{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.998480850723595, "eval_steps": 500, "global_step": 4689, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0006396418005916686, "grad_norm": 115.30694580078125, "learning_rate": 5e-06, "loss": 6.4114, "step": 1 }, { "epoch": 0.0012792836011833373, "grad_norm": 109.575439453125, "learning_rate": 1e-05, "loss": 5.8471, "step": 2 }, { "epoch": 0.001918925401775006, "grad_norm": 64.81423950195312, "learning_rate": 1.5e-05, "loss": 4.3482, "step": 3 }, { "epoch": 0.0025585672023666745, "grad_norm": 37.4569206237793, "learning_rate": 2e-05, "loss": 3.6161, "step": 4 }, { "epoch": 0.0031982090029583432, "grad_norm": 29.528892517089844, "learning_rate": 2.5e-05, "loss": 2.6967, "step": 5 }, { "epoch": 0.003837850803550012, "grad_norm": 25.729040145874023, "learning_rate": 3e-05, "loss": 2.6412, "step": 6 }, { "epoch": 0.004477492604141681, "grad_norm": 21.95215606689453, "learning_rate": 3.5e-05, "loss": 2.2728, "step": 7 }, { "epoch": 0.005117134404733349, "grad_norm": 17.429595947265625, "learning_rate": 4e-05, "loss": 1.8068, "step": 8 }, { "epoch": 0.005756776205325018, "grad_norm": 13.558813095092773, "learning_rate": 4.5e-05, "loss": 1.7164, "step": 9 }, { "epoch": 0.0063964180059166865, "grad_norm": 8.956698417663574, "learning_rate": 5e-05, "loss": 1.3478, "step": 10 }, { "epoch": 0.007036059806508356, "grad_norm": 11.52576732635498, "learning_rate": 4.99893139559735e-05, "loss": 1.3521, "step": 11 }, { "epoch": 0.007675701607100024, "grad_norm": 7.028160572052002, "learning_rate": 4.9978627911947e-05, "loss": 1.3142, "step": 12 }, { "epoch": 0.008315343407691692, "grad_norm": 5.472947120666504, "learning_rate": 4.99679418679205e-05, "loss": 1.2399, "step": 13 }, { "epoch": 0.008954985208283361, "grad_norm": 5.520193099975586, "learning_rate": 4.995725582389399e-05, "loss": 1.3414, "step": 14 }, { "epoch": 0.00959462700887503, "grad_norm": 5.163415908813477, "learning_rate": 4.99465697798675e-05, "loss": 1.2096, "step": 15 }, { "epoch": 0.010234268809466698, "grad_norm": 4.520339488983154, "learning_rate": 4.993588373584099e-05, "loss": 1.0653, "step": 16 }, { "epoch": 0.010873910610058367, "grad_norm": 4.235777378082275, "learning_rate": 4.992519769181449e-05, "loss": 1.0698, "step": 17 }, { "epoch": 0.011513552410650036, "grad_norm": 4.275694370269775, "learning_rate": 4.991451164778799e-05, "loss": 1.013, "step": 18 }, { "epoch": 0.012153194211241704, "grad_norm": 4.225165843963623, "learning_rate": 4.990382560376149e-05, "loss": 1.0674, "step": 19 }, { "epoch": 0.012792836011833373, "grad_norm": 4.273852348327637, "learning_rate": 4.989313955973499e-05, "loss": 0.9873, "step": 20 }, { "epoch": 0.013432477812425042, "grad_norm": 4.532805442810059, "learning_rate": 4.988245351570849e-05, "loss": 1.0973, "step": 21 }, { "epoch": 0.014072119613016711, "grad_norm": 4.303666114807129, "learning_rate": 4.987176747168199e-05, "loss": 1.1173, "step": 22 }, { "epoch": 0.014711761413608379, "grad_norm": 4.099974632263184, "learning_rate": 4.986108142765548e-05, "loss": 1.0408, "step": 23 }, { "epoch": 0.015351403214200048, "grad_norm": 3.9215502738952637, "learning_rate": 4.985039538362899e-05, "loss": 0.9867, "step": 24 }, { "epoch": 0.015991045014791715, "grad_norm": 3.848891019821167, "learning_rate": 4.983970933960248e-05, "loss": 1.0161, "step": 25 }, { "epoch": 0.016630686815383385, "grad_norm": 4.045166969299316, "learning_rate": 4.9829023295575985e-05, "loss": 1.1399, "step": 26 }, { "epoch": 0.017270328615975054, "grad_norm": 3.542635917663574, "learning_rate": 4.981833725154948e-05, "loss": 0.8839, "step": 27 }, { "epoch": 0.017909970416566723, "grad_norm": 3.7698657512664795, "learning_rate": 4.980765120752298e-05, "loss": 0.9537, "step": 28 }, { "epoch": 0.018549612217158392, "grad_norm": 4.563840389251709, "learning_rate": 4.979696516349648e-05, "loss": 1.116, "step": 29 }, { "epoch": 0.01918925401775006, "grad_norm": 3.640054225921631, "learning_rate": 4.9786279119469976e-05, "loss": 0.9602, "step": 30 }, { "epoch": 0.01982889581834173, "grad_norm": 3.8122613430023193, "learning_rate": 4.977559307544347e-05, "loss": 0.9392, "step": 31 }, { "epoch": 0.020468537618933396, "grad_norm": 3.983224391937256, "learning_rate": 4.9764907031416975e-05, "loss": 1.0715, "step": 32 }, { "epoch": 0.021108179419525065, "grad_norm": 3.8251636028289795, "learning_rate": 4.975422098739047e-05, "loss": 1.0091, "step": 33 }, { "epoch": 0.021747821220116734, "grad_norm": 3.240780830383301, "learning_rate": 4.974353494336397e-05, "loss": 0.8361, "step": 34 }, { "epoch": 0.022387463020708404, "grad_norm": 4.041069984436035, "learning_rate": 4.973284889933747e-05, "loss": 1.0791, "step": 35 }, { "epoch": 0.023027104821300073, "grad_norm": 3.640153408050537, "learning_rate": 4.9722162855310965e-05, "loss": 0.9687, "step": 36 }, { "epoch": 0.023666746621891742, "grad_norm": 3.730983018875122, "learning_rate": 4.9711476811284465e-05, "loss": 0.9859, "step": 37 }, { "epoch": 0.024306388422483408, "grad_norm": 3.9427647590637207, "learning_rate": 4.9700790767257964e-05, "loss": 1.0425, "step": 38 }, { "epoch": 0.024946030223075077, "grad_norm": 4.326479911804199, "learning_rate": 4.9690104723231464e-05, "loss": 1.0436, "step": 39 }, { "epoch": 0.025585672023666746, "grad_norm": 3.6924359798431396, "learning_rate": 4.9679418679204956e-05, "loss": 0.9543, "step": 40 }, { "epoch": 0.026225313824258415, "grad_norm": 3.9280359745025635, "learning_rate": 4.966873263517846e-05, "loss": 1.0221, "step": 41 }, { "epoch": 0.026864955624850084, "grad_norm": 3.4215242862701416, "learning_rate": 4.9658046591151955e-05, "loss": 0.8821, "step": 42 }, { "epoch": 0.027504597425441753, "grad_norm": 3.314079523086548, "learning_rate": 4.9647360547125454e-05, "loss": 0.9022, "step": 43 }, { "epoch": 0.028144239226033423, "grad_norm": 3.8960483074188232, "learning_rate": 4.9636674503098954e-05, "loss": 1.0886, "step": 44 }, { "epoch": 0.02878388102662509, "grad_norm": 3.6893134117126465, "learning_rate": 4.962598845907245e-05, "loss": 1.0148, "step": 45 }, { "epoch": 0.029423522827216757, "grad_norm": 3.6006226539611816, "learning_rate": 4.961530241504595e-05, "loss": 0.9509, "step": 46 }, { "epoch": 0.030063164627808427, "grad_norm": 3.676569938659668, "learning_rate": 4.960461637101945e-05, "loss": 0.9786, "step": 47 }, { "epoch": 0.030702806428400096, "grad_norm": 3.2735321521759033, "learning_rate": 4.959393032699295e-05, "loss": 0.9687, "step": 48 }, { "epoch": 0.031342448228991765, "grad_norm": 3.3601109981536865, "learning_rate": 4.9583244282966444e-05, "loss": 0.9033, "step": 49 }, { "epoch": 0.03198209002958343, "grad_norm": 3.4429924488067627, "learning_rate": 4.957255823893995e-05, "loss": 0.9358, "step": 50 }, { "epoch": 0.0326217318301751, "grad_norm": 3.9405481815338135, "learning_rate": 4.956187219491344e-05, "loss": 0.8988, "step": 51 }, { "epoch": 0.03326137363076677, "grad_norm": 3.5133135318756104, "learning_rate": 4.955118615088694e-05, "loss": 0.9658, "step": 52 }, { "epoch": 0.03390101543135844, "grad_norm": 3.6065900325775146, "learning_rate": 4.954050010686044e-05, "loss": 0.93, "step": 53 }, { "epoch": 0.03454065723195011, "grad_norm": 3.22421932220459, "learning_rate": 4.952981406283394e-05, "loss": 0.8686, "step": 54 }, { "epoch": 0.03518029903254178, "grad_norm": 3.5975608825683594, "learning_rate": 4.951912801880744e-05, "loss": 0.9983, "step": 55 }, { "epoch": 0.035819940833133446, "grad_norm": 3.5553078651428223, "learning_rate": 4.950844197478094e-05, "loss": 0.9925, "step": 56 }, { "epoch": 0.03645958263372511, "grad_norm": 3.6313040256500244, "learning_rate": 4.949775593075444e-05, "loss": 0.9489, "step": 57 }, { "epoch": 0.037099224434316784, "grad_norm": 3.73193621635437, "learning_rate": 4.948706988672794e-05, "loss": 0.8969, "step": 58 }, { "epoch": 0.03773886623490845, "grad_norm": 3.727299213409424, "learning_rate": 4.947638384270144e-05, "loss": 0.9545, "step": 59 }, { "epoch": 0.03837850803550012, "grad_norm": 3.72043776512146, "learning_rate": 4.946569779867493e-05, "loss": 1.0084, "step": 60 }, { "epoch": 0.03901814983609179, "grad_norm": 3.5858588218688965, "learning_rate": 4.9455011754648436e-05, "loss": 1.0442, "step": 61 }, { "epoch": 0.03965779163668346, "grad_norm": 3.367790699005127, "learning_rate": 4.944432571062193e-05, "loss": 0.9894, "step": 62 }, { "epoch": 0.040297433437275126, "grad_norm": 3.3638293743133545, "learning_rate": 4.943363966659543e-05, "loss": 1.055, "step": 63 }, { "epoch": 0.04093707523786679, "grad_norm": 3.0173652172088623, "learning_rate": 4.942295362256893e-05, "loss": 0.9459, "step": 64 }, { "epoch": 0.041576717038458465, "grad_norm": 3.372331380844116, "learning_rate": 4.941226757854243e-05, "loss": 0.9825, "step": 65 }, { "epoch": 0.04221635883905013, "grad_norm": 3.7092132568359375, "learning_rate": 4.9401581534515926e-05, "loss": 1.0245, "step": 66 }, { "epoch": 0.0428560006396418, "grad_norm": 3.6751811504364014, "learning_rate": 4.9390895490489425e-05, "loss": 0.957, "step": 67 }, { "epoch": 0.04349564244023347, "grad_norm": 3.696737051010132, "learning_rate": 4.9380209446462925e-05, "loss": 0.9626, "step": 68 }, { "epoch": 0.044135284240825134, "grad_norm": 3.4946482181549072, "learning_rate": 4.936952340243642e-05, "loss": 0.9912, "step": 69 }, { "epoch": 0.04477492604141681, "grad_norm": 3.5095081329345703, "learning_rate": 4.9358837358409923e-05, "loss": 0.9987, "step": 70 }, { "epoch": 0.04541456784200847, "grad_norm": 3.264599084854126, "learning_rate": 4.9348151314383416e-05, "loss": 0.9057, "step": 71 }, { "epoch": 0.046054209642600145, "grad_norm": 3.213542938232422, "learning_rate": 4.9337465270356915e-05, "loss": 0.8873, "step": 72 }, { "epoch": 0.04669385144319181, "grad_norm": 3.387552499771118, "learning_rate": 4.9326779226330415e-05, "loss": 0.9401, "step": 73 }, { "epoch": 0.047333493243783484, "grad_norm": 3.8830254077911377, "learning_rate": 4.9316093182303914e-05, "loss": 1.1228, "step": 74 }, { "epoch": 0.04797313504437515, "grad_norm": 3.1371631622314453, "learning_rate": 4.930540713827741e-05, "loss": 0.9813, "step": 75 }, { "epoch": 0.048612776844966815, "grad_norm": 3.096027374267578, "learning_rate": 4.929472109425091e-05, "loss": 0.8039, "step": 76 }, { "epoch": 0.04925241864555849, "grad_norm": 2.909639358520508, "learning_rate": 4.9284035050224405e-05, "loss": 0.8033, "step": 77 }, { "epoch": 0.049892060446150154, "grad_norm": 3.4502925872802734, "learning_rate": 4.9273349006197905e-05, "loss": 0.9759, "step": 78 }, { "epoch": 0.050531702246741826, "grad_norm": 2.8735854625701904, "learning_rate": 4.9262662962171404e-05, "loss": 0.893, "step": 79 }, { "epoch": 0.05117134404733349, "grad_norm": 3.286386489868164, "learning_rate": 4.9251976918144904e-05, "loss": 0.8929, "step": 80 }, { "epoch": 0.051810985847925164, "grad_norm": 3.041092872619629, "learning_rate": 4.924129087411841e-05, "loss": 0.8326, "step": 81 }, { "epoch": 0.05245062764851683, "grad_norm": 3.4309558868408203, "learning_rate": 4.92306048300919e-05, "loss": 0.9463, "step": 82 }, { "epoch": 0.053090269449108496, "grad_norm": 4.044023036956787, "learning_rate": 4.92199187860654e-05, "loss": 1.1622, "step": 83 }, { "epoch": 0.05372991124970017, "grad_norm": 3.4805939197540283, "learning_rate": 4.92092327420389e-05, "loss": 0.9696, "step": 84 }, { "epoch": 0.054369553050291834, "grad_norm": 3.2364139556884766, "learning_rate": 4.91985466980124e-05, "loss": 0.9124, "step": 85 }, { "epoch": 0.05500919485088351, "grad_norm": 3.1523385047912598, "learning_rate": 4.918786065398589e-05, "loss": 0.8971, "step": 86 }, { "epoch": 0.05564883665147517, "grad_norm": 3.268002510070801, "learning_rate": 4.91771746099594e-05, "loss": 0.9238, "step": 87 }, { "epoch": 0.056288478452066845, "grad_norm": 2.9969351291656494, "learning_rate": 4.916648856593289e-05, "loss": 0.8588, "step": 88 }, { "epoch": 0.05692812025265851, "grad_norm": 3.401979923248291, "learning_rate": 4.915580252190639e-05, "loss": 0.9757, "step": 89 }, { "epoch": 0.05756776205325018, "grad_norm": 3.6688380241394043, "learning_rate": 4.914511647787989e-05, "loss": 0.9622, "step": 90 }, { "epoch": 0.05820740385384185, "grad_norm": 2.9018354415893555, "learning_rate": 4.913443043385339e-05, "loss": 0.8216, "step": 91 }, { "epoch": 0.058847045654433515, "grad_norm": 3.3676681518554688, "learning_rate": 4.912374438982689e-05, "loss": 0.883, "step": 92 }, { "epoch": 0.05948668745502519, "grad_norm": 3.1586813926696777, "learning_rate": 4.911305834580039e-05, "loss": 0.9087, "step": 93 }, { "epoch": 0.06012632925561685, "grad_norm": 3.241666793823242, "learning_rate": 4.910237230177389e-05, "loss": 0.8813, "step": 94 }, { "epoch": 0.060765971056208526, "grad_norm": 2.8825364112854004, "learning_rate": 4.909168625774738e-05, "loss": 0.809, "step": 95 }, { "epoch": 0.06140561285680019, "grad_norm": 3.058403491973877, "learning_rate": 4.9081000213720887e-05, "loss": 0.8959, "step": 96 }, { "epoch": 0.06204525465739186, "grad_norm": 3.4625747203826904, "learning_rate": 4.907031416969438e-05, "loss": 1.0556, "step": 97 }, { "epoch": 0.06268489645798353, "grad_norm": 2.9675588607788086, "learning_rate": 4.905962812566788e-05, "loss": 0.8407, "step": 98 }, { "epoch": 0.0633245382585752, "grad_norm": 3.3189573287963867, "learning_rate": 4.904894208164138e-05, "loss": 0.9563, "step": 99 }, { "epoch": 0.06396418005916686, "grad_norm": 3.119657039642334, "learning_rate": 4.903825603761488e-05, "loss": 0.9348, "step": 100 }, { "epoch": 0.06460382185975853, "grad_norm": 3.3534693717956543, "learning_rate": 4.9027569993588377e-05, "loss": 0.9842, "step": 101 }, { "epoch": 0.0652434636603502, "grad_norm": 3.1526596546173096, "learning_rate": 4.9016883949561876e-05, "loss": 0.9038, "step": 102 }, { "epoch": 0.06588310546094188, "grad_norm": 3.2262892723083496, "learning_rate": 4.9006197905535375e-05, "loss": 0.907, "step": 103 }, { "epoch": 0.06652274726153354, "grad_norm": 3.2489101886749268, "learning_rate": 4.899551186150887e-05, "loss": 0.9427, "step": 104 }, { "epoch": 0.06716238906212521, "grad_norm": 3.2974557876586914, "learning_rate": 4.8984825817482374e-05, "loss": 1.0098, "step": 105 }, { "epoch": 0.06780203086271688, "grad_norm": 3.0968425273895264, "learning_rate": 4.8974139773455867e-05, "loss": 0.8744, "step": 106 }, { "epoch": 0.06844167266330854, "grad_norm": 3.087939739227295, "learning_rate": 4.8963453729429366e-05, "loss": 0.9359, "step": 107 }, { "epoch": 0.06908131446390021, "grad_norm": 3.2230167388916016, "learning_rate": 4.8952767685402865e-05, "loss": 0.9531, "step": 108 }, { "epoch": 0.06972095626449189, "grad_norm": 3.247502088546753, "learning_rate": 4.8942081641376365e-05, "loss": 0.8503, "step": 109 }, { "epoch": 0.07036059806508356, "grad_norm": 3.499711275100708, "learning_rate": 4.8931395597349864e-05, "loss": 0.9251, "step": 110 }, { "epoch": 0.07100023986567522, "grad_norm": 3.1631062030792236, "learning_rate": 4.8920709553323363e-05, "loss": 0.9323, "step": 111 }, { "epoch": 0.07163988166626689, "grad_norm": 3.4049339294433594, "learning_rate": 4.891002350929686e-05, "loss": 0.932, "step": 112 }, { "epoch": 0.07227952346685856, "grad_norm": 3.1144092082977295, "learning_rate": 4.889933746527036e-05, "loss": 0.9352, "step": 113 }, { "epoch": 0.07291916526745022, "grad_norm": 3.3719403743743896, "learning_rate": 4.888865142124386e-05, "loss": 0.9683, "step": 114 }, { "epoch": 0.0735588070680419, "grad_norm": 3.163418769836426, "learning_rate": 4.8877965377217354e-05, "loss": 0.9329, "step": 115 }, { "epoch": 0.07419844886863357, "grad_norm": 3.4448797702789307, "learning_rate": 4.886727933319086e-05, "loss": 0.9916, "step": 116 }, { "epoch": 0.07483809066922524, "grad_norm": 3.127434253692627, "learning_rate": 4.885659328916435e-05, "loss": 0.8456, "step": 117 }, { "epoch": 0.0754777324698169, "grad_norm": 2.9916157722473145, "learning_rate": 4.884590724513785e-05, "loss": 0.9171, "step": 118 }, { "epoch": 0.07611737427040857, "grad_norm": 3.6702394485473633, "learning_rate": 4.883522120111135e-05, "loss": 1.003, "step": 119 }, { "epoch": 0.07675701607100024, "grad_norm": 3.3792991638183594, "learning_rate": 4.882453515708485e-05, "loss": 0.9366, "step": 120 }, { "epoch": 0.0773966578715919, "grad_norm": 3.2419188022613525, "learning_rate": 4.8813849113058343e-05, "loss": 0.9857, "step": 121 }, { "epoch": 0.07803629967218358, "grad_norm": 3.113842010498047, "learning_rate": 4.880316306903185e-05, "loss": 0.9532, "step": 122 }, { "epoch": 0.07867594147277525, "grad_norm": 3.0012636184692383, "learning_rate": 4.879247702500534e-05, "loss": 0.9319, "step": 123 }, { "epoch": 0.07931558327336692, "grad_norm": 3.0980920791625977, "learning_rate": 4.878179098097884e-05, "loss": 0.8973, "step": 124 }, { "epoch": 0.07995522507395858, "grad_norm": 2.9623830318450928, "learning_rate": 4.877110493695234e-05, "loss": 0.8228, "step": 125 }, { "epoch": 0.08059486687455025, "grad_norm": 2.924691915512085, "learning_rate": 4.876041889292584e-05, "loss": 0.8359, "step": 126 }, { "epoch": 0.08123450867514193, "grad_norm": 3.207602024078369, "learning_rate": 4.874973284889934e-05, "loss": 0.9506, "step": 127 }, { "epoch": 0.08187415047573358, "grad_norm": 3.3331074714660645, "learning_rate": 4.873904680487284e-05, "loss": 0.9785, "step": 128 }, { "epoch": 0.08251379227632526, "grad_norm": 3.4897632598876953, "learning_rate": 4.872836076084634e-05, "loss": 0.9967, "step": 129 }, { "epoch": 0.08315343407691693, "grad_norm": 3.305739402770996, "learning_rate": 4.871767471681983e-05, "loss": 0.9802, "step": 130 }, { "epoch": 0.0837930758775086, "grad_norm": 3.3973934650421143, "learning_rate": 4.870698867279334e-05, "loss": 0.9837, "step": 131 }, { "epoch": 0.08443271767810026, "grad_norm": 2.781184196472168, "learning_rate": 4.869630262876683e-05, "loss": 0.8409, "step": 132 }, { "epoch": 0.08507235947869193, "grad_norm": 3.37329363822937, "learning_rate": 4.868561658474033e-05, "loss": 0.9242, "step": 133 }, { "epoch": 0.0857120012792836, "grad_norm": 3.1330392360687256, "learning_rate": 4.867493054071383e-05, "loss": 0.9759, "step": 134 }, { "epoch": 0.08635164307987526, "grad_norm": 2.9041836261749268, "learning_rate": 4.866424449668733e-05, "loss": 0.8898, "step": 135 }, { "epoch": 0.08699128488046694, "grad_norm": 3.207829236984253, "learning_rate": 4.865355845266083e-05, "loss": 0.9794, "step": 136 }, { "epoch": 0.08763092668105861, "grad_norm": 2.3934268951416016, "learning_rate": 4.8642872408634326e-05, "loss": 0.7443, "step": 137 }, { "epoch": 0.08827056848165027, "grad_norm": 3.6512794494628906, "learning_rate": 4.8632186364607826e-05, "loss": 1.0446, "step": 138 }, { "epoch": 0.08891021028224194, "grad_norm": 2.666923999786377, "learning_rate": 4.8621500320581325e-05, "loss": 0.7934, "step": 139 }, { "epoch": 0.08954985208283361, "grad_norm": 3.061638832092285, "learning_rate": 4.8610814276554825e-05, "loss": 0.934, "step": 140 }, { "epoch": 0.09018949388342529, "grad_norm": 3.193471908569336, "learning_rate": 4.860012823252832e-05, "loss": 0.8959, "step": 141 }, { "epoch": 0.09082913568401695, "grad_norm": 2.9615864753723145, "learning_rate": 4.858944218850182e-05, "loss": 0.8799, "step": 142 }, { "epoch": 0.09146877748460862, "grad_norm": 3.2776529788970947, "learning_rate": 4.8578756144475316e-05, "loss": 0.9657, "step": 143 }, { "epoch": 0.09210841928520029, "grad_norm": 2.8650059700012207, "learning_rate": 4.8568070100448815e-05, "loss": 0.8783, "step": 144 }, { "epoch": 0.09274806108579195, "grad_norm": 3.1735057830810547, "learning_rate": 4.8557384056422315e-05, "loss": 0.893, "step": 145 }, { "epoch": 0.09338770288638362, "grad_norm": 3.1530520915985107, "learning_rate": 4.8546698012395814e-05, "loss": 0.9654, "step": 146 }, { "epoch": 0.0940273446869753, "grad_norm": 2.96382737159729, "learning_rate": 4.853601196836931e-05, "loss": 0.911, "step": 147 }, { "epoch": 0.09466698648756697, "grad_norm": 2.9157848358154297, "learning_rate": 4.852532592434281e-05, "loss": 0.9214, "step": 148 }, { "epoch": 0.09530662828815863, "grad_norm": 3.0061349868774414, "learning_rate": 4.851463988031631e-05, "loss": 0.8943, "step": 149 }, { "epoch": 0.0959462700887503, "grad_norm": 2.904080629348755, "learning_rate": 4.8503953836289805e-05, "loss": 0.8833, "step": 150 }, { "epoch": 0.09658591188934197, "grad_norm": 2.603848457336426, "learning_rate": 4.849326779226331e-05, "loss": 0.7851, "step": 151 }, { "epoch": 0.09722555368993363, "grad_norm": 2.883955240249634, "learning_rate": 4.84825817482368e-05, "loss": 0.8886, "step": 152 }, { "epoch": 0.0978651954905253, "grad_norm": 3.298178195953369, "learning_rate": 4.84718957042103e-05, "loss": 0.9739, "step": 153 }, { "epoch": 0.09850483729111698, "grad_norm": 3.0739529132843018, "learning_rate": 4.84612096601838e-05, "loss": 0.9313, "step": 154 }, { "epoch": 0.09914447909170865, "grad_norm": 2.864802598953247, "learning_rate": 4.84505236161573e-05, "loss": 0.8005, "step": 155 }, { "epoch": 0.09978412089230031, "grad_norm": 3.0745465755462646, "learning_rate": 4.8439837572130794e-05, "loss": 0.9582, "step": 156 }, { "epoch": 0.10042376269289198, "grad_norm": 2.968920946121216, "learning_rate": 4.84291515281043e-05, "loss": 0.9369, "step": 157 }, { "epoch": 0.10106340449348365, "grad_norm": 3.003913164138794, "learning_rate": 4.84184654840778e-05, "loss": 0.8767, "step": 158 }, { "epoch": 0.10170304629407531, "grad_norm": 3.1298813819885254, "learning_rate": 4.840777944005129e-05, "loss": 0.9916, "step": 159 }, { "epoch": 0.10234268809466698, "grad_norm": 3.1826727390289307, "learning_rate": 4.83970933960248e-05, "loss": 0.8268, "step": 160 }, { "epoch": 0.10298232989525866, "grad_norm": 2.9182395935058594, "learning_rate": 4.838640735199829e-05, "loss": 0.8493, "step": 161 }, { "epoch": 0.10362197169585033, "grad_norm": 3.172877073287964, "learning_rate": 4.837572130797179e-05, "loss": 0.9514, "step": 162 }, { "epoch": 0.10426161349644199, "grad_norm": 3.046769618988037, "learning_rate": 4.836503526394529e-05, "loss": 0.9571, "step": 163 }, { "epoch": 0.10490125529703366, "grad_norm": 3.3287999629974365, "learning_rate": 4.835434921991879e-05, "loss": 0.809, "step": 164 }, { "epoch": 0.10554089709762533, "grad_norm": 2.8156962394714355, "learning_rate": 4.834366317589228e-05, "loss": 0.9603, "step": 165 }, { "epoch": 0.10618053889821699, "grad_norm": 2.867738723754883, "learning_rate": 4.833297713186579e-05, "loss": 0.8771, "step": 166 }, { "epoch": 0.10682018069880866, "grad_norm": 3.0130057334899902, "learning_rate": 4.832229108783928e-05, "loss": 0.9795, "step": 167 }, { "epoch": 0.10745982249940034, "grad_norm": 3.038479804992676, "learning_rate": 4.8311605043812786e-05, "loss": 1.0077, "step": 168 }, { "epoch": 0.10809946429999201, "grad_norm": 2.715528726577759, "learning_rate": 4.830091899978628e-05, "loss": 0.8767, "step": 169 }, { "epoch": 0.10873910610058367, "grad_norm": 2.719451427459717, "learning_rate": 4.829023295575978e-05, "loss": 0.8893, "step": 170 }, { "epoch": 0.10937874790117534, "grad_norm": 3.0025105476379395, "learning_rate": 4.827954691173328e-05, "loss": 0.8376, "step": 171 }, { "epoch": 0.11001838970176701, "grad_norm": 2.7460434436798096, "learning_rate": 4.826886086770678e-05, "loss": 0.8464, "step": 172 }, { "epoch": 0.11065803150235867, "grad_norm": 2.9328606128692627, "learning_rate": 4.8258174823680276e-05, "loss": 0.8323, "step": 173 }, { "epoch": 0.11129767330295035, "grad_norm": 2.961212158203125, "learning_rate": 4.8247488779653776e-05, "loss": 0.9018, "step": 174 }, { "epoch": 0.11193731510354202, "grad_norm": 2.966740846633911, "learning_rate": 4.8236802735627275e-05, "loss": 0.8428, "step": 175 }, { "epoch": 0.11257695690413369, "grad_norm": 3.171058177947998, "learning_rate": 4.822611669160077e-05, "loss": 0.9487, "step": 176 }, { "epoch": 0.11321659870472535, "grad_norm": 2.882718563079834, "learning_rate": 4.8215430647574274e-05, "loss": 0.9581, "step": 177 }, { "epoch": 0.11385624050531702, "grad_norm": 2.833556890487671, "learning_rate": 4.8204744603547766e-05, "loss": 0.8506, "step": 178 }, { "epoch": 0.1144958823059087, "grad_norm": 2.9089512825012207, "learning_rate": 4.8194058559521266e-05, "loss": 0.9213, "step": 179 }, { "epoch": 0.11513552410650035, "grad_norm": 3.0946218967437744, "learning_rate": 4.8183372515494765e-05, "loss": 0.8109, "step": 180 }, { "epoch": 0.11577516590709203, "grad_norm": 2.8648128509521484, "learning_rate": 4.8172686471468265e-05, "loss": 0.8754, "step": 181 }, { "epoch": 0.1164148077076837, "grad_norm": 2.9012584686279297, "learning_rate": 4.8162000427441764e-05, "loss": 0.8946, "step": 182 }, { "epoch": 0.11705444950827537, "grad_norm": 3.00886869430542, "learning_rate": 4.815131438341526e-05, "loss": 1.0621, "step": 183 }, { "epoch": 0.11769409130886703, "grad_norm": 2.6910293102264404, "learning_rate": 4.814062833938876e-05, "loss": 0.8765, "step": 184 }, { "epoch": 0.1183337331094587, "grad_norm": 2.775951862335205, "learning_rate": 4.8129942295362255e-05, "loss": 0.8297, "step": 185 }, { "epoch": 0.11897337491005038, "grad_norm": 2.6360793113708496, "learning_rate": 4.811925625133576e-05, "loss": 0.8422, "step": 186 }, { "epoch": 0.11961301671064203, "grad_norm": 2.991544485092163, "learning_rate": 4.8108570207309254e-05, "loss": 0.9109, "step": 187 }, { "epoch": 0.1202526585112337, "grad_norm": 3.1472723484039307, "learning_rate": 4.809788416328275e-05, "loss": 1.0306, "step": 188 }, { "epoch": 0.12089230031182538, "grad_norm": 2.992020845413208, "learning_rate": 4.808719811925625e-05, "loss": 0.9407, "step": 189 }, { "epoch": 0.12153194211241705, "grad_norm": 2.8963804244995117, "learning_rate": 4.807651207522975e-05, "loss": 0.8547, "step": 190 }, { "epoch": 0.12217158391300871, "grad_norm": 3.120312452316284, "learning_rate": 4.806582603120325e-05, "loss": 1.0028, "step": 191 }, { "epoch": 0.12281122571360038, "grad_norm": 3.0206565856933594, "learning_rate": 4.805513998717675e-05, "loss": 0.878, "step": 192 }, { "epoch": 0.12345086751419206, "grad_norm": 2.732942819595337, "learning_rate": 4.804445394315025e-05, "loss": 0.8709, "step": 193 }, { "epoch": 0.12409050931478371, "grad_norm": 2.938957691192627, "learning_rate": 4.803376789912375e-05, "loss": 0.965, "step": 194 }, { "epoch": 0.12473015111537539, "grad_norm": 3.0302512645721436, "learning_rate": 4.802308185509725e-05, "loss": 0.936, "step": 195 }, { "epoch": 0.12536979291596706, "grad_norm": 2.846325159072876, "learning_rate": 4.801239581107074e-05, "loss": 0.7807, "step": 196 }, { "epoch": 0.12600943471655873, "grad_norm": 3.189849376678467, "learning_rate": 4.800170976704425e-05, "loss": 0.9737, "step": 197 }, { "epoch": 0.1266490765171504, "grad_norm": 2.9430770874023438, "learning_rate": 4.799102372301774e-05, "loss": 0.8094, "step": 198 }, { "epoch": 0.12728871831774208, "grad_norm": 2.7001142501831055, "learning_rate": 4.798033767899124e-05, "loss": 0.8156, "step": 199 }, { "epoch": 0.12792836011833372, "grad_norm": 2.87261962890625, "learning_rate": 4.796965163496474e-05, "loss": 0.8413, "step": 200 }, { "epoch": 0.1285680019189254, "grad_norm": 2.9979734420776367, "learning_rate": 4.795896559093824e-05, "loss": 0.8899, "step": 201 }, { "epoch": 0.12920764371951707, "grad_norm": 3.017146110534668, "learning_rate": 4.794827954691173e-05, "loss": 0.9235, "step": 202 }, { "epoch": 0.12984728552010874, "grad_norm": 2.893805742263794, "learning_rate": 4.793759350288524e-05, "loss": 0.8124, "step": 203 }, { "epoch": 0.1304869273207004, "grad_norm": 3.0101611614227295, "learning_rate": 4.7926907458858736e-05, "loss": 0.8679, "step": 204 }, { "epoch": 0.13112656912129209, "grad_norm": 2.552396535873413, "learning_rate": 4.791622141483223e-05, "loss": 0.7325, "step": 205 }, { "epoch": 0.13176621092188376, "grad_norm": 3.1043059825897217, "learning_rate": 4.7905535370805735e-05, "loss": 0.8962, "step": 206 }, { "epoch": 0.1324058527224754, "grad_norm": 3.2721590995788574, "learning_rate": 4.789484932677923e-05, "loss": 0.9915, "step": 207 }, { "epoch": 0.13304549452306708, "grad_norm": 3.175801992416382, "learning_rate": 4.788416328275273e-05, "loss": 0.9229, "step": 208 }, { "epoch": 0.13368513632365875, "grad_norm": 2.9646801948547363, "learning_rate": 4.7873477238726226e-05, "loss": 0.7331, "step": 209 }, { "epoch": 0.13432477812425042, "grad_norm": 3.0931332111358643, "learning_rate": 4.7862791194699726e-05, "loss": 0.8776, "step": 210 }, { "epoch": 0.1349644199248421, "grad_norm": 3.100283622741699, "learning_rate": 4.785210515067322e-05, "loss": 0.9053, "step": 211 }, { "epoch": 0.13560406172543377, "grad_norm": 3.1369335651397705, "learning_rate": 4.7841419106646724e-05, "loss": 0.9115, "step": 212 }, { "epoch": 0.13624370352602544, "grad_norm": 2.7910146713256836, "learning_rate": 4.783073306262022e-05, "loss": 0.8834, "step": 213 }, { "epoch": 0.13688334532661708, "grad_norm": 2.5720582008361816, "learning_rate": 4.7820047018593716e-05, "loss": 0.7837, "step": 214 }, { "epoch": 0.13752298712720876, "grad_norm": 2.730604410171509, "learning_rate": 4.7809360974567216e-05, "loss": 0.9334, "step": 215 }, { "epoch": 0.13816262892780043, "grad_norm": 2.7905635833740234, "learning_rate": 4.7798674930540715e-05, "loss": 0.7764, "step": 216 }, { "epoch": 0.1388022707283921, "grad_norm": 2.859790325164795, "learning_rate": 4.7787988886514214e-05, "loss": 0.9586, "step": 217 }, { "epoch": 0.13944191252898377, "grad_norm": 2.570192575454712, "learning_rate": 4.7777302842487714e-05, "loss": 0.7886, "step": 218 }, { "epoch": 0.14008155432957545, "grad_norm": 2.871694326400757, "learning_rate": 4.776661679846121e-05, "loss": 0.9145, "step": 219 }, { "epoch": 0.14072119613016712, "grad_norm": 2.7373812198638916, "learning_rate": 4.7755930754434706e-05, "loss": 0.8752, "step": 220 }, { "epoch": 0.14136083793075876, "grad_norm": 3.17299747467041, "learning_rate": 4.774524471040821e-05, "loss": 0.9535, "step": 221 }, { "epoch": 0.14200047973135044, "grad_norm": 3.0749080181121826, "learning_rate": 4.7734558666381704e-05, "loss": 0.8973, "step": 222 }, { "epoch": 0.1426401215319421, "grad_norm": 3.2594897747039795, "learning_rate": 4.772387262235521e-05, "loss": 0.887, "step": 223 }, { "epoch": 0.14327976333253378, "grad_norm": 3.124821424484253, "learning_rate": 4.77131865783287e-05, "loss": 0.8867, "step": 224 }, { "epoch": 0.14391940513312546, "grad_norm": 2.854959726333618, "learning_rate": 4.77025005343022e-05, "loss": 0.8612, "step": 225 }, { "epoch": 0.14455904693371713, "grad_norm": 2.895678758621216, "learning_rate": 4.76918144902757e-05, "loss": 0.82, "step": 226 }, { "epoch": 0.1451986887343088, "grad_norm": 2.8061985969543457, "learning_rate": 4.76811284462492e-05, "loss": 0.8399, "step": 227 }, { "epoch": 0.14583833053490045, "grad_norm": 3.1230058670043945, "learning_rate": 4.76704424022227e-05, "loss": 0.8948, "step": 228 }, { "epoch": 0.14647797233549212, "grad_norm": 3.0216288566589355, "learning_rate": 4.76597563581962e-05, "loss": 0.9485, "step": 229 }, { "epoch": 0.1471176141360838, "grad_norm": 2.8085646629333496, "learning_rate": 4.76490703141697e-05, "loss": 0.8112, "step": 230 }, { "epoch": 0.14775725593667546, "grad_norm": 3.0322203636169434, "learning_rate": 4.763838427014319e-05, "loss": 0.9738, "step": 231 }, { "epoch": 0.14839689773726714, "grad_norm": 2.917573928833008, "learning_rate": 4.76276982261167e-05, "loss": 0.9267, "step": 232 }, { "epoch": 0.1490365395378588, "grad_norm": 3.0448379516601562, "learning_rate": 4.761701218209019e-05, "loss": 0.8845, "step": 233 }, { "epoch": 0.14967618133845048, "grad_norm": 2.8761885166168213, "learning_rate": 4.760632613806369e-05, "loss": 0.8912, "step": 234 }, { "epoch": 0.15031582313904213, "grad_norm": 2.9035568237304688, "learning_rate": 4.759564009403719e-05, "loss": 1.0309, "step": 235 }, { "epoch": 0.1509554649396338, "grad_norm": 2.924506187438965, "learning_rate": 4.758495405001069e-05, "loss": 0.8586, "step": 236 }, { "epoch": 0.15159510674022547, "grad_norm": 2.5669422149658203, "learning_rate": 4.757426800598419e-05, "loss": 0.7553, "step": 237 }, { "epoch": 0.15223474854081714, "grad_norm": 2.7570383548736572, "learning_rate": 4.756358196195769e-05, "loss": 0.8244, "step": 238 }, { "epoch": 0.15287439034140882, "grad_norm": 2.893439531326294, "learning_rate": 4.755289591793119e-05, "loss": 0.807, "step": 239 }, { "epoch": 0.1535140321420005, "grad_norm": 2.4479477405548096, "learning_rate": 4.754220987390468e-05, "loss": 0.727, "step": 240 }, { "epoch": 0.15415367394259216, "grad_norm": 3.0554516315460205, "learning_rate": 4.7531523829878186e-05, "loss": 0.9386, "step": 241 }, { "epoch": 0.1547933157431838, "grad_norm": 2.8616034984588623, "learning_rate": 4.752083778585168e-05, "loss": 0.8254, "step": 242 }, { "epoch": 0.15543295754377548, "grad_norm": 3.0332019329071045, "learning_rate": 4.751015174182518e-05, "loss": 0.841, "step": 243 }, { "epoch": 0.15607259934436715, "grad_norm": 3.25240421295166, "learning_rate": 4.749946569779868e-05, "loss": 0.9434, "step": 244 }, { "epoch": 0.15671224114495882, "grad_norm": 2.9794118404388428, "learning_rate": 4.7488779653772176e-05, "loss": 0.7924, "step": 245 }, { "epoch": 0.1573518829455505, "grad_norm": 3.0838968753814697, "learning_rate": 4.747809360974567e-05, "loss": 0.9092, "step": 246 }, { "epoch": 0.15799152474614217, "grad_norm": 3.1214678287506104, "learning_rate": 4.7467407565719175e-05, "loss": 0.8556, "step": 247 }, { "epoch": 0.15863116654673384, "grad_norm": 3.2549057006835938, "learning_rate": 4.745672152169267e-05, "loss": 0.8633, "step": 248 }, { "epoch": 0.1592708083473255, "grad_norm": 2.9489269256591797, "learning_rate": 4.744603547766617e-05, "loss": 0.8536, "step": 249 }, { "epoch": 0.15991045014791716, "grad_norm": 2.9182708263397217, "learning_rate": 4.743534943363967e-05, "loss": 0.8327, "step": 250 }, { "epoch": 0.16055009194850883, "grad_norm": 2.681732654571533, "learning_rate": 4.7424663389613166e-05, "loss": 0.8328, "step": 251 }, { "epoch": 0.1611897337491005, "grad_norm": 2.963179349899292, "learning_rate": 4.741397734558667e-05, "loss": 0.915, "step": 252 }, { "epoch": 0.16182937554969218, "grad_norm": 2.7239153385162354, "learning_rate": 4.7403291301560164e-05, "loss": 0.802, "step": 253 }, { "epoch": 0.16246901735028385, "grad_norm": 2.6116347312927246, "learning_rate": 4.7392605257533664e-05, "loss": 0.8365, "step": 254 }, { "epoch": 0.16310865915087552, "grad_norm": 2.9473235607147217, "learning_rate": 4.738191921350716e-05, "loss": 0.8955, "step": 255 }, { "epoch": 0.16374830095146717, "grad_norm": 2.610490083694458, "learning_rate": 4.737123316948066e-05, "loss": 0.8179, "step": 256 }, { "epoch": 0.16438794275205884, "grad_norm": 2.599161148071289, "learning_rate": 4.7360547125454155e-05, "loss": 0.8483, "step": 257 }, { "epoch": 0.1650275845526505, "grad_norm": 2.55717396736145, "learning_rate": 4.734986108142766e-05, "loss": 0.847, "step": 258 }, { "epoch": 0.1656672263532422, "grad_norm": 2.6633405685424805, "learning_rate": 4.7339175037401154e-05, "loss": 0.8278, "step": 259 }, { "epoch": 0.16630686815383386, "grad_norm": 2.5367047786712646, "learning_rate": 4.732848899337465e-05, "loss": 0.8217, "step": 260 }, { "epoch": 0.16694650995442553, "grad_norm": 2.723659038543701, "learning_rate": 4.731780294934815e-05, "loss": 0.87, "step": 261 }, { "epoch": 0.1675861517550172, "grad_norm": 3.103633403778076, "learning_rate": 4.730711690532165e-05, "loss": 1.0308, "step": 262 }, { "epoch": 0.16822579355560885, "grad_norm": 2.508518695831299, "learning_rate": 4.729643086129515e-05, "loss": 0.8472, "step": 263 }, { "epoch": 0.16886543535620052, "grad_norm": 2.7026095390319824, "learning_rate": 4.728574481726865e-05, "loss": 0.8161, "step": 264 }, { "epoch": 0.1695050771567922, "grad_norm": 2.884580373764038, "learning_rate": 4.727505877324215e-05, "loss": 0.8383, "step": 265 }, { "epoch": 0.17014471895738387, "grad_norm": 3.5235071182250977, "learning_rate": 4.726437272921564e-05, "loss": 0.9077, "step": 266 }, { "epoch": 0.17078436075797554, "grad_norm": 2.661553144454956, "learning_rate": 4.725368668518915e-05, "loss": 0.7792, "step": 267 }, { "epoch": 0.1714240025585672, "grad_norm": 2.683823347091675, "learning_rate": 4.724300064116264e-05, "loss": 0.771, "step": 268 }, { "epoch": 0.17206364435915888, "grad_norm": 2.753601312637329, "learning_rate": 4.723231459713614e-05, "loss": 0.7982, "step": 269 }, { "epoch": 0.17270328615975053, "grad_norm": 3.1290347576141357, "learning_rate": 4.722162855310964e-05, "loss": 0.8601, "step": 270 }, { "epoch": 0.1733429279603422, "grad_norm": 2.8989670276641846, "learning_rate": 4.721094250908314e-05, "loss": 0.8535, "step": 271 }, { "epoch": 0.17398256976093388, "grad_norm": 2.718829393386841, "learning_rate": 4.720025646505664e-05, "loss": 0.8542, "step": 272 }, { "epoch": 0.17462221156152555, "grad_norm": 2.7551136016845703, "learning_rate": 4.718957042103014e-05, "loss": 0.7925, "step": 273 }, { "epoch": 0.17526185336211722, "grad_norm": 2.7832024097442627, "learning_rate": 4.717888437700364e-05, "loss": 0.7897, "step": 274 }, { "epoch": 0.1759014951627089, "grad_norm": 3.1213130950927734, "learning_rate": 4.716819833297713e-05, "loss": 0.8246, "step": 275 }, { "epoch": 0.17654113696330054, "grad_norm": 3.139709949493408, "learning_rate": 4.7157512288950636e-05, "loss": 0.8428, "step": 276 }, { "epoch": 0.1771807787638922, "grad_norm": 3.0290613174438477, "learning_rate": 4.714682624492413e-05, "loss": 0.9477, "step": 277 }, { "epoch": 0.17782042056448388, "grad_norm": 2.9898009300231934, "learning_rate": 4.7136140200897635e-05, "loss": 0.8169, "step": 278 }, { "epoch": 0.17846006236507556, "grad_norm": 2.819793462753296, "learning_rate": 4.712545415687113e-05, "loss": 0.932, "step": 279 }, { "epoch": 0.17909970416566723, "grad_norm": 2.7697415351867676, "learning_rate": 4.711476811284463e-05, "loss": 0.8292, "step": 280 }, { "epoch": 0.1797393459662589, "grad_norm": 2.452153205871582, "learning_rate": 4.7104082068818126e-05, "loss": 0.7456, "step": 281 }, { "epoch": 0.18037898776685057, "grad_norm": 2.829197406768799, "learning_rate": 4.7093396024791626e-05, "loss": 0.9367, "step": 282 }, { "epoch": 0.18101862956744222, "grad_norm": 2.7254505157470703, "learning_rate": 4.7082709980765125e-05, "loss": 0.9341, "step": 283 }, { "epoch": 0.1816582713680339, "grad_norm": 2.5844085216522217, "learning_rate": 4.7072023936738624e-05, "loss": 0.7766, "step": 284 }, { "epoch": 0.18229791316862556, "grad_norm": 2.2345259189605713, "learning_rate": 4.7061337892712124e-05, "loss": 0.6529, "step": 285 }, { "epoch": 0.18293755496921724, "grad_norm": 2.6041507720947266, "learning_rate": 4.7050651848685616e-05, "loss": 0.8856, "step": 286 }, { "epoch": 0.1835771967698089, "grad_norm": 2.6847994327545166, "learning_rate": 4.703996580465912e-05, "loss": 0.8321, "step": 287 }, { "epoch": 0.18421683857040058, "grad_norm": 3.025704860687256, "learning_rate": 4.7029279760632615e-05, "loss": 0.783, "step": 288 }, { "epoch": 0.18485648037099225, "grad_norm": 2.742975950241089, "learning_rate": 4.7018593716606114e-05, "loss": 0.9032, "step": 289 }, { "epoch": 0.1854961221715839, "grad_norm": 2.452404737472534, "learning_rate": 4.7007907672579614e-05, "loss": 0.8441, "step": 290 }, { "epoch": 0.18613576397217557, "grad_norm": 2.590944528579712, "learning_rate": 4.699722162855311e-05, "loss": 0.8323, "step": 291 }, { "epoch": 0.18677540577276724, "grad_norm": 2.843992233276367, "learning_rate": 4.6986535584526606e-05, "loss": 0.8646, "step": 292 }, { "epoch": 0.18741504757335892, "grad_norm": 2.8486318588256836, "learning_rate": 4.697584954050011e-05, "loss": 0.8576, "step": 293 }, { "epoch": 0.1880546893739506, "grad_norm": 2.80191969871521, "learning_rate": 4.6965163496473604e-05, "loss": 0.8727, "step": 294 }, { "epoch": 0.18869433117454226, "grad_norm": 3.0136806964874268, "learning_rate": 4.6954477452447104e-05, "loss": 0.8943, "step": 295 }, { "epoch": 0.18933397297513394, "grad_norm": 2.673966407775879, "learning_rate": 4.694379140842061e-05, "loss": 0.805, "step": 296 }, { "epoch": 0.18997361477572558, "grad_norm": 2.6993069648742676, "learning_rate": 4.69331053643941e-05, "loss": 0.8435, "step": 297 }, { "epoch": 0.19061325657631725, "grad_norm": 2.735931634902954, "learning_rate": 4.69224193203676e-05, "loss": 0.894, "step": 298 }, { "epoch": 0.19125289837690893, "grad_norm": 2.6338067054748535, "learning_rate": 4.69117332763411e-05, "loss": 0.8343, "step": 299 }, { "epoch": 0.1918925401775006, "grad_norm": 2.6077582836151123, "learning_rate": 4.69010472323146e-05, "loss": 0.8534, "step": 300 }, { "epoch": 0.19253218197809227, "grad_norm": 2.636435031890869, "learning_rate": 4.689036118828809e-05, "loss": 0.897, "step": 301 }, { "epoch": 0.19317182377868394, "grad_norm": 2.7182765007019043, "learning_rate": 4.68796751442616e-05, "loss": 0.8465, "step": 302 }, { "epoch": 0.19381146557927562, "grad_norm": 2.917398452758789, "learning_rate": 4.686898910023509e-05, "loss": 0.8881, "step": 303 }, { "epoch": 0.19445110737986726, "grad_norm": 2.8616085052490234, "learning_rate": 4.685830305620859e-05, "loss": 0.8546, "step": 304 }, { "epoch": 0.19509074918045893, "grad_norm": 2.760434150695801, "learning_rate": 4.684761701218209e-05, "loss": 0.9518, "step": 305 }, { "epoch": 0.1957303909810506, "grad_norm": 2.4656758308410645, "learning_rate": 4.683693096815559e-05, "loss": 0.7429, "step": 306 }, { "epoch": 0.19637003278164228, "grad_norm": 2.6935067176818848, "learning_rate": 4.682624492412909e-05, "loss": 0.8073, "step": 307 }, { "epoch": 0.19700967458223395, "grad_norm": 2.8546817302703857, "learning_rate": 4.681555888010259e-05, "loss": 0.9638, "step": 308 }, { "epoch": 0.19764931638282562, "grad_norm": 2.565056562423706, "learning_rate": 4.680487283607609e-05, "loss": 0.8272, "step": 309 }, { "epoch": 0.1982889581834173, "grad_norm": 2.670307159423828, "learning_rate": 4.679418679204959e-05, "loss": 0.8595, "step": 310 }, { "epoch": 0.19892859998400894, "grad_norm": 2.8646392822265625, "learning_rate": 4.678350074802309e-05, "loss": 0.924, "step": 311 }, { "epoch": 0.19956824178460061, "grad_norm": 2.329155683517456, "learning_rate": 4.677281470399658e-05, "loss": 0.7529, "step": 312 }, { "epoch": 0.2002078835851923, "grad_norm": 2.937229633331299, "learning_rate": 4.6762128659970085e-05, "loss": 0.8528, "step": 313 }, { "epoch": 0.20084752538578396, "grad_norm": 3.061223030090332, "learning_rate": 4.675144261594358e-05, "loss": 0.9067, "step": 314 }, { "epoch": 0.20148716718637563, "grad_norm": 2.890824794769287, "learning_rate": 4.674075657191708e-05, "loss": 0.9379, "step": 315 }, { "epoch": 0.2021268089869673, "grad_norm": 2.474018096923828, "learning_rate": 4.673007052789058e-05, "loss": 0.7366, "step": 316 }, { "epoch": 0.20276645078755898, "grad_norm": 2.6298065185546875, "learning_rate": 4.6719384483864076e-05, "loss": 0.7878, "step": 317 }, { "epoch": 0.20340609258815062, "grad_norm": 2.8355021476745605, "learning_rate": 4.6708698439837575e-05, "loss": 0.7836, "step": 318 }, { "epoch": 0.2040457343887423, "grad_norm": 2.437777280807495, "learning_rate": 4.6698012395811075e-05, "loss": 0.6924, "step": 319 }, { "epoch": 0.20468537618933397, "grad_norm": 3.3331644535064697, "learning_rate": 4.6687326351784574e-05, "loss": 1.021, "step": 320 }, { "epoch": 0.20532501798992564, "grad_norm": 2.9480056762695312, "learning_rate": 4.667664030775807e-05, "loss": 0.845, "step": 321 }, { "epoch": 0.2059646597905173, "grad_norm": 2.711811065673828, "learning_rate": 4.666595426373157e-05, "loss": 0.7977, "step": 322 }, { "epoch": 0.20660430159110899, "grad_norm": 2.9610745906829834, "learning_rate": 4.6655268219705066e-05, "loss": 0.8494, "step": 323 }, { "epoch": 0.20724394339170066, "grad_norm": 2.647684097290039, "learning_rate": 4.6644582175678565e-05, "loss": 0.8241, "step": 324 }, { "epoch": 0.2078835851922923, "grad_norm": 2.822852611541748, "learning_rate": 4.6633896131652064e-05, "loss": 0.8214, "step": 325 }, { "epoch": 0.20852322699288398, "grad_norm": 2.310638427734375, "learning_rate": 4.6623210087625564e-05, "loss": 0.7653, "step": 326 }, { "epoch": 0.20916286879347565, "grad_norm": 2.8434946537017822, "learning_rate": 4.6612524043599056e-05, "loss": 0.9074, "step": 327 }, { "epoch": 0.20980251059406732, "grad_norm": 2.6273133754730225, "learning_rate": 4.660183799957256e-05, "loss": 0.8539, "step": 328 }, { "epoch": 0.210442152394659, "grad_norm": 2.555723190307617, "learning_rate": 4.659115195554606e-05, "loss": 0.7931, "step": 329 }, { "epoch": 0.21108179419525067, "grad_norm": 2.832242965698242, "learning_rate": 4.6580465911519554e-05, "loss": 0.9129, "step": 330 }, { "epoch": 0.21172143599584234, "grad_norm": 2.4606082439422607, "learning_rate": 4.656977986749306e-05, "loss": 0.719, "step": 331 }, { "epoch": 0.21236107779643398, "grad_norm": 2.9017698764801025, "learning_rate": 4.655909382346655e-05, "loss": 0.8765, "step": 332 }, { "epoch": 0.21300071959702566, "grad_norm": 2.6410350799560547, "learning_rate": 4.654840777944005e-05, "loss": 0.7867, "step": 333 }, { "epoch": 0.21364036139761733, "grad_norm": 2.5876753330230713, "learning_rate": 4.653772173541355e-05, "loss": 0.7032, "step": 334 }, { "epoch": 0.214280003198209, "grad_norm": 2.436483860015869, "learning_rate": 4.652703569138705e-05, "loss": 0.784, "step": 335 }, { "epoch": 0.21491964499880067, "grad_norm": 3.1525931358337402, "learning_rate": 4.651634964736055e-05, "loss": 0.912, "step": 336 }, { "epoch": 0.21555928679939235, "grad_norm": 3.039365530014038, "learning_rate": 4.650566360333405e-05, "loss": 0.9294, "step": 337 }, { "epoch": 0.21619892859998402, "grad_norm": 3.1444387435913086, "learning_rate": 4.649497755930754e-05, "loss": 0.8717, "step": 338 }, { "epoch": 0.21683857040057566, "grad_norm": 2.7917325496673584, "learning_rate": 4.648429151528105e-05, "loss": 0.9408, "step": 339 }, { "epoch": 0.21747821220116734, "grad_norm": 2.665494203567505, "learning_rate": 4.647360547125454e-05, "loss": 0.7739, "step": 340 }, { "epoch": 0.218117854001759, "grad_norm": 3.186284065246582, "learning_rate": 4.646291942722804e-05, "loss": 0.8443, "step": 341 }, { "epoch": 0.21875749580235068, "grad_norm": 2.6965200901031494, "learning_rate": 4.645223338320155e-05, "loss": 0.8259, "step": 342 }, { "epoch": 0.21939713760294235, "grad_norm": 2.7016642093658447, "learning_rate": 4.644154733917504e-05, "loss": 0.831, "step": 343 }, { "epoch": 0.22003677940353403, "grad_norm": 2.3008852005004883, "learning_rate": 4.643086129514854e-05, "loss": 0.6377, "step": 344 }, { "epoch": 0.2206764212041257, "grad_norm": 2.7286880016326904, "learning_rate": 4.642017525112204e-05, "loss": 0.8643, "step": 345 }, { "epoch": 0.22131606300471734, "grad_norm": 3.0022411346435547, "learning_rate": 4.640948920709554e-05, "loss": 0.941, "step": 346 }, { "epoch": 0.22195570480530902, "grad_norm": 3.082437515258789, "learning_rate": 4.639880316306903e-05, "loss": 0.9995, "step": 347 }, { "epoch": 0.2225953466059007, "grad_norm": 2.608405113220215, "learning_rate": 4.6388117119042536e-05, "loss": 0.8163, "step": 348 }, { "epoch": 0.22323498840649236, "grad_norm": 2.5102648735046387, "learning_rate": 4.637743107501603e-05, "loss": 0.7536, "step": 349 }, { "epoch": 0.22387463020708404, "grad_norm": 2.536804437637329, "learning_rate": 4.636674503098953e-05, "loss": 0.7645, "step": 350 }, { "epoch": 0.2245142720076757, "grad_norm": 2.5854899883270264, "learning_rate": 4.635605898696303e-05, "loss": 0.8361, "step": 351 }, { "epoch": 0.22515391380826738, "grad_norm": 2.534740924835205, "learning_rate": 4.634537294293653e-05, "loss": 0.8351, "step": 352 }, { "epoch": 0.22579355560885903, "grad_norm": 2.5224814414978027, "learning_rate": 4.6334686898910026e-05, "loss": 0.7384, "step": 353 }, { "epoch": 0.2264331974094507, "grad_norm": 2.448772668838501, "learning_rate": 4.6324000854883525e-05, "loss": 0.811, "step": 354 }, { "epoch": 0.22707283921004237, "grad_norm": 2.641885757446289, "learning_rate": 4.6313314810857025e-05, "loss": 0.7952, "step": 355 }, { "epoch": 0.22771248101063404, "grad_norm": 2.855888605117798, "learning_rate": 4.630262876683052e-05, "loss": 0.8237, "step": 356 }, { "epoch": 0.22835212281122572, "grad_norm": 2.7013163566589355, "learning_rate": 4.6291942722804023e-05, "loss": 0.8137, "step": 357 }, { "epoch": 0.2289917646118174, "grad_norm": 2.7953360080718994, "learning_rate": 4.6281256678777516e-05, "loss": 0.8377, "step": 358 }, { "epoch": 0.22963140641240906, "grad_norm": 2.8884384632110596, "learning_rate": 4.6270570634751015e-05, "loss": 0.8629, "step": 359 }, { "epoch": 0.2302710482130007, "grad_norm": 2.9556541442871094, "learning_rate": 4.6259884590724515e-05, "loss": 0.9102, "step": 360 }, { "epoch": 0.23091069001359238, "grad_norm": 2.8044021129608154, "learning_rate": 4.6249198546698014e-05, "loss": 0.8388, "step": 361 }, { "epoch": 0.23155033181418405, "grad_norm": 2.432013511657715, "learning_rate": 4.6238512502671514e-05, "loss": 0.7672, "step": 362 }, { "epoch": 0.23218997361477572, "grad_norm": 2.922989845275879, "learning_rate": 4.622782645864501e-05, "loss": 0.9464, "step": 363 }, { "epoch": 0.2328296154153674, "grad_norm": 2.6194958686828613, "learning_rate": 4.621714041461851e-05, "loss": 0.8294, "step": 364 }, { "epoch": 0.23346925721595907, "grad_norm": 2.463254451751709, "learning_rate": 4.620645437059201e-05, "loss": 0.7614, "step": 365 }, { "epoch": 0.23410889901655074, "grad_norm": 2.737752914428711, "learning_rate": 4.619576832656551e-05, "loss": 0.9387, "step": 366 }, { "epoch": 0.2347485408171424, "grad_norm": 2.485262870788574, "learning_rate": 4.6185082282539004e-05, "loss": 0.7469, "step": 367 }, { "epoch": 0.23538818261773406, "grad_norm": 2.812809944152832, "learning_rate": 4.617439623851251e-05, "loss": 0.9078, "step": 368 }, { "epoch": 0.23602782441832573, "grad_norm": 2.802497625350952, "learning_rate": 4.6163710194486e-05, "loss": 0.9106, "step": 369 }, { "epoch": 0.2366674662189174, "grad_norm": 2.443861484527588, "learning_rate": 4.61530241504595e-05, "loss": 0.799, "step": 370 }, { "epoch": 0.23730710801950908, "grad_norm": 2.6237952709198, "learning_rate": 4.6142338106433e-05, "loss": 0.8169, "step": 371 }, { "epoch": 0.23794674982010075, "grad_norm": 2.2601051330566406, "learning_rate": 4.61316520624065e-05, "loss": 0.7139, "step": 372 }, { "epoch": 0.23858639162069242, "grad_norm": 2.7410929203033447, "learning_rate": 4.612096601837999e-05, "loss": 0.9006, "step": 373 }, { "epoch": 0.23922603342128407, "grad_norm": 2.777866840362549, "learning_rate": 4.61102799743535e-05, "loss": 0.8401, "step": 374 }, { "epoch": 0.23986567522187574, "grad_norm": 3.059474229812622, "learning_rate": 4.6099593930327e-05, "loss": 0.8802, "step": 375 }, { "epoch": 0.2405053170224674, "grad_norm": 2.2261245250701904, "learning_rate": 4.608890788630049e-05, "loss": 0.7075, "step": 376 }, { "epoch": 0.24114495882305909, "grad_norm": 2.6875627040863037, "learning_rate": 4.6078221842274e-05, "loss": 0.8127, "step": 377 }, { "epoch": 0.24178460062365076, "grad_norm": 3.2723631858825684, "learning_rate": 4.606753579824749e-05, "loss": 1.087, "step": 378 }, { "epoch": 0.24242424242424243, "grad_norm": 2.5249931812286377, "learning_rate": 4.605684975422099e-05, "loss": 0.7964, "step": 379 }, { "epoch": 0.2430638842248341, "grad_norm": 2.862531900405884, "learning_rate": 4.604616371019449e-05, "loss": 0.9279, "step": 380 }, { "epoch": 0.24370352602542575, "grad_norm": 2.866821527481079, "learning_rate": 4.603547766616799e-05, "loss": 0.8377, "step": 381 }, { "epoch": 0.24434316782601742, "grad_norm": 2.5239150524139404, "learning_rate": 4.602479162214148e-05, "loss": 0.8168, "step": 382 }, { "epoch": 0.2449828096266091, "grad_norm": 2.564471960067749, "learning_rate": 4.6014105578114987e-05, "loss": 0.835, "step": 383 }, { "epoch": 0.24562245142720077, "grad_norm": 2.5914828777313232, "learning_rate": 4.600341953408848e-05, "loss": 0.8291, "step": 384 }, { "epoch": 0.24626209322779244, "grad_norm": 2.713080644607544, "learning_rate": 4.599273349006198e-05, "loss": 0.8057, "step": 385 }, { "epoch": 0.2469017350283841, "grad_norm": 2.5737624168395996, "learning_rate": 4.598204744603548e-05, "loss": 0.8268, "step": 386 }, { "epoch": 0.24754137682897578, "grad_norm": 2.7671921253204346, "learning_rate": 4.597136140200898e-05, "loss": 0.9292, "step": 387 }, { "epoch": 0.24818101862956743, "grad_norm": 2.4558112621307373, "learning_rate": 4.5960675357982477e-05, "loss": 0.7355, "step": 388 }, { "epoch": 0.2488206604301591, "grad_norm": 2.8342125415802, "learning_rate": 4.5949989313955976e-05, "loss": 0.9629, "step": 389 }, { "epoch": 0.24946030223075077, "grad_norm": 2.3475425243377686, "learning_rate": 4.5939303269929475e-05, "loss": 0.7883, "step": 390 }, { "epoch": 0.25009994403134245, "grad_norm": 2.593355655670166, "learning_rate": 4.5928617225902975e-05, "loss": 0.7518, "step": 391 }, { "epoch": 0.2507395858319341, "grad_norm": 2.8946495056152344, "learning_rate": 4.5917931181876474e-05, "loss": 0.9147, "step": 392 }, { "epoch": 0.2513792276325258, "grad_norm": 2.570875406265259, "learning_rate": 4.590724513784997e-05, "loss": 0.7989, "step": 393 }, { "epoch": 0.25201886943311747, "grad_norm": 2.8372998237609863, "learning_rate": 4.589655909382347e-05, "loss": 0.7927, "step": 394 }, { "epoch": 0.25265851123370914, "grad_norm": 2.7271525859832764, "learning_rate": 4.5885873049796965e-05, "loss": 0.872, "step": 395 }, { "epoch": 0.2532981530343008, "grad_norm": 2.768200397491455, "learning_rate": 4.5875187005770465e-05, "loss": 0.7903, "step": 396 }, { "epoch": 0.2539377948348925, "grad_norm": 2.891479253768921, "learning_rate": 4.5864500961743964e-05, "loss": 0.8306, "step": 397 }, { "epoch": 0.25457743663548416, "grad_norm": 2.669311761856079, "learning_rate": 4.5853814917717463e-05, "loss": 0.8316, "step": 398 }, { "epoch": 0.2552170784360758, "grad_norm": 2.4247336387634277, "learning_rate": 4.584312887369096e-05, "loss": 0.7606, "step": 399 }, { "epoch": 0.25585672023666745, "grad_norm": 2.8361196517944336, "learning_rate": 4.583244282966446e-05, "loss": 0.9152, "step": 400 }, { "epoch": 0.2564963620372591, "grad_norm": 2.529350519180298, "learning_rate": 4.582175678563796e-05, "loss": 0.7546, "step": 401 }, { "epoch": 0.2571360038378508, "grad_norm": 2.8802082538604736, "learning_rate": 4.5811070741611454e-05, "loss": 0.9035, "step": 402 }, { "epoch": 0.25777564563844246, "grad_norm": 2.907050132751465, "learning_rate": 4.580038469758496e-05, "loss": 0.9008, "step": 403 }, { "epoch": 0.25841528743903414, "grad_norm": 2.8581337928771973, "learning_rate": 4.578969865355845e-05, "loss": 0.8454, "step": 404 }, { "epoch": 0.2590549292396258, "grad_norm": 2.6416478157043457, "learning_rate": 4.577901260953195e-05, "loss": 0.8683, "step": 405 }, { "epoch": 0.2596945710402175, "grad_norm": 2.726173162460327, "learning_rate": 4.576832656550545e-05, "loss": 0.7448, "step": 406 }, { "epoch": 0.26033421284080915, "grad_norm": 2.6585590839385986, "learning_rate": 4.575764052147895e-05, "loss": 0.7702, "step": 407 }, { "epoch": 0.2609738546414008, "grad_norm": 2.6481173038482666, "learning_rate": 4.574695447745245e-05, "loss": 0.8915, "step": 408 }, { "epoch": 0.2616134964419925, "grad_norm": 2.8057031631469727, "learning_rate": 4.573626843342595e-05, "loss": 0.7919, "step": 409 }, { "epoch": 0.26225313824258417, "grad_norm": 2.424503803253174, "learning_rate": 4.572558238939945e-05, "loss": 0.7658, "step": 410 }, { "epoch": 0.26289278004317584, "grad_norm": 2.7346384525299072, "learning_rate": 4.571489634537294e-05, "loss": 0.9483, "step": 411 }, { "epoch": 0.2635324218437675, "grad_norm": 2.6265981197357178, "learning_rate": 4.570421030134645e-05, "loss": 0.8086, "step": 412 }, { "epoch": 0.26417206364435913, "grad_norm": 2.5911974906921387, "learning_rate": 4.569352425731994e-05, "loss": 0.8003, "step": 413 }, { "epoch": 0.2648117054449508, "grad_norm": 2.497795343399048, "learning_rate": 4.568283821329344e-05, "loss": 0.8405, "step": 414 }, { "epoch": 0.2654513472455425, "grad_norm": 2.5634653568267822, "learning_rate": 4.567215216926694e-05, "loss": 0.7734, "step": 415 }, { "epoch": 0.26609098904613415, "grad_norm": 2.757187843322754, "learning_rate": 4.566146612524044e-05, "loss": 0.9181, "step": 416 }, { "epoch": 0.2667306308467258, "grad_norm": 2.64090633392334, "learning_rate": 4.565078008121393e-05, "loss": 0.8195, "step": 417 }, { "epoch": 0.2673702726473175, "grad_norm": 2.511357069015503, "learning_rate": 4.564009403718744e-05, "loss": 0.7861, "step": 418 }, { "epoch": 0.26800991444790917, "grad_norm": 2.4804275035858154, "learning_rate": 4.562940799316093e-05, "loss": 0.789, "step": 419 }, { "epoch": 0.26864955624850084, "grad_norm": 2.790694236755371, "learning_rate": 4.5618721949134436e-05, "loss": 0.6871, "step": 420 }, { "epoch": 0.2692891980490925, "grad_norm": 2.5106687545776367, "learning_rate": 4.5608035905107935e-05, "loss": 0.758, "step": 421 }, { "epoch": 0.2699288398496842, "grad_norm": 2.534241199493408, "learning_rate": 4.559734986108143e-05, "loss": 0.8383, "step": 422 }, { "epoch": 0.27056848165027586, "grad_norm": 2.6573526859283447, "learning_rate": 4.5586663817054934e-05, "loss": 0.7304, "step": 423 }, { "epoch": 0.27120812345086753, "grad_norm": 2.482849359512329, "learning_rate": 4.5575977773028427e-05, "loss": 0.75, "step": 424 }, { "epoch": 0.2718477652514592, "grad_norm": 2.5034193992614746, "learning_rate": 4.5565291729001926e-05, "loss": 0.7602, "step": 425 }, { "epoch": 0.2724874070520509, "grad_norm": 2.8357973098754883, "learning_rate": 4.5554605684975425e-05, "loss": 0.8598, "step": 426 }, { "epoch": 0.2731270488526425, "grad_norm": 2.5167903900146484, "learning_rate": 4.5543919640948925e-05, "loss": 0.8883, "step": 427 }, { "epoch": 0.27376669065323417, "grad_norm": 2.647885322570801, "learning_rate": 4.553323359692242e-05, "loss": 0.8711, "step": 428 }, { "epoch": 0.27440633245382584, "grad_norm": 2.8058571815490723, "learning_rate": 4.552254755289592e-05, "loss": 0.9287, "step": 429 }, { "epoch": 0.2750459742544175, "grad_norm": 2.494300603866577, "learning_rate": 4.5511861508869416e-05, "loss": 0.7829, "step": 430 }, { "epoch": 0.2756856160550092, "grad_norm": 2.3351948261260986, "learning_rate": 4.5501175464842915e-05, "loss": 0.7023, "step": 431 }, { "epoch": 0.27632525785560086, "grad_norm": 2.4500770568847656, "learning_rate": 4.5490489420816415e-05, "loss": 0.7681, "step": 432 }, { "epoch": 0.27696489965619253, "grad_norm": 2.6197237968444824, "learning_rate": 4.5479803376789914e-05, "loss": 0.862, "step": 433 }, { "epoch": 0.2776045414567842, "grad_norm": 2.4630415439605713, "learning_rate": 4.546911733276341e-05, "loss": 0.714, "step": 434 }, { "epoch": 0.2782441832573759, "grad_norm": 2.408474922180176, "learning_rate": 4.545843128873691e-05, "loss": 0.7727, "step": 435 }, { "epoch": 0.27888382505796755, "grad_norm": 2.6363437175750732, "learning_rate": 4.544774524471041e-05, "loss": 0.7386, "step": 436 }, { "epoch": 0.2795234668585592, "grad_norm": 2.4919941425323486, "learning_rate": 4.5437059200683905e-05, "loss": 0.7964, "step": 437 }, { "epoch": 0.2801631086591509, "grad_norm": 2.2515480518341064, "learning_rate": 4.542637315665741e-05, "loss": 0.7267, "step": 438 }, { "epoch": 0.28080275045974257, "grad_norm": 2.4243528842926025, "learning_rate": 4.5415687112630903e-05, "loss": 0.7142, "step": 439 }, { "epoch": 0.28144239226033424, "grad_norm": 2.6440441608428955, "learning_rate": 4.54050010686044e-05, "loss": 0.7376, "step": 440 }, { "epoch": 0.28208203406092586, "grad_norm": 2.3073890209198, "learning_rate": 4.53943150245779e-05, "loss": 0.7706, "step": 441 }, { "epoch": 0.28272167586151753, "grad_norm": 2.70876407623291, "learning_rate": 4.53836289805514e-05, "loss": 0.8541, "step": 442 }, { "epoch": 0.2833613176621092, "grad_norm": 2.3511955738067627, "learning_rate": 4.53729429365249e-05, "loss": 0.7319, "step": 443 }, { "epoch": 0.2840009594627009, "grad_norm": 2.6385610103607178, "learning_rate": 4.53622568924984e-05, "loss": 0.7293, "step": 444 }, { "epoch": 0.28464060126329255, "grad_norm": 2.6569063663482666, "learning_rate": 4.53515708484719e-05, "loss": 0.8382, "step": 445 }, { "epoch": 0.2852802430638842, "grad_norm": 2.4706740379333496, "learning_rate": 4.534088480444539e-05, "loss": 0.726, "step": 446 }, { "epoch": 0.2859198848644759, "grad_norm": 2.933239459991455, "learning_rate": 4.53301987604189e-05, "loss": 0.9803, "step": 447 }, { "epoch": 0.28655952666506757, "grad_norm": 2.9820454120635986, "learning_rate": 4.531951271639239e-05, "loss": 1.0244, "step": 448 }, { "epoch": 0.28719916846565924, "grad_norm": 2.8230414390563965, "learning_rate": 4.53088266723659e-05, "loss": 0.837, "step": 449 }, { "epoch": 0.2878388102662509, "grad_norm": 2.7445719242095947, "learning_rate": 4.529814062833939e-05, "loss": 0.9338, "step": 450 }, { "epoch": 0.2884784520668426, "grad_norm": 2.9792659282684326, "learning_rate": 4.528745458431289e-05, "loss": 0.9416, "step": 451 }, { "epoch": 0.28911809386743426, "grad_norm": 2.9139254093170166, "learning_rate": 4.527676854028639e-05, "loss": 0.8946, "step": 452 }, { "epoch": 0.28975773566802593, "grad_norm": 2.4100377559661865, "learning_rate": 4.526608249625989e-05, "loss": 0.7475, "step": 453 }, { "epoch": 0.2903973774686176, "grad_norm": 2.572016954421997, "learning_rate": 4.525539645223339e-05, "loss": 0.7986, "step": 454 }, { "epoch": 0.2910370192692092, "grad_norm": 2.9937071800231934, "learning_rate": 4.5244710408206886e-05, "loss": 0.9822, "step": 455 }, { "epoch": 0.2916766610698009, "grad_norm": 2.890455722808838, "learning_rate": 4.5234024364180386e-05, "loss": 0.9258, "step": 456 }, { "epoch": 0.29231630287039256, "grad_norm": 2.4596166610717773, "learning_rate": 4.522333832015388e-05, "loss": 0.75, "step": 457 }, { "epoch": 0.29295594467098424, "grad_norm": 2.647298812866211, "learning_rate": 4.5212652276127385e-05, "loss": 0.8474, "step": 458 }, { "epoch": 0.2935955864715759, "grad_norm": 2.4020044803619385, "learning_rate": 4.520196623210088e-05, "loss": 0.7695, "step": 459 }, { "epoch": 0.2942352282721676, "grad_norm": 2.337449312210083, "learning_rate": 4.5191280188074376e-05, "loss": 0.8351, "step": 460 }, { "epoch": 0.29487487007275925, "grad_norm": 2.482130527496338, "learning_rate": 4.5180594144047876e-05, "loss": 0.859, "step": 461 }, { "epoch": 0.2955145118733509, "grad_norm": 2.4470834732055664, "learning_rate": 4.5169908100021375e-05, "loss": 0.7388, "step": 462 }, { "epoch": 0.2961541536739426, "grad_norm": 2.231738805770874, "learning_rate": 4.515922205599487e-05, "loss": 0.6551, "step": 463 }, { "epoch": 0.29679379547453427, "grad_norm": 2.5150177478790283, "learning_rate": 4.5148536011968374e-05, "loss": 0.8901, "step": 464 }, { "epoch": 0.29743343727512594, "grad_norm": 2.5069150924682617, "learning_rate": 4.5137849967941866e-05, "loss": 0.7837, "step": 465 }, { "epoch": 0.2980730790757176, "grad_norm": 2.964963674545288, "learning_rate": 4.5127163923915366e-05, "loss": 1.016, "step": 466 }, { "epoch": 0.2987127208763093, "grad_norm": 3.0640437602996826, "learning_rate": 4.511647787988887e-05, "loss": 0.96, "step": 467 }, { "epoch": 0.29935236267690096, "grad_norm": 2.9575908184051514, "learning_rate": 4.5105791835862365e-05, "loss": 0.8377, "step": 468 }, { "epoch": 0.2999920044774926, "grad_norm": 2.550337076187134, "learning_rate": 4.5095105791835864e-05, "loss": 0.8829, "step": 469 }, { "epoch": 0.30063164627808425, "grad_norm": 2.4377126693725586, "learning_rate": 4.508441974780936e-05, "loss": 0.7808, "step": 470 }, { "epoch": 0.3012712880786759, "grad_norm": 3.052569627761841, "learning_rate": 4.507373370378286e-05, "loss": 0.9143, "step": 471 }, { "epoch": 0.3019109298792676, "grad_norm": 2.787297487258911, "learning_rate": 4.5063047659756355e-05, "loss": 0.8985, "step": 472 }, { "epoch": 0.30255057167985927, "grad_norm": 2.5775625705718994, "learning_rate": 4.505236161572986e-05, "loss": 0.8606, "step": 473 }, { "epoch": 0.30319021348045094, "grad_norm": 2.481354236602783, "learning_rate": 4.5041675571703354e-05, "loss": 0.8308, "step": 474 }, { "epoch": 0.3038298552810426, "grad_norm": 2.566333532333374, "learning_rate": 4.503098952767685e-05, "loss": 0.7915, "step": 475 }, { "epoch": 0.3044694970816343, "grad_norm": 2.772073984146118, "learning_rate": 4.502030348365035e-05, "loss": 0.9494, "step": 476 }, { "epoch": 0.30510913888222596, "grad_norm": 2.6241090297698975, "learning_rate": 4.500961743962385e-05, "loss": 0.8687, "step": 477 }, { "epoch": 0.30574878068281763, "grad_norm": 2.497037649154663, "learning_rate": 4.499893139559735e-05, "loss": 0.8067, "step": 478 }, { "epoch": 0.3063884224834093, "grad_norm": 2.2416837215423584, "learning_rate": 4.498824535157085e-05, "loss": 0.7778, "step": 479 }, { "epoch": 0.307028064284001, "grad_norm": 2.4029901027679443, "learning_rate": 4.497755930754435e-05, "loss": 0.7819, "step": 480 }, { "epoch": 0.30766770608459265, "grad_norm": 2.4983389377593994, "learning_rate": 4.496687326351785e-05, "loss": 0.8115, "step": 481 }, { "epoch": 0.3083073478851843, "grad_norm": 2.6600162982940674, "learning_rate": 4.495618721949135e-05, "loss": 0.8323, "step": 482 }, { "epoch": 0.30894698968577594, "grad_norm": 2.304379940032959, "learning_rate": 4.494550117546484e-05, "loss": 0.7997, "step": 483 }, { "epoch": 0.3095866314863676, "grad_norm": 2.4892849922180176, "learning_rate": 4.493481513143835e-05, "loss": 0.6917, "step": 484 }, { "epoch": 0.3102262732869593, "grad_norm": 2.624267578125, "learning_rate": 4.492412908741184e-05, "loss": 0.8025, "step": 485 }, { "epoch": 0.31086591508755096, "grad_norm": 2.465531349182129, "learning_rate": 4.491344304338534e-05, "loss": 0.809, "step": 486 }, { "epoch": 0.31150555688814263, "grad_norm": 2.4929726123809814, "learning_rate": 4.490275699935884e-05, "loss": 0.7541, "step": 487 }, { "epoch": 0.3121451986887343, "grad_norm": 2.432112216949463, "learning_rate": 4.489207095533234e-05, "loss": 0.7769, "step": 488 }, { "epoch": 0.312784840489326, "grad_norm": 2.6986589431762695, "learning_rate": 4.488138491130584e-05, "loss": 0.8269, "step": 489 }, { "epoch": 0.31342448228991765, "grad_norm": 2.663753032684326, "learning_rate": 4.487069886727934e-05, "loss": 0.6985, "step": 490 }, { "epoch": 0.3140641240905093, "grad_norm": 2.7952847480773926, "learning_rate": 4.4860012823252836e-05, "loss": 0.8281, "step": 491 }, { "epoch": 0.314703765891101, "grad_norm": 2.578540086746216, "learning_rate": 4.484932677922633e-05, "loss": 0.8079, "step": 492 }, { "epoch": 0.31534340769169267, "grad_norm": 2.872422456741333, "learning_rate": 4.4838640735199835e-05, "loss": 0.8898, "step": 493 }, { "epoch": 0.31598304949228434, "grad_norm": 2.4779903888702393, "learning_rate": 4.482795469117333e-05, "loss": 0.8286, "step": 494 }, { "epoch": 0.316622691292876, "grad_norm": 2.6066203117370605, "learning_rate": 4.481726864714683e-05, "loss": 0.7893, "step": 495 }, { "epoch": 0.3172623330934677, "grad_norm": 2.8848042488098145, "learning_rate": 4.4806582603120326e-05, "loss": 0.8778, "step": 496 }, { "epoch": 0.3179019748940593, "grad_norm": 2.7134692668914795, "learning_rate": 4.4795896559093826e-05, "loss": 0.8456, "step": 497 }, { "epoch": 0.318541616694651, "grad_norm": 2.522134780883789, "learning_rate": 4.4785210515067325e-05, "loss": 0.7932, "step": 498 }, { "epoch": 0.31918125849524265, "grad_norm": 2.80462908744812, "learning_rate": 4.4774524471040824e-05, "loss": 0.904, "step": 499 }, { "epoch": 0.3198209002958343, "grad_norm": 2.497408151626587, "learning_rate": 4.4763838427014324e-05, "loss": 0.7034, "step": 500 }, { "epoch": 0.320460542096426, "grad_norm": 2.8543717861175537, "learning_rate": 4.4753152382987816e-05, "loss": 0.952, "step": 501 }, { "epoch": 0.32110018389701767, "grad_norm": 2.526951789855957, "learning_rate": 4.474246633896132e-05, "loss": 0.707, "step": 502 }, { "epoch": 0.32173982569760934, "grad_norm": 2.8484466075897217, "learning_rate": 4.4731780294934815e-05, "loss": 0.7867, "step": 503 }, { "epoch": 0.322379467498201, "grad_norm": 2.264899253845215, "learning_rate": 4.472109425090832e-05, "loss": 0.7351, "step": 504 }, { "epoch": 0.3230191092987927, "grad_norm": 2.4186136722564697, "learning_rate": 4.4710408206881814e-05, "loss": 0.8134, "step": 505 }, { "epoch": 0.32365875109938436, "grad_norm": 2.5458221435546875, "learning_rate": 4.469972216285531e-05, "loss": 0.8059, "step": 506 }, { "epoch": 0.32429839289997603, "grad_norm": 2.675720691680908, "learning_rate": 4.468903611882881e-05, "loss": 0.9216, "step": 507 }, { "epoch": 0.3249380347005677, "grad_norm": 2.3849453926086426, "learning_rate": 4.467835007480231e-05, "loss": 0.7255, "step": 508 }, { "epoch": 0.3255776765011594, "grad_norm": 2.522523880004883, "learning_rate": 4.4667664030775805e-05, "loss": 0.764, "step": 509 }, { "epoch": 0.32621731830175105, "grad_norm": 2.300499677658081, "learning_rate": 4.465697798674931e-05, "loss": 0.6444, "step": 510 }, { "epoch": 0.32685696010234266, "grad_norm": 2.8246982097625732, "learning_rate": 4.46462919427228e-05, "loss": 0.8461, "step": 511 }, { "epoch": 0.32749660190293434, "grad_norm": 2.3655967712402344, "learning_rate": 4.46356058986963e-05, "loss": 0.7246, "step": 512 }, { "epoch": 0.328136243703526, "grad_norm": 2.973665952682495, "learning_rate": 4.462491985466981e-05, "loss": 0.8732, "step": 513 }, { "epoch": 0.3287758855041177, "grad_norm": 2.558032751083374, "learning_rate": 4.46142338106433e-05, "loss": 0.7513, "step": 514 }, { "epoch": 0.32941552730470935, "grad_norm": 2.8842430114746094, "learning_rate": 4.46035477666168e-05, "loss": 0.7467, "step": 515 }, { "epoch": 0.330055169105301, "grad_norm": 2.5235350131988525, "learning_rate": 4.45928617225903e-05, "loss": 0.7728, "step": 516 }, { "epoch": 0.3306948109058927, "grad_norm": 2.788074493408203, "learning_rate": 4.45821756785638e-05, "loss": 0.8571, "step": 517 }, { "epoch": 0.3313344527064844, "grad_norm": 2.650552749633789, "learning_rate": 4.457148963453729e-05, "loss": 0.8053, "step": 518 }, { "epoch": 0.33197409450707605, "grad_norm": 2.4916484355926514, "learning_rate": 4.45608035905108e-05, "loss": 0.7712, "step": 519 }, { "epoch": 0.3326137363076677, "grad_norm": 2.484419822692871, "learning_rate": 4.455011754648429e-05, "loss": 0.797, "step": 520 }, { "epoch": 0.3332533781082594, "grad_norm": 2.747328996658325, "learning_rate": 4.453943150245779e-05, "loss": 0.8449, "step": 521 }, { "epoch": 0.33389301990885106, "grad_norm": 2.469801187515259, "learning_rate": 4.452874545843129e-05, "loss": 0.8487, "step": 522 }, { "epoch": 0.33453266170944274, "grad_norm": 2.670841932296753, "learning_rate": 4.451805941440479e-05, "loss": 0.8178, "step": 523 }, { "epoch": 0.3351723035100344, "grad_norm": 2.2457292079925537, "learning_rate": 4.450737337037829e-05, "loss": 0.7296, "step": 524 }, { "epoch": 0.335811945310626, "grad_norm": 2.5042967796325684, "learning_rate": 4.449668732635179e-05, "loss": 0.8448, "step": 525 }, { "epoch": 0.3364515871112177, "grad_norm": 2.4827215671539307, "learning_rate": 4.448600128232529e-05, "loss": 0.8862, "step": 526 }, { "epoch": 0.33709122891180937, "grad_norm": 2.4088759422302246, "learning_rate": 4.447531523829878e-05, "loss": 0.7664, "step": 527 }, { "epoch": 0.33773087071240104, "grad_norm": 2.49212646484375, "learning_rate": 4.4464629194272286e-05, "loss": 0.8548, "step": 528 }, { "epoch": 0.3383705125129927, "grad_norm": 2.1127588748931885, "learning_rate": 4.445394315024578e-05, "loss": 0.7091, "step": 529 }, { "epoch": 0.3390101543135844, "grad_norm": 2.767030715942383, "learning_rate": 4.444325710621928e-05, "loss": 0.9049, "step": 530 }, { "epoch": 0.33964979611417606, "grad_norm": 2.315673828125, "learning_rate": 4.443257106219278e-05, "loss": 0.7995, "step": 531 }, { "epoch": 0.34028943791476773, "grad_norm": 2.6289587020874023, "learning_rate": 4.4421885018166276e-05, "loss": 0.8373, "step": 532 }, { "epoch": 0.3409290797153594, "grad_norm": 2.2535407543182373, "learning_rate": 4.4411198974139776e-05, "loss": 0.7047, "step": 533 }, { "epoch": 0.3415687215159511, "grad_norm": 2.6374125480651855, "learning_rate": 4.4400512930113275e-05, "loss": 0.7812, "step": 534 }, { "epoch": 0.34220836331654275, "grad_norm": 2.6607789993286133, "learning_rate": 4.4389826886086774e-05, "loss": 0.761, "step": 535 }, { "epoch": 0.3428480051171344, "grad_norm": 2.724668264389038, "learning_rate": 4.4379140842060274e-05, "loss": 0.7987, "step": 536 }, { "epoch": 0.3434876469177261, "grad_norm": 2.52717924118042, "learning_rate": 4.436845479803377e-05, "loss": 0.7947, "step": 537 }, { "epoch": 0.34412728871831777, "grad_norm": 2.9766016006469727, "learning_rate": 4.4357768754007266e-05, "loss": 0.8849, "step": 538 }, { "epoch": 0.3447669305189094, "grad_norm": 2.571988582611084, "learning_rate": 4.434708270998077e-05, "loss": 0.7992, "step": 539 }, { "epoch": 0.34540657231950106, "grad_norm": 2.6817004680633545, "learning_rate": 4.4336396665954264e-05, "loss": 0.7466, "step": 540 }, { "epoch": 0.34604621412009273, "grad_norm": 2.3611767292022705, "learning_rate": 4.4325710621927764e-05, "loss": 0.7875, "step": 541 }, { "epoch": 0.3466858559206844, "grad_norm": 2.5309157371520996, "learning_rate": 4.431502457790126e-05, "loss": 0.8233, "step": 542 }, { "epoch": 0.3473254977212761, "grad_norm": 2.8166468143463135, "learning_rate": 4.430433853387476e-05, "loss": 0.8753, "step": 543 }, { "epoch": 0.34796513952186775, "grad_norm": 2.665196180343628, "learning_rate": 4.429365248984826e-05, "loss": 0.8156, "step": 544 }, { "epoch": 0.3486047813224594, "grad_norm": 2.1333603858947754, "learning_rate": 4.428296644582176e-05, "loss": 0.695, "step": 545 }, { "epoch": 0.3492444231230511, "grad_norm": 2.1260366439819336, "learning_rate": 4.427228040179526e-05, "loss": 0.7013, "step": 546 }, { "epoch": 0.34988406492364277, "grad_norm": 2.301292657852173, "learning_rate": 4.426159435776875e-05, "loss": 0.7797, "step": 547 }, { "epoch": 0.35052370672423444, "grad_norm": 2.5352783203125, "learning_rate": 4.425090831374226e-05, "loss": 0.8562, "step": 548 }, { "epoch": 0.3511633485248261, "grad_norm": 2.4450230598449707, "learning_rate": 4.424022226971575e-05, "loss": 0.8164, "step": 549 }, { "epoch": 0.3518029903254178, "grad_norm": 2.4418418407440186, "learning_rate": 4.422953622568925e-05, "loss": 0.6877, "step": 550 }, { "epoch": 0.35244263212600946, "grad_norm": 2.504390001296997, "learning_rate": 4.421885018166275e-05, "loss": 0.7671, "step": 551 }, { "epoch": 0.3530822739266011, "grad_norm": 2.4340758323669434, "learning_rate": 4.420816413763625e-05, "loss": 0.8134, "step": 552 }, { "epoch": 0.35372191572719275, "grad_norm": 2.650157928466797, "learning_rate": 4.419747809360974e-05, "loss": 0.9067, "step": 553 }, { "epoch": 0.3543615575277844, "grad_norm": 2.4354360103607178, "learning_rate": 4.418679204958325e-05, "loss": 0.8253, "step": 554 }, { "epoch": 0.3550011993283761, "grad_norm": 2.449326992034912, "learning_rate": 4.417610600555674e-05, "loss": 0.7755, "step": 555 }, { "epoch": 0.35564084112896777, "grad_norm": 2.734926700592041, "learning_rate": 4.416541996153024e-05, "loss": 0.838, "step": 556 }, { "epoch": 0.35628048292955944, "grad_norm": 2.658278703689575, "learning_rate": 4.415473391750374e-05, "loss": 0.8729, "step": 557 }, { "epoch": 0.3569201247301511, "grad_norm": 2.790825366973877, "learning_rate": 4.414404787347724e-05, "loss": 0.8542, "step": 558 }, { "epoch": 0.3575597665307428, "grad_norm": 2.4853923320770264, "learning_rate": 4.413336182945074e-05, "loss": 0.7759, "step": 559 }, { "epoch": 0.35819940833133446, "grad_norm": 2.8261659145355225, "learning_rate": 4.412267578542424e-05, "loss": 0.9195, "step": 560 }, { "epoch": 0.35883905013192613, "grad_norm": 2.0461819171905518, "learning_rate": 4.411198974139774e-05, "loss": 0.6423, "step": 561 }, { "epoch": 0.3594786919325178, "grad_norm": 2.6489789485931396, "learning_rate": 4.410130369737124e-05, "loss": 0.8877, "step": 562 }, { "epoch": 0.3601183337331095, "grad_norm": 2.5838587284088135, "learning_rate": 4.4090617653344736e-05, "loss": 0.7386, "step": 563 }, { "epoch": 0.36075797553370115, "grad_norm": 2.292025566101074, "learning_rate": 4.407993160931823e-05, "loss": 0.767, "step": 564 }, { "epoch": 0.3613976173342928, "grad_norm": 2.5135250091552734, "learning_rate": 4.4069245565291735e-05, "loss": 0.7544, "step": 565 }, { "epoch": 0.36203725913488444, "grad_norm": 2.694716691970825, "learning_rate": 4.405855952126523e-05, "loss": 0.9038, "step": 566 }, { "epoch": 0.3626769009354761, "grad_norm": 2.45570969581604, "learning_rate": 4.404787347723873e-05, "loss": 0.7544, "step": 567 }, { "epoch": 0.3633165427360678, "grad_norm": 2.5258474349975586, "learning_rate": 4.4037187433212226e-05, "loss": 0.8299, "step": 568 }, { "epoch": 0.36395618453665946, "grad_norm": 2.649857759475708, "learning_rate": 4.4026501389185726e-05, "loss": 0.7911, "step": 569 }, { "epoch": 0.3645958263372511, "grad_norm": 2.8530423641204834, "learning_rate": 4.4015815345159225e-05, "loss": 0.8102, "step": 570 }, { "epoch": 0.3652354681378428, "grad_norm": 2.6826438903808594, "learning_rate": 4.4005129301132724e-05, "loss": 0.8136, "step": 571 }, { "epoch": 0.3658751099384345, "grad_norm": 2.5145070552825928, "learning_rate": 4.3994443257106224e-05, "loss": 0.7439, "step": 572 }, { "epoch": 0.36651475173902615, "grad_norm": 2.6360299587249756, "learning_rate": 4.3983757213079716e-05, "loss": 0.6884, "step": 573 }, { "epoch": 0.3671543935396178, "grad_norm": 2.543938636779785, "learning_rate": 4.397307116905322e-05, "loss": 0.7776, "step": 574 }, { "epoch": 0.3677940353402095, "grad_norm": 2.270566940307617, "learning_rate": 4.3962385125026715e-05, "loss": 0.6941, "step": 575 }, { "epoch": 0.36843367714080116, "grad_norm": 2.6573848724365234, "learning_rate": 4.3951699081000214e-05, "loss": 0.8608, "step": 576 }, { "epoch": 0.36907331894139284, "grad_norm": 2.537231683731079, "learning_rate": 4.3941013036973714e-05, "loss": 0.8478, "step": 577 }, { "epoch": 0.3697129607419845, "grad_norm": 2.367879867553711, "learning_rate": 4.393032699294721e-05, "loss": 0.7484, "step": 578 }, { "epoch": 0.3703526025425762, "grad_norm": 3.0089163780212402, "learning_rate": 4.391964094892071e-05, "loss": 0.9008, "step": 579 }, { "epoch": 0.3709922443431678, "grad_norm": 2.5588526725769043, "learning_rate": 4.390895490489421e-05, "loss": 0.836, "step": 580 }, { "epoch": 0.37163188614375947, "grad_norm": 2.2014873027801514, "learning_rate": 4.389826886086771e-05, "loss": 0.7329, "step": 581 }, { "epoch": 0.37227152794435114, "grad_norm": 2.430637836456299, "learning_rate": 4.3887582816841204e-05, "loss": 0.7465, "step": 582 }, { "epoch": 0.3729111697449428, "grad_norm": 2.7012386322021484, "learning_rate": 4.387689677281471e-05, "loss": 0.835, "step": 583 }, { "epoch": 0.3735508115455345, "grad_norm": 2.56974720954895, "learning_rate": 4.38662107287882e-05, "loss": 0.8503, "step": 584 }, { "epoch": 0.37419045334612616, "grad_norm": 2.5912535190582275, "learning_rate": 4.38555246847617e-05, "loss": 0.8007, "step": 585 }, { "epoch": 0.37483009514671783, "grad_norm": 2.491722345352173, "learning_rate": 4.38448386407352e-05, "loss": 0.8769, "step": 586 }, { "epoch": 0.3754697369473095, "grad_norm": 2.7597715854644775, "learning_rate": 4.38341525967087e-05, "loss": 0.8429, "step": 587 }, { "epoch": 0.3761093787479012, "grad_norm": 2.3039841651916504, "learning_rate": 4.38234665526822e-05, "loss": 0.7368, "step": 588 }, { "epoch": 0.37674902054849285, "grad_norm": 2.0839362144470215, "learning_rate": 4.38127805086557e-05, "loss": 0.6954, "step": 589 }, { "epoch": 0.3773886623490845, "grad_norm": 1.9851723909378052, "learning_rate": 4.38020944646292e-05, "loss": 0.6272, "step": 590 }, { "epoch": 0.3780283041496762, "grad_norm": 2.592808723449707, "learning_rate": 4.37914084206027e-05, "loss": 0.8367, "step": 591 }, { "epoch": 0.37866794595026787, "grad_norm": 2.5516512393951416, "learning_rate": 4.37807223765762e-05, "loss": 0.8028, "step": 592 }, { "epoch": 0.37930758775085954, "grad_norm": 2.127110004425049, "learning_rate": 4.377003633254969e-05, "loss": 0.6786, "step": 593 }, { "epoch": 0.37994722955145116, "grad_norm": 2.6587941646575928, "learning_rate": 4.3759350288523196e-05, "loss": 0.8044, "step": 594 }, { "epoch": 0.38058687135204283, "grad_norm": 2.694045305252075, "learning_rate": 4.374866424449669e-05, "loss": 0.8164, "step": 595 }, { "epoch": 0.3812265131526345, "grad_norm": 2.5876169204711914, "learning_rate": 4.373797820047019e-05, "loss": 0.7456, "step": 596 }, { "epoch": 0.3818661549532262, "grad_norm": 2.4754750728607178, "learning_rate": 4.372729215644369e-05, "loss": 0.7261, "step": 597 }, { "epoch": 0.38250579675381785, "grad_norm": 2.9321911334991455, "learning_rate": 4.371660611241719e-05, "loss": 0.9218, "step": 598 }, { "epoch": 0.3831454385544095, "grad_norm": 2.8330905437469482, "learning_rate": 4.370592006839068e-05, "loss": 0.9054, "step": 599 }, { "epoch": 0.3837850803550012, "grad_norm": 2.649747371673584, "learning_rate": 4.3695234024364185e-05, "loss": 0.7467, "step": 600 }, { "epoch": 0.38442472215559287, "grad_norm": 2.5304954051971436, "learning_rate": 4.368454798033768e-05, "loss": 0.8089, "step": 601 }, { "epoch": 0.38506436395618454, "grad_norm": 2.575817108154297, "learning_rate": 4.367386193631118e-05, "loss": 0.7682, "step": 602 }, { "epoch": 0.3857040057567762, "grad_norm": 3.011615753173828, "learning_rate": 4.366317589228468e-05, "loss": 0.8105, "step": 603 }, { "epoch": 0.3863436475573679, "grad_norm": 2.668299674987793, "learning_rate": 4.3652489848258176e-05, "loss": 0.8447, "step": 604 }, { "epoch": 0.38698328935795956, "grad_norm": 2.440359592437744, "learning_rate": 4.3641803804231676e-05, "loss": 0.7538, "step": 605 }, { "epoch": 0.38762293115855123, "grad_norm": 2.5039072036743164, "learning_rate": 4.3631117760205175e-05, "loss": 0.7949, "step": 606 }, { "epoch": 0.3882625729591429, "grad_norm": 2.30733585357666, "learning_rate": 4.3620431716178674e-05, "loss": 0.7126, "step": 607 }, { "epoch": 0.3889022147597345, "grad_norm": 2.566895008087158, "learning_rate": 4.360974567215217e-05, "loss": 0.8112, "step": 608 }, { "epoch": 0.3895418565603262, "grad_norm": 2.3991849422454834, "learning_rate": 4.359905962812567e-05, "loss": 0.7751, "step": 609 }, { "epoch": 0.39018149836091787, "grad_norm": 2.2058398723602295, "learning_rate": 4.3588373584099166e-05, "loss": 0.6873, "step": 610 }, { "epoch": 0.39082114016150954, "grad_norm": 2.379000425338745, "learning_rate": 4.3577687540072665e-05, "loss": 0.7854, "step": 611 }, { "epoch": 0.3914607819621012, "grad_norm": 2.1002843379974365, "learning_rate": 4.3567001496046164e-05, "loss": 0.6344, "step": 612 }, { "epoch": 0.3921004237626929, "grad_norm": 2.43048357963562, "learning_rate": 4.3556315452019664e-05, "loss": 0.8256, "step": 613 }, { "epoch": 0.39274006556328456, "grad_norm": 2.9100863933563232, "learning_rate": 4.354562940799316e-05, "loss": 0.844, "step": 614 }, { "epoch": 0.39337970736387623, "grad_norm": 2.8449697494506836, "learning_rate": 4.353494336396666e-05, "loss": 0.9032, "step": 615 }, { "epoch": 0.3940193491644679, "grad_norm": 2.6021840572357178, "learning_rate": 4.352425731994016e-05, "loss": 0.8271, "step": 616 }, { "epoch": 0.3946589909650596, "grad_norm": 2.6643600463867188, "learning_rate": 4.351357127591366e-05, "loss": 0.8255, "step": 617 }, { "epoch": 0.39529863276565125, "grad_norm": 2.3905458450317383, "learning_rate": 4.350288523188716e-05, "loss": 0.7539, "step": 618 }, { "epoch": 0.3959382745662429, "grad_norm": 2.3749024868011475, "learning_rate": 4.349219918786065e-05, "loss": 0.8191, "step": 619 }, { "epoch": 0.3965779163668346, "grad_norm": 2.5093674659729004, "learning_rate": 4.348151314383416e-05, "loss": 0.7669, "step": 620 }, { "epoch": 0.39721755816742627, "grad_norm": 2.4019482135772705, "learning_rate": 4.347082709980765e-05, "loss": 0.7744, "step": 621 }, { "epoch": 0.3978571999680179, "grad_norm": 2.5259127616882324, "learning_rate": 4.346014105578115e-05, "loss": 0.8141, "step": 622 }, { "epoch": 0.39849684176860956, "grad_norm": 2.394785165786743, "learning_rate": 4.344945501175465e-05, "loss": 0.8367, "step": 623 }, { "epoch": 0.39913648356920123, "grad_norm": 2.8428847789764404, "learning_rate": 4.343876896772815e-05, "loss": 0.9098, "step": 624 }, { "epoch": 0.3997761253697929, "grad_norm": 2.2933173179626465, "learning_rate": 4.342808292370165e-05, "loss": 0.8307, "step": 625 }, { "epoch": 0.4004157671703846, "grad_norm": 2.549668073654175, "learning_rate": 4.341739687967515e-05, "loss": 0.799, "step": 626 }, { "epoch": 0.40105540897097625, "grad_norm": 2.5822505950927734, "learning_rate": 4.340671083564865e-05, "loss": 0.9867, "step": 627 }, { "epoch": 0.4016950507715679, "grad_norm": 2.5839316844940186, "learning_rate": 4.339602479162214e-05, "loss": 0.7672, "step": 628 }, { "epoch": 0.4023346925721596, "grad_norm": 2.860914468765259, "learning_rate": 4.338533874759565e-05, "loss": 0.9099, "step": 629 }, { "epoch": 0.40297433437275126, "grad_norm": 2.6417458057403564, "learning_rate": 4.337465270356914e-05, "loss": 0.8955, "step": 630 }, { "epoch": 0.40361397617334294, "grad_norm": 2.3838489055633545, "learning_rate": 4.336396665954264e-05, "loss": 0.7301, "step": 631 }, { "epoch": 0.4042536179739346, "grad_norm": 2.394200325012207, "learning_rate": 4.335328061551614e-05, "loss": 0.7594, "step": 632 }, { "epoch": 0.4048932597745263, "grad_norm": 2.947063684463501, "learning_rate": 4.334259457148964e-05, "loss": 0.9043, "step": 633 }, { "epoch": 0.40553290157511795, "grad_norm": 2.514294147491455, "learning_rate": 4.333190852746313e-05, "loss": 0.8195, "step": 634 }, { "epoch": 0.4061725433757096, "grad_norm": 2.889430284500122, "learning_rate": 4.3321222483436636e-05, "loss": 0.821, "step": 635 }, { "epoch": 0.40681218517630124, "grad_norm": 2.493847370147705, "learning_rate": 4.3310536439410135e-05, "loss": 0.8217, "step": 636 }, { "epoch": 0.4074518269768929, "grad_norm": 2.4664089679718018, "learning_rate": 4.329985039538363e-05, "loss": 0.7581, "step": 637 }, { "epoch": 0.4080914687774846, "grad_norm": 2.623796224594116, "learning_rate": 4.3289164351357134e-05, "loss": 0.9139, "step": 638 }, { "epoch": 0.40873111057807626, "grad_norm": 2.465691328048706, "learning_rate": 4.327847830733063e-05, "loss": 0.8096, "step": 639 }, { "epoch": 0.40937075237866793, "grad_norm": 2.3869857788085938, "learning_rate": 4.3267792263304126e-05, "loss": 0.7679, "step": 640 }, { "epoch": 0.4100103941792596, "grad_norm": 2.521512985229492, "learning_rate": 4.3257106219277625e-05, "loss": 0.7575, "step": 641 }, { "epoch": 0.4106500359798513, "grad_norm": 2.2285306453704834, "learning_rate": 4.3246420175251125e-05, "loss": 0.6798, "step": 642 }, { "epoch": 0.41128967778044295, "grad_norm": 2.48858904838562, "learning_rate": 4.323573413122462e-05, "loss": 0.7829, "step": 643 }, { "epoch": 0.4119293195810346, "grad_norm": 2.2363147735595703, "learning_rate": 4.3225048087198124e-05, "loss": 0.8079, "step": 644 }, { "epoch": 0.4125689613816263, "grad_norm": 2.4952003955841064, "learning_rate": 4.3214362043171616e-05, "loss": 0.8183, "step": 645 }, { "epoch": 0.41320860318221797, "grad_norm": 2.6612093448638916, "learning_rate": 4.320367599914512e-05, "loss": 0.9394, "step": 646 }, { "epoch": 0.41384824498280964, "grad_norm": 2.4674930572509766, "learning_rate": 4.3192989955118615e-05, "loss": 0.7378, "step": 647 }, { "epoch": 0.4144878867834013, "grad_norm": 2.1883046627044678, "learning_rate": 4.3182303911092114e-05, "loss": 0.6946, "step": 648 }, { "epoch": 0.415127528583993, "grad_norm": 2.3450024127960205, "learning_rate": 4.3171617867065614e-05, "loss": 0.6772, "step": 649 }, { "epoch": 0.4157671703845846, "grad_norm": 2.1584982872009277, "learning_rate": 4.316093182303911e-05, "loss": 0.6317, "step": 650 }, { "epoch": 0.4164068121851763, "grad_norm": 2.2315256595611572, "learning_rate": 4.315024577901261e-05, "loss": 0.6715, "step": 651 }, { "epoch": 0.41704645398576795, "grad_norm": 2.278326988220215, "learning_rate": 4.313955973498611e-05, "loss": 0.6759, "step": 652 }, { "epoch": 0.4176860957863596, "grad_norm": 2.892369031906128, "learning_rate": 4.312887369095961e-05, "loss": 0.8931, "step": 653 }, { "epoch": 0.4183257375869513, "grad_norm": 2.7841877937316895, "learning_rate": 4.3118187646933104e-05, "loss": 0.7409, "step": 654 }, { "epoch": 0.41896537938754297, "grad_norm": 2.8826382160186768, "learning_rate": 4.310750160290661e-05, "loss": 0.8583, "step": 655 }, { "epoch": 0.41960502118813464, "grad_norm": 2.4668517112731934, "learning_rate": 4.30968155588801e-05, "loss": 0.7036, "step": 656 }, { "epoch": 0.4202446629887263, "grad_norm": 2.5809171199798584, "learning_rate": 4.30861295148536e-05, "loss": 0.8181, "step": 657 }, { "epoch": 0.420884304789318, "grad_norm": 2.7291839122772217, "learning_rate": 4.30754434708271e-05, "loss": 0.8102, "step": 658 }, { "epoch": 0.42152394658990966, "grad_norm": 2.2775955200195312, "learning_rate": 4.30647574268006e-05, "loss": 0.6718, "step": 659 }, { "epoch": 0.42216358839050133, "grad_norm": 2.565253734588623, "learning_rate": 4.30540713827741e-05, "loss": 0.8058, "step": 660 }, { "epoch": 0.422803230191093, "grad_norm": 2.368832588195801, "learning_rate": 4.30433853387476e-05, "loss": 0.7757, "step": 661 }, { "epoch": 0.4234428719916847, "grad_norm": 2.6588382720947266, "learning_rate": 4.30326992947211e-05, "loss": 0.842, "step": 662 }, { "epoch": 0.42408251379227635, "grad_norm": 2.6485090255737305, "learning_rate": 4.302201325069459e-05, "loss": 0.8455, "step": 663 }, { "epoch": 0.42472215559286797, "grad_norm": 2.6250391006469727, "learning_rate": 4.30113272066681e-05, "loss": 0.866, "step": 664 }, { "epoch": 0.42536179739345964, "grad_norm": 2.5179715156555176, "learning_rate": 4.300064116264159e-05, "loss": 0.795, "step": 665 }, { "epoch": 0.4260014391940513, "grad_norm": 2.139284372329712, "learning_rate": 4.298995511861509e-05, "loss": 0.6789, "step": 666 }, { "epoch": 0.426641080994643, "grad_norm": 2.2436509132385254, "learning_rate": 4.297926907458859e-05, "loss": 0.7285, "step": 667 }, { "epoch": 0.42728072279523466, "grad_norm": 2.4669735431671143, "learning_rate": 4.296858303056209e-05, "loss": 0.7738, "step": 668 }, { "epoch": 0.42792036459582633, "grad_norm": 2.4628779888153076, "learning_rate": 4.295789698653559e-05, "loss": 0.8483, "step": 669 }, { "epoch": 0.428560006396418, "grad_norm": 2.321608543395996, "learning_rate": 4.2947210942509087e-05, "loss": 0.756, "step": 670 }, { "epoch": 0.4291996481970097, "grad_norm": 2.641051769256592, "learning_rate": 4.2936524898482586e-05, "loss": 0.7812, "step": 671 }, { "epoch": 0.42983928999760135, "grad_norm": 2.4621758460998535, "learning_rate": 4.292583885445608e-05, "loss": 0.8161, "step": 672 }, { "epoch": 0.430478931798193, "grad_norm": 2.2134177684783936, "learning_rate": 4.2915152810429585e-05, "loss": 0.6612, "step": 673 }, { "epoch": 0.4311185735987847, "grad_norm": 2.3274316787719727, "learning_rate": 4.290446676640308e-05, "loss": 0.7569, "step": 674 }, { "epoch": 0.43175821539937637, "grad_norm": 2.4170377254486084, "learning_rate": 4.2893780722376583e-05, "loss": 0.891, "step": 675 }, { "epoch": 0.43239785719996804, "grad_norm": 2.400930643081665, "learning_rate": 4.2883094678350076e-05, "loss": 0.7742, "step": 676 }, { "epoch": 0.4330374990005597, "grad_norm": 2.357038974761963, "learning_rate": 4.2872408634323575e-05, "loss": 0.7248, "step": 677 }, { "epoch": 0.43367714080115133, "grad_norm": 2.403651714324951, "learning_rate": 4.2861722590297075e-05, "loss": 0.8527, "step": 678 }, { "epoch": 0.434316782601743, "grad_norm": 2.695835590362549, "learning_rate": 4.2851036546270574e-05, "loss": 0.7556, "step": 679 }, { "epoch": 0.4349564244023347, "grad_norm": 2.6627137660980225, "learning_rate": 4.284035050224407e-05, "loss": 0.8369, "step": 680 }, { "epoch": 0.43559606620292635, "grad_norm": 2.368640661239624, "learning_rate": 4.282966445821757e-05, "loss": 0.6754, "step": 681 }, { "epoch": 0.436235708003518, "grad_norm": 2.3832530975341797, "learning_rate": 4.281897841419107e-05, "loss": 0.7884, "step": 682 }, { "epoch": 0.4368753498041097, "grad_norm": 2.2132256031036377, "learning_rate": 4.2808292370164565e-05, "loss": 0.7255, "step": 683 }, { "epoch": 0.43751499160470136, "grad_norm": 2.579366683959961, "learning_rate": 4.279760632613807e-05, "loss": 0.841, "step": 684 }, { "epoch": 0.43815463340529304, "grad_norm": 2.5500547885894775, "learning_rate": 4.2786920282111563e-05, "loss": 0.8392, "step": 685 }, { "epoch": 0.4387942752058847, "grad_norm": 2.4645004272460938, "learning_rate": 4.277623423808506e-05, "loss": 0.684, "step": 686 }, { "epoch": 0.4394339170064764, "grad_norm": 2.4809513092041016, "learning_rate": 4.276554819405856e-05, "loss": 0.684, "step": 687 }, { "epoch": 0.44007355880706805, "grad_norm": 2.3200199604034424, "learning_rate": 4.275486215003206e-05, "loss": 0.7441, "step": 688 }, { "epoch": 0.4407132006076597, "grad_norm": 2.687345027923584, "learning_rate": 4.2744176106005554e-05, "loss": 0.8809, "step": 689 }, { "epoch": 0.4413528424082514, "grad_norm": 2.7118911743164062, "learning_rate": 4.273349006197906e-05, "loss": 0.786, "step": 690 }, { "epoch": 0.4419924842088431, "grad_norm": 2.361036539077759, "learning_rate": 4.272280401795255e-05, "loss": 0.7542, "step": 691 }, { "epoch": 0.4426321260094347, "grad_norm": 2.331491231918335, "learning_rate": 4.271211797392605e-05, "loss": 0.7253, "step": 692 }, { "epoch": 0.44327176781002636, "grad_norm": 2.825608015060425, "learning_rate": 4.270143192989955e-05, "loss": 0.815, "step": 693 }, { "epoch": 0.44391140961061804, "grad_norm": 2.79476261138916, "learning_rate": 4.269074588587305e-05, "loss": 0.7544, "step": 694 }, { "epoch": 0.4445510514112097, "grad_norm": 2.341146945953369, "learning_rate": 4.268005984184655e-05, "loss": 0.7679, "step": 695 }, { "epoch": 0.4451906932118014, "grad_norm": 2.362579584121704, "learning_rate": 4.266937379782005e-05, "loss": 0.8176, "step": 696 }, { "epoch": 0.44583033501239305, "grad_norm": 2.415343999862671, "learning_rate": 4.265868775379355e-05, "loss": 0.772, "step": 697 }, { "epoch": 0.4464699768129847, "grad_norm": 2.3519582748413086, "learning_rate": 4.264800170976704e-05, "loss": 0.7768, "step": 698 }, { "epoch": 0.4471096186135764, "grad_norm": 2.468914270401001, "learning_rate": 4.263731566574055e-05, "loss": 0.8066, "step": 699 }, { "epoch": 0.44774926041416807, "grad_norm": 2.216883420944214, "learning_rate": 4.262662962171404e-05, "loss": 0.741, "step": 700 }, { "epoch": 0.44838890221475974, "grad_norm": 2.224919319152832, "learning_rate": 4.2615943577687546e-05, "loss": 0.7428, "step": 701 }, { "epoch": 0.4490285440153514, "grad_norm": 2.4262194633483887, "learning_rate": 4.260525753366104e-05, "loss": 0.7415, "step": 702 }, { "epoch": 0.4496681858159431, "grad_norm": 2.3034839630126953, "learning_rate": 4.259457148963454e-05, "loss": 0.7152, "step": 703 }, { "epoch": 0.45030782761653476, "grad_norm": 2.5050270557403564, "learning_rate": 4.258388544560804e-05, "loss": 0.8726, "step": 704 }, { "epoch": 0.45094746941712643, "grad_norm": 2.637089252471924, "learning_rate": 4.257319940158154e-05, "loss": 0.7758, "step": 705 }, { "epoch": 0.45158711121771805, "grad_norm": 2.314626455307007, "learning_rate": 4.2562513357555037e-05, "loss": 0.8125, "step": 706 }, { "epoch": 0.4522267530183097, "grad_norm": 2.5563905239105225, "learning_rate": 4.2551827313528536e-05, "loss": 0.8101, "step": 707 }, { "epoch": 0.4528663948189014, "grad_norm": 2.3011550903320312, "learning_rate": 4.2541141269502035e-05, "loss": 0.7487, "step": 708 }, { "epoch": 0.45350603661949307, "grad_norm": 2.784237861633301, "learning_rate": 4.253045522547553e-05, "loss": 0.8605, "step": 709 }, { "epoch": 0.45414567842008474, "grad_norm": 2.527440309524536, "learning_rate": 4.2519769181449034e-05, "loss": 0.7039, "step": 710 }, { "epoch": 0.4547853202206764, "grad_norm": 2.402970314025879, "learning_rate": 4.2509083137422527e-05, "loss": 0.802, "step": 711 }, { "epoch": 0.4554249620212681, "grad_norm": 2.44575572013855, "learning_rate": 4.2498397093396026e-05, "loss": 0.8497, "step": 712 }, { "epoch": 0.45606460382185976, "grad_norm": 2.604088068008423, "learning_rate": 4.2487711049369525e-05, "loss": 0.8716, "step": 713 }, { "epoch": 0.45670424562245143, "grad_norm": 2.4849510192871094, "learning_rate": 4.2477025005343025e-05, "loss": 0.8625, "step": 714 }, { "epoch": 0.4573438874230431, "grad_norm": 2.149947166442871, "learning_rate": 4.2466338961316524e-05, "loss": 0.6496, "step": 715 }, { "epoch": 0.4579835292236348, "grad_norm": 2.463686227798462, "learning_rate": 4.245565291729002e-05, "loss": 0.8031, "step": 716 }, { "epoch": 0.45862317102422645, "grad_norm": 2.275045156478882, "learning_rate": 4.244496687326352e-05, "loss": 0.7826, "step": 717 }, { "epoch": 0.4592628128248181, "grad_norm": 2.113935947418213, "learning_rate": 4.2434280829237015e-05, "loss": 0.6638, "step": 718 }, { "epoch": 0.4599024546254098, "grad_norm": 2.5344903469085693, "learning_rate": 4.242359478521052e-05, "loss": 0.8024, "step": 719 }, { "epoch": 0.4605420964260014, "grad_norm": 2.180123805999756, "learning_rate": 4.2412908741184014e-05, "loss": 0.6937, "step": 720 }, { "epoch": 0.4611817382265931, "grad_norm": 2.5835466384887695, "learning_rate": 4.2402222697157513e-05, "loss": 0.8583, "step": 721 }, { "epoch": 0.46182138002718476, "grad_norm": 2.340942144393921, "learning_rate": 4.239153665313101e-05, "loss": 0.7583, "step": 722 }, { "epoch": 0.46246102182777643, "grad_norm": 2.4271631240844727, "learning_rate": 4.238085060910451e-05, "loss": 0.7599, "step": 723 }, { "epoch": 0.4631006636283681, "grad_norm": 2.501920223236084, "learning_rate": 4.2370164565078005e-05, "loss": 0.8234, "step": 724 }, { "epoch": 0.4637403054289598, "grad_norm": 2.327273368835449, "learning_rate": 4.235947852105151e-05, "loss": 0.7222, "step": 725 }, { "epoch": 0.46437994722955145, "grad_norm": 2.3421308994293213, "learning_rate": 4.2348792477025003e-05, "loss": 0.7665, "step": 726 }, { "epoch": 0.4650195890301431, "grad_norm": 2.3444700241088867, "learning_rate": 4.23381064329985e-05, "loss": 0.7521, "step": 727 }, { "epoch": 0.4656592308307348, "grad_norm": 2.665940284729004, "learning_rate": 4.232742038897201e-05, "loss": 0.9051, "step": 728 }, { "epoch": 0.46629887263132647, "grad_norm": 2.394313097000122, "learning_rate": 4.23167343449455e-05, "loss": 0.7246, "step": 729 }, { "epoch": 0.46693851443191814, "grad_norm": 2.325242280960083, "learning_rate": 4.230604830091901e-05, "loss": 0.7279, "step": 730 }, { "epoch": 0.4675781562325098, "grad_norm": 2.416950225830078, "learning_rate": 4.22953622568925e-05, "loss": 0.7872, "step": 731 }, { "epoch": 0.4682177980331015, "grad_norm": 2.328209400177002, "learning_rate": 4.2284676212866e-05, "loss": 0.7682, "step": 732 }, { "epoch": 0.46885743983369316, "grad_norm": 2.7438161373138428, "learning_rate": 4.22739901688395e-05, "loss": 0.8456, "step": 733 }, { "epoch": 0.4694970816342848, "grad_norm": 2.4973058700561523, "learning_rate": 4.2263304124813e-05, "loss": 0.7679, "step": 734 }, { "epoch": 0.47013672343487645, "grad_norm": 2.284014940261841, "learning_rate": 4.225261808078649e-05, "loss": 0.6976, "step": 735 }, { "epoch": 0.4707763652354681, "grad_norm": 2.4707276821136475, "learning_rate": 4.224193203676e-05, "loss": 0.8378, "step": 736 }, { "epoch": 0.4714160070360598, "grad_norm": 2.4387924671173096, "learning_rate": 4.223124599273349e-05, "loss": 0.8649, "step": 737 }, { "epoch": 0.47205564883665146, "grad_norm": 2.16929030418396, "learning_rate": 4.222055994870699e-05, "loss": 0.7006, "step": 738 }, { "epoch": 0.47269529063724314, "grad_norm": 2.5939579010009766, "learning_rate": 4.220987390468049e-05, "loss": 0.8128, "step": 739 }, { "epoch": 0.4733349324378348, "grad_norm": 2.0849668979644775, "learning_rate": 4.219918786065399e-05, "loss": 0.5965, "step": 740 }, { "epoch": 0.4739745742384265, "grad_norm": 2.613360643386841, "learning_rate": 4.218850181662749e-05, "loss": 0.8357, "step": 741 }, { "epoch": 0.47461421603901816, "grad_norm": 2.1418871879577637, "learning_rate": 4.2177815772600986e-05, "loss": 0.6704, "step": 742 }, { "epoch": 0.47525385783960983, "grad_norm": 2.3548357486724854, "learning_rate": 4.2167129728574486e-05, "loss": 0.787, "step": 743 }, { "epoch": 0.4758934996402015, "grad_norm": 2.6763994693756104, "learning_rate": 4.215644368454798e-05, "loss": 0.8784, "step": 744 }, { "epoch": 0.4765331414407932, "grad_norm": 2.7560031414031982, "learning_rate": 4.2145757640521485e-05, "loss": 0.8917, "step": 745 }, { "epoch": 0.47717278324138485, "grad_norm": 2.253741979598999, "learning_rate": 4.213507159649498e-05, "loss": 0.8011, "step": 746 }, { "epoch": 0.4778124250419765, "grad_norm": 2.534224271774292, "learning_rate": 4.2124385552468476e-05, "loss": 0.796, "step": 747 }, { "epoch": 0.47845206684256814, "grad_norm": 2.5827114582061768, "learning_rate": 4.2113699508441976e-05, "loss": 0.8557, "step": 748 }, { "epoch": 0.4790917086431598, "grad_norm": 2.3602304458618164, "learning_rate": 4.2103013464415475e-05, "loss": 0.8351, "step": 749 }, { "epoch": 0.4797313504437515, "grad_norm": 2.4108176231384277, "learning_rate": 4.2092327420388975e-05, "loss": 0.729, "step": 750 }, { "epoch": 0.48037099224434315, "grad_norm": 2.093555450439453, "learning_rate": 4.2081641376362474e-05, "loss": 0.6602, "step": 751 }, { "epoch": 0.4810106340449348, "grad_norm": 2.5413529872894287, "learning_rate": 4.207095533233597e-05, "loss": 0.8545, "step": 752 }, { "epoch": 0.4816502758455265, "grad_norm": 2.3444695472717285, "learning_rate": 4.2060269288309466e-05, "loss": 0.6782, "step": 753 }, { "epoch": 0.48228991764611817, "grad_norm": 2.5395138263702393, "learning_rate": 4.204958324428297e-05, "loss": 0.8499, "step": 754 }, { "epoch": 0.48292955944670984, "grad_norm": 2.4707767963409424, "learning_rate": 4.2038897200256465e-05, "loss": 0.721, "step": 755 }, { "epoch": 0.4835692012473015, "grad_norm": 2.2747201919555664, "learning_rate": 4.2028211156229964e-05, "loss": 0.7129, "step": 756 }, { "epoch": 0.4842088430478932, "grad_norm": 2.6218323707580566, "learning_rate": 4.201752511220346e-05, "loss": 0.7978, "step": 757 }, { "epoch": 0.48484848484848486, "grad_norm": 2.5273592472076416, "learning_rate": 4.200683906817696e-05, "loss": 0.745, "step": 758 }, { "epoch": 0.48548812664907653, "grad_norm": 2.452383041381836, "learning_rate": 4.199615302415046e-05, "loss": 0.8259, "step": 759 }, { "epoch": 0.4861277684496682, "grad_norm": 2.210493803024292, "learning_rate": 4.198546698012396e-05, "loss": 0.7466, "step": 760 }, { "epoch": 0.4867674102502599, "grad_norm": 2.46187686920166, "learning_rate": 4.197478093609746e-05, "loss": 0.7492, "step": 761 }, { "epoch": 0.4874070520508515, "grad_norm": 2.3991000652313232, "learning_rate": 4.196409489207096e-05, "loss": 0.7425, "step": 762 }, { "epoch": 0.48804669385144317, "grad_norm": 2.3745670318603516, "learning_rate": 4.195340884804446e-05, "loss": 0.8105, "step": 763 }, { "epoch": 0.48868633565203484, "grad_norm": 2.2570762634277344, "learning_rate": 4.194272280401795e-05, "loss": 0.7296, "step": 764 }, { "epoch": 0.4893259774526265, "grad_norm": 2.485466480255127, "learning_rate": 4.193203675999146e-05, "loss": 0.8015, "step": 765 }, { "epoch": 0.4899656192532182, "grad_norm": 2.5229861736297607, "learning_rate": 4.192135071596495e-05, "loss": 0.8643, "step": 766 }, { "epoch": 0.49060526105380986, "grad_norm": 2.723752975463867, "learning_rate": 4.191066467193845e-05, "loss": 0.9526, "step": 767 }, { "epoch": 0.49124490285440153, "grad_norm": 2.643864154815674, "learning_rate": 4.189997862791195e-05, "loss": 0.8067, "step": 768 }, { "epoch": 0.4918845446549932, "grad_norm": 2.9591357707977295, "learning_rate": 4.188929258388545e-05, "loss": 0.9238, "step": 769 }, { "epoch": 0.4925241864555849, "grad_norm": 2.3780622482299805, "learning_rate": 4.187860653985894e-05, "loss": 0.7758, "step": 770 }, { "epoch": 0.49316382825617655, "grad_norm": 2.1047439575195312, "learning_rate": 4.186792049583245e-05, "loss": 0.7042, "step": 771 }, { "epoch": 0.4938034700567682, "grad_norm": 2.330016851425171, "learning_rate": 4.185723445180594e-05, "loss": 0.7378, "step": 772 }, { "epoch": 0.4944431118573599, "grad_norm": 2.4735641479492188, "learning_rate": 4.184654840777944e-05, "loss": 0.8509, "step": 773 }, { "epoch": 0.49508275365795157, "grad_norm": 2.3342504501342773, "learning_rate": 4.1835862363752946e-05, "loss": 0.7791, "step": 774 }, { "epoch": 0.49572239545854324, "grad_norm": 2.426173686981201, "learning_rate": 4.182517631972644e-05, "loss": 0.7744, "step": 775 }, { "epoch": 0.49636203725913486, "grad_norm": 2.3046963214874268, "learning_rate": 4.181449027569994e-05, "loss": 0.7835, "step": 776 }, { "epoch": 0.49700167905972653, "grad_norm": 2.3580424785614014, "learning_rate": 4.180380423167344e-05, "loss": 0.7936, "step": 777 }, { "epoch": 0.4976413208603182, "grad_norm": 2.607560873031616, "learning_rate": 4.1793118187646936e-05, "loss": 0.8767, "step": 778 }, { "epoch": 0.4982809626609099, "grad_norm": 2.2512693405151367, "learning_rate": 4.178243214362043e-05, "loss": 0.6273, "step": 779 }, { "epoch": 0.49892060446150155, "grad_norm": 2.3312618732452393, "learning_rate": 4.1771746099593935e-05, "loss": 0.8266, "step": 780 }, { "epoch": 0.4995602462620932, "grad_norm": 2.2288873195648193, "learning_rate": 4.176106005556743e-05, "loss": 0.7246, "step": 781 }, { "epoch": 0.5001998880626849, "grad_norm": 2.559891939163208, "learning_rate": 4.175037401154093e-05, "loss": 0.8888, "step": 782 }, { "epoch": 0.5008395298632765, "grad_norm": 2.577299118041992, "learning_rate": 4.1739687967514426e-05, "loss": 0.833, "step": 783 }, { "epoch": 0.5014791716638682, "grad_norm": 2.1614084243774414, "learning_rate": 4.1729001923487926e-05, "loss": 0.6953, "step": 784 }, { "epoch": 0.5021188134644599, "grad_norm": 2.394045114517212, "learning_rate": 4.1718315879461425e-05, "loss": 0.7687, "step": 785 }, { "epoch": 0.5027584552650516, "grad_norm": 2.584552049636841, "learning_rate": 4.1707629835434924e-05, "loss": 0.8308, "step": 786 }, { "epoch": 0.5033980970656432, "grad_norm": 2.7457361221313477, "learning_rate": 4.1696943791408424e-05, "loss": 0.9089, "step": 787 }, { "epoch": 0.5040377388662349, "grad_norm": 2.0862643718719482, "learning_rate": 4.168625774738192e-05, "loss": 0.7044, "step": 788 }, { "epoch": 0.5046773806668265, "grad_norm": 2.2941691875457764, "learning_rate": 4.167557170335542e-05, "loss": 0.736, "step": 789 }, { "epoch": 0.5053170224674183, "grad_norm": 2.494553565979004, "learning_rate": 4.1664885659328915e-05, "loss": 0.8029, "step": 790 }, { "epoch": 0.5059566642680099, "grad_norm": 2.7531251907348633, "learning_rate": 4.165419961530242e-05, "loss": 0.7177, "step": 791 }, { "epoch": 0.5065963060686016, "grad_norm": 2.6599185466766357, "learning_rate": 4.1643513571275914e-05, "loss": 0.7248, "step": 792 }, { "epoch": 0.5072359478691932, "grad_norm": 2.495180130004883, "learning_rate": 4.163282752724941e-05, "loss": 0.7985, "step": 793 }, { "epoch": 0.507875589669785, "grad_norm": 2.3413760662078857, "learning_rate": 4.162214148322291e-05, "loss": 0.6592, "step": 794 }, { "epoch": 0.5085152314703766, "grad_norm": 2.274296760559082, "learning_rate": 4.161145543919641e-05, "loss": 0.6942, "step": 795 }, { "epoch": 0.5091548732709683, "grad_norm": 2.517688035964966, "learning_rate": 4.160076939516991e-05, "loss": 0.7514, "step": 796 }, { "epoch": 0.5097945150715599, "grad_norm": 2.3168115615844727, "learning_rate": 4.159008335114341e-05, "loss": 0.7295, "step": 797 }, { "epoch": 0.5104341568721515, "grad_norm": 2.2231526374816895, "learning_rate": 4.157939730711691e-05, "loss": 0.6427, "step": 798 }, { "epoch": 0.5110737986727433, "grad_norm": 2.4800660610198975, "learning_rate": 4.15687112630904e-05, "loss": 0.7576, "step": 799 }, { "epoch": 0.5117134404733349, "grad_norm": 2.3524868488311768, "learning_rate": 4.155802521906391e-05, "loss": 0.7715, "step": 800 }, { "epoch": 0.5123530822739266, "grad_norm": 2.6067728996276855, "learning_rate": 4.15473391750374e-05, "loss": 0.8254, "step": 801 }, { "epoch": 0.5129927240745182, "grad_norm": 2.444256067276001, "learning_rate": 4.15366531310109e-05, "loss": 0.7808, "step": 802 }, { "epoch": 0.51363236587511, "grad_norm": 2.729552745819092, "learning_rate": 4.15259670869844e-05, "loss": 0.8508, "step": 803 }, { "epoch": 0.5142720076757016, "grad_norm": 2.523963451385498, "learning_rate": 4.15152810429579e-05, "loss": 0.8453, "step": 804 }, { "epoch": 0.5149116494762933, "grad_norm": 2.5863211154937744, "learning_rate": 4.150459499893139e-05, "loss": 0.8191, "step": 805 }, { "epoch": 0.5155512912768849, "grad_norm": 2.0983970165252686, "learning_rate": 4.14939089549049e-05, "loss": 0.7109, "step": 806 }, { "epoch": 0.5161909330774767, "grad_norm": 2.326378345489502, "learning_rate": 4.14832229108784e-05, "loss": 0.7702, "step": 807 }, { "epoch": 0.5168305748780683, "grad_norm": 2.384821891784668, "learning_rate": 4.147253686685189e-05, "loss": 0.775, "step": 808 }, { "epoch": 0.51747021667866, "grad_norm": 2.3771309852600098, "learning_rate": 4.1461850822825396e-05, "loss": 0.6902, "step": 809 }, { "epoch": 0.5181098584792516, "grad_norm": 2.3961310386657715, "learning_rate": 4.145116477879889e-05, "loss": 0.6649, "step": 810 }, { "epoch": 0.5187495002798432, "grad_norm": 2.2681758403778076, "learning_rate": 4.144047873477239e-05, "loss": 0.7042, "step": 811 }, { "epoch": 0.519389142080435, "grad_norm": 2.1639442443847656, "learning_rate": 4.142979269074589e-05, "loss": 0.6832, "step": 812 }, { "epoch": 0.5200287838810266, "grad_norm": 2.4273269176483154, "learning_rate": 4.141910664671939e-05, "loss": 0.787, "step": 813 }, { "epoch": 0.5206684256816183, "grad_norm": 2.7979812622070312, "learning_rate": 4.1408420602692886e-05, "loss": 0.9597, "step": 814 }, { "epoch": 0.5213080674822099, "grad_norm": 2.4153497219085693, "learning_rate": 4.1397734558666386e-05, "loss": 0.8146, "step": 815 }, { "epoch": 0.5219477092828017, "grad_norm": 2.2426140308380127, "learning_rate": 4.138704851463988e-05, "loss": 0.7293, "step": 816 }, { "epoch": 0.5225873510833933, "grad_norm": 2.6007134914398193, "learning_rate": 4.1376362470613384e-05, "loss": 0.8676, "step": 817 }, { "epoch": 0.523226992883985, "grad_norm": 2.4803342819213867, "learning_rate": 4.136567642658688e-05, "loss": 0.7309, "step": 818 }, { "epoch": 0.5238666346845766, "grad_norm": 2.0530762672424316, "learning_rate": 4.1354990382560376e-05, "loss": 0.6582, "step": 819 }, { "epoch": 0.5245062764851683, "grad_norm": 2.6229400634765625, "learning_rate": 4.1344304338533876e-05, "loss": 0.9341, "step": 820 }, { "epoch": 0.52514591828576, "grad_norm": 2.2598581314086914, "learning_rate": 4.1333618294507375e-05, "loss": 0.7169, "step": 821 }, { "epoch": 0.5257855600863517, "grad_norm": 2.365225076675415, "learning_rate": 4.1322932250480874e-05, "loss": 0.834, "step": 822 }, { "epoch": 0.5264252018869433, "grad_norm": 2.0500223636627197, "learning_rate": 4.1312246206454374e-05, "loss": 0.6791, "step": 823 }, { "epoch": 0.527064843687535, "grad_norm": 2.4313559532165527, "learning_rate": 4.130156016242787e-05, "loss": 0.7526, "step": 824 }, { "epoch": 0.5277044854881267, "grad_norm": 2.3353288173675537, "learning_rate": 4.1290874118401366e-05, "loss": 0.7322, "step": 825 }, { "epoch": 0.5283441272887183, "grad_norm": 2.41013503074646, "learning_rate": 4.128018807437487e-05, "loss": 0.797, "step": 826 }, { "epoch": 0.52898376908931, "grad_norm": 2.5067005157470703, "learning_rate": 4.1269502030348364e-05, "loss": 0.7427, "step": 827 }, { "epoch": 0.5296234108899016, "grad_norm": 2.6221978664398193, "learning_rate": 4.1258815986321864e-05, "loss": 0.8642, "step": 828 }, { "epoch": 0.5302630526904933, "grad_norm": 2.5964040756225586, "learning_rate": 4.124812994229536e-05, "loss": 0.8008, "step": 829 }, { "epoch": 0.530902694491085, "grad_norm": 2.1217386722564697, "learning_rate": 4.123744389826886e-05, "loss": 0.6759, "step": 830 }, { "epoch": 0.5315423362916767, "grad_norm": 2.4662091732025146, "learning_rate": 4.122675785424236e-05, "loss": 0.8088, "step": 831 }, { "epoch": 0.5321819780922683, "grad_norm": 2.3242239952087402, "learning_rate": 4.121607181021586e-05, "loss": 0.8301, "step": 832 }, { "epoch": 0.53282161989286, "grad_norm": 2.286344528198242, "learning_rate": 4.120538576618936e-05, "loss": 0.7303, "step": 833 }, { "epoch": 0.5334612616934516, "grad_norm": 2.096362829208374, "learning_rate": 4.119469972216285e-05, "loss": 0.686, "step": 834 }, { "epoch": 0.5341009034940434, "grad_norm": 2.350806951522827, "learning_rate": 4.118401367813636e-05, "loss": 0.7674, "step": 835 }, { "epoch": 0.534740545294635, "grad_norm": 2.3228611946105957, "learning_rate": 4.117332763410985e-05, "loss": 0.7578, "step": 836 }, { "epoch": 0.5353801870952267, "grad_norm": 2.219318389892578, "learning_rate": 4.116264159008335e-05, "loss": 0.7058, "step": 837 }, { "epoch": 0.5360198288958183, "grad_norm": 2.051234722137451, "learning_rate": 4.115195554605685e-05, "loss": 0.6298, "step": 838 }, { "epoch": 0.53665947069641, "grad_norm": 2.0875167846679688, "learning_rate": 4.114126950203035e-05, "loss": 0.6579, "step": 839 }, { "epoch": 0.5372991124970017, "grad_norm": 2.814260959625244, "learning_rate": 4.113058345800385e-05, "loss": 0.9552, "step": 840 }, { "epoch": 0.5379387542975933, "grad_norm": 2.2160706520080566, "learning_rate": 4.111989741397735e-05, "loss": 0.6829, "step": 841 }, { "epoch": 0.538578396098185, "grad_norm": 2.3203299045562744, "learning_rate": 4.110921136995085e-05, "loss": 0.7216, "step": 842 }, { "epoch": 0.5392180378987766, "grad_norm": 2.5681164264678955, "learning_rate": 4.109852532592435e-05, "loss": 0.8983, "step": 843 }, { "epoch": 0.5398576796993684, "grad_norm": 2.9693334102630615, "learning_rate": 4.108783928189785e-05, "loss": 0.9235, "step": 844 }, { "epoch": 0.54049732149996, "grad_norm": 2.320012331008911, "learning_rate": 4.107715323787134e-05, "loss": 0.7369, "step": 845 }, { "epoch": 0.5411369633005517, "grad_norm": 2.2545132637023926, "learning_rate": 4.1066467193844846e-05, "loss": 0.7332, "step": 846 }, { "epoch": 0.5417766051011433, "grad_norm": 2.706484317779541, "learning_rate": 4.105578114981834e-05, "loss": 0.7563, "step": 847 }, { "epoch": 0.5424162469017351, "grad_norm": 2.2728209495544434, "learning_rate": 4.104509510579184e-05, "loss": 0.7921, "step": 848 }, { "epoch": 0.5430558887023267, "grad_norm": 2.2434425354003906, "learning_rate": 4.103440906176534e-05, "loss": 0.7594, "step": 849 }, { "epoch": 0.5436955305029184, "grad_norm": 2.4385409355163574, "learning_rate": 4.1023723017738836e-05, "loss": 0.7746, "step": 850 }, { "epoch": 0.54433517230351, "grad_norm": 2.4708523750305176, "learning_rate": 4.101303697371233e-05, "loss": 0.771, "step": 851 }, { "epoch": 0.5449748141041018, "grad_norm": 2.6323025226593018, "learning_rate": 4.1002350929685835e-05, "loss": 0.8149, "step": 852 }, { "epoch": 0.5456144559046934, "grad_norm": 2.2841379642486572, "learning_rate": 4.0991664885659334e-05, "loss": 0.7075, "step": 853 }, { "epoch": 0.546254097705285, "grad_norm": 2.273214101791382, "learning_rate": 4.098097884163283e-05, "loss": 0.7082, "step": 854 }, { "epoch": 0.5468937395058767, "grad_norm": 2.3645529747009277, "learning_rate": 4.097029279760633e-05, "loss": 0.7747, "step": 855 }, { "epoch": 0.5475333813064683, "grad_norm": 2.2649810314178467, "learning_rate": 4.0959606753579826e-05, "loss": 0.8063, "step": 856 }, { "epoch": 0.5481730231070601, "grad_norm": 2.247239112854004, "learning_rate": 4.0948920709553325e-05, "loss": 0.6845, "step": 857 }, { "epoch": 0.5488126649076517, "grad_norm": 2.3738226890563965, "learning_rate": 4.0938234665526824e-05, "loss": 0.8023, "step": 858 }, { "epoch": 0.5494523067082434, "grad_norm": 2.4073843955993652, "learning_rate": 4.0927548621500324e-05, "loss": 0.7924, "step": 859 }, { "epoch": 0.550091948508835, "grad_norm": 2.217334270477295, "learning_rate": 4.0916862577473816e-05, "loss": 0.7423, "step": 860 }, { "epoch": 0.5507315903094268, "grad_norm": 2.7021453380584717, "learning_rate": 4.090617653344732e-05, "loss": 0.8054, "step": 861 }, { "epoch": 0.5513712321100184, "grad_norm": 2.407155752182007, "learning_rate": 4.0895490489420815e-05, "loss": 0.7896, "step": 862 }, { "epoch": 0.5520108739106101, "grad_norm": 2.5113189220428467, "learning_rate": 4.0884804445394314e-05, "loss": 0.7933, "step": 863 }, { "epoch": 0.5526505157112017, "grad_norm": 2.4268243312835693, "learning_rate": 4.0874118401367814e-05, "loss": 0.8049, "step": 864 }, { "epoch": 0.5532901575117934, "grad_norm": 2.3329579830169678, "learning_rate": 4.086343235734131e-05, "loss": 0.7039, "step": 865 }, { "epoch": 0.5539297993123851, "grad_norm": 2.568941831588745, "learning_rate": 4.085274631331481e-05, "loss": 0.8756, "step": 866 }, { "epoch": 0.5545694411129767, "grad_norm": 2.2570316791534424, "learning_rate": 4.084206026928831e-05, "loss": 0.7051, "step": 867 }, { "epoch": 0.5552090829135684, "grad_norm": 2.3210926055908203, "learning_rate": 4.083137422526181e-05, "loss": 0.6965, "step": 868 }, { "epoch": 0.55584872471416, "grad_norm": 2.353562116622925, "learning_rate": 4.0820688181235304e-05, "loss": 0.7586, "step": 869 }, { "epoch": 0.5564883665147518, "grad_norm": 1.8056342601776123, "learning_rate": 4.081000213720881e-05, "loss": 0.6007, "step": 870 }, { "epoch": 0.5571280083153434, "grad_norm": 2.4414591789245605, "learning_rate": 4.07993160931823e-05, "loss": 0.7651, "step": 871 }, { "epoch": 0.5577676501159351, "grad_norm": 2.388673782348633, "learning_rate": 4.078863004915581e-05, "loss": 0.8275, "step": 872 }, { "epoch": 0.5584072919165267, "grad_norm": 2.5591752529144287, "learning_rate": 4.07779440051293e-05, "loss": 0.8951, "step": 873 }, { "epoch": 0.5590469337171184, "grad_norm": 2.5922563076019287, "learning_rate": 4.07672579611028e-05, "loss": 0.8393, "step": 874 }, { "epoch": 0.5596865755177101, "grad_norm": 2.4653162956237793, "learning_rate": 4.07565719170763e-05, "loss": 0.7547, "step": 875 }, { "epoch": 0.5603262173183018, "grad_norm": 2.1400020122528076, "learning_rate": 4.07458858730498e-05, "loss": 0.6497, "step": 876 }, { "epoch": 0.5609658591188934, "grad_norm": 2.6126105785369873, "learning_rate": 4.07351998290233e-05, "loss": 0.8739, "step": 877 }, { "epoch": 0.5616055009194851, "grad_norm": 2.373138904571533, "learning_rate": 4.07245137849968e-05, "loss": 0.8179, "step": 878 }, { "epoch": 0.5622451427200768, "grad_norm": 2.454766273498535, "learning_rate": 4.07138277409703e-05, "loss": 0.8469, "step": 879 }, { "epoch": 0.5628847845206685, "grad_norm": 2.2886855602264404, "learning_rate": 4.070314169694379e-05, "loss": 0.7826, "step": 880 }, { "epoch": 0.5635244263212601, "grad_norm": 2.350181818008423, "learning_rate": 4.0692455652917296e-05, "loss": 0.8548, "step": 881 }, { "epoch": 0.5641640681218517, "grad_norm": 2.328355073928833, "learning_rate": 4.068176960889079e-05, "loss": 0.7654, "step": 882 }, { "epoch": 0.5648037099224434, "grad_norm": 2.591658592224121, "learning_rate": 4.067108356486429e-05, "loss": 0.8854, "step": 883 }, { "epoch": 0.5654433517230351, "grad_norm": 2.2084527015686035, "learning_rate": 4.066039752083779e-05, "loss": 0.6809, "step": 884 }, { "epoch": 0.5660829935236268, "grad_norm": 2.2749183177948, "learning_rate": 4.064971147681129e-05, "loss": 0.7978, "step": 885 }, { "epoch": 0.5667226353242184, "grad_norm": 2.679457902908325, "learning_rate": 4.0639025432784786e-05, "loss": 0.9257, "step": 886 }, { "epoch": 0.5673622771248101, "grad_norm": 2.0867230892181396, "learning_rate": 4.0628339388758286e-05, "loss": 0.7228, "step": 887 }, { "epoch": 0.5680019189254017, "grad_norm": 2.5408248901367188, "learning_rate": 4.0617653344731785e-05, "loss": 0.8027, "step": 888 }, { "epoch": 0.5686415607259935, "grad_norm": 2.151369571685791, "learning_rate": 4.060696730070528e-05, "loss": 0.7427, "step": 889 }, { "epoch": 0.5692812025265851, "grad_norm": 2.505272150039673, "learning_rate": 4.0596281256678784e-05, "loss": 0.6939, "step": 890 }, { "epoch": 0.5699208443271768, "grad_norm": 2.562251567840576, "learning_rate": 4.0585595212652276e-05, "loss": 0.766, "step": 891 }, { "epoch": 0.5705604861277684, "grad_norm": 2.436009645462036, "learning_rate": 4.0574909168625776e-05, "loss": 0.7833, "step": 892 }, { "epoch": 0.5712001279283602, "grad_norm": 2.7431294918060303, "learning_rate": 4.0564223124599275e-05, "loss": 0.7327, "step": 893 }, { "epoch": 0.5718397697289518, "grad_norm": 2.437372922897339, "learning_rate": 4.0553537080572774e-05, "loss": 0.7623, "step": 894 }, { "epoch": 0.5724794115295434, "grad_norm": 2.344759225845337, "learning_rate": 4.054285103654627e-05, "loss": 0.7997, "step": 895 }, { "epoch": 0.5731190533301351, "grad_norm": 2.7062759399414062, "learning_rate": 4.053216499251977e-05, "loss": 0.848, "step": 896 }, { "epoch": 0.5737586951307267, "grad_norm": 2.716770887374878, "learning_rate": 4.0521478948493266e-05, "loss": 0.8653, "step": 897 }, { "epoch": 0.5743983369313185, "grad_norm": 2.593524694442749, "learning_rate": 4.051079290446677e-05, "loss": 0.8759, "step": 898 }, { "epoch": 0.5750379787319101, "grad_norm": 2.676051616668701, "learning_rate": 4.050010686044027e-05, "loss": 0.8395, "step": 899 }, { "epoch": 0.5756776205325018, "grad_norm": 2.438495635986328, "learning_rate": 4.0489420816413764e-05, "loss": 0.811, "step": 900 }, { "epoch": 0.5763172623330934, "grad_norm": 2.6083335876464844, "learning_rate": 4.047873477238727e-05, "loss": 0.8095, "step": 901 }, { "epoch": 0.5769569041336852, "grad_norm": 2.230010509490967, "learning_rate": 4.046804872836076e-05, "loss": 0.7149, "step": 902 }, { "epoch": 0.5775965459342768, "grad_norm": 2.290432929992676, "learning_rate": 4.045736268433426e-05, "loss": 0.7345, "step": 903 }, { "epoch": 0.5782361877348685, "grad_norm": 2.2592225074768066, "learning_rate": 4.044667664030776e-05, "loss": 0.6788, "step": 904 }, { "epoch": 0.5788758295354601, "grad_norm": 2.3218696117401123, "learning_rate": 4.043599059628126e-05, "loss": 0.7009, "step": 905 }, { "epoch": 0.5795154713360519, "grad_norm": 1.7487784624099731, "learning_rate": 4.042530455225475e-05, "loss": 0.6401, "step": 906 }, { "epoch": 0.5801551131366435, "grad_norm": 2.319746255874634, "learning_rate": 4.041461850822826e-05, "loss": 0.7132, "step": 907 }, { "epoch": 0.5807947549372352, "grad_norm": 2.304169178009033, "learning_rate": 4.040393246420175e-05, "loss": 0.7472, "step": 908 }, { "epoch": 0.5814343967378268, "grad_norm": 2.371488332748413, "learning_rate": 4.039324642017525e-05, "loss": 0.7464, "step": 909 }, { "epoch": 0.5820740385384184, "grad_norm": 2.3133323192596436, "learning_rate": 4.038256037614875e-05, "loss": 0.6964, "step": 910 }, { "epoch": 0.5827136803390102, "grad_norm": 2.2671494483947754, "learning_rate": 4.037187433212225e-05, "loss": 0.7227, "step": 911 }, { "epoch": 0.5833533221396018, "grad_norm": 2.6780896186828613, "learning_rate": 4.036118828809575e-05, "loss": 0.7842, "step": 912 }, { "epoch": 0.5839929639401935, "grad_norm": 2.6332082748413086, "learning_rate": 4.035050224406925e-05, "loss": 0.8686, "step": 913 }, { "epoch": 0.5846326057407851, "grad_norm": 2.6990888118743896, "learning_rate": 4.033981620004275e-05, "loss": 0.8382, "step": 914 }, { "epoch": 0.5852722475413769, "grad_norm": 2.5040202140808105, "learning_rate": 4.032913015601624e-05, "loss": 0.7601, "step": 915 }, { "epoch": 0.5859118893419685, "grad_norm": 2.675201654434204, "learning_rate": 4.031844411198975e-05, "loss": 0.8651, "step": 916 }, { "epoch": 0.5865515311425602, "grad_norm": 2.1978743076324463, "learning_rate": 4.030775806796324e-05, "loss": 0.6559, "step": 917 }, { "epoch": 0.5871911729431518, "grad_norm": 2.3096039295196533, "learning_rate": 4.029707202393674e-05, "loss": 0.7137, "step": 918 }, { "epoch": 0.5878308147437435, "grad_norm": 2.233640670776367, "learning_rate": 4.028638597991024e-05, "loss": 0.7059, "step": 919 }, { "epoch": 0.5884704565443352, "grad_norm": 2.2236380577087402, "learning_rate": 4.027569993588374e-05, "loss": 0.6919, "step": 920 }, { "epoch": 0.5891100983449269, "grad_norm": 2.382692337036133, "learning_rate": 4.026501389185724e-05, "loss": 0.7835, "step": 921 }, { "epoch": 0.5897497401455185, "grad_norm": 2.4091837406158447, "learning_rate": 4.0254327847830736e-05, "loss": 0.7366, "step": 922 }, { "epoch": 0.5903893819461101, "grad_norm": 2.0652902126312256, "learning_rate": 4.0243641803804235e-05, "loss": 0.6362, "step": 923 }, { "epoch": 0.5910290237467019, "grad_norm": 2.447798728942871, "learning_rate": 4.023295575977773e-05, "loss": 0.7498, "step": 924 }, { "epoch": 0.5916686655472935, "grad_norm": 2.377028226852417, "learning_rate": 4.0222269715751234e-05, "loss": 0.7927, "step": 925 }, { "epoch": 0.5923083073478852, "grad_norm": 1.9503337144851685, "learning_rate": 4.021158367172473e-05, "loss": 0.6526, "step": 926 }, { "epoch": 0.5929479491484768, "grad_norm": 2.4022982120513916, "learning_rate": 4.020089762769823e-05, "loss": 0.8673, "step": 927 }, { "epoch": 0.5935875909490685, "grad_norm": 2.441439628601074, "learning_rate": 4.0190211583671725e-05, "loss": 0.8123, "step": 928 }, { "epoch": 0.5942272327496602, "grad_norm": 2.3275411128997803, "learning_rate": 4.0179525539645225e-05, "loss": 0.7722, "step": 929 }, { "epoch": 0.5948668745502519, "grad_norm": 2.7536025047302246, "learning_rate": 4.0168839495618724e-05, "loss": 0.8429, "step": 930 }, { "epoch": 0.5955065163508435, "grad_norm": 2.31563138961792, "learning_rate": 4.0158153451592224e-05, "loss": 0.7979, "step": 931 }, { "epoch": 0.5961461581514352, "grad_norm": 2.359586715698242, "learning_rate": 4.014746740756572e-05, "loss": 0.7203, "step": 932 }, { "epoch": 0.5967857999520269, "grad_norm": 2.407341241836548, "learning_rate": 4.013678136353922e-05, "loss": 0.804, "step": 933 }, { "epoch": 0.5974254417526186, "grad_norm": 1.792413592338562, "learning_rate": 4.012609531951272e-05, "loss": 0.5876, "step": 934 }, { "epoch": 0.5980650835532102, "grad_norm": 2.349578857421875, "learning_rate": 4.0115409275486214e-05, "loss": 0.8117, "step": 935 }, { "epoch": 0.5987047253538019, "grad_norm": 2.211759090423584, "learning_rate": 4.010472323145972e-05, "loss": 0.7203, "step": 936 }, { "epoch": 0.5993443671543935, "grad_norm": 2.309387445449829, "learning_rate": 4.009403718743321e-05, "loss": 0.756, "step": 937 }, { "epoch": 0.5999840089549852, "grad_norm": 2.1751136779785156, "learning_rate": 4.008335114340671e-05, "loss": 0.6437, "step": 938 }, { "epoch": 0.6006236507555769, "grad_norm": 2.28783917427063, "learning_rate": 4.007266509938021e-05, "loss": 0.6768, "step": 939 }, { "epoch": 0.6012632925561685, "grad_norm": 2.1996519565582275, "learning_rate": 4.006197905535371e-05, "loss": 0.6821, "step": 940 }, { "epoch": 0.6019029343567602, "grad_norm": 2.0751750469207764, "learning_rate": 4.0051293011327204e-05, "loss": 0.6784, "step": 941 }, { "epoch": 0.6025425761573519, "grad_norm": 2.0684049129486084, "learning_rate": 4.004060696730071e-05, "loss": 0.6572, "step": 942 }, { "epoch": 0.6031822179579436, "grad_norm": 2.560596227645874, "learning_rate": 4.00299209232742e-05, "loss": 0.7658, "step": 943 }, { "epoch": 0.6038218597585352, "grad_norm": 2.3507702350616455, "learning_rate": 4.00192348792477e-05, "loss": 0.8368, "step": 944 }, { "epoch": 0.6044615015591269, "grad_norm": 2.741117000579834, "learning_rate": 4.000854883522121e-05, "loss": 0.6982, "step": 945 }, { "epoch": 0.6051011433597185, "grad_norm": 2.4322903156280518, "learning_rate": 3.99978627911947e-05, "loss": 0.7642, "step": 946 }, { "epoch": 0.6057407851603103, "grad_norm": 2.6147563457489014, "learning_rate": 3.99871767471682e-05, "loss": 0.6749, "step": 947 }, { "epoch": 0.6063804269609019, "grad_norm": 2.37351655960083, "learning_rate": 3.99764907031417e-05, "loss": 0.7726, "step": 948 }, { "epoch": 0.6070200687614936, "grad_norm": 2.1228601932525635, "learning_rate": 3.99658046591152e-05, "loss": 0.6969, "step": 949 }, { "epoch": 0.6076597105620852, "grad_norm": 2.356920003890991, "learning_rate": 3.995511861508869e-05, "loss": 0.8022, "step": 950 }, { "epoch": 0.6082993523626768, "grad_norm": 2.4392523765563965, "learning_rate": 3.99444325710622e-05, "loss": 0.804, "step": 951 }, { "epoch": 0.6089389941632686, "grad_norm": 2.4725987911224365, "learning_rate": 3.993374652703569e-05, "loss": 0.7574, "step": 952 }, { "epoch": 0.6095786359638602, "grad_norm": 2.684683084487915, "learning_rate": 3.992306048300919e-05, "loss": 0.7596, "step": 953 }, { "epoch": 0.6102182777644519, "grad_norm": 2.5766384601593018, "learning_rate": 3.991237443898269e-05, "loss": 0.8009, "step": 954 }, { "epoch": 0.6108579195650435, "grad_norm": 2.322838544845581, "learning_rate": 3.990168839495619e-05, "loss": 0.722, "step": 955 }, { "epoch": 0.6114975613656353, "grad_norm": 2.2413270473480225, "learning_rate": 3.989100235092969e-05, "loss": 0.7197, "step": 956 }, { "epoch": 0.6121372031662269, "grad_norm": 2.4533560276031494, "learning_rate": 3.988031630690319e-05, "loss": 0.8411, "step": 957 }, { "epoch": 0.6127768449668186, "grad_norm": 1.9486346244812012, "learning_rate": 3.9869630262876686e-05, "loss": 0.613, "step": 958 }, { "epoch": 0.6134164867674102, "grad_norm": 2.55692458152771, "learning_rate": 3.9858944218850185e-05, "loss": 0.7848, "step": 959 }, { "epoch": 0.614056128568002, "grad_norm": 2.433396816253662, "learning_rate": 3.9848258174823685e-05, "loss": 0.7827, "step": 960 }, { "epoch": 0.6146957703685936, "grad_norm": 2.615607738494873, "learning_rate": 3.983757213079718e-05, "loss": 0.7819, "step": 961 }, { "epoch": 0.6153354121691853, "grad_norm": 2.2539865970611572, "learning_rate": 3.9826886086770683e-05, "loss": 0.6861, "step": 962 }, { "epoch": 0.6159750539697769, "grad_norm": 2.2904000282287598, "learning_rate": 3.9816200042744176e-05, "loss": 0.7327, "step": 963 }, { "epoch": 0.6166146957703686, "grad_norm": 2.159097194671631, "learning_rate": 3.9805513998717675e-05, "loss": 0.6517, "step": 964 }, { "epoch": 0.6172543375709603, "grad_norm": 2.511418342590332, "learning_rate": 3.9794827954691175e-05, "loss": 0.8489, "step": 965 }, { "epoch": 0.6178939793715519, "grad_norm": 2.5162479877471924, "learning_rate": 3.9784141910664674e-05, "loss": 0.8049, "step": 966 }, { "epoch": 0.6185336211721436, "grad_norm": 2.2590129375457764, "learning_rate": 3.9773455866638173e-05, "loss": 0.703, "step": 967 }, { "epoch": 0.6191732629727352, "grad_norm": 2.4057836532592773, "learning_rate": 3.976276982261167e-05, "loss": 0.794, "step": 968 }, { "epoch": 0.619812904773327, "grad_norm": 2.1555848121643066, "learning_rate": 3.975208377858517e-05, "loss": 0.6879, "step": 969 }, { "epoch": 0.6204525465739186, "grad_norm": 3.082021713256836, "learning_rate": 3.9741397734558665e-05, "loss": 0.8459, "step": 970 }, { "epoch": 0.6210921883745103, "grad_norm": 2.719717025756836, "learning_rate": 3.973071169053217e-05, "loss": 0.7577, "step": 971 }, { "epoch": 0.6217318301751019, "grad_norm": 2.287407398223877, "learning_rate": 3.9720025646505664e-05, "loss": 0.7307, "step": 972 }, { "epoch": 0.6223714719756936, "grad_norm": 1.997767448425293, "learning_rate": 3.970933960247916e-05, "loss": 0.6546, "step": 973 }, { "epoch": 0.6230111137762853, "grad_norm": 2.116257905960083, "learning_rate": 3.969865355845266e-05, "loss": 0.7164, "step": 974 }, { "epoch": 0.623650755576877, "grad_norm": 2.9210846424102783, "learning_rate": 3.968796751442616e-05, "loss": 0.8839, "step": 975 }, { "epoch": 0.6242903973774686, "grad_norm": 2.0119614601135254, "learning_rate": 3.967728147039966e-05, "loss": 0.6569, "step": 976 }, { "epoch": 0.6249300391780603, "grad_norm": 2.344700813293457, "learning_rate": 3.966659542637316e-05, "loss": 0.7608, "step": 977 }, { "epoch": 0.625569680978652, "grad_norm": 2.141934394836426, "learning_rate": 3.965590938234666e-05, "loss": 0.6702, "step": 978 }, { "epoch": 0.6262093227792436, "grad_norm": 2.2295076847076416, "learning_rate": 3.964522333832015e-05, "loss": 0.7682, "step": 979 }, { "epoch": 0.6268489645798353, "grad_norm": 2.2250473499298096, "learning_rate": 3.963453729429366e-05, "loss": 0.7693, "step": 980 }, { "epoch": 0.6274886063804269, "grad_norm": 2.484199047088623, "learning_rate": 3.962385125026715e-05, "loss": 0.7112, "step": 981 }, { "epoch": 0.6281282481810186, "grad_norm": 2.427258014678955, "learning_rate": 3.961316520624065e-05, "loss": 0.7067, "step": 982 }, { "epoch": 0.6287678899816103, "grad_norm": 2.7425003051757812, "learning_rate": 3.960247916221415e-05, "loss": 0.8382, "step": 983 }, { "epoch": 0.629407531782202, "grad_norm": 2.24448299407959, "learning_rate": 3.959179311818765e-05, "loss": 0.7345, "step": 984 }, { "epoch": 0.6300471735827936, "grad_norm": 2.4819138050079346, "learning_rate": 3.958110707416115e-05, "loss": 0.7582, "step": 985 }, { "epoch": 0.6306868153833853, "grad_norm": 2.452561855316162, "learning_rate": 3.957042103013465e-05, "loss": 0.7174, "step": 986 }, { "epoch": 0.631326457183977, "grad_norm": 2.4645004272460938, "learning_rate": 3.955973498610814e-05, "loss": 0.7948, "step": 987 }, { "epoch": 0.6319660989845687, "grad_norm": 2.4163429737091064, "learning_rate": 3.9549048942081647e-05, "loss": 0.8258, "step": 988 }, { "epoch": 0.6326057407851603, "grad_norm": 2.1647913455963135, "learning_rate": 3.953836289805514e-05, "loss": 0.6836, "step": 989 }, { "epoch": 0.633245382585752, "grad_norm": 2.318499803543091, "learning_rate": 3.952767685402864e-05, "loss": 0.7331, "step": 990 }, { "epoch": 0.6338850243863436, "grad_norm": 2.34328031539917, "learning_rate": 3.9516990810002145e-05, "loss": 0.7087, "step": 991 }, { "epoch": 0.6345246661869354, "grad_norm": 2.3378255367279053, "learning_rate": 3.950630476597564e-05, "loss": 0.7267, "step": 992 }, { "epoch": 0.635164307987527, "grad_norm": 2.475339889526367, "learning_rate": 3.9495618721949137e-05, "loss": 0.7421, "step": 993 }, { "epoch": 0.6358039497881186, "grad_norm": 2.289686918258667, "learning_rate": 3.9484932677922636e-05, "loss": 0.8081, "step": 994 }, { "epoch": 0.6364435915887103, "grad_norm": 2.2486777305603027, "learning_rate": 3.9474246633896135e-05, "loss": 0.7988, "step": 995 }, { "epoch": 0.637083233389302, "grad_norm": 2.104947805404663, "learning_rate": 3.946356058986963e-05, "loss": 0.719, "step": 996 }, { "epoch": 0.6377228751898937, "grad_norm": 2.2510128021240234, "learning_rate": 3.9452874545843134e-05, "loss": 0.7524, "step": 997 }, { "epoch": 0.6383625169904853, "grad_norm": 2.2770988941192627, "learning_rate": 3.9442188501816627e-05, "loss": 0.7286, "step": 998 }, { "epoch": 0.639002158791077, "grad_norm": 2.0234215259552, "learning_rate": 3.9431502457790126e-05, "loss": 0.646, "step": 999 }, { "epoch": 0.6396418005916686, "grad_norm": 2.0593552589416504, "learning_rate": 3.9420816413763625e-05, "loss": 0.6898, "step": 1000 }, { "epoch": 0.6402814423922604, "grad_norm": 2.0624172687530518, "learning_rate": 3.9410130369737125e-05, "loss": 0.5996, "step": 1001 }, { "epoch": 0.640921084192852, "grad_norm": 2.4475672245025635, "learning_rate": 3.9399444325710624e-05, "loss": 0.7919, "step": 1002 }, { "epoch": 0.6415607259934437, "grad_norm": 2.5255558490753174, "learning_rate": 3.9388758281684123e-05, "loss": 0.8562, "step": 1003 }, { "epoch": 0.6422003677940353, "grad_norm": 2.2773284912109375, "learning_rate": 3.937807223765762e-05, "loss": 0.7647, "step": 1004 }, { "epoch": 0.6428400095946271, "grad_norm": 2.457221269607544, "learning_rate": 3.9367386193631115e-05, "loss": 0.7382, "step": 1005 }, { "epoch": 0.6434796513952187, "grad_norm": 2.2238290309906006, "learning_rate": 3.935670014960462e-05, "loss": 0.6545, "step": 1006 }, { "epoch": 0.6441192931958103, "grad_norm": 2.4462924003601074, "learning_rate": 3.9346014105578114e-05, "loss": 0.8379, "step": 1007 }, { "epoch": 0.644758934996402, "grad_norm": 2.400723695755005, "learning_rate": 3.9335328061551613e-05, "loss": 0.748, "step": 1008 }, { "epoch": 0.6453985767969936, "grad_norm": 2.4213650226593018, "learning_rate": 3.932464201752511e-05, "loss": 0.7917, "step": 1009 }, { "epoch": 0.6460382185975854, "grad_norm": 2.2447752952575684, "learning_rate": 3.931395597349861e-05, "loss": 0.6654, "step": 1010 }, { "epoch": 0.646677860398177, "grad_norm": 2.2563722133636475, "learning_rate": 3.930326992947211e-05, "loss": 0.7058, "step": 1011 }, { "epoch": 0.6473175021987687, "grad_norm": 2.510535955429077, "learning_rate": 3.929258388544561e-05, "loss": 0.9369, "step": 1012 }, { "epoch": 0.6479571439993603, "grad_norm": 2.573002338409424, "learning_rate": 3.928189784141911e-05, "loss": 0.8924, "step": 1013 }, { "epoch": 0.6485967857999521, "grad_norm": 2.2554931640625, "learning_rate": 3.927121179739261e-05, "loss": 0.6641, "step": 1014 }, { "epoch": 0.6492364276005437, "grad_norm": 2.2975242137908936, "learning_rate": 3.926052575336611e-05, "loss": 0.7967, "step": 1015 }, { "epoch": 0.6498760694011354, "grad_norm": 2.3706226348876953, "learning_rate": 3.92498397093396e-05, "loss": 0.7115, "step": 1016 }, { "epoch": 0.650515711201727, "grad_norm": 1.9498761892318726, "learning_rate": 3.923915366531311e-05, "loss": 0.6575, "step": 1017 }, { "epoch": 0.6511553530023187, "grad_norm": 2.1991360187530518, "learning_rate": 3.92284676212866e-05, "loss": 0.7199, "step": 1018 }, { "epoch": 0.6517949948029104, "grad_norm": 2.3318216800689697, "learning_rate": 3.92177815772601e-05, "loss": 0.7546, "step": 1019 }, { "epoch": 0.6524346366035021, "grad_norm": 2.1762449741363525, "learning_rate": 3.92070955332336e-05, "loss": 0.7239, "step": 1020 }, { "epoch": 0.6530742784040937, "grad_norm": 2.4617691040039062, "learning_rate": 3.91964094892071e-05, "loss": 0.8038, "step": 1021 }, { "epoch": 0.6537139202046853, "grad_norm": 2.2549099922180176, "learning_rate": 3.91857234451806e-05, "loss": 0.7112, "step": 1022 }, { "epoch": 0.6543535620052771, "grad_norm": 2.4799864292144775, "learning_rate": 3.91750374011541e-05, "loss": 0.7606, "step": 1023 }, { "epoch": 0.6549932038058687, "grad_norm": 2.43270206451416, "learning_rate": 3.9164351357127596e-05, "loss": 0.7288, "step": 1024 }, { "epoch": 0.6556328456064604, "grad_norm": 2.5053627490997314, "learning_rate": 3.915366531310109e-05, "loss": 0.7419, "step": 1025 }, { "epoch": 0.656272487407052, "grad_norm": 2.3089120388031006, "learning_rate": 3.9142979269074595e-05, "loss": 0.7503, "step": 1026 }, { "epoch": 0.6569121292076437, "grad_norm": 2.567331552505493, "learning_rate": 3.913229322504809e-05, "loss": 0.7968, "step": 1027 }, { "epoch": 0.6575517710082354, "grad_norm": 2.1532084941864014, "learning_rate": 3.912160718102159e-05, "loss": 0.6958, "step": 1028 }, { "epoch": 0.6581914128088271, "grad_norm": 2.290431499481201, "learning_rate": 3.9110921136995086e-05, "loss": 0.7493, "step": 1029 }, { "epoch": 0.6588310546094187, "grad_norm": 2.2117385864257812, "learning_rate": 3.9100235092968586e-05, "loss": 0.6606, "step": 1030 }, { "epoch": 0.6594706964100104, "grad_norm": 2.5073018074035645, "learning_rate": 3.908954904894208e-05, "loss": 0.8315, "step": 1031 }, { "epoch": 0.660110338210602, "grad_norm": 2.0758044719696045, "learning_rate": 3.9078863004915585e-05, "loss": 0.6932, "step": 1032 }, { "epoch": 0.6607499800111938, "grad_norm": 2.434968948364258, "learning_rate": 3.906817696088908e-05, "loss": 0.8139, "step": 1033 }, { "epoch": 0.6613896218117854, "grad_norm": 2.257331371307373, "learning_rate": 3.9057490916862577e-05, "loss": 0.741, "step": 1034 }, { "epoch": 0.662029263612377, "grad_norm": 2.3283777236938477, "learning_rate": 3.9046804872836076e-05, "loss": 0.7625, "step": 1035 }, { "epoch": 0.6626689054129687, "grad_norm": 2.2232840061187744, "learning_rate": 3.9036118828809575e-05, "loss": 0.7106, "step": 1036 }, { "epoch": 0.6633085472135604, "grad_norm": 1.8899500370025635, "learning_rate": 3.9025432784783075e-05, "loss": 0.6227, "step": 1037 }, { "epoch": 0.6639481890141521, "grad_norm": 2.3554022312164307, "learning_rate": 3.9014746740756574e-05, "loss": 0.8066, "step": 1038 }, { "epoch": 0.6645878308147437, "grad_norm": 2.1485507488250732, "learning_rate": 3.900406069673007e-05, "loss": 0.7169, "step": 1039 }, { "epoch": 0.6652274726153354, "grad_norm": 2.33443284034729, "learning_rate": 3.899337465270357e-05, "loss": 0.903, "step": 1040 }, { "epoch": 0.665867114415927, "grad_norm": 2.198026180267334, "learning_rate": 3.898268860867707e-05, "loss": 0.8025, "step": 1041 }, { "epoch": 0.6665067562165188, "grad_norm": 2.3127546310424805, "learning_rate": 3.8972002564650565e-05, "loss": 0.8436, "step": 1042 }, { "epoch": 0.6671463980171104, "grad_norm": 2.124969244003296, "learning_rate": 3.896131652062407e-05, "loss": 0.6896, "step": 1043 }, { "epoch": 0.6677860398177021, "grad_norm": 2.501819133758545, "learning_rate": 3.895063047659756e-05, "loss": 0.8593, "step": 1044 }, { "epoch": 0.6684256816182937, "grad_norm": 2.178406238555908, "learning_rate": 3.893994443257106e-05, "loss": 0.7511, "step": 1045 }, { "epoch": 0.6690653234188855, "grad_norm": 2.3316667079925537, "learning_rate": 3.892925838854456e-05, "loss": 0.7708, "step": 1046 }, { "epoch": 0.6697049652194771, "grad_norm": 2.149301528930664, "learning_rate": 3.891857234451806e-05, "loss": 0.7585, "step": 1047 }, { "epoch": 0.6703446070200688, "grad_norm": 2.2174315452575684, "learning_rate": 3.890788630049156e-05, "loss": 0.7536, "step": 1048 }, { "epoch": 0.6709842488206604, "grad_norm": 2.4261577129364014, "learning_rate": 3.889720025646506e-05, "loss": 0.8253, "step": 1049 }, { "epoch": 0.671623890621252, "grad_norm": 2.417027711868286, "learning_rate": 3.888651421243856e-05, "loss": 0.8187, "step": 1050 }, { "epoch": 0.6722635324218438, "grad_norm": 2.6399002075195312, "learning_rate": 3.887582816841205e-05, "loss": 0.8556, "step": 1051 }, { "epoch": 0.6729031742224354, "grad_norm": 2.147928476333618, "learning_rate": 3.886514212438556e-05, "loss": 0.7248, "step": 1052 }, { "epoch": 0.6735428160230271, "grad_norm": 2.2155518531799316, "learning_rate": 3.885445608035905e-05, "loss": 0.7822, "step": 1053 }, { "epoch": 0.6741824578236187, "grad_norm": 2.535156726837158, "learning_rate": 3.884377003633255e-05, "loss": 0.7741, "step": 1054 }, { "epoch": 0.6748220996242105, "grad_norm": 2.3333871364593506, "learning_rate": 3.883308399230605e-05, "loss": 0.6934, "step": 1055 }, { "epoch": 0.6754617414248021, "grad_norm": 2.1857028007507324, "learning_rate": 3.882239794827955e-05, "loss": 0.6746, "step": 1056 }, { "epoch": 0.6761013832253938, "grad_norm": 2.3149261474609375, "learning_rate": 3.881171190425305e-05, "loss": 0.7206, "step": 1057 }, { "epoch": 0.6767410250259854, "grad_norm": 2.512051820755005, "learning_rate": 3.880102586022655e-05, "loss": 0.7582, "step": 1058 }, { "epoch": 0.6773806668265772, "grad_norm": 2.1747212409973145, "learning_rate": 3.879033981620005e-05, "loss": 0.6835, "step": 1059 }, { "epoch": 0.6780203086271688, "grad_norm": 2.1035051345825195, "learning_rate": 3.877965377217354e-05, "loss": 0.6676, "step": 1060 }, { "epoch": 0.6786599504277605, "grad_norm": 2.3119547367095947, "learning_rate": 3.8768967728147046e-05, "loss": 0.7497, "step": 1061 }, { "epoch": 0.6792995922283521, "grad_norm": 2.011989116668701, "learning_rate": 3.875828168412054e-05, "loss": 0.6539, "step": 1062 }, { "epoch": 0.6799392340289437, "grad_norm": 2.3933212757110596, "learning_rate": 3.874759564009404e-05, "loss": 0.7156, "step": 1063 }, { "epoch": 0.6805788758295355, "grad_norm": 2.542637586593628, "learning_rate": 3.873690959606754e-05, "loss": 0.7975, "step": 1064 }, { "epoch": 0.6812185176301271, "grad_norm": 2.5723378658294678, "learning_rate": 3.8726223552041036e-05, "loss": 0.8028, "step": 1065 }, { "epoch": 0.6818581594307188, "grad_norm": 2.502739429473877, "learning_rate": 3.871553750801453e-05, "loss": 0.7489, "step": 1066 }, { "epoch": 0.6824978012313104, "grad_norm": 2.404087781906128, "learning_rate": 3.8704851463988035e-05, "loss": 0.8516, "step": 1067 }, { "epoch": 0.6831374430319022, "grad_norm": 2.5609021186828613, "learning_rate": 3.869416541996153e-05, "loss": 0.7856, "step": 1068 }, { "epoch": 0.6837770848324938, "grad_norm": 2.3363285064697266, "learning_rate": 3.8683479375935034e-05, "loss": 0.7413, "step": 1069 }, { "epoch": 0.6844167266330855, "grad_norm": 1.9547827243804932, "learning_rate": 3.867279333190853e-05, "loss": 0.6662, "step": 1070 }, { "epoch": 0.6850563684336771, "grad_norm": 2.200296640396118, "learning_rate": 3.8662107287882026e-05, "loss": 0.7274, "step": 1071 }, { "epoch": 0.6856960102342688, "grad_norm": 2.2395646572113037, "learning_rate": 3.865142124385553e-05, "loss": 0.771, "step": 1072 }, { "epoch": 0.6863356520348605, "grad_norm": 2.557474136352539, "learning_rate": 3.8640735199829025e-05, "loss": 0.9435, "step": 1073 }, { "epoch": 0.6869752938354522, "grad_norm": 2.2866761684417725, "learning_rate": 3.8630049155802524e-05, "loss": 0.8536, "step": 1074 }, { "epoch": 0.6876149356360438, "grad_norm": 2.2908213138580322, "learning_rate": 3.861936311177602e-05, "loss": 0.7573, "step": 1075 }, { "epoch": 0.6882545774366355, "grad_norm": 2.2182838916778564, "learning_rate": 3.860867706774952e-05, "loss": 0.6515, "step": 1076 }, { "epoch": 0.6888942192372272, "grad_norm": 2.248753309249878, "learning_rate": 3.8597991023723015e-05, "loss": 0.7935, "step": 1077 }, { "epoch": 0.6895338610378188, "grad_norm": 2.6073074340820312, "learning_rate": 3.858730497969652e-05, "loss": 0.9092, "step": 1078 }, { "epoch": 0.6901735028384105, "grad_norm": 2.2033393383026123, "learning_rate": 3.8576618935670014e-05, "loss": 0.685, "step": 1079 }, { "epoch": 0.6908131446390021, "grad_norm": 2.3583688735961914, "learning_rate": 3.856593289164351e-05, "loss": 0.7056, "step": 1080 }, { "epoch": 0.6914527864395938, "grad_norm": 2.2697761058807373, "learning_rate": 3.855524684761701e-05, "loss": 0.7562, "step": 1081 }, { "epoch": 0.6920924282401855, "grad_norm": 2.031430244445801, "learning_rate": 3.854456080359051e-05, "loss": 0.6171, "step": 1082 }, { "epoch": 0.6927320700407772, "grad_norm": 2.197084903717041, "learning_rate": 3.853387475956401e-05, "loss": 0.7065, "step": 1083 }, { "epoch": 0.6933717118413688, "grad_norm": 2.3392534255981445, "learning_rate": 3.852318871553751e-05, "loss": 0.772, "step": 1084 }, { "epoch": 0.6940113536419605, "grad_norm": 2.515352487564087, "learning_rate": 3.851250267151101e-05, "loss": 0.8118, "step": 1085 }, { "epoch": 0.6946509954425522, "grad_norm": 2.1398885250091553, "learning_rate": 3.85018166274845e-05, "loss": 0.6057, "step": 1086 }, { "epoch": 0.6952906372431439, "grad_norm": 2.4276764392852783, "learning_rate": 3.849113058345801e-05, "loss": 0.7836, "step": 1087 }, { "epoch": 0.6959302790437355, "grad_norm": 2.5848066806793213, "learning_rate": 3.84804445394315e-05, "loss": 0.8149, "step": 1088 }, { "epoch": 0.6965699208443272, "grad_norm": 2.8381292819976807, "learning_rate": 3.8469758495405e-05, "loss": 0.865, "step": 1089 }, { "epoch": 0.6972095626449188, "grad_norm": 2.4076383113861084, "learning_rate": 3.84590724513785e-05, "loss": 0.7594, "step": 1090 }, { "epoch": 0.6978492044455105, "grad_norm": 1.9375122785568237, "learning_rate": 3.8448386407352e-05, "loss": 0.6165, "step": 1091 }, { "epoch": 0.6984888462461022, "grad_norm": 2.3143324851989746, "learning_rate": 3.84377003633255e-05, "loss": 0.8394, "step": 1092 }, { "epoch": 0.6991284880466938, "grad_norm": 2.289259433746338, "learning_rate": 3.8427014319299e-05, "loss": 0.781, "step": 1093 }, { "epoch": 0.6997681298472855, "grad_norm": 2.3176772594451904, "learning_rate": 3.84163282752725e-05, "loss": 0.7327, "step": 1094 }, { "epoch": 0.7004077716478772, "grad_norm": 2.1678993701934814, "learning_rate": 3.840564223124599e-05, "loss": 0.7075, "step": 1095 }, { "epoch": 0.7010474134484689, "grad_norm": 2.2163405418395996, "learning_rate": 3.8394956187219496e-05, "loss": 0.7503, "step": 1096 }, { "epoch": 0.7016870552490605, "grad_norm": 2.2522881031036377, "learning_rate": 3.838427014319299e-05, "loss": 0.6734, "step": 1097 }, { "epoch": 0.7023266970496522, "grad_norm": 1.8087902069091797, "learning_rate": 3.8373584099166495e-05, "loss": 0.5597, "step": 1098 }, { "epoch": 0.7029663388502438, "grad_norm": 2.146606683731079, "learning_rate": 3.836289805513999e-05, "loss": 0.7376, "step": 1099 }, { "epoch": 0.7036059806508356, "grad_norm": 2.0617082118988037, "learning_rate": 3.835221201111349e-05, "loss": 0.729, "step": 1100 }, { "epoch": 0.7042456224514272, "grad_norm": 2.1947948932647705, "learning_rate": 3.8341525967086986e-05, "loss": 0.7183, "step": 1101 }, { "epoch": 0.7048852642520189, "grad_norm": 2.5354106426239014, "learning_rate": 3.8330839923060486e-05, "loss": 0.8183, "step": 1102 }, { "epoch": 0.7055249060526105, "grad_norm": 2.1710827350616455, "learning_rate": 3.8320153879033985e-05, "loss": 0.7325, "step": 1103 }, { "epoch": 0.7061645478532022, "grad_norm": 2.609731674194336, "learning_rate": 3.8309467835007484e-05, "loss": 0.6996, "step": 1104 }, { "epoch": 0.7068041896537939, "grad_norm": 2.4650039672851562, "learning_rate": 3.8298781790980984e-05, "loss": 0.7949, "step": 1105 }, { "epoch": 0.7074438314543855, "grad_norm": 2.3932008743286133, "learning_rate": 3.8288095746954476e-05, "loss": 0.793, "step": 1106 }, { "epoch": 0.7080834732549772, "grad_norm": 2.358497142791748, "learning_rate": 3.827740970292798e-05, "loss": 0.6543, "step": 1107 }, { "epoch": 0.7087231150555688, "grad_norm": 2.4218297004699707, "learning_rate": 3.8266723658901475e-05, "loss": 0.8511, "step": 1108 }, { "epoch": 0.7093627568561606, "grad_norm": 2.6183223724365234, "learning_rate": 3.8256037614874974e-05, "loss": 0.8149, "step": 1109 }, { "epoch": 0.7100023986567522, "grad_norm": 2.5073516368865967, "learning_rate": 3.8245351570848474e-05, "loss": 0.7997, "step": 1110 }, { "epoch": 0.7106420404573439, "grad_norm": 2.2073638439178467, "learning_rate": 3.823466552682197e-05, "loss": 0.6717, "step": 1111 }, { "epoch": 0.7112816822579355, "grad_norm": 2.2807748317718506, "learning_rate": 3.8223979482795466e-05, "loss": 0.779, "step": 1112 }, { "epoch": 0.7119213240585273, "grad_norm": 2.1985785961151123, "learning_rate": 3.821329343876897e-05, "loss": 0.7542, "step": 1113 }, { "epoch": 0.7125609658591189, "grad_norm": 2.1787567138671875, "learning_rate": 3.8202607394742464e-05, "loss": 0.7691, "step": 1114 }, { "epoch": 0.7132006076597106, "grad_norm": 2.225193977355957, "learning_rate": 3.8191921350715964e-05, "loss": 0.7979, "step": 1115 }, { "epoch": 0.7138402494603022, "grad_norm": 2.2395787239074707, "learning_rate": 3.818123530668947e-05, "loss": 0.8434, "step": 1116 }, { "epoch": 0.714479891260894, "grad_norm": 1.956053376197815, "learning_rate": 3.817054926266296e-05, "loss": 0.722, "step": 1117 }, { "epoch": 0.7151195330614856, "grad_norm": 2.5603792667388916, "learning_rate": 3.815986321863646e-05, "loss": 0.8775, "step": 1118 }, { "epoch": 0.7157591748620772, "grad_norm": 2.296046495437622, "learning_rate": 3.814917717460996e-05, "loss": 0.7028, "step": 1119 }, { "epoch": 0.7163988166626689, "grad_norm": 1.8569482564926147, "learning_rate": 3.813849113058346e-05, "loss": 0.6368, "step": 1120 }, { "epoch": 0.7170384584632605, "grad_norm": 2.0514161586761475, "learning_rate": 3.812780508655695e-05, "loss": 0.7731, "step": 1121 }, { "epoch": 0.7176781002638523, "grad_norm": 2.2029731273651123, "learning_rate": 3.811711904253046e-05, "loss": 0.7006, "step": 1122 }, { "epoch": 0.7183177420644439, "grad_norm": 2.734997510910034, "learning_rate": 3.810643299850395e-05, "loss": 0.8155, "step": 1123 }, { "epoch": 0.7189573838650356, "grad_norm": 2.1038763523101807, "learning_rate": 3.809574695447746e-05, "loss": 0.728, "step": 1124 }, { "epoch": 0.7195970256656272, "grad_norm": 2.012888193130493, "learning_rate": 3.808506091045095e-05, "loss": 0.7125, "step": 1125 }, { "epoch": 0.720236667466219, "grad_norm": 2.211409568786621, "learning_rate": 3.807437486642445e-05, "loss": 0.7129, "step": 1126 }, { "epoch": 0.7208763092668106, "grad_norm": 2.124588966369629, "learning_rate": 3.806368882239795e-05, "loss": 0.7434, "step": 1127 }, { "epoch": 0.7215159510674023, "grad_norm": 2.153137445449829, "learning_rate": 3.805300277837145e-05, "loss": 0.6642, "step": 1128 }, { "epoch": 0.7221555928679939, "grad_norm": 1.9890538454055786, "learning_rate": 3.804231673434495e-05, "loss": 0.6062, "step": 1129 }, { "epoch": 0.7227952346685856, "grad_norm": 2.062160015106201, "learning_rate": 3.803163069031845e-05, "loss": 0.7052, "step": 1130 }, { "epoch": 0.7234348764691773, "grad_norm": 2.4277961254119873, "learning_rate": 3.802094464629195e-05, "loss": 0.8142, "step": 1131 }, { "epoch": 0.7240745182697689, "grad_norm": 2.8217086791992188, "learning_rate": 3.801025860226544e-05, "loss": 0.8606, "step": 1132 }, { "epoch": 0.7247141600703606, "grad_norm": 2.7864484786987305, "learning_rate": 3.7999572558238946e-05, "loss": 0.7296, "step": 1133 }, { "epoch": 0.7253538018709522, "grad_norm": 2.5194432735443115, "learning_rate": 3.798888651421244e-05, "loss": 0.8165, "step": 1134 }, { "epoch": 0.725993443671544, "grad_norm": 2.039736747741699, "learning_rate": 3.797820047018594e-05, "loss": 0.6588, "step": 1135 }, { "epoch": 0.7266330854721356, "grad_norm": 2.533721923828125, "learning_rate": 3.796751442615944e-05, "loss": 0.8458, "step": 1136 }, { "epoch": 0.7272727272727273, "grad_norm": 2.209456205368042, "learning_rate": 3.7956828382132936e-05, "loss": 0.7995, "step": 1137 }, { "epoch": 0.7279123690733189, "grad_norm": 2.631016969680786, "learning_rate": 3.7946142338106436e-05, "loss": 0.7869, "step": 1138 }, { "epoch": 0.7285520108739106, "grad_norm": 2.063816547393799, "learning_rate": 3.7935456294079935e-05, "loss": 0.6902, "step": 1139 }, { "epoch": 0.7291916526745023, "grad_norm": 2.4370014667510986, "learning_rate": 3.7924770250053434e-05, "loss": 0.81, "step": 1140 }, { "epoch": 0.729831294475094, "grad_norm": 2.1266560554504395, "learning_rate": 3.791408420602693e-05, "loss": 0.6829, "step": 1141 }, { "epoch": 0.7304709362756856, "grad_norm": 2.5482261180877686, "learning_rate": 3.790339816200043e-05, "loss": 0.8279, "step": 1142 }, { "epoch": 0.7311105780762773, "grad_norm": 2.3252758979797363, "learning_rate": 3.7892712117973926e-05, "loss": 0.7678, "step": 1143 }, { "epoch": 0.731750219876869, "grad_norm": 2.2964940071105957, "learning_rate": 3.7882026073947425e-05, "loss": 0.7522, "step": 1144 }, { "epoch": 0.7323898616774607, "grad_norm": 2.393054485321045, "learning_rate": 3.7871340029920924e-05, "loss": 0.7094, "step": 1145 }, { "epoch": 0.7330295034780523, "grad_norm": 2.358607530593872, "learning_rate": 3.7860653985894424e-05, "loss": 0.7883, "step": 1146 }, { "epoch": 0.7336691452786439, "grad_norm": 1.9570059776306152, "learning_rate": 3.784996794186792e-05, "loss": 0.6241, "step": 1147 }, { "epoch": 0.7343087870792356, "grad_norm": 2.6454644203186035, "learning_rate": 3.783928189784142e-05, "loss": 0.9089, "step": 1148 }, { "epoch": 0.7349484288798273, "grad_norm": 2.110250234603882, "learning_rate": 3.782859585381492e-05, "loss": 0.6571, "step": 1149 }, { "epoch": 0.735588070680419, "grad_norm": 2.5248188972473145, "learning_rate": 3.7817909809788414e-05, "loss": 0.7574, "step": 1150 }, { "epoch": 0.7362277124810106, "grad_norm": 2.235224485397339, "learning_rate": 3.780722376576192e-05, "loss": 0.6953, "step": 1151 }, { "epoch": 0.7368673542816023, "grad_norm": 2.39093017578125, "learning_rate": 3.779653772173541e-05, "loss": 0.7167, "step": 1152 }, { "epoch": 0.7375069960821939, "grad_norm": 2.3500821590423584, "learning_rate": 3.778585167770892e-05, "loss": 0.731, "step": 1153 }, { "epoch": 0.7381466378827857, "grad_norm": 2.0226786136627197, "learning_rate": 3.777516563368241e-05, "loss": 0.7074, "step": 1154 }, { "epoch": 0.7387862796833773, "grad_norm": 2.3884618282318115, "learning_rate": 3.776447958965591e-05, "loss": 0.7841, "step": 1155 }, { "epoch": 0.739425921483969, "grad_norm": 2.2239785194396973, "learning_rate": 3.775379354562941e-05, "loss": 0.7623, "step": 1156 }, { "epoch": 0.7400655632845606, "grad_norm": 2.219381809234619, "learning_rate": 3.774310750160291e-05, "loss": 0.7284, "step": 1157 }, { "epoch": 0.7407052050851524, "grad_norm": 1.8879082202911377, "learning_rate": 3.77324214575764e-05, "loss": 0.5831, "step": 1158 }, { "epoch": 0.741344846885744, "grad_norm": 2.2116897106170654, "learning_rate": 3.772173541354991e-05, "loss": 0.7395, "step": 1159 }, { "epoch": 0.7419844886863356, "grad_norm": 2.4407951831817627, "learning_rate": 3.77110493695234e-05, "loss": 0.7016, "step": 1160 }, { "epoch": 0.7426241304869273, "grad_norm": 2.165018320083618, "learning_rate": 3.77003633254969e-05, "loss": 0.7261, "step": 1161 }, { "epoch": 0.7432637722875189, "grad_norm": 2.498748540878296, "learning_rate": 3.768967728147041e-05, "loss": 0.8053, "step": 1162 }, { "epoch": 0.7439034140881107, "grad_norm": 2.3558831214904785, "learning_rate": 3.76789912374439e-05, "loss": 0.7776, "step": 1163 }, { "epoch": 0.7445430558887023, "grad_norm": 2.302196741104126, "learning_rate": 3.76683051934174e-05, "loss": 0.7353, "step": 1164 }, { "epoch": 0.745182697689294, "grad_norm": 2.3921613693237305, "learning_rate": 3.76576191493909e-05, "loss": 0.7795, "step": 1165 }, { "epoch": 0.7458223394898856, "grad_norm": 2.159858465194702, "learning_rate": 3.76469331053644e-05, "loss": 0.6372, "step": 1166 }, { "epoch": 0.7464619812904774, "grad_norm": 2.30668568611145, "learning_rate": 3.763624706133789e-05, "loss": 0.7958, "step": 1167 }, { "epoch": 0.747101623091069, "grad_norm": 2.2490170001983643, "learning_rate": 3.7625561017311396e-05, "loss": 0.6638, "step": 1168 }, { "epoch": 0.7477412648916607, "grad_norm": 2.138835906982422, "learning_rate": 3.761487497328489e-05, "loss": 0.6424, "step": 1169 }, { "epoch": 0.7483809066922523, "grad_norm": 2.253960609436035, "learning_rate": 3.760418892925839e-05, "loss": 0.6889, "step": 1170 }, { "epoch": 0.749020548492844, "grad_norm": 2.385439395904541, "learning_rate": 3.759350288523189e-05, "loss": 0.7765, "step": 1171 }, { "epoch": 0.7496601902934357, "grad_norm": 2.426828145980835, "learning_rate": 3.758281684120539e-05, "loss": 0.8011, "step": 1172 }, { "epoch": 0.7502998320940274, "grad_norm": 1.8592880964279175, "learning_rate": 3.7572130797178886e-05, "loss": 0.5694, "step": 1173 }, { "epoch": 0.750939473894619, "grad_norm": 2.2702317237854004, "learning_rate": 3.7561444753152386e-05, "loss": 0.7349, "step": 1174 }, { "epoch": 0.7515791156952106, "grad_norm": 2.5193734169006348, "learning_rate": 3.7550758709125885e-05, "loss": 0.8441, "step": 1175 }, { "epoch": 0.7522187574958024, "grad_norm": 2.177778959274292, "learning_rate": 3.754007266509938e-05, "loss": 0.7284, "step": 1176 }, { "epoch": 0.752858399296394, "grad_norm": 2.343198299407959, "learning_rate": 3.7529386621072884e-05, "loss": 0.7082, "step": 1177 }, { "epoch": 0.7534980410969857, "grad_norm": 2.4855828285217285, "learning_rate": 3.7518700577046376e-05, "loss": 0.8086, "step": 1178 }, { "epoch": 0.7541376828975773, "grad_norm": 2.3655359745025635, "learning_rate": 3.7508014533019876e-05, "loss": 0.7972, "step": 1179 }, { "epoch": 0.754777324698169, "grad_norm": 2.330594301223755, "learning_rate": 3.7497328488993375e-05, "loss": 0.7256, "step": 1180 }, { "epoch": 0.7554169664987607, "grad_norm": 2.319443702697754, "learning_rate": 3.7486642444966874e-05, "loss": 0.7633, "step": 1181 }, { "epoch": 0.7560566082993524, "grad_norm": 2.285426139831543, "learning_rate": 3.7475956400940374e-05, "loss": 0.7064, "step": 1182 }, { "epoch": 0.756696250099944, "grad_norm": 2.323478937149048, "learning_rate": 3.746527035691387e-05, "loss": 0.741, "step": 1183 }, { "epoch": 0.7573358919005357, "grad_norm": 2.4266202449798584, "learning_rate": 3.745458431288737e-05, "loss": 0.6884, "step": 1184 }, { "epoch": 0.7579755337011274, "grad_norm": 1.986000418663025, "learning_rate": 3.744389826886087e-05, "loss": 0.6064, "step": 1185 }, { "epoch": 0.7586151755017191, "grad_norm": 2.5264949798583984, "learning_rate": 3.743321222483437e-05, "loss": 0.6683, "step": 1186 }, { "epoch": 0.7592548173023107, "grad_norm": 1.829809546470642, "learning_rate": 3.7422526180807864e-05, "loss": 0.5837, "step": 1187 }, { "epoch": 0.7598944591029023, "grad_norm": 2.492159366607666, "learning_rate": 3.741184013678137e-05, "loss": 0.7506, "step": 1188 }, { "epoch": 0.760534100903494, "grad_norm": 2.6433253288269043, "learning_rate": 3.740115409275486e-05, "loss": 0.8966, "step": 1189 }, { "epoch": 0.7611737427040857, "grad_norm": 2.0945053100585938, "learning_rate": 3.739046804872836e-05, "loss": 0.6797, "step": 1190 }, { "epoch": 0.7618133845046774, "grad_norm": 2.496220111846924, "learning_rate": 3.737978200470186e-05, "loss": 0.8196, "step": 1191 }, { "epoch": 0.762453026305269, "grad_norm": 2.0942041873931885, "learning_rate": 3.736909596067536e-05, "loss": 0.6706, "step": 1192 }, { "epoch": 0.7630926681058607, "grad_norm": 2.4206995964050293, "learning_rate": 3.735840991664886e-05, "loss": 0.7298, "step": 1193 }, { "epoch": 0.7637323099064524, "grad_norm": 2.0311660766601562, "learning_rate": 3.734772387262236e-05, "loss": 0.6598, "step": 1194 }, { "epoch": 0.7643719517070441, "grad_norm": 2.4630625247955322, "learning_rate": 3.733703782859586e-05, "loss": 0.8063, "step": 1195 }, { "epoch": 0.7650115935076357, "grad_norm": 2.1187448501586914, "learning_rate": 3.732635178456935e-05, "loss": 0.6538, "step": 1196 }, { "epoch": 0.7656512353082274, "grad_norm": 2.124770402908325, "learning_rate": 3.731566574054286e-05, "loss": 0.7195, "step": 1197 }, { "epoch": 0.766290877108819, "grad_norm": 2.3621788024902344, "learning_rate": 3.730497969651635e-05, "loss": 0.7508, "step": 1198 }, { "epoch": 0.7669305189094108, "grad_norm": 2.4492368698120117, "learning_rate": 3.729429365248985e-05, "loss": 0.7801, "step": 1199 }, { "epoch": 0.7675701607100024, "grad_norm": 2.283175230026245, "learning_rate": 3.728360760846335e-05, "loss": 0.7324, "step": 1200 }, { "epoch": 0.7682098025105941, "grad_norm": 2.2819981575012207, "learning_rate": 3.727292156443685e-05, "loss": 0.7157, "step": 1201 }, { "epoch": 0.7688494443111857, "grad_norm": 2.2561097145080566, "learning_rate": 3.726223552041034e-05, "loss": 0.7515, "step": 1202 }, { "epoch": 0.7694890861117774, "grad_norm": 2.3356516361236572, "learning_rate": 3.725154947638385e-05, "loss": 0.732, "step": 1203 }, { "epoch": 0.7701287279123691, "grad_norm": 2.5061001777648926, "learning_rate": 3.724086343235734e-05, "loss": 0.7872, "step": 1204 }, { "epoch": 0.7707683697129607, "grad_norm": 2.3949875831604004, "learning_rate": 3.723017738833084e-05, "loss": 0.8577, "step": 1205 }, { "epoch": 0.7714080115135524, "grad_norm": 2.086625337600708, "learning_rate": 3.721949134430434e-05, "loss": 0.7291, "step": 1206 }, { "epoch": 0.772047653314144, "grad_norm": 2.0133514404296875, "learning_rate": 3.720880530027784e-05, "loss": 0.6942, "step": 1207 }, { "epoch": 0.7726872951147358, "grad_norm": 2.4376726150512695, "learning_rate": 3.7198119256251344e-05, "loss": 0.7066, "step": 1208 }, { "epoch": 0.7733269369153274, "grad_norm": 2.303718090057373, "learning_rate": 3.7187433212224836e-05, "loss": 0.7749, "step": 1209 }, { "epoch": 0.7739665787159191, "grad_norm": 2.269663095474243, "learning_rate": 3.7176747168198335e-05, "loss": 0.7027, "step": 1210 }, { "epoch": 0.7746062205165107, "grad_norm": 2.428384304046631, "learning_rate": 3.7166061124171835e-05, "loss": 0.7895, "step": 1211 }, { "epoch": 0.7752458623171025, "grad_norm": 2.3879854679107666, "learning_rate": 3.7155375080145334e-05, "loss": 0.6408, "step": 1212 }, { "epoch": 0.7758855041176941, "grad_norm": 2.0581510066986084, "learning_rate": 3.714468903611883e-05, "loss": 0.7013, "step": 1213 }, { "epoch": 0.7765251459182858, "grad_norm": 2.1578493118286133, "learning_rate": 3.713400299209233e-05, "loss": 0.7207, "step": 1214 }, { "epoch": 0.7771647877188774, "grad_norm": 2.231703996658325, "learning_rate": 3.7123316948065826e-05, "loss": 0.7003, "step": 1215 }, { "epoch": 0.777804429519469, "grad_norm": 2.595261335372925, "learning_rate": 3.7112630904039325e-05, "loss": 0.8654, "step": 1216 }, { "epoch": 0.7784440713200608, "grad_norm": 2.0633652210235596, "learning_rate": 3.7101944860012824e-05, "loss": 0.6487, "step": 1217 }, { "epoch": 0.7790837131206524, "grad_norm": 2.335822343826294, "learning_rate": 3.7091258815986324e-05, "loss": 0.7327, "step": 1218 }, { "epoch": 0.7797233549212441, "grad_norm": 2.217700958251953, "learning_rate": 3.708057277195982e-05, "loss": 0.7911, "step": 1219 }, { "epoch": 0.7803629967218357, "grad_norm": 2.5208353996276855, "learning_rate": 3.706988672793332e-05, "loss": 0.7615, "step": 1220 }, { "epoch": 0.7810026385224275, "grad_norm": 2.1740236282348633, "learning_rate": 3.705920068390682e-05, "loss": 0.7098, "step": 1221 }, { "epoch": 0.7816422803230191, "grad_norm": 2.3347630500793457, "learning_rate": 3.7048514639880314e-05, "loss": 0.7488, "step": 1222 }, { "epoch": 0.7822819221236108, "grad_norm": 2.2441177368164062, "learning_rate": 3.703782859585382e-05, "loss": 0.72, "step": 1223 }, { "epoch": 0.7829215639242024, "grad_norm": 2.384330987930298, "learning_rate": 3.702714255182731e-05, "loss": 0.6368, "step": 1224 }, { "epoch": 0.7835612057247942, "grad_norm": 2.217966079711914, "learning_rate": 3.701645650780081e-05, "loss": 0.7255, "step": 1225 }, { "epoch": 0.7842008475253858, "grad_norm": 2.063870668411255, "learning_rate": 3.700577046377431e-05, "loss": 0.6603, "step": 1226 }, { "epoch": 0.7848404893259775, "grad_norm": 2.428542375564575, "learning_rate": 3.699508441974781e-05, "loss": 0.7724, "step": 1227 }, { "epoch": 0.7854801311265691, "grad_norm": 2.1868059635162354, "learning_rate": 3.698439837572131e-05, "loss": 0.7082, "step": 1228 }, { "epoch": 0.7861197729271608, "grad_norm": 2.1543080806732178, "learning_rate": 3.697371233169481e-05, "loss": 0.6656, "step": 1229 }, { "epoch": 0.7867594147277525, "grad_norm": 2.152196168899536, "learning_rate": 3.696302628766831e-05, "loss": 0.6334, "step": 1230 }, { "epoch": 0.7873990565283441, "grad_norm": 2.2862462997436523, "learning_rate": 3.69523402436418e-05, "loss": 0.7609, "step": 1231 }, { "epoch": 0.7880386983289358, "grad_norm": 2.5716629028320312, "learning_rate": 3.694165419961531e-05, "loss": 0.7653, "step": 1232 }, { "epoch": 0.7886783401295274, "grad_norm": 1.9692749977111816, "learning_rate": 3.69309681555888e-05, "loss": 0.6466, "step": 1233 }, { "epoch": 0.7893179819301192, "grad_norm": 2.7022125720977783, "learning_rate": 3.69202821115623e-05, "loss": 0.849, "step": 1234 }, { "epoch": 0.7899576237307108, "grad_norm": 1.8877711296081543, "learning_rate": 3.69095960675358e-05, "loss": 0.5916, "step": 1235 }, { "epoch": 0.7905972655313025, "grad_norm": 2.6520678997039795, "learning_rate": 3.68989100235093e-05, "loss": 0.7768, "step": 1236 }, { "epoch": 0.7912369073318941, "grad_norm": 2.200363874435425, "learning_rate": 3.68882239794828e-05, "loss": 0.6769, "step": 1237 }, { "epoch": 0.7918765491324858, "grad_norm": 2.4259159564971924, "learning_rate": 3.68775379354563e-05, "loss": 0.7247, "step": 1238 }, { "epoch": 0.7925161909330775, "grad_norm": 2.5592780113220215, "learning_rate": 3.68668518914298e-05, "loss": 0.8512, "step": 1239 }, { "epoch": 0.7931558327336692, "grad_norm": 2.426992654800415, "learning_rate": 3.6856165847403296e-05, "loss": 0.7994, "step": 1240 }, { "epoch": 0.7937954745342608, "grad_norm": 2.3934638500213623, "learning_rate": 3.6845479803376795e-05, "loss": 0.7471, "step": 1241 }, { "epoch": 0.7944351163348525, "grad_norm": 2.1817221641540527, "learning_rate": 3.683479375935029e-05, "loss": 0.654, "step": 1242 }, { "epoch": 0.7950747581354441, "grad_norm": 2.0756351947784424, "learning_rate": 3.6824107715323794e-05, "loss": 0.6676, "step": 1243 }, { "epoch": 0.7957143999360358, "grad_norm": 2.337855339050293, "learning_rate": 3.681342167129729e-05, "loss": 0.7586, "step": 1244 }, { "epoch": 0.7963540417366275, "grad_norm": 2.191373109817505, "learning_rate": 3.6802735627270786e-05, "loss": 0.7261, "step": 1245 }, { "epoch": 0.7969936835372191, "grad_norm": 2.321526050567627, "learning_rate": 3.6792049583244285e-05, "loss": 0.7456, "step": 1246 }, { "epoch": 0.7976333253378108, "grad_norm": 2.1950039863586426, "learning_rate": 3.6781363539217785e-05, "loss": 0.7507, "step": 1247 }, { "epoch": 0.7982729671384025, "grad_norm": 2.4047510623931885, "learning_rate": 3.677067749519128e-05, "loss": 0.7925, "step": 1248 }, { "epoch": 0.7989126089389942, "grad_norm": 2.0003113746643066, "learning_rate": 3.6759991451164783e-05, "loss": 0.6481, "step": 1249 }, { "epoch": 0.7995522507395858, "grad_norm": 2.548973560333252, "learning_rate": 3.6749305407138276e-05, "loss": 0.7367, "step": 1250 }, { "epoch": 0.8001918925401775, "grad_norm": 2.0148658752441406, "learning_rate": 3.6738619363111775e-05, "loss": 0.6819, "step": 1251 }, { "epoch": 0.8008315343407691, "grad_norm": 2.331186294555664, "learning_rate": 3.6727933319085275e-05, "loss": 0.7564, "step": 1252 }, { "epoch": 0.8014711761413609, "grad_norm": 2.488466739654541, "learning_rate": 3.6717247275058774e-05, "loss": 0.7621, "step": 1253 }, { "epoch": 0.8021108179419525, "grad_norm": 2.188941478729248, "learning_rate": 3.6706561231032274e-05, "loss": 0.6951, "step": 1254 }, { "epoch": 0.8027504597425442, "grad_norm": 2.0087170600891113, "learning_rate": 3.669587518700577e-05, "loss": 0.6634, "step": 1255 }, { "epoch": 0.8033901015431358, "grad_norm": 2.3581948280334473, "learning_rate": 3.668518914297927e-05, "loss": 0.7753, "step": 1256 }, { "epoch": 0.8040297433437276, "grad_norm": 1.9907422065734863, "learning_rate": 3.6674503098952765e-05, "loss": 0.7065, "step": 1257 }, { "epoch": 0.8046693851443192, "grad_norm": 2.2611794471740723, "learning_rate": 3.666381705492627e-05, "loss": 0.7019, "step": 1258 }, { "epoch": 0.8053090269449108, "grad_norm": 1.917324423789978, "learning_rate": 3.6653131010899764e-05, "loss": 0.6498, "step": 1259 }, { "epoch": 0.8059486687455025, "grad_norm": 2.1342484951019287, "learning_rate": 3.664244496687326e-05, "loss": 0.6829, "step": 1260 }, { "epoch": 0.8065883105460941, "grad_norm": 2.04067063331604, "learning_rate": 3.663175892284676e-05, "loss": 0.6444, "step": 1261 }, { "epoch": 0.8072279523466859, "grad_norm": 2.402163028717041, "learning_rate": 3.662107287882026e-05, "loss": 0.7433, "step": 1262 }, { "epoch": 0.8078675941472775, "grad_norm": 2.3471882343292236, "learning_rate": 3.661038683479376e-05, "loss": 0.6615, "step": 1263 }, { "epoch": 0.8085072359478692, "grad_norm": 2.4029300212860107, "learning_rate": 3.659970079076726e-05, "loss": 0.78, "step": 1264 }, { "epoch": 0.8091468777484608, "grad_norm": 2.2626712322235107, "learning_rate": 3.658901474674076e-05, "loss": 0.7374, "step": 1265 }, { "epoch": 0.8097865195490526, "grad_norm": 2.345632314682007, "learning_rate": 3.657832870271426e-05, "loss": 0.7719, "step": 1266 }, { "epoch": 0.8104261613496442, "grad_norm": 2.2906014919281006, "learning_rate": 3.656764265868776e-05, "loss": 0.6792, "step": 1267 }, { "epoch": 0.8110658031502359, "grad_norm": 2.0952188968658447, "learning_rate": 3.655695661466125e-05, "loss": 0.6668, "step": 1268 }, { "epoch": 0.8117054449508275, "grad_norm": 2.4131739139556885, "learning_rate": 3.654627057063476e-05, "loss": 0.7827, "step": 1269 }, { "epoch": 0.8123450867514193, "grad_norm": 2.5857861042022705, "learning_rate": 3.653558452660825e-05, "loss": 0.7691, "step": 1270 }, { "epoch": 0.8129847285520109, "grad_norm": 2.2531378269195557, "learning_rate": 3.652489848258175e-05, "loss": 0.7299, "step": 1271 }, { "epoch": 0.8136243703526025, "grad_norm": 2.096651315689087, "learning_rate": 3.651421243855525e-05, "loss": 0.7459, "step": 1272 }, { "epoch": 0.8142640121531942, "grad_norm": 2.3306047916412354, "learning_rate": 3.650352639452875e-05, "loss": 0.7505, "step": 1273 }, { "epoch": 0.8149036539537858, "grad_norm": 2.36478590965271, "learning_rate": 3.649284035050225e-05, "loss": 0.7543, "step": 1274 }, { "epoch": 0.8155432957543776, "grad_norm": 2.353835344314575, "learning_rate": 3.6482154306475747e-05, "loss": 0.7407, "step": 1275 }, { "epoch": 0.8161829375549692, "grad_norm": 2.0713343620300293, "learning_rate": 3.6471468262449246e-05, "loss": 0.6208, "step": 1276 }, { "epoch": 0.8168225793555609, "grad_norm": 2.1474461555480957, "learning_rate": 3.646078221842274e-05, "loss": 0.647, "step": 1277 }, { "epoch": 0.8174622211561525, "grad_norm": 2.1109511852264404, "learning_rate": 3.6450096174396245e-05, "loss": 0.7284, "step": 1278 }, { "epoch": 0.8181018629567443, "grad_norm": 2.1241261959075928, "learning_rate": 3.643941013036974e-05, "loss": 0.7017, "step": 1279 }, { "epoch": 0.8187415047573359, "grad_norm": 2.4038076400756836, "learning_rate": 3.6428724086343237e-05, "loss": 0.7721, "step": 1280 }, { "epoch": 0.8193811465579276, "grad_norm": 2.181736469268799, "learning_rate": 3.6418038042316736e-05, "loss": 0.7521, "step": 1281 }, { "epoch": 0.8200207883585192, "grad_norm": 2.0946333408355713, "learning_rate": 3.6407351998290235e-05, "loss": 0.7338, "step": 1282 }, { "epoch": 0.8206604301591109, "grad_norm": 2.207449197769165, "learning_rate": 3.639666595426373e-05, "loss": 0.7318, "step": 1283 }, { "epoch": 0.8213000719597026, "grad_norm": 2.225128650665283, "learning_rate": 3.6385979910237234e-05, "loss": 0.7681, "step": 1284 }, { "epoch": 0.8219397137602943, "grad_norm": 2.0560288429260254, "learning_rate": 3.6375293866210733e-05, "loss": 0.6559, "step": 1285 }, { "epoch": 0.8225793555608859, "grad_norm": 2.371389389038086, "learning_rate": 3.6364607822184226e-05, "loss": 0.8418, "step": 1286 }, { "epoch": 0.8232189973614775, "grad_norm": 2.5029571056365967, "learning_rate": 3.635392177815773e-05, "loss": 0.7838, "step": 1287 }, { "epoch": 0.8238586391620693, "grad_norm": 2.071765422821045, "learning_rate": 3.6343235734131225e-05, "loss": 0.666, "step": 1288 }, { "epoch": 0.8244982809626609, "grad_norm": 2.1000685691833496, "learning_rate": 3.6332549690104724e-05, "loss": 0.7008, "step": 1289 }, { "epoch": 0.8251379227632526, "grad_norm": 2.053774356842041, "learning_rate": 3.6321863646078223e-05, "loss": 0.7242, "step": 1290 }, { "epoch": 0.8257775645638442, "grad_norm": 2.024888038635254, "learning_rate": 3.631117760205172e-05, "loss": 0.6743, "step": 1291 }, { "epoch": 0.8264172063644359, "grad_norm": 2.2509822845458984, "learning_rate": 3.6300491558025215e-05, "loss": 0.768, "step": 1292 }, { "epoch": 0.8270568481650276, "grad_norm": 2.769113302230835, "learning_rate": 3.628980551399872e-05, "loss": 0.8041, "step": 1293 }, { "epoch": 0.8276964899656193, "grad_norm": 2.3014938831329346, "learning_rate": 3.6279119469972214e-05, "loss": 0.6788, "step": 1294 }, { "epoch": 0.8283361317662109, "grad_norm": 2.126314163208008, "learning_rate": 3.626843342594572e-05, "loss": 0.6831, "step": 1295 }, { "epoch": 0.8289757735668026, "grad_norm": 2.3572607040405273, "learning_rate": 3.625774738191921e-05, "loss": 0.7451, "step": 1296 }, { "epoch": 0.8296154153673942, "grad_norm": 2.5624842643737793, "learning_rate": 3.624706133789271e-05, "loss": 0.8626, "step": 1297 }, { "epoch": 0.830255057167986, "grad_norm": 2.42989444732666, "learning_rate": 3.623637529386621e-05, "loss": 0.8091, "step": 1298 }, { "epoch": 0.8308946989685776, "grad_norm": 2.4899890422821045, "learning_rate": 3.622568924983971e-05, "loss": 0.7937, "step": 1299 }, { "epoch": 0.8315343407691692, "grad_norm": 1.9585925340652466, "learning_rate": 3.621500320581321e-05, "loss": 0.6753, "step": 1300 }, { "epoch": 0.8321739825697609, "grad_norm": 2.3551599979400635, "learning_rate": 3.620431716178671e-05, "loss": 0.7959, "step": 1301 }, { "epoch": 0.8328136243703526, "grad_norm": 2.1406025886535645, "learning_rate": 3.619363111776021e-05, "loss": 0.7247, "step": 1302 }, { "epoch": 0.8334532661709443, "grad_norm": 2.042062759399414, "learning_rate": 3.61829450737337e-05, "loss": 0.6943, "step": 1303 }, { "epoch": 0.8340929079715359, "grad_norm": 2.0793874263763428, "learning_rate": 3.617225902970721e-05, "loss": 0.6605, "step": 1304 }, { "epoch": 0.8347325497721276, "grad_norm": 2.354625940322876, "learning_rate": 3.61615729856807e-05, "loss": 0.7457, "step": 1305 }, { "epoch": 0.8353721915727192, "grad_norm": 2.216197967529297, "learning_rate": 3.61508869416542e-05, "loss": 0.7381, "step": 1306 }, { "epoch": 0.836011833373311, "grad_norm": 2.133580446243286, "learning_rate": 3.61402008976277e-05, "loss": 0.6919, "step": 1307 }, { "epoch": 0.8366514751739026, "grad_norm": 2.187563180923462, "learning_rate": 3.61295148536012e-05, "loss": 0.7091, "step": 1308 }, { "epoch": 0.8372911169744943, "grad_norm": 2.0050559043884277, "learning_rate": 3.61188288095747e-05, "loss": 0.6969, "step": 1309 }, { "epoch": 0.8379307587750859, "grad_norm": 1.9472792148590088, "learning_rate": 3.61081427655482e-05, "loss": 0.6985, "step": 1310 }, { "epoch": 0.8385704005756777, "grad_norm": 1.801424503326416, "learning_rate": 3.6097456721521696e-05, "loss": 0.5894, "step": 1311 }, { "epoch": 0.8392100423762693, "grad_norm": 2.658172607421875, "learning_rate": 3.608677067749519e-05, "loss": 0.8383, "step": 1312 }, { "epoch": 0.839849684176861, "grad_norm": 2.0976152420043945, "learning_rate": 3.6076084633468695e-05, "loss": 0.6931, "step": 1313 }, { "epoch": 0.8404893259774526, "grad_norm": 2.410163164138794, "learning_rate": 3.606539858944219e-05, "loss": 0.6566, "step": 1314 }, { "epoch": 0.8411289677780442, "grad_norm": 2.395289182662964, "learning_rate": 3.605471254541569e-05, "loss": 0.8125, "step": 1315 }, { "epoch": 0.841768609578636, "grad_norm": 2.275268793106079, "learning_rate": 3.6044026501389187e-05, "loss": 0.6973, "step": 1316 }, { "epoch": 0.8424082513792276, "grad_norm": 2.461775541305542, "learning_rate": 3.6033340457362686e-05, "loss": 0.7726, "step": 1317 }, { "epoch": 0.8430478931798193, "grad_norm": 2.811631202697754, "learning_rate": 3.6022654413336185e-05, "loss": 0.8024, "step": 1318 }, { "epoch": 0.8436875349804109, "grad_norm": 2.365971565246582, "learning_rate": 3.6011968369309685e-05, "loss": 0.731, "step": 1319 }, { "epoch": 0.8443271767810027, "grad_norm": 2.075807571411133, "learning_rate": 3.6001282325283184e-05, "loss": 0.6405, "step": 1320 }, { "epoch": 0.8449668185815943, "grad_norm": 2.1783554553985596, "learning_rate": 3.599059628125668e-05, "loss": 0.7214, "step": 1321 }, { "epoch": 0.845606460382186, "grad_norm": 1.9325662851333618, "learning_rate": 3.597991023723018e-05, "loss": 0.5924, "step": 1322 }, { "epoch": 0.8462461021827776, "grad_norm": 2.0185577869415283, "learning_rate": 3.5969224193203675e-05, "loss": 0.6725, "step": 1323 }, { "epoch": 0.8468857439833694, "grad_norm": 2.0572102069854736, "learning_rate": 3.595853814917718e-05, "loss": 0.6862, "step": 1324 }, { "epoch": 0.847525385783961, "grad_norm": 2.135138750076294, "learning_rate": 3.5947852105150674e-05, "loss": 0.6981, "step": 1325 }, { "epoch": 0.8481650275845527, "grad_norm": 2.1671605110168457, "learning_rate": 3.593716606112417e-05, "loss": 0.7776, "step": 1326 }, { "epoch": 0.8488046693851443, "grad_norm": 2.223288059234619, "learning_rate": 3.592648001709767e-05, "loss": 0.7327, "step": 1327 }, { "epoch": 0.8494443111857359, "grad_norm": 2.356409788131714, "learning_rate": 3.591579397307117e-05, "loss": 0.7353, "step": 1328 }, { "epoch": 0.8500839529863277, "grad_norm": 2.5746231079101562, "learning_rate": 3.5905107929044665e-05, "loss": 0.8148, "step": 1329 }, { "epoch": 0.8507235947869193, "grad_norm": 2.176095485687256, "learning_rate": 3.589442188501817e-05, "loss": 0.7427, "step": 1330 }, { "epoch": 0.851363236587511, "grad_norm": 2.352288246154785, "learning_rate": 3.588373584099167e-05, "loss": 0.7535, "step": 1331 }, { "epoch": 0.8520028783881026, "grad_norm": 2.154296875, "learning_rate": 3.587304979696516e-05, "loss": 0.6683, "step": 1332 }, { "epoch": 0.8526425201886944, "grad_norm": 2.0666000843048096, "learning_rate": 3.586236375293867e-05, "loss": 0.6675, "step": 1333 }, { "epoch": 0.853282161989286, "grad_norm": 2.3061776161193848, "learning_rate": 3.585167770891216e-05, "loss": 0.7446, "step": 1334 }, { "epoch": 0.8539218037898777, "grad_norm": 2.3385169506073, "learning_rate": 3.584099166488566e-05, "loss": 0.7534, "step": 1335 }, { "epoch": 0.8545614455904693, "grad_norm": 2.1738851070404053, "learning_rate": 3.583030562085916e-05, "loss": 0.7418, "step": 1336 }, { "epoch": 0.855201087391061, "grad_norm": 2.168400287628174, "learning_rate": 3.581961957683266e-05, "loss": 0.5973, "step": 1337 }, { "epoch": 0.8558407291916527, "grad_norm": 2.1141319274902344, "learning_rate": 3.580893353280615e-05, "loss": 0.6944, "step": 1338 }, { "epoch": 0.8564803709922444, "grad_norm": 2.0818159580230713, "learning_rate": 3.579824748877966e-05, "loss": 0.7369, "step": 1339 }, { "epoch": 0.857120012792836, "grad_norm": 2.6422712802886963, "learning_rate": 3.578756144475315e-05, "loss": 0.8136, "step": 1340 }, { "epoch": 0.8577596545934277, "grad_norm": 2.1801748275756836, "learning_rate": 3.577687540072665e-05, "loss": 0.7068, "step": 1341 }, { "epoch": 0.8583992963940194, "grad_norm": 2.3806281089782715, "learning_rate": 3.576618935670015e-05, "loss": 0.8342, "step": 1342 }, { "epoch": 0.859038938194611, "grad_norm": 2.6606218814849854, "learning_rate": 3.575550331267365e-05, "loss": 0.9223, "step": 1343 }, { "epoch": 0.8596785799952027, "grad_norm": 2.5878489017486572, "learning_rate": 3.574481726864715e-05, "loss": 0.81, "step": 1344 }, { "epoch": 0.8603182217957943, "grad_norm": 2.1978557109832764, "learning_rate": 3.573413122462065e-05, "loss": 0.7554, "step": 1345 }, { "epoch": 0.860957863596386, "grad_norm": 2.2777504920959473, "learning_rate": 3.572344518059415e-05, "loss": 0.7967, "step": 1346 }, { "epoch": 0.8615975053969777, "grad_norm": 2.2588183879852295, "learning_rate": 3.571275913656764e-05, "loss": 0.7188, "step": 1347 }, { "epoch": 0.8622371471975694, "grad_norm": 2.308361768722534, "learning_rate": 3.5702073092541146e-05, "loss": 0.8122, "step": 1348 }, { "epoch": 0.862876788998161, "grad_norm": 2.2274303436279297, "learning_rate": 3.569138704851464e-05, "loss": 0.6891, "step": 1349 }, { "epoch": 0.8635164307987527, "grad_norm": 1.8308266401290894, "learning_rate": 3.5680701004488144e-05, "loss": 0.5985, "step": 1350 }, { "epoch": 0.8641560725993443, "grad_norm": 2.005376100540161, "learning_rate": 3.567001496046164e-05, "loss": 0.7149, "step": 1351 }, { "epoch": 0.8647957143999361, "grad_norm": 2.1678292751312256, "learning_rate": 3.5659328916435136e-05, "loss": 0.7674, "step": 1352 }, { "epoch": 0.8654353562005277, "grad_norm": 2.299746513366699, "learning_rate": 3.5648642872408636e-05, "loss": 0.7136, "step": 1353 }, { "epoch": 0.8660749980011194, "grad_norm": 2.1002919673919678, "learning_rate": 3.5637956828382135e-05, "loss": 0.6933, "step": 1354 }, { "epoch": 0.866714639801711, "grad_norm": 2.0909488201141357, "learning_rate": 3.5627270784355635e-05, "loss": 0.7582, "step": 1355 }, { "epoch": 0.8673542816023027, "grad_norm": 2.0758700370788574, "learning_rate": 3.5616584740329134e-05, "loss": 0.7156, "step": 1356 }, { "epoch": 0.8679939234028944, "grad_norm": 2.148381233215332, "learning_rate": 3.560589869630263e-05, "loss": 0.7108, "step": 1357 }, { "epoch": 0.868633565203486, "grad_norm": 2.36637806892395, "learning_rate": 3.5595212652276126e-05, "loss": 0.7925, "step": 1358 }, { "epoch": 0.8692732070040777, "grad_norm": 2.166687488555908, "learning_rate": 3.558452660824963e-05, "loss": 0.6827, "step": 1359 }, { "epoch": 0.8699128488046693, "grad_norm": 2.006511688232422, "learning_rate": 3.5573840564223125e-05, "loss": 0.6206, "step": 1360 }, { "epoch": 0.8705524906052611, "grad_norm": 2.1921260356903076, "learning_rate": 3.5563154520196624e-05, "loss": 0.7716, "step": 1361 }, { "epoch": 0.8711921324058527, "grad_norm": 2.094515323638916, "learning_rate": 3.555246847617012e-05, "loss": 0.6804, "step": 1362 }, { "epoch": 0.8718317742064444, "grad_norm": 2.1194989681243896, "learning_rate": 3.554178243214362e-05, "loss": 0.719, "step": 1363 }, { "epoch": 0.872471416007036, "grad_norm": 2.3637473583221436, "learning_rate": 3.553109638811712e-05, "loss": 0.7319, "step": 1364 }, { "epoch": 0.8731110578076278, "grad_norm": 2.376315116882324, "learning_rate": 3.552041034409062e-05, "loss": 0.8048, "step": 1365 }, { "epoch": 0.8737506996082194, "grad_norm": 2.3273696899414062, "learning_rate": 3.550972430006412e-05, "loss": 0.7703, "step": 1366 }, { "epoch": 0.8743903414088111, "grad_norm": 2.234257936477661, "learning_rate": 3.549903825603761e-05, "loss": 0.6514, "step": 1367 }, { "epoch": 0.8750299832094027, "grad_norm": 2.3246567249298096, "learning_rate": 3.548835221201112e-05, "loss": 0.7174, "step": 1368 }, { "epoch": 0.8756696250099945, "grad_norm": 2.4329986572265625, "learning_rate": 3.547766616798461e-05, "loss": 0.6824, "step": 1369 }, { "epoch": 0.8763092668105861, "grad_norm": 2.325556516647339, "learning_rate": 3.546698012395811e-05, "loss": 0.733, "step": 1370 }, { "epoch": 0.8769489086111777, "grad_norm": 2.095371723175049, "learning_rate": 3.545629407993161e-05, "loss": 0.7055, "step": 1371 }, { "epoch": 0.8775885504117694, "grad_norm": 2.398172616958618, "learning_rate": 3.544560803590511e-05, "loss": 0.8113, "step": 1372 }, { "epoch": 0.878228192212361, "grad_norm": 2.422332286834717, "learning_rate": 3.54349219918786e-05, "loss": 0.774, "step": 1373 }, { "epoch": 0.8788678340129528, "grad_norm": 2.316647529602051, "learning_rate": 3.542423594785211e-05, "loss": 0.7921, "step": 1374 }, { "epoch": 0.8795074758135444, "grad_norm": 2.2691285610198975, "learning_rate": 3.54135499038256e-05, "loss": 0.8109, "step": 1375 }, { "epoch": 0.8801471176141361, "grad_norm": 2.6274847984313965, "learning_rate": 3.54028638597991e-05, "loss": 0.8763, "step": 1376 }, { "epoch": 0.8807867594147277, "grad_norm": 2.0136759281158447, "learning_rate": 3.539217781577261e-05, "loss": 0.6571, "step": 1377 }, { "epoch": 0.8814264012153195, "grad_norm": 2.4123120307922363, "learning_rate": 3.53814917717461e-05, "loss": 0.7667, "step": 1378 }, { "epoch": 0.8820660430159111, "grad_norm": 2.4716055393218994, "learning_rate": 3.5370805727719606e-05, "loss": 0.7813, "step": 1379 }, { "epoch": 0.8827056848165028, "grad_norm": 2.250933885574341, "learning_rate": 3.53601196836931e-05, "loss": 0.7448, "step": 1380 }, { "epoch": 0.8833453266170944, "grad_norm": 2.155230760574341, "learning_rate": 3.53494336396666e-05, "loss": 0.6957, "step": 1381 }, { "epoch": 0.8839849684176861, "grad_norm": 2.1631875038146973, "learning_rate": 3.53387475956401e-05, "loss": 0.7243, "step": 1382 }, { "epoch": 0.8846246102182778, "grad_norm": 2.1185851097106934, "learning_rate": 3.5328061551613596e-05, "loss": 0.751, "step": 1383 }, { "epoch": 0.8852642520188694, "grad_norm": 2.457045316696167, "learning_rate": 3.531737550758709e-05, "loss": 0.8195, "step": 1384 }, { "epoch": 0.8859038938194611, "grad_norm": 2.2588415145874023, "learning_rate": 3.5306689463560595e-05, "loss": 0.7922, "step": 1385 }, { "epoch": 0.8865435356200527, "grad_norm": 2.1469454765319824, "learning_rate": 3.529600341953409e-05, "loss": 0.7189, "step": 1386 }, { "epoch": 0.8871831774206445, "grad_norm": 2.1095893383026123, "learning_rate": 3.528531737550759e-05, "loss": 0.6831, "step": 1387 }, { "epoch": 0.8878228192212361, "grad_norm": 1.88996422290802, "learning_rate": 3.5274631331481086e-05, "loss": 0.5968, "step": 1388 }, { "epoch": 0.8884624610218278, "grad_norm": 2.091191053390503, "learning_rate": 3.5263945287454586e-05, "loss": 0.6709, "step": 1389 }, { "epoch": 0.8891021028224194, "grad_norm": 2.206300735473633, "learning_rate": 3.5253259243428085e-05, "loss": 0.6793, "step": 1390 }, { "epoch": 0.8897417446230111, "grad_norm": 2.602550506591797, "learning_rate": 3.5242573199401584e-05, "loss": 0.8169, "step": 1391 }, { "epoch": 0.8903813864236028, "grad_norm": 2.4747698307037354, "learning_rate": 3.5231887155375084e-05, "loss": 0.6866, "step": 1392 }, { "epoch": 0.8910210282241945, "grad_norm": 2.1457183361053467, "learning_rate": 3.5221201111348576e-05, "loss": 0.6873, "step": 1393 }, { "epoch": 0.8916606700247861, "grad_norm": 2.2383368015289307, "learning_rate": 3.521051506732208e-05, "loss": 0.6547, "step": 1394 }, { "epoch": 0.8923003118253778, "grad_norm": 2.245839834213257, "learning_rate": 3.5199829023295575e-05, "loss": 0.6049, "step": 1395 }, { "epoch": 0.8929399536259695, "grad_norm": 2.3442234992980957, "learning_rate": 3.5189142979269074e-05, "loss": 0.751, "step": 1396 }, { "epoch": 0.8935795954265612, "grad_norm": 2.34509015083313, "learning_rate": 3.5178456935242574e-05, "loss": 0.7231, "step": 1397 }, { "epoch": 0.8942192372271528, "grad_norm": 2.611557722091675, "learning_rate": 3.516777089121607e-05, "loss": 0.7842, "step": 1398 }, { "epoch": 0.8948588790277444, "grad_norm": 2.5007386207580566, "learning_rate": 3.515708484718957e-05, "loss": 0.755, "step": 1399 }, { "epoch": 0.8954985208283361, "grad_norm": 2.210387706756592, "learning_rate": 3.514639880316307e-05, "loss": 0.743, "step": 1400 }, { "epoch": 0.8961381626289278, "grad_norm": 2.619443655014038, "learning_rate": 3.513571275913657e-05, "loss": 0.7962, "step": 1401 }, { "epoch": 0.8967778044295195, "grad_norm": 2.3215034008026123, "learning_rate": 3.5125026715110064e-05, "loss": 0.7684, "step": 1402 }, { "epoch": 0.8974174462301111, "grad_norm": 2.1196274757385254, "learning_rate": 3.511434067108357e-05, "loss": 0.6856, "step": 1403 }, { "epoch": 0.8980570880307028, "grad_norm": 1.861092448234558, "learning_rate": 3.510365462705706e-05, "loss": 0.6071, "step": 1404 }, { "epoch": 0.8986967298312944, "grad_norm": 2.4183058738708496, "learning_rate": 3.509296858303056e-05, "loss": 0.8031, "step": 1405 }, { "epoch": 0.8993363716318862, "grad_norm": 2.504423141479492, "learning_rate": 3.508228253900406e-05, "loss": 0.8647, "step": 1406 }, { "epoch": 0.8999760134324778, "grad_norm": 2.1402695178985596, "learning_rate": 3.507159649497756e-05, "loss": 0.7569, "step": 1407 }, { "epoch": 0.9006156552330695, "grad_norm": 2.400038719177246, "learning_rate": 3.506091045095106e-05, "loss": 0.805, "step": 1408 }, { "epoch": 0.9012552970336611, "grad_norm": 1.9367976188659668, "learning_rate": 3.505022440692456e-05, "loss": 0.6685, "step": 1409 }, { "epoch": 0.9018949388342529, "grad_norm": 1.9515469074249268, "learning_rate": 3.503953836289806e-05, "loss": 0.6853, "step": 1410 }, { "epoch": 0.9025345806348445, "grad_norm": 2.433276891708374, "learning_rate": 3.502885231887156e-05, "loss": 0.7776, "step": 1411 }, { "epoch": 0.9031742224354361, "grad_norm": 1.9331090450286865, "learning_rate": 3.501816627484506e-05, "loss": 0.5848, "step": 1412 }, { "epoch": 0.9038138642360278, "grad_norm": 2.093459367752075, "learning_rate": 3.500748023081855e-05, "loss": 0.6599, "step": 1413 }, { "epoch": 0.9044535060366194, "grad_norm": 2.2528626918792725, "learning_rate": 3.4996794186792056e-05, "loss": 0.6265, "step": 1414 }, { "epoch": 0.9050931478372112, "grad_norm": 2.2050235271453857, "learning_rate": 3.498610814276555e-05, "loss": 0.7569, "step": 1415 }, { "epoch": 0.9057327896378028, "grad_norm": 2.386476993560791, "learning_rate": 3.497542209873905e-05, "loss": 0.7386, "step": 1416 }, { "epoch": 0.9063724314383945, "grad_norm": 2.1573355197906494, "learning_rate": 3.496473605471255e-05, "loss": 0.7586, "step": 1417 }, { "epoch": 0.9070120732389861, "grad_norm": 2.611687183380127, "learning_rate": 3.495405001068605e-05, "loss": 0.9539, "step": 1418 }, { "epoch": 0.9076517150395779, "grad_norm": 1.9923269748687744, "learning_rate": 3.494336396665954e-05, "loss": 0.6406, "step": 1419 }, { "epoch": 0.9082913568401695, "grad_norm": 2.258986234664917, "learning_rate": 3.4932677922633046e-05, "loss": 0.7374, "step": 1420 }, { "epoch": 0.9089309986407612, "grad_norm": 2.371077299118042, "learning_rate": 3.492199187860654e-05, "loss": 0.7627, "step": 1421 }, { "epoch": 0.9095706404413528, "grad_norm": 2.3209691047668457, "learning_rate": 3.491130583458004e-05, "loss": 0.7666, "step": 1422 }, { "epoch": 0.9102102822419446, "grad_norm": 2.3601765632629395, "learning_rate": 3.4900619790553544e-05, "loss": 0.9136, "step": 1423 }, { "epoch": 0.9108499240425362, "grad_norm": 2.2075514793395996, "learning_rate": 3.4889933746527036e-05, "loss": 0.7335, "step": 1424 }, { "epoch": 0.9114895658431279, "grad_norm": 2.5802149772644043, "learning_rate": 3.4879247702500536e-05, "loss": 0.8581, "step": 1425 }, { "epoch": 0.9121292076437195, "grad_norm": 2.288961887359619, "learning_rate": 3.4868561658474035e-05, "loss": 0.7055, "step": 1426 }, { "epoch": 0.9127688494443111, "grad_norm": 2.0689785480499268, "learning_rate": 3.4857875614447534e-05, "loss": 0.6377, "step": 1427 }, { "epoch": 0.9134084912449029, "grad_norm": 2.295675039291382, "learning_rate": 3.484718957042103e-05, "loss": 0.7938, "step": 1428 }, { "epoch": 0.9140481330454945, "grad_norm": 1.9098725318908691, "learning_rate": 3.483650352639453e-05, "loss": 0.5767, "step": 1429 }, { "epoch": 0.9146877748460862, "grad_norm": 2.506603956222534, "learning_rate": 3.4825817482368026e-05, "loss": 0.8863, "step": 1430 }, { "epoch": 0.9153274166466778, "grad_norm": 2.042794704437256, "learning_rate": 3.4815131438341525e-05, "loss": 0.7206, "step": 1431 }, { "epoch": 0.9159670584472696, "grad_norm": 1.9123684167861938, "learning_rate": 3.4804445394315024e-05, "loss": 0.6235, "step": 1432 }, { "epoch": 0.9166067002478612, "grad_norm": 1.985778570175171, "learning_rate": 3.4793759350288524e-05, "loss": 0.6174, "step": 1433 }, { "epoch": 0.9172463420484529, "grad_norm": 1.978415846824646, "learning_rate": 3.478307330626202e-05, "loss": 0.6026, "step": 1434 }, { "epoch": 0.9178859838490445, "grad_norm": 2.103729486465454, "learning_rate": 3.477238726223552e-05, "loss": 0.6872, "step": 1435 }, { "epoch": 0.9185256256496362, "grad_norm": 2.2244601249694824, "learning_rate": 3.476170121820902e-05, "loss": 0.7687, "step": 1436 }, { "epoch": 0.9191652674502279, "grad_norm": 2.4220504760742188, "learning_rate": 3.475101517418252e-05, "loss": 0.7686, "step": 1437 }, { "epoch": 0.9198049092508196, "grad_norm": 2.257708787918091, "learning_rate": 3.474032913015602e-05, "loss": 0.6922, "step": 1438 }, { "epoch": 0.9204445510514112, "grad_norm": 2.208747625350952, "learning_rate": 3.472964308612951e-05, "loss": 0.7214, "step": 1439 }, { "epoch": 0.9210841928520028, "grad_norm": 2.384122371673584, "learning_rate": 3.471895704210302e-05, "loss": 0.7772, "step": 1440 }, { "epoch": 0.9217238346525946, "grad_norm": 2.1721436977386475, "learning_rate": 3.470827099807651e-05, "loss": 0.6018, "step": 1441 }, { "epoch": 0.9223634764531862, "grad_norm": 2.0613491535186768, "learning_rate": 3.469758495405001e-05, "loss": 0.773, "step": 1442 }, { "epoch": 0.9230031182537779, "grad_norm": 1.8981919288635254, "learning_rate": 3.468689891002351e-05, "loss": 0.592, "step": 1443 }, { "epoch": 0.9236427600543695, "grad_norm": 2.4995343685150146, "learning_rate": 3.467621286599701e-05, "loss": 0.8375, "step": 1444 }, { "epoch": 0.9242824018549612, "grad_norm": 2.4255168437957764, "learning_rate": 3.466552682197051e-05, "loss": 0.8258, "step": 1445 }, { "epoch": 0.9249220436555529, "grad_norm": 2.2315685749053955, "learning_rate": 3.465484077794401e-05, "loss": 0.6425, "step": 1446 }, { "epoch": 0.9255616854561446, "grad_norm": 2.0109851360321045, "learning_rate": 3.464415473391751e-05, "loss": 0.696, "step": 1447 }, { "epoch": 0.9262013272567362, "grad_norm": 2.160836935043335, "learning_rate": 3.4633468689891e-05, "loss": 0.7189, "step": 1448 }, { "epoch": 0.9268409690573279, "grad_norm": 2.1626944541931152, "learning_rate": 3.462278264586451e-05, "loss": 0.7197, "step": 1449 }, { "epoch": 0.9274806108579196, "grad_norm": 2.059540033340454, "learning_rate": 3.4612096601838e-05, "loss": 0.774, "step": 1450 }, { "epoch": 0.9281202526585113, "grad_norm": 1.9875566959381104, "learning_rate": 3.46014105578115e-05, "loss": 0.7031, "step": 1451 }, { "epoch": 0.9287598944591029, "grad_norm": 2.532210111618042, "learning_rate": 3.4590724513785e-05, "loss": 0.693, "step": 1452 }, { "epoch": 0.9293995362596946, "grad_norm": 2.38069224357605, "learning_rate": 3.45800384697585e-05, "loss": 0.8662, "step": 1453 }, { "epoch": 0.9300391780602862, "grad_norm": 2.1424291133880615, "learning_rate": 3.456935242573199e-05, "loss": 0.6892, "step": 1454 }, { "epoch": 0.9306788198608779, "grad_norm": 2.37778902053833, "learning_rate": 3.4558666381705496e-05, "loss": 0.7303, "step": 1455 }, { "epoch": 0.9313184616614696, "grad_norm": 2.07857608795166, "learning_rate": 3.4547980337678996e-05, "loss": 0.6485, "step": 1456 }, { "epoch": 0.9319581034620612, "grad_norm": 1.9782344102859497, "learning_rate": 3.453729429365249e-05, "loss": 0.664, "step": 1457 }, { "epoch": 0.9325977452626529, "grad_norm": 2.370725631713867, "learning_rate": 3.4526608249625994e-05, "loss": 0.8319, "step": 1458 }, { "epoch": 0.9332373870632446, "grad_norm": 2.090789318084717, "learning_rate": 3.451592220559949e-05, "loss": 0.7378, "step": 1459 }, { "epoch": 0.9338770288638363, "grad_norm": 2.2956361770629883, "learning_rate": 3.4505236161572986e-05, "loss": 0.6983, "step": 1460 }, { "epoch": 0.9345166706644279, "grad_norm": 2.0403873920440674, "learning_rate": 3.4494550117546486e-05, "loss": 0.6757, "step": 1461 }, { "epoch": 0.9351563124650196, "grad_norm": 2.0827760696411133, "learning_rate": 3.4483864073519985e-05, "loss": 0.6727, "step": 1462 }, { "epoch": 0.9357959542656112, "grad_norm": 2.2579751014709473, "learning_rate": 3.4473178029493484e-05, "loss": 0.767, "step": 1463 }, { "epoch": 0.936435596066203, "grad_norm": 2.264143943786621, "learning_rate": 3.4462491985466984e-05, "loss": 0.6654, "step": 1464 }, { "epoch": 0.9370752378667946, "grad_norm": 2.1262547969818115, "learning_rate": 3.4451805941440476e-05, "loss": 0.6198, "step": 1465 }, { "epoch": 0.9377148796673863, "grad_norm": 2.262063503265381, "learning_rate": 3.444111989741398e-05, "loss": 0.7275, "step": 1466 }, { "epoch": 0.9383545214679779, "grad_norm": 2.2953622341156006, "learning_rate": 3.4430433853387475e-05, "loss": 0.7939, "step": 1467 }, { "epoch": 0.9389941632685695, "grad_norm": 1.8402847051620483, "learning_rate": 3.4419747809360974e-05, "loss": 0.6079, "step": 1468 }, { "epoch": 0.9396338050691613, "grad_norm": 2.457789659500122, "learning_rate": 3.440906176533448e-05, "loss": 0.756, "step": 1469 }, { "epoch": 0.9402734468697529, "grad_norm": 2.532585620880127, "learning_rate": 3.439837572130797e-05, "loss": 0.7221, "step": 1470 }, { "epoch": 0.9409130886703446, "grad_norm": 2.0720150470733643, "learning_rate": 3.438768967728147e-05, "loss": 0.6831, "step": 1471 }, { "epoch": 0.9415527304709362, "grad_norm": 2.1068005561828613, "learning_rate": 3.437700363325497e-05, "loss": 0.6341, "step": 1472 }, { "epoch": 0.942192372271528, "grad_norm": 2.184021234512329, "learning_rate": 3.436631758922847e-05, "loss": 0.7116, "step": 1473 }, { "epoch": 0.9428320140721196, "grad_norm": 2.212113380432129, "learning_rate": 3.4355631545201964e-05, "loss": 0.7128, "step": 1474 }, { "epoch": 0.9434716558727113, "grad_norm": 2.516669511795044, "learning_rate": 3.434494550117547e-05, "loss": 0.7688, "step": 1475 }, { "epoch": 0.9441112976733029, "grad_norm": 2.029060125350952, "learning_rate": 3.433425945714896e-05, "loss": 0.5678, "step": 1476 }, { "epoch": 0.9447509394738947, "grad_norm": 2.0237064361572266, "learning_rate": 3.432357341312246e-05, "loss": 0.6731, "step": 1477 }, { "epoch": 0.9453905812744863, "grad_norm": 2.291206121444702, "learning_rate": 3.431288736909596e-05, "loss": 0.6812, "step": 1478 }, { "epoch": 0.946030223075078, "grad_norm": 2.2760465145111084, "learning_rate": 3.430220132506946e-05, "loss": 0.739, "step": 1479 }, { "epoch": 0.9466698648756696, "grad_norm": 2.578695774078369, "learning_rate": 3.429151528104296e-05, "loss": 0.7474, "step": 1480 }, { "epoch": 0.9473095066762613, "grad_norm": 2.1519055366516113, "learning_rate": 3.428082923701646e-05, "loss": 0.6507, "step": 1481 }, { "epoch": 0.947949148476853, "grad_norm": 2.2226076126098633, "learning_rate": 3.427014319298996e-05, "loss": 0.7141, "step": 1482 }, { "epoch": 0.9485887902774446, "grad_norm": 2.4331486225128174, "learning_rate": 3.425945714896345e-05, "loss": 0.8209, "step": 1483 }, { "epoch": 0.9492284320780363, "grad_norm": 2.1664061546325684, "learning_rate": 3.424877110493696e-05, "loss": 0.7168, "step": 1484 }, { "epoch": 0.9498680738786279, "grad_norm": 1.9615627527236938, "learning_rate": 3.423808506091045e-05, "loss": 0.6672, "step": 1485 }, { "epoch": 0.9505077156792197, "grad_norm": 2.095708131790161, "learning_rate": 3.422739901688395e-05, "loss": 0.7392, "step": 1486 }, { "epoch": 0.9511473574798113, "grad_norm": 1.9985183477401733, "learning_rate": 3.421671297285745e-05, "loss": 0.6717, "step": 1487 }, { "epoch": 0.951786999280403, "grad_norm": 1.9108582735061646, "learning_rate": 3.420602692883095e-05, "loss": 0.585, "step": 1488 }, { "epoch": 0.9524266410809946, "grad_norm": 1.8438045978546143, "learning_rate": 3.419534088480445e-05, "loss": 0.6819, "step": 1489 }, { "epoch": 0.9530662828815863, "grad_norm": 2.203334331512451, "learning_rate": 3.418465484077795e-05, "loss": 0.7779, "step": 1490 }, { "epoch": 0.953705924682178, "grad_norm": 1.9355978965759277, "learning_rate": 3.4173968796751446e-05, "loss": 0.684, "step": 1491 }, { "epoch": 0.9543455664827697, "grad_norm": 1.9291232824325562, "learning_rate": 3.4163282752724945e-05, "loss": 0.6304, "step": 1492 }, { "epoch": 0.9549852082833613, "grad_norm": 2.56270170211792, "learning_rate": 3.4152596708698445e-05, "loss": 0.8354, "step": 1493 }, { "epoch": 0.955624850083953, "grad_norm": 2.3271262645721436, "learning_rate": 3.414191066467194e-05, "loss": 0.6864, "step": 1494 }, { "epoch": 0.9562644918845447, "grad_norm": 2.4378902912139893, "learning_rate": 3.4131224620645444e-05, "loss": 0.8168, "step": 1495 }, { "epoch": 0.9569041336851363, "grad_norm": 2.4102671146392822, "learning_rate": 3.4120538576618936e-05, "loss": 0.7631, "step": 1496 }, { "epoch": 0.957543775485728, "grad_norm": 2.0062508583068848, "learning_rate": 3.4109852532592436e-05, "loss": 0.6655, "step": 1497 }, { "epoch": 0.9581834172863196, "grad_norm": 2.330242156982422, "learning_rate": 3.4099166488565935e-05, "loss": 0.7531, "step": 1498 }, { "epoch": 0.9588230590869113, "grad_norm": 1.935307502746582, "learning_rate": 3.4088480444539434e-05, "loss": 0.6319, "step": 1499 }, { "epoch": 0.959462700887503, "grad_norm": 2.0610244274139404, "learning_rate": 3.407779440051293e-05, "loss": 0.6892, "step": 1500 }, { "epoch": 0.9601023426880947, "grad_norm": 1.7754333019256592, "learning_rate": 3.406710835648643e-05, "loss": 0.5632, "step": 1501 }, { "epoch": 0.9607419844886863, "grad_norm": 2.2314975261688232, "learning_rate": 3.405642231245993e-05, "loss": 0.7993, "step": 1502 }, { "epoch": 0.961381626289278, "grad_norm": 2.5227909088134766, "learning_rate": 3.4045736268433425e-05, "loss": 0.7917, "step": 1503 }, { "epoch": 0.9620212680898697, "grad_norm": 2.2489991188049316, "learning_rate": 3.403505022440693e-05, "loss": 0.7007, "step": 1504 }, { "epoch": 0.9626609098904614, "grad_norm": 2.4014620780944824, "learning_rate": 3.4024364180380424e-05, "loss": 0.7098, "step": 1505 }, { "epoch": 0.963300551691053, "grad_norm": 2.0850815773010254, "learning_rate": 3.401367813635392e-05, "loss": 0.6114, "step": 1506 }, { "epoch": 0.9639401934916447, "grad_norm": 2.3688106536865234, "learning_rate": 3.400299209232742e-05, "loss": 0.7705, "step": 1507 }, { "epoch": 0.9645798352922363, "grad_norm": 2.0088326930999756, "learning_rate": 3.399230604830092e-05, "loss": 0.6809, "step": 1508 }, { "epoch": 0.9652194770928281, "grad_norm": 2.115326404571533, "learning_rate": 3.3981620004274414e-05, "loss": 0.7547, "step": 1509 }, { "epoch": 0.9658591188934197, "grad_norm": 2.5346519947052, "learning_rate": 3.397093396024792e-05, "loss": 0.7843, "step": 1510 }, { "epoch": 0.9664987606940113, "grad_norm": 2.709911346435547, "learning_rate": 3.396024791622141e-05, "loss": 0.8325, "step": 1511 }, { "epoch": 0.967138402494603, "grad_norm": 2.412773609161377, "learning_rate": 3.394956187219491e-05, "loss": 0.7499, "step": 1512 }, { "epoch": 0.9677780442951947, "grad_norm": 2.4920361042022705, "learning_rate": 3.393887582816841e-05, "loss": 0.8206, "step": 1513 }, { "epoch": 0.9684176860957864, "grad_norm": 1.972916841506958, "learning_rate": 3.392818978414191e-05, "loss": 0.6819, "step": 1514 }, { "epoch": 0.969057327896378, "grad_norm": 2.2179787158966064, "learning_rate": 3.391750374011541e-05, "loss": 0.7832, "step": 1515 }, { "epoch": 0.9696969696969697, "grad_norm": 2.270247220993042, "learning_rate": 3.390681769608891e-05, "loss": 0.7791, "step": 1516 }, { "epoch": 0.9703366114975613, "grad_norm": 1.8921737670898438, "learning_rate": 3.389613165206241e-05, "loss": 0.65, "step": 1517 }, { "epoch": 0.9709762532981531, "grad_norm": 2.5758469104766846, "learning_rate": 3.388544560803591e-05, "loss": 0.9067, "step": 1518 }, { "epoch": 0.9716158950987447, "grad_norm": 2.161949634552002, "learning_rate": 3.387475956400941e-05, "loss": 0.7332, "step": 1519 }, { "epoch": 0.9722555368993364, "grad_norm": 2.2156999111175537, "learning_rate": 3.38640735199829e-05, "loss": 0.7205, "step": 1520 }, { "epoch": 0.972895178699928, "grad_norm": 1.9285770654678345, "learning_rate": 3.385338747595641e-05, "loss": 0.624, "step": 1521 }, { "epoch": 0.9735348205005198, "grad_norm": 2.0817832946777344, "learning_rate": 3.38427014319299e-05, "loss": 0.6611, "step": 1522 }, { "epoch": 0.9741744623011114, "grad_norm": 2.0828697681427, "learning_rate": 3.38320153879034e-05, "loss": 0.7319, "step": 1523 }, { "epoch": 0.974814104101703, "grad_norm": 2.047278881072998, "learning_rate": 3.38213293438769e-05, "loss": 0.6958, "step": 1524 }, { "epoch": 0.9754537459022947, "grad_norm": 2.0445549488067627, "learning_rate": 3.38106432998504e-05, "loss": 0.658, "step": 1525 }, { "epoch": 0.9760933877028863, "grad_norm": 2.2505154609680176, "learning_rate": 3.37999572558239e-05, "loss": 0.7333, "step": 1526 }, { "epoch": 0.9767330295034781, "grad_norm": 2.253756523132324, "learning_rate": 3.3789271211797396e-05, "loss": 0.6782, "step": 1527 }, { "epoch": 0.9773726713040697, "grad_norm": 2.053600788116455, "learning_rate": 3.3778585167770895e-05, "loss": 0.6976, "step": 1528 }, { "epoch": 0.9780123131046614, "grad_norm": 2.214647054672241, "learning_rate": 3.376789912374439e-05, "loss": 0.7142, "step": 1529 }, { "epoch": 0.978651954905253, "grad_norm": 2.3531408309936523, "learning_rate": 3.3757213079717894e-05, "loss": 0.7426, "step": 1530 }, { "epoch": 0.9792915967058448, "grad_norm": 2.190523147583008, "learning_rate": 3.374652703569139e-05, "loss": 0.7056, "step": 1531 }, { "epoch": 0.9799312385064364, "grad_norm": 2.0233254432678223, "learning_rate": 3.3735840991664886e-05, "loss": 0.6839, "step": 1532 }, { "epoch": 0.9805708803070281, "grad_norm": 2.0214545726776123, "learning_rate": 3.3725154947638385e-05, "loss": 0.6686, "step": 1533 }, { "epoch": 0.9812105221076197, "grad_norm": 2.2215795516967773, "learning_rate": 3.3714468903611885e-05, "loss": 0.71, "step": 1534 }, { "epoch": 0.9818501639082114, "grad_norm": 2.437448263168335, "learning_rate": 3.3703782859585384e-05, "loss": 0.7416, "step": 1535 }, { "epoch": 0.9824898057088031, "grad_norm": 2.5444507598876953, "learning_rate": 3.3693096815558884e-05, "loss": 0.8026, "step": 1536 }, { "epoch": 0.9831294475093948, "grad_norm": 2.484264612197876, "learning_rate": 3.368241077153238e-05, "loss": 0.6371, "step": 1537 }, { "epoch": 0.9837690893099864, "grad_norm": 2.301780939102173, "learning_rate": 3.3671724727505875e-05, "loss": 0.821, "step": 1538 }, { "epoch": 0.984408731110578, "grad_norm": 2.186701774597168, "learning_rate": 3.366103868347938e-05, "loss": 0.7156, "step": 1539 }, { "epoch": 0.9850483729111698, "grad_norm": 2.459995985031128, "learning_rate": 3.3650352639452874e-05, "loss": 0.8182, "step": 1540 }, { "epoch": 0.9856880147117614, "grad_norm": 1.895358920097351, "learning_rate": 3.3639666595426374e-05, "loss": 0.6198, "step": 1541 }, { "epoch": 0.9863276565123531, "grad_norm": 2.1757967472076416, "learning_rate": 3.362898055139987e-05, "loss": 0.6945, "step": 1542 }, { "epoch": 0.9869672983129447, "grad_norm": 2.508127212524414, "learning_rate": 3.361829450737337e-05, "loss": 0.8474, "step": 1543 }, { "epoch": 0.9876069401135364, "grad_norm": 1.9849086999893188, "learning_rate": 3.3607608463346865e-05, "loss": 0.6226, "step": 1544 }, { "epoch": 0.9882465819141281, "grad_norm": 2.3702750205993652, "learning_rate": 3.359692241932037e-05, "loss": 0.7921, "step": 1545 }, { "epoch": 0.9888862237147198, "grad_norm": 1.851857304573059, "learning_rate": 3.3586236375293864e-05, "loss": 0.6299, "step": 1546 }, { "epoch": 0.9895258655153114, "grad_norm": 2.113546133041382, "learning_rate": 3.357555033126737e-05, "loss": 0.691, "step": 1547 }, { "epoch": 0.9901655073159031, "grad_norm": 2.486071825027466, "learning_rate": 3.356486428724087e-05, "loss": 0.7461, "step": 1548 }, { "epoch": 0.9908051491164948, "grad_norm": 1.8651572465896606, "learning_rate": 3.355417824321436e-05, "loss": 0.5847, "step": 1549 }, { "epoch": 0.9914447909170865, "grad_norm": 2.235811710357666, "learning_rate": 3.354349219918787e-05, "loss": 0.7416, "step": 1550 }, { "epoch": 0.9920844327176781, "grad_norm": 2.370832681655884, "learning_rate": 3.353280615516136e-05, "loss": 0.7106, "step": 1551 }, { "epoch": 0.9927240745182697, "grad_norm": 1.9883408546447754, "learning_rate": 3.352212011113486e-05, "loss": 0.6786, "step": 1552 }, { "epoch": 0.9933637163188614, "grad_norm": 2.5140347480773926, "learning_rate": 3.351143406710836e-05, "loss": 0.7636, "step": 1553 }, { "epoch": 0.9940033581194531, "grad_norm": 1.814552664756775, "learning_rate": 3.350074802308186e-05, "loss": 0.5652, "step": 1554 }, { "epoch": 0.9946429999200448, "grad_norm": 2.2113420963287354, "learning_rate": 3.349006197905535e-05, "loss": 0.7076, "step": 1555 }, { "epoch": 0.9952826417206364, "grad_norm": 2.382270574569702, "learning_rate": 3.347937593502886e-05, "loss": 0.7714, "step": 1556 }, { "epoch": 0.9959222835212281, "grad_norm": 2.217782497406006, "learning_rate": 3.346868989100235e-05, "loss": 0.6295, "step": 1557 }, { "epoch": 0.9965619253218198, "grad_norm": 2.3199214935302734, "learning_rate": 3.345800384697585e-05, "loss": 0.6673, "step": 1558 }, { "epoch": 0.9972015671224115, "grad_norm": 2.612952470779419, "learning_rate": 3.344731780294935e-05, "loss": 0.8183, "step": 1559 }, { "epoch": 0.9978412089230031, "grad_norm": 2.0006492137908936, "learning_rate": 3.343663175892285e-05, "loss": 0.6892, "step": 1560 }, { "epoch": 0.9984808507235948, "grad_norm": 2.211374282836914, "learning_rate": 3.342594571489635e-05, "loss": 0.7048, "step": 1561 }, { "epoch": 0.9991204925241864, "grad_norm": 2.4126431941986084, "learning_rate": 3.3415259670869847e-05, "loss": 0.8143, "step": 1562 }, { "epoch": 0.9997601343247782, "grad_norm": 2.181459665298462, "learning_rate": 3.3404573626843346e-05, "loss": 0.71, "step": 1563 }, { "epoch": 1.0, "grad_norm": 3.5695137977600098, "learning_rate": 3.339388758281684e-05, "loss": 0.6863, "step": 1564 }, { "epoch": 1.0006396418005916, "grad_norm": 1.6426266431808472, "learning_rate": 3.3383201538790345e-05, "loss": 0.5212, "step": 1565 }, { "epoch": 1.0012792836011832, "grad_norm": 1.604065179824829, "learning_rate": 3.337251549476384e-05, "loss": 0.4942, "step": 1566 }, { "epoch": 1.001918925401775, "grad_norm": 1.596436619758606, "learning_rate": 3.336182945073734e-05, "loss": 0.4653, "step": 1567 }, { "epoch": 1.0025585672023667, "grad_norm": 2.0100901126861572, "learning_rate": 3.3351143406710836e-05, "loss": 0.4729, "step": 1568 }, { "epoch": 1.0031982090029583, "grad_norm": 1.6763489246368408, "learning_rate": 3.3340457362684335e-05, "loss": 0.5096, "step": 1569 }, { "epoch": 1.00383785080355, "grad_norm": 1.9359748363494873, "learning_rate": 3.3329771318657835e-05, "loss": 0.6162, "step": 1570 }, { "epoch": 1.0044774926041418, "grad_norm": 2.0272462368011475, "learning_rate": 3.3319085274631334e-05, "loss": 0.5823, "step": 1571 }, { "epoch": 1.0051171344047334, "grad_norm": 1.9165846109390259, "learning_rate": 3.3308399230604833e-05, "loss": 0.4592, "step": 1572 }, { "epoch": 1.005756776205325, "grad_norm": 1.9332995414733887, "learning_rate": 3.3297713186578326e-05, "loss": 0.5524, "step": 1573 }, { "epoch": 1.0063964180059166, "grad_norm": 1.8141871690750122, "learning_rate": 3.328702714255183e-05, "loss": 0.4715, "step": 1574 }, { "epoch": 1.0070360598065085, "grad_norm": 2.228400230407715, "learning_rate": 3.3276341098525325e-05, "loss": 0.6197, "step": 1575 }, { "epoch": 1.0076757016071, "grad_norm": 2.3265390396118164, "learning_rate": 3.326565505449883e-05, "loss": 0.5837, "step": 1576 }, { "epoch": 1.0083153434076917, "grad_norm": 2.107447624206543, "learning_rate": 3.3254969010472323e-05, "loss": 0.547, "step": 1577 }, { "epoch": 1.0089549852082833, "grad_norm": 2.1493191719055176, "learning_rate": 3.324428296644582e-05, "loss": 0.5573, "step": 1578 }, { "epoch": 1.009594627008875, "grad_norm": 2.201444149017334, "learning_rate": 3.323359692241932e-05, "loss": 0.5181, "step": 1579 }, { "epoch": 1.0102342688094668, "grad_norm": 2.342329263687134, "learning_rate": 3.322291087839282e-05, "loss": 0.5142, "step": 1580 }, { "epoch": 1.0108739106100584, "grad_norm": 2.622166156768799, "learning_rate": 3.321222483436632e-05, "loss": 0.5671, "step": 1581 }, { "epoch": 1.01151355241065, "grad_norm": 2.068490982055664, "learning_rate": 3.320153879033982e-05, "loss": 0.458, "step": 1582 }, { "epoch": 1.0121531942112416, "grad_norm": 2.3126823902130127, "learning_rate": 3.319085274631332e-05, "loss": 0.4838, "step": 1583 }, { "epoch": 1.0127928360118335, "grad_norm": 2.4509313106536865, "learning_rate": 3.318016670228681e-05, "loss": 0.5925, "step": 1584 }, { "epoch": 1.013432477812425, "grad_norm": 2.2765822410583496, "learning_rate": 3.316948065826032e-05, "loss": 0.454, "step": 1585 }, { "epoch": 1.0140721196130167, "grad_norm": 2.35550856590271, "learning_rate": 3.315879461423381e-05, "loss": 0.5222, "step": 1586 }, { "epoch": 1.0147117614136083, "grad_norm": 2.231818914413452, "learning_rate": 3.314810857020731e-05, "loss": 0.5094, "step": 1587 }, { "epoch": 1.0153514032142001, "grad_norm": 2.6193008422851562, "learning_rate": 3.313742252618081e-05, "loss": 0.635, "step": 1588 }, { "epoch": 1.0159910450147918, "grad_norm": 2.495405435562134, "learning_rate": 3.312673648215431e-05, "loss": 0.5587, "step": 1589 }, { "epoch": 1.0166306868153834, "grad_norm": 2.183990001678467, "learning_rate": 3.31160504381278e-05, "loss": 0.5388, "step": 1590 }, { "epoch": 1.017270328615975, "grad_norm": 2.247999668121338, "learning_rate": 3.310536439410131e-05, "loss": 0.5116, "step": 1591 }, { "epoch": 1.0179099704165666, "grad_norm": 2.329559087753296, "learning_rate": 3.30946783500748e-05, "loss": 0.5222, "step": 1592 }, { "epoch": 1.0185496122171585, "grad_norm": 2.255418062210083, "learning_rate": 3.30839923060483e-05, "loss": 0.5116, "step": 1593 }, { "epoch": 1.01918925401775, "grad_norm": 2.4894025325775146, "learning_rate": 3.3073306262021806e-05, "loss": 0.5985, "step": 1594 }, { "epoch": 1.0198288958183417, "grad_norm": 2.6374289989471436, "learning_rate": 3.30626202179953e-05, "loss": 0.5363, "step": 1595 }, { "epoch": 1.0204685376189333, "grad_norm": 2.0918147563934326, "learning_rate": 3.30519341739688e-05, "loss": 0.4625, "step": 1596 }, { "epoch": 1.0211081794195251, "grad_norm": 2.248098373413086, "learning_rate": 3.30412481299423e-05, "loss": 0.4838, "step": 1597 }, { "epoch": 1.0217478212201168, "grad_norm": 1.9481654167175293, "learning_rate": 3.3030562085915797e-05, "loss": 0.4333, "step": 1598 }, { "epoch": 1.0223874630207084, "grad_norm": 2.1654884815216064, "learning_rate": 3.301987604188929e-05, "loss": 0.481, "step": 1599 }, { "epoch": 1.0230271048213, "grad_norm": 2.157902717590332, "learning_rate": 3.3009189997862795e-05, "loss": 0.4918, "step": 1600 }, { "epoch": 1.0236667466218918, "grad_norm": 1.9855064153671265, "learning_rate": 3.299850395383629e-05, "loss": 0.4431, "step": 1601 }, { "epoch": 1.0243063884224834, "grad_norm": 2.373035430908203, "learning_rate": 3.298781790980979e-05, "loss": 0.4841, "step": 1602 }, { "epoch": 1.024946030223075, "grad_norm": 2.2268319129943848, "learning_rate": 3.2977131865783287e-05, "loss": 0.4685, "step": 1603 }, { "epoch": 1.0255856720236667, "grad_norm": 2.439455986022949, "learning_rate": 3.2966445821756786e-05, "loss": 0.5072, "step": 1604 }, { "epoch": 1.0262253138242585, "grad_norm": 2.6799020767211914, "learning_rate": 3.2955759777730285e-05, "loss": 0.5656, "step": 1605 }, { "epoch": 1.0268649556248501, "grad_norm": 2.32594895362854, "learning_rate": 3.2945073733703785e-05, "loss": 0.4995, "step": 1606 }, { "epoch": 1.0275045974254418, "grad_norm": 2.4114809036254883, "learning_rate": 3.2934387689677284e-05, "loss": 0.5164, "step": 1607 }, { "epoch": 1.0281442392260334, "grad_norm": 2.1412720680236816, "learning_rate": 3.292370164565078e-05, "loss": 0.4681, "step": 1608 }, { "epoch": 1.028783881026625, "grad_norm": 2.4099087715148926, "learning_rate": 3.291301560162428e-05, "loss": 0.5592, "step": 1609 }, { "epoch": 1.0294235228272168, "grad_norm": 2.376927614212036, "learning_rate": 3.2902329557597775e-05, "loss": 0.4882, "step": 1610 }, { "epoch": 1.0300631646278084, "grad_norm": 2.545624256134033, "learning_rate": 3.289164351357128e-05, "loss": 0.5526, "step": 1611 }, { "epoch": 1.0307028064284, "grad_norm": 2.2848265171051025, "learning_rate": 3.2880957469544774e-05, "loss": 0.5354, "step": 1612 }, { "epoch": 1.0313424482289917, "grad_norm": 2.2950668334960938, "learning_rate": 3.2870271425518273e-05, "loss": 0.498, "step": 1613 }, { "epoch": 1.0319820900295835, "grad_norm": 2.34885835647583, "learning_rate": 3.285958538149177e-05, "loss": 0.4906, "step": 1614 }, { "epoch": 1.0326217318301751, "grad_norm": 2.462394952774048, "learning_rate": 3.284889933746527e-05, "loss": 0.5359, "step": 1615 }, { "epoch": 1.0332613736307668, "grad_norm": 2.243147373199463, "learning_rate": 3.283821329343877e-05, "loss": 0.4938, "step": 1616 }, { "epoch": 1.0339010154313584, "grad_norm": 2.5488319396972656, "learning_rate": 3.282752724941227e-05, "loss": 0.569, "step": 1617 }, { "epoch": 1.0345406572319502, "grad_norm": 2.2287886142730713, "learning_rate": 3.281684120538577e-05, "loss": 0.5268, "step": 1618 }, { "epoch": 1.0351802990325418, "grad_norm": 2.110866069793701, "learning_rate": 3.280615516135926e-05, "loss": 0.484, "step": 1619 }, { "epoch": 1.0358199408331334, "grad_norm": 2.268686532974243, "learning_rate": 3.279546911733277e-05, "loss": 0.5439, "step": 1620 }, { "epoch": 1.036459582633725, "grad_norm": 2.119105100631714, "learning_rate": 3.278478307330626e-05, "loss": 0.4944, "step": 1621 }, { "epoch": 1.0370992244343167, "grad_norm": 1.9542510509490967, "learning_rate": 3.277409702927976e-05, "loss": 0.441, "step": 1622 }, { "epoch": 1.0377388662349085, "grad_norm": 2.3195297718048096, "learning_rate": 3.276341098525326e-05, "loss": 0.5325, "step": 1623 }, { "epoch": 1.0383785080355001, "grad_norm": 2.036125421524048, "learning_rate": 3.275272494122676e-05, "loss": 0.4529, "step": 1624 }, { "epoch": 1.0390181498360918, "grad_norm": 2.167020559310913, "learning_rate": 3.274203889720026e-05, "loss": 0.4869, "step": 1625 }, { "epoch": 1.0396577916366834, "grad_norm": 2.308004140853882, "learning_rate": 3.273135285317376e-05, "loss": 0.5272, "step": 1626 }, { "epoch": 1.0402974334372752, "grad_norm": 2.354403257369995, "learning_rate": 3.272066680914726e-05, "loss": 0.5588, "step": 1627 }, { "epoch": 1.0409370752378668, "grad_norm": 2.3287439346313477, "learning_rate": 3.270998076512075e-05, "loss": 0.4983, "step": 1628 }, { "epoch": 1.0415767170384584, "grad_norm": 2.4980506896972656, "learning_rate": 3.2699294721094256e-05, "loss": 0.6183, "step": 1629 }, { "epoch": 1.04221635883905, "grad_norm": 2.5118374824523926, "learning_rate": 3.268860867706775e-05, "loss": 0.6046, "step": 1630 }, { "epoch": 1.042856000639642, "grad_norm": 2.1099486351013184, "learning_rate": 3.2677922633041255e-05, "loss": 0.4761, "step": 1631 }, { "epoch": 1.0434956424402335, "grad_norm": 2.3047168254852295, "learning_rate": 3.266723658901475e-05, "loss": 0.5008, "step": 1632 }, { "epoch": 1.0441352842408251, "grad_norm": 2.1408493518829346, "learning_rate": 3.265655054498825e-05, "loss": 0.4468, "step": 1633 }, { "epoch": 1.0447749260414168, "grad_norm": 2.2916908264160156, "learning_rate": 3.2645864500961746e-05, "loss": 0.4752, "step": 1634 }, { "epoch": 1.0454145678420084, "grad_norm": 2.1892850399017334, "learning_rate": 3.2635178456935246e-05, "loss": 0.4713, "step": 1635 }, { "epoch": 1.0460542096426002, "grad_norm": 2.178524971008301, "learning_rate": 3.262449241290874e-05, "loss": 0.467, "step": 1636 }, { "epoch": 1.0466938514431918, "grad_norm": 2.6131863594055176, "learning_rate": 3.2613806368882245e-05, "loss": 0.5901, "step": 1637 }, { "epoch": 1.0473334932437834, "grad_norm": 2.690558910369873, "learning_rate": 3.260312032485574e-05, "loss": 0.5401, "step": 1638 }, { "epoch": 1.047973135044375, "grad_norm": 2.3080806732177734, "learning_rate": 3.2592434280829236e-05, "loss": 0.468, "step": 1639 }, { "epoch": 1.048612776844967, "grad_norm": 2.7645251750946045, "learning_rate": 3.258174823680274e-05, "loss": 0.5848, "step": 1640 }, { "epoch": 1.0492524186455585, "grad_norm": 2.3509116172790527, "learning_rate": 3.2571062192776235e-05, "loss": 0.4677, "step": 1641 }, { "epoch": 1.0498920604461501, "grad_norm": 2.726024627685547, "learning_rate": 3.2560376148749735e-05, "loss": 0.5132, "step": 1642 }, { "epoch": 1.0505317022467417, "grad_norm": 2.6302695274353027, "learning_rate": 3.2549690104723234e-05, "loss": 0.5078, "step": 1643 }, { "epoch": 1.0511713440473336, "grad_norm": 2.5397214889526367, "learning_rate": 3.253900406069673e-05, "loss": 0.5132, "step": 1644 }, { "epoch": 1.0518109858479252, "grad_norm": 2.930471658706665, "learning_rate": 3.2528318016670226e-05, "loss": 0.6909, "step": 1645 }, { "epoch": 1.0524506276485168, "grad_norm": 2.448770046234131, "learning_rate": 3.251763197264373e-05, "loss": 0.5303, "step": 1646 }, { "epoch": 1.0530902694491084, "grad_norm": 2.4772374629974365, "learning_rate": 3.2506945928617225e-05, "loss": 0.5678, "step": 1647 }, { "epoch": 1.0537299112497003, "grad_norm": 2.4332692623138428, "learning_rate": 3.2496259884590724e-05, "loss": 0.5135, "step": 1648 }, { "epoch": 1.054369553050292, "grad_norm": 2.41996431350708, "learning_rate": 3.248557384056422e-05, "loss": 0.5068, "step": 1649 }, { "epoch": 1.0550091948508835, "grad_norm": 2.6703288555145264, "learning_rate": 3.247488779653772e-05, "loss": 0.6021, "step": 1650 }, { "epoch": 1.0556488366514751, "grad_norm": 2.1734867095947266, "learning_rate": 3.246420175251122e-05, "loss": 0.4897, "step": 1651 }, { "epoch": 1.0562884784520667, "grad_norm": 2.1070706844329834, "learning_rate": 3.245351570848472e-05, "loss": 0.4673, "step": 1652 }, { "epoch": 1.0569281202526586, "grad_norm": 2.2720072269439697, "learning_rate": 3.244282966445822e-05, "loss": 0.5331, "step": 1653 }, { "epoch": 1.0575677620532502, "grad_norm": 2.6807985305786133, "learning_rate": 3.243214362043171e-05, "loss": 0.563, "step": 1654 }, { "epoch": 1.0582074038538418, "grad_norm": 2.374823808670044, "learning_rate": 3.242145757640522e-05, "loss": 0.5634, "step": 1655 }, { "epoch": 1.0588470456544334, "grad_norm": 2.0399231910705566, "learning_rate": 3.241077153237871e-05, "loss": 0.4685, "step": 1656 }, { "epoch": 1.0594866874550253, "grad_norm": 2.1718246936798096, "learning_rate": 3.240008548835221e-05, "loss": 0.4879, "step": 1657 }, { "epoch": 1.060126329255617, "grad_norm": 2.1819610595703125, "learning_rate": 3.238939944432571e-05, "loss": 0.5479, "step": 1658 }, { "epoch": 1.0607659710562085, "grad_norm": 2.3052191734313965, "learning_rate": 3.237871340029921e-05, "loss": 0.5069, "step": 1659 }, { "epoch": 1.0614056128568001, "grad_norm": 2.1954407691955566, "learning_rate": 3.236802735627271e-05, "loss": 0.504, "step": 1660 }, { "epoch": 1.062045254657392, "grad_norm": 2.302370309829712, "learning_rate": 3.235734131224621e-05, "loss": 0.5981, "step": 1661 }, { "epoch": 1.0626848964579836, "grad_norm": 2.2455694675445557, "learning_rate": 3.234665526821971e-05, "loss": 0.5061, "step": 1662 }, { "epoch": 1.0633245382585752, "grad_norm": 2.276129722595215, "learning_rate": 3.233596922419321e-05, "loss": 0.5088, "step": 1663 }, { "epoch": 1.0639641800591668, "grad_norm": 2.2016842365264893, "learning_rate": 3.232528318016671e-05, "loss": 0.4994, "step": 1664 }, { "epoch": 1.0646038218597584, "grad_norm": 2.456360340118408, "learning_rate": 3.23145971361402e-05, "loss": 0.5224, "step": 1665 }, { "epoch": 1.0652434636603503, "grad_norm": 2.2001917362213135, "learning_rate": 3.2303911092113706e-05, "loss": 0.4921, "step": 1666 }, { "epoch": 1.065883105460942, "grad_norm": 2.542221784591675, "learning_rate": 3.22932250480872e-05, "loss": 0.5592, "step": 1667 }, { "epoch": 1.0665227472615335, "grad_norm": 2.315314769744873, "learning_rate": 3.22825390040607e-05, "loss": 0.4884, "step": 1668 }, { "epoch": 1.0671623890621251, "grad_norm": 2.0502121448516846, "learning_rate": 3.22718529600342e-05, "loss": 0.4319, "step": 1669 }, { "epoch": 1.067802030862717, "grad_norm": 2.166858434677124, "learning_rate": 3.2261166916007696e-05, "loss": 0.4877, "step": 1670 }, { "epoch": 1.0684416726633086, "grad_norm": 2.3658769130706787, "learning_rate": 3.2250480871981196e-05, "loss": 0.5817, "step": 1671 }, { "epoch": 1.0690813144639002, "grad_norm": 2.1855645179748535, "learning_rate": 3.2239794827954695e-05, "loss": 0.5, "step": 1672 }, { "epoch": 1.0697209562644918, "grad_norm": 2.242687463760376, "learning_rate": 3.2229108783928194e-05, "loss": 0.5415, "step": 1673 }, { "epoch": 1.0703605980650837, "grad_norm": 2.314005136489868, "learning_rate": 3.221842273990169e-05, "loss": 0.5546, "step": 1674 }, { "epoch": 1.0710002398656753, "grad_norm": 2.3146510124206543, "learning_rate": 3.220773669587519e-05, "loss": 0.5637, "step": 1675 }, { "epoch": 1.071639881666267, "grad_norm": 2.439074993133545, "learning_rate": 3.2197050651848686e-05, "loss": 0.5315, "step": 1676 }, { "epoch": 1.0722795234668585, "grad_norm": 2.0321543216705322, "learning_rate": 3.2186364607822185e-05, "loss": 0.5095, "step": 1677 }, { "epoch": 1.0729191652674501, "grad_norm": 2.128948450088501, "learning_rate": 3.2175678563795684e-05, "loss": 0.4817, "step": 1678 }, { "epoch": 1.073558807068042, "grad_norm": 1.978027105331421, "learning_rate": 3.2164992519769184e-05, "loss": 0.4654, "step": 1679 }, { "epoch": 1.0741984488686336, "grad_norm": 2.456768751144409, "learning_rate": 3.2154306475742676e-05, "loss": 0.5976, "step": 1680 }, { "epoch": 1.0748380906692252, "grad_norm": 2.5293171405792236, "learning_rate": 3.214362043171618e-05, "loss": 0.6063, "step": 1681 }, { "epoch": 1.0754777324698168, "grad_norm": 2.1288278102874756, "learning_rate": 3.2132934387689675e-05, "loss": 0.4797, "step": 1682 }, { "epoch": 1.0761173742704087, "grad_norm": 2.437877655029297, "learning_rate": 3.2122248343663175e-05, "loss": 0.5627, "step": 1683 }, { "epoch": 1.0767570160710003, "grad_norm": 2.3062119483947754, "learning_rate": 3.2111562299636674e-05, "loss": 0.5625, "step": 1684 }, { "epoch": 1.077396657871592, "grad_norm": 2.208761215209961, "learning_rate": 3.210087625561017e-05, "loss": 0.5284, "step": 1685 }, { "epoch": 1.0780362996721835, "grad_norm": 2.0689878463745117, "learning_rate": 3.209019021158367e-05, "loss": 0.4581, "step": 1686 }, { "epoch": 1.0786759414727753, "grad_norm": 2.234243631362915, "learning_rate": 3.207950416755717e-05, "loss": 0.5071, "step": 1687 }, { "epoch": 1.079315583273367, "grad_norm": 2.042379379272461, "learning_rate": 3.206881812353067e-05, "loss": 0.4514, "step": 1688 }, { "epoch": 1.0799552250739586, "grad_norm": 2.1682631969451904, "learning_rate": 3.205813207950417e-05, "loss": 0.4962, "step": 1689 }, { "epoch": 1.0805948668745502, "grad_norm": 2.0820109844207764, "learning_rate": 3.204744603547767e-05, "loss": 0.4754, "step": 1690 }, { "epoch": 1.0812345086751418, "grad_norm": 2.0925025939941406, "learning_rate": 3.203675999145116e-05, "loss": 0.4463, "step": 1691 }, { "epoch": 1.0818741504757337, "grad_norm": 2.506754159927368, "learning_rate": 3.202607394742467e-05, "loss": 0.5349, "step": 1692 }, { "epoch": 1.0825137922763253, "grad_norm": 2.241452693939209, "learning_rate": 3.201538790339816e-05, "loss": 0.506, "step": 1693 }, { "epoch": 1.0831534340769169, "grad_norm": 2.0173118114471436, "learning_rate": 3.200470185937166e-05, "loss": 0.4268, "step": 1694 }, { "epoch": 1.0837930758775085, "grad_norm": 2.372399091720581, "learning_rate": 3.199401581534516e-05, "loss": 0.5435, "step": 1695 }, { "epoch": 1.0844327176781003, "grad_norm": 2.4139435291290283, "learning_rate": 3.198332977131866e-05, "loss": 0.487, "step": 1696 }, { "epoch": 1.085072359478692, "grad_norm": 2.4056973457336426, "learning_rate": 3.197264372729216e-05, "loss": 0.5084, "step": 1697 }, { "epoch": 1.0857120012792836, "grad_norm": 2.368945598602295, "learning_rate": 3.196195768326566e-05, "loss": 0.5362, "step": 1698 }, { "epoch": 1.0863516430798752, "grad_norm": 2.039180040359497, "learning_rate": 3.195127163923916e-05, "loss": 0.4644, "step": 1699 }, { "epoch": 1.086991284880467, "grad_norm": 2.312699556350708, "learning_rate": 3.194058559521265e-05, "loss": 0.529, "step": 1700 }, { "epoch": 1.0876309266810587, "grad_norm": 2.5925090312957764, "learning_rate": 3.1929899551186156e-05, "loss": 0.5571, "step": 1701 }, { "epoch": 1.0882705684816503, "grad_norm": 2.3800933361053467, "learning_rate": 3.191921350715965e-05, "loss": 0.4864, "step": 1702 }, { "epoch": 1.0889102102822419, "grad_norm": 2.4689550399780273, "learning_rate": 3.190852746313315e-05, "loss": 0.5101, "step": 1703 }, { "epoch": 1.0895498520828335, "grad_norm": 2.5429491996765137, "learning_rate": 3.189784141910665e-05, "loss": 0.5454, "step": 1704 }, { "epoch": 1.0901894938834253, "grad_norm": 2.4416191577911377, "learning_rate": 3.188715537508015e-05, "loss": 0.5248, "step": 1705 }, { "epoch": 1.090829135684017, "grad_norm": 2.0285744667053223, "learning_rate": 3.1876469331053646e-05, "loss": 0.4487, "step": 1706 }, { "epoch": 1.0914687774846086, "grad_norm": 2.597395658493042, "learning_rate": 3.1865783287027146e-05, "loss": 0.5802, "step": 1707 }, { "epoch": 1.0921084192852002, "grad_norm": 2.3871214389801025, "learning_rate": 3.1855097243000645e-05, "loss": 0.5307, "step": 1708 }, { "epoch": 1.092748061085792, "grad_norm": 2.5163402557373047, "learning_rate": 3.184441119897414e-05, "loss": 0.5412, "step": 1709 }, { "epoch": 1.0933877028863837, "grad_norm": 2.5021064281463623, "learning_rate": 3.1833725154947644e-05, "loss": 0.5411, "step": 1710 }, { "epoch": 1.0940273446869753, "grad_norm": 2.2159810066223145, "learning_rate": 3.1823039110921136e-05, "loss": 0.4951, "step": 1711 }, { "epoch": 1.0946669864875669, "grad_norm": 2.221435546875, "learning_rate": 3.1812353066894636e-05, "loss": 0.5281, "step": 1712 }, { "epoch": 1.0953066282881587, "grad_norm": 2.063404083251953, "learning_rate": 3.1801667022868135e-05, "loss": 0.4629, "step": 1713 }, { "epoch": 1.0959462700887503, "grad_norm": 2.227576971054077, "learning_rate": 3.1790980978841634e-05, "loss": 0.5423, "step": 1714 }, { "epoch": 1.096585911889342, "grad_norm": 2.4510653018951416, "learning_rate": 3.178029493481513e-05, "loss": 0.5714, "step": 1715 }, { "epoch": 1.0972255536899336, "grad_norm": 2.192448616027832, "learning_rate": 3.176960889078863e-05, "loss": 0.5217, "step": 1716 }, { "epoch": 1.0978651954905252, "grad_norm": 2.5083277225494385, "learning_rate": 3.175892284676213e-05, "loss": 0.471, "step": 1717 }, { "epoch": 1.098504837291117, "grad_norm": 2.673832893371582, "learning_rate": 3.174823680273563e-05, "loss": 0.5701, "step": 1718 }, { "epoch": 1.0991444790917086, "grad_norm": 2.177384614944458, "learning_rate": 3.173755075870913e-05, "loss": 0.4577, "step": 1719 }, { "epoch": 1.0997841208923003, "grad_norm": 1.9219969511032104, "learning_rate": 3.1726864714682624e-05, "loss": 0.4965, "step": 1720 }, { "epoch": 1.1004237626928919, "grad_norm": 2.3052754402160645, "learning_rate": 3.171617867065613e-05, "loss": 0.5333, "step": 1721 }, { "epoch": 1.1010634044934837, "grad_norm": 2.6739320755004883, "learning_rate": 3.170549262662962e-05, "loss": 0.6156, "step": 1722 }, { "epoch": 1.1017030462940753, "grad_norm": 2.549940824508667, "learning_rate": 3.169480658260312e-05, "loss": 0.5416, "step": 1723 }, { "epoch": 1.102342688094667, "grad_norm": 2.229623794555664, "learning_rate": 3.168412053857662e-05, "loss": 0.5133, "step": 1724 }, { "epoch": 1.1029823298952586, "grad_norm": 2.307368755340576, "learning_rate": 3.167343449455012e-05, "loss": 0.5406, "step": 1725 }, { "epoch": 1.1036219716958504, "grad_norm": 2.2113728523254395, "learning_rate": 3.166274845052361e-05, "loss": 0.4913, "step": 1726 }, { "epoch": 1.104261613496442, "grad_norm": 2.130842685699463, "learning_rate": 3.165206240649712e-05, "loss": 0.4465, "step": 1727 }, { "epoch": 1.1049012552970336, "grad_norm": 2.5895724296569824, "learning_rate": 3.164137636247061e-05, "loss": 0.5207, "step": 1728 }, { "epoch": 1.1055408970976253, "grad_norm": 2.168288469314575, "learning_rate": 3.163069031844411e-05, "loss": 0.4188, "step": 1729 }, { "epoch": 1.1061805388982169, "grad_norm": 2.2262396812438965, "learning_rate": 3.162000427441761e-05, "loss": 0.4625, "step": 1730 }, { "epoch": 1.1068201806988087, "grad_norm": 1.9149888753890991, "learning_rate": 3.160931823039111e-05, "loss": 0.4358, "step": 1731 }, { "epoch": 1.1074598224994003, "grad_norm": 2.387164354324341, "learning_rate": 3.159863218636461e-05, "loss": 0.5349, "step": 1732 }, { "epoch": 1.108099464299992, "grad_norm": 2.6190738677978516, "learning_rate": 3.158794614233811e-05, "loss": 0.6151, "step": 1733 }, { "epoch": 1.1087391061005836, "grad_norm": 2.2280044555664062, "learning_rate": 3.157726009831161e-05, "loss": 0.4655, "step": 1734 }, { "epoch": 1.1093787479011754, "grad_norm": 2.3109242916107178, "learning_rate": 3.15665740542851e-05, "loss": 0.4759, "step": 1735 }, { "epoch": 1.110018389701767, "grad_norm": 2.2519354820251465, "learning_rate": 3.155588801025861e-05, "loss": 0.4684, "step": 1736 }, { "epoch": 1.1106580315023586, "grad_norm": 2.682269811630249, "learning_rate": 3.15452019662321e-05, "loss": 0.5475, "step": 1737 }, { "epoch": 1.1112976733029503, "grad_norm": 2.540397882461548, "learning_rate": 3.15345159222056e-05, "loss": 0.5639, "step": 1738 }, { "epoch": 1.111937315103542, "grad_norm": 2.049651861190796, "learning_rate": 3.15238298781791e-05, "loss": 0.4704, "step": 1739 }, { "epoch": 1.1125769569041337, "grad_norm": 2.3338117599487305, "learning_rate": 3.15131438341526e-05, "loss": 0.5141, "step": 1740 }, { "epoch": 1.1132165987047253, "grad_norm": 2.401749849319458, "learning_rate": 3.15024577901261e-05, "loss": 0.4323, "step": 1741 }, { "epoch": 1.113856240505317, "grad_norm": 2.462519645690918, "learning_rate": 3.1491771746099596e-05, "loss": 0.5605, "step": 1742 }, { "epoch": 1.1144958823059088, "grad_norm": 2.33021879196167, "learning_rate": 3.1481085702073096e-05, "loss": 0.4488, "step": 1743 }, { "epoch": 1.1151355241065004, "grad_norm": 2.8066039085388184, "learning_rate": 3.1470399658046595e-05, "loss": 0.6131, "step": 1744 }, { "epoch": 1.115775165907092, "grad_norm": 2.5402162075042725, "learning_rate": 3.1459713614020094e-05, "loss": 0.5407, "step": 1745 }, { "epoch": 1.1164148077076836, "grad_norm": 1.9940400123596191, "learning_rate": 3.144902756999359e-05, "loss": 0.4291, "step": 1746 }, { "epoch": 1.1170544495082755, "grad_norm": 2.5242414474487305, "learning_rate": 3.143834152596709e-05, "loss": 0.4987, "step": 1747 }, { "epoch": 1.117694091308867, "grad_norm": 2.269988775253296, "learning_rate": 3.1427655481940586e-05, "loss": 0.5295, "step": 1748 }, { "epoch": 1.1183337331094587, "grad_norm": 1.8427963256835938, "learning_rate": 3.1416969437914085e-05, "loss": 0.4444, "step": 1749 }, { "epoch": 1.1189733749100503, "grad_norm": 2.09195613861084, "learning_rate": 3.1406283393887584e-05, "loss": 0.4826, "step": 1750 }, { "epoch": 1.119613016710642, "grad_norm": 2.6894187927246094, "learning_rate": 3.1395597349861084e-05, "loss": 0.6025, "step": 1751 }, { "epoch": 1.1202526585112338, "grad_norm": 2.4898767471313477, "learning_rate": 3.138491130583458e-05, "loss": 0.563, "step": 1752 }, { "epoch": 1.1208923003118254, "grad_norm": 2.3334531784057617, "learning_rate": 3.137422526180808e-05, "loss": 0.5537, "step": 1753 }, { "epoch": 1.121531942112417, "grad_norm": 2.3252806663513184, "learning_rate": 3.136353921778158e-05, "loss": 0.4919, "step": 1754 }, { "epoch": 1.1221715839130086, "grad_norm": 2.38567852973938, "learning_rate": 3.1352853173755074e-05, "loss": 0.5485, "step": 1755 }, { "epoch": 1.1228112257136005, "grad_norm": 2.1960718631744385, "learning_rate": 3.134216712972858e-05, "loss": 0.512, "step": 1756 }, { "epoch": 1.123450867514192, "grad_norm": 2.3051846027374268, "learning_rate": 3.133148108570207e-05, "loss": 0.5179, "step": 1757 }, { "epoch": 1.1240905093147837, "grad_norm": 2.105882406234741, "learning_rate": 3.132079504167557e-05, "loss": 0.4633, "step": 1758 }, { "epoch": 1.1247301511153753, "grad_norm": 2.0388476848602295, "learning_rate": 3.131010899764907e-05, "loss": 0.4703, "step": 1759 }, { "epoch": 1.1253697929159672, "grad_norm": 2.288141965866089, "learning_rate": 3.129942295362257e-05, "loss": 0.5103, "step": 1760 }, { "epoch": 1.1260094347165588, "grad_norm": 2.0263402462005615, "learning_rate": 3.1288736909596064e-05, "loss": 0.4017, "step": 1761 }, { "epoch": 1.1266490765171504, "grad_norm": 2.3946094512939453, "learning_rate": 3.127805086556957e-05, "loss": 0.5202, "step": 1762 }, { "epoch": 1.127288718317742, "grad_norm": 2.4939112663269043, "learning_rate": 3.126736482154307e-05, "loss": 0.5099, "step": 1763 }, { "epoch": 1.1279283601183336, "grad_norm": 2.4583992958068848, "learning_rate": 3.125667877751656e-05, "loss": 0.5652, "step": 1764 }, { "epoch": 1.1285680019189255, "grad_norm": 2.297574520111084, "learning_rate": 3.124599273349007e-05, "loss": 0.5321, "step": 1765 }, { "epoch": 1.129207643719517, "grad_norm": 2.2621891498565674, "learning_rate": 3.123530668946356e-05, "loss": 0.5335, "step": 1766 }, { "epoch": 1.1298472855201087, "grad_norm": 2.1876683235168457, "learning_rate": 3.122462064543706e-05, "loss": 0.4652, "step": 1767 }, { "epoch": 1.1304869273207003, "grad_norm": 2.2956509590148926, "learning_rate": 3.121393460141056e-05, "loss": 0.5176, "step": 1768 }, { "epoch": 1.1311265691212922, "grad_norm": 2.2569634914398193, "learning_rate": 3.120324855738406e-05, "loss": 0.5787, "step": 1769 }, { "epoch": 1.1317662109218838, "grad_norm": 2.247763156890869, "learning_rate": 3.119256251335755e-05, "loss": 0.5321, "step": 1770 }, { "epoch": 1.1324058527224754, "grad_norm": 2.1102590560913086, "learning_rate": 3.118187646933106e-05, "loss": 0.4761, "step": 1771 }, { "epoch": 1.133045494523067, "grad_norm": 2.3571970462799072, "learning_rate": 3.117119042530455e-05, "loss": 0.5254, "step": 1772 }, { "epoch": 1.1336851363236589, "grad_norm": 2.1841487884521484, "learning_rate": 3.1160504381278056e-05, "loss": 0.495, "step": 1773 }, { "epoch": 1.1343247781242505, "grad_norm": 2.3618931770324707, "learning_rate": 3.114981833725155e-05, "loss": 0.5374, "step": 1774 }, { "epoch": 1.134964419924842, "grad_norm": 2.4433460235595703, "learning_rate": 3.113913229322505e-05, "loss": 0.5619, "step": 1775 }, { "epoch": 1.1356040617254337, "grad_norm": 2.4330520629882812, "learning_rate": 3.112844624919855e-05, "loss": 0.5556, "step": 1776 }, { "epoch": 1.1362437035260253, "grad_norm": 2.3832008838653564, "learning_rate": 3.111776020517205e-05, "loss": 0.5469, "step": 1777 }, { "epoch": 1.1368833453266172, "grad_norm": 2.4882397651672363, "learning_rate": 3.1107074161145546e-05, "loss": 0.5791, "step": 1778 }, { "epoch": 1.1375229871272088, "grad_norm": 2.6583292484283447, "learning_rate": 3.1096388117119046e-05, "loss": 0.6074, "step": 1779 }, { "epoch": 1.1381626289278004, "grad_norm": 2.230259656906128, "learning_rate": 3.1085702073092545e-05, "loss": 0.4952, "step": 1780 }, { "epoch": 1.138802270728392, "grad_norm": 2.4918019771575928, "learning_rate": 3.107501602906604e-05, "loss": 0.5324, "step": 1781 }, { "epoch": 1.1394419125289839, "grad_norm": 2.433915853500366, "learning_rate": 3.1064329985039544e-05, "loss": 0.5071, "step": 1782 }, { "epoch": 1.1400815543295755, "grad_norm": 2.3743603229522705, "learning_rate": 3.1053643941013036e-05, "loss": 0.5497, "step": 1783 }, { "epoch": 1.140721196130167, "grad_norm": 2.286311388015747, "learning_rate": 3.1042957896986536e-05, "loss": 0.4842, "step": 1784 }, { "epoch": 1.1413608379307587, "grad_norm": 2.4942941665649414, "learning_rate": 3.1032271852960035e-05, "loss": 0.5559, "step": 1785 }, { "epoch": 1.1420004797313505, "grad_norm": 2.2576510906219482, "learning_rate": 3.1021585808933534e-05, "loss": 0.5333, "step": 1786 }, { "epoch": 1.1426401215319422, "grad_norm": 2.5893917083740234, "learning_rate": 3.1010899764907034e-05, "loss": 0.601, "step": 1787 }, { "epoch": 1.1432797633325338, "grad_norm": 2.2144362926483154, "learning_rate": 3.100021372088053e-05, "loss": 0.4977, "step": 1788 }, { "epoch": 1.1439194051331254, "grad_norm": 2.635012626647949, "learning_rate": 3.098952767685403e-05, "loss": 0.6411, "step": 1789 }, { "epoch": 1.144559046933717, "grad_norm": 2.1270768642425537, "learning_rate": 3.0978841632827525e-05, "loss": 0.4926, "step": 1790 }, { "epoch": 1.1451986887343089, "grad_norm": 2.225350856781006, "learning_rate": 3.096815558880103e-05, "loss": 0.4963, "step": 1791 }, { "epoch": 1.1458383305349005, "grad_norm": 2.297593355178833, "learning_rate": 3.0957469544774524e-05, "loss": 0.5099, "step": 1792 }, { "epoch": 1.146477972335492, "grad_norm": 2.215409517288208, "learning_rate": 3.094678350074802e-05, "loss": 0.4963, "step": 1793 }, { "epoch": 1.1471176141360837, "grad_norm": 2.4630534648895264, "learning_rate": 3.093609745672152e-05, "loss": 0.5437, "step": 1794 }, { "epoch": 1.1477572559366755, "grad_norm": 2.34175443649292, "learning_rate": 3.092541141269502e-05, "loss": 0.5717, "step": 1795 }, { "epoch": 1.1483968977372672, "grad_norm": 2.273455858230591, "learning_rate": 3.091472536866852e-05, "loss": 0.512, "step": 1796 }, { "epoch": 1.1490365395378588, "grad_norm": 2.186774492263794, "learning_rate": 3.090403932464202e-05, "loss": 0.5155, "step": 1797 }, { "epoch": 1.1496761813384504, "grad_norm": 2.2865583896636963, "learning_rate": 3.089335328061552e-05, "loss": 0.5246, "step": 1798 }, { "epoch": 1.1503158231390422, "grad_norm": 2.0999932289123535, "learning_rate": 3.088266723658901e-05, "loss": 0.4981, "step": 1799 }, { "epoch": 1.1509554649396339, "grad_norm": 2.296555757522583, "learning_rate": 3.087198119256252e-05, "loss": 0.5723, "step": 1800 }, { "epoch": 1.1515951067402255, "grad_norm": 2.5469870567321777, "learning_rate": 3.086129514853601e-05, "loss": 0.6252, "step": 1801 }, { "epoch": 1.152234748540817, "grad_norm": 2.245955228805542, "learning_rate": 3.085060910450952e-05, "loss": 0.543, "step": 1802 }, { "epoch": 1.1528743903414087, "grad_norm": 2.162105083465576, "learning_rate": 3.083992306048301e-05, "loss": 0.481, "step": 1803 }, { "epoch": 1.1535140321420005, "grad_norm": 2.15701961517334, "learning_rate": 3.082923701645651e-05, "loss": 0.5094, "step": 1804 }, { "epoch": 1.1541536739425922, "grad_norm": 2.099560260772705, "learning_rate": 3.081855097243001e-05, "loss": 0.5572, "step": 1805 }, { "epoch": 1.1547933157431838, "grad_norm": 1.998724341392517, "learning_rate": 3.080786492840351e-05, "loss": 0.4999, "step": 1806 }, { "epoch": 1.1554329575437754, "grad_norm": 2.2188196182250977, "learning_rate": 3.0797178884377e-05, "loss": 0.4778, "step": 1807 }, { "epoch": 1.1560725993443672, "grad_norm": 2.0485172271728516, "learning_rate": 3.078649284035051e-05, "loss": 0.4841, "step": 1808 }, { "epoch": 1.1567122411449589, "grad_norm": 2.4112133979797363, "learning_rate": 3.0775806796324006e-05, "loss": 0.5285, "step": 1809 }, { "epoch": 1.1573518829455505, "grad_norm": 2.2543160915374756, "learning_rate": 3.07651207522975e-05, "loss": 0.494, "step": 1810 }, { "epoch": 1.157991524746142, "grad_norm": 2.1535301208496094, "learning_rate": 3.0754434708271005e-05, "loss": 0.5282, "step": 1811 }, { "epoch": 1.158631166546734, "grad_norm": 2.1569716930389404, "learning_rate": 3.07437486642445e-05, "loss": 0.5009, "step": 1812 }, { "epoch": 1.1592708083473255, "grad_norm": 2.5529816150665283, "learning_rate": 3.0733062620218e-05, "loss": 0.5303, "step": 1813 }, { "epoch": 1.1599104501479172, "grad_norm": 2.2742972373962402, "learning_rate": 3.0722376576191496e-05, "loss": 0.5143, "step": 1814 }, { "epoch": 1.1605500919485088, "grad_norm": 2.1131622791290283, "learning_rate": 3.0711690532164995e-05, "loss": 0.439, "step": 1815 }, { "epoch": 1.1611897337491004, "grad_norm": 2.4731392860412598, "learning_rate": 3.070100448813849e-05, "loss": 0.4983, "step": 1816 }, { "epoch": 1.1618293755496922, "grad_norm": 2.3981497287750244, "learning_rate": 3.0690318444111994e-05, "loss": 0.4753, "step": 1817 }, { "epoch": 1.1624690173502839, "grad_norm": 2.3521344661712646, "learning_rate": 3.067963240008549e-05, "loss": 0.5067, "step": 1818 }, { "epoch": 1.1631086591508755, "grad_norm": 2.4216907024383545, "learning_rate": 3.0668946356058986e-05, "loss": 0.4858, "step": 1819 }, { "epoch": 1.163748300951467, "grad_norm": 2.7841217517852783, "learning_rate": 3.0658260312032485e-05, "loss": 0.5465, "step": 1820 }, { "epoch": 1.164387942752059, "grad_norm": 2.0943174362182617, "learning_rate": 3.0647574268005985e-05, "loss": 0.4304, "step": 1821 }, { "epoch": 1.1650275845526505, "grad_norm": 2.673572063446045, "learning_rate": 3.0636888223979484e-05, "loss": 0.5114, "step": 1822 }, { "epoch": 1.1656672263532422, "grad_norm": 2.243863105773926, "learning_rate": 3.0626202179952984e-05, "loss": 0.4814, "step": 1823 }, { "epoch": 1.1663068681538338, "grad_norm": 2.5512664318084717, "learning_rate": 3.061551613592648e-05, "loss": 0.5605, "step": 1824 }, { "epoch": 1.1669465099544256, "grad_norm": 2.4531712532043457, "learning_rate": 3.0604830091899975e-05, "loss": 0.5505, "step": 1825 }, { "epoch": 1.1675861517550172, "grad_norm": 2.149388313293457, "learning_rate": 3.059414404787348e-05, "loss": 0.5078, "step": 1826 }, { "epoch": 1.1682257935556088, "grad_norm": 2.3568930625915527, "learning_rate": 3.0583458003846974e-05, "loss": 0.5571, "step": 1827 }, { "epoch": 1.1688654353562005, "grad_norm": 2.529860258102417, "learning_rate": 3.0572771959820474e-05, "loss": 0.5956, "step": 1828 }, { "epoch": 1.169505077156792, "grad_norm": 2.334620714187622, "learning_rate": 3.056208591579397e-05, "loss": 0.5125, "step": 1829 }, { "epoch": 1.170144718957384, "grad_norm": 2.1386635303497314, "learning_rate": 3.055139987176747e-05, "loss": 0.4714, "step": 1830 }, { "epoch": 1.1707843607579755, "grad_norm": 2.1763722896575928, "learning_rate": 3.054071382774097e-05, "loss": 0.4904, "step": 1831 }, { "epoch": 1.1714240025585672, "grad_norm": 2.3565046787261963, "learning_rate": 3.053002778371447e-05, "loss": 0.5369, "step": 1832 }, { "epoch": 1.172063644359159, "grad_norm": 2.5247156620025635, "learning_rate": 3.051934173968797e-05, "loss": 0.6099, "step": 1833 }, { "epoch": 1.1727032861597506, "grad_norm": 2.020989179611206, "learning_rate": 3.050865569566147e-05, "loss": 0.5122, "step": 1834 }, { "epoch": 1.1733429279603422, "grad_norm": 2.1518349647521973, "learning_rate": 3.0497969651634966e-05, "loss": 0.5161, "step": 1835 }, { "epoch": 1.1739825697609338, "grad_norm": 2.229703903198242, "learning_rate": 3.0487283607608462e-05, "loss": 0.5164, "step": 1836 }, { "epoch": 1.1746222115615255, "grad_norm": 2.6590027809143066, "learning_rate": 3.0476597563581964e-05, "loss": 0.5673, "step": 1837 }, { "epoch": 1.1752618533621173, "grad_norm": 2.182640314102173, "learning_rate": 3.0465911519555464e-05, "loss": 0.4899, "step": 1838 }, { "epoch": 1.175901495162709, "grad_norm": 2.5984950065612793, "learning_rate": 3.045522547552896e-05, "loss": 0.5967, "step": 1839 }, { "epoch": 1.1765411369633005, "grad_norm": 2.2198374271392822, "learning_rate": 3.0444539431502463e-05, "loss": 0.4849, "step": 1840 }, { "epoch": 1.1771807787638922, "grad_norm": 2.1248881816864014, "learning_rate": 3.043385338747596e-05, "loss": 0.4681, "step": 1841 }, { "epoch": 1.1778204205644838, "grad_norm": 2.1325602531433105, "learning_rate": 3.0423167343449454e-05, "loss": 0.4678, "step": 1842 }, { "epoch": 1.1784600623650756, "grad_norm": 2.462951898574829, "learning_rate": 3.0412481299422957e-05, "loss": 0.5682, "step": 1843 }, { "epoch": 1.1790997041656672, "grad_norm": 2.3943634033203125, "learning_rate": 3.0401795255396453e-05, "loss": 0.5249, "step": 1844 }, { "epoch": 1.1797393459662588, "grad_norm": 2.098130226135254, "learning_rate": 3.039110921136995e-05, "loss": 0.4924, "step": 1845 }, { "epoch": 1.1803789877668507, "grad_norm": 2.0938916206359863, "learning_rate": 3.0380423167343452e-05, "loss": 0.4612, "step": 1846 }, { "epoch": 1.1810186295674423, "grad_norm": 2.520514726638794, "learning_rate": 3.0369737123316948e-05, "loss": 0.5647, "step": 1847 }, { "epoch": 1.181658271368034, "grad_norm": 2.529978036880493, "learning_rate": 3.0359051079290447e-05, "loss": 0.575, "step": 1848 }, { "epoch": 1.1822979131686255, "grad_norm": 2.61244535446167, "learning_rate": 3.0348365035263947e-05, "loss": 0.5425, "step": 1849 }, { "epoch": 1.1829375549692172, "grad_norm": 2.6496524810791016, "learning_rate": 3.0337678991237446e-05, "loss": 0.5568, "step": 1850 }, { "epoch": 1.183577196769809, "grad_norm": 2.020493745803833, "learning_rate": 3.0326992947210942e-05, "loss": 0.4521, "step": 1851 }, { "epoch": 1.1842168385704006, "grad_norm": 2.384413242340088, "learning_rate": 3.0316306903184445e-05, "loss": 0.5559, "step": 1852 }, { "epoch": 1.1848564803709922, "grad_norm": 2.1782498359680176, "learning_rate": 3.030562085915794e-05, "loss": 0.46, "step": 1853 }, { "epoch": 1.1854961221715838, "grad_norm": 2.1637609004974365, "learning_rate": 3.0294934815131437e-05, "loss": 0.4933, "step": 1854 }, { "epoch": 1.1861357639721755, "grad_norm": 2.533543348312378, "learning_rate": 3.028424877110494e-05, "loss": 0.5828, "step": 1855 }, { "epoch": 1.1867754057727673, "grad_norm": 2.0163798332214355, "learning_rate": 3.0273562727078435e-05, "loss": 0.4684, "step": 1856 }, { "epoch": 1.187415047573359, "grad_norm": 2.392141580581665, "learning_rate": 3.0262876683051938e-05, "loss": 0.4986, "step": 1857 }, { "epoch": 1.1880546893739505, "grad_norm": 2.5294408798217773, "learning_rate": 3.0252190639025434e-05, "loss": 0.5441, "step": 1858 }, { "epoch": 1.1886943311745424, "grad_norm": 2.6419923305511475, "learning_rate": 3.024150459499893e-05, "loss": 0.5689, "step": 1859 }, { "epoch": 1.189333972975134, "grad_norm": 2.1667978763580322, "learning_rate": 3.0230818550972433e-05, "loss": 0.4693, "step": 1860 }, { "epoch": 1.1899736147757256, "grad_norm": 1.8922816514968872, "learning_rate": 3.0220132506945932e-05, "loss": 0.3944, "step": 1861 }, { "epoch": 1.1906132565763172, "grad_norm": 2.4143950939178467, "learning_rate": 3.0209446462919428e-05, "loss": 0.4918, "step": 1862 }, { "epoch": 1.1912528983769088, "grad_norm": 2.2610855102539062, "learning_rate": 3.019876041889293e-05, "loss": 0.4902, "step": 1863 }, { "epoch": 1.1918925401775007, "grad_norm": 2.3496017456054688, "learning_rate": 3.0188074374866427e-05, "loss": 0.5427, "step": 1864 }, { "epoch": 1.1925321819780923, "grad_norm": 2.298569679260254, "learning_rate": 3.0177388330839923e-05, "loss": 0.528, "step": 1865 }, { "epoch": 1.193171823778684, "grad_norm": 2.2193431854248047, "learning_rate": 3.0166702286813426e-05, "loss": 0.4479, "step": 1866 }, { "epoch": 1.1938114655792755, "grad_norm": 2.7167887687683105, "learning_rate": 3.015601624278692e-05, "loss": 0.6171, "step": 1867 }, { "epoch": 1.1944511073798671, "grad_norm": 2.5493767261505127, "learning_rate": 3.0145330198760418e-05, "loss": 0.5822, "step": 1868 }, { "epoch": 1.195090749180459, "grad_norm": 2.3377022743225098, "learning_rate": 3.013464415473392e-05, "loss": 0.5856, "step": 1869 }, { "epoch": 1.1957303909810506, "grad_norm": 2.2534713745117188, "learning_rate": 3.0123958110707416e-05, "loss": 0.5162, "step": 1870 }, { "epoch": 1.1963700327816422, "grad_norm": 2.7288925647735596, "learning_rate": 3.0113272066680916e-05, "loss": 0.58, "step": 1871 }, { "epoch": 1.197009674582234, "grad_norm": 2.2652347087860107, "learning_rate": 3.0102586022654415e-05, "loss": 0.5065, "step": 1872 }, { "epoch": 1.1976493163828257, "grad_norm": 2.3203070163726807, "learning_rate": 3.0091899978627914e-05, "loss": 0.5162, "step": 1873 }, { "epoch": 1.1982889581834173, "grad_norm": 2.561286449432373, "learning_rate": 3.008121393460141e-05, "loss": 0.5865, "step": 1874 }, { "epoch": 1.198928599984009, "grad_norm": 2.284147024154663, "learning_rate": 3.0070527890574913e-05, "loss": 0.497, "step": 1875 }, { "epoch": 1.1995682417846005, "grad_norm": 2.2626378536224365, "learning_rate": 3.005984184654841e-05, "loss": 0.5086, "step": 1876 }, { "epoch": 1.2002078835851924, "grad_norm": 2.298335552215576, "learning_rate": 3.0049155802521905e-05, "loss": 0.5078, "step": 1877 }, { "epoch": 1.200847525385784, "grad_norm": 2.6296801567077637, "learning_rate": 3.0038469758495408e-05, "loss": 0.6498, "step": 1878 }, { "epoch": 1.2014871671863756, "grad_norm": 2.3466734886169434, "learning_rate": 3.0027783714468904e-05, "loss": 0.5188, "step": 1879 }, { "epoch": 1.2021268089869672, "grad_norm": 2.5008387565612793, "learning_rate": 3.00170976704424e-05, "loss": 0.551, "step": 1880 }, { "epoch": 1.202766450787559, "grad_norm": 2.2959585189819336, "learning_rate": 3.0006411626415902e-05, "loss": 0.4949, "step": 1881 }, { "epoch": 1.2034060925881507, "grad_norm": 2.023841619491577, "learning_rate": 2.99957255823894e-05, "loss": 0.4609, "step": 1882 }, { "epoch": 1.2040457343887423, "grad_norm": 2.2053587436676025, "learning_rate": 2.9985039538362898e-05, "loss": 0.5189, "step": 1883 }, { "epoch": 1.204685376189334, "grad_norm": 2.360405683517456, "learning_rate": 2.99743534943364e-05, "loss": 0.5432, "step": 1884 }, { "epoch": 1.2053250179899258, "grad_norm": 2.5589892864227295, "learning_rate": 2.9963667450309897e-05, "loss": 0.5874, "step": 1885 }, { "epoch": 1.2059646597905174, "grad_norm": 2.4862349033355713, "learning_rate": 2.99529814062834e-05, "loss": 0.5617, "step": 1886 }, { "epoch": 1.206604301591109, "grad_norm": 2.2344589233398438, "learning_rate": 2.9942295362256895e-05, "loss": 0.5109, "step": 1887 }, { "epoch": 1.2072439433917006, "grad_norm": 2.1723625659942627, "learning_rate": 2.993160931823039e-05, "loss": 0.4738, "step": 1888 }, { "epoch": 1.2078835851922922, "grad_norm": 2.378105640411377, "learning_rate": 2.9920923274203894e-05, "loss": 0.5761, "step": 1889 }, { "epoch": 1.208523226992884, "grad_norm": 2.038362741470337, "learning_rate": 2.991023723017739e-05, "loss": 0.46, "step": 1890 }, { "epoch": 1.2091628687934757, "grad_norm": 2.382270574569702, "learning_rate": 2.9899551186150886e-05, "loss": 0.5294, "step": 1891 }, { "epoch": 1.2098025105940673, "grad_norm": 2.626929759979248, "learning_rate": 2.988886514212439e-05, "loss": 0.6001, "step": 1892 }, { "epoch": 1.210442152394659, "grad_norm": 2.4395911693573, "learning_rate": 2.9878179098097885e-05, "loss": 0.5452, "step": 1893 }, { "epoch": 1.2110817941952507, "grad_norm": 2.2741150856018066, "learning_rate": 2.9867493054071384e-05, "loss": 0.5078, "step": 1894 }, { "epoch": 1.2117214359958424, "grad_norm": 2.165040969848633, "learning_rate": 2.9856807010044883e-05, "loss": 0.501, "step": 1895 }, { "epoch": 1.212361077796434, "grad_norm": 2.318448305130005, "learning_rate": 2.9846120966018383e-05, "loss": 0.5125, "step": 1896 }, { "epoch": 1.2130007195970256, "grad_norm": 2.4866325855255127, "learning_rate": 2.983543492199188e-05, "loss": 0.4923, "step": 1897 }, { "epoch": 1.2136403613976174, "grad_norm": 2.2698774337768555, "learning_rate": 2.982474887796538e-05, "loss": 0.5061, "step": 1898 }, { "epoch": 1.214280003198209, "grad_norm": 2.0199472904205322, "learning_rate": 2.9814062833938877e-05, "loss": 0.455, "step": 1899 }, { "epoch": 1.2149196449988007, "grad_norm": 2.336916446685791, "learning_rate": 2.9803376789912373e-05, "loss": 0.5062, "step": 1900 }, { "epoch": 1.2155592867993923, "grad_norm": 1.9909005165100098, "learning_rate": 2.9792690745885876e-05, "loss": 0.4283, "step": 1901 }, { "epoch": 1.216198928599984, "grad_norm": 2.293056011199951, "learning_rate": 2.9782004701859372e-05, "loss": 0.5115, "step": 1902 }, { "epoch": 1.2168385704005757, "grad_norm": 2.2186899185180664, "learning_rate": 2.9771318657832868e-05, "loss": 0.4795, "step": 1903 }, { "epoch": 1.2174782122011674, "grad_norm": 2.1828689575195312, "learning_rate": 2.976063261380637e-05, "loss": 0.4769, "step": 1904 }, { "epoch": 1.218117854001759, "grad_norm": 2.4945461750030518, "learning_rate": 2.9749946569779867e-05, "loss": 0.5201, "step": 1905 }, { "epoch": 1.2187574958023506, "grad_norm": 2.6482813358306885, "learning_rate": 2.9739260525753366e-05, "loss": 0.5395, "step": 1906 }, { "epoch": 1.2193971376029424, "grad_norm": 2.400118827819824, "learning_rate": 2.972857448172687e-05, "loss": 0.4887, "step": 1907 }, { "epoch": 1.220036779403534, "grad_norm": 2.3764233589172363, "learning_rate": 2.9717888437700365e-05, "loss": 0.4791, "step": 1908 }, { "epoch": 1.2206764212041257, "grad_norm": 2.2382543087005615, "learning_rate": 2.970720239367386e-05, "loss": 0.4716, "step": 1909 }, { "epoch": 1.2213160630047173, "grad_norm": 2.2786457538604736, "learning_rate": 2.9696516349647364e-05, "loss": 0.4923, "step": 1910 }, { "epoch": 1.2219557048053091, "grad_norm": 2.7733383178710938, "learning_rate": 2.968583030562086e-05, "loss": 0.5627, "step": 1911 }, { "epoch": 1.2225953466059007, "grad_norm": 2.51462459564209, "learning_rate": 2.9675144261594356e-05, "loss": 0.503, "step": 1912 }, { "epoch": 1.2232349884064924, "grad_norm": 2.627152681350708, "learning_rate": 2.966445821756786e-05, "loss": 0.4894, "step": 1913 }, { "epoch": 1.223874630207084, "grad_norm": 2.597862482070923, "learning_rate": 2.9653772173541354e-05, "loss": 0.5304, "step": 1914 }, { "epoch": 1.2245142720076756, "grad_norm": 2.7536518573760986, "learning_rate": 2.9643086129514857e-05, "loss": 0.5714, "step": 1915 }, { "epoch": 1.2251539138082674, "grad_norm": 2.5098819732666016, "learning_rate": 2.9632400085488353e-05, "loss": 0.5616, "step": 1916 }, { "epoch": 1.225793555608859, "grad_norm": 2.7121522426605225, "learning_rate": 2.9621714041461852e-05, "loss": 0.6312, "step": 1917 }, { "epoch": 1.2264331974094507, "grad_norm": 2.089224100112915, "learning_rate": 2.9611027997435352e-05, "loss": 0.478, "step": 1918 }, { "epoch": 1.2270728392100423, "grad_norm": 2.100416898727417, "learning_rate": 2.960034195340885e-05, "loss": 0.457, "step": 1919 }, { "epoch": 1.2277124810106341, "grad_norm": 2.5298514366149902, "learning_rate": 2.9589655909382347e-05, "loss": 0.5628, "step": 1920 }, { "epoch": 1.2283521228112257, "grad_norm": 2.3800530433654785, "learning_rate": 2.957896986535585e-05, "loss": 0.4894, "step": 1921 }, { "epoch": 1.2289917646118174, "grad_norm": 2.2956044673919678, "learning_rate": 2.9568283821329346e-05, "loss": 0.5338, "step": 1922 }, { "epoch": 1.229631406412409, "grad_norm": 2.2654309272766113, "learning_rate": 2.9557597777302842e-05, "loss": 0.5196, "step": 1923 }, { "epoch": 1.2302710482130008, "grad_norm": 2.2639081478118896, "learning_rate": 2.9546911733276345e-05, "loss": 0.5301, "step": 1924 }, { "epoch": 1.2309106900135924, "grad_norm": 2.1569902896881104, "learning_rate": 2.953622568924984e-05, "loss": 0.5003, "step": 1925 }, { "epoch": 1.231550331814184, "grad_norm": 2.600153923034668, "learning_rate": 2.9525539645223337e-05, "loss": 0.5973, "step": 1926 }, { "epoch": 1.2321899736147757, "grad_norm": 2.052147626876831, "learning_rate": 2.951485360119684e-05, "loss": 0.4899, "step": 1927 }, { "epoch": 1.2328296154153673, "grad_norm": 2.007266044616699, "learning_rate": 2.9504167557170335e-05, "loss": 0.537, "step": 1928 }, { "epoch": 1.2334692572159591, "grad_norm": 2.7690622806549072, "learning_rate": 2.9493481513143835e-05, "loss": 0.615, "step": 1929 }, { "epoch": 1.2341088990165507, "grad_norm": 2.003932476043701, "learning_rate": 2.9482795469117337e-05, "loss": 0.478, "step": 1930 }, { "epoch": 1.2347485408171424, "grad_norm": 1.9905788898468018, "learning_rate": 2.9472109425090833e-05, "loss": 0.456, "step": 1931 }, { "epoch": 1.235388182617734, "grad_norm": 2.386472702026367, "learning_rate": 2.946142338106433e-05, "loss": 0.5624, "step": 1932 }, { "epoch": 1.2360278244183258, "grad_norm": 2.2222349643707275, "learning_rate": 2.9450737337037832e-05, "loss": 0.5586, "step": 1933 }, { "epoch": 1.2366674662189174, "grad_norm": 2.3216359615325928, "learning_rate": 2.9440051293011328e-05, "loss": 0.5685, "step": 1934 }, { "epoch": 1.237307108019509, "grad_norm": 2.619050979614258, "learning_rate": 2.9429365248984824e-05, "loss": 0.6147, "step": 1935 }, { "epoch": 1.2379467498201007, "grad_norm": 2.078671932220459, "learning_rate": 2.9418679204958327e-05, "loss": 0.4646, "step": 1936 }, { "epoch": 1.2385863916206925, "grad_norm": 2.0084242820739746, "learning_rate": 2.9407993160931823e-05, "loss": 0.4625, "step": 1937 }, { "epoch": 1.2392260334212841, "grad_norm": 2.3187005519866943, "learning_rate": 2.9397307116905322e-05, "loss": 0.546, "step": 1938 }, { "epoch": 1.2398656752218757, "grad_norm": 2.308591604232788, "learning_rate": 2.938662107287882e-05, "loss": 0.5192, "step": 1939 }, { "epoch": 1.2405053170224674, "grad_norm": 2.412846088409424, "learning_rate": 2.937593502885232e-05, "loss": 0.5236, "step": 1940 }, { "epoch": 1.241144958823059, "grad_norm": 2.4006268978118896, "learning_rate": 2.936524898482582e-05, "loss": 0.5036, "step": 1941 }, { "epoch": 1.2417846006236508, "grad_norm": 2.17791485786438, "learning_rate": 2.935456294079932e-05, "loss": 0.5213, "step": 1942 }, { "epoch": 1.2424242424242424, "grad_norm": 2.010676860809326, "learning_rate": 2.9343876896772816e-05, "loss": 0.4613, "step": 1943 }, { "epoch": 1.243063884224834, "grad_norm": 2.296203851699829, "learning_rate": 2.9333190852746318e-05, "loss": 0.5059, "step": 1944 }, { "epoch": 1.2437035260254257, "grad_norm": 2.5326197147369385, "learning_rate": 2.9322504808719814e-05, "loss": 0.5295, "step": 1945 }, { "epoch": 1.2443431678260175, "grad_norm": 2.0551929473876953, "learning_rate": 2.931181876469331e-05, "loss": 0.4428, "step": 1946 }, { "epoch": 1.2449828096266091, "grad_norm": 2.3067052364349365, "learning_rate": 2.9301132720666813e-05, "loss": 0.5254, "step": 1947 }, { "epoch": 1.2456224514272007, "grad_norm": 2.5025124549865723, "learning_rate": 2.929044667664031e-05, "loss": 0.5666, "step": 1948 }, { "epoch": 1.2462620932277924, "grad_norm": 2.6275241374969482, "learning_rate": 2.9279760632613805e-05, "loss": 0.5826, "step": 1949 }, { "epoch": 1.2469017350283842, "grad_norm": 2.2546980381011963, "learning_rate": 2.9269074588587308e-05, "loss": 0.5274, "step": 1950 }, { "epoch": 1.2475413768289758, "grad_norm": 3.0122833251953125, "learning_rate": 2.9258388544560804e-05, "loss": 0.6895, "step": 1951 }, { "epoch": 1.2481810186295674, "grad_norm": 2.42378306388855, "learning_rate": 2.9247702500534303e-05, "loss": 0.5366, "step": 1952 }, { "epoch": 1.248820660430159, "grad_norm": 2.654308795928955, "learning_rate": 2.9237016456507806e-05, "loss": 0.591, "step": 1953 }, { "epoch": 1.2494603022307507, "grad_norm": 2.3251614570617676, "learning_rate": 2.9226330412481302e-05, "loss": 0.5264, "step": 1954 }, { "epoch": 1.2500999440313425, "grad_norm": 2.356510877609253, "learning_rate": 2.9215644368454798e-05, "loss": 0.4748, "step": 1955 }, { "epoch": 1.2507395858319341, "grad_norm": 2.6153526306152344, "learning_rate": 2.92049583244283e-05, "loss": 0.5786, "step": 1956 }, { "epoch": 1.2513792276325257, "grad_norm": 2.101062774658203, "learning_rate": 2.9194272280401796e-05, "loss": 0.4809, "step": 1957 }, { "epoch": 1.2520188694331176, "grad_norm": 2.471029281616211, "learning_rate": 2.9183586236375292e-05, "loss": 0.6066, "step": 1958 }, { "epoch": 1.2526585112337092, "grad_norm": 2.107891082763672, "learning_rate": 2.9172900192348795e-05, "loss": 0.476, "step": 1959 }, { "epoch": 1.2532981530343008, "grad_norm": 2.149592399597168, "learning_rate": 2.916221414832229e-05, "loss": 0.5439, "step": 1960 }, { "epoch": 1.2539377948348924, "grad_norm": 2.310904026031494, "learning_rate": 2.915152810429579e-05, "loss": 0.5272, "step": 1961 }, { "epoch": 1.254577436635484, "grad_norm": 1.9122196435928345, "learning_rate": 2.914084206026929e-05, "loss": 0.4634, "step": 1962 }, { "epoch": 1.2552170784360759, "grad_norm": 2.219306230545044, "learning_rate": 2.913015601624279e-05, "loss": 0.5078, "step": 1963 }, { "epoch": 1.2558567202366675, "grad_norm": 2.1937732696533203, "learning_rate": 2.9119469972216285e-05, "loss": 0.5078, "step": 1964 }, { "epoch": 1.2564963620372591, "grad_norm": 2.5236258506774902, "learning_rate": 2.9108783928189788e-05, "loss": 0.5697, "step": 1965 }, { "epoch": 1.2571360038378507, "grad_norm": 2.051093339920044, "learning_rate": 2.9098097884163284e-05, "loss": 0.4919, "step": 1966 }, { "epoch": 1.2577756456384424, "grad_norm": 2.2349143028259277, "learning_rate": 2.908741184013678e-05, "loss": 0.5124, "step": 1967 }, { "epoch": 1.2584152874390342, "grad_norm": 2.3856165409088135, "learning_rate": 2.9076725796110283e-05, "loss": 0.5226, "step": 1968 }, { "epoch": 1.2590549292396258, "grad_norm": 2.5890698432922363, "learning_rate": 2.906603975208378e-05, "loss": 0.552, "step": 1969 }, { "epoch": 1.2596945710402174, "grad_norm": 2.295560121536255, "learning_rate": 2.905535370805728e-05, "loss": 0.498, "step": 1970 }, { "epoch": 1.2603342128408093, "grad_norm": 2.6017038822174072, "learning_rate": 2.9044667664030777e-05, "loss": 0.5966, "step": 1971 }, { "epoch": 1.2609738546414009, "grad_norm": 2.2091705799102783, "learning_rate": 2.9033981620004273e-05, "loss": 0.4673, "step": 1972 }, { "epoch": 1.2616134964419925, "grad_norm": 2.3184378147125244, "learning_rate": 2.9023295575977776e-05, "loss": 0.4996, "step": 1973 }, { "epoch": 1.2622531382425841, "grad_norm": 2.452347993850708, "learning_rate": 2.9012609531951272e-05, "loss": 0.5428, "step": 1974 }, { "epoch": 1.2628927800431757, "grad_norm": 2.132094621658325, "learning_rate": 2.900192348792477e-05, "loss": 0.4738, "step": 1975 }, { "epoch": 1.2635324218437676, "grad_norm": 2.8011162281036377, "learning_rate": 2.8991237443898274e-05, "loss": 0.5909, "step": 1976 }, { "epoch": 1.2641720636443592, "grad_norm": 2.4866397380828857, "learning_rate": 2.898055139987177e-05, "loss": 0.5347, "step": 1977 }, { "epoch": 1.2648117054449508, "grad_norm": 2.5434610843658447, "learning_rate": 2.8969865355845266e-05, "loss": 0.5399, "step": 1978 }, { "epoch": 1.2654513472455424, "grad_norm": 2.4744534492492676, "learning_rate": 2.895917931181877e-05, "loss": 0.5092, "step": 1979 }, { "epoch": 1.266090989046134, "grad_norm": 2.4128072261810303, "learning_rate": 2.8948493267792265e-05, "loss": 0.5439, "step": 1980 }, { "epoch": 1.2667306308467259, "grad_norm": 2.2428719997406006, "learning_rate": 2.893780722376576e-05, "loss": 0.5078, "step": 1981 }, { "epoch": 1.2673702726473175, "grad_norm": 2.4592859745025635, "learning_rate": 2.8927121179739264e-05, "loss": 0.545, "step": 1982 }, { "epoch": 1.2680099144479091, "grad_norm": 2.5110604763031006, "learning_rate": 2.891643513571276e-05, "loss": 0.5183, "step": 1983 }, { "epoch": 1.268649556248501, "grad_norm": 2.4705893993377686, "learning_rate": 2.890574909168626e-05, "loss": 0.576, "step": 1984 }, { "epoch": 1.2692891980490926, "grad_norm": 2.5122761726379395, "learning_rate": 2.8895063047659758e-05, "loss": 0.5709, "step": 1985 }, { "epoch": 1.2699288398496842, "grad_norm": 2.5504796504974365, "learning_rate": 2.8884377003633258e-05, "loss": 0.4922, "step": 1986 }, { "epoch": 1.2705684816502758, "grad_norm": 2.3992555141448975, "learning_rate": 2.8873690959606754e-05, "loss": 0.5057, "step": 1987 }, { "epoch": 1.2712081234508674, "grad_norm": 2.371886968612671, "learning_rate": 2.8863004915580256e-05, "loss": 0.5184, "step": 1988 }, { "epoch": 1.2718477652514593, "grad_norm": 2.611604690551758, "learning_rate": 2.8852318871553752e-05, "loss": 0.5043, "step": 1989 }, { "epoch": 1.2724874070520509, "grad_norm": 2.582867383956909, "learning_rate": 2.8841632827527248e-05, "loss": 0.5469, "step": 1990 }, { "epoch": 1.2731270488526425, "grad_norm": 2.025519371032715, "learning_rate": 2.883094678350075e-05, "loss": 0.4452, "step": 1991 }, { "epoch": 1.2737666906532341, "grad_norm": 2.218400239944458, "learning_rate": 2.8820260739474247e-05, "loss": 0.5025, "step": 1992 }, { "epoch": 1.2744063324538257, "grad_norm": 2.2676448822021484, "learning_rate": 2.8809574695447743e-05, "loss": 0.504, "step": 1993 }, { "epoch": 1.2750459742544176, "grad_norm": 2.5380170345306396, "learning_rate": 2.8798888651421246e-05, "loss": 0.5355, "step": 1994 }, { "epoch": 1.2756856160550092, "grad_norm": 2.441412925720215, "learning_rate": 2.878820260739474e-05, "loss": 0.5809, "step": 1995 }, { "epoch": 1.2763252578556008, "grad_norm": 2.257662296295166, "learning_rate": 2.877751656336824e-05, "loss": 0.5474, "step": 1996 }, { "epoch": 1.2769648996561926, "grad_norm": 2.474874258041382, "learning_rate": 2.876683051934174e-05, "loss": 0.5936, "step": 1997 }, { "epoch": 1.2776045414567843, "grad_norm": 2.524951696395874, "learning_rate": 2.875614447531524e-05, "loss": 0.56, "step": 1998 }, { "epoch": 1.2782441832573759, "grad_norm": 2.394655227661133, "learning_rate": 2.8745458431288743e-05, "loss": 0.5084, "step": 1999 }, { "epoch": 1.2788838250579675, "grad_norm": 2.157370090484619, "learning_rate": 2.873477238726224e-05, "loss": 0.4924, "step": 2000 }, { "epoch": 1.279523466858559, "grad_norm": 2.449563503265381, "learning_rate": 2.8724086343235734e-05, "loss": 0.5842, "step": 2001 }, { "epoch": 1.280163108659151, "grad_norm": 2.3932130336761475, "learning_rate": 2.8713400299209237e-05, "loss": 0.5419, "step": 2002 }, { "epoch": 1.2808027504597426, "grad_norm": 2.4203569889068604, "learning_rate": 2.8702714255182733e-05, "loss": 0.5544, "step": 2003 }, { "epoch": 1.2814423922603342, "grad_norm": 2.7092268466949463, "learning_rate": 2.869202821115623e-05, "loss": 0.6667, "step": 2004 }, { "epoch": 1.2820820340609258, "grad_norm": 2.446917772293091, "learning_rate": 2.8681342167129732e-05, "loss": 0.5398, "step": 2005 }, { "epoch": 1.2827216758615174, "grad_norm": 2.144728183746338, "learning_rate": 2.8670656123103228e-05, "loss": 0.5031, "step": 2006 }, { "epoch": 1.2833613176621093, "grad_norm": 1.9469785690307617, "learning_rate": 2.8659970079076727e-05, "loss": 0.4171, "step": 2007 }, { "epoch": 1.2840009594627009, "grad_norm": 2.4777307510375977, "learning_rate": 2.8649284035050227e-05, "loss": 0.5256, "step": 2008 }, { "epoch": 1.2846406012632925, "grad_norm": 2.231151819229126, "learning_rate": 2.8638597991023726e-05, "loss": 0.5158, "step": 2009 }, { "epoch": 1.2852802430638843, "grad_norm": 2.5464847087860107, "learning_rate": 2.8627911946997222e-05, "loss": 0.5611, "step": 2010 }, { "epoch": 1.285919884864476, "grad_norm": 2.2185094356536865, "learning_rate": 2.8617225902970725e-05, "loss": 0.4874, "step": 2011 }, { "epoch": 1.2865595266650676, "grad_norm": 2.411947011947632, "learning_rate": 2.860653985894422e-05, "loss": 0.5173, "step": 2012 }, { "epoch": 1.2871991684656592, "grad_norm": 2.1727848052978516, "learning_rate": 2.8595853814917717e-05, "loss": 0.4461, "step": 2013 }, { "epoch": 1.2878388102662508, "grad_norm": 2.1403584480285645, "learning_rate": 2.858516777089122e-05, "loss": 0.4893, "step": 2014 }, { "epoch": 1.2884784520668426, "grad_norm": 2.215038299560547, "learning_rate": 2.8574481726864715e-05, "loss": 0.509, "step": 2015 }, { "epoch": 1.2891180938674343, "grad_norm": 2.4422502517700195, "learning_rate": 2.856379568283821e-05, "loss": 0.5538, "step": 2016 }, { "epoch": 1.2897577356680259, "grad_norm": 2.3239777088165283, "learning_rate": 2.8553109638811714e-05, "loss": 0.5624, "step": 2017 }, { "epoch": 1.2903973774686177, "grad_norm": 2.610250949859619, "learning_rate": 2.854242359478521e-05, "loss": 0.6156, "step": 2018 }, { "epoch": 1.291037019269209, "grad_norm": 2.389676332473755, "learning_rate": 2.853173755075871e-05, "loss": 0.5765, "step": 2019 }, { "epoch": 1.291676661069801, "grad_norm": 2.3729984760284424, "learning_rate": 2.852105150673221e-05, "loss": 0.5785, "step": 2020 }, { "epoch": 1.2923163028703926, "grad_norm": 2.128331422805786, "learning_rate": 2.8510365462705708e-05, "loss": 0.4843, "step": 2021 }, { "epoch": 1.2929559446709842, "grad_norm": 1.9310767650604248, "learning_rate": 2.8499679418679204e-05, "loss": 0.4125, "step": 2022 }, { "epoch": 1.293595586471576, "grad_norm": 2.1316521167755127, "learning_rate": 2.8488993374652707e-05, "loss": 0.4842, "step": 2023 }, { "epoch": 1.2942352282721676, "grad_norm": 2.2978675365448, "learning_rate": 2.8478307330626203e-05, "loss": 0.5318, "step": 2024 }, { "epoch": 1.2948748700727593, "grad_norm": 2.1795082092285156, "learning_rate": 2.84676212865997e-05, "loss": 0.508, "step": 2025 }, { "epoch": 1.2955145118733509, "grad_norm": 2.3023741245269775, "learning_rate": 2.84569352425732e-05, "loss": 0.4939, "step": 2026 }, { "epoch": 1.2961541536739425, "grad_norm": 2.1928141117095947, "learning_rate": 2.8446249198546698e-05, "loss": 0.5242, "step": 2027 }, { "epoch": 1.2967937954745343, "grad_norm": 2.3251402378082275, "learning_rate": 2.84355631545202e-05, "loss": 0.5041, "step": 2028 }, { "epoch": 1.297433437275126, "grad_norm": 2.124814033508301, "learning_rate": 2.8424877110493696e-05, "loss": 0.4453, "step": 2029 }, { "epoch": 1.2980730790757176, "grad_norm": 2.234825849533081, "learning_rate": 2.8414191066467196e-05, "loss": 0.4578, "step": 2030 }, { "epoch": 1.2987127208763094, "grad_norm": 2.198017120361328, "learning_rate": 2.8403505022440695e-05, "loss": 0.4864, "step": 2031 }, { "epoch": 1.299352362676901, "grad_norm": 2.599411725997925, "learning_rate": 2.8392818978414194e-05, "loss": 0.586, "step": 2032 }, { "epoch": 1.2999920044774926, "grad_norm": 3.019258737564087, "learning_rate": 2.838213293438769e-05, "loss": 0.6559, "step": 2033 }, { "epoch": 1.3006316462780843, "grad_norm": 2.443129539489746, "learning_rate": 2.8371446890361193e-05, "loss": 0.5496, "step": 2034 }, { "epoch": 1.3012712880786759, "grad_norm": 2.0341763496398926, "learning_rate": 2.836076084633469e-05, "loss": 0.4104, "step": 2035 }, { "epoch": 1.3019109298792677, "grad_norm": 2.5824708938598633, "learning_rate": 2.8350074802308185e-05, "loss": 0.5244, "step": 2036 }, { "epoch": 1.3025505716798593, "grad_norm": 2.288459300994873, "learning_rate": 2.8339388758281688e-05, "loss": 0.5062, "step": 2037 }, { "epoch": 1.303190213480451, "grad_norm": 2.3950438499450684, "learning_rate": 2.8328702714255184e-05, "loss": 0.5136, "step": 2038 }, { "epoch": 1.3038298552810426, "grad_norm": 2.1054158210754395, "learning_rate": 2.831801667022868e-05, "loss": 0.4868, "step": 2039 }, { "epoch": 1.3044694970816342, "grad_norm": 2.3945541381835938, "learning_rate": 2.8307330626202182e-05, "loss": 0.4904, "step": 2040 }, { "epoch": 1.305109138882226, "grad_norm": 2.5768918991088867, "learning_rate": 2.829664458217568e-05, "loss": 0.5297, "step": 2041 }, { "epoch": 1.3057487806828176, "grad_norm": 1.9596999883651733, "learning_rate": 2.8285958538149178e-05, "loss": 0.4286, "step": 2042 }, { "epoch": 1.3063884224834093, "grad_norm": 2.276869535446167, "learning_rate": 2.8275272494122677e-05, "loss": 0.508, "step": 2043 }, { "epoch": 1.307028064284001, "grad_norm": 2.4440102577209473, "learning_rate": 2.8264586450096177e-05, "loss": 0.5578, "step": 2044 }, { "epoch": 1.3076677060845927, "grad_norm": 2.5011610984802246, "learning_rate": 2.8253900406069672e-05, "loss": 0.5728, "step": 2045 }, { "epoch": 1.3083073478851843, "grad_norm": 2.142320394515991, "learning_rate": 2.8243214362043175e-05, "loss": 0.4671, "step": 2046 }, { "epoch": 1.308946989685776, "grad_norm": 2.733914613723755, "learning_rate": 2.823252831801667e-05, "loss": 0.6407, "step": 2047 }, { "epoch": 1.3095866314863676, "grad_norm": 2.557730197906494, "learning_rate": 2.8221842273990167e-05, "loss": 0.5838, "step": 2048 }, { "epoch": 1.3102262732869594, "grad_norm": 2.604875326156616, "learning_rate": 2.821115622996367e-05, "loss": 0.6167, "step": 2049 }, { "epoch": 1.310865915087551, "grad_norm": 2.5942413806915283, "learning_rate": 2.8200470185937166e-05, "loss": 0.5882, "step": 2050 }, { "epoch": 1.3115055568881426, "grad_norm": 2.3755242824554443, "learning_rate": 2.8189784141910662e-05, "loss": 0.4943, "step": 2051 }, { "epoch": 1.3121451986887342, "grad_norm": 2.50661301612854, "learning_rate": 2.8179098097884165e-05, "loss": 0.5179, "step": 2052 }, { "epoch": 1.3127848404893259, "grad_norm": 2.281099319458008, "learning_rate": 2.8168412053857664e-05, "loss": 0.4805, "step": 2053 }, { "epoch": 1.3134244822899177, "grad_norm": 2.772557258605957, "learning_rate": 2.8157726009831163e-05, "loss": 0.6278, "step": 2054 }, { "epoch": 1.3140641240905093, "grad_norm": 2.296475410461426, "learning_rate": 2.8147039965804663e-05, "loss": 0.5352, "step": 2055 }, { "epoch": 1.314703765891101, "grad_norm": 2.5317020416259766, "learning_rate": 2.813635392177816e-05, "loss": 0.5365, "step": 2056 }, { "epoch": 1.3153434076916928, "grad_norm": 2.149646759033203, "learning_rate": 2.812566787775166e-05, "loss": 0.4913, "step": 2057 }, { "epoch": 1.3159830494922844, "grad_norm": 2.709839105606079, "learning_rate": 2.8114981833725157e-05, "loss": 0.6162, "step": 2058 }, { "epoch": 1.316622691292876, "grad_norm": 2.190150499343872, "learning_rate": 2.8104295789698653e-05, "loss": 0.4981, "step": 2059 }, { "epoch": 1.3172623330934676, "grad_norm": 2.7094614505767822, "learning_rate": 2.8093609745672156e-05, "loss": 0.5431, "step": 2060 }, { "epoch": 1.3179019748940592, "grad_norm": 2.36130690574646, "learning_rate": 2.8082923701645652e-05, "loss": 0.522, "step": 2061 }, { "epoch": 1.318541616694651, "grad_norm": 2.252898693084717, "learning_rate": 2.8072237657619148e-05, "loss": 0.5399, "step": 2062 }, { "epoch": 1.3191812584952427, "grad_norm": 1.9746092557907104, "learning_rate": 2.806155161359265e-05, "loss": 0.4657, "step": 2063 }, { "epoch": 1.3198209002958343, "grad_norm": 2.377559185028076, "learning_rate": 2.8050865569566147e-05, "loss": 0.5234, "step": 2064 }, { "epoch": 1.320460542096426, "grad_norm": 2.5517830848693848, "learning_rate": 2.8040179525539646e-05, "loss": 0.5731, "step": 2065 }, { "epoch": 1.3211001838970176, "grad_norm": 2.527186155319214, "learning_rate": 2.8029493481513146e-05, "loss": 0.5295, "step": 2066 }, { "epoch": 1.3217398256976094, "grad_norm": 2.2997121810913086, "learning_rate": 2.8018807437486645e-05, "loss": 0.4839, "step": 2067 }, { "epoch": 1.322379467498201, "grad_norm": 2.2630481719970703, "learning_rate": 2.800812139346014e-05, "loss": 0.4631, "step": 2068 }, { "epoch": 1.3230191092987926, "grad_norm": 2.2099435329437256, "learning_rate": 2.7997435349433644e-05, "loss": 0.4858, "step": 2069 }, { "epoch": 1.3236587510993845, "grad_norm": 2.2741899490356445, "learning_rate": 2.798674930540714e-05, "loss": 0.5324, "step": 2070 }, { "epoch": 1.324298392899976, "grad_norm": 2.35532808303833, "learning_rate": 2.7976063261380636e-05, "loss": 0.5085, "step": 2071 }, { "epoch": 1.3249380347005677, "grad_norm": 2.399014711380005, "learning_rate": 2.796537721735414e-05, "loss": 0.5461, "step": 2072 }, { "epoch": 1.3255776765011593, "grad_norm": 2.3861753940582275, "learning_rate": 2.7954691173327634e-05, "loss": 0.4752, "step": 2073 }, { "epoch": 1.326217318301751, "grad_norm": 2.0552330017089844, "learning_rate": 2.794400512930113e-05, "loss": 0.4591, "step": 2074 }, { "epoch": 1.3268569601023428, "grad_norm": 2.3268253803253174, "learning_rate": 2.7933319085274633e-05, "loss": 0.5582, "step": 2075 }, { "epoch": 1.3274966019029344, "grad_norm": 2.1823971271514893, "learning_rate": 2.7922633041248132e-05, "loss": 0.4822, "step": 2076 }, { "epoch": 1.328136243703526, "grad_norm": 2.5841736793518066, "learning_rate": 2.791194699722163e-05, "loss": 0.6848, "step": 2077 }, { "epoch": 1.3287758855041176, "grad_norm": 2.1023504734039307, "learning_rate": 2.790126095319513e-05, "loss": 0.4682, "step": 2078 }, { "epoch": 1.3294155273047092, "grad_norm": 1.984799861907959, "learning_rate": 2.7890574909168627e-05, "loss": 0.4474, "step": 2079 }, { "epoch": 1.330055169105301, "grad_norm": 2.2900149822235107, "learning_rate": 2.7879888865142123e-05, "loss": 0.4714, "step": 2080 }, { "epoch": 1.3306948109058927, "grad_norm": 2.4979443550109863, "learning_rate": 2.7869202821115626e-05, "loss": 0.5637, "step": 2081 }, { "epoch": 1.3313344527064843, "grad_norm": 2.433444023132324, "learning_rate": 2.7858516777089122e-05, "loss": 0.5719, "step": 2082 }, { "epoch": 1.3319740945070762, "grad_norm": 2.504610300064087, "learning_rate": 2.7847830733062625e-05, "loss": 0.5263, "step": 2083 }, { "epoch": 1.3326137363076678, "grad_norm": 2.452442169189453, "learning_rate": 2.783714468903612e-05, "loss": 0.5364, "step": 2084 }, { "epoch": 1.3332533781082594, "grad_norm": 3.985201120376587, "learning_rate": 2.7826458645009616e-05, "loss": 0.6818, "step": 2085 }, { "epoch": 1.333893019908851, "grad_norm": 2.133826971054077, "learning_rate": 2.781577260098312e-05, "loss": 0.4908, "step": 2086 }, { "epoch": 1.3345326617094426, "grad_norm": 2.267771005630493, "learning_rate": 2.7805086556956615e-05, "loss": 0.551, "step": 2087 }, { "epoch": 1.3351723035100345, "grad_norm": 2.3498358726501465, "learning_rate": 2.7794400512930115e-05, "loss": 0.5345, "step": 2088 }, { "epoch": 1.335811945310626, "grad_norm": 2.802976369857788, "learning_rate": 2.7783714468903614e-05, "loss": 0.5857, "step": 2089 }, { "epoch": 1.3364515871112177, "grad_norm": 2.341111660003662, "learning_rate": 2.7773028424877113e-05, "loss": 0.4999, "step": 2090 }, { "epoch": 1.3370912289118093, "grad_norm": 2.1392176151275635, "learning_rate": 2.776234238085061e-05, "loss": 0.4702, "step": 2091 }, { "epoch": 1.337730870712401, "grad_norm": 2.261763572692871, "learning_rate": 2.7751656336824112e-05, "loss": 0.4695, "step": 2092 }, { "epoch": 1.3383705125129928, "grad_norm": 2.3268396854400635, "learning_rate": 2.7740970292797608e-05, "loss": 0.5237, "step": 2093 }, { "epoch": 1.3390101543135844, "grad_norm": 2.6014983654022217, "learning_rate": 2.7730284248771104e-05, "loss": 0.5824, "step": 2094 }, { "epoch": 1.339649796114176, "grad_norm": 2.150987148284912, "learning_rate": 2.7719598204744607e-05, "loss": 0.4741, "step": 2095 }, { "epoch": 1.3402894379147678, "grad_norm": 2.799398422241211, "learning_rate": 2.7708912160718103e-05, "loss": 0.5981, "step": 2096 }, { "epoch": 1.3409290797153595, "grad_norm": 2.435011148452759, "learning_rate": 2.76982261166916e-05, "loss": 0.5574, "step": 2097 }, { "epoch": 1.341568721515951, "grad_norm": 2.4173593521118164, "learning_rate": 2.76875400726651e-05, "loss": 0.5573, "step": 2098 }, { "epoch": 1.3422083633165427, "grad_norm": 2.50612473487854, "learning_rate": 2.76768540286386e-05, "loss": 0.6099, "step": 2099 }, { "epoch": 1.3428480051171343, "grad_norm": 2.367081642150879, "learning_rate": 2.7666167984612097e-05, "loss": 0.5173, "step": 2100 }, { "epoch": 1.3434876469177262, "grad_norm": 2.1075406074523926, "learning_rate": 2.76554819405856e-05, "loss": 0.4961, "step": 2101 }, { "epoch": 1.3441272887183178, "grad_norm": 2.4579215049743652, "learning_rate": 2.7644795896559095e-05, "loss": 0.5693, "step": 2102 }, { "epoch": 1.3447669305189094, "grad_norm": 2.2384231090545654, "learning_rate": 2.763410985253259e-05, "loss": 0.5457, "step": 2103 }, { "epoch": 1.345406572319501, "grad_norm": 2.145146131515503, "learning_rate": 2.7623423808506094e-05, "loss": 0.496, "step": 2104 }, { "epoch": 1.3460462141200926, "grad_norm": 2.1262755393981934, "learning_rate": 2.761273776447959e-05, "loss": 0.5263, "step": 2105 }, { "epoch": 1.3466858559206845, "grad_norm": 2.1277053356170654, "learning_rate": 2.7602051720453086e-05, "loss": 0.5083, "step": 2106 }, { "epoch": 1.347325497721276, "grad_norm": 2.3164451122283936, "learning_rate": 2.759136567642659e-05, "loss": 0.556, "step": 2107 }, { "epoch": 1.3479651395218677, "grad_norm": 2.571687936782837, "learning_rate": 2.7580679632400085e-05, "loss": 0.582, "step": 2108 }, { "epoch": 1.3486047813224595, "grad_norm": 2.159640312194824, "learning_rate": 2.7569993588373584e-05, "loss": 0.5143, "step": 2109 }, { "epoch": 1.3492444231230512, "grad_norm": 2.2526590824127197, "learning_rate": 2.7559307544347084e-05, "loss": 0.4905, "step": 2110 }, { "epoch": 1.3498840649236428, "grad_norm": 2.506826639175415, "learning_rate": 2.7548621500320583e-05, "loss": 0.5409, "step": 2111 }, { "epoch": 1.3505237067242344, "grad_norm": 2.7504212856292725, "learning_rate": 2.7537935456294082e-05, "loss": 0.5882, "step": 2112 }, { "epoch": 1.351163348524826, "grad_norm": 2.5309371948242188, "learning_rate": 2.752724941226758e-05, "loss": 0.5614, "step": 2113 }, { "epoch": 1.3518029903254178, "grad_norm": 2.4666011333465576, "learning_rate": 2.7516563368241078e-05, "loss": 0.588, "step": 2114 }, { "epoch": 1.3524426321260095, "grad_norm": 2.1948835849761963, "learning_rate": 2.750587732421458e-05, "loss": 0.4583, "step": 2115 }, { "epoch": 1.353082273926601, "grad_norm": 2.1075820922851562, "learning_rate": 2.7495191280188076e-05, "loss": 0.4812, "step": 2116 }, { "epoch": 1.3537219157271927, "grad_norm": 2.339005947113037, "learning_rate": 2.7484505236161572e-05, "loss": 0.5513, "step": 2117 }, { "epoch": 1.3543615575277843, "grad_norm": 2.250328302383423, "learning_rate": 2.7473819192135075e-05, "loss": 0.4958, "step": 2118 }, { "epoch": 1.3550011993283761, "grad_norm": 2.2444028854370117, "learning_rate": 2.746313314810857e-05, "loss": 0.4974, "step": 2119 }, { "epoch": 1.3556408411289678, "grad_norm": 2.374600410461426, "learning_rate": 2.7452447104082067e-05, "loss": 0.531, "step": 2120 }, { "epoch": 1.3562804829295594, "grad_norm": 2.4628140926361084, "learning_rate": 2.744176106005557e-05, "loss": 0.5539, "step": 2121 }, { "epoch": 1.3569201247301512, "grad_norm": 2.035003900527954, "learning_rate": 2.743107501602907e-05, "loss": 0.4566, "step": 2122 }, { "epoch": 1.3575597665307428, "grad_norm": 2.145343780517578, "learning_rate": 2.7420388972002565e-05, "loss": 0.512, "step": 2123 }, { "epoch": 1.3581994083313345, "grad_norm": 2.484570264816284, "learning_rate": 2.7409702927976068e-05, "loss": 0.5532, "step": 2124 }, { "epoch": 1.358839050131926, "grad_norm": 2.4494516849517822, "learning_rate": 2.7399016883949564e-05, "loss": 0.5327, "step": 2125 }, { "epoch": 1.3594786919325177, "grad_norm": 2.1916258335113525, "learning_rate": 2.738833083992306e-05, "loss": 0.4664, "step": 2126 }, { "epoch": 1.3601183337331095, "grad_norm": 2.4104466438293457, "learning_rate": 2.7377644795896563e-05, "loss": 0.5273, "step": 2127 }, { "epoch": 1.3607579755337011, "grad_norm": 2.0217537879943848, "learning_rate": 2.736695875187006e-05, "loss": 0.4607, "step": 2128 }, { "epoch": 1.3613976173342928, "grad_norm": 2.6108813285827637, "learning_rate": 2.7356272707843555e-05, "loss": 0.5809, "step": 2129 }, { "epoch": 1.3620372591348844, "grad_norm": 2.5624256134033203, "learning_rate": 2.7345586663817057e-05, "loss": 0.5379, "step": 2130 }, { "epoch": 1.362676900935476, "grad_norm": 2.43609356880188, "learning_rate": 2.7334900619790553e-05, "loss": 0.5331, "step": 2131 }, { "epoch": 1.3633165427360678, "grad_norm": 2.9627552032470703, "learning_rate": 2.7324214575764053e-05, "loss": 0.598, "step": 2132 }, { "epoch": 1.3639561845366595, "grad_norm": 2.130108118057251, "learning_rate": 2.7313528531737552e-05, "loss": 0.4547, "step": 2133 }, { "epoch": 1.364595826337251, "grad_norm": 2.660867691040039, "learning_rate": 2.730284248771105e-05, "loss": 0.5587, "step": 2134 }, { "epoch": 1.365235468137843, "grad_norm": 2.347076892852783, "learning_rate": 2.7292156443684547e-05, "loss": 0.5002, "step": 2135 }, { "epoch": 1.3658751099384345, "grad_norm": 2.2299551963806152, "learning_rate": 2.728147039965805e-05, "loss": 0.5184, "step": 2136 }, { "epoch": 1.3665147517390261, "grad_norm": 2.504868507385254, "learning_rate": 2.7270784355631546e-05, "loss": 0.5281, "step": 2137 }, { "epoch": 1.3671543935396178, "grad_norm": 2.4945545196533203, "learning_rate": 2.7260098311605042e-05, "loss": 0.5573, "step": 2138 }, { "epoch": 1.3677940353402094, "grad_norm": 2.51690411567688, "learning_rate": 2.7249412267578545e-05, "loss": 0.515, "step": 2139 }, { "epoch": 1.3684336771408012, "grad_norm": 2.4938085079193115, "learning_rate": 2.723872622355204e-05, "loss": 0.6039, "step": 2140 }, { "epoch": 1.3690733189413928, "grad_norm": 2.6224842071533203, "learning_rate": 2.7228040179525543e-05, "loss": 0.5899, "step": 2141 }, { "epoch": 1.3697129607419845, "grad_norm": 2.0296831130981445, "learning_rate": 2.721735413549904e-05, "loss": 0.4765, "step": 2142 }, { "epoch": 1.3703526025425763, "grad_norm": 2.07785964012146, "learning_rate": 2.7206668091472535e-05, "loss": 0.4803, "step": 2143 }, { "epoch": 1.3709922443431677, "grad_norm": 2.2916152477264404, "learning_rate": 2.7195982047446038e-05, "loss": 0.5085, "step": 2144 }, { "epoch": 1.3716318861437595, "grad_norm": 2.2170231342315674, "learning_rate": 2.7185296003419538e-05, "loss": 0.4794, "step": 2145 }, { "epoch": 1.3722715279443511, "grad_norm": 2.2349820137023926, "learning_rate": 2.7174609959393034e-05, "loss": 0.4767, "step": 2146 }, { "epoch": 1.3729111697449428, "grad_norm": 2.1949474811553955, "learning_rate": 2.7163923915366536e-05, "loss": 0.4729, "step": 2147 }, { "epoch": 1.3735508115455346, "grad_norm": 2.1735739707946777, "learning_rate": 2.7153237871340032e-05, "loss": 0.5466, "step": 2148 }, { "epoch": 1.3741904533461262, "grad_norm": 2.28950834274292, "learning_rate": 2.7142551827313528e-05, "loss": 0.5615, "step": 2149 }, { "epoch": 1.3748300951467178, "grad_norm": 2.4909775257110596, "learning_rate": 2.713186578328703e-05, "loss": 0.5696, "step": 2150 }, { "epoch": 1.3754697369473095, "grad_norm": 2.452730655670166, "learning_rate": 2.7121179739260527e-05, "loss": 0.5121, "step": 2151 }, { "epoch": 1.376109378747901, "grad_norm": 2.5877861976623535, "learning_rate": 2.7110493695234023e-05, "loss": 0.5762, "step": 2152 }, { "epoch": 1.376749020548493, "grad_norm": 2.182504415512085, "learning_rate": 2.7099807651207526e-05, "loss": 0.4633, "step": 2153 }, { "epoch": 1.3773886623490845, "grad_norm": 2.3482775688171387, "learning_rate": 2.708912160718102e-05, "loss": 0.5491, "step": 2154 }, { "epoch": 1.3780283041496761, "grad_norm": 2.494331121444702, "learning_rate": 2.707843556315452e-05, "loss": 0.5298, "step": 2155 }, { "epoch": 1.378667945950268, "grad_norm": 2.030103921890259, "learning_rate": 2.706774951912802e-05, "loss": 0.4647, "step": 2156 }, { "epoch": 1.3793075877508596, "grad_norm": 2.099980354309082, "learning_rate": 2.705706347510152e-05, "loss": 0.4702, "step": 2157 }, { "epoch": 1.3799472295514512, "grad_norm": 2.0252654552459717, "learning_rate": 2.7046377431075016e-05, "loss": 0.4824, "step": 2158 }, { "epoch": 1.3805868713520428, "grad_norm": 2.409728765487671, "learning_rate": 2.703569138704852e-05, "loss": 0.561, "step": 2159 }, { "epoch": 1.3812265131526344, "grad_norm": 2.1638243198394775, "learning_rate": 2.7025005343022014e-05, "loss": 0.4875, "step": 2160 }, { "epoch": 1.3818661549532263, "grad_norm": 2.7950870990753174, "learning_rate": 2.701431929899551e-05, "loss": 0.6157, "step": 2161 }, { "epoch": 1.382505796753818, "grad_norm": 2.2581465244293213, "learning_rate": 2.7003633254969013e-05, "loss": 0.5136, "step": 2162 }, { "epoch": 1.3831454385544095, "grad_norm": 2.0895376205444336, "learning_rate": 2.699294721094251e-05, "loss": 0.4632, "step": 2163 }, { "epoch": 1.3837850803550011, "grad_norm": 2.4460158348083496, "learning_rate": 2.6982261166916005e-05, "loss": 0.5093, "step": 2164 }, { "epoch": 1.3844247221555928, "grad_norm": 2.2036702632904053, "learning_rate": 2.6971575122889508e-05, "loss": 0.4756, "step": 2165 }, { "epoch": 1.3850643639561846, "grad_norm": 2.2187347412109375, "learning_rate": 2.6960889078863004e-05, "loss": 0.4978, "step": 2166 }, { "epoch": 1.3857040057567762, "grad_norm": 2.660968065261841, "learning_rate": 2.6950203034836507e-05, "loss": 0.6019, "step": 2167 }, { "epoch": 1.3863436475573678, "grad_norm": 2.3281824588775635, "learning_rate": 2.6939516990810006e-05, "loss": 0.4823, "step": 2168 }, { "epoch": 1.3869832893579597, "grad_norm": 2.594407796859741, "learning_rate": 2.6928830946783502e-05, "loss": 0.5807, "step": 2169 }, { "epoch": 1.3876229311585513, "grad_norm": 2.920761823654175, "learning_rate": 2.6918144902757005e-05, "loss": 0.6076, "step": 2170 }, { "epoch": 1.388262572959143, "grad_norm": 2.4506754875183105, "learning_rate": 2.69074588587305e-05, "loss": 0.5178, "step": 2171 }, { "epoch": 1.3889022147597345, "grad_norm": 2.345679998397827, "learning_rate": 2.6896772814703997e-05, "loss": 0.5214, "step": 2172 }, { "epoch": 1.3895418565603261, "grad_norm": 2.139457941055298, "learning_rate": 2.68860867706775e-05, "loss": 0.4267, "step": 2173 }, { "epoch": 1.390181498360918, "grad_norm": 2.454946279525757, "learning_rate": 2.6875400726650995e-05, "loss": 0.5434, "step": 2174 }, { "epoch": 1.3908211401615096, "grad_norm": 2.123443365097046, "learning_rate": 2.686471468262449e-05, "loss": 0.4884, "step": 2175 }, { "epoch": 1.3914607819621012, "grad_norm": 2.107789993286133, "learning_rate": 2.6854028638597994e-05, "loss": 0.4471, "step": 2176 }, { "epoch": 1.3921004237626928, "grad_norm": 2.5171778202056885, "learning_rate": 2.684334259457149e-05, "loss": 0.5957, "step": 2177 }, { "epoch": 1.3927400655632844, "grad_norm": 2.0856642723083496, "learning_rate": 2.683265655054499e-05, "loss": 0.4599, "step": 2178 }, { "epoch": 1.3933797073638763, "grad_norm": 2.1569645404815674, "learning_rate": 2.682197050651849e-05, "loss": 0.4768, "step": 2179 }, { "epoch": 1.394019349164468, "grad_norm": 2.365912675857544, "learning_rate": 2.6811284462491988e-05, "loss": 0.5399, "step": 2180 }, { "epoch": 1.3946589909650595, "grad_norm": 2.346978187561035, "learning_rate": 2.6800598418465484e-05, "loss": 0.539, "step": 2181 }, { "epoch": 1.3952986327656514, "grad_norm": 2.289849281311035, "learning_rate": 2.6789912374438987e-05, "loss": 0.5232, "step": 2182 }, { "epoch": 1.395938274566243, "grad_norm": 1.9996365308761597, "learning_rate": 2.6779226330412483e-05, "loss": 0.4733, "step": 2183 }, { "epoch": 1.3965779163668346, "grad_norm": 2.292644500732422, "learning_rate": 2.676854028638598e-05, "loss": 0.498, "step": 2184 }, { "epoch": 1.3972175581674262, "grad_norm": 2.5906386375427246, "learning_rate": 2.675785424235948e-05, "loss": 0.5188, "step": 2185 }, { "epoch": 1.3978571999680178, "grad_norm": 1.995419979095459, "learning_rate": 2.6747168198332977e-05, "loss": 0.438, "step": 2186 }, { "epoch": 1.3984968417686097, "grad_norm": 2.6388261318206787, "learning_rate": 2.6736482154306473e-05, "loss": 0.5653, "step": 2187 }, { "epoch": 1.3991364835692013, "grad_norm": 2.474968433380127, "learning_rate": 2.6725796110279976e-05, "loss": 0.5431, "step": 2188 }, { "epoch": 1.399776125369793, "grad_norm": 2.0440359115600586, "learning_rate": 2.6715110066253472e-05, "loss": 0.4536, "step": 2189 }, { "epoch": 1.4004157671703845, "grad_norm": 2.609251022338867, "learning_rate": 2.670442402222697e-05, "loss": 0.5955, "step": 2190 }, { "epoch": 1.4010554089709761, "grad_norm": 2.4600322246551514, "learning_rate": 2.6693737978200474e-05, "loss": 0.5551, "step": 2191 }, { "epoch": 1.401695050771568, "grad_norm": 1.9794594049453735, "learning_rate": 2.668305193417397e-05, "loss": 0.4636, "step": 2192 }, { "epoch": 1.4023346925721596, "grad_norm": 2.4079878330230713, "learning_rate": 2.6672365890147466e-05, "loss": 0.4984, "step": 2193 }, { "epoch": 1.4029743343727512, "grad_norm": 2.2058138847351074, "learning_rate": 2.666167984612097e-05, "loss": 0.4616, "step": 2194 }, { "epoch": 1.403613976173343, "grad_norm": 2.2484633922576904, "learning_rate": 2.6650993802094465e-05, "loss": 0.4869, "step": 2195 }, { "epoch": 1.4042536179739347, "grad_norm": 2.3188061714172363, "learning_rate": 2.6640307758067968e-05, "loss": 0.4867, "step": 2196 }, { "epoch": 1.4048932597745263, "grad_norm": 2.2876102924346924, "learning_rate": 2.6629621714041464e-05, "loss": 0.5466, "step": 2197 }, { "epoch": 1.405532901575118, "grad_norm": 2.480281114578247, "learning_rate": 2.661893567001496e-05, "loss": 0.5372, "step": 2198 }, { "epoch": 1.4061725433757095, "grad_norm": 2.280669927597046, "learning_rate": 2.6608249625988462e-05, "loss": 0.4989, "step": 2199 }, { "epoch": 1.4068121851763014, "grad_norm": 2.2180023193359375, "learning_rate": 2.659756358196196e-05, "loss": 0.4653, "step": 2200 }, { "epoch": 1.407451826976893, "grad_norm": 2.4890365600585938, "learning_rate": 2.6586877537935458e-05, "loss": 0.5191, "step": 2201 }, { "epoch": 1.4080914687774846, "grad_norm": 2.0783698558807373, "learning_rate": 2.6576191493908957e-05, "loss": 0.4173, "step": 2202 }, { "epoch": 1.4087311105780762, "grad_norm": 2.147512197494507, "learning_rate": 2.6565505449882456e-05, "loss": 0.4562, "step": 2203 }, { "epoch": 1.4093707523786678, "grad_norm": 2.341219425201416, "learning_rate": 2.6554819405855952e-05, "loss": 0.5178, "step": 2204 }, { "epoch": 1.4100103941792597, "grad_norm": 2.4911327362060547, "learning_rate": 2.6544133361829455e-05, "loss": 0.5357, "step": 2205 }, { "epoch": 1.4106500359798513, "grad_norm": 2.4268505573272705, "learning_rate": 2.653344731780295e-05, "loss": 0.5103, "step": 2206 }, { "epoch": 1.411289677780443, "grad_norm": 2.058560848236084, "learning_rate": 2.6522761273776447e-05, "loss": 0.4807, "step": 2207 }, { "epoch": 1.4119293195810347, "grad_norm": 2.4109654426574707, "learning_rate": 2.651207522974995e-05, "loss": 0.5472, "step": 2208 }, { "epoch": 1.4125689613816264, "grad_norm": 2.400390386581421, "learning_rate": 2.6501389185723446e-05, "loss": 0.5038, "step": 2209 }, { "epoch": 1.413208603182218, "grad_norm": 2.4504222869873047, "learning_rate": 2.6490703141696942e-05, "loss": 0.5602, "step": 2210 }, { "epoch": 1.4138482449828096, "grad_norm": 2.4026997089385986, "learning_rate": 2.6480017097670445e-05, "loss": 0.5372, "step": 2211 }, { "epoch": 1.4144878867834012, "grad_norm": 2.321833848953247, "learning_rate": 2.646933105364394e-05, "loss": 0.52, "step": 2212 }, { "epoch": 1.415127528583993, "grad_norm": 2.1148695945739746, "learning_rate": 2.645864500961744e-05, "loss": 0.4957, "step": 2213 }, { "epoch": 1.4157671703845847, "grad_norm": 2.3939766883850098, "learning_rate": 2.6447958965590943e-05, "loss": 0.5347, "step": 2214 }, { "epoch": 1.4164068121851763, "grad_norm": 2.4524459838867188, "learning_rate": 2.643727292156444e-05, "loss": 0.5177, "step": 2215 }, { "epoch": 1.417046453985768, "grad_norm": 2.472960948944092, "learning_rate": 2.6426586877537935e-05, "loss": 0.5091, "step": 2216 }, { "epoch": 1.4176860957863595, "grad_norm": 2.2612154483795166, "learning_rate": 2.6415900833511437e-05, "loss": 0.4907, "step": 2217 }, { "epoch": 1.4183257375869514, "grad_norm": 2.2258989810943604, "learning_rate": 2.6405214789484933e-05, "loss": 0.4859, "step": 2218 }, { "epoch": 1.418965379387543, "grad_norm": 2.5067334175109863, "learning_rate": 2.639452874545843e-05, "loss": 0.5395, "step": 2219 }, { "epoch": 1.4196050211881346, "grad_norm": 2.2099735736846924, "learning_rate": 2.6383842701431932e-05, "loss": 0.4753, "step": 2220 }, { "epoch": 1.4202446629887264, "grad_norm": 2.1398520469665527, "learning_rate": 2.6373156657405428e-05, "loss": 0.4466, "step": 2221 }, { "epoch": 1.420884304789318, "grad_norm": 2.32903790473938, "learning_rate": 2.6362470613378924e-05, "loss": 0.5017, "step": 2222 }, { "epoch": 1.4215239465899097, "grad_norm": 2.1925742626190186, "learning_rate": 2.6351784569352427e-05, "loss": 0.5192, "step": 2223 }, { "epoch": 1.4221635883905013, "grad_norm": 1.9855402708053589, "learning_rate": 2.6341098525325926e-05, "loss": 0.4411, "step": 2224 }, { "epoch": 1.422803230191093, "grad_norm": 1.9421648979187012, "learning_rate": 2.6330412481299426e-05, "loss": 0.4103, "step": 2225 }, { "epoch": 1.4234428719916847, "grad_norm": 1.8968526124954224, "learning_rate": 2.6319726437272925e-05, "loss": 0.4386, "step": 2226 }, { "epoch": 1.4240825137922763, "grad_norm": 2.6044423580169678, "learning_rate": 2.630904039324642e-05, "loss": 0.5969, "step": 2227 }, { "epoch": 1.424722155592868, "grad_norm": 2.27577543258667, "learning_rate": 2.6298354349219924e-05, "loss": 0.4865, "step": 2228 }, { "epoch": 1.4253617973934596, "grad_norm": 2.3630144596099854, "learning_rate": 2.628766830519342e-05, "loss": 0.5102, "step": 2229 }, { "epoch": 1.4260014391940512, "grad_norm": 2.4413297176361084, "learning_rate": 2.6276982261166916e-05, "loss": 0.5066, "step": 2230 }, { "epoch": 1.426641080994643, "grad_norm": 2.246939182281494, "learning_rate": 2.6266296217140418e-05, "loss": 0.4822, "step": 2231 }, { "epoch": 1.4272807227952347, "grad_norm": 2.679086685180664, "learning_rate": 2.6255610173113914e-05, "loss": 0.615, "step": 2232 }, { "epoch": 1.4279203645958263, "grad_norm": 2.3805325031280518, "learning_rate": 2.624492412908741e-05, "loss": 0.5101, "step": 2233 }, { "epoch": 1.4285600063964181, "grad_norm": 2.2592151165008545, "learning_rate": 2.6234238085060913e-05, "loss": 0.5103, "step": 2234 }, { "epoch": 1.4291996481970097, "grad_norm": 2.27573823928833, "learning_rate": 2.622355204103441e-05, "loss": 0.5052, "step": 2235 }, { "epoch": 1.4298392899976013, "grad_norm": 2.236330986022949, "learning_rate": 2.621286599700791e-05, "loss": 0.4856, "step": 2236 }, { "epoch": 1.430478931798193, "grad_norm": 2.019353151321411, "learning_rate": 2.6202179952981408e-05, "loss": 0.4785, "step": 2237 }, { "epoch": 1.4311185735987846, "grad_norm": 2.6522879600524902, "learning_rate": 2.6191493908954907e-05, "loss": 0.6043, "step": 2238 }, { "epoch": 1.4317582153993764, "grad_norm": 2.162611246109009, "learning_rate": 2.6180807864928403e-05, "loss": 0.4513, "step": 2239 }, { "epoch": 1.432397857199968, "grad_norm": 2.396352529525757, "learning_rate": 2.6170121820901906e-05, "loss": 0.504, "step": 2240 }, { "epoch": 1.4330374990005597, "grad_norm": 2.499436378479004, "learning_rate": 2.6159435776875402e-05, "loss": 0.5159, "step": 2241 }, { "epoch": 1.4336771408011513, "grad_norm": 2.3926210403442383, "learning_rate": 2.6148749732848898e-05, "loss": 0.5528, "step": 2242 }, { "epoch": 1.434316782601743, "grad_norm": 2.022723913192749, "learning_rate": 2.61380636888224e-05, "loss": 0.461, "step": 2243 }, { "epoch": 1.4349564244023347, "grad_norm": 2.447625160217285, "learning_rate": 2.6127377644795896e-05, "loss": 0.6057, "step": 2244 }, { "epoch": 1.4355960662029263, "grad_norm": 2.4095206260681152, "learning_rate": 2.6116691600769392e-05, "loss": 0.5665, "step": 2245 }, { "epoch": 1.436235708003518, "grad_norm": 2.1642065048217773, "learning_rate": 2.6106005556742895e-05, "loss": 0.4461, "step": 2246 }, { "epoch": 1.4368753498041098, "grad_norm": 2.603368043899536, "learning_rate": 2.6095319512716395e-05, "loss": 0.5777, "step": 2247 }, { "epoch": 1.4375149916047014, "grad_norm": 2.2961888313293457, "learning_rate": 2.608463346868989e-05, "loss": 0.5096, "step": 2248 }, { "epoch": 1.438154633405293, "grad_norm": 2.879202127456665, "learning_rate": 2.6073947424663393e-05, "loss": 0.6394, "step": 2249 }, { "epoch": 1.4387942752058847, "grad_norm": 2.4922022819519043, "learning_rate": 2.606326138063689e-05, "loss": 0.5425, "step": 2250 }, { "epoch": 1.4394339170064763, "grad_norm": 2.512561798095703, "learning_rate": 2.6052575336610392e-05, "loss": 0.5895, "step": 2251 }, { "epoch": 1.440073558807068, "grad_norm": 2.3080883026123047, "learning_rate": 2.6041889292583888e-05, "loss": 0.4951, "step": 2252 }, { "epoch": 1.4407132006076597, "grad_norm": 2.3077144622802734, "learning_rate": 2.6031203248557384e-05, "loss": 0.5104, "step": 2253 }, { "epoch": 1.4413528424082513, "grad_norm": 2.0974791049957275, "learning_rate": 2.6020517204530887e-05, "loss": 0.4529, "step": 2254 }, { "epoch": 1.4419924842088432, "grad_norm": 2.2111384868621826, "learning_rate": 2.6009831160504383e-05, "loss": 0.5113, "step": 2255 }, { "epoch": 1.4426321260094346, "grad_norm": 2.3056976795196533, "learning_rate": 2.599914511647788e-05, "loss": 0.5128, "step": 2256 }, { "epoch": 1.4432717678100264, "grad_norm": 2.189061164855957, "learning_rate": 2.598845907245138e-05, "loss": 0.45, "step": 2257 }, { "epoch": 1.443911409610618, "grad_norm": 2.0347671508789062, "learning_rate": 2.5977773028424877e-05, "loss": 0.4605, "step": 2258 }, { "epoch": 1.4445510514112097, "grad_norm": 2.1968576908111572, "learning_rate": 2.5967086984398377e-05, "loss": 0.4658, "step": 2259 }, { "epoch": 1.4451906932118015, "grad_norm": 2.511888027191162, "learning_rate": 2.5956400940371876e-05, "loss": 0.5669, "step": 2260 }, { "epoch": 1.445830335012393, "grad_norm": 2.248568296432495, "learning_rate": 2.5945714896345375e-05, "loss": 0.4958, "step": 2261 }, { "epoch": 1.4464699768129847, "grad_norm": 2.163270950317383, "learning_rate": 2.593502885231887e-05, "loss": 0.4576, "step": 2262 }, { "epoch": 1.4471096186135763, "grad_norm": 2.094024896621704, "learning_rate": 2.5924342808292374e-05, "loss": 0.4509, "step": 2263 }, { "epoch": 1.447749260414168, "grad_norm": 2.8308749198913574, "learning_rate": 2.591365676426587e-05, "loss": 0.5922, "step": 2264 }, { "epoch": 1.4483889022147598, "grad_norm": 2.6014363765716553, "learning_rate": 2.5902970720239366e-05, "loss": 0.5073, "step": 2265 }, { "epoch": 1.4490285440153514, "grad_norm": 2.258899688720703, "learning_rate": 2.589228467621287e-05, "loss": 0.5131, "step": 2266 }, { "epoch": 1.449668185815943, "grad_norm": 2.1131486892700195, "learning_rate": 2.5881598632186365e-05, "loss": 0.4759, "step": 2267 }, { "epoch": 1.4503078276165349, "grad_norm": 2.4243154525756836, "learning_rate": 2.587091258815986e-05, "loss": 0.541, "step": 2268 }, { "epoch": 1.4509474694171265, "grad_norm": 2.215507984161377, "learning_rate": 2.5860226544133364e-05, "loss": 0.4902, "step": 2269 }, { "epoch": 1.451587111217718, "grad_norm": 2.332162380218506, "learning_rate": 2.5849540500106863e-05, "loss": 0.507, "step": 2270 }, { "epoch": 1.4522267530183097, "grad_norm": 2.3548402786254883, "learning_rate": 2.583885445608036e-05, "loss": 0.4851, "step": 2271 }, { "epoch": 1.4528663948189013, "grad_norm": 2.058729887008667, "learning_rate": 2.582816841205386e-05, "loss": 0.4478, "step": 2272 }, { "epoch": 1.4535060366194932, "grad_norm": 2.3999671936035156, "learning_rate": 2.5817482368027358e-05, "loss": 0.5128, "step": 2273 }, { "epoch": 1.4541456784200848, "grad_norm": 2.3504152297973633, "learning_rate": 2.5806796324000854e-05, "loss": 0.5526, "step": 2274 }, { "epoch": 1.4547853202206764, "grad_norm": 2.4086127281188965, "learning_rate": 2.5796110279974356e-05, "loss": 0.4998, "step": 2275 }, { "epoch": 1.455424962021268, "grad_norm": 2.562897205352783, "learning_rate": 2.5785424235947852e-05, "loss": 0.546, "step": 2276 }, { "epoch": 1.4560646038218596, "grad_norm": 2.3442258834838867, "learning_rate": 2.5774738191921348e-05, "loss": 0.4747, "step": 2277 }, { "epoch": 1.4567042456224515, "grad_norm": 2.460014581680298, "learning_rate": 2.576405214789485e-05, "loss": 0.5114, "step": 2278 }, { "epoch": 1.457343887423043, "grad_norm": 2.154784679412842, "learning_rate": 2.5753366103868347e-05, "loss": 0.4355, "step": 2279 }, { "epoch": 1.4579835292236347, "grad_norm": 1.9900468587875366, "learning_rate": 2.574268005984185e-05, "loss": 0.4314, "step": 2280 }, { "epoch": 1.4586231710242266, "grad_norm": 2.4974210262298584, "learning_rate": 2.5731994015815346e-05, "loss": 0.5147, "step": 2281 }, { "epoch": 1.4592628128248182, "grad_norm": 2.3759498596191406, "learning_rate": 2.5721307971788845e-05, "loss": 0.4576, "step": 2282 }, { "epoch": 1.4599024546254098, "grad_norm": 2.3022379875183105, "learning_rate": 2.5710621927762344e-05, "loss": 0.4939, "step": 2283 }, { "epoch": 1.4605420964260014, "grad_norm": 2.2871007919311523, "learning_rate": 2.5699935883735844e-05, "loss": 0.4867, "step": 2284 }, { "epoch": 1.461181738226593, "grad_norm": 2.8387856483459473, "learning_rate": 2.568924983970934e-05, "loss": 0.6164, "step": 2285 }, { "epoch": 1.4618213800271849, "grad_norm": 2.685382127761841, "learning_rate": 2.5678563795682843e-05, "loss": 0.5572, "step": 2286 }, { "epoch": 1.4624610218277765, "grad_norm": 2.6641671657562256, "learning_rate": 2.566787775165634e-05, "loss": 0.5765, "step": 2287 }, { "epoch": 1.463100663628368, "grad_norm": 2.3019654750823975, "learning_rate": 2.5657191707629834e-05, "loss": 0.49, "step": 2288 }, { "epoch": 1.4637403054289597, "grad_norm": 2.3412725925445557, "learning_rate": 2.5646505663603337e-05, "loss": 0.4738, "step": 2289 }, { "epoch": 1.4643799472295513, "grad_norm": 2.0882978439331055, "learning_rate": 2.5635819619576833e-05, "loss": 0.4569, "step": 2290 }, { "epoch": 1.4650195890301432, "grad_norm": 2.3611629009246826, "learning_rate": 2.562513357555033e-05, "loss": 0.5354, "step": 2291 }, { "epoch": 1.4656592308307348, "grad_norm": 2.6620607376098633, "learning_rate": 2.5614447531523832e-05, "loss": 0.5473, "step": 2292 }, { "epoch": 1.4662988726313264, "grad_norm": 2.0741662979125977, "learning_rate": 2.560376148749733e-05, "loss": 0.4435, "step": 2293 }, { "epoch": 1.4669385144319183, "grad_norm": 2.37638258934021, "learning_rate": 2.5593075443470827e-05, "loss": 0.5466, "step": 2294 }, { "epoch": 1.4675781562325099, "grad_norm": 2.0607833862304688, "learning_rate": 2.558238939944433e-05, "loss": 0.4425, "step": 2295 }, { "epoch": 1.4682177980331015, "grad_norm": 1.9675531387329102, "learning_rate": 2.5571703355417826e-05, "loss": 0.4611, "step": 2296 }, { "epoch": 1.468857439833693, "grad_norm": 2.290937662124634, "learning_rate": 2.5561017311391322e-05, "loss": 0.5219, "step": 2297 }, { "epoch": 1.4694970816342847, "grad_norm": 2.2166943550109863, "learning_rate": 2.5550331267364825e-05, "loss": 0.5278, "step": 2298 }, { "epoch": 1.4701367234348766, "grad_norm": 2.4589569568634033, "learning_rate": 2.553964522333832e-05, "loss": 0.5253, "step": 2299 }, { "epoch": 1.4707763652354682, "grad_norm": 2.170689105987549, "learning_rate": 2.5528959179311817e-05, "loss": 0.4899, "step": 2300 }, { "epoch": 1.4714160070360598, "grad_norm": 2.7934813499450684, "learning_rate": 2.551827313528532e-05, "loss": 0.6217, "step": 2301 }, { "epoch": 1.4720556488366514, "grad_norm": 2.2422893047332764, "learning_rate": 2.5507587091258815e-05, "loss": 0.5055, "step": 2302 }, { "epoch": 1.472695290637243, "grad_norm": 2.328583240509033, "learning_rate": 2.5496901047232315e-05, "loss": 0.5058, "step": 2303 }, { "epoch": 1.4733349324378349, "grad_norm": 2.06060528755188, "learning_rate": 2.5486215003205814e-05, "loss": 0.4975, "step": 2304 }, { "epoch": 1.4739745742384265, "grad_norm": 1.9319361448287964, "learning_rate": 2.5475528959179313e-05, "loss": 0.4185, "step": 2305 }, { "epoch": 1.474614216039018, "grad_norm": 1.9154685735702515, "learning_rate": 2.546484291515281e-05, "loss": 0.4282, "step": 2306 }, { "epoch": 1.47525385783961, "grad_norm": 2.055645227432251, "learning_rate": 2.5454156871126312e-05, "loss": 0.4691, "step": 2307 }, { "epoch": 1.4758934996402016, "grad_norm": 2.6475746631622314, "learning_rate": 2.5443470827099808e-05, "loss": 0.5837, "step": 2308 }, { "epoch": 1.4765331414407932, "grad_norm": 2.161628484725952, "learning_rate": 2.543278478307331e-05, "loss": 0.4263, "step": 2309 }, { "epoch": 1.4771727832413848, "grad_norm": 2.270693302154541, "learning_rate": 2.5422098739046807e-05, "loss": 0.5034, "step": 2310 }, { "epoch": 1.4778124250419764, "grad_norm": 2.5863564014434814, "learning_rate": 2.5411412695020303e-05, "loss": 0.5412, "step": 2311 }, { "epoch": 1.4784520668425682, "grad_norm": 2.4512579441070557, "learning_rate": 2.5400726650993806e-05, "loss": 0.5, "step": 2312 }, { "epoch": 1.4790917086431599, "grad_norm": 2.654994249343872, "learning_rate": 2.53900406069673e-05, "loss": 0.563, "step": 2313 }, { "epoch": 1.4797313504437515, "grad_norm": 2.3832905292510986, "learning_rate": 2.5379354562940798e-05, "loss": 0.4877, "step": 2314 }, { "epoch": 1.480370992244343, "grad_norm": 2.3197555541992188, "learning_rate": 2.53686685189143e-05, "loss": 0.4872, "step": 2315 }, { "epoch": 1.4810106340449347, "grad_norm": 2.1848902702331543, "learning_rate": 2.53579824748878e-05, "loss": 0.4878, "step": 2316 }, { "epoch": 1.4816502758455266, "grad_norm": 2.4237613677978516, "learning_rate": 2.5347296430861296e-05, "loss": 0.5306, "step": 2317 }, { "epoch": 1.4822899176461182, "grad_norm": 2.2572357654571533, "learning_rate": 2.53366103868348e-05, "loss": 0.468, "step": 2318 }, { "epoch": 1.4829295594467098, "grad_norm": 2.74531888961792, "learning_rate": 2.5325924342808294e-05, "loss": 0.6163, "step": 2319 }, { "epoch": 1.4835692012473016, "grad_norm": 2.414482355117798, "learning_rate": 2.531523829878179e-05, "loss": 0.4906, "step": 2320 }, { "epoch": 1.4842088430478932, "grad_norm": 2.572911500930786, "learning_rate": 2.5304552254755293e-05, "loss": 0.5517, "step": 2321 }, { "epoch": 1.4848484848484849, "grad_norm": 2.223451614379883, "learning_rate": 2.529386621072879e-05, "loss": 0.483, "step": 2322 }, { "epoch": 1.4854881266490765, "grad_norm": 2.360363245010376, "learning_rate": 2.5283180166702285e-05, "loss": 0.5478, "step": 2323 }, { "epoch": 1.486127768449668, "grad_norm": 2.163233995437622, "learning_rate": 2.5272494122675788e-05, "loss": 0.4739, "step": 2324 }, { "epoch": 1.48676741025026, "grad_norm": 2.0591564178466797, "learning_rate": 2.5261808078649284e-05, "loss": 0.4739, "step": 2325 }, { "epoch": 1.4874070520508516, "grad_norm": 2.2115094661712646, "learning_rate": 2.5251122034622783e-05, "loss": 0.4749, "step": 2326 }, { "epoch": 1.4880466938514432, "grad_norm": 2.305901288986206, "learning_rate": 2.5240435990596282e-05, "loss": 0.5349, "step": 2327 }, { "epoch": 1.4886863356520348, "grad_norm": 2.492730140686035, "learning_rate": 2.5229749946569782e-05, "loss": 0.5528, "step": 2328 }, { "epoch": 1.4893259774526264, "grad_norm": 2.506945848464966, "learning_rate": 2.5219063902543278e-05, "loss": 0.594, "step": 2329 }, { "epoch": 1.4899656192532182, "grad_norm": 2.1096086502075195, "learning_rate": 2.520837785851678e-05, "loss": 0.4492, "step": 2330 }, { "epoch": 1.4906052610538099, "grad_norm": 2.1972506046295166, "learning_rate": 2.5197691814490277e-05, "loss": 0.5063, "step": 2331 }, { "epoch": 1.4912449028544015, "grad_norm": 2.3153460025787354, "learning_rate": 2.5187005770463773e-05, "loss": 0.5166, "step": 2332 }, { "epoch": 1.4918845446549933, "grad_norm": 2.286513566970825, "learning_rate": 2.5176319726437275e-05, "loss": 0.5647, "step": 2333 }, { "epoch": 1.492524186455585, "grad_norm": 2.254351854324341, "learning_rate": 2.516563368241077e-05, "loss": 0.5644, "step": 2334 }, { "epoch": 1.4931638282561766, "grad_norm": 2.4628243446350098, "learning_rate": 2.5154947638384267e-05, "loss": 0.566, "step": 2335 }, { "epoch": 1.4938034700567682, "grad_norm": 2.4899988174438477, "learning_rate": 2.514426159435777e-05, "loss": 0.5532, "step": 2336 }, { "epoch": 1.4944431118573598, "grad_norm": 2.2579925060272217, "learning_rate": 2.5133575550331266e-05, "loss": 0.4957, "step": 2337 }, { "epoch": 1.4950827536579516, "grad_norm": 2.414663314819336, "learning_rate": 2.512288950630477e-05, "loss": 0.5331, "step": 2338 }, { "epoch": 1.4957223954585432, "grad_norm": 2.4178664684295654, "learning_rate": 2.5112203462278268e-05, "loss": 0.5849, "step": 2339 }, { "epoch": 1.4963620372591349, "grad_norm": 2.6198863983154297, "learning_rate": 2.5101517418251764e-05, "loss": 0.5785, "step": 2340 }, { "epoch": 1.4970016790597265, "grad_norm": 2.1563780307769775, "learning_rate": 2.5090831374225267e-05, "loss": 0.4707, "step": 2341 }, { "epoch": 1.497641320860318, "grad_norm": 2.6375300884246826, "learning_rate": 2.5080145330198763e-05, "loss": 0.6339, "step": 2342 }, { "epoch": 1.49828096266091, "grad_norm": 2.2239177227020264, "learning_rate": 2.506945928617226e-05, "loss": 0.5054, "step": 2343 }, { "epoch": 1.4989206044615015, "grad_norm": 2.573611259460449, "learning_rate": 2.505877324214576e-05, "loss": 0.5459, "step": 2344 }, { "epoch": 1.4995602462620932, "grad_norm": 2.5579721927642822, "learning_rate": 2.5048087198119257e-05, "loss": 0.6102, "step": 2345 }, { "epoch": 1.500199888062685, "grad_norm": 2.1255881786346436, "learning_rate": 2.5037401154092753e-05, "loss": 0.4868, "step": 2346 }, { "epoch": 1.5008395298632764, "grad_norm": 1.931162714958191, "learning_rate": 2.5026715110066256e-05, "loss": 0.4776, "step": 2347 }, { "epoch": 1.5014791716638682, "grad_norm": 2.4322550296783447, "learning_rate": 2.5016029066039752e-05, "loss": 0.5074, "step": 2348 }, { "epoch": 1.5021188134644599, "grad_norm": 2.068201780319214, "learning_rate": 2.500534302201325e-05, "loss": 0.4391, "step": 2349 }, { "epoch": 1.5027584552650515, "grad_norm": 2.310361862182617, "learning_rate": 2.499465697798675e-05, "loss": 0.5295, "step": 2350 }, { "epoch": 1.5033980970656433, "grad_norm": 2.4590678215026855, "learning_rate": 2.498397093396025e-05, "loss": 0.5207, "step": 2351 }, { "epoch": 1.504037738866235, "grad_norm": 1.9980255365371704, "learning_rate": 2.497328488993375e-05, "loss": 0.4232, "step": 2352 }, { "epoch": 1.5046773806668265, "grad_norm": 2.018057107925415, "learning_rate": 2.4962598845907246e-05, "loss": 0.4972, "step": 2353 }, { "epoch": 1.5053170224674184, "grad_norm": 2.4456212520599365, "learning_rate": 2.4951912801880745e-05, "loss": 0.5755, "step": 2354 }, { "epoch": 1.5059566642680098, "grad_norm": 2.4807541370391846, "learning_rate": 2.4941226757854244e-05, "loss": 0.5315, "step": 2355 }, { "epoch": 1.5065963060686016, "grad_norm": 2.744309425354004, "learning_rate": 2.493054071382774e-05, "loss": 0.586, "step": 2356 }, { "epoch": 1.5072359478691932, "grad_norm": 2.254199981689453, "learning_rate": 2.491985466980124e-05, "loss": 0.4765, "step": 2357 }, { "epoch": 1.5078755896697849, "grad_norm": 2.388324022293091, "learning_rate": 2.490916862577474e-05, "loss": 0.522, "step": 2358 }, { "epoch": 1.5085152314703767, "grad_norm": 2.601102113723755, "learning_rate": 2.489848258174824e-05, "loss": 0.5713, "step": 2359 }, { "epoch": 1.5091548732709683, "grad_norm": 2.91523814201355, "learning_rate": 2.4887796537721734e-05, "loss": 0.6079, "step": 2360 }, { "epoch": 1.50979451507156, "grad_norm": 2.6223254203796387, "learning_rate": 2.4877110493695234e-05, "loss": 0.5552, "step": 2361 }, { "epoch": 1.5104341568721515, "grad_norm": 2.5035362243652344, "learning_rate": 2.4866424449668736e-05, "loss": 0.5441, "step": 2362 }, { "epoch": 1.5110737986727432, "grad_norm": 2.1271495819091797, "learning_rate": 2.4855738405642232e-05, "loss": 0.4628, "step": 2363 }, { "epoch": 1.511713440473335, "grad_norm": 2.455970287322998, "learning_rate": 2.4845052361615732e-05, "loss": 0.5418, "step": 2364 }, { "epoch": 1.5123530822739266, "grad_norm": 2.3929998874664307, "learning_rate": 2.483436631758923e-05, "loss": 0.5146, "step": 2365 }, { "epoch": 1.5129927240745182, "grad_norm": 2.2422893047332764, "learning_rate": 2.4823680273562727e-05, "loss": 0.4333, "step": 2366 }, { "epoch": 1.51363236587511, "grad_norm": 2.44172739982605, "learning_rate": 2.4812994229536226e-05, "loss": 0.5739, "step": 2367 }, { "epoch": 1.5142720076757015, "grad_norm": 2.661695718765259, "learning_rate": 2.4802308185509726e-05, "loss": 0.5704, "step": 2368 }, { "epoch": 1.5149116494762933, "grad_norm": 2.466061592102051, "learning_rate": 2.4791622141483222e-05, "loss": 0.5118, "step": 2369 }, { "epoch": 1.515551291276885, "grad_norm": 2.4462573528289795, "learning_rate": 2.478093609745672e-05, "loss": 0.521, "step": 2370 }, { "epoch": 1.5161909330774765, "grad_norm": 2.2767608165740967, "learning_rate": 2.477025005343022e-05, "loss": 0.4889, "step": 2371 }, { "epoch": 1.5168305748780684, "grad_norm": 2.4078407287597656, "learning_rate": 2.475956400940372e-05, "loss": 0.5219, "step": 2372 }, { "epoch": 1.51747021667866, "grad_norm": 2.4542019367218018, "learning_rate": 2.474887796537722e-05, "loss": 0.549, "step": 2373 }, { "epoch": 1.5181098584792516, "grad_norm": 1.9831424951553345, "learning_rate": 2.473819192135072e-05, "loss": 0.4752, "step": 2374 }, { "epoch": 1.5187495002798432, "grad_norm": 2.366851568222046, "learning_rate": 2.4727505877324218e-05, "loss": 0.528, "step": 2375 }, { "epoch": 1.5193891420804349, "grad_norm": 2.438781261444092, "learning_rate": 2.4716819833297714e-05, "loss": 0.5119, "step": 2376 }, { "epoch": 1.5200287838810267, "grad_norm": 2.2130415439605713, "learning_rate": 2.4706133789271213e-05, "loss": 0.4586, "step": 2377 }, { "epoch": 1.5206684256816183, "grad_norm": 2.1566548347473145, "learning_rate": 2.4695447745244713e-05, "loss": 0.4803, "step": 2378 }, { "epoch": 1.52130806748221, "grad_norm": 2.7691001892089844, "learning_rate": 2.468476170121821e-05, "loss": 0.5838, "step": 2379 }, { "epoch": 1.5219477092828018, "grad_norm": 2.4336585998535156, "learning_rate": 2.4674075657191708e-05, "loss": 0.5288, "step": 2380 }, { "epoch": 1.5225873510833932, "grad_norm": 2.7915258407592773, "learning_rate": 2.4663389613165207e-05, "loss": 0.6181, "step": 2381 }, { "epoch": 1.523226992883985, "grad_norm": 2.3237874507904053, "learning_rate": 2.4652703569138703e-05, "loss": 0.5097, "step": 2382 }, { "epoch": 1.5238666346845766, "grad_norm": 2.3393502235412598, "learning_rate": 2.4642017525112203e-05, "loss": 0.4951, "step": 2383 }, { "epoch": 1.5245062764851682, "grad_norm": 1.9856390953063965, "learning_rate": 2.4631331481085702e-05, "loss": 0.4398, "step": 2384 }, { "epoch": 1.52514591828576, "grad_norm": 2.613715410232544, "learning_rate": 2.4620645437059205e-05, "loss": 0.5613, "step": 2385 }, { "epoch": 1.5257855600863517, "grad_norm": 2.336085796356201, "learning_rate": 2.46099593930327e-05, "loss": 0.5135, "step": 2386 }, { "epoch": 1.5264252018869433, "grad_norm": 2.4587197303771973, "learning_rate": 2.45992733490062e-05, "loss": 0.534, "step": 2387 }, { "epoch": 1.5270648436875351, "grad_norm": 2.4791629314422607, "learning_rate": 2.45885873049797e-05, "loss": 0.5948, "step": 2388 }, { "epoch": 1.5277044854881265, "grad_norm": 2.2141366004943848, "learning_rate": 2.4577901260953196e-05, "loss": 0.4922, "step": 2389 }, { "epoch": 1.5283441272887184, "grad_norm": 2.0014305114746094, "learning_rate": 2.4567215216926695e-05, "loss": 0.4436, "step": 2390 }, { "epoch": 1.52898376908931, "grad_norm": 2.351747751235962, "learning_rate": 2.4556529172900194e-05, "loss": 0.5386, "step": 2391 }, { "epoch": 1.5296234108899016, "grad_norm": 2.6862196922302246, "learning_rate": 2.454584312887369e-05, "loss": 0.5773, "step": 2392 }, { "epoch": 1.5302630526904935, "grad_norm": 2.5580666065216064, "learning_rate": 2.453515708484719e-05, "loss": 0.5424, "step": 2393 }, { "epoch": 1.5309026944910848, "grad_norm": 2.2380003929138184, "learning_rate": 2.452447104082069e-05, "loss": 0.47, "step": 2394 }, { "epoch": 1.5315423362916767, "grad_norm": 2.3826396465301514, "learning_rate": 2.4513784996794188e-05, "loss": 0.464, "step": 2395 }, { "epoch": 1.5321819780922683, "grad_norm": 2.5672996044158936, "learning_rate": 2.4503098952767688e-05, "loss": 0.6625, "step": 2396 }, { "epoch": 1.53282161989286, "grad_norm": 2.3602516651153564, "learning_rate": 2.4492412908741187e-05, "loss": 0.5199, "step": 2397 }, { "epoch": 1.5334612616934518, "grad_norm": 2.279737949371338, "learning_rate": 2.4481726864714683e-05, "loss": 0.526, "step": 2398 }, { "epoch": 1.5341009034940434, "grad_norm": 2.4020626544952393, "learning_rate": 2.4471040820688182e-05, "loss": 0.5661, "step": 2399 }, { "epoch": 1.534740545294635, "grad_norm": 2.4102251529693604, "learning_rate": 2.4460354776661682e-05, "loss": 0.4876, "step": 2400 }, { "epoch": 1.5353801870952268, "grad_norm": 2.311112403869629, "learning_rate": 2.444966873263518e-05, "loss": 0.5119, "step": 2401 }, { "epoch": 1.5360198288958182, "grad_norm": 2.345923662185669, "learning_rate": 2.4438982688608677e-05, "loss": 0.5181, "step": 2402 }, { "epoch": 1.53665947069641, "grad_norm": 2.7882421016693115, "learning_rate": 2.4428296644582176e-05, "loss": 0.5897, "step": 2403 }, { "epoch": 1.5372991124970017, "grad_norm": 2.60638427734375, "learning_rate": 2.4417610600555676e-05, "loss": 0.535, "step": 2404 }, { "epoch": 1.5379387542975933, "grad_norm": 2.110541582107544, "learning_rate": 2.4406924556529172e-05, "loss": 0.4471, "step": 2405 }, { "epoch": 1.5385783960981851, "grad_norm": 2.3438408374786377, "learning_rate": 2.439623851250267e-05, "loss": 0.5193, "step": 2406 }, { "epoch": 1.5392180378987765, "grad_norm": 2.492509126663208, "learning_rate": 2.438555246847617e-05, "loss": 0.5633, "step": 2407 }, { "epoch": 1.5398576796993684, "grad_norm": 2.2724616527557373, "learning_rate": 2.437486642444967e-05, "loss": 0.486, "step": 2408 }, { "epoch": 1.54049732149996, "grad_norm": 2.726543426513672, "learning_rate": 2.436418038042317e-05, "loss": 0.6241, "step": 2409 }, { "epoch": 1.5411369633005516, "grad_norm": 2.4403836727142334, "learning_rate": 2.435349433639667e-05, "loss": 0.5459, "step": 2410 }, { "epoch": 1.5417766051011434, "grad_norm": 2.583202362060547, "learning_rate": 2.4342808292370165e-05, "loss": 0.5753, "step": 2411 }, { "epoch": 1.542416246901735, "grad_norm": 2.208462715148926, "learning_rate": 2.4332122248343664e-05, "loss": 0.4685, "step": 2412 }, { "epoch": 1.5430558887023267, "grad_norm": 2.230743169784546, "learning_rate": 2.4321436204317163e-05, "loss": 0.5163, "step": 2413 }, { "epoch": 1.5436955305029185, "grad_norm": 2.3793694972991943, "learning_rate": 2.4310750160290663e-05, "loss": 0.4592, "step": 2414 }, { "epoch": 1.54433517230351, "grad_norm": 2.219308376312256, "learning_rate": 2.430006411626416e-05, "loss": 0.5265, "step": 2415 }, { "epoch": 1.5449748141041018, "grad_norm": 2.5354859828948975, "learning_rate": 2.4289378072237658e-05, "loss": 0.4937, "step": 2416 }, { "epoch": 1.5456144559046934, "grad_norm": 2.6889488697052, "learning_rate": 2.4278692028211157e-05, "loss": 0.5672, "step": 2417 }, { "epoch": 1.546254097705285, "grad_norm": 2.38702130317688, "learning_rate": 2.4268005984184657e-05, "loss": 0.5382, "step": 2418 }, { "epoch": 1.5468937395058768, "grad_norm": 2.2605645656585693, "learning_rate": 2.4257319940158156e-05, "loss": 0.5044, "step": 2419 }, { "epoch": 1.5475333813064682, "grad_norm": 2.3581440448760986, "learning_rate": 2.4246633896131655e-05, "loss": 0.5478, "step": 2420 }, { "epoch": 1.54817302310706, "grad_norm": 2.385565996170044, "learning_rate": 2.423594785210515e-05, "loss": 0.5248, "step": 2421 }, { "epoch": 1.5488126649076517, "grad_norm": 2.7944037914276123, "learning_rate": 2.422526180807865e-05, "loss": 0.5119, "step": 2422 }, { "epoch": 1.5494523067082433, "grad_norm": 2.3456242084503174, "learning_rate": 2.421457576405215e-05, "loss": 0.5525, "step": 2423 }, { "epoch": 1.5500919485088351, "grad_norm": 2.555832624435425, "learning_rate": 2.4203889720025646e-05, "loss": 0.5438, "step": 2424 }, { "epoch": 1.5507315903094268, "grad_norm": 2.172679901123047, "learning_rate": 2.4193203675999145e-05, "loss": 0.5005, "step": 2425 }, { "epoch": 1.5513712321100184, "grad_norm": 2.465785264968872, "learning_rate": 2.4182517631972645e-05, "loss": 0.5269, "step": 2426 }, { "epoch": 1.5520108739106102, "grad_norm": 2.101972818374634, "learning_rate": 2.417183158794614e-05, "loss": 0.4562, "step": 2427 }, { "epoch": 1.5526505157112016, "grad_norm": 2.3771657943725586, "learning_rate": 2.416114554391964e-05, "loss": 0.5279, "step": 2428 }, { "epoch": 1.5532901575117934, "grad_norm": 2.1550076007843018, "learning_rate": 2.415045949989314e-05, "loss": 0.4694, "step": 2429 }, { "epoch": 1.553929799312385, "grad_norm": 2.417736053466797, "learning_rate": 2.413977345586664e-05, "loss": 0.5019, "step": 2430 }, { "epoch": 1.5545694411129767, "grad_norm": 2.389709234237671, "learning_rate": 2.4129087411840138e-05, "loss": 0.5168, "step": 2431 }, { "epoch": 1.5552090829135685, "grad_norm": 2.6814632415771484, "learning_rate": 2.4118401367813638e-05, "loss": 0.6498, "step": 2432 }, { "epoch": 1.55584872471416, "grad_norm": 2.4444580078125, "learning_rate": 2.4107715323787137e-05, "loss": 0.5677, "step": 2433 }, { "epoch": 1.5564883665147518, "grad_norm": 2.2038381099700928, "learning_rate": 2.4097029279760633e-05, "loss": 0.5135, "step": 2434 }, { "epoch": 1.5571280083153434, "grad_norm": 2.348320245742798, "learning_rate": 2.4086343235734132e-05, "loss": 0.5614, "step": 2435 }, { "epoch": 1.557767650115935, "grad_norm": 2.051631212234497, "learning_rate": 2.407565719170763e-05, "loss": 0.4845, "step": 2436 }, { "epoch": 1.5584072919165268, "grad_norm": 2.6718955039978027, "learning_rate": 2.4064971147681128e-05, "loss": 0.6259, "step": 2437 }, { "epoch": 1.5590469337171184, "grad_norm": 2.91152286529541, "learning_rate": 2.4054285103654627e-05, "loss": 0.6573, "step": 2438 }, { "epoch": 1.55968657551771, "grad_norm": 2.3460750579833984, "learning_rate": 2.4043599059628126e-05, "loss": 0.5212, "step": 2439 }, { "epoch": 1.560326217318302, "grad_norm": 2.128023862838745, "learning_rate": 2.4032913015601626e-05, "loss": 0.4552, "step": 2440 }, { "epoch": 1.5609658591188933, "grad_norm": 2.336611747741699, "learning_rate": 2.4022226971575125e-05, "loss": 0.5525, "step": 2441 }, { "epoch": 1.5616055009194851, "grad_norm": 2.3026328086853027, "learning_rate": 2.4011540927548624e-05, "loss": 0.5435, "step": 2442 }, { "epoch": 1.5622451427200768, "grad_norm": 2.2032392024993896, "learning_rate": 2.4000854883522124e-05, "loss": 0.4847, "step": 2443 }, { "epoch": 1.5628847845206684, "grad_norm": 2.166548490524292, "learning_rate": 2.399016883949562e-05, "loss": 0.4893, "step": 2444 }, { "epoch": 1.5635244263212602, "grad_norm": 2.324126720428467, "learning_rate": 2.397948279546912e-05, "loss": 0.4876, "step": 2445 }, { "epoch": 1.5641640681218516, "grad_norm": 2.2490391731262207, "learning_rate": 2.396879675144262e-05, "loss": 0.5261, "step": 2446 }, { "epoch": 1.5648037099224434, "grad_norm": 2.0372722148895264, "learning_rate": 2.3958110707416114e-05, "loss": 0.4597, "step": 2447 }, { "epoch": 1.565443351723035, "grad_norm": 2.200812578201294, "learning_rate": 2.3947424663389614e-05, "loss": 0.4848, "step": 2448 }, { "epoch": 1.5660829935236267, "grad_norm": 2.1502532958984375, "learning_rate": 2.3936738619363113e-05, "loss": 0.4964, "step": 2449 }, { "epoch": 1.5667226353242185, "grad_norm": 2.05069899559021, "learning_rate": 2.392605257533661e-05, "loss": 0.4847, "step": 2450 }, { "epoch": 1.5673622771248101, "grad_norm": 2.511824131011963, "learning_rate": 2.391536653131011e-05, "loss": 0.5475, "step": 2451 }, { "epoch": 1.5680019189254017, "grad_norm": 2.2022783756256104, "learning_rate": 2.3904680487283608e-05, "loss": 0.5098, "step": 2452 }, { "epoch": 1.5686415607259936, "grad_norm": 2.268644332885742, "learning_rate": 2.3893994443257107e-05, "loss": 0.4785, "step": 2453 }, { "epoch": 1.569281202526585, "grad_norm": 2.7114834785461426, "learning_rate": 2.3883308399230607e-05, "loss": 0.5204, "step": 2454 }, { "epoch": 1.5699208443271768, "grad_norm": 2.5339622497558594, "learning_rate": 2.3872622355204106e-05, "loss": 0.5187, "step": 2455 }, { "epoch": 1.5705604861277684, "grad_norm": 2.329665422439575, "learning_rate": 2.3861936311177605e-05, "loss": 0.4988, "step": 2456 }, { "epoch": 1.57120012792836, "grad_norm": 2.543318033218384, "learning_rate": 2.38512502671511e-05, "loss": 0.524, "step": 2457 }, { "epoch": 1.571839769728952, "grad_norm": 2.1351418495178223, "learning_rate": 2.38405642231246e-05, "loss": 0.4507, "step": 2458 }, { "epoch": 1.5724794115295433, "grad_norm": 2.34116792678833, "learning_rate": 2.38298781790981e-05, "loss": 0.4895, "step": 2459 }, { "epoch": 1.5731190533301351, "grad_norm": 2.2495195865631104, "learning_rate": 2.3819192135071596e-05, "loss": 0.4784, "step": 2460 }, { "epoch": 1.5737586951307267, "grad_norm": 2.2945520877838135, "learning_rate": 2.3808506091045095e-05, "loss": 0.4666, "step": 2461 }, { "epoch": 1.5743983369313184, "grad_norm": 2.7183754444122314, "learning_rate": 2.3797820047018595e-05, "loss": 0.6223, "step": 2462 }, { "epoch": 1.5750379787319102, "grad_norm": 2.485534191131592, "learning_rate": 2.3787134002992094e-05, "loss": 0.5399, "step": 2463 }, { "epoch": 1.5756776205325018, "grad_norm": 2.1604371070861816, "learning_rate": 2.3776447958965593e-05, "loss": 0.4515, "step": 2464 }, { "epoch": 1.5763172623330934, "grad_norm": 2.5859181880950928, "learning_rate": 2.3765761914939093e-05, "loss": 0.5557, "step": 2465 }, { "epoch": 1.5769569041336853, "grad_norm": 2.3516976833343506, "learning_rate": 2.375507587091259e-05, "loss": 0.5024, "step": 2466 }, { "epoch": 1.5775965459342767, "grad_norm": 2.5704262256622314, "learning_rate": 2.3744389826886088e-05, "loss": 0.5738, "step": 2467 }, { "epoch": 1.5782361877348685, "grad_norm": 2.746694564819336, "learning_rate": 2.3733703782859587e-05, "loss": 0.569, "step": 2468 }, { "epoch": 1.5788758295354601, "grad_norm": 2.1925268173217773, "learning_rate": 2.3723017738833083e-05, "loss": 0.5233, "step": 2469 }, { "epoch": 1.5795154713360517, "grad_norm": 2.1631176471710205, "learning_rate": 2.3712331694806583e-05, "loss": 0.4705, "step": 2470 }, { "epoch": 1.5801551131366436, "grad_norm": 2.339540958404541, "learning_rate": 2.3701645650780082e-05, "loss": 0.4981, "step": 2471 }, { "epoch": 1.5807947549372352, "grad_norm": 2.373715400695801, "learning_rate": 2.369095960675358e-05, "loss": 0.4896, "step": 2472 }, { "epoch": 1.5814343967378268, "grad_norm": 2.7771546840667725, "learning_rate": 2.3680273562727078e-05, "loss": 0.5849, "step": 2473 }, { "epoch": 1.5820740385384184, "grad_norm": 2.1099908351898193, "learning_rate": 2.3669587518700577e-05, "loss": 0.5005, "step": 2474 }, { "epoch": 1.58271368033901, "grad_norm": 2.2248928546905518, "learning_rate": 2.3658901474674076e-05, "loss": 0.4991, "step": 2475 }, { "epoch": 1.583353322139602, "grad_norm": 1.9041866064071655, "learning_rate": 2.3648215430647576e-05, "loss": 0.4407, "step": 2476 }, { "epoch": 1.5839929639401935, "grad_norm": 2.2991416454315186, "learning_rate": 2.3637529386621075e-05, "loss": 0.5053, "step": 2477 }, { "epoch": 1.5846326057407851, "grad_norm": 2.454655170440674, "learning_rate": 2.3626843342594574e-05, "loss": 0.5965, "step": 2478 }, { "epoch": 1.585272247541377, "grad_norm": 2.389505386352539, "learning_rate": 2.361615729856807e-05, "loss": 0.4951, "step": 2479 }, { "epoch": 1.5859118893419684, "grad_norm": 2.505373239517212, "learning_rate": 2.360547125454157e-05, "loss": 0.5485, "step": 2480 }, { "epoch": 1.5865515311425602, "grad_norm": 2.362473726272583, "learning_rate": 2.359478521051507e-05, "loss": 0.5577, "step": 2481 }, { "epoch": 1.5871911729431518, "grad_norm": 2.4360294342041016, "learning_rate": 2.3584099166488565e-05, "loss": 0.5513, "step": 2482 }, { "epoch": 1.5878308147437434, "grad_norm": 2.365406036376953, "learning_rate": 2.3573413122462064e-05, "loss": 0.5373, "step": 2483 }, { "epoch": 1.5884704565443353, "grad_norm": 2.66648530960083, "learning_rate": 2.3562727078435564e-05, "loss": 0.5579, "step": 2484 }, { "epoch": 1.589110098344927, "grad_norm": 2.3460564613342285, "learning_rate": 2.3552041034409063e-05, "loss": 0.5011, "step": 2485 }, { "epoch": 1.5897497401455185, "grad_norm": 2.4095308780670166, "learning_rate": 2.3541354990382562e-05, "loss": 0.4704, "step": 2486 }, { "epoch": 1.5903893819461101, "grad_norm": 2.5295562744140625, "learning_rate": 2.3530668946356062e-05, "loss": 0.5096, "step": 2487 }, { "epoch": 1.5910290237467017, "grad_norm": 2.5730931758880615, "learning_rate": 2.351998290232956e-05, "loss": 0.6036, "step": 2488 }, { "epoch": 1.5916686655472936, "grad_norm": 2.3112635612487793, "learning_rate": 2.3509296858303057e-05, "loss": 0.5241, "step": 2489 }, { "epoch": 1.5923083073478852, "grad_norm": 2.616288661956787, "learning_rate": 2.3498610814276557e-05, "loss": 0.576, "step": 2490 }, { "epoch": 1.5929479491484768, "grad_norm": 2.232785701751709, "learning_rate": 2.3487924770250056e-05, "loss": 0.4771, "step": 2491 }, { "epoch": 1.5935875909490687, "grad_norm": 2.0340754985809326, "learning_rate": 2.3477238726223552e-05, "loss": 0.4216, "step": 2492 }, { "epoch": 1.59422723274966, "grad_norm": 2.366130828857422, "learning_rate": 2.346655268219705e-05, "loss": 0.5477, "step": 2493 }, { "epoch": 1.594866874550252, "grad_norm": 2.0449624061584473, "learning_rate": 2.345586663817055e-05, "loss": 0.4029, "step": 2494 }, { "epoch": 1.5955065163508435, "grad_norm": 2.3952925205230713, "learning_rate": 2.3445180594144047e-05, "loss": 0.529, "step": 2495 }, { "epoch": 1.5961461581514351, "grad_norm": 2.255967140197754, "learning_rate": 2.3434494550117546e-05, "loss": 0.4837, "step": 2496 }, { "epoch": 1.596785799952027, "grad_norm": 2.468334913253784, "learning_rate": 2.3423808506091045e-05, "loss": 0.5097, "step": 2497 }, { "epoch": 1.5974254417526186, "grad_norm": 2.680081605911255, "learning_rate": 2.3413122462064545e-05, "loss": 0.5233, "step": 2498 }, { "epoch": 1.5980650835532102, "grad_norm": 2.3744771480560303, "learning_rate": 2.3402436418038044e-05, "loss": 0.4636, "step": 2499 }, { "epoch": 1.598704725353802, "grad_norm": 2.4233438968658447, "learning_rate": 2.3391750374011543e-05, "loss": 0.5244, "step": 2500 }, { "epoch": 1.5993443671543934, "grad_norm": 2.5019216537475586, "learning_rate": 2.3381064329985043e-05, "loss": 0.5743, "step": 2501 }, { "epoch": 1.5999840089549853, "grad_norm": 2.3580856323242188, "learning_rate": 2.337037828595854e-05, "loss": 0.4786, "step": 2502 }, { "epoch": 1.6006236507555769, "grad_norm": 2.263636350631714, "learning_rate": 2.3359692241932038e-05, "loss": 0.483, "step": 2503 }, { "epoch": 1.6012632925561685, "grad_norm": 2.3565735816955566, "learning_rate": 2.3349006197905537e-05, "loss": 0.5169, "step": 2504 }, { "epoch": 1.6019029343567603, "grad_norm": 2.528686761856079, "learning_rate": 2.3338320153879033e-05, "loss": 0.5606, "step": 2505 }, { "epoch": 1.6025425761573517, "grad_norm": 2.5530025959014893, "learning_rate": 2.3327634109852533e-05, "loss": 0.5467, "step": 2506 }, { "epoch": 1.6031822179579436, "grad_norm": 2.213629722595215, "learning_rate": 2.3316948065826032e-05, "loss": 0.4782, "step": 2507 }, { "epoch": 1.6038218597585352, "grad_norm": 2.1079697608947754, "learning_rate": 2.3306262021799528e-05, "loss": 0.4336, "step": 2508 }, { "epoch": 1.6044615015591268, "grad_norm": 2.2900006771087646, "learning_rate": 2.329557597777303e-05, "loss": 0.5071, "step": 2509 }, { "epoch": 1.6051011433597187, "grad_norm": 2.401519298553467, "learning_rate": 2.328488993374653e-05, "loss": 0.5066, "step": 2510 }, { "epoch": 1.6057407851603103, "grad_norm": 2.4686508178710938, "learning_rate": 2.3274203889720026e-05, "loss": 0.5248, "step": 2511 }, { "epoch": 1.6063804269609019, "grad_norm": 2.6671738624572754, "learning_rate": 2.3263517845693526e-05, "loss": 0.6211, "step": 2512 }, { "epoch": 1.6070200687614937, "grad_norm": 2.3263304233551025, "learning_rate": 2.3252831801667025e-05, "loss": 0.5074, "step": 2513 }, { "epoch": 1.6076597105620851, "grad_norm": 2.212210178375244, "learning_rate": 2.3242145757640524e-05, "loss": 0.4756, "step": 2514 }, { "epoch": 1.608299352362677, "grad_norm": 2.4901797771453857, "learning_rate": 2.323145971361402e-05, "loss": 0.5385, "step": 2515 }, { "epoch": 1.6089389941632686, "grad_norm": 2.246525287628174, "learning_rate": 2.322077366958752e-05, "loss": 0.5141, "step": 2516 }, { "epoch": 1.6095786359638602, "grad_norm": 2.166330575942993, "learning_rate": 2.321008762556102e-05, "loss": 0.5059, "step": 2517 }, { "epoch": 1.610218277764452, "grad_norm": 2.4365246295928955, "learning_rate": 2.3199401581534515e-05, "loss": 0.5342, "step": 2518 }, { "epoch": 1.6108579195650434, "grad_norm": 2.8213133811950684, "learning_rate": 2.3188715537508014e-05, "loss": 0.5542, "step": 2519 }, { "epoch": 1.6114975613656353, "grad_norm": 2.5161750316619873, "learning_rate": 2.3178029493481514e-05, "loss": 0.5332, "step": 2520 }, { "epoch": 1.6121372031662269, "grad_norm": 2.147672176361084, "learning_rate": 2.3167343449455013e-05, "loss": 0.4664, "step": 2521 }, { "epoch": 1.6127768449668185, "grad_norm": 2.2341268062591553, "learning_rate": 2.3156657405428512e-05, "loss": 0.4846, "step": 2522 }, { "epoch": 1.6134164867674103, "grad_norm": 2.222297430038452, "learning_rate": 2.3145971361402012e-05, "loss": 0.4714, "step": 2523 }, { "epoch": 1.614056128568002, "grad_norm": 2.679208517074585, "learning_rate": 2.3135285317375508e-05, "loss": 0.5589, "step": 2524 }, { "epoch": 1.6146957703685936, "grad_norm": 2.6643195152282715, "learning_rate": 2.3124599273349007e-05, "loss": 0.6067, "step": 2525 }, { "epoch": 1.6153354121691854, "grad_norm": 2.6646013259887695, "learning_rate": 2.3113913229322506e-05, "loss": 0.5803, "step": 2526 }, { "epoch": 1.6159750539697768, "grad_norm": 1.8550915718078613, "learning_rate": 2.3103227185296006e-05, "loss": 0.4113, "step": 2527 }, { "epoch": 1.6166146957703686, "grad_norm": 2.5979645252227783, "learning_rate": 2.3092541141269502e-05, "loss": 0.5713, "step": 2528 }, { "epoch": 1.6172543375709603, "grad_norm": 2.0909793376922607, "learning_rate": 2.3081855097243e-05, "loss": 0.4413, "step": 2529 }, { "epoch": 1.6178939793715519, "grad_norm": 2.5317177772521973, "learning_rate": 2.30711690532165e-05, "loss": 0.6021, "step": 2530 }, { "epoch": 1.6185336211721437, "grad_norm": 2.742863416671753, "learning_rate": 2.3060483009189996e-05, "loss": 0.6303, "step": 2531 }, { "epoch": 1.6191732629727351, "grad_norm": 2.336408853530884, "learning_rate": 2.30497969651635e-05, "loss": 0.5161, "step": 2532 }, { "epoch": 1.619812904773327, "grad_norm": 2.3802170753479004, "learning_rate": 2.3039110921137e-05, "loss": 0.5682, "step": 2533 }, { "epoch": 1.6204525465739186, "grad_norm": 2.4165353775024414, "learning_rate": 2.3028424877110495e-05, "loss": 0.4955, "step": 2534 }, { "epoch": 1.6210921883745102, "grad_norm": 2.000215768814087, "learning_rate": 2.3017738833083994e-05, "loss": 0.4386, "step": 2535 }, { "epoch": 1.621731830175102, "grad_norm": 2.3797097206115723, "learning_rate": 2.3007052789057493e-05, "loss": 0.5436, "step": 2536 }, { "epoch": 1.6223714719756936, "grad_norm": 2.0173850059509277, "learning_rate": 2.299636674503099e-05, "loss": 0.4529, "step": 2537 }, { "epoch": 1.6230111137762853, "grad_norm": 2.5582783222198486, "learning_rate": 2.298568070100449e-05, "loss": 0.5541, "step": 2538 }, { "epoch": 1.623650755576877, "grad_norm": 2.180779457092285, "learning_rate": 2.2974994656977988e-05, "loss": 0.4889, "step": 2539 }, { "epoch": 1.6242903973774685, "grad_norm": 2.3111088275909424, "learning_rate": 2.2964308612951487e-05, "loss": 0.5305, "step": 2540 }, { "epoch": 1.6249300391780603, "grad_norm": 2.559722661972046, "learning_rate": 2.2953622568924983e-05, "loss": 0.5528, "step": 2541 }, { "epoch": 1.625569680978652, "grad_norm": 2.272745370864868, "learning_rate": 2.2942936524898483e-05, "loss": 0.5074, "step": 2542 }, { "epoch": 1.6262093227792436, "grad_norm": 2.2575020790100098, "learning_rate": 2.2932250480871982e-05, "loss": 0.5299, "step": 2543 }, { "epoch": 1.6268489645798354, "grad_norm": 2.011913537979126, "learning_rate": 2.292156443684548e-05, "loss": 0.4872, "step": 2544 }, { "epoch": 1.6274886063804268, "grad_norm": 2.4279534816741943, "learning_rate": 2.291087839281898e-05, "loss": 0.5225, "step": 2545 }, { "epoch": 1.6281282481810186, "grad_norm": 2.4316117763519287, "learning_rate": 2.290019234879248e-05, "loss": 0.5218, "step": 2546 }, { "epoch": 1.6287678899816103, "grad_norm": 2.136850357055664, "learning_rate": 2.2889506304765976e-05, "loss": 0.464, "step": 2547 }, { "epoch": 1.6294075317822019, "grad_norm": 2.725249767303467, "learning_rate": 2.2878820260739475e-05, "loss": 0.5861, "step": 2548 }, { "epoch": 1.6300471735827937, "grad_norm": 2.4032304286956787, "learning_rate": 2.2868134216712975e-05, "loss": 0.5284, "step": 2549 }, { "epoch": 1.6306868153833853, "grad_norm": 2.399120807647705, "learning_rate": 2.285744817268647e-05, "loss": 0.5152, "step": 2550 }, { "epoch": 1.631326457183977, "grad_norm": 2.2249791622161865, "learning_rate": 2.284676212865997e-05, "loss": 0.4273, "step": 2551 }, { "epoch": 1.6319660989845688, "grad_norm": 2.3641135692596436, "learning_rate": 2.283607608463347e-05, "loss": 0.5114, "step": 2552 }, { "epoch": 1.6326057407851602, "grad_norm": 2.41913104057312, "learning_rate": 2.2825390040606965e-05, "loss": 0.5252, "step": 2553 }, { "epoch": 1.633245382585752, "grad_norm": 2.295541763305664, "learning_rate": 2.2814703996580465e-05, "loss": 0.4923, "step": 2554 }, { "epoch": 1.6338850243863436, "grad_norm": 2.612786293029785, "learning_rate": 2.2804017952553968e-05, "loss": 0.546, "step": 2555 }, { "epoch": 1.6345246661869353, "grad_norm": 2.3593502044677734, "learning_rate": 2.2793331908527467e-05, "loss": 0.5378, "step": 2556 }, { "epoch": 1.635164307987527, "grad_norm": 2.059650182723999, "learning_rate": 2.2782645864500963e-05, "loss": 0.4711, "step": 2557 }, { "epoch": 1.6358039497881185, "grad_norm": 2.145604133605957, "learning_rate": 2.2771959820474462e-05, "loss": 0.4969, "step": 2558 }, { "epoch": 1.6364435915887103, "grad_norm": 2.426478147506714, "learning_rate": 2.276127377644796e-05, "loss": 0.5175, "step": 2559 }, { "epoch": 1.637083233389302, "grad_norm": 2.0644280910491943, "learning_rate": 2.2750587732421458e-05, "loss": 0.4738, "step": 2560 }, { "epoch": 1.6377228751898936, "grad_norm": 2.0993101596832275, "learning_rate": 2.2739901688394957e-05, "loss": 0.4775, "step": 2561 }, { "epoch": 1.6383625169904854, "grad_norm": 2.2274608612060547, "learning_rate": 2.2729215644368456e-05, "loss": 0.513, "step": 2562 }, { "epoch": 1.639002158791077, "grad_norm": 2.3448235988616943, "learning_rate": 2.2718529600341952e-05, "loss": 0.5602, "step": 2563 }, { "epoch": 1.6396418005916686, "grad_norm": 2.2966411113739014, "learning_rate": 2.2707843556315452e-05, "loss": 0.4986, "step": 2564 }, { "epoch": 1.6402814423922605, "grad_norm": 2.4774394035339355, "learning_rate": 2.269715751228895e-05, "loss": 0.5447, "step": 2565 }, { "epoch": 1.6409210841928519, "grad_norm": 2.184979200363159, "learning_rate": 2.268647146826245e-05, "loss": 0.4976, "step": 2566 }, { "epoch": 1.6415607259934437, "grad_norm": 2.3675427436828613, "learning_rate": 2.267578542423595e-05, "loss": 0.4856, "step": 2567 }, { "epoch": 1.6422003677940353, "grad_norm": 1.8464293479919434, "learning_rate": 2.266509938020945e-05, "loss": 0.4123, "step": 2568 }, { "epoch": 1.642840009594627, "grad_norm": 2.4367034435272217, "learning_rate": 2.265441333618295e-05, "loss": 0.5033, "step": 2569 }, { "epoch": 1.6434796513952188, "grad_norm": 2.310029983520508, "learning_rate": 2.2643727292156444e-05, "loss": 0.4984, "step": 2570 }, { "epoch": 1.6441192931958102, "grad_norm": 2.379513740539551, "learning_rate": 2.2633041248129944e-05, "loss": 0.5556, "step": 2571 }, { "epoch": 1.644758934996402, "grad_norm": 2.559941291809082, "learning_rate": 2.2622355204103443e-05, "loss": 0.5274, "step": 2572 }, { "epoch": 1.6453985767969936, "grad_norm": 2.173079252243042, "learning_rate": 2.261166916007694e-05, "loss": 0.4719, "step": 2573 }, { "epoch": 1.6460382185975853, "grad_norm": 2.2452356815338135, "learning_rate": 2.260098311605044e-05, "loss": 0.5161, "step": 2574 }, { "epoch": 1.646677860398177, "grad_norm": 2.241701602935791, "learning_rate": 2.2590297072023938e-05, "loss": 0.5116, "step": 2575 }, { "epoch": 1.6473175021987687, "grad_norm": 2.3983466625213623, "learning_rate": 2.2579611027997434e-05, "loss": 0.5111, "step": 2576 }, { "epoch": 1.6479571439993603, "grad_norm": 1.8889271020889282, "learning_rate": 2.2568924983970933e-05, "loss": 0.4058, "step": 2577 }, { "epoch": 1.6485967857999522, "grad_norm": 2.5848183631896973, "learning_rate": 2.2558238939944436e-05, "loss": 0.5651, "step": 2578 }, { "epoch": 1.6492364276005436, "grad_norm": 2.315823554992676, "learning_rate": 2.2547552895917932e-05, "loss": 0.5282, "step": 2579 }, { "epoch": 1.6498760694011354, "grad_norm": 2.0703957080841064, "learning_rate": 2.253686685189143e-05, "loss": 0.4409, "step": 2580 }, { "epoch": 1.650515711201727, "grad_norm": 2.217512607574463, "learning_rate": 2.252618080786493e-05, "loss": 0.4882, "step": 2581 }, { "epoch": 1.6511553530023186, "grad_norm": 2.308084487915039, "learning_rate": 2.2515494763838427e-05, "loss": 0.483, "step": 2582 }, { "epoch": 1.6517949948029105, "grad_norm": 2.424596071243286, "learning_rate": 2.2504808719811926e-05, "loss": 0.5044, "step": 2583 }, { "epoch": 1.652434636603502, "grad_norm": 2.650787830352783, "learning_rate": 2.2494122675785425e-05, "loss": 0.5302, "step": 2584 }, { "epoch": 1.6530742784040937, "grad_norm": 2.6999995708465576, "learning_rate": 2.2483436631758925e-05, "loss": 0.5953, "step": 2585 }, { "epoch": 1.6537139202046853, "grad_norm": 2.433746337890625, "learning_rate": 2.247275058773242e-05, "loss": 0.5218, "step": 2586 }, { "epoch": 1.654353562005277, "grad_norm": 2.474039077758789, "learning_rate": 2.246206454370592e-05, "loss": 0.5407, "step": 2587 }, { "epoch": 1.6549932038058688, "grad_norm": 2.5290632247924805, "learning_rate": 2.245137849967942e-05, "loss": 0.5568, "step": 2588 }, { "epoch": 1.6556328456064604, "grad_norm": 2.3100783824920654, "learning_rate": 2.244069245565292e-05, "loss": 0.4886, "step": 2589 }, { "epoch": 1.656272487407052, "grad_norm": 2.191134452819824, "learning_rate": 2.2430006411626418e-05, "loss": 0.4679, "step": 2590 }, { "epoch": 1.6569121292076439, "grad_norm": 2.317922592163086, "learning_rate": 2.2419320367599918e-05, "loss": 0.5093, "step": 2591 }, { "epoch": 1.6575517710082353, "grad_norm": 2.3259685039520264, "learning_rate": 2.2408634323573414e-05, "loss": 0.4974, "step": 2592 }, { "epoch": 1.658191412808827, "grad_norm": 2.282165765762329, "learning_rate": 2.2397948279546913e-05, "loss": 0.5191, "step": 2593 }, { "epoch": 1.6588310546094187, "grad_norm": 2.230090379714966, "learning_rate": 2.2387262235520412e-05, "loss": 0.4937, "step": 2594 }, { "epoch": 1.6594706964100103, "grad_norm": 2.2409491539001465, "learning_rate": 2.2376576191493908e-05, "loss": 0.5004, "step": 2595 }, { "epoch": 1.6601103382106022, "grad_norm": 2.1581904888153076, "learning_rate": 2.2365890147467408e-05, "loss": 0.4849, "step": 2596 }, { "epoch": 1.6607499800111938, "grad_norm": 2.3513121604919434, "learning_rate": 2.2355204103440907e-05, "loss": 0.5291, "step": 2597 }, { "epoch": 1.6613896218117854, "grad_norm": 2.3284194469451904, "learning_rate": 2.2344518059414406e-05, "loss": 0.506, "step": 2598 }, { "epoch": 1.662029263612377, "grad_norm": 2.3850560188293457, "learning_rate": 2.2333832015387902e-05, "loss": 0.5509, "step": 2599 }, { "epoch": 1.6626689054129686, "grad_norm": 2.166862726211548, "learning_rate": 2.23231459713614e-05, "loss": 0.481, "step": 2600 }, { "epoch": 1.6633085472135605, "grad_norm": 2.1800949573516846, "learning_rate": 2.2312459927334904e-05, "loss": 0.4643, "step": 2601 }, { "epoch": 1.663948189014152, "grad_norm": 1.9909067153930664, "learning_rate": 2.23017738833084e-05, "loss": 0.4281, "step": 2602 }, { "epoch": 1.6645878308147437, "grad_norm": 2.312584400177002, "learning_rate": 2.22910878392819e-05, "loss": 0.5142, "step": 2603 }, { "epoch": 1.6652274726153355, "grad_norm": 2.3507843017578125, "learning_rate": 2.22804017952554e-05, "loss": 0.5246, "step": 2604 }, { "epoch": 1.665867114415927, "grad_norm": 2.3416669368743896, "learning_rate": 2.2269715751228895e-05, "loss": 0.5173, "step": 2605 }, { "epoch": 1.6665067562165188, "grad_norm": 2.5131280422210693, "learning_rate": 2.2259029707202394e-05, "loss": 0.61, "step": 2606 }, { "epoch": 1.6671463980171104, "grad_norm": 2.2798163890838623, "learning_rate": 2.2248343663175894e-05, "loss": 0.5147, "step": 2607 }, { "epoch": 1.667786039817702, "grad_norm": 2.3884902000427246, "learning_rate": 2.223765761914939e-05, "loss": 0.5237, "step": 2608 }, { "epoch": 1.6684256816182939, "grad_norm": 2.1361193656921387, "learning_rate": 2.222697157512289e-05, "loss": 0.5225, "step": 2609 }, { "epoch": 1.6690653234188855, "grad_norm": 2.3209760189056396, "learning_rate": 2.221628553109639e-05, "loss": 0.5232, "step": 2610 }, { "epoch": 1.669704965219477, "grad_norm": 2.5959839820861816, "learning_rate": 2.2205599487069888e-05, "loss": 0.5796, "step": 2611 }, { "epoch": 1.670344607020069, "grad_norm": 2.0414974689483643, "learning_rate": 2.2194913443043387e-05, "loss": 0.4931, "step": 2612 }, { "epoch": 1.6709842488206603, "grad_norm": 2.2084851264953613, "learning_rate": 2.2184227399016887e-05, "loss": 0.503, "step": 2613 }, { "epoch": 1.6716238906212522, "grad_norm": 2.4800655841827393, "learning_rate": 2.2173541354990386e-05, "loss": 0.5165, "step": 2614 }, { "epoch": 1.6722635324218438, "grad_norm": 2.23939847946167, "learning_rate": 2.2162855310963882e-05, "loss": 0.5291, "step": 2615 }, { "epoch": 1.6729031742224354, "grad_norm": 2.307274103164673, "learning_rate": 2.215216926693738e-05, "loss": 0.5308, "step": 2616 }, { "epoch": 1.6735428160230272, "grad_norm": 2.3671650886535645, "learning_rate": 2.214148322291088e-05, "loss": 0.5045, "step": 2617 }, { "epoch": 1.6741824578236186, "grad_norm": 1.9408921003341675, "learning_rate": 2.2130797178884377e-05, "loss": 0.433, "step": 2618 }, { "epoch": 1.6748220996242105, "grad_norm": 2.1856043338775635, "learning_rate": 2.2120111134857876e-05, "loss": 0.5002, "step": 2619 }, { "epoch": 1.675461741424802, "grad_norm": 2.113482713699341, "learning_rate": 2.2109425090831375e-05, "loss": 0.5113, "step": 2620 }, { "epoch": 1.6761013832253937, "grad_norm": 2.0282042026519775, "learning_rate": 2.209873904680487e-05, "loss": 0.4542, "step": 2621 }, { "epoch": 1.6767410250259855, "grad_norm": 2.4339025020599365, "learning_rate": 2.208805300277837e-05, "loss": 0.6055, "step": 2622 }, { "epoch": 1.6773806668265772, "grad_norm": 2.0931270122528076, "learning_rate": 2.207736695875187e-05, "loss": 0.4387, "step": 2623 }, { "epoch": 1.6780203086271688, "grad_norm": 2.082490921020508, "learning_rate": 2.206668091472537e-05, "loss": 0.4739, "step": 2624 }, { "epoch": 1.6786599504277606, "grad_norm": 2.464775562286377, "learning_rate": 2.205599487069887e-05, "loss": 0.5754, "step": 2625 }, { "epoch": 1.679299592228352, "grad_norm": 2.403154134750366, "learning_rate": 2.2045308826672368e-05, "loss": 0.4517, "step": 2626 }, { "epoch": 1.6799392340289439, "grad_norm": 2.4314749240875244, "learning_rate": 2.2034622782645867e-05, "loss": 0.5536, "step": 2627 }, { "epoch": 1.6805788758295355, "grad_norm": 2.4847919940948486, "learning_rate": 2.2023936738619363e-05, "loss": 0.5423, "step": 2628 }, { "epoch": 1.681218517630127, "grad_norm": 2.0763776302337646, "learning_rate": 2.2013250694592863e-05, "loss": 0.4765, "step": 2629 }, { "epoch": 1.681858159430719, "grad_norm": 2.3855700492858887, "learning_rate": 2.2002564650566362e-05, "loss": 0.5392, "step": 2630 }, { "epoch": 1.6824978012313103, "grad_norm": 2.0628979206085205, "learning_rate": 2.1991878606539858e-05, "loss": 0.4635, "step": 2631 }, { "epoch": 1.6831374430319022, "grad_norm": 1.7442479133605957, "learning_rate": 2.1981192562513357e-05, "loss": 0.3898, "step": 2632 }, { "epoch": 1.6837770848324938, "grad_norm": 2.3893167972564697, "learning_rate": 2.1970506518486857e-05, "loss": 0.4624, "step": 2633 }, { "epoch": 1.6844167266330854, "grad_norm": 2.4031567573547363, "learning_rate": 2.1959820474460356e-05, "loss": 0.5156, "step": 2634 }, { "epoch": 1.6850563684336772, "grad_norm": 2.734078884124756, "learning_rate": 2.1949134430433856e-05, "loss": 0.582, "step": 2635 }, { "epoch": 1.6856960102342688, "grad_norm": 2.3971729278564453, "learning_rate": 2.1938448386407355e-05, "loss": 0.5392, "step": 2636 }, { "epoch": 1.6863356520348605, "grad_norm": 2.26690936088562, "learning_rate": 2.192776234238085e-05, "loss": 0.5037, "step": 2637 }, { "epoch": 1.6869752938354523, "grad_norm": 2.397167444229126, "learning_rate": 2.191707629835435e-05, "loss": 0.527, "step": 2638 }, { "epoch": 1.6876149356360437, "grad_norm": 2.739813804626465, "learning_rate": 2.190639025432785e-05, "loss": 0.585, "step": 2639 }, { "epoch": 1.6882545774366355, "grad_norm": 2.084416389465332, "learning_rate": 2.189570421030135e-05, "loss": 0.4488, "step": 2640 }, { "epoch": 1.6888942192372272, "grad_norm": 2.519582986831665, "learning_rate": 2.1885018166274845e-05, "loss": 0.5626, "step": 2641 }, { "epoch": 1.6895338610378188, "grad_norm": 2.360438108444214, "learning_rate": 2.1874332122248344e-05, "loss": 0.5438, "step": 2642 }, { "epoch": 1.6901735028384106, "grad_norm": 2.7401225566864014, "learning_rate": 2.1863646078221844e-05, "loss": 0.5803, "step": 2643 }, { "epoch": 1.690813144639002, "grad_norm": 2.3514299392700195, "learning_rate": 2.185296003419534e-05, "loss": 0.4884, "step": 2644 }, { "epoch": 1.6914527864395938, "grad_norm": 2.3277571201324463, "learning_rate": 2.184227399016884e-05, "loss": 0.5094, "step": 2645 }, { "epoch": 1.6920924282401855, "grad_norm": 2.3622419834136963, "learning_rate": 2.183158794614234e-05, "loss": 0.5348, "step": 2646 }, { "epoch": 1.692732070040777, "grad_norm": 2.3978912830352783, "learning_rate": 2.1820901902115838e-05, "loss": 0.5384, "step": 2647 }, { "epoch": 1.693371711841369, "grad_norm": 2.294590950012207, "learning_rate": 2.1810215858089337e-05, "loss": 0.5264, "step": 2648 }, { "epoch": 1.6940113536419605, "grad_norm": 2.33931303024292, "learning_rate": 2.1799529814062836e-05, "loss": 0.5296, "step": 2649 }, { "epoch": 1.6946509954425522, "grad_norm": 2.219364881515503, "learning_rate": 2.1788843770036332e-05, "loss": 0.5125, "step": 2650 }, { "epoch": 1.695290637243144, "grad_norm": 2.0647964477539062, "learning_rate": 2.1778157726009832e-05, "loss": 0.427, "step": 2651 }, { "epoch": 1.6959302790437354, "grad_norm": 2.1907999515533447, "learning_rate": 2.176747168198333e-05, "loss": 0.4691, "step": 2652 }, { "epoch": 1.6965699208443272, "grad_norm": 2.2468862533569336, "learning_rate": 2.175678563795683e-05, "loss": 0.4703, "step": 2653 }, { "epoch": 1.6972095626449188, "grad_norm": 2.134443759918213, "learning_rate": 2.1746099593930327e-05, "loss": 0.4764, "step": 2654 }, { "epoch": 1.6978492044455105, "grad_norm": 2.3065402507781982, "learning_rate": 2.1735413549903826e-05, "loss": 0.4695, "step": 2655 }, { "epoch": 1.6984888462461023, "grad_norm": 2.2199900150299072, "learning_rate": 2.1724727505877325e-05, "loss": 0.4493, "step": 2656 }, { "epoch": 1.6991284880466937, "grad_norm": 2.345433235168457, "learning_rate": 2.1714041461850825e-05, "loss": 0.5201, "step": 2657 }, { "epoch": 1.6997681298472855, "grad_norm": 2.6745223999023438, "learning_rate": 2.1703355417824324e-05, "loss": 0.5153, "step": 2658 }, { "epoch": 1.7004077716478772, "grad_norm": 2.2623071670532227, "learning_rate": 2.1692669373797823e-05, "loss": 0.5347, "step": 2659 }, { "epoch": 1.7010474134484688, "grad_norm": 2.07926082611084, "learning_rate": 2.168198332977132e-05, "loss": 0.437, "step": 2660 }, { "epoch": 1.7016870552490606, "grad_norm": 1.9367485046386719, "learning_rate": 2.167129728574482e-05, "loss": 0.4556, "step": 2661 }, { "epoch": 1.7023266970496522, "grad_norm": 2.360860586166382, "learning_rate": 2.1660611241718318e-05, "loss": 0.555, "step": 2662 }, { "epoch": 1.7029663388502438, "grad_norm": 2.382340908050537, "learning_rate": 2.1649925197691814e-05, "loss": 0.4895, "step": 2663 }, { "epoch": 1.7036059806508357, "grad_norm": 2.5638585090637207, "learning_rate": 2.1639239153665313e-05, "loss": 0.563, "step": 2664 }, { "epoch": 1.704245622451427, "grad_norm": 2.3636674880981445, "learning_rate": 2.1628553109638813e-05, "loss": 0.5476, "step": 2665 }, { "epoch": 1.704885264252019, "grad_norm": 2.633293628692627, "learning_rate": 2.161786706561231e-05, "loss": 0.6173, "step": 2666 }, { "epoch": 1.7055249060526105, "grad_norm": 2.334656000137329, "learning_rate": 2.1607181021585808e-05, "loss": 0.5153, "step": 2667 }, { "epoch": 1.7061645478532022, "grad_norm": 2.401369571685791, "learning_rate": 2.1596494977559307e-05, "loss": 0.5303, "step": 2668 }, { "epoch": 1.706804189653794, "grad_norm": 2.0251777172088623, "learning_rate": 2.1585808933532807e-05, "loss": 0.4164, "step": 2669 }, { "epoch": 1.7074438314543854, "grad_norm": 2.3030428886413574, "learning_rate": 2.1575122889506306e-05, "loss": 0.4798, "step": 2670 }, { "epoch": 1.7080834732549772, "grad_norm": 2.1975905895233154, "learning_rate": 2.1564436845479806e-05, "loss": 0.4875, "step": 2671 }, { "epoch": 1.7087231150555688, "grad_norm": 2.6817076206207275, "learning_rate": 2.1553750801453305e-05, "loss": 0.4836, "step": 2672 }, { "epoch": 1.7093627568561605, "grad_norm": 2.809296131134033, "learning_rate": 2.15430647574268e-05, "loss": 0.5827, "step": 2673 }, { "epoch": 1.7100023986567523, "grad_norm": 2.5263898372650146, "learning_rate": 2.15323787134003e-05, "loss": 0.5547, "step": 2674 }, { "epoch": 1.710642040457344, "grad_norm": 1.942217230796814, "learning_rate": 2.15216926693738e-05, "loss": 0.3903, "step": 2675 }, { "epoch": 1.7112816822579355, "grad_norm": 2.0551159381866455, "learning_rate": 2.1511006625347296e-05, "loss": 0.4718, "step": 2676 }, { "epoch": 1.7119213240585274, "grad_norm": 2.2917423248291016, "learning_rate": 2.1500320581320795e-05, "loss": 0.5013, "step": 2677 }, { "epoch": 1.7125609658591188, "grad_norm": 2.160872220993042, "learning_rate": 2.1489634537294294e-05, "loss": 0.5068, "step": 2678 }, { "epoch": 1.7132006076597106, "grad_norm": 2.2712011337280273, "learning_rate": 2.1478948493267794e-05, "loss": 0.5293, "step": 2679 }, { "epoch": 1.7138402494603022, "grad_norm": 2.1471195220947266, "learning_rate": 2.1468262449241293e-05, "loss": 0.5069, "step": 2680 }, { "epoch": 1.7144798912608938, "grad_norm": 2.3133046627044678, "learning_rate": 2.1457576405214792e-05, "loss": 0.5018, "step": 2681 }, { "epoch": 1.7151195330614857, "grad_norm": 2.4129765033721924, "learning_rate": 2.1446890361188292e-05, "loss": 0.5156, "step": 2682 }, { "epoch": 1.715759174862077, "grad_norm": 2.685666084289551, "learning_rate": 2.1436204317161788e-05, "loss": 0.5877, "step": 2683 }, { "epoch": 1.716398816662669, "grad_norm": 2.536916971206665, "learning_rate": 2.1425518273135287e-05, "loss": 0.5649, "step": 2684 }, { "epoch": 1.7170384584632605, "grad_norm": 2.58223819732666, "learning_rate": 2.1414832229108786e-05, "loss": 0.5849, "step": 2685 }, { "epoch": 1.7176781002638521, "grad_norm": 2.4905548095703125, "learning_rate": 2.1404146185082282e-05, "loss": 0.5486, "step": 2686 }, { "epoch": 1.718317742064444, "grad_norm": 2.3483517169952393, "learning_rate": 2.1393460141055782e-05, "loss": 0.5212, "step": 2687 }, { "epoch": 1.7189573838650356, "grad_norm": 2.4959635734558105, "learning_rate": 2.138277409702928e-05, "loss": 0.5784, "step": 2688 }, { "epoch": 1.7195970256656272, "grad_norm": 2.4645330905914307, "learning_rate": 2.1372088053002777e-05, "loss": 0.5065, "step": 2689 }, { "epoch": 1.720236667466219, "grad_norm": 2.55702543258667, "learning_rate": 2.1361402008976276e-05, "loss": 0.5177, "step": 2690 }, { "epoch": 1.7208763092668105, "grad_norm": 2.447925329208374, "learning_rate": 2.1350715964949776e-05, "loss": 0.5278, "step": 2691 }, { "epoch": 1.7215159510674023, "grad_norm": 2.4395155906677246, "learning_rate": 2.1340029920923275e-05, "loss": 0.5456, "step": 2692 }, { "epoch": 1.722155592867994, "grad_norm": 2.313857316970825, "learning_rate": 2.1329343876896775e-05, "loss": 0.5294, "step": 2693 }, { "epoch": 1.7227952346685855, "grad_norm": 2.389639377593994, "learning_rate": 2.1318657832870274e-05, "loss": 0.5167, "step": 2694 }, { "epoch": 1.7234348764691774, "grad_norm": 2.291781425476074, "learning_rate": 2.1307971788843773e-05, "loss": 0.5264, "step": 2695 }, { "epoch": 1.7240745182697688, "grad_norm": 2.516266345977783, "learning_rate": 2.129728574481727e-05, "loss": 0.5836, "step": 2696 }, { "epoch": 1.7247141600703606, "grad_norm": 2.0757901668548584, "learning_rate": 2.128659970079077e-05, "loss": 0.4871, "step": 2697 }, { "epoch": 1.7253538018709522, "grad_norm": 2.7365918159484863, "learning_rate": 2.1275913656764268e-05, "loss": 0.5389, "step": 2698 }, { "epoch": 1.7259934436715438, "grad_norm": 2.2034716606140137, "learning_rate": 2.1265227612737764e-05, "loss": 0.5078, "step": 2699 }, { "epoch": 1.7266330854721357, "grad_norm": 1.9844567775726318, "learning_rate": 2.1254541568711263e-05, "loss": 0.4717, "step": 2700 }, { "epoch": 1.7272727272727273, "grad_norm": 2.068657875061035, "learning_rate": 2.1243855524684763e-05, "loss": 0.4478, "step": 2701 }, { "epoch": 1.727912369073319, "grad_norm": 2.292952537536621, "learning_rate": 2.1233169480658262e-05, "loss": 0.5104, "step": 2702 }, { "epoch": 1.7285520108739107, "grad_norm": 2.1269376277923584, "learning_rate": 2.122248343663176e-05, "loss": 0.4561, "step": 2703 }, { "epoch": 1.7291916526745021, "grad_norm": 2.290296792984009, "learning_rate": 2.121179739260526e-05, "loss": 0.5308, "step": 2704 }, { "epoch": 1.729831294475094, "grad_norm": 2.1942138671875, "learning_rate": 2.1201111348578757e-05, "loss": 0.4779, "step": 2705 }, { "epoch": 1.7304709362756856, "grad_norm": 2.4728095531463623, "learning_rate": 2.1190425304552256e-05, "loss": 0.5806, "step": 2706 }, { "epoch": 1.7311105780762772, "grad_norm": 2.411494493484497, "learning_rate": 2.1179739260525755e-05, "loss": 0.5074, "step": 2707 }, { "epoch": 1.731750219876869, "grad_norm": 2.0176281929016113, "learning_rate": 2.116905321649925e-05, "loss": 0.4025, "step": 2708 }, { "epoch": 1.7323898616774607, "grad_norm": 2.5532777309417725, "learning_rate": 2.115836717247275e-05, "loss": 0.4898, "step": 2709 }, { "epoch": 1.7330295034780523, "grad_norm": 2.271014928817749, "learning_rate": 2.114768112844625e-05, "loss": 0.4581, "step": 2710 }, { "epoch": 1.733669145278644, "grad_norm": 2.446220636367798, "learning_rate": 2.113699508441975e-05, "loss": 0.4832, "step": 2711 }, { "epoch": 1.7343087870792355, "grad_norm": 2.006302833557129, "learning_rate": 2.1126309040393245e-05, "loss": 0.4575, "step": 2712 }, { "epoch": 1.7349484288798274, "grad_norm": 2.2831568717956543, "learning_rate": 2.1115622996366745e-05, "loss": 0.4792, "step": 2713 }, { "epoch": 1.735588070680419, "grad_norm": 2.3639678955078125, "learning_rate": 2.1104936952340244e-05, "loss": 0.487, "step": 2714 }, { "epoch": 1.7362277124810106, "grad_norm": 2.579700231552124, "learning_rate": 2.1094250908313744e-05, "loss": 0.5431, "step": 2715 }, { "epoch": 1.7368673542816024, "grad_norm": 2.3579726219177246, "learning_rate": 2.1083564864287243e-05, "loss": 0.5355, "step": 2716 }, { "epoch": 1.7375069960821938, "grad_norm": 2.5764262676239014, "learning_rate": 2.1072878820260742e-05, "loss": 0.5081, "step": 2717 }, { "epoch": 1.7381466378827857, "grad_norm": 2.2579660415649414, "learning_rate": 2.1062192776234238e-05, "loss": 0.4355, "step": 2718 }, { "epoch": 1.7387862796833773, "grad_norm": 2.340811252593994, "learning_rate": 2.1051506732207738e-05, "loss": 0.4853, "step": 2719 }, { "epoch": 1.739425921483969, "grad_norm": 2.223498821258545, "learning_rate": 2.1040820688181237e-05, "loss": 0.4966, "step": 2720 }, { "epoch": 1.7400655632845607, "grad_norm": 2.233729124069214, "learning_rate": 2.1030134644154733e-05, "loss": 0.4446, "step": 2721 }, { "epoch": 1.7407052050851524, "grad_norm": 2.414647102355957, "learning_rate": 2.1019448600128232e-05, "loss": 0.4673, "step": 2722 }, { "epoch": 1.741344846885744, "grad_norm": 2.403012752532959, "learning_rate": 2.100876255610173e-05, "loss": 0.4835, "step": 2723 }, { "epoch": 1.7419844886863356, "grad_norm": 2.7517170906066895, "learning_rate": 2.099807651207523e-05, "loss": 0.5839, "step": 2724 }, { "epoch": 1.7426241304869272, "grad_norm": 2.5492401123046875, "learning_rate": 2.098739046804873e-05, "loss": 0.5046, "step": 2725 }, { "epoch": 1.743263772287519, "grad_norm": 2.58609676361084, "learning_rate": 2.097670442402223e-05, "loss": 0.5653, "step": 2726 }, { "epoch": 1.7439034140881107, "grad_norm": 2.214102268218994, "learning_rate": 2.096601837999573e-05, "loss": 0.5014, "step": 2727 }, { "epoch": 1.7445430558887023, "grad_norm": 2.146833896636963, "learning_rate": 2.0955332335969225e-05, "loss": 0.4724, "step": 2728 }, { "epoch": 1.7451826976892941, "grad_norm": 2.0483169555664062, "learning_rate": 2.0944646291942724e-05, "loss": 0.4511, "step": 2729 }, { "epoch": 1.7458223394898855, "grad_norm": 2.2580761909484863, "learning_rate": 2.0933960247916224e-05, "loss": 0.475, "step": 2730 }, { "epoch": 1.7464619812904774, "grad_norm": 2.654022455215454, "learning_rate": 2.092327420388972e-05, "loss": 0.5649, "step": 2731 }, { "epoch": 1.747101623091069, "grad_norm": 2.297478675842285, "learning_rate": 2.091258815986322e-05, "loss": 0.4369, "step": 2732 }, { "epoch": 1.7477412648916606, "grad_norm": 2.2317726612091064, "learning_rate": 2.090190211583672e-05, "loss": 0.4485, "step": 2733 }, { "epoch": 1.7483809066922524, "grad_norm": 2.0698795318603516, "learning_rate": 2.0891216071810214e-05, "loss": 0.4651, "step": 2734 }, { "epoch": 1.749020548492844, "grad_norm": 2.26355242729187, "learning_rate": 2.0880530027783714e-05, "loss": 0.503, "step": 2735 }, { "epoch": 1.7496601902934357, "grad_norm": 2.4342384338378906, "learning_rate": 2.0869843983757213e-05, "loss": 0.4994, "step": 2736 }, { "epoch": 1.7502998320940275, "grad_norm": 2.657132148742676, "learning_rate": 2.0859157939730713e-05, "loss": 0.549, "step": 2737 }, { "epoch": 1.750939473894619, "grad_norm": 2.6180858612060547, "learning_rate": 2.0848471895704212e-05, "loss": 0.5755, "step": 2738 }, { "epoch": 1.7515791156952107, "grad_norm": 2.4720981121063232, "learning_rate": 2.083778585167771e-05, "loss": 0.5363, "step": 2739 }, { "epoch": 1.7522187574958024, "grad_norm": 2.6236979961395264, "learning_rate": 2.082709980765121e-05, "loss": 0.5526, "step": 2740 }, { "epoch": 1.752858399296394, "grad_norm": 2.3086047172546387, "learning_rate": 2.0816413763624707e-05, "loss": 0.5098, "step": 2741 }, { "epoch": 1.7534980410969858, "grad_norm": 2.465480327606201, "learning_rate": 2.0805727719598206e-05, "loss": 0.5077, "step": 2742 }, { "epoch": 1.7541376828975772, "grad_norm": 2.3380141258239746, "learning_rate": 2.0795041675571705e-05, "loss": 0.544, "step": 2743 }, { "epoch": 1.754777324698169, "grad_norm": 2.066955327987671, "learning_rate": 2.07843556315452e-05, "loss": 0.4561, "step": 2744 }, { "epoch": 1.7554169664987607, "grad_norm": 2.0033040046691895, "learning_rate": 2.07736695875187e-05, "loss": 0.4036, "step": 2745 }, { "epoch": 1.7560566082993523, "grad_norm": 2.2523396015167236, "learning_rate": 2.07629835434922e-05, "loss": 0.5443, "step": 2746 }, { "epoch": 1.7566962500999441, "grad_norm": 2.8302853107452393, "learning_rate": 2.0752297499465696e-05, "loss": 0.6189, "step": 2747 }, { "epoch": 1.7573358919005357, "grad_norm": 2.0967698097229004, "learning_rate": 2.07416114554392e-05, "loss": 0.4722, "step": 2748 }, { "epoch": 1.7579755337011274, "grad_norm": 2.1303067207336426, "learning_rate": 2.0730925411412698e-05, "loss": 0.4575, "step": 2749 }, { "epoch": 1.7586151755017192, "grad_norm": 2.3548195362091064, "learning_rate": 2.0720239367386194e-05, "loss": 0.523, "step": 2750 }, { "epoch": 1.7592548173023106, "grad_norm": 2.5518958568573, "learning_rate": 2.0709553323359693e-05, "loss": 0.5023, "step": 2751 }, { "epoch": 1.7598944591029024, "grad_norm": 2.3645482063293457, "learning_rate": 2.0698867279333193e-05, "loss": 0.5029, "step": 2752 }, { "epoch": 1.760534100903494, "grad_norm": 2.020030975341797, "learning_rate": 2.0688181235306692e-05, "loss": 0.4404, "step": 2753 }, { "epoch": 1.7611737427040857, "grad_norm": 2.188493251800537, "learning_rate": 2.0677495191280188e-05, "loss": 0.5262, "step": 2754 }, { "epoch": 1.7618133845046775, "grad_norm": 2.2824320793151855, "learning_rate": 2.0666809147253688e-05, "loss": 0.491, "step": 2755 }, { "epoch": 1.762453026305269, "grad_norm": 2.4223709106445312, "learning_rate": 2.0656123103227187e-05, "loss": 0.499, "step": 2756 }, { "epoch": 1.7630926681058607, "grad_norm": 2.6509532928466797, "learning_rate": 2.0645437059200683e-05, "loss": 0.6081, "step": 2757 }, { "epoch": 1.7637323099064524, "grad_norm": 2.5494544506073, "learning_rate": 2.0634751015174182e-05, "loss": 0.5476, "step": 2758 }, { "epoch": 1.764371951707044, "grad_norm": 2.4070253372192383, "learning_rate": 2.062406497114768e-05, "loss": 0.4977, "step": 2759 }, { "epoch": 1.7650115935076358, "grad_norm": 2.3602166175842285, "learning_rate": 2.061337892712118e-05, "loss": 0.5285, "step": 2760 }, { "epoch": 1.7656512353082274, "grad_norm": 2.388374090194702, "learning_rate": 2.060269288309468e-05, "loss": 0.5323, "step": 2761 }, { "epoch": 1.766290877108819, "grad_norm": 2.2147531509399414, "learning_rate": 2.059200683906818e-05, "loss": 0.4189, "step": 2762 }, { "epoch": 1.7669305189094109, "grad_norm": 2.5422163009643555, "learning_rate": 2.0581320795041676e-05, "loss": 0.5374, "step": 2763 }, { "epoch": 1.7675701607100023, "grad_norm": 2.307199716567993, "learning_rate": 2.0570634751015175e-05, "loss": 0.5011, "step": 2764 }, { "epoch": 1.7682098025105941, "grad_norm": 2.382908821105957, "learning_rate": 2.0559948706988674e-05, "loss": 0.5394, "step": 2765 }, { "epoch": 1.7688494443111857, "grad_norm": 2.2391819953918457, "learning_rate": 2.0549262662962174e-05, "loss": 0.4584, "step": 2766 }, { "epoch": 1.7694890861117774, "grad_norm": 2.414435386657715, "learning_rate": 2.053857661893567e-05, "loss": 0.5168, "step": 2767 }, { "epoch": 1.7701287279123692, "grad_norm": 2.6296498775482178, "learning_rate": 2.052789057490917e-05, "loss": 0.5576, "step": 2768 }, { "epoch": 1.7707683697129606, "grad_norm": 2.425842523574829, "learning_rate": 2.051720453088267e-05, "loss": 0.5158, "step": 2769 }, { "epoch": 1.7714080115135524, "grad_norm": 2.3860042095184326, "learning_rate": 2.0506518486856164e-05, "loss": 0.5222, "step": 2770 }, { "epoch": 1.772047653314144, "grad_norm": 2.504329204559326, "learning_rate": 2.0495832442829667e-05, "loss": 0.5406, "step": 2771 }, { "epoch": 1.7726872951147357, "grad_norm": 2.3346235752105713, "learning_rate": 2.0485146398803167e-05, "loss": 0.5279, "step": 2772 }, { "epoch": 1.7733269369153275, "grad_norm": 2.253188371658325, "learning_rate": 2.0474460354776662e-05, "loss": 0.4823, "step": 2773 }, { "epoch": 1.7739665787159191, "grad_norm": 2.167649745941162, "learning_rate": 2.0463774310750162e-05, "loss": 0.4633, "step": 2774 }, { "epoch": 1.7746062205165107, "grad_norm": 2.0699386596679688, "learning_rate": 2.045308826672366e-05, "loss": 0.4717, "step": 2775 }, { "epoch": 1.7752458623171026, "grad_norm": 2.171119213104248, "learning_rate": 2.0442402222697157e-05, "loss": 0.4561, "step": 2776 }, { "epoch": 1.775885504117694, "grad_norm": 2.9215235710144043, "learning_rate": 2.0431716178670657e-05, "loss": 0.5582, "step": 2777 }, { "epoch": 1.7765251459182858, "grad_norm": 2.1220853328704834, "learning_rate": 2.0421030134644156e-05, "loss": 0.4898, "step": 2778 }, { "epoch": 1.7771647877188774, "grad_norm": 2.2881810665130615, "learning_rate": 2.0410344090617652e-05, "loss": 0.5048, "step": 2779 }, { "epoch": 1.777804429519469, "grad_norm": 2.4088737964630127, "learning_rate": 2.039965804659115e-05, "loss": 0.5668, "step": 2780 }, { "epoch": 1.7784440713200609, "grad_norm": 2.85402250289917, "learning_rate": 2.038897200256465e-05, "loss": 0.6494, "step": 2781 }, { "epoch": 1.7790837131206523, "grad_norm": 2.4570300579071045, "learning_rate": 2.037828595853815e-05, "loss": 0.5642, "step": 2782 }, { "epoch": 1.7797233549212441, "grad_norm": 2.45947527885437, "learning_rate": 2.036759991451165e-05, "loss": 0.5535, "step": 2783 }, { "epoch": 1.7803629967218357, "grad_norm": 2.2584729194641113, "learning_rate": 2.035691387048515e-05, "loss": 0.5012, "step": 2784 }, { "epoch": 1.7810026385224274, "grad_norm": 2.148829698562622, "learning_rate": 2.0346227826458648e-05, "loss": 0.4715, "step": 2785 }, { "epoch": 1.7816422803230192, "grad_norm": 2.112736701965332, "learning_rate": 2.0335541782432144e-05, "loss": 0.4649, "step": 2786 }, { "epoch": 1.7822819221236108, "grad_norm": 2.688622236251831, "learning_rate": 2.0324855738405643e-05, "loss": 0.5545, "step": 2787 }, { "epoch": 1.7829215639242024, "grad_norm": 2.1854984760284424, "learning_rate": 2.0314169694379143e-05, "loss": 0.4671, "step": 2788 }, { "epoch": 1.7835612057247943, "grad_norm": 2.436605453491211, "learning_rate": 2.030348365035264e-05, "loss": 0.5054, "step": 2789 }, { "epoch": 1.7842008475253857, "grad_norm": 2.344019889831543, "learning_rate": 2.0292797606326138e-05, "loss": 0.5215, "step": 2790 }, { "epoch": 1.7848404893259775, "grad_norm": 2.161363124847412, "learning_rate": 2.0282111562299637e-05, "loss": 0.4662, "step": 2791 }, { "epoch": 1.7854801311265691, "grad_norm": 2.3229241371154785, "learning_rate": 2.0271425518273133e-05, "loss": 0.5488, "step": 2792 }, { "epoch": 1.7861197729271607, "grad_norm": 2.2552490234375, "learning_rate": 2.0260739474246633e-05, "loss": 0.5126, "step": 2793 }, { "epoch": 1.7867594147277526, "grad_norm": 2.301288604736328, "learning_rate": 2.0250053430220136e-05, "loss": 0.5465, "step": 2794 }, { "epoch": 1.787399056528344, "grad_norm": 2.272421360015869, "learning_rate": 2.0239367386193635e-05, "loss": 0.4651, "step": 2795 }, { "epoch": 1.7880386983289358, "grad_norm": 2.031331777572632, "learning_rate": 2.022868134216713e-05, "loss": 0.4683, "step": 2796 }, { "epoch": 1.7886783401295274, "grad_norm": 2.4139904975891113, "learning_rate": 2.021799529814063e-05, "loss": 0.4937, "step": 2797 }, { "epoch": 1.789317981930119, "grad_norm": 2.238555669784546, "learning_rate": 2.020730925411413e-05, "loss": 0.4962, "step": 2798 }, { "epoch": 1.7899576237307109, "grad_norm": 2.5187525749206543, "learning_rate": 2.0196623210087626e-05, "loss": 0.593, "step": 2799 }, { "epoch": 1.7905972655313025, "grad_norm": 2.1062705516815186, "learning_rate": 2.0185937166061125e-05, "loss": 0.4517, "step": 2800 }, { "epoch": 1.7912369073318941, "grad_norm": 2.270381450653076, "learning_rate": 2.0175251122034624e-05, "loss": 0.483, "step": 2801 }, { "epoch": 1.791876549132486, "grad_norm": 2.4763448238372803, "learning_rate": 2.016456507800812e-05, "loss": 0.5357, "step": 2802 }, { "epoch": 1.7925161909330773, "grad_norm": 2.541749954223633, "learning_rate": 2.015387903398162e-05, "loss": 0.5305, "step": 2803 }, { "epoch": 1.7931558327336692, "grad_norm": 2.6028640270233154, "learning_rate": 2.014319298995512e-05, "loss": 0.561, "step": 2804 }, { "epoch": 1.7937954745342608, "grad_norm": 2.383382558822632, "learning_rate": 2.013250694592862e-05, "loss": 0.5404, "step": 2805 }, { "epoch": 1.7944351163348524, "grad_norm": 2.184458017349243, "learning_rate": 2.0121820901902118e-05, "loss": 0.4944, "step": 2806 }, { "epoch": 1.7950747581354443, "grad_norm": 2.631732225418091, "learning_rate": 2.0111134857875617e-05, "loss": 0.5581, "step": 2807 }, { "epoch": 1.7957143999360357, "grad_norm": 2.4651522636413574, "learning_rate": 2.0100448813849116e-05, "loss": 0.5583, "step": 2808 }, { "epoch": 1.7963540417366275, "grad_norm": 2.227365255355835, "learning_rate": 2.0089762769822612e-05, "loss": 0.4797, "step": 2809 }, { "epoch": 1.796993683537219, "grad_norm": 2.237375020980835, "learning_rate": 2.0079076725796112e-05, "loss": 0.4999, "step": 2810 }, { "epoch": 1.7976333253378107, "grad_norm": 2.3141372203826904, "learning_rate": 2.006839068176961e-05, "loss": 0.5572, "step": 2811 }, { "epoch": 1.7982729671384026, "grad_norm": 2.1367897987365723, "learning_rate": 2.0057704637743107e-05, "loss": 0.4739, "step": 2812 }, { "epoch": 1.7989126089389942, "grad_norm": 2.7138278484344482, "learning_rate": 2.0047018593716606e-05, "loss": 0.5358, "step": 2813 }, { "epoch": 1.7995522507395858, "grad_norm": 2.4364922046661377, "learning_rate": 2.0036332549690106e-05, "loss": 0.5178, "step": 2814 }, { "epoch": 1.8001918925401776, "grad_norm": 2.3911404609680176, "learning_rate": 2.0025646505663602e-05, "loss": 0.5185, "step": 2815 }, { "epoch": 1.800831534340769, "grad_norm": 2.4266908168792725, "learning_rate": 2.00149604616371e-05, "loss": 0.5385, "step": 2816 }, { "epoch": 1.8014711761413609, "grad_norm": 2.301403760910034, "learning_rate": 2.0004274417610604e-05, "loss": 0.5091, "step": 2817 }, { "epoch": 1.8021108179419525, "grad_norm": 2.1748011112213135, "learning_rate": 1.99935883735841e-05, "loss": 0.5035, "step": 2818 }, { "epoch": 1.802750459742544, "grad_norm": 2.486557960510254, "learning_rate": 1.99829023295576e-05, "loss": 0.5657, "step": 2819 }, { "epoch": 1.803390101543136, "grad_norm": 2.9996259212493896, "learning_rate": 1.99722162855311e-05, "loss": 0.6418, "step": 2820 }, { "epoch": 1.8040297433437276, "grad_norm": 2.488780975341797, "learning_rate": 1.9961530241504595e-05, "loss": 0.5772, "step": 2821 }, { "epoch": 1.8046693851443192, "grad_norm": 2.3787550926208496, "learning_rate": 1.9950844197478094e-05, "loss": 0.5399, "step": 2822 }, { "epoch": 1.8053090269449108, "grad_norm": 2.30735445022583, "learning_rate": 1.9940158153451593e-05, "loss": 0.5211, "step": 2823 }, { "epoch": 1.8059486687455024, "grad_norm": 2.4023263454437256, "learning_rate": 1.9929472109425093e-05, "loss": 0.5413, "step": 2824 }, { "epoch": 1.8065883105460943, "grad_norm": 2.2471938133239746, "learning_rate": 1.991878606539859e-05, "loss": 0.4598, "step": 2825 }, { "epoch": 1.8072279523466859, "grad_norm": 2.5233891010284424, "learning_rate": 1.9908100021372088e-05, "loss": 0.5087, "step": 2826 }, { "epoch": 1.8078675941472775, "grad_norm": 2.597228765487671, "learning_rate": 1.9897413977345587e-05, "loss": 0.5766, "step": 2827 }, { "epoch": 1.8085072359478693, "grad_norm": 2.249992609024048, "learning_rate": 1.9886727933319087e-05, "loss": 0.5059, "step": 2828 }, { "epoch": 1.8091468777484607, "grad_norm": 2.3526294231414795, "learning_rate": 1.9876041889292586e-05, "loss": 0.538, "step": 2829 }, { "epoch": 1.8097865195490526, "grad_norm": 2.0748045444488525, "learning_rate": 1.9865355845266085e-05, "loss": 0.4645, "step": 2830 }, { "epoch": 1.8104261613496442, "grad_norm": 2.502467393875122, "learning_rate": 1.985466980123958e-05, "loss": 0.5954, "step": 2831 }, { "epoch": 1.8110658031502358, "grad_norm": 2.1872975826263428, "learning_rate": 1.984398375721308e-05, "loss": 0.5333, "step": 2832 }, { "epoch": 1.8117054449508276, "grad_norm": 2.1395134925842285, "learning_rate": 1.983329771318658e-05, "loss": 0.4916, "step": 2833 }, { "epoch": 1.8123450867514193, "grad_norm": 1.8827162981033325, "learning_rate": 1.9822611669160076e-05, "loss": 0.4423, "step": 2834 }, { "epoch": 1.8129847285520109, "grad_norm": 2.33115816116333, "learning_rate": 1.9811925625133575e-05, "loss": 0.5272, "step": 2835 }, { "epoch": 1.8136243703526025, "grad_norm": 2.1068661212921143, "learning_rate": 1.9801239581107075e-05, "loss": 0.4565, "step": 2836 }, { "epoch": 1.814264012153194, "grad_norm": 2.497335910797119, "learning_rate": 1.9790553537080574e-05, "loss": 0.5472, "step": 2837 }, { "epoch": 1.814903653953786, "grad_norm": 2.2983293533325195, "learning_rate": 1.977986749305407e-05, "loss": 0.5695, "step": 2838 }, { "epoch": 1.8155432957543776, "grad_norm": 2.3338510990142822, "learning_rate": 1.976918144902757e-05, "loss": 0.5426, "step": 2839 }, { "epoch": 1.8161829375549692, "grad_norm": 2.2502028942108154, "learning_rate": 1.9758495405001072e-05, "loss": 0.4919, "step": 2840 }, { "epoch": 1.816822579355561, "grad_norm": 2.1771280765533447, "learning_rate": 1.9747809360974568e-05, "loss": 0.4862, "step": 2841 }, { "epoch": 1.8174622211561524, "grad_norm": 1.9078037738800049, "learning_rate": 1.9737123316948068e-05, "loss": 0.4006, "step": 2842 }, { "epoch": 1.8181018629567443, "grad_norm": 2.28057861328125, "learning_rate": 1.9726437272921567e-05, "loss": 0.5188, "step": 2843 }, { "epoch": 1.8187415047573359, "grad_norm": 2.471477508544922, "learning_rate": 1.9715751228895063e-05, "loss": 0.531, "step": 2844 }, { "epoch": 1.8193811465579275, "grad_norm": 2.534019947052002, "learning_rate": 1.9705065184868562e-05, "loss": 0.5377, "step": 2845 }, { "epoch": 1.8200207883585193, "grad_norm": 2.325458288192749, "learning_rate": 1.9694379140842062e-05, "loss": 0.5048, "step": 2846 }, { "epoch": 1.820660430159111, "grad_norm": 2.1005265712738037, "learning_rate": 1.9683693096815558e-05, "loss": 0.5358, "step": 2847 }, { "epoch": 1.8213000719597026, "grad_norm": 2.2133257389068604, "learning_rate": 1.9673007052789057e-05, "loss": 0.4617, "step": 2848 }, { "epoch": 1.8219397137602944, "grad_norm": 2.370957851409912, "learning_rate": 1.9662321008762556e-05, "loss": 0.5456, "step": 2849 }, { "epoch": 1.8225793555608858, "grad_norm": 2.4923248291015625, "learning_rate": 1.9651634964736056e-05, "loss": 0.5363, "step": 2850 }, { "epoch": 1.8232189973614776, "grad_norm": 2.3630828857421875, "learning_rate": 1.9640948920709555e-05, "loss": 0.5031, "step": 2851 }, { "epoch": 1.8238586391620693, "grad_norm": 2.4305341243743896, "learning_rate": 1.9630262876683054e-05, "loss": 0.5095, "step": 2852 }, { "epoch": 1.8244982809626609, "grad_norm": 2.325582981109619, "learning_rate": 1.9619576832656554e-05, "loss": 0.5035, "step": 2853 }, { "epoch": 1.8251379227632527, "grad_norm": 2.299703359603882, "learning_rate": 1.960889078863005e-05, "loss": 0.4883, "step": 2854 }, { "epoch": 1.825777564563844, "grad_norm": 2.228072166442871, "learning_rate": 1.959820474460355e-05, "loss": 0.4957, "step": 2855 }, { "epoch": 1.826417206364436, "grad_norm": 2.7845544815063477, "learning_rate": 1.958751870057705e-05, "loss": 0.5759, "step": 2856 }, { "epoch": 1.8270568481650276, "grad_norm": 2.498368501663208, "learning_rate": 1.9576832656550545e-05, "loss": 0.5698, "step": 2857 }, { "epoch": 1.8276964899656192, "grad_norm": 2.3309435844421387, "learning_rate": 1.9566146612524044e-05, "loss": 0.5041, "step": 2858 }, { "epoch": 1.828336131766211, "grad_norm": 2.438725471496582, "learning_rate": 1.9555460568497543e-05, "loss": 0.4812, "step": 2859 }, { "epoch": 1.8289757735668026, "grad_norm": 1.9939138889312744, "learning_rate": 1.954477452447104e-05, "loss": 0.4068, "step": 2860 }, { "epoch": 1.8296154153673942, "grad_norm": 2.1259148120880127, "learning_rate": 1.953408848044454e-05, "loss": 0.4568, "step": 2861 }, { "epoch": 1.830255057167986, "grad_norm": 2.136159896850586, "learning_rate": 1.9523402436418038e-05, "loss": 0.4804, "step": 2862 }, { "epoch": 1.8308946989685775, "grad_norm": 2.6476261615753174, "learning_rate": 1.9512716392391537e-05, "loss": 0.547, "step": 2863 }, { "epoch": 1.8315343407691693, "grad_norm": 2.4074833393096924, "learning_rate": 1.9502030348365037e-05, "loss": 0.4942, "step": 2864 }, { "epoch": 1.832173982569761, "grad_norm": 2.452183485031128, "learning_rate": 1.9491344304338536e-05, "loss": 0.5082, "step": 2865 }, { "epoch": 1.8328136243703526, "grad_norm": 2.49965500831604, "learning_rate": 1.9480658260312035e-05, "loss": 0.5594, "step": 2866 }, { "epoch": 1.8334532661709444, "grad_norm": 2.890207529067993, "learning_rate": 1.946997221628553e-05, "loss": 0.6236, "step": 2867 }, { "epoch": 1.8340929079715358, "grad_norm": 2.6452999114990234, "learning_rate": 1.945928617225903e-05, "loss": 0.5172, "step": 2868 }, { "epoch": 1.8347325497721276, "grad_norm": 2.1806747913360596, "learning_rate": 1.944860012823253e-05, "loss": 0.5026, "step": 2869 }, { "epoch": 1.8353721915727192, "grad_norm": 2.406280994415283, "learning_rate": 1.9437914084206026e-05, "loss": 0.5113, "step": 2870 }, { "epoch": 1.8360118333733109, "grad_norm": 2.241525650024414, "learning_rate": 1.9427228040179525e-05, "loss": 0.4731, "step": 2871 }, { "epoch": 1.8366514751739027, "grad_norm": 2.9569907188415527, "learning_rate": 1.9416541996153025e-05, "loss": 0.6266, "step": 2872 }, { "epoch": 1.8372911169744943, "grad_norm": 2.120638370513916, "learning_rate": 1.9405855952126524e-05, "loss": 0.4776, "step": 2873 }, { "epoch": 1.837930758775086, "grad_norm": 2.5313446521759033, "learning_rate": 1.9395169908100024e-05, "loss": 0.5621, "step": 2874 }, { "epoch": 1.8385704005756778, "grad_norm": 2.3138656616210938, "learning_rate": 1.9384483864073523e-05, "loss": 0.4946, "step": 2875 }, { "epoch": 1.8392100423762692, "grad_norm": 2.272691011428833, "learning_rate": 1.937379782004702e-05, "loss": 0.504, "step": 2876 }, { "epoch": 1.839849684176861, "grad_norm": 2.0644941329956055, "learning_rate": 1.9363111776020518e-05, "loss": 0.4001, "step": 2877 }, { "epoch": 1.8404893259774526, "grad_norm": 2.3746023178100586, "learning_rate": 1.9352425731994018e-05, "loss": 0.482, "step": 2878 }, { "epoch": 1.8411289677780442, "grad_norm": 2.5728492736816406, "learning_rate": 1.9341739687967517e-05, "loss": 0.5322, "step": 2879 }, { "epoch": 1.841768609578636, "grad_norm": 2.387606620788574, "learning_rate": 1.9331053643941013e-05, "loss": 0.5333, "step": 2880 }, { "epoch": 1.8424082513792275, "grad_norm": 2.3684723377227783, "learning_rate": 1.9320367599914512e-05, "loss": 0.5318, "step": 2881 }, { "epoch": 1.8430478931798193, "grad_norm": 2.52715802192688, "learning_rate": 1.930968155588801e-05, "loss": 0.6003, "step": 2882 }, { "epoch": 1.843687534980411, "grad_norm": 2.1936612129211426, "learning_rate": 1.9298995511861508e-05, "loss": 0.502, "step": 2883 }, { "epoch": 1.8443271767810026, "grad_norm": 2.4667599201202393, "learning_rate": 1.9288309467835007e-05, "loss": 0.5527, "step": 2884 }, { "epoch": 1.8449668185815944, "grad_norm": 2.4780595302581787, "learning_rate": 1.9277623423808506e-05, "loss": 0.5833, "step": 2885 }, { "epoch": 1.845606460382186, "grad_norm": 2.8425557613372803, "learning_rate": 1.9266937379782006e-05, "loss": 0.6324, "step": 2886 }, { "epoch": 1.8462461021827776, "grad_norm": 2.422700881958008, "learning_rate": 1.9256251335755505e-05, "loss": 0.517, "step": 2887 }, { "epoch": 1.8468857439833695, "grad_norm": 2.296245813369751, "learning_rate": 1.9245565291729004e-05, "loss": 0.5092, "step": 2888 }, { "epoch": 1.8475253857839609, "grad_norm": 2.169027328491211, "learning_rate": 1.92348792477025e-05, "loss": 0.5144, "step": 2889 }, { "epoch": 1.8481650275845527, "grad_norm": 2.3023126125335693, "learning_rate": 1.9224193203676e-05, "loss": 0.5187, "step": 2890 }, { "epoch": 1.8488046693851443, "grad_norm": 2.524099349975586, "learning_rate": 1.92135071596495e-05, "loss": 0.5299, "step": 2891 }, { "epoch": 1.849444311185736, "grad_norm": 2.147122383117676, "learning_rate": 1.9202821115622995e-05, "loss": 0.4887, "step": 2892 }, { "epoch": 1.8500839529863278, "grad_norm": 2.1998541355133057, "learning_rate": 1.9192135071596494e-05, "loss": 0.499, "step": 2893 }, { "epoch": 1.8507235947869192, "grad_norm": 2.1991591453552246, "learning_rate": 1.9181449027569994e-05, "loss": 0.5174, "step": 2894 }, { "epoch": 1.851363236587511, "grad_norm": 2.147448778152466, "learning_rate": 1.9170762983543493e-05, "loss": 0.4673, "step": 2895 }, { "epoch": 1.8520028783881026, "grad_norm": 2.2695560455322266, "learning_rate": 1.9160076939516993e-05, "loss": 0.5346, "step": 2896 }, { "epoch": 1.8526425201886942, "grad_norm": 2.296457290649414, "learning_rate": 1.9149390895490492e-05, "loss": 0.5016, "step": 2897 }, { "epoch": 1.853282161989286, "grad_norm": 2.324726104736328, "learning_rate": 1.913870485146399e-05, "loss": 0.521, "step": 2898 }, { "epoch": 1.8539218037898777, "grad_norm": 2.3072283267974854, "learning_rate": 1.9128018807437487e-05, "loss": 0.5735, "step": 2899 }, { "epoch": 1.8545614455904693, "grad_norm": 2.0744760036468506, "learning_rate": 1.9117332763410987e-05, "loss": 0.4706, "step": 2900 }, { "epoch": 1.8552010873910612, "grad_norm": 2.046598434448242, "learning_rate": 1.9106646719384486e-05, "loss": 0.4366, "step": 2901 }, { "epoch": 1.8558407291916525, "grad_norm": 2.2961080074310303, "learning_rate": 1.9095960675357982e-05, "loss": 0.4851, "step": 2902 }, { "epoch": 1.8564803709922444, "grad_norm": 3.0587995052337646, "learning_rate": 1.908527463133148e-05, "loss": 0.6864, "step": 2903 }, { "epoch": 1.857120012792836, "grad_norm": 2.288538694381714, "learning_rate": 1.907458858730498e-05, "loss": 0.4571, "step": 2904 }, { "epoch": 1.8577596545934276, "grad_norm": 2.589794874191284, "learning_rate": 1.9063902543278477e-05, "loss": 0.5282, "step": 2905 }, { "epoch": 1.8583992963940195, "grad_norm": 2.2429935932159424, "learning_rate": 1.9053216499251976e-05, "loss": 0.4864, "step": 2906 }, { "epoch": 1.8590389381946109, "grad_norm": 2.186279058456421, "learning_rate": 1.9042530455225475e-05, "loss": 0.4685, "step": 2907 }, { "epoch": 1.8596785799952027, "grad_norm": 2.2375638484954834, "learning_rate": 1.9031844411198975e-05, "loss": 0.527, "step": 2908 }, { "epoch": 1.8603182217957943, "grad_norm": 2.140592098236084, "learning_rate": 1.9021158367172474e-05, "loss": 0.4668, "step": 2909 }, { "epoch": 1.860957863596386, "grad_norm": 2.629301071166992, "learning_rate": 1.9010472323145973e-05, "loss": 0.5853, "step": 2910 }, { "epoch": 1.8615975053969778, "grad_norm": 2.436850070953369, "learning_rate": 1.8999786279119473e-05, "loss": 0.4926, "step": 2911 }, { "epoch": 1.8622371471975694, "grad_norm": 2.32812237739563, "learning_rate": 1.898910023509297e-05, "loss": 0.4996, "step": 2912 }, { "epoch": 1.862876788998161, "grad_norm": 2.576978921890259, "learning_rate": 1.8978414191066468e-05, "loss": 0.5053, "step": 2913 }, { "epoch": 1.8635164307987528, "grad_norm": 2.375523567199707, "learning_rate": 1.8967728147039967e-05, "loss": 0.5484, "step": 2914 }, { "epoch": 1.8641560725993442, "grad_norm": 2.790060520172119, "learning_rate": 1.8957042103013463e-05, "loss": 0.6171, "step": 2915 }, { "epoch": 1.864795714399936, "grad_norm": 2.5728256702423096, "learning_rate": 1.8946356058986963e-05, "loss": 0.5514, "step": 2916 }, { "epoch": 1.8654353562005277, "grad_norm": 2.630537986755371, "learning_rate": 1.8935670014960462e-05, "loss": 0.5538, "step": 2917 }, { "epoch": 1.8660749980011193, "grad_norm": 2.4287662506103516, "learning_rate": 1.892498397093396e-05, "loss": 0.4809, "step": 2918 }, { "epoch": 1.8667146398017112, "grad_norm": 2.2396273612976074, "learning_rate": 1.891429792690746e-05, "loss": 0.4775, "step": 2919 }, { "epoch": 1.8673542816023025, "grad_norm": 2.4905190467834473, "learning_rate": 1.890361188288096e-05, "loss": 0.5294, "step": 2920 }, { "epoch": 1.8679939234028944, "grad_norm": 2.278452157974243, "learning_rate": 1.889292583885446e-05, "loss": 0.5034, "step": 2921 }, { "epoch": 1.868633565203486, "grad_norm": 2.7109076976776123, "learning_rate": 1.8882239794827956e-05, "loss": 0.5633, "step": 2922 }, { "epoch": 1.8692732070040776, "grad_norm": 2.3873202800750732, "learning_rate": 1.8871553750801455e-05, "loss": 0.5639, "step": 2923 }, { "epoch": 1.8699128488046695, "grad_norm": 2.337348222732544, "learning_rate": 1.8860867706774954e-05, "loss": 0.5228, "step": 2924 }, { "epoch": 1.870552490605261, "grad_norm": 2.482011556625366, "learning_rate": 1.885018166274845e-05, "loss": 0.5571, "step": 2925 }, { "epoch": 1.8711921324058527, "grad_norm": 2.2913031578063965, "learning_rate": 1.883949561872195e-05, "loss": 0.5206, "step": 2926 }, { "epoch": 1.8718317742064445, "grad_norm": 2.7040319442749023, "learning_rate": 1.882880957469545e-05, "loss": 0.6375, "step": 2927 }, { "epoch": 1.872471416007036, "grad_norm": 2.2623605728149414, "learning_rate": 1.8818123530668945e-05, "loss": 0.4861, "step": 2928 }, { "epoch": 1.8731110578076278, "grad_norm": 2.1366677284240723, "learning_rate": 1.8807437486642444e-05, "loss": 0.4707, "step": 2929 }, { "epoch": 1.8737506996082194, "grad_norm": 2.506088972091675, "learning_rate": 1.8796751442615944e-05, "loss": 0.5611, "step": 2930 }, { "epoch": 1.874390341408811, "grad_norm": 2.580218553543091, "learning_rate": 1.8786065398589443e-05, "loss": 0.4617, "step": 2931 }, { "epoch": 1.8750299832094028, "grad_norm": 2.405839443206787, "learning_rate": 1.8775379354562942e-05, "loss": 0.5625, "step": 2932 }, { "epoch": 1.8756696250099945, "grad_norm": 2.0239696502685547, "learning_rate": 1.8764693310536442e-05, "loss": 0.4668, "step": 2933 }, { "epoch": 1.876309266810586, "grad_norm": 2.750504732131958, "learning_rate": 1.8754007266509938e-05, "loss": 0.5686, "step": 2934 }, { "epoch": 1.8769489086111777, "grad_norm": 2.5134050846099854, "learning_rate": 1.8743321222483437e-05, "loss": 0.489, "step": 2935 }, { "epoch": 1.8775885504117693, "grad_norm": 2.1368775367736816, "learning_rate": 1.8732635178456937e-05, "loss": 0.478, "step": 2936 }, { "epoch": 1.8782281922123611, "grad_norm": 2.401207208633423, "learning_rate": 1.8721949134430436e-05, "loss": 0.514, "step": 2937 }, { "epoch": 1.8788678340129528, "grad_norm": 2.598897695541382, "learning_rate": 1.8711263090403932e-05, "loss": 0.6011, "step": 2938 }, { "epoch": 1.8795074758135444, "grad_norm": 2.474565267562866, "learning_rate": 1.870057704637743e-05, "loss": 0.5442, "step": 2939 }, { "epoch": 1.8801471176141362, "grad_norm": 2.3614892959594727, "learning_rate": 1.868989100235093e-05, "loss": 0.5204, "step": 2940 }, { "epoch": 1.8807867594147276, "grad_norm": 2.716115951538086, "learning_rate": 1.867920495832443e-05, "loss": 0.5508, "step": 2941 }, { "epoch": 1.8814264012153195, "grad_norm": 2.105520486831665, "learning_rate": 1.866851891429793e-05, "loss": 0.4866, "step": 2942 }, { "epoch": 1.882066043015911, "grad_norm": 2.2073347568511963, "learning_rate": 1.865783287027143e-05, "loss": 0.5264, "step": 2943 }, { "epoch": 1.8827056848165027, "grad_norm": 2.342784881591797, "learning_rate": 1.8647146826244925e-05, "loss": 0.5095, "step": 2944 }, { "epoch": 1.8833453266170945, "grad_norm": 2.5862765312194824, "learning_rate": 1.8636460782218424e-05, "loss": 0.5496, "step": 2945 }, { "epoch": 1.8839849684176861, "grad_norm": 2.324101686477661, "learning_rate": 1.8625774738191923e-05, "loss": 0.5267, "step": 2946 }, { "epoch": 1.8846246102182778, "grad_norm": 2.2458910942077637, "learning_rate": 1.861508869416542e-05, "loss": 0.498, "step": 2947 }, { "epoch": 1.8852642520188694, "grad_norm": 1.9799495935440063, "learning_rate": 1.860440265013892e-05, "loss": 0.4484, "step": 2948 }, { "epoch": 1.885903893819461, "grad_norm": 2.2013511657714844, "learning_rate": 1.8593716606112418e-05, "loss": 0.4924, "step": 2949 }, { "epoch": 1.8865435356200528, "grad_norm": 2.6202101707458496, "learning_rate": 1.8583030562085917e-05, "loss": 0.6297, "step": 2950 }, { "epoch": 1.8871831774206445, "grad_norm": 2.379664659500122, "learning_rate": 1.8572344518059413e-05, "loss": 0.5283, "step": 2951 }, { "epoch": 1.887822819221236, "grad_norm": 2.2940313816070557, "learning_rate": 1.8561658474032913e-05, "loss": 0.4914, "step": 2952 }, { "epoch": 1.888462461021828, "grad_norm": 2.6438848972320557, "learning_rate": 1.8550972430006412e-05, "loss": 0.5502, "step": 2953 }, { "epoch": 1.8891021028224193, "grad_norm": 2.051809549331665, "learning_rate": 1.854028638597991e-05, "loss": 0.4924, "step": 2954 }, { "epoch": 1.8897417446230111, "grad_norm": 2.2035608291625977, "learning_rate": 1.852960034195341e-05, "loss": 0.5055, "step": 2955 }, { "epoch": 1.8903813864236028, "grad_norm": 2.3531949520111084, "learning_rate": 1.851891429792691e-05, "loss": 0.5324, "step": 2956 }, { "epoch": 1.8910210282241944, "grad_norm": 2.36861515045166, "learning_rate": 1.8508228253900406e-05, "loss": 0.548, "step": 2957 }, { "epoch": 1.8916606700247862, "grad_norm": 2.393678903579712, "learning_rate": 1.8497542209873906e-05, "loss": 0.4805, "step": 2958 }, { "epoch": 1.8923003118253778, "grad_norm": 2.4288806915283203, "learning_rate": 1.8486856165847405e-05, "loss": 0.5568, "step": 2959 }, { "epoch": 1.8929399536259695, "grad_norm": 2.0793449878692627, "learning_rate": 1.84761701218209e-05, "loss": 0.4437, "step": 2960 }, { "epoch": 1.8935795954265613, "grad_norm": 2.4150569438934326, "learning_rate": 1.84654840777944e-05, "loss": 0.4948, "step": 2961 }, { "epoch": 1.8942192372271527, "grad_norm": 2.2338144779205322, "learning_rate": 1.84547980337679e-05, "loss": 0.4872, "step": 2962 }, { "epoch": 1.8948588790277445, "grad_norm": 2.272186756134033, "learning_rate": 1.84441119897414e-05, "loss": 0.5006, "step": 2963 }, { "epoch": 1.8954985208283361, "grad_norm": 2.1584689617156982, "learning_rate": 1.84334259457149e-05, "loss": 0.4713, "step": 2964 }, { "epoch": 1.8961381626289278, "grad_norm": 2.4406025409698486, "learning_rate": 1.8422739901688398e-05, "loss": 0.5635, "step": 2965 }, { "epoch": 1.8967778044295196, "grad_norm": 2.464693546295166, "learning_rate": 1.8412053857661897e-05, "loss": 0.5373, "step": 2966 }, { "epoch": 1.897417446230111, "grad_norm": 2.3238608837127686, "learning_rate": 1.8401367813635393e-05, "loss": 0.4669, "step": 2967 }, { "epoch": 1.8980570880307028, "grad_norm": 2.6213347911834717, "learning_rate": 1.8390681769608892e-05, "loss": 0.5633, "step": 2968 }, { "epoch": 1.8986967298312944, "grad_norm": 2.555800437927246, "learning_rate": 1.8379995725582392e-05, "loss": 0.5642, "step": 2969 }, { "epoch": 1.899336371631886, "grad_norm": 2.4231338500976562, "learning_rate": 1.8369309681555888e-05, "loss": 0.4436, "step": 2970 }, { "epoch": 1.899976013432478, "grad_norm": 2.431324005126953, "learning_rate": 1.8358623637529387e-05, "loss": 0.519, "step": 2971 }, { "epoch": 1.9006156552330695, "grad_norm": 2.5057456493377686, "learning_rate": 1.8347937593502886e-05, "loss": 0.5272, "step": 2972 }, { "epoch": 1.9012552970336611, "grad_norm": 2.324465751647949, "learning_rate": 1.8337251549476382e-05, "loss": 0.5113, "step": 2973 }, { "epoch": 1.901894938834253, "grad_norm": 2.5816757678985596, "learning_rate": 1.8326565505449882e-05, "loss": 0.576, "step": 2974 }, { "epoch": 1.9025345806348444, "grad_norm": 2.0733630657196045, "learning_rate": 1.831587946142338e-05, "loss": 0.4283, "step": 2975 }, { "epoch": 1.9031742224354362, "grad_norm": 2.216127872467041, "learning_rate": 1.830519341739688e-05, "loss": 0.4933, "step": 2976 }, { "epoch": 1.9038138642360278, "grad_norm": 2.7155752182006836, "learning_rate": 1.829450737337038e-05, "loss": 0.5388, "step": 2977 }, { "epoch": 1.9044535060366194, "grad_norm": 2.3714749813079834, "learning_rate": 1.828382132934388e-05, "loss": 0.5123, "step": 2978 }, { "epoch": 1.9050931478372113, "grad_norm": 2.344045877456665, "learning_rate": 1.827313528531738e-05, "loss": 0.477, "step": 2979 }, { "epoch": 1.9057327896378027, "grad_norm": 2.5849430561065674, "learning_rate": 1.8262449241290875e-05, "loss": 0.524, "step": 2980 }, { "epoch": 1.9063724314383945, "grad_norm": 2.4501564502716064, "learning_rate": 1.8251763197264374e-05, "loss": 0.555, "step": 2981 }, { "epoch": 1.9070120732389861, "grad_norm": 1.8876103162765503, "learning_rate": 1.8241077153237873e-05, "loss": 0.4177, "step": 2982 }, { "epoch": 1.9076517150395778, "grad_norm": 2.443512201309204, "learning_rate": 1.823039110921137e-05, "loss": 0.5273, "step": 2983 }, { "epoch": 1.9082913568401696, "grad_norm": 2.362765312194824, "learning_rate": 1.821970506518487e-05, "loss": 0.5382, "step": 2984 }, { "epoch": 1.9089309986407612, "grad_norm": 2.348677158355713, "learning_rate": 1.8209019021158368e-05, "loss": 0.5361, "step": 2985 }, { "epoch": 1.9095706404413528, "grad_norm": 2.2172768115997314, "learning_rate": 1.8198332977131864e-05, "loss": 0.4562, "step": 2986 }, { "epoch": 1.9102102822419447, "grad_norm": 2.3510067462921143, "learning_rate": 1.8187646933105367e-05, "loss": 0.5394, "step": 2987 }, { "epoch": 1.910849924042536, "grad_norm": 2.348907709121704, "learning_rate": 1.8176960889078866e-05, "loss": 0.5132, "step": 2988 }, { "epoch": 1.911489565843128, "grad_norm": 2.321542739868164, "learning_rate": 1.8166274845052362e-05, "loss": 0.5038, "step": 2989 }, { "epoch": 1.9121292076437195, "grad_norm": 2.314908027648926, "learning_rate": 1.815558880102586e-05, "loss": 0.4966, "step": 2990 }, { "epoch": 1.9127688494443111, "grad_norm": 2.22035813331604, "learning_rate": 1.814490275699936e-05, "loss": 0.4783, "step": 2991 }, { "epoch": 1.913408491244903, "grad_norm": 2.2341954708099365, "learning_rate": 1.813421671297286e-05, "loss": 0.5306, "step": 2992 }, { "epoch": 1.9140481330454944, "grad_norm": 2.263852119445801, "learning_rate": 1.8123530668946356e-05, "loss": 0.5019, "step": 2993 }, { "epoch": 1.9146877748460862, "grad_norm": 2.124631404876709, "learning_rate": 1.8112844624919855e-05, "loss": 0.4434, "step": 2994 }, { "epoch": 1.9153274166466778, "grad_norm": 2.5393638610839844, "learning_rate": 1.8102158580893355e-05, "loss": 0.5231, "step": 2995 }, { "epoch": 1.9159670584472694, "grad_norm": 2.1628592014312744, "learning_rate": 1.809147253686685e-05, "loss": 0.4982, "step": 2996 }, { "epoch": 1.9166067002478613, "grad_norm": 2.546919584274292, "learning_rate": 1.808078649284035e-05, "loss": 0.59, "step": 2997 }, { "epoch": 1.917246342048453, "grad_norm": 2.281437873840332, "learning_rate": 1.807010044881385e-05, "loss": 0.5009, "step": 2998 }, { "epoch": 1.9178859838490445, "grad_norm": 2.231894016265869, "learning_rate": 1.805941440478735e-05, "loss": 0.5017, "step": 2999 }, { "epoch": 1.9185256256496364, "grad_norm": 2.126573085784912, "learning_rate": 1.8048728360760848e-05, "loss": 0.4442, "step": 3000 }, { "epoch": 1.9191652674502278, "grad_norm": 2.1402084827423096, "learning_rate": 1.8038042316734348e-05, "loss": 0.4721, "step": 3001 }, { "epoch": 1.9198049092508196, "grad_norm": 2.5384037494659424, "learning_rate": 1.8027356272707844e-05, "loss": 0.5233, "step": 3002 }, { "epoch": 1.9204445510514112, "grad_norm": 2.306366443634033, "learning_rate": 1.8016670228681343e-05, "loss": 0.503, "step": 3003 }, { "epoch": 1.9210841928520028, "grad_norm": 2.258857250213623, "learning_rate": 1.8005984184654842e-05, "loss": 0.5245, "step": 3004 }, { "epoch": 1.9217238346525947, "grad_norm": 2.570263385772705, "learning_rate": 1.799529814062834e-05, "loss": 0.5526, "step": 3005 }, { "epoch": 1.922363476453186, "grad_norm": 2.4310100078582764, "learning_rate": 1.7984612096601838e-05, "loss": 0.4631, "step": 3006 }, { "epoch": 1.923003118253778, "grad_norm": 2.628833293914795, "learning_rate": 1.7973926052575337e-05, "loss": 0.5495, "step": 3007 }, { "epoch": 1.9236427600543695, "grad_norm": 2.5494179725646973, "learning_rate": 1.7963240008548836e-05, "loss": 0.5466, "step": 3008 }, { "epoch": 1.9242824018549611, "grad_norm": 2.444270610809326, "learning_rate": 1.7952553964522332e-05, "loss": 0.5158, "step": 3009 }, { "epoch": 1.924922043655553, "grad_norm": 1.8992811441421509, "learning_rate": 1.7941867920495835e-05, "loss": 0.4101, "step": 3010 }, { "epoch": 1.9255616854561446, "grad_norm": 2.1182570457458496, "learning_rate": 1.7931181876469334e-05, "loss": 0.4505, "step": 3011 }, { "epoch": 1.9262013272567362, "grad_norm": 2.212345600128174, "learning_rate": 1.792049583244283e-05, "loss": 0.538, "step": 3012 }, { "epoch": 1.926840969057328, "grad_norm": 2.1981735229492188, "learning_rate": 1.790980978841633e-05, "loss": 0.477, "step": 3013 }, { "epoch": 1.9274806108579194, "grad_norm": 2.655529260635376, "learning_rate": 1.789912374438983e-05, "loss": 0.5713, "step": 3014 }, { "epoch": 1.9281202526585113, "grad_norm": 2.3781497478485107, "learning_rate": 1.7888437700363325e-05, "loss": 0.4905, "step": 3015 }, { "epoch": 1.928759894459103, "grad_norm": 2.2360687255859375, "learning_rate": 1.7877751656336824e-05, "loss": 0.4368, "step": 3016 }, { "epoch": 1.9293995362596945, "grad_norm": 2.6301515102386475, "learning_rate": 1.7867065612310324e-05, "loss": 0.5156, "step": 3017 }, { "epoch": 1.9300391780602864, "grad_norm": 2.265232563018799, "learning_rate": 1.785637956828382e-05, "loss": 0.5159, "step": 3018 }, { "epoch": 1.9306788198608777, "grad_norm": 2.2301290035247803, "learning_rate": 1.784569352425732e-05, "loss": 0.4527, "step": 3019 }, { "epoch": 1.9313184616614696, "grad_norm": 2.714449405670166, "learning_rate": 1.783500748023082e-05, "loss": 0.5691, "step": 3020 }, { "epoch": 1.9319581034620612, "grad_norm": 2.274967908859253, "learning_rate": 1.7824321436204318e-05, "loss": 0.4735, "step": 3021 }, { "epoch": 1.9325977452626528, "grad_norm": 2.453223943710327, "learning_rate": 1.7813635392177817e-05, "loss": 0.5531, "step": 3022 }, { "epoch": 1.9332373870632447, "grad_norm": 2.511776924133301, "learning_rate": 1.7802949348151317e-05, "loss": 0.5687, "step": 3023 }, { "epoch": 1.9338770288638363, "grad_norm": 2.385563611984253, "learning_rate": 1.7792263304124816e-05, "loss": 0.5505, "step": 3024 }, { "epoch": 1.934516670664428, "grad_norm": 2.4991912841796875, "learning_rate": 1.7781577260098312e-05, "loss": 0.5437, "step": 3025 }, { "epoch": 1.9351563124650197, "grad_norm": 2.4782683849334717, "learning_rate": 1.777089121607181e-05, "loss": 0.5373, "step": 3026 }, { "epoch": 1.9357959542656111, "grad_norm": 2.317281723022461, "learning_rate": 1.776020517204531e-05, "loss": 0.4439, "step": 3027 }, { "epoch": 1.936435596066203, "grad_norm": 2.05065655708313, "learning_rate": 1.7749519128018807e-05, "loss": 0.427, "step": 3028 }, { "epoch": 1.9370752378667946, "grad_norm": 2.3775722980499268, "learning_rate": 1.7738833083992306e-05, "loss": 0.4866, "step": 3029 }, { "epoch": 1.9377148796673862, "grad_norm": 2.2226779460906982, "learning_rate": 1.7728147039965805e-05, "loss": 0.4843, "step": 3030 }, { "epoch": 1.938354521467978, "grad_norm": 2.216209650039673, "learning_rate": 1.77174609959393e-05, "loss": 0.4761, "step": 3031 }, { "epoch": 1.9389941632685694, "grad_norm": 2.2940866947174072, "learning_rate": 1.77067749519128e-05, "loss": 0.4643, "step": 3032 }, { "epoch": 1.9396338050691613, "grad_norm": 2.479513168334961, "learning_rate": 1.7696088907886303e-05, "loss": 0.531, "step": 3033 }, { "epoch": 1.940273446869753, "grad_norm": 2.4281535148620605, "learning_rate": 1.7685402863859803e-05, "loss": 0.5095, "step": 3034 }, { "epoch": 1.9409130886703445, "grad_norm": 2.246185779571533, "learning_rate": 1.76747168198333e-05, "loss": 0.479, "step": 3035 }, { "epoch": 1.9415527304709363, "grad_norm": 2.2305679321289062, "learning_rate": 1.7664030775806798e-05, "loss": 0.5134, "step": 3036 }, { "epoch": 1.942192372271528, "grad_norm": 2.1311020851135254, "learning_rate": 1.7653344731780298e-05, "loss": 0.4557, "step": 3037 }, { "epoch": 1.9428320140721196, "grad_norm": 2.451103448867798, "learning_rate": 1.7642658687753794e-05, "loss": 0.506, "step": 3038 }, { "epoch": 1.9434716558727114, "grad_norm": 2.1855053901672363, "learning_rate": 1.7631972643727293e-05, "loss": 0.4452, "step": 3039 }, { "epoch": 1.9441112976733028, "grad_norm": 2.606523036956787, "learning_rate": 1.7621286599700792e-05, "loss": 0.544, "step": 3040 }, { "epoch": 1.9447509394738947, "grad_norm": 2.280884265899658, "learning_rate": 1.7610600555674288e-05, "loss": 0.4756, "step": 3041 }, { "epoch": 1.9453905812744863, "grad_norm": 2.6737313270568848, "learning_rate": 1.7599914511647788e-05, "loss": 0.5752, "step": 3042 }, { "epoch": 1.946030223075078, "grad_norm": 2.865755319595337, "learning_rate": 1.7589228467621287e-05, "loss": 0.5725, "step": 3043 }, { "epoch": 1.9466698648756697, "grad_norm": 2.591252326965332, "learning_rate": 1.7578542423594786e-05, "loss": 0.5937, "step": 3044 }, { "epoch": 1.9473095066762613, "grad_norm": 2.2542731761932373, "learning_rate": 1.7567856379568286e-05, "loss": 0.4685, "step": 3045 }, { "epoch": 1.947949148476853, "grad_norm": 2.729081630706787, "learning_rate": 1.7557170335541785e-05, "loss": 0.5462, "step": 3046 }, { "epoch": 1.9485887902774446, "grad_norm": 2.0769948959350586, "learning_rate": 1.754648429151528e-05, "loss": 0.4565, "step": 3047 }, { "epoch": 1.9492284320780362, "grad_norm": 2.435673236846924, "learning_rate": 1.753579824748878e-05, "loss": 0.5068, "step": 3048 }, { "epoch": 1.949868073878628, "grad_norm": 2.4823808670043945, "learning_rate": 1.752511220346228e-05, "loss": 0.5019, "step": 3049 }, { "epoch": 1.9505077156792197, "grad_norm": 2.8090693950653076, "learning_rate": 1.751442615943578e-05, "loss": 0.5619, "step": 3050 }, { "epoch": 1.9511473574798113, "grad_norm": 2.2274117469787598, "learning_rate": 1.7503740115409275e-05, "loss": 0.4628, "step": 3051 }, { "epoch": 1.9517869992804031, "grad_norm": 2.081827402114868, "learning_rate": 1.7493054071382774e-05, "loss": 0.4409, "step": 3052 }, { "epoch": 1.9524266410809945, "grad_norm": 2.340615749359131, "learning_rate": 1.7482368027356274e-05, "loss": 0.4745, "step": 3053 }, { "epoch": 1.9530662828815863, "grad_norm": 2.2291791439056396, "learning_rate": 1.747168198332977e-05, "loss": 0.4801, "step": 3054 }, { "epoch": 1.953705924682178, "grad_norm": 2.5104756355285645, "learning_rate": 1.746099593930327e-05, "loss": 0.5641, "step": 3055 }, { "epoch": 1.9543455664827696, "grad_norm": 2.5856759548187256, "learning_rate": 1.7450309895276772e-05, "loss": 0.5749, "step": 3056 }, { "epoch": 1.9549852082833614, "grad_norm": 2.6332132816314697, "learning_rate": 1.7439623851250268e-05, "loss": 0.5672, "step": 3057 }, { "epoch": 1.955624850083953, "grad_norm": 2.5158519744873047, "learning_rate": 1.7428937807223767e-05, "loss": 0.5407, "step": 3058 }, { "epoch": 1.9562644918845447, "grad_norm": 2.2477149963378906, "learning_rate": 1.7418251763197267e-05, "loss": 0.4761, "step": 3059 }, { "epoch": 1.9569041336851363, "grad_norm": 2.567655563354492, "learning_rate": 1.7407565719170763e-05, "loss": 0.5278, "step": 3060 }, { "epoch": 1.9575437754857279, "grad_norm": 2.1150951385498047, "learning_rate": 1.7396879675144262e-05, "loss": 0.4789, "step": 3061 }, { "epoch": 1.9581834172863197, "grad_norm": 2.217879056930542, "learning_rate": 1.738619363111776e-05, "loss": 0.451, "step": 3062 }, { "epoch": 1.9588230590869113, "grad_norm": 2.183075189590454, "learning_rate": 1.737550758709126e-05, "loss": 0.4829, "step": 3063 }, { "epoch": 1.959462700887503, "grad_norm": 2.404634714126587, "learning_rate": 1.7364821543064757e-05, "loss": 0.4893, "step": 3064 }, { "epoch": 1.9601023426880948, "grad_norm": 2.8002612590789795, "learning_rate": 1.7354135499038256e-05, "loss": 0.5211, "step": 3065 }, { "epoch": 1.9607419844886862, "grad_norm": 2.499987840652466, "learning_rate": 1.7343449455011755e-05, "loss": 0.5745, "step": 3066 }, { "epoch": 1.961381626289278, "grad_norm": 2.4582366943359375, "learning_rate": 1.7332763410985255e-05, "loss": 0.4864, "step": 3067 }, { "epoch": 1.9620212680898697, "grad_norm": 2.733107805252075, "learning_rate": 1.7322077366958754e-05, "loss": 0.5544, "step": 3068 }, { "epoch": 1.9626609098904613, "grad_norm": 2.6358394622802734, "learning_rate": 1.7311391322932253e-05, "loss": 0.5606, "step": 3069 }, { "epoch": 1.963300551691053, "grad_norm": 1.966907262802124, "learning_rate": 1.730070527890575e-05, "loss": 0.4333, "step": 3070 }, { "epoch": 1.9639401934916447, "grad_norm": 2.583651542663574, "learning_rate": 1.729001923487925e-05, "loss": 0.5282, "step": 3071 }, { "epoch": 1.9645798352922363, "grad_norm": 2.4442920684814453, "learning_rate": 1.7279333190852748e-05, "loss": 0.5422, "step": 3072 }, { "epoch": 1.9652194770928282, "grad_norm": 2.4457221031188965, "learning_rate": 1.7268647146826244e-05, "loss": 0.4959, "step": 3073 }, { "epoch": 1.9658591188934196, "grad_norm": 2.5622451305389404, "learning_rate": 1.7257961102799743e-05, "loss": 0.5233, "step": 3074 }, { "epoch": 1.9664987606940114, "grad_norm": 2.5282044410705566, "learning_rate": 1.7247275058773243e-05, "loss": 0.5662, "step": 3075 }, { "epoch": 1.967138402494603, "grad_norm": 2.5381572246551514, "learning_rate": 1.7236589014746742e-05, "loss": 0.5321, "step": 3076 }, { "epoch": 1.9677780442951947, "grad_norm": 2.80287504196167, "learning_rate": 1.7225902970720238e-05, "loss": 0.5776, "step": 3077 }, { "epoch": 1.9684176860957865, "grad_norm": 2.027730941772461, "learning_rate": 1.7215216926693737e-05, "loss": 0.4621, "step": 3078 }, { "epoch": 1.9690573278963779, "grad_norm": 2.3324129581451416, "learning_rate": 1.720453088266724e-05, "loss": 0.5041, "step": 3079 }, { "epoch": 1.9696969696969697, "grad_norm": 2.5484001636505127, "learning_rate": 1.7193844838640736e-05, "loss": 0.5477, "step": 3080 }, { "epoch": 1.9703366114975613, "grad_norm": 2.2478559017181396, "learning_rate": 1.7183158794614236e-05, "loss": 0.4545, "step": 3081 }, { "epoch": 1.970976253298153, "grad_norm": 2.5246973037719727, "learning_rate": 1.7172472750587735e-05, "loss": 0.5894, "step": 3082 }, { "epoch": 1.9716158950987448, "grad_norm": 2.2863972187042236, "learning_rate": 1.716178670656123e-05, "loss": 0.5205, "step": 3083 }, { "epoch": 1.9722555368993364, "grad_norm": 2.898996353149414, "learning_rate": 1.715110066253473e-05, "loss": 0.563, "step": 3084 }, { "epoch": 1.972895178699928, "grad_norm": 2.2894740104675293, "learning_rate": 1.714041461850823e-05, "loss": 0.4931, "step": 3085 }, { "epoch": 1.9735348205005199, "grad_norm": 2.2987220287323, "learning_rate": 1.7129728574481726e-05, "loss": 0.461, "step": 3086 }, { "epoch": 1.9741744623011113, "grad_norm": 2.349090576171875, "learning_rate": 1.7119042530455225e-05, "loss": 0.5559, "step": 3087 }, { "epoch": 1.974814104101703, "grad_norm": 2.413607358932495, "learning_rate": 1.7108356486428724e-05, "loss": 0.5607, "step": 3088 }, { "epoch": 1.9754537459022947, "grad_norm": 2.560260534286499, "learning_rate": 1.7097670442402224e-05, "loss": 0.5358, "step": 3089 }, { "epoch": 1.9760933877028863, "grad_norm": 2.351215124130249, "learning_rate": 1.7086984398375723e-05, "loss": 0.5353, "step": 3090 }, { "epoch": 1.9767330295034782, "grad_norm": 2.2487165927886963, "learning_rate": 1.7076298354349222e-05, "loss": 0.5013, "step": 3091 }, { "epoch": 1.9773726713040696, "grad_norm": 2.1342883110046387, "learning_rate": 1.7065612310322722e-05, "loss": 0.4601, "step": 3092 }, { "epoch": 1.9780123131046614, "grad_norm": 1.9691661596298218, "learning_rate": 1.7054926266296218e-05, "loss": 0.4331, "step": 3093 }, { "epoch": 1.978651954905253, "grad_norm": 2.109966278076172, "learning_rate": 1.7044240222269717e-05, "loss": 0.4633, "step": 3094 }, { "epoch": 1.9792915967058446, "grad_norm": 2.1279499530792236, "learning_rate": 1.7033554178243216e-05, "loss": 0.5282, "step": 3095 }, { "epoch": 1.9799312385064365, "grad_norm": 2.070390224456787, "learning_rate": 1.7022868134216712e-05, "loss": 0.4413, "step": 3096 }, { "epoch": 1.980570880307028, "grad_norm": 2.4855387210845947, "learning_rate": 1.7012182090190212e-05, "loss": 0.5064, "step": 3097 }, { "epoch": 1.9812105221076197, "grad_norm": 2.0367043018341064, "learning_rate": 1.700149604616371e-05, "loss": 0.4512, "step": 3098 }, { "epoch": 1.9818501639082116, "grad_norm": 2.409388542175293, "learning_rate": 1.6990810002137207e-05, "loss": 0.4886, "step": 3099 }, { "epoch": 1.982489805708803, "grad_norm": 2.350985527038574, "learning_rate": 1.6980123958110707e-05, "loss": 0.5295, "step": 3100 }, { "epoch": 1.9831294475093948, "grad_norm": 2.4386706352233887, "learning_rate": 1.6969437914084206e-05, "loss": 0.4977, "step": 3101 }, { "epoch": 1.9837690893099864, "grad_norm": 2.4338319301605225, "learning_rate": 1.6958751870057705e-05, "loss": 0.5428, "step": 3102 }, { "epoch": 1.984408731110578, "grad_norm": 1.9656285047531128, "learning_rate": 1.6948065826031205e-05, "loss": 0.448, "step": 3103 }, { "epoch": 1.9850483729111699, "grad_norm": 2.2694687843322754, "learning_rate": 1.6937379782004704e-05, "loss": 0.5236, "step": 3104 }, { "epoch": 1.9856880147117613, "grad_norm": 2.2327353954315186, "learning_rate": 1.6926693737978203e-05, "loss": 0.4987, "step": 3105 }, { "epoch": 1.986327656512353, "grad_norm": 2.2643015384674072, "learning_rate": 1.69160076939517e-05, "loss": 0.531, "step": 3106 }, { "epoch": 1.9869672983129447, "grad_norm": 2.438274383544922, "learning_rate": 1.69053216499252e-05, "loss": 0.532, "step": 3107 }, { "epoch": 1.9876069401135363, "grad_norm": 2.36454701423645, "learning_rate": 1.6894635605898698e-05, "loss": 0.4898, "step": 3108 }, { "epoch": 1.9882465819141282, "grad_norm": 2.1013450622558594, "learning_rate": 1.6883949561872194e-05, "loss": 0.399, "step": 3109 }, { "epoch": 1.9888862237147198, "grad_norm": 2.293032646179199, "learning_rate": 1.6873263517845693e-05, "loss": 0.5122, "step": 3110 }, { "epoch": 1.9895258655153114, "grad_norm": 2.1009013652801514, "learning_rate": 1.6862577473819193e-05, "loss": 0.457, "step": 3111 }, { "epoch": 1.9901655073159032, "grad_norm": 2.314861536026001, "learning_rate": 1.6851891429792692e-05, "loss": 0.4906, "step": 3112 }, { "epoch": 1.9908051491164946, "grad_norm": 2.2989134788513184, "learning_rate": 1.684120538576619e-05, "loss": 0.432, "step": 3113 }, { "epoch": 1.9914447909170865, "grad_norm": 2.49627685546875, "learning_rate": 1.683051934173969e-05, "loss": 0.469, "step": 3114 }, { "epoch": 1.992084432717678, "grad_norm": 2.0957040786743164, "learning_rate": 1.6819833297713187e-05, "loss": 0.4659, "step": 3115 }, { "epoch": 1.9927240745182697, "grad_norm": 2.485936403274536, "learning_rate": 1.6809147253686686e-05, "loss": 0.5456, "step": 3116 }, { "epoch": 1.9933637163188616, "grad_norm": 2.732510805130005, "learning_rate": 1.6798461209660185e-05, "loss": 0.5705, "step": 3117 }, { "epoch": 1.994003358119453, "grad_norm": 2.1635005474090576, "learning_rate": 1.6787775165633685e-05, "loss": 0.4087, "step": 3118 }, { "epoch": 1.9946429999200448, "grad_norm": 2.3673348426818848, "learning_rate": 1.677708912160718e-05, "loss": 0.5093, "step": 3119 }, { "epoch": 1.9952826417206364, "grad_norm": 2.510932207107544, "learning_rate": 1.676640307758068e-05, "loss": 0.5167, "step": 3120 }, { "epoch": 1.995922283521228, "grad_norm": 2.699578285217285, "learning_rate": 1.675571703355418e-05, "loss": 0.5348, "step": 3121 }, { "epoch": 1.9965619253218199, "grad_norm": 2.4369664192199707, "learning_rate": 1.6745030989527676e-05, "loss": 0.4954, "step": 3122 }, { "epoch": 1.9972015671224115, "grad_norm": 2.1577939987182617, "learning_rate": 1.6734344945501175e-05, "loss": 0.459, "step": 3123 }, { "epoch": 1.997841208923003, "grad_norm": 2.1966986656188965, "learning_rate": 1.6723658901474674e-05, "loss": 0.4481, "step": 3124 }, { "epoch": 1.998480850723595, "grad_norm": 2.145503520965576, "learning_rate": 1.6712972857448174e-05, "loss": 0.4754, "step": 3125 }, { "epoch": 1.9991204925241863, "grad_norm": 2.522552967071533, "learning_rate": 1.6702286813421673e-05, "loss": 0.4993, "step": 3126 }, { "epoch": 1.9997601343247782, "grad_norm": 2.595780611038208, "learning_rate": 1.6691600769395172e-05, "loss": 0.5107, "step": 3127 }, { "epoch": 2.0, "grad_norm": 3.449460029602051, "learning_rate": 1.668091472536867e-05, "loss": 0.416, "step": 3128 }, { "epoch": 2.000639641800592, "grad_norm": 1.6779128313064575, "learning_rate": 1.6670228681342168e-05, "loss": 0.3353, "step": 3129 }, { "epoch": 2.0012792836011832, "grad_norm": 1.5910295248031616, "learning_rate": 1.6659542637315667e-05, "loss": 0.3762, "step": 3130 }, { "epoch": 2.001918925401775, "grad_norm": 1.697697401046753, "learning_rate": 1.6648856593289163e-05, "loss": 0.3306, "step": 3131 }, { "epoch": 2.0025585672023665, "grad_norm": 1.518368124961853, "learning_rate": 1.6638170549262662e-05, "loss": 0.327, "step": 3132 }, { "epoch": 2.0031982090029583, "grad_norm": 1.7516897916793823, "learning_rate": 1.6627484505236162e-05, "loss": 0.3522, "step": 3133 }, { "epoch": 2.00383785080355, "grad_norm": 1.559342861175537, "learning_rate": 1.661679846120966e-05, "loss": 0.3021, "step": 3134 }, { "epoch": 2.0044774926041415, "grad_norm": 1.6947582960128784, "learning_rate": 1.660611241718316e-05, "loss": 0.3277, "step": 3135 }, { "epoch": 2.0051171344047334, "grad_norm": 1.9805963039398193, "learning_rate": 1.659542637315666e-05, "loss": 0.3193, "step": 3136 }, { "epoch": 2.005756776205325, "grad_norm": 1.708906888961792, "learning_rate": 1.658474032913016e-05, "loss": 0.3352, "step": 3137 }, { "epoch": 2.0063964180059166, "grad_norm": 2.005021572113037, "learning_rate": 1.6574054285103655e-05, "loss": 0.3301, "step": 3138 }, { "epoch": 2.0070360598065085, "grad_norm": 1.9154053926467896, "learning_rate": 1.6563368241077155e-05, "loss": 0.3003, "step": 3139 }, { "epoch": 2.0076757016071, "grad_norm": 2.0008208751678467, "learning_rate": 1.6552682197050654e-05, "loss": 0.2872, "step": 3140 }, { "epoch": 2.0083153434076917, "grad_norm": 2.1309220790863037, "learning_rate": 1.654199615302415e-05, "loss": 0.3055, "step": 3141 }, { "epoch": 2.0089549852082835, "grad_norm": 2.131603956222534, "learning_rate": 1.653131010899765e-05, "loss": 0.2969, "step": 3142 }, { "epoch": 2.009594627008875, "grad_norm": 2.8020849227905273, "learning_rate": 1.652062406497115e-05, "loss": 0.3187, "step": 3143 }, { "epoch": 2.0102342688094668, "grad_norm": 2.71633243560791, "learning_rate": 1.6509938020944645e-05, "loss": 0.3, "step": 3144 }, { "epoch": 2.010873910610058, "grad_norm": 2.8960108757019043, "learning_rate": 1.6499251976918144e-05, "loss": 0.3143, "step": 3145 }, { "epoch": 2.01151355241065, "grad_norm": 2.872610569000244, "learning_rate": 1.6488565932891643e-05, "loss": 0.3024, "step": 3146 }, { "epoch": 2.012153194211242, "grad_norm": 2.6689562797546387, "learning_rate": 1.6477879888865143e-05, "loss": 0.2687, "step": 3147 }, { "epoch": 2.0127928360118332, "grad_norm": 3.2189183235168457, "learning_rate": 1.6467193844838642e-05, "loss": 0.3055, "step": 3148 }, { "epoch": 2.013432477812425, "grad_norm": 3.3254477977752686, "learning_rate": 1.645650780081214e-05, "loss": 0.3233, "step": 3149 }, { "epoch": 2.014072119613017, "grad_norm": 3.1897618770599365, "learning_rate": 1.644582175678564e-05, "loss": 0.2796, "step": 3150 }, { "epoch": 2.0147117614136083, "grad_norm": 3.6358282566070557, "learning_rate": 1.6435135712759137e-05, "loss": 0.3246, "step": 3151 }, { "epoch": 2.0153514032142, "grad_norm": 3.135077953338623, "learning_rate": 1.6424449668732636e-05, "loss": 0.2811, "step": 3152 }, { "epoch": 2.0159910450147915, "grad_norm": 3.6325466632843018, "learning_rate": 1.6413763624706135e-05, "loss": 0.2951, "step": 3153 }, { "epoch": 2.0166306868153834, "grad_norm": 3.7397799491882324, "learning_rate": 1.640307758067963e-05, "loss": 0.3308, "step": 3154 }, { "epoch": 2.017270328615975, "grad_norm": 3.0837008953094482, "learning_rate": 1.639239153665313e-05, "loss": 0.2761, "step": 3155 }, { "epoch": 2.0179099704165666, "grad_norm": 2.698352098464966, "learning_rate": 1.638170549262663e-05, "loss": 0.2523, "step": 3156 }, { "epoch": 2.0185496122171585, "grad_norm": 3.8014771938323975, "learning_rate": 1.637101944860013e-05, "loss": 0.3365, "step": 3157 }, { "epoch": 2.01918925401775, "grad_norm": 2.8840444087982178, "learning_rate": 1.636033340457363e-05, "loss": 0.2794, "step": 3158 }, { "epoch": 2.0198288958183417, "grad_norm": 3.2458548545837402, "learning_rate": 1.6349647360547128e-05, "loss": 0.3257, "step": 3159 }, { "epoch": 2.0204685376189335, "grad_norm": 2.931417226791382, "learning_rate": 1.6338961316520628e-05, "loss": 0.3198, "step": 3160 }, { "epoch": 2.021108179419525, "grad_norm": 2.8906733989715576, "learning_rate": 1.6328275272494124e-05, "loss": 0.3006, "step": 3161 }, { "epoch": 2.0217478212201168, "grad_norm": 3.2544641494750977, "learning_rate": 1.6317589228467623e-05, "loss": 0.3437, "step": 3162 }, { "epoch": 2.0223874630207086, "grad_norm": 2.798978567123413, "learning_rate": 1.6306903184441122e-05, "loss": 0.2978, "step": 3163 }, { "epoch": 2.0230271048213, "grad_norm": 3.4615495204925537, "learning_rate": 1.6296217140414618e-05, "loss": 0.3628, "step": 3164 }, { "epoch": 2.023666746621892, "grad_norm": 2.4950344562530518, "learning_rate": 1.6285531096388118e-05, "loss": 0.284, "step": 3165 }, { "epoch": 2.0243063884224832, "grad_norm": 2.7329065799713135, "learning_rate": 1.6274845052361617e-05, "loss": 0.3045, "step": 3166 }, { "epoch": 2.024946030223075, "grad_norm": 2.344383478164673, "learning_rate": 1.6264159008335113e-05, "loss": 0.2859, "step": 3167 }, { "epoch": 2.025585672023667, "grad_norm": 2.4195828437805176, "learning_rate": 1.6253472964308612e-05, "loss": 0.3003, "step": 3168 }, { "epoch": 2.0262253138242583, "grad_norm": 2.586026668548584, "learning_rate": 1.624278692028211e-05, "loss": 0.3086, "step": 3169 }, { "epoch": 2.02686495562485, "grad_norm": 2.6065242290496826, "learning_rate": 1.623210087625561e-05, "loss": 0.3079, "step": 3170 }, { "epoch": 2.0275045974254415, "grad_norm": 2.847074508666992, "learning_rate": 1.622141483222911e-05, "loss": 0.3241, "step": 3171 }, { "epoch": 2.0281442392260334, "grad_norm": 2.3567025661468506, "learning_rate": 1.621072878820261e-05, "loss": 0.2637, "step": 3172 }, { "epoch": 2.028783881026625, "grad_norm": 2.294857978820801, "learning_rate": 1.6200042744176106e-05, "loss": 0.2702, "step": 3173 }, { "epoch": 2.0294235228272166, "grad_norm": 2.289886951446533, "learning_rate": 1.6189356700149605e-05, "loss": 0.3044, "step": 3174 }, { "epoch": 2.0300631646278084, "grad_norm": 2.121716022491455, "learning_rate": 1.6178670656123104e-05, "loss": 0.2667, "step": 3175 }, { "epoch": 2.0307028064284003, "grad_norm": 2.6956703662872314, "learning_rate": 1.6167984612096604e-05, "loss": 0.2687, "step": 3176 }, { "epoch": 2.0313424482289917, "grad_norm": 2.691291570663452, "learning_rate": 1.61572985680701e-05, "loss": 0.2943, "step": 3177 }, { "epoch": 2.0319820900295835, "grad_norm": 3.67265248298645, "learning_rate": 1.61466125240436e-05, "loss": 0.3831, "step": 3178 }, { "epoch": 2.032621731830175, "grad_norm": 1.999361515045166, "learning_rate": 1.61359264800171e-05, "loss": 0.2548, "step": 3179 }, { "epoch": 2.0332613736307668, "grad_norm": 2.9225454330444336, "learning_rate": 1.6125240435990598e-05, "loss": 0.3297, "step": 3180 }, { "epoch": 2.0339010154313586, "grad_norm": 2.4496564865112305, "learning_rate": 1.6114554391964097e-05, "loss": 0.2729, "step": 3181 }, { "epoch": 2.03454065723195, "grad_norm": 3.0396206378936768, "learning_rate": 1.6103868347937597e-05, "loss": 0.3091, "step": 3182 }, { "epoch": 2.035180299032542, "grad_norm": 2.9822778701782227, "learning_rate": 1.6093182303911093e-05, "loss": 0.3054, "step": 3183 }, { "epoch": 2.0358199408331332, "grad_norm": 2.0436558723449707, "learning_rate": 1.6082496259884592e-05, "loss": 0.247, "step": 3184 }, { "epoch": 2.036459582633725, "grad_norm": 2.5129218101501465, "learning_rate": 1.607181021585809e-05, "loss": 0.2828, "step": 3185 }, { "epoch": 2.037099224434317, "grad_norm": 2.7617108821868896, "learning_rate": 1.6061124171831587e-05, "loss": 0.2711, "step": 3186 }, { "epoch": 2.0377388662349083, "grad_norm": 3.0609190464019775, "learning_rate": 1.6050438127805087e-05, "loss": 0.31, "step": 3187 }, { "epoch": 2.0383785080355, "grad_norm": 2.60442852973938, "learning_rate": 1.6039752083778586e-05, "loss": 0.277, "step": 3188 }, { "epoch": 2.039018149836092, "grad_norm": 2.3617653846740723, "learning_rate": 1.6029066039752085e-05, "loss": 0.2499, "step": 3189 }, { "epoch": 2.0396577916366834, "grad_norm": 2.6222386360168457, "learning_rate": 1.601837999572558e-05, "loss": 0.3078, "step": 3190 }, { "epoch": 2.040297433437275, "grad_norm": 2.4635252952575684, "learning_rate": 1.600769395169908e-05, "loss": 0.2807, "step": 3191 }, { "epoch": 2.0409370752378666, "grad_norm": 2.7139599323272705, "learning_rate": 1.599700790767258e-05, "loss": 0.3031, "step": 3192 }, { "epoch": 2.0415767170384584, "grad_norm": 2.8060879707336426, "learning_rate": 1.598632186364608e-05, "loss": 0.3309, "step": 3193 }, { "epoch": 2.0422163588390503, "grad_norm": 2.574420213699341, "learning_rate": 1.597563581961958e-05, "loss": 0.2647, "step": 3194 }, { "epoch": 2.0428560006396417, "grad_norm": 3.502035140991211, "learning_rate": 1.5964949775593078e-05, "loss": 0.3351, "step": 3195 }, { "epoch": 2.0434956424402335, "grad_norm": 2.8940072059631348, "learning_rate": 1.5954263731566574e-05, "loss": 0.3199, "step": 3196 }, { "epoch": 2.0441352842408254, "grad_norm": 2.750485420227051, "learning_rate": 1.5943577687540073e-05, "loss": 0.2863, "step": 3197 }, { "epoch": 2.0447749260414168, "grad_norm": 2.437612295150757, "learning_rate": 1.5932891643513573e-05, "loss": 0.2654, "step": 3198 }, { "epoch": 2.0454145678420086, "grad_norm": 3.353499174118042, "learning_rate": 1.592220559948707e-05, "loss": 0.3058, "step": 3199 }, { "epoch": 2.0460542096426, "grad_norm": 2.707676649093628, "learning_rate": 1.5911519555460568e-05, "loss": 0.2841, "step": 3200 }, { "epoch": 2.046693851443192, "grad_norm": 2.9310965538024902, "learning_rate": 1.5900833511434068e-05, "loss": 0.3341, "step": 3201 }, { "epoch": 2.0473334932437837, "grad_norm": 2.8691303730010986, "learning_rate": 1.5890147467407564e-05, "loss": 0.2995, "step": 3202 }, { "epoch": 2.047973135044375, "grad_norm": 2.653183698654175, "learning_rate": 1.5879461423381066e-05, "loss": 0.2781, "step": 3203 }, { "epoch": 2.048612776844967, "grad_norm": 2.5871102809906006, "learning_rate": 1.5868775379354566e-05, "loss": 0.2884, "step": 3204 }, { "epoch": 2.0492524186455583, "grad_norm": 3.0146594047546387, "learning_rate": 1.5858089335328065e-05, "loss": 0.3131, "step": 3205 }, { "epoch": 2.04989206044615, "grad_norm": 2.956112861633301, "learning_rate": 1.584740329130156e-05, "loss": 0.307, "step": 3206 }, { "epoch": 2.050531702246742, "grad_norm": 2.8111886978149414, "learning_rate": 1.583671724727506e-05, "loss": 0.2979, "step": 3207 }, { "epoch": 2.0511713440473334, "grad_norm": 2.4186933040618896, "learning_rate": 1.582603120324856e-05, "loss": 0.2598, "step": 3208 }, { "epoch": 2.051810985847925, "grad_norm": 2.7398626804351807, "learning_rate": 1.5815345159222056e-05, "loss": 0.3058, "step": 3209 }, { "epoch": 2.052450627648517, "grad_norm": 2.7144486904144287, "learning_rate": 1.5804659115195555e-05, "loss": 0.2994, "step": 3210 }, { "epoch": 2.0530902694491084, "grad_norm": 2.864875555038452, "learning_rate": 1.5793973071169054e-05, "loss": 0.3262, "step": 3211 }, { "epoch": 2.0537299112497003, "grad_norm": 2.4187493324279785, "learning_rate": 1.578328702714255e-05, "loss": 0.3022, "step": 3212 }, { "epoch": 2.0543695530502917, "grad_norm": 2.491227388381958, "learning_rate": 1.577260098311605e-05, "loss": 0.263, "step": 3213 }, { "epoch": 2.0550091948508835, "grad_norm": 2.6596786975860596, "learning_rate": 1.576191493908955e-05, "loss": 0.3023, "step": 3214 }, { "epoch": 2.0556488366514754, "grad_norm": 3.1954710483551025, "learning_rate": 1.575122889506305e-05, "loss": 0.3333, "step": 3215 }, { "epoch": 2.0562884784520667, "grad_norm": 3.25301194190979, "learning_rate": 1.5740542851036548e-05, "loss": 0.3294, "step": 3216 }, { "epoch": 2.0569281202526586, "grad_norm": 2.6421799659729004, "learning_rate": 1.5729856807010047e-05, "loss": 0.2713, "step": 3217 }, { "epoch": 2.05756776205325, "grad_norm": 3.407914638519287, "learning_rate": 1.5719170762983547e-05, "loss": 0.341, "step": 3218 }, { "epoch": 2.058207403853842, "grad_norm": 2.7729814052581787, "learning_rate": 1.5708484718957042e-05, "loss": 0.2861, "step": 3219 }, { "epoch": 2.0588470456544337, "grad_norm": 2.9381232261657715, "learning_rate": 1.5697798674930542e-05, "loss": 0.3389, "step": 3220 }, { "epoch": 2.059486687455025, "grad_norm": 2.676520586013794, "learning_rate": 1.568711263090404e-05, "loss": 0.295, "step": 3221 }, { "epoch": 2.060126329255617, "grad_norm": 2.7993195056915283, "learning_rate": 1.5676426586877537e-05, "loss": 0.311, "step": 3222 }, { "epoch": 2.0607659710562087, "grad_norm": 2.848257303237915, "learning_rate": 1.5665740542851037e-05, "loss": 0.2875, "step": 3223 }, { "epoch": 2.0614056128568, "grad_norm": 2.6933562755584717, "learning_rate": 1.5655054498824536e-05, "loss": 0.2928, "step": 3224 }, { "epoch": 2.062045254657392, "grad_norm": 2.7110655307769775, "learning_rate": 1.5644368454798032e-05, "loss": 0.2609, "step": 3225 }, { "epoch": 2.0626848964579834, "grad_norm": 3.1989595890045166, "learning_rate": 1.5633682410771535e-05, "loss": 0.3319, "step": 3226 }, { "epoch": 2.063324538258575, "grad_norm": 2.603562116622925, "learning_rate": 1.5622996366745034e-05, "loss": 0.2546, "step": 3227 }, { "epoch": 2.063964180059167, "grad_norm": 3.1629462242126465, "learning_rate": 1.561231032271853e-05, "loss": 0.3066, "step": 3228 }, { "epoch": 2.0646038218597584, "grad_norm": 2.6760365962982178, "learning_rate": 1.560162427869203e-05, "loss": 0.2827, "step": 3229 }, { "epoch": 2.0652434636603503, "grad_norm": 2.3832077980041504, "learning_rate": 1.559093823466553e-05, "loss": 0.2777, "step": 3230 }, { "epoch": 2.0658831054609417, "grad_norm": 3.096395492553711, "learning_rate": 1.5580252190639028e-05, "loss": 0.3242, "step": 3231 }, { "epoch": 2.0665227472615335, "grad_norm": 3.1770401000976562, "learning_rate": 1.5569566146612524e-05, "loss": 0.2627, "step": 3232 }, { "epoch": 2.0671623890621253, "grad_norm": 2.8355541229248047, "learning_rate": 1.5558880102586023e-05, "loss": 0.2977, "step": 3233 }, { "epoch": 2.0678020308627167, "grad_norm": 2.670912504196167, "learning_rate": 1.5548194058559523e-05, "loss": 0.3027, "step": 3234 }, { "epoch": 2.0684416726633086, "grad_norm": 2.2594873905181885, "learning_rate": 1.553750801453302e-05, "loss": 0.2624, "step": 3235 }, { "epoch": 2.0690813144639004, "grad_norm": 3.151336431503296, "learning_rate": 1.5526821970506518e-05, "loss": 0.301, "step": 3236 }, { "epoch": 2.069720956264492, "grad_norm": 3.330171585083008, "learning_rate": 1.5516135926480017e-05, "loss": 0.3277, "step": 3237 }, { "epoch": 2.0703605980650837, "grad_norm": 2.6647558212280273, "learning_rate": 1.5505449882453517e-05, "loss": 0.2838, "step": 3238 }, { "epoch": 2.071000239865675, "grad_norm": 2.5245156288146973, "learning_rate": 1.5494763838427016e-05, "loss": 0.2961, "step": 3239 }, { "epoch": 2.071639881666267, "grad_norm": 2.5992631912231445, "learning_rate": 1.5484077794400516e-05, "loss": 0.2693, "step": 3240 }, { "epoch": 2.0722795234668587, "grad_norm": 2.877854108810425, "learning_rate": 1.547339175037401e-05, "loss": 0.2962, "step": 3241 }, { "epoch": 2.07291916526745, "grad_norm": 2.711557388305664, "learning_rate": 1.546270570634751e-05, "loss": 0.288, "step": 3242 }, { "epoch": 2.073558807068042, "grad_norm": 2.771714687347412, "learning_rate": 1.545201966232101e-05, "loss": 0.2765, "step": 3243 }, { "epoch": 2.0741984488686334, "grad_norm": 2.429236888885498, "learning_rate": 1.5441333618294506e-05, "loss": 0.2563, "step": 3244 }, { "epoch": 2.074838090669225, "grad_norm": 2.883639097213745, "learning_rate": 1.5430647574268006e-05, "loss": 0.3183, "step": 3245 }, { "epoch": 2.075477732469817, "grad_norm": 3.3720297813415527, "learning_rate": 1.5419961530241505e-05, "loss": 0.2925, "step": 3246 }, { "epoch": 2.0761173742704084, "grad_norm": 2.7470321655273438, "learning_rate": 1.5409275486215004e-05, "loss": 0.2961, "step": 3247 }, { "epoch": 2.0767570160710003, "grad_norm": 2.5316994190216064, "learning_rate": 1.53985894421885e-05, "loss": 0.2613, "step": 3248 }, { "epoch": 2.077396657871592, "grad_norm": 2.7023704051971436, "learning_rate": 1.5387903398162003e-05, "loss": 0.2608, "step": 3249 }, { "epoch": 2.0780362996721835, "grad_norm": 2.663525104522705, "learning_rate": 1.5377217354135502e-05, "loss": 0.2833, "step": 3250 }, { "epoch": 2.0786759414727753, "grad_norm": 2.6081383228302, "learning_rate": 1.5366531310109e-05, "loss": 0.2604, "step": 3251 }, { "epoch": 2.0793155832733667, "grad_norm": 2.700937032699585, "learning_rate": 1.5355845266082498e-05, "loss": 0.2704, "step": 3252 }, { "epoch": 2.0799552250739586, "grad_norm": 3.3110196590423584, "learning_rate": 1.5345159222055997e-05, "loss": 0.2994, "step": 3253 }, { "epoch": 2.0805948668745504, "grad_norm": 2.718968152999878, "learning_rate": 1.5334473178029493e-05, "loss": 0.2641, "step": 3254 }, { "epoch": 2.081234508675142, "grad_norm": 3.172600030899048, "learning_rate": 1.5323787134002992e-05, "loss": 0.3076, "step": 3255 }, { "epoch": 2.0818741504757337, "grad_norm": 2.9849905967712402, "learning_rate": 1.5313101089976492e-05, "loss": 0.3096, "step": 3256 }, { "epoch": 2.082513792276325, "grad_norm": 3.1546828746795654, "learning_rate": 1.5302415045949988e-05, "loss": 0.3006, "step": 3257 }, { "epoch": 2.083153434076917, "grad_norm": 2.601928949356079, "learning_rate": 1.5291729001923487e-05, "loss": 0.2734, "step": 3258 }, { "epoch": 2.0837930758775087, "grad_norm": 2.700784921646118, "learning_rate": 1.5281042957896986e-05, "loss": 0.2794, "step": 3259 }, { "epoch": 2.0844327176781, "grad_norm": 3.1294023990631104, "learning_rate": 1.5270356913870486e-05, "loss": 0.3098, "step": 3260 }, { "epoch": 2.085072359478692, "grad_norm": 2.5297465324401855, "learning_rate": 1.5259670869843985e-05, "loss": 0.279, "step": 3261 }, { "epoch": 2.085712001279284, "grad_norm": 2.892437219619751, "learning_rate": 1.5248984825817483e-05, "loss": 0.2939, "step": 3262 }, { "epoch": 2.086351643079875, "grad_norm": 2.8874454498291016, "learning_rate": 1.5238298781790982e-05, "loss": 0.296, "step": 3263 }, { "epoch": 2.086991284880467, "grad_norm": 2.9296672344207764, "learning_rate": 1.522761273776448e-05, "loss": 0.3122, "step": 3264 }, { "epoch": 2.0876309266810584, "grad_norm": 2.9001364707946777, "learning_rate": 1.521692669373798e-05, "loss": 0.2765, "step": 3265 }, { "epoch": 2.0882705684816503, "grad_norm": 2.669949531555176, "learning_rate": 1.5206240649711479e-05, "loss": 0.3069, "step": 3266 }, { "epoch": 2.088910210282242, "grad_norm": 3.0146543979644775, "learning_rate": 1.5195554605684975e-05, "loss": 0.2975, "step": 3267 }, { "epoch": 2.0895498520828335, "grad_norm": 2.7401692867279053, "learning_rate": 1.5184868561658474e-05, "loss": 0.2788, "step": 3268 }, { "epoch": 2.0901894938834253, "grad_norm": 2.876371383666992, "learning_rate": 1.5174182517631973e-05, "loss": 0.2945, "step": 3269 }, { "epoch": 2.0908291356840167, "grad_norm": 2.3925490379333496, "learning_rate": 1.5163496473605471e-05, "loss": 0.2676, "step": 3270 }, { "epoch": 2.0914687774846086, "grad_norm": 2.8799896240234375, "learning_rate": 1.515281042957897e-05, "loss": 0.2998, "step": 3271 }, { "epoch": 2.0921084192852004, "grad_norm": 2.9084677696228027, "learning_rate": 1.514212438555247e-05, "loss": 0.3046, "step": 3272 }, { "epoch": 2.092748061085792, "grad_norm": 2.9953341484069824, "learning_rate": 1.5131438341525969e-05, "loss": 0.2805, "step": 3273 }, { "epoch": 2.0933877028863837, "grad_norm": 3.266188144683838, "learning_rate": 1.5120752297499465e-05, "loss": 0.2944, "step": 3274 }, { "epoch": 2.0940273446869755, "grad_norm": 2.7826449871063232, "learning_rate": 1.5110066253472966e-05, "loss": 0.2753, "step": 3275 }, { "epoch": 2.094666986487567, "grad_norm": 2.854180335998535, "learning_rate": 1.5099380209446465e-05, "loss": 0.3095, "step": 3276 }, { "epoch": 2.0953066282881587, "grad_norm": 2.8137595653533936, "learning_rate": 1.5088694165419961e-05, "loss": 0.2961, "step": 3277 }, { "epoch": 2.09594627008875, "grad_norm": 2.908651351928711, "learning_rate": 1.507800812139346e-05, "loss": 0.2537, "step": 3278 }, { "epoch": 2.096585911889342, "grad_norm": 3.0123391151428223, "learning_rate": 1.506732207736696e-05, "loss": 0.3113, "step": 3279 }, { "epoch": 2.097225553689934, "grad_norm": 2.7820565700531006, "learning_rate": 1.5056636033340458e-05, "loss": 0.2918, "step": 3280 }, { "epoch": 2.097865195490525, "grad_norm": 2.8627681732177734, "learning_rate": 1.5045949989313957e-05, "loss": 0.3028, "step": 3281 }, { "epoch": 2.098504837291117, "grad_norm": 2.9475295543670654, "learning_rate": 1.5035263945287457e-05, "loss": 0.2941, "step": 3282 }, { "epoch": 2.0991444790917084, "grad_norm": 3.054466724395752, "learning_rate": 1.5024577901260953e-05, "loss": 0.308, "step": 3283 }, { "epoch": 2.0997841208923003, "grad_norm": 2.772033452987671, "learning_rate": 1.5013891857234452e-05, "loss": 0.2655, "step": 3284 }, { "epoch": 2.100423762692892, "grad_norm": 3.1366946697235107, "learning_rate": 1.5003205813207951e-05, "loss": 0.295, "step": 3285 }, { "epoch": 2.1010634044934835, "grad_norm": 2.5524094104766846, "learning_rate": 1.4992519769181449e-05, "loss": 0.263, "step": 3286 }, { "epoch": 2.1017030462940753, "grad_norm": 2.7674403190612793, "learning_rate": 1.4981833725154948e-05, "loss": 0.2847, "step": 3287 }, { "epoch": 2.102342688094667, "grad_norm": 2.9924843311309814, "learning_rate": 1.4971147681128448e-05, "loss": 0.302, "step": 3288 }, { "epoch": 2.1029823298952586, "grad_norm": 2.7296512126922607, "learning_rate": 1.4960461637101947e-05, "loss": 0.279, "step": 3289 }, { "epoch": 2.1036219716958504, "grad_norm": 2.4712929725646973, "learning_rate": 1.4949775593075443e-05, "loss": 0.2431, "step": 3290 }, { "epoch": 2.104261613496442, "grad_norm": 3.1025404930114746, "learning_rate": 1.4939089549048942e-05, "loss": 0.3214, "step": 3291 }, { "epoch": 2.1049012552970336, "grad_norm": 3.0940849781036377, "learning_rate": 1.4928403505022442e-05, "loss": 0.3067, "step": 3292 }, { "epoch": 2.1055408970976255, "grad_norm": 2.9295239448547363, "learning_rate": 1.491771746099594e-05, "loss": 0.2979, "step": 3293 }, { "epoch": 2.106180538898217, "grad_norm": 2.9662773609161377, "learning_rate": 1.4907031416969439e-05, "loss": 0.3117, "step": 3294 }, { "epoch": 2.1068201806988087, "grad_norm": 2.6901750564575195, "learning_rate": 1.4896345372942938e-05, "loss": 0.284, "step": 3295 }, { "epoch": 2.1074598224994006, "grad_norm": 2.865873098373413, "learning_rate": 1.4885659328916434e-05, "loss": 0.3094, "step": 3296 }, { "epoch": 2.108099464299992, "grad_norm": 3.3490869998931885, "learning_rate": 1.4874973284889933e-05, "loss": 0.3159, "step": 3297 }, { "epoch": 2.108739106100584, "grad_norm": 2.8624188899993896, "learning_rate": 1.4864287240863434e-05, "loss": 0.3002, "step": 3298 }, { "epoch": 2.109378747901175, "grad_norm": 2.627501964569092, "learning_rate": 1.485360119683693e-05, "loss": 0.2713, "step": 3299 }, { "epoch": 2.110018389701767, "grad_norm": 2.5993735790252686, "learning_rate": 1.484291515281043e-05, "loss": 0.3047, "step": 3300 }, { "epoch": 2.110658031502359, "grad_norm": 2.5539181232452393, "learning_rate": 1.483222910878393e-05, "loss": 0.2842, "step": 3301 }, { "epoch": 2.1112976733029503, "grad_norm": 2.971036434173584, "learning_rate": 1.4821543064757429e-05, "loss": 0.3129, "step": 3302 }, { "epoch": 2.111937315103542, "grad_norm": 2.9908058643341064, "learning_rate": 1.4810857020730926e-05, "loss": 0.2893, "step": 3303 }, { "epoch": 2.1125769569041335, "grad_norm": 2.337106227874756, "learning_rate": 1.4800170976704426e-05, "loss": 0.2813, "step": 3304 }, { "epoch": 2.1132165987047253, "grad_norm": 2.473165273666382, "learning_rate": 1.4789484932677925e-05, "loss": 0.2861, "step": 3305 }, { "epoch": 2.113856240505317, "grad_norm": 2.905780792236328, "learning_rate": 1.4778798888651421e-05, "loss": 0.2922, "step": 3306 }, { "epoch": 2.1144958823059086, "grad_norm": 2.6335463523864746, "learning_rate": 1.476811284462492e-05, "loss": 0.2775, "step": 3307 }, { "epoch": 2.1151355241065004, "grad_norm": 2.7311782836914062, "learning_rate": 1.475742680059842e-05, "loss": 0.2832, "step": 3308 }, { "epoch": 2.115775165907092, "grad_norm": 3.064622640609741, "learning_rate": 1.4746740756571917e-05, "loss": 0.3248, "step": 3309 }, { "epoch": 2.1164148077076836, "grad_norm": 2.511990785598755, "learning_rate": 1.4736054712545417e-05, "loss": 0.2734, "step": 3310 }, { "epoch": 2.1170544495082755, "grad_norm": 2.5764358043670654, "learning_rate": 1.4725368668518916e-05, "loss": 0.2979, "step": 3311 }, { "epoch": 2.117694091308867, "grad_norm": 2.4979262351989746, "learning_rate": 1.4714682624492412e-05, "loss": 0.2788, "step": 3312 }, { "epoch": 2.1183337331094587, "grad_norm": 2.798145294189453, "learning_rate": 1.4703996580465911e-05, "loss": 0.3077, "step": 3313 }, { "epoch": 2.1189733749100506, "grad_norm": 2.6941370964050293, "learning_rate": 1.469331053643941e-05, "loss": 0.2939, "step": 3314 }, { "epoch": 2.119613016710642, "grad_norm": 2.527987241744995, "learning_rate": 1.468262449241291e-05, "loss": 0.2551, "step": 3315 }, { "epoch": 2.120252658511234, "grad_norm": 3.3765578269958496, "learning_rate": 1.4671938448386408e-05, "loss": 0.3339, "step": 3316 }, { "epoch": 2.120892300311825, "grad_norm": 2.503570795059204, "learning_rate": 1.4661252404359907e-05, "loss": 0.2646, "step": 3317 }, { "epoch": 2.121531942112417, "grad_norm": 2.9610562324523926, "learning_rate": 1.4650566360333406e-05, "loss": 0.3163, "step": 3318 }, { "epoch": 2.122171583913009, "grad_norm": 2.8845345973968506, "learning_rate": 1.4639880316306902e-05, "loss": 0.3079, "step": 3319 }, { "epoch": 2.1228112257136003, "grad_norm": 2.881183385848999, "learning_rate": 1.4629194272280402e-05, "loss": 0.2834, "step": 3320 }, { "epoch": 2.123450867514192, "grad_norm": 2.780571222305298, "learning_rate": 1.4618508228253903e-05, "loss": 0.3087, "step": 3321 }, { "epoch": 2.124090509314784, "grad_norm": 2.384935140609741, "learning_rate": 1.4607822184227399e-05, "loss": 0.2594, "step": 3322 }, { "epoch": 2.1247301511153753, "grad_norm": 3.1249091625213623, "learning_rate": 1.4597136140200898e-05, "loss": 0.3069, "step": 3323 }, { "epoch": 2.125369792915967, "grad_norm": 2.998181104660034, "learning_rate": 1.4586450096174398e-05, "loss": 0.3112, "step": 3324 }, { "epoch": 2.1260094347165586, "grad_norm": 2.590634822845459, "learning_rate": 1.4575764052147895e-05, "loss": 0.2646, "step": 3325 }, { "epoch": 2.1266490765171504, "grad_norm": 3.157170295715332, "learning_rate": 1.4565078008121395e-05, "loss": 0.3284, "step": 3326 }, { "epoch": 2.1272887183177422, "grad_norm": 2.5375778675079346, "learning_rate": 1.4554391964094894e-05, "loss": 0.265, "step": 3327 }, { "epoch": 2.1279283601183336, "grad_norm": 3.733571767807007, "learning_rate": 1.454370592006839e-05, "loss": 0.324, "step": 3328 }, { "epoch": 2.1285680019189255, "grad_norm": 2.771312952041626, "learning_rate": 1.453301987604189e-05, "loss": 0.2974, "step": 3329 }, { "epoch": 2.129207643719517, "grad_norm": 2.676919460296631, "learning_rate": 1.4522333832015389e-05, "loss": 0.278, "step": 3330 }, { "epoch": 2.1298472855201087, "grad_norm": 2.596200942993164, "learning_rate": 1.4511647787988888e-05, "loss": 0.294, "step": 3331 }, { "epoch": 2.1304869273207006, "grad_norm": 3.036965847015381, "learning_rate": 1.4500961743962386e-05, "loss": 0.2903, "step": 3332 }, { "epoch": 2.131126569121292, "grad_norm": 3.010483503341675, "learning_rate": 1.4490275699935885e-05, "loss": 0.2975, "step": 3333 }, { "epoch": 2.131766210921884, "grad_norm": 3.0769550800323486, "learning_rate": 1.4479589655909384e-05, "loss": 0.2878, "step": 3334 }, { "epoch": 2.132405852722475, "grad_norm": 2.7077112197875977, "learning_rate": 1.446890361188288e-05, "loss": 0.2944, "step": 3335 }, { "epoch": 2.133045494523067, "grad_norm": 3.1698193550109863, "learning_rate": 1.445821756785638e-05, "loss": 0.2907, "step": 3336 }, { "epoch": 2.133685136323659, "grad_norm": 2.898766279220581, "learning_rate": 1.4447531523829879e-05, "loss": 0.2838, "step": 3337 }, { "epoch": 2.1343247781242503, "grad_norm": 2.564615249633789, "learning_rate": 1.4436845479803377e-05, "loss": 0.2644, "step": 3338 }, { "epoch": 2.134964419924842, "grad_norm": 2.5013158321380615, "learning_rate": 1.4426159435776876e-05, "loss": 0.2676, "step": 3339 }, { "epoch": 2.135604061725434, "grad_norm": 3.6368777751922607, "learning_rate": 1.4415473391750375e-05, "loss": 0.3047, "step": 3340 }, { "epoch": 2.1362437035260253, "grad_norm": 3.0526676177978516, "learning_rate": 1.4404787347723871e-05, "loss": 0.318, "step": 3341 }, { "epoch": 2.136883345326617, "grad_norm": 3.0170764923095703, "learning_rate": 1.439410130369737e-05, "loss": 0.2822, "step": 3342 }, { "epoch": 2.1375229871272086, "grad_norm": 2.3196122646331787, "learning_rate": 1.438341525967087e-05, "loss": 0.2389, "step": 3343 }, { "epoch": 2.1381626289278004, "grad_norm": 2.5502870082855225, "learning_rate": 1.4372729215644371e-05, "loss": 0.2909, "step": 3344 }, { "epoch": 2.1388022707283922, "grad_norm": 2.881182909011841, "learning_rate": 1.4362043171617867e-05, "loss": 0.314, "step": 3345 }, { "epoch": 2.1394419125289836, "grad_norm": 2.882300615310669, "learning_rate": 1.4351357127591367e-05, "loss": 0.272, "step": 3346 }, { "epoch": 2.1400815543295755, "grad_norm": 3.044785976409912, "learning_rate": 1.4340671083564866e-05, "loss": 0.2888, "step": 3347 }, { "epoch": 2.1407211961301673, "grad_norm": 3.0978946685791016, "learning_rate": 1.4329985039538364e-05, "loss": 0.3126, "step": 3348 }, { "epoch": 2.1413608379307587, "grad_norm": 3.6918516159057617, "learning_rate": 1.4319298995511863e-05, "loss": 0.3276, "step": 3349 }, { "epoch": 2.1420004797313505, "grad_norm": 2.791208505630493, "learning_rate": 1.4308612951485362e-05, "loss": 0.2766, "step": 3350 }, { "epoch": 2.142640121531942, "grad_norm": 2.750880002975464, "learning_rate": 1.4297926907458858e-05, "loss": 0.3169, "step": 3351 }, { "epoch": 2.143279763332534, "grad_norm": 2.405256509780884, "learning_rate": 1.4287240863432358e-05, "loss": 0.2649, "step": 3352 }, { "epoch": 2.1439194051331256, "grad_norm": 2.3942768573760986, "learning_rate": 1.4276554819405857e-05, "loss": 0.2422, "step": 3353 }, { "epoch": 2.144559046933717, "grad_norm": 3.2327497005462646, "learning_rate": 1.4265868775379355e-05, "loss": 0.3109, "step": 3354 }, { "epoch": 2.145198688734309, "grad_norm": 3.0916550159454346, "learning_rate": 1.4255182731352854e-05, "loss": 0.3093, "step": 3355 }, { "epoch": 2.1458383305349003, "grad_norm": 2.913485050201416, "learning_rate": 1.4244496687326353e-05, "loss": 0.2844, "step": 3356 }, { "epoch": 2.146477972335492, "grad_norm": 3.2898309230804443, "learning_rate": 1.423381064329985e-05, "loss": 0.3317, "step": 3357 }, { "epoch": 2.147117614136084, "grad_norm": 2.7780044078826904, "learning_rate": 1.4223124599273349e-05, "loss": 0.3027, "step": 3358 }, { "epoch": 2.1477572559366753, "grad_norm": 2.799602746963501, "learning_rate": 1.4212438555246848e-05, "loss": 0.277, "step": 3359 }, { "epoch": 2.148396897737267, "grad_norm": 2.9556028842926025, "learning_rate": 1.4201752511220347e-05, "loss": 0.2848, "step": 3360 }, { "epoch": 2.149036539537859, "grad_norm": 2.9669811725616455, "learning_rate": 1.4191066467193845e-05, "loss": 0.3034, "step": 3361 }, { "epoch": 2.1496761813384504, "grad_norm": 2.8910956382751465, "learning_rate": 1.4180380423167345e-05, "loss": 0.272, "step": 3362 }, { "epoch": 2.1503158231390422, "grad_norm": 3.1302740573883057, "learning_rate": 1.4169694379140844e-05, "loss": 0.3078, "step": 3363 }, { "epoch": 2.1509554649396336, "grad_norm": 3.0801546573638916, "learning_rate": 1.415900833511434e-05, "loss": 0.3043, "step": 3364 }, { "epoch": 2.1515951067402255, "grad_norm": 2.647568941116333, "learning_rate": 1.414832229108784e-05, "loss": 0.2723, "step": 3365 }, { "epoch": 2.1522347485408173, "grad_norm": 2.8725883960723877, "learning_rate": 1.4137636247061339e-05, "loss": 0.2625, "step": 3366 }, { "epoch": 2.1528743903414087, "grad_norm": 2.886364698410034, "learning_rate": 1.4126950203034836e-05, "loss": 0.2982, "step": 3367 }, { "epoch": 2.1535140321420005, "grad_norm": 2.9265527725219727, "learning_rate": 1.4116264159008336e-05, "loss": 0.2883, "step": 3368 }, { "epoch": 2.1541536739425924, "grad_norm": 2.4564144611358643, "learning_rate": 1.4105578114981835e-05, "loss": 0.2732, "step": 3369 }, { "epoch": 2.154793315743184, "grad_norm": 2.6180050373077393, "learning_rate": 1.4094892070955331e-05, "loss": 0.2887, "step": 3370 }, { "epoch": 2.1554329575437756, "grad_norm": 2.618345260620117, "learning_rate": 1.4084206026928832e-05, "loss": 0.2792, "step": 3371 }, { "epoch": 2.156072599344367, "grad_norm": 2.967028856277466, "learning_rate": 1.4073519982902331e-05, "loss": 0.2945, "step": 3372 }, { "epoch": 2.156712241144959, "grad_norm": 3.5304341316223145, "learning_rate": 1.406283393887583e-05, "loss": 0.3093, "step": 3373 }, { "epoch": 2.1573518829455507, "grad_norm": 2.704852819442749, "learning_rate": 1.4052147894849327e-05, "loss": 0.2748, "step": 3374 }, { "epoch": 2.157991524746142, "grad_norm": 2.722247362136841, "learning_rate": 1.4041461850822826e-05, "loss": 0.2743, "step": 3375 }, { "epoch": 2.158631166546734, "grad_norm": 3.7692978382110596, "learning_rate": 1.4030775806796325e-05, "loss": 0.3565, "step": 3376 }, { "epoch": 2.1592708083473253, "grad_norm": 2.812537670135498, "learning_rate": 1.4020089762769823e-05, "loss": 0.2525, "step": 3377 }, { "epoch": 2.159910450147917, "grad_norm": 2.6271371841430664, "learning_rate": 1.4009403718743322e-05, "loss": 0.2953, "step": 3378 }, { "epoch": 2.160550091948509, "grad_norm": 3.192307710647583, "learning_rate": 1.3998717674716822e-05, "loss": 0.3093, "step": 3379 }, { "epoch": 2.1611897337491004, "grad_norm": 3.243069648742676, "learning_rate": 1.3988031630690318e-05, "loss": 0.2989, "step": 3380 }, { "epoch": 2.1618293755496922, "grad_norm": 3.1782214641571045, "learning_rate": 1.3977345586663817e-05, "loss": 0.3023, "step": 3381 }, { "epoch": 2.1624690173502836, "grad_norm": 2.870701551437378, "learning_rate": 1.3966659542637317e-05, "loss": 0.2988, "step": 3382 }, { "epoch": 2.1631086591508755, "grad_norm": 2.7732129096984863, "learning_rate": 1.3955973498610814e-05, "loss": 0.2828, "step": 3383 }, { "epoch": 2.1637483009514673, "grad_norm": 2.599611282348633, "learning_rate": 1.3945287454584314e-05, "loss": 0.2854, "step": 3384 }, { "epoch": 2.1643879427520587, "grad_norm": 3.072861909866333, "learning_rate": 1.3934601410557813e-05, "loss": 0.3059, "step": 3385 }, { "epoch": 2.1650275845526505, "grad_norm": 2.7385823726654053, "learning_rate": 1.3923915366531312e-05, "loss": 0.3106, "step": 3386 }, { "epoch": 2.1656672263532424, "grad_norm": 2.8344128131866455, "learning_rate": 1.3913229322504808e-05, "loss": 0.293, "step": 3387 }, { "epoch": 2.1663068681538338, "grad_norm": 2.4170472621917725, "learning_rate": 1.3902543278478308e-05, "loss": 0.2688, "step": 3388 }, { "epoch": 2.1669465099544256, "grad_norm": 2.664489984512329, "learning_rate": 1.3891857234451807e-05, "loss": 0.2807, "step": 3389 }, { "epoch": 2.167586151755017, "grad_norm": 2.6602396965026855, "learning_rate": 1.3881171190425305e-05, "loss": 0.2936, "step": 3390 }, { "epoch": 2.168225793555609, "grad_norm": 2.9426655769348145, "learning_rate": 1.3870485146398804e-05, "loss": 0.3038, "step": 3391 }, { "epoch": 2.1688654353562007, "grad_norm": 2.8860256671905518, "learning_rate": 1.3859799102372303e-05, "loss": 0.3081, "step": 3392 }, { "epoch": 2.169505077156792, "grad_norm": 2.702208995819092, "learning_rate": 1.38491130583458e-05, "loss": 0.2803, "step": 3393 }, { "epoch": 2.170144718957384, "grad_norm": 3.1027512550354004, "learning_rate": 1.38384270143193e-05, "loss": 0.3046, "step": 3394 }, { "epoch": 2.1707843607579758, "grad_norm": 3.0601143836975098, "learning_rate": 1.38277409702928e-05, "loss": 0.2921, "step": 3395 }, { "epoch": 2.171424002558567, "grad_norm": 3.29142165184021, "learning_rate": 1.3817054926266296e-05, "loss": 0.3275, "step": 3396 }, { "epoch": 2.172063644359159, "grad_norm": 2.895599603652954, "learning_rate": 1.3806368882239795e-05, "loss": 0.3053, "step": 3397 }, { "epoch": 2.1727032861597504, "grad_norm": 2.7596819400787354, "learning_rate": 1.3795682838213294e-05, "loss": 0.2662, "step": 3398 }, { "epoch": 2.1733429279603422, "grad_norm": 3.2723777294158936, "learning_rate": 1.3784996794186792e-05, "loss": 0.3229, "step": 3399 }, { "epoch": 2.173982569760934, "grad_norm": 3.1947109699249268, "learning_rate": 1.3774310750160291e-05, "loss": 0.312, "step": 3400 }, { "epoch": 2.1746222115615255, "grad_norm": 3.437711238861084, "learning_rate": 1.376362470613379e-05, "loss": 0.3301, "step": 3401 }, { "epoch": 2.1752618533621173, "grad_norm": 2.752490997314453, "learning_rate": 1.375293866210729e-05, "loss": 0.2879, "step": 3402 }, { "epoch": 2.1759014951627087, "grad_norm": 2.922455310821533, "learning_rate": 1.3742252618080786e-05, "loss": 0.2952, "step": 3403 }, { "epoch": 2.1765411369633005, "grad_norm": 2.505164384841919, "learning_rate": 1.3731566574054286e-05, "loss": 0.2655, "step": 3404 }, { "epoch": 2.1771807787638924, "grad_norm": 3.0617635250091553, "learning_rate": 1.3720880530027785e-05, "loss": 0.3192, "step": 3405 }, { "epoch": 2.1778204205644838, "grad_norm": 2.7670798301696777, "learning_rate": 1.3710194486001283e-05, "loss": 0.2838, "step": 3406 }, { "epoch": 2.1784600623650756, "grad_norm": 2.8397114276885986, "learning_rate": 1.3699508441974782e-05, "loss": 0.2785, "step": 3407 }, { "epoch": 2.179099704165667, "grad_norm": 3.077963352203369, "learning_rate": 1.3688822397948281e-05, "loss": 0.2929, "step": 3408 }, { "epoch": 2.179739345966259, "grad_norm": 3.0644330978393555, "learning_rate": 1.3678136353921777e-05, "loss": 0.2865, "step": 3409 }, { "epoch": 2.1803789877668507, "grad_norm": 2.621067523956299, "learning_rate": 1.3667450309895277e-05, "loss": 0.2673, "step": 3410 }, { "epoch": 2.181018629567442, "grad_norm": 3.0704424381256104, "learning_rate": 1.3656764265868776e-05, "loss": 0.3176, "step": 3411 }, { "epoch": 2.181658271368034, "grad_norm": 3.1157379150390625, "learning_rate": 1.3646078221842274e-05, "loss": 0.3075, "step": 3412 }, { "epoch": 2.1822979131686258, "grad_norm": 3.213707208633423, "learning_rate": 1.3635392177815773e-05, "loss": 0.2793, "step": 3413 }, { "epoch": 2.182937554969217, "grad_norm": 2.6101722717285156, "learning_rate": 1.3624706133789272e-05, "loss": 0.2636, "step": 3414 }, { "epoch": 2.183577196769809, "grad_norm": 2.9204750061035156, "learning_rate": 1.3614020089762772e-05, "loss": 0.292, "step": 3415 }, { "epoch": 2.1842168385704004, "grad_norm": 3.1458258628845215, "learning_rate": 1.3603334045736268e-05, "loss": 0.267, "step": 3416 }, { "epoch": 2.1848564803709922, "grad_norm": 2.9545929431915283, "learning_rate": 1.3592648001709769e-05, "loss": 0.3117, "step": 3417 }, { "epoch": 2.185496122171584, "grad_norm": 2.680281639099121, "learning_rate": 1.3581961957683268e-05, "loss": 0.2697, "step": 3418 }, { "epoch": 2.1861357639721755, "grad_norm": 2.8024208545684814, "learning_rate": 1.3571275913656764e-05, "loss": 0.2978, "step": 3419 }, { "epoch": 2.1867754057727673, "grad_norm": 3.025855541229248, "learning_rate": 1.3560589869630263e-05, "loss": 0.2808, "step": 3420 }, { "epoch": 2.187415047573359, "grad_norm": 3.2208971977233887, "learning_rate": 1.3549903825603763e-05, "loss": 0.3339, "step": 3421 }, { "epoch": 2.1880546893739505, "grad_norm": 2.4828367233276367, "learning_rate": 1.353921778157726e-05, "loss": 0.2814, "step": 3422 }, { "epoch": 2.1886943311745424, "grad_norm": 2.6162936687469482, "learning_rate": 1.352853173755076e-05, "loss": 0.2625, "step": 3423 }, { "epoch": 2.1893339729751338, "grad_norm": 2.6846094131469727, "learning_rate": 1.351784569352426e-05, "loss": 0.29, "step": 3424 }, { "epoch": 2.1899736147757256, "grad_norm": 2.86295485496521, "learning_rate": 1.3507159649497755e-05, "loss": 0.3253, "step": 3425 }, { "epoch": 2.1906132565763174, "grad_norm": 2.699244976043701, "learning_rate": 1.3496473605471255e-05, "loss": 0.2953, "step": 3426 }, { "epoch": 2.191252898376909, "grad_norm": 2.9537737369537354, "learning_rate": 1.3485787561444754e-05, "loss": 0.3111, "step": 3427 }, { "epoch": 2.1918925401775007, "grad_norm": 2.543488025665283, "learning_rate": 1.3475101517418253e-05, "loss": 0.3009, "step": 3428 }, { "epoch": 2.192532181978092, "grad_norm": 2.7410712242126465, "learning_rate": 1.3464415473391751e-05, "loss": 0.2775, "step": 3429 }, { "epoch": 2.193171823778684, "grad_norm": 2.979616641998291, "learning_rate": 1.345372942936525e-05, "loss": 0.3075, "step": 3430 }, { "epoch": 2.1938114655792758, "grad_norm": 2.9277937412261963, "learning_rate": 1.344304338533875e-05, "loss": 0.2885, "step": 3431 }, { "epoch": 2.194451107379867, "grad_norm": 2.8581950664520264, "learning_rate": 1.3432357341312246e-05, "loss": 0.2782, "step": 3432 }, { "epoch": 2.195090749180459, "grad_norm": 2.4586994647979736, "learning_rate": 1.3421671297285745e-05, "loss": 0.2519, "step": 3433 }, { "epoch": 2.1957303909810504, "grad_norm": 3.1406280994415283, "learning_rate": 1.3410985253259244e-05, "loss": 0.3196, "step": 3434 }, { "epoch": 2.1963700327816422, "grad_norm": 2.5794754028320312, "learning_rate": 1.3400299209232742e-05, "loss": 0.3065, "step": 3435 }, { "epoch": 2.197009674582234, "grad_norm": 2.432429313659668, "learning_rate": 1.3389613165206241e-05, "loss": 0.2801, "step": 3436 }, { "epoch": 2.1976493163828255, "grad_norm": 2.5403757095336914, "learning_rate": 1.337892712117974e-05, "loss": 0.28, "step": 3437 }, { "epoch": 2.1982889581834173, "grad_norm": 2.7475318908691406, "learning_rate": 1.3368241077153237e-05, "loss": 0.2747, "step": 3438 }, { "epoch": 2.198928599984009, "grad_norm": 2.8518126010894775, "learning_rate": 1.3357555033126736e-05, "loss": 0.3006, "step": 3439 }, { "epoch": 2.1995682417846005, "grad_norm": 2.685335159301758, "learning_rate": 1.3346868989100237e-05, "loss": 0.2915, "step": 3440 }, { "epoch": 2.2002078835851924, "grad_norm": 3.181511163711548, "learning_rate": 1.3336182945073733e-05, "loss": 0.3398, "step": 3441 }, { "epoch": 2.2008475253857838, "grad_norm": 2.777080535888672, "learning_rate": 1.3325496901047232e-05, "loss": 0.3063, "step": 3442 }, { "epoch": 2.2014871671863756, "grad_norm": 2.3552916049957275, "learning_rate": 1.3314810857020732e-05, "loss": 0.2554, "step": 3443 }, { "epoch": 2.2021268089869674, "grad_norm": 3.068506956100464, "learning_rate": 1.3304124812994231e-05, "loss": 0.2936, "step": 3444 }, { "epoch": 2.202766450787559, "grad_norm": 3.520688056945801, "learning_rate": 1.3293438768967729e-05, "loss": 0.3561, "step": 3445 }, { "epoch": 2.2034060925881507, "grad_norm": 2.4779372215270996, "learning_rate": 1.3282752724941228e-05, "loss": 0.2822, "step": 3446 }, { "epoch": 2.2040457343887425, "grad_norm": 2.91658616065979, "learning_rate": 1.3272066680914728e-05, "loss": 0.2783, "step": 3447 }, { "epoch": 2.204685376189334, "grad_norm": 2.7341294288635254, "learning_rate": 1.3261380636888224e-05, "loss": 0.2648, "step": 3448 }, { "epoch": 2.2053250179899258, "grad_norm": 3.193854331970215, "learning_rate": 1.3250694592861723e-05, "loss": 0.2955, "step": 3449 }, { "epoch": 2.205964659790517, "grad_norm": 2.6825780868530273, "learning_rate": 1.3240008548835222e-05, "loss": 0.2744, "step": 3450 }, { "epoch": 2.206604301591109, "grad_norm": 2.523312568664551, "learning_rate": 1.322932250480872e-05, "loss": 0.2778, "step": 3451 }, { "epoch": 2.207243943391701, "grad_norm": 2.689265251159668, "learning_rate": 1.321863646078222e-05, "loss": 0.2669, "step": 3452 }, { "epoch": 2.207883585192292, "grad_norm": 2.6073591709136963, "learning_rate": 1.3207950416755719e-05, "loss": 0.2803, "step": 3453 }, { "epoch": 2.208523226992884, "grad_norm": 2.992279052734375, "learning_rate": 1.3197264372729215e-05, "loss": 0.2748, "step": 3454 }, { "epoch": 2.2091628687934755, "grad_norm": 3.035036325454712, "learning_rate": 1.3186578328702714e-05, "loss": 0.3243, "step": 3455 }, { "epoch": 2.2098025105940673, "grad_norm": 2.693161725997925, "learning_rate": 1.3175892284676213e-05, "loss": 0.2809, "step": 3456 }, { "epoch": 2.210442152394659, "grad_norm": 3.079709053039551, "learning_rate": 1.3165206240649713e-05, "loss": 0.3027, "step": 3457 }, { "epoch": 2.2110817941952505, "grad_norm": 3.111102819442749, "learning_rate": 1.315452019662321e-05, "loss": 0.3032, "step": 3458 }, { "epoch": 2.2117214359958424, "grad_norm": 2.6593542098999023, "learning_rate": 1.314383415259671e-05, "loss": 0.2664, "step": 3459 }, { "epoch": 2.2123610777964338, "grad_norm": 3.213458299636841, "learning_rate": 1.3133148108570209e-05, "loss": 0.3159, "step": 3460 }, { "epoch": 2.2130007195970256, "grad_norm": 3.1140432357788086, "learning_rate": 1.3122462064543705e-05, "loss": 0.3099, "step": 3461 }, { "epoch": 2.2136403613976174, "grad_norm": 2.8638763427734375, "learning_rate": 1.3111776020517204e-05, "loss": 0.2673, "step": 3462 }, { "epoch": 2.214280003198209, "grad_norm": 2.9843013286590576, "learning_rate": 1.3101089976490704e-05, "loss": 0.2828, "step": 3463 }, { "epoch": 2.2149196449988007, "grad_norm": 2.785283088684082, "learning_rate": 1.3090403932464202e-05, "loss": 0.2827, "step": 3464 }, { "epoch": 2.2155592867993925, "grad_norm": 2.647834062576294, "learning_rate": 1.3079717888437701e-05, "loss": 0.2496, "step": 3465 }, { "epoch": 2.216198928599984, "grad_norm": 2.7125985622406006, "learning_rate": 1.30690318444112e-05, "loss": 0.2965, "step": 3466 }, { "epoch": 2.2168385704005757, "grad_norm": 3.4798755645751953, "learning_rate": 1.3058345800384696e-05, "loss": 0.292, "step": 3467 }, { "epoch": 2.217478212201167, "grad_norm": 2.8353967666625977, "learning_rate": 1.3047659756358197e-05, "loss": 0.284, "step": 3468 }, { "epoch": 2.218117854001759, "grad_norm": 2.951139450073242, "learning_rate": 1.3036973712331697e-05, "loss": 0.2733, "step": 3469 }, { "epoch": 2.218757495802351, "grad_norm": 3.917747974395752, "learning_rate": 1.3026287668305196e-05, "loss": 0.3437, "step": 3470 }, { "epoch": 2.219397137602942, "grad_norm": 3.203145742416382, "learning_rate": 1.3015601624278692e-05, "loss": 0.3045, "step": 3471 }, { "epoch": 2.220036779403534, "grad_norm": 3.0355777740478516, "learning_rate": 1.3004915580252191e-05, "loss": 0.2826, "step": 3472 }, { "epoch": 2.220676421204126, "grad_norm": 2.922559976577759, "learning_rate": 1.299422953622569e-05, "loss": 0.2841, "step": 3473 }, { "epoch": 2.2213160630047173, "grad_norm": 3.310992956161499, "learning_rate": 1.2983543492199188e-05, "loss": 0.2893, "step": 3474 }, { "epoch": 2.221955704805309, "grad_norm": 2.6760876178741455, "learning_rate": 1.2972857448172688e-05, "loss": 0.2732, "step": 3475 }, { "epoch": 2.2225953466059005, "grad_norm": 2.867703676223755, "learning_rate": 1.2962171404146187e-05, "loss": 0.299, "step": 3476 }, { "epoch": 2.2232349884064924, "grad_norm": 2.7198235988616943, "learning_rate": 1.2951485360119683e-05, "loss": 0.2922, "step": 3477 }, { "epoch": 2.223874630207084, "grad_norm": 3.2691850662231445, "learning_rate": 1.2940799316093182e-05, "loss": 0.3039, "step": 3478 }, { "epoch": 2.2245142720076756, "grad_norm": 2.9139389991760254, "learning_rate": 1.2930113272066682e-05, "loss": 0.3006, "step": 3479 }, { "epoch": 2.2251539138082674, "grad_norm": 3.0620779991149902, "learning_rate": 1.291942722804018e-05, "loss": 0.3219, "step": 3480 }, { "epoch": 2.225793555608859, "grad_norm": 3.0976994037628174, "learning_rate": 1.2908741184013679e-05, "loss": 0.3073, "step": 3481 }, { "epoch": 2.2264331974094507, "grad_norm": 2.9936912059783936, "learning_rate": 1.2898055139987178e-05, "loss": 0.3193, "step": 3482 }, { "epoch": 2.2270728392100425, "grad_norm": 2.6903512477874756, "learning_rate": 1.2887369095960674e-05, "loss": 0.2939, "step": 3483 }, { "epoch": 2.227712481010634, "grad_norm": 3.3316521644592285, "learning_rate": 1.2876683051934174e-05, "loss": 0.2894, "step": 3484 }, { "epoch": 2.2283521228112257, "grad_norm": 2.9921982288360596, "learning_rate": 1.2865997007907673e-05, "loss": 0.3064, "step": 3485 }, { "epoch": 2.2289917646118176, "grad_norm": 2.711712598800659, "learning_rate": 1.2855310963881172e-05, "loss": 0.2814, "step": 3486 }, { "epoch": 2.229631406412409, "grad_norm": 2.6264872550964355, "learning_rate": 1.284462491985467e-05, "loss": 0.2915, "step": 3487 }, { "epoch": 2.230271048213001, "grad_norm": 2.4429709911346436, "learning_rate": 1.283393887582817e-05, "loss": 0.268, "step": 3488 }, { "epoch": 2.230910690013592, "grad_norm": 2.457186698913574, "learning_rate": 1.2823252831801669e-05, "loss": 0.2916, "step": 3489 }, { "epoch": 2.231550331814184, "grad_norm": 3.016545534133911, "learning_rate": 1.2812566787775165e-05, "loss": 0.2995, "step": 3490 }, { "epoch": 2.232189973614776, "grad_norm": 2.7489140033721924, "learning_rate": 1.2801880743748666e-05, "loss": 0.2965, "step": 3491 }, { "epoch": 2.2328296154153673, "grad_norm": 2.608473777770996, "learning_rate": 1.2791194699722165e-05, "loss": 0.2758, "step": 3492 }, { "epoch": 2.233469257215959, "grad_norm": 3.392732858657837, "learning_rate": 1.2780508655695661e-05, "loss": 0.3289, "step": 3493 }, { "epoch": 2.234108899016551, "grad_norm": 3.0134336948394775, "learning_rate": 1.276982261166916e-05, "loss": 0.3151, "step": 3494 }, { "epoch": 2.2347485408171424, "grad_norm": 2.6988487243652344, "learning_rate": 1.275913656764266e-05, "loss": 0.2755, "step": 3495 }, { "epoch": 2.235388182617734, "grad_norm": 3.099886655807495, "learning_rate": 1.2748450523616157e-05, "loss": 0.3069, "step": 3496 }, { "epoch": 2.2360278244183256, "grad_norm": 2.533621072769165, "learning_rate": 1.2737764479589657e-05, "loss": 0.2794, "step": 3497 }, { "epoch": 2.2366674662189174, "grad_norm": 2.615140676498413, "learning_rate": 1.2727078435563156e-05, "loss": 0.2849, "step": 3498 }, { "epoch": 2.2373071080195093, "grad_norm": 2.7561891078948975, "learning_rate": 1.2716392391536655e-05, "loss": 0.2835, "step": 3499 }, { "epoch": 2.2379467498201007, "grad_norm": 2.9579265117645264, "learning_rate": 1.2705706347510151e-05, "loss": 0.2871, "step": 3500 }, { "epoch": 2.2385863916206925, "grad_norm": 2.5754003524780273, "learning_rate": 1.269502030348365e-05, "loss": 0.2673, "step": 3501 }, { "epoch": 2.239226033421284, "grad_norm": 3.4438931941986084, "learning_rate": 1.268433425945715e-05, "loss": 0.3123, "step": 3502 }, { "epoch": 2.2398656752218757, "grad_norm": 2.4750845432281494, "learning_rate": 1.2673648215430648e-05, "loss": 0.2662, "step": 3503 }, { "epoch": 2.2405053170224676, "grad_norm": 2.9451913833618164, "learning_rate": 1.2662962171404147e-05, "loss": 0.2835, "step": 3504 }, { "epoch": 2.241144958823059, "grad_norm": 2.945578098297119, "learning_rate": 1.2652276127377647e-05, "loss": 0.2939, "step": 3505 }, { "epoch": 2.241784600623651, "grad_norm": 2.783414125442505, "learning_rate": 1.2641590083351143e-05, "loss": 0.2902, "step": 3506 }, { "epoch": 2.242424242424242, "grad_norm": 2.7330236434936523, "learning_rate": 1.2630904039324642e-05, "loss": 0.284, "step": 3507 }, { "epoch": 2.243063884224834, "grad_norm": 3.278259515762329, "learning_rate": 1.2620217995298141e-05, "loss": 0.3287, "step": 3508 }, { "epoch": 2.243703526025426, "grad_norm": 2.8566737174987793, "learning_rate": 1.2609531951271639e-05, "loss": 0.2773, "step": 3509 }, { "epoch": 2.2443431678260173, "grad_norm": 3.131185531616211, "learning_rate": 1.2598845907245138e-05, "loss": 0.2857, "step": 3510 }, { "epoch": 2.244982809626609, "grad_norm": 2.4174184799194336, "learning_rate": 1.2588159863218638e-05, "loss": 0.269, "step": 3511 }, { "epoch": 2.245622451427201, "grad_norm": 2.4447731971740723, "learning_rate": 1.2577473819192134e-05, "loss": 0.2692, "step": 3512 }, { "epoch": 2.2462620932277924, "grad_norm": 3.203326940536499, "learning_rate": 1.2566787775165633e-05, "loss": 0.3228, "step": 3513 }, { "epoch": 2.246901735028384, "grad_norm": 2.9603841304779053, "learning_rate": 1.2556101731139134e-05, "loss": 0.3081, "step": 3514 }, { "epoch": 2.2475413768289756, "grad_norm": 2.5194952487945557, "learning_rate": 1.2545415687112633e-05, "loss": 0.2684, "step": 3515 }, { "epoch": 2.2481810186295674, "grad_norm": 2.6615219116210938, "learning_rate": 1.253472964308613e-05, "loss": 0.2706, "step": 3516 }, { "epoch": 2.2488206604301593, "grad_norm": 2.532273054122925, "learning_rate": 1.2524043599059629e-05, "loss": 0.2542, "step": 3517 }, { "epoch": 2.2494603022307507, "grad_norm": 2.634317636489868, "learning_rate": 1.2513357555033128e-05, "loss": 0.2808, "step": 3518 }, { "epoch": 2.2500999440313425, "grad_norm": 2.510207414627075, "learning_rate": 1.2502671511006626e-05, "loss": 0.2723, "step": 3519 }, { "epoch": 2.2507395858319343, "grad_norm": 2.733276605606079, "learning_rate": 1.2491985466980125e-05, "loss": 0.2714, "step": 3520 }, { "epoch": 2.2513792276325257, "grad_norm": 2.5398309230804443, "learning_rate": 1.2481299422953623e-05, "loss": 0.2778, "step": 3521 }, { "epoch": 2.2520188694331176, "grad_norm": 2.616506576538086, "learning_rate": 1.2470613378927122e-05, "loss": 0.2673, "step": 3522 }, { "epoch": 2.252658511233709, "grad_norm": 2.689331293106079, "learning_rate": 1.245992733490062e-05, "loss": 0.2695, "step": 3523 }, { "epoch": 2.253298153034301, "grad_norm": 3.1806883811950684, "learning_rate": 1.244924129087412e-05, "loss": 0.2884, "step": 3524 }, { "epoch": 2.2539377948348926, "grad_norm": 3.4878897666931152, "learning_rate": 1.2438555246847617e-05, "loss": 0.3052, "step": 3525 }, { "epoch": 2.254577436635484, "grad_norm": 2.564763069152832, "learning_rate": 1.2427869202821116e-05, "loss": 0.2591, "step": 3526 }, { "epoch": 2.255217078436076, "grad_norm": 3.0779974460601807, "learning_rate": 1.2417183158794616e-05, "loss": 0.2996, "step": 3527 }, { "epoch": 2.2558567202366673, "grad_norm": 3.2080490589141846, "learning_rate": 1.2406497114768113e-05, "loss": 0.3045, "step": 3528 }, { "epoch": 2.256496362037259, "grad_norm": 2.921027421951294, "learning_rate": 1.2395811070741611e-05, "loss": 0.2745, "step": 3529 }, { "epoch": 2.257136003837851, "grad_norm": 2.5587399005889893, "learning_rate": 1.238512502671511e-05, "loss": 0.2563, "step": 3530 }, { "epoch": 2.2577756456384424, "grad_norm": 2.963634967803955, "learning_rate": 1.237443898268861e-05, "loss": 0.2807, "step": 3531 }, { "epoch": 2.258415287439034, "grad_norm": 2.8558361530303955, "learning_rate": 1.2363752938662109e-05, "loss": 0.2667, "step": 3532 }, { "epoch": 2.2590549292396256, "grad_norm": 3.426204204559326, "learning_rate": 1.2353066894635607e-05, "loss": 0.3137, "step": 3533 }, { "epoch": 2.2596945710402174, "grad_norm": 3.069042444229126, "learning_rate": 1.2342380850609104e-05, "loss": 0.2926, "step": 3534 }, { "epoch": 2.2603342128408093, "grad_norm": 3.452301263809204, "learning_rate": 1.2331694806582604e-05, "loss": 0.3159, "step": 3535 }, { "epoch": 2.2609738546414007, "grad_norm": 3.6270313262939453, "learning_rate": 1.2321008762556101e-05, "loss": 0.3129, "step": 3536 }, { "epoch": 2.2616134964419925, "grad_norm": 3.6193034648895264, "learning_rate": 1.2310322718529602e-05, "loss": 0.3215, "step": 3537 }, { "epoch": 2.2622531382425843, "grad_norm": 2.4998440742492676, "learning_rate": 1.22996366745031e-05, "loss": 0.2587, "step": 3538 }, { "epoch": 2.2628927800431757, "grad_norm": 3.1039974689483643, "learning_rate": 1.2288950630476598e-05, "loss": 0.3018, "step": 3539 }, { "epoch": 2.2635324218437676, "grad_norm": 2.9664714336395264, "learning_rate": 1.2278264586450097e-05, "loss": 0.306, "step": 3540 }, { "epoch": 2.264172063644359, "grad_norm": 3.3815581798553467, "learning_rate": 1.2267578542423595e-05, "loss": 0.3236, "step": 3541 }, { "epoch": 2.264811705444951, "grad_norm": 2.8701741695404053, "learning_rate": 1.2256892498397094e-05, "loss": 0.3001, "step": 3542 }, { "epoch": 2.2654513472455426, "grad_norm": 2.553720712661743, "learning_rate": 1.2246206454370594e-05, "loss": 0.2727, "step": 3543 }, { "epoch": 2.266090989046134, "grad_norm": 3.5508580207824707, "learning_rate": 1.2235520410344091e-05, "loss": 0.3707, "step": 3544 }, { "epoch": 2.266730630846726, "grad_norm": 2.6788525581359863, "learning_rate": 1.222483436631759e-05, "loss": 0.2791, "step": 3545 }, { "epoch": 2.2673702726473177, "grad_norm": 3.6063945293426514, "learning_rate": 1.2214148322291088e-05, "loss": 0.2972, "step": 3546 }, { "epoch": 2.268009914447909, "grad_norm": 2.747265338897705, "learning_rate": 1.2203462278264586e-05, "loss": 0.2586, "step": 3547 }, { "epoch": 2.268649556248501, "grad_norm": 2.4529383182525635, "learning_rate": 1.2192776234238085e-05, "loss": 0.2541, "step": 3548 }, { "epoch": 2.2692891980490923, "grad_norm": 3.0293221473693848, "learning_rate": 1.2182090190211585e-05, "loss": 0.3092, "step": 3549 }, { "epoch": 2.269928839849684, "grad_norm": 2.801374673843384, "learning_rate": 1.2171404146185082e-05, "loss": 0.2795, "step": 3550 }, { "epoch": 2.270568481650276, "grad_norm": 3.0589401721954346, "learning_rate": 1.2160718102158582e-05, "loss": 0.3201, "step": 3551 }, { "epoch": 2.2712081234508674, "grad_norm": 2.9472100734710693, "learning_rate": 1.215003205813208e-05, "loss": 0.3126, "step": 3552 }, { "epoch": 2.2718477652514593, "grad_norm": 2.8621063232421875, "learning_rate": 1.2139346014105579e-05, "loss": 0.3024, "step": 3553 }, { "epoch": 2.2724874070520507, "grad_norm": 2.146125316619873, "learning_rate": 1.2128659970079078e-05, "loss": 0.2638, "step": 3554 }, { "epoch": 2.2731270488526425, "grad_norm": 3.0356833934783936, "learning_rate": 1.2117973926052576e-05, "loss": 0.294, "step": 3555 }, { "epoch": 2.2737666906532343, "grad_norm": 2.876336097717285, "learning_rate": 1.2107287882026075e-05, "loss": 0.299, "step": 3556 }, { "epoch": 2.2744063324538257, "grad_norm": 2.3675389289855957, "learning_rate": 1.2096601837999573e-05, "loss": 0.2381, "step": 3557 }, { "epoch": 2.2750459742544176, "grad_norm": 2.785595417022705, "learning_rate": 1.208591579397307e-05, "loss": 0.2713, "step": 3558 }, { "epoch": 2.275685616055009, "grad_norm": 3.246232509613037, "learning_rate": 1.207522974994657e-05, "loss": 0.2857, "step": 3559 }, { "epoch": 2.276325257855601, "grad_norm": 3.060328245162964, "learning_rate": 1.2064543705920069e-05, "loss": 0.3072, "step": 3560 }, { "epoch": 2.2769648996561926, "grad_norm": 3.2622430324554443, "learning_rate": 1.2053857661893568e-05, "loss": 0.3001, "step": 3561 }, { "epoch": 2.277604541456784, "grad_norm": 3.003283977508545, "learning_rate": 1.2043171617867066e-05, "loss": 0.2907, "step": 3562 }, { "epoch": 2.278244183257376, "grad_norm": 2.7570948600769043, "learning_rate": 1.2032485573840564e-05, "loss": 0.2956, "step": 3563 }, { "epoch": 2.2788838250579677, "grad_norm": 2.963020086288452, "learning_rate": 1.2021799529814063e-05, "loss": 0.2987, "step": 3564 }, { "epoch": 2.279523466858559, "grad_norm": 3.440944194793701, "learning_rate": 1.2011113485787563e-05, "loss": 0.3164, "step": 3565 }, { "epoch": 2.280163108659151, "grad_norm": 2.6674869060516357, "learning_rate": 1.2000427441761062e-05, "loss": 0.2763, "step": 3566 }, { "epoch": 2.280802750459743, "grad_norm": 2.35956072807312, "learning_rate": 1.198974139773456e-05, "loss": 0.246, "step": 3567 }, { "epoch": 2.281442392260334, "grad_norm": 2.8054215908050537, "learning_rate": 1.1979055353708057e-05, "loss": 0.2925, "step": 3568 }, { "epoch": 2.282082034060926, "grad_norm": 3.342362403869629, "learning_rate": 1.1968369309681557e-05, "loss": 0.2962, "step": 3569 }, { "epoch": 2.2827216758615174, "grad_norm": 2.6458470821380615, "learning_rate": 1.1957683265655054e-05, "loss": 0.2823, "step": 3570 }, { "epoch": 2.2833613176621093, "grad_norm": 2.852384090423584, "learning_rate": 1.1946997221628554e-05, "loss": 0.2847, "step": 3571 }, { "epoch": 2.284000959462701, "grad_norm": 3.3162930011749268, "learning_rate": 1.1936311177602053e-05, "loss": 0.3047, "step": 3572 }, { "epoch": 2.2846406012632925, "grad_norm": 2.9299237728118896, "learning_rate": 1.192562513357555e-05, "loss": 0.3103, "step": 3573 }, { "epoch": 2.2852802430638843, "grad_norm": 2.87814998626709, "learning_rate": 1.191493908954905e-05, "loss": 0.2912, "step": 3574 }, { "epoch": 2.2859198848644757, "grad_norm": 3.104611873626709, "learning_rate": 1.1904253045522548e-05, "loss": 0.3076, "step": 3575 }, { "epoch": 2.2865595266650676, "grad_norm": 2.6216070652008057, "learning_rate": 1.1893567001496047e-05, "loss": 0.2493, "step": 3576 }, { "epoch": 2.2871991684656594, "grad_norm": 2.7422173023223877, "learning_rate": 1.1882880957469546e-05, "loss": 0.2779, "step": 3577 }, { "epoch": 2.287838810266251, "grad_norm": 3.13505220413208, "learning_rate": 1.1872194913443044e-05, "loss": 0.2831, "step": 3578 }, { "epoch": 2.2884784520668426, "grad_norm": 3.029228925704956, "learning_rate": 1.1861508869416542e-05, "loss": 0.2738, "step": 3579 }, { "epoch": 2.289118093867434, "grad_norm": 3.0017192363739014, "learning_rate": 1.1850822825390041e-05, "loss": 0.299, "step": 3580 }, { "epoch": 2.289757735668026, "grad_norm": 3.0335376262664795, "learning_rate": 1.1840136781363539e-05, "loss": 0.2707, "step": 3581 }, { "epoch": 2.2903973774686177, "grad_norm": 3.517801284790039, "learning_rate": 1.1829450737337038e-05, "loss": 0.3206, "step": 3582 }, { "epoch": 2.291037019269209, "grad_norm": 3.0517585277557373, "learning_rate": 1.1818764693310537e-05, "loss": 0.2749, "step": 3583 }, { "epoch": 2.291676661069801, "grad_norm": 2.737506866455078, "learning_rate": 1.1808078649284035e-05, "loss": 0.2896, "step": 3584 }, { "epoch": 2.2923163028703923, "grad_norm": 3.2319812774658203, "learning_rate": 1.1797392605257535e-05, "loss": 0.2848, "step": 3585 }, { "epoch": 2.292955944670984, "grad_norm": 2.5811519622802734, "learning_rate": 1.1786706561231032e-05, "loss": 0.2723, "step": 3586 }, { "epoch": 2.293595586471576, "grad_norm": 3.0970749855041504, "learning_rate": 1.1776020517204532e-05, "loss": 0.2942, "step": 3587 }, { "epoch": 2.2942352282721674, "grad_norm": 2.8350048065185547, "learning_rate": 1.1765334473178031e-05, "loss": 0.2902, "step": 3588 }, { "epoch": 2.2948748700727593, "grad_norm": 3.1132586002349854, "learning_rate": 1.1754648429151529e-05, "loss": 0.3253, "step": 3589 }, { "epoch": 2.295514511873351, "grad_norm": 2.8081939220428467, "learning_rate": 1.1743962385125028e-05, "loss": 0.3361, "step": 3590 }, { "epoch": 2.2961541536739425, "grad_norm": 2.7446351051330566, "learning_rate": 1.1733276341098526e-05, "loss": 0.3125, "step": 3591 }, { "epoch": 2.2967937954745343, "grad_norm": 2.469299554824829, "learning_rate": 1.1722590297072023e-05, "loss": 0.2807, "step": 3592 }, { "epoch": 2.297433437275126, "grad_norm": 2.5957143306732178, "learning_rate": 1.1711904253045523e-05, "loss": 0.269, "step": 3593 }, { "epoch": 2.2980730790757176, "grad_norm": 3.183300733566284, "learning_rate": 1.1701218209019022e-05, "loss": 0.3129, "step": 3594 }, { "epoch": 2.2987127208763094, "grad_norm": 3.1013343334198, "learning_rate": 1.1690532164992521e-05, "loss": 0.3364, "step": 3595 }, { "epoch": 2.299352362676901, "grad_norm": 2.8254292011260986, "learning_rate": 1.1679846120966019e-05, "loss": 0.2968, "step": 3596 }, { "epoch": 2.2999920044774926, "grad_norm": 2.916802167892456, "learning_rate": 1.1669160076939517e-05, "loss": 0.3055, "step": 3597 }, { "epoch": 2.3006316462780845, "grad_norm": 2.860269784927368, "learning_rate": 1.1658474032913016e-05, "loss": 0.2841, "step": 3598 }, { "epoch": 2.301271288078676, "grad_norm": 3.069105625152588, "learning_rate": 1.1647787988886515e-05, "loss": 0.3359, "step": 3599 }, { "epoch": 2.3019109298792677, "grad_norm": 2.949805498123169, "learning_rate": 1.1637101944860013e-05, "loss": 0.3142, "step": 3600 }, { "epoch": 2.302550571679859, "grad_norm": 2.347810983657837, "learning_rate": 1.1626415900833512e-05, "loss": 0.2713, "step": 3601 }, { "epoch": 2.303190213480451, "grad_norm": 2.819849967956543, "learning_rate": 1.161572985680701e-05, "loss": 0.2732, "step": 3602 }, { "epoch": 2.303829855281043, "grad_norm": 3.033372640609741, "learning_rate": 1.160504381278051e-05, "loss": 0.3099, "step": 3603 }, { "epoch": 2.304469497081634, "grad_norm": 3.0310096740722656, "learning_rate": 1.1594357768754007e-05, "loss": 0.3128, "step": 3604 }, { "epoch": 2.305109138882226, "grad_norm": 2.5342955589294434, "learning_rate": 1.1583671724727507e-05, "loss": 0.2754, "step": 3605 }, { "epoch": 2.3057487806828174, "grad_norm": 2.884960651397705, "learning_rate": 1.1572985680701006e-05, "loss": 0.287, "step": 3606 }, { "epoch": 2.3063884224834093, "grad_norm": 2.89473032951355, "learning_rate": 1.1562299636674504e-05, "loss": 0.3224, "step": 3607 }, { "epoch": 2.307028064284001, "grad_norm": 2.676666498184204, "learning_rate": 1.1551613592648003e-05, "loss": 0.2937, "step": 3608 }, { "epoch": 2.3076677060845925, "grad_norm": 2.7825429439544678, "learning_rate": 1.15409275486215e-05, "loss": 0.2927, "step": 3609 }, { "epoch": 2.3083073478851843, "grad_norm": 3.067427396774292, "learning_rate": 1.1530241504594998e-05, "loss": 0.3044, "step": 3610 }, { "epoch": 2.3089469896857757, "grad_norm": 2.424522876739502, "learning_rate": 1.15195554605685e-05, "loss": 0.2595, "step": 3611 }, { "epoch": 2.3095866314863676, "grad_norm": 2.830282688140869, "learning_rate": 1.1508869416541997e-05, "loss": 0.293, "step": 3612 }, { "epoch": 2.3102262732869594, "grad_norm": 2.446810007095337, "learning_rate": 1.1498183372515495e-05, "loss": 0.2833, "step": 3613 }, { "epoch": 2.310865915087551, "grad_norm": 2.5802533626556396, "learning_rate": 1.1487497328488994e-05, "loss": 0.2757, "step": 3614 }, { "epoch": 2.3115055568881426, "grad_norm": 3.2124335765838623, "learning_rate": 1.1476811284462492e-05, "loss": 0.2916, "step": 3615 }, { "epoch": 2.3121451986887345, "grad_norm": 3.295328140258789, "learning_rate": 1.1466125240435991e-05, "loss": 0.2986, "step": 3616 }, { "epoch": 2.312784840489326, "grad_norm": 3.008997678756714, "learning_rate": 1.145543919640949e-05, "loss": 0.3017, "step": 3617 }, { "epoch": 2.3134244822899177, "grad_norm": 2.7125957012176514, "learning_rate": 1.1444753152382988e-05, "loss": 0.2679, "step": 3618 }, { "epoch": 2.3140641240905095, "grad_norm": 2.620945692062378, "learning_rate": 1.1434067108356487e-05, "loss": 0.2816, "step": 3619 }, { "epoch": 2.314703765891101, "grad_norm": 2.4135873317718506, "learning_rate": 1.1423381064329985e-05, "loss": 0.2611, "step": 3620 }, { "epoch": 2.315343407691693, "grad_norm": 2.9060771465301514, "learning_rate": 1.1412695020303483e-05, "loss": 0.3122, "step": 3621 }, { "epoch": 2.315983049492284, "grad_norm": 2.7879769802093506, "learning_rate": 1.1402008976276984e-05, "loss": 0.2905, "step": 3622 }, { "epoch": 2.316622691292876, "grad_norm": 3.1545228958129883, "learning_rate": 1.1391322932250481e-05, "loss": 0.2966, "step": 3623 }, { "epoch": 2.317262333093468, "grad_norm": 3.8493826389312744, "learning_rate": 1.138063688822398e-05, "loss": 0.347, "step": 3624 }, { "epoch": 2.3179019748940592, "grad_norm": 3.12675142288208, "learning_rate": 1.1369950844197479e-05, "loss": 0.3052, "step": 3625 }, { "epoch": 2.318541616694651, "grad_norm": 3.5017809867858887, "learning_rate": 1.1359264800170976e-05, "loss": 0.3243, "step": 3626 }, { "epoch": 2.3191812584952425, "grad_norm": 3.026428699493408, "learning_rate": 1.1348578756144476e-05, "loss": 0.2856, "step": 3627 }, { "epoch": 2.3198209002958343, "grad_norm": 2.612839698791504, "learning_rate": 1.1337892712117975e-05, "loss": 0.2697, "step": 3628 }, { "epoch": 2.320460542096426, "grad_norm": 3.0483486652374268, "learning_rate": 1.1327206668091474e-05, "loss": 0.3003, "step": 3629 }, { "epoch": 2.3211001838970176, "grad_norm": 2.959425449371338, "learning_rate": 1.1316520624064972e-05, "loss": 0.2974, "step": 3630 }, { "epoch": 2.3217398256976094, "grad_norm": 3.1794562339782715, "learning_rate": 1.130583458003847e-05, "loss": 0.3078, "step": 3631 }, { "epoch": 2.322379467498201, "grad_norm": 2.986335277557373, "learning_rate": 1.1295148536011969e-05, "loss": 0.3065, "step": 3632 }, { "epoch": 2.3230191092987926, "grad_norm": 2.8978092670440674, "learning_rate": 1.1284462491985467e-05, "loss": 0.3007, "step": 3633 }, { "epoch": 2.3236587510993845, "grad_norm": 3.015186071395874, "learning_rate": 1.1273776447958966e-05, "loss": 0.2925, "step": 3634 }, { "epoch": 2.324298392899976, "grad_norm": 2.970170259475708, "learning_rate": 1.1263090403932465e-05, "loss": 0.2929, "step": 3635 }, { "epoch": 2.3249380347005677, "grad_norm": 2.594212055206299, "learning_rate": 1.1252404359905963e-05, "loss": 0.2692, "step": 3636 }, { "epoch": 2.3255776765011595, "grad_norm": 2.7781248092651367, "learning_rate": 1.1241718315879462e-05, "loss": 0.2988, "step": 3637 }, { "epoch": 2.326217318301751, "grad_norm": 3.0339715480804443, "learning_rate": 1.123103227185296e-05, "loss": 0.3237, "step": 3638 }, { "epoch": 2.3268569601023428, "grad_norm": 3.0787346363067627, "learning_rate": 1.122034622782646e-05, "loss": 0.2851, "step": 3639 }, { "epoch": 2.327496601902934, "grad_norm": 3.1304264068603516, "learning_rate": 1.1209660183799959e-05, "loss": 0.2996, "step": 3640 }, { "epoch": 2.328136243703526, "grad_norm": 2.516671895980835, "learning_rate": 1.1198974139773456e-05, "loss": 0.2806, "step": 3641 }, { "epoch": 2.328775885504118, "grad_norm": 2.9395248889923096, "learning_rate": 1.1188288095746954e-05, "loss": 0.2813, "step": 3642 }, { "epoch": 2.3294155273047092, "grad_norm": 2.470202922821045, "learning_rate": 1.1177602051720453e-05, "loss": 0.2676, "step": 3643 }, { "epoch": 2.330055169105301, "grad_norm": 2.4521126747131348, "learning_rate": 1.1166916007693951e-05, "loss": 0.2614, "step": 3644 }, { "epoch": 2.330694810905893, "grad_norm": 2.8323287963867188, "learning_rate": 1.1156229963667452e-05, "loss": 0.2964, "step": 3645 }, { "epoch": 2.3313344527064843, "grad_norm": 2.8041605949401855, "learning_rate": 1.114554391964095e-05, "loss": 0.3195, "step": 3646 }, { "epoch": 2.331974094507076, "grad_norm": 2.9341700077056885, "learning_rate": 1.1134857875614448e-05, "loss": 0.2682, "step": 3647 }, { "epoch": 2.3326137363076676, "grad_norm": 2.4643263816833496, "learning_rate": 1.1124171831587947e-05, "loss": 0.2755, "step": 3648 }, { "epoch": 2.3332533781082594, "grad_norm": 2.8114049434661865, "learning_rate": 1.1113485787561445e-05, "loss": 0.3238, "step": 3649 }, { "epoch": 2.3338930199088512, "grad_norm": 2.4782729148864746, "learning_rate": 1.1102799743534944e-05, "loss": 0.2692, "step": 3650 }, { "epoch": 2.3345326617094426, "grad_norm": 2.503711700439453, "learning_rate": 1.1092113699508443e-05, "loss": 0.2578, "step": 3651 }, { "epoch": 2.3351723035100345, "grad_norm": 2.252203941345215, "learning_rate": 1.1081427655481941e-05, "loss": 0.2558, "step": 3652 }, { "epoch": 2.335811945310626, "grad_norm": 2.3472766876220703, "learning_rate": 1.107074161145544e-05, "loss": 0.2442, "step": 3653 }, { "epoch": 2.3364515871112177, "grad_norm": 2.6745517253875732, "learning_rate": 1.1060055567428938e-05, "loss": 0.2721, "step": 3654 }, { "epoch": 2.3370912289118095, "grad_norm": 2.808493137359619, "learning_rate": 1.1049369523402436e-05, "loss": 0.2842, "step": 3655 }, { "epoch": 2.337730870712401, "grad_norm": 3.1037187576293945, "learning_rate": 1.1038683479375935e-05, "loss": 0.2903, "step": 3656 }, { "epoch": 2.3383705125129928, "grad_norm": 3.305421829223633, "learning_rate": 1.1027997435349434e-05, "loss": 0.3088, "step": 3657 }, { "epoch": 2.339010154313584, "grad_norm": 2.80588960647583, "learning_rate": 1.1017311391322934e-05, "loss": 0.2875, "step": 3658 }, { "epoch": 2.339649796114176, "grad_norm": 2.851426601409912, "learning_rate": 1.1006625347296431e-05, "loss": 0.2864, "step": 3659 }, { "epoch": 2.340289437914768, "grad_norm": 3.5976970195770264, "learning_rate": 1.0995939303269929e-05, "loss": 0.2983, "step": 3660 }, { "epoch": 2.3409290797153592, "grad_norm": 2.727888584136963, "learning_rate": 1.0985253259243428e-05, "loss": 0.2842, "step": 3661 }, { "epoch": 2.341568721515951, "grad_norm": 3.325143575668335, "learning_rate": 1.0974567215216928e-05, "loss": 0.2972, "step": 3662 }, { "epoch": 2.342208363316543, "grad_norm": 3.104851245880127, "learning_rate": 1.0963881171190425e-05, "loss": 0.3287, "step": 3663 }, { "epoch": 2.3428480051171343, "grad_norm": 3.4042844772338867, "learning_rate": 1.0953195127163925e-05, "loss": 0.2965, "step": 3664 }, { "epoch": 2.343487646917726, "grad_norm": 2.57411527633667, "learning_rate": 1.0942509083137422e-05, "loss": 0.259, "step": 3665 }, { "epoch": 2.344127288718318, "grad_norm": 3.6349639892578125, "learning_rate": 1.0931823039110922e-05, "loss": 0.3281, "step": 3666 }, { "epoch": 2.3447669305189094, "grad_norm": 2.897465705871582, "learning_rate": 1.092113699508442e-05, "loss": 0.2843, "step": 3667 }, { "epoch": 2.3454065723195012, "grad_norm": 2.945551872253418, "learning_rate": 1.0910450951057919e-05, "loss": 0.2843, "step": 3668 }, { "epoch": 2.3460462141200926, "grad_norm": 2.63677716255188, "learning_rate": 1.0899764907031418e-05, "loss": 0.2751, "step": 3669 }, { "epoch": 2.3466858559206845, "grad_norm": 2.6026413440704346, "learning_rate": 1.0889078863004916e-05, "loss": 0.2596, "step": 3670 }, { "epoch": 2.3473254977212763, "grad_norm": 2.672790288925171, "learning_rate": 1.0878392818978415e-05, "loss": 0.2818, "step": 3671 }, { "epoch": 2.3479651395218677, "grad_norm": 3.1021134853363037, "learning_rate": 1.0867706774951913e-05, "loss": 0.3195, "step": 3672 }, { "epoch": 2.3486047813224595, "grad_norm": 2.8973262310028076, "learning_rate": 1.0857020730925412e-05, "loss": 0.2964, "step": 3673 }, { "epoch": 2.349244423123051, "grad_norm": 2.77655029296875, "learning_rate": 1.0846334686898912e-05, "loss": 0.3002, "step": 3674 }, { "epoch": 2.3498840649236428, "grad_norm": 3.0009922981262207, "learning_rate": 1.083564864287241e-05, "loss": 0.2659, "step": 3675 }, { "epoch": 2.3505237067242346, "grad_norm": 2.9666941165924072, "learning_rate": 1.0824962598845907e-05, "loss": 0.2883, "step": 3676 }, { "epoch": 2.351163348524826, "grad_norm": 2.9443798065185547, "learning_rate": 1.0814276554819406e-05, "loss": 0.2621, "step": 3677 }, { "epoch": 2.351802990325418, "grad_norm": 3.0699689388275146, "learning_rate": 1.0803590510792904e-05, "loss": 0.3216, "step": 3678 }, { "epoch": 2.3524426321260092, "grad_norm": 2.7166452407836914, "learning_rate": 1.0792904466766403e-05, "loss": 0.3031, "step": 3679 }, { "epoch": 2.353082273926601, "grad_norm": 2.7714357376098633, "learning_rate": 1.0782218422739903e-05, "loss": 0.2893, "step": 3680 }, { "epoch": 2.353721915727193, "grad_norm": 2.809751272201538, "learning_rate": 1.07715323787134e-05, "loss": 0.2869, "step": 3681 }, { "epoch": 2.3543615575277843, "grad_norm": 2.7445809841156006, "learning_rate": 1.07608463346869e-05, "loss": 0.2663, "step": 3682 }, { "epoch": 2.355001199328376, "grad_norm": 2.7037882804870605, "learning_rate": 1.0750160290660397e-05, "loss": 0.2791, "step": 3683 }, { "epoch": 2.3556408411289675, "grad_norm": 2.7959351539611816, "learning_rate": 1.0739474246633897e-05, "loss": 0.2668, "step": 3684 }, { "epoch": 2.3562804829295594, "grad_norm": 2.936558723449707, "learning_rate": 1.0728788202607396e-05, "loss": 0.2747, "step": 3685 }, { "epoch": 2.3569201247301512, "grad_norm": 2.8345210552215576, "learning_rate": 1.0718102158580894e-05, "loss": 0.2765, "step": 3686 }, { "epoch": 2.3575597665307426, "grad_norm": 2.9661409854888916, "learning_rate": 1.0707416114554393e-05, "loss": 0.2932, "step": 3687 }, { "epoch": 2.3581994083313345, "grad_norm": 2.79435133934021, "learning_rate": 1.0696730070527891e-05, "loss": 0.2833, "step": 3688 }, { "epoch": 2.3588390501319263, "grad_norm": 3.4028706550598145, "learning_rate": 1.0686044026501389e-05, "loss": 0.3369, "step": 3689 }, { "epoch": 2.3594786919325177, "grad_norm": 2.9375522136688232, "learning_rate": 1.0675357982474888e-05, "loss": 0.2764, "step": 3690 }, { "epoch": 2.3601183337331095, "grad_norm": 2.9318432807922363, "learning_rate": 1.0664671938448387e-05, "loss": 0.2938, "step": 3691 }, { "epoch": 2.3607579755337014, "grad_norm": 3.0722882747650146, "learning_rate": 1.0653985894421887e-05, "loss": 0.3198, "step": 3692 }, { "epoch": 2.3613976173342928, "grad_norm": 3.190333366394043, "learning_rate": 1.0643299850395384e-05, "loss": 0.314, "step": 3693 }, { "epoch": 2.3620372591348846, "grad_norm": 2.869821548461914, "learning_rate": 1.0632613806368882e-05, "loss": 0.297, "step": 3694 }, { "epoch": 2.362676900935476, "grad_norm": 2.383671760559082, "learning_rate": 1.0621927762342381e-05, "loss": 0.2533, "step": 3695 }, { "epoch": 2.363316542736068, "grad_norm": 2.9709298610687256, "learning_rate": 1.061124171831588e-05, "loss": 0.2927, "step": 3696 }, { "epoch": 2.3639561845366597, "grad_norm": 2.5270161628723145, "learning_rate": 1.0600555674289378e-05, "loss": 0.2609, "step": 3697 }, { "epoch": 2.364595826337251, "grad_norm": 2.8073136806488037, "learning_rate": 1.0589869630262878e-05, "loss": 0.3017, "step": 3698 }, { "epoch": 2.365235468137843, "grad_norm": 2.8503897190093994, "learning_rate": 1.0579183586236375e-05, "loss": 0.2802, "step": 3699 }, { "epoch": 2.3658751099384343, "grad_norm": 3.4927291870117188, "learning_rate": 1.0568497542209875e-05, "loss": 0.3041, "step": 3700 }, { "epoch": 2.366514751739026, "grad_norm": 2.66800856590271, "learning_rate": 1.0557811498183372e-05, "loss": 0.2682, "step": 3701 }, { "epoch": 2.367154393539618, "grad_norm": 2.816920280456543, "learning_rate": 1.0547125454156872e-05, "loss": 0.2908, "step": 3702 }, { "epoch": 2.3677940353402094, "grad_norm": 2.8394041061401367, "learning_rate": 1.0536439410130371e-05, "loss": 0.2957, "step": 3703 }, { "epoch": 2.368433677140801, "grad_norm": 2.9479761123657227, "learning_rate": 1.0525753366103869e-05, "loss": 0.2872, "step": 3704 }, { "epoch": 2.3690733189413926, "grad_norm": 2.8398666381835938, "learning_rate": 1.0515067322077366e-05, "loss": 0.2759, "step": 3705 }, { "epoch": 2.3697129607419845, "grad_norm": 2.759230375289917, "learning_rate": 1.0504381278050866e-05, "loss": 0.2443, "step": 3706 }, { "epoch": 2.3703526025425763, "grad_norm": 3.539905071258545, "learning_rate": 1.0493695234024365e-05, "loss": 0.3492, "step": 3707 }, { "epoch": 2.3709922443431677, "grad_norm": 2.892258882522583, "learning_rate": 1.0483009189997865e-05, "loss": 0.2783, "step": 3708 }, { "epoch": 2.3716318861437595, "grad_norm": 3.180210828781128, "learning_rate": 1.0472323145971362e-05, "loss": 0.3087, "step": 3709 }, { "epoch": 2.372271527944351, "grad_norm": 2.7415599822998047, "learning_rate": 1.046163710194486e-05, "loss": 0.2646, "step": 3710 }, { "epoch": 2.3729111697449428, "grad_norm": 2.877748489379883, "learning_rate": 1.045095105791836e-05, "loss": 0.2888, "step": 3711 }, { "epoch": 2.3735508115455346, "grad_norm": 3.225186586380005, "learning_rate": 1.0440265013891857e-05, "loss": 0.2963, "step": 3712 }, { "epoch": 2.374190453346126, "grad_norm": 3.4280874729156494, "learning_rate": 1.0429578969865356e-05, "loss": 0.3265, "step": 3713 }, { "epoch": 2.374830095146718, "grad_norm": 3.0741846561431885, "learning_rate": 1.0418892925838856e-05, "loss": 0.3147, "step": 3714 }, { "epoch": 2.3754697369473097, "grad_norm": 2.8286306858062744, "learning_rate": 1.0408206881812353e-05, "loss": 0.2968, "step": 3715 }, { "epoch": 2.376109378747901, "grad_norm": 3.084357500076294, "learning_rate": 1.0397520837785853e-05, "loss": 0.3014, "step": 3716 }, { "epoch": 2.376749020548493, "grad_norm": 2.366436719894409, "learning_rate": 1.038683479375935e-05, "loss": 0.2577, "step": 3717 }, { "epoch": 2.3773886623490847, "grad_norm": 3.192760705947876, "learning_rate": 1.0376148749732848e-05, "loss": 0.3105, "step": 3718 }, { "epoch": 2.378028304149676, "grad_norm": 2.9491522312164307, "learning_rate": 1.0365462705706349e-05, "loss": 0.2733, "step": 3719 }, { "epoch": 2.378667945950268, "grad_norm": 2.8468129634857178, "learning_rate": 1.0354776661679847e-05, "loss": 0.2958, "step": 3720 }, { "epoch": 2.3793075877508594, "grad_norm": 3.020120620727539, "learning_rate": 1.0344090617653346e-05, "loss": 0.287, "step": 3721 }, { "epoch": 2.379947229551451, "grad_norm": 2.782242774963379, "learning_rate": 1.0333404573626844e-05, "loss": 0.2834, "step": 3722 }, { "epoch": 2.380586871352043, "grad_norm": 2.4562535285949707, "learning_rate": 1.0322718529600341e-05, "loss": 0.265, "step": 3723 }, { "epoch": 2.3812265131526344, "grad_norm": 3.276191473007202, "learning_rate": 1.031203248557384e-05, "loss": 0.2997, "step": 3724 }, { "epoch": 2.3818661549532263, "grad_norm": 3.6544899940490723, "learning_rate": 1.030134644154734e-05, "loss": 0.2853, "step": 3725 }, { "epoch": 2.3825057967538177, "grad_norm": 3.0346362590789795, "learning_rate": 1.0290660397520838e-05, "loss": 0.3135, "step": 3726 }, { "epoch": 2.3831454385544095, "grad_norm": 2.6481335163116455, "learning_rate": 1.0279974353494337e-05, "loss": 0.2849, "step": 3727 }, { "epoch": 2.3837850803550014, "grad_norm": 3.0483789443969727, "learning_rate": 1.0269288309467835e-05, "loss": 0.3003, "step": 3728 }, { "epoch": 2.3844247221555928, "grad_norm": 2.8507449626922607, "learning_rate": 1.0258602265441334e-05, "loss": 0.2897, "step": 3729 }, { "epoch": 2.3850643639561846, "grad_norm": 3.2301740646362305, "learning_rate": 1.0247916221414834e-05, "loss": 0.3326, "step": 3730 }, { "epoch": 2.385704005756776, "grad_norm": 2.715714931488037, "learning_rate": 1.0237230177388331e-05, "loss": 0.2821, "step": 3731 }, { "epoch": 2.386343647557368, "grad_norm": 3.216115951538086, "learning_rate": 1.022654413336183e-05, "loss": 0.2876, "step": 3732 }, { "epoch": 2.3869832893579597, "grad_norm": 2.814248561859131, "learning_rate": 1.0215858089335328e-05, "loss": 0.2834, "step": 3733 }, { "epoch": 2.387622931158551, "grad_norm": 3.2641689777374268, "learning_rate": 1.0205172045308826e-05, "loss": 0.3174, "step": 3734 }, { "epoch": 2.388262572959143, "grad_norm": 3.176546573638916, "learning_rate": 1.0194486001282325e-05, "loss": 0.3059, "step": 3735 }, { "epoch": 2.3889022147597343, "grad_norm": 4.12556791305542, "learning_rate": 1.0183799957255825e-05, "loss": 0.2998, "step": 3736 }, { "epoch": 2.389541856560326, "grad_norm": 3.233046770095825, "learning_rate": 1.0173113913229324e-05, "loss": 0.3255, "step": 3737 }, { "epoch": 2.390181498360918, "grad_norm": 3.198136329650879, "learning_rate": 1.0162427869202822e-05, "loss": 0.3273, "step": 3738 }, { "epoch": 2.3908211401615094, "grad_norm": 3.109236478805542, "learning_rate": 1.015174182517632e-05, "loss": 0.3073, "step": 3739 }, { "epoch": 2.391460781962101, "grad_norm": 3.0272021293640137, "learning_rate": 1.0141055781149819e-05, "loss": 0.2934, "step": 3740 }, { "epoch": 2.392100423762693, "grad_norm": 2.720465660095215, "learning_rate": 1.0130369737123316e-05, "loss": 0.2869, "step": 3741 }, { "epoch": 2.3927400655632844, "grad_norm": 2.529658794403076, "learning_rate": 1.0119683693096817e-05, "loss": 0.2758, "step": 3742 }, { "epoch": 2.3933797073638763, "grad_norm": 3.0153563022613525, "learning_rate": 1.0108997649070315e-05, "loss": 0.282, "step": 3743 }, { "epoch": 2.394019349164468, "grad_norm": 3.0945286750793457, "learning_rate": 1.0098311605043813e-05, "loss": 0.287, "step": 3744 }, { "epoch": 2.3946589909650595, "grad_norm": 2.4137110710144043, "learning_rate": 1.0087625561017312e-05, "loss": 0.2544, "step": 3745 }, { "epoch": 2.3952986327656514, "grad_norm": 2.4856338500976562, "learning_rate": 1.007693951699081e-05, "loss": 0.2748, "step": 3746 }, { "epoch": 2.3959382745662428, "grad_norm": 3.0739831924438477, "learning_rate": 1.006625347296431e-05, "loss": 0.2976, "step": 3747 }, { "epoch": 2.3965779163668346, "grad_norm": 3.1753807067871094, "learning_rate": 1.0055567428937809e-05, "loss": 0.3064, "step": 3748 }, { "epoch": 2.3972175581674264, "grad_norm": 3.212027072906494, "learning_rate": 1.0044881384911306e-05, "loss": 0.313, "step": 3749 }, { "epoch": 2.397857199968018, "grad_norm": 2.9604339599609375, "learning_rate": 1.0034195340884806e-05, "loss": 0.282, "step": 3750 }, { "epoch": 2.3984968417686097, "grad_norm": 3.2050273418426514, "learning_rate": 1.0023509296858303e-05, "loss": 0.2993, "step": 3751 }, { "epoch": 2.399136483569201, "grad_norm": 3.095064878463745, "learning_rate": 1.0012823252831801e-05, "loss": 0.306, "step": 3752 }, { "epoch": 2.399776125369793, "grad_norm": 2.8404853343963623, "learning_rate": 1.0002137208805302e-05, "loss": 0.2786, "step": 3753 }, { "epoch": 2.4004157671703847, "grad_norm": 3.09138560295105, "learning_rate": 9.9914511647788e-06, "loss": 0.3047, "step": 3754 }, { "epoch": 2.401055408970976, "grad_norm": 2.408557653427124, "learning_rate": 9.980765120752297e-06, "loss": 0.2469, "step": 3755 }, { "epoch": 2.401695050771568, "grad_norm": 2.66947865486145, "learning_rate": 9.970079076725797e-06, "loss": 0.2922, "step": 3756 }, { "epoch": 2.4023346925721594, "grad_norm": 3.7358579635620117, "learning_rate": 9.959393032699294e-06, "loss": 0.327, "step": 3757 }, { "epoch": 2.402974334372751, "grad_norm": 3.0420963764190674, "learning_rate": 9.948706988672794e-06, "loss": 0.3022, "step": 3758 }, { "epoch": 2.403613976173343, "grad_norm": 2.7667346000671387, "learning_rate": 9.938020944646293e-06, "loss": 0.2858, "step": 3759 }, { "epoch": 2.4042536179739344, "grad_norm": 2.8193728923797607, "learning_rate": 9.92733490061979e-06, "loss": 0.2927, "step": 3760 }, { "epoch": 2.4048932597745263, "grad_norm": 3.4549965858459473, "learning_rate": 9.91664885659329e-06, "loss": 0.33, "step": 3761 }, { "epoch": 2.405532901575118, "grad_norm": 3.107081174850464, "learning_rate": 9.905962812566788e-06, "loss": 0.3167, "step": 3762 }, { "epoch": 2.4061725433757095, "grad_norm": 3.1439502239227295, "learning_rate": 9.895276768540287e-06, "loss": 0.3096, "step": 3763 }, { "epoch": 2.4068121851763014, "grad_norm": 2.7166993618011475, "learning_rate": 9.884590724513785e-06, "loss": 0.2972, "step": 3764 }, { "epoch": 2.4074518269768928, "grad_norm": 2.7572853565216064, "learning_rate": 9.873904680487284e-06, "loss": 0.2771, "step": 3765 }, { "epoch": 2.4080914687774846, "grad_norm": 2.433554172515869, "learning_rate": 9.863218636460784e-06, "loss": 0.2796, "step": 3766 }, { "epoch": 2.4087311105780764, "grad_norm": 3.07726788520813, "learning_rate": 9.852532592434281e-06, "loss": 0.3298, "step": 3767 }, { "epoch": 2.409370752378668, "grad_norm": 2.5659122467041016, "learning_rate": 9.841846548407779e-06, "loss": 0.2553, "step": 3768 }, { "epoch": 2.4100103941792597, "grad_norm": 2.7963790893554688, "learning_rate": 9.831160504381278e-06, "loss": 0.271, "step": 3769 }, { "epoch": 2.4106500359798515, "grad_norm": 3.315323829650879, "learning_rate": 9.820474460354778e-06, "loss": 0.3064, "step": 3770 }, { "epoch": 2.411289677780443, "grad_norm": 3.1749017238616943, "learning_rate": 9.809788416328277e-06, "loss": 0.2982, "step": 3771 }, { "epoch": 2.4119293195810347, "grad_norm": 3.3845622539520264, "learning_rate": 9.799102372301775e-06, "loss": 0.3226, "step": 3772 }, { "epoch": 2.412568961381626, "grad_norm": 4.004214286804199, "learning_rate": 9.788416328275272e-06, "loss": 0.4031, "step": 3773 }, { "epoch": 2.413208603182218, "grad_norm": 3.194394111633301, "learning_rate": 9.777730284248772e-06, "loss": 0.2979, "step": 3774 }, { "epoch": 2.41384824498281, "grad_norm": 2.644986629486084, "learning_rate": 9.76704424022227e-06, "loss": 0.2844, "step": 3775 }, { "epoch": 2.414487886783401, "grad_norm": 2.4975733757019043, "learning_rate": 9.756358196195769e-06, "loss": 0.2555, "step": 3776 }, { "epoch": 2.415127528583993, "grad_norm": 2.4662675857543945, "learning_rate": 9.745672152169268e-06, "loss": 0.2635, "step": 3777 }, { "epoch": 2.4157671703845844, "grad_norm": 2.750217914581299, "learning_rate": 9.734986108142766e-06, "loss": 0.2826, "step": 3778 }, { "epoch": 2.4164068121851763, "grad_norm": 2.7455925941467285, "learning_rate": 9.724300064116265e-06, "loss": 0.3025, "step": 3779 }, { "epoch": 2.417046453985768, "grad_norm": 3.1072282791137695, "learning_rate": 9.713614020089763e-06, "loss": 0.3015, "step": 3780 }, { "epoch": 2.4176860957863595, "grad_norm": 3.4795072078704834, "learning_rate": 9.702927976063262e-06, "loss": 0.3053, "step": 3781 }, { "epoch": 2.4183257375869514, "grad_norm": 3.366302490234375, "learning_rate": 9.692241932036761e-06, "loss": 0.3326, "step": 3782 }, { "epoch": 2.4189653793875427, "grad_norm": 3.1606807708740234, "learning_rate": 9.681555888010259e-06, "loss": 0.305, "step": 3783 }, { "epoch": 2.4196050211881346, "grad_norm": 3.016425371170044, "learning_rate": 9.670869843983758e-06, "loss": 0.312, "step": 3784 }, { "epoch": 2.4202446629887264, "grad_norm": 2.9911797046661377, "learning_rate": 9.660183799957256e-06, "loss": 0.2563, "step": 3785 }, { "epoch": 2.420884304789318, "grad_norm": 3.333845615386963, "learning_rate": 9.649497755930754e-06, "loss": 0.2976, "step": 3786 }, { "epoch": 2.4215239465899097, "grad_norm": 2.6827268600463867, "learning_rate": 9.638811711904253e-06, "loss": 0.2878, "step": 3787 }, { "epoch": 2.4221635883905015, "grad_norm": 2.8698997497558594, "learning_rate": 9.628125667877753e-06, "loss": 0.2922, "step": 3788 }, { "epoch": 2.422803230191093, "grad_norm": 3.5182323455810547, "learning_rate": 9.61743962385125e-06, "loss": 0.3209, "step": 3789 }, { "epoch": 2.4234428719916847, "grad_norm": 3.059401273727417, "learning_rate": 9.60675357982475e-06, "loss": 0.3213, "step": 3790 }, { "epoch": 2.4240825137922766, "grad_norm": 2.9321200847625732, "learning_rate": 9.596067535798247e-06, "loss": 0.2907, "step": 3791 }, { "epoch": 2.424722155592868, "grad_norm": 3.1854536533355713, "learning_rate": 9.585381491771747e-06, "loss": 0.3111, "step": 3792 }, { "epoch": 2.42536179739346, "grad_norm": 3.072195529937744, "learning_rate": 9.574695447745246e-06, "loss": 0.3044, "step": 3793 }, { "epoch": 2.426001439194051, "grad_norm": 2.6200971603393555, "learning_rate": 9.564009403718744e-06, "loss": 0.2712, "step": 3794 }, { "epoch": 2.426641080994643, "grad_norm": 2.600599527359009, "learning_rate": 9.553323359692243e-06, "loss": 0.2755, "step": 3795 }, { "epoch": 2.427280722795235, "grad_norm": 2.7904534339904785, "learning_rate": 9.54263731566574e-06, "loss": 0.294, "step": 3796 }, { "epoch": 2.4279203645958263, "grad_norm": 3.008108377456665, "learning_rate": 9.531951271639238e-06, "loss": 0.2795, "step": 3797 }, { "epoch": 2.428560006396418, "grad_norm": 3.046015501022339, "learning_rate": 9.521265227612738e-06, "loss": 0.2723, "step": 3798 }, { "epoch": 2.4291996481970095, "grad_norm": 2.8530921936035156, "learning_rate": 9.510579183586237e-06, "loss": 0.2778, "step": 3799 }, { "epoch": 2.4298392899976013, "grad_norm": 2.9153363704681396, "learning_rate": 9.499893139559736e-06, "loss": 0.2916, "step": 3800 }, { "epoch": 2.430478931798193, "grad_norm": 2.841264486312866, "learning_rate": 9.489207095533234e-06, "loss": 0.291, "step": 3801 }, { "epoch": 2.4311185735987846, "grad_norm": 2.686324119567871, "learning_rate": 9.478521051506732e-06, "loss": 0.2732, "step": 3802 }, { "epoch": 2.4317582153993764, "grad_norm": 2.989762544631958, "learning_rate": 9.467835007480231e-06, "loss": 0.2931, "step": 3803 }, { "epoch": 2.432397857199968, "grad_norm": 4.386168003082275, "learning_rate": 9.45714896345373e-06, "loss": 0.3725, "step": 3804 }, { "epoch": 2.4330374990005597, "grad_norm": 3.045278549194336, "learning_rate": 9.44646291942723e-06, "loss": 0.2673, "step": 3805 }, { "epoch": 2.4336771408011515, "grad_norm": 2.8226819038391113, "learning_rate": 9.435776875400727e-06, "loss": 0.2795, "step": 3806 }, { "epoch": 2.434316782601743, "grad_norm": 2.549082040786743, "learning_rate": 9.425090831374225e-06, "loss": 0.2406, "step": 3807 }, { "epoch": 2.4349564244023347, "grad_norm": 2.201199769973755, "learning_rate": 9.414404787347725e-06, "loss": 0.2643, "step": 3808 }, { "epoch": 2.435596066202926, "grad_norm": 2.9440882205963135, "learning_rate": 9.403718743321222e-06, "loss": 0.288, "step": 3809 }, { "epoch": 2.436235708003518, "grad_norm": 2.640242338180542, "learning_rate": 9.393032699294722e-06, "loss": 0.2742, "step": 3810 }, { "epoch": 2.43687534980411, "grad_norm": 2.9424214363098145, "learning_rate": 9.382346655268221e-06, "loss": 0.2899, "step": 3811 }, { "epoch": 2.437514991604701, "grad_norm": 2.7310006618499756, "learning_rate": 9.371660611241719e-06, "loss": 0.2965, "step": 3812 }, { "epoch": 2.438154633405293, "grad_norm": 2.5351955890655518, "learning_rate": 9.360974567215218e-06, "loss": 0.2855, "step": 3813 }, { "epoch": 2.438794275205885, "grad_norm": 2.6945552825927734, "learning_rate": 9.350288523188716e-06, "loss": 0.2923, "step": 3814 }, { "epoch": 2.4394339170064763, "grad_norm": 2.9604012966156006, "learning_rate": 9.339602479162215e-06, "loss": 0.2966, "step": 3815 }, { "epoch": 2.440073558807068, "grad_norm": 2.9590959548950195, "learning_rate": 9.328916435135714e-06, "loss": 0.2887, "step": 3816 }, { "epoch": 2.44071320060766, "grad_norm": 2.7463204860687256, "learning_rate": 9.318230391109212e-06, "loss": 0.2952, "step": 3817 }, { "epoch": 2.4413528424082513, "grad_norm": 3.2178103923797607, "learning_rate": 9.30754434708271e-06, "loss": 0.2919, "step": 3818 }, { "epoch": 2.441992484208843, "grad_norm": 2.7675511837005615, "learning_rate": 9.296858303056209e-06, "loss": 0.3024, "step": 3819 }, { "epoch": 2.4426321260094346, "grad_norm": 3.3939640522003174, "learning_rate": 9.286172259029707e-06, "loss": 0.3119, "step": 3820 }, { "epoch": 2.4432717678100264, "grad_norm": 3.474416971206665, "learning_rate": 9.275486215003206e-06, "loss": 0.3304, "step": 3821 }, { "epoch": 2.4439114096106183, "grad_norm": 3.2494993209838867, "learning_rate": 9.264800170976705e-06, "loss": 0.3305, "step": 3822 }, { "epoch": 2.4445510514112097, "grad_norm": 3.611361503601074, "learning_rate": 9.254114126950203e-06, "loss": 0.3414, "step": 3823 }, { "epoch": 2.4451906932118015, "grad_norm": 2.5496439933776855, "learning_rate": 9.243428082923702e-06, "loss": 0.2901, "step": 3824 }, { "epoch": 2.445830335012393, "grad_norm": 2.8153884410858154, "learning_rate": 9.2327420388972e-06, "loss": 0.2907, "step": 3825 }, { "epoch": 2.4464699768129847, "grad_norm": 2.9571709632873535, "learning_rate": 9.2220559948707e-06, "loss": 0.2957, "step": 3826 }, { "epoch": 2.4471096186135766, "grad_norm": 2.7724413871765137, "learning_rate": 9.211369950844199e-06, "loss": 0.277, "step": 3827 }, { "epoch": 2.447749260414168, "grad_norm": 3.408076524734497, "learning_rate": 9.200683906817697e-06, "loss": 0.3127, "step": 3828 }, { "epoch": 2.44838890221476, "grad_norm": 2.7393248081207275, "learning_rate": 9.189997862791196e-06, "loss": 0.2981, "step": 3829 }, { "epoch": 2.449028544015351, "grad_norm": 3.1942086219787598, "learning_rate": 9.179311818764694e-06, "loss": 0.3203, "step": 3830 }, { "epoch": 2.449668185815943, "grad_norm": 3.0015649795532227, "learning_rate": 9.168625774738191e-06, "loss": 0.3244, "step": 3831 }, { "epoch": 2.450307827616535, "grad_norm": 3.103132486343384, "learning_rate": 9.15793973071169e-06, "loss": 0.3077, "step": 3832 }, { "epoch": 2.4509474694171263, "grad_norm": 2.9493842124938965, "learning_rate": 9.14725368668519e-06, "loss": 0.3186, "step": 3833 }, { "epoch": 2.451587111217718, "grad_norm": 2.5046045780181885, "learning_rate": 9.13656764265869e-06, "loss": 0.2629, "step": 3834 }, { "epoch": 2.4522267530183095, "grad_norm": 2.747251510620117, "learning_rate": 9.125881598632187e-06, "loss": 0.2943, "step": 3835 }, { "epoch": 2.4528663948189013, "grad_norm": 2.305379867553711, "learning_rate": 9.115195554605685e-06, "loss": 0.2509, "step": 3836 }, { "epoch": 2.453506036619493, "grad_norm": 3.2020890712738037, "learning_rate": 9.104509510579184e-06, "loss": 0.3169, "step": 3837 }, { "epoch": 2.4541456784200846, "grad_norm": 2.862238645553589, "learning_rate": 9.093823466552683e-06, "loss": 0.2717, "step": 3838 }, { "epoch": 2.4547853202206764, "grad_norm": 3.574880838394165, "learning_rate": 9.083137422526181e-06, "loss": 0.3171, "step": 3839 }, { "epoch": 2.4554249620212683, "grad_norm": 3.0155539512634277, "learning_rate": 9.07245137849968e-06, "loss": 0.3112, "step": 3840 }, { "epoch": 2.4560646038218596, "grad_norm": 2.5281171798706055, "learning_rate": 9.061765334473178e-06, "loss": 0.2634, "step": 3841 }, { "epoch": 2.4567042456224515, "grad_norm": 2.6424858570098877, "learning_rate": 9.051079290446677e-06, "loss": 0.2873, "step": 3842 }, { "epoch": 2.4573438874230433, "grad_norm": 2.6515753269195557, "learning_rate": 9.040393246420175e-06, "loss": 0.2972, "step": 3843 }, { "epoch": 2.4579835292236347, "grad_norm": 2.188934803009033, "learning_rate": 9.029707202393674e-06, "loss": 0.2395, "step": 3844 }, { "epoch": 2.4586231710242266, "grad_norm": 3.127741813659668, "learning_rate": 9.019021158367174e-06, "loss": 0.3043, "step": 3845 }, { "epoch": 2.459262812824818, "grad_norm": 2.7275326251983643, "learning_rate": 9.008335114340671e-06, "loss": 0.2901, "step": 3846 }, { "epoch": 2.45990245462541, "grad_norm": 3.017045021057129, "learning_rate": 8.99764907031417e-06, "loss": 0.296, "step": 3847 }, { "epoch": 2.4605420964260016, "grad_norm": 3.1838059425354004, "learning_rate": 8.986963026287669e-06, "loss": 0.3134, "step": 3848 }, { "epoch": 2.461181738226593, "grad_norm": 3.933943271636963, "learning_rate": 8.976276982261166e-06, "loss": 0.3207, "step": 3849 }, { "epoch": 2.461821380027185, "grad_norm": 3.2233517169952393, "learning_rate": 8.965590938234667e-06, "loss": 0.294, "step": 3850 }, { "epoch": 2.4624610218277763, "grad_norm": 3.0609567165374756, "learning_rate": 8.954904894208165e-06, "loss": 0.3083, "step": 3851 }, { "epoch": 2.463100663628368, "grad_norm": 3.034419298171997, "learning_rate": 8.944218850181663e-06, "loss": 0.2866, "step": 3852 }, { "epoch": 2.46374030542896, "grad_norm": 2.9410407543182373, "learning_rate": 8.933532806155162e-06, "loss": 0.2609, "step": 3853 }, { "epoch": 2.4643799472295513, "grad_norm": 2.7242746353149414, "learning_rate": 8.92284676212866e-06, "loss": 0.2627, "step": 3854 }, { "epoch": 2.465019589030143, "grad_norm": 3.1908862590789795, "learning_rate": 8.912160718102159e-06, "loss": 0.2887, "step": 3855 }, { "epoch": 2.4656592308307346, "grad_norm": 3.2623515129089355, "learning_rate": 8.901474674075658e-06, "loss": 0.3116, "step": 3856 }, { "epoch": 2.4662988726313264, "grad_norm": 2.709096670150757, "learning_rate": 8.890788630049156e-06, "loss": 0.2738, "step": 3857 }, { "epoch": 2.4669385144319183, "grad_norm": 2.7787728309631348, "learning_rate": 8.880102586022655e-06, "loss": 0.2679, "step": 3858 }, { "epoch": 2.4675781562325096, "grad_norm": 3.2225756645202637, "learning_rate": 8.869416541996153e-06, "loss": 0.2948, "step": 3859 }, { "epoch": 2.4682177980331015, "grad_norm": 3.0603277683258057, "learning_rate": 8.85873049796965e-06, "loss": 0.3131, "step": 3860 }, { "epoch": 2.4688574398336933, "grad_norm": 3.017467498779297, "learning_rate": 8.848044453943152e-06, "loss": 0.2859, "step": 3861 }, { "epoch": 2.4694970816342847, "grad_norm": 3.512159585952759, "learning_rate": 8.83735840991665e-06, "loss": 0.3014, "step": 3862 }, { "epoch": 2.4701367234348766, "grad_norm": 3.199126720428467, "learning_rate": 8.826672365890149e-06, "loss": 0.2867, "step": 3863 }, { "epoch": 2.470776365235468, "grad_norm": 2.4926111698150635, "learning_rate": 8.815986321863646e-06, "loss": 0.27, "step": 3864 }, { "epoch": 2.47141600703606, "grad_norm": 3.3452162742614746, "learning_rate": 8.805300277837144e-06, "loss": 0.3301, "step": 3865 }, { "epoch": 2.4720556488366516, "grad_norm": 2.844399929046631, "learning_rate": 8.794614233810643e-06, "loss": 0.2904, "step": 3866 }, { "epoch": 2.472695290637243, "grad_norm": 2.7875826358795166, "learning_rate": 8.783928189784143e-06, "loss": 0.278, "step": 3867 }, { "epoch": 2.473334932437835, "grad_norm": 3.422585964202881, "learning_rate": 8.77324214575764e-06, "loss": 0.3017, "step": 3868 }, { "epoch": 2.4739745742384267, "grad_norm": 2.911555290222168, "learning_rate": 8.76255610173114e-06, "loss": 0.2923, "step": 3869 }, { "epoch": 2.474614216039018, "grad_norm": 3.060211658477783, "learning_rate": 8.751870057704638e-06, "loss": 0.2735, "step": 3870 }, { "epoch": 2.47525385783961, "grad_norm": 3.1995270252227783, "learning_rate": 8.741184013678137e-06, "loss": 0.3038, "step": 3871 }, { "epoch": 2.4758934996402013, "grad_norm": 2.997093915939331, "learning_rate": 8.730497969651635e-06, "loss": 0.2703, "step": 3872 }, { "epoch": 2.476533141440793, "grad_norm": 3.3046493530273438, "learning_rate": 8.719811925625134e-06, "loss": 0.3212, "step": 3873 }, { "epoch": 2.477172783241385, "grad_norm": 2.493839740753174, "learning_rate": 8.709125881598633e-06, "loss": 0.268, "step": 3874 }, { "epoch": 2.4778124250419764, "grad_norm": 3.9661970138549805, "learning_rate": 8.698439837572131e-06, "loss": 0.3268, "step": 3875 }, { "epoch": 2.4784520668425682, "grad_norm": 3.3390679359436035, "learning_rate": 8.68775379354563e-06, "loss": 0.2832, "step": 3876 }, { "epoch": 2.4790917086431596, "grad_norm": 3.179314374923706, "learning_rate": 8.677067749519128e-06, "loss": 0.3027, "step": 3877 }, { "epoch": 2.4797313504437515, "grad_norm": 2.945326089859009, "learning_rate": 8.666381705492627e-06, "loss": 0.3058, "step": 3878 }, { "epoch": 2.4803709922443433, "grad_norm": 2.443571090698242, "learning_rate": 8.655695661466127e-06, "loss": 0.288, "step": 3879 }, { "epoch": 2.4810106340449347, "grad_norm": 3.9710521697998047, "learning_rate": 8.645009617439624e-06, "loss": 0.3439, "step": 3880 }, { "epoch": 2.4816502758455266, "grad_norm": 3.116760015487671, "learning_rate": 8.634323573413122e-06, "loss": 0.2744, "step": 3881 }, { "epoch": 2.482289917646118, "grad_norm": 3.2043404579162598, "learning_rate": 8.623637529386621e-06, "loss": 0.3218, "step": 3882 }, { "epoch": 2.48292955944671, "grad_norm": 2.778614044189453, "learning_rate": 8.612951485360119e-06, "loss": 0.3039, "step": 3883 }, { "epoch": 2.4835692012473016, "grad_norm": 2.793134927749634, "learning_rate": 8.60226544133362e-06, "loss": 0.2741, "step": 3884 }, { "epoch": 2.484208843047893, "grad_norm": 2.952721118927002, "learning_rate": 8.591579397307118e-06, "loss": 0.2887, "step": 3885 }, { "epoch": 2.484848484848485, "grad_norm": 2.861395835876465, "learning_rate": 8.580893353280615e-06, "loss": 0.2936, "step": 3886 }, { "epoch": 2.4854881266490767, "grad_norm": 3.0399374961853027, "learning_rate": 8.570207309254115e-06, "loss": 0.2947, "step": 3887 }, { "epoch": 2.486127768449668, "grad_norm": 3.764336109161377, "learning_rate": 8.559521265227612e-06, "loss": 0.3227, "step": 3888 }, { "epoch": 2.48676741025026, "grad_norm": 2.946716785430908, "learning_rate": 8.548835221201112e-06, "loss": 0.2827, "step": 3889 }, { "epoch": 2.4874070520508513, "grad_norm": 2.3790247440338135, "learning_rate": 8.538149177174611e-06, "loss": 0.268, "step": 3890 }, { "epoch": 2.488046693851443, "grad_norm": 3.0598161220550537, "learning_rate": 8.527463133148109e-06, "loss": 0.3098, "step": 3891 }, { "epoch": 2.488686335652035, "grad_norm": 2.887455701828003, "learning_rate": 8.516777089121608e-06, "loss": 0.3085, "step": 3892 }, { "epoch": 2.4893259774526264, "grad_norm": 2.9641199111938477, "learning_rate": 8.506091045095106e-06, "loss": 0.3061, "step": 3893 }, { "epoch": 2.4899656192532182, "grad_norm": 2.924095869064331, "learning_rate": 8.495405001068604e-06, "loss": 0.2748, "step": 3894 }, { "epoch": 2.49060526105381, "grad_norm": 2.6567180156707764, "learning_rate": 8.484718957042103e-06, "loss": 0.2891, "step": 3895 }, { "epoch": 2.4912449028544015, "grad_norm": 3.831763505935669, "learning_rate": 8.474032913015602e-06, "loss": 0.3186, "step": 3896 }, { "epoch": 2.4918845446549933, "grad_norm": 3.099663257598877, "learning_rate": 8.463346868989102e-06, "loss": 0.2924, "step": 3897 }, { "epoch": 2.4925241864555847, "grad_norm": 2.84446382522583, "learning_rate": 8.4526608249626e-06, "loss": 0.3218, "step": 3898 }, { "epoch": 2.4931638282561766, "grad_norm": 3.2212624549865723, "learning_rate": 8.441974780936097e-06, "loss": 0.334, "step": 3899 }, { "epoch": 2.4938034700567684, "grad_norm": 2.6497578620910645, "learning_rate": 8.431288736909596e-06, "loss": 0.2723, "step": 3900 }, { "epoch": 2.49444311185736, "grad_norm": 3.1708333492279053, "learning_rate": 8.420602692883096e-06, "loss": 0.3016, "step": 3901 }, { "epoch": 2.4950827536579516, "grad_norm": 2.6580488681793213, "learning_rate": 8.409916648856593e-06, "loss": 0.2629, "step": 3902 }, { "epoch": 2.495722395458543, "grad_norm": 3.1520209312438965, "learning_rate": 8.399230604830093e-06, "loss": 0.3161, "step": 3903 }, { "epoch": 2.496362037259135, "grad_norm": 3.023639440536499, "learning_rate": 8.38854456080359e-06, "loss": 0.3246, "step": 3904 }, { "epoch": 2.4970016790597267, "grad_norm": 2.6570332050323486, "learning_rate": 8.37785851677709e-06, "loss": 0.2733, "step": 3905 }, { "epoch": 2.497641320860318, "grad_norm": 2.9623055458068848, "learning_rate": 8.367172472750587e-06, "loss": 0.3021, "step": 3906 }, { "epoch": 2.49828096266091, "grad_norm": 3.133467435836792, "learning_rate": 8.356486428724087e-06, "loss": 0.3116, "step": 3907 }, { "epoch": 2.4989206044615013, "grad_norm": 2.862210988998413, "learning_rate": 8.345800384697586e-06, "loss": 0.2773, "step": 3908 }, { "epoch": 2.499560246262093, "grad_norm": 2.55251407623291, "learning_rate": 8.335114340671084e-06, "loss": 0.2911, "step": 3909 }, { "epoch": 2.500199888062685, "grad_norm": 2.627422571182251, "learning_rate": 8.324428296644582e-06, "loss": 0.2591, "step": 3910 }, { "epoch": 2.5008395298632764, "grad_norm": 2.694646120071411, "learning_rate": 8.313742252618081e-06, "loss": 0.2883, "step": 3911 }, { "epoch": 2.5014791716638682, "grad_norm": 2.600728988647461, "learning_rate": 8.30305620859158e-06, "loss": 0.2816, "step": 3912 }, { "epoch": 2.5021188134644596, "grad_norm": 2.8494765758514404, "learning_rate": 8.29237016456508e-06, "loss": 0.2964, "step": 3913 }, { "epoch": 2.5027584552650515, "grad_norm": 2.6035451889038086, "learning_rate": 8.281684120538577e-06, "loss": 0.2791, "step": 3914 }, { "epoch": 2.5033980970656433, "grad_norm": 2.9588165283203125, "learning_rate": 8.270998076512075e-06, "loss": 0.2856, "step": 3915 }, { "epoch": 2.504037738866235, "grad_norm": 3.0478639602661133, "learning_rate": 8.260312032485574e-06, "loss": 0.2933, "step": 3916 }, { "epoch": 2.5046773806668265, "grad_norm": 2.9690191745758057, "learning_rate": 8.249625988459072e-06, "loss": 0.3171, "step": 3917 }, { "epoch": 2.5053170224674184, "grad_norm": 2.783714771270752, "learning_rate": 8.238939944432571e-06, "loss": 0.2907, "step": 3918 }, { "epoch": 2.50595666426801, "grad_norm": 2.7072505950927734, "learning_rate": 8.22825390040607e-06, "loss": 0.2691, "step": 3919 }, { "epoch": 2.5065963060686016, "grad_norm": 3.027251958847046, "learning_rate": 8.217567856379568e-06, "loss": 0.3043, "step": 3920 }, { "epoch": 2.5072359478691935, "grad_norm": 2.955143928527832, "learning_rate": 8.206881812353068e-06, "loss": 0.2907, "step": 3921 }, { "epoch": 2.507875589669785, "grad_norm": 3.3920645713806152, "learning_rate": 8.196195768326565e-06, "loss": 0.3007, "step": 3922 }, { "epoch": 2.5085152314703767, "grad_norm": 3.103003978729248, "learning_rate": 8.185509724300065e-06, "loss": 0.2806, "step": 3923 }, { "epoch": 2.509154873270968, "grad_norm": 2.414053440093994, "learning_rate": 8.174823680273564e-06, "loss": 0.2626, "step": 3924 }, { "epoch": 2.50979451507156, "grad_norm": 2.831071138381958, "learning_rate": 8.164137636247062e-06, "loss": 0.2681, "step": 3925 }, { "epoch": 2.5104341568721518, "grad_norm": 3.113445520401001, "learning_rate": 8.153451592220561e-06, "loss": 0.3075, "step": 3926 }, { "epoch": 2.511073798672743, "grad_norm": 2.6940696239471436, "learning_rate": 8.142765548194059e-06, "loss": 0.2855, "step": 3927 }, { "epoch": 2.511713440473335, "grad_norm": 3.4920425415039062, "learning_rate": 8.132079504167556e-06, "loss": 0.3122, "step": 3928 }, { "epoch": 2.5123530822739264, "grad_norm": 2.999638557434082, "learning_rate": 8.121393460141056e-06, "loss": 0.3005, "step": 3929 }, { "epoch": 2.5129927240745182, "grad_norm": 4.281359672546387, "learning_rate": 8.110707416114555e-06, "loss": 0.2857, "step": 3930 }, { "epoch": 2.51363236587511, "grad_norm": 2.734402656555176, "learning_rate": 8.100021372088053e-06, "loss": 0.2738, "step": 3931 }, { "epoch": 2.5142720076757015, "grad_norm": 3.25498366355896, "learning_rate": 8.089335328061552e-06, "loss": 0.2969, "step": 3932 }, { "epoch": 2.5149116494762933, "grad_norm": 2.784135103225708, "learning_rate": 8.07864928403505e-06, "loss": 0.2899, "step": 3933 }, { "epoch": 2.5155512912768847, "grad_norm": 3.077578067779541, "learning_rate": 8.06796324000855e-06, "loss": 0.3244, "step": 3934 }, { "epoch": 2.5161909330774765, "grad_norm": 2.8698017597198486, "learning_rate": 8.057277195982049e-06, "loss": 0.2667, "step": 3935 }, { "epoch": 2.5168305748780684, "grad_norm": 3.7617104053497314, "learning_rate": 8.046591151955546e-06, "loss": 0.3495, "step": 3936 }, { "epoch": 2.51747021667866, "grad_norm": 2.79166841506958, "learning_rate": 8.035905107929046e-06, "loss": 0.2674, "step": 3937 }, { "epoch": 2.5181098584792516, "grad_norm": 2.9812519550323486, "learning_rate": 8.025219063902543e-06, "loss": 0.2957, "step": 3938 }, { "epoch": 2.518749500279843, "grad_norm": 2.6640431880950928, "learning_rate": 8.014533019876043e-06, "loss": 0.2538, "step": 3939 }, { "epoch": 2.519389142080435, "grad_norm": 3.042208671569824, "learning_rate": 8.00384697584954e-06, "loss": 0.3077, "step": 3940 }, { "epoch": 2.5200287838810267, "grad_norm": 2.7115213871002197, "learning_rate": 7.99316093182304e-06, "loss": 0.2562, "step": 3941 }, { "epoch": 2.5206684256816185, "grad_norm": 2.6850244998931885, "learning_rate": 7.982474887796539e-06, "loss": 0.2683, "step": 3942 }, { "epoch": 2.52130806748221, "grad_norm": 2.752390146255493, "learning_rate": 7.971788843770037e-06, "loss": 0.2732, "step": 3943 }, { "epoch": 2.5219477092828018, "grad_norm": 3.4455316066741943, "learning_rate": 7.961102799743534e-06, "loss": 0.3295, "step": 3944 }, { "epoch": 2.522587351083393, "grad_norm": 2.862778663635254, "learning_rate": 7.950416755717034e-06, "loss": 0.2688, "step": 3945 }, { "epoch": 2.523226992883985, "grad_norm": 3.092811107635498, "learning_rate": 7.939730711690533e-06, "loss": 0.3134, "step": 3946 }, { "epoch": 2.523866634684577, "grad_norm": 3.047186851501465, "learning_rate": 7.929044667664032e-06, "loss": 0.3042, "step": 3947 }, { "epoch": 2.5245062764851682, "grad_norm": 3.0295207500457764, "learning_rate": 7.91835862363753e-06, "loss": 0.3017, "step": 3948 }, { "epoch": 2.52514591828576, "grad_norm": 3.1070966720581055, "learning_rate": 7.907672579611028e-06, "loss": 0.2831, "step": 3949 }, { "epoch": 2.5257855600863515, "grad_norm": 2.9946415424346924, "learning_rate": 7.896986535584527e-06, "loss": 0.287, "step": 3950 }, { "epoch": 2.5264252018869433, "grad_norm": 2.954479694366455, "learning_rate": 7.886300491558025e-06, "loss": 0.2925, "step": 3951 }, { "epoch": 2.527064843687535, "grad_norm": 2.645458459854126, "learning_rate": 7.875614447531524e-06, "loss": 0.2816, "step": 3952 }, { "epoch": 2.5277044854881265, "grad_norm": 2.9948172569274902, "learning_rate": 7.864928403505024e-06, "loss": 0.2759, "step": 3953 }, { "epoch": 2.5283441272887184, "grad_norm": 3.8406200408935547, "learning_rate": 7.854242359478521e-06, "loss": 0.3134, "step": 3954 }, { "epoch": 2.5289837690893098, "grad_norm": 3.5990071296691895, "learning_rate": 7.84355631545202e-06, "loss": 0.3293, "step": 3955 }, { "epoch": 2.5296234108899016, "grad_norm": 2.8128585815429688, "learning_rate": 7.832870271425518e-06, "loss": 0.2828, "step": 3956 }, { "epoch": 2.5302630526904935, "grad_norm": 2.500379800796509, "learning_rate": 7.822184227399016e-06, "loss": 0.276, "step": 3957 }, { "epoch": 2.530902694491085, "grad_norm": 3.474045991897583, "learning_rate": 7.811498183372517e-06, "loss": 0.319, "step": 3958 }, { "epoch": 2.5315423362916767, "grad_norm": 3.13374924659729, "learning_rate": 7.800812139346015e-06, "loss": 0.3268, "step": 3959 }, { "epoch": 2.532181978092268, "grad_norm": 3.1712162494659424, "learning_rate": 7.790126095319514e-06, "loss": 0.3041, "step": 3960 }, { "epoch": 2.53282161989286, "grad_norm": 3.28678297996521, "learning_rate": 7.779440051293012e-06, "loss": 0.3128, "step": 3961 }, { "epoch": 2.5334612616934518, "grad_norm": 2.8915796279907227, "learning_rate": 7.76875400726651e-06, "loss": 0.2954, "step": 3962 }, { "epoch": 2.5341009034940436, "grad_norm": 2.7176880836486816, "learning_rate": 7.758067963240009e-06, "loss": 0.287, "step": 3963 }, { "epoch": 2.534740545294635, "grad_norm": 3.1310877799987793, "learning_rate": 7.747381919213508e-06, "loss": 0.2817, "step": 3964 }, { "epoch": 2.535380187095227, "grad_norm": 2.8056352138519287, "learning_rate": 7.736695875187006e-06, "loss": 0.2795, "step": 3965 }, { "epoch": 2.5360198288958182, "grad_norm": 3.34025502204895, "learning_rate": 7.726009831160505e-06, "loss": 0.3309, "step": 3966 }, { "epoch": 2.53665947069641, "grad_norm": 2.857496500015259, "learning_rate": 7.715323787134003e-06, "loss": 0.279, "step": 3967 }, { "epoch": 2.537299112497002, "grad_norm": 2.914743185043335, "learning_rate": 7.704637743107502e-06, "loss": 0.2792, "step": 3968 }, { "epoch": 2.5379387542975933, "grad_norm": 3.172365665435791, "learning_rate": 7.693951699081002e-06, "loss": 0.2887, "step": 3969 }, { "epoch": 2.538578396098185, "grad_norm": 2.498138427734375, "learning_rate": 7.6832656550545e-06, "loss": 0.278, "step": 3970 }, { "epoch": 2.5392180378987765, "grad_norm": 2.6336593627929688, "learning_rate": 7.672579611027999e-06, "loss": 0.2843, "step": 3971 }, { "epoch": 2.5398576796993684, "grad_norm": 2.6753458976745605, "learning_rate": 7.661893567001496e-06, "loss": 0.2703, "step": 3972 }, { "epoch": 2.54049732149996, "grad_norm": 2.757615327835083, "learning_rate": 7.651207522974994e-06, "loss": 0.2837, "step": 3973 }, { "epoch": 2.5411369633005516, "grad_norm": 3.0092389583587646, "learning_rate": 7.640521478948493e-06, "loss": 0.2946, "step": 3974 }, { "epoch": 2.5417766051011434, "grad_norm": 3.061602830886841, "learning_rate": 7.629835434921993e-06, "loss": 0.2963, "step": 3975 }, { "epoch": 2.542416246901735, "grad_norm": 3.014116048812866, "learning_rate": 7.619149390895491e-06, "loss": 0.3126, "step": 3976 }, { "epoch": 2.5430558887023267, "grad_norm": 2.7754018306732178, "learning_rate": 7.60846334686899e-06, "loss": 0.3018, "step": 3977 }, { "epoch": 2.5436955305029185, "grad_norm": 2.6593613624572754, "learning_rate": 7.597777302842487e-06, "loss": 0.2675, "step": 3978 }, { "epoch": 2.54433517230351, "grad_norm": 2.8170251846313477, "learning_rate": 7.587091258815987e-06, "loss": 0.2756, "step": 3979 }, { "epoch": 2.5449748141041018, "grad_norm": 2.7848563194274902, "learning_rate": 7.576405214789485e-06, "loss": 0.3, "step": 3980 }, { "epoch": 2.545614455904693, "grad_norm": 2.87302303314209, "learning_rate": 7.5657191707629845e-06, "loss": 0.2922, "step": 3981 }, { "epoch": 2.546254097705285, "grad_norm": 3.23467755317688, "learning_rate": 7.555033126736483e-06, "loss": 0.317, "step": 3982 }, { "epoch": 2.546893739505877, "grad_norm": 2.7781662940979004, "learning_rate": 7.544347082709981e-06, "loss": 0.2736, "step": 3983 }, { "epoch": 2.5475333813064682, "grad_norm": 3.339779853820801, "learning_rate": 7.53366103868348e-06, "loss": 0.328, "step": 3984 }, { "epoch": 2.54817302310706, "grad_norm": 2.7671165466308594, "learning_rate": 7.522974994656979e-06, "loss": 0.2959, "step": 3985 }, { "epoch": 2.5488126649076515, "grad_norm": 2.848484754562378, "learning_rate": 7.512288950630476e-06, "loss": 0.2797, "step": 3986 }, { "epoch": 2.5494523067082433, "grad_norm": 3.0425779819488525, "learning_rate": 7.501602906603976e-06, "loss": 0.3006, "step": 3987 }, { "epoch": 2.550091948508835, "grad_norm": 3.1285667419433594, "learning_rate": 7.490916862577474e-06, "loss": 0.311, "step": 3988 }, { "epoch": 2.550731590309427, "grad_norm": 2.9664113521575928, "learning_rate": 7.4802308185509735e-06, "loss": 0.2844, "step": 3989 }, { "epoch": 2.5513712321100184, "grad_norm": 2.473754405975342, "learning_rate": 7.469544774524471e-06, "loss": 0.2855, "step": 3990 }, { "epoch": 2.55201087391061, "grad_norm": 2.819472074508667, "learning_rate": 7.45885873049797e-06, "loss": 0.2886, "step": 3991 }, { "epoch": 2.5526505157112016, "grad_norm": 2.516455888748169, "learning_rate": 7.448172686471469e-06, "loss": 0.2477, "step": 3992 }, { "epoch": 2.5532901575117934, "grad_norm": 3.2210848331451416, "learning_rate": 7.437486642444967e-06, "loss": 0.2987, "step": 3993 }, { "epoch": 2.5539297993123853, "grad_norm": 2.665578842163086, "learning_rate": 7.426800598418465e-06, "loss": 0.2768, "step": 3994 }, { "epoch": 2.5545694411129767, "grad_norm": 2.6386947631835938, "learning_rate": 7.416114554391965e-06, "loss": 0.2756, "step": 3995 }, { "epoch": 2.5552090829135685, "grad_norm": 2.5386404991149902, "learning_rate": 7.405428510365463e-06, "loss": 0.2931, "step": 3996 }, { "epoch": 2.55584872471416, "grad_norm": 2.7998013496398926, "learning_rate": 7.3947424663389625e-06, "loss": 0.299, "step": 3997 }, { "epoch": 2.5564883665147518, "grad_norm": 3.289069652557373, "learning_rate": 7.38405642231246e-06, "loss": 0.2997, "step": 3998 }, { "epoch": 2.5571280083153436, "grad_norm": 2.8917007446289062, "learning_rate": 7.373370378285959e-06, "loss": 0.2718, "step": 3999 }, { "epoch": 2.557767650115935, "grad_norm": 3.172271251678467, "learning_rate": 7.362684334259458e-06, "loss": 0.3084, "step": 4000 }, { "epoch": 2.558407291916527, "grad_norm": 3.154325246810913, "learning_rate": 7.351998290232956e-06, "loss": 0.309, "step": 4001 }, { "epoch": 2.559046933717118, "grad_norm": 3.2781569957733154, "learning_rate": 7.341312246206455e-06, "loss": 0.3389, "step": 4002 }, { "epoch": 2.55968657551771, "grad_norm": 2.648505449295044, "learning_rate": 7.3306262021799536e-06, "loss": 0.2812, "step": 4003 }, { "epoch": 2.560326217318302, "grad_norm": 2.9028067588806152, "learning_rate": 7.319940158153451e-06, "loss": 0.2761, "step": 4004 }, { "epoch": 2.5609658591188933, "grad_norm": 2.9735097885131836, "learning_rate": 7.3092541141269514e-06, "loss": 0.2909, "step": 4005 }, { "epoch": 2.561605500919485, "grad_norm": 3.0845820903778076, "learning_rate": 7.298568070100449e-06, "loss": 0.3103, "step": 4006 }, { "epoch": 2.5622451427200765, "grad_norm": 3.088407516479492, "learning_rate": 7.287882026073948e-06, "loss": 0.317, "step": 4007 }, { "epoch": 2.5628847845206684, "grad_norm": 2.7409865856170654, "learning_rate": 7.277195982047447e-06, "loss": 0.2958, "step": 4008 }, { "epoch": 2.56352442632126, "grad_norm": 2.571981906890869, "learning_rate": 7.266509938020945e-06, "loss": 0.2662, "step": 4009 }, { "epoch": 2.5641640681218516, "grad_norm": 2.704202651977539, "learning_rate": 7.255823893994444e-06, "loss": 0.2677, "step": 4010 }, { "epoch": 2.5648037099224434, "grad_norm": 3.417504072189331, "learning_rate": 7.2451378499679425e-06, "loss": 0.3036, "step": 4011 }, { "epoch": 2.565443351723035, "grad_norm": 3.1518378257751465, "learning_rate": 7.23445180594144e-06, "loss": 0.3001, "step": 4012 }, { "epoch": 2.5660829935236267, "grad_norm": 2.7487339973449707, "learning_rate": 7.2237657619149396e-06, "loss": 0.3017, "step": 4013 }, { "epoch": 2.5667226353242185, "grad_norm": 2.619185209274292, "learning_rate": 7.213079717888438e-06, "loss": 0.2794, "step": 4014 }, { "epoch": 2.5673622771248104, "grad_norm": 2.819486141204834, "learning_rate": 7.202393673861936e-06, "loss": 0.2912, "step": 4015 }, { "epoch": 2.5680019189254017, "grad_norm": 2.6165525913238525, "learning_rate": 7.191707629835435e-06, "loss": 0.2865, "step": 4016 }, { "epoch": 2.5686415607259936, "grad_norm": 2.7600765228271484, "learning_rate": 7.181021585808934e-06, "loss": 0.2846, "step": 4017 }, { "epoch": 2.569281202526585, "grad_norm": 2.990995168685913, "learning_rate": 7.170335541782433e-06, "loss": 0.307, "step": 4018 }, { "epoch": 2.569920844327177, "grad_norm": 3.0928447246551514, "learning_rate": 7.1596494977559315e-06, "loss": 0.2963, "step": 4019 }, { "epoch": 2.5705604861277687, "grad_norm": 2.7217769622802734, "learning_rate": 7.148963453729429e-06, "loss": 0.2705, "step": 4020 }, { "epoch": 2.57120012792836, "grad_norm": 2.7806236743927, "learning_rate": 7.1382774097029285e-06, "loss": 0.2911, "step": 4021 }, { "epoch": 2.571839769728952, "grad_norm": 2.488596200942993, "learning_rate": 7.127591365676427e-06, "loss": 0.2555, "step": 4022 }, { "epoch": 2.5724794115295433, "grad_norm": 3.095839023590088, "learning_rate": 7.116905321649925e-06, "loss": 0.2877, "step": 4023 }, { "epoch": 2.573119053330135, "grad_norm": 3.1489639282226562, "learning_rate": 7.106219277623424e-06, "loss": 0.3054, "step": 4024 }, { "epoch": 2.573758695130727, "grad_norm": 2.6779065132141113, "learning_rate": 7.095533233596923e-06, "loss": 0.2885, "step": 4025 }, { "epoch": 2.5743983369313184, "grad_norm": 3.1690926551818848, "learning_rate": 7.084847189570422e-06, "loss": 0.3234, "step": 4026 }, { "epoch": 2.57503797873191, "grad_norm": 3.006356954574585, "learning_rate": 7.07416114554392e-06, "loss": 0.282, "step": 4027 }, { "epoch": 2.5756776205325016, "grad_norm": 3.131333589553833, "learning_rate": 7.063475101517418e-06, "loss": 0.2896, "step": 4028 }, { "epoch": 2.5763172623330934, "grad_norm": 2.638676881790161, "learning_rate": 7.0527890574909175e-06, "loss": 0.2626, "step": 4029 }, { "epoch": 2.5769569041336853, "grad_norm": 2.6633353233337402, "learning_rate": 7.042103013464416e-06, "loss": 0.2764, "step": 4030 }, { "epoch": 2.5775965459342767, "grad_norm": 2.9712777137756348, "learning_rate": 7.031416969437915e-06, "loss": 0.2985, "step": 4031 }, { "epoch": 2.5782361877348685, "grad_norm": 2.6915102005004883, "learning_rate": 7.020730925411413e-06, "loss": 0.2768, "step": 4032 }, { "epoch": 2.57887582953546, "grad_norm": 2.3778769969940186, "learning_rate": 7.0100448813849115e-06, "loss": 0.2317, "step": 4033 }, { "epoch": 2.5795154713360517, "grad_norm": 2.6297054290771484, "learning_rate": 6.999358837358411e-06, "loss": 0.2694, "step": 4034 }, { "epoch": 2.5801551131366436, "grad_norm": 3.0256714820861816, "learning_rate": 6.9886727933319086e-06, "loss": 0.2985, "step": 4035 }, { "epoch": 2.5807947549372354, "grad_norm": 2.7137451171875, "learning_rate": 6.977986749305407e-06, "loss": 0.2594, "step": 4036 }, { "epoch": 2.581434396737827, "grad_norm": 3.3964784145355225, "learning_rate": 6.9673007052789065e-06, "loss": 0.3148, "step": 4037 }, { "epoch": 2.582074038538418, "grad_norm": 2.715463876724243, "learning_rate": 6.956614661252404e-06, "loss": 0.2957, "step": 4038 }, { "epoch": 2.58271368033901, "grad_norm": 3.4258534908294678, "learning_rate": 6.9459286172259035e-06, "loss": 0.3052, "step": 4039 }, { "epoch": 2.583353322139602, "grad_norm": 2.7731049060821533, "learning_rate": 6.935242573199402e-06, "loss": 0.2786, "step": 4040 }, { "epoch": 2.5839929639401937, "grad_norm": 3.120088815689087, "learning_rate": 6.9245565291729e-06, "loss": 0.3164, "step": 4041 }, { "epoch": 2.584632605740785, "grad_norm": 3.1760048866271973, "learning_rate": 6.9138704851464e-06, "loss": 0.3056, "step": 4042 }, { "epoch": 2.585272247541377, "grad_norm": 2.9035680294036865, "learning_rate": 6.9031844411198975e-06, "loss": 0.2629, "step": 4043 }, { "epoch": 2.5859118893419684, "grad_norm": 3.0123603343963623, "learning_rate": 6.892498397093396e-06, "loss": 0.2954, "step": 4044 }, { "epoch": 2.58655153114256, "grad_norm": 2.7939774990081787, "learning_rate": 6.881812353066895e-06, "loss": 0.2842, "step": 4045 }, { "epoch": 2.587191172943152, "grad_norm": 3.3975231647491455, "learning_rate": 6.871126309040393e-06, "loss": 0.3054, "step": 4046 }, { "epoch": 2.5878308147437434, "grad_norm": 2.6104512214660645, "learning_rate": 6.8604402650138924e-06, "loss": 0.2876, "step": 4047 }, { "epoch": 2.5884704565443353, "grad_norm": 2.675142765045166, "learning_rate": 6.849754220987391e-06, "loss": 0.2713, "step": 4048 }, { "epoch": 2.5891100983449267, "grad_norm": 2.454266309738159, "learning_rate": 6.839068176960889e-06, "loss": 0.2504, "step": 4049 }, { "epoch": 2.5897497401455185, "grad_norm": 3.079059600830078, "learning_rate": 6.828382132934388e-06, "loss": 0.2757, "step": 4050 }, { "epoch": 2.5903893819461103, "grad_norm": 2.8647725582122803, "learning_rate": 6.8176960889078865e-06, "loss": 0.289, "step": 4051 }, { "epoch": 2.5910290237467017, "grad_norm": 2.5410890579223633, "learning_rate": 6.807010044881386e-06, "loss": 0.2809, "step": 4052 }, { "epoch": 2.5916686655472936, "grad_norm": 3.003767251968384, "learning_rate": 6.796324000854884e-06, "loss": 0.2836, "step": 4053 }, { "epoch": 2.592308307347885, "grad_norm": 3.547102928161621, "learning_rate": 6.785637956828382e-06, "loss": 0.3019, "step": 4054 }, { "epoch": 2.592947949148477, "grad_norm": 2.8899435997009277, "learning_rate": 6.774951912801881e-06, "loss": 0.2901, "step": 4055 }, { "epoch": 2.5935875909490687, "grad_norm": 2.9045917987823486, "learning_rate": 6.76426586877538e-06, "loss": 0.3119, "step": 4056 }, { "epoch": 2.59422723274966, "grad_norm": 2.90828013420105, "learning_rate": 6.753579824748878e-06, "loss": 0.2734, "step": 4057 }, { "epoch": 2.594866874550252, "grad_norm": 2.9471561908721924, "learning_rate": 6.742893780722377e-06, "loss": 0.2726, "step": 4058 }, { "epoch": 2.5955065163508433, "grad_norm": 3.0729422569274902, "learning_rate": 6.7322077366958755e-06, "loss": 0.2866, "step": 4059 }, { "epoch": 2.596146158151435, "grad_norm": 3.5099430084228516, "learning_rate": 6.721521692669375e-06, "loss": 0.3069, "step": 4060 }, { "epoch": 2.596785799952027, "grad_norm": 2.2890100479125977, "learning_rate": 6.7108356486428725e-06, "loss": 0.2404, "step": 4061 }, { "epoch": 2.597425441752619, "grad_norm": 3.3020029067993164, "learning_rate": 6.700149604616371e-06, "loss": 0.3025, "step": 4062 }, { "epoch": 2.59806508355321, "grad_norm": 3.097515344619751, "learning_rate": 6.68946356058987e-06, "loss": 0.2925, "step": 4063 }, { "epoch": 2.598704725353802, "grad_norm": 2.8480024337768555, "learning_rate": 6.678777516563368e-06, "loss": 0.2968, "step": 4064 }, { "epoch": 2.5993443671543934, "grad_norm": 3.331103563308716, "learning_rate": 6.6680914725368666e-06, "loss": 0.2908, "step": 4065 }, { "epoch": 2.5999840089549853, "grad_norm": 2.9043595790863037, "learning_rate": 6.657405428510366e-06, "loss": 0.277, "step": 4066 }, { "epoch": 2.600623650755577, "grad_norm": 2.9335644245147705, "learning_rate": 6.6467193844838644e-06, "loss": 0.2937, "step": 4067 }, { "epoch": 2.6012632925561685, "grad_norm": 2.8348264694213867, "learning_rate": 6.636033340457364e-06, "loss": 0.2869, "step": 4068 }, { "epoch": 2.6019029343567603, "grad_norm": 3.2087388038635254, "learning_rate": 6.6253472964308615e-06, "loss": 0.2994, "step": 4069 }, { "epoch": 2.6025425761573517, "grad_norm": 3.7750985622406006, "learning_rate": 6.61466125240436e-06, "loss": 0.3279, "step": 4070 }, { "epoch": 2.6031822179579436, "grad_norm": 2.9611592292785645, "learning_rate": 6.603975208377859e-06, "loss": 0.2988, "step": 4071 }, { "epoch": 2.6038218597585354, "grad_norm": 3.236565351486206, "learning_rate": 6.593289164351357e-06, "loss": 0.2778, "step": 4072 }, { "epoch": 2.604461501559127, "grad_norm": 3.189505100250244, "learning_rate": 6.582603120324856e-06, "loss": 0.2825, "step": 4073 }, { "epoch": 2.6051011433597187, "grad_norm": 2.6999635696411133, "learning_rate": 6.571917076298355e-06, "loss": 0.2905, "step": 4074 }, { "epoch": 2.60574078516031, "grad_norm": 3.3205056190490723, "learning_rate": 6.5612310322718526e-06, "loss": 0.2985, "step": 4075 }, { "epoch": 2.606380426960902, "grad_norm": 2.713329553604126, "learning_rate": 6.550544988245352e-06, "loss": 0.2801, "step": 4076 }, { "epoch": 2.6070200687614937, "grad_norm": 2.5777816772460938, "learning_rate": 6.5398589442188504e-06, "loss": 0.2761, "step": 4077 }, { "epoch": 2.607659710562085, "grad_norm": 3.083207130432129, "learning_rate": 6.529172900192348e-06, "loss": 0.3011, "step": 4078 }, { "epoch": 2.608299352362677, "grad_norm": 2.7377207279205322, "learning_rate": 6.518486856165848e-06, "loss": 0.2865, "step": 4079 }, { "epoch": 2.6089389941632684, "grad_norm": 2.998675584793091, "learning_rate": 6.507800812139346e-06, "loss": 0.2871, "step": 4080 }, { "epoch": 2.60957863596386, "grad_norm": 2.904697895050049, "learning_rate": 6.497114768112845e-06, "loss": 0.287, "step": 4081 }, { "epoch": 2.610218277764452, "grad_norm": 3.5210788249969482, "learning_rate": 6.486428724086344e-06, "loss": 0.301, "step": 4082 }, { "epoch": 2.6108579195650434, "grad_norm": 2.9328877925872803, "learning_rate": 6.4757426800598415e-06, "loss": 0.3037, "step": 4083 }, { "epoch": 2.6114975613656353, "grad_norm": 2.5591320991516113, "learning_rate": 6.465056636033341e-06, "loss": 0.2738, "step": 4084 }, { "epoch": 2.6121372031662267, "grad_norm": 3.4498910903930664, "learning_rate": 6.454370592006839e-06, "loss": 0.3155, "step": 4085 }, { "epoch": 2.6127768449668185, "grad_norm": 3.096059560775757, "learning_rate": 6.443684547980337e-06, "loss": 0.3301, "step": 4086 }, { "epoch": 2.6134164867674103, "grad_norm": 2.978118419647217, "learning_rate": 6.4329985039538364e-06, "loss": 0.3004, "step": 4087 }, { "epoch": 2.614056128568002, "grad_norm": 2.6096348762512207, "learning_rate": 6.422312459927335e-06, "loss": 0.2883, "step": 4088 }, { "epoch": 2.6146957703685936, "grad_norm": 2.766460418701172, "learning_rate": 6.411626415900834e-06, "loss": 0.2613, "step": 4089 }, { "epoch": 2.6153354121691854, "grad_norm": 3.018059492111206, "learning_rate": 6.400940371874333e-06, "loss": 0.322, "step": 4090 }, { "epoch": 2.615975053969777, "grad_norm": 3.1155269145965576, "learning_rate": 6.3902543278478305e-06, "loss": 0.3166, "step": 4091 }, { "epoch": 2.6166146957703686, "grad_norm": 2.544541597366333, "learning_rate": 6.37956828382133e-06, "loss": 0.2626, "step": 4092 }, { "epoch": 2.6172543375709605, "grad_norm": 3.250281572341919, "learning_rate": 6.368882239794828e-06, "loss": 0.2917, "step": 4093 }, { "epoch": 2.617893979371552, "grad_norm": 2.824223041534424, "learning_rate": 6.358196195768328e-06, "loss": 0.2765, "step": 4094 }, { "epoch": 2.6185336211721437, "grad_norm": 2.7045154571533203, "learning_rate": 6.347510151741825e-06, "loss": 0.2823, "step": 4095 }, { "epoch": 2.619173262972735, "grad_norm": 3.0567705631256104, "learning_rate": 6.336824107715324e-06, "loss": 0.2925, "step": 4096 }, { "epoch": 2.619812904773327, "grad_norm": 3.1804537773132324, "learning_rate": 6.326138063688823e-06, "loss": 0.2905, "step": 4097 }, { "epoch": 2.620452546573919, "grad_norm": 3.218569040298462, "learning_rate": 6.315452019662321e-06, "loss": 0.2998, "step": 4098 }, { "epoch": 2.62109218837451, "grad_norm": 2.8695592880249023, "learning_rate": 6.3047659756358195e-06, "loss": 0.2942, "step": 4099 }, { "epoch": 2.621731830175102, "grad_norm": 2.8517274856567383, "learning_rate": 6.294079931609319e-06, "loss": 0.2795, "step": 4100 }, { "epoch": 2.6223714719756934, "grad_norm": 3.258681297302246, "learning_rate": 6.2833938875828165e-06, "loss": 0.2932, "step": 4101 }, { "epoch": 2.6230111137762853, "grad_norm": 2.917255401611328, "learning_rate": 6.272707843556317e-06, "loss": 0.2898, "step": 4102 }, { "epoch": 2.623650755576877, "grad_norm": 2.938506603240967, "learning_rate": 6.262021799529814e-06, "loss": 0.3056, "step": 4103 }, { "epoch": 2.6242903973774685, "grad_norm": 2.802382707595825, "learning_rate": 6.251335755503313e-06, "loss": 0.2829, "step": 4104 }, { "epoch": 2.6249300391780603, "grad_norm": 2.872706890106201, "learning_rate": 6.240649711476811e-06, "loss": 0.2924, "step": 4105 }, { "epoch": 2.6255696809786517, "grad_norm": 3.044586658477783, "learning_rate": 6.22996366745031e-06, "loss": 0.308, "step": 4106 }, { "epoch": 2.6262093227792436, "grad_norm": 2.8546431064605713, "learning_rate": 6.2192776234238084e-06, "loss": 0.2886, "step": 4107 }, { "epoch": 2.6268489645798354, "grad_norm": 2.623234272003174, "learning_rate": 6.208591579397308e-06, "loss": 0.2724, "step": 4108 }, { "epoch": 2.627488606380427, "grad_norm": 3.020480155944824, "learning_rate": 6.1979055353708055e-06, "loss": 0.3103, "step": 4109 }, { "epoch": 2.6281282481810186, "grad_norm": 3.087705612182617, "learning_rate": 6.187219491344305e-06, "loss": 0.308, "step": 4110 }, { "epoch": 2.62876788998161, "grad_norm": 2.831956386566162, "learning_rate": 6.176533447317803e-06, "loss": 0.2956, "step": 4111 }, { "epoch": 2.629407531782202, "grad_norm": 2.6048920154571533, "learning_rate": 6.165847403291302e-06, "loss": 0.2971, "step": 4112 }, { "epoch": 2.6300471735827937, "grad_norm": 2.5622875690460205, "learning_rate": 6.155161359264801e-06, "loss": 0.2731, "step": 4113 }, { "epoch": 2.6306868153833856, "grad_norm": 2.952578544616699, "learning_rate": 6.144475315238299e-06, "loss": 0.3012, "step": 4114 }, { "epoch": 2.631326457183977, "grad_norm": 2.9624619483947754, "learning_rate": 6.133789271211797e-06, "loss": 0.2823, "step": 4115 }, { "epoch": 2.631966098984569, "grad_norm": 2.854189395904541, "learning_rate": 6.123103227185297e-06, "loss": 0.2993, "step": 4116 }, { "epoch": 2.63260574078516, "grad_norm": 3.04116153717041, "learning_rate": 6.112417183158795e-06, "loss": 0.3294, "step": 4117 }, { "epoch": 2.633245382585752, "grad_norm": 2.9307477474212646, "learning_rate": 6.101731139132293e-06, "loss": 0.291, "step": 4118 }, { "epoch": 2.633885024386344, "grad_norm": 2.656273365020752, "learning_rate": 6.091045095105792e-06, "loss": 0.2822, "step": 4119 }, { "epoch": 2.6345246661869353, "grad_norm": 3.1066153049468994, "learning_rate": 6.080359051079291e-06, "loss": 0.3067, "step": 4120 }, { "epoch": 2.635164307987527, "grad_norm": 2.728170394897461, "learning_rate": 6.069673007052789e-06, "loss": 0.2658, "step": 4121 }, { "epoch": 2.6358039497881185, "grad_norm": 2.8378944396972656, "learning_rate": 6.058986963026288e-06, "loss": 0.2826, "step": 4122 }, { "epoch": 2.6364435915887103, "grad_norm": 3.1763226985931396, "learning_rate": 6.048300918999786e-06, "loss": 0.2976, "step": 4123 }, { "epoch": 2.637083233389302, "grad_norm": 3.4446120262145996, "learning_rate": 6.037614874973285e-06, "loss": 0.3283, "step": 4124 }, { "epoch": 2.6377228751898936, "grad_norm": 3.0102880001068115, "learning_rate": 6.026928830946784e-06, "loss": 0.3093, "step": 4125 }, { "epoch": 2.6383625169904854, "grad_norm": 2.9607622623443604, "learning_rate": 6.016242786920282e-06, "loss": 0.3053, "step": 4126 }, { "epoch": 2.639002158791077, "grad_norm": 2.8787426948547363, "learning_rate": 6.005556742893781e-06, "loss": 0.2801, "step": 4127 }, { "epoch": 2.6396418005916686, "grad_norm": 2.6342411041259766, "learning_rate": 5.99487069886728e-06, "loss": 0.2734, "step": 4128 }, { "epoch": 2.6402814423922605, "grad_norm": 3.4327261447906494, "learning_rate": 5.984184654840778e-06, "loss": 0.3107, "step": 4129 }, { "epoch": 2.640921084192852, "grad_norm": 2.9412829875946045, "learning_rate": 5.973498610814277e-06, "loss": 0.2986, "step": 4130 }, { "epoch": 2.6415607259934437, "grad_norm": 2.458150863647461, "learning_rate": 5.962812566787775e-06, "loss": 0.2578, "step": 4131 }, { "epoch": 2.642200367794035, "grad_norm": 3.3725287914276123, "learning_rate": 5.952126522761274e-06, "loss": 0.3139, "step": 4132 }, { "epoch": 2.642840009594627, "grad_norm": 3.250953435897827, "learning_rate": 5.941440478734773e-06, "loss": 0.3064, "step": 4133 }, { "epoch": 2.643479651395219, "grad_norm": 2.531280517578125, "learning_rate": 5.930754434708271e-06, "loss": 0.2549, "step": 4134 }, { "epoch": 2.64411929319581, "grad_norm": 2.4597527980804443, "learning_rate": 5.920068390681769e-06, "loss": 0.2585, "step": 4135 }, { "epoch": 2.644758934996402, "grad_norm": 2.8698153495788574, "learning_rate": 5.909382346655269e-06, "loss": 0.3029, "step": 4136 }, { "epoch": 2.6453985767969934, "grad_norm": 3.027813673019409, "learning_rate": 5.898696302628767e-06, "loss": 0.3142, "step": 4137 }, { "epoch": 2.6460382185975853, "grad_norm": 2.9331483840942383, "learning_rate": 5.888010258602266e-06, "loss": 0.2862, "step": 4138 }, { "epoch": 2.646677860398177, "grad_norm": 3.0726869106292725, "learning_rate": 5.877324214575764e-06, "loss": 0.2923, "step": 4139 }, { "epoch": 2.647317502198769, "grad_norm": 2.5462653636932373, "learning_rate": 5.866638170549263e-06, "loss": 0.2852, "step": 4140 }, { "epoch": 2.6479571439993603, "grad_norm": 2.565436840057373, "learning_rate": 5.855952126522761e-06, "loss": 0.2619, "step": 4141 }, { "epoch": 2.648596785799952, "grad_norm": 3.403623580932617, "learning_rate": 5.845266082496261e-06, "loss": 0.3462, "step": 4142 }, { "epoch": 2.6492364276005436, "grad_norm": 2.9035401344299316, "learning_rate": 5.834580038469758e-06, "loss": 0.3012, "step": 4143 }, { "epoch": 2.6498760694011354, "grad_norm": 2.489408254623413, "learning_rate": 5.823893994443258e-06, "loss": 0.2695, "step": 4144 }, { "epoch": 2.6505157112017272, "grad_norm": 3.242091655731201, "learning_rate": 5.813207950416756e-06, "loss": 0.3183, "step": 4145 }, { "epoch": 2.6511553530023186, "grad_norm": 2.4779622554779053, "learning_rate": 5.802521906390255e-06, "loss": 0.2602, "step": 4146 }, { "epoch": 2.6517949948029105, "grad_norm": 3.315955400466919, "learning_rate": 5.791835862363753e-06, "loss": 0.2795, "step": 4147 }, { "epoch": 2.652434636603502, "grad_norm": 2.996861696243286, "learning_rate": 5.781149818337252e-06, "loss": 0.2877, "step": 4148 }, { "epoch": 2.6530742784040937, "grad_norm": 2.8245441913604736, "learning_rate": 5.77046377431075e-06, "loss": 0.289, "step": 4149 }, { "epoch": 2.6537139202046856, "grad_norm": 2.9259579181671143, "learning_rate": 5.75977773028425e-06, "loss": 0.3059, "step": 4150 }, { "epoch": 2.654353562005277, "grad_norm": 2.6691040992736816, "learning_rate": 5.749091686257747e-06, "loss": 0.2711, "step": 4151 }, { "epoch": 2.654993203805869, "grad_norm": 3.4666895866394043, "learning_rate": 5.738405642231246e-06, "loss": 0.2953, "step": 4152 }, { "epoch": 2.65563284560646, "grad_norm": 2.7008304595947266, "learning_rate": 5.727719598204745e-06, "loss": 0.2763, "step": 4153 }, { "epoch": 2.656272487407052, "grad_norm": 3.0840418338775635, "learning_rate": 5.717033554178244e-06, "loss": 0.2928, "step": 4154 }, { "epoch": 2.656912129207644, "grad_norm": 3.2053513526916504, "learning_rate": 5.706347510151741e-06, "loss": 0.3142, "step": 4155 }, { "epoch": 2.6575517710082353, "grad_norm": 3.2546536922454834, "learning_rate": 5.695661466125241e-06, "loss": 0.3102, "step": 4156 }, { "epoch": 2.658191412808827, "grad_norm": 3.1947944164276123, "learning_rate": 5.684975422098739e-06, "loss": 0.2905, "step": 4157 }, { "epoch": 2.6588310546094185, "grad_norm": 3.201735734939575, "learning_rate": 5.674289378072238e-06, "loss": 0.3058, "step": 4158 }, { "epoch": 2.6594706964100103, "grad_norm": 2.9859352111816406, "learning_rate": 5.663603334045737e-06, "loss": 0.2993, "step": 4159 }, { "epoch": 2.660110338210602, "grad_norm": 3.122661590576172, "learning_rate": 5.652917290019235e-06, "loss": 0.2867, "step": 4160 }, { "epoch": 2.660749980011194, "grad_norm": 2.6536948680877686, "learning_rate": 5.642231245992733e-06, "loss": 0.2663, "step": 4161 }, { "epoch": 2.6613896218117854, "grad_norm": 3.0495078563690186, "learning_rate": 5.631545201966233e-06, "loss": 0.2985, "step": 4162 }, { "epoch": 2.662029263612377, "grad_norm": 3.108170509338379, "learning_rate": 5.620859157939731e-06, "loss": 0.3308, "step": 4163 }, { "epoch": 2.6626689054129686, "grad_norm": 3.2326366901397705, "learning_rate": 5.61017311391323e-06, "loss": 0.2939, "step": 4164 }, { "epoch": 2.6633085472135605, "grad_norm": 2.168445348739624, "learning_rate": 5.599487069886728e-06, "loss": 0.2424, "step": 4165 }, { "epoch": 2.6639481890141523, "grad_norm": 2.6619482040405273, "learning_rate": 5.588801025860227e-06, "loss": 0.2654, "step": 4166 }, { "epoch": 2.6645878308147437, "grad_norm": 2.5055179595947266, "learning_rate": 5.578114981833726e-06, "loss": 0.2801, "step": 4167 }, { "epoch": 2.6652274726153355, "grad_norm": 3.1837360858917236, "learning_rate": 5.567428937807224e-06, "loss": 0.3115, "step": 4168 }, { "epoch": 2.665867114415927, "grad_norm": 2.5889251232147217, "learning_rate": 5.556742893780722e-06, "loss": 0.2524, "step": 4169 }, { "epoch": 2.666506756216519, "grad_norm": 2.5486278533935547, "learning_rate": 5.546056849754222e-06, "loss": 0.2824, "step": 4170 }, { "epoch": 2.6671463980171106, "grad_norm": 3.0237362384796143, "learning_rate": 5.53537080572772e-06, "loss": 0.2861, "step": 4171 }, { "epoch": 2.667786039817702, "grad_norm": 3.123845338821411, "learning_rate": 5.524684761701218e-06, "loss": 0.3142, "step": 4172 }, { "epoch": 2.668425681618294, "grad_norm": 2.7165184020996094, "learning_rate": 5.513998717674717e-06, "loss": 0.3037, "step": 4173 }, { "epoch": 2.6690653234188852, "grad_norm": 3.402109146118164, "learning_rate": 5.503312673648216e-06, "loss": 0.2981, "step": 4174 }, { "epoch": 2.669704965219477, "grad_norm": 3.0483319759368896, "learning_rate": 5.492626629621714e-06, "loss": 0.3018, "step": 4175 }, { "epoch": 2.670344607020069, "grad_norm": 2.8692407608032227, "learning_rate": 5.481940585595213e-06, "loss": 0.2783, "step": 4176 }, { "epoch": 2.6709842488206603, "grad_norm": 2.7753992080688477, "learning_rate": 5.471254541568711e-06, "loss": 0.2686, "step": 4177 }, { "epoch": 2.671623890621252, "grad_norm": 3.161330461502075, "learning_rate": 5.46056849754221e-06, "loss": 0.2931, "step": 4178 }, { "epoch": 2.6722635324218436, "grad_norm": 3.287898540496826, "learning_rate": 5.449882453515709e-06, "loss": 0.2971, "step": 4179 }, { "epoch": 2.6729031742224354, "grad_norm": 3.2551393508911133, "learning_rate": 5.439196409489208e-06, "loss": 0.3176, "step": 4180 }, { "epoch": 2.6735428160230272, "grad_norm": 2.699275016784668, "learning_rate": 5.428510365462706e-06, "loss": 0.2939, "step": 4181 }, { "epoch": 2.6741824578236186, "grad_norm": 2.2508926391601562, "learning_rate": 5.417824321436205e-06, "loss": 0.2436, "step": 4182 }, { "epoch": 2.6748220996242105, "grad_norm": 2.7938640117645264, "learning_rate": 5.407138277409703e-06, "loss": 0.2834, "step": 4183 }, { "epoch": 2.675461741424802, "grad_norm": 2.591665744781494, "learning_rate": 5.396452233383202e-06, "loss": 0.2577, "step": 4184 }, { "epoch": 2.6761013832253937, "grad_norm": 2.881643295288086, "learning_rate": 5.3857661893567e-06, "loss": 0.2878, "step": 4185 }, { "epoch": 2.6767410250259855, "grad_norm": 3.2424135208129883, "learning_rate": 5.375080145330199e-06, "loss": 0.2822, "step": 4186 }, { "epoch": 2.6773806668265774, "grad_norm": 2.951124906539917, "learning_rate": 5.364394101303698e-06, "loss": 0.2882, "step": 4187 }, { "epoch": 2.6780203086271688, "grad_norm": 2.629875659942627, "learning_rate": 5.353708057277197e-06, "loss": 0.2837, "step": 4188 }, { "epoch": 2.6786599504277606, "grad_norm": 2.9838707447052, "learning_rate": 5.343022013250694e-06, "loss": 0.2696, "step": 4189 }, { "epoch": 2.679299592228352, "grad_norm": 3.3642942905426025, "learning_rate": 5.332335969224194e-06, "loss": 0.2945, "step": 4190 }, { "epoch": 2.679939234028944, "grad_norm": 2.6537294387817383, "learning_rate": 5.321649925197692e-06, "loss": 0.2659, "step": 4191 }, { "epoch": 2.6805788758295357, "grad_norm": 2.961134672164917, "learning_rate": 5.310963881171191e-06, "loss": 0.3021, "step": 4192 }, { "epoch": 2.681218517630127, "grad_norm": 2.9832959175109863, "learning_rate": 5.300277837144689e-06, "loss": 0.2759, "step": 4193 }, { "epoch": 2.681858159430719, "grad_norm": 3.2399749755859375, "learning_rate": 5.289591793118188e-06, "loss": 0.2901, "step": 4194 }, { "epoch": 2.6824978012313103, "grad_norm": 3.1127965450286865, "learning_rate": 5.278905749091686e-06, "loss": 0.2898, "step": 4195 }, { "epoch": 2.683137443031902, "grad_norm": 2.775202989578247, "learning_rate": 5.2682197050651856e-06, "loss": 0.2701, "step": 4196 }, { "epoch": 2.683777084832494, "grad_norm": 3.1817328929901123, "learning_rate": 5.257533661038683e-06, "loss": 0.2887, "step": 4197 }, { "epoch": 2.6844167266330854, "grad_norm": 2.8848459720611572, "learning_rate": 5.246847617012183e-06, "loss": 0.2833, "step": 4198 }, { "epoch": 2.6850563684336772, "grad_norm": 3.141246795654297, "learning_rate": 5.236161572985681e-06, "loss": 0.3281, "step": 4199 }, { "epoch": 2.6856960102342686, "grad_norm": 2.347219467163086, "learning_rate": 5.22547552895918e-06, "loss": 0.2425, "step": 4200 }, { "epoch": 2.6863356520348605, "grad_norm": 2.8728418350219727, "learning_rate": 5.214789484932678e-06, "loss": 0.2825, "step": 4201 }, { "epoch": 2.6869752938354523, "grad_norm": 2.6260263919830322, "learning_rate": 5.204103440906177e-06, "loss": 0.2744, "step": 4202 }, { "epoch": 2.6876149356360437, "grad_norm": 2.8408377170562744, "learning_rate": 5.193417396879675e-06, "loss": 0.2717, "step": 4203 }, { "epoch": 2.6882545774366355, "grad_norm": 2.8726351261138916, "learning_rate": 5.1827313528531745e-06, "loss": 0.2622, "step": 4204 }, { "epoch": 2.688894219237227, "grad_norm": 3.2461130619049072, "learning_rate": 5.172045308826673e-06, "loss": 0.3063, "step": 4205 }, { "epoch": 2.6895338610378188, "grad_norm": 3.5422470569610596, "learning_rate": 5.161359264800171e-06, "loss": 0.3048, "step": 4206 }, { "epoch": 2.6901735028384106, "grad_norm": 2.274430513381958, "learning_rate": 5.15067322077367e-06, "loss": 0.2461, "step": 4207 }, { "epoch": 2.690813144639002, "grad_norm": 3.0163540840148926, "learning_rate": 5.139987176747169e-06, "loss": 0.2998, "step": 4208 }, { "epoch": 2.691452786439594, "grad_norm": 3.1758873462677, "learning_rate": 5.129301132720667e-06, "loss": 0.2838, "step": 4209 }, { "epoch": 2.6920924282401852, "grad_norm": 2.705134391784668, "learning_rate": 5.118615088694166e-06, "loss": 0.2716, "step": 4210 }, { "epoch": 2.692732070040777, "grad_norm": 3.293877124786377, "learning_rate": 5.107929044667664e-06, "loss": 0.3109, "step": 4211 }, { "epoch": 2.693371711841369, "grad_norm": 2.952885150909424, "learning_rate": 5.097243000641163e-06, "loss": 0.2894, "step": 4212 }, { "epoch": 2.6940113536419608, "grad_norm": 2.751307725906372, "learning_rate": 5.086556956614662e-06, "loss": 0.2919, "step": 4213 }, { "epoch": 2.694650995442552, "grad_norm": 2.981849193572998, "learning_rate": 5.07587091258816e-06, "loss": 0.2938, "step": 4214 }, { "epoch": 2.695290637243144, "grad_norm": 3.51705265045166, "learning_rate": 5.065184868561658e-06, "loss": 0.3294, "step": 4215 }, { "epoch": 2.6959302790437354, "grad_norm": 3.0744051933288574, "learning_rate": 5.0544988245351576e-06, "loss": 0.2863, "step": 4216 }, { "epoch": 2.6965699208443272, "grad_norm": 2.6534125804901123, "learning_rate": 5.043812780508656e-06, "loss": 0.2721, "step": 4217 }, { "epoch": 2.697209562644919, "grad_norm": 3.1245999336242676, "learning_rate": 5.033126736482155e-06, "loss": 0.2685, "step": 4218 }, { "epoch": 2.6978492044455105, "grad_norm": 3.1842539310455322, "learning_rate": 5.022440692455653e-06, "loss": 0.2827, "step": 4219 }, { "epoch": 2.6984888462461023, "grad_norm": 2.8639585971832275, "learning_rate": 5.011754648429152e-06, "loss": 0.2741, "step": 4220 }, { "epoch": 2.6991284880466937, "grad_norm": 3.223266839981079, "learning_rate": 5.001068604402651e-06, "loss": 0.2813, "step": 4221 }, { "epoch": 2.6997681298472855, "grad_norm": 2.59563946723938, "learning_rate": 4.990382560376149e-06, "loss": 0.2703, "step": 4222 }, { "epoch": 2.7004077716478774, "grad_norm": 3.1214075088500977, "learning_rate": 4.979696516349647e-06, "loss": 0.3095, "step": 4223 }, { "epoch": 2.7010474134484688, "grad_norm": 3.323255777359009, "learning_rate": 4.9690104723231465e-06, "loss": 0.2836, "step": 4224 }, { "epoch": 2.7016870552490606, "grad_norm": 2.9470183849334717, "learning_rate": 4.958324428296645e-06, "loss": 0.2959, "step": 4225 }, { "epoch": 2.702326697049652, "grad_norm": 2.841754198074341, "learning_rate": 4.9476383842701436e-06, "loss": 0.2668, "step": 4226 }, { "epoch": 2.702966338850244, "grad_norm": 2.7331454753875732, "learning_rate": 4.936952340243642e-06, "loss": 0.2629, "step": 4227 }, { "epoch": 2.7036059806508357, "grad_norm": 3.3476362228393555, "learning_rate": 4.926266296217141e-06, "loss": 0.2822, "step": 4228 }, { "epoch": 2.704245622451427, "grad_norm": 3.634173631668091, "learning_rate": 4.915580252190639e-06, "loss": 0.3238, "step": 4229 }, { "epoch": 2.704885264252019, "grad_norm": 2.7092347145080566, "learning_rate": 4.9048942081641385e-06, "loss": 0.2771, "step": 4230 }, { "epoch": 2.7055249060526103, "grad_norm": 3.4174089431762695, "learning_rate": 4.894208164137636e-06, "loss": 0.3338, "step": 4231 }, { "epoch": 2.706164547853202, "grad_norm": 3.521181583404541, "learning_rate": 4.883522120111135e-06, "loss": 0.313, "step": 4232 }, { "epoch": 2.706804189653794, "grad_norm": 3.2000532150268555, "learning_rate": 4.872836076084634e-06, "loss": 0.2663, "step": 4233 }, { "epoch": 2.7074438314543854, "grad_norm": 3.327611207962036, "learning_rate": 4.8621500320581325e-06, "loss": 0.2922, "step": 4234 }, { "epoch": 2.7080834732549772, "grad_norm": 2.673038959503174, "learning_rate": 4.851463988031631e-06, "loss": 0.2725, "step": 4235 }, { "epoch": 2.7087231150555686, "grad_norm": 2.920344829559326, "learning_rate": 4.8407779440051296e-06, "loss": 0.2803, "step": 4236 }, { "epoch": 2.7093627568561605, "grad_norm": 2.897177219390869, "learning_rate": 4.830091899978628e-06, "loss": 0.3026, "step": 4237 }, { "epoch": 2.7100023986567523, "grad_norm": 3.0198631286621094, "learning_rate": 4.819405855952127e-06, "loss": 0.2877, "step": 4238 }, { "epoch": 2.710642040457344, "grad_norm": 2.6498470306396484, "learning_rate": 4.808719811925625e-06, "loss": 0.2596, "step": 4239 }, { "epoch": 2.7112816822579355, "grad_norm": 3.356194257736206, "learning_rate": 4.798033767899124e-06, "loss": 0.3074, "step": 4240 }, { "epoch": 2.7119213240585274, "grad_norm": 3.342958450317383, "learning_rate": 4.787347723872623e-06, "loss": 0.3235, "step": 4241 }, { "epoch": 2.7125609658591188, "grad_norm": 2.8352184295654297, "learning_rate": 4.7766616798461215e-06, "loss": 0.2694, "step": 4242 }, { "epoch": 2.7132006076597106, "grad_norm": 2.9823131561279297, "learning_rate": 4.765975635819619e-06, "loss": 0.2917, "step": 4243 }, { "epoch": 2.7138402494603024, "grad_norm": 3.069110870361328, "learning_rate": 4.7552895917931185e-06, "loss": 0.3048, "step": 4244 }, { "epoch": 2.714479891260894, "grad_norm": 2.6191227436065674, "learning_rate": 4.744603547766617e-06, "loss": 0.2805, "step": 4245 }, { "epoch": 2.7151195330614857, "grad_norm": 2.5602385997772217, "learning_rate": 4.7339175037401155e-06, "loss": 0.2715, "step": 4246 }, { "epoch": 2.715759174862077, "grad_norm": 3.137227773666382, "learning_rate": 4.723231459713615e-06, "loss": 0.3087, "step": 4247 }, { "epoch": 2.716398816662669, "grad_norm": 2.524340867996216, "learning_rate": 4.712545415687113e-06, "loss": 0.2628, "step": 4248 }, { "epoch": 2.7170384584632608, "grad_norm": 3.0208139419555664, "learning_rate": 4.701859371660611e-06, "loss": 0.2891, "step": 4249 }, { "epoch": 2.717678100263852, "grad_norm": 2.7642719745635986, "learning_rate": 4.6911733276341105e-06, "loss": 0.2808, "step": 4250 }, { "epoch": 2.718317742064444, "grad_norm": 2.7058794498443604, "learning_rate": 4.680487283607609e-06, "loss": 0.2731, "step": 4251 }, { "epoch": 2.7189573838650354, "grad_norm": 2.7685511112213135, "learning_rate": 4.6698012395811075e-06, "loss": 0.2963, "step": 4252 }, { "epoch": 2.719597025665627, "grad_norm": 3.138655662536621, "learning_rate": 4.659115195554606e-06, "loss": 0.2915, "step": 4253 }, { "epoch": 2.720236667466219, "grad_norm": 2.9547863006591797, "learning_rate": 4.6484291515281045e-06, "loss": 0.2812, "step": 4254 }, { "epoch": 2.7208763092668105, "grad_norm": 2.6979265213012695, "learning_rate": 4.637743107501603e-06, "loss": 0.2777, "step": 4255 }, { "epoch": 2.7215159510674023, "grad_norm": 2.6382367610931396, "learning_rate": 4.6270570634751015e-06, "loss": 0.2528, "step": 4256 }, { "epoch": 2.7221555928679937, "grad_norm": 2.7664802074432373, "learning_rate": 4.6163710194486e-06, "loss": 0.2712, "step": 4257 }, { "epoch": 2.7227952346685855, "grad_norm": 3.006429672241211, "learning_rate": 4.605684975422099e-06, "loss": 0.2812, "step": 4258 }, { "epoch": 2.7234348764691774, "grad_norm": 2.851895809173584, "learning_rate": 4.594998931395598e-06, "loss": 0.2895, "step": 4259 }, { "epoch": 2.7240745182697688, "grad_norm": 2.8017094135284424, "learning_rate": 4.584312887369096e-06, "loss": 0.2591, "step": 4260 }, { "epoch": 2.7247141600703606, "grad_norm": 3.3680760860443115, "learning_rate": 4.573626843342595e-06, "loss": 0.288, "step": 4261 }, { "epoch": 2.725353801870952, "grad_norm": 2.263298988342285, "learning_rate": 4.5629407993160935e-06, "loss": 0.2514, "step": 4262 }, { "epoch": 2.725993443671544, "grad_norm": 2.707742691040039, "learning_rate": 4.552254755289592e-06, "loss": 0.2798, "step": 4263 }, { "epoch": 2.7266330854721357, "grad_norm": 2.7986104488372803, "learning_rate": 4.5415687112630905e-06, "loss": 0.3024, "step": 4264 }, { "epoch": 2.7272727272727275, "grad_norm": 2.538247585296631, "learning_rate": 4.530882667236589e-06, "loss": 0.2689, "step": 4265 }, { "epoch": 2.727912369073319, "grad_norm": 2.6567046642303467, "learning_rate": 4.5201966232100875e-06, "loss": 0.2737, "step": 4266 }, { "epoch": 2.7285520108739107, "grad_norm": 2.814138174057007, "learning_rate": 4.509510579183587e-06, "loss": 0.2854, "step": 4267 }, { "epoch": 2.729191652674502, "grad_norm": 3.2301576137542725, "learning_rate": 4.498824535157085e-06, "loss": 0.3337, "step": 4268 }, { "epoch": 2.729831294475094, "grad_norm": 3.3410801887512207, "learning_rate": 4.488138491130583e-06, "loss": 0.3102, "step": 4269 }, { "epoch": 2.730470936275686, "grad_norm": 2.9629862308502197, "learning_rate": 4.4774524471040824e-06, "loss": 0.3011, "step": 4270 }, { "epoch": 2.731110578076277, "grad_norm": 2.753415822982788, "learning_rate": 4.466766403077581e-06, "loss": 0.3009, "step": 4271 }, { "epoch": 2.731750219876869, "grad_norm": 2.6558845043182373, "learning_rate": 4.4560803590510795e-06, "loss": 0.2821, "step": 4272 }, { "epoch": 2.7323898616774605, "grad_norm": 2.7958014011383057, "learning_rate": 4.445394315024578e-06, "loss": 0.2767, "step": 4273 }, { "epoch": 2.7330295034780523, "grad_norm": 2.5357003211975098, "learning_rate": 4.4347082709980765e-06, "loss": 0.2557, "step": 4274 }, { "epoch": 2.733669145278644, "grad_norm": 2.817138671875, "learning_rate": 4.424022226971576e-06, "loss": 0.2833, "step": 4275 }, { "epoch": 2.7343087870792355, "grad_norm": 2.883695363998413, "learning_rate": 4.413336182945074e-06, "loss": 0.2795, "step": 4276 }, { "epoch": 2.7349484288798274, "grad_norm": 3.019054651260376, "learning_rate": 4.402650138918572e-06, "loss": 0.2828, "step": 4277 }, { "epoch": 2.7355880706804188, "grad_norm": 2.4605958461761475, "learning_rate": 4.391964094892071e-06, "loss": 0.2547, "step": 4278 }, { "epoch": 2.7362277124810106, "grad_norm": 2.8073604106903076, "learning_rate": 4.38127805086557e-06, "loss": 0.2618, "step": 4279 }, { "epoch": 2.7368673542816024, "grad_norm": 3.1890933513641357, "learning_rate": 4.3705920068390684e-06, "loss": 0.3149, "step": 4280 }, { "epoch": 2.737506996082194, "grad_norm": 2.758699655532837, "learning_rate": 4.359905962812567e-06, "loss": 0.2642, "step": 4281 }, { "epoch": 2.7381466378827857, "grad_norm": 3.0185227394104004, "learning_rate": 4.3492199187860655e-06, "loss": 0.302, "step": 4282 }, { "epoch": 2.738786279683377, "grad_norm": 2.9913456439971924, "learning_rate": 4.338533874759564e-06, "loss": 0.2947, "step": 4283 }, { "epoch": 2.739425921483969, "grad_norm": 3.417546272277832, "learning_rate": 4.327847830733063e-06, "loss": 0.3232, "step": 4284 }, { "epoch": 2.7400655632845607, "grad_norm": 3.3433175086975098, "learning_rate": 4.317161786706561e-06, "loss": 0.3161, "step": 4285 }, { "epoch": 2.7407052050851526, "grad_norm": 3.0465805530548096, "learning_rate": 4.3064757426800595e-06, "loss": 0.2781, "step": 4286 }, { "epoch": 2.741344846885744, "grad_norm": 3.096892833709717, "learning_rate": 4.295789698653559e-06, "loss": 0.2965, "step": 4287 }, { "epoch": 2.7419844886863354, "grad_norm": 3.2183213233947754, "learning_rate": 4.285103654627057e-06, "loss": 0.2968, "step": 4288 }, { "epoch": 2.742624130486927, "grad_norm": 3.0616166591644287, "learning_rate": 4.274417610600556e-06, "loss": 0.2947, "step": 4289 }, { "epoch": 2.743263772287519, "grad_norm": 3.0991125106811523, "learning_rate": 4.2637315665740544e-06, "loss": 0.289, "step": 4290 }, { "epoch": 2.743903414088111, "grad_norm": 2.7623724937438965, "learning_rate": 4.253045522547553e-06, "loss": 0.2643, "step": 4291 }, { "epoch": 2.7445430558887023, "grad_norm": 2.611386299133301, "learning_rate": 4.2423594785210515e-06, "loss": 0.2585, "step": 4292 }, { "epoch": 2.745182697689294, "grad_norm": 3.471163511276245, "learning_rate": 4.231673434494551e-06, "loss": 0.3117, "step": 4293 }, { "epoch": 2.7458223394898855, "grad_norm": 3.1270809173583984, "learning_rate": 4.2209873904680485e-06, "loss": 0.2695, "step": 4294 }, { "epoch": 2.7464619812904774, "grad_norm": 3.1040518283843994, "learning_rate": 4.210301346441548e-06, "loss": 0.2915, "step": 4295 }, { "epoch": 2.747101623091069, "grad_norm": 3.2834489345550537, "learning_rate": 4.199615302415046e-06, "loss": 0.3236, "step": 4296 }, { "epoch": 2.7477412648916606, "grad_norm": 2.616297483444214, "learning_rate": 4.188929258388545e-06, "loss": 0.2593, "step": 4297 }, { "epoch": 2.7483809066922524, "grad_norm": 3.05403208732605, "learning_rate": 4.178243214362043e-06, "loss": 0.2999, "step": 4298 }, { "epoch": 2.749020548492844, "grad_norm": 2.8387467861175537, "learning_rate": 4.167557170335542e-06, "loss": 0.2715, "step": 4299 }, { "epoch": 2.7496601902934357, "grad_norm": 3.0170047283172607, "learning_rate": 4.1568711263090404e-06, "loss": 0.3102, "step": 4300 }, { "epoch": 2.7502998320940275, "grad_norm": 3.2853238582611084, "learning_rate": 4.14618508228254e-06, "loss": 0.2833, "step": 4301 }, { "epoch": 2.750939473894619, "grad_norm": 2.645761489868164, "learning_rate": 4.1354990382560375e-06, "loss": 0.2832, "step": 4302 }, { "epoch": 2.7515791156952107, "grad_norm": 2.951225757598877, "learning_rate": 4.124812994229536e-06, "loss": 0.2751, "step": 4303 }, { "epoch": 2.752218757495802, "grad_norm": 3.365863561630249, "learning_rate": 4.114126950203035e-06, "loss": 0.2885, "step": 4304 }, { "epoch": 2.752858399296394, "grad_norm": 2.9383087158203125, "learning_rate": 4.103440906176534e-06, "loss": 0.2691, "step": 4305 }, { "epoch": 2.753498041096986, "grad_norm": 2.956564426422119, "learning_rate": 4.092754862150032e-06, "loss": 0.2851, "step": 4306 }, { "epoch": 2.754137682897577, "grad_norm": 2.7642822265625, "learning_rate": 4.082068818123531e-06, "loss": 0.2559, "step": 4307 }, { "epoch": 2.754777324698169, "grad_norm": 2.8226330280303955, "learning_rate": 4.071382774097029e-06, "loss": 0.2947, "step": 4308 }, { "epoch": 2.7554169664987604, "grad_norm": 2.5690696239471436, "learning_rate": 4.060696730070528e-06, "loss": 0.278, "step": 4309 }, { "epoch": 2.7560566082993523, "grad_norm": 2.728264331817627, "learning_rate": 4.0500106860440264e-06, "loss": 0.2755, "step": 4310 }, { "epoch": 2.756696250099944, "grad_norm": 3.820427417755127, "learning_rate": 4.039324642017525e-06, "loss": 0.328, "step": 4311 }, { "epoch": 2.757335891900536, "grad_norm": 3.085919141769409, "learning_rate": 4.028638597991024e-06, "loss": 0.3017, "step": 4312 }, { "epoch": 2.7579755337011274, "grad_norm": 2.4799747467041016, "learning_rate": 4.017952553964523e-06, "loss": 0.2752, "step": 4313 }, { "epoch": 2.758615175501719, "grad_norm": 2.7526347637176514, "learning_rate": 4.007266509938021e-06, "loss": 0.2852, "step": 4314 }, { "epoch": 2.7592548173023106, "grad_norm": 3.2440788745880127, "learning_rate": 3.99658046591152e-06, "loss": 0.2774, "step": 4315 }, { "epoch": 2.7598944591029024, "grad_norm": 3.0366628170013428, "learning_rate": 3.985894421885018e-06, "loss": 0.2959, "step": 4316 }, { "epoch": 2.7605341009034943, "grad_norm": 3.4696261882781982, "learning_rate": 3.975208377858517e-06, "loss": 0.3348, "step": 4317 }, { "epoch": 2.7611737427040857, "grad_norm": 2.8783366680145264, "learning_rate": 3.964522333832016e-06, "loss": 0.2849, "step": 4318 }, { "epoch": 2.7618133845046775, "grad_norm": 3.1641640663146973, "learning_rate": 3.953836289805514e-06, "loss": 0.3092, "step": 4319 }, { "epoch": 2.762453026305269, "grad_norm": 2.837355375289917, "learning_rate": 3.9431502457790124e-06, "loss": 0.2783, "step": 4320 }, { "epoch": 2.7630926681058607, "grad_norm": 3.71797251701355, "learning_rate": 3.932464201752512e-06, "loss": 0.2831, "step": 4321 }, { "epoch": 2.7637323099064526, "grad_norm": 2.7682456970214844, "learning_rate": 3.92177815772601e-06, "loss": 0.2827, "step": 4322 }, { "epoch": 2.764371951707044, "grad_norm": 2.8644909858703613, "learning_rate": 3.911092113699508e-06, "loss": 0.2739, "step": 4323 }, { "epoch": 2.765011593507636, "grad_norm": 2.6375932693481445, "learning_rate": 3.900406069673007e-06, "loss": 0.2696, "step": 4324 }, { "epoch": 2.765651235308227, "grad_norm": 2.5685291290283203, "learning_rate": 3.889720025646506e-06, "loss": 0.2862, "step": 4325 }, { "epoch": 2.766290877108819, "grad_norm": 2.8904924392700195, "learning_rate": 3.879033981620004e-06, "loss": 0.2928, "step": 4326 }, { "epoch": 2.766930518909411, "grad_norm": 2.633225679397583, "learning_rate": 3.868347937593503e-06, "loss": 0.2808, "step": 4327 }, { "epoch": 2.7675701607100023, "grad_norm": 2.960737466812134, "learning_rate": 3.857661893567001e-06, "loss": 0.3142, "step": 4328 }, { "epoch": 2.768209802510594, "grad_norm": 2.710519552230835, "learning_rate": 3.846975849540501e-06, "loss": 0.2606, "step": 4329 }, { "epoch": 2.7688494443111855, "grad_norm": 3.3091506958007812, "learning_rate": 3.836289805513999e-06, "loss": 0.3251, "step": 4330 }, { "epoch": 2.7694890861117774, "grad_norm": 3.3194949626922607, "learning_rate": 3.825603761487497e-06, "loss": 0.2808, "step": 4331 }, { "epoch": 2.770128727912369, "grad_norm": 3.1072676181793213, "learning_rate": 3.814917717460996e-06, "loss": 0.2722, "step": 4332 }, { "epoch": 2.7707683697129606, "grad_norm": 2.84649920463562, "learning_rate": 3.804231673434495e-06, "loss": 0.2841, "step": 4333 }, { "epoch": 2.7714080115135524, "grad_norm": 2.699164867401123, "learning_rate": 3.7935456294079933e-06, "loss": 0.2688, "step": 4334 }, { "epoch": 2.772047653314144, "grad_norm": 2.55708384513855, "learning_rate": 3.7828595853814923e-06, "loss": 0.2679, "step": 4335 }, { "epoch": 2.7726872951147357, "grad_norm": 3.57153058052063, "learning_rate": 3.7721735413549904e-06, "loss": 0.3103, "step": 4336 }, { "epoch": 2.7733269369153275, "grad_norm": 2.890146493911743, "learning_rate": 3.7614874973284893e-06, "loss": 0.2904, "step": 4337 }, { "epoch": 2.7739665787159193, "grad_norm": 2.9208571910858154, "learning_rate": 3.750801453301988e-06, "loss": 0.2812, "step": 4338 }, { "epoch": 2.7746062205165107, "grad_norm": 2.7111175060272217, "learning_rate": 3.7401154092754868e-06, "loss": 0.2941, "step": 4339 }, { "epoch": 2.7752458623171026, "grad_norm": 3.1619319915771484, "learning_rate": 3.729429365248985e-06, "loss": 0.2947, "step": 4340 }, { "epoch": 2.775885504117694, "grad_norm": 2.8458549976348877, "learning_rate": 3.7187433212224834e-06, "loss": 0.2706, "step": 4341 }, { "epoch": 2.776525145918286, "grad_norm": 2.991636037826538, "learning_rate": 3.7080572771959823e-06, "loss": 0.3078, "step": 4342 }, { "epoch": 2.7771647877188776, "grad_norm": 2.2828590869903564, "learning_rate": 3.6973712331694812e-06, "loss": 0.2424, "step": 4343 }, { "epoch": 2.777804429519469, "grad_norm": 2.745360851287842, "learning_rate": 3.6866851891429793e-06, "loss": 0.2866, "step": 4344 }, { "epoch": 2.778444071320061, "grad_norm": 2.9150893688201904, "learning_rate": 3.675999145116478e-06, "loss": 0.2782, "step": 4345 }, { "epoch": 2.7790837131206523, "grad_norm": 2.833770990371704, "learning_rate": 3.6653131010899768e-06, "loss": 0.2686, "step": 4346 }, { "epoch": 2.779723354921244, "grad_norm": 2.651599407196045, "learning_rate": 3.6546270570634757e-06, "loss": 0.2562, "step": 4347 }, { "epoch": 2.780362996721836, "grad_norm": 2.827512502670288, "learning_rate": 3.643941013036974e-06, "loss": 0.2857, "step": 4348 }, { "epoch": 2.7810026385224274, "grad_norm": 3.3250107765197754, "learning_rate": 3.6332549690104723e-06, "loss": 0.2835, "step": 4349 }, { "epoch": 2.781642280323019, "grad_norm": 3.0457489490509033, "learning_rate": 3.6225689249839713e-06, "loss": 0.3035, "step": 4350 }, { "epoch": 2.7822819221236106, "grad_norm": 3.0998637676239014, "learning_rate": 3.6118828809574698e-06, "loss": 0.3205, "step": 4351 }, { "epoch": 2.7829215639242024, "grad_norm": 3.358431100845337, "learning_rate": 3.601196836930968e-06, "loss": 0.3037, "step": 4352 }, { "epoch": 2.7835612057247943, "grad_norm": 2.650522470474243, "learning_rate": 3.590510792904467e-06, "loss": 0.2775, "step": 4353 }, { "epoch": 2.7842008475253857, "grad_norm": 4.187964916229248, "learning_rate": 3.5798247488779657e-06, "loss": 0.3216, "step": 4354 }, { "epoch": 2.7848404893259775, "grad_norm": 3.1567907333374023, "learning_rate": 3.5691387048514643e-06, "loss": 0.2811, "step": 4355 }, { "epoch": 2.785480131126569, "grad_norm": 3.484435796737671, "learning_rate": 3.5584526608249624e-06, "loss": 0.2766, "step": 4356 }, { "epoch": 2.7861197729271607, "grad_norm": 3.3332550525665283, "learning_rate": 3.5477666167984613e-06, "loss": 0.3362, "step": 4357 }, { "epoch": 2.7867594147277526, "grad_norm": 2.9056642055511475, "learning_rate": 3.53708057277196e-06, "loss": 0.2717, "step": 4358 }, { "epoch": 2.787399056528344, "grad_norm": 3.070425510406494, "learning_rate": 3.5263945287454587e-06, "loss": 0.302, "step": 4359 }, { "epoch": 2.788038698328936, "grad_norm": 3.1967034339904785, "learning_rate": 3.5157084847189577e-06, "loss": 0.2879, "step": 4360 }, { "epoch": 2.788678340129527, "grad_norm": 3.0473732948303223, "learning_rate": 3.5050224406924558e-06, "loss": 0.3098, "step": 4361 }, { "epoch": 2.789317981930119, "grad_norm": 2.8728370666503906, "learning_rate": 3.4943363966659543e-06, "loss": 0.2813, "step": 4362 }, { "epoch": 2.789957623730711, "grad_norm": 3.050708055496216, "learning_rate": 3.4836503526394532e-06, "loss": 0.2851, "step": 4363 }, { "epoch": 2.7905972655313027, "grad_norm": 3.4656426906585693, "learning_rate": 3.4729643086129517e-06, "loss": 0.2976, "step": 4364 }, { "epoch": 2.791236907331894, "grad_norm": 2.9025158882141113, "learning_rate": 3.46227826458645e-06, "loss": 0.3071, "step": 4365 }, { "epoch": 2.791876549132486, "grad_norm": 3.0199522972106934, "learning_rate": 3.4515922205599488e-06, "loss": 0.3034, "step": 4366 }, { "epoch": 2.7925161909330773, "grad_norm": 2.7764556407928467, "learning_rate": 3.4409061765334477e-06, "loss": 0.2871, "step": 4367 }, { "epoch": 2.793155832733669, "grad_norm": 2.6626172065734863, "learning_rate": 3.4302201325069462e-06, "loss": 0.2799, "step": 4368 }, { "epoch": 2.793795474534261, "grad_norm": 2.648641347885132, "learning_rate": 3.4195340884804443e-06, "loss": 0.2761, "step": 4369 }, { "epoch": 2.7944351163348524, "grad_norm": 2.799649715423584, "learning_rate": 3.4088480444539433e-06, "loss": 0.2965, "step": 4370 }, { "epoch": 2.7950747581354443, "grad_norm": 3.063737392425537, "learning_rate": 3.398162000427442e-06, "loss": 0.3055, "step": 4371 }, { "epoch": 2.7957143999360357, "grad_norm": 3.050278663635254, "learning_rate": 3.3874759564009407e-06, "loss": 0.2963, "step": 4372 }, { "epoch": 2.7963540417366275, "grad_norm": 3.035537004470825, "learning_rate": 3.376789912374439e-06, "loss": 0.2972, "step": 4373 }, { "epoch": 2.7969936835372193, "grad_norm": 2.829928398132324, "learning_rate": 3.3661038683479377e-06, "loss": 0.2796, "step": 4374 }, { "epoch": 2.7976333253378107, "grad_norm": 3.306140899658203, "learning_rate": 3.3554178243214363e-06, "loss": 0.3257, "step": 4375 }, { "epoch": 2.7982729671384026, "grad_norm": 3.1015918254852295, "learning_rate": 3.344731780294935e-06, "loss": 0.2802, "step": 4376 }, { "epoch": 2.798912608938994, "grad_norm": 2.5656542778015137, "learning_rate": 3.3340457362684333e-06, "loss": 0.2749, "step": 4377 }, { "epoch": 2.799552250739586, "grad_norm": 3.343717098236084, "learning_rate": 3.3233596922419322e-06, "loss": 0.3091, "step": 4378 }, { "epoch": 2.8001918925401776, "grad_norm": 3.0400617122650146, "learning_rate": 3.3126736482154307e-06, "loss": 0.3018, "step": 4379 }, { "epoch": 2.800831534340769, "grad_norm": 3.060997247695923, "learning_rate": 3.3019876041889297e-06, "loss": 0.2844, "step": 4380 }, { "epoch": 2.801471176141361, "grad_norm": 2.625800848007202, "learning_rate": 3.291301560162428e-06, "loss": 0.2574, "step": 4381 }, { "epoch": 2.8021108179419523, "grad_norm": 2.535931348800659, "learning_rate": 3.2806155161359263e-06, "loss": 0.249, "step": 4382 }, { "epoch": 2.802750459742544, "grad_norm": 2.6953437328338623, "learning_rate": 3.2699294721094252e-06, "loss": 0.2939, "step": 4383 }, { "epoch": 2.803390101543136, "grad_norm": 2.51912522315979, "learning_rate": 3.259243428082924e-06, "loss": 0.2707, "step": 4384 }, { "epoch": 2.804029743343728, "grad_norm": 3.424211263656616, "learning_rate": 3.2485573840564227e-06, "loss": 0.3125, "step": 4385 }, { "epoch": 2.804669385144319, "grad_norm": 2.679070472717285, "learning_rate": 3.2378713400299208e-06, "loss": 0.2781, "step": 4386 }, { "epoch": 2.8053090269449106, "grad_norm": 2.960639238357544, "learning_rate": 3.2271852960034197e-06, "loss": 0.2779, "step": 4387 }, { "epoch": 2.8059486687455024, "grad_norm": 2.8190581798553467, "learning_rate": 3.2164992519769182e-06, "loss": 0.2968, "step": 4388 }, { "epoch": 2.8065883105460943, "grad_norm": 2.830000400543213, "learning_rate": 3.205813207950417e-06, "loss": 0.2794, "step": 4389 }, { "epoch": 2.807227952346686, "grad_norm": 3.1681251525878906, "learning_rate": 3.1951271639239152e-06, "loss": 0.2954, "step": 4390 }, { "epoch": 2.8078675941472775, "grad_norm": 3.336529493331909, "learning_rate": 3.184441119897414e-06, "loss": 0.3086, "step": 4391 }, { "epoch": 2.8085072359478693, "grad_norm": 2.824638605117798, "learning_rate": 3.1737550758709127e-06, "loss": 0.3031, "step": 4392 }, { "epoch": 2.8091468777484607, "grad_norm": 2.7733805179595947, "learning_rate": 3.1630690318444116e-06, "loss": 0.2981, "step": 4393 }, { "epoch": 2.8097865195490526, "grad_norm": 2.6935651302337646, "learning_rate": 3.1523829878179097e-06, "loss": 0.2525, "step": 4394 }, { "epoch": 2.8104261613496444, "grad_norm": 2.861525058746338, "learning_rate": 3.1416969437914082e-06, "loss": 0.2942, "step": 4395 }, { "epoch": 2.811065803150236, "grad_norm": 2.9324049949645996, "learning_rate": 3.131010899764907e-06, "loss": 0.275, "step": 4396 }, { "epoch": 2.8117054449508276, "grad_norm": 3.4254677295684814, "learning_rate": 3.1203248557384057e-06, "loss": 0.3047, "step": 4397 }, { "epoch": 2.812345086751419, "grad_norm": 2.902474880218506, "learning_rate": 3.1096388117119042e-06, "loss": 0.2991, "step": 4398 }, { "epoch": 2.812984728552011, "grad_norm": 3.1528453826904297, "learning_rate": 3.0989527676854027e-06, "loss": 0.2864, "step": 4399 }, { "epoch": 2.8136243703526027, "grad_norm": 2.527876138687134, "learning_rate": 3.0882667236589017e-06, "loss": 0.2738, "step": 4400 }, { "epoch": 2.814264012153194, "grad_norm": 2.8778088092803955, "learning_rate": 3.0775806796324006e-06, "loss": 0.2776, "step": 4401 }, { "epoch": 2.814903653953786, "grad_norm": 2.662203311920166, "learning_rate": 3.0668946356058987e-06, "loss": 0.2826, "step": 4402 }, { "epoch": 2.8155432957543773, "grad_norm": 2.9346282482147217, "learning_rate": 3.0562085915793976e-06, "loss": 0.2772, "step": 4403 }, { "epoch": 2.816182937554969, "grad_norm": 3.0452077388763428, "learning_rate": 3.045522547552896e-06, "loss": 0.3035, "step": 4404 }, { "epoch": 2.816822579355561, "grad_norm": 2.934515953063965, "learning_rate": 3.0348365035263947e-06, "loss": 0.2905, "step": 4405 }, { "epoch": 2.8174622211561524, "grad_norm": 3.2118186950683594, "learning_rate": 3.024150459499893e-06, "loss": 0.3183, "step": 4406 }, { "epoch": 2.8181018629567443, "grad_norm": 2.4275498390197754, "learning_rate": 3.013464415473392e-06, "loss": 0.2464, "step": 4407 }, { "epoch": 2.8187415047573356, "grad_norm": 2.818660020828247, "learning_rate": 3.0027783714468906e-06, "loss": 0.259, "step": 4408 }, { "epoch": 2.8193811465579275, "grad_norm": 2.9263291358947754, "learning_rate": 2.992092327420389e-06, "loss": 0.2972, "step": 4409 }, { "epoch": 2.8200207883585193, "grad_norm": 2.783811569213867, "learning_rate": 2.9814062833938877e-06, "loss": 0.2654, "step": 4410 }, { "epoch": 2.820660430159111, "grad_norm": 2.725036144256592, "learning_rate": 2.9707202393673866e-06, "loss": 0.2806, "step": 4411 }, { "epoch": 2.8213000719597026, "grad_norm": 3.0917141437530518, "learning_rate": 2.9600341953408847e-06, "loss": 0.3035, "step": 4412 }, { "epoch": 2.8219397137602944, "grad_norm": 3.1890900135040283, "learning_rate": 2.9493481513143836e-06, "loss": 0.3042, "step": 4413 }, { "epoch": 2.822579355560886, "grad_norm": 2.684833526611328, "learning_rate": 2.938662107287882e-06, "loss": 0.2932, "step": 4414 }, { "epoch": 2.8232189973614776, "grad_norm": 3.2052884101867676, "learning_rate": 2.9279760632613807e-06, "loss": 0.3093, "step": 4415 }, { "epoch": 2.8238586391620695, "grad_norm": 2.8202271461486816, "learning_rate": 2.917290019234879e-06, "loss": 0.2974, "step": 4416 }, { "epoch": 2.824498280962661, "grad_norm": 3.0298025608062744, "learning_rate": 2.906603975208378e-06, "loss": 0.2873, "step": 4417 }, { "epoch": 2.8251379227632527, "grad_norm": 3.641127109527588, "learning_rate": 2.8959179311818766e-06, "loss": 0.2691, "step": 4418 }, { "epoch": 2.825777564563844, "grad_norm": 2.972038507461548, "learning_rate": 2.885231887155375e-06, "loss": 0.2884, "step": 4419 }, { "epoch": 2.826417206364436, "grad_norm": 2.6751515865325928, "learning_rate": 2.8745458431288737e-06, "loss": 0.2743, "step": 4420 }, { "epoch": 2.827056848165028, "grad_norm": 3.1087398529052734, "learning_rate": 2.8638597991023726e-06, "loss": 0.3031, "step": 4421 }, { "epoch": 2.827696489965619, "grad_norm": 2.8744654655456543, "learning_rate": 2.8531737550758707e-06, "loss": 0.2735, "step": 4422 }, { "epoch": 2.828336131766211, "grad_norm": 2.2815442085266113, "learning_rate": 2.8424877110493696e-06, "loss": 0.2462, "step": 4423 }, { "epoch": 2.8289757735668024, "grad_norm": 2.687335252761841, "learning_rate": 2.8318016670228686e-06, "loss": 0.2748, "step": 4424 }, { "epoch": 2.8296154153673942, "grad_norm": 2.5950405597686768, "learning_rate": 2.8211156229963667e-06, "loss": 0.2687, "step": 4425 }, { "epoch": 2.830255057167986, "grad_norm": 2.342142105102539, "learning_rate": 2.8104295789698656e-06, "loss": 0.2572, "step": 4426 }, { "epoch": 2.8308946989685775, "grad_norm": 2.861114740371704, "learning_rate": 2.799743534943364e-06, "loss": 0.2811, "step": 4427 }, { "epoch": 2.8315343407691693, "grad_norm": 2.8731443881988525, "learning_rate": 2.789057490916863e-06, "loss": 0.283, "step": 4428 }, { "epoch": 2.8321739825697607, "grad_norm": 3.097060441970825, "learning_rate": 2.778371446890361e-06, "loss": 0.3096, "step": 4429 }, { "epoch": 2.8328136243703526, "grad_norm": 4.110934257507324, "learning_rate": 2.76768540286386e-06, "loss": 0.3314, "step": 4430 }, { "epoch": 2.8334532661709444, "grad_norm": 2.848787546157837, "learning_rate": 2.7569993588373586e-06, "loss": 0.2873, "step": 4431 }, { "epoch": 2.834092907971536, "grad_norm": 2.7672512531280518, "learning_rate": 2.746313314810857e-06, "loss": 0.2787, "step": 4432 }, { "epoch": 2.8347325497721276, "grad_norm": 2.677736282348633, "learning_rate": 2.7356272707843556e-06, "loss": 0.2816, "step": 4433 }, { "epoch": 2.835372191572719, "grad_norm": 3.465515613555908, "learning_rate": 2.7249412267578546e-06, "loss": 0.2938, "step": 4434 }, { "epoch": 2.836011833373311, "grad_norm": 2.5248990058898926, "learning_rate": 2.714255182731353e-06, "loss": 0.2536, "step": 4435 }, { "epoch": 2.8366514751739027, "grad_norm": 2.5295493602752686, "learning_rate": 2.7035691387048516e-06, "loss": 0.2795, "step": 4436 }, { "epoch": 2.8372911169744945, "grad_norm": 2.877410888671875, "learning_rate": 2.69288309467835e-06, "loss": 0.2868, "step": 4437 }, { "epoch": 2.837930758775086, "grad_norm": 3.1989567279815674, "learning_rate": 2.682197050651849e-06, "loss": 0.2704, "step": 4438 }, { "epoch": 2.8385704005756778, "grad_norm": 2.678420305252075, "learning_rate": 2.671511006625347e-06, "loss": 0.2627, "step": 4439 }, { "epoch": 2.839210042376269, "grad_norm": 2.7687106132507324, "learning_rate": 2.660824962598846e-06, "loss": 0.2703, "step": 4440 }, { "epoch": 2.839849684176861, "grad_norm": 2.8759844303131104, "learning_rate": 2.6501389185723446e-06, "loss": 0.2849, "step": 4441 }, { "epoch": 2.840489325977453, "grad_norm": 2.9912939071655273, "learning_rate": 2.639452874545843e-06, "loss": 0.2894, "step": 4442 }, { "epoch": 2.8411289677780442, "grad_norm": 3.125586748123169, "learning_rate": 2.6287668305193416e-06, "loss": 0.2847, "step": 4443 }, { "epoch": 2.841768609578636, "grad_norm": 3.2092106342315674, "learning_rate": 2.6180807864928406e-06, "loss": 0.3125, "step": 4444 }, { "epoch": 2.8424082513792275, "grad_norm": 2.9209115505218506, "learning_rate": 2.607394742466339e-06, "loss": 0.3, "step": 4445 }, { "epoch": 2.8430478931798193, "grad_norm": 3.406400442123413, "learning_rate": 2.5967086984398376e-06, "loss": 0.3029, "step": 4446 }, { "epoch": 2.843687534980411, "grad_norm": 2.841463804244995, "learning_rate": 2.5860226544133365e-06, "loss": 0.2708, "step": 4447 }, { "epoch": 2.8443271767810026, "grad_norm": 2.6019279956817627, "learning_rate": 2.575336610386835e-06, "loss": 0.2326, "step": 4448 }, { "epoch": 2.8449668185815944, "grad_norm": 3.1764168739318848, "learning_rate": 2.5646505663603336e-06, "loss": 0.2887, "step": 4449 }, { "epoch": 2.845606460382186, "grad_norm": 3.4707717895507812, "learning_rate": 2.553964522333832e-06, "loss": 0.3073, "step": 4450 }, { "epoch": 2.8462461021827776, "grad_norm": 3.472691297531128, "learning_rate": 2.543278478307331e-06, "loss": 0.2948, "step": 4451 }, { "epoch": 2.8468857439833695, "grad_norm": 3.0213184356689453, "learning_rate": 2.532592434280829e-06, "loss": 0.3179, "step": 4452 }, { "epoch": 2.847525385783961, "grad_norm": 2.8417153358459473, "learning_rate": 2.521906390254328e-06, "loss": 0.289, "step": 4453 }, { "epoch": 2.8481650275845527, "grad_norm": 3.0796499252319336, "learning_rate": 2.5112203462278266e-06, "loss": 0.2905, "step": 4454 }, { "epoch": 2.848804669385144, "grad_norm": 3.237510919570923, "learning_rate": 2.5005343022013255e-06, "loss": 0.2824, "step": 4455 }, { "epoch": 2.849444311185736, "grad_norm": 2.8167152404785156, "learning_rate": 2.4898482581748236e-06, "loss": 0.267, "step": 4456 }, { "epoch": 2.8500839529863278, "grad_norm": 3.1566784381866455, "learning_rate": 2.4791622141483225e-06, "loss": 0.2993, "step": 4457 }, { "epoch": 2.850723594786919, "grad_norm": 3.1024036407470703, "learning_rate": 2.468476170121821e-06, "loss": 0.2976, "step": 4458 }, { "epoch": 2.851363236587511, "grad_norm": 3.156390428543091, "learning_rate": 2.4577901260953196e-06, "loss": 0.3021, "step": 4459 }, { "epoch": 2.8520028783881024, "grad_norm": 3.0627458095550537, "learning_rate": 2.447104082068818e-06, "loss": 0.3186, "step": 4460 }, { "epoch": 2.8526425201886942, "grad_norm": 2.8380753993988037, "learning_rate": 2.436418038042317e-06, "loss": 0.2671, "step": 4461 }, { "epoch": 2.853282161989286, "grad_norm": 3.080984354019165, "learning_rate": 2.4257319940158155e-06, "loss": 0.2833, "step": 4462 }, { "epoch": 2.853921803789878, "grad_norm": 3.3176052570343018, "learning_rate": 2.415045949989314e-06, "loss": 0.3048, "step": 4463 }, { "epoch": 2.8545614455904693, "grad_norm": 2.612539052963257, "learning_rate": 2.4043599059628125e-06, "loss": 0.2625, "step": 4464 }, { "epoch": 2.855201087391061, "grad_norm": 3.0982754230499268, "learning_rate": 2.3936738619363115e-06, "loss": 0.2867, "step": 4465 }, { "epoch": 2.8558407291916525, "grad_norm": 3.2011759281158447, "learning_rate": 2.3829878179098096e-06, "loss": 0.3032, "step": 4466 }, { "epoch": 2.8564803709922444, "grad_norm": 2.8386285305023193, "learning_rate": 2.3723017738833085e-06, "loss": 0.2833, "step": 4467 }, { "epoch": 2.8571200127928362, "grad_norm": 3.224090814590454, "learning_rate": 2.3616157298568075e-06, "loss": 0.3061, "step": 4468 }, { "epoch": 2.8577596545934276, "grad_norm": 2.700939893722534, "learning_rate": 2.3509296858303055e-06, "loss": 0.2576, "step": 4469 }, { "epoch": 2.8583992963940195, "grad_norm": 3.0068764686584473, "learning_rate": 2.3402436418038045e-06, "loss": 0.3104, "step": 4470 }, { "epoch": 2.859038938194611, "grad_norm": 3.267613410949707, "learning_rate": 2.329557597777303e-06, "loss": 0.2954, "step": 4471 }, { "epoch": 2.8596785799952027, "grad_norm": 2.724755048751831, "learning_rate": 2.3188715537508015e-06, "loss": 0.2525, "step": 4472 }, { "epoch": 2.8603182217957945, "grad_norm": 2.891340732574463, "learning_rate": 2.3081855097243e-06, "loss": 0.2697, "step": 4473 }, { "epoch": 2.860957863596386, "grad_norm": 2.728368043899536, "learning_rate": 2.297499465697799e-06, "loss": 0.2832, "step": 4474 }, { "epoch": 2.8615975053969778, "grad_norm": 2.3273205757141113, "learning_rate": 2.2868134216712975e-06, "loss": 0.2386, "step": 4475 }, { "epoch": 2.862237147197569, "grad_norm": 2.6215415000915527, "learning_rate": 2.276127377644796e-06, "loss": 0.2768, "step": 4476 }, { "epoch": 2.862876788998161, "grad_norm": 2.777740478515625, "learning_rate": 2.2654413336182945e-06, "loss": 0.2642, "step": 4477 }, { "epoch": 2.863516430798753, "grad_norm": 3.0811619758605957, "learning_rate": 2.2547552895917935e-06, "loss": 0.2731, "step": 4478 }, { "epoch": 2.8641560725993442, "grad_norm": 3.0682265758514404, "learning_rate": 2.2440692455652915e-06, "loss": 0.2958, "step": 4479 }, { "epoch": 2.864795714399936, "grad_norm": 2.815882921218872, "learning_rate": 2.2333832015387905e-06, "loss": 0.2821, "step": 4480 }, { "epoch": 2.8654353562005275, "grad_norm": 3.0600154399871826, "learning_rate": 2.222697157512289e-06, "loss": 0.3083, "step": 4481 }, { "epoch": 2.8660749980011193, "grad_norm": 2.6533071994781494, "learning_rate": 2.212011113485788e-06, "loss": 0.2635, "step": 4482 }, { "epoch": 2.866714639801711, "grad_norm": 2.6439638137817383, "learning_rate": 2.201325069459286e-06, "loss": 0.2573, "step": 4483 }, { "epoch": 2.8673542816023025, "grad_norm": 3.31026291847229, "learning_rate": 2.190639025432785e-06, "loss": 0.3141, "step": 4484 }, { "epoch": 2.8679939234028944, "grad_norm": 3.262610912322998, "learning_rate": 2.1799529814062835e-06, "loss": 0.3036, "step": 4485 }, { "epoch": 2.868633565203486, "grad_norm": 2.77650785446167, "learning_rate": 2.169266937379782e-06, "loss": 0.273, "step": 4486 }, { "epoch": 2.8692732070040776, "grad_norm": 3.118419647216797, "learning_rate": 2.1585808933532805e-06, "loss": 0.279, "step": 4487 }, { "epoch": 2.8699128488046695, "grad_norm": 3.176316022872925, "learning_rate": 2.1478948493267794e-06, "loss": 0.2782, "step": 4488 }, { "epoch": 2.8705524906052613, "grad_norm": 3.211397886276245, "learning_rate": 2.137208805300278e-06, "loss": 0.2885, "step": 4489 }, { "epoch": 2.8711921324058527, "grad_norm": 3.126208543777466, "learning_rate": 2.1265227612737765e-06, "loss": 0.2837, "step": 4490 }, { "epoch": 2.8718317742064445, "grad_norm": 2.1356916427612305, "learning_rate": 2.1158367172472754e-06, "loss": 0.2516, "step": 4491 }, { "epoch": 2.872471416007036, "grad_norm": 3.3706891536712646, "learning_rate": 2.105150673220774e-06, "loss": 0.3187, "step": 4492 }, { "epoch": 2.8731110578076278, "grad_norm": 3.4606504440307617, "learning_rate": 2.0944646291942724e-06, "loss": 0.2996, "step": 4493 }, { "epoch": 2.8737506996082196, "grad_norm": 3.250021457672119, "learning_rate": 2.083778585167771e-06, "loss": 0.3108, "step": 4494 }, { "epoch": 2.874390341408811, "grad_norm": 2.7848429679870605, "learning_rate": 2.07309254114127e-06, "loss": 0.2632, "step": 4495 }, { "epoch": 2.875029983209403, "grad_norm": 2.243865966796875, "learning_rate": 2.062406497114768e-06, "loss": 0.2432, "step": 4496 }, { "epoch": 2.8756696250099942, "grad_norm": 2.5174126625061035, "learning_rate": 2.051720453088267e-06, "loss": 0.2667, "step": 4497 }, { "epoch": 2.876309266810586, "grad_norm": 3.000579833984375, "learning_rate": 2.0410344090617654e-06, "loss": 0.2652, "step": 4498 }, { "epoch": 2.876948908611178, "grad_norm": 3.139763116836548, "learning_rate": 2.030348365035264e-06, "loss": 0.2981, "step": 4499 }, { "epoch": 2.8775885504117693, "grad_norm": 2.74404239654541, "learning_rate": 2.0196623210087625e-06, "loss": 0.2581, "step": 4500 }, { "epoch": 2.878228192212361, "grad_norm": 2.860971212387085, "learning_rate": 2.0089762769822614e-06, "loss": 0.2817, "step": 4501 }, { "epoch": 2.8788678340129525, "grad_norm": 3.165374994277954, "learning_rate": 1.99829023295576e-06, "loss": 0.2826, "step": 4502 }, { "epoch": 2.8795074758135444, "grad_norm": 2.5561602115631104, "learning_rate": 1.9876041889292584e-06, "loss": 0.2511, "step": 4503 }, { "epoch": 2.880147117614136, "grad_norm": 2.6605477333068848, "learning_rate": 1.976918144902757e-06, "loss": 0.2697, "step": 4504 }, { "epoch": 2.8807867594147276, "grad_norm": 3.8273935317993164, "learning_rate": 1.966232100876256e-06, "loss": 0.3125, "step": 4505 }, { "epoch": 2.8814264012153195, "grad_norm": 3.6742067337036133, "learning_rate": 1.955546056849754e-06, "loss": 0.3285, "step": 4506 }, { "epoch": 2.882066043015911, "grad_norm": 3.0872433185577393, "learning_rate": 1.944860012823253e-06, "loss": 0.2994, "step": 4507 }, { "epoch": 2.8827056848165027, "grad_norm": 2.846733808517456, "learning_rate": 1.9341739687967514e-06, "loss": 0.2831, "step": 4508 }, { "epoch": 2.8833453266170945, "grad_norm": 2.8222081661224365, "learning_rate": 1.9234879247702504e-06, "loss": 0.2686, "step": 4509 }, { "epoch": 2.8839849684176864, "grad_norm": 2.885746717453003, "learning_rate": 1.9128018807437485e-06, "loss": 0.2595, "step": 4510 }, { "epoch": 2.8846246102182778, "grad_norm": 2.5349819660186768, "learning_rate": 1.9021158367172474e-06, "loss": 0.2918, "step": 4511 }, { "epoch": 2.885264252018869, "grad_norm": 3.315539598464966, "learning_rate": 1.8914297926907461e-06, "loss": 0.3017, "step": 4512 }, { "epoch": 2.885903893819461, "grad_norm": 3.2616286277770996, "learning_rate": 1.8807437486642446e-06, "loss": 0.2977, "step": 4513 }, { "epoch": 2.886543535620053, "grad_norm": 3.0158700942993164, "learning_rate": 1.8700577046377434e-06, "loss": 0.2667, "step": 4514 }, { "epoch": 2.8871831774206447, "grad_norm": 2.6524617671966553, "learning_rate": 1.8593716606112417e-06, "loss": 0.2821, "step": 4515 }, { "epoch": 2.887822819221236, "grad_norm": 2.8941731452941895, "learning_rate": 1.8486856165847406e-06, "loss": 0.2974, "step": 4516 }, { "epoch": 2.888462461021828, "grad_norm": 2.765868902206421, "learning_rate": 1.837999572558239e-06, "loss": 0.2752, "step": 4517 }, { "epoch": 2.8891021028224193, "grad_norm": 2.797605514526367, "learning_rate": 1.8273135285317379e-06, "loss": 0.3112, "step": 4518 }, { "epoch": 2.889741744623011, "grad_norm": 2.6544525623321533, "learning_rate": 1.8166274845052362e-06, "loss": 0.2703, "step": 4519 }, { "epoch": 2.890381386423603, "grad_norm": 3.714121103286743, "learning_rate": 1.8059414404787349e-06, "loss": 0.3115, "step": 4520 }, { "epoch": 2.8910210282241944, "grad_norm": 2.5904996395111084, "learning_rate": 1.7952553964522334e-06, "loss": 0.2619, "step": 4521 }, { "epoch": 2.891660670024786, "grad_norm": 3.224226713180542, "learning_rate": 1.7845693524257321e-06, "loss": 0.303, "step": 4522 }, { "epoch": 2.8923003118253776, "grad_norm": 3.2155778408050537, "learning_rate": 1.7738833083992306e-06, "loss": 0.2972, "step": 4523 }, { "epoch": 2.8929399536259695, "grad_norm": 3.257056474685669, "learning_rate": 1.7631972643727294e-06, "loss": 0.3011, "step": 4524 }, { "epoch": 2.8935795954265613, "grad_norm": 3.115983486175537, "learning_rate": 1.7525112203462279e-06, "loss": 0.2917, "step": 4525 }, { "epoch": 2.8942192372271527, "grad_norm": 3.4388442039489746, "learning_rate": 1.7418251763197266e-06, "loss": 0.3171, "step": 4526 }, { "epoch": 2.8948588790277445, "grad_norm": 2.5056612491607666, "learning_rate": 1.731139132293225e-06, "loss": 0.2642, "step": 4527 }, { "epoch": 2.895498520828336, "grad_norm": 3.1889901161193848, "learning_rate": 1.7204530882667239e-06, "loss": 0.3055, "step": 4528 }, { "epoch": 2.8961381626289278, "grad_norm": 3.3815791606903076, "learning_rate": 1.7097670442402222e-06, "loss": 0.2895, "step": 4529 }, { "epoch": 2.8967778044295196, "grad_norm": 3.011918783187866, "learning_rate": 1.699081000213721e-06, "loss": 0.3007, "step": 4530 }, { "epoch": 2.897417446230111, "grad_norm": 2.953803777694702, "learning_rate": 1.6883949561872194e-06, "loss": 0.2794, "step": 4531 }, { "epoch": 2.898057088030703, "grad_norm": 3.4943125247955322, "learning_rate": 1.6777089121607181e-06, "loss": 0.3091, "step": 4532 }, { "epoch": 2.8986967298312942, "grad_norm": 2.9962806701660156, "learning_rate": 1.6670228681342166e-06, "loss": 0.2724, "step": 4533 }, { "epoch": 2.899336371631886, "grad_norm": 2.714372158050537, "learning_rate": 1.6563368241077154e-06, "loss": 0.2733, "step": 4534 }, { "epoch": 2.899976013432478, "grad_norm": 2.6885035037994385, "learning_rate": 1.645650780081214e-06, "loss": 0.2838, "step": 4535 }, { "epoch": 2.9006156552330697, "grad_norm": 2.593261957168579, "learning_rate": 1.6349647360547126e-06, "loss": 0.2649, "step": 4536 }, { "epoch": 2.901255297033661, "grad_norm": 2.710954189300537, "learning_rate": 1.6242786920282113e-06, "loss": 0.2735, "step": 4537 }, { "epoch": 2.901894938834253, "grad_norm": 2.6329758167266846, "learning_rate": 1.6135926480017099e-06, "loss": 0.2472, "step": 4538 }, { "epoch": 2.9025345806348444, "grad_norm": 2.478379964828491, "learning_rate": 1.6029066039752086e-06, "loss": 0.244, "step": 4539 }, { "epoch": 2.903174222435436, "grad_norm": 2.824335813522339, "learning_rate": 1.592220559948707e-06, "loss": 0.2779, "step": 4540 }, { "epoch": 2.903813864236028, "grad_norm": 3.711716651916504, "learning_rate": 1.5815345159222058e-06, "loss": 0.305, "step": 4541 }, { "epoch": 2.9044535060366194, "grad_norm": 3.162688970565796, "learning_rate": 1.5708484718957041e-06, "loss": 0.2961, "step": 4542 }, { "epoch": 2.9050931478372113, "grad_norm": 2.8410279750823975, "learning_rate": 1.5601624278692028e-06, "loss": 0.282, "step": 4543 }, { "epoch": 2.9057327896378027, "grad_norm": 2.512073278427124, "learning_rate": 1.5494763838427014e-06, "loss": 0.2541, "step": 4544 }, { "epoch": 2.9063724314383945, "grad_norm": 3.05137038230896, "learning_rate": 1.5387903398162003e-06, "loss": 0.2748, "step": 4545 }, { "epoch": 2.9070120732389864, "grad_norm": 3.158571481704712, "learning_rate": 1.5281042957896988e-06, "loss": 0.2934, "step": 4546 }, { "epoch": 2.9076517150395778, "grad_norm": 3.0834968090057373, "learning_rate": 1.5174182517631973e-06, "loss": 0.2638, "step": 4547 }, { "epoch": 2.9082913568401696, "grad_norm": 2.686398983001709, "learning_rate": 1.506732207736696e-06, "loss": 0.2628, "step": 4548 }, { "epoch": 2.908930998640761, "grad_norm": 2.960505485534668, "learning_rate": 1.4960461637101946e-06, "loss": 0.2825, "step": 4549 }, { "epoch": 2.909570640441353, "grad_norm": 2.898348569869995, "learning_rate": 1.4853601196836933e-06, "loss": 0.2795, "step": 4550 }, { "epoch": 2.9102102822419447, "grad_norm": 3.2978429794311523, "learning_rate": 1.4746740756571918e-06, "loss": 0.3135, "step": 4551 }, { "epoch": 2.910849924042536, "grad_norm": 2.648906946182251, "learning_rate": 1.4639880316306903e-06, "loss": 0.25, "step": 4552 }, { "epoch": 2.911489565843128, "grad_norm": 2.886461019515991, "learning_rate": 1.453301987604189e-06, "loss": 0.2965, "step": 4553 }, { "epoch": 2.9121292076437193, "grad_norm": 2.8545072078704834, "learning_rate": 1.4426159435776876e-06, "loss": 0.2652, "step": 4554 }, { "epoch": 2.912768849444311, "grad_norm": 3.019754648208618, "learning_rate": 1.4319298995511863e-06, "loss": 0.295, "step": 4555 }, { "epoch": 2.913408491244903, "grad_norm": 3.1926445960998535, "learning_rate": 1.4212438555246848e-06, "loss": 0.2914, "step": 4556 }, { "epoch": 2.9140481330454944, "grad_norm": 3.1505846977233887, "learning_rate": 1.4105578114981833e-06, "loss": 0.2963, "step": 4557 }, { "epoch": 2.914687774846086, "grad_norm": 3.0904791355133057, "learning_rate": 1.399871767471682e-06, "loss": 0.2917, "step": 4558 }, { "epoch": 2.9153274166466776, "grad_norm": 2.906182050704956, "learning_rate": 1.3891857234451806e-06, "loss": 0.2804, "step": 4559 }, { "epoch": 2.9159670584472694, "grad_norm": 3.5451202392578125, "learning_rate": 1.3784996794186793e-06, "loss": 0.3088, "step": 4560 }, { "epoch": 2.9166067002478613, "grad_norm": 3.023319959640503, "learning_rate": 1.3678136353921778e-06, "loss": 0.2729, "step": 4561 }, { "epoch": 2.917246342048453, "grad_norm": 2.8218863010406494, "learning_rate": 1.3571275913656765e-06, "loss": 0.2796, "step": 4562 }, { "epoch": 2.9178859838490445, "grad_norm": 2.7403781414031982, "learning_rate": 1.346441547339175e-06, "loss": 0.2801, "step": 4563 }, { "epoch": 2.9185256256496364, "grad_norm": 2.7108497619628906, "learning_rate": 1.3357555033126736e-06, "loss": 0.2733, "step": 4564 }, { "epoch": 2.9191652674502278, "grad_norm": 3.103050708770752, "learning_rate": 1.3250694592861723e-06, "loss": 0.284, "step": 4565 }, { "epoch": 2.9198049092508196, "grad_norm": 2.8473711013793945, "learning_rate": 1.3143834152596708e-06, "loss": 0.2772, "step": 4566 }, { "epoch": 2.9204445510514114, "grad_norm": 3.30690860748291, "learning_rate": 1.3036973712331695e-06, "loss": 0.2965, "step": 4567 }, { "epoch": 2.921084192852003, "grad_norm": 2.8652989864349365, "learning_rate": 1.2930113272066683e-06, "loss": 0.2906, "step": 4568 }, { "epoch": 2.9217238346525947, "grad_norm": 2.619109869003296, "learning_rate": 1.2823252831801668e-06, "loss": 0.2501, "step": 4569 }, { "epoch": 2.922363476453186, "grad_norm": 2.9598729610443115, "learning_rate": 1.2716392391536655e-06, "loss": 0.3186, "step": 4570 }, { "epoch": 2.923003118253778, "grad_norm": 2.9078493118286133, "learning_rate": 1.260953195127164e-06, "loss": 0.2738, "step": 4571 }, { "epoch": 2.9236427600543697, "grad_norm": 2.7794830799102783, "learning_rate": 1.2502671511006627e-06, "loss": 0.2777, "step": 4572 }, { "epoch": 2.924282401854961, "grad_norm": 2.8971762657165527, "learning_rate": 1.2395811070741613e-06, "loss": 0.2937, "step": 4573 }, { "epoch": 2.924922043655553, "grad_norm": 2.7297163009643555, "learning_rate": 1.2288950630476598e-06, "loss": 0.2604, "step": 4574 }, { "epoch": 2.9255616854561444, "grad_norm": 2.7503600120544434, "learning_rate": 1.2182090190211585e-06, "loss": 0.2768, "step": 4575 }, { "epoch": 2.926201327256736, "grad_norm": 2.616666078567505, "learning_rate": 1.207522974994657e-06, "loss": 0.2734, "step": 4576 }, { "epoch": 2.926840969057328, "grad_norm": 3.06693434715271, "learning_rate": 1.1968369309681557e-06, "loss": 0.2854, "step": 4577 }, { "epoch": 2.9274806108579194, "grad_norm": 3.1562938690185547, "learning_rate": 1.1861508869416543e-06, "loss": 0.275, "step": 4578 }, { "epoch": 2.9281202526585113, "grad_norm": 2.811310052871704, "learning_rate": 1.1754648429151528e-06, "loss": 0.2588, "step": 4579 }, { "epoch": 2.9287598944591027, "grad_norm": 3.0411245822906494, "learning_rate": 1.1647787988886515e-06, "loss": 0.2912, "step": 4580 }, { "epoch": 2.9293995362596945, "grad_norm": 2.5922415256500244, "learning_rate": 1.15409275486215e-06, "loss": 0.2643, "step": 4581 }, { "epoch": 2.9300391780602864, "grad_norm": 2.923546075820923, "learning_rate": 1.1434067108356487e-06, "loss": 0.2655, "step": 4582 }, { "epoch": 2.9306788198608777, "grad_norm": 3.06540584564209, "learning_rate": 1.1327206668091473e-06, "loss": 0.2842, "step": 4583 }, { "epoch": 2.9313184616614696, "grad_norm": 2.955547571182251, "learning_rate": 1.1220346227826458e-06, "loss": 0.3139, "step": 4584 }, { "epoch": 2.931958103462061, "grad_norm": 3.281717300415039, "learning_rate": 1.1113485787561445e-06, "loss": 0.316, "step": 4585 }, { "epoch": 2.932597745262653, "grad_norm": 2.9767303466796875, "learning_rate": 1.100662534729643e-06, "loss": 0.2929, "step": 4586 }, { "epoch": 2.9332373870632447, "grad_norm": 3.0934088230133057, "learning_rate": 1.0899764907031417e-06, "loss": 0.2836, "step": 4587 }, { "epoch": 2.9338770288638365, "grad_norm": 2.8757448196411133, "learning_rate": 1.0792904466766403e-06, "loss": 0.2863, "step": 4588 }, { "epoch": 2.934516670664428, "grad_norm": 2.8582520484924316, "learning_rate": 1.068604402650139e-06, "loss": 0.2793, "step": 4589 }, { "epoch": 2.9351563124650197, "grad_norm": 2.8924968242645264, "learning_rate": 1.0579183586236377e-06, "loss": 0.2853, "step": 4590 }, { "epoch": 2.935795954265611, "grad_norm": 2.6857917308807373, "learning_rate": 1.0472323145971362e-06, "loss": 0.2709, "step": 4591 }, { "epoch": 2.936435596066203, "grad_norm": 2.851781129837036, "learning_rate": 1.036546270570635e-06, "loss": 0.2837, "step": 4592 }, { "epoch": 2.937075237866795, "grad_norm": 2.95515775680542, "learning_rate": 1.0258602265441335e-06, "loss": 0.3108, "step": 4593 }, { "epoch": 2.937714879667386, "grad_norm": 3.1146178245544434, "learning_rate": 1.015174182517632e-06, "loss": 0.2955, "step": 4594 }, { "epoch": 2.938354521467978, "grad_norm": 2.9489970207214355, "learning_rate": 1.0044881384911307e-06, "loss": 0.3026, "step": 4595 }, { "epoch": 2.9389941632685694, "grad_norm": 3.0633018016815186, "learning_rate": 9.938020944646292e-07, "loss": 0.2744, "step": 4596 }, { "epoch": 2.9396338050691613, "grad_norm": 3.242702007293701, "learning_rate": 9.83116050438128e-07, "loss": 0.3041, "step": 4597 }, { "epoch": 2.940273446869753, "grad_norm": 3.3694849014282227, "learning_rate": 9.724300064116265e-07, "loss": 0.3213, "step": 4598 }, { "epoch": 2.9409130886703445, "grad_norm": 3.079346179962158, "learning_rate": 9.617439623851252e-07, "loss": 0.3116, "step": 4599 }, { "epoch": 2.9415527304709363, "grad_norm": 2.477478504180908, "learning_rate": 9.510579183586237e-07, "loss": 0.2413, "step": 4600 }, { "epoch": 2.9421923722715277, "grad_norm": 3.136911153793335, "learning_rate": 9.403718743321223e-07, "loss": 0.2701, "step": 4601 }, { "epoch": 2.9428320140721196, "grad_norm": 3.002061605453491, "learning_rate": 9.296858303056208e-07, "loss": 0.2876, "step": 4602 }, { "epoch": 2.9434716558727114, "grad_norm": 2.8170931339263916, "learning_rate": 9.189997862791195e-07, "loss": 0.2912, "step": 4603 }, { "epoch": 2.944111297673303, "grad_norm": 2.8673248291015625, "learning_rate": 9.083137422526181e-07, "loss": 0.28, "step": 4604 }, { "epoch": 2.9447509394738947, "grad_norm": 3.366997241973877, "learning_rate": 8.976276982261167e-07, "loss": 0.2881, "step": 4605 }, { "epoch": 2.945390581274486, "grad_norm": 2.804033041000366, "learning_rate": 8.869416541996153e-07, "loss": 0.2745, "step": 4606 }, { "epoch": 2.946030223075078, "grad_norm": 3.1108407974243164, "learning_rate": 8.762556101731139e-07, "loss": 0.286, "step": 4607 }, { "epoch": 2.9466698648756697, "grad_norm": 3.3729159832000732, "learning_rate": 8.655695661466125e-07, "loss": 0.2911, "step": 4608 }, { "epoch": 2.9473095066762616, "grad_norm": 3.1210105419158936, "learning_rate": 8.548835221201111e-07, "loss": 0.2777, "step": 4609 }, { "epoch": 2.947949148476853, "grad_norm": 3.2672693729400635, "learning_rate": 8.441974780936097e-07, "loss": 0.2989, "step": 4610 }, { "epoch": 2.9485887902774444, "grad_norm": 3.032050132751465, "learning_rate": 8.335114340671083e-07, "loss": 0.262, "step": 4611 }, { "epoch": 2.949228432078036, "grad_norm": 3.284799814224243, "learning_rate": 8.22825390040607e-07, "loss": 0.2883, "step": 4612 }, { "epoch": 2.949868073878628, "grad_norm": 2.4401063919067383, "learning_rate": 8.121393460141057e-07, "loss": 0.2458, "step": 4613 }, { "epoch": 2.95050771567922, "grad_norm": 3.0984020233154297, "learning_rate": 8.014533019876043e-07, "loss": 0.274, "step": 4614 }, { "epoch": 2.9511473574798113, "grad_norm": 2.945162534713745, "learning_rate": 7.907672579611029e-07, "loss": 0.2926, "step": 4615 }, { "epoch": 2.951786999280403, "grad_norm": 2.8837413787841797, "learning_rate": 7.800812139346014e-07, "loss": 0.2818, "step": 4616 }, { "epoch": 2.9524266410809945, "grad_norm": 2.7469866275787354, "learning_rate": 7.693951699081002e-07, "loss": 0.2657, "step": 4617 }, { "epoch": 2.9530662828815863, "grad_norm": 2.9806694984436035, "learning_rate": 7.587091258815987e-07, "loss": 0.2623, "step": 4618 }, { "epoch": 2.953705924682178, "grad_norm": 3.107755422592163, "learning_rate": 7.480230818550973e-07, "loss": 0.2943, "step": 4619 }, { "epoch": 2.9543455664827696, "grad_norm": 3.3334574699401855, "learning_rate": 7.373370378285959e-07, "loss": 0.3062, "step": 4620 }, { "epoch": 2.9549852082833614, "grad_norm": 2.7644970417022705, "learning_rate": 7.266509938020945e-07, "loss": 0.2529, "step": 4621 }, { "epoch": 2.955624850083953, "grad_norm": 3.0519533157348633, "learning_rate": 7.159649497755931e-07, "loss": 0.2793, "step": 4622 }, { "epoch": 2.9562644918845447, "grad_norm": 2.708420991897583, "learning_rate": 7.052789057490917e-07, "loss": 0.2743, "step": 4623 }, { "epoch": 2.9569041336851365, "grad_norm": 2.8920557498931885, "learning_rate": 6.945928617225903e-07, "loss": 0.2816, "step": 4624 }, { "epoch": 2.957543775485728, "grad_norm": 3.275573253631592, "learning_rate": 6.839068176960889e-07, "loss": 0.3154, "step": 4625 }, { "epoch": 2.9581834172863197, "grad_norm": 2.6203067302703857, "learning_rate": 6.732207736695875e-07, "loss": 0.2602, "step": 4626 }, { "epoch": 2.958823059086911, "grad_norm": 2.8467485904693604, "learning_rate": 6.625347296430861e-07, "loss": 0.2629, "step": 4627 }, { "epoch": 2.959462700887503, "grad_norm": 2.786341905593872, "learning_rate": 6.518486856165848e-07, "loss": 0.2406, "step": 4628 }, { "epoch": 2.960102342688095, "grad_norm": 3.226491928100586, "learning_rate": 6.411626415900834e-07, "loss": 0.2766, "step": 4629 }, { "epoch": 2.960741984488686, "grad_norm": 3.217517137527466, "learning_rate": 6.30476597563582e-07, "loss": 0.3048, "step": 4630 }, { "epoch": 2.961381626289278, "grad_norm": 2.7901575565338135, "learning_rate": 6.197905535370806e-07, "loss": 0.2738, "step": 4631 }, { "epoch": 2.9620212680898694, "grad_norm": 2.7078211307525635, "learning_rate": 6.091045095105793e-07, "loss": 0.2655, "step": 4632 }, { "epoch": 2.9626609098904613, "grad_norm": 3.1929845809936523, "learning_rate": 5.984184654840779e-07, "loss": 0.2868, "step": 4633 }, { "epoch": 2.963300551691053, "grad_norm": 2.801015615463257, "learning_rate": 5.877324214575764e-07, "loss": 0.2869, "step": 4634 }, { "epoch": 2.963940193491645, "grad_norm": 3.106300115585327, "learning_rate": 5.77046377431075e-07, "loss": 0.2797, "step": 4635 }, { "epoch": 2.9645798352922363, "grad_norm": 2.3474364280700684, "learning_rate": 5.663603334045736e-07, "loss": 0.2464, "step": 4636 }, { "epoch": 2.965219477092828, "grad_norm": 3.233705759048462, "learning_rate": 5.556742893780722e-07, "loss": 0.2834, "step": 4637 }, { "epoch": 2.9658591188934196, "grad_norm": 2.533975601196289, "learning_rate": 5.449882453515709e-07, "loss": 0.2609, "step": 4638 }, { "epoch": 2.9664987606940114, "grad_norm": 3.2399234771728516, "learning_rate": 5.343022013250695e-07, "loss": 0.311, "step": 4639 }, { "epoch": 2.9671384024946033, "grad_norm": 3.1690189838409424, "learning_rate": 5.236161572985681e-07, "loss": 0.2663, "step": 4640 }, { "epoch": 2.9677780442951947, "grad_norm": 2.751340389251709, "learning_rate": 5.129301132720667e-07, "loss": 0.2567, "step": 4641 }, { "epoch": 2.9684176860957865, "grad_norm": 3.2145743370056152, "learning_rate": 5.022440692455654e-07, "loss": 0.2953, "step": 4642 }, { "epoch": 2.969057327896378, "grad_norm": 3.530580759048462, "learning_rate": 4.91558025219064e-07, "loss": 0.3116, "step": 4643 }, { "epoch": 2.9696969696969697, "grad_norm": 2.7425405979156494, "learning_rate": 4.808719811925626e-07, "loss": 0.2679, "step": 4644 }, { "epoch": 2.9703366114975616, "grad_norm": 2.740150213241577, "learning_rate": 4.7018593716606116e-07, "loss": 0.2739, "step": 4645 }, { "epoch": 2.970976253298153, "grad_norm": 3.510528087615967, "learning_rate": 4.5949989313955973e-07, "loss": 0.3106, "step": 4646 }, { "epoch": 2.971615895098745, "grad_norm": 3.5076143741607666, "learning_rate": 4.4881384911305835e-07, "loss": 0.2982, "step": 4647 }, { "epoch": 2.972255536899336, "grad_norm": 2.959351062774658, "learning_rate": 4.3812780508655697e-07, "loss": 0.2874, "step": 4648 }, { "epoch": 2.972895178699928, "grad_norm": 2.9966440200805664, "learning_rate": 4.2744176106005554e-07, "loss": 0.2705, "step": 4649 }, { "epoch": 2.97353482050052, "grad_norm": 2.4923782348632812, "learning_rate": 4.1675571703355416e-07, "loss": 0.2624, "step": 4650 }, { "epoch": 2.9741744623011113, "grad_norm": 3.163743019104004, "learning_rate": 4.0606967300705283e-07, "loss": 0.2943, "step": 4651 }, { "epoch": 2.974814104101703, "grad_norm": 3.299694061279297, "learning_rate": 3.9538362898055145e-07, "loss": 0.3077, "step": 4652 }, { "epoch": 2.9754537459022945, "grad_norm": 3.307133674621582, "learning_rate": 3.846975849540501e-07, "loss": 0.307, "step": 4653 }, { "epoch": 2.9760933877028863, "grad_norm": 3.399186611175537, "learning_rate": 3.7401154092754864e-07, "loss": 0.3026, "step": 4654 }, { "epoch": 2.976733029503478, "grad_norm": 3.3977606296539307, "learning_rate": 3.6332549690104726e-07, "loss": 0.3022, "step": 4655 }, { "epoch": 2.9773726713040696, "grad_norm": 3.213376998901367, "learning_rate": 3.5263945287454583e-07, "loss": 0.2829, "step": 4656 }, { "epoch": 2.9780123131046614, "grad_norm": 3.924910545349121, "learning_rate": 3.4195340884804445e-07, "loss": 0.2802, "step": 4657 }, { "epoch": 2.978651954905253, "grad_norm": 2.69236421585083, "learning_rate": 3.3126736482154307e-07, "loss": 0.245, "step": 4658 }, { "epoch": 2.9792915967058446, "grad_norm": 2.9249889850616455, "learning_rate": 3.205813207950417e-07, "loss": 0.2761, "step": 4659 }, { "epoch": 2.9799312385064365, "grad_norm": 3.207481861114502, "learning_rate": 3.098952767685403e-07, "loss": 0.292, "step": 4660 }, { "epoch": 2.9805708803070283, "grad_norm": 3.408125400543213, "learning_rate": 2.9920923274203894e-07, "loss": 0.3128, "step": 4661 }, { "epoch": 2.9812105221076197, "grad_norm": 3.132514238357544, "learning_rate": 2.885231887155375e-07, "loss": 0.2999, "step": 4662 }, { "epoch": 2.9818501639082116, "grad_norm": 3.2416889667510986, "learning_rate": 2.778371446890361e-07, "loss": 0.2716, "step": 4663 }, { "epoch": 2.982489805708803, "grad_norm": 3.1789774894714355, "learning_rate": 2.6715110066253475e-07, "loss": 0.2896, "step": 4664 }, { "epoch": 2.983129447509395, "grad_norm": 3.2657458782196045, "learning_rate": 2.5646505663603337e-07, "loss": 0.3093, "step": 4665 }, { "epoch": 2.9837690893099866, "grad_norm": 2.9810163974761963, "learning_rate": 2.45779012609532e-07, "loss": 0.2547, "step": 4666 }, { "epoch": 2.984408731110578, "grad_norm": 2.948413133621216, "learning_rate": 2.3509296858303058e-07, "loss": 0.2837, "step": 4667 }, { "epoch": 2.98504837291117, "grad_norm": 2.8497731685638428, "learning_rate": 2.2440692455652918e-07, "loss": 0.2936, "step": 4668 }, { "epoch": 2.9856880147117613, "grad_norm": 2.8002233505249023, "learning_rate": 2.1372088053002777e-07, "loss": 0.278, "step": 4669 }, { "epoch": 2.986327656512353, "grad_norm": 3.0508875846862793, "learning_rate": 2.0303483650352642e-07, "loss": 0.2853, "step": 4670 }, { "epoch": 2.986967298312945, "grad_norm": 2.9186458587646484, "learning_rate": 1.9234879247702504e-07, "loss": 0.2628, "step": 4671 }, { "epoch": 2.9876069401135363, "grad_norm": 3.23622989654541, "learning_rate": 1.8166274845052363e-07, "loss": 0.2986, "step": 4672 }, { "epoch": 2.988246581914128, "grad_norm": 2.586787462234497, "learning_rate": 1.7097670442402223e-07, "loss": 0.2546, "step": 4673 }, { "epoch": 2.9888862237147196, "grad_norm": 2.9180619716644287, "learning_rate": 1.6029066039752085e-07, "loss": 0.2896, "step": 4674 }, { "epoch": 2.9895258655153114, "grad_norm": 3.361057758331299, "learning_rate": 1.4960461637101947e-07, "loss": 0.2963, "step": 4675 }, { "epoch": 2.9901655073159032, "grad_norm": 2.8037657737731934, "learning_rate": 1.3891857234451806e-07, "loss": 0.2759, "step": 4676 }, { "epoch": 2.9908051491164946, "grad_norm": 3.336202383041382, "learning_rate": 1.2823252831801668e-07, "loss": 0.3032, "step": 4677 }, { "epoch": 2.9914447909170865, "grad_norm": 3.1167173385620117, "learning_rate": 1.1754648429151529e-07, "loss": 0.2851, "step": 4678 }, { "epoch": 2.992084432717678, "grad_norm": 3.106213331222534, "learning_rate": 1.0686044026501388e-07, "loss": 0.281, "step": 4679 }, { "epoch": 2.9927240745182697, "grad_norm": 3.0309648513793945, "learning_rate": 9.617439623851252e-08, "loss": 0.2963, "step": 4680 }, { "epoch": 2.9933637163188616, "grad_norm": 3.160137414932251, "learning_rate": 8.548835221201111e-08, "loss": 0.3064, "step": 4681 }, { "epoch": 2.994003358119453, "grad_norm": 2.576639175415039, "learning_rate": 7.480230818550973e-08, "loss": 0.2664, "step": 4682 }, { "epoch": 2.994642999920045, "grad_norm": 2.7932701110839844, "learning_rate": 6.411626415900834e-08, "loss": 0.2658, "step": 4683 }, { "epoch": 2.995282641720636, "grad_norm": 3.1135575771331787, "learning_rate": 5.343022013250694e-08, "loss": 0.2885, "step": 4684 }, { "epoch": 2.995922283521228, "grad_norm": 2.361483097076416, "learning_rate": 4.2744176106005557e-08, "loss": 0.2544, "step": 4685 }, { "epoch": 2.99656192532182, "grad_norm": 3.1596367359161377, "learning_rate": 3.205813207950417e-08, "loss": 0.2872, "step": 4686 }, { "epoch": 2.9972015671224117, "grad_norm": 3.0970194339752197, "learning_rate": 2.1372088053002778e-08, "loss": 0.2975, "step": 4687 }, { "epoch": 2.997841208923003, "grad_norm": 2.7904469966888428, "learning_rate": 1.0686044026501389e-08, "loss": 0.279, "step": 4688 }, { "epoch": 2.998480850723595, "grad_norm": 3.129556655883789, "learning_rate": 0.0, "loss": 0.3075, "step": 4689 } ], "logging_steps": 1, "max_steps": 4689, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 10000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.0989668175037286e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }