087, "step": 134 }, { "epoch": 0.6553398058252428, "grad_norm": 4.0348888803242655, "learning_rate": 7.5766426918465455e-06, "loss": 0.333, "step": 135 }, { "epoch": 0.6601941747572816, "grad_norm": 3.4205146965325266, "learning_rate": 7.5438942900761035e-06, "loss": 0.2855, "step": 136 }, { "epoch": 0.6650485436893204, "grad_norm": 3.412779284207671, "learning_rate": 7.51099797669389e-06, "loss": 0.3524, "step": 137 }, { "epoch": 0.6699029126213593, "grad_norm": 4.100430036338693, "learning_rate": 7.477955664415678e-06, "loss": 0.3284, "step": 138 }, { "epoch": 0.6747572815533981, "grad_norm": 3.720199127017926, "learning_rate": 7.444769274446168e-06, "loss": 0.3126, "step": 139 }, { "epoch": 0.6796116504854369, "grad_norm": 3.8004784956588096, "learning_rate": 7.411440736367281e-06, "loss": 0.2948, "step": 140 }, { "epoch": 0.6844660194174758, "grad_norm": 3.5169102335864197, "learning_rate": 7.377971988025964e-06, "loss": 0.2755, "step": 141 }, { "epoch": 0.6893203883495146, "grad_norm": 3.633867939521945, "learning_rate": 7.3443649754215175e-06, "loss": 0.2561, "step": 142 }, { "epoch": 0.6941747572815534, "grad_norm": 4.117823557197984, "learning_rate": 7.310621652592449e-06, "loss": 0.3183, "step": 143 }, { "epoch": 0.6990291262135923, "grad_norm": 3.6453109102828125, "learning_rate": 7.276743981502856e-06, "loss": 0.2784, "step": 144 }, { "epoch": 0.7038834951456311, "grad_norm": 3.7103243970413438, "learning_rate": 7.242733931928352e-06, "loss": 0.2566, "step": 145 }, { "epoch": 0.7087378640776699, "grad_norm": 2.8634018006912907, "learning_rate": 7.208593481341536e-06, "loss": 0.263, "step": 146 }, { "epoch": 0.7135922330097088, "grad_norm": 3.264744989210774, "learning_rate": 7.1743246147970095e-06, "loss": 0.2541, "step": 147 }, { "epoch": 0.7184466019417476, "grad_norm": 3.8329899318886365, "learning_rate": 7.139929324815965e-06, "loss": 0.2955, "step": 148 }, { "epoch": 0.7233009708737864, "grad_norm": 3.057133605338264, "learning_rate": 7.105409611270332e-06, "loss": 0.2343, "step": 149 }, { "epoch": 0.7281553398058253, "grad_norm": 3.0782458045158125, "learning_rate": 7.070767481266493e-06, "loss": 0.2848, "step": 150 }, { "epoch": 0.7330097087378641, "grad_norm": 4.5134038568086785, "learning_rate": 7.036004949028587e-06, "loss": 0.3047, "step": 151 }, { "epoch": 0.7378640776699029, "grad_norm": 3.4495413151855634, "learning_rate": 7.00112403578139e-06, "loss": 0.3213, "step": 152 }, { "epoch": 0.7427184466019418, "grad_norm": 3.6153705645026473, "learning_rate": 6.9661267696328015e-06, "loss": 0.3286, "step": 153 }, { "epoch": 0.7475728155339806, "grad_norm": 3.5409135769472484, "learning_rate": 6.931015185455915e-06, "loss": 0.2804, "step": 154 }, { "epoch": 0.7524271844660194, "grad_norm": 4.081839122757467, "learning_rate": 6.895791324770702e-06, "loss": 0.3751, "step": 155 }, { "epoch": 0.7572815533980582, "grad_norm": 3.700678050097594, "learning_rate": 6.860457235625322e-06, "loss": 0.3016, "step": 156 }, { "epoch": 0.7621359223300971, "grad_norm": 3.3810443516637267, "learning_rate": 6.825014972477024e-06, "loss": 0.3056, "step": 157 }, { "epoch": 0.7669902912621359, "grad_norm": 3.500935431083706, "learning_rate": 6.7894665960727105e-06, "loss": 0.2945, "step": 158 }, { "epoch": 0.7718446601941747, "grad_norm": 3.434907597687763, "learning_rate": 6.7538141733291e-06, "loss": 0.2763, "step": 159 }, { "epoch": 0.7766990291262136, "grad_norm": 3.493356091277342, "learning_rate": 6.7180597772125665e-06, "loss": 0.2843, "step": 160 }, { "epoch": 0.7815533980582524, "grad_norm": 3.2671065559456505, "learning_rate": 6.682205486618592e-06, "loss": 0.2955, "step": 161 }, { "epoch": 0.7864077669902912, "grad_norm": 3.572930865165925, "learning_rate": 6.646253386250909e-06, "loss": 0.3555, "step": 162 }, { "epoch": 0.7912621359223301, "grad_norm": 3.353967102879005, "learning_rate": 6.610205566500272e-06, "loss": 0.3002, "step": 163 }, { "epoch": 0.7961165048543689, "grad_norm": 3.621050618749983, "learning_rate": 6.574064123322925e-06, "loss": 0.32, "step": 164 }, { "epoch": 0.8009708737864077, "grad_norm": 3.1954385846083224, "learning_rate": 6.537831158118733e-06, "loss": 0.2386, "step": 165 }, { "epoch": 0.8058252427184466, "grad_norm": 3.498291968306301, "learning_rate": 6.50150877760899e-06, "loss": 0.3214, "step": 166 }, { "epoch": 0.8106796116504854, "grad_norm": 3.6931182322968876, "learning_rate": 6.465099093713944e-06, "loss": 0.3249, "step": 167 }, { "epoch": 0.8155339805825242, "grad_norm": 2.8313942704171597, "learning_rate": 6.42860422342998e-06, "loss": 0.277, "step": 168 }, { "epoch": 0.8203883495145631, "grad_norm": 3.5716383992818224, "learning_rate": 6.392026288706549e-06, "loss": 0.2689, "step": 169 }, { "epoch": 0.8252427184466019, "grad_norm": 3.176200152955033, "learning_rate": 6.3553674163227786e-06, "loss": 0.2275, "step": 170 }, { "epoch": 0.8300970873786407, "grad_norm": 3.2229277647359478, "learning_rate": 6.318629737763818e-06, "loss": 0.3031, "step": 171 }, { "epoch": 0.8349514563106796, "grad_norm": 4.096738874622841, "learning_rate": 6.281815389096903e-06, "loss": 0.2688, "step": 172 }, { "epoch": 0.8398058252427184, "grad_norm": 3.832793824430796, "learning_rate": 6.244926510847162e-06, "loss": 0.3124, "step": 173 }, { "epoch": 0.8446601941747572, "grad_norm": 3.842229798125395, "learning_rate": 6.207965247873151e-06, "loss": 0.3541, "step": 174 }, { "epoch": 0.8495145631067961, "grad_norm": 3.3136829491923647, "learning_rate": 6.1709337492421515e-06, "loss": 0.2365, "step": 175 }, { "epoch": 0.8543689320388349, "grad_norm": 3.4725652481004587, "learning_rate": 6.133834168105206e-06, "loss": 0.2936, "step": 176 }, { "epoch": 0.8592233009708737, "grad_norm": 3.504250626880649, "learning_rate": 6.096668661571934e-06, "loss": 0.3113, "step": 177 }, { "epoch": 0.8640776699029126, "grad_norm": 3.672219050586378, "learning_rate": 6.0594393905851065e-06, "loss": 0.3333, "step": 178 }, { "epoch": 0.8689320388349514, "grad_norm": 3.9044739145181255, "learning_rate": 6.0221485197949995e-06, "loss": 0.2887, "step": 179 }, { "epoch": 0.8737864077669902, "grad_norm": 3.8629510412843744, "learning_rate": 5.9847982174335314e-06, "loss": 0.3359, "step": 180 }, { "epoch": 0.8786407766990292, "grad_norm": 4.0714916209398035, "learning_rate": 5.9473906551881985e-06, "loss": 0.3581, "step": 181 }, { "epoch": 0.883495145631068, "grad_norm": 3.4522804075936957, "learning_rate": 5.9099280080758085e-06, "loss": 0.2594, "step": 182 }, { "epoch": 0.8883495145631068, "grad_norm": 4.288129870849474, "learning_rate": 5.872412454315999e-06, "loss": 0.3649, "step": 183 }, { "epoch": 0.8932038834951457, "grad_norm": 3.9685985589287602, "learning_rate": 5.834846175204612e-06, "loss": 0.3596, "step": 184 }, { "epoch": 0.8980582524271845, "grad_norm": 3.8055775375801986, "learning_rate": 5.797231354986842e-06, "loss": 0.3317, "step": 185 }, { "epoch": 0.9029126213592233, "grad_norm": 3.3371096323112766, "learning_rate": 5.759570180730255e-06, "loss": 0.3251, "step": 186 }, { "epoch": 0.9077669902912622, "grad_norm": 3.118923832267533, "learning_rate": 5.721864842197612e-06, "loss": 0.2382, "step": 187 }, { "epoch": 0.912621359223301, "grad_norm": 4.13009064895878, "learning_rate": 5.684117531719552e-06, "loss": 0.4122, "step": 188 }, { "epoch": 0.9174757281553398, "grad_norm": 4.589591211779461, "learning_rate": 5.646330444067121e-06, "loss": 0.3073, "step": 189 }, { "epoch": 0.9223300970873787, "grad_norm": 3.113626275612425, "learning_rate": 5.608505776324158e-06, "loss": 0.25, "step": 190 }, { "epoch": 0.9271844660194175, "grad_norm": 3.9416392350920835, "learning_rate": 5.570645727759558e-06, "loss": 0.3232, "step": 191 }, { "epoch": 0.9320388349514563, "grad_norm": 3.489820470468405, "learning_rate": 5.532752499699381e-06, "loss": 0.355, "step": 192 }, { "epoch": 0.9368932038834952, "grad_norm": 3.3456720028459177, "learning_rate": 5.494828295398874e-06, "loss": 0.2735, "step": 193 }, { "epoch": 0.941747572815534, "grad_norm": 3.1645574613781116, "learning_rate": 5.456875319914355e-06, "loss": 0.2552, "step": 194 }, { "epoch": 0.9466019417475728, "grad_norm": 3.310670471294068, "learning_rate": 5.4188957799750145e-06, "loss": 0.2289, "step": 195 }, { "epoch": 0.9514563106796117, "grad_norm": 2.9162726270426353, "learning_rate": 5.380891883854591e-06, "loss": 0.2711, "step": 196 }, { "epoch": 0.9563106796116505, "grad_norm": 2.980226316434736, "learning_rate": 5.34286584124299e-06, "loss": 0.231, "step": 197 }, { "epoch": 0.9611650485436893, "grad_norm": 2.98131376385244, "learning_rate": 5.304819863117796e-06, "loss": 0.2436, "step": 198 }, { "epoch": 0.9660194174757282, "grad_norm": 3.067413002199315, "learning_rate": 5.266756161615719e-06, "loss": 0.3038, "step": 199 }, { "epoch": 0.970873786407767, "grad_norm": 3.7508267167237856, "learning_rate": 5.228676949903974e-06, "loss": 0.3191, "step": 200 }, { "epoch": 0.9757281553398058, "grad_norm": 3.551674655703027, "learning_rate": 5.190584442051594e-06, "loss": 0.3213, "step": 201 }, { "epoch": 0.9805825242718447, "grad_norm": 3.4741442297689504, "learning_rate": 5.1524808529007075e-06, "loss": 0.3261, "step": 202 }, { "epoch": 0.9854368932038835, "grad_norm": 3.1977123160337, "learning_rate": 5.114368397937744e-06, "loss": 0.3034, "step": 203 }, { "epoch": 0.9902912621359223, "grad_norm": 2.749801273765845, "learning_rate": 5.07624929316463e-06, "loss": 0.2442, "step": 204 }, { "epoch": 0.9951456310679612, "grad_norm": 3.555611580765495, "learning_rate": 5.038125754969933e-06, "loss": 0.2291, "step": 205 }, { "epoch": 1.0, "grad_norm": 2.750179427306159, "learning_rate": 5e-06, "loss": 0.1469, "step": 206 }, { "epoch": 1.0048543689320388, "grad_norm": 3.6074292657758336, "learning_rate": 4.9618742450300675e-06, "loss": 0.2411, "step": 207 }, { "epoch": 1.0097087378640777, "grad_norm": 3.2982860816255175, "learning_rate": 4.923750706835371e-06, "loss": 0.2252, "step": 208 }, { "epoch": 1.0145631067961165, "grad_norm": 2.751687078673673, "learning_rate": 4.8856316020622564e-06, "loss": 0.1935, "step": 209 }, { "epoch": 1.0194174757281553, "grad_norm": 2.131324360315531, "learning_rate": 4.847519147099294e-06, "loss": 0.1307, "step": 210 }, { "epoch": 1.0242718446601942, "grad_norm": 2.9525937881413524, "learning_rate": 4.809415557948407e-06, "loss": 0.201, "step": 211 }, { "epoch": 1.029126213592233, "grad_norm": 2.800908040363257, "learning_rate": 4.771323050096028e-06, "loss": 0.1956, "step": 212 }, { "epoch": 1.0339805825242718, "grad_norm": 3.896512675233651, "learning_rate": 4.733243838384282e-06, "loss": 0.2521, "step": 213 }, { "epoch": 1.0388349514563107, "grad_norm": 3.3243568354090476, "learning_rate": 4.6951801368822055e-06, "loss": 0.1846, "step": 214 }, { "epoch": 1.0436893203883495, "grad_norm": 3.345967739972327, "learning_rate": 4.6571341587570114e-06, "loss": 0.1885, "step": 215 }, { "epoch": 1.0485436893203883, "grad_norm": 2.6990059522214787, "learning_rate": 4.619108116145411e-06, "loss": 0.2062, "step": 216 }, { "epoch": 1.0533980582524272, "grad_norm": 2.8034632634279855, "learning_rate": 4.581104220024988e-06, "loss": 0.1962, "step": 217 }, { "epoch": 1.058252427184466, "grad_norm": 3.096371883439816, "learning_rate": 4.5431246800856455e-06, "loss": 0.2176, "step": 218 }, { "epoch": 1.0631067961165048, "grad_norm": 3.234301301503053, "learning_rate": 4.505171704601128e-06, "loss": 0.1573, "step": 219 }, { "epoch": 1.0679611650485437, "grad_norm": 2.7827553596014325, "learning_rate": 4.467247500300621e-06, "loss": 0.1558, "step": 220 }, { "epoch": 1.0728155339805825, "grad_norm": 4.596075537757511, "learning_rate": 4.4293542722404435e-06, "loss": 0.1895, "step": 221 }, { "epoch": 1.0776699029126213, "grad_norm": 3.4313974912911025, "learning_rate": 4.391494223675843e-06, "loss": 0.2125, "step": 222 }, { "epoch": 1.0825242718446602, "grad_norm": 3.1698085004641663, "learning_rate": 4.3536695559328816e-06, "loss": 0.1564, "step": 223 }, { "epoch": 1.087378640776699, "grad_norm": 3.721202767416967, "learning_rate": 4.31588246828045e-06, "loss": 0.1878, "step": 224 }, { "epoch": 1.0922330097087378, "grad_norm": 2.952333401393123, "learning_rate": 4.278135157802389e-06, "loss": 0.1717, "step": 225 }, { "epoch": 1.0970873786407767, "grad_norm": 2.971294433009444, "learning_rate": 4.240429819269746e-06, "loss": 0.1363, "step": 226 }, { "epoch": 1.1019417475728155, "grad_norm": 3.126492959068957, "learning_rate": 4.20276864501316e-06, "loss": 0.1567, "step": 227 }, { "epoch": 1.1067961165048543, "grad_norm": 3.453777131016959, "learning_rate": 4.165153824795391e-06, "loss": 0.1705, "step": 228 }, { "epoch": 1.1116504854368932, "grad_norm": 2.9032949757849646, "learning_rate": 4.127587545684002e-06, "loss": 0.1557, "step": 229 }, { "epoch": 1.116504854368932, "grad_norm": 3.921098873254642, "learning_rate": 4.090071991924194e-06, "loss": 0.1543, "step": 230 }, { "epoch": 1.1213592233009708, "grad_norm": 3.270393778248402, "learning_rate": 4.052609344811802e-06, "loss": 0.159, "step": 231 }, { "epoch": 1.1262135922330097, "grad_norm": 3.1626074130907393, "learning_rate": 4.015201782566471e-06, "loss": 0.1811, "step": 232 }, { "epoch": 1.1310679611650485, "grad_norm": 3.3647207921675664, "learning_rate": 3.977851480205003e-06, "loss": 0.1842, "step": 233 }, { "epoch": 1.1359223300970873, "grad_norm": 2.8874044173439906, "learning_rate": 3.940560609414894e-06, "loss": 0.1381, "step": 234 }, { "epoch": 1.1407766990291262, "grad_norm": 3.279861092848255, "learning_rate": 3.903331338428067e-06, "loss": 0.1665, "step": 235 }, { "epoch": 1.145631067961165, "grad_norm": 3.1603391725100702, "learning_rate": 3.866165831894796e-06, "loss": 0.1401, "step": 236 }, { "epoch": 1.1504854368932038, "grad_norm": 3.392088063739412, "learning_rate": 3.829066250757851e-06, "loss": 0.1821, "step": 237 }, { "epoch": 1.1553398058252426, "grad_norm": 4.192296653671298, "learning_rate": 3.7920347521268514e-06, "loss": 0.1728, "step": 238 }, { "epoch": 1.1601941747572815, "grad_norm": 2.86078515364689, "learning_rate": 3.7550734891528413e-06, "loss": 0.1662, "step": 239 }, { "epoch": 1.1650485436893203, "grad_norm": 3.363908060650987, "learning_rate": 3.7181846109031007e-06, "loss": 0.169, "step": 240 }, { "epoch": 1.1699029126213591, "grad_norm": 2.939951981128744, "learning_rate": 3.6813702622361858e-06, "loss": 0.1335, "step": 241 }, { "epoch": 1.174757281553398, "grad_norm": 3.5426747856829905, "learning_rate": 3.6446325836772244e-06, "loss": 0.193, "step": 242 }, { "epoch": 1.1796116504854368, "grad_norm": 3.085063003996511, "learning_rate": 3.6079737112934533e-06, "loss": 0.1775, "step": 243 }, { "epoch": 1.1844660194174756, "grad_norm": 3.5078991938473894, "learning_rate": 3.5713957765700224e-06, "loss": 0.164, "step": 244 }, { "epoch": 1.1893203883495145, "grad_norm": 2.615217282840924, "learning_rate": 3.5349009062860586e-06, "loss": 0.1591, "step": 245 }, { "epoch": 1.1941747572815533, "grad_norm": 3.6803453651452793, "learning_rate": 3.4984912223910105e-06, "loss": 0.1413, "step": 246 }, { "epoch": 1.1990291262135921, "grad_norm": 3.4449942839520555, "learning_rate": 3.46216884188127e-06, "loss": 0.163, "step": 247 }, { "epoch": 1.203883495145631, "grad_norm": 2.7954187431215565, "learning_rate": 3.425935876677077e-06, "loss": 0.1653, "step": 248 }, { "epoch": 1.2087378640776698, "grad_norm": 3.3379500940316094, "learning_rate": 3.38979443349973e-06, "loss": 0.1498, "step": 249 }, { "epoch": 1.2135922330097086, "grad_norm": 3.7339988958250427, "learning_rate": 3.3537466137490937e-06, "loss": 0.1635, "step": 250 }, { "epoch": 1.2184466019417475, "grad_norm": 3.1712814085947807, "learning_rate": 3.3177945133814093e-06, "loss": 0.2052, "step": 251 }, { "epoch": 1.2233009708737863, "grad_norm": 3.785681030228593, "learning_rate": 3.2819402227874364e-06, "loss": 0.1841, "step": 252 }, { "epoch": 1.2281553398058254, "grad_norm": 3.380080489299224, "learning_rate": 3.2461858266709017e-06, "loss": 0.2052, "step": 253 }, { "epoch": 1.233009708737864, "grad_norm": 2.5462863024797766, "learning_rate": 3.2105334039272924e-06, "loss": 0.1693, "step": 254 }, { "epoch": 1.237864077669903, "grad_norm": 2.751706147069006, "learning_rate": 3.1749850275229777e-06, "loss": 0.1716, "step": 255 }, { "epoch": 1.2427184466019416, "grad_norm": 2.9259614329694346, "learning_rate": 3.1395427643746802e-06, "loss": 0.1665, "step": 256 }, { "epoch": 1.2475728155339807, "grad_norm": 2.9294906505296137, "learning_rate": 3.1042086752292995e-06, "loss": 0.1389, "step": 257 }, { "epoch": 1.2524271844660193, "grad_norm": 3.3865475928641207, "learning_rate": 3.068984814544087e-06, "loss": 0.2233, "step": 258 }, { "epoch": 1.2572815533980584, "grad_norm": 3.725741013397862, "learning_rate": 3.0338732303671993e-06, "loss": 0.1465, "step": 259 }, { "epoch": 1.262135922330097, "grad_norm": 3.0795015825477137, "learning_rate": 2.99887596421861e-06, "loss": 0.1747, "step": 260 }, { "epoch": 1.266990291262136, "grad_norm": 3.611562608462532, "learning_rate": 2.9639950509714138e-06, "loss": 0.1867, "step": 261 }, { "epoch": 1.2718446601941746, "grad_norm": 3.084400701369303, "learning_rate": 2.929232518733507e-06, "loss": 0.2018, "step": 262 }, { "epoch": 1.2766990291262137, "grad_norm": 3.1946687798944713, "learning_rate": 2.8945903887296686e-06, "loss": 0.1715, "step": 263 }, { "epoch": 1.2815533980582523, "grad_norm": 3.5486237317517695, "learning_rate": 2.860070675184036e-06, "loss": 0.1851, "step": 264 }, { "epoch": 1.2864077669902914, "grad_norm": 3.501162227913844, "learning_rate": 2.8256753852029917e-06, "loss": 0.181, "step": 265 }, { "epoch": 1.29126213592233, "grad_norm": 3.6998358923196752, "learning_rate": 2.7914065186584637e-06, "loss": 0.1855, "step": 266 }, { "epoch": 1.296116504854369, "grad_norm": 3.533496753991655, "learning_rate": 2.757266068071648e-06, "loss": 0.1686, "step": 267 }, { "epoch": 1.3009708737864076, "grad_norm": 4.0820367314540364, "learning_rate": 2.7232560184971437e-06, "loss": 0.2041, "step": 268 }, { "epoch": 1.3058252427184467, "grad_norm": 2.9637906965920973, "learning_rate": 2.689378347407553e-06, "loss": 0.1769, "step": 269 }, { "epoch": 1.3106796116504853, "grad_norm": 3.28408303596329, "learning_rate": 2.6556350245784833e-06, "loss": 0.1478, "step": 270 }, { "epoch": 1.3155339805825244, "grad_norm": 3.4932538693112005, "learning_rate": 2.6220280119740376e-06, "loss": 0.1784, "step": 271 }, { "epoch": 1.3203883495145632, "grad_norm": 2.9444515487006915, "learning_rate": 2.588559263632719e-06, "loss": 0.1742, "step": 272 }, { "epoch": 1.325242718446602, "grad_norm": 3.485379112038064, "learning_rate": 2.555230725553832e-06, "loss": 0.1452, "step": 273 }, { "epoch": 1.3300970873786409, "grad_norm": 3.9882951570278484, "learning_rate": 2.522044335584322e-06, "loss": 0.2052, "step": 274 }, { "epoch": 1.3349514563106797, "grad_norm": 4.110332411155784, "learning_rate": 2.489002023306112e-06, "loss": 0.2437, "step": 275 }, { "epoch": 1.3398058252427185, "grad_norm": 3.0399564213447783, "learning_rate": 2.4561057099238973e-06, "loss": 0.1818, "step": 276 }, { "epoch": 1.3446601941747574, "grad_norm": 4.446329888375363, "learning_rate": 2.423357308153454e-06, "loss": 0.204, "step": 277 }, { "epoch": 1.3495145631067962, "grad_norm": 2.748301776472504, "learning_rate": 2.390758722110418e-06, "loss": 0.1495, "step": 278 }, { "epoch": 1.354368932038835, "grad_norm": 3.1032791062681646, "learning_rate": 2.358311847199567e-06, "loss": 0.1958, "step": 279 }, { "epoch": 1.3592233009708738, "grad_norm": 2.9234204018047594, "learning_rate": 2.3260185700046295e-06, "loss": 0.1332, "step": 280 }, { "epoch": 1.3640776699029127, "grad_norm": 2.8010316743774832, "learning_rate": 2.2938807681785764e-06, "loss": 0.1638, "step": 281 }, { "epoch": 1.3689320388349515, "grad_norm": 3.1777341991793406, "learning_rate": 2.2619003103344607e-06, "loss": 0.1726, "step": 282 }, { "epoch": 1.3737864077669903, "grad_norm": 3.3059600212196347, "learning_rate": 2.2300790559367553e-06, "loss": 0.1628, "step": 283 }, { "epoch": 1.3786407766990292, "grad_norm": 3.0674105340701687, "learning_rate": 2.1984188551932513e-06, "loss": 0.1453, "step": 284 }, { "epoch": 1.383495145631068, "grad_norm": 3.9514680456604148, "learning_rate": 2.166921548947466e-06, "loss": 0.2181, "step": 285 }, { "epoch": 1.3883495145631068, "grad_norm": 2.9964673443034773, "learning_rate": 2.1355889685716225e-06, "loss": 0.1539, "step": 286 }, { "epoch": 1.3932038834951457, "grad_norm": 3.1345212878687363, "learning_rate": 2.1044229358601543e-06, "loss": 0.1716, "step": 287 }, { "epoch": 1.3980582524271845, "grad_norm": 3.072100411386996, "learning_rate": 2.0734252629237892e-06, "loss": 0.155, "step": 288 }, { "epoch": 1.4029126213592233, "grad_norm": 3.12310671799428, "learning_rate": 2.0425977520841837e-06, "loss": 0.1471, "step": 289 }, { "epoch": 1.4077669902912622, "grad_norm": 2.9614677816599273, "learning_rate": 2.011942195769122e-06, "loss": 0.154, "step": 290 }, { "epoch": 1.412621359223301, "grad_norm": 2.711481098825533, "learning_rate": 1.9814603764083112e-06, "loss": 0.1469, "step": 291 }, { "epoch": 1.4174757281553398, "grad_norm": 3.6914419930416904, "learning_rate": 1.9511540663297284e-06, "loss": 0.1843, "step": 292 }, { "epoch": 1.4223300970873787, "grad_norm": 2.715597600156834, "learning_rate": 1.921025027656587e-06, "loss": 0.1454, "step": 293 }, { "epoch": 1.4271844660194175, "grad_norm": 3.342565246233355, "learning_rate": 1.8910750122048638e-06, "loss": 0.1728, "step": 294 }, { "epoch": 1.4320388349514563, "grad_norm": 3.1790483488750163, "learning_rate": 1.8613057613814584e-06, "loss": 0.1501, "step": 295 }, { "epoch": 1.4368932038834952, "grad_norm": 2.9576338390873245, "learning_rate": 1.8317190060829242e-06, "loss": 0.1574, "step": 296 }, { "epoch": 1.441747572815534, "grad_norm": 3.193861736304933, "learning_rate": 1.8023164665948455e-06, "loss": 0.1804, "step": 297 }, { "epoch": 1.4466019417475728, "grad_norm": 3.4043347296850635, "learning_rate": 1.773099852491796e-06, "loss": 0.1843, "step": 298 }, { "epoch": 1.4514563106796117, "grad_norm": 2.9147696115237043, "learning_rate": 1.7440708625379503e-06, "loss": 0.1448, "step": 299 }, { "epoch": 1.4563106796116505, "grad_norm": 3.67343773463864, "learning_rate": 1.7152311845883096e-06, "loss": 0.1968, "step": 300 }, { "epoch": 1.4611650485436893, "grad_norm": 3.2061340304430224, "learning_rate": 1.686582495490554e-06, "loss": 0.2155, "step": 301 }, { "epoch": 1.4660194174757282, "grad_norm": 3.1289793948282103, "learning_rate": 1.658126460987558e-06, "loss": 0.1748, "step": 302 }, { "epoch": 1.470873786407767, "grad_norm": 3.4296643260484427, "learning_rate": 1.6298647356205255e-06, "loss": 0.1805, "step": 303 }, { "epoch": 1.4757281553398058, "grad_norm": 2.6569119305504505, "learning_rate": 1.601798962632799e-06, "loss": 0.16, "step": 304 }, { "epoch": 1.4805825242718447, "grad_norm": 3.737755757012023, "learning_rate": 1.573930773874306e-06, "loss": 0.1898, "step": 305 }, { "epoch": 1.4854368932038835, "grad_norm": 3.285818119573095, "learning_rate": 1.5462617897066863e-06, "loss": 0.1655, "step": 306 }, { "epoch": 1.4902912621359223, "grad_norm": 2.5935396134988675, "learning_rate": 1.5187936189090668e-06, "loss": 0.1618, "step": 307 }, { "epoch": 1.4951456310679612, "grad_norm": 3.3197078655403596, "learning_rate": 1.491527858584535e-06, "loss": 0.1826, "step": 308 }, { "epoch": 1.5, "grad_norm": 2.805570770413659, "learning_rate": 1.4644660940672628e-06, "loss": 0.1652, "step": 309 }, { "epoch": 1.5048543689320388, "grad_norm": 3.87545230747002, "learning_rate": 1.4376098988303406e-06, "loss": 0.1326, "step": 310 }, { "epoch": 1.5097087378640777, "grad_norm": 2.97370482259783, "learning_rate": 1.4109608343942855e-06, "loss": 0.1612, "step": 311 }, { "epoch": 1.5145631067961165, "grad_norm": 2.923170481056903, "learning_rate": 1.3845204502362442e-06, "loss": 0.1735, "step": 312 }, { "epoch": 1.5194174757281553, "grad_norm": 3.755722029546262, "learning_rate": 1.35829028369991e-06, "loss": 0.1738, "step": 313 }, { "epoch": 1.5242718446601942, "grad_norm": 3.073418135837225, "learning_rate": 1.3322718599061252e-06, "loss": 0.1626, "step": 314 }, { "epoch": 1.529126213592233, "grad_norm": 3.3545932991866856, "learning_rate": 1.306466691664216e-06, "loss": 0.1852, "step": 315 }, { "epoch": 1.5339805825242718, "grad_norm": 3.0420631745569264, "learning_rate": 1.28087627938402e-06, "loss": 0.2058, "step": 316 }, { "epoch": 1.5388349514563107, "grad_norm": 3.288084006190745, "learning_rate": 1.2555021109886589e-06, "loss": 0.1782, "step": 317 }, { "epoch": 1.5436893203883495, "grad_norm": 3.4669766167403604, "learning_rate": 1.2303456618280141e-06, "loss": 0.1534, "step": 318 }, { "epoch": 1.5485436893203883, "grad_norm": 2.8546758802857943, "learning_rate": 1.2054083945929534e-06, "loss": 0.1504, "step": 319 }, { "epoch": 1.5533980582524272, "grad_norm": 2.5744717120278082, "learning_rate": 1.1806917592302763e-06, "loss": 0.1528, "step": 320 }, { "epoch": 1.558252427184466, "grad_norm": 3.307605123935886, "learning_rate": 1.1561971928584158e-06, "loss": 0.1587, "step": 321 }, { "epoch": 1.5631067961165048, "grad_norm": 3.1062458626679987, "learning_rate": 1.1319261196838782e-06, "loss": 0.1916, "step": 322 }, { "epoch": 1.5679611650485437, "grad_norm": 3.806330561607627, "learning_rate": 1.1078799509184246e-06, "loss": 0.1676, "step": 323 }, { "epoch": 1.5728155339805825, "grad_norm": 3.701532006854811, "learning_rate": 1.0840600846970333e-06, "loss": 0.2029, "step": 324 }, { "epoch": 1.5776699029126213, "grad_norm": 3.1259651978100718, "learning_rate": 1.0604679059965923e-06, "loss": 0.2124, "step": 325 }, { "epoch": 1.5825242718446602, "grad_norm": 3.22550450415583, "learning_rate": 1.0371047865553847e-06, "loss": 0.1994, "step": 326 }, { "epoch": 1.587378640776699, "grad_norm": 3.2766712984535236, "learning_rate": 1.0139720847933166e-06, "loss": 0.197, "step": 327 }, { "epoch": 1.5922330097087378, "grad_norm": 3.7019747182049834, "learning_rate": 9.91071145732948e-07, "loss": 0.175, "step": 328 }, { "epoch": 1.5970873786407767, "grad_norm": 3.794491022818783, "learning_rate": 9.684033009212752e-07, "loss": 0.2009, "step": 329 }, { "epoch": 1.6019417475728155, "grad_norm": 3.428558902601033, "learning_rate": 9.459698683523205e-07, "loss": 0.189, "step": 330 }, { "epoch": 1.6067961165048543, "grad_norm": 3.744875862238987, "learning_rate": 9.237721523904891e-07, "loss": 0.2289, "step": 331 }, { "epoch": 1.6116504854368932, "grad_norm": 2.4674345418991823, "learning_rate": 9.018114436947373e-07, "loss": 0.1579, "step": 332 }, { "epoch": 1.616504854368932, "grad_norm": 3.058578338654439, "learning_rate": 8.80089019143524e-07, "loss": 0.1542, "step": 333 }, { "epoch": 1.6213592233009708, "grad_norm": 2.825721990993473, "learning_rate": 8.586061417605668e-07, "loss": 0.1411, "step": 334 }, { "epoch": 1.6262135922330097, "grad_norm": 3.450065248410591, "learning_rate": 8.373640606414097e-07, "loss": 0.1621, "step": 335 }, { "epoch": 1.6310679611650487, "grad_norm": 3.6691308256662456, "learning_rate": 8.163640108807897e-07, "loss": 0.2316, "step": 336 }, { "epoch": 1.6359223300970873, "grad_norm": 2.9947021116141754, "learning_rate": 7.956072135008336e-07, "loss": 0.1574, "step": 337 }, { "epoch": 1.6407766990291264, "grad_norm": 3.278695868417599, "learning_rate": 7.750948753800508e-07, "loss": 0.1481, "step": 338 }, { "epoch": 1.645631067961165, "grad_norm": 3.703013731780411, "learning_rate": 7.548281891831715e-07, "loss": 0.203, "step": 339 }, { "epoch": 1.650485436893204, "grad_norm": 3.3722154741779953, "learning_rate": 7.348083332917927e-07, "loss": 0.1677, "step": 340 }, { "epoch": 1.6553398058252426, "grad_norm": 5.7178253424321746, "learning_rate": 7.150364717358699e-07, "loss": 0.1978, "step": 341 }, { "epoch": 1.6601941747572817, "grad_norm": 2.9025833998160206, "learning_rate": 6.955137541260287e-07, "loss": 0.1671, "step": 342 }, { "epoch": 1.6650485436893203, "grad_norm": 3.2608625687251656, "learning_rate": 6.762413155867276e-07, "loss": 0.1748, "step": 343 }, { "epoch": 1.6699029126213594, "grad_norm": 3.810077269631539, "learning_rate": 6.572202766902569e-07, "loss": 0.2342, "step": 344 }, { "epoch": 1.674757281553398, "grad_norm": 3.119269749383546, "learning_rate": 6.384517433915794e-07, "loss": 0.1598, "step": 345 }, { "epoch": 1.679611650485437, "grad_norm": 2.9692473587980013, "learning_rate": 6.199368069640343e-07, "loss": 0.1663, "step": 346 }, { "epoch": 1.6844660194174756, "grad_norm": 3.41232556605209, "learning_rate": 6.016765439358774e-07, "loss": 0.2109, "step": 347 }, { "epoch": 1.6893203883495147, "grad_norm": 2.970773165693587, "learning_rate": 5.836720160276971e-07, "loss": 0.183, "step": 348 }, { "epoch": 1.6941747572815533, "grad_norm": 3.1209834435239054, "learning_rate": 5.659242700906719e-07, "loss": 0.1703, "step": 349 }, { "epoch": 1.6990291262135924, "grad_norm": 2.706946357159076, "learning_rate": 5.484343380457124e-07, "loss": 0.1603, "step": 350 }, { "epoch": 1.703883495145631, "grad_norm": 3.085681096910252, "learning_rate": 5.312032368234527e-07, "loss": 0.1809, "step": 351 }, { "epoch": 1.70873786407767, "grad_norm": 3.0908332326767227, "learning_rate": 5.1423196830513e-07, "loss": 0.183, "step": 352 }, { "epoch": 1.7135922330097086, "grad_norm": 3.0274657389189654, "learning_rate": 4.975215192643246e-07, "loss": 0.1634, "step": 353 }, { "epoch": 1.7184466019417477, "grad_norm": 2.5910174115174067, "learning_rate": 4.81072861309591e-07, "loss": 0.1224, "step": 354 }, { "epoch": 1.7233009708737863, "grad_norm": 2.823969566040542, "learning_rate": 4.648869508279613e-07, "loss": 0.157, "step": 355 }, { "epoch": 1.7281553398058254, "grad_norm": 2.9595443993378625, "learning_rate": 4.4896472892933693e-07, "loss": 0.1448, "step": 356 }, { "epoch": 1.733009708737864, "grad_norm": 2.9674587181707066, "learning_rate": 4.333071213917722e-07, "loss": 0.1561, "step": 357 }, { "epoch": 1.737864077669903, "grad_norm": 2.971975487243502, "learning_rate": 4.179150386076425e-07, "loss": 0.1807, "step": 358 }, { "epoch": 1.7427184466019416, "grad_norm": 3.5592330828269465, "learning_rate": 4.027893755307144e-07, "loss": 0.1957, "step": 359 }, { "epoch": 1.7475728155339807, "grad_norm": 3.4457487102374276, "learning_rate": 3.8793101162410417e-07, "loss": 0.1815, "step": 360 }, { "epoch": 1.7524271844660193, "grad_norm": 3.134881639795192, "learning_rate": 3.733408108091485e-07, "loss": 0.1673, "step": 361 }, { "epoch": 1.7572815533980584, "grad_norm": 3.678352034117385, "learning_rate": 3.5901962141516975e-07, "loss": 0.1868, "step": 362 }, { "epoch": 1.762135922330097, "grad_norm": 3.122016578093726, "learning_rate": 3.4496827613015206e-07, "loss": 0.1693, "step": 363 }, { "epoch": 1.766990291262136, "grad_norm": 3.058903089372746, "learning_rate": 3.3118759195232273e-07, "loss": 0.1581, "step": 364 }, { "epoch": 1.7718446601941746, "grad_norm": 3.59995245371114, "learning_rate": 3.176783701426528e-07, "loss": 0.2394, "step": 365 }, { "epoch": 1.7766990291262137, "grad_norm": 3.459079793100832, "learning_rate": 3.0444139617826605e-07, "loss": 0.1932, "step": 366 }, { "epoch": 1.7815533980582523, "grad_norm": 3.7129334593953818, "learning_rate": 2.91477439706771e-07, "loss": 0.2044, "step": 367 }, { "epoch": 1.7864077669902914, "grad_norm": 3.604631619699467, "learning_rate": 2.787872545015069e-07, "loss": 0.1796, "step": 368 }, { "epoch": 1.79126213592233, "grad_norm": 3.160625540613814, "learning_rate": 2.663715784177201e-07, "loss": 0.1859, "step": 369 }, { "epoch": 1.796116504854369, "grad_norm": 3.330868483974817, "learning_rate": 2.542311333496622e-07, "loss": 0.1366, "step": 370 }, { "epoch": 1.8009708737864076, "grad_norm": 3.312629290688821, "learning_rate": 2.423666251886114e-07, "loss": 0.1682, "step": 371 }, { "epoch": 1.8058252427184467, "grad_norm": 3.2912055141193104, "learning_rate": 2.307787437818365e-07, "loss": 0.1658, "step": 372 }, { "epoch": 1.8106796116504853, "grad_norm": 3.813237415315296, "learning_rate": 2.1946816289248163e-07, "loss": 0.1761, "step": 373 }, { "epoch": 1.8155339805825244, "grad_norm": 3.46072257123938, "learning_rate": 2.0843554016039326e-07, "loss": 0.1773, "step": 374 }, { "epoch": 1.820388349514563, "grad_norm": 3.1090270180019077, "learning_rate": 1.9768151706388016e-07, "loss": 0.156, "step": 375 }, { "epoch": 1.825242718446602, "grad_norm": 3.7606812831013468, "learning_rate": 1.8720671888242058e-07, "loss": 0.1659, "step": 376 }, { "epoch": 1.8300970873786406, "grad_norm": 3.630180348742183, "learning_rate": 1.7701175466029895e-07, "loss": 0.2017, "step": 377 }, { "epoch": 1.8349514563106797, "grad_norm": 3.548564346588287, "learning_rate": 1.6709721717120042e-07, "loss": 0.2736, "step": 378 }, { "epoch": 1.8398058252427183, "grad_norm": 2.58820624396961, "learning_rate": 1.574636828837395e-07, "loss": 0.1636, "step": 379 }, { "epoch": 1.8446601941747574, "grad_norm": 3.2009268622796507, "learning_rate": 1.4811171192794628e-07, "loss": 0.1477, "step": 380 }, { "epoch": 1.849514563106796, "grad_norm": 3.668850842502455, "learning_rate": 1.3904184806269705e-07, "loss": 0.208, "step": 381 }, { "epoch": 1.854368932038835, "grad_norm": 2.8566670252001605, "learning_rate": 1.3025461864409395e-07, "loss": 0.1333, "step": 382 }, { "epoch": 1.8592233009708736, "grad_norm": 3.769624398617395, "learning_rate": 1.2175053459481e-07, "loss": 0.2162, "step": 383 }, { "epoch": 1.8640776699029127, "grad_norm": 3.5203837282760717, "learning_rate": 1.1353009037437523e-07, "loss": 0.1783, "step": 384 }, { "epoch": 1.8689320388349513, "grad_norm": 3.0533590437151257, "learning_rate": 1.0559376395043285e-07, "loss": 0.1636, "step": 385 }, { "epoch": 1.8737864077669903, "grad_norm": 3.244251275203498, "learning_rate": 9.794201677094162e-08, "loss": 0.1659, "step": 386 }, { "epoch": 1.8786407766990292, "grad_norm": 3.5161837604256796, "learning_rate": 9.05752937373533e-08, "loss": 0.1707, "step": 387 }, { "epoch": 1.883495145631068, "grad_norm": 2.8369908420705965, "learning_rate": 8.34940231787379e-08, "loss": 0.1493, "step": 388 }, { "epoch": 1.8883495145631068, "grad_norm": 2.9716609378210834, "learning_rate": 7.66986168268824e-08, "loss": 0.1417, "step": 389 }, { "epoch": 1.8932038834951457, "grad_norm": 3.542879526364103, "learning_rate": 7.018946979234997e-08, "loss": 0.2002, "step": 390 }, { "epoch": 1.8980582524271845, "grad_norm": 3.0956905601973057, "learning_rate": 6.396696054150719e-08, "loss": 0.1513, "step": 391 }, { "epoch": 1.9029126213592233, "grad_norm": 3.4395097945742426, "learning_rate": 5.803145087451945e-08, "loss": 0.1856, "step": 392 }, { "epoch": 1.9077669902912622, "grad_norm": 3.5337908722933937, "learning_rate": 5.238328590431163e-08, "loss": 0.1943, "step": 393 }, { "epoch": 1.912621359223301, "grad_norm": 2.7737787495552304, "learning_rate": 4.702279403650534e-08, "loss": 0.1496, "step": 394 }, { "epoch": 1.9174757281553398, "grad_norm": 3.8937710005570234, "learning_rate": 4.195028695032133e-08, "loss": 0.2289, "step": 395 }, { "epoch": 1.9223300970873787, "grad_norm": 3.3826066398740853, "learning_rate": 3.716605958046071e-08, "loss": 0.179, "step": 396 }, { "epoch": 1.9271844660194175, "grad_norm": 3.3574202573717886, "learning_rate": 3.2670390099951985e-08, "loss": 0.1842, "step": 397 }, { "epoch": 1.9320388349514563, "grad_norm": 3.4211377835157464, "learning_rate": 2.846353990398065e-08, "loss": 0.1794, "step": 398 }, { "epoch": 1.9368932038834952, "grad_norm": 3.2237719120411232, "learning_rate": 2.4545753594688582e-08, "loss": 0.1531, "step": 399 }, { "epoch": 1.941747572815534, "grad_norm": 3.6660882822246132, "learning_rate": 2.0917258966953735e-08, "loss": 0.1851, "step": 400 }, { "epoch": 1.9466019417475728, "grad_norm": 3.384308263205741, "learning_rate": 1.757826699514298e-08, "loss": 0.2262, "step": 401 }, { "epoch": 1.9514563106796117, "grad_norm": 3.0941560464813507, "learning_rate": 1.4528971820846894e-08, "loss": 0.1645, "step": 402 }, { "epoch": 1.9563106796116505, "grad_norm": 2.8371139141201667, "learning_rate": 1.176955074159214e-08, "loss": 0.1382, "step": 403 }, { "epoch": 1.9611650485436893, "grad_norm": 3.2651439167859735, "learning_rate": 9.300164200530815e-09, "loss": 0.1556, "step": 404 }, { "epoch": 1.9660194174757282, "grad_norm": 3.223736788971525, "learning_rate": 7.120955777112915e-09, "loss": 0.1552, "step": 405 }, { "epoch": 1.970873786407767, "grad_norm": 3.297969705359936, "learning_rate": 5.232052178738567e-09, "loss": 0.1517, "step": 406 }, { "epoch": 1.9757281553398058, "grad_norm": 3.3209447677111235, "learning_rate": 3.633563233388926e-09, "loss": 0.1755, "step": 407 }, { "epoch": 1.9805825242718447, "grad_norm": 3.5781779376616685, "learning_rate": 2.3255818832423894e-09, "loss": 0.1723, "step": 408 }, { "epoch": 1.9854368932038835, "grad_norm": 3.17071653312937, "learning_rate": 1.3081841792694783e-09, "loss": 0.1544, "step": 409 }, { "epoch": 1.9902912621359223, "grad_norm": 3.3777328087738194, "learning_rate": 5.814292768108187e-10, "loss": 0.1555, "step": 410 }, { "epoch": 1.9951456310679612, "grad_norm": 3.2676077636224314, "learning_rate": 1.453594321393359e-10, "loss": 0.178, "step": 411 }, { "epoch": 2.0, "grad_norm": 2.731489227558426, "learning_rate": 0.0, "loss": 0.1683, "step": 412 }, { "epoch": 2.0, "step": 412, "total_flos": 956555218944.0, "train_loss": 0.23991625754216922, "train_runtime": 257.1054, "train_samples_per_second": 12.765, "train_steps_per_second": 1.602 } ], "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": 956555218944.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }