{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 11721, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.000256, "grad_norm": 13.9375, "learning_rate": 5e-05, "loss": 5.0668, "step": 1 }, { "epoch": 0.000512, "grad_norm": 4.34375, "learning_rate": 4.999573415237608e-05, "loss": 3.8496, "step": 2 }, { "epoch": 0.000768, "grad_norm": 3.1875, "learning_rate": 4.999146830475216e-05, "loss": 3.6141, "step": 3 }, { "epoch": 0.001024, "grad_norm": 2.6875, "learning_rate": 4.998720245712823e-05, "loss": 3.3289, "step": 4 }, { "epoch": 0.00128, "grad_norm": 2.765625, "learning_rate": 4.998293660950431e-05, "loss": 3.3289, "step": 5 }, { "epoch": 0.001536, "grad_norm": 2.390625, "learning_rate": 4.997867076188039e-05, "loss": 3.2139, "step": 6 }, { "epoch": 0.001792, "grad_norm": 1.984375, "learning_rate": 4.997440491425647e-05, "loss": 3.1277, "step": 7 }, { "epoch": 0.002048, "grad_norm": 1.4765625, "learning_rate": 4.997013906663254e-05, "loss": 2.9207, "step": 8 }, { "epoch": 0.002304, "grad_norm": 1.46875, "learning_rate": 4.996587321900862e-05, "loss": 2.853, "step": 9 }, { "epoch": 0.00256, "grad_norm": 1.3359375, "learning_rate": 4.996160737138469e-05, "loss": 2.8234, "step": 10 }, { "epoch": 0.002816, "grad_norm": 1.2265625, "learning_rate": 4.995734152376078e-05, "loss": 2.8791, "step": 11 }, { "epoch": 0.003072, "grad_norm": 1.0859375, "learning_rate": 4.995307567613685e-05, "loss": 2.8151, "step": 12 }, { "epoch": 0.003328, "grad_norm": 1.078125, "learning_rate": 4.994880982851293e-05, "loss": 2.8136, "step": 13 }, { "epoch": 0.003584, "grad_norm": 1.0078125, "learning_rate": 4.9944543980889e-05, "loss": 2.733, "step": 14 }, { "epoch": 0.00384, "grad_norm": 0.984375, "learning_rate": 4.994027813326508e-05, "loss": 2.7711, "step": 15 }, { "epoch": 0.004096, "grad_norm": 0.9296875, "learning_rate": 4.993601228564116e-05, "loss": 2.6806, "step": 16 }, { "epoch": 0.004352, "grad_norm": 0.90625, "learning_rate": 4.993174643801724e-05, "loss": 2.6814, "step": 17 }, { "epoch": 0.004608, "grad_norm": 0.94140625, "learning_rate": 4.992748059039332e-05, "loss": 2.7762, "step": 18 }, { "epoch": 0.004864, "grad_norm": 0.90625, "learning_rate": 4.9923214742769393e-05, "loss": 2.7266, "step": 19 }, { "epoch": 0.00512, "grad_norm": 0.9296875, "learning_rate": 4.991894889514547e-05, "loss": 2.6561, "step": 20 }, { "epoch": 0.005376, "grad_norm": 0.86328125, "learning_rate": 4.991468304752154e-05, "loss": 2.655, "step": 21 }, { "epoch": 0.005632, "grad_norm": 0.921875, "learning_rate": 4.991041719989762e-05, "loss": 2.6547, "step": 22 }, { "epoch": 0.005888, "grad_norm": 0.8203125, "learning_rate": 4.99061513522737e-05, "loss": 2.5858, "step": 23 }, { "epoch": 0.006144, "grad_norm": 1.0546875, "learning_rate": 4.990188550464978e-05, "loss": 2.6207, "step": 24 }, { "epoch": 0.0064, "grad_norm": 1.0078125, "learning_rate": 4.989761965702585e-05, "loss": 2.6117, "step": 25 }, { "epoch": 0.006656, "grad_norm": 0.8203125, "learning_rate": 4.9893353809401934e-05, "loss": 2.5768, "step": 26 }, { "epoch": 0.006912, "grad_norm": 0.93359375, "learning_rate": 4.988908796177801e-05, "loss": 2.5712, "step": 27 }, { "epoch": 0.007168, "grad_norm": 0.96484375, "learning_rate": 4.988482211415408e-05, "loss": 2.6222, "step": 28 }, { "epoch": 0.007424, "grad_norm": 0.9140625, "learning_rate": 4.9880556266530156e-05, "loss": 2.6012, "step": 29 }, { "epoch": 0.00768, "grad_norm": 0.90234375, "learning_rate": 4.987629041890624e-05, "loss": 2.5622, "step": 30 }, { "epoch": 0.007936, "grad_norm": 0.8671875, "learning_rate": 4.987202457128232e-05, "loss": 2.5489, "step": 31 }, { "epoch": 0.008192, "grad_norm": 0.86328125, "learning_rate": 4.986775872365839e-05, "loss": 2.5326, "step": 32 }, { "epoch": 0.008448, "grad_norm": 0.890625, "learning_rate": 4.986349287603447e-05, "loss": 2.4663, "step": 33 }, { "epoch": 0.008704, "grad_norm": 0.7890625, "learning_rate": 4.985922702841055e-05, "loss": 2.4393, "step": 34 }, { "epoch": 0.00896, "grad_norm": 0.890625, "learning_rate": 4.985496118078662e-05, "loss": 2.5233, "step": 35 }, { "epoch": 0.009216, "grad_norm": 0.86328125, "learning_rate": 4.98506953331627e-05, "loss": 2.5162, "step": 36 }, { "epoch": 0.009472, "grad_norm": 0.85546875, "learning_rate": 4.9846429485538784e-05, "loss": 2.4974, "step": 37 }, { "epoch": 0.009728, "grad_norm": 0.85546875, "learning_rate": 4.984216363791486e-05, "loss": 2.452, "step": 38 }, { "epoch": 0.009984, "grad_norm": 0.9296875, "learning_rate": 4.983789779029093e-05, "loss": 2.5105, "step": 39 }, { "epoch": 0.01024, "grad_norm": 0.87109375, "learning_rate": 4.983363194266701e-05, "loss": 2.4345, "step": 40 }, { "epoch": 0.010496, "grad_norm": 0.8828125, "learning_rate": 4.982936609504309e-05, "loss": 2.3587, "step": 41 }, { "epoch": 0.010752, "grad_norm": 0.91796875, "learning_rate": 4.982510024741916e-05, "loss": 2.5015, "step": 42 }, { "epoch": 0.011008, "grad_norm": 0.8984375, "learning_rate": 4.9820834399795244e-05, "loss": 2.4501, "step": 43 }, { "epoch": 0.011264, "grad_norm": 0.9296875, "learning_rate": 4.981656855217132e-05, "loss": 2.4863, "step": 44 }, { "epoch": 0.01152, "grad_norm": 0.91015625, "learning_rate": 4.98123027045474e-05, "loss": 2.4312, "step": 45 }, { "epoch": 0.011776, "grad_norm": 0.9296875, "learning_rate": 4.980803685692347e-05, "loss": 2.4501, "step": 46 }, { "epoch": 0.012032, "grad_norm": 0.94921875, "learning_rate": 4.980377100929955e-05, "loss": 2.4296, "step": 47 }, { "epoch": 0.012288, "grad_norm": 0.9140625, "learning_rate": 4.979950516167562e-05, "loss": 2.3717, "step": 48 }, { "epoch": 0.012544, "grad_norm": 1.015625, "learning_rate": 4.97952393140517e-05, "loss": 2.4149, "step": 49 }, { "epoch": 0.0128, "grad_norm": 0.94921875, "learning_rate": 4.9790973466427784e-05, "loss": 2.4097, "step": 50 }, { "epoch": 0.013056, "grad_norm": 0.95703125, "learning_rate": 4.978670761880386e-05, "loss": 2.4458, "step": 51 }, { "epoch": 0.013312, "grad_norm": 0.99609375, "learning_rate": 4.978244177117994e-05, "loss": 2.3199, "step": 52 }, { "epoch": 0.013568, "grad_norm": 1.0234375, "learning_rate": 4.977817592355601e-05, "loss": 2.3236, "step": 53 }, { "epoch": 0.013824, "grad_norm": 0.9375, "learning_rate": 4.977391007593209e-05, "loss": 2.2662, "step": 54 }, { "epoch": 0.01408, "grad_norm": 1.015625, "learning_rate": 4.976964422830817e-05, "loss": 2.3522, "step": 55 }, { "epoch": 0.014336, "grad_norm": 0.98828125, "learning_rate": 4.976537838068425e-05, "loss": 2.2466, "step": 56 }, { "epoch": 0.014592, "grad_norm": 1.1171875, "learning_rate": 4.9761112533060324e-05, "loss": 2.3267, "step": 57 }, { "epoch": 0.014848, "grad_norm": 1.25, "learning_rate": 4.97568466854364e-05, "loss": 2.2987, "step": 58 }, { "epoch": 0.015104, "grad_norm": 1.140625, "learning_rate": 4.975258083781247e-05, "loss": 2.2966, "step": 59 }, { "epoch": 0.01536, "grad_norm": 1.3828125, "learning_rate": 4.9748314990188554e-05, "loss": 2.3059, "step": 60 }, { "epoch": 0.015616, "grad_norm": 1.328125, "learning_rate": 4.974404914256463e-05, "loss": 2.2253, "step": 61 }, { "epoch": 0.015872, "grad_norm": 1.2109375, "learning_rate": 4.973978329494071e-05, "loss": 2.2493, "step": 62 }, { "epoch": 0.016128, "grad_norm": 1.21875, "learning_rate": 4.973551744731678e-05, "loss": 2.2106, "step": 63 }, { "epoch": 0.016384, "grad_norm": 1.2734375, "learning_rate": 4.9731251599692864e-05, "loss": 2.243, "step": 64 }, { "epoch": 0.01664, "grad_norm": 1.1328125, "learning_rate": 4.972698575206894e-05, "loss": 2.1977, "step": 65 }, { "epoch": 0.016896, "grad_norm": 1.2421875, "learning_rate": 4.972271990444501e-05, "loss": 2.2525, "step": 66 }, { "epoch": 0.017152, "grad_norm": 1.28125, "learning_rate": 4.9718454056821094e-05, "loss": 2.1998, "step": 67 }, { "epoch": 0.017408, "grad_norm": 1.375, "learning_rate": 4.971418820919717e-05, "loss": 2.2602, "step": 68 }, { "epoch": 0.017664, "grad_norm": 1.296875, "learning_rate": 4.970992236157325e-05, "loss": 2.1674, "step": 69 }, { "epoch": 0.01792, "grad_norm": 1.4765625, "learning_rate": 4.970565651394932e-05, "loss": 2.1507, "step": 70 }, { "epoch": 0.018176, "grad_norm": 1.09375, "learning_rate": 4.9701390666325404e-05, "loss": 2.1094, "step": 71 }, { "epoch": 0.018432, "grad_norm": 1.53125, "learning_rate": 4.969712481870148e-05, "loss": 2.1872, "step": 72 }, { "epoch": 0.018688, "grad_norm": 1.3125, "learning_rate": 4.969285897107755e-05, "loss": 2.1455, "step": 73 }, { "epoch": 0.018944, "grad_norm": 1.375, "learning_rate": 4.9688593123453634e-05, "loss": 2.1714, "step": 74 }, { "epoch": 0.0192, "grad_norm": 1.4296875, "learning_rate": 4.9684327275829715e-05, "loss": 2.1809, "step": 75 }, { "epoch": 0.019456, "grad_norm": 1.3125, "learning_rate": 4.968006142820579e-05, "loss": 2.0828, "step": 76 }, { "epoch": 0.019712, "grad_norm": 1.4375, "learning_rate": 4.9675795580581863e-05, "loss": 2.1553, "step": 77 }, { "epoch": 0.019968, "grad_norm": 1.3984375, "learning_rate": 4.967152973295794e-05, "loss": 2.0594, "step": 78 }, { "epoch": 0.020224, "grad_norm": 1.4375, "learning_rate": 4.966726388533402e-05, "loss": 2.105, "step": 79 }, { "epoch": 0.02048, "grad_norm": 1.3671875, "learning_rate": 4.966299803771009e-05, "loss": 2.0872, "step": 80 }, { "epoch": 0.020736, "grad_norm": 1.6953125, "learning_rate": 4.9658732190086174e-05, "loss": 2.0694, "step": 81 }, { "epoch": 0.020992, "grad_norm": 1.546875, "learning_rate": 4.965446634246225e-05, "loss": 2.0909, "step": 82 }, { "epoch": 0.021248, "grad_norm": 1.4765625, "learning_rate": 4.965020049483833e-05, "loss": 2.1063, "step": 83 }, { "epoch": 0.021504, "grad_norm": 1.5546875, "learning_rate": 4.9645934647214404e-05, "loss": 2.0504, "step": 84 }, { "epoch": 0.02176, "grad_norm": 1.484375, "learning_rate": 4.964166879959048e-05, "loss": 2.122, "step": 85 }, { "epoch": 0.022016, "grad_norm": 1.5546875, "learning_rate": 4.963740295196656e-05, "loss": 2.0383, "step": 86 }, { "epoch": 0.022272, "grad_norm": 1.65625, "learning_rate": 4.963313710434263e-05, "loss": 2.0272, "step": 87 }, { "epoch": 0.022528, "grad_norm": 1.6015625, "learning_rate": 4.9628871256718714e-05, "loss": 2.0743, "step": 88 }, { "epoch": 0.022784, "grad_norm": 1.578125, "learning_rate": 4.962460540909479e-05, "loss": 2.0283, "step": 89 }, { "epoch": 0.02304, "grad_norm": 1.4375, "learning_rate": 4.962033956147087e-05, "loss": 2.0151, "step": 90 }, { "epoch": 0.023296, "grad_norm": 1.734375, "learning_rate": 4.9616073713846944e-05, "loss": 2.0023, "step": 91 }, { "epoch": 0.023552, "grad_norm": 1.5390625, "learning_rate": 4.961180786622302e-05, "loss": 1.9912, "step": 92 }, { "epoch": 0.023808, "grad_norm": 1.625, "learning_rate": 4.960754201859909e-05, "loss": 1.9845, "step": 93 }, { "epoch": 0.024064, "grad_norm": 1.59375, "learning_rate": 4.960327617097518e-05, "loss": 2.0745, "step": 94 }, { "epoch": 0.02432, "grad_norm": 1.5546875, "learning_rate": 4.9599010323351254e-05, "loss": 1.9677, "step": 95 }, { "epoch": 0.024576, "grad_norm": 1.6171875, "learning_rate": 4.959474447572733e-05, "loss": 2.0309, "step": 96 }, { "epoch": 0.024832, "grad_norm": 1.546875, "learning_rate": 4.95904786281034e-05, "loss": 1.9489, "step": 97 }, { "epoch": 0.025088, "grad_norm": 1.6328125, "learning_rate": 4.9586212780479484e-05, "loss": 2.0103, "step": 98 }, { "epoch": 0.025344, "grad_norm": 1.5078125, "learning_rate": 4.958194693285556e-05, "loss": 1.9483, "step": 99 }, { "epoch": 0.0256, "grad_norm": 1.625, "learning_rate": 4.957768108523164e-05, "loss": 1.9969, "step": 100 }, { "epoch": 0.025856, "grad_norm": 1.59375, "learning_rate": 4.957341523760772e-05, "loss": 1.955, "step": 101 }, { "epoch": 0.026112, "grad_norm": 1.4140625, "learning_rate": 4.9569149389983795e-05, "loss": 1.8897, "step": 102 }, { "epoch": 0.026368, "grad_norm": 1.703125, "learning_rate": 4.956488354235987e-05, "loss": 1.9777, "step": 103 }, { "epoch": 0.026624, "grad_norm": 1.6875, "learning_rate": 4.956061769473594e-05, "loss": 1.9827, "step": 104 }, { "epoch": 0.02688, "grad_norm": 1.4921875, "learning_rate": 4.9556351847112024e-05, "loss": 1.9131, "step": 105 }, { "epoch": 0.027136, "grad_norm": 1.7578125, "learning_rate": 4.95520859994881e-05, "loss": 1.9134, "step": 106 }, { "epoch": 0.027392, "grad_norm": 1.671875, "learning_rate": 4.954782015186418e-05, "loss": 1.9172, "step": 107 }, { "epoch": 0.027648, "grad_norm": 1.640625, "learning_rate": 4.9543554304240254e-05, "loss": 1.9225, "step": 108 }, { "epoch": 0.027904, "grad_norm": 1.5703125, "learning_rate": 4.9539288456616335e-05, "loss": 1.9454, "step": 109 }, { "epoch": 0.02816, "grad_norm": 2.234375, "learning_rate": 4.953502260899241e-05, "loss": 1.9331, "step": 110 }, { "epoch": 0.028416, "grad_norm": 1.6796875, "learning_rate": 4.9530756761368483e-05, "loss": 1.933, "step": 111 }, { "epoch": 0.028672, "grad_norm": 1.8515625, "learning_rate": 4.952649091374456e-05, "loss": 1.9129, "step": 112 }, { "epoch": 0.028928, "grad_norm": 1.8203125, "learning_rate": 4.9522225066120645e-05, "loss": 1.8792, "step": 113 }, { "epoch": 0.029184, "grad_norm": 2.015625, "learning_rate": 4.951795921849672e-05, "loss": 1.9328, "step": 114 }, { "epoch": 0.02944, "grad_norm": 1.6796875, "learning_rate": 4.9513693370872794e-05, "loss": 1.8749, "step": 115 }, { "epoch": 0.029696, "grad_norm": 1.703125, "learning_rate": 4.9509427523248875e-05, "loss": 1.9127, "step": 116 }, { "epoch": 0.029952, "grad_norm": 1.96875, "learning_rate": 4.950516167562495e-05, "loss": 1.8625, "step": 117 }, { "epoch": 0.030208, "grad_norm": 1.6015625, "learning_rate": 4.9500895828001024e-05, "loss": 1.8334, "step": 118 }, { "epoch": 0.030464, "grad_norm": 1.8984375, "learning_rate": 4.9496629980377105e-05, "loss": 1.8872, "step": 119 }, { "epoch": 0.03072, "grad_norm": 1.90625, "learning_rate": 4.9492364132753186e-05, "loss": 1.8097, "step": 120 }, { "epoch": 0.030976, "grad_norm": 1.734375, "learning_rate": 4.948809828512926e-05, "loss": 1.9105, "step": 121 }, { "epoch": 0.031232, "grad_norm": 1.765625, "learning_rate": 4.9483832437505334e-05, "loss": 1.7726, "step": 122 }, { "epoch": 0.031488, "grad_norm": 1.6875, "learning_rate": 4.947956658988141e-05, "loss": 1.8824, "step": 123 }, { "epoch": 0.031744, "grad_norm": 1.84375, "learning_rate": 4.947530074225749e-05, "loss": 1.8696, "step": 124 }, { "epoch": 0.032, "grad_norm": 1.6328125, "learning_rate": 4.9471034894633564e-05, "loss": 1.8297, "step": 125 }, { "epoch": 0.032256, "grad_norm": 1.7109375, "learning_rate": 4.9466769047009645e-05, "loss": 1.7575, "step": 126 }, { "epoch": 0.032512, "grad_norm": 1.7890625, "learning_rate": 4.946250319938572e-05, "loss": 1.7896, "step": 127 }, { "epoch": 0.032768, "grad_norm": 1.828125, "learning_rate": 4.94582373517618e-05, "loss": 1.8516, "step": 128 }, { "epoch": 0.033024, "grad_norm": 1.890625, "learning_rate": 4.9453971504137874e-05, "loss": 1.7899, "step": 129 }, { "epoch": 0.03328, "grad_norm": 1.9296875, "learning_rate": 4.944970565651395e-05, "loss": 1.8454, "step": 130 }, { "epoch": 0.033536, "grad_norm": 1.84375, "learning_rate": 4.944543980889002e-05, "loss": 1.8143, "step": 131 }, { "epoch": 0.033792, "grad_norm": 1.9140625, "learning_rate": 4.9441173961266104e-05, "loss": 1.7879, "step": 132 }, { "epoch": 0.034048, "grad_norm": 1.953125, "learning_rate": 4.9436908113642185e-05, "loss": 1.8338, "step": 133 }, { "epoch": 0.034304, "grad_norm": 1.84375, "learning_rate": 4.943264226601826e-05, "loss": 1.7488, "step": 134 }, { "epoch": 0.03456, "grad_norm": 1.953125, "learning_rate": 4.942837641839434e-05, "loss": 1.7858, "step": 135 }, { "epoch": 0.034816, "grad_norm": 1.7421875, "learning_rate": 4.9424110570770415e-05, "loss": 1.7527, "step": 136 }, { "epoch": 0.035072, "grad_norm": 2.21875, "learning_rate": 4.941984472314649e-05, "loss": 1.8653, "step": 137 }, { "epoch": 0.035328, "grad_norm": 2.078125, "learning_rate": 4.941557887552257e-05, "loss": 1.7514, "step": 138 }, { "epoch": 0.035584, "grad_norm": 1.8203125, "learning_rate": 4.941131302789865e-05, "loss": 1.775, "step": 139 }, { "epoch": 0.03584, "grad_norm": 1.765625, "learning_rate": 4.9407047180274725e-05, "loss": 1.7787, "step": 140 }, { "epoch": 0.036096, "grad_norm": 1.7890625, "learning_rate": 4.94027813326508e-05, "loss": 1.7926, "step": 141 }, { "epoch": 0.036352, "grad_norm": 1.9140625, "learning_rate": 4.9398515485026874e-05, "loss": 1.7329, "step": 142 }, { "epoch": 0.036608, "grad_norm": 1.8359375, "learning_rate": 4.9394249637402955e-05, "loss": 1.7812, "step": 143 }, { "epoch": 0.036864, "grad_norm": 2.140625, "learning_rate": 4.938998378977903e-05, "loss": 1.7115, "step": 144 }, { "epoch": 0.03712, "grad_norm": 2.15625, "learning_rate": 4.938571794215511e-05, "loss": 1.7321, "step": 145 }, { "epoch": 0.037376, "grad_norm": 1.84375, "learning_rate": 4.9381452094531184e-05, "loss": 1.8258, "step": 146 }, { "epoch": 0.037632, "grad_norm": 2.015625, "learning_rate": 4.9377186246907265e-05, "loss": 1.7198, "step": 147 }, { "epoch": 0.037888, "grad_norm": 1.9140625, "learning_rate": 4.937292039928334e-05, "loss": 1.7018, "step": 148 }, { "epoch": 0.038144, "grad_norm": 1.921875, "learning_rate": 4.9368654551659414e-05, "loss": 1.7487, "step": 149 }, { "epoch": 0.0384, "grad_norm": 1.90625, "learning_rate": 4.9364388704035495e-05, "loss": 1.7039, "step": 150 }, { "epoch": 0.038656, "grad_norm": 1.78125, "learning_rate": 4.936012285641157e-05, "loss": 1.7421, "step": 151 }, { "epoch": 0.038912, "grad_norm": 1.84375, "learning_rate": 4.935585700878765e-05, "loss": 1.6556, "step": 152 }, { "epoch": 0.039168, "grad_norm": 1.90625, "learning_rate": 4.9351591161163725e-05, "loss": 1.7277, "step": 153 }, { "epoch": 0.039424, "grad_norm": 1.90625, "learning_rate": 4.9347325313539806e-05, "loss": 1.7489, "step": 154 }, { "epoch": 0.03968, "grad_norm": 2.0, "learning_rate": 4.934305946591588e-05, "loss": 1.7052, "step": 155 }, { "epoch": 0.039936, "grad_norm": 2.203125, "learning_rate": 4.9338793618291954e-05, "loss": 1.7708, "step": 156 }, { "epoch": 0.040192, "grad_norm": 1.9609375, "learning_rate": 4.9334527770668035e-05, "loss": 1.6825, "step": 157 }, { "epoch": 0.040448, "grad_norm": 1.84375, "learning_rate": 4.9330261923044116e-05, "loss": 1.7026, "step": 158 }, { "epoch": 0.040704, "grad_norm": 1.921875, "learning_rate": 4.932599607542019e-05, "loss": 1.7233, "step": 159 }, { "epoch": 0.04096, "grad_norm": 1.984375, "learning_rate": 4.9321730227796265e-05, "loss": 1.7464, "step": 160 }, { "epoch": 0.041216, "grad_norm": 1.8984375, "learning_rate": 4.931746438017234e-05, "loss": 1.6769, "step": 161 }, { "epoch": 0.041472, "grad_norm": 1.7734375, "learning_rate": 4.931319853254842e-05, "loss": 1.7106, "step": 162 }, { "epoch": 0.041728, "grad_norm": 1.9296875, "learning_rate": 4.9308932684924494e-05, "loss": 1.6307, "step": 163 }, { "epoch": 0.041984, "grad_norm": 2.1875, "learning_rate": 4.9304666837300575e-05, "loss": 1.7086, "step": 164 }, { "epoch": 0.04224, "grad_norm": 2.03125, "learning_rate": 4.9300400989676656e-05, "loss": 1.6809, "step": 165 }, { "epoch": 0.042496, "grad_norm": 1.875, "learning_rate": 4.929613514205273e-05, "loss": 1.6646, "step": 166 }, { "epoch": 0.042752, "grad_norm": 1.890625, "learning_rate": 4.9291869294428805e-05, "loss": 1.6178, "step": 167 }, { "epoch": 0.043008, "grad_norm": 2.15625, "learning_rate": 4.928760344680488e-05, "loss": 1.7098, "step": 168 }, { "epoch": 0.043264, "grad_norm": 1.796875, "learning_rate": 4.928333759918096e-05, "loss": 1.6471, "step": 169 }, { "epoch": 0.04352, "grad_norm": 2.0, "learning_rate": 4.9279071751557035e-05, "loss": 1.7198, "step": 170 }, { "epoch": 0.043776, "grad_norm": 1.9921875, "learning_rate": 4.9274805903933116e-05, "loss": 1.6987, "step": 171 }, { "epoch": 0.044032, "grad_norm": 1.9609375, "learning_rate": 4.927054005630919e-05, "loss": 1.6829, "step": 172 }, { "epoch": 0.044288, "grad_norm": 2.078125, "learning_rate": 4.926627420868527e-05, "loss": 1.7319, "step": 173 }, { "epoch": 0.044544, "grad_norm": 2.046875, "learning_rate": 4.9262008361061345e-05, "loss": 1.6764, "step": 174 }, { "epoch": 0.0448, "grad_norm": 1.9140625, "learning_rate": 4.925774251343742e-05, "loss": 1.6083, "step": 175 }, { "epoch": 0.045056, "grad_norm": 2.03125, "learning_rate": 4.92534766658135e-05, "loss": 1.6746, "step": 176 }, { "epoch": 0.045312, "grad_norm": 2.0, "learning_rate": 4.924921081818958e-05, "loss": 1.6424, "step": 177 }, { "epoch": 0.045568, "grad_norm": 2.09375, "learning_rate": 4.9244944970565656e-05, "loss": 1.6847, "step": 178 }, { "epoch": 0.045824, "grad_norm": 2.046875, "learning_rate": 4.924067912294173e-05, "loss": 1.669, "step": 179 }, { "epoch": 0.04608, "grad_norm": 2.09375, "learning_rate": 4.9236413275317804e-05, "loss": 1.6319, "step": 180 }, { "epoch": 0.046336, "grad_norm": 2.28125, "learning_rate": 4.9232147427693885e-05, "loss": 1.6182, "step": 181 }, { "epoch": 0.046592, "grad_norm": 2.296875, "learning_rate": 4.922788158006996e-05, "loss": 1.6482, "step": 182 }, { "epoch": 0.046848, "grad_norm": 2.140625, "learning_rate": 4.922361573244604e-05, "loss": 1.5928, "step": 183 }, { "epoch": 0.047104, "grad_norm": 1.96875, "learning_rate": 4.921934988482212e-05, "loss": 1.6464, "step": 184 }, { "epoch": 0.04736, "grad_norm": 2.09375, "learning_rate": 4.9215084037198196e-05, "loss": 1.6083, "step": 185 }, { "epoch": 0.047616, "grad_norm": 1.9296875, "learning_rate": 4.921081818957427e-05, "loss": 1.5948, "step": 186 }, { "epoch": 0.047872, "grad_norm": 2.234375, "learning_rate": 4.9206552341950344e-05, "loss": 1.6405, "step": 187 }, { "epoch": 0.048128, "grad_norm": 2.234375, "learning_rate": 4.9202286494326426e-05, "loss": 1.6457, "step": 188 }, { "epoch": 0.048384, "grad_norm": 2.265625, "learning_rate": 4.91980206467025e-05, "loss": 1.6023, "step": 189 }, { "epoch": 0.04864, "grad_norm": 2.171875, "learning_rate": 4.919375479907858e-05, "loss": 1.6197, "step": 190 }, { "epoch": 0.048896, "grad_norm": 2.265625, "learning_rate": 4.9189488951454655e-05, "loss": 1.6202, "step": 191 }, { "epoch": 0.049152, "grad_norm": 2.015625, "learning_rate": 4.9185223103830736e-05, "loss": 1.5307, "step": 192 }, { "epoch": 0.049408, "grad_norm": 2.125, "learning_rate": 4.918095725620681e-05, "loss": 1.6035, "step": 193 }, { "epoch": 0.049664, "grad_norm": 2.0, "learning_rate": 4.9176691408582885e-05, "loss": 1.611, "step": 194 }, { "epoch": 0.04992, "grad_norm": 2.21875, "learning_rate": 4.9172425560958966e-05, "loss": 1.6442, "step": 195 }, { "epoch": 0.050176, "grad_norm": 2.09375, "learning_rate": 4.916815971333505e-05, "loss": 1.5583, "step": 196 }, { "epoch": 0.050432, "grad_norm": 1.7734375, "learning_rate": 4.916389386571112e-05, "loss": 1.5812, "step": 197 }, { "epoch": 0.050688, "grad_norm": 2.15625, "learning_rate": 4.9159628018087195e-05, "loss": 1.6093, "step": 198 }, { "epoch": 0.050944, "grad_norm": 2.203125, "learning_rate": 4.9155362170463276e-05, "loss": 1.5823, "step": 199 }, { "epoch": 0.0512, "grad_norm": 1.984375, "learning_rate": 4.915109632283935e-05, "loss": 1.6072, "step": 200 }, { "epoch": 0.051456, "grad_norm": 2.34375, "learning_rate": 4.9146830475215425e-05, "loss": 1.6181, "step": 201 }, { "epoch": 0.051712, "grad_norm": 2.359375, "learning_rate": 4.9142564627591506e-05, "loss": 1.5957, "step": 202 }, { "epoch": 0.051968, "grad_norm": 2.109375, "learning_rate": 4.913829877996759e-05, "loss": 1.5871, "step": 203 }, { "epoch": 0.052224, "grad_norm": 2.34375, "learning_rate": 4.913403293234366e-05, "loss": 1.6018, "step": 204 }, { "epoch": 0.05248, "grad_norm": 2.265625, "learning_rate": 4.9129767084719735e-05, "loss": 1.6011, "step": 205 }, { "epoch": 0.052736, "grad_norm": 1.984375, "learning_rate": 4.912550123709581e-05, "loss": 1.5924, "step": 206 }, { "epoch": 0.052992, "grad_norm": 2.296875, "learning_rate": 4.912123538947189e-05, "loss": 1.6036, "step": 207 }, { "epoch": 0.053248, "grad_norm": 2.28125, "learning_rate": 4.9116969541847965e-05, "loss": 1.5979, "step": 208 }, { "epoch": 0.053504, "grad_norm": 2.21875, "learning_rate": 4.9112703694224046e-05, "loss": 1.5598, "step": 209 }, { "epoch": 0.05376, "grad_norm": 2.03125, "learning_rate": 4.910843784660012e-05, "loss": 1.5844, "step": 210 }, { "epoch": 0.054016, "grad_norm": 2.09375, "learning_rate": 4.91041719989762e-05, "loss": 1.5775, "step": 211 }, { "epoch": 0.054272, "grad_norm": 2.1875, "learning_rate": 4.9099906151352276e-05, "loss": 1.5797, "step": 212 }, { "epoch": 0.054528, "grad_norm": 2.03125, "learning_rate": 4.909564030372835e-05, "loss": 1.5664, "step": 213 }, { "epoch": 0.054784, "grad_norm": 2.015625, "learning_rate": 4.9091374456104424e-05, "loss": 1.5471, "step": 214 }, { "epoch": 0.05504, "grad_norm": 2.203125, "learning_rate": 4.908710860848051e-05, "loss": 1.5752, "step": 215 }, { "epoch": 0.055296, "grad_norm": 1.84375, "learning_rate": 4.9082842760856586e-05, "loss": 1.5398, "step": 216 }, { "epoch": 0.055552, "grad_norm": 2.234375, "learning_rate": 4.907857691323266e-05, "loss": 1.5433, "step": 217 }, { "epoch": 0.055808, "grad_norm": 2.125, "learning_rate": 4.907431106560874e-05, "loss": 1.5691, "step": 218 }, { "epoch": 0.056064, "grad_norm": 2.28125, "learning_rate": 4.9070045217984816e-05, "loss": 1.4747, "step": 219 }, { "epoch": 0.05632, "grad_norm": 2.25, "learning_rate": 4.906577937036089e-05, "loss": 1.5545, "step": 220 }, { "epoch": 0.056576, "grad_norm": 2.140625, "learning_rate": 4.906151352273697e-05, "loss": 1.5337, "step": 221 }, { "epoch": 0.056832, "grad_norm": 2.296875, "learning_rate": 4.905724767511305e-05, "loss": 1.5217, "step": 222 }, { "epoch": 0.057088, "grad_norm": 1.9921875, "learning_rate": 4.9052981827489126e-05, "loss": 1.5326, "step": 223 }, { "epoch": 0.057344, "grad_norm": 2.265625, "learning_rate": 4.90487159798652e-05, "loss": 1.5819, "step": 224 }, { "epoch": 0.0576, "grad_norm": 2.234375, "learning_rate": 4.9044450132241275e-05, "loss": 1.5518, "step": 225 }, { "epoch": 0.057856, "grad_norm": 1.9609375, "learning_rate": 4.9040184284617356e-05, "loss": 1.5557, "step": 226 }, { "epoch": 0.058112, "grad_norm": 2.015625, "learning_rate": 4.903591843699343e-05, "loss": 1.5525, "step": 227 }, { "epoch": 0.058368, "grad_norm": 2.375, "learning_rate": 4.903165258936951e-05, "loss": 1.5862, "step": 228 }, { "epoch": 0.058624, "grad_norm": 2.140625, "learning_rate": 4.9027386741745586e-05, "loss": 1.551, "step": 229 }, { "epoch": 0.05888, "grad_norm": 2.296875, "learning_rate": 4.902312089412167e-05, "loss": 1.5245, "step": 230 }, { "epoch": 0.059136, "grad_norm": 2.234375, "learning_rate": 4.901885504649774e-05, "loss": 1.555, "step": 231 }, { "epoch": 0.059392, "grad_norm": 2.171875, "learning_rate": 4.9014589198873815e-05, "loss": 1.5364, "step": 232 }, { "epoch": 0.059648, "grad_norm": 2.203125, "learning_rate": 4.9010323351249896e-05, "loss": 1.5301, "step": 233 }, { "epoch": 0.059904, "grad_norm": 2.203125, "learning_rate": 4.900605750362598e-05, "loss": 1.5062, "step": 234 }, { "epoch": 0.06016, "grad_norm": 2.109375, "learning_rate": 4.900179165600205e-05, "loss": 1.488, "step": 235 }, { "epoch": 0.060416, "grad_norm": 2.1875, "learning_rate": 4.8997525808378126e-05, "loss": 1.4925, "step": 236 }, { "epoch": 0.060672, "grad_norm": 2.1875, "learning_rate": 4.899325996075421e-05, "loss": 1.5577, "step": 237 }, { "epoch": 0.060928, "grad_norm": 2.265625, "learning_rate": 4.898899411313028e-05, "loss": 1.5758, "step": 238 }, { "epoch": 0.061184, "grad_norm": 2.453125, "learning_rate": 4.8984728265506355e-05, "loss": 1.5494, "step": 239 }, { "epoch": 0.06144, "grad_norm": 2.265625, "learning_rate": 4.8980462417882436e-05, "loss": 1.4806, "step": 240 }, { "epoch": 0.061696, "grad_norm": 2.453125, "learning_rate": 4.897619657025852e-05, "loss": 1.5353, "step": 241 }, { "epoch": 0.061952, "grad_norm": 2.09375, "learning_rate": 4.897193072263459e-05, "loss": 1.4716, "step": 242 }, { "epoch": 0.062208, "grad_norm": 2.28125, "learning_rate": 4.8967664875010666e-05, "loss": 1.4682, "step": 243 }, { "epoch": 0.062464, "grad_norm": 2.265625, "learning_rate": 4.896339902738674e-05, "loss": 1.5145, "step": 244 }, { "epoch": 0.06272, "grad_norm": 2.34375, "learning_rate": 4.895913317976282e-05, "loss": 1.5411, "step": 245 }, { "epoch": 0.062976, "grad_norm": 2.53125, "learning_rate": 4.8954867332138896e-05, "loss": 1.5289, "step": 246 }, { "epoch": 0.063232, "grad_norm": 2.640625, "learning_rate": 4.895060148451498e-05, "loss": 1.496, "step": 247 }, { "epoch": 0.063488, "grad_norm": 2.421875, "learning_rate": 4.894633563689106e-05, "loss": 1.5183, "step": 248 }, { "epoch": 0.063744, "grad_norm": 2.375, "learning_rate": 4.894206978926713e-05, "loss": 1.476, "step": 249 }, { "epoch": 0.064, "grad_norm": 2.21875, "learning_rate": 4.8937803941643206e-05, "loss": 1.5199, "step": 250 }, { "epoch": 0.064256, "grad_norm": 2.515625, "learning_rate": 4.893353809401928e-05, "loss": 1.5078, "step": 251 }, { "epoch": 0.064512, "grad_norm": 2.53125, "learning_rate": 4.892927224639536e-05, "loss": 1.4749, "step": 252 }, { "epoch": 0.064768, "grad_norm": 2.234375, "learning_rate": 4.8925006398771436e-05, "loss": 1.4371, "step": 253 }, { "epoch": 0.065024, "grad_norm": 2.515625, "learning_rate": 4.892074055114752e-05, "loss": 1.4957, "step": 254 }, { "epoch": 0.06528, "grad_norm": 2.59375, "learning_rate": 4.891647470352359e-05, "loss": 1.511, "step": 255 }, { "epoch": 0.065536, "grad_norm": 2.8125, "learning_rate": 4.891220885589967e-05, "loss": 1.4942, "step": 256 }, { "epoch": 0.065792, "grad_norm": 2.5625, "learning_rate": 4.8907943008275746e-05, "loss": 1.4961, "step": 257 }, { "epoch": 0.066048, "grad_norm": 2.40625, "learning_rate": 4.890367716065182e-05, "loss": 1.4534, "step": 258 }, { "epoch": 0.066304, "grad_norm": 2.453125, "learning_rate": 4.88994113130279e-05, "loss": 1.4739, "step": 259 }, { "epoch": 0.06656, "grad_norm": 2.46875, "learning_rate": 4.889514546540398e-05, "loss": 1.4574, "step": 260 }, { "epoch": 0.066816, "grad_norm": 2.421875, "learning_rate": 4.889087961778006e-05, "loss": 1.474, "step": 261 }, { "epoch": 0.067072, "grad_norm": 2.375, "learning_rate": 4.888661377015613e-05, "loss": 1.48, "step": 262 }, { "epoch": 0.067328, "grad_norm": 2.59375, "learning_rate": 4.8882347922532206e-05, "loss": 1.4356, "step": 263 }, { "epoch": 0.067584, "grad_norm": 2.46875, "learning_rate": 4.8878082074908287e-05, "loss": 1.4966, "step": 264 }, { "epoch": 0.06784, "grad_norm": 2.3125, "learning_rate": 4.887381622728436e-05, "loss": 1.4575, "step": 265 }, { "epoch": 0.068096, "grad_norm": 2.390625, "learning_rate": 4.886955037966044e-05, "loss": 1.4602, "step": 266 }, { "epoch": 0.068352, "grad_norm": 2.40625, "learning_rate": 4.886528453203652e-05, "loss": 1.4882, "step": 267 }, { "epoch": 0.068608, "grad_norm": 2.546875, "learning_rate": 4.88610186844126e-05, "loss": 1.4301, "step": 268 }, { "epoch": 0.068864, "grad_norm": 2.546875, "learning_rate": 4.885675283678867e-05, "loss": 1.4798, "step": 269 }, { "epoch": 0.06912, "grad_norm": 2.625, "learning_rate": 4.8852486989164746e-05, "loss": 1.4329, "step": 270 }, { "epoch": 0.069376, "grad_norm": 2.515625, "learning_rate": 4.884822114154083e-05, "loss": 1.4347, "step": 271 }, { "epoch": 0.069632, "grad_norm": 2.78125, "learning_rate": 4.88439552939169e-05, "loss": 1.4584, "step": 272 }, { "epoch": 0.069888, "grad_norm": 2.515625, "learning_rate": 4.883968944629298e-05, "loss": 1.4704, "step": 273 }, { "epoch": 0.070144, "grad_norm": 2.3125, "learning_rate": 4.8835423598669056e-05, "loss": 1.4863, "step": 274 }, { "epoch": 0.0704, "grad_norm": 2.71875, "learning_rate": 4.883115775104514e-05, "loss": 1.4406, "step": 275 }, { "epoch": 0.070656, "grad_norm": 2.3125, "learning_rate": 4.882689190342121e-05, "loss": 1.4104, "step": 276 }, { "epoch": 0.070912, "grad_norm": 2.359375, "learning_rate": 4.8822626055797286e-05, "loss": 1.4123, "step": 277 }, { "epoch": 0.071168, "grad_norm": 2.5625, "learning_rate": 4.881836020817337e-05, "loss": 1.4639, "step": 278 }, { "epoch": 0.071424, "grad_norm": 2.109375, "learning_rate": 4.881409436054945e-05, "loss": 1.445, "step": 279 }, { "epoch": 0.07168, "grad_norm": 2.296875, "learning_rate": 4.880982851292552e-05, "loss": 1.5113, "step": 280 }, { "epoch": 0.071936, "grad_norm": 2.296875, "learning_rate": 4.8805562665301597e-05, "loss": 1.4277, "step": 281 }, { "epoch": 0.072192, "grad_norm": 2.484375, "learning_rate": 4.880129681767768e-05, "loss": 1.4616, "step": 282 }, { "epoch": 0.072448, "grad_norm": 2.4375, "learning_rate": 4.879703097005375e-05, "loss": 1.4176, "step": 283 }, { "epoch": 0.072704, "grad_norm": 2.5, "learning_rate": 4.8792765122429826e-05, "loss": 1.4402, "step": 284 }, { "epoch": 0.07296, "grad_norm": 2.53125, "learning_rate": 4.878849927480591e-05, "loss": 1.4465, "step": 285 }, { "epoch": 0.073216, "grad_norm": 2.453125, "learning_rate": 4.878423342718199e-05, "loss": 1.491, "step": 286 }, { "epoch": 0.073472, "grad_norm": 2.359375, "learning_rate": 4.877996757955806e-05, "loss": 1.4301, "step": 287 }, { "epoch": 0.073728, "grad_norm": 2.28125, "learning_rate": 4.877570173193414e-05, "loss": 1.4456, "step": 288 }, { "epoch": 0.073984, "grad_norm": 2.640625, "learning_rate": 4.877143588431021e-05, "loss": 1.4613, "step": 289 }, { "epoch": 0.07424, "grad_norm": 2.546875, "learning_rate": 4.876717003668629e-05, "loss": 1.4438, "step": 290 }, { "epoch": 0.074496, "grad_norm": 2.453125, "learning_rate": 4.8762904189062366e-05, "loss": 1.4258, "step": 291 }, { "epoch": 0.074752, "grad_norm": 2.53125, "learning_rate": 4.875863834143845e-05, "loss": 1.4418, "step": 292 }, { "epoch": 0.075008, "grad_norm": 2.59375, "learning_rate": 4.875437249381452e-05, "loss": 1.4312, "step": 293 }, { "epoch": 0.075264, "grad_norm": 2.671875, "learning_rate": 4.87501066461906e-05, "loss": 1.4274, "step": 294 }, { "epoch": 0.07552, "grad_norm": 2.546875, "learning_rate": 4.874584079856668e-05, "loss": 1.4523, "step": 295 }, { "epoch": 0.075776, "grad_norm": 2.453125, "learning_rate": 4.874157495094275e-05, "loss": 1.4219, "step": 296 }, { "epoch": 0.076032, "grad_norm": 2.421875, "learning_rate": 4.873730910331883e-05, "loss": 1.4023, "step": 297 }, { "epoch": 0.076288, "grad_norm": 2.375, "learning_rate": 4.873304325569491e-05, "loss": 1.3625, "step": 298 }, { "epoch": 0.076544, "grad_norm": 2.25, "learning_rate": 4.872877740807099e-05, "loss": 1.3942, "step": 299 }, { "epoch": 0.0768, "grad_norm": 2.1875, "learning_rate": 4.872451156044706e-05, "loss": 1.4187, "step": 300 }, { "epoch": 0.077056, "grad_norm": 2.515625, "learning_rate": 4.872024571282314e-05, "loss": 1.438, "step": 301 }, { "epoch": 0.077312, "grad_norm": 2.28125, "learning_rate": 4.871597986519922e-05, "loss": 1.3752, "step": 302 }, { "epoch": 0.077568, "grad_norm": 2.484375, "learning_rate": 4.871171401757529e-05, "loss": 1.3774, "step": 303 }, { "epoch": 0.077824, "grad_norm": 2.390625, "learning_rate": 4.870744816995137e-05, "loss": 1.393, "step": 304 }, { "epoch": 0.07808, "grad_norm": 3.015625, "learning_rate": 4.8703182322327453e-05, "loss": 1.4618, "step": 305 }, { "epoch": 0.078336, "grad_norm": 2.515625, "learning_rate": 4.869891647470353e-05, "loss": 1.4248, "step": 306 }, { "epoch": 0.078592, "grad_norm": 2.59375, "learning_rate": 4.86946506270796e-05, "loss": 1.3912, "step": 307 }, { "epoch": 0.078848, "grad_norm": 2.59375, "learning_rate": 4.8690384779455676e-05, "loss": 1.407, "step": 308 }, { "epoch": 0.079104, "grad_norm": 2.5625, "learning_rate": 4.868611893183176e-05, "loss": 1.4209, "step": 309 }, { "epoch": 0.07936, "grad_norm": 2.25, "learning_rate": 4.868185308420783e-05, "loss": 1.3726, "step": 310 }, { "epoch": 0.079616, "grad_norm": 2.359375, "learning_rate": 4.867758723658391e-05, "loss": 1.3994, "step": 311 }, { "epoch": 0.079872, "grad_norm": 2.421875, "learning_rate": 4.867332138895999e-05, "loss": 1.3895, "step": 312 }, { "epoch": 0.080128, "grad_norm": 2.546875, "learning_rate": 4.866905554133607e-05, "loss": 1.3558, "step": 313 }, { "epoch": 0.080384, "grad_norm": 2.296875, "learning_rate": 4.866478969371214e-05, "loss": 1.394, "step": 314 }, { "epoch": 0.08064, "grad_norm": 2.796875, "learning_rate": 4.8660523846088216e-05, "loss": 1.4176, "step": 315 }, { "epoch": 0.080896, "grad_norm": 2.5625, "learning_rate": 4.86562579984643e-05, "loss": 1.4403, "step": 316 }, { "epoch": 0.081152, "grad_norm": 2.140625, "learning_rate": 4.865199215084038e-05, "loss": 1.3934, "step": 317 }, { "epoch": 0.081408, "grad_norm": 2.625, "learning_rate": 4.864772630321645e-05, "loss": 1.4171, "step": 318 }, { "epoch": 0.081664, "grad_norm": 2.375, "learning_rate": 4.864346045559253e-05, "loss": 1.3782, "step": 319 }, { "epoch": 0.08192, "grad_norm": 2.59375, "learning_rate": 4.863919460796861e-05, "loss": 1.3604, "step": 320 }, { "epoch": 0.082176, "grad_norm": 2.609375, "learning_rate": 4.863492876034468e-05, "loss": 1.3604, "step": 321 }, { "epoch": 0.082432, "grad_norm": 2.421875, "learning_rate": 4.863066291272076e-05, "loss": 1.3712, "step": 322 }, { "epoch": 0.082688, "grad_norm": 2.5625, "learning_rate": 4.862639706509684e-05, "loss": 1.3733, "step": 323 }, { "epoch": 0.082944, "grad_norm": 2.21875, "learning_rate": 4.862213121747292e-05, "loss": 1.3858, "step": 324 }, { "epoch": 0.0832, "grad_norm": 2.4375, "learning_rate": 4.861786536984899e-05, "loss": 1.3398, "step": 325 }, { "epoch": 0.083456, "grad_norm": 2.421875, "learning_rate": 4.861359952222507e-05, "loss": 1.3975, "step": 326 }, { "epoch": 0.083712, "grad_norm": 2.46875, "learning_rate": 4.860933367460114e-05, "loss": 1.3495, "step": 327 }, { "epoch": 0.083968, "grad_norm": 2.234375, "learning_rate": 4.860506782697722e-05, "loss": 1.3591, "step": 328 }, { "epoch": 0.084224, "grad_norm": 2.375, "learning_rate": 4.86008019793533e-05, "loss": 1.3565, "step": 329 }, { "epoch": 0.08448, "grad_norm": 2.359375, "learning_rate": 4.859653613172938e-05, "loss": 1.3631, "step": 330 }, { "epoch": 0.084736, "grad_norm": 2.6875, "learning_rate": 4.859227028410546e-05, "loss": 1.3668, "step": 331 }, { "epoch": 0.084992, "grad_norm": 2.25, "learning_rate": 4.858800443648153e-05, "loss": 1.3649, "step": 332 }, { "epoch": 0.085248, "grad_norm": 2.46875, "learning_rate": 4.858373858885761e-05, "loss": 1.3302, "step": 333 }, { "epoch": 0.085504, "grad_norm": 2.453125, "learning_rate": 4.857947274123368e-05, "loss": 1.3837, "step": 334 }, { "epoch": 0.08576, "grad_norm": 2.59375, "learning_rate": 4.857520689360976e-05, "loss": 1.3522, "step": 335 }, { "epoch": 0.086016, "grad_norm": 2.578125, "learning_rate": 4.8570941045985844e-05, "loss": 1.3364, "step": 336 }, { "epoch": 0.086272, "grad_norm": 2.53125, "learning_rate": 4.856667519836192e-05, "loss": 1.3699, "step": 337 }, { "epoch": 0.086528, "grad_norm": 2.40625, "learning_rate": 4.856240935073799e-05, "loss": 1.3882, "step": 338 }, { "epoch": 0.086784, "grad_norm": 2.71875, "learning_rate": 4.8558143503114073e-05, "loss": 1.3487, "step": 339 }, { "epoch": 0.08704, "grad_norm": 2.796875, "learning_rate": 4.855387765549015e-05, "loss": 1.3729, "step": 340 }, { "epoch": 0.087296, "grad_norm": 2.46875, "learning_rate": 4.854961180786622e-05, "loss": 1.361, "step": 341 }, { "epoch": 0.087552, "grad_norm": 2.578125, "learning_rate": 4.85453459602423e-05, "loss": 1.3687, "step": 342 }, { "epoch": 0.087808, "grad_norm": 2.453125, "learning_rate": 4.8541080112618384e-05, "loss": 1.3309, "step": 343 }, { "epoch": 0.088064, "grad_norm": 2.40625, "learning_rate": 4.853681426499446e-05, "loss": 1.3244, "step": 344 }, { "epoch": 0.08832, "grad_norm": 2.609375, "learning_rate": 4.853254841737053e-05, "loss": 1.3232, "step": 345 }, { "epoch": 0.088576, "grad_norm": 2.609375, "learning_rate": 4.8528282569746614e-05, "loss": 1.3778, "step": 346 }, { "epoch": 0.088832, "grad_norm": 2.3125, "learning_rate": 4.852401672212269e-05, "loss": 1.3067, "step": 347 }, { "epoch": 0.089088, "grad_norm": 2.703125, "learning_rate": 4.851975087449876e-05, "loss": 1.3457, "step": 348 }, { "epoch": 0.089344, "grad_norm": 2.359375, "learning_rate": 4.851548502687484e-05, "loss": 1.3158, "step": 349 }, { "epoch": 0.0896, "grad_norm": 2.609375, "learning_rate": 4.8511219179250924e-05, "loss": 1.3724, "step": 350 }, { "epoch": 0.089856, "grad_norm": 2.390625, "learning_rate": 4.8506953331627e-05, "loss": 1.3133, "step": 351 }, { "epoch": 0.090112, "grad_norm": 2.71875, "learning_rate": 4.850268748400307e-05, "loss": 1.2902, "step": 352 }, { "epoch": 0.090368, "grad_norm": 2.578125, "learning_rate": 4.849842163637915e-05, "loss": 1.3383, "step": 353 }, { "epoch": 0.090624, "grad_norm": 2.375, "learning_rate": 4.849415578875523e-05, "loss": 1.3155, "step": 354 }, { "epoch": 0.09088, "grad_norm": 2.6875, "learning_rate": 4.84898899411313e-05, "loss": 1.3205, "step": 355 }, { "epoch": 0.091136, "grad_norm": 2.703125, "learning_rate": 4.848562409350738e-05, "loss": 1.3488, "step": 356 }, { "epoch": 0.091392, "grad_norm": 2.78125, "learning_rate": 4.848135824588346e-05, "loss": 1.326, "step": 357 }, { "epoch": 0.091648, "grad_norm": 2.6875, "learning_rate": 4.847709239825954e-05, "loss": 1.356, "step": 358 }, { "epoch": 0.091904, "grad_norm": 2.734375, "learning_rate": 4.847282655063561e-05, "loss": 1.3191, "step": 359 }, { "epoch": 0.09216, "grad_norm": 2.59375, "learning_rate": 4.846856070301169e-05, "loss": 1.3219, "step": 360 }, { "epoch": 0.092416, "grad_norm": 2.921875, "learning_rate": 4.846429485538777e-05, "loss": 1.3356, "step": 361 }, { "epoch": 0.092672, "grad_norm": 2.59375, "learning_rate": 4.846002900776385e-05, "loss": 1.2743, "step": 362 }, { "epoch": 0.092928, "grad_norm": 2.59375, "learning_rate": 4.8455763160139924e-05, "loss": 1.3086, "step": 363 }, { "epoch": 0.093184, "grad_norm": 2.5625, "learning_rate": 4.8451497312516e-05, "loss": 1.3146, "step": 364 }, { "epoch": 0.09344, "grad_norm": 2.59375, "learning_rate": 4.844723146489208e-05, "loss": 1.3004, "step": 365 }, { "epoch": 0.093696, "grad_norm": 2.640625, "learning_rate": 4.844296561726815e-05, "loss": 1.3229, "step": 366 }, { "epoch": 0.093952, "grad_norm": 2.65625, "learning_rate": 4.843869976964423e-05, "loss": 1.3104, "step": 367 }, { "epoch": 0.094208, "grad_norm": 2.296875, "learning_rate": 4.843443392202031e-05, "loss": 1.2928, "step": 368 }, { "epoch": 0.094464, "grad_norm": 2.71875, "learning_rate": 4.843016807439639e-05, "loss": 1.3326, "step": 369 }, { "epoch": 0.09472, "grad_norm": 2.515625, "learning_rate": 4.8425902226772464e-05, "loss": 1.3077, "step": 370 }, { "epoch": 0.094976, "grad_norm": 2.5, "learning_rate": 4.842163637914854e-05, "loss": 1.3201, "step": 371 }, { "epoch": 0.095232, "grad_norm": 2.578125, "learning_rate": 4.841737053152461e-05, "loss": 1.3025, "step": 372 }, { "epoch": 0.095488, "grad_norm": 2.71875, "learning_rate": 4.841310468390069e-05, "loss": 1.2899, "step": 373 }, { "epoch": 0.095744, "grad_norm": 2.375, "learning_rate": 4.840883883627677e-05, "loss": 1.314, "step": 374 }, { "epoch": 0.096, "grad_norm": 2.78125, "learning_rate": 4.840457298865285e-05, "loss": 1.3321, "step": 375 }, { "epoch": 0.096256, "grad_norm": 2.625, "learning_rate": 4.840030714102892e-05, "loss": 1.3422, "step": 376 }, { "epoch": 0.096512, "grad_norm": 2.65625, "learning_rate": 4.8396041293405004e-05, "loss": 1.3137, "step": 377 }, { "epoch": 0.096768, "grad_norm": 2.578125, "learning_rate": 4.839177544578108e-05, "loss": 1.3039, "step": 378 }, { "epoch": 0.097024, "grad_norm": 2.65625, "learning_rate": 4.838750959815715e-05, "loss": 1.3006, "step": 379 }, { "epoch": 0.09728, "grad_norm": 2.375, "learning_rate": 4.8383243750533234e-05, "loss": 1.3158, "step": 380 }, { "epoch": 0.097536, "grad_norm": 2.46875, "learning_rate": 4.8378977902909315e-05, "loss": 1.2508, "step": 381 }, { "epoch": 0.097792, "grad_norm": 3.015625, "learning_rate": 4.837471205528539e-05, "loss": 1.2765, "step": 382 }, { "epoch": 0.098048, "grad_norm": 2.625, "learning_rate": 4.837044620766146e-05, "loss": 1.3461, "step": 383 }, { "epoch": 0.098304, "grad_norm": 2.453125, "learning_rate": 4.8366180360037544e-05, "loss": 1.3068, "step": 384 }, { "epoch": 0.09856, "grad_norm": 2.765625, "learning_rate": 4.836191451241362e-05, "loss": 1.2956, "step": 385 }, { "epoch": 0.098816, "grad_norm": 2.421875, "learning_rate": 4.835764866478969e-05, "loss": 1.3028, "step": 386 }, { "epoch": 0.099072, "grad_norm": 2.390625, "learning_rate": 4.8353382817165774e-05, "loss": 1.317, "step": 387 }, { "epoch": 0.099328, "grad_norm": 3.0, "learning_rate": 4.8349116969541855e-05, "loss": 1.2737, "step": 388 }, { "epoch": 0.099584, "grad_norm": 2.703125, "learning_rate": 4.834485112191793e-05, "loss": 1.2997, "step": 389 }, { "epoch": 0.09984, "grad_norm": 2.53125, "learning_rate": 4.8340585274294e-05, "loss": 1.2789, "step": 390 }, { "epoch": 0.100096, "grad_norm": 2.71875, "learning_rate": 4.833631942667008e-05, "loss": 1.2491, "step": 391 }, { "epoch": 0.100352, "grad_norm": 3.078125, "learning_rate": 4.833205357904616e-05, "loss": 1.2935, "step": 392 }, { "epoch": 0.100608, "grad_norm": 2.484375, "learning_rate": 4.832778773142223e-05, "loss": 1.3159, "step": 393 }, { "epoch": 0.100864, "grad_norm": 2.625, "learning_rate": 4.8323521883798314e-05, "loss": 1.3087, "step": 394 }, { "epoch": 0.10112, "grad_norm": 2.84375, "learning_rate": 4.8319256036174395e-05, "loss": 1.2751, "step": 395 }, { "epoch": 0.101376, "grad_norm": 2.4375, "learning_rate": 4.831499018855047e-05, "loss": 1.2759, "step": 396 }, { "epoch": 0.101632, "grad_norm": 2.734375, "learning_rate": 4.8310724340926543e-05, "loss": 1.2697, "step": 397 }, { "epoch": 0.101888, "grad_norm": 2.65625, "learning_rate": 4.830645849330262e-05, "loss": 1.2734, "step": 398 }, { "epoch": 0.102144, "grad_norm": 2.453125, "learning_rate": 4.83021926456787e-05, "loss": 1.2737, "step": 399 }, { "epoch": 0.1024, "grad_norm": 2.515625, "learning_rate": 4.829792679805478e-05, "loss": 1.2237, "step": 400 }, { "epoch": 0.102656, "grad_norm": 2.421875, "learning_rate": 4.8293660950430854e-05, "loss": 1.2734, "step": 401 }, { "epoch": 0.102912, "grad_norm": 2.59375, "learning_rate": 4.828939510280693e-05, "loss": 1.2318, "step": 402 }, { "epoch": 0.103168, "grad_norm": 2.703125, "learning_rate": 4.828512925518301e-05, "loss": 1.2986, "step": 403 }, { "epoch": 0.103424, "grad_norm": 2.484375, "learning_rate": 4.8280863407559084e-05, "loss": 1.2212, "step": 404 }, { "epoch": 0.10368, "grad_norm": 2.828125, "learning_rate": 4.827659755993516e-05, "loss": 1.2677, "step": 405 }, { "epoch": 0.103936, "grad_norm": 2.640625, "learning_rate": 4.827233171231124e-05, "loss": 1.2345, "step": 406 }, { "epoch": 0.104192, "grad_norm": 2.390625, "learning_rate": 4.826806586468732e-05, "loss": 1.2529, "step": 407 }, { "epoch": 0.104448, "grad_norm": 2.4375, "learning_rate": 4.8263800017063394e-05, "loss": 1.2423, "step": 408 }, { "epoch": 0.104704, "grad_norm": 2.453125, "learning_rate": 4.825953416943947e-05, "loss": 1.2637, "step": 409 }, { "epoch": 0.10496, "grad_norm": 2.5, "learning_rate": 4.825526832181554e-05, "loss": 1.2396, "step": 410 }, { "epoch": 0.105216, "grad_norm": 2.6875, "learning_rate": 4.8251002474191624e-05, "loss": 1.23, "step": 411 }, { "epoch": 0.105472, "grad_norm": 2.53125, "learning_rate": 4.82467366265677e-05, "loss": 1.2238, "step": 412 }, { "epoch": 0.105728, "grad_norm": 2.625, "learning_rate": 4.824247077894378e-05, "loss": 1.2604, "step": 413 }, { "epoch": 0.105984, "grad_norm": 2.46875, "learning_rate": 4.823820493131986e-05, "loss": 1.2625, "step": 414 }, { "epoch": 0.10624, "grad_norm": 2.59375, "learning_rate": 4.8233939083695934e-05, "loss": 1.2954, "step": 415 }, { "epoch": 0.106496, "grad_norm": 2.640625, "learning_rate": 4.822967323607201e-05, "loss": 1.2746, "step": 416 }, { "epoch": 0.106752, "grad_norm": 2.828125, "learning_rate": 4.822540738844808e-05, "loss": 1.2788, "step": 417 }, { "epoch": 0.107008, "grad_norm": 2.46875, "learning_rate": 4.8221141540824164e-05, "loss": 1.2453, "step": 418 }, { "epoch": 0.107264, "grad_norm": 2.71875, "learning_rate": 4.8216875693200245e-05, "loss": 1.2855, "step": 419 }, { "epoch": 0.10752, "grad_norm": 2.5625, "learning_rate": 4.821260984557632e-05, "loss": 1.239, "step": 420 }, { "epoch": 0.107776, "grad_norm": 3.046875, "learning_rate": 4.8208343997952394e-05, "loss": 1.2436, "step": 421 }, { "epoch": 0.108032, "grad_norm": 3.03125, "learning_rate": 4.8204078150328475e-05, "loss": 1.2382, "step": 422 }, { "epoch": 0.108288, "grad_norm": 2.5625, "learning_rate": 4.819981230270455e-05, "loss": 1.2441, "step": 423 }, { "epoch": 0.108544, "grad_norm": 3.078125, "learning_rate": 4.819554645508062e-05, "loss": 1.245, "step": 424 }, { "epoch": 0.1088, "grad_norm": 2.5625, "learning_rate": 4.8191280607456704e-05, "loss": 1.2207, "step": 425 }, { "epoch": 0.109056, "grad_norm": 2.625, "learning_rate": 4.8187014759832785e-05, "loss": 1.2481, "step": 426 }, { "epoch": 0.109312, "grad_norm": 2.640625, "learning_rate": 4.818274891220886e-05, "loss": 1.2372, "step": 427 }, { "epoch": 0.109568, "grad_norm": 2.71875, "learning_rate": 4.8178483064584934e-05, "loss": 1.2303, "step": 428 }, { "epoch": 0.109824, "grad_norm": 2.734375, "learning_rate": 4.8174217216961015e-05, "loss": 1.2388, "step": 429 }, { "epoch": 0.11008, "grad_norm": 2.703125, "learning_rate": 4.816995136933709e-05, "loss": 1.2365, "step": 430 }, { "epoch": 0.110336, "grad_norm": 2.953125, "learning_rate": 4.8165685521713163e-05, "loss": 1.2435, "step": 431 }, { "epoch": 0.110592, "grad_norm": 2.734375, "learning_rate": 4.8161419674089244e-05, "loss": 1.225, "step": 432 }, { "epoch": 0.110848, "grad_norm": 2.578125, "learning_rate": 4.8157153826465325e-05, "loss": 1.1945, "step": 433 }, { "epoch": 0.111104, "grad_norm": 2.71875, "learning_rate": 4.81528879788414e-05, "loss": 1.2339, "step": 434 }, { "epoch": 0.11136, "grad_norm": 2.65625, "learning_rate": 4.8148622131217474e-05, "loss": 1.2488, "step": 435 }, { "epoch": 0.111616, "grad_norm": 2.3125, "learning_rate": 4.814435628359355e-05, "loss": 1.2166, "step": 436 }, { "epoch": 0.111872, "grad_norm": 2.484375, "learning_rate": 4.814009043596963e-05, "loss": 1.1974, "step": 437 }, { "epoch": 0.112128, "grad_norm": 2.796875, "learning_rate": 4.813582458834571e-05, "loss": 1.2465, "step": 438 }, { "epoch": 0.112384, "grad_norm": 2.609375, "learning_rate": 4.8131558740721785e-05, "loss": 1.2608, "step": 439 }, { "epoch": 0.11264, "grad_norm": 2.515625, "learning_rate": 4.812729289309786e-05, "loss": 1.2065, "step": 440 }, { "epoch": 0.112896, "grad_norm": 2.765625, "learning_rate": 4.812302704547394e-05, "loss": 1.2481, "step": 441 }, { "epoch": 0.113152, "grad_norm": 3.046875, "learning_rate": 4.8118761197850014e-05, "loss": 1.2284, "step": 442 }, { "epoch": 0.113408, "grad_norm": 2.375, "learning_rate": 4.811449535022609e-05, "loss": 1.2119, "step": 443 }, { "epoch": 0.113664, "grad_norm": 2.84375, "learning_rate": 4.811022950260217e-05, "loss": 1.1955, "step": 444 }, { "epoch": 0.11392, "grad_norm": 3.15625, "learning_rate": 4.810596365497825e-05, "loss": 1.2275, "step": 445 }, { "epoch": 0.114176, "grad_norm": 2.40625, "learning_rate": 4.8101697807354325e-05, "loss": 1.2163, "step": 446 }, { "epoch": 0.114432, "grad_norm": 2.796875, "learning_rate": 4.80974319597304e-05, "loss": 1.2016, "step": 447 }, { "epoch": 0.114688, "grad_norm": 2.6875, "learning_rate": 4.809316611210648e-05, "loss": 1.2061, "step": 448 }, { "epoch": 0.114944, "grad_norm": 2.484375, "learning_rate": 4.8088900264482554e-05, "loss": 1.2003, "step": 449 }, { "epoch": 0.1152, "grad_norm": 2.796875, "learning_rate": 4.808463441685863e-05, "loss": 1.2788, "step": 450 }, { "epoch": 0.115456, "grad_norm": 2.53125, "learning_rate": 4.808036856923471e-05, "loss": 1.2559, "step": 451 }, { "epoch": 0.115712, "grad_norm": 2.96875, "learning_rate": 4.807610272161079e-05, "loss": 1.2246, "step": 452 }, { "epoch": 0.115968, "grad_norm": 2.890625, "learning_rate": 4.8071836873986865e-05, "loss": 1.2219, "step": 453 }, { "epoch": 0.116224, "grad_norm": 2.640625, "learning_rate": 4.806757102636294e-05, "loss": 1.1989, "step": 454 }, { "epoch": 0.11648, "grad_norm": 2.765625, "learning_rate": 4.8063305178739014e-05, "loss": 1.2343, "step": 455 }, { "epoch": 0.116736, "grad_norm": 2.328125, "learning_rate": 4.8059039331115095e-05, "loss": 1.1503, "step": 456 }, { "epoch": 0.116992, "grad_norm": 2.890625, "learning_rate": 4.805477348349117e-05, "loss": 1.2004, "step": 457 }, { "epoch": 0.117248, "grad_norm": 2.28125, "learning_rate": 4.805050763586725e-05, "loss": 1.1581, "step": 458 }, { "epoch": 0.117504, "grad_norm": 2.65625, "learning_rate": 4.8046241788243324e-05, "loss": 1.2024, "step": 459 }, { "epoch": 0.11776, "grad_norm": 2.59375, "learning_rate": 4.8041975940619405e-05, "loss": 1.2146, "step": 460 }, { "epoch": 0.118016, "grad_norm": 2.421875, "learning_rate": 4.803771009299548e-05, "loss": 1.203, "step": 461 }, { "epoch": 0.118272, "grad_norm": 2.765625, "learning_rate": 4.8033444245371554e-05, "loss": 1.1742, "step": 462 }, { "epoch": 0.118528, "grad_norm": 2.65625, "learning_rate": 4.8029178397747635e-05, "loss": 1.2186, "step": 463 }, { "epoch": 0.118784, "grad_norm": 2.59375, "learning_rate": 4.8024912550123716e-05, "loss": 1.2669, "step": 464 }, { "epoch": 0.11904, "grad_norm": 2.578125, "learning_rate": 4.802064670249979e-05, "loss": 1.1652, "step": 465 }, { "epoch": 0.119296, "grad_norm": 2.53125, "learning_rate": 4.8016380854875864e-05, "loss": 1.2108, "step": 466 }, { "epoch": 0.119552, "grad_norm": 2.546875, "learning_rate": 4.8012115007251945e-05, "loss": 1.1808, "step": 467 }, { "epoch": 0.119808, "grad_norm": 3.0625, "learning_rate": 4.800784915962802e-05, "loss": 1.1963, "step": 468 }, { "epoch": 0.120064, "grad_norm": 2.765625, "learning_rate": 4.8003583312004094e-05, "loss": 1.2297, "step": 469 }, { "epoch": 0.12032, "grad_norm": 2.703125, "learning_rate": 4.7999317464380175e-05, "loss": 1.2167, "step": 470 }, { "epoch": 0.120576, "grad_norm": 2.890625, "learning_rate": 4.7995051616756256e-05, "loss": 1.1687, "step": 471 }, { "epoch": 0.120832, "grad_norm": 2.546875, "learning_rate": 4.799078576913233e-05, "loss": 1.1696, "step": 472 }, { "epoch": 0.121088, "grad_norm": 3.0, "learning_rate": 4.7986519921508405e-05, "loss": 1.2201, "step": 473 }, { "epoch": 0.121344, "grad_norm": 2.671875, "learning_rate": 4.798225407388448e-05, "loss": 1.1975, "step": 474 }, { "epoch": 0.1216, "grad_norm": 2.75, "learning_rate": 4.797798822626056e-05, "loss": 1.1767, "step": 475 }, { "epoch": 0.121856, "grad_norm": 2.546875, "learning_rate": 4.7973722378636634e-05, "loss": 1.2076, "step": 476 }, { "epoch": 0.122112, "grad_norm": 2.875, "learning_rate": 4.7969456531012715e-05, "loss": 1.212, "step": 477 }, { "epoch": 0.122368, "grad_norm": 2.5, "learning_rate": 4.7965190683388796e-05, "loss": 1.1181, "step": 478 }, { "epoch": 0.122624, "grad_norm": 2.34375, "learning_rate": 4.796092483576487e-05, "loss": 1.2206, "step": 479 }, { "epoch": 0.12288, "grad_norm": 2.828125, "learning_rate": 4.7956658988140945e-05, "loss": 1.1415, "step": 480 }, { "epoch": 0.123136, "grad_norm": 2.578125, "learning_rate": 4.795239314051702e-05, "loss": 1.1652, "step": 481 }, { "epoch": 0.123392, "grad_norm": 2.46875, "learning_rate": 4.79481272928931e-05, "loss": 1.1567, "step": 482 }, { "epoch": 0.123648, "grad_norm": 2.984375, "learning_rate": 4.794386144526918e-05, "loss": 1.2082, "step": 483 }, { "epoch": 0.123904, "grad_norm": 2.671875, "learning_rate": 4.7939595597645255e-05, "loss": 1.1374, "step": 484 }, { "epoch": 0.12416, "grad_norm": 2.703125, "learning_rate": 4.793532975002133e-05, "loss": 1.1723, "step": 485 }, { "epoch": 0.124416, "grad_norm": 2.78125, "learning_rate": 4.793106390239741e-05, "loss": 1.1584, "step": 486 }, { "epoch": 0.124672, "grad_norm": 3.09375, "learning_rate": 4.7926798054773485e-05, "loss": 1.1791, "step": 487 }, { "epoch": 0.124928, "grad_norm": 2.6875, "learning_rate": 4.792253220714956e-05, "loss": 1.1432, "step": 488 }, { "epoch": 0.125184, "grad_norm": 2.625, "learning_rate": 4.791826635952564e-05, "loss": 1.17, "step": 489 }, { "epoch": 0.12544, "grad_norm": 2.984375, "learning_rate": 4.791400051190172e-05, "loss": 1.1851, "step": 490 }, { "epoch": 0.125696, "grad_norm": 2.828125, "learning_rate": 4.7909734664277796e-05, "loss": 1.1523, "step": 491 }, { "epoch": 0.125952, "grad_norm": 2.84375, "learning_rate": 4.790546881665387e-05, "loss": 1.1821, "step": 492 }, { "epoch": 0.126208, "grad_norm": 3.28125, "learning_rate": 4.790120296902995e-05, "loss": 1.2014, "step": 493 }, { "epoch": 0.126464, "grad_norm": 2.734375, "learning_rate": 4.7896937121406025e-05, "loss": 1.2193, "step": 494 }, { "epoch": 0.12672, "grad_norm": 2.703125, "learning_rate": 4.78926712737821e-05, "loss": 1.1866, "step": 495 }, { "epoch": 0.126976, "grad_norm": 2.890625, "learning_rate": 4.788840542615818e-05, "loss": 1.1713, "step": 496 }, { "epoch": 0.127232, "grad_norm": 2.84375, "learning_rate": 4.788413957853426e-05, "loss": 1.1778, "step": 497 }, { "epoch": 0.127488, "grad_norm": 2.546875, "learning_rate": 4.7879873730910336e-05, "loss": 1.1478, "step": 498 }, { "epoch": 0.127744, "grad_norm": 2.453125, "learning_rate": 4.787560788328641e-05, "loss": 1.1695, "step": 499 }, { "epoch": 0.128, "grad_norm": 2.640625, "learning_rate": 4.7871342035662484e-05, "loss": 1.1644, "step": 500 }, { "epoch": 0.128256, "grad_norm": 2.671875, "learning_rate": 4.7867076188038565e-05, "loss": 1.1625, "step": 501 }, { "epoch": 0.128512, "grad_norm": 2.875, "learning_rate": 4.7862810340414646e-05, "loss": 1.1323, "step": 502 }, { "epoch": 0.128768, "grad_norm": 2.859375, "learning_rate": 4.785854449279072e-05, "loss": 1.2053, "step": 503 }, { "epoch": 0.129024, "grad_norm": 2.4375, "learning_rate": 4.7854278645166795e-05, "loss": 1.1687, "step": 504 }, { "epoch": 0.12928, "grad_norm": 2.65625, "learning_rate": 4.7850012797542876e-05, "loss": 1.1676, "step": 505 }, { "epoch": 0.129536, "grad_norm": 2.65625, "learning_rate": 4.784574694991895e-05, "loss": 1.1573, "step": 506 }, { "epoch": 0.129792, "grad_norm": 2.6875, "learning_rate": 4.7841481102295024e-05, "loss": 1.1496, "step": 507 }, { "epoch": 0.130048, "grad_norm": 2.3125, "learning_rate": 4.7837215254671106e-05, "loss": 1.1821, "step": 508 }, { "epoch": 0.130304, "grad_norm": 2.984375, "learning_rate": 4.7832949407047187e-05, "loss": 1.1726, "step": 509 }, { "epoch": 0.13056, "grad_norm": 2.578125, "learning_rate": 4.782868355942326e-05, "loss": 1.1828, "step": 510 }, { "epoch": 0.130816, "grad_norm": 2.65625, "learning_rate": 4.7824417711799335e-05, "loss": 1.1455, "step": 511 }, { "epoch": 0.131072, "grad_norm": 2.71875, "learning_rate": 4.7820151864175416e-05, "loss": 1.1556, "step": 512 }, { "epoch": 0.131328, "grad_norm": 2.65625, "learning_rate": 4.781588601655149e-05, "loss": 1.1594, "step": 513 }, { "epoch": 0.131584, "grad_norm": 3.234375, "learning_rate": 4.7811620168927565e-05, "loss": 1.1747, "step": 514 }, { "epoch": 0.13184, "grad_norm": 2.9375, "learning_rate": 4.7807354321303646e-05, "loss": 1.1451, "step": 515 }, { "epoch": 0.132096, "grad_norm": 2.65625, "learning_rate": 4.780308847367973e-05, "loss": 1.1487, "step": 516 }, { "epoch": 0.132352, "grad_norm": 3.21875, "learning_rate": 4.77988226260558e-05, "loss": 1.2026, "step": 517 }, { "epoch": 0.132608, "grad_norm": 2.4375, "learning_rate": 4.7794556778431875e-05, "loss": 1.1329, "step": 518 }, { "epoch": 0.132864, "grad_norm": 3.046875, "learning_rate": 4.779029093080795e-05, "loss": 1.1144, "step": 519 }, { "epoch": 0.13312, "grad_norm": 2.65625, "learning_rate": 4.778602508318403e-05, "loss": 1.1052, "step": 520 }, { "epoch": 0.133376, "grad_norm": 3.171875, "learning_rate": 4.778175923556011e-05, "loss": 1.1138, "step": 521 }, { "epoch": 0.133632, "grad_norm": 2.65625, "learning_rate": 4.7777493387936186e-05, "loss": 1.156, "step": 522 }, { "epoch": 0.133888, "grad_norm": 2.84375, "learning_rate": 4.777322754031226e-05, "loss": 1.1496, "step": 523 }, { "epoch": 0.134144, "grad_norm": 2.96875, "learning_rate": 4.776896169268834e-05, "loss": 1.1275, "step": 524 }, { "epoch": 0.1344, "grad_norm": 2.609375, "learning_rate": 4.7764695845064415e-05, "loss": 1.1242, "step": 525 }, { "epoch": 0.134656, "grad_norm": 2.890625, "learning_rate": 4.776042999744049e-05, "loss": 1.1725, "step": 526 }, { "epoch": 0.134912, "grad_norm": 3.15625, "learning_rate": 4.775616414981657e-05, "loss": 1.1613, "step": 527 }, { "epoch": 0.135168, "grad_norm": 2.875, "learning_rate": 4.775189830219265e-05, "loss": 1.1712, "step": 528 }, { "epoch": 0.135424, "grad_norm": 2.515625, "learning_rate": 4.7747632454568726e-05, "loss": 1.1165, "step": 529 }, { "epoch": 0.13568, "grad_norm": 2.4375, "learning_rate": 4.77433666069448e-05, "loss": 1.1593, "step": 530 }, { "epoch": 0.135936, "grad_norm": 3.203125, "learning_rate": 4.773910075932088e-05, "loss": 1.1183, "step": 531 }, { "epoch": 0.136192, "grad_norm": 2.828125, "learning_rate": 4.7734834911696956e-05, "loss": 1.094, "step": 532 }, { "epoch": 0.136448, "grad_norm": 2.78125, "learning_rate": 4.773056906407303e-05, "loss": 1.1586, "step": 533 }, { "epoch": 0.136704, "grad_norm": 3.1875, "learning_rate": 4.772630321644911e-05, "loss": 1.1353, "step": 534 }, { "epoch": 0.13696, "grad_norm": 2.609375, "learning_rate": 4.772203736882519e-05, "loss": 1.1287, "step": 535 }, { "epoch": 0.137216, "grad_norm": 2.8125, "learning_rate": 4.7717771521201266e-05, "loss": 1.1246, "step": 536 }, { "epoch": 0.137472, "grad_norm": 2.59375, "learning_rate": 4.771350567357734e-05, "loss": 1.1722, "step": 537 }, { "epoch": 0.137728, "grad_norm": 2.5625, "learning_rate": 4.7709239825953415e-05, "loss": 1.1104, "step": 538 }, { "epoch": 0.137984, "grad_norm": 3.1875, "learning_rate": 4.7704973978329496e-05, "loss": 1.1529, "step": 539 }, { "epoch": 0.13824, "grad_norm": 2.6875, "learning_rate": 4.770070813070558e-05, "loss": 1.1282, "step": 540 }, { "epoch": 0.138496, "grad_norm": 2.75, "learning_rate": 4.769644228308165e-05, "loss": 1.1246, "step": 541 }, { "epoch": 0.138752, "grad_norm": 2.796875, "learning_rate": 4.769217643545773e-05, "loss": 1.1092, "step": 542 }, { "epoch": 0.139008, "grad_norm": 2.34375, "learning_rate": 4.7687910587833807e-05, "loss": 1.0936, "step": 543 }, { "epoch": 0.139264, "grad_norm": 3.5, "learning_rate": 4.768364474020988e-05, "loss": 1.0865, "step": 544 }, { "epoch": 0.13952, "grad_norm": 2.859375, "learning_rate": 4.7679378892585955e-05, "loss": 1.11, "step": 545 }, { "epoch": 0.139776, "grad_norm": 2.59375, "learning_rate": 4.7675113044962036e-05, "loss": 1.1452, "step": 546 }, { "epoch": 0.140032, "grad_norm": 2.796875, "learning_rate": 4.767084719733812e-05, "loss": 1.1198, "step": 547 }, { "epoch": 0.140288, "grad_norm": 2.953125, "learning_rate": 4.766658134971419e-05, "loss": 1.0723, "step": 548 }, { "epoch": 0.140544, "grad_norm": 2.84375, "learning_rate": 4.7662315502090266e-05, "loss": 1.0745, "step": 549 }, { "epoch": 0.1408, "grad_norm": 2.765625, "learning_rate": 4.765804965446635e-05, "loss": 1.1535, "step": 550 }, { "epoch": 0.141056, "grad_norm": 2.671875, "learning_rate": 4.765378380684242e-05, "loss": 1.114, "step": 551 }, { "epoch": 0.141312, "grad_norm": 2.921875, "learning_rate": 4.7649517959218495e-05, "loss": 1.1597, "step": 552 }, { "epoch": 0.141568, "grad_norm": 3.109375, "learning_rate": 4.7645252111594576e-05, "loss": 1.1561, "step": 553 }, { "epoch": 0.141824, "grad_norm": 2.796875, "learning_rate": 4.764098626397066e-05, "loss": 1.0907, "step": 554 }, { "epoch": 0.14208, "grad_norm": 2.765625, "learning_rate": 4.763672041634673e-05, "loss": 1.1042, "step": 555 }, { "epoch": 0.142336, "grad_norm": 2.921875, "learning_rate": 4.7632454568722806e-05, "loss": 1.1243, "step": 556 }, { "epoch": 0.142592, "grad_norm": 2.890625, "learning_rate": 4.762818872109888e-05, "loss": 1.1019, "step": 557 }, { "epoch": 0.142848, "grad_norm": 3.25, "learning_rate": 4.762392287347496e-05, "loss": 1.0956, "step": 558 }, { "epoch": 0.143104, "grad_norm": 2.84375, "learning_rate": 4.761965702585104e-05, "loss": 1.0961, "step": 559 }, { "epoch": 0.14336, "grad_norm": 2.859375, "learning_rate": 4.7615391178227116e-05, "loss": 1.1031, "step": 560 }, { "epoch": 0.143616, "grad_norm": 2.96875, "learning_rate": 4.76111253306032e-05, "loss": 1.1259, "step": 561 }, { "epoch": 0.143872, "grad_norm": 2.421875, "learning_rate": 4.760685948297927e-05, "loss": 1.1205, "step": 562 }, { "epoch": 0.144128, "grad_norm": 3.140625, "learning_rate": 4.7602593635355346e-05, "loss": 1.0901, "step": 563 }, { "epoch": 0.144384, "grad_norm": 2.59375, "learning_rate": 4.759832778773142e-05, "loss": 1.1116, "step": 564 }, { "epoch": 0.14464, "grad_norm": 2.703125, "learning_rate": 4.75940619401075e-05, "loss": 1.0722, "step": 565 }, { "epoch": 0.144896, "grad_norm": 3.140625, "learning_rate": 4.758979609248358e-05, "loss": 1.0947, "step": 566 }, { "epoch": 0.145152, "grad_norm": 3.015625, "learning_rate": 4.758553024485966e-05, "loss": 1.1324, "step": 567 }, { "epoch": 0.145408, "grad_norm": 2.625, "learning_rate": 4.758126439723573e-05, "loss": 1.0917, "step": 568 }, { "epoch": 0.145664, "grad_norm": 2.8125, "learning_rate": 4.757699854961181e-05, "loss": 1.0916, "step": 569 }, { "epoch": 0.14592, "grad_norm": 2.859375, "learning_rate": 4.7572732701987886e-05, "loss": 1.1307, "step": 570 }, { "epoch": 0.146176, "grad_norm": 2.421875, "learning_rate": 4.756846685436396e-05, "loss": 1.1125, "step": 571 }, { "epoch": 0.146432, "grad_norm": 2.8125, "learning_rate": 4.756420100674004e-05, "loss": 1.0905, "step": 572 }, { "epoch": 0.146688, "grad_norm": 2.78125, "learning_rate": 4.755993515911612e-05, "loss": 1.0652, "step": 573 }, { "epoch": 0.146944, "grad_norm": 2.421875, "learning_rate": 4.75556693114922e-05, "loss": 1.1072, "step": 574 }, { "epoch": 0.1472, "grad_norm": 2.84375, "learning_rate": 4.755140346386827e-05, "loss": 1.0555, "step": 575 }, { "epoch": 0.147456, "grad_norm": 2.890625, "learning_rate": 4.754713761624435e-05, "loss": 1.0561, "step": 576 }, { "epoch": 0.147712, "grad_norm": 3.125, "learning_rate": 4.7542871768620426e-05, "loss": 1.0716, "step": 577 }, { "epoch": 0.147968, "grad_norm": 2.59375, "learning_rate": 4.75386059209965e-05, "loss": 1.0848, "step": 578 }, { "epoch": 0.148224, "grad_norm": 2.984375, "learning_rate": 4.753434007337258e-05, "loss": 1.0966, "step": 579 }, { "epoch": 0.14848, "grad_norm": 2.84375, "learning_rate": 4.753007422574866e-05, "loss": 1.1057, "step": 580 }, { "epoch": 0.148736, "grad_norm": 2.9375, "learning_rate": 4.752580837812474e-05, "loss": 1.0805, "step": 581 }, { "epoch": 0.148992, "grad_norm": 2.9375, "learning_rate": 4.752154253050081e-05, "loss": 1.0888, "step": 582 }, { "epoch": 0.149248, "grad_norm": 3.046875, "learning_rate": 4.7517276682876886e-05, "loss": 1.0826, "step": 583 }, { "epoch": 0.149504, "grad_norm": 2.6875, "learning_rate": 4.751301083525297e-05, "loss": 1.1176, "step": 584 }, { "epoch": 0.14976, "grad_norm": 2.640625, "learning_rate": 4.750874498762905e-05, "loss": 1.0937, "step": 585 }, { "epoch": 0.150016, "grad_norm": 2.9375, "learning_rate": 4.750447914000512e-05, "loss": 1.0707, "step": 586 }, { "epoch": 0.150272, "grad_norm": 2.5625, "learning_rate": 4.7500213292381196e-05, "loss": 1.0484, "step": 587 }, { "epoch": 0.150528, "grad_norm": 2.734375, "learning_rate": 4.749594744475728e-05, "loss": 1.0829, "step": 588 }, { "epoch": 0.150784, "grad_norm": 2.8125, "learning_rate": 4.749168159713335e-05, "loss": 1.0793, "step": 589 }, { "epoch": 0.15104, "grad_norm": 2.640625, "learning_rate": 4.7487415749509426e-05, "loss": 1.0851, "step": 590 }, { "epoch": 0.151296, "grad_norm": 2.671875, "learning_rate": 4.748314990188551e-05, "loss": 1.0708, "step": 591 }, { "epoch": 0.151552, "grad_norm": 2.546875, "learning_rate": 4.747888405426159e-05, "loss": 1.0972, "step": 592 }, { "epoch": 0.151808, "grad_norm": 2.625, "learning_rate": 4.747461820663766e-05, "loss": 1.0678, "step": 593 }, { "epoch": 0.152064, "grad_norm": 2.515625, "learning_rate": 4.7470352359013736e-05, "loss": 1.0392, "step": 594 }, { "epoch": 0.15232, "grad_norm": 2.84375, "learning_rate": 4.746608651138982e-05, "loss": 1.0581, "step": 595 }, { "epoch": 0.152576, "grad_norm": 2.859375, "learning_rate": 4.746182066376589e-05, "loss": 1.0928, "step": 596 }, { "epoch": 0.152832, "grad_norm": 2.75, "learning_rate": 4.7457554816141966e-05, "loss": 1.022, "step": 597 }, { "epoch": 0.153088, "grad_norm": 2.96875, "learning_rate": 4.745328896851805e-05, "loss": 1.0889, "step": 598 }, { "epoch": 0.153344, "grad_norm": 2.78125, "learning_rate": 4.744902312089413e-05, "loss": 1.0376, "step": 599 }, { "epoch": 0.1536, "grad_norm": 2.6875, "learning_rate": 4.74447572732702e-05, "loss": 1.0898, "step": 600 }, { "epoch": 0.153856, "grad_norm": 2.828125, "learning_rate": 4.7440491425646277e-05, "loss": 1.0821, "step": 601 }, { "epoch": 0.154112, "grad_norm": 2.53125, "learning_rate": 4.743622557802235e-05, "loss": 1.0557, "step": 602 }, { "epoch": 0.154368, "grad_norm": 3.171875, "learning_rate": 4.743195973039843e-05, "loss": 1.0831, "step": 603 }, { "epoch": 0.154624, "grad_norm": 2.546875, "learning_rate": 4.742769388277451e-05, "loss": 1.0406, "step": 604 }, { "epoch": 0.15488, "grad_norm": 2.671875, "learning_rate": 4.742342803515059e-05, "loss": 1.0452, "step": 605 }, { "epoch": 0.155136, "grad_norm": 2.90625, "learning_rate": 4.741916218752666e-05, "loss": 1.0851, "step": 606 }, { "epoch": 0.155392, "grad_norm": 2.5625, "learning_rate": 4.741489633990274e-05, "loss": 1.0612, "step": 607 }, { "epoch": 0.155648, "grad_norm": 2.875, "learning_rate": 4.741063049227882e-05, "loss": 1.0837, "step": 608 }, { "epoch": 0.155904, "grad_norm": 2.859375, "learning_rate": 4.740636464465489e-05, "loss": 1.0559, "step": 609 }, { "epoch": 0.15616, "grad_norm": 2.75, "learning_rate": 4.740209879703097e-05, "loss": 1.0843, "step": 610 }, { "epoch": 0.156416, "grad_norm": 2.609375, "learning_rate": 4.739783294940705e-05, "loss": 1.104, "step": 611 }, { "epoch": 0.156672, "grad_norm": 2.953125, "learning_rate": 4.739356710178313e-05, "loss": 1.0977, "step": 612 }, { "epoch": 0.156928, "grad_norm": 2.90625, "learning_rate": 4.73893012541592e-05, "loss": 1.099, "step": 613 }, { "epoch": 0.157184, "grad_norm": 2.78125, "learning_rate": 4.738503540653528e-05, "loss": 1.0176, "step": 614 }, { "epoch": 0.15744, "grad_norm": 2.953125, "learning_rate": 4.738076955891136e-05, "loss": 1.0127, "step": 615 }, { "epoch": 0.157696, "grad_norm": 3.140625, "learning_rate": 4.737650371128743e-05, "loss": 1.0515, "step": 616 }, { "epoch": 0.157952, "grad_norm": 2.59375, "learning_rate": 4.737223786366351e-05, "loss": 1.1335, "step": 617 }, { "epoch": 0.158208, "grad_norm": 2.84375, "learning_rate": 4.736797201603959e-05, "loss": 1.0904, "step": 618 }, { "epoch": 0.158464, "grad_norm": 2.828125, "learning_rate": 4.736370616841567e-05, "loss": 1.061, "step": 619 }, { "epoch": 0.15872, "grad_norm": 2.796875, "learning_rate": 4.735944032079174e-05, "loss": 1.091, "step": 620 }, { "epoch": 0.158976, "grad_norm": 3.0, "learning_rate": 4.7355174473167816e-05, "loss": 1.0191, "step": 621 }, { "epoch": 0.159232, "grad_norm": 2.828125, "learning_rate": 4.73509086255439e-05, "loss": 1.0931, "step": 622 }, { "epoch": 0.159488, "grad_norm": 2.609375, "learning_rate": 4.734664277791998e-05, "loss": 1.0844, "step": 623 }, { "epoch": 0.159744, "grad_norm": 2.984375, "learning_rate": 4.734237693029605e-05, "loss": 1.073, "step": 624 }, { "epoch": 0.16, "grad_norm": 3.0625, "learning_rate": 4.7338111082672134e-05, "loss": 1.0952, "step": 625 }, { "epoch": 0.160256, "grad_norm": 2.765625, "learning_rate": 4.733384523504821e-05, "loss": 1.0517, "step": 626 }, { "epoch": 0.160512, "grad_norm": 2.703125, "learning_rate": 4.732957938742428e-05, "loss": 1.0576, "step": 627 }, { "epoch": 0.160768, "grad_norm": 3.015625, "learning_rate": 4.7325313539800356e-05, "loss": 1.0528, "step": 628 }, { "epoch": 0.161024, "grad_norm": 3.0, "learning_rate": 4.732104769217644e-05, "loss": 1.0443, "step": 629 }, { "epoch": 0.16128, "grad_norm": 2.625, "learning_rate": 4.731678184455252e-05, "loss": 1.0563, "step": 630 }, { "epoch": 0.161536, "grad_norm": 2.734375, "learning_rate": 4.731251599692859e-05, "loss": 1.033, "step": 631 }, { "epoch": 0.161792, "grad_norm": 2.765625, "learning_rate": 4.730825014930467e-05, "loss": 1.032, "step": 632 }, { "epoch": 0.162048, "grad_norm": 2.78125, "learning_rate": 4.730398430168075e-05, "loss": 1.0593, "step": 633 }, { "epoch": 0.162304, "grad_norm": 2.9375, "learning_rate": 4.729971845405682e-05, "loss": 1.0544, "step": 634 }, { "epoch": 0.16256, "grad_norm": 2.75, "learning_rate": 4.7295452606432896e-05, "loss": 1.0359, "step": 635 }, { "epoch": 0.162816, "grad_norm": 2.921875, "learning_rate": 4.729118675880898e-05, "loss": 1.0893, "step": 636 }, { "epoch": 0.163072, "grad_norm": 2.984375, "learning_rate": 4.728692091118506e-05, "loss": 1.0746, "step": 637 }, { "epoch": 0.163328, "grad_norm": 2.890625, "learning_rate": 4.728265506356113e-05, "loss": 1.0457, "step": 638 }, { "epoch": 0.163584, "grad_norm": 3.109375, "learning_rate": 4.727838921593721e-05, "loss": 1.092, "step": 639 }, { "epoch": 0.16384, "grad_norm": 2.75, "learning_rate": 4.727412336831328e-05, "loss": 1.0607, "step": 640 }, { "epoch": 0.164096, "grad_norm": 2.765625, "learning_rate": 4.726985752068936e-05, "loss": 1.0339, "step": 641 }, { "epoch": 0.164352, "grad_norm": 3.0625, "learning_rate": 4.7265591673065443e-05, "loss": 1.0298, "step": 642 }, { "epoch": 0.164608, "grad_norm": 2.890625, "learning_rate": 4.726132582544152e-05, "loss": 1.0336, "step": 643 }, { "epoch": 0.164864, "grad_norm": 2.796875, "learning_rate": 4.72570599778176e-05, "loss": 1.0617, "step": 644 }, { "epoch": 0.16512, "grad_norm": 3.0, "learning_rate": 4.725279413019367e-05, "loss": 1.0389, "step": 645 }, { "epoch": 0.165376, "grad_norm": 2.9375, "learning_rate": 4.724852828256975e-05, "loss": 1.0635, "step": 646 }, { "epoch": 0.165632, "grad_norm": 2.75, "learning_rate": 4.724426243494582e-05, "loss": 1.0387, "step": 647 }, { "epoch": 0.165888, "grad_norm": 3.125, "learning_rate": 4.72399965873219e-05, "loss": 1.0478, "step": 648 }, { "epoch": 0.166144, "grad_norm": 3.203125, "learning_rate": 4.7235730739697984e-05, "loss": 1.0675, "step": 649 }, { "epoch": 0.1664, "grad_norm": 2.421875, "learning_rate": 4.723146489207406e-05, "loss": 1.0358, "step": 650 }, { "epoch": 0.166656, "grad_norm": 3.234375, "learning_rate": 4.722719904445013e-05, "loss": 1.0367, "step": 651 }, { "epoch": 0.166912, "grad_norm": 3.5625, "learning_rate": 4.722293319682621e-05, "loss": 1.0396, "step": 652 }, { "epoch": 0.167168, "grad_norm": 3.109375, "learning_rate": 4.721866734920229e-05, "loss": 0.9982, "step": 653 }, { "epoch": 0.167424, "grad_norm": 3.15625, "learning_rate": 4.721440150157836e-05, "loss": 1.0896, "step": 654 }, { "epoch": 0.16768, "grad_norm": 3.671875, "learning_rate": 4.721013565395444e-05, "loss": 1.0533, "step": 655 }, { "epoch": 0.167936, "grad_norm": 3.1875, "learning_rate": 4.7205869806330524e-05, "loss": 1.0219, "step": 656 }, { "epoch": 0.168192, "grad_norm": 2.953125, "learning_rate": 4.72016039587066e-05, "loss": 1.0104, "step": 657 }, { "epoch": 0.168448, "grad_norm": 3.296875, "learning_rate": 4.719733811108267e-05, "loss": 1.0534, "step": 658 }, { "epoch": 0.168704, "grad_norm": 3.140625, "learning_rate": 4.7193072263458753e-05, "loss": 1.0153, "step": 659 }, { "epoch": 0.16896, "grad_norm": 2.84375, "learning_rate": 4.718880641583483e-05, "loss": 1.0059, "step": 660 }, { "epoch": 0.169216, "grad_norm": 3.015625, "learning_rate": 4.718454056821091e-05, "loss": 1.0332, "step": 661 }, { "epoch": 0.169472, "grad_norm": 3.15625, "learning_rate": 4.718027472058698e-05, "loss": 1.0622, "step": 662 }, { "epoch": 0.169728, "grad_norm": 2.984375, "learning_rate": 4.7176008872963064e-05, "loss": 1.0039, "step": 663 }, { "epoch": 0.169984, "grad_norm": 2.8125, "learning_rate": 4.717174302533914e-05, "loss": 1.036, "step": 664 }, { "epoch": 0.17024, "grad_norm": 2.96875, "learning_rate": 4.716747717771521e-05, "loss": 1.038, "step": 665 }, { "epoch": 0.170496, "grad_norm": 3.234375, "learning_rate": 4.716321133009129e-05, "loss": 1.0608, "step": 666 }, { "epoch": 0.170752, "grad_norm": 2.84375, "learning_rate": 4.715894548246737e-05, "loss": 1.0772, "step": 667 }, { "epoch": 0.171008, "grad_norm": 2.796875, "learning_rate": 4.715467963484345e-05, "loss": 1.0124, "step": 668 }, { "epoch": 0.171264, "grad_norm": 2.875, "learning_rate": 4.715041378721952e-05, "loss": 1.0043, "step": 669 }, { "epoch": 0.17152, "grad_norm": 3.453125, "learning_rate": 4.71461479395956e-05, "loss": 1.0233, "step": 670 }, { "epoch": 0.171776, "grad_norm": 3.015625, "learning_rate": 4.714188209197168e-05, "loss": 1.0378, "step": 671 }, { "epoch": 0.172032, "grad_norm": 3.1875, "learning_rate": 4.713761624434775e-05, "loss": 1.0391, "step": 672 }, { "epoch": 0.172288, "grad_norm": 3.109375, "learning_rate": 4.713335039672383e-05, "loss": 1.0243, "step": 673 }, { "epoch": 0.172544, "grad_norm": 2.765625, "learning_rate": 4.712908454909991e-05, "loss": 1.0418, "step": 674 }, { "epoch": 0.1728, "grad_norm": 3.046875, "learning_rate": 4.712481870147599e-05, "loss": 0.9967, "step": 675 }, { "epoch": 0.173056, "grad_norm": 3.125, "learning_rate": 4.7120552853852063e-05, "loss": 1.029, "step": 676 }, { "epoch": 0.173312, "grad_norm": 2.84375, "learning_rate": 4.711628700622814e-05, "loss": 1.0238, "step": 677 }, { "epoch": 0.173568, "grad_norm": 3.1875, "learning_rate": 4.711202115860422e-05, "loss": 0.9907, "step": 678 }, { "epoch": 0.173824, "grad_norm": 3.109375, "learning_rate": 4.710775531098029e-05, "loss": 0.9974, "step": 679 }, { "epoch": 0.17408, "grad_norm": 2.765625, "learning_rate": 4.710348946335637e-05, "loss": 1.0259, "step": 680 }, { "epoch": 0.174336, "grad_norm": 3.25, "learning_rate": 4.709922361573245e-05, "loss": 1.0392, "step": 681 }, { "epoch": 0.174592, "grad_norm": 2.875, "learning_rate": 4.709495776810853e-05, "loss": 1.0154, "step": 682 }, { "epoch": 0.174848, "grad_norm": 2.765625, "learning_rate": 4.7090691920484604e-05, "loss": 1.0285, "step": 683 }, { "epoch": 0.175104, "grad_norm": 2.78125, "learning_rate": 4.708642607286068e-05, "loss": 1.0462, "step": 684 }, { "epoch": 0.17536, "grad_norm": 2.796875, "learning_rate": 4.708216022523675e-05, "loss": 1.0417, "step": 685 }, { "epoch": 0.175616, "grad_norm": 2.5, "learning_rate": 4.707789437761283e-05, "loss": 1.0221, "step": 686 }, { "epoch": 0.175872, "grad_norm": 3.0, "learning_rate": 4.7073628529988914e-05, "loss": 0.9965, "step": 687 }, { "epoch": 0.176128, "grad_norm": 2.8125, "learning_rate": 4.706936268236499e-05, "loss": 1.0167, "step": 688 }, { "epoch": 0.176384, "grad_norm": 2.484375, "learning_rate": 4.706509683474106e-05, "loss": 1.0239, "step": 689 }, { "epoch": 0.17664, "grad_norm": 2.9375, "learning_rate": 4.7060830987117144e-05, "loss": 1.0033, "step": 690 }, { "epoch": 0.176896, "grad_norm": 2.921875, "learning_rate": 4.705656513949322e-05, "loss": 1.0442, "step": 691 }, { "epoch": 0.177152, "grad_norm": 2.8125, "learning_rate": 4.705229929186929e-05, "loss": 1.0192, "step": 692 }, { "epoch": 0.177408, "grad_norm": 2.96875, "learning_rate": 4.704803344424537e-05, "loss": 1.0329, "step": 693 }, { "epoch": 0.177664, "grad_norm": 2.890625, "learning_rate": 4.7043767596621454e-05, "loss": 1.0115, "step": 694 }, { "epoch": 0.17792, "grad_norm": 2.765625, "learning_rate": 4.703950174899753e-05, "loss": 0.9813, "step": 695 }, { "epoch": 0.178176, "grad_norm": 2.921875, "learning_rate": 4.70352359013736e-05, "loss": 0.9962, "step": 696 }, { "epoch": 0.178432, "grad_norm": 2.859375, "learning_rate": 4.7030970053749684e-05, "loss": 1.0117, "step": 697 }, { "epoch": 0.178688, "grad_norm": 2.796875, "learning_rate": 4.702670420612576e-05, "loss": 1.0092, "step": 698 }, { "epoch": 0.178944, "grad_norm": 2.8125, "learning_rate": 4.702243835850183e-05, "loss": 1.028, "step": 699 }, { "epoch": 0.1792, "grad_norm": 2.953125, "learning_rate": 4.7018172510877914e-05, "loss": 1.0395, "step": 700 }, { "epoch": 0.179456, "grad_norm": 2.875, "learning_rate": 4.7013906663253995e-05, "loss": 1.016, "step": 701 }, { "epoch": 0.179712, "grad_norm": 2.84375, "learning_rate": 4.700964081563007e-05, "loss": 1.0156, "step": 702 }, { "epoch": 0.179968, "grad_norm": 2.65625, "learning_rate": 4.700537496800614e-05, "loss": 1.0528, "step": 703 }, { "epoch": 0.180224, "grad_norm": 2.78125, "learning_rate": 4.700110912038222e-05, "loss": 1.0129, "step": 704 }, { "epoch": 0.18048, "grad_norm": 2.90625, "learning_rate": 4.69968432727583e-05, "loss": 1.0087, "step": 705 }, { "epoch": 0.180736, "grad_norm": 2.5625, "learning_rate": 4.699257742513438e-05, "loss": 1.0265, "step": 706 }, { "epoch": 0.180992, "grad_norm": 2.90625, "learning_rate": 4.6988311577510454e-05, "loss": 0.9866, "step": 707 }, { "epoch": 0.181248, "grad_norm": 2.734375, "learning_rate": 4.6984045729886535e-05, "loss": 0.9846, "step": 708 }, { "epoch": 0.181504, "grad_norm": 2.921875, "learning_rate": 4.697977988226261e-05, "loss": 0.9859, "step": 709 }, { "epoch": 0.18176, "grad_norm": 2.765625, "learning_rate": 4.697551403463868e-05, "loss": 0.9765, "step": 710 }, { "epoch": 0.182016, "grad_norm": 3.09375, "learning_rate": 4.697124818701476e-05, "loss": 1.0432, "step": 711 }, { "epoch": 0.182272, "grad_norm": 3.5625, "learning_rate": 4.696698233939084e-05, "loss": 0.9856, "step": 712 }, { "epoch": 0.182528, "grad_norm": 2.6875, "learning_rate": 4.696271649176692e-05, "loss": 1.0017, "step": 713 }, { "epoch": 0.182784, "grad_norm": 2.734375, "learning_rate": 4.6958450644142994e-05, "loss": 1.0054, "step": 714 }, { "epoch": 0.18304, "grad_norm": 2.953125, "learning_rate": 4.695418479651907e-05, "loss": 0.9733, "step": 715 }, { "epoch": 0.183296, "grad_norm": 2.96875, "learning_rate": 4.694991894889515e-05, "loss": 0.9473, "step": 716 }, { "epoch": 0.183552, "grad_norm": 2.984375, "learning_rate": 4.6945653101271224e-05, "loss": 1.0048, "step": 717 }, { "epoch": 0.183808, "grad_norm": 3.203125, "learning_rate": 4.69413872536473e-05, "loss": 1.0121, "step": 718 }, { "epoch": 0.184064, "grad_norm": 2.859375, "learning_rate": 4.693712140602338e-05, "loss": 0.9624, "step": 719 }, { "epoch": 0.18432, "grad_norm": 2.953125, "learning_rate": 4.693285555839946e-05, "loss": 0.9657, "step": 720 }, { "epoch": 0.184576, "grad_norm": 3.0625, "learning_rate": 4.6928589710775534e-05, "loss": 0.9657, "step": 721 }, { "epoch": 0.184832, "grad_norm": 3.0, "learning_rate": 4.692432386315161e-05, "loss": 1.0121, "step": 722 }, { "epoch": 0.185088, "grad_norm": 2.625, "learning_rate": 4.692005801552769e-05, "loss": 0.9519, "step": 723 }, { "epoch": 0.185344, "grad_norm": 2.890625, "learning_rate": 4.6915792167903764e-05, "loss": 1.0066, "step": 724 }, { "epoch": 0.1856, "grad_norm": 3.34375, "learning_rate": 4.6911526320279845e-05, "loss": 1.0124, "step": 725 }, { "epoch": 0.185856, "grad_norm": 2.796875, "learning_rate": 4.690726047265592e-05, "loss": 0.9502, "step": 726 }, { "epoch": 0.186112, "grad_norm": 2.6875, "learning_rate": 4.6902994625032e-05, "loss": 1.0253, "step": 727 }, { "epoch": 0.186368, "grad_norm": 3.3125, "learning_rate": 4.6898728777408074e-05, "loss": 0.9477, "step": 728 }, { "epoch": 0.186624, "grad_norm": 2.59375, "learning_rate": 4.689446292978415e-05, "loss": 0.9844, "step": 729 }, { "epoch": 0.18688, "grad_norm": 2.90625, "learning_rate": 4.689019708216022e-05, "loss": 1.0033, "step": 730 }, { "epoch": 0.187136, "grad_norm": 3.25, "learning_rate": 4.6885931234536304e-05, "loss": 0.9581, "step": 731 }, { "epoch": 0.187392, "grad_norm": 2.671875, "learning_rate": 4.6881665386912385e-05, "loss": 1.0039, "step": 732 }, { "epoch": 0.187648, "grad_norm": 2.5, "learning_rate": 4.687739953928846e-05, "loss": 0.9984, "step": 733 }, { "epoch": 0.187904, "grad_norm": 2.65625, "learning_rate": 4.6873133691664533e-05, "loss": 0.9676, "step": 734 }, { "epoch": 0.18816, "grad_norm": 2.96875, "learning_rate": 4.6868867844040615e-05, "loss": 1.0037, "step": 735 }, { "epoch": 0.188416, "grad_norm": 3.296875, "learning_rate": 4.686460199641669e-05, "loss": 1.01, "step": 736 }, { "epoch": 0.188672, "grad_norm": 2.703125, "learning_rate": 4.686033614879276e-05, "loss": 0.9934, "step": 737 }, { "epoch": 0.188928, "grad_norm": 2.75, "learning_rate": 4.6856070301168844e-05, "loss": 0.9992, "step": 738 }, { "epoch": 0.189184, "grad_norm": 3.375, "learning_rate": 4.6851804453544925e-05, "loss": 0.9767, "step": 739 }, { "epoch": 0.18944, "grad_norm": 2.625, "learning_rate": 4.6847538605921e-05, "loss": 1.003, "step": 740 }, { "epoch": 0.189696, "grad_norm": 2.609375, "learning_rate": 4.6843272758297074e-05, "loss": 0.9985, "step": 741 }, { "epoch": 0.189952, "grad_norm": 2.765625, "learning_rate": 4.6839006910673155e-05, "loss": 0.982, "step": 742 }, { "epoch": 0.190208, "grad_norm": 2.359375, "learning_rate": 4.683474106304923e-05, "loss": 1.0125, "step": 743 }, { "epoch": 0.190464, "grad_norm": 2.859375, "learning_rate": 4.683047521542531e-05, "loss": 1.0059, "step": 744 }, { "epoch": 0.19072, "grad_norm": 2.84375, "learning_rate": 4.6826209367801384e-05, "loss": 0.9404, "step": 745 }, { "epoch": 0.190976, "grad_norm": 2.921875, "learning_rate": 4.6821943520177465e-05, "loss": 0.9485, "step": 746 }, { "epoch": 0.191232, "grad_norm": 2.890625, "learning_rate": 4.681767767255354e-05, "loss": 1.0116, "step": 747 }, { "epoch": 0.191488, "grad_norm": 3.0625, "learning_rate": 4.6813411824929614e-05, "loss": 0.9691, "step": 748 }, { "epoch": 0.191744, "grad_norm": 2.8125, "learning_rate": 4.680914597730569e-05, "loss": 0.9841, "step": 749 }, { "epoch": 0.192, "grad_norm": 2.84375, "learning_rate": 4.680488012968177e-05, "loss": 0.976, "step": 750 }, { "epoch": 0.192256, "grad_norm": 2.671875, "learning_rate": 4.680061428205785e-05, "loss": 0.9733, "step": 751 }, { "epoch": 0.192512, "grad_norm": 2.828125, "learning_rate": 4.6796348434433924e-05, "loss": 0.9303, "step": 752 }, { "epoch": 0.192768, "grad_norm": 2.96875, "learning_rate": 4.679208258681e-05, "loss": 0.8962, "step": 753 }, { "epoch": 0.193024, "grad_norm": 2.796875, "learning_rate": 4.678781673918608e-05, "loss": 0.9606, "step": 754 }, { "epoch": 0.19328, "grad_norm": 2.625, "learning_rate": 4.6783550891562154e-05, "loss": 0.9567, "step": 755 }, { "epoch": 0.193536, "grad_norm": 2.6875, "learning_rate": 4.677928504393823e-05, "loss": 1.009, "step": 756 }, { "epoch": 0.193792, "grad_norm": 3.015625, "learning_rate": 4.677501919631431e-05, "loss": 0.9203, "step": 757 }, { "epoch": 0.194048, "grad_norm": 2.6875, "learning_rate": 4.677075334869039e-05, "loss": 0.9471, "step": 758 }, { "epoch": 0.194304, "grad_norm": 3.046875, "learning_rate": 4.6766487501066465e-05, "loss": 0.9793, "step": 759 }, { "epoch": 0.19456, "grad_norm": 2.90625, "learning_rate": 4.676222165344254e-05, "loss": 0.9236, "step": 760 }, { "epoch": 0.194816, "grad_norm": 3.21875, "learning_rate": 4.675795580581862e-05, "loss": 0.9696, "step": 761 }, { "epoch": 0.195072, "grad_norm": 2.9375, "learning_rate": 4.6753689958194694e-05, "loss": 0.9607, "step": 762 }, { "epoch": 0.195328, "grad_norm": 2.5625, "learning_rate": 4.6749424110570775e-05, "loss": 0.9592, "step": 763 }, { "epoch": 0.195584, "grad_norm": 2.875, "learning_rate": 4.674515826294685e-05, "loss": 0.9702, "step": 764 }, { "epoch": 0.19584, "grad_norm": 2.625, "learning_rate": 4.674089241532293e-05, "loss": 0.9534, "step": 765 }, { "epoch": 0.196096, "grad_norm": 2.828125, "learning_rate": 4.6736626567699005e-05, "loss": 0.9675, "step": 766 }, { "epoch": 0.196352, "grad_norm": 3.03125, "learning_rate": 4.673236072007508e-05, "loss": 0.9604, "step": 767 }, { "epoch": 0.196608, "grad_norm": 2.859375, "learning_rate": 4.6728094872451153e-05, "loss": 0.9541, "step": 768 }, { "epoch": 0.196864, "grad_norm": 3.0, "learning_rate": 4.6723829024827234e-05, "loss": 0.9788, "step": 769 }, { "epoch": 0.19712, "grad_norm": 2.59375, "learning_rate": 4.6719563177203315e-05, "loss": 0.9604, "step": 770 }, { "epoch": 0.197376, "grad_norm": 2.625, "learning_rate": 4.671529732957939e-05, "loss": 0.9715, "step": 771 }, { "epoch": 0.197632, "grad_norm": 2.765625, "learning_rate": 4.671103148195547e-05, "loss": 0.9651, "step": 772 }, { "epoch": 0.197888, "grad_norm": 2.734375, "learning_rate": 4.6706765634331545e-05, "loss": 0.9836, "step": 773 }, { "epoch": 0.198144, "grad_norm": 2.484375, "learning_rate": 4.670249978670762e-05, "loss": 0.9686, "step": 774 }, { "epoch": 0.1984, "grad_norm": 2.640625, "learning_rate": 4.6698233939083694e-05, "loss": 0.9677, "step": 775 }, { "epoch": 0.198656, "grad_norm": 2.984375, "learning_rate": 4.6693968091459775e-05, "loss": 0.967, "step": 776 }, { "epoch": 0.198912, "grad_norm": 2.84375, "learning_rate": 4.6689702243835856e-05, "loss": 0.9454, "step": 777 }, { "epoch": 0.199168, "grad_norm": 3.125, "learning_rate": 4.668543639621193e-05, "loss": 0.9217, "step": 778 }, { "epoch": 0.199424, "grad_norm": 2.953125, "learning_rate": 4.6681170548588004e-05, "loss": 0.946, "step": 779 }, { "epoch": 0.19968, "grad_norm": 2.984375, "learning_rate": 4.6676904700964085e-05, "loss": 0.9581, "step": 780 }, { "epoch": 0.199936, "grad_norm": 2.953125, "learning_rate": 4.667263885334016e-05, "loss": 0.9734, "step": 781 }, { "epoch": 0.200192, "grad_norm": 2.8125, "learning_rate": 4.6668373005716234e-05, "loss": 0.9528, "step": 782 }, { "epoch": 0.200448, "grad_norm": 2.625, "learning_rate": 4.6664107158092315e-05, "loss": 0.954, "step": 783 }, { "epoch": 0.200704, "grad_norm": 2.609375, "learning_rate": 4.6659841310468396e-05, "loss": 0.9757, "step": 784 }, { "epoch": 0.20096, "grad_norm": 3.0625, "learning_rate": 4.665557546284447e-05, "loss": 0.9172, "step": 785 }, { "epoch": 0.201216, "grad_norm": 2.6875, "learning_rate": 4.6651309615220544e-05, "loss": 0.9396, "step": 786 }, { "epoch": 0.201472, "grad_norm": 3.03125, "learning_rate": 4.664704376759662e-05, "loss": 0.9069, "step": 787 }, { "epoch": 0.201728, "grad_norm": 2.84375, "learning_rate": 4.66427779199727e-05, "loss": 0.9471, "step": 788 }, { "epoch": 0.201984, "grad_norm": 2.96875, "learning_rate": 4.663851207234878e-05, "loss": 0.9714, "step": 789 }, { "epoch": 0.20224, "grad_norm": 2.65625, "learning_rate": 4.6634246224724855e-05, "loss": 0.9605, "step": 790 }, { "epoch": 0.202496, "grad_norm": 3.140625, "learning_rate": 4.6629980377100936e-05, "loss": 0.9515, "step": 791 }, { "epoch": 0.202752, "grad_norm": 3.296875, "learning_rate": 4.662571452947701e-05, "loss": 0.9792, "step": 792 }, { "epoch": 0.203008, "grad_norm": 2.78125, "learning_rate": 4.6621448681853085e-05, "loss": 0.9637, "step": 793 }, { "epoch": 0.203264, "grad_norm": 3.0, "learning_rate": 4.661718283422916e-05, "loss": 0.9465, "step": 794 }, { "epoch": 0.20352, "grad_norm": 2.765625, "learning_rate": 4.661291698660524e-05, "loss": 0.9713, "step": 795 }, { "epoch": 0.203776, "grad_norm": 2.703125, "learning_rate": 4.660865113898132e-05, "loss": 0.938, "step": 796 }, { "epoch": 0.204032, "grad_norm": 2.8125, "learning_rate": 4.6604385291357395e-05, "loss": 0.9608, "step": 797 }, { "epoch": 0.204288, "grad_norm": 2.75, "learning_rate": 4.660011944373347e-05, "loss": 0.9672, "step": 798 }, { "epoch": 0.204544, "grad_norm": 2.625, "learning_rate": 4.659585359610955e-05, "loss": 0.8968, "step": 799 }, { "epoch": 0.2048, "grad_norm": 2.625, "learning_rate": 4.6591587748485625e-05, "loss": 0.9664, "step": 800 }, { "epoch": 0.205056, "grad_norm": 2.515625, "learning_rate": 4.65873219008617e-05, "loss": 0.9547, "step": 801 }, { "epoch": 0.205312, "grad_norm": 2.71875, "learning_rate": 4.658305605323778e-05, "loss": 0.9586, "step": 802 }, { "epoch": 0.205568, "grad_norm": 2.875, "learning_rate": 4.657879020561386e-05, "loss": 0.9285, "step": 803 }, { "epoch": 0.205824, "grad_norm": 2.703125, "learning_rate": 4.6574524357989935e-05, "loss": 0.8998, "step": 804 }, { "epoch": 0.20608, "grad_norm": 2.890625, "learning_rate": 4.657025851036601e-05, "loss": 0.9609, "step": 805 }, { "epoch": 0.206336, "grad_norm": 2.9375, "learning_rate": 4.656599266274209e-05, "loss": 0.9251, "step": 806 }, { "epoch": 0.206592, "grad_norm": 2.703125, "learning_rate": 4.6561726815118165e-05, "loss": 1.0036, "step": 807 }, { "epoch": 0.206848, "grad_norm": 2.578125, "learning_rate": 4.6557460967494246e-05, "loss": 0.918, "step": 808 }, { "epoch": 0.207104, "grad_norm": 2.671875, "learning_rate": 4.655319511987032e-05, "loss": 0.9285, "step": 809 }, { "epoch": 0.20736, "grad_norm": 2.359375, "learning_rate": 4.65489292722464e-05, "loss": 0.9383, "step": 810 }, { "epoch": 0.207616, "grad_norm": 2.484375, "learning_rate": 4.6544663424622476e-05, "loss": 0.962, "step": 811 }, { "epoch": 0.207872, "grad_norm": 2.75, "learning_rate": 4.654039757699855e-05, "loss": 0.9247, "step": 812 }, { "epoch": 0.208128, "grad_norm": 2.875, "learning_rate": 4.6536131729374624e-05, "loss": 0.893, "step": 813 }, { "epoch": 0.208384, "grad_norm": 2.390625, "learning_rate": 4.6531865881750705e-05, "loss": 0.909, "step": 814 }, { "epoch": 0.20864, "grad_norm": 2.609375, "learning_rate": 4.6527600034126786e-05, "loss": 0.9071, "step": 815 }, { "epoch": 0.208896, "grad_norm": 2.796875, "learning_rate": 4.652333418650286e-05, "loss": 0.9485, "step": 816 }, { "epoch": 0.209152, "grad_norm": 2.734375, "learning_rate": 4.6519068338878935e-05, "loss": 0.9729, "step": 817 }, { "epoch": 0.209408, "grad_norm": 2.921875, "learning_rate": 4.6514802491255016e-05, "loss": 0.932, "step": 818 }, { "epoch": 0.209664, "grad_norm": 2.859375, "learning_rate": 4.651053664363109e-05, "loss": 0.9597, "step": 819 }, { "epoch": 0.20992, "grad_norm": 2.734375, "learning_rate": 4.6506270796007164e-05, "loss": 0.9527, "step": 820 }, { "epoch": 0.210176, "grad_norm": 2.703125, "learning_rate": 4.6502004948383245e-05, "loss": 0.9685, "step": 821 }, { "epoch": 0.210432, "grad_norm": 2.59375, "learning_rate": 4.6497739100759326e-05, "loss": 0.9665, "step": 822 }, { "epoch": 0.210688, "grad_norm": 3.203125, "learning_rate": 4.64934732531354e-05, "loss": 0.9012, "step": 823 }, { "epoch": 0.210944, "grad_norm": 2.890625, "learning_rate": 4.6489207405511475e-05, "loss": 0.9344, "step": 824 }, { "epoch": 0.2112, "grad_norm": 3.03125, "learning_rate": 4.6484941557887556e-05, "loss": 0.8912, "step": 825 }, { "epoch": 0.211456, "grad_norm": 3.28125, "learning_rate": 4.648067571026363e-05, "loss": 0.9521, "step": 826 }, { "epoch": 0.211712, "grad_norm": 2.359375, "learning_rate": 4.647640986263971e-05, "loss": 0.9134, "step": 827 }, { "epoch": 0.211968, "grad_norm": 2.8125, "learning_rate": 4.6472144015015786e-05, "loss": 0.9404, "step": 828 }, { "epoch": 0.212224, "grad_norm": 2.84375, "learning_rate": 4.6467878167391867e-05, "loss": 0.9372, "step": 829 }, { "epoch": 0.21248, "grad_norm": 2.578125, "learning_rate": 4.646361231976794e-05, "loss": 0.9403, "step": 830 }, { "epoch": 0.212736, "grad_norm": 2.4375, "learning_rate": 4.6459346472144015e-05, "loss": 0.9587, "step": 831 }, { "epoch": 0.212992, "grad_norm": 2.546875, "learning_rate": 4.645508062452009e-05, "loss": 0.8967, "step": 832 }, { "epoch": 0.213248, "grad_norm": 2.578125, "learning_rate": 4.645081477689617e-05, "loss": 0.9115, "step": 833 }, { "epoch": 0.213504, "grad_norm": 2.375, "learning_rate": 4.644654892927225e-05, "loss": 0.9156, "step": 834 }, { "epoch": 0.21376, "grad_norm": 2.421875, "learning_rate": 4.6442283081648326e-05, "loss": 0.9111, "step": 835 }, { "epoch": 0.214016, "grad_norm": 2.328125, "learning_rate": 4.64380172340244e-05, "loss": 0.9633, "step": 836 }, { "epoch": 0.214272, "grad_norm": 2.640625, "learning_rate": 4.643375138640048e-05, "loss": 0.9434, "step": 837 }, { "epoch": 0.214528, "grad_norm": 2.734375, "learning_rate": 4.6429485538776555e-05, "loss": 0.9391, "step": 838 }, { "epoch": 0.214784, "grad_norm": 2.625, "learning_rate": 4.642521969115263e-05, "loss": 0.953, "step": 839 }, { "epoch": 0.21504, "grad_norm": 2.71875, "learning_rate": 4.642095384352871e-05, "loss": 0.9327, "step": 840 }, { "epoch": 0.215296, "grad_norm": 2.8125, "learning_rate": 4.641668799590479e-05, "loss": 0.9473, "step": 841 }, { "epoch": 0.215552, "grad_norm": 2.59375, "learning_rate": 4.6412422148280866e-05, "loss": 0.9374, "step": 842 }, { "epoch": 0.215808, "grad_norm": 2.796875, "learning_rate": 4.640815630065694e-05, "loss": 0.8839, "step": 843 }, { "epoch": 0.216064, "grad_norm": 2.65625, "learning_rate": 4.640389045303302e-05, "loss": 0.9283, "step": 844 }, { "epoch": 0.21632, "grad_norm": 2.765625, "learning_rate": 4.6399624605409096e-05, "loss": 0.9211, "step": 845 }, { "epoch": 0.216576, "grad_norm": 3.171875, "learning_rate": 4.6395358757785177e-05, "loss": 0.9196, "step": 846 }, { "epoch": 0.216832, "grad_norm": 2.8125, "learning_rate": 4.639109291016125e-05, "loss": 0.8719, "step": 847 }, { "epoch": 0.217088, "grad_norm": 2.84375, "learning_rate": 4.638682706253733e-05, "loss": 0.916, "step": 848 }, { "epoch": 0.217344, "grad_norm": 2.75, "learning_rate": 4.6382561214913406e-05, "loss": 0.9521, "step": 849 }, { "epoch": 0.2176, "grad_norm": 3.0, "learning_rate": 4.637829536728948e-05, "loss": 0.896, "step": 850 }, { "epoch": 0.217856, "grad_norm": 2.765625, "learning_rate": 4.6374029519665555e-05, "loss": 0.9073, "step": 851 }, { "epoch": 0.218112, "grad_norm": 3.0, "learning_rate": 4.6369763672041636e-05, "loss": 0.9213, "step": 852 }, { "epoch": 0.218368, "grad_norm": 3.078125, "learning_rate": 4.636549782441772e-05, "loss": 0.8887, "step": 853 }, { "epoch": 0.218624, "grad_norm": 3.1875, "learning_rate": 4.636123197679379e-05, "loss": 0.9401, "step": 854 }, { "epoch": 0.21888, "grad_norm": 3.03125, "learning_rate": 4.635696612916987e-05, "loss": 0.9456, "step": 855 }, { "epoch": 0.219136, "grad_norm": 2.875, "learning_rate": 4.6352700281545946e-05, "loss": 0.93, "step": 856 }, { "epoch": 0.219392, "grad_norm": 2.796875, "learning_rate": 4.634843443392202e-05, "loss": 0.8592, "step": 857 }, { "epoch": 0.219648, "grad_norm": 2.40625, "learning_rate": 4.6344168586298095e-05, "loss": 0.9317, "step": 858 }, { "epoch": 0.219904, "grad_norm": 2.921875, "learning_rate": 4.6339902738674176e-05, "loss": 0.9288, "step": 859 }, { "epoch": 0.22016, "grad_norm": 2.765625, "learning_rate": 4.633563689105026e-05, "loss": 0.862, "step": 860 }, { "epoch": 0.220416, "grad_norm": 2.8125, "learning_rate": 4.633137104342633e-05, "loss": 0.9135, "step": 861 }, { "epoch": 0.220672, "grad_norm": 2.78125, "learning_rate": 4.6327105195802405e-05, "loss": 0.9251, "step": 862 }, { "epoch": 0.220928, "grad_norm": 2.9375, "learning_rate": 4.6322839348178487e-05, "loss": 0.9043, "step": 863 }, { "epoch": 0.221184, "grad_norm": 2.640625, "learning_rate": 4.631857350055456e-05, "loss": 0.883, "step": 864 }, { "epoch": 0.22144, "grad_norm": 3.0, "learning_rate": 4.631430765293064e-05, "loss": 0.9097, "step": 865 }, { "epoch": 0.221696, "grad_norm": 2.875, "learning_rate": 4.6310041805306716e-05, "loss": 0.9406, "step": 866 }, { "epoch": 0.221952, "grad_norm": 2.703125, "learning_rate": 4.63057759576828e-05, "loss": 0.9144, "step": 867 }, { "epoch": 0.222208, "grad_norm": 3.109375, "learning_rate": 4.630151011005887e-05, "loss": 0.8875, "step": 868 }, { "epoch": 0.222464, "grad_norm": 2.59375, "learning_rate": 4.6297244262434946e-05, "loss": 0.925, "step": 869 }, { "epoch": 0.22272, "grad_norm": 2.609375, "learning_rate": 4.629297841481103e-05, "loss": 0.8806, "step": 870 }, { "epoch": 0.222976, "grad_norm": 2.8125, "learning_rate": 4.62887125671871e-05, "loss": 0.8936, "step": 871 }, { "epoch": 0.223232, "grad_norm": 2.859375, "learning_rate": 4.628444671956318e-05, "loss": 0.892, "step": 872 }, { "epoch": 0.223488, "grad_norm": 3.1875, "learning_rate": 4.6280180871939256e-05, "loss": 0.9039, "step": 873 }, { "epoch": 0.223744, "grad_norm": 2.75, "learning_rate": 4.627591502431534e-05, "loss": 0.857, "step": 874 }, { "epoch": 0.224, "grad_norm": 2.734375, "learning_rate": 4.627164917669141e-05, "loss": 0.9158, "step": 875 }, { "epoch": 0.224256, "grad_norm": 2.734375, "learning_rate": 4.6267383329067486e-05, "loss": 0.9105, "step": 876 }, { "epoch": 0.224512, "grad_norm": 2.78125, "learning_rate": 4.626311748144356e-05, "loss": 0.9084, "step": 877 }, { "epoch": 0.224768, "grad_norm": 2.984375, "learning_rate": 4.625885163381964e-05, "loss": 0.9195, "step": 878 }, { "epoch": 0.225024, "grad_norm": 2.75, "learning_rate": 4.625458578619572e-05, "loss": 0.9086, "step": 879 }, { "epoch": 0.22528, "grad_norm": 2.90625, "learning_rate": 4.6250319938571796e-05, "loss": 0.9117, "step": 880 }, { "epoch": 0.225536, "grad_norm": 3.125, "learning_rate": 4.624605409094787e-05, "loss": 0.8896, "step": 881 }, { "epoch": 0.225792, "grad_norm": 2.859375, "learning_rate": 4.624178824332395e-05, "loss": 0.9216, "step": 882 }, { "epoch": 0.226048, "grad_norm": 2.5625, "learning_rate": 4.6237522395700026e-05, "loss": 0.9018, "step": 883 }, { "epoch": 0.226304, "grad_norm": 3.25, "learning_rate": 4.623325654807611e-05, "loss": 0.9083, "step": 884 }, { "epoch": 0.22656, "grad_norm": 2.9375, "learning_rate": 4.622899070045218e-05, "loss": 0.8984, "step": 885 }, { "epoch": 0.226816, "grad_norm": 2.5, "learning_rate": 4.622472485282826e-05, "loss": 0.9448, "step": 886 }, { "epoch": 0.227072, "grad_norm": 3.0625, "learning_rate": 4.622045900520434e-05, "loss": 0.9051, "step": 887 }, { "epoch": 0.227328, "grad_norm": 2.796875, "learning_rate": 4.621619315758041e-05, "loss": 0.9039, "step": 888 }, { "epoch": 0.227584, "grad_norm": 2.953125, "learning_rate": 4.621192730995649e-05, "loss": 0.8937, "step": 889 }, { "epoch": 0.22784, "grad_norm": 2.90625, "learning_rate": 4.6207661462332566e-05, "loss": 0.8839, "step": 890 }, { "epoch": 0.228096, "grad_norm": 3.015625, "learning_rate": 4.620339561470865e-05, "loss": 0.9112, "step": 891 }, { "epoch": 0.228352, "grad_norm": 2.65625, "learning_rate": 4.619912976708472e-05, "loss": 0.9193, "step": 892 }, { "epoch": 0.228608, "grad_norm": 2.671875, "learning_rate": 4.61948639194608e-05, "loss": 0.9017, "step": 893 }, { "epoch": 0.228864, "grad_norm": 2.703125, "learning_rate": 4.619059807183688e-05, "loss": 0.9122, "step": 894 }, { "epoch": 0.22912, "grad_norm": 2.578125, "learning_rate": 4.618633222421295e-05, "loss": 0.8612, "step": 895 }, { "epoch": 0.229376, "grad_norm": 2.546875, "learning_rate": 4.6182066376589025e-05, "loss": 0.8832, "step": 896 }, { "epoch": 0.229632, "grad_norm": 2.5, "learning_rate": 4.6177800528965106e-05, "loss": 0.9129, "step": 897 }, { "epoch": 0.229888, "grad_norm": 2.828125, "learning_rate": 4.617353468134119e-05, "loss": 0.8786, "step": 898 }, { "epoch": 0.230144, "grad_norm": 2.84375, "learning_rate": 4.616926883371726e-05, "loss": 0.8972, "step": 899 }, { "epoch": 0.2304, "grad_norm": 3.015625, "learning_rate": 4.6165002986093336e-05, "loss": 0.9036, "step": 900 }, { "epoch": 0.230656, "grad_norm": 2.796875, "learning_rate": 4.616073713846942e-05, "loss": 0.9004, "step": 901 }, { "epoch": 0.230912, "grad_norm": 2.84375, "learning_rate": 4.615647129084549e-05, "loss": 0.9321, "step": 902 }, { "epoch": 0.231168, "grad_norm": 2.71875, "learning_rate": 4.6152205443221566e-05, "loss": 0.9085, "step": 903 }, { "epoch": 0.231424, "grad_norm": 2.875, "learning_rate": 4.6147939595597653e-05, "loss": 0.901, "step": 904 }, { "epoch": 0.23168, "grad_norm": 2.484375, "learning_rate": 4.614367374797373e-05, "loss": 0.8535, "step": 905 }, { "epoch": 0.231936, "grad_norm": 3.0625, "learning_rate": 4.61394079003498e-05, "loss": 0.8907, "step": 906 }, { "epoch": 0.232192, "grad_norm": 2.90625, "learning_rate": 4.6135142052725876e-05, "loss": 0.8898, "step": 907 }, { "epoch": 0.232448, "grad_norm": 2.578125, "learning_rate": 4.613087620510196e-05, "loss": 0.8634, "step": 908 }, { "epoch": 0.232704, "grad_norm": 3.0, "learning_rate": 4.612661035747803e-05, "loss": 0.889, "step": 909 }, { "epoch": 0.23296, "grad_norm": 2.671875, "learning_rate": 4.612234450985411e-05, "loss": 0.8987, "step": 910 }, { "epoch": 0.233216, "grad_norm": 2.765625, "learning_rate": 4.611807866223019e-05, "loss": 0.9151, "step": 911 }, { "epoch": 0.233472, "grad_norm": 2.703125, "learning_rate": 4.611381281460627e-05, "loss": 0.9043, "step": 912 }, { "epoch": 0.233728, "grad_norm": 2.921875, "learning_rate": 4.610954696698234e-05, "loss": 0.8916, "step": 913 }, { "epoch": 0.233984, "grad_norm": 2.515625, "learning_rate": 4.6105281119358416e-05, "loss": 0.8897, "step": 914 }, { "epoch": 0.23424, "grad_norm": 2.984375, "learning_rate": 4.610101527173449e-05, "loss": 0.9014, "step": 915 }, { "epoch": 0.234496, "grad_norm": 2.84375, "learning_rate": 4.609674942411057e-05, "loss": 0.86, "step": 916 }, { "epoch": 0.234752, "grad_norm": 2.6875, "learning_rate": 4.609248357648665e-05, "loss": 0.8805, "step": 917 }, { "epoch": 0.235008, "grad_norm": 2.875, "learning_rate": 4.608821772886273e-05, "loss": 0.8773, "step": 918 }, { "epoch": 0.235264, "grad_norm": 2.734375, "learning_rate": 4.60839518812388e-05, "loss": 0.8947, "step": 919 }, { "epoch": 0.23552, "grad_norm": 2.671875, "learning_rate": 4.607968603361488e-05, "loss": 0.8729, "step": 920 }, { "epoch": 0.235776, "grad_norm": 2.40625, "learning_rate": 4.6075420185990957e-05, "loss": 0.8939, "step": 921 }, { "epoch": 0.236032, "grad_norm": 2.703125, "learning_rate": 4.607115433836703e-05, "loss": 0.905, "step": 922 }, { "epoch": 0.236288, "grad_norm": 2.53125, "learning_rate": 4.606688849074312e-05, "loss": 0.8786, "step": 923 }, { "epoch": 0.236544, "grad_norm": 2.5, "learning_rate": 4.606262264311919e-05, "loss": 0.8644, "step": 924 }, { "epoch": 0.2368, "grad_norm": 2.671875, "learning_rate": 4.605835679549527e-05, "loss": 0.9417, "step": 925 }, { "epoch": 0.237056, "grad_norm": 2.546875, "learning_rate": 4.605409094787134e-05, "loss": 0.892, "step": 926 }, { "epoch": 0.237312, "grad_norm": 2.640625, "learning_rate": 4.604982510024742e-05, "loss": 0.8649, "step": 927 }, { "epoch": 0.237568, "grad_norm": 2.625, "learning_rate": 4.60455592526235e-05, "loss": 0.8885, "step": 928 }, { "epoch": 0.237824, "grad_norm": 2.65625, "learning_rate": 4.604129340499958e-05, "loss": 0.8721, "step": 929 }, { "epoch": 0.23808, "grad_norm": 2.828125, "learning_rate": 4.603702755737565e-05, "loss": 0.89, "step": 930 }, { "epoch": 0.238336, "grad_norm": 3.0625, "learning_rate": 4.603276170975173e-05, "loss": 0.9133, "step": 931 }, { "epoch": 0.238592, "grad_norm": 3.09375, "learning_rate": 4.602849586212781e-05, "loss": 0.8898, "step": 932 }, { "epoch": 0.238848, "grad_norm": 2.90625, "learning_rate": 4.602423001450388e-05, "loss": 0.8714, "step": 933 }, { "epoch": 0.239104, "grad_norm": 2.875, "learning_rate": 4.6019964166879956e-05, "loss": 0.8845, "step": 934 }, { "epoch": 0.23936, "grad_norm": 2.640625, "learning_rate": 4.601569831925604e-05, "loss": 0.8654, "step": 935 }, { "epoch": 0.239616, "grad_norm": 2.765625, "learning_rate": 4.601143247163212e-05, "loss": 0.8652, "step": 936 }, { "epoch": 0.239872, "grad_norm": 2.890625, "learning_rate": 4.600716662400819e-05, "loss": 0.8301, "step": 937 }, { "epoch": 0.240128, "grad_norm": 2.9375, "learning_rate": 4.600290077638427e-05, "loss": 0.9076, "step": 938 }, { "epoch": 0.240384, "grad_norm": 2.6875, "learning_rate": 4.599863492876035e-05, "loss": 0.8616, "step": 939 }, { "epoch": 0.24064, "grad_norm": 2.625, "learning_rate": 4.599436908113642e-05, "loss": 0.8695, "step": 940 }, { "epoch": 0.240896, "grad_norm": 2.625, "learning_rate": 4.5990103233512496e-05, "loss": 0.8602, "step": 941 }, { "epoch": 0.241152, "grad_norm": 2.8125, "learning_rate": 4.598583738588858e-05, "loss": 0.8731, "step": 942 }, { "epoch": 0.241408, "grad_norm": 2.578125, "learning_rate": 4.598157153826466e-05, "loss": 0.8515, "step": 943 }, { "epoch": 0.241664, "grad_norm": 2.8125, "learning_rate": 4.597730569064073e-05, "loss": 0.8323, "step": 944 }, { "epoch": 0.24192, "grad_norm": 2.921875, "learning_rate": 4.597303984301681e-05, "loss": 0.901, "step": 945 }, { "epoch": 0.242176, "grad_norm": 2.921875, "learning_rate": 4.596877399539289e-05, "loss": 0.8403, "step": 946 }, { "epoch": 0.242432, "grad_norm": 2.96875, "learning_rate": 4.596450814776896e-05, "loss": 0.8844, "step": 947 }, { "epoch": 0.242688, "grad_norm": 3.0625, "learning_rate": 4.596024230014504e-05, "loss": 0.8582, "step": 948 }, { "epoch": 0.242944, "grad_norm": 3.046875, "learning_rate": 4.595597645252112e-05, "loss": 0.8715, "step": 949 }, { "epoch": 0.2432, "grad_norm": 2.875, "learning_rate": 4.59517106048972e-05, "loss": 0.8891, "step": 950 }, { "epoch": 0.243456, "grad_norm": 3.125, "learning_rate": 4.594744475727327e-05, "loss": 0.8585, "step": 951 }, { "epoch": 0.243712, "grad_norm": 3.140625, "learning_rate": 4.594317890964935e-05, "loss": 0.8741, "step": 952 }, { "epoch": 0.243968, "grad_norm": 2.765625, "learning_rate": 4.593891306202543e-05, "loss": 0.8668, "step": 953 }, { "epoch": 0.244224, "grad_norm": 3.15625, "learning_rate": 4.59346472144015e-05, "loss": 0.8835, "step": 954 }, { "epoch": 0.24448, "grad_norm": 3.09375, "learning_rate": 4.593038136677758e-05, "loss": 0.8872, "step": 955 }, { "epoch": 0.244736, "grad_norm": 2.875, "learning_rate": 4.592611551915366e-05, "loss": 0.9271, "step": 956 }, { "epoch": 0.244992, "grad_norm": 3.09375, "learning_rate": 4.592184967152974e-05, "loss": 0.8419, "step": 957 }, { "epoch": 0.245248, "grad_norm": 2.515625, "learning_rate": 4.591758382390581e-05, "loss": 0.8864, "step": 958 }, { "epoch": 0.245504, "grad_norm": 2.640625, "learning_rate": 4.591331797628189e-05, "loss": 0.8904, "step": 959 }, { "epoch": 0.24576, "grad_norm": 3.0, "learning_rate": 4.590905212865796e-05, "loss": 0.8517, "step": 960 }, { "epoch": 0.246016, "grad_norm": 2.59375, "learning_rate": 4.590478628103404e-05, "loss": 0.8183, "step": 961 }, { "epoch": 0.246272, "grad_norm": 2.734375, "learning_rate": 4.5900520433410123e-05, "loss": 0.8743, "step": 962 }, { "epoch": 0.246528, "grad_norm": 3.015625, "learning_rate": 4.58962545857862e-05, "loss": 0.8363, "step": 963 }, { "epoch": 0.246784, "grad_norm": 2.90625, "learning_rate": 4.589198873816227e-05, "loss": 0.8421, "step": 964 }, { "epoch": 0.24704, "grad_norm": 2.90625, "learning_rate": 4.588772289053835e-05, "loss": 0.871, "step": 965 }, { "epoch": 0.247296, "grad_norm": 3.3125, "learning_rate": 4.588345704291443e-05, "loss": 0.8446, "step": 966 }, { "epoch": 0.247552, "grad_norm": 3.046875, "learning_rate": 4.587919119529051e-05, "loss": 0.8753, "step": 967 }, { "epoch": 0.247808, "grad_norm": 3.0, "learning_rate": 4.587492534766658e-05, "loss": 0.8317, "step": 968 }, { "epoch": 0.248064, "grad_norm": 3.125, "learning_rate": 4.5870659500042664e-05, "loss": 0.8805, "step": 969 }, { "epoch": 0.24832, "grad_norm": 2.921875, "learning_rate": 4.586639365241874e-05, "loss": 0.8603, "step": 970 }, { "epoch": 0.248576, "grad_norm": 2.796875, "learning_rate": 4.586212780479481e-05, "loss": 0.8581, "step": 971 }, { "epoch": 0.248832, "grad_norm": 2.921875, "learning_rate": 4.585786195717089e-05, "loss": 0.8124, "step": 972 }, { "epoch": 0.249088, "grad_norm": 2.71875, "learning_rate": 4.585359610954697e-05, "loss": 0.8497, "step": 973 }, { "epoch": 0.249344, "grad_norm": 2.734375, "learning_rate": 4.584933026192305e-05, "loss": 0.8796, "step": 974 }, { "epoch": 0.2496, "grad_norm": 3.015625, "learning_rate": 4.584506441429912e-05, "loss": 0.8587, "step": 975 }, { "epoch": 0.249856, "grad_norm": 2.796875, "learning_rate": 4.5840798566675204e-05, "loss": 0.8785, "step": 976 }, { "epoch": 0.250112, "grad_norm": 2.453125, "learning_rate": 4.583653271905128e-05, "loss": 0.82, "step": 977 }, { "epoch": 0.250368, "grad_norm": 2.46875, "learning_rate": 4.583226687142735e-05, "loss": 0.8628, "step": 978 }, { "epoch": 0.250624, "grad_norm": 2.859375, "learning_rate": 4.582800102380343e-05, "loss": 0.8211, "step": 979 }, { "epoch": 0.25088, "grad_norm": 2.84375, "learning_rate": 4.582373517617951e-05, "loss": 0.8486, "step": 980 }, { "epoch": 0.251136, "grad_norm": 2.546875, "learning_rate": 4.581946932855559e-05, "loss": 0.832, "step": 981 }, { "epoch": 0.251392, "grad_norm": 2.75, "learning_rate": 4.581520348093166e-05, "loss": 0.8369, "step": 982 }, { "epoch": 0.251648, "grad_norm": 2.875, "learning_rate": 4.581093763330774e-05, "loss": 0.8263, "step": 983 }, { "epoch": 0.251904, "grad_norm": 2.859375, "learning_rate": 4.580667178568382e-05, "loss": 0.8426, "step": 984 }, { "epoch": 0.25216, "grad_norm": 2.71875, "learning_rate": 4.580240593805989e-05, "loss": 0.8527, "step": 985 }, { "epoch": 0.252416, "grad_norm": 2.609375, "learning_rate": 4.5798140090435974e-05, "loss": 0.858, "step": 986 }, { "epoch": 0.252672, "grad_norm": 2.8125, "learning_rate": 4.5793874242812055e-05, "loss": 0.8523, "step": 987 }, { "epoch": 0.252928, "grad_norm": 2.46875, "learning_rate": 4.578960839518813e-05, "loss": 0.8854, "step": 988 }, { "epoch": 0.253184, "grad_norm": 2.921875, "learning_rate": 4.57853425475642e-05, "loss": 0.8431, "step": 989 }, { "epoch": 0.25344, "grad_norm": 2.515625, "learning_rate": 4.578107669994028e-05, "loss": 0.8519, "step": 990 }, { "epoch": 0.253696, "grad_norm": 2.65625, "learning_rate": 4.577681085231636e-05, "loss": 0.8495, "step": 991 }, { "epoch": 0.253952, "grad_norm": 2.546875, "learning_rate": 4.577254500469243e-05, "loss": 0.8938, "step": 992 }, { "epoch": 0.254208, "grad_norm": 2.859375, "learning_rate": 4.5768279157068514e-05, "loss": 0.8255, "step": 993 }, { "epoch": 0.254464, "grad_norm": 2.4375, "learning_rate": 4.576401330944459e-05, "loss": 0.8685, "step": 994 }, { "epoch": 0.25472, "grad_norm": 2.453125, "learning_rate": 4.575974746182067e-05, "loss": 0.8755, "step": 995 }, { "epoch": 0.254976, "grad_norm": 2.75, "learning_rate": 4.5755481614196743e-05, "loss": 0.8152, "step": 996 }, { "epoch": 0.255232, "grad_norm": 2.65625, "learning_rate": 4.575121576657282e-05, "loss": 0.837, "step": 997 }, { "epoch": 0.255488, "grad_norm": 2.65625, "learning_rate": 4.574694991894889e-05, "loss": 0.8594, "step": 998 }, { "epoch": 0.255744, "grad_norm": 2.734375, "learning_rate": 4.574268407132497e-05, "loss": 0.8701, "step": 999 }, { "epoch": 0.256, "grad_norm": 2.59375, "learning_rate": 4.5738418223701054e-05, "loss": 0.8559, "step": 1000 }, { "epoch": 0.256256, "grad_norm": 2.71875, "learning_rate": 4.573415237607713e-05, "loss": 0.8478, "step": 1001 }, { "epoch": 0.256512, "grad_norm": 2.75, "learning_rate": 4.572988652845321e-05, "loss": 0.8233, "step": 1002 }, { "epoch": 0.256768, "grad_norm": 2.84375, "learning_rate": 4.5725620680829284e-05, "loss": 0.7952, "step": 1003 }, { "epoch": 0.257024, "grad_norm": 3.171875, "learning_rate": 4.572135483320536e-05, "loss": 0.7962, "step": 1004 }, { "epoch": 0.25728, "grad_norm": 2.8125, "learning_rate": 4.571708898558143e-05, "loss": 0.8512, "step": 1005 }, { "epoch": 0.257536, "grad_norm": 3.03125, "learning_rate": 4.571282313795752e-05, "loss": 0.8246, "step": 1006 }, { "epoch": 0.257792, "grad_norm": 3.03125, "learning_rate": 4.5708557290333594e-05, "loss": 0.8635, "step": 1007 }, { "epoch": 0.258048, "grad_norm": 2.9375, "learning_rate": 4.570429144270967e-05, "loss": 0.827, "step": 1008 }, { "epoch": 0.258304, "grad_norm": 2.875, "learning_rate": 4.570002559508574e-05, "loss": 0.8616, "step": 1009 }, { "epoch": 0.25856, "grad_norm": 2.75, "learning_rate": 4.5695759747461824e-05, "loss": 0.8313, "step": 1010 }, { "epoch": 0.258816, "grad_norm": 3.1875, "learning_rate": 4.56914938998379e-05, "loss": 0.8951, "step": 1011 }, { "epoch": 0.259072, "grad_norm": 3.40625, "learning_rate": 4.568722805221398e-05, "loss": 0.8052, "step": 1012 }, { "epoch": 0.259328, "grad_norm": 2.796875, "learning_rate": 4.568296220459005e-05, "loss": 0.8491, "step": 1013 }, { "epoch": 0.259584, "grad_norm": 2.828125, "learning_rate": 4.5678696356966134e-05, "loss": 0.8619, "step": 1014 }, { "epoch": 0.25984, "grad_norm": 3.03125, "learning_rate": 4.567443050934221e-05, "loss": 0.9084, "step": 1015 }, { "epoch": 0.260096, "grad_norm": 3.15625, "learning_rate": 4.567016466171828e-05, "loss": 0.8961, "step": 1016 }, { "epoch": 0.260352, "grad_norm": 2.921875, "learning_rate": 4.566589881409436e-05, "loss": 0.8228, "step": 1017 }, { "epoch": 0.260608, "grad_norm": 2.71875, "learning_rate": 4.566163296647044e-05, "loss": 0.8517, "step": 1018 }, { "epoch": 0.260864, "grad_norm": 3.09375, "learning_rate": 4.565736711884652e-05, "loss": 0.8452, "step": 1019 }, { "epoch": 0.26112, "grad_norm": 2.65625, "learning_rate": 4.5653101271222594e-05, "loss": 0.8579, "step": 1020 }, { "epoch": 0.261376, "grad_norm": 2.53125, "learning_rate": 4.5648835423598675e-05, "loss": 0.8825, "step": 1021 }, { "epoch": 0.261632, "grad_norm": 2.59375, "learning_rate": 4.564456957597475e-05, "loss": 0.8377, "step": 1022 }, { "epoch": 0.261888, "grad_norm": 2.78125, "learning_rate": 4.564030372835082e-05, "loss": 0.811, "step": 1023 }, { "epoch": 0.262144, "grad_norm": 2.6875, "learning_rate": 4.56360378807269e-05, "loss": 0.8531, "step": 1024 }, { "epoch": 0.2624, "grad_norm": 3.0625, "learning_rate": 4.5631772033102985e-05, "loss": 0.8744, "step": 1025 }, { "epoch": 0.262656, "grad_norm": 2.9375, "learning_rate": 4.562750618547906e-05, "loss": 0.8267, "step": 1026 }, { "epoch": 0.262912, "grad_norm": 2.890625, "learning_rate": 4.5623240337855134e-05, "loss": 0.8348, "step": 1027 }, { "epoch": 0.263168, "grad_norm": 2.8125, "learning_rate": 4.561897449023121e-05, "loss": 0.8625, "step": 1028 }, { "epoch": 0.263424, "grad_norm": 3.078125, "learning_rate": 4.561470864260729e-05, "loss": 0.9029, "step": 1029 }, { "epoch": 0.26368, "grad_norm": 2.71875, "learning_rate": 4.561044279498336e-05, "loss": 0.8264, "step": 1030 }, { "epoch": 0.263936, "grad_norm": 2.9375, "learning_rate": 4.5606176947359444e-05, "loss": 0.8292, "step": 1031 }, { "epoch": 0.264192, "grad_norm": 2.859375, "learning_rate": 4.560191109973552e-05, "loss": 0.8178, "step": 1032 }, { "epoch": 0.264448, "grad_norm": 2.78125, "learning_rate": 4.55976452521116e-05, "loss": 0.8403, "step": 1033 }, { "epoch": 0.264704, "grad_norm": 2.65625, "learning_rate": 4.5593379404487674e-05, "loss": 0.8668, "step": 1034 }, { "epoch": 0.26496, "grad_norm": 2.828125, "learning_rate": 4.558911355686375e-05, "loss": 0.824, "step": 1035 }, { "epoch": 0.265216, "grad_norm": 2.625, "learning_rate": 4.558484770923983e-05, "loss": 0.808, "step": 1036 }, { "epoch": 0.265472, "grad_norm": 2.5625, "learning_rate": 4.5580581861615904e-05, "loss": 0.8612, "step": 1037 }, { "epoch": 0.265728, "grad_norm": 2.640625, "learning_rate": 4.5576316013991985e-05, "loss": 0.8551, "step": 1038 }, { "epoch": 0.265984, "grad_norm": 2.75, "learning_rate": 4.557205016636806e-05, "loss": 0.8335, "step": 1039 }, { "epoch": 0.26624, "grad_norm": 2.65625, "learning_rate": 4.556778431874414e-05, "loss": 0.854, "step": 1040 }, { "epoch": 0.266496, "grad_norm": 2.734375, "learning_rate": 4.5563518471120214e-05, "loss": 0.8513, "step": 1041 }, { "epoch": 0.266752, "grad_norm": 2.984375, "learning_rate": 4.555925262349629e-05, "loss": 0.8691, "step": 1042 }, { "epoch": 0.267008, "grad_norm": 2.65625, "learning_rate": 4.555498677587236e-05, "loss": 0.8174, "step": 1043 }, { "epoch": 0.267264, "grad_norm": 2.609375, "learning_rate": 4.5550720928248444e-05, "loss": 0.8657, "step": 1044 }, { "epoch": 0.26752, "grad_norm": 2.84375, "learning_rate": 4.5546455080624525e-05, "loss": 0.8336, "step": 1045 }, { "epoch": 0.267776, "grad_norm": 2.828125, "learning_rate": 4.55421892330006e-05, "loss": 0.8728, "step": 1046 }, { "epoch": 0.268032, "grad_norm": 2.4375, "learning_rate": 4.553792338537667e-05, "loss": 0.8139, "step": 1047 }, { "epoch": 0.268288, "grad_norm": 3.046875, "learning_rate": 4.5533657537752754e-05, "loss": 0.8269, "step": 1048 }, { "epoch": 0.268544, "grad_norm": 3.078125, "learning_rate": 4.552939169012883e-05, "loss": 0.8432, "step": 1049 }, { "epoch": 0.2688, "grad_norm": 2.59375, "learning_rate": 4.552512584250491e-05, "loss": 0.8187, "step": 1050 }, { "epoch": 0.269056, "grad_norm": 2.59375, "learning_rate": 4.552085999488099e-05, "loss": 0.8349, "step": 1051 }, { "epoch": 0.269312, "grad_norm": 2.90625, "learning_rate": 4.5516594147257065e-05, "loss": 0.8355, "step": 1052 }, { "epoch": 0.269568, "grad_norm": 2.609375, "learning_rate": 4.551232829963314e-05, "loss": 0.8225, "step": 1053 }, { "epoch": 0.269824, "grad_norm": 2.578125, "learning_rate": 4.5508062452009213e-05, "loss": 0.8456, "step": 1054 }, { "epoch": 0.27008, "grad_norm": 2.765625, "learning_rate": 4.5503796604385295e-05, "loss": 0.8386, "step": 1055 }, { "epoch": 0.270336, "grad_norm": 2.9375, "learning_rate": 4.549953075676137e-05, "loss": 0.8291, "step": 1056 }, { "epoch": 0.270592, "grad_norm": 2.921875, "learning_rate": 4.549526490913745e-05, "loss": 0.8471, "step": 1057 }, { "epoch": 0.270848, "grad_norm": 2.90625, "learning_rate": 4.5490999061513524e-05, "loss": 0.8195, "step": 1058 }, { "epoch": 0.271104, "grad_norm": 2.84375, "learning_rate": 4.5486733213889605e-05, "loss": 0.8255, "step": 1059 }, { "epoch": 0.27136, "grad_norm": 2.875, "learning_rate": 4.548246736626568e-05, "loss": 0.8035, "step": 1060 }, { "epoch": 0.271616, "grad_norm": 2.78125, "learning_rate": 4.5478201518641754e-05, "loss": 0.8109, "step": 1061 }, { "epoch": 0.271872, "grad_norm": 2.65625, "learning_rate": 4.547393567101783e-05, "loss": 0.8188, "step": 1062 }, { "epoch": 0.272128, "grad_norm": 2.671875, "learning_rate": 4.546966982339391e-05, "loss": 0.8182, "step": 1063 }, { "epoch": 0.272384, "grad_norm": 3.125, "learning_rate": 4.546540397576999e-05, "loss": 0.8484, "step": 1064 }, { "epoch": 0.27264, "grad_norm": 2.734375, "learning_rate": 4.5461138128146064e-05, "loss": 0.8189, "step": 1065 }, { "epoch": 0.272896, "grad_norm": 2.8125, "learning_rate": 4.545687228052214e-05, "loss": 0.8047, "step": 1066 }, { "epoch": 0.273152, "grad_norm": 2.703125, "learning_rate": 4.545260643289822e-05, "loss": 0.8643, "step": 1067 }, { "epoch": 0.273408, "grad_norm": 2.640625, "learning_rate": 4.5448340585274294e-05, "loss": 0.7722, "step": 1068 }, { "epoch": 0.273664, "grad_norm": 2.375, "learning_rate": 4.5444074737650375e-05, "loss": 0.84, "step": 1069 }, { "epoch": 0.27392, "grad_norm": 2.703125, "learning_rate": 4.5439808890026456e-05, "loss": 0.8644, "step": 1070 }, { "epoch": 0.274176, "grad_norm": 3.109375, "learning_rate": 4.543554304240253e-05, "loss": 0.8523, "step": 1071 }, { "epoch": 0.274432, "grad_norm": 2.640625, "learning_rate": 4.5431277194778604e-05, "loss": 0.814, "step": 1072 }, { "epoch": 0.274688, "grad_norm": 2.671875, "learning_rate": 4.542701134715468e-05, "loss": 0.8274, "step": 1073 }, { "epoch": 0.274944, "grad_norm": 2.9375, "learning_rate": 4.542274549953076e-05, "loss": 0.833, "step": 1074 }, { "epoch": 0.2752, "grad_norm": 3.078125, "learning_rate": 4.5418479651906834e-05, "loss": 0.8145, "step": 1075 }, { "epoch": 0.275456, "grad_norm": 2.65625, "learning_rate": 4.5414213804282915e-05, "loss": 0.8203, "step": 1076 }, { "epoch": 0.275712, "grad_norm": 2.90625, "learning_rate": 4.540994795665899e-05, "loss": 0.8462, "step": 1077 }, { "epoch": 0.275968, "grad_norm": 2.96875, "learning_rate": 4.540568210903507e-05, "loss": 0.8075, "step": 1078 }, { "epoch": 0.276224, "grad_norm": 2.546875, "learning_rate": 4.5401416261411145e-05, "loss": 0.8172, "step": 1079 }, { "epoch": 0.27648, "grad_norm": 2.828125, "learning_rate": 4.539715041378722e-05, "loss": 0.8009, "step": 1080 }, { "epoch": 0.276736, "grad_norm": 2.671875, "learning_rate": 4.539288456616329e-05, "loss": 0.836, "step": 1081 }, { "epoch": 0.276992, "grad_norm": 2.5625, "learning_rate": 4.5388618718539374e-05, "loss": 0.8407, "step": 1082 }, { "epoch": 0.277248, "grad_norm": 2.3125, "learning_rate": 4.5384352870915455e-05, "loss": 0.8634, "step": 1083 }, { "epoch": 0.277504, "grad_norm": 3.078125, "learning_rate": 4.538008702329153e-05, "loss": 0.8502, "step": 1084 }, { "epoch": 0.27776, "grad_norm": 2.765625, "learning_rate": 4.537582117566761e-05, "loss": 0.7966, "step": 1085 }, { "epoch": 0.278016, "grad_norm": 2.828125, "learning_rate": 4.5371555328043685e-05, "loss": 0.8427, "step": 1086 }, { "epoch": 0.278272, "grad_norm": 2.875, "learning_rate": 4.536728948041976e-05, "loss": 0.8427, "step": 1087 }, { "epoch": 0.278528, "grad_norm": 2.8125, "learning_rate": 4.536302363279584e-05, "loss": 0.8346, "step": 1088 }, { "epoch": 0.278784, "grad_norm": 2.6875, "learning_rate": 4.535875778517192e-05, "loss": 0.8081, "step": 1089 }, { "epoch": 0.27904, "grad_norm": 2.84375, "learning_rate": 4.5354491937547995e-05, "loss": 0.8027, "step": 1090 }, { "epoch": 0.279296, "grad_norm": 2.59375, "learning_rate": 4.535022608992407e-05, "loss": 0.8278, "step": 1091 }, { "epoch": 0.279552, "grad_norm": 2.609375, "learning_rate": 4.5345960242300144e-05, "loss": 0.8215, "step": 1092 }, { "epoch": 0.279808, "grad_norm": 2.8125, "learning_rate": 4.5341694394676225e-05, "loss": 0.751, "step": 1093 }, { "epoch": 0.280064, "grad_norm": 2.625, "learning_rate": 4.53374285470523e-05, "loss": 0.8307, "step": 1094 }, { "epoch": 0.28032, "grad_norm": 2.71875, "learning_rate": 4.533316269942838e-05, "loss": 0.8501, "step": 1095 }, { "epoch": 0.280576, "grad_norm": 2.921875, "learning_rate": 4.5328896851804455e-05, "loss": 0.8042, "step": 1096 }, { "epoch": 0.280832, "grad_norm": 3.015625, "learning_rate": 4.5324631004180536e-05, "loss": 0.8271, "step": 1097 }, { "epoch": 0.281088, "grad_norm": 2.546875, "learning_rate": 4.532036515655661e-05, "loss": 0.8089, "step": 1098 }, { "epoch": 0.281344, "grad_norm": 2.703125, "learning_rate": 4.5316099308932684e-05, "loss": 0.7992, "step": 1099 }, { "epoch": 0.2816, "grad_norm": 2.8125, "learning_rate": 4.5311833461308765e-05, "loss": 0.8397, "step": 1100 }, { "epoch": 0.281856, "grad_norm": 2.890625, "learning_rate": 4.530756761368484e-05, "loss": 0.7935, "step": 1101 }, { "epoch": 0.282112, "grad_norm": 3.015625, "learning_rate": 4.530330176606092e-05, "loss": 0.8092, "step": 1102 }, { "epoch": 0.282368, "grad_norm": 2.625, "learning_rate": 4.5299035918436995e-05, "loss": 0.8255, "step": 1103 }, { "epoch": 0.282624, "grad_norm": 2.734375, "learning_rate": 4.5294770070813076e-05, "loss": 0.8117, "step": 1104 }, { "epoch": 0.28288, "grad_norm": 3.015625, "learning_rate": 4.529050422318915e-05, "loss": 0.7812, "step": 1105 }, { "epoch": 0.283136, "grad_norm": 2.859375, "learning_rate": 4.5286238375565224e-05, "loss": 0.8643, "step": 1106 }, { "epoch": 0.283392, "grad_norm": 2.6875, "learning_rate": 4.5281972527941305e-05, "loss": 0.8064, "step": 1107 }, { "epoch": 0.283648, "grad_norm": 2.75, "learning_rate": 4.5277706680317386e-05, "loss": 0.8675, "step": 1108 }, { "epoch": 0.283904, "grad_norm": 2.703125, "learning_rate": 4.527344083269346e-05, "loss": 0.7941, "step": 1109 }, { "epoch": 0.28416, "grad_norm": 2.5, "learning_rate": 4.5269174985069535e-05, "loss": 0.7958, "step": 1110 }, { "epoch": 0.284416, "grad_norm": 2.671875, "learning_rate": 4.526490913744561e-05, "loss": 0.8118, "step": 1111 }, { "epoch": 0.284672, "grad_norm": 2.671875, "learning_rate": 4.526064328982169e-05, "loss": 0.831, "step": 1112 }, { "epoch": 0.284928, "grad_norm": 2.703125, "learning_rate": 4.5256377442197765e-05, "loss": 0.8063, "step": 1113 }, { "epoch": 0.285184, "grad_norm": 2.96875, "learning_rate": 4.5252111594573846e-05, "loss": 0.7885, "step": 1114 }, { "epoch": 0.28544, "grad_norm": 2.890625, "learning_rate": 4.524784574694992e-05, "loss": 0.8095, "step": 1115 }, { "epoch": 0.285696, "grad_norm": 3.03125, "learning_rate": 4.5243579899326e-05, "loss": 0.8346, "step": 1116 }, { "epoch": 0.285952, "grad_norm": 2.4375, "learning_rate": 4.5239314051702075e-05, "loss": 0.7993, "step": 1117 }, { "epoch": 0.286208, "grad_norm": 2.859375, "learning_rate": 4.523504820407815e-05, "loss": 0.7902, "step": 1118 }, { "epoch": 0.286464, "grad_norm": 2.671875, "learning_rate": 4.523078235645423e-05, "loss": 0.8257, "step": 1119 }, { "epoch": 0.28672, "grad_norm": 2.546875, "learning_rate": 4.5226516508830305e-05, "loss": 0.8014, "step": 1120 }, { "epoch": 0.286976, "grad_norm": 2.75, "learning_rate": 4.5222250661206386e-05, "loss": 0.8312, "step": 1121 }, { "epoch": 0.287232, "grad_norm": 2.5625, "learning_rate": 4.521798481358246e-05, "loss": 0.8522, "step": 1122 }, { "epoch": 0.287488, "grad_norm": 2.671875, "learning_rate": 4.521371896595854e-05, "loss": 0.8137, "step": 1123 }, { "epoch": 0.287744, "grad_norm": 2.578125, "learning_rate": 4.5209453118334615e-05, "loss": 0.7556, "step": 1124 }, { "epoch": 0.288, "grad_norm": 3.0625, "learning_rate": 4.520518727071069e-05, "loss": 0.7643, "step": 1125 }, { "epoch": 0.288256, "grad_norm": 2.734375, "learning_rate": 4.5200921423086764e-05, "loss": 0.8147, "step": 1126 }, { "epoch": 0.288512, "grad_norm": 2.765625, "learning_rate": 4.519665557546285e-05, "loss": 0.8248, "step": 1127 }, { "epoch": 0.288768, "grad_norm": 2.828125, "learning_rate": 4.5192389727838926e-05, "loss": 0.8276, "step": 1128 }, { "epoch": 0.289024, "grad_norm": 2.703125, "learning_rate": 4.5188123880215e-05, "loss": 0.7618, "step": 1129 }, { "epoch": 0.28928, "grad_norm": 2.59375, "learning_rate": 4.5183858032591075e-05, "loss": 0.8175, "step": 1130 }, { "epoch": 0.289536, "grad_norm": 2.609375, "learning_rate": 4.5179592184967156e-05, "loss": 0.8162, "step": 1131 }, { "epoch": 0.289792, "grad_norm": 2.640625, "learning_rate": 4.517532633734323e-05, "loss": 0.7685, "step": 1132 }, { "epoch": 0.290048, "grad_norm": 2.921875, "learning_rate": 4.517106048971931e-05, "loss": 0.7879, "step": 1133 }, { "epoch": 0.290304, "grad_norm": 2.90625, "learning_rate": 4.516679464209539e-05, "loss": 0.7564, "step": 1134 }, { "epoch": 0.29056, "grad_norm": 2.40625, "learning_rate": 4.5162528794471466e-05, "loss": 0.7658, "step": 1135 }, { "epoch": 0.290816, "grad_norm": 3.140625, "learning_rate": 4.515826294684754e-05, "loss": 0.8071, "step": 1136 }, { "epoch": 0.291072, "grad_norm": 2.859375, "learning_rate": 4.5153997099223615e-05, "loss": 0.8038, "step": 1137 }, { "epoch": 0.291328, "grad_norm": 2.59375, "learning_rate": 4.5149731251599696e-05, "loss": 0.7565, "step": 1138 }, { "epoch": 0.291584, "grad_norm": 2.953125, "learning_rate": 4.514546540397577e-05, "loss": 0.809, "step": 1139 }, { "epoch": 0.29184, "grad_norm": 2.46875, "learning_rate": 4.514119955635185e-05, "loss": 0.7834, "step": 1140 }, { "epoch": 0.292096, "grad_norm": 2.78125, "learning_rate": 4.5136933708727925e-05, "loss": 0.8345, "step": 1141 }, { "epoch": 0.292352, "grad_norm": 2.59375, "learning_rate": 4.5132667861104006e-05, "loss": 0.7937, "step": 1142 }, { "epoch": 0.292608, "grad_norm": 2.65625, "learning_rate": 4.512840201348008e-05, "loss": 0.8117, "step": 1143 }, { "epoch": 0.292864, "grad_norm": 2.4375, "learning_rate": 4.5124136165856155e-05, "loss": 0.8303, "step": 1144 }, { "epoch": 0.29312, "grad_norm": 2.71875, "learning_rate": 4.511987031823223e-05, "loss": 0.7534, "step": 1145 }, { "epoch": 0.293376, "grad_norm": 2.625, "learning_rate": 4.511560447060831e-05, "loss": 0.78, "step": 1146 }, { "epoch": 0.293632, "grad_norm": 2.828125, "learning_rate": 4.511133862298439e-05, "loss": 0.7983, "step": 1147 }, { "epoch": 0.293888, "grad_norm": 2.5625, "learning_rate": 4.5107072775360466e-05, "loss": 0.7987, "step": 1148 }, { "epoch": 0.294144, "grad_norm": 2.796875, "learning_rate": 4.5102806927736547e-05, "loss": 0.7651, "step": 1149 }, { "epoch": 0.2944, "grad_norm": 2.984375, "learning_rate": 4.509854108011262e-05, "loss": 0.819, "step": 1150 }, { "epoch": 0.294656, "grad_norm": 2.78125, "learning_rate": 4.5094275232488695e-05, "loss": 0.7819, "step": 1151 }, { "epoch": 0.294912, "grad_norm": 2.734375, "learning_rate": 4.5090009384864776e-05, "loss": 0.7781, "step": 1152 }, { "epoch": 0.295168, "grad_norm": 2.875, "learning_rate": 4.508574353724086e-05, "loss": 0.8109, "step": 1153 }, { "epoch": 0.295424, "grad_norm": 2.78125, "learning_rate": 4.508147768961693e-05, "loss": 0.8212, "step": 1154 }, { "epoch": 0.29568, "grad_norm": 2.578125, "learning_rate": 4.5077211841993006e-05, "loss": 0.8135, "step": 1155 }, { "epoch": 0.295936, "grad_norm": 2.796875, "learning_rate": 4.507294599436908e-05, "loss": 0.7826, "step": 1156 }, { "epoch": 0.296192, "grad_norm": 2.859375, "learning_rate": 4.506868014674516e-05, "loss": 0.7762, "step": 1157 }, { "epoch": 0.296448, "grad_norm": 2.6875, "learning_rate": 4.5064414299121235e-05, "loss": 0.7764, "step": 1158 }, { "epoch": 0.296704, "grad_norm": 2.59375, "learning_rate": 4.5060148451497316e-05, "loss": 0.8111, "step": 1159 }, { "epoch": 0.29696, "grad_norm": 2.59375, "learning_rate": 4.505588260387339e-05, "loss": 0.8042, "step": 1160 }, { "epoch": 0.297216, "grad_norm": 2.5625, "learning_rate": 4.505161675624947e-05, "loss": 0.7658, "step": 1161 }, { "epoch": 0.297472, "grad_norm": 2.796875, "learning_rate": 4.5047350908625546e-05, "loss": 0.7637, "step": 1162 }, { "epoch": 0.297728, "grad_norm": 2.515625, "learning_rate": 4.504308506100162e-05, "loss": 0.7803, "step": 1163 }, { "epoch": 0.297984, "grad_norm": 2.5, "learning_rate": 4.5038819213377694e-05, "loss": 0.7908, "step": 1164 }, { "epoch": 0.29824, "grad_norm": 2.703125, "learning_rate": 4.5034553365753776e-05, "loss": 0.8145, "step": 1165 }, { "epoch": 0.298496, "grad_norm": 2.46875, "learning_rate": 4.5030287518129857e-05, "loss": 0.739, "step": 1166 }, { "epoch": 0.298752, "grad_norm": 2.328125, "learning_rate": 4.502602167050593e-05, "loss": 0.7992, "step": 1167 }, { "epoch": 0.299008, "grad_norm": 2.671875, "learning_rate": 4.502175582288201e-05, "loss": 0.7755, "step": 1168 }, { "epoch": 0.299264, "grad_norm": 3.015625, "learning_rate": 4.5017489975258086e-05, "loss": 0.7774, "step": 1169 }, { "epoch": 0.29952, "grad_norm": 2.640625, "learning_rate": 4.501322412763416e-05, "loss": 0.8134, "step": 1170 }, { "epoch": 0.299776, "grad_norm": 2.625, "learning_rate": 4.500895828001024e-05, "loss": 0.7781, "step": 1171 }, { "epoch": 0.300032, "grad_norm": 2.65625, "learning_rate": 4.500469243238632e-05, "loss": 0.8036, "step": 1172 }, { "epoch": 0.300288, "grad_norm": 2.921875, "learning_rate": 4.50004265847624e-05, "loss": 0.7942, "step": 1173 }, { "epoch": 0.300544, "grad_norm": 2.71875, "learning_rate": 4.499616073713847e-05, "loss": 0.7831, "step": 1174 }, { "epoch": 0.3008, "grad_norm": 2.640625, "learning_rate": 4.4991894889514545e-05, "loss": 0.783, "step": 1175 }, { "epoch": 0.301056, "grad_norm": 2.6875, "learning_rate": 4.4987629041890626e-05, "loss": 0.7434, "step": 1176 }, { "epoch": 0.301312, "grad_norm": 2.609375, "learning_rate": 4.49833631942667e-05, "loss": 0.7529, "step": 1177 }, { "epoch": 0.301568, "grad_norm": 2.765625, "learning_rate": 4.497909734664278e-05, "loss": 0.7916, "step": 1178 }, { "epoch": 0.301824, "grad_norm": 2.640625, "learning_rate": 4.4974831499018856e-05, "loss": 0.7802, "step": 1179 }, { "epoch": 0.30208, "grad_norm": 2.765625, "learning_rate": 4.497056565139494e-05, "loss": 0.8156, "step": 1180 }, { "epoch": 0.302336, "grad_norm": 2.796875, "learning_rate": 4.496629980377101e-05, "loss": 0.7526, "step": 1181 }, { "epoch": 0.302592, "grad_norm": 2.84375, "learning_rate": 4.4962033956147085e-05, "loss": 0.7666, "step": 1182 }, { "epoch": 0.302848, "grad_norm": 2.53125, "learning_rate": 4.4957768108523167e-05, "loss": 0.7779, "step": 1183 }, { "epoch": 0.303104, "grad_norm": 2.75, "learning_rate": 4.495350226089924e-05, "loss": 0.7864, "step": 1184 }, { "epoch": 0.30336, "grad_norm": 2.9375, "learning_rate": 4.494923641327532e-05, "loss": 0.7937, "step": 1185 }, { "epoch": 0.303616, "grad_norm": 3.046875, "learning_rate": 4.4944970565651396e-05, "loss": 0.7577, "step": 1186 }, { "epoch": 0.303872, "grad_norm": 2.671875, "learning_rate": 4.494070471802748e-05, "loss": 0.7519, "step": 1187 }, { "epoch": 0.304128, "grad_norm": 2.703125, "learning_rate": 4.493643887040355e-05, "loss": 0.8264, "step": 1188 }, { "epoch": 0.304384, "grad_norm": 2.78125, "learning_rate": 4.4932173022779626e-05, "loss": 0.7985, "step": 1189 }, { "epoch": 0.30464, "grad_norm": 2.734375, "learning_rate": 4.492790717515571e-05, "loss": 0.7868, "step": 1190 }, { "epoch": 0.304896, "grad_norm": 2.453125, "learning_rate": 4.492364132753179e-05, "loss": 0.7843, "step": 1191 }, { "epoch": 0.305152, "grad_norm": 2.515625, "learning_rate": 4.491937547990786e-05, "loss": 0.8093, "step": 1192 }, { "epoch": 0.305408, "grad_norm": 2.78125, "learning_rate": 4.4915109632283936e-05, "loss": 0.7585, "step": 1193 }, { "epoch": 0.305664, "grad_norm": 2.71875, "learning_rate": 4.491084378466001e-05, "loss": 0.7964, "step": 1194 }, { "epoch": 0.30592, "grad_norm": 2.875, "learning_rate": 4.490657793703609e-05, "loss": 0.7582, "step": 1195 }, { "epoch": 0.306176, "grad_norm": 3.015625, "learning_rate": 4.4902312089412166e-05, "loss": 0.7972, "step": 1196 }, { "epoch": 0.306432, "grad_norm": 2.96875, "learning_rate": 4.489804624178825e-05, "loss": 0.8068, "step": 1197 }, { "epoch": 0.306688, "grad_norm": 2.921875, "learning_rate": 4.489378039416433e-05, "loss": 0.7922, "step": 1198 }, { "epoch": 0.306944, "grad_norm": 3.25, "learning_rate": 4.48895145465404e-05, "loss": 0.7744, "step": 1199 }, { "epoch": 0.3072, "grad_norm": 3.28125, "learning_rate": 4.4885248698916476e-05, "loss": 0.782, "step": 1200 }, { "epoch": 0.307456, "grad_norm": 2.671875, "learning_rate": 4.488098285129255e-05, "loss": 0.7731, "step": 1201 }, { "epoch": 0.307712, "grad_norm": 2.765625, "learning_rate": 4.487671700366863e-05, "loss": 0.7652, "step": 1202 }, { "epoch": 0.307968, "grad_norm": 2.75, "learning_rate": 4.4872451156044706e-05, "loss": 0.7526, "step": 1203 }, { "epoch": 0.308224, "grad_norm": 2.84375, "learning_rate": 4.486818530842079e-05, "loss": 0.798, "step": 1204 }, { "epoch": 0.30848, "grad_norm": 2.671875, "learning_rate": 4.486391946079686e-05, "loss": 0.7915, "step": 1205 }, { "epoch": 0.308736, "grad_norm": 2.875, "learning_rate": 4.485965361317294e-05, "loss": 0.8119, "step": 1206 }, { "epoch": 0.308992, "grad_norm": 2.921875, "learning_rate": 4.485538776554902e-05, "loss": 0.8037, "step": 1207 }, { "epoch": 0.309248, "grad_norm": 2.578125, "learning_rate": 4.485112191792509e-05, "loss": 0.8007, "step": 1208 }, { "epoch": 0.309504, "grad_norm": 2.828125, "learning_rate": 4.484685607030117e-05, "loss": 0.7698, "step": 1209 }, { "epoch": 0.30976, "grad_norm": 2.671875, "learning_rate": 4.484259022267725e-05, "loss": 0.8264, "step": 1210 }, { "epoch": 0.310016, "grad_norm": 2.703125, "learning_rate": 4.483832437505333e-05, "loss": 0.766, "step": 1211 }, { "epoch": 0.310272, "grad_norm": 2.984375, "learning_rate": 4.48340585274294e-05, "loss": 0.7625, "step": 1212 }, { "epoch": 0.310528, "grad_norm": 2.65625, "learning_rate": 4.4829792679805476e-05, "loss": 0.7748, "step": 1213 }, { "epoch": 0.310784, "grad_norm": 2.703125, "learning_rate": 4.482552683218156e-05, "loss": 0.7963, "step": 1214 }, { "epoch": 0.31104, "grad_norm": 2.734375, "learning_rate": 4.482126098455763e-05, "loss": 0.8146, "step": 1215 }, { "epoch": 0.311296, "grad_norm": 2.625, "learning_rate": 4.481699513693371e-05, "loss": 0.7709, "step": 1216 }, { "epoch": 0.311552, "grad_norm": 2.578125, "learning_rate": 4.481272928930979e-05, "loss": 0.7521, "step": 1217 }, { "epoch": 0.311808, "grad_norm": 2.796875, "learning_rate": 4.480846344168587e-05, "loss": 0.7296, "step": 1218 }, { "epoch": 0.312064, "grad_norm": 2.75, "learning_rate": 4.480419759406194e-05, "loss": 0.7567, "step": 1219 }, { "epoch": 0.31232, "grad_norm": 2.609375, "learning_rate": 4.4799931746438016e-05, "loss": 0.7689, "step": 1220 }, { "epoch": 0.312576, "grad_norm": 2.859375, "learning_rate": 4.47956658988141e-05, "loss": 0.7995, "step": 1221 }, { "epoch": 0.312832, "grad_norm": 3.0, "learning_rate": 4.479140005119017e-05, "loss": 0.7726, "step": 1222 }, { "epoch": 0.313088, "grad_norm": 2.828125, "learning_rate": 4.478713420356625e-05, "loss": 0.791, "step": 1223 }, { "epoch": 0.313344, "grad_norm": 2.734375, "learning_rate": 4.478286835594233e-05, "loss": 0.7585, "step": 1224 }, { "epoch": 0.3136, "grad_norm": 2.46875, "learning_rate": 4.477860250831841e-05, "loss": 0.7318, "step": 1225 }, { "epoch": 0.313856, "grad_norm": 2.8125, "learning_rate": 4.477433666069448e-05, "loss": 0.7569, "step": 1226 }, { "epoch": 0.314112, "grad_norm": 2.875, "learning_rate": 4.4770070813070556e-05, "loss": 0.7694, "step": 1227 }, { "epoch": 0.314368, "grad_norm": 2.640625, "learning_rate": 4.476580496544663e-05, "loss": 0.7652, "step": 1228 }, { "epoch": 0.314624, "grad_norm": 2.734375, "learning_rate": 4.476153911782272e-05, "loss": 0.7894, "step": 1229 }, { "epoch": 0.31488, "grad_norm": 2.53125, "learning_rate": 4.475727327019879e-05, "loss": 0.7435, "step": 1230 }, { "epoch": 0.315136, "grad_norm": 3.09375, "learning_rate": 4.475300742257487e-05, "loss": 0.7579, "step": 1231 }, { "epoch": 0.315392, "grad_norm": 3.0, "learning_rate": 4.474874157495095e-05, "loss": 0.7762, "step": 1232 }, { "epoch": 0.315648, "grad_norm": 2.53125, "learning_rate": 4.474447572732702e-05, "loss": 0.7172, "step": 1233 }, { "epoch": 0.315904, "grad_norm": 2.984375, "learning_rate": 4.4740209879703096e-05, "loss": 0.7579, "step": 1234 }, { "epoch": 0.31616, "grad_norm": 2.921875, "learning_rate": 4.473594403207918e-05, "loss": 0.7967, "step": 1235 }, { "epoch": 0.316416, "grad_norm": 2.921875, "learning_rate": 4.473167818445526e-05, "loss": 0.7317, "step": 1236 }, { "epoch": 0.316672, "grad_norm": 2.78125, "learning_rate": 4.472741233683133e-05, "loss": 0.7871, "step": 1237 }, { "epoch": 0.316928, "grad_norm": 2.71875, "learning_rate": 4.472314648920741e-05, "loss": 0.7584, "step": 1238 }, { "epoch": 0.317184, "grad_norm": 3.078125, "learning_rate": 4.471888064158348e-05, "loss": 0.7058, "step": 1239 }, { "epoch": 0.31744, "grad_norm": 2.734375, "learning_rate": 4.471461479395956e-05, "loss": 0.7599, "step": 1240 }, { "epoch": 0.317696, "grad_norm": 2.90625, "learning_rate": 4.4710348946335637e-05, "loss": 0.716, "step": 1241 }, { "epoch": 0.317952, "grad_norm": 2.84375, "learning_rate": 4.470608309871172e-05, "loss": 0.7761, "step": 1242 }, { "epoch": 0.318208, "grad_norm": 2.8125, "learning_rate": 4.470181725108779e-05, "loss": 0.7554, "step": 1243 }, { "epoch": 0.318464, "grad_norm": 2.71875, "learning_rate": 4.469755140346387e-05, "loss": 0.7571, "step": 1244 }, { "epoch": 0.31872, "grad_norm": 2.734375, "learning_rate": 4.469328555583995e-05, "loss": 0.7495, "step": 1245 }, { "epoch": 0.318976, "grad_norm": 2.75, "learning_rate": 4.468901970821602e-05, "loss": 0.7912, "step": 1246 }, { "epoch": 0.319232, "grad_norm": 3.109375, "learning_rate": 4.46847538605921e-05, "loss": 0.773, "step": 1247 }, { "epoch": 0.319488, "grad_norm": 2.953125, "learning_rate": 4.4680488012968184e-05, "loss": 0.7521, "step": 1248 }, { "epoch": 0.319744, "grad_norm": 2.890625, "learning_rate": 4.467622216534426e-05, "loss": 0.7812, "step": 1249 }, { "epoch": 0.32, "grad_norm": 2.6875, "learning_rate": 4.467195631772033e-05, "loss": 0.7802, "step": 1250 }, { "epoch": 0.320256, "grad_norm": 3.0, "learning_rate": 4.466769047009641e-05, "loss": 0.769, "step": 1251 }, { "epoch": 0.320512, "grad_norm": 2.859375, "learning_rate": 4.466342462247249e-05, "loss": 0.7397, "step": 1252 }, { "epoch": 0.320768, "grad_norm": 2.8125, "learning_rate": 4.465915877484856e-05, "loss": 0.7564, "step": 1253 }, { "epoch": 0.321024, "grad_norm": 2.609375, "learning_rate": 4.465489292722464e-05, "loss": 0.7778, "step": 1254 }, { "epoch": 0.32128, "grad_norm": 2.71875, "learning_rate": 4.4650627079600724e-05, "loss": 0.7266, "step": 1255 }, { "epoch": 0.321536, "grad_norm": 2.609375, "learning_rate": 4.46463612319768e-05, "loss": 0.7554, "step": 1256 }, { "epoch": 0.321792, "grad_norm": 2.65625, "learning_rate": 4.464209538435287e-05, "loss": 0.7747, "step": 1257 }, { "epoch": 0.322048, "grad_norm": 2.84375, "learning_rate": 4.4637829536728947e-05, "loss": 0.8037, "step": 1258 }, { "epoch": 0.322304, "grad_norm": 2.59375, "learning_rate": 4.463356368910503e-05, "loss": 0.7513, "step": 1259 }, { "epoch": 0.32256, "grad_norm": 3.015625, "learning_rate": 4.46292978414811e-05, "loss": 0.7528, "step": 1260 }, { "epoch": 0.322816, "grad_norm": 3.015625, "learning_rate": 4.462503199385718e-05, "loss": 0.78, "step": 1261 }, { "epoch": 0.323072, "grad_norm": 2.6875, "learning_rate": 4.462076614623326e-05, "loss": 0.7496, "step": 1262 }, { "epoch": 0.323328, "grad_norm": 2.765625, "learning_rate": 4.461650029860934e-05, "loss": 0.7667, "step": 1263 }, { "epoch": 0.323584, "grad_norm": 2.765625, "learning_rate": 4.461223445098541e-05, "loss": 0.7539, "step": 1264 }, { "epoch": 0.32384, "grad_norm": 2.796875, "learning_rate": 4.460796860336149e-05, "loss": 0.7361, "step": 1265 }, { "epoch": 0.324096, "grad_norm": 2.9375, "learning_rate": 4.460370275573757e-05, "loss": 0.7816, "step": 1266 }, { "epoch": 0.324352, "grad_norm": 2.65625, "learning_rate": 4.459943690811364e-05, "loss": 0.7395, "step": 1267 }, { "epoch": 0.324608, "grad_norm": 2.53125, "learning_rate": 4.459517106048972e-05, "loss": 0.7854, "step": 1268 }, { "epoch": 0.324864, "grad_norm": 2.703125, "learning_rate": 4.45909052128658e-05, "loss": 0.7649, "step": 1269 }, { "epoch": 0.32512, "grad_norm": 2.921875, "learning_rate": 4.458663936524188e-05, "loss": 0.7341, "step": 1270 }, { "epoch": 0.325376, "grad_norm": 2.734375, "learning_rate": 4.458237351761795e-05, "loss": 0.7988, "step": 1271 }, { "epoch": 0.325632, "grad_norm": 2.53125, "learning_rate": 4.457810766999403e-05, "loss": 0.7385, "step": 1272 }, { "epoch": 0.325888, "grad_norm": 2.984375, "learning_rate": 4.457384182237011e-05, "loss": 0.7625, "step": 1273 }, { "epoch": 0.326144, "grad_norm": 2.921875, "learning_rate": 4.456957597474619e-05, "loss": 0.7715, "step": 1274 }, { "epoch": 0.3264, "grad_norm": 3.125, "learning_rate": 4.456531012712226e-05, "loss": 0.7755, "step": 1275 }, { "epoch": 0.326656, "grad_norm": 2.921875, "learning_rate": 4.456104427949834e-05, "loss": 0.761, "step": 1276 }, { "epoch": 0.326912, "grad_norm": 3.03125, "learning_rate": 4.455677843187441e-05, "loss": 0.7674, "step": 1277 }, { "epoch": 0.327168, "grad_norm": 2.90625, "learning_rate": 4.455251258425049e-05, "loss": 0.7695, "step": 1278 }, { "epoch": 0.327424, "grad_norm": 2.8125, "learning_rate": 4.454824673662657e-05, "loss": 0.7739, "step": 1279 }, { "epoch": 0.32768, "grad_norm": 2.9375, "learning_rate": 4.454398088900265e-05, "loss": 0.7745, "step": 1280 }, { "epoch": 0.327936, "grad_norm": 2.625, "learning_rate": 4.453971504137873e-05, "loss": 0.7611, "step": 1281 }, { "epoch": 0.328192, "grad_norm": 2.8125, "learning_rate": 4.4535449193754803e-05, "loss": 0.7827, "step": 1282 }, { "epoch": 0.328448, "grad_norm": 3.0, "learning_rate": 4.453118334613088e-05, "loss": 0.7564, "step": 1283 }, { "epoch": 0.328704, "grad_norm": 2.828125, "learning_rate": 4.452691749850695e-05, "loss": 0.7324, "step": 1284 }, { "epoch": 0.32896, "grad_norm": 2.796875, "learning_rate": 4.452265165088303e-05, "loss": 0.7941, "step": 1285 }, { "epoch": 0.329216, "grad_norm": 2.484375, "learning_rate": 4.451838580325911e-05, "loss": 0.7366, "step": 1286 }, { "epoch": 0.329472, "grad_norm": 2.734375, "learning_rate": 4.451411995563519e-05, "loss": 0.7273, "step": 1287 }, { "epoch": 0.329728, "grad_norm": 2.5625, "learning_rate": 4.450985410801126e-05, "loss": 0.7764, "step": 1288 }, { "epoch": 0.329984, "grad_norm": 2.34375, "learning_rate": 4.4505588260387344e-05, "loss": 0.7357, "step": 1289 }, { "epoch": 0.33024, "grad_norm": 2.59375, "learning_rate": 4.450132241276342e-05, "loss": 0.7382, "step": 1290 }, { "epoch": 0.330496, "grad_norm": 2.921875, "learning_rate": 4.449705656513949e-05, "loss": 0.6898, "step": 1291 }, { "epoch": 0.330752, "grad_norm": 2.6875, "learning_rate": 4.449279071751557e-05, "loss": 0.7602, "step": 1292 }, { "epoch": 0.331008, "grad_norm": 2.625, "learning_rate": 4.4488524869891654e-05, "loss": 0.7507, "step": 1293 }, { "epoch": 0.331264, "grad_norm": 2.59375, "learning_rate": 4.448425902226773e-05, "loss": 0.7626, "step": 1294 }, { "epoch": 0.33152, "grad_norm": 2.578125, "learning_rate": 4.44799931746438e-05, "loss": 0.7591, "step": 1295 }, { "epoch": 0.331776, "grad_norm": 2.671875, "learning_rate": 4.447572732701988e-05, "loss": 0.7912, "step": 1296 }, { "epoch": 0.332032, "grad_norm": 2.71875, "learning_rate": 4.447146147939596e-05, "loss": 0.7366, "step": 1297 }, { "epoch": 0.332288, "grad_norm": 2.53125, "learning_rate": 4.446719563177203e-05, "loss": 0.7182, "step": 1298 }, { "epoch": 0.332544, "grad_norm": 2.453125, "learning_rate": 4.4462929784148113e-05, "loss": 0.7713, "step": 1299 }, { "epoch": 0.3328, "grad_norm": 2.65625, "learning_rate": 4.4458663936524195e-05, "loss": 0.7403, "step": 1300 }, { "epoch": 0.333056, "grad_norm": 2.796875, "learning_rate": 4.445439808890027e-05, "loss": 0.7832, "step": 1301 }, { "epoch": 0.333312, "grad_norm": 2.890625, "learning_rate": 4.445013224127634e-05, "loss": 0.7712, "step": 1302 }, { "epoch": 0.333568, "grad_norm": 2.78125, "learning_rate": 4.444586639365242e-05, "loss": 0.7555, "step": 1303 }, { "epoch": 0.333824, "grad_norm": 2.703125, "learning_rate": 4.44416005460285e-05, "loss": 0.7243, "step": 1304 }, { "epoch": 0.33408, "grad_norm": 2.90625, "learning_rate": 4.443733469840457e-05, "loss": 0.7555, "step": 1305 }, { "epoch": 0.334336, "grad_norm": 2.875, "learning_rate": 4.4433068850780654e-05, "loss": 0.7878, "step": 1306 }, { "epoch": 0.334592, "grad_norm": 2.609375, "learning_rate": 4.442880300315673e-05, "loss": 0.7824, "step": 1307 }, { "epoch": 0.334848, "grad_norm": 2.734375, "learning_rate": 4.442453715553281e-05, "loss": 0.7251, "step": 1308 }, { "epoch": 0.335104, "grad_norm": 2.9375, "learning_rate": 4.442027130790888e-05, "loss": 0.7572, "step": 1309 }, { "epoch": 0.33536, "grad_norm": 2.6875, "learning_rate": 4.441600546028496e-05, "loss": 0.7666, "step": 1310 }, { "epoch": 0.335616, "grad_norm": 2.5, "learning_rate": 4.441173961266104e-05, "loss": 0.7847, "step": 1311 }, { "epoch": 0.335872, "grad_norm": 2.65625, "learning_rate": 4.440747376503712e-05, "loss": 0.7296, "step": 1312 }, { "epoch": 0.336128, "grad_norm": 2.78125, "learning_rate": 4.4403207917413194e-05, "loss": 0.7597, "step": 1313 }, { "epoch": 0.336384, "grad_norm": 2.78125, "learning_rate": 4.439894206978927e-05, "loss": 0.7571, "step": 1314 }, { "epoch": 0.33664, "grad_norm": 2.5, "learning_rate": 4.439467622216535e-05, "loss": 0.7494, "step": 1315 }, { "epoch": 0.336896, "grad_norm": 2.5, "learning_rate": 4.4390410374541423e-05, "loss": 0.7551, "step": 1316 }, { "epoch": 0.337152, "grad_norm": 2.53125, "learning_rate": 4.43861445269175e-05, "loss": 0.7201, "step": 1317 }, { "epoch": 0.337408, "grad_norm": 2.234375, "learning_rate": 4.438187867929358e-05, "loss": 0.7692, "step": 1318 }, { "epoch": 0.337664, "grad_norm": 2.5, "learning_rate": 4.437761283166966e-05, "loss": 0.725, "step": 1319 }, { "epoch": 0.33792, "grad_norm": 2.6875, "learning_rate": 4.4373346984045734e-05, "loss": 0.7193, "step": 1320 }, { "epoch": 0.338176, "grad_norm": 2.875, "learning_rate": 4.436908113642181e-05, "loss": 0.7611, "step": 1321 }, { "epoch": 0.338432, "grad_norm": 2.78125, "learning_rate": 4.436481528879788e-05, "loss": 0.765, "step": 1322 }, { "epoch": 0.338688, "grad_norm": 2.671875, "learning_rate": 4.4360549441173964e-05, "loss": 0.6874, "step": 1323 }, { "epoch": 0.338944, "grad_norm": 2.53125, "learning_rate": 4.435628359355004e-05, "loss": 0.7775, "step": 1324 }, { "epoch": 0.3392, "grad_norm": 2.75, "learning_rate": 4.435201774592612e-05, "loss": 0.8337, "step": 1325 }, { "epoch": 0.339456, "grad_norm": 2.734375, "learning_rate": 4.434775189830219e-05, "loss": 0.7324, "step": 1326 }, { "epoch": 0.339712, "grad_norm": 2.40625, "learning_rate": 4.4343486050678274e-05, "loss": 0.714, "step": 1327 }, { "epoch": 0.339968, "grad_norm": 2.828125, "learning_rate": 4.433922020305435e-05, "loss": 0.78, "step": 1328 }, { "epoch": 0.340224, "grad_norm": 2.625, "learning_rate": 4.433495435543042e-05, "loss": 0.7633, "step": 1329 }, { "epoch": 0.34048, "grad_norm": 2.671875, "learning_rate": 4.4330688507806504e-05, "loss": 0.7647, "step": 1330 }, { "epoch": 0.340736, "grad_norm": 2.328125, "learning_rate": 4.4326422660182585e-05, "loss": 0.7499, "step": 1331 }, { "epoch": 0.340992, "grad_norm": 2.703125, "learning_rate": 4.432215681255866e-05, "loss": 0.742, "step": 1332 }, { "epoch": 0.341248, "grad_norm": 2.828125, "learning_rate": 4.431789096493473e-05, "loss": 0.7037, "step": 1333 }, { "epoch": 0.341504, "grad_norm": 2.515625, "learning_rate": 4.4313625117310814e-05, "loss": 0.7, "step": 1334 }, { "epoch": 0.34176, "grad_norm": 2.421875, "learning_rate": 4.430935926968689e-05, "loss": 0.766, "step": 1335 }, { "epoch": 0.342016, "grad_norm": 2.890625, "learning_rate": 4.430509342206296e-05, "loss": 0.739, "step": 1336 }, { "epoch": 0.342272, "grad_norm": 2.75, "learning_rate": 4.4300827574439044e-05, "loss": 0.7634, "step": 1337 }, { "epoch": 0.342528, "grad_norm": 2.453125, "learning_rate": 4.4296561726815125e-05, "loss": 0.7449, "step": 1338 }, { "epoch": 0.342784, "grad_norm": 2.796875, "learning_rate": 4.42922958791912e-05, "loss": 0.7351, "step": 1339 }, { "epoch": 0.34304, "grad_norm": 2.9375, "learning_rate": 4.4288030031567274e-05, "loss": 0.7351, "step": 1340 }, { "epoch": 0.343296, "grad_norm": 2.671875, "learning_rate": 4.428376418394335e-05, "loss": 0.7678, "step": 1341 }, { "epoch": 0.343552, "grad_norm": 2.75, "learning_rate": 4.427949833631943e-05, "loss": 0.7384, "step": 1342 }, { "epoch": 0.343808, "grad_norm": 2.640625, "learning_rate": 4.42752324886955e-05, "loss": 0.7344, "step": 1343 }, { "epoch": 0.344064, "grad_norm": 2.96875, "learning_rate": 4.4270966641071584e-05, "loss": 0.7815, "step": 1344 }, { "epoch": 0.34432, "grad_norm": 2.65625, "learning_rate": 4.426670079344766e-05, "loss": 0.7102, "step": 1345 }, { "epoch": 0.344576, "grad_norm": 2.578125, "learning_rate": 4.426243494582374e-05, "loss": 0.6879, "step": 1346 }, { "epoch": 0.344832, "grad_norm": 2.53125, "learning_rate": 4.4258169098199814e-05, "loss": 0.7223, "step": 1347 }, { "epoch": 0.345088, "grad_norm": 2.734375, "learning_rate": 4.425390325057589e-05, "loss": 0.7489, "step": 1348 }, { "epoch": 0.345344, "grad_norm": 2.78125, "learning_rate": 4.424963740295197e-05, "loss": 0.6848, "step": 1349 }, { "epoch": 0.3456, "grad_norm": 2.8125, "learning_rate": 4.424537155532805e-05, "loss": 0.7441, "step": 1350 }, { "epoch": 0.345856, "grad_norm": 2.734375, "learning_rate": 4.4241105707704124e-05, "loss": 0.7328, "step": 1351 }, { "epoch": 0.346112, "grad_norm": 2.53125, "learning_rate": 4.42368398600802e-05, "loss": 0.7452, "step": 1352 }, { "epoch": 0.346368, "grad_norm": 2.75, "learning_rate": 4.423257401245628e-05, "loss": 0.761, "step": 1353 }, { "epoch": 0.346624, "grad_norm": 2.8125, "learning_rate": 4.4228308164832354e-05, "loss": 0.7479, "step": 1354 }, { "epoch": 0.34688, "grad_norm": 2.390625, "learning_rate": 4.422404231720843e-05, "loss": 0.7443, "step": 1355 }, { "epoch": 0.347136, "grad_norm": 2.578125, "learning_rate": 4.421977646958451e-05, "loss": 0.7635, "step": 1356 }, { "epoch": 0.347392, "grad_norm": 2.5, "learning_rate": 4.421551062196059e-05, "loss": 0.7619, "step": 1357 }, { "epoch": 0.347648, "grad_norm": 2.578125, "learning_rate": 4.4211244774336665e-05, "loss": 0.758, "step": 1358 }, { "epoch": 0.347904, "grad_norm": 2.859375, "learning_rate": 4.420697892671274e-05, "loss": 0.7369, "step": 1359 }, { "epoch": 0.34816, "grad_norm": 2.859375, "learning_rate": 4.420271307908881e-05, "loss": 0.7649, "step": 1360 }, { "epoch": 0.348416, "grad_norm": 2.578125, "learning_rate": 4.4198447231464894e-05, "loss": 0.7169, "step": 1361 }, { "epoch": 0.348672, "grad_norm": 2.546875, "learning_rate": 4.419418138384097e-05, "loss": 0.7654, "step": 1362 }, { "epoch": 0.348928, "grad_norm": 2.625, "learning_rate": 4.418991553621705e-05, "loss": 0.7959, "step": 1363 }, { "epoch": 0.349184, "grad_norm": 2.921875, "learning_rate": 4.418564968859313e-05, "loss": 0.7101, "step": 1364 }, { "epoch": 0.34944, "grad_norm": 2.640625, "learning_rate": 4.4181383840969205e-05, "loss": 0.753, "step": 1365 }, { "epoch": 0.349696, "grad_norm": 2.59375, "learning_rate": 4.417711799334528e-05, "loss": 0.7101, "step": 1366 }, { "epoch": 0.349952, "grad_norm": 2.828125, "learning_rate": 4.417285214572135e-05, "loss": 0.7377, "step": 1367 }, { "epoch": 0.350208, "grad_norm": 2.875, "learning_rate": 4.4168586298097434e-05, "loss": 0.7182, "step": 1368 }, { "epoch": 0.350464, "grad_norm": 2.953125, "learning_rate": 4.416432045047351e-05, "loss": 0.7057, "step": 1369 }, { "epoch": 0.35072, "grad_norm": 2.796875, "learning_rate": 4.416005460284959e-05, "loss": 0.7937, "step": 1370 }, { "epoch": 0.350976, "grad_norm": 2.5, "learning_rate": 4.4155788755225664e-05, "loss": 0.7224, "step": 1371 }, { "epoch": 0.351232, "grad_norm": 2.484375, "learning_rate": 4.4151522907601745e-05, "loss": 0.706, "step": 1372 }, { "epoch": 0.351488, "grad_norm": 2.671875, "learning_rate": 4.414725705997782e-05, "loss": 0.7347, "step": 1373 }, { "epoch": 0.351744, "grad_norm": 2.65625, "learning_rate": 4.4142991212353893e-05, "loss": 0.7248, "step": 1374 }, { "epoch": 0.352, "grad_norm": 2.640625, "learning_rate": 4.4138725364729975e-05, "loss": 0.7525, "step": 1375 }, { "epoch": 0.352256, "grad_norm": 2.5625, "learning_rate": 4.4134459517106056e-05, "loss": 0.7782, "step": 1376 }, { "epoch": 0.352512, "grad_norm": 2.734375, "learning_rate": 4.413019366948213e-05, "loss": 0.7651, "step": 1377 }, { "epoch": 0.352768, "grad_norm": 2.5625, "learning_rate": 4.4125927821858204e-05, "loss": 0.7412, "step": 1378 }, { "epoch": 0.353024, "grad_norm": 2.59375, "learning_rate": 4.4121661974234285e-05, "loss": 0.721, "step": 1379 }, { "epoch": 0.35328, "grad_norm": 2.953125, "learning_rate": 4.411739612661036e-05, "loss": 0.7084, "step": 1380 }, { "epoch": 0.353536, "grad_norm": 2.78125, "learning_rate": 4.4113130278986434e-05, "loss": 0.7524, "step": 1381 }, { "epoch": 0.353792, "grad_norm": 2.625, "learning_rate": 4.4108864431362515e-05, "loss": 0.733, "step": 1382 }, { "epoch": 0.354048, "grad_norm": 3.140625, "learning_rate": 4.4104598583738596e-05, "loss": 0.7392, "step": 1383 }, { "epoch": 0.354304, "grad_norm": 3.140625, "learning_rate": 4.410033273611467e-05, "loss": 0.7431, "step": 1384 }, { "epoch": 0.35456, "grad_norm": 2.875, "learning_rate": 4.4096066888490744e-05, "loss": 0.7349, "step": 1385 }, { "epoch": 0.354816, "grad_norm": 2.640625, "learning_rate": 4.409180104086682e-05, "loss": 0.7701, "step": 1386 }, { "epoch": 0.355072, "grad_norm": 2.6875, "learning_rate": 4.40875351932429e-05, "loss": 0.7292, "step": 1387 }, { "epoch": 0.355328, "grad_norm": 2.859375, "learning_rate": 4.4083269345618974e-05, "loss": 0.7494, "step": 1388 }, { "epoch": 0.355584, "grad_norm": 2.671875, "learning_rate": 4.4079003497995055e-05, "loss": 0.7234, "step": 1389 }, { "epoch": 0.35584, "grad_norm": 2.515625, "learning_rate": 4.407473765037113e-05, "loss": 0.7233, "step": 1390 }, { "epoch": 0.356096, "grad_norm": 2.640625, "learning_rate": 4.407047180274721e-05, "loss": 0.7373, "step": 1391 }, { "epoch": 0.356352, "grad_norm": 2.734375, "learning_rate": 4.4066205955123285e-05, "loss": 0.782, "step": 1392 }, { "epoch": 0.356608, "grad_norm": 2.65625, "learning_rate": 4.406194010749936e-05, "loss": 0.7088, "step": 1393 }, { "epoch": 0.356864, "grad_norm": 2.390625, "learning_rate": 4.405767425987544e-05, "loss": 0.7147, "step": 1394 }, { "epoch": 0.35712, "grad_norm": 2.5625, "learning_rate": 4.405340841225152e-05, "loss": 0.7284, "step": 1395 }, { "epoch": 0.357376, "grad_norm": 2.90625, "learning_rate": 4.4049142564627595e-05, "loss": 0.7593, "step": 1396 }, { "epoch": 0.357632, "grad_norm": 2.765625, "learning_rate": 4.404487671700367e-05, "loss": 0.7317, "step": 1397 }, { "epoch": 0.357888, "grad_norm": 2.8125, "learning_rate": 4.404061086937975e-05, "loss": 0.7471, "step": 1398 }, { "epoch": 0.358144, "grad_norm": 2.671875, "learning_rate": 4.4036345021755825e-05, "loss": 0.7439, "step": 1399 }, { "epoch": 0.3584, "grad_norm": 2.65625, "learning_rate": 4.40320791741319e-05, "loss": 0.7315, "step": 1400 }, { "epoch": 0.358656, "grad_norm": 2.421875, "learning_rate": 4.402781332650798e-05, "loss": 0.7378, "step": 1401 }, { "epoch": 0.358912, "grad_norm": 2.8125, "learning_rate": 4.402354747888406e-05, "loss": 0.7316, "step": 1402 }, { "epoch": 0.359168, "grad_norm": 2.640625, "learning_rate": 4.4019281631260135e-05, "loss": 0.7004, "step": 1403 }, { "epoch": 0.359424, "grad_norm": 2.484375, "learning_rate": 4.401501578363621e-05, "loss": 0.7653, "step": 1404 }, { "epoch": 0.35968, "grad_norm": 2.25, "learning_rate": 4.4010749936012284e-05, "loss": 0.7179, "step": 1405 }, { "epoch": 0.359936, "grad_norm": 2.4375, "learning_rate": 4.4006484088388365e-05, "loss": 0.7254, "step": 1406 }, { "epoch": 0.360192, "grad_norm": 2.296875, "learning_rate": 4.400221824076444e-05, "loss": 0.7393, "step": 1407 }, { "epoch": 0.360448, "grad_norm": 2.765625, "learning_rate": 4.399795239314052e-05, "loss": 0.749, "step": 1408 }, { "epoch": 0.360704, "grad_norm": 2.546875, "learning_rate": 4.3993686545516594e-05, "loss": 0.7727, "step": 1409 }, { "epoch": 0.36096, "grad_norm": 2.78125, "learning_rate": 4.3989420697892676e-05, "loss": 0.6885, "step": 1410 }, { "epoch": 0.361216, "grad_norm": 2.71875, "learning_rate": 4.398515485026875e-05, "loss": 0.6928, "step": 1411 }, { "epoch": 0.361472, "grad_norm": 2.671875, "learning_rate": 4.3980889002644824e-05, "loss": 0.7181, "step": 1412 }, { "epoch": 0.361728, "grad_norm": 2.484375, "learning_rate": 4.3976623155020905e-05, "loss": 0.7296, "step": 1413 }, { "epoch": 0.361984, "grad_norm": 2.640625, "learning_rate": 4.3972357307396986e-05, "loss": 0.7322, "step": 1414 }, { "epoch": 0.36224, "grad_norm": 2.59375, "learning_rate": 4.396809145977306e-05, "loss": 0.6991, "step": 1415 }, { "epoch": 0.362496, "grad_norm": 2.703125, "learning_rate": 4.3963825612149135e-05, "loss": 0.719, "step": 1416 }, { "epoch": 0.362752, "grad_norm": 2.796875, "learning_rate": 4.3959559764525216e-05, "loss": 0.7441, "step": 1417 }, { "epoch": 0.363008, "grad_norm": 3.109375, "learning_rate": 4.395529391690129e-05, "loss": 0.7237, "step": 1418 }, { "epoch": 0.363264, "grad_norm": 2.78125, "learning_rate": 4.3951028069277364e-05, "loss": 0.6989, "step": 1419 }, { "epoch": 0.36352, "grad_norm": 2.640625, "learning_rate": 4.3946762221653445e-05, "loss": 0.7339, "step": 1420 }, { "epoch": 0.363776, "grad_norm": 2.6875, "learning_rate": 4.3942496374029526e-05, "loss": 0.7161, "step": 1421 }, { "epoch": 0.364032, "grad_norm": 2.671875, "learning_rate": 4.39382305264056e-05, "loss": 0.7219, "step": 1422 }, { "epoch": 0.364288, "grad_norm": 2.546875, "learning_rate": 4.3933964678781675e-05, "loss": 0.7418, "step": 1423 }, { "epoch": 0.364544, "grad_norm": 2.578125, "learning_rate": 4.392969883115775e-05, "loss": 0.7482, "step": 1424 }, { "epoch": 0.3648, "grad_norm": 2.765625, "learning_rate": 4.392543298353383e-05, "loss": 0.7427, "step": 1425 }, { "epoch": 0.365056, "grad_norm": 2.9375, "learning_rate": 4.3921167135909904e-05, "loss": 0.73, "step": 1426 }, { "epoch": 0.365312, "grad_norm": 2.984375, "learning_rate": 4.3916901288285985e-05, "loss": 0.722, "step": 1427 }, { "epoch": 0.365568, "grad_norm": 2.859375, "learning_rate": 4.3912635440662067e-05, "loss": 0.7153, "step": 1428 }, { "epoch": 0.365824, "grad_norm": 2.796875, "learning_rate": 4.390836959303814e-05, "loss": 0.711, "step": 1429 }, { "epoch": 0.36608, "grad_norm": 2.5625, "learning_rate": 4.3904103745414215e-05, "loss": 0.724, "step": 1430 }, { "epoch": 0.366336, "grad_norm": 2.875, "learning_rate": 4.389983789779029e-05, "loss": 0.7646, "step": 1431 }, { "epoch": 0.366592, "grad_norm": 2.78125, "learning_rate": 4.389557205016637e-05, "loss": 0.7068, "step": 1432 }, { "epoch": 0.366848, "grad_norm": 2.375, "learning_rate": 4.389130620254245e-05, "loss": 0.7501, "step": 1433 }, { "epoch": 0.367104, "grad_norm": 2.6875, "learning_rate": 4.3887040354918526e-05, "loss": 0.7264, "step": 1434 }, { "epoch": 0.36736, "grad_norm": 2.921875, "learning_rate": 4.38827745072946e-05, "loss": 0.6941, "step": 1435 }, { "epoch": 0.367616, "grad_norm": 2.71875, "learning_rate": 4.387850865967068e-05, "loss": 0.7235, "step": 1436 }, { "epoch": 0.367872, "grad_norm": 2.5625, "learning_rate": 4.3874242812046755e-05, "loss": 0.6939, "step": 1437 }, { "epoch": 0.368128, "grad_norm": 2.875, "learning_rate": 4.386997696442283e-05, "loss": 0.7425, "step": 1438 }, { "epoch": 0.368384, "grad_norm": 2.90625, "learning_rate": 4.386571111679891e-05, "loss": 0.6986, "step": 1439 }, { "epoch": 0.36864, "grad_norm": 2.453125, "learning_rate": 4.386144526917499e-05, "loss": 0.7733, "step": 1440 }, { "epoch": 0.368896, "grad_norm": 2.796875, "learning_rate": 4.3857179421551066e-05, "loss": 0.6908, "step": 1441 }, { "epoch": 0.369152, "grad_norm": 3.03125, "learning_rate": 4.385291357392714e-05, "loss": 0.7518, "step": 1442 }, { "epoch": 0.369408, "grad_norm": 2.640625, "learning_rate": 4.3848647726303214e-05, "loss": 0.6895, "step": 1443 }, { "epoch": 0.369664, "grad_norm": 2.71875, "learning_rate": 4.3844381878679295e-05, "loss": 0.7039, "step": 1444 }, { "epoch": 0.36992, "grad_norm": 2.65625, "learning_rate": 4.384011603105537e-05, "loss": 0.716, "step": 1445 }, { "epoch": 0.370176, "grad_norm": 2.90625, "learning_rate": 4.383585018343145e-05, "loss": 0.6873, "step": 1446 }, { "epoch": 0.370432, "grad_norm": 2.75, "learning_rate": 4.383158433580753e-05, "loss": 0.6972, "step": 1447 }, { "epoch": 0.370688, "grad_norm": 2.46875, "learning_rate": 4.3827318488183606e-05, "loss": 0.7302, "step": 1448 }, { "epoch": 0.370944, "grad_norm": 2.765625, "learning_rate": 4.382305264055968e-05, "loss": 0.7397, "step": 1449 }, { "epoch": 0.3712, "grad_norm": 2.78125, "learning_rate": 4.3818786792935755e-05, "loss": 0.6869, "step": 1450 }, { "epoch": 0.371456, "grad_norm": 2.765625, "learning_rate": 4.3814520945311836e-05, "loss": 0.7252, "step": 1451 }, { "epoch": 0.371712, "grad_norm": 2.859375, "learning_rate": 4.381025509768792e-05, "loss": 0.7391, "step": 1452 }, { "epoch": 0.371968, "grad_norm": 2.703125, "learning_rate": 4.380598925006399e-05, "loss": 0.7236, "step": 1453 }, { "epoch": 0.372224, "grad_norm": 2.6875, "learning_rate": 4.3801723402440065e-05, "loss": 0.743, "step": 1454 }, { "epoch": 0.37248, "grad_norm": 2.421875, "learning_rate": 4.3797457554816146e-05, "loss": 0.7525, "step": 1455 }, { "epoch": 0.372736, "grad_norm": 2.9375, "learning_rate": 4.379319170719222e-05, "loss": 0.7408, "step": 1456 }, { "epoch": 0.372992, "grad_norm": 2.5625, "learning_rate": 4.3788925859568295e-05, "loss": 0.7015, "step": 1457 }, { "epoch": 0.373248, "grad_norm": 2.734375, "learning_rate": 4.3784660011944376e-05, "loss": 0.6763, "step": 1458 }, { "epoch": 0.373504, "grad_norm": 2.640625, "learning_rate": 4.378039416432046e-05, "loss": 0.7126, "step": 1459 }, { "epoch": 0.37376, "grad_norm": 2.734375, "learning_rate": 4.377612831669653e-05, "loss": 0.6998, "step": 1460 }, { "epoch": 0.374016, "grad_norm": 2.75, "learning_rate": 4.3771862469072605e-05, "loss": 0.7113, "step": 1461 }, { "epoch": 0.374272, "grad_norm": 2.46875, "learning_rate": 4.3767596621448686e-05, "loss": 0.6934, "step": 1462 }, { "epoch": 0.374528, "grad_norm": 2.453125, "learning_rate": 4.376333077382476e-05, "loss": 0.7347, "step": 1463 }, { "epoch": 0.374784, "grad_norm": 2.296875, "learning_rate": 4.3759064926200835e-05, "loss": 0.686, "step": 1464 }, { "epoch": 0.37504, "grad_norm": 2.5625, "learning_rate": 4.3754799078576916e-05, "loss": 0.6733, "step": 1465 }, { "epoch": 0.375296, "grad_norm": 2.71875, "learning_rate": 4.3750533230953e-05, "loss": 0.7125, "step": 1466 }, { "epoch": 0.375552, "grad_norm": 2.703125, "learning_rate": 4.374626738332907e-05, "loss": 0.7097, "step": 1467 }, { "epoch": 0.375808, "grad_norm": 2.5, "learning_rate": 4.3742001535705146e-05, "loss": 0.7072, "step": 1468 }, { "epoch": 0.376064, "grad_norm": 2.75, "learning_rate": 4.373773568808122e-05, "loss": 0.7305, "step": 1469 }, { "epoch": 0.37632, "grad_norm": 3.09375, "learning_rate": 4.37334698404573e-05, "loss": 0.7499, "step": 1470 }, { "epoch": 0.376576, "grad_norm": 2.796875, "learning_rate": 4.3729203992833375e-05, "loss": 0.7101, "step": 1471 }, { "epoch": 0.376832, "grad_norm": 2.3125, "learning_rate": 4.3724938145209456e-05, "loss": 0.6967, "step": 1472 }, { "epoch": 0.377088, "grad_norm": 2.609375, "learning_rate": 4.372067229758553e-05, "loss": 0.7119, "step": 1473 }, { "epoch": 0.377344, "grad_norm": 2.5, "learning_rate": 4.371640644996161e-05, "loss": 0.7216, "step": 1474 }, { "epoch": 0.3776, "grad_norm": 2.75, "learning_rate": 4.3712140602337686e-05, "loss": 0.7246, "step": 1475 }, { "epoch": 0.377856, "grad_norm": 2.40625, "learning_rate": 4.370787475471376e-05, "loss": 0.732, "step": 1476 }, { "epoch": 0.378112, "grad_norm": 2.703125, "learning_rate": 4.370360890708984e-05, "loss": 0.6912, "step": 1477 }, { "epoch": 0.378368, "grad_norm": 3.0, "learning_rate": 4.369934305946592e-05, "loss": 0.7288, "step": 1478 }, { "epoch": 0.378624, "grad_norm": 3.125, "learning_rate": 4.3695077211841996e-05, "loss": 0.6926, "step": 1479 }, { "epoch": 0.37888, "grad_norm": 2.703125, "learning_rate": 4.369081136421807e-05, "loss": 0.6937, "step": 1480 }, { "epoch": 0.379136, "grad_norm": 2.765625, "learning_rate": 4.368654551659415e-05, "loss": 0.7046, "step": 1481 }, { "epoch": 0.379392, "grad_norm": 2.875, "learning_rate": 4.3682279668970226e-05, "loss": 0.7332, "step": 1482 }, { "epoch": 0.379648, "grad_norm": 2.59375, "learning_rate": 4.36780138213463e-05, "loss": 0.676, "step": 1483 }, { "epoch": 0.379904, "grad_norm": 2.5625, "learning_rate": 4.367374797372238e-05, "loss": 0.7306, "step": 1484 }, { "epoch": 0.38016, "grad_norm": 2.515625, "learning_rate": 4.366948212609846e-05, "loss": 0.6826, "step": 1485 }, { "epoch": 0.380416, "grad_norm": 2.5625, "learning_rate": 4.3665216278474537e-05, "loss": 0.7017, "step": 1486 }, { "epoch": 0.380672, "grad_norm": 2.546875, "learning_rate": 4.366095043085061e-05, "loss": 0.7476, "step": 1487 }, { "epoch": 0.380928, "grad_norm": 2.890625, "learning_rate": 4.3656684583226685e-05, "loss": 0.67, "step": 1488 }, { "epoch": 0.381184, "grad_norm": 2.8125, "learning_rate": 4.3652418735602766e-05, "loss": 0.7496, "step": 1489 }, { "epoch": 0.38144, "grad_norm": 2.609375, "learning_rate": 4.364815288797884e-05, "loss": 0.6717, "step": 1490 }, { "epoch": 0.381696, "grad_norm": 2.609375, "learning_rate": 4.364388704035492e-05, "loss": 0.6875, "step": 1491 }, { "epoch": 0.381952, "grad_norm": 2.609375, "learning_rate": 4.3639621192730996e-05, "loss": 0.6955, "step": 1492 }, { "epoch": 0.382208, "grad_norm": 2.53125, "learning_rate": 4.363535534510708e-05, "loss": 0.689, "step": 1493 }, { "epoch": 0.382464, "grad_norm": 2.546875, "learning_rate": 4.363108949748315e-05, "loss": 0.6798, "step": 1494 }, { "epoch": 0.38272, "grad_norm": 2.75, "learning_rate": 4.3626823649859225e-05, "loss": 0.6981, "step": 1495 }, { "epoch": 0.382976, "grad_norm": 2.4375, "learning_rate": 4.3622557802235306e-05, "loss": 0.749, "step": 1496 }, { "epoch": 0.383232, "grad_norm": 2.46875, "learning_rate": 4.361829195461139e-05, "loss": 0.6926, "step": 1497 }, { "epoch": 0.383488, "grad_norm": 2.921875, "learning_rate": 4.361402610698746e-05, "loss": 0.686, "step": 1498 }, { "epoch": 0.383744, "grad_norm": 2.765625, "learning_rate": 4.3609760259363536e-05, "loss": 0.7196, "step": 1499 }, { "epoch": 0.384, "grad_norm": 2.546875, "learning_rate": 4.360549441173962e-05, "loss": 0.7208, "step": 1500 }, { "epoch": 0.384256, "grad_norm": 2.5625, "learning_rate": 4.360122856411569e-05, "loss": 0.6823, "step": 1501 }, { "epoch": 0.384512, "grad_norm": 2.484375, "learning_rate": 4.3596962716491766e-05, "loss": 0.725, "step": 1502 }, { "epoch": 0.384768, "grad_norm": 2.609375, "learning_rate": 4.3592696868867847e-05, "loss": 0.7014, "step": 1503 }, { "epoch": 0.385024, "grad_norm": 2.828125, "learning_rate": 4.358843102124393e-05, "loss": 0.6872, "step": 1504 }, { "epoch": 0.38528, "grad_norm": 2.953125, "learning_rate": 4.358416517362e-05, "loss": 0.7275, "step": 1505 }, { "epoch": 0.385536, "grad_norm": 2.921875, "learning_rate": 4.3579899325996076e-05, "loss": 0.7212, "step": 1506 }, { "epoch": 0.385792, "grad_norm": 2.671875, "learning_rate": 4.357563347837215e-05, "loss": 0.7378, "step": 1507 }, { "epoch": 0.386048, "grad_norm": 2.453125, "learning_rate": 4.357136763074823e-05, "loss": 0.6993, "step": 1508 }, { "epoch": 0.386304, "grad_norm": 2.625, "learning_rate": 4.3567101783124306e-05, "loss": 0.6595, "step": 1509 }, { "epoch": 0.38656, "grad_norm": 3.0, "learning_rate": 4.356283593550039e-05, "loss": 0.7302, "step": 1510 }, { "epoch": 0.386816, "grad_norm": 2.546875, "learning_rate": 4.355857008787647e-05, "loss": 0.6922, "step": 1511 }, { "epoch": 0.387072, "grad_norm": 2.640625, "learning_rate": 4.355430424025254e-05, "loss": 0.6858, "step": 1512 }, { "epoch": 0.387328, "grad_norm": 2.6875, "learning_rate": 4.3550038392628616e-05, "loss": 0.773, "step": 1513 }, { "epoch": 0.387584, "grad_norm": 2.484375, "learning_rate": 4.354577254500469e-05, "loss": 0.7197, "step": 1514 }, { "epoch": 0.38784, "grad_norm": 2.40625, "learning_rate": 4.354150669738077e-05, "loss": 0.7421, "step": 1515 }, { "epoch": 0.388096, "grad_norm": 3.03125, "learning_rate": 4.353724084975685e-05, "loss": 0.687, "step": 1516 }, { "epoch": 0.388352, "grad_norm": 2.90625, "learning_rate": 4.353297500213293e-05, "loss": 0.7107, "step": 1517 }, { "epoch": 0.388608, "grad_norm": 2.625, "learning_rate": 4.3528709154509e-05, "loss": 0.6864, "step": 1518 }, { "epoch": 0.388864, "grad_norm": 2.796875, "learning_rate": 4.352444330688508e-05, "loss": 0.7218, "step": 1519 }, { "epoch": 0.38912, "grad_norm": 2.734375, "learning_rate": 4.3520177459261157e-05, "loss": 0.6927, "step": 1520 }, { "epoch": 0.389376, "grad_norm": 2.734375, "learning_rate": 4.351591161163723e-05, "loss": 0.6829, "step": 1521 }, { "epoch": 0.389632, "grad_norm": 2.75, "learning_rate": 4.351164576401331e-05, "loss": 0.6996, "step": 1522 }, { "epoch": 0.389888, "grad_norm": 2.46875, "learning_rate": 4.350737991638939e-05, "loss": 0.6763, "step": 1523 }, { "epoch": 0.390144, "grad_norm": 2.5625, "learning_rate": 4.350311406876547e-05, "loss": 0.7229, "step": 1524 }, { "epoch": 0.3904, "grad_norm": 2.65625, "learning_rate": 4.349884822114154e-05, "loss": 0.6973, "step": 1525 }, { "epoch": 0.390656, "grad_norm": 2.59375, "learning_rate": 4.349458237351762e-05, "loss": 0.7336, "step": 1526 }, { "epoch": 0.390912, "grad_norm": 2.78125, "learning_rate": 4.34903165258937e-05, "loss": 0.6805, "step": 1527 }, { "epoch": 0.391168, "grad_norm": 2.890625, "learning_rate": 4.348605067826977e-05, "loss": 0.7329, "step": 1528 }, { "epoch": 0.391424, "grad_norm": 2.671875, "learning_rate": 4.348178483064585e-05, "loss": 0.6951, "step": 1529 }, { "epoch": 0.39168, "grad_norm": 2.421875, "learning_rate": 4.347751898302193e-05, "loss": 0.7335, "step": 1530 }, { "epoch": 0.391936, "grad_norm": 2.546875, "learning_rate": 4.347325313539801e-05, "loss": 0.6941, "step": 1531 }, { "epoch": 0.392192, "grad_norm": 2.59375, "learning_rate": 4.346898728777408e-05, "loss": 0.7124, "step": 1532 }, { "epoch": 0.392448, "grad_norm": 2.46875, "learning_rate": 4.3464721440150156e-05, "loss": 0.7248, "step": 1533 }, { "epoch": 0.392704, "grad_norm": 2.71875, "learning_rate": 4.346045559252624e-05, "loss": 0.662, "step": 1534 }, { "epoch": 0.39296, "grad_norm": 2.78125, "learning_rate": 4.345618974490232e-05, "loss": 0.6914, "step": 1535 }, { "epoch": 0.393216, "grad_norm": 2.546875, "learning_rate": 4.345192389727839e-05, "loss": 0.712, "step": 1536 }, { "epoch": 0.393472, "grad_norm": 2.5625, "learning_rate": 4.3447658049654466e-05, "loss": 0.7049, "step": 1537 }, { "epoch": 0.393728, "grad_norm": 2.828125, "learning_rate": 4.344339220203055e-05, "loss": 0.6976, "step": 1538 }, { "epoch": 0.393984, "grad_norm": 2.796875, "learning_rate": 4.343912635440662e-05, "loss": 0.7509, "step": 1539 }, { "epoch": 0.39424, "grad_norm": 2.78125, "learning_rate": 4.3434860506782696e-05, "loss": 0.667, "step": 1540 }, { "epoch": 0.394496, "grad_norm": 2.84375, "learning_rate": 4.343059465915878e-05, "loss": 0.716, "step": 1541 }, { "epoch": 0.394752, "grad_norm": 2.890625, "learning_rate": 4.342632881153486e-05, "loss": 0.6706, "step": 1542 }, { "epoch": 0.395008, "grad_norm": 2.796875, "learning_rate": 4.342206296391093e-05, "loss": 0.6881, "step": 1543 }, { "epoch": 0.395264, "grad_norm": 2.5625, "learning_rate": 4.341779711628701e-05, "loss": 0.741, "step": 1544 }, { "epoch": 0.39552, "grad_norm": 2.625, "learning_rate": 4.341353126866309e-05, "loss": 0.6485, "step": 1545 }, { "epoch": 0.395776, "grad_norm": 2.515625, "learning_rate": 4.340926542103916e-05, "loss": 0.7342, "step": 1546 }, { "epoch": 0.396032, "grad_norm": 2.828125, "learning_rate": 4.3404999573415236e-05, "loss": 0.6714, "step": 1547 }, { "epoch": 0.396288, "grad_norm": 2.828125, "learning_rate": 4.340073372579132e-05, "loss": 0.7346, "step": 1548 }, { "epoch": 0.396544, "grad_norm": 2.46875, "learning_rate": 4.33964678781674e-05, "loss": 0.7321, "step": 1549 }, { "epoch": 0.3968, "grad_norm": 2.59375, "learning_rate": 4.339220203054347e-05, "loss": 0.6918, "step": 1550 }, { "epoch": 0.397056, "grad_norm": 2.4375, "learning_rate": 4.338793618291955e-05, "loss": 0.6977, "step": 1551 }, { "epoch": 0.397312, "grad_norm": 2.84375, "learning_rate": 4.338367033529562e-05, "loss": 0.7053, "step": 1552 }, { "epoch": 0.397568, "grad_norm": 2.40625, "learning_rate": 4.33794044876717e-05, "loss": 0.7162, "step": 1553 }, { "epoch": 0.397824, "grad_norm": 2.609375, "learning_rate": 4.337513864004778e-05, "loss": 0.6474, "step": 1554 }, { "epoch": 0.39808, "grad_norm": 2.625, "learning_rate": 4.337087279242386e-05, "loss": 0.6437, "step": 1555 }, { "epoch": 0.398336, "grad_norm": 2.78125, "learning_rate": 4.336660694479993e-05, "loss": 0.6861, "step": 1556 }, { "epoch": 0.398592, "grad_norm": 2.671875, "learning_rate": 4.336234109717601e-05, "loss": 0.6858, "step": 1557 }, { "epoch": 0.398848, "grad_norm": 2.875, "learning_rate": 4.335807524955209e-05, "loss": 0.6819, "step": 1558 }, { "epoch": 0.399104, "grad_norm": 2.84375, "learning_rate": 4.335380940192816e-05, "loss": 0.7111, "step": 1559 }, { "epoch": 0.39936, "grad_norm": 2.609375, "learning_rate": 4.334954355430424e-05, "loss": 0.7201, "step": 1560 }, { "epoch": 0.399616, "grad_norm": 2.703125, "learning_rate": 4.3345277706680323e-05, "loss": 0.6794, "step": 1561 }, { "epoch": 0.399872, "grad_norm": 2.65625, "learning_rate": 4.33410118590564e-05, "loss": 0.7045, "step": 1562 }, { "epoch": 0.400128, "grad_norm": 2.875, "learning_rate": 4.333674601143247e-05, "loss": 0.6884, "step": 1563 }, { "epoch": 0.400384, "grad_norm": 2.71875, "learning_rate": 4.333248016380855e-05, "loss": 0.6928, "step": 1564 }, { "epoch": 0.40064, "grad_norm": 2.578125, "learning_rate": 4.332821431618463e-05, "loss": 0.6734, "step": 1565 }, { "epoch": 0.400896, "grad_norm": 2.4375, "learning_rate": 4.33239484685607e-05, "loss": 0.7, "step": 1566 }, { "epoch": 0.401152, "grad_norm": 2.625, "learning_rate": 4.331968262093678e-05, "loss": 0.6719, "step": 1567 }, { "epoch": 0.401408, "grad_norm": 2.75, "learning_rate": 4.3315416773312864e-05, "loss": 0.686, "step": 1568 }, { "epoch": 0.401664, "grad_norm": 2.46875, "learning_rate": 4.331115092568894e-05, "loss": 0.682, "step": 1569 }, { "epoch": 0.40192, "grad_norm": 2.796875, "learning_rate": 4.330688507806501e-05, "loss": 0.6865, "step": 1570 }, { "epoch": 0.402176, "grad_norm": 2.890625, "learning_rate": 4.3302619230441086e-05, "loss": 0.6534, "step": 1571 }, { "epoch": 0.402432, "grad_norm": 2.578125, "learning_rate": 4.329835338281717e-05, "loss": 0.7075, "step": 1572 }, { "epoch": 0.402688, "grad_norm": 2.765625, "learning_rate": 4.329408753519325e-05, "loss": 0.6402, "step": 1573 }, { "epoch": 0.402944, "grad_norm": 3.046875, "learning_rate": 4.328982168756932e-05, "loss": 0.7562, "step": 1574 }, { "epoch": 0.4032, "grad_norm": 2.890625, "learning_rate": 4.3285555839945404e-05, "loss": 0.7184, "step": 1575 }, { "epoch": 0.403456, "grad_norm": 2.484375, "learning_rate": 4.328128999232148e-05, "loss": 0.7241, "step": 1576 }, { "epoch": 0.403712, "grad_norm": 2.515625, "learning_rate": 4.327702414469755e-05, "loss": 0.7397, "step": 1577 }, { "epoch": 0.403968, "grad_norm": 2.421875, "learning_rate": 4.3272758297073627e-05, "loss": 0.7104, "step": 1578 }, { "epoch": 0.404224, "grad_norm": 2.515625, "learning_rate": 4.326849244944971e-05, "loss": 0.68, "step": 1579 }, { "epoch": 0.40448, "grad_norm": 2.8125, "learning_rate": 4.326422660182579e-05, "loss": 0.6881, "step": 1580 }, { "epoch": 0.404736, "grad_norm": 2.703125, "learning_rate": 4.325996075420186e-05, "loss": 0.6996, "step": 1581 }, { "epoch": 0.404992, "grad_norm": 2.21875, "learning_rate": 4.325569490657794e-05, "loss": 0.6954, "step": 1582 }, { "epoch": 0.405248, "grad_norm": 2.84375, "learning_rate": 4.325142905895402e-05, "loss": 0.6963, "step": 1583 }, { "epoch": 0.405504, "grad_norm": 2.65625, "learning_rate": 4.324716321133009e-05, "loss": 0.6358, "step": 1584 }, { "epoch": 0.40576, "grad_norm": 2.484375, "learning_rate": 4.324289736370617e-05, "loss": 0.6712, "step": 1585 }, { "epoch": 0.406016, "grad_norm": 2.796875, "learning_rate": 4.323863151608225e-05, "loss": 0.6361, "step": 1586 }, { "epoch": 0.406272, "grad_norm": 2.828125, "learning_rate": 4.323436566845833e-05, "loss": 0.7294, "step": 1587 }, { "epoch": 0.406528, "grad_norm": 2.640625, "learning_rate": 4.32300998208344e-05, "loss": 0.6942, "step": 1588 }, { "epoch": 0.406784, "grad_norm": 2.3125, "learning_rate": 4.322583397321048e-05, "loss": 0.6606, "step": 1589 }, { "epoch": 0.40704, "grad_norm": 2.65625, "learning_rate": 4.322156812558655e-05, "loss": 0.6515, "step": 1590 }, { "epoch": 0.407296, "grad_norm": 2.625, "learning_rate": 4.321730227796263e-05, "loss": 0.6884, "step": 1591 }, { "epoch": 0.407552, "grad_norm": 2.625, "learning_rate": 4.321303643033871e-05, "loss": 0.6873, "step": 1592 }, { "epoch": 0.407808, "grad_norm": 2.59375, "learning_rate": 4.320877058271479e-05, "loss": 0.6755, "step": 1593 }, { "epoch": 0.408064, "grad_norm": 2.515625, "learning_rate": 4.320450473509087e-05, "loss": 0.655, "step": 1594 }, { "epoch": 0.40832, "grad_norm": 2.625, "learning_rate": 4.320023888746694e-05, "loss": 0.653, "step": 1595 }, { "epoch": 0.408576, "grad_norm": 2.453125, "learning_rate": 4.319597303984302e-05, "loss": 0.6652, "step": 1596 }, { "epoch": 0.408832, "grad_norm": 2.40625, "learning_rate": 4.319170719221909e-05, "loss": 0.6622, "step": 1597 }, { "epoch": 0.409088, "grad_norm": 2.78125, "learning_rate": 4.318744134459517e-05, "loss": 0.6843, "step": 1598 }, { "epoch": 0.409344, "grad_norm": 2.546875, "learning_rate": 4.3183175496971254e-05, "loss": 0.6802, "step": 1599 }, { "epoch": 0.4096, "grad_norm": 2.984375, "learning_rate": 4.317890964934733e-05, "loss": 0.6934, "step": 1600 }, { "epoch": 0.409856, "grad_norm": 2.71875, "learning_rate": 4.31746438017234e-05, "loss": 0.7021, "step": 1601 }, { "epoch": 0.410112, "grad_norm": 2.4375, "learning_rate": 4.3170377954099484e-05, "loss": 0.6795, "step": 1602 }, { "epoch": 0.410368, "grad_norm": 2.609375, "learning_rate": 4.316611210647556e-05, "loss": 0.6865, "step": 1603 }, { "epoch": 0.410624, "grad_norm": 2.890625, "learning_rate": 4.316184625885163e-05, "loss": 0.6653, "step": 1604 }, { "epoch": 0.41088, "grad_norm": 2.984375, "learning_rate": 4.315758041122771e-05, "loss": 0.7059, "step": 1605 }, { "epoch": 0.411136, "grad_norm": 2.546875, "learning_rate": 4.3153314563603794e-05, "loss": 0.7013, "step": 1606 }, { "epoch": 0.411392, "grad_norm": 2.6875, "learning_rate": 4.314904871597987e-05, "loss": 0.6859, "step": 1607 }, { "epoch": 0.411648, "grad_norm": 2.625, "learning_rate": 4.314478286835594e-05, "loss": 0.6986, "step": 1608 }, { "epoch": 0.411904, "grad_norm": 2.59375, "learning_rate": 4.3140517020732024e-05, "loss": 0.7364, "step": 1609 }, { "epoch": 0.41216, "grad_norm": 2.75, "learning_rate": 4.31362511731081e-05, "loss": 0.6612, "step": 1610 }, { "epoch": 0.412416, "grad_norm": 2.625, "learning_rate": 4.313198532548417e-05, "loss": 0.6716, "step": 1611 }, { "epoch": 0.412672, "grad_norm": 2.65625, "learning_rate": 4.312771947786025e-05, "loss": 0.6446, "step": 1612 }, { "epoch": 0.412928, "grad_norm": 2.71875, "learning_rate": 4.3123453630236334e-05, "loss": 0.7022, "step": 1613 }, { "epoch": 0.413184, "grad_norm": 2.734375, "learning_rate": 4.311918778261241e-05, "loss": 0.6779, "step": 1614 }, { "epoch": 0.41344, "grad_norm": 2.5625, "learning_rate": 4.311492193498848e-05, "loss": 0.7446, "step": 1615 }, { "epoch": 0.413696, "grad_norm": 2.515625, "learning_rate": 4.311065608736456e-05, "loss": 0.7091, "step": 1616 }, { "epoch": 0.413952, "grad_norm": 2.90625, "learning_rate": 4.310639023974064e-05, "loss": 0.7044, "step": 1617 }, { "epoch": 0.414208, "grad_norm": 2.671875, "learning_rate": 4.310212439211672e-05, "loss": 0.719, "step": 1618 }, { "epoch": 0.414464, "grad_norm": 2.59375, "learning_rate": 4.3097858544492793e-05, "loss": 0.6608, "step": 1619 }, { "epoch": 0.41472, "grad_norm": 2.5625, "learning_rate": 4.309359269686887e-05, "loss": 0.6919, "step": 1620 }, { "epoch": 0.414976, "grad_norm": 2.4375, "learning_rate": 4.308932684924495e-05, "loss": 0.6573, "step": 1621 }, { "epoch": 0.415232, "grad_norm": 2.40625, "learning_rate": 4.308506100162102e-05, "loss": 0.7054, "step": 1622 }, { "epoch": 0.415488, "grad_norm": 2.59375, "learning_rate": 4.30807951539971e-05, "loss": 0.6442, "step": 1623 }, { "epoch": 0.415744, "grad_norm": 2.71875, "learning_rate": 4.307652930637318e-05, "loss": 0.6434, "step": 1624 }, { "epoch": 0.416, "grad_norm": 2.421875, "learning_rate": 4.307226345874926e-05, "loss": 0.653, "step": 1625 }, { "epoch": 0.416256, "grad_norm": 2.78125, "learning_rate": 4.3067997611125334e-05, "loss": 0.721, "step": 1626 }, { "epoch": 0.416512, "grad_norm": 2.671875, "learning_rate": 4.306373176350141e-05, "loss": 0.6668, "step": 1627 }, { "epoch": 0.416768, "grad_norm": 2.453125, "learning_rate": 4.305946591587749e-05, "loss": 0.6397, "step": 1628 }, { "epoch": 0.417024, "grad_norm": 2.765625, "learning_rate": 4.305520006825356e-05, "loss": 0.7215, "step": 1629 }, { "epoch": 0.41728, "grad_norm": 2.5625, "learning_rate": 4.305093422062964e-05, "loss": 0.6886, "step": 1630 }, { "epoch": 0.417536, "grad_norm": 2.671875, "learning_rate": 4.304666837300572e-05, "loss": 0.6788, "step": 1631 }, { "epoch": 0.417792, "grad_norm": 2.46875, "learning_rate": 4.30424025253818e-05, "loss": 0.6776, "step": 1632 }, { "epoch": 0.418048, "grad_norm": 2.71875, "learning_rate": 4.3038136677757874e-05, "loss": 0.7035, "step": 1633 }, { "epoch": 0.418304, "grad_norm": 2.71875, "learning_rate": 4.303387083013395e-05, "loss": 0.6852, "step": 1634 }, { "epoch": 0.41856, "grad_norm": 2.59375, "learning_rate": 4.302960498251002e-05, "loss": 0.6557, "step": 1635 }, { "epoch": 0.418816, "grad_norm": 2.75, "learning_rate": 4.3025339134886103e-05, "loss": 0.6456, "step": 1636 }, { "epoch": 0.419072, "grad_norm": 2.78125, "learning_rate": 4.3021073287262184e-05, "loss": 0.6875, "step": 1637 }, { "epoch": 0.419328, "grad_norm": 2.90625, "learning_rate": 4.301680743963826e-05, "loss": 0.6684, "step": 1638 }, { "epoch": 0.419584, "grad_norm": 2.8125, "learning_rate": 4.301254159201433e-05, "loss": 0.6853, "step": 1639 }, { "epoch": 0.41984, "grad_norm": 2.78125, "learning_rate": 4.3008275744390414e-05, "loss": 0.6893, "step": 1640 }, { "epoch": 0.420096, "grad_norm": 2.65625, "learning_rate": 4.300400989676649e-05, "loss": 0.6915, "step": 1641 }, { "epoch": 0.420352, "grad_norm": 2.609375, "learning_rate": 4.299974404914256e-05, "loss": 0.6289, "step": 1642 }, { "epoch": 0.420608, "grad_norm": 2.59375, "learning_rate": 4.2995478201518644e-05, "loss": 0.6672, "step": 1643 }, { "epoch": 0.420864, "grad_norm": 2.34375, "learning_rate": 4.2991212353894725e-05, "loss": 0.6774, "step": 1644 }, { "epoch": 0.42112, "grad_norm": 2.796875, "learning_rate": 4.29869465062708e-05, "loss": 0.7069, "step": 1645 }, { "epoch": 0.421376, "grad_norm": 2.921875, "learning_rate": 4.298268065864687e-05, "loss": 0.641, "step": 1646 }, { "epoch": 0.421632, "grad_norm": 2.515625, "learning_rate": 4.2978414811022954e-05, "loss": 0.705, "step": 1647 }, { "epoch": 0.421888, "grad_norm": 2.828125, "learning_rate": 4.297414896339903e-05, "loss": 0.6572, "step": 1648 }, { "epoch": 0.422144, "grad_norm": 2.953125, "learning_rate": 4.29698831157751e-05, "loss": 0.6688, "step": 1649 }, { "epoch": 0.4224, "grad_norm": 2.78125, "learning_rate": 4.2965617268151184e-05, "loss": 0.6664, "step": 1650 }, { "epoch": 0.422656, "grad_norm": 2.84375, "learning_rate": 4.2961351420527265e-05, "loss": 0.6858, "step": 1651 }, { "epoch": 0.422912, "grad_norm": 2.671875, "learning_rate": 4.295708557290334e-05, "loss": 0.6795, "step": 1652 }, { "epoch": 0.423168, "grad_norm": 2.46875, "learning_rate": 4.2952819725279413e-05, "loss": 0.6663, "step": 1653 }, { "epoch": 0.423424, "grad_norm": 2.96875, "learning_rate": 4.294855387765549e-05, "loss": 0.6603, "step": 1654 }, { "epoch": 0.42368, "grad_norm": 2.75, "learning_rate": 4.294428803003157e-05, "loss": 0.6794, "step": 1655 }, { "epoch": 0.423936, "grad_norm": 3.046875, "learning_rate": 4.294002218240765e-05, "loss": 0.6808, "step": 1656 }, { "epoch": 0.424192, "grad_norm": 2.828125, "learning_rate": 4.2935756334783724e-05, "loss": 0.6749, "step": 1657 }, { "epoch": 0.424448, "grad_norm": 2.75, "learning_rate": 4.2931490487159805e-05, "loss": 0.7026, "step": 1658 }, { "epoch": 0.424704, "grad_norm": 3.03125, "learning_rate": 4.292722463953588e-05, "loss": 0.6983, "step": 1659 }, { "epoch": 0.42496, "grad_norm": 2.796875, "learning_rate": 4.2922958791911954e-05, "loss": 0.668, "step": 1660 }, { "epoch": 0.425216, "grad_norm": 2.859375, "learning_rate": 4.291869294428803e-05, "loss": 0.668, "step": 1661 }, { "epoch": 0.425472, "grad_norm": 3.0, "learning_rate": 4.291442709666411e-05, "loss": 0.6747, "step": 1662 }, { "epoch": 0.425728, "grad_norm": 2.6875, "learning_rate": 4.291016124904019e-05, "loss": 0.6593, "step": 1663 }, { "epoch": 0.425984, "grad_norm": 2.65625, "learning_rate": 4.2905895401416264e-05, "loss": 0.6869, "step": 1664 }, { "epoch": 0.42624, "grad_norm": 3.078125, "learning_rate": 4.290162955379234e-05, "loss": 0.6998, "step": 1665 }, { "epoch": 0.426496, "grad_norm": 3.0625, "learning_rate": 4.289736370616842e-05, "loss": 0.6784, "step": 1666 }, { "epoch": 0.426752, "grad_norm": 2.390625, "learning_rate": 4.2893097858544494e-05, "loss": 0.6515, "step": 1667 }, { "epoch": 0.427008, "grad_norm": 2.703125, "learning_rate": 4.288883201092057e-05, "loss": 0.6657, "step": 1668 }, { "epoch": 0.427264, "grad_norm": 2.8125, "learning_rate": 4.288456616329665e-05, "loss": 0.678, "step": 1669 }, { "epoch": 0.42752, "grad_norm": 2.671875, "learning_rate": 4.288030031567273e-05, "loss": 0.6749, "step": 1670 }, { "epoch": 0.427776, "grad_norm": 2.640625, "learning_rate": 4.2876034468048804e-05, "loss": 0.6828, "step": 1671 }, { "epoch": 0.428032, "grad_norm": 2.6875, "learning_rate": 4.287176862042488e-05, "loss": 0.7051, "step": 1672 }, { "epoch": 0.428288, "grad_norm": 2.6875, "learning_rate": 4.286750277280095e-05, "loss": 0.6756, "step": 1673 }, { "epoch": 0.428544, "grad_norm": 2.53125, "learning_rate": 4.2863236925177034e-05, "loss": 0.6683, "step": 1674 }, { "epoch": 0.4288, "grad_norm": 2.703125, "learning_rate": 4.2858971077553115e-05, "loss": 0.6891, "step": 1675 }, { "epoch": 0.429056, "grad_norm": 2.78125, "learning_rate": 4.285470522992919e-05, "loss": 0.6523, "step": 1676 }, { "epoch": 0.429312, "grad_norm": 2.421875, "learning_rate": 4.285043938230527e-05, "loss": 0.7094, "step": 1677 }, { "epoch": 0.429568, "grad_norm": 2.53125, "learning_rate": 4.2846173534681345e-05, "loss": 0.6845, "step": 1678 }, { "epoch": 0.429824, "grad_norm": 2.546875, "learning_rate": 4.284190768705742e-05, "loss": 0.6445, "step": 1679 }, { "epoch": 0.43008, "grad_norm": 2.578125, "learning_rate": 4.283764183943349e-05, "loss": 0.6545, "step": 1680 }, { "epoch": 0.430336, "grad_norm": 2.484375, "learning_rate": 4.2833375991809574e-05, "loss": 0.668, "step": 1681 }, { "epoch": 0.430592, "grad_norm": 2.34375, "learning_rate": 4.2829110144185655e-05, "loss": 0.6679, "step": 1682 }, { "epoch": 0.430848, "grad_norm": 2.5625, "learning_rate": 4.282484429656173e-05, "loss": 0.6429, "step": 1683 }, { "epoch": 0.431104, "grad_norm": 2.90625, "learning_rate": 4.2820578448937804e-05, "loss": 0.6682, "step": 1684 }, { "epoch": 0.43136, "grad_norm": 2.546875, "learning_rate": 4.2816312601313885e-05, "loss": 0.6497, "step": 1685 }, { "epoch": 0.431616, "grad_norm": 2.59375, "learning_rate": 4.281204675368996e-05, "loss": 0.6997, "step": 1686 }, { "epoch": 0.431872, "grad_norm": 2.4375, "learning_rate": 4.280778090606603e-05, "loss": 0.6654, "step": 1687 }, { "epoch": 0.432128, "grad_norm": 2.546875, "learning_rate": 4.2803515058442114e-05, "loss": 0.6671, "step": 1688 }, { "epoch": 0.432384, "grad_norm": 2.515625, "learning_rate": 4.2799249210818195e-05, "loss": 0.6216, "step": 1689 }, { "epoch": 0.43264, "grad_norm": 2.453125, "learning_rate": 4.279498336319427e-05, "loss": 0.6793, "step": 1690 }, { "epoch": 0.432896, "grad_norm": 2.28125, "learning_rate": 4.2790717515570344e-05, "loss": 0.6716, "step": 1691 }, { "epoch": 0.433152, "grad_norm": 2.5625, "learning_rate": 4.2786451667946425e-05, "loss": 0.6806, "step": 1692 }, { "epoch": 0.433408, "grad_norm": 2.59375, "learning_rate": 4.27821858203225e-05, "loss": 0.6492, "step": 1693 }, { "epoch": 0.433664, "grad_norm": 2.5, "learning_rate": 4.2777919972698574e-05, "loss": 0.6305, "step": 1694 }, { "epoch": 0.43392, "grad_norm": 2.40625, "learning_rate": 4.2773654125074655e-05, "loss": 0.6189, "step": 1695 }, { "epoch": 0.434176, "grad_norm": 2.515625, "learning_rate": 4.2769388277450736e-05, "loss": 0.6458, "step": 1696 }, { "epoch": 0.434432, "grad_norm": 2.71875, "learning_rate": 4.276512242982681e-05, "loss": 0.7145, "step": 1697 }, { "epoch": 0.434688, "grad_norm": 2.5625, "learning_rate": 4.2760856582202884e-05, "loss": 0.6771, "step": 1698 }, { "epoch": 0.434944, "grad_norm": 2.703125, "learning_rate": 4.275659073457896e-05, "loss": 0.6921, "step": 1699 }, { "epoch": 0.4352, "grad_norm": 2.640625, "learning_rate": 4.275232488695504e-05, "loss": 0.7022, "step": 1700 }, { "epoch": 0.435456, "grad_norm": 2.515625, "learning_rate": 4.274805903933112e-05, "loss": 0.7176, "step": 1701 }, { "epoch": 0.435712, "grad_norm": 2.40625, "learning_rate": 4.2743793191707195e-05, "loss": 0.7063, "step": 1702 }, { "epoch": 0.435968, "grad_norm": 2.765625, "learning_rate": 4.273952734408327e-05, "loss": 0.6535, "step": 1703 }, { "epoch": 0.436224, "grad_norm": 2.75, "learning_rate": 4.273526149645935e-05, "loss": 0.6626, "step": 1704 }, { "epoch": 0.43648, "grad_norm": 3.15625, "learning_rate": 4.2730995648835424e-05, "loss": 0.6531, "step": 1705 }, { "epoch": 0.436736, "grad_norm": 2.40625, "learning_rate": 4.27267298012115e-05, "loss": 0.6626, "step": 1706 }, { "epoch": 0.436992, "grad_norm": 2.578125, "learning_rate": 4.272246395358758e-05, "loss": 0.6455, "step": 1707 }, { "epoch": 0.437248, "grad_norm": 2.984375, "learning_rate": 4.271819810596366e-05, "loss": 0.6952, "step": 1708 }, { "epoch": 0.437504, "grad_norm": 2.8125, "learning_rate": 4.2713932258339735e-05, "loss": 0.6768, "step": 1709 }, { "epoch": 0.43776, "grad_norm": 2.5625, "learning_rate": 4.270966641071581e-05, "loss": 0.6416, "step": 1710 }, { "epoch": 0.438016, "grad_norm": 2.78125, "learning_rate": 4.270540056309189e-05, "loss": 0.6503, "step": 1711 }, { "epoch": 0.438272, "grad_norm": 2.796875, "learning_rate": 4.2701134715467965e-05, "loss": 0.6459, "step": 1712 }, { "epoch": 0.438528, "grad_norm": 2.671875, "learning_rate": 4.269686886784404e-05, "loss": 0.6319, "step": 1713 }, { "epoch": 0.438784, "grad_norm": 2.84375, "learning_rate": 4.269260302022012e-05, "loss": 0.6884, "step": 1714 }, { "epoch": 0.43904, "grad_norm": 2.8125, "learning_rate": 4.26883371725962e-05, "loss": 0.6711, "step": 1715 }, { "epoch": 0.439296, "grad_norm": 2.703125, "learning_rate": 4.2684071324972275e-05, "loss": 0.6924, "step": 1716 }, { "epoch": 0.439552, "grad_norm": 2.671875, "learning_rate": 4.267980547734835e-05, "loss": 0.6262, "step": 1717 }, { "epoch": 0.439808, "grad_norm": 2.984375, "learning_rate": 4.2675539629724424e-05, "loss": 0.707, "step": 1718 }, { "epoch": 0.440064, "grad_norm": 2.84375, "learning_rate": 4.2671273782100505e-05, "loss": 0.6398, "step": 1719 }, { "epoch": 0.44032, "grad_norm": 2.875, "learning_rate": 4.2667007934476586e-05, "loss": 0.6084, "step": 1720 }, { "epoch": 0.440576, "grad_norm": 2.78125, "learning_rate": 4.266274208685266e-05, "loss": 0.6449, "step": 1721 }, { "epoch": 0.440832, "grad_norm": 2.703125, "learning_rate": 4.2658476239228734e-05, "loss": 0.6449, "step": 1722 }, { "epoch": 0.441088, "grad_norm": 2.859375, "learning_rate": 4.2654210391604815e-05, "loss": 0.71, "step": 1723 }, { "epoch": 0.441344, "grad_norm": 2.5625, "learning_rate": 4.264994454398089e-05, "loss": 0.6591, "step": 1724 }, { "epoch": 0.4416, "grad_norm": 2.71875, "learning_rate": 4.2645678696356964e-05, "loss": 0.6671, "step": 1725 }, { "epoch": 0.441856, "grad_norm": 2.59375, "learning_rate": 4.2641412848733045e-05, "loss": 0.6446, "step": 1726 }, { "epoch": 0.442112, "grad_norm": 2.6875, "learning_rate": 4.2637147001109126e-05, "loss": 0.7014, "step": 1727 }, { "epoch": 0.442368, "grad_norm": 3.046875, "learning_rate": 4.26328811534852e-05, "loss": 0.6533, "step": 1728 }, { "epoch": 0.442624, "grad_norm": 2.765625, "learning_rate": 4.2628615305861274e-05, "loss": 0.6599, "step": 1729 }, { "epoch": 0.44288, "grad_norm": 2.515625, "learning_rate": 4.2624349458237356e-05, "loss": 0.6511, "step": 1730 }, { "epoch": 0.443136, "grad_norm": 2.953125, "learning_rate": 4.262008361061343e-05, "loss": 0.6769, "step": 1731 }, { "epoch": 0.443392, "grad_norm": 2.984375, "learning_rate": 4.2615817762989504e-05, "loss": 0.6765, "step": 1732 }, { "epoch": 0.443648, "grad_norm": 2.78125, "learning_rate": 4.2611551915365585e-05, "loss": 0.6817, "step": 1733 }, { "epoch": 0.443904, "grad_norm": 2.640625, "learning_rate": 4.2607286067741666e-05, "loss": 0.687, "step": 1734 }, { "epoch": 0.44416, "grad_norm": 2.484375, "learning_rate": 4.260302022011774e-05, "loss": 0.6892, "step": 1735 }, { "epoch": 0.444416, "grad_norm": 3.015625, "learning_rate": 4.2598754372493815e-05, "loss": 0.6673, "step": 1736 }, { "epoch": 0.444672, "grad_norm": 2.578125, "learning_rate": 4.259448852486989e-05, "loss": 0.666, "step": 1737 }, { "epoch": 0.444928, "grad_norm": 2.625, "learning_rate": 4.259022267724597e-05, "loss": 0.6602, "step": 1738 }, { "epoch": 0.445184, "grad_norm": 2.65625, "learning_rate": 4.258595682962205e-05, "loss": 0.6843, "step": 1739 }, { "epoch": 0.44544, "grad_norm": 2.59375, "learning_rate": 4.2581690981998125e-05, "loss": 0.6518, "step": 1740 }, { "epoch": 0.445696, "grad_norm": 2.671875, "learning_rate": 4.2577425134374206e-05, "loss": 0.6141, "step": 1741 }, { "epoch": 0.445952, "grad_norm": 2.65625, "learning_rate": 4.257315928675028e-05, "loss": 0.6496, "step": 1742 }, { "epoch": 0.446208, "grad_norm": 2.828125, "learning_rate": 4.2568893439126355e-05, "loss": 0.6545, "step": 1743 }, { "epoch": 0.446464, "grad_norm": 2.765625, "learning_rate": 4.256462759150243e-05, "loss": 0.6182, "step": 1744 }, { "epoch": 0.44672, "grad_norm": 2.484375, "learning_rate": 4.256036174387851e-05, "loss": 0.6887, "step": 1745 }, { "epoch": 0.446976, "grad_norm": 2.5, "learning_rate": 4.255609589625459e-05, "loss": 0.607, "step": 1746 }, { "epoch": 0.447232, "grad_norm": 2.609375, "learning_rate": 4.2551830048630665e-05, "loss": 0.6434, "step": 1747 }, { "epoch": 0.447488, "grad_norm": 2.59375, "learning_rate": 4.254756420100674e-05, "loss": 0.6455, "step": 1748 }, { "epoch": 0.447744, "grad_norm": 2.671875, "learning_rate": 4.254329835338282e-05, "loss": 0.6661, "step": 1749 }, { "epoch": 0.448, "grad_norm": 2.96875, "learning_rate": 4.2539032505758895e-05, "loss": 0.6591, "step": 1750 }, { "epoch": 0.448256, "grad_norm": 2.53125, "learning_rate": 4.253476665813497e-05, "loss": 0.6577, "step": 1751 }, { "epoch": 0.448512, "grad_norm": 2.625, "learning_rate": 4.253050081051105e-05, "loss": 0.665, "step": 1752 }, { "epoch": 0.448768, "grad_norm": 2.40625, "learning_rate": 4.252623496288713e-05, "loss": 0.6509, "step": 1753 }, { "epoch": 0.449024, "grad_norm": 2.53125, "learning_rate": 4.2521969115263206e-05, "loss": 0.6288, "step": 1754 }, { "epoch": 0.44928, "grad_norm": 2.59375, "learning_rate": 4.251770326763928e-05, "loss": 0.6683, "step": 1755 }, { "epoch": 0.449536, "grad_norm": 2.53125, "learning_rate": 4.251343742001536e-05, "loss": 0.6236, "step": 1756 }, { "epoch": 0.449792, "grad_norm": 2.265625, "learning_rate": 4.2509171572391435e-05, "loss": 0.6265, "step": 1757 }, { "epoch": 0.450048, "grad_norm": 2.546875, "learning_rate": 4.2504905724767516e-05, "loss": 0.6567, "step": 1758 }, { "epoch": 0.450304, "grad_norm": 2.375, "learning_rate": 4.250063987714359e-05, "loss": 0.6785, "step": 1759 }, { "epoch": 0.45056, "grad_norm": 2.328125, "learning_rate": 4.249637402951967e-05, "loss": 0.7115, "step": 1760 }, { "epoch": 0.450816, "grad_norm": 2.5625, "learning_rate": 4.2492108181895746e-05, "loss": 0.6502, "step": 1761 }, { "epoch": 0.451072, "grad_norm": 2.671875, "learning_rate": 4.248784233427182e-05, "loss": 0.69, "step": 1762 }, { "epoch": 0.451328, "grad_norm": 2.296875, "learning_rate": 4.2483576486647894e-05, "loss": 0.639, "step": 1763 }, { "epoch": 0.451584, "grad_norm": 2.375, "learning_rate": 4.2479310639023975e-05, "loss": 0.6573, "step": 1764 }, { "epoch": 0.45184, "grad_norm": 2.796875, "learning_rate": 4.2475044791400056e-05, "loss": 0.663, "step": 1765 }, { "epoch": 0.452096, "grad_norm": 2.515625, "learning_rate": 4.247077894377613e-05, "loss": 0.7069, "step": 1766 }, { "epoch": 0.452352, "grad_norm": 2.546875, "learning_rate": 4.2466513096152205e-05, "loss": 0.6517, "step": 1767 }, { "epoch": 0.452608, "grad_norm": 2.28125, "learning_rate": 4.2462247248528286e-05, "loss": 0.6615, "step": 1768 }, { "epoch": 0.452864, "grad_norm": 2.5625, "learning_rate": 4.245798140090436e-05, "loss": 0.6422, "step": 1769 }, { "epoch": 0.45312, "grad_norm": 2.421875, "learning_rate": 4.2453715553280435e-05, "loss": 0.6583, "step": 1770 }, { "epoch": 0.453376, "grad_norm": 2.390625, "learning_rate": 4.2449449705656516e-05, "loss": 0.6745, "step": 1771 }, { "epoch": 0.453632, "grad_norm": 2.59375, "learning_rate": 4.24451838580326e-05, "loss": 0.6283, "step": 1772 }, { "epoch": 0.453888, "grad_norm": 2.375, "learning_rate": 4.244091801040867e-05, "loss": 0.7095, "step": 1773 }, { "epoch": 0.454144, "grad_norm": 2.609375, "learning_rate": 4.2436652162784745e-05, "loss": 0.6626, "step": 1774 }, { "epoch": 0.4544, "grad_norm": 2.84375, "learning_rate": 4.2432386315160826e-05, "loss": 0.6296, "step": 1775 }, { "epoch": 0.454656, "grad_norm": 2.8125, "learning_rate": 4.24281204675369e-05, "loss": 0.6355, "step": 1776 }, { "epoch": 0.454912, "grad_norm": 2.40625, "learning_rate": 4.242385461991298e-05, "loss": 0.6664, "step": 1777 }, { "epoch": 0.455168, "grad_norm": 2.59375, "learning_rate": 4.2419588772289056e-05, "loss": 0.662, "step": 1778 }, { "epoch": 0.455424, "grad_norm": 2.6875, "learning_rate": 4.241532292466514e-05, "loss": 0.6682, "step": 1779 }, { "epoch": 0.45568, "grad_norm": 2.625, "learning_rate": 4.241105707704121e-05, "loss": 0.6223, "step": 1780 }, { "epoch": 0.455936, "grad_norm": 2.65625, "learning_rate": 4.2406791229417285e-05, "loss": 0.6432, "step": 1781 }, { "epoch": 0.456192, "grad_norm": 2.75, "learning_rate": 4.240252538179336e-05, "loss": 0.6455, "step": 1782 }, { "epoch": 0.456448, "grad_norm": 2.96875, "learning_rate": 4.239825953416944e-05, "loss": 0.6833, "step": 1783 }, { "epoch": 0.456704, "grad_norm": 2.671875, "learning_rate": 4.239399368654552e-05, "loss": 0.6876, "step": 1784 }, { "epoch": 0.45696, "grad_norm": 2.359375, "learning_rate": 4.2389727838921596e-05, "loss": 0.6515, "step": 1785 }, { "epoch": 0.457216, "grad_norm": 2.625, "learning_rate": 4.238546199129767e-05, "loss": 0.6611, "step": 1786 }, { "epoch": 0.457472, "grad_norm": 2.671875, "learning_rate": 4.238119614367375e-05, "loss": 0.6822, "step": 1787 }, { "epoch": 0.457728, "grad_norm": 2.671875, "learning_rate": 4.2376930296049826e-05, "loss": 0.6289, "step": 1788 }, { "epoch": 0.457984, "grad_norm": 2.578125, "learning_rate": 4.23726644484259e-05, "loss": 0.678, "step": 1789 }, { "epoch": 0.45824, "grad_norm": 2.6875, "learning_rate": 4.236839860080198e-05, "loss": 0.6509, "step": 1790 }, { "epoch": 0.458496, "grad_norm": 2.84375, "learning_rate": 4.236413275317806e-05, "loss": 0.6449, "step": 1791 }, { "epoch": 0.458752, "grad_norm": 2.84375, "learning_rate": 4.2359866905554136e-05, "loss": 0.6897, "step": 1792 }, { "epoch": 0.459008, "grad_norm": 2.71875, "learning_rate": 4.235560105793021e-05, "loss": 0.6823, "step": 1793 }, { "epoch": 0.459264, "grad_norm": 2.953125, "learning_rate": 4.235133521030629e-05, "loss": 0.6281, "step": 1794 }, { "epoch": 0.45952, "grad_norm": 3.15625, "learning_rate": 4.2347069362682366e-05, "loss": 0.6489, "step": 1795 }, { "epoch": 0.459776, "grad_norm": 2.75, "learning_rate": 4.234280351505845e-05, "loss": 0.6665, "step": 1796 }, { "epoch": 0.460032, "grad_norm": 2.671875, "learning_rate": 4.233853766743452e-05, "loss": 0.6476, "step": 1797 }, { "epoch": 0.460288, "grad_norm": 2.75, "learning_rate": 4.23342718198106e-05, "loss": 0.6473, "step": 1798 }, { "epoch": 0.460544, "grad_norm": 2.546875, "learning_rate": 4.2330005972186676e-05, "loss": 0.6885, "step": 1799 }, { "epoch": 0.4608, "grad_norm": 2.6875, "learning_rate": 4.232574012456275e-05, "loss": 0.6785, "step": 1800 }, { "epoch": 0.461056, "grad_norm": 2.59375, "learning_rate": 4.2321474276938825e-05, "loss": 0.6454, "step": 1801 }, { "epoch": 0.461312, "grad_norm": 2.3125, "learning_rate": 4.2317208429314906e-05, "loss": 0.6069, "step": 1802 }, { "epoch": 0.461568, "grad_norm": 2.546875, "learning_rate": 4.231294258169099e-05, "loss": 0.6729, "step": 1803 }, { "epoch": 0.461824, "grad_norm": 2.625, "learning_rate": 4.230867673406706e-05, "loss": 0.6489, "step": 1804 }, { "epoch": 0.46208, "grad_norm": 2.4375, "learning_rate": 4.230441088644314e-05, "loss": 0.6541, "step": 1805 }, { "epoch": 0.462336, "grad_norm": 2.53125, "learning_rate": 4.2300145038819217e-05, "loss": 0.6377, "step": 1806 }, { "epoch": 0.462592, "grad_norm": 2.6875, "learning_rate": 4.229587919119529e-05, "loss": 0.6658, "step": 1807 }, { "epoch": 0.462848, "grad_norm": 2.578125, "learning_rate": 4.2291613343571365e-05, "loss": 0.6164, "step": 1808 }, { "epoch": 0.463104, "grad_norm": 2.53125, "learning_rate": 4.2287347495947446e-05, "loss": 0.6218, "step": 1809 }, { "epoch": 0.46336, "grad_norm": 2.5625, "learning_rate": 4.228308164832353e-05, "loss": 0.6867, "step": 1810 }, { "epoch": 0.463616, "grad_norm": 2.59375, "learning_rate": 4.22788158006996e-05, "loss": 0.6605, "step": 1811 }, { "epoch": 0.463872, "grad_norm": 2.609375, "learning_rate": 4.2274549953075676e-05, "loss": 0.7173, "step": 1812 }, { "epoch": 0.464128, "grad_norm": 2.203125, "learning_rate": 4.227028410545176e-05, "loss": 0.6626, "step": 1813 }, { "epoch": 0.464384, "grad_norm": 2.5, "learning_rate": 4.226601825782783e-05, "loss": 0.6404, "step": 1814 }, { "epoch": 0.46464, "grad_norm": 2.609375, "learning_rate": 4.2261752410203905e-05, "loss": 0.6281, "step": 1815 }, { "epoch": 0.464896, "grad_norm": 2.96875, "learning_rate": 4.2257486562579986e-05, "loss": 0.6481, "step": 1816 }, { "epoch": 0.465152, "grad_norm": 2.765625, "learning_rate": 4.225322071495607e-05, "loss": 0.6234, "step": 1817 }, { "epoch": 0.465408, "grad_norm": 2.625, "learning_rate": 4.224895486733214e-05, "loss": 0.6176, "step": 1818 }, { "epoch": 0.465664, "grad_norm": 2.984375, "learning_rate": 4.2244689019708216e-05, "loss": 0.6274, "step": 1819 }, { "epoch": 0.46592, "grad_norm": 2.84375, "learning_rate": 4.224042317208429e-05, "loss": 0.6459, "step": 1820 }, { "epoch": 0.466176, "grad_norm": 2.765625, "learning_rate": 4.223615732446037e-05, "loss": 0.629, "step": 1821 }, { "epoch": 0.466432, "grad_norm": 2.5, "learning_rate": 4.223189147683645e-05, "loss": 0.6072, "step": 1822 }, { "epoch": 0.466688, "grad_norm": 2.6875, "learning_rate": 4.2227625629212527e-05, "loss": 0.6563, "step": 1823 }, { "epoch": 0.466944, "grad_norm": 2.765625, "learning_rate": 4.222335978158861e-05, "loss": 0.652, "step": 1824 }, { "epoch": 0.4672, "grad_norm": 2.421875, "learning_rate": 4.221909393396468e-05, "loss": 0.648, "step": 1825 }, { "epoch": 0.467456, "grad_norm": 2.609375, "learning_rate": 4.2214828086340756e-05, "loss": 0.6394, "step": 1826 }, { "epoch": 0.467712, "grad_norm": 2.84375, "learning_rate": 4.221056223871683e-05, "loss": 0.6349, "step": 1827 }, { "epoch": 0.467968, "grad_norm": 2.5, "learning_rate": 4.220629639109291e-05, "loss": 0.6666, "step": 1828 }, { "epoch": 0.468224, "grad_norm": 2.4375, "learning_rate": 4.220203054346899e-05, "loss": 0.6625, "step": 1829 }, { "epoch": 0.46848, "grad_norm": 2.5, "learning_rate": 4.219776469584507e-05, "loss": 0.6824, "step": 1830 }, { "epoch": 0.468736, "grad_norm": 2.75, "learning_rate": 4.219349884822114e-05, "loss": 0.6135, "step": 1831 }, { "epoch": 0.468992, "grad_norm": 2.5625, "learning_rate": 4.218923300059722e-05, "loss": 0.6562, "step": 1832 }, { "epoch": 0.469248, "grad_norm": 2.4375, "learning_rate": 4.2184967152973296e-05, "loss": 0.6252, "step": 1833 }, { "epoch": 0.469504, "grad_norm": 3.09375, "learning_rate": 4.218070130534937e-05, "loss": 0.5786, "step": 1834 }, { "epoch": 0.46976, "grad_norm": 2.640625, "learning_rate": 4.217643545772545e-05, "loss": 0.657, "step": 1835 }, { "epoch": 0.470016, "grad_norm": 2.59375, "learning_rate": 4.217216961010153e-05, "loss": 0.6396, "step": 1836 }, { "epoch": 0.470272, "grad_norm": 2.78125, "learning_rate": 4.216790376247761e-05, "loss": 0.655, "step": 1837 }, { "epoch": 0.470528, "grad_norm": 2.625, "learning_rate": 4.216363791485368e-05, "loss": 0.6632, "step": 1838 }, { "epoch": 0.470784, "grad_norm": 2.859375, "learning_rate": 4.215937206722976e-05, "loss": 0.6167, "step": 1839 }, { "epoch": 0.47104, "grad_norm": 2.609375, "learning_rate": 4.2155106219605837e-05, "loss": 0.6731, "step": 1840 }, { "epoch": 0.471296, "grad_norm": 2.59375, "learning_rate": 4.215084037198192e-05, "loss": 0.6291, "step": 1841 }, { "epoch": 0.471552, "grad_norm": 2.78125, "learning_rate": 4.214657452435799e-05, "loss": 0.6683, "step": 1842 }, { "epoch": 0.471808, "grad_norm": 2.4375, "learning_rate": 4.214230867673407e-05, "loss": 0.6298, "step": 1843 }, { "epoch": 0.472064, "grad_norm": 2.78125, "learning_rate": 4.213804282911015e-05, "loss": 0.6108, "step": 1844 }, { "epoch": 0.47232, "grad_norm": 2.640625, "learning_rate": 4.213377698148622e-05, "loss": 0.6656, "step": 1845 }, { "epoch": 0.472576, "grad_norm": 2.578125, "learning_rate": 4.2129511133862296e-05, "loss": 0.6727, "step": 1846 }, { "epoch": 0.472832, "grad_norm": 2.34375, "learning_rate": 4.212524528623838e-05, "loss": 0.6548, "step": 1847 }, { "epoch": 0.473088, "grad_norm": 2.515625, "learning_rate": 4.212097943861446e-05, "loss": 0.6594, "step": 1848 }, { "epoch": 0.473344, "grad_norm": 2.75, "learning_rate": 4.211671359099053e-05, "loss": 0.6119, "step": 1849 }, { "epoch": 0.4736, "grad_norm": 2.859375, "learning_rate": 4.2112447743366606e-05, "loss": 0.719, "step": 1850 }, { "epoch": 0.473856, "grad_norm": 2.546875, "learning_rate": 4.210818189574269e-05, "loss": 0.671, "step": 1851 }, { "epoch": 0.474112, "grad_norm": 2.5, "learning_rate": 4.210391604811876e-05, "loss": 0.6524, "step": 1852 }, { "epoch": 0.474368, "grad_norm": 2.765625, "learning_rate": 4.2099650200494836e-05, "loss": 0.6421, "step": 1853 }, { "epoch": 0.474624, "grad_norm": 2.875, "learning_rate": 4.209538435287092e-05, "loss": 0.6152, "step": 1854 }, { "epoch": 0.47488, "grad_norm": 2.6875, "learning_rate": 4.2091118505247e-05, "loss": 0.632, "step": 1855 }, { "epoch": 0.475136, "grad_norm": 2.421875, "learning_rate": 4.208685265762307e-05, "loss": 0.6648, "step": 1856 }, { "epoch": 0.475392, "grad_norm": 2.890625, "learning_rate": 4.2082586809999146e-05, "loss": 0.6195, "step": 1857 }, { "epoch": 0.475648, "grad_norm": 2.8125, "learning_rate": 4.207832096237523e-05, "loss": 0.6692, "step": 1858 }, { "epoch": 0.475904, "grad_norm": 2.8125, "learning_rate": 4.20740551147513e-05, "loss": 0.6011, "step": 1859 }, { "epoch": 0.47616, "grad_norm": 2.953125, "learning_rate": 4.206978926712738e-05, "loss": 0.6025, "step": 1860 }, { "epoch": 0.476416, "grad_norm": 2.6875, "learning_rate": 4.206552341950346e-05, "loss": 0.6238, "step": 1861 }, { "epoch": 0.476672, "grad_norm": 2.609375, "learning_rate": 4.206125757187954e-05, "loss": 0.6198, "step": 1862 }, { "epoch": 0.476928, "grad_norm": 2.5, "learning_rate": 4.205699172425561e-05, "loss": 0.6375, "step": 1863 }, { "epoch": 0.477184, "grad_norm": 2.578125, "learning_rate": 4.205272587663169e-05, "loss": 0.6306, "step": 1864 }, { "epoch": 0.47744, "grad_norm": 2.484375, "learning_rate": 4.204846002900776e-05, "loss": 0.6506, "step": 1865 }, { "epoch": 0.477696, "grad_norm": 2.640625, "learning_rate": 4.204419418138384e-05, "loss": 0.6598, "step": 1866 }, { "epoch": 0.477952, "grad_norm": 2.484375, "learning_rate": 4.203992833375992e-05, "loss": 0.6409, "step": 1867 }, { "epoch": 0.478208, "grad_norm": 2.640625, "learning_rate": 4.2035662486136e-05, "loss": 0.6153, "step": 1868 }, { "epoch": 0.478464, "grad_norm": 2.46875, "learning_rate": 4.203139663851207e-05, "loss": 0.6835, "step": 1869 }, { "epoch": 0.47872, "grad_norm": 2.5625, "learning_rate": 4.202713079088815e-05, "loss": 0.6422, "step": 1870 }, { "epoch": 0.478976, "grad_norm": 2.625, "learning_rate": 4.202286494326423e-05, "loss": 0.6575, "step": 1871 }, { "epoch": 0.479232, "grad_norm": 2.71875, "learning_rate": 4.20185990956403e-05, "loss": 0.6337, "step": 1872 }, { "epoch": 0.479488, "grad_norm": 2.6875, "learning_rate": 4.201433324801638e-05, "loss": 0.6952, "step": 1873 }, { "epoch": 0.479744, "grad_norm": 2.703125, "learning_rate": 4.201006740039246e-05, "loss": 0.6342, "step": 1874 }, { "epoch": 0.48, "grad_norm": 2.546875, "learning_rate": 4.200580155276854e-05, "loss": 0.6252, "step": 1875 }, { "epoch": 0.480256, "grad_norm": 2.34375, "learning_rate": 4.200153570514461e-05, "loss": 0.636, "step": 1876 }, { "epoch": 0.480512, "grad_norm": 2.984375, "learning_rate": 4.199726985752069e-05, "loss": 0.6343, "step": 1877 }, { "epoch": 0.480768, "grad_norm": 2.59375, "learning_rate": 4.199300400989677e-05, "loss": 0.6251, "step": 1878 }, { "epoch": 0.481024, "grad_norm": 2.375, "learning_rate": 4.198873816227285e-05, "loss": 0.6107, "step": 1879 }, { "epoch": 0.48128, "grad_norm": 2.25, "learning_rate": 4.198447231464892e-05, "loss": 0.6271, "step": 1880 }, { "epoch": 0.481536, "grad_norm": 2.703125, "learning_rate": 4.1980206467025003e-05, "loss": 0.6511, "step": 1881 }, { "epoch": 0.481792, "grad_norm": 2.890625, "learning_rate": 4.197594061940108e-05, "loss": 0.6352, "step": 1882 }, { "epoch": 0.482048, "grad_norm": 2.421875, "learning_rate": 4.197167477177715e-05, "loss": 0.645, "step": 1883 }, { "epoch": 0.482304, "grad_norm": 2.453125, "learning_rate": 4.1967408924153226e-05, "loss": 0.6623, "step": 1884 }, { "epoch": 0.48256, "grad_norm": 2.515625, "learning_rate": 4.196314307652931e-05, "loss": 0.6052, "step": 1885 }, { "epoch": 0.482816, "grad_norm": 2.671875, "learning_rate": 4.195887722890539e-05, "loss": 0.6342, "step": 1886 }, { "epoch": 0.483072, "grad_norm": 2.328125, "learning_rate": 4.195461138128146e-05, "loss": 0.664, "step": 1887 }, { "epoch": 0.483328, "grad_norm": 2.59375, "learning_rate": 4.1950345533657544e-05, "loss": 0.6498, "step": 1888 }, { "epoch": 0.483584, "grad_norm": 2.59375, "learning_rate": 4.194607968603362e-05, "loss": 0.6219, "step": 1889 }, { "epoch": 0.48384, "grad_norm": 2.390625, "learning_rate": 4.194181383840969e-05, "loss": 0.6404, "step": 1890 }, { "epoch": 0.484096, "grad_norm": 2.5625, "learning_rate": 4.1937547990785766e-05, "loss": 0.6275, "step": 1891 }, { "epoch": 0.484352, "grad_norm": 2.640625, "learning_rate": 4.193328214316185e-05, "loss": 0.6555, "step": 1892 }, { "epoch": 0.484608, "grad_norm": 2.65625, "learning_rate": 4.192901629553793e-05, "loss": 0.6343, "step": 1893 }, { "epoch": 0.484864, "grad_norm": 2.453125, "learning_rate": 4.1924750447914e-05, "loss": 0.6536, "step": 1894 }, { "epoch": 0.48512, "grad_norm": 2.328125, "learning_rate": 4.192048460029008e-05, "loss": 0.6235, "step": 1895 }, { "epoch": 0.485376, "grad_norm": 2.34375, "learning_rate": 4.191621875266616e-05, "loss": 0.6733, "step": 1896 }, { "epoch": 0.485632, "grad_norm": 2.71875, "learning_rate": 4.191195290504223e-05, "loss": 0.6115, "step": 1897 }, { "epoch": 0.485888, "grad_norm": 2.40625, "learning_rate": 4.190768705741831e-05, "loss": 0.6595, "step": 1898 }, { "epoch": 0.486144, "grad_norm": 2.734375, "learning_rate": 4.190342120979439e-05, "loss": 0.6289, "step": 1899 }, { "epoch": 0.4864, "grad_norm": 2.4375, "learning_rate": 4.189915536217047e-05, "loss": 0.6683, "step": 1900 }, { "epoch": 0.486656, "grad_norm": 2.6875, "learning_rate": 4.189488951454654e-05, "loss": 0.6408, "step": 1901 }, { "epoch": 0.486912, "grad_norm": 2.5, "learning_rate": 4.189062366692262e-05, "loss": 0.6502, "step": 1902 }, { "epoch": 0.487168, "grad_norm": 2.390625, "learning_rate": 4.18863578192987e-05, "loss": 0.6109, "step": 1903 }, { "epoch": 0.487424, "grad_norm": 2.484375, "learning_rate": 4.188209197167477e-05, "loss": 0.6807, "step": 1904 }, { "epoch": 0.48768, "grad_norm": 2.71875, "learning_rate": 4.1877826124050854e-05, "loss": 0.6413, "step": 1905 }, { "epoch": 0.487936, "grad_norm": 2.578125, "learning_rate": 4.187356027642693e-05, "loss": 0.6531, "step": 1906 }, { "epoch": 0.488192, "grad_norm": 2.328125, "learning_rate": 4.186929442880301e-05, "loss": 0.6387, "step": 1907 }, { "epoch": 0.488448, "grad_norm": 2.390625, "learning_rate": 4.186502858117908e-05, "loss": 0.6595, "step": 1908 }, { "epoch": 0.488704, "grad_norm": 2.515625, "learning_rate": 4.186076273355516e-05, "loss": 0.6183, "step": 1909 }, { "epoch": 0.48896, "grad_norm": 2.4375, "learning_rate": 4.185649688593123e-05, "loss": 0.6168, "step": 1910 }, { "epoch": 0.489216, "grad_norm": 2.609375, "learning_rate": 4.185223103830731e-05, "loss": 0.674, "step": 1911 }, { "epoch": 0.489472, "grad_norm": 2.5625, "learning_rate": 4.1847965190683394e-05, "loss": 0.6295, "step": 1912 }, { "epoch": 0.489728, "grad_norm": 2.46875, "learning_rate": 4.184369934305947e-05, "loss": 0.6612, "step": 1913 }, { "epoch": 0.489984, "grad_norm": 2.5, "learning_rate": 4.183943349543554e-05, "loss": 0.6207, "step": 1914 }, { "epoch": 0.49024, "grad_norm": 2.546875, "learning_rate": 4.183516764781162e-05, "loss": 0.6354, "step": 1915 }, { "epoch": 0.490496, "grad_norm": 2.59375, "learning_rate": 4.18309018001877e-05, "loss": 0.6517, "step": 1916 }, { "epoch": 0.490752, "grad_norm": 2.796875, "learning_rate": 4.182663595256377e-05, "loss": 0.6184, "step": 1917 }, { "epoch": 0.491008, "grad_norm": 2.484375, "learning_rate": 4.182237010493985e-05, "loss": 0.5959, "step": 1918 }, { "epoch": 0.491264, "grad_norm": 2.484375, "learning_rate": 4.1818104257315934e-05, "loss": 0.6375, "step": 1919 }, { "epoch": 0.49152, "grad_norm": 2.8125, "learning_rate": 4.181383840969201e-05, "loss": 0.6422, "step": 1920 }, { "epoch": 0.491776, "grad_norm": 2.953125, "learning_rate": 4.180957256206808e-05, "loss": 0.6417, "step": 1921 }, { "epoch": 0.492032, "grad_norm": 2.828125, "learning_rate": 4.1805306714444164e-05, "loss": 0.6708, "step": 1922 }, { "epoch": 0.492288, "grad_norm": 2.28125, "learning_rate": 4.180104086682024e-05, "loss": 0.6688, "step": 1923 }, { "epoch": 0.492544, "grad_norm": 2.859375, "learning_rate": 4.179677501919632e-05, "loss": 0.6093, "step": 1924 }, { "epoch": 0.4928, "grad_norm": 2.765625, "learning_rate": 4.179250917157239e-05, "loss": 0.6, "step": 1925 }, { "epoch": 0.493056, "grad_norm": 2.484375, "learning_rate": 4.1788243323948474e-05, "loss": 0.6448, "step": 1926 }, { "epoch": 0.493312, "grad_norm": 2.75, "learning_rate": 4.178397747632455e-05, "loss": 0.5946, "step": 1927 }, { "epoch": 0.493568, "grad_norm": 2.59375, "learning_rate": 4.177971162870062e-05, "loss": 0.6115, "step": 1928 }, { "epoch": 0.493824, "grad_norm": 2.75, "learning_rate": 4.17754457810767e-05, "loss": 0.6288, "step": 1929 }, { "epoch": 0.49408, "grad_norm": 2.359375, "learning_rate": 4.177117993345278e-05, "loss": 0.6687, "step": 1930 }, { "epoch": 0.494336, "grad_norm": 2.4375, "learning_rate": 4.176691408582886e-05, "loss": 0.6401, "step": 1931 }, { "epoch": 0.494592, "grad_norm": 2.515625, "learning_rate": 4.176264823820493e-05, "loss": 0.6322, "step": 1932 }, { "epoch": 0.494848, "grad_norm": 2.53125, "learning_rate": 4.175838239058101e-05, "loss": 0.6074, "step": 1933 }, { "epoch": 0.495104, "grad_norm": 2.765625, "learning_rate": 4.175411654295709e-05, "loss": 0.6243, "step": 1934 }, { "epoch": 0.49536, "grad_norm": 2.734375, "learning_rate": 4.174985069533316e-05, "loss": 0.6853, "step": 1935 }, { "epoch": 0.495616, "grad_norm": 2.484375, "learning_rate": 4.174558484770924e-05, "loss": 0.6298, "step": 1936 }, { "epoch": 0.495872, "grad_norm": 2.625, "learning_rate": 4.1741319000085325e-05, "loss": 0.5976, "step": 1937 }, { "epoch": 0.496128, "grad_norm": 2.703125, "learning_rate": 4.17370531524614e-05, "loss": 0.6356, "step": 1938 }, { "epoch": 0.496384, "grad_norm": 2.40625, "learning_rate": 4.1732787304837473e-05, "loss": 0.6111, "step": 1939 }, { "epoch": 0.49664, "grad_norm": 2.4375, "learning_rate": 4.172852145721355e-05, "loss": 0.6472, "step": 1940 }, { "epoch": 0.496896, "grad_norm": 2.59375, "learning_rate": 4.172425560958963e-05, "loss": 0.6054, "step": 1941 }, { "epoch": 0.497152, "grad_norm": 2.734375, "learning_rate": 4.17199897619657e-05, "loss": 0.6193, "step": 1942 }, { "epoch": 0.497408, "grad_norm": 2.359375, "learning_rate": 4.1715723914341784e-05, "loss": 0.644, "step": 1943 }, { "epoch": 0.497664, "grad_norm": 2.59375, "learning_rate": 4.171145806671786e-05, "loss": 0.6214, "step": 1944 }, { "epoch": 0.49792, "grad_norm": 2.4375, "learning_rate": 4.170719221909394e-05, "loss": 0.6042, "step": 1945 }, { "epoch": 0.498176, "grad_norm": 2.3125, "learning_rate": 4.1702926371470014e-05, "loss": 0.5859, "step": 1946 }, { "epoch": 0.498432, "grad_norm": 2.421875, "learning_rate": 4.169866052384609e-05, "loss": 0.5836, "step": 1947 }, { "epoch": 0.498688, "grad_norm": 2.515625, "learning_rate": 4.169439467622216e-05, "loss": 0.6206, "step": 1948 }, { "epoch": 0.498944, "grad_norm": 2.5, "learning_rate": 4.169012882859824e-05, "loss": 0.64, "step": 1949 }, { "epoch": 0.4992, "grad_norm": 2.5625, "learning_rate": 4.1685862980974324e-05, "loss": 0.6233, "step": 1950 }, { "epoch": 0.499456, "grad_norm": 2.546875, "learning_rate": 4.16815971333504e-05, "loss": 0.5805, "step": 1951 }, { "epoch": 0.499712, "grad_norm": 2.734375, "learning_rate": 4.167733128572648e-05, "loss": 0.6215, "step": 1952 }, { "epoch": 0.499968, "grad_norm": 2.8125, "learning_rate": 4.1673065438102554e-05, "loss": 0.6343, "step": 1953 }, { "epoch": 0.500224, "grad_norm": 2.734375, "learning_rate": 4.166879959047863e-05, "loss": 0.6292, "step": 1954 }, { "epoch": 0.50048, "grad_norm": 2.375, "learning_rate": 4.16645337428547e-05, "loss": 0.624, "step": 1955 }, { "epoch": 0.500736, "grad_norm": 2.40625, "learning_rate": 4.1660267895230783e-05, "loss": 0.6571, "step": 1956 }, { "epoch": 0.500992, "grad_norm": 2.5625, "learning_rate": 4.1656002047606864e-05, "loss": 0.6199, "step": 1957 }, { "epoch": 0.501248, "grad_norm": 2.5625, "learning_rate": 4.165173619998294e-05, "loss": 0.6246, "step": 1958 }, { "epoch": 0.501504, "grad_norm": 2.75, "learning_rate": 4.164747035235901e-05, "loss": 0.647, "step": 1959 }, { "epoch": 0.50176, "grad_norm": 2.875, "learning_rate": 4.1643204504735094e-05, "loss": 0.5968, "step": 1960 }, { "epoch": 0.502016, "grad_norm": 2.5, "learning_rate": 4.163893865711117e-05, "loss": 0.6433, "step": 1961 }, { "epoch": 0.502272, "grad_norm": 2.46875, "learning_rate": 4.163467280948725e-05, "loss": 0.6462, "step": 1962 }, { "epoch": 0.502528, "grad_norm": 2.8125, "learning_rate": 4.1630406961863324e-05, "loss": 0.6536, "step": 1963 }, { "epoch": 0.502784, "grad_norm": 2.5, "learning_rate": 4.1626141114239405e-05, "loss": 0.6222, "step": 1964 }, { "epoch": 0.50304, "grad_norm": 2.53125, "learning_rate": 4.162187526661548e-05, "loss": 0.6431, "step": 1965 }, { "epoch": 0.503296, "grad_norm": 2.46875, "learning_rate": 4.161760941899155e-05, "loss": 0.6221, "step": 1966 }, { "epoch": 0.503552, "grad_norm": 2.390625, "learning_rate": 4.161334357136763e-05, "loss": 0.6208, "step": 1967 }, { "epoch": 0.503808, "grad_norm": 2.59375, "learning_rate": 4.160907772374371e-05, "loss": 0.6164, "step": 1968 }, { "epoch": 0.504064, "grad_norm": 2.46875, "learning_rate": 4.160481187611979e-05, "loss": 0.6133, "step": 1969 }, { "epoch": 0.50432, "grad_norm": 2.546875, "learning_rate": 4.1600546028495864e-05, "loss": 0.6011, "step": 1970 }, { "epoch": 0.504576, "grad_norm": 2.6875, "learning_rate": 4.1596280180871945e-05, "loss": 0.6766, "step": 1971 }, { "epoch": 0.504832, "grad_norm": 2.578125, "learning_rate": 4.159201433324802e-05, "loss": 0.6414, "step": 1972 }, { "epoch": 0.505088, "grad_norm": 2.8125, "learning_rate": 4.1587748485624093e-05, "loss": 0.6311, "step": 1973 }, { "epoch": 0.505344, "grad_norm": 2.359375, "learning_rate": 4.158348263800017e-05, "loss": 0.6374, "step": 1974 }, { "epoch": 0.5056, "grad_norm": 2.640625, "learning_rate": 4.157921679037625e-05, "loss": 0.6343, "step": 1975 }, { "epoch": 0.505856, "grad_norm": 2.796875, "learning_rate": 4.157495094275233e-05, "loss": 0.6041, "step": 1976 }, { "epoch": 0.506112, "grad_norm": 2.625, "learning_rate": 4.1570685095128404e-05, "loss": 0.6253, "step": 1977 }, { "epoch": 0.506368, "grad_norm": 2.421875, "learning_rate": 4.156641924750448e-05, "loss": 0.6448, "step": 1978 }, { "epoch": 0.506624, "grad_norm": 2.734375, "learning_rate": 4.156215339988056e-05, "loss": 0.645, "step": 1979 }, { "epoch": 0.50688, "grad_norm": 2.46875, "learning_rate": 4.1557887552256634e-05, "loss": 0.6325, "step": 1980 }, { "epoch": 0.507136, "grad_norm": 2.734375, "learning_rate": 4.1553621704632715e-05, "loss": 0.6484, "step": 1981 }, { "epoch": 0.507392, "grad_norm": 2.484375, "learning_rate": 4.154935585700879e-05, "loss": 0.642, "step": 1982 }, { "epoch": 0.507648, "grad_norm": 2.53125, "learning_rate": 4.154509000938487e-05, "loss": 0.634, "step": 1983 }, { "epoch": 0.507904, "grad_norm": 2.9375, "learning_rate": 4.1540824161760944e-05, "loss": 0.6276, "step": 1984 }, { "epoch": 0.50816, "grad_norm": 2.59375, "learning_rate": 4.153655831413702e-05, "loss": 0.6227, "step": 1985 }, { "epoch": 0.508416, "grad_norm": 2.328125, "learning_rate": 4.15322924665131e-05, "loss": 0.6949, "step": 1986 }, { "epoch": 0.508672, "grad_norm": 2.421875, "learning_rate": 4.1528026618889174e-05, "loss": 0.6146, "step": 1987 }, { "epoch": 0.508928, "grad_norm": 2.40625, "learning_rate": 4.1523760771265255e-05, "loss": 0.6309, "step": 1988 }, { "epoch": 0.509184, "grad_norm": 2.234375, "learning_rate": 4.151949492364133e-05, "loss": 0.5969, "step": 1989 }, { "epoch": 0.50944, "grad_norm": 2.515625, "learning_rate": 4.151522907601741e-05, "loss": 0.6229, "step": 1990 }, { "epoch": 0.509696, "grad_norm": 2.625, "learning_rate": 4.1510963228393484e-05, "loss": 0.6222, "step": 1991 }, { "epoch": 0.509952, "grad_norm": 2.484375, "learning_rate": 4.150669738076956e-05, "loss": 0.6194, "step": 1992 }, { "epoch": 0.510208, "grad_norm": 2.34375, "learning_rate": 4.150243153314563e-05, "loss": 0.6092, "step": 1993 }, { "epoch": 0.510464, "grad_norm": 2.53125, "learning_rate": 4.1498165685521714e-05, "loss": 0.6541, "step": 1994 }, { "epoch": 0.51072, "grad_norm": 2.859375, "learning_rate": 4.1493899837897795e-05, "loss": 0.643, "step": 1995 }, { "epoch": 0.510976, "grad_norm": 2.703125, "learning_rate": 4.148963399027387e-05, "loss": 0.6467, "step": 1996 }, { "epoch": 0.511232, "grad_norm": 2.546875, "learning_rate": 4.1485368142649944e-05, "loss": 0.6128, "step": 1997 }, { "epoch": 0.511488, "grad_norm": 2.484375, "learning_rate": 4.1481102295026025e-05, "loss": 0.5968, "step": 1998 }, { "epoch": 0.511744, "grad_norm": 2.59375, "learning_rate": 4.14768364474021e-05, "loss": 0.6561, "step": 1999 }, { "epoch": 0.512, "grad_norm": 2.53125, "learning_rate": 4.147257059977818e-05, "loss": 0.6535, "step": 2000 }, { "epoch": 0.512256, "grad_norm": 2.546875, "learning_rate": 4.146830475215426e-05, "loss": 0.5952, "step": 2001 }, { "epoch": 0.512512, "grad_norm": 2.375, "learning_rate": 4.1464038904530335e-05, "loss": 0.657, "step": 2002 }, { "epoch": 0.512768, "grad_norm": 2.4375, "learning_rate": 4.145977305690641e-05, "loss": 0.646, "step": 2003 }, { "epoch": 0.513024, "grad_norm": 2.609375, "learning_rate": 4.1455507209282484e-05, "loss": 0.6377, "step": 2004 }, { "epoch": 0.51328, "grad_norm": 2.671875, "learning_rate": 4.1451241361658565e-05, "loss": 0.596, "step": 2005 }, { "epoch": 0.513536, "grad_norm": 2.40625, "learning_rate": 4.144697551403464e-05, "loss": 0.6233, "step": 2006 }, { "epoch": 0.513792, "grad_norm": 2.3125, "learning_rate": 4.144270966641072e-05, "loss": 0.6182, "step": 2007 }, { "epoch": 0.514048, "grad_norm": 2.390625, "learning_rate": 4.1438443818786794e-05, "loss": 0.615, "step": 2008 }, { "epoch": 0.514304, "grad_norm": 2.5, "learning_rate": 4.1434177971162875e-05, "loss": 0.5712, "step": 2009 }, { "epoch": 0.51456, "grad_norm": 2.40625, "learning_rate": 4.142991212353895e-05, "loss": 0.647, "step": 2010 }, { "epoch": 0.514816, "grad_norm": 2.546875, "learning_rate": 4.1425646275915024e-05, "loss": 0.5841, "step": 2011 }, { "epoch": 0.515072, "grad_norm": 2.96875, "learning_rate": 4.14213804282911e-05, "loss": 0.627, "step": 2012 }, { "epoch": 0.515328, "grad_norm": 2.875, "learning_rate": 4.141711458066718e-05, "loss": 0.6504, "step": 2013 }, { "epoch": 0.515584, "grad_norm": 2.765625, "learning_rate": 4.141284873304326e-05, "loss": 0.6294, "step": 2014 }, { "epoch": 0.51584, "grad_norm": 2.6875, "learning_rate": 4.1408582885419335e-05, "loss": 0.6124, "step": 2015 }, { "epoch": 0.516096, "grad_norm": 2.6875, "learning_rate": 4.140431703779541e-05, "loss": 0.6154, "step": 2016 }, { "epoch": 0.516352, "grad_norm": 3.0625, "learning_rate": 4.140005119017149e-05, "loss": 0.6285, "step": 2017 }, { "epoch": 0.516608, "grad_norm": 2.78125, "learning_rate": 4.1395785342547564e-05, "loss": 0.6201, "step": 2018 }, { "epoch": 0.516864, "grad_norm": 2.703125, "learning_rate": 4.139151949492364e-05, "loss": 0.5843, "step": 2019 }, { "epoch": 0.51712, "grad_norm": 2.53125, "learning_rate": 4.1387253647299726e-05, "loss": 0.6199, "step": 2020 }, { "epoch": 0.517376, "grad_norm": 2.5625, "learning_rate": 4.13829877996758e-05, "loss": 0.6278, "step": 2021 }, { "epoch": 0.517632, "grad_norm": 2.796875, "learning_rate": 4.1378721952051875e-05, "loss": 0.6232, "step": 2022 }, { "epoch": 0.517888, "grad_norm": 2.921875, "learning_rate": 4.137445610442795e-05, "loss": 0.6425, "step": 2023 }, { "epoch": 0.518144, "grad_norm": 2.75, "learning_rate": 4.137019025680403e-05, "loss": 0.6068, "step": 2024 }, { "epoch": 0.5184, "grad_norm": 2.59375, "learning_rate": 4.1365924409180104e-05, "loss": 0.6475, "step": 2025 }, { "epoch": 0.518656, "grad_norm": 2.71875, "learning_rate": 4.1361658561556185e-05, "loss": 0.6231, "step": 2026 }, { "epoch": 0.518912, "grad_norm": 2.765625, "learning_rate": 4.135739271393226e-05, "loss": 0.6212, "step": 2027 }, { "epoch": 0.519168, "grad_norm": 2.28125, "learning_rate": 4.135312686630834e-05, "loss": 0.6159, "step": 2028 }, { "epoch": 0.519424, "grad_norm": 2.6875, "learning_rate": 4.1348861018684415e-05, "loss": 0.6388, "step": 2029 }, { "epoch": 0.51968, "grad_norm": 2.734375, "learning_rate": 4.134459517106049e-05, "loss": 0.6157, "step": 2030 }, { "epoch": 0.519936, "grad_norm": 2.40625, "learning_rate": 4.1340329323436563e-05, "loss": 0.6173, "step": 2031 }, { "epoch": 0.520192, "grad_norm": 2.46875, "learning_rate": 4.1336063475812645e-05, "loss": 0.6197, "step": 2032 }, { "epoch": 0.520448, "grad_norm": 2.71875, "learning_rate": 4.1331797628188726e-05, "loss": 0.6093, "step": 2033 }, { "epoch": 0.520704, "grad_norm": 2.671875, "learning_rate": 4.13275317805648e-05, "loss": 0.6096, "step": 2034 }, { "epoch": 0.52096, "grad_norm": 2.609375, "learning_rate": 4.132326593294088e-05, "loss": 0.6041, "step": 2035 }, { "epoch": 0.521216, "grad_norm": 2.59375, "learning_rate": 4.1319000085316955e-05, "loss": 0.6592, "step": 2036 }, { "epoch": 0.521472, "grad_norm": 2.71875, "learning_rate": 4.131473423769303e-05, "loss": 0.6518, "step": 2037 }, { "epoch": 0.521728, "grad_norm": 2.46875, "learning_rate": 4.1310468390069104e-05, "loss": 0.6254, "step": 2038 }, { "epoch": 0.521984, "grad_norm": 2.75, "learning_rate": 4.130620254244519e-05, "loss": 0.6475, "step": 2039 }, { "epoch": 0.52224, "grad_norm": 2.6875, "learning_rate": 4.1301936694821266e-05, "loss": 0.6154, "step": 2040 }, { "epoch": 0.522496, "grad_norm": 2.5625, "learning_rate": 4.129767084719734e-05, "loss": 0.6439, "step": 2041 }, { "epoch": 0.522752, "grad_norm": 2.6875, "learning_rate": 4.1293404999573414e-05, "loss": 0.6417, "step": 2042 }, { "epoch": 0.523008, "grad_norm": 2.71875, "learning_rate": 4.1289139151949495e-05, "loss": 0.5916, "step": 2043 }, { "epoch": 0.523264, "grad_norm": 2.65625, "learning_rate": 4.128487330432557e-05, "loss": 0.6169, "step": 2044 }, { "epoch": 0.52352, "grad_norm": 2.6875, "learning_rate": 4.128060745670165e-05, "loss": 0.6321, "step": 2045 }, { "epoch": 0.523776, "grad_norm": 2.4375, "learning_rate": 4.1276341609077725e-05, "loss": 0.586, "step": 2046 }, { "epoch": 0.524032, "grad_norm": 2.609375, "learning_rate": 4.1272075761453806e-05, "loss": 0.587, "step": 2047 }, { "epoch": 0.524288, "grad_norm": 2.546875, "learning_rate": 4.126780991382988e-05, "loss": 0.6062, "step": 2048 }, { "epoch": 0.524544, "grad_norm": 2.296875, "learning_rate": 4.1263544066205954e-05, "loss": 0.6487, "step": 2049 }, { "epoch": 0.5248, "grad_norm": 2.34375, "learning_rate": 4.125927821858203e-05, "loss": 0.631, "step": 2050 }, { "epoch": 0.525056, "grad_norm": 2.484375, "learning_rate": 4.125501237095811e-05, "loss": 0.6168, "step": 2051 }, { "epoch": 0.525312, "grad_norm": 2.515625, "learning_rate": 4.125074652333419e-05, "loss": 0.6255, "step": 2052 }, { "epoch": 0.525568, "grad_norm": 2.296875, "learning_rate": 4.1246480675710265e-05, "loss": 0.6164, "step": 2053 }, { "epoch": 0.525824, "grad_norm": 2.515625, "learning_rate": 4.1242214828086346e-05, "loss": 0.638, "step": 2054 }, { "epoch": 0.52608, "grad_norm": 2.171875, "learning_rate": 4.123794898046242e-05, "loss": 0.6321, "step": 2055 }, { "epoch": 0.526336, "grad_norm": 2.28125, "learning_rate": 4.1233683132838495e-05, "loss": 0.6168, "step": 2056 }, { "epoch": 0.526592, "grad_norm": 2.46875, "learning_rate": 4.122941728521457e-05, "loss": 0.581, "step": 2057 }, { "epoch": 0.526848, "grad_norm": 2.390625, "learning_rate": 4.122515143759065e-05, "loss": 0.6176, "step": 2058 }, { "epoch": 0.527104, "grad_norm": 2.453125, "learning_rate": 4.122088558996673e-05, "loss": 0.63, "step": 2059 }, { "epoch": 0.52736, "grad_norm": 2.4375, "learning_rate": 4.1216619742342805e-05, "loss": 0.6103, "step": 2060 }, { "epoch": 0.527616, "grad_norm": 2.609375, "learning_rate": 4.121235389471888e-05, "loss": 0.6408, "step": 2061 }, { "epoch": 0.527872, "grad_norm": 2.703125, "learning_rate": 4.120808804709496e-05, "loss": 0.5923, "step": 2062 }, { "epoch": 0.528128, "grad_norm": 2.421875, "learning_rate": 4.1203822199471035e-05, "loss": 0.5801, "step": 2063 }, { "epoch": 0.528384, "grad_norm": 2.515625, "learning_rate": 4.1199556351847116e-05, "loss": 0.6259, "step": 2064 }, { "epoch": 0.52864, "grad_norm": 2.390625, "learning_rate": 4.119529050422319e-05, "loss": 0.6131, "step": 2065 }, { "epoch": 0.528896, "grad_norm": 2.734375, "learning_rate": 4.119102465659927e-05, "loss": 0.6104, "step": 2066 }, { "epoch": 0.529152, "grad_norm": 2.8125, "learning_rate": 4.1186758808975345e-05, "loss": 0.5971, "step": 2067 }, { "epoch": 0.529408, "grad_norm": 2.546875, "learning_rate": 4.118249296135142e-05, "loss": 0.6235, "step": 2068 }, { "epoch": 0.529664, "grad_norm": 2.453125, "learning_rate": 4.11782271137275e-05, "loss": 0.6444, "step": 2069 }, { "epoch": 0.52992, "grad_norm": 2.78125, "learning_rate": 4.1173961266103575e-05, "loss": 0.599, "step": 2070 }, { "epoch": 0.530176, "grad_norm": 2.53125, "learning_rate": 4.1169695418479656e-05, "loss": 0.5807, "step": 2071 }, { "epoch": 0.530432, "grad_norm": 2.53125, "learning_rate": 4.116542957085573e-05, "loss": 0.6088, "step": 2072 }, { "epoch": 0.530688, "grad_norm": 2.875, "learning_rate": 4.116116372323181e-05, "loss": 0.6359, "step": 2073 }, { "epoch": 0.530944, "grad_norm": 2.4375, "learning_rate": 4.1156897875607886e-05, "loss": 0.6069, "step": 2074 }, { "epoch": 0.5312, "grad_norm": 2.34375, "learning_rate": 4.115263202798396e-05, "loss": 0.6442, "step": 2075 }, { "epoch": 0.531456, "grad_norm": 2.421875, "learning_rate": 4.1148366180360034e-05, "loss": 0.6293, "step": 2076 }, { "epoch": 0.531712, "grad_norm": 2.875, "learning_rate": 4.1144100332736115e-05, "loss": 0.6592, "step": 2077 }, { "epoch": 0.531968, "grad_norm": 2.59375, "learning_rate": 4.1139834485112196e-05, "loss": 0.6319, "step": 2078 }, { "epoch": 0.532224, "grad_norm": 2.5625, "learning_rate": 4.113556863748827e-05, "loss": 0.6452, "step": 2079 }, { "epoch": 0.53248, "grad_norm": 2.65625, "learning_rate": 4.1131302789864345e-05, "loss": 0.5807, "step": 2080 }, { "epoch": 0.532736, "grad_norm": 2.46875, "learning_rate": 4.1127036942240426e-05, "loss": 0.5957, "step": 2081 }, { "epoch": 0.532992, "grad_norm": 2.453125, "learning_rate": 4.11227710946165e-05, "loss": 0.6092, "step": 2082 }, { "epoch": 0.533248, "grad_norm": 2.71875, "learning_rate": 4.111850524699258e-05, "loss": 0.5887, "step": 2083 }, { "epoch": 0.533504, "grad_norm": 2.578125, "learning_rate": 4.111423939936866e-05, "loss": 0.6026, "step": 2084 }, { "epoch": 0.53376, "grad_norm": 2.46875, "learning_rate": 4.1109973551744736e-05, "loss": 0.6247, "step": 2085 }, { "epoch": 0.534016, "grad_norm": 2.90625, "learning_rate": 4.110570770412081e-05, "loss": 0.6224, "step": 2086 }, { "epoch": 0.534272, "grad_norm": 2.5625, "learning_rate": 4.1101441856496885e-05, "loss": 0.5983, "step": 2087 }, { "epoch": 0.534528, "grad_norm": 2.5625, "learning_rate": 4.1097176008872966e-05, "loss": 0.6103, "step": 2088 }, { "epoch": 0.534784, "grad_norm": 2.21875, "learning_rate": 4.109291016124904e-05, "loss": 0.6172, "step": 2089 }, { "epoch": 0.53504, "grad_norm": 2.6875, "learning_rate": 4.108864431362512e-05, "loss": 0.5837, "step": 2090 }, { "epoch": 0.535296, "grad_norm": 2.46875, "learning_rate": 4.1084378466001196e-05, "loss": 0.6076, "step": 2091 }, { "epoch": 0.535552, "grad_norm": 2.5, "learning_rate": 4.108011261837728e-05, "loss": 0.6325, "step": 2092 }, { "epoch": 0.535808, "grad_norm": 2.421875, "learning_rate": 4.107584677075335e-05, "loss": 0.6113, "step": 2093 }, { "epoch": 0.536064, "grad_norm": 2.609375, "learning_rate": 4.1071580923129425e-05, "loss": 0.6219, "step": 2094 }, { "epoch": 0.53632, "grad_norm": 2.671875, "learning_rate": 4.10673150755055e-05, "loss": 0.6122, "step": 2095 }, { "epoch": 0.536576, "grad_norm": 2.34375, "learning_rate": 4.106304922788158e-05, "loss": 0.567, "step": 2096 }, { "epoch": 0.536832, "grad_norm": 2.75, "learning_rate": 4.105878338025766e-05, "loss": 0.6095, "step": 2097 }, { "epoch": 0.537088, "grad_norm": 2.421875, "learning_rate": 4.1054517532633736e-05, "loss": 0.5946, "step": 2098 }, { "epoch": 0.537344, "grad_norm": 2.59375, "learning_rate": 4.105025168500981e-05, "loss": 0.6205, "step": 2099 }, { "epoch": 0.5376, "grad_norm": 2.640625, "learning_rate": 4.104598583738589e-05, "loss": 0.6124, "step": 2100 }, { "epoch": 0.537856, "grad_norm": 2.609375, "learning_rate": 4.1041719989761965e-05, "loss": 0.6101, "step": 2101 }, { "epoch": 0.538112, "grad_norm": 2.78125, "learning_rate": 4.1037454142138046e-05, "loss": 0.5629, "step": 2102 }, { "epoch": 0.538368, "grad_norm": 2.390625, "learning_rate": 4.103318829451413e-05, "loss": 0.6245, "step": 2103 }, { "epoch": 0.538624, "grad_norm": 2.265625, "learning_rate": 4.10289224468902e-05, "loss": 0.6179, "step": 2104 }, { "epoch": 0.53888, "grad_norm": 2.5, "learning_rate": 4.1024656599266276e-05, "loss": 0.5607, "step": 2105 }, { "epoch": 0.539136, "grad_norm": 2.34375, "learning_rate": 4.102039075164235e-05, "loss": 0.6018, "step": 2106 }, { "epoch": 0.539392, "grad_norm": 2.328125, "learning_rate": 4.101612490401843e-05, "loss": 0.5782, "step": 2107 }, { "epoch": 0.539648, "grad_norm": 2.203125, "learning_rate": 4.1011859056394506e-05, "loss": 0.6034, "step": 2108 }, { "epoch": 0.539904, "grad_norm": 2.484375, "learning_rate": 4.100759320877059e-05, "loss": 0.6055, "step": 2109 }, { "epoch": 0.54016, "grad_norm": 2.421875, "learning_rate": 4.100332736114666e-05, "loss": 0.6333, "step": 2110 }, { "epoch": 0.540416, "grad_norm": 2.390625, "learning_rate": 4.099906151352274e-05, "loss": 0.559, "step": 2111 }, { "epoch": 0.540672, "grad_norm": 2.65625, "learning_rate": 4.0994795665898816e-05, "loss": 0.5789, "step": 2112 }, { "epoch": 0.540928, "grad_norm": 2.59375, "learning_rate": 4.099052981827489e-05, "loss": 0.6115, "step": 2113 }, { "epoch": 0.541184, "grad_norm": 2.40625, "learning_rate": 4.0986263970650965e-05, "loss": 0.5696, "step": 2114 }, { "epoch": 0.54144, "grad_norm": 2.546875, "learning_rate": 4.0981998123027046e-05, "loss": 0.6158, "step": 2115 }, { "epoch": 0.541696, "grad_norm": 2.9375, "learning_rate": 4.097773227540313e-05, "loss": 0.5661, "step": 2116 }, { "epoch": 0.541952, "grad_norm": 2.6875, "learning_rate": 4.09734664277792e-05, "loss": 0.61, "step": 2117 }, { "epoch": 0.542208, "grad_norm": 2.453125, "learning_rate": 4.096920058015528e-05, "loss": 0.5833, "step": 2118 }, { "epoch": 0.542464, "grad_norm": 2.625, "learning_rate": 4.0964934732531356e-05, "loss": 0.6136, "step": 2119 }, { "epoch": 0.54272, "grad_norm": 2.484375, "learning_rate": 4.096066888490743e-05, "loss": 0.5829, "step": 2120 }, { "epoch": 0.542976, "grad_norm": 2.453125, "learning_rate": 4.095640303728351e-05, "loss": 0.5866, "step": 2121 }, { "epoch": 0.543232, "grad_norm": 2.453125, "learning_rate": 4.095213718965959e-05, "loss": 0.614, "step": 2122 }, { "epoch": 0.543488, "grad_norm": 2.578125, "learning_rate": 4.094787134203567e-05, "loss": 0.6034, "step": 2123 }, { "epoch": 0.543744, "grad_norm": 2.671875, "learning_rate": 4.094360549441174e-05, "loss": 0.5657, "step": 2124 }, { "epoch": 0.544, "grad_norm": 2.5, "learning_rate": 4.0939339646787816e-05, "loss": 0.6144, "step": 2125 }, { "epoch": 0.544256, "grad_norm": 2.390625, "learning_rate": 4.09350737991639e-05, "loss": 0.6208, "step": 2126 }, { "epoch": 0.544512, "grad_norm": 2.5625, "learning_rate": 4.093080795153997e-05, "loss": 0.6374, "step": 2127 }, { "epoch": 0.544768, "grad_norm": 2.609375, "learning_rate": 4.092654210391605e-05, "loss": 0.6011, "step": 2128 }, { "epoch": 0.545024, "grad_norm": 2.5625, "learning_rate": 4.0922276256292126e-05, "loss": 0.6346, "step": 2129 }, { "epoch": 0.54528, "grad_norm": 2.578125, "learning_rate": 4.091801040866821e-05, "loss": 0.6084, "step": 2130 }, { "epoch": 0.545536, "grad_norm": 2.703125, "learning_rate": 4.091374456104428e-05, "loss": 0.6208, "step": 2131 }, { "epoch": 0.545792, "grad_norm": 2.609375, "learning_rate": 4.0909478713420356e-05, "loss": 0.5819, "step": 2132 }, { "epoch": 0.546048, "grad_norm": 2.65625, "learning_rate": 4.090521286579644e-05, "loss": 0.6541, "step": 2133 }, { "epoch": 0.546304, "grad_norm": 2.671875, "learning_rate": 4.090094701817251e-05, "loss": 0.6092, "step": 2134 }, { "epoch": 0.54656, "grad_norm": 2.4375, "learning_rate": 4.089668117054859e-05, "loss": 0.5951, "step": 2135 }, { "epoch": 0.546816, "grad_norm": 2.59375, "learning_rate": 4.0892415322924666e-05, "loss": 0.5777, "step": 2136 }, { "epoch": 0.547072, "grad_norm": 2.53125, "learning_rate": 4.088814947530075e-05, "loss": 0.5995, "step": 2137 }, { "epoch": 0.547328, "grad_norm": 2.484375, "learning_rate": 4.088388362767682e-05, "loss": 0.5921, "step": 2138 }, { "epoch": 0.547584, "grad_norm": 2.546875, "learning_rate": 4.0879617780052896e-05, "loss": 0.6081, "step": 2139 }, { "epoch": 0.54784, "grad_norm": 2.625, "learning_rate": 4.087535193242897e-05, "loss": 0.6259, "step": 2140 }, { "epoch": 0.548096, "grad_norm": 2.4375, "learning_rate": 4.087108608480506e-05, "loss": 0.6083, "step": 2141 }, { "epoch": 0.548352, "grad_norm": 2.625, "learning_rate": 4.086682023718113e-05, "loss": 0.6002, "step": 2142 }, { "epoch": 0.548608, "grad_norm": 2.359375, "learning_rate": 4.0862554389557207e-05, "loss": 0.595, "step": 2143 }, { "epoch": 0.548864, "grad_norm": 2.234375, "learning_rate": 4.085828854193328e-05, "loss": 0.6173, "step": 2144 }, { "epoch": 0.54912, "grad_norm": 2.65625, "learning_rate": 4.085402269430936e-05, "loss": 0.6197, "step": 2145 }, { "epoch": 0.549376, "grad_norm": 2.5, "learning_rate": 4.0849756846685436e-05, "loss": 0.5852, "step": 2146 }, { "epoch": 0.549632, "grad_norm": 2.453125, "learning_rate": 4.084549099906152e-05, "loss": 0.6228, "step": 2147 }, { "epoch": 0.549888, "grad_norm": 2.40625, "learning_rate": 4.084122515143759e-05, "loss": 0.5999, "step": 2148 }, { "epoch": 0.550144, "grad_norm": 2.34375, "learning_rate": 4.083695930381367e-05, "loss": 0.6362, "step": 2149 }, { "epoch": 0.5504, "grad_norm": 2.484375, "learning_rate": 4.083269345618975e-05, "loss": 0.6257, "step": 2150 }, { "epoch": 0.550656, "grad_norm": 2.328125, "learning_rate": 4.082842760856582e-05, "loss": 0.6205, "step": 2151 }, { "epoch": 0.550912, "grad_norm": 2.4375, "learning_rate": 4.08241617609419e-05, "loss": 0.5644, "step": 2152 }, { "epoch": 0.551168, "grad_norm": 2.453125, "learning_rate": 4.0819895913317976e-05, "loss": 0.593, "step": 2153 }, { "epoch": 0.551424, "grad_norm": 2.8125, "learning_rate": 4.081563006569406e-05, "loss": 0.5956, "step": 2154 }, { "epoch": 0.55168, "grad_norm": 2.59375, "learning_rate": 4.081136421807013e-05, "loss": 0.634, "step": 2155 }, { "epoch": 0.551936, "grad_norm": 2.609375, "learning_rate": 4.080709837044621e-05, "loss": 0.6315, "step": 2156 }, { "epoch": 0.552192, "grad_norm": 3.0, "learning_rate": 4.080283252282229e-05, "loss": 0.6356, "step": 2157 }, { "epoch": 0.552448, "grad_norm": 2.96875, "learning_rate": 4.079856667519836e-05, "loss": 0.6057, "step": 2158 }, { "epoch": 0.552704, "grad_norm": 2.375, "learning_rate": 4.0794300827574435e-05, "loss": 0.5939, "step": 2159 }, { "epoch": 0.55296, "grad_norm": 2.734375, "learning_rate": 4.0790034979950517e-05, "loss": 0.5972, "step": 2160 }, { "epoch": 0.553216, "grad_norm": 2.5625, "learning_rate": 4.07857691323266e-05, "loss": 0.6201, "step": 2161 }, { "epoch": 0.553472, "grad_norm": 2.515625, "learning_rate": 4.078150328470267e-05, "loss": 0.609, "step": 2162 }, { "epoch": 0.553728, "grad_norm": 2.453125, "learning_rate": 4.0777237437078746e-05, "loss": 0.6141, "step": 2163 }, { "epoch": 0.553984, "grad_norm": 2.734375, "learning_rate": 4.077297158945483e-05, "loss": 0.6009, "step": 2164 }, { "epoch": 0.55424, "grad_norm": 2.75, "learning_rate": 4.07687057418309e-05, "loss": 0.5762, "step": 2165 }, { "epoch": 0.554496, "grad_norm": 2.40625, "learning_rate": 4.076443989420698e-05, "loss": 0.5983, "step": 2166 }, { "epoch": 0.554752, "grad_norm": 2.21875, "learning_rate": 4.0760174046583064e-05, "loss": 0.6128, "step": 2167 }, { "epoch": 0.555008, "grad_norm": 2.71875, "learning_rate": 4.075590819895914e-05, "loss": 0.5909, "step": 2168 }, { "epoch": 0.555264, "grad_norm": 2.703125, "learning_rate": 4.075164235133521e-05, "loss": 0.5565, "step": 2169 }, { "epoch": 0.55552, "grad_norm": 2.5625, "learning_rate": 4.0747376503711286e-05, "loss": 0.5919, "step": 2170 }, { "epoch": 0.555776, "grad_norm": 2.140625, "learning_rate": 4.074311065608737e-05, "loss": 0.6091, "step": 2171 }, { "epoch": 0.556032, "grad_norm": 2.703125, "learning_rate": 4.073884480846344e-05, "loss": 0.5756, "step": 2172 }, { "epoch": 0.556288, "grad_norm": 2.6875, "learning_rate": 4.073457896083952e-05, "loss": 0.5885, "step": 2173 }, { "epoch": 0.556544, "grad_norm": 2.484375, "learning_rate": 4.07303131132156e-05, "loss": 0.6218, "step": 2174 }, { "epoch": 0.5568, "grad_norm": 2.84375, "learning_rate": 4.072604726559168e-05, "loss": 0.5941, "step": 2175 }, { "epoch": 0.557056, "grad_norm": 2.484375, "learning_rate": 4.072178141796775e-05, "loss": 0.5611, "step": 2176 }, { "epoch": 0.557312, "grad_norm": 2.65625, "learning_rate": 4.0717515570343826e-05, "loss": 0.6128, "step": 2177 }, { "epoch": 0.557568, "grad_norm": 2.578125, "learning_rate": 4.07132497227199e-05, "loss": 0.5754, "step": 2178 }, { "epoch": 0.557824, "grad_norm": 2.25, "learning_rate": 4.070898387509598e-05, "loss": 0.6212, "step": 2179 }, { "epoch": 0.55808, "grad_norm": 2.53125, "learning_rate": 4.070471802747206e-05, "loss": 0.6069, "step": 2180 }, { "epoch": 0.558336, "grad_norm": 2.53125, "learning_rate": 4.070045217984814e-05, "loss": 0.5849, "step": 2181 }, { "epoch": 0.558592, "grad_norm": 2.421875, "learning_rate": 4.069618633222422e-05, "loss": 0.6265, "step": 2182 }, { "epoch": 0.558848, "grad_norm": 2.5, "learning_rate": 4.069192048460029e-05, "loss": 0.5488, "step": 2183 }, { "epoch": 0.559104, "grad_norm": 2.765625, "learning_rate": 4.068765463697637e-05, "loss": 0.5929, "step": 2184 }, { "epoch": 0.55936, "grad_norm": 2.640625, "learning_rate": 4.068338878935245e-05, "loss": 0.605, "step": 2185 }, { "epoch": 0.559616, "grad_norm": 2.703125, "learning_rate": 4.067912294172853e-05, "loss": 0.5917, "step": 2186 }, { "epoch": 0.559872, "grad_norm": 2.359375, "learning_rate": 4.06748570941046e-05, "loss": 0.5963, "step": 2187 }, { "epoch": 0.560128, "grad_norm": 2.359375, "learning_rate": 4.067059124648068e-05, "loss": 0.6183, "step": 2188 }, { "epoch": 0.560384, "grad_norm": 2.59375, "learning_rate": 4.066632539885675e-05, "loss": 0.6276, "step": 2189 }, { "epoch": 0.56064, "grad_norm": 2.5, "learning_rate": 4.066205955123283e-05, "loss": 0.5925, "step": 2190 }, { "epoch": 0.560896, "grad_norm": 2.6875, "learning_rate": 4.065779370360891e-05, "loss": 0.5758, "step": 2191 }, { "epoch": 0.561152, "grad_norm": 2.734375, "learning_rate": 4.065352785598499e-05, "loss": 0.5661, "step": 2192 }, { "epoch": 0.561408, "grad_norm": 2.375, "learning_rate": 4.064926200836106e-05, "loss": 0.5846, "step": 2193 }, { "epoch": 0.561664, "grad_norm": 2.515625, "learning_rate": 4.064499616073714e-05, "loss": 0.5813, "step": 2194 }, { "epoch": 0.56192, "grad_norm": 2.578125, "learning_rate": 4.064073031311322e-05, "loss": 0.6121, "step": 2195 }, { "epoch": 0.562176, "grad_norm": 2.375, "learning_rate": 4.063646446548929e-05, "loss": 0.635, "step": 2196 }, { "epoch": 0.562432, "grad_norm": 2.25, "learning_rate": 4.0632198617865366e-05, "loss": 0.5764, "step": 2197 }, { "epoch": 0.562688, "grad_norm": 2.3125, "learning_rate": 4.062793277024145e-05, "loss": 0.6104, "step": 2198 }, { "epoch": 0.562944, "grad_norm": 2.46875, "learning_rate": 4.062366692261753e-05, "loss": 0.6141, "step": 2199 }, { "epoch": 0.5632, "grad_norm": 2.4375, "learning_rate": 4.06194010749936e-05, "loss": 0.6257, "step": 2200 }, { "epoch": 0.563456, "grad_norm": 2.25, "learning_rate": 4.0615135227369683e-05, "loss": 0.6254, "step": 2201 }, { "epoch": 0.563712, "grad_norm": 2.53125, "learning_rate": 4.061086937974576e-05, "loss": 0.5639, "step": 2202 }, { "epoch": 0.563968, "grad_norm": 2.453125, "learning_rate": 4.060660353212183e-05, "loss": 0.5829, "step": 2203 }, { "epoch": 0.564224, "grad_norm": 2.609375, "learning_rate": 4.060233768449791e-05, "loss": 0.639, "step": 2204 }, { "epoch": 0.56448, "grad_norm": 2.515625, "learning_rate": 4.0598071836873994e-05, "loss": 0.5741, "step": 2205 }, { "epoch": 0.564736, "grad_norm": 2.546875, "learning_rate": 4.059380598925007e-05, "loss": 0.5762, "step": 2206 }, { "epoch": 0.564992, "grad_norm": 2.90625, "learning_rate": 4.058954014162614e-05, "loss": 0.6176, "step": 2207 }, { "epoch": 0.565248, "grad_norm": 2.71875, "learning_rate": 4.058527429400222e-05, "loss": 0.5757, "step": 2208 }, { "epoch": 0.565504, "grad_norm": 2.328125, "learning_rate": 4.05810084463783e-05, "loss": 0.5458, "step": 2209 }, { "epoch": 0.56576, "grad_norm": 2.71875, "learning_rate": 4.057674259875437e-05, "loss": 0.5714, "step": 2210 }, { "epoch": 0.566016, "grad_norm": 2.71875, "learning_rate": 4.057247675113045e-05, "loss": 0.5816, "step": 2211 }, { "epoch": 0.566272, "grad_norm": 2.671875, "learning_rate": 4.056821090350653e-05, "loss": 0.6452, "step": 2212 }, { "epoch": 0.566528, "grad_norm": 2.390625, "learning_rate": 4.056394505588261e-05, "loss": 0.5882, "step": 2213 }, { "epoch": 0.566784, "grad_norm": 2.546875, "learning_rate": 4.055967920825868e-05, "loss": 0.6298, "step": 2214 }, { "epoch": 0.56704, "grad_norm": 2.640625, "learning_rate": 4.055541336063476e-05, "loss": 0.614, "step": 2215 }, { "epoch": 0.567296, "grad_norm": 2.53125, "learning_rate": 4.055114751301084e-05, "loss": 0.5986, "step": 2216 }, { "epoch": 0.567552, "grad_norm": 2.421875, "learning_rate": 4.054688166538691e-05, "loss": 0.5876, "step": 2217 }, { "epoch": 0.567808, "grad_norm": 2.578125, "learning_rate": 4.0542615817762993e-05, "loss": 0.5728, "step": 2218 }, { "epoch": 0.568064, "grad_norm": 2.75, "learning_rate": 4.053834997013907e-05, "loss": 0.5979, "step": 2219 }, { "epoch": 0.56832, "grad_norm": 2.515625, "learning_rate": 4.053408412251515e-05, "loss": 0.5913, "step": 2220 }, { "epoch": 0.568576, "grad_norm": 2.390625, "learning_rate": 4.052981827489122e-05, "loss": 0.5902, "step": 2221 }, { "epoch": 0.568832, "grad_norm": 2.453125, "learning_rate": 4.05255524272673e-05, "loss": 0.5861, "step": 2222 }, { "epoch": 0.569088, "grad_norm": 2.640625, "learning_rate": 4.052128657964338e-05, "loss": 0.6083, "step": 2223 }, { "epoch": 0.569344, "grad_norm": 2.515625, "learning_rate": 4.051702073201946e-05, "loss": 0.6329, "step": 2224 }, { "epoch": 0.5696, "grad_norm": 2.421875, "learning_rate": 4.0512754884395534e-05, "loss": 0.5515, "step": 2225 }, { "epoch": 0.569856, "grad_norm": 2.53125, "learning_rate": 4.050848903677161e-05, "loss": 0.613, "step": 2226 }, { "epoch": 0.570112, "grad_norm": 2.546875, "learning_rate": 4.050422318914768e-05, "loss": 0.6245, "step": 2227 }, { "epoch": 0.570368, "grad_norm": 2.453125, "learning_rate": 4.049995734152376e-05, "loss": 0.6026, "step": 2228 }, { "epoch": 0.570624, "grad_norm": 2.375, "learning_rate": 4.049569149389984e-05, "loss": 0.6102, "step": 2229 }, { "epoch": 0.57088, "grad_norm": 2.6875, "learning_rate": 4.049142564627592e-05, "loss": 0.5679, "step": 2230 }, { "epoch": 0.571136, "grad_norm": 2.765625, "learning_rate": 4.0487159798652e-05, "loss": 0.6142, "step": 2231 }, { "epoch": 0.571392, "grad_norm": 2.59375, "learning_rate": 4.0482893951028074e-05, "loss": 0.5921, "step": 2232 }, { "epoch": 0.571648, "grad_norm": 2.421875, "learning_rate": 4.047862810340415e-05, "loss": 0.5555, "step": 2233 }, { "epoch": 0.571904, "grad_norm": 2.34375, "learning_rate": 4.047436225578022e-05, "loss": 0.5706, "step": 2234 }, { "epoch": 0.57216, "grad_norm": 2.640625, "learning_rate": 4.04700964081563e-05, "loss": 0.6195, "step": 2235 }, { "epoch": 0.572416, "grad_norm": 2.6875, "learning_rate": 4.046583056053238e-05, "loss": 0.5959, "step": 2236 }, { "epoch": 0.572672, "grad_norm": 2.65625, "learning_rate": 4.046156471290846e-05, "loss": 0.5811, "step": 2237 }, { "epoch": 0.572928, "grad_norm": 2.5625, "learning_rate": 4.045729886528453e-05, "loss": 0.5581, "step": 2238 }, { "epoch": 0.573184, "grad_norm": 2.578125, "learning_rate": 4.0453033017660614e-05, "loss": 0.624, "step": 2239 }, { "epoch": 0.57344, "grad_norm": 2.546875, "learning_rate": 4.044876717003669e-05, "loss": 0.5999, "step": 2240 }, { "epoch": 0.573696, "grad_norm": 2.578125, "learning_rate": 4.044450132241276e-05, "loss": 0.6287, "step": 2241 }, { "epoch": 0.573952, "grad_norm": 2.703125, "learning_rate": 4.044023547478884e-05, "loss": 0.597, "step": 2242 }, { "epoch": 0.574208, "grad_norm": 2.65625, "learning_rate": 4.0435969627164925e-05, "loss": 0.6172, "step": 2243 }, { "epoch": 0.574464, "grad_norm": 2.390625, "learning_rate": 4.0431703779541e-05, "loss": 0.6463, "step": 2244 }, { "epoch": 0.57472, "grad_norm": 2.484375, "learning_rate": 4.042743793191707e-05, "loss": 0.5702, "step": 2245 }, { "epoch": 0.574976, "grad_norm": 2.875, "learning_rate": 4.042317208429315e-05, "loss": 0.5661, "step": 2246 }, { "epoch": 0.575232, "grad_norm": 2.578125, "learning_rate": 4.041890623666923e-05, "loss": 0.5685, "step": 2247 }, { "epoch": 0.575488, "grad_norm": 2.296875, "learning_rate": 4.04146403890453e-05, "loss": 0.5572, "step": 2248 }, { "epoch": 0.575744, "grad_norm": 2.34375, "learning_rate": 4.0410374541421384e-05, "loss": 0.5662, "step": 2249 }, { "epoch": 0.576, "grad_norm": 2.5625, "learning_rate": 4.0406108693797465e-05, "loss": 0.5978, "step": 2250 }, { "epoch": 0.576256, "grad_norm": 2.515625, "learning_rate": 4.040184284617354e-05, "loss": 0.5285, "step": 2251 }, { "epoch": 0.576512, "grad_norm": 2.4375, "learning_rate": 4.039757699854961e-05, "loss": 0.5612, "step": 2252 }, { "epoch": 0.576768, "grad_norm": 2.34375, "learning_rate": 4.039331115092569e-05, "loss": 0.6134, "step": 2253 }, { "epoch": 0.577024, "grad_norm": 2.25, "learning_rate": 4.038904530330177e-05, "loss": 0.5591, "step": 2254 }, { "epoch": 0.57728, "grad_norm": 2.53125, "learning_rate": 4.038477945567784e-05, "loss": 0.5823, "step": 2255 }, { "epoch": 0.577536, "grad_norm": 2.4375, "learning_rate": 4.0380513608053924e-05, "loss": 0.5999, "step": 2256 }, { "epoch": 0.577792, "grad_norm": 2.515625, "learning_rate": 4.037624776043e-05, "loss": 0.601, "step": 2257 }, { "epoch": 0.578048, "grad_norm": 2.453125, "learning_rate": 4.037198191280608e-05, "loss": 0.6257, "step": 2258 }, { "epoch": 0.578304, "grad_norm": 2.65625, "learning_rate": 4.0367716065182154e-05, "loss": 0.5794, "step": 2259 }, { "epoch": 0.57856, "grad_norm": 2.5, "learning_rate": 4.036345021755823e-05, "loss": 0.603, "step": 2260 }, { "epoch": 0.578816, "grad_norm": 2.484375, "learning_rate": 4.03591843699343e-05, "loss": 0.6427, "step": 2261 }, { "epoch": 0.579072, "grad_norm": 2.984375, "learning_rate": 4.035491852231039e-05, "loss": 0.5892, "step": 2262 }, { "epoch": 0.579328, "grad_norm": 2.625, "learning_rate": 4.0350652674686464e-05, "loss": 0.5939, "step": 2263 }, { "epoch": 0.579584, "grad_norm": 2.46875, "learning_rate": 4.034638682706254e-05, "loss": 0.5895, "step": 2264 }, { "epoch": 0.57984, "grad_norm": 2.703125, "learning_rate": 4.034212097943862e-05, "loss": 0.5917, "step": 2265 }, { "epoch": 0.580096, "grad_norm": 2.609375, "learning_rate": 4.0337855131814694e-05, "loss": 0.5591, "step": 2266 }, { "epoch": 0.580352, "grad_norm": 2.578125, "learning_rate": 4.033358928419077e-05, "loss": 0.5995, "step": 2267 }, { "epoch": 0.580608, "grad_norm": 2.890625, "learning_rate": 4.032932343656685e-05, "loss": 0.5721, "step": 2268 }, { "epoch": 0.580864, "grad_norm": 2.578125, "learning_rate": 4.032505758894293e-05, "loss": 0.5934, "step": 2269 }, { "epoch": 0.58112, "grad_norm": 2.5625, "learning_rate": 4.0320791741319004e-05, "loss": 0.5933, "step": 2270 }, { "epoch": 0.581376, "grad_norm": 2.53125, "learning_rate": 4.031652589369508e-05, "loss": 0.5547, "step": 2271 }, { "epoch": 0.581632, "grad_norm": 2.734375, "learning_rate": 4.031226004607115e-05, "loss": 0.5558, "step": 2272 }, { "epoch": 0.581888, "grad_norm": 2.6875, "learning_rate": 4.0307994198447234e-05, "loss": 0.6223, "step": 2273 }, { "epoch": 0.582144, "grad_norm": 2.75, "learning_rate": 4.030372835082331e-05, "loss": 0.615, "step": 2274 }, { "epoch": 0.5824, "grad_norm": 2.765625, "learning_rate": 4.029946250319939e-05, "loss": 0.5837, "step": 2275 }, { "epoch": 0.582656, "grad_norm": 2.375, "learning_rate": 4.0295196655575463e-05, "loss": 0.6035, "step": 2276 }, { "epoch": 0.582912, "grad_norm": 2.546875, "learning_rate": 4.0290930807951545e-05, "loss": 0.5751, "step": 2277 }, { "epoch": 0.583168, "grad_norm": 2.859375, "learning_rate": 4.028666496032762e-05, "loss": 0.6039, "step": 2278 }, { "epoch": 0.583424, "grad_norm": 2.53125, "learning_rate": 4.028239911270369e-05, "loss": 0.5806, "step": 2279 }, { "epoch": 0.58368, "grad_norm": 2.375, "learning_rate": 4.0278133265079774e-05, "loss": 0.596, "step": 2280 }, { "epoch": 0.583936, "grad_norm": 2.484375, "learning_rate": 4.027386741745585e-05, "loss": 0.5517, "step": 2281 }, { "epoch": 0.584192, "grad_norm": 2.640625, "learning_rate": 4.026960156983193e-05, "loss": 0.5773, "step": 2282 }, { "epoch": 0.584448, "grad_norm": 2.625, "learning_rate": 4.0265335722208004e-05, "loss": 0.554, "step": 2283 }, { "epoch": 0.584704, "grad_norm": 2.6875, "learning_rate": 4.0261069874584085e-05, "loss": 0.5729, "step": 2284 }, { "epoch": 0.58496, "grad_norm": 2.515625, "learning_rate": 4.025680402696016e-05, "loss": 0.5615, "step": 2285 }, { "epoch": 0.585216, "grad_norm": 2.78125, "learning_rate": 4.025253817933623e-05, "loss": 0.5729, "step": 2286 }, { "epoch": 0.585472, "grad_norm": 2.609375, "learning_rate": 4.0248272331712314e-05, "loss": 0.5828, "step": 2287 }, { "epoch": 0.585728, "grad_norm": 2.6875, "learning_rate": 4.0244006484088395e-05, "loss": 0.5852, "step": 2288 }, { "epoch": 0.585984, "grad_norm": 2.453125, "learning_rate": 4.023974063646447e-05, "loss": 0.6054, "step": 2289 }, { "epoch": 0.58624, "grad_norm": 2.65625, "learning_rate": 4.0235474788840544e-05, "loss": 0.5738, "step": 2290 }, { "epoch": 0.586496, "grad_norm": 2.421875, "learning_rate": 4.023120894121662e-05, "loss": 0.6111, "step": 2291 }, { "epoch": 0.586752, "grad_norm": 2.671875, "learning_rate": 4.02269430935927e-05, "loss": 0.6044, "step": 2292 }, { "epoch": 0.587008, "grad_norm": 2.65625, "learning_rate": 4.0222677245968773e-05, "loss": 0.5646, "step": 2293 }, { "epoch": 0.587264, "grad_norm": 2.578125, "learning_rate": 4.0218411398344854e-05, "loss": 0.6399, "step": 2294 }, { "epoch": 0.58752, "grad_norm": 2.328125, "learning_rate": 4.021414555072093e-05, "loss": 0.5913, "step": 2295 }, { "epoch": 0.587776, "grad_norm": 2.5, "learning_rate": 4.020987970309701e-05, "loss": 0.5603, "step": 2296 }, { "epoch": 0.588032, "grad_norm": 2.65625, "learning_rate": 4.0205613855473084e-05, "loss": 0.5816, "step": 2297 }, { "epoch": 0.588288, "grad_norm": 2.296875, "learning_rate": 4.020134800784916e-05, "loss": 0.5914, "step": 2298 }, { "epoch": 0.588544, "grad_norm": 2.59375, "learning_rate": 4.019708216022524e-05, "loss": 0.5752, "step": 2299 }, { "epoch": 0.5888, "grad_norm": 2.703125, "learning_rate": 4.0192816312601314e-05, "loss": 0.5806, "step": 2300 }, { "epoch": 0.589056, "grad_norm": 2.765625, "learning_rate": 4.0188550464977395e-05, "loss": 0.6106, "step": 2301 }, { "epoch": 0.589312, "grad_norm": 2.390625, "learning_rate": 4.018428461735347e-05, "loss": 0.6221, "step": 2302 }, { "epoch": 0.589568, "grad_norm": 2.703125, "learning_rate": 4.018001876972955e-05, "loss": 0.5618, "step": 2303 }, { "epoch": 0.589824, "grad_norm": 2.546875, "learning_rate": 4.0175752922105624e-05, "loss": 0.5765, "step": 2304 }, { "epoch": 0.59008, "grad_norm": 2.53125, "learning_rate": 4.01714870744817e-05, "loss": 0.61, "step": 2305 }, { "epoch": 0.590336, "grad_norm": 2.453125, "learning_rate": 4.016722122685778e-05, "loss": 0.6112, "step": 2306 }, { "epoch": 0.590592, "grad_norm": 2.546875, "learning_rate": 4.016295537923386e-05, "loss": 0.5508, "step": 2307 }, { "epoch": 0.590848, "grad_norm": 2.375, "learning_rate": 4.0158689531609935e-05, "loss": 0.5938, "step": 2308 }, { "epoch": 0.591104, "grad_norm": 2.5, "learning_rate": 4.015442368398601e-05, "loss": 0.5666, "step": 2309 }, { "epoch": 0.59136, "grad_norm": 2.5, "learning_rate": 4.0150157836362083e-05, "loss": 0.5925, "step": 2310 }, { "epoch": 0.591616, "grad_norm": 2.375, "learning_rate": 4.0145891988738164e-05, "loss": 0.5963, "step": 2311 }, { "epoch": 0.591872, "grad_norm": 2.421875, "learning_rate": 4.014162614111424e-05, "loss": 0.5818, "step": 2312 }, { "epoch": 0.592128, "grad_norm": 2.53125, "learning_rate": 4.013736029349032e-05, "loss": 0.6328, "step": 2313 }, { "epoch": 0.592384, "grad_norm": 2.40625, "learning_rate": 4.01330944458664e-05, "loss": 0.5508, "step": 2314 }, { "epoch": 0.59264, "grad_norm": 2.5, "learning_rate": 4.0128828598242475e-05, "loss": 0.5696, "step": 2315 }, { "epoch": 0.592896, "grad_norm": 2.546875, "learning_rate": 4.012456275061855e-05, "loss": 0.5356, "step": 2316 }, { "epoch": 0.593152, "grad_norm": 2.53125, "learning_rate": 4.0120296902994624e-05, "loss": 0.5619, "step": 2317 }, { "epoch": 0.593408, "grad_norm": 2.28125, "learning_rate": 4.0116031055370705e-05, "loss": 0.5945, "step": 2318 }, { "epoch": 0.593664, "grad_norm": 2.65625, "learning_rate": 4.011176520774678e-05, "loss": 0.5711, "step": 2319 }, { "epoch": 0.59392, "grad_norm": 2.578125, "learning_rate": 4.010749936012286e-05, "loss": 0.6119, "step": 2320 }, { "epoch": 0.594176, "grad_norm": 2.40625, "learning_rate": 4.0103233512498934e-05, "loss": 0.6085, "step": 2321 }, { "epoch": 0.594432, "grad_norm": 2.4375, "learning_rate": 4.0098967664875015e-05, "loss": 0.626, "step": 2322 }, { "epoch": 0.594688, "grad_norm": 2.34375, "learning_rate": 4.009470181725109e-05, "loss": 0.6014, "step": 2323 }, { "epoch": 0.594944, "grad_norm": 2.609375, "learning_rate": 4.0090435969627164e-05, "loss": 0.562, "step": 2324 }, { "epoch": 0.5952, "grad_norm": 2.4375, "learning_rate": 4.0086170122003245e-05, "loss": 0.6355, "step": 2325 }, { "epoch": 0.595456, "grad_norm": 2.375, "learning_rate": 4.0081904274379326e-05, "loss": 0.5481, "step": 2326 }, { "epoch": 0.595712, "grad_norm": 2.484375, "learning_rate": 4.00776384267554e-05, "loss": 0.5617, "step": 2327 }, { "epoch": 0.595968, "grad_norm": 2.265625, "learning_rate": 4.0073372579131474e-05, "loss": 0.5375, "step": 2328 }, { "epoch": 0.596224, "grad_norm": 2.4375, "learning_rate": 4.0069106731507555e-05, "loss": 0.5933, "step": 2329 }, { "epoch": 0.59648, "grad_norm": 2.484375, "learning_rate": 4.006484088388363e-05, "loss": 0.6097, "step": 2330 }, { "epoch": 0.596736, "grad_norm": 2.453125, "learning_rate": 4.0060575036259704e-05, "loss": 0.5946, "step": 2331 }, { "epoch": 0.596992, "grad_norm": 2.265625, "learning_rate": 4.0056309188635785e-05, "loss": 0.5686, "step": 2332 }, { "epoch": 0.597248, "grad_norm": 2.4375, "learning_rate": 4.0052043341011866e-05, "loss": 0.5616, "step": 2333 }, { "epoch": 0.597504, "grad_norm": 2.5, "learning_rate": 4.004777749338794e-05, "loss": 0.5715, "step": 2334 }, { "epoch": 0.59776, "grad_norm": 2.4375, "learning_rate": 4.0043511645764015e-05, "loss": 0.581, "step": 2335 }, { "epoch": 0.598016, "grad_norm": 2.59375, "learning_rate": 4.003924579814009e-05, "loss": 0.5688, "step": 2336 }, { "epoch": 0.598272, "grad_norm": 2.40625, "learning_rate": 4.003497995051617e-05, "loss": 0.5826, "step": 2337 }, { "epoch": 0.598528, "grad_norm": 2.359375, "learning_rate": 4.0030714102892244e-05, "loss": 0.5665, "step": 2338 }, { "epoch": 0.598784, "grad_norm": 2.578125, "learning_rate": 4.0026448255268325e-05, "loss": 0.6086, "step": 2339 }, { "epoch": 0.59904, "grad_norm": 2.21875, "learning_rate": 4.00221824076444e-05, "loss": 0.5762, "step": 2340 }, { "epoch": 0.599296, "grad_norm": 2.25, "learning_rate": 4.001791656002048e-05, "loss": 0.6006, "step": 2341 }, { "epoch": 0.599552, "grad_norm": 2.59375, "learning_rate": 4.0013650712396555e-05, "loss": 0.5684, "step": 2342 }, { "epoch": 0.599808, "grad_norm": 2.5, "learning_rate": 4.000938486477263e-05, "loss": 0.5838, "step": 2343 }, { "epoch": 0.600064, "grad_norm": 2.359375, "learning_rate": 4.00051190171487e-05, "loss": 0.6006, "step": 2344 }, { "epoch": 0.60032, "grad_norm": 2.390625, "learning_rate": 4.000085316952479e-05, "loss": 0.5767, "step": 2345 }, { "epoch": 0.600576, "grad_norm": 2.5, "learning_rate": 3.9996587321900865e-05, "loss": 0.5795, "step": 2346 }, { "epoch": 0.600832, "grad_norm": 2.8125, "learning_rate": 3.999232147427694e-05, "loss": 0.5873, "step": 2347 }, { "epoch": 0.601088, "grad_norm": 2.484375, "learning_rate": 3.998805562665302e-05, "loss": 0.5657, "step": 2348 }, { "epoch": 0.601344, "grad_norm": 2.421875, "learning_rate": 3.9983789779029095e-05, "loss": 0.5574, "step": 2349 }, { "epoch": 0.6016, "grad_norm": 2.625, "learning_rate": 3.997952393140517e-05, "loss": 0.5694, "step": 2350 }, { "epoch": 0.601856, "grad_norm": 2.375, "learning_rate": 3.997525808378125e-05, "loss": 0.5947, "step": 2351 }, { "epoch": 0.602112, "grad_norm": 2.421875, "learning_rate": 3.997099223615733e-05, "loss": 0.5917, "step": 2352 }, { "epoch": 0.602368, "grad_norm": 2.484375, "learning_rate": 3.9966726388533406e-05, "loss": 0.5688, "step": 2353 }, { "epoch": 0.602624, "grad_norm": 2.703125, "learning_rate": 3.996246054090948e-05, "loss": 0.5343, "step": 2354 }, { "epoch": 0.60288, "grad_norm": 2.28125, "learning_rate": 3.9958194693285554e-05, "loss": 0.6082, "step": 2355 }, { "epoch": 0.603136, "grad_norm": 2.40625, "learning_rate": 3.9953928845661635e-05, "loss": 0.5757, "step": 2356 }, { "epoch": 0.603392, "grad_norm": 2.828125, "learning_rate": 3.994966299803771e-05, "loss": 0.5885, "step": 2357 }, { "epoch": 0.603648, "grad_norm": 2.8125, "learning_rate": 3.994539715041379e-05, "loss": 0.6081, "step": 2358 }, { "epoch": 0.603904, "grad_norm": 2.5, "learning_rate": 3.9941131302789865e-05, "loss": 0.552, "step": 2359 }, { "epoch": 0.60416, "grad_norm": 2.390625, "learning_rate": 3.9936865455165946e-05, "loss": 0.5642, "step": 2360 }, { "epoch": 0.604416, "grad_norm": 2.453125, "learning_rate": 3.993259960754202e-05, "loss": 0.5694, "step": 2361 }, { "epoch": 0.604672, "grad_norm": 2.78125, "learning_rate": 3.9928333759918094e-05, "loss": 0.6015, "step": 2362 }, { "epoch": 0.604928, "grad_norm": 2.609375, "learning_rate": 3.9924067912294175e-05, "loss": 0.6011, "step": 2363 }, { "epoch": 0.605184, "grad_norm": 2.375, "learning_rate": 3.9919802064670256e-05, "loss": 0.5708, "step": 2364 }, { "epoch": 0.60544, "grad_norm": 2.328125, "learning_rate": 3.991553621704633e-05, "loss": 0.5928, "step": 2365 }, { "epoch": 0.605696, "grad_norm": 2.234375, "learning_rate": 3.9911270369422405e-05, "loss": 0.6214, "step": 2366 }, { "epoch": 0.605952, "grad_norm": 2.28125, "learning_rate": 3.9907004521798486e-05, "loss": 0.5621, "step": 2367 }, { "epoch": 0.606208, "grad_norm": 2.359375, "learning_rate": 3.990273867417456e-05, "loss": 0.5855, "step": 2368 }, { "epoch": 0.606464, "grad_norm": 2.59375, "learning_rate": 3.9898472826550635e-05, "loss": 0.6297, "step": 2369 }, { "epoch": 0.60672, "grad_norm": 2.515625, "learning_rate": 3.9894206978926716e-05, "loss": 0.5471, "step": 2370 }, { "epoch": 0.606976, "grad_norm": 2.6875, "learning_rate": 3.9889941131302797e-05, "loss": 0.5847, "step": 2371 }, { "epoch": 0.607232, "grad_norm": 2.421875, "learning_rate": 3.988567528367887e-05, "loss": 0.5798, "step": 2372 }, { "epoch": 0.607488, "grad_norm": 2.453125, "learning_rate": 3.9881409436054945e-05, "loss": 0.5847, "step": 2373 }, { "epoch": 0.607744, "grad_norm": 2.265625, "learning_rate": 3.987714358843102e-05, "loss": 0.5759, "step": 2374 }, { "epoch": 0.608, "grad_norm": 2.5, "learning_rate": 3.98728777408071e-05, "loss": 0.5776, "step": 2375 }, { "epoch": 0.608256, "grad_norm": 2.640625, "learning_rate": 3.9868611893183175e-05, "loss": 0.5692, "step": 2376 }, { "epoch": 0.608512, "grad_norm": 2.515625, "learning_rate": 3.9864346045559256e-05, "loss": 0.6022, "step": 2377 }, { "epoch": 0.608768, "grad_norm": 2.640625, "learning_rate": 3.986008019793534e-05, "loss": 0.6451, "step": 2378 }, { "epoch": 0.609024, "grad_norm": 2.59375, "learning_rate": 3.985581435031141e-05, "loss": 0.5759, "step": 2379 }, { "epoch": 0.60928, "grad_norm": 2.515625, "learning_rate": 3.9851548502687485e-05, "loss": 0.5924, "step": 2380 }, { "epoch": 0.609536, "grad_norm": 2.890625, "learning_rate": 3.984728265506356e-05, "loss": 0.57, "step": 2381 }, { "epoch": 0.609792, "grad_norm": 2.640625, "learning_rate": 3.984301680743964e-05, "loss": 0.5794, "step": 2382 }, { "epoch": 0.610048, "grad_norm": 2.421875, "learning_rate": 3.9838750959815715e-05, "loss": 0.5611, "step": 2383 }, { "epoch": 0.610304, "grad_norm": 2.4375, "learning_rate": 3.9834485112191796e-05, "loss": 0.5401, "step": 2384 }, { "epoch": 0.61056, "grad_norm": 2.453125, "learning_rate": 3.983021926456787e-05, "loss": 0.5577, "step": 2385 }, { "epoch": 0.610816, "grad_norm": 2.296875, "learning_rate": 3.982595341694395e-05, "loss": 0.6039, "step": 2386 }, { "epoch": 0.611072, "grad_norm": 2.5, "learning_rate": 3.9821687569320026e-05, "loss": 0.5836, "step": 2387 }, { "epoch": 0.611328, "grad_norm": 2.546875, "learning_rate": 3.98174217216961e-05, "loss": 0.5927, "step": 2388 }, { "epoch": 0.611584, "grad_norm": 2.46875, "learning_rate": 3.981315587407218e-05, "loss": 0.5889, "step": 2389 }, { "epoch": 0.61184, "grad_norm": 2.578125, "learning_rate": 3.980889002644826e-05, "loss": 0.5498, "step": 2390 }, { "epoch": 0.612096, "grad_norm": 2.484375, "learning_rate": 3.9804624178824336e-05, "loss": 0.5792, "step": 2391 }, { "epoch": 0.612352, "grad_norm": 2.65625, "learning_rate": 3.980035833120041e-05, "loss": 0.5445, "step": 2392 }, { "epoch": 0.612608, "grad_norm": 2.625, "learning_rate": 3.9796092483576485e-05, "loss": 0.5562, "step": 2393 }, { "epoch": 0.612864, "grad_norm": 2.40625, "learning_rate": 3.9791826635952566e-05, "loss": 0.5643, "step": 2394 }, { "epoch": 0.61312, "grad_norm": 2.65625, "learning_rate": 3.978756078832864e-05, "loss": 0.5344, "step": 2395 }, { "epoch": 0.613376, "grad_norm": 2.53125, "learning_rate": 3.978329494070472e-05, "loss": 0.5647, "step": 2396 }, { "epoch": 0.613632, "grad_norm": 2.421875, "learning_rate": 3.97790290930808e-05, "loss": 0.571, "step": 2397 }, { "epoch": 0.613888, "grad_norm": 2.484375, "learning_rate": 3.9774763245456876e-05, "loss": 0.5826, "step": 2398 }, { "epoch": 0.614144, "grad_norm": 2.4375, "learning_rate": 3.977049739783295e-05, "loss": 0.5704, "step": 2399 }, { "epoch": 0.6144, "grad_norm": 2.484375, "learning_rate": 3.9766231550209025e-05, "loss": 0.5865, "step": 2400 }, { "epoch": 0.614656, "grad_norm": 2.546875, "learning_rate": 3.9761965702585106e-05, "loss": 0.5936, "step": 2401 }, { "epoch": 0.614912, "grad_norm": 2.265625, "learning_rate": 3.975769985496118e-05, "loss": 0.5568, "step": 2402 }, { "epoch": 0.615168, "grad_norm": 2.359375, "learning_rate": 3.975343400733726e-05, "loss": 0.5584, "step": 2403 }, { "epoch": 0.615424, "grad_norm": 2.34375, "learning_rate": 3.9749168159713335e-05, "loss": 0.5422, "step": 2404 }, { "epoch": 0.61568, "grad_norm": 2.6875, "learning_rate": 3.9744902312089417e-05, "loss": 0.6044, "step": 2405 }, { "epoch": 0.615936, "grad_norm": 2.3125, "learning_rate": 3.974063646446549e-05, "loss": 0.5782, "step": 2406 }, { "epoch": 0.616192, "grad_norm": 2.375, "learning_rate": 3.9736370616841565e-05, "loss": 0.581, "step": 2407 }, { "epoch": 0.616448, "grad_norm": 2.625, "learning_rate": 3.9732104769217646e-05, "loss": 0.6102, "step": 2408 }, { "epoch": 0.616704, "grad_norm": 2.796875, "learning_rate": 3.972783892159373e-05, "loss": 0.5806, "step": 2409 }, { "epoch": 0.61696, "grad_norm": 2.625, "learning_rate": 3.97235730739698e-05, "loss": 0.5727, "step": 2410 }, { "epoch": 0.617216, "grad_norm": 2.421875, "learning_rate": 3.9719307226345876e-05, "loss": 0.5724, "step": 2411 }, { "epoch": 0.617472, "grad_norm": 2.4375, "learning_rate": 3.971504137872196e-05, "loss": 0.6031, "step": 2412 }, { "epoch": 0.617728, "grad_norm": 2.140625, "learning_rate": 3.971077553109803e-05, "loss": 0.5594, "step": 2413 }, { "epoch": 0.617984, "grad_norm": 2.375, "learning_rate": 3.9706509683474105e-05, "loss": 0.5802, "step": 2414 }, { "epoch": 0.61824, "grad_norm": 2.34375, "learning_rate": 3.9702243835850186e-05, "loss": 0.6218, "step": 2415 }, { "epoch": 0.618496, "grad_norm": 2.6875, "learning_rate": 3.969797798822627e-05, "loss": 0.6074, "step": 2416 }, { "epoch": 0.618752, "grad_norm": 2.421875, "learning_rate": 3.969371214060234e-05, "loss": 0.586, "step": 2417 }, { "epoch": 0.619008, "grad_norm": 2.234375, "learning_rate": 3.9689446292978416e-05, "loss": 0.5603, "step": 2418 }, { "epoch": 0.619264, "grad_norm": 2.4375, "learning_rate": 3.968518044535449e-05, "loss": 0.5669, "step": 2419 }, { "epoch": 0.61952, "grad_norm": 2.578125, "learning_rate": 3.968091459773057e-05, "loss": 0.5967, "step": 2420 }, { "epoch": 0.619776, "grad_norm": 2.484375, "learning_rate": 3.9676648750106645e-05, "loss": 0.574, "step": 2421 }, { "epoch": 0.620032, "grad_norm": 2.53125, "learning_rate": 3.9672382902482726e-05, "loss": 0.5563, "step": 2422 }, { "epoch": 0.620288, "grad_norm": 2.1875, "learning_rate": 3.96681170548588e-05, "loss": 0.5759, "step": 2423 }, { "epoch": 0.620544, "grad_norm": 2.359375, "learning_rate": 3.966385120723488e-05, "loss": 0.5873, "step": 2424 }, { "epoch": 0.6208, "grad_norm": 2.640625, "learning_rate": 3.9659585359610956e-05, "loss": 0.575, "step": 2425 }, { "epoch": 0.621056, "grad_norm": 2.671875, "learning_rate": 3.965531951198703e-05, "loss": 0.5576, "step": 2426 }, { "epoch": 0.621312, "grad_norm": 2.546875, "learning_rate": 3.965105366436311e-05, "loss": 0.5777, "step": 2427 }, { "epoch": 0.621568, "grad_norm": 2.703125, "learning_rate": 3.964678781673919e-05, "loss": 0.5717, "step": 2428 }, { "epoch": 0.621824, "grad_norm": 2.734375, "learning_rate": 3.964252196911527e-05, "loss": 0.5631, "step": 2429 }, { "epoch": 0.62208, "grad_norm": 2.5, "learning_rate": 3.963825612149134e-05, "loss": 0.5922, "step": 2430 }, { "epoch": 0.622336, "grad_norm": 2.71875, "learning_rate": 3.963399027386742e-05, "loss": 0.5934, "step": 2431 }, { "epoch": 0.622592, "grad_norm": 2.90625, "learning_rate": 3.9629724426243496e-05, "loss": 0.5898, "step": 2432 }, { "epoch": 0.622848, "grad_norm": 2.4375, "learning_rate": 3.962545857861957e-05, "loss": 0.6145, "step": 2433 }, { "epoch": 0.623104, "grad_norm": 2.546875, "learning_rate": 3.962119273099565e-05, "loss": 0.5681, "step": 2434 }, { "epoch": 0.62336, "grad_norm": 2.8125, "learning_rate": 3.961692688337173e-05, "loss": 0.57, "step": 2435 }, { "epoch": 0.623616, "grad_norm": 2.34375, "learning_rate": 3.961266103574781e-05, "loss": 0.6208, "step": 2436 }, { "epoch": 0.623872, "grad_norm": 2.796875, "learning_rate": 3.960839518812388e-05, "loss": 0.5651, "step": 2437 }, { "epoch": 0.624128, "grad_norm": 2.921875, "learning_rate": 3.9604129340499955e-05, "loss": 0.5914, "step": 2438 }, { "epoch": 0.624384, "grad_norm": 2.5, "learning_rate": 3.9599863492876036e-05, "loss": 0.574, "step": 2439 }, { "epoch": 0.62464, "grad_norm": 2.671875, "learning_rate": 3.959559764525211e-05, "loss": 0.5993, "step": 2440 }, { "epoch": 0.624896, "grad_norm": 2.453125, "learning_rate": 3.959133179762819e-05, "loss": 0.5833, "step": 2441 }, { "epoch": 0.625152, "grad_norm": 2.4375, "learning_rate": 3.9587065950004266e-05, "loss": 0.5714, "step": 2442 }, { "epoch": 0.625408, "grad_norm": 2.46875, "learning_rate": 3.958280010238035e-05, "loss": 0.5977, "step": 2443 }, { "epoch": 0.625664, "grad_norm": 2.578125, "learning_rate": 3.957853425475642e-05, "loss": 0.5508, "step": 2444 }, { "epoch": 0.62592, "grad_norm": 2.265625, "learning_rate": 3.9574268407132496e-05, "loss": 0.5622, "step": 2445 }, { "epoch": 0.626176, "grad_norm": 2.359375, "learning_rate": 3.957000255950858e-05, "loss": 0.5667, "step": 2446 }, { "epoch": 0.626432, "grad_norm": 2.359375, "learning_rate": 3.956573671188466e-05, "loss": 0.6362, "step": 2447 }, { "epoch": 0.626688, "grad_norm": 2.265625, "learning_rate": 3.956147086426073e-05, "loss": 0.5748, "step": 2448 }, { "epoch": 0.626944, "grad_norm": 2.5, "learning_rate": 3.9557205016636806e-05, "loss": 0.5494, "step": 2449 }, { "epoch": 0.6272, "grad_norm": 2.734375, "learning_rate": 3.955293916901289e-05, "loss": 0.569, "step": 2450 }, { "epoch": 0.627456, "grad_norm": 2.703125, "learning_rate": 3.954867332138896e-05, "loss": 0.6106, "step": 2451 }, { "epoch": 0.627712, "grad_norm": 2.59375, "learning_rate": 3.9544407473765036e-05, "loss": 0.6061, "step": 2452 }, { "epoch": 0.627968, "grad_norm": 2.5625, "learning_rate": 3.954014162614112e-05, "loss": 0.5779, "step": 2453 }, { "epoch": 0.628224, "grad_norm": 2.375, "learning_rate": 3.95358757785172e-05, "loss": 0.5283, "step": 2454 }, { "epoch": 0.62848, "grad_norm": 3.0, "learning_rate": 3.953160993089327e-05, "loss": 0.6046, "step": 2455 }, { "epoch": 0.628736, "grad_norm": 3.09375, "learning_rate": 3.9527344083269346e-05, "loss": 0.5385, "step": 2456 }, { "epoch": 0.628992, "grad_norm": 2.609375, "learning_rate": 3.952307823564542e-05, "loss": 0.596, "step": 2457 }, { "epoch": 0.629248, "grad_norm": 2.65625, "learning_rate": 3.95188123880215e-05, "loss": 0.5824, "step": 2458 }, { "epoch": 0.629504, "grad_norm": 2.578125, "learning_rate": 3.9514546540397576e-05, "loss": 0.5541, "step": 2459 }, { "epoch": 0.62976, "grad_norm": 2.484375, "learning_rate": 3.951028069277366e-05, "loss": 0.5384, "step": 2460 }, { "epoch": 0.630016, "grad_norm": 2.96875, "learning_rate": 3.950601484514974e-05, "loss": 0.563, "step": 2461 }, { "epoch": 0.630272, "grad_norm": 2.875, "learning_rate": 3.950174899752581e-05, "loss": 0.5972, "step": 2462 }, { "epoch": 0.630528, "grad_norm": 2.59375, "learning_rate": 3.9497483149901887e-05, "loss": 0.5996, "step": 2463 }, { "epoch": 0.630784, "grad_norm": 2.640625, "learning_rate": 3.949321730227796e-05, "loss": 0.574, "step": 2464 }, { "epoch": 0.63104, "grad_norm": 2.390625, "learning_rate": 3.948895145465404e-05, "loss": 0.5738, "step": 2465 }, { "epoch": 0.631296, "grad_norm": 2.59375, "learning_rate": 3.948468560703012e-05, "loss": 0.6405, "step": 2466 }, { "epoch": 0.631552, "grad_norm": 2.5625, "learning_rate": 3.94804197594062e-05, "loss": 0.5655, "step": 2467 }, { "epoch": 0.631808, "grad_norm": 2.53125, "learning_rate": 3.947615391178227e-05, "loss": 0.5661, "step": 2468 }, { "epoch": 0.632064, "grad_norm": 2.4375, "learning_rate": 3.947188806415835e-05, "loss": 0.5936, "step": 2469 }, { "epoch": 0.63232, "grad_norm": 2.34375, "learning_rate": 3.946762221653443e-05, "loss": 0.5533, "step": 2470 }, { "epoch": 0.632576, "grad_norm": 2.71875, "learning_rate": 3.94633563689105e-05, "loss": 0.5561, "step": 2471 }, { "epoch": 0.632832, "grad_norm": 2.109375, "learning_rate": 3.945909052128658e-05, "loss": 0.5744, "step": 2472 }, { "epoch": 0.633088, "grad_norm": 2.359375, "learning_rate": 3.945482467366266e-05, "loss": 0.5441, "step": 2473 }, { "epoch": 0.633344, "grad_norm": 2.15625, "learning_rate": 3.945055882603874e-05, "loss": 0.5422, "step": 2474 }, { "epoch": 0.6336, "grad_norm": 2.390625, "learning_rate": 3.944629297841481e-05, "loss": 0.5187, "step": 2475 }, { "epoch": 0.633856, "grad_norm": 2.578125, "learning_rate": 3.9442027130790886e-05, "loss": 0.5746, "step": 2476 }, { "epoch": 0.634112, "grad_norm": 2.234375, "learning_rate": 3.943776128316697e-05, "loss": 0.5723, "step": 2477 }, { "epoch": 0.634368, "grad_norm": 2.359375, "learning_rate": 3.943349543554304e-05, "loss": 0.5742, "step": 2478 }, { "epoch": 0.634624, "grad_norm": 2.421875, "learning_rate": 3.942922958791912e-05, "loss": 0.5684, "step": 2479 }, { "epoch": 0.63488, "grad_norm": 2.3125, "learning_rate": 3.94249637402952e-05, "loss": 0.5674, "step": 2480 }, { "epoch": 0.635136, "grad_norm": 2.421875, "learning_rate": 3.942069789267128e-05, "loss": 0.5992, "step": 2481 }, { "epoch": 0.635392, "grad_norm": 2.359375, "learning_rate": 3.941643204504735e-05, "loss": 0.5814, "step": 2482 }, { "epoch": 0.635648, "grad_norm": 2.4375, "learning_rate": 3.9412166197423426e-05, "loss": 0.5649, "step": 2483 }, { "epoch": 0.635904, "grad_norm": 2.28125, "learning_rate": 3.940790034979951e-05, "loss": 0.561, "step": 2484 }, { "epoch": 0.63616, "grad_norm": 2.28125, "learning_rate": 3.940363450217559e-05, "loss": 0.5557, "step": 2485 }, { "epoch": 0.636416, "grad_norm": 2.671875, "learning_rate": 3.939936865455166e-05, "loss": 0.5812, "step": 2486 }, { "epoch": 0.636672, "grad_norm": 2.484375, "learning_rate": 3.939510280692774e-05, "loss": 0.5124, "step": 2487 }, { "epoch": 0.636928, "grad_norm": 2.3125, "learning_rate": 3.939083695930382e-05, "loss": 0.5492, "step": 2488 }, { "epoch": 0.637184, "grad_norm": 2.375, "learning_rate": 3.938657111167989e-05, "loss": 0.5629, "step": 2489 }, { "epoch": 0.63744, "grad_norm": 2.75, "learning_rate": 3.9382305264055966e-05, "loss": 0.6036, "step": 2490 }, { "epoch": 0.637696, "grad_norm": 2.8125, "learning_rate": 3.937803941643205e-05, "loss": 0.5864, "step": 2491 }, { "epoch": 0.637952, "grad_norm": 2.6875, "learning_rate": 3.937377356880813e-05, "loss": 0.599, "step": 2492 }, { "epoch": 0.638208, "grad_norm": 2.84375, "learning_rate": 3.93695077211842e-05, "loss": 0.5736, "step": 2493 }, { "epoch": 0.638464, "grad_norm": 2.484375, "learning_rate": 3.936524187356028e-05, "loss": 0.6025, "step": 2494 }, { "epoch": 0.63872, "grad_norm": 2.546875, "learning_rate": 3.936097602593636e-05, "loss": 0.6074, "step": 2495 }, { "epoch": 0.638976, "grad_norm": 2.640625, "learning_rate": 3.935671017831243e-05, "loss": 0.5234, "step": 2496 }, { "epoch": 0.639232, "grad_norm": 2.515625, "learning_rate": 3.9352444330688507e-05, "loss": 0.5397, "step": 2497 }, { "epoch": 0.639488, "grad_norm": 2.765625, "learning_rate": 3.934817848306459e-05, "loss": 0.5515, "step": 2498 }, { "epoch": 0.639744, "grad_norm": 2.59375, "learning_rate": 3.934391263544067e-05, "loss": 0.5917, "step": 2499 }, { "epoch": 0.64, "grad_norm": 2.28125, "learning_rate": 3.933964678781674e-05, "loss": 0.5729, "step": 2500 }, { "epoch": 0.640256, "grad_norm": 2.578125, "learning_rate": 3.933538094019282e-05, "loss": 0.556, "step": 2501 }, { "epoch": 0.640512, "grad_norm": 2.484375, "learning_rate": 3.933111509256889e-05, "loss": 0.5665, "step": 2502 }, { "epoch": 0.640768, "grad_norm": 2.5625, "learning_rate": 3.932684924494497e-05, "loss": 0.5613, "step": 2503 }, { "epoch": 0.641024, "grad_norm": 2.53125, "learning_rate": 3.932258339732105e-05, "loss": 0.5638, "step": 2504 }, { "epoch": 0.64128, "grad_norm": 2.53125, "learning_rate": 3.931831754969713e-05, "loss": 0.5378, "step": 2505 }, { "epoch": 0.641536, "grad_norm": 2.453125, "learning_rate": 3.93140517020732e-05, "loss": 0.5552, "step": 2506 }, { "epoch": 0.641792, "grad_norm": 2.5, "learning_rate": 3.930978585444928e-05, "loss": 0.5535, "step": 2507 }, { "epoch": 0.642048, "grad_norm": 2.359375, "learning_rate": 3.930552000682536e-05, "loss": 0.5851, "step": 2508 }, { "epoch": 0.642304, "grad_norm": 2.40625, "learning_rate": 3.930125415920143e-05, "loss": 0.5435, "step": 2509 }, { "epoch": 0.64256, "grad_norm": 2.640625, "learning_rate": 3.929698831157751e-05, "loss": 0.5443, "step": 2510 }, { "epoch": 0.642816, "grad_norm": 2.375, "learning_rate": 3.9292722463953594e-05, "loss": 0.5486, "step": 2511 }, { "epoch": 0.643072, "grad_norm": 2.328125, "learning_rate": 3.928845661632967e-05, "loss": 0.5696, "step": 2512 }, { "epoch": 0.643328, "grad_norm": 2.296875, "learning_rate": 3.928419076870574e-05, "loss": 0.5887, "step": 2513 }, { "epoch": 0.643584, "grad_norm": 2.203125, "learning_rate": 3.927992492108182e-05, "loss": 0.5377, "step": 2514 }, { "epoch": 0.64384, "grad_norm": 2.46875, "learning_rate": 3.92756590734579e-05, "loss": 0.5508, "step": 2515 }, { "epoch": 0.644096, "grad_norm": 2.375, "learning_rate": 3.927139322583397e-05, "loss": 0.5959, "step": 2516 }, { "epoch": 0.644352, "grad_norm": 2.3125, "learning_rate": 3.926712737821005e-05, "loss": 0.5793, "step": 2517 }, { "epoch": 0.644608, "grad_norm": 2.1875, "learning_rate": 3.9262861530586134e-05, "loss": 0.5632, "step": 2518 }, { "epoch": 0.644864, "grad_norm": 2.328125, "learning_rate": 3.925859568296221e-05, "loss": 0.5366, "step": 2519 }, { "epoch": 0.64512, "grad_norm": 2.25, "learning_rate": 3.925432983533828e-05, "loss": 0.5618, "step": 2520 }, { "epoch": 0.645376, "grad_norm": 2.015625, "learning_rate": 3.925006398771436e-05, "loss": 0.5721, "step": 2521 }, { "epoch": 0.645632, "grad_norm": 2.234375, "learning_rate": 3.924579814009044e-05, "loss": 0.5779, "step": 2522 }, { "epoch": 0.645888, "grad_norm": 2.40625, "learning_rate": 3.924153229246651e-05, "loss": 0.577, "step": 2523 }, { "epoch": 0.646144, "grad_norm": 2.296875, "learning_rate": 3.923726644484259e-05, "loss": 0.578, "step": 2524 }, { "epoch": 0.6464, "grad_norm": 2.296875, "learning_rate": 3.923300059721867e-05, "loss": 0.577, "step": 2525 }, { "epoch": 0.646656, "grad_norm": 2.421875, "learning_rate": 3.922873474959475e-05, "loss": 0.5472, "step": 2526 }, { "epoch": 0.646912, "grad_norm": 2.609375, "learning_rate": 3.922446890197082e-05, "loss": 0.5806, "step": 2527 }, { "epoch": 0.647168, "grad_norm": 2.484375, "learning_rate": 3.92202030543469e-05, "loss": 0.5408, "step": 2528 }, { "epoch": 0.647424, "grad_norm": 2.4375, "learning_rate": 3.921593720672298e-05, "loss": 0.5714, "step": 2529 }, { "epoch": 0.64768, "grad_norm": 2.390625, "learning_rate": 3.921167135909906e-05, "loss": 0.5686, "step": 2530 }, { "epoch": 0.647936, "grad_norm": 2.640625, "learning_rate": 3.920740551147513e-05, "loss": 0.5288, "step": 2531 }, { "epoch": 0.648192, "grad_norm": 2.6875, "learning_rate": 3.920313966385121e-05, "loss": 0.593, "step": 2532 }, { "epoch": 0.648448, "grad_norm": 2.515625, "learning_rate": 3.919887381622729e-05, "loss": 0.603, "step": 2533 }, { "epoch": 0.648704, "grad_norm": 2.359375, "learning_rate": 3.919460796860336e-05, "loss": 0.5233, "step": 2534 }, { "epoch": 0.64896, "grad_norm": 2.625, "learning_rate": 3.919034212097944e-05, "loss": 0.5996, "step": 2535 }, { "epoch": 0.649216, "grad_norm": 2.5, "learning_rate": 3.918607627335552e-05, "loss": 0.5458, "step": 2536 }, { "epoch": 0.649472, "grad_norm": 2.5625, "learning_rate": 3.91818104257316e-05, "loss": 0.5562, "step": 2537 }, { "epoch": 0.649728, "grad_norm": 2.40625, "learning_rate": 3.9177544578107673e-05, "loss": 0.5483, "step": 2538 }, { "epoch": 0.649984, "grad_norm": 2.328125, "learning_rate": 3.917327873048375e-05, "loss": 0.5707, "step": 2539 }, { "epoch": 0.65024, "grad_norm": 2.328125, "learning_rate": 3.916901288285982e-05, "loss": 0.5466, "step": 2540 }, { "epoch": 0.650496, "grad_norm": 2.375, "learning_rate": 3.91647470352359e-05, "loss": 0.5501, "step": 2541 }, { "epoch": 0.650752, "grad_norm": 2.78125, "learning_rate": 3.916048118761198e-05, "loss": 0.5799, "step": 2542 }, { "epoch": 0.651008, "grad_norm": 2.328125, "learning_rate": 3.915621533998806e-05, "loss": 0.589, "step": 2543 }, { "epoch": 0.651264, "grad_norm": 2.546875, "learning_rate": 3.915194949236414e-05, "loss": 0.5815, "step": 2544 }, { "epoch": 0.65152, "grad_norm": 2.515625, "learning_rate": 3.9147683644740214e-05, "loss": 0.5385, "step": 2545 }, { "epoch": 0.651776, "grad_norm": 2.640625, "learning_rate": 3.914341779711629e-05, "loss": 0.5281, "step": 2546 }, { "epoch": 0.652032, "grad_norm": 2.734375, "learning_rate": 3.913915194949236e-05, "loss": 0.5655, "step": 2547 }, { "epoch": 0.652288, "grad_norm": 2.71875, "learning_rate": 3.913488610186844e-05, "loss": 0.5724, "step": 2548 }, { "epoch": 0.652544, "grad_norm": 2.53125, "learning_rate": 3.9130620254244524e-05, "loss": 0.5775, "step": 2549 }, { "epoch": 0.6528, "grad_norm": 2.421875, "learning_rate": 3.91263544066206e-05, "loss": 0.6236, "step": 2550 }, { "epoch": 0.653056, "grad_norm": 2.796875, "learning_rate": 3.912208855899667e-05, "loss": 0.5606, "step": 2551 }, { "epoch": 0.653312, "grad_norm": 2.484375, "learning_rate": 3.9117822711372754e-05, "loss": 0.542, "step": 2552 }, { "epoch": 0.653568, "grad_norm": 2.59375, "learning_rate": 3.911355686374883e-05, "loss": 0.5457, "step": 2553 }, { "epoch": 0.653824, "grad_norm": 2.453125, "learning_rate": 3.91092910161249e-05, "loss": 0.5807, "step": 2554 }, { "epoch": 0.65408, "grad_norm": 2.40625, "learning_rate": 3.910502516850098e-05, "loss": 0.5548, "step": 2555 }, { "epoch": 0.654336, "grad_norm": 2.71875, "learning_rate": 3.9100759320877064e-05, "loss": 0.5465, "step": 2556 }, { "epoch": 0.654592, "grad_norm": 2.4375, "learning_rate": 3.909649347325314e-05, "loss": 0.5595, "step": 2557 }, { "epoch": 0.654848, "grad_norm": 2.59375, "learning_rate": 3.909222762562921e-05, "loss": 0.5827, "step": 2558 }, { "epoch": 0.655104, "grad_norm": 2.34375, "learning_rate": 3.9087961778005294e-05, "loss": 0.5524, "step": 2559 }, { "epoch": 0.65536, "grad_norm": 3.078125, "learning_rate": 3.908369593038137e-05, "loss": 0.5642, "step": 2560 }, { "epoch": 0.655616, "grad_norm": 2.375, "learning_rate": 3.907943008275744e-05, "loss": 0.5488, "step": 2561 }, { "epoch": 0.655872, "grad_norm": 2.40625, "learning_rate": 3.9075164235133524e-05, "loss": 0.5848, "step": 2562 }, { "epoch": 0.656128, "grad_norm": 2.6875, "learning_rate": 3.9070898387509605e-05, "loss": 0.5255, "step": 2563 }, { "epoch": 0.656384, "grad_norm": 2.984375, "learning_rate": 3.906663253988568e-05, "loss": 0.5487, "step": 2564 }, { "epoch": 0.65664, "grad_norm": 2.359375, "learning_rate": 3.906236669226175e-05, "loss": 0.5677, "step": 2565 }, { "epoch": 0.656896, "grad_norm": 2.53125, "learning_rate": 3.905810084463783e-05, "loss": 0.6169, "step": 2566 }, { "epoch": 0.657152, "grad_norm": 2.375, "learning_rate": 3.905383499701391e-05, "loss": 0.5405, "step": 2567 }, { "epoch": 0.657408, "grad_norm": 2.515625, "learning_rate": 3.904956914938999e-05, "loss": 0.5692, "step": 2568 }, { "epoch": 0.657664, "grad_norm": 2.359375, "learning_rate": 3.9045303301766064e-05, "loss": 0.5147, "step": 2569 }, { "epoch": 0.65792, "grad_norm": 2.3125, "learning_rate": 3.904103745414214e-05, "loss": 0.5858, "step": 2570 }, { "epoch": 0.658176, "grad_norm": 2.421875, "learning_rate": 3.903677160651822e-05, "loss": 0.5729, "step": 2571 }, { "epoch": 0.658432, "grad_norm": 2.59375, "learning_rate": 3.903250575889429e-05, "loss": 0.5534, "step": 2572 }, { "epoch": 0.658688, "grad_norm": 2.40625, "learning_rate": 3.902823991127037e-05, "loss": 0.5665, "step": 2573 }, { "epoch": 0.658944, "grad_norm": 2.1875, "learning_rate": 3.902397406364645e-05, "loss": 0.5439, "step": 2574 }, { "epoch": 0.6592, "grad_norm": 2.4375, "learning_rate": 3.901970821602253e-05, "loss": 0.533, "step": 2575 }, { "epoch": 0.659456, "grad_norm": 2.515625, "learning_rate": 3.9015442368398604e-05, "loss": 0.5325, "step": 2576 }, { "epoch": 0.659712, "grad_norm": 2.515625, "learning_rate": 3.901117652077468e-05, "loss": 0.5634, "step": 2577 }, { "epoch": 0.659968, "grad_norm": 2.296875, "learning_rate": 3.900691067315076e-05, "loss": 0.5412, "step": 2578 }, { "epoch": 0.660224, "grad_norm": 2.484375, "learning_rate": 3.9002644825526834e-05, "loss": 0.5088, "step": 2579 }, { "epoch": 0.66048, "grad_norm": 2.53125, "learning_rate": 3.899837897790291e-05, "loss": 0.5547, "step": 2580 }, { "epoch": 0.660736, "grad_norm": 2.578125, "learning_rate": 3.899411313027899e-05, "loss": 0.5129, "step": 2581 }, { "epoch": 0.660992, "grad_norm": 2.359375, "learning_rate": 3.898984728265507e-05, "loss": 0.5353, "step": 2582 }, { "epoch": 0.661248, "grad_norm": 2.5, "learning_rate": 3.8985581435031144e-05, "loss": 0.5628, "step": 2583 }, { "epoch": 0.661504, "grad_norm": 2.28125, "learning_rate": 3.898131558740722e-05, "loss": 0.53, "step": 2584 }, { "epoch": 0.66176, "grad_norm": 2.265625, "learning_rate": 3.897704973978329e-05, "loss": 0.5547, "step": 2585 }, { "epoch": 0.662016, "grad_norm": 2.515625, "learning_rate": 3.8972783892159374e-05, "loss": 0.5442, "step": 2586 }, { "epoch": 0.662272, "grad_norm": 2.65625, "learning_rate": 3.8968518044535455e-05, "loss": 0.5847, "step": 2587 }, { "epoch": 0.662528, "grad_norm": 2.359375, "learning_rate": 3.896425219691153e-05, "loss": 0.5681, "step": 2588 }, { "epoch": 0.662784, "grad_norm": 2.578125, "learning_rate": 3.89599863492876e-05, "loss": 0.6057, "step": 2589 }, { "epoch": 0.66304, "grad_norm": 2.515625, "learning_rate": 3.8955720501663684e-05, "loss": 0.5928, "step": 2590 }, { "epoch": 0.663296, "grad_norm": 2.546875, "learning_rate": 3.895145465403976e-05, "loss": 0.535, "step": 2591 }, { "epoch": 0.663552, "grad_norm": 2.40625, "learning_rate": 3.894718880641583e-05, "loss": 0.5843, "step": 2592 }, { "epoch": 0.663808, "grad_norm": 2.40625, "learning_rate": 3.8942922958791914e-05, "loss": 0.5506, "step": 2593 }, { "epoch": 0.664064, "grad_norm": 2.515625, "learning_rate": 3.8938657111167995e-05, "loss": 0.606, "step": 2594 }, { "epoch": 0.66432, "grad_norm": 2.46875, "learning_rate": 3.893439126354407e-05, "loss": 0.5543, "step": 2595 }, { "epoch": 0.664576, "grad_norm": 2.234375, "learning_rate": 3.8930125415920143e-05, "loss": 0.5644, "step": 2596 }, { "epoch": 0.664832, "grad_norm": 2.296875, "learning_rate": 3.8925859568296225e-05, "loss": 0.5451, "step": 2597 }, { "epoch": 0.665088, "grad_norm": 2.25, "learning_rate": 3.89215937206723e-05, "loss": 0.5558, "step": 2598 }, { "epoch": 0.665344, "grad_norm": 2.484375, "learning_rate": 3.891732787304837e-05, "loss": 0.6026, "step": 2599 }, { "epoch": 0.6656, "grad_norm": 2.765625, "learning_rate": 3.8913062025424454e-05, "loss": 0.5327, "step": 2600 }, { "epoch": 0.665856, "grad_norm": 2.328125, "learning_rate": 3.8908796177800535e-05, "loss": 0.5594, "step": 2601 }, { "epoch": 0.666112, "grad_norm": 2.53125, "learning_rate": 3.890453033017661e-05, "loss": 0.5844, "step": 2602 }, { "epoch": 0.666368, "grad_norm": 2.59375, "learning_rate": 3.8900264482552684e-05, "loss": 0.5608, "step": 2603 }, { "epoch": 0.666624, "grad_norm": 2.328125, "learning_rate": 3.889599863492876e-05, "loss": 0.5766, "step": 2604 }, { "epoch": 0.66688, "grad_norm": 2.390625, "learning_rate": 3.889173278730484e-05, "loss": 0.5404, "step": 2605 }, { "epoch": 0.667136, "grad_norm": 2.359375, "learning_rate": 3.888746693968091e-05, "loss": 0.5551, "step": 2606 }, { "epoch": 0.667392, "grad_norm": 2.5, "learning_rate": 3.8883201092056994e-05, "loss": 0.5576, "step": 2607 }, { "epoch": 0.667648, "grad_norm": 2.5, "learning_rate": 3.8878935244433075e-05, "loss": 0.5799, "step": 2608 }, { "epoch": 0.667904, "grad_norm": 2.3125, "learning_rate": 3.887466939680915e-05, "loss": 0.5641, "step": 2609 }, { "epoch": 0.66816, "grad_norm": 2.515625, "learning_rate": 3.8870403549185224e-05, "loss": 0.5781, "step": 2610 }, { "epoch": 0.668416, "grad_norm": 2.75, "learning_rate": 3.88661377015613e-05, "loss": 0.5892, "step": 2611 }, { "epoch": 0.668672, "grad_norm": 2.640625, "learning_rate": 3.886187185393738e-05, "loss": 0.5648, "step": 2612 }, { "epoch": 0.668928, "grad_norm": 2.609375, "learning_rate": 3.885760600631346e-05, "loss": 0.536, "step": 2613 }, { "epoch": 0.669184, "grad_norm": 2.625, "learning_rate": 3.8853340158689534e-05, "loss": 0.5798, "step": 2614 }, { "epoch": 0.66944, "grad_norm": 2.375, "learning_rate": 3.884907431106561e-05, "loss": 0.5591, "step": 2615 }, { "epoch": 0.669696, "grad_norm": 2.421875, "learning_rate": 3.884480846344169e-05, "loss": 0.5611, "step": 2616 }, { "epoch": 0.669952, "grad_norm": 2.46875, "learning_rate": 3.8840542615817764e-05, "loss": 0.5655, "step": 2617 }, { "epoch": 0.670208, "grad_norm": 2.40625, "learning_rate": 3.883627676819384e-05, "loss": 0.5326, "step": 2618 }, { "epoch": 0.670464, "grad_norm": 2.546875, "learning_rate": 3.883201092056992e-05, "loss": 0.5154, "step": 2619 }, { "epoch": 0.67072, "grad_norm": 2.453125, "learning_rate": 3.8827745072946e-05, "loss": 0.5414, "step": 2620 }, { "epoch": 0.670976, "grad_norm": 2.359375, "learning_rate": 3.8823479225322075e-05, "loss": 0.5545, "step": 2621 }, { "epoch": 0.671232, "grad_norm": 2.453125, "learning_rate": 3.881921337769815e-05, "loss": 0.5588, "step": 2622 }, { "epoch": 0.671488, "grad_norm": 2.5625, "learning_rate": 3.881494753007422e-05, "loss": 0.5443, "step": 2623 }, { "epoch": 0.671744, "grad_norm": 2.65625, "learning_rate": 3.8810681682450304e-05, "loss": 0.569, "step": 2624 }, { "epoch": 0.672, "grad_norm": 2.421875, "learning_rate": 3.880641583482638e-05, "loss": 0.5328, "step": 2625 }, { "epoch": 0.672256, "grad_norm": 2.265625, "learning_rate": 3.880214998720246e-05, "loss": 0.5455, "step": 2626 }, { "epoch": 0.672512, "grad_norm": 2.390625, "learning_rate": 3.879788413957854e-05, "loss": 0.56, "step": 2627 }, { "epoch": 0.672768, "grad_norm": 2.390625, "learning_rate": 3.8793618291954615e-05, "loss": 0.5394, "step": 2628 }, { "epoch": 0.673024, "grad_norm": 2.421875, "learning_rate": 3.878935244433069e-05, "loss": 0.5655, "step": 2629 }, { "epoch": 0.67328, "grad_norm": 2.5625, "learning_rate": 3.8785086596706763e-05, "loss": 0.5963, "step": 2630 }, { "epoch": 0.673536, "grad_norm": 2.359375, "learning_rate": 3.8780820749082844e-05, "loss": 0.5763, "step": 2631 }, { "epoch": 0.673792, "grad_norm": 2.328125, "learning_rate": 3.8776554901458925e-05, "loss": 0.5294, "step": 2632 }, { "epoch": 0.674048, "grad_norm": 2.28125, "learning_rate": 3.8772289053835e-05, "loss": 0.5542, "step": 2633 }, { "epoch": 0.674304, "grad_norm": 2.65625, "learning_rate": 3.8768023206211074e-05, "loss": 0.5539, "step": 2634 }, { "epoch": 0.67456, "grad_norm": 2.265625, "learning_rate": 3.8763757358587155e-05, "loss": 0.5406, "step": 2635 }, { "epoch": 0.674816, "grad_norm": 2.375, "learning_rate": 3.875949151096323e-05, "loss": 0.5697, "step": 2636 }, { "epoch": 0.675072, "grad_norm": 2.28125, "learning_rate": 3.8755225663339304e-05, "loss": 0.5518, "step": 2637 }, { "epoch": 0.675328, "grad_norm": 2.21875, "learning_rate": 3.8750959815715385e-05, "loss": 0.5667, "step": 2638 }, { "epoch": 0.675584, "grad_norm": 2.34375, "learning_rate": 3.8746693968091466e-05, "loss": 0.5595, "step": 2639 }, { "epoch": 0.67584, "grad_norm": 2.453125, "learning_rate": 3.874242812046754e-05, "loss": 0.5575, "step": 2640 }, { "epoch": 0.676096, "grad_norm": 2.125, "learning_rate": 3.8738162272843614e-05, "loss": 0.5624, "step": 2641 }, { "epoch": 0.676352, "grad_norm": 2.65625, "learning_rate": 3.8733896425219695e-05, "loss": 0.5955, "step": 2642 }, { "epoch": 0.676608, "grad_norm": 2.609375, "learning_rate": 3.872963057759577e-05, "loss": 0.5803, "step": 2643 }, { "epoch": 0.676864, "grad_norm": 2.5, "learning_rate": 3.8725364729971844e-05, "loss": 0.5784, "step": 2644 }, { "epoch": 0.67712, "grad_norm": 2.453125, "learning_rate": 3.8721098882347925e-05, "loss": 0.5552, "step": 2645 }, { "epoch": 0.677376, "grad_norm": 2.671875, "learning_rate": 3.8716833034724006e-05, "loss": 0.5275, "step": 2646 }, { "epoch": 0.677632, "grad_norm": 2.671875, "learning_rate": 3.871256718710008e-05, "loss": 0.5531, "step": 2647 }, { "epoch": 0.677888, "grad_norm": 2.40625, "learning_rate": 3.8708301339476154e-05, "loss": 0.5427, "step": 2648 }, { "epoch": 0.678144, "grad_norm": 2.421875, "learning_rate": 3.870403549185223e-05, "loss": 0.5728, "step": 2649 }, { "epoch": 0.6784, "grad_norm": 2.140625, "learning_rate": 3.869976964422831e-05, "loss": 0.5677, "step": 2650 }, { "epoch": 0.678656, "grad_norm": 2.453125, "learning_rate": 3.869550379660439e-05, "loss": 0.5584, "step": 2651 }, { "epoch": 0.678912, "grad_norm": 2.515625, "learning_rate": 3.8691237948980465e-05, "loss": 0.5871, "step": 2652 }, { "epoch": 0.679168, "grad_norm": 2.34375, "learning_rate": 3.868697210135654e-05, "loss": 0.5631, "step": 2653 }, { "epoch": 0.679424, "grad_norm": 2.265625, "learning_rate": 3.868270625373262e-05, "loss": 0.5554, "step": 2654 }, { "epoch": 0.67968, "grad_norm": 2.453125, "learning_rate": 3.8678440406108695e-05, "loss": 0.5674, "step": 2655 }, { "epoch": 0.679936, "grad_norm": 2.6875, "learning_rate": 3.867417455848477e-05, "loss": 0.5771, "step": 2656 }, { "epoch": 0.680192, "grad_norm": 2.390625, "learning_rate": 3.866990871086085e-05, "loss": 0.5537, "step": 2657 }, { "epoch": 0.680448, "grad_norm": 2.546875, "learning_rate": 3.866564286323693e-05, "loss": 0.5359, "step": 2658 }, { "epoch": 0.680704, "grad_norm": 2.546875, "learning_rate": 3.8661377015613005e-05, "loss": 0.5726, "step": 2659 }, { "epoch": 0.68096, "grad_norm": 2.59375, "learning_rate": 3.865711116798908e-05, "loss": 0.5424, "step": 2660 }, { "epoch": 0.681216, "grad_norm": 2.625, "learning_rate": 3.865284532036516e-05, "loss": 0.6067, "step": 2661 }, { "epoch": 0.681472, "grad_norm": 2.3125, "learning_rate": 3.8648579472741235e-05, "loss": 0.5758, "step": 2662 }, { "epoch": 0.681728, "grad_norm": 2.515625, "learning_rate": 3.864431362511731e-05, "loss": 0.5715, "step": 2663 }, { "epoch": 0.681984, "grad_norm": 2.578125, "learning_rate": 3.864004777749339e-05, "loss": 0.5991, "step": 2664 }, { "epoch": 0.68224, "grad_norm": 2.65625, "learning_rate": 3.863578192986947e-05, "loss": 0.5697, "step": 2665 }, { "epoch": 0.682496, "grad_norm": 2.484375, "learning_rate": 3.8631516082245545e-05, "loss": 0.5528, "step": 2666 }, { "epoch": 0.682752, "grad_norm": 2.375, "learning_rate": 3.862725023462162e-05, "loss": 0.5627, "step": 2667 }, { "epoch": 0.683008, "grad_norm": 2.390625, "learning_rate": 3.8622984386997694e-05, "loss": 0.5808, "step": 2668 }, { "epoch": 0.683264, "grad_norm": 2.703125, "learning_rate": 3.8618718539373775e-05, "loss": 0.5769, "step": 2669 }, { "epoch": 0.68352, "grad_norm": 2.5, "learning_rate": 3.8614452691749856e-05, "loss": 0.5453, "step": 2670 }, { "epoch": 0.683776, "grad_norm": 2.484375, "learning_rate": 3.861018684412593e-05, "loss": 0.5572, "step": 2671 }, { "epoch": 0.684032, "grad_norm": 2.40625, "learning_rate": 3.8605920996502005e-05, "loss": 0.5214, "step": 2672 }, { "epoch": 0.684288, "grad_norm": 2.703125, "learning_rate": 3.8601655148878086e-05, "loss": 0.5201, "step": 2673 }, { "epoch": 0.684544, "grad_norm": 2.53125, "learning_rate": 3.859738930125416e-05, "loss": 0.5596, "step": 2674 }, { "epoch": 0.6848, "grad_norm": 2.34375, "learning_rate": 3.8593123453630234e-05, "loss": 0.5734, "step": 2675 }, { "epoch": 0.685056, "grad_norm": 2.359375, "learning_rate": 3.8588857606006315e-05, "loss": 0.517, "step": 2676 }, { "epoch": 0.685312, "grad_norm": 2.40625, "learning_rate": 3.8584591758382396e-05, "loss": 0.523, "step": 2677 }, { "epoch": 0.685568, "grad_norm": 2.375, "learning_rate": 3.858032591075847e-05, "loss": 0.545, "step": 2678 }, { "epoch": 0.685824, "grad_norm": 2.40625, "learning_rate": 3.8576060063134545e-05, "loss": 0.5957, "step": 2679 }, { "epoch": 0.68608, "grad_norm": 2.140625, "learning_rate": 3.8571794215510626e-05, "loss": 0.557, "step": 2680 }, { "epoch": 0.686336, "grad_norm": 2.25, "learning_rate": 3.85675283678867e-05, "loss": 0.5574, "step": 2681 }, { "epoch": 0.686592, "grad_norm": 2.265625, "learning_rate": 3.8563262520262774e-05, "loss": 0.5065, "step": 2682 }, { "epoch": 0.686848, "grad_norm": 2.515625, "learning_rate": 3.8558996672638855e-05, "loss": 0.5535, "step": 2683 }, { "epoch": 0.687104, "grad_norm": 2.4375, "learning_rate": 3.8554730825014936e-05, "loss": 0.5562, "step": 2684 }, { "epoch": 0.68736, "grad_norm": 2.46875, "learning_rate": 3.855046497739101e-05, "loss": 0.5681, "step": 2685 }, { "epoch": 0.687616, "grad_norm": 2.375, "learning_rate": 3.8546199129767085e-05, "loss": 0.5194, "step": 2686 }, { "epoch": 0.687872, "grad_norm": 2.4375, "learning_rate": 3.854193328214316e-05, "loss": 0.5282, "step": 2687 }, { "epoch": 0.688128, "grad_norm": 2.4375, "learning_rate": 3.853766743451924e-05, "loss": 0.539, "step": 2688 }, { "epoch": 0.688384, "grad_norm": 2.578125, "learning_rate": 3.853340158689532e-05, "loss": 0.5907, "step": 2689 }, { "epoch": 0.68864, "grad_norm": 2.4375, "learning_rate": 3.8529135739271396e-05, "loss": 0.5695, "step": 2690 }, { "epoch": 0.688896, "grad_norm": 2.578125, "learning_rate": 3.8524869891647477e-05, "loss": 0.5716, "step": 2691 }, { "epoch": 0.689152, "grad_norm": 2.921875, "learning_rate": 3.852060404402355e-05, "loss": 0.5135, "step": 2692 }, { "epoch": 0.689408, "grad_norm": 2.546875, "learning_rate": 3.8516338196399625e-05, "loss": 0.5088, "step": 2693 }, { "epoch": 0.689664, "grad_norm": 2.5, "learning_rate": 3.85120723487757e-05, "loss": 0.557, "step": 2694 }, { "epoch": 0.68992, "grad_norm": 2.4375, "learning_rate": 3.850780650115178e-05, "loss": 0.5859, "step": 2695 }, { "epoch": 0.690176, "grad_norm": 2.359375, "learning_rate": 3.850354065352786e-05, "loss": 0.5363, "step": 2696 }, { "epoch": 0.690432, "grad_norm": 2.53125, "learning_rate": 3.8499274805903936e-05, "loss": 0.5442, "step": 2697 }, { "epoch": 0.690688, "grad_norm": 2.796875, "learning_rate": 3.849500895828001e-05, "loss": 0.6078, "step": 2698 }, { "epoch": 0.690944, "grad_norm": 2.375, "learning_rate": 3.849074311065609e-05, "loss": 0.5701, "step": 2699 }, { "epoch": 0.6912, "grad_norm": 2.21875, "learning_rate": 3.8486477263032165e-05, "loss": 0.5565, "step": 2700 }, { "epoch": 0.691456, "grad_norm": 2.703125, "learning_rate": 3.848221141540824e-05, "loss": 0.5664, "step": 2701 }, { "epoch": 0.691712, "grad_norm": 2.84375, "learning_rate": 3.847794556778432e-05, "loss": 0.5009, "step": 2702 }, { "epoch": 0.691968, "grad_norm": 2.59375, "learning_rate": 3.84736797201604e-05, "loss": 0.5416, "step": 2703 }, { "epoch": 0.692224, "grad_norm": 2.703125, "learning_rate": 3.8469413872536476e-05, "loss": 0.5186, "step": 2704 }, { "epoch": 0.69248, "grad_norm": 2.53125, "learning_rate": 3.846514802491255e-05, "loss": 0.5438, "step": 2705 }, { "epoch": 0.692736, "grad_norm": 2.75, "learning_rate": 3.846088217728863e-05, "loss": 0.5389, "step": 2706 }, { "epoch": 0.692992, "grad_norm": 2.515625, "learning_rate": 3.8456616329664706e-05, "loss": 0.5605, "step": 2707 }, { "epoch": 0.693248, "grad_norm": 2.546875, "learning_rate": 3.845235048204078e-05, "loss": 0.5169, "step": 2708 }, { "epoch": 0.693504, "grad_norm": 2.5, "learning_rate": 3.844808463441686e-05, "loss": 0.5211, "step": 2709 }, { "epoch": 0.69376, "grad_norm": 2.46875, "learning_rate": 3.844381878679294e-05, "loss": 0.5696, "step": 2710 }, { "epoch": 0.694016, "grad_norm": 2.40625, "learning_rate": 3.8439552939169016e-05, "loss": 0.5604, "step": 2711 }, { "epoch": 0.694272, "grad_norm": 2.3125, "learning_rate": 3.843528709154509e-05, "loss": 0.5564, "step": 2712 }, { "epoch": 0.694528, "grad_norm": 2.265625, "learning_rate": 3.8431021243921165e-05, "loss": 0.53, "step": 2713 }, { "epoch": 0.694784, "grad_norm": 2.625, "learning_rate": 3.8426755396297246e-05, "loss": 0.5495, "step": 2714 }, { "epoch": 0.69504, "grad_norm": 2.421875, "learning_rate": 3.842248954867333e-05, "loss": 0.5704, "step": 2715 }, { "epoch": 0.695296, "grad_norm": 2.40625, "learning_rate": 3.84182237010494e-05, "loss": 0.5324, "step": 2716 }, { "epoch": 0.695552, "grad_norm": 2.265625, "learning_rate": 3.8413957853425475e-05, "loss": 0.5733, "step": 2717 }, { "epoch": 0.695808, "grad_norm": 2.46875, "learning_rate": 3.8409692005801556e-05, "loss": 0.5803, "step": 2718 }, { "epoch": 0.696064, "grad_norm": 2.625, "learning_rate": 3.840542615817763e-05, "loss": 0.5608, "step": 2719 }, { "epoch": 0.69632, "grad_norm": 2.28125, "learning_rate": 3.8401160310553705e-05, "loss": 0.5616, "step": 2720 }, { "epoch": 0.696576, "grad_norm": 2.28125, "learning_rate": 3.8396894462929786e-05, "loss": 0.5861, "step": 2721 }, { "epoch": 0.696832, "grad_norm": 2.53125, "learning_rate": 3.839262861530587e-05, "loss": 0.5762, "step": 2722 }, { "epoch": 0.697088, "grad_norm": 2.53125, "learning_rate": 3.838836276768194e-05, "loss": 0.563, "step": 2723 }, { "epoch": 0.697344, "grad_norm": 2.265625, "learning_rate": 3.8384096920058015e-05, "loss": 0.5496, "step": 2724 }, { "epoch": 0.6976, "grad_norm": 2.390625, "learning_rate": 3.8379831072434097e-05, "loss": 0.5398, "step": 2725 }, { "epoch": 0.697856, "grad_norm": 2.609375, "learning_rate": 3.837556522481017e-05, "loss": 0.5281, "step": 2726 }, { "epoch": 0.698112, "grad_norm": 2.453125, "learning_rate": 3.8371299377186245e-05, "loss": 0.5518, "step": 2727 }, { "epoch": 0.698368, "grad_norm": 2.5, "learning_rate": 3.8367033529562326e-05, "loss": 0.5216, "step": 2728 }, { "epoch": 0.698624, "grad_norm": 2.421875, "learning_rate": 3.836276768193841e-05, "loss": 0.5389, "step": 2729 }, { "epoch": 0.69888, "grad_norm": 2.4375, "learning_rate": 3.835850183431448e-05, "loss": 0.5334, "step": 2730 }, { "epoch": 0.699136, "grad_norm": 2.671875, "learning_rate": 3.8354235986690556e-05, "loss": 0.5516, "step": 2731 }, { "epoch": 0.699392, "grad_norm": 2.5, "learning_rate": 3.834997013906663e-05, "loss": 0.5393, "step": 2732 }, { "epoch": 0.699648, "grad_norm": 2.40625, "learning_rate": 3.834570429144271e-05, "loss": 0.5938, "step": 2733 }, { "epoch": 0.699904, "grad_norm": 2.296875, "learning_rate": 3.834143844381879e-05, "loss": 0.5479, "step": 2734 }, { "epoch": 0.70016, "grad_norm": 2.5, "learning_rate": 3.8337172596194866e-05, "loss": 0.5631, "step": 2735 }, { "epoch": 0.700416, "grad_norm": 2.484375, "learning_rate": 3.833290674857094e-05, "loss": 0.518, "step": 2736 }, { "epoch": 0.700672, "grad_norm": 2.453125, "learning_rate": 3.832864090094702e-05, "loss": 0.5305, "step": 2737 }, { "epoch": 0.700928, "grad_norm": 2.484375, "learning_rate": 3.8324375053323096e-05, "loss": 0.5547, "step": 2738 }, { "epoch": 0.701184, "grad_norm": 2.4375, "learning_rate": 3.832010920569917e-05, "loss": 0.5561, "step": 2739 }, { "epoch": 0.70144, "grad_norm": 2.328125, "learning_rate": 3.831584335807525e-05, "loss": 0.5881, "step": 2740 }, { "epoch": 0.701696, "grad_norm": 2.4375, "learning_rate": 3.831157751045133e-05, "loss": 0.5357, "step": 2741 }, { "epoch": 0.701952, "grad_norm": 2.390625, "learning_rate": 3.8307311662827406e-05, "loss": 0.509, "step": 2742 }, { "epoch": 0.702208, "grad_norm": 2.53125, "learning_rate": 3.830304581520348e-05, "loss": 0.561, "step": 2743 }, { "epoch": 0.702464, "grad_norm": 2.484375, "learning_rate": 3.829877996757956e-05, "loss": 0.5567, "step": 2744 }, { "epoch": 0.70272, "grad_norm": 2.6875, "learning_rate": 3.8294514119955636e-05, "loss": 0.5638, "step": 2745 }, { "epoch": 0.702976, "grad_norm": 2.640625, "learning_rate": 3.829024827233171e-05, "loss": 0.5518, "step": 2746 }, { "epoch": 0.703232, "grad_norm": 2.703125, "learning_rate": 3.828598242470779e-05, "loss": 0.547, "step": 2747 }, { "epoch": 0.703488, "grad_norm": 2.375, "learning_rate": 3.828171657708387e-05, "loss": 0.5131, "step": 2748 }, { "epoch": 0.703744, "grad_norm": 2.328125, "learning_rate": 3.827745072945995e-05, "loss": 0.5441, "step": 2749 }, { "epoch": 0.704, "grad_norm": 2.265625, "learning_rate": 3.827318488183602e-05, "loss": 0.5444, "step": 2750 }, { "epoch": 0.704256, "grad_norm": 2.484375, "learning_rate": 3.8268919034212095e-05, "loss": 0.5522, "step": 2751 }, { "epoch": 0.704512, "grad_norm": 2.390625, "learning_rate": 3.8264653186588176e-05, "loss": 0.5749, "step": 2752 }, { "epoch": 0.704768, "grad_norm": 2.234375, "learning_rate": 3.826038733896426e-05, "loss": 0.5497, "step": 2753 }, { "epoch": 0.705024, "grad_norm": 2.390625, "learning_rate": 3.825612149134033e-05, "loss": 0.5373, "step": 2754 }, { "epoch": 0.70528, "grad_norm": 2.234375, "learning_rate": 3.8251855643716406e-05, "loss": 0.5279, "step": 2755 }, { "epoch": 0.705536, "grad_norm": 2.53125, "learning_rate": 3.824758979609249e-05, "loss": 0.5375, "step": 2756 }, { "epoch": 0.705792, "grad_norm": 2.515625, "learning_rate": 3.824332394846856e-05, "loss": 0.5497, "step": 2757 }, { "epoch": 0.706048, "grad_norm": 2.484375, "learning_rate": 3.8239058100844635e-05, "loss": 0.5788, "step": 2758 }, { "epoch": 0.706304, "grad_norm": 2.78125, "learning_rate": 3.8234792253220716e-05, "loss": 0.5263, "step": 2759 }, { "epoch": 0.70656, "grad_norm": 2.6875, "learning_rate": 3.82305264055968e-05, "loss": 0.5083, "step": 2760 }, { "epoch": 0.706816, "grad_norm": 2.34375, "learning_rate": 3.822626055797287e-05, "loss": 0.556, "step": 2761 }, { "epoch": 0.707072, "grad_norm": 2.453125, "learning_rate": 3.8221994710348946e-05, "loss": 0.5248, "step": 2762 }, { "epoch": 0.707328, "grad_norm": 2.546875, "learning_rate": 3.821772886272503e-05, "loss": 0.556, "step": 2763 }, { "epoch": 0.707584, "grad_norm": 2.28125, "learning_rate": 3.82134630151011e-05, "loss": 0.5838, "step": 2764 }, { "epoch": 0.70784, "grad_norm": 2.453125, "learning_rate": 3.8209197167477176e-05, "loss": 0.5365, "step": 2765 }, { "epoch": 0.708096, "grad_norm": 2.1875, "learning_rate": 3.820493131985326e-05, "loss": 0.5787, "step": 2766 }, { "epoch": 0.708352, "grad_norm": 2.453125, "learning_rate": 3.820066547222934e-05, "loss": 0.5392, "step": 2767 }, { "epoch": 0.708608, "grad_norm": 2.359375, "learning_rate": 3.819639962460541e-05, "loss": 0.5517, "step": 2768 }, { "epoch": 0.708864, "grad_norm": 2.484375, "learning_rate": 3.8192133776981486e-05, "loss": 0.5327, "step": 2769 }, { "epoch": 0.70912, "grad_norm": 2.234375, "learning_rate": 3.818786792935756e-05, "loss": 0.5308, "step": 2770 }, { "epoch": 0.709376, "grad_norm": 2.5625, "learning_rate": 3.818360208173364e-05, "loss": 0.5433, "step": 2771 }, { "epoch": 0.709632, "grad_norm": 2.375, "learning_rate": 3.817933623410972e-05, "loss": 0.544, "step": 2772 }, { "epoch": 0.709888, "grad_norm": 2.421875, "learning_rate": 3.81750703864858e-05, "loss": 0.5806, "step": 2773 }, { "epoch": 0.710144, "grad_norm": 2.546875, "learning_rate": 3.817080453886188e-05, "loss": 0.5313, "step": 2774 }, { "epoch": 0.7104, "grad_norm": 2.65625, "learning_rate": 3.816653869123795e-05, "loss": 0.5508, "step": 2775 }, { "epoch": 0.710656, "grad_norm": 2.453125, "learning_rate": 3.8162272843614026e-05, "loss": 0.5521, "step": 2776 }, { "epoch": 0.710912, "grad_norm": 2.34375, "learning_rate": 3.81580069959901e-05, "loss": 0.544, "step": 2777 }, { "epoch": 0.711168, "grad_norm": 2.46875, "learning_rate": 3.815374114836618e-05, "loss": 0.5604, "step": 2778 }, { "epoch": 0.711424, "grad_norm": 2.515625, "learning_rate": 3.814947530074226e-05, "loss": 0.5566, "step": 2779 }, { "epoch": 0.71168, "grad_norm": 2.234375, "learning_rate": 3.814520945311834e-05, "loss": 0.5348, "step": 2780 }, { "epoch": 0.711936, "grad_norm": 2.28125, "learning_rate": 3.814094360549441e-05, "loss": 0.5254, "step": 2781 }, { "epoch": 0.712192, "grad_norm": 2.484375, "learning_rate": 3.813667775787049e-05, "loss": 0.5451, "step": 2782 }, { "epoch": 0.712448, "grad_norm": 2.359375, "learning_rate": 3.8132411910246567e-05, "loss": 0.5517, "step": 2783 }, { "epoch": 0.712704, "grad_norm": 2.4375, "learning_rate": 3.812814606262264e-05, "loss": 0.5487, "step": 2784 }, { "epoch": 0.71296, "grad_norm": 2.3125, "learning_rate": 3.812388021499872e-05, "loss": 0.555, "step": 2785 }, { "epoch": 0.713216, "grad_norm": 2.359375, "learning_rate": 3.81196143673748e-05, "loss": 0.5357, "step": 2786 }, { "epoch": 0.713472, "grad_norm": 2.625, "learning_rate": 3.811534851975088e-05, "loss": 0.5552, "step": 2787 }, { "epoch": 0.713728, "grad_norm": 2.46875, "learning_rate": 3.811108267212695e-05, "loss": 0.5615, "step": 2788 }, { "epoch": 0.713984, "grad_norm": 2.34375, "learning_rate": 3.810681682450303e-05, "loss": 0.5716, "step": 2789 }, { "epoch": 0.71424, "grad_norm": 2.40625, "learning_rate": 3.810255097687911e-05, "loss": 0.5502, "step": 2790 }, { "epoch": 0.714496, "grad_norm": 2.375, "learning_rate": 3.809828512925519e-05, "loss": 0.519, "step": 2791 }, { "epoch": 0.714752, "grad_norm": 2.328125, "learning_rate": 3.809401928163126e-05, "loss": 0.5742, "step": 2792 }, { "epoch": 0.715008, "grad_norm": 2.34375, "learning_rate": 3.808975343400734e-05, "loss": 0.5288, "step": 2793 }, { "epoch": 0.715264, "grad_norm": 2.46875, "learning_rate": 3.808548758638342e-05, "loss": 0.5553, "step": 2794 }, { "epoch": 0.71552, "grad_norm": 2.5625, "learning_rate": 3.808122173875949e-05, "loss": 0.5276, "step": 2795 }, { "epoch": 0.715776, "grad_norm": 2.4375, "learning_rate": 3.8076955891135566e-05, "loss": 0.5395, "step": 2796 }, { "epoch": 0.716032, "grad_norm": 2.359375, "learning_rate": 3.807269004351165e-05, "loss": 0.5869, "step": 2797 }, { "epoch": 0.716288, "grad_norm": 2.328125, "learning_rate": 3.806842419588773e-05, "loss": 0.5613, "step": 2798 }, { "epoch": 0.716544, "grad_norm": 2.296875, "learning_rate": 3.80641583482638e-05, "loss": 0.5399, "step": 2799 }, { "epoch": 0.7168, "grad_norm": 2.21875, "learning_rate": 3.8059892500639877e-05, "loss": 0.4918, "step": 2800 }, { "epoch": 0.717056, "grad_norm": 2.125, "learning_rate": 3.805562665301596e-05, "loss": 0.537, "step": 2801 }, { "epoch": 0.717312, "grad_norm": 2.21875, "learning_rate": 3.805136080539203e-05, "loss": 0.5521, "step": 2802 }, { "epoch": 0.717568, "grad_norm": 2.265625, "learning_rate": 3.8047094957768106e-05, "loss": 0.5276, "step": 2803 }, { "epoch": 0.717824, "grad_norm": 2.28125, "learning_rate": 3.804282911014419e-05, "loss": 0.5303, "step": 2804 }, { "epoch": 0.71808, "grad_norm": 2.15625, "learning_rate": 3.803856326252027e-05, "loss": 0.5887, "step": 2805 }, { "epoch": 0.718336, "grad_norm": 2.328125, "learning_rate": 3.803429741489634e-05, "loss": 0.5731, "step": 2806 }, { "epoch": 0.718592, "grad_norm": 2.15625, "learning_rate": 3.803003156727242e-05, "loss": 0.5135, "step": 2807 }, { "epoch": 0.718848, "grad_norm": 2.296875, "learning_rate": 3.80257657196485e-05, "loss": 0.5421, "step": 2808 }, { "epoch": 0.719104, "grad_norm": 2.265625, "learning_rate": 3.802149987202457e-05, "loss": 0.5319, "step": 2809 }, { "epoch": 0.71936, "grad_norm": 2.390625, "learning_rate": 3.801723402440065e-05, "loss": 0.5386, "step": 2810 }, { "epoch": 0.719616, "grad_norm": 2.0625, "learning_rate": 3.801296817677673e-05, "loss": 0.5302, "step": 2811 }, { "epoch": 0.719872, "grad_norm": 2.28125, "learning_rate": 3.800870232915281e-05, "loss": 0.4974, "step": 2812 }, { "epoch": 0.720128, "grad_norm": 2.515625, "learning_rate": 3.800443648152888e-05, "loss": 0.5309, "step": 2813 }, { "epoch": 0.720384, "grad_norm": 2.3125, "learning_rate": 3.800017063390496e-05, "loss": 0.5337, "step": 2814 }, { "epoch": 0.72064, "grad_norm": 2.21875, "learning_rate": 3.799590478628103e-05, "loss": 0.5139, "step": 2815 }, { "epoch": 0.720896, "grad_norm": 2.359375, "learning_rate": 3.799163893865711e-05, "loss": 0.5569, "step": 2816 }, { "epoch": 0.721152, "grad_norm": 2.359375, "learning_rate": 3.798737309103319e-05, "loss": 0.5555, "step": 2817 }, { "epoch": 0.721408, "grad_norm": 2.453125, "learning_rate": 3.798310724340927e-05, "loss": 0.5091, "step": 2818 }, { "epoch": 0.721664, "grad_norm": 2.3125, "learning_rate": 3.797884139578534e-05, "loss": 0.5807, "step": 2819 }, { "epoch": 0.72192, "grad_norm": 2.328125, "learning_rate": 3.797457554816142e-05, "loss": 0.5854, "step": 2820 }, { "epoch": 0.722176, "grad_norm": 2.203125, "learning_rate": 3.79703097005375e-05, "loss": 0.5496, "step": 2821 }, { "epoch": 0.722432, "grad_norm": 2.515625, "learning_rate": 3.796604385291357e-05, "loss": 0.5323, "step": 2822 }, { "epoch": 0.722688, "grad_norm": 2.234375, "learning_rate": 3.796177800528965e-05, "loss": 0.5157, "step": 2823 }, { "epoch": 0.722944, "grad_norm": 2.390625, "learning_rate": 3.7957512157665733e-05, "loss": 0.5436, "step": 2824 }, { "epoch": 0.7232, "grad_norm": 2.140625, "learning_rate": 3.795324631004181e-05, "loss": 0.5656, "step": 2825 }, { "epoch": 0.723456, "grad_norm": 2.40625, "learning_rate": 3.794898046241788e-05, "loss": 0.5624, "step": 2826 }, { "epoch": 0.723712, "grad_norm": 2.3125, "learning_rate": 3.794471461479396e-05, "loss": 0.5492, "step": 2827 }, { "epoch": 0.723968, "grad_norm": 2.140625, "learning_rate": 3.794044876717004e-05, "loss": 0.5251, "step": 2828 }, { "epoch": 0.724224, "grad_norm": 2.390625, "learning_rate": 3.793618291954611e-05, "loss": 0.5601, "step": 2829 }, { "epoch": 0.72448, "grad_norm": 2.46875, "learning_rate": 3.793191707192219e-05, "loss": 0.547, "step": 2830 }, { "epoch": 0.724736, "grad_norm": 2.59375, "learning_rate": 3.7927651224298274e-05, "loss": 0.5384, "step": 2831 }, { "epoch": 0.724992, "grad_norm": 2.1875, "learning_rate": 3.792338537667435e-05, "loss": 0.5652, "step": 2832 }, { "epoch": 0.725248, "grad_norm": 2.296875, "learning_rate": 3.791911952905042e-05, "loss": 0.5355, "step": 2833 }, { "epoch": 0.725504, "grad_norm": 2.40625, "learning_rate": 3.7914853681426496e-05, "loss": 0.537, "step": 2834 }, { "epoch": 0.72576, "grad_norm": 2.3125, "learning_rate": 3.791058783380258e-05, "loss": 0.529, "step": 2835 }, { "epoch": 0.726016, "grad_norm": 2.546875, "learning_rate": 3.790632198617866e-05, "loss": 0.5521, "step": 2836 }, { "epoch": 0.726272, "grad_norm": 2.453125, "learning_rate": 3.790205613855473e-05, "loss": 0.5354, "step": 2837 }, { "epoch": 0.726528, "grad_norm": 2.296875, "learning_rate": 3.7897790290930814e-05, "loss": 0.5463, "step": 2838 }, { "epoch": 0.726784, "grad_norm": 2.65625, "learning_rate": 3.789352444330689e-05, "loss": 0.5452, "step": 2839 }, { "epoch": 0.72704, "grad_norm": 2.828125, "learning_rate": 3.788925859568296e-05, "loss": 0.5452, "step": 2840 }, { "epoch": 0.727296, "grad_norm": 2.65625, "learning_rate": 3.788499274805904e-05, "loss": 0.5456, "step": 2841 }, { "epoch": 0.727552, "grad_norm": 2.421875, "learning_rate": 3.788072690043512e-05, "loss": 0.5454, "step": 2842 }, { "epoch": 0.727808, "grad_norm": 2.375, "learning_rate": 3.78764610528112e-05, "loss": 0.5162, "step": 2843 }, { "epoch": 0.728064, "grad_norm": 2.5625, "learning_rate": 3.787219520518727e-05, "loss": 0.5379, "step": 2844 }, { "epoch": 0.72832, "grad_norm": 2.75, "learning_rate": 3.786792935756335e-05, "loss": 0.537, "step": 2845 }, { "epoch": 0.728576, "grad_norm": 2.546875, "learning_rate": 3.786366350993943e-05, "loss": 0.5504, "step": 2846 }, { "epoch": 0.728832, "grad_norm": 2.21875, "learning_rate": 3.78593976623155e-05, "loss": 0.5682, "step": 2847 }, { "epoch": 0.729088, "grad_norm": 2.421875, "learning_rate": 3.785513181469158e-05, "loss": 0.5518, "step": 2848 }, { "epoch": 0.729344, "grad_norm": 2.5625, "learning_rate": 3.785086596706766e-05, "loss": 0.5748, "step": 2849 }, { "epoch": 0.7296, "grad_norm": 2.578125, "learning_rate": 3.784660011944374e-05, "loss": 0.5506, "step": 2850 }, { "epoch": 0.729856, "grad_norm": 2.484375, "learning_rate": 3.784233427181981e-05, "loss": 0.5639, "step": 2851 }, { "epoch": 0.730112, "grad_norm": 2.375, "learning_rate": 3.783806842419589e-05, "loss": 0.4812, "step": 2852 }, { "epoch": 0.730368, "grad_norm": 2.609375, "learning_rate": 3.783380257657196e-05, "loss": 0.5118, "step": 2853 }, { "epoch": 0.730624, "grad_norm": 2.296875, "learning_rate": 3.782953672894804e-05, "loss": 0.564, "step": 2854 }, { "epoch": 0.73088, "grad_norm": 2.453125, "learning_rate": 3.7825270881324124e-05, "loss": 0.5574, "step": 2855 }, { "epoch": 0.731136, "grad_norm": 2.453125, "learning_rate": 3.78210050337002e-05, "loss": 0.5323, "step": 2856 }, { "epoch": 0.731392, "grad_norm": 2.484375, "learning_rate": 3.781673918607628e-05, "loss": 0.5811, "step": 2857 }, { "epoch": 0.731648, "grad_norm": 2.515625, "learning_rate": 3.7812473338452353e-05, "loss": 0.5664, "step": 2858 }, { "epoch": 0.731904, "grad_norm": 2.46875, "learning_rate": 3.780820749082843e-05, "loss": 0.5163, "step": 2859 }, { "epoch": 0.73216, "grad_norm": 2.421875, "learning_rate": 3.78039416432045e-05, "loss": 0.5567, "step": 2860 }, { "epoch": 0.732416, "grad_norm": 2.328125, "learning_rate": 3.779967579558058e-05, "loss": 0.5378, "step": 2861 }, { "epoch": 0.732672, "grad_norm": 2.25, "learning_rate": 3.7795409947956664e-05, "loss": 0.5559, "step": 2862 }, { "epoch": 0.732928, "grad_norm": 2.125, "learning_rate": 3.779114410033274e-05, "loss": 0.5302, "step": 2863 }, { "epoch": 0.733184, "grad_norm": 2.265625, "learning_rate": 3.778687825270881e-05, "loss": 0.5214, "step": 2864 }, { "epoch": 0.73344, "grad_norm": 2.28125, "learning_rate": 3.7782612405084894e-05, "loss": 0.5374, "step": 2865 }, { "epoch": 0.733696, "grad_norm": 2.453125, "learning_rate": 3.777834655746097e-05, "loss": 0.5434, "step": 2866 }, { "epoch": 0.733952, "grad_norm": 2.3125, "learning_rate": 3.777408070983704e-05, "loss": 0.5168, "step": 2867 }, { "epoch": 0.734208, "grad_norm": 2.328125, "learning_rate": 3.776981486221312e-05, "loss": 0.5244, "step": 2868 }, { "epoch": 0.734464, "grad_norm": 2.171875, "learning_rate": 3.7765549014589204e-05, "loss": 0.5419, "step": 2869 }, { "epoch": 0.73472, "grad_norm": 2.3125, "learning_rate": 3.776128316696528e-05, "loss": 0.5174, "step": 2870 }, { "epoch": 0.734976, "grad_norm": 2.40625, "learning_rate": 3.775701731934135e-05, "loss": 0.5447, "step": 2871 }, { "epoch": 0.735232, "grad_norm": 2.484375, "learning_rate": 3.7752751471717434e-05, "loss": 0.5517, "step": 2872 }, { "epoch": 0.735488, "grad_norm": 2.28125, "learning_rate": 3.774848562409351e-05, "loss": 0.5788, "step": 2873 }, { "epoch": 0.735744, "grad_norm": 2.46875, "learning_rate": 3.774421977646959e-05, "loss": 0.5313, "step": 2874 }, { "epoch": 0.736, "grad_norm": 2.609375, "learning_rate": 3.773995392884566e-05, "loss": 0.5324, "step": 2875 }, { "epoch": 0.736256, "grad_norm": 2.4375, "learning_rate": 3.7735688081221744e-05, "loss": 0.5509, "step": 2876 }, { "epoch": 0.736512, "grad_norm": 2.28125, "learning_rate": 3.773142223359782e-05, "loss": 0.546, "step": 2877 }, { "epoch": 0.736768, "grad_norm": 2.421875, "learning_rate": 3.772715638597389e-05, "loss": 0.5728, "step": 2878 }, { "epoch": 0.737024, "grad_norm": 2.46875, "learning_rate": 3.772289053834997e-05, "loss": 0.531, "step": 2879 }, { "epoch": 0.73728, "grad_norm": 2.15625, "learning_rate": 3.771862469072605e-05, "loss": 0.5591, "step": 2880 }, { "epoch": 0.737536, "grad_norm": 2.4375, "learning_rate": 3.771435884310213e-05, "loss": 0.4895, "step": 2881 }, { "epoch": 0.737792, "grad_norm": 2.5, "learning_rate": 3.7710092995478204e-05, "loss": 0.5357, "step": 2882 }, { "epoch": 0.738048, "grad_norm": 2.40625, "learning_rate": 3.770582714785428e-05, "loss": 0.5246, "step": 2883 }, { "epoch": 0.738304, "grad_norm": 2.703125, "learning_rate": 3.770156130023036e-05, "loss": 0.5432, "step": 2884 }, { "epoch": 0.73856, "grad_norm": 2.390625, "learning_rate": 3.769729545260643e-05, "loss": 0.5834, "step": 2885 }, { "epoch": 0.738816, "grad_norm": 2.75, "learning_rate": 3.769302960498251e-05, "loss": 0.5425, "step": 2886 }, { "epoch": 0.739072, "grad_norm": 2.59375, "learning_rate": 3.768876375735859e-05, "loss": 0.515, "step": 2887 }, { "epoch": 0.739328, "grad_norm": 2.15625, "learning_rate": 3.768449790973467e-05, "loss": 0.5616, "step": 2888 }, { "epoch": 0.739584, "grad_norm": 2.21875, "learning_rate": 3.7680232062110744e-05, "loss": 0.5092, "step": 2889 }, { "epoch": 0.73984, "grad_norm": 2.71875, "learning_rate": 3.767596621448682e-05, "loss": 0.5422, "step": 2890 }, { "epoch": 0.740096, "grad_norm": 2.515625, "learning_rate": 3.76717003668629e-05, "loss": 0.5383, "step": 2891 }, { "epoch": 0.740352, "grad_norm": 2.515625, "learning_rate": 3.766743451923897e-05, "loss": 0.5411, "step": 2892 }, { "epoch": 0.740608, "grad_norm": 2.203125, "learning_rate": 3.7663168671615054e-05, "loss": 0.5138, "step": 2893 }, { "epoch": 0.740864, "grad_norm": 2.578125, "learning_rate": 3.765890282399113e-05, "loss": 0.5178, "step": 2894 }, { "epoch": 0.74112, "grad_norm": 2.546875, "learning_rate": 3.765463697636721e-05, "loss": 0.5458, "step": 2895 }, { "epoch": 0.741376, "grad_norm": 2.421875, "learning_rate": 3.7650371128743284e-05, "loss": 0.5176, "step": 2896 }, { "epoch": 0.741632, "grad_norm": 2.453125, "learning_rate": 3.764610528111936e-05, "loss": 0.5755, "step": 2897 }, { "epoch": 0.741888, "grad_norm": 2.390625, "learning_rate": 3.764183943349543e-05, "loss": 0.4827, "step": 2898 }, { "epoch": 0.742144, "grad_norm": 2.421875, "learning_rate": 3.7637573585871514e-05, "loss": 0.4934, "step": 2899 }, { "epoch": 0.7424, "grad_norm": 2.6875, "learning_rate": 3.7633307738247595e-05, "loss": 0.5073, "step": 2900 }, { "epoch": 0.742656, "grad_norm": 2.234375, "learning_rate": 3.762904189062367e-05, "loss": 0.471, "step": 2901 }, { "epoch": 0.742912, "grad_norm": 2.265625, "learning_rate": 3.762477604299974e-05, "loss": 0.4995, "step": 2902 }, { "epoch": 0.743168, "grad_norm": 2.515625, "learning_rate": 3.7620510195375824e-05, "loss": 0.5658, "step": 2903 }, { "epoch": 0.743424, "grad_norm": 2.421875, "learning_rate": 3.76162443477519e-05, "loss": 0.4659, "step": 2904 }, { "epoch": 0.74368, "grad_norm": 2.53125, "learning_rate": 3.761197850012797e-05, "loss": 0.5344, "step": 2905 }, { "epoch": 0.743936, "grad_norm": 2.25, "learning_rate": 3.7607712652504054e-05, "loss": 0.4914, "step": 2906 }, { "epoch": 0.744192, "grad_norm": 2.546875, "learning_rate": 3.7603446804880135e-05, "loss": 0.5313, "step": 2907 }, { "epoch": 0.744448, "grad_norm": 2.46875, "learning_rate": 3.759918095725621e-05, "loss": 0.5504, "step": 2908 }, { "epoch": 0.744704, "grad_norm": 2.4375, "learning_rate": 3.759491510963228e-05, "loss": 0.5501, "step": 2909 }, { "epoch": 0.74496, "grad_norm": 2.296875, "learning_rate": 3.7590649262008364e-05, "loss": 0.5284, "step": 2910 }, { "epoch": 0.745216, "grad_norm": 2.5, "learning_rate": 3.758638341438444e-05, "loss": 0.5348, "step": 2911 }, { "epoch": 0.745472, "grad_norm": 2.265625, "learning_rate": 3.758211756676052e-05, "loss": 0.5159, "step": 2912 }, { "epoch": 0.745728, "grad_norm": 2.5, "learning_rate": 3.7577851719136594e-05, "loss": 0.5285, "step": 2913 }, { "epoch": 0.745984, "grad_norm": 2.28125, "learning_rate": 3.7573585871512675e-05, "loss": 0.5383, "step": 2914 }, { "epoch": 0.74624, "grad_norm": 2.234375, "learning_rate": 3.756932002388875e-05, "loss": 0.5424, "step": 2915 }, { "epoch": 0.746496, "grad_norm": 2.40625, "learning_rate": 3.7565054176264823e-05, "loss": 0.5018, "step": 2916 }, { "epoch": 0.746752, "grad_norm": 2.453125, "learning_rate": 3.75607883286409e-05, "loss": 0.5241, "step": 2917 }, { "epoch": 0.747008, "grad_norm": 2.328125, "learning_rate": 3.755652248101698e-05, "loss": 0.5353, "step": 2918 }, { "epoch": 0.747264, "grad_norm": 2.546875, "learning_rate": 3.755225663339306e-05, "loss": 0.5323, "step": 2919 }, { "epoch": 0.74752, "grad_norm": 2.515625, "learning_rate": 3.7547990785769134e-05, "loss": 0.5541, "step": 2920 }, { "epoch": 0.747776, "grad_norm": 2.328125, "learning_rate": 3.7543724938145215e-05, "loss": 0.5071, "step": 2921 }, { "epoch": 0.748032, "grad_norm": 2.5625, "learning_rate": 3.753945909052129e-05, "loss": 0.5269, "step": 2922 }, { "epoch": 0.748288, "grad_norm": 2.296875, "learning_rate": 3.7535193242897364e-05, "loss": 0.5644, "step": 2923 }, { "epoch": 0.748544, "grad_norm": 2.3125, "learning_rate": 3.753092739527344e-05, "loss": 0.54, "step": 2924 }, { "epoch": 0.7488, "grad_norm": 2.421875, "learning_rate": 3.752666154764952e-05, "loss": 0.5532, "step": 2925 }, { "epoch": 0.749056, "grad_norm": 2.34375, "learning_rate": 3.75223957000256e-05, "loss": 0.5521, "step": 2926 }, { "epoch": 0.749312, "grad_norm": 2.265625, "learning_rate": 3.7518129852401674e-05, "loss": 0.5328, "step": 2927 }, { "epoch": 0.749568, "grad_norm": 2.25, "learning_rate": 3.751386400477775e-05, "loss": 0.5205, "step": 2928 }, { "epoch": 0.749824, "grad_norm": 2.21875, "learning_rate": 3.750959815715383e-05, "loss": 0.5782, "step": 2929 }, { "epoch": 0.75008, "grad_norm": 2.34375, "learning_rate": 3.7505332309529904e-05, "loss": 0.5072, "step": 2930 }, { "epoch": 0.750336, "grad_norm": 2.265625, "learning_rate": 3.750106646190598e-05, "loss": 0.5062, "step": 2931 }, { "epoch": 0.750592, "grad_norm": 2.3125, "learning_rate": 3.749680061428206e-05, "loss": 0.4968, "step": 2932 }, { "epoch": 0.750848, "grad_norm": 2.390625, "learning_rate": 3.749253476665814e-05, "loss": 0.5192, "step": 2933 }, { "epoch": 0.751104, "grad_norm": 2.328125, "learning_rate": 3.7488268919034214e-05, "loss": 0.5496, "step": 2934 }, { "epoch": 0.75136, "grad_norm": 2.421875, "learning_rate": 3.748400307141029e-05, "loss": 0.5517, "step": 2935 }, { "epoch": 0.751616, "grad_norm": 2.1875, "learning_rate": 3.747973722378637e-05, "loss": 0.5062, "step": 2936 }, { "epoch": 0.751872, "grad_norm": 2.28125, "learning_rate": 3.7475471376162444e-05, "loss": 0.5396, "step": 2937 }, { "epoch": 0.752128, "grad_norm": 2.484375, "learning_rate": 3.7471205528538525e-05, "loss": 0.4957, "step": 2938 }, { "epoch": 0.752384, "grad_norm": 2.375, "learning_rate": 3.74669396809146e-05, "loss": 0.5613, "step": 2939 }, { "epoch": 0.75264, "grad_norm": 2.25, "learning_rate": 3.746267383329068e-05, "loss": 0.5278, "step": 2940 }, { "epoch": 0.752896, "grad_norm": 2.375, "learning_rate": 3.7458407985666755e-05, "loss": 0.5645, "step": 2941 }, { "epoch": 0.753152, "grad_norm": 2.71875, "learning_rate": 3.745414213804283e-05, "loss": 0.5337, "step": 2942 }, { "epoch": 0.753408, "grad_norm": 2.3125, "learning_rate": 3.74498762904189e-05, "loss": 0.5116, "step": 2943 }, { "epoch": 0.753664, "grad_norm": 2.296875, "learning_rate": 3.7445610442794984e-05, "loss": 0.5092, "step": 2944 }, { "epoch": 0.75392, "grad_norm": 2.296875, "learning_rate": 3.7441344595171065e-05, "loss": 0.5412, "step": 2945 }, { "epoch": 0.754176, "grad_norm": 2.40625, "learning_rate": 3.743707874754714e-05, "loss": 0.5157, "step": 2946 }, { "epoch": 0.754432, "grad_norm": 2.625, "learning_rate": 3.7432812899923214e-05, "loss": 0.5158, "step": 2947 }, { "epoch": 0.754688, "grad_norm": 2.390625, "learning_rate": 3.7428547052299295e-05, "loss": 0.5337, "step": 2948 }, { "epoch": 0.754944, "grad_norm": 2.28125, "learning_rate": 3.742428120467537e-05, "loss": 0.5151, "step": 2949 }, { "epoch": 0.7552, "grad_norm": 2.328125, "learning_rate": 3.7420015357051443e-05, "loss": 0.5141, "step": 2950 }, { "epoch": 0.755456, "grad_norm": 2.34375, "learning_rate": 3.7415749509427524e-05, "loss": 0.5102, "step": 2951 }, { "epoch": 0.755712, "grad_norm": 2.671875, "learning_rate": 3.7411483661803606e-05, "loss": 0.5338, "step": 2952 }, { "epoch": 0.755968, "grad_norm": 2.734375, "learning_rate": 3.740721781417968e-05, "loss": 0.5477, "step": 2953 }, { "epoch": 0.756224, "grad_norm": 2.515625, "learning_rate": 3.7402951966555754e-05, "loss": 0.5578, "step": 2954 }, { "epoch": 0.75648, "grad_norm": 2.359375, "learning_rate": 3.7398686118931835e-05, "loss": 0.5085, "step": 2955 }, { "epoch": 0.756736, "grad_norm": 2.578125, "learning_rate": 3.739442027130791e-05, "loss": 0.61, "step": 2956 }, { "epoch": 0.756992, "grad_norm": 2.375, "learning_rate": 3.739015442368399e-05, "loss": 0.5011, "step": 2957 }, { "epoch": 0.757248, "grad_norm": 2.421875, "learning_rate": 3.7385888576060065e-05, "loss": 0.5368, "step": 2958 }, { "epoch": 0.757504, "grad_norm": 2.9375, "learning_rate": 3.7381622728436146e-05, "loss": 0.5501, "step": 2959 }, { "epoch": 0.75776, "grad_norm": 2.71875, "learning_rate": 3.737735688081222e-05, "loss": 0.5794, "step": 2960 }, { "epoch": 0.758016, "grad_norm": 2.59375, "learning_rate": 3.7373091033188294e-05, "loss": 0.561, "step": 2961 }, { "epoch": 0.758272, "grad_norm": 2.5625, "learning_rate": 3.736882518556437e-05, "loss": 0.5714, "step": 2962 }, { "epoch": 0.758528, "grad_norm": 2.421875, "learning_rate": 3.736455933794045e-05, "loss": 0.5144, "step": 2963 }, { "epoch": 0.758784, "grad_norm": 2.53125, "learning_rate": 3.736029349031653e-05, "loss": 0.5546, "step": 2964 }, { "epoch": 0.75904, "grad_norm": 2.46875, "learning_rate": 3.7356027642692605e-05, "loss": 0.5475, "step": 2965 }, { "epoch": 0.759296, "grad_norm": 2.34375, "learning_rate": 3.735176179506868e-05, "loss": 0.5825, "step": 2966 }, { "epoch": 0.759552, "grad_norm": 2.59375, "learning_rate": 3.734749594744476e-05, "loss": 0.5201, "step": 2967 }, { "epoch": 0.759808, "grad_norm": 2.515625, "learning_rate": 3.7343230099820834e-05, "loss": 0.518, "step": 2968 }, { "epoch": 0.760064, "grad_norm": 2.34375, "learning_rate": 3.733896425219691e-05, "loss": 0.5632, "step": 2969 }, { "epoch": 0.76032, "grad_norm": 2.46875, "learning_rate": 3.733469840457299e-05, "loss": 0.5396, "step": 2970 }, { "epoch": 0.760576, "grad_norm": 2.40625, "learning_rate": 3.733043255694907e-05, "loss": 0.5063, "step": 2971 }, { "epoch": 0.760832, "grad_norm": 2.28125, "learning_rate": 3.7326166709325145e-05, "loss": 0.5549, "step": 2972 }, { "epoch": 0.761088, "grad_norm": 2.53125, "learning_rate": 3.732190086170122e-05, "loss": 0.5556, "step": 2973 }, { "epoch": 0.761344, "grad_norm": 2.4375, "learning_rate": 3.73176350140773e-05, "loss": 0.5381, "step": 2974 }, { "epoch": 0.7616, "grad_norm": 2.296875, "learning_rate": 3.7313369166453375e-05, "loss": 0.5301, "step": 2975 }, { "epoch": 0.761856, "grad_norm": 2.6875, "learning_rate": 3.7309103318829456e-05, "loss": 0.5562, "step": 2976 }, { "epoch": 0.762112, "grad_norm": 2.484375, "learning_rate": 3.730483747120553e-05, "loss": 0.541, "step": 2977 }, { "epoch": 0.762368, "grad_norm": 2.65625, "learning_rate": 3.730057162358161e-05, "loss": 0.5483, "step": 2978 }, { "epoch": 0.762624, "grad_norm": 2.5625, "learning_rate": 3.7296305775957685e-05, "loss": 0.566, "step": 2979 }, { "epoch": 0.76288, "grad_norm": 2.421875, "learning_rate": 3.729203992833376e-05, "loss": 0.5233, "step": 2980 }, { "epoch": 0.763136, "grad_norm": 2.265625, "learning_rate": 3.7287774080709834e-05, "loss": 0.5305, "step": 2981 }, { "epoch": 0.763392, "grad_norm": 2.546875, "learning_rate": 3.7283508233085915e-05, "loss": 0.5209, "step": 2982 }, { "epoch": 0.763648, "grad_norm": 2.34375, "learning_rate": 3.7279242385461996e-05, "loss": 0.5226, "step": 2983 }, { "epoch": 0.763904, "grad_norm": 2.328125, "learning_rate": 3.727497653783807e-05, "loss": 0.5336, "step": 2984 }, { "epoch": 0.76416, "grad_norm": 2.515625, "learning_rate": 3.727071069021415e-05, "loss": 0.5442, "step": 2985 }, { "epoch": 0.764416, "grad_norm": 2.453125, "learning_rate": 3.7266444842590225e-05, "loss": 0.5363, "step": 2986 }, { "epoch": 0.764672, "grad_norm": 2.453125, "learning_rate": 3.72621789949663e-05, "loss": 0.5225, "step": 2987 }, { "epoch": 0.764928, "grad_norm": 2.484375, "learning_rate": 3.7257913147342374e-05, "loss": 0.5034, "step": 2988 }, { "epoch": 0.765184, "grad_norm": 2.359375, "learning_rate": 3.7253647299718455e-05, "loss": 0.5171, "step": 2989 }, { "epoch": 0.76544, "grad_norm": 2.265625, "learning_rate": 3.7249381452094536e-05, "loss": 0.5512, "step": 2990 }, { "epoch": 0.765696, "grad_norm": 2.4375, "learning_rate": 3.724511560447061e-05, "loss": 0.5298, "step": 2991 }, { "epoch": 0.765952, "grad_norm": 2.59375, "learning_rate": 3.7240849756846685e-05, "loss": 0.5619, "step": 2992 }, { "epoch": 0.766208, "grad_norm": 2.484375, "learning_rate": 3.7236583909222766e-05, "loss": 0.5227, "step": 2993 }, { "epoch": 0.766464, "grad_norm": 2.265625, "learning_rate": 3.723231806159884e-05, "loss": 0.5063, "step": 2994 }, { "epoch": 0.76672, "grad_norm": 2.234375, "learning_rate": 3.722805221397492e-05, "loss": 0.5323, "step": 2995 }, { "epoch": 0.766976, "grad_norm": 2.5, "learning_rate": 3.7223786366350995e-05, "loss": 0.5344, "step": 2996 }, { "epoch": 0.767232, "grad_norm": 2.484375, "learning_rate": 3.7219520518727076e-05, "loss": 0.5536, "step": 2997 }, { "epoch": 0.767488, "grad_norm": 2.171875, "learning_rate": 3.721525467110315e-05, "loss": 0.5457, "step": 2998 }, { "epoch": 0.767744, "grad_norm": 2.28125, "learning_rate": 3.7210988823479225e-05, "loss": 0.5666, "step": 2999 }, { "epoch": 0.768, "grad_norm": 2.09375, "learning_rate": 3.72067229758553e-05, "loss": 0.5344, "step": 3000 }, { "epoch": 0.768256, "grad_norm": 2.3125, "learning_rate": 3.720245712823138e-05, "loss": 0.4925, "step": 3001 }, { "epoch": 0.768512, "grad_norm": 2.40625, "learning_rate": 3.719819128060746e-05, "loss": 0.4982, "step": 3002 }, { "epoch": 0.768768, "grad_norm": 2.53125, "learning_rate": 3.7193925432983535e-05, "loss": 0.5292, "step": 3003 }, { "epoch": 0.769024, "grad_norm": 2.40625, "learning_rate": 3.7189659585359616e-05, "loss": 0.5397, "step": 3004 }, { "epoch": 0.76928, "grad_norm": 2.0625, "learning_rate": 3.718539373773569e-05, "loss": 0.5474, "step": 3005 }, { "epoch": 0.769536, "grad_norm": 2.203125, "learning_rate": 3.7181127890111765e-05, "loss": 0.5721, "step": 3006 }, { "epoch": 0.769792, "grad_norm": 2.25, "learning_rate": 3.717686204248784e-05, "loss": 0.5616, "step": 3007 }, { "epoch": 0.770048, "grad_norm": 2.515625, "learning_rate": 3.717259619486392e-05, "loss": 0.5374, "step": 3008 }, { "epoch": 0.770304, "grad_norm": 2.359375, "learning_rate": 3.716833034724e-05, "loss": 0.5552, "step": 3009 }, { "epoch": 0.77056, "grad_norm": 2.15625, "learning_rate": 3.7164064499616076e-05, "loss": 0.5405, "step": 3010 }, { "epoch": 0.770816, "grad_norm": 2.265625, "learning_rate": 3.715979865199215e-05, "loss": 0.5579, "step": 3011 }, { "epoch": 0.771072, "grad_norm": 2.359375, "learning_rate": 3.715553280436823e-05, "loss": 0.5503, "step": 3012 }, { "epoch": 0.771328, "grad_norm": 2.703125, "learning_rate": 3.7151266956744305e-05, "loss": 0.535, "step": 3013 }, { "epoch": 0.771584, "grad_norm": 2.53125, "learning_rate": 3.7147001109120386e-05, "loss": 0.5133, "step": 3014 }, { "epoch": 0.77184, "grad_norm": 2.546875, "learning_rate": 3.714273526149646e-05, "loss": 0.5158, "step": 3015 }, { "epoch": 0.772096, "grad_norm": 2.4375, "learning_rate": 3.713846941387254e-05, "loss": 0.499, "step": 3016 }, { "epoch": 0.772352, "grad_norm": 2.40625, "learning_rate": 3.7134203566248616e-05, "loss": 0.5143, "step": 3017 }, { "epoch": 0.772608, "grad_norm": 2.34375, "learning_rate": 3.712993771862469e-05, "loss": 0.5513, "step": 3018 }, { "epoch": 0.772864, "grad_norm": 2.21875, "learning_rate": 3.712567187100077e-05, "loss": 0.5255, "step": 3019 }, { "epoch": 0.77312, "grad_norm": 2.359375, "learning_rate": 3.7121406023376845e-05, "loss": 0.5089, "step": 3020 }, { "epoch": 0.773376, "grad_norm": 2.59375, "learning_rate": 3.7117140175752926e-05, "loss": 0.5586, "step": 3021 }, { "epoch": 0.773632, "grad_norm": 2.3125, "learning_rate": 3.7112874328129e-05, "loss": 0.5278, "step": 3022 }, { "epoch": 0.773888, "grad_norm": 2.578125, "learning_rate": 3.710860848050508e-05, "loss": 0.5193, "step": 3023 }, { "epoch": 0.774144, "grad_norm": 2.421875, "learning_rate": 3.7104342632881156e-05, "loss": 0.5213, "step": 3024 }, { "epoch": 0.7744, "grad_norm": 2.671875, "learning_rate": 3.710007678525723e-05, "loss": 0.5165, "step": 3025 }, { "epoch": 0.774656, "grad_norm": 2.375, "learning_rate": 3.7095810937633304e-05, "loss": 0.5044, "step": 3026 }, { "epoch": 0.774912, "grad_norm": 2.390625, "learning_rate": 3.7091545090009386e-05, "loss": 0.5625, "step": 3027 }, { "epoch": 0.775168, "grad_norm": 2.25, "learning_rate": 3.7087279242385467e-05, "loss": 0.5367, "step": 3028 }, { "epoch": 0.775424, "grad_norm": 2.625, "learning_rate": 3.708301339476154e-05, "loss": 0.5435, "step": 3029 }, { "epoch": 0.77568, "grad_norm": 2.75, "learning_rate": 3.7078747547137615e-05, "loss": 0.5228, "step": 3030 }, { "epoch": 0.775936, "grad_norm": 2.453125, "learning_rate": 3.7074481699513696e-05, "loss": 0.5156, "step": 3031 }, { "epoch": 0.776192, "grad_norm": 2.296875, "learning_rate": 3.707021585188977e-05, "loss": 0.5861, "step": 3032 }, { "epoch": 0.776448, "grad_norm": 2.421875, "learning_rate": 3.7065950004265845e-05, "loss": 0.5742, "step": 3033 }, { "epoch": 0.776704, "grad_norm": 2.4375, "learning_rate": 3.706168415664193e-05, "loss": 0.5489, "step": 3034 }, { "epoch": 0.77696, "grad_norm": 2.609375, "learning_rate": 3.705741830901801e-05, "loss": 0.538, "step": 3035 }, { "epoch": 0.777216, "grad_norm": 2.390625, "learning_rate": 3.705315246139408e-05, "loss": 0.5495, "step": 3036 }, { "epoch": 0.777472, "grad_norm": 2.421875, "learning_rate": 3.7048886613770155e-05, "loss": 0.542, "step": 3037 }, { "epoch": 0.777728, "grad_norm": 2.390625, "learning_rate": 3.7044620766146236e-05, "loss": 0.5385, "step": 3038 }, { "epoch": 0.777984, "grad_norm": 2.5, "learning_rate": 3.704035491852231e-05, "loss": 0.5691, "step": 3039 }, { "epoch": 0.77824, "grad_norm": 2.359375, "learning_rate": 3.703608907089839e-05, "loss": 0.5186, "step": 3040 }, { "epoch": 0.778496, "grad_norm": 2.3125, "learning_rate": 3.7031823223274466e-05, "loss": 0.5552, "step": 3041 }, { "epoch": 0.778752, "grad_norm": 2.25, "learning_rate": 3.702755737565055e-05, "loss": 0.5314, "step": 3042 }, { "epoch": 0.779008, "grad_norm": 2.296875, "learning_rate": 3.702329152802662e-05, "loss": 0.4712, "step": 3043 }, { "epoch": 0.779264, "grad_norm": 2.15625, "learning_rate": 3.7019025680402696e-05, "loss": 0.4886, "step": 3044 }, { "epoch": 0.77952, "grad_norm": 2.296875, "learning_rate": 3.701475983277877e-05, "loss": 0.5254, "step": 3045 }, { "epoch": 0.779776, "grad_norm": 2.53125, "learning_rate": 3.701049398515485e-05, "loss": 0.4959, "step": 3046 }, { "epoch": 0.780032, "grad_norm": 2.5, "learning_rate": 3.700622813753093e-05, "loss": 0.5091, "step": 3047 }, { "epoch": 0.780288, "grad_norm": 2.21875, "learning_rate": 3.7001962289907006e-05, "loss": 0.4703, "step": 3048 }, { "epoch": 0.780544, "grad_norm": 2.109375, "learning_rate": 3.699769644228308e-05, "loss": 0.5388, "step": 3049 }, { "epoch": 0.7808, "grad_norm": 2.09375, "learning_rate": 3.699343059465916e-05, "loss": 0.5241, "step": 3050 }, { "epoch": 0.781056, "grad_norm": 2.40625, "learning_rate": 3.6989164747035236e-05, "loss": 0.5328, "step": 3051 }, { "epoch": 0.781312, "grad_norm": 2.546875, "learning_rate": 3.698489889941131e-05, "loss": 0.4998, "step": 3052 }, { "epoch": 0.781568, "grad_norm": 2.390625, "learning_rate": 3.69806330517874e-05, "loss": 0.5023, "step": 3053 }, { "epoch": 0.781824, "grad_norm": 2.109375, "learning_rate": 3.697636720416347e-05, "loss": 0.5295, "step": 3054 }, { "epoch": 0.78208, "grad_norm": 2.359375, "learning_rate": 3.6972101356539546e-05, "loss": 0.5629, "step": 3055 }, { "epoch": 0.782336, "grad_norm": 2.328125, "learning_rate": 3.696783550891562e-05, "loss": 0.5331, "step": 3056 }, { "epoch": 0.782592, "grad_norm": 2.328125, "learning_rate": 3.69635696612917e-05, "loss": 0.5342, "step": 3057 }, { "epoch": 0.782848, "grad_norm": 2.25, "learning_rate": 3.6959303813667776e-05, "loss": 0.5812, "step": 3058 }, { "epoch": 0.783104, "grad_norm": 2.140625, "learning_rate": 3.695503796604386e-05, "loss": 0.5166, "step": 3059 }, { "epoch": 0.78336, "grad_norm": 2.359375, "learning_rate": 3.695077211841993e-05, "loss": 0.526, "step": 3060 }, { "epoch": 0.783616, "grad_norm": 2.375, "learning_rate": 3.694650627079601e-05, "loss": 0.526, "step": 3061 }, { "epoch": 0.783872, "grad_norm": 2.53125, "learning_rate": 3.6942240423172087e-05, "loss": 0.5242, "step": 3062 }, { "epoch": 0.784128, "grad_norm": 2.296875, "learning_rate": 3.693797457554816e-05, "loss": 0.5494, "step": 3063 }, { "epoch": 0.784384, "grad_norm": 2.40625, "learning_rate": 3.6933708727924235e-05, "loss": 0.5128, "step": 3064 }, { "epoch": 0.78464, "grad_norm": 2.34375, "learning_rate": 3.6929442880300316e-05, "loss": 0.5177, "step": 3065 }, { "epoch": 0.784896, "grad_norm": 2.59375, "learning_rate": 3.69251770326764e-05, "loss": 0.5656, "step": 3066 }, { "epoch": 0.785152, "grad_norm": 2.515625, "learning_rate": 3.692091118505247e-05, "loss": 0.5562, "step": 3067 }, { "epoch": 0.785408, "grad_norm": 2.296875, "learning_rate": 3.691664533742855e-05, "loss": 0.5143, "step": 3068 }, { "epoch": 0.785664, "grad_norm": 2.703125, "learning_rate": 3.691237948980463e-05, "loss": 0.5163, "step": 3069 }, { "epoch": 0.78592, "grad_norm": 2.546875, "learning_rate": 3.69081136421807e-05, "loss": 0.5244, "step": 3070 }, { "epoch": 0.786176, "grad_norm": 2.5625, "learning_rate": 3.6903847794556775e-05, "loss": 0.5577, "step": 3071 }, { "epoch": 0.786432, "grad_norm": 2.4375, "learning_rate": 3.6899581946932856e-05, "loss": 0.5188, "step": 3072 }, { "epoch": 0.786688, "grad_norm": 2.5, "learning_rate": 3.689531609930894e-05, "loss": 0.5137, "step": 3073 }, { "epoch": 0.786944, "grad_norm": 2.28125, "learning_rate": 3.689105025168501e-05, "loss": 0.5191, "step": 3074 }, { "epoch": 0.7872, "grad_norm": 2.546875, "learning_rate": 3.6886784404061086e-05, "loss": 0.5663, "step": 3075 }, { "epoch": 0.787456, "grad_norm": 2.625, "learning_rate": 3.688251855643717e-05, "loss": 0.567, "step": 3076 }, { "epoch": 0.787712, "grad_norm": 2.421875, "learning_rate": 3.687825270881324e-05, "loss": 0.5453, "step": 3077 }, { "epoch": 0.787968, "grad_norm": 2.40625, "learning_rate": 3.687398686118932e-05, "loss": 0.5114, "step": 3078 }, { "epoch": 0.788224, "grad_norm": 2.375, "learning_rate": 3.6869721013565396e-05, "loss": 0.5343, "step": 3079 }, { "epoch": 0.78848, "grad_norm": 2.609375, "learning_rate": 3.686545516594148e-05, "loss": 0.5537, "step": 3080 }, { "epoch": 0.788736, "grad_norm": 2.421875, "learning_rate": 3.686118931831755e-05, "loss": 0.552, "step": 3081 }, { "epoch": 0.788992, "grad_norm": 2.3125, "learning_rate": 3.6856923470693626e-05, "loss": 0.4963, "step": 3082 }, { "epoch": 0.789248, "grad_norm": 2.5625, "learning_rate": 3.685265762306971e-05, "loss": 0.5494, "step": 3083 }, { "epoch": 0.789504, "grad_norm": 2.328125, "learning_rate": 3.684839177544578e-05, "loss": 0.5183, "step": 3084 }, { "epoch": 0.78976, "grad_norm": 2.265625, "learning_rate": 3.684412592782186e-05, "loss": 0.4899, "step": 3085 }, { "epoch": 0.790016, "grad_norm": 2.421875, "learning_rate": 3.683986008019794e-05, "loss": 0.545, "step": 3086 }, { "epoch": 0.790272, "grad_norm": 2.46875, "learning_rate": 3.683559423257402e-05, "loss": 0.5656, "step": 3087 }, { "epoch": 0.790528, "grad_norm": 2.453125, "learning_rate": 3.683132838495009e-05, "loss": 0.5002, "step": 3088 }, { "epoch": 0.790784, "grad_norm": 2.265625, "learning_rate": 3.6827062537326166e-05, "loss": 0.5374, "step": 3089 }, { "epoch": 0.79104, "grad_norm": 2.28125, "learning_rate": 3.682279668970224e-05, "loss": 0.4902, "step": 3090 }, { "epoch": 0.791296, "grad_norm": 2.359375, "learning_rate": 3.681853084207832e-05, "loss": 0.5234, "step": 3091 }, { "epoch": 0.791552, "grad_norm": 2.328125, "learning_rate": 3.68142649944544e-05, "loss": 0.5003, "step": 3092 }, { "epoch": 0.791808, "grad_norm": 2.125, "learning_rate": 3.680999914683048e-05, "loss": 0.5273, "step": 3093 }, { "epoch": 0.792064, "grad_norm": 2.328125, "learning_rate": 3.680573329920655e-05, "loss": 0.5342, "step": 3094 }, { "epoch": 0.79232, "grad_norm": 2.40625, "learning_rate": 3.680146745158263e-05, "loss": 0.5125, "step": 3095 }, { "epoch": 0.792576, "grad_norm": 2.484375, "learning_rate": 3.6797201603958706e-05, "loss": 0.5615, "step": 3096 }, { "epoch": 0.792832, "grad_norm": 2.078125, "learning_rate": 3.679293575633479e-05, "loss": 0.4868, "step": 3097 }, { "epoch": 0.793088, "grad_norm": 2.46875, "learning_rate": 3.678866990871086e-05, "loss": 0.5128, "step": 3098 }, { "epoch": 0.793344, "grad_norm": 2.40625, "learning_rate": 3.678440406108694e-05, "loss": 0.5118, "step": 3099 }, { "epoch": 0.7936, "grad_norm": 2.65625, "learning_rate": 3.678013821346302e-05, "loss": 0.561, "step": 3100 }, { "epoch": 0.793856, "grad_norm": 2.390625, "learning_rate": 3.677587236583909e-05, "loss": 0.4941, "step": 3101 }, { "epoch": 0.794112, "grad_norm": 2.703125, "learning_rate": 3.677160651821517e-05, "loss": 0.5454, "step": 3102 }, { "epoch": 0.794368, "grad_norm": 2.296875, "learning_rate": 3.676734067059125e-05, "loss": 0.505, "step": 3103 }, { "epoch": 0.794624, "grad_norm": 2.328125, "learning_rate": 3.676307482296733e-05, "loss": 0.5039, "step": 3104 }, { "epoch": 0.79488, "grad_norm": 2.3125, "learning_rate": 3.67588089753434e-05, "loss": 0.5656, "step": 3105 }, { "epoch": 0.795136, "grad_norm": 2.515625, "learning_rate": 3.675454312771948e-05, "loss": 0.4813, "step": 3106 }, { "epoch": 0.795392, "grad_norm": 2.34375, "learning_rate": 3.675027728009556e-05, "loss": 0.471, "step": 3107 }, { "epoch": 0.795648, "grad_norm": 2.546875, "learning_rate": 3.674601143247163e-05, "loss": 0.5699, "step": 3108 }, { "epoch": 0.795904, "grad_norm": 2.375, "learning_rate": 3.6741745584847706e-05, "loss": 0.5182, "step": 3109 }, { "epoch": 0.79616, "grad_norm": 2.515625, "learning_rate": 3.673747973722379e-05, "loss": 0.5166, "step": 3110 }, { "epoch": 0.796416, "grad_norm": 2.390625, "learning_rate": 3.673321388959987e-05, "loss": 0.5042, "step": 3111 }, { "epoch": 0.796672, "grad_norm": 2.109375, "learning_rate": 3.672894804197594e-05, "loss": 0.537, "step": 3112 }, { "epoch": 0.796928, "grad_norm": 2.46875, "learning_rate": 3.6724682194352016e-05, "loss": 0.5008, "step": 3113 }, { "epoch": 0.797184, "grad_norm": 2.5625, "learning_rate": 3.67204163467281e-05, "loss": 0.5311, "step": 3114 }, { "epoch": 0.79744, "grad_norm": 2.3125, "learning_rate": 3.671615049910417e-05, "loss": 0.5458, "step": 3115 }, { "epoch": 0.797696, "grad_norm": 2.34375, "learning_rate": 3.671188465148025e-05, "loss": 0.5197, "step": 3116 }, { "epoch": 0.797952, "grad_norm": 2.296875, "learning_rate": 3.6707618803856334e-05, "loss": 0.4992, "step": 3117 }, { "epoch": 0.798208, "grad_norm": 2.671875, "learning_rate": 3.670335295623241e-05, "loss": 0.5448, "step": 3118 }, { "epoch": 0.798464, "grad_norm": 2.359375, "learning_rate": 3.669908710860848e-05, "loss": 0.4939, "step": 3119 }, { "epoch": 0.79872, "grad_norm": 2.171875, "learning_rate": 3.6694821260984557e-05, "loss": 0.5039, "step": 3120 }, { "epoch": 0.798976, "grad_norm": 2.34375, "learning_rate": 3.669055541336064e-05, "loss": 0.5228, "step": 3121 }, { "epoch": 0.799232, "grad_norm": 2.578125, "learning_rate": 3.668628956573671e-05, "loss": 0.5093, "step": 3122 }, { "epoch": 0.799488, "grad_norm": 2.40625, "learning_rate": 3.668202371811279e-05, "loss": 0.5227, "step": 3123 }, { "epoch": 0.799744, "grad_norm": 2.296875, "learning_rate": 3.667775787048887e-05, "loss": 0.5115, "step": 3124 }, { "epoch": 0.8, "grad_norm": 2.421875, "learning_rate": 3.667349202286495e-05, "loss": 0.5152, "step": 3125 }, { "epoch": 0.800256, "grad_norm": 2.421875, "learning_rate": 3.666922617524102e-05, "loss": 0.5024, "step": 3126 }, { "epoch": 0.800512, "grad_norm": 2.421875, "learning_rate": 3.66649603276171e-05, "loss": 0.508, "step": 3127 }, { "epoch": 0.800768, "grad_norm": 2.46875, "learning_rate": 3.666069447999317e-05, "loss": 0.508, "step": 3128 }, { "epoch": 0.801024, "grad_norm": 2.46875, "learning_rate": 3.665642863236925e-05, "loss": 0.5357, "step": 3129 }, { "epoch": 0.80128, "grad_norm": 2.46875, "learning_rate": 3.665216278474533e-05, "loss": 0.5192, "step": 3130 }, { "epoch": 0.801536, "grad_norm": 2.359375, "learning_rate": 3.664789693712141e-05, "loss": 0.5078, "step": 3131 }, { "epoch": 0.801792, "grad_norm": 2.4375, "learning_rate": 3.664363108949748e-05, "loss": 0.5018, "step": 3132 }, { "epoch": 0.802048, "grad_norm": 2.265625, "learning_rate": 3.663936524187356e-05, "loss": 0.4882, "step": 3133 }, { "epoch": 0.802304, "grad_norm": 2.484375, "learning_rate": 3.663509939424964e-05, "loss": 0.5413, "step": 3134 }, { "epoch": 0.80256, "grad_norm": 2.828125, "learning_rate": 3.663083354662572e-05, "loss": 0.5564, "step": 3135 }, { "epoch": 0.802816, "grad_norm": 2.5625, "learning_rate": 3.66265676990018e-05, "loss": 0.5226, "step": 3136 }, { "epoch": 0.803072, "grad_norm": 2.59375, "learning_rate": 3.662230185137787e-05, "loss": 0.5545, "step": 3137 }, { "epoch": 0.803328, "grad_norm": 2.3125, "learning_rate": 3.661803600375395e-05, "loss": 0.4932, "step": 3138 }, { "epoch": 0.803584, "grad_norm": 2.296875, "learning_rate": 3.661377015613002e-05, "loss": 0.514, "step": 3139 }, { "epoch": 0.80384, "grad_norm": 2.5, "learning_rate": 3.66095043085061e-05, "loss": 0.5145, "step": 3140 }, { "epoch": 0.804096, "grad_norm": 2.5625, "learning_rate": 3.660523846088218e-05, "loss": 0.5436, "step": 3141 }, { "epoch": 0.804352, "grad_norm": 2.46875, "learning_rate": 3.660097261325826e-05, "loss": 0.5173, "step": 3142 }, { "epoch": 0.804608, "grad_norm": 2.578125, "learning_rate": 3.659670676563433e-05, "loss": 0.4887, "step": 3143 }, { "epoch": 0.804864, "grad_norm": 2.453125, "learning_rate": 3.6592440918010414e-05, "loss": 0.5351, "step": 3144 }, { "epoch": 0.80512, "grad_norm": 2.421875, "learning_rate": 3.658817507038649e-05, "loss": 0.5322, "step": 3145 }, { "epoch": 0.805376, "grad_norm": 2.359375, "learning_rate": 3.658390922276256e-05, "loss": 0.572, "step": 3146 }, { "epoch": 0.805632, "grad_norm": 2.34375, "learning_rate": 3.6579643375138636e-05, "loss": 0.5419, "step": 3147 }, { "epoch": 0.805888, "grad_norm": 2.125, "learning_rate": 3.657537752751472e-05, "loss": 0.5155, "step": 3148 }, { "epoch": 0.806144, "grad_norm": 2.609375, "learning_rate": 3.65711116798908e-05, "loss": 0.5285, "step": 3149 }, { "epoch": 0.8064, "grad_norm": 2.515625, "learning_rate": 3.656684583226687e-05, "loss": 0.5409, "step": 3150 }, { "epoch": 0.806656, "grad_norm": 2.453125, "learning_rate": 3.6562579984642954e-05, "loss": 0.5419, "step": 3151 }, { "epoch": 0.806912, "grad_norm": 2.5, "learning_rate": 3.655831413701903e-05, "loss": 0.4725, "step": 3152 }, { "epoch": 0.807168, "grad_norm": 2.296875, "learning_rate": 3.65540482893951e-05, "loss": 0.4857, "step": 3153 }, { "epoch": 0.807424, "grad_norm": 2.421875, "learning_rate": 3.6549782441771177e-05, "loss": 0.5326, "step": 3154 }, { "epoch": 0.80768, "grad_norm": 2.453125, "learning_rate": 3.6545516594147264e-05, "loss": 0.5191, "step": 3155 }, { "epoch": 0.807936, "grad_norm": 2.421875, "learning_rate": 3.654125074652334e-05, "loss": 0.5251, "step": 3156 }, { "epoch": 0.808192, "grad_norm": 2.453125, "learning_rate": 3.653698489889941e-05, "loss": 0.5262, "step": 3157 }, { "epoch": 0.808448, "grad_norm": 2.625, "learning_rate": 3.653271905127549e-05, "loss": 0.5574, "step": 3158 }, { "epoch": 0.808704, "grad_norm": 2.15625, "learning_rate": 3.652845320365157e-05, "loss": 0.5646, "step": 3159 }, { "epoch": 0.80896, "grad_norm": 2.15625, "learning_rate": 3.652418735602764e-05, "loss": 0.5281, "step": 3160 }, { "epoch": 0.809216, "grad_norm": 2.234375, "learning_rate": 3.6519921508403723e-05, "loss": 0.5052, "step": 3161 }, { "epoch": 0.809472, "grad_norm": 2.421875, "learning_rate": 3.65156556607798e-05, "loss": 0.549, "step": 3162 }, { "epoch": 0.809728, "grad_norm": 2.203125, "learning_rate": 3.651138981315588e-05, "loss": 0.5274, "step": 3163 }, { "epoch": 0.809984, "grad_norm": 2.265625, "learning_rate": 3.650712396553195e-05, "loss": 0.534, "step": 3164 }, { "epoch": 0.81024, "grad_norm": 2.15625, "learning_rate": 3.650285811790803e-05, "loss": 0.5166, "step": 3165 }, { "epoch": 0.810496, "grad_norm": 2.53125, "learning_rate": 3.649859227028411e-05, "loss": 0.5334, "step": 3166 }, { "epoch": 0.810752, "grad_norm": 2.359375, "learning_rate": 3.649432642266018e-05, "loss": 0.4908, "step": 3167 }, { "epoch": 0.811008, "grad_norm": 2.15625, "learning_rate": 3.6490060575036264e-05, "loss": 0.4974, "step": 3168 }, { "epoch": 0.811264, "grad_norm": 2.1875, "learning_rate": 3.648579472741234e-05, "loss": 0.556, "step": 3169 }, { "epoch": 0.81152, "grad_norm": 2.265625, "learning_rate": 3.648152887978842e-05, "loss": 0.5199, "step": 3170 }, { "epoch": 0.811776, "grad_norm": 2.375, "learning_rate": 3.647726303216449e-05, "loss": 0.5424, "step": 3171 }, { "epoch": 0.812032, "grad_norm": 2.375, "learning_rate": 3.647299718454057e-05, "loss": 0.5, "step": 3172 }, { "epoch": 0.812288, "grad_norm": 2.28125, "learning_rate": 3.646873133691664e-05, "loss": 0.5596, "step": 3173 }, { "epoch": 0.812544, "grad_norm": 2.265625, "learning_rate": 3.646446548929273e-05, "loss": 0.5542, "step": 3174 }, { "epoch": 0.8128, "grad_norm": 2.1875, "learning_rate": 3.6460199641668804e-05, "loss": 0.4932, "step": 3175 }, { "epoch": 0.813056, "grad_norm": 2.625, "learning_rate": 3.645593379404488e-05, "loss": 0.4987, "step": 3176 }, { "epoch": 0.813312, "grad_norm": 2.578125, "learning_rate": 3.645166794642095e-05, "loss": 0.5472, "step": 3177 }, { "epoch": 0.813568, "grad_norm": 2.421875, "learning_rate": 3.6447402098797033e-05, "loss": 0.519, "step": 3178 }, { "epoch": 0.813824, "grad_norm": 2.4375, "learning_rate": 3.644313625117311e-05, "loss": 0.5376, "step": 3179 }, { "epoch": 0.81408, "grad_norm": 2.296875, "learning_rate": 3.643887040354919e-05, "loss": 0.5448, "step": 3180 }, { "epoch": 0.814336, "grad_norm": 2.59375, "learning_rate": 3.643460455592526e-05, "loss": 0.5016, "step": 3181 }, { "epoch": 0.814592, "grad_norm": 2.734375, "learning_rate": 3.6430338708301344e-05, "loss": 0.5084, "step": 3182 }, { "epoch": 0.814848, "grad_norm": 2.359375, "learning_rate": 3.642607286067742e-05, "loss": 0.5076, "step": 3183 }, { "epoch": 0.815104, "grad_norm": 2.296875, "learning_rate": 3.642180701305349e-05, "loss": 0.5318, "step": 3184 }, { "epoch": 0.81536, "grad_norm": 2.578125, "learning_rate": 3.6417541165429574e-05, "loss": 0.4926, "step": 3185 }, { "epoch": 0.815616, "grad_norm": 2.421875, "learning_rate": 3.641327531780565e-05, "loss": 0.5302, "step": 3186 }, { "epoch": 0.815872, "grad_norm": 2.375, "learning_rate": 3.640900947018173e-05, "loss": 0.5269, "step": 3187 }, { "epoch": 0.816128, "grad_norm": 2.328125, "learning_rate": 3.64047436225578e-05, "loss": 0.521, "step": 3188 }, { "epoch": 0.816384, "grad_norm": 2.53125, "learning_rate": 3.6400477774933884e-05, "loss": 0.4853, "step": 3189 }, { "epoch": 0.81664, "grad_norm": 2.5, "learning_rate": 3.639621192730996e-05, "loss": 0.5001, "step": 3190 }, { "epoch": 0.816896, "grad_norm": 2.265625, "learning_rate": 3.639194607968603e-05, "loss": 0.5155, "step": 3191 }, { "epoch": 0.817152, "grad_norm": 2.5625, "learning_rate": 3.638768023206211e-05, "loss": 0.4789, "step": 3192 }, { "epoch": 0.817408, "grad_norm": 2.609375, "learning_rate": 3.638341438443819e-05, "loss": 0.4888, "step": 3193 }, { "epoch": 0.817664, "grad_norm": 2.5, "learning_rate": 3.637914853681427e-05, "loss": 0.508, "step": 3194 }, { "epoch": 0.81792, "grad_norm": 2.140625, "learning_rate": 3.6374882689190343e-05, "loss": 0.512, "step": 3195 }, { "epoch": 0.818176, "grad_norm": 2.453125, "learning_rate": 3.637061684156642e-05, "loss": 0.5128, "step": 3196 }, { "epoch": 0.818432, "grad_norm": 2.765625, "learning_rate": 3.63663509939425e-05, "loss": 0.5033, "step": 3197 }, { "epoch": 0.818688, "grad_norm": 2.34375, "learning_rate": 3.636208514631857e-05, "loss": 0.5383, "step": 3198 }, { "epoch": 0.818944, "grad_norm": 2.265625, "learning_rate": 3.6357819298694654e-05, "loss": 0.4588, "step": 3199 }, { "epoch": 0.8192, "grad_norm": 2.40625, "learning_rate": 3.6353553451070735e-05, "loss": 0.5546, "step": 3200 }, { "epoch": 0.819456, "grad_norm": 2.25, "learning_rate": 3.634928760344681e-05, "loss": 0.5386, "step": 3201 }, { "epoch": 0.819712, "grad_norm": 2.4375, "learning_rate": 3.6345021755822884e-05, "loss": 0.5208, "step": 3202 }, { "epoch": 0.819968, "grad_norm": 2.4375, "learning_rate": 3.634075590819896e-05, "loss": 0.4903, "step": 3203 }, { "epoch": 0.820224, "grad_norm": 2.390625, "learning_rate": 3.633649006057504e-05, "loss": 0.5255, "step": 3204 }, { "epoch": 0.82048, "grad_norm": 2.40625, "learning_rate": 3.633222421295111e-05, "loss": 0.5464, "step": 3205 }, { "epoch": 0.820736, "grad_norm": 2.46875, "learning_rate": 3.6327958365327194e-05, "loss": 0.5459, "step": 3206 }, { "epoch": 0.820992, "grad_norm": 2.390625, "learning_rate": 3.632369251770327e-05, "loss": 0.498, "step": 3207 }, { "epoch": 0.821248, "grad_norm": 2.25, "learning_rate": 3.631942667007935e-05, "loss": 0.5221, "step": 3208 }, { "epoch": 0.821504, "grad_norm": 2.296875, "learning_rate": 3.6315160822455424e-05, "loss": 0.5172, "step": 3209 }, { "epoch": 0.82176, "grad_norm": 2.453125, "learning_rate": 3.63108949748315e-05, "loss": 0.5504, "step": 3210 }, { "epoch": 0.822016, "grad_norm": 2.34375, "learning_rate": 3.630662912720757e-05, "loss": 0.5149, "step": 3211 }, { "epoch": 0.822272, "grad_norm": 2.140625, "learning_rate": 3.630236327958365e-05, "loss": 0.5661, "step": 3212 }, { "epoch": 0.822528, "grad_norm": 2.25, "learning_rate": 3.6298097431959734e-05, "loss": 0.502, "step": 3213 }, { "epoch": 0.822784, "grad_norm": 2.40625, "learning_rate": 3.629383158433581e-05, "loss": 0.5271, "step": 3214 }, { "epoch": 0.82304, "grad_norm": 2.28125, "learning_rate": 3.628956573671189e-05, "loss": 0.5333, "step": 3215 }, { "epoch": 0.823296, "grad_norm": 2.328125, "learning_rate": 3.6285299889087964e-05, "loss": 0.5079, "step": 3216 }, { "epoch": 0.823552, "grad_norm": 2.453125, "learning_rate": 3.628103404146404e-05, "loss": 0.5382, "step": 3217 }, { "epoch": 0.823808, "grad_norm": 2.515625, "learning_rate": 3.627676819384012e-05, "loss": 0.5225, "step": 3218 }, { "epoch": 0.824064, "grad_norm": 2.578125, "learning_rate": 3.62725023462162e-05, "loss": 0.5213, "step": 3219 }, { "epoch": 0.82432, "grad_norm": 2.328125, "learning_rate": 3.6268236498592275e-05, "loss": 0.5091, "step": 3220 }, { "epoch": 0.824576, "grad_norm": 2.34375, "learning_rate": 3.626397065096835e-05, "loss": 0.5115, "step": 3221 }, { "epoch": 0.824832, "grad_norm": 2.5, "learning_rate": 3.625970480334442e-05, "loss": 0.5762, "step": 3222 }, { "epoch": 0.825088, "grad_norm": 2.5625, "learning_rate": 3.6255438955720504e-05, "loss": 0.5312, "step": 3223 }, { "epoch": 0.825344, "grad_norm": 2.390625, "learning_rate": 3.625117310809658e-05, "loss": 0.5396, "step": 3224 }, { "epoch": 0.8256, "grad_norm": 2.28125, "learning_rate": 3.624690726047266e-05, "loss": 0.5059, "step": 3225 }, { "epoch": 0.825856, "grad_norm": 2.4375, "learning_rate": 3.6242641412848734e-05, "loss": 0.5365, "step": 3226 }, { "epoch": 0.826112, "grad_norm": 2.609375, "learning_rate": 3.6238375565224815e-05, "loss": 0.5622, "step": 3227 }, { "epoch": 0.826368, "grad_norm": 2.578125, "learning_rate": 3.623410971760089e-05, "loss": 0.4901, "step": 3228 }, { "epoch": 0.826624, "grad_norm": 2.21875, "learning_rate": 3.622984386997696e-05, "loss": 0.5287, "step": 3229 }, { "epoch": 0.82688, "grad_norm": 2.515625, "learning_rate": 3.622557802235304e-05, "loss": 0.5562, "step": 3230 }, { "epoch": 0.827136, "grad_norm": 2.390625, "learning_rate": 3.622131217472912e-05, "loss": 0.5282, "step": 3231 }, { "epoch": 0.827392, "grad_norm": 2.34375, "learning_rate": 3.62170463271052e-05, "loss": 0.5203, "step": 3232 }, { "epoch": 0.827648, "grad_norm": 2.453125, "learning_rate": 3.6212780479481274e-05, "loss": 0.5188, "step": 3233 }, { "epoch": 0.827904, "grad_norm": 2.359375, "learning_rate": 3.6208514631857355e-05, "loss": 0.5045, "step": 3234 }, { "epoch": 0.82816, "grad_norm": 2.359375, "learning_rate": 3.620424878423343e-05, "loss": 0.4993, "step": 3235 }, { "epoch": 0.828416, "grad_norm": 2.59375, "learning_rate": 3.6199982936609504e-05, "loss": 0.5, "step": 3236 }, { "epoch": 0.828672, "grad_norm": 2.296875, "learning_rate": 3.6195717088985585e-05, "loss": 0.5153, "step": 3237 }, { "epoch": 0.828928, "grad_norm": 2.359375, "learning_rate": 3.6191451241361666e-05, "loss": 0.5303, "step": 3238 }, { "epoch": 0.829184, "grad_norm": 2.453125, "learning_rate": 3.618718539373774e-05, "loss": 0.4991, "step": 3239 }, { "epoch": 0.82944, "grad_norm": 2.265625, "learning_rate": 3.6182919546113814e-05, "loss": 0.5162, "step": 3240 }, { "epoch": 0.829696, "grad_norm": 2.390625, "learning_rate": 3.617865369848989e-05, "loss": 0.5003, "step": 3241 }, { "epoch": 0.829952, "grad_norm": 2.609375, "learning_rate": 3.617438785086597e-05, "loss": 0.5033, "step": 3242 }, { "epoch": 0.830208, "grad_norm": 2.515625, "learning_rate": 3.6170122003242044e-05, "loss": 0.514, "step": 3243 }, { "epoch": 0.830464, "grad_norm": 2.5, "learning_rate": 3.6165856155618125e-05, "loss": 0.519, "step": 3244 }, { "epoch": 0.83072, "grad_norm": 2.21875, "learning_rate": 3.61615903079942e-05, "loss": 0.5061, "step": 3245 }, { "epoch": 0.830976, "grad_norm": 2.0625, "learning_rate": 3.615732446037028e-05, "loss": 0.4705, "step": 3246 }, { "epoch": 0.831232, "grad_norm": 2.5, "learning_rate": 3.6153058612746354e-05, "loss": 0.5185, "step": 3247 }, { "epoch": 0.831488, "grad_norm": 2.375, "learning_rate": 3.614879276512243e-05, "loss": 0.5235, "step": 3248 }, { "epoch": 0.831744, "grad_norm": 2.265625, "learning_rate": 3.614452691749851e-05, "loss": 0.4797, "step": 3249 }, { "epoch": 0.832, "grad_norm": 2.515625, "learning_rate": 3.6140261069874584e-05, "loss": 0.4912, "step": 3250 }, { "epoch": 0.832256, "grad_norm": 2.40625, "learning_rate": 3.6135995222250665e-05, "loss": 0.5157, "step": 3251 }, { "epoch": 0.832512, "grad_norm": 2.328125, "learning_rate": 3.613172937462674e-05, "loss": 0.4849, "step": 3252 }, { "epoch": 0.832768, "grad_norm": 2.4375, "learning_rate": 3.612746352700282e-05, "loss": 0.5299, "step": 3253 }, { "epoch": 0.833024, "grad_norm": 2.609375, "learning_rate": 3.6123197679378895e-05, "loss": 0.5633, "step": 3254 }, { "epoch": 0.83328, "grad_norm": 2.734375, "learning_rate": 3.611893183175497e-05, "loss": 0.5237, "step": 3255 }, { "epoch": 0.833536, "grad_norm": 2.265625, "learning_rate": 3.611466598413104e-05, "loss": 0.5038, "step": 3256 }, { "epoch": 0.833792, "grad_norm": 2.453125, "learning_rate": 3.611040013650713e-05, "loss": 0.4861, "step": 3257 }, { "epoch": 0.834048, "grad_norm": 2.5625, "learning_rate": 3.6106134288883205e-05, "loss": 0.5098, "step": 3258 }, { "epoch": 0.834304, "grad_norm": 2.4375, "learning_rate": 3.610186844125928e-05, "loss": 0.5353, "step": 3259 }, { "epoch": 0.83456, "grad_norm": 2.46875, "learning_rate": 3.6097602593635354e-05, "loss": 0.5144, "step": 3260 }, { "epoch": 0.834816, "grad_norm": 2.5, "learning_rate": 3.6093336746011435e-05, "loss": 0.4892, "step": 3261 }, { "epoch": 0.835072, "grad_norm": 2.4375, "learning_rate": 3.608907089838751e-05, "loss": 0.4935, "step": 3262 }, { "epoch": 0.835328, "grad_norm": 2.234375, "learning_rate": 3.608480505076359e-05, "loss": 0.5022, "step": 3263 }, { "epoch": 0.835584, "grad_norm": 2.140625, "learning_rate": 3.608053920313967e-05, "loss": 0.5367, "step": 3264 }, { "epoch": 0.83584, "grad_norm": 2.5, "learning_rate": 3.6076273355515745e-05, "loss": 0.5409, "step": 3265 }, { "epoch": 0.836096, "grad_norm": 2.53125, "learning_rate": 3.607200750789182e-05, "loss": 0.49, "step": 3266 }, { "epoch": 0.836352, "grad_norm": 2.265625, "learning_rate": 3.6067741660267894e-05, "loss": 0.4932, "step": 3267 }, { "epoch": 0.836608, "grad_norm": 2.25, "learning_rate": 3.6063475812643975e-05, "loss": 0.5147, "step": 3268 }, { "epoch": 0.836864, "grad_norm": 2.1875, "learning_rate": 3.605920996502005e-05, "loss": 0.5222, "step": 3269 }, { "epoch": 0.83712, "grad_norm": 2.40625, "learning_rate": 3.605494411739613e-05, "loss": 0.4957, "step": 3270 }, { "epoch": 0.837376, "grad_norm": 2.359375, "learning_rate": 3.6050678269772204e-05, "loss": 0.5026, "step": 3271 }, { "epoch": 0.837632, "grad_norm": 2.140625, "learning_rate": 3.6046412422148286e-05, "loss": 0.5184, "step": 3272 }, { "epoch": 0.837888, "grad_norm": 2.078125, "learning_rate": 3.604214657452436e-05, "loss": 0.5764, "step": 3273 }, { "epoch": 0.838144, "grad_norm": 2.09375, "learning_rate": 3.6037880726900434e-05, "loss": 0.5068, "step": 3274 }, { "epoch": 0.8384, "grad_norm": 2.09375, "learning_rate": 3.603361487927651e-05, "loss": 0.5143, "step": 3275 }, { "epoch": 0.838656, "grad_norm": 2.359375, "learning_rate": 3.6029349031652596e-05, "loss": 0.527, "step": 3276 }, { "epoch": 0.838912, "grad_norm": 2.234375, "learning_rate": 3.602508318402867e-05, "loss": 0.5135, "step": 3277 }, { "epoch": 0.839168, "grad_norm": 2.265625, "learning_rate": 3.6020817336404745e-05, "loss": 0.4837, "step": 3278 }, { "epoch": 0.839424, "grad_norm": 2.296875, "learning_rate": 3.601655148878082e-05, "loss": 0.5135, "step": 3279 }, { "epoch": 0.83968, "grad_norm": 2.390625, "learning_rate": 3.60122856411569e-05, "loss": 0.5367, "step": 3280 }, { "epoch": 0.839936, "grad_norm": 2.296875, "learning_rate": 3.6008019793532974e-05, "loss": 0.4927, "step": 3281 }, { "epoch": 0.840192, "grad_norm": 2.375, "learning_rate": 3.6003753945909055e-05, "loss": 0.5461, "step": 3282 }, { "epoch": 0.840448, "grad_norm": 2.515625, "learning_rate": 3.5999488098285136e-05, "loss": 0.4898, "step": 3283 }, { "epoch": 0.840704, "grad_norm": 2.09375, "learning_rate": 3.599522225066121e-05, "loss": 0.5079, "step": 3284 }, { "epoch": 0.84096, "grad_norm": 2.484375, "learning_rate": 3.5990956403037285e-05, "loss": 0.5093, "step": 3285 }, { "epoch": 0.841216, "grad_norm": 2.4375, "learning_rate": 3.598669055541336e-05, "loss": 0.5102, "step": 3286 }, { "epoch": 0.841472, "grad_norm": 2.328125, "learning_rate": 3.598242470778944e-05, "loss": 0.5092, "step": 3287 }, { "epoch": 0.841728, "grad_norm": 2.40625, "learning_rate": 3.5978158860165514e-05, "loss": 0.5381, "step": 3288 }, { "epoch": 0.841984, "grad_norm": 2.234375, "learning_rate": 3.5973893012541595e-05, "loss": 0.5142, "step": 3289 }, { "epoch": 0.84224, "grad_norm": 2.34375, "learning_rate": 3.596962716491767e-05, "loss": 0.523, "step": 3290 }, { "epoch": 0.842496, "grad_norm": 2.3125, "learning_rate": 3.596536131729375e-05, "loss": 0.4927, "step": 3291 }, { "epoch": 0.842752, "grad_norm": 2.671875, "learning_rate": 3.5961095469669825e-05, "loss": 0.5102, "step": 3292 }, { "epoch": 0.843008, "grad_norm": 2.421875, "learning_rate": 3.59568296220459e-05, "loss": 0.4875, "step": 3293 }, { "epoch": 0.843264, "grad_norm": 2.21875, "learning_rate": 3.5952563774421974e-05, "loss": 0.5278, "step": 3294 }, { "epoch": 0.84352, "grad_norm": 2.25, "learning_rate": 3.5948297926798055e-05, "loss": 0.5241, "step": 3295 }, { "epoch": 0.843776, "grad_norm": 2.34375, "learning_rate": 3.5944032079174136e-05, "loss": 0.5122, "step": 3296 }, { "epoch": 0.844032, "grad_norm": 2.15625, "learning_rate": 3.593976623155021e-05, "loss": 0.5034, "step": 3297 }, { "epoch": 0.844288, "grad_norm": 2.203125, "learning_rate": 3.593550038392629e-05, "loss": 0.5121, "step": 3298 }, { "epoch": 0.844544, "grad_norm": 2.390625, "learning_rate": 3.5931234536302365e-05, "loss": 0.5445, "step": 3299 }, { "epoch": 0.8448, "grad_norm": 2.140625, "learning_rate": 3.592696868867844e-05, "loss": 0.5264, "step": 3300 }, { "epoch": 0.845056, "grad_norm": 2.046875, "learning_rate": 3.592270284105452e-05, "loss": 0.5317, "step": 3301 }, { "epoch": 0.845312, "grad_norm": 2.328125, "learning_rate": 3.59184369934306e-05, "loss": 0.5318, "step": 3302 }, { "epoch": 0.845568, "grad_norm": 2.203125, "learning_rate": 3.5914171145806676e-05, "loss": 0.5466, "step": 3303 }, { "epoch": 0.845824, "grad_norm": 2.28125, "learning_rate": 3.590990529818275e-05, "loss": 0.5303, "step": 3304 }, { "epoch": 0.84608, "grad_norm": 2.3125, "learning_rate": 3.5905639450558824e-05, "loss": 0.4983, "step": 3305 }, { "epoch": 0.846336, "grad_norm": 2.171875, "learning_rate": 3.5901373602934905e-05, "loss": 0.4969, "step": 3306 }, { "epoch": 0.846592, "grad_norm": 2.328125, "learning_rate": 3.589710775531098e-05, "loss": 0.47, "step": 3307 }, { "epoch": 0.846848, "grad_norm": 2.1875, "learning_rate": 3.589284190768706e-05, "loss": 0.5243, "step": 3308 }, { "epoch": 0.847104, "grad_norm": 2.5, "learning_rate": 3.5888576060063135e-05, "loss": 0.5509, "step": 3309 }, { "epoch": 0.84736, "grad_norm": 2.40625, "learning_rate": 3.5884310212439216e-05, "loss": 0.5238, "step": 3310 }, { "epoch": 0.847616, "grad_norm": 2.359375, "learning_rate": 3.588004436481529e-05, "loss": 0.5024, "step": 3311 }, { "epoch": 0.847872, "grad_norm": 2.453125, "learning_rate": 3.5875778517191365e-05, "loss": 0.502, "step": 3312 }, { "epoch": 0.848128, "grad_norm": 2.21875, "learning_rate": 3.5871512669567446e-05, "loss": 0.4912, "step": 3313 }, { "epoch": 0.848384, "grad_norm": 2.5, "learning_rate": 3.586724682194352e-05, "loss": 0.4914, "step": 3314 }, { "epoch": 0.84864, "grad_norm": 2.390625, "learning_rate": 3.58629809743196e-05, "loss": 0.5037, "step": 3315 }, { "epoch": 0.848896, "grad_norm": 2.390625, "learning_rate": 3.5858715126695675e-05, "loss": 0.4905, "step": 3316 }, { "epoch": 0.849152, "grad_norm": 2.65625, "learning_rate": 3.5854449279071756e-05, "loss": 0.5128, "step": 3317 }, { "epoch": 0.849408, "grad_norm": 2.609375, "learning_rate": 3.585018343144783e-05, "loss": 0.4801, "step": 3318 }, { "epoch": 0.849664, "grad_norm": 2.546875, "learning_rate": 3.5845917583823905e-05, "loss": 0.5155, "step": 3319 }, { "epoch": 0.84992, "grad_norm": 2.34375, "learning_rate": 3.5841651736199986e-05, "loss": 0.4985, "step": 3320 }, { "epoch": 0.850176, "grad_norm": 2.109375, "learning_rate": 3.583738588857607e-05, "loss": 0.5153, "step": 3321 }, { "epoch": 0.850432, "grad_norm": 2.53125, "learning_rate": 3.583312004095214e-05, "loss": 0.5437, "step": 3322 }, { "epoch": 0.850688, "grad_norm": 2.359375, "learning_rate": 3.5828854193328215e-05, "loss": 0.5327, "step": 3323 }, { "epoch": 0.850944, "grad_norm": 2.546875, "learning_rate": 3.582458834570429e-05, "loss": 0.4993, "step": 3324 }, { "epoch": 0.8512, "grad_norm": 2.046875, "learning_rate": 3.582032249808037e-05, "loss": 0.556, "step": 3325 }, { "epoch": 0.851456, "grad_norm": 2.234375, "learning_rate": 3.5816056650456445e-05, "loss": 0.5039, "step": 3326 }, { "epoch": 0.851712, "grad_norm": 2.203125, "learning_rate": 3.5811790802832526e-05, "loss": 0.5073, "step": 3327 }, { "epoch": 0.851968, "grad_norm": 2.171875, "learning_rate": 3.58075249552086e-05, "loss": 0.5459, "step": 3328 }, { "epoch": 0.852224, "grad_norm": 2.578125, "learning_rate": 3.580325910758468e-05, "loss": 0.5352, "step": 3329 }, { "epoch": 0.85248, "grad_norm": 2.25, "learning_rate": 3.5798993259960756e-05, "loss": 0.5384, "step": 3330 }, { "epoch": 0.852736, "grad_norm": 2.359375, "learning_rate": 3.579472741233683e-05, "loss": 0.4982, "step": 3331 }, { "epoch": 0.852992, "grad_norm": 2.046875, "learning_rate": 3.579046156471291e-05, "loss": 0.5063, "step": 3332 }, { "epoch": 0.853248, "grad_norm": 2.25, "learning_rate": 3.5786195717088985e-05, "loss": 0.5499, "step": 3333 }, { "epoch": 0.853504, "grad_norm": 2.234375, "learning_rate": 3.5781929869465066e-05, "loss": 0.5559, "step": 3334 }, { "epoch": 0.85376, "grad_norm": 2.078125, "learning_rate": 3.577766402184114e-05, "loss": 0.5355, "step": 3335 }, { "epoch": 0.854016, "grad_norm": 2.359375, "learning_rate": 3.577339817421722e-05, "loss": 0.5167, "step": 3336 }, { "epoch": 0.854272, "grad_norm": 2.3125, "learning_rate": 3.5769132326593296e-05, "loss": 0.5239, "step": 3337 }, { "epoch": 0.854528, "grad_norm": 2.359375, "learning_rate": 3.576486647896937e-05, "loss": 0.5052, "step": 3338 }, { "epoch": 0.854784, "grad_norm": 2.40625, "learning_rate": 3.576060063134545e-05, "loss": 0.4815, "step": 3339 }, { "epoch": 0.85504, "grad_norm": 2.453125, "learning_rate": 3.575633478372153e-05, "loss": 0.5443, "step": 3340 }, { "epoch": 0.855296, "grad_norm": 2.21875, "learning_rate": 3.5752068936097606e-05, "loss": 0.5319, "step": 3341 }, { "epoch": 0.855552, "grad_norm": 2.15625, "learning_rate": 3.574780308847368e-05, "loss": 0.5075, "step": 3342 }, { "epoch": 0.855808, "grad_norm": 2.46875, "learning_rate": 3.5743537240849755e-05, "loss": 0.4833, "step": 3343 }, { "epoch": 0.856064, "grad_norm": 2.1875, "learning_rate": 3.5739271393225836e-05, "loss": 0.5142, "step": 3344 }, { "epoch": 0.85632, "grad_norm": 2.328125, "learning_rate": 3.573500554560191e-05, "loss": 0.5145, "step": 3345 }, { "epoch": 0.856576, "grad_norm": 2.453125, "learning_rate": 3.573073969797799e-05, "loss": 0.4633, "step": 3346 }, { "epoch": 0.856832, "grad_norm": 2.34375, "learning_rate": 3.572647385035407e-05, "loss": 0.4943, "step": 3347 }, { "epoch": 0.857088, "grad_norm": 2.4375, "learning_rate": 3.5722208002730147e-05, "loss": 0.5307, "step": 3348 }, { "epoch": 0.857344, "grad_norm": 2.21875, "learning_rate": 3.571794215510622e-05, "loss": 0.5196, "step": 3349 }, { "epoch": 0.8576, "grad_norm": 2.1875, "learning_rate": 3.5713676307482295e-05, "loss": 0.5142, "step": 3350 }, { "epoch": 0.857856, "grad_norm": 2.390625, "learning_rate": 3.5709410459858376e-05, "loss": 0.5348, "step": 3351 }, { "epoch": 0.858112, "grad_norm": 2.296875, "learning_rate": 3.570514461223445e-05, "loss": 0.565, "step": 3352 }, { "epoch": 0.858368, "grad_norm": 2.25, "learning_rate": 3.570087876461053e-05, "loss": 0.5038, "step": 3353 }, { "epoch": 0.858624, "grad_norm": 2.34375, "learning_rate": 3.5696612916986606e-05, "loss": 0.514, "step": 3354 }, { "epoch": 0.85888, "grad_norm": 2.46875, "learning_rate": 3.569234706936269e-05, "loss": 0.5199, "step": 3355 }, { "epoch": 0.859136, "grad_norm": 2.359375, "learning_rate": 3.568808122173876e-05, "loss": 0.5344, "step": 3356 }, { "epoch": 0.859392, "grad_norm": 2.4375, "learning_rate": 3.5683815374114835e-05, "loss": 0.5108, "step": 3357 }, { "epoch": 0.859648, "grad_norm": 2.546875, "learning_rate": 3.5679549526490916e-05, "loss": 0.4906, "step": 3358 }, { "epoch": 0.859904, "grad_norm": 2.328125, "learning_rate": 3.5675283678867e-05, "loss": 0.5166, "step": 3359 }, { "epoch": 0.86016, "grad_norm": 2.5, "learning_rate": 3.567101783124307e-05, "loss": 0.5089, "step": 3360 }, { "epoch": 0.860416, "grad_norm": 2.234375, "learning_rate": 3.5666751983619146e-05, "loss": 0.513, "step": 3361 }, { "epoch": 0.860672, "grad_norm": 2.421875, "learning_rate": 3.566248613599523e-05, "loss": 0.5296, "step": 3362 }, { "epoch": 0.860928, "grad_norm": 2.515625, "learning_rate": 3.56582202883713e-05, "loss": 0.4885, "step": 3363 }, { "epoch": 0.861184, "grad_norm": 2.484375, "learning_rate": 3.5653954440747376e-05, "loss": 0.4651, "step": 3364 }, { "epoch": 0.86144, "grad_norm": 2.59375, "learning_rate": 3.5649688593123457e-05, "loss": 0.5342, "step": 3365 }, { "epoch": 0.861696, "grad_norm": 2.28125, "learning_rate": 3.564542274549954e-05, "loss": 0.5042, "step": 3366 }, { "epoch": 0.861952, "grad_norm": 2.3125, "learning_rate": 3.564115689787561e-05, "loss": 0.5077, "step": 3367 }, { "epoch": 0.862208, "grad_norm": 2.296875, "learning_rate": 3.5636891050251686e-05, "loss": 0.5179, "step": 3368 }, { "epoch": 0.862464, "grad_norm": 2.265625, "learning_rate": 3.563262520262776e-05, "loss": 0.487, "step": 3369 }, { "epoch": 0.86272, "grad_norm": 2.21875, "learning_rate": 3.562835935500384e-05, "loss": 0.5098, "step": 3370 }, { "epoch": 0.862976, "grad_norm": 2.515625, "learning_rate": 3.5624093507379916e-05, "loss": 0.4889, "step": 3371 }, { "epoch": 0.863232, "grad_norm": 2.53125, "learning_rate": 3.5619827659756e-05, "loss": 0.5185, "step": 3372 }, { "epoch": 0.863488, "grad_norm": 2.5, "learning_rate": 3.561556181213207e-05, "loss": 0.4828, "step": 3373 }, { "epoch": 0.863744, "grad_norm": 2.28125, "learning_rate": 3.561129596450815e-05, "loss": 0.5199, "step": 3374 }, { "epoch": 0.864, "grad_norm": 2.359375, "learning_rate": 3.5607030116884226e-05, "loss": 0.5039, "step": 3375 }, { "epoch": 0.864256, "grad_norm": 2.421875, "learning_rate": 3.56027642692603e-05, "loss": 0.5116, "step": 3376 }, { "epoch": 0.864512, "grad_norm": 2.578125, "learning_rate": 3.5598498421636375e-05, "loss": 0.5025, "step": 3377 }, { "epoch": 0.864768, "grad_norm": 2.28125, "learning_rate": 3.559423257401246e-05, "loss": 0.5112, "step": 3378 }, { "epoch": 0.865024, "grad_norm": 2.234375, "learning_rate": 3.558996672638854e-05, "loss": 0.4943, "step": 3379 }, { "epoch": 0.86528, "grad_norm": 2.5, "learning_rate": 3.558570087876461e-05, "loss": 0.5472, "step": 3380 }, { "epoch": 0.865536, "grad_norm": 2.40625, "learning_rate": 3.558143503114069e-05, "loss": 0.5125, "step": 3381 }, { "epoch": 0.865792, "grad_norm": 2.359375, "learning_rate": 3.5577169183516767e-05, "loss": 0.4918, "step": 3382 }, { "epoch": 0.866048, "grad_norm": 2.3125, "learning_rate": 3.557290333589284e-05, "loss": 0.5152, "step": 3383 }, { "epoch": 0.866304, "grad_norm": 2.453125, "learning_rate": 3.556863748826892e-05, "loss": 0.5087, "step": 3384 }, { "epoch": 0.86656, "grad_norm": 2.453125, "learning_rate": 3.5564371640645e-05, "loss": 0.5232, "step": 3385 }, { "epoch": 0.866816, "grad_norm": 2.453125, "learning_rate": 3.556010579302108e-05, "loss": 0.5326, "step": 3386 }, { "epoch": 0.867072, "grad_norm": 2.1875, "learning_rate": 3.555583994539715e-05, "loss": 0.478, "step": 3387 }, { "epoch": 0.867328, "grad_norm": 2.234375, "learning_rate": 3.5551574097773226e-05, "loss": 0.5488, "step": 3388 }, { "epoch": 0.867584, "grad_norm": 2.3125, "learning_rate": 3.554730825014931e-05, "loss": 0.5024, "step": 3389 }, { "epoch": 0.86784, "grad_norm": 2.453125, "learning_rate": 3.554304240252538e-05, "loss": 0.5054, "step": 3390 }, { "epoch": 0.868096, "grad_norm": 2.3125, "learning_rate": 3.553877655490146e-05, "loss": 0.4764, "step": 3391 }, { "epoch": 0.868352, "grad_norm": 2.421875, "learning_rate": 3.5534510707277536e-05, "loss": 0.493, "step": 3392 }, { "epoch": 0.868608, "grad_norm": 2.234375, "learning_rate": 3.553024485965362e-05, "loss": 0.4957, "step": 3393 }, { "epoch": 0.868864, "grad_norm": 2.625, "learning_rate": 3.552597901202969e-05, "loss": 0.5027, "step": 3394 }, { "epoch": 0.86912, "grad_norm": 2.265625, "learning_rate": 3.5521713164405766e-05, "loss": 0.5012, "step": 3395 }, { "epoch": 0.869376, "grad_norm": 2.328125, "learning_rate": 3.551744731678185e-05, "loss": 0.5347, "step": 3396 }, { "epoch": 0.869632, "grad_norm": 2.234375, "learning_rate": 3.551318146915792e-05, "loss": 0.5038, "step": 3397 }, { "epoch": 0.869888, "grad_norm": 2.3125, "learning_rate": 3.5508915621534e-05, "loss": 0.4912, "step": 3398 }, { "epoch": 0.870144, "grad_norm": 2.25, "learning_rate": 3.5504649773910076e-05, "loss": 0.5134, "step": 3399 }, { "epoch": 0.8704, "grad_norm": 2.390625, "learning_rate": 3.550038392628616e-05, "loss": 0.4929, "step": 3400 }, { "epoch": 0.870656, "grad_norm": 2.3125, "learning_rate": 3.549611807866223e-05, "loss": 0.4853, "step": 3401 }, { "epoch": 0.870912, "grad_norm": 2.4375, "learning_rate": 3.5491852231038306e-05, "loss": 0.5235, "step": 3402 }, { "epoch": 0.871168, "grad_norm": 2.3125, "learning_rate": 3.548758638341439e-05, "loss": 0.509, "step": 3403 }, { "epoch": 0.871424, "grad_norm": 2.3125, "learning_rate": 3.548332053579047e-05, "loss": 0.5, "step": 3404 }, { "epoch": 0.87168, "grad_norm": 2.625, "learning_rate": 3.547905468816654e-05, "loss": 0.5116, "step": 3405 }, { "epoch": 0.871936, "grad_norm": 2.28125, "learning_rate": 3.547478884054262e-05, "loss": 0.4935, "step": 3406 }, { "epoch": 0.872192, "grad_norm": 2.375, "learning_rate": 3.547052299291869e-05, "loss": 0.493, "step": 3407 }, { "epoch": 0.872448, "grad_norm": 2.484375, "learning_rate": 3.546625714529477e-05, "loss": 0.5176, "step": 3408 }, { "epoch": 0.872704, "grad_norm": 2.1875, "learning_rate": 3.5461991297670846e-05, "loss": 0.5174, "step": 3409 }, { "epoch": 0.87296, "grad_norm": 2.328125, "learning_rate": 3.545772545004693e-05, "loss": 0.5196, "step": 3410 }, { "epoch": 0.873216, "grad_norm": 2.203125, "learning_rate": 3.545345960242301e-05, "loss": 0.461, "step": 3411 }, { "epoch": 0.873472, "grad_norm": 2.25, "learning_rate": 3.544919375479908e-05, "loss": 0.5081, "step": 3412 }, { "epoch": 0.873728, "grad_norm": 2.265625, "learning_rate": 3.544492790717516e-05, "loss": 0.5064, "step": 3413 }, { "epoch": 0.873984, "grad_norm": 2.390625, "learning_rate": 3.544066205955123e-05, "loss": 0.5103, "step": 3414 }, { "epoch": 0.87424, "grad_norm": 2.125, "learning_rate": 3.543639621192731e-05, "loss": 0.5048, "step": 3415 }, { "epoch": 0.874496, "grad_norm": 2.203125, "learning_rate": 3.5432130364303386e-05, "loss": 0.505, "step": 3416 }, { "epoch": 0.874752, "grad_norm": 2.296875, "learning_rate": 3.542786451667947e-05, "loss": 0.4976, "step": 3417 }, { "epoch": 0.875008, "grad_norm": 2.21875, "learning_rate": 3.542359866905554e-05, "loss": 0.5096, "step": 3418 }, { "epoch": 0.875264, "grad_norm": 2.3125, "learning_rate": 3.541933282143162e-05, "loss": 0.5211, "step": 3419 }, { "epoch": 0.87552, "grad_norm": 2.28125, "learning_rate": 3.54150669738077e-05, "loss": 0.5245, "step": 3420 }, { "epoch": 0.875776, "grad_norm": 2.28125, "learning_rate": 3.541080112618377e-05, "loss": 0.5057, "step": 3421 }, { "epoch": 0.876032, "grad_norm": 2.328125, "learning_rate": 3.540653527855985e-05, "loss": 0.5401, "step": 3422 }, { "epoch": 0.876288, "grad_norm": 2.421875, "learning_rate": 3.5402269430935933e-05, "loss": 0.5147, "step": 3423 }, { "epoch": 0.876544, "grad_norm": 2.484375, "learning_rate": 3.539800358331201e-05, "loss": 0.5517, "step": 3424 }, { "epoch": 0.8768, "grad_norm": 2.53125, "learning_rate": 3.539373773568808e-05, "loss": 0.5105, "step": 3425 }, { "epoch": 0.877056, "grad_norm": 2.109375, "learning_rate": 3.5389471888064156e-05, "loss": 0.5538, "step": 3426 }, { "epoch": 0.877312, "grad_norm": 2.25, "learning_rate": 3.538520604044024e-05, "loss": 0.5351, "step": 3427 }, { "epoch": 0.877568, "grad_norm": 2.3125, "learning_rate": 3.538094019281631e-05, "loss": 0.4895, "step": 3428 }, { "epoch": 0.877824, "grad_norm": 2.21875, "learning_rate": 3.537667434519239e-05, "loss": 0.488, "step": 3429 }, { "epoch": 0.87808, "grad_norm": 2.1875, "learning_rate": 3.5372408497568474e-05, "loss": 0.5034, "step": 3430 }, { "epoch": 0.878336, "grad_norm": 2.1875, "learning_rate": 3.536814264994455e-05, "loss": 0.4956, "step": 3431 }, { "epoch": 0.878592, "grad_norm": 2.328125, "learning_rate": 3.536387680232062e-05, "loss": 0.5163, "step": 3432 }, { "epoch": 0.878848, "grad_norm": 2.484375, "learning_rate": 3.5359610954696696e-05, "loss": 0.5002, "step": 3433 }, { "epoch": 0.879104, "grad_norm": 2.15625, "learning_rate": 3.535534510707278e-05, "loss": 0.4556, "step": 3434 }, { "epoch": 0.87936, "grad_norm": 2.1875, "learning_rate": 3.535107925944885e-05, "loss": 0.4779, "step": 3435 }, { "epoch": 0.879616, "grad_norm": 2.5625, "learning_rate": 3.534681341182493e-05, "loss": 0.5304, "step": 3436 }, { "epoch": 0.879872, "grad_norm": 2.453125, "learning_rate": 3.534254756420101e-05, "loss": 0.5131, "step": 3437 }, { "epoch": 0.880128, "grad_norm": 2.125, "learning_rate": 3.533828171657709e-05, "loss": 0.5224, "step": 3438 }, { "epoch": 0.880384, "grad_norm": 2.40625, "learning_rate": 3.533401586895316e-05, "loss": 0.5187, "step": 3439 }, { "epoch": 0.88064, "grad_norm": 2.421875, "learning_rate": 3.5329750021329237e-05, "loss": 0.4939, "step": 3440 }, { "epoch": 0.880896, "grad_norm": 2.34375, "learning_rate": 3.532548417370532e-05, "loss": 0.4712, "step": 3441 }, { "epoch": 0.881152, "grad_norm": 2.140625, "learning_rate": 3.53212183260814e-05, "loss": 0.5077, "step": 3442 }, { "epoch": 0.881408, "grad_norm": 2.390625, "learning_rate": 3.531695247845747e-05, "loss": 0.5006, "step": 3443 }, { "epoch": 0.881664, "grad_norm": 2.40625, "learning_rate": 3.531268663083355e-05, "loss": 0.4813, "step": 3444 }, { "epoch": 0.88192, "grad_norm": 2.234375, "learning_rate": 3.530842078320963e-05, "loss": 0.5313, "step": 3445 }, { "epoch": 0.882176, "grad_norm": 2.234375, "learning_rate": 3.53041549355857e-05, "loss": 0.5049, "step": 3446 }, { "epoch": 0.882432, "grad_norm": 2.28125, "learning_rate": 3.529988908796178e-05, "loss": 0.5168, "step": 3447 }, { "epoch": 0.882688, "grad_norm": 2.296875, "learning_rate": 3.529562324033786e-05, "loss": 0.453, "step": 3448 }, { "epoch": 0.882944, "grad_norm": 2.40625, "learning_rate": 3.529135739271394e-05, "loss": 0.5364, "step": 3449 }, { "epoch": 0.8832, "grad_norm": 2.421875, "learning_rate": 3.528709154509001e-05, "loss": 0.5163, "step": 3450 }, { "epoch": 0.883456, "grad_norm": 2.71875, "learning_rate": 3.528282569746609e-05, "loss": 0.4985, "step": 3451 }, { "epoch": 0.883712, "grad_norm": 2.234375, "learning_rate": 3.527855984984216e-05, "loss": 0.4846, "step": 3452 }, { "epoch": 0.883968, "grad_norm": 2.484375, "learning_rate": 3.527429400221824e-05, "loss": 0.4843, "step": 3453 }, { "epoch": 0.884224, "grad_norm": 2.4375, "learning_rate": 3.527002815459432e-05, "loss": 0.515, "step": 3454 }, { "epoch": 0.88448, "grad_norm": 2.125, "learning_rate": 3.52657623069704e-05, "loss": 0.5321, "step": 3455 }, { "epoch": 0.884736, "grad_norm": 2.125, "learning_rate": 3.526149645934647e-05, "loss": 0.5458, "step": 3456 }, { "epoch": 0.884992, "grad_norm": 2.265625, "learning_rate": 3.525723061172255e-05, "loss": 0.4718, "step": 3457 }, { "epoch": 0.885248, "grad_norm": 2.46875, "learning_rate": 3.525296476409863e-05, "loss": 0.5068, "step": 3458 }, { "epoch": 0.885504, "grad_norm": 2.328125, "learning_rate": 3.52486989164747e-05, "loss": 0.5109, "step": 3459 }, { "epoch": 0.88576, "grad_norm": 2.125, "learning_rate": 3.524443306885078e-05, "loss": 0.5281, "step": 3460 }, { "epoch": 0.886016, "grad_norm": 2.53125, "learning_rate": 3.5240167221226864e-05, "loss": 0.4799, "step": 3461 }, { "epoch": 0.886272, "grad_norm": 2.203125, "learning_rate": 3.523590137360294e-05, "loss": 0.4821, "step": 3462 }, { "epoch": 0.886528, "grad_norm": 2.3125, "learning_rate": 3.523163552597901e-05, "loss": 0.5092, "step": 3463 }, { "epoch": 0.886784, "grad_norm": 2.1875, "learning_rate": 3.5227369678355094e-05, "loss": 0.5185, "step": 3464 }, { "epoch": 0.88704, "grad_norm": 2.34375, "learning_rate": 3.522310383073117e-05, "loss": 0.5013, "step": 3465 }, { "epoch": 0.887296, "grad_norm": 2.21875, "learning_rate": 3.521883798310724e-05, "loss": 0.5407, "step": 3466 }, { "epoch": 0.887552, "grad_norm": 2.3125, "learning_rate": 3.521457213548332e-05, "loss": 0.4836, "step": 3467 }, { "epoch": 0.887808, "grad_norm": 2.515625, "learning_rate": 3.5210306287859404e-05, "loss": 0.5127, "step": 3468 }, { "epoch": 0.888064, "grad_norm": 2.25, "learning_rate": 3.520604044023548e-05, "loss": 0.5314, "step": 3469 }, { "epoch": 0.88832, "grad_norm": 2.34375, "learning_rate": 3.520177459261155e-05, "loss": 0.4894, "step": 3470 }, { "epoch": 0.888576, "grad_norm": 2.046875, "learning_rate": 3.519750874498763e-05, "loss": 0.5126, "step": 3471 }, { "epoch": 0.888832, "grad_norm": 2.390625, "learning_rate": 3.519324289736371e-05, "loss": 0.4856, "step": 3472 }, { "epoch": 0.889088, "grad_norm": 2.453125, "learning_rate": 3.518897704973978e-05, "loss": 0.4952, "step": 3473 }, { "epoch": 0.889344, "grad_norm": 2.484375, "learning_rate": 3.518471120211586e-05, "loss": 0.4937, "step": 3474 }, { "epoch": 0.8896, "grad_norm": 2.28125, "learning_rate": 3.518044535449194e-05, "loss": 0.529, "step": 3475 }, { "epoch": 0.889856, "grad_norm": 2.25, "learning_rate": 3.517617950686802e-05, "loss": 0.4997, "step": 3476 }, { "epoch": 0.890112, "grad_norm": 2.328125, "learning_rate": 3.517191365924409e-05, "loss": 0.4899, "step": 3477 }, { "epoch": 0.890368, "grad_norm": 2.3125, "learning_rate": 3.516764781162017e-05, "loss": 0.5299, "step": 3478 }, { "epoch": 0.890624, "grad_norm": 2.125, "learning_rate": 3.516338196399625e-05, "loss": 0.4887, "step": 3479 }, { "epoch": 0.89088, "grad_norm": 2.25, "learning_rate": 3.515911611637233e-05, "loss": 0.49, "step": 3480 }, { "epoch": 0.891136, "grad_norm": 2.203125, "learning_rate": 3.5154850268748403e-05, "loss": 0.4917, "step": 3481 }, { "epoch": 0.891392, "grad_norm": 2.375, "learning_rate": 3.515058442112448e-05, "loss": 0.508, "step": 3482 }, { "epoch": 0.891648, "grad_norm": 2.421875, "learning_rate": 3.514631857350056e-05, "loss": 0.4666, "step": 3483 }, { "epoch": 0.891904, "grad_norm": 2.15625, "learning_rate": 3.514205272587663e-05, "loss": 0.5461, "step": 3484 }, { "epoch": 0.89216, "grad_norm": 2.453125, "learning_rate": 3.513778687825271e-05, "loss": 0.4856, "step": 3485 }, { "epoch": 0.892416, "grad_norm": 2.328125, "learning_rate": 3.513352103062879e-05, "loss": 0.5328, "step": 3486 }, { "epoch": 0.892672, "grad_norm": 2.328125, "learning_rate": 3.512925518300487e-05, "loss": 0.5115, "step": 3487 }, { "epoch": 0.892928, "grad_norm": 2.375, "learning_rate": 3.5124989335380944e-05, "loss": 0.4932, "step": 3488 }, { "epoch": 0.893184, "grad_norm": 2.40625, "learning_rate": 3.512072348775702e-05, "loss": 0.5346, "step": 3489 }, { "epoch": 0.89344, "grad_norm": 2.28125, "learning_rate": 3.511645764013309e-05, "loss": 0.5135, "step": 3490 }, { "epoch": 0.893696, "grad_norm": 2.25, "learning_rate": 3.511219179250917e-05, "loss": 0.5084, "step": 3491 }, { "epoch": 0.893952, "grad_norm": 2.65625, "learning_rate": 3.510792594488525e-05, "loss": 0.5306, "step": 3492 }, { "epoch": 0.894208, "grad_norm": 2.265625, "learning_rate": 3.510366009726133e-05, "loss": 0.4438, "step": 3493 }, { "epoch": 0.894464, "grad_norm": 2.296875, "learning_rate": 3.509939424963741e-05, "loss": 0.5106, "step": 3494 }, { "epoch": 0.89472, "grad_norm": 2.34375, "learning_rate": 3.5095128402013484e-05, "loss": 0.4777, "step": 3495 }, { "epoch": 0.894976, "grad_norm": 2.265625, "learning_rate": 3.509086255438956e-05, "loss": 0.5131, "step": 3496 }, { "epoch": 0.895232, "grad_norm": 2.328125, "learning_rate": 3.508659670676563e-05, "loss": 0.5152, "step": 3497 }, { "epoch": 0.895488, "grad_norm": 2.171875, "learning_rate": 3.5082330859141713e-05, "loss": 0.4853, "step": 3498 }, { "epoch": 0.895744, "grad_norm": 2.34375, "learning_rate": 3.5078065011517794e-05, "loss": 0.4825, "step": 3499 }, { "epoch": 0.896, "grad_norm": 2.28125, "learning_rate": 3.507379916389387e-05, "loss": 0.5303, "step": 3500 }, { "epoch": 0.896256, "grad_norm": 2.09375, "learning_rate": 3.506953331626994e-05, "loss": 0.4981, "step": 3501 }, { "epoch": 0.896512, "grad_norm": 2.21875, "learning_rate": 3.5065267468646024e-05, "loss": 0.452, "step": 3502 }, { "epoch": 0.896768, "grad_norm": 2.234375, "learning_rate": 3.50610016210221e-05, "loss": 0.5593, "step": 3503 }, { "epoch": 0.897024, "grad_norm": 2.265625, "learning_rate": 3.505673577339817e-05, "loss": 0.5591, "step": 3504 }, { "epoch": 0.89728, "grad_norm": 2.515625, "learning_rate": 3.5052469925774254e-05, "loss": 0.4895, "step": 3505 }, { "epoch": 0.897536, "grad_norm": 2.296875, "learning_rate": 3.5048204078150335e-05, "loss": 0.5089, "step": 3506 }, { "epoch": 0.897792, "grad_norm": 2.1875, "learning_rate": 3.504393823052641e-05, "loss": 0.5247, "step": 3507 }, { "epoch": 0.898048, "grad_norm": 2.390625, "learning_rate": 3.503967238290248e-05, "loss": 0.5075, "step": 3508 }, { "epoch": 0.898304, "grad_norm": 2.40625, "learning_rate": 3.503540653527856e-05, "loss": 0.5109, "step": 3509 }, { "epoch": 0.89856, "grad_norm": 2.375, "learning_rate": 3.503114068765464e-05, "loss": 0.5009, "step": 3510 }, { "epoch": 0.898816, "grad_norm": 2.3125, "learning_rate": 3.502687484003071e-05, "loss": 0.5123, "step": 3511 }, { "epoch": 0.899072, "grad_norm": 2.234375, "learning_rate": 3.5022608992406794e-05, "loss": 0.5001, "step": 3512 }, { "epoch": 0.899328, "grad_norm": 2.234375, "learning_rate": 3.5018343144782875e-05, "loss": 0.5143, "step": 3513 }, { "epoch": 0.899584, "grad_norm": 2.359375, "learning_rate": 3.501407729715895e-05, "loss": 0.4777, "step": 3514 }, { "epoch": 0.89984, "grad_norm": 2.3125, "learning_rate": 3.5009811449535023e-05, "loss": 0.5153, "step": 3515 }, { "epoch": 0.900096, "grad_norm": 2.3125, "learning_rate": 3.50055456019111e-05, "loss": 0.4968, "step": 3516 }, { "epoch": 0.900352, "grad_norm": 2.3125, "learning_rate": 3.500127975428718e-05, "loss": 0.5158, "step": 3517 }, { "epoch": 0.900608, "grad_norm": 2.21875, "learning_rate": 3.499701390666325e-05, "loss": 0.4786, "step": 3518 }, { "epoch": 0.900864, "grad_norm": 2.21875, "learning_rate": 3.4992748059039334e-05, "loss": 0.5266, "step": 3519 }, { "epoch": 0.90112, "grad_norm": 2.328125, "learning_rate": 3.498848221141541e-05, "loss": 0.5144, "step": 3520 }, { "epoch": 0.901376, "grad_norm": 2.296875, "learning_rate": 3.498421636379149e-05, "loss": 0.476, "step": 3521 }, { "epoch": 0.901632, "grad_norm": 2.15625, "learning_rate": 3.4979950516167564e-05, "loss": 0.5082, "step": 3522 }, { "epoch": 0.901888, "grad_norm": 2.296875, "learning_rate": 3.497568466854364e-05, "loss": 0.4818, "step": 3523 }, { "epoch": 0.902144, "grad_norm": 2.171875, "learning_rate": 3.497141882091972e-05, "loss": 0.5127, "step": 3524 }, { "epoch": 0.9024, "grad_norm": 2.25, "learning_rate": 3.49671529732958e-05, "loss": 0.5039, "step": 3525 }, { "epoch": 0.902656, "grad_norm": 2.1875, "learning_rate": 3.4962887125671874e-05, "loss": 0.5278, "step": 3526 }, { "epoch": 0.902912, "grad_norm": 2.21875, "learning_rate": 3.495862127804795e-05, "loss": 0.4951, "step": 3527 }, { "epoch": 0.903168, "grad_norm": 2.15625, "learning_rate": 3.495435543042403e-05, "loss": 0.5159, "step": 3528 }, { "epoch": 0.903424, "grad_norm": 2.421875, "learning_rate": 3.4950089582800104e-05, "loss": 0.4937, "step": 3529 }, { "epoch": 0.90368, "grad_norm": 2.359375, "learning_rate": 3.494582373517618e-05, "loss": 0.5193, "step": 3530 }, { "epoch": 0.903936, "grad_norm": 2.28125, "learning_rate": 3.494155788755226e-05, "loss": 0.5178, "step": 3531 }, { "epoch": 0.904192, "grad_norm": 2.21875, "learning_rate": 3.493729203992834e-05, "loss": 0.4887, "step": 3532 }, { "epoch": 0.904448, "grad_norm": 2.34375, "learning_rate": 3.4933026192304414e-05, "loss": 0.4621, "step": 3533 }, { "epoch": 0.904704, "grad_norm": 2.46875, "learning_rate": 3.492876034468049e-05, "loss": 0.5005, "step": 3534 }, { "epoch": 0.90496, "grad_norm": 2.390625, "learning_rate": 3.492449449705656e-05, "loss": 0.4948, "step": 3535 }, { "epoch": 0.905216, "grad_norm": 2.265625, "learning_rate": 3.4920228649432644e-05, "loss": 0.5031, "step": 3536 }, { "epoch": 0.905472, "grad_norm": 2.40625, "learning_rate": 3.491596280180872e-05, "loss": 0.4871, "step": 3537 }, { "epoch": 0.905728, "grad_norm": 2.265625, "learning_rate": 3.49116969541848e-05, "loss": 0.4817, "step": 3538 }, { "epoch": 0.905984, "grad_norm": 2.5625, "learning_rate": 3.4907431106560874e-05, "loss": 0.4975, "step": 3539 }, { "epoch": 0.90624, "grad_norm": 2.125, "learning_rate": 3.4903165258936955e-05, "loss": 0.5033, "step": 3540 }, { "epoch": 0.906496, "grad_norm": 2.453125, "learning_rate": 3.489889941131303e-05, "loss": 0.5082, "step": 3541 }, { "epoch": 0.906752, "grad_norm": 2.265625, "learning_rate": 3.48946335636891e-05, "loss": 0.5466, "step": 3542 }, { "epoch": 0.907008, "grad_norm": 2.375, "learning_rate": 3.4890367716065184e-05, "loss": 0.4767, "step": 3543 }, { "epoch": 0.907264, "grad_norm": 2.296875, "learning_rate": 3.4886101868441265e-05, "loss": 0.4652, "step": 3544 }, { "epoch": 0.90752, "grad_norm": 2.296875, "learning_rate": 3.488183602081734e-05, "loss": 0.5006, "step": 3545 }, { "epoch": 0.907776, "grad_norm": 2.578125, "learning_rate": 3.4877570173193414e-05, "loss": 0.4746, "step": 3546 }, { "epoch": 0.908032, "grad_norm": 2.546875, "learning_rate": 3.4873304325569495e-05, "loss": 0.5322, "step": 3547 }, { "epoch": 0.908288, "grad_norm": 2.40625, "learning_rate": 3.486903847794557e-05, "loss": 0.494, "step": 3548 }, { "epoch": 0.908544, "grad_norm": 2.390625, "learning_rate": 3.486477263032164e-05, "loss": 0.5383, "step": 3549 }, { "epoch": 0.9088, "grad_norm": 2.390625, "learning_rate": 3.4860506782697724e-05, "loss": 0.4723, "step": 3550 }, { "epoch": 0.909056, "grad_norm": 2.4375, "learning_rate": 3.4856240935073805e-05, "loss": 0.4684, "step": 3551 }, { "epoch": 0.909312, "grad_norm": 2.375, "learning_rate": 3.485197508744988e-05, "loss": 0.5073, "step": 3552 }, { "epoch": 0.909568, "grad_norm": 2.15625, "learning_rate": 3.4847709239825954e-05, "loss": 0.445, "step": 3553 }, { "epoch": 0.909824, "grad_norm": 2.515625, "learning_rate": 3.484344339220203e-05, "loss": 0.5473, "step": 3554 }, { "epoch": 0.91008, "grad_norm": 2.1875, "learning_rate": 3.483917754457811e-05, "loss": 0.5229, "step": 3555 }, { "epoch": 0.910336, "grad_norm": 2.140625, "learning_rate": 3.4834911696954184e-05, "loss": 0.5255, "step": 3556 }, { "epoch": 0.910592, "grad_norm": 2.359375, "learning_rate": 3.4830645849330265e-05, "loss": 0.5059, "step": 3557 }, { "epoch": 0.910848, "grad_norm": 2.21875, "learning_rate": 3.482638000170634e-05, "loss": 0.5462, "step": 3558 }, { "epoch": 0.911104, "grad_norm": 2.53125, "learning_rate": 3.482211415408242e-05, "loss": 0.5255, "step": 3559 }, { "epoch": 0.91136, "grad_norm": 2.296875, "learning_rate": 3.4817848306458494e-05, "loss": 0.4848, "step": 3560 }, { "epoch": 0.911616, "grad_norm": 2.234375, "learning_rate": 3.481358245883457e-05, "loss": 0.4867, "step": 3561 }, { "epoch": 0.911872, "grad_norm": 2.296875, "learning_rate": 3.480931661121065e-05, "loss": 0.45, "step": 3562 }, { "epoch": 0.912128, "grad_norm": 2.53125, "learning_rate": 3.480505076358673e-05, "loss": 0.4817, "step": 3563 }, { "epoch": 0.912384, "grad_norm": 2.234375, "learning_rate": 3.4800784915962805e-05, "loss": 0.5104, "step": 3564 }, { "epoch": 0.91264, "grad_norm": 2.25, "learning_rate": 3.479651906833888e-05, "loss": 0.4734, "step": 3565 }, { "epoch": 0.912896, "grad_norm": 2.40625, "learning_rate": 3.479225322071496e-05, "loss": 0.4985, "step": 3566 }, { "epoch": 0.913152, "grad_norm": 2.265625, "learning_rate": 3.4787987373091034e-05, "loss": 0.4824, "step": 3567 }, { "epoch": 0.913408, "grad_norm": 2.34375, "learning_rate": 3.478372152546711e-05, "loss": 0.5089, "step": 3568 }, { "epoch": 0.913664, "grad_norm": 2.125, "learning_rate": 3.477945567784319e-05, "loss": 0.4981, "step": 3569 }, { "epoch": 0.91392, "grad_norm": 2.34375, "learning_rate": 3.477518983021927e-05, "loss": 0.4932, "step": 3570 }, { "epoch": 0.914176, "grad_norm": 2.359375, "learning_rate": 3.4770923982595345e-05, "loss": 0.4855, "step": 3571 }, { "epoch": 0.914432, "grad_norm": 2.34375, "learning_rate": 3.476665813497142e-05, "loss": 0.5074, "step": 3572 }, { "epoch": 0.914688, "grad_norm": 2.328125, "learning_rate": 3.4762392287347493e-05, "loss": 0.474, "step": 3573 }, { "epoch": 0.914944, "grad_norm": 2.140625, "learning_rate": 3.4758126439723575e-05, "loss": 0.5042, "step": 3574 }, { "epoch": 0.9152, "grad_norm": 2.28125, "learning_rate": 3.475386059209965e-05, "loss": 0.5244, "step": 3575 }, { "epoch": 0.915456, "grad_norm": 2.140625, "learning_rate": 3.474959474447573e-05, "loss": 0.5337, "step": 3576 }, { "epoch": 0.915712, "grad_norm": 2.3125, "learning_rate": 3.474532889685181e-05, "loss": 0.525, "step": 3577 }, { "epoch": 0.915968, "grad_norm": 2.265625, "learning_rate": 3.4741063049227885e-05, "loss": 0.4813, "step": 3578 }, { "epoch": 0.916224, "grad_norm": 2.140625, "learning_rate": 3.473679720160396e-05, "loss": 0.5057, "step": 3579 }, { "epoch": 0.91648, "grad_norm": 2.1875, "learning_rate": 3.4732531353980034e-05, "loss": 0.5055, "step": 3580 }, { "epoch": 0.916736, "grad_norm": 2.0625, "learning_rate": 3.4728265506356115e-05, "loss": 0.488, "step": 3581 }, { "epoch": 0.916992, "grad_norm": 2.390625, "learning_rate": 3.4723999658732196e-05, "loss": 0.512, "step": 3582 }, { "epoch": 0.917248, "grad_norm": 2.421875, "learning_rate": 3.471973381110827e-05, "loss": 0.4863, "step": 3583 }, { "epoch": 0.917504, "grad_norm": 2.359375, "learning_rate": 3.4715467963484344e-05, "loss": 0.5124, "step": 3584 }, { "epoch": 0.91776, "grad_norm": 2.265625, "learning_rate": 3.4711202115860425e-05, "loss": 0.4948, "step": 3585 }, { "epoch": 0.918016, "grad_norm": 2.453125, "learning_rate": 3.47069362682365e-05, "loss": 0.5251, "step": 3586 }, { "epoch": 0.918272, "grad_norm": 2.21875, "learning_rate": 3.4702670420612574e-05, "loss": 0.4943, "step": 3587 }, { "epoch": 0.918528, "grad_norm": 2.40625, "learning_rate": 3.4698404572988655e-05, "loss": 0.5118, "step": 3588 }, { "epoch": 0.918784, "grad_norm": 2.53125, "learning_rate": 3.4694138725364736e-05, "loss": 0.5342, "step": 3589 }, { "epoch": 0.91904, "grad_norm": 2.3125, "learning_rate": 3.468987287774081e-05, "loss": 0.4604, "step": 3590 }, { "epoch": 0.919296, "grad_norm": 2.296875, "learning_rate": 3.4685607030116884e-05, "loss": 0.5024, "step": 3591 }, { "epoch": 0.919552, "grad_norm": 2.171875, "learning_rate": 3.4681341182492966e-05, "loss": 0.4688, "step": 3592 }, { "epoch": 0.919808, "grad_norm": 2.1875, "learning_rate": 3.467707533486904e-05, "loss": 0.5047, "step": 3593 }, { "epoch": 0.920064, "grad_norm": 2.3125, "learning_rate": 3.4672809487245114e-05, "loss": 0.4865, "step": 3594 }, { "epoch": 0.92032, "grad_norm": 2.390625, "learning_rate": 3.4668543639621195e-05, "loss": 0.5005, "step": 3595 }, { "epoch": 0.920576, "grad_norm": 2.4375, "learning_rate": 3.4664277791997276e-05, "loss": 0.5003, "step": 3596 }, { "epoch": 0.920832, "grad_norm": 2.359375, "learning_rate": 3.466001194437335e-05, "loss": 0.4525, "step": 3597 }, { "epoch": 0.921088, "grad_norm": 2.40625, "learning_rate": 3.4655746096749425e-05, "loss": 0.449, "step": 3598 }, { "epoch": 0.921344, "grad_norm": 2.46875, "learning_rate": 3.46514802491255e-05, "loss": 0.4993, "step": 3599 }, { "epoch": 0.9216, "grad_norm": 2.375, "learning_rate": 3.464721440150158e-05, "loss": 0.4945, "step": 3600 }, { "epoch": 0.921856, "grad_norm": 2.328125, "learning_rate": 3.464294855387766e-05, "loss": 0.5001, "step": 3601 }, { "epoch": 0.922112, "grad_norm": 2.46875, "learning_rate": 3.4638682706253735e-05, "loss": 0.5268, "step": 3602 }, { "epoch": 0.922368, "grad_norm": 2.234375, "learning_rate": 3.463441685862981e-05, "loss": 0.5231, "step": 3603 }, { "epoch": 0.922624, "grad_norm": 2.203125, "learning_rate": 3.463015101100589e-05, "loss": 0.5194, "step": 3604 }, { "epoch": 0.92288, "grad_norm": 2.3125, "learning_rate": 3.4625885163381965e-05, "loss": 0.5162, "step": 3605 }, { "epoch": 0.923136, "grad_norm": 2.375, "learning_rate": 3.462161931575804e-05, "loss": 0.4952, "step": 3606 }, { "epoch": 0.923392, "grad_norm": 2.421875, "learning_rate": 3.461735346813412e-05, "loss": 0.479, "step": 3607 }, { "epoch": 0.923648, "grad_norm": 2.328125, "learning_rate": 3.46130876205102e-05, "loss": 0.4776, "step": 3608 }, { "epoch": 0.923904, "grad_norm": 2.453125, "learning_rate": 3.4608821772886275e-05, "loss": 0.489, "step": 3609 }, { "epoch": 0.92416, "grad_norm": 2.4375, "learning_rate": 3.460455592526235e-05, "loss": 0.5242, "step": 3610 }, { "epoch": 0.924416, "grad_norm": 2.375, "learning_rate": 3.460029007763843e-05, "loss": 0.4934, "step": 3611 }, { "epoch": 0.924672, "grad_norm": 2.296875, "learning_rate": 3.4596024230014505e-05, "loss": 0.49, "step": 3612 }, { "epoch": 0.924928, "grad_norm": 2.328125, "learning_rate": 3.459175838239058e-05, "loss": 0.5136, "step": 3613 }, { "epoch": 0.925184, "grad_norm": 2.25, "learning_rate": 3.458749253476666e-05, "loss": 0.5069, "step": 3614 }, { "epoch": 0.92544, "grad_norm": 2.203125, "learning_rate": 3.458322668714274e-05, "loss": 0.5054, "step": 3615 }, { "epoch": 0.925696, "grad_norm": 2.09375, "learning_rate": 3.4578960839518816e-05, "loss": 0.4994, "step": 3616 }, { "epoch": 0.925952, "grad_norm": 2.359375, "learning_rate": 3.457469499189489e-05, "loss": 0.4913, "step": 3617 }, { "epoch": 0.926208, "grad_norm": 2.40625, "learning_rate": 3.4570429144270964e-05, "loss": 0.4965, "step": 3618 }, { "epoch": 0.926464, "grad_norm": 2.28125, "learning_rate": 3.4566163296647045e-05, "loss": 0.479, "step": 3619 }, { "epoch": 0.92672, "grad_norm": 2.21875, "learning_rate": 3.456189744902312e-05, "loss": 0.4736, "step": 3620 }, { "epoch": 0.926976, "grad_norm": 2.140625, "learning_rate": 3.45576316013992e-05, "loss": 0.4534, "step": 3621 }, { "epoch": 0.927232, "grad_norm": 2.21875, "learning_rate": 3.4553365753775275e-05, "loss": 0.492, "step": 3622 }, { "epoch": 0.927488, "grad_norm": 2.421875, "learning_rate": 3.4549099906151356e-05, "loss": 0.4713, "step": 3623 }, { "epoch": 0.927744, "grad_norm": 2.265625, "learning_rate": 3.454483405852743e-05, "loss": 0.4956, "step": 3624 }, { "epoch": 0.928, "grad_norm": 2.1875, "learning_rate": 3.4540568210903504e-05, "loss": 0.4796, "step": 3625 }, { "epoch": 0.928256, "grad_norm": 2.390625, "learning_rate": 3.4536302363279585e-05, "loss": 0.4788, "step": 3626 }, { "epoch": 0.928512, "grad_norm": 2.421875, "learning_rate": 3.4532036515655666e-05, "loss": 0.5308, "step": 3627 }, { "epoch": 0.928768, "grad_norm": 2.484375, "learning_rate": 3.452777066803174e-05, "loss": 0.4743, "step": 3628 }, { "epoch": 0.929024, "grad_norm": 2.296875, "learning_rate": 3.4523504820407815e-05, "loss": 0.4816, "step": 3629 }, { "epoch": 0.92928, "grad_norm": 2.390625, "learning_rate": 3.4519238972783896e-05, "loss": 0.4578, "step": 3630 }, { "epoch": 0.929536, "grad_norm": 2.34375, "learning_rate": 3.451497312515997e-05, "loss": 0.4856, "step": 3631 }, { "epoch": 0.929792, "grad_norm": 2.203125, "learning_rate": 3.4510707277536045e-05, "loss": 0.4729, "step": 3632 }, { "epoch": 0.930048, "grad_norm": 2.421875, "learning_rate": 3.4506441429912126e-05, "loss": 0.5034, "step": 3633 }, { "epoch": 0.930304, "grad_norm": 2.25, "learning_rate": 3.450217558228821e-05, "loss": 0.4911, "step": 3634 }, { "epoch": 0.93056, "grad_norm": 2.46875, "learning_rate": 3.449790973466428e-05, "loss": 0.4776, "step": 3635 }, { "epoch": 0.930816, "grad_norm": 2.390625, "learning_rate": 3.4493643887040355e-05, "loss": 0.4856, "step": 3636 }, { "epoch": 0.931072, "grad_norm": 2.359375, "learning_rate": 3.448937803941643e-05, "loss": 0.5012, "step": 3637 }, { "epoch": 0.931328, "grad_norm": 2.46875, "learning_rate": 3.448511219179251e-05, "loss": 0.4843, "step": 3638 }, { "epoch": 0.931584, "grad_norm": 2.28125, "learning_rate": 3.4480846344168585e-05, "loss": 0.5073, "step": 3639 }, { "epoch": 0.93184, "grad_norm": 2.171875, "learning_rate": 3.4476580496544666e-05, "loss": 0.5194, "step": 3640 }, { "epoch": 0.932096, "grad_norm": 2.328125, "learning_rate": 3.447231464892075e-05, "loss": 0.5273, "step": 3641 }, { "epoch": 0.932352, "grad_norm": 2.171875, "learning_rate": 3.446804880129682e-05, "loss": 0.5061, "step": 3642 }, { "epoch": 0.932608, "grad_norm": 2.203125, "learning_rate": 3.4463782953672895e-05, "loss": 0.5012, "step": 3643 }, { "epoch": 0.932864, "grad_norm": 2.296875, "learning_rate": 3.445951710604897e-05, "loss": 0.5347, "step": 3644 }, { "epoch": 0.93312, "grad_norm": 2.5, "learning_rate": 3.445525125842505e-05, "loss": 0.4966, "step": 3645 }, { "epoch": 0.933376, "grad_norm": 2.390625, "learning_rate": 3.445098541080113e-05, "loss": 0.5068, "step": 3646 }, { "epoch": 0.933632, "grad_norm": 2.21875, "learning_rate": 3.4446719563177206e-05, "loss": 0.5329, "step": 3647 }, { "epoch": 0.933888, "grad_norm": 2.25, "learning_rate": 3.444245371555328e-05, "loss": 0.5054, "step": 3648 }, { "epoch": 0.934144, "grad_norm": 2.453125, "learning_rate": 3.443818786792936e-05, "loss": 0.5273, "step": 3649 }, { "epoch": 0.9344, "grad_norm": 2.34375, "learning_rate": 3.4433922020305436e-05, "loss": 0.5032, "step": 3650 }, { "epoch": 0.934656, "grad_norm": 2.25, "learning_rate": 3.442965617268151e-05, "loss": 0.536, "step": 3651 }, { "epoch": 0.934912, "grad_norm": 2.109375, "learning_rate": 3.442539032505759e-05, "loss": 0.4991, "step": 3652 }, { "epoch": 0.935168, "grad_norm": 2.1875, "learning_rate": 3.442112447743367e-05, "loss": 0.5286, "step": 3653 }, { "epoch": 0.935424, "grad_norm": 2.234375, "learning_rate": 3.4416858629809746e-05, "loss": 0.504, "step": 3654 }, { "epoch": 0.93568, "grad_norm": 2.265625, "learning_rate": 3.441259278218582e-05, "loss": 0.5213, "step": 3655 }, { "epoch": 0.935936, "grad_norm": 2.328125, "learning_rate": 3.4408326934561895e-05, "loss": 0.5401, "step": 3656 }, { "epoch": 0.936192, "grad_norm": 2.28125, "learning_rate": 3.4404061086937976e-05, "loss": 0.5408, "step": 3657 }, { "epoch": 0.936448, "grad_norm": 2.078125, "learning_rate": 3.439979523931405e-05, "loss": 0.4846, "step": 3658 }, { "epoch": 0.936704, "grad_norm": 2.296875, "learning_rate": 3.439552939169013e-05, "loss": 0.4782, "step": 3659 }, { "epoch": 0.93696, "grad_norm": 2.5, "learning_rate": 3.439126354406621e-05, "loss": 0.5549, "step": 3660 }, { "epoch": 0.937216, "grad_norm": 2.390625, "learning_rate": 3.4386997696442286e-05, "loss": 0.4995, "step": 3661 }, { "epoch": 0.937472, "grad_norm": 2.171875, "learning_rate": 3.438273184881836e-05, "loss": 0.4724, "step": 3662 }, { "epoch": 0.937728, "grad_norm": 2.390625, "learning_rate": 3.4378466001194435e-05, "loss": 0.5064, "step": 3663 }, { "epoch": 0.937984, "grad_norm": 2.21875, "learning_rate": 3.4374200153570516e-05, "loss": 0.5121, "step": 3664 }, { "epoch": 0.93824, "grad_norm": 2.203125, "learning_rate": 3.43699343059466e-05, "loss": 0.4872, "step": 3665 }, { "epoch": 0.938496, "grad_norm": 2.21875, "learning_rate": 3.436566845832267e-05, "loss": 0.5006, "step": 3666 }, { "epoch": 0.938752, "grad_norm": 2.40625, "learning_rate": 3.4361402610698746e-05, "loss": 0.4882, "step": 3667 }, { "epoch": 0.939008, "grad_norm": 2.34375, "learning_rate": 3.435713676307483e-05, "loss": 0.4967, "step": 3668 }, { "epoch": 0.939264, "grad_norm": 2.15625, "learning_rate": 3.43528709154509e-05, "loss": 0.4667, "step": 3669 }, { "epoch": 0.93952, "grad_norm": 2.109375, "learning_rate": 3.4348605067826975e-05, "loss": 0.4785, "step": 3670 }, { "epoch": 0.939776, "grad_norm": 2.171875, "learning_rate": 3.4344339220203056e-05, "loss": 0.5218, "step": 3671 }, { "epoch": 0.940032, "grad_norm": 2.28125, "learning_rate": 3.434007337257914e-05, "loss": 0.5074, "step": 3672 }, { "epoch": 0.940288, "grad_norm": 2.1875, "learning_rate": 3.433580752495521e-05, "loss": 0.4702, "step": 3673 }, { "epoch": 0.940544, "grad_norm": 2.3125, "learning_rate": 3.4331541677331286e-05, "loss": 0.4992, "step": 3674 }, { "epoch": 0.9408, "grad_norm": 2.234375, "learning_rate": 3.432727582970737e-05, "loss": 0.4896, "step": 3675 }, { "epoch": 0.941056, "grad_norm": 2.359375, "learning_rate": 3.432300998208344e-05, "loss": 0.503, "step": 3676 }, { "epoch": 0.941312, "grad_norm": 2.421875, "learning_rate": 3.4318744134459515e-05, "loss": 0.4892, "step": 3677 }, { "epoch": 0.941568, "grad_norm": 2.359375, "learning_rate": 3.4314478286835596e-05, "loss": 0.5493, "step": 3678 }, { "epoch": 0.941824, "grad_norm": 2.109375, "learning_rate": 3.431021243921168e-05, "loss": 0.5078, "step": 3679 }, { "epoch": 0.94208, "grad_norm": 2.25, "learning_rate": 3.430594659158775e-05, "loss": 0.471, "step": 3680 }, { "epoch": 0.942336, "grad_norm": 2.5625, "learning_rate": 3.4301680743963826e-05, "loss": 0.5019, "step": 3681 }, { "epoch": 0.942592, "grad_norm": 2.625, "learning_rate": 3.42974148963399e-05, "loss": 0.4878, "step": 3682 }, { "epoch": 0.942848, "grad_norm": 2.375, "learning_rate": 3.429314904871598e-05, "loss": 0.5249, "step": 3683 }, { "epoch": 0.943104, "grad_norm": 2.09375, "learning_rate": 3.428888320109206e-05, "loss": 0.5024, "step": 3684 }, { "epoch": 0.94336, "grad_norm": 2.390625, "learning_rate": 3.4284617353468137e-05, "loss": 0.5189, "step": 3685 }, { "epoch": 0.943616, "grad_norm": 2.46875, "learning_rate": 3.428035150584421e-05, "loss": 0.4771, "step": 3686 }, { "epoch": 0.943872, "grad_norm": 2.453125, "learning_rate": 3.427608565822029e-05, "loss": 0.4424, "step": 3687 }, { "epoch": 0.944128, "grad_norm": 2.21875, "learning_rate": 3.4271819810596366e-05, "loss": 0.508, "step": 3688 }, { "epoch": 0.944384, "grad_norm": 2.359375, "learning_rate": 3.426755396297244e-05, "loss": 0.4929, "step": 3689 }, { "epoch": 0.94464, "grad_norm": 2.453125, "learning_rate": 3.426328811534852e-05, "loss": 0.4641, "step": 3690 }, { "epoch": 0.944896, "grad_norm": 2.421875, "learning_rate": 3.42590222677246e-05, "loss": 0.5017, "step": 3691 }, { "epoch": 0.945152, "grad_norm": 2.375, "learning_rate": 3.425475642010068e-05, "loss": 0.5205, "step": 3692 }, { "epoch": 0.945408, "grad_norm": 2.390625, "learning_rate": 3.425049057247675e-05, "loss": 0.5188, "step": 3693 }, { "epoch": 0.945664, "grad_norm": 2.4375, "learning_rate": 3.424622472485283e-05, "loss": 0.4933, "step": 3694 }, { "epoch": 0.94592, "grad_norm": 2.25, "learning_rate": 3.4241958877228906e-05, "loss": 0.4986, "step": 3695 }, { "epoch": 0.946176, "grad_norm": 2.296875, "learning_rate": 3.423769302960498e-05, "loss": 0.5263, "step": 3696 }, { "epoch": 0.946432, "grad_norm": 2.46875, "learning_rate": 3.423342718198106e-05, "loss": 0.5318, "step": 3697 }, { "epoch": 0.946688, "grad_norm": 2.125, "learning_rate": 3.422916133435714e-05, "loss": 0.543, "step": 3698 }, { "epoch": 0.946944, "grad_norm": 2.515625, "learning_rate": 3.422489548673322e-05, "loss": 0.4567, "step": 3699 }, { "epoch": 0.9472, "grad_norm": 2.4375, "learning_rate": 3.422062963910929e-05, "loss": 0.5252, "step": 3700 }, { "epoch": 0.947456, "grad_norm": 2.609375, "learning_rate": 3.4216363791485365e-05, "loss": 0.5084, "step": 3701 }, { "epoch": 0.947712, "grad_norm": 2.15625, "learning_rate": 3.4212097943861447e-05, "loss": 0.4985, "step": 3702 }, { "epoch": 0.947968, "grad_norm": 2.265625, "learning_rate": 3.420783209623753e-05, "loss": 0.4821, "step": 3703 }, { "epoch": 0.948224, "grad_norm": 2.421875, "learning_rate": 3.42035662486136e-05, "loss": 0.5087, "step": 3704 }, { "epoch": 0.94848, "grad_norm": 2.25, "learning_rate": 3.4199300400989676e-05, "loss": 0.4975, "step": 3705 }, { "epoch": 0.948736, "grad_norm": 2.25, "learning_rate": 3.419503455336576e-05, "loss": 0.4862, "step": 3706 }, { "epoch": 0.948992, "grad_norm": 2.359375, "learning_rate": 3.419076870574183e-05, "loss": 0.5231, "step": 3707 }, { "epoch": 0.949248, "grad_norm": 2.375, "learning_rate": 3.4186502858117906e-05, "loss": 0.4936, "step": 3708 }, { "epoch": 0.949504, "grad_norm": 2.203125, "learning_rate": 3.418223701049399e-05, "loss": 0.4622, "step": 3709 }, { "epoch": 0.94976, "grad_norm": 2.25, "learning_rate": 3.417797116287007e-05, "loss": 0.4737, "step": 3710 }, { "epoch": 0.950016, "grad_norm": 2.234375, "learning_rate": 3.417370531524614e-05, "loss": 0.4479, "step": 3711 }, { "epoch": 0.950272, "grad_norm": 2.5, "learning_rate": 3.4169439467622216e-05, "loss": 0.4685, "step": 3712 }, { "epoch": 0.950528, "grad_norm": 2.34375, "learning_rate": 3.41651736199983e-05, "loss": 0.5163, "step": 3713 }, { "epoch": 0.950784, "grad_norm": 2.171875, "learning_rate": 3.416090777237437e-05, "loss": 0.4898, "step": 3714 }, { "epoch": 0.95104, "grad_norm": 2.265625, "learning_rate": 3.4156641924750446e-05, "loss": 0.4809, "step": 3715 }, { "epoch": 0.951296, "grad_norm": 2.34375, "learning_rate": 3.415237607712653e-05, "loss": 0.4931, "step": 3716 }, { "epoch": 0.951552, "grad_norm": 2.25, "learning_rate": 3.414811022950261e-05, "loss": 0.464, "step": 3717 }, { "epoch": 0.951808, "grad_norm": 2.265625, "learning_rate": 3.414384438187868e-05, "loss": 0.4884, "step": 3718 }, { "epoch": 0.952064, "grad_norm": 2.3125, "learning_rate": 3.4139578534254756e-05, "loss": 0.4813, "step": 3719 }, { "epoch": 0.95232, "grad_norm": 2.265625, "learning_rate": 3.413531268663083e-05, "loss": 0.4804, "step": 3720 }, { "epoch": 0.952576, "grad_norm": 2.15625, "learning_rate": 3.413104683900691e-05, "loss": 0.541, "step": 3721 }, { "epoch": 0.952832, "grad_norm": 2.359375, "learning_rate": 3.4126780991382986e-05, "loss": 0.5281, "step": 3722 }, { "epoch": 0.953088, "grad_norm": 2.1875, "learning_rate": 3.412251514375907e-05, "loss": 0.5242, "step": 3723 }, { "epoch": 0.953344, "grad_norm": 2.15625, "learning_rate": 3.411824929613515e-05, "loss": 0.4404, "step": 3724 }, { "epoch": 0.9536, "grad_norm": 2.140625, "learning_rate": 3.411398344851122e-05, "loss": 0.4791, "step": 3725 }, { "epoch": 0.953856, "grad_norm": 2.234375, "learning_rate": 3.41097176008873e-05, "loss": 0.4851, "step": 3726 }, { "epoch": 0.954112, "grad_norm": 2.296875, "learning_rate": 3.410545175326337e-05, "loss": 0.4631, "step": 3727 }, { "epoch": 0.954368, "grad_norm": 2.046875, "learning_rate": 3.410118590563945e-05, "loss": 0.5158, "step": 3728 }, { "epoch": 0.954624, "grad_norm": 2.3125, "learning_rate": 3.409692005801553e-05, "loss": 0.5201, "step": 3729 }, { "epoch": 0.95488, "grad_norm": 2.609375, "learning_rate": 3.409265421039161e-05, "loss": 0.5134, "step": 3730 }, { "epoch": 0.955136, "grad_norm": 2.359375, "learning_rate": 3.408838836276768e-05, "loss": 0.4847, "step": 3731 }, { "epoch": 0.955392, "grad_norm": 2.203125, "learning_rate": 3.408412251514376e-05, "loss": 0.469, "step": 3732 }, { "epoch": 0.955648, "grad_norm": 2.140625, "learning_rate": 3.407985666751984e-05, "loss": 0.5211, "step": 3733 }, { "epoch": 0.955904, "grad_norm": 2.296875, "learning_rate": 3.407559081989591e-05, "loss": 0.5048, "step": 3734 }, { "epoch": 0.95616, "grad_norm": 2.484375, "learning_rate": 3.407132497227199e-05, "loss": 0.5183, "step": 3735 }, { "epoch": 0.956416, "grad_norm": 2.375, "learning_rate": 3.406705912464807e-05, "loss": 0.4729, "step": 3736 }, { "epoch": 0.956672, "grad_norm": 2.09375, "learning_rate": 3.406279327702415e-05, "loss": 0.5088, "step": 3737 }, { "epoch": 0.956928, "grad_norm": 2.34375, "learning_rate": 3.405852742940022e-05, "loss": 0.4899, "step": 3738 }, { "epoch": 0.957184, "grad_norm": 2.28125, "learning_rate": 3.40542615817763e-05, "loss": 0.491, "step": 3739 }, { "epoch": 0.95744, "grad_norm": 2.484375, "learning_rate": 3.404999573415238e-05, "loss": 0.4751, "step": 3740 }, { "epoch": 0.957696, "grad_norm": 2.5625, "learning_rate": 3.404572988652845e-05, "loss": 0.5244, "step": 3741 }, { "epoch": 0.957952, "grad_norm": 2.3125, "learning_rate": 3.404146403890453e-05, "loss": 0.4982, "step": 3742 }, { "epoch": 0.958208, "grad_norm": 2.5625, "learning_rate": 3.4037198191280613e-05, "loss": 0.5011, "step": 3743 }, { "epoch": 0.958464, "grad_norm": 2.21875, "learning_rate": 3.403293234365669e-05, "loss": 0.4931, "step": 3744 }, { "epoch": 0.95872, "grad_norm": 2.453125, "learning_rate": 3.402866649603276e-05, "loss": 0.4854, "step": 3745 }, { "epoch": 0.958976, "grad_norm": 2.359375, "learning_rate": 3.4024400648408836e-05, "loss": 0.5265, "step": 3746 }, { "epoch": 0.959232, "grad_norm": 2.453125, "learning_rate": 3.402013480078492e-05, "loss": 0.5248, "step": 3747 }, { "epoch": 0.959488, "grad_norm": 2.34375, "learning_rate": 3.4015868953161e-05, "loss": 0.4575, "step": 3748 }, { "epoch": 0.959744, "grad_norm": 2.453125, "learning_rate": 3.401160310553707e-05, "loss": 0.4426, "step": 3749 }, { "epoch": 0.96, "grad_norm": 2.328125, "learning_rate": 3.400733725791315e-05, "loss": 0.4648, "step": 3750 }, { "epoch": 0.960256, "grad_norm": 2.328125, "learning_rate": 3.400307141028923e-05, "loss": 0.4572, "step": 3751 }, { "epoch": 0.960512, "grad_norm": 2.40625, "learning_rate": 3.39988055626653e-05, "loss": 0.491, "step": 3752 }, { "epoch": 0.960768, "grad_norm": 2.078125, "learning_rate": 3.3994539715041376e-05, "loss": 0.5035, "step": 3753 }, { "epoch": 0.961024, "grad_norm": 2.21875, "learning_rate": 3.399027386741746e-05, "loss": 0.4903, "step": 3754 }, { "epoch": 0.96128, "grad_norm": 2.28125, "learning_rate": 3.398600801979354e-05, "loss": 0.5152, "step": 3755 }, { "epoch": 0.961536, "grad_norm": 2.359375, "learning_rate": 3.398174217216961e-05, "loss": 0.482, "step": 3756 }, { "epoch": 0.961792, "grad_norm": 2.21875, "learning_rate": 3.397747632454569e-05, "loss": 0.5078, "step": 3757 }, { "epoch": 0.962048, "grad_norm": 2.078125, "learning_rate": 3.397321047692177e-05, "loss": 0.4853, "step": 3758 }, { "epoch": 0.962304, "grad_norm": 2.328125, "learning_rate": 3.396894462929784e-05, "loss": 0.475, "step": 3759 }, { "epoch": 0.96256, "grad_norm": 2.21875, "learning_rate": 3.396467878167392e-05, "loss": 0.5144, "step": 3760 }, { "epoch": 0.962816, "grad_norm": 2.4375, "learning_rate": 3.396041293405e-05, "loss": 0.4641, "step": 3761 }, { "epoch": 0.963072, "grad_norm": 2.328125, "learning_rate": 3.395614708642608e-05, "loss": 0.4806, "step": 3762 }, { "epoch": 0.963328, "grad_norm": 2.390625, "learning_rate": 3.395188123880215e-05, "loss": 0.4823, "step": 3763 }, { "epoch": 0.963584, "grad_norm": 2.28125, "learning_rate": 3.394761539117823e-05, "loss": 0.5207, "step": 3764 }, { "epoch": 0.96384, "grad_norm": 2.578125, "learning_rate": 3.39433495435543e-05, "loss": 0.4859, "step": 3765 }, { "epoch": 0.964096, "grad_norm": 2.4375, "learning_rate": 3.393908369593038e-05, "loss": 0.4846, "step": 3766 }, { "epoch": 0.964352, "grad_norm": 2.265625, "learning_rate": 3.3934817848306464e-05, "loss": 0.4818, "step": 3767 }, { "epoch": 0.964608, "grad_norm": 2.40625, "learning_rate": 3.393055200068254e-05, "loss": 0.465, "step": 3768 }, { "epoch": 0.964864, "grad_norm": 2.421875, "learning_rate": 3.392628615305861e-05, "loss": 0.512, "step": 3769 }, { "epoch": 0.96512, "grad_norm": 2.390625, "learning_rate": 3.392202030543469e-05, "loss": 0.505, "step": 3770 }, { "epoch": 0.965376, "grad_norm": 2.484375, "learning_rate": 3.391775445781077e-05, "loss": 0.4837, "step": 3771 }, { "epoch": 0.965632, "grad_norm": 2.234375, "learning_rate": 3.391348861018684e-05, "loss": 0.4932, "step": 3772 }, { "epoch": 0.965888, "grad_norm": 2.296875, "learning_rate": 3.390922276256292e-05, "loss": 0.4995, "step": 3773 }, { "epoch": 0.966144, "grad_norm": 2.25, "learning_rate": 3.3904956914939004e-05, "loss": 0.5137, "step": 3774 }, { "epoch": 0.9664, "grad_norm": 2.25, "learning_rate": 3.390069106731508e-05, "loss": 0.5027, "step": 3775 }, { "epoch": 0.966656, "grad_norm": 2.125, "learning_rate": 3.389642521969115e-05, "loss": 0.4823, "step": 3776 }, { "epoch": 0.966912, "grad_norm": 2.421875, "learning_rate": 3.389215937206723e-05, "loss": 0.5013, "step": 3777 }, { "epoch": 0.967168, "grad_norm": 2.390625, "learning_rate": 3.388789352444331e-05, "loss": 0.4811, "step": 3778 }, { "epoch": 0.967424, "grad_norm": 2.09375, "learning_rate": 3.388362767681938e-05, "loss": 0.503, "step": 3779 }, { "epoch": 0.96768, "grad_norm": 2.359375, "learning_rate": 3.387936182919546e-05, "loss": 0.4709, "step": 3780 }, { "epoch": 0.967936, "grad_norm": 2.25, "learning_rate": 3.3875095981571544e-05, "loss": 0.5062, "step": 3781 }, { "epoch": 0.968192, "grad_norm": 2.15625, "learning_rate": 3.387083013394762e-05, "loss": 0.5032, "step": 3782 }, { "epoch": 0.968448, "grad_norm": 2.125, "learning_rate": 3.386656428632369e-05, "loss": 0.5072, "step": 3783 }, { "epoch": 0.968704, "grad_norm": 2.34375, "learning_rate": 3.386229843869977e-05, "loss": 0.528, "step": 3784 }, { "epoch": 0.96896, "grad_norm": 2.46875, "learning_rate": 3.385803259107585e-05, "loss": 0.4822, "step": 3785 }, { "epoch": 0.969216, "grad_norm": 2.28125, "learning_rate": 3.385376674345193e-05, "loss": 0.5497, "step": 3786 }, { "epoch": 0.969472, "grad_norm": 2.28125, "learning_rate": 3.3849500895828e-05, "loss": 0.5051, "step": 3787 }, { "epoch": 0.969728, "grad_norm": 2.296875, "learning_rate": 3.3845235048204084e-05, "loss": 0.4726, "step": 3788 }, { "epoch": 0.969984, "grad_norm": 2.515625, "learning_rate": 3.384096920058016e-05, "loss": 0.4972, "step": 3789 }, { "epoch": 0.97024, "grad_norm": 2.421875, "learning_rate": 3.383670335295623e-05, "loss": 0.4859, "step": 3790 }, { "epoch": 0.970496, "grad_norm": 2.421875, "learning_rate": 3.383243750533231e-05, "loss": 0.4885, "step": 3791 }, { "epoch": 0.970752, "grad_norm": 2.25, "learning_rate": 3.382817165770839e-05, "loss": 0.5295, "step": 3792 }, { "epoch": 0.971008, "grad_norm": 2.171875, "learning_rate": 3.382390581008447e-05, "loss": 0.4624, "step": 3793 }, { "epoch": 0.971264, "grad_norm": 2.328125, "learning_rate": 3.381963996246054e-05, "loss": 0.4893, "step": 3794 }, { "epoch": 0.97152, "grad_norm": 2.21875, "learning_rate": 3.381537411483662e-05, "loss": 0.4772, "step": 3795 }, { "epoch": 0.971776, "grad_norm": 2.25, "learning_rate": 3.38111082672127e-05, "loss": 0.4792, "step": 3796 }, { "epoch": 0.972032, "grad_norm": 2.265625, "learning_rate": 3.380684241958877e-05, "loss": 0.4879, "step": 3797 }, { "epoch": 0.972288, "grad_norm": 2.265625, "learning_rate": 3.380257657196485e-05, "loss": 0.5034, "step": 3798 }, { "epoch": 0.972544, "grad_norm": 2.3125, "learning_rate": 3.379831072434093e-05, "loss": 0.4929, "step": 3799 }, { "epoch": 0.9728, "grad_norm": 2.21875, "learning_rate": 3.379404487671701e-05, "loss": 0.4642, "step": 3800 }, { "epoch": 0.973056, "grad_norm": 2.15625, "learning_rate": 3.3789779029093084e-05, "loss": 0.4636, "step": 3801 }, { "epoch": 0.973312, "grad_norm": 2.328125, "learning_rate": 3.378551318146916e-05, "loss": 0.4853, "step": 3802 }, { "epoch": 0.973568, "grad_norm": 2.3125, "learning_rate": 3.378124733384523e-05, "loss": 0.4819, "step": 3803 }, { "epoch": 0.973824, "grad_norm": 2.21875, "learning_rate": 3.377698148622131e-05, "loss": 0.517, "step": 3804 }, { "epoch": 0.97408, "grad_norm": 2.28125, "learning_rate": 3.3772715638597394e-05, "loss": 0.5027, "step": 3805 }, { "epoch": 0.974336, "grad_norm": 2.484375, "learning_rate": 3.376844979097347e-05, "loss": 0.4886, "step": 3806 }, { "epoch": 0.974592, "grad_norm": 2.390625, "learning_rate": 3.376418394334955e-05, "loss": 0.5149, "step": 3807 }, { "epoch": 0.974848, "grad_norm": 2.421875, "learning_rate": 3.3759918095725624e-05, "loss": 0.4779, "step": 3808 }, { "epoch": 0.975104, "grad_norm": 2.40625, "learning_rate": 3.37556522481017e-05, "loss": 0.4909, "step": 3809 }, { "epoch": 0.97536, "grad_norm": 2.25, "learning_rate": 3.375138640047777e-05, "loss": 0.4432, "step": 3810 }, { "epoch": 0.975616, "grad_norm": 2.375, "learning_rate": 3.374712055285385e-05, "loss": 0.5014, "step": 3811 }, { "epoch": 0.975872, "grad_norm": 2.578125, "learning_rate": 3.3742854705229934e-05, "loss": 0.5047, "step": 3812 }, { "epoch": 0.976128, "grad_norm": 2.40625, "learning_rate": 3.373858885760601e-05, "loss": 0.4991, "step": 3813 }, { "epoch": 0.976384, "grad_norm": 2.234375, "learning_rate": 3.373432300998208e-05, "loss": 0.5027, "step": 3814 }, { "epoch": 0.97664, "grad_norm": 2.171875, "learning_rate": 3.3730057162358164e-05, "loss": 0.4926, "step": 3815 }, { "epoch": 0.976896, "grad_norm": 2.3125, "learning_rate": 3.372579131473424e-05, "loss": 0.5128, "step": 3816 }, { "epoch": 0.977152, "grad_norm": 2.171875, "learning_rate": 3.372152546711031e-05, "loss": 0.4604, "step": 3817 }, { "epoch": 0.977408, "grad_norm": 2.421875, "learning_rate": 3.3717259619486393e-05, "loss": 0.5114, "step": 3818 }, { "epoch": 0.977664, "grad_norm": 2.5, "learning_rate": 3.3712993771862475e-05, "loss": 0.4743, "step": 3819 }, { "epoch": 0.97792, "grad_norm": 2.65625, "learning_rate": 3.370872792423855e-05, "loss": 0.5018, "step": 3820 }, { "epoch": 0.978176, "grad_norm": 2.234375, "learning_rate": 3.370446207661462e-05, "loss": 0.4654, "step": 3821 }, { "epoch": 0.978432, "grad_norm": 2.09375, "learning_rate": 3.3700196228990704e-05, "loss": 0.4847, "step": 3822 }, { "epoch": 0.978688, "grad_norm": 2.515625, "learning_rate": 3.369593038136678e-05, "loss": 0.4516, "step": 3823 }, { "epoch": 0.978944, "grad_norm": 2.671875, "learning_rate": 3.369166453374286e-05, "loss": 0.4869, "step": 3824 }, { "epoch": 0.9792, "grad_norm": 2.421875, "learning_rate": 3.3687398686118934e-05, "loss": 0.4876, "step": 3825 }, { "epoch": 0.979456, "grad_norm": 2.421875, "learning_rate": 3.3683132838495015e-05, "loss": 0.4621, "step": 3826 }, { "epoch": 0.979712, "grad_norm": 2.21875, "learning_rate": 3.367886699087109e-05, "loss": 0.4587, "step": 3827 }, { "epoch": 0.979968, "grad_norm": 2.421875, "learning_rate": 3.367460114324716e-05, "loss": 0.4467, "step": 3828 }, { "epoch": 0.980224, "grad_norm": 2.359375, "learning_rate": 3.367033529562324e-05, "loss": 0.5063, "step": 3829 }, { "epoch": 0.98048, "grad_norm": 2.390625, "learning_rate": 3.366606944799932e-05, "loss": 0.4589, "step": 3830 }, { "epoch": 0.980736, "grad_norm": 2.15625, "learning_rate": 3.36618036003754e-05, "loss": 0.5155, "step": 3831 }, { "epoch": 0.980992, "grad_norm": 2.234375, "learning_rate": 3.3657537752751474e-05, "loss": 0.4778, "step": 3832 }, { "epoch": 0.981248, "grad_norm": 2.25, "learning_rate": 3.365327190512755e-05, "loss": 0.5174, "step": 3833 }, { "epoch": 0.981504, "grad_norm": 2.40625, "learning_rate": 3.364900605750363e-05, "loss": 0.4958, "step": 3834 }, { "epoch": 0.98176, "grad_norm": 2.28125, "learning_rate": 3.3644740209879703e-05, "loss": 0.5073, "step": 3835 }, { "epoch": 0.982016, "grad_norm": 2.46875, "learning_rate": 3.364047436225578e-05, "loss": 0.4638, "step": 3836 }, { "epoch": 0.982272, "grad_norm": 2.515625, "learning_rate": 3.363620851463186e-05, "loss": 0.4525, "step": 3837 }, { "epoch": 0.982528, "grad_norm": 2.25, "learning_rate": 3.363194266700794e-05, "loss": 0.5202, "step": 3838 }, { "epoch": 0.982784, "grad_norm": 2.234375, "learning_rate": 3.3627676819384014e-05, "loss": 0.4964, "step": 3839 }, { "epoch": 0.98304, "grad_norm": 2.375, "learning_rate": 3.362341097176009e-05, "loss": 0.5015, "step": 3840 }, { "epoch": 0.983296, "grad_norm": 2.484375, "learning_rate": 3.361914512413617e-05, "loss": 0.488, "step": 3841 }, { "epoch": 0.983552, "grad_norm": 2.296875, "learning_rate": 3.3614879276512244e-05, "loss": 0.4964, "step": 3842 }, { "epoch": 0.983808, "grad_norm": 2.3125, "learning_rate": 3.361061342888832e-05, "loss": 0.4957, "step": 3843 }, { "epoch": 0.984064, "grad_norm": 2.46875, "learning_rate": 3.36063475812644e-05, "loss": 0.5118, "step": 3844 }, { "epoch": 0.98432, "grad_norm": 2.265625, "learning_rate": 3.360208173364048e-05, "loss": 0.4672, "step": 3845 }, { "epoch": 0.984576, "grad_norm": 2.265625, "learning_rate": 3.3597815886016554e-05, "loss": 0.4896, "step": 3846 }, { "epoch": 0.984832, "grad_norm": 2.359375, "learning_rate": 3.359355003839263e-05, "loss": 0.5131, "step": 3847 }, { "epoch": 0.985088, "grad_norm": 2.0625, "learning_rate": 3.35892841907687e-05, "loss": 0.5008, "step": 3848 }, { "epoch": 0.985344, "grad_norm": 2.3125, "learning_rate": 3.3585018343144784e-05, "loss": 0.4959, "step": 3849 }, { "epoch": 0.9856, "grad_norm": 2.28125, "learning_rate": 3.3580752495520865e-05, "loss": 0.48, "step": 3850 }, { "epoch": 0.985856, "grad_norm": 2.234375, "learning_rate": 3.357648664789694e-05, "loss": 0.5099, "step": 3851 }, { "epoch": 0.986112, "grad_norm": 2.3125, "learning_rate": 3.357222080027301e-05, "loss": 0.4735, "step": 3852 }, { "epoch": 0.986368, "grad_norm": 2.328125, "learning_rate": 3.3567954952649094e-05, "loss": 0.4815, "step": 3853 }, { "epoch": 0.986624, "grad_norm": 2.609375, "learning_rate": 3.356368910502517e-05, "loss": 0.4867, "step": 3854 }, { "epoch": 0.98688, "grad_norm": 2.171875, "learning_rate": 3.355942325740124e-05, "loss": 0.5005, "step": 3855 }, { "epoch": 0.987136, "grad_norm": 2.09375, "learning_rate": 3.3555157409777324e-05, "loss": 0.5434, "step": 3856 }, { "epoch": 0.987392, "grad_norm": 2.203125, "learning_rate": 3.3550891562153405e-05, "loss": 0.4612, "step": 3857 }, { "epoch": 0.987648, "grad_norm": 2.296875, "learning_rate": 3.354662571452948e-05, "loss": 0.4804, "step": 3858 }, { "epoch": 0.987904, "grad_norm": 2.171875, "learning_rate": 3.3542359866905554e-05, "loss": 0.485, "step": 3859 }, { "epoch": 0.98816, "grad_norm": 2.234375, "learning_rate": 3.3538094019281635e-05, "loss": 0.4789, "step": 3860 }, { "epoch": 0.988416, "grad_norm": 2.28125, "learning_rate": 3.353382817165771e-05, "loss": 0.4731, "step": 3861 }, { "epoch": 0.988672, "grad_norm": 2.015625, "learning_rate": 3.352956232403378e-05, "loss": 0.4701, "step": 3862 }, { "epoch": 0.988928, "grad_norm": 2.125, "learning_rate": 3.3525296476409864e-05, "loss": 0.4775, "step": 3863 }, { "epoch": 0.989184, "grad_norm": 2.125, "learning_rate": 3.3521030628785945e-05, "loss": 0.4985, "step": 3864 }, { "epoch": 0.98944, "grad_norm": 2.21875, "learning_rate": 3.351676478116202e-05, "loss": 0.4636, "step": 3865 }, { "epoch": 0.989696, "grad_norm": 1.984375, "learning_rate": 3.3512498933538094e-05, "loss": 0.5203, "step": 3866 }, { "epoch": 0.989952, "grad_norm": 2.3125, "learning_rate": 3.350823308591417e-05, "loss": 0.4858, "step": 3867 }, { "epoch": 0.990208, "grad_norm": 2.15625, "learning_rate": 3.350396723829025e-05, "loss": 0.5072, "step": 3868 }, { "epoch": 0.990464, "grad_norm": 2.34375, "learning_rate": 3.349970139066633e-05, "loss": 0.4969, "step": 3869 }, { "epoch": 0.99072, "grad_norm": 2.34375, "learning_rate": 3.3495435543042404e-05, "loss": 0.4636, "step": 3870 }, { "epoch": 0.990976, "grad_norm": 2.421875, "learning_rate": 3.3491169695418485e-05, "loss": 0.4846, "step": 3871 }, { "epoch": 0.991232, "grad_norm": 2.421875, "learning_rate": 3.348690384779456e-05, "loss": 0.4855, "step": 3872 }, { "epoch": 0.991488, "grad_norm": 2.296875, "learning_rate": 3.3482638000170634e-05, "loss": 0.5011, "step": 3873 }, { "epoch": 0.991744, "grad_norm": 2.296875, "learning_rate": 3.347837215254671e-05, "loss": 0.4817, "step": 3874 }, { "epoch": 0.992, "grad_norm": 2.375, "learning_rate": 3.347410630492279e-05, "loss": 0.4965, "step": 3875 }, { "epoch": 0.992256, "grad_norm": 2.4375, "learning_rate": 3.346984045729887e-05, "loss": 0.4626, "step": 3876 }, { "epoch": 0.992512, "grad_norm": 2.546875, "learning_rate": 3.3465574609674945e-05, "loss": 0.4998, "step": 3877 }, { "epoch": 0.992768, "grad_norm": 2.265625, "learning_rate": 3.346130876205102e-05, "loss": 0.5193, "step": 3878 }, { "epoch": 0.993024, "grad_norm": 2.078125, "learning_rate": 3.34570429144271e-05, "loss": 0.506, "step": 3879 }, { "epoch": 0.99328, "grad_norm": 2.234375, "learning_rate": 3.3452777066803174e-05, "loss": 0.5095, "step": 3880 }, { "epoch": 0.993536, "grad_norm": 2.3125, "learning_rate": 3.344851121917925e-05, "loss": 0.5032, "step": 3881 }, { "epoch": 0.993792, "grad_norm": 2.390625, "learning_rate": 3.344424537155533e-05, "loss": 0.4633, "step": 3882 }, { "epoch": 0.994048, "grad_norm": 2.078125, "learning_rate": 3.343997952393141e-05, "loss": 0.47, "step": 3883 }, { "epoch": 0.994304, "grad_norm": 2.046875, "learning_rate": 3.3435713676307485e-05, "loss": 0.4759, "step": 3884 }, { "epoch": 0.99456, "grad_norm": 2.421875, "learning_rate": 3.343144782868356e-05, "loss": 0.4414, "step": 3885 }, { "epoch": 0.994816, "grad_norm": 2.28125, "learning_rate": 3.342718198105963e-05, "loss": 0.4538, "step": 3886 }, { "epoch": 0.995072, "grad_norm": 2.28125, "learning_rate": 3.3422916133435714e-05, "loss": 0.47, "step": 3887 }, { "epoch": 0.995328, "grad_norm": 2.1875, "learning_rate": 3.3418650285811795e-05, "loss": 0.482, "step": 3888 }, { "epoch": 0.995584, "grad_norm": 2.234375, "learning_rate": 3.341438443818787e-05, "loss": 0.4839, "step": 3889 }, { "epoch": 0.99584, "grad_norm": 2.578125, "learning_rate": 3.341011859056395e-05, "loss": 0.4781, "step": 3890 }, { "epoch": 0.996096, "grad_norm": 2.5, "learning_rate": 3.3405852742940025e-05, "loss": 0.4726, "step": 3891 }, { "epoch": 0.996352, "grad_norm": 2.40625, "learning_rate": 3.34015868953161e-05, "loss": 0.4316, "step": 3892 }, { "epoch": 0.996608, "grad_norm": 2.234375, "learning_rate": 3.3397321047692174e-05, "loss": 0.4763, "step": 3893 }, { "epoch": 0.996864, "grad_norm": 2.296875, "learning_rate": 3.3393055200068255e-05, "loss": 0.5042, "step": 3894 }, { "epoch": 0.99712, "grad_norm": 2.609375, "learning_rate": 3.3388789352444336e-05, "loss": 0.5116, "step": 3895 }, { "epoch": 0.997376, "grad_norm": 2.375, "learning_rate": 3.338452350482041e-05, "loss": 0.4846, "step": 3896 }, { "epoch": 0.997632, "grad_norm": 2.359375, "learning_rate": 3.3380257657196484e-05, "loss": 0.4934, "step": 3897 }, { "epoch": 0.997888, "grad_norm": 2.296875, "learning_rate": 3.3375991809572565e-05, "loss": 0.4689, "step": 3898 }, { "epoch": 0.998144, "grad_norm": 2.15625, "learning_rate": 3.337172596194864e-05, "loss": 0.5356, "step": 3899 }, { "epoch": 0.9984, "grad_norm": 2.484375, "learning_rate": 3.3367460114324714e-05, "loss": 0.4998, "step": 3900 }, { "epoch": 0.998656, "grad_norm": 1.859375, "learning_rate": 3.3363194266700795e-05, "loss": 0.4831, "step": 3901 }, { "epoch": 0.998912, "grad_norm": 2.453125, "learning_rate": 3.3358928419076876e-05, "loss": 0.4674, "step": 3902 }, { "epoch": 0.999168, "grad_norm": 2.46875, "learning_rate": 3.335466257145295e-05, "loss": 0.4598, "step": 3903 }, { "epoch": 0.999424, "grad_norm": 2.1875, "learning_rate": 3.3350396723829024e-05, "loss": 0.4828, "step": 3904 }, { "epoch": 0.99968, "grad_norm": 2.171875, "learning_rate": 3.3346130876205105e-05, "loss": 0.4691, "step": 3905 }, { "epoch": 0.999936, "grad_norm": 2.515625, "learning_rate": 3.334186502858118e-05, "loss": 0.4696, "step": 3906 }, { "epoch": 1.0, "grad_norm": 3.796875, "learning_rate": 3.333759918095726e-05, "loss": 0.5325, "step": 3907 }, { "epoch": 1.000256, "grad_norm": 2.6875, "learning_rate": 3.3333333333333335e-05, "loss": 0.4657, "step": 3908 }, { "epoch": 1.000512, "grad_norm": 2.46875, "learning_rate": 3.3329067485709416e-05, "loss": 0.4815, "step": 3909 }, { "epoch": 1.000768, "grad_norm": 2.125, "learning_rate": 3.332480163808549e-05, "loss": 0.4406, "step": 3910 }, { "epoch": 1.001024, "grad_norm": 2.265625, "learning_rate": 3.3320535790461565e-05, "loss": 0.4588, "step": 3911 }, { "epoch": 1.00128, "grad_norm": 2.15625, "learning_rate": 3.331626994283764e-05, "loss": 0.4907, "step": 3912 }, { "epoch": 1.001536, "grad_norm": 2.171875, "learning_rate": 3.331200409521372e-05, "loss": 0.4992, "step": 3913 }, { "epoch": 1.001792, "grad_norm": 2.375, "learning_rate": 3.33077382475898e-05, "loss": 0.4587, "step": 3914 }, { "epoch": 1.002048, "grad_norm": 2.53125, "learning_rate": 3.3303472399965875e-05, "loss": 0.4451, "step": 3915 }, { "epoch": 1.002304, "grad_norm": 2.21875, "learning_rate": 3.329920655234195e-05, "loss": 0.5152, "step": 3916 }, { "epoch": 1.00256, "grad_norm": 2.28125, "learning_rate": 3.329494070471803e-05, "loss": 0.462, "step": 3917 }, { "epoch": 1.002816, "grad_norm": 2.140625, "learning_rate": 3.3290674857094105e-05, "loss": 0.4751, "step": 3918 }, { "epoch": 1.003072, "grad_norm": 2.3125, "learning_rate": 3.328640900947018e-05, "loss": 0.5172, "step": 3919 }, { "epoch": 1.003328, "grad_norm": 2.171875, "learning_rate": 3.328214316184626e-05, "loss": 0.4762, "step": 3920 }, { "epoch": 1.003584, "grad_norm": 2.21875, "learning_rate": 3.327787731422234e-05, "loss": 0.4734, "step": 3921 }, { "epoch": 1.00384, "grad_norm": 2.125, "learning_rate": 3.3273611466598415e-05, "loss": 0.4871, "step": 3922 }, { "epoch": 1.004096, "grad_norm": 2.21875, "learning_rate": 3.326934561897449e-05, "loss": 0.4794, "step": 3923 }, { "epoch": 1.004352, "grad_norm": 2.203125, "learning_rate": 3.326507977135057e-05, "loss": 0.4742, "step": 3924 }, { "epoch": 1.004608, "grad_norm": 2.234375, "learning_rate": 3.3260813923726645e-05, "loss": 0.484, "step": 3925 }, { "epoch": 1.004864, "grad_norm": 2.09375, "learning_rate": 3.3256548076102726e-05, "loss": 0.4534, "step": 3926 }, { "epoch": 1.00512, "grad_norm": 2.09375, "learning_rate": 3.32522822284788e-05, "loss": 0.4463, "step": 3927 }, { "epoch": 1.005376, "grad_norm": 2.15625, "learning_rate": 3.324801638085488e-05, "loss": 0.4457, "step": 3928 }, { "epoch": 1.005632, "grad_norm": 2.171875, "learning_rate": 3.3243750533230956e-05, "loss": 0.4717, "step": 3929 }, { "epoch": 1.005888, "grad_norm": 2.296875, "learning_rate": 3.323948468560703e-05, "loss": 0.5274, "step": 3930 }, { "epoch": 1.006144, "grad_norm": 2.078125, "learning_rate": 3.3235218837983104e-05, "loss": 0.4778, "step": 3931 }, { "epoch": 1.0064, "grad_norm": 2.15625, "learning_rate": 3.3230952990359185e-05, "loss": 0.4759, "step": 3932 }, { "epoch": 1.006656, "grad_norm": 2.234375, "learning_rate": 3.3226687142735266e-05, "loss": 0.4742, "step": 3933 }, { "epoch": 1.006912, "grad_norm": 2.296875, "learning_rate": 3.322242129511134e-05, "loss": 0.4716, "step": 3934 }, { "epoch": 1.007168, "grad_norm": 2.171875, "learning_rate": 3.3218155447487415e-05, "loss": 0.4383, "step": 3935 }, { "epoch": 1.007424, "grad_norm": 2.265625, "learning_rate": 3.3213889599863496e-05, "loss": 0.4831, "step": 3936 }, { "epoch": 1.00768, "grad_norm": 2.109375, "learning_rate": 3.320962375223957e-05, "loss": 0.4801, "step": 3937 }, { "epoch": 1.007936, "grad_norm": 2.4375, "learning_rate": 3.3205357904615644e-05, "loss": 0.4888, "step": 3938 }, { "epoch": 1.008192, "grad_norm": 2.34375, "learning_rate": 3.3201092056991725e-05, "loss": 0.4626, "step": 3939 }, { "epoch": 1.008448, "grad_norm": 2.21875, "learning_rate": 3.3196826209367806e-05, "loss": 0.4484, "step": 3940 }, { "epoch": 1.008704, "grad_norm": 2.21875, "learning_rate": 3.319256036174388e-05, "loss": 0.4841, "step": 3941 }, { "epoch": 1.00896, "grad_norm": 2.03125, "learning_rate": 3.3188294514119955e-05, "loss": 0.4817, "step": 3942 }, { "epoch": 1.009216, "grad_norm": 2.5, "learning_rate": 3.3184028666496036e-05, "loss": 0.4823, "step": 3943 }, { "epoch": 1.009472, "grad_norm": 2.328125, "learning_rate": 3.317976281887211e-05, "loss": 0.4619, "step": 3944 }, { "epoch": 1.009728, "grad_norm": 2.28125, "learning_rate": 3.3175496971248184e-05, "loss": 0.4719, "step": 3945 }, { "epoch": 1.009984, "grad_norm": 2.09375, "learning_rate": 3.3171231123624265e-05, "loss": 0.5123, "step": 3946 }, { "epoch": 1.01024, "grad_norm": 2.375, "learning_rate": 3.3166965276000347e-05, "loss": 0.4368, "step": 3947 }, { "epoch": 1.010496, "grad_norm": 2.171875, "learning_rate": 3.316269942837642e-05, "loss": 0.4847, "step": 3948 }, { "epoch": 1.010752, "grad_norm": 2.34375, "learning_rate": 3.3158433580752495e-05, "loss": 0.4461, "step": 3949 }, { "epoch": 1.011008, "grad_norm": 2.109375, "learning_rate": 3.315416773312857e-05, "loss": 0.4814, "step": 3950 }, { "epoch": 1.011264, "grad_norm": 2.3125, "learning_rate": 3.314990188550465e-05, "loss": 0.4989, "step": 3951 }, { "epoch": 1.01152, "grad_norm": 2.078125, "learning_rate": 3.314563603788073e-05, "loss": 0.4682, "step": 3952 }, { "epoch": 1.011776, "grad_norm": 2.1875, "learning_rate": 3.3141370190256806e-05, "loss": 0.4824, "step": 3953 }, { "epoch": 1.012032, "grad_norm": 2.34375, "learning_rate": 3.313710434263289e-05, "loss": 0.5049, "step": 3954 }, { "epoch": 1.012288, "grad_norm": 2.09375, "learning_rate": 3.313283849500896e-05, "loss": 0.4902, "step": 3955 }, { "epoch": 1.012544, "grad_norm": 2.34375, "learning_rate": 3.3128572647385035e-05, "loss": 0.493, "step": 3956 }, { "epoch": 1.0128, "grad_norm": 2.109375, "learning_rate": 3.312430679976111e-05, "loss": 0.4996, "step": 3957 }, { "epoch": 1.013056, "grad_norm": 2.203125, "learning_rate": 3.312004095213719e-05, "loss": 0.5052, "step": 3958 }, { "epoch": 1.013312, "grad_norm": 2.125, "learning_rate": 3.311577510451327e-05, "loss": 0.4567, "step": 3959 }, { "epoch": 1.013568, "grad_norm": 2.328125, "learning_rate": 3.3111509256889346e-05, "loss": 0.4948, "step": 3960 }, { "epoch": 1.013824, "grad_norm": 2.515625, "learning_rate": 3.310724340926542e-05, "loss": 0.4617, "step": 3961 }, { "epoch": 1.01408, "grad_norm": 2.40625, "learning_rate": 3.31029775616415e-05, "loss": 0.4001, "step": 3962 }, { "epoch": 1.014336, "grad_norm": 2.4375, "learning_rate": 3.3098711714017575e-05, "loss": 0.4776, "step": 3963 }, { "epoch": 1.014592, "grad_norm": 2.3125, "learning_rate": 3.309444586639365e-05, "loss": 0.4942, "step": 3964 }, { "epoch": 1.014848, "grad_norm": 2.3125, "learning_rate": 3.309018001876973e-05, "loss": 0.4559, "step": 3965 }, { "epoch": 1.015104, "grad_norm": 2.453125, "learning_rate": 3.308591417114581e-05, "loss": 0.507, "step": 3966 }, { "epoch": 1.01536, "grad_norm": 2.40625, "learning_rate": 3.3081648323521886e-05, "loss": 0.4754, "step": 3967 }, { "epoch": 1.015616, "grad_norm": 2.328125, "learning_rate": 3.307738247589796e-05, "loss": 0.4926, "step": 3968 }, { "epoch": 1.015872, "grad_norm": 2.40625, "learning_rate": 3.307311662827404e-05, "loss": 0.4771, "step": 3969 }, { "epoch": 1.016128, "grad_norm": 2.375, "learning_rate": 3.3068850780650116e-05, "loss": 0.4628, "step": 3970 }, { "epoch": 1.016384, "grad_norm": 2.34375, "learning_rate": 3.30645849330262e-05, "loss": 0.4804, "step": 3971 }, { "epoch": 1.01664, "grad_norm": 2.328125, "learning_rate": 3.306031908540227e-05, "loss": 0.4672, "step": 3972 }, { "epoch": 1.016896, "grad_norm": 2.390625, "learning_rate": 3.305605323777835e-05, "loss": 0.4484, "step": 3973 }, { "epoch": 1.017152, "grad_norm": 2.203125, "learning_rate": 3.3051787390154426e-05, "loss": 0.502, "step": 3974 }, { "epoch": 1.017408, "grad_norm": 2.375, "learning_rate": 3.30475215425305e-05, "loss": 0.4717, "step": 3975 }, { "epoch": 1.017664, "grad_norm": 2.203125, "learning_rate": 3.3043255694906575e-05, "loss": 0.5019, "step": 3976 }, { "epoch": 1.01792, "grad_norm": 2.640625, "learning_rate": 3.3038989847282656e-05, "loss": 0.4799, "step": 3977 }, { "epoch": 1.018176, "grad_norm": 2.578125, "learning_rate": 3.303472399965874e-05, "loss": 0.5038, "step": 3978 }, { "epoch": 1.018432, "grad_norm": 2.125, "learning_rate": 3.303045815203481e-05, "loss": 0.4771, "step": 3979 }, { "epoch": 1.018688, "grad_norm": 2.34375, "learning_rate": 3.3026192304410885e-05, "loss": 0.4914, "step": 3980 }, { "epoch": 1.018944, "grad_norm": 2.625, "learning_rate": 3.3021926456786966e-05, "loss": 0.4941, "step": 3981 }, { "epoch": 1.0192, "grad_norm": 2.359375, "learning_rate": 3.301766060916304e-05, "loss": 0.5168, "step": 3982 }, { "epoch": 1.019456, "grad_norm": 2.21875, "learning_rate": 3.3013394761539115e-05, "loss": 0.444, "step": 3983 }, { "epoch": 1.019712, "grad_norm": 2.390625, "learning_rate": 3.3009128913915196e-05, "loss": 0.4627, "step": 3984 }, { "epoch": 1.019968, "grad_norm": 2.578125, "learning_rate": 3.300486306629128e-05, "loss": 0.4529, "step": 3985 }, { "epoch": 1.020224, "grad_norm": 2.296875, "learning_rate": 3.300059721866735e-05, "loss": 0.4949, "step": 3986 }, { "epoch": 1.02048, "grad_norm": 2.109375, "learning_rate": 3.2996331371043426e-05, "loss": 0.4889, "step": 3987 }, { "epoch": 1.020736, "grad_norm": 2.125, "learning_rate": 3.299206552341951e-05, "loss": 0.5128, "step": 3988 }, { "epoch": 1.020992, "grad_norm": 2.28125, "learning_rate": 3.298779967579558e-05, "loss": 0.4913, "step": 3989 }, { "epoch": 1.021248, "grad_norm": 2.40625, "learning_rate": 3.298353382817166e-05, "loss": 0.4654, "step": 3990 }, { "epoch": 1.021504, "grad_norm": 2.171875, "learning_rate": 3.2979267980547736e-05, "loss": 0.4611, "step": 3991 }, { "epoch": 1.02176, "grad_norm": 2.25, "learning_rate": 3.297500213292382e-05, "loss": 0.454, "step": 3992 }, { "epoch": 1.022016, "grad_norm": 2.21875, "learning_rate": 3.297073628529989e-05, "loss": 0.4539, "step": 3993 }, { "epoch": 1.022272, "grad_norm": 2.265625, "learning_rate": 3.2966470437675966e-05, "loss": 0.4989, "step": 3994 }, { "epoch": 1.022528, "grad_norm": 2.40625, "learning_rate": 3.296220459005204e-05, "loss": 0.4841, "step": 3995 }, { "epoch": 1.022784, "grad_norm": 2.453125, "learning_rate": 3.295793874242812e-05, "loss": 0.4903, "step": 3996 }, { "epoch": 1.02304, "grad_norm": 2.28125, "learning_rate": 3.29536728948042e-05, "loss": 0.4932, "step": 3997 }, { "epoch": 1.023296, "grad_norm": 2.21875, "learning_rate": 3.2949407047180276e-05, "loss": 0.4366, "step": 3998 }, { "epoch": 1.023552, "grad_norm": 2.21875, "learning_rate": 3.294514119955635e-05, "loss": 0.5043, "step": 3999 }, { "epoch": 1.023808, "grad_norm": 2.0625, "learning_rate": 3.294087535193243e-05, "loss": 0.4894, "step": 4000 }, { "epoch": 1.024064, "grad_norm": 2.25, "learning_rate": 3.2936609504308506e-05, "loss": 0.5011, "step": 4001 }, { "epoch": 1.02432, "grad_norm": 2.15625, "learning_rate": 3.293234365668458e-05, "loss": 0.5308, "step": 4002 }, { "epoch": 1.024576, "grad_norm": 2.28125, "learning_rate": 3.292807780906066e-05, "loss": 0.4527, "step": 4003 }, { "epoch": 1.024832, "grad_norm": 2.328125, "learning_rate": 3.292381196143674e-05, "loss": 0.4964, "step": 4004 }, { "epoch": 1.025088, "grad_norm": 2.203125, "learning_rate": 3.2919546113812817e-05, "loss": 0.5044, "step": 4005 }, { "epoch": 1.025344, "grad_norm": 2.40625, "learning_rate": 3.291528026618889e-05, "loss": 0.4851, "step": 4006 }, { "epoch": 1.0256, "grad_norm": 2.28125, "learning_rate": 3.291101441856497e-05, "loss": 0.4811, "step": 4007 }, { "epoch": 1.025856, "grad_norm": 2.34375, "learning_rate": 3.2906748570941046e-05, "loss": 0.4755, "step": 4008 }, { "epoch": 1.026112, "grad_norm": 2.0625, "learning_rate": 3.290248272331713e-05, "loss": 0.4608, "step": 4009 }, { "epoch": 1.026368, "grad_norm": 2.046875, "learning_rate": 3.28982168756932e-05, "loss": 0.5113, "step": 4010 }, { "epoch": 1.026624, "grad_norm": 2.296875, "learning_rate": 3.289395102806928e-05, "loss": 0.4266, "step": 4011 }, { "epoch": 1.02688, "grad_norm": 2.28125, "learning_rate": 3.288968518044536e-05, "loss": 0.4647, "step": 4012 }, { "epoch": 1.027136, "grad_norm": 2.21875, "learning_rate": 3.288541933282143e-05, "loss": 0.4685, "step": 4013 }, { "epoch": 1.027392, "grad_norm": 2.203125, "learning_rate": 3.2881153485197505e-05, "loss": 0.4699, "step": 4014 }, { "epoch": 1.027648, "grad_norm": 2.21875, "learning_rate": 3.2876887637573586e-05, "loss": 0.4855, "step": 4015 }, { "epoch": 1.027904, "grad_norm": 2.359375, "learning_rate": 3.287262178994967e-05, "loss": 0.5065, "step": 4016 }, { "epoch": 1.02816, "grad_norm": 2.171875, "learning_rate": 3.286835594232574e-05, "loss": 0.4565, "step": 4017 }, { "epoch": 1.028416, "grad_norm": 2.15625, "learning_rate": 3.286409009470182e-05, "loss": 0.4741, "step": 4018 }, { "epoch": 1.028672, "grad_norm": 2.25, "learning_rate": 3.28598242470779e-05, "loss": 0.456, "step": 4019 }, { "epoch": 1.028928, "grad_norm": 2.234375, "learning_rate": 3.285555839945397e-05, "loss": 0.4745, "step": 4020 }, { "epoch": 1.029184, "grad_norm": 2.140625, "learning_rate": 3.2851292551830046e-05, "loss": 0.5134, "step": 4021 }, { "epoch": 1.02944, "grad_norm": 2.28125, "learning_rate": 3.2847026704206127e-05, "loss": 0.4863, "step": 4022 }, { "epoch": 1.029696, "grad_norm": 1.984375, "learning_rate": 3.284276085658221e-05, "loss": 0.4665, "step": 4023 }, { "epoch": 1.029952, "grad_norm": 2.265625, "learning_rate": 3.283849500895828e-05, "loss": 0.4677, "step": 4024 }, { "epoch": 1.030208, "grad_norm": 2.1875, "learning_rate": 3.2834229161334356e-05, "loss": 0.5026, "step": 4025 }, { "epoch": 1.030464, "grad_norm": 2.1875, "learning_rate": 3.282996331371044e-05, "loss": 0.4866, "step": 4026 }, { "epoch": 1.03072, "grad_norm": 2.21875, "learning_rate": 3.282569746608651e-05, "loss": 0.4832, "step": 4027 }, { "epoch": 1.030976, "grad_norm": 2.328125, "learning_rate": 3.282143161846259e-05, "loss": 0.4981, "step": 4028 }, { "epoch": 1.031232, "grad_norm": 2.453125, "learning_rate": 3.281716577083867e-05, "loss": 0.4963, "step": 4029 }, { "epoch": 1.031488, "grad_norm": 2.375, "learning_rate": 3.281289992321475e-05, "loss": 0.4653, "step": 4030 }, { "epoch": 1.031744, "grad_norm": 2.21875, "learning_rate": 3.280863407559082e-05, "loss": 0.4768, "step": 4031 }, { "epoch": 1.032, "grad_norm": 2.28125, "learning_rate": 3.2804368227966896e-05, "loss": 0.4767, "step": 4032 }, { "epoch": 1.032256, "grad_norm": 2.171875, "learning_rate": 3.280010238034297e-05, "loss": 0.4891, "step": 4033 }, { "epoch": 1.032512, "grad_norm": 2.234375, "learning_rate": 3.279583653271905e-05, "loss": 0.4471, "step": 4034 }, { "epoch": 1.032768, "grad_norm": 2.28125, "learning_rate": 3.279157068509513e-05, "loss": 0.4918, "step": 4035 }, { "epoch": 1.033024, "grad_norm": 1.9921875, "learning_rate": 3.278730483747121e-05, "loss": 0.4994, "step": 4036 }, { "epoch": 1.03328, "grad_norm": 2.203125, "learning_rate": 3.278303898984729e-05, "loss": 0.4551, "step": 4037 }, { "epoch": 1.033536, "grad_norm": 2.3125, "learning_rate": 3.277877314222336e-05, "loss": 0.4842, "step": 4038 }, { "epoch": 1.033792, "grad_norm": 2.265625, "learning_rate": 3.2774507294599437e-05, "loss": 0.4921, "step": 4039 }, { "epoch": 1.034048, "grad_norm": 2.390625, "learning_rate": 3.277024144697551e-05, "loss": 0.4605, "step": 4040 }, { "epoch": 1.0343040000000001, "grad_norm": 2.21875, "learning_rate": 3.276597559935159e-05, "loss": 0.4954, "step": 4041 }, { "epoch": 1.03456, "grad_norm": 2.1875, "learning_rate": 3.276170975172767e-05, "loss": 0.4659, "step": 4042 }, { "epoch": 1.034816, "grad_norm": 2.296875, "learning_rate": 3.275744390410375e-05, "loss": 0.4622, "step": 4043 }, { "epoch": 1.035072, "grad_norm": 2.3125, "learning_rate": 3.275317805647982e-05, "loss": 0.4688, "step": 4044 }, { "epoch": 1.035328, "grad_norm": 2.328125, "learning_rate": 3.27489122088559e-05, "loss": 0.504, "step": 4045 }, { "epoch": 1.035584, "grad_norm": 2.1875, "learning_rate": 3.274464636123198e-05, "loss": 0.4886, "step": 4046 }, { "epoch": 1.03584, "grad_norm": 2.140625, "learning_rate": 3.274038051360806e-05, "loss": 0.4798, "step": 4047 }, { "epoch": 1.036096, "grad_norm": 2.21875, "learning_rate": 3.273611466598413e-05, "loss": 0.4838, "step": 4048 }, { "epoch": 1.036352, "grad_norm": 2.078125, "learning_rate": 3.273184881836021e-05, "loss": 0.4894, "step": 4049 }, { "epoch": 1.036608, "grad_norm": 2.140625, "learning_rate": 3.272758297073629e-05, "loss": 0.5009, "step": 4050 }, { "epoch": 1.036864, "grad_norm": 2.40625, "learning_rate": 3.272331712311236e-05, "loss": 0.4502, "step": 4051 }, { "epoch": 1.03712, "grad_norm": 2.015625, "learning_rate": 3.271905127548844e-05, "loss": 0.4493, "step": 4052 }, { "epoch": 1.037376, "grad_norm": 2.125, "learning_rate": 3.271478542786452e-05, "loss": 0.4677, "step": 4053 }, { "epoch": 1.0376319999999999, "grad_norm": 2.328125, "learning_rate": 3.27105195802406e-05, "loss": 0.4414, "step": 4054 }, { "epoch": 1.037888, "grad_norm": 2.34375, "learning_rate": 3.270625373261667e-05, "loss": 0.4813, "step": 4055 }, { "epoch": 1.038144, "grad_norm": 2.375, "learning_rate": 3.270198788499275e-05, "loss": 0.4728, "step": 4056 }, { "epoch": 1.0384, "grad_norm": 2.171875, "learning_rate": 3.269772203736883e-05, "loss": 0.457, "step": 4057 }, { "epoch": 1.038656, "grad_norm": 2.25, "learning_rate": 3.26934561897449e-05, "loss": 0.4593, "step": 4058 }, { "epoch": 1.038912, "grad_norm": 2.09375, "learning_rate": 3.2689190342120976e-05, "loss": 0.4917, "step": 4059 }, { "epoch": 1.039168, "grad_norm": 2.453125, "learning_rate": 3.268492449449706e-05, "loss": 0.4853, "step": 4060 }, { "epoch": 1.039424, "grad_norm": 2.125, "learning_rate": 3.268065864687314e-05, "loss": 0.4259, "step": 4061 }, { "epoch": 1.03968, "grad_norm": 2.234375, "learning_rate": 3.267639279924921e-05, "loss": 0.458, "step": 4062 }, { "epoch": 1.039936, "grad_norm": 2.28125, "learning_rate": 3.267212695162529e-05, "loss": 0.4926, "step": 4063 }, { "epoch": 1.040192, "grad_norm": 2.140625, "learning_rate": 3.266786110400137e-05, "loss": 0.4774, "step": 4064 }, { "epoch": 1.040448, "grad_norm": 2.25, "learning_rate": 3.266359525637744e-05, "loss": 0.4664, "step": 4065 }, { "epoch": 1.040704, "grad_norm": 2.5, "learning_rate": 3.2659329408753516e-05, "loss": 0.417, "step": 4066 }, { "epoch": 1.04096, "grad_norm": 2.265625, "learning_rate": 3.2655063561129604e-05, "loss": 0.4771, "step": 4067 }, { "epoch": 1.041216, "grad_norm": 2.328125, "learning_rate": 3.265079771350568e-05, "loss": 0.4275, "step": 4068 }, { "epoch": 1.041472, "grad_norm": 2.34375, "learning_rate": 3.264653186588175e-05, "loss": 0.4745, "step": 4069 }, { "epoch": 1.041728, "grad_norm": 2.390625, "learning_rate": 3.264226601825783e-05, "loss": 0.4669, "step": 4070 }, { "epoch": 1.041984, "grad_norm": 2.390625, "learning_rate": 3.263800017063391e-05, "loss": 0.4821, "step": 4071 }, { "epoch": 1.04224, "grad_norm": 2.09375, "learning_rate": 3.263373432300998e-05, "loss": 0.441, "step": 4072 }, { "epoch": 1.042496, "grad_norm": 2.28125, "learning_rate": 3.262946847538606e-05, "loss": 0.527, "step": 4073 }, { "epoch": 1.042752, "grad_norm": 2.125, "learning_rate": 3.262520262776214e-05, "loss": 0.4939, "step": 4074 }, { "epoch": 1.043008, "grad_norm": 2.140625, "learning_rate": 3.262093678013822e-05, "loss": 0.4754, "step": 4075 }, { "epoch": 1.043264, "grad_norm": 2.25, "learning_rate": 3.261667093251429e-05, "loss": 0.4763, "step": 4076 }, { "epoch": 1.04352, "grad_norm": 2.140625, "learning_rate": 3.261240508489037e-05, "loss": 0.4743, "step": 4077 }, { "epoch": 1.043776, "grad_norm": 2.234375, "learning_rate": 3.260813923726644e-05, "loss": 0.4596, "step": 4078 }, { "epoch": 1.044032, "grad_norm": 2.265625, "learning_rate": 3.260387338964252e-05, "loss": 0.4653, "step": 4079 }, { "epoch": 1.044288, "grad_norm": 2.34375, "learning_rate": 3.2599607542018603e-05, "loss": 0.4975, "step": 4080 }, { "epoch": 1.044544, "grad_norm": 2.0625, "learning_rate": 3.259534169439468e-05, "loss": 0.4456, "step": 4081 }, { "epoch": 1.0448, "grad_norm": 2.171875, "learning_rate": 3.259107584677075e-05, "loss": 0.4485, "step": 4082 }, { "epoch": 1.045056, "grad_norm": 2.359375, "learning_rate": 3.258680999914683e-05, "loss": 0.4417, "step": 4083 }, { "epoch": 1.045312, "grad_norm": 2.3125, "learning_rate": 3.258254415152291e-05, "loss": 0.4892, "step": 4084 }, { "epoch": 1.045568, "grad_norm": 2.546875, "learning_rate": 3.257827830389898e-05, "loss": 0.4617, "step": 4085 }, { "epoch": 1.045824, "grad_norm": 2.1875, "learning_rate": 3.257401245627506e-05, "loss": 0.4492, "step": 4086 }, { "epoch": 1.04608, "grad_norm": 2.46875, "learning_rate": 3.2569746608651144e-05, "loss": 0.4652, "step": 4087 }, { "epoch": 1.046336, "grad_norm": 2.5, "learning_rate": 3.256548076102722e-05, "loss": 0.472, "step": 4088 }, { "epoch": 1.046592, "grad_norm": 2.1875, "learning_rate": 3.256121491340329e-05, "loss": 0.5045, "step": 4089 }, { "epoch": 1.046848, "grad_norm": 2.140625, "learning_rate": 3.255694906577937e-05, "loss": 0.4921, "step": 4090 }, { "epoch": 1.047104, "grad_norm": 2.28125, "learning_rate": 3.255268321815545e-05, "loss": 0.4685, "step": 4091 }, { "epoch": 1.04736, "grad_norm": 2.390625, "learning_rate": 3.254841737053153e-05, "loss": 0.4904, "step": 4092 }, { "epoch": 1.047616, "grad_norm": 2.34375, "learning_rate": 3.25441515229076e-05, "loss": 0.503, "step": 4093 }, { "epoch": 1.047872, "grad_norm": 2.46875, "learning_rate": 3.2539885675283684e-05, "loss": 0.4577, "step": 4094 }, { "epoch": 1.048128, "grad_norm": 2.296875, "learning_rate": 3.253561982765976e-05, "loss": 0.4567, "step": 4095 }, { "epoch": 1.048384, "grad_norm": 2.28125, "learning_rate": 3.253135398003583e-05, "loss": 0.4622, "step": 4096 }, { "epoch": 1.04864, "grad_norm": 2.046875, "learning_rate": 3.2527088132411907e-05, "loss": 0.4745, "step": 4097 }, { "epoch": 1.048896, "grad_norm": 2.28125, "learning_rate": 3.252282228478799e-05, "loss": 0.5326, "step": 4098 }, { "epoch": 1.049152, "grad_norm": 2.34375, "learning_rate": 3.251855643716407e-05, "loss": 0.4751, "step": 4099 }, { "epoch": 1.049408, "grad_norm": 2.296875, "learning_rate": 3.251429058954014e-05, "loss": 0.478, "step": 4100 }, { "epoch": 1.049664, "grad_norm": 2.46875, "learning_rate": 3.2510024741916224e-05, "loss": 0.4804, "step": 4101 }, { "epoch": 1.04992, "grad_norm": 2.328125, "learning_rate": 3.25057588942923e-05, "loss": 0.4936, "step": 4102 }, { "epoch": 1.050176, "grad_norm": 2.46875, "learning_rate": 3.250149304666837e-05, "loss": 0.5166, "step": 4103 }, { "epoch": 1.050432, "grad_norm": 2.359375, "learning_rate": 3.249722719904445e-05, "loss": 0.4789, "step": 4104 }, { "epoch": 1.050688, "grad_norm": 2.484375, "learning_rate": 3.249296135142053e-05, "loss": 0.4907, "step": 4105 }, { "epoch": 1.050944, "grad_norm": 2.109375, "learning_rate": 3.248869550379661e-05, "loss": 0.4461, "step": 4106 }, { "epoch": 1.0512, "grad_norm": 2.3125, "learning_rate": 3.248442965617268e-05, "loss": 0.4863, "step": 4107 }, { "epoch": 1.051456, "grad_norm": 2.28125, "learning_rate": 3.248016380854876e-05, "loss": 0.4612, "step": 4108 }, { "epoch": 1.051712, "grad_norm": 2.078125, "learning_rate": 3.247589796092484e-05, "loss": 0.468, "step": 4109 }, { "epoch": 1.051968, "grad_norm": 2.140625, "learning_rate": 3.247163211330091e-05, "loss": 0.4787, "step": 4110 }, { "epoch": 1.052224, "grad_norm": 2.328125, "learning_rate": 3.2467366265676994e-05, "loss": 0.4613, "step": 4111 }, { "epoch": 1.05248, "grad_norm": 2.375, "learning_rate": 3.246310041805307e-05, "loss": 0.4828, "step": 4112 }, { "epoch": 1.052736, "grad_norm": 2.3125, "learning_rate": 3.245883457042915e-05, "loss": 0.4854, "step": 4113 }, { "epoch": 1.052992, "grad_norm": 2.265625, "learning_rate": 3.245456872280522e-05, "loss": 0.4717, "step": 4114 }, { "epoch": 1.053248, "grad_norm": 2.15625, "learning_rate": 3.24503028751813e-05, "loss": 0.4833, "step": 4115 }, { "epoch": 1.053504, "grad_norm": 2.203125, "learning_rate": 3.244603702755738e-05, "loss": 0.45, "step": 4116 }, { "epoch": 1.05376, "grad_norm": 2.125, "learning_rate": 3.244177117993345e-05, "loss": 0.4764, "step": 4117 }, { "epoch": 1.054016, "grad_norm": 2.09375, "learning_rate": 3.2437505332309534e-05, "loss": 0.4217, "step": 4118 }, { "epoch": 1.054272, "grad_norm": 2.265625, "learning_rate": 3.243323948468561e-05, "loss": 0.4664, "step": 4119 }, { "epoch": 1.054528, "grad_norm": 2.25, "learning_rate": 3.242897363706169e-05, "loss": 0.4817, "step": 4120 }, { "epoch": 1.054784, "grad_norm": 2.421875, "learning_rate": 3.2424707789437764e-05, "loss": 0.4788, "step": 4121 }, { "epoch": 1.05504, "grad_norm": 2.140625, "learning_rate": 3.242044194181384e-05, "loss": 0.4592, "step": 4122 }, { "epoch": 1.055296, "grad_norm": 2.234375, "learning_rate": 3.241617609418991e-05, "loss": 0.4856, "step": 4123 }, { "epoch": 1.055552, "grad_norm": 2.3125, "learning_rate": 3.241191024656599e-05, "loss": 0.4621, "step": 4124 }, { "epoch": 1.055808, "grad_norm": 2.359375, "learning_rate": 3.2407644398942074e-05, "loss": 0.437, "step": 4125 }, { "epoch": 1.0560640000000001, "grad_norm": 2.203125, "learning_rate": 3.240337855131815e-05, "loss": 0.4724, "step": 4126 }, { "epoch": 1.05632, "grad_norm": 2.265625, "learning_rate": 3.239911270369422e-05, "loss": 0.4417, "step": 4127 }, { "epoch": 1.056576, "grad_norm": 2.296875, "learning_rate": 3.2394846856070304e-05, "loss": 0.4609, "step": 4128 }, { "epoch": 1.056832, "grad_norm": 2.453125, "learning_rate": 3.239058100844638e-05, "loss": 0.4591, "step": 4129 }, { "epoch": 1.057088, "grad_norm": 2.15625, "learning_rate": 3.238631516082246e-05, "loss": 0.4419, "step": 4130 }, { "epoch": 1.057344, "grad_norm": 2.21875, "learning_rate": 3.238204931319853e-05, "loss": 0.494, "step": 4131 }, { "epoch": 1.0576, "grad_norm": 2.390625, "learning_rate": 3.2377783465574614e-05, "loss": 0.4616, "step": 4132 }, { "epoch": 1.057856, "grad_norm": 2.125, "learning_rate": 3.237351761795069e-05, "loss": 0.4669, "step": 4133 }, { "epoch": 1.058112, "grad_norm": 2.078125, "learning_rate": 3.236925177032676e-05, "loss": 0.48, "step": 4134 }, { "epoch": 1.058368, "grad_norm": 2.203125, "learning_rate": 3.2364985922702844e-05, "loss": 0.4898, "step": 4135 }, { "epoch": 1.058624, "grad_norm": 2.375, "learning_rate": 3.236072007507892e-05, "loss": 0.4835, "step": 4136 }, { "epoch": 1.05888, "grad_norm": 2.171875, "learning_rate": 3.2356454227455e-05, "loss": 0.4857, "step": 4137 }, { "epoch": 1.059136, "grad_norm": 2.0625, "learning_rate": 3.2352188379831073e-05, "loss": 0.4665, "step": 4138 }, { "epoch": 1.059392, "grad_norm": 2.234375, "learning_rate": 3.2347922532207155e-05, "loss": 0.4922, "step": 4139 }, { "epoch": 1.059648, "grad_norm": 2.140625, "learning_rate": 3.234365668458323e-05, "loss": 0.4852, "step": 4140 }, { "epoch": 1.059904, "grad_norm": 2.109375, "learning_rate": 3.23393908369593e-05, "loss": 0.4885, "step": 4141 }, { "epoch": 1.06016, "grad_norm": 2.109375, "learning_rate": 3.233512498933538e-05, "loss": 0.4283, "step": 4142 }, { "epoch": 1.060416, "grad_norm": 2.28125, "learning_rate": 3.233085914171146e-05, "loss": 0.4794, "step": 4143 }, { "epoch": 1.060672, "grad_norm": 2.25, "learning_rate": 3.232659329408754e-05, "loss": 0.4792, "step": 4144 }, { "epoch": 1.060928, "grad_norm": 2.109375, "learning_rate": 3.2322327446463614e-05, "loss": 0.4805, "step": 4145 }, { "epoch": 1.061184, "grad_norm": 2.390625, "learning_rate": 3.231806159883969e-05, "loss": 0.4682, "step": 4146 }, { "epoch": 1.06144, "grad_norm": 2.359375, "learning_rate": 3.231379575121577e-05, "loss": 0.464, "step": 4147 }, { "epoch": 1.061696, "grad_norm": 2.296875, "learning_rate": 3.230952990359184e-05, "loss": 0.4891, "step": 4148 }, { "epoch": 1.061952, "grad_norm": 2.65625, "learning_rate": 3.2305264055967924e-05, "loss": 0.4387, "step": 4149 }, { "epoch": 1.062208, "grad_norm": 2.34375, "learning_rate": 3.2300998208344005e-05, "loss": 0.461, "step": 4150 }, { "epoch": 1.062464, "grad_norm": 2.5, "learning_rate": 3.229673236072008e-05, "loss": 0.4525, "step": 4151 }, { "epoch": 1.06272, "grad_norm": 2.375, "learning_rate": 3.2292466513096154e-05, "loss": 0.469, "step": 4152 }, { "epoch": 1.062976, "grad_norm": 2.59375, "learning_rate": 3.228820066547223e-05, "loss": 0.4901, "step": 4153 }, { "epoch": 1.063232, "grad_norm": 2.484375, "learning_rate": 3.228393481784831e-05, "loss": 0.4456, "step": 4154 }, { "epoch": 1.063488, "grad_norm": 2.265625, "learning_rate": 3.2279668970224383e-05, "loss": 0.4602, "step": 4155 }, { "epoch": 1.063744, "grad_norm": 2.109375, "learning_rate": 3.2275403122600464e-05, "loss": 0.4443, "step": 4156 }, { "epoch": 1.064, "grad_norm": 2.265625, "learning_rate": 3.227113727497654e-05, "loss": 0.5215, "step": 4157 }, { "epoch": 1.064256, "grad_norm": 2.40625, "learning_rate": 3.226687142735262e-05, "loss": 0.4627, "step": 4158 }, { "epoch": 1.064512, "grad_norm": 2.09375, "learning_rate": 3.2262605579728694e-05, "loss": 0.461, "step": 4159 }, { "epoch": 1.064768, "grad_norm": 2.109375, "learning_rate": 3.225833973210477e-05, "loss": 0.5169, "step": 4160 }, { "epoch": 1.065024, "grad_norm": 2.21875, "learning_rate": 3.225407388448084e-05, "loss": 0.4384, "step": 4161 }, { "epoch": 1.06528, "grad_norm": 2.3125, "learning_rate": 3.2249808036856924e-05, "loss": 0.4521, "step": 4162 }, { "epoch": 1.065536, "grad_norm": 2.15625, "learning_rate": 3.2245542189233005e-05, "loss": 0.472, "step": 4163 }, { "epoch": 1.065792, "grad_norm": 2.453125, "learning_rate": 3.224127634160908e-05, "loss": 0.4727, "step": 4164 }, { "epoch": 1.0660479999999999, "grad_norm": 2.25, "learning_rate": 3.223701049398516e-05, "loss": 0.4607, "step": 4165 }, { "epoch": 1.066304, "grad_norm": 2.328125, "learning_rate": 3.2232744646361234e-05, "loss": 0.4853, "step": 4166 }, { "epoch": 1.06656, "grad_norm": 2.28125, "learning_rate": 3.222847879873731e-05, "loss": 0.4787, "step": 4167 }, { "epoch": 1.066816, "grad_norm": 2.140625, "learning_rate": 3.222421295111338e-05, "loss": 0.4833, "step": 4168 }, { "epoch": 1.067072, "grad_norm": 2.140625, "learning_rate": 3.221994710348947e-05, "loss": 0.5178, "step": 4169 }, { "epoch": 1.067328, "grad_norm": 2.109375, "learning_rate": 3.2215681255865545e-05, "loss": 0.5278, "step": 4170 }, { "epoch": 1.067584, "grad_norm": 2.125, "learning_rate": 3.221141540824162e-05, "loss": 0.4675, "step": 4171 }, { "epoch": 1.06784, "grad_norm": 2.203125, "learning_rate": 3.2207149560617693e-05, "loss": 0.4596, "step": 4172 }, { "epoch": 1.068096, "grad_norm": 2.25, "learning_rate": 3.2202883712993774e-05, "loss": 0.4874, "step": 4173 }, { "epoch": 1.068352, "grad_norm": 2.0625, "learning_rate": 3.219861786536985e-05, "loss": 0.4614, "step": 4174 }, { "epoch": 1.068608, "grad_norm": 2.53125, "learning_rate": 3.219435201774593e-05, "loss": 0.5008, "step": 4175 }, { "epoch": 1.068864, "grad_norm": 2.328125, "learning_rate": 3.2190086170122004e-05, "loss": 0.4767, "step": 4176 }, { "epoch": 1.06912, "grad_norm": 2.28125, "learning_rate": 3.2185820322498085e-05, "loss": 0.4714, "step": 4177 }, { "epoch": 1.069376, "grad_norm": 2.109375, "learning_rate": 3.218155447487416e-05, "loss": 0.4604, "step": 4178 }, { "epoch": 1.069632, "grad_norm": 2.203125, "learning_rate": 3.2177288627250234e-05, "loss": 0.4942, "step": 4179 }, { "epoch": 1.069888, "grad_norm": 2.1875, "learning_rate": 3.217302277962631e-05, "loss": 0.4548, "step": 4180 }, { "epoch": 1.070144, "grad_norm": 2.15625, "learning_rate": 3.216875693200239e-05, "loss": 0.4481, "step": 4181 }, { "epoch": 1.0704, "grad_norm": 2.25, "learning_rate": 3.216449108437847e-05, "loss": 0.5416, "step": 4182 }, { "epoch": 1.070656, "grad_norm": 2.1875, "learning_rate": 3.2160225236754544e-05, "loss": 0.4813, "step": 4183 }, { "epoch": 1.070912, "grad_norm": 2.234375, "learning_rate": 3.2155959389130625e-05, "loss": 0.4796, "step": 4184 }, { "epoch": 1.071168, "grad_norm": 2.171875, "learning_rate": 3.21516935415067e-05, "loss": 0.4799, "step": 4185 }, { "epoch": 1.071424, "grad_norm": 2.109375, "learning_rate": 3.2147427693882774e-05, "loss": 0.4323, "step": 4186 }, { "epoch": 1.07168, "grad_norm": 2.390625, "learning_rate": 3.214316184625885e-05, "loss": 0.4568, "step": 4187 }, { "epoch": 1.071936, "grad_norm": 2.203125, "learning_rate": 3.2138895998634936e-05, "loss": 0.4761, "step": 4188 }, { "epoch": 1.072192, "grad_norm": 2.296875, "learning_rate": 3.213463015101101e-05, "loss": 0.4539, "step": 4189 }, { "epoch": 1.072448, "grad_norm": 2.21875, "learning_rate": 3.2130364303387084e-05, "loss": 0.4867, "step": 4190 }, { "epoch": 1.072704, "grad_norm": 2.265625, "learning_rate": 3.212609845576316e-05, "loss": 0.4543, "step": 4191 }, { "epoch": 1.07296, "grad_norm": 2.203125, "learning_rate": 3.212183260813924e-05, "loss": 0.4349, "step": 4192 }, { "epoch": 1.073216, "grad_norm": 2.15625, "learning_rate": 3.2117566760515314e-05, "loss": 0.4691, "step": 4193 }, { "epoch": 1.073472, "grad_norm": 2.4375, "learning_rate": 3.2113300912891395e-05, "loss": 0.475, "step": 4194 }, { "epoch": 1.073728, "grad_norm": 2.359375, "learning_rate": 3.210903506526747e-05, "loss": 0.4838, "step": 4195 }, { "epoch": 1.073984, "grad_norm": 2.109375, "learning_rate": 3.210476921764355e-05, "loss": 0.5128, "step": 4196 }, { "epoch": 1.07424, "grad_norm": 2.21875, "learning_rate": 3.2100503370019625e-05, "loss": 0.4628, "step": 4197 }, { "epoch": 1.074496, "grad_norm": 2.140625, "learning_rate": 3.20962375223957e-05, "loss": 0.475, "step": 4198 }, { "epoch": 1.074752, "grad_norm": 2.15625, "learning_rate": 3.209197167477178e-05, "loss": 0.4751, "step": 4199 }, { "epoch": 1.075008, "grad_norm": 2.296875, "learning_rate": 3.2087705827147854e-05, "loss": 0.4671, "step": 4200 }, { "epoch": 1.075264, "grad_norm": 2.28125, "learning_rate": 3.2083439979523935e-05, "loss": 0.4526, "step": 4201 }, { "epoch": 1.07552, "grad_norm": 2.21875, "learning_rate": 3.207917413190001e-05, "loss": 0.4491, "step": 4202 }, { "epoch": 1.075776, "grad_norm": 2.328125, "learning_rate": 3.207490828427609e-05, "loss": 0.4656, "step": 4203 }, { "epoch": 1.076032, "grad_norm": 2.203125, "learning_rate": 3.2070642436652165e-05, "loss": 0.4679, "step": 4204 }, { "epoch": 1.076288, "grad_norm": 2.34375, "learning_rate": 3.206637658902824e-05, "loss": 0.4728, "step": 4205 }, { "epoch": 1.076544, "grad_norm": 2.3125, "learning_rate": 3.206211074140431e-05, "loss": 0.4752, "step": 4206 }, { "epoch": 1.0768, "grad_norm": 2.5, "learning_rate": 3.2057844893780394e-05, "loss": 0.4712, "step": 4207 }, { "epoch": 1.077056, "grad_norm": 2.203125, "learning_rate": 3.2053579046156475e-05, "loss": 0.5074, "step": 4208 }, { "epoch": 1.077312, "grad_norm": 2.21875, "learning_rate": 3.204931319853255e-05, "loss": 0.4351, "step": 4209 }, { "epoch": 1.077568, "grad_norm": 2.25, "learning_rate": 3.2045047350908624e-05, "loss": 0.4419, "step": 4210 }, { "epoch": 1.0778240000000001, "grad_norm": 2.40625, "learning_rate": 3.2040781503284705e-05, "loss": 0.4909, "step": 4211 }, { "epoch": 1.07808, "grad_norm": 2.265625, "learning_rate": 3.203651565566078e-05, "loss": 0.4753, "step": 4212 }, { "epoch": 1.078336, "grad_norm": 2.25, "learning_rate": 3.203224980803686e-05, "loss": 0.4695, "step": 4213 }, { "epoch": 1.078592, "grad_norm": 2.1875, "learning_rate": 3.2027983960412935e-05, "loss": 0.4329, "step": 4214 }, { "epoch": 1.078848, "grad_norm": 2.34375, "learning_rate": 3.2023718112789016e-05, "loss": 0.4976, "step": 4215 }, { "epoch": 1.079104, "grad_norm": 2.34375, "learning_rate": 3.201945226516509e-05, "loss": 0.4189, "step": 4216 }, { "epoch": 1.07936, "grad_norm": 2.328125, "learning_rate": 3.2015186417541164e-05, "loss": 0.4573, "step": 4217 }, { "epoch": 1.079616, "grad_norm": 2.21875, "learning_rate": 3.2010920569917245e-05, "loss": 0.4687, "step": 4218 }, { "epoch": 1.079872, "grad_norm": 2.46875, "learning_rate": 3.200665472229332e-05, "loss": 0.4412, "step": 4219 }, { "epoch": 1.080128, "grad_norm": 2.390625, "learning_rate": 3.20023888746694e-05, "loss": 0.5149, "step": 4220 }, { "epoch": 1.080384, "grad_norm": 2.328125, "learning_rate": 3.1998123027045475e-05, "loss": 0.4784, "step": 4221 }, { "epoch": 1.08064, "grad_norm": 2.234375, "learning_rate": 3.1993857179421556e-05, "loss": 0.4583, "step": 4222 }, { "epoch": 1.080896, "grad_norm": 2.234375, "learning_rate": 3.198959133179763e-05, "loss": 0.4492, "step": 4223 }, { "epoch": 1.081152, "grad_norm": 2.40625, "learning_rate": 3.1985325484173704e-05, "loss": 0.4408, "step": 4224 }, { "epoch": 1.081408, "grad_norm": 2.15625, "learning_rate": 3.198105963654978e-05, "loss": 0.4686, "step": 4225 }, { "epoch": 1.081664, "grad_norm": 2.234375, "learning_rate": 3.197679378892586e-05, "loss": 0.4738, "step": 4226 }, { "epoch": 1.08192, "grad_norm": 2.21875, "learning_rate": 3.197252794130194e-05, "loss": 0.4627, "step": 4227 }, { "epoch": 1.082176, "grad_norm": 2.28125, "learning_rate": 3.1968262093678015e-05, "loss": 0.4687, "step": 4228 }, { "epoch": 1.082432, "grad_norm": 2.203125, "learning_rate": 3.196399624605409e-05, "loss": 0.4723, "step": 4229 }, { "epoch": 1.082688, "grad_norm": 2.390625, "learning_rate": 3.195973039843017e-05, "loss": 0.511, "step": 4230 }, { "epoch": 1.082944, "grad_norm": 2.265625, "learning_rate": 3.1955464550806245e-05, "loss": 0.4524, "step": 4231 }, { "epoch": 1.0832, "grad_norm": 2.109375, "learning_rate": 3.1951198703182326e-05, "loss": 0.4537, "step": 4232 }, { "epoch": 1.083456, "grad_norm": 2.0625, "learning_rate": 3.1946932855558407e-05, "loss": 0.5108, "step": 4233 }, { "epoch": 1.083712, "grad_norm": 2.34375, "learning_rate": 3.194266700793448e-05, "loss": 0.4641, "step": 4234 }, { "epoch": 1.083968, "grad_norm": 2.375, "learning_rate": 3.1938401160310555e-05, "loss": 0.4694, "step": 4235 }, { "epoch": 1.084224, "grad_norm": 2.359375, "learning_rate": 3.193413531268663e-05, "loss": 0.4891, "step": 4236 }, { "epoch": 1.08448, "grad_norm": 1.9921875, "learning_rate": 3.192986946506271e-05, "loss": 0.4677, "step": 4237 }, { "epoch": 1.084736, "grad_norm": 2.3125, "learning_rate": 3.1925603617438785e-05, "loss": 0.4673, "step": 4238 }, { "epoch": 1.084992, "grad_norm": 2.40625, "learning_rate": 3.1921337769814866e-05, "loss": 0.4518, "step": 4239 }, { "epoch": 1.085248, "grad_norm": 2.109375, "learning_rate": 3.191707192219094e-05, "loss": 0.4772, "step": 4240 }, { "epoch": 1.085504, "grad_norm": 2.09375, "learning_rate": 3.191280607456702e-05, "loss": 0.485, "step": 4241 }, { "epoch": 1.08576, "grad_norm": 2.46875, "learning_rate": 3.1908540226943095e-05, "loss": 0.4637, "step": 4242 }, { "epoch": 1.086016, "grad_norm": 2.234375, "learning_rate": 3.190427437931917e-05, "loss": 0.4584, "step": 4243 }, { "epoch": 1.086272, "grad_norm": 2.375, "learning_rate": 3.1900008531695244e-05, "loss": 0.4553, "step": 4244 }, { "epoch": 1.086528, "grad_norm": 2.078125, "learning_rate": 3.1895742684071325e-05, "loss": 0.4875, "step": 4245 }, { "epoch": 1.086784, "grad_norm": 2.09375, "learning_rate": 3.1891476836447406e-05, "loss": 0.4827, "step": 4246 }, { "epoch": 1.08704, "grad_norm": 2.28125, "learning_rate": 3.188721098882348e-05, "loss": 0.5046, "step": 4247 }, { "epoch": 1.087296, "grad_norm": 2.171875, "learning_rate": 3.188294514119956e-05, "loss": 0.4274, "step": 4248 }, { "epoch": 1.087552, "grad_norm": 2.25, "learning_rate": 3.1878679293575636e-05, "loss": 0.4393, "step": 4249 }, { "epoch": 1.0878079999999999, "grad_norm": 2.234375, "learning_rate": 3.187441344595171e-05, "loss": 0.4712, "step": 4250 }, { "epoch": 1.088064, "grad_norm": 2.25, "learning_rate": 3.187014759832779e-05, "loss": 0.4933, "step": 4251 }, { "epoch": 1.08832, "grad_norm": 2.25, "learning_rate": 3.186588175070387e-05, "loss": 0.4637, "step": 4252 }, { "epoch": 1.088576, "grad_norm": 2.078125, "learning_rate": 3.1861615903079946e-05, "loss": 0.4786, "step": 4253 }, { "epoch": 1.088832, "grad_norm": 2.34375, "learning_rate": 3.185735005545602e-05, "loss": 0.4716, "step": 4254 }, { "epoch": 1.089088, "grad_norm": 2.359375, "learning_rate": 3.1853084207832095e-05, "loss": 0.4601, "step": 4255 }, { "epoch": 1.089344, "grad_norm": 2.34375, "learning_rate": 3.1848818360208176e-05, "loss": 0.4939, "step": 4256 }, { "epoch": 1.0896, "grad_norm": 2.03125, "learning_rate": 3.184455251258425e-05, "loss": 0.4422, "step": 4257 }, { "epoch": 1.089856, "grad_norm": 2.046875, "learning_rate": 3.184028666496033e-05, "loss": 0.4615, "step": 4258 }, { "epoch": 1.090112, "grad_norm": 2.125, "learning_rate": 3.1836020817336405e-05, "loss": 0.4571, "step": 4259 }, { "epoch": 1.090368, "grad_norm": 2.296875, "learning_rate": 3.1831754969712486e-05, "loss": 0.4641, "step": 4260 }, { "epoch": 1.090624, "grad_norm": 2.25, "learning_rate": 3.182748912208856e-05, "loss": 0.45, "step": 4261 }, { "epoch": 1.09088, "grad_norm": 2.171875, "learning_rate": 3.1823223274464635e-05, "loss": 0.4549, "step": 4262 }, { "epoch": 1.091136, "grad_norm": 2.125, "learning_rate": 3.181895742684071e-05, "loss": 0.4566, "step": 4263 }, { "epoch": 1.091392, "grad_norm": 2.34375, "learning_rate": 3.181469157921679e-05, "loss": 0.4602, "step": 4264 }, { "epoch": 1.091648, "grad_norm": 2.21875, "learning_rate": 3.181042573159287e-05, "loss": 0.4649, "step": 4265 }, { "epoch": 1.091904, "grad_norm": 2.109375, "learning_rate": 3.1806159883968945e-05, "loss": 0.4094, "step": 4266 }, { "epoch": 1.09216, "grad_norm": 2.109375, "learning_rate": 3.1801894036345027e-05, "loss": 0.4848, "step": 4267 }, { "epoch": 1.092416, "grad_norm": 2.15625, "learning_rate": 3.17976281887211e-05, "loss": 0.4548, "step": 4268 }, { "epoch": 1.092672, "grad_norm": 2.125, "learning_rate": 3.1793362341097175e-05, "loss": 0.4451, "step": 4269 }, { "epoch": 1.092928, "grad_norm": 2.34375, "learning_rate": 3.178909649347325e-05, "loss": 0.4672, "step": 4270 }, { "epoch": 1.093184, "grad_norm": 2.328125, "learning_rate": 3.178483064584934e-05, "loss": 0.4735, "step": 4271 }, { "epoch": 1.09344, "grad_norm": 2.25, "learning_rate": 3.178056479822541e-05, "loss": 0.4947, "step": 4272 }, { "epoch": 1.093696, "grad_norm": 2.296875, "learning_rate": 3.1776298950601486e-05, "loss": 0.4889, "step": 4273 }, { "epoch": 1.093952, "grad_norm": 2.203125, "learning_rate": 3.177203310297756e-05, "loss": 0.484, "step": 4274 }, { "epoch": 1.094208, "grad_norm": 2.203125, "learning_rate": 3.176776725535364e-05, "loss": 0.4961, "step": 4275 }, { "epoch": 1.094464, "grad_norm": 2.296875, "learning_rate": 3.1763501407729715e-05, "loss": 0.463, "step": 4276 }, { "epoch": 1.09472, "grad_norm": 2.3125, "learning_rate": 3.1759235560105796e-05, "loss": 0.4225, "step": 4277 }, { "epoch": 1.094976, "grad_norm": 2.21875, "learning_rate": 3.175496971248187e-05, "loss": 0.4742, "step": 4278 }, { "epoch": 1.095232, "grad_norm": 2.046875, "learning_rate": 3.175070386485795e-05, "loss": 0.5012, "step": 4279 }, { "epoch": 1.095488, "grad_norm": 2.046875, "learning_rate": 3.1746438017234026e-05, "loss": 0.5103, "step": 4280 }, { "epoch": 1.095744, "grad_norm": 1.9921875, "learning_rate": 3.17421721696101e-05, "loss": 0.5072, "step": 4281 }, { "epoch": 1.096, "grad_norm": 2.078125, "learning_rate": 3.173790632198618e-05, "loss": 0.4483, "step": 4282 }, { "epoch": 1.096256, "grad_norm": 2.109375, "learning_rate": 3.1733640474362255e-05, "loss": 0.4582, "step": 4283 }, { "epoch": 1.096512, "grad_norm": 2.078125, "learning_rate": 3.1729374626738336e-05, "loss": 0.4546, "step": 4284 }, { "epoch": 1.096768, "grad_norm": 2.234375, "learning_rate": 3.172510877911441e-05, "loss": 0.4844, "step": 4285 }, { "epoch": 1.097024, "grad_norm": 2.03125, "learning_rate": 3.172084293149049e-05, "loss": 0.4554, "step": 4286 }, { "epoch": 1.09728, "grad_norm": 2.234375, "learning_rate": 3.1716577083866566e-05, "loss": 0.4561, "step": 4287 }, { "epoch": 1.097536, "grad_norm": 2.203125, "learning_rate": 3.171231123624264e-05, "loss": 0.4675, "step": 4288 }, { "epoch": 1.097792, "grad_norm": 2.140625, "learning_rate": 3.1708045388618715e-05, "loss": 0.4804, "step": 4289 }, { "epoch": 1.098048, "grad_norm": 2.234375, "learning_rate": 3.17037795409948e-05, "loss": 0.4585, "step": 4290 }, { "epoch": 1.098304, "grad_norm": 2.046875, "learning_rate": 3.169951369337088e-05, "loss": 0.4624, "step": 4291 }, { "epoch": 1.09856, "grad_norm": 2.203125, "learning_rate": 3.169524784574695e-05, "loss": 0.4816, "step": 4292 }, { "epoch": 1.098816, "grad_norm": 2.09375, "learning_rate": 3.1690981998123025e-05, "loss": 0.4676, "step": 4293 }, { "epoch": 1.099072, "grad_norm": 2.0625, "learning_rate": 3.1686716150499106e-05, "loss": 0.4963, "step": 4294 }, { "epoch": 1.099328, "grad_norm": 2.28125, "learning_rate": 3.168245030287518e-05, "loss": 0.4704, "step": 4295 }, { "epoch": 1.0995840000000001, "grad_norm": 2.203125, "learning_rate": 3.167818445525126e-05, "loss": 0.4913, "step": 4296 }, { "epoch": 1.09984, "grad_norm": 2.03125, "learning_rate": 3.167391860762734e-05, "loss": 0.4622, "step": 4297 }, { "epoch": 1.100096, "grad_norm": 2.09375, "learning_rate": 3.166965276000342e-05, "loss": 0.5046, "step": 4298 }, { "epoch": 1.100352, "grad_norm": 2.0625, "learning_rate": 3.166538691237949e-05, "loss": 0.5073, "step": 4299 }, { "epoch": 1.100608, "grad_norm": 2.359375, "learning_rate": 3.1661121064755565e-05, "loss": 0.474, "step": 4300 }, { "epoch": 1.100864, "grad_norm": 2.15625, "learning_rate": 3.1656855217131646e-05, "loss": 0.4778, "step": 4301 }, { "epoch": 1.10112, "grad_norm": 2.3125, "learning_rate": 3.165258936950772e-05, "loss": 0.4814, "step": 4302 }, { "epoch": 1.101376, "grad_norm": 2.140625, "learning_rate": 3.16483235218838e-05, "loss": 0.4886, "step": 4303 }, { "epoch": 1.101632, "grad_norm": 2.1875, "learning_rate": 3.1644057674259876e-05, "loss": 0.4774, "step": 4304 }, { "epoch": 1.101888, "grad_norm": 2.1875, "learning_rate": 3.163979182663596e-05, "loss": 0.4804, "step": 4305 }, { "epoch": 1.102144, "grad_norm": 2.1875, "learning_rate": 3.163552597901203e-05, "loss": 0.4774, "step": 4306 }, { "epoch": 1.1024, "grad_norm": 2.234375, "learning_rate": 3.1631260131388106e-05, "loss": 0.4906, "step": 4307 }, { "epoch": 1.102656, "grad_norm": 2.234375, "learning_rate": 3.162699428376418e-05, "loss": 0.4852, "step": 4308 }, { "epoch": 1.102912, "grad_norm": 2.28125, "learning_rate": 3.162272843614026e-05, "loss": 0.4468, "step": 4309 }, { "epoch": 1.103168, "grad_norm": 2.265625, "learning_rate": 3.161846258851634e-05, "loss": 0.4981, "step": 4310 }, { "epoch": 1.103424, "grad_norm": 2.296875, "learning_rate": 3.1614196740892416e-05, "loss": 0.4611, "step": 4311 }, { "epoch": 1.10368, "grad_norm": 2.296875, "learning_rate": 3.160993089326849e-05, "loss": 0.4813, "step": 4312 }, { "epoch": 1.103936, "grad_norm": 2.125, "learning_rate": 3.160566504564457e-05, "loss": 0.4761, "step": 4313 }, { "epoch": 1.104192, "grad_norm": 2.1875, "learning_rate": 3.1601399198020646e-05, "loss": 0.4767, "step": 4314 }, { "epoch": 1.104448, "grad_norm": 2.265625, "learning_rate": 3.159713335039673e-05, "loss": 0.4624, "step": 4315 }, { "epoch": 1.104704, "grad_norm": 2.203125, "learning_rate": 3.159286750277281e-05, "loss": 0.4536, "step": 4316 }, { "epoch": 1.10496, "grad_norm": 2.25, "learning_rate": 3.158860165514888e-05, "loss": 0.4736, "step": 4317 }, { "epoch": 1.105216, "grad_norm": 2.4375, "learning_rate": 3.1584335807524956e-05, "loss": 0.4432, "step": 4318 }, { "epoch": 1.105472, "grad_norm": 2.21875, "learning_rate": 3.158006995990103e-05, "loss": 0.4852, "step": 4319 }, { "epoch": 1.105728, "grad_norm": 2.046875, "learning_rate": 3.157580411227711e-05, "loss": 0.4486, "step": 4320 }, { "epoch": 1.105984, "grad_norm": 2.203125, "learning_rate": 3.1571538264653186e-05, "loss": 0.477, "step": 4321 }, { "epoch": 1.1062400000000001, "grad_norm": 2.21875, "learning_rate": 3.156727241702927e-05, "loss": 0.462, "step": 4322 }, { "epoch": 1.106496, "grad_norm": 2.3125, "learning_rate": 3.156300656940534e-05, "loss": 0.4486, "step": 4323 }, { "epoch": 1.106752, "grad_norm": 2.0, "learning_rate": 3.155874072178142e-05, "loss": 0.4911, "step": 4324 }, { "epoch": 1.107008, "grad_norm": 2.125, "learning_rate": 3.1554474874157497e-05, "loss": 0.466, "step": 4325 }, { "epoch": 1.107264, "grad_norm": 2.140625, "learning_rate": 3.155020902653357e-05, "loss": 0.4585, "step": 4326 }, { "epoch": 1.10752, "grad_norm": 2.046875, "learning_rate": 3.1545943178909645e-05, "loss": 0.483, "step": 4327 }, { "epoch": 1.107776, "grad_norm": 2.234375, "learning_rate": 3.1541677331285726e-05, "loss": 0.468, "step": 4328 }, { "epoch": 1.108032, "grad_norm": 2.21875, "learning_rate": 3.153741148366181e-05, "loss": 0.4925, "step": 4329 }, { "epoch": 1.108288, "grad_norm": 2.09375, "learning_rate": 3.153314563603788e-05, "loss": 0.4122, "step": 4330 }, { "epoch": 1.108544, "grad_norm": 2.109375, "learning_rate": 3.152887978841396e-05, "loss": 0.4767, "step": 4331 }, { "epoch": 1.1088, "grad_norm": 2.140625, "learning_rate": 3.152461394079004e-05, "loss": 0.4656, "step": 4332 }, { "epoch": 1.109056, "grad_norm": 2.34375, "learning_rate": 3.152034809316611e-05, "loss": 0.4784, "step": 4333 }, { "epoch": 1.109312, "grad_norm": 2.203125, "learning_rate": 3.151608224554219e-05, "loss": 0.4802, "step": 4334 }, { "epoch": 1.1095679999999999, "grad_norm": 2.140625, "learning_rate": 3.151181639791827e-05, "loss": 0.4488, "step": 4335 }, { "epoch": 1.109824, "grad_norm": 1.953125, "learning_rate": 3.150755055029435e-05, "loss": 0.4568, "step": 4336 }, { "epoch": 1.11008, "grad_norm": 2.09375, "learning_rate": 3.150328470267042e-05, "loss": 0.4496, "step": 4337 }, { "epoch": 1.110336, "grad_norm": 2.1875, "learning_rate": 3.1499018855046496e-05, "loss": 0.4653, "step": 4338 }, { "epoch": 1.110592, "grad_norm": 2.109375, "learning_rate": 3.149475300742258e-05, "loss": 0.4398, "step": 4339 }, { "epoch": 1.110848, "grad_norm": 2.0625, "learning_rate": 3.149048715979865e-05, "loss": 0.4572, "step": 4340 }, { "epoch": 1.111104, "grad_norm": 2.15625, "learning_rate": 3.148622131217473e-05, "loss": 0.4928, "step": 4341 }, { "epoch": 1.11136, "grad_norm": 2.203125, "learning_rate": 3.1481955464550807e-05, "loss": 0.4545, "step": 4342 }, { "epoch": 1.111616, "grad_norm": 2.171875, "learning_rate": 3.147768961692689e-05, "loss": 0.4307, "step": 4343 }, { "epoch": 1.111872, "grad_norm": 2.140625, "learning_rate": 3.147342376930296e-05, "loss": 0.4713, "step": 4344 }, { "epoch": 1.112128, "grad_norm": 2.140625, "learning_rate": 3.1469157921679036e-05, "loss": 0.4859, "step": 4345 }, { "epoch": 1.112384, "grad_norm": 2.203125, "learning_rate": 3.146489207405512e-05, "loss": 0.4606, "step": 4346 }, { "epoch": 1.11264, "grad_norm": 2.140625, "learning_rate": 3.146062622643119e-05, "loss": 0.4831, "step": 4347 }, { "epoch": 1.112896, "grad_norm": 2.046875, "learning_rate": 3.145636037880727e-05, "loss": 0.4902, "step": 4348 }, { "epoch": 1.113152, "grad_norm": 2.109375, "learning_rate": 3.145209453118335e-05, "loss": 0.4766, "step": 4349 }, { "epoch": 1.113408, "grad_norm": 2.53125, "learning_rate": 3.144782868355943e-05, "loss": 0.4901, "step": 4350 }, { "epoch": 1.113664, "grad_norm": 2.375, "learning_rate": 3.14435628359355e-05, "loss": 0.4792, "step": 4351 }, { "epoch": 1.11392, "grad_norm": 2.53125, "learning_rate": 3.1439296988311576e-05, "loss": 0.4549, "step": 4352 }, { "epoch": 1.114176, "grad_norm": 2.28125, "learning_rate": 3.143503114068766e-05, "loss": 0.4845, "step": 4353 }, { "epoch": 1.114432, "grad_norm": 2.234375, "learning_rate": 3.143076529306374e-05, "loss": 0.4901, "step": 4354 }, { "epoch": 1.114688, "grad_norm": 2.171875, "learning_rate": 3.142649944543981e-05, "loss": 0.5236, "step": 4355 }, { "epoch": 1.114944, "grad_norm": 2.09375, "learning_rate": 3.142223359781589e-05, "loss": 0.4772, "step": 4356 }, { "epoch": 1.1152, "grad_norm": 2.078125, "learning_rate": 3.141796775019196e-05, "loss": 0.4566, "step": 4357 }, { "epoch": 1.115456, "grad_norm": 2.28125, "learning_rate": 3.141370190256804e-05, "loss": 0.4886, "step": 4358 }, { "epoch": 1.115712, "grad_norm": 2.296875, "learning_rate": 3.1409436054944117e-05, "loss": 0.4342, "step": 4359 }, { "epoch": 1.115968, "grad_norm": 2.296875, "learning_rate": 3.14051702073202e-05, "loss": 0.468, "step": 4360 }, { "epoch": 1.1162239999999999, "grad_norm": 2.125, "learning_rate": 3.140090435969627e-05, "loss": 0.4659, "step": 4361 }, { "epoch": 1.11648, "grad_norm": 2.078125, "learning_rate": 3.139663851207235e-05, "loss": 0.4976, "step": 4362 }, { "epoch": 1.116736, "grad_norm": 2.3125, "learning_rate": 3.139237266444843e-05, "loss": 0.4343, "step": 4363 }, { "epoch": 1.116992, "grad_norm": 2.015625, "learning_rate": 3.13881068168245e-05, "loss": 0.4639, "step": 4364 }, { "epoch": 1.117248, "grad_norm": 1.9453125, "learning_rate": 3.138384096920058e-05, "loss": 0.4853, "step": 4365 }, { "epoch": 1.117504, "grad_norm": 1.984375, "learning_rate": 3.137957512157666e-05, "loss": 0.4872, "step": 4366 }, { "epoch": 1.11776, "grad_norm": 2.46875, "learning_rate": 3.137530927395274e-05, "loss": 0.4804, "step": 4367 }, { "epoch": 1.118016, "grad_norm": 2.46875, "learning_rate": 3.137104342632881e-05, "loss": 0.4205, "step": 4368 }, { "epoch": 1.118272, "grad_norm": 2.421875, "learning_rate": 3.136677757870489e-05, "loss": 0.4787, "step": 4369 }, { "epoch": 1.118528, "grad_norm": 2.15625, "learning_rate": 3.136251173108097e-05, "loss": 0.4607, "step": 4370 }, { "epoch": 1.118784, "grad_norm": 2.140625, "learning_rate": 3.135824588345704e-05, "loss": 0.472, "step": 4371 }, { "epoch": 1.11904, "grad_norm": 2.359375, "learning_rate": 3.135398003583312e-05, "loss": 0.4908, "step": 4372 }, { "epoch": 1.119296, "grad_norm": 2.3125, "learning_rate": 3.1349714188209204e-05, "loss": 0.4236, "step": 4373 }, { "epoch": 1.119552, "grad_norm": 2.046875, "learning_rate": 3.134544834058528e-05, "loss": 0.4884, "step": 4374 }, { "epoch": 1.119808, "grad_norm": 2.234375, "learning_rate": 3.134118249296135e-05, "loss": 0.4718, "step": 4375 }, { "epoch": 1.120064, "grad_norm": 2.328125, "learning_rate": 3.1336916645337426e-05, "loss": 0.4439, "step": 4376 }, { "epoch": 1.12032, "grad_norm": 2.296875, "learning_rate": 3.133265079771351e-05, "loss": 0.4755, "step": 4377 }, { "epoch": 1.120576, "grad_norm": 2.3125, "learning_rate": 3.132838495008958e-05, "loss": 0.4479, "step": 4378 }, { "epoch": 1.120832, "grad_norm": 2.125, "learning_rate": 3.132411910246566e-05, "loss": 0.4315, "step": 4379 }, { "epoch": 1.121088, "grad_norm": 2.21875, "learning_rate": 3.1319853254841744e-05, "loss": 0.4514, "step": 4380 }, { "epoch": 1.121344, "grad_norm": 2.515625, "learning_rate": 3.131558740721782e-05, "loss": 0.4446, "step": 4381 }, { "epoch": 1.1216, "grad_norm": 2.4375, "learning_rate": 3.131132155959389e-05, "loss": 0.4524, "step": 4382 }, { "epoch": 1.121856, "grad_norm": 2.015625, "learning_rate": 3.130705571196997e-05, "loss": 0.4688, "step": 4383 }, { "epoch": 1.122112, "grad_norm": 2.1875, "learning_rate": 3.130278986434605e-05, "loss": 0.4999, "step": 4384 }, { "epoch": 1.122368, "grad_norm": 2.15625, "learning_rate": 3.129852401672212e-05, "loss": 0.4722, "step": 4385 }, { "epoch": 1.122624, "grad_norm": 2.34375, "learning_rate": 3.12942581690982e-05, "loss": 0.5092, "step": 4386 }, { "epoch": 1.12288, "grad_norm": 2.21875, "learning_rate": 3.128999232147428e-05, "loss": 0.4275, "step": 4387 }, { "epoch": 1.123136, "grad_norm": 2.078125, "learning_rate": 3.128572647385036e-05, "loss": 0.4908, "step": 4388 }, { "epoch": 1.123392, "grad_norm": 2.03125, "learning_rate": 3.128146062622643e-05, "loss": 0.4801, "step": 4389 }, { "epoch": 1.123648, "grad_norm": 2.21875, "learning_rate": 3.127719477860251e-05, "loss": 0.4604, "step": 4390 }, { "epoch": 1.123904, "grad_norm": 2.234375, "learning_rate": 3.127292893097858e-05, "loss": 0.4504, "step": 4391 }, { "epoch": 1.12416, "grad_norm": 2.5625, "learning_rate": 3.126866308335467e-05, "loss": 0.4551, "step": 4392 }, { "epoch": 1.124416, "grad_norm": 2.421875, "learning_rate": 3.126439723573074e-05, "loss": 0.4785, "step": 4393 }, { "epoch": 1.124672, "grad_norm": 2.25, "learning_rate": 3.126013138810682e-05, "loss": 0.4422, "step": 4394 }, { "epoch": 1.124928, "grad_norm": 2.15625, "learning_rate": 3.12558655404829e-05, "loss": 0.4463, "step": 4395 }, { "epoch": 1.125184, "grad_norm": 2.234375, "learning_rate": 3.125159969285897e-05, "loss": 0.4675, "step": 4396 }, { "epoch": 1.12544, "grad_norm": 2.25, "learning_rate": 3.124733384523505e-05, "loss": 0.4971, "step": 4397 }, { "epoch": 1.125696, "grad_norm": 2.296875, "learning_rate": 3.124306799761113e-05, "loss": 0.4431, "step": 4398 }, { "epoch": 1.125952, "grad_norm": 2.359375, "learning_rate": 3.123880214998721e-05, "loss": 0.4362, "step": 4399 }, { "epoch": 1.126208, "grad_norm": 2.140625, "learning_rate": 3.1234536302363283e-05, "loss": 0.4729, "step": 4400 }, { "epoch": 1.126464, "grad_norm": 2.203125, "learning_rate": 3.123027045473936e-05, "loss": 0.4969, "step": 4401 }, { "epoch": 1.12672, "grad_norm": 2.171875, "learning_rate": 3.122600460711543e-05, "loss": 0.4772, "step": 4402 }, { "epoch": 1.126976, "grad_norm": 2.453125, "learning_rate": 3.122173875949151e-05, "loss": 0.4606, "step": 4403 }, { "epoch": 1.127232, "grad_norm": 2.1875, "learning_rate": 3.121747291186759e-05, "loss": 0.5, "step": 4404 }, { "epoch": 1.127488, "grad_norm": 2.234375, "learning_rate": 3.121320706424367e-05, "loss": 0.4449, "step": 4405 }, { "epoch": 1.127744, "grad_norm": 2.453125, "learning_rate": 3.120894121661974e-05, "loss": 0.4533, "step": 4406 }, { "epoch": 1.1280000000000001, "grad_norm": 2.328125, "learning_rate": 3.1204675368995824e-05, "loss": 0.481, "step": 4407 }, { "epoch": 1.128256, "grad_norm": 2.515625, "learning_rate": 3.12004095213719e-05, "loss": 0.464, "step": 4408 }, { "epoch": 1.128512, "grad_norm": 2.359375, "learning_rate": 3.119614367374797e-05, "loss": 0.4797, "step": 4409 }, { "epoch": 1.128768, "grad_norm": 2.484375, "learning_rate": 3.1191877826124046e-05, "loss": 0.4863, "step": 4410 }, { "epoch": 1.129024, "grad_norm": 2.53125, "learning_rate": 3.118761197850013e-05, "loss": 0.4611, "step": 4411 }, { "epoch": 1.12928, "grad_norm": 2.40625, "learning_rate": 3.118334613087621e-05, "loss": 0.4706, "step": 4412 }, { "epoch": 1.129536, "grad_norm": 2.359375, "learning_rate": 3.117908028325228e-05, "loss": 0.4496, "step": 4413 }, { "epoch": 1.129792, "grad_norm": 2.359375, "learning_rate": 3.1174814435628364e-05, "loss": 0.501, "step": 4414 }, { "epoch": 1.130048, "grad_norm": 2.34375, "learning_rate": 3.117054858800444e-05, "loss": 0.5118, "step": 4415 }, { "epoch": 1.130304, "grad_norm": 2.296875, "learning_rate": 3.116628274038051e-05, "loss": 0.4615, "step": 4416 }, { "epoch": 1.13056, "grad_norm": 2.15625, "learning_rate": 3.116201689275659e-05, "loss": 0.4772, "step": 4417 }, { "epoch": 1.130816, "grad_norm": 2.234375, "learning_rate": 3.1157751045132674e-05, "loss": 0.4635, "step": 4418 }, { "epoch": 1.131072, "grad_norm": 2.265625, "learning_rate": 3.115348519750875e-05, "loss": 0.4705, "step": 4419 }, { "epoch": 1.131328, "grad_norm": 2.3125, "learning_rate": 3.114921934988482e-05, "loss": 0.4837, "step": 4420 }, { "epoch": 1.131584, "grad_norm": 1.90625, "learning_rate": 3.11449535022609e-05, "loss": 0.4308, "step": 4421 }, { "epoch": 1.13184, "grad_norm": 1.9765625, "learning_rate": 3.114068765463698e-05, "loss": 0.4826, "step": 4422 }, { "epoch": 1.132096, "grad_norm": 2.234375, "learning_rate": 3.113642180701305e-05, "loss": 0.4152, "step": 4423 }, { "epoch": 1.132352, "grad_norm": 2.328125, "learning_rate": 3.1132155959389134e-05, "loss": 0.4455, "step": 4424 }, { "epoch": 1.132608, "grad_norm": 2.09375, "learning_rate": 3.112789011176521e-05, "loss": 0.4595, "step": 4425 }, { "epoch": 1.132864, "grad_norm": 2.28125, "learning_rate": 3.112362426414129e-05, "loss": 0.5098, "step": 4426 }, { "epoch": 1.13312, "grad_norm": 2.140625, "learning_rate": 3.111935841651736e-05, "loss": 0.4671, "step": 4427 }, { "epoch": 1.133376, "grad_norm": 2.140625, "learning_rate": 3.111509256889344e-05, "loss": 0.4547, "step": 4428 }, { "epoch": 1.133632, "grad_norm": 2.15625, "learning_rate": 3.111082672126952e-05, "loss": 0.4584, "step": 4429 }, { "epoch": 1.133888, "grad_norm": 2.109375, "learning_rate": 3.110656087364559e-05, "loss": 0.4848, "step": 4430 }, { "epoch": 1.134144, "grad_norm": 2.078125, "learning_rate": 3.1102295026021674e-05, "loss": 0.4746, "step": 4431 }, { "epoch": 1.1344, "grad_norm": 2.296875, "learning_rate": 3.109802917839775e-05, "loss": 0.4676, "step": 4432 }, { "epoch": 1.134656, "grad_norm": 2.453125, "learning_rate": 3.109376333077383e-05, "loss": 0.4498, "step": 4433 }, { "epoch": 1.134912, "grad_norm": 2.140625, "learning_rate": 3.10894974831499e-05, "loss": 0.4809, "step": 4434 }, { "epoch": 1.135168, "grad_norm": 2.296875, "learning_rate": 3.108523163552598e-05, "loss": 0.4753, "step": 4435 }, { "epoch": 1.135424, "grad_norm": 2.203125, "learning_rate": 3.108096578790206e-05, "loss": 0.4481, "step": 4436 }, { "epoch": 1.13568, "grad_norm": 2.0625, "learning_rate": 3.107669994027814e-05, "loss": 0.4371, "step": 4437 }, { "epoch": 1.135936, "grad_norm": 2.171875, "learning_rate": 3.1072434092654214e-05, "loss": 0.454, "step": 4438 }, { "epoch": 1.136192, "grad_norm": 2.21875, "learning_rate": 3.106816824503029e-05, "loss": 0.4905, "step": 4439 }, { "epoch": 1.1364480000000001, "grad_norm": 2.328125, "learning_rate": 3.106390239740636e-05, "loss": 0.499, "step": 4440 }, { "epoch": 1.136704, "grad_norm": 2.046875, "learning_rate": 3.1059636549782444e-05, "loss": 0.474, "step": 4441 }, { "epoch": 1.13696, "grad_norm": 2.109375, "learning_rate": 3.105537070215852e-05, "loss": 0.4463, "step": 4442 }, { "epoch": 1.137216, "grad_norm": 2.203125, "learning_rate": 3.10511048545346e-05, "loss": 0.4742, "step": 4443 }, { "epoch": 1.137472, "grad_norm": 2.3125, "learning_rate": 3.104683900691068e-05, "loss": 0.4471, "step": 4444 }, { "epoch": 1.137728, "grad_norm": 2.296875, "learning_rate": 3.1042573159286754e-05, "loss": 0.4748, "step": 4445 }, { "epoch": 1.1379839999999999, "grad_norm": 2.21875, "learning_rate": 3.103830731166283e-05, "loss": 0.4565, "step": 4446 }, { "epoch": 1.13824, "grad_norm": 2.09375, "learning_rate": 3.10340414640389e-05, "loss": 0.4648, "step": 4447 }, { "epoch": 1.138496, "grad_norm": 2.140625, "learning_rate": 3.1029775616414984e-05, "loss": 0.4101, "step": 4448 }, { "epoch": 1.138752, "grad_norm": 2.15625, "learning_rate": 3.102550976879106e-05, "loss": 0.5034, "step": 4449 }, { "epoch": 1.139008, "grad_norm": 2.0625, "learning_rate": 3.102124392116714e-05, "loss": 0.4063, "step": 4450 }, { "epoch": 1.139264, "grad_norm": 2.078125, "learning_rate": 3.101697807354321e-05, "loss": 0.4768, "step": 4451 }, { "epoch": 1.13952, "grad_norm": 2.3125, "learning_rate": 3.1012712225919294e-05, "loss": 0.4316, "step": 4452 }, { "epoch": 1.139776, "grad_norm": 2.140625, "learning_rate": 3.100844637829537e-05, "loss": 0.4523, "step": 4453 }, { "epoch": 1.140032, "grad_norm": 2.4375, "learning_rate": 3.100418053067144e-05, "loss": 0.4971, "step": 4454 }, { "epoch": 1.140288, "grad_norm": 2.625, "learning_rate": 3.0999914683047524e-05, "loss": 0.5111, "step": 4455 }, { "epoch": 1.140544, "grad_norm": 2.40625, "learning_rate": 3.0995648835423605e-05, "loss": 0.452, "step": 4456 }, { "epoch": 1.1408, "grad_norm": 2.296875, "learning_rate": 3.099138298779968e-05, "loss": 0.4453, "step": 4457 }, { "epoch": 1.141056, "grad_norm": 2.21875, "learning_rate": 3.0987117140175753e-05, "loss": 0.4367, "step": 4458 }, { "epoch": 1.141312, "grad_norm": 2.03125, "learning_rate": 3.098285129255183e-05, "loss": 0.4662, "step": 4459 }, { "epoch": 1.141568, "grad_norm": 2.359375, "learning_rate": 3.097858544492791e-05, "loss": 0.4868, "step": 4460 }, { "epoch": 1.141824, "grad_norm": 2.15625, "learning_rate": 3.097431959730398e-05, "loss": 0.423, "step": 4461 }, { "epoch": 1.14208, "grad_norm": 2.21875, "learning_rate": 3.0970053749680064e-05, "loss": 0.4656, "step": 4462 }, { "epoch": 1.142336, "grad_norm": 2.21875, "learning_rate": 3.0965787902056145e-05, "loss": 0.4644, "step": 4463 }, { "epoch": 1.142592, "grad_norm": 2.1875, "learning_rate": 3.096152205443222e-05, "loss": 0.4353, "step": 4464 }, { "epoch": 1.142848, "grad_norm": 2.09375, "learning_rate": 3.0957256206808294e-05, "loss": 0.4897, "step": 4465 }, { "epoch": 1.1431040000000001, "grad_norm": 2.21875, "learning_rate": 3.095299035918437e-05, "loss": 0.4678, "step": 4466 }, { "epoch": 1.14336, "grad_norm": 2.078125, "learning_rate": 3.094872451156045e-05, "loss": 0.4473, "step": 4467 }, { "epoch": 1.143616, "grad_norm": 2.140625, "learning_rate": 3.094445866393652e-05, "loss": 0.4449, "step": 4468 }, { "epoch": 1.143872, "grad_norm": 2.234375, "learning_rate": 3.0940192816312604e-05, "loss": 0.4799, "step": 4469 }, { "epoch": 1.144128, "grad_norm": 2.359375, "learning_rate": 3.093592696868868e-05, "loss": 0.4396, "step": 4470 }, { "epoch": 1.144384, "grad_norm": 2.21875, "learning_rate": 3.093166112106476e-05, "loss": 0.4358, "step": 4471 }, { "epoch": 1.1446399999999999, "grad_norm": 2.359375, "learning_rate": 3.0927395273440834e-05, "loss": 0.4551, "step": 4472 }, { "epoch": 1.144896, "grad_norm": 2.25, "learning_rate": 3.092312942581691e-05, "loss": 0.4656, "step": 4473 }, { "epoch": 1.145152, "grad_norm": 2.03125, "learning_rate": 3.091886357819299e-05, "loss": 0.4823, "step": 4474 }, { "epoch": 1.145408, "grad_norm": 2.1875, "learning_rate": 3.091459773056907e-05, "loss": 0.4313, "step": 4475 }, { "epoch": 1.145664, "grad_norm": 2.015625, "learning_rate": 3.0910331882945144e-05, "loss": 0.4691, "step": 4476 }, { "epoch": 1.14592, "grad_norm": 2.109375, "learning_rate": 3.090606603532122e-05, "loss": 0.453, "step": 4477 }, { "epoch": 1.146176, "grad_norm": 1.953125, "learning_rate": 3.09018001876973e-05, "loss": 0.4595, "step": 4478 }, { "epoch": 1.146432, "grad_norm": 2.4375, "learning_rate": 3.0897534340073374e-05, "loss": 0.4531, "step": 4479 }, { "epoch": 1.146688, "grad_norm": 2.40625, "learning_rate": 3.089326849244945e-05, "loss": 0.4819, "step": 4480 }, { "epoch": 1.146944, "grad_norm": 2.109375, "learning_rate": 3.088900264482553e-05, "loss": 0.5024, "step": 4481 }, { "epoch": 1.1472, "grad_norm": 2.3125, "learning_rate": 3.088473679720161e-05, "loss": 0.4645, "step": 4482 }, { "epoch": 1.147456, "grad_norm": 2.4375, "learning_rate": 3.0880470949577685e-05, "loss": 0.441, "step": 4483 }, { "epoch": 1.147712, "grad_norm": 2.1875, "learning_rate": 3.087620510195376e-05, "loss": 0.4625, "step": 4484 }, { "epoch": 1.147968, "grad_norm": 2.078125, "learning_rate": 3.087193925432983e-05, "loss": 0.4517, "step": 4485 }, { "epoch": 1.148224, "grad_norm": 2.1875, "learning_rate": 3.0867673406705914e-05, "loss": 0.4667, "step": 4486 }, { "epoch": 1.14848, "grad_norm": 2.21875, "learning_rate": 3.086340755908199e-05, "loss": 0.459, "step": 4487 }, { "epoch": 1.148736, "grad_norm": 2.109375, "learning_rate": 3.085914171145807e-05, "loss": 0.4826, "step": 4488 }, { "epoch": 1.148992, "grad_norm": 2.484375, "learning_rate": 3.0854875863834144e-05, "loss": 0.4218, "step": 4489 }, { "epoch": 1.149248, "grad_norm": 2.265625, "learning_rate": 3.0850610016210225e-05, "loss": 0.4532, "step": 4490 }, { "epoch": 1.149504, "grad_norm": 2.171875, "learning_rate": 3.08463441685863e-05, "loss": 0.4739, "step": 4491 }, { "epoch": 1.1497600000000001, "grad_norm": 2.21875, "learning_rate": 3.0842078320962373e-05, "loss": 0.4584, "step": 4492 }, { "epoch": 1.150016, "grad_norm": 2.25, "learning_rate": 3.0837812473338454e-05, "loss": 0.4543, "step": 4493 }, { "epoch": 1.150272, "grad_norm": 2.1875, "learning_rate": 3.0833546625714536e-05, "loss": 0.4469, "step": 4494 }, { "epoch": 1.150528, "grad_norm": 2.375, "learning_rate": 3.082928077809061e-05, "loss": 0.4538, "step": 4495 }, { "epoch": 1.150784, "grad_norm": 2.34375, "learning_rate": 3.0825014930466684e-05, "loss": 0.4673, "step": 4496 }, { "epoch": 1.15104, "grad_norm": 2.1875, "learning_rate": 3.0820749082842765e-05, "loss": 0.4671, "step": 4497 }, { "epoch": 1.151296, "grad_norm": 2.203125, "learning_rate": 3.081648323521884e-05, "loss": 0.4292, "step": 4498 }, { "epoch": 1.151552, "grad_norm": 2.125, "learning_rate": 3.0812217387594914e-05, "loss": 0.4694, "step": 4499 }, { "epoch": 1.151808, "grad_norm": 2.140625, "learning_rate": 3.0807951539970995e-05, "loss": 0.4519, "step": 4500 }, { "epoch": 1.152064, "grad_norm": 2.484375, "learning_rate": 3.0803685692347076e-05, "loss": 0.4417, "step": 4501 }, { "epoch": 1.15232, "grad_norm": 2.296875, "learning_rate": 3.079941984472315e-05, "loss": 0.5055, "step": 4502 }, { "epoch": 1.152576, "grad_norm": 2.25, "learning_rate": 3.0795153997099224e-05, "loss": 0.5238, "step": 4503 }, { "epoch": 1.152832, "grad_norm": 2.078125, "learning_rate": 3.07908881494753e-05, "loss": 0.4613, "step": 4504 }, { "epoch": 1.153088, "grad_norm": 2.078125, "learning_rate": 3.078662230185138e-05, "loss": 0.4503, "step": 4505 }, { "epoch": 1.153344, "grad_norm": 2.28125, "learning_rate": 3.0782356454227454e-05, "loss": 0.4578, "step": 4506 }, { "epoch": 1.1536, "grad_norm": 2.1875, "learning_rate": 3.0778090606603535e-05, "loss": 0.4857, "step": 4507 }, { "epoch": 1.153856, "grad_norm": 2.1875, "learning_rate": 3.077382475897961e-05, "loss": 0.4692, "step": 4508 }, { "epoch": 1.154112, "grad_norm": 2.15625, "learning_rate": 3.076955891135569e-05, "loss": 0.4599, "step": 4509 }, { "epoch": 1.154368, "grad_norm": 2.171875, "learning_rate": 3.0765293063731764e-05, "loss": 0.4288, "step": 4510 }, { "epoch": 1.154624, "grad_norm": 2.21875, "learning_rate": 3.076102721610784e-05, "loss": 0.402, "step": 4511 }, { "epoch": 1.15488, "grad_norm": 2.03125, "learning_rate": 3.075676136848392e-05, "loss": 0.4684, "step": 4512 }, { "epoch": 1.155136, "grad_norm": 2.1875, "learning_rate": 3.075249552086e-05, "loss": 0.4498, "step": 4513 }, { "epoch": 1.155392, "grad_norm": 2.296875, "learning_rate": 3.0748229673236075e-05, "loss": 0.4898, "step": 4514 }, { "epoch": 1.155648, "grad_norm": 2.078125, "learning_rate": 3.074396382561215e-05, "loss": 0.4683, "step": 4515 }, { "epoch": 1.155904, "grad_norm": 2.140625, "learning_rate": 3.073969797798823e-05, "loss": 0.4857, "step": 4516 }, { "epoch": 1.15616, "grad_norm": 2.21875, "learning_rate": 3.0735432130364305e-05, "loss": 0.5124, "step": 4517 }, { "epoch": 1.156416, "grad_norm": 2.40625, "learning_rate": 3.073116628274038e-05, "loss": 0.4675, "step": 4518 }, { "epoch": 1.156672, "grad_norm": 2.25, "learning_rate": 3.072690043511646e-05, "loss": 0.4837, "step": 4519 }, { "epoch": 1.156928, "grad_norm": 2.15625, "learning_rate": 3.072263458749254e-05, "loss": 0.4882, "step": 4520 }, { "epoch": 1.157184, "grad_norm": 2.046875, "learning_rate": 3.0718368739868615e-05, "loss": 0.4578, "step": 4521 }, { "epoch": 1.15744, "grad_norm": 2.015625, "learning_rate": 3.071410289224469e-05, "loss": 0.4682, "step": 4522 }, { "epoch": 1.157696, "grad_norm": 2.125, "learning_rate": 3.0709837044620764e-05, "loss": 0.476, "step": 4523 }, { "epoch": 1.157952, "grad_norm": 2.078125, "learning_rate": 3.0705571196996845e-05, "loss": 0.4604, "step": 4524 }, { "epoch": 1.158208, "grad_norm": 2.09375, "learning_rate": 3.070130534937292e-05, "loss": 0.468, "step": 4525 }, { "epoch": 1.158464, "grad_norm": 2.125, "learning_rate": 3.0697039501749e-05, "loss": 0.4454, "step": 4526 }, { "epoch": 1.15872, "grad_norm": 2.125, "learning_rate": 3.069277365412508e-05, "loss": 0.4538, "step": 4527 }, { "epoch": 1.158976, "grad_norm": 2.125, "learning_rate": 3.0688507806501155e-05, "loss": 0.4874, "step": 4528 }, { "epoch": 1.159232, "grad_norm": 2.078125, "learning_rate": 3.068424195887723e-05, "loss": 0.4462, "step": 4529 }, { "epoch": 1.159488, "grad_norm": 2.140625, "learning_rate": 3.0679976111253304e-05, "loss": 0.4676, "step": 4530 }, { "epoch": 1.1597439999999999, "grad_norm": 2.203125, "learning_rate": 3.0675710263629385e-05, "loss": 0.4619, "step": 4531 }, { "epoch": 1.16, "grad_norm": 2.09375, "learning_rate": 3.067144441600546e-05, "loss": 0.4442, "step": 4532 }, { "epoch": 1.160256, "grad_norm": 2.1875, "learning_rate": 3.066717856838154e-05, "loss": 0.4736, "step": 4533 }, { "epoch": 1.160512, "grad_norm": 2.296875, "learning_rate": 3.0662912720757615e-05, "loss": 0.4522, "step": 4534 }, { "epoch": 1.160768, "grad_norm": 2.375, "learning_rate": 3.0658646873133696e-05, "loss": 0.4575, "step": 4535 }, { "epoch": 1.161024, "grad_norm": 2.21875, "learning_rate": 3.065438102550977e-05, "loss": 0.4764, "step": 4536 }, { "epoch": 1.16128, "grad_norm": 2.484375, "learning_rate": 3.0650115177885844e-05, "loss": 0.4675, "step": 4537 }, { "epoch": 1.161536, "grad_norm": 2.21875, "learning_rate": 3.0645849330261925e-05, "loss": 0.4804, "step": 4538 }, { "epoch": 1.161792, "grad_norm": 1.9765625, "learning_rate": 3.0641583482638006e-05, "loss": 0.4497, "step": 4539 }, { "epoch": 1.162048, "grad_norm": 2.234375, "learning_rate": 3.063731763501408e-05, "loss": 0.4982, "step": 4540 }, { "epoch": 1.162304, "grad_norm": 2.40625, "learning_rate": 3.0633051787390155e-05, "loss": 0.4859, "step": 4541 }, { "epoch": 1.16256, "grad_norm": 2.15625, "learning_rate": 3.0628785939766236e-05, "loss": 0.482, "step": 4542 }, { "epoch": 1.162816, "grad_norm": 2.078125, "learning_rate": 3.062452009214231e-05, "loss": 0.4295, "step": 4543 }, { "epoch": 1.163072, "grad_norm": 2.125, "learning_rate": 3.0620254244518384e-05, "loss": 0.4657, "step": 4544 }, { "epoch": 1.163328, "grad_norm": 2.21875, "learning_rate": 3.0615988396894465e-05, "loss": 0.4672, "step": 4545 }, { "epoch": 1.163584, "grad_norm": 2.265625, "learning_rate": 3.0611722549270546e-05, "loss": 0.4402, "step": 4546 }, { "epoch": 1.16384, "grad_norm": 2.1875, "learning_rate": 3.060745670164662e-05, "loss": 0.4579, "step": 4547 }, { "epoch": 1.164096, "grad_norm": 2.171875, "learning_rate": 3.0603190854022695e-05, "loss": 0.4705, "step": 4548 }, { "epoch": 1.164352, "grad_norm": 2.140625, "learning_rate": 3.059892500639877e-05, "loss": 0.4415, "step": 4549 }, { "epoch": 1.164608, "grad_norm": 2.03125, "learning_rate": 3.059465915877485e-05, "loss": 0.4504, "step": 4550 }, { "epoch": 1.1648640000000001, "grad_norm": 2.046875, "learning_rate": 3.0590393311150925e-05, "loss": 0.4621, "step": 4551 }, { "epoch": 1.16512, "grad_norm": 2.171875, "learning_rate": 3.0586127463527006e-05, "loss": 0.4391, "step": 4552 }, { "epoch": 1.165376, "grad_norm": 2.0, "learning_rate": 3.058186161590308e-05, "loss": 0.5252, "step": 4553 }, { "epoch": 1.165632, "grad_norm": 2.046875, "learning_rate": 3.057759576827916e-05, "loss": 0.4772, "step": 4554 }, { "epoch": 1.165888, "grad_norm": 2.015625, "learning_rate": 3.0573329920655235e-05, "loss": 0.4485, "step": 4555 }, { "epoch": 1.166144, "grad_norm": 1.9921875, "learning_rate": 3.056906407303131e-05, "loss": 0.4832, "step": 4556 }, { "epoch": 1.1663999999999999, "grad_norm": 2.0, "learning_rate": 3.056479822540739e-05, "loss": 0.4706, "step": 4557 }, { "epoch": 1.166656, "grad_norm": 2.109375, "learning_rate": 3.056053237778347e-05, "loss": 0.4295, "step": 4558 }, { "epoch": 1.166912, "grad_norm": 2.109375, "learning_rate": 3.0556266530159546e-05, "loss": 0.446, "step": 4559 }, { "epoch": 1.167168, "grad_norm": 2.015625, "learning_rate": 3.055200068253562e-05, "loss": 0.4769, "step": 4560 }, { "epoch": 1.167424, "grad_norm": 2.21875, "learning_rate": 3.05477348349117e-05, "loss": 0.4736, "step": 4561 }, { "epoch": 1.16768, "grad_norm": 2.15625, "learning_rate": 3.0543468987287775e-05, "loss": 0.4748, "step": 4562 }, { "epoch": 1.167936, "grad_norm": 2.046875, "learning_rate": 3.053920313966385e-05, "loss": 0.4741, "step": 4563 }, { "epoch": 1.168192, "grad_norm": 2.09375, "learning_rate": 3.053493729203993e-05, "loss": 0.5136, "step": 4564 }, { "epoch": 1.168448, "grad_norm": 2.015625, "learning_rate": 3.053067144441601e-05, "loss": 0.499, "step": 4565 }, { "epoch": 1.168704, "grad_norm": 2.078125, "learning_rate": 3.0526405596792086e-05, "loss": 0.4792, "step": 4566 }, { "epoch": 1.16896, "grad_norm": 2.15625, "learning_rate": 3.052213974916816e-05, "loss": 0.4732, "step": 4567 }, { "epoch": 1.169216, "grad_norm": 2.296875, "learning_rate": 3.0517873901544234e-05, "loss": 0.4445, "step": 4568 }, { "epoch": 1.169472, "grad_norm": 2.046875, "learning_rate": 3.051360805392032e-05, "loss": 0.4265, "step": 4569 }, { "epoch": 1.169728, "grad_norm": 2.40625, "learning_rate": 3.0509342206296393e-05, "loss": 0.5065, "step": 4570 }, { "epoch": 1.169984, "grad_norm": 2.0, "learning_rate": 3.0505076358672467e-05, "loss": 0.4873, "step": 4571 }, { "epoch": 1.17024, "grad_norm": 1.9609375, "learning_rate": 3.0500810511048545e-05, "loss": 0.482, "step": 4572 }, { "epoch": 1.170496, "grad_norm": 2.078125, "learning_rate": 3.0496544663424626e-05, "loss": 0.5186, "step": 4573 }, { "epoch": 1.170752, "grad_norm": 2.1875, "learning_rate": 3.04922788158007e-05, "loss": 0.4418, "step": 4574 }, { "epoch": 1.171008, "grad_norm": 2.359375, "learning_rate": 3.0488012968176778e-05, "loss": 0.481, "step": 4575 }, { "epoch": 1.171264, "grad_norm": 2.15625, "learning_rate": 3.048374712055286e-05, "loss": 0.4925, "step": 4576 }, { "epoch": 1.1715200000000001, "grad_norm": 2.109375, "learning_rate": 3.0479481272928933e-05, "loss": 0.4854, "step": 4577 }, { "epoch": 1.171776, "grad_norm": 2.140625, "learning_rate": 3.0475215425305008e-05, "loss": 0.4283, "step": 4578 }, { "epoch": 1.172032, "grad_norm": 2.234375, "learning_rate": 3.0470949577681085e-05, "loss": 0.4792, "step": 4579 }, { "epoch": 1.172288, "grad_norm": 2.3125, "learning_rate": 3.0466683730057166e-05, "loss": 0.4668, "step": 4580 }, { "epoch": 1.172544, "grad_norm": 1.9921875, "learning_rate": 3.046241788243324e-05, "loss": 0.5002, "step": 4581 }, { "epoch": 1.1728, "grad_norm": 1.9921875, "learning_rate": 3.0458152034809318e-05, "loss": 0.4999, "step": 4582 }, { "epoch": 1.1730559999999999, "grad_norm": 2.09375, "learning_rate": 3.0453886187185393e-05, "loss": 0.5085, "step": 4583 }, { "epoch": 1.173312, "grad_norm": 2.25, "learning_rate": 3.0449620339561474e-05, "loss": 0.4799, "step": 4584 }, { "epoch": 1.173568, "grad_norm": 2.109375, "learning_rate": 3.044535449193755e-05, "loss": 0.4654, "step": 4585 }, { "epoch": 1.173824, "grad_norm": 2.1875, "learning_rate": 3.0441088644313626e-05, "loss": 0.4726, "step": 4586 }, { "epoch": 1.17408, "grad_norm": 2.203125, "learning_rate": 3.04368227966897e-05, "loss": 0.4482, "step": 4587 }, { "epoch": 1.174336, "grad_norm": 2.109375, "learning_rate": 3.043255694906578e-05, "loss": 0.4454, "step": 4588 }, { "epoch": 1.174592, "grad_norm": 2.234375, "learning_rate": 3.042829110144186e-05, "loss": 0.4608, "step": 4589 }, { "epoch": 1.174848, "grad_norm": 2.15625, "learning_rate": 3.0424025253817933e-05, "loss": 0.4575, "step": 4590 }, { "epoch": 1.175104, "grad_norm": 2.34375, "learning_rate": 3.041975940619401e-05, "loss": 0.5161, "step": 4591 }, { "epoch": 1.17536, "grad_norm": 2.234375, "learning_rate": 3.041549355857009e-05, "loss": 0.4451, "step": 4592 }, { "epoch": 1.175616, "grad_norm": 2.109375, "learning_rate": 3.0411227710946166e-05, "loss": 0.4653, "step": 4593 }, { "epoch": 1.175872, "grad_norm": 2.265625, "learning_rate": 3.0406961863322243e-05, "loss": 0.4301, "step": 4594 }, { "epoch": 1.176128, "grad_norm": 2.28125, "learning_rate": 3.0402696015698324e-05, "loss": 0.4761, "step": 4595 }, { "epoch": 1.176384, "grad_norm": 2.09375, "learning_rate": 3.03984301680744e-05, "loss": 0.4678, "step": 4596 }, { "epoch": 1.17664, "grad_norm": 2.328125, "learning_rate": 3.0394164320450473e-05, "loss": 0.4602, "step": 4597 }, { "epoch": 1.176896, "grad_norm": 2.40625, "learning_rate": 3.038989847282655e-05, "loss": 0.4667, "step": 4598 }, { "epoch": 1.177152, "grad_norm": 2.40625, "learning_rate": 3.038563262520263e-05, "loss": 0.4587, "step": 4599 }, { "epoch": 1.177408, "grad_norm": 2.234375, "learning_rate": 3.0381366777578706e-05, "loss": 0.4459, "step": 4600 }, { "epoch": 1.177664, "grad_norm": 2.09375, "learning_rate": 3.0377100929954784e-05, "loss": 0.4826, "step": 4601 }, { "epoch": 1.17792, "grad_norm": 2.140625, "learning_rate": 3.0372835082330858e-05, "loss": 0.3995, "step": 4602 }, { "epoch": 1.1781760000000001, "grad_norm": 2.171875, "learning_rate": 3.036856923470694e-05, "loss": 0.4437, "step": 4603 }, { "epoch": 1.178432, "grad_norm": 2.25, "learning_rate": 3.0364303387083017e-05, "loss": 0.4635, "step": 4604 }, { "epoch": 1.178688, "grad_norm": 2.3125, "learning_rate": 3.036003753945909e-05, "loss": 0.4479, "step": 4605 }, { "epoch": 1.178944, "grad_norm": 2.09375, "learning_rate": 3.0355771691835165e-05, "loss": 0.4501, "step": 4606 }, { "epoch": 1.1792, "grad_norm": 2.328125, "learning_rate": 3.0351505844211246e-05, "loss": 0.4371, "step": 4607 }, { "epoch": 1.179456, "grad_norm": 2.109375, "learning_rate": 3.0347239996587324e-05, "loss": 0.4381, "step": 4608 }, { "epoch": 1.179712, "grad_norm": 2.484375, "learning_rate": 3.0342974148963398e-05, "loss": 0.4749, "step": 4609 }, { "epoch": 1.179968, "grad_norm": 2.265625, "learning_rate": 3.033870830133948e-05, "loss": 0.4741, "step": 4610 }, { "epoch": 1.180224, "grad_norm": 2.109375, "learning_rate": 3.0334442453715557e-05, "loss": 0.4801, "step": 4611 }, { "epoch": 1.18048, "grad_norm": 2.453125, "learning_rate": 3.033017660609163e-05, "loss": 0.4516, "step": 4612 }, { "epoch": 1.180736, "grad_norm": 2.171875, "learning_rate": 3.032591075846771e-05, "loss": 0.466, "step": 4613 }, { "epoch": 1.180992, "grad_norm": 2.1875, "learning_rate": 3.032164491084379e-05, "loss": 0.4795, "step": 4614 }, { "epoch": 1.181248, "grad_norm": 2.265625, "learning_rate": 3.0317379063219864e-05, "loss": 0.4161, "step": 4615 }, { "epoch": 1.1815039999999999, "grad_norm": 2.203125, "learning_rate": 3.0313113215595938e-05, "loss": 0.4578, "step": 4616 }, { "epoch": 1.18176, "grad_norm": 1.9609375, "learning_rate": 3.0308847367972016e-05, "loss": 0.4527, "step": 4617 }, { "epoch": 1.182016, "grad_norm": 2.0625, "learning_rate": 3.0304581520348097e-05, "loss": 0.4299, "step": 4618 }, { "epoch": 1.182272, "grad_norm": 1.984375, "learning_rate": 3.030031567272417e-05, "loss": 0.4678, "step": 4619 }, { "epoch": 1.182528, "grad_norm": 1.921875, "learning_rate": 3.029604982510025e-05, "loss": 0.4725, "step": 4620 }, { "epoch": 1.182784, "grad_norm": 2.296875, "learning_rate": 3.0291783977476323e-05, "loss": 0.4761, "step": 4621 }, { "epoch": 1.18304, "grad_norm": 2.21875, "learning_rate": 3.0287518129852404e-05, "loss": 0.4731, "step": 4622 }, { "epoch": 1.183296, "grad_norm": 2.359375, "learning_rate": 3.0283252282228482e-05, "loss": 0.467, "step": 4623 }, { "epoch": 1.183552, "grad_norm": 2.359375, "learning_rate": 3.0278986434604556e-05, "loss": 0.4819, "step": 4624 }, { "epoch": 1.183808, "grad_norm": 2.296875, "learning_rate": 3.0274720586980637e-05, "loss": 0.4577, "step": 4625 }, { "epoch": 1.184064, "grad_norm": 2.15625, "learning_rate": 3.027045473935671e-05, "loss": 0.4767, "step": 4626 }, { "epoch": 1.18432, "grad_norm": 2.40625, "learning_rate": 3.026618889173279e-05, "loss": 0.4774, "step": 4627 }, { "epoch": 1.184576, "grad_norm": 2.078125, "learning_rate": 3.0261923044108863e-05, "loss": 0.476, "step": 4628 }, { "epoch": 1.184832, "grad_norm": 2.0625, "learning_rate": 3.0257657196484944e-05, "loss": 0.5066, "step": 4629 }, { "epoch": 1.185088, "grad_norm": 2.203125, "learning_rate": 3.0253391348861022e-05, "loss": 0.4793, "step": 4630 }, { "epoch": 1.185344, "grad_norm": 2.34375, "learning_rate": 3.0249125501237096e-05, "loss": 0.4725, "step": 4631 }, { "epoch": 1.1856, "grad_norm": 2.265625, "learning_rate": 3.0244859653613174e-05, "loss": 0.5027, "step": 4632 }, { "epoch": 1.185856, "grad_norm": 2.203125, "learning_rate": 3.0240593805989255e-05, "loss": 0.4561, "step": 4633 }, { "epoch": 1.186112, "grad_norm": 2.21875, "learning_rate": 3.023632795836533e-05, "loss": 0.4559, "step": 4634 }, { "epoch": 1.186368, "grad_norm": 2.0, "learning_rate": 3.0232062110741403e-05, "loss": 0.4443, "step": 4635 }, { "epoch": 1.1866240000000001, "grad_norm": 2.140625, "learning_rate": 3.022779626311748e-05, "loss": 0.4431, "step": 4636 }, { "epoch": 1.18688, "grad_norm": 2.125, "learning_rate": 3.0223530415493562e-05, "loss": 0.471, "step": 4637 }, { "epoch": 1.187136, "grad_norm": 2.3125, "learning_rate": 3.0219264567869636e-05, "loss": 0.4754, "step": 4638 }, { "epoch": 1.187392, "grad_norm": 2.390625, "learning_rate": 3.0214998720245714e-05, "loss": 0.4267, "step": 4639 }, { "epoch": 1.187648, "grad_norm": 2.09375, "learning_rate": 3.021073287262179e-05, "loss": 0.4704, "step": 4640 }, { "epoch": 1.187904, "grad_norm": 2.203125, "learning_rate": 3.020646702499787e-05, "loss": 0.4671, "step": 4641 }, { "epoch": 1.1881599999999999, "grad_norm": 2.296875, "learning_rate": 3.0202201177373947e-05, "loss": 0.4465, "step": 4642 }, { "epoch": 1.188416, "grad_norm": 2.09375, "learning_rate": 3.019793532975002e-05, "loss": 0.4463, "step": 4643 }, { "epoch": 1.188672, "grad_norm": 2.296875, "learning_rate": 3.0193669482126102e-05, "loss": 0.4259, "step": 4644 }, { "epoch": 1.188928, "grad_norm": 2.15625, "learning_rate": 3.0189403634502177e-05, "loss": 0.4798, "step": 4645 }, { "epoch": 1.189184, "grad_norm": 2.171875, "learning_rate": 3.0185137786878254e-05, "loss": 0.4263, "step": 4646 }, { "epoch": 1.18944, "grad_norm": 2.203125, "learning_rate": 3.018087193925433e-05, "loss": 0.4608, "step": 4647 }, { "epoch": 1.189696, "grad_norm": 2.390625, "learning_rate": 3.017660609163041e-05, "loss": 0.4329, "step": 4648 }, { "epoch": 1.189952, "grad_norm": 2.0625, "learning_rate": 3.0172340244006487e-05, "loss": 0.4984, "step": 4649 }, { "epoch": 1.190208, "grad_norm": 2.265625, "learning_rate": 3.016807439638256e-05, "loss": 0.4654, "step": 4650 }, { "epoch": 1.190464, "grad_norm": 2.4375, "learning_rate": 3.016380854875864e-05, "loss": 0.456, "step": 4651 }, { "epoch": 1.19072, "grad_norm": 2.28125, "learning_rate": 3.015954270113472e-05, "loss": 0.4896, "step": 4652 }, { "epoch": 1.190976, "grad_norm": 2.328125, "learning_rate": 3.0155276853510794e-05, "loss": 0.4857, "step": 4653 }, { "epoch": 1.191232, "grad_norm": 2.1875, "learning_rate": 3.015101100588687e-05, "loss": 0.4679, "step": 4654 }, { "epoch": 1.191488, "grad_norm": 2.09375, "learning_rate": 3.0146745158262946e-05, "loss": 0.4847, "step": 4655 }, { "epoch": 1.191744, "grad_norm": 2.15625, "learning_rate": 3.0142479310639027e-05, "loss": 0.4762, "step": 4656 }, { "epoch": 1.192, "grad_norm": 2.265625, "learning_rate": 3.0138213463015102e-05, "loss": 0.4202, "step": 4657 }, { "epoch": 1.192256, "grad_norm": 2.09375, "learning_rate": 3.013394761539118e-05, "loss": 0.4186, "step": 4658 }, { "epoch": 1.192512, "grad_norm": 2.15625, "learning_rate": 3.012968176776726e-05, "loss": 0.4607, "step": 4659 }, { "epoch": 1.192768, "grad_norm": 2.171875, "learning_rate": 3.0125415920143335e-05, "loss": 0.4498, "step": 4660 }, { "epoch": 1.193024, "grad_norm": 2.140625, "learning_rate": 3.0121150072519412e-05, "loss": 0.4955, "step": 4661 }, { "epoch": 1.1932800000000001, "grad_norm": 2.171875, "learning_rate": 3.0116884224895487e-05, "loss": 0.4611, "step": 4662 }, { "epoch": 1.193536, "grad_norm": 2.203125, "learning_rate": 3.0112618377271568e-05, "loss": 0.4334, "step": 4663 }, { "epoch": 1.193792, "grad_norm": 2.171875, "learning_rate": 3.0108352529647642e-05, "loss": 0.456, "step": 4664 }, { "epoch": 1.194048, "grad_norm": 2.328125, "learning_rate": 3.010408668202372e-05, "loss": 0.4636, "step": 4665 }, { "epoch": 1.194304, "grad_norm": 2.140625, "learning_rate": 3.0099820834399794e-05, "loss": 0.4753, "step": 4666 }, { "epoch": 1.19456, "grad_norm": 2.25, "learning_rate": 3.0095554986775875e-05, "loss": 0.4647, "step": 4667 }, { "epoch": 1.1948159999999999, "grad_norm": 2.046875, "learning_rate": 3.0091289139151953e-05, "loss": 0.4314, "step": 4668 }, { "epoch": 1.195072, "grad_norm": 1.9609375, "learning_rate": 3.0087023291528027e-05, "loss": 0.4687, "step": 4669 }, { "epoch": 1.195328, "grad_norm": 2.140625, "learning_rate": 3.00827574439041e-05, "loss": 0.4289, "step": 4670 }, { "epoch": 1.195584, "grad_norm": 2.078125, "learning_rate": 3.0078491596280185e-05, "loss": 0.4406, "step": 4671 }, { "epoch": 1.19584, "grad_norm": 2.171875, "learning_rate": 3.007422574865626e-05, "loss": 0.4896, "step": 4672 }, { "epoch": 1.196096, "grad_norm": 2.171875, "learning_rate": 3.0069959901032334e-05, "loss": 0.4505, "step": 4673 }, { "epoch": 1.196352, "grad_norm": 2.25, "learning_rate": 3.0065694053408415e-05, "loss": 0.4598, "step": 4674 }, { "epoch": 1.196608, "grad_norm": 2.265625, "learning_rate": 3.0061428205784493e-05, "loss": 0.4257, "step": 4675 }, { "epoch": 1.196864, "grad_norm": 1.9921875, "learning_rate": 3.0057162358160567e-05, "loss": 0.4857, "step": 4676 }, { "epoch": 1.19712, "grad_norm": 2.078125, "learning_rate": 3.0052896510536645e-05, "loss": 0.4161, "step": 4677 }, { "epoch": 1.197376, "grad_norm": 2.0625, "learning_rate": 3.0048630662912726e-05, "loss": 0.4241, "step": 4678 }, { "epoch": 1.197632, "grad_norm": 2.171875, "learning_rate": 3.00443648152888e-05, "loss": 0.4789, "step": 4679 }, { "epoch": 1.197888, "grad_norm": 1.9765625, "learning_rate": 3.0040098967664874e-05, "loss": 0.4597, "step": 4680 }, { "epoch": 1.198144, "grad_norm": 2.234375, "learning_rate": 3.0035833120040952e-05, "loss": 0.476, "step": 4681 }, { "epoch": 1.1984, "grad_norm": 2.203125, "learning_rate": 3.0031567272417033e-05, "loss": 0.4789, "step": 4682 }, { "epoch": 1.198656, "grad_norm": 2.28125, "learning_rate": 3.0027301424793107e-05, "loss": 0.4481, "step": 4683 }, { "epoch": 1.198912, "grad_norm": 2.015625, "learning_rate": 3.0023035577169185e-05, "loss": 0.491, "step": 4684 }, { "epoch": 1.199168, "grad_norm": 2.1875, "learning_rate": 3.001876972954526e-05, "loss": 0.4427, "step": 4685 }, { "epoch": 1.199424, "grad_norm": 2.21875, "learning_rate": 3.001450388192134e-05, "loss": 0.4521, "step": 4686 }, { "epoch": 1.19968, "grad_norm": 2.375, "learning_rate": 3.0010238034297418e-05, "loss": 0.4826, "step": 4687 }, { "epoch": 1.1999360000000001, "grad_norm": 2.03125, "learning_rate": 3.0005972186673492e-05, "loss": 0.4503, "step": 4688 }, { "epoch": 1.200192, "grad_norm": 2.234375, "learning_rate": 3.0001706339049566e-05, "loss": 0.4591, "step": 4689 }, { "epoch": 1.200448, "grad_norm": 2.15625, "learning_rate": 2.999744049142565e-05, "loss": 0.4714, "step": 4690 }, { "epoch": 1.200704, "grad_norm": 2.390625, "learning_rate": 2.9993174643801725e-05, "loss": 0.4688, "step": 4691 }, { "epoch": 1.20096, "grad_norm": 2.21875, "learning_rate": 2.99889087961778e-05, "loss": 0.4449, "step": 4692 }, { "epoch": 1.201216, "grad_norm": 2.171875, "learning_rate": 2.998464294855388e-05, "loss": 0.4897, "step": 4693 }, { "epoch": 1.201472, "grad_norm": 2.34375, "learning_rate": 2.9980377100929958e-05, "loss": 0.4622, "step": 4694 }, { "epoch": 1.201728, "grad_norm": 2.296875, "learning_rate": 2.9976111253306032e-05, "loss": 0.4744, "step": 4695 }, { "epoch": 1.201984, "grad_norm": 2.421875, "learning_rate": 2.997184540568211e-05, "loss": 0.4409, "step": 4696 }, { "epoch": 1.20224, "grad_norm": 2.140625, "learning_rate": 2.996757955805819e-05, "loss": 0.4737, "step": 4697 }, { "epoch": 1.202496, "grad_norm": 2.28125, "learning_rate": 2.9963313710434265e-05, "loss": 0.4615, "step": 4698 }, { "epoch": 1.202752, "grad_norm": 2.3125, "learning_rate": 2.995904786281034e-05, "loss": 0.4454, "step": 4699 }, { "epoch": 1.203008, "grad_norm": 2.34375, "learning_rate": 2.9954782015186417e-05, "loss": 0.4756, "step": 4700 }, { "epoch": 1.203264, "grad_norm": 2.078125, "learning_rate": 2.9950516167562498e-05, "loss": 0.4477, "step": 4701 }, { "epoch": 1.20352, "grad_norm": 2.203125, "learning_rate": 2.9946250319938572e-05, "loss": 0.4959, "step": 4702 }, { "epoch": 1.203776, "grad_norm": 2.34375, "learning_rate": 2.994198447231465e-05, "loss": 0.469, "step": 4703 }, { "epoch": 1.204032, "grad_norm": 2.203125, "learning_rate": 2.9937718624690724e-05, "loss": 0.4216, "step": 4704 }, { "epoch": 1.204288, "grad_norm": 2.140625, "learning_rate": 2.9933452777066805e-05, "loss": 0.4475, "step": 4705 }, { "epoch": 1.204544, "grad_norm": 2.3125, "learning_rate": 2.9929186929442883e-05, "loss": 0.4809, "step": 4706 }, { "epoch": 1.2048, "grad_norm": 2.21875, "learning_rate": 2.9924921081818957e-05, "loss": 0.4802, "step": 4707 }, { "epoch": 1.205056, "grad_norm": 2.03125, "learning_rate": 2.992065523419504e-05, "loss": 0.4683, "step": 4708 }, { "epoch": 1.205312, "grad_norm": 2.078125, "learning_rate": 2.9916389386571113e-05, "loss": 0.4861, "step": 4709 }, { "epoch": 1.205568, "grad_norm": 2.09375, "learning_rate": 2.991212353894719e-05, "loss": 0.4673, "step": 4710 }, { "epoch": 1.205824, "grad_norm": 1.828125, "learning_rate": 2.9907857691323265e-05, "loss": 0.4619, "step": 4711 }, { "epoch": 1.20608, "grad_norm": 2.140625, "learning_rate": 2.9903591843699346e-05, "loss": 0.4481, "step": 4712 }, { "epoch": 1.206336, "grad_norm": 1.953125, "learning_rate": 2.9899325996075423e-05, "loss": 0.4566, "step": 4713 }, { "epoch": 1.206592, "grad_norm": 2.078125, "learning_rate": 2.9895060148451498e-05, "loss": 0.4613, "step": 4714 }, { "epoch": 1.206848, "grad_norm": 2.046875, "learning_rate": 2.9890794300827575e-05, "loss": 0.4808, "step": 4715 }, { "epoch": 1.207104, "grad_norm": 2.046875, "learning_rate": 2.9886528453203656e-05, "loss": 0.4753, "step": 4716 }, { "epoch": 1.20736, "grad_norm": 2.03125, "learning_rate": 2.988226260557973e-05, "loss": 0.4613, "step": 4717 }, { "epoch": 1.207616, "grad_norm": 2.203125, "learning_rate": 2.9877996757955805e-05, "loss": 0.4183, "step": 4718 }, { "epoch": 1.207872, "grad_norm": 2.046875, "learning_rate": 2.9873730910331882e-05, "loss": 0.4493, "step": 4719 }, { "epoch": 1.208128, "grad_norm": 2.046875, "learning_rate": 2.9869465062707963e-05, "loss": 0.4341, "step": 4720 }, { "epoch": 1.2083840000000001, "grad_norm": 2.203125, "learning_rate": 2.9865199215084038e-05, "loss": 0.4377, "step": 4721 }, { "epoch": 1.20864, "grad_norm": 2.234375, "learning_rate": 2.9860933367460115e-05, "loss": 0.5218, "step": 4722 }, { "epoch": 1.208896, "grad_norm": 2.125, "learning_rate": 2.9856667519836196e-05, "loss": 0.4269, "step": 4723 }, { "epoch": 1.209152, "grad_norm": 2.15625, "learning_rate": 2.985240167221227e-05, "loss": 0.4421, "step": 4724 }, { "epoch": 1.209408, "grad_norm": 2.140625, "learning_rate": 2.984813582458835e-05, "loss": 0.4814, "step": 4725 }, { "epoch": 1.209664, "grad_norm": 2.046875, "learning_rate": 2.9843869976964423e-05, "loss": 0.4216, "step": 4726 }, { "epoch": 1.2099199999999999, "grad_norm": 2.28125, "learning_rate": 2.9839604129340504e-05, "loss": 0.4397, "step": 4727 }, { "epoch": 1.210176, "grad_norm": 2.359375, "learning_rate": 2.9835338281716578e-05, "loss": 0.4471, "step": 4728 }, { "epoch": 1.210432, "grad_norm": 2.296875, "learning_rate": 2.9831072434092656e-05, "loss": 0.459, "step": 4729 }, { "epoch": 1.210688, "grad_norm": 2.25, "learning_rate": 2.982680658646873e-05, "loss": 0.4364, "step": 4730 }, { "epoch": 1.210944, "grad_norm": 2.125, "learning_rate": 2.982254073884481e-05, "loss": 0.472, "step": 4731 }, { "epoch": 1.2112, "grad_norm": 2.25, "learning_rate": 2.981827489122089e-05, "loss": 0.4309, "step": 4732 }, { "epoch": 1.211456, "grad_norm": 2.09375, "learning_rate": 2.9814009043596963e-05, "loss": 0.4547, "step": 4733 }, { "epoch": 1.211712, "grad_norm": 2.171875, "learning_rate": 2.980974319597304e-05, "loss": 0.4541, "step": 4734 }, { "epoch": 1.211968, "grad_norm": 2.078125, "learning_rate": 2.980547734834912e-05, "loss": 0.4612, "step": 4735 }, { "epoch": 1.212224, "grad_norm": 2.171875, "learning_rate": 2.9801211500725196e-05, "loss": 0.4292, "step": 4736 }, { "epoch": 1.21248, "grad_norm": 2.140625, "learning_rate": 2.979694565310127e-05, "loss": 0.4794, "step": 4737 }, { "epoch": 1.212736, "grad_norm": 2.1875, "learning_rate": 2.9792679805477348e-05, "loss": 0.4912, "step": 4738 }, { "epoch": 1.212992, "grad_norm": 2.109375, "learning_rate": 2.978841395785343e-05, "loss": 0.4537, "step": 4739 }, { "epoch": 1.213248, "grad_norm": 2.125, "learning_rate": 2.9784148110229503e-05, "loss": 0.4765, "step": 4740 }, { "epoch": 1.213504, "grad_norm": 2.09375, "learning_rate": 2.977988226260558e-05, "loss": 0.5052, "step": 4741 }, { "epoch": 1.21376, "grad_norm": 2.078125, "learning_rate": 2.977561641498166e-05, "loss": 0.4686, "step": 4742 }, { "epoch": 1.214016, "grad_norm": 2.03125, "learning_rate": 2.9771350567357736e-05, "loss": 0.4423, "step": 4743 }, { "epoch": 1.214272, "grad_norm": 2.03125, "learning_rate": 2.9767084719733814e-05, "loss": 0.4155, "step": 4744 }, { "epoch": 1.214528, "grad_norm": 2.25, "learning_rate": 2.9762818872109888e-05, "loss": 0.4607, "step": 4745 }, { "epoch": 1.214784, "grad_norm": 2.25, "learning_rate": 2.975855302448597e-05, "loss": 0.4877, "step": 4746 }, { "epoch": 1.2150400000000001, "grad_norm": 2.15625, "learning_rate": 2.9754287176862043e-05, "loss": 0.4836, "step": 4747 }, { "epoch": 1.215296, "grad_norm": 2.109375, "learning_rate": 2.975002132923812e-05, "loss": 0.449, "step": 4748 }, { "epoch": 1.215552, "grad_norm": 2.125, "learning_rate": 2.9745755481614195e-05, "loss": 0.4641, "step": 4749 }, { "epoch": 1.215808, "grad_norm": 2.234375, "learning_rate": 2.9741489633990276e-05, "loss": 0.4996, "step": 4750 }, { "epoch": 1.216064, "grad_norm": 1.96875, "learning_rate": 2.9737223786366354e-05, "loss": 0.4644, "step": 4751 }, { "epoch": 1.21632, "grad_norm": 2.09375, "learning_rate": 2.9732957938742428e-05, "loss": 0.4845, "step": 4752 }, { "epoch": 1.2165759999999999, "grad_norm": 2.140625, "learning_rate": 2.9728692091118506e-05, "loss": 0.4866, "step": 4753 }, { "epoch": 1.216832, "grad_norm": 2.03125, "learning_rate": 2.9724426243494587e-05, "loss": 0.4271, "step": 4754 }, { "epoch": 1.217088, "grad_norm": 2.171875, "learning_rate": 2.972016039587066e-05, "loss": 0.4583, "step": 4755 }, { "epoch": 1.217344, "grad_norm": 2.109375, "learning_rate": 2.9715894548246735e-05, "loss": 0.5022, "step": 4756 }, { "epoch": 1.2176, "grad_norm": 2.078125, "learning_rate": 2.9711628700622816e-05, "loss": 0.4357, "step": 4757 }, { "epoch": 1.217856, "grad_norm": 2.203125, "learning_rate": 2.9707362852998894e-05, "loss": 0.44, "step": 4758 }, { "epoch": 1.218112, "grad_norm": 2.375, "learning_rate": 2.9703097005374968e-05, "loss": 0.4694, "step": 4759 }, { "epoch": 1.218368, "grad_norm": 2.28125, "learning_rate": 2.9698831157751046e-05, "loss": 0.4589, "step": 4760 }, { "epoch": 1.218624, "grad_norm": 2.140625, "learning_rate": 2.9694565310127127e-05, "loss": 0.5157, "step": 4761 }, { "epoch": 1.21888, "grad_norm": 2.015625, "learning_rate": 2.96902994625032e-05, "loss": 0.4576, "step": 4762 }, { "epoch": 1.219136, "grad_norm": 1.9921875, "learning_rate": 2.968603361487928e-05, "loss": 0.4269, "step": 4763 }, { "epoch": 1.219392, "grad_norm": 2.09375, "learning_rate": 2.9681767767255353e-05, "loss": 0.4527, "step": 4764 }, { "epoch": 1.219648, "grad_norm": 2.03125, "learning_rate": 2.9677501919631434e-05, "loss": 0.4686, "step": 4765 }, { "epoch": 1.219904, "grad_norm": 2.15625, "learning_rate": 2.967323607200751e-05, "loss": 0.4544, "step": 4766 }, { "epoch": 1.22016, "grad_norm": 2.03125, "learning_rate": 2.9668970224383586e-05, "loss": 0.4468, "step": 4767 }, { "epoch": 1.220416, "grad_norm": 2.28125, "learning_rate": 2.966470437675966e-05, "loss": 0.4407, "step": 4768 }, { "epoch": 1.220672, "grad_norm": 2.015625, "learning_rate": 2.966043852913574e-05, "loss": 0.4622, "step": 4769 }, { "epoch": 1.220928, "grad_norm": 2.375, "learning_rate": 2.965617268151182e-05, "loss": 0.4663, "step": 4770 }, { "epoch": 1.221184, "grad_norm": 2.234375, "learning_rate": 2.9651906833887893e-05, "loss": 0.4784, "step": 4771 }, { "epoch": 1.22144, "grad_norm": 2.15625, "learning_rate": 2.9647640986263974e-05, "loss": 0.4365, "step": 4772 }, { "epoch": 1.2216960000000001, "grad_norm": 2.359375, "learning_rate": 2.9643375138640052e-05, "loss": 0.4734, "step": 4773 }, { "epoch": 1.221952, "grad_norm": 2.171875, "learning_rate": 2.9639109291016126e-05, "loss": 0.4382, "step": 4774 }, { "epoch": 1.222208, "grad_norm": 2.015625, "learning_rate": 2.96348434433922e-05, "loss": 0.4366, "step": 4775 }, { "epoch": 1.222464, "grad_norm": 2.140625, "learning_rate": 2.963057759576828e-05, "loss": 0.4856, "step": 4776 }, { "epoch": 1.22272, "grad_norm": 2.28125, "learning_rate": 2.962631174814436e-05, "loss": 0.4613, "step": 4777 }, { "epoch": 1.222976, "grad_norm": 2.359375, "learning_rate": 2.9622045900520434e-05, "loss": 0.4536, "step": 4778 }, { "epoch": 1.223232, "grad_norm": 2.109375, "learning_rate": 2.961778005289651e-05, "loss": 0.4447, "step": 4779 }, { "epoch": 1.223488, "grad_norm": 2.09375, "learning_rate": 2.9613514205272592e-05, "loss": 0.4245, "step": 4780 }, { "epoch": 1.223744, "grad_norm": 2.1875, "learning_rate": 2.9609248357648666e-05, "loss": 0.483, "step": 4781 }, { "epoch": 1.224, "grad_norm": 2.390625, "learning_rate": 2.9604982510024744e-05, "loss": 0.4334, "step": 4782 }, { "epoch": 1.224256, "grad_norm": 2.203125, "learning_rate": 2.960071666240082e-05, "loss": 0.4401, "step": 4783 }, { "epoch": 1.224512, "grad_norm": 2.25, "learning_rate": 2.95964508147769e-05, "loss": 0.4561, "step": 4784 }, { "epoch": 1.224768, "grad_norm": 2.1875, "learning_rate": 2.9592184967152974e-05, "loss": 0.4179, "step": 4785 }, { "epoch": 1.225024, "grad_norm": 2.03125, "learning_rate": 2.958791911952905e-05, "loss": 0.4821, "step": 4786 }, { "epoch": 1.22528, "grad_norm": 2.1875, "learning_rate": 2.9583653271905126e-05, "loss": 0.4464, "step": 4787 }, { "epoch": 1.225536, "grad_norm": 2.0625, "learning_rate": 2.9579387424281207e-05, "loss": 0.4542, "step": 4788 }, { "epoch": 1.225792, "grad_norm": 2.390625, "learning_rate": 2.9575121576657284e-05, "loss": 0.4371, "step": 4789 }, { "epoch": 1.226048, "grad_norm": 2.234375, "learning_rate": 2.957085572903336e-05, "loss": 0.4835, "step": 4790 }, { "epoch": 1.226304, "grad_norm": 2.09375, "learning_rate": 2.956658988140944e-05, "loss": 0.4506, "step": 4791 }, { "epoch": 1.22656, "grad_norm": 2.015625, "learning_rate": 2.9562324033785517e-05, "loss": 0.492, "step": 4792 }, { "epoch": 1.226816, "grad_norm": 2.0, "learning_rate": 2.955805818616159e-05, "loss": 0.4553, "step": 4793 }, { "epoch": 1.227072, "grad_norm": 2.171875, "learning_rate": 2.9553792338537666e-05, "loss": 0.4591, "step": 4794 }, { "epoch": 1.227328, "grad_norm": 2.046875, "learning_rate": 2.9549526490913747e-05, "loss": 0.4531, "step": 4795 }, { "epoch": 1.227584, "grad_norm": 2.125, "learning_rate": 2.9545260643289825e-05, "loss": 0.4488, "step": 4796 }, { "epoch": 1.22784, "grad_norm": 2.03125, "learning_rate": 2.95409947956659e-05, "loss": 0.4322, "step": 4797 }, { "epoch": 1.228096, "grad_norm": 2.25, "learning_rate": 2.9536728948041976e-05, "loss": 0.46, "step": 4798 }, { "epoch": 1.228352, "grad_norm": 1.875, "learning_rate": 2.9532463100418057e-05, "loss": 0.4684, "step": 4799 }, { "epoch": 1.228608, "grad_norm": 2.125, "learning_rate": 2.9528197252794132e-05, "loss": 0.4682, "step": 4800 }, { "epoch": 1.228864, "grad_norm": 2.09375, "learning_rate": 2.9523931405170206e-05, "loss": 0.4107, "step": 4801 }, { "epoch": 1.22912, "grad_norm": 2.15625, "learning_rate": 2.9519665557546284e-05, "loss": 0.4478, "step": 4802 }, { "epoch": 1.229376, "grad_norm": 2.09375, "learning_rate": 2.9515399709922365e-05, "loss": 0.4691, "step": 4803 }, { "epoch": 1.229632, "grad_norm": 2.0625, "learning_rate": 2.951113386229844e-05, "loss": 0.432, "step": 4804 }, { "epoch": 1.229888, "grad_norm": 2.375, "learning_rate": 2.9506868014674517e-05, "loss": 0.4668, "step": 4805 }, { "epoch": 1.230144, "grad_norm": 2.03125, "learning_rate": 2.9502602167050598e-05, "loss": 0.456, "step": 4806 }, { "epoch": 1.2304, "grad_norm": 2.15625, "learning_rate": 2.9498336319426672e-05, "loss": 0.4524, "step": 4807 }, { "epoch": 1.230656, "grad_norm": 2.25, "learning_rate": 2.949407047180275e-05, "loss": 0.4786, "step": 4808 }, { "epoch": 1.230912, "grad_norm": 2.140625, "learning_rate": 2.9489804624178824e-05, "loss": 0.4654, "step": 4809 }, { "epoch": 1.231168, "grad_norm": 2.21875, "learning_rate": 2.9485538776554905e-05, "loss": 0.4558, "step": 4810 }, { "epoch": 1.231424, "grad_norm": 2.078125, "learning_rate": 2.948127292893098e-05, "loss": 0.4303, "step": 4811 }, { "epoch": 1.2316799999999999, "grad_norm": 2.015625, "learning_rate": 2.9477007081307057e-05, "loss": 0.487, "step": 4812 }, { "epoch": 1.231936, "grad_norm": 2.3125, "learning_rate": 2.947274123368313e-05, "loss": 0.4581, "step": 4813 }, { "epoch": 1.232192, "grad_norm": 2.140625, "learning_rate": 2.9468475386059212e-05, "loss": 0.4603, "step": 4814 }, { "epoch": 1.232448, "grad_norm": 2.1875, "learning_rate": 2.946420953843529e-05, "loss": 0.4919, "step": 4815 }, { "epoch": 1.232704, "grad_norm": 2.15625, "learning_rate": 2.9459943690811364e-05, "loss": 0.4479, "step": 4816 }, { "epoch": 1.23296, "grad_norm": 2.28125, "learning_rate": 2.9455677843187442e-05, "loss": 0.4529, "step": 4817 }, { "epoch": 1.233216, "grad_norm": 2.0, "learning_rate": 2.9451411995563523e-05, "loss": 0.5019, "step": 4818 }, { "epoch": 1.233472, "grad_norm": 2.234375, "learning_rate": 2.9447146147939597e-05, "loss": 0.4711, "step": 4819 }, { "epoch": 1.233728, "grad_norm": 2.265625, "learning_rate": 2.944288030031567e-05, "loss": 0.4423, "step": 4820 }, { "epoch": 1.233984, "grad_norm": 2.203125, "learning_rate": 2.9438614452691752e-05, "loss": 0.5155, "step": 4821 }, { "epoch": 1.23424, "grad_norm": 2.0625, "learning_rate": 2.943434860506783e-05, "loss": 0.4493, "step": 4822 }, { "epoch": 1.234496, "grad_norm": 2.078125, "learning_rate": 2.9430082757443904e-05, "loss": 0.4703, "step": 4823 }, { "epoch": 1.234752, "grad_norm": 2.1875, "learning_rate": 2.9425816909819982e-05, "loss": 0.4432, "step": 4824 }, { "epoch": 1.235008, "grad_norm": 2.125, "learning_rate": 2.9421551062196063e-05, "loss": 0.4603, "step": 4825 }, { "epoch": 1.235264, "grad_norm": 2.15625, "learning_rate": 2.9417285214572137e-05, "loss": 0.464, "step": 4826 }, { "epoch": 1.23552, "grad_norm": 2.140625, "learning_rate": 2.9413019366948215e-05, "loss": 0.4624, "step": 4827 }, { "epoch": 1.235776, "grad_norm": 2.140625, "learning_rate": 2.940875351932429e-05, "loss": 0.4464, "step": 4828 }, { "epoch": 1.236032, "grad_norm": 2.109375, "learning_rate": 2.940448767170037e-05, "loss": 0.4304, "step": 4829 }, { "epoch": 1.236288, "grad_norm": 2.0625, "learning_rate": 2.9400221824076444e-05, "loss": 0.4647, "step": 4830 }, { "epoch": 1.236544, "grad_norm": 2.09375, "learning_rate": 2.9395955976452522e-05, "loss": 0.4497, "step": 4831 }, { "epoch": 1.2368000000000001, "grad_norm": 2.109375, "learning_rate": 2.9391690128828596e-05, "loss": 0.4336, "step": 4832 }, { "epoch": 1.237056, "grad_norm": 1.9921875, "learning_rate": 2.9387424281204677e-05, "loss": 0.4935, "step": 4833 }, { "epoch": 1.237312, "grad_norm": 2.234375, "learning_rate": 2.9383158433580755e-05, "loss": 0.4624, "step": 4834 }, { "epoch": 1.237568, "grad_norm": 2.171875, "learning_rate": 2.937889258595683e-05, "loss": 0.4787, "step": 4835 }, { "epoch": 1.237824, "grad_norm": 2.109375, "learning_rate": 2.9374626738332907e-05, "loss": 0.4311, "step": 4836 }, { "epoch": 1.23808, "grad_norm": 2.25, "learning_rate": 2.9370360890708988e-05, "loss": 0.4855, "step": 4837 }, { "epoch": 1.2383359999999999, "grad_norm": 2.203125, "learning_rate": 2.9366095043085062e-05, "loss": 0.436, "step": 4838 }, { "epoch": 1.238592, "grad_norm": 2.125, "learning_rate": 2.9361829195461137e-05, "loss": 0.4563, "step": 4839 }, { "epoch": 1.238848, "grad_norm": 2.25, "learning_rate": 2.9357563347837218e-05, "loss": 0.4903, "step": 4840 }, { "epoch": 1.239104, "grad_norm": 2.21875, "learning_rate": 2.9353297500213295e-05, "loss": 0.4745, "step": 4841 }, { "epoch": 1.23936, "grad_norm": 2.109375, "learning_rate": 2.934903165258937e-05, "loss": 0.482, "step": 4842 }, { "epoch": 1.239616, "grad_norm": 2.28125, "learning_rate": 2.9344765804965447e-05, "loss": 0.4392, "step": 4843 }, { "epoch": 1.239872, "grad_norm": 2.09375, "learning_rate": 2.9340499957341528e-05, "loss": 0.4886, "step": 4844 }, { "epoch": 1.240128, "grad_norm": 2.28125, "learning_rate": 2.9336234109717602e-05, "loss": 0.4782, "step": 4845 }, { "epoch": 1.240384, "grad_norm": 2.03125, "learning_rate": 2.933196826209368e-05, "loss": 0.4379, "step": 4846 }, { "epoch": 1.24064, "grad_norm": 2.09375, "learning_rate": 2.9327702414469754e-05, "loss": 0.4593, "step": 4847 }, { "epoch": 1.240896, "grad_norm": 2.421875, "learning_rate": 2.9323436566845835e-05, "loss": 0.4733, "step": 4848 }, { "epoch": 1.241152, "grad_norm": 2.0, "learning_rate": 2.931917071922191e-05, "loss": 0.4479, "step": 4849 }, { "epoch": 1.241408, "grad_norm": 2.140625, "learning_rate": 2.9314904871597987e-05, "loss": 0.5144, "step": 4850 }, { "epoch": 1.241664, "grad_norm": 2.046875, "learning_rate": 2.931063902397406e-05, "loss": 0.4681, "step": 4851 }, { "epoch": 1.24192, "grad_norm": 2.1875, "learning_rate": 2.9306373176350143e-05, "loss": 0.4681, "step": 4852 }, { "epoch": 1.242176, "grad_norm": 1.9765625, "learning_rate": 2.930210732872622e-05, "loss": 0.4387, "step": 4853 }, { "epoch": 1.242432, "grad_norm": 2.234375, "learning_rate": 2.9297841481102295e-05, "loss": 0.4442, "step": 4854 }, { "epoch": 1.242688, "grad_norm": 2.203125, "learning_rate": 2.9293575633478376e-05, "loss": 0.4461, "step": 4855 }, { "epoch": 1.242944, "grad_norm": 2.109375, "learning_rate": 2.9289309785854453e-05, "loss": 0.4767, "step": 4856 }, { "epoch": 1.2432, "grad_norm": 2.046875, "learning_rate": 2.9285043938230528e-05, "loss": 0.4674, "step": 4857 }, { "epoch": 1.2434560000000001, "grad_norm": 1.9765625, "learning_rate": 2.9280778090606602e-05, "loss": 0.4803, "step": 4858 }, { "epoch": 1.243712, "grad_norm": 2.046875, "learning_rate": 2.9276512242982683e-05, "loss": 0.4677, "step": 4859 }, { "epoch": 1.243968, "grad_norm": 2.265625, "learning_rate": 2.927224639535876e-05, "loss": 0.4906, "step": 4860 }, { "epoch": 1.244224, "grad_norm": 2.328125, "learning_rate": 2.9267980547734835e-05, "loss": 0.4491, "step": 4861 }, { "epoch": 1.24448, "grad_norm": 2.421875, "learning_rate": 2.9263714700110912e-05, "loss": 0.4675, "step": 4862 }, { "epoch": 1.244736, "grad_norm": 2.359375, "learning_rate": 2.9259448852486993e-05, "loss": 0.374, "step": 4863 }, { "epoch": 1.2449919999999999, "grad_norm": 2.03125, "learning_rate": 2.9255183004863068e-05, "loss": 0.4874, "step": 4864 }, { "epoch": 1.245248, "grad_norm": 2.171875, "learning_rate": 2.9250917157239145e-05, "loss": 0.4231, "step": 4865 }, { "epoch": 1.245504, "grad_norm": 2.359375, "learning_rate": 2.924665130961522e-05, "loss": 0.4353, "step": 4866 }, { "epoch": 1.24576, "grad_norm": 2.375, "learning_rate": 2.92423854619913e-05, "loss": 0.4292, "step": 4867 }, { "epoch": 1.246016, "grad_norm": 2.234375, "learning_rate": 2.9238119614367375e-05, "loss": 0.4695, "step": 4868 }, { "epoch": 1.246272, "grad_norm": 2.046875, "learning_rate": 2.9233853766743453e-05, "loss": 0.4673, "step": 4869 }, { "epoch": 1.246528, "grad_norm": 2.109375, "learning_rate": 2.9229587919119534e-05, "loss": 0.4458, "step": 4870 }, { "epoch": 1.246784, "grad_norm": 2.140625, "learning_rate": 2.9225322071495608e-05, "loss": 0.4351, "step": 4871 }, { "epoch": 1.24704, "grad_norm": 2.15625, "learning_rate": 2.9221056223871686e-05, "loss": 0.488, "step": 4872 }, { "epoch": 1.247296, "grad_norm": 2.21875, "learning_rate": 2.921679037624776e-05, "loss": 0.466, "step": 4873 }, { "epoch": 1.247552, "grad_norm": 2.25, "learning_rate": 2.921252452862384e-05, "loss": 0.4591, "step": 4874 }, { "epoch": 1.247808, "grad_norm": 2.15625, "learning_rate": 2.920825868099992e-05, "loss": 0.4663, "step": 4875 }, { "epoch": 1.248064, "grad_norm": 2.0625, "learning_rate": 2.9203992833375993e-05, "loss": 0.4446, "step": 4876 }, { "epoch": 1.24832, "grad_norm": 2.078125, "learning_rate": 2.9199726985752067e-05, "loss": 0.4467, "step": 4877 }, { "epoch": 1.248576, "grad_norm": 2.328125, "learning_rate": 2.9195461138128148e-05, "loss": 0.4314, "step": 4878 }, { "epoch": 1.248832, "grad_norm": 2.28125, "learning_rate": 2.9191195290504226e-05, "loss": 0.469, "step": 4879 }, { "epoch": 1.249088, "grad_norm": 2.296875, "learning_rate": 2.91869294428803e-05, "loss": 0.4564, "step": 4880 }, { "epoch": 1.249344, "grad_norm": 2.09375, "learning_rate": 2.9182663595256378e-05, "loss": 0.4283, "step": 4881 }, { "epoch": 1.2496, "grad_norm": 2.0625, "learning_rate": 2.917839774763246e-05, "loss": 0.4682, "step": 4882 }, { "epoch": 1.249856, "grad_norm": 2.171875, "learning_rate": 2.9174131900008533e-05, "loss": 0.4861, "step": 4883 }, { "epoch": 1.2501120000000001, "grad_norm": 2.09375, "learning_rate": 2.916986605238461e-05, "loss": 0.4028, "step": 4884 }, { "epoch": 1.250368, "grad_norm": 2.171875, "learning_rate": 2.9165600204760685e-05, "loss": 0.4377, "step": 4885 }, { "epoch": 1.250624, "grad_norm": 2.0, "learning_rate": 2.9161334357136766e-05, "loss": 0.4436, "step": 4886 }, { "epoch": 1.25088, "grad_norm": 2.234375, "learning_rate": 2.915706850951284e-05, "loss": 0.4368, "step": 4887 }, { "epoch": 1.251136, "grad_norm": 1.8984375, "learning_rate": 2.9152802661888918e-05, "loss": 0.4987, "step": 4888 }, { "epoch": 1.251392, "grad_norm": 2.234375, "learning_rate": 2.9148536814265e-05, "loss": 0.4345, "step": 4889 }, { "epoch": 1.2516479999999999, "grad_norm": 2.140625, "learning_rate": 2.9144270966641073e-05, "loss": 0.4797, "step": 4890 }, { "epoch": 1.2519040000000001, "grad_norm": 2.1875, "learning_rate": 2.914000511901715e-05, "loss": 0.4341, "step": 4891 }, { "epoch": 1.25216, "grad_norm": 2.125, "learning_rate": 2.9135739271393225e-05, "loss": 0.4497, "step": 4892 }, { "epoch": 1.252416, "grad_norm": 2.34375, "learning_rate": 2.9131473423769306e-05, "loss": 0.4376, "step": 4893 }, { "epoch": 1.252672, "grad_norm": 2.234375, "learning_rate": 2.9127207576145384e-05, "loss": 0.4703, "step": 4894 }, { "epoch": 1.252928, "grad_norm": 1.9765625, "learning_rate": 2.9122941728521458e-05, "loss": 0.4764, "step": 4895 }, { "epoch": 1.253184, "grad_norm": 2.234375, "learning_rate": 2.9118675880897532e-05, "loss": 0.4362, "step": 4896 }, { "epoch": 1.2534399999999999, "grad_norm": 2.1875, "learning_rate": 2.9114410033273613e-05, "loss": 0.4717, "step": 4897 }, { "epoch": 1.253696, "grad_norm": 2.234375, "learning_rate": 2.911014418564969e-05, "loss": 0.4642, "step": 4898 }, { "epoch": 1.253952, "grad_norm": 2.140625, "learning_rate": 2.9105878338025765e-05, "loss": 0.4604, "step": 4899 }, { "epoch": 1.254208, "grad_norm": 2.25, "learning_rate": 2.9101612490401843e-05, "loss": 0.468, "step": 4900 }, { "epoch": 1.254464, "grad_norm": 2.140625, "learning_rate": 2.9097346642777924e-05, "loss": 0.4383, "step": 4901 }, { "epoch": 1.25472, "grad_norm": 1.984375, "learning_rate": 2.9093080795153998e-05, "loss": 0.4621, "step": 4902 }, { "epoch": 1.254976, "grad_norm": 2.078125, "learning_rate": 2.9088814947530073e-05, "loss": 0.4219, "step": 4903 }, { "epoch": 1.255232, "grad_norm": 2.140625, "learning_rate": 2.9084549099906157e-05, "loss": 0.4848, "step": 4904 }, { "epoch": 1.255488, "grad_norm": 2.125, "learning_rate": 2.908028325228223e-05, "loss": 0.4564, "step": 4905 }, { "epoch": 1.255744, "grad_norm": 2.3125, "learning_rate": 2.9076017404658306e-05, "loss": 0.4199, "step": 4906 }, { "epoch": 1.256, "grad_norm": 2.203125, "learning_rate": 2.9071751557034383e-05, "loss": 0.4314, "step": 4907 }, { "epoch": 1.256256, "grad_norm": 2.21875, "learning_rate": 2.9067485709410464e-05, "loss": 0.4826, "step": 4908 }, { "epoch": 1.256512, "grad_norm": 2.3125, "learning_rate": 2.906321986178654e-05, "loss": 0.4288, "step": 4909 }, { "epoch": 1.256768, "grad_norm": 2.109375, "learning_rate": 2.9058954014162616e-05, "loss": 0.4464, "step": 4910 }, { "epoch": 1.257024, "grad_norm": 2.1875, "learning_rate": 2.905468816653869e-05, "loss": 0.4412, "step": 4911 }, { "epoch": 1.25728, "grad_norm": 2.046875, "learning_rate": 2.905042231891477e-05, "loss": 0.4255, "step": 4912 }, { "epoch": 1.257536, "grad_norm": 2.015625, "learning_rate": 2.9046156471290846e-05, "loss": 0.4873, "step": 4913 }, { "epoch": 1.257792, "grad_norm": 2.046875, "learning_rate": 2.9041890623666923e-05, "loss": 0.4731, "step": 4914 }, { "epoch": 1.258048, "grad_norm": 2.25, "learning_rate": 2.9037624776042998e-05, "loss": 0.4431, "step": 4915 }, { "epoch": 1.2583039999999999, "grad_norm": 2.25, "learning_rate": 2.903335892841908e-05, "loss": 0.4565, "step": 4916 }, { "epoch": 1.2585600000000001, "grad_norm": 2.140625, "learning_rate": 2.9029093080795156e-05, "loss": 0.4549, "step": 4917 }, { "epoch": 1.258816, "grad_norm": 2.0625, "learning_rate": 2.902482723317123e-05, "loss": 0.4506, "step": 4918 }, { "epoch": 1.259072, "grad_norm": 2.171875, "learning_rate": 2.902056138554731e-05, "loss": 0.4781, "step": 4919 }, { "epoch": 1.259328, "grad_norm": 2.125, "learning_rate": 2.901629553792339e-05, "loss": 0.4571, "step": 4920 }, { "epoch": 1.259584, "grad_norm": 2.21875, "learning_rate": 2.9012029690299464e-05, "loss": 0.4315, "step": 4921 }, { "epoch": 1.25984, "grad_norm": 2.078125, "learning_rate": 2.9007763842675538e-05, "loss": 0.4584, "step": 4922 }, { "epoch": 1.2600959999999999, "grad_norm": 2.09375, "learning_rate": 2.9003497995051622e-05, "loss": 0.4645, "step": 4923 }, { "epoch": 1.260352, "grad_norm": 2.375, "learning_rate": 2.8999232147427697e-05, "loss": 0.4505, "step": 4924 }, { "epoch": 1.260608, "grad_norm": 2.328125, "learning_rate": 2.899496629980377e-05, "loss": 0.4662, "step": 4925 }, { "epoch": 1.260864, "grad_norm": 2.1875, "learning_rate": 2.899070045217985e-05, "loss": 0.4528, "step": 4926 }, { "epoch": 1.26112, "grad_norm": 2.03125, "learning_rate": 2.898643460455593e-05, "loss": 0.4743, "step": 4927 }, { "epoch": 1.261376, "grad_norm": 2.265625, "learning_rate": 2.8982168756932004e-05, "loss": 0.4628, "step": 4928 }, { "epoch": 1.261632, "grad_norm": 2.421875, "learning_rate": 2.897790290930808e-05, "loss": 0.4664, "step": 4929 }, { "epoch": 1.261888, "grad_norm": 2.359375, "learning_rate": 2.8973637061684156e-05, "loss": 0.4712, "step": 4930 }, { "epoch": 1.262144, "grad_norm": 2.09375, "learning_rate": 2.8969371214060237e-05, "loss": 0.4546, "step": 4931 }, { "epoch": 1.2624, "grad_norm": 2.234375, "learning_rate": 2.896510536643631e-05, "loss": 0.4716, "step": 4932 }, { "epoch": 1.262656, "grad_norm": 2.03125, "learning_rate": 2.896083951881239e-05, "loss": 0.5083, "step": 4933 }, { "epoch": 1.262912, "grad_norm": 2.265625, "learning_rate": 2.8956573671188463e-05, "loss": 0.4599, "step": 4934 }, { "epoch": 1.263168, "grad_norm": 2.421875, "learning_rate": 2.8952307823564544e-05, "loss": 0.4378, "step": 4935 }, { "epoch": 1.263424, "grad_norm": 1.921875, "learning_rate": 2.894804197594062e-05, "loss": 0.4356, "step": 4936 }, { "epoch": 1.26368, "grad_norm": 1.9375, "learning_rate": 2.8943776128316696e-05, "loss": 0.4503, "step": 4937 }, { "epoch": 1.263936, "grad_norm": 2.1875, "learning_rate": 2.8939510280692777e-05, "loss": 0.408, "step": 4938 }, { "epoch": 1.264192, "grad_norm": 1.9921875, "learning_rate": 2.8935244433068855e-05, "loss": 0.4424, "step": 4939 }, { "epoch": 1.264448, "grad_norm": 2.015625, "learning_rate": 2.893097858544493e-05, "loss": 0.4708, "step": 4940 }, { "epoch": 1.264704, "grad_norm": 2.171875, "learning_rate": 2.8926712737821003e-05, "loss": 0.4512, "step": 4941 }, { "epoch": 1.2649599999999999, "grad_norm": 2.328125, "learning_rate": 2.8922446890197084e-05, "loss": 0.4449, "step": 4942 }, { "epoch": 1.2652160000000001, "grad_norm": 2.3125, "learning_rate": 2.8918181042573162e-05, "loss": 0.4617, "step": 4943 }, { "epoch": 1.265472, "grad_norm": 2.046875, "learning_rate": 2.8913915194949236e-05, "loss": 0.4754, "step": 4944 }, { "epoch": 1.265728, "grad_norm": 2.171875, "learning_rate": 2.8909649347325314e-05, "loss": 0.4765, "step": 4945 }, { "epoch": 1.265984, "grad_norm": 2.046875, "learning_rate": 2.8905383499701395e-05, "loss": 0.4746, "step": 4946 }, { "epoch": 1.26624, "grad_norm": 2.28125, "learning_rate": 2.890111765207747e-05, "loss": 0.4477, "step": 4947 }, { "epoch": 1.266496, "grad_norm": 2.203125, "learning_rate": 2.8896851804453547e-05, "loss": 0.457, "step": 4948 }, { "epoch": 1.2667519999999999, "grad_norm": 2.203125, "learning_rate": 2.889258595682962e-05, "loss": 0.4515, "step": 4949 }, { "epoch": 1.2670080000000001, "grad_norm": 2.234375, "learning_rate": 2.8888320109205702e-05, "loss": 0.4255, "step": 4950 }, { "epoch": 1.267264, "grad_norm": 2.046875, "learning_rate": 2.8884054261581776e-05, "loss": 0.4548, "step": 4951 }, { "epoch": 1.26752, "grad_norm": 1.8828125, "learning_rate": 2.8879788413957854e-05, "loss": 0.4512, "step": 4952 }, { "epoch": 1.267776, "grad_norm": 2.078125, "learning_rate": 2.8875522566333935e-05, "loss": 0.4796, "step": 4953 }, { "epoch": 1.268032, "grad_norm": 2.09375, "learning_rate": 2.887125671871001e-05, "loss": 0.4392, "step": 4954 }, { "epoch": 1.268288, "grad_norm": 2.171875, "learning_rate": 2.8866990871086087e-05, "loss": 0.4584, "step": 4955 }, { "epoch": 1.268544, "grad_norm": 2.140625, "learning_rate": 2.886272502346216e-05, "loss": 0.4619, "step": 4956 }, { "epoch": 1.2688, "grad_norm": 2.015625, "learning_rate": 2.8858459175838242e-05, "loss": 0.5105, "step": 4957 }, { "epoch": 1.269056, "grad_norm": 2.140625, "learning_rate": 2.885419332821432e-05, "loss": 0.4593, "step": 4958 }, { "epoch": 1.269312, "grad_norm": 2.125, "learning_rate": 2.8849927480590394e-05, "loss": 0.4586, "step": 4959 }, { "epoch": 1.269568, "grad_norm": 1.9765625, "learning_rate": 2.884566163296647e-05, "loss": 0.4392, "step": 4960 }, { "epoch": 1.269824, "grad_norm": 2.140625, "learning_rate": 2.884139578534255e-05, "loss": 0.3788, "step": 4961 }, { "epoch": 1.27008, "grad_norm": 2.0625, "learning_rate": 2.8837129937718627e-05, "loss": 0.4306, "step": 4962 }, { "epoch": 1.270336, "grad_norm": 2.140625, "learning_rate": 2.88328640900947e-05, "loss": 0.4625, "step": 4963 }, { "epoch": 1.270592, "grad_norm": 1.8515625, "learning_rate": 2.882859824247078e-05, "loss": 0.4535, "step": 4964 }, { "epoch": 1.270848, "grad_norm": 2.15625, "learning_rate": 2.882433239484686e-05, "loss": 0.4549, "step": 4965 }, { "epoch": 1.271104, "grad_norm": 2.125, "learning_rate": 2.8820066547222934e-05, "loss": 0.4542, "step": 4966 }, { "epoch": 1.27136, "grad_norm": 2.109375, "learning_rate": 2.8815800699599012e-05, "loss": 0.4742, "step": 4967 }, { "epoch": 1.271616, "grad_norm": 2.234375, "learning_rate": 2.8811534851975086e-05, "loss": 0.4813, "step": 4968 }, { "epoch": 1.2718720000000001, "grad_norm": 2.109375, "learning_rate": 2.8807269004351167e-05, "loss": 0.4503, "step": 4969 }, { "epoch": 1.272128, "grad_norm": 2.125, "learning_rate": 2.880300315672724e-05, "loss": 0.4789, "step": 4970 }, { "epoch": 1.272384, "grad_norm": 2.046875, "learning_rate": 2.879873730910332e-05, "loss": 0.4339, "step": 4971 }, { "epoch": 1.27264, "grad_norm": 2.171875, "learning_rate": 2.87944714614794e-05, "loss": 0.4288, "step": 4972 }, { "epoch": 1.272896, "grad_norm": 2.234375, "learning_rate": 2.8790205613855474e-05, "loss": 0.4364, "step": 4973 }, { "epoch": 1.273152, "grad_norm": 2.109375, "learning_rate": 2.8785939766231552e-05, "loss": 0.4372, "step": 4974 }, { "epoch": 1.2734079999999999, "grad_norm": 2.203125, "learning_rate": 2.8781673918607626e-05, "loss": 0.4795, "step": 4975 }, { "epoch": 1.2736640000000001, "grad_norm": 2.09375, "learning_rate": 2.8777408070983707e-05, "loss": 0.4431, "step": 4976 }, { "epoch": 1.27392, "grad_norm": 2.078125, "learning_rate": 2.8773142223359785e-05, "loss": 0.4779, "step": 4977 }, { "epoch": 1.274176, "grad_norm": 2.34375, "learning_rate": 2.876887637573586e-05, "loss": 0.4342, "step": 4978 }, { "epoch": 1.274432, "grad_norm": 2.21875, "learning_rate": 2.8764610528111934e-05, "loss": 0.4563, "step": 4979 }, { "epoch": 1.274688, "grad_norm": 2.09375, "learning_rate": 2.8760344680488015e-05, "loss": 0.4607, "step": 4980 }, { "epoch": 1.274944, "grad_norm": 2.0625, "learning_rate": 2.8756078832864092e-05, "loss": 0.4879, "step": 4981 }, { "epoch": 1.2752, "grad_norm": 2.3125, "learning_rate": 2.8751812985240167e-05, "loss": 0.4662, "step": 4982 }, { "epoch": 1.275456, "grad_norm": 2.109375, "learning_rate": 2.8747547137616244e-05, "loss": 0.4606, "step": 4983 }, { "epoch": 1.275712, "grad_norm": 2.015625, "learning_rate": 2.8743281289992325e-05, "loss": 0.4594, "step": 4984 }, { "epoch": 1.275968, "grad_norm": 2.171875, "learning_rate": 2.87390154423684e-05, "loss": 0.4264, "step": 4985 }, { "epoch": 1.276224, "grad_norm": 2.1875, "learning_rate": 2.8734749594744477e-05, "loss": 0.4332, "step": 4986 }, { "epoch": 1.27648, "grad_norm": 2.234375, "learning_rate": 2.8730483747120558e-05, "loss": 0.4797, "step": 4987 }, { "epoch": 1.276736, "grad_norm": 2.3125, "learning_rate": 2.8726217899496633e-05, "loss": 0.4523, "step": 4988 }, { "epoch": 1.276992, "grad_norm": 2.09375, "learning_rate": 2.8721952051872707e-05, "loss": 0.45, "step": 4989 }, { "epoch": 1.277248, "grad_norm": 1.8671875, "learning_rate": 2.8717686204248784e-05, "loss": 0.4661, "step": 4990 }, { "epoch": 1.277504, "grad_norm": 2.140625, "learning_rate": 2.8713420356624865e-05, "loss": 0.4456, "step": 4991 }, { "epoch": 1.27776, "grad_norm": 2.328125, "learning_rate": 2.870915450900094e-05, "loss": 0.482, "step": 4992 }, { "epoch": 1.278016, "grad_norm": 2.15625, "learning_rate": 2.8704888661377017e-05, "loss": 0.4273, "step": 4993 }, { "epoch": 1.278272, "grad_norm": 2.25, "learning_rate": 2.870062281375309e-05, "loss": 0.4383, "step": 4994 }, { "epoch": 1.278528, "grad_norm": 2.265625, "learning_rate": 2.8696356966129173e-05, "loss": 0.4647, "step": 4995 }, { "epoch": 1.278784, "grad_norm": 2.109375, "learning_rate": 2.869209111850525e-05, "loss": 0.4304, "step": 4996 }, { "epoch": 1.27904, "grad_norm": 1.984375, "learning_rate": 2.8687825270881325e-05, "loss": 0.4818, "step": 4997 }, { "epoch": 1.279296, "grad_norm": 2.25, "learning_rate": 2.86835594232574e-05, "loss": 0.4102, "step": 4998 }, { "epoch": 1.279552, "grad_norm": 2.234375, "learning_rate": 2.867929357563348e-05, "loss": 0.4788, "step": 4999 }, { "epoch": 1.279808, "grad_norm": 2.171875, "learning_rate": 2.8675027728009558e-05, "loss": 0.4808, "step": 5000 }, { "epoch": 1.2800639999999999, "grad_norm": 2.09375, "learning_rate": 2.8670761880385632e-05, "loss": 0.4683, "step": 5001 }, { "epoch": 1.2803200000000001, "grad_norm": 2.015625, "learning_rate": 2.8666496032761713e-05, "loss": 0.4329, "step": 5002 }, { "epoch": 1.280576, "grad_norm": 2.203125, "learning_rate": 2.866223018513779e-05, "loss": 0.447, "step": 5003 }, { "epoch": 1.280832, "grad_norm": 2.28125, "learning_rate": 2.8657964337513865e-05, "loss": 0.4478, "step": 5004 }, { "epoch": 1.281088, "grad_norm": 2.28125, "learning_rate": 2.865369848988994e-05, "loss": 0.4754, "step": 5005 }, { "epoch": 1.281344, "grad_norm": 2.140625, "learning_rate": 2.8649432642266024e-05, "loss": 0.444, "step": 5006 }, { "epoch": 1.2816, "grad_norm": 2.15625, "learning_rate": 2.8645166794642098e-05, "loss": 0.4364, "step": 5007 }, { "epoch": 1.2818559999999999, "grad_norm": 2.15625, "learning_rate": 2.8640900947018172e-05, "loss": 0.4367, "step": 5008 }, { "epoch": 1.282112, "grad_norm": 2.171875, "learning_rate": 2.863663509939425e-05, "loss": 0.47, "step": 5009 }, { "epoch": 1.282368, "grad_norm": 2.265625, "learning_rate": 2.863236925177033e-05, "loss": 0.4933, "step": 5010 }, { "epoch": 1.282624, "grad_norm": 2.015625, "learning_rate": 2.8628103404146405e-05, "loss": 0.4661, "step": 5011 }, { "epoch": 1.28288, "grad_norm": 2.140625, "learning_rate": 2.8623837556522483e-05, "loss": 0.4459, "step": 5012 }, { "epoch": 1.283136, "grad_norm": 2.046875, "learning_rate": 2.8619571708898557e-05, "loss": 0.4565, "step": 5013 }, { "epoch": 1.283392, "grad_norm": 2.125, "learning_rate": 2.8615305861274638e-05, "loss": 0.4594, "step": 5014 }, { "epoch": 1.283648, "grad_norm": 2.28125, "learning_rate": 2.8611040013650716e-05, "loss": 0.4299, "step": 5015 }, { "epoch": 1.283904, "grad_norm": 2.21875, "learning_rate": 2.860677416602679e-05, "loss": 0.4474, "step": 5016 }, { "epoch": 1.28416, "grad_norm": 2.234375, "learning_rate": 2.8602508318402864e-05, "loss": 0.4607, "step": 5017 }, { "epoch": 1.284416, "grad_norm": 1.96875, "learning_rate": 2.8598242470778945e-05, "loss": 0.4723, "step": 5018 }, { "epoch": 1.284672, "grad_norm": 2.0625, "learning_rate": 2.8593976623155023e-05, "loss": 0.4417, "step": 5019 }, { "epoch": 1.284928, "grad_norm": 2.1875, "learning_rate": 2.8589710775531097e-05, "loss": 0.4881, "step": 5020 }, { "epoch": 1.285184, "grad_norm": 2.125, "learning_rate": 2.8585444927907178e-05, "loss": 0.4492, "step": 5021 }, { "epoch": 1.28544, "grad_norm": 2.3125, "learning_rate": 2.8581179080283256e-05, "loss": 0.4748, "step": 5022 }, { "epoch": 1.285696, "grad_norm": 1.9375, "learning_rate": 2.857691323265933e-05, "loss": 0.4392, "step": 5023 }, { "epoch": 1.285952, "grad_norm": 2.0625, "learning_rate": 2.8572647385035404e-05, "loss": 0.4525, "step": 5024 }, { "epoch": 1.286208, "grad_norm": 2.015625, "learning_rate": 2.856838153741149e-05, "loss": 0.4383, "step": 5025 }, { "epoch": 1.286464, "grad_norm": 2.09375, "learning_rate": 2.8564115689787563e-05, "loss": 0.4483, "step": 5026 }, { "epoch": 1.2867199999999999, "grad_norm": 2.078125, "learning_rate": 2.8559849842163637e-05, "loss": 0.4661, "step": 5027 }, { "epoch": 1.2869760000000001, "grad_norm": 2.21875, "learning_rate": 2.8555583994539715e-05, "loss": 0.4344, "step": 5028 }, { "epoch": 1.287232, "grad_norm": 2.0, "learning_rate": 2.8551318146915796e-05, "loss": 0.4837, "step": 5029 }, { "epoch": 1.287488, "grad_norm": 2.109375, "learning_rate": 2.854705229929187e-05, "loss": 0.4715, "step": 5030 }, { "epoch": 1.287744, "grad_norm": 2.078125, "learning_rate": 2.8542786451667948e-05, "loss": 0.4253, "step": 5031 }, { "epoch": 1.288, "grad_norm": 2.1875, "learning_rate": 2.8538520604044022e-05, "loss": 0.4064, "step": 5032 }, { "epoch": 1.288256, "grad_norm": 2.046875, "learning_rate": 2.8534254756420103e-05, "loss": 0.4567, "step": 5033 }, { "epoch": 1.2885119999999999, "grad_norm": 2.328125, "learning_rate": 2.8529988908796178e-05, "loss": 0.4768, "step": 5034 }, { "epoch": 1.2887680000000001, "grad_norm": 2.21875, "learning_rate": 2.8525723061172255e-05, "loss": 0.4897, "step": 5035 }, { "epoch": 1.289024, "grad_norm": 2.25, "learning_rate": 2.8521457213548336e-05, "loss": 0.4563, "step": 5036 }, { "epoch": 1.28928, "grad_norm": 2.28125, "learning_rate": 2.851719136592441e-05, "loss": 0.3885, "step": 5037 }, { "epoch": 1.289536, "grad_norm": 2.171875, "learning_rate": 2.8512925518300488e-05, "loss": 0.4443, "step": 5038 }, { "epoch": 1.289792, "grad_norm": 2.171875, "learning_rate": 2.8508659670676562e-05, "loss": 0.4641, "step": 5039 }, { "epoch": 1.290048, "grad_norm": 2.25, "learning_rate": 2.8504393823052643e-05, "loss": 0.4712, "step": 5040 }, { "epoch": 1.290304, "grad_norm": 2.234375, "learning_rate": 2.850012797542872e-05, "loss": 0.41, "step": 5041 }, { "epoch": 1.29056, "grad_norm": 2.078125, "learning_rate": 2.8495862127804795e-05, "loss": 0.4252, "step": 5042 }, { "epoch": 1.290816, "grad_norm": 2.171875, "learning_rate": 2.849159628018087e-05, "loss": 0.4731, "step": 5043 }, { "epoch": 1.291072, "grad_norm": 2.3125, "learning_rate": 2.848733043255695e-05, "loss": 0.4438, "step": 5044 }, { "epoch": 1.291328, "grad_norm": 2.203125, "learning_rate": 2.848306458493303e-05, "loss": 0.4597, "step": 5045 }, { "epoch": 1.291584, "grad_norm": 2.078125, "learning_rate": 2.8478798737309103e-05, "loss": 0.4413, "step": 5046 }, { "epoch": 1.29184, "grad_norm": 2.125, "learning_rate": 2.847453288968518e-05, "loss": 0.5055, "step": 5047 }, { "epoch": 1.292096, "grad_norm": 2.1875, "learning_rate": 2.847026704206126e-05, "loss": 0.4448, "step": 5048 }, { "epoch": 1.292352, "grad_norm": 2.046875, "learning_rate": 2.8466001194437336e-05, "loss": 0.4436, "step": 5049 }, { "epoch": 1.292608, "grad_norm": 2.1875, "learning_rate": 2.8461735346813413e-05, "loss": 0.4478, "step": 5050 }, { "epoch": 1.292864, "grad_norm": 2.25, "learning_rate": 2.8457469499189494e-05, "loss": 0.4354, "step": 5051 }, { "epoch": 1.29312, "grad_norm": 2.03125, "learning_rate": 2.845320365156557e-05, "loss": 0.4341, "step": 5052 }, { "epoch": 1.293376, "grad_norm": 2.109375, "learning_rate": 2.8448937803941643e-05, "loss": 0.4268, "step": 5053 }, { "epoch": 1.2936320000000001, "grad_norm": 2.265625, "learning_rate": 2.844467195631772e-05, "loss": 0.4468, "step": 5054 }, { "epoch": 1.293888, "grad_norm": 2.34375, "learning_rate": 2.84404061086938e-05, "loss": 0.4794, "step": 5055 }, { "epoch": 1.294144, "grad_norm": 2.015625, "learning_rate": 2.8436140261069876e-05, "loss": 0.4564, "step": 5056 }, { "epoch": 1.2944, "grad_norm": 2.046875, "learning_rate": 2.8431874413445953e-05, "loss": 0.4474, "step": 5057 }, { "epoch": 1.294656, "grad_norm": 2.15625, "learning_rate": 2.8427608565822028e-05, "loss": 0.4429, "step": 5058 }, { "epoch": 1.294912, "grad_norm": 2.078125, "learning_rate": 2.842334271819811e-05, "loss": 0.4475, "step": 5059 }, { "epoch": 1.2951679999999999, "grad_norm": 2.171875, "learning_rate": 2.8419076870574186e-05, "loss": 0.4673, "step": 5060 }, { "epoch": 1.2954240000000001, "grad_norm": 1.9453125, "learning_rate": 2.841481102295026e-05, "loss": 0.4504, "step": 5061 }, { "epoch": 1.29568, "grad_norm": 2.265625, "learning_rate": 2.8410545175326335e-05, "loss": 0.4046, "step": 5062 }, { "epoch": 1.295936, "grad_norm": 1.96875, "learning_rate": 2.8406279327702416e-05, "loss": 0.4761, "step": 5063 }, { "epoch": 1.296192, "grad_norm": 2.09375, "learning_rate": 2.8402013480078494e-05, "loss": 0.5047, "step": 5064 }, { "epoch": 1.296448, "grad_norm": 2.1875, "learning_rate": 2.8397747632454568e-05, "loss": 0.4475, "step": 5065 }, { "epoch": 1.296704, "grad_norm": 2.28125, "learning_rate": 2.8393481784830646e-05, "loss": 0.4741, "step": 5066 }, { "epoch": 1.29696, "grad_norm": 2.015625, "learning_rate": 2.8389215937206727e-05, "loss": 0.4493, "step": 5067 }, { "epoch": 1.297216, "grad_norm": 2.1875, "learning_rate": 2.83849500895828e-05, "loss": 0.4749, "step": 5068 }, { "epoch": 1.297472, "grad_norm": 2.265625, "learning_rate": 2.838068424195888e-05, "loss": 0.432, "step": 5069 }, { "epoch": 1.297728, "grad_norm": 2.21875, "learning_rate": 2.837641839433496e-05, "loss": 0.4573, "step": 5070 }, { "epoch": 1.297984, "grad_norm": 2.15625, "learning_rate": 2.8372152546711034e-05, "loss": 0.447, "step": 5071 }, { "epoch": 1.29824, "grad_norm": 2.125, "learning_rate": 2.8367886699087108e-05, "loss": 0.4634, "step": 5072 }, { "epoch": 1.298496, "grad_norm": 2.109375, "learning_rate": 2.8363620851463186e-05, "loss": 0.4667, "step": 5073 }, { "epoch": 1.298752, "grad_norm": 2.0, "learning_rate": 2.8359355003839267e-05, "loss": 0.4522, "step": 5074 }, { "epoch": 1.299008, "grad_norm": 2.171875, "learning_rate": 2.835508915621534e-05, "loss": 0.4572, "step": 5075 }, { "epoch": 1.299264, "grad_norm": 2.3125, "learning_rate": 2.835082330859142e-05, "loss": 0.4985, "step": 5076 }, { "epoch": 1.29952, "grad_norm": 2.28125, "learning_rate": 2.8346557460967493e-05, "loss": 0.4866, "step": 5077 }, { "epoch": 1.299776, "grad_norm": 1.96875, "learning_rate": 2.8342291613343574e-05, "loss": 0.4688, "step": 5078 }, { "epoch": 1.300032, "grad_norm": 2.0625, "learning_rate": 2.833802576571965e-05, "loss": 0.4553, "step": 5079 }, { "epoch": 1.300288, "grad_norm": 2.046875, "learning_rate": 2.8333759918095726e-05, "loss": 0.4589, "step": 5080 }, { "epoch": 1.300544, "grad_norm": 2.125, "learning_rate": 2.83294940704718e-05, "loss": 0.4317, "step": 5081 }, { "epoch": 1.3008, "grad_norm": 2.265625, "learning_rate": 2.832522822284788e-05, "loss": 0.4729, "step": 5082 }, { "epoch": 1.301056, "grad_norm": 2.234375, "learning_rate": 2.832096237522396e-05, "loss": 0.4395, "step": 5083 }, { "epoch": 1.301312, "grad_norm": 2.28125, "learning_rate": 2.8316696527600033e-05, "loss": 0.4293, "step": 5084 }, { "epoch": 1.301568, "grad_norm": 2.21875, "learning_rate": 2.8312430679976114e-05, "loss": 0.4159, "step": 5085 }, { "epoch": 1.3018239999999999, "grad_norm": 2.1875, "learning_rate": 2.8308164832352192e-05, "loss": 0.4658, "step": 5086 }, { "epoch": 1.3020800000000001, "grad_norm": 2.25, "learning_rate": 2.8303898984728266e-05, "loss": 0.4645, "step": 5087 }, { "epoch": 1.302336, "grad_norm": 2.140625, "learning_rate": 2.8299633137104344e-05, "loss": 0.4308, "step": 5088 }, { "epoch": 1.302592, "grad_norm": 2.09375, "learning_rate": 2.8295367289480425e-05, "loss": 0.477, "step": 5089 }, { "epoch": 1.302848, "grad_norm": 1.984375, "learning_rate": 2.82911014418565e-05, "loss": 0.4747, "step": 5090 }, { "epoch": 1.303104, "grad_norm": 2.109375, "learning_rate": 2.8286835594232573e-05, "loss": 0.4827, "step": 5091 }, { "epoch": 1.30336, "grad_norm": 2.015625, "learning_rate": 2.828256974660865e-05, "loss": 0.4414, "step": 5092 }, { "epoch": 1.3036159999999999, "grad_norm": 2.140625, "learning_rate": 2.8278303898984732e-05, "loss": 0.435, "step": 5093 }, { "epoch": 1.303872, "grad_norm": 2.234375, "learning_rate": 2.8274038051360806e-05, "loss": 0.4622, "step": 5094 }, { "epoch": 1.304128, "grad_norm": 1.953125, "learning_rate": 2.8269772203736884e-05, "loss": 0.4811, "step": 5095 }, { "epoch": 1.304384, "grad_norm": 2.046875, "learning_rate": 2.8265506356112958e-05, "loss": 0.4814, "step": 5096 }, { "epoch": 1.30464, "grad_norm": 2.046875, "learning_rate": 2.826124050848904e-05, "loss": 0.5014, "step": 5097 }, { "epoch": 1.304896, "grad_norm": 2.140625, "learning_rate": 2.8256974660865117e-05, "loss": 0.4358, "step": 5098 }, { "epoch": 1.305152, "grad_norm": 2.15625, "learning_rate": 2.825270881324119e-05, "loss": 0.4504, "step": 5099 }, { "epoch": 1.305408, "grad_norm": 2.1875, "learning_rate": 2.8248442965617272e-05, "loss": 0.4285, "step": 5100 }, { "epoch": 1.305664, "grad_norm": 2.140625, "learning_rate": 2.8244177117993346e-05, "loss": 0.4711, "step": 5101 }, { "epoch": 1.30592, "grad_norm": 2.234375, "learning_rate": 2.8239911270369424e-05, "loss": 0.4762, "step": 5102 }, { "epoch": 1.306176, "grad_norm": 2.09375, "learning_rate": 2.82356454227455e-05, "loss": 0.4696, "step": 5103 }, { "epoch": 1.306432, "grad_norm": 1.984375, "learning_rate": 2.823137957512158e-05, "loss": 0.4271, "step": 5104 }, { "epoch": 1.306688, "grad_norm": 2.125, "learning_rate": 2.8227113727497657e-05, "loss": 0.4546, "step": 5105 }, { "epoch": 1.306944, "grad_norm": 2.3125, "learning_rate": 2.822284787987373e-05, "loss": 0.4148, "step": 5106 }, { "epoch": 1.3072, "grad_norm": 2.140625, "learning_rate": 2.821858203224981e-05, "loss": 0.4649, "step": 5107 }, { "epoch": 1.307456, "grad_norm": 2.1875, "learning_rate": 2.821431618462589e-05, "loss": 0.4531, "step": 5108 }, { "epoch": 1.307712, "grad_norm": 2.171875, "learning_rate": 2.8210050337001964e-05, "loss": 0.4583, "step": 5109 }, { "epoch": 1.307968, "grad_norm": 1.9765625, "learning_rate": 2.820578448937804e-05, "loss": 0.4468, "step": 5110 }, { "epoch": 1.308224, "grad_norm": 1.9765625, "learning_rate": 2.8201518641754116e-05, "loss": 0.481, "step": 5111 }, { "epoch": 1.3084799999999999, "grad_norm": 2.140625, "learning_rate": 2.8197252794130197e-05, "loss": 0.5201, "step": 5112 }, { "epoch": 1.3087360000000001, "grad_norm": 2.21875, "learning_rate": 2.819298694650627e-05, "loss": 0.4856, "step": 5113 }, { "epoch": 1.308992, "grad_norm": 2.25, "learning_rate": 2.818872109888235e-05, "loss": 0.4607, "step": 5114 }, { "epoch": 1.309248, "grad_norm": 2.03125, "learning_rate": 2.8184455251258423e-05, "loss": 0.4614, "step": 5115 }, { "epoch": 1.309504, "grad_norm": 2.015625, "learning_rate": 2.8180189403634505e-05, "loss": 0.4478, "step": 5116 }, { "epoch": 1.30976, "grad_norm": 2.09375, "learning_rate": 2.8175923556010582e-05, "loss": 0.447, "step": 5117 }, { "epoch": 1.310016, "grad_norm": 2.078125, "learning_rate": 2.8171657708386656e-05, "loss": 0.4385, "step": 5118 }, { "epoch": 1.3102719999999999, "grad_norm": 2.046875, "learning_rate": 2.8167391860762737e-05, "loss": 0.4319, "step": 5119 }, { "epoch": 1.3105280000000001, "grad_norm": 2.171875, "learning_rate": 2.8163126013138812e-05, "loss": 0.4726, "step": 5120 }, { "epoch": 1.310784, "grad_norm": 2.171875, "learning_rate": 2.815886016551489e-05, "loss": 0.4922, "step": 5121 }, { "epoch": 1.31104, "grad_norm": 2.09375, "learning_rate": 2.8154594317890964e-05, "loss": 0.4173, "step": 5122 }, { "epoch": 1.311296, "grad_norm": 2.0625, "learning_rate": 2.8150328470267045e-05, "loss": 0.4794, "step": 5123 }, { "epoch": 1.311552, "grad_norm": 2.09375, "learning_rate": 2.8146062622643122e-05, "loss": 0.4551, "step": 5124 }, { "epoch": 1.311808, "grad_norm": 2.328125, "learning_rate": 2.8141796775019197e-05, "loss": 0.484, "step": 5125 }, { "epoch": 1.312064, "grad_norm": 2.296875, "learning_rate": 2.813753092739527e-05, "loss": 0.4674, "step": 5126 }, { "epoch": 1.31232, "grad_norm": 2.171875, "learning_rate": 2.8133265079771355e-05, "loss": 0.4818, "step": 5127 }, { "epoch": 1.312576, "grad_norm": 2.234375, "learning_rate": 2.812899923214743e-05, "loss": 0.4333, "step": 5128 }, { "epoch": 1.312832, "grad_norm": 2.171875, "learning_rate": 2.8124733384523504e-05, "loss": 0.4069, "step": 5129 }, { "epoch": 1.313088, "grad_norm": 2.21875, "learning_rate": 2.812046753689958e-05, "loss": 0.4598, "step": 5130 }, { "epoch": 1.313344, "grad_norm": 1.9140625, "learning_rate": 2.8116201689275663e-05, "loss": 0.4213, "step": 5131 }, { "epoch": 1.3136, "grad_norm": 2.328125, "learning_rate": 2.8111935841651737e-05, "loss": 0.4395, "step": 5132 }, { "epoch": 1.313856, "grad_norm": 2.3125, "learning_rate": 2.8107669994027814e-05, "loss": 0.4451, "step": 5133 }, { "epoch": 1.314112, "grad_norm": 2.15625, "learning_rate": 2.8103404146403896e-05, "loss": 0.4632, "step": 5134 }, { "epoch": 1.314368, "grad_norm": 2.25, "learning_rate": 2.809913829877997e-05, "loss": 0.4647, "step": 5135 }, { "epoch": 1.314624, "grad_norm": 2.265625, "learning_rate": 2.8094872451156044e-05, "loss": 0.423, "step": 5136 }, { "epoch": 1.31488, "grad_norm": 2.125, "learning_rate": 2.8090606603532122e-05, "loss": 0.4939, "step": 5137 }, { "epoch": 1.315136, "grad_norm": 1.875, "learning_rate": 2.8086340755908203e-05, "loss": 0.4767, "step": 5138 }, { "epoch": 1.3153920000000001, "grad_norm": 2.109375, "learning_rate": 2.8082074908284277e-05, "loss": 0.4407, "step": 5139 }, { "epoch": 1.315648, "grad_norm": 1.9921875, "learning_rate": 2.8077809060660355e-05, "loss": 0.4817, "step": 5140 }, { "epoch": 1.315904, "grad_norm": 2.1875, "learning_rate": 2.807354321303643e-05, "loss": 0.4492, "step": 5141 }, { "epoch": 1.31616, "grad_norm": 2.0, "learning_rate": 2.806927736541251e-05, "loss": 0.4328, "step": 5142 }, { "epoch": 1.316416, "grad_norm": 2.171875, "learning_rate": 2.8065011517788588e-05, "loss": 0.4573, "step": 5143 }, { "epoch": 1.316672, "grad_norm": 2.046875, "learning_rate": 2.8060745670164662e-05, "loss": 0.4303, "step": 5144 }, { "epoch": 1.3169279999999999, "grad_norm": 2.09375, "learning_rate": 2.8056479822540736e-05, "loss": 0.4564, "step": 5145 }, { "epoch": 1.3171840000000001, "grad_norm": 2.40625, "learning_rate": 2.8052213974916817e-05, "loss": 0.48, "step": 5146 }, { "epoch": 1.31744, "grad_norm": 2.09375, "learning_rate": 2.8047948127292895e-05, "loss": 0.4521, "step": 5147 }, { "epoch": 1.317696, "grad_norm": 1.921875, "learning_rate": 2.804368227966897e-05, "loss": 0.4578, "step": 5148 }, { "epoch": 1.317952, "grad_norm": 2.140625, "learning_rate": 2.803941643204505e-05, "loss": 0.4499, "step": 5149 }, { "epoch": 1.318208, "grad_norm": 2.171875, "learning_rate": 2.8035150584421128e-05, "loss": 0.457, "step": 5150 }, { "epoch": 1.318464, "grad_norm": 2.046875, "learning_rate": 2.8030884736797202e-05, "loss": 0.458, "step": 5151 }, { "epoch": 1.31872, "grad_norm": 2.3125, "learning_rate": 2.802661888917328e-05, "loss": 0.4549, "step": 5152 }, { "epoch": 1.318976, "grad_norm": 2.0625, "learning_rate": 2.802235304154936e-05, "loss": 0.4359, "step": 5153 }, { "epoch": 1.319232, "grad_norm": 2.140625, "learning_rate": 2.8018087193925435e-05, "loss": 0.4245, "step": 5154 }, { "epoch": 1.319488, "grad_norm": 2.03125, "learning_rate": 2.801382134630151e-05, "loss": 0.4491, "step": 5155 }, { "epoch": 1.319744, "grad_norm": 2.28125, "learning_rate": 2.8009555498677587e-05, "loss": 0.4796, "step": 5156 }, { "epoch": 1.32, "grad_norm": 2.109375, "learning_rate": 2.8005289651053668e-05, "loss": 0.4728, "step": 5157 }, { "epoch": 1.320256, "grad_norm": 2.171875, "learning_rate": 2.8001023803429742e-05, "loss": 0.4335, "step": 5158 }, { "epoch": 1.320512, "grad_norm": 2.09375, "learning_rate": 2.799675795580582e-05, "loss": 0.4541, "step": 5159 }, { "epoch": 1.320768, "grad_norm": 2.046875, "learning_rate": 2.7992492108181894e-05, "loss": 0.4349, "step": 5160 }, { "epoch": 1.321024, "grad_norm": 2.234375, "learning_rate": 2.7988226260557975e-05, "loss": 0.4699, "step": 5161 }, { "epoch": 1.32128, "grad_norm": 2.203125, "learning_rate": 2.7983960412934053e-05, "loss": 0.4607, "step": 5162 }, { "epoch": 1.321536, "grad_norm": 2.21875, "learning_rate": 2.7979694565310127e-05, "loss": 0.4397, "step": 5163 }, { "epoch": 1.321792, "grad_norm": 2.234375, "learning_rate": 2.79754287176862e-05, "loss": 0.4473, "step": 5164 }, { "epoch": 1.3220480000000001, "grad_norm": 2.1875, "learning_rate": 2.7971162870062282e-05, "loss": 0.4442, "step": 5165 }, { "epoch": 1.322304, "grad_norm": 2.0625, "learning_rate": 2.796689702243836e-05, "loss": 0.4381, "step": 5166 }, { "epoch": 1.32256, "grad_norm": 2.109375, "learning_rate": 2.7962631174814434e-05, "loss": 0.4642, "step": 5167 }, { "epoch": 1.322816, "grad_norm": 2.234375, "learning_rate": 2.7958365327190515e-05, "loss": 0.4569, "step": 5168 }, { "epoch": 1.323072, "grad_norm": 2.375, "learning_rate": 2.7954099479566593e-05, "loss": 0.4816, "step": 5169 }, { "epoch": 1.323328, "grad_norm": 2.171875, "learning_rate": 2.7949833631942667e-05, "loss": 0.4556, "step": 5170 }, { "epoch": 1.3235839999999999, "grad_norm": 2.125, "learning_rate": 2.7945567784318745e-05, "loss": 0.4485, "step": 5171 }, { "epoch": 1.3238400000000001, "grad_norm": 2.25, "learning_rate": 2.7941301936694826e-05, "loss": 0.4426, "step": 5172 }, { "epoch": 1.324096, "grad_norm": 2.140625, "learning_rate": 2.79370360890709e-05, "loss": 0.4872, "step": 5173 }, { "epoch": 1.324352, "grad_norm": 2.40625, "learning_rate": 2.7932770241446975e-05, "loss": 0.4489, "step": 5174 }, { "epoch": 1.324608, "grad_norm": 2.09375, "learning_rate": 2.7928504393823052e-05, "loss": 0.4296, "step": 5175 }, { "epoch": 1.324864, "grad_norm": 2.125, "learning_rate": 2.7924238546199133e-05, "loss": 0.4825, "step": 5176 }, { "epoch": 1.32512, "grad_norm": 2.125, "learning_rate": 2.7919972698575208e-05, "loss": 0.4564, "step": 5177 }, { "epoch": 1.3253759999999999, "grad_norm": 2.140625, "learning_rate": 2.7915706850951285e-05, "loss": 0.4608, "step": 5178 }, { "epoch": 1.325632, "grad_norm": 2.15625, "learning_rate": 2.791144100332736e-05, "loss": 0.4968, "step": 5179 }, { "epoch": 1.325888, "grad_norm": 2.140625, "learning_rate": 2.790717515570344e-05, "loss": 0.4396, "step": 5180 }, { "epoch": 1.326144, "grad_norm": 1.9453125, "learning_rate": 2.7902909308079518e-05, "loss": 0.4508, "step": 5181 }, { "epoch": 1.3264, "grad_norm": 2.15625, "learning_rate": 2.7898643460455592e-05, "loss": 0.4857, "step": 5182 }, { "epoch": 1.326656, "grad_norm": 2.1875, "learning_rate": 2.7894377612831673e-05, "loss": 0.4752, "step": 5183 }, { "epoch": 1.326912, "grad_norm": 2.109375, "learning_rate": 2.7890111765207748e-05, "loss": 0.4608, "step": 5184 }, { "epoch": 1.327168, "grad_norm": 2.390625, "learning_rate": 2.7885845917583825e-05, "loss": 0.4676, "step": 5185 }, { "epoch": 1.327424, "grad_norm": 2.34375, "learning_rate": 2.78815800699599e-05, "loss": 0.4781, "step": 5186 }, { "epoch": 1.32768, "grad_norm": 2.015625, "learning_rate": 2.787731422233598e-05, "loss": 0.4721, "step": 5187 }, { "epoch": 1.327936, "grad_norm": 2.046875, "learning_rate": 2.787304837471206e-05, "loss": 0.4891, "step": 5188 }, { "epoch": 1.328192, "grad_norm": 2.15625, "learning_rate": 2.7868782527088133e-05, "loss": 0.4631, "step": 5189 }, { "epoch": 1.328448, "grad_norm": 2.328125, "learning_rate": 2.786451667946421e-05, "loss": 0.4558, "step": 5190 }, { "epoch": 1.328704, "grad_norm": 2.140625, "learning_rate": 2.786025083184029e-05, "loss": 0.4811, "step": 5191 }, { "epoch": 1.32896, "grad_norm": 2.046875, "learning_rate": 2.7855984984216366e-05, "loss": 0.479, "step": 5192 }, { "epoch": 1.329216, "grad_norm": 2.09375, "learning_rate": 2.785171913659244e-05, "loss": 0.4115, "step": 5193 }, { "epoch": 1.329472, "grad_norm": 2.078125, "learning_rate": 2.7847453288968518e-05, "loss": 0.4513, "step": 5194 }, { "epoch": 1.329728, "grad_norm": 2.234375, "learning_rate": 2.78431874413446e-05, "loss": 0.4882, "step": 5195 }, { "epoch": 1.329984, "grad_norm": 2.21875, "learning_rate": 2.7838921593720673e-05, "loss": 0.4524, "step": 5196 }, { "epoch": 1.3302399999999999, "grad_norm": 2.171875, "learning_rate": 2.783465574609675e-05, "loss": 0.4394, "step": 5197 }, { "epoch": 1.3304960000000001, "grad_norm": 2.0625, "learning_rate": 2.783038989847283e-05, "loss": 0.4605, "step": 5198 }, { "epoch": 1.330752, "grad_norm": 2.15625, "learning_rate": 2.7826124050848906e-05, "loss": 0.4413, "step": 5199 }, { "epoch": 1.331008, "grad_norm": 2.125, "learning_rate": 2.7821858203224983e-05, "loss": 0.4194, "step": 5200 }, { "epoch": 1.331264, "grad_norm": 2.078125, "learning_rate": 2.7817592355601058e-05, "loss": 0.4628, "step": 5201 }, { "epoch": 1.33152, "grad_norm": 2.203125, "learning_rate": 2.781332650797714e-05, "loss": 0.473, "step": 5202 }, { "epoch": 1.331776, "grad_norm": 2.015625, "learning_rate": 2.7809060660353213e-05, "loss": 0.4295, "step": 5203 }, { "epoch": 1.3320319999999999, "grad_norm": 1.921875, "learning_rate": 2.780479481272929e-05, "loss": 0.482, "step": 5204 }, { "epoch": 1.332288, "grad_norm": 2.125, "learning_rate": 2.7800528965105365e-05, "loss": 0.4411, "step": 5205 }, { "epoch": 1.332544, "grad_norm": 2.1875, "learning_rate": 2.7796263117481446e-05, "loss": 0.4491, "step": 5206 }, { "epoch": 1.3328, "grad_norm": 2.1875, "learning_rate": 2.7791997269857524e-05, "loss": 0.4666, "step": 5207 }, { "epoch": 1.333056, "grad_norm": 1.8984375, "learning_rate": 2.7787731422233598e-05, "loss": 0.4295, "step": 5208 }, { "epoch": 1.333312, "grad_norm": 1.9609375, "learning_rate": 2.7783465574609676e-05, "loss": 0.4468, "step": 5209 }, { "epoch": 1.333568, "grad_norm": 2.078125, "learning_rate": 2.7779199726985757e-05, "loss": 0.4452, "step": 5210 }, { "epoch": 1.333824, "grad_norm": 2.296875, "learning_rate": 2.777493387936183e-05, "loss": 0.4483, "step": 5211 }, { "epoch": 1.33408, "grad_norm": 2.28125, "learning_rate": 2.7770668031737905e-05, "loss": 0.4441, "step": 5212 }, { "epoch": 1.334336, "grad_norm": 2.046875, "learning_rate": 2.7766402184113983e-05, "loss": 0.4628, "step": 5213 }, { "epoch": 1.334592, "grad_norm": 1.96875, "learning_rate": 2.7762136336490064e-05, "loss": 0.4401, "step": 5214 }, { "epoch": 1.334848, "grad_norm": 2.140625, "learning_rate": 2.7757870488866138e-05, "loss": 0.4834, "step": 5215 }, { "epoch": 1.335104, "grad_norm": 2.0625, "learning_rate": 2.7753604641242216e-05, "loss": 0.4754, "step": 5216 }, { "epoch": 1.33536, "grad_norm": 2.125, "learning_rate": 2.7749338793618297e-05, "loss": 0.4451, "step": 5217 }, { "epoch": 1.335616, "grad_norm": 2.078125, "learning_rate": 2.774507294599437e-05, "loss": 0.4427, "step": 5218 }, { "epoch": 1.335872, "grad_norm": 2.21875, "learning_rate": 2.774080709837045e-05, "loss": 0.4521, "step": 5219 }, { "epoch": 1.336128, "grad_norm": 2.046875, "learning_rate": 2.7736541250746523e-05, "loss": 0.4181, "step": 5220 }, { "epoch": 1.336384, "grad_norm": 2.140625, "learning_rate": 2.7732275403122604e-05, "loss": 0.4549, "step": 5221 }, { "epoch": 1.33664, "grad_norm": 2.0625, "learning_rate": 2.7728009555498678e-05, "loss": 0.4746, "step": 5222 }, { "epoch": 1.3368959999999999, "grad_norm": 1.96875, "learning_rate": 2.7723743707874756e-05, "loss": 0.4372, "step": 5223 }, { "epoch": 1.3371520000000001, "grad_norm": 2.203125, "learning_rate": 2.771947786025083e-05, "loss": 0.4737, "step": 5224 }, { "epoch": 1.337408, "grad_norm": 2.125, "learning_rate": 2.771521201262691e-05, "loss": 0.4668, "step": 5225 }, { "epoch": 1.337664, "grad_norm": 2.328125, "learning_rate": 2.771094616500299e-05, "loss": 0.4179, "step": 5226 }, { "epoch": 1.33792, "grad_norm": 1.921875, "learning_rate": 2.7706680317379063e-05, "loss": 0.4766, "step": 5227 }, { "epoch": 1.338176, "grad_norm": 2.234375, "learning_rate": 2.7702414469755137e-05, "loss": 0.4486, "step": 5228 }, { "epoch": 1.338432, "grad_norm": 2.1875, "learning_rate": 2.7698148622131222e-05, "loss": 0.4296, "step": 5229 }, { "epoch": 1.3386879999999999, "grad_norm": 2.203125, "learning_rate": 2.7693882774507296e-05, "loss": 0.4519, "step": 5230 }, { "epoch": 1.3389440000000001, "grad_norm": 2.15625, "learning_rate": 2.768961692688337e-05, "loss": 0.4278, "step": 5231 }, { "epoch": 1.3392, "grad_norm": 2.140625, "learning_rate": 2.768535107925945e-05, "loss": 0.4491, "step": 5232 }, { "epoch": 1.339456, "grad_norm": 2.21875, "learning_rate": 2.768108523163553e-05, "loss": 0.4524, "step": 5233 }, { "epoch": 1.339712, "grad_norm": 1.9921875, "learning_rate": 2.7676819384011603e-05, "loss": 0.4623, "step": 5234 }, { "epoch": 1.339968, "grad_norm": 2.25, "learning_rate": 2.767255353638768e-05, "loss": 0.4437, "step": 5235 }, { "epoch": 1.340224, "grad_norm": 2.203125, "learning_rate": 2.7668287688763762e-05, "loss": 0.4857, "step": 5236 }, { "epoch": 1.34048, "grad_norm": 1.953125, "learning_rate": 2.7664021841139836e-05, "loss": 0.4344, "step": 5237 }, { "epoch": 1.340736, "grad_norm": 2.0, "learning_rate": 2.765975599351591e-05, "loss": 0.4461, "step": 5238 }, { "epoch": 1.340992, "grad_norm": 2.125, "learning_rate": 2.7655490145891988e-05, "loss": 0.4637, "step": 5239 }, { "epoch": 1.341248, "grad_norm": 1.9765625, "learning_rate": 2.765122429826807e-05, "loss": 0.4621, "step": 5240 }, { "epoch": 1.341504, "grad_norm": 2.125, "learning_rate": 2.7646958450644144e-05, "loss": 0.4335, "step": 5241 }, { "epoch": 1.34176, "grad_norm": 2.171875, "learning_rate": 2.764269260302022e-05, "loss": 0.4658, "step": 5242 }, { "epoch": 1.342016, "grad_norm": 1.9453125, "learning_rate": 2.7638426755396295e-05, "loss": 0.4466, "step": 5243 }, { "epoch": 1.342272, "grad_norm": 2.265625, "learning_rate": 2.7634160907772377e-05, "loss": 0.418, "step": 5244 }, { "epoch": 1.342528, "grad_norm": 2.1875, "learning_rate": 2.7629895060148454e-05, "loss": 0.445, "step": 5245 }, { "epoch": 1.342784, "grad_norm": 2.03125, "learning_rate": 2.762562921252453e-05, "loss": 0.4294, "step": 5246 }, { "epoch": 1.34304, "grad_norm": 2.4375, "learning_rate": 2.762136336490061e-05, "loss": 0.4576, "step": 5247 }, { "epoch": 1.343296, "grad_norm": 2.203125, "learning_rate": 2.7617097517276687e-05, "loss": 0.4742, "step": 5248 }, { "epoch": 1.343552, "grad_norm": 2.078125, "learning_rate": 2.761283166965276e-05, "loss": 0.4321, "step": 5249 }, { "epoch": 1.3438080000000001, "grad_norm": 1.953125, "learning_rate": 2.7608565822028836e-05, "loss": 0.4401, "step": 5250 }, { "epoch": 1.344064, "grad_norm": 1.9296875, "learning_rate": 2.7604299974404917e-05, "loss": 0.4096, "step": 5251 }, { "epoch": 1.34432, "grad_norm": 2.125, "learning_rate": 2.7600034126780994e-05, "loss": 0.4887, "step": 5252 }, { "epoch": 1.344576, "grad_norm": 2.03125, "learning_rate": 2.759576827915707e-05, "loss": 0.4646, "step": 5253 }, { "epoch": 1.344832, "grad_norm": 1.9453125, "learning_rate": 2.7591502431533146e-05, "loss": 0.4538, "step": 5254 }, { "epoch": 1.345088, "grad_norm": 2.0, "learning_rate": 2.7587236583909227e-05, "loss": 0.4436, "step": 5255 }, { "epoch": 1.3453439999999999, "grad_norm": 2.171875, "learning_rate": 2.75829707362853e-05, "loss": 0.4465, "step": 5256 }, { "epoch": 1.3456000000000001, "grad_norm": 2.125, "learning_rate": 2.7578704888661376e-05, "loss": 0.4863, "step": 5257 }, { "epoch": 1.345856, "grad_norm": 1.921875, "learning_rate": 2.7574439041037454e-05, "loss": 0.4332, "step": 5258 }, { "epoch": 1.346112, "grad_norm": 2.078125, "learning_rate": 2.7570173193413535e-05, "loss": 0.3987, "step": 5259 }, { "epoch": 1.346368, "grad_norm": 1.96875, "learning_rate": 2.756590734578961e-05, "loss": 0.4205, "step": 5260 }, { "epoch": 1.346624, "grad_norm": 2.171875, "learning_rate": 2.7561641498165686e-05, "loss": 0.4369, "step": 5261 }, { "epoch": 1.34688, "grad_norm": 2.0625, "learning_rate": 2.755737565054176e-05, "loss": 0.4189, "step": 5262 }, { "epoch": 1.347136, "grad_norm": 2.109375, "learning_rate": 2.7553109802917842e-05, "loss": 0.4119, "step": 5263 }, { "epoch": 1.347392, "grad_norm": 2.171875, "learning_rate": 2.754884395529392e-05, "loss": 0.4095, "step": 5264 }, { "epoch": 1.347648, "grad_norm": 1.9453125, "learning_rate": 2.7544578107669994e-05, "loss": 0.4503, "step": 5265 }, { "epoch": 1.347904, "grad_norm": 2.09375, "learning_rate": 2.7540312260046075e-05, "loss": 0.4444, "step": 5266 }, { "epoch": 1.34816, "grad_norm": 2.046875, "learning_rate": 2.753604641242215e-05, "loss": 0.4494, "step": 5267 }, { "epoch": 1.348416, "grad_norm": 2.203125, "learning_rate": 2.7531780564798227e-05, "loss": 0.4738, "step": 5268 }, { "epoch": 1.348672, "grad_norm": 2.015625, "learning_rate": 2.75275147171743e-05, "loss": 0.4637, "step": 5269 }, { "epoch": 1.348928, "grad_norm": 2.078125, "learning_rate": 2.7523248869550382e-05, "loss": 0.4409, "step": 5270 }, { "epoch": 1.349184, "grad_norm": 2.390625, "learning_rate": 2.751898302192646e-05, "loss": 0.4777, "step": 5271 }, { "epoch": 1.34944, "grad_norm": 2.21875, "learning_rate": 2.7514717174302534e-05, "loss": 0.4425, "step": 5272 }, { "epoch": 1.349696, "grad_norm": 2.015625, "learning_rate": 2.751045132667861e-05, "loss": 0.4079, "step": 5273 }, { "epoch": 1.349952, "grad_norm": 2.203125, "learning_rate": 2.7506185479054693e-05, "loss": 0.4306, "step": 5274 }, { "epoch": 1.350208, "grad_norm": 2.078125, "learning_rate": 2.7501919631430767e-05, "loss": 0.4653, "step": 5275 }, { "epoch": 1.350464, "grad_norm": 2.109375, "learning_rate": 2.749765378380684e-05, "loss": 0.449, "step": 5276 }, { "epoch": 1.35072, "grad_norm": 2.171875, "learning_rate": 2.749338793618292e-05, "loss": 0.459, "step": 5277 }, { "epoch": 1.350976, "grad_norm": 2.140625, "learning_rate": 2.7489122088559e-05, "loss": 0.4652, "step": 5278 }, { "epoch": 1.351232, "grad_norm": 2.109375, "learning_rate": 2.7484856240935074e-05, "loss": 0.4359, "step": 5279 }, { "epoch": 1.351488, "grad_norm": 2.046875, "learning_rate": 2.7480590393311152e-05, "loss": 0.4278, "step": 5280 }, { "epoch": 1.351744, "grad_norm": 2.171875, "learning_rate": 2.7476324545687233e-05, "loss": 0.4087, "step": 5281 }, { "epoch": 1.3519999999999999, "grad_norm": 2.125, "learning_rate": 2.7472058698063307e-05, "loss": 0.4365, "step": 5282 }, { "epoch": 1.3522560000000001, "grad_norm": 2.078125, "learning_rate": 2.7467792850439385e-05, "loss": 0.4378, "step": 5283 }, { "epoch": 1.352512, "grad_norm": 2.28125, "learning_rate": 2.746352700281546e-05, "loss": 0.441, "step": 5284 }, { "epoch": 1.352768, "grad_norm": 2.15625, "learning_rate": 2.745926115519154e-05, "loss": 0.4115, "step": 5285 }, { "epoch": 1.353024, "grad_norm": 2.21875, "learning_rate": 2.7454995307567614e-05, "loss": 0.4606, "step": 5286 }, { "epoch": 1.35328, "grad_norm": 2.171875, "learning_rate": 2.7450729459943692e-05, "loss": 0.4544, "step": 5287 }, { "epoch": 1.353536, "grad_norm": 2.125, "learning_rate": 2.7446463612319766e-05, "loss": 0.4292, "step": 5288 }, { "epoch": 1.3537919999999999, "grad_norm": 1.9609375, "learning_rate": 2.7442197764695847e-05, "loss": 0.4583, "step": 5289 }, { "epoch": 1.354048, "grad_norm": 2.09375, "learning_rate": 2.7437931917071925e-05, "loss": 0.4295, "step": 5290 }, { "epoch": 1.354304, "grad_norm": 1.9375, "learning_rate": 2.7433666069448e-05, "loss": 0.4804, "step": 5291 }, { "epoch": 1.35456, "grad_norm": 2.125, "learning_rate": 2.7429400221824077e-05, "loss": 0.4165, "step": 5292 }, { "epoch": 1.354816, "grad_norm": 2.21875, "learning_rate": 2.7425134374200158e-05, "loss": 0.4545, "step": 5293 }, { "epoch": 1.355072, "grad_norm": 2.203125, "learning_rate": 2.7420868526576232e-05, "loss": 0.395, "step": 5294 }, { "epoch": 1.355328, "grad_norm": 1.96875, "learning_rate": 2.7416602678952306e-05, "loss": 0.4624, "step": 5295 }, { "epoch": 1.355584, "grad_norm": 2.09375, "learning_rate": 2.7412336831328387e-05, "loss": 0.4151, "step": 5296 }, { "epoch": 1.35584, "grad_norm": 2.109375, "learning_rate": 2.7408070983704465e-05, "loss": 0.4596, "step": 5297 }, { "epoch": 1.356096, "grad_norm": 2.0625, "learning_rate": 2.740380513608054e-05, "loss": 0.4672, "step": 5298 }, { "epoch": 1.356352, "grad_norm": 2.03125, "learning_rate": 2.7399539288456617e-05, "loss": 0.4549, "step": 5299 }, { "epoch": 1.356608, "grad_norm": 2.25, "learning_rate": 2.7395273440832698e-05, "loss": 0.4895, "step": 5300 }, { "epoch": 1.356864, "grad_norm": 2.078125, "learning_rate": 2.7391007593208772e-05, "loss": 0.4482, "step": 5301 }, { "epoch": 1.35712, "grad_norm": 2.265625, "learning_rate": 2.738674174558485e-05, "loss": 0.4146, "step": 5302 }, { "epoch": 1.357376, "grad_norm": 2.0, "learning_rate": 2.7382475897960924e-05, "loss": 0.4572, "step": 5303 }, { "epoch": 1.357632, "grad_norm": 1.859375, "learning_rate": 2.7378210050337005e-05, "loss": 0.4315, "step": 5304 }, { "epoch": 1.357888, "grad_norm": 1.9765625, "learning_rate": 2.737394420271308e-05, "loss": 0.4206, "step": 5305 }, { "epoch": 1.358144, "grad_norm": 2.125, "learning_rate": 2.7369678355089157e-05, "loss": 0.4506, "step": 5306 }, { "epoch": 1.3584, "grad_norm": 1.9609375, "learning_rate": 2.736541250746523e-05, "loss": 0.4299, "step": 5307 }, { "epoch": 1.3586559999999999, "grad_norm": 1.9765625, "learning_rate": 2.7361146659841313e-05, "loss": 0.4643, "step": 5308 }, { "epoch": 1.3589120000000001, "grad_norm": 2.046875, "learning_rate": 2.735688081221739e-05, "loss": 0.4443, "step": 5309 }, { "epoch": 1.359168, "grad_norm": 2.171875, "learning_rate": 2.7352614964593464e-05, "loss": 0.4631, "step": 5310 }, { "epoch": 1.359424, "grad_norm": 2.171875, "learning_rate": 2.7348349116969542e-05, "loss": 0.4736, "step": 5311 }, { "epoch": 1.35968, "grad_norm": 1.9765625, "learning_rate": 2.7344083269345623e-05, "loss": 0.4888, "step": 5312 }, { "epoch": 1.359936, "grad_norm": 1.9921875, "learning_rate": 2.7339817421721697e-05, "loss": 0.4551, "step": 5313 }, { "epoch": 1.360192, "grad_norm": 2.0625, "learning_rate": 2.733555157409777e-05, "loss": 0.4911, "step": 5314 }, { "epoch": 1.3604479999999999, "grad_norm": 2.125, "learning_rate": 2.7331285726473853e-05, "loss": 0.4197, "step": 5315 }, { "epoch": 1.3607040000000001, "grad_norm": 1.8828125, "learning_rate": 2.732701987884993e-05, "loss": 0.4587, "step": 5316 }, { "epoch": 1.36096, "grad_norm": 1.953125, "learning_rate": 2.7322754031226005e-05, "loss": 0.4478, "step": 5317 }, { "epoch": 1.361216, "grad_norm": 2.046875, "learning_rate": 2.7318488183602082e-05, "loss": 0.4618, "step": 5318 }, { "epoch": 1.361472, "grad_norm": 2.25, "learning_rate": 2.7314222335978163e-05, "loss": 0.4653, "step": 5319 }, { "epoch": 1.361728, "grad_norm": 2.140625, "learning_rate": 2.7309956488354238e-05, "loss": 0.4704, "step": 5320 }, { "epoch": 1.361984, "grad_norm": 2.0625, "learning_rate": 2.7305690640730315e-05, "loss": 0.447, "step": 5321 }, { "epoch": 1.36224, "grad_norm": 2.09375, "learning_rate": 2.730142479310639e-05, "loss": 0.4926, "step": 5322 }, { "epoch": 1.362496, "grad_norm": 2.21875, "learning_rate": 2.729715894548247e-05, "loss": 0.4518, "step": 5323 }, { "epoch": 1.362752, "grad_norm": 2.0625, "learning_rate": 2.7292893097858545e-05, "loss": 0.4767, "step": 5324 }, { "epoch": 1.363008, "grad_norm": 2.078125, "learning_rate": 2.7288627250234622e-05, "loss": 0.44, "step": 5325 }, { "epoch": 1.363264, "grad_norm": 2.15625, "learning_rate": 2.7284361402610697e-05, "loss": 0.4277, "step": 5326 }, { "epoch": 1.36352, "grad_norm": 2.28125, "learning_rate": 2.7280095554986778e-05, "loss": 0.4562, "step": 5327 }, { "epoch": 1.363776, "grad_norm": 2.0, "learning_rate": 2.7275829707362855e-05, "loss": 0.4756, "step": 5328 }, { "epoch": 1.364032, "grad_norm": 2.140625, "learning_rate": 2.727156385973893e-05, "loss": 0.4118, "step": 5329 }, { "epoch": 1.364288, "grad_norm": 2.265625, "learning_rate": 2.726729801211501e-05, "loss": 0.4653, "step": 5330 }, { "epoch": 1.364544, "grad_norm": 2.453125, "learning_rate": 2.726303216449109e-05, "loss": 0.435, "step": 5331 }, { "epoch": 1.3648, "grad_norm": 2.109375, "learning_rate": 2.7258766316867163e-05, "loss": 0.4067, "step": 5332 }, { "epoch": 1.365056, "grad_norm": 2.03125, "learning_rate": 2.7254500469243237e-05, "loss": 0.4532, "step": 5333 }, { "epoch": 1.365312, "grad_norm": 2.0625, "learning_rate": 2.7250234621619318e-05, "loss": 0.485, "step": 5334 }, { "epoch": 1.3655680000000001, "grad_norm": 2.015625, "learning_rate": 2.7245968773995396e-05, "loss": 0.4577, "step": 5335 }, { "epoch": 1.365824, "grad_norm": 2.15625, "learning_rate": 2.724170292637147e-05, "loss": 0.4532, "step": 5336 }, { "epoch": 1.36608, "grad_norm": 1.9375, "learning_rate": 2.7237437078747548e-05, "loss": 0.4575, "step": 5337 }, { "epoch": 1.366336, "grad_norm": 2.046875, "learning_rate": 2.723317123112363e-05, "loss": 0.4475, "step": 5338 }, { "epoch": 1.366592, "grad_norm": 2.03125, "learning_rate": 2.7228905383499703e-05, "loss": 0.4569, "step": 5339 }, { "epoch": 1.366848, "grad_norm": 1.953125, "learning_rate": 2.722463953587578e-05, "loss": 0.4818, "step": 5340 }, { "epoch": 1.3671039999999999, "grad_norm": 2.171875, "learning_rate": 2.7220373688251855e-05, "loss": 0.4349, "step": 5341 }, { "epoch": 1.3673600000000001, "grad_norm": 2.21875, "learning_rate": 2.7216107840627936e-05, "loss": 0.422, "step": 5342 }, { "epoch": 1.367616, "grad_norm": 1.8671875, "learning_rate": 2.721184199300401e-05, "loss": 0.4354, "step": 5343 }, { "epoch": 1.367872, "grad_norm": 2.03125, "learning_rate": 2.7207576145380088e-05, "loss": 0.4202, "step": 5344 }, { "epoch": 1.368128, "grad_norm": 2.0, "learning_rate": 2.7203310297756162e-05, "loss": 0.4598, "step": 5345 }, { "epoch": 1.368384, "grad_norm": 2.109375, "learning_rate": 2.7199044450132243e-05, "loss": 0.4654, "step": 5346 }, { "epoch": 1.36864, "grad_norm": 2.234375, "learning_rate": 2.719477860250832e-05, "loss": 0.4341, "step": 5347 }, { "epoch": 1.368896, "grad_norm": 2.1875, "learning_rate": 2.7190512754884395e-05, "loss": 0.4653, "step": 5348 }, { "epoch": 1.369152, "grad_norm": 2.0625, "learning_rate": 2.7186246907260476e-05, "loss": 0.4531, "step": 5349 }, { "epoch": 1.369408, "grad_norm": 2.046875, "learning_rate": 2.7181981059636554e-05, "loss": 0.4343, "step": 5350 }, { "epoch": 1.369664, "grad_norm": 2.0, "learning_rate": 2.7177715212012628e-05, "loss": 0.442, "step": 5351 }, { "epoch": 1.36992, "grad_norm": 2.296875, "learning_rate": 2.7173449364388702e-05, "loss": 0.4482, "step": 5352 }, { "epoch": 1.370176, "grad_norm": 2.125, "learning_rate": 2.7169183516764783e-05, "loss": 0.4674, "step": 5353 }, { "epoch": 1.370432, "grad_norm": 2.171875, "learning_rate": 2.716491766914086e-05, "loss": 0.4276, "step": 5354 }, { "epoch": 1.370688, "grad_norm": 2.015625, "learning_rate": 2.7160651821516935e-05, "loss": 0.4453, "step": 5355 }, { "epoch": 1.370944, "grad_norm": 2.234375, "learning_rate": 2.7156385973893013e-05, "loss": 0.4456, "step": 5356 }, { "epoch": 1.3712, "grad_norm": 2.015625, "learning_rate": 2.7152120126269094e-05, "loss": 0.4379, "step": 5357 }, { "epoch": 1.371456, "grad_norm": 2.0625, "learning_rate": 2.7147854278645168e-05, "loss": 0.4619, "step": 5358 }, { "epoch": 1.371712, "grad_norm": 2.15625, "learning_rate": 2.7143588431021242e-05, "loss": 0.4425, "step": 5359 }, { "epoch": 1.371968, "grad_norm": 2.171875, "learning_rate": 2.713932258339732e-05, "loss": 0.4284, "step": 5360 }, { "epoch": 1.372224, "grad_norm": 2.109375, "learning_rate": 2.71350567357734e-05, "loss": 0.4465, "step": 5361 }, { "epoch": 1.37248, "grad_norm": 2.1875, "learning_rate": 2.7130790888149475e-05, "loss": 0.4346, "step": 5362 }, { "epoch": 1.372736, "grad_norm": 1.921875, "learning_rate": 2.7126525040525553e-05, "loss": 0.4385, "step": 5363 }, { "epoch": 1.372992, "grad_norm": 2.171875, "learning_rate": 2.7122259192901634e-05, "loss": 0.4818, "step": 5364 }, { "epoch": 1.373248, "grad_norm": 2.203125, "learning_rate": 2.711799334527771e-05, "loss": 0.4627, "step": 5365 }, { "epoch": 1.373504, "grad_norm": 2.328125, "learning_rate": 2.7113727497653786e-05, "loss": 0.4116, "step": 5366 }, { "epoch": 1.3737599999999999, "grad_norm": 2.0625, "learning_rate": 2.710946165002986e-05, "loss": 0.3728, "step": 5367 }, { "epoch": 1.3740160000000001, "grad_norm": 2.109375, "learning_rate": 2.710519580240594e-05, "loss": 0.481, "step": 5368 }, { "epoch": 1.374272, "grad_norm": 2.3125, "learning_rate": 2.7100929954782016e-05, "loss": 0.461, "step": 5369 }, { "epoch": 1.374528, "grad_norm": 2.296875, "learning_rate": 2.7096664107158093e-05, "loss": 0.4336, "step": 5370 }, { "epoch": 1.374784, "grad_norm": 2.0625, "learning_rate": 2.7092398259534167e-05, "loss": 0.4652, "step": 5371 }, { "epoch": 1.37504, "grad_norm": 1.921875, "learning_rate": 2.708813241191025e-05, "loss": 0.4671, "step": 5372 }, { "epoch": 1.375296, "grad_norm": 2.15625, "learning_rate": 2.7083866564286326e-05, "loss": 0.4524, "step": 5373 }, { "epoch": 1.3755519999999999, "grad_norm": 2.078125, "learning_rate": 2.70796007166624e-05, "loss": 0.429, "step": 5374 }, { "epoch": 1.375808, "grad_norm": 2.125, "learning_rate": 2.7075334869038478e-05, "loss": 0.472, "step": 5375 }, { "epoch": 1.376064, "grad_norm": 2.234375, "learning_rate": 2.707106902141456e-05, "loss": 0.4415, "step": 5376 }, { "epoch": 1.37632, "grad_norm": 2.21875, "learning_rate": 2.7066803173790633e-05, "loss": 0.4377, "step": 5377 }, { "epoch": 1.376576, "grad_norm": 2.21875, "learning_rate": 2.7062537326166708e-05, "loss": 0.4325, "step": 5378 }, { "epoch": 1.376832, "grad_norm": 2.078125, "learning_rate": 2.7058271478542792e-05, "loss": 0.433, "step": 5379 }, { "epoch": 1.377088, "grad_norm": 2.15625, "learning_rate": 2.7054005630918866e-05, "loss": 0.4228, "step": 5380 }, { "epoch": 1.377344, "grad_norm": 2.078125, "learning_rate": 2.704973978329494e-05, "loss": 0.4442, "step": 5381 }, { "epoch": 1.3776, "grad_norm": 2.125, "learning_rate": 2.704547393567102e-05, "loss": 0.4608, "step": 5382 }, { "epoch": 1.377856, "grad_norm": 2.125, "learning_rate": 2.70412080880471e-05, "loss": 0.4184, "step": 5383 }, { "epoch": 1.378112, "grad_norm": 2.203125, "learning_rate": 2.7036942240423174e-05, "loss": 0.4464, "step": 5384 }, { "epoch": 1.378368, "grad_norm": 2.234375, "learning_rate": 2.703267639279925e-05, "loss": 0.4253, "step": 5385 }, { "epoch": 1.378624, "grad_norm": 2.125, "learning_rate": 2.7028410545175326e-05, "loss": 0.46, "step": 5386 }, { "epoch": 1.37888, "grad_norm": 2.140625, "learning_rate": 2.7024144697551407e-05, "loss": 0.4567, "step": 5387 }, { "epoch": 1.379136, "grad_norm": 2.15625, "learning_rate": 2.701987884992748e-05, "loss": 0.4471, "step": 5388 }, { "epoch": 1.379392, "grad_norm": 2.140625, "learning_rate": 2.701561300230356e-05, "loss": 0.4439, "step": 5389 }, { "epoch": 1.379648, "grad_norm": 2.09375, "learning_rate": 2.7011347154679633e-05, "loss": 0.4275, "step": 5390 }, { "epoch": 1.379904, "grad_norm": 1.96875, "learning_rate": 2.7007081307055714e-05, "loss": 0.4204, "step": 5391 }, { "epoch": 1.38016, "grad_norm": 2.140625, "learning_rate": 2.700281545943179e-05, "loss": 0.4693, "step": 5392 }, { "epoch": 1.3804159999999999, "grad_norm": 2.046875, "learning_rate": 2.6998549611807866e-05, "loss": 0.4318, "step": 5393 }, { "epoch": 1.3806720000000001, "grad_norm": 2.046875, "learning_rate": 2.6994283764183943e-05, "loss": 0.4547, "step": 5394 }, { "epoch": 1.380928, "grad_norm": 2.171875, "learning_rate": 2.6990017916560024e-05, "loss": 0.4585, "step": 5395 }, { "epoch": 1.381184, "grad_norm": 2.234375, "learning_rate": 2.69857520689361e-05, "loss": 0.4909, "step": 5396 }, { "epoch": 1.38144, "grad_norm": 2.140625, "learning_rate": 2.6981486221312173e-05, "loss": 0.4369, "step": 5397 }, { "epoch": 1.381696, "grad_norm": 2.0625, "learning_rate": 2.6977220373688254e-05, "loss": 0.4621, "step": 5398 }, { "epoch": 1.381952, "grad_norm": 1.890625, "learning_rate": 2.697295452606433e-05, "loss": 0.4461, "step": 5399 }, { "epoch": 1.3822079999999999, "grad_norm": 1.9140625, "learning_rate": 2.6968688678440406e-05, "loss": 0.4775, "step": 5400 }, { "epoch": 1.3824640000000001, "grad_norm": 2.34375, "learning_rate": 2.6964422830816484e-05, "loss": 0.4533, "step": 5401 }, { "epoch": 1.38272, "grad_norm": 2.0, "learning_rate": 2.6960156983192565e-05, "loss": 0.4286, "step": 5402 }, { "epoch": 1.382976, "grad_norm": 2.140625, "learning_rate": 2.695589113556864e-05, "loss": 0.4343, "step": 5403 }, { "epoch": 1.383232, "grad_norm": 2.296875, "learning_rate": 2.6951625287944717e-05, "loss": 0.4696, "step": 5404 }, { "epoch": 1.383488, "grad_norm": 2.015625, "learning_rate": 2.694735944032079e-05, "loss": 0.4682, "step": 5405 }, { "epoch": 1.383744, "grad_norm": 2.15625, "learning_rate": 2.6943093592696872e-05, "loss": 0.4674, "step": 5406 }, { "epoch": 1.384, "grad_norm": 2.421875, "learning_rate": 2.6938827745072946e-05, "loss": 0.4178, "step": 5407 }, { "epoch": 1.384256, "grad_norm": 2.296875, "learning_rate": 2.6934561897449024e-05, "loss": 0.4176, "step": 5408 }, { "epoch": 1.384512, "grad_norm": 2.140625, "learning_rate": 2.6930296049825098e-05, "loss": 0.4472, "step": 5409 }, { "epoch": 1.384768, "grad_norm": 2.203125, "learning_rate": 2.692603020220118e-05, "loss": 0.4576, "step": 5410 }, { "epoch": 1.385024, "grad_norm": 1.96875, "learning_rate": 2.6921764354577257e-05, "loss": 0.4332, "step": 5411 }, { "epoch": 1.38528, "grad_norm": 2.140625, "learning_rate": 2.691749850695333e-05, "loss": 0.4361, "step": 5412 }, { "epoch": 1.385536, "grad_norm": 1.8515625, "learning_rate": 2.6913232659329412e-05, "loss": 0.4202, "step": 5413 }, { "epoch": 1.385792, "grad_norm": 2.015625, "learning_rate": 2.690896681170549e-05, "loss": 0.4358, "step": 5414 }, { "epoch": 1.386048, "grad_norm": 2.125, "learning_rate": 2.6904700964081564e-05, "loss": 0.4449, "step": 5415 }, { "epoch": 1.386304, "grad_norm": 2.0625, "learning_rate": 2.6900435116457638e-05, "loss": 0.4487, "step": 5416 }, { "epoch": 1.38656, "grad_norm": 1.953125, "learning_rate": 2.689616926883372e-05, "loss": 0.4836, "step": 5417 }, { "epoch": 1.386816, "grad_norm": 1.9921875, "learning_rate": 2.6891903421209797e-05, "loss": 0.4828, "step": 5418 }, { "epoch": 1.387072, "grad_norm": 2.109375, "learning_rate": 2.688763757358587e-05, "loss": 0.4734, "step": 5419 }, { "epoch": 1.3873280000000001, "grad_norm": 2.3125, "learning_rate": 2.688337172596195e-05, "loss": 0.4332, "step": 5420 }, { "epoch": 1.387584, "grad_norm": 2.09375, "learning_rate": 2.687910587833803e-05, "loss": 0.4012, "step": 5421 }, { "epoch": 1.38784, "grad_norm": 2.03125, "learning_rate": 2.6874840030714104e-05, "loss": 0.4491, "step": 5422 }, { "epoch": 1.388096, "grad_norm": 1.859375, "learning_rate": 2.6870574183090182e-05, "loss": 0.4858, "step": 5423 }, { "epoch": 1.388352, "grad_norm": 2.03125, "learning_rate": 2.6866308335466256e-05, "loss": 0.5194, "step": 5424 }, { "epoch": 1.388608, "grad_norm": 1.859375, "learning_rate": 2.6862042487842337e-05, "loss": 0.4767, "step": 5425 }, { "epoch": 1.3888639999999999, "grad_norm": 2.234375, "learning_rate": 2.685777664021841e-05, "loss": 0.4669, "step": 5426 }, { "epoch": 1.3891200000000001, "grad_norm": 1.9765625, "learning_rate": 2.685351079259449e-05, "loss": 0.429, "step": 5427 }, { "epoch": 1.389376, "grad_norm": 1.7734375, "learning_rate": 2.684924494497057e-05, "loss": 0.4518, "step": 5428 }, { "epoch": 1.389632, "grad_norm": 2.109375, "learning_rate": 2.6844979097346644e-05, "loss": 0.399, "step": 5429 }, { "epoch": 1.389888, "grad_norm": 2.125, "learning_rate": 2.6840713249722722e-05, "loss": 0.4592, "step": 5430 }, { "epoch": 1.390144, "grad_norm": 2.046875, "learning_rate": 2.6836447402098796e-05, "loss": 0.4162, "step": 5431 }, { "epoch": 1.3904, "grad_norm": 2.109375, "learning_rate": 2.6832181554474877e-05, "loss": 0.4518, "step": 5432 }, { "epoch": 1.390656, "grad_norm": 2.1875, "learning_rate": 2.6827915706850955e-05, "loss": 0.4714, "step": 5433 }, { "epoch": 1.390912, "grad_norm": 2.09375, "learning_rate": 2.682364985922703e-05, "loss": 0.4438, "step": 5434 }, { "epoch": 1.391168, "grad_norm": 2.09375, "learning_rate": 2.6819384011603104e-05, "loss": 0.4223, "step": 5435 }, { "epoch": 1.391424, "grad_norm": 2.078125, "learning_rate": 2.6815118163979185e-05, "loss": 0.4469, "step": 5436 }, { "epoch": 1.39168, "grad_norm": 2.078125, "learning_rate": 2.6810852316355262e-05, "loss": 0.4453, "step": 5437 }, { "epoch": 1.391936, "grad_norm": 2.03125, "learning_rate": 2.6806586468731336e-05, "loss": 0.4419, "step": 5438 }, { "epoch": 1.392192, "grad_norm": 1.953125, "learning_rate": 2.6802320621107414e-05, "loss": 0.4747, "step": 5439 }, { "epoch": 1.392448, "grad_norm": 2.28125, "learning_rate": 2.6798054773483495e-05, "loss": 0.4571, "step": 5440 }, { "epoch": 1.392704, "grad_norm": 1.96875, "learning_rate": 2.679378892585957e-05, "loss": 0.4501, "step": 5441 }, { "epoch": 1.39296, "grad_norm": 2.34375, "learning_rate": 2.6789523078235647e-05, "loss": 0.4417, "step": 5442 }, { "epoch": 1.393216, "grad_norm": 1.84375, "learning_rate": 2.678525723061172e-05, "loss": 0.4226, "step": 5443 }, { "epoch": 1.393472, "grad_norm": 2.09375, "learning_rate": 2.6780991382987802e-05, "loss": 0.4061, "step": 5444 }, { "epoch": 1.393728, "grad_norm": 1.953125, "learning_rate": 2.6776725535363877e-05, "loss": 0.4534, "step": 5445 }, { "epoch": 1.3939840000000001, "grad_norm": 2.09375, "learning_rate": 2.6772459687739954e-05, "loss": 0.4584, "step": 5446 }, { "epoch": 1.39424, "grad_norm": 2.046875, "learning_rate": 2.6768193840116035e-05, "loss": 0.4965, "step": 5447 }, { "epoch": 1.394496, "grad_norm": 2.09375, "learning_rate": 2.676392799249211e-05, "loss": 0.4465, "step": 5448 }, { "epoch": 1.394752, "grad_norm": 2.265625, "learning_rate": 2.6759662144868187e-05, "loss": 0.443, "step": 5449 }, { "epoch": 1.395008, "grad_norm": 2.078125, "learning_rate": 2.675539629724426e-05, "loss": 0.4644, "step": 5450 }, { "epoch": 1.395264, "grad_norm": 2.0625, "learning_rate": 2.6751130449620343e-05, "loss": 0.4626, "step": 5451 }, { "epoch": 1.3955199999999999, "grad_norm": 2.140625, "learning_rate": 2.674686460199642e-05, "loss": 0.4089, "step": 5452 }, { "epoch": 1.3957760000000001, "grad_norm": 2.0625, "learning_rate": 2.6742598754372495e-05, "loss": 0.4596, "step": 5453 }, { "epoch": 1.396032, "grad_norm": 2.15625, "learning_rate": 2.673833290674857e-05, "loss": 0.4204, "step": 5454 }, { "epoch": 1.396288, "grad_norm": 2.03125, "learning_rate": 2.673406705912465e-05, "loss": 0.4746, "step": 5455 }, { "epoch": 1.396544, "grad_norm": 2.203125, "learning_rate": 2.6729801211500727e-05, "loss": 0.4979, "step": 5456 }, { "epoch": 1.3968, "grad_norm": 2.140625, "learning_rate": 2.6725535363876802e-05, "loss": 0.4274, "step": 5457 }, { "epoch": 1.397056, "grad_norm": 2.171875, "learning_rate": 2.672126951625288e-05, "loss": 0.4567, "step": 5458 }, { "epoch": 1.3973119999999999, "grad_norm": 2.1875, "learning_rate": 2.671700366862896e-05, "loss": 0.4693, "step": 5459 }, { "epoch": 1.397568, "grad_norm": 2.109375, "learning_rate": 2.6712737821005035e-05, "loss": 0.4546, "step": 5460 }, { "epoch": 1.397824, "grad_norm": 2.03125, "learning_rate": 2.670847197338111e-05, "loss": 0.4326, "step": 5461 }, { "epoch": 1.39808, "grad_norm": 2.09375, "learning_rate": 2.6704206125757193e-05, "loss": 0.4598, "step": 5462 }, { "epoch": 1.398336, "grad_norm": 2.0625, "learning_rate": 2.6699940278133268e-05, "loss": 0.4455, "step": 5463 }, { "epoch": 1.398592, "grad_norm": 2.015625, "learning_rate": 2.6695674430509342e-05, "loss": 0.465, "step": 5464 }, { "epoch": 1.398848, "grad_norm": 1.9765625, "learning_rate": 2.669140858288542e-05, "loss": 0.4385, "step": 5465 }, { "epoch": 1.399104, "grad_norm": 1.9765625, "learning_rate": 2.66871427352615e-05, "loss": 0.4088, "step": 5466 }, { "epoch": 1.39936, "grad_norm": 2.046875, "learning_rate": 2.6682876887637575e-05, "loss": 0.4256, "step": 5467 }, { "epoch": 1.399616, "grad_norm": 2.09375, "learning_rate": 2.6678611040013653e-05, "loss": 0.4342, "step": 5468 }, { "epoch": 1.399872, "grad_norm": 2.0, "learning_rate": 2.6674345192389727e-05, "loss": 0.4723, "step": 5469 }, { "epoch": 1.400128, "grad_norm": 2.0, "learning_rate": 2.6670079344765808e-05, "loss": 0.4633, "step": 5470 }, { "epoch": 1.400384, "grad_norm": 2.109375, "learning_rate": 2.6665813497141886e-05, "loss": 0.4767, "step": 5471 }, { "epoch": 1.40064, "grad_norm": 2.015625, "learning_rate": 2.666154764951796e-05, "loss": 0.457, "step": 5472 }, { "epoch": 1.400896, "grad_norm": 2.109375, "learning_rate": 2.6657281801894034e-05, "loss": 0.4564, "step": 5473 }, { "epoch": 1.401152, "grad_norm": 1.953125, "learning_rate": 2.6653015954270115e-05, "loss": 0.4175, "step": 5474 }, { "epoch": 1.401408, "grad_norm": 2.078125, "learning_rate": 2.6648750106646193e-05, "loss": 0.4572, "step": 5475 }, { "epoch": 1.401664, "grad_norm": 2.0, "learning_rate": 2.6644484259022267e-05, "loss": 0.4492, "step": 5476 }, { "epoch": 1.40192, "grad_norm": 2.234375, "learning_rate": 2.6640218411398348e-05, "loss": 0.4342, "step": 5477 }, { "epoch": 1.4021759999999999, "grad_norm": 2.21875, "learning_rate": 2.6635952563774426e-05, "loss": 0.4639, "step": 5478 }, { "epoch": 1.4024320000000001, "grad_norm": 2.015625, "learning_rate": 2.66316867161505e-05, "loss": 0.4401, "step": 5479 }, { "epoch": 1.402688, "grad_norm": 2.15625, "learning_rate": 2.6627420868526574e-05, "loss": 0.4718, "step": 5480 }, { "epoch": 1.402944, "grad_norm": 2.078125, "learning_rate": 2.662315502090266e-05, "loss": 0.4585, "step": 5481 }, { "epoch": 1.4032, "grad_norm": 2.234375, "learning_rate": 2.6618889173278733e-05, "loss": 0.4339, "step": 5482 }, { "epoch": 1.403456, "grad_norm": 2.265625, "learning_rate": 2.6614623325654807e-05, "loss": 0.4285, "step": 5483 }, { "epoch": 1.403712, "grad_norm": 2.09375, "learning_rate": 2.6610357478030885e-05, "loss": 0.4812, "step": 5484 }, { "epoch": 1.4039679999999999, "grad_norm": 1.8671875, "learning_rate": 2.6606091630406966e-05, "loss": 0.4597, "step": 5485 }, { "epoch": 1.4042240000000001, "grad_norm": 2.015625, "learning_rate": 2.660182578278304e-05, "loss": 0.413, "step": 5486 }, { "epoch": 1.40448, "grad_norm": 2.296875, "learning_rate": 2.6597559935159118e-05, "loss": 0.473, "step": 5487 }, { "epoch": 1.404736, "grad_norm": 1.953125, "learning_rate": 2.6593294087535192e-05, "loss": 0.4494, "step": 5488 }, { "epoch": 1.404992, "grad_norm": 2.0625, "learning_rate": 2.6589028239911273e-05, "loss": 0.4659, "step": 5489 }, { "epoch": 1.405248, "grad_norm": 2.125, "learning_rate": 2.6584762392287347e-05, "loss": 0.4533, "step": 5490 }, { "epoch": 1.405504, "grad_norm": 2.09375, "learning_rate": 2.6580496544663425e-05, "loss": 0.4459, "step": 5491 }, { "epoch": 1.40576, "grad_norm": 2.125, "learning_rate": 2.65762306970395e-05, "loss": 0.4298, "step": 5492 }, { "epoch": 1.406016, "grad_norm": 2.265625, "learning_rate": 2.657196484941558e-05, "loss": 0.4477, "step": 5493 }, { "epoch": 1.406272, "grad_norm": 2.390625, "learning_rate": 2.6567699001791658e-05, "loss": 0.438, "step": 5494 }, { "epoch": 1.406528, "grad_norm": 2.015625, "learning_rate": 2.6563433154167732e-05, "loss": 0.4377, "step": 5495 }, { "epoch": 1.406784, "grad_norm": 2.171875, "learning_rate": 2.6559167306543813e-05, "loss": 0.4425, "step": 5496 }, { "epoch": 1.40704, "grad_norm": 2.171875, "learning_rate": 2.655490145891989e-05, "loss": 0.447, "step": 5497 }, { "epoch": 1.407296, "grad_norm": 2.234375, "learning_rate": 2.6550635611295965e-05, "loss": 0.4431, "step": 5498 }, { "epoch": 1.407552, "grad_norm": 2.390625, "learning_rate": 2.654636976367204e-05, "loss": 0.491, "step": 5499 }, { "epoch": 1.407808, "grad_norm": 2.296875, "learning_rate": 2.654210391604812e-05, "loss": 0.459, "step": 5500 }, { "epoch": 1.408064, "grad_norm": 2.09375, "learning_rate": 2.6537838068424198e-05, "loss": 0.4268, "step": 5501 }, { "epoch": 1.40832, "grad_norm": 2.0, "learning_rate": 2.6533572220800272e-05, "loss": 0.4573, "step": 5502 }, { "epoch": 1.408576, "grad_norm": 1.9609375, "learning_rate": 2.652930637317635e-05, "loss": 0.4467, "step": 5503 }, { "epoch": 1.4088319999999999, "grad_norm": 2.03125, "learning_rate": 2.652504052555243e-05, "loss": 0.4421, "step": 5504 }, { "epoch": 1.4090880000000001, "grad_norm": 2.046875, "learning_rate": 2.6520774677928505e-05, "loss": 0.4655, "step": 5505 }, { "epoch": 1.409344, "grad_norm": 1.984375, "learning_rate": 2.6516508830304583e-05, "loss": 0.4451, "step": 5506 }, { "epoch": 1.4096, "grad_norm": 1.90625, "learning_rate": 2.6512242982680657e-05, "loss": 0.4585, "step": 5507 }, { "epoch": 1.409856, "grad_norm": 2.09375, "learning_rate": 2.650797713505674e-05, "loss": 0.4325, "step": 5508 }, { "epoch": 1.410112, "grad_norm": 2.109375, "learning_rate": 2.6503711287432813e-05, "loss": 0.4122, "step": 5509 }, { "epoch": 1.410368, "grad_norm": 2.03125, "learning_rate": 2.649944543980889e-05, "loss": 0.4449, "step": 5510 }, { "epoch": 1.4106239999999999, "grad_norm": 2.171875, "learning_rate": 2.649517959218497e-05, "loss": 0.4564, "step": 5511 }, { "epoch": 1.4108800000000001, "grad_norm": 2.25, "learning_rate": 2.6490913744561046e-05, "loss": 0.4104, "step": 5512 }, { "epoch": 1.411136, "grad_norm": 1.984375, "learning_rate": 2.6486647896937123e-05, "loss": 0.4298, "step": 5513 }, { "epoch": 1.411392, "grad_norm": 2.09375, "learning_rate": 2.6482382049313198e-05, "loss": 0.4365, "step": 5514 }, { "epoch": 1.411648, "grad_norm": 1.8984375, "learning_rate": 2.647811620168928e-05, "loss": 0.4564, "step": 5515 }, { "epoch": 1.411904, "grad_norm": 2.09375, "learning_rate": 2.6473850354065356e-05, "loss": 0.4258, "step": 5516 }, { "epoch": 1.41216, "grad_norm": 2.09375, "learning_rate": 2.646958450644143e-05, "loss": 0.4486, "step": 5517 }, { "epoch": 1.412416, "grad_norm": 2.109375, "learning_rate": 2.6465318658817505e-05, "loss": 0.4473, "step": 5518 }, { "epoch": 1.412672, "grad_norm": 2.234375, "learning_rate": 2.6461052811193586e-05, "loss": 0.456, "step": 5519 }, { "epoch": 1.412928, "grad_norm": 1.953125, "learning_rate": 2.6456786963569663e-05, "loss": 0.436, "step": 5520 }, { "epoch": 1.413184, "grad_norm": 1.9765625, "learning_rate": 2.6452521115945738e-05, "loss": 0.4145, "step": 5521 }, { "epoch": 1.41344, "grad_norm": 2.046875, "learning_rate": 2.6448255268321815e-05, "loss": 0.4752, "step": 5522 }, { "epoch": 1.413696, "grad_norm": 2.234375, "learning_rate": 2.6443989420697896e-05, "loss": 0.4094, "step": 5523 }, { "epoch": 1.413952, "grad_norm": 2.078125, "learning_rate": 2.643972357307397e-05, "loss": 0.4554, "step": 5524 }, { "epoch": 1.414208, "grad_norm": 1.9609375, "learning_rate": 2.643545772545005e-05, "loss": 0.4236, "step": 5525 }, { "epoch": 1.414464, "grad_norm": 2.28125, "learning_rate": 2.643119187782613e-05, "loss": 0.444, "step": 5526 }, { "epoch": 1.41472, "grad_norm": 2.15625, "learning_rate": 2.6426926030202204e-05, "loss": 0.4575, "step": 5527 }, { "epoch": 1.414976, "grad_norm": 2.203125, "learning_rate": 2.6422660182578278e-05, "loss": 0.4442, "step": 5528 }, { "epoch": 1.415232, "grad_norm": 2.015625, "learning_rate": 2.6418394334954356e-05, "loss": 0.3945, "step": 5529 }, { "epoch": 1.415488, "grad_norm": 2.140625, "learning_rate": 2.6414128487330437e-05, "loss": 0.4471, "step": 5530 }, { "epoch": 1.4157440000000001, "grad_norm": 2.171875, "learning_rate": 2.640986263970651e-05, "loss": 0.4327, "step": 5531 }, { "epoch": 1.416, "grad_norm": 2.03125, "learning_rate": 2.640559679208259e-05, "loss": 0.481, "step": 5532 }, { "epoch": 1.416256, "grad_norm": 2.015625, "learning_rate": 2.6401330944458663e-05, "loss": 0.4597, "step": 5533 }, { "epoch": 1.416512, "grad_norm": 1.9453125, "learning_rate": 2.6397065096834744e-05, "loss": 0.4386, "step": 5534 }, { "epoch": 1.416768, "grad_norm": 2.09375, "learning_rate": 2.639279924921082e-05, "loss": 0.4606, "step": 5535 }, { "epoch": 1.417024, "grad_norm": 2.09375, "learning_rate": 2.6388533401586896e-05, "loss": 0.4703, "step": 5536 }, { "epoch": 1.4172799999999999, "grad_norm": 2.0625, "learning_rate": 2.638426755396297e-05, "loss": 0.4397, "step": 5537 }, { "epoch": 1.4175360000000001, "grad_norm": 2.21875, "learning_rate": 2.638000170633905e-05, "loss": 0.4812, "step": 5538 }, { "epoch": 1.417792, "grad_norm": 2.234375, "learning_rate": 2.637573585871513e-05, "loss": 0.474, "step": 5539 }, { "epoch": 1.418048, "grad_norm": 2.140625, "learning_rate": 2.6371470011091203e-05, "loss": 0.4767, "step": 5540 }, { "epoch": 1.418304, "grad_norm": 2.03125, "learning_rate": 2.636720416346728e-05, "loss": 0.4504, "step": 5541 }, { "epoch": 1.41856, "grad_norm": 2.0625, "learning_rate": 2.6362938315843362e-05, "loss": 0.4435, "step": 5542 }, { "epoch": 1.418816, "grad_norm": 1.90625, "learning_rate": 2.6358672468219436e-05, "loss": 0.4286, "step": 5543 }, { "epoch": 1.419072, "grad_norm": 2.0625, "learning_rate": 2.6354406620595514e-05, "loss": 0.4199, "step": 5544 }, { "epoch": 1.419328, "grad_norm": 2.03125, "learning_rate": 2.6350140772971595e-05, "loss": 0.4359, "step": 5545 }, { "epoch": 1.419584, "grad_norm": 2.15625, "learning_rate": 2.634587492534767e-05, "loss": 0.4551, "step": 5546 }, { "epoch": 1.41984, "grad_norm": 2.078125, "learning_rate": 2.6341609077723743e-05, "loss": 0.4723, "step": 5547 }, { "epoch": 1.420096, "grad_norm": 2.0625, "learning_rate": 2.633734323009982e-05, "loss": 0.4789, "step": 5548 }, { "epoch": 1.420352, "grad_norm": 1.9765625, "learning_rate": 2.6333077382475902e-05, "loss": 0.4423, "step": 5549 }, { "epoch": 1.420608, "grad_norm": 2.09375, "learning_rate": 2.6328811534851976e-05, "loss": 0.4637, "step": 5550 }, { "epoch": 1.420864, "grad_norm": 1.96875, "learning_rate": 2.6324545687228054e-05, "loss": 0.4408, "step": 5551 }, { "epoch": 1.42112, "grad_norm": 2.015625, "learning_rate": 2.6320279839604128e-05, "loss": 0.4599, "step": 5552 }, { "epoch": 1.421376, "grad_norm": 1.96875, "learning_rate": 2.631601399198021e-05, "loss": 0.4208, "step": 5553 }, { "epoch": 1.421632, "grad_norm": 2.171875, "learning_rate": 2.6311748144356287e-05, "loss": 0.474, "step": 5554 }, { "epoch": 1.421888, "grad_norm": 1.9921875, "learning_rate": 2.630748229673236e-05, "loss": 0.4586, "step": 5555 }, { "epoch": 1.422144, "grad_norm": 1.9765625, "learning_rate": 2.6303216449108435e-05, "loss": 0.4356, "step": 5556 }, { "epoch": 1.4224, "grad_norm": 2.0625, "learning_rate": 2.6298950601484516e-05, "loss": 0.4477, "step": 5557 }, { "epoch": 1.422656, "grad_norm": 1.859375, "learning_rate": 2.6294684753860594e-05, "loss": 0.4438, "step": 5558 }, { "epoch": 1.422912, "grad_norm": 2.078125, "learning_rate": 2.6290418906236668e-05, "loss": 0.413, "step": 5559 }, { "epoch": 1.423168, "grad_norm": 2.046875, "learning_rate": 2.628615305861275e-05, "loss": 0.5007, "step": 5560 }, { "epoch": 1.423424, "grad_norm": 2.015625, "learning_rate": 2.6281887210988827e-05, "loss": 0.4635, "step": 5561 }, { "epoch": 1.42368, "grad_norm": 2.078125, "learning_rate": 2.62776213633649e-05, "loss": 0.4157, "step": 5562 }, { "epoch": 1.4239359999999999, "grad_norm": 2.15625, "learning_rate": 2.6273355515740976e-05, "loss": 0.4698, "step": 5563 }, { "epoch": 1.4241920000000001, "grad_norm": 2.078125, "learning_rate": 2.626908966811706e-05, "loss": 0.4372, "step": 5564 }, { "epoch": 1.424448, "grad_norm": 1.9375, "learning_rate": 2.6264823820493134e-05, "loss": 0.4178, "step": 5565 }, { "epoch": 1.424704, "grad_norm": 2.046875, "learning_rate": 2.626055797286921e-05, "loss": 0.4651, "step": 5566 }, { "epoch": 1.42496, "grad_norm": 2.265625, "learning_rate": 2.6256292125245286e-05, "loss": 0.4103, "step": 5567 }, { "epoch": 1.425216, "grad_norm": 2.0, "learning_rate": 2.6252026277621367e-05, "loss": 0.4957, "step": 5568 }, { "epoch": 1.425472, "grad_norm": 1.953125, "learning_rate": 2.624776042999744e-05, "loss": 0.4342, "step": 5569 }, { "epoch": 1.4257279999999999, "grad_norm": 2.109375, "learning_rate": 2.624349458237352e-05, "loss": 0.4467, "step": 5570 }, { "epoch": 1.425984, "grad_norm": 2.078125, "learning_rate": 2.6239228734749593e-05, "loss": 0.4851, "step": 5571 }, { "epoch": 1.42624, "grad_norm": 2.0, "learning_rate": 2.6234962887125674e-05, "loss": 0.4484, "step": 5572 }, { "epoch": 1.426496, "grad_norm": 1.9453125, "learning_rate": 2.6230697039501752e-05, "loss": 0.4701, "step": 5573 }, { "epoch": 1.426752, "grad_norm": 2.015625, "learning_rate": 2.6226431191877826e-05, "loss": 0.4468, "step": 5574 }, { "epoch": 1.427008, "grad_norm": 2.09375, "learning_rate": 2.6222165344253907e-05, "loss": 0.4345, "step": 5575 }, { "epoch": 1.427264, "grad_norm": 2.15625, "learning_rate": 2.621789949662998e-05, "loss": 0.444, "step": 5576 }, { "epoch": 1.42752, "grad_norm": 2.375, "learning_rate": 2.621363364900606e-05, "loss": 0.4637, "step": 5577 }, { "epoch": 1.427776, "grad_norm": 2.125, "learning_rate": 2.6209367801382134e-05, "loss": 0.4256, "step": 5578 }, { "epoch": 1.428032, "grad_norm": 2.015625, "learning_rate": 2.6205101953758215e-05, "loss": 0.4548, "step": 5579 }, { "epoch": 1.428288, "grad_norm": 2.234375, "learning_rate": 2.6200836106134292e-05, "loss": 0.4669, "step": 5580 }, { "epoch": 1.428544, "grad_norm": 2.34375, "learning_rate": 2.6196570258510367e-05, "loss": 0.4552, "step": 5581 }, { "epoch": 1.4288, "grad_norm": 2.390625, "learning_rate": 2.619230441088644e-05, "loss": 0.467, "step": 5582 }, { "epoch": 1.429056, "grad_norm": 2.09375, "learning_rate": 2.6188038563262525e-05, "loss": 0.4753, "step": 5583 }, { "epoch": 1.429312, "grad_norm": 1.9453125, "learning_rate": 2.61837727156386e-05, "loss": 0.4433, "step": 5584 }, { "epoch": 1.429568, "grad_norm": 2.109375, "learning_rate": 2.6179506868014674e-05, "loss": 0.4685, "step": 5585 }, { "epoch": 1.429824, "grad_norm": 2.140625, "learning_rate": 2.617524102039075e-05, "loss": 0.4669, "step": 5586 }, { "epoch": 1.43008, "grad_norm": 2.0, "learning_rate": 2.6170975172766832e-05, "loss": 0.4276, "step": 5587 }, { "epoch": 1.430336, "grad_norm": 2.203125, "learning_rate": 2.6166709325142907e-05, "loss": 0.4482, "step": 5588 }, { "epoch": 1.4305919999999999, "grad_norm": 2.140625, "learning_rate": 2.6162443477518984e-05, "loss": 0.4622, "step": 5589 }, { "epoch": 1.4308480000000001, "grad_norm": 2.046875, "learning_rate": 2.615817762989506e-05, "loss": 0.4133, "step": 5590 }, { "epoch": 1.431104, "grad_norm": 1.9921875, "learning_rate": 2.615391178227114e-05, "loss": 0.4014, "step": 5591 }, { "epoch": 1.43136, "grad_norm": 2.03125, "learning_rate": 2.6149645934647214e-05, "loss": 0.3998, "step": 5592 }, { "epoch": 1.431616, "grad_norm": 1.96875, "learning_rate": 2.614538008702329e-05, "loss": 0.4539, "step": 5593 }, { "epoch": 1.431872, "grad_norm": 1.984375, "learning_rate": 2.6141114239399373e-05, "loss": 0.4563, "step": 5594 }, { "epoch": 1.432128, "grad_norm": 2.09375, "learning_rate": 2.6136848391775447e-05, "loss": 0.4757, "step": 5595 }, { "epoch": 1.4323839999999999, "grad_norm": 2.21875, "learning_rate": 2.6132582544151525e-05, "loss": 0.4499, "step": 5596 }, { "epoch": 1.4326400000000001, "grad_norm": 2.0625, "learning_rate": 2.61283166965276e-05, "loss": 0.4235, "step": 5597 }, { "epoch": 1.432896, "grad_norm": 2.09375, "learning_rate": 2.612405084890368e-05, "loss": 0.4557, "step": 5598 }, { "epoch": 1.433152, "grad_norm": 1.890625, "learning_rate": 2.6119785001279758e-05, "loss": 0.4326, "step": 5599 }, { "epoch": 1.433408, "grad_norm": 1.9921875, "learning_rate": 2.6115519153655832e-05, "loss": 0.4362, "step": 5600 }, { "epoch": 1.433664, "grad_norm": 2.125, "learning_rate": 2.6111253306031906e-05, "loss": 0.4329, "step": 5601 }, { "epoch": 1.43392, "grad_norm": 2.078125, "learning_rate": 2.6106987458407987e-05, "loss": 0.4396, "step": 5602 }, { "epoch": 1.434176, "grad_norm": 2.25, "learning_rate": 2.6102721610784065e-05, "loss": 0.4237, "step": 5603 }, { "epoch": 1.434432, "grad_norm": 2.03125, "learning_rate": 2.609845576316014e-05, "loss": 0.4256, "step": 5604 }, { "epoch": 1.434688, "grad_norm": 2.125, "learning_rate": 2.6094189915536217e-05, "loss": 0.4586, "step": 5605 }, { "epoch": 1.434944, "grad_norm": 1.9921875, "learning_rate": 2.6089924067912298e-05, "loss": 0.4607, "step": 5606 }, { "epoch": 1.4352, "grad_norm": 1.8828125, "learning_rate": 2.6085658220288372e-05, "loss": 0.4348, "step": 5607 }, { "epoch": 1.435456, "grad_norm": 2.078125, "learning_rate": 2.608139237266445e-05, "loss": 0.4464, "step": 5608 }, { "epoch": 1.435712, "grad_norm": 1.859375, "learning_rate": 2.607712652504053e-05, "loss": 0.4657, "step": 5609 }, { "epoch": 1.435968, "grad_norm": 2.203125, "learning_rate": 2.6072860677416605e-05, "loss": 0.4658, "step": 5610 }, { "epoch": 1.436224, "grad_norm": 2.234375, "learning_rate": 2.606859482979268e-05, "loss": 0.4586, "step": 5611 }, { "epoch": 1.43648, "grad_norm": 1.9296875, "learning_rate": 2.6064328982168757e-05, "loss": 0.4426, "step": 5612 }, { "epoch": 1.436736, "grad_norm": 1.921875, "learning_rate": 2.6060063134544838e-05, "loss": 0.4695, "step": 5613 }, { "epoch": 1.436992, "grad_norm": 2.0625, "learning_rate": 2.6055797286920912e-05, "loss": 0.4121, "step": 5614 }, { "epoch": 1.437248, "grad_norm": 2.21875, "learning_rate": 2.605153143929699e-05, "loss": 0.4563, "step": 5615 }, { "epoch": 1.4375040000000001, "grad_norm": 2.234375, "learning_rate": 2.6047265591673064e-05, "loss": 0.4432, "step": 5616 }, { "epoch": 1.43776, "grad_norm": 2.09375, "learning_rate": 2.6042999744049145e-05, "loss": 0.4112, "step": 5617 }, { "epoch": 1.438016, "grad_norm": 2.171875, "learning_rate": 2.6038733896425223e-05, "loss": 0.441, "step": 5618 }, { "epoch": 1.438272, "grad_norm": 2.0625, "learning_rate": 2.6034468048801297e-05, "loss": 0.4305, "step": 5619 }, { "epoch": 1.438528, "grad_norm": 2.125, "learning_rate": 2.603020220117737e-05, "loss": 0.4681, "step": 5620 }, { "epoch": 1.438784, "grad_norm": 2.125, "learning_rate": 2.6025936353553452e-05, "loss": 0.4437, "step": 5621 }, { "epoch": 1.4390399999999999, "grad_norm": 2.296875, "learning_rate": 2.602167050592953e-05, "loss": 0.4547, "step": 5622 }, { "epoch": 1.4392960000000001, "grad_norm": 2.0, "learning_rate": 2.6017404658305604e-05, "loss": 0.4218, "step": 5623 }, { "epoch": 1.439552, "grad_norm": 2.109375, "learning_rate": 2.6013138810681685e-05, "loss": 0.4696, "step": 5624 }, { "epoch": 1.439808, "grad_norm": 1.9921875, "learning_rate": 2.6008872963057763e-05, "loss": 0.4536, "step": 5625 }, { "epoch": 1.440064, "grad_norm": 2.046875, "learning_rate": 2.6004607115433837e-05, "loss": 0.4381, "step": 5626 }, { "epoch": 1.44032, "grad_norm": 2.203125, "learning_rate": 2.6000341267809915e-05, "loss": 0.4837, "step": 5627 }, { "epoch": 1.440576, "grad_norm": 2.1875, "learning_rate": 2.5996075420185996e-05, "loss": 0.4001, "step": 5628 }, { "epoch": 1.440832, "grad_norm": 2.15625, "learning_rate": 2.599180957256207e-05, "loss": 0.4179, "step": 5629 }, { "epoch": 1.441088, "grad_norm": 2.046875, "learning_rate": 2.5987543724938144e-05, "loss": 0.4613, "step": 5630 }, { "epoch": 1.441344, "grad_norm": 2.078125, "learning_rate": 2.5983277877314222e-05, "loss": 0.4313, "step": 5631 }, { "epoch": 1.4416, "grad_norm": 1.9921875, "learning_rate": 2.5979012029690303e-05, "loss": 0.4627, "step": 5632 }, { "epoch": 1.441856, "grad_norm": 2.09375, "learning_rate": 2.5974746182066377e-05, "loss": 0.4554, "step": 5633 }, { "epoch": 1.442112, "grad_norm": 1.953125, "learning_rate": 2.5970480334442455e-05, "loss": 0.4399, "step": 5634 }, { "epoch": 1.442368, "grad_norm": 2.078125, "learning_rate": 2.596621448681853e-05, "loss": 0.4754, "step": 5635 }, { "epoch": 1.442624, "grad_norm": 2.125, "learning_rate": 2.596194863919461e-05, "loss": 0.473, "step": 5636 }, { "epoch": 1.44288, "grad_norm": 2.109375, "learning_rate": 2.5957682791570688e-05, "loss": 0.448, "step": 5637 }, { "epoch": 1.443136, "grad_norm": 1.9921875, "learning_rate": 2.5953416943946762e-05, "loss": 0.4397, "step": 5638 }, { "epoch": 1.443392, "grad_norm": 2.015625, "learning_rate": 2.5949151096322837e-05, "loss": 0.4444, "step": 5639 }, { "epoch": 1.443648, "grad_norm": 2.015625, "learning_rate": 2.5944885248698918e-05, "loss": 0.4312, "step": 5640 }, { "epoch": 1.443904, "grad_norm": 1.9765625, "learning_rate": 2.5940619401074995e-05, "loss": 0.4618, "step": 5641 }, { "epoch": 1.44416, "grad_norm": 2.25, "learning_rate": 2.593635355345107e-05, "loss": 0.4569, "step": 5642 }, { "epoch": 1.444416, "grad_norm": 2.0625, "learning_rate": 2.593208770582715e-05, "loss": 0.4329, "step": 5643 }, { "epoch": 1.444672, "grad_norm": 2.171875, "learning_rate": 2.5927821858203228e-05, "loss": 0.4336, "step": 5644 }, { "epoch": 1.444928, "grad_norm": 2.03125, "learning_rate": 2.5923556010579303e-05, "loss": 0.4401, "step": 5645 }, { "epoch": 1.445184, "grad_norm": 2.015625, "learning_rate": 2.591929016295538e-05, "loss": 0.4443, "step": 5646 }, { "epoch": 1.44544, "grad_norm": 2.046875, "learning_rate": 2.591502431533146e-05, "loss": 0.4423, "step": 5647 }, { "epoch": 1.4456959999999999, "grad_norm": 2.015625, "learning_rate": 2.5910758467707535e-05, "loss": 0.4189, "step": 5648 }, { "epoch": 1.4459520000000001, "grad_norm": 2.078125, "learning_rate": 2.590649262008361e-05, "loss": 0.4186, "step": 5649 }, { "epoch": 1.446208, "grad_norm": 2.03125, "learning_rate": 2.5902226772459687e-05, "loss": 0.4143, "step": 5650 }, { "epoch": 1.446464, "grad_norm": 2.1875, "learning_rate": 2.589796092483577e-05, "loss": 0.4371, "step": 5651 }, { "epoch": 1.44672, "grad_norm": 2.15625, "learning_rate": 2.5893695077211843e-05, "loss": 0.4457, "step": 5652 }, { "epoch": 1.446976, "grad_norm": 2.078125, "learning_rate": 2.588942922958792e-05, "loss": 0.4603, "step": 5653 }, { "epoch": 1.447232, "grad_norm": 2.109375, "learning_rate": 2.5885163381963995e-05, "loss": 0.4723, "step": 5654 }, { "epoch": 1.4474879999999999, "grad_norm": 1.8515625, "learning_rate": 2.5880897534340076e-05, "loss": 0.4609, "step": 5655 }, { "epoch": 1.447744, "grad_norm": 2.0, "learning_rate": 2.5876631686716153e-05, "loss": 0.4905, "step": 5656 }, { "epoch": 1.448, "grad_norm": 1.9453125, "learning_rate": 2.5872365839092228e-05, "loss": 0.4425, "step": 5657 }, { "epoch": 1.448256, "grad_norm": 1.8828125, "learning_rate": 2.586809999146831e-05, "loss": 0.4616, "step": 5658 }, { "epoch": 1.448512, "grad_norm": 1.90625, "learning_rate": 2.5863834143844383e-05, "loss": 0.4493, "step": 5659 }, { "epoch": 1.448768, "grad_norm": 2.078125, "learning_rate": 2.585956829622046e-05, "loss": 0.4763, "step": 5660 }, { "epoch": 1.449024, "grad_norm": 2.015625, "learning_rate": 2.5855302448596535e-05, "loss": 0.4554, "step": 5661 }, { "epoch": 1.44928, "grad_norm": 2.046875, "learning_rate": 2.5851036600972616e-05, "loss": 0.4526, "step": 5662 }, { "epoch": 1.449536, "grad_norm": 2.125, "learning_rate": 2.5846770753348694e-05, "loss": 0.4871, "step": 5663 }, { "epoch": 1.449792, "grad_norm": 1.921875, "learning_rate": 2.5842504905724768e-05, "loss": 0.4469, "step": 5664 }, { "epoch": 1.450048, "grad_norm": 1.953125, "learning_rate": 2.5838239058100845e-05, "loss": 0.4718, "step": 5665 }, { "epoch": 1.450304, "grad_norm": 2.34375, "learning_rate": 2.5833973210476926e-05, "loss": 0.4892, "step": 5666 }, { "epoch": 1.45056, "grad_norm": 1.953125, "learning_rate": 2.5829707362853e-05, "loss": 0.4575, "step": 5667 }, { "epoch": 1.450816, "grad_norm": 1.9921875, "learning_rate": 2.5825441515229075e-05, "loss": 0.4314, "step": 5668 }, { "epoch": 1.451072, "grad_norm": 1.8203125, "learning_rate": 2.5821175667605153e-05, "loss": 0.4361, "step": 5669 }, { "epoch": 1.451328, "grad_norm": 2.015625, "learning_rate": 2.5816909819981234e-05, "loss": 0.4391, "step": 5670 }, { "epoch": 1.451584, "grad_norm": 2.109375, "learning_rate": 2.5812643972357308e-05, "loss": 0.444, "step": 5671 }, { "epoch": 1.45184, "grad_norm": 2.328125, "learning_rate": 2.5808378124733386e-05, "loss": 0.424, "step": 5672 }, { "epoch": 1.452096, "grad_norm": 1.8828125, "learning_rate": 2.5804112277109467e-05, "loss": 0.4731, "step": 5673 }, { "epoch": 1.4523519999999999, "grad_norm": 2.0625, "learning_rate": 2.579984642948554e-05, "loss": 0.4295, "step": 5674 }, { "epoch": 1.4526080000000001, "grad_norm": 2.015625, "learning_rate": 2.579558058186162e-05, "loss": 0.4553, "step": 5675 }, { "epoch": 1.452864, "grad_norm": 2.15625, "learning_rate": 2.5791314734237693e-05, "loss": 0.4289, "step": 5676 }, { "epoch": 1.45312, "grad_norm": 2.09375, "learning_rate": 2.5787048886613774e-05, "loss": 0.429, "step": 5677 }, { "epoch": 1.453376, "grad_norm": 2.125, "learning_rate": 2.5782783038989848e-05, "loss": 0.4691, "step": 5678 }, { "epoch": 1.453632, "grad_norm": 1.9921875, "learning_rate": 2.5778517191365926e-05, "loss": 0.4189, "step": 5679 }, { "epoch": 1.453888, "grad_norm": 2.0, "learning_rate": 2.5774251343742e-05, "loss": 0.4457, "step": 5680 }, { "epoch": 1.4541439999999999, "grad_norm": 1.8828125, "learning_rate": 2.576998549611808e-05, "loss": 0.4525, "step": 5681 }, { "epoch": 1.4544000000000001, "grad_norm": 2.125, "learning_rate": 2.576571964849416e-05, "loss": 0.4313, "step": 5682 }, { "epoch": 1.454656, "grad_norm": 1.921875, "learning_rate": 2.5761453800870233e-05, "loss": 0.4362, "step": 5683 }, { "epoch": 1.454912, "grad_norm": 1.96875, "learning_rate": 2.5757187953246307e-05, "loss": 0.4447, "step": 5684 }, { "epoch": 1.455168, "grad_norm": 1.8359375, "learning_rate": 2.5752922105622392e-05, "loss": 0.457, "step": 5685 }, { "epoch": 1.455424, "grad_norm": 1.9921875, "learning_rate": 2.5748656257998466e-05, "loss": 0.4186, "step": 5686 }, { "epoch": 1.45568, "grad_norm": 1.890625, "learning_rate": 2.574439041037454e-05, "loss": 0.4285, "step": 5687 }, { "epoch": 1.455936, "grad_norm": 2.0, "learning_rate": 2.5740124562750618e-05, "loss": 0.4241, "step": 5688 }, { "epoch": 1.456192, "grad_norm": 2.03125, "learning_rate": 2.57358587151267e-05, "loss": 0.4331, "step": 5689 }, { "epoch": 1.456448, "grad_norm": 2.0, "learning_rate": 2.5731592867502773e-05, "loss": 0.4522, "step": 5690 }, { "epoch": 1.456704, "grad_norm": 2.046875, "learning_rate": 2.572732701987885e-05, "loss": 0.4533, "step": 5691 }, { "epoch": 1.45696, "grad_norm": 2.09375, "learning_rate": 2.5723061172254932e-05, "loss": 0.4333, "step": 5692 }, { "epoch": 1.457216, "grad_norm": 1.9609375, "learning_rate": 2.5718795324631006e-05, "loss": 0.4426, "step": 5693 }, { "epoch": 1.457472, "grad_norm": 2.203125, "learning_rate": 2.571452947700708e-05, "loss": 0.4235, "step": 5694 }, { "epoch": 1.457728, "grad_norm": 2.21875, "learning_rate": 2.5710263629383158e-05, "loss": 0.4235, "step": 5695 }, { "epoch": 1.457984, "grad_norm": 2.015625, "learning_rate": 2.570599778175924e-05, "loss": 0.4645, "step": 5696 }, { "epoch": 1.45824, "grad_norm": 1.8828125, "learning_rate": 2.5701731934135313e-05, "loss": 0.4375, "step": 5697 }, { "epoch": 1.458496, "grad_norm": 2.125, "learning_rate": 2.569746608651139e-05, "loss": 0.4488, "step": 5698 }, { "epoch": 1.458752, "grad_norm": 2.125, "learning_rate": 2.5693200238887465e-05, "loss": 0.471, "step": 5699 }, { "epoch": 1.459008, "grad_norm": 2.0625, "learning_rate": 2.5688934391263546e-05, "loss": 0.4756, "step": 5700 }, { "epoch": 1.4592640000000001, "grad_norm": 2.28125, "learning_rate": 2.5684668543639624e-05, "loss": 0.4537, "step": 5701 }, { "epoch": 1.45952, "grad_norm": 2.25, "learning_rate": 2.56804026960157e-05, "loss": 0.4457, "step": 5702 }, { "epoch": 1.459776, "grad_norm": 2.015625, "learning_rate": 2.5676136848391773e-05, "loss": 0.4281, "step": 5703 }, { "epoch": 1.460032, "grad_norm": 2.125, "learning_rate": 2.5671871000767857e-05, "loss": 0.45, "step": 5704 }, { "epoch": 1.460288, "grad_norm": 2.078125, "learning_rate": 2.566760515314393e-05, "loss": 0.433, "step": 5705 }, { "epoch": 1.460544, "grad_norm": 2.078125, "learning_rate": 2.5663339305520006e-05, "loss": 0.446, "step": 5706 }, { "epoch": 1.4607999999999999, "grad_norm": 2.109375, "learning_rate": 2.5659073457896087e-05, "loss": 0.4154, "step": 5707 }, { "epoch": 1.4610560000000001, "grad_norm": 2.21875, "learning_rate": 2.5654807610272164e-05, "loss": 0.4318, "step": 5708 }, { "epoch": 1.461312, "grad_norm": 2.078125, "learning_rate": 2.565054176264824e-05, "loss": 0.4569, "step": 5709 }, { "epoch": 1.461568, "grad_norm": 2.09375, "learning_rate": 2.5646275915024316e-05, "loss": 0.4581, "step": 5710 }, { "epoch": 1.461824, "grad_norm": 1.96875, "learning_rate": 2.5642010067400397e-05, "loss": 0.4837, "step": 5711 }, { "epoch": 1.46208, "grad_norm": 2.125, "learning_rate": 2.563774421977647e-05, "loss": 0.4285, "step": 5712 }, { "epoch": 1.462336, "grad_norm": 2.234375, "learning_rate": 2.5633478372152546e-05, "loss": 0.4794, "step": 5713 }, { "epoch": 1.462592, "grad_norm": 2.015625, "learning_rate": 2.5629212524528623e-05, "loss": 0.4211, "step": 5714 }, { "epoch": 1.462848, "grad_norm": 2.0625, "learning_rate": 2.5624946676904704e-05, "loss": 0.4525, "step": 5715 }, { "epoch": 1.463104, "grad_norm": 2.140625, "learning_rate": 2.562068082928078e-05, "loss": 0.4322, "step": 5716 }, { "epoch": 1.46336, "grad_norm": 2.03125, "learning_rate": 2.5616414981656856e-05, "loss": 0.4746, "step": 5717 }, { "epoch": 1.463616, "grad_norm": 2.171875, "learning_rate": 2.561214913403293e-05, "loss": 0.4646, "step": 5718 }, { "epoch": 1.463872, "grad_norm": 2.09375, "learning_rate": 2.560788328640901e-05, "loss": 0.4315, "step": 5719 }, { "epoch": 1.464128, "grad_norm": 2.09375, "learning_rate": 2.560361743878509e-05, "loss": 0.3964, "step": 5720 }, { "epoch": 1.464384, "grad_norm": 2.0625, "learning_rate": 2.5599351591161164e-05, "loss": 0.4456, "step": 5721 }, { "epoch": 1.46464, "grad_norm": 2.046875, "learning_rate": 2.5595085743537238e-05, "loss": 0.4918, "step": 5722 }, { "epoch": 1.464896, "grad_norm": 1.9453125, "learning_rate": 2.559081989591332e-05, "loss": 0.4963, "step": 5723 }, { "epoch": 1.465152, "grad_norm": 2.046875, "learning_rate": 2.5586554048289397e-05, "loss": 0.4484, "step": 5724 }, { "epoch": 1.465408, "grad_norm": 2.046875, "learning_rate": 2.558228820066547e-05, "loss": 0.4666, "step": 5725 }, { "epoch": 1.465664, "grad_norm": 2.15625, "learning_rate": 2.5578022353041552e-05, "loss": 0.4812, "step": 5726 }, { "epoch": 1.4659200000000001, "grad_norm": 2.125, "learning_rate": 2.557375650541763e-05, "loss": 0.4546, "step": 5727 }, { "epoch": 1.466176, "grad_norm": 2.0625, "learning_rate": 2.5569490657793704e-05, "loss": 0.4374, "step": 5728 }, { "epoch": 1.466432, "grad_norm": 1.9609375, "learning_rate": 2.556522481016978e-05, "loss": 0.4739, "step": 5729 }, { "epoch": 1.466688, "grad_norm": 1.9140625, "learning_rate": 2.5560958962545862e-05, "loss": 0.4555, "step": 5730 }, { "epoch": 1.466944, "grad_norm": 1.984375, "learning_rate": 2.5556693114921937e-05, "loss": 0.436, "step": 5731 }, { "epoch": 1.4672, "grad_norm": 2.15625, "learning_rate": 2.555242726729801e-05, "loss": 0.4755, "step": 5732 }, { "epoch": 1.4674559999999999, "grad_norm": 1.9375, "learning_rate": 2.554816141967409e-05, "loss": 0.4539, "step": 5733 }, { "epoch": 1.4677120000000001, "grad_norm": 2.03125, "learning_rate": 2.554389557205017e-05, "loss": 0.4114, "step": 5734 }, { "epoch": 1.467968, "grad_norm": 2.09375, "learning_rate": 2.5539629724426244e-05, "loss": 0.4247, "step": 5735 }, { "epoch": 1.468224, "grad_norm": 1.921875, "learning_rate": 2.553536387680232e-05, "loss": 0.43, "step": 5736 }, { "epoch": 1.46848, "grad_norm": 2.0625, "learning_rate": 2.5531098029178396e-05, "loss": 0.4439, "step": 5737 }, { "epoch": 1.468736, "grad_norm": 2.109375, "learning_rate": 2.5526832181554477e-05, "loss": 0.4485, "step": 5738 }, { "epoch": 1.468992, "grad_norm": 2.1875, "learning_rate": 2.5522566333930555e-05, "loss": 0.4099, "step": 5739 }, { "epoch": 1.4692479999999999, "grad_norm": 1.9375, "learning_rate": 2.551830048630663e-05, "loss": 0.4676, "step": 5740 }, { "epoch": 1.469504, "grad_norm": 1.90625, "learning_rate": 2.551403463868271e-05, "loss": 0.4718, "step": 5741 }, { "epoch": 1.46976, "grad_norm": 1.984375, "learning_rate": 2.5509768791058784e-05, "loss": 0.4599, "step": 5742 }, { "epoch": 1.470016, "grad_norm": 2.1875, "learning_rate": 2.5505502943434862e-05, "loss": 0.4269, "step": 5743 }, { "epoch": 1.470272, "grad_norm": 2.0625, "learning_rate": 2.5501237095810936e-05, "loss": 0.4485, "step": 5744 }, { "epoch": 1.470528, "grad_norm": 2.09375, "learning_rate": 2.5496971248187017e-05, "loss": 0.447, "step": 5745 }, { "epoch": 1.470784, "grad_norm": 1.890625, "learning_rate": 2.5492705400563095e-05, "loss": 0.46, "step": 5746 }, { "epoch": 1.47104, "grad_norm": 1.8671875, "learning_rate": 2.548843955293917e-05, "loss": 0.4491, "step": 5747 }, { "epoch": 1.471296, "grad_norm": 1.953125, "learning_rate": 2.5484173705315247e-05, "loss": 0.423, "step": 5748 }, { "epoch": 1.471552, "grad_norm": 2.25, "learning_rate": 2.5479907857691328e-05, "loss": 0.449, "step": 5749 }, { "epoch": 1.471808, "grad_norm": 2.203125, "learning_rate": 2.5475642010067402e-05, "loss": 0.3951, "step": 5750 }, { "epoch": 1.472064, "grad_norm": 2.046875, "learning_rate": 2.5471376162443476e-05, "loss": 0.4156, "step": 5751 }, { "epoch": 1.47232, "grad_norm": 1.9453125, "learning_rate": 2.5467110314819554e-05, "loss": 0.4701, "step": 5752 }, { "epoch": 1.472576, "grad_norm": 2.0625, "learning_rate": 2.5462844467195635e-05, "loss": 0.4501, "step": 5753 }, { "epoch": 1.472832, "grad_norm": 1.9453125, "learning_rate": 2.545857861957171e-05, "loss": 0.4306, "step": 5754 }, { "epoch": 1.473088, "grad_norm": 1.8203125, "learning_rate": 2.5454312771947787e-05, "loss": 0.492, "step": 5755 }, { "epoch": 1.473344, "grad_norm": 2.09375, "learning_rate": 2.5450046924323868e-05, "loss": 0.4019, "step": 5756 }, { "epoch": 1.4736, "grad_norm": 2.09375, "learning_rate": 2.5445781076699942e-05, "loss": 0.4601, "step": 5757 }, { "epoch": 1.473856, "grad_norm": 2.140625, "learning_rate": 2.544151522907602e-05, "loss": 0.4266, "step": 5758 }, { "epoch": 1.4741119999999999, "grad_norm": 2.078125, "learning_rate": 2.5437249381452094e-05, "loss": 0.4731, "step": 5759 }, { "epoch": 1.4743680000000001, "grad_norm": 2.109375, "learning_rate": 2.5432983533828175e-05, "loss": 0.4272, "step": 5760 }, { "epoch": 1.474624, "grad_norm": 2.078125, "learning_rate": 2.542871768620425e-05, "loss": 0.479, "step": 5761 }, { "epoch": 1.47488, "grad_norm": 2.296875, "learning_rate": 2.5424451838580327e-05, "loss": 0.4715, "step": 5762 }, { "epoch": 1.475136, "grad_norm": 2.171875, "learning_rate": 2.54201859909564e-05, "loss": 0.4706, "step": 5763 }, { "epoch": 1.475392, "grad_norm": 2.09375, "learning_rate": 2.5415920143332482e-05, "loss": 0.4208, "step": 5764 }, { "epoch": 1.475648, "grad_norm": 2.109375, "learning_rate": 2.541165429570856e-05, "loss": 0.4206, "step": 5765 }, { "epoch": 1.4759039999999999, "grad_norm": 2.21875, "learning_rate": 2.5407388448084634e-05, "loss": 0.4266, "step": 5766 }, { "epoch": 1.4761600000000001, "grad_norm": 1.9921875, "learning_rate": 2.5403122600460712e-05, "loss": 0.4469, "step": 5767 }, { "epoch": 1.476416, "grad_norm": 2.09375, "learning_rate": 2.5398856752836793e-05, "loss": 0.4356, "step": 5768 }, { "epoch": 1.476672, "grad_norm": 1.9375, "learning_rate": 2.5394590905212867e-05, "loss": 0.4518, "step": 5769 }, { "epoch": 1.476928, "grad_norm": 2.0625, "learning_rate": 2.539032505758894e-05, "loss": 0.4504, "step": 5770 }, { "epoch": 1.477184, "grad_norm": 1.9453125, "learning_rate": 2.538605920996502e-05, "loss": 0.4295, "step": 5771 }, { "epoch": 1.47744, "grad_norm": 1.875, "learning_rate": 2.53817933623411e-05, "loss": 0.4466, "step": 5772 }, { "epoch": 1.477696, "grad_norm": 2.046875, "learning_rate": 2.5377527514717175e-05, "loss": 0.4487, "step": 5773 }, { "epoch": 1.477952, "grad_norm": 2.34375, "learning_rate": 2.5373261667093252e-05, "loss": 0.4429, "step": 5774 }, { "epoch": 1.478208, "grad_norm": 2.296875, "learning_rate": 2.5368995819469333e-05, "loss": 0.4293, "step": 5775 }, { "epoch": 1.478464, "grad_norm": 2.34375, "learning_rate": 2.5364729971845407e-05, "loss": 0.4573, "step": 5776 }, { "epoch": 1.47872, "grad_norm": 2.203125, "learning_rate": 2.5360464124221485e-05, "loss": 0.4756, "step": 5777 }, { "epoch": 1.478976, "grad_norm": 2.15625, "learning_rate": 2.535619827659756e-05, "loss": 0.4449, "step": 5778 }, { "epoch": 1.479232, "grad_norm": 1.9453125, "learning_rate": 2.535193242897364e-05, "loss": 0.4544, "step": 5779 }, { "epoch": 1.479488, "grad_norm": 2.15625, "learning_rate": 2.5347666581349715e-05, "loss": 0.4404, "step": 5780 }, { "epoch": 1.479744, "grad_norm": 2.109375, "learning_rate": 2.5343400733725792e-05, "loss": 0.4292, "step": 5781 }, { "epoch": 1.48, "grad_norm": 2.125, "learning_rate": 2.5339134886101867e-05, "loss": 0.4486, "step": 5782 }, { "epoch": 1.480256, "grad_norm": 2.078125, "learning_rate": 2.5334869038477948e-05, "loss": 0.4517, "step": 5783 }, { "epoch": 1.480512, "grad_norm": 2.109375, "learning_rate": 2.5330603190854025e-05, "loss": 0.4318, "step": 5784 }, { "epoch": 1.4807679999999999, "grad_norm": 2.171875, "learning_rate": 2.53263373432301e-05, "loss": 0.4324, "step": 5785 }, { "epoch": 1.4810240000000001, "grad_norm": 2.234375, "learning_rate": 2.5322071495606174e-05, "loss": 0.458, "step": 5786 }, { "epoch": 1.48128, "grad_norm": 2.046875, "learning_rate": 2.5317805647982258e-05, "loss": 0.4477, "step": 5787 }, { "epoch": 1.481536, "grad_norm": 2.03125, "learning_rate": 2.5313539800358333e-05, "loss": 0.4518, "step": 5788 }, { "epoch": 1.481792, "grad_norm": 2.21875, "learning_rate": 2.5309273952734407e-05, "loss": 0.4505, "step": 5789 }, { "epoch": 1.482048, "grad_norm": 2.0625, "learning_rate": 2.5305008105110488e-05, "loss": 0.4574, "step": 5790 }, { "epoch": 1.482304, "grad_norm": 2.1875, "learning_rate": 2.5300742257486566e-05, "loss": 0.4494, "step": 5791 }, { "epoch": 1.4825599999999999, "grad_norm": 2.1875, "learning_rate": 2.529647640986264e-05, "loss": 0.456, "step": 5792 }, { "epoch": 1.4828160000000001, "grad_norm": 2.03125, "learning_rate": 2.5292210562238717e-05, "loss": 0.4323, "step": 5793 }, { "epoch": 1.483072, "grad_norm": 1.90625, "learning_rate": 2.52879447146148e-05, "loss": 0.4808, "step": 5794 }, { "epoch": 1.483328, "grad_norm": 2.125, "learning_rate": 2.5283678866990873e-05, "loss": 0.4451, "step": 5795 }, { "epoch": 1.483584, "grad_norm": 2.15625, "learning_rate": 2.527941301936695e-05, "loss": 0.4546, "step": 5796 }, { "epoch": 1.48384, "grad_norm": 2.109375, "learning_rate": 2.5275147171743025e-05, "loss": 0.4246, "step": 5797 }, { "epoch": 1.484096, "grad_norm": 2.109375, "learning_rate": 2.5270881324119106e-05, "loss": 0.4286, "step": 5798 }, { "epoch": 1.484352, "grad_norm": 2.203125, "learning_rate": 2.526661547649518e-05, "loss": 0.4581, "step": 5799 }, { "epoch": 1.484608, "grad_norm": 1.9921875, "learning_rate": 2.5262349628871258e-05, "loss": 0.4705, "step": 5800 }, { "epoch": 1.484864, "grad_norm": 2.015625, "learning_rate": 2.5258083781247332e-05, "loss": 0.4208, "step": 5801 }, { "epoch": 1.48512, "grad_norm": 2.234375, "learning_rate": 2.5253817933623413e-05, "loss": 0.4332, "step": 5802 }, { "epoch": 1.485376, "grad_norm": 2.015625, "learning_rate": 2.524955208599949e-05, "loss": 0.4644, "step": 5803 }, { "epoch": 1.485632, "grad_norm": 2.09375, "learning_rate": 2.5245286238375565e-05, "loss": 0.4649, "step": 5804 }, { "epoch": 1.485888, "grad_norm": 2.046875, "learning_rate": 2.5241020390751646e-05, "loss": 0.4135, "step": 5805 }, { "epoch": 1.486144, "grad_norm": 1.9921875, "learning_rate": 2.5236754543127724e-05, "loss": 0.4298, "step": 5806 }, { "epoch": 1.4864, "grad_norm": 2.0625, "learning_rate": 2.5232488695503798e-05, "loss": 0.4491, "step": 5807 }, { "epoch": 1.486656, "grad_norm": 2.109375, "learning_rate": 2.5228222847879872e-05, "loss": 0.4548, "step": 5808 }, { "epoch": 1.486912, "grad_norm": 2.25, "learning_rate": 2.5223957000255953e-05, "loss": 0.4727, "step": 5809 }, { "epoch": 1.487168, "grad_norm": 2.15625, "learning_rate": 2.521969115263203e-05, "loss": 0.4283, "step": 5810 }, { "epoch": 1.487424, "grad_norm": 1.96875, "learning_rate": 2.5215425305008105e-05, "loss": 0.468, "step": 5811 }, { "epoch": 1.4876800000000001, "grad_norm": 1.90625, "learning_rate": 2.5211159457384183e-05, "loss": 0.4819, "step": 5812 }, { "epoch": 1.487936, "grad_norm": 2.171875, "learning_rate": 2.5206893609760264e-05, "loss": 0.4412, "step": 5813 }, { "epoch": 1.488192, "grad_norm": 2.15625, "learning_rate": 2.5202627762136338e-05, "loss": 0.463, "step": 5814 }, { "epoch": 1.488448, "grad_norm": 2.1875, "learning_rate": 2.5198361914512412e-05, "loss": 0.4471, "step": 5815 }, { "epoch": 1.488704, "grad_norm": 2.078125, "learning_rate": 2.519409606688849e-05, "loss": 0.4279, "step": 5816 }, { "epoch": 1.48896, "grad_norm": 2.015625, "learning_rate": 2.518983021926457e-05, "loss": 0.4431, "step": 5817 }, { "epoch": 1.4892159999999999, "grad_norm": 1.8984375, "learning_rate": 2.5185564371640645e-05, "loss": 0.457, "step": 5818 }, { "epoch": 1.4894720000000001, "grad_norm": 1.8828125, "learning_rate": 2.5181298524016723e-05, "loss": 0.4693, "step": 5819 }, { "epoch": 1.489728, "grad_norm": 2.09375, "learning_rate": 2.5177032676392797e-05, "loss": 0.4598, "step": 5820 }, { "epoch": 1.489984, "grad_norm": 2.109375, "learning_rate": 2.5172766828768878e-05, "loss": 0.4472, "step": 5821 }, { "epoch": 1.49024, "grad_norm": 2.140625, "learning_rate": 2.5168500981144956e-05, "loss": 0.418, "step": 5822 }, { "epoch": 1.490496, "grad_norm": 1.9140625, "learning_rate": 2.516423513352103e-05, "loss": 0.4629, "step": 5823 }, { "epoch": 1.490752, "grad_norm": 2.21875, "learning_rate": 2.515996928589711e-05, "loss": 0.4133, "step": 5824 }, { "epoch": 1.491008, "grad_norm": 1.9375, "learning_rate": 2.5155703438273185e-05, "loss": 0.4535, "step": 5825 }, { "epoch": 1.491264, "grad_norm": 1.96875, "learning_rate": 2.5151437590649263e-05, "loss": 0.4274, "step": 5826 }, { "epoch": 1.49152, "grad_norm": 2.046875, "learning_rate": 2.5147171743025337e-05, "loss": 0.4331, "step": 5827 }, { "epoch": 1.491776, "grad_norm": 2.234375, "learning_rate": 2.514290589540142e-05, "loss": 0.4519, "step": 5828 }, { "epoch": 1.492032, "grad_norm": 2.203125, "learning_rate": 2.5138640047777496e-05, "loss": 0.4187, "step": 5829 }, { "epoch": 1.492288, "grad_norm": 2.21875, "learning_rate": 2.513437420015357e-05, "loss": 0.4395, "step": 5830 }, { "epoch": 1.492544, "grad_norm": 2.109375, "learning_rate": 2.5130108352529648e-05, "loss": 0.4485, "step": 5831 }, { "epoch": 1.4928, "grad_norm": 2.015625, "learning_rate": 2.512584250490573e-05, "loss": 0.4456, "step": 5832 }, { "epoch": 1.493056, "grad_norm": 2.0, "learning_rate": 2.5121576657281803e-05, "loss": 0.4607, "step": 5833 }, { "epoch": 1.493312, "grad_norm": 1.859375, "learning_rate": 2.5117310809657878e-05, "loss": 0.4442, "step": 5834 }, { "epoch": 1.493568, "grad_norm": 2.046875, "learning_rate": 2.5113044962033955e-05, "loss": 0.4306, "step": 5835 }, { "epoch": 1.493824, "grad_norm": 2.109375, "learning_rate": 2.5108779114410036e-05, "loss": 0.4102, "step": 5836 }, { "epoch": 1.49408, "grad_norm": 2.03125, "learning_rate": 2.510451326678611e-05, "loss": 0.4773, "step": 5837 }, { "epoch": 1.494336, "grad_norm": 2.21875, "learning_rate": 2.5100247419162188e-05, "loss": 0.4233, "step": 5838 }, { "epoch": 1.494592, "grad_norm": 2.125, "learning_rate": 2.509598157153827e-05, "loss": 0.4162, "step": 5839 }, { "epoch": 1.494848, "grad_norm": 1.96875, "learning_rate": 2.5091715723914343e-05, "loss": 0.4706, "step": 5840 }, { "epoch": 1.495104, "grad_norm": 1.9453125, "learning_rate": 2.508744987629042e-05, "loss": 0.4137, "step": 5841 }, { "epoch": 1.49536, "grad_norm": 2.0625, "learning_rate": 2.5083184028666495e-05, "loss": 0.4399, "step": 5842 }, { "epoch": 1.495616, "grad_norm": 1.921875, "learning_rate": 2.5078918181042576e-05, "loss": 0.436, "step": 5843 }, { "epoch": 1.4958719999999999, "grad_norm": 2.234375, "learning_rate": 2.507465233341865e-05, "loss": 0.4002, "step": 5844 }, { "epoch": 1.4961280000000001, "grad_norm": 2.046875, "learning_rate": 2.507038648579473e-05, "loss": 0.4156, "step": 5845 }, { "epoch": 1.496384, "grad_norm": 2.234375, "learning_rate": 2.5066120638170803e-05, "loss": 0.4922, "step": 5846 }, { "epoch": 1.49664, "grad_norm": 2.0, "learning_rate": 2.5061854790546884e-05, "loss": 0.4975, "step": 5847 }, { "epoch": 1.496896, "grad_norm": 1.8203125, "learning_rate": 2.505758894292296e-05, "loss": 0.4721, "step": 5848 }, { "epoch": 1.497152, "grad_norm": 1.875, "learning_rate": 2.5053323095299036e-05, "loss": 0.4272, "step": 5849 }, { "epoch": 1.497408, "grad_norm": 2.0625, "learning_rate": 2.5049057247675113e-05, "loss": 0.4394, "step": 5850 }, { "epoch": 1.4976639999999999, "grad_norm": 1.9296875, "learning_rate": 2.5044791400051194e-05, "loss": 0.4638, "step": 5851 }, { "epoch": 1.49792, "grad_norm": 2.03125, "learning_rate": 2.504052555242727e-05, "loss": 0.4204, "step": 5852 }, { "epoch": 1.498176, "grad_norm": 1.921875, "learning_rate": 2.5036259704803343e-05, "loss": 0.4526, "step": 5853 }, { "epoch": 1.498432, "grad_norm": 1.8984375, "learning_rate": 2.5031993857179424e-05, "loss": 0.4645, "step": 5854 }, { "epoch": 1.498688, "grad_norm": 1.9140625, "learning_rate": 2.50277280095555e-05, "loss": 0.453, "step": 5855 }, { "epoch": 1.498944, "grad_norm": 1.90625, "learning_rate": 2.5023462161931576e-05, "loss": 0.4064, "step": 5856 }, { "epoch": 1.4992, "grad_norm": 1.9609375, "learning_rate": 2.5019196314307653e-05, "loss": 0.4582, "step": 5857 }, { "epoch": 1.499456, "grad_norm": 2.109375, "learning_rate": 2.5014930466683734e-05, "loss": 0.4463, "step": 5858 }, { "epoch": 1.499712, "grad_norm": 2.0625, "learning_rate": 2.501066461905981e-05, "loss": 0.4081, "step": 5859 }, { "epoch": 1.499968, "grad_norm": 2.046875, "learning_rate": 2.5006398771435886e-05, "loss": 0.4204, "step": 5860 }, { "epoch": 1.500224, "grad_norm": 1.9765625, "learning_rate": 2.500213292381196e-05, "loss": 0.4449, "step": 5861 }, { "epoch": 1.50048, "grad_norm": 2.09375, "learning_rate": 2.499786707618804e-05, "loss": 0.4301, "step": 5862 }, { "epoch": 1.5007359999999998, "grad_norm": 1.984375, "learning_rate": 2.4993601228564116e-05, "loss": 0.4674, "step": 5863 }, { "epoch": 1.500992, "grad_norm": 1.953125, "learning_rate": 2.4989335380940194e-05, "loss": 0.4061, "step": 5864 }, { "epoch": 1.501248, "grad_norm": 2.109375, "learning_rate": 2.498506953331627e-05, "loss": 0.4605, "step": 5865 }, { "epoch": 1.501504, "grad_norm": 2.203125, "learning_rate": 2.4980803685692346e-05, "loss": 0.4304, "step": 5866 }, { "epoch": 1.50176, "grad_norm": 2.21875, "learning_rate": 2.4976537838068427e-05, "loss": 0.4325, "step": 5867 }, { "epoch": 1.502016, "grad_norm": 2.0, "learning_rate": 2.49722719904445e-05, "loss": 0.436, "step": 5868 }, { "epoch": 1.502272, "grad_norm": 2.1875, "learning_rate": 2.496800614282058e-05, "loss": 0.4724, "step": 5869 }, { "epoch": 1.5025279999999999, "grad_norm": 2.078125, "learning_rate": 2.496374029519666e-05, "loss": 0.4142, "step": 5870 }, { "epoch": 1.5027840000000001, "grad_norm": 1.90625, "learning_rate": 2.4959474447572734e-05, "loss": 0.3926, "step": 5871 }, { "epoch": 1.50304, "grad_norm": 2.140625, "learning_rate": 2.495520859994881e-05, "loss": 0.4456, "step": 5872 }, { "epoch": 1.503296, "grad_norm": 2.015625, "learning_rate": 2.495094275232489e-05, "loss": 0.4561, "step": 5873 }, { "epoch": 1.503552, "grad_norm": 2.15625, "learning_rate": 2.4946676904700967e-05, "loss": 0.4238, "step": 5874 }, { "epoch": 1.503808, "grad_norm": 2.1875, "learning_rate": 2.494241105707704e-05, "loss": 0.4201, "step": 5875 }, { "epoch": 1.504064, "grad_norm": 2.25, "learning_rate": 2.493814520945312e-05, "loss": 0.4004, "step": 5876 }, { "epoch": 1.5043199999999999, "grad_norm": 2.03125, "learning_rate": 2.4933879361829196e-05, "loss": 0.4318, "step": 5877 }, { "epoch": 1.5045760000000001, "grad_norm": 2.0625, "learning_rate": 2.4929613514205274e-05, "loss": 0.494, "step": 5878 }, { "epoch": 1.504832, "grad_norm": 2.125, "learning_rate": 2.492534766658135e-05, "loss": 0.4247, "step": 5879 }, { "epoch": 1.505088, "grad_norm": 2.125, "learning_rate": 2.492108181895743e-05, "loss": 0.4427, "step": 5880 }, { "epoch": 1.505344, "grad_norm": 1.9921875, "learning_rate": 2.4916815971333504e-05, "loss": 0.4757, "step": 5881 }, { "epoch": 1.5056, "grad_norm": 2.140625, "learning_rate": 2.491255012370958e-05, "loss": 0.4395, "step": 5882 }, { "epoch": 1.505856, "grad_norm": 1.984375, "learning_rate": 2.490828427608566e-05, "loss": 0.4652, "step": 5883 }, { "epoch": 1.506112, "grad_norm": 1.84375, "learning_rate": 2.4904018428461737e-05, "loss": 0.4444, "step": 5884 }, { "epoch": 1.5063680000000002, "grad_norm": 1.9453125, "learning_rate": 2.489975258083781e-05, "loss": 0.4277, "step": 5885 }, { "epoch": 1.506624, "grad_norm": 2.15625, "learning_rate": 2.4895486733213892e-05, "loss": 0.394, "step": 5886 }, { "epoch": 1.50688, "grad_norm": 1.8671875, "learning_rate": 2.489122088558997e-05, "loss": 0.4277, "step": 5887 }, { "epoch": 1.507136, "grad_norm": 2.046875, "learning_rate": 2.4886955037966044e-05, "loss": 0.4213, "step": 5888 }, { "epoch": 1.5073919999999998, "grad_norm": 2.046875, "learning_rate": 2.4882689190342125e-05, "loss": 0.4513, "step": 5889 }, { "epoch": 1.507648, "grad_norm": 2.171875, "learning_rate": 2.48784233427182e-05, "loss": 0.4176, "step": 5890 }, { "epoch": 1.507904, "grad_norm": 2.03125, "learning_rate": 2.4874157495094277e-05, "loss": 0.4338, "step": 5891 }, { "epoch": 1.50816, "grad_norm": 2.03125, "learning_rate": 2.4869891647470354e-05, "loss": 0.4372, "step": 5892 }, { "epoch": 1.508416, "grad_norm": 1.9765625, "learning_rate": 2.4865625799846432e-05, "loss": 0.4575, "step": 5893 }, { "epoch": 1.508672, "grad_norm": 2.125, "learning_rate": 2.4861359952222506e-05, "loss": 0.4243, "step": 5894 }, { "epoch": 1.508928, "grad_norm": 2.21875, "learning_rate": 2.4857094104598584e-05, "loss": 0.4993, "step": 5895 }, { "epoch": 1.5091839999999999, "grad_norm": 2.140625, "learning_rate": 2.485282825697466e-05, "loss": 0.4589, "step": 5896 }, { "epoch": 1.5094400000000001, "grad_norm": 2.109375, "learning_rate": 2.484856240935074e-05, "loss": 0.4565, "step": 5897 }, { "epoch": 1.509696, "grad_norm": 1.9765625, "learning_rate": 2.4844296561726817e-05, "loss": 0.447, "step": 5898 }, { "epoch": 1.509952, "grad_norm": 2.15625, "learning_rate": 2.4840030714102895e-05, "loss": 0.4487, "step": 5899 }, { "epoch": 1.510208, "grad_norm": 1.9453125, "learning_rate": 2.483576486647897e-05, "loss": 0.4219, "step": 5900 }, { "epoch": 1.510464, "grad_norm": 2.09375, "learning_rate": 2.4831499018855047e-05, "loss": 0.4403, "step": 5901 }, { "epoch": 1.51072, "grad_norm": 2.1875, "learning_rate": 2.4827233171231124e-05, "loss": 0.4651, "step": 5902 }, { "epoch": 1.5109759999999999, "grad_norm": 2.09375, "learning_rate": 2.4822967323607202e-05, "loss": 0.4475, "step": 5903 }, { "epoch": 1.5112320000000001, "grad_norm": 1.984375, "learning_rate": 2.481870147598328e-05, "loss": 0.4364, "step": 5904 }, { "epoch": 1.511488, "grad_norm": 1.90625, "learning_rate": 2.4814435628359357e-05, "loss": 0.4246, "step": 5905 }, { "epoch": 1.511744, "grad_norm": 1.9453125, "learning_rate": 2.4810169780735435e-05, "loss": 0.4228, "step": 5906 }, { "epoch": 1.512, "grad_norm": 2.15625, "learning_rate": 2.480590393311151e-05, "loss": 0.4467, "step": 5907 }, { "epoch": 1.512256, "grad_norm": 2.171875, "learning_rate": 2.480163808548759e-05, "loss": 0.4387, "step": 5908 }, { "epoch": 1.512512, "grad_norm": 2.015625, "learning_rate": 2.4797372237863664e-05, "loss": 0.4642, "step": 5909 }, { "epoch": 1.512768, "grad_norm": 2.078125, "learning_rate": 2.4793106390239742e-05, "loss": 0.4179, "step": 5910 }, { "epoch": 1.5130240000000001, "grad_norm": 2.171875, "learning_rate": 2.478884054261582e-05, "loss": 0.4303, "step": 5911 }, { "epoch": 1.51328, "grad_norm": 2.25, "learning_rate": 2.4784574694991897e-05, "loss": 0.4681, "step": 5912 }, { "epoch": 1.513536, "grad_norm": 2.0, "learning_rate": 2.478030884736797e-05, "loss": 0.4484, "step": 5913 }, { "epoch": 1.513792, "grad_norm": 2.015625, "learning_rate": 2.477604299974405e-05, "loss": 0.4345, "step": 5914 }, { "epoch": 1.5140479999999998, "grad_norm": 1.9453125, "learning_rate": 2.4771777152120127e-05, "loss": 0.44, "step": 5915 }, { "epoch": 1.514304, "grad_norm": 2.0625, "learning_rate": 2.4767511304496205e-05, "loss": 0.461, "step": 5916 }, { "epoch": 1.51456, "grad_norm": 2.125, "learning_rate": 2.476324545687228e-05, "loss": 0.4303, "step": 5917 }, { "epoch": 1.5148160000000002, "grad_norm": 2.171875, "learning_rate": 2.475897960924836e-05, "loss": 0.4501, "step": 5918 }, { "epoch": 1.515072, "grad_norm": 2.1875, "learning_rate": 2.4754713761624438e-05, "loss": 0.4433, "step": 5919 }, { "epoch": 1.515328, "grad_norm": 2.03125, "learning_rate": 2.4750447914000512e-05, "loss": 0.4007, "step": 5920 }, { "epoch": 1.515584, "grad_norm": 2.203125, "learning_rate": 2.4746182066376593e-05, "loss": 0.471, "step": 5921 }, { "epoch": 1.5158399999999999, "grad_norm": 2.03125, "learning_rate": 2.4741916218752667e-05, "loss": 0.483, "step": 5922 }, { "epoch": 1.516096, "grad_norm": 2.03125, "learning_rate": 2.4737650371128745e-05, "loss": 0.4365, "step": 5923 }, { "epoch": 1.516352, "grad_norm": 2.046875, "learning_rate": 2.4733384523504822e-05, "loss": 0.4693, "step": 5924 }, { "epoch": 1.516608, "grad_norm": 1.9609375, "learning_rate": 2.47291186758809e-05, "loss": 0.421, "step": 5925 }, { "epoch": 1.516864, "grad_norm": 2.046875, "learning_rate": 2.4724852828256974e-05, "loss": 0.4099, "step": 5926 }, { "epoch": 1.51712, "grad_norm": 2.140625, "learning_rate": 2.4720586980633052e-05, "loss": 0.4479, "step": 5927 }, { "epoch": 1.517376, "grad_norm": 2.0, "learning_rate": 2.471632113300913e-05, "loss": 0.4889, "step": 5928 }, { "epoch": 1.5176319999999999, "grad_norm": 2.078125, "learning_rate": 2.4712055285385207e-05, "loss": 0.439, "step": 5929 }, { "epoch": 1.5178880000000001, "grad_norm": 2.078125, "learning_rate": 2.4707789437761285e-05, "loss": 0.4648, "step": 5930 }, { "epoch": 1.518144, "grad_norm": 1.9609375, "learning_rate": 2.4703523590137363e-05, "loss": 0.4383, "step": 5931 }, { "epoch": 1.5184, "grad_norm": 2.390625, "learning_rate": 2.4699257742513437e-05, "loss": 0.4308, "step": 5932 }, { "epoch": 1.518656, "grad_norm": 2.15625, "learning_rate": 2.4694991894889515e-05, "loss": 0.4446, "step": 5933 }, { "epoch": 1.518912, "grad_norm": 2.046875, "learning_rate": 2.4690726047265592e-05, "loss": 0.4866, "step": 5934 }, { "epoch": 1.519168, "grad_norm": 1.9296875, "learning_rate": 2.468646019964167e-05, "loss": 0.4027, "step": 5935 }, { "epoch": 1.5194239999999999, "grad_norm": 1.9765625, "learning_rate": 2.4682194352017747e-05, "loss": 0.4348, "step": 5936 }, { "epoch": 1.5196800000000001, "grad_norm": 2.015625, "learning_rate": 2.4677928504393825e-05, "loss": 0.4371, "step": 5937 }, { "epoch": 1.519936, "grad_norm": 1.984375, "learning_rate": 2.4673662656769903e-05, "loss": 0.4529, "step": 5938 }, { "epoch": 1.520192, "grad_norm": 2.171875, "learning_rate": 2.4669396809145977e-05, "loss": 0.4399, "step": 5939 }, { "epoch": 1.520448, "grad_norm": 1.90625, "learning_rate": 2.4665130961522058e-05, "loss": 0.454, "step": 5940 }, { "epoch": 1.5207039999999998, "grad_norm": 2.09375, "learning_rate": 2.4660865113898132e-05, "loss": 0.4026, "step": 5941 }, { "epoch": 1.52096, "grad_norm": 2.109375, "learning_rate": 2.465659926627421e-05, "loss": 0.4087, "step": 5942 }, { "epoch": 1.521216, "grad_norm": 1.9765625, "learning_rate": 2.4652333418650288e-05, "loss": 0.4068, "step": 5943 }, { "epoch": 1.5214720000000002, "grad_norm": 1.828125, "learning_rate": 2.4648067571026365e-05, "loss": 0.4647, "step": 5944 }, { "epoch": 1.521728, "grad_norm": 1.8984375, "learning_rate": 2.464380172340244e-05, "loss": 0.4828, "step": 5945 }, { "epoch": 1.521984, "grad_norm": 2.078125, "learning_rate": 2.4639535875778517e-05, "loss": 0.4251, "step": 5946 }, { "epoch": 1.52224, "grad_norm": 2.140625, "learning_rate": 2.4635270028154595e-05, "loss": 0.4327, "step": 5947 }, { "epoch": 1.5224959999999998, "grad_norm": 2.3125, "learning_rate": 2.4631004180530673e-05, "loss": 0.4501, "step": 5948 }, { "epoch": 1.522752, "grad_norm": 2.203125, "learning_rate": 2.462673833290675e-05, "loss": 0.4511, "step": 5949 }, { "epoch": 1.523008, "grad_norm": 2.0, "learning_rate": 2.4622472485282828e-05, "loss": 0.4414, "step": 5950 }, { "epoch": 1.523264, "grad_norm": 2.0, "learning_rate": 2.4618206637658902e-05, "loss": 0.421, "step": 5951 }, { "epoch": 1.52352, "grad_norm": 2.125, "learning_rate": 2.461394079003498e-05, "loss": 0.4093, "step": 5952 }, { "epoch": 1.523776, "grad_norm": 2.125, "learning_rate": 2.460967494241106e-05, "loss": 0.4844, "step": 5953 }, { "epoch": 1.524032, "grad_norm": 2.078125, "learning_rate": 2.4605409094787135e-05, "loss": 0.4368, "step": 5954 }, { "epoch": 1.5242879999999999, "grad_norm": 2.03125, "learning_rate": 2.4601143247163213e-05, "loss": 0.4566, "step": 5955 }, { "epoch": 1.5245440000000001, "grad_norm": 2.125, "learning_rate": 2.459687739953929e-05, "loss": 0.4299, "step": 5956 }, { "epoch": 1.5248, "grad_norm": 1.96875, "learning_rate": 2.4592611551915368e-05, "loss": 0.4265, "step": 5957 }, { "epoch": 1.525056, "grad_norm": 1.9375, "learning_rate": 2.4588345704291442e-05, "loss": 0.4268, "step": 5958 }, { "epoch": 1.525312, "grad_norm": 2.15625, "learning_rate": 2.4584079856667523e-05, "loss": 0.4807, "step": 5959 }, { "epoch": 1.525568, "grad_norm": 2.140625, "learning_rate": 2.4579814009043598e-05, "loss": 0.4679, "step": 5960 }, { "epoch": 1.525824, "grad_norm": 2.046875, "learning_rate": 2.4575548161419675e-05, "loss": 0.4805, "step": 5961 }, { "epoch": 1.5260799999999999, "grad_norm": 2.0625, "learning_rate": 2.4571282313795753e-05, "loss": 0.4489, "step": 5962 }, { "epoch": 1.5263360000000001, "grad_norm": 2.296875, "learning_rate": 2.456701646617183e-05, "loss": 0.4064, "step": 5963 }, { "epoch": 1.526592, "grad_norm": 2.109375, "learning_rate": 2.4562750618547905e-05, "loss": 0.4526, "step": 5964 }, { "epoch": 1.526848, "grad_norm": 1.9453125, "learning_rate": 2.4558484770923983e-05, "loss": 0.4294, "step": 5965 }, { "epoch": 1.527104, "grad_norm": 1.9609375, "learning_rate": 2.455421892330006e-05, "loss": 0.476, "step": 5966 }, { "epoch": 1.52736, "grad_norm": 2.046875, "learning_rate": 2.4549953075676138e-05, "loss": 0.443, "step": 5967 }, { "epoch": 1.527616, "grad_norm": 2.125, "learning_rate": 2.4545687228052212e-05, "loss": 0.4668, "step": 5968 }, { "epoch": 1.527872, "grad_norm": 2.03125, "learning_rate": 2.4541421380428293e-05, "loss": 0.4419, "step": 5969 }, { "epoch": 1.5281280000000002, "grad_norm": 2.015625, "learning_rate": 2.453715553280437e-05, "loss": 0.4638, "step": 5970 }, { "epoch": 1.528384, "grad_norm": 1.8671875, "learning_rate": 2.4532889685180445e-05, "loss": 0.4194, "step": 5971 }, { "epoch": 1.52864, "grad_norm": 2.015625, "learning_rate": 2.4528623837556526e-05, "loss": 0.4324, "step": 5972 }, { "epoch": 1.528896, "grad_norm": 1.8515625, "learning_rate": 2.45243579899326e-05, "loss": 0.4384, "step": 5973 }, { "epoch": 1.5291519999999998, "grad_norm": 2.109375, "learning_rate": 2.4520092142308678e-05, "loss": 0.4036, "step": 5974 }, { "epoch": 1.529408, "grad_norm": 1.890625, "learning_rate": 2.4515826294684756e-05, "loss": 0.427, "step": 5975 }, { "epoch": 1.529664, "grad_norm": 2.046875, "learning_rate": 2.4511560447060833e-05, "loss": 0.4219, "step": 5976 }, { "epoch": 1.52992, "grad_norm": 1.9375, "learning_rate": 2.4507294599436908e-05, "loss": 0.4718, "step": 5977 }, { "epoch": 1.530176, "grad_norm": 2.09375, "learning_rate": 2.450302875181299e-05, "loss": 0.4487, "step": 5978 }, { "epoch": 1.530432, "grad_norm": 1.96875, "learning_rate": 2.4498762904189063e-05, "loss": 0.4451, "step": 5979 }, { "epoch": 1.530688, "grad_norm": 2.265625, "learning_rate": 2.449449705656514e-05, "loss": 0.4393, "step": 5980 }, { "epoch": 1.5309439999999999, "grad_norm": 1.9453125, "learning_rate": 2.4490231208941218e-05, "loss": 0.4731, "step": 5981 }, { "epoch": 1.5312000000000001, "grad_norm": 2.03125, "learning_rate": 2.4485965361317296e-05, "loss": 0.4196, "step": 5982 }, { "epoch": 1.531456, "grad_norm": 2.109375, "learning_rate": 2.448169951369337e-05, "loss": 0.4477, "step": 5983 }, { "epoch": 1.531712, "grad_norm": 2.078125, "learning_rate": 2.4477433666069448e-05, "loss": 0.441, "step": 5984 }, { "epoch": 1.531968, "grad_norm": 1.96875, "learning_rate": 2.447316781844553e-05, "loss": 0.4985, "step": 5985 }, { "epoch": 1.532224, "grad_norm": 2.1875, "learning_rate": 2.4468901970821603e-05, "loss": 0.4237, "step": 5986 }, { "epoch": 1.53248, "grad_norm": 2.015625, "learning_rate": 2.446463612319768e-05, "loss": 0.4364, "step": 5987 }, { "epoch": 1.5327359999999999, "grad_norm": 2.3125, "learning_rate": 2.446037027557376e-05, "loss": 0.4661, "step": 5988 }, { "epoch": 1.5329920000000001, "grad_norm": 2.171875, "learning_rate": 2.4456104427949836e-05, "loss": 0.4211, "step": 5989 }, { "epoch": 1.533248, "grad_norm": 2.171875, "learning_rate": 2.445183858032591e-05, "loss": 0.3962, "step": 5990 }, { "epoch": 1.533504, "grad_norm": 2.0625, "learning_rate": 2.444757273270199e-05, "loss": 0.4157, "step": 5991 }, { "epoch": 1.53376, "grad_norm": 1.9296875, "learning_rate": 2.4443306885078066e-05, "loss": 0.4601, "step": 5992 }, { "epoch": 1.534016, "grad_norm": 2.015625, "learning_rate": 2.4439041037454143e-05, "loss": 0.4202, "step": 5993 }, { "epoch": 1.534272, "grad_norm": 2.03125, "learning_rate": 2.443477518983022e-05, "loss": 0.4409, "step": 5994 }, { "epoch": 1.534528, "grad_norm": 1.890625, "learning_rate": 2.44305093422063e-05, "loss": 0.4355, "step": 5995 }, { "epoch": 1.5347840000000001, "grad_norm": 2.171875, "learning_rate": 2.4426243494582373e-05, "loss": 0.4566, "step": 5996 }, { "epoch": 1.53504, "grad_norm": 2.09375, "learning_rate": 2.442197764695845e-05, "loss": 0.4417, "step": 5997 }, { "epoch": 1.535296, "grad_norm": 2.046875, "learning_rate": 2.4417711799334528e-05, "loss": 0.4102, "step": 5998 }, { "epoch": 1.535552, "grad_norm": 1.9296875, "learning_rate": 2.4413445951710606e-05, "loss": 0.4261, "step": 5999 }, { "epoch": 1.5358079999999998, "grad_norm": 1.8828125, "learning_rate": 2.4409180104086683e-05, "loss": 0.4692, "step": 6000 }, { "epoch": 1.536064, "grad_norm": 2.140625, "learning_rate": 2.440491425646276e-05, "loss": 0.439, "step": 6001 }, { "epoch": 1.53632, "grad_norm": 2.203125, "learning_rate": 2.440064840883884e-05, "loss": 0.4408, "step": 6002 }, { "epoch": 1.5365760000000002, "grad_norm": 1.8984375, "learning_rate": 2.4396382561214913e-05, "loss": 0.4523, "step": 6003 }, { "epoch": 1.536832, "grad_norm": 2.09375, "learning_rate": 2.4392116713590994e-05, "loss": 0.4592, "step": 6004 }, { "epoch": 1.537088, "grad_norm": 1.9453125, "learning_rate": 2.438785086596707e-05, "loss": 0.4642, "step": 6005 }, { "epoch": 1.537344, "grad_norm": 2.1875, "learning_rate": 2.4383585018343146e-05, "loss": 0.4704, "step": 6006 }, { "epoch": 1.5375999999999999, "grad_norm": 1.9765625, "learning_rate": 2.4379319170719224e-05, "loss": 0.4606, "step": 6007 }, { "epoch": 1.5378560000000001, "grad_norm": 2.078125, "learning_rate": 2.43750533230953e-05, "loss": 0.4413, "step": 6008 }, { "epoch": 1.538112, "grad_norm": 2.078125, "learning_rate": 2.4370787475471376e-05, "loss": 0.427, "step": 6009 }, { "epoch": 1.538368, "grad_norm": 1.9921875, "learning_rate": 2.4366521627847457e-05, "loss": 0.4506, "step": 6010 }, { "epoch": 1.538624, "grad_norm": 1.875, "learning_rate": 2.436225578022353e-05, "loss": 0.4381, "step": 6011 }, { "epoch": 1.53888, "grad_norm": 1.921875, "learning_rate": 2.435798993259961e-05, "loss": 0.4715, "step": 6012 }, { "epoch": 1.539136, "grad_norm": 2.09375, "learning_rate": 2.4353724084975686e-05, "loss": 0.49, "step": 6013 }, { "epoch": 1.5393919999999999, "grad_norm": 2.046875, "learning_rate": 2.4349458237351764e-05, "loss": 0.4242, "step": 6014 }, { "epoch": 1.5396480000000001, "grad_norm": 1.8125, "learning_rate": 2.4345192389727838e-05, "loss": 0.4426, "step": 6015 }, { "epoch": 1.539904, "grad_norm": 1.9765625, "learning_rate": 2.4340926542103916e-05, "loss": 0.4424, "step": 6016 }, { "epoch": 1.54016, "grad_norm": 2.109375, "learning_rate": 2.4336660694479993e-05, "loss": 0.486, "step": 6017 }, { "epoch": 1.540416, "grad_norm": 1.9765625, "learning_rate": 2.433239484685607e-05, "loss": 0.4544, "step": 6018 }, { "epoch": 1.540672, "grad_norm": 2.078125, "learning_rate": 2.432812899923215e-05, "loss": 0.424, "step": 6019 }, { "epoch": 1.540928, "grad_norm": 1.9921875, "learning_rate": 2.4323863151608226e-05, "loss": 0.4337, "step": 6020 }, { "epoch": 1.5411839999999999, "grad_norm": 2.015625, "learning_rate": 2.4319597303984304e-05, "loss": 0.4188, "step": 6021 }, { "epoch": 1.5414400000000001, "grad_norm": 2.03125, "learning_rate": 2.431533145636038e-05, "loss": 0.4422, "step": 6022 }, { "epoch": 1.541696, "grad_norm": 1.953125, "learning_rate": 2.431106560873646e-05, "loss": 0.4449, "step": 6023 }, { "epoch": 1.541952, "grad_norm": 2.015625, "learning_rate": 2.4306799761112534e-05, "loss": 0.4378, "step": 6024 }, { "epoch": 1.542208, "grad_norm": 1.96875, "learning_rate": 2.430253391348861e-05, "loss": 0.418, "step": 6025 }, { "epoch": 1.5424639999999998, "grad_norm": 1.8046875, "learning_rate": 2.429826806586469e-05, "loss": 0.463, "step": 6026 }, { "epoch": 1.54272, "grad_norm": 2.015625, "learning_rate": 2.4294002218240767e-05, "loss": 0.4231, "step": 6027 }, { "epoch": 1.542976, "grad_norm": 1.953125, "learning_rate": 2.428973637061684e-05, "loss": 0.4136, "step": 6028 }, { "epoch": 1.5432320000000002, "grad_norm": 2.046875, "learning_rate": 2.4285470522992922e-05, "loss": 0.421, "step": 6029 }, { "epoch": 1.543488, "grad_norm": 2.15625, "learning_rate": 2.4281204675368996e-05, "loss": 0.4686, "step": 6030 }, { "epoch": 1.543744, "grad_norm": 2.171875, "learning_rate": 2.4276938827745074e-05, "loss": 0.4192, "step": 6031 }, { "epoch": 1.544, "grad_norm": 2.0, "learning_rate": 2.427267298012115e-05, "loss": 0.407, "step": 6032 }, { "epoch": 1.5442559999999999, "grad_norm": 2.046875, "learning_rate": 2.426840713249723e-05, "loss": 0.4657, "step": 6033 }, { "epoch": 1.544512, "grad_norm": 2.125, "learning_rate": 2.4264141284873307e-05, "loss": 0.4221, "step": 6034 }, { "epoch": 1.544768, "grad_norm": 2.0, "learning_rate": 2.425987543724938e-05, "loss": 0.4367, "step": 6035 }, { "epoch": 1.545024, "grad_norm": 2.21875, "learning_rate": 2.4255609589625462e-05, "loss": 0.4348, "step": 6036 }, { "epoch": 1.54528, "grad_norm": 2.046875, "learning_rate": 2.4251343742001536e-05, "loss": 0.4287, "step": 6037 }, { "epoch": 1.545536, "grad_norm": 1.984375, "learning_rate": 2.4247077894377614e-05, "loss": 0.487, "step": 6038 }, { "epoch": 1.545792, "grad_norm": 2.203125, "learning_rate": 2.424281204675369e-05, "loss": 0.4358, "step": 6039 }, { "epoch": 1.5460479999999999, "grad_norm": 2.03125, "learning_rate": 2.423854619912977e-05, "loss": 0.4411, "step": 6040 }, { "epoch": 1.5463040000000001, "grad_norm": 2.125, "learning_rate": 2.4234280351505844e-05, "loss": 0.4379, "step": 6041 }, { "epoch": 1.54656, "grad_norm": 2.140625, "learning_rate": 2.4230014503881925e-05, "loss": 0.4717, "step": 6042 }, { "epoch": 1.546816, "grad_norm": 2.03125, "learning_rate": 2.4225748656258e-05, "loss": 0.4791, "step": 6043 }, { "epoch": 1.547072, "grad_norm": 2.046875, "learning_rate": 2.4221482808634077e-05, "loss": 0.4262, "step": 6044 }, { "epoch": 1.547328, "grad_norm": 2.15625, "learning_rate": 2.4217216961010154e-05, "loss": 0.4573, "step": 6045 }, { "epoch": 1.547584, "grad_norm": 1.9296875, "learning_rate": 2.4212951113386232e-05, "loss": 0.4469, "step": 6046 }, { "epoch": 1.5478399999999999, "grad_norm": 2.15625, "learning_rate": 2.4208685265762306e-05, "loss": 0.5011, "step": 6047 }, { "epoch": 1.5480960000000001, "grad_norm": 2.203125, "learning_rate": 2.4204419418138384e-05, "loss": 0.4346, "step": 6048 }, { "epoch": 1.548352, "grad_norm": 2.0625, "learning_rate": 2.420015357051446e-05, "loss": 0.4482, "step": 6049 }, { "epoch": 1.548608, "grad_norm": 2.046875, "learning_rate": 2.419588772289054e-05, "loss": 0.4108, "step": 6050 }, { "epoch": 1.548864, "grad_norm": 1.875, "learning_rate": 2.4191621875266617e-05, "loss": 0.4213, "step": 6051 }, { "epoch": 1.54912, "grad_norm": 2.03125, "learning_rate": 2.4187356027642694e-05, "loss": 0.4242, "step": 6052 }, { "epoch": 1.549376, "grad_norm": 1.9609375, "learning_rate": 2.4183090180018772e-05, "loss": 0.4327, "step": 6053 }, { "epoch": 1.549632, "grad_norm": 1.9140625, "learning_rate": 2.4178824332394846e-05, "loss": 0.4302, "step": 6054 }, { "epoch": 1.5498880000000002, "grad_norm": 1.890625, "learning_rate": 2.4174558484770927e-05, "loss": 0.4607, "step": 6055 }, { "epoch": 1.550144, "grad_norm": 1.9609375, "learning_rate": 2.4170292637147e-05, "loss": 0.4783, "step": 6056 }, { "epoch": 1.5504, "grad_norm": 2.046875, "learning_rate": 2.416602678952308e-05, "loss": 0.4415, "step": 6057 }, { "epoch": 1.550656, "grad_norm": 2.21875, "learning_rate": 2.4161760941899157e-05, "loss": 0.4538, "step": 6058 }, { "epoch": 1.5509119999999998, "grad_norm": 1.8671875, "learning_rate": 2.4157495094275235e-05, "loss": 0.4174, "step": 6059 }, { "epoch": 1.551168, "grad_norm": 2.078125, "learning_rate": 2.415322924665131e-05, "loss": 0.4001, "step": 6060 }, { "epoch": 1.551424, "grad_norm": 2.234375, "learning_rate": 2.414896339902739e-05, "loss": 0.4484, "step": 6061 }, { "epoch": 1.55168, "grad_norm": 2.234375, "learning_rate": 2.4144697551403464e-05, "loss": 0.4267, "step": 6062 }, { "epoch": 1.551936, "grad_norm": 2.0625, "learning_rate": 2.4140431703779542e-05, "loss": 0.4423, "step": 6063 }, { "epoch": 1.552192, "grad_norm": 2.109375, "learning_rate": 2.413616585615562e-05, "loss": 0.4633, "step": 6064 }, { "epoch": 1.552448, "grad_norm": 1.9765625, "learning_rate": 2.4131900008531697e-05, "loss": 0.4341, "step": 6065 }, { "epoch": 1.5527039999999999, "grad_norm": 1.9375, "learning_rate": 2.412763416090777e-05, "loss": 0.4274, "step": 6066 }, { "epoch": 1.5529600000000001, "grad_norm": 2.046875, "learning_rate": 2.412336831328385e-05, "loss": 0.4713, "step": 6067 }, { "epoch": 1.553216, "grad_norm": 1.875, "learning_rate": 2.411910246565993e-05, "loss": 0.455, "step": 6068 }, { "epoch": 1.553472, "grad_norm": 1.8125, "learning_rate": 2.4114836618036004e-05, "loss": 0.4419, "step": 6069 }, { "epoch": 1.553728, "grad_norm": 1.984375, "learning_rate": 2.4110570770412082e-05, "loss": 0.4618, "step": 6070 }, { "epoch": 1.553984, "grad_norm": 2.109375, "learning_rate": 2.410630492278816e-05, "loss": 0.4609, "step": 6071 }, { "epoch": 1.55424, "grad_norm": 1.9296875, "learning_rate": 2.4102039075164237e-05, "loss": 0.4612, "step": 6072 }, { "epoch": 1.5544959999999999, "grad_norm": 1.921875, "learning_rate": 2.409777322754031e-05, "loss": 0.388, "step": 6073 }, { "epoch": 1.5547520000000001, "grad_norm": 2.109375, "learning_rate": 2.4093507379916393e-05, "loss": 0.4346, "step": 6074 }, { "epoch": 1.555008, "grad_norm": 1.984375, "learning_rate": 2.4089241532292467e-05, "loss": 0.4393, "step": 6075 }, { "epoch": 1.555264, "grad_norm": 1.921875, "learning_rate": 2.4084975684668545e-05, "loss": 0.429, "step": 6076 }, { "epoch": 1.55552, "grad_norm": 1.9765625, "learning_rate": 2.4080709837044622e-05, "loss": 0.4653, "step": 6077 }, { "epoch": 1.555776, "grad_norm": 2.0, "learning_rate": 2.40764439894207e-05, "loss": 0.4269, "step": 6078 }, { "epoch": 1.556032, "grad_norm": 2.078125, "learning_rate": 2.4072178141796774e-05, "loss": 0.4118, "step": 6079 }, { "epoch": 1.556288, "grad_norm": 2.015625, "learning_rate": 2.4067912294172855e-05, "loss": 0.4718, "step": 6080 }, { "epoch": 1.5565440000000001, "grad_norm": 2.03125, "learning_rate": 2.406364644654893e-05, "loss": 0.4052, "step": 6081 }, { "epoch": 1.5568, "grad_norm": 2.234375, "learning_rate": 2.4059380598925007e-05, "loss": 0.4226, "step": 6082 }, { "epoch": 1.557056, "grad_norm": 2.125, "learning_rate": 2.4055114751301085e-05, "loss": 0.4681, "step": 6083 }, { "epoch": 1.557312, "grad_norm": 2.09375, "learning_rate": 2.4050848903677162e-05, "loss": 0.464, "step": 6084 }, { "epoch": 1.5575679999999998, "grad_norm": 2.15625, "learning_rate": 2.404658305605324e-05, "loss": 0.4575, "step": 6085 }, { "epoch": 1.557824, "grad_norm": 1.9765625, "learning_rate": 2.4042317208429314e-05, "loss": 0.4358, "step": 6086 }, { "epoch": 1.55808, "grad_norm": 1.96875, "learning_rate": 2.4038051360805395e-05, "loss": 0.4619, "step": 6087 }, { "epoch": 1.5583360000000002, "grad_norm": 2.015625, "learning_rate": 2.403378551318147e-05, "loss": 0.4361, "step": 6088 }, { "epoch": 1.558592, "grad_norm": 2.171875, "learning_rate": 2.4029519665557547e-05, "loss": 0.4504, "step": 6089 }, { "epoch": 1.558848, "grad_norm": 2.015625, "learning_rate": 2.4025253817933625e-05, "loss": 0.4617, "step": 6090 }, { "epoch": 1.559104, "grad_norm": 2.109375, "learning_rate": 2.4020987970309703e-05, "loss": 0.4352, "step": 6091 }, { "epoch": 1.5593599999999999, "grad_norm": 2.0, "learning_rate": 2.4016722122685777e-05, "loss": 0.4447, "step": 6092 }, { "epoch": 1.5596160000000001, "grad_norm": 2.078125, "learning_rate": 2.4012456275061858e-05, "loss": 0.4259, "step": 6093 }, { "epoch": 1.559872, "grad_norm": 1.953125, "learning_rate": 2.4008190427437932e-05, "loss": 0.4402, "step": 6094 }, { "epoch": 1.560128, "grad_norm": 2.109375, "learning_rate": 2.400392457981401e-05, "loss": 0.4173, "step": 6095 }, { "epoch": 1.560384, "grad_norm": 1.921875, "learning_rate": 2.3999658732190087e-05, "loss": 0.4361, "step": 6096 }, { "epoch": 1.56064, "grad_norm": 2.03125, "learning_rate": 2.3995392884566165e-05, "loss": 0.4176, "step": 6097 }, { "epoch": 1.560896, "grad_norm": 1.9921875, "learning_rate": 2.399112703694224e-05, "loss": 0.387, "step": 6098 }, { "epoch": 1.5611519999999999, "grad_norm": 2.0625, "learning_rate": 2.3986861189318317e-05, "loss": 0.4659, "step": 6099 }, { "epoch": 1.5614080000000001, "grad_norm": 2.078125, "learning_rate": 2.3982595341694398e-05, "loss": 0.4183, "step": 6100 }, { "epoch": 1.561664, "grad_norm": 2.125, "learning_rate": 2.3978329494070472e-05, "loss": 0.4151, "step": 6101 }, { "epoch": 1.56192, "grad_norm": 1.8671875, "learning_rate": 2.397406364644655e-05, "loss": 0.4709, "step": 6102 }, { "epoch": 1.562176, "grad_norm": 2.015625, "learning_rate": 2.3969797798822628e-05, "loss": 0.4802, "step": 6103 }, { "epoch": 1.562432, "grad_norm": 2.03125, "learning_rate": 2.3965531951198705e-05, "loss": 0.4383, "step": 6104 }, { "epoch": 1.562688, "grad_norm": 2.15625, "learning_rate": 2.396126610357478e-05, "loss": 0.4594, "step": 6105 }, { "epoch": 1.5629439999999999, "grad_norm": 2.078125, "learning_rate": 2.395700025595086e-05, "loss": 0.4305, "step": 6106 }, { "epoch": 1.5632000000000001, "grad_norm": 2.015625, "learning_rate": 2.3952734408326935e-05, "loss": 0.4195, "step": 6107 }, { "epoch": 1.563456, "grad_norm": 1.953125, "learning_rate": 2.3948468560703013e-05, "loss": 0.4569, "step": 6108 }, { "epoch": 1.563712, "grad_norm": 2.0625, "learning_rate": 2.394420271307909e-05, "loss": 0.4114, "step": 6109 }, { "epoch": 1.563968, "grad_norm": 2.203125, "learning_rate": 2.3939936865455168e-05, "loss": 0.4421, "step": 6110 }, { "epoch": 1.5642239999999998, "grad_norm": 1.9921875, "learning_rate": 2.3935671017831242e-05, "loss": 0.4311, "step": 6111 }, { "epoch": 1.56448, "grad_norm": 2.140625, "learning_rate": 2.3931405170207323e-05, "loss": 0.4003, "step": 6112 }, { "epoch": 1.564736, "grad_norm": 2.09375, "learning_rate": 2.3927139322583397e-05, "loss": 0.4521, "step": 6113 }, { "epoch": 1.5649920000000002, "grad_norm": 1.9453125, "learning_rate": 2.3922873474959475e-05, "loss": 0.4311, "step": 6114 }, { "epoch": 1.565248, "grad_norm": 2.140625, "learning_rate": 2.3918607627335553e-05, "loss": 0.4582, "step": 6115 }, { "epoch": 1.565504, "grad_norm": 1.859375, "learning_rate": 2.391434177971163e-05, "loss": 0.417, "step": 6116 }, { "epoch": 1.56576, "grad_norm": 1.984375, "learning_rate": 2.3910075932087708e-05, "loss": 0.4397, "step": 6117 }, { "epoch": 1.5660159999999999, "grad_norm": 2.03125, "learning_rate": 2.3905810084463782e-05, "loss": 0.4858, "step": 6118 }, { "epoch": 1.566272, "grad_norm": 2.1875, "learning_rate": 2.3901544236839863e-05, "loss": 0.4604, "step": 6119 }, { "epoch": 1.566528, "grad_norm": 2.1875, "learning_rate": 2.3897278389215938e-05, "loss": 0.4603, "step": 6120 }, { "epoch": 1.566784, "grad_norm": 1.9765625, "learning_rate": 2.3893012541592015e-05, "loss": 0.4499, "step": 6121 }, { "epoch": 1.56704, "grad_norm": 1.984375, "learning_rate": 2.3888746693968093e-05, "loss": 0.4404, "step": 6122 }, { "epoch": 1.567296, "grad_norm": 2.078125, "learning_rate": 2.388448084634417e-05, "loss": 0.4258, "step": 6123 }, { "epoch": 1.567552, "grad_norm": 2.125, "learning_rate": 2.3880214998720245e-05, "loss": 0.4456, "step": 6124 }, { "epoch": 1.5678079999999999, "grad_norm": 2.09375, "learning_rate": 2.3875949151096326e-05, "loss": 0.4076, "step": 6125 }, { "epoch": 1.5680640000000001, "grad_norm": 2.109375, "learning_rate": 2.38716833034724e-05, "loss": 0.4519, "step": 6126 }, { "epoch": 1.56832, "grad_norm": 1.890625, "learning_rate": 2.3867417455848478e-05, "loss": 0.4568, "step": 6127 }, { "epoch": 1.568576, "grad_norm": 2.15625, "learning_rate": 2.3863151608224555e-05, "loss": 0.431, "step": 6128 }, { "epoch": 1.568832, "grad_norm": 2.125, "learning_rate": 2.3858885760600633e-05, "loss": 0.4226, "step": 6129 }, { "epoch": 1.569088, "grad_norm": 2.078125, "learning_rate": 2.3854619912976707e-05, "loss": 0.4227, "step": 6130 }, { "epoch": 1.569344, "grad_norm": 1.8984375, "learning_rate": 2.385035406535279e-05, "loss": 0.4339, "step": 6131 }, { "epoch": 1.5695999999999999, "grad_norm": 1.984375, "learning_rate": 2.3846088217728866e-05, "loss": 0.4105, "step": 6132 }, { "epoch": 1.5698560000000001, "grad_norm": 2.21875, "learning_rate": 2.384182237010494e-05, "loss": 0.45, "step": 6133 }, { "epoch": 1.570112, "grad_norm": 2.28125, "learning_rate": 2.3837556522481018e-05, "loss": 0.4713, "step": 6134 }, { "epoch": 1.570368, "grad_norm": 2.09375, "learning_rate": 2.3833290674857096e-05, "loss": 0.4346, "step": 6135 }, { "epoch": 1.570624, "grad_norm": 1.9921875, "learning_rate": 2.3829024827233173e-05, "loss": 0.4469, "step": 6136 }, { "epoch": 1.57088, "grad_norm": 1.9609375, "learning_rate": 2.3824758979609248e-05, "loss": 0.4492, "step": 6137 }, { "epoch": 1.571136, "grad_norm": 2.03125, "learning_rate": 2.382049313198533e-05, "loss": 0.4174, "step": 6138 }, { "epoch": 1.571392, "grad_norm": 2.078125, "learning_rate": 2.3816227284361403e-05, "loss": 0.419, "step": 6139 }, { "epoch": 1.5716480000000002, "grad_norm": 2.109375, "learning_rate": 2.381196143673748e-05, "loss": 0.4177, "step": 6140 }, { "epoch": 1.571904, "grad_norm": 2.078125, "learning_rate": 2.3807695589113558e-05, "loss": 0.445, "step": 6141 }, { "epoch": 1.57216, "grad_norm": 1.921875, "learning_rate": 2.3803429741489636e-05, "loss": 0.4281, "step": 6142 }, { "epoch": 1.572416, "grad_norm": 2.046875, "learning_rate": 2.379916389386571e-05, "loss": 0.4503, "step": 6143 }, { "epoch": 1.5726719999999998, "grad_norm": 2.328125, "learning_rate": 2.379489804624179e-05, "loss": 0.4506, "step": 6144 }, { "epoch": 1.572928, "grad_norm": 2.125, "learning_rate": 2.3790632198617865e-05, "loss": 0.4068, "step": 6145 }, { "epoch": 1.573184, "grad_norm": 2.078125, "learning_rate": 2.3786366350993943e-05, "loss": 0.4558, "step": 6146 }, { "epoch": 1.57344, "grad_norm": 1.9375, "learning_rate": 2.378210050337002e-05, "loss": 0.4772, "step": 6147 }, { "epoch": 1.573696, "grad_norm": 1.921875, "learning_rate": 2.37778346557461e-05, "loss": 0.447, "step": 6148 }, { "epoch": 1.573952, "grad_norm": 2.109375, "learning_rate": 2.3773568808122176e-05, "loss": 0.4263, "step": 6149 }, { "epoch": 1.574208, "grad_norm": 2.265625, "learning_rate": 2.376930296049825e-05, "loss": 0.4496, "step": 6150 }, { "epoch": 1.5744639999999999, "grad_norm": 2.140625, "learning_rate": 2.376503711287433e-05, "loss": 0.4269, "step": 6151 }, { "epoch": 1.5747200000000001, "grad_norm": 1.859375, "learning_rate": 2.3760771265250406e-05, "loss": 0.4564, "step": 6152 }, { "epoch": 1.574976, "grad_norm": 2.046875, "learning_rate": 2.3756505417626483e-05, "loss": 0.4419, "step": 6153 }, { "epoch": 1.575232, "grad_norm": 2.015625, "learning_rate": 2.375223957000256e-05, "loss": 0.4689, "step": 6154 }, { "epoch": 1.575488, "grad_norm": 1.984375, "learning_rate": 2.374797372237864e-05, "loss": 0.4319, "step": 6155 }, { "epoch": 1.575744, "grad_norm": 2.046875, "learning_rate": 2.3743707874754713e-05, "loss": 0.4225, "step": 6156 }, { "epoch": 1.576, "grad_norm": 2.125, "learning_rate": 2.3739442027130794e-05, "loss": 0.4727, "step": 6157 }, { "epoch": 1.5762559999999999, "grad_norm": 2.125, "learning_rate": 2.3735176179506868e-05, "loss": 0.4301, "step": 6158 }, { "epoch": 1.5765120000000001, "grad_norm": 2.046875, "learning_rate": 2.3730910331882946e-05, "loss": 0.3807, "step": 6159 }, { "epoch": 1.576768, "grad_norm": 2.1875, "learning_rate": 2.3726644484259024e-05, "loss": 0.4539, "step": 6160 }, { "epoch": 1.577024, "grad_norm": 2.203125, "learning_rate": 2.37223786366351e-05, "loss": 0.4258, "step": 6161 }, { "epoch": 1.57728, "grad_norm": 2.234375, "learning_rate": 2.3718112789011175e-05, "loss": 0.4455, "step": 6162 }, { "epoch": 1.577536, "grad_norm": 2.015625, "learning_rate": 2.3713846941387256e-05, "loss": 0.4226, "step": 6163 }, { "epoch": 1.577792, "grad_norm": 1.8671875, "learning_rate": 2.370958109376333e-05, "loss": 0.4375, "step": 6164 }, { "epoch": 1.578048, "grad_norm": 1.984375, "learning_rate": 2.370531524613941e-05, "loss": 0.4337, "step": 6165 }, { "epoch": 1.5783040000000002, "grad_norm": 2.0625, "learning_rate": 2.3701049398515486e-05, "loss": 0.4549, "step": 6166 }, { "epoch": 1.57856, "grad_norm": 2.140625, "learning_rate": 2.3696783550891564e-05, "loss": 0.4261, "step": 6167 }, { "epoch": 1.578816, "grad_norm": 2.015625, "learning_rate": 2.369251770326764e-05, "loss": 0.4484, "step": 6168 }, { "epoch": 1.579072, "grad_norm": 2.015625, "learning_rate": 2.3688251855643716e-05, "loss": 0.4071, "step": 6169 }, { "epoch": 1.5793279999999998, "grad_norm": 1.921875, "learning_rate": 2.3683986008019797e-05, "loss": 0.434, "step": 6170 }, { "epoch": 1.579584, "grad_norm": 2.109375, "learning_rate": 2.367972016039587e-05, "loss": 0.4681, "step": 6171 }, { "epoch": 1.57984, "grad_norm": 2.0, "learning_rate": 2.367545431277195e-05, "loss": 0.4119, "step": 6172 }, { "epoch": 1.580096, "grad_norm": 2.078125, "learning_rate": 2.3671188465148026e-05, "loss": 0.4339, "step": 6173 }, { "epoch": 1.580352, "grad_norm": 2.015625, "learning_rate": 2.3666922617524104e-05, "loss": 0.4456, "step": 6174 }, { "epoch": 1.580608, "grad_norm": 2.265625, "learning_rate": 2.3662656769900178e-05, "loss": 0.4549, "step": 6175 }, { "epoch": 1.580864, "grad_norm": 2.1875, "learning_rate": 2.365839092227626e-05, "loss": 0.4273, "step": 6176 }, { "epoch": 1.5811199999999999, "grad_norm": 2.203125, "learning_rate": 2.3654125074652333e-05, "loss": 0.4576, "step": 6177 }, { "epoch": 1.5813760000000001, "grad_norm": 1.9921875, "learning_rate": 2.364985922702841e-05, "loss": 0.406, "step": 6178 }, { "epoch": 1.581632, "grad_norm": 2.0625, "learning_rate": 2.364559337940449e-05, "loss": 0.4317, "step": 6179 }, { "epoch": 1.581888, "grad_norm": 1.8828125, "learning_rate": 2.3641327531780566e-05, "loss": 0.4279, "step": 6180 }, { "epoch": 1.582144, "grad_norm": 1.9296875, "learning_rate": 2.363706168415664e-05, "loss": 0.4649, "step": 6181 }, { "epoch": 1.5824, "grad_norm": 1.953125, "learning_rate": 2.3632795836532722e-05, "loss": 0.4459, "step": 6182 }, { "epoch": 1.582656, "grad_norm": 2.03125, "learning_rate": 2.36285299889088e-05, "loss": 0.4201, "step": 6183 }, { "epoch": 1.5829119999999999, "grad_norm": 2.0, "learning_rate": 2.3624264141284874e-05, "loss": 0.4528, "step": 6184 }, { "epoch": 1.5831680000000001, "grad_norm": 2.015625, "learning_rate": 2.361999829366095e-05, "loss": 0.4326, "step": 6185 }, { "epoch": 1.583424, "grad_norm": 2.109375, "learning_rate": 2.361573244603703e-05, "loss": 0.4369, "step": 6186 }, { "epoch": 1.58368, "grad_norm": 1.96875, "learning_rate": 2.3611466598413107e-05, "loss": 0.4348, "step": 6187 }, { "epoch": 1.583936, "grad_norm": 2.0625, "learning_rate": 2.360720075078918e-05, "loss": 0.436, "step": 6188 }, { "epoch": 1.584192, "grad_norm": 2.15625, "learning_rate": 2.3602934903165262e-05, "loss": 0.4774, "step": 6189 }, { "epoch": 1.584448, "grad_norm": 1.9296875, "learning_rate": 2.3598669055541336e-05, "loss": 0.429, "step": 6190 }, { "epoch": 1.584704, "grad_norm": 2.03125, "learning_rate": 2.3594403207917414e-05, "loss": 0.4279, "step": 6191 }, { "epoch": 1.5849600000000001, "grad_norm": 2.046875, "learning_rate": 2.359013736029349e-05, "loss": 0.4727, "step": 6192 }, { "epoch": 1.585216, "grad_norm": 2.15625, "learning_rate": 2.358587151266957e-05, "loss": 0.4067, "step": 6193 }, { "epoch": 1.585472, "grad_norm": 1.9375, "learning_rate": 2.3581605665045643e-05, "loss": 0.4581, "step": 6194 }, { "epoch": 1.585728, "grad_norm": 1.9296875, "learning_rate": 2.3577339817421724e-05, "loss": 0.4472, "step": 6195 }, { "epoch": 1.5859839999999998, "grad_norm": 2.125, "learning_rate": 2.35730739697978e-05, "loss": 0.4335, "step": 6196 }, { "epoch": 1.58624, "grad_norm": 2.03125, "learning_rate": 2.3568808122173876e-05, "loss": 0.4566, "step": 6197 }, { "epoch": 1.586496, "grad_norm": 2.0625, "learning_rate": 2.3564542274549954e-05, "loss": 0.4272, "step": 6198 }, { "epoch": 1.5867520000000002, "grad_norm": 1.9375, "learning_rate": 2.3560276426926032e-05, "loss": 0.4322, "step": 6199 }, { "epoch": 1.587008, "grad_norm": 2.078125, "learning_rate": 2.355601057930211e-05, "loss": 0.4051, "step": 6200 }, { "epoch": 1.587264, "grad_norm": 1.890625, "learning_rate": 2.3551744731678184e-05, "loss": 0.4162, "step": 6201 }, { "epoch": 1.58752, "grad_norm": 2.046875, "learning_rate": 2.3547478884054265e-05, "loss": 0.4288, "step": 6202 }, { "epoch": 1.5877759999999999, "grad_norm": 1.9921875, "learning_rate": 2.354321303643034e-05, "loss": 0.4477, "step": 6203 }, { "epoch": 1.588032, "grad_norm": 1.9296875, "learning_rate": 2.3538947188806417e-05, "loss": 0.4472, "step": 6204 }, { "epoch": 1.588288, "grad_norm": 2.046875, "learning_rate": 2.3534681341182494e-05, "loss": 0.4488, "step": 6205 }, { "epoch": 1.588544, "grad_norm": 2.03125, "learning_rate": 2.3530415493558572e-05, "loss": 0.457, "step": 6206 }, { "epoch": 1.5888, "grad_norm": 1.9921875, "learning_rate": 2.3526149645934646e-05, "loss": 0.4159, "step": 6207 }, { "epoch": 1.589056, "grad_norm": 2.03125, "learning_rate": 2.3521883798310727e-05, "loss": 0.4579, "step": 6208 }, { "epoch": 1.589312, "grad_norm": 1.9921875, "learning_rate": 2.35176179506868e-05, "loss": 0.4653, "step": 6209 }, { "epoch": 1.5895679999999999, "grad_norm": 1.9609375, "learning_rate": 2.351335210306288e-05, "loss": 0.4665, "step": 6210 }, { "epoch": 1.5898240000000001, "grad_norm": 2.203125, "learning_rate": 2.3509086255438957e-05, "loss": 0.4216, "step": 6211 }, { "epoch": 1.59008, "grad_norm": 1.90625, "learning_rate": 2.3504820407815034e-05, "loss": 0.4626, "step": 6212 }, { "epoch": 1.590336, "grad_norm": 1.90625, "learning_rate": 2.350055456019111e-05, "loss": 0.4385, "step": 6213 }, { "epoch": 1.590592, "grad_norm": 2.140625, "learning_rate": 2.349628871256719e-05, "loss": 0.4216, "step": 6214 }, { "epoch": 1.590848, "grad_norm": 2.203125, "learning_rate": 2.3492022864943267e-05, "loss": 0.4354, "step": 6215 }, { "epoch": 1.591104, "grad_norm": 1.890625, "learning_rate": 2.348775701731934e-05, "loss": 0.4485, "step": 6216 }, { "epoch": 1.5913599999999999, "grad_norm": 1.9921875, "learning_rate": 2.348349116969542e-05, "loss": 0.4244, "step": 6217 }, { "epoch": 1.5916160000000001, "grad_norm": 1.96875, "learning_rate": 2.3479225322071497e-05, "loss": 0.4414, "step": 6218 }, { "epoch": 1.591872, "grad_norm": 1.96875, "learning_rate": 2.3474959474447575e-05, "loss": 0.4568, "step": 6219 }, { "epoch": 1.592128, "grad_norm": 1.984375, "learning_rate": 2.347069362682365e-05, "loss": 0.4108, "step": 6220 }, { "epoch": 1.592384, "grad_norm": 2.015625, "learning_rate": 2.346642777919973e-05, "loss": 0.4531, "step": 6221 }, { "epoch": 1.5926399999999998, "grad_norm": 1.96875, "learning_rate": 2.3462161931575804e-05, "loss": 0.4656, "step": 6222 }, { "epoch": 1.592896, "grad_norm": 2.28125, "learning_rate": 2.3457896083951882e-05, "loss": 0.3861, "step": 6223 }, { "epoch": 1.593152, "grad_norm": 1.984375, "learning_rate": 2.345363023632796e-05, "loss": 0.4219, "step": 6224 }, { "epoch": 1.5934080000000002, "grad_norm": 2.015625, "learning_rate": 2.3449364388704037e-05, "loss": 0.4388, "step": 6225 }, { "epoch": 1.593664, "grad_norm": 2.140625, "learning_rate": 2.344509854108011e-05, "loss": 0.4337, "step": 6226 }, { "epoch": 1.59392, "grad_norm": 2.3125, "learning_rate": 2.3440832693456192e-05, "loss": 0.4479, "step": 6227 }, { "epoch": 1.594176, "grad_norm": 1.9453125, "learning_rate": 2.3436566845832267e-05, "loss": 0.458, "step": 6228 }, { "epoch": 1.5944319999999998, "grad_norm": 1.953125, "learning_rate": 2.3432300998208344e-05, "loss": 0.4613, "step": 6229 }, { "epoch": 1.594688, "grad_norm": 2.0625, "learning_rate": 2.3428035150584422e-05, "loss": 0.4549, "step": 6230 }, { "epoch": 1.594944, "grad_norm": 2.0625, "learning_rate": 2.34237693029605e-05, "loss": 0.453, "step": 6231 }, { "epoch": 1.5952, "grad_norm": 1.953125, "learning_rate": 2.3419503455336577e-05, "loss": 0.4394, "step": 6232 }, { "epoch": 1.595456, "grad_norm": 2.1875, "learning_rate": 2.3415237607712655e-05, "loss": 0.4368, "step": 6233 }, { "epoch": 1.595712, "grad_norm": 1.9609375, "learning_rate": 2.3410971760088733e-05, "loss": 0.4393, "step": 6234 }, { "epoch": 1.595968, "grad_norm": 2.109375, "learning_rate": 2.3406705912464807e-05, "loss": 0.4401, "step": 6235 }, { "epoch": 1.5962239999999999, "grad_norm": 2.046875, "learning_rate": 2.3402440064840885e-05, "loss": 0.4419, "step": 6236 }, { "epoch": 1.5964800000000001, "grad_norm": 1.9453125, "learning_rate": 2.3398174217216962e-05, "loss": 0.4694, "step": 6237 }, { "epoch": 1.596736, "grad_norm": 2.203125, "learning_rate": 2.339390836959304e-05, "loss": 0.4361, "step": 6238 }, { "epoch": 1.596992, "grad_norm": 2.0, "learning_rate": 2.3389642521969114e-05, "loss": 0.4334, "step": 6239 }, { "epoch": 1.597248, "grad_norm": 2.078125, "learning_rate": 2.3385376674345195e-05, "loss": 0.4253, "step": 6240 }, { "epoch": 1.597504, "grad_norm": 2.09375, "learning_rate": 2.338111082672127e-05, "loss": 0.4318, "step": 6241 }, { "epoch": 1.59776, "grad_norm": 1.9921875, "learning_rate": 2.3376844979097347e-05, "loss": 0.4557, "step": 6242 }, { "epoch": 1.5980159999999999, "grad_norm": 2.046875, "learning_rate": 2.3372579131473425e-05, "loss": 0.4373, "step": 6243 }, { "epoch": 1.5982720000000001, "grad_norm": 2.03125, "learning_rate": 2.3368313283849502e-05, "loss": 0.4826, "step": 6244 }, { "epoch": 1.598528, "grad_norm": 1.8984375, "learning_rate": 2.3364047436225577e-05, "loss": 0.4024, "step": 6245 }, { "epoch": 1.598784, "grad_norm": 1.8828125, "learning_rate": 2.3359781588601658e-05, "loss": 0.455, "step": 6246 }, { "epoch": 1.59904, "grad_norm": 1.9375, "learning_rate": 2.3355515740977735e-05, "loss": 0.4832, "step": 6247 }, { "epoch": 1.599296, "grad_norm": 1.96875, "learning_rate": 2.335124989335381e-05, "loss": 0.4253, "step": 6248 }, { "epoch": 1.599552, "grad_norm": 1.96875, "learning_rate": 2.3346984045729887e-05, "loss": 0.4768, "step": 6249 }, { "epoch": 1.599808, "grad_norm": 2.078125, "learning_rate": 2.3342718198105965e-05, "loss": 0.4209, "step": 6250 }, { "epoch": 1.6000640000000002, "grad_norm": 2.046875, "learning_rate": 2.3338452350482043e-05, "loss": 0.4193, "step": 6251 }, { "epoch": 1.60032, "grad_norm": 1.9765625, "learning_rate": 2.3334186502858117e-05, "loss": 0.4128, "step": 6252 }, { "epoch": 1.600576, "grad_norm": 1.9453125, "learning_rate": 2.3329920655234198e-05, "loss": 0.4471, "step": 6253 }, { "epoch": 1.600832, "grad_norm": 1.90625, "learning_rate": 2.3325654807610272e-05, "loss": 0.4381, "step": 6254 }, { "epoch": 1.6010879999999998, "grad_norm": 2.046875, "learning_rate": 2.332138895998635e-05, "loss": 0.4472, "step": 6255 }, { "epoch": 1.601344, "grad_norm": 1.9375, "learning_rate": 2.3317123112362428e-05, "loss": 0.4494, "step": 6256 }, { "epoch": 1.6016, "grad_norm": 2.078125, "learning_rate": 2.3312857264738505e-05, "loss": 0.4074, "step": 6257 }, { "epoch": 1.601856, "grad_norm": 1.921875, "learning_rate": 2.330859141711458e-05, "loss": 0.4359, "step": 6258 }, { "epoch": 1.602112, "grad_norm": 1.9921875, "learning_rate": 2.330432556949066e-05, "loss": 0.4403, "step": 6259 }, { "epoch": 1.602368, "grad_norm": 2.015625, "learning_rate": 2.3300059721866735e-05, "loss": 0.4683, "step": 6260 }, { "epoch": 1.602624, "grad_norm": 1.96875, "learning_rate": 2.3295793874242812e-05, "loss": 0.4572, "step": 6261 }, { "epoch": 1.6028799999999999, "grad_norm": 2.109375, "learning_rate": 2.329152802661889e-05, "loss": 0.4409, "step": 6262 }, { "epoch": 1.6031360000000001, "grad_norm": 2.078125, "learning_rate": 2.3287262178994968e-05, "loss": 0.382, "step": 6263 }, { "epoch": 1.603392, "grad_norm": 2.046875, "learning_rate": 2.3282996331371045e-05, "loss": 0.4262, "step": 6264 }, { "epoch": 1.603648, "grad_norm": 2.09375, "learning_rate": 2.3278730483747123e-05, "loss": 0.4341, "step": 6265 }, { "epoch": 1.603904, "grad_norm": 2.046875, "learning_rate": 2.32744646361232e-05, "loss": 0.4495, "step": 6266 }, { "epoch": 1.60416, "grad_norm": 1.96875, "learning_rate": 2.3270198788499275e-05, "loss": 0.4282, "step": 6267 }, { "epoch": 1.604416, "grad_norm": 2.078125, "learning_rate": 2.3265932940875353e-05, "loss": 0.4462, "step": 6268 }, { "epoch": 1.6046719999999999, "grad_norm": 1.984375, "learning_rate": 2.326166709325143e-05, "loss": 0.4809, "step": 6269 }, { "epoch": 1.6049280000000001, "grad_norm": 1.921875, "learning_rate": 2.3257401245627508e-05, "loss": 0.485, "step": 6270 }, { "epoch": 1.605184, "grad_norm": 2.078125, "learning_rate": 2.3253135398003582e-05, "loss": 0.4279, "step": 6271 }, { "epoch": 1.60544, "grad_norm": 2.09375, "learning_rate": 2.3248869550379663e-05, "loss": 0.4433, "step": 6272 }, { "epoch": 1.605696, "grad_norm": 1.953125, "learning_rate": 2.3244603702755737e-05, "loss": 0.4469, "step": 6273 }, { "epoch": 1.605952, "grad_norm": 2.0625, "learning_rate": 2.3240337855131815e-05, "loss": 0.4578, "step": 6274 }, { "epoch": 1.606208, "grad_norm": 2.046875, "learning_rate": 2.3236072007507893e-05, "loss": 0.4223, "step": 6275 }, { "epoch": 1.606464, "grad_norm": 1.921875, "learning_rate": 2.323180615988397e-05, "loss": 0.4586, "step": 6276 }, { "epoch": 1.6067200000000001, "grad_norm": 1.9765625, "learning_rate": 2.3227540312260045e-05, "loss": 0.4291, "step": 6277 }, { "epoch": 1.606976, "grad_norm": 1.9453125, "learning_rate": 2.3223274464636126e-05, "loss": 0.444, "step": 6278 }, { "epoch": 1.607232, "grad_norm": 2.03125, "learning_rate": 2.32190086170122e-05, "loss": 0.4483, "step": 6279 }, { "epoch": 1.607488, "grad_norm": 1.875, "learning_rate": 2.3214742769388278e-05, "loss": 0.457, "step": 6280 }, { "epoch": 1.6077439999999998, "grad_norm": 2.046875, "learning_rate": 2.3210476921764355e-05, "loss": 0.4478, "step": 6281 }, { "epoch": 1.608, "grad_norm": 1.9765625, "learning_rate": 2.3206211074140433e-05, "loss": 0.4628, "step": 6282 }, { "epoch": 1.608256, "grad_norm": 2.046875, "learning_rate": 2.320194522651651e-05, "loss": 0.4004, "step": 6283 }, { "epoch": 1.6085120000000002, "grad_norm": 1.9921875, "learning_rate": 2.3197679378892588e-05, "loss": 0.4098, "step": 6284 }, { "epoch": 1.608768, "grad_norm": 1.9921875, "learning_rate": 2.3193413531268666e-05, "loss": 0.4583, "step": 6285 }, { "epoch": 1.609024, "grad_norm": 1.859375, "learning_rate": 2.318914768364474e-05, "loss": 0.4473, "step": 6286 }, { "epoch": 1.60928, "grad_norm": 1.8828125, "learning_rate": 2.3184881836020818e-05, "loss": 0.4606, "step": 6287 }, { "epoch": 1.6095359999999999, "grad_norm": 2.03125, "learning_rate": 2.3180615988396896e-05, "loss": 0.4544, "step": 6288 }, { "epoch": 1.6097920000000001, "grad_norm": 2.078125, "learning_rate": 2.3176350140772973e-05, "loss": 0.4479, "step": 6289 }, { "epoch": 1.610048, "grad_norm": 2.03125, "learning_rate": 2.3172084293149047e-05, "loss": 0.4622, "step": 6290 }, { "epoch": 1.610304, "grad_norm": 1.9765625, "learning_rate": 2.316781844552513e-05, "loss": 0.3981, "step": 6291 }, { "epoch": 1.61056, "grad_norm": 1.96875, "learning_rate": 2.3163552597901203e-05, "loss": 0.4371, "step": 6292 }, { "epoch": 1.610816, "grad_norm": 2.0, "learning_rate": 2.315928675027728e-05, "loss": 0.42, "step": 6293 }, { "epoch": 1.611072, "grad_norm": 1.7734375, "learning_rate": 2.3155020902653358e-05, "loss": 0.4587, "step": 6294 }, { "epoch": 1.6113279999999999, "grad_norm": 2.0, "learning_rate": 2.3150755055029436e-05, "loss": 0.4757, "step": 6295 }, { "epoch": 1.6115840000000001, "grad_norm": 2.046875, "learning_rate": 2.3146489207405513e-05, "loss": 0.4341, "step": 6296 }, { "epoch": 1.61184, "grad_norm": 2.015625, "learning_rate": 2.314222335978159e-05, "loss": 0.4562, "step": 6297 }, { "epoch": 1.612096, "grad_norm": 2.015625, "learning_rate": 2.313795751215767e-05, "loss": 0.4419, "step": 6298 }, { "epoch": 1.612352, "grad_norm": 1.984375, "learning_rate": 2.3133691664533743e-05, "loss": 0.4489, "step": 6299 }, { "epoch": 1.612608, "grad_norm": 2.0, "learning_rate": 2.312942581690982e-05, "loss": 0.406, "step": 6300 }, { "epoch": 1.612864, "grad_norm": 1.9609375, "learning_rate": 2.3125159969285898e-05, "loss": 0.4552, "step": 6301 }, { "epoch": 1.6131199999999999, "grad_norm": 2.03125, "learning_rate": 2.3120894121661976e-05, "loss": 0.4602, "step": 6302 }, { "epoch": 1.6133760000000001, "grad_norm": 1.8828125, "learning_rate": 2.3116628274038054e-05, "loss": 0.4488, "step": 6303 }, { "epoch": 1.613632, "grad_norm": 1.984375, "learning_rate": 2.311236242641413e-05, "loss": 0.4271, "step": 6304 }, { "epoch": 1.613888, "grad_norm": 1.9140625, "learning_rate": 2.3108096578790205e-05, "loss": 0.4565, "step": 6305 }, { "epoch": 1.614144, "grad_norm": 1.9375, "learning_rate": 2.3103830731166283e-05, "loss": 0.4231, "step": 6306 }, { "epoch": 1.6143999999999998, "grad_norm": 2.078125, "learning_rate": 2.309956488354236e-05, "loss": 0.3917, "step": 6307 }, { "epoch": 1.614656, "grad_norm": 2.140625, "learning_rate": 2.309529903591844e-05, "loss": 0.4282, "step": 6308 }, { "epoch": 1.614912, "grad_norm": 2.21875, "learning_rate": 2.3091033188294513e-05, "loss": 0.4446, "step": 6309 }, { "epoch": 1.6151680000000002, "grad_norm": 2.203125, "learning_rate": 2.3086767340670594e-05, "loss": 0.438, "step": 6310 }, { "epoch": 1.615424, "grad_norm": 1.8515625, "learning_rate": 2.3082501493046668e-05, "loss": 0.4134, "step": 6311 }, { "epoch": 1.61568, "grad_norm": 2.28125, "learning_rate": 2.3078235645422746e-05, "loss": 0.446, "step": 6312 }, { "epoch": 1.615936, "grad_norm": 2.25, "learning_rate": 2.3073969797798827e-05, "loss": 0.431, "step": 6313 }, { "epoch": 1.6161919999999999, "grad_norm": 2.140625, "learning_rate": 2.30697039501749e-05, "loss": 0.4788, "step": 6314 }, { "epoch": 1.616448, "grad_norm": 2.03125, "learning_rate": 2.306543810255098e-05, "loss": 0.4063, "step": 6315 }, { "epoch": 1.616704, "grad_norm": 2.046875, "learning_rate": 2.3061172254927056e-05, "loss": 0.4272, "step": 6316 }, { "epoch": 1.61696, "grad_norm": 2.125, "learning_rate": 2.3056906407303134e-05, "loss": 0.4155, "step": 6317 }, { "epoch": 1.617216, "grad_norm": 2.0, "learning_rate": 2.3052640559679208e-05, "loss": 0.4053, "step": 6318 }, { "epoch": 1.617472, "grad_norm": 1.9765625, "learning_rate": 2.3048374712055286e-05, "loss": 0.4109, "step": 6319 }, { "epoch": 1.617728, "grad_norm": 1.8671875, "learning_rate": 2.3044108864431364e-05, "loss": 0.472, "step": 6320 }, { "epoch": 1.6179839999999999, "grad_norm": 1.734375, "learning_rate": 2.303984301680744e-05, "loss": 0.434, "step": 6321 }, { "epoch": 1.6182400000000001, "grad_norm": 2.0, "learning_rate": 2.3035577169183515e-05, "loss": 0.4182, "step": 6322 }, { "epoch": 1.618496, "grad_norm": 2.03125, "learning_rate": 2.3031311321559596e-05, "loss": 0.4064, "step": 6323 }, { "epoch": 1.618752, "grad_norm": 2.078125, "learning_rate": 2.302704547393567e-05, "loss": 0.3849, "step": 6324 }, { "epoch": 1.619008, "grad_norm": 1.8984375, "learning_rate": 2.302277962631175e-05, "loss": 0.4404, "step": 6325 }, { "epoch": 1.619264, "grad_norm": 1.9453125, "learning_rate": 2.3018513778687826e-05, "loss": 0.4476, "step": 6326 }, { "epoch": 1.61952, "grad_norm": 2.09375, "learning_rate": 2.3014247931063904e-05, "loss": 0.4046, "step": 6327 }, { "epoch": 1.6197759999999999, "grad_norm": 1.9609375, "learning_rate": 2.3009982083439978e-05, "loss": 0.4307, "step": 6328 }, { "epoch": 1.6200320000000001, "grad_norm": 1.9296875, "learning_rate": 2.300571623581606e-05, "loss": 0.4071, "step": 6329 }, { "epoch": 1.620288, "grad_norm": 1.859375, "learning_rate": 2.3001450388192137e-05, "loss": 0.4578, "step": 6330 }, { "epoch": 1.620544, "grad_norm": 2.078125, "learning_rate": 2.299718454056821e-05, "loss": 0.4624, "step": 6331 }, { "epoch": 1.6208, "grad_norm": 2.015625, "learning_rate": 2.299291869294429e-05, "loss": 0.429, "step": 6332 }, { "epoch": 1.621056, "grad_norm": 1.96875, "learning_rate": 2.2988652845320366e-05, "loss": 0.4248, "step": 6333 }, { "epoch": 1.621312, "grad_norm": 1.9765625, "learning_rate": 2.2984386997696444e-05, "loss": 0.438, "step": 6334 }, { "epoch": 1.621568, "grad_norm": 1.953125, "learning_rate": 2.298012115007252e-05, "loss": 0.4257, "step": 6335 }, { "epoch": 1.6218240000000002, "grad_norm": 2.15625, "learning_rate": 2.29758553024486e-05, "loss": 0.4058, "step": 6336 }, { "epoch": 1.62208, "grad_norm": 2.140625, "learning_rate": 2.2971589454824673e-05, "loss": 0.4208, "step": 6337 }, { "epoch": 1.622336, "grad_norm": 2.0, "learning_rate": 2.296732360720075e-05, "loss": 0.4429, "step": 6338 }, { "epoch": 1.622592, "grad_norm": 2.0, "learning_rate": 2.296305775957683e-05, "loss": 0.4231, "step": 6339 }, { "epoch": 1.6228479999999998, "grad_norm": 1.921875, "learning_rate": 2.2958791911952906e-05, "loss": 0.4138, "step": 6340 }, { "epoch": 1.623104, "grad_norm": 2.0625, "learning_rate": 2.295452606432898e-05, "loss": 0.4324, "step": 6341 }, { "epoch": 1.62336, "grad_norm": 2.03125, "learning_rate": 2.2950260216705062e-05, "loss": 0.4428, "step": 6342 }, { "epoch": 1.623616, "grad_norm": 2.109375, "learning_rate": 2.2945994369081136e-05, "loss": 0.4499, "step": 6343 }, { "epoch": 1.623872, "grad_norm": 2.015625, "learning_rate": 2.2941728521457214e-05, "loss": 0.4394, "step": 6344 }, { "epoch": 1.624128, "grad_norm": 2.0, "learning_rate": 2.293746267383329e-05, "loss": 0.445, "step": 6345 }, { "epoch": 1.624384, "grad_norm": 2.046875, "learning_rate": 2.293319682620937e-05, "loss": 0.4266, "step": 6346 }, { "epoch": 1.6246399999999999, "grad_norm": 1.9765625, "learning_rate": 2.2928930978585447e-05, "loss": 0.4429, "step": 6347 }, { "epoch": 1.6248960000000001, "grad_norm": 2.03125, "learning_rate": 2.2924665130961524e-05, "loss": 0.4294, "step": 6348 }, { "epoch": 1.625152, "grad_norm": 1.921875, "learning_rate": 2.2920399283337602e-05, "loss": 0.4119, "step": 6349 }, { "epoch": 1.625408, "grad_norm": 1.9921875, "learning_rate": 2.2916133435713676e-05, "loss": 0.4016, "step": 6350 }, { "epoch": 1.625664, "grad_norm": 1.9140625, "learning_rate": 2.2911867588089754e-05, "loss": 0.4054, "step": 6351 }, { "epoch": 1.62592, "grad_norm": 1.9375, "learning_rate": 2.290760174046583e-05, "loss": 0.4469, "step": 6352 }, { "epoch": 1.626176, "grad_norm": 2.015625, "learning_rate": 2.290333589284191e-05, "loss": 0.4559, "step": 6353 }, { "epoch": 1.6264319999999999, "grad_norm": 2.015625, "learning_rate": 2.2899070045217987e-05, "loss": 0.4193, "step": 6354 }, { "epoch": 1.6266880000000001, "grad_norm": 1.9140625, "learning_rate": 2.2894804197594064e-05, "loss": 0.4753, "step": 6355 }, { "epoch": 1.626944, "grad_norm": 2.03125, "learning_rate": 2.289053834997014e-05, "loss": 0.4339, "step": 6356 }, { "epoch": 1.6272, "grad_norm": 1.9453125, "learning_rate": 2.2886272502346216e-05, "loss": 0.4306, "step": 6357 }, { "epoch": 1.627456, "grad_norm": 2.15625, "learning_rate": 2.2882006654722294e-05, "loss": 0.4455, "step": 6358 }, { "epoch": 1.627712, "grad_norm": 1.9140625, "learning_rate": 2.2877740807098372e-05, "loss": 0.3987, "step": 6359 }, { "epoch": 1.627968, "grad_norm": 2.03125, "learning_rate": 2.2873474959474446e-05, "loss": 0.4352, "step": 6360 }, { "epoch": 1.628224, "grad_norm": 1.953125, "learning_rate": 2.2869209111850527e-05, "loss": 0.44, "step": 6361 }, { "epoch": 1.6284800000000001, "grad_norm": 1.9375, "learning_rate": 2.2864943264226605e-05, "loss": 0.4265, "step": 6362 }, { "epoch": 1.628736, "grad_norm": 2.03125, "learning_rate": 2.286067741660268e-05, "loss": 0.4436, "step": 6363 }, { "epoch": 1.628992, "grad_norm": 2.0625, "learning_rate": 2.285641156897876e-05, "loss": 0.4324, "step": 6364 }, { "epoch": 1.629248, "grad_norm": 2.03125, "learning_rate": 2.2852145721354834e-05, "loss": 0.4399, "step": 6365 }, { "epoch": 1.6295039999999998, "grad_norm": 1.8984375, "learning_rate": 2.2847879873730912e-05, "loss": 0.4256, "step": 6366 }, { "epoch": 1.62976, "grad_norm": 1.8515625, "learning_rate": 2.284361402610699e-05, "loss": 0.4651, "step": 6367 }, { "epoch": 1.630016, "grad_norm": 1.7421875, "learning_rate": 2.2839348178483067e-05, "loss": 0.4495, "step": 6368 }, { "epoch": 1.6302720000000002, "grad_norm": 2.046875, "learning_rate": 2.283508233085914e-05, "loss": 0.439, "step": 6369 }, { "epoch": 1.630528, "grad_norm": 2.0625, "learning_rate": 2.283081648323522e-05, "loss": 0.4577, "step": 6370 }, { "epoch": 1.630784, "grad_norm": 2.015625, "learning_rate": 2.2826550635611297e-05, "loss": 0.4613, "step": 6371 }, { "epoch": 1.63104, "grad_norm": 1.9296875, "learning_rate": 2.2822284787987374e-05, "loss": 0.4143, "step": 6372 }, { "epoch": 1.6312959999999999, "grad_norm": 2.015625, "learning_rate": 2.281801894036345e-05, "loss": 0.4308, "step": 6373 }, { "epoch": 1.6315520000000001, "grad_norm": 2.078125, "learning_rate": 2.281375309273953e-05, "loss": 0.4346, "step": 6374 }, { "epoch": 1.631808, "grad_norm": 1.796875, "learning_rate": 2.2809487245115604e-05, "loss": 0.4537, "step": 6375 }, { "epoch": 1.632064, "grad_norm": 2.09375, "learning_rate": 2.280522139749168e-05, "loss": 0.4135, "step": 6376 }, { "epoch": 1.63232, "grad_norm": 1.9296875, "learning_rate": 2.280095554986776e-05, "loss": 0.4322, "step": 6377 }, { "epoch": 1.632576, "grad_norm": 2.125, "learning_rate": 2.2796689702243837e-05, "loss": 0.4405, "step": 6378 }, { "epoch": 1.632832, "grad_norm": 2.125, "learning_rate": 2.2792423854619915e-05, "loss": 0.4021, "step": 6379 }, { "epoch": 1.6330879999999999, "grad_norm": 1.9296875, "learning_rate": 2.2788158006995992e-05, "loss": 0.4197, "step": 6380 }, { "epoch": 1.6333440000000001, "grad_norm": 2.078125, "learning_rate": 2.278389215937207e-05, "loss": 0.4641, "step": 6381 }, { "epoch": 1.6336, "grad_norm": 1.9375, "learning_rate": 2.2779626311748144e-05, "loss": 0.4161, "step": 6382 }, { "epoch": 1.633856, "grad_norm": 1.96875, "learning_rate": 2.2775360464124222e-05, "loss": 0.4813, "step": 6383 }, { "epoch": 1.634112, "grad_norm": 2.0625, "learning_rate": 2.27710946165003e-05, "loss": 0.4047, "step": 6384 }, { "epoch": 1.634368, "grad_norm": 2.0, "learning_rate": 2.2766828768876377e-05, "loss": 0.4211, "step": 6385 }, { "epoch": 1.634624, "grad_norm": 2.03125, "learning_rate": 2.2762562921252455e-05, "loss": 0.4294, "step": 6386 }, { "epoch": 1.6348799999999999, "grad_norm": 1.9296875, "learning_rate": 2.2758297073628532e-05, "loss": 0.428, "step": 6387 }, { "epoch": 1.6351360000000001, "grad_norm": 1.875, "learning_rate": 2.2754031226004607e-05, "loss": 0.4228, "step": 6388 }, { "epoch": 1.635392, "grad_norm": 1.9765625, "learning_rate": 2.2749765378380684e-05, "loss": 0.4346, "step": 6389 }, { "epoch": 1.635648, "grad_norm": 1.9296875, "learning_rate": 2.2745499530756762e-05, "loss": 0.4114, "step": 6390 }, { "epoch": 1.635904, "grad_norm": 2.09375, "learning_rate": 2.274123368313284e-05, "loss": 0.4367, "step": 6391 }, { "epoch": 1.6361599999999998, "grad_norm": 1.9609375, "learning_rate": 2.2736967835508914e-05, "loss": 0.4417, "step": 6392 }, { "epoch": 1.636416, "grad_norm": 1.8359375, "learning_rate": 2.2732701987884995e-05, "loss": 0.4376, "step": 6393 }, { "epoch": 1.636672, "grad_norm": 1.96875, "learning_rate": 2.272843614026107e-05, "loss": 0.4093, "step": 6394 }, { "epoch": 1.6369280000000002, "grad_norm": 1.875, "learning_rate": 2.2724170292637147e-05, "loss": 0.4412, "step": 6395 }, { "epoch": 1.637184, "grad_norm": 1.9375, "learning_rate": 2.2719904445013228e-05, "loss": 0.4126, "step": 6396 }, { "epoch": 1.63744, "grad_norm": 1.921875, "learning_rate": 2.2715638597389302e-05, "loss": 0.4238, "step": 6397 }, { "epoch": 1.637696, "grad_norm": 1.8671875, "learning_rate": 2.271137274976538e-05, "loss": 0.4668, "step": 6398 }, { "epoch": 1.6379519999999999, "grad_norm": 2.171875, "learning_rate": 2.2707106902141458e-05, "loss": 0.4468, "step": 6399 }, { "epoch": 1.638208, "grad_norm": 1.984375, "learning_rate": 2.2702841054517535e-05, "loss": 0.4296, "step": 6400 }, { "epoch": 1.638464, "grad_norm": 2.015625, "learning_rate": 2.269857520689361e-05, "loss": 0.4604, "step": 6401 }, { "epoch": 1.63872, "grad_norm": 1.9375, "learning_rate": 2.2694309359269687e-05, "loss": 0.4545, "step": 6402 }, { "epoch": 1.638976, "grad_norm": 1.859375, "learning_rate": 2.2690043511645765e-05, "loss": 0.4559, "step": 6403 }, { "epoch": 1.639232, "grad_norm": 1.984375, "learning_rate": 2.2685777664021842e-05, "loss": 0.4108, "step": 6404 }, { "epoch": 1.639488, "grad_norm": 2.046875, "learning_rate": 2.268151181639792e-05, "loss": 0.4641, "step": 6405 }, { "epoch": 1.6397439999999999, "grad_norm": 2.03125, "learning_rate": 2.2677245968773998e-05, "loss": 0.4052, "step": 6406 }, { "epoch": 1.6400000000000001, "grad_norm": 2.03125, "learning_rate": 2.2672980121150072e-05, "loss": 0.4626, "step": 6407 }, { "epoch": 1.640256, "grad_norm": 2.078125, "learning_rate": 2.266871427352615e-05, "loss": 0.444, "step": 6408 }, { "epoch": 1.640512, "grad_norm": 1.890625, "learning_rate": 2.2664448425902227e-05, "loss": 0.4336, "step": 6409 }, { "epoch": 1.640768, "grad_norm": 2.109375, "learning_rate": 2.2660182578278305e-05, "loss": 0.4316, "step": 6410 }, { "epoch": 1.641024, "grad_norm": 2.125, "learning_rate": 2.2655916730654383e-05, "loss": 0.4173, "step": 6411 }, { "epoch": 1.64128, "grad_norm": 1.8359375, "learning_rate": 2.265165088303046e-05, "loss": 0.4424, "step": 6412 }, { "epoch": 1.6415359999999999, "grad_norm": 2.078125, "learning_rate": 2.2647385035406538e-05, "loss": 0.4157, "step": 6413 }, { "epoch": 1.6417920000000001, "grad_norm": 2.109375, "learning_rate": 2.2643119187782612e-05, "loss": 0.4272, "step": 6414 }, { "epoch": 1.642048, "grad_norm": 1.9765625, "learning_rate": 2.2638853340158693e-05, "loss": 0.4441, "step": 6415 }, { "epoch": 1.642304, "grad_norm": 2.109375, "learning_rate": 2.2634587492534768e-05, "loss": 0.4195, "step": 6416 }, { "epoch": 1.64256, "grad_norm": 1.921875, "learning_rate": 2.2630321644910845e-05, "loss": 0.4445, "step": 6417 }, { "epoch": 1.642816, "grad_norm": 1.90625, "learning_rate": 2.2626055797286923e-05, "loss": 0.4269, "step": 6418 }, { "epoch": 1.643072, "grad_norm": 1.9140625, "learning_rate": 2.2621789949663e-05, "loss": 0.452, "step": 6419 }, { "epoch": 1.643328, "grad_norm": 2.125, "learning_rate": 2.2617524102039075e-05, "loss": 0.4038, "step": 6420 }, { "epoch": 1.6435840000000002, "grad_norm": 2.03125, "learning_rate": 2.2613258254415152e-05, "loss": 0.4109, "step": 6421 }, { "epoch": 1.64384, "grad_norm": 2.0, "learning_rate": 2.260899240679123e-05, "loss": 0.449, "step": 6422 }, { "epoch": 1.644096, "grad_norm": 2.015625, "learning_rate": 2.2604726559167308e-05, "loss": 0.4251, "step": 6423 }, { "epoch": 1.644352, "grad_norm": 2.015625, "learning_rate": 2.2600460711543382e-05, "loss": 0.4475, "step": 6424 }, { "epoch": 1.6446079999999998, "grad_norm": 1.9609375, "learning_rate": 2.2596194863919463e-05, "loss": 0.4011, "step": 6425 }, { "epoch": 1.644864, "grad_norm": 2.1875, "learning_rate": 2.2591929016295537e-05, "loss": 0.4462, "step": 6426 }, { "epoch": 1.64512, "grad_norm": 2.015625, "learning_rate": 2.2587663168671615e-05, "loss": 0.4102, "step": 6427 }, { "epoch": 1.645376, "grad_norm": 1.890625, "learning_rate": 2.2583397321047696e-05, "loss": 0.4339, "step": 6428 }, { "epoch": 1.645632, "grad_norm": 1.9453125, "learning_rate": 2.257913147342377e-05, "loss": 0.4428, "step": 6429 }, { "epoch": 1.645888, "grad_norm": 2.109375, "learning_rate": 2.2574865625799848e-05, "loss": 0.4147, "step": 6430 }, { "epoch": 1.646144, "grad_norm": 2.109375, "learning_rate": 2.2570599778175926e-05, "loss": 0.46, "step": 6431 }, { "epoch": 1.6463999999999999, "grad_norm": 2.03125, "learning_rate": 2.2566333930552003e-05, "loss": 0.444, "step": 6432 }, { "epoch": 1.6466560000000001, "grad_norm": 2.0625, "learning_rate": 2.2562068082928077e-05, "loss": 0.4551, "step": 6433 }, { "epoch": 1.646912, "grad_norm": 1.9296875, "learning_rate": 2.2557802235304155e-05, "loss": 0.4466, "step": 6434 }, { "epoch": 1.647168, "grad_norm": 1.9921875, "learning_rate": 2.2553536387680233e-05, "loss": 0.435, "step": 6435 }, { "epoch": 1.647424, "grad_norm": 2.125, "learning_rate": 2.254927054005631e-05, "loss": 0.4494, "step": 6436 }, { "epoch": 1.64768, "grad_norm": 1.9921875, "learning_rate": 2.2545004692432388e-05, "loss": 0.4082, "step": 6437 }, { "epoch": 1.647936, "grad_norm": 1.8984375, "learning_rate": 2.2540738844808466e-05, "loss": 0.4392, "step": 6438 }, { "epoch": 1.6481919999999999, "grad_norm": 2.0, "learning_rate": 2.253647299718454e-05, "loss": 0.4435, "step": 6439 }, { "epoch": 1.6484480000000001, "grad_norm": 2.078125, "learning_rate": 2.2532207149560618e-05, "loss": 0.4405, "step": 6440 }, { "epoch": 1.648704, "grad_norm": 2.0, "learning_rate": 2.2527941301936695e-05, "loss": 0.4414, "step": 6441 }, { "epoch": 1.64896, "grad_norm": 1.859375, "learning_rate": 2.2523675454312773e-05, "loss": 0.4305, "step": 6442 }, { "epoch": 1.649216, "grad_norm": 1.9765625, "learning_rate": 2.2519409606688847e-05, "loss": 0.448, "step": 6443 }, { "epoch": 1.649472, "grad_norm": 1.90625, "learning_rate": 2.2515143759064928e-05, "loss": 0.4434, "step": 6444 }, { "epoch": 1.649728, "grad_norm": 2.015625, "learning_rate": 2.2510877911441006e-05, "loss": 0.4661, "step": 6445 }, { "epoch": 1.649984, "grad_norm": 1.7734375, "learning_rate": 2.250661206381708e-05, "loss": 0.4213, "step": 6446 }, { "epoch": 1.6502400000000002, "grad_norm": 1.8828125, "learning_rate": 2.250234621619316e-05, "loss": 0.4279, "step": 6447 }, { "epoch": 1.650496, "grad_norm": 2.125, "learning_rate": 2.2498080368569236e-05, "loss": 0.4512, "step": 6448 }, { "epoch": 1.650752, "grad_norm": 1.96875, "learning_rate": 2.2493814520945313e-05, "loss": 0.4399, "step": 6449 }, { "epoch": 1.651008, "grad_norm": 1.9375, "learning_rate": 2.248954867332139e-05, "loss": 0.4583, "step": 6450 }, { "epoch": 1.6512639999999998, "grad_norm": 1.9609375, "learning_rate": 2.248528282569747e-05, "loss": 0.425, "step": 6451 }, { "epoch": 1.65152, "grad_norm": 2.0, "learning_rate": 2.2481016978073543e-05, "loss": 0.4393, "step": 6452 }, { "epoch": 1.651776, "grad_norm": 2.015625, "learning_rate": 2.247675113044962e-05, "loss": 0.461, "step": 6453 }, { "epoch": 1.652032, "grad_norm": 2.0625, "learning_rate": 2.2472485282825698e-05, "loss": 0.4214, "step": 6454 }, { "epoch": 1.652288, "grad_norm": 2.046875, "learning_rate": 2.2468219435201776e-05, "loss": 0.4207, "step": 6455 }, { "epoch": 1.652544, "grad_norm": 1.8671875, "learning_rate": 2.2463953587577853e-05, "loss": 0.4526, "step": 6456 }, { "epoch": 1.6528, "grad_norm": 2.03125, "learning_rate": 2.245968773995393e-05, "loss": 0.4684, "step": 6457 }, { "epoch": 1.6530559999999999, "grad_norm": 1.984375, "learning_rate": 2.2455421892330005e-05, "loss": 0.4362, "step": 6458 }, { "epoch": 1.6533120000000001, "grad_norm": 1.765625, "learning_rate": 2.2451156044706083e-05, "loss": 0.4261, "step": 6459 }, { "epoch": 1.653568, "grad_norm": 1.953125, "learning_rate": 2.2446890197082164e-05, "loss": 0.4613, "step": 6460 }, { "epoch": 1.653824, "grad_norm": 1.8828125, "learning_rate": 2.2442624349458238e-05, "loss": 0.469, "step": 6461 }, { "epoch": 1.65408, "grad_norm": 2.03125, "learning_rate": 2.2438358501834316e-05, "loss": 0.4375, "step": 6462 }, { "epoch": 1.654336, "grad_norm": 1.9375, "learning_rate": 2.2434092654210394e-05, "loss": 0.4208, "step": 6463 }, { "epoch": 1.654592, "grad_norm": 2.015625, "learning_rate": 2.242982680658647e-05, "loss": 0.427, "step": 6464 }, { "epoch": 1.6548479999999999, "grad_norm": 2.0, "learning_rate": 2.2425560958962545e-05, "loss": 0.4275, "step": 6465 }, { "epoch": 1.6551040000000001, "grad_norm": 2.0, "learning_rate": 2.2421295111338627e-05, "loss": 0.4598, "step": 6466 }, { "epoch": 1.65536, "grad_norm": 1.875, "learning_rate": 2.24170292637147e-05, "loss": 0.391, "step": 6467 }, { "epoch": 1.655616, "grad_norm": 1.9375, "learning_rate": 2.241276341609078e-05, "loss": 0.4514, "step": 6468 }, { "epoch": 1.655872, "grad_norm": 1.96875, "learning_rate": 2.2408497568466856e-05, "loss": 0.4336, "step": 6469 }, { "epoch": 1.656128, "grad_norm": 2.015625, "learning_rate": 2.2404231720842934e-05, "loss": 0.448, "step": 6470 }, { "epoch": 1.656384, "grad_norm": 2.125, "learning_rate": 2.2399965873219008e-05, "loss": 0.4817, "step": 6471 }, { "epoch": 1.65664, "grad_norm": 2.0625, "learning_rate": 2.2395700025595086e-05, "loss": 0.4113, "step": 6472 }, { "epoch": 1.6568960000000001, "grad_norm": 2.171875, "learning_rate": 2.2391434177971163e-05, "loss": 0.444, "step": 6473 }, { "epoch": 1.657152, "grad_norm": 1.7890625, "learning_rate": 2.238716833034724e-05, "loss": 0.426, "step": 6474 }, { "epoch": 1.657408, "grad_norm": 1.9921875, "learning_rate": 2.2382902482723315e-05, "loss": 0.4755, "step": 6475 }, { "epoch": 1.657664, "grad_norm": 2.078125, "learning_rate": 2.2378636635099396e-05, "loss": 0.4265, "step": 6476 }, { "epoch": 1.6579199999999998, "grad_norm": 1.9921875, "learning_rate": 2.2374370787475474e-05, "loss": 0.4141, "step": 6477 }, { "epoch": 1.658176, "grad_norm": 1.9921875, "learning_rate": 2.2370104939851548e-05, "loss": 0.4445, "step": 6478 }, { "epoch": 1.658432, "grad_norm": 1.953125, "learning_rate": 2.236583909222763e-05, "loss": 0.4158, "step": 6479 }, { "epoch": 1.6586880000000002, "grad_norm": 2.0625, "learning_rate": 2.2361573244603704e-05, "loss": 0.4349, "step": 6480 }, { "epoch": 1.658944, "grad_norm": 1.8671875, "learning_rate": 2.235730739697978e-05, "loss": 0.4323, "step": 6481 }, { "epoch": 1.6592, "grad_norm": 2.125, "learning_rate": 2.235304154935586e-05, "loss": 0.4512, "step": 6482 }, { "epoch": 1.659456, "grad_norm": 1.9140625, "learning_rate": 2.2348775701731936e-05, "loss": 0.4177, "step": 6483 }, { "epoch": 1.6597119999999999, "grad_norm": 2.015625, "learning_rate": 2.234450985410801e-05, "loss": 0.4353, "step": 6484 }, { "epoch": 1.659968, "grad_norm": 1.9140625, "learning_rate": 2.2340244006484092e-05, "loss": 0.4358, "step": 6485 }, { "epoch": 1.660224, "grad_norm": 2.078125, "learning_rate": 2.2335978158860166e-05, "loss": 0.4383, "step": 6486 }, { "epoch": 1.66048, "grad_norm": 2.171875, "learning_rate": 2.2331712311236244e-05, "loss": 0.4155, "step": 6487 }, { "epoch": 1.660736, "grad_norm": 1.9453125, "learning_rate": 2.232744646361232e-05, "loss": 0.4784, "step": 6488 }, { "epoch": 1.660992, "grad_norm": 1.9765625, "learning_rate": 2.23231806159884e-05, "loss": 0.4296, "step": 6489 }, { "epoch": 1.661248, "grad_norm": 2.15625, "learning_rate": 2.2318914768364473e-05, "loss": 0.4344, "step": 6490 }, { "epoch": 1.6615039999999999, "grad_norm": 2.109375, "learning_rate": 2.231464892074055e-05, "loss": 0.4265, "step": 6491 }, { "epoch": 1.6617600000000001, "grad_norm": 2.203125, "learning_rate": 2.231038307311663e-05, "loss": 0.4144, "step": 6492 }, { "epoch": 1.662016, "grad_norm": 2.0625, "learning_rate": 2.2306117225492706e-05, "loss": 0.4014, "step": 6493 }, { "epoch": 1.662272, "grad_norm": 1.78125, "learning_rate": 2.2301851377868784e-05, "loss": 0.4489, "step": 6494 }, { "epoch": 1.662528, "grad_norm": 1.8984375, "learning_rate": 2.229758553024486e-05, "loss": 0.4172, "step": 6495 }, { "epoch": 1.662784, "grad_norm": 2.03125, "learning_rate": 2.229331968262094e-05, "loss": 0.4452, "step": 6496 }, { "epoch": 1.66304, "grad_norm": 2.234375, "learning_rate": 2.2289053834997013e-05, "loss": 0.419, "step": 6497 }, { "epoch": 1.6632959999999999, "grad_norm": 2.21875, "learning_rate": 2.2284787987373095e-05, "loss": 0.4402, "step": 6498 }, { "epoch": 1.6635520000000001, "grad_norm": 1.953125, "learning_rate": 2.228052213974917e-05, "loss": 0.4404, "step": 6499 }, { "epoch": 1.663808, "grad_norm": 1.96875, "learning_rate": 2.2276256292125246e-05, "loss": 0.389, "step": 6500 }, { "epoch": 1.664064, "grad_norm": 1.984375, "learning_rate": 2.2271990444501324e-05, "loss": 0.4101, "step": 6501 }, { "epoch": 1.66432, "grad_norm": 2.0625, "learning_rate": 2.2267724596877402e-05, "loss": 0.4451, "step": 6502 }, { "epoch": 1.6645759999999998, "grad_norm": 2.0, "learning_rate": 2.2263458749253476e-05, "loss": 0.4343, "step": 6503 }, { "epoch": 1.664832, "grad_norm": 2.046875, "learning_rate": 2.2259192901629554e-05, "loss": 0.4374, "step": 6504 }, { "epoch": 1.665088, "grad_norm": 1.8125, "learning_rate": 2.225492705400563e-05, "loss": 0.4809, "step": 6505 }, { "epoch": 1.6653440000000002, "grad_norm": 2.015625, "learning_rate": 2.225066120638171e-05, "loss": 0.4528, "step": 6506 }, { "epoch": 1.6656, "grad_norm": 2.078125, "learning_rate": 2.2246395358757787e-05, "loss": 0.4112, "step": 6507 }, { "epoch": 1.665856, "grad_norm": 1.9609375, "learning_rate": 2.2242129511133864e-05, "loss": 0.4189, "step": 6508 }, { "epoch": 1.666112, "grad_norm": 1.8984375, "learning_rate": 2.223786366350994e-05, "loss": 0.4635, "step": 6509 }, { "epoch": 1.6663679999999998, "grad_norm": 1.8359375, "learning_rate": 2.2233597815886016e-05, "loss": 0.439, "step": 6510 }, { "epoch": 1.666624, "grad_norm": 2.0, "learning_rate": 2.2229331968262097e-05, "loss": 0.4492, "step": 6511 }, { "epoch": 1.66688, "grad_norm": 1.9609375, "learning_rate": 2.222506612063817e-05, "loss": 0.4175, "step": 6512 }, { "epoch": 1.667136, "grad_norm": 1.953125, "learning_rate": 2.222080027301425e-05, "loss": 0.4928, "step": 6513 }, { "epoch": 1.667392, "grad_norm": 1.96875, "learning_rate": 2.2216534425390327e-05, "loss": 0.4173, "step": 6514 }, { "epoch": 1.667648, "grad_norm": 1.84375, "learning_rate": 2.2212268577766404e-05, "loss": 0.4267, "step": 6515 }, { "epoch": 1.667904, "grad_norm": 2.125, "learning_rate": 2.220800273014248e-05, "loss": 0.4314, "step": 6516 }, { "epoch": 1.6681599999999999, "grad_norm": 2.015625, "learning_rate": 2.220373688251856e-05, "loss": 0.4494, "step": 6517 }, { "epoch": 1.6684160000000001, "grad_norm": 2.0, "learning_rate": 2.2199471034894634e-05, "loss": 0.3843, "step": 6518 }, { "epoch": 1.668672, "grad_norm": 2.1875, "learning_rate": 2.2195205187270712e-05, "loss": 0.4421, "step": 6519 }, { "epoch": 1.668928, "grad_norm": 1.9296875, "learning_rate": 2.219093933964679e-05, "loss": 0.4249, "step": 6520 }, { "epoch": 1.669184, "grad_norm": 2.09375, "learning_rate": 2.2186673492022867e-05, "loss": 0.4389, "step": 6521 }, { "epoch": 1.66944, "grad_norm": 1.9140625, "learning_rate": 2.218240764439894e-05, "loss": 0.3861, "step": 6522 }, { "epoch": 1.669696, "grad_norm": 2.203125, "learning_rate": 2.217814179677502e-05, "loss": 0.4163, "step": 6523 }, { "epoch": 1.6699519999999999, "grad_norm": 1.890625, "learning_rate": 2.2173875949151097e-05, "loss": 0.4542, "step": 6524 }, { "epoch": 1.6702080000000001, "grad_norm": 1.9453125, "learning_rate": 2.2169610101527174e-05, "loss": 0.4562, "step": 6525 }, { "epoch": 1.670464, "grad_norm": 1.9453125, "learning_rate": 2.2165344253903252e-05, "loss": 0.4333, "step": 6526 }, { "epoch": 1.67072, "grad_norm": 1.9453125, "learning_rate": 2.216107840627933e-05, "loss": 0.4265, "step": 6527 }, { "epoch": 1.670976, "grad_norm": 2.09375, "learning_rate": 2.2156812558655407e-05, "loss": 0.4359, "step": 6528 }, { "epoch": 1.671232, "grad_norm": 1.9609375, "learning_rate": 2.215254671103148e-05, "loss": 0.4569, "step": 6529 }, { "epoch": 1.671488, "grad_norm": 2.03125, "learning_rate": 2.2148280863407563e-05, "loss": 0.407, "step": 6530 }, { "epoch": 1.671744, "grad_norm": 2.03125, "learning_rate": 2.2144015015783637e-05, "loss": 0.4047, "step": 6531 }, { "epoch": 1.6720000000000002, "grad_norm": 2.046875, "learning_rate": 2.2139749168159714e-05, "loss": 0.4399, "step": 6532 }, { "epoch": 1.672256, "grad_norm": 2.0, "learning_rate": 2.2135483320535792e-05, "loss": 0.4286, "step": 6533 }, { "epoch": 1.672512, "grad_norm": 2.0625, "learning_rate": 2.213121747291187e-05, "loss": 0.461, "step": 6534 }, { "epoch": 1.672768, "grad_norm": 2.140625, "learning_rate": 2.2126951625287944e-05, "loss": 0.4225, "step": 6535 }, { "epoch": 1.6730239999999998, "grad_norm": 1.9375, "learning_rate": 2.2122685777664025e-05, "loss": 0.4574, "step": 6536 }, { "epoch": 1.67328, "grad_norm": 1.984375, "learning_rate": 2.21184199300401e-05, "loss": 0.4695, "step": 6537 }, { "epoch": 1.673536, "grad_norm": 1.9453125, "learning_rate": 2.2114154082416177e-05, "loss": 0.4589, "step": 6538 }, { "epoch": 1.673792, "grad_norm": 1.984375, "learning_rate": 2.2109888234792255e-05, "loss": 0.4712, "step": 6539 }, { "epoch": 1.674048, "grad_norm": 2.109375, "learning_rate": 2.2105622387168332e-05, "loss": 0.4517, "step": 6540 }, { "epoch": 1.674304, "grad_norm": 2.3125, "learning_rate": 2.2101356539544407e-05, "loss": 0.4295, "step": 6541 }, { "epoch": 1.67456, "grad_norm": 1.9765625, "learning_rate": 2.2097090691920484e-05, "loss": 0.4514, "step": 6542 }, { "epoch": 1.6748159999999999, "grad_norm": 2.171875, "learning_rate": 2.2092824844296565e-05, "loss": 0.4096, "step": 6543 }, { "epoch": 1.6750720000000001, "grad_norm": 2.1875, "learning_rate": 2.208855899667264e-05, "loss": 0.465, "step": 6544 }, { "epoch": 1.675328, "grad_norm": 2.109375, "learning_rate": 2.2084293149048717e-05, "loss": 0.4737, "step": 6545 }, { "epoch": 1.675584, "grad_norm": 2.125, "learning_rate": 2.2080027301424795e-05, "loss": 0.4584, "step": 6546 }, { "epoch": 1.67584, "grad_norm": 2.265625, "learning_rate": 2.2075761453800872e-05, "loss": 0.424, "step": 6547 }, { "epoch": 1.676096, "grad_norm": 1.9921875, "learning_rate": 2.2071495606176947e-05, "loss": 0.4189, "step": 6548 }, { "epoch": 1.676352, "grad_norm": 1.9140625, "learning_rate": 2.2067229758553028e-05, "loss": 0.4259, "step": 6549 }, { "epoch": 1.6766079999999999, "grad_norm": 2.03125, "learning_rate": 2.2062963910929102e-05, "loss": 0.4308, "step": 6550 }, { "epoch": 1.6768640000000001, "grad_norm": 2.09375, "learning_rate": 2.205869806330518e-05, "loss": 0.445, "step": 6551 }, { "epoch": 1.67712, "grad_norm": 2.140625, "learning_rate": 2.2054432215681257e-05, "loss": 0.4288, "step": 6552 }, { "epoch": 1.677376, "grad_norm": 1.953125, "learning_rate": 2.2050166368057335e-05, "loss": 0.4454, "step": 6553 }, { "epoch": 1.677632, "grad_norm": 2.0, "learning_rate": 2.204590052043341e-05, "loss": 0.4584, "step": 6554 }, { "epoch": 1.677888, "grad_norm": 2.03125, "learning_rate": 2.2041634672809487e-05, "loss": 0.4553, "step": 6555 }, { "epoch": 1.678144, "grad_norm": 2.015625, "learning_rate": 2.2037368825185565e-05, "loss": 0.3885, "step": 6556 }, { "epoch": 1.6784, "grad_norm": 1.953125, "learning_rate": 2.2033102977561642e-05, "loss": 0.4697, "step": 6557 }, { "epoch": 1.6786560000000001, "grad_norm": 1.9375, "learning_rate": 2.202883712993772e-05, "loss": 0.3936, "step": 6558 }, { "epoch": 1.678912, "grad_norm": 1.828125, "learning_rate": 2.2024571282313798e-05, "loss": 0.4362, "step": 6559 }, { "epoch": 1.679168, "grad_norm": 2.140625, "learning_rate": 2.2020305434689875e-05, "loss": 0.4659, "step": 6560 }, { "epoch": 1.679424, "grad_norm": 2.1875, "learning_rate": 2.201603958706595e-05, "loss": 0.4341, "step": 6561 }, { "epoch": 1.6796799999999998, "grad_norm": 2.1875, "learning_rate": 2.201177373944203e-05, "loss": 0.4277, "step": 6562 }, { "epoch": 1.679936, "grad_norm": 1.9375, "learning_rate": 2.2007507891818105e-05, "loss": 0.4111, "step": 6563 }, { "epoch": 1.680192, "grad_norm": 2.015625, "learning_rate": 2.2003242044194182e-05, "loss": 0.4172, "step": 6564 }, { "epoch": 1.6804480000000002, "grad_norm": 1.875, "learning_rate": 2.199897619657026e-05, "loss": 0.4781, "step": 6565 }, { "epoch": 1.680704, "grad_norm": 1.984375, "learning_rate": 2.1994710348946338e-05, "loss": 0.4305, "step": 6566 }, { "epoch": 1.68096, "grad_norm": 1.8828125, "learning_rate": 2.1990444501322412e-05, "loss": 0.4352, "step": 6567 }, { "epoch": 1.681216, "grad_norm": 1.9921875, "learning_rate": 2.1986178653698493e-05, "loss": 0.4524, "step": 6568 }, { "epoch": 1.6814719999999999, "grad_norm": 1.8984375, "learning_rate": 2.1981912806074567e-05, "loss": 0.4327, "step": 6569 }, { "epoch": 1.6817280000000001, "grad_norm": 2.03125, "learning_rate": 2.1977646958450645e-05, "loss": 0.4354, "step": 6570 }, { "epoch": 1.681984, "grad_norm": 2.171875, "learning_rate": 2.1973381110826723e-05, "loss": 0.451, "step": 6571 }, { "epoch": 1.68224, "grad_norm": 1.9453125, "learning_rate": 2.19691152632028e-05, "loss": 0.4565, "step": 6572 }, { "epoch": 1.682496, "grad_norm": 1.8984375, "learning_rate": 2.1964849415578875e-05, "loss": 0.4285, "step": 6573 }, { "epoch": 1.682752, "grad_norm": 1.984375, "learning_rate": 2.1960583567954952e-05, "loss": 0.4456, "step": 6574 }, { "epoch": 1.683008, "grad_norm": 1.9453125, "learning_rate": 2.1956317720331033e-05, "loss": 0.469, "step": 6575 }, { "epoch": 1.6832639999999999, "grad_norm": 1.9375, "learning_rate": 2.1952051872707108e-05, "loss": 0.4473, "step": 6576 }, { "epoch": 1.6835200000000001, "grad_norm": 1.828125, "learning_rate": 2.1947786025083185e-05, "loss": 0.4273, "step": 6577 }, { "epoch": 1.683776, "grad_norm": 1.953125, "learning_rate": 2.1943520177459263e-05, "loss": 0.4116, "step": 6578 }, { "epoch": 1.684032, "grad_norm": 1.9765625, "learning_rate": 2.193925432983534e-05, "loss": 0.4384, "step": 6579 }, { "epoch": 1.684288, "grad_norm": 1.9375, "learning_rate": 2.1934988482211415e-05, "loss": 0.4235, "step": 6580 }, { "epoch": 1.684544, "grad_norm": 2.09375, "learning_rate": 2.1930722634587496e-05, "loss": 0.4235, "step": 6581 }, { "epoch": 1.6848, "grad_norm": 2.125, "learning_rate": 2.192645678696357e-05, "loss": 0.4192, "step": 6582 }, { "epoch": 1.6850559999999999, "grad_norm": 1.984375, "learning_rate": 2.1922190939339648e-05, "loss": 0.4535, "step": 6583 }, { "epoch": 1.6853120000000001, "grad_norm": 1.90625, "learning_rate": 2.1917925091715725e-05, "loss": 0.4472, "step": 6584 }, { "epoch": 1.685568, "grad_norm": 1.8984375, "learning_rate": 2.1913659244091803e-05, "loss": 0.4769, "step": 6585 }, { "epoch": 1.685824, "grad_norm": 1.875, "learning_rate": 2.1909393396467877e-05, "loss": 0.4485, "step": 6586 }, { "epoch": 1.68608, "grad_norm": 1.9921875, "learning_rate": 2.190512754884396e-05, "loss": 0.4223, "step": 6587 }, { "epoch": 1.6863359999999998, "grad_norm": 1.8671875, "learning_rate": 2.1900861701220033e-05, "loss": 0.4115, "step": 6588 }, { "epoch": 1.686592, "grad_norm": 1.953125, "learning_rate": 2.189659585359611e-05, "loss": 0.4524, "step": 6589 }, { "epoch": 1.686848, "grad_norm": 1.9375, "learning_rate": 2.1892330005972188e-05, "loss": 0.3972, "step": 6590 }, { "epoch": 1.6871040000000002, "grad_norm": 1.921875, "learning_rate": 2.1888064158348266e-05, "loss": 0.4386, "step": 6591 }, { "epoch": 1.68736, "grad_norm": 2.0625, "learning_rate": 2.1883798310724343e-05, "loss": 0.4286, "step": 6592 }, { "epoch": 1.687616, "grad_norm": 1.890625, "learning_rate": 2.1879532463100417e-05, "loss": 0.4081, "step": 6593 }, { "epoch": 1.687872, "grad_norm": 1.890625, "learning_rate": 2.18752666154765e-05, "loss": 0.4091, "step": 6594 }, { "epoch": 1.6881279999999999, "grad_norm": 1.984375, "learning_rate": 2.1871000767852573e-05, "loss": 0.4158, "step": 6595 }, { "epoch": 1.688384, "grad_norm": 2.0, "learning_rate": 2.186673492022865e-05, "loss": 0.401, "step": 6596 }, { "epoch": 1.68864, "grad_norm": 1.8671875, "learning_rate": 2.1862469072604728e-05, "loss": 0.4358, "step": 6597 }, { "epoch": 1.688896, "grad_norm": 1.9453125, "learning_rate": 2.1858203224980806e-05, "loss": 0.4169, "step": 6598 }, { "epoch": 1.689152, "grad_norm": 2.015625, "learning_rate": 2.185393737735688e-05, "loss": 0.4298, "step": 6599 }, { "epoch": 1.689408, "grad_norm": 2.03125, "learning_rate": 2.184967152973296e-05, "loss": 0.4447, "step": 6600 }, { "epoch": 1.689664, "grad_norm": 2.046875, "learning_rate": 2.1845405682109035e-05, "loss": 0.4703, "step": 6601 }, { "epoch": 1.6899199999999999, "grad_norm": 2.125, "learning_rate": 2.1841139834485113e-05, "loss": 0.4272, "step": 6602 }, { "epoch": 1.6901760000000001, "grad_norm": 2.0625, "learning_rate": 2.183687398686119e-05, "loss": 0.4587, "step": 6603 }, { "epoch": 1.690432, "grad_norm": 1.9375, "learning_rate": 2.1832608139237268e-05, "loss": 0.4381, "step": 6604 }, { "epoch": 1.690688, "grad_norm": 2.125, "learning_rate": 2.1828342291613343e-05, "loss": 0.4273, "step": 6605 }, { "epoch": 1.690944, "grad_norm": 2.015625, "learning_rate": 2.182407644398942e-05, "loss": 0.4185, "step": 6606 }, { "epoch": 1.6912, "grad_norm": 1.9921875, "learning_rate": 2.1819810596365498e-05, "loss": 0.4321, "step": 6607 }, { "epoch": 1.691456, "grad_norm": 1.9375, "learning_rate": 2.1815544748741576e-05, "loss": 0.4108, "step": 6608 }, { "epoch": 1.6917119999999999, "grad_norm": 1.8359375, "learning_rate": 2.1811278901117653e-05, "loss": 0.4227, "step": 6609 }, { "epoch": 1.6919680000000001, "grad_norm": 2.03125, "learning_rate": 2.180701305349373e-05, "loss": 0.4128, "step": 6610 }, { "epoch": 1.692224, "grad_norm": 2.015625, "learning_rate": 2.180274720586981e-05, "loss": 0.4295, "step": 6611 }, { "epoch": 1.69248, "grad_norm": 2.109375, "learning_rate": 2.1798481358245883e-05, "loss": 0.4487, "step": 6612 }, { "epoch": 1.692736, "grad_norm": 2.09375, "learning_rate": 2.1794215510621964e-05, "loss": 0.4194, "step": 6613 }, { "epoch": 1.692992, "grad_norm": 1.8125, "learning_rate": 2.1789949662998038e-05, "loss": 0.4646, "step": 6614 }, { "epoch": 1.693248, "grad_norm": 1.8671875, "learning_rate": 2.1785683815374116e-05, "loss": 0.4261, "step": 6615 }, { "epoch": 1.693504, "grad_norm": 2.203125, "learning_rate": 2.1781417967750193e-05, "loss": 0.4233, "step": 6616 }, { "epoch": 1.6937600000000002, "grad_norm": 2.140625, "learning_rate": 2.177715212012627e-05, "loss": 0.4139, "step": 6617 }, { "epoch": 1.694016, "grad_norm": 2.15625, "learning_rate": 2.1772886272502345e-05, "loss": 0.4066, "step": 6618 }, { "epoch": 1.694272, "grad_norm": 1.9921875, "learning_rate": 2.1768620424878426e-05, "loss": 0.4204, "step": 6619 }, { "epoch": 1.694528, "grad_norm": 1.9453125, "learning_rate": 2.17643545772545e-05, "loss": 0.4648, "step": 6620 }, { "epoch": 1.6947839999999998, "grad_norm": 1.8671875, "learning_rate": 2.1760088729630578e-05, "loss": 0.3991, "step": 6621 }, { "epoch": 1.69504, "grad_norm": 1.859375, "learning_rate": 2.1755822882006656e-05, "loss": 0.4004, "step": 6622 }, { "epoch": 1.695296, "grad_norm": 1.953125, "learning_rate": 2.1751557034382734e-05, "loss": 0.4705, "step": 6623 }, { "epoch": 1.695552, "grad_norm": 2.0, "learning_rate": 2.174729118675881e-05, "loss": 0.4113, "step": 6624 }, { "epoch": 1.695808, "grad_norm": 1.8828125, "learning_rate": 2.1743025339134885e-05, "loss": 0.4463, "step": 6625 }, { "epoch": 1.696064, "grad_norm": 2.078125, "learning_rate": 2.1738759491510967e-05, "loss": 0.4349, "step": 6626 }, { "epoch": 1.69632, "grad_norm": 1.8828125, "learning_rate": 2.173449364388704e-05, "loss": 0.4635, "step": 6627 }, { "epoch": 1.6965759999999999, "grad_norm": 2.0625, "learning_rate": 2.173022779626312e-05, "loss": 0.4248, "step": 6628 }, { "epoch": 1.6968320000000001, "grad_norm": 1.90625, "learning_rate": 2.1725961948639196e-05, "loss": 0.4543, "step": 6629 }, { "epoch": 1.697088, "grad_norm": 1.84375, "learning_rate": 2.1721696101015274e-05, "loss": 0.4313, "step": 6630 }, { "epoch": 1.697344, "grad_norm": 1.90625, "learning_rate": 2.1717430253391348e-05, "loss": 0.4636, "step": 6631 }, { "epoch": 1.6976, "grad_norm": 1.890625, "learning_rate": 2.171316440576743e-05, "loss": 0.4499, "step": 6632 }, { "epoch": 1.697856, "grad_norm": 2.125, "learning_rate": 2.1708898558143503e-05, "loss": 0.4461, "step": 6633 }, { "epoch": 1.698112, "grad_norm": 2.0, "learning_rate": 2.170463271051958e-05, "loss": 0.3897, "step": 6634 }, { "epoch": 1.6983679999999999, "grad_norm": 1.9140625, "learning_rate": 2.170036686289566e-05, "loss": 0.4593, "step": 6635 }, { "epoch": 1.6986240000000001, "grad_norm": 2.015625, "learning_rate": 2.1696101015271736e-05, "loss": 0.447, "step": 6636 }, { "epoch": 1.69888, "grad_norm": 1.96875, "learning_rate": 2.169183516764781e-05, "loss": 0.4191, "step": 6637 }, { "epoch": 1.699136, "grad_norm": 2.03125, "learning_rate": 2.168756932002389e-05, "loss": 0.4107, "step": 6638 }, { "epoch": 1.699392, "grad_norm": 1.8203125, "learning_rate": 2.1683303472399966e-05, "loss": 0.4386, "step": 6639 }, { "epoch": 1.699648, "grad_norm": 1.921875, "learning_rate": 2.1679037624776044e-05, "loss": 0.4649, "step": 6640 }, { "epoch": 1.699904, "grad_norm": 1.9453125, "learning_rate": 2.167477177715212e-05, "loss": 0.3763, "step": 6641 }, { "epoch": 1.70016, "grad_norm": 1.8671875, "learning_rate": 2.16705059295282e-05, "loss": 0.4485, "step": 6642 }, { "epoch": 1.7004160000000001, "grad_norm": 2.015625, "learning_rate": 2.1666240081904276e-05, "loss": 0.4528, "step": 6643 }, { "epoch": 1.700672, "grad_norm": 2.0, "learning_rate": 2.166197423428035e-05, "loss": 0.4454, "step": 6644 }, { "epoch": 1.700928, "grad_norm": 1.9609375, "learning_rate": 2.1657708386656432e-05, "loss": 0.432, "step": 6645 }, { "epoch": 1.701184, "grad_norm": 2.03125, "learning_rate": 2.1653442539032506e-05, "loss": 0.4509, "step": 6646 }, { "epoch": 1.7014399999999998, "grad_norm": 1.984375, "learning_rate": 2.1649176691408584e-05, "loss": 0.4497, "step": 6647 }, { "epoch": 1.701696, "grad_norm": 1.921875, "learning_rate": 2.164491084378466e-05, "loss": 0.4133, "step": 6648 }, { "epoch": 1.701952, "grad_norm": 1.8984375, "learning_rate": 2.164064499616074e-05, "loss": 0.5041, "step": 6649 }, { "epoch": 1.7022080000000002, "grad_norm": 1.8515625, "learning_rate": 2.1636379148536813e-05, "loss": 0.4496, "step": 6650 }, { "epoch": 1.702464, "grad_norm": 1.875, "learning_rate": 2.1632113300912894e-05, "loss": 0.4142, "step": 6651 }, { "epoch": 1.70272, "grad_norm": 1.9140625, "learning_rate": 2.162784745328897e-05, "loss": 0.4475, "step": 6652 }, { "epoch": 1.702976, "grad_norm": 1.90625, "learning_rate": 2.1623581605665046e-05, "loss": 0.4861, "step": 6653 }, { "epoch": 1.7032319999999999, "grad_norm": 1.9609375, "learning_rate": 2.1619315758041124e-05, "loss": 0.4535, "step": 6654 }, { "epoch": 1.7034880000000001, "grad_norm": 1.8359375, "learning_rate": 2.16150499104172e-05, "loss": 0.4237, "step": 6655 }, { "epoch": 1.703744, "grad_norm": 1.90625, "learning_rate": 2.1610784062793276e-05, "loss": 0.403, "step": 6656 }, { "epoch": 1.704, "grad_norm": 2.125, "learning_rate": 2.1606518215169353e-05, "loss": 0.4519, "step": 6657 }, { "epoch": 1.704256, "grad_norm": 1.8984375, "learning_rate": 2.1602252367545435e-05, "loss": 0.4322, "step": 6658 }, { "epoch": 1.704512, "grad_norm": 1.953125, "learning_rate": 2.159798651992151e-05, "loss": 0.4061, "step": 6659 }, { "epoch": 1.704768, "grad_norm": 1.921875, "learning_rate": 2.1593720672297586e-05, "loss": 0.4216, "step": 6660 }, { "epoch": 1.7050239999999999, "grad_norm": 1.921875, "learning_rate": 2.1589454824673664e-05, "loss": 0.4204, "step": 6661 }, { "epoch": 1.7052800000000001, "grad_norm": 1.953125, "learning_rate": 2.1585188977049742e-05, "loss": 0.4491, "step": 6662 }, { "epoch": 1.705536, "grad_norm": 2.03125, "learning_rate": 2.1580923129425816e-05, "loss": 0.4446, "step": 6663 }, { "epoch": 1.705792, "grad_norm": 2.03125, "learning_rate": 2.1576657281801897e-05, "loss": 0.4226, "step": 6664 }, { "epoch": 1.706048, "grad_norm": 2.015625, "learning_rate": 2.157239143417797e-05, "loss": 0.4494, "step": 6665 }, { "epoch": 1.706304, "grad_norm": 1.8203125, "learning_rate": 2.156812558655405e-05, "loss": 0.4414, "step": 6666 }, { "epoch": 1.70656, "grad_norm": 1.96875, "learning_rate": 2.1563859738930127e-05, "loss": 0.405, "step": 6667 }, { "epoch": 1.7068159999999999, "grad_norm": 1.984375, "learning_rate": 2.1559593891306204e-05, "loss": 0.4334, "step": 6668 }, { "epoch": 1.7070720000000001, "grad_norm": 1.8984375, "learning_rate": 2.155532804368228e-05, "loss": 0.4157, "step": 6669 }, { "epoch": 1.707328, "grad_norm": 2.0625, "learning_rate": 2.155106219605836e-05, "loss": 0.4208, "step": 6670 }, { "epoch": 1.707584, "grad_norm": 1.96875, "learning_rate": 2.1546796348434434e-05, "loss": 0.4683, "step": 6671 }, { "epoch": 1.70784, "grad_norm": 1.953125, "learning_rate": 2.154253050081051e-05, "loss": 0.4207, "step": 6672 }, { "epoch": 1.7080959999999998, "grad_norm": 2.3125, "learning_rate": 2.153826465318659e-05, "loss": 0.4113, "step": 6673 }, { "epoch": 1.708352, "grad_norm": 2.0625, "learning_rate": 2.1533998805562667e-05, "loss": 0.4455, "step": 6674 }, { "epoch": 1.708608, "grad_norm": 2.046875, "learning_rate": 2.1529732957938744e-05, "loss": 0.4552, "step": 6675 }, { "epoch": 1.7088640000000002, "grad_norm": 1.9609375, "learning_rate": 2.152546711031482e-05, "loss": 0.4657, "step": 6676 }, { "epoch": 1.70912, "grad_norm": 1.9921875, "learning_rate": 2.15212012626909e-05, "loss": 0.4369, "step": 6677 }, { "epoch": 1.709376, "grad_norm": 1.921875, "learning_rate": 2.1516935415066974e-05, "loss": 0.4348, "step": 6678 }, { "epoch": 1.709632, "grad_norm": 2.03125, "learning_rate": 2.1512669567443052e-05, "loss": 0.434, "step": 6679 }, { "epoch": 1.7098879999999999, "grad_norm": 2.109375, "learning_rate": 2.150840371981913e-05, "loss": 0.4176, "step": 6680 }, { "epoch": 1.710144, "grad_norm": 1.921875, "learning_rate": 2.1504137872195207e-05, "loss": 0.4239, "step": 6681 }, { "epoch": 1.7104, "grad_norm": 2.0625, "learning_rate": 2.149987202457128e-05, "loss": 0.4117, "step": 6682 }, { "epoch": 1.710656, "grad_norm": 1.828125, "learning_rate": 2.1495606176947362e-05, "loss": 0.4384, "step": 6683 }, { "epoch": 1.710912, "grad_norm": 2.109375, "learning_rate": 2.1491340329323437e-05, "loss": 0.4362, "step": 6684 }, { "epoch": 1.711168, "grad_norm": 2.015625, "learning_rate": 2.1487074481699514e-05, "loss": 0.4481, "step": 6685 }, { "epoch": 1.711424, "grad_norm": 1.9765625, "learning_rate": 2.1482808634075592e-05, "loss": 0.4252, "step": 6686 }, { "epoch": 1.7116799999999999, "grad_norm": 2.203125, "learning_rate": 2.147854278645167e-05, "loss": 0.4472, "step": 6687 }, { "epoch": 1.7119360000000001, "grad_norm": 2.046875, "learning_rate": 2.1474276938827744e-05, "loss": 0.4502, "step": 6688 }, { "epoch": 1.712192, "grad_norm": 2.0, "learning_rate": 2.1470011091203825e-05, "loss": 0.4234, "step": 6689 }, { "epoch": 1.712448, "grad_norm": 2.125, "learning_rate": 2.1465745243579903e-05, "loss": 0.4104, "step": 6690 }, { "epoch": 1.712704, "grad_norm": 2.203125, "learning_rate": 2.1461479395955977e-05, "loss": 0.4384, "step": 6691 }, { "epoch": 1.71296, "grad_norm": 1.8984375, "learning_rate": 2.1457213548332054e-05, "loss": 0.448, "step": 6692 }, { "epoch": 1.713216, "grad_norm": 2.078125, "learning_rate": 2.1452947700708132e-05, "loss": 0.4095, "step": 6693 }, { "epoch": 1.7134719999999999, "grad_norm": 1.8515625, "learning_rate": 2.144868185308421e-05, "loss": 0.45, "step": 6694 }, { "epoch": 1.7137280000000001, "grad_norm": 2.078125, "learning_rate": 2.1444416005460284e-05, "loss": 0.4046, "step": 6695 }, { "epoch": 1.713984, "grad_norm": 2.078125, "learning_rate": 2.1440150157836365e-05, "loss": 0.427, "step": 6696 }, { "epoch": 1.71424, "grad_norm": 2.09375, "learning_rate": 2.143588431021244e-05, "loss": 0.419, "step": 6697 }, { "epoch": 1.714496, "grad_norm": 2.140625, "learning_rate": 2.1431618462588517e-05, "loss": 0.4362, "step": 6698 }, { "epoch": 1.714752, "grad_norm": 2.0625, "learning_rate": 2.1427352614964595e-05, "loss": 0.4198, "step": 6699 }, { "epoch": 1.715008, "grad_norm": 2.015625, "learning_rate": 2.1423086767340672e-05, "loss": 0.4374, "step": 6700 }, { "epoch": 1.715264, "grad_norm": 1.8984375, "learning_rate": 2.1418820919716747e-05, "loss": 0.3889, "step": 6701 }, { "epoch": 1.7155200000000002, "grad_norm": 2.0, "learning_rate": 2.1414555072092828e-05, "loss": 0.3824, "step": 6702 }, { "epoch": 1.715776, "grad_norm": 2.09375, "learning_rate": 2.1410289224468902e-05, "loss": 0.4609, "step": 6703 }, { "epoch": 1.716032, "grad_norm": 2.078125, "learning_rate": 2.140602337684498e-05, "loss": 0.4569, "step": 6704 }, { "epoch": 1.716288, "grad_norm": 2.0625, "learning_rate": 2.1401757529221057e-05, "loss": 0.4256, "step": 6705 }, { "epoch": 1.7165439999999998, "grad_norm": 1.9140625, "learning_rate": 2.1397491681597135e-05, "loss": 0.4187, "step": 6706 }, { "epoch": 1.7168, "grad_norm": 1.90625, "learning_rate": 2.1393225833973212e-05, "loss": 0.4429, "step": 6707 }, { "epoch": 1.717056, "grad_norm": 1.921875, "learning_rate": 2.1388959986349287e-05, "loss": 0.4501, "step": 6708 }, { "epoch": 1.717312, "grad_norm": 1.90625, "learning_rate": 2.1384694138725368e-05, "loss": 0.4458, "step": 6709 }, { "epoch": 1.717568, "grad_norm": 1.890625, "learning_rate": 2.1380428291101442e-05, "loss": 0.4114, "step": 6710 }, { "epoch": 1.717824, "grad_norm": 1.96875, "learning_rate": 2.137616244347752e-05, "loss": 0.4053, "step": 6711 }, { "epoch": 1.71808, "grad_norm": 1.9921875, "learning_rate": 2.1371896595853597e-05, "loss": 0.4422, "step": 6712 }, { "epoch": 1.7183359999999999, "grad_norm": 1.8828125, "learning_rate": 2.1367630748229675e-05, "loss": 0.4636, "step": 6713 }, { "epoch": 1.7185920000000001, "grad_norm": 1.9765625, "learning_rate": 2.136336490060575e-05, "loss": 0.4663, "step": 6714 }, { "epoch": 1.718848, "grad_norm": 1.78125, "learning_rate": 2.135909905298183e-05, "loss": 0.441, "step": 6715 }, { "epoch": 1.719104, "grad_norm": 1.9453125, "learning_rate": 2.1354833205357905e-05, "loss": 0.456, "step": 6716 }, { "epoch": 1.71936, "grad_norm": 2.03125, "learning_rate": 2.1350567357733982e-05, "loss": 0.4757, "step": 6717 }, { "epoch": 1.719616, "grad_norm": 2.0, "learning_rate": 2.134630151011006e-05, "loss": 0.4194, "step": 6718 }, { "epoch": 1.719872, "grad_norm": 1.875, "learning_rate": 2.1342035662486138e-05, "loss": 0.4108, "step": 6719 }, { "epoch": 1.7201279999999999, "grad_norm": 1.921875, "learning_rate": 2.1337769814862212e-05, "loss": 0.4051, "step": 6720 }, { "epoch": 1.7203840000000001, "grad_norm": 1.9765625, "learning_rate": 2.1333503967238293e-05, "loss": 0.4598, "step": 6721 }, { "epoch": 1.72064, "grad_norm": 2.03125, "learning_rate": 2.1329238119614367e-05, "loss": 0.4325, "step": 6722 }, { "epoch": 1.720896, "grad_norm": 2.15625, "learning_rate": 2.1324972271990445e-05, "loss": 0.4377, "step": 6723 }, { "epoch": 1.721152, "grad_norm": 2.0625, "learning_rate": 2.1320706424366522e-05, "loss": 0.4191, "step": 6724 }, { "epoch": 1.721408, "grad_norm": 1.8828125, "learning_rate": 2.13164405767426e-05, "loss": 0.4063, "step": 6725 }, { "epoch": 1.721664, "grad_norm": 2.046875, "learning_rate": 2.1312174729118678e-05, "loss": 0.4652, "step": 6726 }, { "epoch": 1.72192, "grad_norm": 2.140625, "learning_rate": 2.1307908881494752e-05, "loss": 0.4156, "step": 6727 }, { "epoch": 1.7221760000000002, "grad_norm": 1.890625, "learning_rate": 2.1303643033870833e-05, "loss": 0.4464, "step": 6728 }, { "epoch": 1.722432, "grad_norm": 2.0625, "learning_rate": 2.1299377186246907e-05, "loss": 0.3801, "step": 6729 }, { "epoch": 1.722688, "grad_norm": 2.0625, "learning_rate": 2.1295111338622985e-05, "loss": 0.4094, "step": 6730 }, { "epoch": 1.722944, "grad_norm": 2.046875, "learning_rate": 2.1290845490999063e-05, "loss": 0.4097, "step": 6731 }, { "epoch": 1.7231999999999998, "grad_norm": 1.9140625, "learning_rate": 2.128657964337514e-05, "loss": 0.4818, "step": 6732 }, { "epoch": 1.723456, "grad_norm": 2.09375, "learning_rate": 2.1282313795751215e-05, "loss": 0.426, "step": 6733 }, { "epoch": 1.723712, "grad_norm": 1.984375, "learning_rate": 2.1278047948127296e-05, "loss": 0.4301, "step": 6734 }, { "epoch": 1.723968, "grad_norm": 2.046875, "learning_rate": 2.127378210050337e-05, "loss": 0.4416, "step": 6735 }, { "epoch": 1.724224, "grad_norm": 2.015625, "learning_rate": 2.1269516252879448e-05, "loss": 0.3973, "step": 6736 }, { "epoch": 1.72448, "grad_norm": 2.109375, "learning_rate": 2.1265250405255525e-05, "loss": 0.4315, "step": 6737 }, { "epoch": 1.724736, "grad_norm": 1.96875, "learning_rate": 2.1260984557631603e-05, "loss": 0.4329, "step": 6738 }, { "epoch": 1.7249919999999999, "grad_norm": 1.90625, "learning_rate": 2.125671871000768e-05, "loss": 0.4263, "step": 6739 }, { "epoch": 1.7252480000000001, "grad_norm": 2.078125, "learning_rate": 2.1252452862383758e-05, "loss": 0.4522, "step": 6740 }, { "epoch": 1.725504, "grad_norm": 2.015625, "learning_rate": 2.1248187014759836e-05, "loss": 0.4018, "step": 6741 }, { "epoch": 1.72576, "grad_norm": 1.9921875, "learning_rate": 2.124392116713591e-05, "loss": 0.4719, "step": 6742 }, { "epoch": 1.726016, "grad_norm": 1.96875, "learning_rate": 2.1239655319511988e-05, "loss": 0.4274, "step": 6743 }, { "epoch": 1.726272, "grad_norm": 1.953125, "learning_rate": 2.1235389471888065e-05, "loss": 0.408, "step": 6744 }, { "epoch": 1.726528, "grad_norm": 2.078125, "learning_rate": 2.1231123624264143e-05, "loss": 0.4457, "step": 6745 }, { "epoch": 1.7267839999999999, "grad_norm": 2.0625, "learning_rate": 2.1226857776640217e-05, "loss": 0.4078, "step": 6746 }, { "epoch": 1.7270400000000001, "grad_norm": 1.9296875, "learning_rate": 2.12225919290163e-05, "loss": 0.4334, "step": 6747 }, { "epoch": 1.727296, "grad_norm": 2.109375, "learning_rate": 2.1218326081392373e-05, "loss": 0.4382, "step": 6748 }, { "epoch": 1.727552, "grad_norm": 1.8828125, "learning_rate": 2.121406023376845e-05, "loss": 0.4361, "step": 6749 }, { "epoch": 1.727808, "grad_norm": 2.03125, "learning_rate": 2.1209794386144528e-05, "loss": 0.4362, "step": 6750 }, { "epoch": 1.728064, "grad_norm": 2.0, "learning_rate": 2.1205528538520606e-05, "loss": 0.4136, "step": 6751 }, { "epoch": 1.72832, "grad_norm": 2.015625, "learning_rate": 2.120126269089668e-05, "loss": 0.4505, "step": 6752 }, { "epoch": 1.728576, "grad_norm": 2.046875, "learning_rate": 2.119699684327276e-05, "loss": 0.4464, "step": 6753 }, { "epoch": 1.7288320000000001, "grad_norm": 2.203125, "learning_rate": 2.1192730995648835e-05, "loss": 0.4281, "step": 6754 }, { "epoch": 1.729088, "grad_norm": 1.9921875, "learning_rate": 2.1188465148024913e-05, "loss": 0.4089, "step": 6755 }, { "epoch": 1.729344, "grad_norm": 1.8671875, "learning_rate": 2.118419930040099e-05, "loss": 0.3902, "step": 6756 }, { "epoch": 1.7296, "grad_norm": 2.0625, "learning_rate": 2.1179933452777068e-05, "loss": 0.4305, "step": 6757 }, { "epoch": 1.7298559999999998, "grad_norm": 1.8046875, "learning_rate": 2.1175667605153146e-05, "loss": 0.4342, "step": 6758 }, { "epoch": 1.730112, "grad_norm": 2.0, "learning_rate": 2.1171401757529223e-05, "loss": 0.4652, "step": 6759 }, { "epoch": 1.730368, "grad_norm": 2.015625, "learning_rate": 2.11671359099053e-05, "loss": 0.4267, "step": 6760 }, { "epoch": 1.7306240000000002, "grad_norm": 1.96875, "learning_rate": 2.1162870062281375e-05, "loss": 0.3846, "step": 6761 }, { "epoch": 1.73088, "grad_norm": 1.90625, "learning_rate": 2.1158604214657453e-05, "loss": 0.4643, "step": 6762 }, { "epoch": 1.731136, "grad_norm": 1.953125, "learning_rate": 2.115433836703353e-05, "loss": 0.4016, "step": 6763 }, { "epoch": 1.731392, "grad_norm": 1.8828125, "learning_rate": 2.1150072519409608e-05, "loss": 0.4483, "step": 6764 }, { "epoch": 1.7316479999999999, "grad_norm": 2.109375, "learning_rate": 2.1145806671785683e-05, "loss": 0.436, "step": 6765 }, { "epoch": 1.731904, "grad_norm": 2.03125, "learning_rate": 2.1141540824161764e-05, "loss": 0.4633, "step": 6766 }, { "epoch": 1.73216, "grad_norm": 2.078125, "learning_rate": 2.1137274976537838e-05, "loss": 0.4298, "step": 6767 }, { "epoch": 1.732416, "grad_norm": 1.9140625, "learning_rate": 2.1133009128913916e-05, "loss": 0.4497, "step": 6768 }, { "epoch": 1.732672, "grad_norm": 1.8671875, "learning_rate": 2.1128743281289993e-05, "loss": 0.4158, "step": 6769 }, { "epoch": 1.732928, "grad_norm": 1.8203125, "learning_rate": 2.112447743366607e-05, "loss": 0.4219, "step": 6770 }, { "epoch": 1.733184, "grad_norm": 1.8671875, "learning_rate": 2.1120211586042145e-05, "loss": 0.4641, "step": 6771 }, { "epoch": 1.7334399999999999, "grad_norm": 1.9140625, "learning_rate": 2.1115945738418226e-05, "loss": 0.4064, "step": 6772 }, { "epoch": 1.7336960000000001, "grad_norm": 1.9296875, "learning_rate": 2.1111679890794304e-05, "loss": 0.4466, "step": 6773 }, { "epoch": 1.733952, "grad_norm": 2.09375, "learning_rate": 2.1107414043170378e-05, "loss": 0.3976, "step": 6774 }, { "epoch": 1.734208, "grad_norm": 2.09375, "learning_rate": 2.1103148195546456e-05, "loss": 0.4284, "step": 6775 }, { "epoch": 1.734464, "grad_norm": 2.0, "learning_rate": 2.1098882347922533e-05, "loss": 0.4522, "step": 6776 }, { "epoch": 1.73472, "grad_norm": 2.15625, "learning_rate": 2.109461650029861e-05, "loss": 0.4141, "step": 6777 }, { "epoch": 1.734976, "grad_norm": 2.046875, "learning_rate": 2.1090350652674685e-05, "loss": 0.4451, "step": 6778 }, { "epoch": 1.7352319999999999, "grad_norm": 2.0625, "learning_rate": 2.1086084805050766e-05, "loss": 0.4541, "step": 6779 }, { "epoch": 1.7354880000000001, "grad_norm": 1.9921875, "learning_rate": 2.108181895742684e-05, "loss": 0.4347, "step": 6780 }, { "epoch": 1.735744, "grad_norm": 1.859375, "learning_rate": 2.1077553109802918e-05, "loss": 0.4276, "step": 6781 }, { "epoch": 1.736, "grad_norm": 1.984375, "learning_rate": 2.1073287262178996e-05, "loss": 0.4825, "step": 6782 }, { "epoch": 1.736256, "grad_norm": 1.8203125, "learning_rate": 2.1069021414555074e-05, "loss": 0.4221, "step": 6783 }, { "epoch": 1.7365119999999998, "grad_norm": 1.9453125, "learning_rate": 2.1064755566931148e-05, "loss": 0.4508, "step": 6784 }, { "epoch": 1.736768, "grad_norm": 1.921875, "learning_rate": 2.106048971930723e-05, "loss": 0.4064, "step": 6785 }, { "epoch": 1.737024, "grad_norm": 1.859375, "learning_rate": 2.1056223871683303e-05, "loss": 0.4513, "step": 6786 }, { "epoch": 1.7372800000000002, "grad_norm": 2.0, "learning_rate": 2.105195802405938e-05, "loss": 0.3878, "step": 6787 }, { "epoch": 1.737536, "grad_norm": 1.9765625, "learning_rate": 2.104769217643546e-05, "loss": 0.4688, "step": 6788 }, { "epoch": 1.737792, "grad_norm": 1.9609375, "learning_rate": 2.1043426328811536e-05, "loss": 0.4347, "step": 6789 }, { "epoch": 1.738048, "grad_norm": 1.9765625, "learning_rate": 2.1039160481187614e-05, "loss": 0.4254, "step": 6790 }, { "epoch": 1.7383039999999998, "grad_norm": 2.015625, "learning_rate": 2.103489463356369e-05, "loss": 0.4283, "step": 6791 }, { "epoch": 1.73856, "grad_norm": 2.015625, "learning_rate": 2.103062878593977e-05, "loss": 0.4132, "step": 6792 }, { "epoch": 1.738816, "grad_norm": 1.8828125, "learning_rate": 2.1026362938315843e-05, "loss": 0.4379, "step": 6793 }, { "epoch": 1.739072, "grad_norm": 1.90625, "learning_rate": 2.102209709069192e-05, "loss": 0.3906, "step": 6794 }, { "epoch": 1.739328, "grad_norm": 1.984375, "learning_rate": 2.1017831243068e-05, "loss": 0.4881, "step": 6795 }, { "epoch": 1.739584, "grad_norm": 2.203125, "learning_rate": 2.1013565395444076e-05, "loss": 0.4396, "step": 6796 }, { "epoch": 1.73984, "grad_norm": 2.171875, "learning_rate": 2.100929954782015e-05, "loss": 0.4155, "step": 6797 }, { "epoch": 1.7400959999999999, "grad_norm": 1.8828125, "learning_rate": 2.100503370019623e-05, "loss": 0.4314, "step": 6798 }, { "epoch": 1.7403520000000001, "grad_norm": 1.875, "learning_rate": 2.1000767852572306e-05, "loss": 0.4384, "step": 6799 }, { "epoch": 1.740608, "grad_norm": 1.9453125, "learning_rate": 2.0996502004948384e-05, "loss": 0.4832, "step": 6800 }, { "epoch": 1.740864, "grad_norm": 2.046875, "learning_rate": 2.099223615732446e-05, "loss": 0.4346, "step": 6801 }, { "epoch": 1.74112, "grad_norm": 2.015625, "learning_rate": 2.098797030970054e-05, "loss": 0.463, "step": 6802 }, { "epoch": 1.741376, "grad_norm": 2.0, "learning_rate": 2.0983704462076613e-05, "loss": 0.4102, "step": 6803 }, { "epoch": 1.741632, "grad_norm": 2.015625, "learning_rate": 2.0979438614452694e-05, "loss": 0.4501, "step": 6804 }, { "epoch": 1.7418879999999999, "grad_norm": 1.8828125, "learning_rate": 2.0975172766828772e-05, "loss": 0.4235, "step": 6805 }, { "epoch": 1.7421440000000001, "grad_norm": 1.8984375, "learning_rate": 2.0970906919204846e-05, "loss": 0.4249, "step": 6806 }, { "epoch": 1.7424, "grad_norm": 2.03125, "learning_rate": 2.0966641071580924e-05, "loss": 0.4065, "step": 6807 }, { "epoch": 1.742656, "grad_norm": 1.8203125, "learning_rate": 2.0962375223957e-05, "loss": 0.3991, "step": 6808 }, { "epoch": 1.742912, "grad_norm": 1.9921875, "learning_rate": 2.095810937633308e-05, "loss": 0.4457, "step": 6809 }, { "epoch": 1.743168, "grad_norm": 2.0625, "learning_rate": 2.0953843528709157e-05, "loss": 0.4306, "step": 6810 }, { "epoch": 1.743424, "grad_norm": 2.015625, "learning_rate": 2.0949577681085234e-05, "loss": 0.4088, "step": 6811 }, { "epoch": 1.74368, "grad_norm": 1.8984375, "learning_rate": 2.094531183346131e-05, "loss": 0.4272, "step": 6812 }, { "epoch": 1.7439360000000002, "grad_norm": 2.046875, "learning_rate": 2.0941045985837386e-05, "loss": 0.4162, "step": 6813 }, { "epoch": 1.744192, "grad_norm": 1.984375, "learning_rate": 2.0936780138213464e-05, "loss": 0.4826, "step": 6814 }, { "epoch": 1.744448, "grad_norm": 1.8828125, "learning_rate": 2.093251429058954e-05, "loss": 0.457, "step": 6815 }, { "epoch": 1.744704, "grad_norm": 1.9296875, "learning_rate": 2.0928248442965616e-05, "loss": 0.4373, "step": 6816 }, { "epoch": 1.7449599999999998, "grad_norm": 2.125, "learning_rate": 2.0923982595341697e-05, "loss": 0.4156, "step": 6817 }, { "epoch": 1.745216, "grad_norm": 1.8984375, "learning_rate": 2.091971674771777e-05, "loss": 0.443, "step": 6818 }, { "epoch": 1.745472, "grad_norm": 2.09375, "learning_rate": 2.091545090009385e-05, "loss": 0.4645, "step": 6819 }, { "epoch": 1.745728, "grad_norm": 1.796875, "learning_rate": 2.0911185052469926e-05, "loss": 0.4741, "step": 6820 }, { "epoch": 1.745984, "grad_norm": 2.046875, "learning_rate": 2.0906919204846004e-05, "loss": 0.4487, "step": 6821 }, { "epoch": 1.74624, "grad_norm": 2.109375, "learning_rate": 2.0902653357222082e-05, "loss": 0.4293, "step": 6822 }, { "epoch": 1.746496, "grad_norm": 1.8671875, "learning_rate": 2.089838750959816e-05, "loss": 0.4542, "step": 6823 }, { "epoch": 1.7467519999999999, "grad_norm": 1.9921875, "learning_rate": 2.0894121661974237e-05, "loss": 0.3921, "step": 6824 }, { "epoch": 1.7470080000000001, "grad_norm": 1.90625, "learning_rate": 2.088985581435031e-05, "loss": 0.4148, "step": 6825 }, { "epoch": 1.747264, "grad_norm": 1.90625, "learning_rate": 2.088558996672639e-05, "loss": 0.4222, "step": 6826 }, { "epoch": 1.74752, "grad_norm": 2.0625, "learning_rate": 2.0881324119102467e-05, "loss": 0.4628, "step": 6827 }, { "epoch": 1.747776, "grad_norm": 2.046875, "learning_rate": 2.0877058271478544e-05, "loss": 0.4011, "step": 6828 }, { "epoch": 1.748032, "grad_norm": 2.0, "learning_rate": 2.087279242385462e-05, "loss": 0.4109, "step": 6829 }, { "epoch": 1.748288, "grad_norm": 2.015625, "learning_rate": 2.08685265762307e-05, "loss": 0.4165, "step": 6830 }, { "epoch": 1.7485439999999999, "grad_norm": 1.828125, "learning_rate": 2.0864260728606774e-05, "loss": 0.4424, "step": 6831 }, { "epoch": 1.7488000000000001, "grad_norm": 1.9296875, "learning_rate": 2.085999488098285e-05, "loss": 0.4598, "step": 6832 }, { "epoch": 1.749056, "grad_norm": 2.078125, "learning_rate": 2.085572903335893e-05, "loss": 0.423, "step": 6833 }, { "epoch": 1.749312, "grad_norm": 2.078125, "learning_rate": 2.0851463185735007e-05, "loss": 0.4586, "step": 6834 }, { "epoch": 1.749568, "grad_norm": 1.9921875, "learning_rate": 2.084719733811108e-05, "loss": 0.4481, "step": 6835 }, { "epoch": 1.749824, "grad_norm": 1.859375, "learning_rate": 2.0842931490487162e-05, "loss": 0.4226, "step": 6836 }, { "epoch": 1.75008, "grad_norm": 1.7578125, "learning_rate": 2.083866564286324e-05, "loss": 0.4159, "step": 6837 }, { "epoch": 1.750336, "grad_norm": 1.9296875, "learning_rate": 2.0834399795239314e-05, "loss": 0.3925, "step": 6838 }, { "epoch": 1.7505920000000001, "grad_norm": 2.171875, "learning_rate": 2.0830133947615392e-05, "loss": 0.4141, "step": 6839 }, { "epoch": 1.750848, "grad_norm": 1.9609375, "learning_rate": 2.082586809999147e-05, "loss": 0.4351, "step": 6840 }, { "epoch": 1.751104, "grad_norm": 1.9453125, "learning_rate": 2.0821602252367547e-05, "loss": 0.4267, "step": 6841 }, { "epoch": 1.75136, "grad_norm": 1.953125, "learning_rate": 2.0817336404743625e-05, "loss": 0.4021, "step": 6842 }, { "epoch": 1.7516159999999998, "grad_norm": 1.921875, "learning_rate": 2.0813070557119702e-05, "loss": 0.4348, "step": 6843 }, { "epoch": 1.751872, "grad_norm": 1.875, "learning_rate": 2.0808804709495777e-05, "loss": 0.3908, "step": 6844 }, { "epoch": 1.752128, "grad_norm": 1.953125, "learning_rate": 2.0804538861871854e-05, "loss": 0.4877, "step": 6845 }, { "epoch": 1.7523840000000002, "grad_norm": 1.96875, "learning_rate": 2.0800273014247932e-05, "loss": 0.4198, "step": 6846 }, { "epoch": 1.75264, "grad_norm": 2.046875, "learning_rate": 2.079600716662401e-05, "loss": 0.4649, "step": 6847 }, { "epoch": 1.752896, "grad_norm": 2.03125, "learning_rate": 2.0791741319000084e-05, "loss": 0.4334, "step": 6848 }, { "epoch": 1.753152, "grad_norm": 2.046875, "learning_rate": 2.0787475471376165e-05, "loss": 0.4689, "step": 6849 }, { "epoch": 1.7534079999999999, "grad_norm": 2.09375, "learning_rate": 2.078320962375224e-05, "loss": 0.408, "step": 6850 }, { "epoch": 1.7536640000000001, "grad_norm": 1.9140625, "learning_rate": 2.0778943776128317e-05, "loss": 0.4854, "step": 6851 }, { "epoch": 1.75392, "grad_norm": 2.0625, "learning_rate": 2.0774677928504394e-05, "loss": 0.4321, "step": 6852 }, { "epoch": 1.754176, "grad_norm": 1.9375, "learning_rate": 2.0770412080880472e-05, "loss": 0.4483, "step": 6853 }, { "epoch": 1.754432, "grad_norm": 1.9453125, "learning_rate": 2.076614623325655e-05, "loss": 0.3974, "step": 6854 }, { "epoch": 1.754688, "grad_norm": 1.890625, "learning_rate": 2.0761880385632627e-05, "loss": 0.4432, "step": 6855 }, { "epoch": 1.754944, "grad_norm": 2.015625, "learning_rate": 2.0757614538008705e-05, "loss": 0.4412, "step": 6856 }, { "epoch": 1.7551999999999999, "grad_norm": 1.9375, "learning_rate": 2.075334869038478e-05, "loss": 0.4632, "step": 6857 }, { "epoch": 1.7554560000000001, "grad_norm": 1.921875, "learning_rate": 2.0749082842760857e-05, "loss": 0.4312, "step": 6858 }, { "epoch": 1.755712, "grad_norm": 1.90625, "learning_rate": 2.0744816995136935e-05, "loss": 0.4275, "step": 6859 }, { "epoch": 1.755968, "grad_norm": 1.859375, "learning_rate": 2.0740551147513012e-05, "loss": 0.4294, "step": 6860 }, { "epoch": 1.756224, "grad_norm": 1.921875, "learning_rate": 2.073628529988909e-05, "loss": 0.4793, "step": 6861 }, { "epoch": 1.75648, "grad_norm": 1.8828125, "learning_rate": 2.0732019452265168e-05, "loss": 0.4133, "step": 6862 }, { "epoch": 1.756736, "grad_norm": 1.9609375, "learning_rate": 2.0727753604641242e-05, "loss": 0.4473, "step": 6863 }, { "epoch": 1.7569919999999999, "grad_norm": 1.8515625, "learning_rate": 2.072348775701732e-05, "loss": 0.4288, "step": 6864 }, { "epoch": 1.7572480000000001, "grad_norm": 2.046875, "learning_rate": 2.0719221909393397e-05, "loss": 0.4337, "step": 6865 }, { "epoch": 1.757504, "grad_norm": 1.8046875, "learning_rate": 2.0714956061769475e-05, "loss": 0.4287, "step": 6866 }, { "epoch": 1.75776, "grad_norm": 1.84375, "learning_rate": 2.071069021414555e-05, "loss": 0.411, "step": 6867 }, { "epoch": 1.758016, "grad_norm": 1.90625, "learning_rate": 2.070642436652163e-05, "loss": 0.4398, "step": 6868 }, { "epoch": 1.7582719999999998, "grad_norm": 1.8671875, "learning_rate": 2.0702158518897704e-05, "loss": 0.4299, "step": 6869 }, { "epoch": 1.758528, "grad_norm": 2.03125, "learning_rate": 2.0697892671273782e-05, "loss": 0.4453, "step": 6870 }, { "epoch": 1.758784, "grad_norm": 2.0, "learning_rate": 2.0693626823649863e-05, "loss": 0.4296, "step": 6871 }, { "epoch": 1.7590400000000002, "grad_norm": 2.21875, "learning_rate": 2.0689360976025937e-05, "loss": 0.4321, "step": 6872 }, { "epoch": 1.759296, "grad_norm": 1.828125, "learning_rate": 2.0685095128402015e-05, "loss": 0.4142, "step": 6873 }, { "epoch": 1.759552, "grad_norm": 1.9453125, "learning_rate": 2.0680829280778093e-05, "loss": 0.408, "step": 6874 }, { "epoch": 1.759808, "grad_norm": 1.8046875, "learning_rate": 2.067656343315417e-05, "loss": 0.4475, "step": 6875 }, { "epoch": 1.7600639999999999, "grad_norm": 2.140625, "learning_rate": 2.0672297585530245e-05, "loss": 0.4443, "step": 6876 }, { "epoch": 1.76032, "grad_norm": 1.84375, "learning_rate": 2.0668031737906322e-05, "loss": 0.4222, "step": 6877 }, { "epoch": 1.760576, "grad_norm": 1.9453125, "learning_rate": 2.06637658902824e-05, "loss": 0.4096, "step": 6878 }, { "epoch": 1.760832, "grad_norm": 1.8203125, "learning_rate": 2.0659500042658478e-05, "loss": 0.4367, "step": 6879 }, { "epoch": 1.761088, "grad_norm": 2.0, "learning_rate": 2.0655234195034552e-05, "loss": 0.4161, "step": 6880 }, { "epoch": 1.761344, "grad_norm": 1.9765625, "learning_rate": 2.0650968347410633e-05, "loss": 0.4295, "step": 6881 }, { "epoch": 1.7616, "grad_norm": 1.9296875, "learning_rate": 2.0646702499786707e-05, "loss": 0.4322, "step": 6882 }, { "epoch": 1.7618559999999999, "grad_norm": 2.0625, "learning_rate": 2.0642436652162785e-05, "loss": 0.4095, "step": 6883 }, { "epoch": 1.7621120000000001, "grad_norm": 2.03125, "learning_rate": 2.0638170804538862e-05, "loss": 0.4425, "step": 6884 }, { "epoch": 1.762368, "grad_norm": 1.96875, "learning_rate": 2.063390495691494e-05, "loss": 0.4315, "step": 6885 }, { "epoch": 1.762624, "grad_norm": 2.0, "learning_rate": 2.0629639109291014e-05, "loss": 0.4213, "step": 6886 }, { "epoch": 1.76288, "grad_norm": 1.953125, "learning_rate": 2.0625373261667095e-05, "loss": 0.4325, "step": 6887 }, { "epoch": 1.763136, "grad_norm": 1.9609375, "learning_rate": 2.0621107414043173e-05, "loss": 0.4213, "step": 6888 }, { "epoch": 1.763392, "grad_norm": 2.15625, "learning_rate": 2.0616841566419247e-05, "loss": 0.4143, "step": 6889 }, { "epoch": 1.7636479999999999, "grad_norm": 2.046875, "learning_rate": 2.0612575718795325e-05, "loss": 0.4501, "step": 6890 }, { "epoch": 1.7639040000000001, "grad_norm": 2.0, "learning_rate": 2.0608309871171403e-05, "loss": 0.3884, "step": 6891 }, { "epoch": 1.76416, "grad_norm": 2.15625, "learning_rate": 2.060404402354748e-05, "loss": 0.4363, "step": 6892 }, { "epoch": 1.764416, "grad_norm": 1.9140625, "learning_rate": 2.0599778175923558e-05, "loss": 0.4276, "step": 6893 }, { "epoch": 1.764672, "grad_norm": 2.0, "learning_rate": 2.0595512328299636e-05, "loss": 0.4405, "step": 6894 }, { "epoch": 1.764928, "grad_norm": 1.96875, "learning_rate": 2.059124648067571e-05, "loss": 0.4308, "step": 6895 }, { "epoch": 1.765184, "grad_norm": 1.9609375, "learning_rate": 2.0586980633051788e-05, "loss": 0.414, "step": 6896 }, { "epoch": 1.76544, "grad_norm": 2.03125, "learning_rate": 2.0582714785427865e-05, "loss": 0.4782, "step": 6897 }, { "epoch": 1.7656960000000002, "grad_norm": 2.03125, "learning_rate": 2.0578448937803943e-05, "loss": 0.4468, "step": 6898 }, { "epoch": 1.765952, "grad_norm": 1.8828125, "learning_rate": 2.0574183090180017e-05, "loss": 0.4366, "step": 6899 }, { "epoch": 1.766208, "grad_norm": 2.0, "learning_rate": 2.0569917242556098e-05, "loss": 0.4475, "step": 6900 }, { "epoch": 1.766464, "grad_norm": 2.078125, "learning_rate": 2.0565651394932172e-05, "loss": 0.4315, "step": 6901 }, { "epoch": 1.7667199999999998, "grad_norm": 1.8984375, "learning_rate": 2.056138554730825e-05, "loss": 0.479, "step": 6902 }, { "epoch": 1.766976, "grad_norm": 1.8984375, "learning_rate": 2.055711969968433e-05, "loss": 0.4305, "step": 6903 }, { "epoch": 1.767232, "grad_norm": 1.984375, "learning_rate": 2.0552853852060405e-05, "loss": 0.4321, "step": 6904 }, { "epoch": 1.767488, "grad_norm": 1.9765625, "learning_rate": 2.0548588004436483e-05, "loss": 0.4444, "step": 6905 }, { "epoch": 1.767744, "grad_norm": 2.046875, "learning_rate": 2.054432215681256e-05, "loss": 0.4232, "step": 6906 }, { "epoch": 1.768, "grad_norm": 1.984375, "learning_rate": 2.054005630918864e-05, "loss": 0.4399, "step": 6907 }, { "epoch": 1.768256, "grad_norm": 1.96875, "learning_rate": 2.0535790461564713e-05, "loss": 0.4209, "step": 6908 }, { "epoch": 1.7685119999999999, "grad_norm": 1.9921875, "learning_rate": 2.053152461394079e-05, "loss": 0.4337, "step": 6909 }, { "epoch": 1.7687680000000001, "grad_norm": 1.890625, "learning_rate": 2.0527258766316868e-05, "loss": 0.4185, "step": 6910 }, { "epoch": 1.769024, "grad_norm": 1.859375, "learning_rate": 2.0522992918692946e-05, "loss": 0.4515, "step": 6911 }, { "epoch": 1.76928, "grad_norm": 1.78125, "learning_rate": 2.0518727071069023e-05, "loss": 0.4148, "step": 6912 }, { "epoch": 1.769536, "grad_norm": 1.9375, "learning_rate": 2.05144612234451e-05, "loss": 0.4665, "step": 6913 }, { "epoch": 1.769792, "grad_norm": 1.828125, "learning_rate": 2.0510195375821175e-05, "loss": 0.4447, "step": 6914 }, { "epoch": 1.770048, "grad_norm": 1.875, "learning_rate": 2.0505929528197253e-05, "loss": 0.3845, "step": 6915 }, { "epoch": 1.7703039999999999, "grad_norm": 1.9375, "learning_rate": 2.050166368057333e-05, "loss": 0.442, "step": 6916 }, { "epoch": 1.7705600000000001, "grad_norm": 1.984375, "learning_rate": 2.0497397832949408e-05, "loss": 0.4146, "step": 6917 }, { "epoch": 1.770816, "grad_norm": 1.9921875, "learning_rate": 2.0493131985325482e-05, "loss": 0.4689, "step": 6918 }, { "epoch": 1.771072, "grad_norm": 2.1875, "learning_rate": 2.0488866137701563e-05, "loss": 0.4293, "step": 6919 }, { "epoch": 1.771328, "grad_norm": 2.0, "learning_rate": 2.048460029007764e-05, "loss": 0.4135, "step": 6920 }, { "epoch": 1.771584, "grad_norm": 1.8828125, "learning_rate": 2.0480334442453715e-05, "loss": 0.4453, "step": 6921 }, { "epoch": 1.77184, "grad_norm": 1.9765625, "learning_rate": 2.0476068594829796e-05, "loss": 0.4675, "step": 6922 }, { "epoch": 1.772096, "grad_norm": 2.1875, "learning_rate": 2.047180274720587e-05, "loss": 0.4506, "step": 6923 }, { "epoch": 1.7723520000000001, "grad_norm": 1.9296875, "learning_rate": 2.046753689958195e-05, "loss": 0.4231, "step": 6924 }, { "epoch": 1.772608, "grad_norm": 1.9140625, "learning_rate": 2.0463271051958026e-05, "loss": 0.4061, "step": 6925 }, { "epoch": 1.772864, "grad_norm": 1.8515625, "learning_rate": 2.0459005204334104e-05, "loss": 0.4062, "step": 6926 }, { "epoch": 1.77312, "grad_norm": 1.953125, "learning_rate": 2.0454739356710178e-05, "loss": 0.4038, "step": 6927 }, { "epoch": 1.7733759999999998, "grad_norm": 2.0, "learning_rate": 2.0450473509086256e-05, "loss": 0.4365, "step": 6928 }, { "epoch": 1.773632, "grad_norm": 2.0625, "learning_rate": 2.0446207661462333e-05, "loss": 0.4324, "step": 6929 }, { "epoch": 1.773888, "grad_norm": 1.828125, "learning_rate": 2.044194181383841e-05, "loss": 0.4126, "step": 6930 }, { "epoch": 1.7741440000000002, "grad_norm": 1.9140625, "learning_rate": 2.0437675966214485e-05, "loss": 0.4469, "step": 6931 }, { "epoch": 1.7744, "grad_norm": 1.921875, "learning_rate": 2.0433410118590566e-05, "loss": 0.4205, "step": 6932 }, { "epoch": 1.774656, "grad_norm": 2.046875, "learning_rate": 2.042914427096664e-05, "loss": 0.4089, "step": 6933 }, { "epoch": 1.774912, "grad_norm": 1.7578125, "learning_rate": 2.0424878423342718e-05, "loss": 0.4664, "step": 6934 }, { "epoch": 1.7751679999999999, "grad_norm": 1.859375, "learning_rate": 2.0420612575718796e-05, "loss": 0.4515, "step": 6935 }, { "epoch": 1.7754240000000001, "grad_norm": 1.8984375, "learning_rate": 2.0416346728094873e-05, "loss": 0.4162, "step": 6936 }, { "epoch": 1.77568, "grad_norm": 1.875, "learning_rate": 2.041208088047095e-05, "loss": 0.4918, "step": 6937 }, { "epoch": 1.775936, "grad_norm": 1.9921875, "learning_rate": 2.040781503284703e-05, "loss": 0.454, "step": 6938 }, { "epoch": 1.776192, "grad_norm": 1.8359375, "learning_rate": 2.0403549185223106e-05, "loss": 0.4184, "step": 6939 }, { "epoch": 1.776448, "grad_norm": 1.90625, "learning_rate": 2.039928333759918e-05, "loss": 0.4445, "step": 6940 }, { "epoch": 1.776704, "grad_norm": 1.9375, "learning_rate": 2.0395017489975258e-05, "loss": 0.447, "step": 6941 }, { "epoch": 1.7769599999999999, "grad_norm": 1.796875, "learning_rate": 2.0390751642351336e-05, "loss": 0.4371, "step": 6942 }, { "epoch": 1.7772160000000001, "grad_norm": 1.8515625, "learning_rate": 2.0386485794727414e-05, "loss": 0.4355, "step": 6943 }, { "epoch": 1.777472, "grad_norm": 1.8828125, "learning_rate": 2.038221994710349e-05, "loss": 0.4212, "step": 6944 }, { "epoch": 1.777728, "grad_norm": 2.015625, "learning_rate": 2.037795409947957e-05, "loss": 0.4177, "step": 6945 }, { "epoch": 1.777984, "grad_norm": 1.96875, "learning_rate": 2.0373688251855643e-05, "loss": 0.4552, "step": 6946 }, { "epoch": 1.77824, "grad_norm": 2.0, "learning_rate": 2.036942240423172e-05, "loss": 0.4197, "step": 6947 }, { "epoch": 1.778496, "grad_norm": 1.8125, "learning_rate": 2.03651565566078e-05, "loss": 0.4453, "step": 6948 }, { "epoch": 1.7787519999999999, "grad_norm": 2.03125, "learning_rate": 2.0360890708983876e-05, "loss": 0.4422, "step": 6949 }, { "epoch": 1.7790080000000001, "grad_norm": 1.8515625, "learning_rate": 2.035662486135995e-05, "loss": 0.4162, "step": 6950 }, { "epoch": 1.779264, "grad_norm": 2.03125, "learning_rate": 2.035235901373603e-05, "loss": 0.4486, "step": 6951 }, { "epoch": 1.77952, "grad_norm": 1.828125, "learning_rate": 2.034809316611211e-05, "loss": 0.4132, "step": 6952 }, { "epoch": 1.779776, "grad_norm": 2.015625, "learning_rate": 2.0343827318488183e-05, "loss": 0.4479, "step": 6953 }, { "epoch": 1.7800319999999998, "grad_norm": 1.953125, "learning_rate": 2.0339561470864264e-05, "loss": 0.4145, "step": 6954 }, { "epoch": 1.780288, "grad_norm": 1.6015625, "learning_rate": 2.033529562324034e-05, "loss": 0.4268, "step": 6955 }, { "epoch": 1.780544, "grad_norm": 1.984375, "learning_rate": 2.0331029775616416e-05, "loss": 0.4216, "step": 6956 }, { "epoch": 1.7808000000000002, "grad_norm": 1.859375, "learning_rate": 2.0326763927992494e-05, "loss": 0.4485, "step": 6957 }, { "epoch": 1.781056, "grad_norm": 1.921875, "learning_rate": 2.032249808036857e-05, "loss": 0.4397, "step": 6958 }, { "epoch": 1.781312, "grad_norm": 2.046875, "learning_rate": 2.0318232232744646e-05, "loss": 0.4568, "step": 6959 }, { "epoch": 1.781568, "grad_norm": 1.8359375, "learning_rate": 2.0313966385120724e-05, "loss": 0.4251, "step": 6960 }, { "epoch": 1.7818239999999999, "grad_norm": 1.921875, "learning_rate": 2.03097005374968e-05, "loss": 0.4321, "step": 6961 }, { "epoch": 1.78208, "grad_norm": 1.7734375, "learning_rate": 2.030543468987288e-05, "loss": 0.4616, "step": 6962 }, { "epoch": 1.782336, "grad_norm": 1.875, "learning_rate": 2.0301168842248957e-05, "loss": 0.4161, "step": 6963 }, { "epoch": 1.782592, "grad_norm": 1.8359375, "learning_rate": 2.0296902994625034e-05, "loss": 0.427, "step": 6964 }, { "epoch": 1.782848, "grad_norm": 1.953125, "learning_rate": 2.029263714700111e-05, "loss": 0.4197, "step": 6965 }, { "epoch": 1.783104, "grad_norm": 1.96875, "learning_rate": 2.0288371299377186e-05, "loss": 0.4561, "step": 6966 }, { "epoch": 1.78336, "grad_norm": 2.078125, "learning_rate": 2.0284105451753264e-05, "loss": 0.4033, "step": 6967 }, { "epoch": 1.7836159999999999, "grad_norm": 1.9296875, "learning_rate": 2.027983960412934e-05, "loss": 0.4291, "step": 6968 }, { "epoch": 1.7838720000000001, "grad_norm": 1.828125, "learning_rate": 2.027557375650542e-05, "loss": 0.4301, "step": 6969 }, { "epoch": 1.784128, "grad_norm": 1.859375, "learning_rate": 2.0271307908881497e-05, "loss": 0.4275, "step": 6970 }, { "epoch": 1.784384, "grad_norm": 1.890625, "learning_rate": 2.0267042061257574e-05, "loss": 0.4653, "step": 6971 }, { "epoch": 1.78464, "grad_norm": 2.015625, "learning_rate": 2.026277621363365e-05, "loss": 0.4729, "step": 6972 }, { "epoch": 1.784896, "grad_norm": 1.828125, "learning_rate": 2.025851036600973e-05, "loss": 0.4587, "step": 6973 }, { "epoch": 1.785152, "grad_norm": 2.015625, "learning_rate": 2.0254244518385804e-05, "loss": 0.4377, "step": 6974 }, { "epoch": 1.7854079999999999, "grad_norm": 2.03125, "learning_rate": 2.024997867076188e-05, "loss": 0.4365, "step": 6975 }, { "epoch": 1.7856640000000001, "grad_norm": 1.875, "learning_rate": 2.024571282313796e-05, "loss": 0.4339, "step": 6976 }, { "epoch": 1.78592, "grad_norm": 1.8046875, "learning_rate": 2.0241446975514037e-05, "loss": 0.4377, "step": 6977 }, { "epoch": 1.786176, "grad_norm": 1.9765625, "learning_rate": 2.023718112789011e-05, "loss": 0.3995, "step": 6978 }, { "epoch": 1.786432, "grad_norm": 1.9765625, "learning_rate": 2.023291528026619e-05, "loss": 0.4305, "step": 6979 }, { "epoch": 1.786688, "grad_norm": 2.140625, "learning_rate": 2.0228649432642266e-05, "loss": 0.4216, "step": 6980 }, { "epoch": 1.786944, "grad_norm": 1.984375, "learning_rate": 2.0224383585018344e-05, "loss": 0.4389, "step": 6981 }, { "epoch": 1.7872, "grad_norm": 2.1875, "learning_rate": 2.022011773739442e-05, "loss": 0.3974, "step": 6982 }, { "epoch": 1.7874560000000002, "grad_norm": 1.9765625, "learning_rate": 2.02158518897705e-05, "loss": 0.462, "step": 6983 }, { "epoch": 1.787712, "grad_norm": 2.046875, "learning_rate": 2.0211586042146574e-05, "loss": 0.507, "step": 6984 }, { "epoch": 1.787968, "grad_norm": 2.046875, "learning_rate": 2.020732019452265e-05, "loss": 0.4191, "step": 6985 }, { "epoch": 1.788224, "grad_norm": 1.7890625, "learning_rate": 2.0203054346898732e-05, "loss": 0.4453, "step": 6986 }, { "epoch": 1.7884799999999998, "grad_norm": 1.828125, "learning_rate": 2.0198788499274807e-05, "loss": 0.4228, "step": 6987 }, { "epoch": 1.788736, "grad_norm": 2.09375, "learning_rate": 2.0194522651650884e-05, "loss": 0.4466, "step": 6988 }, { "epoch": 1.788992, "grad_norm": 2.203125, "learning_rate": 2.0190256804026962e-05, "loss": 0.4393, "step": 6989 }, { "epoch": 1.789248, "grad_norm": 2.203125, "learning_rate": 2.018599095640304e-05, "loss": 0.4428, "step": 6990 }, { "epoch": 1.789504, "grad_norm": 1.9609375, "learning_rate": 2.0181725108779114e-05, "loss": 0.4695, "step": 6991 }, { "epoch": 1.78976, "grad_norm": 1.8828125, "learning_rate": 2.0177459261155195e-05, "loss": 0.4204, "step": 6992 }, { "epoch": 1.790016, "grad_norm": 1.90625, "learning_rate": 2.017319341353127e-05, "loss": 0.4467, "step": 6993 }, { "epoch": 1.7902719999999999, "grad_norm": 2.109375, "learning_rate": 2.0168927565907347e-05, "loss": 0.4202, "step": 6994 }, { "epoch": 1.7905280000000001, "grad_norm": 1.921875, "learning_rate": 2.0164661718283425e-05, "loss": 0.4389, "step": 6995 }, { "epoch": 1.790784, "grad_norm": 1.921875, "learning_rate": 2.0160395870659502e-05, "loss": 0.4629, "step": 6996 }, { "epoch": 1.79104, "grad_norm": 1.8046875, "learning_rate": 2.0156130023035576e-05, "loss": 0.4689, "step": 6997 }, { "epoch": 1.791296, "grad_norm": 1.7890625, "learning_rate": 2.0151864175411654e-05, "loss": 0.3981, "step": 6998 }, { "epoch": 1.791552, "grad_norm": 1.90625, "learning_rate": 2.0147598327787732e-05, "loss": 0.3769, "step": 6999 }, { "epoch": 1.791808, "grad_norm": 1.9609375, "learning_rate": 2.014333248016381e-05, "loss": 0.4149, "step": 7000 }, { "epoch": 1.7920639999999999, "grad_norm": 2.0625, "learning_rate": 2.0139066632539887e-05, "loss": 0.4261, "step": 7001 }, { "epoch": 1.7923200000000001, "grad_norm": 1.8984375, "learning_rate": 2.0134800784915965e-05, "loss": 0.4327, "step": 7002 }, { "epoch": 1.792576, "grad_norm": 1.984375, "learning_rate": 2.0130534937292042e-05, "loss": 0.4188, "step": 7003 }, { "epoch": 1.792832, "grad_norm": 1.7890625, "learning_rate": 2.0126269089668117e-05, "loss": 0.4436, "step": 7004 }, { "epoch": 1.793088, "grad_norm": 1.75, "learning_rate": 2.0122003242044198e-05, "loss": 0.4492, "step": 7005 }, { "epoch": 1.793344, "grad_norm": 2.140625, "learning_rate": 2.0117737394420272e-05, "loss": 0.4121, "step": 7006 }, { "epoch": 1.7936, "grad_norm": 1.8125, "learning_rate": 2.011347154679635e-05, "loss": 0.3985, "step": 7007 }, { "epoch": 1.793856, "grad_norm": 2.125, "learning_rate": 2.0109205699172427e-05, "loss": 0.4387, "step": 7008 }, { "epoch": 1.7941120000000002, "grad_norm": 1.890625, "learning_rate": 2.0104939851548505e-05, "loss": 0.429, "step": 7009 }, { "epoch": 1.794368, "grad_norm": 1.8984375, "learning_rate": 2.010067400392458e-05, "loss": 0.4394, "step": 7010 }, { "epoch": 1.794624, "grad_norm": 1.90625, "learning_rate": 2.0096408156300657e-05, "loss": 0.4142, "step": 7011 }, { "epoch": 1.79488, "grad_norm": 2.015625, "learning_rate": 2.0092142308676734e-05, "loss": 0.4105, "step": 7012 }, { "epoch": 1.7951359999999998, "grad_norm": 2.046875, "learning_rate": 2.0087876461052812e-05, "loss": 0.433, "step": 7013 }, { "epoch": 1.795392, "grad_norm": 1.984375, "learning_rate": 2.008361061342889e-05, "loss": 0.4168, "step": 7014 }, { "epoch": 1.795648, "grad_norm": 2.078125, "learning_rate": 2.0079344765804967e-05, "loss": 0.4323, "step": 7015 }, { "epoch": 1.795904, "grad_norm": 1.84375, "learning_rate": 2.0075078918181042e-05, "loss": 0.4572, "step": 7016 }, { "epoch": 1.79616, "grad_norm": 1.9921875, "learning_rate": 2.007081307055712e-05, "loss": 0.4156, "step": 7017 }, { "epoch": 1.796416, "grad_norm": 1.9921875, "learning_rate": 2.00665472229332e-05, "loss": 0.3914, "step": 7018 }, { "epoch": 1.796672, "grad_norm": 1.90625, "learning_rate": 2.0062281375309275e-05, "loss": 0.4045, "step": 7019 }, { "epoch": 1.7969279999999999, "grad_norm": 1.9296875, "learning_rate": 2.0058015527685352e-05, "loss": 0.395, "step": 7020 }, { "epoch": 1.7971840000000001, "grad_norm": 2.15625, "learning_rate": 2.005374968006143e-05, "loss": 0.4315, "step": 7021 }, { "epoch": 1.79744, "grad_norm": 1.9375, "learning_rate": 2.0049483832437508e-05, "loss": 0.4304, "step": 7022 }, { "epoch": 1.797696, "grad_norm": 1.765625, "learning_rate": 2.0045217984813582e-05, "loss": 0.3994, "step": 7023 }, { "epoch": 1.797952, "grad_norm": 1.953125, "learning_rate": 2.0040952137189663e-05, "loss": 0.4059, "step": 7024 }, { "epoch": 1.798208, "grad_norm": 1.921875, "learning_rate": 2.0036686289565737e-05, "loss": 0.4234, "step": 7025 }, { "epoch": 1.798464, "grad_norm": 1.9609375, "learning_rate": 2.0032420441941815e-05, "loss": 0.4382, "step": 7026 }, { "epoch": 1.7987199999999999, "grad_norm": 1.921875, "learning_rate": 2.0028154594317893e-05, "loss": 0.4615, "step": 7027 }, { "epoch": 1.7989760000000001, "grad_norm": 1.7890625, "learning_rate": 2.002388874669397e-05, "loss": 0.4254, "step": 7028 }, { "epoch": 1.799232, "grad_norm": 1.875, "learning_rate": 2.0019622899070044e-05, "loss": 0.4367, "step": 7029 }, { "epoch": 1.799488, "grad_norm": 2.015625, "learning_rate": 2.0015357051446122e-05, "loss": 0.4408, "step": 7030 }, { "epoch": 1.799744, "grad_norm": 2.15625, "learning_rate": 2.00110912038222e-05, "loss": 0.425, "step": 7031 }, { "epoch": 1.8, "grad_norm": 1.90625, "learning_rate": 2.0006825356198277e-05, "loss": 0.4547, "step": 7032 }, { "epoch": 1.800256, "grad_norm": 1.9609375, "learning_rate": 2.000255950857435e-05, "loss": 0.4306, "step": 7033 }, { "epoch": 1.800512, "grad_norm": 1.890625, "learning_rate": 1.9998293660950433e-05, "loss": 0.4363, "step": 7034 }, { "epoch": 1.8007680000000001, "grad_norm": 1.703125, "learning_rate": 1.999402781332651e-05, "loss": 0.4387, "step": 7035 }, { "epoch": 1.801024, "grad_norm": 1.984375, "learning_rate": 1.9989761965702585e-05, "loss": 0.4174, "step": 7036 }, { "epoch": 1.80128, "grad_norm": 1.9375, "learning_rate": 1.9985496118078666e-05, "loss": 0.4391, "step": 7037 }, { "epoch": 1.801536, "grad_norm": 1.8671875, "learning_rate": 1.998123027045474e-05, "loss": 0.3965, "step": 7038 }, { "epoch": 1.8017919999999998, "grad_norm": 1.890625, "learning_rate": 1.9976964422830818e-05, "loss": 0.4311, "step": 7039 }, { "epoch": 1.802048, "grad_norm": 1.84375, "learning_rate": 1.9972698575206895e-05, "loss": 0.4431, "step": 7040 }, { "epoch": 1.802304, "grad_norm": 2.15625, "learning_rate": 1.9968432727582973e-05, "loss": 0.4295, "step": 7041 }, { "epoch": 1.8025600000000002, "grad_norm": 1.8515625, "learning_rate": 1.9964166879959047e-05, "loss": 0.4314, "step": 7042 }, { "epoch": 1.802816, "grad_norm": 2.09375, "learning_rate": 1.9959901032335128e-05, "loss": 0.4292, "step": 7043 }, { "epoch": 1.803072, "grad_norm": 1.9375, "learning_rate": 1.9955635184711202e-05, "loss": 0.3977, "step": 7044 }, { "epoch": 1.803328, "grad_norm": 2.046875, "learning_rate": 1.995136933708728e-05, "loss": 0.4192, "step": 7045 }, { "epoch": 1.8035839999999999, "grad_norm": 1.8984375, "learning_rate": 1.9947103489463358e-05, "loss": 0.4428, "step": 7046 }, { "epoch": 1.80384, "grad_norm": 1.9296875, "learning_rate": 1.9942837641839435e-05, "loss": 0.4278, "step": 7047 }, { "epoch": 1.804096, "grad_norm": 1.8671875, "learning_rate": 1.993857179421551e-05, "loss": 0.3972, "step": 7048 }, { "epoch": 1.804352, "grad_norm": 2.03125, "learning_rate": 1.9934305946591587e-05, "loss": 0.4511, "step": 7049 }, { "epoch": 1.804608, "grad_norm": 2.09375, "learning_rate": 1.993004009896767e-05, "loss": 0.4006, "step": 7050 }, { "epoch": 1.804864, "grad_norm": 2.125, "learning_rate": 1.9925774251343743e-05, "loss": 0.4047, "step": 7051 }, { "epoch": 1.80512, "grad_norm": 1.9140625, "learning_rate": 1.992150840371982e-05, "loss": 0.4049, "step": 7052 }, { "epoch": 1.8053759999999999, "grad_norm": 1.96875, "learning_rate": 1.9917242556095898e-05, "loss": 0.4381, "step": 7053 }, { "epoch": 1.8056320000000001, "grad_norm": 2.0625, "learning_rate": 1.9912976708471976e-05, "loss": 0.4163, "step": 7054 }, { "epoch": 1.805888, "grad_norm": 1.9765625, "learning_rate": 1.990871086084805e-05, "loss": 0.4463, "step": 7055 }, { "epoch": 1.806144, "grad_norm": 2.078125, "learning_rate": 1.990444501322413e-05, "loss": 0.4566, "step": 7056 }, { "epoch": 1.8064, "grad_norm": 2.0, "learning_rate": 1.9900179165600205e-05, "loss": 0.4339, "step": 7057 }, { "epoch": 1.806656, "grad_norm": 1.859375, "learning_rate": 1.9895913317976283e-05, "loss": 0.4104, "step": 7058 }, { "epoch": 1.806912, "grad_norm": 2.046875, "learning_rate": 1.989164747035236e-05, "loss": 0.4819, "step": 7059 }, { "epoch": 1.8071679999999999, "grad_norm": 2.0, "learning_rate": 1.9887381622728438e-05, "loss": 0.4108, "step": 7060 }, { "epoch": 1.8074240000000001, "grad_norm": 1.90625, "learning_rate": 1.9883115775104512e-05, "loss": 0.4571, "step": 7061 }, { "epoch": 1.80768, "grad_norm": 1.859375, "learning_rate": 1.987884992748059e-05, "loss": 0.4364, "step": 7062 }, { "epoch": 1.807936, "grad_norm": 1.90625, "learning_rate": 1.9874584079856668e-05, "loss": 0.4401, "step": 7063 }, { "epoch": 1.808192, "grad_norm": 1.921875, "learning_rate": 1.9870318232232745e-05, "loss": 0.4358, "step": 7064 }, { "epoch": 1.808448, "grad_norm": 1.8671875, "learning_rate": 1.9866052384608823e-05, "loss": 0.3979, "step": 7065 }, { "epoch": 1.808704, "grad_norm": 1.875, "learning_rate": 1.98617865369849e-05, "loss": 0.4265, "step": 7066 }, { "epoch": 1.80896, "grad_norm": 1.984375, "learning_rate": 1.985752068936098e-05, "loss": 0.4593, "step": 7067 }, { "epoch": 1.8092160000000002, "grad_norm": 1.90625, "learning_rate": 1.9853254841737053e-05, "loss": 0.4403, "step": 7068 }, { "epoch": 1.809472, "grad_norm": 2.078125, "learning_rate": 1.9848988994113134e-05, "loss": 0.4282, "step": 7069 }, { "epoch": 1.809728, "grad_norm": 1.8984375, "learning_rate": 1.9844723146489208e-05, "loss": 0.4348, "step": 7070 }, { "epoch": 1.809984, "grad_norm": 1.921875, "learning_rate": 1.9840457298865286e-05, "loss": 0.445, "step": 7071 }, { "epoch": 1.8102399999999998, "grad_norm": 2.140625, "learning_rate": 1.9836191451241363e-05, "loss": 0.4504, "step": 7072 }, { "epoch": 1.810496, "grad_norm": 1.9609375, "learning_rate": 1.983192560361744e-05, "loss": 0.4356, "step": 7073 }, { "epoch": 1.810752, "grad_norm": 1.8359375, "learning_rate": 1.9827659755993515e-05, "loss": 0.4234, "step": 7074 }, { "epoch": 1.811008, "grad_norm": 1.8359375, "learning_rate": 1.9823393908369596e-05, "loss": 0.4257, "step": 7075 }, { "epoch": 1.811264, "grad_norm": 1.7734375, "learning_rate": 1.981912806074567e-05, "loss": 0.4638, "step": 7076 }, { "epoch": 1.81152, "grad_norm": 2.0, "learning_rate": 1.9814862213121748e-05, "loss": 0.4266, "step": 7077 }, { "epoch": 1.811776, "grad_norm": 1.9453125, "learning_rate": 1.9810596365497826e-05, "loss": 0.4483, "step": 7078 }, { "epoch": 1.8120319999999999, "grad_norm": 1.8125, "learning_rate": 1.9806330517873903e-05, "loss": 0.4367, "step": 7079 }, { "epoch": 1.8122880000000001, "grad_norm": 1.921875, "learning_rate": 1.9802064670249978e-05, "loss": 0.4456, "step": 7080 }, { "epoch": 1.812544, "grad_norm": 1.90625, "learning_rate": 1.9797798822626055e-05, "loss": 0.4274, "step": 7081 }, { "epoch": 1.8128, "grad_norm": 1.953125, "learning_rate": 1.9793532975002133e-05, "loss": 0.4426, "step": 7082 }, { "epoch": 1.813056, "grad_norm": 1.90625, "learning_rate": 1.978926712737821e-05, "loss": 0.4346, "step": 7083 }, { "epoch": 1.813312, "grad_norm": 1.9140625, "learning_rate": 1.978500127975429e-05, "loss": 0.4216, "step": 7084 }, { "epoch": 1.813568, "grad_norm": 2.0, "learning_rate": 1.9780735432130366e-05, "loss": 0.4174, "step": 7085 }, { "epoch": 1.8138239999999999, "grad_norm": 1.921875, "learning_rate": 1.9776469584506444e-05, "loss": 0.4263, "step": 7086 }, { "epoch": 1.8140800000000001, "grad_norm": 1.8359375, "learning_rate": 1.9772203736882518e-05, "loss": 0.4236, "step": 7087 }, { "epoch": 1.814336, "grad_norm": 1.953125, "learning_rate": 1.97679378892586e-05, "loss": 0.4288, "step": 7088 }, { "epoch": 1.814592, "grad_norm": 2.078125, "learning_rate": 1.9763672041634673e-05, "loss": 0.3975, "step": 7089 }, { "epoch": 1.814848, "grad_norm": 2.234375, "learning_rate": 1.975940619401075e-05, "loss": 0.4029, "step": 7090 }, { "epoch": 1.815104, "grad_norm": 1.8828125, "learning_rate": 1.975514034638683e-05, "loss": 0.432, "step": 7091 }, { "epoch": 1.81536, "grad_norm": 1.8515625, "learning_rate": 1.9750874498762906e-05, "loss": 0.4261, "step": 7092 }, { "epoch": 1.815616, "grad_norm": 1.921875, "learning_rate": 1.974660865113898e-05, "loss": 0.4274, "step": 7093 }, { "epoch": 1.8158720000000002, "grad_norm": 2.03125, "learning_rate": 1.974234280351506e-05, "loss": 0.4379, "step": 7094 }, { "epoch": 1.816128, "grad_norm": 1.890625, "learning_rate": 1.9738076955891136e-05, "loss": 0.4477, "step": 7095 }, { "epoch": 1.816384, "grad_norm": 1.90625, "learning_rate": 1.9733811108267213e-05, "loss": 0.4478, "step": 7096 }, { "epoch": 1.81664, "grad_norm": 1.9765625, "learning_rate": 1.972954526064329e-05, "loss": 0.3909, "step": 7097 }, { "epoch": 1.8168959999999998, "grad_norm": 1.9375, "learning_rate": 1.972527941301937e-05, "loss": 0.4308, "step": 7098 }, { "epoch": 1.817152, "grad_norm": 1.953125, "learning_rate": 1.9721013565395443e-05, "loss": 0.4448, "step": 7099 }, { "epoch": 1.817408, "grad_norm": 1.953125, "learning_rate": 1.971674771777152e-05, "loss": 0.4461, "step": 7100 }, { "epoch": 1.817664, "grad_norm": 1.953125, "learning_rate": 1.97124818701476e-05, "loss": 0.4453, "step": 7101 }, { "epoch": 1.81792, "grad_norm": 2.15625, "learning_rate": 1.9708216022523676e-05, "loss": 0.4258, "step": 7102 }, { "epoch": 1.818176, "grad_norm": 1.796875, "learning_rate": 1.9703950174899754e-05, "loss": 0.423, "step": 7103 }, { "epoch": 1.818432, "grad_norm": 2.0625, "learning_rate": 1.969968432727583e-05, "loss": 0.4471, "step": 7104 }, { "epoch": 1.8186879999999999, "grad_norm": 1.6640625, "learning_rate": 1.969541847965191e-05, "loss": 0.4332, "step": 7105 }, { "epoch": 1.8189440000000001, "grad_norm": 1.8984375, "learning_rate": 1.9691152632027983e-05, "loss": 0.4362, "step": 7106 }, { "epoch": 1.8192, "grad_norm": 1.9140625, "learning_rate": 1.9686886784404064e-05, "loss": 0.4257, "step": 7107 }, { "epoch": 1.819456, "grad_norm": 1.890625, "learning_rate": 1.968262093678014e-05, "loss": 0.3873, "step": 7108 }, { "epoch": 1.819712, "grad_norm": 1.859375, "learning_rate": 1.9678355089156216e-05, "loss": 0.4363, "step": 7109 }, { "epoch": 1.819968, "grad_norm": 2.0625, "learning_rate": 1.9674089241532294e-05, "loss": 0.4215, "step": 7110 }, { "epoch": 1.820224, "grad_norm": 2.03125, "learning_rate": 1.966982339390837e-05, "loss": 0.4147, "step": 7111 }, { "epoch": 1.8204799999999999, "grad_norm": 2.046875, "learning_rate": 1.9665557546284446e-05, "loss": 0.4363, "step": 7112 }, { "epoch": 1.8207360000000001, "grad_norm": 1.8515625, "learning_rate": 1.9661291698660523e-05, "loss": 0.4015, "step": 7113 }, { "epoch": 1.820992, "grad_norm": 1.9140625, "learning_rate": 1.96570258510366e-05, "loss": 0.4393, "step": 7114 }, { "epoch": 1.821248, "grad_norm": 1.90625, "learning_rate": 1.965276000341268e-05, "loss": 0.3901, "step": 7115 }, { "epoch": 1.821504, "grad_norm": 1.8828125, "learning_rate": 1.9648494155788756e-05, "loss": 0.4419, "step": 7116 }, { "epoch": 1.82176, "grad_norm": 1.859375, "learning_rate": 1.9644228308164834e-05, "loss": 0.4344, "step": 7117 }, { "epoch": 1.822016, "grad_norm": 2.0, "learning_rate": 1.963996246054091e-05, "loss": 0.4444, "step": 7118 }, { "epoch": 1.822272, "grad_norm": 1.828125, "learning_rate": 1.9635696612916986e-05, "loss": 0.4513, "step": 7119 }, { "epoch": 1.8225280000000001, "grad_norm": 2.015625, "learning_rate": 1.9631430765293067e-05, "loss": 0.4427, "step": 7120 }, { "epoch": 1.822784, "grad_norm": 1.8359375, "learning_rate": 1.962716491766914e-05, "loss": 0.4122, "step": 7121 }, { "epoch": 1.82304, "grad_norm": 2.015625, "learning_rate": 1.962289907004522e-05, "loss": 0.4411, "step": 7122 }, { "epoch": 1.823296, "grad_norm": 1.921875, "learning_rate": 1.9618633222421297e-05, "loss": 0.4051, "step": 7123 }, { "epoch": 1.8235519999999998, "grad_norm": 1.8984375, "learning_rate": 1.9614367374797374e-05, "loss": 0.4643, "step": 7124 }, { "epoch": 1.823808, "grad_norm": 1.84375, "learning_rate": 1.961010152717345e-05, "loss": 0.4556, "step": 7125 }, { "epoch": 1.824064, "grad_norm": 1.9765625, "learning_rate": 1.960583567954953e-05, "loss": 0.4002, "step": 7126 }, { "epoch": 1.8243200000000002, "grad_norm": 1.890625, "learning_rate": 1.9601569831925604e-05, "loss": 0.4056, "step": 7127 }, { "epoch": 1.824576, "grad_norm": 1.7421875, "learning_rate": 1.959730398430168e-05, "loss": 0.4487, "step": 7128 }, { "epoch": 1.824832, "grad_norm": 1.953125, "learning_rate": 1.959303813667776e-05, "loss": 0.4127, "step": 7129 }, { "epoch": 1.825088, "grad_norm": 1.8125, "learning_rate": 1.9588772289053837e-05, "loss": 0.4392, "step": 7130 }, { "epoch": 1.8253439999999999, "grad_norm": 1.875, "learning_rate": 1.958450644142991e-05, "loss": 0.4319, "step": 7131 }, { "epoch": 1.8256000000000001, "grad_norm": 2.0, "learning_rate": 1.958024059380599e-05, "loss": 0.432, "step": 7132 }, { "epoch": 1.825856, "grad_norm": 2.015625, "learning_rate": 1.957597474618207e-05, "loss": 0.5023, "step": 7133 }, { "epoch": 1.826112, "grad_norm": 1.8984375, "learning_rate": 1.9571708898558144e-05, "loss": 0.4225, "step": 7134 }, { "epoch": 1.826368, "grad_norm": 1.875, "learning_rate": 1.956744305093422e-05, "loss": 0.4357, "step": 7135 }, { "epoch": 1.826624, "grad_norm": 2.078125, "learning_rate": 1.95631772033103e-05, "loss": 0.4488, "step": 7136 }, { "epoch": 1.82688, "grad_norm": 1.9921875, "learning_rate": 1.9558911355686377e-05, "loss": 0.4168, "step": 7137 }, { "epoch": 1.8271359999999999, "grad_norm": 1.875, "learning_rate": 1.955464550806245e-05, "loss": 0.4002, "step": 7138 }, { "epoch": 1.8273920000000001, "grad_norm": 1.9375, "learning_rate": 1.9550379660438532e-05, "loss": 0.4064, "step": 7139 }, { "epoch": 1.827648, "grad_norm": 1.6796875, "learning_rate": 1.9546113812814606e-05, "loss": 0.4929, "step": 7140 }, { "epoch": 1.827904, "grad_norm": 1.9375, "learning_rate": 1.9541847965190684e-05, "loss": 0.4306, "step": 7141 }, { "epoch": 1.82816, "grad_norm": 1.859375, "learning_rate": 1.9537582117566762e-05, "loss": 0.419, "step": 7142 }, { "epoch": 1.828416, "grad_norm": 1.984375, "learning_rate": 1.953331626994284e-05, "loss": 0.4104, "step": 7143 }, { "epoch": 1.828672, "grad_norm": 2.0625, "learning_rate": 1.9529050422318914e-05, "loss": 0.4361, "step": 7144 }, { "epoch": 1.8289279999999999, "grad_norm": 2.03125, "learning_rate": 1.9524784574694995e-05, "loss": 0.434, "step": 7145 }, { "epoch": 1.8291840000000001, "grad_norm": 2.078125, "learning_rate": 1.952051872707107e-05, "loss": 0.4546, "step": 7146 }, { "epoch": 1.82944, "grad_norm": 1.8828125, "learning_rate": 1.9516252879447147e-05, "loss": 0.4537, "step": 7147 }, { "epoch": 1.829696, "grad_norm": 1.84375, "learning_rate": 1.9511987031823224e-05, "loss": 0.4165, "step": 7148 }, { "epoch": 1.829952, "grad_norm": 1.890625, "learning_rate": 1.9507721184199302e-05, "loss": 0.4026, "step": 7149 }, { "epoch": 1.8302079999999998, "grad_norm": 1.84375, "learning_rate": 1.950345533657538e-05, "loss": 0.426, "step": 7150 }, { "epoch": 1.830464, "grad_norm": 2.078125, "learning_rate": 1.9499189488951454e-05, "loss": 0.4267, "step": 7151 }, { "epoch": 1.83072, "grad_norm": 2.015625, "learning_rate": 1.9494923641327535e-05, "loss": 0.4417, "step": 7152 }, { "epoch": 1.8309760000000002, "grad_norm": 1.953125, "learning_rate": 1.949065779370361e-05, "loss": 0.4295, "step": 7153 }, { "epoch": 1.831232, "grad_norm": 1.890625, "learning_rate": 1.9486391946079687e-05, "loss": 0.4458, "step": 7154 }, { "epoch": 1.831488, "grad_norm": 1.984375, "learning_rate": 1.9482126098455765e-05, "loss": 0.4685, "step": 7155 }, { "epoch": 1.831744, "grad_norm": 1.921875, "learning_rate": 1.9477860250831842e-05, "loss": 0.4319, "step": 7156 }, { "epoch": 1.8319999999999999, "grad_norm": 2.015625, "learning_rate": 1.9473594403207916e-05, "loss": 0.4108, "step": 7157 }, { "epoch": 1.832256, "grad_norm": 1.9375, "learning_rate": 1.9469328555583997e-05, "loss": 0.4111, "step": 7158 }, { "epoch": 1.832512, "grad_norm": 1.953125, "learning_rate": 1.9465062707960072e-05, "loss": 0.4372, "step": 7159 }, { "epoch": 1.832768, "grad_norm": 1.859375, "learning_rate": 1.946079686033615e-05, "loss": 0.484, "step": 7160 }, { "epoch": 1.833024, "grad_norm": 1.8671875, "learning_rate": 1.9456531012712227e-05, "loss": 0.4313, "step": 7161 }, { "epoch": 1.83328, "grad_norm": 1.90625, "learning_rate": 1.9452265165088305e-05, "loss": 0.4359, "step": 7162 }, { "epoch": 1.833536, "grad_norm": 1.921875, "learning_rate": 1.944799931746438e-05, "loss": 0.4726, "step": 7163 }, { "epoch": 1.8337919999999999, "grad_norm": 2.171875, "learning_rate": 1.9443733469840457e-05, "loss": 0.4234, "step": 7164 }, { "epoch": 1.8340480000000001, "grad_norm": 1.96875, "learning_rate": 1.9439467622216538e-05, "loss": 0.4197, "step": 7165 }, { "epoch": 1.834304, "grad_norm": 2.0, "learning_rate": 1.9435201774592612e-05, "loss": 0.4335, "step": 7166 }, { "epoch": 1.83456, "grad_norm": 1.734375, "learning_rate": 1.943093592696869e-05, "loss": 0.4196, "step": 7167 }, { "epoch": 1.834816, "grad_norm": 2.03125, "learning_rate": 1.9426670079344767e-05, "loss": 0.456, "step": 7168 }, { "epoch": 1.835072, "grad_norm": 1.9921875, "learning_rate": 1.9422404231720845e-05, "loss": 0.4251, "step": 7169 }, { "epoch": 1.835328, "grad_norm": 1.859375, "learning_rate": 1.941813838409692e-05, "loss": 0.4191, "step": 7170 }, { "epoch": 1.8355839999999999, "grad_norm": 1.96875, "learning_rate": 1.9413872536473e-05, "loss": 0.4704, "step": 7171 }, { "epoch": 1.8358400000000001, "grad_norm": 1.921875, "learning_rate": 1.9409606688849074e-05, "loss": 0.3903, "step": 7172 }, { "epoch": 1.836096, "grad_norm": 2.015625, "learning_rate": 1.9405340841225152e-05, "loss": 0.4462, "step": 7173 }, { "epoch": 1.836352, "grad_norm": 1.9140625, "learning_rate": 1.940107499360123e-05, "loss": 0.3943, "step": 7174 }, { "epoch": 1.836608, "grad_norm": 1.796875, "learning_rate": 1.9396809145977307e-05, "loss": 0.4236, "step": 7175 }, { "epoch": 1.836864, "grad_norm": 1.9609375, "learning_rate": 1.9392543298353382e-05, "loss": 0.4011, "step": 7176 }, { "epoch": 1.83712, "grad_norm": 1.9453125, "learning_rate": 1.9388277450729463e-05, "loss": 0.4001, "step": 7177 }, { "epoch": 1.837376, "grad_norm": 1.8515625, "learning_rate": 1.9384011603105537e-05, "loss": 0.4434, "step": 7178 }, { "epoch": 1.8376320000000002, "grad_norm": 1.890625, "learning_rate": 1.9379745755481615e-05, "loss": 0.4746, "step": 7179 }, { "epoch": 1.837888, "grad_norm": 2.03125, "learning_rate": 1.9375479907857692e-05, "loss": 0.4472, "step": 7180 }, { "epoch": 1.838144, "grad_norm": 2.03125, "learning_rate": 1.937121406023377e-05, "loss": 0.4749, "step": 7181 }, { "epoch": 1.8384, "grad_norm": 1.9921875, "learning_rate": 1.9366948212609848e-05, "loss": 0.441, "step": 7182 }, { "epoch": 1.8386559999999998, "grad_norm": 1.8828125, "learning_rate": 1.9362682364985922e-05, "loss": 0.4187, "step": 7183 }, { "epoch": 1.838912, "grad_norm": 2.046875, "learning_rate": 1.9358416517362003e-05, "loss": 0.4224, "step": 7184 }, { "epoch": 1.839168, "grad_norm": 2.0, "learning_rate": 1.9354150669738077e-05, "loss": 0.4178, "step": 7185 }, { "epoch": 1.839424, "grad_norm": 2.0, "learning_rate": 1.9349884822114155e-05, "loss": 0.4511, "step": 7186 }, { "epoch": 1.83968, "grad_norm": 2.125, "learning_rate": 1.9345618974490233e-05, "loss": 0.4345, "step": 7187 }, { "epoch": 1.839936, "grad_norm": 1.8671875, "learning_rate": 1.934135312686631e-05, "loss": 0.407, "step": 7188 }, { "epoch": 1.840192, "grad_norm": 1.9453125, "learning_rate": 1.9337087279242384e-05, "loss": 0.449, "step": 7189 }, { "epoch": 1.8404479999999999, "grad_norm": 1.9609375, "learning_rate": 1.9332821431618465e-05, "loss": 0.4126, "step": 7190 }, { "epoch": 1.8407040000000001, "grad_norm": 1.7890625, "learning_rate": 1.932855558399454e-05, "loss": 0.4583, "step": 7191 }, { "epoch": 1.84096, "grad_norm": 1.890625, "learning_rate": 1.9324289736370617e-05, "loss": 0.4681, "step": 7192 }, { "epoch": 1.841216, "grad_norm": 1.9453125, "learning_rate": 1.9320023888746695e-05, "loss": 0.4333, "step": 7193 }, { "epoch": 1.841472, "grad_norm": 1.8671875, "learning_rate": 1.9315758041122773e-05, "loss": 0.4499, "step": 7194 }, { "epoch": 1.841728, "grad_norm": 1.953125, "learning_rate": 1.9311492193498847e-05, "loss": 0.4323, "step": 7195 }, { "epoch": 1.841984, "grad_norm": 1.953125, "learning_rate": 1.9307226345874928e-05, "loss": 0.4149, "step": 7196 }, { "epoch": 1.8422399999999999, "grad_norm": 1.8828125, "learning_rate": 1.9302960498251002e-05, "loss": 0.4369, "step": 7197 }, { "epoch": 1.8424960000000001, "grad_norm": 2.03125, "learning_rate": 1.929869465062708e-05, "loss": 0.441, "step": 7198 }, { "epoch": 1.842752, "grad_norm": 1.890625, "learning_rate": 1.9294428803003158e-05, "loss": 0.4258, "step": 7199 }, { "epoch": 1.843008, "grad_norm": 2.140625, "learning_rate": 1.9290162955379235e-05, "loss": 0.4417, "step": 7200 }, { "epoch": 1.843264, "grad_norm": 2.0625, "learning_rate": 1.9285897107755313e-05, "loss": 0.4242, "step": 7201 }, { "epoch": 1.84352, "grad_norm": 1.8671875, "learning_rate": 1.9281631260131387e-05, "loss": 0.392, "step": 7202 }, { "epoch": 1.843776, "grad_norm": 2.03125, "learning_rate": 1.9277365412507468e-05, "loss": 0.4481, "step": 7203 }, { "epoch": 1.844032, "grad_norm": 2.0, "learning_rate": 1.9273099564883542e-05, "loss": 0.4644, "step": 7204 }, { "epoch": 1.8442880000000001, "grad_norm": 1.9765625, "learning_rate": 1.926883371725962e-05, "loss": 0.4532, "step": 7205 }, { "epoch": 1.844544, "grad_norm": 1.9296875, "learning_rate": 1.9264567869635698e-05, "loss": 0.4402, "step": 7206 }, { "epoch": 1.8448, "grad_norm": 1.8359375, "learning_rate": 1.9260302022011775e-05, "loss": 0.4321, "step": 7207 }, { "epoch": 1.845056, "grad_norm": 1.9453125, "learning_rate": 1.925603617438785e-05, "loss": 0.3996, "step": 7208 }, { "epoch": 1.8453119999999998, "grad_norm": 1.71875, "learning_rate": 1.925177032676393e-05, "loss": 0.4282, "step": 7209 }, { "epoch": 1.845568, "grad_norm": 1.9765625, "learning_rate": 1.9247504479140005e-05, "loss": 0.4271, "step": 7210 }, { "epoch": 1.845824, "grad_norm": 2.046875, "learning_rate": 1.9243238631516083e-05, "loss": 0.4133, "step": 7211 }, { "epoch": 1.8460800000000002, "grad_norm": 2.171875, "learning_rate": 1.923897278389216e-05, "loss": 0.437, "step": 7212 }, { "epoch": 1.846336, "grad_norm": 2.109375, "learning_rate": 1.9234706936268238e-05, "loss": 0.4324, "step": 7213 }, { "epoch": 1.846592, "grad_norm": 1.828125, "learning_rate": 1.9230441088644316e-05, "loss": 0.4105, "step": 7214 }, { "epoch": 1.846848, "grad_norm": 1.90625, "learning_rate": 1.922617524102039e-05, "loss": 0.4439, "step": 7215 }, { "epoch": 1.8471039999999999, "grad_norm": 1.8359375, "learning_rate": 1.922190939339647e-05, "loss": 0.4369, "step": 7216 }, { "epoch": 1.8473600000000001, "grad_norm": 1.8125, "learning_rate": 1.9217643545772545e-05, "loss": 0.4086, "step": 7217 }, { "epoch": 1.847616, "grad_norm": 1.96875, "learning_rate": 1.9213377698148623e-05, "loss": 0.4287, "step": 7218 }, { "epoch": 1.847872, "grad_norm": 2.109375, "learning_rate": 1.92091118505247e-05, "loss": 0.4198, "step": 7219 }, { "epoch": 1.848128, "grad_norm": 2.046875, "learning_rate": 1.9204846002900778e-05, "loss": 0.4419, "step": 7220 }, { "epoch": 1.848384, "grad_norm": 1.859375, "learning_rate": 1.9200580155276852e-05, "loss": 0.4382, "step": 7221 }, { "epoch": 1.84864, "grad_norm": 2.03125, "learning_rate": 1.9196314307652933e-05, "loss": 0.4411, "step": 7222 }, { "epoch": 1.8488959999999999, "grad_norm": 2.109375, "learning_rate": 1.9192048460029008e-05, "loss": 0.424, "step": 7223 }, { "epoch": 1.8491520000000001, "grad_norm": 1.9921875, "learning_rate": 1.9187782612405085e-05, "loss": 0.4772, "step": 7224 }, { "epoch": 1.849408, "grad_norm": 1.8828125, "learning_rate": 1.9183516764781163e-05, "loss": 0.4663, "step": 7225 }, { "epoch": 1.849664, "grad_norm": 1.9375, "learning_rate": 1.917925091715724e-05, "loss": 0.4425, "step": 7226 }, { "epoch": 1.84992, "grad_norm": 1.9453125, "learning_rate": 1.9174985069533315e-05, "loss": 0.4041, "step": 7227 }, { "epoch": 1.850176, "grad_norm": 1.90625, "learning_rate": 1.9170719221909396e-05, "loss": 0.4281, "step": 7228 }, { "epoch": 1.850432, "grad_norm": 1.8359375, "learning_rate": 1.916645337428547e-05, "loss": 0.4534, "step": 7229 }, { "epoch": 1.8506879999999999, "grad_norm": 1.9296875, "learning_rate": 1.9162187526661548e-05, "loss": 0.46, "step": 7230 }, { "epoch": 1.8509440000000001, "grad_norm": 1.9453125, "learning_rate": 1.9157921679037626e-05, "loss": 0.4207, "step": 7231 }, { "epoch": 1.8512, "grad_norm": 2.109375, "learning_rate": 1.9153655831413703e-05, "loss": 0.4276, "step": 7232 }, { "epoch": 1.851456, "grad_norm": 1.953125, "learning_rate": 1.914938998378978e-05, "loss": 0.4019, "step": 7233 }, { "epoch": 1.851712, "grad_norm": 1.8984375, "learning_rate": 1.9145124136165855e-05, "loss": 0.4219, "step": 7234 }, { "epoch": 1.8519679999999998, "grad_norm": 2.125, "learning_rate": 1.9140858288541936e-05, "loss": 0.4492, "step": 7235 }, { "epoch": 1.852224, "grad_norm": 2.078125, "learning_rate": 1.913659244091801e-05, "loss": 0.4463, "step": 7236 }, { "epoch": 1.85248, "grad_norm": 1.7578125, "learning_rate": 1.9132326593294088e-05, "loss": 0.3862, "step": 7237 }, { "epoch": 1.8527360000000002, "grad_norm": 1.96875, "learning_rate": 1.9128060745670166e-05, "loss": 0.4579, "step": 7238 }, { "epoch": 1.852992, "grad_norm": 1.8984375, "learning_rate": 1.9123794898046243e-05, "loss": 0.3934, "step": 7239 }, { "epoch": 1.853248, "grad_norm": 1.7578125, "learning_rate": 1.9119529050422318e-05, "loss": 0.4199, "step": 7240 }, { "epoch": 1.853504, "grad_norm": 1.8515625, "learning_rate": 1.91152632027984e-05, "loss": 0.4156, "step": 7241 }, { "epoch": 1.8537599999999999, "grad_norm": 2.0625, "learning_rate": 1.9110997355174473e-05, "loss": 0.4667, "step": 7242 }, { "epoch": 1.854016, "grad_norm": 2.046875, "learning_rate": 1.910673150755055e-05, "loss": 0.4795, "step": 7243 }, { "epoch": 1.854272, "grad_norm": 2.03125, "learning_rate": 1.910246565992663e-05, "loss": 0.4369, "step": 7244 }, { "epoch": 1.854528, "grad_norm": 1.9765625, "learning_rate": 1.9098199812302706e-05, "loss": 0.4535, "step": 7245 }, { "epoch": 1.854784, "grad_norm": 1.8515625, "learning_rate": 1.909393396467878e-05, "loss": 0.4476, "step": 7246 }, { "epoch": 1.85504, "grad_norm": 1.78125, "learning_rate": 1.908966811705486e-05, "loss": 0.4388, "step": 7247 }, { "epoch": 1.855296, "grad_norm": 1.96875, "learning_rate": 1.908540226943094e-05, "loss": 0.4651, "step": 7248 }, { "epoch": 1.8555519999999999, "grad_norm": 1.796875, "learning_rate": 1.9081136421807013e-05, "loss": 0.4389, "step": 7249 }, { "epoch": 1.8558080000000001, "grad_norm": 2.015625, "learning_rate": 1.907687057418309e-05, "loss": 0.4213, "step": 7250 }, { "epoch": 1.856064, "grad_norm": 1.796875, "learning_rate": 1.907260472655917e-05, "loss": 0.4217, "step": 7251 }, { "epoch": 1.85632, "grad_norm": 1.9140625, "learning_rate": 1.9068338878935246e-05, "loss": 0.4497, "step": 7252 }, { "epoch": 1.856576, "grad_norm": 1.8828125, "learning_rate": 1.906407303131132e-05, "loss": 0.4502, "step": 7253 }, { "epoch": 1.856832, "grad_norm": 1.8125, "learning_rate": 1.90598071836874e-05, "loss": 0.4015, "step": 7254 }, { "epoch": 1.857088, "grad_norm": 1.78125, "learning_rate": 1.9055541336063476e-05, "loss": 0.439, "step": 7255 }, { "epoch": 1.8573439999999999, "grad_norm": 1.9921875, "learning_rate": 1.9051275488439553e-05, "loss": 0.4173, "step": 7256 }, { "epoch": 1.8576000000000001, "grad_norm": 1.90625, "learning_rate": 1.904700964081563e-05, "loss": 0.456, "step": 7257 }, { "epoch": 1.857856, "grad_norm": 1.7734375, "learning_rate": 1.904274379319171e-05, "loss": 0.4456, "step": 7258 }, { "epoch": 1.858112, "grad_norm": 1.96875, "learning_rate": 1.9038477945567783e-05, "loss": 0.4818, "step": 7259 }, { "epoch": 1.858368, "grad_norm": 1.8671875, "learning_rate": 1.9034212097943864e-05, "loss": 0.4302, "step": 7260 }, { "epoch": 1.858624, "grad_norm": 2.046875, "learning_rate": 1.9029946250319938e-05, "loss": 0.424, "step": 7261 }, { "epoch": 1.85888, "grad_norm": 1.84375, "learning_rate": 1.9025680402696016e-05, "loss": 0.4554, "step": 7262 }, { "epoch": 1.859136, "grad_norm": 1.953125, "learning_rate": 1.9021414555072094e-05, "loss": 0.3935, "step": 7263 }, { "epoch": 1.8593920000000002, "grad_norm": 1.9609375, "learning_rate": 1.901714870744817e-05, "loss": 0.4671, "step": 7264 }, { "epoch": 1.859648, "grad_norm": 2.046875, "learning_rate": 1.901288285982425e-05, "loss": 0.4261, "step": 7265 }, { "epoch": 1.859904, "grad_norm": 1.90625, "learning_rate": 1.9008617012200327e-05, "loss": 0.451, "step": 7266 }, { "epoch": 1.86016, "grad_norm": 1.8828125, "learning_rate": 1.9004351164576404e-05, "loss": 0.4566, "step": 7267 }, { "epoch": 1.8604159999999998, "grad_norm": 1.984375, "learning_rate": 1.900008531695248e-05, "loss": 0.395, "step": 7268 }, { "epoch": 1.860672, "grad_norm": 1.9140625, "learning_rate": 1.8995819469328556e-05, "loss": 0.4451, "step": 7269 }, { "epoch": 1.860928, "grad_norm": 2.078125, "learning_rate": 1.8991553621704634e-05, "loss": 0.4369, "step": 7270 }, { "epoch": 1.861184, "grad_norm": 2.078125, "learning_rate": 1.898728777408071e-05, "loss": 0.4472, "step": 7271 }, { "epoch": 1.86144, "grad_norm": 1.953125, "learning_rate": 1.8983021926456786e-05, "loss": 0.4293, "step": 7272 }, { "epoch": 1.861696, "grad_norm": 1.890625, "learning_rate": 1.8978756078832867e-05, "loss": 0.4248, "step": 7273 }, { "epoch": 1.861952, "grad_norm": 1.96875, "learning_rate": 1.897449023120894e-05, "loss": 0.4002, "step": 7274 }, { "epoch": 1.8622079999999999, "grad_norm": 1.7890625, "learning_rate": 1.897022438358502e-05, "loss": 0.4079, "step": 7275 }, { "epoch": 1.8624640000000001, "grad_norm": 2.0625, "learning_rate": 1.8965958535961096e-05, "loss": 0.4508, "step": 7276 }, { "epoch": 1.86272, "grad_norm": 1.9765625, "learning_rate": 1.8961692688337174e-05, "loss": 0.4274, "step": 7277 }, { "epoch": 1.862976, "grad_norm": 1.8359375, "learning_rate": 1.8957426840713248e-05, "loss": 0.4348, "step": 7278 }, { "epoch": 1.863232, "grad_norm": 1.9296875, "learning_rate": 1.895316099308933e-05, "loss": 0.4254, "step": 7279 }, { "epoch": 1.863488, "grad_norm": 1.8828125, "learning_rate": 1.8948895145465407e-05, "loss": 0.4289, "step": 7280 }, { "epoch": 1.863744, "grad_norm": 1.90625, "learning_rate": 1.894462929784148e-05, "loss": 0.4276, "step": 7281 }, { "epoch": 1.8639999999999999, "grad_norm": 1.7890625, "learning_rate": 1.894036345021756e-05, "loss": 0.4624, "step": 7282 }, { "epoch": 1.8642560000000001, "grad_norm": 1.953125, "learning_rate": 1.8936097602593637e-05, "loss": 0.4241, "step": 7283 }, { "epoch": 1.864512, "grad_norm": 1.9296875, "learning_rate": 1.8931831754969714e-05, "loss": 0.4187, "step": 7284 }, { "epoch": 1.864768, "grad_norm": 2.046875, "learning_rate": 1.892756590734579e-05, "loss": 0.4373, "step": 7285 }, { "epoch": 1.865024, "grad_norm": 1.96875, "learning_rate": 1.892330005972187e-05, "loss": 0.3891, "step": 7286 }, { "epoch": 1.86528, "grad_norm": 1.9921875, "learning_rate": 1.8919034212097944e-05, "loss": 0.4164, "step": 7287 }, { "epoch": 1.865536, "grad_norm": 2.046875, "learning_rate": 1.891476836447402e-05, "loss": 0.4402, "step": 7288 }, { "epoch": 1.865792, "grad_norm": 1.8359375, "learning_rate": 1.89105025168501e-05, "loss": 0.427, "step": 7289 }, { "epoch": 1.8660480000000002, "grad_norm": 1.9296875, "learning_rate": 1.8906236669226177e-05, "loss": 0.4504, "step": 7290 }, { "epoch": 1.866304, "grad_norm": 1.84375, "learning_rate": 1.890197082160225e-05, "loss": 0.4281, "step": 7291 }, { "epoch": 1.86656, "grad_norm": 2.046875, "learning_rate": 1.8897704973978332e-05, "loss": 0.3999, "step": 7292 }, { "epoch": 1.866816, "grad_norm": 1.90625, "learning_rate": 1.8893439126354406e-05, "loss": 0.4378, "step": 7293 }, { "epoch": 1.8670719999999998, "grad_norm": 1.9375, "learning_rate": 1.8889173278730484e-05, "loss": 0.4175, "step": 7294 }, { "epoch": 1.867328, "grad_norm": 2.0, "learning_rate": 1.888490743110656e-05, "loss": 0.4651, "step": 7295 }, { "epoch": 1.867584, "grad_norm": 1.9375, "learning_rate": 1.888064158348264e-05, "loss": 0.4446, "step": 7296 }, { "epoch": 1.86784, "grad_norm": 1.953125, "learning_rate": 1.8876375735858717e-05, "loss": 0.4347, "step": 7297 }, { "epoch": 1.868096, "grad_norm": 1.9453125, "learning_rate": 1.8872109888234795e-05, "loss": 0.4407, "step": 7298 }, { "epoch": 1.868352, "grad_norm": 1.84375, "learning_rate": 1.8867844040610872e-05, "loss": 0.452, "step": 7299 }, { "epoch": 1.868608, "grad_norm": 1.90625, "learning_rate": 1.8863578192986946e-05, "loss": 0.4136, "step": 7300 }, { "epoch": 1.8688639999999999, "grad_norm": 2.09375, "learning_rate": 1.8859312345363024e-05, "loss": 0.4216, "step": 7301 }, { "epoch": 1.8691200000000001, "grad_norm": 2.0, "learning_rate": 1.8855046497739102e-05, "loss": 0.4098, "step": 7302 }, { "epoch": 1.869376, "grad_norm": 1.984375, "learning_rate": 1.885078065011518e-05, "loss": 0.4034, "step": 7303 }, { "epoch": 1.869632, "grad_norm": 1.78125, "learning_rate": 1.8846514802491254e-05, "loss": 0.4328, "step": 7304 }, { "epoch": 1.869888, "grad_norm": 1.8515625, "learning_rate": 1.8842248954867335e-05, "loss": 0.4856, "step": 7305 }, { "epoch": 1.870144, "grad_norm": 1.7109375, "learning_rate": 1.883798310724341e-05, "loss": 0.4648, "step": 7306 }, { "epoch": 1.8704, "grad_norm": 1.875, "learning_rate": 1.8833717259619487e-05, "loss": 0.4367, "step": 7307 }, { "epoch": 1.8706559999999999, "grad_norm": 1.9140625, "learning_rate": 1.8829451411995564e-05, "loss": 0.4305, "step": 7308 }, { "epoch": 1.8709120000000001, "grad_norm": 1.90625, "learning_rate": 1.8825185564371642e-05, "loss": 0.3975, "step": 7309 }, { "epoch": 1.871168, "grad_norm": 1.8828125, "learning_rate": 1.8820919716747716e-05, "loss": 0.4332, "step": 7310 }, { "epoch": 1.871424, "grad_norm": 1.9296875, "learning_rate": 1.8816653869123797e-05, "loss": 0.4026, "step": 7311 }, { "epoch": 1.87168, "grad_norm": 1.8984375, "learning_rate": 1.881238802149987e-05, "loss": 0.5059, "step": 7312 }, { "epoch": 1.871936, "grad_norm": 1.78125, "learning_rate": 1.880812217387595e-05, "loss": 0.4249, "step": 7313 }, { "epoch": 1.872192, "grad_norm": 1.765625, "learning_rate": 1.8803856326252027e-05, "loss": 0.4316, "step": 7314 }, { "epoch": 1.872448, "grad_norm": 1.8203125, "learning_rate": 1.8799590478628105e-05, "loss": 0.4399, "step": 7315 }, { "epoch": 1.8727040000000001, "grad_norm": 1.90625, "learning_rate": 1.8795324631004182e-05, "loss": 0.4359, "step": 7316 }, { "epoch": 1.87296, "grad_norm": 2.0625, "learning_rate": 1.879105878338026e-05, "loss": 0.4338, "step": 7317 }, { "epoch": 1.873216, "grad_norm": 1.90625, "learning_rate": 1.8786792935756337e-05, "loss": 0.4377, "step": 7318 }, { "epoch": 1.873472, "grad_norm": 2.078125, "learning_rate": 1.8782527088132412e-05, "loss": 0.417, "step": 7319 }, { "epoch": 1.8737279999999998, "grad_norm": 1.8359375, "learning_rate": 1.877826124050849e-05, "loss": 0.4626, "step": 7320 }, { "epoch": 1.873984, "grad_norm": 1.8515625, "learning_rate": 1.8773995392884567e-05, "loss": 0.4002, "step": 7321 }, { "epoch": 1.87424, "grad_norm": 1.8046875, "learning_rate": 1.8769729545260645e-05, "loss": 0.4486, "step": 7322 }, { "epoch": 1.8744960000000002, "grad_norm": 2.0, "learning_rate": 1.876546369763672e-05, "loss": 0.4516, "step": 7323 }, { "epoch": 1.874752, "grad_norm": 1.8359375, "learning_rate": 1.87611978500128e-05, "loss": 0.4622, "step": 7324 }, { "epoch": 1.875008, "grad_norm": 1.953125, "learning_rate": 1.8756932002388874e-05, "loss": 0.4355, "step": 7325 }, { "epoch": 1.875264, "grad_norm": 1.953125, "learning_rate": 1.8752666154764952e-05, "loss": 0.4326, "step": 7326 }, { "epoch": 1.8755199999999999, "grad_norm": 1.84375, "learning_rate": 1.874840030714103e-05, "loss": 0.4293, "step": 7327 }, { "epoch": 1.875776, "grad_norm": 1.890625, "learning_rate": 1.8744134459517107e-05, "loss": 0.4426, "step": 7328 }, { "epoch": 1.876032, "grad_norm": 1.8125, "learning_rate": 1.8739868611893185e-05, "loss": 0.4418, "step": 7329 }, { "epoch": 1.876288, "grad_norm": 1.84375, "learning_rate": 1.8735602764269263e-05, "loss": 0.4468, "step": 7330 }, { "epoch": 1.876544, "grad_norm": 1.890625, "learning_rate": 1.873133691664534e-05, "loss": 0.4254, "step": 7331 }, { "epoch": 1.8768, "grad_norm": 1.96875, "learning_rate": 1.8727071069021414e-05, "loss": 0.4637, "step": 7332 }, { "epoch": 1.877056, "grad_norm": 1.8671875, "learning_rate": 1.8722805221397492e-05, "loss": 0.401, "step": 7333 }, { "epoch": 1.8773119999999999, "grad_norm": 1.8671875, "learning_rate": 1.871853937377357e-05, "loss": 0.449, "step": 7334 }, { "epoch": 1.8775680000000001, "grad_norm": 1.8984375, "learning_rate": 1.8714273526149647e-05, "loss": 0.4303, "step": 7335 }, { "epoch": 1.877824, "grad_norm": 1.9140625, "learning_rate": 1.8710007678525722e-05, "loss": 0.4131, "step": 7336 }, { "epoch": 1.87808, "grad_norm": 1.859375, "learning_rate": 1.8705741830901803e-05, "loss": 0.4569, "step": 7337 }, { "epoch": 1.878336, "grad_norm": 1.96875, "learning_rate": 1.8701475983277877e-05, "loss": 0.4149, "step": 7338 }, { "epoch": 1.878592, "grad_norm": 1.8515625, "learning_rate": 1.8697210135653955e-05, "loss": 0.4361, "step": 7339 }, { "epoch": 1.878848, "grad_norm": 1.859375, "learning_rate": 1.8692944288030032e-05, "loss": 0.4576, "step": 7340 }, { "epoch": 1.8791039999999999, "grad_norm": 1.703125, "learning_rate": 1.868867844040611e-05, "loss": 0.4299, "step": 7341 }, { "epoch": 1.8793600000000001, "grad_norm": 1.9375, "learning_rate": 1.8684412592782184e-05, "loss": 0.4486, "step": 7342 }, { "epoch": 1.879616, "grad_norm": 2.03125, "learning_rate": 1.8680146745158265e-05, "loss": 0.4199, "step": 7343 }, { "epoch": 1.879872, "grad_norm": 1.9375, "learning_rate": 1.867588089753434e-05, "loss": 0.4392, "step": 7344 }, { "epoch": 1.880128, "grad_norm": 1.9453125, "learning_rate": 1.8671615049910417e-05, "loss": 0.4361, "step": 7345 }, { "epoch": 1.880384, "grad_norm": 1.8984375, "learning_rate": 1.8667349202286495e-05, "loss": 0.4304, "step": 7346 }, { "epoch": 1.88064, "grad_norm": 1.9453125, "learning_rate": 1.8663083354662573e-05, "loss": 0.4002, "step": 7347 }, { "epoch": 1.880896, "grad_norm": 1.890625, "learning_rate": 1.865881750703865e-05, "loss": 0.4244, "step": 7348 }, { "epoch": 1.8811520000000002, "grad_norm": 1.8515625, "learning_rate": 1.8654551659414728e-05, "loss": 0.4143, "step": 7349 }, { "epoch": 1.881408, "grad_norm": 1.734375, "learning_rate": 1.8650285811790805e-05, "loss": 0.4403, "step": 7350 }, { "epoch": 1.881664, "grad_norm": 2.03125, "learning_rate": 1.864601996416688e-05, "loss": 0.3902, "step": 7351 }, { "epoch": 1.88192, "grad_norm": 1.9453125, "learning_rate": 1.8641754116542957e-05, "loss": 0.47, "step": 7352 }, { "epoch": 1.8821759999999998, "grad_norm": 1.9140625, "learning_rate": 1.8637488268919035e-05, "loss": 0.4106, "step": 7353 }, { "epoch": 1.882432, "grad_norm": 1.8515625, "learning_rate": 1.8633222421295113e-05, "loss": 0.4057, "step": 7354 }, { "epoch": 1.882688, "grad_norm": 1.8828125, "learning_rate": 1.8628956573671187e-05, "loss": 0.4279, "step": 7355 }, { "epoch": 1.882944, "grad_norm": 2.015625, "learning_rate": 1.8624690726047268e-05, "loss": 0.4677, "step": 7356 }, { "epoch": 1.8832, "grad_norm": 2.109375, "learning_rate": 1.8620424878423342e-05, "loss": 0.4227, "step": 7357 }, { "epoch": 1.883456, "grad_norm": 2.15625, "learning_rate": 1.861615903079942e-05, "loss": 0.4068, "step": 7358 }, { "epoch": 1.883712, "grad_norm": 2.0, "learning_rate": 1.8611893183175498e-05, "loss": 0.4441, "step": 7359 }, { "epoch": 1.8839679999999999, "grad_norm": 1.9609375, "learning_rate": 1.8607627335551575e-05, "loss": 0.4073, "step": 7360 }, { "epoch": 1.8842240000000001, "grad_norm": 1.8671875, "learning_rate": 1.860336148792765e-05, "loss": 0.477, "step": 7361 }, { "epoch": 1.88448, "grad_norm": 2.078125, "learning_rate": 1.859909564030373e-05, "loss": 0.3959, "step": 7362 }, { "epoch": 1.884736, "grad_norm": 1.890625, "learning_rate": 1.8594829792679808e-05, "loss": 0.4596, "step": 7363 }, { "epoch": 1.884992, "grad_norm": 1.9296875, "learning_rate": 1.8590563945055882e-05, "loss": 0.4333, "step": 7364 }, { "epoch": 1.885248, "grad_norm": 1.8515625, "learning_rate": 1.858629809743196e-05, "loss": 0.454, "step": 7365 }, { "epoch": 1.885504, "grad_norm": 1.84375, "learning_rate": 1.8582032249808038e-05, "loss": 0.4277, "step": 7366 }, { "epoch": 1.8857599999999999, "grad_norm": 1.9140625, "learning_rate": 1.8577766402184115e-05, "loss": 0.4648, "step": 7367 }, { "epoch": 1.8860160000000001, "grad_norm": 1.875, "learning_rate": 1.8573500554560193e-05, "loss": 0.4001, "step": 7368 }, { "epoch": 1.886272, "grad_norm": 1.953125, "learning_rate": 1.856923470693627e-05, "loss": 0.4411, "step": 7369 }, { "epoch": 1.886528, "grad_norm": 1.9609375, "learning_rate": 1.8564968859312345e-05, "loss": 0.4388, "step": 7370 }, { "epoch": 1.886784, "grad_norm": 1.921875, "learning_rate": 1.8560703011688423e-05, "loss": 0.4349, "step": 7371 }, { "epoch": 1.88704, "grad_norm": 1.9140625, "learning_rate": 1.85564371640645e-05, "loss": 0.4325, "step": 7372 }, { "epoch": 1.887296, "grad_norm": 1.8828125, "learning_rate": 1.8552171316440578e-05, "loss": 0.4595, "step": 7373 }, { "epoch": 1.887552, "grad_norm": 1.8125, "learning_rate": 1.8547905468816652e-05, "loss": 0.3905, "step": 7374 }, { "epoch": 1.8878080000000002, "grad_norm": 1.8359375, "learning_rate": 1.8543639621192733e-05, "loss": 0.395, "step": 7375 }, { "epoch": 1.888064, "grad_norm": 1.96875, "learning_rate": 1.8539373773568808e-05, "loss": 0.4106, "step": 7376 }, { "epoch": 1.88832, "grad_norm": 1.7421875, "learning_rate": 1.8535107925944885e-05, "loss": 0.4281, "step": 7377 }, { "epoch": 1.888576, "grad_norm": 1.9453125, "learning_rate": 1.8530842078320966e-05, "loss": 0.4296, "step": 7378 }, { "epoch": 1.8888319999999998, "grad_norm": 1.8671875, "learning_rate": 1.852657623069704e-05, "loss": 0.4357, "step": 7379 }, { "epoch": 1.889088, "grad_norm": 1.8671875, "learning_rate": 1.8522310383073118e-05, "loss": 0.4522, "step": 7380 }, { "epoch": 1.889344, "grad_norm": 1.984375, "learning_rate": 1.8518044535449196e-05, "loss": 0.4439, "step": 7381 }, { "epoch": 1.8896, "grad_norm": 1.890625, "learning_rate": 1.8513778687825273e-05, "loss": 0.4315, "step": 7382 }, { "epoch": 1.889856, "grad_norm": 1.859375, "learning_rate": 1.8509512840201348e-05, "loss": 0.4374, "step": 7383 }, { "epoch": 1.890112, "grad_norm": 1.9765625, "learning_rate": 1.8505246992577425e-05, "loss": 0.4177, "step": 7384 }, { "epoch": 1.890368, "grad_norm": 1.890625, "learning_rate": 1.8500981144953503e-05, "loss": 0.431, "step": 7385 }, { "epoch": 1.8906239999999999, "grad_norm": 1.859375, "learning_rate": 1.849671529732958e-05, "loss": 0.3912, "step": 7386 }, { "epoch": 1.8908800000000001, "grad_norm": 1.8828125, "learning_rate": 1.8492449449705655e-05, "loss": 0.4157, "step": 7387 }, { "epoch": 1.891136, "grad_norm": 1.921875, "learning_rate": 1.8488183602081736e-05, "loss": 0.4178, "step": 7388 }, { "epoch": 1.891392, "grad_norm": 1.96875, "learning_rate": 1.848391775445781e-05, "loss": 0.4166, "step": 7389 }, { "epoch": 1.891648, "grad_norm": 1.8046875, "learning_rate": 1.8479651906833888e-05, "loss": 0.4444, "step": 7390 }, { "epoch": 1.891904, "grad_norm": 1.8671875, "learning_rate": 1.8475386059209966e-05, "loss": 0.4229, "step": 7391 }, { "epoch": 1.89216, "grad_norm": 1.7734375, "learning_rate": 1.8471120211586043e-05, "loss": 0.4453, "step": 7392 }, { "epoch": 1.8924159999999999, "grad_norm": 1.90625, "learning_rate": 1.8466854363962118e-05, "loss": 0.4305, "step": 7393 }, { "epoch": 1.8926720000000001, "grad_norm": 1.8671875, "learning_rate": 1.84625885163382e-05, "loss": 0.4157, "step": 7394 }, { "epoch": 1.892928, "grad_norm": 1.8203125, "learning_rate": 1.8458322668714276e-05, "loss": 0.4473, "step": 7395 }, { "epoch": 1.893184, "grad_norm": 2.015625, "learning_rate": 1.845405682109035e-05, "loss": 0.4894, "step": 7396 }, { "epoch": 1.89344, "grad_norm": 1.796875, "learning_rate": 1.8449790973466428e-05, "loss": 0.4631, "step": 7397 }, { "epoch": 1.893696, "grad_norm": 2.015625, "learning_rate": 1.8445525125842506e-05, "loss": 0.3958, "step": 7398 }, { "epoch": 1.893952, "grad_norm": 1.8671875, "learning_rate": 1.8441259278218583e-05, "loss": 0.4527, "step": 7399 }, { "epoch": 1.894208, "grad_norm": 1.7578125, "learning_rate": 1.843699343059466e-05, "loss": 0.3964, "step": 7400 }, { "epoch": 1.8944640000000001, "grad_norm": 2.046875, "learning_rate": 1.843272758297074e-05, "loss": 0.4407, "step": 7401 }, { "epoch": 1.89472, "grad_norm": 1.8515625, "learning_rate": 1.8428461735346813e-05, "loss": 0.4083, "step": 7402 }, { "epoch": 1.894976, "grad_norm": 1.7890625, "learning_rate": 1.842419588772289e-05, "loss": 0.4013, "step": 7403 }, { "epoch": 1.895232, "grad_norm": 1.8515625, "learning_rate": 1.841993004009897e-05, "loss": 0.4477, "step": 7404 }, { "epoch": 1.8954879999999998, "grad_norm": 1.9609375, "learning_rate": 1.8415664192475046e-05, "loss": 0.4361, "step": 7405 }, { "epoch": 1.895744, "grad_norm": 1.90625, "learning_rate": 1.841139834485112e-05, "loss": 0.4381, "step": 7406 }, { "epoch": 1.896, "grad_norm": 1.875, "learning_rate": 1.84071324972272e-05, "loss": 0.4497, "step": 7407 }, { "epoch": 1.8962560000000002, "grad_norm": 1.8359375, "learning_rate": 1.8402866649603276e-05, "loss": 0.4169, "step": 7408 }, { "epoch": 1.896512, "grad_norm": 1.7109375, "learning_rate": 1.8398600801979353e-05, "loss": 0.4479, "step": 7409 }, { "epoch": 1.896768, "grad_norm": 1.859375, "learning_rate": 1.839433495435543e-05, "loss": 0.4174, "step": 7410 }, { "epoch": 1.897024, "grad_norm": 1.953125, "learning_rate": 1.839006910673151e-05, "loss": 0.397, "step": 7411 }, { "epoch": 1.8972799999999999, "grad_norm": 1.875, "learning_rate": 1.8385803259107586e-05, "loss": 0.4317, "step": 7412 }, { "epoch": 1.8975360000000001, "grad_norm": 1.84375, "learning_rate": 1.8381537411483664e-05, "loss": 0.4354, "step": 7413 }, { "epoch": 1.897792, "grad_norm": 1.9921875, "learning_rate": 1.837727156385974e-05, "loss": 0.4523, "step": 7414 }, { "epoch": 1.898048, "grad_norm": 1.890625, "learning_rate": 1.8373005716235816e-05, "loss": 0.4577, "step": 7415 }, { "epoch": 1.898304, "grad_norm": 1.9296875, "learning_rate": 1.8368739868611893e-05, "loss": 0.4483, "step": 7416 }, { "epoch": 1.89856, "grad_norm": 1.9140625, "learning_rate": 1.836447402098797e-05, "loss": 0.4395, "step": 7417 }, { "epoch": 1.898816, "grad_norm": 2.078125, "learning_rate": 1.836020817336405e-05, "loss": 0.3831, "step": 7418 }, { "epoch": 1.8990719999999999, "grad_norm": 1.8828125, "learning_rate": 1.8355942325740126e-05, "loss": 0.4266, "step": 7419 }, { "epoch": 1.8993280000000001, "grad_norm": 1.9609375, "learning_rate": 1.8351676478116204e-05, "loss": 0.429, "step": 7420 }, { "epoch": 1.899584, "grad_norm": 1.8515625, "learning_rate": 1.8347410630492278e-05, "loss": 0.4465, "step": 7421 }, { "epoch": 1.89984, "grad_norm": 1.90625, "learning_rate": 1.8343144782868356e-05, "loss": 0.4414, "step": 7422 }, { "epoch": 1.900096, "grad_norm": 1.7890625, "learning_rate": 1.8338878935244434e-05, "loss": 0.4104, "step": 7423 }, { "epoch": 1.900352, "grad_norm": 1.90625, "learning_rate": 1.833461308762051e-05, "loss": 0.4512, "step": 7424 }, { "epoch": 1.900608, "grad_norm": 1.9375, "learning_rate": 1.8330347239996586e-05, "loss": 0.4152, "step": 7425 }, { "epoch": 1.9008639999999999, "grad_norm": 1.96875, "learning_rate": 1.8326081392372667e-05, "loss": 0.4487, "step": 7426 }, { "epoch": 1.9011200000000001, "grad_norm": 1.875, "learning_rate": 1.832181554474874e-05, "loss": 0.4324, "step": 7427 }, { "epoch": 1.901376, "grad_norm": 1.96875, "learning_rate": 1.831754969712482e-05, "loss": 0.4288, "step": 7428 }, { "epoch": 1.901632, "grad_norm": 1.9140625, "learning_rate": 1.83132838495009e-05, "loss": 0.4278, "step": 7429 }, { "epoch": 1.901888, "grad_norm": 1.8203125, "learning_rate": 1.8309018001876974e-05, "loss": 0.4311, "step": 7430 }, { "epoch": 1.9021439999999998, "grad_norm": 1.8515625, "learning_rate": 1.830475215425305e-05, "loss": 0.4047, "step": 7431 }, { "epoch": 1.9024, "grad_norm": 1.734375, "learning_rate": 1.830048630662913e-05, "loss": 0.4371, "step": 7432 }, { "epoch": 1.902656, "grad_norm": 1.8984375, "learning_rate": 1.8296220459005207e-05, "loss": 0.4603, "step": 7433 }, { "epoch": 1.9029120000000002, "grad_norm": 1.8046875, "learning_rate": 1.829195461138128e-05, "loss": 0.4396, "step": 7434 }, { "epoch": 1.903168, "grad_norm": 1.84375, "learning_rate": 1.828768876375736e-05, "loss": 0.4496, "step": 7435 }, { "epoch": 1.903424, "grad_norm": 1.9609375, "learning_rate": 1.8283422916133436e-05, "loss": 0.4477, "step": 7436 }, { "epoch": 1.90368, "grad_norm": 1.9296875, "learning_rate": 1.8279157068509514e-05, "loss": 0.4382, "step": 7437 }, { "epoch": 1.9039359999999999, "grad_norm": 1.96875, "learning_rate": 1.8274891220885588e-05, "loss": 0.4374, "step": 7438 }, { "epoch": 1.904192, "grad_norm": 1.8359375, "learning_rate": 1.827062537326167e-05, "loss": 0.4219, "step": 7439 }, { "epoch": 1.904448, "grad_norm": 2.0, "learning_rate": 1.8266359525637744e-05, "loss": 0.4431, "step": 7440 }, { "epoch": 1.904704, "grad_norm": 1.9453125, "learning_rate": 1.826209367801382e-05, "loss": 0.4417, "step": 7441 }, { "epoch": 1.90496, "grad_norm": 1.8359375, "learning_rate": 1.82578278303899e-05, "loss": 0.4242, "step": 7442 }, { "epoch": 1.905216, "grad_norm": 1.9921875, "learning_rate": 1.8253561982765977e-05, "loss": 0.4565, "step": 7443 }, { "epoch": 1.905472, "grad_norm": 1.859375, "learning_rate": 1.8249296135142054e-05, "loss": 0.4372, "step": 7444 }, { "epoch": 1.9057279999999999, "grad_norm": 1.734375, "learning_rate": 1.8245030287518132e-05, "loss": 0.433, "step": 7445 }, { "epoch": 1.9059840000000001, "grad_norm": 1.765625, "learning_rate": 1.824076443989421e-05, "loss": 0.4603, "step": 7446 }, { "epoch": 1.90624, "grad_norm": 1.9765625, "learning_rate": 1.8236498592270284e-05, "loss": 0.4215, "step": 7447 }, { "epoch": 1.906496, "grad_norm": 1.828125, "learning_rate": 1.8232232744646365e-05, "loss": 0.4528, "step": 7448 }, { "epoch": 1.906752, "grad_norm": 1.90625, "learning_rate": 1.822796689702244e-05, "loss": 0.4551, "step": 7449 }, { "epoch": 1.907008, "grad_norm": 1.9296875, "learning_rate": 1.8223701049398517e-05, "loss": 0.4379, "step": 7450 }, { "epoch": 1.907264, "grad_norm": 1.8359375, "learning_rate": 1.8219435201774594e-05, "loss": 0.3907, "step": 7451 }, { "epoch": 1.9075199999999999, "grad_norm": 1.75, "learning_rate": 1.8215169354150672e-05, "loss": 0.4606, "step": 7452 }, { "epoch": 1.9077760000000001, "grad_norm": 1.890625, "learning_rate": 1.8210903506526746e-05, "loss": 0.4251, "step": 7453 }, { "epoch": 1.908032, "grad_norm": 1.8515625, "learning_rate": 1.8206637658902824e-05, "loss": 0.4468, "step": 7454 }, { "epoch": 1.908288, "grad_norm": 1.8203125, "learning_rate": 1.82023718112789e-05, "loss": 0.437, "step": 7455 }, { "epoch": 1.908544, "grad_norm": 2.015625, "learning_rate": 1.819810596365498e-05, "loss": 0.4316, "step": 7456 }, { "epoch": 1.9088, "grad_norm": 2.03125, "learning_rate": 1.8193840116031054e-05, "loss": 0.4427, "step": 7457 }, { "epoch": 1.909056, "grad_norm": 2.015625, "learning_rate": 1.8189574268407135e-05, "loss": 0.4263, "step": 7458 }, { "epoch": 1.909312, "grad_norm": 1.9296875, "learning_rate": 1.818530842078321e-05, "loss": 0.4476, "step": 7459 }, { "epoch": 1.9095680000000002, "grad_norm": 1.75, "learning_rate": 1.8181042573159286e-05, "loss": 0.4595, "step": 7460 }, { "epoch": 1.909824, "grad_norm": 1.7890625, "learning_rate": 1.8176776725535368e-05, "loss": 0.449, "step": 7461 }, { "epoch": 1.91008, "grad_norm": 2.09375, "learning_rate": 1.8172510877911442e-05, "loss": 0.4136, "step": 7462 }, { "epoch": 1.910336, "grad_norm": 1.859375, "learning_rate": 1.816824503028752e-05, "loss": 0.4446, "step": 7463 }, { "epoch": 1.9105919999999998, "grad_norm": 1.9453125, "learning_rate": 1.8163979182663597e-05, "loss": 0.4329, "step": 7464 }, { "epoch": 1.910848, "grad_norm": 2.109375, "learning_rate": 1.8159713335039675e-05, "loss": 0.3945, "step": 7465 }, { "epoch": 1.911104, "grad_norm": 1.875, "learning_rate": 1.815544748741575e-05, "loss": 0.4141, "step": 7466 }, { "epoch": 1.91136, "grad_norm": 1.9453125, "learning_rate": 1.8151181639791827e-05, "loss": 0.4104, "step": 7467 }, { "epoch": 1.911616, "grad_norm": 2.046875, "learning_rate": 1.8146915792167904e-05, "loss": 0.4242, "step": 7468 }, { "epoch": 1.911872, "grad_norm": 1.859375, "learning_rate": 1.8142649944543982e-05, "loss": 0.4321, "step": 7469 }, { "epoch": 1.912128, "grad_norm": 1.828125, "learning_rate": 1.813838409692006e-05, "loss": 0.4068, "step": 7470 }, { "epoch": 1.9123839999999999, "grad_norm": 1.8828125, "learning_rate": 1.8134118249296137e-05, "loss": 0.4111, "step": 7471 }, { "epoch": 1.9126400000000001, "grad_norm": 1.828125, "learning_rate": 1.812985240167221e-05, "loss": 0.4567, "step": 7472 }, { "epoch": 1.912896, "grad_norm": 1.7890625, "learning_rate": 1.812558655404829e-05, "loss": 0.404, "step": 7473 }, { "epoch": 1.913152, "grad_norm": 1.8359375, "learning_rate": 1.8121320706424367e-05, "loss": 0.4414, "step": 7474 }, { "epoch": 1.913408, "grad_norm": 1.9765625, "learning_rate": 1.8117054858800445e-05, "loss": 0.4412, "step": 7475 }, { "epoch": 1.913664, "grad_norm": 1.7890625, "learning_rate": 1.811278901117652e-05, "loss": 0.4027, "step": 7476 }, { "epoch": 1.91392, "grad_norm": 2.078125, "learning_rate": 1.81085231635526e-05, "loss": 0.4297, "step": 7477 }, { "epoch": 1.9141759999999999, "grad_norm": 1.953125, "learning_rate": 1.8104257315928677e-05, "loss": 0.4272, "step": 7478 }, { "epoch": 1.9144320000000001, "grad_norm": 1.9609375, "learning_rate": 1.8099991468304752e-05, "loss": 0.4628, "step": 7479 }, { "epoch": 1.914688, "grad_norm": 2.015625, "learning_rate": 1.8095725620680833e-05, "loss": 0.409, "step": 7480 }, { "epoch": 1.914944, "grad_norm": 1.9765625, "learning_rate": 1.8091459773056907e-05, "loss": 0.4332, "step": 7481 }, { "epoch": 1.9152, "grad_norm": 1.96875, "learning_rate": 1.8087193925432985e-05, "loss": 0.3992, "step": 7482 }, { "epoch": 1.915456, "grad_norm": 1.8984375, "learning_rate": 1.8082928077809062e-05, "loss": 0.426, "step": 7483 }, { "epoch": 1.915712, "grad_norm": 2.046875, "learning_rate": 1.807866223018514e-05, "loss": 0.4638, "step": 7484 }, { "epoch": 1.915968, "grad_norm": 2.0, "learning_rate": 1.8074396382561214e-05, "loss": 0.4519, "step": 7485 }, { "epoch": 1.9162240000000001, "grad_norm": 2.03125, "learning_rate": 1.8070130534937292e-05, "loss": 0.4584, "step": 7486 }, { "epoch": 1.91648, "grad_norm": 1.96875, "learning_rate": 1.806586468731337e-05, "loss": 0.4427, "step": 7487 }, { "epoch": 1.916736, "grad_norm": 1.828125, "learning_rate": 1.8061598839689447e-05, "loss": 0.4463, "step": 7488 }, { "epoch": 1.916992, "grad_norm": 1.859375, "learning_rate": 1.805733299206552e-05, "loss": 0.4196, "step": 7489 }, { "epoch": 1.9172479999999998, "grad_norm": 1.828125, "learning_rate": 1.8053067144441603e-05, "loss": 0.4435, "step": 7490 }, { "epoch": 1.917504, "grad_norm": 1.8984375, "learning_rate": 1.8048801296817677e-05, "loss": 0.438, "step": 7491 }, { "epoch": 1.91776, "grad_norm": 1.859375, "learning_rate": 1.8044535449193754e-05, "loss": 0.3556, "step": 7492 }, { "epoch": 1.9180160000000002, "grad_norm": 2.015625, "learning_rate": 1.8040269601569836e-05, "loss": 0.4321, "step": 7493 }, { "epoch": 1.918272, "grad_norm": 1.9921875, "learning_rate": 1.803600375394591e-05, "loss": 0.4298, "step": 7494 }, { "epoch": 1.918528, "grad_norm": 1.921875, "learning_rate": 1.8031737906321987e-05, "loss": 0.4106, "step": 7495 }, { "epoch": 1.918784, "grad_norm": 1.828125, "learning_rate": 1.8027472058698065e-05, "loss": 0.4371, "step": 7496 }, { "epoch": 1.9190399999999999, "grad_norm": 1.9375, "learning_rate": 1.8023206211074143e-05, "loss": 0.4346, "step": 7497 }, { "epoch": 1.9192960000000001, "grad_norm": 1.96875, "learning_rate": 1.8018940363450217e-05, "loss": 0.4405, "step": 7498 }, { "epoch": 1.919552, "grad_norm": 1.84375, "learning_rate": 1.8014674515826298e-05, "loss": 0.4398, "step": 7499 }, { "epoch": 1.919808, "grad_norm": 1.9453125, "learning_rate": 1.8010408668202372e-05, "loss": 0.3985, "step": 7500 }, { "epoch": 1.920064, "grad_norm": 1.890625, "learning_rate": 1.800614282057845e-05, "loss": 0.4487, "step": 7501 }, { "epoch": 1.92032, "grad_norm": 1.78125, "learning_rate": 1.8001876972954528e-05, "loss": 0.4523, "step": 7502 }, { "epoch": 1.920576, "grad_norm": 1.90625, "learning_rate": 1.7997611125330605e-05, "loss": 0.4281, "step": 7503 }, { "epoch": 1.9208319999999999, "grad_norm": 2.15625, "learning_rate": 1.799334527770668e-05, "loss": 0.4556, "step": 7504 }, { "epoch": 1.9210880000000001, "grad_norm": 2.015625, "learning_rate": 1.7989079430082757e-05, "loss": 0.4417, "step": 7505 }, { "epoch": 1.921344, "grad_norm": 1.8359375, "learning_rate": 1.7984813582458835e-05, "loss": 0.445, "step": 7506 }, { "epoch": 1.9216, "grad_norm": 1.828125, "learning_rate": 1.7980547734834913e-05, "loss": 0.4304, "step": 7507 }, { "epoch": 1.921856, "grad_norm": 2.046875, "learning_rate": 1.7976281887210987e-05, "loss": 0.4184, "step": 7508 }, { "epoch": 1.922112, "grad_norm": 2.0, "learning_rate": 1.7972016039587068e-05, "loss": 0.4363, "step": 7509 }, { "epoch": 1.922368, "grad_norm": 1.8515625, "learning_rate": 1.7967750191963145e-05, "loss": 0.4281, "step": 7510 }, { "epoch": 1.9226239999999999, "grad_norm": 1.75, "learning_rate": 1.796348434433922e-05, "loss": 0.4421, "step": 7511 }, { "epoch": 1.9228800000000001, "grad_norm": 2.03125, "learning_rate": 1.79592184967153e-05, "loss": 0.4695, "step": 7512 }, { "epoch": 1.923136, "grad_norm": 1.9375, "learning_rate": 1.7954952649091375e-05, "loss": 0.4568, "step": 7513 }, { "epoch": 1.923392, "grad_norm": 1.921875, "learning_rate": 1.7950686801467453e-05, "loss": 0.4377, "step": 7514 }, { "epoch": 1.923648, "grad_norm": 1.8515625, "learning_rate": 1.794642095384353e-05, "loss": 0.427, "step": 7515 }, { "epoch": 1.9239039999999998, "grad_norm": 1.78125, "learning_rate": 1.7942155106219608e-05, "loss": 0.3849, "step": 7516 }, { "epoch": 1.92416, "grad_norm": 1.8828125, "learning_rate": 1.7937889258595682e-05, "loss": 0.4103, "step": 7517 }, { "epoch": 1.924416, "grad_norm": 1.9921875, "learning_rate": 1.793362341097176e-05, "loss": 0.4258, "step": 7518 }, { "epoch": 1.9246720000000002, "grad_norm": 1.875, "learning_rate": 1.7929357563347838e-05, "loss": 0.44, "step": 7519 }, { "epoch": 1.924928, "grad_norm": 2.0625, "learning_rate": 1.7925091715723915e-05, "loss": 0.4545, "step": 7520 }, { "epoch": 1.925184, "grad_norm": 1.9921875, "learning_rate": 1.7920825868099993e-05, "loss": 0.4556, "step": 7521 }, { "epoch": 1.92544, "grad_norm": 1.828125, "learning_rate": 1.791656002047607e-05, "loss": 0.4088, "step": 7522 }, { "epoch": 1.9256959999999999, "grad_norm": 1.8125, "learning_rate": 1.7912294172852145e-05, "loss": 0.4043, "step": 7523 }, { "epoch": 1.925952, "grad_norm": 1.78125, "learning_rate": 1.7908028325228222e-05, "loss": 0.4335, "step": 7524 }, { "epoch": 1.926208, "grad_norm": 2.0, "learning_rate": 1.79037624776043e-05, "loss": 0.4127, "step": 7525 }, { "epoch": 1.926464, "grad_norm": 1.8359375, "learning_rate": 1.7899496629980378e-05, "loss": 0.3998, "step": 7526 }, { "epoch": 1.92672, "grad_norm": 1.875, "learning_rate": 1.7895230782356455e-05, "loss": 0.4272, "step": 7527 }, { "epoch": 1.926976, "grad_norm": 1.921875, "learning_rate": 1.7890964934732533e-05, "loss": 0.4237, "step": 7528 }, { "epoch": 1.927232, "grad_norm": 1.9140625, "learning_rate": 1.788669908710861e-05, "loss": 0.411, "step": 7529 }, { "epoch": 1.9274879999999999, "grad_norm": 1.875, "learning_rate": 1.7882433239484685e-05, "loss": 0.4358, "step": 7530 }, { "epoch": 1.9277440000000001, "grad_norm": 1.9140625, "learning_rate": 1.7878167391860766e-05, "loss": 0.4407, "step": 7531 }, { "epoch": 1.928, "grad_norm": 1.90625, "learning_rate": 1.787390154423684e-05, "loss": 0.4465, "step": 7532 }, { "epoch": 1.928256, "grad_norm": 1.9453125, "learning_rate": 1.7869635696612918e-05, "loss": 0.4083, "step": 7533 }, { "epoch": 1.928512, "grad_norm": 1.84375, "learning_rate": 1.7865369848988996e-05, "loss": 0.402, "step": 7534 }, { "epoch": 1.928768, "grad_norm": 1.7578125, "learning_rate": 1.7861104001365073e-05, "loss": 0.4377, "step": 7535 }, { "epoch": 1.929024, "grad_norm": 1.984375, "learning_rate": 1.7856838153741148e-05, "loss": 0.3902, "step": 7536 }, { "epoch": 1.9292799999999999, "grad_norm": 1.8515625, "learning_rate": 1.7852572306117225e-05, "loss": 0.4184, "step": 7537 }, { "epoch": 1.9295360000000001, "grad_norm": 1.9140625, "learning_rate": 1.7848306458493303e-05, "loss": 0.3911, "step": 7538 }, { "epoch": 1.929792, "grad_norm": 1.921875, "learning_rate": 1.784404061086938e-05, "loss": 0.4108, "step": 7539 }, { "epoch": 1.930048, "grad_norm": 1.9296875, "learning_rate": 1.7839774763245458e-05, "loss": 0.4083, "step": 7540 }, { "epoch": 1.930304, "grad_norm": 2.015625, "learning_rate": 1.7835508915621536e-05, "loss": 0.4229, "step": 7541 }, { "epoch": 1.93056, "grad_norm": 1.78125, "learning_rate": 1.7831243067997613e-05, "loss": 0.4266, "step": 7542 }, { "epoch": 1.930816, "grad_norm": 1.875, "learning_rate": 1.7826977220373688e-05, "loss": 0.4308, "step": 7543 }, { "epoch": 1.931072, "grad_norm": 1.953125, "learning_rate": 1.782271137274977e-05, "loss": 0.4403, "step": 7544 }, { "epoch": 1.9313280000000002, "grad_norm": 1.875, "learning_rate": 1.7818445525125843e-05, "loss": 0.4519, "step": 7545 }, { "epoch": 1.931584, "grad_norm": 1.859375, "learning_rate": 1.781417967750192e-05, "loss": 0.4332, "step": 7546 }, { "epoch": 1.93184, "grad_norm": 1.9296875, "learning_rate": 1.7809913829878e-05, "loss": 0.4238, "step": 7547 }, { "epoch": 1.932096, "grad_norm": 2.0, "learning_rate": 1.7805647982254076e-05, "loss": 0.4387, "step": 7548 }, { "epoch": 1.9323519999999998, "grad_norm": 1.9765625, "learning_rate": 1.780138213463015e-05, "loss": 0.4277, "step": 7549 }, { "epoch": 1.932608, "grad_norm": 1.890625, "learning_rate": 1.779711628700623e-05, "loss": 0.4446, "step": 7550 }, { "epoch": 1.932864, "grad_norm": 1.8984375, "learning_rate": 1.7792850439382306e-05, "loss": 0.4533, "step": 7551 }, { "epoch": 1.93312, "grad_norm": 1.953125, "learning_rate": 1.7788584591758383e-05, "loss": 0.4609, "step": 7552 }, { "epoch": 1.933376, "grad_norm": 1.8828125, "learning_rate": 1.778431874413446e-05, "loss": 0.4398, "step": 7553 }, { "epoch": 1.933632, "grad_norm": 1.953125, "learning_rate": 1.778005289651054e-05, "loss": 0.4431, "step": 7554 }, { "epoch": 1.933888, "grad_norm": 2.0625, "learning_rate": 1.7775787048886613e-05, "loss": 0.4417, "step": 7555 }, { "epoch": 1.9341439999999999, "grad_norm": 1.953125, "learning_rate": 1.777152120126269e-05, "loss": 0.4717, "step": 7556 }, { "epoch": 1.9344000000000001, "grad_norm": 1.84375, "learning_rate": 1.7767255353638768e-05, "loss": 0.3927, "step": 7557 }, { "epoch": 1.934656, "grad_norm": 1.984375, "learning_rate": 1.7762989506014846e-05, "loss": 0.4145, "step": 7558 }, { "epoch": 1.934912, "grad_norm": 1.921875, "learning_rate": 1.7758723658390923e-05, "loss": 0.4582, "step": 7559 }, { "epoch": 1.935168, "grad_norm": 1.9296875, "learning_rate": 1.7754457810767e-05, "loss": 0.4161, "step": 7560 }, { "epoch": 1.935424, "grad_norm": 1.9609375, "learning_rate": 1.775019196314308e-05, "loss": 0.3972, "step": 7561 }, { "epoch": 1.93568, "grad_norm": 1.984375, "learning_rate": 1.7745926115519153e-05, "loss": 0.4403, "step": 7562 }, { "epoch": 1.9359359999999999, "grad_norm": 1.8515625, "learning_rate": 1.7741660267895234e-05, "loss": 0.4702, "step": 7563 }, { "epoch": 1.9361920000000001, "grad_norm": 1.9140625, "learning_rate": 1.773739442027131e-05, "loss": 0.4373, "step": 7564 }, { "epoch": 1.936448, "grad_norm": 1.90625, "learning_rate": 1.7733128572647386e-05, "loss": 0.4303, "step": 7565 }, { "epoch": 1.936704, "grad_norm": 1.9609375, "learning_rate": 1.7728862725023464e-05, "loss": 0.4198, "step": 7566 }, { "epoch": 1.93696, "grad_norm": 1.8828125, "learning_rate": 1.772459687739954e-05, "loss": 0.4788, "step": 7567 }, { "epoch": 1.937216, "grad_norm": 2.125, "learning_rate": 1.7720331029775616e-05, "loss": 0.4086, "step": 7568 }, { "epoch": 1.937472, "grad_norm": 1.921875, "learning_rate": 1.7716065182151693e-05, "loss": 0.4197, "step": 7569 }, { "epoch": 1.937728, "grad_norm": 1.96875, "learning_rate": 1.771179933452777e-05, "loss": 0.4101, "step": 7570 }, { "epoch": 1.9379840000000002, "grad_norm": 1.84375, "learning_rate": 1.770753348690385e-05, "loss": 0.4505, "step": 7571 }, { "epoch": 1.93824, "grad_norm": 1.7734375, "learning_rate": 1.7703267639279926e-05, "loss": 0.4284, "step": 7572 }, { "epoch": 1.938496, "grad_norm": 1.9375, "learning_rate": 1.7699001791656004e-05, "loss": 0.4349, "step": 7573 }, { "epoch": 1.938752, "grad_norm": 1.84375, "learning_rate": 1.7694735944032078e-05, "loss": 0.4324, "step": 7574 }, { "epoch": 1.9390079999999998, "grad_norm": 1.9765625, "learning_rate": 1.7690470096408156e-05, "loss": 0.4187, "step": 7575 }, { "epoch": 1.939264, "grad_norm": 1.8515625, "learning_rate": 1.7686204248784237e-05, "loss": 0.4397, "step": 7576 }, { "epoch": 1.93952, "grad_norm": 1.9765625, "learning_rate": 1.768193840116031e-05, "loss": 0.4039, "step": 7577 }, { "epoch": 1.939776, "grad_norm": 2.015625, "learning_rate": 1.767767255353639e-05, "loss": 0.4279, "step": 7578 }, { "epoch": 1.940032, "grad_norm": 1.84375, "learning_rate": 1.7673406705912466e-05, "loss": 0.4259, "step": 7579 }, { "epoch": 1.940288, "grad_norm": 1.78125, "learning_rate": 1.7669140858288544e-05, "loss": 0.4111, "step": 7580 }, { "epoch": 1.940544, "grad_norm": 1.7890625, "learning_rate": 1.7664875010664618e-05, "loss": 0.4576, "step": 7581 }, { "epoch": 1.9407999999999999, "grad_norm": 1.90625, "learning_rate": 1.76606091630407e-05, "loss": 0.4189, "step": 7582 }, { "epoch": 1.9410560000000001, "grad_norm": 1.90625, "learning_rate": 1.7656343315416774e-05, "loss": 0.4339, "step": 7583 }, { "epoch": 1.941312, "grad_norm": 1.96875, "learning_rate": 1.765207746779285e-05, "loss": 0.4276, "step": 7584 }, { "epoch": 1.941568, "grad_norm": 1.9296875, "learning_rate": 1.764781162016893e-05, "loss": 0.4362, "step": 7585 }, { "epoch": 1.941824, "grad_norm": 2.09375, "learning_rate": 1.7643545772545007e-05, "loss": 0.4407, "step": 7586 }, { "epoch": 1.94208, "grad_norm": 1.8203125, "learning_rate": 1.763927992492108e-05, "loss": 0.4253, "step": 7587 }, { "epoch": 1.942336, "grad_norm": 1.8671875, "learning_rate": 1.763501407729716e-05, "loss": 0.4127, "step": 7588 }, { "epoch": 1.9425919999999999, "grad_norm": 1.796875, "learning_rate": 1.7630748229673236e-05, "loss": 0.4252, "step": 7589 }, { "epoch": 1.9428480000000001, "grad_norm": 2.03125, "learning_rate": 1.7626482382049314e-05, "loss": 0.4226, "step": 7590 }, { "epoch": 1.943104, "grad_norm": 1.9609375, "learning_rate": 1.762221653442539e-05, "loss": 0.443, "step": 7591 }, { "epoch": 1.94336, "grad_norm": 1.890625, "learning_rate": 1.761795068680147e-05, "loss": 0.3986, "step": 7592 }, { "epoch": 1.943616, "grad_norm": 2.015625, "learning_rate": 1.7613684839177547e-05, "loss": 0.3944, "step": 7593 }, { "epoch": 1.943872, "grad_norm": 1.8046875, "learning_rate": 1.760941899155362e-05, "loss": 0.4162, "step": 7594 }, { "epoch": 1.944128, "grad_norm": 1.9140625, "learning_rate": 1.7605153143929702e-05, "loss": 0.4227, "step": 7595 }, { "epoch": 1.944384, "grad_norm": 1.8125, "learning_rate": 1.7600887296305776e-05, "loss": 0.4092, "step": 7596 }, { "epoch": 1.9446400000000001, "grad_norm": 1.8828125, "learning_rate": 1.7596621448681854e-05, "loss": 0.4351, "step": 7597 }, { "epoch": 1.944896, "grad_norm": 1.875, "learning_rate": 1.759235560105793e-05, "loss": 0.4146, "step": 7598 }, { "epoch": 1.945152, "grad_norm": 1.984375, "learning_rate": 1.758808975343401e-05, "loss": 0.4087, "step": 7599 }, { "epoch": 1.945408, "grad_norm": 1.8515625, "learning_rate": 1.7583823905810084e-05, "loss": 0.4394, "step": 7600 }, { "epoch": 1.9456639999999998, "grad_norm": 1.8046875, "learning_rate": 1.7579558058186165e-05, "loss": 0.4385, "step": 7601 }, { "epoch": 1.94592, "grad_norm": 1.921875, "learning_rate": 1.757529221056224e-05, "loss": 0.4421, "step": 7602 }, { "epoch": 1.946176, "grad_norm": 1.8984375, "learning_rate": 1.7571026362938317e-05, "loss": 0.4209, "step": 7603 }, { "epoch": 1.9464320000000002, "grad_norm": 1.90625, "learning_rate": 1.7566760515314394e-05, "loss": 0.3962, "step": 7604 }, { "epoch": 1.946688, "grad_norm": 1.7734375, "learning_rate": 1.7562494667690472e-05, "loss": 0.4403, "step": 7605 }, { "epoch": 1.946944, "grad_norm": 1.875, "learning_rate": 1.7558228820066546e-05, "loss": 0.4196, "step": 7606 }, { "epoch": 1.9472, "grad_norm": 1.9453125, "learning_rate": 1.7553962972442624e-05, "loss": 0.4276, "step": 7607 }, { "epoch": 1.9474559999999999, "grad_norm": 1.8984375, "learning_rate": 1.7549697124818705e-05, "loss": 0.3958, "step": 7608 }, { "epoch": 1.947712, "grad_norm": 2.046875, "learning_rate": 1.754543127719478e-05, "loss": 0.4105, "step": 7609 }, { "epoch": 1.947968, "grad_norm": 1.78125, "learning_rate": 1.7541165429570857e-05, "loss": 0.475, "step": 7610 }, { "epoch": 1.948224, "grad_norm": 1.9140625, "learning_rate": 1.7536899581946934e-05, "loss": 0.4278, "step": 7611 }, { "epoch": 1.94848, "grad_norm": 1.890625, "learning_rate": 1.7532633734323012e-05, "loss": 0.4443, "step": 7612 }, { "epoch": 1.948736, "grad_norm": 1.9765625, "learning_rate": 1.7528367886699086e-05, "loss": 0.4076, "step": 7613 }, { "epoch": 1.948992, "grad_norm": 1.890625, "learning_rate": 1.7524102039075167e-05, "loss": 0.4116, "step": 7614 }, { "epoch": 1.9492479999999999, "grad_norm": 1.9296875, "learning_rate": 1.751983619145124e-05, "loss": 0.4311, "step": 7615 }, { "epoch": 1.9495040000000001, "grad_norm": 1.8515625, "learning_rate": 1.751557034382732e-05, "loss": 0.4166, "step": 7616 }, { "epoch": 1.94976, "grad_norm": 1.8671875, "learning_rate": 1.7511304496203397e-05, "loss": 0.4719, "step": 7617 }, { "epoch": 1.950016, "grad_norm": 1.9375, "learning_rate": 1.7507038648579475e-05, "loss": 0.4288, "step": 7618 }, { "epoch": 1.950272, "grad_norm": 2.046875, "learning_rate": 1.750277280095555e-05, "loss": 0.4453, "step": 7619 }, { "epoch": 1.950528, "grad_norm": 1.828125, "learning_rate": 1.7498506953331626e-05, "loss": 0.3972, "step": 7620 }, { "epoch": 1.950784, "grad_norm": 1.9296875, "learning_rate": 1.7494241105707704e-05, "loss": 0.4471, "step": 7621 }, { "epoch": 1.9510399999999999, "grad_norm": 1.8359375, "learning_rate": 1.7489975258083782e-05, "loss": 0.4051, "step": 7622 }, { "epoch": 1.9512960000000001, "grad_norm": 2.0, "learning_rate": 1.748570941045986e-05, "loss": 0.4604, "step": 7623 }, { "epoch": 1.951552, "grad_norm": 1.828125, "learning_rate": 1.7481443562835937e-05, "loss": 0.4187, "step": 7624 }, { "epoch": 1.951808, "grad_norm": 1.8828125, "learning_rate": 1.7477177715212015e-05, "loss": 0.4589, "step": 7625 }, { "epoch": 1.952064, "grad_norm": 1.875, "learning_rate": 1.747291186758809e-05, "loss": 0.4485, "step": 7626 }, { "epoch": 1.95232, "grad_norm": 1.8515625, "learning_rate": 1.746864601996417e-05, "loss": 0.4606, "step": 7627 }, { "epoch": 1.952576, "grad_norm": 2.046875, "learning_rate": 1.7464380172340244e-05, "loss": 0.4108, "step": 7628 }, { "epoch": 1.952832, "grad_norm": 1.8046875, "learning_rate": 1.7460114324716322e-05, "loss": 0.4258, "step": 7629 }, { "epoch": 1.9530880000000002, "grad_norm": 1.9453125, "learning_rate": 1.74558484770924e-05, "loss": 0.4276, "step": 7630 }, { "epoch": 1.953344, "grad_norm": 1.8203125, "learning_rate": 1.7451582629468477e-05, "loss": 0.3936, "step": 7631 }, { "epoch": 1.9536, "grad_norm": 2.046875, "learning_rate": 1.744731678184455e-05, "loss": 0.4035, "step": 7632 }, { "epoch": 1.953856, "grad_norm": 2.078125, "learning_rate": 1.7443050934220633e-05, "loss": 0.4158, "step": 7633 }, { "epoch": 1.9541119999999998, "grad_norm": 1.8671875, "learning_rate": 1.7438785086596707e-05, "loss": 0.4725, "step": 7634 }, { "epoch": 1.954368, "grad_norm": 1.9765625, "learning_rate": 1.7434519238972785e-05, "loss": 0.4203, "step": 7635 }, { "epoch": 1.954624, "grad_norm": 2.046875, "learning_rate": 1.7430253391348862e-05, "loss": 0.4431, "step": 7636 }, { "epoch": 1.95488, "grad_norm": 1.7578125, "learning_rate": 1.742598754372494e-05, "loss": 0.4127, "step": 7637 }, { "epoch": 1.955136, "grad_norm": 1.8515625, "learning_rate": 1.7421721696101014e-05, "loss": 0.4238, "step": 7638 }, { "epoch": 1.955392, "grad_norm": 1.703125, "learning_rate": 1.7417455848477092e-05, "loss": 0.4363, "step": 7639 }, { "epoch": 1.955648, "grad_norm": 1.84375, "learning_rate": 1.741319000085317e-05, "loss": 0.4185, "step": 7640 }, { "epoch": 1.9559039999999999, "grad_norm": 1.953125, "learning_rate": 1.7408924153229247e-05, "loss": 0.4388, "step": 7641 }, { "epoch": 1.9561600000000001, "grad_norm": 1.953125, "learning_rate": 1.7404658305605325e-05, "loss": 0.4711, "step": 7642 }, { "epoch": 1.956416, "grad_norm": 1.8359375, "learning_rate": 1.7400392457981402e-05, "loss": 0.4439, "step": 7643 }, { "epoch": 1.956672, "grad_norm": 2.046875, "learning_rate": 1.739612661035748e-05, "loss": 0.4492, "step": 7644 }, { "epoch": 1.956928, "grad_norm": 1.8828125, "learning_rate": 1.7391860762733554e-05, "loss": 0.4268, "step": 7645 }, { "epoch": 1.957184, "grad_norm": 1.875, "learning_rate": 1.7387594915109635e-05, "loss": 0.4364, "step": 7646 }, { "epoch": 1.95744, "grad_norm": 1.9375, "learning_rate": 1.738332906748571e-05, "loss": 0.4555, "step": 7647 }, { "epoch": 1.9576959999999999, "grad_norm": 1.8359375, "learning_rate": 1.7379063219861787e-05, "loss": 0.3937, "step": 7648 }, { "epoch": 1.9579520000000001, "grad_norm": 1.9140625, "learning_rate": 1.7374797372237865e-05, "loss": 0.4824, "step": 7649 }, { "epoch": 1.958208, "grad_norm": 1.859375, "learning_rate": 1.7370531524613943e-05, "loss": 0.421, "step": 7650 }, { "epoch": 1.958464, "grad_norm": 1.7890625, "learning_rate": 1.7366265676990017e-05, "loss": 0.4702, "step": 7651 }, { "epoch": 1.95872, "grad_norm": 2.015625, "learning_rate": 1.7361999829366098e-05, "loss": 0.4385, "step": 7652 }, { "epoch": 1.958976, "grad_norm": 1.8359375, "learning_rate": 1.7357733981742172e-05, "loss": 0.4351, "step": 7653 }, { "epoch": 1.959232, "grad_norm": 1.65625, "learning_rate": 1.735346813411825e-05, "loss": 0.4343, "step": 7654 }, { "epoch": 1.959488, "grad_norm": 1.7578125, "learning_rate": 1.7349202286494327e-05, "loss": 0.4291, "step": 7655 }, { "epoch": 1.9597440000000002, "grad_norm": 1.8359375, "learning_rate": 1.7344936438870405e-05, "loss": 0.3994, "step": 7656 }, { "epoch": 1.96, "grad_norm": 1.8984375, "learning_rate": 1.7340670591246483e-05, "loss": 0.4468, "step": 7657 }, { "epoch": 1.960256, "grad_norm": 1.8359375, "learning_rate": 1.7336404743622557e-05, "loss": 0.4265, "step": 7658 }, { "epoch": 1.960512, "grad_norm": 1.8359375, "learning_rate": 1.7332138895998638e-05, "loss": 0.4041, "step": 7659 }, { "epoch": 1.9607679999999998, "grad_norm": 1.9921875, "learning_rate": 1.7327873048374712e-05, "loss": 0.4326, "step": 7660 }, { "epoch": 1.961024, "grad_norm": 1.875, "learning_rate": 1.732360720075079e-05, "loss": 0.4285, "step": 7661 }, { "epoch": 1.96128, "grad_norm": 1.65625, "learning_rate": 1.7319341353126868e-05, "loss": 0.404, "step": 7662 }, { "epoch": 1.961536, "grad_norm": 1.8125, "learning_rate": 1.7315075505502945e-05, "loss": 0.4015, "step": 7663 }, { "epoch": 1.961792, "grad_norm": 1.796875, "learning_rate": 1.731080965787902e-05, "loss": 0.4311, "step": 7664 }, { "epoch": 1.962048, "grad_norm": 1.953125, "learning_rate": 1.73065438102551e-05, "loss": 0.4277, "step": 7665 }, { "epoch": 1.962304, "grad_norm": 1.8046875, "learning_rate": 1.7302277962631175e-05, "loss": 0.4574, "step": 7666 }, { "epoch": 1.9625599999999999, "grad_norm": 1.9765625, "learning_rate": 1.7298012115007253e-05, "loss": 0.4206, "step": 7667 }, { "epoch": 1.9628160000000001, "grad_norm": 2.09375, "learning_rate": 1.729374626738333e-05, "loss": 0.4228, "step": 7668 }, { "epoch": 1.963072, "grad_norm": 2.046875, "learning_rate": 1.7289480419759408e-05, "loss": 0.4242, "step": 7669 }, { "epoch": 1.963328, "grad_norm": 1.75, "learning_rate": 1.7285214572135482e-05, "loss": 0.4234, "step": 7670 }, { "epoch": 1.963584, "grad_norm": 1.8984375, "learning_rate": 1.728094872451156e-05, "loss": 0.4347, "step": 7671 }, { "epoch": 1.96384, "grad_norm": 1.7421875, "learning_rate": 1.7276682876887637e-05, "loss": 0.4187, "step": 7672 }, { "epoch": 1.964096, "grad_norm": 1.78125, "learning_rate": 1.7272417029263715e-05, "loss": 0.4507, "step": 7673 }, { "epoch": 1.9643519999999999, "grad_norm": 1.84375, "learning_rate": 1.7268151181639793e-05, "loss": 0.4578, "step": 7674 }, { "epoch": 1.9646080000000001, "grad_norm": 1.9375, "learning_rate": 1.726388533401587e-05, "loss": 0.4363, "step": 7675 }, { "epoch": 1.964864, "grad_norm": 1.765625, "learning_rate": 1.7259619486391948e-05, "loss": 0.4407, "step": 7676 }, { "epoch": 1.96512, "grad_norm": 1.8828125, "learning_rate": 1.7255353638768022e-05, "loss": 0.4497, "step": 7677 }, { "epoch": 1.965376, "grad_norm": 1.8515625, "learning_rate": 1.7251087791144103e-05, "loss": 0.4047, "step": 7678 }, { "epoch": 1.965632, "grad_norm": 1.828125, "learning_rate": 1.7246821943520178e-05, "loss": 0.4655, "step": 7679 }, { "epoch": 1.965888, "grad_norm": 1.984375, "learning_rate": 1.7242556095896255e-05, "loss": 0.443, "step": 7680 }, { "epoch": 1.966144, "grad_norm": 1.859375, "learning_rate": 1.7238290248272333e-05, "loss": 0.4281, "step": 7681 }, { "epoch": 1.9664000000000001, "grad_norm": 1.828125, "learning_rate": 1.723402440064841e-05, "loss": 0.4278, "step": 7682 }, { "epoch": 1.966656, "grad_norm": 2.015625, "learning_rate": 1.7229758553024485e-05, "loss": 0.4293, "step": 7683 }, { "epoch": 1.966912, "grad_norm": 1.765625, "learning_rate": 1.7225492705400566e-05, "loss": 0.4472, "step": 7684 }, { "epoch": 1.967168, "grad_norm": 1.9375, "learning_rate": 1.722122685777664e-05, "loss": 0.4211, "step": 7685 }, { "epoch": 1.9674239999999998, "grad_norm": 1.84375, "learning_rate": 1.7216961010152718e-05, "loss": 0.4243, "step": 7686 }, { "epoch": 1.96768, "grad_norm": 1.8359375, "learning_rate": 1.7212695162528795e-05, "loss": 0.4145, "step": 7687 }, { "epoch": 1.967936, "grad_norm": 1.9765625, "learning_rate": 1.7208429314904873e-05, "loss": 0.4256, "step": 7688 }, { "epoch": 1.9681920000000002, "grad_norm": 1.859375, "learning_rate": 1.7204163467280947e-05, "loss": 0.4274, "step": 7689 }, { "epoch": 1.968448, "grad_norm": 1.8125, "learning_rate": 1.7199897619657025e-05, "loss": 0.4397, "step": 7690 }, { "epoch": 1.968704, "grad_norm": 1.953125, "learning_rate": 1.7195631772033106e-05, "loss": 0.4156, "step": 7691 }, { "epoch": 1.96896, "grad_norm": 1.78125, "learning_rate": 1.719136592440918e-05, "loss": 0.4367, "step": 7692 }, { "epoch": 1.9692159999999999, "grad_norm": 1.84375, "learning_rate": 1.7187100076785258e-05, "loss": 0.4367, "step": 7693 }, { "epoch": 1.9694720000000001, "grad_norm": 1.875, "learning_rate": 1.7182834229161336e-05, "loss": 0.4367, "step": 7694 }, { "epoch": 1.969728, "grad_norm": 2.015625, "learning_rate": 1.7178568381537413e-05, "loss": 0.44, "step": 7695 }, { "epoch": 1.969984, "grad_norm": 1.8828125, "learning_rate": 1.7174302533913488e-05, "loss": 0.4155, "step": 7696 }, { "epoch": 1.97024, "grad_norm": 2.015625, "learning_rate": 1.717003668628957e-05, "loss": 0.3532, "step": 7697 }, { "epoch": 1.970496, "grad_norm": 1.9140625, "learning_rate": 1.7165770838665643e-05, "loss": 0.4679, "step": 7698 }, { "epoch": 1.970752, "grad_norm": 1.828125, "learning_rate": 1.716150499104172e-05, "loss": 0.4333, "step": 7699 }, { "epoch": 1.9710079999999999, "grad_norm": 1.9140625, "learning_rate": 1.7157239143417798e-05, "loss": 0.444, "step": 7700 }, { "epoch": 1.9712640000000001, "grad_norm": 1.7890625, "learning_rate": 1.7152973295793876e-05, "loss": 0.4597, "step": 7701 }, { "epoch": 1.97152, "grad_norm": 2.015625, "learning_rate": 1.714870744816995e-05, "loss": 0.4507, "step": 7702 }, { "epoch": 1.971776, "grad_norm": 1.8203125, "learning_rate": 1.714444160054603e-05, "loss": 0.4786, "step": 7703 }, { "epoch": 1.972032, "grad_norm": 1.8125, "learning_rate": 1.7140175752922105e-05, "loss": 0.4241, "step": 7704 }, { "epoch": 1.972288, "grad_norm": 1.8984375, "learning_rate": 1.7135909905298183e-05, "loss": 0.4422, "step": 7705 }, { "epoch": 1.972544, "grad_norm": 1.8984375, "learning_rate": 1.713164405767426e-05, "loss": 0.4032, "step": 7706 }, { "epoch": 1.9727999999999999, "grad_norm": 1.984375, "learning_rate": 1.712737821005034e-05, "loss": 0.4558, "step": 7707 }, { "epoch": 1.9730560000000001, "grad_norm": 1.859375, "learning_rate": 1.7123112362426416e-05, "loss": 0.4167, "step": 7708 }, { "epoch": 1.973312, "grad_norm": 1.7890625, "learning_rate": 1.711884651480249e-05, "loss": 0.4732, "step": 7709 }, { "epoch": 1.973568, "grad_norm": 1.7890625, "learning_rate": 1.711458066717857e-05, "loss": 0.4386, "step": 7710 }, { "epoch": 1.973824, "grad_norm": 1.875, "learning_rate": 1.7110314819554646e-05, "loss": 0.3835, "step": 7711 }, { "epoch": 1.9740799999999998, "grad_norm": 1.8515625, "learning_rate": 1.7106048971930723e-05, "loss": 0.3989, "step": 7712 }, { "epoch": 1.974336, "grad_norm": 1.796875, "learning_rate": 1.71017831243068e-05, "loss": 0.4408, "step": 7713 }, { "epoch": 1.974592, "grad_norm": 1.9765625, "learning_rate": 1.709751727668288e-05, "loss": 0.4366, "step": 7714 }, { "epoch": 1.9748480000000002, "grad_norm": 1.9921875, "learning_rate": 1.7093251429058953e-05, "loss": 0.3957, "step": 7715 }, { "epoch": 1.975104, "grad_norm": 1.9296875, "learning_rate": 1.7088985581435034e-05, "loss": 0.4647, "step": 7716 }, { "epoch": 1.97536, "grad_norm": 1.9921875, "learning_rate": 1.7084719733811108e-05, "loss": 0.4103, "step": 7717 }, { "epoch": 1.975616, "grad_norm": 1.8359375, "learning_rate": 1.7080453886187186e-05, "loss": 0.4223, "step": 7718 }, { "epoch": 1.9758719999999999, "grad_norm": 1.765625, "learning_rate": 1.7076188038563263e-05, "loss": 0.4725, "step": 7719 }, { "epoch": 1.976128, "grad_norm": 1.796875, "learning_rate": 1.707192219093934e-05, "loss": 0.4398, "step": 7720 }, { "epoch": 1.976384, "grad_norm": 1.84375, "learning_rate": 1.7067656343315415e-05, "loss": 0.4201, "step": 7721 }, { "epoch": 1.97664, "grad_norm": 1.7265625, "learning_rate": 1.7063390495691493e-05, "loss": 0.4319, "step": 7722 }, { "epoch": 1.976896, "grad_norm": 1.71875, "learning_rate": 1.7059124648067574e-05, "loss": 0.4532, "step": 7723 }, { "epoch": 1.977152, "grad_norm": 1.8046875, "learning_rate": 1.705485880044365e-05, "loss": 0.427, "step": 7724 }, { "epoch": 1.977408, "grad_norm": 1.84375, "learning_rate": 1.7050592952819726e-05, "loss": 0.4257, "step": 7725 }, { "epoch": 1.9776639999999999, "grad_norm": 1.84375, "learning_rate": 1.7046327105195804e-05, "loss": 0.4393, "step": 7726 }, { "epoch": 1.9779200000000001, "grad_norm": 1.90625, "learning_rate": 1.704206125757188e-05, "loss": 0.4317, "step": 7727 }, { "epoch": 1.978176, "grad_norm": 1.8828125, "learning_rate": 1.7037795409947956e-05, "loss": 0.4586, "step": 7728 }, { "epoch": 1.978432, "grad_norm": 1.8828125, "learning_rate": 1.7033529562324037e-05, "loss": 0.4559, "step": 7729 }, { "epoch": 1.978688, "grad_norm": 1.953125, "learning_rate": 1.702926371470011e-05, "loss": 0.4339, "step": 7730 }, { "epoch": 1.978944, "grad_norm": 1.828125, "learning_rate": 1.702499786707619e-05, "loss": 0.436, "step": 7731 }, { "epoch": 1.9792, "grad_norm": 1.84375, "learning_rate": 1.7020732019452266e-05, "loss": 0.4355, "step": 7732 }, { "epoch": 1.9794559999999999, "grad_norm": 2.046875, "learning_rate": 1.7016466171828344e-05, "loss": 0.4442, "step": 7733 }, { "epoch": 1.9797120000000001, "grad_norm": 1.9296875, "learning_rate": 1.7012200324204418e-05, "loss": 0.4011, "step": 7734 }, { "epoch": 1.979968, "grad_norm": 1.8984375, "learning_rate": 1.70079344765805e-05, "loss": 0.4319, "step": 7735 }, { "epoch": 1.980224, "grad_norm": 1.953125, "learning_rate": 1.7003668628956573e-05, "loss": 0.4438, "step": 7736 }, { "epoch": 1.98048, "grad_norm": 1.921875, "learning_rate": 1.699940278133265e-05, "loss": 0.4105, "step": 7737 }, { "epoch": 1.980736, "grad_norm": 1.953125, "learning_rate": 1.699513693370873e-05, "loss": 0.4418, "step": 7738 }, { "epoch": 1.980992, "grad_norm": 1.9375, "learning_rate": 1.6990871086084806e-05, "loss": 0.4163, "step": 7739 }, { "epoch": 1.981248, "grad_norm": 1.8359375, "learning_rate": 1.6986605238460884e-05, "loss": 0.426, "step": 7740 }, { "epoch": 1.9815040000000002, "grad_norm": 1.84375, "learning_rate": 1.698233939083696e-05, "loss": 0.4321, "step": 7741 }, { "epoch": 1.98176, "grad_norm": 1.9453125, "learning_rate": 1.697807354321304e-05, "loss": 0.4599, "step": 7742 }, { "epoch": 1.982016, "grad_norm": 1.9921875, "learning_rate": 1.6973807695589114e-05, "loss": 0.427, "step": 7743 }, { "epoch": 1.982272, "grad_norm": 1.9453125, "learning_rate": 1.696954184796519e-05, "loss": 0.4473, "step": 7744 }, { "epoch": 1.9825279999999998, "grad_norm": 1.96875, "learning_rate": 1.696527600034127e-05, "loss": 0.4615, "step": 7745 }, { "epoch": 1.982784, "grad_norm": 1.96875, "learning_rate": 1.6961010152717347e-05, "loss": 0.4404, "step": 7746 }, { "epoch": 1.98304, "grad_norm": 1.7734375, "learning_rate": 1.695674430509342e-05, "loss": 0.4438, "step": 7747 }, { "epoch": 1.983296, "grad_norm": 1.921875, "learning_rate": 1.6952478457469502e-05, "loss": 0.4044, "step": 7748 }, { "epoch": 1.983552, "grad_norm": 1.875, "learning_rate": 1.6948212609845576e-05, "loss": 0.4182, "step": 7749 }, { "epoch": 1.983808, "grad_norm": 1.96875, "learning_rate": 1.6943946762221654e-05, "loss": 0.433, "step": 7750 }, { "epoch": 1.984064, "grad_norm": 1.796875, "learning_rate": 1.693968091459773e-05, "loss": 0.3653, "step": 7751 }, { "epoch": 1.9843199999999999, "grad_norm": 1.9453125, "learning_rate": 1.693541506697381e-05, "loss": 0.4157, "step": 7752 }, { "epoch": 1.9845760000000001, "grad_norm": 1.8515625, "learning_rate": 1.6931149219349883e-05, "loss": 0.4318, "step": 7753 }, { "epoch": 1.984832, "grad_norm": 2.046875, "learning_rate": 1.6926883371725964e-05, "loss": 0.416, "step": 7754 }, { "epoch": 1.985088, "grad_norm": 1.9921875, "learning_rate": 1.6922617524102042e-05, "loss": 0.4095, "step": 7755 }, { "epoch": 1.985344, "grad_norm": 1.9375, "learning_rate": 1.6918351676478116e-05, "loss": 0.4339, "step": 7756 }, { "epoch": 1.9856, "grad_norm": 1.9375, "learning_rate": 1.6914085828854194e-05, "loss": 0.4238, "step": 7757 }, { "epoch": 1.985856, "grad_norm": 1.921875, "learning_rate": 1.690981998123027e-05, "loss": 0.4267, "step": 7758 }, { "epoch": 1.9861119999999999, "grad_norm": 1.859375, "learning_rate": 1.690555413360635e-05, "loss": 0.4753, "step": 7759 }, { "epoch": 1.9863680000000001, "grad_norm": 2.0, "learning_rate": 1.6901288285982424e-05, "loss": 0.4178, "step": 7760 }, { "epoch": 1.986624, "grad_norm": 1.984375, "learning_rate": 1.6897022438358505e-05, "loss": 0.416, "step": 7761 }, { "epoch": 1.98688, "grad_norm": 1.796875, "learning_rate": 1.689275659073458e-05, "loss": 0.4305, "step": 7762 }, { "epoch": 1.987136, "grad_norm": 1.7890625, "learning_rate": 1.6888490743110657e-05, "loss": 0.4245, "step": 7763 }, { "epoch": 1.987392, "grad_norm": 1.890625, "learning_rate": 1.6884224895486734e-05, "loss": 0.4335, "step": 7764 }, { "epoch": 1.987648, "grad_norm": 1.8984375, "learning_rate": 1.6879959047862812e-05, "loss": 0.404, "step": 7765 }, { "epoch": 1.987904, "grad_norm": 1.953125, "learning_rate": 1.6875693200238886e-05, "loss": 0.4056, "step": 7766 }, { "epoch": 1.9881600000000001, "grad_norm": 1.9375, "learning_rate": 1.6871427352614967e-05, "loss": 0.4546, "step": 7767 }, { "epoch": 1.988416, "grad_norm": 1.890625, "learning_rate": 1.686716150499104e-05, "loss": 0.4086, "step": 7768 }, { "epoch": 1.988672, "grad_norm": 1.953125, "learning_rate": 1.686289565736712e-05, "loss": 0.444, "step": 7769 }, { "epoch": 1.988928, "grad_norm": 1.78125, "learning_rate": 1.6858629809743197e-05, "loss": 0.3996, "step": 7770 }, { "epoch": 1.9891839999999998, "grad_norm": 1.953125, "learning_rate": 1.6854363962119274e-05, "loss": 0.4155, "step": 7771 }, { "epoch": 1.98944, "grad_norm": 1.859375, "learning_rate": 1.6850098114495352e-05, "loss": 0.4162, "step": 7772 }, { "epoch": 1.989696, "grad_norm": 1.84375, "learning_rate": 1.684583226687143e-05, "loss": 0.4288, "step": 7773 }, { "epoch": 1.9899520000000002, "grad_norm": 1.8125, "learning_rate": 1.6841566419247507e-05, "loss": 0.4175, "step": 7774 }, { "epoch": 1.990208, "grad_norm": 1.9609375, "learning_rate": 1.683730057162358e-05, "loss": 0.4014, "step": 7775 }, { "epoch": 1.990464, "grad_norm": 1.9375, "learning_rate": 1.683303472399966e-05, "loss": 0.4597, "step": 7776 }, { "epoch": 1.99072, "grad_norm": 1.9140625, "learning_rate": 1.6828768876375737e-05, "loss": 0.4626, "step": 7777 }, { "epoch": 1.9909759999999999, "grad_norm": 2.109375, "learning_rate": 1.6824503028751815e-05, "loss": 0.4328, "step": 7778 }, { "epoch": 1.9912320000000001, "grad_norm": 1.84375, "learning_rate": 1.682023718112789e-05, "loss": 0.4384, "step": 7779 }, { "epoch": 1.991488, "grad_norm": 1.7578125, "learning_rate": 1.681597133350397e-05, "loss": 0.4003, "step": 7780 }, { "epoch": 1.991744, "grad_norm": 2.015625, "learning_rate": 1.6811705485880044e-05, "loss": 0.4141, "step": 7781 }, { "epoch": 1.992, "grad_norm": 1.859375, "learning_rate": 1.6807439638256122e-05, "loss": 0.4165, "step": 7782 }, { "epoch": 1.992256, "grad_norm": 1.859375, "learning_rate": 1.68031737906322e-05, "loss": 0.4772, "step": 7783 }, { "epoch": 1.992512, "grad_norm": 1.8828125, "learning_rate": 1.6798907943008277e-05, "loss": 0.4146, "step": 7784 }, { "epoch": 1.9927679999999999, "grad_norm": 1.921875, "learning_rate": 1.679464209538435e-05, "loss": 0.4655, "step": 7785 }, { "epoch": 1.9930240000000001, "grad_norm": 1.7578125, "learning_rate": 1.6790376247760432e-05, "loss": 0.392, "step": 7786 }, { "epoch": 1.99328, "grad_norm": 1.828125, "learning_rate": 1.6786110400136507e-05, "loss": 0.429, "step": 7787 }, { "epoch": 1.993536, "grad_norm": 1.9453125, "learning_rate": 1.6781844552512584e-05, "loss": 0.4575, "step": 7788 }, { "epoch": 1.993792, "grad_norm": 1.953125, "learning_rate": 1.6777578704888662e-05, "loss": 0.4337, "step": 7789 }, { "epoch": 1.994048, "grad_norm": 1.9296875, "learning_rate": 1.677331285726474e-05, "loss": 0.4092, "step": 7790 }, { "epoch": 1.994304, "grad_norm": 2.03125, "learning_rate": 1.6769047009640817e-05, "loss": 0.4245, "step": 7791 }, { "epoch": 1.9945599999999999, "grad_norm": 1.90625, "learning_rate": 1.676478116201689e-05, "loss": 0.4383, "step": 7792 }, { "epoch": 1.9948160000000001, "grad_norm": 1.9453125, "learning_rate": 1.6760515314392973e-05, "loss": 0.3865, "step": 7793 }, { "epoch": 1.995072, "grad_norm": 1.953125, "learning_rate": 1.6756249466769047e-05, "loss": 0.4386, "step": 7794 }, { "epoch": 1.995328, "grad_norm": 1.9453125, "learning_rate": 1.6751983619145125e-05, "loss": 0.4489, "step": 7795 }, { "epoch": 1.995584, "grad_norm": 1.8984375, "learning_rate": 1.6747717771521202e-05, "loss": 0.456, "step": 7796 }, { "epoch": 1.9958399999999998, "grad_norm": 1.8984375, "learning_rate": 1.674345192389728e-05, "loss": 0.4213, "step": 7797 }, { "epoch": 1.996096, "grad_norm": 1.8203125, "learning_rate": 1.6739186076273354e-05, "loss": 0.4741, "step": 7798 }, { "epoch": 1.996352, "grad_norm": 1.8125, "learning_rate": 1.6734920228649435e-05, "loss": 0.4415, "step": 7799 }, { "epoch": 1.9966080000000002, "grad_norm": 1.734375, "learning_rate": 1.673065438102551e-05, "loss": 0.3978, "step": 7800 }, { "epoch": 1.996864, "grad_norm": 1.7578125, "learning_rate": 1.6726388533401587e-05, "loss": 0.4567, "step": 7801 }, { "epoch": 1.99712, "grad_norm": 1.8203125, "learning_rate": 1.6722122685777665e-05, "loss": 0.458, "step": 7802 }, { "epoch": 1.997376, "grad_norm": 2.0625, "learning_rate": 1.6717856838153742e-05, "loss": 0.4104, "step": 7803 }, { "epoch": 1.9976319999999999, "grad_norm": 1.90625, "learning_rate": 1.6713590990529817e-05, "loss": 0.4434, "step": 7804 }, { "epoch": 1.997888, "grad_norm": 2.0, "learning_rate": 1.6709325142905898e-05, "loss": 0.4142, "step": 7805 }, { "epoch": 1.998144, "grad_norm": 1.84375, "learning_rate": 1.6705059295281975e-05, "loss": 0.4141, "step": 7806 }, { "epoch": 1.9984, "grad_norm": 1.8984375, "learning_rate": 1.670079344765805e-05, "loss": 0.4304, "step": 7807 }, { "epoch": 1.998656, "grad_norm": 1.8125, "learning_rate": 1.6696527600034127e-05, "loss": 0.4466, "step": 7808 }, { "epoch": 1.998912, "grad_norm": 1.9765625, "learning_rate": 1.6692261752410205e-05, "loss": 0.4142, "step": 7809 }, { "epoch": 1.999168, "grad_norm": 1.8984375, "learning_rate": 1.6687995904786283e-05, "loss": 0.4172, "step": 7810 }, { "epoch": 1.9994239999999999, "grad_norm": 1.9296875, "learning_rate": 1.6683730057162357e-05, "loss": 0.4176, "step": 7811 }, { "epoch": 1.9996800000000001, "grad_norm": 1.75, "learning_rate": 1.6679464209538438e-05, "loss": 0.4611, "step": 7812 }, { "epoch": 1.999936, "grad_norm": 2.09375, "learning_rate": 1.6675198361914512e-05, "loss": 0.4083, "step": 7813 }, { "epoch": 2.0, "grad_norm": 3.453125, "learning_rate": 1.667093251429059e-05, "loss": 0.3867, "step": 7814 }, { "epoch": 2.000256, "grad_norm": 2.0, "learning_rate": 1.6666666666666667e-05, "loss": 0.417, "step": 7815 }, { "epoch": 2.000512, "grad_norm": 1.8828125, "learning_rate": 1.6662400819042745e-05, "loss": 0.4371, "step": 7816 }, { "epoch": 2.000768, "grad_norm": 1.921875, "learning_rate": 1.665813497141882e-05, "loss": 0.4133, "step": 7817 }, { "epoch": 2.001024, "grad_norm": 1.890625, "learning_rate": 1.66538691237949e-05, "loss": 0.4503, "step": 7818 }, { "epoch": 2.00128, "grad_norm": 1.9140625, "learning_rate": 1.6649603276170975e-05, "loss": 0.4219, "step": 7819 }, { "epoch": 2.001536, "grad_norm": 1.8984375, "learning_rate": 1.6645337428547052e-05, "loss": 0.4413, "step": 7820 }, { "epoch": 2.001792, "grad_norm": 1.90625, "learning_rate": 1.664107158092313e-05, "loss": 0.4342, "step": 7821 }, { "epoch": 2.002048, "grad_norm": 1.796875, "learning_rate": 1.6636805733299208e-05, "loss": 0.4582, "step": 7822 }, { "epoch": 2.002304, "grad_norm": 1.7578125, "learning_rate": 1.6632539885675285e-05, "loss": 0.3988, "step": 7823 }, { "epoch": 2.00256, "grad_norm": 1.8359375, "learning_rate": 1.6628274038051363e-05, "loss": 0.4375, "step": 7824 }, { "epoch": 2.002816, "grad_norm": 1.9453125, "learning_rate": 1.662400819042744e-05, "loss": 0.441, "step": 7825 }, { "epoch": 2.003072, "grad_norm": 2.03125, "learning_rate": 1.6619742342803515e-05, "loss": 0.4326, "step": 7826 }, { "epoch": 2.003328, "grad_norm": 1.7578125, "learning_rate": 1.6615476495179593e-05, "loss": 0.429, "step": 7827 }, { "epoch": 2.003584, "grad_norm": 1.8984375, "learning_rate": 1.661121064755567e-05, "loss": 0.4307, "step": 7828 }, { "epoch": 2.00384, "grad_norm": 1.671875, "learning_rate": 1.6606944799931748e-05, "loss": 0.4417, "step": 7829 }, { "epoch": 2.004096, "grad_norm": 1.7421875, "learning_rate": 1.6602678952307822e-05, "loss": 0.4018, "step": 7830 }, { "epoch": 2.004352, "grad_norm": 1.84375, "learning_rate": 1.6598413104683903e-05, "loss": 0.4328, "step": 7831 }, { "epoch": 2.004608, "grad_norm": 1.78125, "learning_rate": 1.6594147257059977e-05, "loss": 0.4163, "step": 7832 }, { "epoch": 2.004864, "grad_norm": 1.875, "learning_rate": 1.6589881409436055e-05, "loss": 0.4033, "step": 7833 }, { "epoch": 2.00512, "grad_norm": 1.8984375, "learning_rate": 1.6585615561812133e-05, "loss": 0.4139, "step": 7834 }, { "epoch": 2.005376, "grad_norm": 1.859375, "learning_rate": 1.658134971418821e-05, "loss": 0.4249, "step": 7835 }, { "epoch": 2.005632, "grad_norm": 1.8046875, "learning_rate": 1.6577083866564285e-05, "loss": 0.4338, "step": 7836 }, { "epoch": 2.005888, "grad_norm": 1.8828125, "learning_rate": 1.6572818018940366e-05, "loss": 0.453, "step": 7837 }, { "epoch": 2.006144, "grad_norm": 1.859375, "learning_rate": 1.6568552171316443e-05, "loss": 0.434, "step": 7838 }, { "epoch": 2.0064, "grad_norm": 1.8515625, "learning_rate": 1.6564286323692518e-05, "loss": 0.4228, "step": 7839 }, { "epoch": 2.006656, "grad_norm": 1.90625, "learning_rate": 1.6560020476068595e-05, "loss": 0.4065, "step": 7840 }, { "epoch": 2.006912, "grad_norm": 1.8671875, "learning_rate": 1.6555754628444673e-05, "loss": 0.4376, "step": 7841 }, { "epoch": 2.007168, "grad_norm": 1.796875, "learning_rate": 1.655148878082075e-05, "loss": 0.4497, "step": 7842 }, { "epoch": 2.007424, "grad_norm": 1.9140625, "learning_rate": 1.6547222933196825e-05, "loss": 0.3906, "step": 7843 }, { "epoch": 2.00768, "grad_norm": 1.9609375, "learning_rate": 1.6542957085572906e-05, "loss": 0.4425, "step": 7844 }, { "epoch": 2.007936, "grad_norm": 1.8984375, "learning_rate": 1.653869123794898e-05, "loss": 0.4546, "step": 7845 }, { "epoch": 2.008192, "grad_norm": 1.8203125, "learning_rate": 1.6534425390325058e-05, "loss": 0.3976, "step": 7846 }, { "epoch": 2.008448, "grad_norm": 1.8125, "learning_rate": 1.6530159542701135e-05, "loss": 0.4157, "step": 7847 }, { "epoch": 2.008704, "grad_norm": 1.9453125, "learning_rate": 1.6525893695077213e-05, "loss": 0.4244, "step": 7848 }, { "epoch": 2.00896, "grad_norm": 1.9296875, "learning_rate": 1.6521627847453287e-05, "loss": 0.4355, "step": 7849 }, { "epoch": 2.009216, "grad_norm": 1.828125, "learning_rate": 1.651736199982937e-05, "loss": 0.4892, "step": 7850 }, { "epoch": 2.009472, "grad_norm": 1.90625, "learning_rate": 1.6513096152205443e-05, "loss": 0.4291, "step": 7851 }, { "epoch": 2.009728, "grad_norm": 1.78125, "learning_rate": 1.650883030458152e-05, "loss": 0.3941, "step": 7852 }, { "epoch": 2.009984, "grad_norm": 1.9453125, "learning_rate": 1.6504564456957598e-05, "loss": 0.4273, "step": 7853 }, { "epoch": 2.01024, "grad_norm": 1.875, "learning_rate": 1.6500298609333676e-05, "loss": 0.4264, "step": 7854 }, { "epoch": 2.010496, "grad_norm": 1.875, "learning_rate": 1.6496032761709753e-05, "loss": 0.4051, "step": 7855 }, { "epoch": 2.010752, "grad_norm": 1.703125, "learning_rate": 1.649176691408583e-05, "loss": 0.4169, "step": 7856 }, { "epoch": 2.011008, "grad_norm": 1.875, "learning_rate": 1.648750106646191e-05, "loss": 0.4239, "step": 7857 }, { "epoch": 2.011264, "grad_norm": 1.875, "learning_rate": 1.6483235218837983e-05, "loss": 0.4244, "step": 7858 }, { "epoch": 2.01152, "grad_norm": 1.796875, "learning_rate": 1.647896937121406e-05, "loss": 0.4483, "step": 7859 }, { "epoch": 2.011776, "grad_norm": 1.8984375, "learning_rate": 1.6474703523590138e-05, "loss": 0.4249, "step": 7860 }, { "epoch": 2.012032, "grad_norm": 1.8984375, "learning_rate": 1.6470437675966216e-05, "loss": 0.4659, "step": 7861 }, { "epoch": 2.012288, "grad_norm": 1.9296875, "learning_rate": 1.646617182834229e-05, "loss": 0.4058, "step": 7862 }, { "epoch": 2.012544, "grad_norm": 1.7109375, "learning_rate": 1.646190598071837e-05, "loss": 0.405, "step": 7863 }, { "epoch": 2.0128, "grad_norm": 1.9140625, "learning_rate": 1.6457640133094445e-05, "loss": 0.4192, "step": 7864 }, { "epoch": 2.013056, "grad_norm": 1.8515625, "learning_rate": 1.6453374285470523e-05, "loss": 0.3949, "step": 7865 }, { "epoch": 2.013312, "grad_norm": 1.828125, "learning_rate": 1.64491084378466e-05, "loss": 0.4416, "step": 7866 }, { "epoch": 2.013568, "grad_norm": 1.84375, "learning_rate": 1.644484259022268e-05, "loss": 0.449, "step": 7867 }, { "epoch": 2.013824, "grad_norm": 1.8515625, "learning_rate": 1.6440576742598753e-05, "loss": 0.3917, "step": 7868 }, { "epoch": 2.01408, "grad_norm": 1.8828125, "learning_rate": 1.6436310894974834e-05, "loss": 0.4347, "step": 7869 }, { "epoch": 2.014336, "grad_norm": 1.7265625, "learning_rate": 1.643204504735091e-05, "loss": 0.4169, "step": 7870 }, { "epoch": 2.014592, "grad_norm": 1.828125, "learning_rate": 1.6427779199726986e-05, "loss": 0.3764, "step": 7871 }, { "epoch": 2.014848, "grad_norm": 1.90625, "learning_rate": 1.6423513352103063e-05, "loss": 0.4302, "step": 7872 }, { "epoch": 2.015104, "grad_norm": 1.9140625, "learning_rate": 1.641924750447914e-05, "loss": 0.3986, "step": 7873 }, { "epoch": 2.01536, "grad_norm": 1.9765625, "learning_rate": 1.641498165685522e-05, "loss": 0.4149, "step": 7874 }, { "epoch": 2.015616, "grad_norm": 2.0, "learning_rate": 1.6410715809231296e-05, "loss": 0.3883, "step": 7875 }, { "epoch": 2.015872, "grad_norm": 1.9140625, "learning_rate": 1.6406449961607374e-05, "loss": 0.4245, "step": 7876 }, { "epoch": 2.016128, "grad_norm": 1.9375, "learning_rate": 1.6402184113983448e-05, "loss": 0.3759, "step": 7877 }, { "epoch": 2.016384, "grad_norm": 1.875, "learning_rate": 1.6397918266359526e-05, "loss": 0.4476, "step": 7878 }, { "epoch": 2.01664, "grad_norm": 1.8828125, "learning_rate": 1.6393652418735603e-05, "loss": 0.3935, "step": 7879 }, { "epoch": 2.016896, "grad_norm": 1.828125, "learning_rate": 1.638938657111168e-05, "loss": 0.4066, "step": 7880 }, { "epoch": 2.017152, "grad_norm": 1.8515625, "learning_rate": 1.6385120723487755e-05, "loss": 0.447, "step": 7881 }, { "epoch": 2.017408, "grad_norm": 1.7890625, "learning_rate": 1.6380854875863836e-05, "loss": 0.4249, "step": 7882 }, { "epoch": 2.017664, "grad_norm": 1.90625, "learning_rate": 1.637658902823991e-05, "loss": 0.4325, "step": 7883 }, { "epoch": 2.01792, "grad_norm": 1.921875, "learning_rate": 1.637232318061599e-05, "loss": 0.3959, "step": 7884 }, { "epoch": 2.018176, "grad_norm": 1.8359375, "learning_rate": 1.6368057332992066e-05, "loss": 0.42, "step": 7885 }, { "epoch": 2.018432, "grad_norm": 1.7890625, "learning_rate": 1.6363791485368144e-05, "loss": 0.4031, "step": 7886 }, { "epoch": 2.018688, "grad_norm": 1.9140625, "learning_rate": 1.635952563774422e-05, "loss": 0.4214, "step": 7887 }, { "epoch": 2.018944, "grad_norm": 1.9453125, "learning_rate": 1.63552597901203e-05, "loss": 0.4192, "step": 7888 }, { "epoch": 2.0192, "grad_norm": 1.96875, "learning_rate": 1.6350993942496377e-05, "loss": 0.4407, "step": 7889 }, { "epoch": 2.019456, "grad_norm": 1.9921875, "learning_rate": 1.634672809487245e-05, "loss": 0.4336, "step": 7890 }, { "epoch": 2.019712, "grad_norm": 1.90625, "learning_rate": 1.634246224724853e-05, "loss": 0.4316, "step": 7891 }, { "epoch": 2.019968, "grad_norm": 1.84375, "learning_rate": 1.6338196399624606e-05, "loss": 0.3881, "step": 7892 }, { "epoch": 2.020224, "grad_norm": 1.953125, "learning_rate": 1.6333930552000684e-05, "loss": 0.4449, "step": 7893 }, { "epoch": 2.02048, "grad_norm": 1.8203125, "learning_rate": 1.6329664704376758e-05, "loss": 0.3943, "step": 7894 }, { "epoch": 2.020736, "grad_norm": 2.109375, "learning_rate": 1.632539885675284e-05, "loss": 0.4069, "step": 7895 }, { "epoch": 2.020992, "grad_norm": 1.8046875, "learning_rate": 1.6321133009128913e-05, "loss": 0.4552, "step": 7896 }, { "epoch": 2.021248, "grad_norm": 1.765625, "learning_rate": 1.631686716150499e-05, "loss": 0.4294, "step": 7897 }, { "epoch": 2.021504, "grad_norm": 1.875, "learning_rate": 1.631260131388107e-05, "loss": 0.4235, "step": 7898 }, { "epoch": 2.02176, "grad_norm": 1.8125, "learning_rate": 1.6308335466257146e-05, "loss": 0.4495, "step": 7899 }, { "epoch": 2.022016, "grad_norm": 1.84375, "learning_rate": 1.630406961863322e-05, "loss": 0.4389, "step": 7900 }, { "epoch": 2.022272, "grad_norm": 1.9296875, "learning_rate": 1.6299803771009302e-05, "loss": 0.4311, "step": 7901 }, { "epoch": 2.022528, "grad_norm": 1.921875, "learning_rate": 1.6295537923385376e-05, "loss": 0.4431, "step": 7902 }, { "epoch": 2.022784, "grad_norm": 1.703125, "learning_rate": 1.6291272075761454e-05, "loss": 0.4584, "step": 7903 }, { "epoch": 2.02304, "grad_norm": 2.03125, "learning_rate": 1.628700622813753e-05, "loss": 0.4228, "step": 7904 }, { "epoch": 2.023296, "grad_norm": 1.8984375, "learning_rate": 1.628274038051361e-05, "loss": 0.448, "step": 7905 }, { "epoch": 2.023552, "grad_norm": 1.84375, "learning_rate": 1.6278474532889687e-05, "loss": 0.3836, "step": 7906 }, { "epoch": 2.023808, "grad_norm": 1.71875, "learning_rate": 1.6274208685265764e-05, "loss": 0.441, "step": 7907 }, { "epoch": 2.024064, "grad_norm": 1.796875, "learning_rate": 1.6269942837641842e-05, "loss": 0.4289, "step": 7908 }, { "epoch": 2.02432, "grad_norm": 1.78125, "learning_rate": 1.6265676990017916e-05, "loss": 0.4264, "step": 7909 }, { "epoch": 2.024576, "grad_norm": 1.8828125, "learning_rate": 1.6261411142393994e-05, "loss": 0.4315, "step": 7910 }, { "epoch": 2.024832, "grad_norm": 1.8515625, "learning_rate": 1.625714529477007e-05, "loss": 0.4554, "step": 7911 }, { "epoch": 2.025088, "grad_norm": 1.96875, "learning_rate": 1.625287944714615e-05, "loss": 0.4398, "step": 7912 }, { "epoch": 2.025344, "grad_norm": 1.9140625, "learning_rate": 1.6248613599522223e-05, "loss": 0.441, "step": 7913 }, { "epoch": 2.0256, "grad_norm": 1.859375, "learning_rate": 1.6244347751898304e-05, "loss": 0.4053, "step": 7914 }, { "epoch": 2.025856, "grad_norm": 1.8359375, "learning_rate": 1.624008190427438e-05, "loss": 0.4228, "step": 7915 }, { "epoch": 2.026112, "grad_norm": 1.859375, "learning_rate": 1.6235816056650456e-05, "loss": 0.421, "step": 7916 }, { "epoch": 2.026368, "grad_norm": 1.8359375, "learning_rate": 1.6231550209026534e-05, "loss": 0.4053, "step": 7917 }, { "epoch": 2.026624, "grad_norm": 1.9453125, "learning_rate": 1.622728436140261e-05, "loss": 0.4411, "step": 7918 }, { "epoch": 2.02688, "grad_norm": 2.046875, "learning_rate": 1.622301851377869e-05, "loss": 0.4139, "step": 7919 }, { "epoch": 2.027136, "grad_norm": 1.8359375, "learning_rate": 1.6218752666154767e-05, "loss": 0.4414, "step": 7920 }, { "epoch": 2.027392, "grad_norm": 1.8828125, "learning_rate": 1.6214486818530845e-05, "loss": 0.4126, "step": 7921 }, { "epoch": 2.027648, "grad_norm": 1.9296875, "learning_rate": 1.621022097090692e-05, "loss": 0.4348, "step": 7922 }, { "epoch": 2.027904, "grad_norm": 1.8203125, "learning_rate": 1.6205955123282997e-05, "loss": 0.4528, "step": 7923 }, { "epoch": 2.02816, "grad_norm": 2.0625, "learning_rate": 1.6201689275659074e-05, "loss": 0.4118, "step": 7924 }, { "epoch": 2.028416, "grad_norm": 1.796875, "learning_rate": 1.6197423428035152e-05, "loss": 0.4447, "step": 7925 }, { "epoch": 2.028672, "grad_norm": 1.8125, "learning_rate": 1.619315758041123e-05, "loss": 0.429, "step": 7926 }, { "epoch": 2.028928, "grad_norm": 1.875, "learning_rate": 1.6188891732787307e-05, "loss": 0.4192, "step": 7927 }, { "epoch": 2.029184, "grad_norm": 1.796875, "learning_rate": 1.618462588516338e-05, "loss": 0.3683, "step": 7928 }, { "epoch": 2.02944, "grad_norm": 2.015625, "learning_rate": 1.618036003753946e-05, "loss": 0.4387, "step": 7929 }, { "epoch": 2.029696, "grad_norm": 2.015625, "learning_rate": 1.6176094189915537e-05, "loss": 0.4507, "step": 7930 }, { "epoch": 2.029952, "grad_norm": 1.7265625, "learning_rate": 1.6171828342291614e-05, "loss": 0.414, "step": 7931 }, { "epoch": 2.030208, "grad_norm": 1.984375, "learning_rate": 1.616756249466769e-05, "loss": 0.4298, "step": 7932 }, { "epoch": 2.030464, "grad_norm": 1.8515625, "learning_rate": 1.616329664704377e-05, "loss": 0.4298, "step": 7933 }, { "epoch": 2.03072, "grad_norm": 1.765625, "learning_rate": 1.6159030799419844e-05, "loss": 0.394, "step": 7934 }, { "epoch": 2.030976, "grad_norm": 1.921875, "learning_rate": 1.615476495179592e-05, "loss": 0.4452, "step": 7935 }, { "epoch": 2.031232, "grad_norm": 1.84375, "learning_rate": 1.6150499104172003e-05, "loss": 0.4262, "step": 7936 }, { "epoch": 2.031488, "grad_norm": 1.8984375, "learning_rate": 1.6146233256548077e-05, "loss": 0.4355, "step": 7937 }, { "epoch": 2.031744, "grad_norm": 1.8515625, "learning_rate": 1.6141967408924155e-05, "loss": 0.4318, "step": 7938 }, { "epoch": 2.032, "grad_norm": 1.7890625, "learning_rate": 1.6137701561300232e-05, "loss": 0.4473, "step": 7939 }, { "epoch": 2.032256, "grad_norm": 1.890625, "learning_rate": 1.613343571367631e-05, "loss": 0.4564, "step": 7940 }, { "epoch": 2.032512, "grad_norm": 1.859375, "learning_rate": 1.6129169866052384e-05, "loss": 0.4279, "step": 7941 }, { "epoch": 2.032768, "grad_norm": 1.734375, "learning_rate": 1.6124904018428462e-05, "loss": 0.4342, "step": 7942 }, { "epoch": 2.033024, "grad_norm": 1.875, "learning_rate": 1.612063817080454e-05, "loss": 0.4645, "step": 7943 }, { "epoch": 2.03328, "grad_norm": 1.828125, "learning_rate": 1.6116372323180617e-05, "loss": 0.3975, "step": 7944 }, { "epoch": 2.033536, "grad_norm": 1.921875, "learning_rate": 1.611210647555669e-05, "loss": 0.4291, "step": 7945 }, { "epoch": 2.033792, "grad_norm": 2.078125, "learning_rate": 1.6107840627932772e-05, "loss": 0.4352, "step": 7946 }, { "epoch": 2.034048, "grad_norm": 1.7734375, "learning_rate": 1.6103574780308847e-05, "loss": 0.4553, "step": 7947 }, { "epoch": 2.034304, "grad_norm": 1.65625, "learning_rate": 1.6099308932684924e-05, "loss": 0.4412, "step": 7948 }, { "epoch": 2.03456, "grad_norm": 1.875, "learning_rate": 1.6095043085061002e-05, "loss": 0.3823, "step": 7949 }, { "epoch": 2.034816, "grad_norm": 1.8828125, "learning_rate": 1.609077723743708e-05, "loss": 0.4822, "step": 7950 }, { "epoch": 2.035072, "grad_norm": 2.078125, "learning_rate": 1.6086511389813154e-05, "loss": 0.4165, "step": 7951 }, { "epoch": 2.035328, "grad_norm": 1.8046875, "learning_rate": 1.6082245542189235e-05, "loss": 0.4156, "step": 7952 }, { "epoch": 2.035584, "grad_norm": 1.9140625, "learning_rate": 1.6077979694565313e-05, "loss": 0.4529, "step": 7953 }, { "epoch": 2.03584, "grad_norm": 1.796875, "learning_rate": 1.6073713846941387e-05, "loss": 0.4038, "step": 7954 }, { "epoch": 2.036096, "grad_norm": 1.734375, "learning_rate": 1.6069447999317468e-05, "loss": 0.4641, "step": 7955 }, { "epoch": 2.036352, "grad_norm": 1.8515625, "learning_rate": 1.6065182151693542e-05, "loss": 0.3877, "step": 7956 }, { "epoch": 2.036608, "grad_norm": 1.7265625, "learning_rate": 1.606091630406962e-05, "loss": 0.4518, "step": 7957 }, { "epoch": 2.036864, "grad_norm": 1.765625, "learning_rate": 1.6056650456445698e-05, "loss": 0.4044, "step": 7958 }, { "epoch": 2.03712, "grad_norm": 2.03125, "learning_rate": 1.6052384608821775e-05, "loss": 0.417, "step": 7959 }, { "epoch": 2.037376, "grad_norm": 1.953125, "learning_rate": 1.604811876119785e-05, "loss": 0.4205, "step": 7960 }, { "epoch": 2.037632, "grad_norm": 1.8828125, "learning_rate": 1.6043852913573927e-05, "loss": 0.4598, "step": 7961 }, { "epoch": 2.037888, "grad_norm": 2.109375, "learning_rate": 1.6039587065950005e-05, "loss": 0.4442, "step": 7962 }, { "epoch": 2.038144, "grad_norm": 1.8984375, "learning_rate": 1.6035321218326082e-05, "loss": 0.4433, "step": 7963 }, { "epoch": 2.0384, "grad_norm": 1.828125, "learning_rate": 1.6031055370702157e-05, "loss": 0.4292, "step": 7964 }, { "epoch": 2.038656, "grad_norm": 1.9765625, "learning_rate": 1.6026789523078238e-05, "loss": 0.4282, "step": 7965 }, { "epoch": 2.038912, "grad_norm": 1.7578125, "learning_rate": 1.6022523675454312e-05, "loss": 0.4545, "step": 7966 }, { "epoch": 2.039168, "grad_norm": 1.8984375, "learning_rate": 1.601825782783039e-05, "loss": 0.4374, "step": 7967 }, { "epoch": 2.039424, "grad_norm": 1.8984375, "learning_rate": 1.6013991980206467e-05, "loss": 0.4362, "step": 7968 }, { "epoch": 2.03968, "grad_norm": 1.7734375, "learning_rate": 1.6009726132582545e-05, "loss": 0.4393, "step": 7969 }, { "epoch": 2.039936, "grad_norm": 1.921875, "learning_rate": 1.6005460284958623e-05, "loss": 0.4515, "step": 7970 }, { "epoch": 2.040192, "grad_norm": 1.7734375, "learning_rate": 1.60011944373347e-05, "loss": 0.4424, "step": 7971 }, { "epoch": 2.040448, "grad_norm": 1.7421875, "learning_rate": 1.5996928589710778e-05, "loss": 0.4352, "step": 7972 }, { "epoch": 2.040704, "grad_norm": 1.796875, "learning_rate": 1.5992662742086852e-05, "loss": 0.4259, "step": 7973 }, { "epoch": 2.04096, "grad_norm": 1.84375, "learning_rate": 1.598839689446293e-05, "loss": 0.4454, "step": 7974 }, { "epoch": 2.041216, "grad_norm": 1.9375, "learning_rate": 1.5984131046839007e-05, "loss": 0.4045, "step": 7975 }, { "epoch": 2.041472, "grad_norm": 1.75, "learning_rate": 1.5979865199215085e-05, "loss": 0.3934, "step": 7976 }, { "epoch": 2.041728, "grad_norm": 2.015625, "learning_rate": 1.5975599351591163e-05, "loss": 0.4273, "step": 7977 }, { "epoch": 2.041984, "grad_norm": 1.9609375, "learning_rate": 1.597133350396724e-05, "loss": 0.431, "step": 7978 }, { "epoch": 2.04224, "grad_norm": 1.796875, "learning_rate": 1.5967067656343315e-05, "loss": 0.396, "step": 7979 }, { "epoch": 2.042496, "grad_norm": 1.8984375, "learning_rate": 1.5962801808719392e-05, "loss": 0.4089, "step": 7980 }, { "epoch": 2.042752, "grad_norm": 1.8671875, "learning_rate": 1.595853596109547e-05, "loss": 0.4073, "step": 7981 }, { "epoch": 2.043008, "grad_norm": 1.8515625, "learning_rate": 1.5954270113471548e-05, "loss": 0.3968, "step": 7982 }, { "epoch": 2.043264, "grad_norm": 1.8359375, "learning_rate": 1.5950004265847622e-05, "loss": 0.4021, "step": 7983 }, { "epoch": 2.04352, "grad_norm": 1.7109375, "learning_rate": 1.5945738418223703e-05, "loss": 0.4183, "step": 7984 }, { "epoch": 2.043776, "grad_norm": 1.8046875, "learning_rate": 1.594147257059978e-05, "loss": 0.4288, "step": 7985 }, { "epoch": 2.044032, "grad_norm": 1.828125, "learning_rate": 1.5937206722975855e-05, "loss": 0.4446, "step": 7986 }, { "epoch": 2.044288, "grad_norm": 1.7421875, "learning_rate": 1.5932940875351936e-05, "loss": 0.4117, "step": 7987 }, { "epoch": 2.044544, "grad_norm": 1.890625, "learning_rate": 1.592867502772801e-05, "loss": 0.4044, "step": 7988 }, { "epoch": 2.0448, "grad_norm": 2.0, "learning_rate": 1.5924409180104088e-05, "loss": 0.417, "step": 7989 }, { "epoch": 2.045056, "grad_norm": 1.9453125, "learning_rate": 1.5920143332480166e-05, "loss": 0.4002, "step": 7990 }, { "epoch": 2.045312, "grad_norm": 1.9921875, "learning_rate": 1.5915877484856243e-05, "loss": 0.4665, "step": 7991 }, { "epoch": 2.045568, "grad_norm": 1.671875, "learning_rate": 1.5911611637232317e-05, "loss": 0.4319, "step": 7992 }, { "epoch": 2.045824, "grad_norm": 1.8125, "learning_rate": 1.5907345789608395e-05, "loss": 0.4444, "step": 7993 }, { "epoch": 2.04608, "grad_norm": 1.8125, "learning_rate": 1.5903079941984473e-05, "loss": 0.4268, "step": 7994 }, { "epoch": 2.046336, "grad_norm": 1.8515625, "learning_rate": 1.589881409436055e-05, "loss": 0.4401, "step": 7995 }, { "epoch": 2.046592, "grad_norm": 1.8125, "learning_rate": 1.5894548246736625e-05, "loss": 0.4444, "step": 7996 }, { "epoch": 2.046848, "grad_norm": 1.921875, "learning_rate": 1.5890282399112706e-05, "loss": 0.3596, "step": 7997 }, { "epoch": 2.047104, "grad_norm": 1.703125, "learning_rate": 1.588601655148878e-05, "loss": 0.4169, "step": 7998 }, { "epoch": 2.04736, "grad_norm": 1.78125, "learning_rate": 1.5881750703864858e-05, "loss": 0.3565, "step": 7999 }, { "epoch": 2.047616, "grad_norm": 1.9140625, "learning_rate": 1.5877484856240935e-05, "loss": 0.4063, "step": 8000 }, { "epoch": 2.047872, "grad_norm": 1.828125, "learning_rate": 1.5873219008617013e-05, "loss": 0.3998, "step": 8001 }, { "epoch": 2.048128, "grad_norm": 1.828125, "learning_rate": 1.586895316099309e-05, "loss": 0.4084, "step": 8002 }, { "epoch": 2.048384, "grad_norm": 1.84375, "learning_rate": 1.5864687313369168e-05, "loss": 0.4358, "step": 8003 }, { "epoch": 2.04864, "grad_norm": 1.859375, "learning_rate": 1.5860421465745246e-05, "loss": 0.421, "step": 8004 }, { "epoch": 2.048896, "grad_norm": 1.75, "learning_rate": 1.585615561812132e-05, "loss": 0.4128, "step": 8005 }, { "epoch": 2.049152, "grad_norm": 1.828125, "learning_rate": 1.58518897704974e-05, "loss": 0.4148, "step": 8006 }, { "epoch": 2.049408, "grad_norm": 1.9140625, "learning_rate": 1.5847623922873475e-05, "loss": 0.4346, "step": 8007 }, { "epoch": 2.049664, "grad_norm": 1.875, "learning_rate": 1.5843358075249553e-05, "loss": 0.391, "step": 8008 }, { "epoch": 2.04992, "grad_norm": 1.8671875, "learning_rate": 1.583909222762563e-05, "loss": 0.4218, "step": 8009 }, { "epoch": 2.050176, "grad_norm": 1.9296875, "learning_rate": 1.583482638000171e-05, "loss": 0.4455, "step": 8010 }, { "epoch": 2.050432, "grad_norm": 1.796875, "learning_rate": 1.5830560532377783e-05, "loss": 0.3695, "step": 8011 }, { "epoch": 2.050688, "grad_norm": 1.7421875, "learning_rate": 1.582629468475386e-05, "loss": 0.4504, "step": 8012 }, { "epoch": 2.050944, "grad_norm": 1.8515625, "learning_rate": 1.5822028837129938e-05, "loss": 0.4259, "step": 8013 }, { "epoch": 2.0512, "grad_norm": 1.921875, "learning_rate": 1.5817762989506016e-05, "loss": 0.4479, "step": 8014 }, { "epoch": 2.051456, "grad_norm": 2.078125, "learning_rate": 1.581349714188209e-05, "loss": 0.4505, "step": 8015 }, { "epoch": 2.051712, "grad_norm": 1.75, "learning_rate": 1.580923129425817e-05, "loss": 0.4362, "step": 8016 }, { "epoch": 2.051968, "grad_norm": 1.8359375, "learning_rate": 1.5804965446634245e-05, "loss": 0.4323, "step": 8017 }, { "epoch": 2.052224, "grad_norm": 1.796875, "learning_rate": 1.5800699599010323e-05, "loss": 0.4161, "step": 8018 }, { "epoch": 2.05248, "grad_norm": 1.7578125, "learning_rate": 1.5796433751386404e-05, "loss": 0.4339, "step": 8019 }, { "epoch": 2.052736, "grad_norm": 1.890625, "learning_rate": 1.5792167903762478e-05, "loss": 0.4002, "step": 8020 }, { "epoch": 2.052992, "grad_norm": 1.8671875, "learning_rate": 1.5787902056138556e-05, "loss": 0.4408, "step": 8021 }, { "epoch": 2.053248, "grad_norm": 1.8359375, "learning_rate": 1.5783636208514634e-05, "loss": 0.4357, "step": 8022 }, { "epoch": 2.053504, "grad_norm": 1.796875, "learning_rate": 1.577937036089071e-05, "loss": 0.4439, "step": 8023 }, { "epoch": 2.05376, "grad_norm": 1.8359375, "learning_rate": 1.5775104513266785e-05, "loss": 0.4098, "step": 8024 }, { "epoch": 2.054016, "grad_norm": 1.7890625, "learning_rate": 1.5770838665642863e-05, "loss": 0.4383, "step": 8025 }, { "epoch": 2.054272, "grad_norm": 1.9140625, "learning_rate": 1.576657281801894e-05, "loss": 0.4074, "step": 8026 }, { "epoch": 2.054528, "grad_norm": 1.8828125, "learning_rate": 1.576230697039502e-05, "loss": 0.4482, "step": 8027 }, { "epoch": 2.054784, "grad_norm": 1.890625, "learning_rate": 1.5758041122771096e-05, "loss": 0.4271, "step": 8028 }, { "epoch": 2.05504, "grad_norm": 1.875, "learning_rate": 1.5753775275147174e-05, "loss": 0.4304, "step": 8029 }, { "epoch": 2.055296, "grad_norm": 1.6796875, "learning_rate": 1.5749509427523248e-05, "loss": 0.4437, "step": 8030 }, { "epoch": 2.055552, "grad_norm": 1.828125, "learning_rate": 1.5745243579899326e-05, "loss": 0.4195, "step": 8031 }, { "epoch": 2.055808, "grad_norm": 1.84375, "learning_rate": 1.5740977732275403e-05, "loss": 0.4432, "step": 8032 }, { "epoch": 2.056064, "grad_norm": 1.78125, "learning_rate": 1.573671188465148e-05, "loss": 0.4426, "step": 8033 }, { "epoch": 2.05632, "grad_norm": 1.84375, "learning_rate": 1.573244603702756e-05, "loss": 0.4204, "step": 8034 }, { "epoch": 2.056576, "grad_norm": 1.671875, "learning_rate": 1.5728180189403636e-05, "loss": 0.418, "step": 8035 }, { "epoch": 2.056832, "grad_norm": 1.84375, "learning_rate": 1.5723914341779714e-05, "loss": 0.3875, "step": 8036 }, { "epoch": 2.057088, "grad_norm": 1.875, "learning_rate": 1.5719648494155788e-05, "loss": 0.4012, "step": 8037 }, { "epoch": 2.057344, "grad_norm": 1.8125, "learning_rate": 1.571538264653187e-05, "loss": 0.4369, "step": 8038 }, { "epoch": 2.0576, "grad_norm": 1.9765625, "learning_rate": 1.5711116798907943e-05, "loss": 0.4275, "step": 8039 }, { "epoch": 2.057856, "grad_norm": 1.75, "learning_rate": 1.570685095128402e-05, "loss": 0.4162, "step": 8040 }, { "epoch": 2.058112, "grad_norm": 2.015625, "learning_rate": 1.57025851036601e-05, "loss": 0.4018, "step": 8041 }, { "epoch": 2.058368, "grad_norm": 1.8515625, "learning_rate": 1.5698319256036176e-05, "loss": 0.4194, "step": 8042 }, { "epoch": 2.058624, "grad_norm": 1.8203125, "learning_rate": 1.569405340841225e-05, "loss": 0.4473, "step": 8043 }, { "epoch": 2.05888, "grad_norm": 1.7421875, "learning_rate": 1.568978756078833e-05, "loss": 0.4414, "step": 8044 }, { "epoch": 2.059136, "grad_norm": 1.9296875, "learning_rate": 1.5685521713164406e-05, "loss": 0.4082, "step": 8045 }, { "epoch": 2.059392, "grad_norm": 1.8828125, "learning_rate": 1.5681255865540484e-05, "loss": 0.4352, "step": 8046 }, { "epoch": 2.059648, "grad_norm": 1.7109375, "learning_rate": 1.567699001791656e-05, "loss": 0.4424, "step": 8047 }, { "epoch": 2.059904, "grad_norm": 1.796875, "learning_rate": 1.567272417029264e-05, "loss": 0.4137, "step": 8048 }, { "epoch": 2.06016, "grad_norm": 1.9453125, "learning_rate": 1.5668458322668713e-05, "loss": 0.4268, "step": 8049 }, { "epoch": 2.060416, "grad_norm": 1.875, "learning_rate": 1.566419247504479e-05, "loss": 0.4502, "step": 8050 }, { "epoch": 2.060672, "grad_norm": 1.7890625, "learning_rate": 1.5659926627420872e-05, "loss": 0.4545, "step": 8051 }, { "epoch": 2.060928, "grad_norm": 1.8828125, "learning_rate": 1.5655660779796946e-05, "loss": 0.4407, "step": 8052 }, { "epoch": 2.061184, "grad_norm": 1.8515625, "learning_rate": 1.5651394932173024e-05, "loss": 0.4578, "step": 8053 }, { "epoch": 2.06144, "grad_norm": 2.03125, "learning_rate": 1.56471290845491e-05, "loss": 0.3829, "step": 8054 }, { "epoch": 2.061696, "grad_norm": 1.7578125, "learning_rate": 1.564286323692518e-05, "loss": 0.4235, "step": 8055 }, { "epoch": 2.061952, "grad_norm": 1.7734375, "learning_rate": 1.5638597389301253e-05, "loss": 0.4096, "step": 8056 }, { "epoch": 2.062208, "grad_norm": 1.859375, "learning_rate": 1.5634331541677334e-05, "loss": 0.4174, "step": 8057 }, { "epoch": 2.062464, "grad_norm": 1.8828125, "learning_rate": 1.563006569405341e-05, "loss": 0.4369, "step": 8058 }, { "epoch": 2.06272, "grad_norm": 2.0625, "learning_rate": 1.5625799846429486e-05, "loss": 0.4542, "step": 8059 }, { "epoch": 2.062976, "grad_norm": 1.875, "learning_rate": 1.5621533998805564e-05, "loss": 0.4301, "step": 8060 }, { "epoch": 2.063232, "grad_norm": 1.84375, "learning_rate": 1.5617268151181642e-05, "loss": 0.4279, "step": 8061 }, { "epoch": 2.063488, "grad_norm": 1.90625, "learning_rate": 1.5613002303557716e-05, "loss": 0.426, "step": 8062 }, { "epoch": 2.063744, "grad_norm": 1.8046875, "learning_rate": 1.5608736455933794e-05, "loss": 0.446, "step": 8063 }, { "epoch": 2.064, "grad_norm": 2.03125, "learning_rate": 1.560447060830987e-05, "loss": 0.4439, "step": 8064 }, { "epoch": 2.064256, "grad_norm": 1.84375, "learning_rate": 1.560020476068595e-05, "loss": 0.4097, "step": 8065 }, { "epoch": 2.064512, "grad_norm": 1.90625, "learning_rate": 1.5595938913062023e-05, "loss": 0.4348, "step": 8066 }, { "epoch": 2.064768, "grad_norm": 2.09375, "learning_rate": 1.5591673065438104e-05, "loss": 0.4464, "step": 8067 }, { "epoch": 2.065024, "grad_norm": 1.84375, "learning_rate": 1.5587407217814182e-05, "loss": 0.3959, "step": 8068 }, { "epoch": 2.06528, "grad_norm": 1.828125, "learning_rate": 1.5583141370190256e-05, "loss": 0.4502, "step": 8069 }, { "epoch": 2.065536, "grad_norm": 1.7578125, "learning_rate": 1.5578875522566337e-05, "loss": 0.4794, "step": 8070 }, { "epoch": 2.065792, "grad_norm": 1.875, "learning_rate": 1.557460967494241e-05, "loss": 0.4107, "step": 8071 }, { "epoch": 2.066048, "grad_norm": 1.8984375, "learning_rate": 1.557034382731849e-05, "loss": 0.4495, "step": 8072 }, { "epoch": 2.066304, "grad_norm": 1.8828125, "learning_rate": 1.5566077979694567e-05, "loss": 0.44, "step": 8073 }, { "epoch": 2.06656, "grad_norm": 1.96875, "learning_rate": 1.5561812132070644e-05, "loss": 0.4286, "step": 8074 }, { "epoch": 2.066816, "grad_norm": 1.8125, "learning_rate": 1.555754628444672e-05, "loss": 0.4574, "step": 8075 }, { "epoch": 2.067072, "grad_norm": 1.9375, "learning_rate": 1.5553280436822796e-05, "loss": 0.3862, "step": 8076 }, { "epoch": 2.067328, "grad_norm": 1.78125, "learning_rate": 1.5549014589198874e-05, "loss": 0.4344, "step": 8077 }, { "epoch": 2.067584, "grad_norm": 1.953125, "learning_rate": 1.554474874157495e-05, "loss": 0.4343, "step": 8078 }, { "epoch": 2.06784, "grad_norm": 1.9296875, "learning_rate": 1.554048289395103e-05, "loss": 0.4014, "step": 8079 }, { "epoch": 2.068096, "grad_norm": 1.84375, "learning_rate": 1.5536217046327107e-05, "loss": 0.4233, "step": 8080 }, { "epoch": 2.068352, "grad_norm": 1.828125, "learning_rate": 1.553195119870318e-05, "loss": 0.4284, "step": 8081 }, { "epoch": 2.0686080000000002, "grad_norm": 1.9296875, "learning_rate": 1.552768535107926e-05, "loss": 0.4367, "step": 8082 }, { "epoch": 2.068864, "grad_norm": 1.8359375, "learning_rate": 1.552341950345534e-05, "loss": 0.4164, "step": 8083 }, { "epoch": 2.06912, "grad_norm": 1.9453125, "learning_rate": 1.5519153655831414e-05, "loss": 0.4517, "step": 8084 }, { "epoch": 2.069376, "grad_norm": 1.84375, "learning_rate": 1.5514887808207492e-05, "loss": 0.4215, "step": 8085 }, { "epoch": 2.069632, "grad_norm": 1.8828125, "learning_rate": 1.551062196058357e-05, "loss": 0.4358, "step": 8086 }, { "epoch": 2.069888, "grad_norm": 2.03125, "learning_rate": 1.5506356112959647e-05, "loss": 0.4317, "step": 8087 }, { "epoch": 2.070144, "grad_norm": 1.9375, "learning_rate": 1.550209026533572e-05, "loss": 0.4083, "step": 8088 }, { "epoch": 2.0704, "grad_norm": 1.75, "learning_rate": 1.5497824417711802e-05, "loss": 0.4416, "step": 8089 }, { "epoch": 2.070656, "grad_norm": 1.65625, "learning_rate": 1.5493558570087877e-05, "loss": 0.4749, "step": 8090 }, { "epoch": 2.070912, "grad_norm": 1.875, "learning_rate": 1.5489292722463954e-05, "loss": 0.3885, "step": 8091 }, { "epoch": 2.071168, "grad_norm": 1.890625, "learning_rate": 1.5485026874840032e-05, "loss": 0.4357, "step": 8092 }, { "epoch": 2.071424, "grad_norm": 1.875, "learning_rate": 1.548076102721611e-05, "loss": 0.4502, "step": 8093 }, { "epoch": 2.07168, "grad_norm": 1.75, "learning_rate": 1.5476495179592184e-05, "loss": 0.4188, "step": 8094 }, { "epoch": 2.071936, "grad_norm": 1.9140625, "learning_rate": 1.547222933196826e-05, "loss": 0.4457, "step": 8095 }, { "epoch": 2.072192, "grad_norm": 1.875, "learning_rate": 1.546796348434434e-05, "loss": 0.4613, "step": 8096 }, { "epoch": 2.072448, "grad_norm": 1.828125, "learning_rate": 1.5463697636720417e-05, "loss": 0.4098, "step": 8097 }, { "epoch": 2.072704, "grad_norm": 1.796875, "learning_rate": 1.5459431789096495e-05, "loss": 0.4408, "step": 8098 }, { "epoch": 2.07296, "grad_norm": 1.921875, "learning_rate": 1.5455165941472572e-05, "loss": 0.4518, "step": 8099 }, { "epoch": 2.073216, "grad_norm": 1.8359375, "learning_rate": 1.545090009384865e-05, "loss": 0.4509, "step": 8100 }, { "epoch": 2.073472, "grad_norm": 1.9140625, "learning_rate": 1.5446634246224724e-05, "loss": 0.4366, "step": 8101 }, { "epoch": 2.073728, "grad_norm": 1.7421875, "learning_rate": 1.5442368398600805e-05, "loss": 0.4383, "step": 8102 }, { "epoch": 2.073984, "grad_norm": 1.8671875, "learning_rate": 1.543810255097688e-05, "loss": 0.4213, "step": 8103 }, { "epoch": 2.07424, "grad_norm": 1.875, "learning_rate": 1.5433836703352957e-05, "loss": 0.4116, "step": 8104 }, { "epoch": 2.074496, "grad_norm": 1.8046875, "learning_rate": 1.5429570855729035e-05, "loss": 0.4166, "step": 8105 }, { "epoch": 2.074752, "grad_norm": 1.7890625, "learning_rate": 1.5425305008105112e-05, "loss": 0.4623, "step": 8106 }, { "epoch": 2.075008, "grad_norm": 1.8515625, "learning_rate": 1.5421039160481187e-05, "loss": 0.4338, "step": 8107 }, { "epoch": 2.0752639999999998, "grad_norm": 1.90625, "learning_rate": 1.5416773312857268e-05, "loss": 0.437, "step": 8108 }, { "epoch": 2.07552, "grad_norm": 1.8359375, "learning_rate": 1.5412507465233342e-05, "loss": 0.4105, "step": 8109 }, { "epoch": 2.075776, "grad_norm": 1.875, "learning_rate": 1.540824161760942e-05, "loss": 0.4047, "step": 8110 }, { "epoch": 2.076032, "grad_norm": 1.9375, "learning_rate": 1.5403975769985497e-05, "loss": 0.376, "step": 8111 }, { "epoch": 2.076288, "grad_norm": 1.703125, "learning_rate": 1.5399709922361575e-05, "loss": 0.4331, "step": 8112 }, { "epoch": 2.076544, "grad_norm": 1.9296875, "learning_rate": 1.539544407473765e-05, "loss": 0.4331, "step": 8113 }, { "epoch": 2.0768, "grad_norm": 1.734375, "learning_rate": 1.5391178227113727e-05, "loss": 0.4398, "step": 8114 }, { "epoch": 2.077056, "grad_norm": 1.953125, "learning_rate": 1.5386912379489805e-05, "loss": 0.4167, "step": 8115 }, { "epoch": 2.077312, "grad_norm": 1.78125, "learning_rate": 1.5382646531865882e-05, "loss": 0.4221, "step": 8116 }, { "epoch": 2.077568, "grad_norm": 2.015625, "learning_rate": 1.537838068424196e-05, "loss": 0.4418, "step": 8117 }, { "epoch": 2.077824, "grad_norm": 1.8671875, "learning_rate": 1.5374114836618038e-05, "loss": 0.4083, "step": 8118 }, { "epoch": 2.07808, "grad_norm": 1.8359375, "learning_rate": 1.5369848988994115e-05, "loss": 0.4384, "step": 8119 }, { "epoch": 2.078336, "grad_norm": 1.921875, "learning_rate": 1.536558314137019e-05, "loss": 0.4105, "step": 8120 }, { "epoch": 2.078592, "grad_norm": 1.8671875, "learning_rate": 1.536131729374627e-05, "loss": 0.4234, "step": 8121 }, { "epoch": 2.078848, "grad_norm": 1.8515625, "learning_rate": 1.5357051446122345e-05, "loss": 0.4415, "step": 8122 }, { "epoch": 2.079104, "grad_norm": 1.8125, "learning_rate": 1.5352785598498422e-05, "loss": 0.3835, "step": 8123 }, { "epoch": 2.07936, "grad_norm": 1.8046875, "learning_rate": 1.53485197508745e-05, "loss": 0.4647, "step": 8124 }, { "epoch": 2.079616, "grad_norm": 1.8671875, "learning_rate": 1.5344253903250578e-05, "loss": 0.4394, "step": 8125 }, { "epoch": 2.079872, "grad_norm": 1.8359375, "learning_rate": 1.5339988055626652e-05, "loss": 0.4347, "step": 8126 }, { "epoch": 2.080128, "grad_norm": 1.9765625, "learning_rate": 1.533572220800273e-05, "loss": 0.4153, "step": 8127 }, { "epoch": 2.080384, "grad_norm": 1.9296875, "learning_rate": 1.5331456360378807e-05, "loss": 0.4535, "step": 8128 }, { "epoch": 2.08064, "grad_norm": 1.9140625, "learning_rate": 1.5327190512754885e-05, "loss": 0.3887, "step": 8129 }, { "epoch": 2.080896, "grad_norm": 1.7265625, "learning_rate": 1.5322924665130963e-05, "loss": 0.4532, "step": 8130 }, { "epoch": 2.081152, "grad_norm": 1.90625, "learning_rate": 1.531865881750704e-05, "loss": 0.4061, "step": 8131 }, { "epoch": 2.081408, "grad_norm": 1.859375, "learning_rate": 1.5314392969883118e-05, "loss": 0.4739, "step": 8132 }, { "epoch": 2.081664, "grad_norm": 1.890625, "learning_rate": 1.5310127122259192e-05, "loss": 0.3972, "step": 8133 }, { "epoch": 2.08192, "grad_norm": 1.78125, "learning_rate": 1.5305861274635273e-05, "loss": 0.4237, "step": 8134 }, { "epoch": 2.082176, "grad_norm": 1.953125, "learning_rate": 1.5301595427011347e-05, "loss": 0.3953, "step": 8135 }, { "epoch": 2.082432, "grad_norm": 1.859375, "learning_rate": 1.5297329579387425e-05, "loss": 0.4111, "step": 8136 }, { "epoch": 2.082688, "grad_norm": 1.921875, "learning_rate": 1.5293063731763503e-05, "loss": 0.3847, "step": 8137 }, { "epoch": 2.082944, "grad_norm": 1.9375, "learning_rate": 1.528879788413958e-05, "loss": 0.4065, "step": 8138 }, { "epoch": 2.0832, "grad_norm": 1.890625, "learning_rate": 1.5284532036515655e-05, "loss": 0.4217, "step": 8139 }, { "epoch": 2.083456, "grad_norm": 1.8984375, "learning_rate": 1.5280266188891736e-05, "loss": 0.4026, "step": 8140 }, { "epoch": 2.083712, "grad_norm": 1.7578125, "learning_rate": 1.527600034126781e-05, "loss": 0.4547, "step": 8141 }, { "epoch": 2.083968, "grad_norm": 1.7578125, "learning_rate": 1.5271734493643888e-05, "loss": 0.4442, "step": 8142 }, { "epoch": 2.084224, "grad_norm": 1.8515625, "learning_rate": 1.5267468646019965e-05, "loss": 0.382, "step": 8143 }, { "epoch": 2.08448, "grad_norm": 1.8203125, "learning_rate": 1.5263202798396043e-05, "loss": 0.4188, "step": 8144 }, { "epoch": 2.084736, "grad_norm": 1.8125, "learning_rate": 1.5258936950772117e-05, "loss": 0.3678, "step": 8145 }, { "epoch": 2.084992, "grad_norm": 1.78125, "learning_rate": 1.5254671103148197e-05, "loss": 0.4241, "step": 8146 }, { "epoch": 2.085248, "grad_norm": 1.8203125, "learning_rate": 1.5250405255524273e-05, "loss": 0.4355, "step": 8147 }, { "epoch": 2.085504, "grad_norm": 1.8828125, "learning_rate": 1.524613940790035e-05, "loss": 0.3918, "step": 8148 }, { "epoch": 2.08576, "grad_norm": 1.9140625, "learning_rate": 1.524187356027643e-05, "loss": 0.4347, "step": 8149 }, { "epoch": 2.086016, "grad_norm": 1.9765625, "learning_rate": 1.5237607712652504e-05, "loss": 0.3955, "step": 8150 }, { "epoch": 2.086272, "grad_norm": 1.875, "learning_rate": 1.5233341865028583e-05, "loss": 0.4216, "step": 8151 }, { "epoch": 2.086528, "grad_norm": 1.859375, "learning_rate": 1.5229076017404659e-05, "loss": 0.3966, "step": 8152 }, { "epoch": 2.086784, "grad_norm": 1.84375, "learning_rate": 1.5224810169780737e-05, "loss": 0.4758, "step": 8153 }, { "epoch": 2.08704, "grad_norm": 1.90625, "learning_rate": 1.5220544322156813e-05, "loss": 0.4077, "step": 8154 }, { "epoch": 2.087296, "grad_norm": 1.890625, "learning_rate": 1.521627847453289e-05, "loss": 0.4173, "step": 8155 }, { "epoch": 2.087552, "grad_norm": 1.796875, "learning_rate": 1.5212012626908966e-05, "loss": 0.4238, "step": 8156 }, { "epoch": 2.087808, "grad_norm": 1.828125, "learning_rate": 1.5207746779285046e-05, "loss": 0.4478, "step": 8157 }, { "epoch": 2.088064, "grad_norm": 1.734375, "learning_rate": 1.5203480931661122e-05, "loss": 0.4566, "step": 8158 }, { "epoch": 2.08832, "grad_norm": 1.8359375, "learning_rate": 1.51992150840372e-05, "loss": 0.4293, "step": 8159 }, { "epoch": 2.088576, "grad_norm": 1.8671875, "learning_rate": 1.5194949236413275e-05, "loss": 0.431, "step": 8160 }, { "epoch": 2.088832, "grad_norm": 1.9453125, "learning_rate": 1.5190683388789353e-05, "loss": 0.4429, "step": 8161 }, { "epoch": 2.089088, "grad_norm": 1.859375, "learning_rate": 1.5186417541165429e-05, "loss": 0.4417, "step": 8162 }, { "epoch": 2.089344, "grad_norm": 1.9140625, "learning_rate": 1.5182151693541508e-05, "loss": 0.4233, "step": 8163 }, { "epoch": 2.0896, "grad_norm": 1.7734375, "learning_rate": 1.5177885845917583e-05, "loss": 0.4136, "step": 8164 }, { "epoch": 2.089856, "grad_norm": 1.796875, "learning_rate": 1.5173619998293662e-05, "loss": 0.4334, "step": 8165 }, { "epoch": 2.090112, "grad_norm": 1.8359375, "learning_rate": 1.516935415066974e-05, "loss": 0.4193, "step": 8166 }, { "epoch": 2.090368, "grad_norm": 1.8515625, "learning_rate": 1.5165088303045815e-05, "loss": 0.4228, "step": 8167 }, { "epoch": 2.090624, "grad_norm": 1.765625, "learning_rate": 1.5160822455421895e-05, "loss": 0.4016, "step": 8168 }, { "epoch": 2.09088, "grad_norm": 1.8828125, "learning_rate": 1.5156556607797969e-05, "loss": 0.4614, "step": 8169 }, { "epoch": 2.091136, "grad_norm": 1.8125, "learning_rate": 1.5152290760174048e-05, "loss": 0.4314, "step": 8170 }, { "epoch": 2.091392, "grad_norm": 1.9296875, "learning_rate": 1.5148024912550124e-05, "loss": 0.43, "step": 8171 }, { "epoch": 2.091648, "grad_norm": 1.859375, "learning_rate": 1.5143759064926202e-05, "loss": 0.4303, "step": 8172 }, { "epoch": 2.091904, "grad_norm": 1.8203125, "learning_rate": 1.5139493217302278e-05, "loss": 0.4088, "step": 8173 }, { "epoch": 2.09216, "grad_norm": 1.9140625, "learning_rate": 1.5135227369678356e-05, "loss": 0.4133, "step": 8174 }, { "epoch": 2.092416, "grad_norm": 1.890625, "learning_rate": 1.5130961522054432e-05, "loss": 0.4301, "step": 8175 }, { "epoch": 2.092672, "grad_norm": 1.8515625, "learning_rate": 1.5126695674430511e-05, "loss": 0.4304, "step": 8176 }, { "epoch": 2.092928, "grad_norm": 1.8125, "learning_rate": 1.5122429826806587e-05, "loss": 0.4178, "step": 8177 }, { "epoch": 2.093184, "grad_norm": 2.015625, "learning_rate": 1.5118163979182665e-05, "loss": 0.4207, "step": 8178 }, { "epoch": 2.09344, "grad_norm": 1.890625, "learning_rate": 1.511389813155874e-05, "loss": 0.4481, "step": 8179 }, { "epoch": 2.093696, "grad_norm": 1.796875, "learning_rate": 1.5109632283934818e-05, "loss": 0.4039, "step": 8180 }, { "epoch": 2.093952, "grad_norm": 1.8203125, "learning_rate": 1.5105366436310894e-05, "loss": 0.417, "step": 8181 }, { "epoch": 2.094208, "grad_norm": 1.8671875, "learning_rate": 1.5101100588686974e-05, "loss": 0.4025, "step": 8182 }, { "epoch": 2.094464, "grad_norm": 1.84375, "learning_rate": 1.5096834741063051e-05, "loss": 0.4471, "step": 8183 }, { "epoch": 2.09472, "grad_norm": 1.78125, "learning_rate": 1.5092568893439127e-05, "loss": 0.4666, "step": 8184 }, { "epoch": 2.094976, "grad_norm": 1.90625, "learning_rate": 1.5088303045815205e-05, "loss": 0.4202, "step": 8185 }, { "epoch": 2.095232, "grad_norm": 1.8046875, "learning_rate": 1.508403719819128e-05, "loss": 0.4265, "step": 8186 }, { "epoch": 2.095488, "grad_norm": 1.828125, "learning_rate": 1.507977135056736e-05, "loss": 0.4016, "step": 8187 }, { "epoch": 2.095744, "grad_norm": 1.734375, "learning_rate": 1.5075505502943434e-05, "loss": 0.4427, "step": 8188 }, { "epoch": 2.096, "grad_norm": 1.7734375, "learning_rate": 1.5071239655319514e-05, "loss": 0.4297, "step": 8189 }, { "epoch": 2.096256, "grad_norm": 1.9453125, "learning_rate": 1.506697380769559e-05, "loss": 0.4278, "step": 8190 }, { "epoch": 2.096512, "grad_norm": 1.7265625, "learning_rate": 1.5062707960071667e-05, "loss": 0.4072, "step": 8191 }, { "epoch": 2.096768, "grad_norm": 1.90625, "learning_rate": 1.5058442112447743e-05, "loss": 0.4212, "step": 8192 }, { "epoch": 2.097024, "grad_norm": 2.0, "learning_rate": 1.5054176264823821e-05, "loss": 0.4447, "step": 8193 }, { "epoch": 2.09728, "grad_norm": 1.7890625, "learning_rate": 1.5049910417199897e-05, "loss": 0.4038, "step": 8194 }, { "epoch": 2.097536, "grad_norm": 1.65625, "learning_rate": 1.5045644569575976e-05, "loss": 0.4203, "step": 8195 }, { "epoch": 2.097792, "grad_norm": 1.671875, "learning_rate": 1.504137872195205e-05, "loss": 0.428, "step": 8196 }, { "epoch": 2.098048, "grad_norm": 1.8359375, "learning_rate": 1.503711287432813e-05, "loss": 0.4445, "step": 8197 }, { "epoch": 2.098304, "grad_norm": 1.8125, "learning_rate": 1.5032847026704208e-05, "loss": 0.4163, "step": 8198 }, { "epoch": 2.09856, "grad_norm": 1.8359375, "learning_rate": 1.5028581179080283e-05, "loss": 0.449, "step": 8199 }, { "epoch": 2.098816, "grad_norm": 1.78125, "learning_rate": 1.5024315331456363e-05, "loss": 0.4147, "step": 8200 }, { "epoch": 2.099072, "grad_norm": 1.8046875, "learning_rate": 1.5020049483832437e-05, "loss": 0.4263, "step": 8201 }, { "epoch": 2.099328, "grad_norm": 1.9296875, "learning_rate": 1.5015783636208516e-05, "loss": 0.4458, "step": 8202 }, { "epoch": 2.099584, "grad_norm": 1.796875, "learning_rate": 1.5011517788584592e-05, "loss": 0.4302, "step": 8203 }, { "epoch": 2.09984, "grad_norm": 1.8515625, "learning_rate": 1.500725194096067e-05, "loss": 0.4401, "step": 8204 }, { "epoch": 2.100096, "grad_norm": 1.7265625, "learning_rate": 1.5002986093336746e-05, "loss": 0.4371, "step": 8205 }, { "epoch": 2.100352, "grad_norm": 1.84375, "learning_rate": 1.4998720245712825e-05, "loss": 0.4309, "step": 8206 }, { "epoch": 2.100608, "grad_norm": 1.890625, "learning_rate": 1.49944543980889e-05, "loss": 0.4347, "step": 8207 }, { "epoch": 2.100864, "grad_norm": 1.8828125, "learning_rate": 1.4990188550464979e-05, "loss": 0.4252, "step": 8208 }, { "epoch": 2.10112, "grad_norm": 1.7421875, "learning_rate": 1.4985922702841055e-05, "loss": 0.429, "step": 8209 }, { "epoch": 2.101376, "grad_norm": 1.78125, "learning_rate": 1.4981656855217133e-05, "loss": 0.4436, "step": 8210 }, { "epoch": 2.101632, "grad_norm": 1.7578125, "learning_rate": 1.4977391007593209e-05, "loss": 0.4407, "step": 8211 }, { "epoch": 2.101888, "grad_norm": 1.828125, "learning_rate": 1.4973125159969286e-05, "loss": 0.3945, "step": 8212 }, { "epoch": 2.102144, "grad_norm": 1.734375, "learning_rate": 1.4968859312345362e-05, "loss": 0.4714, "step": 8213 }, { "epoch": 2.1024, "grad_norm": 1.875, "learning_rate": 1.4964593464721442e-05, "loss": 0.3979, "step": 8214 }, { "epoch": 2.102656, "grad_norm": 1.890625, "learning_rate": 1.496032761709752e-05, "loss": 0.4034, "step": 8215 }, { "epoch": 2.102912, "grad_norm": 1.8359375, "learning_rate": 1.4956061769473595e-05, "loss": 0.4822, "step": 8216 }, { "epoch": 2.103168, "grad_norm": 1.6953125, "learning_rate": 1.4951795921849673e-05, "loss": 0.4277, "step": 8217 }, { "epoch": 2.103424, "grad_norm": 2.03125, "learning_rate": 1.4947530074225749e-05, "loss": 0.3572, "step": 8218 }, { "epoch": 2.1036799999999998, "grad_norm": 1.9453125, "learning_rate": 1.4943264226601828e-05, "loss": 0.4108, "step": 8219 }, { "epoch": 2.103936, "grad_norm": 1.8671875, "learning_rate": 1.4938998378977902e-05, "loss": 0.379, "step": 8220 }, { "epoch": 2.104192, "grad_norm": 1.9375, "learning_rate": 1.4934732531353982e-05, "loss": 0.4293, "step": 8221 }, { "epoch": 2.104448, "grad_norm": 1.859375, "learning_rate": 1.4930466683730058e-05, "loss": 0.411, "step": 8222 }, { "epoch": 2.104704, "grad_norm": 1.90625, "learning_rate": 1.4926200836106135e-05, "loss": 0.41, "step": 8223 }, { "epoch": 2.10496, "grad_norm": 1.953125, "learning_rate": 1.4921934988482211e-05, "loss": 0.4184, "step": 8224 }, { "epoch": 2.105216, "grad_norm": 1.734375, "learning_rate": 1.4917669140858289e-05, "loss": 0.433, "step": 8225 }, { "epoch": 2.105472, "grad_norm": 1.796875, "learning_rate": 1.4913403293234365e-05, "loss": 0.4072, "step": 8226 }, { "epoch": 2.105728, "grad_norm": 1.8046875, "learning_rate": 1.4909137445610444e-05, "loss": 0.4068, "step": 8227 }, { "epoch": 2.105984, "grad_norm": 1.8359375, "learning_rate": 1.490487159798652e-05, "loss": 0.3893, "step": 8228 }, { "epoch": 2.10624, "grad_norm": 1.734375, "learning_rate": 1.4900605750362598e-05, "loss": 0.4387, "step": 8229 }, { "epoch": 2.106496, "grad_norm": 1.75, "learning_rate": 1.4896339902738674e-05, "loss": 0.4521, "step": 8230 }, { "epoch": 2.106752, "grad_norm": 1.8828125, "learning_rate": 1.4892074055114751e-05, "loss": 0.4384, "step": 8231 }, { "epoch": 2.107008, "grad_norm": 1.8984375, "learning_rate": 1.488780820749083e-05, "loss": 0.4166, "step": 8232 }, { "epoch": 2.107264, "grad_norm": 1.7890625, "learning_rate": 1.4883542359866907e-05, "loss": 0.4322, "step": 8233 }, { "epoch": 2.10752, "grad_norm": 1.84375, "learning_rate": 1.4879276512242984e-05, "loss": 0.4017, "step": 8234 }, { "epoch": 2.107776, "grad_norm": 1.75, "learning_rate": 1.487501066461906e-05, "loss": 0.4419, "step": 8235 }, { "epoch": 2.108032, "grad_norm": 1.8515625, "learning_rate": 1.4870744816995138e-05, "loss": 0.4159, "step": 8236 }, { "epoch": 2.108288, "grad_norm": 1.9375, "learning_rate": 1.4866478969371214e-05, "loss": 0.4175, "step": 8237 }, { "epoch": 2.108544, "grad_norm": 1.7265625, "learning_rate": 1.4862213121747293e-05, "loss": 0.4403, "step": 8238 }, { "epoch": 2.1088, "grad_norm": 1.8671875, "learning_rate": 1.4857947274123368e-05, "loss": 0.4272, "step": 8239 }, { "epoch": 2.109056, "grad_norm": 1.9453125, "learning_rate": 1.4853681426499447e-05, "loss": 0.4155, "step": 8240 }, { "epoch": 2.109312, "grad_norm": 1.9140625, "learning_rate": 1.4849415578875523e-05, "loss": 0.4372, "step": 8241 }, { "epoch": 2.109568, "grad_norm": 1.9375, "learning_rate": 1.48451497312516e-05, "loss": 0.3825, "step": 8242 }, { "epoch": 2.109824, "grad_norm": 1.90625, "learning_rate": 1.4840883883627677e-05, "loss": 0.4149, "step": 8243 }, { "epoch": 2.11008, "grad_norm": 1.7734375, "learning_rate": 1.4836618036003754e-05, "loss": 0.4151, "step": 8244 }, { "epoch": 2.110336, "grad_norm": 1.7890625, "learning_rate": 1.483235218837983e-05, "loss": 0.4017, "step": 8245 }, { "epoch": 2.110592, "grad_norm": 1.84375, "learning_rate": 1.482808634075591e-05, "loss": 0.398, "step": 8246 }, { "epoch": 2.110848, "grad_norm": 1.875, "learning_rate": 1.4823820493131987e-05, "loss": 0.4288, "step": 8247 }, { "epoch": 2.111104, "grad_norm": 1.875, "learning_rate": 1.4819554645508063e-05, "loss": 0.4245, "step": 8248 }, { "epoch": 2.11136, "grad_norm": 1.734375, "learning_rate": 1.481528879788414e-05, "loss": 0.4262, "step": 8249 }, { "epoch": 2.111616, "grad_norm": 1.765625, "learning_rate": 1.4811022950260217e-05, "loss": 0.4512, "step": 8250 }, { "epoch": 2.111872, "grad_norm": 1.796875, "learning_rate": 1.4806757102636296e-05, "loss": 0.4492, "step": 8251 }, { "epoch": 2.1121280000000002, "grad_norm": 1.71875, "learning_rate": 1.4802491255012372e-05, "loss": 0.4503, "step": 8252 }, { "epoch": 2.112384, "grad_norm": 1.78125, "learning_rate": 1.479822540738845e-05, "loss": 0.4258, "step": 8253 }, { "epoch": 2.11264, "grad_norm": 1.921875, "learning_rate": 1.4793959559764526e-05, "loss": 0.4217, "step": 8254 }, { "epoch": 2.112896, "grad_norm": 1.7578125, "learning_rate": 1.4789693712140603e-05, "loss": 0.4303, "step": 8255 }, { "epoch": 2.113152, "grad_norm": 1.8671875, "learning_rate": 1.478542786451668e-05, "loss": 0.4659, "step": 8256 }, { "epoch": 2.113408, "grad_norm": 1.8671875, "learning_rate": 1.4781162016892759e-05, "loss": 0.4414, "step": 8257 }, { "epoch": 2.113664, "grad_norm": 1.9609375, "learning_rate": 1.4776896169268833e-05, "loss": 0.4107, "step": 8258 }, { "epoch": 2.11392, "grad_norm": 1.78125, "learning_rate": 1.4772630321644912e-05, "loss": 0.4305, "step": 8259 }, { "epoch": 2.114176, "grad_norm": 1.7890625, "learning_rate": 1.4768364474020988e-05, "loss": 0.4285, "step": 8260 }, { "epoch": 2.114432, "grad_norm": 1.8125, "learning_rate": 1.4764098626397066e-05, "loss": 0.4301, "step": 8261 }, { "epoch": 2.114688, "grad_norm": 1.8359375, "learning_rate": 1.4759832778773142e-05, "loss": 0.3863, "step": 8262 }, { "epoch": 2.114944, "grad_norm": 1.765625, "learning_rate": 1.475556693114922e-05, "loss": 0.4165, "step": 8263 }, { "epoch": 2.1152, "grad_norm": 1.9375, "learning_rate": 1.4751301083525299e-05, "loss": 0.408, "step": 8264 }, { "epoch": 2.115456, "grad_norm": 1.78125, "learning_rate": 1.4747035235901375e-05, "loss": 0.4212, "step": 8265 }, { "epoch": 2.115712, "grad_norm": 1.921875, "learning_rate": 1.4742769388277452e-05, "loss": 0.4191, "step": 8266 }, { "epoch": 2.115968, "grad_norm": 1.8359375, "learning_rate": 1.4738503540653528e-05, "loss": 0.4322, "step": 8267 }, { "epoch": 2.116224, "grad_norm": 1.8125, "learning_rate": 1.4734237693029606e-05, "loss": 0.4518, "step": 8268 }, { "epoch": 2.11648, "grad_norm": 1.8828125, "learning_rate": 1.4729971845405682e-05, "loss": 0.4205, "step": 8269 }, { "epoch": 2.116736, "grad_norm": 2.046875, "learning_rate": 1.4725705997781761e-05, "loss": 0.4618, "step": 8270 }, { "epoch": 2.116992, "grad_norm": 1.9921875, "learning_rate": 1.4721440150157836e-05, "loss": 0.416, "step": 8271 }, { "epoch": 2.117248, "grad_norm": 1.8359375, "learning_rate": 1.4717174302533915e-05, "loss": 0.4525, "step": 8272 }, { "epoch": 2.117504, "grad_norm": 2.03125, "learning_rate": 1.4712908454909991e-05, "loss": 0.4131, "step": 8273 }, { "epoch": 2.11776, "grad_norm": 1.90625, "learning_rate": 1.4708642607286069e-05, "loss": 0.4326, "step": 8274 }, { "epoch": 2.118016, "grad_norm": 1.9453125, "learning_rate": 1.4704376759662145e-05, "loss": 0.4592, "step": 8275 }, { "epoch": 2.118272, "grad_norm": 2.03125, "learning_rate": 1.4700110912038222e-05, "loss": 0.4043, "step": 8276 }, { "epoch": 2.118528, "grad_norm": 1.9609375, "learning_rate": 1.4695845064414298e-05, "loss": 0.4321, "step": 8277 }, { "epoch": 2.118784, "grad_norm": 1.8125, "learning_rate": 1.4691579216790378e-05, "loss": 0.4313, "step": 8278 }, { "epoch": 2.11904, "grad_norm": 1.9296875, "learning_rate": 1.4687313369166453e-05, "loss": 0.435, "step": 8279 }, { "epoch": 2.119296, "grad_norm": 1.953125, "learning_rate": 1.4683047521542531e-05, "loss": 0.4187, "step": 8280 }, { "epoch": 2.119552, "grad_norm": 1.9375, "learning_rate": 1.4678781673918609e-05, "loss": 0.3993, "step": 8281 }, { "epoch": 2.119808, "grad_norm": 1.9921875, "learning_rate": 1.4674515826294685e-05, "loss": 0.4398, "step": 8282 }, { "epoch": 2.120064, "grad_norm": 2.0, "learning_rate": 1.4670249978670764e-05, "loss": 0.3657, "step": 8283 }, { "epoch": 2.12032, "grad_norm": 1.8984375, "learning_rate": 1.466598413104684e-05, "loss": 0.3953, "step": 8284 }, { "epoch": 2.120576, "grad_norm": 1.8125, "learning_rate": 1.4661718283422918e-05, "loss": 0.4084, "step": 8285 }, { "epoch": 2.120832, "grad_norm": 2.0625, "learning_rate": 1.4657452435798994e-05, "loss": 0.4182, "step": 8286 }, { "epoch": 2.121088, "grad_norm": 1.9453125, "learning_rate": 1.4653186588175071e-05, "loss": 0.421, "step": 8287 }, { "epoch": 2.121344, "grad_norm": 1.6875, "learning_rate": 1.4648920740551147e-05, "loss": 0.4091, "step": 8288 }, { "epoch": 2.1216, "grad_norm": 1.8359375, "learning_rate": 1.4644654892927227e-05, "loss": 0.4008, "step": 8289 }, { "epoch": 2.121856, "grad_norm": 1.875, "learning_rate": 1.4640389045303301e-05, "loss": 0.3872, "step": 8290 }, { "epoch": 2.122112, "grad_norm": 1.8125, "learning_rate": 1.463612319767938e-05, "loss": 0.4167, "step": 8291 }, { "epoch": 2.122368, "grad_norm": 1.703125, "learning_rate": 1.4631857350055456e-05, "loss": 0.4178, "step": 8292 }, { "epoch": 2.122624, "grad_norm": 2.0, "learning_rate": 1.4627591502431534e-05, "loss": 0.3978, "step": 8293 }, { "epoch": 2.12288, "grad_norm": 1.953125, "learning_rate": 1.462332565480761e-05, "loss": 0.424, "step": 8294 }, { "epoch": 2.123136, "grad_norm": 1.8515625, "learning_rate": 1.4619059807183687e-05, "loss": 0.4183, "step": 8295 }, { "epoch": 2.123392, "grad_norm": 1.8515625, "learning_rate": 1.4614793959559767e-05, "loss": 0.4331, "step": 8296 }, { "epoch": 2.123648, "grad_norm": 1.90625, "learning_rate": 1.4610528111935843e-05, "loss": 0.4403, "step": 8297 }, { "epoch": 2.123904, "grad_norm": 1.828125, "learning_rate": 1.460626226431192e-05, "loss": 0.4019, "step": 8298 }, { "epoch": 2.12416, "grad_norm": 2.015625, "learning_rate": 1.4601996416687996e-05, "loss": 0.4584, "step": 8299 }, { "epoch": 2.124416, "grad_norm": 1.7421875, "learning_rate": 1.4597730569064074e-05, "loss": 0.4235, "step": 8300 }, { "epoch": 2.124672, "grad_norm": 1.890625, "learning_rate": 1.459346472144015e-05, "loss": 0.4323, "step": 8301 }, { "epoch": 2.124928, "grad_norm": 1.796875, "learning_rate": 1.458919887381623e-05, "loss": 0.4295, "step": 8302 }, { "epoch": 2.125184, "grad_norm": 1.921875, "learning_rate": 1.4584933026192305e-05, "loss": 0.4213, "step": 8303 }, { "epoch": 2.12544, "grad_norm": 1.9140625, "learning_rate": 1.4580667178568383e-05, "loss": 0.4307, "step": 8304 }, { "epoch": 2.125696, "grad_norm": 1.9609375, "learning_rate": 1.4576401330944459e-05, "loss": 0.3998, "step": 8305 }, { "epoch": 2.125952, "grad_norm": 1.828125, "learning_rate": 1.4572135483320537e-05, "loss": 0.4139, "step": 8306 }, { "epoch": 2.126208, "grad_norm": 1.7890625, "learning_rate": 1.4567869635696613e-05, "loss": 0.4203, "step": 8307 }, { "epoch": 2.126464, "grad_norm": 2.03125, "learning_rate": 1.4563603788072692e-05, "loss": 0.4244, "step": 8308 }, { "epoch": 2.12672, "grad_norm": 1.8125, "learning_rate": 1.4559337940448766e-05, "loss": 0.3854, "step": 8309 }, { "epoch": 2.126976, "grad_norm": 1.9375, "learning_rate": 1.4555072092824846e-05, "loss": 0.3873, "step": 8310 }, { "epoch": 2.1272320000000002, "grad_norm": 1.8125, "learning_rate": 1.4550806245200921e-05, "loss": 0.4149, "step": 8311 }, { "epoch": 2.127488, "grad_norm": 1.7734375, "learning_rate": 1.4546540397576999e-05, "loss": 0.4339, "step": 8312 }, { "epoch": 2.127744, "grad_norm": 1.7421875, "learning_rate": 1.4542274549953078e-05, "loss": 0.4451, "step": 8313 }, { "epoch": 2.128, "grad_norm": 1.8359375, "learning_rate": 1.4538008702329153e-05, "loss": 0.4129, "step": 8314 }, { "epoch": 2.128256, "grad_norm": 1.9375, "learning_rate": 1.4533742854705232e-05, "loss": 0.4322, "step": 8315 }, { "epoch": 2.128512, "grad_norm": 1.8671875, "learning_rate": 1.4529477007081308e-05, "loss": 0.3935, "step": 8316 }, { "epoch": 2.128768, "grad_norm": 1.6875, "learning_rate": 1.4525211159457386e-05, "loss": 0.39, "step": 8317 }, { "epoch": 2.129024, "grad_norm": 1.703125, "learning_rate": 1.4520945311833462e-05, "loss": 0.4246, "step": 8318 }, { "epoch": 2.12928, "grad_norm": 1.8046875, "learning_rate": 1.451667946420954e-05, "loss": 0.4303, "step": 8319 }, { "epoch": 2.129536, "grad_norm": 1.8828125, "learning_rate": 1.4512413616585615e-05, "loss": 0.428, "step": 8320 }, { "epoch": 2.129792, "grad_norm": 1.890625, "learning_rate": 1.4508147768961695e-05, "loss": 0.4028, "step": 8321 }, { "epoch": 2.130048, "grad_norm": 1.7578125, "learning_rate": 1.4503881921337769e-05, "loss": 0.4083, "step": 8322 }, { "epoch": 2.130304, "grad_norm": 1.734375, "learning_rate": 1.4499616073713848e-05, "loss": 0.4496, "step": 8323 }, { "epoch": 2.13056, "grad_norm": 1.75, "learning_rate": 1.4495350226089924e-05, "loss": 0.4325, "step": 8324 }, { "epoch": 2.130816, "grad_norm": 1.71875, "learning_rate": 1.4491084378466002e-05, "loss": 0.4041, "step": 8325 }, { "epoch": 2.131072, "grad_norm": 1.8125, "learning_rate": 1.4486818530842078e-05, "loss": 0.4393, "step": 8326 }, { "epoch": 2.131328, "grad_norm": 1.71875, "learning_rate": 1.4482552683218155e-05, "loss": 0.4566, "step": 8327 }, { "epoch": 2.131584, "grad_norm": 1.8828125, "learning_rate": 1.4478286835594231e-05, "loss": 0.4377, "step": 8328 }, { "epoch": 2.13184, "grad_norm": 1.9453125, "learning_rate": 1.447402098797031e-05, "loss": 0.465, "step": 8329 }, { "epoch": 2.1320959999999998, "grad_norm": 2.046875, "learning_rate": 1.4469755140346388e-05, "loss": 0.4176, "step": 8330 }, { "epoch": 2.132352, "grad_norm": 1.7109375, "learning_rate": 1.4465489292722464e-05, "loss": 0.4117, "step": 8331 }, { "epoch": 2.132608, "grad_norm": 1.75, "learning_rate": 1.4461223445098542e-05, "loss": 0.4256, "step": 8332 }, { "epoch": 2.132864, "grad_norm": 1.8046875, "learning_rate": 1.4456957597474618e-05, "loss": 0.4551, "step": 8333 }, { "epoch": 2.13312, "grad_norm": 1.8828125, "learning_rate": 1.4452691749850697e-05, "loss": 0.4175, "step": 8334 }, { "epoch": 2.133376, "grad_norm": 2.125, "learning_rate": 1.4448425902226773e-05, "loss": 0.4391, "step": 8335 }, { "epoch": 2.133632, "grad_norm": 1.9609375, "learning_rate": 1.4444160054602851e-05, "loss": 0.394, "step": 8336 }, { "epoch": 2.133888, "grad_norm": 2.078125, "learning_rate": 1.4439894206978927e-05, "loss": 0.4357, "step": 8337 }, { "epoch": 2.134144, "grad_norm": 1.859375, "learning_rate": 1.4435628359355005e-05, "loss": 0.4469, "step": 8338 }, { "epoch": 2.1344, "grad_norm": 1.9140625, "learning_rate": 1.443136251173108e-05, "loss": 0.4531, "step": 8339 }, { "epoch": 2.134656, "grad_norm": 1.7265625, "learning_rate": 1.442709666410716e-05, "loss": 0.3928, "step": 8340 }, { "epoch": 2.134912, "grad_norm": 1.75, "learning_rate": 1.4422830816483234e-05, "loss": 0.434, "step": 8341 }, { "epoch": 2.135168, "grad_norm": 1.7265625, "learning_rate": 1.4418564968859314e-05, "loss": 0.441, "step": 8342 }, { "epoch": 2.135424, "grad_norm": 1.703125, "learning_rate": 1.441429912123539e-05, "loss": 0.399, "step": 8343 }, { "epoch": 2.13568, "grad_norm": 1.84375, "learning_rate": 1.4410033273611467e-05, "loss": 0.4634, "step": 8344 }, { "epoch": 2.135936, "grad_norm": 1.8671875, "learning_rate": 1.4405767425987543e-05, "loss": 0.4114, "step": 8345 }, { "epoch": 2.136192, "grad_norm": 1.953125, "learning_rate": 1.440150157836362e-05, "loss": 0.4366, "step": 8346 }, { "epoch": 2.136448, "grad_norm": 1.8046875, "learning_rate": 1.43972357307397e-05, "loss": 0.4489, "step": 8347 }, { "epoch": 2.136704, "grad_norm": 1.875, "learning_rate": 1.4392969883115776e-05, "loss": 0.4206, "step": 8348 }, { "epoch": 2.13696, "grad_norm": 1.8828125, "learning_rate": 1.4388704035491854e-05, "loss": 0.4431, "step": 8349 }, { "epoch": 2.137216, "grad_norm": 1.6640625, "learning_rate": 1.438443818786793e-05, "loss": 0.4268, "step": 8350 }, { "epoch": 2.137472, "grad_norm": 1.953125, "learning_rate": 1.4380172340244007e-05, "loss": 0.4613, "step": 8351 }, { "epoch": 2.137728, "grad_norm": 1.828125, "learning_rate": 1.4375906492620083e-05, "loss": 0.4161, "step": 8352 }, { "epoch": 2.137984, "grad_norm": 1.7421875, "learning_rate": 1.4371640644996163e-05, "loss": 0.4333, "step": 8353 }, { "epoch": 2.13824, "grad_norm": 1.796875, "learning_rate": 1.4367374797372239e-05, "loss": 0.4755, "step": 8354 }, { "epoch": 2.138496, "grad_norm": 1.7890625, "learning_rate": 1.4363108949748316e-05, "loss": 0.4118, "step": 8355 }, { "epoch": 2.138752, "grad_norm": 1.609375, "learning_rate": 1.4358843102124392e-05, "loss": 0.466, "step": 8356 }, { "epoch": 2.139008, "grad_norm": 1.96875, "learning_rate": 1.435457725450047e-05, "loss": 0.4314, "step": 8357 }, { "epoch": 2.139264, "grad_norm": 1.8125, "learning_rate": 1.4350311406876546e-05, "loss": 0.4291, "step": 8358 }, { "epoch": 2.13952, "grad_norm": 1.8828125, "learning_rate": 1.4346045559252625e-05, "loss": 0.4331, "step": 8359 }, { "epoch": 2.139776, "grad_norm": 1.8046875, "learning_rate": 1.43417797116287e-05, "loss": 0.4063, "step": 8360 }, { "epoch": 2.140032, "grad_norm": 1.875, "learning_rate": 1.4337513864004779e-05, "loss": 0.3975, "step": 8361 }, { "epoch": 2.140288, "grad_norm": 1.8125, "learning_rate": 1.4333248016380856e-05, "loss": 0.4149, "step": 8362 }, { "epoch": 2.1405440000000002, "grad_norm": 1.7578125, "learning_rate": 1.4328982168756932e-05, "loss": 0.4373, "step": 8363 }, { "epoch": 2.1408, "grad_norm": 1.7890625, "learning_rate": 1.4324716321133012e-05, "loss": 0.4692, "step": 8364 }, { "epoch": 2.141056, "grad_norm": 1.8046875, "learning_rate": 1.4320450473509086e-05, "loss": 0.4352, "step": 8365 }, { "epoch": 2.141312, "grad_norm": 1.9609375, "learning_rate": 1.4316184625885165e-05, "loss": 0.4029, "step": 8366 }, { "epoch": 2.141568, "grad_norm": 1.8984375, "learning_rate": 1.4311918778261241e-05, "loss": 0.4518, "step": 8367 }, { "epoch": 2.141824, "grad_norm": 1.7421875, "learning_rate": 1.4307652930637319e-05, "loss": 0.4452, "step": 8368 }, { "epoch": 2.14208, "grad_norm": 1.890625, "learning_rate": 1.4303387083013395e-05, "loss": 0.4316, "step": 8369 }, { "epoch": 2.142336, "grad_norm": 1.765625, "learning_rate": 1.4299121235389473e-05, "loss": 0.4157, "step": 8370 }, { "epoch": 2.142592, "grad_norm": 1.8828125, "learning_rate": 1.4294855387765549e-05, "loss": 0.4483, "step": 8371 }, { "epoch": 2.142848, "grad_norm": 1.90625, "learning_rate": 1.4290589540141628e-05, "loss": 0.45, "step": 8372 }, { "epoch": 2.143104, "grad_norm": 1.8515625, "learning_rate": 1.4286323692517702e-05, "loss": 0.4605, "step": 8373 }, { "epoch": 2.14336, "grad_norm": 1.84375, "learning_rate": 1.4282057844893782e-05, "loss": 0.3961, "step": 8374 }, { "epoch": 2.143616, "grad_norm": 1.90625, "learning_rate": 1.4277791997269857e-05, "loss": 0.4217, "step": 8375 }, { "epoch": 2.143872, "grad_norm": 1.7890625, "learning_rate": 1.4273526149645935e-05, "loss": 0.4358, "step": 8376 }, { "epoch": 2.144128, "grad_norm": 1.6953125, "learning_rate": 1.4269260302022011e-05, "loss": 0.3991, "step": 8377 }, { "epoch": 2.144384, "grad_norm": 1.84375, "learning_rate": 1.4264994454398089e-05, "loss": 0.4421, "step": 8378 }, { "epoch": 2.14464, "grad_norm": 1.7578125, "learning_rate": 1.4260728606774168e-05, "loss": 0.412, "step": 8379 }, { "epoch": 2.144896, "grad_norm": 1.9375, "learning_rate": 1.4256462759150244e-05, "loss": 0.4098, "step": 8380 }, { "epoch": 2.145152, "grad_norm": 1.75, "learning_rate": 1.4252196911526322e-05, "loss": 0.4147, "step": 8381 }, { "epoch": 2.145408, "grad_norm": 1.78125, "learning_rate": 1.4247931063902398e-05, "loss": 0.4619, "step": 8382 }, { "epoch": 2.145664, "grad_norm": 1.7890625, "learning_rate": 1.4243665216278475e-05, "loss": 0.3901, "step": 8383 }, { "epoch": 2.14592, "grad_norm": 1.609375, "learning_rate": 1.4239399368654551e-05, "loss": 0.3962, "step": 8384 }, { "epoch": 2.146176, "grad_norm": 1.703125, "learning_rate": 1.423513352103063e-05, "loss": 0.3931, "step": 8385 }, { "epoch": 2.146432, "grad_norm": 1.8125, "learning_rate": 1.4230867673406707e-05, "loss": 0.3947, "step": 8386 }, { "epoch": 2.146688, "grad_norm": 1.7578125, "learning_rate": 1.4226601825782784e-05, "loss": 0.4021, "step": 8387 }, { "epoch": 2.146944, "grad_norm": 1.859375, "learning_rate": 1.422233597815886e-05, "loss": 0.4375, "step": 8388 }, { "epoch": 2.1471999999999998, "grad_norm": 1.6796875, "learning_rate": 1.4218070130534938e-05, "loss": 0.4258, "step": 8389 }, { "epoch": 2.147456, "grad_norm": 1.71875, "learning_rate": 1.4213804282911014e-05, "loss": 0.4015, "step": 8390 }, { "epoch": 2.147712, "grad_norm": 1.765625, "learning_rate": 1.4209538435287093e-05, "loss": 0.4152, "step": 8391 }, { "epoch": 2.147968, "grad_norm": 1.7109375, "learning_rate": 1.4205272587663167e-05, "loss": 0.4114, "step": 8392 }, { "epoch": 2.148224, "grad_norm": 1.84375, "learning_rate": 1.4201006740039247e-05, "loss": 0.4664, "step": 8393 }, { "epoch": 2.14848, "grad_norm": 1.8515625, "learning_rate": 1.4196740892415323e-05, "loss": 0.4434, "step": 8394 }, { "epoch": 2.148736, "grad_norm": 1.7265625, "learning_rate": 1.41924750447914e-05, "loss": 0.4105, "step": 8395 }, { "epoch": 2.148992, "grad_norm": 1.8984375, "learning_rate": 1.418820919716748e-05, "loss": 0.4276, "step": 8396 }, { "epoch": 2.149248, "grad_norm": 1.78125, "learning_rate": 1.4183943349543554e-05, "loss": 0.4044, "step": 8397 }, { "epoch": 2.149504, "grad_norm": 1.8046875, "learning_rate": 1.4179677501919633e-05, "loss": 0.4218, "step": 8398 }, { "epoch": 2.14976, "grad_norm": 1.8125, "learning_rate": 1.417541165429571e-05, "loss": 0.4267, "step": 8399 }, { "epoch": 2.150016, "grad_norm": 1.7890625, "learning_rate": 1.4171145806671787e-05, "loss": 0.426, "step": 8400 }, { "epoch": 2.150272, "grad_norm": 1.8203125, "learning_rate": 1.4166879959047863e-05, "loss": 0.3877, "step": 8401 }, { "epoch": 2.150528, "grad_norm": 1.8046875, "learning_rate": 1.416261411142394e-05, "loss": 0.4346, "step": 8402 }, { "epoch": 2.150784, "grad_norm": 1.921875, "learning_rate": 1.4158348263800017e-05, "loss": 0.468, "step": 8403 }, { "epoch": 2.15104, "grad_norm": 1.8125, "learning_rate": 1.4154082416176096e-05, "loss": 0.4472, "step": 8404 }, { "epoch": 2.151296, "grad_norm": 1.8828125, "learning_rate": 1.4149816568552172e-05, "loss": 0.4226, "step": 8405 }, { "epoch": 2.151552, "grad_norm": 1.6171875, "learning_rate": 1.414555072092825e-05, "loss": 0.4338, "step": 8406 }, { "epoch": 2.151808, "grad_norm": 1.8671875, "learning_rate": 1.4141284873304325e-05, "loss": 0.4366, "step": 8407 }, { "epoch": 2.152064, "grad_norm": 1.9609375, "learning_rate": 1.4137019025680403e-05, "loss": 0.4, "step": 8408 }, { "epoch": 2.15232, "grad_norm": 1.875, "learning_rate": 1.4132753178056479e-05, "loss": 0.4516, "step": 8409 }, { "epoch": 2.152576, "grad_norm": 1.90625, "learning_rate": 1.4128487330432558e-05, "loss": 0.4352, "step": 8410 }, { "epoch": 2.152832, "grad_norm": 1.6640625, "learning_rate": 1.4124221482808636e-05, "loss": 0.4041, "step": 8411 }, { "epoch": 2.153088, "grad_norm": 1.8671875, "learning_rate": 1.4119955635184712e-05, "loss": 0.4055, "step": 8412 }, { "epoch": 2.153344, "grad_norm": 1.8515625, "learning_rate": 1.411568978756079e-05, "loss": 0.424, "step": 8413 }, { "epoch": 2.1536, "grad_norm": 1.8671875, "learning_rate": 1.4111423939936866e-05, "loss": 0.3884, "step": 8414 }, { "epoch": 2.153856, "grad_norm": 1.8671875, "learning_rate": 1.4107158092312945e-05, "loss": 0.4135, "step": 8415 }, { "epoch": 2.154112, "grad_norm": 1.953125, "learning_rate": 1.410289224468902e-05, "loss": 0.4133, "step": 8416 }, { "epoch": 2.154368, "grad_norm": 1.734375, "learning_rate": 1.4098626397065099e-05, "loss": 0.4148, "step": 8417 }, { "epoch": 2.154624, "grad_norm": 1.9453125, "learning_rate": 1.4094360549441175e-05, "loss": 0.4204, "step": 8418 }, { "epoch": 2.15488, "grad_norm": 1.78125, "learning_rate": 1.4090094701817252e-05, "loss": 0.4052, "step": 8419 }, { "epoch": 2.155136, "grad_norm": 1.7578125, "learning_rate": 1.4085828854193328e-05, "loss": 0.4411, "step": 8420 }, { "epoch": 2.155392, "grad_norm": 1.9375, "learning_rate": 1.4081563006569406e-05, "loss": 0.4043, "step": 8421 }, { "epoch": 2.1556480000000002, "grad_norm": 1.921875, "learning_rate": 1.4077297158945482e-05, "loss": 0.4276, "step": 8422 }, { "epoch": 2.155904, "grad_norm": 1.8515625, "learning_rate": 1.4073031311321561e-05, "loss": 0.4309, "step": 8423 }, { "epoch": 2.15616, "grad_norm": 1.7890625, "learning_rate": 1.4068765463697635e-05, "loss": 0.4542, "step": 8424 }, { "epoch": 2.156416, "grad_norm": 1.875, "learning_rate": 1.4064499616073715e-05, "loss": 0.4584, "step": 8425 }, { "epoch": 2.156672, "grad_norm": 1.8515625, "learning_rate": 1.406023376844979e-05, "loss": 0.4396, "step": 8426 }, { "epoch": 2.156928, "grad_norm": 1.9296875, "learning_rate": 1.4055967920825868e-05, "loss": 0.4452, "step": 8427 }, { "epoch": 2.157184, "grad_norm": 1.75, "learning_rate": 1.4051702073201948e-05, "loss": 0.4279, "step": 8428 }, { "epoch": 2.15744, "grad_norm": 1.828125, "learning_rate": 1.4047436225578022e-05, "loss": 0.438, "step": 8429 }, { "epoch": 2.157696, "grad_norm": 1.8203125, "learning_rate": 1.4043170377954101e-05, "loss": 0.4356, "step": 8430 }, { "epoch": 2.157952, "grad_norm": 1.7734375, "learning_rate": 1.4038904530330177e-05, "loss": 0.4255, "step": 8431 }, { "epoch": 2.158208, "grad_norm": 1.8984375, "learning_rate": 1.4034638682706255e-05, "loss": 0.4306, "step": 8432 }, { "epoch": 2.158464, "grad_norm": 1.96875, "learning_rate": 1.4030372835082331e-05, "loss": 0.4654, "step": 8433 }, { "epoch": 2.15872, "grad_norm": 1.875, "learning_rate": 1.4026106987458409e-05, "loss": 0.4074, "step": 8434 }, { "epoch": 2.158976, "grad_norm": 1.8984375, "learning_rate": 1.4021841139834485e-05, "loss": 0.4265, "step": 8435 }, { "epoch": 2.159232, "grad_norm": 1.84375, "learning_rate": 1.4017575292210564e-05, "loss": 0.3945, "step": 8436 }, { "epoch": 2.159488, "grad_norm": 1.734375, "learning_rate": 1.401330944458664e-05, "loss": 0.4085, "step": 8437 }, { "epoch": 2.159744, "grad_norm": 1.765625, "learning_rate": 1.4009043596962718e-05, "loss": 0.4272, "step": 8438 }, { "epoch": 2.16, "grad_norm": 1.984375, "learning_rate": 1.4004777749338793e-05, "loss": 0.4249, "step": 8439 }, { "epoch": 2.160256, "grad_norm": 1.8671875, "learning_rate": 1.4000511901714871e-05, "loss": 0.3986, "step": 8440 }, { "epoch": 2.1605119999999998, "grad_norm": 1.9453125, "learning_rate": 1.3996246054090947e-05, "loss": 0.4294, "step": 8441 }, { "epoch": 2.160768, "grad_norm": 1.828125, "learning_rate": 1.3991980206467026e-05, "loss": 0.4168, "step": 8442 }, { "epoch": 2.161024, "grad_norm": 1.7265625, "learning_rate": 1.39877143588431e-05, "loss": 0.3894, "step": 8443 }, { "epoch": 2.16128, "grad_norm": 1.859375, "learning_rate": 1.398344851121918e-05, "loss": 0.3901, "step": 8444 }, { "epoch": 2.161536, "grad_norm": 1.9609375, "learning_rate": 1.3979182663595258e-05, "loss": 0.4235, "step": 8445 }, { "epoch": 2.161792, "grad_norm": 1.9765625, "learning_rate": 1.3974916815971334e-05, "loss": 0.4157, "step": 8446 }, { "epoch": 2.162048, "grad_norm": 1.8671875, "learning_rate": 1.3970650968347413e-05, "loss": 0.4512, "step": 8447 }, { "epoch": 2.162304, "grad_norm": 1.890625, "learning_rate": 1.3966385120723487e-05, "loss": 0.4532, "step": 8448 }, { "epoch": 2.16256, "grad_norm": 1.78125, "learning_rate": 1.3962119273099567e-05, "loss": 0.4744, "step": 8449 }, { "epoch": 2.162816, "grad_norm": 1.796875, "learning_rate": 1.3957853425475643e-05, "loss": 0.4345, "step": 8450 }, { "epoch": 2.163072, "grad_norm": 1.7734375, "learning_rate": 1.395358757785172e-05, "loss": 0.3784, "step": 8451 }, { "epoch": 2.163328, "grad_norm": 1.734375, "learning_rate": 1.3949321730227796e-05, "loss": 0.4179, "step": 8452 }, { "epoch": 2.163584, "grad_norm": 1.8203125, "learning_rate": 1.3945055882603874e-05, "loss": 0.4022, "step": 8453 }, { "epoch": 2.16384, "grad_norm": 1.8671875, "learning_rate": 1.394079003497995e-05, "loss": 0.4184, "step": 8454 }, { "epoch": 2.164096, "grad_norm": 1.890625, "learning_rate": 1.393652418735603e-05, "loss": 0.4279, "step": 8455 }, { "epoch": 2.164352, "grad_norm": 1.8125, "learning_rate": 1.3932258339732105e-05, "loss": 0.4749, "step": 8456 }, { "epoch": 2.164608, "grad_norm": 1.7890625, "learning_rate": 1.3927992492108183e-05, "loss": 0.4426, "step": 8457 }, { "epoch": 2.164864, "grad_norm": 1.8203125, "learning_rate": 1.3923726644484259e-05, "loss": 0.4229, "step": 8458 }, { "epoch": 2.16512, "grad_norm": 1.8203125, "learning_rate": 1.3919460796860336e-05, "loss": 0.4008, "step": 8459 }, { "epoch": 2.165376, "grad_norm": 1.828125, "learning_rate": 1.3915194949236416e-05, "loss": 0.4208, "step": 8460 }, { "epoch": 2.165632, "grad_norm": 1.734375, "learning_rate": 1.3910929101612492e-05, "loss": 0.4556, "step": 8461 }, { "epoch": 2.165888, "grad_norm": 1.8359375, "learning_rate": 1.390666325398857e-05, "loss": 0.4412, "step": 8462 }, { "epoch": 2.166144, "grad_norm": 1.671875, "learning_rate": 1.3902397406364645e-05, "loss": 0.4267, "step": 8463 }, { "epoch": 2.1664, "grad_norm": 1.8984375, "learning_rate": 1.3898131558740723e-05, "loss": 0.3989, "step": 8464 }, { "epoch": 2.166656, "grad_norm": 1.7890625, "learning_rate": 1.3893865711116799e-05, "loss": 0.4176, "step": 8465 }, { "epoch": 2.166912, "grad_norm": 1.8125, "learning_rate": 1.3889599863492878e-05, "loss": 0.4285, "step": 8466 }, { "epoch": 2.167168, "grad_norm": 1.765625, "learning_rate": 1.3885334015868953e-05, "loss": 0.4055, "step": 8467 }, { "epoch": 2.167424, "grad_norm": 1.765625, "learning_rate": 1.3881068168245032e-05, "loss": 0.4586, "step": 8468 }, { "epoch": 2.16768, "grad_norm": 1.7109375, "learning_rate": 1.3876802320621108e-05, "loss": 0.4342, "step": 8469 }, { "epoch": 2.167936, "grad_norm": 1.765625, "learning_rate": 1.3872536472997186e-05, "loss": 0.413, "step": 8470 }, { "epoch": 2.168192, "grad_norm": 1.8359375, "learning_rate": 1.3868270625373261e-05, "loss": 0.4189, "step": 8471 }, { "epoch": 2.168448, "grad_norm": 1.890625, "learning_rate": 1.3864004777749339e-05, "loss": 0.4087, "step": 8472 }, { "epoch": 2.168704, "grad_norm": 1.71875, "learning_rate": 1.3859738930125415e-05, "loss": 0.4426, "step": 8473 }, { "epoch": 2.16896, "grad_norm": 1.796875, "learning_rate": 1.3855473082501494e-05, "loss": 0.445, "step": 8474 }, { "epoch": 2.169216, "grad_norm": 1.8359375, "learning_rate": 1.3851207234877569e-05, "loss": 0.433, "step": 8475 }, { "epoch": 2.169472, "grad_norm": 1.8359375, "learning_rate": 1.3846941387253648e-05, "loss": 0.4124, "step": 8476 }, { "epoch": 2.169728, "grad_norm": 1.984375, "learning_rate": 1.3842675539629726e-05, "loss": 0.4069, "step": 8477 }, { "epoch": 2.169984, "grad_norm": 1.90625, "learning_rate": 1.3838409692005802e-05, "loss": 0.4652, "step": 8478 }, { "epoch": 2.17024, "grad_norm": 1.8203125, "learning_rate": 1.3834143844381881e-05, "loss": 0.4082, "step": 8479 }, { "epoch": 2.170496, "grad_norm": 1.828125, "learning_rate": 1.3829877996757955e-05, "loss": 0.4154, "step": 8480 }, { "epoch": 2.170752, "grad_norm": 1.9453125, "learning_rate": 1.3825612149134035e-05, "loss": 0.4237, "step": 8481 }, { "epoch": 2.171008, "grad_norm": 1.84375, "learning_rate": 1.382134630151011e-05, "loss": 0.4156, "step": 8482 }, { "epoch": 2.171264, "grad_norm": 1.84375, "learning_rate": 1.3817080453886188e-05, "loss": 0.4238, "step": 8483 }, { "epoch": 2.17152, "grad_norm": 1.8203125, "learning_rate": 1.3812814606262264e-05, "loss": 0.4059, "step": 8484 }, { "epoch": 2.171776, "grad_norm": 1.84375, "learning_rate": 1.3808548758638344e-05, "loss": 0.3924, "step": 8485 }, { "epoch": 2.172032, "grad_norm": 1.8203125, "learning_rate": 1.3804282911014418e-05, "loss": 0.4138, "step": 8486 }, { "epoch": 2.172288, "grad_norm": 2.03125, "learning_rate": 1.3800017063390497e-05, "loss": 0.4233, "step": 8487 }, { "epoch": 2.172544, "grad_norm": 1.984375, "learning_rate": 1.3795751215766573e-05, "loss": 0.4426, "step": 8488 }, { "epoch": 2.1728, "grad_norm": 1.8828125, "learning_rate": 1.379148536814265e-05, "loss": 0.4131, "step": 8489 }, { "epoch": 2.173056, "grad_norm": 1.828125, "learning_rate": 1.3787219520518727e-05, "loss": 0.4619, "step": 8490 }, { "epoch": 2.173312, "grad_norm": 1.828125, "learning_rate": 1.3782953672894804e-05, "loss": 0.4144, "step": 8491 }, { "epoch": 2.173568, "grad_norm": 1.9296875, "learning_rate": 1.377868782527088e-05, "loss": 0.4183, "step": 8492 }, { "epoch": 2.173824, "grad_norm": 1.90625, "learning_rate": 1.377442197764696e-05, "loss": 0.381, "step": 8493 }, { "epoch": 2.17408, "grad_norm": 1.6953125, "learning_rate": 1.3770156130023037e-05, "loss": 0.4308, "step": 8494 }, { "epoch": 2.174336, "grad_norm": 1.8046875, "learning_rate": 1.3765890282399113e-05, "loss": 0.3951, "step": 8495 }, { "epoch": 2.174592, "grad_norm": 1.75, "learning_rate": 1.3761624434775191e-05, "loss": 0.3832, "step": 8496 }, { "epoch": 2.174848, "grad_norm": 1.9453125, "learning_rate": 1.3757358587151267e-05, "loss": 0.4384, "step": 8497 }, { "epoch": 2.175104, "grad_norm": 1.8515625, "learning_rate": 1.3753092739527346e-05, "loss": 0.3923, "step": 8498 }, { "epoch": 2.17536, "grad_norm": 1.796875, "learning_rate": 1.374882689190342e-05, "loss": 0.4042, "step": 8499 }, { "epoch": 2.1756159999999998, "grad_norm": 1.7578125, "learning_rate": 1.37445610442795e-05, "loss": 0.4183, "step": 8500 }, { "epoch": 2.175872, "grad_norm": 1.796875, "learning_rate": 1.3740295196655576e-05, "loss": 0.4398, "step": 8501 }, { "epoch": 2.176128, "grad_norm": 1.859375, "learning_rate": 1.3736029349031654e-05, "loss": 0.4203, "step": 8502 }, { "epoch": 2.176384, "grad_norm": 1.9765625, "learning_rate": 1.373176350140773e-05, "loss": 0.3976, "step": 8503 }, { "epoch": 2.17664, "grad_norm": 1.8515625, "learning_rate": 1.3727497653783807e-05, "loss": 0.4667, "step": 8504 }, { "epoch": 2.176896, "grad_norm": 2.0, "learning_rate": 1.3723231806159883e-05, "loss": 0.4398, "step": 8505 }, { "epoch": 2.177152, "grad_norm": 1.8359375, "learning_rate": 1.3718965958535962e-05, "loss": 0.3894, "step": 8506 }, { "epoch": 2.177408, "grad_norm": 1.828125, "learning_rate": 1.3714700110912038e-05, "loss": 0.4359, "step": 8507 }, { "epoch": 2.177664, "grad_norm": 1.8046875, "learning_rate": 1.3710434263288116e-05, "loss": 0.402, "step": 8508 }, { "epoch": 2.17792, "grad_norm": 1.8515625, "learning_rate": 1.3706168415664194e-05, "loss": 0.4307, "step": 8509 }, { "epoch": 2.178176, "grad_norm": 1.8828125, "learning_rate": 1.370190256804027e-05, "loss": 0.4642, "step": 8510 }, { "epoch": 2.178432, "grad_norm": 1.9765625, "learning_rate": 1.3697636720416349e-05, "loss": 0.4184, "step": 8511 }, { "epoch": 2.178688, "grad_norm": 1.8671875, "learning_rate": 1.3693370872792425e-05, "loss": 0.425, "step": 8512 }, { "epoch": 2.178944, "grad_norm": 1.8984375, "learning_rate": 1.3689105025168503e-05, "loss": 0.3819, "step": 8513 }, { "epoch": 2.1792, "grad_norm": 1.9296875, "learning_rate": 1.3684839177544579e-05, "loss": 0.3987, "step": 8514 }, { "epoch": 2.179456, "grad_norm": 1.8046875, "learning_rate": 1.3680573329920656e-05, "loss": 0.4031, "step": 8515 }, { "epoch": 2.179712, "grad_norm": 1.7421875, "learning_rate": 1.3676307482296732e-05, "loss": 0.4064, "step": 8516 }, { "epoch": 2.179968, "grad_norm": 1.7734375, "learning_rate": 1.3672041634672812e-05, "loss": 0.4243, "step": 8517 }, { "epoch": 2.180224, "grad_norm": 1.8515625, "learning_rate": 1.3667775787048886e-05, "loss": 0.396, "step": 8518 }, { "epoch": 2.18048, "grad_norm": 1.6953125, "learning_rate": 1.3663509939424965e-05, "loss": 0.4442, "step": 8519 }, { "epoch": 2.180736, "grad_norm": 1.7890625, "learning_rate": 1.3659244091801041e-05, "loss": 0.438, "step": 8520 }, { "epoch": 2.180992, "grad_norm": 1.9296875, "learning_rate": 1.3654978244177119e-05, "loss": 0.4506, "step": 8521 }, { "epoch": 2.181248, "grad_norm": 1.828125, "learning_rate": 1.3650712396553195e-05, "loss": 0.4143, "step": 8522 }, { "epoch": 2.181504, "grad_norm": 1.78125, "learning_rate": 1.3646446548929272e-05, "loss": 0.404, "step": 8523 }, { "epoch": 2.18176, "grad_norm": 1.8359375, "learning_rate": 1.3642180701305348e-05, "loss": 0.4442, "step": 8524 }, { "epoch": 2.182016, "grad_norm": 1.8125, "learning_rate": 1.3637914853681428e-05, "loss": 0.3766, "step": 8525 }, { "epoch": 2.182272, "grad_norm": 1.90625, "learning_rate": 1.3633649006057505e-05, "loss": 0.4325, "step": 8526 }, { "epoch": 2.182528, "grad_norm": 1.90625, "learning_rate": 1.3629383158433581e-05, "loss": 0.413, "step": 8527 }, { "epoch": 2.182784, "grad_norm": 1.7265625, "learning_rate": 1.3625117310809659e-05, "loss": 0.4115, "step": 8528 }, { "epoch": 2.18304, "grad_norm": 1.859375, "learning_rate": 1.3620851463185735e-05, "loss": 0.4197, "step": 8529 }, { "epoch": 2.183296, "grad_norm": 1.8828125, "learning_rate": 1.3616585615561814e-05, "loss": 0.4573, "step": 8530 }, { "epoch": 2.183552, "grad_norm": 1.765625, "learning_rate": 1.361231976793789e-05, "loss": 0.4018, "step": 8531 }, { "epoch": 2.183808, "grad_norm": 1.7890625, "learning_rate": 1.3608053920313968e-05, "loss": 0.427, "step": 8532 }, { "epoch": 2.1840640000000002, "grad_norm": 1.8046875, "learning_rate": 1.3603788072690044e-05, "loss": 0.4294, "step": 8533 }, { "epoch": 2.18432, "grad_norm": 1.984375, "learning_rate": 1.3599522225066122e-05, "loss": 0.4308, "step": 8534 }, { "epoch": 2.184576, "grad_norm": 1.8515625, "learning_rate": 1.3595256377442197e-05, "loss": 0.4048, "step": 8535 }, { "epoch": 2.184832, "grad_norm": 1.9609375, "learning_rate": 1.3590990529818277e-05, "loss": 0.4438, "step": 8536 }, { "epoch": 2.185088, "grad_norm": 1.7265625, "learning_rate": 1.3586724682194351e-05, "loss": 0.3946, "step": 8537 }, { "epoch": 2.185344, "grad_norm": 1.7578125, "learning_rate": 1.358245883457043e-05, "loss": 0.4605, "step": 8538 }, { "epoch": 2.1856, "grad_norm": 1.78125, "learning_rate": 1.3578192986946506e-05, "loss": 0.4389, "step": 8539 }, { "epoch": 2.185856, "grad_norm": 1.8203125, "learning_rate": 1.3573927139322584e-05, "loss": 0.4026, "step": 8540 }, { "epoch": 2.186112, "grad_norm": 1.90625, "learning_rate": 1.356966129169866e-05, "loss": 0.4219, "step": 8541 }, { "epoch": 2.186368, "grad_norm": 1.8125, "learning_rate": 1.3565395444074738e-05, "loss": 0.4065, "step": 8542 }, { "epoch": 2.186624, "grad_norm": 1.9375, "learning_rate": 1.3561129596450817e-05, "loss": 0.3983, "step": 8543 }, { "epoch": 2.18688, "grad_norm": 1.671875, "learning_rate": 1.3556863748826893e-05, "loss": 0.4459, "step": 8544 }, { "epoch": 2.187136, "grad_norm": 1.7734375, "learning_rate": 1.355259790120297e-05, "loss": 0.4367, "step": 8545 }, { "epoch": 2.187392, "grad_norm": 1.828125, "learning_rate": 1.3548332053579047e-05, "loss": 0.4802, "step": 8546 }, { "epoch": 2.187648, "grad_norm": 1.7890625, "learning_rate": 1.3544066205955124e-05, "loss": 0.4346, "step": 8547 }, { "epoch": 2.187904, "grad_norm": 1.859375, "learning_rate": 1.35398003583312e-05, "loss": 0.3949, "step": 8548 }, { "epoch": 2.18816, "grad_norm": 1.9453125, "learning_rate": 1.353553451070728e-05, "loss": 0.4415, "step": 8549 }, { "epoch": 2.188416, "grad_norm": 1.921875, "learning_rate": 1.3531268663083354e-05, "loss": 0.4316, "step": 8550 }, { "epoch": 2.188672, "grad_norm": 1.9453125, "learning_rate": 1.3527002815459433e-05, "loss": 0.4146, "step": 8551 }, { "epoch": 2.188928, "grad_norm": 1.796875, "learning_rate": 1.352273696783551e-05, "loss": 0.4091, "step": 8552 }, { "epoch": 2.189184, "grad_norm": 1.765625, "learning_rate": 1.3518471120211587e-05, "loss": 0.4368, "step": 8553 }, { "epoch": 2.18944, "grad_norm": 1.8515625, "learning_rate": 1.3514205272587663e-05, "loss": 0.4522, "step": 8554 }, { "epoch": 2.189696, "grad_norm": 1.6875, "learning_rate": 1.350993942496374e-05, "loss": 0.4576, "step": 8555 }, { "epoch": 2.189952, "grad_norm": 1.84375, "learning_rate": 1.3505673577339816e-05, "loss": 0.4342, "step": 8556 }, { "epoch": 2.190208, "grad_norm": 1.859375, "learning_rate": 1.3501407729715896e-05, "loss": 0.4451, "step": 8557 }, { "epoch": 2.190464, "grad_norm": 1.8671875, "learning_rate": 1.3497141882091972e-05, "loss": 0.4712, "step": 8558 }, { "epoch": 2.19072, "grad_norm": 1.8203125, "learning_rate": 1.349287603446805e-05, "loss": 0.4377, "step": 8559 }, { "epoch": 2.190976, "grad_norm": 1.953125, "learning_rate": 1.3488610186844127e-05, "loss": 0.3925, "step": 8560 }, { "epoch": 2.191232, "grad_norm": 1.84375, "learning_rate": 1.3484344339220203e-05, "loss": 0.3988, "step": 8561 }, { "epoch": 2.191488, "grad_norm": 1.859375, "learning_rate": 1.3480078491596282e-05, "loss": 0.4417, "step": 8562 }, { "epoch": 2.191744, "grad_norm": 1.8046875, "learning_rate": 1.3475812643972358e-05, "loss": 0.4123, "step": 8563 }, { "epoch": 2.192, "grad_norm": 1.90625, "learning_rate": 1.3471546796348436e-05, "loss": 0.4096, "step": 8564 }, { "epoch": 2.192256, "grad_norm": 1.703125, "learning_rate": 1.3467280948724512e-05, "loss": 0.4352, "step": 8565 }, { "epoch": 2.192512, "grad_norm": 1.9296875, "learning_rate": 1.346301510110059e-05, "loss": 0.4206, "step": 8566 }, { "epoch": 2.192768, "grad_norm": 1.7265625, "learning_rate": 1.3458749253476666e-05, "loss": 0.439, "step": 8567 }, { "epoch": 2.193024, "grad_norm": 1.9140625, "learning_rate": 1.3454483405852745e-05, "loss": 0.4019, "step": 8568 }, { "epoch": 2.19328, "grad_norm": 1.703125, "learning_rate": 1.3450217558228819e-05, "loss": 0.451, "step": 8569 }, { "epoch": 2.193536, "grad_norm": 1.7578125, "learning_rate": 1.3445951710604898e-05, "loss": 0.427, "step": 8570 }, { "epoch": 2.193792, "grad_norm": 1.7578125, "learning_rate": 1.3441685862980974e-05, "loss": 0.4321, "step": 8571 }, { "epoch": 2.194048, "grad_norm": 1.828125, "learning_rate": 1.3437420015357052e-05, "loss": 0.4339, "step": 8572 }, { "epoch": 2.194304, "grad_norm": 1.796875, "learning_rate": 1.3433154167733128e-05, "loss": 0.4333, "step": 8573 }, { "epoch": 2.19456, "grad_norm": 1.921875, "learning_rate": 1.3428888320109206e-05, "loss": 0.4788, "step": 8574 }, { "epoch": 2.194816, "grad_norm": 1.875, "learning_rate": 1.3424622472485285e-05, "loss": 0.4282, "step": 8575 }, { "epoch": 2.195072, "grad_norm": 1.8671875, "learning_rate": 1.3420356624861361e-05, "loss": 0.4599, "step": 8576 }, { "epoch": 2.195328, "grad_norm": 1.8125, "learning_rate": 1.3416090777237439e-05, "loss": 0.4278, "step": 8577 }, { "epoch": 2.195584, "grad_norm": 1.8125, "learning_rate": 1.3411824929613515e-05, "loss": 0.4283, "step": 8578 }, { "epoch": 2.19584, "grad_norm": 1.9453125, "learning_rate": 1.3407559081989592e-05, "loss": 0.4322, "step": 8579 }, { "epoch": 2.196096, "grad_norm": 1.828125, "learning_rate": 1.3403293234365668e-05, "loss": 0.4304, "step": 8580 }, { "epoch": 2.196352, "grad_norm": 1.796875, "learning_rate": 1.3399027386741748e-05, "loss": 0.4197, "step": 8581 }, { "epoch": 2.196608, "grad_norm": 1.875, "learning_rate": 1.3394761539117824e-05, "loss": 0.4139, "step": 8582 }, { "epoch": 2.196864, "grad_norm": 1.78125, "learning_rate": 1.3390495691493901e-05, "loss": 0.4219, "step": 8583 }, { "epoch": 2.19712, "grad_norm": 1.703125, "learning_rate": 1.3386229843869977e-05, "loss": 0.4175, "step": 8584 }, { "epoch": 2.197376, "grad_norm": 1.8515625, "learning_rate": 1.3381963996246055e-05, "loss": 0.4356, "step": 8585 }, { "epoch": 2.197632, "grad_norm": 1.7578125, "learning_rate": 1.337769814862213e-05, "loss": 0.4281, "step": 8586 }, { "epoch": 2.197888, "grad_norm": 1.9375, "learning_rate": 1.337343230099821e-05, "loss": 0.4127, "step": 8587 }, { "epoch": 2.198144, "grad_norm": 1.9140625, "learning_rate": 1.3369166453374284e-05, "loss": 0.4305, "step": 8588 }, { "epoch": 2.1984, "grad_norm": 1.84375, "learning_rate": 1.3364900605750364e-05, "loss": 0.44, "step": 8589 }, { "epoch": 2.198656, "grad_norm": 1.7109375, "learning_rate": 1.336063475812644e-05, "loss": 0.4324, "step": 8590 }, { "epoch": 2.198912, "grad_norm": 1.6171875, "learning_rate": 1.3356368910502517e-05, "loss": 0.4117, "step": 8591 }, { "epoch": 2.1991680000000002, "grad_norm": 1.8125, "learning_rate": 1.3352103062878597e-05, "loss": 0.4245, "step": 8592 }, { "epoch": 2.199424, "grad_norm": 1.8671875, "learning_rate": 1.3347837215254671e-05, "loss": 0.4328, "step": 8593 }, { "epoch": 2.19968, "grad_norm": 1.921875, "learning_rate": 1.334357136763075e-05, "loss": 0.4174, "step": 8594 }, { "epoch": 2.199936, "grad_norm": 1.84375, "learning_rate": 1.3339305520006826e-05, "loss": 0.397, "step": 8595 }, { "epoch": 2.200192, "grad_norm": 1.765625, "learning_rate": 1.3335039672382904e-05, "loss": 0.4103, "step": 8596 }, { "epoch": 2.200448, "grad_norm": 1.796875, "learning_rate": 1.333077382475898e-05, "loss": 0.4003, "step": 8597 }, { "epoch": 2.200704, "grad_norm": 1.875, "learning_rate": 1.3326507977135058e-05, "loss": 0.4427, "step": 8598 }, { "epoch": 2.20096, "grad_norm": 1.8515625, "learning_rate": 1.3322242129511134e-05, "loss": 0.4023, "step": 8599 }, { "epoch": 2.201216, "grad_norm": 1.984375, "learning_rate": 1.3317976281887213e-05, "loss": 0.4033, "step": 8600 }, { "epoch": 2.201472, "grad_norm": 1.65625, "learning_rate": 1.3313710434263287e-05, "loss": 0.3994, "step": 8601 }, { "epoch": 2.201728, "grad_norm": 1.7890625, "learning_rate": 1.3309444586639366e-05, "loss": 0.4608, "step": 8602 }, { "epoch": 2.201984, "grad_norm": 1.8984375, "learning_rate": 1.3305178739015442e-05, "loss": 0.399, "step": 8603 }, { "epoch": 2.20224, "grad_norm": 1.7734375, "learning_rate": 1.330091289139152e-05, "loss": 0.4305, "step": 8604 }, { "epoch": 2.202496, "grad_norm": 1.734375, "learning_rate": 1.3296647043767596e-05, "loss": 0.4307, "step": 8605 }, { "epoch": 2.202752, "grad_norm": 1.9375, "learning_rate": 1.3292381196143674e-05, "loss": 0.4238, "step": 8606 }, { "epoch": 2.203008, "grad_norm": 1.7734375, "learning_rate": 1.328811534851975e-05, "loss": 0.4366, "step": 8607 }, { "epoch": 2.203264, "grad_norm": 1.8984375, "learning_rate": 1.3283849500895829e-05, "loss": 0.4425, "step": 8608 }, { "epoch": 2.20352, "grad_norm": 1.8203125, "learning_rate": 1.3279583653271907e-05, "loss": 0.3807, "step": 8609 }, { "epoch": 2.203776, "grad_norm": 1.9765625, "learning_rate": 1.3275317805647983e-05, "loss": 0.4275, "step": 8610 }, { "epoch": 2.2040319999999998, "grad_norm": 1.84375, "learning_rate": 1.327105195802406e-05, "loss": 0.4539, "step": 8611 }, { "epoch": 2.204288, "grad_norm": 1.6015625, "learning_rate": 1.3266786110400136e-05, "loss": 0.4333, "step": 8612 }, { "epoch": 2.204544, "grad_norm": 1.7890625, "learning_rate": 1.3262520262776216e-05, "loss": 0.4017, "step": 8613 }, { "epoch": 2.2048, "grad_norm": 1.8125, "learning_rate": 1.3258254415152292e-05, "loss": 0.4618, "step": 8614 }, { "epoch": 2.205056, "grad_norm": 1.7578125, "learning_rate": 1.325398856752837e-05, "loss": 0.3992, "step": 8615 }, { "epoch": 2.205312, "grad_norm": 1.96875, "learning_rate": 1.3249722719904445e-05, "loss": 0.443, "step": 8616 }, { "epoch": 2.205568, "grad_norm": 1.765625, "learning_rate": 1.3245456872280523e-05, "loss": 0.4399, "step": 8617 }, { "epoch": 2.205824, "grad_norm": 1.765625, "learning_rate": 1.3241191024656599e-05, "loss": 0.4375, "step": 8618 }, { "epoch": 2.20608, "grad_norm": 1.8515625, "learning_rate": 1.3236925177032678e-05, "loss": 0.3953, "step": 8619 }, { "epoch": 2.206336, "grad_norm": 1.859375, "learning_rate": 1.3232659329408752e-05, "loss": 0.4393, "step": 8620 }, { "epoch": 2.206592, "grad_norm": 1.859375, "learning_rate": 1.3228393481784832e-05, "loss": 0.4228, "step": 8621 }, { "epoch": 2.206848, "grad_norm": 1.7109375, "learning_rate": 1.3224127634160908e-05, "loss": 0.4157, "step": 8622 }, { "epoch": 2.207104, "grad_norm": 2.0, "learning_rate": 1.3219861786536985e-05, "loss": 0.4074, "step": 8623 }, { "epoch": 2.20736, "grad_norm": 1.8046875, "learning_rate": 1.3215595938913065e-05, "loss": 0.4343, "step": 8624 }, { "epoch": 2.207616, "grad_norm": 1.8671875, "learning_rate": 1.3211330091289139e-05, "loss": 0.419, "step": 8625 }, { "epoch": 2.207872, "grad_norm": 1.78125, "learning_rate": 1.3207064243665218e-05, "loss": 0.4552, "step": 8626 }, { "epoch": 2.208128, "grad_norm": 1.7421875, "learning_rate": 1.3202798396041294e-05, "loss": 0.4032, "step": 8627 }, { "epoch": 2.208384, "grad_norm": 1.8046875, "learning_rate": 1.3198532548417372e-05, "loss": 0.4431, "step": 8628 }, { "epoch": 2.20864, "grad_norm": 1.84375, "learning_rate": 1.3194266700793448e-05, "loss": 0.4305, "step": 8629 }, { "epoch": 2.208896, "grad_norm": 1.890625, "learning_rate": 1.3190000853169526e-05, "loss": 0.4145, "step": 8630 }, { "epoch": 2.209152, "grad_norm": 1.890625, "learning_rate": 1.3185735005545602e-05, "loss": 0.3983, "step": 8631 }, { "epoch": 2.209408, "grad_norm": 1.59375, "learning_rate": 1.3181469157921681e-05, "loss": 0.4163, "step": 8632 }, { "epoch": 2.209664, "grad_norm": 1.6484375, "learning_rate": 1.3177203310297757e-05, "loss": 0.433, "step": 8633 }, { "epoch": 2.20992, "grad_norm": 1.8515625, "learning_rate": 1.3172937462673834e-05, "loss": 0.3754, "step": 8634 }, { "epoch": 2.210176, "grad_norm": 1.828125, "learning_rate": 1.316867161504991e-05, "loss": 0.4478, "step": 8635 }, { "epoch": 2.210432, "grad_norm": 1.84375, "learning_rate": 1.3164405767425988e-05, "loss": 0.3783, "step": 8636 }, { "epoch": 2.210688, "grad_norm": 1.953125, "learning_rate": 1.3160139919802064e-05, "loss": 0.4264, "step": 8637 }, { "epoch": 2.210944, "grad_norm": 1.7421875, "learning_rate": 1.3155874072178143e-05, "loss": 0.4264, "step": 8638 }, { "epoch": 2.2112, "grad_norm": 1.8515625, "learning_rate": 1.3151608224554218e-05, "loss": 0.395, "step": 8639 }, { "epoch": 2.211456, "grad_norm": 1.8046875, "learning_rate": 1.3147342376930297e-05, "loss": 0.4001, "step": 8640 }, { "epoch": 2.211712, "grad_norm": 1.90625, "learning_rate": 1.3143076529306375e-05, "loss": 0.415, "step": 8641 }, { "epoch": 2.211968, "grad_norm": 1.8203125, "learning_rate": 1.313881068168245e-05, "loss": 0.4314, "step": 8642 }, { "epoch": 2.212224, "grad_norm": 1.7421875, "learning_rate": 1.313454483405853e-05, "loss": 0.4036, "step": 8643 }, { "epoch": 2.2124800000000002, "grad_norm": 1.8203125, "learning_rate": 1.3130278986434604e-05, "loss": 0.4448, "step": 8644 }, { "epoch": 2.212736, "grad_norm": 1.828125, "learning_rate": 1.3126013138810684e-05, "loss": 0.3862, "step": 8645 }, { "epoch": 2.212992, "grad_norm": 1.75, "learning_rate": 1.312174729118676e-05, "loss": 0.4256, "step": 8646 }, { "epoch": 2.213248, "grad_norm": 1.7109375, "learning_rate": 1.3117481443562837e-05, "loss": 0.451, "step": 8647 }, { "epoch": 2.213504, "grad_norm": 1.7265625, "learning_rate": 1.3113215595938913e-05, "loss": 0.4404, "step": 8648 }, { "epoch": 2.21376, "grad_norm": 1.828125, "learning_rate": 1.310894974831499e-05, "loss": 0.4498, "step": 8649 }, { "epoch": 2.214016, "grad_norm": 1.8671875, "learning_rate": 1.3104683900691067e-05, "loss": 0.4337, "step": 8650 }, { "epoch": 2.214272, "grad_norm": 1.8984375, "learning_rate": 1.3100418053067146e-05, "loss": 0.4717, "step": 8651 }, { "epoch": 2.214528, "grad_norm": 1.7890625, "learning_rate": 1.309615220544322e-05, "loss": 0.4233, "step": 8652 }, { "epoch": 2.214784, "grad_norm": 1.8359375, "learning_rate": 1.30918863578193e-05, "loss": 0.4482, "step": 8653 }, { "epoch": 2.21504, "grad_norm": 1.75, "learning_rate": 1.3087620510195376e-05, "loss": 0.4197, "step": 8654 }, { "epoch": 2.215296, "grad_norm": 1.7578125, "learning_rate": 1.3083354662571453e-05, "loss": 0.4164, "step": 8655 }, { "epoch": 2.215552, "grad_norm": 1.7734375, "learning_rate": 1.307908881494753e-05, "loss": 0.4387, "step": 8656 }, { "epoch": 2.215808, "grad_norm": 1.84375, "learning_rate": 1.3074822967323607e-05, "loss": 0.3898, "step": 8657 }, { "epoch": 2.216064, "grad_norm": 1.875, "learning_rate": 1.3070557119699686e-05, "loss": 0.4309, "step": 8658 }, { "epoch": 2.21632, "grad_norm": 1.9140625, "learning_rate": 1.3066291272075762e-05, "loss": 0.4602, "step": 8659 }, { "epoch": 2.216576, "grad_norm": 1.875, "learning_rate": 1.306202542445184e-05, "loss": 0.395, "step": 8660 }, { "epoch": 2.216832, "grad_norm": 1.8515625, "learning_rate": 1.3057759576827916e-05, "loss": 0.4198, "step": 8661 }, { "epoch": 2.217088, "grad_norm": 1.8125, "learning_rate": 1.3053493729203994e-05, "loss": 0.4127, "step": 8662 }, { "epoch": 2.217344, "grad_norm": 1.9140625, "learning_rate": 1.304922788158007e-05, "loss": 0.406, "step": 8663 }, { "epoch": 2.2176, "grad_norm": 1.7578125, "learning_rate": 1.3044962033956149e-05, "loss": 0.4308, "step": 8664 }, { "epoch": 2.217856, "grad_norm": 1.8125, "learning_rate": 1.3040696186332225e-05, "loss": 0.4416, "step": 8665 }, { "epoch": 2.218112, "grad_norm": 1.7890625, "learning_rate": 1.3036430338708302e-05, "loss": 0.4176, "step": 8666 }, { "epoch": 2.218368, "grad_norm": 1.8203125, "learning_rate": 1.3032164491084378e-05, "loss": 0.4221, "step": 8667 }, { "epoch": 2.218624, "grad_norm": 1.9296875, "learning_rate": 1.3027898643460456e-05, "loss": 0.3934, "step": 8668 }, { "epoch": 2.21888, "grad_norm": 1.984375, "learning_rate": 1.3023632795836532e-05, "loss": 0.4257, "step": 8669 }, { "epoch": 2.2191359999999998, "grad_norm": 1.890625, "learning_rate": 1.3019366948212611e-05, "loss": 0.4144, "step": 8670 }, { "epoch": 2.219392, "grad_norm": 1.765625, "learning_rate": 1.3015101100588686e-05, "loss": 0.4366, "step": 8671 }, { "epoch": 2.219648, "grad_norm": 1.75, "learning_rate": 1.3010835252964765e-05, "loss": 0.4282, "step": 8672 }, { "epoch": 2.219904, "grad_norm": 1.75, "learning_rate": 1.3006569405340843e-05, "loss": 0.4484, "step": 8673 }, { "epoch": 2.22016, "grad_norm": 1.84375, "learning_rate": 1.3002303557716919e-05, "loss": 0.4288, "step": 8674 }, { "epoch": 2.220416, "grad_norm": 1.8515625, "learning_rate": 1.2998037710092998e-05, "loss": 0.436, "step": 8675 }, { "epoch": 2.220672, "grad_norm": 1.8828125, "learning_rate": 1.2993771862469072e-05, "loss": 0.458, "step": 8676 }, { "epoch": 2.220928, "grad_norm": 1.765625, "learning_rate": 1.2989506014845152e-05, "loss": 0.4178, "step": 8677 }, { "epoch": 2.221184, "grad_norm": 1.8515625, "learning_rate": 1.2985240167221228e-05, "loss": 0.4328, "step": 8678 }, { "epoch": 2.22144, "grad_norm": 1.7109375, "learning_rate": 1.2980974319597305e-05, "loss": 0.3919, "step": 8679 }, { "epoch": 2.221696, "grad_norm": 1.78125, "learning_rate": 1.2976708471973381e-05, "loss": 0.4278, "step": 8680 }, { "epoch": 2.221952, "grad_norm": 1.9296875, "learning_rate": 1.2972442624349459e-05, "loss": 0.4123, "step": 8681 }, { "epoch": 2.222208, "grad_norm": 1.8359375, "learning_rate": 1.2968176776725535e-05, "loss": 0.4154, "step": 8682 }, { "epoch": 2.222464, "grad_norm": 1.796875, "learning_rate": 1.2963910929101614e-05, "loss": 0.4841, "step": 8683 }, { "epoch": 2.22272, "grad_norm": 1.9296875, "learning_rate": 1.295964508147769e-05, "loss": 0.4367, "step": 8684 }, { "epoch": 2.222976, "grad_norm": 1.9140625, "learning_rate": 1.2955379233853768e-05, "loss": 0.4227, "step": 8685 }, { "epoch": 2.223232, "grad_norm": 1.8203125, "learning_rate": 1.2951113386229844e-05, "loss": 0.4151, "step": 8686 }, { "epoch": 2.223488, "grad_norm": 1.859375, "learning_rate": 1.2946847538605921e-05, "loss": 0.4527, "step": 8687 }, { "epoch": 2.223744, "grad_norm": 1.828125, "learning_rate": 1.2942581690981997e-05, "loss": 0.3886, "step": 8688 }, { "epoch": 2.224, "grad_norm": 1.75, "learning_rate": 1.2938315843358077e-05, "loss": 0.4143, "step": 8689 }, { "epoch": 2.224256, "grad_norm": 1.8359375, "learning_rate": 1.2934049995734154e-05, "loss": 0.4128, "step": 8690 }, { "epoch": 2.224512, "grad_norm": 1.8828125, "learning_rate": 1.292978414811023e-05, "loss": 0.4124, "step": 8691 }, { "epoch": 2.224768, "grad_norm": 1.796875, "learning_rate": 1.2925518300486308e-05, "loss": 0.4206, "step": 8692 }, { "epoch": 2.225024, "grad_norm": 1.7265625, "learning_rate": 1.2921252452862384e-05, "loss": 0.4292, "step": 8693 }, { "epoch": 2.22528, "grad_norm": 1.9375, "learning_rate": 1.2916986605238463e-05, "loss": 0.4357, "step": 8694 }, { "epoch": 2.225536, "grad_norm": 1.859375, "learning_rate": 1.2912720757614538e-05, "loss": 0.3992, "step": 8695 }, { "epoch": 2.225792, "grad_norm": 1.7265625, "learning_rate": 1.2908454909990617e-05, "loss": 0.4114, "step": 8696 }, { "epoch": 2.226048, "grad_norm": 1.8046875, "learning_rate": 1.2904189062366693e-05, "loss": 0.4528, "step": 8697 }, { "epoch": 2.226304, "grad_norm": 1.875, "learning_rate": 1.289992321474277e-05, "loss": 0.3929, "step": 8698 }, { "epoch": 2.22656, "grad_norm": 1.78125, "learning_rate": 1.2895657367118846e-05, "loss": 0.4673, "step": 8699 }, { "epoch": 2.226816, "grad_norm": 1.8515625, "learning_rate": 1.2891391519494924e-05, "loss": 0.4117, "step": 8700 }, { "epoch": 2.227072, "grad_norm": 1.8203125, "learning_rate": 1.2887125671871e-05, "loss": 0.4409, "step": 8701 }, { "epoch": 2.227328, "grad_norm": 1.7421875, "learning_rate": 1.288285982424708e-05, "loss": 0.4556, "step": 8702 }, { "epoch": 2.2275840000000002, "grad_norm": 1.75, "learning_rate": 1.2878593976623154e-05, "loss": 0.4409, "step": 8703 }, { "epoch": 2.22784, "grad_norm": 1.75, "learning_rate": 1.2874328128999233e-05, "loss": 0.4451, "step": 8704 }, { "epoch": 2.228096, "grad_norm": 1.7734375, "learning_rate": 1.2870062281375309e-05, "loss": 0.4187, "step": 8705 }, { "epoch": 2.228352, "grad_norm": 1.9140625, "learning_rate": 1.2865796433751387e-05, "loss": 0.4393, "step": 8706 }, { "epoch": 2.228608, "grad_norm": 1.7890625, "learning_rate": 1.2861530586127466e-05, "loss": 0.4076, "step": 8707 }, { "epoch": 2.228864, "grad_norm": 1.9921875, "learning_rate": 1.285726473850354e-05, "loss": 0.4365, "step": 8708 }, { "epoch": 2.22912, "grad_norm": 1.8203125, "learning_rate": 1.285299889087962e-05, "loss": 0.4138, "step": 8709 }, { "epoch": 2.229376, "grad_norm": 1.84375, "learning_rate": 1.2848733043255696e-05, "loss": 0.4528, "step": 8710 }, { "epoch": 2.229632, "grad_norm": 1.859375, "learning_rate": 1.2844467195631773e-05, "loss": 0.4209, "step": 8711 }, { "epoch": 2.229888, "grad_norm": 1.78125, "learning_rate": 1.284020134800785e-05, "loss": 0.3836, "step": 8712 }, { "epoch": 2.230144, "grad_norm": 1.7890625, "learning_rate": 1.2835935500383929e-05, "loss": 0.3926, "step": 8713 }, { "epoch": 2.2304, "grad_norm": 1.890625, "learning_rate": 1.2831669652760003e-05, "loss": 0.4121, "step": 8714 }, { "epoch": 2.230656, "grad_norm": 1.890625, "learning_rate": 1.2827403805136082e-05, "loss": 0.4402, "step": 8715 }, { "epoch": 2.230912, "grad_norm": 1.8125, "learning_rate": 1.2823137957512158e-05, "loss": 0.392, "step": 8716 }, { "epoch": 2.231168, "grad_norm": 1.7890625, "learning_rate": 1.2818872109888236e-05, "loss": 0.389, "step": 8717 }, { "epoch": 2.231424, "grad_norm": 1.8125, "learning_rate": 1.2814606262264312e-05, "loss": 0.4607, "step": 8718 }, { "epoch": 2.23168, "grad_norm": 1.84375, "learning_rate": 1.281034041464039e-05, "loss": 0.4249, "step": 8719 }, { "epoch": 2.231936, "grad_norm": 1.7421875, "learning_rate": 1.2806074567016465e-05, "loss": 0.4085, "step": 8720 }, { "epoch": 2.232192, "grad_norm": 1.8828125, "learning_rate": 1.2801808719392545e-05, "loss": 0.4168, "step": 8721 }, { "epoch": 2.2324479999999998, "grad_norm": 1.828125, "learning_rate": 1.2797542871768619e-05, "loss": 0.4217, "step": 8722 }, { "epoch": 2.232704, "grad_norm": 1.90625, "learning_rate": 1.2793277024144698e-05, "loss": 0.4461, "step": 8723 }, { "epoch": 2.23296, "grad_norm": 1.6796875, "learning_rate": 1.2789011176520776e-05, "loss": 0.4279, "step": 8724 }, { "epoch": 2.233216, "grad_norm": 1.75, "learning_rate": 1.2784745328896852e-05, "loss": 0.4317, "step": 8725 }, { "epoch": 2.233472, "grad_norm": 1.765625, "learning_rate": 1.2780479481272931e-05, "loss": 0.4337, "step": 8726 }, { "epoch": 2.233728, "grad_norm": 1.734375, "learning_rate": 1.2776213633649006e-05, "loss": 0.4186, "step": 8727 }, { "epoch": 2.233984, "grad_norm": 1.78125, "learning_rate": 1.2771947786025085e-05, "loss": 0.4338, "step": 8728 }, { "epoch": 2.23424, "grad_norm": 1.921875, "learning_rate": 1.276768193840116e-05, "loss": 0.427, "step": 8729 }, { "epoch": 2.234496, "grad_norm": 1.7421875, "learning_rate": 1.2763416090777238e-05, "loss": 0.4316, "step": 8730 }, { "epoch": 2.234752, "grad_norm": 1.8515625, "learning_rate": 1.2759150243153314e-05, "loss": 0.4129, "step": 8731 }, { "epoch": 2.235008, "grad_norm": 1.8671875, "learning_rate": 1.2754884395529392e-05, "loss": 0.4438, "step": 8732 }, { "epoch": 2.235264, "grad_norm": 1.875, "learning_rate": 1.2750618547905468e-05, "loss": 0.4403, "step": 8733 }, { "epoch": 2.23552, "grad_norm": 1.84375, "learning_rate": 1.2746352700281547e-05, "loss": 0.4375, "step": 8734 }, { "epoch": 2.235776, "grad_norm": 1.78125, "learning_rate": 1.2742086852657623e-05, "loss": 0.4209, "step": 8735 }, { "epoch": 2.236032, "grad_norm": 1.75, "learning_rate": 1.2737821005033701e-05, "loss": 0.4583, "step": 8736 }, { "epoch": 2.236288, "grad_norm": 1.84375, "learning_rate": 1.2733555157409777e-05, "loss": 0.4308, "step": 8737 }, { "epoch": 2.236544, "grad_norm": 1.9140625, "learning_rate": 1.2729289309785855e-05, "loss": 0.4154, "step": 8738 }, { "epoch": 2.2368, "grad_norm": 1.8671875, "learning_rate": 1.2725023462161934e-05, "loss": 0.44, "step": 8739 }, { "epoch": 2.237056, "grad_norm": 1.7421875, "learning_rate": 1.272075761453801e-05, "loss": 0.4433, "step": 8740 }, { "epoch": 2.237312, "grad_norm": 1.7421875, "learning_rate": 1.2716491766914088e-05, "loss": 0.4419, "step": 8741 }, { "epoch": 2.237568, "grad_norm": 1.7578125, "learning_rate": 1.2712225919290164e-05, "loss": 0.4281, "step": 8742 }, { "epoch": 2.237824, "grad_norm": 1.828125, "learning_rate": 1.2707960071666241e-05, "loss": 0.4066, "step": 8743 }, { "epoch": 2.23808, "grad_norm": 2.046875, "learning_rate": 1.2703694224042317e-05, "loss": 0.4486, "step": 8744 }, { "epoch": 2.238336, "grad_norm": 1.7890625, "learning_rate": 1.2699428376418397e-05, "loss": 0.4031, "step": 8745 }, { "epoch": 2.238592, "grad_norm": 1.9609375, "learning_rate": 1.269516252879447e-05, "loss": 0.4387, "step": 8746 }, { "epoch": 2.238848, "grad_norm": 1.9609375, "learning_rate": 1.269089668117055e-05, "loss": 0.424, "step": 8747 }, { "epoch": 2.239104, "grad_norm": 1.7890625, "learning_rate": 1.2686630833546626e-05, "loss": 0.3572, "step": 8748 }, { "epoch": 2.23936, "grad_norm": 1.8515625, "learning_rate": 1.2682364985922704e-05, "loss": 0.4477, "step": 8749 }, { "epoch": 2.239616, "grad_norm": 1.90625, "learning_rate": 1.267809913829878e-05, "loss": 0.413, "step": 8750 }, { "epoch": 2.239872, "grad_norm": 1.8125, "learning_rate": 1.2673833290674857e-05, "loss": 0.4239, "step": 8751 }, { "epoch": 2.240128, "grad_norm": 1.8671875, "learning_rate": 1.2669567443050933e-05, "loss": 0.4603, "step": 8752 }, { "epoch": 2.240384, "grad_norm": 1.7265625, "learning_rate": 1.2665301595427013e-05, "loss": 0.4016, "step": 8753 }, { "epoch": 2.24064, "grad_norm": 1.8671875, "learning_rate": 1.2661035747803087e-05, "loss": 0.4474, "step": 8754 }, { "epoch": 2.240896, "grad_norm": 1.703125, "learning_rate": 1.2656769900179166e-05, "loss": 0.4169, "step": 8755 }, { "epoch": 2.241152, "grad_norm": 1.7578125, "learning_rate": 1.2652504052555244e-05, "loss": 0.47, "step": 8756 }, { "epoch": 2.241408, "grad_norm": 1.8984375, "learning_rate": 1.264823820493132e-05, "loss": 0.413, "step": 8757 }, { "epoch": 2.241664, "grad_norm": 1.7734375, "learning_rate": 1.26439723573074e-05, "loss": 0.4123, "step": 8758 }, { "epoch": 2.24192, "grad_norm": 1.8203125, "learning_rate": 1.2639706509683475e-05, "loss": 0.4414, "step": 8759 }, { "epoch": 2.242176, "grad_norm": 1.828125, "learning_rate": 1.2635440662059553e-05, "loss": 0.3995, "step": 8760 }, { "epoch": 2.242432, "grad_norm": 1.71875, "learning_rate": 1.2631174814435629e-05, "loss": 0.4177, "step": 8761 }, { "epoch": 2.242688, "grad_norm": 1.7421875, "learning_rate": 1.2626908966811706e-05, "loss": 0.4286, "step": 8762 }, { "epoch": 2.242944, "grad_norm": 1.8515625, "learning_rate": 1.2622643119187782e-05, "loss": 0.459, "step": 8763 }, { "epoch": 2.2432, "grad_norm": 1.8828125, "learning_rate": 1.2618377271563862e-05, "loss": 0.3932, "step": 8764 }, { "epoch": 2.243456, "grad_norm": 1.8828125, "learning_rate": 1.2614111423939936e-05, "loss": 0.3926, "step": 8765 }, { "epoch": 2.243712, "grad_norm": 1.71875, "learning_rate": 1.2609845576316015e-05, "loss": 0.4413, "step": 8766 }, { "epoch": 2.243968, "grad_norm": 1.921875, "learning_rate": 1.2605579728692091e-05, "loss": 0.4304, "step": 8767 }, { "epoch": 2.244224, "grad_norm": 1.9375, "learning_rate": 1.2601313881068169e-05, "loss": 0.4306, "step": 8768 }, { "epoch": 2.24448, "grad_norm": 1.828125, "learning_rate": 1.2597048033444245e-05, "loss": 0.4339, "step": 8769 }, { "epoch": 2.244736, "grad_norm": 1.90625, "learning_rate": 1.2592782185820323e-05, "loss": 0.4107, "step": 8770 }, { "epoch": 2.244992, "grad_norm": 1.7578125, "learning_rate": 1.2588516338196399e-05, "loss": 0.42, "step": 8771 }, { "epoch": 2.245248, "grad_norm": 1.9140625, "learning_rate": 1.2584250490572478e-05, "loss": 0.4179, "step": 8772 }, { "epoch": 2.245504, "grad_norm": 1.75, "learning_rate": 1.2579984642948556e-05, "loss": 0.4306, "step": 8773 }, { "epoch": 2.24576, "grad_norm": 1.8671875, "learning_rate": 1.2575718795324632e-05, "loss": 0.3988, "step": 8774 }, { "epoch": 2.246016, "grad_norm": 1.7265625, "learning_rate": 1.257145294770071e-05, "loss": 0.4218, "step": 8775 }, { "epoch": 2.246272, "grad_norm": 1.7578125, "learning_rate": 1.2567187100076785e-05, "loss": 0.4112, "step": 8776 }, { "epoch": 2.246528, "grad_norm": 1.75, "learning_rate": 1.2562921252452865e-05, "loss": 0.4196, "step": 8777 }, { "epoch": 2.246784, "grad_norm": 1.7578125, "learning_rate": 1.2558655404828939e-05, "loss": 0.4397, "step": 8778 }, { "epoch": 2.24704, "grad_norm": 1.953125, "learning_rate": 1.2554389557205018e-05, "loss": 0.4322, "step": 8779 }, { "epoch": 2.247296, "grad_norm": 1.734375, "learning_rate": 1.2550123709581094e-05, "loss": 0.4731, "step": 8780 }, { "epoch": 2.2475519999999998, "grad_norm": 1.7890625, "learning_rate": 1.2545857861957172e-05, "loss": 0.4085, "step": 8781 }, { "epoch": 2.247808, "grad_norm": 1.8046875, "learning_rate": 1.2541592014333248e-05, "loss": 0.4375, "step": 8782 }, { "epoch": 2.248064, "grad_norm": 1.859375, "learning_rate": 1.2537326166709325e-05, "loss": 0.3919, "step": 8783 }, { "epoch": 2.24832, "grad_norm": 1.7734375, "learning_rate": 1.2533060319085401e-05, "loss": 0.4196, "step": 8784 }, { "epoch": 2.248576, "grad_norm": 1.8671875, "learning_rate": 1.252879447146148e-05, "loss": 0.4117, "step": 8785 }, { "epoch": 2.248832, "grad_norm": 1.8671875, "learning_rate": 1.2524528623837557e-05, "loss": 0.4003, "step": 8786 }, { "epoch": 2.249088, "grad_norm": 1.7578125, "learning_rate": 1.2520262776213634e-05, "loss": 0.4352, "step": 8787 }, { "epoch": 2.249344, "grad_norm": 1.765625, "learning_rate": 1.2515996928589712e-05, "loss": 0.4706, "step": 8788 }, { "epoch": 2.2496, "grad_norm": 1.859375, "learning_rate": 1.2511731080965788e-05, "loss": 0.4512, "step": 8789 }, { "epoch": 2.249856, "grad_norm": 1.875, "learning_rate": 1.2507465233341867e-05, "loss": 0.4235, "step": 8790 }, { "epoch": 2.250112, "grad_norm": 1.8203125, "learning_rate": 1.2503199385717943e-05, "loss": 0.4342, "step": 8791 }, { "epoch": 2.250368, "grad_norm": 1.703125, "learning_rate": 1.249893353809402e-05, "loss": 0.4238, "step": 8792 }, { "epoch": 2.250624, "grad_norm": 1.8046875, "learning_rate": 1.2494667690470097e-05, "loss": 0.4677, "step": 8793 }, { "epoch": 2.25088, "grad_norm": 1.8125, "learning_rate": 1.2490401842846173e-05, "loss": 0.4427, "step": 8794 }, { "epoch": 2.251136, "grad_norm": 1.7421875, "learning_rate": 1.248613599522225e-05, "loss": 0.4211, "step": 8795 }, { "epoch": 2.251392, "grad_norm": 1.828125, "learning_rate": 1.248187014759833e-05, "loss": 0.4316, "step": 8796 }, { "epoch": 2.251648, "grad_norm": 1.7890625, "learning_rate": 1.2477604299974406e-05, "loss": 0.442, "step": 8797 }, { "epoch": 2.251904, "grad_norm": 1.75, "learning_rate": 1.2473338452350483e-05, "loss": 0.4243, "step": 8798 }, { "epoch": 2.25216, "grad_norm": 1.71875, "learning_rate": 1.246907260472656e-05, "loss": 0.4134, "step": 8799 }, { "epoch": 2.252416, "grad_norm": 1.8125, "learning_rate": 1.2464806757102637e-05, "loss": 0.4066, "step": 8800 }, { "epoch": 2.252672, "grad_norm": 1.8203125, "learning_rate": 1.2460540909478715e-05, "loss": 0.3812, "step": 8801 }, { "epoch": 2.252928, "grad_norm": 1.6796875, "learning_rate": 1.245627506185479e-05, "loss": 0.4549, "step": 8802 }, { "epoch": 2.253184, "grad_norm": 1.78125, "learning_rate": 1.2452009214230868e-05, "loss": 0.4066, "step": 8803 }, { "epoch": 2.25344, "grad_norm": 1.9453125, "learning_rate": 1.2447743366606946e-05, "loss": 0.4435, "step": 8804 }, { "epoch": 2.253696, "grad_norm": 1.7578125, "learning_rate": 1.2443477518983022e-05, "loss": 0.465, "step": 8805 }, { "epoch": 2.253952, "grad_norm": 1.8671875, "learning_rate": 1.24392116713591e-05, "loss": 0.3988, "step": 8806 }, { "epoch": 2.254208, "grad_norm": 1.71875, "learning_rate": 1.2434945823735177e-05, "loss": 0.4051, "step": 8807 }, { "epoch": 2.254464, "grad_norm": 1.671875, "learning_rate": 1.2430679976111253e-05, "loss": 0.4197, "step": 8808 }, { "epoch": 2.25472, "grad_norm": 1.796875, "learning_rate": 1.242641412848733e-05, "loss": 0.3951, "step": 8809 }, { "epoch": 2.254976, "grad_norm": 1.8515625, "learning_rate": 1.2422148280863408e-05, "loss": 0.4296, "step": 8810 }, { "epoch": 2.255232, "grad_norm": 1.796875, "learning_rate": 1.2417882433239484e-05, "loss": 0.4272, "step": 8811 }, { "epoch": 2.255488, "grad_norm": 1.9140625, "learning_rate": 1.2413616585615562e-05, "loss": 0.4409, "step": 8812 }, { "epoch": 2.255744, "grad_norm": 1.796875, "learning_rate": 1.240935073799164e-05, "loss": 0.4082, "step": 8813 }, { "epoch": 2.2560000000000002, "grad_norm": 1.8828125, "learning_rate": 1.2405084890367717e-05, "loss": 0.3931, "step": 8814 }, { "epoch": 2.256256, "grad_norm": 1.9296875, "learning_rate": 1.2400819042743795e-05, "loss": 0.4351, "step": 8815 }, { "epoch": 2.256512, "grad_norm": 1.765625, "learning_rate": 1.2396553195119871e-05, "loss": 0.3794, "step": 8816 }, { "epoch": 2.256768, "grad_norm": 1.890625, "learning_rate": 1.2392287347495949e-05, "loss": 0.4189, "step": 8817 }, { "epoch": 2.257024, "grad_norm": 1.890625, "learning_rate": 1.2388021499872025e-05, "loss": 0.4702, "step": 8818 }, { "epoch": 2.25728, "grad_norm": 1.75, "learning_rate": 1.2383755652248102e-05, "loss": 0.4008, "step": 8819 }, { "epoch": 2.257536, "grad_norm": 1.6796875, "learning_rate": 1.237948980462418e-05, "loss": 0.4281, "step": 8820 }, { "epoch": 2.2577920000000002, "grad_norm": 1.734375, "learning_rate": 1.2375223957000256e-05, "loss": 0.4574, "step": 8821 }, { "epoch": 2.258048, "grad_norm": 1.7890625, "learning_rate": 1.2370958109376334e-05, "loss": 0.4106, "step": 8822 }, { "epoch": 2.258304, "grad_norm": 2.015625, "learning_rate": 1.2366692261752411e-05, "loss": 0.4208, "step": 8823 }, { "epoch": 2.25856, "grad_norm": 1.828125, "learning_rate": 1.2362426414128487e-05, "loss": 0.4085, "step": 8824 }, { "epoch": 2.258816, "grad_norm": 1.828125, "learning_rate": 1.2358160566504565e-05, "loss": 0.4057, "step": 8825 }, { "epoch": 2.259072, "grad_norm": 1.8828125, "learning_rate": 1.2353894718880642e-05, "loss": 0.4093, "step": 8826 }, { "epoch": 2.259328, "grad_norm": 1.859375, "learning_rate": 1.2349628871256718e-05, "loss": 0.4182, "step": 8827 }, { "epoch": 2.259584, "grad_norm": 1.828125, "learning_rate": 1.2345363023632796e-05, "loss": 0.4308, "step": 8828 }, { "epoch": 2.25984, "grad_norm": 1.9296875, "learning_rate": 1.2341097176008874e-05, "loss": 0.396, "step": 8829 }, { "epoch": 2.260096, "grad_norm": 1.7265625, "learning_rate": 1.2336831328384951e-05, "loss": 0.4295, "step": 8830 }, { "epoch": 2.260352, "grad_norm": 1.7734375, "learning_rate": 1.2332565480761029e-05, "loss": 0.4539, "step": 8831 }, { "epoch": 2.260608, "grad_norm": 1.8984375, "learning_rate": 1.2328299633137105e-05, "loss": 0.4338, "step": 8832 }, { "epoch": 2.2608639999999998, "grad_norm": 1.8515625, "learning_rate": 1.2324033785513183e-05, "loss": 0.421, "step": 8833 }, { "epoch": 2.26112, "grad_norm": 1.84375, "learning_rate": 1.2319767937889259e-05, "loss": 0.4159, "step": 8834 }, { "epoch": 2.261376, "grad_norm": 1.828125, "learning_rate": 1.2315502090265336e-05, "loss": 0.4758, "step": 8835 }, { "epoch": 2.261632, "grad_norm": 1.7890625, "learning_rate": 1.2311236242641414e-05, "loss": 0.4084, "step": 8836 }, { "epoch": 2.261888, "grad_norm": 1.828125, "learning_rate": 1.230697039501749e-05, "loss": 0.4027, "step": 8837 }, { "epoch": 2.262144, "grad_norm": 1.8125, "learning_rate": 1.2302704547393568e-05, "loss": 0.443, "step": 8838 }, { "epoch": 2.2624, "grad_norm": 1.765625, "learning_rate": 1.2298438699769645e-05, "loss": 0.4135, "step": 8839 }, { "epoch": 2.262656, "grad_norm": 1.734375, "learning_rate": 1.2294172852145721e-05, "loss": 0.3984, "step": 8840 }, { "epoch": 2.262912, "grad_norm": 1.6328125, "learning_rate": 1.2289907004521799e-05, "loss": 0.3855, "step": 8841 }, { "epoch": 2.263168, "grad_norm": 1.78125, "learning_rate": 1.2285641156897876e-05, "loss": 0.4447, "step": 8842 }, { "epoch": 2.263424, "grad_norm": 1.8203125, "learning_rate": 1.2281375309273952e-05, "loss": 0.4496, "step": 8843 }, { "epoch": 2.26368, "grad_norm": 1.8046875, "learning_rate": 1.227710946165003e-05, "loss": 0.435, "step": 8844 }, { "epoch": 2.263936, "grad_norm": 1.8984375, "learning_rate": 1.2272843614026106e-05, "loss": 0.4295, "step": 8845 }, { "epoch": 2.264192, "grad_norm": 1.7890625, "learning_rate": 1.2268577766402185e-05, "loss": 0.4192, "step": 8846 }, { "epoch": 2.264448, "grad_norm": 1.734375, "learning_rate": 1.2264311918778263e-05, "loss": 0.4303, "step": 8847 }, { "epoch": 2.264704, "grad_norm": 1.796875, "learning_rate": 1.2260046071154339e-05, "loss": 0.4235, "step": 8848 }, { "epoch": 2.26496, "grad_norm": 1.875, "learning_rate": 1.2255780223530417e-05, "loss": 0.4152, "step": 8849 }, { "epoch": 2.265216, "grad_norm": 1.796875, "learning_rate": 1.2251514375906494e-05, "loss": 0.419, "step": 8850 }, { "epoch": 2.265472, "grad_norm": 1.859375, "learning_rate": 1.224724852828257e-05, "loss": 0.4029, "step": 8851 }, { "epoch": 2.265728, "grad_norm": 1.84375, "learning_rate": 1.2242982680658648e-05, "loss": 0.4279, "step": 8852 }, { "epoch": 2.265984, "grad_norm": 1.8359375, "learning_rate": 1.2238716833034724e-05, "loss": 0.4097, "step": 8853 }, { "epoch": 2.26624, "grad_norm": 1.7578125, "learning_rate": 1.2234450985410802e-05, "loss": 0.4223, "step": 8854 }, { "epoch": 2.266496, "grad_norm": 1.8359375, "learning_rate": 1.223018513778688e-05, "loss": 0.4402, "step": 8855 }, { "epoch": 2.266752, "grad_norm": 1.78125, "learning_rate": 1.2225919290162955e-05, "loss": 0.4091, "step": 8856 }, { "epoch": 2.267008, "grad_norm": 1.890625, "learning_rate": 1.2221653442539033e-05, "loss": 0.4373, "step": 8857 }, { "epoch": 2.267264, "grad_norm": 1.78125, "learning_rate": 1.221738759491511e-05, "loss": 0.4058, "step": 8858 }, { "epoch": 2.26752, "grad_norm": 1.7890625, "learning_rate": 1.2213121747291186e-05, "loss": 0.4459, "step": 8859 }, { "epoch": 2.267776, "grad_norm": 1.75, "learning_rate": 1.2208855899667264e-05, "loss": 0.4083, "step": 8860 }, { "epoch": 2.268032, "grad_norm": 1.796875, "learning_rate": 1.2204590052043342e-05, "loss": 0.4346, "step": 8861 }, { "epoch": 2.268288, "grad_norm": 1.75, "learning_rate": 1.220032420441942e-05, "loss": 0.427, "step": 8862 }, { "epoch": 2.268544, "grad_norm": 1.8046875, "learning_rate": 1.2196058356795497e-05, "loss": 0.4289, "step": 8863 }, { "epoch": 2.2688, "grad_norm": 1.9375, "learning_rate": 1.2191792509171573e-05, "loss": 0.4185, "step": 8864 }, { "epoch": 2.269056, "grad_norm": 1.8828125, "learning_rate": 1.218752666154765e-05, "loss": 0.4502, "step": 8865 }, { "epoch": 2.269312, "grad_norm": 1.78125, "learning_rate": 1.2183260813923728e-05, "loss": 0.4199, "step": 8866 }, { "epoch": 2.269568, "grad_norm": 1.765625, "learning_rate": 1.2178994966299804e-05, "loss": 0.4351, "step": 8867 }, { "epoch": 2.269824, "grad_norm": 1.90625, "learning_rate": 1.2174729118675882e-05, "loss": 0.4008, "step": 8868 }, { "epoch": 2.27008, "grad_norm": 1.96875, "learning_rate": 1.2170463271051958e-05, "loss": 0.4335, "step": 8869 }, { "epoch": 2.270336, "grad_norm": 1.7890625, "learning_rate": 1.2166197423428036e-05, "loss": 0.44, "step": 8870 }, { "epoch": 2.270592, "grad_norm": 1.7109375, "learning_rate": 1.2161931575804113e-05, "loss": 0.4051, "step": 8871 }, { "epoch": 2.270848, "grad_norm": 1.828125, "learning_rate": 1.215766572818019e-05, "loss": 0.4128, "step": 8872 }, { "epoch": 2.2711040000000002, "grad_norm": 1.8125, "learning_rate": 1.2153399880556267e-05, "loss": 0.3999, "step": 8873 }, { "epoch": 2.27136, "grad_norm": 1.9609375, "learning_rate": 1.2149134032932344e-05, "loss": 0.4177, "step": 8874 }, { "epoch": 2.271616, "grad_norm": 1.796875, "learning_rate": 1.214486818530842e-05, "loss": 0.4455, "step": 8875 }, { "epoch": 2.271872, "grad_norm": 1.75, "learning_rate": 1.2140602337684498e-05, "loss": 0.4177, "step": 8876 }, { "epoch": 2.272128, "grad_norm": 1.7890625, "learning_rate": 1.2136336490060576e-05, "loss": 0.4369, "step": 8877 }, { "epoch": 2.272384, "grad_norm": 1.7890625, "learning_rate": 1.2132070642436653e-05, "loss": 0.4854, "step": 8878 }, { "epoch": 2.27264, "grad_norm": 1.7578125, "learning_rate": 1.2127804794812731e-05, "loss": 0.4144, "step": 8879 }, { "epoch": 2.2728960000000002, "grad_norm": 1.828125, "learning_rate": 1.2123538947188807e-05, "loss": 0.4593, "step": 8880 }, { "epoch": 2.273152, "grad_norm": 1.6953125, "learning_rate": 1.2119273099564885e-05, "loss": 0.4092, "step": 8881 }, { "epoch": 2.273408, "grad_norm": 1.7734375, "learning_rate": 1.2115007251940962e-05, "loss": 0.4401, "step": 8882 }, { "epoch": 2.273664, "grad_norm": 1.796875, "learning_rate": 1.2110741404317038e-05, "loss": 0.4098, "step": 8883 }, { "epoch": 2.27392, "grad_norm": 1.6875, "learning_rate": 1.2106475556693116e-05, "loss": 0.4223, "step": 8884 }, { "epoch": 2.2741759999999998, "grad_norm": 1.7421875, "learning_rate": 1.2102209709069192e-05, "loss": 0.4457, "step": 8885 }, { "epoch": 2.274432, "grad_norm": 1.78125, "learning_rate": 1.209794386144527e-05, "loss": 0.4155, "step": 8886 }, { "epoch": 2.274688, "grad_norm": 1.8671875, "learning_rate": 1.2093678013821347e-05, "loss": 0.4028, "step": 8887 }, { "epoch": 2.274944, "grad_norm": 1.890625, "learning_rate": 1.2089412166197423e-05, "loss": 0.3978, "step": 8888 }, { "epoch": 2.2752, "grad_norm": 1.7734375, "learning_rate": 1.20851463185735e-05, "loss": 0.4185, "step": 8889 }, { "epoch": 2.275456, "grad_norm": 1.7421875, "learning_rate": 1.2080880470949578e-05, "loss": 0.4033, "step": 8890 }, { "epoch": 2.275712, "grad_norm": 1.734375, "learning_rate": 1.2076614623325654e-05, "loss": 0.4047, "step": 8891 }, { "epoch": 2.2759679999999998, "grad_norm": 1.8046875, "learning_rate": 1.2072348775701732e-05, "loss": 0.418, "step": 8892 }, { "epoch": 2.276224, "grad_norm": 1.8515625, "learning_rate": 1.206808292807781e-05, "loss": 0.4178, "step": 8893 }, { "epoch": 2.27648, "grad_norm": 1.8671875, "learning_rate": 1.2063817080453886e-05, "loss": 0.4426, "step": 8894 }, { "epoch": 2.276736, "grad_norm": 1.984375, "learning_rate": 1.2059551232829965e-05, "loss": 0.4105, "step": 8895 }, { "epoch": 2.276992, "grad_norm": 1.7890625, "learning_rate": 1.2055285385206041e-05, "loss": 0.4028, "step": 8896 }, { "epoch": 2.277248, "grad_norm": 1.6015625, "learning_rate": 1.2051019537582119e-05, "loss": 0.4362, "step": 8897 }, { "epoch": 2.277504, "grad_norm": 1.90625, "learning_rate": 1.2046753689958196e-05, "loss": 0.4477, "step": 8898 }, { "epoch": 2.27776, "grad_norm": 1.7421875, "learning_rate": 1.2042487842334272e-05, "loss": 0.3914, "step": 8899 }, { "epoch": 2.278016, "grad_norm": 1.875, "learning_rate": 1.203822199471035e-05, "loss": 0.4389, "step": 8900 }, { "epoch": 2.278272, "grad_norm": 1.65625, "learning_rate": 1.2033956147086428e-05, "loss": 0.4237, "step": 8901 }, { "epoch": 2.278528, "grad_norm": 1.828125, "learning_rate": 1.2029690299462504e-05, "loss": 0.3973, "step": 8902 }, { "epoch": 2.278784, "grad_norm": 1.78125, "learning_rate": 1.2025424451838581e-05, "loss": 0.4726, "step": 8903 }, { "epoch": 2.27904, "grad_norm": 1.8515625, "learning_rate": 1.2021158604214657e-05, "loss": 0.3736, "step": 8904 }, { "epoch": 2.279296, "grad_norm": 1.640625, "learning_rate": 1.2016892756590735e-05, "loss": 0.4572, "step": 8905 }, { "epoch": 2.279552, "grad_norm": 1.828125, "learning_rate": 1.2012626908966812e-05, "loss": 0.4356, "step": 8906 }, { "epoch": 2.279808, "grad_norm": 1.7734375, "learning_rate": 1.2008361061342888e-05, "loss": 0.4093, "step": 8907 }, { "epoch": 2.280064, "grad_norm": 1.8046875, "learning_rate": 1.2004095213718966e-05, "loss": 0.4247, "step": 8908 }, { "epoch": 2.28032, "grad_norm": 1.78125, "learning_rate": 1.1999829366095044e-05, "loss": 0.4268, "step": 8909 }, { "epoch": 2.280576, "grad_norm": 1.828125, "learning_rate": 1.199556351847112e-05, "loss": 0.3969, "step": 8910 }, { "epoch": 2.280832, "grad_norm": 1.8984375, "learning_rate": 1.1991297670847199e-05, "loss": 0.4284, "step": 8911 }, { "epoch": 2.281088, "grad_norm": 1.734375, "learning_rate": 1.1987031823223275e-05, "loss": 0.4421, "step": 8912 }, { "epoch": 2.281344, "grad_norm": 1.78125, "learning_rate": 1.1982765975599353e-05, "loss": 0.4086, "step": 8913 }, { "epoch": 2.2816, "grad_norm": 1.8203125, "learning_rate": 1.197850012797543e-05, "loss": 0.4272, "step": 8914 }, { "epoch": 2.281856, "grad_norm": 1.765625, "learning_rate": 1.1974234280351506e-05, "loss": 0.4227, "step": 8915 }, { "epoch": 2.282112, "grad_norm": 1.96875, "learning_rate": 1.1969968432727584e-05, "loss": 0.415, "step": 8916 }, { "epoch": 2.282368, "grad_norm": 1.890625, "learning_rate": 1.1965702585103662e-05, "loss": 0.405, "step": 8917 }, { "epoch": 2.282624, "grad_norm": 1.6171875, "learning_rate": 1.1961436737479738e-05, "loss": 0.4354, "step": 8918 }, { "epoch": 2.28288, "grad_norm": 1.734375, "learning_rate": 1.1957170889855815e-05, "loss": 0.4202, "step": 8919 }, { "epoch": 2.283136, "grad_norm": 1.796875, "learning_rate": 1.1952905042231891e-05, "loss": 0.4481, "step": 8920 }, { "epoch": 2.283392, "grad_norm": 1.8828125, "learning_rate": 1.1948639194607969e-05, "loss": 0.4294, "step": 8921 }, { "epoch": 2.283648, "grad_norm": 1.8515625, "learning_rate": 1.1944373346984046e-05, "loss": 0.4497, "step": 8922 }, { "epoch": 2.283904, "grad_norm": 1.796875, "learning_rate": 1.1940107499360122e-05, "loss": 0.3959, "step": 8923 }, { "epoch": 2.28416, "grad_norm": 1.84375, "learning_rate": 1.19358416517362e-05, "loss": 0.4584, "step": 8924 }, { "epoch": 2.2844160000000002, "grad_norm": 1.8203125, "learning_rate": 1.1931575804112278e-05, "loss": 0.4355, "step": 8925 }, { "epoch": 2.284672, "grad_norm": 1.796875, "learning_rate": 1.1927309956488354e-05, "loss": 0.4235, "step": 8926 }, { "epoch": 2.284928, "grad_norm": 1.7578125, "learning_rate": 1.1923044108864433e-05, "loss": 0.4483, "step": 8927 }, { "epoch": 2.285184, "grad_norm": 1.796875, "learning_rate": 1.1918778261240509e-05, "loss": 0.4344, "step": 8928 }, { "epoch": 2.28544, "grad_norm": 1.78125, "learning_rate": 1.1914512413616587e-05, "loss": 0.3924, "step": 8929 }, { "epoch": 2.285696, "grad_norm": 1.765625, "learning_rate": 1.1910246565992664e-05, "loss": 0.4382, "step": 8930 }, { "epoch": 2.285952, "grad_norm": 1.8203125, "learning_rate": 1.190598071836874e-05, "loss": 0.4165, "step": 8931 }, { "epoch": 2.2862080000000002, "grad_norm": 1.7890625, "learning_rate": 1.1901714870744818e-05, "loss": 0.4377, "step": 8932 }, { "epoch": 2.286464, "grad_norm": 1.8046875, "learning_rate": 1.1897449023120896e-05, "loss": 0.4314, "step": 8933 }, { "epoch": 2.28672, "grad_norm": 1.9609375, "learning_rate": 1.1893183175496972e-05, "loss": 0.4279, "step": 8934 }, { "epoch": 2.286976, "grad_norm": 1.828125, "learning_rate": 1.188891732787305e-05, "loss": 0.419, "step": 8935 }, { "epoch": 2.287232, "grad_norm": 2.0, "learning_rate": 1.1884651480249125e-05, "loss": 0.3968, "step": 8936 }, { "epoch": 2.287488, "grad_norm": 1.90625, "learning_rate": 1.1880385632625203e-05, "loss": 0.4293, "step": 8937 }, { "epoch": 2.287744, "grad_norm": 2.0, "learning_rate": 1.187611978500128e-05, "loss": 0.4805, "step": 8938 }, { "epoch": 2.288, "grad_norm": 1.8984375, "learning_rate": 1.1871853937377356e-05, "loss": 0.4107, "step": 8939 }, { "epoch": 2.288256, "grad_norm": 1.8125, "learning_rate": 1.1867588089753434e-05, "loss": 0.4254, "step": 8940 }, { "epoch": 2.288512, "grad_norm": 1.890625, "learning_rate": 1.1863322242129512e-05, "loss": 0.4425, "step": 8941 }, { "epoch": 2.288768, "grad_norm": 1.8515625, "learning_rate": 1.1859056394505588e-05, "loss": 0.3639, "step": 8942 }, { "epoch": 2.289024, "grad_norm": 1.71875, "learning_rate": 1.1854790546881665e-05, "loss": 0.4341, "step": 8943 }, { "epoch": 2.2892799999999998, "grad_norm": 1.7734375, "learning_rate": 1.1850524699257743e-05, "loss": 0.443, "step": 8944 }, { "epoch": 2.289536, "grad_norm": 1.875, "learning_rate": 1.184625885163382e-05, "loss": 0.4268, "step": 8945 }, { "epoch": 2.289792, "grad_norm": 1.8203125, "learning_rate": 1.1841993004009898e-05, "loss": 0.3855, "step": 8946 }, { "epoch": 2.290048, "grad_norm": 1.90625, "learning_rate": 1.1837727156385974e-05, "loss": 0.4071, "step": 8947 }, { "epoch": 2.290304, "grad_norm": 1.8515625, "learning_rate": 1.1833461308762052e-05, "loss": 0.4467, "step": 8948 }, { "epoch": 2.29056, "grad_norm": 1.8203125, "learning_rate": 1.182919546113813e-05, "loss": 0.4193, "step": 8949 }, { "epoch": 2.290816, "grad_norm": 1.796875, "learning_rate": 1.1824929613514206e-05, "loss": 0.4393, "step": 8950 }, { "epoch": 2.2910719999999998, "grad_norm": 1.765625, "learning_rate": 1.1820663765890283e-05, "loss": 0.4007, "step": 8951 }, { "epoch": 2.291328, "grad_norm": 1.875, "learning_rate": 1.1816397918266361e-05, "loss": 0.3978, "step": 8952 }, { "epoch": 2.291584, "grad_norm": 1.8203125, "learning_rate": 1.1812132070642437e-05, "loss": 0.4222, "step": 8953 }, { "epoch": 2.29184, "grad_norm": 1.8984375, "learning_rate": 1.1807866223018514e-05, "loss": 0.4139, "step": 8954 }, { "epoch": 2.292096, "grad_norm": 1.8515625, "learning_rate": 1.180360037539459e-05, "loss": 0.4474, "step": 8955 }, { "epoch": 2.292352, "grad_norm": 1.796875, "learning_rate": 1.1799334527770668e-05, "loss": 0.3941, "step": 8956 }, { "epoch": 2.292608, "grad_norm": 1.84375, "learning_rate": 1.1795068680146746e-05, "loss": 0.4289, "step": 8957 }, { "epoch": 2.292864, "grad_norm": 1.6796875, "learning_rate": 1.1790802832522822e-05, "loss": 0.4265, "step": 8958 }, { "epoch": 2.29312, "grad_norm": 1.7734375, "learning_rate": 1.17865369848989e-05, "loss": 0.4529, "step": 8959 }, { "epoch": 2.293376, "grad_norm": 1.7890625, "learning_rate": 1.1782271137274977e-05, "loss": 0.4256, "step": 8960 }, { "epoch": 2.293632, "grad_norm": 1.6640625, "learning_rate": 1.1778005289651055e-05, "loss": 0.4061, "step": 8961 }, { "epoch": 2.293888, "grad_norm": 1.6484375, "learning_rate": 1.1773739442027132e-05, "loss": 0.4434, "step": 8962 }, { "epoch": 2.294144, "grad_norm": 1.8671875, "learning_rate": 1.1769473594403208e-05, "loss": 0.4372, "step": 8963 }, { "epoch": 2.2944, "grad_norm": 1.828125, "learning_rate": 1.1765207746779286e-05, "loss": 0.4308, "step": 8964 }, { "epoch": 2.294656, "grad_norm": 1.9375, "learning_rate": 1.1760941899155364e-05, "loss": 0.4373, "step": 8965 }, { "epoch": 2.294912, "grad_norm": 1.765625, "learning_rate": 1.175667605153144e-05, "loss": 0.4822, "step": 8966 }, { "epoch": 2.295168, "grad_norm": 1.8125, "learning_rate": 1.1752410203907517e-05, "loss": 0.3909, "step": 8967 }, { "epoch": 2.295424, "grad_norm": 1.6953125, "learning_rate": 1.1748144356283595e-05, "loss": 0.4387, "step": 8968 }, { "epoch": 2.29568, "grad_norm": 1.640625, "learning_rate": 1.174387850865967e-05, "loss": 0.426, "step": 8969 }, { "epoch": 2.295936, "grad_norm": 1.734375, "learning_rate": 1.1739612661035748e-05, "loss": 0.4313, "step": 8970 }, { "epoch": 2.296192, "grad_norm": 1.78125, "learning_rate": 1.1735346813411824e-05, "loss": 0.3964, "step": 8971 }, { "epoch": 2.296448, "grad_norm": 1.8984375, "learning_rate": 1.1731080965787902e-05, "loss": 0.3965, "step": 8972 }, { "epoch": 2.296704, "grad_norm": 1.8359375, "learning_rate": 1.172681511816398e-05, "loss": 0.4513, "step": 8973 }, { "epoch": 2.29696, "grad_norm": 1.6875, "learning_rate": 1.1722549270540056e-05, "loss": 0.4299, "step": 8974 }, { "epoch": 2.297216, "grad_norm": 1.7109375, "learning_rate": 1.1718283422916133e-05, "loss": 0.4276, "step": 8975 }, { "epoch": 2.297472, "grad_norm": 1.71875, "learning_rate": 1.1714017575292211e-05, "loss": 0.4163, "step": 8976 }, { "epoch": 2.297728, "grad_norm": 1.796875, "learning_rate": 1.1709751727668289e-05, "loss": 0.4031, "step": 8977 }, { "epoch": 2.297984, "grad_norm": 1.9375, "learning_rate": 1.1705485880044366e-05, "loss": 0.4209, "step": 8978 }, { "epoch": 2.29824, "grad_norm": 1.7578125, "learning_rate": 1.1701220032420442e-05, "loss": 0.3987, "step": 8979 }, { "epoch": 2.298496, "grad_norm": 1.7421875, "learning_rate": 1.169695418479652e-05, "loss": 0.4222, "step": 8980 }, { "epoch": 2.298752, "grad_norm": 1.734375, "learning_rate": 1.1692688337172598e-05, "loss": 0.4411, "step": 8981 }, { "epoch": 2.299008, "grad_norm": 1.8046875, "learning_rate": 1.1688422489548674e-05, "loss": 0.4208, "step": 8982 }, { "epoch": 2.299264, "grad_norm": 1.6796875, "learning_rate": 1.1684156641924751e-05, "loss": 0.4167, "step": 8983 }, { "epoch": 2.2995200000000002, "grad_norm": 1.8984375, "learning_rate": 1.1679890794300829e-05, "loss": 0.4343, "step": 8984 }, { "epoch": 2.299776, "grad_norm": 1.8125, "learning_rate": 1.1675624946676905e-05, "loss": 0.4284, "step": 8985 }, { "epoch": 2.300032, "grad_norm": 1.828125, "learning_rate": 1.1671359099052982e-05, "loss": 0.4229, "step": 8986 }, { "epoch": 2.300288, "grad_norm": 1.765625, "learning_rate": 1.1667093251429058e-05, "loss": 0.3876, "step": 8987 }, { "epoch": 2.300544, "grad_norm": 1.84375, "learning_rate": 1.1662827403805136e-05, "loss": 0.4176, "step": 8988 }, { "epoch": 2.3008, "grad_norm": 1.796875, "learning_rate": 1.1658561556181214e-05, "loss": 0.4245, "step": 8989 }, { "epoch": 2.301056, "grad_norm": 1.6875, "learning_rate": 1.165429570855729e-05, "loss": 0.4042, "step": 8990 }, { "epoch": 2.3013120000000002, "grad_norm": 1.8359375, "learning_rate": 1.1650029860933367e-05, "loss": 0.4066, "step": 8991 }, { "epoch": 2.301568, "grad_norm": 1.84375, "learning_rate": 1.1645764013309445e-05, "loss": 0.4366, "step": 8992 }, { "epoch": 2.301824, "grad_norm": 1.78125, "learning_rate": 1.1641498165685523e-05, "loss": 0.4185, "step": 8993 }, { "epoch": 2.30208, "grad_norm": 1.7734375, "learning_rate": 1.16372323180616e-05, "loss": 0.4373, "step": 8994 }, { "epoch": 2.302336, "grad_norm": 1.9296875, "learning_rate": 1.1632966470437676e-05, "loss": 0.423, "step": 8995 }, { "epoch": 2.302592, "grad_norm": 1.765625, "learning_rate": 1.1628700622813754e-05, "loss": 0.4618, "step": 8996 }, { "epoch": 2.302848, "grad_norm": 1.9296875, "learning_rate": 1.1624434775189832e-05, "loss": 0.4172, "step": 8997 }, { "epoch": 2.303104, "grad_norm": 1.828125, "learning_rate": 1.1620168927565908e-05, "loss": 0.4251, "step": 8998 }, { "epoch": 2.30336, "grad_norm": 1.765625, "learning_rate": 1.1615903079941985e-05, "loss": 0.4298, "step": 8999 }, { "epoch": 2.303616, "grad_norm": 1.78125, "learning_rate": 1.1611637232318063e-05, "loss": 0.4674, "step": 9000 }, { "epoch": 2.303872, "grad_norm": 1.90625, "learning_rate": 1.1607371384694139e-05, "loss": 0.4181, "step": 9001 }, { "epoch": 2.304128, "grad_norm": 1.90625, "learning_rate": 1.1603105537070216e-05, "loss": 0.4716, "step": 9002 }, { "epoch": 2.3043839999999998, "grad_norm": 1.90625, "learning_rate": 1.1598839689446294e-05, "loss": 0.4299, "step": 9003 }, { "epoch": 2.30464, "grad_norm": 1.65625, "learning_rate": 1.159457384182237e-05, "loss": 0.4147, "step": 9004 }, { "epoch": 2.304896, "grad_norm": 1.8515625, "learning_rate": 1.1590307994198448e-05, "loss": 0.4363, "step": 9005 }, { "epoch": 2.305152, "grad_norm": 1.8984375, "learning_rate": 1.1586042146574524e-05, "loss": 0.4406, "step": 9006 }, { "epoch": 2.305408, "grad_norm": 1.7109375, "learning_rate": 1.1581776298950601e-05, "loss": 0.4378, "step": 9007 }, { "epoch": 2.305664, "grad_norm": 1.7421875, "learning_rate": 1.1577510451326679e-05, "loss": 0.4056, "step": 9008 }, { "epoch": 2.30592, "grad_norm": 1.71875, "learning_rate": 1.1573244603702757e-05, "loss": 0.4144, "step": 9009 }, { "epoch": 2.306176, "grad_norm": 1.8046875, "learning_rate": 1.1568978756078834e-05, "loss": 0.4191, "step": 9010 }, { "epoch": 2.306432, "grad_norm": 1.7734375, "learning_rate": 1.156471290845491e-05, "loss": 0.4004, "step": 9011 }, { "epoch": 2.306688, "grad_norm": 1.7890625, "learning_rate": 1.1560447060830988e-05, "loss": 0.4498, "step": 9012 }, { "epoch": 2.306944, "grad_norm": 1.7578125, "learning_rate": 1.1556181213207066e-05, "loss": 0.4464, "step": 9013 }, { "epoch": 2.3072, "grad_norm": 1.8203125, "learning_rate": 1.1551915365583142e-05, "loss": 0.4304, "step": 9014 }, { "epoch": 2.307456, "grad_norm": 1.8515625, "learning_rate": 1.154764951795922e-05, "loss": 0.4305, "step": 9015 }, { "epoch": 2.307712, "grad_norm": 1.7890625, "learning_rate": 1.1543383670335297e-05, "loss": 0.4265, "step": 9016 }, { "epoch": 2.307968, "grad_norm": 1.9921875, "learning_rate": 1.1539117822711373e-05, "loss": 0.4241, "step": 9017 }, { "epoch": 2.308224, "grad_norm": 1.78125, "learning_rate": 1.153485197508745e-05, "loss": 0.4181, "step": 9018 }, { "epoch": 2.30848, "grad_norm": 1.828125, "learning_rate": 1.1530586127463528e-05, "loss": 0.4423, "step": 9019 }, { "epoch": 2.308736, "grad_norm": 1.828125, "learning_rate": 1.1526320279839604e-05, "loss": 0.4306, "step": 9020 }, { "epoch": 2.308992, "grad_norm": 1.7421875, "learning_rate": 1.1522054432215682e-05, "loss": 0.458, "step": 9021 }, { "epoch": 2.309248, "grad_norm": 1.90625, "learning_rate": 1.1517788584591758e-05, "loss": 0.4381, "step": 9022 }, { "epoch": 2.309504, "grad_norm": 1.734375, "learning_rate": 1.1513522736967835e-05, "loss": 0.4332, "step": 9023 }, { "epoch": 2.30976, "grad_norm": 1.7421875, "learning_rate": 1.1509256889343913e-05, "loss": 0.4386, "step": 9024 }, { "epoch": 2.310016, "grad_norm": 1.828125, "learning_rate": 1.1504991041719989e-05, "loss": 0.444, "step": 9025 }, { "epoch": 2.310272, "grad_norm": 1.8203125, "learning_rate": 1.1500725194096068e-05, "loss": 0.414, "step": 9026 }, { "epoch": 2.310528, "grad_norm": 2.0, "learning_rate": 1.1496459346472144e-05, "loss": 0.4439, "step": 9027 }, { "epoch": 2.310784, "grad_norm": 1.8515625, "learning_rate": 1.1492193498848222e-05, "loss": 0.4082, "step": 9028 }, { "epoch": 2.31104, "grad_norm": 1.8359375, "learning_rate": 1.14879276512243e-05, "loss": 0.4224, "step": 9029 }, { "epoch": 2.311296, "grad_norm": 1.65625, "learning_rate": 1.1483661803600376e-05, "loss": 0.4511, "step": 9030 }, { "epoch": 2.311552, "grad_norm": 1.6171875, "learning_rate": 1.1479395955976453e-05, "loss": 0.4289, "step": 9031 }, { "epoch": 2.311808, "grad_norm": 1.6796875, "learning_rate": 1.1475130108352531e-05, "loss": 0.439, "step": 9032 }, { "epoch": 2.312064, "grad_norm": 1.9140625, "learning_rate": 1.1470864260728607e-05, "loss": 0.3916, "step": 9033 }, { "epoch": 2.31232, "grad_norm": 1.6875, "learning_rate": 1.1466598413104684e-05, "loss": 0.4052, "step": 9034 }, { "epoch": 2.312576, "grad_norm": 1.7890625, "learning_rate": 1.1462332565480762e-05, "loss": 0.4316, "step": 9035 }, { "epoch": 2.312832, "grad_norm": 1.7578125, "learning_rate": 1.1458066717856838e-05, "loss": 0.3891, "step": 9036 }, { "epoch": 2.313088, "grad_norm": 1.8359375, "learning_rate": 1.1453800870232916e-05, "loss": 0.4085, "step": 9037 }, { "epoch": 2.313344, "grad_norm": 1.8203125, "learning_rate": 1.1449535022608993e-05, "loss": 0.4587, "step": 9038 }, { "epoch": 2.3136, "grad_norm": 1.9765625, "learning_rate": 1.144526917498507e-05, "loss": 0.4249, "step": 9039 }, { "epoch": 2.313856, "grad_norm": 1.8203125, "learning_rate": 1.1441003327361147e-05, "loss": 0.4374, "step": 9040 }, { "epoch": 2.314112, "grad_norm": 1.765625, "learning_rate": 1.1436737479737223e-05, "loss": 0.4002, "step": 9041 }, { "epoch": 2.314368, "grad_norm": 1.71875, "learning_rate": 1.1432471632113302e-05, "loss": 0.4134, "step": 9042 }, { "epoch": 2.3146240000000002, "grad_norm": 1.8203125, "learning_rate": 1.142820578448938e-05, "loss": 0.3879, "step": 9043 }, { "epoch": 2.31488, "grad_norm": 1.7734375, "learning_rate": 1.1423939936865456e-05, "loss": 0.3975, "step": 9044 }, { "epoch": 2.315136, "grad_norm": 1.828125, "learning_rate": 1.1419674089241534e-05, "loss": 0.4177, "step": 9045 }, { "epoch": 2.315392, "grad_norm": 1.8671875, "learning_rate": 1.141540824161761e-05, "loss": 0.4581, "step": 9046 }, { "epoch": 2.315648, "grad_norm": 1.734375, "learning_rate": 1.1411142393993687e-05, "loss": 0.4337, "step": 9047 }, { "epoch": 2.315904, "grad_norm": 1.8984375, "learning_rate": 1.1406876546369765e-05, "loss": 0.4219, "step": 9048 }, { "epoch": 2.31616, "grad_norm": 1.765625, "learning_rate": 1.140261069874584e-05, "loss": 0.4397, "step": 9049 }, { "epoch": 2.316416, "grad_norm": 1.7890625, "learning_rate": 1.1398344851121918e-05, "loss": 0.4235, "step": 9050 }, { "epoch": 2.316672, "grad_norm": 1.7890625, "learning_rate": 1.1394079003497996e-05, "loss": 0.4259, "step": 9051 }, { "epoch": 2.316928, "grad_norm": 1.8359375, "learning_rate": 1.1389813155874072e-05, "loss": 0.4363, "step": 9052 }, { "epoch": 2.317184, "grad_norm": 1.6484375, "learning_rate": 1.138554730825015e-05, "loss": 0.4384, "step": 9053 }, { "epoch": 2.31744, "grad_norm": 1.859375, "learning_rate": 1.1381281460626227e-05, "loss": 0.4303, "step": 9054 }, { "epoch": 2.3176959999999998, "grad_norm": 1.828125, "learning_rate": 1.1377015613002303e-05, "loss": 0.4377, "step": 9055 }, { "epoch": 2.317952, "grad_norm": 1.84375, "learning_rate": 1.1372749765378381e-05, "loss": 0.396, "step": 9056 }, { "epoch": 2.318208, "grad_norm": 1.7578125, "learning_rate": 1.1368483917754457e-05, "loss": 0.4143, "step": 9057 }, { "epoch": 2.318464, "grad_norm": 1.8671875, "learning_rate": 1.1364218070130535e-05, "loss": 0.4404, "step": 9058 }, { "epoch": 2.31872, "grad_norm": 2.03125, "learning_rate": 1.1359952222506614e-05, "loss": 0.4359, "step": 9059 }, { "epoch": 2.318976, "grad_norm": 1.9375, "learning_rate": 1.135568637488269e-05, "loss": 0.4118, "step": 9060 }, { "epoch": 2.319232, "grad_norm": 1.6953125, "learning_rate": 1.1351420527258768e-05, "loss": 0.3932, "step": 9061 }, { "epoch": 2.3194879999999998, "grad_norm": 1.7109375, "learning_rate": 1.1347154679634844e-05, "loss": 0.4426, "step": 9062 }, { "epoch": 2.319744, "grad_norm": 1.8046875, "learning_rate": 1.1342888832010921e-05, "loss": 0.4085, "step": 9063 }, { "epoch": 2.32, "grad_norm": 1.8671875, "learning_rate": 1.1338622984386999e-05, "loss": 0.4141, "step": 9064 }, { "epoch": 2.320256, "grad_norm": 1.8984375, "learning_rate": 1.1334357136763075e-05, "loss": 0.4114, "step": 9065 }, { "epoch": 2.320512, "grad_norm": 1.71875, "learning_rate": 1.1330091289139152e-05, "loss": 0.4276, "step": 9066 }, { "epoch": 2.320768, "grad_norm": 1.9765625, "learning_rate": 1.132582544151523e-05, "loss": 0.4, "step": 9067 }, { "epoch": 2.321024, "grad_norm": 1.8828125, "learning_rate": 1.1321559593891306e-05, "loss": 0.4491, "step": 9068 }, { "epoch": 2.32128, "grad_norm": 1.8046875, "learning_rate": 1.1317293746267384e-05, "loss": 0.4276, "step": 9069 }, { "epoch": 2.321536, "grad_norm": 1.96875, "learning_rate": 1.1313027898643461e-05, "loss": 0.3927, "step": 9070 }, { "epoch": 2.321792, "grad_norm": 1.859375, "learning_rate": 1.1308762051019537e-05, "loss": 0.4084, "step": 9071 }, { "epoch": 2.322048, "grad_norm": 1.9453125, "learning_rate": 1.1304496203395615e-05, "loss": 0.3929, "step": 9072 }, { "epoch": 2.322304, "grad_norm": 1.8203125, "learning_rate": 1.1300230355771691e-05, "loss": 0.4206, "step": 9073 }, { "epoch": 2.32256, "grad_norm": 1.875, "learning_rate": 1.1295964508147769e-05, "loss": 0.4278, "step": 9074 }, { "epoch": 2.322816, "grad_norm": 1.8125, "learning_rate": 1.1291698660523848e-05, "loss": 0.4304, "step": 9075 }, { "epoch": 2.323072, "grad_norm": 1.8125, "learning_rate": 1.1287432812899924e-05, "loss": 0.4268, "step": 9076 }, { "epoch": 2.323328, "grad_norm": 1.84375, "learning_rate": 1.1283166965276002e-05, "loss": 0.4237, "step": 9077 }, { "epoch": 2.323584, "grad_norm": 1.8984375, "learning_rate": 1.1278901117652078e-05, "loss": 0.4506, "step": 9078 }, { "epoch": 2.32384, "grad_norm": 1.65625, "learning_rate": 1.1274635270028155e-05, "loss": 0.4175, "step": 9079 }, { "epoch": 2.324096, "grad_norm": 1.859375, "learning_rate": 1.1270369422404233e-05, "loss": 0.4198, "step": 9080 }, { "epoch": 2.324352, "grad_norm": 1.9140625, "learning_rate": 1.1266103574780309e-05, "loss": 0.4132, "step": 9081 }, { "epoch": 2.324608, "grad_norm": 1.8046875, "learning_rate": 1.1261837727156386e-05, "loss": 0.465, "step": 9082 }, { "epoch": 2.324864, "grad_norm": 1.8203125, "learning_rate": 1.1257571879532464e-05, "loss": 0.4409, "step": 9083 }, { "epoch": 2.32512, "grad_norm": 1.8828125, "learning_rate": 1.125330603190854e-05, "loss": 0.4176, "step": 9084 }, { "epoch": 2.325376, "grad_norm": 1.9140625, "learning_rate": 1.1249040184284618e-05, "loss": 0.4155, "step": 9085 }, { "epoch": 2.325632, "grad_norm": 1.890625, "learning_rate": 1.1244774336660695e-05, "loss": 0.4187, "step": 9086 }, { "epoch": 2.325888, "grad_norm": 1.796875, "learning_rate": 1.1240508489036771e-05, "loss": 0.4584, "step": 9087 }, { "epoch": 2.326144, "grad_norm": 1.7734375, "learning_rate": 1.1236242641412849e-05, "loss": 0.4183, "step": 9088 }, { "epoch": 2.3264, "grad_norm": 1.7265625, "learning_rate": 1.1231976793788927e-05, "loss": 0.4092, "step": 9089 }, { "epoch": 2.326656, "grad_norm": 1.796875, "learning_rate": 1.1227710946165003e-05, "loss": 0.4463, "step": 9090 }, { "epoch": 2.326912, "grad_norm": 1.8359375, "learning_rate": 1.1223445098541082e-05, "loss": 0.4169, "step": 9091 }, { "epoch": 2.327168, "grad_norm": 1.8984375, "learning_rate": 1.1219179250917158e-05, "loss": 0.387, "step": 9092 }, { "epoch": 2.327424, "grad_norm": 1.78125, "learning_rate": 1.1214913403293236e-05, "loss": 0.4179, "step": 9093 }, { "epoch": 2.32768, "grad_norm": 1.859375, "learning_rate": 1.1210647555669313e-05, "loss": 0.4004, "step": 9094 }, { "epoch": 2.3279360000000002, "grad_norm": 1.875, "learning_rate": 1.120638170804539e-05, "loss": 0.4254, "step": 9095 }, { "epoch": 2.328192, "grad_norm": 1.78125, "learning_rate": 1.1202115860421467e-05, "loss": 0.4294, "step": 9096 }, { "epoch": 2.328448, "grad_norm": 1.8984375, "learning_rate": 1.1197850012797543e-05, "loss": 0.4365, "step": 9097 }, { "epoch": 2.328704, "grad_norm": 1.734375, "learning_rate": 1.119358416517362e-05, "loss": 0.4466, "step": 9098 }, { "epoch": 2.32896, "grad_norm": 1.796875, "learning_rate": 1.1189318317549698e-05, "loss": 0.4137, "step": 9099 }, { "epoch": 2.329216, "grad_norm": 1.859375, "learning_rate": 1.1185052469925774e-05, "loss": 0.4092, "step": 9100 }, { "epoch": 2.329472, "grad_norm": 1.9375, "learning_rate": 1.1180786622301852e-05, "loss": 0.4489, "step": 9101 }, { "epoch": 2.3297280000000002, "grad_norm": 1.75, "learning_rate": 1.117652077467793e-05, "loss": 0.426, "step": 9102 }, { "epoch": 2.329984, "grad_norm": 1.796875, "learning_rate": 1.1172254927054005e-05, "loss": 0.4302, "step": 9103 }, { "epoch": 2.33024, "grad_norm": 1.8984375, "learning_rate": 1.1167989079430083e-05, "loss": 0.4454, "step": 9104 }, { "epoch": 2.330496, "grad_norm": 1.8359375, "learning_rate": 1.116372323180616e-05, "loss": 0.4396, "step": 9105 }, { "epoch": 2.330752, "grad_norm": 1.8046875, "learning_rate": 1.1159457384182237e-05, "loss": 0.439, "step": 9106 }, { "epoch": 2.331008, "grad_norm": 1.7734375, "learning_rate": 1.1155191536558314e-05, "loss": 0.4256, "step": 9107 }, { "epoch": 2.331264, "grad_norm": 1.71875, "learning_rate": 1.1150925688934392e-05, "loss": 0.3876, "step": 9108 }, { "epoch": 2.33152, "grad_norm": 1.796875, "learning_rate": 1.114665984131047e-05, "loss": 0.4273, "step": 9109 }, { "epoch": 2.331776, "grad_norm": 1.8203125, "learning_rate": 1.1142393993686547e-05, "loss": 0.427, "step": 9110 }, { "epoch": 2.332032, "grad_norm": 1.7421875, "learning_rate": 1.1138128146062623e-05, "loss": 0.4317, "step": 9111 }, { "epoch": 2.332288, "grad_norm": 1.8359375, "learning_rate": 1.1133862298438701e-05, "loss": 0.4044, "step": 9112 }, { "epoch": 2.332544, "grad_norm": 1.8828125, "learning_rate": 1.1129596450814777e-05, "loss": 0.4268, "step": 9113 }, { "epoch": 2.3327999999999998, "grad_norm": 1.765625, "learning_rate": 1.1125330603190854e-05, "loss": 0.3892, "step": 9114 }, { "epoch": 2.333056, "grad_norm": 1.6875, "learning_rate": 1.1121064755566932e-05, "loss": 0.4138, "step": 9115 }, { "epoch": 2.333312, "grad_norm": 1.78125, "learning_rate": 1.1116798907943008e-05, "loss": 0.3931, "step": 9116 }, { "epoch": 2.333568, "grad_norm": 1.8359375, "learning_rate": 1.1112533060319086e-05, "loss": 0.3817, "step": 9117 }, { "epoch": 2.333824, "grad_norm": 1.75, "learning_rate": 1.1108267212695163e-05, "loss": 0.4489, "step": 9118 }, { "epoch": 2.33408, "grad_norm": 1.84375, "learning_rate": 1.110400136507124e-05, "loss": 0.4287, "step": 9119 }, { "epoch": 2.334336, "grad_norm": 2.015625, "learning_rate": 1.1099735517447317e-05, "loss": 0.4457, "step": 9120 }, { "epoch": 2.334592, "grad_norm": 1.7734375, "learning_rate": 1.1095469669823395e-05, "loss": 0.4333, "step": 9121 }, { "epoch": 2.334848, "grad_norm": 1.75, "learning_rate": 1.109120382219947e-05, "loss": 0.4144, "step": 9122 }, { "epoch": 2.335104, "grad_norm": 1.8203125, "learning_rate": 1.1086937974575548e-05, "loss": 0.4133, "step": 9123 }, { "epoch": 2.33536, "grad_norm": 1.828125, "learning_rate": 1.1082672126951626e-05, "loss": 0.4245, "step": 9124 }, { "epoch": 2.335616, "grad_norm": 1.7578125, "learning_rate": 1.1078406279327704e-05, "loss": 0.4246, "step": 9125 }, { "epoch": 2.335872, "grad_norm": 1.8671875, "learning_rate": 1.1074140431703781e-05, "loss": 0.4167, "step": 9126 }, { "epoch": 2.336128, "grad_norm": 1.6875, "learning_rate": 1.1069874584079857e-05, "loss": 0.4068, "step": 9127 }, { "epoch": 2.336384, "grad_norm": 1.6796875, "learning_rate": 1.1065608736455935e-05, "loss": 0.4021, "step": 9128 }, { "epoch": 2.33664, "grad_norm": 1.796875, "learning_rate": 1.1061342888832013e-05, "loss": 0.4044, "step": 9129 }, { "epoch": 2.336896, "grad_norm": 1.828125, "learning_rate": 1.1057077041208088e-05, "loss": 0.4007, "step": 9130 }, { "epoch": 2.337152, "grad_norm": 1.7421875, "learning_rate": 1.1052811193584166e-05, "loss": 0.4597, "step": 9131 }, { "epoch": 2.337408, "grad_norm": 1.8203125, "learning_rate": 1.1048545345960242e-05, "loss": 0.4217, "step": 9132 }, { "epoch": 2.337664, "grad_norm": 1.71875, "learning_rate": 1.104427949833632e-05, "loss": 0.3711, "step": 9133 }, { "epoch": 2.33792, "grad_norm": 1.7890625, "learning_rate": 1.1040013650712397e-05, "loss": 0.4389, "step": 9134 }, { "epoch": 2.338176, "grad_norm": 1.734375, "learning_rate": 1.1035747803088473e-05, "loss": 0.3941, "step": 9135 }, { "epoch": 2.338432, "grad_norm": 1.8125, "learning_rate": 1.1031481955464551e-05, "loss": 0.3927, "step": 9136 }, { "epoch": 2.338688, "grad_norm": 1.8515625, "learning_rate": 1.1027216107840629e-05, "loss": 0.4093, "step": 9137 }, { "epoch": 2.338944, "grad_norm": 1.7890625, "learning_rate": 1.1022950260216705e-05, "loss": 0.4424, "step": 9138 }, { "epoch": 2.3392, "grad_norm": 1.7890625, "learning_rate": 1.1018684412592782e-05, "loss": 0.4284, "step": 9139 }, { "epoch": 2.339456, "grad_norm": 1.6796875, "learning_rate": 1.101441856496886e-05, "loss": 0.3768, "step": 9140 }, { "epoch": 2.339712, "grad_norm": 1.8359375, "learning_rate": 1.1010152717344938e-05, "loss": 0.4249, "step": 9141 }, { "epoch": 2.339968, "grad_norm": 1.7109375, "learning_rate": 1.1005886869721015e-05, "loss": 0.4197, "step": 9142 }, { "epoch": 2.340224, "grad_norm": 1.7578125, "learning_rate": 1.1001621022097091e-05, "loss": 0.4332, "step": 9143 }, { "epoch": 2.34048, "grad_norm": 1.9765625, "learning_rate": 1.0997355174473169e-05, "loss": 0.4202, "step": 9144 }, { "epoch": 2.340736, "grad_norm": 1.796875, "learning_rate": 1.0993089326849247e-05, "loss": 0.4267, "step": 9145 }, { "epoch": 2.340992, "grad_norm": 1.703125, "learning_rate": 1.0988823479225322e-05, "loss": 0.4339, "step": 9146 }, { "epoch": 2.341248, "grad_norm": 1.6875, "learning_rate": 1.09845576316014e-05, "loss": 0.4318, "step": 9147 }, { "epoch": 2.341504, "grad_norm": 1.7578125, "learning_rate": 1.0980291783977476e-05, "loss": 0.3981, "step": 9148 }, { "epoch": 2.34176, "grad_norm": 1.7265625, "learning_rate": 1.0976025936353554e-05, "loss": 0.4355, "step": 9149 }, { "epoch": 2.342016, "grad_norm": 1.78125, "learning_rate": 1.0971760088729631e-05, "loss": 0.4308, "step": 9150 }, { "epoch": 2.342272, "grad_norm": 1.7734375, "learning_rate": 1.0967494241105707e-05, "loss": 0.4192, "step": 9151 }, { "epoch": 2.342528, "grad_norm": 1.6796875, "learning_rate": 1.0963228393481785e-05, "loss": 0.4217, "step": 9152 }, { "epoch": 2.342784, "grad_norm": 1.8515625, "learning_rate": 1.0958962545857863e-05, "loss": 0.473, "step": 9153 }, { "epoch": 2.3430400000000002, "grad_norm": 1.8359375, "learning_rate": 1.0954696698233939e-05, "loss": 0.4204, "step": 9154 }, { "epoch": 2.343296, "grad_norm": 1.7421875, "learning_rate": 1.0950430850610016e-05, "loss": 0.4335, "step": 9155 }, { "epoch": 2.343552, "grad_norm": 1.890625, "learning_rate": 1.0946165002986094e-05, "loss": 0.406, "step": 9156 }, { "epoch": 2.343808, "grad_norm": 1.71875, "learning_rate": 1.0941899155362172e-05, "loss": 0.3986, "step": 9157 }, { "epoch": 2.344064, "grad_norm": 1.84375, "learning_rate": 1.093763330773825e-05, "loss": 0.43, "step": 9158 }, { "epoch": 2.34432, "grad_norm": 1.671875, "learning_rate": 1.0933367460114325e-05, "loss": 0.434, "step": 9159 }, { "epoch": 2.344576, "grad_norm": 1.71875, "learning_rate": 1.0929101612490403e-05, "loss": 0.4004, "step": 9160 }, { "epoch": 2.3448320000000002, "grad_norm": 1.671875, "learning_rate": 1.092483576486648e-05, "loss": 0.4507, "step": 9161 }, { "epoch": 2.345088, "grad_norm": 1.828125, "learning_rate": 1.0920569917242556e-05, "loss": 0.4455, "step": 9162 }, { "epoch": 2.345344, "grad_norm": 1.765625, "learning_rate": 1.0916304069618634e-05, "loss": 0.4254, "step": 9163 }, { "epoch": 2.3456, "grad_norm": 1.7890625, "learning_rate": 1.091203822199471e-05, "loss": 0.4402, "step": 9164 }, { "epoch": 2.345856, "grad_norm": 1.828125, "learning_rate": 1.0907772374370788e-05, "loss": 0.4225, "step": 9165 }, { "epoch": 2.3461119999999998, "grad_norm": 1.9375, "learning_rate": 1.0903506526746865e-05, "loss": 0.4232, "step": 9166 }, { "epoch": 2.346368, "grad_norm": 1.75, "learning_rate": 1.0899240679122941e-05, "loss": 0.4443, "step": 9167 }, { "epoch": 2.346624, "grad_norm": 1.84375, "learning_rate": 1.0894974831499019e-05, "loss": 0.3915, "step": 9168 }, { "epoch": 2.34688, "grad_norm": 1.7265625, "learning_rate": 1.0890708983875097e-05, "loss": 0.4127, "step": 9169 }, { "epoch": 2.347136, "grad_norm": 1.8046875, "learning_rate": 1.0886443136251173e-05, "loss": 0.4293, "step": 9170 }, { "epoch": 2.347392, "grad_norm": 1.9375, "learning_rate": 1.088217728862725e-05, "loss": 0.4414, "step": 9171 }, { "epoch": 2.347648, "grad_norm": 1.71875, "learning_rate": 1.0877911441003328e-05, "loss": 0.4144, "step": 9172 }, { "epoch": 2.3479039999999998, "grad_norm": 1.765625, "learning_rate": 1.0873645593379406e-05, "loss": 0.4233, "step": 9173 }, { "epoch": 2.34816, "grad_norm": 1.7890625, "learning_rate": 1.0869379745755483e-05, "loss": 0.4227, "step": 9174 }, { "epoch": 2.348416, "grad_norm": 1.9765625, "learning_rate": 1.086511389813156e-05, "loss": 0.4505, "step": 9175 }, { "epoch": 2.348672, "grad_norm": 1.84375, "learning_rate": 1.0860848050507637e-05, "loss": 0.4142, "step": 9176 }, { "epoch": 2.348928, "grad_norm": 1.78125, "learning_rate": 1.0856582202883715e-05, "loss": 0.4397, "step": 9177 }, { "epoch": 2.349184, "grad_norm": 1.625, "learning_rate": 1.085231635525979e-05, "loss": 0.4051, "step": 9178 }, { "epoch": 2.34944, "grad_norm": 1.78125, "learning_rate": 1.0848050507635868e-05, "loss": 0.4185, "step": 9179 }, { "epoch": 2.349696, "grad_norm": 1.6640625, "learning_rate": 1.0843784660011946e-05, "loss": 0.4315, "step": 9180 }, { "epoch": 2.349952, "grad_norm": 1.7109375, "learning_rate": 1.0839518812388022e-05, "loss": 0.4431, "step": 9181 }, { "epoch": 2.350208, "grad_norm": 1.8203125, "learning_rate": 1.08352529647641e-05, "loss": 0.4665, "step": 9182 }, { "epoch": 2.350464, "grad_norm": 1.84375, "learning_rate": 1.0830987117140175e-05, "loss": 0.4274, "step": 9183 }, { "epoch": 2.35072, "grad_norm": 1.875, "learning_rate": 1.0826721269516253e-05, "loss": 0.4933, "step": 9184 }, { "epoch": 2.350976, "grad_norm": 1.953125, "learning_rate": 1.082245542189233e-05, "loss": 0.4188, "step": 9185 }, { "epoch": 2.351232, "grad_norm": 1.703125, "learning_rate": 1.0818189574268407e-05, "loss": 0.4588, "step": 9186 }, { "epoch": 2.351488, "grad_norm": 1.65625, "learning_rate": 1.0813923726644484e-05, "loss": 0.4376, "step": 9187 }, { "epoch": 2.351744, "grad_norm": 1.703125, "learning_rate": 1.0809657879020562e-05, "loss": 0.4438, "step": 9188 }, { "epoch": 2.352, "grad_norm": 1.6953125, "learning_rate": 1.0805392031396638e-05, "loss": 0.452, "step": 9189 }, { "epoch": 2.352256, "grad_norm": 1.765625, "learning_rate": 1.0801126183772717e-05, "loss": 0.4026, "step": 9190 }, { "epoch": 2.352512, "grad_norm": 1.765625, "learning_rate": 1.0796860336148793e-05, "loss": 0.43, "step": 9191 }, { "epoch": 2.352768, "grad_norm": 1.65625, "learning_rate": 1.0792594488524871e-05, "loss": 0.4368, "step": 9192 }, { "epoch": 2.353024, "grad_norm": 1.7578125, "learning_rate": 1.0788328640900949e-05, "loss": 0.4079, "step": 9193 }, { "epoch": 2.35328, "grad_norm": 1.7421875, "learning_rate": 1.0784062793277024e-05, "loss": 0.4223, "step": 9194 }, { "epoch": 2.353536, "grad_norm": 1.7265625, "learning_rate": 1.0779796945653102e-05, "loss": 0.4032, "step": 9195 }, { "epoch": 2.353792, "grad_norm": 1.8359375, "learning_rate": 1.077553109802918e-05, "loss": 0.4061, "step": 9196 }, { "epoch": 2.354048, "grad_norm": 2.078125, "learning_rate": 1.0771265250405256e-05, "loss": 0.4249, "step": 9197 }, { "epoch": 2.354304, "grad_norm": 1.6875, "learning_rate": 1.0766999402781333e-05, "loss": 0.4588, "step": 9198 }, { "epoch": 2.35456, "grad_norm": 1.828125, "learning_rate": 1.076273355515741e-05, "loss": 0.4042, "step": 9199 }, { "epoch": 2.354816, "grad_norm": 1.84375, "learning_rate": 1.0758467707533487e-05, "loss": 0.4589, "step": 9200 }, { "epoch": 2.355072, "grad_norm": 1.75, "learning_rate": 1.0754201859909565e-05, "loss": 0.4232, "step": 9201 }, { "epoch": 2.355328, "grad_norm": 1.75, "learning_rate": 1.074993601228564e-05, "loss": 0.4295, "step": 9202 }, { "epoch": 2.355584, "grad_norm": 1.8515625, "learning_rate": 1.0745670164661718e-05, "loss": 0.4296, "step": 9203 }, { "epoch": 2.35584, "grad_norm": 1.65625, "learning_rate": 1.0741404317037796e-05, "loss": 0.4442, "step": 9204 }, { "epoch": 2.356096, "grad_norm": 1.796875, "learning_rate": 1.0737138469413872e-05, "loss": 0.4593, "step": 9205 }, { "epoch": 2.3563520000000002, "grad_norm": 1.890625, "learning_rate": 1.0732872621789951e-05, "loss": 0.4443, "step": 9206 }, { "epoch": 2.356608, "grad_norm": 1.75, "learning_rate": 1.0728606774166027e-05, "loss": 0.4155, "step": 9207 }, { "epoch": 2.356864, "grad_norm": 1.859375, "learning_rate": 1.0724340926542105e-05, "loss": 0.409, "step": 9208 }, { "epoch": 2.35712, "grad_norm": 1.7734375, "learning_rate": 1.0720075078918183e-05, "loss": 0.4099, "step": 9209 }, { "epoch": 2.357376, "grad_norm": 1.7109375, "learning_rate": 1.0715809231294258e-05, "loss": 0.4193, "step": 9210 }, { "epoch": 2.357632, "grad_norm": 1.7578125, "learning_rate": 1.0711543383670336e-05, "loss": 0.4489, "step": 9211 }, { "epoch": 2.357888, "grad_norm": 1.7421875, "learning_rate": 1.0707277536046414e-05, "loss": 0.4486, "step": 9212 }, { "epoch": 2.3581440000000002, "grad_norm": 1.6796875, "learning_rate": 1.070301168842249e-05, "loss": 0.4138, "step": 9213 }, { "epoch": 2.3584, "grad_norm": 1.796875, "learning_rate": 1.0698745840798567e-05, "loss": 0.4833, "step": 9214 }, { "epoch": 2.358656, "grad_norm": 1.8046875, "learning_rate": 1.0694479993174643e-05, "loss": 0.4082, "step": 9215 }, { "epoch": 2.358912, "grad_norm": 1.890625, "learning_rate": 1.0690214145550721e-05, "loss": 0.431, "step": 9216 }, { "epoch": 2.359168, "grad_norm": 1.7734375, "learning_rate": 1.0685948297926799e-05, "loss": 0.4262, "step": 9217 }, { "epoch": 2.359424, "grad_norm": 1.8125, "learning_rate": 1.0681682450302875e-05, "loss": 0.3901, "step": 9218 }, { "epoch": 2.35968, "grad_norm": 1.6796875, "learning_rate": 1.0677416602678952e-05, "loss": 0.445, "step": 9219 }, { "epoch": 2.359936, "grad_norm": 1.8359375, "learning_rate": 1.067315075505503e-05, "loss": 0.427, "step": 9220 }, { "epoch": 2.360192, "grad_norm": 1.8984375, "learning_rate": 1.0668884907431106e-05, "loss": 0.4153, "step": 9221 }, { "epoch": 2.360448, "grad_norm": 1.75, "learning_rate": 1.0664619059807184e-05, "loss": 0.4599, "step": 9222 }, { "epoch": 2.360704, "grad_norm": 1.9375, "learning_rate": 1.0660353212183261e-05, "loss": 0.4498, "step": 9223 }, { "epoch": 2.36096, "grad_norm": 1.6953125, "learning_rate": 1.0656087364559339e-05, "loss": 0.4097, "step": 9224 }, { "epoch": 2.3612159999999998, "grad_norm": 1.8984375, "learning_rate": 1.0651821516935417e-05, "loss": 0.4427, "step": 9225 }, { "epoch": 2.361472, "grad_norm": 1.75, "learning_rate": 1.0647555669311492e-05, "loss": 0.4574, "step": 9226 }, { "epoch": 2.361728, "grad_norm": 1.796875, "learning_rate": 1.064328982168757e-05, "loss": 0.4118, "step": 9227 }, { "epoch": 2.361984, "grad_norm": 1.796875, "learning_rate": 1.0639023974063648e-05, "loss": 0.417, "step": 9228 }, { "epoch": 2.36224, "grad_norm": 1.859375, "learning_rate": 1.0634758126439724e-05, "loss": 0.4197, "step": 9229 }, { "epoch": 2.362496, "grad_norm": 1.8828125, "learning_rate": 1.0630492278815801e-05, "loss": 0.3848, "step": 9230 }, { "epoch": 2.362752, "grad_norm": 1.84375, "learning_rate": 1.0626226431191879e-05, "loss": 0.3957, "step": 9231 }, { "epoch": 2.3630079999999998, "grad_norm": 1.9609375, "learning_rate": 1.0621960583567955e-05, "loss": 0.4037, "step": 9232 }, { "epoch": 2.363264, "grad_norm": 1.765625, "learning_rate": 1.0617694735944033e-05, "loss": 0.4596, "step": 9233 }, { "epoch": 2.36352, "grad_norm": 1.703125, "learning_rate": 1.0613428888320109e-05, "loss": 0.4588, "step": 9234 }, { "epoch": 2.363776, "grad_norm": 1.6953125, "learning_rate": 1.0609163040696186e-05, "loss": 0.4299, "step": 9235 }, { "epoch": 2.364032, "grad_norm": 1.859375, "learning_rate": 1.0604897193072264e-05, "loss": 0.3976, "step": 9236 }, { "epoch": 2.364288, "grad_norm": 1.9375, "learning_rate": 1.060063134544834e-05, "loss": 0.4115, "step": 9237 }, { "epoch": 2.364544, "grad_norm": 1.8125, "learning_rate": 1.0596365497824418e-05, "loss": 0.4167, "step": 9238 }, { "epoch": 2.3648, "grad_norm": 1.71875, "learning_rate": 1.0592099650200495e-05, "loss": 0.4014, "step": 9239 }, { "epoch": 2.365056, "grad_norm": 1.75, "learning_rate": 1.0587833802576573e-05, "loss": 0.3975, "step": 9240 }, { "epoch": 2.365312, "grad_norm": 1.6953125, "learning_rate": 1.058356795495265e-05, "loss": 0.3933, "step": 9241 }, { "epoch": 2.365568, "grad_norm": 1.765625, "learning_rate": 1.0579302107328726e-05, "loss": 0.4041, "step": 9242 }, { "epoch": 2.365824, "grad_norm": 1.6796875, "learning_rate": 1.0575036259704804e-05, "loss": 0.4048, "step": 9243 }, { "epoch": 2.36608, "grad_norm": 1.8671875, "learning_rate": 1.0570770412080882e-05, "loss": 0.4159, "step": 9244 }, { "epoch": 2.366336, "grad_norm": 1.75, "learning_rate": 1.0566504564456958e-05, "loss": 0.4045, "step": 9245 }, { "epoch": 2.366592, "grad_norm": 1.7109375, "learning_rate": 1.0562238716833035e-05, "loss": 0.4102, "step": 9246 }, { "epoch": 2.366848, "grad_norm": 1.8203125, "learning_rate": 1.0557972869209113e-05, "loss": 0.4022, "step": 9247 }, { "epoch": 2.367104, "grad_norm": 1.6875, "learning_rate": 1.0553707021585189e-05, "loss": 0.4447, "step": 9248 }, { "epoch": 2.36736, "grad_norm": 1.8203125, "learning_rate": 1.0549441173961267e-05, "loss": 0.4468, "step": 9249 }, { "epoch": 2.367616, "grad_norm": 1.7265625, "learning_rate": 1.0545175326337343e-05, "loss": 0.4185, "step": 9250 }, { "epoch": 2.367872, "grad_norm": 1.875, "learning_rate": 1.054090947871342e-05, "loss": 0.431, "step": 9251 }, { "epoch": 2.368128, "grad_norm": 1.78125, "learning_rate": 1.0536643631089498e-05, "loss": 0.419, "step": 9252 }, { "epoch": 2.368384, "grad_norm": 1.6875, "learning_rate": 1.0532377783465574e-05, "loss": 0.4248, "step": 9253 }, { "epoch": 2.36864, "grad_norm": 1.703125, "learning_rate": 1.0528111935841652e-05, "loss": 0.4303, "step": 9254 }, { "epoch": 2.368896, "grad_norm": 1.78125, "learning_rate": 1.052384608821773e-05, "loss": 0.4398, "step": 9255 }, { "epoch": 2.369152, "grad_norm": 1.796875, "learning_rate": 1.0519580240593807e-05, "loss": 0.4419, "step": 9256 }, { "epoch": 2.369408, "grad_norm": 1.765625, "learning_rate": 1.0515314392969885e-05, "loss": 0.4156, "step": 9257 }, { "epoch": 2.369664, "grad_norm": 1.8828125, "learning_rate": 1.051104854534596e-05, "loss": 0.3975, "step": 9258 }, { "epoch": 2.36992, "grad_norm": 1.8203125, "learning_rate": 1.0506782697722038e-05, "loss": 0.4281, "step": 9259 }, { "epoch": 2.370176, "grad_norm": 1.8203125, "learning_rate": 1.0502516850098116e-05, "loss": 0.4033, "step": 9260 }, { "epoch": 2.370432, "grad_norm": 1.8203125, "learning_rate": 1.0498251002474192e-05, "loss": 0.4596, "step": 9261 }, { "epoch": 2.370688, "grad_norm": 1.8515625, "learning_rate": 1.049398515485027e-05, "loss": 0.4303, "step": 9262 }, { "epoch": 2.370944, "grad_norm": 1.8828125, "learning_rate": 1.0489719307226347e-05, "loss": 0.4372, "step": 9263 }, { "epoch": 2.3712, "grad_norm": 1.7734375, "learning_rate": 1.0485453459602423e-05, "loss": 0.4215, "step": 9264 }, { "epoch": 2.3714560000000002, "grad_norm": 1.859375, "learning_rate": 1.04811876119785e-05, "loss": 0.4118, "step": 9265 }, { "epoch": 2.371712, "grad_norm": 1.953125, "learning_rate": 1.0476921764354578e-05, "loss": 0.4617, "step": 9266 }, { "epoch": 2.371968, "grad_norm": 1.765625, "learning_rate": 1.0472655916730654e-05, "loss": 0.4419, "step": 9267 }, { "epoch": 2.372224, "grad_norm": 1.7421875, "learning_rate": 1.0468390069106732e-05, "loss": 0.4338, "step": 9268 }, { "epoch": 2.37248, "grad_norm": 1.734375, "learning_rate": 1.0464124221482808e-05, "loss": 0.4022, "step": 9269 }, { "epoch": 2.372736, "grad_norm": 1.734375, "learning_rate": 1.0459858373858886e-05, "loss": 0.4234, "step": 9270 }, { "epoch": 2.372992, "grad_norm": 1.828125, "learning_rate": 1.0455592526234963e-05, "loss": 0.4322, "step": 9271 }, { "epoch": 2.3732480000000002, "grad_norm": 1.6953125, "learning_rate": 1.0451326678611041e-05, "loss": 0.4004, "step": 9272 }, { "epoch": 2.373504, "grad_norm": 1.828125, "learning_rate": 1.0447060830987119e-05, "loss": 0.3955, "step": 9273 }, { "epoch": 2.37376, "grad_norm": 1.8046875, "learning_rate": 1.0442794983363194e-05, "loss": 0.3882, "step": 9274 }, { "epoch": 2.374016, "grad_norm": 1.703125, "learning_rate": 1.0438529135739272e-05, "loss": 0.4266, "step": 9275 }, { "epoch": 2.374272, "grad_norm": 1.875, "learning_rate": 1.043426328811535e-05, "loss": 0.401, "step": 9276 }, { "epoch": 2.374528, "grad_norm": 1.7265625, "learning_rate": 1.0429997440491426e-05, "loss": 0.4134, "step": 9277 }, { "epoch": 2.374784, "grad_norm": 1.71875, "learning_rate": 1.0425731592867503e-05, "loss": 0.463, "step": 9278 }, { "epoch": 2.37504, "grad_norm": 1.8125, "learning_rate": 1.0421465745243581e-05, "loss": 0.3703, "step": 9279 }, { "epoch": 2.375296, "grad_norm": 1.78125, "learning_rate": 1.0417199897619657e-05, "loss": 0.4248, "step": 9280 }, { "epoch": 2.375552, "grad_norm": 1.8671875, "learning_rate": 1.0412934049995735e-05, "loss": 0.42, "step": 9281 }, { "epoch": 2.375808, "grad_norm": 1.78125, "learning_rate": 1.0408668202371812e-05, "loss": 0.4167, "step": 9282 }, { "epoch": 2.376064, "grad_norm": 1.7421875, "learning_rate": 1.0404402354747888e-05, "loss": 0.4137, "step": 9283 }, { "epoch": 2.3763199999999998, "grad_norm": 1.84375, "learning_rate": 1.0400136507123966e-05, "loss": 0.3849, "step": 9284 }, { "epoch": 2.376576, "grad_norm": 1.703125, "learning_rate": 1.0395870659500042e-05, "loss": 0.4019, "step": 9285 }, { "epoch": 2.376832, "grad_norm": 1.578125, "learning_rate": 1.039160481187612e-05, "loss": 0.4225, "step": 9286 }, { "epoch": 2.377088, "grad_norm": 1.8046875, "learning_rate": 1.0387338964252197e-05, "loss": 0.4326, "step": 9287 }, { "epoch": 2.377344, "grad_norm": 1.8515625, "learning_rate": 1.0383073116628275e-05, "loss": 0.451, "step": 9288 }, { "epoch": 2.3776, "grad_norm": 1.6875, "learning_rate": 1.0378807269004353e-05, "loss": 0.4317, "step": 9289 }, { "epoch": 2.377856, "grad_norm": 1.7109375, "learning_rate": 1.0374541421380428e-05, "loss": 0.4393, "step": 9290 }, { "epoch": 2.378112, "grad_norm": 1.921875, "learning_rate": 1.0370275573756506e-05, "loss": 0.4368, "step": 9291 }, { "epoch": 2.378368, "grad_norm": 1.7578125, "learning_rate": 1.0366009726132584e-05, "loss": 0.4532, "step": 9292 }, { "epoch": 2.378624, "grad_norm": 1.828125, "learning_rate": 1.036174387850866e-05, "loss": 0.4232, "step": 9293 }, { "epoch": 2.37888, "grad_norm": 1.84375, "learning_rate": 1.0357478030884737e-05, "loss": 0.3949, "step": 9294 }, { "epoch": 2.379136, "grad_norm": 1.859375, "learning_rate": 1.0353212183260815e-05, "loss": 0.4116, "step": 9295 }, { "epoch": 2.379392, "grad_norm": 1.6796875, "learning_rate": 1.0348946335636891e-05, "loss": 0.4316, "step": 9296 }, { "epoch": 2.379648, "grad_norm": 1.703125, "learning_rate": 1.0344680488012969e-05, "loss": 0.4122, "step": 9297 }, { "epoch": 2.379904, "grad_norm": 1.9296875, "learning_rate": 1.0340414640389046e-05, "loss": 0.4541, "step": 9298 }, { "epoch": 2.38016, "grad_norm": 1.828125, "learning_rate": 1.0336148792765122e-05, "loss": 0.4075, "step": 9299 }, { "epoch": 2.380416, "grad_norm": 1.703125, "learning_rate": 1.03318829451412e-05, "loss": 0.4194, "step": 9300 }, { "epoch": 2.380672, "grad_norm": 1.6875, "learning_rate": 1.0327617097517276e-05, "loss": 0.4387, "step": 9301 }, { "epoch": 2.380928, "grad_norm": 1.8359375, "learning_rate": 1.0323351249893354e-05, "loss": 0.4419, "step": 9302 }, { "epoch": 2.381184, "grad_norm": 1.7734375, "learning_rate": 1.0319085402269431e-05, "loss": 0.431, "step": 9303 }, { "epoch": 2.38144, "grad_norm": 1.7578125, "learning_rate": 1.0314819554645507e-05, "loss": 0.4107, "step": 9304 }, { "epoch": 2.381696, "grad_norm": 1.8046875, "learning_rate": 1.0310553707021587e-05, "loss": 0.3988, "step": 9305 }, { "epoch": 2.381952, "grad_norm": 1.8359375, "learning_rate": 1.0306287859397662e-05, "loss": 0.421, "step": 9306 }, { "epoch": 2.382208, "grad_norm": 1.9140625, "learning_rate": 1.030202201177374e-05, "loss": 0.4191, "step": 9307 }, { "epoch": 2.382464, "grad_norm": 1.703125, "learning_rate": 1.0297756164149818e-05, "loss": 0.4239, "step": 9308 }, { "epoch": 2.38272, "grad_norm": 1.8984375, "learning_rate": 1.0293490316525894e-05, "loss": 0.4529, "step": 9309 }, { "epoch": 2.382976, "grad_norm": 1.765625, "learning_rate": 1.0289224468901971e-05, "loss": 0.4174, "step": 9310 }, { "epoch": 2.383232, "grad_norm": 1.78125, "learning_rate": 1.0284958621278049e-05, "loss": 0.4255, "step": 9311 }, { "epoch": 2.383488, "grad_norm": 1.796875, "learning_rate": 1.0280692773654125e-05, "loss": 0.4335, "step": 9312 }, { "epoch": 2.383744, "grad_norm": 1.875, "learning_rate": 1.0276426926030203e-05, "loss": 0.4445, "step": 9313 }, { "epoch": 2.384, "grad_norm": 1.7109375, "learning_rate": 1.027216107840628e-05, "loss": 0.4462, "step": 9314 }, { "epoch": 2.384256, "grad_norm": 1.84375, "learning_rate": 1.0267895230782356e-05, "loss": 0.4128, "step": 9315 }, { "epoch": 2.384512, "grad_norm": 1.796875, "learning_rate": 1.0263629383158434e-05, "loss": 0.4429, "step": 9316 }, { "epoch": 2.384768, "grad_norm": 1.875, "learning_rate": 1.0259363535534512e-05, "loss": 0.4839, "step": 9317 }, { "epoch": 2.385024, "grad_norm": 1.8515625, "learning_rate": 1.0255097687910588e-05, "loss": 0.415, "step": 9318 }, { "epoch": 2.38528, "grad_norm": 1.65625, "learning_rate": 1.0250831840286665e-05, "loss": 0.431, "step": 9319 }, { "epoch": 2.385536, "grad_norm": 1.765625, "learning_rate": 1.0246565992662741e-05, "loss": 0.4057, "step": 9320 }, { "epoch": 2.385792, "grad_norm": 1.8125, "learning_rate": 1.024230014503882e-05, "loss": 0.4226, "step": 9321 }, { "epoch": 2.386048, "grad_norm": 1.7109375, "learning_rate": 1.0238034297414898e-05, "loss": 0.3882, "step": 9322 }, { "epoch": 2.386304, "grad_norm": 1.75, "learning_rate": 1.0233768449790974e-05, "loss": 0.4443, "step": 9323 }, { "epoch": 2.3865600000000002, "grad_norm": 1.7578125, "learning_rate": 1.0229502602167052e-05, "loss": 0.4368, "step": 9324 }, { "epoch": 2.386816, "grad_norm": 1.7265625, "learning_rate": 1.0225236754543128e-05, "loss": 0.4417, "step": 9325 }, { "epoch": 2.387072, "grad_norm": 1.6875, "learning_rate": 1.0220970906919205e-05, "loss": 0.4141, "step": 9326 }, { "epoch": 2.387328, "grad_norm": 1.9375, "learning_rate": 1.0216705059295283e-05, "loss": 0.4097, "step": 9327 }, { "epoch": 2.387584, "grad_norm": 1.84375, "learning_rate": 1.0212439211671359e-05, "loss": 0.4199, "step": 9328 }, { "epoch": 2.38784, "grad_norm": 1.8203125, "learning_rate": 1.0208173364047437e-05, "loss": 0.3862, "step": 9329 }, { "epoch": 2.388096, "grad_norm": 1.828125, "learning_rate": 1.0203907516423514e-05, "loss": 0.4167, "step": 9330 }, { "epoch": 2.388352, "grad_norm": 1.75, "learning_rate": 1.019964166879959e-05, "loss": 0.4078, "step": 9331 }, { "epoch": 2.388608, "grad_norm": 1.7734375, "learning_rate": 1.0195375821175668e-05, "loss": 0.4, "step": 9332 }, { "epoch": 2.388864, "grad_norm": 1.7890625, "learning_rate": 1.0191109973551746e-05, "loss": 0.4298, "step": 9333 }, { "epoch": 2.38912, "grad_norm": 1.9609375, "learning_rate": 1.0186844125927822e-05, "loss": 0.4288, "step": 9334 }, { "epoch": 2.389376, "grad_norm": 1.84375, "learning_rate": 1.01825782783039e-05, "loss": 0.4658, "step": 9335 }, { "epoch": 2.3896319999999998, "grad_norm": 1.9296875, "learning_rate": 1.0178312430679975e-05, "loss": 0.4286, "step": 9336 }, { "epoch": 2.389888, "grad_norm": 1.9375, "learning_rate": 1.0174046583056055e-05, "loss": 0.44, "step": 9337 }, { "epoch": 2.390144, "grad_norm": 1.875, "learning_rate": 1.0169780735432132e-05, "loss": 0.4212, "step": 9338 }, { "epoch": 2.3904, "grad_norm": 1.7421875, "learning_rate": 1.0165514887808208e-05, "loss": 0.4299, "step": 9339 }, { "epoch": 2.390656, "grad_norm": 1.953125, "learning_rate": 1.0161249040184286e-05, "loss": 0.3995, "step": 9340 }, { "epoch": 2.390912, "grad_norm": 1.796875, "learning_rate": 1.0156983192560362e-05, "loss": 0.4484, "step": 9341 }, { "epoch": 2.391168, "grad_norm": 1.84375, "learning_rate": 1.015271734493644e-05, "loss": 0.4105, "step": 9342 }, { "epoch": 2.3914239999999998, "grad_norm": 1.8125, "learning_rate": 1.0148451497312517e-05, "loss": 0.4155, "step": 9343 }, { "epoch": 2.39168, "grad_norm": 1.9140625, "learning_rate": 1.0144185649688593e-05, "loss": 0.4124, "step": 9344 }, { "epoch": 2.391936, "grad_norm": 1.8125, "learning_rate": 1.013991980206467e-05, "loss": 0.4067, "step": 9345 }, { "epoch": 2.392192, "grad_norm": 1.8828125, "learning_rate": 1.0135653954440748e-05, "loss": 0.4517, "step": 9346 }, { "epoch": 2.392448, "grad_norm": 1.7890625, "learning_rate": 1.0131388106816824e-05, "loss": 0.4053, "step": 9347 }, { "epoch": 2.392704, "grad_norm": 2.0625, "learning_rate": 1.0127122259192902e-05, "loss": 0.4718, "step": 9348 }, { "epoch": 2.39296, "grad_norm": 1.875, "learning_rate": 1.012285641156898e-05, "loss": 0.4228, "step": 9349 }, { "epoch": 2.393216, "grad_norm": 1.8984375, "learning_rate": 1.0118590563945056e-05, "loss": 0.4143, "step": 9350 }, { "epoch": 2.393472, "grad_norm": 1.859375, "learning_rate": 1.0114324716321133e-05, "loss": 0.4082, "step": 9351 }, { "epoch": 2.393728, "grad_norm": 1.7578125, "learning_rate": 1.011005886869721e-05, "loss": 0.4032, "step": 9352 }, { "epoch": 2.393984, "grad_norm": 1.7109375, "learning_rate": 1.0105793021073287e-05, "loss": 0.4332, "step": 9353 }, { "epoch": 2.39424, "grad_norm": 1.8359375, "learning_rate": 1.0101527173449366e-05, "loss": 0.4209, "step": 9354 }, { "epoch": 2.394496, "grad_norm": 1.6953125, "learning_rate": 1.0097261325825442e-05, "loss": 0.3932, "step": 9355 }, { "epoch": 2.394752, "grad_norm": 1.765625, "learning_rate": 1.009299547820152e-05, "loss": 0.4151, "step": 9356 }, { "epoch": 2.395008, "grad_norm": 1.703125, "learning_rate": 1.0088729630577597e-05, "loss": 0.3802, "step": 9357 }, { "epoch": 2.395264, "grad_norm": 1.8125, "learning_rate": 1.0084463782953673e-05, "loss": 0.4474, "step": 9358 }, { "epoch": 2.39552, "grad_norm": 1.6953125, "learning_rate": 1.0080197935329751e-05, "loss": 0.4075, "step": 9359 }, { "epoch": 2.395776, "grad_norm": 1.78125, "learning_rate": 1.0075932087705827e-05, "loss": 0.4341, "step": 9360 }, { "epoch": 2.396032, "grad_norm": 1.890625, "learning_rate": 1.0071666240081905e-05, "loss": 0.4215, "step": 9361 }, { "epoch": 2.396288, "grad_norm": 1.765625, "learning_rate": 1.0067400392457982e-05, "loss": 0.4514, "step": 9362 }, { "epoch": 2.396544, "grad_norm": 1.890625, "learning_rate": 1.0063134544834058e-05, "loss": 0.4225, "step": 9363 }, { "epoch": 2.3968, "grad_norm": 1.734375, "learning_rate": 1.0058868697210136e-05, "loss": 0.4311, "step": 9364 }, { "epoch": 2.397056, "grad_norm": 1.8046875, "learning_rate": 1.0054602849586214e-05, "loss": 0.4103, "step": 9365 }, { "epoch": 2.397312, "grad_norm": 1.71875, "learning_rate": 1.005033700196229e-05, "loss": 0.4268, "step": 9366 }, { "epoch": 2.397568, "grad_norm": 1.734375, "learning_rate": 1.0046071154338367e-05, "loss": 0.4005, "step": 9367 }, { "epoch": 2.397824, "grad_norm": 1.75, "learning_rate": 1.0041805306714445e-05, "loss": 0.4112, "step": 9368 }, { "epoch": 2.39808, "grad_norm": 1.828125, "learning_rate": 1.0037539459090521e-05, "loss": 0.4517, "step": 9369 }, { "epoch": 2.398336, "grad_norm": 1.8125, "learning_rate": 1.00332736114666e-05, "loss": 0.4097, "step": 9370 }, { "epoch": 2.398592, "grad_norm": 1.8671875, "learning_rate": 1.0029007763842676e-05, "loss": 0.4056, "step": 9371 }, { "epoch": 2.398848, "grad_norm": 1.6640625, "learning_rate": 1.0024741916218754e-05, "loss": 0.4528, "step": 9372 }, { "epoch": 2.399104, "grad_norm": 1.8515625, "learning_rate": 1.0020476068594831e-05, "loss": 0.3911, "step": 9373 }, { "epoch": 2.39936, "grad_norm": 1.7890625, "learning_rate": 1.0016210220970907e-05, "loss": 0.4079, "step": 9374 }, { "epoch": 2.399616, "grad_norm": 1.6640625, "learning_rate": 1.0011944373346985e-05, "loss": 0.4573, "step": 9375 }, { "epoch": 2.3998720000000002, "grad_norm": 1.78125, "learning_rate": 1.0007678525723061e-05, "loss": 0.4486, "step": 9376 }, { "epoch": 2.400128, "grad_norm": 1.90625, "learning_rate": 1.0003412678099139e-05, "loss": 0.4158, "step": 9377 }, { "epoch": 2.400384, "grad_norm": 1.8203125, "learning_rate": 9.999146830475216e-06, "loss": 0.4008, "step": 9378 }, { "epoch": 2.40064, "grad_norm": 1.71875, "learning_rate": 9.994880982851292e-06, "loss": 0.4328, "step": 9379 }, { "epoch": 2.400896, "grad_norm": 1.75, "learning_rate": 9.99061513522737e-06, "loss": 0.4053, "step": 9380 }, { "epoch": 2.401152, "grad_norm": 1.796875, "learning_rate": 9.986349287603448e-06, "loss": 0.3599, "step": 9381 }, { "epoch": 2.401408, "grad_norm": 1.828125, "learning_rate": 9.982083439979524e-06, "loss": 0.4381, "step": 9382 }, { "epoch": 2.4016640000000002, "grad_norm": 1.7890625, "learning_rate": 9.977817592355601e-06, "loss": 0.3925, "step": 9383 }, { "epoch": 2.40192, "grad_norm": 1.875, "learning_rate": 9.973551744731679e-06, "loss": 0.4443, "step": 9384 }, { "epoch": 2.402176, "grad_norm": 1.796875, "learning_rate": 9.969285897107755e-06, "loss": 0.4299, "step": 9385 }, { "epoch": 2.402432, "grad_norm": 1.8046875, "learning_rate": 9.965020049483834e-06, "loss": 0.411, "step": 9386 }, { "epoch": 2.402688, "grad_norm": 1.8046875, "learning_rate": 9.96075420185991e-06, "loss": 0.4487, "step": 9387 }, { "epoch": 2.402944, "grad_norm": 1.6875, "learning_rate": 9.956488354235988e-06, "loss": 0.4099, "step": 9388 }, { "epoch": 2.4032, "grad_norm": 1.7890625, "learning_rate": 9.952222506612065e-06, "loss": 0.4506, "step": 9389 }, { "epoch": 2.403456, "grad_norm": 1.671875, "learning_rate": 9.947956658988141e-06, "loss": 0.3797, "step": 9390 }, { "epoch": 2.403712, "grad_norm": 1.8203125, "learning_rate": 9.943690811364219e-06, "loss": 0.4329, "step": 9391 }, { "epoch": 2.403968, "grad_norm": 1.640625, "learning_rate": 9.939424963740295e-06, "loss": 0.4269, "step": 9392 }, { "epoch": 2.404224, "grad_norm": 1.8359375, "learning_rate": 9.935159116116373e-06, "loss": 0.396, "step": 9393 }, { "epoch": 2.40448, "grad_norm": 1.75, "learning_rate": 9.93089326849245e-06, "loss": 0.4105, "step": 9394 }, { "epoch": 2.4047359999999998, "grad_norm": 1.7421875, "learning_rate": 9.926627420868526e-06, "loss": 0.4065, "step": 9395 }, { "epoch": 2.404992, "grad_norm": 1.8125, "learning_rate": 9.922361573244604e-06, "loss": 0.4244, "step": 9396 }, { "epoch": 2.405248, "grad_norm": 1.75, "learning_rate": 9.918095725620682e-06, "loss": 0.451, "step": 9397 }, { "epoch": 2.405504, "grad_norm": 1.8359375, "learning_rate": 9.913829877996758e-06, "loss": 0.4174, "step": 9398 }, { "epoch": 2.40576, "grad_norm": 1.78125, "learning_rate": 9.909564030372835e-06, "loss": 0.4267, "step": 9399 }, { "epoch": 2.406016, "grad_norm": 1.6484375, "learning_rate": 9.905298182748913e-06, "loss": 0.422, "step": 9400 }, { "epoch": 2.406272, "grad_norm": 1.8359375, "learning_rate": 9.901032335124989e-06, "loss": 0.4152, "step": 9401 }, { "epoch": 2.406528, "grad_norm": 1.6640625, "learning_rate": 9.896766487501067e-06, "loss": 0.4298, "step": 9402 }, { "epoch": 2.406784, "grad_norm": 1.6953125, "learning_rate": 9.892500639877144e-06, "loss": 0.4472, "step": 9403 }, { "epoch": 2.40704, "grad_norm": 1.7109375, "learning_rate": 9.888234792253222e-06, "loss": 0.3901, "step": 9404 }, { "epoch": 2.407296, "grad_norm": 1.6640625, "learning_rate": 9.8839689446293e-06, "loss": 0.407, "step": 9405 }, { "epoch": 2.407552, "grad_norm": 1.765625, "learning_rate": 9.879703097005375e-06, "loss": 0.4283, "step": 9406 }, { "epoch": 2.407808, "grad_norm": 1.8046875, "learning_rate": 9.875437249381453e-06, "loss": 0.4199, "step": 9407 }, { "epoch": 2.408064, "grad_norm": 1.71875, "learning_rate": 9.87117140175753e-06, "loss": 0.4065, "step": 9408 }, { "epoch": 2.40832, "grad_norm": 1.84375, "learning_rate": 9.866905554133607e-06, "loss": 0.4294, "step": 9409 }, { "epoch": 2.408576, "grad_norm": 1.7734375, "learning_rate": 9.862639706509684e-06, "loss": 0.4304, "step": 9410 }, { "epoch": 2.408832, "grad_norm": 1.8125, "learning_rate": 9.85837385888576e-06, "loss": 0.361, "step": 9411 }, { "epoch": 2.409088, "grad_norm": 1.8203125, "learning_rate": 9.854108011261838e-06, "loss": 0.3759, "step": 9412 }, { "epoch": 2.409344, "grad_norm": 1.84375, "learning_rate": 9.849842163637916e-06, "loss": 0.446, "step": 9413 }, { "epoch": 2.4096, "grad_norm": 1.6875, "learning_rate": 9.845576316013992e-06, "loss": 0.4224, "step": 9414 }, { "epoch": 2.409856, "grad_norm": 1.875, "learning_rate": 9.84131046839007e-06, "loss": 0.431, "step": 9415 }, { "epoch": 2.410112, "grad_norm": 1.7890625, "learning_rate": 9.837044620766147e-06, "loss": 0.4339, "step": 9416 }, { "epoch": 2.410368, "grad_norm": 1.7734375, "learning_rate": 9.832778773142223e-06, "loss": 0.4596, "step": 9417 }, { "epoch": 2.410624, "grad_norm": 1.8984375, "learning_rate": 9.8285129255183e-06, "loss": 0.4095, "step": 9418 }, { "epoch": 2.41088, "grad_norm": 1.8359375, "learning_rate": 9.824247077894378e-06, "loss": 0.4198, "step": 9419 }, { "epoch": 2.411136, "grad_norm": 1.875, "learning_rate": 9.819981230270456e-06, "loss": 0.3987, "step": 9420 }, { "epoch": 2.411392, "grad_norm": 1.875, "learning_rate": 9.815715382646533e-06, "loss": 0.4451, "step": 9421 }, { "epoch": 2.411648, "grad_norm": 1.6328125, "learning_rate": 9.81144953502261e-06, "loss": 0.4595, "step": 9422 }, { "epoch": 2.411904, "grad_norm": 1.6484375, "learning_rate": 9.807183687398687e-06, "loss": 0.4228, "step": 9423 }, { "epoch": 2.41216, "grad_norm": 1.765625, "learning_rate": 9.802917839774765e-06, "loss": 0.4247, "step": 9424 }, { "epoch": 2.412416, "grad_norm": 1.828125, "learning_rate": 9.79865199215084e-06, "loss": 0.4503, "step": 9425 }, { "epoch": 2.412672, "grad_norm": 1.6328125, "learning_rate": 9.794386144526918e-06, "loss": 0.3942, "step": 9426 }, { "epoch": 2.412928, "grad_norm": 1.953125, "learning_rate": 9.790120296902994e-06, "loss": 0.4252, "step": 9427 }, { "epoch": 2.413184, "grad_norm": 1.75, "learning_rate": 9.785854449279072e-06, "loss": 0.4317, "step": 9428 }, { "epoch": 2.41344, "grad_norm": 1.7890625, "learning_rate": 9.78158860165515e-06, "loss": 0.4064, "step": 9429 }, { "epoch": 2.413696, "grad_norm": 1.796875, "learning_rate": 9.777322754031226e-06, "loss": 0.4106, "step": 9430 }, { "epoch": 2.413952, "grad_norm": 2.078125, "learning_rate": 9.773056906407303e-06, "loss": 0.4418, "step": 9431 }, { "epoch": 2.414208, "grad_norm": 1.859375, "learning_rate": 9.768791058783381e-06, "loss": 0.4376, "step": 9432 }, { "epoch": 2.414464, "grad_norm": 1.6875, "learning_rate": 9.764525211159457e-06, "loss": 0.4184, "step": 9433 }, { "epoch": 2.41472, "grad_norm": 1.6640625, "learning_rate": 9.760259363535535e-06, "loss": 0.4245, "step": 9434 }, { "epoch": 2.4149760000000002, "grad_norm": 1.8125, "learning_rate": 9.755993515911612e-06, "loss": 0.4485, "step": 9435 }, { "epoch": 2.415232, "grad_norm": 1.734375, "learning_rate": 9.75172766828769e-06, "loss": 0.44, "step": 9436 }, { "epoch": 2.415488, "grad_norm": 1.8515625, "learning_rate": 9.747461820663767e-06, "loss": 0.4414, "step": 9437 }, { "epoch": 2.415744, "grad_norm": 1.8046875, "learning_rate": 9.743195973039843e-06, "loss": 0.3976, "step": 9438 }, { "epoch": 2.416, "grad_norm": 1.7890625, "learning_rate": 9.738930125415921e-06, "loss": 0.409, "step": 9439 }, { "epoch": 2.416256, "grad_norm": 1.7109375, "learning_rate": 9.734664277791999e-06, "loss": 0.4529, "step": 9440 }, { "epoch": 2.416512, "grad_norm": 1.796875, "learning_rate": 9.730398430168075e-06, "loss": 0.4114, "step": 9441 }, { "epoch": 2.4167680000000002, "grad_norm": 1.8515625, "learning_rate": 9.726132582544152e-06, "loss": 0.4558, "step": 9442 }, { "epoch": 2.417024, "grad_norm": 1.859375, "learning_rate": 9.721866734920228e-06, "loss": 0.4013, "step": 9443 }, { "epoch": 2.41728, "grad_norm": 1.609375, "learning_rate": 9.717600887296306e-06, "loss": 0.4326, "step": 9444 }, { "epoch": 2.417536, "grad_norm": 1.859375, "learning_rate": 9.713335039672384e-06, "loss": 0.4155, "step": 9445 }, { "epoch": 2.417792, "grad_norm": 1.6953125, "learning_rate": 9.70906919204846e-06, "loss": 0.4383, "step": 9446 }, { "epoch": 2.4180479999999998, "grad_norm": 1.796875, "learning_rate": 9.704803344424537e-06, "loss": 0.413, "step": 9447 }, { "epoch": 2.418304, "grad_norm": 1.75, "learning_rate": 9.700537496800615e-06, "loss": 0.4319, "step": 9448 }, { "epoch": 2.41856, "grad_norm": 1.78125, "learning_rate": 9.696271649176691e-06, "loss": 0.4246, "step": 9449 }, { "epoch": 2.418816, "grad_norm": 1.8984375, "learning_rate": 9.692005801552769e-06, "loss": 0.4082, "step": 9450 }, { "epoch": 2.419072, "grad_norm": 1.765625, "learning_rate": 9.687739953928846e-06, "loss": 0.4095, "step": 9451 }, { "epoch": 2.419328, "grad_norm": 1.671875, "learning_rate": 9.683474106304924e-06, "loss": 0.4347, "step": 9452 }, { "epoch": 2.419584, "grad_norm": 1.734375, "learning_rate": 9.679208258681001e-06, "loss": 0.4587, "step": 9453 }, { "epoch": 2.4198399999999998, "grad_norm": 1.7109375, "learning_rate": 9.674942411057077e-06, "loss": 0.4033, "step": 9454 }, { "epoch": 2.420096, "grad_norm": 1.9453125, "learning_rate": 9.670676563433155e-06, "loss": 0.4601, "step": 9455 }, { "epoch": 2.420352, "grad_norm": 1.75, "learning_rate": 9.666410715809233e-06, "loss": 0.4662, "step": 9456 }, { "epoch": 2.420608, "grad_norm": 1.8203125, "learning_rate": 9.662144868185309e-06, "loss": 0.3822, "step": 9457 }, { "epoch": 2.420864, "grad_norm": 1.765625, "learning_rate": 9.657879020561386e-06, "loss": 0.4479, "step": 9458 }, { "epoch": 2.42112, "grad_norm": 1.734375, "learning_rate": 9.653613172937464e-06, "loss": 0.4063, "step": 9459 }, { "epoch": 2.421376, "grad_norm": 1.875, "learning_rate": 9.64934732531354e-06, "loss": 0.4073, "step": 9460 }, { "epoch": 2.421632, "grad_norm": 1.7734375, "learning_rate": 9.645081477689618e-06, "loss": 0.4034, "step": 9461 }, { "epoch": 2.421888, "grad_norm": 1.828125, "learning_rate": 9.640815630065694e-06, "loss": 0.414, "step": 9462 }, { "epoch": 2.422144, "grad_norm": 1.75, "learning_rate": 9.636549782441771e-06, "loss": 0.4031, "step": 9463 }, { "epoch": 2.4224, "grad_norm": 1.7421875, "learning_rate": 9.632283934817849e-06, "loss": 0.4437, "step": 9464 }, { "epoch": 2.422656, "grad_norm": 1.7421875, "learning_rate": 9.628018087193925e-06, "loss": 0.4076, "step": 9465 }, { "epoch": 2.422912, "grad_norm": 1.8984375, "learning_rate": 9.623752239570003e-06, "loss": 0.4024, "step": 9466 }, { "epoch": 2.423168, "grad_norm": 1.875, "learning_rate": 9.61948639194608e-06, "loss": 0.4092, "step": 9467 }, { "epoch": 2.423424, "grad_norm": 1.828125, "learning_rate": 9.615220544322158e-06, "loss": 0.4526, "step": 9468 }, { "epoch": 2.42368, "grad_norm": 1.6875, "learning_rate": 9.610954696698235e-06, "loss": 0.4249, "step": 9469 }, { "epoch": 2.423936, "grad_norm": 1.8125, "learning_rate": 9.606688849074311e-06, "loss": 0.3956, "step": 9470 }, { "epoch": 2.424192, "grad_norm": 1.765625, "learning_rate": 9.602423001450389e-06, "loss": 0.44, "step": 9471 }, { "epoch": 2.424448, "grad_norm": 1.71875, "learning_rate": 9.598157153826467e-06, "loss": 0.4544, "step": 9472 }, { "epoch": 2.424704, "grad_norm": 1.7578125, "learning_rate": 9.593891306202543e-06, "loss": 0.419, "step": 9473 }, { "epoch": 2.42496, "grad_norm": 1.75, "learning_rate": 9.58962545857862e-06, "loss": 0.4399, "step": 9474 }, { "epoch": 2.425216, "grad_norm": 1.8359375, "learning_rate": 9.585359610954698e-06, "loss": 0.4383, "step": 9475 }, { "epoch": 2.425472, "grad_norm": 1.7265625, "learning_rate": 9.581093763330774e-06, "loss": 0.38, "step": 9476 }, { "epoch": 2.425728, "grad_norm": 1.6640625, "learning_rate": 9.576827915706852e-06, "loss": 0.4066, "step": 9477 }, { "epoch": 2.425984, "grad_norm": 1.703125, "learning_rate": 9.572562068082928e-06, "loss": 0.4198, "step": 9478 }, { "epoch": 2.42624, "grad_norm": 1.8515625, "learning_rate": 9.568296220459005e-06, "loss": 0.4563, "step": 9479 }, { "epoch": 2.426496, "grad_norm": 1.859375, "learning_rate": 9.564030372835083e-06, "loss": 0.3982, "step": 9480 }, { "epoch": 2.426752, "grad_norm": 1.9296875, "learning_rate": 9.559764525211159e-06, "loss": 0.4059, "step": 9481 }, { "epoch": 2.427008, "grad_norm": 1.8828125, "learning_rate": 9.555498677587237e-06, "loss": 0.4415, "step": 9482 }, { "epoch": 2.427264, "grad_norm": 1.8671875, "learning_rate": 9.551232829963314e-06, "loss": 0.4659, "step": 9483 }, { "epoch": 2.42752, "grad_norm": 1.765625, "learning_rate": 9.54696698233939e-06, "loss": 0.411, "step": 9484 }, { "epoch": 2.427776, "grad_norm": 1.703125, "learning_rate": 9.54270113471547e-06, "loss": 0.4106, "step": 9485 }, { "epoch": 2.428032, "grad_norm": 1.875, "learning_rate": 9.538435287091545e-06, "loss": 0.4145, "step": 9486 }, { "epoch": 2.4282880000000002, "grad_norm": 1.75, "learning_rate": 9.534169439467623e-06, "loss": 0.4158, "step": 9487 }, { "epoch": 2.428544, "grad_norm": 1.90625, "learning_rate": 9.5299035918437e-06, "loss": 0.4144, "step": 9488 }, { "epoch": 2.4288, "grad_norm": 1.828125, "learning_rate": 9.525637744219777e-06, "loss": 0.4305, "step": 9489 }, { "epoch": 2.429056, "grad_norm": 1.8203125, "learning_rate": 9.521371896595854e-06, "loss": 0.4273, "step": 9490 }, { "epoch": 2.429312, "grad_norm": 1.84375, "learning_rate": 9.517106048971932e-06, "loss": 0.3695, "step": 9491 }, { "epoch": 2.429568, "grad_norm": 1.671875, "learning_rate": 9.512840201348008e-06, "loss": 0.4059, "step": 9492 }, { "epoch": 2.429824, "grad_norm": 1.8828125, "learning_rate": 9.508574353724086e-06, "loss": 0.48, "step": 9493 }, { "epoch": 2.4300800000000002, "grad_norm": 1.875, "learning_rate": 9.504308506100163e-06, "loss": 0.3738, "step": 9494 }, { "epoch": 2.430336, "grad_norm": 1.84375, "learning_rate": 9.50004265847624e-06, "loss": 0.426, "step": 9495 }, { "epoch": 2.430592, "grad_norm": 1.6484375, "learning_rate": 9.495776810852317e-06, "loss": 0.4496, "step": 9496 }, { "epoch": 2.430848, "grad_norm": 1.7734375, "learning_rate": 9.491510963228393e-06, "loss": 0.4477, "step": 9497 }, { "epoch": 2.431104, "grad_norm": 1.828125, "learning_rate": 9.48724511560447e-06, "loss": 0.4221, "step": 9498 }, { "epoch": 2.43136, "grad_norm": 1.546875, "learning_rate": 9.482979267980548e-06, "loss": 0.3906, "step": 9499 }, { "epoch": 2.431616, "grad_norm": 1.7578125, "learning_rate": 9.478713420356624e-06, "loss": 0.4083, "step": 9500 }, { "epoch": 2.431872, "grad_norm": 1.875, "learning_rate": 9.474447572732703e-06, "loss": 0.4087, "step": 9501 }, { "epoch": 2.432128, "grad_norm": 1.78125, "learning_rate": 9.47018172510878e-06, "loss": 0.403, "step": 9502 }, { "epoch": 2.432384, "grad_norm": 1.9140625, "learning_rate": 9.465915877484857e-06, "loss": 0.36, "step": 9503 }, { "epoch": 2.43264, "grad_norm": 1.6796875, "learning_rate": 9.461650029860935e-06, "loss": 0.4187, "step": 9504 }, { "epoch": 2.432896, "grad_norm": 1.8515625, "learning_rate": 9.45738418223701e-06, "loss": 0.4364, "step": 9505 }, { "epoch": 2.4331519999999998, "grad_norm": 1.8515625, "learning_rate": 9.453118334613088e-06, "loss": 0.3878, "step": 9506 }, { "epoch": 2.433408, "grad_norm": 1.7890625, "learning_rate": 9.448852486989166e-06, "loss": 0.4127, "step": 9507 }, { "epoch": 2.433664, "grad_norm": 1.890625, "learning_rate": 9.444586639365242e-06, "loss": 0.4477, "step": 9508 }, { "epoch": 2.43392, "grad_norm": 1.734375, "learning_rate": 9.44032079174132e-06, "loss": 0.3966, "step": 9509 }, { "epoch": 2.434176, "grad_norm": 1.8203125, "learning_rate": 9.436054944117397e-06, "loss": 0.3818, "step": 9510 }, { "epoch": 2.434432, "grad_norm": 1.8515625, "learning_rate": 9.431789096493473e-06, "loss": 0.3991, "step": 9511 }, { "epoch": 2.434688, "grad_norm": 1.78125, "learning_rate": 9.427523248869551e-06, "loss": 0.4258, "step": 9512 }, { "epoch": 2.4349439999999998, "grad_norm": 1.796875, "learning_rate": 9.423257401245627e-06, "loss": 0.4322, "step": 9513 }, { "epoch": 2.4352, "grad_norm": 1.75, "learning_rate": 9.418991553621705e-06, "loss": 0.4447, "step": 9514 }, { "epoch": 2.435456, "grad_norm": 1.7734375, "learning_rate": 9.414725705997782e-06, "loss": 0.4275, "step": 9515 }, { "epoch": 2.435712, "grad_norm": 1.8671875, "learning_rate": 9.410459858373858e-06, "loss": 0.4268, "step": 9516 }, { "epoch": 2.435968, "grad_norm": 1.6640625, "learning_rate": 9.406194010749936e-06, "loss": 0.4245, "step": 9517 }, { "epoch": 2.436224, "grad_norm": 1.734375, "learning_rate": 9.401928163126013e-06, "loss": 0.4199, "step": 9518 }, { "epoch": 2.43648, "grad_norm": 1.71875, "learning_rate": 9.397662315502091e-06, "loss": 0.4333, "step": 9519 }, { "epoch": 2.436736, "grad_norm": 1.75, "learning_rate": 9.393396467878169e-06, "loss": 0.443, "step": 9520 }, { "epoch": 2.436992, "grad_norm": 1.6484375, "learning_rate": 9.389130620254245e-06, "loss": 0.4245, "step": 9521 }, { "epoch": 2.437248, "grad_norm": 2.015625, "learning_rate": 9.384864772630322e-06, "loss": 0.4533, "step": 9522 }, { "epoch": 2.437504, "grad_norm": 1.796875, "learning_rate": 9.3805989250064e-06, "loss": 0.4287, "step": 9523 }, { "epoch": 2.43776, "grad_norm": 1.953125, "learning_rate": 9.376333077382476e-06, "loss": 0.442, "step": 9524 }, { "epoch": 2.438016, "grad_norm": 1.796875, "learning_rate": 9.372067229758554e-06, "loss": 0.4052, "step": 9525 }, { "epoch": 2.438272, "grad_norm": 1.796875, "learning_rate": 9.367801382134631e-06, "loss": 0.4299, "step": 9526 }, { "epoch": 2.438528, "grad_norm": 1.9140625, "learning_rate": 9.363535534510707e-06, "loss": 0.3912, "step": 9527 }, { "epoch": 2.438784, "grad_norm": 1.8828125, "learning_rate": 9.359269686886785e-06, "loss": 0.4217, "step": 9528 }, { "epoch": 2.43904, "grad_norm": 1.828125, "learning_rate": 9.355003839262861e-06, "loss": 0.3959, "step": 9529 }, { "epoch": 2.439296, "grad_norm": 1.7421875, "learning_rate": 9.350737991638939e-06, "loss": 0.4013, "step": 9530 }, { "epoch": 2.439552, "grad_norm": 1.828125, "learning_rate": 9.346472144015016e-06, "loss": 0.4152, "step": 9531 }, { "epoch": 2.439808, "grad_norm": 1.859375, "learning_rate": 9.342206296391092e-06, "loss": 0.4105, "step": 9532 }, { "epoch": 2.440064, "grad_norm": 1.75, "learning_rate": 9.33794044876717e-06, "loss": 0.4378, "step": 9533 }, { "epoch": 2.44032, "grad_norm": 1.8046875, "learning_rate": 9.333674601143247e-06, "loss": 0.367, "step": 9534 }, { "epoch": 2.440576, "grad_norm": 1.7265625, "learning_rate": 9.329408753519325e-06, "loss": 0.3998, "step": 9535 }, { "epoch": 2.440832, "grad_norm": 1.75, "learning_rate": 9.325142905895403e-06, "loss": 0.3789, "step": 9536 }, { "epoch": 2.441088, "grad_norm": 1.609375, "learning_rate": 9.320877058271479e-06, "loss": 0.411, "step": 9537 }, { "epoch": 2.441344, "grad_norm": 1.8203125, "learning_rate": 9.316611210647556e-06, "loss": 0.439, "step": 9538 }, { "epoch": 2.4416, "grad_norm": 1.8671875, "learning_rate": 9.312345363023634e-06, "loss": 0.431, "step": 9539 }, { "epoch": 2.441856, "grad_norm": 1.703125, "learning_rate": 9.30807951539971e-06, "loss": 0.4677, "step": 9540 }, { "epoch": 2.442112, "grad_norm": 1.6484375, "learning_rate": 9.303813667775788e-06, "loss": 0.4283, "step": 9541 }, { "epoch": 2.442368, "grad_norm": 1.71875, "learning_rate": 9.299547820151865e-06, "loss": 0.4424, "step": 9542 }, { "epoch": 2.442624, "grad_norm": 1.7109375, "learning_rate": 9.295281972527941e-06, "loss": 0.4451, "step": 9543 }, { "epoch": 2.44288, "grad_norm": 1.796875, "learning_rate": 9.291016124904019e-06, "loss": 0.4193, "step": 9544 }, { "epoch": 2.443136, "grad_norm": 1.859375, "learning_rate": 9.286750277280097e-06, "loss": 0.3946, "step": 9545 }, { "epoch": 2.4433920000000002, "grad_norm": 1.7734375, "learning_rate": 9.282484429656173e-06, "loss": 0.4363, "step": 9546 }, { "epoch": 2.443648, "grad_norm": 1.6875, "learning_rate": 9.27821858203225e-06, "loss": 0.4536, "step": 9547 }, { "epoch": 2.443904, "grad_norm": 1.8515625, "learning_rate": 9.273952734408326e-06, "loss": 0.4002, "step": 9548 }, { "epoch": 2.44416, "grad_norm": 1.765625, "learning_rate": 9.269686886784404e-06, "loss": 0.3969, "step": 9549 }, { "epoch": 2.444416, "grad_norm": 1.7890625, "learning_rate": 9.265421039160483e-06, "loss": 0.3994, "step": 9550 }, { "epoch": 2.444672, "grad_norm": 1.8125, "learning_rate": 9.261155191536559e-06, "loss": 0.4093, "step": 9551 }, { "epoch": 2.444928, "grad_norm": 1.875, "learning_rate": 9.256889343912637e-06, "loss": 0.4222, "step": 9552 }, { "epoch": 2.4451840000000002, "grad_norm": 1.7890625, "learning_rate": 9.252623496288713e-06, "loss": 0.4191, "step": 9553 }, { "epoch": 2.44544, "grad_norm": 1.8046875, "learning_rate": 9.24835764866479e-06, "loss": 0.4205, "step": 9554 }, { "epoch": 2.445696, "grad_norm": 1.859375, "learning_rate": 9.244091801040868e-06, "loss": 0.4176, "step": 9555 }, { "epoch": 2.445952, "grad_norm": 1.6328125, "learning_rate": 9.239825953416944e-06, "loss": 0.4302, "step": 9556 }, { "epoch": 2.446208, "grad_norm": 1.796875, "learning_rate": 9.235560105793022e-06, "loss": 0.3454, "step": 9557 }, { "epoch": 2.446464, "grad_norm": 1.703125, "learning_rate": 9.2312942581691e-06, "loss": 0.4285, "step": 9558 }, { "epoch": 2.44672, "grad_norm": 1.7421875, "learning_rate": 9.227028410545175e-06, "loss": 0.4096, "step": 9559 }, { "epoch": 2.446976, "grad_norm": 1.6640625, "learning_rate": 9.222762562921253e-06, "loss": 0.4428, "step": 9560 }, { "epoch": 2.447232, "grad_norm": 1.8046875, "learning_rate": 9.21849671529733e-06, "loss": 0.425, "step": 9561 }, { "epoch": 2.447488, "grad_norm": 1.703125, "learning_rate": 9.214230867673407e-06, "loss": 0.4291, "step": 9562 }, { "epoch": 2.447744, "grad_norm": 1.875, "learning_rate": 9.209965020049484e-06, "loss": 0.4255, "step": 9563 }, { "epoch": 2.448, "grad_norm": 1.875, "learning_rate": 9.20569917242556e-06, "loss": 0.4003, "step": 9564 }, { "epoch": 2.4482559999999998, "grad_norm": 1.8359375, "learning_rate": 9.201433324801638e-06, "loss": 0.3736, "step": 9565 }, { "epoch": 2.448512, "grad_norm": 1.9296875, "learning_rate": 9.197167477177715e-06, "loss": 0.386, "step": 9566 }, { "epoch": 2.448768, "grad_norm": 1.734375, "learning_rate": 9.192901629553793e-06, "loss": 0.4291, "step": 9567 }, { "epoch": 2.449024, "grad_norm": 1.796875, "learning_rate": 9.18863578192987e-06, "loss": 0.4211, "step": 9568 }, { "epoch": 2.44928, "grad_norm": 1.7109375, "learning_rate": 9.184369934305947e-06, "loss": 0.4476, "step": 9569 }, { "epoch": 2.449536, "grad_norm": 1.921875, "learning_rate": 9.180104086682024e-06, "loss": 0.3958, "step": 9570 }, { "epoch": 2.449792, "grad_norm": 1.703125, "learning_rate": 9.175838239058102e-06, "loss": 0.4088, "step": 9571 }, { "epoch": 2.450048, "grad_norm": 1.71875, "learning_rate": 9.171572391434178e-06, "loss": 0.4434, "step": 9572 }, { "epoch": 2.450304, "grad_norm": 1.8515625, "learning_rate": 9.167306543810256e-06, "loss": 0.4028, "step": 9573 }, { "epoch": 2.45056, "grad_norm": 1.8046875, "learning_rate": 9.163040696186333e-06, "loss": 0.409, "step": 9574 }, { "epoch": 2.450816, "grad_norm": 1.8046875, "learning_rate": 9.15877484856241e-06, "loss": 0.4402, "step": 9575 }, { "epoch": 2.451072, "grad_norm": 1.7890625, "learning_rate": 9.154509000938487e-06, "loss": 0.4523, "step": 9576 }, { "epoch": 2.451328, "grad_norm": 1.7734375, "learning_rate": 9.150243153314565e-06, "loss": 0.4503, "step": 9577 }, { "epoch": 2.451584, "grad_norm": 1.828125, "learning_rate": 9.14597730569064e-06, "loss": 0.4284, "step": 9578 }, { "epoch": 2.45184, "grad_norm": 1.7109375, "learning_rate": 9.141711458066718e-06, "loss": 0.4331, "step": 9579 }, { "epoch": 2.452096, "grad_norm": 1.734375, "learning_rate": 9.137445610442794e-06, "loss": 0.4217, "step": 9580 }, { "epoch": 2.452352, "grad_norm": 1.8359375, "learning_rate": 9.133179762818872e-06, "loss": 0.4463, "step": 9581 }, { "epoch": 2.452608, "grad_norm": 1.71875, "learning_rate": 9.12891391519495e-06, "loss": 0.4253, "step": 9582 }, { "epoch": 2.452864, "grad_norm": 1.671875, "learning_rate": 9.124648067571027e-06, "loss": 0.3926, "step": 9583 }, { "epoch": 2.45312, "grad_norm": 1.8984375, "learning_rate": 9.120382219947105e-06, "loss": 0.4167, "step": 9584 }, { "epoch": 2.453376, "grad_norm": 1.9140625, "learning_rate": 9.116116372323182e-06, "loss": 0.4345, "step": 9585 }, { "epoch": 2.453632, "grad_norm": 1.8125, "learning_rate": 9.111850524699258e-06, "loss": 0.4372, "step": 9586 }, { "epoch": 2.453888, "grad_norm": 1.875, "learning_rate": 9.107584677075336e-06, "loss": 0.4368, "step": 9587 }, { "epoch": 2.454144, "grad_norm": 1.7109375, "learning_rate": 9.103318829451412e-06, "loss": 0.4225, "step": 9588 }, { "epoch": 2.4544, "grad_norm": 1.8046875, "learning_rate": 9.09905298182749e-06, "loss": 0.4623, "step": 9589 }, { "epoch": 2.454656, "grad_norm": 1.6171875, "learning_rate": 9.094787134203567e-06, "loss": 0.443, "step": 9590 }, { "epoch": 2.454912, "grad_norm": 1.8203125, "learning_rate": 9.090521286579643e-06, "loss": 0.4174, "step": 9591 }, { "epoch": 2.455168, "grad_norm": 1.671875, "learning_rate": 9.086255438955721e-06, "loss": 0.4066, "step": 9592 }, { "epoch": 2.455424, "grad_norm": 1.765625, "learning_rate": 9.081989591331799e-06, "loss": 0.4484, "step": 9593 }, { "epoch": 2.45568, "grad_norm": 1.8515625, "learning_rate": 9.077723743707875e-06, "loss": 0.4062, "step": 9594 }, { "epoch": 2.455936, "grad_norm": 1.8125, "learning_rate": 9.073457896083952e-06, "loss": 0.3934, "step": 9595 }, { "epoch": 2.456192, "grad_norm": 1.7109375, "learning_rate": 9.06919204846003e-06, "loss": 0.4362, "step": 9596 }, { "epoch": 2.456448, "grad_norm": 1.7890625, "learning_rate": 9.064926200836106e-06, "loss": 0.4028, "step": 9597 }, { "epoch": 2.456704, "grad_norm": 1.7734375, "learning_rate": 9.060660353212183e-06, "loss": 0.4351, "step": 9598 }, { "epoch": 2.45696, "grad_norm": 1.65625, "learning_rate": 9.05639450558826e-06, "loss": 0.4003, "step": 9599 }, { "epoch": 2.457216, "grad_norm": 1.8359375, "learning_rate": 9.052128657964339e-06, "loss": 0.4123, "step": 9600 }, { "epoch": 2.457472, "grad_norm": 1.703125, "learning_rate": 9.047862810340416e-06, "loss": 0.4173, "step": 9601 }, { "epoch": 2.457728, "grad_norm": 1.796875, "learning_rate": 9.043596962716492e-06, "loss": 0.4074, "step": 9602 }, { "epoch": 2.457984, "grad_norm": 1.703125, "learning_rate": 9.03933111509257e-06, "loss": 0.4385, "step": 9603 }, { "epoch": 2.45824, "grad_norm": 1.8984375, "learning_rate": 9.035065267468646e-06, "loss": 0.4103, "step": 9604 }, { "epoch": 2.4584960000000002, "grad_norm": 1.734375, "learning_rate": 9.030799419844724e-06, "loss": 0.4371, "step": 9605 }, { "epoch": 2.458752, "grad_norm": 1.671875, "learning_rate": 9.026533572220801e-06, "loss": 0.4738, "step": 9606 }, { "epoch": 2.459008, "grad_norm": 1.6875, "learning_rate": 9.022267724596877e-06, "loss": 0.4226, "step": 9607 }, { "epoch": 2.459264, "grad_norm": 1.7421875, "learning_rate": 9.018001876972955e-06, "loss": 0.3977, "step": 9608 }, { "epoch": 2.45952, "grad_norm": 1.7421875, "learning_rate": 9.013736029349033e-06, "loss": 0.4512, "step": 9609 }, { "epoch": 2.459776, "grad_norm": 1.6875, "learning_rate": 9.009470181725109e-06, "loss": 0.4196, "step": 9610 }, { "epoch": 2.460032, "grad_norm": 1.84375, "learning_rate": 9.005204334101186e-06, "loss": 0.431, "step": 9611 }, { "epoch": 2.460288, "grad_norm": 1.7265625, "learning_rate": 9.000938486477264e-06, "loss": 0.442, "step": 9612 }, { "epoch": 2.460544, "grad_norm": 1.75, "learning_rate": 8.99667263885334e-06, "loss": 0.4154, "step": 9613 }, { "epoch": 2.4608, "grad_norm": 1.78125, "learning_rate": 8.992406791229417e-06, "loss": 0.4167, "step": 9614 }, { "epoch": 2.461056, "grad_norm": 1.640625, "learning_rate": 8.988140943605493e-06, "loss": 0.428, "step": 9615 }, { "epoch": 2.461312, "grad_norm": 1.8203125, "learning_rate": 8.983875095981573e-06, "loss": 0.4234, "step": 9616 }, { "epoch": 2.4615679999999998, "grad_norm": 1.7109375, "learning_rate": 8.97960924835765e-06, "loss": 0.4195, "step": 9617 }, { "epoch": 2.461824, "grad_norm": 1.8125, "learning_rate": 8.975343400733726e-06, "loss": 0.4176, "step": 9618 }, { "epoch": 2.46208, "grad_norm": 1.7734375, "learning_rate": 8.971077553109804e-06, "loss": 0.4253, "step": 9619 }, { "epoch": 2.462336, "grad_norm": 1.8203125, "learning_rate": 8.96681170548588e-06, "loss": 0.4372, "step": 9620 }, { "epoch": 2.462592, "grad_norm": 1.796875, "learning_rate": 8.962545857861958e-06, "loss": 0.4644, "step": 9621 }, { "epoch": 2.462848, "grad_norm": 1.609375, "learning_rate": 8.958280010238035e-06, "loss": 0.3957, "step": 9622 }, { "epoch": 2.463104, "grad_norm": 1.6953125, "learning_rate": 8.954014162614111e-06, "loss": 0.4335, "step": 9623 }, { "epoch": 2.4633599999999998, "grad_norm": 1.9140625, "learning_rate": 8.949748314990189e-06, "loss": 0.4017, "step": 9624 }, { "epoch": 2.463616, "grad_norm": 1.796875, "learning_rate": 8.945482467366267e-06, "loss": 0.4355, "step": 9625 }, { "epoch": 2.463872, "grad_norm": 1.65625, "learning_rate": 8.941216619742343e-06, "loss": 0.4254, "step": 9626 }, { "epoch": 2.464128, "grad_norm": 1.8359375, "learning_rate": 8.93695077211842e-06, "loss": 0.434, "step": 9627 }, { "epoch": 2.464384, "grad_norm": 1.90625, "learning_rate": 8.932684924494498e-06, "loss": 0.4119, "step": 9628 }, { "epoch": 2.46464, "grad_norm": 1.75, "learning_rate": 8.928419076870574e-06, "loss": 0.4317, "step": 9629 }, { "epoch": 2.464896, "grad_norm": 1.7265625, "learning_rate": 8.924153229246651e-06, "loss": 0.4479, "step": 9630 }, { "epoch": 2.465152, "grad_norm": 1.6640625, "learning_rate": 8.919887381622729e-06, "loss": 0.459, "step": 9631 }, { "epoch": 2.465408, "grad_norm": 1.6484375, "learning_rate": 8.915621533998807e-06, "loss": 0.4385, "step": 9632 }, { "epoch": 2.465664, "grad_norm": 1.8046875, "learning_rate": 8.911355686374884e-06, "loss": 0.4119, "step": 9633 }, { "epoch": 2.46592, "grad_norm": 1.90625, "learning_rate": 8.90708983875096e-06, "loss": 0.4261, "step": 9634 }, { "epoch": 2.466176, "grad_norm": 1.8359375, "learning_rate": 8.902823991127038e-06, "loss": 0.4065, "step": 9635 }, { "epoch": 2.466432, "grad_norm": 1.84375, "learning_rate": 8.898558143503116e-06, "loss": 0.4227, "step": 9636 }, { "epoch": 2.466688, "grad_norm": 1.7578125, "learning_rate": 8.894292295879192e-06, "loss": 0.4111, "step": 9637 }, { "epoch": 2.466944, "grad_norm": 1.7578125, "learning_rate": 8.89002644825527e-06, "loss": 0.4571, "step": 9638 }, { "epoch": 2.4672, "grad_norm": 1.6875, "learning_rate": 8.885760600631345e-06, "loss": 0.4369, "step": 9639 }, { "epoch": 2.467456, "grad_norm": 1.71875, "learning_rate": 8.881494753007423e-06, "loss": 0.4282, "step": 9640 }, { "epoch": 2.467712, "grad_norm": 1.7109375, "learning_rate": 8.8772289053835e-06, "loss": 0.4184, "step": 9641 }, { "epoch": 2.467968, "grad_norm": 1.8125, "learning_rate": 8.872963057759577e-06, "loss": 0.4139, "step": 9642 }, { "epoch": 2.468224, "grad_norm": 1.7109375, "learning_rate": 8.868697210135654e-06, "loss": 0.4341, "step": 9643 }, { "epoch": 2.46848, "grad_norm": 1.734375, "learning_rate": 8.864431362511732e-06, "loss": 0.435, "step": 9644 }, { "epoch": 2.468736, "grad_norm": 1.7109375, "learning_rate": 8.860165514887808e-06, "loss": 0.4091, "step": 9645 }, { "epoch": 2.468992, "grad_norm": 1.7578125, "learning_rate": 8.855899667263885e-06, "loss": 0.4296, "step": 9646 }, { "epoch": 2.469248, "grad_norm": 1.7890625, "learning_rate": 8.851633819639963e-06, "loss": 0.4446, "step": 9647 }, { "epoch": 2.469504, "grad_norm": 1.8671875, "learning_rate": 8.847367972016039e-06, "loss": 0.4467, "step": 9648 }, { "epoch": 2.46976, "grad_norm": 1.7734375, "learning_rate": 8.843102124392118e-06, "loss": 0.3828, "step": 9649 }, { "epoch": 2.470016, "grad_norm": 1.8046875, "learning_rate": 8.838836276768194e-06, "loss": 0.4071, "step": 9650 }, { "epoch": 2.470272, "grad_norm": 1.84375, "learning_rate": 8.834570429144272e-06, "loss": 0.4182, "step": 9651 }, { "epoch": 2.470528, "grad_norm": 1.9609375, "learning_rate": 8.83030458152035e-06, "loss": 0.4174, "step": 9652 }, { "epoch": 2.470784, "grad_norm": 1.84375, "learning_rate": 8.826038733896426e-06, "loss": 0.4358, "step": 9653 }, { "epoch": 2.47104, "grad_norm": 1.71875, "learning_rate": 8.821772886272503e-06, "loss": 0.4501, "step": 9654 }, { "epoch": 2.471296, "grad_norm": 1.75, "learning_rate": 8.81750703864858e-06, "loss": 0.4315, "step": 9655 }, { "epoch": 2.471552, "grad_norm": 1.875, "learning_rate": 8.813241191024657e-06, "loss": 0.4363, "step": 9656 }, { "epoch": 2.4718080000000002, "grad_norm": 1.9765625, "learning_rate": 8.808975343400735e-06, "loss": 0.4275, "step": 9657 }, { "epoch": 2.472064, "grad_norm": 1.71875, "learning_rate": 8.80470949577681e-06, "loss": 0.4407, "step": 9658 }, { "epoch": 2.47232, "grad_norm": 1.7578125, "learning_rate": 8.800443648152888e-06, "loss": 0.4088, "step": 9659 }, { "epoch": 2.472576, "grad_norm": 1.7109375, "learning_rate": 8.796177800528966e-06, "loss": 0.4308, "step": 9660 }, { "epoch": 2.472832, "grad_norm": 1.7578125, "learning_rate": 8.791911952905042e-06, "loss": 0.3964, "step": 9661 }, { "epoch": 2.473088, "grad_norm": 1.96875, "learning_rate": 8.78764610528112e-06, "loss": 0.4588, "step": 9662 }, { "epoch": 2.473344, "grad_norm": 1.8125, "learning_rate": 8.783380257657197e-06, "loss": 0.4083, "step": 9663 }, { "epoch": 2.4736000000000002, "grad_norm": 1.703125, "learning_rate": 8.779114410033273e-06, "loss": 0.4729, "step": 9664 }, { "epoch": 2.473856, "grad_norm": 1.7109375, "learning_rate": 8.774848562409352e-06, "loss": 0.4008, "step": 9665 }, { "epoch": 2.474112, "grad_norm": 1.75, "learning_rate": 8.770582714785428e-06, "loss": 0.46, "step": 9666 }, { "epoch": 2.474368, "grad_norm": 1.8359375, "learning_rate": 8.766316867161506e-06, "loss": 0.4246, "step": 9667 }, { "epoch": 2.474624, "grad_norm": 1.671875, "learning_rate": 8.762051019537584e-06, "loss": 0.433, "step": 9668 }, { "epoch": 2.47488, "grad_norm": 1.65625, "learning_rate": 8.75778517191366e-06, "loss": 0.4207, "step": 9669 }, { "epoch": 2.475136, "grad_norm": 1.828125, "learning_rate": 8.753519324289737e-06, "loss": 0.4653, "step": 9670 }, { "epoch": 2.475392, "grad_norm": 2.046875, "learning_rate": 8.749253476665813e-06, "loss": 0.3944, "step": 9671 }, { "epoch": 2.475648, "grad_norm": 1.8671875, "learning_rate": 8.744987629041891e-06, "loss": 0.4528, "step": 9672 }, { "epoch": 2.475904, "grad_norm": 1.828125, "learning_rate": 8.740721781417969e-06, "loss": 0.447, "step": 9673 }, { "epoch": 2.47616, "grad_norm": 1.5859375, "learning_rate": 8.736455933794045e-06, "loss": 0.4104, "step": 9674 }, { "epoch": 2.476416, "grad_norm": 1.7578125, "learning_rate": 8.732190086170122e-06, "loss": 0.4132, "step": 9675 }, { "epoch": 2.4766719999999998, "grad_norm": 1.7578125, "learning_rate": 8.7279242385462e-06, "loss": 0.4039, "step": 9676 }, { "epoch": 2.476928, "grad_norm": 1.7578125, "learning_rate": 8.723658390922276e-06, "loss": 0.3785, "step": 9677 }, { "epoch": 2.477184, "grad_norm": 1.84375, "learning_rate": 8.719392543298353e-06, "loss": 0.431, "step": 9678 }, { "epoch": 2.47744, "grad_norm": 1.71875, "learning_rate": 8.715126695674431e-06, "loss": 0.4136, "step": 9679 }, { "epoch": 2.477696, "grad_norm": 1.7578125, "learning_rate": 8.710860848050507e-06, "loss": 0.4554, "step": 9680 }, { "epoch": 2.477952, "grad_norm": 1.828125, "learning_rate": 8.706595000426585e-06, "loss": 0.4252, "step": 9681 }, { "epoch": 2.478208, "grad_norm": 1.6953125, "learning_rate": 8.702329152802662e-06, "loss": 0.4342, "step": 9682 }, { "epoch": 2.478464, "grad_norm": 1.8046875, "learning_rate": 8.69806330517874e-06, "loss": 0.4498, "step": 9683 }, { "epoch": 2.47872, "grad_norm": 1.8125, "learning_rate": 8.693797457554818e-06, "loss": 0.388, "step": 9684 }, { "epoch": 2.478976, "grad_norm": 1.65625, "learning_rate": 8.689531609930894e-06, "loss": 0.427, "step": 9685 }, { "epoch": 2.479232, "grad_norm": 1.8828125, "learning_rate": 8.685265762306971e-06, "loss": 0.4567, "step": 9686 }, { "epoch": 2.479488, "grad_norm": 1.7890625, "learning_rate": 8.680999914683049e-06, "loss": 0.4277, "step": 9687 }, { "epoch": 2.479744, "grad_norm": 1.6953125, "learning_rate": 8.676734067059125e-06, "loss": 0.3985, "step": 9688 }, { "epoch": 2.48, "grad_norm": 1.8671875, "learning_rate": 8.672468219435203e-06, "loss": 0.4278, "step": 9689 }, { "epoch": 2.480256, "grad_norm": 1.7109375, "learning_rate": 8.668202371811279e-06, "loss": 0.4274, "step": 9690 }, { "epoch": 2.480512, "grad_norm": 1.828125, "learning_rate": 8.663936524187356e-06, "loss": 0.4285, "step": 9691 }, { "epoch": 2.480768, "grad_norm": 1.875, "learning_rate": 8.659670676563434e-06, "loss": 0.3861, "step": 9692 }, { "epoch": 2.481024, "grad_norm": 1.796875, "learning_rate": 8.65540482893951e-06, "loss": 0.4041, "step": 9693 }, { "epoch": 2.48128, "grad_norm": 1.765625, "learning_rate": 8.651138981315587e-06, "loss": 0.4514, "step": 9694 }, { "epoch": 2.481536, "grad_norm": 1.78125, "learning_rate": 8.646873133691665e-06, "loss": 0.3865, "step": 9695 }, { "epoch": 2.481792, "grad_norm": 1.734375, "learning_rate": 8.642607286067741e-06, "loss": 0.4187, "step": 9696 }, { "epoch": 2.482048, "grad_norm": 1.8515625, "learning_rate": 8.638341438443819e-06, "loss": 0.4509, "step": 9697 }, { "epoch": 2.482304, "grad_norm": 1.6171875, "learning_rate": 8.634075590819896e-06, "loss": 0.4555, "step": 9698 }, { "epoch": 2.48256, "grad_norm": 1.796875, "learning_rate": 8.629809743195974e-06, "loss": 0.4458, "step": 9699 }, { "epoch": 2.482816, "grad_norm": 1.9375, "learning_rate": 8.625543895572052e-06, "loss": 0.4266, "step": 9700 }, { "epoch": 2.483072, "grad_norm": 1.8359375, "learning_rate": 8.621278047948128e-06, "loss": 0.4118, "step": 9701 }, { "epoch": 2.483328, "grad_norm": 1.8671875, "learning_rate": 8.617012200324205e-06, "loss": 0.4325, "step": 9702 }, { "epoch": 2.483584, "grad_norm": 1.859375, "learning_rate": 8.612746352700283e-06, "loss": 0.4005, "step": 9703 }, { "epoch": 2.48384, "grad_norm": 1.6953125, "learning_rate": 8.608480505076359e-06, "loss": 0.4351, "step": 9704 }, { "epoch": 2.484096, "grad_norm": 1.6953125, "learning_rate": 8.604214657452437e-06, "loss": 0.4432, "step": 9705 }, { "epoch": 2.484352, "grad_norm": 1.875, "learning_rate": 8.599948809828513e-06, "loss": 0.445, "step": 9706 }, { "epoch": 2.484608, "grad_norm": 1.859375, "learning_rate": 8.59568296220459e-06, "loss": 0.4301, "step": 9707 }, { "epoch": 2.484864, "grad_norm": 1.6953125, "learning_rate": 8.591417114580668e-06, "loss": 0.4164, "step": 9708 }, { "epoch": 2.48512, "grad_norm": 1.7109375, "learning_rate": 8.587151266956744e-06, "loss": 0.4015, "step": 9709 }, { "epoch": 2.485376, "grad_norm": 1.7578125, "learning_rate": 8.582885419332821e-06, "loss": 0.3961, "step": 9710 }, { "epoch": 2.485632, "grad_norm": 1.8515625, "learning_rate": 8.578619571708899e-06, "loss": 0.3951, "step": 9711 }, { "epoch": 2.485888, "grad_norm": 1.8515625, "learning_rate": 8.574353724084975e-06, "loss": 0.4436, "step": 9712 }, { "epoch": 2.486144, "grad_norm": 1.6875, "learning_rate": 8.570087876461053e-06, "loss": 0.4012, "step": 9713 }, { "epoch": 2.4864, "grad_norm": 1.734375, "learning_rate": 8.56582202883713e-06, "loss": 0.4327, "step": 9714 }, { "epoch": 2.486656, "grad_norm": 1.7890625, "learning_rate": 8.561556181213208e-06, "loss": 0.4456, "step": 9715 }, { "epoch": 2.4869120000000002, "grad_norm": 1.8125, "learning_rate": 8.557290333589286e-06, "loss": 0.4249, "step": 9716 }, { "epoch": 2.487168, "grad_norm": 1.8828125, "learning_rate": 8.553024485965362e-06, "loss": 0.4098, "step": 9717 }, { "epoch": 2.487424, "grad_norm": 1.6875, "learning_rate": 8.54875863834144e-06, "loss": 0.4363, "step": 9718 }, { "epoch": 2.48768, "grad_norm": 1.7578125, "learning_rate": 8.544492790717517e-06, "loss": 0.4017, "step": 9719 }, { "epoch": 2.487936, "grad_norm": 1.875, "learning_rate": 8.540226943093593e-06, "loss": 0.4592, "step": 9720 }, { "epoch": 2.488192, "grad_norm": 1.6953125, "learning_rate": 8.53596109546967e-06, "loss": 0.3955, "step": 9721 }, { "epoch": 2.488448, "grad_norm": 1.8046875, "learning_rate": 8.531695247845747e-06, "loss": 0.3995, "step": 9722 }, { "epoch": 2.4887040000000002, "grad_norm": 1.8671875, "learning_rate": 8.527429400221824e-06, "loss": 0.4218, "step": 9723 }, { "epoch": 2.48896, "grad_norm": 1.703125, "learning_rate": 8.523163552597902e-06, "loss": 0.382, "step": 9724 }, { "epoch": 2.489216, "grad_norm": 1.78125, "learning_rate": 8.518897704973978e-06, "loss": 0.4216, "step": 9725 }, { "epoch": 2.489472, "grad_norm": 1.8203125, "learning_rate": 8.514631857350055e-06, "loss": 0.4457, "step": 9726 }, { "epoch": 2.489728, "grad_norm": 1.8203125, "learning_rate": 8.510366009726133e-06, "loss": 0.3742, "step": 9727 }, { "epoch": 2.4899839999999998, "grad_norm": 1.90625, "learning_rate": 8.506100162102209e-06, "loss": 0.4334, "step": 9728 }, { "epoch": 2.49024, "grad_norm": 1.7421875, "learning_rate": 8.501834314478287e-06, "loss": 0.4509, "step": 9729 }, { "epoch": 2.490496, "grad_norm": 1.7265625, "learning_rate": 8.497568466854364e-06, "loss": 0.4225, "step": 9730 }, { "epoch": 2.490752, "grad_norm": 1.7421875, "learning_rate": 8.493302619230442e-06, "loss": 0.4047, "step": 9731 }, { "epoch": 2.491008, "grad_norm": 1.7578125, "learning_rate": 8.48903677160652e-06, "loss": 0.4694, "step": 9732 }, { "epoch": 2.491264, "grad_norm": 1.8203125, "learning_rate": 8.484770923982596e-06, "loss": 0.4323, "step": 9733 }, { "epoch": 2.49152, "grad_norm": 1.703125, "learning_rate": 8.480505076358673e-06, "loss": 0.4367, "step": 9734 }, { "epoch": 2.4917759999999998, "grad_norm": 1.8984375, "learning_rate": 8.476239228734751e-06, "loss": 0.4061, "step": 9735 }, { "epoch": 2.492032, "grad_norm": 1.78125, "learning_rate": 8.471973381110827e-06, "loss": 0.4432, "step": 9736 }, { "epoch": 2.492288, "grad_norm": 1.796875, "learning_rate": 8.467707533486905e-06, "loss": 0.4109, "step": 9737 }, { "epoch": 2.492544, "grad_norm": 1.78125, "learning_rate": 8.463441685862982e-06, "loss": 0.4112, "step": 9738 }, { "epoch": 2.4928, "grad_norm": 1.7265625, "learning_rate": 8.459175838239058e-06, "loss": 0.4286, "step": 9739 }, { "epoch": 2.493056, "grad_norm": 1.71875, "learning_rate": 8.454909990615136e-06, "loss": 0.4124, "step": 9740 }, { "epoch": 2.493312, "grad_norm": 1.7109375, "learning_rate": 8.450644142991212e-06, "loss": 0.4543, "step": 9741 }, { "epoch": 2.493568, "grad_norm": 1.75, "learning_rate": 8.44637829536729e-06, "loss": 0.3836, "step": 9742 }, { "epoch": 2.493824, "grad_norm": 1.75, "learning_rate": 8.442112447743367e-06, "loss": 0.425, "step": 9743 }, { "epoch": 2.49408, "grad_norm": 1.75, "learning_rate": 8.437846600119443e-06, "loss": 0.4698, "step": 9744 }, { "epoch": 2.494336, "grad_norm": 1.8515625, "learning_rate": 8.43358075249552e-06, "loss": 0.3902, "step": 9745 }, { "epoch": 2.494592, "grad_norm": 1.890625, "learning_rate": 8.429314904871598e-06, "loss": 0.372, "step": 9746 }, { "epoch": 2.494848, "grad_norm": 1.6796875, "learning_rate": 8.425049057247676e-06, "loss": 0.429, "step": 9747 }, { "epoch": 2.495104, "grad_norm": 1.7734375, "learning_rate": 8.420783209623754e-06, "loss": 0.404, "step": 9748 }, { "epoch": 2.49536, "grad_norm": 1.7109375, "learning_rate": 8.41651736199983e-06, "loss": 0.4263, "step": 9749 }, { "epoch": 2.495616, "grad_norm": 1.7109375, "learning_rate": 8.412251514375907e-06, "loss": 0.4085, "step": 9750 }, { "epoch": 2.495872, "grad_norm": 1.734375, "learning_rate": 8.407985666751985e-06, "loss": 0.4574, "step": 9751 }, { "epoch": 2.496128, "grad_norm": 1.8828125, "learning_rate": 8.403719819128061e-06, "loss": 0.4052, "step": 9752 }, { "epoch": 2.496384, "grad_norm": 1.8515625, "learning_rate": 8.399453971504139e-06, "loss": 0.4161, "step": 9753 }, { "epoch": 2.49664, "grad_norm": 1.734375, "learning_rate": 8.395188123880216e-06, "loss": 0.4599, "step": 9754 }, { "epoch": 2.496896, "grad_norm": 1.8046875, "learning_rate": 8.390922276256292e-06, "loss": 0.4076, "step": 9755 }, { "epoch": 2.497152, "grad_norm": 1.8046875, "learning_rate": 8.38665642863237e-06, "loss": 0.4637, "step": 9756 }, { "epoch": 2.497408, "grad_norm": 1.796875, "learning_rate": 8.382390581008446e-06, "loss": 0.4967, "step": 9757 }, { "epoch": 2.497664, "grad_norm": 1.9609375, "learning_rate": 8.378124733384523e-06, "loss": 0.4517, "step": 9758 }, { "epoch": 2.49792, "grad_norm": 1.9609375, "learning_rate": 8.373858885760601e-06, "loss": 0.4184, "step": 9759 }, { "epoch": 2.498176, "grad_norm": 1.640625, "learning_rate": 8.369593038136677e-06, "loss": 0.4008, "step": 9760 }, { "epoch": 2.498432, "grad_norm": 1.78125, "learning_rate": 8.365327190512755e-06, "loss": 0.4139, "step": 9761 }, { "epoch": 2.498688, "grad_norm": 1.6171875, "learning_rate": 8.361061342888832e-06, "loss": 0.3883, "step": 9762 }, { "epoch": 2.498944, "grad_norm": 1.9140625, "learning_rate": 8.356795495264908e-06, "loss": 0.4434, "step": 9763 }, { "epoch": 2.4992, "grad_norm": 1.7421875, "learning_rate": 8.352529647640988e-06, "loss": 0.4204, "step": 9764 }, { "epoch": 2.499456, "grad_norm": 1.8828125, "learning_rate": 8.348263800017064e-06, "loss": 0.4079, "step": 9765 }, { "epoch": 2.499712, "grad_norm": 1.59375, "learning_rate": 8.343997952393141e-06, "loss": 0.371, "step": 9766 }, { "epoch": 2.499968, "grad_norm": 1.8203125, "learning_rate": 8.339732104769219e-06, "loss": 0.4248, "step": 9767 }, { "epoch": 2.5002240000000002, "grad_norm": 1.7890625, "learning_rate": 8.335466257145295e-06, "loss": 0.4142, "step": 9768 }, { "epoch": 2.50048, "grad_norm": 1.890625, "learning_rate": 8.331200409521373e-06, "loss": 0.3929, "step": 9769 }, { "epoch": 2.500736, "grad_norm": 1.8359375, "learning_rate": 8.32693456189745e-06, "loss": 0.4256, "step": 9770 }, { "epoch": 2.500992, "grad_norm": 1.703125, "learning_rate": 8.322668714273526e-06, "loss": 0.4026, "step": 9771 }, { "epoch": 2.501248, "grad_norm": 1.7265625, "learning_rate": 8.318402866649604e-06, "loss": 0.3897, "step": 9772 }, { "epoch": 2.5015039999999997, "grad_norm": 1.796875, "learning_rate": 8.314137019025681e-06, "loss": 0.4354, "step": 9773 }, { "epoch": 2.50176, "grad_norm": 1.7578125, "learning_rate": 8.309871171401757e-06, "loss": 0.4183, "step": 9774 }, { "epoch": 2.5020160000000002, "grad_norm": 1.7265625, "learning_rate": 8.305605323777835e-06, "loss": 0.41, "step": 9775 }, { "epoch": 2.502272, "grad_norm": 1.859375, "learning_rate": 8.301339476153911e-06, "loss": 0.4377, "step": 9776 }, { "epoch": 2.502528, "grad_norm": 1.8828125, "learning_rate": 8.297073628529989e-06, "loss": 0.4162, "step": 9777 }, { "epoch": 2.502784, "grad_norm": 1.671875, "learning_rate": 8.292807780906066e-06, "loss": 0.413, "step": 9778 }, { "epoch": 2.50304, "grad_norm": 1.6953125, "learning_rate": 8.288541933282142e-06, "loss": 0.4388, "step": 9779 }, { "epoch": 2.5032959999999997, "grad_norm": 1.7265625, "learning_rate": 8.284276085658222e-06, "loss": 0.4149, "step": 9780 }, { "epoch": 2.503552, "grad_norm": 1.7421875, "learning_rate": 8.280010238034298e-06, "loss": 0.4032, "step": 9781 }, { "epoch": 2.5038080000000003, "grad_norm": 1.8125, "learning_rate": 8.275744390410375e-06, "loss": 0.4257, "step": 9782 }, { "epoch": 2.504064, "grad_norm": 1.7421875, "learning_rate": 8.271478542786453e-06, "loss": 0.445, "step": 9783 }, { "epoch": 2.50432, "grad_norm": 1.7265625, "learning_rate": 8.267212695162529e-06, "loss": 0.4399, "step": 9784 }, { "epoch": 2.504576, "grad_norm": 1.7109375, "learning_rate": 8.262946847538607e-06, "loss": 0.4298, "step": 9785 }, { "epoch": 2.504832, "grad_norm": 1.828125, "learning_rate": 8.258680999914684e-06, "loss": 0.3883, "step": 9786 }, { "epoch": 2.5050879999999998, "grad_norm": 1.7734375, "learning_rate": 8.25441515229076e-06, "loss": 0.4239, "step": 9787 }, { "epoch": 2.505344, "grad_norm": 1.84375, "learning_rate": 8.250149304666838e-06, "loss": 0.417, "step": 9788 }, { "epoch": 2.5056000000000003, "grad_norm": 1.7734375, "learning_rate": 8.245883457042915e-06, "loss": 0.4247, "step": 9789 }, { "epoch": 2.505856, "grad_norm": 1.7421875, "learning_rate": 8.241617609418991e-06, "loss": 0.4362, "step": 9790 }, { "epoch": 2.506112, "grad_norm": 1.8515625, "learning_rate": 8.237351761795069e-06, "loss": 0.4245, "step": 9791 }, { "epoch": 2.506368, "grad_norm": 1.734375, "learning_rate": 8.233085914171145e-06, "loss": 0.3963, "step": 9792 }, { "epoch": 2.506624, "grad_norm": 1.8671875, "learning_rate": 8.228820066547223e-06, "loss": 0.4196, "step": 9793 }, { "epoch": 2.5068799999999998, "grad_norm": 1.6953125, "learning_rate": 8.2245542189233e-06, "loss": 0.4278, "step": 9794 }, { "epoch": 2.507136, "grad_norm": 1.5546875, "learning_rate": 8.220288371299376e-06, "loss": 0.407, "step": 9795 }, { "epoch": 2.507392, "grad_norm": 1.859375, "learning_rate": 8.216022523675456e-06, "loss": 0.4124, "step": 9796 }, { "epoch": 2.507648, "grad_norm": 1.7265625, "learning_rate": 8.211756676051532e-06, "loss": 0.4263, "step": 9797 }, { "epoch": 2.507904, "grad_norm": 1.8359375, "learning_rate": 8.20749082842761e-06, "loss": 0.3959, "step": 9798 }, { "epoch": 2.50816, "grad_norm": 1.6484375, "learning_rate": 8.203224980803687e-06, "loss": 0.4669, "step": 9799 }, { "epoch": 2.508416, "grad_norm": 1.7890625, "learning_rate": 8.198959133179763e-06, "loss": 0.4201, "step": 9800 }, { "epoch": 2.508672, "grad_norm": 1.875, "learning_rate": 8.19469328555584e-06, "loss": 0.423, "step": 9801 }, { "epoch": 2.508928, "grad_norm": 1.84375, "learning_rate": 8.190427437931918e-06, "loss": 0.4236, "step": 9802 }, { "epoch": 2.509184, "grad_norm": 1.6875, "learning_rate": 8.186161590307994e-06, "loss": 0.3964, "step": 9803 }, { "epoch": 2.50944, "grad_norm": 1.8515625, "learning_rate": 8.181895742684072e-06, "loss": 0.4156, "step": 9804 }, { "epoch": 2.509696, "grad_norm": 1.96875, "learning_rate": 8.17762989506015e-06, "loss": 0.3914, "step": 9805 }, { "epoch": 2.509952, "grad_norm": 1.8203125, "learning_rate": 8.173364047436225e-06, "loss": 0.3988, "step": 9806 }, { "epoch": 2.510208, "grad_norm": 1.8515625, "learning_rate": 8.169098199812303e-06, "loss": 0.4049, "step": 9807 }, { "epoch": 2.510464, "grad_norm": 1.640625, "learning_rate": 8.164832352188379e-06, "loss": 0.3901, "step": 9808 }, { "epoch": 2.51072, "grad_norm": 1.7734375, "learning_rate": 8.160566504564457e-06, "loss": 0.4457, "step": 9809 }, { "epoch": 2.510976, "grad_norm": 2.0, "learning_rate": 8.156300656940534e-06, "loss": 0.4247, "step": 9810 }, { "epoch": 2.511232, "grad_norm": 1.8046875, "learning_rate": 8.15203480931661e-06, "loss": 0.4409, "step": 9811 }, { "epoch": 2.511488, "grad_norm": 1.7578125, "learning_rate": 8.147768961692688e-06, "loss": 0.4183, "step": 9812 }, { "epoch": 2.511744, "grad_norm": 1.84375, "learning_rate": 8.143503114068766e-06, "loss": 0.4034, "step": 9813 }, { "epoch": 2.512, "grad_norm": 1.8046875, "learning_rate": 8.139237266444843e-06, "loss": 0.4402, "step": 9814 }, { "epoch": 2.512256, "grad_norm": 1.75, "learning_rate": 8.134971418820921e-06, "loss": 0.4314, "step": 9815 }, { "epoch": 2.512512, "grad_norm": 1.75, "learning_rate": 8.130705571196997e-06, "loss": 0.3838, "step": 9816 }, { "epoch": 2.512768, "grad_norm": 1.71875, "learning_rate": 8.126439723573075e-06, "loss": 0.4437, "step": 9817 }, { "epoch": 2.513024, "grad_norm": 1.765625, "learning_rate": 8.122173875949152e-06, "loss": 0.4062, "step": 9818 }, { "epoch": 2.51328, "grad_norm": 1.84375, "learning_rate": 8.117908028325228e-06, "loss": 0.4664, "step": 9819 }, { "epoch": 2.513536, "grad_norm": 1.8828125, "learning_rate": 8.113642180701306e-06, "loss": 0.4143, "step": 9820 }, { "epoch": 2.513792, "grad_norm": 1.8671875, "learning_rate": 8.109376333077383e-06, "loss": 0.4252, "step": 9821 }, { "epoch": 2.514048, "grad_norm": 1.71875, "learning_rate": 8.10511048545346e-06, "loss": 0.4263, "step": 9822 }, { "epoch": 2.514304, "grad_norm": 1.8984375, "learning_rate": 8.100844637829537e-06, "loss": 0.4178, "step": 9823 }, { "epoch": 2.51456, "grad_norm": 1.7109375, "learning_rate": 8.096578790205615e-06, "loss": 0.4097, "step": 9824 }, { "epoch": 2.514816, "grad_norm": 1.625, "learning_rate": 8.09231294258169e-06, "loss": 0.4422, "step": 9825 }, { "epoch": 2.515072, "grad_norm": 1.765625, "learning_rate": 8.088047094957768e-06, "loss": 0.4045, "step": 9826 }, { "epoch": 2.5153280000000002, "grad_norm": 1.671875, "learning_rate": 8.083781247333844e-06, "loss": 0.4468, "step": 9827 }, { "epoch": 2.515584, "grad_norm": 1.7265625, "learning_rate": 8.079515399709922e-06, "loss": 0.4272, "step": 9828 }, { "epoch": 2.51584, "grad_norm": 1.75, "learning_rate": 8.075249552086001e-06, "loss": 0.4344, "step": 9829 }, { "epoch": 2.516096, "grad_norm": 1.84375, "learning_rate": 8.070983704462077e-06, "loss": 0.4063, "step": 9830 }, { "epoch": 2.516352, "grad_norm": 1.7421875, "learning_rate": 8.066717856838155e-06, "loss": 0.3819, "step": 9831 }, { "epoch": 2.5166079999999997, "grad_norm": 1.890625, "learning_rate": 8.062452009214231e-06, "loss": 0.3949, "step": 9832 }, { "epoch": 2.516864, "grad_norm": 1.8203125, "learning_rate": 8.058186161590309e-06, "loss": 0.4229, "step": 9833 }, { "epoch": 2.5171200000000002, "grad_norm": 1.765625, "learning_rate": 8.053920313966386e-06, "loss": 0.4524, "step": 9834 }, { "epoch": 2.517376, "grad_norm": 1.7734375, "learning_rate": 8.049654466342462e-06, "loss": 0.3995, "step": 9835 }, { "epoch": 2.517632, "grad_norm": 1.734375, "learning_rate": 8.04538861871854e-06, "loss": 0.4253, "step": 9836 }, { "epoch": 2.517888, "grad_norm": 1.6640625, "learning_rate": 8.041122771094617e-06, "loss": 0.4476, "step": 9837 }, { "epoch": 2.518144, "grad_norm": 1.765625, "learning_rate": 8.036856923470693e-06, "loss": 0.4311, "step": 9838 }, { "epoch": 2.5183999999999997, "grad_norm": 1.765625, "learning_rate": 8.032591075846771e-06, "loss": 0.4312, "step": 9839 }, { "epoch": 2.518656, "grad_norm": 1.7421875, "learning_rate": 8.028325228222849e-06, "loss": 0.4434, "step": 9840 }, { "epoch": 2.5189120000000003, "grad_norm": 1.765625, "learning_rate": 8.024059380598925e-06, "loss": 0.4253, "step": 9841 }, { "epoch": 2.519168, "grad_norm": 1.71875, "learning_rate": 8.019793532975002e-06, "loss": 0.4071, "step": 9842 }, { "epoch": 2.519424, "grad_norm": 1.8046875, "learning_rate": 8.015527685351078e-06, "loss": 0.4403, "step": 9843 }, { "epoch": 2.51968, "grad_norm": 1.7265625, "learning_rate": 8.011261837727156e-06, "loss": 0.4179, "step": 9844 }, { "epoch": 2.519936, "grad_norm": 1.875, "learning_rate": 8.006995990103234e-06, "loss": 0.4277, "step": 9845 }, { "epoch": 2.5201919999999998, "grad_norm": 1.71875, "learning_rate": 8.002730142479311e-06, "loss": 0.3955, "step": 9846 }, { "epoch": 2.520448, "grad_norm": 1.7734375, "learning_rate": 7.998464294855389e-06, "loss": 0.4298, "step": 9847 }, { "epoch": 2.520704, "grad_norm": 1.75, "learning_rate": 7.994198447231465e-06, "loss": 0.4237, "step": 9848 }, { "epoch": 2.52096, "grad_norm": 1.75, "learning_rate": 7.989932599607543e-06, "loss": 0.3968, "step": 9849 }, { "epoch": 2.521216, "grad_norm": 1.734375, "learning_rate": 7.98566675198362e-06, "loss": 0.4218, "step": 9850 }, { "epoch": 2.521472, "grad_norm": 1.8984375, "learning_rate": 7.981400904359696e-06, "loss": 0.4223, "step": 9851 }, { "epoch": 2.521728, "grad_norm": 1.6796875, "learning_rate": 7.977135056735774e-06, "loss": 0.412, "step": 9852 }, { "epoch": 2.521984, "grad_norm": 1.859375, "learning_rate": 7.972869209111851e-06, "loss": 0.4319, "step": 9853 }, { "epoch": 2.52224, "grad_norm": 1.6640625, "learning_rate": 7.968603361487927e-06, "loss": 0.425, "step": 9854 }, { "epoch": 2.522496, "grad_norm": 1.734375, "learning_rate": 7.964337513864005e-06, "loss": 0.429, "step": 9855 }, { "epoch": 2.522752, "grad_norm": 1.7734375, "learning_rate": 7.960071666240083e-06, "loss": 0.4432, "step": 9856 }, { "epoch": 2.523008, "grad_norm": 1.828125, "learning_rate": 7.955805818616159e-06, "loss": 0.4434, "step": 9857 }, { "epoch": 2.523264, "grad_norm": 1.8203125, "learning_rate": 7.951539970992236e-06, "loss": 0.4329, "step": 9858 }, { "epoch": 2.52352, "grad_norm": 1.78125, "learning_rate": 7.947274123368312e-06, "loss": 0.4111, "step": 9859 }, { "epoch": 2.523776, "grad_norm": 1.8046875, "learning_rate": 7.94300827574439e-06, "loss": 0.4447, "step": 9860 }, { "epoch": 2.524032, "grad_norm": 1.8359375, "learning_rate": 7.938742428120468e-06, "loss": 0.3962, "step": 9861 }, { "epoch": 2.524288, "grad_norm": 1.6328125, "learning_rate": 7.934476580496545e-06, "loss": 0.4262, "step": 9862 }, { "epoch": 2.524544, "grad_norm": 1.7734375, "learning_rate": 7.930210732872623e-06, "loss": 0.3937, "step": 9863 }, { "epoch": 2.5248, "grad_norm": 1.7421875, "learning_rate": 7.9259448852487e-06, "loss": 0.4429, "step": 9864 }, { "epoch": 2.525056, "grad_norm": 1.6640625, "learning_rate": 7.921679037624777e-06, "loss": 0.3995, "step": 9865 }, { "epoch": 2.525312, "grad_norm": 1.7265625, "learning_rate": 7.917413190000854e-06, "loss": 0.4038, "step": 9866 }, { "epoch": 2.525568, "grad_norm": 1.7734375, "learning_rate": 7.91314734237693e-06, "loss": 0.4296, "step": 9867 }, { "epoch": 2.525824, "grad_norm": 1.875, "learning_rate": 7.908881494753008e-06, "loss": 0.3964, "step": 9868 }, { "epoch": 2.52608, "grad_norm": 1.890625, "learning_rate": 7.904615647129085e-06, "loss": 0.3966, "step": 9869 }, { "epoch": 2.526336, "grad_norm": 1.8359375, "learning_rate": 7.900349799505161e-06, "loss": 0.4433, "step": 9870 }, { "epoch": 2.526592, "grad_norm": 1.8125, "learning_rate": 7.896083951881239e-06, "loss": 0.4438, "step": 9871 }, { "epoch": 2.526848, "grad_norm": 1.7890625, "learning_rate": 7.891818104257317e-06, "loss": 0.4443, "step": 9872 }, { "epoch": 2.527104, "grad_norm": 1.796875, "learning_rate": 7.887552256633393e-06, "loss": 0.4259, "step": 9873 }, { "epoch": 2.52736, "grad_norm": 1.71875, "learning_rate": 7.88328640900947e-06, "loss": 0.4255, "step": 9874 }, { "epoch": 2.527616, "grad_norm": 1.7421875, "learning_rate": 7.879020561385548e-06, "loss": 0.4305, "step": 9875 }, { "epoch": 2.527872, "grad_norm": 1.7265625, "learning_rate": 7.874754713761624e-06, "loss": 0.4514, "step": 9876 }, { "epoch": 2.528128, "grad_norm": 1.8359375, "learning_rate": 7.870488866137702e-06, "loss": 0.4434, "step": 9877 }, { "epoch": 2.528384, "grad_norm": 1.7890625, "learning_rate": 7.86622301851378e-06, "loss": 0.3942, "step": 9878 }, { "epoch": 2.52864, "grad_norm": 1.796875, "learning_rate": 7.861957170889857e-06, "loss": 0.4561, "step": 9879 }, { "epoch": 2.528896, "grad_norm": 1.7734375, "learning_rate": 7.857691323265935e-06, "loss": 0.4176, "step": 9880 }, { "epoch": 2.529152, "grad_norm": 1.8125, "learning_rate": 7.85342547564201e-06, "loss": 0.4328, "step": 9881 }, { "epoch": 2.529408, "grad_norm": 1.8828125, "learning_rate": 7.849159628018088e-06, "loss": 0.393, "step": 9882 }, { "epoch": 2.529664, "grad_norm": 1.890625, "learning_rate": 7.844893780394164e-06, "loss": 0.4199, "step": 9883 }, { "epoch": 2.5299199999999997, "grad_norm": 1.7109375, "learning_rate": 7.840627932770242e-06, "loss": 0.4469, "step": 9884 }, { "epoch": 2.530176, "grad_norm": 1.7734375, "learning_rate": 7.83636208514632e-06, "loss": 0.4083, "step": 9885 }, { "epoch": 2.5304320000000002, "grad_norm": 1.7109375, "learning_rate": 7.832096237522395e-06, "loss": 0.431, "step": 9886 }, { "epoch": 2.530688, "grad_norm": 1.7265625, "learning_rate": 7.827830389898473e-06, "loss": 0.4298, "step": 9887 }, { "epoch": 2.530944, "grad_norm": 1.796875, "learning_rate": 7.82356454227455e-06, "loss": 0.3908, "step": 9888 }, { "epoch": 2.5312, "grad_norm": 1.796875, "learning_rate": 7.819298694650627e-06, "loss": 0.4283, "step": 9889 }, { "epoch": 2.531456, "grad_norm": 1.8671875, "learning_rate": 7.815032847026704e-06, "loss": 0.3891, "step": 9890 }, { "epoch": 2.5317119999999997, "grad_norm": 1.796875, "learning_rate": 7.810766999402782e-06, "loss": 0.4023, "step": 9891 }, { "epoch": 2.531968, "grad_norm": 1.8125, "learning_rate": 7.806501151778858e-06, "loss": 0.4237, "step": 9892 }, { "epoch": 2.5322240000000003, "grad_norm": 1.7734375, "learning_rate": 7.802235304154936e-06, "loss": 0.3963, "step": 9893 }, { "epoch": 2.53248, "grad_norm": 1.875, "learning_rate": 7.797969456531012e-06, "loss": 0.385, "step": 9894 }, { "epoch": 2.532736, "grad_norm": 1.6875, "learning_rate": 7.793703608907091e-06, "loss": 0.4149, "step": 9895 }, { "epoch": 2.532992, "grad_norm": 1.7421875, "learning_rate": 7.789437761283169e-06, "loss": 0.4045, "step": 9896 }, { "epoch": 2.533248, "grad_norm": 1.7734375, "learning_rate": 7.785171913659245e-06, "loss": 0.3848, "step": 9897 }, { "epoch": 2.5335039999999998, "grad_norm": 1.8515625, "learning_rate": 7.780906066035322e-06, "loss": 0.4018, "step": 9898 }, { "epoch": 2.53376, "grad_norm": 1.6953125, "learning_rate": 7.776640218411398e-06, "loss": 0.4496, "step": 9899 }, { "epoch": 2.5340160000000003, "grad_norm": 1.71875, "learning_rate": 7.772374370787476e-06, "loss": 0.4327, "step": 9900 }, { "epoch": 2.534272, "grad_norm": 1.7265625, "learning_rate": 7.768108523163553e-06, "loss": 0.4546, "step": 9901 }, { "epoch": 2.534528, "grad_norm": 1.6875, "learning_rate": 7.76384267553963e-06, "loss": 0.4184, "step": 9902 }, { "epoch": 2.534784, "grad_norm": 1.8046875, "learning_rate": 7.759576827915707e-06, "loss": 0.4494, "step": 9903 }, { "epoch": 2.53504, "grad_norm": 1.625, "learning_rate": 7.755310980291785e-06, "loss": 0.4173, "step": 9904 }, { "epoch": 2.5352959999999998, "grad_norm": 1.6875, "learning_rate": 7.75104513266786e-06, "loss": 0.4372, "step": 9905 }, { "epoch": 2.535552, "grad_norm": 1.84375, "learning_rate": 7.746779285043938e-06, "loss": 0.4536, "step": 9906 }, { "epoch": 2.535808, "grad_norm": 1.6953125, "learning_rate": 7.742513437420016e-06, "loss": 0.4473, "step": 9907 }, { "epoch": 2.536064, "grad_norm": 1.828125, "learning_rate": 7.738247589796092e-06, "loss": 0.4414, "step": 9908 }, { "epoch": 2.53632, "grad_norm": 1.65625, "learning_rate": 7.73398174217217e-06, "loss": 0.4414, "step": 9909 }, { "epoch": 2.536576, "grad_norm": 1.7734375, "learning_rate": 7.729715894548247e-06, "loss": 0.4208, "step": 9910 }, { "epoch": 2.536832, "grad_norm": 1.8125, "learning_rate": 7.725450046924325e-06, "loss": 0.4238, "step": 9911 }, { "epoch": 2.537088, "grad_norm": 1.765625, "learning_rate": 7.721184199300403e-06, "loss": 0.4071, "step": 9912 }, { "epoch": 2.537344, "grad_norm": 1.765625, "learning_rate": 7.716918351676479e-06, "loss": 0.4195, "step": 9913 }, { "epoch": 2.5376, "grad_norm": 1.734375, "learning_rate": 7.712652504052556e-06, "loss": 0.4406, "step": 9914 }, { "epoch": 2.537856, "grad_norm": 1.8515625, "learning_rate": 7.708386656428634e-06, "loss": 0.4163, "step": 9915 }, { "epoch": 2.538112, "grad_norm": 1.7890625, "learning_rate": 7.70412080880471e-06, "loss": 0.4406, "step": 9916 }, { "epoch": 2.538368, "grad_norm": 1.75, "learning_rate": 7.699854961180787e-06, "loss": 0.4105, "step": 9917 }, { "epoch": 2.538624, "grad_norm": 1.890625, "learning_rate": 7.695589113556863e-06, "loss": 0.4035, "step": 9918 }, { "epoch": 2.53888, "grad_norm": 1.703125, "learning_rate": 7.691323265932941e-06, "loss": 0.4502, "step": 9919 }, { "epoch": 2.539136, "grad_norm": 1.8515625, "learning_rate": 7.687057418309019e-06, "loss": 0.3953, "step": 9920 }, { "epoch": 2.539392, "grad_norm": 1.8984375, "learning_rate": 7.682791570685095e-06, "loss": 0.4317, "step": 9921 }, { "epoch": 2.539648, "grad_norm": 1.828125, "learning_rate": 7.678525723061172e-06, "loss": 0.379, "step": 9922 }, { "epoch": 2.539904, "grad_norm": 1.78125, "learning_rate": 7.67425987543725e-06, "loss": 0.4866, "step": 9923 }, { "epoch": 2.54016, "grad_norm": 1.75, "learning_rate": 7.669994027813326e-06, "loss": 0.4441, "step": 9924 }, { "epoch": 2.540416, "grad_norm": 1.8984375, "learning_rate": 7.665728180189404e-06, "loss": 0.3856, "step": 9925 }, { "epoch": 2.540672, "grad_norm": 1.6328125, "learning_rate": 7.661462332565481e-06, "loss": 0.4028, "step": 9926 }, { "epoch": 2.540928, "grad_norm": 1.75, "learning_rate": 7.657196484941559e-06, "loss": 0.4009, "step": 9927 }, { "epoch": 2.541184, "grad_norm": 1.84375, "learning_rate": 7.652930637317637e-06, "loss": 0.4159, "step": 9928 }, { "epoch": 2.54144, "grad_norm": 1.7421875, "learning_rate": 7.648664789693713e-06, "loss": 0.4053, "step": 9929 }, { "epoch": 2.541696, "grad_norm": 1.7421875, "learning_rate": 7.64439894206979e-06, "loss": 0.4267, "step": 9930 }, { "epoch": 2.541952, "grad_norm": 1.8203125, "learning_rate": 7.640133094445868e-06, "loss": 0.3739, "step": 9931 }, { "epoch": 2.542208, "grad_norm": 1.734375, "learning_rate": 7.635867246821944e-06, "loss": 0.3963, "step": 9932 }, { "epoch": 2.542464, "grad_norm": 1.7734375, "learning_rate": 7.631601399198021e-06, "loss": 0.4411, "step": 9933 }, { "epoch": 2.54272, "grad_norm": 1.7265625, "learning_rate": 7.627335551574098e-06, "loss": 0.4357, "step": 9934 }, { "epoch": 2.542976, "grad_norm": 1.8046875, "learning_rate": 7.623069703950175e-06, "loss": 0.4131, "step": 9935 }, { "epoch": 2.543232, "grad_norm": 1.6875, "learning_rate": 7.618803856326252e-06, "loss": 0.4298, "step": 9936 }, { "epoch": 2.543488, "grad_norm": 1.796875, "learning_rate": 7.6145380087023296e-06, "loss": 0.4021, "step": 9937 }, { "epoch": 2.5437440000000002, "grad_norm": 1.734375, "learning_rate": 7.610272161078406e-06, "loss": 0.4139, "step": 9938 }, { "epoch": 2.544, "grad_norm": 1.6796875, "learning_rate": 7.606006313454483e-06, "loss": 0.4395, "step": 9939 }, { "epoch": 2.544256, "grad_norm": 1.7109375, "learning_rate": 7.601740465830561e-06, "loss": 0.407, "step": 9940 }, { "epoch": 2.544512, "grad_norm": 1.6484375, "learning_rate": 7.597474618206638e-06, "loss": 0.4002, "step": 9941 }, { "epoch": 2.544768, "grad_norm": 1.71875, "learning_rate": 7.5932087705827145e-06, "loss": 0.4106, "step": 9942 }, { "epoch": 2.5450239999999997, "grad_norm": 1.8828125, "learning_rate": 7.588942922958791e-06, "loss": 0.3976, "step": 9943 }, { "epoch": 2.54528, "grad_norm": 1.734375, "learning_rate": 7.58467707533487e-06, "loss": 0.4146, "step": 9944 }, { "epoch": 2.5455360000000002, "grad_norm": 1.7734375, "learning_rate": 7.580411227710947e-06, "loss": 0.4056, "step": 9945 }, { "epoch": 2.545792, "grad_norm": 1.6953125, "learning_rate": 7.576145380087024e-06, "loss": 0.4199, "step": 9946 }, { "epoch": 2.546048, "grad_norm": 1.7578125, "learning_rate": 7.571879532463101e-06, "loss": 0.4296, "step": 9947 }, { "epoch": 2.546304, "grad_norm": 1.921875, "learning_rate": 7.567613684839178e-06, "loss": 0.4188, "step": 9948 }, { "epoch": 2.54656, "grad_norm": 1.7421875, "learning_rate": 7.5633478372152555e-06, "loss": 0.4084, "step": 9949 }, { "epoch": 2.5468159999999997, "grad_norm": 1.7421875, "learning_rate": 7.559081989591332e-06, "loss": 0.4168, "step": 9950 }, { "epoch": 2.547072, "grad_norm": 1.8203125, "learning_rate": 7.554816141967409e-06, "loss": 0.4331, "step": 9951 }, { "epoch": 2.5473280000000003, "grad_norm": 1.8125, "learning_rate": 7.550550294343487e-06, "loss": 0.3965, "step": 9952 }, { "epoch": 2.547584, "grad_norm": 1.859375, "learning_rate": 7.5462844467195636e-06, "loss": 0.3838, "step": 9953 }, { "epoch": 2.54784, "grad_norm": 1.75, "learning_rate": 7.54201859909564e-06, "loss": 0.4017, "step": 9954 }, { "epoch": 2.548096, "grad_norm": 1.828125, "learning_rate": 7.537752751471717e-06, "loss": 0.3981, "step": 9955 }, { "epoch": 2.548352, "grad_norm": 1.7578125, "learning_rate": 7.533486903847795e-06, "loss": 0.4514, "step": 9956 }, { "epoch": 2.5486079999999998, "grad_norm": 1.7421875, "learning_rate": 7.529221056223872e-06, "loss": 0.4183, "step": 9957 }, { "epoch": 2.548864, "grad_norm": 1.828125, "learning_rate": 7.5249552085999485e-06, "loss": 0.4366, "step": 9958 }, { "epoch": 2.5491200000000003, "grad_norm": 1.671875, "learning_rate": 7.520689360976025e-06, "loss": 0.3872, "step": 9959 }, { "epoch": 2.549376, "grad_norm": 1.796875, "learning_rate": 7.516423513352104e-06, "loss": 0.4407, "step": 9960 }, { "epoch": 2.549632, "grad_norm": 1.7734375, "learning_rate": 7.512157665728181e-06, "loss": 0.4021, "step": 9961 }, { "epoch": 2.549888, "grad_norm": 1.7890625, "learning_rate": 7.507891818104258e-06, "loss": 0.4221, "step": 9962 }, { "epoch": 2.550144, "grad_norm": 1.9296875, "learning_rate": 7.503625970480335e-06, "loss": 0.3974, "step": 9963 }, { "epoch": 2.5504, "grad_norm": 1.828125, "learning_rate": 7.499360122856413e-06, "loss": 0.4301, "step": 9964 }, { "epoch": 2.550656, "grad_norm": 1.765625, "learning_rate": 7.4950942752324895e-06, "loss": 0.3886, "step": 9965 }, { "epoch": 2.550912, "grad_norm": 1.65625, "learning_rate": 7.490828427608566e-06, "loss": 0.4219, "step": 9966 }, { "epoch": 2.551168, "grad_norm": 1.671875, "learning_rate": 7.486562579984643e-06, "loss": 0.4158, "step": 9967 }, { "epoch": 2.551424, "grad_norm": 1.75, "learning_rate": 7.482296732360721e-06, "loss": 0.4479, "step": 9968 }, { "epoch": 2.55168, "grad_norm": 1.8515625, "learning_rate": 7.4780308847367976e-06, "loss": 0.4475, "step": 9969 }, { "epoch": 2.551936, "grad_norm": 1.765625, "learning_rate": 7.473765037112874e-06, "loss": 0.4345, "step": 9970 }, { "epoch": 2.552192, "grad_norm": 1.7265625, "learning_rate": 7.469499189488951e-06, "loss": 0.4482, "step": 9971 }, { "epoch": 2.552448, "grad_norm": 1.921875, "learning_rate": 7.465233341865029e-06, "loss": 0.4491, "step": 9972 }, { "epoch": 2.552704, "grad_norm": 1.8984375, "learning_rate": 7.460967494241106e-06, "loss": 0.4276, "step": 9973 }, { "epoch": 2.55296, "grad_norm": 1.7265625, "learning_rate": 7.4567016466171825e-06, "loss": 0.4202, "step": 9974 }, { "epoch": 2.553216, "grad_norm": 1.6640625, "learning_rate": 7.45243579899326e-06, "loss": 0.3944, "step": 9975 }, { "epoch": 2.553472, "grad_norm": 1.65625, "learning_rate": 7.448169951369337e-06, "loss": 0.4252, "step": 9976 }, { "epoch": 2.553728, "grad_norm": 1.875, "learning_rate": 7.443904103745415e-06, "loss": 0.4349, "step": 9977 }, { "epoch": 2.553984, "grad_norm": 1.8203125, "learning_rate": 7.439638256121492e-06, "loss": 0.429, "step": 9978 }, { "epoch": 2.55424, "grad_norm": 1.734375, "learning_rate": 7.435372408497569e-06, "loss": 0.4254, "step": 9979 }, { "epoch": 2.554496, "grad_norm": 1.734375, "learning_rate": 7.431106560873647e-06, "loss": 0.402, "step": 9980 }, { "epoch": 2.554752, "grad_norm": 1.828125, "learning_rate": 7.4268407132497235e-06, "loss": 0.4279, "step": 9981 }, { "epoch": 2.555008, "grad_norm": 1.71875, "learning_rate": 7.4225748656258e-06, "loss": 0.3786, "step": 9982 }, { "epoch": 2.555264, "grad_norm": 1.71875, "learning_rate": 7.418309018001877e-06, "loss": 0.4148, "step": 9983 }, { "epoch": 2.55552, "grad_norm": 1.7578125, "learning_rate": 7.414043170377955e-06, "loss": 0.4226, "step": 9984 }, { "epoch": 2.555776, "grad_norm": 1.90625, "learning_rate": 7.4097773227540316e-06, "loss": 0.4122, "step": 9985 }, { "epoch": 2.556032, "grad_norm": 1.7109375, "learning_rate": 7.405511475130108e-06, "loss": 0.4494, "step": 9986 }, { "epoch": 2.556288, "grad_norm": 1.7578125, "learning_rate": 7.401245627506186e-06, "loss": 0.402, "step": 9987 }, { "epoch": 2.556544, "grad_norm": 1.7578125, "learning_rate": 7.396979779882263e-06, "loss": 0.3748, "step": 9988 }, { "epoch": 2.5568, "grad_norm": 1.703125, "learning_rate": 7.39271393225834e-06, "loss": 0.4236, "step": 9989 }, { "epoch": 2.557056, "grad_norm": 1.765625, "learning_rate": 7.3884480846344165e-06, "loss": 0.4094, "step": 9990 }, { "epoch": 2.557312, "grad_norm": 1.7265625, "learning_rate": 7.384182237010494e-06, "loss": 0.4282, "step": 9991 }, { "epoch": 2.557568, "grad_norm": 1.734375, "learning_rate": 7.379916389386571e-06, "loss": 0.3822, "step": 9992 }, { "epoch": 2.557824, "grad_norm": 1.7890625, "learning_rate": 7.375650541762649e-06, "loss": 0.4247, "step": 9993 }, { "epoch": 2.55808, "grad_norm": 1.859375, "learning_rate": 7.371384694138726e-06, "loss": 0.44, "step": 9994 }, { "epoch": 2.558336, "grad_norm": 1.8125, "learning_rate": 7.367118846514803e-06, "loss": 0.3973, "step": 9995 }, { "epoch": 2.558592, "grad_norm": 1.65625, "learning_rate": 7.362852998890881e-06, "loss": 0.4262, "step": 9996 }, { "epoch": 2.5588480000000002, "grad_norm": 1.625, "learning_rate": 7.3585871512669575e-06, "loss": 0.4068, "step": 9997 }, { "epoch": 2.559104, "grad_norm": 2.015625, "learning_rate": 7.354321303643034e-06, "loss": 0.4326, "step": 9998 }, { "epoch": 2.55936, "grad_norm": 1.7578125, "learning_rate": 7.350055456019111e-06, "loss": 0.4096, "step": 9999 }, { "epoch": 2.559616, "grad_norm": 1.8515625, "learning_rate": 7.345789608395189e-06, "loss": 0.4535, "step": 10000 }, { "epoch": 2.559872, "grad_norm": 1.7890625, "learning_rate": 7.3415237607712656e-06, "loss": 0.4228, "step": 10001 }, { "epoch": 2.5601279999999997, "grad_norm": 1.7109375, "learning_rate": 7.337257913147342e-06, "loss": 0.398, "step": 10002 }, { "epoch": 2.560384, "grad_norm": 1.8125, "learning_rate": 7.33299206552342e-06, "loss": 0.4592, "step": 10003 }, { "epoch": 2.5606400000000002, "grad_norm": 1.75, "learning_rate": 7.328726217899497e-06, "loss": 0.4043, "step": 10004 }, { "epoch": 2.560896, "grad_norm": 1.796875, "learning_rate": 7.324460370275574e-06, "loss": 0.4224, "step": 10005 }, { "epoch": 2.561152, "grad_norm": 1.890625, "learning_rate": 7.3201945226516505e-06, "loss": 0.4185, "step": 10006 }, { "epoch": 2.561408, "grad_norm": 1.671875, "learning_rate": 7.315928675027728e-06, "loss": 0.4126, "step": 10007 }, { "epoch": 2.561664, "grad_norm": 1.671875, "learning_rate": 7.311662827403805e-06, "loss": 0.4056, "step": 10008 }, { "epoch": 2.5619199999999998, "grad_norm": 1.640625, "learning_rate": 7.307396979779883e-06, "loss": 0.4054, "step": 10009 }, { "epoch": 2.562176, "grad_norm": 1.890625, "learning_rate": 7.30313113215596e-06, "loss": 0.3919, "step": 10010 }, { "epoch": 2.5624320000000003, "grad_norm": 1.8125, "learning_rate": 7.298865284532037e-06, "loss": 0.4102, "step": 10011 }, { "epoch": 2.562688, "grad_norm": 1.703125, "learning_rate": 7.294599436908115e-06, "loss": 0.4389, "step": 10012 }, { "epoch": 2.562944, "grad_norm": 1.875, "learning_rate": 7.2903335892841915e-06, "loss": 0.436, "step": 10013 }, { "epoch": 2.5632, "grad_norm": 1.890625, "learning_rate": 7.286067741660268e-06, "loss": 0.4328, "step": 10014 }, { "epoch": 2.563456, "grad_norm": 1.7265625, "learning_rate": 7.281801894036346e-06, "loss": 0.4339, "step": 10015 }, { "epoch": 2.5637119999999998, "grad_norm": 1.71875, "learning_rate": 7.277536046412423e-06, "loss": 0.4116, "step": 10016 }, { "epoch": 2.563968, "grad_norm": 1.7265625, "learning_rate": 7.2732701987884996e-06, "loss": 0.3872, "step": 10017 }, { "epoch": 2.564224, "grad_norm": 1.6640625, "learning_rate": 7.269004351164576e-06, "loss": 0.4387, "step": 10018 }, { "epoch": 2.56448, "grad_norm": 1.78125, "learning_rate": 7.264738503540654e-06, "loss": 0.4391, "step": 10019 }, { "epoch": 2.564736, "grad_norm": 1.8046875, "learning_rate": 7.260472655916731e-06, "loss": 0.4654, "step": 10020 }, { "epoch": 2.564992, "grad_norm": 1.7578125, "learning_rate": 7.256206808292808e-06, "loss": 0.3937, "step": 10021 }, { "epoch": 2.565248, "grad_norm": 1.7109375, "learning_rate": 7.2519409606688845e-06, "loss": 0.4349, "step": 10022 }, { "epoch": 2.565504, "grad_norm": 1.8046875, "learning_rate": 7.247675113044962e-06, "loss": 0.4205, "step": 10023 }, { "epoch": 2.56576, "grad_norm": 1.65625, "learning_rate": 7.243409265421039e-06, "loss": 0.4497, "step": 10024 }, { "epoch": 2.566016, "grad_norm": 1.6953125, "learning_rate": 7.239143417797116e-06, "loss": 0.3813, "step": 10025 }, { "epoch": 2.566272, "grad_norm": 1.734375, "learning_rate": 7.234877570173194e-06, "loss": 0.3809, "step": 10026 }, { "epoch": 2.566528, "grad_norm": 1.7578125, "learning_rate": 7.230611722549271e-06, "loss": 0.3839, "step": 10027 }, { "epoch": 2.566784, "grad_norm": 1.8046875, "learning_rate": 7.226345874925349e-06, "loss": 0.4392, "step": 10028 }, { "epoch": 2.56704, "grad_norm": 1.6875, "learning_rate": 7.2220800273014255e-06, "loss": 0.422, "step": 10029 }, { "epoch": 2.567296, "grad_norm": 1.875, "learning_rate": 7.217814179677502e-06, "loss": 0.3997, "step": 10030 }, { "epoch": 2.567552, "grad_norm": 1.71875, "learning_rate": 7.21354833205358e-06, "loss": 0.4289, "step": 10031 }, { "epoch": 2.567808, "grad_norm": 1.6875, "learning_rate": 7.209282484429657e-06, "loss": 0.4478, "step": 10032 }, { "epoch": 2.568064, "grad_norm": 1.734375, "learning_rate": 7.2050166368057336e-06, "loss": 0.437, "step": 10033 }, { "epoch": 2.56832, "grad_norm": 1.6328125, "learning_rate": 7.20075078918181e-06, "loss": 0.4225, "step": 10034 }, { "epoch": 2.568576, "grad_norm": 1.71875, "learning_rate": 7.196484941557888e-06, "loss": 0.4229, "step": 10035 }, { "epoch": 2.568832, "grad_norm": 1.90625, "learning_rate": 7.192219093933965e-06, "loss": 0.4311, "step": 10036 }, { "epoch": 2.569088, "grad_norm": 1.7734375, "learning_rate": 7.187953246310042e-06, "loss": 0.3639, "step": 10037 }, { "epoch": 2.569344, "grad_norm": 1.8203125, "learning_rate": 7.183687398686119e-06, "loss": 0.4303, "step": 10038 }, { "epoch": 2.5696, "grad_norm": 1.78125, "learning_rate": 7.179421551062196e-06, "loss": 0.4114, "step": 10039 }, { "epoch": 2.569856, "grad_norm": 1.7890625, "learning_rate": 7.175155703438273e-06, "loss": 0.4183, "step": 10040 }, { "epoch": 2.570112, "grad_norm": 1.8203125, "learning_rate": 7.17088985581435e-06, "loss": 0.3684, "step": 10041 }, { "epoch": 2.570368, "grad_norm": 1.7265625, "learning_rate": 7.166624008190428e-06, "loss": 0.4421, "step": 10042 }, { "epoch": 2.570624, "grad_norm": 1.8125, "learning_rate": 7.162358160566506e-06, "loss": 0.4011, "step": 10043 }, { "epoch": 2.57088, "grad_norm": 1.828125, "learning_rate": 7.158092312942583e-06, "loss": 0.4071, "step": 10044 }, { "epoch": 2.571136, "grad_norm": 1.84375, "learning_rate": 7.1538264653186595e-06, "loss": 0.424, "step": 10045 }, { "epoch": 2.571392, "grad_norm": 1.7421875, "learning_rate": 7.149560617694736e-06, "loss": 0.4362, "step": 10046 }, { "epoch": 2.571648, "grad_norm": 1.6953125, "learning_rate": 7.145294770070814e-06, "loss": 0.4461, "step": 10047 }, { "epoch": 2.571904, "grad_norm": 1.765625, "learning_rate": 7.141028922446891e-06, "loss": 0.4175, "step": 10048 }, { "epoch": 2.5721600000000002, "grad_norm": 1.734375, "learning_rate": 7.1367630748229676e-06, "loss": 0.4236, "step": 10049 }, { "epoch": 2.572416, "grad_norm": 1.7890625, "learning_rate": 7.132497227199044e-06, "loss": 0.4181, "step": 10050 }, { "epoch": 2.572672, "grad_norm": 1.7734375, "learning_rate": 7.128231379575122e-06, "loss": 0.3994, "step": 10051 }, { "epoch": 2.572928, "grad_norm": 1.6875, "learning_rate": 7.123965531951199e-06, "loss": 0.3943, "step": 10052 }, { "epoch": 2.573184, "grad_norm": 1.734375, "learning_rate": 7.119699684327276e-06, "loss": 0.4002, "step": 10053 }, { "epoch": 2.5734399999999997, "grad_norm": 1.828125, "learning_rate": 7.115433836703353e-06, "loss": 0.3883, "step": 10054 }, { "epoch": 2.573696, "grad_norm": 1.734375, "learning_rate": 7.11116798907943e-06, "loss": 0.4173, "step": 10055 }, { "epoch": 2.5739520000000002, "grad_norm": 1.7265625, "learning_rate": 7.106902141455507e-06, "loss": 0.4244, "step": 10056 }, { "epoch": 2.574208, "grad_norm": 1.625, "learning_rate": 7.102636293831584e-06, "loss": 0.3818, "step": 10057 }, { "epoch": 2.574464, "grad_norm": 1.8046875, "learning_rate": 7.098370446207661e-06, "loss": 0.4517, "step": 10058 }, { "epoch": 2.57472, "grad_norm": 1.640625, "learning_rate": 7.09410459858374e-06, "loss": 0.4383, "step": 10059 }, { "epoch": 2.574976, "grad_norm": 1.8125, "learning_rate": 7.089838750959817e-06, "loss": 0.3802, "step": 10060 }, { "epoch": 2.5752319999999997, "grad_norm": 1.8359375, "learning_rate": 7.0855729033358935e-06, "loss": 0.4196, "step": 10061 }, { "epoch": 2.575488, "grad_norm": 1.7578125, "learning_rate": 7.08130705571197e-06, "loss": 0.378, "step": 10062 }, { "epoch": 2.5757440000000003, "grad_norm": 1.703125, "learning_rate": 7.077041208088048e-06, "loss": 0.4136, "step": 10063 }, { "epoch": 2.576, "grad_norm": 1.75, "learning_rate": 7.072775360464125e-06, "loss": 0.431, "step": 10064 }, { "epoch": 2.576256, "grad_norm": 1.78125, "learning_rate": 7.0685095128402016e-06, "loss": 0.4183, "step": 10065 }, { "epoch": 2.576512, "grad_norm": 1.6640625, "learning_rate": 7.064243665216279e-06, "loss": 0.4599, "step": 10066 }, { "epoch": 2.576768, "grad_norm": 1.6875, "learning_rate": 7.059977817592356e-06, "loss": 0.4458, "step": 10067 }, { "epoch": 2.5770239999999998, "grad_norm": 1.671875, "learning_rate": 7.055711969968433e-06, "loss": 0.4274, "step": 10068 }, { "epoch": 2.57728, "grad_norm": 1.8515625, "learning_rate": 7.05144612234451e-06, "loss": 0.409, "step": 10069 }, { "epoch": 2.5775360000000003, "grad_norm": 1.7890625, "learning_rate": 7.047180274720587e-06, "loss": 0.425, "step": 10070 }, { "epoch": 2.577792, "grad_norm": 1.703125, "learning_rate": 7.042914427096664e-06, "loss": 0.4105, "step": 10071 }, { "epoch": 2.578048, "grad_norm": 1.65625, "learning_rate": 7.038648579472741e-06, "loss": 0.4028, "step": 10072 }, { "epoch": 2.578304, "grad_norm": 1.75, "learning_rate": 7.034382731848818e-06, "loss": 0.4094, "step": 10073 }, { "epoch": 2.57856, "grad_norm": 1.640625, "learning_rate": 7.030116884224895e-06, "loss": 0.4208, "step": 10074 }, { "epoch": 2.5788159999999998, "grad_norm": 1.796875, "learning_rate": 7.025851036600974e-06, "loss": 0.4494, "step": 10075 }, { "epoch": 2.579072, "grad_norm": 1.6953125, "learning_rate": 7.021585188977051e-06, "loss": 0.4515, "step": 10076 }, { "epoch": 2.579328, "grad_norm": 1.71875, "learning_rate": 7.0173193413531275e-06, "loss": 0.41, "step": 10077 }, { "epoch": 2.579584, "grad_norm": 1.7578125, "learning_rate": 7.013053493729204e-06, "loss": 0.4355, "step": 10078 }, { "epoch": 2.57984, "grad_norm": 1.703125, "learning_rate": 7.008787646105282e-06, "loss": 0.4266, "step": 10079 }, { "epoch": 2.580096, "grad_norm": 1.7578125, "learning_rate": 7.004521798481359e-06, "loss": 0.4426, "step": 10080 }, { "epoch": 2.580352, "grad_norm": 1.859375, "learning_rate": 7.0002559508574356e-06, "loss": 0.4083, "step": 10081 }, { "epoch": 2.580608, "grad_norm": 1.859375, "learning_rate": 6.995990103233513e-06, "loss": 0.375, "step": 10082 }, { "epoch": 2.580864, "grad_norm": 1.921875, "learning_rate": 6.99172425560959e-06, "loss": 0.3961, "step": 10083 }, { "epoch": 2.58112, "grad_norm": 1.6875, "learning_rate": 6.987458407985667e-06, "loss": 0.4644, "step": 10084 }, { "epoch": 2.581376, "grad_norm": 1.7109375, "learning_rate": 6.983192560361744e-06, "loss": 0.4281, "step": 10085 }, { "epoch": 2.581632, "grad_norm": 1.6484375, "learning_rate": 6.978926712737821e-06, "loss": 0.4271, "step": 10086 }, { "epoch": 2.581888, "grad_norm": 1.7421875, "learning_rate": 6.974660865113898e-06, "loss": 0.4056, "step": 10087 }, { "epoch": 2.582144, "grad_norm": 1.828125, "learning_rate": 6.970395017489975e-06, "loss": 0.3615, "step": 10088 }, { "epoch": 2.5824, "grad_norm": 1.75, "learning_rate": 6.9661291698660526e-06, "loss": 0.4183, "step": 10089 }, { "epoch": 2.582656, "grad_norm": 1.8671875, "learning_rate": 6.961863322242129e-06, "loss": 0.3997, "step": 10090 }, { "epoch": 2.582912, "grad_norm": 1.6484375, "learning_rate": 6.957597474618208e-06, "loss": 0.449, "step": 10091 }, { "epoch": 2.583168, "grad_norm": 1.703125, "learning_rate": 6.953331626994285e-06, "loss": 0.3893, "step": 10092 }, { "epoch": 2.583424, "grad_norm": 1.75, "learning_rate": 6.9490657793703615e-06, "loss": 0.4072, "step": 10093 }, { "epoch": 2.58368, "grad_norm": 1.9296875, "learning_rate": 6.944799931746439e-06, "loss": 0.4135, "step": 10094 }, { "epoch": 2.583936, "grad_norm": 1.703125, "learning_rate": 6.940534084122516e-06, "loss": 0.4289, "step": 10095 }, { "epoch": 2.584192, "grad_norm": 1.765625, "learning_rate": 6.936268236498593e-06, "loss": 0.4175, "step": 10096 }, { "epoch": 2.584448, "grad_norm": 1.640625, "learning_rate": 6.9320023888746696e-06, "loss": 0.3977, "step": 10097 }, { "epoch": 2.584704, "grad_norm": 1.71875, "learning_rate": 6.927736541250747e-06, "loss": 0.4544, "step": 10098 }, { "epoch": 2.58496, "grad_norm": 1.78125, "learning_rate": 6.923470693626824e-06, "loss": 0.4091, "step": 10099 }, { "epoch": 2.585216, "grad_norm": 1.7109375, "learning_rate": 6.919204846002901e-06, "loss": 0.4114, "step": 10100 }, { "epoch": 2.585472, "grad_norm": 1.8203125, "learning_rate": 6.914938998378978e-06, "loss": 0.426, "step": 10101 }, { "epoch": 2.585728, "grad_norm": 1.7890625, "learning_rate": 6.910673150755055e-06, "loss": 0.4202, "step": 10102 }, { "epoch": 2.585984, "grad_norm": 1.7265625, "learning_rate": 6.906407303131132e-06, "loss": 0.4018, "step": 10103 }, { "epoch": 2.58624, "grad_norm": 1.7109375, "learning_rate": 6.902141455507209e-06, "loss": 0.4202, "step": 10104 }, { "epoch": 2.586496, "grad_norm": 1.6171875, "learning_rate": 6.8978756078832866e-06, "loss": 0.4179, "step": 10105 }, { "epoch": 2.586752, "grad_norm": 1.765625, "learning_rate": 6.893609760259363e-06, "loss": 0.409, "step": 10106 }, { "epoch": 2.587008, "grad_norm": 1.703125, "learning_rate": 6.88934391263544e-06, "loss": 0.4502, "step": 10107 }, { "epoch": 2.5872640000000002, "grad_norm": 1.765625, "learning_rate": 6.885078065011519e-06, "loss": 0.428, "step": 10108 }, { "epoch": 2.58752, "grad_norm": 1.8203125, "learning_rate": 6.8808122173875955e-06, "loss": 0.472, "step": 10109 }, { "epoch": 2.587776, "grad_norm": 1.7578125, "learning_rate": 6.876546369763673e-06, "loss": 0.4367, "step": 10110 }, { "epoch": 2.588032, "grad_norm": 1.71875, "learning_rate": 6.87228052213975e-06, "loss": 0.4258, "step": 10111 }, { "epoch": 2.588288, "grad_norm": 1.8515625, "learning_rate": 6.868014674515827e-06, "loss": 0.4105, "step": 10112 }, { "epoch": 2.5885439999999997, "grad_norm": 1.7421875, "learning_rate": 6.8637488268919036e-06, "loss": 0.4701, "step": 10113 }, { "epoch": 2.5888, "grad_norm": 1.7890625, "learning_rate": 6.859482979267981e-06, "loss": 0.3898, "step": 10114 }, { "epoch": 2.5890560000000002, "grad_norm": 1.8203125, "learning_rate": 6.855217131644058e-06, "loss": 0.4404, "step": 10115 }, { "epoch": 2.589312, "grad_norm": 1.8125, "learning_rate": 6.850951284020135e-06, "loss": 0.4131, "step": 10116 }, { "epoch": 2.589568, "grad_norm": 1.8046875, "learning_rate": 6.8466854363962125e-06, "loss": 0.4371, "step": 10117 }, { "epoch": 2.589824, "grad_norm": 1.7265625, "learning_rate": 6.842419588772289e-06, "loss": 0.4193, "step": 10118 }, { "epoch": 2.59008, "grad_norm": 1.6796875, "learning_rate": 6.838153741148366e-06, "loss": 0.4294, "step": 10119 }, { "epoch": 2.5903359999999997, "grad_norm": 1.75, "learning_rate": 6.833887893524443e-06, "loss": 0.4047, "step": 10120 }, { "epoch": 2.590592, "grad_norm": 1.640625, "learning_rate": 6.8296220459005206e-06, "loss": 0.4582, "step": 10121 }, { "epoch": 2.5908480000000003, "grad_norm": 1.734375, "learning_rate": 6.825356198276597e-06, "loss": 0.4064, "step": 10122 }, { "epoch": 2.591104, "grad_norm": 1.796875, "learning_rate": 6.821090350652674e-06, "loss": 0.4222, "step": 10123 }, { "epoch": 2.59136, "grad_norm": 1.7421875, "learning_rate": 6.816824503028753e-06, "loss": 0.3941, "step": 10124 }, { "epoch": 2.591616, "grad_norm": 1.9140625, "learning_rate": 6.8125586554048295e-06, "loss": 0.429, "step": 10125 }, { "epoch": 2.591872, "grad_norm": 1.90625, "learning_rate": 6.808292807780907e-06, "loss": 0.4446, "step": 10126 }, { "epoch": 2.5921279999999998, "grad_norm": 1.7578125, "learning_rate": 6.804026960156984e-06, "loss": 0.4709, "step": 10127 }, { "epoch": 2.592384, "grad_norm": 1.859375, "learning_rate": 6.799761112533061e-06, "loss": 0.4451, "step": 10128 }, { "epoch": 2.59264, "grad_norm": 1.796875, "learning_rate": 6.7954952649091384e-06, "loss": 0.4082, "step": 10129 }, { "epoch": 2.592896, "grad_norm": 1.640625, "learning_rate": 6.791229417285215e-06, "loss": 0.4597, "step": 10130 }, { "epoch": 2.593152, "grad_norm": 1.7265625, "learning_rate": 6.786963569661292e-06, "loss": 0.4437, "step": 10131 }, { "epoch": 2.593408, "grad_norm": 1.859375, "learning_rate": 6.782697722037369e-06, "loss": 0.4184, "step": 10132 }, { "epoch": 2.593664, "grad_norm": 1.6953125, "learning_rate": 6.7784318744134465e-06, "loss": 0.4112, "step": 10133 }, { "epoch": 2.59392, "grad_norm": 1.828125, "learning_rate": 6.774166026789523e-06, "loss": 0.4238, "step": 10134 }, { "epoch": 2.594176, "grad_norm": 1.640625, "learning_rate": 6.7699001791656e-06, "loss": 0.4435, "step": 10135 }, { "epoch": 2.594432, "grad_norm": 1.8515625, "learning_rate": 6.765634331541677e-06, "loss": 0.449, "step": 10136 }, { "epoch": 2.594688, "grad_norm": 1.6875, "learning_rate": 6.761368483917755e-06, "loss": 0.4391, "step": 10137 }, { "epoch": 2.594944, "grad_norm": 1.671875, "learning_rate": 6.757102636293831e-06, "loss": 0.4172, "step": 10138 }, { "epoch": 2.5952, "grad_norm": 1.8203125, "learning_rate": 6.752836788669908e-06, "loss": 0.4243, "step": 10139 }, { "epoch": 2.595456, "grad_norm": 1.71875, "learning_rate": 6.748570941045986e-06, "loss": 0.427, "step": 10140 }, { "epoch": 2.595712, "grad_norm": 1.6640625, "learning_rate": 6.7443050934220635e-06, "loss": 0.423, "step": 10141 }, { "epoch": 2.595968, "grad_norm": 1.796875, "learning_rate": 6.740039245798141e-06, "loss": 0.4449, "step": 10142 }, { "epoch": 2.596224, "grad_norm": 1.7421875, "learning_rate": 6.735773398174218e-06, "loss": 0.4492, "step": 10143 }, { "epoch": 2.59648, "grad_norm": 1.7734375, "learning_rate": 6.731507550550295e-06, "loss": 0.4368, "step": 10144 }, { "epoch": 2.596736, "grad_norm": 1.890625, "learning_rate": 6.7272417029263724e-06, "loss": 0.4521, "step": 10145 }, { "epoch": 2.596992, "grad_norm": 1.6875, "learning_rate": 6.722975855302449e-06, "loss": 0.4139, "step": 10146 }, { "epoch": 2.597248, "grad_norm": 1.75, "learning_rate": 6.718710007678526e-06, "loss": 0.3583, "step": 10147 }, { "epoch": 2.597504, "grad_norm": 1.78125, "learning_rate": 6.714444160054603e-06, "loss": 0.3993, "step": 10148 }, { "epoch": 2.59776, "grad_norm": 1.7109375, "learning_rate": 6.7101783124306805e-06, "loss": 0.4274, "step": 10149 }, { "epoch": 2.598016, "grad_norm": 1.78125, "learning_rate": 6.705912464806757e-06, "loss": 0.4087, "step": 10150 }, { "epoch": 2.598272, "grad_norm": 1.6953125, "learning_rate": 6.701646617182834e-06, "loss": 0.4114, "step": 10151 }, { "epoch": 2.598528, "grad_norm": 1.71875, "learning_rate": 6.697380769558912e-06, "loss": 0.4379, "step": 10152 }, { "epoch": 2.598784, "grad_norm": 1.7578125, "learning_rate": 6.693114921934989e-06, "loss": 0.3833, "step": 10153 }, { "epoch": 2.59904, "grad_norm": 1.7421875, "learning_rate": 6.688849074311065e-06, "loss": 0.4209, "step": 10154 }, { "epoch": 2.599296, "grad_norm": 1.8671875, "learning_rate": 6.684583226687142e-06, "loss": 0.4355, "step": 10155 }, { "epoch": 2.599552, "grad_norm": 1.6328125, "learning_rate": 6.68031737906322e-06, "loss": 0.4379, "step": 10156 }, { "epoch": 2.599808, "grad_norm": 1.8828125, "learning_rate": 6.676051531439298e-06, "loss": 0.4429, "step": 10157 }, { "epoch": 2.600064, "grad_norm": 1.890625, "learning_rate": 6.671785683815375e-06, "loss": 0.4567, "step": 10158 }, { "epoch": 2.60032, "grad_norm": 1.84375, "learning_rate": 6.667519836191452e-06, "loss": 0.4113, "step": 10159 }, { "epoch": 2.600576, "grad_norm": 1.703125, "learning_rate": 6.663253988567529e-06, "loss": 0.4286, "step": 10160 }, { "epoch": 2.600832, "grad_norm": 1.734375, "learning_rate": 6.6589881409436064e-06, "loss": 0.4296, "step": 10161 }, { "epoch": 2.601088, "grad_norm": 1.5859375, "learning_rate": 6.654722293319683e-06, "loss": 0.3845, "step": 10162 }, { "epoch": 2.601344, "grad_norm": 1.7421875, "learning_rate": 6.65045644569576e-06, "loss": 0.4063, "step": 10163 }, { "epoch": 2.6016, "grad_norm": 1.8046875, "learning_rate": 6.646190598071837e-06, "loss": 0.4396, "step": 10164 }, { "epoch": 2.6018559999999997, "grad_norm": 1.7578125, "learning_rate": 6.6419247504479145e-06, "loss": 0.434, "step": 10165 }, { "epoch": 2.602112, "grad_norm": 1.765625, "learning_rate": 6.637658902823991e-06, "loss": 0.4252, "step": 10166 }, { "epoch": 2.6023680000000002, "grad_norm": 1.6171875, "learning_rate": 6.633393055200068e-06, "loss": 0.4378, "step": 10167 }, { "epoch": 2.602624, "grad_norm": 1.65625, "learning_rate": 6.629127207576146e-06, "loss": 0.4254, "step": 10168 }, { "epoch": 2.60288, "grad_norm": 1.78125, "learning_rate": 6.624861359952223e-06, "loss": 0.4147, "step": 10169 }, { "epoch": 2.603136, "grad_norm": 1.7265625, "learning_rate": 6.620595512328299e-06, "loss": 0.42, "step": 10170 }, { "epoch": 2.603392, "grad_norm": 1.8046875, "learning_rate": 6.616329664704376e-06, "loss": 0.4611, "step": 10171 }, { "epoch": 2.6036479999999997, "grad_norm": 1.8203125, "learning_rate": 6.612063817080454e-06, "loss": 0.3888, "step": 10172 }, { "epoch": 2.603904, "grad_norm": 1.7578125, "learning_rate": 6.607797969456532e-06, "loss": 0.4781, "step": 10173 }, { "epoch": 2.6041600000000003, "grad_norm": 1.7265625, "learning_rate": 6.603532121832609e-06, "loss": 0.4242, "step": 10174 }, { "epoch": 2.604416, "grad_norm": 1.796875, "learning_rate": 6.599266274208686e-06, "loss": 0.4203, "step": 10175 }, { "epoch": 2.604672, "grad_norm": 1.734375, "learning_rate": 6.595000426584763e-06, "loss": 0.4287, "step": 10176 }, { "epoch": 2.604928, "grad_norm": 1.7734375, "learning_rate": 6.5907345789608404e-06, "loss": 0.4141, "step": 10177 }, { "epoch": 2.605184, "grad_norm": 1.78125, "learning_rate": 6.586468731336917e-06, "loss": 0.4129, "step": 10178 }, { "epoch": 2.6054399999999998, "grad_norm": 1.7890625, "learning_rate": 6.582202883712994e-06, "loss": 0.4125, "step": 10179 }, { "epoch": 2.605696, "grad_norm": 1.640625, "learning_rate": 6.577937036089072e-06, "loss": 0.4492, "step": 10180 }, { "epoch": 2.6059520000000003, "grad_norm": 1.71875, "learning_rate": 6.5736711884651485e-06, "loss": 0.4127, "step": 10181 }, { "epoch": 2.606208, "grad_norm": 1.765625, "learning_rate": 6.569405340841225e-06, "loss": 0.4053, "step": 10182 }, { "epoch": 2.606464, "grad_norm": 1.65625, "learning_rate": 6.565139493217302e-06, "loss": 0.4291, "step": 10183 }, { "epoch": 2.60672, "grad_norm": 1.703125, "learning_rate": 6.56087364559338e-06, "loss": 0.4192, "step": 10184 }, { "epoch": 2.606976, "grad_norm": 1.7890625, "learning_rate": 6.556607797969457e-06, "loss": 0.4399, "step": 10185 }, { "epoch": 2.6072319999999998, "grad_norm": 1.7734375, "learning_rate": 6.552341950345533e-06, "loss": 0.4108, "step": 10186 }, { "epoch": 2.607488, "grad_norm": 1.890625, "learning_rate": 6.54807610272161e-06, "loss": 0.4063, "step": 10187 }, { "epoch": 2.607744, "grad_norm": 1.75, "learning_rate": 6.543810255097688e-06, "loss": 0.4116, "step": 10188 }, { "epoch": 2.608, "grad_norm": 1.78125, "learning_rate": 6.539544407473765e-06, "loss": 0.43, "step": 10189 }, { "epoch": 2.608256, "grad_norm": 1.7734375, "learning_rate": 6.535278559849843e-06, "loss": 0.3928, "step": 10190 }, { "epoch": 2.608512, "grad_norm": 1.7734375, "learning_rate": 6.53101271222592e-06, "loss": 0.3925, "step": 10191 }, { "epoch": 2.608768, "grad_norm": 1.6875, "learning_rate": 6.526746864601997e-06, "loss": 0.426, "step": 10192 }, { "epoch": 2.609024, "grad_norm": 1.7578125, "learning_rate": 6.5224810169780744e-06, "loss": 0.3909, "step": 10193 }, { "epoch": 2.60928, "grad_norm": 1.8203125, "learning_rate": 6.518215169354151e-06, "loss": 0.403, "step": 10194 }, { "epoch": 2.609536, "grad_norm": 1.8203125, "learning_rate": 6.513949321730228e-06, "loss": 0.4162, "step": 10195 }, { "epoch": 2.609792, "grad_norm": 1.71875, "learning_rate": 6.509683474106306e-06, "loss": 0.4231, "step": 10196 }, { "epoch": 2.610048, "grad_norm": 1.6875, "learning_rate": 6.5054176264823825e-06, "loss": 0.4337, "step": 10197 }, { "epoch": 2.610304, "grad_norm": 1.796875, "learning_rate": 6.501151778858459e-06, "loss": 0.4304, "step": 10198 }, { "epoch": 2.61056, "grad_norm": 1.7734375, "learning_rate": 6.496885931234536e-06, "loss": 0.4724, "step": 10199 }, { "epoch": 2.610816, "grad_norm": 1.8125, "learning_rate": 6.492620083610614e-06, "loss": 0.3895, "step": 10200 }, { "epoch": 2.611072, "grad_norm": 1.8046875, "learning_rate": 6.488354235986691e-06, "loss": 0.4287, "step": 10201 }, { "epoch": 2.611328, "grad_norm": 1.671875, "learning_rate": 6.484088388362767e-06, "loss": 0.4577, "step": 10202 }, { "epoch": 2.611584, "grad_norm": 1.75, "learning_rate": 6.479822540738845e-06, "loss": 0.3976, "step": 10203 }, { "epoch": 2.61184, "grad_norm": 1.6328125, "learning_rate": 6.475556693114922e-06, "loss": 0.446, "step": 10204 }, { "epoch": 2.612096, "grad_norm": 1.6875, "learning_rate": 6.471290845490999e-06, "loss": 0.4258, "step": 10205 }, { "epoch": 2.612352, "grad_norm": 1.7265625, "learning_rate": 6.467024997867077e-06, "loss": 0.4196, "step": 10206 }, { "epoch": 2.612608, "grad_norm": 1.7890625, "learning_rate": 6.462759150243154e-06, "loss": 0.4747, "step": 10207 }, { "epoch": 2.612864, "grad_norm": 1.90625, "learning_rate": 6.458493302619232e-06, "loss": 0.4206, "step": 10208 }, { "epoch": 2.61312, "grad_norm": 1.765625, "learning_rate": 6.4542274549953084e-06, "loss": 0.4141, "step": 10209 }, { "epoch": 2.613376, "grad_norm": 1.703125, "learning_rate": 6.449961607371385e-06, "loss": 0.431, "step": 10210 }, { "epoch": 2.613632, "grad_norm": 1.8203125, "learning_rate": 6.445695759747462e-06, "loss": 0.4779, "step": 10211 }, { "epoch": 2.613888, "grad_norm": 1.8046875, "learning_rate": 6.44142991212354e-06, "loss": 0.4358, "step": 10212 }, { "epoch": 2.614144, "grad_norm": 1.6484375, "learning_rate": 6.4371640644996165e-06, "loss": 0.4404, "step": 10213 }, { "epoch": 2.6144, "grad_norm": 1.7890625, "learning_rate": 6.432898216875693e-06, "loss": 0.403, "step": 10214 }, { "epoch": 2.614656, "grad_norm": 1.7265625, "learning_rate": 6.42863236925177e-06, "loss": 0.4419, "step": 10215 }, { "epoch": 2.614912, "grad_norm": 1.671875, "learning_rate": 6.424366521627848e-06, "loss": 0.3823, "step": 10216 }, { "epoch": 2.615168, "grad_norm": 1.765625, "learning_rate": 6.420100674003925e-06, "loss": 0.3824, "step": 10217 }, { "epoch": 2.615424, "grad_norm": 1.7109375, "learning_rate": 6.415834826380001e-06, "loss": 0.4205, "step": 10218 }, { "epoch": 2.6156800000000002, "grad_norm": 1.703125, "learning_rate": 6.411568978756079e-06, "loss": 0.4205, "step": 10219 }, { "epoch": 2.615936, "grad_norm": 1.828125, "learning_rate": 6.407303131132156e-06, "loss": 0.4056, "step": 10220 }, { "epoch": 2.616192, "grad_norm": 1.7109375, "learning_rate": 6.403037283508233e-06, "loss": 0.4298, "step": 10221 }, { "epoch": 2.616448, "grad_norm": 1.703125, "learning_rate": 6.3987714358843095e-06, "loss": 0.4625, "step": 10222 }, { "epoch": 2.616704, "grad_norm": 1.59375, "learning_rate": 6.394505588260388e-06, "loss": 0.4462, "step": 10223 }, { "epoch": 2.6169599999999997, "grad_norm": 1.75, "learning_rate": 6.390239740636466e-06, "loss": 0.4356, "step": 10224 }, { "epoch": 2.617216, "grad_norm": 1.640625, "learning_rate": 6.3859738930125424e-06, "loss": 0.4416, "step": 10225 }, { "epoch": 2.6174720000000002, "grad_norm": 1.671875, "learning_rate": 6.381708045388619e-06, "loss": 0.4047, "step": 10226 }, { "epoch": 2.617728, "grad_norm": 1.703125, "learning_rate": 6.377442197764696e-06, "loss": 0.4327, "step": 10227 }, { "epoch": 2.617984, "grad_norm": 1.71875, "learning_rate": 6.373176350140774e-06, "loss": 0.39, "step": 10228 }, { "epoch": 2.61824, "grad_norm": 1.703125, "learning_rate": 6.3689105025168505e-06, "loss": 0.4252, "step": 10229 }, { "epoch": 2.618496, "grad_norm": 1.6953125, "learning_rate": 6.364644654892927e-06, "loss": 0.4317, "step": 10230 }, { "epoch": 2.6187519999999997, "grad_norm": 1.875, "learning_rate": 6.360378807269005e-06, "loss": 0.3957, "step": 10231 }, { "epoch": 2.619008, "grad_norm": 1.7109375, "learning_rate": 6.356112959645082e-06, "loss": 0.3887, "step": 10232 }, { "epoch": 2.6192640000000003, "grad_norm": 1.734375, "learning_rate": 6.351847112021159e-06, "loss": 0.4429, "step": 10233 }, { "epoch": 2.61952, "grad_norm": 1.7578125, "learning_rate": 6.347581264397235e-06, "loss": 0.4366, "step": 10234 }, { "epoch": 2.619776, "grad_norm": 1.7109375, "learning_rate": 6.343315416773313e-06, "loss": 0.4077, "step": 10235 }, { "epoch": 2.620032, "grad_norm": 1.6640625, "learning_rate": 6.33904956914939e-06, "loss": 0.4065, "step": 10236 }, { "epoch": 2.620288, "grad_norm": 1.78125, "learning_rate": 6.334783721525467e-06, "loss": 0.4088, "step": 10237 }, { "epoch": 2.6205439999999998, "grad_norm": 1.703125, "learning_rate": 6.3305178739015435e-06, "loss": 0.4277, "step": 10238 }, { "epoch": 2.6208, "grad_norm": 1.859375, "learning_rate": 6.326252026277622e-06, "loss": 0.4317, "step": 10239 }, { "epoch": 2.6210560000000003, "grad_norm": 1.640625, "learning_rate": 6.3219861786537e-06, "loss": 0.3812, "step": 10240 }, { "epoch": 2.621312, "grad_norm": 1.8046875, "learning_rate": 6.3177203310297764e-06, "loss": 0.4425, "step": 10241 }, { "epoch": 2.621568, "grad_norm": 1.9140625, "learning_rate": 6.313454483405853e-06, "loss": 0.4192, "step": 10242 }, { "epoch": 2.621824, "grad_norm": 1.90625, "learning_rate": 6.309188635781931e-06, "loss": 0.4037, "step": 10243 }, { "epoch": 2.62208, "grad_norm": 1.7578125, "learning_rate": 6.304922788158008e-06, "loss": 0.4105, "step": 10244 }, { "epoch": 2.622336, "grad_norm": 1.78125, "learning_rate": 6.3006569405340845e-06, "loss": 0.4183, "step": 10245 }, { "epoch": 2.622592, "grad_norm": 1.828125, "learning_rate": 6.296391092910161e-06, "loss": 0.4145, "step": 10246 }, { "epoch": 2.622848, "grad_norm": 1.765625, "learning_rate": 6.292125245286239e-06, "loss": 0.398, "step": 10247 }, { "epoch": 2.623104, "grad_norm": 1.6640625, "learning_rate": 6.287859397662316e-06, "loss": 0.4404, "step": 10248 }, { "epoch": 2.62336, "grad_norm": 1.6875, "learning_rate": 6.283593550038393e-06, "loss": 0.4237, "step": 10249 }, { "epoch": 2.623616, "grad_norm": 1.8203125, "learning_rate": 6.279327702414469e-06, "loss": 0.465, "step": 10250 }, { "epoch": 2.623872, "grad_norm": 1.7421875, "learning_rate": 6.275061854790547e-06, "loss": 0.4167, "step": 10251 }, { "epoch": 2.624128, "grad_norm": 1.59375, "learning_rate": 6.270796007166624e-06, "loss": 0.4138, "step": 10252 }, { "epoch": 2.624384, "grad_norm": 1.7578125, "learning_rate": 6.266530159542701e-06, "loss": 0.4092, "step": 10253 }, { "epoch": 2.62464, "grad_norm": 1.6953125, "learning_rate": 6.262264311918778e-06, "loss": 0.4112, "step": 10254 }, { "epoch": 2.624896, "grad_norm": 1.734375, "learning_rate": 6.257998464294856e-06, "loss": 0.3914, "step": 10255 }, { "epoch": 2.625152, "grad_norm": 1.8203125, "learning_rate": 6.253732616670934e-06, "loss": 0.4306, "step": 10256 }, { "epoch": 2.625408, "grad_norm": 1.765625, "learning_rate": 6.24946676904701e-06, "loss": 0.4091, "step": 10257 }, { "epoch": 2.625664, "grad_norm": 1.734375, "learning_rate": 6.245200921423086e-06, "loss": 0.4364, "step": 10258 }, { "epoch": 2.62592, "grad_norm": 1.7421875, "learning_rate": 6.240935073799165e-06, "loss": 0.4236, "step": 10259 }, { "epoch": 2.626176, "grad_norm": 1.7734375, "learning_rate": 6.236669226175242e-06, "loss": 0.4033, "step": 10260 }, { "epoch": 2.626432, "grad_norm": 1.6953125, "learning_rate": 6.2324033785513185e-06, "loss": 0.4113, "step": 10261 }, { "epoch": 2.626688, "grad_norm": 1.7109375, "learning_rate": 6.228137530927395e-06, "loss": 0.4069, "step": 10262 }, { "epoch": 2.626944, "grad_norm": 1.78125, "learning_rate": 6.223871683303473e-06, "loss": 0.4215, "step": 10263 }, { "epoch": 2.6272, "grad_norm": 1.6171875, "learning_rate": 6.21960583567955e-06, "loss": 0.4515, "step": 10264 }, { "epoch": 2.627456, "grad_norm": 1.765625, "learning_rate": 6.215339988055627e-06, "loss": 0.3785, "step": 10265 }, { "epoch": 2.627712, "grad_norm": 1.734375, "learning_rate": 6.211074140431704e-06, "loss": 0.4253, "step": 10266 }, { "epoch": 2.627968, "grad_norm": 1.75, "learning_rate": 6.206808292807781e-06, "loss": 0.452, "step": 10267 }, { "epoch": 2.628224, "grad_norm": 1.859375, "learning_rate": 6.202542445183859e-06, "loss": 0.4323, "step": 10268 }, { "epoch": 2.62848, "grad_norm": 1.8984375, "learning_rate": 6.1982765975599355e-06, "loss": 0.3907, "step": 10269 }, { "epoch": 2.628736, "grad_norm": 1.75, "learning_rate": 6.194010749936012e-06, "loss": 0.4315, "step": 10270 }, { "epoch": 2.628992, "grad_norm": 1.7109375, "learning_rate": 6.18974490231209e-06, "loss": 0.4386, "step": 10271 }, { "epoch": 2.629248, "grad_norm": 1.75, "learning_rate": 6.185479054688167e-06, "loss": 0.3788, "step": 10272 }, { "epoch": 2.629504, "grad_norm": 1.78125, "learning_rate": 6.181213207064244e-06, "loss": 0.4521, "step": 10273 }, { "epoch": 2.62976, "grad_norm": 1.703125, "learning_rate": 6.176947359440321e-06, "loss": 0.4143, "step": 10274 }, { "epoch": 2.630016, "grad_norm": 1.6953125, "learning_rate": 6.172681511816398e-06, "loss": 0.438, "step": 10275 }, { "epoch": 2.630272, "grad_norm": 1.640625, "learning_rate": 6.168415664192476e-06, "loss": 0.4328, "step": 10276 }, { "epoch": 2.630528, "grad_norm": 1.7578125, "learning_rate": 6.1641498165685525e-06, "loss": 0.4338, "step": 10277 }, { "epoch": 2.6307840000000002, "grad_norm": 1.6484375, "learning_rate": 6.159883968944629e-06, "loss": 0.4059, "step": 10278 }, { "epoch": 2.63104, "grad_norm": 1.6953125, "learning_rate": 6.155618121320707e-06, "loss": 0.4083, "step": 10279 }, { "epoch": 2.631296, "grad_norm": 1.703125, "learning_rate": 6.151352273696784e-06, "loss": 0.424, "step": 10280 }, { "epoch": 2.631552, "grad_norm": 1.71875, "learning_rate": 6.147086426072861e-06, "loss": 0.4241, "step": 10281 }, { "epoch": 2.631808, "grad_norm": 1.8046875, "learning_rate": 6.142820578448938e-06, "loss": 0.4365, "step": 10282 }, { "epoch": 2.6320639999999997, "grad_norm": 1.7421875, "learning_rate": 6.138554730825015e-06, "loss": 0.4364, "step": 10283 }, { "epoch": 2.63232, "grad_norm": 1.640625, "learning_rate": 6.134288883201093e-06, "loss": 0.4163, "step": 10284 }, { "epoch": 2.6325760000000002, "grad_norm": 1.7421875, "learning_rate": 6.1300230355771695e-06, "loss": 0.4474, "step": 10285 }, { "epoch": 2.632832, "grad_norm": 1.765625, "learning_rate": 6.125757187953247e-06, "loss": 0.4535, "step": 10286 }, { "epoch": 2.633088, "grad_norm": 1.671875, "learning_rate": 6.121491340329324e-06, "loss": 0.4273, "step": 10287 }, { "epoch": 2.633344, "grad_norm": 1.7890625, "learning_rate": 6.117225492705401e-06, "loss": 0.4012, "step": 10288 }, { "epoch": 2.6336, "grad_norm": 1.6796875, "learning_rate": 6.112959645081478e-06, "loss": 0.4374, "step": 10289 }, { "epoch": 2.6338559999999998, "grad_norm": 1.6875, "learning_rate": 6.108693797457555e-06, "loss": 0.4116, "step": 10290 }, { "epoch": 2.634112, "grad_norm": 1.7890625, "learning_rate": 6.104427949833632e-06, "loss": 0.4325, "step": 10291 }, { "epoch": 2.6343680000000003, "grad_norm": 1.796875, "learning_rate": 6.10016210220971e-06, "loss": 0.4202, "step": 10292 }, { "epoch": 2.634624, "grad_norm": 1.765625, "learning_rate": 6.0958962545857865e-06, "loss": 0.4292, "step": 10293 }, { "epoch": 2.63488, "grad_norm": 1.7421875, "learning_rate": 6.091630406961864e-06, "loss": 0.4199, "step": 10294 }, { "epoch": 2.635136, "grad_norm": 1.6484375, "learning_rate": 6.087364559337941e-06, "loss": 0.4368, "step": 10295 }, { "epoch": 2.635392, "grad_norm": 1.7421875, "learning_rate": 6.083098711714018e-06, "loss": 0.436, "step": 10296 }, { "epoch": 2.6356479999999998, "grad_norm": 1.8125, "learning_rate": 6.078832864090095e-06, "loss": 0.3887, "step": 10297 }, { "epoch": 2.635904, "grad_norm": 1.7578125, "learning_rate": 6.074567016466172e-06, "loss": 0.433, "step": 10298 }, { "epoch": 2.63616, "grad_norm": 1.78125, "learning_rate": 6.070301168842249e-06, "loss": 0.4156, "step": 10299 }, { "epoch": 2.636416, "grad_norm": 1.734375, "learning_rate": 6.066035321218327e-06, "loss": 0.4587, "step": 10300 }, { "epoch": 2.636672, "grad_norm": 1.65625, "learning_rate": 6.0617694735944035e-06, "loss": 0.4447, "step": 10301 }, { "epoch": 2.636928, "grad_norm": 1.75, "learning_rate": 6.057503625970481e-06, "loss": 0.4029, "step": 10302 }, { "epoch": 2.637184, "grad_norm": 1.78125, "learning_rate": 6.053237778346558e-06, "loss": 0.3975, "step": 10303 }, { "epoch": 2.63744, "grad_norm": 1.65625, "learning_rate": 6.048971930722635e-06, "loss": 0.4198, "step": 10304 }, { "epoch": 2.637696, "grad_norm": 1.7578125, "learning_rate": 6.044706083098712e-06, "loss": 0.4145, "step": 10305 }, { "epoch": 2.637952, "grad_norm": 1.7265625, "learning_rate": 6.040440235474789e-06, "loss": 0.43, "step": 10306 }, { "epoch": 2.638208, "grad_norm": 1.734375, "learning_rate": 6.036174387850866e-06, "loss": 0.428, "step": 10307 }, { "epoch": 2.638464, "grad_norm": 1.6640625, "learning_rate": 6.031908540226943e-06, "loss": 0.4117, "step": 10308 }, { "epoch": 2.63872, "grad_norm": 1.78125, "learning_rate": 6.0276426926030205e-06, "loss": 0.433, "step": 10309 }, { "epoch": 2.638976, "grad_norm": 1.703125, "learning_rate": 6.023376844979098e-06, "loss": 0.4091, "step": 10310 }, { "epoch": 2.639232, "grad_norm": 1.8046875, "learning_rate": 6.019110997355175e-06, "loss": 0.4147, "step": 10311 }, { "epoch": 2.639488, "grad_norm": 1.703125, "learning_rate": 6.014845149731252e-06, "loss": 0.4282, "step": 10312 }, { "epoch": 2.639744, "grad_norm": 1.6328125, "learning_rate": 6.010579302107329e-06, "loss": 0.4249, "step": 10313 }, { "epoch": 2.64, "grad_norm": 1.8359375, "learning_rate": 6.006313454483406e-06, "loss": 0.4118, "step": 10314 }, { "epoch": 2.640256, "grad_norm": 1.6875, "learning_rate": 6.002047606859483e-06, "loss": 0.4287, "step": 10315 }, { "epoch": 2.640512, "grad_norm": 1.703125, "learning_rate": 5.99778175923556e-06, "loss": 0.4225, "step": 10316 }, { "epoch": 2.640768, "grad_norm": 1.765625, "learning_rate": 5.9935159116116375e-06, "loss": 0.3912, "step": 10317 }, { "epoch": 2.641024, "grad_norm": 1.6328125, "learning_rate": 5.989250063987715e-06, "loss": 0.4685, "step": 10318 }, { "epoch": 2.64128, "grad_norm": 1.640625, "learning_rate": 5.984984216363792e-06, "loss": 0.4663, "step": 10319 }, { "epoch": 2.641536, "grad_norm": 1.6171875, "learning_rate": 5.980718368739869e-06, "loss": 0.4631, "step": 10320 }, { "epoch": 2.641792, "grad_norm": 1.796875, "learning_rate": 5.976452521115946e-06, "loss": 0.4147, "step": 10321 }, { "epoch": 2.642048, "grad_norm": 1.6953125, "learning_rate": 5.972186673492023e-06, "loss": 0.3961, "step": 10322 }, { "epoch": 2.642304, "grad_norm": 1.6875, "learning_rate": 5.9679208258681e-06, "loss": 0.4434, "step": 10323 }, { "epoch": 2.64256, "grad_norm": 1.7421875, "learning_rate": 5.963654978244177e-06, "loss": 0.4312, "step": 10324 }, { "epoch": 2.642816, "grad_norm": 1.6015625, "learning_rate": 5.9593891306202545e-06, "loss": 0.454, "step": 10325 }, { "epoch": 2.643072, "grad_norm": 1.7109375, "learning_rate": 5.955123282996332e-06, "loss": 0.4521, "step": 10326 }, { "epoch": 2.643328, "grad_norm": 1.8203125, "learning_rate": 5.950857435372409e-06, "loss": 0.4223, "step": 10327 }, { "epoch": 2.643584, "grad_norm": 1.859375, "learning_rate": 5.946591587748486e-06, "loss": 0.3868, "step": 10328 }, { "epoch": 2.64384, "grad_norm": 1.8359375, "learning_rate": 5.942325740124563e-06, "loss": 0.4025, "step": 10329 }, { "epoch": 2.6440960000000002, "grad_norm": 1.6953125, "learning_rate": 5.93805989250064e-06, "loss": 0.4579, "step": 10330 }, { "epoch": 2.644352, "grad_norm": 1.625, "learning_rate": 5.933794044876717e-06, "loss": 0.4174, "step": 10331 }, { "epoch": 2.644608, "grad_norm": 1.9453125, "learning_rate": 5.929528197252794e-06, "loss": 0.4128, "step": 10332 }, { "epoch": 2.644864, "grad_norm": 1.796875, "learning_rate": 5.9252623496288715e-06, "loss": 0.4121, "step": 10333 }, { "epoch": 2.64512, "grad_norm": 1.71875, "learning_rate": 5.920996502004949e-06, "loss": 0.4097, "step": 10334 }, { "epoch": 2.6453759999999997, "grad_norm": 1.6640625, "learning_rate": 5.916730654381026e-06, "loss": 0.413, "step": 10335 }, { "epoch": 2.645632, "grad_norm": 1.8671875, "learning_rate": 5.912464806757103e-06, "loss": 0.4387, "step": 10336 }, { "epoch": 2.6458880000000002, "grad_norm": 1.8046875, "learning_rate": 5.9081989591331804e-06, "loss": 0.4212, "step": 10337 }, { "epoch": 2.646144, "grad_norm": 1.75, "learning_rate": 5.903933111509257e-06, "loss": 0.457, "step": 10338 }, { "epoch": 2.6464, "grad_norm": 1.71875, "learning_rate": 5.899667263885334e-06, "loss": 0.3999, "step": 10339 }, { "epoch": 2.646656, "grad_norm": 1.6953125, "learning_rate": 5.895401416261411e-06, "loss": 0.4127, "step": 10340 }, { "epoch": 2.646912, "grad_norm": 1.7421875, "learning_rate": 5.8911355686374885e-06, "loss": 0.4374, "step": 10341 }, { "epoch": 2.6471679999999997, "grad_norm": 1.7421875, "learning_rate": 5.886869721013566e-06, "loss": 0.4596, "step": 10342 }, { "epoch": 2.647424, "grad_norm": 1.8359375, "learning_rate": 5.882603873389643e-06, "loss": 0.4117, "step": 10343 }, { "epoch": 2.6476800000000003, "grad_norm": 1.8515625, "learning_rate": 5.87833802576572e-06, "loss": 0.4251, "step": 10344 }, { "epoch": 2.647936, "grad_norm": 1.6484375, "learning_rate": 5.8740721781417974e-06, "loss": 0.447, "step": 10345 }, { "epoch": 2.648192, "grad_norm": 1.7890625, "learning_rate": 5.869806330517874e-06, "loss": 0.428, "step": 10346 }, { "epoch": 2.648448, "grad_norm": 1.71875, "learning_rate": 5.865540482893951e-06, "loss": 0.4427, "step": 10347 }, { "epoch": 2.648704, "grad_norm": 1.703125, "learning_rate": 5.861274635270028e-06, "loss": 0.4274, "step": 10348 }, { "epoch": 2.6489599999999998, "grad_norm": 1.828125, "learning_rate": 5.8570087876461055e-06, "loss": 0.416, "step": 10349 }, { "epoch": 2.649216, "grad_norm": 1.84375, "learning_rate": 5.852742940022183e-06, "loss": 0.4293, "step": 10350 }, { "epoch": 2.6494720000000003, "grad_norm": 1.703125, "learning_rate": 5.84847709239826e-06, "loss": 0.4375, "step": 10351 }, { "epoch": 2.649728, "grad_norm": 1.7421875, "learning_rate": 5.844211244774337e-06, "loss": 0.4297, "step": 10352 }, { "epoch": 2.649984, "grad_norm": 1.734375, "learning_rate": 5.8399453971504144e-06, "loss": 0.4216, "step": 10353 }, { "epoch": 2.65024, "grad_norm": 1.609375, "learning_rate": 5.835679549526491e-06, "loss": 0.406, "step": 10354 }, { "epoch": 2.650496, "grad_norm": 1.65625, "learning_rate": 5.831413701902568e-06, "loss": 0.4137, "step": 10355 }, { "epoch": 2.6507519999999998, "grad_norm": 1.78125, "learning_rate": 5.827147854278645e-06, "loss": 0.4294, "step": 10356 }, { "epoch": 2.651008, "grad_norm": 1.84375, "learning_rate": 5.8228820066547225e-06, "loss": 0.4396, "step": 10357 }, { "epoch": 2.651264, "grad_norm": 1.765625, "learning_rate": 5.8186161590308e-06, "loss": 0.43, "step": 10358 }, { "epoch": 2.65152, "grad_norm": 1.703125, "learning_rate": 5.814350311406877e-06, "loss": 0.4571, "step": 10359 }, { "epoch": 2.651776, "grad_norm": 1.78125, "learning_rate": 5.810084463782954e-06, "loss": 0.4231, "step": 10360 }, { "epoch": 2.652032, "grad_norm": 1.7578125, "learning_rate": 5.8058186161590314e-06, "loss": 0.367, "step": 10361 }, { "epoch": 2.652288, "grad_norm": 1.84375, "learning_rate": 5.801552768535108e-06, "loss": 0.4185, "step": 10362 }, { "epoch": 2.652544, "grad_norm": 1.7578125, "learning_rate": 5.797286920911185e-06, "loss": 0.3979, "step": 10363 }, { "epoch": 2.6528, "grad_norm": 1.703125, "learning_rate": 5.793021073287262e-06, "loss": 0.4242, "step": 10364 }, { "epoch": 2.653056, "grad_norm": 1.734375, "learning_rate": 5.7887552256633395e-06, "loss": 0.4177, "step": 10365 }, { "epoch": 2.653312, "grad_norm": 1.734375, "learning_rate": 5.784489378039417e-06, "loss": 0.4312, "step": 10366 }, { "epoch": 2.653568, "grad_norm": 1.7109375, "learning_rate": 5.780223530415494e-06, "loss": 0.446, "step": 10367 }, { "epoch": 2.653824, "grad_norm": 1.890625, "learning_rate": 5.775957682791571e-06, "loss": 0.4066, "step": 10368 }, { "epoch": 2.65408, "grad_norm": 1.796875, "learning_rate": 5.7716918351676484e-06, "loss": 0.4331, "step": 10369 }, { "epoch": 2.654336, "grad_norm": 1.953125, "learning_rate": 5.767425987543725e-06, "loss": 0.3935, "step": 10370 }, { "epoch": 2.654592, "grad_norm": 1.8046875, "learning_rate": 5.763160139919802e-06, "loss": 0.416, "step": 10371 }, { "epoch": 2.654848, "grad_norm": 1.75, "learning_rate": 5.758894292295879e-06, "loss": 0.41, "step": 10372 }, { "epoch": 2.655104, "grad_norm": 1.6796875, "learning_rate": 5.7546284446719565e-06, "loss": 0.416, "step": 10373 }, { "epoch": 2.65536, "grad_norm": 1.734375, "learning_rate": 5.750362597048034e-06, "loss": 0.4376, "step": 10374 }, { "epoch": 2.655616, "grad_norm": 1.7109375, "learning_rate": 5.746096749424111e-06, "loss": 0.4345, "step": 10375 }, { "epoch": 2.655872, "grad_norm": 1.625, "learning_rate": 5.741830901800188e-06, "loss": 0.4212, "step": 10376 }, { "epoch": 2.656128, "grad_norm": 1.90625, "learning_rate": 5.7375650541762654e-06, "loss": 0.4181, "step": 10377 }, { "epoch": 2.656384, "grad_norm": 1.734375, "learning_rate": 5.733299206552342e-06, "loss": 0.3901, "step": 10378 }, { "epoch": 2.65664, "grad_norm": 1.625, "learning_rate": 5.729033358928419e-06, "loss": 0.4199, "step": 10379 }, { "epoch": 2.656896, "grad_norm": 1.7578125, "learning_rate": 5.724767511304497e-06, "loss": 0.4294, "step": 10380 }, { "epoch": 2.657152, "grad_norm": 1.6796875, "learning_rate": 5.7205016636805735e-06, "loss": 0.4753, "step": 10381 }, { "epoch": 2.657408, "grad_norm": 1.7421875, "learning_rate": 5.716235816056651e-06, "loss": 0.4408, "step": 10382 }, { "epoch": 2.657664, "grad_norm": 1.6640625, "learning_rate": 5.711969968432728e-06, "loss": 0.4358, "step": 10383 }, { "epoch": 2.65792, "grad_norm": 1.765625, "learning_rate": 5.707704120808805e-06, "loss": 0.415, "step": 10384 }, { "epoch": 2.658176, "grad_norm": 1.6875, "learning_rate": 5.7034382731848824e-06, "loss": 0.4181, "step": 10385 }, { "epoch": 2.658432, "grad_norm": 1.75, "learning_rate": 5.699172425560959e-06, "loss": 0.4028, "step": 10386 }, { "epoch": 2.658688, "grad_norm": 1.71875, "learning_rate": 5.694906577937036e-06, "loss": 0.4099, "step": 10387 }, { "epoch": 2.658944, "grad_norm": 1.8046875, "learning_rate": 5.690640730313114e-06, "loss": 0.3976, "step": 10388 }, { "epoch": 2.6592000000000002, "grad_norm": 1.6015625, "learning_rate": 5.6863748826891905e-06, "loss": 0.384, "step": 10389 }, { "epoch": 2.659456, "grad_norm": 1.796875, "learning_rate": 5.682109035065267e-06, "loss": 0.4524, "step": 10390 }, { "epoch": 2.659712, "grad_norm": 1.625, "learning_rate": 5.677843187441345e-06, "loss": 0.4305, "step": 10391 }, { "epoch": 2.659968, "grad_norm": 1.6953125, "learning_rate": 5.673577339817422e-06, "loss": 0.4358, "step": 10392 }, { "epoch": 2.660224, "grad_norm": 1.71875, "learning_rate": 5.6693114921934994e-06, "loss": 0.425, "step": 10393 }, { "epoch": 2.6604799999999997, "grad_norm": 1.9140625, "learning_rate": 5.665045644569576e-06, "loss": 0.4256, "step": 10394 }, { "epoch": 2.660736, "grad_norm": 1.8046875, "learning_rate": 5.660779796945653e-06, "loss": 0.4152, "step": 10395 }, { "epoch": 2.6609920000000002, "grad_norm": 1.7265625, "learning_rate": 5.656513949321731e-06, "loss": 0.4332, "step": 10396 }, { "epoch": 2.661248, "grad_norm": 1.859375, "learning_rate": 5.6522481016978075e-06, "loss": 0.409, "step": 10397 }, { "epoch": 2.661504, "grad_norm": 1.8046875, "learning_rate": 5.647982254073884e-06, "loss": 0.4356, "step": 10398 }, { "epoch": 2.66176, "grad_norm": 1.7421875, "learning_rate": 5.643716406449962e-06, "loss": 0.4104, "step": 10399 }, { "epoch": 2.662016, "grad_norm": 1.734375, "learning_rate": 5.639450558826039e-06, "loss": 0.4116, "step": 10400 }, { "epoch": 2.6622719999999997, "grad_norm": 1.7421875, "learning_rate": 5.6351847112021164e-06, "loss": 0.391, "step": 10401 }, { "epoch": 2.662528, "grad_norm": 1.75, "learning_rate": 5.630918863578193e-06, "loss": 0.4628, "step": 10402 }, { "epoch": 2.6627840000000003, "grad_norm": 1.6875, "learning_rate": 5.62665301595427e-06, "loss": 0.4238, "step": 10403 }, { "epoch": 2.66304, "grad_norm": 1.609375, "learning_rate": 5.622387168330348e-06, "loss": 0.4719, "step": 10404 }, { "epoch": 2.663296, "grad_norm": 1.734375, "learning_rate": 5.6181213207064245e-06, "loss": 0.4215, "step": 10405 }, { "epoch": 2.663552, "grad_norm": 1.765625, "learning_rate": 5.613855473082501e-06, "loss": 0.4119, "step": 10406 }, { "epoch": 2.663808, "grad_norm": 1.8203125, "learning_rate": 5.609589625458579e-06, "loss": 0.3979, "step": 10407 }, { "epoch": 2.6640639999999998, "grad_norm": 1.734375, "learning_rate": 5.605323777834657e-06, "loss": 0.4382, "step": 10408 }, { "epoch": 2.66432, "grad_norm": 1.734375, "learning_rate": 5.6010579302107334e-06, "loss": 0.3698, "step": 10409 }, { "epoch": 2.664576, "grad_norm": 1.8515625, "learning_rate": 5.59679208258681e-06, "loss": 0.4256, "step": 10410 }, { "epoch": 2.664832, "grad_norm": 1.6953125, "learning_rate": 5.592526234962887e-06, "loss": 0.4023, "step": 10411 }, { "epoch": 2.665088, "grad_norm": 1.7578125, "learning_rate": 5.588260387338965e-06, "loss": 0.434, "step": 10412 }, { "epoch": 2.665344, "grad_norm": 1.734375, "learning_rate": 5.5839945397150415e-06, "loss": 0.4653, "step": 10413 }, { "epoch": 2.6656, "grad_norm": 1.7109375, "learning_rate": 5.579728692091118e-06, "loss": 0.3902, "step": 10414 }, { "epoch": 2.665856, "grad_norm": 1.84375, "learning_rate": 5.575462844467196e-06, "loss": 0.4219, "step": 10415 }, { "epoch": 2.666112, "grad_norm": 1.7265625, "learning_rate": 5.571196996843274e-06, "loss": 0.4382, "step": 10416 }, { "epoch": 2.666368, "grad_norm": 1.6796875, "learning_rate": 5.5669311492193504e-06, "loss": 0.4311, "step": 10417 }, { "epoch": 2.666624, "grad_norm": 1.6875, "learning_rate": 5.562665301595427e-06, "loss": 0.3781, "step": 10418 }, { "epoch": 2.66688, "grad_norm": 1.5859375, "learning_rate": 5.558399453971504e-06, "loss": 0.4376, "step": 10419 }, { "epoch": 2.667136, "grad_norm": 1.65625, "learning_rate": 5.554133606347582e-06, "loss": 0.399, "step": 10420 }, { "epoch": 2.667392, "grad_norm": 1.796875, "learning_rate": 5.5498677587236585e-06, "loss": 0.3966, "step": 10421 }, { "epoch": 2.667648, "grad_norm": 1.78125, "learning_rate": 5.545601911099735e-06, "loss": 0.4163, "step": 10422 }, { "epoch": 2.667904, "grad_norm": 1.7578125, "learning_rate": 5.541336063475813e-06, "loss": 0.4015, "step": 10423 }, { "epoch": 2.66816, "grad_norm": 1.828125, "learning_rate": 5.537070215851891e-06, "loss": 0.431, "step": 10424 }, { "epoch": 2.668416, "grad_norm": 1.796875, "learning_rate": 5.5328043682279674e-06, "loss": 0.4434, "step": 10425 }, { "epoch": 2.668672, "grad_norm": 1.7109375, "learning_rate": 5.528538520604044e-06, "loss": 0.4491, "step": 10426 }, { "epoch": 2.668928, "grad_norm": 1.890625, "learning_rate": 5.524272672980121e-06, "loss": 0.4196, "step": 10427 }, { "epoch": 2.669184, "grad_norm": 1.6484375, "learning_rate": 5.520006825356199e-06, "loss": 0.4284, "step": 10428 }, { "epoch": 2.66944, "grad_norm": 1.84375, "learning_rate": 5.5157409777322755e-06, "loss": 0.4676, "step": 10429 }, { "epoch": 2.669696, "grad_norm": 1.71875, "learning_rate": 5.511475130108352e-06, "loss": 0.4466, "step": 10430 }, { "epoch": 2.669952, "grad_norm": 1.84375, "learning_rate": 5.50720928248443e-06, "loss": 0.4233, "step": 10431 }, { "epoch": 2.670208, "grad_norm": 1.8203125, "learning_rate": 5.502943434860508e-06, "loss": 0.3999, "step": 10432 }, { "epoch": 2.670464, "grad_norm": 1.8359375, "learning_rate": 5.4986775872365844e-06, "loss": 0.4347, "step": 10433 }, { "epoch": 2.67072, "grad_norm": 1.796875, "learning_rate": 5.494411739612661e-06, "loss": 0.4243, "step": 10434 }, { "epoch": 2.670976, "grad_norm": 1.6953125, "learning_rate": 5.490145891988738e-06, "loss": 0.3653, "step": 10435 }, { "epoch": 2.671232, "grad_norm": 1.734375, "learning_rate": 5.485880044364816e-06, "loss": 0.4389, "step": 10436 }, { "epoch": 2.671488, "grad_norm": 1.78125, "learning_rate": 5.4816141967408925e-06, "loss": 0.3729, "step": 10437 }, { "epoch": 2.671744, "grad_norm": 1.7109375, "learning_rate": 5.477348349116969e-06, "loss": 0.39, "step": 10438 }, { "epoch": 2.672, "grad_norm": 1.78125, "learning_rate": 5.473082501493047e-06, "loss": 0.4145, "step": 10439 }, { "epoch": 2.672256, "grad_norm": 1.6640625, "learning_rate": 5.468816653869125e-06, "loss": 0.423, "step": 10440 }, { "epoch": 2.672512, "grad_norm": 1.7578125, "learning_rate": 5.4645508062452014e-06, "loss": 0.4428, "step": 10441 }, { "epoch": 2.672768, "grad_norm": 1.6640625, "learning_rate": 5.460284958621278e-06, "loss": 0.3966, "step": 10442 }, { "epoch": 2.673024, "grad_norm": 1.625, "learning_rate": 5.456019110997355e-06, "loss": 0.4191, "step": 10443 }, { "epoch": 2.67328, "grad_norm": 1.6640625, "learning_rate": 5.451753263373433e-06, "loss": 0.4687, "step": 10444 }, { "epoch": 2.673536, "grad_norm": 1.75, "learning_rate": 5.4474874157495095e-06, "loss": 0.4174, "step": 10445 }, { "epoch": 2.6737919999999997, "grad_norm": 1.875, "learning_rate": 5.443221568125586e-06, "loss": 0.3893, "step": 10446 }, { "epoch": 2.674048, "grad_norm": 1.6640625, "learning_rate": 5.438955720501664e-06, "loss": 0.4246, "step": 10447 }, { "epoch": 2.6743040000000002, "grad_norm": 1.7421875, "learning_rate": 5.434689872877742e-06, "loss": 0.4509, "step": 10448 }, { "epoch": 2.67456, "grad_norm": 1.8359375, "learning_rate": 5.4304240252538184e-06, "loss": 0.4297, "step": 10449 }, { "epoch": 2.674816, "grad_norm": 1.59375, "learning_rate": 5.426158177629895e-06, "loss": 0.4275, "step": 10450 }, { "epoch": 2.675072, "grad_norm": 1.703125, "learning_rate": 5.421892330005973e-06, "loss": 0.4068, "step": 10451 }, { "epoch": 2.675328, "grad_norm": 1.7265625, "learning_rate": 5.41762648238205e-06, "loss": 0.4389, "step": 10452 }, { "epoch": 2.6755839999999997, "grad_norm": 1.8671875, "learning_rate": 5.4133606347581265e-06, "loss": 0.4075, "step": 10453 }, { "epoch": 2.67584, "grad_norm": 1.7421875, "learning_rate": 5.409094787134203e-06, "loss": 0.3986, "step": 10454 }, { "epoch": 2.6760960000000003, "grad_norm": 1.703125, "learning_rate": 5.404828939510281e-06, "loss": 0.4414, "step": 10455 }, { "epoch": 2.676352, "grad_norm": 1.671875, "learning_rate": 5.400563091886359e-06, "loss": 0.4403, "step": 10456 }, { "epoch": 2.676608, "grad_norm": 1.8203125, "learning_rate": 5.3962972442624354e-06, "loss": 0.4327, "step": 10457 }, { "epoch": 2.676864, "grad_norm": 1.6484375, "learning_rate": 5.392031396638512e-06, "loss": 0.435, "step": 10458 }, { "epoch": 2.67712, "grad_norm": 1.6796875, "learning_rate": 5.38776554901459e-06, "loss": 0.4623, "step": 10459 }, { "epoch": 2.6773759999999998, "grad_norm": 1.8359375, "learning_rate": 5.383499701390667e-06, "loss": 0.4382, "step": 10460 }, { "epoch": 2.677632, "grad_norm": 1.6953125, "learning_rate": 5.3792338537667435e-06, "loss": 0.4266, "step": 10461 }, { "epoch": 2.6778880000000003, "grad_norm": 1.8046875, "learning_rate": 5.37496800614282e-06, "loss": 0.4312, "step": 10462 }, { "epoch": 2.678144, "grad_norm": 1.65625, "learning_rate": 5.370702158518898e-06, "loss": 0.4502, "step": 10463 }, { "epoch": 2.6784, "grad_norm": 1.7265625, "learning_rate": 5.366436310894976e-06, "loss": 0.4316, "step": 10464 }, { "epoch": 2.678656, "grad_norm": 1.8046875, "learning_rate": 5.3621704632710524e-06, "loss": 0.4442, "step": 10465 }, { "epoch": 2.678912, "grad_norm": 1.71875, "learning_rate": 5.357904615647129e-06, "loss": 0.4451, "step": 10466 }, { "epoch": 2.6791679999999998, "grad_norm": 1.96875, "learning_rate": 5.353638768023207e-06, "loss": 0.4091, "step": 10467 }, { "epoch": 2.679424, "grad_norm": 1.828125, "learning_rate": 5.349372920399284e-06, "loss": 0.4048, "step": 10468 }, { "epoch": 2.67968, "grad_norm": 1.75, "learning_rate": 5.3451070727753605e-06, "loss": 0.4363, "step": 10469 }, { "epoch": 2.679936, "grad_norm": 1.7265625, "learning_rate": 5.340841225151437e-06, "loss": 0.4399, "step": 10470 }, { "epoch": 2.680192, "grad_norm": 1.6875, "learning_rate": 5.336575377527515e-06, "loss": 0.4204, "step": 10471 }, { "epoch": 2.680448, "grad_norm": 1.7890625, "learning_rate": 5.332309529903592e-06, "loss": 0.4124, "step": 10472 }, { "epoch": 2.680704, "grad_norm": 1.703125, "learning_rate": 5.3280436822796694e-06, "loss": 0.4461, "step": 10473 }, { "epoch": 2.68096, "grad_norm": 1.6875, "learning_rate": 5.323777834655746e-06, "loss": 0.4315, "step": 10474 }, { "epoch": 2.681216, "grad_norm": 1.7578125, "learning_rate": 5.319511987031824e-06, "loss": 0.4485, "step": 10475 }, { "epoch": 2.681472, "grad_norm": 1.8125, "learning_rate": 5.315246139407901e-06, "loss": 0.4526, "step": 10476 }, { "epoch": 2.681728, "grad_norm": 1.765625, "learning_rate": 5.3109802917839775e-06, "loss": 0.4332, "step": 10477 }, { "epoch": 2.681984, "grad_norm": 1.7890625, "learning_rate": 5.306714444160054e-06, "loss": 0.4119, "step": 10478 }, { "epoch": 2.68224, "grad_norm": 1.7578125, "learning_rate": 5.302448596536132e-06, "loss": 0.4458, "step": 10479 }, { "epoch": 2.682496, "grad_norm": 1.6796875, "learning_rate": 5.298182748912209e-06, "loss": 0.4415, "step": 10480 }, { "epoch": 2.682752, "grad_norm": 1.71875, "learning_rate": 5.2939169012882864e-06, "loss": 0.4029, "step": 10481 }, { "epoch": 2.683008, "grad_norm": 1.78125, "learning_rate": 5.289651053664363e-06, "loss": 0.4334, "step": 10482 }, { "epoch": 2.683264, "grad_norm": 1.7109375, "learning_rate": 5.285385206040441e-06, "loss": 0.4234, "step": 10483 }, { "epoch": 2.68352, "grad_norm": 1.8125, "learning_rate": 5.281119358416518e-06, "loss": 0.435, "step": 10484 }, { "epoch": 2.683776, "grad_norm": 1.6953125, "learning_rate": 5.2768535107925945e-06, "loss": 0.4546, "step": 10485 }, { "epoch": 2.684032, "grad_norm": 1.6171875, "learning_rate": 5.272587663168671e-06, "loss": 0.3953, "step": 10486 }, { "epoch": 2.684288, "grad_norm": 1.7265625, "learning_rate": 5.268321815544749e-06, "loss": 0.4583, "step": 10487 }, { "epoch": 2.684544, "grad_norm": 1.5546875, "learning_rate": 5.264055967920826e-06, "loss": 0.4215, "step": 10488 }, { "epoch": 2.6848, "grad_norm": 1.796875, "learning_rate": 5.2597901202969034e-06, "loss": 0.438, "step": 10489 }, { "epoch": 2.685056, "grad_norm": 1.71875, "learning_rate": 5.25552427267298e-06, "loss": 0.4657, "step": 10490 }, { "epoch": 2.685312, "grad_norm": 1.71875, "learning_rate": 5.251258425049058e-06, "loss": 0.4017, "step": 10491 }, { "epoch": 2.685568, "grad_norm": 1.734375, "learning_rate": 5.246992577425135e-06, "loss": 0.4019, "step": 10492 }, { "epoch": 2.685824, "grad_norm": 1.875, "learning_rate": 5.2427267298012115e-06, "loss": 0.4568, "step": 10493 }, { "epoch": 2.68608, "grad_norm": 1.703125, "learning_rate": 5.238460882177289e-06, "loss": 0.3923, "step": 10494 }, { "epoch": 2.686336, "grad_norm": 1.578125, "learning_rate": 5.234195034553366e-06, "loss": 0.4081, "step": 10495 }, { "epoch": 2.686592, "grad_norm": 1.8359375, "learning_rate": 5.229929186929443e-06, "loss": 0.4836, "step": 10496 }, { "epoch": 2.686848, "grad_norm": 1.7734375, "learning_rate": 5.2256633393055204e-06, "loss": 0.4291, "step": 10497 }, { "epoch": 2.687104, "grad_norm": 1.7109375, "learning_rate": 5.221397491681597e-06, "loss": 0.4215, "step": 10498 }, { "epoch": 2.68736, "grad_norm": 1.765625, "learning_rate": 5.217131644057675e-06, "loss": 0.4113, "step": 10499 }, { "epoch": 2.6876160000000002, "grad_norm": 1.78125, "learning_rate": 5.212865796433752e-06, "loss": 0.4066, "step": 10500 }, { "epoch": 2.687872, "grad_norm": 1.6953125, "learning_rate": 5.2085999488098285e-06, "loss": 0.4121, "step": 10501 }, { "epoch": 2.688128, "grad_norm": 1.71875, "learning_rate": 5.204334101185906e-06, "loss": 0.3884, "step": 10502 }, { "epoch": 2.688384, "grad_norm": 1.7265625, "learning_rate": 5.200068253561983e-06, "loss": 0.429, "step": 10503 }, { "epoch": 2.68864, "grad_norm": 1.828125, "learning_rate": 5.19580240593806e-06, "loss": 0.4476, "step": 10504 }, { "epoch": 2.6888959999999997, "grad_norm": 1.8203125, "learning_rate": 5.1915365583141374e-06, "loss": 0.4574, "step": 10505 }, { "epoch": 2.689152, "grad_norm": 1.78125, "learning_rate": 5.187270710690214e-06, "loss": 0.4061, "step": 10506 }, { "epoch": 2.6894080000000002, "grad_norm": 1.6875, "learning_rate": 5.183004863066292e-06, "loss": 0.4444, "step": 10507 }, { "epoch": 2.689664, "grad_norm": 1.71875, "learning_rate": 5.178739015442369e-06, "loss": 0.4016, "step": 10508 }, { "epoch": 2.68992, "grad_norm": 1.75, "learning_rate": 5.1744731678184455e-06, "loss": 0.4543, "step": 10509 }, { "epoch": 2.690176, "grad_norm": 1.7421875, "learning_rate": 5.170207320194523e-06, "loss": 0.4019, "step": 10510 }, { "epoch": 2.690432, "grad_norm": 1.671875, "learning_rate": 5.1659414725706e-06, "loss": 0.3959, "step": 10511 }, { "epoch": 2.6906879999999997, "grad_norm": 1.734375, "learning_rate": 5.161675624946677e-06, "loss": 0.4045, "step": 10512 }, { "epoch": 2.690944, "grad_norm": 1.6953125, "learning_rate": 5.157409777322754e-06, "loss": 0.4284, "step": 10513 }, { "epoch": 2.6912000000000003, "grad_norm": 1.9140625, "learning_rate": 5.153143929698831e-06, "loss": 0.4228, "step": 10514 }, { "epoch": 2.691456, "grad_norm": 1.703125, "learning_rate": 5.148878082074909e-06, "loss": 0.436, "step": 10515 }, { "epoch": 2.691712, "grad_norm": 1.734375, "learning_rate": 5.144612234450986e-06, "loss": 0.455, "step": 10516 }, { "epoch": 2.691968, "grad_norm": 1.71875, "learning_rate": 5.1403463868270625e-06, "loss": 0.4003, "step": 10517 }, { "epoch": 2.692224, "grad_norm": 1.7265625, "learning_rate": 5.13608053920314e-06, "loss": 0.4066, "step": 10518 }, { "epoch": 2.6924799999999998, "grad_norm": 1.6796875, "learning_rate": 5.131814691579217e-06, "loss": 0.4163, "step": 10519 }, { "epoch": 2.692736, "grad_norm": 1.7265625, "learning_rate": 5.127548843955294e-06, "loss": 0.4435, "step": 10520 }, { "epoch": 2.6929920000000003, "grad_norm": 1.6875, "learning_rate": 5.123282996331371e-06, "loss": 0.4153, "step": 10521 }, { "epoch": 2.693248, "grad_norm": 1.90625, "learning_rate": 5.119017148707449e-06, "loss": 0.4418, "step": 10522 }, { "epoch": 2.693504, "grad_norm": 1.7265625, "learning_rate": 5.114751301083526e-06, "loss": 0.4197, "step": 10523 }, { "epoch": 2.69376, "grad_norm": 1.7734375, "learning_rate": 5.110485453459603e-06, "loss": 0.4135, "step": 10524 }, { "epoch": 2.694016, "grad_norm": 1.875, "learning_rate": 5.1062196058356795e-06, "loss": 0.451, "step": 10525 }, { "epoch": 2.694272, "grad_norm": 1.7265625, "learning_rate": 5.101953758211757e-06, "loss": 0.4317, "step": 10526 }, { "epoch": 2.694528, "grad_norm": 1.75, "learning_rate": 5.097687910587834e-06, "loss": 0.4347, "step": 10527 }, { "epoch": 2.694784, "grad_norm": 1.8515625, "learning_rate": 5.093422062963911e-06, "loss": 0.3997, "step": 10528 }, { "epoch": 2.69504, "grad_norm": 1.6875, "learning_rate": 5.089156215339988e-06, "loss": 0.4181, "step": 10529 }, { "epoch": 2.695296, "grad_norm": 1.75, "learning_rate": 5.084890367716066e-06, "loss": 0.4291, "step": 10530 }, { "epoch": 2.695552, "grad_norm": 1.765625, "learning_rate": 5.080624520092143e-06, "loss": 0.4504, "step": 10531 }, { "epoch": 2.695808, "grad_norm": 1.8046875, "learning_rate": 5.07635867246822e-06, "loss": 0.4158, "step": 10532 }, { "epoch": 2.696064, "grad_norm": 1.59375, "learning_rate": 5.0720928248442965e-06, "loss": 0.3824, "step": 10533 }, { "epoch": 2.69632, "grad_norm": 1.8515625, "learning_rate": 5.067826977220374e-06, "loss": 0.4429, "step": 10534 }, { "epoch": 2.696576, "grad_norm": 1.7265625, "learning_rate": 5.063561129596451e-06, "loss": 0.4292, "step": 10535 }, { "epoch": 2.696832, "grad_norm": 1.65625, "learning_rate": 5.059295281972528e-06, "loss": 0.4197, "step": 10536 }, { "epoch": 2.697088, "grad_norm": 1.7421875, "learning_rate": 5.055029434348605e-06, "loss": 0.4416, "step": 10537 }, { "epoch": 2.697344, "grad_norm": 1.7109375, "learning_rate": 5.050763586724683e-06, "loss": 0.4041, "step": 10538 }, { "epoch": 2.6976, "grad_norm": 1.765625, "learning_rate": 5.04649773910076e-06, "loss": 0.3959, "step": 10539 }, { "epoch": 2.697856, "grad_norm": 1.7265625, "learning_rate": 5.042231891476837e-06, "loss": 0.3967, "step": 10540 }, { "epoch": 2.698112, "grad_norm": 1.515625, "learning_rate": 5.0379660438529135e-06, "loss": 0.4, "step": 10541 }, { "epoch": 2.698368, "grad_norm": 1.7734375, "learning_rate": 5.033700196228991e-06, "loss": 0.422, "step": 10542 }, { "epoch": 2.698624, "grad_norm": 1.78125, "learning_rate": 5.029434348605068e-06, "loss": 0.4619, "step": 10543 }, { "epoch": 2.69888, "grad_norm": 1.7890625, "learning_rate": 5.025168500981145e-06, "loss": 0.455, "step": 10544 }, { "epoch": 2.699136, "grad_norm": 1.6484375, "learning_rate": 5.0209026533572224e-06, "loss": 0.4246, "step": 10545 }, { "epoch": 2.699392, "grad_norm": 1.703125, "learning_rate": 5.0166368057333e-06, "loss": 0.4134, "step": 10546 }, { "epoch": 2.699648, "grad_norm": 1.7890625, "learning_rate": 5.012370958109377e-06, "loss": 0.4291, "step": 10547 }, { "epoch": 2.699904, "grad_norm": 1.78125, "learning_rate": 5.008105110485454e-06, "loss": 0.4042, "step": 10548 }, { "epoch": 2.70016, "grad_norm": 1.7578125, "learning_rate": 5.0038392628615305e-06, "loss": 0.3899, "step": 10549 }, { "epoch": 2.700416, "grad_norm": 1.796875, "learning_rate": 4.999573415237608e-06, "loss": 0.4221, "step": 10550 }, { "epoch": 2.700672, "grad_norm": 1.7890625, "learning_rate": 4.995307567613685e-06, "loss": 0.3736, "step": 10551 }, { "epoch": 2.700928, "grad_norm": 1.8203125, "learning_rate": 4.991041719989762e-06, "loss": 0.3925, "step": 10552 }, { "epoch": 2.701184, "grad_norm": 1.6875, "learning_rate": 4.9867758723658394e-06, "loss": 0.4406, "step": 10553 }, { "epoch": 2.70144, "grad_norm": 1.703125, "learning_rate": 4.982510024741917e-06, "loss": 0.454, "step": 10554 }, { "epoch": 2.701696, "grad_norm": 1.8046875, "learning_rate": 4.978244177117994e-06, "loss": 0.426, "step": 10555 }, { "epoch": 2.701952, "grad_norm": 1.7265625, "learning_rate": 4.973978329494071e-06, "loss": 0.4548, "step": 10556 }, { "epoch": 2.702208, "grad_norm": 1.8359375, "learning_rate": 4.9697124818701475e-06, "loss": 0.4385, "step": 10557 }, { "epoch": 2.702464, "grad_norm": 1.7109375, "learning_rate": 4.965446634246225e-06, "loss": 0.4571, "step": 10558 }, { "epoch": 2.7027200000000002, "grad_norm": 1.6875, "learning_rate": 4.961180786622302e-06, "loss": 0.4449, "step": 10559 }, { "epoch": 2.702976, "grad_norm": 1.7734375, "learning_rate": 4.956914938998379e-06, "loss": 0.4275, "step": 10560 }, { "epoch": 2.703232, "grad_norm": 1.8125, "learning_rate": 4.9526490913744564e-06, "loss": 0.461, "step": 10561 }, { "epoch": 2.703488, "grad_norm": 1.7890625, "learning_rate": 4.948383243750533e-06, "loss": 0.4183, "step": 10562 }, { "epoch": 2.703744, "grad_norm": 1.7890625, "learning_rate": 4.944117396126611e-06, "loss": 0.4623, "step": 10563 }, { "epoch": 2.7039999999999997, "grad_norm": 1.8125, "learning_rate": 4.939851548502688e-06, "loss": 0.4498, "step": 10564 }, { "epoch": 2.704256, "grad_norm": 1.6796875, "learning_rate": 4.935585700878765e-06, "loss": 0.4315, "step": 10565 }, { "epoch": 2.7045120000000002, "grad_norm": 1.7265625, "learning_rate": 4.931319853254842e-06, "loss": 0.4182, "step": 10566 }, { "epoch": 2.704768, "grad_norm": 1.703125, "learning_rate": 4.927054005630919e-06, "loss": 0.4353, "step": 10567 }, { "epoch": 2.705024, "grad_norm": 1.765625, "learning_rate": 4.922788158006996e-06, "loss": 0.432, "step": 10568 }, { "epoch": 2.70528, "grad_norm": 1.75, "learning_rate": 4.9185223103830734e-06, "loss": 0.4217, "step": 10569 }, { "epoch": 2.705536, "grad_norm": 1.8515625, "learning_rate": 4.91425646275915e-06, "loss": 0.4505, "step": 10570 }, { "epoch": 2.7057919999999998, "grad_norm": 1.6640625, "learning_rate": 4.909990615135228e-06, "loss": 0.3876, "step": 10571 }, { "epoch": 2.706048, "grad_norm": 1.828125, "learning_rate": 4.905724767511305e-06, "loss": 0.4287, "step": 10572 }, { "epoch": 2.7063040000000003, "grad_norm": 1.796875, "learning_rate": 4.901458919887382e-06, "loss": 0.4312, "step": 10573 }, { "epoch": 2.70656, "grad_norm": 1.828125, "learning_rate": 4.897193072263459e-06, "loss": 0.4674, "step": 10574 }, { "epoch": 2.706816, "grad_norm": 1.7265625, "learning_rate": 4.892927224639536e-06, "loss": 0.4217, "step": 10575 }, { "epoch": 2.707072, "grad_norm": 1.6875, "learning_rate": 4.888661377015613e-06, "loss": 0.4197, "step": 10576 }, { "epoch": 2.707328, "grad_norm": 1.796875, "learning_rate": 4.8843955293916904e-06, "loss": 0.3962, "step": 10577 }, { "epoch": 2.7075839999999998, "grad_norm": 1.75, "learning_rate": 4.880129681767767e-06, "loss": 0.399, "step": 10578 }, { "epoch": 2.70784, "grad_norm": 1.75, "learning_rate": 4.875863834143845e-06, "loss": 0.402, "step": 10579 }, { "epoch": 2.708096, "grad_norm": 1.734375, "learning_rate": 4.871597986519922e-06, "loss": 0.4356, "step": 10580 }, { "epoch": 2.708352, "grad_norm": 1.6953125, "learning_rate": 4.867332138895999e-06, "loss": 0.3994, "step": 10581 }, { "epoch": 2.708608, "grad_norm": 1.6015625, "learning_rate": 4.863066291272076e-06, "loss": 0.4107, "step": 10582 }, { "epoch": 2.708864, "grad_norm": 1.6640625, "learning_rate": 4.858800443648153e-06, "loss": 0.4047, "step": 10583 }, { "epoch": 2.70912, "grad_norm": 1.7421875, "learning_rate": 4.85453459602423e-06, "loss": 0.4506, "step": 10584 }, { "epoch": 2.709376, "grad_norm": 1.59375, "learning_rate": 4.8502687484003074e-06, "loss": 0.4306, "step": 10585 }, { "epoch": 2.709632, "grad_norm": 1.7421875, "learning_rate": 4.846002900776384e-06, "loss": 0.4396, "step": 10586 }, { "epoch": 2.709888, "grad_norm": 1.65625, "learning_rate": 4.841737053152462e-06, "loss": 0.413, "step": 10587 }, { "epoch": 2.710144, "grad_norm": 1.59375, "learning_rate": 4.837471205528539e-06, "loss": 0.3891, "step": 10588 }, { "epoch": 2.7104, "grad_norm": 1.796875, "learning_rate": 4.833205357904616e-06, "loss": 0.4481, "step": 10589 }, { "epoch": 2.710656, "grad_norm": 1.8359375, "learning_rate": 4.828939510280693e-06, "loss": 0.4556, "step": 10590 }, { "epoch": 2.710912, "grad_norm": 1.8515625, "learning_rate": 4.82467366265677e-06, "loss": 0.4365, "step": 10591 }, { "epoch": 2.711168, "grad_norm": 1.8828125, "learning_rate": 4.820407815032847e-06, "loss": 0.4283, "step": 10592 }, { "epoch": 2.711424, "grad_norm": 1.6171875, "learning_rate": 4.8161419674089244e-06, "loss": 0.4774, "step": 10593 }, { "epoch": 2.71168, "grad_norm": 1.84375, "learning_rate": 4.811876119785001e-06, "loss": 0.384, "step": 10594 }, { "epoch": 2.711936, "grad_norm": 1.6953125, "learning_rate": 4.807610272161079e-06, "loss": 0.401, "step": 10595 }, { "epoch": 2.712192, "grad_norm": 1.8203125, "learning_rate": 4.803344424537156e-06, "loss": 0.3825, "step": 10596 }, { "epoch": 2.712448, "grad_norm": 1.71875, "learning_rate": 4.799078576913233e-06, "loss": 0.425, "step": 10597 }, { "epoch": 2.712704, "grad_norm": 1.7734375, "learning_rate": 4.79481272928931e-06, "loss": 0.4199, "step": 10598 }, { "epoch": 2.71296, "grad_norm": 1.7421875, "learning_rate": 4.790546881665387e-06, "loss": 0.4193, "step": 10599 }, { "epoch": 2.713216, "grad_norm": 1.7890625, "learning_rate": 4.786281034041464e-06, "loss": 0.4328, "step": 10600 }, { "epoch": 2.713472, "grad_norm": 1.6796875, "learning_rate": 4.7820151864175414e-06, "loss": 0.4197, "step": 10601 }, { "epoch": 2.713728, "grad_norm": 1.65625, "learning_rate": 4.777749338793618e-06, "loss": 0.4457, "step": 10602 }, { "epoch": 2.713984, "grad_norm": 1.828125, "learning_rate": 4.773483491169695e-06, "loss": 0.4422, "step": 10603 }, { "epoch": 2.71424, "grad_norm": 1.6953125, "learning_rate": 4.769217643545773e-06, "loss": 0.4112, "step": 10604 }, { "epoch": 2.714496, "grad_norm": 1.640625, "learning_rate": 4.76495179592185e-06, "loss": 0.4047, "step": 10605 }, { "epoch": 2.714752, "grad_norm": 1.765625, "learning_rate": 4.760685948297927e-06, "loss": 0.4151, "step": 10606 }, { "epoch": 2.715008, "grad_norm": 1.6796875, "learning_rate": 4.756420100674004e-06, "loss": 0.4382, "step": 10607 }, { "epoch": 2.715264, "grad_norm": 1.75, "learning_rate": 4.752154253050082e-06, "loss": 0.4512, "step": 10608 }, { "epoch": 2.71552, "grad_norm": 1.78125, "learning_rate": 4.7478884054261584e-06, "loss": 0.4278, "step": 10609 }, { "epoch": 2.715776, "grad_norm": 1.65625, "learning_rate": 4.743622557802235e-06, "loss": 0.462, "step": 10610 }, { "epoch": 2.7160320000000002, "grad_norm": 1.78125, "learning_rate": 4.739356710178312e-06, "loss": 0.4064, "step": 10611 }, { "epoch": 2.716288, "grad_norm": 1.703125, "learning_rate": 4.73509086255439e-06, "loss": 0.4246, "step": 10612 }, { "epoch": 2.716544, "grad_norm": 1.7578125, "learning_rate": 4.730825014930467e-06, "loss": 0.4037, "step": 10613 }, { "epoch": 2.7168, "grad_norm": 1.7578125, "learning_rate": 4.726559167306544e-06, "loss": 0.4002, "step": 10614 }, { "epoch": 2.717056, "grad_norm": 1.6796875, "learning_rate": 4.722293319682621e-06, "loss": 0.4653, "step": 10615 }, { "epoch": 2.7173119999999997, "grad_norm": 1.8046875, "learning_rate": 4.718027472058699e-06, "loss": 0.4243, "step": 10616 }, { "epoch": 2.717568, "grad_norm": 1.6484375, "learning_rate": 4.7137616244347754e-06, "loss": 0.4152, "step": 10617 }, { "epoch": 2.7178240000000002, "grad_norm": 1.734375, "learning_rate": 4.709495776810852e-06, "loss": 0.4188, "step": 10618 }, { "epoch": 2.71808, "grad_norm": 1.78125, "learning_rate": 4.705229929186929e-06, "loss": 0.4199, "step": 10619 }, { "epoch": 2.718336, "grad_norm": 1.8828125, "learning_rate": 4.700964081563007e-06, "loss": 0.4298, "step": 10620 }, { "epoch": 2.718592, "grad_norm": 1.8515625, "learning_rate": 4.696698233939084e-06, "loss": 0.3978, "step": 10621 }, { "epoch": 2.718848, "grad_norm": 1.8203125, "learning_rate": 4.692432386315161e-06, "loss": 0.4095, "step": 10622 }, { "epoch": 2.7191039999999997, "grad_norm": 1.7265625, "learning_rate": 4.688166538691238e-06, "loss": 0.4105, "step": 10623 }, { "epoch": 2.71936, "grad_norm": 1.609375, "learning_rate": 4.683900691067316e-06, "loss": 0.3961, "step": 10624 }, { "epoch": 2.7196160000000003, "grad_norm": 1.703125, "learning_rate": 4.6796348434433924e-06, "loss": 0.4298, "step": 10625 }, { "epoch": 2.719872, "grad_norm": 1.65625, "learning_rate": 4.675368995819469e-06, "loss": 0.4115, "step": 10626 }, { "epoch": 2.720128, "grad_norm": 1.6875, "learning_rate": 4.671103148195546e-06, "loss": 0.4446, "step": 10627 }, { "epoch": 2.720384, "grad_norm": 1.8046875, "learning_rate": 4.666837300571624e-06, "loss": 0.4498, "step": 10628 }, { "epoch": 2.72064, "grad_norm": 1.734375, "learning_rate": 4.662571452947701e-06, "loss": 0.4041, "step": 10629 }, { "epoch": 2.7208959999999998, "grad_norm": 1.7421875, "learning_rate": 4.658305605323778e-06, "loss": 0.4342, "step": 10630 }, { "epoch": 2.721152, "grad_norm": 1.796875, "learning_rate": 4.654039757699855e-06, "loss": 0.401, "step": 10631 }, { "epoch": 2.7214080000000003, "grad_norm": 1.703125, "learning_rate": 4.649773910075933e-06, "loss": 0.471, "step": 10632 }, { "epoch": 2.721664, "grad_norm": 1.6953125, "learning_rate": 4.6455080624520094e-06, "loss": 0.4473, "step": 10633 }, { "epoch": 2.72192, "grad_norm": 1.75, "learning_rate": 4.641242214828086e-06, "loss": 0.4279, "step": 10634 }, { "epoch": 2.722176, "grad_norm": 1.8046875, "learning_rate": 4.636976367204163e-06, "loss": 0.4702, "step": 10635 }, { "epoch": 2.722432, "grad_norm": 1.6875, "learning_rate": 4.6327105195802416e-06, "loss": 0.4175, "step": 10636 }, { "epoch": 2.7226879999999998, "grad_norm": 1.6953125, "learning_rate": 4.628444671956318e-06, "loss": 0.4423, "step": 10637 }, { "epoch": 2.722944, "grad_norm": 1.6875, "learning_rate": 4.624178824332395e-06, "loss": 0.428, "step": 10638 }, { "epoch": 2.7232, "grad_norm": 1.7890625, "learning_rate": 4.619912976708472e-06, "loss": 0.4392, "step": 10639 }, { "epoch": 2.723456, "grad_norm": 1.6875, "learning_rate": 4.61564712908455e-06, "loss": 0.4185, "step": 10640 }, { "epoch": 2.723712, "grad_norm": 1.7734375, "learning_rate": 4.6113812814606264e-06, "loss": 0.4562, "step": 10641 }, { "epoch": 2.723968, "grad_norm": 1.8515625, "learning_rate": 4.607115433836703e-06, "loss": 0.449, "step": 10642 }, { "epoch": 2.724224, "grad_norm": 1.7734375, "learning_rate": 4.60284958621278e-06, "loss": 0.4283, "step": 10643 }, { "epoch": 2.72448, "grad_norm": 1.6796875, "learning_rate": 4.598583738588858e-06, "loss": 0.4469, "step": 10644 }, { "epoch": 2.724736, "grad_norm": 1.7734375, "learning_rate": 4.594317890964935e-06, "loss": 0.4381, "step": 10645 }, { "epoch": 2.724992, "grad_norm": 1.609375, "learning_rate": 4.590052043341012e-06, "loss": 0.4132, "step": 10646 }, { "epoch": 2.725248, "grad_norm": 1.6875, "learning_rate": 4.585786195717089e-06, "loss": 0.437, "step": 10647 }, { "epoch": 2.725504, "grad_norm": 1.71875, "learning_rate": 4.581520348093167e-06, "loss": 0.4124, "step": 10648 }, { "epoch": 2.72576, "grad_norm": 1.625, "learning_rate": 4.5772545004692434e-06, "loss": 0.4494, "step": 10649 }, { "epoch": 2.726016, "grad_norm": 1.8125, "learning_rate": 4.57298865284532e-06, "loss": 0.4321, "step": 10650 }, { "epoch": 2.726272, "grad_norm": 1.828125, "learning_rate": 4.568722805221397e-06, "loss": 0.4521, "step": 10651 }, { "epoch": 2.726528, "grad_norm": 1.8046875, "learning_rate": 4.564456957597475e-06, "loss": 0.3996, "step": 10652 }, { "epoch": 2.726784, "grad_norm": 1.71875, "learning_rate": 4.560191109973552e-06, "loss": 0.4273, "step": 10653 }, { "epoch": 2.72704, "grad_norm": 1.7578125, "learning_rate": 4.555925262349629e-06, "loss": 0.4453, "step": 10654 }, { "epoch": 2.727296, "grad_norm": 1.734375, "learning_rate": 4.551659414725706e-06, "loss": 0.4245, "step": 10655 }, { "epoch": 2.727552, "grad_norm": 1.7421875, "learning_rate": 4.547393567101784e-06, "loss": 0.4559, "step": 10656 }, { "epoch": 2.727808, "grad_norm": 1.7734375, "learning_rate": 4.5431277194778604e-06, "loss": 0.4245, "step": 10657 }, { "epoch": 2.728064, "grad_norm": 1.734375, "learning_rate": 4.538861871853937e-06, "loss": 0.4145, "step": 10658 }, { "epoch": 2.72832, "grad_norm": 1.6328125, "learning_rate": 4.534596024230015e-06, "loss": 0.407, "step": 10659 }, { "epoch": 2.728576, "grad_norm": 1.90625, "learning_rate": 4.530330176606092e-06, "loss": 0.4253, "step": 10660 }, { "epoch": 2.728832, "grad_norm": 1.734375, "learning_rate": 4.526064328982169e-06, "loss": 0.4134, "step": 10661 }, { "epoch": 2.729088, "grad_norm": 1.734375, "learning_rate": 4.521798481358246e-06, "loss": 0.4236, "step": 10662 }, { "epoch": 2.729344, "grad_norm": 1.7578125, "learning_rate": 4.517532633734323e-06, "loss": 0.4419, "step": 10663 }, { "epoch": 2.7296, "grad_norm": 1.71875, "learning_rate": 4.513266786110401e-06, "loss": 0.4468, "step": 10664 }, { "epoch": 2.729856, "grad_norm": 1.859375, "learning_rate": 4.5090009384864774e-06, "loss": 0.4021, "step": 10665 }, { "epoch": 2.730112, "grad_norm": 1.78125, "learning_rate": 4.504735090862554e-06, "loss": 0.3929, "step": 10666 }, { "epoch": 2.730368, "grad_norm": 1.7421875, "learning_rate": 4.500469243238632e-06, "loss": 0.4116, "step": 10667 }, { "epoch": 2.730624, "grad_norm": 1.7890625, "learning_rate": 4.496203395614709e-06, "loss": 0.442, "step": 10668 }, { "epoch": 2.73088, "grad_norm": 1.6015625, "learning_rate": 4.491937547990786e-06, "loss": 0.458, "step": 10669 }, { "epoch": 2.7311360000000002, "grad_norm": 1.6875, "learning_rate": 4.487671700366863e-06, "loss": 0.4248, "step": 10670 }, { "epoch": 2.731392, "grad_norm": 1.671875, "learning_rate": 4.48340585274294e-06, "loss": 0.4757, "step": 10671 }, { "epoch": 2.731648, "grad_norm": 1.6796875, "learning_rate": 4.479140005119018e-06, "loss": 0.4079, "step": 10672 }, { "epoch": 2.731904, "grad_norm": 1.7578125, "learning_rate": 4.4748741574950944e-06, "loss": 0.4214, "step": 10673 }, { "epoch": 2.73216, "grad_norm": 1.7578125, "learning_rate": 4.470608309871171e-06, "loss": 0.4358, "step": 10674 }, { "epoch": 2.7324159999999997, "grad_norm": 1.734375, "learning_rate": 4.466342462247249e-06, "loss": 0.4036, "step": 10675 }, { "epoch": 2.732672, "grad_norm": 1.71875, "learning_rate": 4.462076614623326e-06, "loss": 0.4149, "step": 10676 }, { "epoch": 2.7329280000000002, "grad_norm": 1.765625, "learning_rate": 4.457810766999403e-06, "loss": 0.3937, "step": 10677 }, { "epoch": 2.733184, "grad_norm": 1.765625, "learning_rate": 4.45354491937548e-06, "loss": 0.4286, "step": 10678 }, { "epoch": 2.73344, "grad_norm": 1.8515625, "learning_rate": 4.449279071751558e-06, "loss": 0.4253, "step": 10679 }, { "epoch": 2.733696, "grad_norm": 1.78125, "learning_rate": 4.445013224127635e-06, "loss": 0.4381, "step": 10680 }, { "epoch": 2.733952, "grad_norm": 1.7734375, "learning_rate": 4.4407473765037114e-06, "loss": 0.4336, "step": 10681 }, { "epoch": 2.7342079999999997, "grad_norm": 1.875, "learning_rate": 4.436481528879788e-06, "loss": 0.4325, "step": 10682 }, { "epoch": 2.734464, "grad_norm": 1.7890625, "learning_rate": 4.432215681255866e-06, "loss": 0.3909, "step": 10683 }, { "epoch": 2.7347200000000003, "grad_norm": 1.71875, "learning_rate": 4.427949833631943e-06, "loss": 0.41, "step": 10684 }, { "epoch": 2.734976, "grad_norm": 1.703125, "learning_rate": 4.4236839860080195e-06, "loss": 0.3752, "step": 10685 }, { "epoch": 2.735232, "grad_norm": 1.7421875, "learning_rate": 4.419418138384097e-06, "loss": 0.4393, "step": 10686 }, { "epoch": 2.735488, "grad_norm": 1.7109375, "learning_rate": 4.415152290760175e-06, "loss": 0.4004, "step": 10687 }, { "epoch": 2.735744, "grad_norm": 1.734375, "learning_rate": 4.410886443136252e-06, "loss": 0.3959, "step": 10688 }, { "epoch": 2.7359999999999998, "grad_norm": 1.8125, "learning_rate": 4.4066205955123285e-06, "loss": 0.4125, "step": 10689 }, { "epoch": 2.736256, "grad_norm": 1.7109375, "learning_rate": 4.402354747888405e-06, "loss": 0.4289, "step": 10690 }, { "epoch": 2.736512, "grad_norm": 1.734375, "learning_rate": 4.398088900264483e-06, "loss": 0.4367, "step": 10691 }, { "epoch": 2.736768, "grad_norm": 1.6796875, "learning_rate": 4.39382305264056e-06, "loss": 0.4115, "step": 10692 }, { "epoch": 2.737024, "grad_norm": 1.6953125, "learning_rate": 4.3895572050166365e-06, "loss": 0.4063, "step": 10693 }, { "epoch": 2.73728, "grad_norm": 1.71875, "learning_rate": 4.385291357392714e-06, "loss": 0.4227, "step": 10694 }, { "epoch": 2.737536, "grad_norm": 1.8515625, "learning_rate": 4.381025509768792e-06, "loss": 0.384, "step": 10695 }, { "epoch": 2.737792, "grad_norm": 1.859375, "learning_rate": 4.376759662144869e-06, "loss": 0.4439, "step": 10696 }, { "epoch": 2.738048, "grad_norm": 1.8359375, "learning_rate": 4.3724938145209455e-06, "loss": 0.4289, "step": 10697 }, { "epoch": 2.738304, "grad_norm": 1.6640625, "learning_rate": 4.368227966897022e-06, "loss": 0.4437, "step": 10698 }, { "epoch": 2.73856, "grad_norm": 1.6015625, "learning_rate": 4.3639621192731e-06, "loss": 0.3842, "step": 10699 }, { "epoch": 2.738816, "grad_norm": 1.8046875, "learning_rate": 4.359696271649177e-06, "loss": 0.4273, "step": 10700 }, { "epoch": 2.739072, "grad_norm": 1.7578125, "learning_rate": 4.3554304240252535e-06, "loss": 0.3999, "step": 10701 }, { "epoch": 2.739328, "grad_norm": 1.6484375, "learning_rate": 4.351164576401331e-06, "loss": 0.4206, "step": 10702 }, { "epoch": 2.739584, "grad_norm": 1.71875, "learning_rate": 4.346898728777409e-06, "loss": 0.4291, "step": 10703 }, { "epoch": 2.73984, "grad_norm": 1.7578125, "learning_rate": 4.342632881153486e-06, "loss": 0.4467, "step": 10704 }, { "epoch": 2.740096, "grad_norm": 1.7421875, "learning_rate": 4.3383670335295625e-06, "loss": 0.4631, "step": 10705 }, { "epoch": 2.740352, "grad_norm": 1.7265625, "learning_rate": 4.334101185905639e-06, "loss": 0.4354, "step": 10706 }, { "epoch": 2.740608, "grad_norm": 1.796875, "learning_rate": 4.329835338281717e-06, "loss": 0.4402, "step": 10707 }, { "epoch": 2.740864, "grad_norm": 1.6640625, "learning_rate": 4.325569490657794e-06, "loss": 0.4396, "step": 10708 }, { "epoch": 2.74112, "grad_norm": 1.7578125, "learning_rate": 4.3213036430338705e-06, "loss": 0.4209, "step": 10709 }, { "epoch": 2.741376, "grad_norm": 1.7734375, "learning_rate": 4.317037795409948e-06, "loss": 0.4075, "step": 10710 }, { "epoch": 2.741632, "grad_norm": 1.7578125, "learning_rate": 4.312771947786026e-06, "loss": 0.4341, "step": 10711 }, { "epoch": 2.741888, "grad_norm": 1.7734375, "learning_rate": 4.308506100162103e-06, "loss": 0.3953, "step": 10712 }, { "epoch": 2.742144, "grad_norm": 1.7734375, "learning_rate": 4.3042402525381795e-06, "loss": 0.4019, "step": 10713 }, { "epoch": 2.7424, "grad_norm": 1.6875, "learning_rate": 4.299974404914256e-06, "loss": 0.4431, "step": 10714 }, { "epoch": 2.742656, "grad_norm": 1.703125, "learning_rate": 4.295708557290334e-06, "loss": 0.4248, "step": 10715 }, { "epoch": 2.742912, "grad_norm": 1.8359375, "learning_rate": 4.291442709666411e-06, "loss": 0.4177, "step": 10716 }, { "epoch": 2.743168, "grad_norm": 1.6640625, "learning_rate": 4.2871768620424875e-06, "loss": 0.4084, "step": 10717 }, { "epoch": 2.743424, "grad_norm": 1.7578125, "learning_rate": 4.282911014418565e-06, "loss": 0.3923, "step": 10718 }, { "epoch": 2.74368, "grad_norm": 1.7890625, "learning_rate": 4.278645166794643e-06, "loss": 0.3982, "step": 10719 }, { "epoch": 2.743936, "grad_norm": 1.75, "learning_rate": 4.27437931917072e-06, "loss": 0.4279, "step": 10720 }, { "epoch": 2.744192, "grad_norm": 1.6953125, "learning_rate": 4.2701134715467965e-06, "loss": 0.4411, "step": 10721 }, { "epoch": 2.744448, "grad_norm": 1.703125, "learning_rate": 4.265847623922873e-06, "loss": 0.4348, "step": 10722 }, { "epoch": 2.744704, "grad_norm": 1.7578125, "learning_rate": 4.261581776298951e-06, "loss": 0.4224, "step": 10723 }, { "epoch": 2.74496, "grad_norm": 1.6328125, "learning_rate": 4.257315928675028e-06, "loss": 0.4377, "step": 10724 }, { "epoch": 2.745216, "grad_norm": 1.84375, "learning_rate": 4.2530500810511045e-06, "loss": 0.4556, "step": 10725 }, { "epoch": 2.745472, "grad_norm": 1.734375, "learning_rate": 4.248784233427182e-06, "loss": 0.4161, "step": 10726 }, { "epoch": 2.7457279999999997, "grad_norm": 1.875, "learning_rate": 4.24451838580326e-06, "loss": 0.4446, "step": 10727 }, { "epoch": 2.745984, "grad_norm": 1.75, "learning_rate": 4.240252538179337e-06, "loss": 0.4055, "step": 10728 }, { "epoch": 2.7462400000000002, "grad_norm": 1.71875, "learning_rate": 4.2359866905554135e-06, "loss": 0.4052, "step": 10729 }, { "epoch": 2.746496, "grad_norm": 1.8125, "learning_rate": 4.231720842931491e-06, "loss": 0.4179, "step": 10730 }, { "epoch": 2.746752, "grad_norm": 1.7265625, "learning_rate": 4.227454995307568e-06, "loss": 0.4281, "step": 10731 }, { "epoch": 2.747008, "grad_norm": 1.7578125, "learning_rate": 4.223189147683645e-06, "loss": 0.4285, "step": 10732 }, { "epoch": 2.747264, "grad_norm": 1.75, "learning_rate": 4.2189233000597215e-06, "loss": 0.4255, "step": 10733 }, { "epoch": 2.7475199999999997, "grad_norm": 1.9140625, "learning_rate": 4.214657452435799e-06, "loss": 0.477, "step": 10734 }, { "epoch": 2.747776, "grad_norm": 1.6875, "learning_rate": 4.210391604811877e-06, "loss": 0.3969, "step": 10735 }, { "epoch": 2.7480320000000003, "grad_norm": 1.75, "learning_rate": 4.206125757187954e-06, "loss": 0.4465, "step": 10736 }, { "epoch": 2.748288, "grad_norm": 1.7734375, "learning_rate": 4.2018599095640305e-06, "loss": 0.3857, "step": 10737 }, { "epoch": 2.748544, "grad_norm": 1.6484375, "learning_rate": 4.197594061940108e-06, "loss": 0.4236, "step": 10738 }, { "epoch": 2.7488, "grad_norm": 1.859375, "learning_rate": 4.193328214316185e-06, "loss": 0.4128, "step": 10739 }, { "epoch": 2.749056, "grad_norm": 1.8046875, "learning_rate": 4.189062366692262e-06, "loss": 0.3955, "step": 10740 }, { "epoch": 2.7493119999999998, "grad_norm": 1.7734375, "learning_rate": 4.1847965190683385e-06, "loss": 0.4335, "step": 10741 }, { "epoch": 2.749568, "grad_norm": 1.78125, "learning_rate": 4.180530671444416e-06, "loss": 0.4093, "step": 10742 }, { "epoch": 2.7498240000000003, "grad_norm": 1.8046875, "learning_rate": 4.176264823820494e-06, "loss": 0.4476, "step": 10743 }, { "epoch": 2.75008, "grad_norm": 1.5390625, "learning_rate": 4.171998976196571e-06, "loss": 0.4285, "step": 10744 }, { "epoch": 2.750336, "grad_norm": 1.8046875, "learning_rate": 4.1677331285726475e-06, "loss": 0.4312, "step": 10745 }, { "epoch": 2.750592, "grad_norm": 1.78125, "learning_rate": 4.163467280948725e-06, "loss": 0.4173, "step": 10746 }, { "epoch": 2.750848, "grad_norm": 1.7109375, "learning_rate": 4.159201433324802e-06, "loss": 0.4405, "step": 10747 }, { "epoch": 2.7511039999999998, "grad_norm": 1.7109375, "learning_rate": 4.154935585700879e-06, "loss": 0.4102, "step": 10748 }, { "epoch": 2.75136, "grad_norm": 1.75, "learning_rate": 4.1506697380769555e-06, "loss": 0.3797, "step": 10749 }, { "epoch": 2.751616, "grad_norm": 1.765625, "learning_rate": 4.146403890453033e-06, "loss": 0.426, "step": 10750 }, { "epoch": 2.751872, "grad_norm": 1.6953125, "learning_rate": 4.142138042829111e-06, "loss": 0.4089, "step": 10751 }, { "epoch": 2.752128, "grad_norm": 1.8203125, "learning_rate": 4.137872195205188e-06, "loss": 0.4082, "step": 10752 }, { "epoch": 2.752384, "grad_norm": 1.8671875, "learning_rate": 4.1336063475812645e-06, "loss": 0.4034, "step": 10753 }, { "epoch": 2.75264, "grad_norm": 1.7890625, "learning_rate": 4.129340499957342e-06, "loss": 0.4456, "step": 10754 }, { "epoch": 2.752896, "grad_norm": 1.640625, "learning_rate": 4.125074652333419e-06, "loss": 0.423, "step": 10755 }, { "epoch": 2.753152, "grad_norm": 1.796875, "learning_rate": 4.120808804709496e-06, "loss": 0.4083, "step": 10756 }, { "epoch": 2.753408, "grad_norm": 1.7890625, "learning_rate": 4.1165429570855725e-06, "loss": 0.4028, "step": 10757 }, { "epoch": 2.753664, "grad_norm": 1.765625, "learning_rate": 4.11227710946165e-06, "loss": 0.4148, "step": 10758 }, { "epoch": 2.75392, "grad_norm": 1.7109375, "learning_rate": 4.108011261837728e-06, "loss": 0.3942, "step": 10759 }, { "epoch": 2.754176, "grad_norm": 1.7734375, "learning_rate": 4.103745414213805e-06, "loss": 0.4412, "step": 10760 }, { "epoch": 2.754432, "grad_norm": 1.7890625, "learning_rate": 4.0994795665898815e-06, "loss": 0.4266, "step": 10761 }, { "epoch": 2.754688, "grad_norm": 1.8046875, "learning_rate": 4.095213718965959e-06, "loss": 0.4273, "step": 10762 }, { "epoch": 2.754944, "grad_norm": 1.7890625, "learning_rate": 4.090947871342036e-06, "loss": 0.4452, "step": 10763 }, { "epoch": 2.7552, "grad_norm": 1.765625, "learning_rate": 4.086682023718113e-06, "loss": 0.4281, "step": 10764 }, { "epoch": 2.755456, "grad_norm": 1.7578125, "learning_rate": 4.0824161760941895e-06, "loss": 0.393, "step": 10765 }, { "epoch": 2.755712, "grad_norm": 1.65625, "learning_rate": 4.078150328470267e-06, "loss": 0.421, "step": 10766 }, { "epoch": 2.755968, "grad_norm": 1.7109375, "learning_rate": 4.073884480846344e-06, "loss": 0.4449, "step": 10767 }, { "epoch": 2.756224, "grad_norm": 1.7421875, "learning_rate": 4.069618633222422e-06, "loss": 0.4161, "step": 10768 }, { "epoch": 2.75648, "grad_norm": 1.6640625, "learning_rate": 4.0653527855984985e-06, "loss": 0.4113, "step": 10769 }, { "epoch": 2.756736, "grad_norm": 1.8359375, "learning_rate": 4.061086937974576e-06, "loss": 0.4345, "step": 10770 }, { "epoch": 2.756992, "grad_norm": 1.71875, "learning_rate": 4.056821090350653e-06, "loss": 0.4376, "step": 10771 }, { "epoch": 2.757248, "grad_norm": 1.75, "learning_rate": 4.05255524272673e-06, "loss": 0.4432, "step": 10772 }, { "epoch": 2.757504, "grad_norm": 1.6953125, "learning_rate": 4.048289395102807e-06, "loss": 0.4403, "step": 10773 }, { "epoch": 2.75776, "grad_norm": 1.7578125, "learning_rate": 4.044023547478884e-06, "loss": 0.4352, "step": 10774 }, { "epoch": 2.758016, "grad_norm": 1.7890625, "learning_rate": 4.039757699854961e-06, "loss": 0.4541, "step": 10775 }, { "epoch": 2.758272, "grad_norm": 1.828125, "learning_rate": 4.035491852231039e-06, "loss": 0.4474, "step": 10776 }, { "epoch": 2.758528, "grad_norm": 1.8359375, "learning_rate": 4.0312260046071155e-06, "loss": 0.4179, "step": 10777 }, { "epoch": 2.758784, "grad_norm": 1.671875, "learning_rate": 4.026960156983193e-06, "loss": 0.4314, "step": 10778 }, { "epoch": 2.75904, "grad_norm": 1.8125, "learning_rate": 4.02269430935927e-06, "loss": 0.4028, "step": 10779 }, { "epoch": 2.759296, "grad_norm": 1.796875, "learning_rate": 4.018428461735347e-06, "loss": 0.4044, "step": 10780 }, { "epoch": 2.7595520000000002, "grad_norm": 1.6640625, "learning_rate": 4.014162614111424e-06, "loss": 0.439, "step": 10781 }, { "epoch": 2.759808, "grad_norm": 1.703125, "learning_rate": 4.009896766487501e-06, "loss": 0.3953, "step": 10782 }, { "epoch": 2.760064, "grad_norm": 1.7109375, "learning_rate": 4.005630918863578e-06, "loss": 0.4016, "step": 10783 }, { "epoch": 2.76032, "grad_norm": 1.7578125, "learning_rate": 4.001365071239656e-06, "loss": 0.4477, "step": 10784 }, { "epoch": 2.760576, "grad_norm": 1.90625, "learning_rate": 3.9970992236157325e-06, "loss": 0.4245, "step": 10785 }, { "epoch": 2.7608319999999997, "grad_norm": 1.71875, "learning_rate": 3.99283337599181e-06, "loss": 0.448, "step": 10786 }, { "epoch": 2.761088, "grad_norm": 1.6328125, "learning_rate": 3.988567528367887e-06, "loss": 0.429, "step": 10787 }, { "epoch": 2.7613440000000002, "grad_norm": 1.8203125, "learning_rate": 3.984301680743964e-06, "loss": 0.4357, "step": 10788 }, { "epoch": 2.7616, "grad_norm": 1.6640625, "learning_rate": 3.980035833120041e-06, "loss": 0.4014, "step": 10789 }, { "epoch": 2.761856, "grad_norm": 1.71875, "learning_rate": 3.975769985496118e-06, "loss": 0.4279, "step": 10790 }, { "epoch": 2.762112, "grad_norm": 1.6328125, "learning_rate": 3.971504137872195e-06, "loss": 0.436, "step": 10791 }, { "epoch": 2.762368, "grad_norm": 1.65625, "learning_rate": 3.967238290248273e-06, "loss": 0.4085, "step": 10792 }, { "epoch": 2.7626239999999997, "grad_norm": 1.7578125, "learning_rate": 3.96297244262435e-06, "loss": 0.4216, "step": 10793 }, { "epoch": 2.76288, "grad_norm": 1.671875, "learning_rate": 3.958706595000427e-06, "loss": 0.417, "step": 10794 }, { "epoch": 2.7631360000000003, "grad_norm": 1.703125, "learning_rate": 3.954440747376504e-06, "loss": 0.4297, "step": 10795 }, { "epoch": 2.763392, "grad_norm": 1.71875, "learning_rate": 3.950174899752581e-06, "loss": 0.3804, "step": 10796 }, { "epoch": 2.763648, "grad_norm": 1.75, "learning_rate": 3.945909052128658e-06, "loss": 0.4527, "step": 10797 }, { "epoch": 2.763904, "grad_norm": 1.703125, "learning_rate": 3.941643204504735e-06, "loss": 0.4266, "step": 10798 }, { "epoch": 2.76416, "grad_norm": 1.8125, "learning_rate": 3.937377356880812e-06, "loss": 0.457, "step": 10799 }, { "epoch": 2.7644159999999998, "grad_norm": 1.71875, "learning_rate": 3.93311150925689e-06, "loss": 0.4411, "step": 10800 }, { "epoch": 2.764672, "grad_norm": 1.828125, "learning_rate": 3.928845661632967e-06, "loss": 0.3979, "step": 10801 }, { "epoch": 2.7649280000000003, "grad_norm": 1.7578125, "learning_rate": 3.924579814009044e-06, "loss": 0.395, "step": 10802 }, { "epoch": 2.765184, "grad_norm": 1.75, "learning_rate": 3.920313966385121e-06, "loss": 0.3945, "step": 10803 }, { "epoch": 2.76544, "grad_norm": 1.828125, "learning_rate": 3.916048118761198e-06, "loss": 0.4383, "step": 10804 }, { "epoch": 2.765696, "grad_norm": 1.7578125, "learning_rate": 3.911782271137275e-06, "loss": 0.4429, "step": 10805 }, { "epoch": 2.765952, "grad_norm": 1.9609375, "learning_rate": 3.907516423513352e-06, "loss": 0.4466, "step": 10806 }, { "epoch": 2.766208, "grad_norm": 1.8203125, "learning_rate": 3.903250575889429e-06, "loss": 0.4531, "step": 10807 }, { "epoch": 2.766464, "grad_norm": 1.6796875, "learning_rate": 3.898984728265506e-06, "loss": 0.4069, "step": 10808 }, { "epoch": 2.76672, "grad_norm": 1.7265625, "learning_rate": 3.894718880641584e-06, "loss": 0.4067, "step": 10809 }, { "epoch": 2.766976, "grad_norm": 1.7265625, "learning_rate": 3.890453033017661e-06, "loss": 0.4434, "step": 10810 }, { "epoch": 2.767232, "grad_norm": 1.7578125, "learning_rate": 3.886187185393738e-06, "loss": 0.4639, "step": 10811 }, { "epoch": 2.767488, "grad_norm": 1.6875, "learning_rate": 3.881921337769815e-06, "loss": 0.4248, "step": 10812 }, { "epoch": 2.767744, "grad_norm": 1.640625, "learning_rate": 3.877655490145892e-06, "loss": 0.4515, "step": 10813 }, { "epoch": 2.768, "grad_norm": 1.8828125, "learning_rate": 3.873389642521969e-06, "loss": 0.4436, "step": 10814 }, { "epoch": 2.768256, "grad_norm": 1.7265625, "learning_rate": 3.869123794898046e-06, "loss": 0.4186, "step": 10815 }, { "epoch": 2.768512, "grad_norm": 1.7109375, "learning_rate": 3.864857947274124e-06, "loss": 0.4314, "step": 10816 }, { "epoch": 2.768768, "grad_norm": 1.84375, "learning_rate": 3.860592099650201e-06, "loss": 0.3983, "step": 10817 }, { "epoch": 2.769024, "grad_norm": 1.6640625, "learning_rate": 3.856326252026278e-06, "loss": 0.4234, "step": 10818 }, { "epoch": 2.76928, "grad_norm": 1.8125, "learning_rate": 3.852060404402355e-06, "loss": 0.4037, "step": 10819 }, { "epoch": 2.769536, "grad_norm": 1.7578125, "learning_rate": 3.847794556778432e-06, "loss": 0.4264, "step": 10820 }, { "epoch": 2.769792, "grad_norm": 1.7265625, "learning_rate": 3.843528709154509e-06, "loss": 0.3846, "step": 10821 }, { "epoch": 2.770048, "grad_norm": 1.6953125, "learning_rate": 3.839262861530586e-06, "loss": 0.4048, "step": 10822 }, { "epoch": 2.770304, "grad_norm": 1.8203125, "learning_rate": 3.834997013906663e-06, "loss": 0.4361, "step": 10823 }, { "epoch": 2.77056, "grad_norm": 1.6796875, "learning_rate": 3.830731166282741e-06, "loss": 0.3885, "step": 10824 }, { "epoch": 2.770816, "grad_norm": 1.6796875, "learning_rate": 3.826465318658818e-06, "loss": 0.4161, "step": 10825 }, { "epoch": 2.771072, "grad_norm": 1.6796875, "learning_rate": 3.822199471034895e-06, "loss": 0.4259, "step": 10826 }, { "epoch": 2.771328, "grad_norm": 1.5390625, "learning_rate": 3.817933623410972e-06, "loss": 0.441, "step": 10827 }, { "epoch": 2.771584, "grad_norm": 1.640625, "learning_rate": 3.813667775787049e-06, "loss": 0.4324, "step": 10828 }, { "epoch": 2.77184, "grad_norm": 1.7578125, "learning_rate": 3.809401928163126e-06, "loss": 0.442, "step": 10829 }, { "epoch": 2.772096, "grad_norm": 1.6640625, "learning_rate": 3.805136080539203e-06, "loss": 0.4132, "step": 10830 }, { "epoch": 2.772352, "grad_norm": 1.7734375, "learning_rate": 3.8008702329152804e-06, "loss": 0.3977, "step": 10831 }, { "epoch": 2.772608, "grad_norm": 1.7421875, "learning_rate": 3.7966043852913572e-06, "loss": 0.3942, "step": 10832 }, { "epoch": 2.772864, "grad_norm": 1.8515625, "learning_rate": 3.792338537667435e-06, "loss": 0.4504, "step": 10833 }, { "epoch": 2.77312, "grad_norm": 1.6875, "learning_rate": 3.788072690043512e-06, "loss": 0.4368, "step": 10834 }, { "epoch": 2.773376, "grad_norm": 1.8515625, "learning_rate": 3.783806842419589e-06, "loss": 0.4076, "step": 10835 }, { "epoch": 2.773632, "grad_norm": 1.75, "learning_rate": 3.779540994795666e-06, "loss": 0.4636, "step": 10836 }, { "epoch": 2.773888, "grad_norm": 1.796875, "learning_rate": 3.7752751471717434e-06, "loss": 0.4323, "step": 10837 }, { "epoch": 2.774144, "grad_norm": 1.7421875, "learning_rate": 3.77100929954782e-06, "loss": 0.4088, "step": 10838 }, { "epoch": 2.7744, "grad_norm": 1.8515625, "learning_rate": 3.7667434519238974e-06, "loss": 0.4503, "step": 10839 }, { "epoch": 2.7746560000000002, "grad_norm": 1.609375, "learning_rate": 3.7624776042999742e-06, "loss": 0.3942, "step": 10840 }, { "epoch": 2.774912, "grad_norm": 1.703125, "learning_rate": 3.758211756676052e-06, "loss": 0.439, "step": 10841 }, { "epoch": 2.775168, "grad_norm": 1.765625, "learning_rate": 3.753945909052129e-06, "loss": 0.439, "step": 10842 }, { "epoch": 2.775424, "grad_norm": 1.8125, "learning_rate": 3.7496800614282063e-06, "loss": 0.4208, "step": 10843 }, { "epoch": 2.77568, "grad_norm": 1.78125, "learning_rate": 3.745414213804283e-06, "loss": 0.4525, "step": 10844 }, { "epoch": 2.7759359999999997, "grad_norm": 1.84375, "learning_rate": 3.7411483661803604e-06, "loss": 0.4055, "step": 10845 }, { "epoch": 2.776192, "grad_norm": 1.7265625, "learning_rate": 3.736882518556437e-06, "loss": 0.4251, "step": 10846 }, { "epoch": 2.7764480000000002, "grad_norm": 1.765625, "learning_rate": 3.7326166709325144e-06, "loss": 0.4405, "step": 10847 }, { "epoch": 2.776704, "grad_norm": 1.859375, "learning_rate": 3.7283508233085912e-06, "loss": 0.4311, "step": 10848 }, { "epoch": 2.77696, "grad_norm": 1.7734375, "learning_rate": 3.7240849756846685e-06, "loss": 0.4075, "step": 10849 }, { "epoch": 2.777216, "grad_norm": 1.6796875, "learning_rate": 3.719819128060746e-06, "loss": 0.4378, "step": 10850 }, { "epoch": 2.777472, "grad_norm": 1.65625, "learning_rate": 3.7155532804368233e-06, "loss": 0.4318, "step": 10851 }, { "epoch": 2.7777279999999998, "grad_norm": 1.859375, "learning_rate": 3.7112874328129e-06, "loss": 0.4082, "step": 10852 }, { "epoch": 2.777984, "grad_norm": 1.734375, "learning_rate": 3.7070215851889774e-06, "loss": 0.4083, "step": 10853 }, { "epoch": 2.7782400000000003, "grad_norm": 1.6328125, "learning_rate": 3.702755737565054e-06, "loss": 0.4424, "step": 10854 }, { "epoch": 2.778496, "grad_norm": 1.7890625, "learning_rate": 3.6984898899411314e-06, "loss": 0.4251, "step": 10855 }, { "epoch": 2.778752, "grad_norm": 1.671875, "learning_rate": 3.6942240423172082e-06, "loss": 0.4464, "step": 10856 }, { "epoch": 2.779008, "grad_norm": 1.7421875, "learning_rate": 3.6899581946932855e-06, "loss": 0.4035, "step": 10857 }, { "epoch": 2.779264, "grad_norm": 1.6171875, "learning_rate": 3.685692347069363e-06, "loss": 0.4512, "step": 10858 }, { "epoch": 2.7795199999999998, "grad_norm": 1.6484375, "learning_rate": 3.6814264994454403e-06, "loss": 0.4106, "step": 10859 }, { "epoch": 2.779776, "grad_norm": 1.7109375, "learning_rate": 3.677160651821517e-06, "loss": 0.4349, "step": 10860 }, { "epoch": 2.780032, "grad_norm": 1.8359375, "learning_rate": 3.6728948041975944e-06, "loss": 0.4149, "step": 10861 }, { "epoch": 2.780288, "grad_norm": 1.7109375, "learning_rate": 3.668628956573671e-06, "loss": 0.4399, "step": 10862 }, { "epoch": 2.780544, "grad_norm": 1.765625, "learning_rate": 3.6643631089497484e-06, "loss": 0.4049, "step": 10863 }, { "epoch": 2.7808, "grad_norm": 1.7734375, "learning_rate": 3.6600972613258252e-06, "loss": 0.3965, "step": 10864 }, { "epoch": 2.781056, "grad_norm": 1.71875, "learning_rate": 3.6558314137019025e-06, "loss": 0.4243, "step": 10865 }, { "epoch": 2.781312, "grad_norm": 1.6796875, "learning_rate": 3.65156556607798e-06, "loss": 0.414, "step": 10866 }, { "epoch": 2.781568, "grad_norm": 1.796875, "learning_rate": 3.6472997184540573e-06, "loss": 0.4179, "step": 10867 }, { "epoch": 2.781824, "grad_norm": 1.7421875, "learning_rate": 3.643033870830134e-06, "loss": 0.4305, "step": 10868 }, { "epoch": 2.78208, "grad_norm": 1.6484375, "learning_rate": 3.6387680232062114e-06, "loss": 0.4353, "step": 10869 }, { "epoch": 2.782336, "grad_norm": 1.8359375, "learning_rate": 3.634502175582288e-06, "loss": 0.42, "step": 10870 }, { "epoch": 2.782592, "grad_norm": 1.6640625, "learning_rate": 3.6302363279583654e-06, "loss": 0.4217, "step": 10871 }, { "epoch": 2.782848, "grad_norm": 1.7265625, "learning_rate": 3.6259704803344422e-06, "loss": 0.4075, "step": 10872 }, { "epoch": 2.783104, "grad_norm": 1.78125, "learning_rate": 3.6217046327105195e-06, "loss": 0.431, "step": 10873 }, { "epoch": 2.78336, "grad_norm": 1.71875, "learning_rate": 3.617438785086597e-06, "loss": 0.4159, "step": 10874 }, { "epoch": 2.783616, "grad_norm": 1.7109375, "learning_rate": 3.6131729374626743e-06, "loss": 0.4018, "step": 10875 }, { "epoch": 2.783872, "grad_norm": 1.765625, "learning_rate": 3.608907089838751e-06, "loss": 0.449, "step": 10876 }, { "epoch": 2.784128, "grad_norm": 1.71875, "learning_rate": 3.6046412422148284e-06, "loss": 0.4089, "step": 10877 }, { "epoch": 2.784384, "grad_norm": 1.875, "learning_rate": 3.600375394590905e-06, "loss": 0.4089, "step": 10878 }, { "epoch": 2.78464, "grad_norm": 1.796875, "learning_rate": 3.5961095469669824e-06, "loss": 0.4076, "step": 10879 }, { "epoch": 2.784896, "grad_norm": 1.75, "learning_rate": 3.5918436993430597e-06, "loss": 0.4222, "step": 10880 }, { "epoch": 2.785152, "grad_norm": 1.578125, "learning_rate": 3.5875778517191365e-06, "loss": 0.4445, "step": 10881 }, { "epoch": 2.785408, "grad_norm": 1.6640625, "learning_rate": 3.583312004095214e-06, "loss": 0.4227, "step": 10882 }, { "epoch": 2.785664, "grad_norm": 1.8984375, "learning_rate": 3.5790461564712913e-06, "loss": 0.4007, "step": 10883 }, { "epoch": 2.78592, "grad_norm": 1.796875, "learning_rate": 3.574780308847368e-06, "loss": 0.3813, "step": 10884 }, { "epoch": 2.786176, "grad_norm": 1.6953125, "learning_rate": 3.5705144612234454e-06, "loss": 0.4349, "step": 10885 }, { "epoch": 2.786432, "grad_norm": 1.703125, "learning_rate": 3.566248613599522e-06, "loss": 0.4396, "step": 10886 }, { "epoch": 2.786688, "grad_norm": 1.8125, "learning_rate": 3.5619827659755994e-06, "loss": 0.4062, "step": 10887 }, { "epoch": 2.786944, "grad_norm": 1.7890625, "learning_rate": 3.5577169183516767e-06, "loss": 0.4221, "step": 10888 }, { "epoch": 2.7872, "grad_norm": 1.8359375, "learning_rate": 3.5534510707277535e-06, "loss": 0.3881, "step": 10889 }, { "epoch": 2.787456, "grad_norm": 1.7421875, "learning_rate": 3.5491852231038307e-06, "loss": 0.4401, "step": 10890 }, { "epoch": 2.787712, "grad_norm": 1.8359375, "learning_rate": 3.5449193754799083e-06, "loss": 0.414, "step": 10891 }, { "epoch": 2.7879680000000002, "grad_norm": 1.7421875, "learning_rate": 3.540653527855985e-06, "loss": 0.4426, "step": 10892 }, { "epoch": 2.788224, "grad_norm": 1.6953125, "learning_rate": 3.5363876802320624e-06, "loss": 0.4267, "step": 10893 }, { "epoch": 2.78848, "grad_norm": 1.671875, "learning_rate": 3.5321218326081396e-06, "loss": 0.4076, "step": 10894 }, { "epoch": 2.788736, "grad_norm": 1.765625, "learning_rate": 3.5278559849842164e-06, "loss": 0.4449, "step": 10895 }, { "epoch": 2.788992, "grad_norm": 1.828125, "learning_rate": 3.5235901373602937e-06, "loss": 0.4076, "step": 10896 }, { "epoch": 2.7892479999999997, "grad_norm": 1.6015625, "learning_rate": 3.5193242897363705e-06, "loss": 0.4182, "step": 10897 }, { "epoch": 2.789504, "grad_norm": 1.6796875, "learning_rate": 3.5150584421124477e-06, "loss": 0.4281, "step": 10898 }, { "epoch": 2.7897600000000002, "grad_norm": 1.6640625, "learning_rate": 3.5107925944885253e-06, "loss": 0.4118, "step": 10899 }, { "epoch": 2.790016, "grad_norm": 1.7734375, "learning_rate": 3.506526746864602e-06, "loss": 0.4191, "step": 10900 }, { "epoch": 2.790272, "grad_norm": 1.640625, "learning_rate": 3.5022608992406794e-06, "loss": 0.4105, "step": 10901 }, { "epoch": 2.790528, "grad_norm": 1.734375, "learning_rate": 3.4979950516167566e-06, "loss": 0.4076, "step": 10902 }, { "epoch": 2.790784, "grad_norm": 1.671875, "learning_rate": 3.4937292039928334e-06, "loss": 0.3998, "step": 10903 }, { "epoch": 2.7910399999999997, "grad_norm": 1.7890625, "learning_rate": 3.4894633563689107e-06, "loss": 0.4214, "step": 10904 }, { "epoch": 2.791296, "grad_norm": 1.8515625, "learning_rate": 3.4851975087449875e-06, "loss": 0.4299, "step": 10905 }, { "epoch": 2.7915520000000003, "grad_norm": 1.8125, "learning_rate": 3.4809316611210647e-06, "loss": 0.4294, "step": 10906 }, { "epoch": 2.791808, "grad_norm": 1.625, "learning_rate": 3.4766658134971423e-06, "loss": 0.4406, "step": 10907 }, { "epoch": 2.792064, "grad_norm": 1.7578125, "learning_rate": 3.4723999658732196e-06, "loss": 0.4383, "step": 10908 }, { "epoch": 2.79232, "grad_norm": 1.8046875, "learning_rate": 3.4681341182492964e-06, "loss": 0.4592, "step": 10909 }, { "epoch": 2.792576, "grad_norm": 1.828125, "learning_rate": 3.4638682706253736e-06, "loss": 0.4375, "step": 10910 }, { "epoch": 2.7928319999999998, "grad_norm": 1.6484375, "learning_rate": 3.4596024230014504e-06, "loss": 0.4017, "step": 10911 }, { "epoch": 2.793088, "grad_norm": 1.78125, "learning_rate": 3.4553365753775277e-06, "loss": 0.4269, "step": 10912 }, { "epoch": 2.7933440000000003, "grad_norm": 1.765625, "learning_rate": 3.4510707277536045e-06, "loss": 0.3982, "step": 10913 }, { "epoch": 2.7936, "grad_norm": 1.7734375, "learning_rate": 3.4468048801296817e-06, "loss": 0.4316, "step": 10914 }, { "epoch": 2.793856, "grad_norm": 1.7890625, "learning_rate": 3.4425390325057593e-06, "loss": 0.4006, "step": 10915 }, { "epoch": 2.794112, "grad_norm": 1.71875, "learning_rate": 3.4382731848818366e-06, "loss": 0.4339, "step": 10916 }, { "epoch": 2.794368, "grad_norm": 1.75, "learning_rate": 3.4340073372579134e-06, "loss": 0.3937, "step": 10917 }, { "epoch": 2.7946239999999998, "grad_norm": 1.7265625, "learning_rate": 3.4297414896339906e-06, "loss": 0.4573, "step": 10918 }, { "epoch": 2.79488, "grad_norm": 1.703125, "learning_rate": 3.4254756420100674e-06, "loss": 0.4047, "step": 10919 }, { "epoch": 2.795136, "grad_norm": 1.7421875, "learning_rate": 3.4212097943861447e-06, "loss": 0.4249, "step": 10920 }, { "epoch": 2.795392, "grad_norm": 1.8359375, "learning_rate": 3.4169439467622215e-06, "loss": 0.4234, "step": 10921 }, { "epoch": 2.795648, "grad_norm": 1.703125, "learning_rate": 3.4126780991382987e-06, "loss": 0.4193, "step": 10922 }, { "epoch": 2.795904, "grad_norm": 1.7421875, "learning_rate": 3.4084122515143763e-06, "loss": 0.4336, "step": 10923 }, { "epoch": 2.79616, "grad_norm": 1.765625, "learning_rate": 3.4041464038904536e-06, "loss": 0.4107, "step": 10924 }, { "epoch": 2.796416, "grad_norm": 1.703125, "learning_rate": 3.3998805562665304e-06, "loss": 0.4292, "step": 10925 }, { "epoch": 2.796672, "grad_norm": 1.6796875, "learning_rate": 3.3956147086426076e-06, "loss": 0.4214, "step": 10926 }, { "epoch": 2.796928, "grad_norm": 1.6796875, "learning_rate": 3.3913488610186844e-06, "loss": 0.4294, "step": 10927 }, { "epoch": 2.797184, "grad_norm": 1.6953125, "learning_rate": 3.3870830133947617e-06, "loss": 0.3665, "step": 10928 }, { "epoch": 2.79744, "grad_norm": 1.78125, "learning_rate": 3.3828171657708385e-06, "loss": 0.4723, "step": 10929 }, { "epoch": 2.797696, "grad_norm": 1.8203125, "learning_rate": 3.3785513181469157e-06, "loss": 0.4041, "step": 10930 }, { "epoch": 2.797952, "grad_norm": 1.6015625, "learning_rate": 3.374285470522993e-06, "loss": 0.4267, "step": 10931 }, { "epoch": 2.798208, "grad_norm": 1.765625, "learning_rate": 3.3700196228990706e-06, "loss": 0.4205, "step": 10932 }, { "epoch": 2.798464, "grad_norm": 1.7421875, "learning_rate": 3.3657537752751474e-06, "loss": 0.444, "step": 10933 }, { "epoch": 2.79872, "grad_norm": 1.796875, "learning_rate": 3.3614879276512246e-06, "loss": 0.4125, "step": 10934 }, { "epoch": 2.798976, "grad_norm": 1.8828125, "learning_rate": 3.3572220800273014e-06, "loss": 0.4289, "step": 10935 }, { "epoch": 2.799232, "grad_norm": 1.7265625, "learning_rate": 3.3529562324033787e-06, "loss": 0.4012, "step": 10936 }, { "epoch": 2.799488, "grad_norm": 1.7265625, "learning_rate": 3.348690384779456e-06, "loss": 0.3676, "step": 10937 }, { "epoch": 2.799744, "grad_norm": 1.8671875, "learning_rate": 3.3444245371555327e-06, "loss": 0.4195, "step": 10938 }, { "epoch": 2.8, "grad_norm": 1.875, "learning_rate": 3.34015868953161e-06, "loss": 0.4417, "step": 10939 }, { "epoch": 2.800256, "grad_norm": 1.6640625, "learning_rate": 3.3358928419076876e-06, "loss": 0.4156, "step": 10940 }, { "epoch": 2.800512, "grad_norm": 1.7890625, "learning_rate": 3.3316269942837644e-06, "loss": 0.3936, "step": 10941 }, { "epoch": 2.800768, "grad_norm": 1.6953125, "learning_rate": 3.3273611466598416e-06, "loss": 0.4185, "step": 10942 }, { "epoch": 2.801024, "grad_norm": 1.6953125, "learning_rate": 3.3230952990359184e-06, "loss": 0.4194, "step": 10943 }, { "epoch": 2.80128, "grad_norm": 1.765625, "learning_rate": 3.3188294514119957e-06, "loss": 0.409, "step": 10944 }, { "epoch": 2.801536, "grad_norm": 1.6953125, "learning_rate": 3.314563603788073e-06, "loss": 0.4501, "step": 10945 }, { "epoch": 2.801792, "grad_norm": 1.7265625, "learning_rate": 3.3102977561641497e-06, "loss": 0.4289, "step": 10946 }, { "epoch": 2.802048, "grad_norm": 1.671875, "learning_rate": 3.306031908540227e-06, "loss": 0.4335, "step": 10947 }, { "epoch": 2.802304, "grad_norm": 1.8828125, "learning_rate": 3.3017660609163046e-06, "loss": 0.4171, "step": 10948 }, { "epoch": 2.80256, "grad_norm": 1.828125, "learning_rate": 3.2975002132923814e-06, "loss": 0.4324, "step": 10949 }, { "epoch": 2.802816, "grad_norm": 1.734375, "learning_rate": 3.2932343656684586e-06, "loss": 0.4214, "step": 10950 }, { "epoch": 2.8030720000000002, "grad_norm": 1.765625, "learning_rate": 3.288968518044536e-06, "loss": 0.429, "step": 10951 }, { "epoch": 2.803328, "grad_norm": 1.8515625, "learning_rate": 3.2847026704206127e-06, "loss": 0.4249, "step": 10952 }, { "epoch": 2.803584, "grad_norm": 1.6484375, "learning_rate": 3.28043682279669e-06, "loss": 0.4403, "step": 10953 }, { "epoch": 2.80384, "grad_norm": 1.703125, "learning_rate": 3.2761709751727667e-06, "loss": 0.4334, "step": 10954 }, { "epoch": 2.804096, "grad_norm": 1.6171875, "learning_rate": 3.271905127548844e-06, "loss": 0.447, "step": 10955 }, { "epoch": 2.8043519999999997, "grad_norm": 1.84375, "learning_rate": 3.2676392799249216e-06, "loss": 0.4031, "step": 10956 }, { "epoch": 2.804608, "grad_norm": 1.7109375, "learning_rate": 3.2633734323009984e-06, "loss": 0.3763, "step": 10957 }, { "epoch": 2.8048640000000002, "grad_norm": 1.75, "learning_rate": 3.2591075846770756e-06, "loss": 0.4679, "step": 10958 }, { "epoch": 2.80512, "grad_norm": 1.796875, "learning_rate": 3.254841737053153e-06, "loss": 0.4018, "step": 10959 }, { "epoch": 2.805376, "grad_norm": 1.8359375, "learning_rate": 3.2505758894292297e-06, "loss": 0.4074, "step": 10960 }, { "epoch": 2.805632, "grad_norm": 1.7421875, "learning_rate": 3.246310041805307e-06, "loss": 0.4396, "step": 10961 }, { "epoch": 2.805888, "grad_norm": 1.7265625, "learning_rate": 3.2420441941813837e-06, "loss": 0.4753, "step": 10962 }, { "epoch": 2.8061439999999997, "grad_norm": 1.6875, "learning_rate": 3.237778346557461e-06, "loss": 0.4049, "step": 10963 }, { "epoch": 2.8064, "grad_norm": 1.671875, "learning_rate": 3.2335124989335386e-06, "loss": 0.4398, "step": 10964 }, { "epoch": 2.8066560000000003, "grad_norm": 1.6328125, "learning_rate": 3.229246651309616e-06, "loss": 0.4165, "step": 10965 }, { "epoch": 2.806912, "grad_norm": 1.6640625, "learning_rate": 3.2249808036856926e-06, "loss": 0.4144, "step": 10966 }, { "epoch": 2.807168, "grad_norm": 1.671875, "learning_rate": 3.22071495606177e-06, "loss": 0.4289, "step": 10967 }, { "epoch": 2.807424, "grad_norm": 1.7421875, "learning_rate": 3.2164491084378467e-06, "loss": 0.4221, "step": 10968 }, { "epoch": 2.80768, "grad_norm": 1.7734375, "learning_rate": 3.212183260813924e-06, "loss": 0.4289, "step": 10969 }, { "epoch": 2.8079359999999998, "grad_norm": 1.734375, "learning_rate": 3.2079174131900007e-06, "loss": 0.3876, "step": 10970 }, { "epoch": 2.808192, "grad_norm": 1.6875, "learning_rate": 3.203651565566078e-06, "loss": 0.424, "step": 10971 }, { "epoch": 2.8084480000000003, "grad_norm": 1.75, "learning_rate": 3.1993857179421547e-06, "loss": 0.4664, "step": 10972 }, { "epoch": 2.808704, "grad_norm": 1.8203125, "learning_rate": 3.195119870318233e-06, "loss": 0.4361, "step": 10973 }, { "epoch": 2.80896, "grad_norm": 1.65625, "learning_rate": 3.1908540226943096e-06, "loss": 0.4396, "step": 10974 }, { "epoch": 2.809216, "grad_norm": 1.7578125, "learning_rate": 3.186588175070387e-06, "loss": 0.4183, "step": 10975 }, { "epoch": 2.809472, "grad_norm": 1.859375, "learning_rate": 3.1823223274464637e-06, "loss": 0.4494, "step": 10976 }, { "epoch": 2.809728, "grad_norm": 1.6171875, "learning_rate": 3.178056479822541e-06, "loss": 0.4514, "step": 10977 }, { "epoch": 2.809984, "grad_norm": 1.71875, "learning_rate": 3.1737906321986177e-06, "loss": 0.4322, "step": 10978 }, { "epoch": 2.81024, "grad_norm": 1.75, "learning_rate": 3.169524784574695e-06, "loss": 0.413, "step": 10979 }, { "epoch": 2.810496, "grad_norm": 1.703125, "learning_rate": 3.1652589369507717e-06, "loss": 0.3932, "step": 10980 }, { "epoch": 2.810752, "grad_norm": 1.7265625, "learning_rate": 3.16099308932685e-06, "loss": 0.4406, "step": 10981 }, { "epoch": 2.811008, "grad_norm": 1.703125, "learning_rate": 3.1567272417029266e-06, "loss": 0.4074, "step": 10982 }, { "epoch": 2.811264, "grad_norm": 1.6015625, "learning_rate": 3.152461394079004e-06, "loss": 0.3963, "step": 10983 }, { "epoch": 2.81152, "grad_norm": 1.6796875, "learning_rate": 3.1481955464550807e-06, "loss": 0.4428, "step": 10984 }, { "epoch": 2.811776, "grad_norm": 1.8203125, "learning_rate": 3.143929698831158e-06, "loss": 0.4412, "step": 10985 }, { "epoch": 2.812032, "grad_norm": 1.65625, "learning_rate": 3.1396638512072347e-06, "loss": 0.4216, "step": 10986 }, { "epoch": 2.812288, "grad_norm": 1.7578125, "learning_rate": 3.135398003583312e-06, "loss": 0.413, "step": 10987 }, { "epoch": 2.812544, "grad_norm": 1.625, "learning_rate": 3.131132155959389e-06, "loss": 0.4189, "step": 10988 }, { "epoch": 2.8128, "grad_norm": 1.7421875, "learning_rate": 3.126866308335467e-06, "loss": 0.3891, "step": 10989 }, { "epoch": 2.813056, "grad_norm": 1.7578125, "learning_rate": 3.122600460711543e-06, "loss": 0.4524, "step": 10990 }, { "epoch": 2.813312, "grad_norm": 1.671875, "learning_rate": 3.118334613087621e-06, "loss": 0.4135, "step": 10991 }, { "epoch": 2.813568, "grad_norm": 1.8046875, "learning_rate": 3.1140687654636977e-06, "loss": 0.4484, "step": 10992 }, { "epoch": 2.813824, "grad_norm": 1.703125, "learning_rate": 3.109802917839775e-06, "loss": 0.4268, "step": 10993 }, { "epoch": 2.81408, "grad_norm": 1.703125, "learning_rate": 3.105537070215852e-06, "loss": 0.428, "step": 10994 }, { "epoch": 2.814336, "grad_norm": 1.7109375, "learning_rate": 3.1012712225919293e-06, "loss": 0.4076, "step": 10995 }, { "epoch": 2.814592, "grad_norm": 1.828125, "learning_rate": 3.097005374968006e-06, "loss": 0.4139, "step": 10996 }, { "epoch": 2.814848, "grad_norm": 1.7265625, "learning_rate": 3.0927395273440834e-06, "loss": 0.416, "step": 10997 }, { "epoch": 2.815104, "grad_norm": 1.796875, "learning_rate": 3.0884736797201606e-06, "loss": 0.4127, "step": 10998 }, { "epoch": 2.81536, "grad_norm": 1.6640625, "learning_rate": 3.084207832096238e-06, "loss": 0.3922, "step": 10999 }, { "epoch": 2.815616, "grad_norm": 1.7109375, "learning_rate": 3.0799419844723147e-06, "loss": 0.434, "step": 11000 }, { "epoch": 2.815872, "grad_norm": 1.625, "learning_rate": 3.075676136848392e-06, "loss": 0.4248, "step": 11001 }, { "epoch": 2.816128, "grad_norm": 1.7109375, "learning_rate": 3.071410289224469e-06, "loss": 0.4176, "step": 11002 }, { "epoch": 2.816384, "grad_norm": 1.7890625, "learning_rate": 3.0671444416005464e-06, "loss": 0.439, "step": 11003 }, { "epoch": 2.81664, "grad_norm": 1.7421875, "learning_rate": 3.0628785939766236e-06, "loss": 0.4104, "step": 11004 }, { "epoch": 2.816896, "grad_norm": 1.71875, "learning_rate": 3.0586127463527004e-06, "loss": 0.4205, "step": 11005 }, { "epoch": 2.817152, "grad_norm": 1.640625, "learning_rate": 3.0543468987287776e-06, "loss": 0.4581, "step": 11006 }, { "epoch": 2.817408, "grad_norm": 1.71875, "learning_rate": 3.050081051104855e-06, "loss": 0.4276, "step": 11007 }, { "epoch": 2.8176639999999997, "grad_norm": 1.6953125, "learning_rate": 3.045815203480932e-06, "loss": 0.4174, "step": 11008 }, { "epoch": 2.81792, "grad_norm": 1.65625, "learning_rate": 3.041549355857009e-06, "loss": 0.4506, "step": 11009 }, { "epoch": 2.8181760000000002, "grad_norm": 1.78125, "learning_rate": 3.037283508233086e-06, "loss": 0.4064, "step": 11010 }, { "epoch": 2.818432, "grad_norm": 1.8046875, "learning_rate": 3.0330176606091634e-06, "loss": 0.3946, "step": 11011 }, { "epoch": 2.818688, "grad_norm": 1.6015625, "learning_rate": 3.0287518129852406e-06, "loss": 0.4284, "step": 11012 }, { "epoch": 2.818944, "grad_norm": 1.5859375, "learning_rate": 3.0244859653613174e-06, "loss": 0.4099, "step": 11013 }, { "epoch": 2.8192, "grad_norm": 1.7421875, "learning_rate": 3.0202201177373946e-06, "loss": 0.4038, "step": 11014 }, { "epoch": 2.8194559999999997, "grad_norm": 1.78125, "learning_rate": 3.0159542701134714e-06, "loss": 0.3946, "step": 11015 }, { "epoch": 2.819712, "grad_norm": 1.7578125, "learning_rate": 3.011688422489549e-06, "loss": 0.4153, "step": 11016 }, { "epoch": 2.8199680000000003, "grad_norm": 1.65625, "learning_rate": 3.007422574865626e-06, "loss": 0.4388, "step": 11017 }, { "epoch": 2.820224, "grad_norm": 1.796875, "learning_rate": 3.003156727241703e-06, "loss": 0.3831, "step": 11018 }, { "epoch": 2.82048, "grad_norm": 1.6640625, "learning_rate": 2.99889087961778e-06, "loss": 0.4708, "step": 11019 }, { "epoch": 2.820736, "grad_norm": 1.6484375, "learning_rate": 2.9946250319938576e-06, "loss": 0.4335, "step": 11020 }, { "epoch": 2.820992, "grad_norm": 1.75, "learning_rate": 2.9903591843699344e-06, "loss": 0.4632, "step": 11021 }, { "epoch": 2.8212479999999998, "grad_norm": 1.765625, "learning_rate": 2.9860933367460116e-06, "loss": 0.3939, "step": 11022 }, { "epoch": 2.821504, "grad_norm": 1.75, "learning_rate": 2.9818274891220884e-06, "loss": 0.4567, "step": 11023 }, { "epoch": 2.8217600000000003, "grad_norm": 1.734375, "learning_rate": 2.977561641498166e-06, "loss": 0.4685, "step": 11024 }, { "epoch": 2.822016, "grad_norm": 1.765625, "learning_rate": 2.973295793874243e-06, "loss": 0.4256, "step": 11025 }, { "epoch": 2.822272, "grad_norm": 1.734375, "learning_rate": 2.96902994625032e-06, "loss": 0.4153, "step": 11026 }, { "epoch": 2.822528, "grad_norm": 1.796875, "learning_rate": 2.964764098626397e-06, "loss": 0.4247, "step": 11027 }, { "epoch": 2.822784, "grad_norm": 1.828125, "learning_rate": 2.9604982510024746e-06, "loss": 0.4224, "step": 11028 }, { "epoch": 2.8230399999999998, "grad_norm": 1.890625, "learning_rate": 2.9562324033785514e-06, "loss": 0.4147, "step": 11029 }, { "epoch": 2.823296, "grad_norm": 1.703125, "learning_rate": 2.9519665557546286e-06, "loss": 0.4292, "step": 11030 }, { "epoch": 2.823552, "grad_norm": 1.7578125, "learning_rate": 2.9477007081307054e-06, "loss": 0.3914, "step": 11031 }, { "epoch": 2.823808, "grad_norm": 1.6640625, "learning_rate": 2.943434860506783e-06, "loss": 0.4092, "step": 11032 }, { "epoch": 2.824064, "grad_norm": 1.59375, "learning_rate": 2.93916901288286e-06, "loss": 0.4166, "step": 11033 }, { "epoch": 2.82432, "grad_norm": 1.75, "learning_rate": 2.934903165258937e-06, "loss": 0.4108, "step": 11034 }, { "epoch": 2.824576, "grad_norm": 1.734375, "learning_rate": 2.930637317635014e-06, "loss": 0.4751, "step": 11035 }, { "epoch": 2.824832, "grad_norm": 1.796875, "learning_rate": 2.9263714700110916e-06, "loss": 0.4137, "step": 11036 }, { "epoch": 2.825088, "grad_norm": 1.6953125, "learning_rate": 2.9221056223871684e-06, "loss": 0.4137, "step": 11037 }, { "epoch": 2.825344, "grad_norm": 1.71875, "learning_rate": 2.9178397747632456e-06, "loss": 0.4136, "step": 11038 }, { "epoch": 2.8256, "grad_norm": 1.7421875, "learning_rate": 2.9135739271393224e-06, "loss": 0.4239, "step": 11039 }, { "epoch": 2.825856, "grad_norm": 1.7421875, "learning_rate": 2.9093080795154e-06, "loss": 0.4335, "step": 11040 }, { "epoch": 2.826112, "grad_norm": 1.7578125, "learning_rate": 2.905042231891477e-06, "loss": 0.4196, "step": 11041 }, { "epoch": 2.826368, "grad_norm": 1.6953125, "learning_rate": 2.900776384267554e-06, "loss": 0.4143, "step": 11042 }, { "epoch": 2.826624, "grad_norm": 1.6796875, "learning_rate": 2.896510536643631e-06, "loss": 0.3671, "step": 11043 }, { "epoch": 2.82688, "grad_norm": 1.8828125, "learning_rate": 2.8922446890197086e-06, "loss": 0.4119, "step": 11044 }, { "epoch": 2.827136, "grad_norm": 1.671875, "learning_rate": 2.8879788413957854e-06, "loss": 0.4419, "step": 11045 }, { "epoch": 2.827392, "grad_norm": 1.7890625, "learning_rate": 2.8837129937718626e-06, "loss": 0.4443, "step": 11046 }, { "epoch": 2.827648, "grad_norm": 1.6484375, "learning_rate": 2.8794471461479394e-06, "loss": 0.4039, "step": 11047 }, { "epoch": 2.827904, "grad_norm": 1.9765625, "learning_rate": 2.875181298524017e-06, "loss": 0.4612, "step": 11048 }, { "epoch": 2.82816, "grad_norm": 1.640625, "learning_rate": 2.870915450900094e-06, "loss": 0.4219, "step": 11049 }, { "epoch": 2.828416, "grad_norm": 1.7265625, "learning_rate": 2.866649603276171e-06, "loss": 0.3694, "step": 11050 }, { "epoch": 2.828672, "grad_norm": 1.6484375, "learning_rate": 2.8623837556522484e-06, "loss": 0.4343, "step": 11051 }, { "epoch": 2.828928, "grad_norm": 1.75, "learning_rate": 2.8581179080283256e-06, "loss": 0.4341, "step": 11052 }, { "epoch": 2.829184, "grad_norm": 1.8046875, "learning_rate": 2.8538520604044024e-06, "loss": 0.4393, "step": 11053 }, { "epoch": 2.82944, "grad_norm": 1.703125, "learning_rate": 2.8495862127804796e-06, "loss": 0.3908, "step": 11054 }, { "epoch": 2.829696, "grad_norm": 1.765625, "learning_rate": 2.845320365156557e-06, "loss": 0.439, "step": 11055 }, { "epoch": 2.829952, "grad_norm": 1.8359375, "learning_rate": 2.8410545175326337e-06, "loss": 0.4014, "step": 11056 }, { "epoch": 2.830208, "grad_norm": 1.6953125, "learning_rate": 2.836788669908711e-06, "loss": 0.4239, "step": 11057 }, { "epoch": 2.830464, "grad_norm": 1.8203125, "learning_rate": 2.832522822284788e-06, "loss": 0.4177, "step": 11058 }, { "epoch": 2.83072, "grad_norm": 1.6796875, "learning_rate": 2.8282569746608654e-06, "loss": 0.4001, "step": 11059 }, { "epoch": 2.830976, "grad_norm": 1.75, "learning_rate": 2.823991127036942e-06, "loss": 0.425, "step": 11060 }, { "epoch": 2.831232, "grad_norm": 1.765625, "learning_rate": 2.8197252794130194e-06, "loss": 0.43, "step": 11061 }, { "epoch": 2.8314880000000002, "grad_norm": 1.75, "learning_rate": 2.8154594317890966e-06, "loss": 0.4081, "step": 11062 }, { "epoch": 2.831744, "grad_norm": 1.7734375, "learning_rate": 2.811193584165174e-06, "loss": 0.425, "step": 11063 }, { "epoch": 2.832, "grad_norm": 1.7109375, "learning_rate": 2.8069277365412507e-06, "loss": 0.3919, "step": 11064 }, { "epoch": 2.832256, "grad_norm": 1.9375, "learning_rate": 2.8026618889173283e-06, "loss": 0.4302, "step": 11065 }, { "epoch": 2.832512, "grad_norm": 1.90625, "learning_rate": 2.798396041293405e-06, "loss": 0.4367, "step": 11066 }, { "epoch": 2.8327679999999997, "grad_norm": 1.734375, "learning_rate": 2.7941301936694824e-06, "loss": 0.4257, "step": 11067 }, { "epoch": 2.833024, "grad_norm": 1.8671875, "learning_rate": 2.789864346045559e-06, "loss": 0.4411, "step": 11068 }, { "epoch": 2.8332800000000002, "grad_norm": 1.765625, "learning_rate": 2.785598498421637e-06, "loss": 0.4026, "step": 11069 }, { "epoch": 2.833536, "grad_norm": 1.7109375, "learning_rate": 2.7813326507977136e-06, "loss": 0.43, "step": 11070 }, { "epoch": 2.833792, "grad_norm": 1.7421875, "learning_rate": 2.777066803173791e-06, "loss": 0.3768, "step": 11071 }, { "epoch": 2.834048, "grad_norm": 1.9453125, "learning_rate": 2.7728009555498677e-06, "loss": 0.3874, "step": 11072 }, { "epoch": 2.834304, "grad_norm": 1.6484375, "learning_rate": 2.7685351079259453e-06, "loss": 0.4219, "step": 11073 }, { "epoch": 2.8345599999999997, "grad_norm": 1.7421875, "learning_rate": 2.764269260302022e-06, "loss": 0.4338, "step": 11074 }, { "epoch": 2.834816, "grad_norm": 1.875, "learning_rate": 2.7600034126780994e-06, "loss": 0.4279, "step": 11075 }, { "epoch": 2.8350720000000003, "grad_norm": 1.75, "learning_rate": 2.755737565054176e-06, "loss": 0.4139, "step": 11076 }, { "epoch": 2.835328, "grad_norm": 1.6796875, "learning_rate": 2.751471717430254e-06, "loss": 0.4136, "step": 11077 }, { "epoch": 2.835584, "grad_norm": 1.640625, "learning_rate": 2.7472058698063306e-06, "loss": 0.4073, "step": 11078 }, { "epoch": 2.83584, "grad_norm": 1.7265625, "learning_rate": 2.742940022182408e-06, "loss": 0.4354, "step": 11079 }, { "epoch": 2.836096, "grad_norm": 1.7890625, "learning_rate": 2.7386741745584847e-06, "loss": 0.4211, "step": 11080 }, { "epoch": 2.8363519999999998, "grad_norm": 1.921875, "learning_rate": 2.7344083269345623e-06, "loss": 0.4008, "step": 11081 }, { "epoch": 2.836608, "grad_norm": 1.78125, "learning_rate": 2.730142479310639e-06, "loss": 0.4561, "step": 11082 }, { "epoch": 2.8368640000000003, "grad_norm": 1.6796875, "learning_rate": 2.7258766316867164e-06, "loss": 0.4402, "step": 11083 }, { "epoch": 2.83712, "grad_norm": 1.7890625, "learning_rate": 2.721610784062793e-06, "loss": 0.4475, "step": 11084 }, { "epoch": 2.837376, "grad_norm": 1.7265625, "learning_rate": 2.717344936438871e-06, "loss": 0.461, "step": 11085 }, { "epoch": 2.837632, "grad_norm": 1.84375, "learning_rate": 2.7130790888149476e-06, "loss": 0.4494, "step": 11086 }, { "epoch": 2.837888, "grad_norm": 1.734375, "learning_rate": 2.708813241191025e-06, "loss": 0.3567, "step": 11087 }, { "epoch": 2.838144, "grad_norm": 1.6640625, "learning_rate": 2.7045473935671017e-06, "loss": 0.4219, "step": 11088 }, { "epoch": 2.8384, "grad_norm": 1.734375, "learning_rate": 2.7002815459431793e-06, "loss": 0.4229, "step": 11089 }, { "epoch": 2.838656, "grad_norm": 1.671875, "learning_rate": 2.696015698319256e-06, "loss": 0.4497, "step": 11090 }, { "epoch": 2.838912, "grad_norm": 1.8359375, "learning_rate": 2.6917498506953334e-06, "loss": 0.409, "step": 11091 }, { "epoch": 2.839168, "grad_norm": 1.8046875, "learning_rate": 2.68748400307141e-06, "loss": 0.4633, "step": 11092 }, { "epoch": 2.839424, "grad_norm": 1.8515625, "learning_rate": 2.683218155447488e-06, "loss": 0.4518, "step": 11093 }, { "epoch": 2.83968, "grad_norm": 1.78125, "learning_rate": 2.6789523078235646e-06, "loss": 0.4101, "step": 11094 }, { "epoch": 2.839936, "grad_norm": 1.7578125, "learning_rate": 2.674686460199642e-06, "loss": 0.4413, "step": 11095 }, { "epoch": 2.840192, "grad_norm": 1.796875, "learning_rate": 2.6704206125757187e-06, "loss": 0.3989, "step": 11096 }, { "epoch": 2.840448, "grad_norm": 1.71875, "learning_rate": 2.666154764951796e-06, "loss": 0.4334, "step": 11097 }, { "epoch": 2.840704, "grad_norm": 1.7578125, "learning_rate": 2.661888917327873e-06, "loss": 0.4375, "step": 11098 }, { "epoch": 2.84096, "grad_norm": 1.703125, "learning_rate": 2.6576230697039504e-06, "loss": 0.4117, "step": 11099 }, { "epoch": 2.841216, "grad_norm": 1.671875, "learning_rate": 2.653357222080027e-06, "loss": 0.4288, "step": 11100 }, { "epoch": 2.841472, "grad_norm": 1.7421875, "learning_rate": 2.6490913744561044e-06, "loss": 0.3969, "step": 11101 }, { "epoch": 2.841728, "grad_norm": 1.7109375, "learning_rate": 2.6448255268321816e-06, "loss": 0.4047, "step": 11102 }, { "epoch": 2.841984, "grad_norm": 1.734375, "learning_rate": 2.640559679208259e-06, "loss": 0.4171, "step": 11103 }, { "epoch": 2.84224, "grad_norm": 1.609375, "learning_rate": 2.6362938315843357e-06, "loss": 0.4036, "step": 11104 }, { "epoch": 2.842496, "grad_norm": 1.8984375, "learning_rate": 2.632027983960413e-06, "loss": 0.4291, "step": 11105 }, { "epoch": 2.842752, "grad_norm": 1.75, "learning_rate": 2.62776213633649e-06, "loss": 0.3989, "step": 11106 }, { "epoch": 2.843008, "grad_norm": 1.734375, "learning_rate": 2.6234962887125674e-06, "loss": 0.4236, "step": 11107 }, { "epoch": 2.843264, "grad_norm": 1.78125, "learning_rate": 2.6192304410886446e-06, "loss": 0.4282, "step": 11108 }, { "epoch": 2.84352, "grad_norm": 1.8046875, "learning_rate": 2.6149645934647214e-06, "loss": 0.4316, "step": 11109 }, { "epoch": 2.843776, "grad_norm": 1.7421875, "learning_rate": 2.6106987458407986e-06, "loss": 0.4266, "step": 11110 }, { "epoch": 2.844032, "grad_norm": 1.7265625, "learning_rate": 2.606432898216876e-06, "loss": 0.42, "step": 11111 }, { "epoch": 2.844288, "grad_norm": 1.8046875, "learning_rate": 2.602167050592953e-06, "loss": 0.4334, "step": 11112 }, { "epoch": 2.844544, "grad_norm": 1.7265625, "learning_rate": 2.59790120296903e-06, "loss": 0.3924, "step": 11113 }, { "epoch": 2.8448, "grad_norm": 1.8125, "learning_rate": 2.593635355345107e-06, "loss": 0.4193, "step": 11114 }, { "epoch": 2.845056, "grad_norm": 1.6796875, "learning_rate": 2.5893695077211844e-06, "loss": 0.4364, "step": 11115 }, { "epoch": 2.845312, "grad_norm": 1.6328125, "learning_rate": 2.5851036600972616e-06, "loss": 0.4489, "step": 11116 }, { "epoch": 2.845568, "grad_norm": 1.734375, "learning_rate": 2.5808378124733384e-06, "loss": 0.4234, "step": 11117 }, { "epoch": 2.845824, "grad_norm": 1.7109375, "learning_rate": 2.5765719648494156e-06, "loss": 0.4474, "step": 11118 }, { "epoch": 2.84608, "grad_norm": 1.8359375, "learning_rate": 2.572306117225493e-06, "loss": 0.4229, "step": 11119 }, { "epoch": 2.846336, "grad_norm": 1.8515625, "learning_rate": 2.56804026960157e-06, "loss": 0.428, "step": 11120 }, { "epoch": 2.8465920000000002, "grad_norm": 1.6953125, "learning_rate": 2.563774421977647e-06, "loss": 0.4513, "step": 11121 }, { "epoch": 2.846848, "grad_norm": 1.75, "learning_rate": 2.5595085743537245e-06, "loss": 0.414, "step": 11122 }, { "epoch": 2.847104, "grad_norm": 1.6640625, "learning_rate": 2.5552427267298014e-06, "loss": 0.4576, "step": 11123 }, { "epoch": 2.84736, "grad_norm": 1.8046875, "learning_rate": 2.5509768791058786e-06, "loss": 0.4232, "step": 11124 }, { "epoch": 2.847616, "grad_norm": 1.640625, "learning_rate": 2.5467110314819554e-06, "loss": 0.4139, "step": 11125 }, { "epoch": 2.8478719999999997, "grad_norm": 1.8125, "learning_rate": 2.542445183858033e-06, "loss": 0.4475, "step": 11126 }, { "epoch": 2.848128, "grad_norm": 1.7109375, "learning_rate": 2.53817933623411e-06, "loss": 0.4047, "step": 11127 }, { "epoch": 2.8483840000000002, "grad_norm": 1.84375, "learning_rate": 2.533913488610187e-06, "loss": 0.3984, "step": 11128 }, { "epoch": 2.84864, "grad_norm": 1.671875, "learning_rate": 2.529647640986264e-06, "loss": 0.426, "step": 11129 }, { "epoch": 2.848896, "grad_norm": 1.6640625, "learning_rate": 2.5253817933623415e-06, "loss": 0.4088, "step": 11130 }, { "epoch": 2.849152, "grad_norm": 1.640625, "learning_rate": 2.5211159457384184e-06, "loss": 0.4051, "step": 11131 }, { "epoch": 2.849408, "grad_norm": 1.7421875, "learning_rate": 2.5168500981144956e-06, "loss": 0.4225, "step": 11132 }, { "epoch": 2.8496639999999998, "grad_norm": 1.796875, "learning_rate": 2.5125842504905724e-06, "loss": 0.4494, "step": 11133 }, { "epoch": 2.84992, "grad_norm": 1.6796875, "learning_rate": 2.50831840286665e-06, "loss": 0.4151, "step": 11134 }, { "epoch": 2.8501760000000003, "grad_norm": 1.71875, "learning_rate": 2.504052555242727e-06, "loss": 0.4429, "step": 11135 }, { "epoch": 2.850432, "grad_norm": 1.7109375, "learning_rate": 2.499786707618804e-06, "loss": 0.4395, "step": 11136 }, { "epoch": 2.850688, "grad_norm": 1.8125, "learning_rate": 2.495520859994881e-06, "loss": 0.4162, "step": 11137 }, { "epoch": 2.850944, "grad_norm": 1.8046875, "learning_rate": 2.4912550123709585e-06, "loss": 0.3839, "step": 11138 }, { "epoch": 2.8512, "grad_norm": 1.8515625, "learning_rate": 2.4869891647470354e-06, "loss": 0.3913, "step": 11139 }, { "epoch": 2.8514559999999998, "grad_norm": 1.75, "learning_rate": 2.4827233171231126e-06, "loss": 0.4194, "step": 11140 }, { "epoch": 2.851712, "grad_norm": 1.6171875, "learning_rate": 2.4784574694991894e-06, "loss": 0.4351, "step": 11141 }, { "epoch": 2.851968, "grad_norm": 1.828125, "learning_rate": 2.4741916218752666e-06, "loss": 0.4241, "step": 11142 }, { "epoch": 2.852224, "grad_norm": 1.9453125, "learning_rate": 2.469925774251344e-06, "loss": 0.3888, "step": 11143 }, { "epoch": 2.85248, "grad_norm": 1.6953125, "learning_rate": 2.465659926627421e-06, "loss": 0.4018, "step": 11144 }, { "epoch": 2.852736, "grad_norm": 1.6875, "learning_rate": 2.461394079003498e-06, "loss": 0.4239, "step": 11145 }, { "epoch": 2.852992, "grad_norm": 1.78125, "learning_rate": 2.457128231379575e-06, "loss": 0.4002, "step": 11146 }, { "epoch": 2.853248, "grad_norm": 1.71875, "learning_rate": 2.4528623837556524e-06, "loss": 0.4347, "step": 11147 }, { "epoch": 2.853504, "grad_norm": 1.8359375, "learning_rate": 2.4485965361317296e-06, "loss": 0.3868, "step": 11148 }, { "epoch": 2.85376, "grad_norm": 1.7421875, "learning_rate": 2.4443306885078064e-06, "loss": 0.3715, "step": 11149 }, { "epoch": 2.854016, "grad_norm": 1.7265625, "learning_rate": 2.4400648408838836e-06, "loss": 0.4177, "step": 11150 }, { "epoch": 2.854272, "grad_norm": 1.765625, "learning_rate": 2.435798993259961e-06, "loss": 0.4818, "step": 11151 }, { "epoch": 2.854528, "grad_norm": 1.609375, "learning_rate": 2.431533145636038e-06, "loss": 0.4167, "step": 11152 }, { "epoch": 2.854784, "grad_norm": 1.75, "learning_rate": 2.427267298012115e-06, "loss": 0.3994, "step": 11153 }, { "epoch": 2.85504, "grad_norm": 1.734375, "learning_rate": 2.423001450388192e-06, "loss": 0.3737, "step": 11154 }, { "epoch": 2.855296, "grad_norm": 1.78125, "learning_rate": 2.4187356027642694e-06, "loss": 0.4391, "step": 11155 }, { "epoch": 2.855552, "grad_norm": 1.8046875, "learning_rate": 2.4144697551403466e-06, "loss": 0.4454, "step": 11156 }, { "epoch": 2.855808, "grad_norm": 1.6953125, "learning_rate": 2.4102039075164234e-06, "loss": 0.4274, "step": 11157 }, { "epoch": 2.856064, "grad_norm": 1.7109375, "learning_rate": 2.4059380598925006e-06, "loss": 0.3967, "step": 11158 }, { "epoch": 2.85632, "grad_norm": 1.7734375, "learning_rate": 2.401672212268578e-06, "loss": 0.4275, "step": 11159 }, { "epoch": 2.856576, "grad_norm": 1.7734375, "learning_rate": 2.397406364644655e-06, "loss": 0.4432, "step": 11160 }, { "epoch": 2.856832, "grad_norm": 1.6328125, "learning_rate": 2.393140517020732e-06, "loss": 0.3975, "step": 11161 }, { "epoch": 2.857088, "grad_norm": 1.7421875, "learning_rate": 2.388874669396809e-06, "loss": 0.4053, "step": 11162 }, { "epoch": 2.857344, "grad_norm": 1.765625, "learning_rate": 2.3846088217728864e-06, "loss": 0.4234, "step": 11163 }, { "epoch": 2.8576, "grad_norm": 1.6953125, "learning_rate": 2.3803429741489636e-06, "loss": 0.4158, "step": 11164 }, { "epoch": 2.857856, "grad_norm": 1.6796875, "learning_rate": 2.376077126525041e-06, "loss": 0.4192, "step": 11165 }, { "epoch": 2.858112, "grad_norm": 1.7734375, "learning_rate": 2.3718112789011176e-06, "loss": 0.4189, "step": 11166 }, { "epoch": 2.858368, "grad_norm": 1.71875, "learning_rate": 2.367545431277195e-06, "loss": 0.386, "step": 11167 }, { "epoch": 2.858624, "grad_norm": 1.6875, "learning_rate": 2.363279583653272e-06, "loss": 0.4035, "step": 11168 }, { "epoch": 2.85888, "grad_norm": 1.765625, "learning_rate": 2.3590137360293493e-06, "loss": 0.4112, "step": 11169 }, { "epoch": 2.859136, "grad_norm": 1.7265625, "learning_rate": 2.354747888405426e-06, "loss": 0.4447, "step": 11170 }, { "epoch": 2.859392, "grad_norm": 1.8046875, "learning_rate": 2.3504820407815034e-06, "loss": 0.4171, "step": 11171 }, { "epoch": 2.859648, "grad_norm": 1.734375, "learning_rate": 2.3462161931575806e-06, "loss": 0.4235, "step": 11172 }, { "epoch": 2.8599040000000002, "grad_norm": 1.6640625, "learning_rate": 2.341950345533658e-06, "loss": 0.4366, "step": 11173 }, { "epoch": 2.86016, "grad_norm": 1.75, "learning_rate": 2.3376844979097346e-06, "loss": 0.392, "step": 11174 }, { "epoch": 2.860416, "grad_norm": 1.6796875, "learning_rate": 2.333418650285812e-06, "loss": 0.4004, "step": 11175 }, { "epoch": 2.860672, "grad_norm": 1.6171875, "learning_rate": 2.329152802661889e-06, "loss": 0.429, "step": 11176 }, { "epoch": 2.860928, "grad_norm": 1.625, "learning_rate": 2.3248869550379663e-06, "loss": 0.4103, "step": 11177 }, { "epoch": 2.8611839999999997, "grad_norm": 1.75, "learning_rate": 2.320621107414043e-06, "loss": 0.4133, "step": 11178 }, { "epoch": 2.86144, "grad_norm": 1.703125, "learning_rate": 2.3163552597901208e-06, "loss": 0.3894, "step": 11179 }, { "epoch": 2.8616960000000002, "grad_norm": 1.8046875, "learning_rate": 2.3120894121661976e-06, "loss": 0.4174, "step": 11180 }, { "epoch": 2.861952, "grad_norm": 1.65625, "learning_rate": 2.307823564542275e-06, "loss": 0.4157, "step": 11181 }, { "epoch": 2.862208, "grad_norm": 1.7578125, "learning_rate": 2.3035577169183516e-06, "loss": 0.4361, "step": 11182 }, { "epoch": 2.862464, "grad_norm": 1.7421875, "learning_rate": 2.299291869294429e-06, "loss": 0.4363, "step": 11183 }, { "epoch": 2.86272, "grad_norm": 1.59375, "learning_rate": 2.295026021670506e-06, "loss": 0.3956, "step": 11184 }, { "epoch": 2.8629759999999997, "grad_norm": 1.671875, "learning_rate": 2.2907601740465833e-06, "loss": 0.4275, "step": 11185 }, { "epoch": 2.863232, "grad_norm": 1.8671875, "learning_rate": 2.28649432642266e-06, "loss": 0.4415, "step": 11186 }, { "epoch": 2.8634880000000003, "grad_norm": 1.6796875, "learning_rate": 2.2822284787987374e-06, "loss": 0.4144, "step": 11187 }, { "epoch": 2.863744, "grad_norm": 1.671875, "learning_rate": 2.2779626311748146e-06, "loss": 0.4286, "step": 11188 }, { "epoch": 2.864, "grad_norm": 1.7265625, "learning_rate": 2.273696783550892e-06, "loss": 0.4165, "step": 11189 }, { "epoch": 2.864256, "grad_norm": 1.8046875, "learning_rate": 2.2694309359269686e-06, "loss": 0.4491, "step": 11190 }, { "epoch": 2.864512, "grad_norm": 1.8125, "learning_rate": 2.265165088303046e-06, "loss": 0.3872, "step": 11191 }, { "epoch": 2.8647679999999998, "grad_norm": 1.6796875, "learning_rate": 2.260899240679123e-06, "loss": 0.4359, "step": 11192 }, { "epoch": 2.865024, "grad_norm": 1.75, "learning_rate": 2.2566333930552003e-06, "loss": 0.4183, "step": 11193 }, { "epoch": 2.8652800000000003, "grad_norm": 1.7578125, "learning_rate": 2.252367545431277e-06, "loss": 0.4264, "step": 11194 }, { "epoch": 2.865536, "grad_norm": 1.7421875, "learning_rate": 2.2481016978073544e-06, "loss": 0.4223, "step": 11195 }, { "epoch": 2.865792, "grad_norm": 1.78125, "learning_rate": 2.2438358501834316e-06, "loss": 0.4223, "step": 11196 }, { "epoch": 2.866048, "grad_norm": 1.8203125, "learning_rate": 2.239570002559509e-06, "loss": 0.4367, "step": 11197 }, { "epoch": 2.866304, "grad_norm": 1.796875, "learning_rate": 2.2353041549355856e-06, "loss": 0.4622, "step": 11198 }, { "epoch": 2.8665599999999998, "grad_norm": 1.65625, "learning_rate": 2.231038307311663e-06, "loss": 0.3922, "step": 11199 }, { "epoch": 2.866816, "grad_norm": 1.6484375, "learning_rate": 2.22677245968774e-06, "loss": 0.4386, "step": 11200 }, { "epoch": 2.867072, "grad_norm": 1.6484375, "learning_rate": 2.2225066120638173e-06, "loss": 0.425, "step": 11201 }, { "epoch": 2.867328, "grad_norm": 1.5625, "learning_rate": 2.218240764439894e-06, "loss": 0.409, "step": 11202 }, { "epoch": 2.867584, "grad_norm": 1.7265625, "learning_rate": 2.2139749168159714e-06, "loss": 0.4397, "step": 11203 }, { "epoch": 2.86784, "grad_norm": 1.7890625, "learning_rate": 2.2097090691920486e-06, "loss": 0.4182, "step": 11204 }, { "epoch": 2.868096, "grad_norm": 1.8125, "learning_rate": 2.205443221568126e-06, "loss": 0.4352, "step": 11205 }, { "epoch": 2.868352, "grad_norm": 1.6953125, "learning_rate": 2.2011773739442026e-06, "loss": 0.3769, "step": 11206 }, { "epoch": 2.868608, "grad_norm": 1.671875, "learning_rate": 2.19691152632028e-06, "loss": 0.4223, "step": 11207 }, { "epoch": 2.868864, "grad_norm": 1.7109375, "learning_rate": 2.192645678696357e-06, "loss": 0.412, "step": 11208 }, { "epoch": 2.86912, "grad_norm": 1.6875, "learning_rate": 2.1883798310724343e-06, "loss": 0.4077, "step": 11209 }, { "epoch": 2.869376, "grad_norm": 1.7421875, "learning_rate": 2.184113983448511e-06, "loss": 0.4139, "step": 11210 }, { "epoch": 2.869632, "grad_norm": 1.703125, "learning_rate": 2.1798481358245884e-06, "loss": 0.4112, "step": 11211 }, { "epoch": 2.869888, "grad_norm": 1.59375, "learning_rate": 2.1755822882006656e-06, "loss": 0.421, "step": 11212 }, { "epoch": 2.870144, "grad_norm": 1.7109375, "learning_rate": 2.171316440576743e-06, "loss": 0.4154, "step": 11213 }, { "epoch": 2.8704, "grad_norm": 1.8515625, "learning_rate": 2.1670505929528196e-06, "loss": 0.3974, "step": 11214 }, { "epoch": 2.870656, "grad_norm": 1.6796875, "learning_rate": 2.162784745328897e-06, "loss": 0.4299, "step": 11215 }, { "epoch": 2.870912, "grad_norm": 1.734375, "learning_rate": 2.158518897704974e-06, "loss": 0.4, "step": 11216 }, { "epoch": 2.871168, "grad_norm": 1.734375, "learning_rate": 2.1542530500810513e-06, "loss": 0.394, "step": 11217 }, { "epoch": 2.871424, "grad_norm": 1.7109375, "learning_rate": 2.149987202457128e-06, "loss": 0.4299, "step": 11218 }, { "epoch": 2.87168, "grad_norm": 1.578125, "learning_rate": 2.1457213548332054e-06, "loss": 0.4488, "step": 11219 }, { "epoch": 2.871936, "grad_norm": 1.765625, "learning_rate": 2.1414555072092826e-06, "loss": 0.4357, "step": 11220 }, { "epoch": 2.872192, "grad_norm": 1.8515625, "learning_rate": 2.13718965958536e-06, "loss": 0.3912, "step": 11221 }, { "epoch": 2.872448, "grad_norm": 1.6953125, "learning_rate": 2.1329238119614366e-06, "loss": 0.3859, "step": 11222 }, { "epoch": 2.872704, "grad_norm": 1.6875, "learning_rate": 2.128657964337514e-06, "loss": 0.4259, "step": 11223 }, { "epoch": 2.87296, "grad_norm": 1.75, "learning_rate": 2.124392116713591e-06, "loss": 0.4288, "step": 11224 }, { "epoch": 2.873216, "grad_norm": 1.734375, "learning_rate": 2.1201262690896683e-06, "loss": 0.4345, "step": 11225 }, { "epoch": 2.873472, "grad_norm": 1.765625, "learning_rate": 2.1158604214657456e-06, "loss": 0.4258, "step": 11226 }, { "epoch": 2.873728, "grad_norm": 1.7265625, "learning_rate": 2.1115945738418224e-06, "loss": 0.452, "step": 11227 }, { "epoch": 2.873984, "grad_norm": 1.7734375, "learning_rate": 2.1073287262178996e-06, "loss": 0.406, "step": 11228 }, { "epoch": 2.87424, "grad_norm": 1.84375, "learning_rate": 2.103062878593977e-06, "loss": 0.4326, "step": 11229 }, { "epoch": 2.874496, "grad_norm": 1.78125, "learning_rate": 2.098797030970054e-06, "loss": 0.4306, "step": 11230 }, { "epoch": 2.874752, "grad_norm": 1.84375, "learning_rate": 2.094531183346131e-06, "loss": 0.4261, "step": 11231 }, { "epoch": 2.8750080000000002, "grad_norm": 1.8046875, "learning_rate": 2.090265335722208e-06, "loss": 0.4047, "step": 11232 }, { "epoch": 2.875264, "grad_norm": 1.671875, "learning_rate": 2.0859994880982853e-06, "loss": 0.4027, "step": 11233 }, { "epoch": 2.87552, "grad_norm": 1.765625, "learning_rate": 2.0817336404743626e-06, "loss": 0.4141, "step": 11234 }, { "epoch": 2.875776, "grad_norm": 1.6640625, "learning_rate": 2.0774677928504394e-06, "loss": 0.413, "step": 11235 }, { "epoch": 2.876032, "grad_norm": 1.7578125, "learning_rate": 2.0732019452265166e-06, "loss": 0.4207, "step": 11236 }, { "epoch": 2.8762879999999997, "grad_norm": 1.71875, "learning_rate": 2.068936097602594e-06, "loss": 0.4023, "step": 11237 }, { "epoch": 2.876544, "grad_norm": 1.8203125, "learning_rate": 2.064670249978671e-06, "loss": 0.3919, "step": 11238 }, { "epoch": 2.8768000000000002, "grad_norm": 1.765625, "learning_rate": 2.060404402354748e-06, "loss": 0.3953, "step": 11239 }, { "epoch": 2.877056, "grad_norm": 1.8203125, "learning_rate": 2.056138554730825e-06, "loss": 0.4201, "step": 11240 }, { "epoch": 2.877312, "grad_norm": 1.8515625, "learning_rate": 2.0518727071069023e-06, "loss": 0.4474, "step": 11241 }, { "epoch": 2.877568, "grad_norm": 1.6015625, "learning_rate": 2.0476068594829796e-06, "loss": 0.4313, "step": 11242 }, { "epoch": 2.877824, "grad_norm": 1.7265625, "learning_rate": 2.0433410118590564e-06, "loss": 0.4257, "step": 11243 }, { "epoch": 2.8780799999999997, "grad_norm": 1.7421875, "learning_rate": 2.0390751642351336e-06, "loss": 0.3916, "step": 11244 }, { "epoch": 2.878336, "grad_norm": 1.625, "learning_rate": 2.034809316611211e-06, "loss": 0.4408, "step": 11245 }, { "epoch": 2.8785920000000003, "grad_norm": 1.828125, "learning_rate": 2.030543468987288e-06, "loss": 0.3909, "step": 11246 }, { "epoch": 2.878848, "grad_norm": 1.703125, "learning_rate": 2.026277621363365e-06, "loss": 0.4224, "step": 11247 }, { "epoch": 2.879104, "grad_norm": 1.828125, "learning_rate": 2.022011773739442e-06, "loss": 0.4035, "step": 11248 }, { "epoch": 2.87936, "grad_norm": 1.6796875, "learning_rate": 2.0177459261155193e-06, "loss": 0.4522, "step": 11249 }, { "epoch": 2.879616, "grad_norm": 1.84375, "learning_rate": 2.0134800784915966e-06, "loss": 0.4555, "step": 11250 }, { "epoch": 2.8798719999999998, "grad_norm": 1.765625, "learning_rate": 2.0092142308676734e-06, "loss": 0.409, "step": 11251 }, { "epoch": 2.880128, "grad_norm": 1.765625, "learning_rate": 2.0049483832437506e-06, "loss": 0.4357, "step": 11252 }, { "epoch": 2.8803840000000003, "grad_norm": 1.609375, "learning_rate": 2.000682535619828e-06, "loss": 0.4377, "step": 11253 }, { "epoch": 2.88064, "grad_norm": 1.6875, "learning_rate": 1.996416687995905e-06, "loss": 0.4356, "step": 11254 }, { "epoch": 2.880896, "grad_norm": 1.6484375, "learning_rate": 1.992150840371982e-06, "loss": 0.4059, "step": 11255 }, { "epoch": 2.881152, "grad_norm": 1.6640625, "learning_rate": 1.987884992748059e-06, "loss": 0.4344, "step": 11256 }, { "epoch": 2.881408, "grad_norm": 1.734375, "learning_rate": 1.9836191451241363e-06, "loss": 0.4509, "step": 11257 }, { "epoch": 2.881664, "grad_norm": 1.7734375, "learning_rate": 1.9793532975002136e-06, "loss": 0.4254, "step": 11258 }, { "epoch": 2.88192, "grad_norm": 1.7578125, "learning_rate": 1.9750874498762904e-06, "loss": 0.4294, "step": 11259 }, { "epoch": 2.882176, "grad_norm": 1.7578125, "learning_rate": 1.9708216022523676e-06, "loss": 0.3914, "step": 11260 }, { "epoch": 2.882432, "grad_norm": 1.703125, "learning_rate": 1.966555754628445e-06, "loss": 0.4115, "step": 11261 }, { "epoch": 2.882688, "grad_norm": 1.703125, "learning_rate": 1.962289907004522e-06, "loss": 0.4226, "step": 11262 }, { "epoch": 2.882944, "grad_norm": 1.7109375, "learning_rate": 1.958024059380599e-06, "loss": 0.4131, "step": 11263 }, { "epoch": 2.8832, "grad_norm": 1.6484375, "learning_rate": 1.953758211756676e-06, "loss": 0.4452, "step": 11264 }, { "epoch": 2.883456, "grad_norm": 1.71875, "learning_rate": 1.949492364132753e-06, "loss": 0.4576, "step": 11265 }, { "epoch": 2.883712, "grad_norm": 1.7265625, "learning_rate": 1.9452265165088306e-06, "loss": 0.4068, "step": 11266 }, { "epoch": 2.883968, "grad_norm": 1.7421875, "learning_rate": 1.9409606688849074e-06, "loss": 0.3936, "step": 11267 }, { "epoch": 2.884224, "grad_norm": 1.765625, "learning_rate": 1.9366948212609846e-06, "loss": 0.4142, "step": 11268 }, { "epoch": 2.88448, "grad_norm": 1.703125, "learning_rate": 1.932428973637062e-06, "loss": 0.4099, "step": 11269 }, { "epoch": 2.884736, "grad_norm": 1.5859375, "learning_rate": 1.928163126013139e-06, "loss": 0.4208, "step": 11270 }, { "epoch": 2.884992, "grad_norm": 1.6796875, "learning_rate": 1.923897278389216e-06, "loss": 0.4278, "step": 11271 }, { "epoch": 2.885248, "grad_norm": 1.71875, "learning_rate": 1.919631430765293e-06, "loss": 0.3967, "step": 11272 }, { "epoch": 2.885504, "grad_norm": 1.7109375, "learning_rate": 1.9153655831413703e-06, "loss": 0.48, "step": 11273 }, { "epoch": 2.88576, "grad_norm": 1.765625, "learning_rate": 1.9110997355174476e-06, "loss": 0.4067, "step": 11274 }, { "epoch": 2.886016, "grad_norm": 1.71875, "learning_rate": 1.9068338878935246e-06, "loss": 0.4242, "step": 11275 }, { "epoch": 2.886272, "grad_norm": 1.59375, "learning_rate": 1.9025680402696016e-06, "loss": 0.4319, "step": 11276 }, { "epoch": 2.886528, "grad_norm": 1.765625, "learning_rate": 1.8983021926456786e-06, "loss": 0.3965, "step": 11277 }, { "epoch": 2.886784, "grad_norm": 1.71875, "learning_rate": 1.894036345021756e-06, "loss": 0.3776, "step": 11278 }, { "epoch": 2.88704, "grad_norm": 1.78125, "learning_rate": 1.889770497397833e-06, "loss": 0.4119, "step": 11279 }, { "epoch": 2.887296, "grad_norm": 1.7421875, "learning_rate": 1.88550464977391e-06, "loss": 0.4335, "step": 11280 }, { "epoch": 2.887552, "grad_norm": 1.6640625, "learning_rate": 1.8812388021499871e-06, "loss": 0.4218, "step": 11281 }, { "epoch": 2.887808, "grad_norm": 1.6640625, "learning_rate": 1.8769729545260646e-06, "loss": 0.43, "step": 11282 }, { "epoch": 2.888064, "grad_norm": 1.78125, "learning_rate": 1.8727071069021416e-06, "loss": 0.4364, "step": 11283 }, { "epoch": 2.88832, "grad_norm": 1.6953125, "learning_rate": 1.8684412592782186e-06, "loss": 0.4101, "step": 11284 }, { "epoch": 2.888576, "grad_norm": 1.6796875, "learning_rate": 1.8641754116542956e-06, "loss": 0.4231, "step": 11285 }, { "epoch": 2.888832, "grad_norm": 1.7421875, "learning_rate": 1.859909564030373e-06, "loss": 0.3978, "step": 11286 }, { "epoch": 2.889088, "grad_norm": 1.71875, "learning_rate": 1.85564371640645e-06, "loss": 0.4075, "step": 11287 }, { "epoch": 2.889344, "grad_norm": 1.84375, "learning_rate": 1.851377868782527e-06, "loss": 0.4119, "step": 11288 }, { "epoch": 2.8895999999999997, "grad_norm": 1.78125, "learning_rate": 1.8471120211586041e-06, "loss": 0.4, "step": 11289 }, { "epoch": 2.889856, "grad_norm": 1.59375, "learning_rate": 1.8428461735346816e-06, "loss": 0.4346, "step": 11290 }, { "epoch": 2.8901120000000002, "grad_norm": 1.84375, "learning_rate": 1.8385803259107586e-06, "loss": 0.428, "step": 11291 }, { "epoch": 2.890368, "grad_norm": 1.7265625, "learning_rate": 1.8343144782868356e-06, "loss": 0.4387, "step": 11292 }, { "epoch": 2.890624, "grad_norm": 1.8046875, "learning_rate": 1.8300486306629126e-06, "loss": 0.4192, "step": 11293 }, { "epoch": 2.89088, "grad_norm": 1.828125, "learning_rate": 1.82578278303899e-06, "loss": 0.4122, "step": 11294 }, { "epoch": 2.891136, "grad_norm": 1.7421875, "learning_rate": 1.821516935415067e-06, "loss": 0.3812, "step": 11295 }, { "epoch": 2.8913919999999997, "grad_norm": 1.7734375, "learning_rate": 1.817251087791144e-06, "loss": 0.4004, "step": 11296 }, { "epoch": 2.891648, "grad_norm": 1.8359375, "learning_rate": 1.8129852401672211e-06, "loss": 0.4258, "step": 11297 }, { "epoch": 2.8919040000000003, "grad_norm": 1.7109375, "learning_rate": 1.8087193925432986e-06, "loss": 0.4229, "step": 11298 }, { "epoch": 2.89216, "grad_norm": 1.734375, "learning_rate": 1.8044535449193756e-06, "loss": 0.4376, "step": 11299 }, { "epoch": 2.892416, "grad_norm": 1.6875, "learning_rate": 1.8001876972954526e-06, "loss": 0.434, "step": 11300 }, { "epoch": 2.892672, "grad_norm": 1.640625, "learning_rate": 1.7959218496715298e-06, "loss": 0.4422, "step": 11301 }, { "epoch": 2.892928, "grad_norm": 1.859375, "learning_rate": 1.791656002047607e-06, "loss": 0.4642, "step": 11302 }, { "epoch": 2.8931839999999998, "grad_norm": 1.6484375, "learning_rate": 1.787390154423684e-06, "loss": 0.4237, "step": 11303 }, { "epoch": 2.89344, "grad_norm": 1.734375, "learning_rate": 1.783124306799761e-06, "loss": 0.4461, "step": 11304 }, { "epoch": 2.8936960000000003, "grad_norm": 1.7265625, "learning_rate": 1.7788584591758383e-06, "loss": 0.4315, "step": 11305 }, { "epoch": 2.893952, "grad_norm": 1.671875, "learning_rate": 1.7745926115519153e-06, "loss": 0.3945, "step": 11306 }, { "epoch": 2.894208, "grad_norm": 1.78125, "learning_rate": 1.7703267639279926e-06, "loss": 0.4004, "step": 11307 }, { "epoch": 2.894464, "grad_norm": 1.765625, "learning_rate": 1.7660609163040698e-06, "loss": 0.4187, "step": 11308 }, { "epoch": 2.89472, "grad_norm": 1.71875, "learning_rate": 1.7617950686801468e-06, "loss": 0.4529, "step": 11309 }, { "epoch": 2.8949759999999998, "grad_norm": 1.734375, "learning_rate": 1.7575292210562238e-06, "loss": 0.4435, "step": 11310 }, { "epoch": 2.895232, "grad_norm": 1.828125, "learning_rate": 1.753263373432301e-06, "loss": 0.4285, "step": 11311 }, { "epoch": 2.895488, "grad_norm": 1.7421875, "learning_rate": 1.7489975258083783e-06, "loss": 0.3991, "step": 11312 }, { "epoch": 2.895744, "grad_norm": 1.7421875, "learning_rate": 1.7447316781844553e-06, "loss": 0.402, "step": 11313 }, { "epoch": 2.896, "grad_norm": 1.71875, "learning_rate": 1.7404658305605323e-06, "loss": 0.4163, "step": 11314 }, { "epoch": 2.896256, "grad_norm": 1.8359375, "learning_rate": 1.7361999829366098e-06, "loss": 0.3859, "step": 11315 }, { "epoch": 2.896512, "grad_norm": 1.6875, "learning_rate": 1.7319341353126868e-06, "loss": 0.4382, "step": 11316 }, { "epoch": 2.896768, "grad_norm": 1.8203125, "learning_rate": 1.7276682876887638e-06, "loss": 0.3858, "step": 11317 }, { "epoch": 2.897024, "grad_norm": 1.859375, "learning_rate": 1.7234024400648408e-06, "loss": 0.3814, "step": 11318 }, { "epoch": 2.89728, "grad_norm": 1.703125, "learning_rate": 1.7191365924409183e-06, "loss": 0.4447, "step": 11319 }, { "epoch": 2.897536, "grad_norm": 1.7578125, "learning_rate": 1.7148707448169953e-06, "loss": 0.397, "step": 11320 }, { "epoch": 2.897792, "grad_norm": 1.6796875, "learning_rate": 1.7106048971930723e-06, "loss": 0.409, "step": 11321 }, { "epoch": 2.898048, "grad_norm": 1.765625, "learning_rate": 1.7063390495691493e-06, "loss": 0.4066, "step": 11322 }, { "epoch": 2.898304, "grad_norm": 1.7578125, "learning_rate": 1.7020732019452268e-06, "loss": 0.4875, "step": 11323 }, { "epoch": 2.89856, "grad_norm": 1.7734375, "learning_rate": 1.6978073543213038e-06, "loss": 0.3957, "step": 11324 }, { "epoch": 2.898816, "grad_norm": 1.7578125, "learning_rate": 1.6935415066973808e-06, "loss": 0.3856, "step": 11325 }, { "epoch": 2.899072, "grad_norm": 1.7578125, "learning_rate": 1.6892756590734578e-06, "loss": 0.4007, "step": 11326 }, { "epoch": 2.899328, "grad_norm": 1.703125, "learning_rate": 1.6850098114495353e-06, "loss": 0.4152, "step": 11327 }, { "epoch": 2.899584, "grad_norm": 1.9609375, "learning_rate": 1.6807439638256123e-06, "loss": 0.4104, "step": 11328 }, { "epoch": 2.89984, "grad_norm": 1.5703125, "learning_rate": 1.6764781162016893e-06, "loss": 0.4534, "step": 11329 }, { "epoch": 2.900096, "grad_norm": 1.7734375, "learning_rate": 1.6722122685777663e-06, "loss": 0.4337, "step": 11330 }, { "epoch": 2.900352, "grad_norm": 1.7578125, "learning_rate": 1.6679464209538438e-06, "loss": 0.4186, "step": 11331 }, { "epoch": 2.900608, "grad_norm": 1.8125, "learning_rate": 1.6636805733299208e-06, "loss": 0.4567, "step": 11332 }, { "epoch": 2.900864, "grad_norm": 1.7265625, "learning_rate": 1.6594147257059978e-06, "loss": 0.4614, "step": 11333 }, { "epoch": 2.90112, "grad_norm": 1.578125, "learning_rate": 1.6551488780820748e-06, "loss": 0.4295, "step": 11334 }, { "epoch": 2.901376, "grad_norm": 1.6328125, "learning_rate": 1.6508830304581523e-06, "loss": 0.4283, "step": 11335 }, { "epoch": 2.901632, "grad_norm": 1.6328125, "learning_rate": 1.6466171828342293e-06, "loss": 0.4623, "step": 11336 }, { "epoch": 2.901888, "grad_norm": 1.7265625, "learning_rate": 1.6423513352103063e-06, "loss": 0.4276, "step": 11337 }, { "epoch": 2.902144, "grad_norm": 1.828125, "learning_rate": 1.6380854875863833e-06, "loss": 0.391, "step": 11338 }, { "epoch": 2.9024, "grad_norm": 1.828125, "learning_rate": 1.6338196399624608e-06, "loss": 0.4225, "step": 11339 }, { "epoch": 2.902656, "grad_norm": 1.7734375, "learning_rate": 1.6295537923385378e-06, "loss": 0.4313, "step": 11340 }, { "epoch": 2.902912, "grad_norm": 1.71875, "learning_rate": 1.6252879447146148e-06, "loss": 0.4115, "step": 11341 }, { "epoch": 2.903168, "grad_norm": 1.7578125, "learning_rate": 1.6210220970906918e-06, "loss": 0.4347, "step": 11342 }, { "epoch": 2.9034240000000002, "grad_norm": 1.8359375, "learning_rate": 1.6167562494667693e-06, "loss": 0.4439, "step": 11343 }, { "epoch": 2.90368, "grad_norm": 1.7890625, "learning_rate": 1.6124904018428463e-06, "loss": 0.4255, "step": 11344 }, { "epoch": 2.903936, "grad_norm": 1.6640625, "learning_rate": 1.6082245542189233e-06, "loss": 0.4113, "step": 11345 }, { "epoch": 2.904192, "grad_norm": 1.8125, "learning_rate": 1.6039587065950003e-06, "loss": 0.3816, "step": 11346 }, { "epoch": 2.904448, "grad_norm": 1.65625, "learning_rate": 1.5996928589710774e-06, "loss": 0.4135, "step": 11347 }, { "epoch": 2.9047039999999997, "grad_norm": 1.96875, "learning_rate": 1.5954270113471548e-06, "loss": 0.4546, "step": 11348 }, { "epoch": 2.90496, "grad_norm": 1.859375, "learning_rate": 1.5911611637232318e-06, "loss": 0.4056, "step": 11349 }, { "epoch": 2.9052160000000002, "grad_norm": 1.765625, "learning_rate": 1.5868953160993088e-06, "loss": 0.4005, "step": 11350 }, { "epoch": 2.905472, "grad_norm": 1.6015625, "learning_rate": 1.5826294684753859e-06, "loss": 0.4287, "step": 11351 }, { "epoch": 2.905728, "grad_norm": 1.7734375, "learning_rate": 1.5783636208514633e-06, "loss": 0.438, "step": 11352 }, { "epoch": 2.905984, "grad_norm": 1.7109375, "learning_rate": 1.5740977732275403e-06, "loss": 0.3878, "step": 11353 }, { "epoch": 2.90624, "grad_norm": 1.671875, "learning_rate": 1.5698319256036173e-06, "loss": 0.4137, "step": 11354 }, { "epoch": 2.9064959999999997, "grad_norm": 1.6640625, "learning_rate": 1.5655660779796946e-06, "loss": 0.4157, "step": 11355 }, { "epoch": 2.906752, "grad_norm": 1.9296875, "learning_rate": 1.5613002303557716e-06, "loss": 0.3981, "step": 11356 }, { "epoch": 2.9070080000000003, "grad_norm": 1.796875, "learning_rate": 1.5570343827318488e-06, "loss": 0.438, "step": 11357 }, { "epoch": 2.907264, "grad_norm": 1.7734375, "learning_rate": 1.552768535107926e-06, "loss": 0.4293, "step": 11358 }, { "epoch": 2.90752, "grad_norm": 1.75, "learning_rate": 1.548502687484003e-06, "loss": 0.3981, "step": 11359 }, { "epoch": 2.907776, "grad_norm": 1.6484375, "learning_rate": 1.5442368398600803e-06, "loss": 0.434, "step": 11360 }, { "epoch": 2.908032, "grad_norm": 1.6875, "learning_rate": 1.5399709922361573e-06, "loss": 0.4064, "step": 11361 }, { "epoch": 2.9082879999999998, "grad_norm": 1.6796875, "learning_rate": 1.5357051446122346e-06, "loss": 0.448, "step": 11362 }, { "epoch": 2.908544, "grad_norm": 1.6328125, "learning_rate": 1.5314392969883118e-06, "loss": 0.4077, "step": 11363 }, { "epoch": 2.9088000000000003, "grad_norm": 1.7265625, "learning_rate": 1.5271734493643888e-06, "loss": 0.4176, "step": 11364 }, { "epoch": 2.909056, "grad_norm": 1.6640625, "learning_rate": 1.522907601740466e-06, "loss": 0.4378, "step": 11365 }, { "epoch": 2.909312, "grad_norm": 1.7421875, "learning_rate": 1.518641754116543e-06, "loss": 0.3962, "step": 11366 }, { "epoch": 2.909568, "grad_norm": 1.7109375, "learning_rate": 1.5143759064926203e-06, "loss": 0.4044, "step": 11367 }, { "epoch": 2.909824, "grad_norm": 1.7421875, "learning_rate": 1.5101100588686973e-06, "loss": 0.4114, "step": 11368 }, { "epoch": 2.91008, "grad_norm": 1.7734375, "learning_rate": 1.5058442112447745e-06, "loss": 0.3951, "step": 11369 }, { "epoch": 2.910336, "grad_norm": 1.9609375, "learning_rate": 1.5015783636208516e-06, "loss": 0.4554, "step": 11370 }, { "epoch": 2.910592, "grad_norm": 1.59375, "learning_rate": 1.4973125159969288e-06, "loss": 0.4334, "step": 11371 }, { "epoch": 2.910848, "grad_norm": 1.7265625, "learning_rate": 1.4930466683730058e-06, "loss": 0.3792, "step": 11372 }, { "epoch": 2.911104, "grad_norm": 1.71875, "learning_rate": 1.488780820749083e-06, "loss": 0.4262, "step": 11373 }, { "epoch": 2.91136, "grad_norm": 1.7578125, "learning_rate": 1.48451497312516e-06, "loss": 0.4094, "step": 11374 }, { "epoch": 2.911616, "grad_norm": 1.6484375, "learning_rate": 1.4802491255012373e-06, "loss": 0.4451, "step": 11375 }, { "epoch": 2.911872, "grad_norm": 1.75, "learning_rate": 1.4759832778773143e-06, "loss": 0.4243, "step": 11376 }, { "epoch": 2.912128, "grad_norm": 1.8125, "learning_rate": 1.4717174302533915e-06, "loss": 0.4378, "step": 11377 }, { "epoch": 2.912384, "grad_norm": 1.7734375, "learning_rate": 1.4674515826294686e-06, "loss": 0.4323, "step": 11378 }, { "epoch": 2.91264, "grad_norm": 1.6875, "learning_rate": 1.4631857350055458e-06, "loss": 0.4062, "step": 11379 }, { "epoch": 2.912896, "grad_norm": 1.78125, "learning_rate": 1.4589198873816228e-06, "loss": 0.4399, "step": 11380 }, { "epoch": 2.913152, "grad_norm": 1.6875, "learning_rate": 1.4546540397577e-06, "loss": 0.4297, "step": 11381 }, { "epoch": 2.913408, "grad_norm": 1.7578125, "learning_rate": 1.450388192133777e-06, "loss": 0.4295, "step": 11382 }, { "epoch": 2.913664, "grad_norm": 1.7421875, "learning_rate": 1.4461223445098543e-06, "loss": 0.3861, "step": 11383 }, { "epoch": 2.91392, "grad_norm": 1.625, "learning_rate": 1.4418564968859313e-06, "loss": 0.4554, "step": 11384 }, { "epoch": 2.914176, "grad_norm": 1.75, "learning_rate": 1.4375906492620085e-06, "loss": 0.4155, "step": 11385 }, { "epoch": 2.914432, "grad_norm": 1.6640625, "learning_rate": 1.4333248016380856e-06, "loss": 0.4559, "step": 11386 }, { "epoch": 2.914688, "grad_norm": 1.859375, "learning_rate": 1.4290589540141628e-06, "loss": 0.4453, "step": 11387 }, { "epoch": 2.914944, "grad_norm": 1.6796875, "learning_rate": 1.4247931063902398e-06, "loss": 0.434, "step": 11388 }, { "epoch": 2.9152, "grad_norm": 1.75, "learning_rate": 1.4205272587663168e-06, "loss": 0.4035, "step": 11389 }, { "epoch": 2.915456, "grad_norm": 1.734375, "learning_rate": 1.416261411142394e-06, "loss": 0.3969, "step": 11390 }, { "epoch": 2.915712, "grad_norm": 1.71875, "learning_rate": 1.411995563518471e-06, "loss": 0.4247, "step": 11391 }, { "epoch": 2.915968, "grad_norm": 1.671875, "learning_rate": 1.4077297158945483e-06, "loss": 0.3834, "step": 11392 }, { "epoch": 2.916224, "grad_norm": 1.8671875, "learning_rate": 1.4034638682706253e-06, "loss": 0.4233, "step": 11393 }, { "epoch": 2.91648, "grad_norm": 1.609375, "learning_rate": 1.3991980206467026e-06, "loss": 0.4287, "step": 11394 }, { "epoch": 2.916736, "grad_norm": 1.7578125, "learning_rate": 1.3949321730227796e-06, "loss": 0.444, "step": 11395 }, { "epoch": 2.916992, "grad_norm": 1.765625, "learning_rate": 1.3906663253988568e-06, "loss": 0.4443, "step": 11396 }, { "epoch": 2.917248, "grad_norm": 1.6796875, "learning_rate": 1.3864004777749338e-06, "loss": 0.4319, "step": 11397 }, { "epoch": 2.917504, "grad_norm": 1.75, "learning_rate": 1.382134630151011e-06, "loss": 0.4326, "step": 11398 }, { "epoch": 2.91776, "grad_norm": 1.65625, "learning_rate": 1.377868782527088e-06, "loss": 0.4328, "step": 11399 }, { "epoch": 2.918016, "grad_norm": 1.7109375, "learning_rate": 1.3736029349031653e-06, "loss": 0.4122, "step": 11400 }, { "epoch": 2.918272, "grad_norm": 1.640625, "learning_rate": 1.3693370872792423e-06, "loss": 0.4324, "step": 11401 }, { "epoch": 2.9185280000000002, "grad_norm": 1.6015625, "learning_rate": 1.3650712396553196e-06, "loss": 0.4439, "step": 11402 }, { "epoch": 2.918784, "grad_norm": 1.765625, "learning_rate": 1.3608053920313966e-06, "loss": 0.3972, "step": 11403 }, { "epoch": 2.91904, "grad_norm": 1.734375, "learning_rate": 1.3565395444074738e-06, "loss": 0.3961, "step": 11404 }, { "epoch": 2.919296, "grad_norm": 1.7734375, "learning_rate": 1.3522736967835508e-06, "loss": 0.3827, "step": 11405 }, { "epoch": 2.919552, "grad_norm": 1.7890625, "learning_rate": 1.348007849159628e-06, "loss": 0.4091, "step": 11406 }, { "epoch": 2.9198079999999997, "grad_norm": 1.75, "learning_rate": 1.343742001535705e-06, "loss": 0.4086, "step": 11407 }, { "epoch": 2.920064, "grad_norm": 1.8046875, "learning_rate": 1.3394761539117823e-06, "loss": 0.3852, "step": 11408 }, { "epoch": 2.9203200000000002, "grad_norm": 1.78125, "learning_rate": 1.3352103062878593e-06, "loss": 0.4185, "step": 11409 }, { "epoch": 2.920576, "grad_norm": 1.6953125, "learning_rate": 1.3309444586639366e-06, "loss": 0.4137, "step": 11410 }, { "epoch": 2.920832, "grad_norm": 1.7734375, "learning_rate": 1.3266786110400136e-06, "loss": 0.4079, "step": 11411 }, { "epoch": 2.921088, "grad_norm": 1.8359375, "learning_rate": 1.3224127634160908e-06, "loss": 0.3886, "step": 11412 }, { "epoch": 2.921344, "grad_norm": 1.7734375, "learning_rate": 1.3181469157921678e-06, "loss": 0.4362, "step": 11413 }, { "epoch": 2.9215999999999998, "grad_norm": 1.625, "learning_rate": 1.313881068168245e-06, "loss": 0.4114, "step": 11414 }, { "epoch": 2.921856, "grad_norm": 1.6796875, "learning_rate": 1.3096152205443223e-06, "loss": 0.4088, "step": 11415 }, { "epoch": 2.9221120000000003, "grad_norm": 1.6484375, "learning_rate": 1.3053493729203993e-06, "loss": 0.4444, "step": 11416 }, { "epoch": 2.922368, "grad_norm": 1.7265625, "learning_rate": 1.3010835252964765e-06, "loss": 0.4061, "step": 11417 }, { "epoch": 2.922624, "grad_norm": 1.6484375, "learning_rate": 1.2968176776725536e-06, "loss": 0.4439, "step": 11418 }, { "epoch": 2.92288, "grad_norm": 1.6953125, "learning_rate": 1.2925518300486308e-06, "loss": 0.4132, "step": 11419 }, { "epoch": 2.923136, "grad_norm": 1.6875, "learning_rate": 1.2882859824247078e-06, "loss": 0.4297, "step": 11420 }, { "epoch": 2.9233919999999998, "grad_norm": 1.65625, "learning_rate": 1.284020134800785e-06, "loss": 0.403, "step": 11421 }, { "epoch": 2.923648, "grad_norm": 1.7890625, "learning_rate": 1.2797542871768623e-06, "loss": 0.4143, "step": 11422 }, { "epoch": 2.923904, "grad_norm": 1.765625, "learning_rate": 1.2754884395529393e-06, "loss": 0.3963, "step": 11423 }, { "epoch": 2.92416, "grad_norm": 1.78125, "learning_rate": 1.2712225919290165e-06, "loss": 0.4126, "step": 11424 }, { "epoch": 2.924416, "grad_norm": 1.7109375, "learning_rate": 1.2669567443050935e-06, "loss": 0.441, "step": 11425 }, { "epoch": 2.924672, "grad_norm": 1.6875, "learning_rate": 1.2626908966811708e-06, "loss": 0.3824, "step": 11426 }, { "epoch": 2.924928, "grad_norm": 1.71875, "learning_rate": 1.2584250490572478e-06, "loss": 0.4323, "step": 11427 }, { "epoch": 2.925184, "grad_norm": 1.6640625, "learning_rate": 1.254159201433325e-06, "loss": 0.4141, "step": 11428 }, { "epoch": 2.92544, "grad_norm": 1.75, "learning_rate": 1.249893353809402e-06, "loss": 0.4312, "step": 11429 }, { "epoch": 2.925696, "grad_norm": 1.8203125, "learning_rate": 1.2456275061854793e-06, "loss": 0.3923, "step": 11430 }, { "epoch": 2.925952, "grad_norm": 1.8046875, "learning_rate": 1.2413616585615563e-06, "loss": 0.4617, "step": 11431 }, { "epoch": 2.926208, "grad_norm": 1.7578125, "learning_rate": 1.2370958109376333e-06, "loss": 0.4187, "step": 11432 }, { "epoch": 2.926464, "grad_norm": 1.7578125, "learning_rate": 1.2328299633137105e-06, "loss": 0.4344, "step": 11433 }, { "epoch": 2.92672, "grad_norm": 1.7421875, "learning_rate": 1.2285641156897876e-06, "loss": 0.4353, "step": 11434 }, { "epoch": 2.926976, "grad_norm": 1.75, "learning_rate": 1.2242982680658648e-06, "loss": 0.4225, "step": 11435 }, { "epoch": 2.927232, "grad_norm": 1.9453125, "learning_rate": 1.2200324204419418e-06, "loss": 0.4234, "step": 11436 }, { "epoch": 2.927488, "grad_norm": 1.6953125, "learning_rate": 1.215766572818019e-06, "loss": 0.4199, "step": 11437 }, { "epoch": 2.927744, "grad_norm": 1.6953125, "learning_rate": 1.211500725194096e-06, "loss": 0.3826, "step": 11438 }, { "epoch": 2.928, "grad_norm": 1.7578125, "learning_rate": 1.2072348775701733e-06, "loss": 0.4153, "step": 11439 }, { "epoch": 2.928256, "grad_norm": 1.6953125, "learning_rate": 1.2029690299462503e-06, "loss": 0.4081, "step": 11440 }, { "epoch": 2.928512, "grad_norm": 1.7578125, "learning_rate": 1.1987031823223275e-06, "loss": 0.4271, "step": 11441 }, { "epoch": 2.928768, "grad_norm": 1.734375, "learning_rate": 1.1944373346984046e-06, "loss": 0.4027, "step": 11442 }, { "epoch": 2.929024, "grad_norm": 1.6796875, "learning_rate": 1.1901714870744818e-06, "loss": 0.4214, "step": 11443 }, { "epoch": 2.92928, "grad_norm": 1.75, "learning_rate": 1.1859056394505588e-06, "loss": 0.4229, "step": 11444 }, { "epoch": 2.929536, "grad_norm": 1.6953125, "learning_rate": 1.181639791826636e-06, "loss": 0.3996, "step": 11445 }, { "epoch": 2.929792, "grad_norm": 1.6796875, "learning_rate": 1.177373944202713e-06, "loss": 0.409, "step": 11446 }, { "epoch": 2.930048, "grad_norm": 1.640625, "learning_rate": 1.1731080965787903e-06, "loss": 0.4122, "step": 11447 }, { "epoch": 2.930304, "grad_norm": 1.78125, "learning_rate": 1.1688422489548673e-06, "loss": 0.4192, "step": 11448 }, { "epoch": 2.93056, "grad_norm": 1.71875, "learning_rate": 1.1645764013309445e-06, "loss": 0.4093, "step": 11449 }, { "epoch": 2.930816, "grad_norm": 1.7890625, "learning_rate": 1.1603105537070216e-06, "loss": 0.409, "step": 11450 }, { "epoch": 2.931072, "grad_norm": 1.65625, "learning_rate": 1.1560447060830988e-06, "loss": 0.4268, "step": 11451 }, { "epoch": 2.931328, "grad_norm": 1.7578125, "learning_rate": 1.1517788584591758e-06, "loss": 0.4038, "step": 11452 }, { "epoch": 2.931584, "grad_norm": 1.796875, "learning_rate": 1.147513010835253e-06, "loss": 0.4148, "step": 11453 }, { "epoch": 2.9318400000000002, "grad_norm": 1.7421875, "learning_rate": 1.14324716321133e-06, "loss": 0.4006, "step": 11454 }, { "epoch": 2.932096, "grad_norm": 1.65625, "learning_rate": 1.1389813155874073e-06, "loss": 0.4363, "step": 11455 }, { "epoch": 2.932352, "grad_norm": 1.625, "learning_rate": 1.1347154679634843e-06, "loss": 0.4404, "step": 11456 }, { "epoch": 2.932608, "grad_norm": 1.7890625, "learning_rate": 1.1304496203395615e-06, "loss": 0.4129, "step": 11457 }, { "epoch": 2.932864, "grad_norm": 1.7109375, "learning_rate": 1.1261837727156386e-06, "loss": 0.4325, "step": 11458 }, { "epoch": 2.9331199999999997, "grad_norm": 1.765625, "learning_rate": 1.1219179250917158e-06, "loss": 0.4519, "step": 11459 }, { "epoch": 2.933376, "grad_norm": 1.7890625, "learning_rate": 1.1176520774677928e-06, "loss": 0.4203, "step": 11460 }, { "epoch": 2.9336320000000002, "grad_norm": 1.7265625, "learning_rate": 1.11338622984387e-06, "loss": 0.4086, "step": 11461 }, { "epoch": 2.933888, "grad_norm": 1.6640625, "learning_rate": 1.109120382219947e-06, "loss": 0.439, "step": 11462 }, { "epoch": 2.934144, "grad_norm": 1.6484375, "learning_rate": 1.1048545345960243e-06, "loss": 0.4294, "step": 11463 }, { "epoch": 2.9344, "grad_norm": 1.78125, "learning_rate": 1.1005886869721013e-06, "loss": 0.4554, "step": 11464 }, { "epoch": 2.934656, "grad_norm": 1.6875, "learning_rate": 1.0963228393481785e-06, "loss": 0.4018, "step": 11465 }, { "epoch": 2.9349119999999997, "grad_norm": 1.890625, "learning_rate": 1.0920569917242556e-06, "loss": 0.4202, "step": 11466 }, { "epoch": 2.935168, "grad_norm": 1.8359375, "learning_rate": 1.0877911441003328e-06, "loss": 0.4333, "step": 11467 }, { "epoch": 2.9354240000000003, "grad_norm": 1.859375, "learning_rate": 1.0835252964764098e-06, "loss": 0.4176, "step": 11468 }, { "epoch": 2.93568, "grad_norm": 1.7890625, "learning_rate": 1.079259448852487e-06, "loss": 0.4227, "step": 11469 }, { "epoch": 2.935936, "grad_norm": 1.6875, "learning_rate": 1.074993601228564e-06, "loss": 0.389, "step": 11470 }, { "epoch": 2.936192, "grad_norm": 1.71875, "learning_rate": 1.0707277536046413e-06, "loss": 0.4182, "step": 11471 }, { "epoch": 2.936448, "grad_norm": 1.7109375, "learning_rate": 1.0664619059807183e-06, "loss": 0.4466, "step": 11472 }, { "epoch": 2.9367039999999998, "grad_norm": 1.84375, "learning_rate": 1.0621960583567955e-06, "loss": 0.414, "step": 11473 }, { "epoch": 2.93696, "grad_norm": 1.78125, "learning_rate": 1.0579302107328728e-06, "loss": 0.3913, "step": 11474 }, { "epoch": 2.9372160000000003, "grad_norm": 1.71875, "learning_rate": 1.0536643631089498e-06, "loss": 0.4512, "step": 11475 }, { "epoch": 2.937472, "grad_norm": 1.6640625, "learning_rate": 1.049398515485027e-06, "loss": 0.3932, "step": 11476 }, { "epoch": 2.937728, "grad_norm": 1.6015625, "learning_rate": 1.045132667861104e-06, "loss": 0.4354, "step": 11477 }, { "epoch": 2.937984, "grad_norm": 1.6875, "learning_rate": 1.0408668202371813e-06, "loss": 0.4187, "step": 11478 }, { "epoch": 2.93824, "grad_norm": 1.7578125, "learning_rate": 1.0366009726132583e-06, "loss": 0.4142, "step": 11479 }, { "epoch": 2.9384959999999998, "grad_norm": 1.6953125, "learning_rate": 1.0323351249893355e-06, "loss": 0.4271, "step": 11480 }, { "epoch": 2.938752, "grad_norm": 1.7265625, "learning_rate": 1.0280692773654125e-06, "loss": 0.392, "step": 11481 }, { "epoch": 2.939008, "grad_norm": 1.71875, "learning_rate": 1.0238034297414898e-06, "loss": 0.4311, "step": 11482 }, { "epoch": 2.939264, "grad_norm": 1.71875, "learning_rate": 1.0195375821175668e-06, "loss": 0.4192, "step": 11483 }, { "epoch": 2.93952, "grad_norm": 1.703125, "learning_rate": 1.015271734493644e-06, "loss": 0.4226, "step": 11484 }, { "epoch": 2.939776, "grad_norm": 1.65625, "learning_rate": 1.011005886869721e-06, "loss": 0.436, "step": 11485 }, { "epoch": 2.940032, "grad_norm": 1.7578125, "learning_rate": 1.0067400392457983e-06, "loss": 0.4348, "step": 11486 }, { "epoch": 2.940288, "grad_norm": 1.6328125, "learning_rate": 1.0024741916218753e-06, "loss": 0.4193, "step": 11487 }, { "epoch": 2.940544, "grad_norm": 1.84375, "learning_rate": 9.982083439979525e-07, "loss": 0.4008, "step": 11488 }, { "epoch": 2.9408, "grad_norm": 1.8203125, "learning_rate": 9.939424963740295e-07, "loss": 0.4154, "step": 11489 }, { "epoch": 2.941056, "grad_norm": 1.8203125, "learning_rate": 9.896766487501068e-07, "loss": 0.393, "step": 11490 }, { "epoch": 2.941312, "grad_norm": 1.7421875, "learning_rate": 9.854108011261838e-07, "loss": 0.3792, "step": 11491 }, { "epoch": 2.941568, "grad_norm": 1.7734375, "learning_rate": 9.81144953502261e-07, "loss": 0.3999, "step": 11492 }, { "epoch": 2.941824, "grad_norm": 1.640625, "learning_rate": 9.76879105878338e-07, "loss": 0.4521, "step": 11493 }, { "epoch": 2.94208, "grad_norm": 1.7265625, "learning_rate": 9.726132582544153e-07, "loss": 0.4249, "step": 11494 }, { "epoch": 2.942336, "grad_norm": 1.7265625, "learning_rate": 9.683474106304923e-07, "loss": 0.3986, "step": 11495 }, { "epoch": 2.942592, "grad_norm": 1.7734375, "learning_rate": 9.640815630065695e-07, "loss": 0.4064, "step": 11496 }, { "epoch": 2.942848, "grad_norm": 1.6484375, "learning_rate": 9.598157153826465e-07, "loss": 0.4425, "step": 11497 }, { "epoch": 2.943104, "grad_norm": 1.75, "learning_rate": 9.555498677587238e-07, "loss": 0.417, "step": 11498 }, { "epoch": 2.94336, "grad_norm": 1.84375, "learning_rate": 9.512840201348008e-07, "loss": 0.4112, "step": 11499 }, { "epoch": 2.943616, "grad_norm": 1.7109375, "learning_rate": 9.47018172510878e-07, "loss": 0.3659, "step": 11500 }, { "epoch": 2.943872, "grad_norm": 1.7109375, "learning_rate": 9.42752324886955e-07, "loss": 0.4111, "step": 11501 }, { "epoch": 2.944128, "grad_norm": 1.7890625, "learning_rate": 9.384864772630323e-07, "loss": 0.4305, "step": 11502 }, { "epoch": 2.944384, "grad_norm": 1.78125, "learning_rate": 9.342206296391093e-07, "loss": 0.4092, "step": 11503 }, { "epoch": 2.94464, "grad_norm": 1.6875, "learning_rate": 9.299547820151865e-07, "loss": 0.4427, "step": 11504 }, { "epoch": 2.944896, "grad_norm": 1.625, "learning_rate": 9.256889343912635e-07, "loss": 0.4142, "step": 11505 }, { "epoch": 2.945152, "grad_norm": 1.671875, "learning_rate": 9.214230867673408e-07, "loss": 0.4282, "step": 11506 }, { "epoch": 2.945408, "grad_norm": 1.78125, "learning_rate": 9.171572391434178e-07, "loss": 0.4043, "step": 11507 }, { "epoch": 2.945664, "grad_norm": 1.765625, "learning_rate": 9.12891391519495e-07, "loss": 0.354, "step": 11508 }, { "epoch": 2.94592, "grad_norm": 1.609375, "learning_rate": 9.08625543895572e-07, "loss": 0.4443, "step": 11509 }, { "epoch": 2.946176, "grad_norm": 1.7421875, "learning_rate": 9.043596962716493e-07, "loss": 0.4123, "step": 11510 }, { "epoch": 2.946432, "grad_norm": 1.703125, "learning_rate": 9.000938486477263e-07, "loss": 0.4454, "step": 11511 }, { "epoch": 2.946688, "grad_norm": 1.6640625, "learning_rate": 8.958280010238035e-07, "loss": 0.41, "step": 11512 }, { "epoch": 2.9469440000000002, "grad_norm": 1.8046875, "learning_rate": 8.915621533998805e-07, "loss": 0.4248, "step": 11513 }, { "epoch": 2.9472, "grad_norm": 1.703125, "learning_rate": 8.872963057759577e-07, "loss": 0.4606, "step": 11514 }, { "epoch": 2.947456, "grad_norm": 1.6484375, "learning_rate": 8.830304581520349e-07, "loss": 0.4193, "step": 11515 }, { "epoch": 2.947712, "grad_norm": 1.6015625, "learning_rate": 8.787646105281119e-07, "loss": 0.4187, "step": 11516 }, { "epoch": 2.947968, "grad_norm": 1.8125, "learning_rate": 8.744987629041892e-07, "loss": 0.4462, "step": 11517 }, { "epoch": 2.9482239999999997, "grad_norm": 1.484375, "learning_rate": 8.702329152802662e-07, "loss": 0.4671, "step": 11518 }, { "epoch": 2.94848, "grad_norm": 1.7734375, "learning_rate": 8.659670676563434e-07, "loss": 0.4301, "step": 11519 }, { "epoch": 2.9487360000000002, "grad_norm": 1.7421875, "learning_rate": 8.617012200324204e-07, "loss": 0.4583, "step": 11520 }, { "epoch": 2.948992, "grad_norm": 1.7734375, "learning_rate": 8.574353724084977e-07, "loss": 0.4178, "step": 11521 }, { "epoch": 2.949248, "grad_norm": 1.7734375, "learning_rate": 8.531695247845747e-07, "loss": 0.4251, "step": 11522 }, { "epoch": 2.949504, "grad_norm": 1.75, "learning_rate": 8.489036771606519e-07, "loss": 0.4329, "step": 11523 }, { "epoch": 2.94976, "grad_norm": 1.71875, "learning_rate": 8.446378295367289e-07, "loss": 0.464, "step": 11524 }, { "epoch": 2.9500159999999997, "grad_norm": 1.8125, "learning_rate": 8.403719819128062e-07, "loss": 0.4098, "step": 11525 }, { "epoch": 2.950272, "grad_norm": 1.7265625, "learning_rate": 8.361061342888832e-07, "loss": 0.4234, "step": 11526 }, { "epoch": 2.9505280000000003, "grad_norm": 1.7890625, "learning_rate": 8.318402866649604e-07, "loss": 0.423, "step": 11527 }, { "epoch": 2.950784, "grad_norm": 1.6171875, "learning_rate": 8.275744390410374e-07, "loss": 0.4379, "step": 11528 }, { "epoch": 2.95104, "grad_norm": 1.6640625, "learning_rate": 8.233085914171147e-07, "loss": 0.3959, "step": 11529 }, { "epoch": 2.951296, "grad_norm": 1.6796875, "learning_rate": 8.190427437931917e-07, "loss": 0.4534, "step": 11530 }, { "epoch": 2.951552, "grad_norm": 1.6640625, "learning_rate": 8.147768961692689e-07, "loss": 0.4289, "step": 11531 }, { "epoch": 2.9518079999999998, "grad_norm": 1.65625, "learning_rate": 8.105110485453459e-07, "loss": 0.4048, "step": 11532 }, { "epoch": 2.952064, "grad_norm": 1.7421875, "learning_rate": 8.062452009214232e-07, "loss": 0.4141, "step": 11533 }, { "epoch": 2.9523200000000003, "grad_norm": 1.8203125, "learning_rate": 8.019793532975002e-07, "loss": 0.4422, "step": 11534 }, { "epoch": 2.952576, "grad_norm": 1.6875, "learning_rate": 7.977135056735774e-07, "loss": 0.4158, "step": 11535 }, { "epoch": 2.952832, "grad_norm": 1.578125, "learning_rate": 7.934476580496544e-07, "loss": 0.3762, "step": 11536 }, { "epoch": 2.953088, "grad_norm": 1.6953125, "learning_rate": 7.891818104257317e-07, "loss": 0.4, "step": 11537 }, { "epoch": 2.953344, "grad_norm": 1.7421875, "learning_rate": 7.849159628018087e-07, "loss": 0.3908, "step": 11538 }, { "epoch": 2.9536, "grad_norm": 1.609375, "learning_rate": 7.806501151778858e-07, "loss": 0.4113, "step": 11539 }, { "epoch": 2.953856, "grad_norm": 1.671875, "learning_rate": 7.76384267553963e-07, "loss": 0.4268, "step": 11540 }, { "epoch": 2.954112, "grad_norm": 1.7421875, "learning_rate": 7.721184199300402e-07, "loss": 0.3946, "step": 11541 }, { "epoch": 2.954368, "grad_norm": 1.7109375, "learning_rate": 7.678525723061173e-07, "loss": 0.3986, "step": 11542 }, { "epoch": 2.954624, "grad_norm": 1.6796875, "learning_rate": 7.635867246821944e-07, "loss": 0.4352, "step": 11543 }, { "epoch": 2.95488, "grad_norm": 1.640625, "learning_rate": 7.593208770582715e-07, "loss": 0.4108, "step": 11544 }, { "epoch": 2.955136, "grad_norm": 1.6640625, "learning_rate": 7.550550294343487e-07, "loss": 0.4597, "step": 11545 }, { "epoch": 2.955392, "grad_norm": 1.7890625, "learning_rate": 7.507891818104258e-07, "loss": 0.4173, "step": 11546 }, { "epoch": 2.955648, "grad_norm": 1.7890625, "learning_rate": 7.465233341865029e-07, "loss": 0.4003, "step": 11547 }, { "epoch": 2.955904, "grad_norm": 1.71875, "learning_rate": 7.4225748656258e-07, "loss": 0.403, "step": 11548 }, { "epoch": 2.95616, "grad_norm": 1.65625, "learning_rate": 7.379916389386572e-07, "loss": 0.4181, "step": 11549 }, { "epoch": 2.956416, "grad_norm": 1.7265625, "learning_rate": 7.337257913147343e-07, "loss": 0.4413, "step": 11550 }, { "epoch": 2.956672, "grad_norm": 1.7265625, "learning_rate": 7.294599436908114e-07, "loss": 0.4512, "step": 11551 }, { "epoch": 2.956928, "grad_norm": 1.734375, "learning_rate": 7.251940960668885e-07, "loss": 0.4018, "step": 11552 }, { "epoch": 2.957184, "grad_norm": 1.765625, "learning_rate": 7.209282484429657e-07, "loss": 0.4525, "step": 11553 }, { "epoch": 2.95744, "grad_norm": 1.7578125, "learning_rate": 7.166624008190428e-07, "loss": 0.4235, "step": 11554 }, { "epoch": 2.957696, "grad_norm": 1.6875, "learning_rate": 7.123965531951199e-07, "loss": 0.4466, "step": 11555 }, { "epoch": 2.957952, "grad_norm": 1.640625, "learning_rate": 7.08130705571197e-07, "loss": 0.4377, "step": 11556 }, { "epoch": 2.958208, "grad_norm": 1.6484375, "learning_rate": 7.038648579472742e-07, "loss": 0.4794, "step": 11557 }, { "epoch": 2.958464, "grad_norm": 1.6640625, "learning_rate": 6.995990103233513e-07, "loss": 0.4155, "step": 11558 }, { "epoch": 2.95872, "grad_norm": 1.7265625, "learning_rate": 6.953331626994284e-07, "loss": 0.3973, "step": 11559 }, { "epoch": 2.958976, "grad_norm": 1.703125, "learning_rate": 6.910673150755055e-07, "loss": 0.4187, "step": 11560 }, { "epoch": 2.959232, "grad_norm": 1.640625, "learning_rate": 6.868014674515827e-07, "loss": 0.4124, "step": 11561 }, { "epoch": 2.959488, "grad_norm": 1.7890625, "learning_rate": 6.825356198276598e-07, "loss": 0.4062, "step": 11562 }, { "epoch": 2.959744, "grad_norm": 1.75, "learning_rate": 6.782697722037369e-07, "loss": 0.4211, "step": 11563 }, { "epoch": 2.96, "grad_norm": 1.7890625, "learning_rate": 6.74003924579814e-07, "loss": 0.4377, "step": 11564 }, { "epoch": 2.960256, "grad_norm": 1.671875, "learning_rate": 6.697380769558912e-07, "loss": 0.4201, "step": 11565 }, { "epoch": 2.960512, "grad_norm": 1.6484375, "learning_rate": 6.654722293319683e-07, "loss": 0.4192, "step": 11566 }, { "epoch": 2.960768, "grad_norm": 1.7578125, "learning_rate": 6.612063817080454e-07, "loss": 0.4102, "step": 11567 }, { "epoch": 2.961024, "grad_norm": 1.6796875, "learning_rate": 6.569405340841225e-07, "loss": 0.3923, "step": 11568 }, { "epoch": 2.96128, "grad_norm": 1.7109375, "learning_rate": 6.526746864601997e-07, "loss": 0.396, "step": 11569 }, { "epoch": 2.9615359999999997, "grad_norm": 1.6171875, "learning_rate": 6.484088388362768e-07, "loss": 0.4689, "step": 11570 }, { "epoch": 2.961792, "grad_norm": 1.6953125, "learning_rate": 6.441429912123539e-07, "loss": 0.4515, "step": 11571 }, { "epoch": 2.9620480000000002, "grad_norm": 1.765625, "learning_rate": 6.398771435884311e-07, "loss": 0.4168, "step": 11572 }, { "epoch": 2.962304, "grad_norm": 1.8359375, "learning_rate": 6.356112959645083e-07, "loss": 0.4625, "step": 11573 }, { "epoch": 2.96256, "grad_norm": 1.7734375, "learning_rate": 6.313454483405854e-07, "loss": 0.4174, "step": 11574 }, { "epoch": 2.962816, "grad_norm": 1.765625, "learning_rate": 6.270796007166625e-07, "loss": 0.4322, "step": 11575 }, { "epoch": 2.963072, "grad_norm": 1.84375, "learning_rate": 6.228137530927396e-07, "loss": 0.4264, "step": 11576 }, { "epoch": 2.9633279999999997, "grad_norm": 1.7265625, "learning_rate": 6.185479054688167e-07, "loss": 0.4036, "step": 11577 }, { "epoch": 2.963584, "grad_norm": 1.75, "learning_rate": 6.142820578448938e-07, "loss": 0.4161, "step": 11578 }, { "epoch": 2.9638400000000003, "grad_norm": 1.828125, "learning_rate": 6.100162102209709e-07, "loss": 0.4068, "step": 11579 }, { "epoch": 2.964096, "grad_norm": 1.7265625, "learning_rate": 6.05750362597048e-07, "loss": 0.4381, "step": 11580 }, { "epoch": 2.964352, "grad_norm": 1.671875, "learning_rate": 6.014845149731252e-07, "loss": 0.4077, "step": 11581 }, { "epoch": 2.964608, "grad_norm": 1.71875, "learning_rate": 5.972186673492023e-07, "loss": 0.4558, "step": 11582 }, { "epoch": 2.964864, "grad_norm": 1.7890625, "learning_rate": 5.929528197252794e-07, "loss": 0.4353, "step": 11583 }, { "epoch": 2.9651199999999998, "grad_norm": 1.75, "learning_rate": 5.886869721013565e-07, "loss": 0.3737, "step": 11584 }, { "epoch": 2.965376, "grad_norm": 1.6875, "learning_rate": 5.844211244774337e-07, "loss": 0.4154, "step": 11585 }, { "epoch": 2.9656320000000003, "grad_norm": 1.6796875, "learning_rate": 5.801552768535108e-07, "loss": 0.3963, "step": 11586 }, { "epoch": 2.965888, "grad_norm": 1.71875, "learning_rate": 5.758894292295879e-07, "loss": 0.394, "step": 11587 }, { "epoch": 2.966144, "grad_norm": 1.7890625, "learning_rate": 5.71623581605665e-07, "loss": 0.382, "step": 11588 }, { "epoch": 2.9664, "grad_norm": 1.625, "learning_rate": 5.673577339817422e-07, "loss": 0.4118, "step": 11589 }, { "epoch": 2.966656, "grad_norm": 1.7578125, "learning_rate": 5.630918863578193e-07, "loss": 0.4308, "step": 11590 }, { "epoch": 2.9669119999999998, "grad_norm": 1.90625, "learning_rate": 5.588260387338964e-07, "loss": 0.45, "step": 11591 }, { "epoch": 2.967168, "grad_norm": 1.71875, "learning_rate": 5.545601911099735e-07, "loss": 0.3744, "step": 11592 }, { "epoch": 2.967424, "grad_norm": 1.84375, "learning_rate": 5.502943434860507e-07, "loss": 0.407, "step": 11593 }, { "epoch": 2.96768, "grad_norm": 1.7734375, "learning_rate": 5.460284958621278e-07, "loss": 0.4656, "step": 11594 }, { "epoch": 2.967936, "grad_norm": 1.6796875, "learning_rate": 5.417626482382049e-07, "loss": 0.3971, "step": 11595 }, { "epoch": 2.968192, "grad_norm": 1.6953125, "learning_rate": 5.37496800614282e-07, "loss": 0.4215, "step": 11596 }, { "epoch": 2.968448, "grad_norm": 1.7734375, "learning_rate": 5.332309529903592e-07, "loss": 0.4171, "step": 11597 }, { "epoch": 2.968704, "grad_norm": 1.6875, "learning_rate": 5.289651053664364e-07, "loss": 0.4047, "step": 11598 }, { "epoch": 2.96896, "grad_norm": 1.6640625, "learning_rate": 5.246992577425135e-07, "loss": 0.4257, "step": 11599 }, { "epoch": 2.969216, "grad_norm": 1.7109375, "learning_rate": 5.204334101185906e-07, "loss": 0.437, "step": 11600 }, { "epoch": 2.969472, "grad_norm": 1.640625, "learning_rate": 5.161675624946678e-07, "loss": 0.4044, "step": 11601 }, { "epoch": 2.969728, "grad_norm": 1.6953125, "learning_rate": 5.119017148707449e-07, "loss": 0.4181, "step": 11602 }, { "epoch": 2.969984, "grad_norm": 1.7578125, "learning_rate": 5.07635867246822e-07, "loss": 0.4196, "step": 11603 }, { "epoch": 2.97024, "grad_norm": 1.65625, "learning_rate": 5.033700196228991e-07, "loss": 0.4084, "step": 11604 }, { "epoch": 2.970496, "grad_norm": 1.6015625, "learning_rate": 4.991041719989763e-07, "loss": 0.3968, "step": 11605 }, { "epoch": 2.970752, "grad_norm": 1.6953125, "learning_rate": 4.948383243750534e-07, "loss": 0.4388, "step": 11606 }, { "epoch": 2.971008, "grad_norm": 1.703125, "learning_rate": 4.905724767511305e-07, "loss": 0.4352, "step": 11607 }, { "epoch": 2.971264, "grad_norm": 1.765625, "learning_rate": 4.863066291272076e-07, "loss": 0.3892, "step": 11608 }, { "epoch": 2.97152, "grad_norm": 1.828125, "learning_rate": 4.820407815032848e-07, "loss": 0.4138, "step": 11609 }, { "epoch": 2.971776, "grad_norm": 1.6640625, "learning_rate": 4.777749338793619e-07, "loss": 0.3791, "step": 11610 }, { "epoch": 2.972032, "grad_norm": 1.8125, "learning_rate": 4.73509086255439e-07, "loss": 0.426, "step": 11611 }, { "epoch": 2.972288, "grad_norm": 1.71875, "learning_rate": 4.6924323863151614e-07, "loss": 0.4248, "step": 11612 }, { "epoch": 2.972544, "grad_norm": 1.75, "learning_rate": 4.6497739100759326e-07, "loss": 0.4064, "step": 11613 }, { "epoch": 2.9728, "grad_norm": 1.6171875, "learning_rate": 4.607115433836704e-07, "loss": 0.4115, "step": 11614 }, { "epoch": 2.973056, "grad_norm": 1.7734375, "learning_rate": 4.564456957597475e-07, "loss": 0.4427, "step": 11615 }, { "epoch": 2.973312, "grad_norm": 1.6484375, "learning_rate": 4.5217984813582464e-07, "loss": 0.4241, "step": 11616 }, { "epoch": 2.973568, "grad_norm": 1.8046875, "learning_rate": 4.4791400051190176e-07, "loss": 0.4118, "step": 11617 }, { "epoch": 2.973824, "grad_norm": 1.8671875, "learning_rate": 4.4364815288797884e-07, "loss": 0.4746, "step": 11618 }, { "epoch": 2.97408, "grad_norm": 1.6171875, "learning_rate": 4.3938230526405596e-07, "loss": 0.4407, "step": 11619 }, { "epoch": 2.974336, "grad_norm": 1.578125, "learning_rate": 4.351164576401331e-07, "loss": 0.4166, "step": 11620 }, { "epoch": 2.974592, "grad_norm": 1.8671875, "learning_rate": 4.308506100162102e-07, "loss": 0.4329, "step": 11621 }, { "epoch": 2.974848, "grad_norm": 1.828125, "learning_rate": 4.2658476239228734e-07, "loss": 0.4119, "step": 11622 }, { "epoch": 2.975104, "grad_norm": 1.640625, "learning_rate": 4.2231891476836446e-07, "loss": 0.4307, "step": 11623 }, { "epoch": 2.9753600000000002, "grad_norm": 1.875, "learning_rate": 4.180530671444416e-07, "loss": 0.4474, "step": 11624 }, { "epoch": 2.975616, "grad_norm": 1.8984375, "learning_rate": 4.137872195205187e-07, "loss": 0.4027, "step": 11625 }, { "epoch": 2.975872, "grad_norm": 1.8125, "learning_rate": 4.0952137189659584e-07, "loss": 0.4184, "step": 11626 }, { "epoch": 2.976128, "grad_norm": 1.6484375, "learning_rate": 4.0525552427267296e-07, "loss": 0.3948, "step": 11627 }, { "epoch": 2.976384, "grad_norm": 1.734375, "learning_rate": 4.009896766487501e-07, "loss": 0.4224, "step": 11628 }, { "epoch": 2.9766399999999997, "grad_norm": 1.78125, "learning_rate": 3.967238290248272e-07, "loss": 0.4251, "step": 11629 }, { "epoch": 2.976896, "grad_norm": 1.734375, "learning_rate": 3.9245798140090434e-07, "loss": 0.4327, "step": 11630 }, { "epoch": 2.9771520000000002, "grad_norm": 1.8359375, "learning_rate": 3.881921337769815e-07, "loss": 0.4382, "step": 11631 }, { "epoch": 2.977408, "grad_norm": 1.640625, "learning_rate": 3.8392628615305864e-07, "loss": 0.4457, "step": 11632 }, { "epoch": 2.977664, "grad_norm": 1.65625, "learning_rate": 3.7966043852913576e-07, "loss": 0.416, "step": 11633 }, { "epoch": 2.97792, "grad_norm": 1.734375, "learning_rate": 3.753945909052129e-07, "loss": 0.425, "step": 11634 }, { "epoch": 2.978176, "grad_norm": 1.7578125, "learning_rate": 3.7112874328129e-07, "loss": 0.4305, "step": 11635 }, { "epoch": 2.9784319999999997, "grad_norm": 1.671875, "learning_rate": 3.6686289565736714e-07, "loss": 0.4179, "step": 11636 }, { "epoch": 2.978688, "grad_norm": 1.6953125, "learning_rate": 3.6259704803344427e-07, "loss": 0.413, "step": 11637 }, { "epoch": 2.9789440000000003, "grad_norm": 1.8046875, "learning_rate": 3.583312004095214e-07, "loss": 0.4628, "step": 11638 }, { "epoch": 2.9792, "grad_norm": 1.7890625, "learning_rate": 3.540653527855985e-07, "loss": 0.4355, "step": 11639 }, { "epoch": 2.979456, "grad_norm": 1.78125, "learning_rate": 3.4979950516167564e-07, "loss": 0.4419, "step": 11640 }, { "epoch": 2.979712, "grad_norm": 1.765625, "learning_rate": 3.4553365753775277e-07, "loss": 0.4045, "step": 11641 }, { "epoch": 2.979968, "grad_norm": 1.765625, "learning_rate": 3.412678099138299e-07, "loss": 0.421, "step": 11642 }, { "epoch": 2.9802239999999998, "grad_norm": 1.671875, "learning_rate": 3.37001962289907e-07, "loss": 0.4062, "step": 11643 }, { "epoch": 2.98048, "grad_norm": 1.7578125, "learning_rate": 3.3273611466598414e-07, "loss": 0.4464, "step": 11644 }, { "epoch": 2.9807360000000003, "grad_norm": 1.8515625, "learning_rate": 3.2847026704206127e-07, "loss": 0.407, "step": 11645 }, { "epoch": 2.980992, "grad_norm": 1.8125, "learning_rate": 3.242044194181384e-07, "loss": 0.4259, "step": 11646 }, { "epoch": 2.981248, "grad_norm": 1.7265625, "learning_rate": 3.1993857179421557e-07, "loss": 0.4622, "step": 11647 }, { "epoch": 2.981504, "grad_norm": 1.6171875, "learning_rate": 3.156727241702927e-07, "loss": 0.4086, "step": 11648 }, { "epoch": 2.98176, "grad_norm": 1.6796875, "learning_rate": 3.114068765463698e-07, "loss": 0.4105, "step": 11649 }, { "epoch": 2.982016, "grad_norm": 1.640625, "learning_rate": 3.071410289224469e-07, "loss": 0.4472, "step": 11650 }, { "epoch": 2.982272, "grad_norm": 1.8125, "learning_rate": 3.02875181298524e-07, "loss": 0.4341, "step": 11651 }, { "epoch": 2.982528, "grad_norm": 1.6171875, "learning_rate": 2.9860933367460114e-07, "loss": 0.4151, "step": 11652 }, { "epoch": 2.982784, "grad_norm": 1.671875, "learning_rate": 2.9434348605067827e-07, "loss": 0.4093, "step": 11653 }, { "epoch": 2.98304, "grad_norm": 1.6328125, "learning_rate": 2.900776384267554e-07, "loss": 0.451, "step": 11654 }, { "epoch": 2.983296, "grad_norm": 1.5859375, "learning_rate": 2.858117908028325e-07, "loss": 0.4174, "step": 11655 }, { "epoch": 2.983552, "grad_norm": 1.7578125, "learning_rate": 2.8154594317890964e-07, "loss": 0.4775, "step": 11656 }, { "epoch": 2.983808, "grad_norm": 1.859375, "learning_rate": 2.7728009555498677e-07, "loss": 0.4046, "step": 11657 }, { "epoch": 2.984064, "grad_norm": 1.7734375, "learning_rate": 2.730142479310639e-07, "loss": 0.4053, "step": 11658 }, { "epoch": 2.98432, "grad_norm": 1.7734375, "learning_rate": 2.68748400307141e-07, "loss": 0.4417, "step": 11659 }, { "epoch": 2.984576, "grad_norm": 1.6640625, "learning_rate": 2.644825526832182e-07, "loss": 0.4174, "step": 11660 }, { "epoch": 2.984832, "grad_norm": 1.828125, "learning_rate": 2.602167050592953e-07, "loss": 0.3997, "step": 11661 }, { "epoch": 2.985088, "grad_norm": 1.6875, "learning_rate": 2.5595085743537244e-07, "loss": 0.414, "step": 11662 }, { "epoch": 2.985344, "grad_norm": 1.6640625, "learning_rate": 2.5168500981144957e-07, "loss": 0.3964, "step": 11663 }, { "epoch": 2.9856, "grad_norm": 1.671875, "learning_rate": 2.474191621875267e-07, "loss": 0.4475, "step": 11664 }, { "epoch": 2.985856, "grad_norm": 1.7265625, "learning_rate": 2.431533145636038e-07, "loss": 0.4461, "step": 11665 }, { "epoch": 2.986112, "grad_norm": 1.6796875, "learning_rate": 2.3888746693968094e-07, "loss": 0.4516, "step": 11666 }, { "epoch": 2.986368, "grad_norm": 1.6796875, "learning_rate": 2.3462161931575807e-07, "loss": 0.4554, "step": 11667 }, { "epoch": 2.986624, "grad_norm": 1.640625, "learning_rate": 2.303557716918352e-07, "loss": 0.3946, "step": 11668 }, { "epoch": 2.98688, "grad_norm": 1.6875, "learning_rate": 2.2608992406791232e-07, "loss": 0.465, "step": 11669 }, { "epoch": 2.987136, "grad_norm": 1.65625, "learning_rate": 2.2182407644398942e-07, "loss": 0.4011, "step": 11670 }, { "epoch": 2.987392, "grad_norm": 1.6875, "learning_rate": 2.1755822882006654e-07, "loss": 0.4192, "step": 11671 }, { "epoch": 2.987648, "grad_norm": 1.890625, "learning_rate": 2.1329238119614367e-07, "loss": 0.4204, "step": 11672 }, { "epoch": 2.987904, "grad_norm": 1.84375, "learning_rate": 2.090265335722208e-07, "loss": 0.4369, "step": 11673 }, { "epoch": 2.98816, "grad_norm": 1.796875, "learning_rate": 2.0476068594829792e-07, "loss": 0.4195, "step": 11674 }, { "epoch": 2.988416, "grad_norm": 1.7734375, "learning_rate": 2.0049483832437504e-07, "loss": 0.3964, "step": 11675 }, { "epoch": 2.988672, "grad_norm": 1.7578125, "learning_rate": 1.9622899070045217e-07, "loss": 0.4729, "step": 11676 }, { "epoch": 2.988928, "grad_norm": 1.6015625, "learning_rate": 1.9196314307652932e-07, "loss": 0.4198, "step": 11677 }, { "epoch": 2.989184, "grad_norm": 1.875, "learning_rate": 1.8769729545260644e-07, "loss": 0.4246, "step": 11678 }, { "epoch": 2.98944, "grad_norm": 1.640625, "learning_rate": 1.8343144782868357e-07, "loss": 0.4115, "step": 11679 }, { "epoch": 2.989696, "grad_norm": 1.7734375, "learning_rate": 1.791656002047607e-07, "loss": 0.4236, "step": 11680 }, { "epoch": 2.989952, "grad_norm": 1.8125, "learning_rate": 1.7489975258083782e-07, "loss": 0.4034, "step": 11681 }, { "epoch": 2.990208, "grad_norm": 1.796875, "learning_rate": 1.7063390495691495e-07, "loss": 0.4339, "step": 11682 }, { "epoch": 2.9904640000000002, "grad_norm": 1.703125, "learning_rate": 1.6636805733299207e-07, "loss": 0.4367, "step": 11683 }, { "epoch": 2.99072, "grad_norm": 1.8203125, "learning_rate": 1.621022097090692e-07, "loss": 0.404, "step": 11684 }, { "epoch": 2.990976, "grad_norm": 1.65625, "learning_rate": 1.5783636208514635e-07, "loss": 0.4365, "step": 11685 }, { "epoch": 2.991232, "grad_norm": 1.9453125, "learning_rate": 1.5357051446122345e-07, "loss": 0.4254, "step": 11686 }, { "epoch": 2.991488, "grad_norm": 1.7734375, "learning_rate": 1.4930466683730057e-07, "loss": 0.4331, "step": 11687 }, { "epoch": 2.9917439999999997, "grad_norm": 1.7109375, "learning_rate": 1.450388192133777e-07, "loss": 0.4081, "step": 11688 }, { "epoch": 2.992, "grad_norm": 1.7890625, "learning_rate": 1.4077297158945482e-07, "loss": 0.4207, "step": 11689 }, { "epoch": 2.9922560000000002, "grad_norm": 1.8828125, "learning_rate": 1.3650712396553195e-07, "loss": 0.4118, "step": 11690 }, { "epoch": 2.992512, "grad_norm": 1.796875, "learning_rate": 1.322412763416091e-07, "loss": 0.4579, "step": 11691 }, { "epoch": 2.992768, "grad_norm": 1.8125, "learning_rate": 1.2797542871768622e-07, "loss": 0.4007, "step": 11692 }, { "epoch": 2.993024, "grad_norm": 1.6796875, "learning_rate": 1.2370958109376335e-07, "loss": 0.4308, "step": 11693 }, { "epoch": 2.99328, "grad_norm": 1.7265625, "learning_rate": 1.1944373346984047e-07, "loss": 0.4336, "step": 11694 }, { "epoch": 2.9935359999999998, "grad_norm": 1.640625, "learning_rate": 1.151778858459176e-07, "loss": 0.4419, "step": 11695 }, { "epoch": 2.993792, "grad_norm": 1.7265625, "learning_rate": 1.1091203822199471e-07, "loss": 0.3869, "step": 11696 }, { "epoch": 2.9940480000000003, "grad_norm": 1.71875, "learning_rate": 1.0664619059807183e-07, "loss": 0.3885, "step": 11697 }, { "epoch": 2.994304, "grad_norm": 1.828125, "learning_rate": 1.0238034297414896e-07, "loss": 0.394, "step": 11698 }, { "epoch": 2.99456, "grad_norm": 1.7109375, "learning_rate": 9.811449535022608e-08, "loss": 0.4347, "step": 11699 }, { "epoch": 2.994816, "grad_norm": 1.796875, "learning_rate": 9.384864772630322e-08, "loss": 0.425, "step": 11700 }, { "epoch": 2.995072, "grad_norm": 1.640625, "learning_rate": 8.958280010238035e-08, "loss": 0.4369, "step": 11701 }, { "epoch": 2.9953279999999998, "grad_norm": 1.8046875, "learning_rate": 8.531695247845747e-08, "loss": 0.4577, "step": 11702 }, { "epoch": 2.995584, "grad_norm": 1.640625, "learning_rate": 8.10511048545346e-08, "loss": 0.4196, "step": 11703 }, { "epoch": 2.99584, "grad_norm": 1.75, "learning_rate": 7.678525723061172e-08, "loss": 0.4845, "step": 11704 }, { "epoch": 2.996096, "grad_norm": 1.7265625, "learning_rate": 7.251940960668885e-08, "loss": 0.4265, "step": 11705 }, { "epoch": 2.996352, "grad_norm": 1.671875, "learning_rate": 6.825356198276597e-08, "loss": 0.4433, "step": 11706 }, { "epoch": 2.996608, "grad_norm": 1.6640625, "learning_rate": 6.398771435884311e-08, "loss": 0.4145, "step": 11707 }, { "epoch": 2.996864, "grad_norm": 1.8203125, "learning_rate": 5.972186673492024e-08, "loss": 0.4088, "step": 11708 }, { "epoch": 2.99712, "grad_norm": 1.8984375, "learning_rate": 5.5456019110997355e-08, "loss": 0.4247, "step": 11709 }, { "epoch": 2.997376, "grad_norm": 1.6953125, "learning_rate": 5.119017148707448e-08, "loss": 0.4265, "step": 11710 }, { "epoch": 2.997632, "grad_norm": 1.578125, "learning_rate": 4.692432386315161e-08, "loss": 0.4275, "step": 11711 }, { "epoch": 2.997888, "grad_norm": 1.6953125, "learning_rate": 4.2658476239228736e-08, "loss": 0.4238, "step": 11712 }, { "epoch": 2.998144, "grad_norm": 1.703125, "learning_rate": 3.839262861530586e-08, "loss": 0.4195, "step": 11713 }, { "epoch": 2.9984, "grad_norm": 1.671875, "learning_rate": 3.4126780991382986e-08, "loss": 0.4022, "step": 11714 }, { "epoch": 2.998656, "grad_norm": 1.6953125, "learning_rate": 2.986093336746012e-08, "loss": 0.4165, "step": 11715 }, { "epoch": 2.998912, "grad_norm": 1.671875, "learning_rate": 2.559508574353724e-08, "loss": 0.3983, "step": 11716 }, { "epoch": 2.999168, "grad_norm": 1.578125, "learning_rate": 2.1329238119614368e-08, "loss": 0.4571, "step": 11717 }, { "epoch": 2.999424, "grad_norm": 1.7265625, "learning_rate": 1.7063390495691493e-08, "loss": 0.4093, "step": 11718 }, { "epoch": 2.99968, "grad_norm": 1.78125, "learning_rate": 1.279754287176862e-08, "loss": 0.4072, "step": 11719 }, { "epoch": 2.999936, "grad_norm": 1.6796875, "learning_rate": 8.531695247845747e-09, "loss": 0.4626, "step": 11720 }, { "epoch": 3.0, "grad_norm": 3.3125, "learning_rate": 4.265847623922873e-09, "loss": 0.4142, "step": 11721 } ], "logging_steps": 1, "max_steps": 11721, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 5000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3.0114080917848687e+19, "train_batch_size": 32, "trial_name": null, "trial_params": null }