{ "best_metric": null, "best_model_checkpoint": null, "epoch": 5.993651979088872, "eval_steps": 500, "global_step": 5352, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0011202389843166542, "grad_norm": 2.8858156204223633, "learning_rate": 5.0000000000000004e-08, "loss": 0.9141, "step": 1 }, { "epoch": 0.0022404779686333084, "grad_norm": 2.804832935333252, "learning_rate": 1.0000000000000001e-07, "loss": 0.9218, "step": 2 }, { "epoch": 0.0033607169529499626, "grad_norm": 2.7312190532684326, "learning_rate": 1.5000000000000002e-07, "loss": 0.9026, "step": 3 }, { "epoch": 0.004480955937266617, "grad_norm": 2.466888904571533, "learning_rate": 2.0000000000000002e-07, "loss": 0.9196, "step": 4 }, { "epoch": 0.005601194921583271, "grad_norm": 2.629023551940918, "learning_rate": 2.5000000000000004e-07, "loss": 0.8756, "step": 5 }, { "epoch": 0.006721433905899925, "grad_norm": 2.747882604598999, "learning_rate": 3.0000000000000004e-07, "loss": 0.9368, "step": 6 }, { "epoch": 0.00784167289021658, "grad_norm": 2.7748570442199707, "learning_rate": 3.5000000000000004e-07, "loss": 0.9265, "step": 7 }, { "epoch": 0.008961911874533234, "grad_norm": 2.38838267326355, "learning_rate": 4.0000000000000003e-07, "loss": 0.9154, "step": 8 }, { "epoch": 0.010082150858849889, "grad_norm": 2.9623191356658936, "learning_rate": 4.5000000000000003e-07, "loss": 0.9322, "step": 9 }, { "epoch": 0.011202389843166542, "grad_norm": 2.4339418411254883, "learning_rate": 5.000000000000001e-07, "loss": 0.9117, "step": 10 }, { "epoch": 0.012322628827483197, "grad_norm": 2.7546939849853516, "learning_rate": 5.5e-07, "loss": 0.9146, "step": 11 }, { "epoch": 0.01344286781179985, "grad_norm": 2.2417454719543457, "learning_rate": 6.000000000000001e-07, "loss": 0.8947, "step": 12 }, { "epoch": 0.014563106796116505, "grad_norm": 2.443024158477783, "learning_rate": 6.5e-07, "loss": 0.8952, "step": 13 }, { "epoch": 0.01568334578043316, "grad_norm": 2.1837103366851807, "learning_rate": 7.000000000000001e-07, "loss": 0.9105, "step": 14 }, { "epoch": 0.016803584764749812, "grad_norm": 2.1527903079986572, "learning_rate": 7.5e-07, "loss": 0.8899, "step": 15 }, { "epoch": 0.017923823749066467, "grad_norm": 2.161756753921509, "learning_rate": 8.000000000000001e-07, "loss": 0.8655, "step": 16 }, { "epoch": 0.019044062733383122, "grad_norm": 1.898628830909729, "learning_rate": 8.500000000000001e-07, "loss": 0.85, "step": 17 }, { "epoch": 0.020164301717699777, "grad_norm": 1.7848337888717651, "learning_rate": 9.000000000000001e-07, "loss": 0.8654, "step": 18 }, { "epoch": 0.02128454070201643, "grad_norm": 1.9204438924789429, "learning_rate": 9.500000000000001e-07, "loss": 0.8685, "step": 19 }, { "epoch": 0.022404779686333084, "grad_norm": 1.6950091123580933, "learning_rate": 1.0000000000000002e-06, "loss": 0.8981, "step": 20 }, { "epoch": 0.02352501867064974, "grad_norm": 1.774417519569397, "learning_rate": 1.0500000000000001e-06, "loss": 0.8953, "step": 21 }, { "epoch": 0.024645257654966394, "grad_norm": 1.7463773488998413, "learning_rate": 1.1e-06, "loss": 0.8668, "step": 22 }, { "epoch": 0.025765496639283045, "grad_norm": 1.5141345262527466, "learning_rate": 1.1500000000000002e-06, "loss": 0.8523, "step": 23 }, { "epoch": 0.0268857356235997, "grad_norm": 1.5256919860839844, "learning_rate": 1.2000000000000002e-06, "loss": 0.837, "step": 24 }, { "epoch": 0.028005974607916356, "grad_norm": 1.3926639556884766, "learning_rate": 1.25e-06, "loss": 0.8498, "step": 25 }, { "epoch": 0.02912621359223301, "grad_norm": 1.2967628240585327, "learning_rate": 1.3e-06, "loss": 0.7906, "step": 26 }, { "epoch": 0.030246452576549662, "grad_norm": 1.2432132959365845, "learning_rate": 1.3500000000000002e-06, "loss": 0.8143, "step": 27 }, { "epoch": 0.03136669156086632, "grad_norm": 1.1862553358078003, "learning_rate": 1.4000000000000001e-06, "loss": 0.7959, "step": 28 }, { "epoch": 0.03248693054518297, "grad_norm": 1.18585205078125, "learning_rate": 1.45e-06, "loss": 0.8263, "step": 29 }, { "epoch": 0.033607169529499624, "grad_norm": 1.118574857711792, "learning_rate": 1.5e-06, "loss": 0.7765, "step": 30 }, { "epoch": 0.03472740851381628, "grad_norm": 1.1179440021514893, "learning_rate": 1.5500000000000002e-06, "loss": 0.8037, "step": 31 }, { "epoch": 0.035847647498132934, "grad_norm": 1.100803017616272, "learning_rate": 1.6000000000000001e-06, "loss": 0.8113, "step": 32 }, { "epoch": 0.03696788648244959, "grad_norm": 1.097655177116394, "learning_rate": 1.6500000000000003e-06, "loss": 0.7993, "step": 33 }, { "epoch": 0.038088125466766244, "grad_norm": 1.0662972927093506, "learning_rate": 1.7000000000000002e-06, "loss": 0.8029, "step": 34 }, { "epoch": 0.039208364451082896, "grad_norm": 1.109535574913025, "learning_rate": 1.75e-06, "loss": 0.8218, "step": 35 }, { "epoch": 0.040328603435399554, "grad_norm": 1.0223349332809448, "learning_rate": 1.8000000000000001e-06, "loss": 0.7871, "step": 36 }, { "epoch": 0.041448842419716206, "grad_norm": 1.0227162837982178, "learning_rate": 1.85e-06, "loss": 0.7944, "step": 37 }, { "epoch": 0.04256908140403286, "grad_norm": 0.9250116348266602, "learning_rate": 1.9000000000000002e-06, "loss": 0.7522, "step": 38 }, { "epoch": 0.043689320388349516, "grad_norm": 0.9528149366378784, "learning_rate": 1.9500000000000004e-06, "loss": 0.7645, "step": 39 }, { "epoch": 0.04480955937266617, "grad_norm": 0.8865862488746643, "learning_rate": 2.0000000000000003e-06, "loss": 0.7861, "step": 40 }, { "epoch": 0.045929798356982826, "grad_norm": 0.9337865114212036, "learning_rate": 2.05e-06, "loss": 0.7427, "step": 41 }, { "epoch": 0.04705003734129948, "grad_norm": 0.880203127861023, "learning_rate": 2.1000000000000002e-06, "loss": 0.7411, "step": 42 }, { "epoch": 0.04817027632561613, "grad_norm": 0.8911599516868591, "learning_rate": 2.15e-06, "loss": 0.7434, "step": 43 }, { "epoch": 0.04929051530993279, "grad_norm": 0.8979325294494629, "learning_rate": 2.2e-06, "loss": 0.7598, "step": 44 }, { "epoch": 0.05041075429424944, "grad_norm": 0.8859411478042603, "learning_rate": 2.25e-06, "loss": 0.7646, "step": 45 }, { "epoch": 0.05153099327856609, "grad_norm": 0.8641071915626526, "learning_rate": 2.3000000000000004e-06, "loss": 0.7559, "step": 46 }, { "epoch": 0.05265123226288275, "grad_norm": 2.738354444503784, "learning_rate": 2.35e-06, "loss": 0.7826, "step": 47 }, { "epoch": 0.0537714712471994, "grad_norm": 0.847560465335846, "learning_rate": 2.4000000000000003e-06, "loss": 0.7469, "step": 48 }, { "epoch": 0.05489171023151606, "grad_norm": 0.8350309729576111, "learning_rate": 2.4500000000000003e-06, "loss": 0.7878, "step": 49 }, { "epoch": 0.05601194921583271, "grad_norm": 0.8858978748321533, "learning_rate": 2.5e-06, "loss": 0.7154, "step": 50 }, { "epoch": 0.05713218820014936, "grad_norm": 0.8486636877059937, "learning_rate": 2.55e-06, "loss": 0.7521, "step": 51 }, { "epoch": 0.05825242718446602, "grad_norm": 0.8095760345458984, "learning_rate": 2.6e-06, "loss": 0.7355, "step": 52 }, { "epoch": 0.05937266616878267, "grad_norm": 1.1256295442581177, "learning_rate": 2.6500000000000005e-06, "loss": 0.7312, "step": 53 }, { "epoch": 0.060492905153099324, "grad_norm": 0.8093723058700562, "learning_rate": 2.7000000000000004e-06, "loss": 0.738, "step": 54 }, { "epoch": 0.06161314413741598, "grad_norm": 0.807765543460846, "learning_rate": 2.7500000000000004e-06, "loss": 0.7055, "step": 55 }, { "epoch": 0.06273338312173264, "grad_norm": 0.8036230206489563, "learning_rate": 2.8000000000000003e-06, "loss": 0.7354, "step": 56 }, { "epoch": 0.0638536221060493, "grad_norm": 0.809104859828949, "learning_rate": 2.85e-06, "loss": 0.7469, "step": 57 }, { "epoch": 0.06497386109036594, "grad_norm": 0.8124133944511414, "learning_rate": 2.9e-06, "loss": 0.7039, "step": 58 }, { "epoch": 0.0660941000746826, "grad_norm": 0.8039435744285583, "learning_rate": 2.95e-06, "loss": 0.7209, "step": 59 }, { "epoch": 0.06721433905899925, "grad_norm": 0.8367541432380676, "learning_rate": 3e-06, "loss": 0.7759, "step": 60 }, { "epoch": 0.06833457804331591, "grad_norm": 0.7983250021934509, "learning_rate": 3.05e-06, "loss": 0.7251, "step": 61 }, { "epoch": 0.06945481702763256, "grad_norm": 0.7989967465400696, "learning_rate": 3.1000000000000004e-06, "loss": 0.7164, "step": 62 }, { "epoch": 0.07057505601194922, "grad_norm": 0.7835646867752075, "learning_rate": 3.1500000000000003e-06, "loss": 0.7124, "step": 63 }, { "epoch": 0.07169529499626587, "grad_norm": 0.7820047736167908, "learning_rate": 3.2000000000000003e-06, "loss": 0.6997, "step": 64 }, { "epoch": 0.07281553398058252, "grad_norm": 0.8633654713630676, "learning_rate": 3.2500000000000002e-06, "loss": 0.7248, "step": 65 }, { "epoch": 0.07393577296489919, "grad_norm": 0.7743967175483704, "learning_rate": 3.3000000000000006e-06, "loss": 0.7237, "step": 66 }, { "epoch": 0.07505601194921584, "grad_norm": 0.7750105857849121, "learning_rate": 3.3500000000000005e-06, "loss": 0.6874, "step": 67 }, { "epoch": 0.07617625093353249, "grad_norm": 0.7676857113838196, "learning_rate": 3.4000000000000005e-06, "loss": 0.6771, "step": 68 }, { "epoch": 0.07729648991784914, "grad_norm": 0.7877640724182129, "learning_rate": 3.45e-06, "loss": 0.7063, "step": 69 }, { "epoch": 0.07841672890216579, "grad_norm": 0.7854837775230408, "learning_rate": 3.5e-06, "loss": 0.6957, "step": 70 }, { "epoch": 0.07953696788648244, "grad_norm": 0.8387333750724792, "learning_rate": 3.5500000000000003e-06, "loss": 0.6923, "step": 71 }, { "epoch": 0.08065720687079911, "grad_norm": 0.7769498229026794, "learning_rate": 3.6000000000000003e-06, "loss": 0.7229, "step": 72 }, { "epoch": 0.08177744585511576, "grad_norm": 0.8273895978927612, "learning_rate": 3.65e-06, "loss": 0.7011, "step": 73 }, { "epoch": 0.08289768483943241, "grad_norm": 0.7759560346603394, "learning_rate": 3.7e-06, "loss": 0.7246, "step": 74 }, { "epoch": 0.08401792382374906, "grad_norm": 0.7503573298454285, "learning_rate": 3.7500000000000005e-06, "loss": 0.6711, "step": 75 }, { "epoch": 0.08513816280806571, "grad_norm": 0.7817795276641846, "learning_rate": 3.8000000000000005e-06, "loss": 0.6771, "step": 76 }, { "epoch": 0.08625840179238238, "grad_norm": 0.7503968477249146, "learning_rate": 3.85e-06, "loss": 0.6903, "step": 77 }, { "epoch": 0.08737864077669903, "grad_norm": 0.7876687049865723, "learning_rate": 3.900000000000001e-06, "loss": 0.6963, "step": 78 }, { "epoch": 0.08849887976101568, "grad_norm": 0.7441173791885376, "learning_rate": 3.95e-06, "loss": 0.6872, "step": 79 }, { "epoch": 0.08961911874533234, "grad_norm": 0.7741108536720276, "learning_rate": 4.000000000000001e-06, "loss": 0.6563, "step": 80 }, { "epoch": 0.09073935772964899, "grad_norm": 0.7747477889060974, "learning_rate": 4.05e-06, "loss": 0.7077, "step": 81 }, { "epoch": 0.09185959671396565, "grad_norm": 0.8173837065696716, "learning_rate": 4.1e-06, "loss": 0.708, "step": 82 }, { "epoch": 0.0929798356982823, "grad_norm": 0.7583895325660706, "learning_rate": 4.15e-06, "loss": 0.6696, "step": 83 }, { "epoch": 0.09410007468259896, "grad_norm": 0.7949450612068176, "learning_rate": 4.2000000000000004e-06, "loss": 0.7041, "step": 84 }, { "epoch": 0.09522031366691561, "grad_norm": 0.7842839360237122, "learning_rate": 4.25e-06, "loss": 0.6552, "step": 85 }, { "epoch": 0.09634055265123226, "grad_norm": 0.769949734210968, "learning_rate": 4.3e-06, "loss": 0.7012, "step": 86 }, { "epoch": 0.09746079163554892, "grad_norm": 0.7680435180664062, "learning_rate": 4.350000000000001e-06, "loss": 0.7026, "step": 87 }, { "epoch": 0.09858103061986558, "grad_norm": 0.7704882621765137, "learning_rate": 4.4e-06, "loss": 0.676, "step": 88 }, { "epoch": 0.09970126960418223, "grad_norm": 0.7687551379203796, "learning_rate": 4.450000000000001e-06, "loss": 0.662, "step": 89 }, { "epoch": 0.10082150858849888, "grad_norm": 0.8296576738357544, "learning_rate": 4.5e-06, "loss": 0.6815, "step": 90 }, { "epoch": 0.10194174757281553, "grad_norm": 0.807574987411499, "learning_rate": 4.5500000000000005e-06, "loss": 0.6959, "step": 91 }, { "epoch": 0.10306198655713218, "grad_norm": 0.8537940979003906, "learning_rate": 4.600000000000001e-06, "loss": 0.6568, "step": 92 }, { "epoch": 0.10418222554144885, "grad_norm": 0.776905357837677, "learning_rate": 4.65e-06, "loss": 0.7027, "step": 93 }, { "epoch": 0.1053024645257655, "grad_norm": 0.7668991684913635, "learning_rate": 4.7e-06, "loss": 0.6537, "step": 94 }, { "epoch": 0.10642270351008215, "grad_norm": 0.7789910435676575, "learning_rate": 4.75e-06, "loss": 0.6637, "step": 95 }, { "epoch": 0.1075429424943988, "grad_norm": 0.7807944416999817, "learning_rate": 4.800000000000001e-06, "loss": 0.7103, "step": 96 }, { "epoch": 0.10866318147871545, "grad_norm": 0.7590618133544922, "learning_rate": 4.85e-06, "loss": 0.6765, "step": 97 }, { "epoch": 0.10978342046303212, "grad_norm": 0.7463409900665283, "learning_rate": 4.9000000000000005e-06, "loss": 0.6795, "step": 98 }, { "epoch": 0.11090365944734877, "grad_norm": 0.8291321992874146, "learning_rate": 4.95e-06, "loss": 0.7311, "step": 99 }, { "epoch": 0.11202389843166542, "grad_norm": 0.7995114326477051, "learning_rate": 5e-06, "loss": 0.684, "step": 100 }, { "epoch": 0.11314413741598207, "grad_norm": 0.7649957537651062, "learning_rate": 4.9999995527397415e-06, "loss": 0.6645, "step": 101 }, { "epoch": 0.11426437640029873, "grad_norm": 0.8313412070274353, "learning_rate": 4.999998210959126e-06, "loss": 0.6656, "step": 102 }, { "epoch": 0.11538461538461539, "grad_norm": 0.7994295358657837, "learning_rate": 4.999995974658632e-06, "loss": 0.6562, "step": 103 }, { "epoch": 0.11650485436893204, "grad_norm": 0.8024242520332336, "learning_rate": 4.999992843839062e-06, "loss": 0.6946, "step": 104 }, { "epoch": 0.1176250933532487, "grad_norm": 0.7950218319892883, "learning_rate": 4.999988818501535e-06, "loss": 0.6833, "step": 105 }, { "epoch": 0.11874533233756535, "grad_norm": 0.8187536597251892, "learning_rate": 4.9999838986474925e-06, "loss": 0.6869, "step": 106 }, { "epoch": 0.119865571321882, "grad_norm": 0.7608385682106018, "learning_rate": 4.999978084278693e-06, "loss": 0.6536, "step": 107 }, { "epoch": 0.12098581030619865, "grad_norm": 0.9910794496536255, "learning_rate": 4.999971375397218e-06, "loss": 0.6444, "step": 108 }, { "epoch": 0.12210604929051531, "grad_norm": 0.8221011757850647, "learning_rate": 4.9999637720054675e-06, "loss": 0.6986, "step": 109 }, { "epoch": 0.12322628827483197, "grad_norm": 0.8212369680404663, "learning_rate": 4.999955274106163e-06, "loss": 0.6559, "step": 110 }, { "epoch": 0.12434652725914862, "grad_norm": 0.7603834867477417, "learning_rate": 4.999945881702344e-06, "loss": 0.6644, "step": 111 }, { "epoch": 0.12546676624346528, "grad_norm": 0.864615261554718, "learning_rate": 4.999935594797372e-06, "loss": 0.7045, "step": 112 }, { "epoch": 0.12658700522778193, "grad_norm": 0.7939414381980896, "learning_rate": 4.999924413394926e-06, "loss": 0.6506, "step": 113 }, { "epoch": 0.1277072442120986, "grad_norm": 0.7965752482414246, "learning_rate": 4.99991233749901e-06, "loss": 0.6634, "step": 114 }, { "epoch": 0.12882748319641524, "grad_norm": 0.809953510761261, "learning_rate": 4.999899367113943e-06, "loss": 0.6613, "step": 115 }, { "epoch": 0.1299477221807319, "grad_norm": 0.7917526960372925, "learning_rate": 4.999885502244365e-06, "loss": 0.6503, "step": 116 }, { "epoch": 0.13106796116504854, "grad_norm": 0.7986327409744263, "learning_rate": 4.999870742895239e-06, "loss": 0.6607, "step": 117 }, { "epoch": 0.1321882001493652, "grad_norm": 1.0296788215637207, "learning_rate": 4.999855089071844e-06, "loss": 0.6705, "step": 118 }, { "epoch": 0.13330843913368184, "grad_norm": 0.7908150553703308, "learning_rate": 4.999838540779782e-06, "loss": 0.6622, "step": 119 }, { "epoch": 0.1344286781179985, "grad_norm": 0.8663723468780518, "learning_rate": 4.999821098024975e-06, "loss": 0.6592, "step": 120 }, { "epoch": 0.13554891710231515, "grad_norm": 0.8147454857826233, "learning_rate": 4.999802760813662e-06, "loss": 0.6478, "step": 121 }, { "epoch": 0.13666915608663183, "grad_norm": 0.810529351234436, "learning_rate": 4.9997835291524065e-06, "loss": 0.6438, "step": 122 }, { "epoch": 0.13778939507094848, "grad_norm": 0.7966436743736267, "learning_rate": 4.999763403048089e-06, "loss": 0.6425, "step": 123 }, { "epoch": 0.13890963405526513, "grad_norm": 0.789413571357727, "learning_rate": 4.999742382507909e-06, "loss": 0.6227, "step": 124 }, { "epoch": 0.14002987303958178, "grad_norm": 0.7998204827308655, "learning_rate": 4.999720467539391e-06, "loss": 0.6635, "step": 125 }, { "epoch": 0.14115011202389843, "grad_norm": 0.8009337782859802, "learning_rate": 4.999697658150374e-06, "loss": 0.6673, "step": 126 }, { "epoch": 0.14227035100821508, "grad_norm": 0.7708600163459778, "learning_rate": 4.99967395434902e-06, "loss": 0.6336, "step": 127 }, { "epoch": 0.14339058999253174, "grad_norm": 0.7975388765335083, "learning_rate": 4.999649356143811e-06, "loss": 0.6673, "step": 128 }, { "epoch": 0.1445108289768484, "grad_norm": 0.83116215467453, "learning_rate": 4.999623863543548e-06, "loss": 0.6902, "step": 129 }, { "epoch": 0.14563106796116504, "grad_norm": 0.8246234655380249, "learning_rate": 4.999597476557352e-06, "loss": 0.6586, "step": 130 }, { "epoch": 0.1467513069454817, "grad_norm": 0.7604647278785706, "learning_rate": 4.999570195194665e-06, "loss": 0.6455, "step": 131 }, { "epoch": 0.14787154592979837, "grad_norm": 0.7587922215461731, "learning_rate": 4.9995420194652475e-06, "loss": 0.6107, "step": 132 }, { "epoch": 0.14899178491411502, "grad_norm": 0.909156858921051, "learning_rate": 4.999512949379183e-06, "loss": 0.679, "step": 133 }, { "epoch": 0.15011202389843167, "grad_norm": 0.8901562690734863, "learning_rate": 4.999482984946872e-06, "loss": 0.6887, "step": 134 }, { "epoch": 0.15123226288274833, "grad_norm": 0.7636528611183167, "learning_rate": 4.999452126179035e-06, "loss": 0.6514, "step": 135 }, { "epoch": 0.15235250186706498, "grad_norm": 0.8096560835838318, "learning_rate": 4.999420373086715e-06, "loss": 0.6937, "step": 136 }, { "epoch": 0.15347274085138163, "grad_norm": 0.8607243299484253, "learning_rate": 4.999387725681274e-06, "loss": 0.6812, "step": 137 }, { "epoch": 0.15459297983569828, "grad_norm": 0.8863621354103088, "learning_rate": 4.9993541839743906e-06, "loss": 0.6829, "step": 138 }, { "epoch": 0.15571321882001493, "grad_norm": 0.8292368054389954, "learning_rate": 4.99931974797807e-06, "loss": 0.6714, "step": 139 }, { "epoch": 0.15683345780433158, "grad_norm": 0.8053487539291382, "learning_rate": 4.999284417704631e-06, "loss": 0.656, "step": 140 }, { "epoch": 0.15795369678864823, "grad_norm": 0.8153090476989746, "learning_rate": 4.999248193166715e-06, "loss": 0.6529, "step": 141 }, { "epoch": 0.1590739357729649, "grad_norm": 0.8820142149925232, "learning_rate": 4.999211074377285e-06, "loss": 0.6507, "step": 142 }, { "epoch": 0.16019417475728157, "grad_norm": 0.8246594071388245, "learning_rate": 4.999173061349623e-06, "loss": 0.6767, "step": 143 }, { "epoch": 0.16131441374159822, "grad_norm": 0.7902995944023132, "learning_rate": 4.999134154097328e-06, "loss": 0.6596, "step": 144 }, { "epoch": 0.16243465272591487, "grad_norm": 0.8101757764816284, "learning_rate": 4.999094352634322e-06, "loss": 0.6462, "step": 145 }, { "epoch": 0.16355489171023152, "grad_norm": 0.8051759600639343, "learning_rate": 4.999053656974847e-06, "loss": 0.6659, "step": 146 }, { "epoch": 0.16467513069454817, "grad_norm": 0.8006038665771484, "learning_rate": 4.999012067133465e-06, "loss": 0.6865, "step": 147 }, { "epoch": 0.16579536967886482, "grad_norm": 0.8025104999542236, "learning_rate": 4.998969583125055e-06, "loss": 0.6558, "step": 148 }, { "epoch": 0.16691560866318148, "grad_norm": 0.7755445241928101, "learning_rate": 4.99892620496482e-06, "loss": 0.6373, "step": 149 }, { "epoch": 0.16803584764749813, "grad_norm": 0.8465038537979126, "learning_rate": 4.99888193266828e-06, "loss": 0.6476, "step": 150 }, { "epoch": 0.16915608663181478, "grad_norm": 0.8304318189620972, "learning_rate": 4.9988367662512775e-06, "loss": 0.6636, "step": 151 }, { "epoch": 0.17027632561613143, "grad_norm": 1.0744889974594116, "learning_rate": 4.99879070572997e-06, "loss": 0.6329, "step": 152 }, { "epoch": 0.1713965646004481, "grad_norm": 0.8096840381622314, "learning_rate": 4.998743751120843e-06, "loss": 0.6515, "step": 153 }, { "epoch": 0.17251680358476476, "grad_norm": 0.8647177219390869, "learning_rate": 4.998695902440693e-06, "loss": 0.669, "step": 154 }, { "epoch": 0.1736370425690814, "grad_norm": 0.8000180125236511, "learning_rate": 4.9986471597066435e-06, "loss": 0.6353, "step": 155 }, { "epoch": 0.17475728155339806, "grad_norm": 0.7994810938835144, "learning_rate": 4.998597522936134e-06, "loss": 0.6312, "step": 156 }, { "epoch": 0.17587752053771472, "grad_norm": 0.8086467385292053, "learning_rate": 4.9985469921469245e-06, "loss": 0.6426, "step": 157 }, { "epoch": 0.17699775952203137, "grad_norm": 0.8089617490768433, "learning_rate": 4.998495567357097e-06, "loss": 0.6671, "step": 158 }, { "epoch": 0.17811799850634802, "grad_norm": 0.7937355041503906, "learning_rate": 4.9984432485850495e-06, "loss": 0.6433, "step": 159 }, { "epoch": 0.17923823749066467, "grad_norm": 0.7971526980400085, "learning_rate": 4.998390035849503e-06, "loss": 0.6371, "step": 160 }, { "epoch": 0.18035847647498132, "grad_norm": 0.8417288064956665, "learning_rate": 4.998335929169498e-06, "loss": 0.6607, "step": 161 }, { "epoch": 0.18147871545929797, "grad_norm": 2.7477307319641113, "learning_rate": 4.998280928564394e-06, "loss": 0.6445, "step": 162 }, { "epoch": 0.18259895444361463, "grad_norm": 0.8154010772705078, "learning_rate": 4.998225034053871e-06, "loss": 0.6518, "step": 163 }, { "epoch": 0.1837191934279313, "grad_norm": 0.8180714249610901, "learning_rate": 4.9981682456579275e-06, "loss": 0.6524, "step": 164 }, { "epoch": 0.18483943241224796, "grad_norm": 0.8008469939231873, "learning_rate": 4.998110563396883e-06, "loss": 0.6508, "step": 165 }, { "epoch": 0.1859596713965646, "grad_norm": 0.7731476426124573, "learning_rate": 4.998051987291378e-06, "loss": 0.6262, "step": 166 }, { "epoch": 0.18707991038088126, "grad_norm": 0.7730596661567688, "learning_rate": 4.99799251736237e-06, "loss": 0.6356, "step": 167 }, { "epoch": 0.1882001493651979, "grad_norm": 0.8305966854095459, "learning_rate": 4.997932153631139e-06, "loss": 0.6584, "step": 168 }, { "epoch": 0.18932038834951456, "grad_norm": 0.8761897683143616, "learning_rate": 4.997870896119282e-06, "loss": 0.6593, "step": 169 }, { "epoch": 0.19044062733383121, "grad_norm": 0.8341963887214661, "learning_rate": 4.9978087448487204e-06, "loss": 0.6293, "step": 170 }, { "epoch": 0.19156086631814787, "grad_norm": 0.8244994282722473, "learning_rate": 4.997745699841689e-06, "loss": 0.6512, "step": 171 }, { "epoch": 0.19268110530246452, "grad_norm": 0.8051140904426575, "learning_rate": 4.997681761120749e-06, "loss": 0.6535, "step": 172 }, { "epoch": 0.19380134428678117, "grad_norm": 0.7865309119224548, "learning_rate": 4.997616928708774e-06, "loss": 0.6457, "step": 173 }, { "epoch": 0.19492158327109785, "grad_norm": 0.7985602021217346, "learning_rate": 4.997551202628966e-06, "loss": 0.6562, "step": 174 }, { "epoch": 0.1960418222554145, "grad_norm": 0.7812699675559998, "learning_rate": 4.99748458290484e-06, "loss": 0.6505, "step": 175 }, { "epoch": 0.19716206123973115, "grad_norm": 0.7868354916572571, "learning_rate": 4.997417069560234e-06, "loss": 0.6295, "step": 176 }, { "epoch": 0.1982823002240478, "grad_norm": 0.8139058947563171, "learning_rate": 4.997348662619305e-06, "loss": 0.6637, "step": 177 }, { "epoch": 0.19940253920836445, "grad_norm": 0.7864823937416077, "learning_rate": 4.997279362106528e-06, "loss": 0.6478, "step": 178 }, { "epoch": 0.2005227781926811, "grad_norm": 0.8095872402191162, "learning_rate": 4.9972091680467e-06, "loss": 0.668, "step": 179 }, { "epoch": 0.20164301717699776, "grad_norm": 0.8363040089607239, "learning_rate": 4.997138080464938e-06, "loss": 0.6757, "step": 180 }, { "epoch": 0.2027632561613144, "grad_norm": 0.8066425323486328, "learning_rate": 4.9970660993866756e-06, "loss": 0.6617, "step": 181 }, { "epoch": 0.20388349514563106, "grad_norm": 0.8129490613937378, "learning_rate": 4.996993224837672e-06, "loss": 0.6463, "step": 182 }, { "epoch": 0.2050037341299477, "grad_norm": 0.8092365264892578, "learning_rate": 4.996919456843998e-06, "loss": 0.6441, "step": 183 }, { "epoch": 0.20612397311426436, "grad_norm": 0.7847099900245667, "learning_rate": 4.996844795432051e-06, "loss": 0.6608, "step": 184 }, { "epoch": 0.20724421209858104, "grad_norm": 0.7771169543266296, "learning_rate": 4.9967692406285454e-06, "loss": 0.6198, "step": 185 }, { "epoch": 0.2083644510828977, "grad_norm": 0.8057869076728821, "learning_rate": 4.996692792460513e-06, "loss": 0.6312, "step": 186 }, { "epoch": 0.20948469006721435, "grad_norm": 0.8194419145584106, "learning_rate": 4.996615450955311e-06, "loss": 0.66, "step": 187 }, { "epoch": 0.210604929051531, "grad_norm": 0.8123747110366821, "learning_rate": 4.99653721614061e-06, "loss": 0.6527, "step": 188 }, { "epoch": 0.21172516803584765, "grad_norm": 0.8024148344993591, "learning_rate": 4.996458088044405e-06, "loss": 0.6426, "step": 189 }, { "epoch": 0.2128454070201643, "grad_norm": 0.8563250303268433, "learning_rate": 4.996378066695008e-06, "loss": 0.6444, "step": 190 }, { "epoch": 0.21396564600448095, "grad_norm": 0.8127154111862183, "learning_rate": 4.99629715212105e-06, "loss": 0.6478, "step": 191 }, { "epoch": 0.2150858849887976, "grad_norm": 0.816790759563446, "learning_rate": 4.996215344351485e-06, "loss": 0.6304, "step": 192 }, { "epoch": 0.21620612397311426, "grad_norm": 0.8222427368164062, "learning_rate": 4.9961326434155834e-06, "loss": 0.6418, "step": 193 }, { "epoch": 0.2173263629574309, "grad_norm": 0.8139140605926514, "learning_rate": 4.996049049342936e-06, "loss": 0.6305, "step": 194 }, { "epoch": 0.21844660194174756, "grad_norm": 0.8003841042518616, "learning_rate": 4.995964562163455e-06, "loss": 0.6474, "step": 195 }, { "epoch": 0.21956684092606424, "grad_norm": 0.8458191156387329, "learning_rate": 4.9958791819073684e-06, "loss": 0.6637, "step": 196 }, { "epoch": 0.2206870799103809, "grad_norm": 0.801009476184845, "learning_rate": 4.995792908605227e-06, "loss": 0.6388, "step": 197 }, { "epoch": 0.22180731889469754, "grad_norm": 0.8174487948417664, "learning_rate": 4.995705742287901e-06, "loss": 0.653, "step": 198 }, { "epoch": 0.2229275578790142, "grad_norm": 0.814853310585022, "learning_rate": 4.995617682986578e-06, "loss": 0.6217, "step": 199 }, { "epoch": 0.22404779686333084, "grad_norm": 0.8986819982528687, "learning_rate": 4.995528730732766e-06, "loss": 0.6547, "step": 200 }, { "epoch": 0.2251680358476475, "grad_norm": 0.8147602081298828, "learning_rate": 4.995438885558294e-06, "loss": 0.6475, "step": 201 }, { "epoch": 0.22628827483196415, "grad_norm": 0.8108645081520081, "learning_rate": 4.995348147495309e-06, "loss": 0.6434, "step": 202 }, { "epoch": 0.2274085138162808, "grad_norm": 0.8559293746948242, "learning_rate": 4.995256516576278e-06, "loss": 0.6559, "step": 203 }, { "epoch": 0.22852875280059745, "grad_norm": 0.810727596282959, "learning_rate": 4.995163992833986e-06, "loss": 0.6365, "step": 204 }, { "epoch": 0.2296489917849141, "grad_norm": 0.8541222214698792, "learning_rate": 4.99507057630154e-06, "loss": 0.6624, "step": 205 }, { "epoch": 0.23076923076923078, "grad_norm": 0.8096019625663757, "learning_rate": 4.994976267012366e-06, "loss": 0.6213, "step": 206 }, { "epoch": 0.23188946975354743, "grad_norm": 0.868386447429657, "learning_rate": 4.994881065000206e-06, "loss": 0.6397, "step": 207 }, { "epoch": 0.23300970873786409, "grad_norm": 0.8383010029792786, "learning_rate": 4.9947849702991275e-06, "loss": 0.6477, "step": 208 }, { "epoch": 0.23412994772218074, "grad_norm": 0.8286524415016174, "learning_rate": 4.994687982943511e-06, "loss": 0.6321, "step": 209 }, { "epoch": 0.2352501867064974, "grad_norm": 0.7969548106193542, "learning_rate": 4.994590102968061e-06, "loss": 0.6284, "step": 210 }, { "epoch": 0.23637042569081404, "grad_norm": 0.8124633431434631, "learning_rate": 4.994491330407799e-06, "loss": 0.6508, "step": 211 }, { "epoch": 0.2374906646751307, "grad_norm": 0.8430159687995911, "learning_rate": 4.994391665298066e-06, "loss": 0.6392, "step": 212 }, { "epoch": 0.23861090365944734, "grad_norm": 1.1165465116500854, "learning_rate": 4.994291107674525e-06, "loss": 0.6609, "step": 213 }, { "epoch": 0.239731142643764, "grad_norm": 0.7861813902854919, "learning_rate": 4.9941896575731555e-06, "loss": 0.627, "step": 214 }, { "epoch": 0.24085138162808065, "grad_norm": 0.8439143300056458, "learning_rate": 4.994087315030256e-06, "loss": 0.6511, "step": 215 }, { "epoch": 0.2419716206123973, "grad_norm": 0.9279224276542664, "learning_rate": 4.993984080082447e-06, "loss": 0.6276, "step": 216 }, { "epoch": 0.24309185959671398, "grad_norm": 0.8302883505821228, "learning_rate": 4.993879952766666e-06, "loss": 0.6399, "step": 217 }, { "epoch": 0.24421209858103063, "grad_norm": 0.772523820400238, "learning_rate": 4.993774933120171e-06, "loss": 0.6284, "step": 218 }, { "epoch": 0.24533233756534728, "grad_norm": 0.8319805264472961, "learning_rate": 4.993669021180539e-06, "loss": 0.6407, "step": 219 }, { "epoch": 0.24645257654966393, "grad_norm": 0.8110228776931763, "learning_rate": 4.993562216985665e-06, "loss": 0.6598, "step": 220 }, { "epoch": 0.24757281553398058, "grad_norm": 0.8476558327674866, "learning_rate": 4.9934545205737665e-06, "loss": 0.6105, "step": 221 }, { "epoch": 0.24869305451829724, "grad_norm": 0.8189626932144165, "learning_rate": 4.993345931983376e-06, "loss": 0.6224, "step": 222 }, { "epoch": 0.2498132935026139, "grad_norm": 0.8342490792274475, "learning_rate": 4.9932364512533485e-06, "loss": 0.6217, "step": 223 }, { "epoch": 0.25093353248693057, "grad_norm": 0.838699460029602, "learning_rate": 4.993126078422856e-06, "loss": 0.6432, "step": 224 }, { "epoch": 0.2520537714712472, "grad_norm": 0.801331102848053, "learning_rate": 4.9930148135313935e-06, "loss": 0.6219, "step": 225 }, { "epoch": 0.25317401045556387, "grad_norm": 0.8075932860374451, "learning_rate": 4.99290265661877e-06, "loss": 0.649, "step": 226 }, { "epoch": 0.2542942494398805, "grad_norm": 0.8010944724082947, "learning_rate": 4.992789607725116e-06, "loss": 0.6159, "step": 227 }, { "epoch": 0.2554144884241972, "grad_norm": 0.8093600273132324, "learning_rate": 4.992675666890884e-06, "loss": 0.6162, "step": 228 }, { "epoch": 0.2565347274085138, "grad_norm": 0.8651375770568848, "learning_rate": 4.99256083415684e-06, "loss": 0.6391, "step": 229 }, { "epoch": 0.2576549663928305, "grad_norm": 0.8180515766143799, "learning_rate": 4.992445109564074e-06, "loss": 0.6627, "step": 230 }, { "epoch": 0.2587752053771471, "grad_norm": 0.8492463231086731, "learning_rate": 4.992328493153992e-06, "loss": 0.6533, "step": 231 }, { "epoch": 0.2598954443614638, "grad_norm": 0.7910256385803223, "learning_rate": 4.992210984968321e-06, "loss": 0.6212, "step": 232 }, { "epoch": 0.26101568334578046, "grad_norm": 0.8081009984016418, "learning_rate": 4.992092585049106e-06, "loss": 0.6464, "step": 233 }, { "epoch": 0.2621359223300971, "grad_norm": 0.8275237083435059, "learning_rate": 4.991973293438712e-06, "loss": 0.6447, "step": 234 }, { "epoch": 0.26325616131441376, "grad_norm": 0.7819504141807556, "learning_rate": 4.991853110179822e-06, "loss": 0.6278, "step": 235 }, { "epoch": 0.2643764002987304, "grad_norm": 0.7954742908477783, "learning_rate": 4.991732035315439e-06, "loss": 0.6259, "step": 236 }, { "epoch": 0.26549663928304706, "grad_norm": 0.7841144800186157, "learning_rate": 4.9916100688888835e-06, "loss": 0.6209, "step": 237 }, { "epoch": 0.2666168782673637, "grad_norm": 0.783143937587738, "learning_rate": 4.9914872109437975e-06, "loss": 0.6015, "step": 238 }, { "epoch": 0.26773711725168037, "grad_norm": 0.8399513363838196, "learning_rate": 4.9913634615241394e-06, "loss": 0.6624, "step": 239 }, { "epoch": 0.268857356235997, "grad_norm": 0.8158865571022034, "learning_rate": 4.9912388206741895e-06, "loss": 0.6607, "step": 240 }, { "epoch": 0.26997759522031367, "grad_norm": 0.8276694416999817, "learning_rate": 4.991113288438543e-06, "loss": 0.6474, "step": 241 }, { "epoch": 0.2710978342046303, "grad_norm": 0.8164044618606567, "learning_rate": 4.9909868648621185e-06, "loss": 0.6352, "step": 242 }, { "epoch": 0.272218073188947, "grad_norm": 0.8372899889945984, "learning_rate": 4.99085954999015e-06, "loss": 0.638, "step": 243 }, { "epoch": 0.27333831217326365, "grad_norm": 0.8520254492759705, "learning_rate": 4.990731343868192e-06, "loss": 0.6591, "step": 244 }, { "epoch": 0.2744585511575803, "grad_norm": 0.8587496876716614, "learning_rate": 4.990602246542118e-06, "loss": 0.6442, "step": 245 }, { "epoch": 0.27557879014189696, "grad_norm": 0.8117641806602478, "learning_rate": 4.99047225805812e-06, "loss": 0.6169, "step": 246 }, { "epoch": 0.2766990291262136, "grad_norm": 0.7888590693473816, "learning_rate": 4.99034137846271e-06, "loss": 0.6345, "step": 247 }, { "epoch": 0.27781926811053026, "grad_norm": 0.8112688064575195, "learning_rate": 4.990209607802715e-06, "loss": 0.6246, "step": 248 }, { "epoch": 0.2789395070948469, "grad_norm": 0.8172190189361572, "learning_rate": 4.990076946125286e-06, "loss": 0.6323, "step": 249 }, { "epoch": 0.28005974607916356, "grad_norm": 0.7784557938575745, "learning_rate": 4.9899433934778905e-06, "loss": 0.6186, "step": 250 }, { "epoch": 0.2811799850634802, "grad_norm": 0.8571611642837524, "learning_rate": 4.9898089499083135e-06, "loss": 0.6157, "step": 251 }, { "epoch": 0.28230022404779687, "grad_norm": 0.798240065574646, "learning_rate": 4.989673615464661e-06, "loss": 0.6201, "step": 252 }, { "epoch": 0.2834204630321135, "grad_norm": 0.8300586342811584, "learning_rate": 4.989537390195356e-06, "loss": 0.6481, "step": 253 }, { "epoch": 0.28454070201643017, "grad_norm": 0.9545755982398987, "learning_rate": 4.989400274149141e-06, "loss": 0.6315, "step": 254 }, { "epoch": 0.28566094100074685, "grad_norm": 0.80037522315979, "learning_rate": 4.989262267375078e-06, "loss": 0.6206, "step": 255 }, { "epoch": 0.2867811799850635, "grad_norm": 0.8587538003921509, "learning_rate": 4.989123369922547e-06, "loss": 0.622, "step": 256 }, { "epoch": 0.28790141896938015, "grad_norm": 0.7835617661476135, "learning_rate": 4.988983581841246e-06, "loss": 0.6255, "step": 257 }, { "epoch": 0.2890216579536968, "grad_norm": 0.8115828037261963, "learning_rate": 4.988842903181192e-06, "loss": 0.6122, "step": 258 }, { "epoch": 0.29014189693801345, "grad_norm": 0.7731125950813293, "learning_rate": 4.988701333992722e-06, "loss": 0.5881, "step": 259 }, { "epoch": 0.2912621359223301, "grad_norm": 0.8486718535423279, "learning_rate": 4.988558874326489e-06, "loss": 0.676, "step": 260 }, { "epoch": 0.29238237490664676, "grad_norm": 0.7868174910545349, "learning_rate": 4.988415524233469e-06, "loss": 0.6267, "step": 261 }, { "epoch": 0.2935026138909634, "grad_norm": 0.7890263795852661, "learning_rate": 4.9882712837649515e-06, "loss": 0.6171, "step": 262 }, { "epoch": 0.29462285287528006, "grad_norm": 0.799913763999939, "learning_rate": 4.988126152972548e-06, "loss": 0.6353, "step": 263 }, { "epoch": 0.29574309185959674, "grad_norm": 0.8258731961250305, "learning_rate": 4.987980131908186e-06, "loss": 0.6371, "step": 264 }, { "epoch": 0.29686333084391336, "grad_norm": 0.8256173729896545, "learning_rate": 4.987833220624116e-06, "loss": 0.609, "step": 265 }, { "epoch": 0.29798356982823004, "grad_norm": 0.7728785872459412, "learning_rate": 4.9876854191729e-06, "loss": 0.6021, "step": 266 }, { "epoch": 0.29910380881254667, "grad_norm": 0.8612363338470459, "learning_rate": 4.987536727607426e-06, "loss": 0.6031, "step": 267 }, { "epoch": 0.30022404779686335, "grad_norm": 0.8287588357925415, "learning_rate": 4.987387145980896e-06, "loss": 0.6365, "step": 268 }, { "epoch": 0.30134428678117997, "grad_norm": 0.7820507884025574, "learning_rate": 4.9872366743468305e-06, "loss": 0.6257, "step": 269 }, { "epoch": 0.30246452576549665, "grad_norm": 0.8158690929412842, "learning_rate": 4.987085312759071e-06, "loss": 0.6465, "step": 270 }, { "epoch": 0.3035847647498133, "grad_norm": 0.804691731929779, "learning_rate": 4.986933061271776e-06, "loss": 0.6384, "step": 271 }, { "epoch": 0.30470500373412995, "grad_norm": 0.8142663240432739, "learning_rate": 4.9867799199394205e-06, "loss": 0.6061, "step": 272 }, { "epoch": 0.3058252427184466, "grad_norm": 0.8177836537361145, "learning_rate": 4.9866258888168e-06, "loss": 0.6186, "step": 273 }, { "epoch": 0.30694548170276326, "grad_norm": 0.8021143078804016, "learning_rate": 4.986470967959031e-06, "loss": 0.6262, "step": 274 }, { "epoch": 0.30806572068707994, "grad_norm": 0.7913358807563782, "learning_rate": 4.986315157421543e-06, "loss": 0.6011, "step": 275 }, { "epoch": 0.30918595967139656, "grad_norm": 0.8460528254508972, "learning_rate": 4.986158457260086e-06, "loss": 0.5983, "step": 276 }, { "epoch": 0.31030619865571324, "grad_norm": 0.8357203006744385, "learning_rate": 4.986000867530729e-06, "loss": 0.6081, "step": 277 }, { "epoch": 0.31142643764002986, "grad_norm": 0.8164505362510681, "learning_rate": 4.9858423882898595e-06, "loss": 0.6408, "step": 278 }, { "epoch": 0.31254667662434654, "grad_norm": 0.8584355115890503, "learning_rate": 4.985683019594183e-06, "loss": 0.6206, "step": 279 }, { "epoch": 0.31366691560866317, "grad_norm": 0.8428062796592712, "learning_rate": 4.985522761500722e-06, "loss": 0.6622, "step": 280 }, { "epoch": 0.31478715459297985, "grad_norm": 0.9295979142189026, "learning_rate": 4.985361614066818e-06, "loss": 0.6374, "step": 281 }, { "epoch": 0.31590739357729647, "grad_norm": 0.7724334597587585, "learning_rate": 4.985199577350132e-06, "loss": 0.6148, "step": 282 }, { "epoch": 0.31702763256161315, "grad_norm": 0.785025954246521, "learning_rate": 4.9850366514086415e-06, "loss": 0.6299, "step": 283 }, { "epoch": 0.3181478715459298, "grad_norm": 0.8610864877700806, "learning_rate": 4.984872836300641e-06, "loss": 0.6464, "step": 284 }, { "epoch": 0.31926811053024645, "grad_norm": 0.8281784653663635, "learning_rate": 4.9847081320847475e-06, "loss": 0.6297, "step": 285 }, { "epoch": 0.32038834951456313, "grad_norm": 0.8076677322387695, "learning_rate": 4.984542538819893e-06, "loss": 0.6144, "step": 286 }, { "epoch": 0.32150858849887975, "grad_norm": 1.0354986190795898, "learning_rate": 4.984376056565328e-06, "loss": 0.6246, "step": 287 }, { "epoch": 0.32262882748319643, "grad_norm": 0.7936146259307861, "learning_rate": 4.98420868538062e-06, "loss": 0.6276, "step": 288 }, { "epoch": 0.32374906646751306, "grad_norm": 0.8247389793395996, "learning_rate": 4.984040425325657e-06, "loss": 0.6326, "step": 289 }, { "epoch": 0.32486930545182974, "grad_norm": 0.8053764700889587, "learning_rate": 4.983871276460643e-06, "loss": 0.6298, "step": 290 }, { "epoch": 0.32598954443614636, "grad_norm": 0.7672686576843262, "learning_rate": 4.983701238846102e-06, "loss": 0.6192, "step": 291 }, { "epoch": 0.32710978342046304, "grad_norm": 0.8261781930923462, "learning_rate": 4.983530312542874e-06, "loss": 0.6571, "step": 292 }, { "epoch": 0.32823002240477966, "grad_norm": 0.8620947599411011, "learning_rate": 4.983358497612118e-06, "loss": 0.6195, "step": 293 }, { "epoch": 0.32935026138909634, "grad_norm": 0.8011974692344666, "learning_rate": 4.983185794115311e-06, "loss": 0.6157, "step": 294 }, { "epoch": 0.33047050037341297, "grad_norm": 0.8179512619972229, "learning_rate": 4.983012202114247e-06, "loss": 0.6086, "step": 295 }, { "epoch": 0.33159073935772965, "grad_norm": 0.82745760679245, "learning_rate": 4.98283772167104e-06, "loss": 0.651, "step": 296 }, { "epoch": 0.3327109783420463, "grad_norm": 0.8494473695755005, "learning_rate": 4.982662352848119e-06, "loss": 0.6114, "step": 297 }, { "epoch": 0.33383121732636295, "grad_norm": 0.80657559633255, "learning_rate": 4.982486095708234e-06, "loss": 0.6105, "step": 298 }, { "epoch": 0.33495145631067963, "grad_norm": 0.8035582900047302, "learning_rate": 4.982308950314449e-06, "loss": 0.6373, "step": 299 }, { "epoch": 0.33607169529499625, "grad_norm": 0.7871240377426147, "learning_rate": 4.982130916730151e-06, "loss": 0.6004, "step": 300 }, { "epoch": 0.33719193427931293, "grad_norm": 0.8356077075004578, "learning_rate": 4.98195199501904e-06, "loss": 0.6164, "step": 301 }, { "epoch": 0.33831217326362956, "grad_norm": 0.7815148234367371, "learning_rate": 4.981772185245135e-06, "loss": 0.6173, "step": 302 }, { "epoch": 0.33943241224794624, "grad_norm": 0.8669472336769104, "learning_rate": 4.981591487472776e-06, "loss": 0.6209, "step": 303 }, { "epoch": 0.34055265123226286, "grad_norm": 0.7833518385887146, "learning_rate": 4.981409901766615e-06, "loss": 0.6178, "step": 304 }, { "epoch": 0.34167289021657954, "grad_norm": 0.79278165102005, "learning_rate": 4.9812274281916275e-06, "loss": 0.6268, "step": 305 }, { "epoch": 0.3427931292008962, "grad_norm": 0.802302360534668, "learning_rate": 4.981044066813102e-06, "loss": 0.5878, "step": 306 }, { "epoch": 0.34391336818521284, "grad_norm": 0.8093838691711426, "learning_rate": 4.9808598176966485e-06, "loss": 0.6419, "step": 307 }, { "epoch": 0.3450336071695295, "grad_norm": 0.7981029152870178, "learning_rate": 4.980674680908192e-06, "loss": 0.6203, "step": 308 }, { "epoch": 0.34615384615384615, "grad_norm": 0.8186250329017639, "learning_rate": 4.980488656513976e-06, "loss": 0.6346, "step": 309 }, { "epoch": 0.3472740851381628, "grad_norm": 0.7659736275672913, "learning_rate": 4.980301744580561e-06, "loss": 0.5925, "step": 310 }, { "epoch": 0.34839432412247945, "grad_norm": 0.8284393548965454, "learning_rate": 4.980113945174826e-06, "loss": 0.6471, "step": 311 }, { "epoch": 0.34951456310679613, "grad_norm": 0.7763761878013611, "learning_rate": 4.979925258363968e-06, "loss": 0.6095, "step": 312 }, { "epoch": 0.35063480209111275, "grad_norm": 0.820344090461731, "learning_rate": 4.979735684215499e-06, "loss": 0.6044, "step": 313 }, { "epoch": 0.35175504107542943, "grad_norm": 0.8457436561584473, "learning_rate": 4.979545222797252e-06, "loss": 0.6176, "step": 314 }, { "epoch": 0.35287528005974605, "grad_norm": 0.8047285079956055, "learning_rate": 4.979353874177375e-06, "loss": 0.5912, "step": 315 }, { "epoch": 0.35399551904406273, "grad_norm": 0.8075456619262695, "learning_rate": 4.9791616384243335e-06, "loss": 0.5807, "step": 316 }, { "epoch": 0.3551157580283794, "grad_norm": 0.7939711809158325, "learning_rate": 4.978968515606912e-06, "loss": 0.5862, "step": 317 }, { "epoch": 0.35623599701269604, "grad_norm": 0.8410739302635193, "learning_rate": 4.97877450579421e-06, "loss": 0.6144, "step": 318 }, { "epoch": 0.3573562359970127, "grad_norm": 0.8608905076980591, "learning_rate": 4.9785796090556485e-06, "loss": 0.6428, "step": 319 }, { "epoch": 0.35847647498132934, "grad_norm": 0.8229684233665466, "learning_rate": 4.978383825460959e-06, "loss": 0.6124, "step": 320 }, { "epoch": 0.359596713965646, "grad_norm": 0.790482223033905, "learning_rate": 4.978187155080199e-06, "loss": 0.6127, "step": 321 }, { "epoch": 0.36071695294996264, "grad_norm": 0.7994086146354675, "learning_rate": 4.9779895979837355e-06, "loss": 0.6337, "step": 322 }, { "epoch": 0.3618371919342793, "grad_norm": 0.8186279535293579, "learning_rate": 4.977791154242257e-06, "loss": 0.6257, "step": 323 }, { "epoch": 0.36295743091859595, "grad_norm": 0.7845602631568909, "learning_rate": 4.977591823926769e-06, "loss": 0.5702, "step": 324 }, { "epoch": 0.3640776699029126, "grad_norm": 0.7722570300102234, "learning_rate": 4.977391607108593e-06, "loss": 0.5897, "step": 325 }, { "epoch": 0.36519790888722925, "grad_norm": 0.8029158115386963, "learning_rate": 4.977190503859368e-06, "loss": 0.6142, "step": 326 }, { "epoch": 0.36631814787154593, "grad_norm": 0.801633894443512, "learning_rate": 4.976988514251051e-06, "loss": 0.6298, "step": 327 }, { "epoch": 0.3674383868558626, "grad_norm": 0.8345485925674438, "learning_rate": 4.976785638355914e-06, "loss": 0.6351, "step": 328 }, { "epoch": 0.36855862584017923, "grad_norm": 0.793038547039032, "learning_rate": 4.97658187624655e-06, "loss": 0.6463, "step": 329 }, { "epoch": 0.3696788648244959, "grad_norm": 0.8270999789237976, "learning_rate": 4.976377227995866e-06, "loss": 0.6193, "step": 330 }, { "epoch": 0.37079910380881254, "grad_norm": 0.8013745546340942, "learning_rate": 4.9761716936770855e-06, "loss": 0.6047, "step": 331 }, { "epoch": 0.3719193427931292, "grad_norm": 0.8266115784645081, "learning_rate": 4.975965273363751e-06, "loss": 0.6226, "step": 332 }, { "epoch": 0.37303958177744584, "grad_norm": 0.8072906732559204, "learning_rate": 4.975757967129722e-06, "loss": 0.615, "step": 333 }, { "epoch": 0.3741598207617625, "grad_norm": 0.7997392416000366, "learning_rate": 4.975549775049174e-06, "loss": 0.6271, "step": 334 }, { "epoch": 0.37528005974607914, "grad_norm": 0.8856087923049927, "learning_rate": 4.9753406971966e-06, "loss": 0.6066, "step": 335 }, { "epoch": 0.3764002987303958, "grad_norm": 0.7950431704521179, "learning_rate": 4.975130733646809e-06, "loss": 0.6001, "step": 336 }, { "epoch": 0.37752053771471245, "grad_norm": 0.8051393032073975, "learning_rate": 4.974919884474929e-06, "loss": 0.6316, "step": 337 }, { "epoch": 0.3786407766990291, "grad_norm": 0.8180161714553833, "learning_rate": 4.974708149756403e-06, "loss": 0.6362, "step": 338 }, { "epoch": 0.3797610156833458, "grad_norm": 0.8257321119308472, "learning_rate": 4.974495529566991e-06, "loss": 0.626, "step": 339 }, { "epoch": 0.38088125466766243, "grad_norm": 0.8660753965377808, "learning_rate": 4.9742820239827705e-06, "loss": 0.6191, "step": 340 }, { "epoch": 0.3820014936519791, "grad_norm": 0.7817429900169373, "learning_rate": 4.974067633080135e-06, "loss": 0.6297, "step": 341 }, { "epoch": 0.38312173263629573, "grad_norm": 0.807461678981781, "learning_rate": 4.973852356935797e-06, "loss": 0.6356, "step": 342 }, { "epoch": 0.3842419716206124, "grad_norm": 0.8301308155059814, "learning_rate": 4.973636195626783e-06, "loss": 0.6205, "step": 343 }, { "epoch": 0.38536221060492903, "grad_norm": 0.897199809551239, "learning_rate": 4.973419149230437e-06, "loss": 0.6455, "step": 344 }, { "epoch": 0.3864824495892457, "grad_norm": 0.8273870944976807, "learning_rate": 4.9732012178244194e-06, "loss": 0.6458, "step": 345 }, { "epoch": 0.38760268857356234, "grad_norm": 0.9393578767776489, "learning_rate": 4.972982401486709e-06, "loss": 0.61, "step": 346 }, { "epoch": 0.388722927557879, "grad_norm": 0.8364170789718628, "learning_rate": 4.9727627002956e-06, "loss": 0.6195, "step": 347 }, { "epoch": 0.3898431665421957, "grad_norm": 0.8208838701248169, "learning_rate": 4.972542114329704e-06, "loss": 0.6246, "step": 348 }, { "epoch": 0.3909634055265123, "grad_norm": 0.8595433831214905, "learning_rate": 4.972320643667946e-06, "loss": 0.6251, "step": 349 }, { "epoch": 0.392083644510829, "grad_norm": 0.7956632375717163, "learning_rate": 4.972098288389572e-06, "loss": 0.608, "step": 350 }, { "epoch": 0.3932038834951456, "grad_norm": 0.8434047698974609, "learning_rate": 4.9718750485741425e-06, "loss": 0.6137, "step": 351 }, { "epoch": 0.3943241224794623, "grad_norm": 0.8272572755813599, "learning_rate": 4.971650924301534e-06, "loss": 0.623, "step": 352 }, { "epoch": 0.3954443614637789, "grad_norm": 0.8429244756698608, "learning_rate": 4.9714259156519406e-06, "loss": 0.6325, "step": 353 }, { "epoch": 0.3965646004480956, "grad_norm": 0.8181564807891846, "learning_rate": 4.971200022705871e-06, "loss": 0.6421, "step": 354 }, { "epoch": 0.39768483943241223, "grad_norm": 0.7761826515197754, "learning_rate": 4.970973245544153e-06, "loss": 0.6063, "step": 355 }, { "epoch": 0.3988050784167289, "grad_norm": 0.8283432126045227, "learning_rate": 4.970745584247928e-06, "loss": 0.6125, "step": 356 }, { "epoch": 0.39992531740104553, "grad_norm": 0.8041115999221802, "learning_rate": 4.9705170388986565e-06, "loss": 0.6227, "step": 357 }, { "epoch": 0.4010455563853622, "grad_norm": 0.792184054851532, "learning_rate": 4.970287609578112e-06, "loss": 0.624, "step": 358 }, { "epoch": 0.4021657953696789, "grad_norm": 0.8069051504135132, "learning_rate": 4.970057296368388e-06, "loss": 0.6162, "step": 359 }, { "epoch": 0.4032860343539955, "grad_norm": 0.7888614535331726, "learning_rate": 4.969826099351892e-06, "loss": 0.6088, "step": 360 }, { "epoch": 0.4044062733383122, "grad_norm": 0.8092378377914429, "learning_rate": 4.969594018611348e-06, "loss": 0.6062, "step": 361 }, { "epoch": 0.4055265123226288, "grad_norm": 0.8325386047363281, "learning_rate": 4.969361054229796e-06, "loss": 0.6277, "step": 362 }, { "epoch": 0.4066467513069455, "grad_norm": 0.860455334186554, "learning_rate": 4.9691272062905935e-06, "loss": 0.6202, "step": 363 }, { "epoch": 0.4077669902912621, "grad_norm": 0.8035297989845276, "learning_rate": 4.968892474877412e-06, "loss": 0.6087, "step": 364 }, { "epoch": 0.4088872292755788, "grad_norm": 0.792544424533844, "learning_rate": 4.968656860074241e-06, "loss": 0.5919, "step": 365 }, { "epoch": 0.4100074682598954, "grad_norm": 0.8256428837776184, "learning_rate": 4.968420361965386e-06, "loss": 0.5922, "step": 366 }, { "epoch": 0.4111277072442121, "grad_norm": 0.8024367094039917, "learning_rate": 4.968182980635468e-06, "loss": 0.6332, "step": 367 }, { "epoch": 0.4122479462285287, "grad_norm": 0.7686941027641296, "learning_rate": 4.967944716169421e-06, "loss": 0.5954, "step": 368 }, { "epoch": 0.4133681852128454, "grad_norm": 0.814935028553009, "learning_rate": 4.967705568652502e-06, "loss": 0.627, "step": 369 }, { "epoch": 0.4144884241971621, "grad_norm": 0.7745496034622192, "learning_rate": 4.967465538170279e-06, "loss": 0.6051, "step": 370 }, { "epoch": 0.4156086631814787, "grad_norm": 0.8013162612915039, "learning_rate": 4.9672246248086344e-06, "loss": 0.6005, "step": 371 }, { "epoch": 0.4167289021657954, "grad_norm": 0.8392379879951477, "learning_rate": 4.966982828653772e-06, "loss": 0.624, "step": 372 }, { "epoch": 0.417849141150112, "grad_norm": 0.781700849533081, "learning_rate": 4.966740149792206e-06, "loss": 0.6064, "step": 373 }, { "epoch": 0.4189693801344287, "grad_norm": 0.8092135190963745, "learning_rate": 4.966496588310771e-06, "loss": 0.6355, "step": 374 }, { "epoch": 0.4200896191187453, "grad_norm": 0.7815409898757935, "learning_rate": 4.966252144296614e-06, "loss": 0.6039, "step": 375 }, { "epoch": 0.421209858103062, "grad_norm": 0.7987800240516663, "learning_rate": 4.9660068178372e-06, "loss": 0.6341, "step": 376 }, { "epoch": 0.4223300970873786, "grad_norm": 0.8279643058776855, "learning_rate": 4.965760609020308e-06, "loss": 0.6119, "step": 377 }, { "epoch": 0.4234503360716953, "grad_norm": 0.79878830909729, "learning_rate": 4.965513517934033e-06, "loss": 0.6334, "step": 378 }, { "epoch": 0.4245705750560119, "grad_norm": 0.8361204862594604, "learning_rate": 4.965265544666788e-06, "loss": 0.6078, "step": 379 }, { "epoch": 0.4256908140403286, "grad_norm": 0.8225858211517334, "learning_rate": 4.965016689307298e-06, "loss": 0.6264, "step": 380 }, { "epoch": 0.4268110530246453, "grad_norm": 0.8204994201660156, "learning_rate": 4.964766951944607e-06, "loss": 0.606, "step": 381 }, { "epoch": 0.4279312920089619, "grad_norm": 0.8047780990600586, "learning_rate": 4.964516332668073e-06, "loss": 0.6053, "step": 382 }, { "epoch": 0.4290515309932786, "grad_norm": 0.8498148322105408, "learning_rate": 4.964264831567368e-06, "loss": 0.6211, "step": 383 }, { "epoch": 0.4301717699775952, "grad_norm": 0.8710355758666992, "learning_rate": 4.964012448732482e-06, "loss": 0.6134, "step": 384 }, { "epoch": 0.4312920089619119, "grad_norm": 0.8357451558113098, "learning_rate": 4.963759184253721e-06, "loss": 0.6339, "step": 385 }, { "epoch": 0.4324122479462285, "grad_norm": 0.8333609700202942, "learning_rate": 4.963505038221704e-06, "loss": 0.623, "step": 386 }, { "epoch": 0.4335324869305452, "grad_norm": 0.8006998300552368, "learning_rate": 4.963250010727366e-06, "loss": 0.621, "step": 387 }, { "epoch": 0.4346527259148618, "grad_norm": 0.8830387592315674, "learning_rate": 4.962994101861959e-06, "loss": 0.5945, "step": 388 }, { "epoch": 0.4357729648991785, "grad_norm": 0.8361951112747192, "learning_rate": 4.9627373117170476e-06, "loss": 0.6042, "step": 389 }, { "epoch": 0.4368932038834951, "grad_norm": 0.8356959819793701, "learning_rate": 4.962479640384516e-06, "loss": 0.6423, "step": 390 }, { "epoch": 0.4380134428678118, "grad_norm": 0.8058585524559021, "learning_rate": 4.962221087956558e-06, "loss": 0.622, "step": 391 }, { "epoch": 0.4391336818521285, "grad_norm": 0.8438712358474731, "learning_rate": 4.961961654525689e-06, "loss": 0.619, "step": 392 }, { "epoch": 0.4402539208364451, "grad_norm": 0.8207183480262756, "learning_rate": 4.961701340184734e-06, "loss": 0.6095, "step": 393 }, { "epoch": 0.4413741598207618, "grad_norm": 0.8222430348396301, "learning_rate": 4.9614401450268364e-06, "loss": 0.6266, "step": 394 }, { "epoch": 0.4424943988050784, "grad_norm": 0.8192475438117981, "learning_rate": 4.961178069145455e-06, "loss": 0.6146, "step": 395 }, { "epoch": 0.4436146377893951, "grad_norm": 0.7848315238952637, "learning_rate": 4.960915112634362e-06, "loss": 0.6046, "step": 396 }, { "epoch": 0.4447348767737117, "grad_norm": 0.8019006848335266, "learning_rate": 4.960651275587644e-06, "loss": 0.6253, "step": 397 }, { "epoch": 0.4458551157580284, "grad_norm": 0.8097095489501953, "learning_rate": 4.960386558099706e-06, "loss": 0.6284, "step": 398 }, { "epoch": 0.446975354742345, "grad_norm": 0.796343207359314, "learning_rate": 4.9601209602652644e-06, "loss": 0.6051, "step": 399 }, { "epoch": 0.4480955937266617, "grad_norm": 0.8076500296592712, "learning_rate": 4.959854482179354e-06, "loss": 0.6215, "step": 400 }, { "epoch": 0.44921583271097837, "grad_norm": 0.8721750974655151, "learning_rate": 4.9595871239373215e-06, "loss": 0.6534, "step": 401 }, { "epoch": 0.450336071695295, "grad_norm": 0.8260684013366699, "learning_rate": 4.959318885634831e-06, "loss": 0.6073, "step": 402 }, { "epoch": 0.45145631067961167, "grad_norm": 0.8113908767700195, "learning_rate": 4.95904976736786e-06, "loss": 0.6004, "step": 403 }, { "epoch": 0.4525765496639283, "grad_norm": 0.8291077017784119, "learning_rate": 4.9587797692327e-06, "loss": 0.622, "step": 404 }, { "epoch": 0.453696788648245, "grad_norm": 0.8331876993179321, "learning_rate": 4.95850889132596e-06, "loss": 0.6367, "step": 405 }, { "epoch": 0.4548170276325616, "grad_norm": 0.8167732357978821, "learning_rate": 4.9582371337445624e-06, "loss": 0.6191, "step": 406 }, { "epoch": 0.4559372666168783, "grad_norm": 0.8163003921508789, "learning_rate": 4.957964496585743e-06, "loss": 0.6197, "step": 407 }, { "epoch": 0.4570575056011949, "grad_norm": 0.8027840852737427, "learning_rate": 4.957690979947055e-06, "loss": 0.6119, "step": 408 }, { "epoch": 0.4581777445855116, "grad_norm": 0.8352331519126892, "learning_rate": 4.957416583926364e-06, "loss": 0.6176, "step": 409 }, { "epoch": 0.4592979835698282, "grad_norm": 0.846203625202179, "learning_rate": 4.957141308621851e-06, "loss": 0.608, "step": 410 }, { "epoch": 0.4604182225541449, "grad_norm": 0.8850703239440918, "learning_rate": 4.956865154132013e-06, "loss": 0.6359, "step": 411 }, { "epoch": 0.46153846153846156, "grad_norm": 0.7965673804283142, "learning_rate": 4.95658812055566e-06, "loss": 0.5849, "step": 412 }, { "epoch": 0.4626587005227782, "grad_norm": 0.862568199634552, "learning_rate": 4.956310207991916e-06, "loss": 0.6176, "step": 413 }, { "epoch": 0.46377893950709487, "grad_norm": 0.8031529784202576, "learning_rate": 4.95603141654022e-06, "loss": 0.5987, "step": 414 }, { "epoch": 0.4648991784914115, "grad_norm": 0.8270638585090637, "learning_rate": 4.9557517463003275e-06, "loss": 0.6611, "step": 415 }, { "epoch": 0.46601941747572817, "grad_norm": 0.7914713025093079, "learning_rate": 4.9554711973723055e-06, "loss": 0.5944, "step": 416 }, { "epoch": 0.4671396564600448, "grad_norm": 0.8575369119644165, "learning_rate": 4.9551897698565376e-06, "loss": 0.6282, "step": 417 }, { "epoch": 0.4682598954443615, "grad_norm": 0.766158401966095, "learning_rate": 4.9549074638537205e-06, "loss": 0.5798, "step": 418 }, { "epoch": 0.4693801344286781, "grad_norm": 0.7910577654838562, "learning_rate": 4.954624279464866e-06, "loss": 0.5881, "step": 419 }, { "epoch": 0.4705003734129948, "grad_norm": 0.8028966188430786, "learning_rate": 4.9543402167912985e-06, "loss": 0.6126, "step": 420 }, { "epoch": 0.4716206123973114, "grad_norm": 0.8077728748321533, "learning_rate": 4.9540552759346596e-06, "loss": 0.6072, "step": 421 }, { "epoch": 0.4727408513816281, "grad_norm": 0.8463570475578308, "learning_rate": 4.953769456996902e-06, "loss": 0.5721, "step": 422 }, { "epoch": 0.47386109036594476, "grad_norm": 0.7810856699943542, "learning_rate": 4.9534827600802956e-06, "loss": 0.5852, "step": 423 }, { "epoch": 0.4749813293502614, "grad_norm": 0.7997978329658508, "learning_rate": 4.953195185287421e-06, "loss": 0.5766, "step": 424 }, { "epoch": 0.47610156833457806, "grad_norm": 0.7943705320358276, "learning_rate": 4.952906732721177e-06, "loss": 0.5915, "step": 425 }, { "epoch": 0.4772218073188947, "grad_norm": 0.7930023670196533, "learning_rate": 4.952617402484773e-06, "loss": 0.6025, "step": 426 }, { "epoch": 0.47834204630321137, "grad_norm": 0.7801458835601807, "learning_rate": 4.952327194681734e-06, "loss": 0.5947, "step": 427 }, { "epoch": 0.479462285287528, "grad_norm": 0.8124021291732788, "learning_rate": 4.952036109415899e-06, "loss": 0.6175, "step": 428 }, { "epoch": 0.48058252427184467, "grad_norm": 0.8290462493896484, "learning_rate": 4.9517441467914195e-06, "loss": 0.6229, "step": 429 }, { "epoch": 0.4817027632561613, "grad_norm": 0.7960165739059448, "learning_rate": 4.951451306912764e-06, "loss": 0.6078, "step": 430 }, { "epoch": 0.48282300224047797, "grad_norm": 0.8182939887046814, "learning_rate": 4.951157589884711e-06, "loss": 0.6145, "step": 431 }, { "epoch": 0.4839432412247946, "grad_norm": 0.7847172021865845, "learning_rate": 4.950862995812356e-06, "loss": 0.592, "step": 432 }, { "epoch": 0.4850634802091113, "grad_norm": 0.8396735191345215, "learning_rate": 4.9505675248011085e-06, "loss": 0.6323, "step": 433 }, { "epoch": 0.48618371919342795, "grad_norm": 0.8656349778175354, "learning_rate": 4.950271176956688e-06, "loss": 0.6237, "step": 434 }, { "epoch": 0.4873039581777446, "grad_norm": 0.8108944296836853, "learning_rate": 4.949973952385131e-06, "loss": 0.6148, "step": 435 }, { "epoch": 0.48842419716206126, "grad_norm": 0.839131236076355, "learning_rate": 4.949675851192786e-06, "loss": 0.6475, "step": 436 }, { "epoch": 0.4895444361463779, "grad_norm": 0.8033477067947388, "learning_rate": 4.949376873486319e-06, "loss": 0.6095, "step": 437 }, { "epoch": 0.49066467513069456, "grad_norm": 0.8268027901649475, "learning_rate": 4.949077019372704e-06, "loss": 0.6096, "step": 438 }, { "epoch": 0.4917849141150112, "grad_norm": 0.8278724551200867, "learning_rate": 4.948776288959233e-06, "loss": 0.6225, "step": 439 }, { "epoch": 0.49290515309932786, "grad_norm": 0.8136724233627319, "learning_rate": 4.948474682353508e-06, "loss": 0.6063, "step": 440 }, { "epoch": 0.4940253920836445, "grad_norm": 0.821102499961853, "learning_rate": 4.948172199663448e-06, "loss": 0.6214, "step": 441 }, { "epoch": 0.49514563106796117, "grad_norm": 0.8143325448036194, "learning_rate": 4.947868840997282e-06, "loss": 0.6021, "step": 442 }, { "epoch": 0.49626587005227785, "grad_norm": 0.8387938141822815, "learning_rate": 4.947564606463556e-06, "loss": 0.6299, "step": 443 }, { "epoch": 0.49738610903659447, "grad_norm": 0.8075438737869263, "learning_rate": 4.9472594961711266e-06, "loss": 0.603, "step": 444 }, { "epoch": 0.49850634802091115, "grad_norm": 0.8184303641319275, "learning_rate": 4.946953510229164e-06, "loss": 0.6126, "step": 445 }, { "epoch": 0.4996265870052278, "grad_norm": 0.8168706893920898, "learning_rate": 4.946646648747155e-06, "loss": 0.5987, "step": 446 }, { "epoch": 0.5007468259895445, "grad_norm": 0.8080923557281494, "learning_rate": 4.946338911834895e-06, "loss": 0.5998, "step": 447 }, { "epoch": 0.5018670649738611, "grad_norm": 0.8014161586761475, "learning_rate": 4.946030299602496e-06, "loss": 0.6279, "step": 448 }, { "epoch": 0.5029873039581777, "grad_norm": 0.7952543497085571, "learning_rate": 4.94572081216038e-06, "loss": 0.5883, "step": 449 }, { "epoch": 0.5041075429424944, "grad_norm": 0.8177149295806885, "learning_rate": 4.945410449619286e-06, "loss": 0.5988, "step": 450 }, { "epoch": 0.5052277819268111, "grad_norm": 0.8595210909843445, "learning_rate": 4.945099212090265e-06, "loss": 0.6387, "step": 451 }, { "epoch": 0.5063480209111277, "grad_norm": 0.8385729193687439, "learning_rate": 4.944787099684678e-06, "loss": 0.6276, "step": 452 }, { "epoch": 0.5074682598954443, "grad_norm": 0.7771918177604675, "learning_rate": 4.944474112514204e-06, "loss": 0.5967, "step": 453 }, { "epoch": 0.508588498879761, "grad_norm": 0.7973781228065491, "learning_rate": 4.9441602506908295e-06, "loss": 0.6055, "step": 454 }, { "epoch": 0.5097087378640777, "grad_norm": 0.8014892935752869, "learning_rate": 4.9438455143268596e-06, "loss": 0.6018, "step": 455 }, { "epoch": 0.5108289768483943, "grad_norm": 0.8037407994270325, "learning_rate": 4.943529903534907e-06, "loss": 0.6117, "step": 456 }, { "epoch": 0.511949215832711, "grad_norm": 0.8133897185325623, "learning_rate": 4.943213418427901e-06, "loss": 0.5902, "step": 457 }, { "epoch": 0.5130694548170276, "grad_norm": 0.81773841381073, "learning_rate": 4.9428960591190834e-06, "loss": 0.6017, "step": 458 }, { "epoch": 0.5141896938013443, "grad_norm": 0.8633530735969543, "learning_rate": 4.942577825722007e-06, "loss": 0.597, "step": 459 }, { "epoch": 0.515309932785661, "grad_norm": 0.7943804264068604, "learning_rate": 4.942258718350539e-06, "loss": 0.605, "step": 460 }, { "epoch": 0.5164301717699776, "grad_norm": 0.8280025124549866, "learning_rate": 4.941938737118857e-06, "loss": 0.5855, "step": 461 }, { "epoch": 0.5175504107542942, "grad_norm": 0.7869625091552734, "learning_rate": 4.941617882141455e-06, "loss": 0.6035, "step": 462 }, { "epoch": 0.5186706497386109, "grad_norm": 0.8214724659919739, "learning_rate": 4.9412961535331365e-06, "loss": 0.6402, "step": 463 }, { "epoch": 0.5197908887229276, "grad_norm": 0.8125516772270203, "learning_rate": 4.940973551409018e-06, "loss": 0.6135, "step": 464 }, { "epoch": 0.5209111277072442, "grad_norm": 0.8744713068008423, "learning_rate": 4.9406500758845305e-06, "loss": 0.5904, "step": 465 }, { "epoch": 0.5220313666915609, "grad_norm": 0.8251977562904358, "learning_rate": 4.940325727075415e-06, "loss": 0.6185, "step": 466 }, { "epoch": 0.5231516056758775, "grad_norm": 0.7986443638801575, "learning_rate": 4.940000505097728e-06, "loss": 0.6177, "step": 467 }, { "epoch": 0.5242718446601942, "grad_norm": 0.8290914297103882, "learning_rate": 4.939674410067834e-06, "loss": 0.6531, "step": 468 }, { "epoch": 0.5253920836445108, "grad_norm": 0.7911964058876038, "learning_rate": 4.939347442102415e-06, "loss": 0.6278, "step": 469 }, { "epoch": 0.5265123226288275, "grad_norm": 0.7842428088188171, "learning_rate": 4.9390196013184614e-06, "loss": 0.6014, "step": 470 }, { "epoch": 0.5276325616131441, "grad_norm": 0.8033813834190369, "learning_rate": 4.9386908878332775e-06, "loss": 0.5975, "step": 471 }, { "epoch": 0.5287528005974608, "grad_norm": 0.7822708487510681, "learning_rate": 4.9383613017644796e-06, "loss": 0.5812, "step": 472 }, { "epoch": 0.5298730395817774, "grad_norm": 0.8360676169395447, "learning_rate": 4.9380308432299976e-06, "loss": 0.6112, "step": 473 }, { "epoch": 0.5309932785660941, "grad_norm": 0.8052594065666199, "learning_rate": 4.93769951234807e-06, "loss": 0.6044, "step": 474 }, { "epoch": 0.5321135175504108, "grad_norm": 0.7881698608398438, "learning_rate": 4.937367309237251e-06, "loss": 0.5778, "step": 475 }, { "epoch": 0.5332337565347274, "grad_norm": 0.8374946117401123, "learning_rate": 4.937034234016406e-06, "loss": 0.6213, "step": 476 }, { "epoch": 0.5343539955190441, "grad_norm": 0.8044434189796448, "learning_rate": 4.936700286804711e-06, "loss": 0.5984, "step": 477 }, { "epoch": 0.5354742345033607, "grad_norm": 0.7946317195892334, "learning_rate": 4.936365467721655e-06, "loss": 0.6027, "step": 478 }, { "epoch": 0.5365944734876774, "grad_norm": 0.8196859955787659, "learning_rate": 4.93602977688704e-06, "loss": 0.6009, "step": 479 }, { "epoch": 0.537714712471994, "grad_norm": 0.8330888748168945, "learning_rate": 4.935693214420979e-06, "loss": 0.6396, "step": 480 }, { "epoch": 0.5388349514563107, "grad_norm": 0.7970585823059082, "learning_rate": 4.935355780443896e-06, "loss": 0.6134, "step": 481 }, { "epoch": 0.5399551904406273, "grad_norm": 0.8149996399879456, "learning_rate": 4.935017475076529e-06, "loss": 0.6214, "step": 482 }, { "epoch": 0.541075429424944, "grad_norm": 0.7842663526535034, "learning_rate": 4.9346782984399246e-06, "loss": 0.6084, "step": 483 }, { "epoch": 0.5421956684092606, "grad_norm": 0.8166002035140991, "learning_rate": 4.934338250655444e-06, "loss": 0.5939, "step": 484 }, { "epoch": 0.5433159073935773, "grad_norm": 0.8198996186256409, "learning_rate": 4.933997331844758e-06, "loss": 0.5925, "step": 485 }, { "epoch": 0.544436146377894, "grad_norm": 0.8149311542510986, "learning_rate": 4.933655542129852e-06, "loss": 0.618, "step": 486 }, { "epoch": 0.5455563853622106, "grad_norm": 0.8132028579711914, "learning_rate": 4.93331288163302e-06, "loss": 0.5923, "step": 487 }, { "epoch": 0.5466766243465273, "grad_norm": 0.8155807852745056, "learning_rate": 4.9329693504768686e-06, "loss": 0.5966, "step": 488 }, { "epoch": 0.5477968633308439, "grad_norm": 0.8111668229103088, "learning_rate": 4.932624948784317e-06, "loss": 0.613, "step": 489 }, { "epoch": 0.5489171023151606, "grad_norm": 0.8030702471733093, "learning_rate": 4.932279676678594e-06, "loss": 0.6077, "step": 490 }, { "epoch": 0.5500373412994772, "grad_norm": 0.8306952118873596, "learning_rate": 4.931933534283241e-06, "loss": 0.6182, "step": 491 }, { "epoch": 0.5511575802837939, "grad_norm": 0.8086608052253723, "learning_rate": 4.931586521722112e-06, "loss": 0.5989, "step": 492 }, { "epoch": 0.5522778192681105, "grad_norm": 0.8051784634590149, "learning_rate": 4.931238639119368e-06, "loss": 0.595, "step": 493 }, { "epoch": 0.5533980582524272, "grad_norm": 0.7761525511741638, "learning_rate": 4.930889886599486e-06, "loss": 0.5773, "step": 494 }, { "epoch": 0.5545182972367438, "grad_norm": 0.7963784337043762, "learning_rate": 4.9305402642872534e-06, "loss": 0.578, "step": 495 }, { "epoch": 0.5556385362210605, "grad_norm": 0.7898165583610535, "learning_rate": 4.9301897723077664e-06, "loss": 0.5954, "step": 496 }, { "epoch": 0.5567587752053772, "grad_norm": 0.7823036909103394, "learning_rate": 4.929838410786435e-06, "loss": 0.5871, "step": 497 }, { "epoch": 0.5578790141896938, "grad_norm": 0.8508079648017883, "learning_rate": 4.929486179848979e-06, "loss": 0.6044, "step": 498 }, { "epoch": 0.5589992531740104, "grad_norm": 0.8375908136367798, "learning_rate": 4.9291330796214285e-06, "loss": 0.6175, "step": 499 }, { "epoch": 0.5601194921583271, "grad_norm": 0.8124059438705444, "learning_rate": 4.928779110230126e-06, "loss": 0.5857, "step": 500 }, { "epoch": 0.5612397311426438, "grad_norm": 0.8159031271934509, "learning_rate": 4.928424271801726e-06, "loss": 0.6013, "step": 501 }, { "epoch": 0.5623599701269604, "grad_norm": 0.7889281511306763, "learning_rate": 4.928068564463192e-06, "loss": 0.5959, "step": 502 }, { "epoch": 0.563480209111277, "grad_norm": 0.8010871410369873, "learning_rate": 4.927711988341798e-06, "loss": 0.591, "step": 503 }, { "epoch": 0.5646004480955937, "grad_norm": 0.8424665927886963, "learning_rate": 4.927354543565131e-06, "loss": 0.5844, "step": 504 }, { "epoch": 0.5657206870799104, "grad_norm": 0.7999626398086548, "learning_rate": 4.9269962302610866e-06, "loss": 0.5836, "step": 505 }, { "epoch": 0.566840926064227, "grad_norm": 0.8242966532707214, "learning_rate": 4.926637048557873e-06, "loss": 0.5929, "step": 506 }, { "epoch": 0.5679611650485437, "grad_norm": 0.8201645016670227, "learning_rate": 4.926276998584008e-06, "loss": 0.5937, "step": 507 }, { "epoch": 0.5690814040328603, "grad_norm": 0.8664683699607849, "learning_rate": 4.925916080468321e-06, "loss": 0.6258, "step": 508 }, { "epoch": 0.570201643017177, "grad_norm": 0.8183404207229614, "learning_rate": 4.925554294339951e-06, "loss": 0.6088, "step": 509 }, { "epoch": 0.5713218820014937, "grad_norm": 0.8237192034721375, "learning_rate": 4.925191640328348e-06, "loss": 0.6054, "step": 510 }, { "epoch": 0.5724421209858103, "grad_norm": 0.8951362371444702, "learning_rate": 4.924828118563273e-06, "loss": 0.5847, "step": 511 }, { "epoch": 0.573562359970127, "grad_norm": 0.8432679176330566, "learning_rate": 4.924463729174796e-06, "loss": 0.6185, "step": 512 }, { "epoch": 0.5746825989544436, "grad_norm": 0.8540483117103577, "learning_rate": 4.924098472293301e-06, "loss": 0.6119, "step": 513 }, { "epoch": 0.5758028379387603, "grad_norm": 0.8214981555938721, "learning_rate": 4.923732348049477e-06, "loss": 0.5815, "step": 514 }, { "epoch": 0.5769230769230769, "grad_norm": 0.8091721534729004, "learning_rate": 4.9233653565743276e-06, "loss": 0.5912, "step": 515 }, { "epoch": 0.5780433159073936, "grad_norm": 0.8201042413711548, "learning_rate": 4.922997497999166e-06, "loss": 0.5754, "step": 516 }, { "epoch": 0.5791635548917102, "grad_norm": 0.8555132746696472, "learning_rate": 4.922628772455613e-06, "loss": 0.6227, "step": 517 }, { "epoch": 0.5802837938760269, "grad_norm": 0.805891752243042, "learning_rate": 4.922259180075604e-06, "loss": 0.5782, "step": 518 }, { "epoch": 0.5814040328603436, "grad_norm": 0.8111713528633118, "learning_rate": 4.921888720991381e-06, "loss": 0.5918, "step": 519 }, { "epoch": 0.5825242718446602, "grad_norm": 0.8208431601524353, "learning_rate": 4.921517395335497e-06, "loss": 0.6038, "step": 520 }, { "epoch": 0.5836445108289768, "grad_norm": 0.826924204826355, "learning_rate": 4.921145203240816e-06, "loss": 0.5922, "step": 521 }, { "epoch": 0.5847647498132935, "grad_norm": 0.8484541177749634, "learning_rate": 4.92077214484051e-06, "loss": 0.596, "step": 522 }, { "epoch": 0.5858849887976102, "grad_norm": 0.8284783363342285, "learning_rate": 4.920398220268064e-06, "loss": 0.599, "step": 523 }, { "epoch": 0.5870052277819268, "grad_norm": 0.8378069400787354, "learning_rate": 4.920023429657273e-06, "loss": 0.6259, "step": 524 }, { "epoch": 0.5881254667662434, "grad_norm": 0.8292249441146851, "learning_rate": 4.919647773142235e-06, "loss": 0.5925, "step": 525 }, { "epoch": 0.5892457057505601, "grad_norm": 0.8202025890350342, "learning_rate": 4.919271250857367e-06, "loss": 0.5932, "step": 526 }, { "epoch": 0.5903659447348768, "grad_norm": 0.8431236147880554, "learning_rate": 4.9188938629373915e-06, "loss": 0.5958, "step": 527 }, { "epoch": 0.5914861837191935, "grad_norm": 0.8396396040916443, "learning_rate": 4.9185156095173395e-06, "loss": 0.6148, "step": 528 }, { "epoch": 0.59260642270351, "grad_norm": 0.8345813155174255, "learning_rate": 4.9181364907325535e-06, "loss": 0.5651, "step": 529 }, { "epoch": 0.5937266616878267, "grad_norm": 0.8040415644645691, "learning_rate": 4.917756506718686e-06, "loss": 0.6102, "step": 530 }, { "epoch": 0.5948469006721434, "grad_norm": 0.7991846799850464, "learning_rate": 4.917375657611697e-06, "loss": 0.6, "step": 531 }, { "epoch": 0.5959671396564601, "grad_norm": 0.8031482696533203, "learning_rate": 4.9169939435478595e-06, "loss": 0.5883, "step": 532 }, { "epoch": 0.5970873786407767, "grad_norm": 0.8042899370193481, "learning_rate": 4.9166113646637534e-06, "loss": 0.561, "step": 533 }, { "epoch": 0.5982076176250933, "grad_norm": 0.8222240209579468, "learning_rate": 4.916227921096267e-06, "loss": 0.5649, "step": 534 }, { "epoch": 0.59932785660941, "grad_norm": 0.7763756513595581, "learning_rate": 4.915843612982601e-06, "loss": 0.577, "step": 535 }, { "epoch": 0.6004480955937267, "grad_norm": 0.8542895913124084, "learning_rate": 4.915458440460265e-06, "loss": 0.6099, "step": 536 }, { "epoch": 0.6015683345780433, "grad_norm": 0.8213333487510681, "learning_rate": 4.915072403667074e-06, "loss": 0.6131, "step": 537 }, { "epoch": 0.6026885735623599, "grad_norm": 0.8075094819068909, "learning_rate": 4.914685502741157e-06, "loss": 0.5938, "step": 538 }, { "epoch": 0.6038088125466766, "grad_norm": 0.843874454498291, "learning_rate": 4.91429773782095e-06, "loss": 0.5921, "step": 539 }, { "epoch": 0.6049290515309933, "grad_norm": 0.8286192417144775, "learning_rate": 4.913909109045198e-06, "loss": 0.6035, "step": 540 }, { "epoch": 0.60604929051531, "grad_norm": 0.7961990237236023, "learning_rate": 4.913519616552957e-06, "loss": 0.6176, "step": 541 }, { "epoch": 0.6071695294996265, "grad_norm": 0.7807387709617615, "learning_rate": 4.913129260483589e-06, "loss": 0.5905, "step": 542 }, { "epoch": 0.6082897684839432, "grad_norm": 0.8079019784927368, "learning_rate": 4.912738040976767e-06, "loss": 0.614, "step": 543 }, { "epoch": 0.6094100074682599, "grad_norm": 0.7950747609138489, "learning_rate": 4.912345958172474e-06, "loss": 0.6129, "step": 544 }, { "epoch": 0.6105302464525766, "grad_norm": 0.7880637645721436, "learning_rate": 4.911953012210998e-06, "loss": 0.5745, "step": 545 }, { "epoch": 0.6116504854368932, "grad_norm": 0.797683596611023, "learning_rate": 4.911559203232941e-06, "loss": 0.5704, "step": 546 }, { "epoch": 0.6127707244212098, "grad_norm": 0.7976189851760864, "learning_rate": 4.911164531379208e-06, "loss": 0.5753, "step": 547 }, { "epoch": 0.6138909634055265, "grad_norm": 0.797524631023407, "learning_rate": 4.910768996791018e-06, "loss": 0.5965, "step": 548 }, { "epoch": 0.6150112023898432, "grad_norm": 0.7966054677963257, "learning_rate": 4.910372599609896e-06, "loss": 0.5926, "step": 549 }, { "epoch": 0.6161314413741599, "grad_norm": 0.8061427474021912, "learning_rate": 4.909975339977676e-06, "loss": 0.6076, "step": 550 }, { "epoch": 0.6172516803584764, "grad_norm": 0.8192665576934814, "learning_rate": 4.909577218036501e-06, "loss": 0.5846, "step": 551 }, { "epoch": 0.6183719193427931, "grad_norm": 0.8142986297607422, "learning_rate": 4.909178233928822e-06, "loss": 0.6269, "step": 552 }, { "epoch": 0.6194921583271098, "grad_norm": 0.8129419684410095, "learning_rate": 4.908778387797399e-06, "loss": 0.6161, "step": 553 }, { "epoch": 0.6206123973114265, "grad_norm": 0.7790163159370422, "learning_rate": 4.9083776797853015e-06, "loss": 0.6039, "step": 554 }, { "epoch": 0.621732636295743, "grad_norm": 0.8370928168296814, "learning_rate": 4.907976110035903e-06, "loss": 0.5813, "step": 555 }, { "epoch": 0.6228528752800597, "grad_norm": 0.8461244702339172, "learning_rate": 4.907573678692891e-06, "loss": 0.5879, "step": 556 }, { "epoch": 0.6239731142643764, "grad_norm": 0.7943955659866333, "learning_rate": 4.907170385900258e-06, "loss": 0.579, "step": 557 }, { "epoch": 0.6250933532486931, "grad_norm": 0.8056941628456116, "learning_rate": 4.9067662318023056e-06, "loss": 0.6096, "step": 558 }, { "epoch": 0.6262135922330098, "grad_norm": 0.8091793060302734, "learning_rate": 4.906361216543643e-06, "loss": 0.5824, "step": 559 }, { "epoch": 0.6273338312173263, "grad_norm": 0.8035262227058411, "learning_rate": 4.905955340269188e-06, "loss": 0.6232, "step": 560 }, { "epoch": 0.628454070201643, "grad_norm": 0.7793251276016235, "learning_rate": 4.9055486031241675e-06, "loss": 0.5901, "step": 561 }, { "epoch": 0.6295743091859597, "grad_norm": 0.7671579122543335, "learning_rate": 4.9051410052541135e-06, "loss": 0.5843, "step": 562 }, { "epoch": 0.6306945481702764, "grad_norm": 0.8493455052375793, "learning_rate": 4.90473254680487e-06, "loss": 0.6254, "step": 563 }, { "epoch": 0.6318147871545929, "grad_norm": 0.8092489838600159, "learning_rate": 4.904323227922586e-06, "loss": 0.5906, "step": 564 }, { "epoch": 0.6329350261389096, "grad_norm": 0.8145341873168945, "learning_rate": 4.903913048753719e-06, "loss": 0.6129, "step": 565 }, { "epoch": 0.6340552651232263, "grad_norm": 0.8953230381011963, "learning_rate": 4.903502009445033e-06, "loss": 0.5975, "step": 566 }, { "epoch": 0.635175504107543, "grad_norm": 0.8133732676506042, "learning_rate": 4.903090110143605e-06, "loss": 0.558, "step": 567 }, { "epoch": 0.6362957430918595, "grad_norm": 0.8249391317367554, "learning_rate": 4.902677350996812e-06, "loss": 0.5893, "step": 568 }, { "epoch": 0.6374159820761762, "grad_norm": 0.8067794442176819, "learning_rate": 4.902263732152345e-06, "loss": 0.5823, "step": 569 }, { "epoch": 0.6385362210604929, "grad_norm": 0.8032618761062622, "learning_rate": 4.901849253758199e-06, "loss": 0.6003, "step": 570 }, { "epoch": 0.6396564600448096, "grad_norm": 0.8413413166999817, "learning_rate": 4.901433915962678e-06, "loss": 0.5742, "step": 571 }, { "epoch": 0.6407766990291263, "grad_norm": 0.8067041039466858, "learning_rate": 4.9010177189143935e-06, "loss": 0.5902, "step": 572 }, { "epoch": 0.6418969380134428, "grad_norm": 0.8752678632736206, "learning_rate": 4.900600662762265e-06, "loss": 0.6143, "step": 573 }, { "epoch": 0.6430171769977595, "grad_norm": 0.8311488628387451, "learning_rate": 4.9001827476555166e-06, "loss": 0.5901, "step": 574 }, { "epoch": 0.6441374159820762, "grad_norm": 0.8206403255462646, "learning_rate": 4.899763973743684e-06, "loss": 0.6056, "step": 575 }, { "epoch": 0.6452576549663929, "grad_norm": 0.7974233627319336, "learning_rate": 4.899344341176606e-06, "loss": 0.5889, "step": 576 }, { "epoch": 0.6463778939507094, "grad_norm": 0.8065476417541504, "learning_rate": 4.898923850104432e-06, "loss": 0.6, "step": 577 }, { "epoch": 0.6474981329350261, "grad_norm": 0.8313128352165222, "learning_rate": 4.898502500677617e-06, "loss": 0.5973, "step": 578 }, { "epoch": 0.6486183719193428, "grad_norm": 0.8816797733306885, "learning_rate": 4.898080293046923e-06, "loss": 0.5843, "step": 579 }, { "epoch": 0.6497386109036595, "grad_norm": 0.816006600856781, "learning_rate": 4.897657227363419e-06, "loss": 0.6189, "step": 580 }, { "epoch": 0.6508588498879762, "grad_norm": 0.8070967197418213, "learning_rate": 4.897233303778481e-06, "loss": 0.5872, "step": 581 }, { "epoch": 0.6519790888722927, "grad_norm": 0.8039142489433289, "learning_rate": 4.896808522443794e-06, "loss": 0.5747, "step": 582 }, { "epoch": 0.6530993278566094, "grad_norm": 0.8226941227912903, "learning_rate": 4.896382883511347e-06, "loss": 0.5845, "step": 583 }, { "epoch": 0.6542195668409261, "grad_norm": 0.8548035025596619, "learning_rate": 4.895956387133437e-06, "loss": 0.5959, "step": 584 }, { "epoch": 0.6553398058252428, "grad_norm": 0.8523133993148804, "learning_rate": 4.895529033462669e-06, "loss": 0.6107, "step": 585 }, { "epoch": 0.6564600448095593, "grad_norm": 0.8199976086616516, "learning_rate": 4.8951008226519525e-06, "loss": 0.5981, "step": 586 }, { "epoch": 0.657580283793876, "grad_norm": 0.8249738812446594, "learning_rate": 4.894671754854505e-06, "loss": 0.5888, "step": 587 }, { "epoch": 0.6587005227781927, "grad_norm": 0.8519604206085205, "learning_rate": 4.894241830223851e-06, "loss": 0.6223, "step": 588 }, { "epoch": 0.6598207617625094, "grad_norm": 0.8221259713172913, "learning_rate": 4.8938110489138205e-06, "loss": 0.5774, "step": 589 }, { "epoch": 0.6609410007468259, "grad_norm": 0.8143469095230103, "learning_rate": 4.893379411078552e-06, "loss": 0.6049, "step": 590 }, { "epoch": 0.6620612397311426, "grad_norm": 0.7872767448425293, "learning_rate": 4.892946916872486e-06, "loss": 0.5796, "step": 591 }, { "epoch": 0.6631814787154593, "grad_norm": 0.8111532926559448, "learning_rate": 4.8925135664503755e-06, "loss": 0.6041, "step": 592 }, { "epoch": 0.664301717699776, "grad_norm": 0.8038745522499084, "learning_rate": 4.892079359967276e-06, "loss": 0.5929, "step": 593 }, { "epoch": 0.6654219566840927, "grad_norm": 0.8693163990974426, "learning_rate": 4.89164429757855e-06, "loss": 0.5892, "step": 594 }, { "epoch": 0.6665421956684092, "grad_norm": 0.7890527248382568, "learning_rate": 4.891208379439866e-06, "loss": 0.5973, "step": 595 }, { "epoch": 0.6676624346527259, "grad_norm": 0.8141840100288391, "learning_rate": 4.890771605707199e-06, "loss": 0.6031, "step": 596 }, { "epoch": 0.6687826736370426, "grad_norm": 0.8265807032585144, "learning_rate": 4.890333976536831e-06, "loss": 0.5893, "step": 597 }, { "epoch": 0.6699029126213593, "grad_norm": 0.8645585179328918, "learning_rate": 4.8898954920853484e-06, "loss": 0.6189, "step": 598 }, { "epoch": 0.6710231516056758, "grad_norm": 0.8112260699272156, "learning_rate": 4.889456152509646e-06, "loss": 0.589, "step": 599 }, { "epoch": 0.6721433905899925, "grad_norm": 0.8134514093399048, "learning_rate": 4.8890159579669214e-06, "loss": 0.5703, "step": 600 }, { "epoch": 0.6732636295743092, "grad_norm": 0.8513573408126831, "learning_rate": 4.888574908614681e-06, "loss": 0.5971, "step": 601 }, { "epoch": 0.6743838685586259, "grad_norm": 0.8489837646484375, "learning_rate": 4.888133004610735e-06, "loss": 0.6084, "step": 602 }, { "epoch": 0.6755041075429425, "grad_norm": 0.8141038417816162, "learning_rate": 4.887690246113201e-06, "loss": 0.596, "step": 603 }, { "epoch": 0.6766243465272591, "grad_norm": 0.8250095844268799, "learning_rate": 4.887246633280501e-06, "loss": 0.5535, "step": 604 }, { "epoch": 0.6777445855115758, "grad_norm": 0.8543534874916077, "learning_rate": 4.886802166271365e-06, "loss": 0.6056, "step": 605 }, { "epoch": 0.6788648244958925, "grad_norm": 0.8766425848007202, "learning_rate": 4.886356845244824e-06, "loss": 0.5984, "step": 606 }, { "epoch": 0.6799850634802092, "grad_norm": 0.8217388391494751, "learning_rate": 4.88591067036022e-06, "loss": 0.6037, "step": 607 }, { "epoch": 0.6811053024645257, "grad_norm": 0.7816200852394104, "learning_rate": 4.885463641777197e-06, "loss": 0.5451, "step": 608 }, { "epoch": 0.6822255414488424, "grad_norm": 0.8485130071640015, "learning_rate": 4.885015759655706e-06, "loss": 0.5917, "step": 609 }, { "epoch": 0.6833457804331591, "grad_norm": 0.8265321850776672, "learning_rate": 4.884567024156002e-06, "loss": 0.5676, "step": 610 }, { "epoch": 0.6844660194174758, "grad_norm": 0.8090165853500366, "learning_rate": 4.884117435438646e-06, "loss": 0.616, "step": 611 }, { "epoch": 0.6855862584017924, "grad_norm": 0.8049173951148987, "learning_rate": 4.883666993664507e-06, "loss": 0.5814, "step": 612 }, { "epoch": 0.686706497386109, "grad_norm": 0.8055282831192017, "learning_rate": 4.883215698994755e-06, "loss": 0.5947, "step": 613 }, { "epoch": 0.6878267363704257, "grad_norm": 0.8200820088386536, "learning_rate": 4.882763551590865e-06, "loss": 0.6262, "step": 614 }, { "epoch": 0.6889469753547424, "grad_norm": 0.808571994304657, "learning_rate": 4.882310551614623e-06, "loss": 0.6029, "step": 615 }, { "epoch": 0.690067214339059, "grad_norm": 0.8104593753814697, "learning_rate": 4.881856699228114e-06, "loss": 0.5979, "step": 616 }, { "epoch": 0.6911874533233756, "grad_norm": 0.7940874695777893, "learning_rate": 4.88140199459373e-06, "loss": 0.5818, "step": 617 }, { "epoch": 0.6923076923076923, "grad_norm": 0.7887553572654724, "learning_rate": 4.880946437874169e-06, "loss": 0.573, "step": 618 }, { "epoch": 0.693427931292009, "grad_norm": 0.8413677215576172, "learning_rate": 4.880490029232431e-06, "loss": 0.6158, "step": 619 }, { "epoch": 0.6945481702763256, "grad_norm": 0.8174417614936829, "learning_rate": 4.880032768831825e-06, "loss": 0.57, "step": 620 }, { "epoch": 0.6956684092606422, "grad_norm": 0.8150051236152649, "learning_rate": 4.879574656835962e-06, "loss": 0.6071, "step": 621 }, { "epoch": 0.6967886482449589, "grad_norm": 0.8536598682403564, "learning_rate": 4.879115693408757e-06, "loss": 0.6294, "step": 622 }, { "epoch": 0.6979088872292756, "grad_norm": 0.8469665050506592, "learning_rate": 4.8786558787144314e-06, "loss": 0.6146, "step": 623 }, { "epoch": 0.6990291262135923, "grad_norm": 0.7985464930534363, "learning_rate": 4.878195212917511e-06, "loss": 0.5528, "step": 624 }, { "epoch": 0.7001493651979089, "grad_norm": 0.8789647817611694, "learning_rate": 4.877733696182827e-06, "loss": 0.5926, "step": 625 }, { "epoch": 0.7012696041822255, "grad_norm": 0.7992759943008423, "learning_rate": 4.877271328675511e-06, "loss": 0.5912, "step": 626 }, { "epoch": 0.7023898431665422, "grad_norm": 0.7898268699645996, "learning_rate": 4.876808110561004e-06, "loss": 0.5722, "step": 627 }, { "epoch": 0.7035100821508589, "grad_norm": 0.8306590914726257, "learning_rate": 4.87634404200505e-06, "loss": 0.627, "step": 628 }, { "epoch": 0.7046303211351755, "grad_norm": 0.8404473662376404, "learning_rate": 4.875879123173694e-06, "loss": 0.5841, "step": 629 }, { "epoch": 0.7057505601194921, "grad_norm": 0.8321950435638428, "learning_rate": 4.87541335423329e-06, "loss": 0.6141, "step": 630 }, { "epoch": 0.7068707991038088, "grad_norm": 0.7946979403495789, "learning_rate": 4.874946735350492e-06, "loss": 0.5849, "step": 631 }, { "epoch": 0.7079910380881255, "grad_norm": 0.8189645409584045, "learning_rate": 4.874479266692261e-06, "loss": 0.6146, "step": 632 }, { "epoch": 0.7091112770724421, "grad_norm": 0.8169258832931519, "learning_rate": 4.8740109484258625e-06, "loss": 0.5926, "step": 633 }, { "epoch": 0.7102315160567588, "grad_norm": 0.7945389151573181, "learning_rate": 4.873541780718863e-06, "loss": 0.5929, "step": 634 }, { "epoch": 0.7113517550410754, "grad_norm": 0.7935434579849243, "learning_rate": 4.873071763739135e-06, "loss": 0.5942, "step": 635 }, { "epoch": 0.7124719940253921, "grad_norm": 0.8001875877380371, "learning_rate": 4.872600897654853e-06, "loss": 0.5957, "step": 636 }, { "epoch": 0.7135922330097088, "grad_norm": 0.8338243961334229, "learning_rate": 4.872129182634499e-06, "loss": 0.5908, "step": 637 }, { "epoch": 0.7147124719940254, "grad_norm": 0.8988234400749207, "learning_rate": 4.871656618846855e-06, "loss": 0.5955, "step": 638 }, { "epoch": 0.715832710978342, "grad_norm": 0.7992603778839111, "learning_rate": 4.87118320646101e-06, "loss": 0.5852, "step": 639 }, { "epoch": 0.7169529499626587, "grad_norm": 0.8259397745132446, "learning_rate": 4.870708945646353e-06, "loss": 0.6156, "step": 640 }, { "epoch": 0.7180731889469754, "grad_norm": 0.893584132194519, "learning_rate": 4.870233836572579e-06, "loss": 0.6117, "step": 641 }, { "epoch": 0.719193427931292, "grad_norm": 0.8482956290245056, "learning_rate": 4.869757879409686e-06, "loss": 0.6018, "step": 642 }, { "epoch": 0.7203136669156086, "grad_norm": 0.7782022356987, "learning_rate": 4.869281074327975e-06, "loss": 0.5761, "step": 643 }, { "epoch": 0.7214339058999253, "grad_norm": 0.8154391050338745, "learning_rate": 4.8688034214980515e-06, "loss": 0.5846, "step": 644 }, { "epoch": 0.722554144884242, "grad_norm": 0.8113802671432495, "learning_rate": 4.868324921090822e-06, "loss": 0.5616, "step": 645 }, { "epoch": 0.7236743838685586, "grad_norm": 0.830033540725708, "learning_rate": 4.867845573277501e-06, "loss": 0.63, "step": 646 }, { "epoch": 0.7247946228528753, "grad_norm": 0.8050087690353394, "learning_rate": 4.867365378229601e-06, "loss": 0.5894, "step": 647 }, { "epoch": 0.7259148618371919, "grad_norm": 0.8076449036598206, "learning_rate": 4.8668843361189385e-06, "loss": 0.6145, "step": 648 }, { "epoch": 0.7270351008215086, "grad_norm": 0.8889169692993164, "learning_rate": 4.8664024471176366e-06, "loss": 0.6154, "step": 649 }, { "epoch": 0.7281553398058253, "grad_norm": 0.8604964017868042, "learning_rate": 4.865919711398118e-06, "loss": 0.5984, "step": 650 }, { "epoch": 0.7292755787901419, "grad_norm": 0.828212320804596, "learning_rate": 4.86543612913311e-06, "loss": 0.5785, "step": 651 }, { "epoch": 0.7303958177744585, "grad_norm": 0.786229133605957, "learning_rate": 4.864951700495642e-06, "loss": 0.5983, "step": 652 }, { "epoch": 0.7315160567587752, "grad_norm": 0.8467420935630798, "learning_rate": 4.864466425659046e-06, "loss": 0.6037, "step": 653 }, { "epoch": 0.7326362957430919, "grad_norm": 0.7861534953117371, "learning_rate": 4.863980304796958e-06, "loss": 0.564, "step": 654 }, { "epoch": 0.7337565347274085, "grad_norm": 0.7819376587867737, "learning_rate": 4.863493338083316e-06, "loss": 0.5783, "step": 655 }, { "epoch": 0.7348767737117252, "grad_norm": 0.7864521741867065, "learning_rate": 4.863005525692362e-06, "loss": 0.594, "step": 656 }, { "epoch": 0.7359970126960418, "grad_norm": 0.7910285592079163, "learning_rate": 4.862516867798636e-06, "loss": 0.5888, "step": 657 }, { "epoch": 0.7371172516803585, "grad_norm": 0.8056003451347351, "learning_rate": 4.862027364576987e-06, "loss": 0.5895, "step": 658 }, { "epoch": 0.7382374906646751, "grad_norm": 0.8140441179275513, "learning_rate": 4.861537016202561e-06, "loss": 0.6015, "step": 659 }, { "epoch": 0.7393577296489918, "grad_norm": 0.8237465620040894, "learning_rate": 4.861045822850811e-06, "loss": 0.6072, "step": 660 }, { "epoch": 0.7404779686333084, "grad_norm": 0.832146942615509, "learning_rate": 4.860553784697487e-06, "loss": 0.6171, "step": 661 }, { "epoch": 0.7415982076176251, "grad_norm": 0.8073914051055908, "learning_rate": 4.860060901918648e-06, "loss": 0.5931, "step": 662 }, { "epoch": 0.7427184466019418, "grad_norm": 0.8193264007568359, "learning_rate": 4.859567174690647e-06, "loss": 0.5948, "step": 663 }, { "epoch": 0.7438386855862584, "grad_norm": 0.8580235838890076, "learning_rate": 4.859072603190148e-06, "loss": 0.6157, "step": 664 }, { "epoch": 0.7449589245705751, "grad_norm": 0.7729256749153137, "learning_rate": 4.8585771875941105e-06, "loss": 0.5876, "step": 665 }, { "epoch": 0.7460791635548917, "grad_norm": 0.844573438167572, "learning_rate": 4.858080928079798e-06, "loss": 0.6206, "step": 666 }, { "epoch": 0.7471994025392084, "grad_norm": 0.816228449344635, "learning_rate": 4.857583824824777e-06, "loss": 0.6247, "step": 667 }, { "epoch": 0.748319641523525, "grad_norm": 0.7984215021133423, "learning_rate": 4.8570858780069155e-06, "loss": 0.6038, "step": 668 }, { "epoch": 0.7494398805078417, "grad_norm": 0.850842297077179, "learning_rate": 4.856587087804382e-06, "loss": 0.6283, "step": 669 }, { "epoch": 0.7505601194921583, "grad_norm": 0.7965848445892334, "learning_rate": 4.856087454395648e-06, "loss": 0.6018, "step": 670 }, { "epoch": 0.751680358476475, "grad_norm": 0.7891208529472351, "learning_rate": 4.855586977959487e-06, "loss": 0.5965, "step": 671 }, { "epoch": 0.7528005974607916, "grad_norm": 0.7875372767448425, "learning_rate": 4.855085658674973e-06, "loss": 0.6004, "step": 672 }, { "epoch": 0.7539208364451083, "grad_norm": 0.7898383736610413, "learning_rate": 4.854583496721482e-06, "loss": 0.5566, "step": 673 }, { "epoch": 0.7550410754294249, "grad_norm": 0.8215773701667786, "learning_rate": 4.854080492278693e-06, "loss": 0.5837, "step": 674 }, { "epoch": 0.7561613144137416, "grad_norm": 0.810920000076294, "learning_rate": 4.853576645526584e-06, "loss": 0.5893, "step": 675 }, { "epoch": 0.7572815533980582, "grad_norm": 0.7786296606063843, "learning_rate": 4.8530719566454345e-06, "loss": 0.5604, "step": 676 }, { "epoch": 0.7584017923823749, "grad_norm": 0.7917574048042297, "learning_rate": 4.852566425815829e-06, "loss": 0.582, "step": 677 }, { "epoch": 0.7595220313666916, "grad_norm": 0.8070117235183716, "learning_rate": 4.8520600532186475e-06, "loss": 0.604, "step": 678 }, { "epoch": 0.7606422703510082, "grad_norm": 0.8068091869354248, "learning_rate": 4.8515528390350765e-06, "loss": 0.5896, "step": 679 }, { "epoch": 0.7617625093353249, "grad_norm": 0.8220896124839783, "learning_rate": 4.8510447834466e-06, "loss": 0.593, "step": 680 }, { "epoch": 0.7628827483196415, "grad_norm": 0.7868808507919312, "learning_rate": 4.850535886635006e-06, "loss": 0.6, "step": 681 }, { "epoch": 0.7640029873039582, "grad_norm": 0.8102167248725891, "learning_rate": 4.850026148782381e-06, "loss": 0.5813, "step": 682 }, { "epoch": 0.7651232262882748, "grad_norm": 0.8151317834854126, "learning_rate": 4.849515570071113e-06, "loss": 0.5747, "step": 683 }, { "epoch": 0.7662434652725915, "grad_norm": 0.8038537502288818, "learning_rate": 4.849004150683892e-06, "loss": 0.6192, "step": 684 }, { "epoch": 0.7673637042569081, "grad_norm": 0.8006526827812195, "learning_rate": 4.848491890803708e-06, "loss": 0.5866, "step": 685 }, { "epoch": 0.7684839432412248, "grad_norm": 0.7970767617225647, "learning_rate": 4.847978790613851e-06, "loss": 0.6098, "step": 686 }, { "epoch": 0.7696041822255415, "grad_norm": 0.7953868508338928, "learning_rate": 4.847464850297914e-06, "loss": 0.5758, "step": 687 }, { "epoch": 0.7707244212098581, "grad_norm": 0.8159863352775574, "learning_rate": 4.8469500700397875e-06, "loss": 0.5949, "step": 688 }, { "epoch": 0.7718446601941747, "grad_norm": 0.7919224500656128, "learning_rate": 4.8464344500236645e-06, "loss": 0.5769, "step": 689 }, { "epoch": 0.7729648991784914, "grad_norm": 0.7827619314193726, "learning_rate": 4.845917990434039e-06, "loss": 0.5923, "step": 690 }, { "epoch": 0.7740851381628081, "grad_norm": 0.7937460541725159, "learning_rate": 4.845400691455703e-06, "loss": 0.5759, "step": 691 }, { "epoch": 0.7752053771471247, "grad_norm": 0.7901214361190796, "learning_rate": 4.844882553273752e-06, "loss": 0.5657, "step": 692 }, { "epoch": 0.7763256161314414, "grad_norm": 0.8160180449485779, "learning_rate": 4.844363576073579e-06, "loss": 0.5971, "step": 693 }, { "epoch": 0.777445855115758, "grad_norm": 0.8019487261772156, "learning_rate": 4.843843760040877e-06, "loss": 0.5804, "step": 694 }, { "epoch": 0.7785660941000747, "grad_norm": 0.7898805141448975, "learning_rate": 4.843323105361643e-06, "loss": 0.5854, "step": 695 }, { "epoch": 0.7796863330843914, "grad_norm": 0.829105794429779, "learning_rate": 4.842801612222171e-06, "loss": 0.5914, "step": 696 }, { "epoch": 0.780806572068708, "grad_norm": 0.7974743843078613, "learning_rate": 4.842279280809054e-06, "loss": 0.5856, "step": 697 }, { "epoch": 0.7819268110530246, "grad_norm": 0.7757387161254883, "learning_rate": 4.841756111309188e-06, "loss": 0.5679, "step": 698 }, { "epoch": 0.7830470500373413, "grad_norm": 0.827438473701477, "learning_rate": 4.841232103909766e-06, "loss": 0.5657, "step": 699 }, { "epoch": 0.784167289021658, "grad_norm": 0.8150497078895569, "learning_rate": 4.840707258798284e-06, "loss": 0.6065, "step": 700 }, { "epoch": 0.7852875280059746, "grad_norm": 0.7733539342880249, "learning_rate": 4.8401815761625345e-06, "loss": 0.5806, "step": 701 }, { "epoch": 0.7864077669902912, "grad_norm": 0.8224393129348755, "learning_rate": 4.839655056190611e-06, "loss": 0.5723, "step": 702 }, { "epoch": 0.7875280059746079, "grad_norm": 0.8295096755027771, "learning_rate": 4.839127699070907e-06, "loss": 0.609, "step": 703 }, { "epoch": 0.7886482449589246, "grad_norm": 0.7875826358795166, "learning_rate": 4.838599504992116e-06, "loss": 0.5625, "step": 704 }, { "epoch": 0.7897684839432412, "grad_norm": 0.8078942894935608, "learning_rate": 4.838070474143228e-06, "loss": 0.6059, "step": 705 }, { "epoch": 0.7908887229275579, "grad_norm": 0.8128692507743835, "learning_rate": 4.837540606713538e-06, "loss": 0.5878, "step": 706 }, { "epoch": 0.7920089619118745, "grad_norm": 0.7869188785552979, "learning_rate": 4.837009902892633e-06, "loss": 0.5741, "step": 707 }, { "epoch": 0.7931292008961912, "grad_norm": 0.7958232164382935, "learning_rate": 4.836478362870406e-06, "loss": 0.5879, "step": 708 }, { "epoch": 0.7942494398805079, "grad_norm": 0.7908474802970886, "learning_rate": 4.835945986837045e-06, "loss": 0.5766, "step": 709 }, { "epoch": 0.7953696788648245, "grad_norm": 0.8136919736862183, "learning_rate": 4.83541277498304e-06, "loss": 0.587, "step": 710 }, { "epoch": 0.7964899178491411, "grad_norm": 0.8330440521240234, "learning_rate": 4.8348787274991765e-06, "loss": 0.5935, "step": 711 }, { "epoch": 0.7976101568334578, "grad_norm": 0.8112781643867493, "learning_rate": 4.834343844576543e-06, "loss": 0.5952, "step": 712 }, { "epoch": 0.7987303958177745, "grad_norm": 0.8082567453384399, "learning_rate": 4.8338081264065235e-06, "loss": 0.5717, "step": 713 }, { "epoch": 0.7998506348020911, "grad_norm": 0.9035626649856567, "learning_rate": 4.8332715731808035e-06, "loss": 0.583, "step": 714 }, { "epoch": 0.8009708737864077, "grad_norm": 0.8441537022590637, "learning_rate": 4.8327341850913645e-06, "loss": 0.6096, "step": 715 }, { "epoch": 0.8020911127707244, "grad_norm": 0.8210310339927673, "learning_rate": 4.832195962330491e-06, "loss": 0.6072, "step": 716 }, { "epoch": 0.8032113517550411, "grad_norm": 0.8119834065437317, "learning_rate": 4.831656905090761e-06, "loss": 0.5864, "step": 717 }, { "epoch": 0.8043315907393578, "grad_norm": 0.8333593606948853, "learning_rate": 4.831117013565056e-06, "loss": 0.6003, "step": 718 }, { "epoch": 0.8054518297236744, "grad_norm": 0.8569757342338562, "learning_rate": 4.83057628794655e-06, "loss": 0.5936, "step": 719 }, { "epoch": 0.806572068707991, "grad_norm": 0.7970093488693237, "learning_rate": 4.830034728428723e-06, "loss": 0.5776, "step": 720 }, { "epoch": 0.8076923076923077, "grad_norm": 0.8280375003814697, "learning_rate": 4.829492335205347e-06, "loss": 0.5952, "step": 721 }, { "epoch": 0.8088125466766244, "grad_norm": 0.8139337301254272, "learning_rate": 4.828949108470496e-06, "loss": 0.6314, "step": 722 }, { "epoch": 0.809932785660941, "grad_norm": 0.8315449357032776, "learning_rate": 4.82840504841854e-06, "loss": 0.5978, "step": 723 }, { "epoch": 0.8110530246452576, "grad_norm": 0.8375460505485535, "learning_rate": 4.827860155244149e-06, "loss": 0.588, "step": 724 }, { "epoch": 0.8121732636295743, "grad_norm": 0.7952830791473389, "learning_rate": 4.827314429142291e-06, "loss": 0.582, "step": 725 }, { "epoch": 0.813293502613891, "grad_norm": 0.8073609471321106, "learning_rate": 4.826767870308228e-06, "loss": 0.5678, "step": 726 }, { "epoch": 0.8144137415982076, "grad_norm": 0.8218507766723633, "learning_rate": 4.826220478937527e-06, "loss": 0.6072, "step": 727 }, { "epoch": 0.8155339805825242, "grad_norm": 0.7980933785438538, "learning_rate": 4.825672255226047e-06, "loss": 0.5524, "step": 728 }, { "epoch": 0.8166542195668409, "grad_norm": 0.8054032921791077, "learning_rate": 4.825123199369947e-06, "loss": 0.5913, "step": 729 }, { "epoch": 0.8177744585511576, "grad_norm": 0.8572160601615906, "learning_rate": 4.824573311565685e-06, "loss": 0.5954, "step": 730 }, { "epoch": 0.8188946975354743, "grad_norm": 0.8065678477287292, "learning_rate": 4.824022592010013e-06, "loss": 0.5966, "step": 731 }, { "epoch": 0.8200149365197908, "grad_norm": 0.812080442905426, "learning_rate": 4.8234710408999865e-06, "loss": 0.5666, "step": 732 }, { "epoch": 0.8211351755041075, "grad_norm": 0.8508359789848328, "learning_rate": 4.822918658432952e-06, "loss": 0.6137, "step": 733 }, { "epoch": 0.8222554144884242, "grad_norm": 0.7996507287025452, "learning_rate": 4.8223654448065585e-06, "loss": 0.6038, "step": 734 }, { "epoch": 0.8233756534727409, "grad_norm": 0.8098906874656677, "learning_rate": 4.821811400218748e-06, "loss": 0.5759, "step": 735 }, { "epoch": 0.8244958924570575, "grad_norm": 0.8356794118881226, "learning_rate": 4.821256524867764e-06, "loss": 0.6151, "step": 736 }, { "epoch": 0.8256161314413741, "grad_norm": 0.8081963658332825, "learning_rate": 4.820700818952145e-06, "loss": 0.5943, "step": 737 }, { "epoch": 0.8267363704256908, "grad_norm": 0.825581967830658, "learning_rate": 4.820144282670728e-06, "loss": 0.5769, "step": 738 }, { "epoch": 0.8278566094100075, "grad_norm": 0.8103387355804443, "learning_rate": 4.819586916222644e-06, "loss": 0.5789, "step": 739 }, { "epoch": 0.8289768483943242, "grad_norm": 0.8200883865356445, "learning_rate": 4.819028719807326e-06, "loss": 0.602, "step": 740 }, { "epoch": 0.8300970873786407, "grad_norm": 0.8113400340080261, "learning_rate": 4.818469693624499e-06, "loss": 0.5951, "step": 741 }, { "epoch": 0.8312173263629574, "grad_norm": 0.8407019972801208, "learning_rate": 4.817909837874189e-06, "loss": 0.5909, "step": 742 }, { "epoch": 0.8323375653472741, "grad_norm": 0.8122291564941406, "learning_rate": 4.8173491527567155e-06, "loss": 0.5964, "step": 743 }, { "epoch": 0.8334578043315908, "grad_norm": 0.8028641939163208, "learning_rate": 4.816787638472697e-06, "loss": 0.5926, "step": 744 }, { "epoch": 0.8345780433159073, "grad_norm": 0.8061012625694275, "learning_rate": 4.816225295223048e-06, "loss": 0.5835, "step": 745 }, { "epoch": 0.835698282300224, "grad_norm": 0.8372674584388733, "learning_rate": 4.815662123208979e-06, "loss": 0.6048, "step": 746 }, { "epoch": 0.8368185212845407, "grad_norm": 0.7943447828292847, "learning_rate": 4.815098122631998e-06, "loss": 0.5999, "step": 747 }, { "epoch": 0.8379387602688574, "grad_norm": 0.7981782555580139, "learning_rate": 4.814533293693909e-06, "loss": 0.5838, "step": 748 }, { "epoch": 0.8390589992531741, "grad_norm": 0.8036529421806335, "learning_rate": 4.8139676365968125e-06, "loss": 0.59, "step": 749 }, { "epoch": 0.8401792382374906, "grad_norm": 0.8037401437759399, "learning_rate": 4.813401151543105e-06, "loss": 0.5603, "step": 750 }, { "epoch": 0.8412994772218073, "grad_norm": 0.8377910852432251, "learning_rate": 4.812833838735479e-06, "loss": 0.5984, "step": 751 }, { "epoch": 0.842419716206124, "grad_norm": 0.7984040975570679, "learning_rate": 4.812265698376924e-06, "loss": 0.5719, "step": 752 }, { "epoch": 0.8435399551904407, "grad_norm": 0.8077371716499329, "learning_rate": 4.811696730670726e-06, "loss": 0.5824, "step": 753 }, { "epoch": 0.8446601941747572, "grad_norm": 0.7634063959121704, "learning_rate": 4.811126935820466e-06, "loss": 0.5584, "step": 754 }, { "epoch": 0.8457804331590739, "grad_norm": 0.8120932579040527, "learning_rate": 4.810556314030021e-06, "loss": 0.5729, "step": 755 }, { "epoch": 0.8469006721433906, "grad_norm": 0.7915536165237427, "learning_rate": 4.8099848655035655e-06, "loss": 0.6039, "step": 756 }, { "epoch": 0.8480209111277073, "grad_norm": 0.8074361085891724, "learning_rate": 4.809412590445566e-06, "loss": 0.5888, "step": 757 }, { "epoch": 0.8491411501120238, "grad_norm": 0.8198902010917664, "learning_rate": 4.808839489060788e-06, "loss": 0.5895, "step": 758 }, { "epoch": 0.8502613890963405, "grad_norm": 0.8113036751747131, "learning_rate": 4.808265561554293e-06, "loss": 0.5938, "step": 759 }, { "epoch": 0.8513816280806572, "grad_norm": 0.7734106183052063, "learning_rate": 4.807690808131437e-06, "loss": 0.5981, "step": 760 }, { "epoch": 0.8525018670649739, "grad_norm": 0.7905157208442688, "learning_rate": 4.80711522899787e-06, "loss": 0.5862, "step": 761 }, { "epoch": 0.8536221060492906, "grad_norm": 0.7930572628974915, "learning_rate": 4.80653882435954e-06, "loss": 0.6078, "step": 762 }, { "epoch": 0.8547423450336071, "grad_norm": 0.7793716788291931, "learning_rate": 4.8059615944226885e-06, "loss": 0.6005, "step": 763 }, { "epoch": 0.8558625840179238, "grad_norm": 0.7978621125221252, "learning_rate": 4.8053835393938545e-06, "loss": 0.5989, "step": 764 }, { "epoch": 0.8569828230022405, "grad_norm": 0.8089454770088196, "learning_rate": 4.804804659479869e-06, "loss": 0.5576, "step": 765 }, { "epoch": 0.8581030619865572, "grad_norm": 0.7966460585594177, "learning_rate": 4.804224954887862e-06, "loss": 0.5777, "step": 766 }, { "epoch": 0.8592233009708737, "grad_norm": 0.8103785514831543, "learning_rate": 4.8036444258252555e-06, "loss": 0.5965, "step": 767 }, { "epoch": 0.8603435399551904, "grad_norm": 0.8107985854148865, "learning_rate": 4.803063072499768e-06, "loss": 0.5909, "step": 768 }, { "epoch": 0.8614637789395071, "grad_norm": 0.8095008730888367, "learning_rate": 4.8024808951194105e-06, "loss": 0.565, "step": 769 }, { "epoch": 0.8625840179238238, "grad_norm": 0.8257828950881958, "learning_rate": 4.801897893892493e-06, "loss": 0.5825, "step": 770 }, { "epoch": 0.8637042569081405, "grad_norm": 0.8019899725914001, "learning_rate": 4.8013140690276186e-06, "loss": 0.5806, "step": 771 }, { "epoch": 0.864824495892457, "grad_norm": 0.809320330619812, "learning_rate": 4.800729420733683e-06, "loss": 0.5778, "step": 772 }, { "epoch": 0.8659447348767737, "grad_norm": 0.8071535229682922, "learning_rate": 4.800143949219879e-06, "loss": 0.5702, "step": 773 }, { "epoch": 0.8670649738610904, "grad_norm": 0.8018308281898499, "learning_rate": 4.799557654695692e-06, "loss": 0.6004, "step": 774 }, { "epoch": 0.8681852128454071, "grad_norm": 0.8141055107116699, "learning_rate": 4.798970537370904e-06, "loss": 0.57, "step": 775 }, { "epoch": 0.8693054518297236, "grad_norm": 0.7862063050270081, "learning_rate": 4.798382597455591e-06, "loss": 0.5528, "step": 776 }, { "epoch": 0.8704256908140403, "grad_norm": 0.8331758975982666, "learning_rate": 4.797793835160122e-06, "loss": 0.6008, "step": 777 }, { "epoch": 0.871545929798357, "grad_norm": 0.823685884475708, "learning_rate": 4.797204250695161e-06, "loss": 0.6154, "step": 778 }, { "epoch": 0.8726661687826737, "grad_norm": 0.7857784032821655, "learning_rate": 4.796613844271665e-06, "loss": 0.5994, "step": 779 }, { "epoch": 0.8737864077669902, "grad_norm": 0.8060506582260132, "learning_rate": 4.796022616100889e-06, "loss": 0.5633, "step": 780 }, { "epoch": 0.8749066467513069, "grad_norm": 0.8090853095054626, "learning_rate": 4.795430566394377e-06, "loss": 0.5573, "step": 781 }, { "epoch": 0.8760268857356236, "grad_norm": 0.8793733716011047, "learning_rate": 4.7948376953639695e-06, "loss": 0.619, "step": 782 }, { "epoch": 0.8771471247199403, "grad_norm": 0.8061932921409607, "learning_rate": 4.794244003221801e-06, "loss": 0.6047, "step": 783 }, { "epoch": 0.878267363704257, "grad_norm": 0.8307778239250183, "learning_rate": 4.7936494901803e-06, "loss": 0.5825, "step": 784 }, { "epoch": 0.8793876026885735, "grad_norm": 0.8569943308830261, "learning_rate": 4.793054156452187e-06, "loss": 0.5754, "step": 785 }, { "epoch": 0.8805078416728902, "grad_norm": 0.793869137763977, "learning_rate": 4.792458002250479e-06, "loss": 0.5864, "step": 786 }, { "epoch": 0.8816280806572069, "grad_norm": 0.796796977519989, "learning_rate": 4.791861027788483e-06, "loss": 0.5988, "step": 787 }, { "epoch": 0.8827483196415236, "grad_norm": 0.8137564063072205, "learning_rate": 4.791263233279802e-06, "loss": 0.5768, "step": 788 }, { "epoch": 0.8838685586258401, "grad_norm": 0.7946325540542603, "learning_rate": 4.790664618938332e-06, "loss": 0.5674, "step": 789 }, { "epoch": 0.8849887976101568, "grad_norm": 0.8001543283462524, "learning_rate": 4.790065184978263e-06, "loss": 0.5705, "step": 790 }, { "epoch": 0.8861090365944735, "grad_norm": 0.8289190530776978, "learning_rate": 4.789464931614075e-06, "loss": 0.6023, "step": 791 }, { "epoch": 0.8872292755787902, "grad_norm": 0.8041342496871948, "learning_rate": 4.788863859060546e-06, "loss": 0.5963, "step": 792 }, { "epoch": 0.8883495145631068, "grad_norm": 0.8325103521347046, "learning_rate": 4.788261967532743e-06, "loss": 0.6005, "step": 793 }, { "epoch": 0.8894697535474234, "grad_norm": 0.7777535319328308, "learning_rate": 4.787659257246029e-06, "loss": 0.5701, "step": 794 }, { "epoch": 0.8905899925317401, "grad_norm": 0.8024612069129944, "learning_rate": 4.787055728416058e-06, "loss": 0.593, "step": 795 }, { "epoch": 0.8917102315160568, "grad_norm": 0.7804939150810242, "learning_rate": 4.786451381258777e-06, "loss": 0.5547, "step": 796 }, { "epoch": 0.8928304705003735, "grad_norm": 0.8120240569114685, "learning_rate": 4.7858462159904284e-06, "loss": 0.5955, "step": 797 }, { "epoch": 0.89395070948469, "grad_norm": 0.7861335873603821, "learning_rate": 4.785240232827543e-06, "loss": 0.5769, "step": 798 }, { "epoch": 0.8950709484690067, "grad_norm": 0.7677375674247742, "learning_rate": 4.784633431986948e-06, "loss": 0.572, "step": 799 }, { "epoch": 0.8961911874533234, "grad_norm": 0.8227370381355286, "learning_rate": 4.784025813685761e-06, "loss": 0.5968, "step": 800 }, { "epoch": 0.8973114264376401, "grad_norm": 0.8148797750473022, "learning_rate": 4.783417378141393e-06, "loss": 0.587, "step": 801 }, { "epoch": 0.8984316654219567, "grad_norm": 0.8100507855415344, "learning_rate": 4.782808125571547e-06, "loss": 0.581, "step": 802 }, { "epoch": 0.8995519044062733, "grad_norm": 0.8154464960098267, "learning_rate": 4.782198056194219e-06, "loss": 0.5932, "step": 803 }, { "epoch": 0.90067214339059, "grad_norm": 0.7960717678070068, "learning_rate": 4.781587170227698e-06, "loss": 0.568, "step": 804 }, { "epoch": 0.9017923823749067, "grad_norm": 0.7840545177459717, "learning_rate": 4.780975467890561e-06, "loss": 0.5709, "step": 805 }, { "epoch": 0.9029126213592233, "grad_norm": 0.7957537174224854, "learning_rate": 4.780362949401683e-06, "loss": 0.5946, "step": 806 }, { "epoch": 0.9040328603435399, "grad_norm": 0.8008480668067932, "learning_rate": 4.779749614980225e-06, "loss": 0.6082, "step": 807 }, { "epoch": 0.9051530993278566, "grad_norm": 0.8121342062950134, "learning_rate": 4.779135464845647e-06, "loss": 0.5799, "step": 808 }, { "epoch": 0.9062733383121733, "grad_norm": 0.7985235452651978, "learning_rate": 4.778520499217694e-06, "loss": 0.6025, "step": 809 }, { "epoch": 0.90739357729649, "grad_norm": 0.7896565198898315, "learning_rate": 4.7779047183164075e-06, "loss": 0.5954, "step": 810 }, { "epoch": 0.9085138162808065, "grad_norm": 0.807032585144043, "learning_rate": 4.7772881223621175e-06, "loss": 0.6022, "step": 811 }, { "epoch": 0.9096340552651232, "grad_norm": 0.8102108836174011, "learning_rate": 4.7766707115754485e-06, "loss": 0.5775, "step": 812 }, { "epoch": 0.9107542942494399, "grad_norm": 0.8097600340843201, "learning_rate": 4.776052486177314e-06, "loss": 0.5877, "step": 813 }, { "epoch": 0.9118745332337566, "grad_norm": 0.7986764907836914, "learning_rate": 4.775433446388921e-06, "loss": 0.5625, "step": 814 }, { "epoch": 0.9129947722180732, "grad_norm": 0.8128889203071594, "learning_rate": 4.7748135924317655e-06, "loss": 0.6031, "step": 815 }, { "epoch": 0.9141150112023898, "grad_norm": 0.7872529029846191, "learning_rate": 4.774192924527638e-06, "loss": 0.5624, "step": 816 }, { "epoch": 0.9152352501867065, "grad_norm": 0.8138707280158997, "learning_rate": 4.773571442898618e-06, "loss": 0.5848, "step": 817 }, { "epoch": 0.9163554891710232, "grad_norm": 0.8301820158958435, "learning_rate": 4.772949147767077e-06, "loss": 0.6031, "step": 818 }, { "epoch": 0.9174757281553398, "grad_norm": 0.8014585971832275, "learning_rate": 4.772326039355677e-06, "loss": 0.5575, "step": 819 }, { "epoch": 0.9185959671396564, "grad_norm": 0.8259865641593933, "learning_rate": 4.771702117887371e-06, "loss": 0.596, "step": 820 }, { "epoch": 0.9197162061239731, "grad_norm": 0.8028122782707214, "learning_rate": 4.771077383585404e-06, "loss": 0.5851, "step": 821 }, { "epoch": 0.9208364451082898, "grad_norm": 0.7960208058357239, "learning_rate": 4.7704518366733095e-06, "loss": 0.5999, "step": 822 }, { "epoch": 0.9219566840926064, "grad_norm": 0.797467827796936, "learning_rate": 4.769825477374915e-06, "loss": 0.5809, "step": 823 }, { "epoch": 0.9230769230769231, "grad_norm": 0.8268144130706787, "learning_rate": 4.7691983059143374e-06, "loss": 0.5821, "step": 824 }, { "epoch": 0.9241971620612397, "grad_norm": 0.803213357925415, "learning_rate": 4.768570322515982e-06, "loss": 0.5606, "step": 825 }, { "epoch": 0.9253174010455564, "grad_norm": 0.8422443866729736, "learning_rate": 4.767941527404547e-06, "loss": 0.5813, "step": 826 }, { "epoch": 0.926437640029873, "grad_norm": 0.7983731031417847, "learning_rate": 4.767311920805021e-06, "loss": 0.5747, "step": 827 }, { "epoch": 0.9275578790141897, "grad_norm": 0.827704906463623, "learning_rate": 4.766681502942681e-06, "loss": 0.5587, "step": 828 }, { "epoch": 0.9286781179985063, "grad_norm": 0.832988977432251, "learning_rate": 4.7660502740430985e-06, "loss": 0.572, "step": 829 }, { "epoch": 0.929798356982823, "grad_norm": 0.8249674439430237, "learning_rate": 4.76541823433213e-06, "loss": 0.5801, "step": 830 }, { "epoch": 0.9309185959671397, "grad_norm": 0.8318766355514526, "learning_rate": 4.764785384035925e-06, "loss": 0.5793, "step": 831 }, { "epoch": 0.9320388349514563, "grad_norm": 0.8395798206329346, "learning_rate": 4.764151723380923e-06, "loss": 0.587, "step": 832 }, { "epoch": 0.933159073935773, "grad_norm": 0.8279564380645752, "learning_rate": 4.763517252593852e-06, "loss": 0.597, "step": 833 }, { "epoch": 0.9342793129200896, "grad_norm": 0.856611967086792, "learning_rate": 4.762881971901732e-06, "loss": 0.5488, "step": 834 }, { "epoch": 0.9353995519044063, "grad_norm": 0.8096729516983032, "learning_rate": 4.762245881531872e-06, "loss": 0.577, "step": 835 }, { "epoch": 0.936519790888723, "grad_norm": 0.8170201778411865, "learning_rate": 4.761608981711868e-06, "loss": 0.5602, "step": 836 }, { "epoch": 0.9376400298730396, "grad_norm": 0.8169147968292236, "learning_rate": 4.76097127266961e-06, "loss": 0.5974, "step": 837 }, { "epoch": 0.9387602688573562, "grad_norm": 0.806937038898468, "learning_rate": 4.760332754633276e-06, "loss": 0.5795, "step": 838 }, { "epoch": 0.9398805078416729, "grad_norm": 0.8193455934524536, "learning_rate": 4.759693427831331e-06, "loss": 0.5886, "step": 839 }, { "epoch": 0.9410007468259896, "grad_norm": 0.8178059458732605, "learning_rate": 4.759053292492532e-06, "loss": 0.5951, "step": 840 }, { "epoch": 0.9421209858103062, "grad_norm": 0.8102588057518005, "learning_rate": 4.758412348845925e-06, "loss": 0.5724, "step": 841 }, { "epoch": 0.9432412247946228, "grad_norm": 0.8178951144218445, "learning_rate": 4.7577705971208466e-06, "loss": 0.5849, "step": 842 }, { "epoch": 0.9443614637789395, "grad_norm": 0.8069207668304443, "learning_rate": 4.757128037546918e-06, "loss": 0.5978, "step": 843 }, { "epoch": 0.9454817027632562, "grad_norm": 0.8033669590950012, "learning_rate": 4.756484670354054e-06, "loss": 0.5794, "step": 844 }, { "epoch": 0.9466019417475728, "grad_norm": 0.8094858527183533, "learning_rate": 4.755840495772455e-06, "loss": 0.6082, "step": 845 }, { "epoch": 0.9477221807318895, "grad_norm": 0.8048908114433289, "learning_rate": 4.755195514032614e-06, "loss": 0.5644, "step": 846 }, { "epoch": 0.9488424197162061, "grad_norm": 0.8288162350654602, "learning_rate": 4.754549725365311e-06, "loss": 0.5665, "step": 847 }, { "epoch": 0.9499626587005228, "grad_norm": 0.8059208989143372, "learning_rate": 4.753903130001612e-06, "loss": 0.6111, "step": 848 }, { "epoch": 0.9510828976848394, "grad_norm": 0.7926841974258423, "learning_rate": 4.753255728172875e-06, "loss": 0.5632, "step": 849 }, { "epoch": 0.9522031366691561, "grad_norm": 0.8072546720504761, "learning_rate": 4.752607520110748e-06, "loss": 0.5953, "step": 850 }, { "epoch": 0.9533233756534727, "grad_norm": 0.8185967803001404, "learning_rate": 4.7519585060471616e-06, "loss": 0.6158, "step": 851 }, { "epoch": 0.9544436146377894, "grad_norm": 0.8182018399238586, "learning_rate": 4.751308686214341e-06, "loss": 0.586, "step": 852 }, { "epoch": 0.955563853622106, "grad_norm": 0.8257445693016052, "learning_rate": 4.750658060844796e-06, "loss": 0.5818, "step": 853 }, { "epoch": 0.9566840926064227, "grad_norm": 0.7723025679588318, "learning_rate": 4.750006630171325e-06, "loss": 0.5754, "step": 854 }, { "epoch": 0.9578043315907394, "grad_norm": 0.7873339653015137, "learning_rate": 4.7493543944270174e-06, "loss": 0.5641, "step": 855 }, { "epoch": 0.958924570575056, "grad_norm": 0.8600917458534241, "learning_rate": 4.748701353845247e-06, "loss": 0.5993, "step": 856 }, { "epoch": 0.9600448095593727, "grad_norm": 0.7842808365821838, "learning_rate": 4.748047508659677e-06, "loss": 0.5928, "step": 857 }, { "epoch": 0.9611650485436893, "grad_norm": 0.7855350375175476, "learning_rate": 4.747392859104258e-06, "loss": 0.5814, "step": 858 }, { "epoch": 0.962285287528006, "grad_norm": 0.8112151026725769, "learning_rate": 4.746737405413231e-06, "loss": 0.5753, "step": 859 }, { "epoch": 0.9634055265123226, "grad_norm": 0.8161853551864624, "learning_rate": 4.746081147821121e-06, "loss": 0.5853, "step": 860 }, { "epoch": 0.9645257654966393, "grad_norm": 0.7908380627632141, "learning_rate": 4.745424086562743e-06, "loss": 0.5854, "step": 861 }, { "epoch": 0.9656460044809559, "grad_norm": 0.8022582530975342, "learning_rate": 4.7447662218731995e-06, "loss": 0.5602, "step": 862 }, { "epoch": 0.9667662434652726, "grad_norm": 0.8379324674606323, "learning_rate": 4.744107553987878e-06, "loss": 0.5921, "step": 863 }, { "epoch": 0.9678864824495892, "grad_norm": 0.8459264636039734, "learning_rate": 4.743448083142458e-06, "loss": 0.5984, "step": 864 }, { "epoch": 0.9690067214339059, "grad_norm": 0.8297575116157532, "learning_rate": 4.742787809572901e-06, "loss": 0.5897, "step": 865 }, { "epoch": 0.9701269604182226, "grad_norm": 0.8278453946113586, "learning_rate": 4.742126733515459e-06, "loss": 0.597, "step": 866 }, { "epoch": 0.9712471994025392, "grad_norm": 0.8626736402511597, "learning_rate": 4.741464855206671e-06, "loss": 0.6084, "step": 867 }, { "epoch": 0.9723674383868559, "grad_norm": 0.8282763957977295, "learning_rate": 4.740802174883363e-06, "loss": 0.5668, "step": 868 }, { "epoch": 0.9734876773711725, "grad_norm": 0.8218764066696167, "learning_rate": 4.740138692782646e-06, "loss": 0.5937, "step": 869 }, { "epoch": 0.9746079163554892, "grad_norm": 0.7809569835662842, "learning_rate": 4.73947440914192e-06, "loss": 0.5895, "step": 870 }, { "epoch": 0.9757281553398058, "grad_norm": 0.8076401948928833, "learning_rate": 4.738809324198872e-06, "loss": 0.5757, "step": 871 }, { "epoch": 0.9768483943241225, "grad_norm": 0.8134318590164185, "learning_rate": 4.738143438191473e-06, "loss": 0.5326, "step": 872 }, { "epoch": 0.9779686333084391, "grad_norm": 0.7635218501091003, "learning_rate": 4.737476751357985e-06, "loss": 0.5476, "step": 873 }, { "epoch": 0.9790888722927558, "grad_norm": 0.8077232241630554, "learning_rate": 4.736809263936952e-06, "loss": 0.5722, "step": 874 }, { "epoch": 0.9802091112770724, "grad_norm": 0.8017358183860779, "learning_rate": 4.736140976167206e-06, "loss": 0.5907, "step": 875 }, { "epoch": 0.9813293502613891, "grad_norm": 0.8405149579048157, "learning_rate": 4.735471888287868e-06, "loss": 0.6333, "step": 876 }, { "epoch": 0.9824495892457058, "grad_norm": 0.7879468202590942, "learning_rate": 4.734802000538342e-06, "loss": 0.5496, "step": 877 }, { "epoch": 0.9835698282300224, "grad_norm": 0.8601053357124329, "learning_rate": 4.734131313158319e-06, "loss": 0.5751, "step": 878 }, { "epoch": 0.984690067214339, "grad_norm": 0.8143794536590576, "learning_rate": 4.733459826387777e-06, "loss": 0.583, "step": 879 }, { "epoch": 0.9858103061986557, "grad_norm": 0.8531054258346558, "learning_rate": 4.732787540466979e-06, "loss": 0.6068, "step": 880 }, { "epoch": 0.9869305451829724, "grad_norm": 0.8039345145225525, "learning_rate": 4.732114455636475e-06, "loss": 0.5873, "step": 881 }, { "epoch": 0.988050784167289, "grad_norm": 0.8260403275489807, "learning_rate": 4.7314405721371e-06, "loss": 0.5922, "step": 882 }, { "epoch": 0.9891710231516057, "grad_norm": 0.8372035622596741, "learning_rate": 4.7307658902099755e-06, "loss": 0.5862, "step": 883 }, { "epoch": 0.9902912621359223, "grad_norm": 0.8514466881752014, "learning_rate": 4.730090410096507e-06, "loss": 0.5981, "step": 884 }, { "epoch": 0.991411501120239, "grad_norm": 0.7753927111625671, "learning_rate": 4.7294141320383875e-06, "loss": 0.6009, "step": 885 }, { "epoch": 0.9925317401045557, "grad_norm": 0.8559523820877075, "learning_rate": 4.7287370562775955e-06, "loss": 0.5903, "step": 886 }, { "epoch": 0.9936519790888723, "grad_norm": 0.7929627895355225, "learning_rate": 4.728059183056394e-06, "loss": 0.5727, "step": 887 }, { "epoch": 0.9947722180731889, "grad_norm": 0.8660935759544373, "learning_rate": 4.72738051261733e-06, "loss": 0.5701, "step": 888 }, { "epoch": 0.9958924570575056, "grad_norm": 0.8257469534873962, "learning_rate": 4.72670104520324e-06, "loss": 0.5592, "step": 889 }, { "epoch": 0.9970126960418223, "grad_norm": 0.8579026460647583, "learning_rate": 4.726020781057241e-06, "loss": 0.5888, "step": 890 }, { "epoch": 0.9981329350261389, "grad_norm": 0.791415810585022, "learning_rate": 4.7253397204227385e-06, "loss": 0.5572, "step": 891 }, { "epoch": 0.9992531740104555, "grad_norm": 0.8314563035964966, "learning_rate": 4.724657863543419e-06, "loss": 0.5832, "step": 892 }, { "epoch": 1.0, "grad_norm": 0.8314563035964966, "learning_rate": 4.72397521066326e-06, "loss": 0.6103, "step": 893 }, { "epoch": 1.0011202389843166, "grad_norm": 1.2335702180862427, "learning_rate": 4.723291762026519e-06, "loss": 0.5434, "step": 894 }, { "epoch": 1.0022404779686334, "grad_norm": 0.8101676106452942, "learning_rate": 4.722607517877737e-06, "loss": 0.5393, "step": 895 }, { "epoch": 1.00336071695295, "grad_norm": 0.7916525602340698, "learning_rate": 4.7219224784617465e-06, "loss": 0.5638, "step": 896 }, { "epoch": 1.0044809559372667, "grad_norm": 0.8107758164405823, "learning_rate": 4.721236644023657e-06, "loss": 0.5773, "step": 897 }, { "epoch": 1.0056011949215833, "grad_norm": 0.8929505348205566, "learning_rate": 4.720550014808867e-06, "loss": 0.5105, "step": 898 }, { "epoch": 1.0067214339058999, "grad_norm": 0.8275009989738464, "learning_rate": 4.719862591063058e-06, "loss": 0.5629, "step": 899 }, { "epoch": 1.0078416728902166, "grad_norm": 0.8205452561378479, "learning_rate": 4.7191743730321955e-06, "loss": 0.5458, "step": 900 }, { "epoch": 1.0089619118745332, "grad_norm": 0.8630054593086243, "learning_rate": 4.718485360962529e-06, "loss": 0.562, "step": 901 }, { "epoch": 1.0100821508588498, "grad_norm": 0.839333176612854, "learning_rate": 4.717795555100595e-06, "loss": 0.5631, "step": 902 }, { "epoch": 1.0112023898431666, "grad_norm": 0.7813014388084412, "learning_rate": 4.717104955693209e-06, "loss": 0.5369, "step": 903 }, { "epoch": 1.0123226288274831, "grad_norm": 0.7793049216270447, "learning_rate": 4.716413562987475e-06, "loss": 0.5637, "step": 904 }, { "epoch": 1.0134428678118, "grad_norm": 0.8571561574935913, "learning_rate": 4.715721377230778e-06, "loss": 0.5722, "step": 905 }, { "epoch": 1.0145631067961165, "grad_norm": 0.8131767511367798, "learning_rate": 4.715028398670787e-06, "loss": 0.5608, "step": 906 }, { "epoch": 1.015683345780433, "grad_norm": 0.8168996572494507, "learning_rate": 4.714334627555458e-06, "loss": 0.5529, "step": 907 }, { "epoch": 1.0168035847647499, "grad_norm": 0.823046088218689, "learning_rate": 4.7136400641330245e-06, "loss": 0.5682, "step": 908 }, { "epoch": 1.0179238237490664, "grad_norm": 0.8340138792991638, "learning_rate": 4.712944708652011e-06, "loss": 0.5731, "step": 909 }, { "epoch": 1.0190440627333832, "grad_norm": 0.8534042835235596, "learning_rate": 4.712248561361218e-06, "loss": 0.5679, "step": 910 }, { "epoch": 1.0201643017176998, "grad_norm": 0.8459539413452148, "learning_rate": 4.711551622509734e-06, "loss": 0.5607, "step": 911 }, { "epoch": 1.0212845407020164, "grad_norm": 0.8298152685165405, "learning_rate": 4.7108538923469296e-06, "loss": 0.5806, "step": 912 }, { "epoch": 1.0224047796863331, "grad_norm": 0.8335070610046387, "learning_rate": 4.710155371122458e-06, "loss": 0.5285, "step": 913 }, { "epoch": 1.0235250186706497, "grad_norm": 0.7781080603599548, "learning_rate": 4.709456059086257e-06, "loss": 0.5824, "step": 914 }, { "epoch": 1.0246452576549665, "grad_norm": 0.8258634805679321, "learning_rate": 4.7087559564885445e-06, "loss": 0.5431, "step": 915 }, { "epoch": 1.025765496639283, "grad_norm": 0.8281342387199402, "learning_rate": 4.708055063579824e-06, "loss": 0.5583, "step": 916 }, { "epoch": 1.0268857356235996, "grad_norm": 0.7836266160011292, "learning_rate": 4.707353380610879e-06, "loss": 0.5636, "step": 917 }, { "epoch": 1.0280059746079164, "grad_norm": 0.834606409072876, "learning_rate": 4.706650907832781e-06, "loss": 0.5432, "step": 918 }, { "epoch": 1.029126213592233, "grad_norm": 0.8574039340019226, "learning_rate": 4.705947645496877e-06, "loss": 0.5452, "step": 919 }, { "epoch": 1.0302464525765496, "grad_norm": 0.7969507575035095, "learning_rate": 4.705243593854802e-06, "loss": 0.5357, "step": 920 }, { "epoch": 1.0313666915608664, "grad_norm": 0.8153135180473328, "learning_rate": 4.7045387531584704e-06, "loss": 0.5316, "step": 921 }, { "epoch": 1.032486930545183, "grad_norm": 0.7883548736572266, "learning_rate": 4.703833123660081e-06, "loss": 0.5232, "step": 922 }, { "epoch": 1.0336071695294997, "grad_norm": 0.8280951380729675, "learning_rate": 4.703126705612113e-06, "loss": 0.5693, "step": 923 }, { "epoch": 1.0347274085138163, "grad_norm": 0.8673230409622192, "learning_rate": 4.702419499267329e-06, "loss": 0.5508, "step": 924 }, { "epoch": 1.0358476474981329, "grad_norm": 0.8065434694290161, "learning_rate": 4.701711504878773e-06, "loss": 0.5389, "step": 925 }, { "epoch": 1.0369678864824496, "grad_norm": 0.797985851764679, "learning_rate": 4.701002722699771e-06, "loss": 0.5393, "step": 926 }, { "epoch": 1.0380881254667662, "grad_norm": 0.8205111026763916, "learning_rate": 4.7002931529839315e-06, "loss": 0.5602, "step": 927 }, { "epoch": 1.039208364451083, "grad_norm": 0.8055931329727173, "learning_rate": 4.699582795985144e-06, "loss": 0.5447, "step": 928 }, { "epoch": 1.0403286034353996, "grad_norm": 0.8045268058776855, "learning_rate": 4.698871651957581e-06, "loss": 0.5299, "step": 929 }, { "epoch": 1.0414488424197161, "grad_norm": 0.7948052883148193, "learning_rate": 4.698159721155694e-06, "loss": 0.5388, "step": 930 }, { "epoch": 1.042569081404033, "grad_norm": 0.8069709539413452, "learning_rate": 4.697447003834219e-06, "loss": 0.5443, "step": 931 }, { "epoch": 1.0436893203883495, "grad_norm": 0.8315683007240295, "learning_rate": 4.6967335002481724e-06, "loss": 0.563, "step": 932 }, { "epoch": 1.044809559372666, "grad_norm": 0.8262251615524292, "learning_rate": 4.69601921065285e-06, "loss": 0.5802, "step": 933 }, { "epoch": 1.0459297983569829, "grad_norm": 0.8720364570617676, "learning_rate": 4.6953041353038324e-06, "loss": 0.5285, "step": 934 }, { "epoch": 1.0470500373412994, "grad_norm": 0.7995201349258423, "learning_rate": 4.694588274456978e-06, "loss": 0.5551, "step": 935 }, { "epoch": 1.0481702763256162, "grad_norm": 0.8372474312782288, "learning_rate": 4.693871628368428e-06, "loss": 0.5293, "step": 936 }, { "epoch": 1.0492905153099328, "grad_norm": 0.854775071144104, "learning_rate": 4.693154197294606e-06, "loss": 0.5472, "step": 937 }, { "epoch": 1.0504107542942493, "grad_norm": 0.8773542046546936, "learning_rate": 4.692435981492212e-06, "loss": 0.5347, "step": 938 }, { "epoch": 1.0515309932785661, "grad_norm": 0.7934802174568176, "learning_rate": 4.69171698121823e-06, "loss": 0.5594, "step": 939 }, { "epoch": 1.0526512322628827, "grad_norm": 0.840215265750885, "learning_rate": 4.690997196729925e-06, "loss": 0.5637, "step": 940 }, { "epoch": 1.0537714712471995, "grad_norm": 0.813681423664093, "learning_rate": 4.690276628284842e-06, "loss": 0.5453, "step": 941 }, { "epoch": 1.054891710231516, "grad_norm": 0.833226203918457, "learning_rate": 4.689555276140807e-06, "loss": 0.5625, "step": 942 }, { "epoch": 1.0560119492158326, "grad_norm": 0.8451018929481506, "learning_rate": 4.688833140555923e-06, "loss": 0.5377, "step": 943 }, { "epoch": 1.0571321882001494, "grad_norm": 0.8202646970748901, "learning_rate": 4.688110221788579e-06, "loss": 0.5439, "step": 944 }, { "epoch": 1.058252427184466, "grad_norm": 0.8503218293190002, "learning_rate": 4.68738652009744e-06, "loss": 0.5693, "step": 945 }, { "epoch": 1.0593726661687826, "grad_norm": 0.8435008525848389, "learning_rate": 4.686662035741452e-06, "loss": 0.5549, "step": 946 }, { "epoch": 1.0604929051530994, "grad_norm": 0.8627398014068604, "learning_rate": 4.685936768979842e-06, "loss": 0.5509, "step": 947 }, { "epoch": 1.061613144137416, "grad_norm": 0.7947062253952026, "learning_rate": 4.685210720072115e-06, "loss": 0.5359, "step": 948 }, { "epoch": 1.0627333831217327, "grad_norm": 0.7926372289657593, "learning_rate": 4.68448388927806e-06, "loss": 0.5033, "step": 949 }, { "epoch": 1.0638536221060493, "grad_norm": 0.800025224685669, "learning_rate": 4.683756276857741e-06, "loss": 0.5379, "step": 950 }, { "epoch": 1.0649738610903658, "grad_norm": 0.8090462684631348, "learning_rate": 4.683027883071505e-06, "loss": 0.5612, "step": 951 }, { "epoch": 1.0660941000746826, "grad_norm": 0.8113719820976257, "learning_rate": 4.682298708179975e-06, "loss": 0.5743, "step": 952 }, { "epoch": 1.0672143390589992, "grad_norm": 0.8232184648513794, "learning_rate": 4.681568752444058e-06, "loss": 0.544, "step": 953 }, { "epoch": 1.068334578043316, "grad_norm": 0.7987185716629028, "learning_rate": 4.680838016124938e-06, "loss": 0.5599, "step": 954 }, { "epoch": 1.0694548170276326, "grad_norm": 0.8448579907417297, "learning_rate": 4.680106499484077e-06, "loss": 0.5707, "step": 955 }, { "epoch": 1.0705750560119491, "grad_norm": 0.8265500068664551, "learning_rate": 4.679374202783219e-06, "loss": 0.5315, "step": 956 }, { "epoch": 1.071695294996266, "grad_norm": 0.8001286387443542, "learning_rate": 4.678641126284385e-06, "loss": 0.5567, "step": 957 }, { "epoch": 1.0728155339805825, "grad_norm": 0.8409720063209534, "learning_rate": 4.6779072702498765e-06, "loss": 0.5274, "step": 958 }, { "epoch": 1.0739357729648993, "grad_norm": 0.8332072496414185, "learning_rate": 4.677172634942273e-06, "loss": 0.5326, "step": 959 }, { "epoch": 1.0750560119492159, "grad_norm": 0.8143296837806702, "learning_rate": 4.676437220624432e-06, "loss": 0.5283, "step": 960 }, { "epoch": 1.0761762509335324, "grad_norm": 0.8352565765380859, "learning_rate": 4.675701027559492e-06, "loss": 0.5528, "step": 961 }, { "epoch": 1.0772964899178492, "grad_norm": 0.8069751262664795, "learning_rate": 4.6749640560108685e-06, "loss": 0.5616, "step": 962 }, { "epoch": 1.0784167289021658, "grad_norm": 0.8762385845184326, "learning_rate": 4.674226306242256e-06, "loss": 0.5461, "step": 963 }, { "epoch": 1.0795369678864823, "grad_norm": 0.8191564679145813, "learning_rate": 4.673487778517628e-06, "loss": 0.5563, "step": 964 }, { "epoch": 1.0806572068707991, "grad_norm": 0.8050143122673035, "learning_rate": 4.672748473101234e-06, "loss": 0.5373, "step": 965 }, { "epoch": 1.0817774458551157, "grad_norm": 0.8051874041557312, "learning_rate": 4.672008390257606e-06, "loss": 0.5327, "step": 966 }, { "epoch": 1.0828976848394325, "grad_norm": 0.8265339136123657, "learning_rate": 4.6712675302515495e-06, "loss": 0.5418, "step": 967 }, { "epoch": 1.084017923823749, "grad_norm": 0.8328646421432495, "learning_rate": 4.670525893348152e-06, "loss": 0.5555, "step": 968 }, { "epoch": 1.0851381628080656, "grad_norm": 0.8175073266029358, "learning_rate": 4.669783479812776e-06, "loss": 0.5664, "step": 969 }, { "epoch": 1.0862584017923824, "grad_norm": 0.8268328309059143, "learning_rate": 4.669040289911064e-06, "loss": 0.5412, "step": 970 }, { "epoch": 1.087378640776699, "grad_norm": 0.8998653888702393, "learning_rate": 4.668296323908935e-06, "loss": 0.5581, "step": 971 }, { "epoch": 1.0884988797610158, "grad_norm": 0.8150838017463684, "learning_rate": 4.6675515820725856e-06, "loss": 0.5404, "step": 972 }, { "epoch": 1.0896191187453323, "grad_norm": 0.8107709288597107, "learning_rate": 4.666806064668493e-06, "loss": 0.5472, "step": 973 }, { "epoch": 1.090739357729649, "grad_norm": 0.8273866772651672, "learning_rate": 4.666059771963406e-06, "loss": 0.5672, "step": 974 }, { "epoch": 1.0918595967139657, "grad_norm": 0.8533821702003479, "learning_rate": 4.6653127042243565e-06, "loss": 0.5573, "step": 975 }, { "epoch": 1.0929798356982823, "grad_norm": 0.809196412563324, "learning_rate": 4.664564861718651e-06, "loss": 0.5339, "step": 976 }, { "epoch": 1.0941000746825988, "grad_norm": 0.8037805557250977, "learning_rate": 4.663816244713874e-06, "loss": 0.5553, "step": 977 }, { "epoch": 1.0952203136669156, "grad_norm": 0.8320299386978149, "learning_rate": 4.663066853477885e-06, "loss": 0.5362, "step": 978 }, { "epoch": 1.0963405526512322, "grad_norm": 0.8118987679481506, "learning_rate": 4.662316688278824e-06, "loss": 0.5683, "step": 979 }, { "epoch": 1.097460791635549, "grad_norm": 0.8285667896270752, "learning_rate": 4.6615657493851075e-06, "loss": 0.5496, "step": 980 }, { "epoch": 1.0985810306198656, "grad_norm": 0.8147162795066833, "learning_rate": 4.660814037065424e-06, "loss": 0.5558, "step": 981 }, { "epoch": 1.0997012696041821, "grad_norm": 0.8943469524383545, "learning_rate": 4.660061551588746e-06, "loss": 0.5359, "step": 982 }, { "epoch": 1.100821508588499, "grad_norm": 0.8224088549613953, "learning_rate": 4.659308293224317e-06, "loss": 0.5215, "step": 983 }, { "epoch": 1.1019417475728155, "grad_norm": 0.8107877969741821, "learning_rate": 4.658554262241659e-06, "loss": 0.5536, "step": 984 }, { "epoch": 1.1030619865571323, "grad_norm": 0.8498128652572632, "learning_rate": 4.6577994589105715e-06, "loss": 0.5537, "step": 985 }, { "epoch": 1.1041822255414488, "grad_norm": 0.8373145461082458, "learning_rate": 4.657043883501128e-06, "loss": 0.5663, "step": 986 }, { "epoch": 1.1053024645257654, "grad_norm": 0.8539902567863464, "learning_rate": 4.656287536283681e-06, "loss": 0.5684, "step": 987 }, { "epoch": 1.1064227035100822, "grad_norm": 0.8307133316993713, "learning_rate": 4.655530417528856e-06, "loss": 0.552, "step": 988 }, { "epoch": 1.1075429424943988, "grad_norm": 0.8355655670166016, "learning_rate": 4.654772527507558e-06, "loss": 0.5439, "step": 989 }, { "epoch": 1.1086631814787156, "grad_norm": 0.8081607222557068, "learning_rate": 4.6540138664909665e-06, "loss": 0.5485, "step": 990 }, { "epoch": 1.1097834204630321, "grad_norm": 0.8134661316871643, "learning_rate": 4.653254434750535e-06, "loss": 0.5661, "step": 991 }, { "epoch": 1.1109036594473487, "grad_norm": 0.8444826602935791, "learning_rate": 4.652494232557995e-06, "loss": 0.5517, "step": 992 }, { "epoch": 1.1120238984316655, "grad_norm": 0.8160927891731262, "learning_rate": 4.651733260185353e-06, "loss": 0.5181, "step": 993 }, { "epoch": 1.113144137415982, "grad_norm": 0.8135287761688232, "learning_rate": 4.650971517904892e-06, "loss": 0.5747, "step": 994 }, { "epoch": 1.1142643764002986, "grad_norm": 0.8516098260879517, "learning_rate": 4.650209005989169e-06, "loss": 0.5464, "step": 995 }, { "epoch": 1.1153846153846154, "grad_norm": 0.814786434173584, "learning_rate": 4.6494457247110166e-06, "loss": 0.5315, "step": 996 }, { "epoch": 1.116504854368932, "grad_norm": 0.8316855430603027, "learning_rate": 4.648681674343543e-06, "loss": 0.5427, "step": 997 }, { "epoch": 1.1176250933532488, "grad_norm": 0.8516353964805603, "learning_rate": 4.647916855160134e-06, "loss": 0.5578, "step": 998 }, { "epoch": 1.1187453323375653, "grad_norm": 0.8202309608459473, "learning_rate": 4.647151267434445e-06, "loss": 0.5515, "step": 999 }, { "epoch": 1.119865571321882, "grad_norm": 0.8232266306877136, "learning_rate": 4.6463849114404115e-06, "loss": 0.564, "step": 1000 }, { "epoch": 1.1209858103061987, "grad_norm": 0.8440135717391968, "learning_rate": 4.645617787452241e-06, "loss": 0.5571, "step": 1001 }, { "epoch": 1.1221060492905153, "grad_norm": 0.8753403425216675, "learning_rate": 4.6448498957444185e-06, "loss": 0.5479, "step": 1002 }, { "epoch": 1.123226288274832, "grad_norm": 0.8252137303352356, "learning_rate": 4.6440812365917e-06, "loss": 0.534, "step": 1003 }, { "epoch": 1.1243465272591486, "grad_norm": 0.8255431652069092, "learning_rate": 4.643311810269118e-06, "loss": 0.5505, "step": 1004 }, { "epoch": 1.1254667662434652, "grad_norm": 0.820588231086731, "learning_rate": 4.642541617051981e-06, "loss": 0.576, "step": 1005 }, { "epoch": 1.126587005227782, "grad_norm": 0.845767617225647, "learning_rate": 4.6417706572158705e-06, "loss": 0.5095, "step": 1006 }, { "epoch": 1.1277072442120986, "grad_norm": 0.8620426654815674, "learning_rate": 4.64099893103664e-06, "loss": 0.5443, "step": 1007 }, { "epoch": 1.1288274831964151, "grad_norm": 0.8254401683807373, "learning_rate": 4.640226438790422e-06, "loss": 0.5401, "step": 1008 }, { "epoch": 1.129947722180732, "grad_norm": 0.8236058354377747, "learning_rate": 4.639453180753619e-06, "loss": 0.5579, "step": 1009 }, { "epoch": 1.1310679611650485, "grad_norm": 0.841072678565979, "learning_rate": 4.63867915720291e-06, "loss": 0.5714, "step": 1010 }, { "epoch": 1.1321882001493653, "grad_norm": 0.8392432928085327, "learning_rate": 4.637904368415247e-06, "loss": 0.5301, "step": 1011 }, { "epoch": 1.1333084391336818, "grad_norm": 0.84500652551651, "learning_rate": 4.637128814667854e-06, "loss": 0.5214, "step": 1012 }, { "epoch": 1.1344286781179984, "grad_norm": 0.7862651944160461, "learning_rate": 4.636352496238234e-06, "loss": 0.5186, "step": 1013 }, { "epoch": 1.1355489171023152, "grad_norm": 0.8130670785903931, "learning_rate": 4.635575413404156e-06, "loss": 0.5428, "step": 1014 }, { "epoch": 1.1366691560866318, "grad_norm": 0.8158490061759949, "learning_rate": 4.634797566443668e-06, "loss": 0.5263, "step": 1015 }, { "epoch": 1.1377893950709486, "grad_norm": 0.8362638354301453, "learning_rate": 4.634018955635092e-06, "loss": 0.5503, "step": 1016 }, { "epoch": 1.1389096340552651, "grad_norm": 0.828471839427948, "learning_rate": 4.6332395812570206e-06, "loss": 0.5525, "step": 1017 }, { "epoch": 1.1400298730395817, "grad_norm": 0.8640450239181519, "learning_rate": 4.632459443588318e-06, "loss": 0.5819, "step": 1018 }, { "epoch": 1.1411501120238985, "grad_norm": 0.8726822733879089, "learning_rate": 4.631678542908126e-06, "loss": 0.5516, "step": 1019 }, { "epoch": 1.142270351008215, "grad_norm": 0.8317193388938904, "learning_rate": 4.630896879495858e-06, "loss": 0.5643, "step": 1020 }, { "epoch": 1.1433905899925318, "grad_norm": 0.8218059539794922, "learning_rate": 4.6301144536311985e-06, "loss": 0.566, "step": 1021 }, { "epoch": 1.1445108289768484, "grad_norm": 0.8336435556411743, "learning_rate": 4.629331265594105e-06, "loss": 0.5294, "step": 1022 }, { "epoch": 1.145631067961165, "grad_norm": 0.8649945855140686, "learning_rate": 4.628547315664809e-06, "loss": 0.5594, "step": 1023 }, { "epoch": 1.1467513069454818, "grad_norm": 0.8594834208488464, "learning_rate": 4.627762604123815e-06, "loss": 0.5429, "step": 1024 }, { "epoch": 1.1478715459297983, "grad_norm": 0.8120294213294983, "learning_rate": 4.626977131251898e-06, "loss": 0.5396, "step": 1025 }, { "epoch": 1.1489917849141151, "grad_norm": 0.8123870491981506, "learning_rate": 4.626190897330109e-06, "loss": 0.5408, "step": 1026 }, { "epoch": 1.1501120238984317, "grad_norm": 0.817854642868042, "learning_rate": 4.625403902639767e-06, "loss": 0.5469, "step": 1027 }, { "epoch": 1.1512322628827483, "grad_norm": 0.8520634174346924, "learning_rate": 4.6246161474624656e-06, "loss": 0.5545, "step": 1028 }, { "epoch": 1.152352501867065, "grad_norm": 0.8475438952445984, "learning_rate": 4.62382763208007e-06, "loss": 0.5228, "step": 1029 }, { "epoch": 1.1534727408513816, "grad_norm": 0.8179640769958496, "learning_rate": 4.623038356774717e-06, "loss": 0.5539, "step": 1030 }, { "epoch": 1.1545929798356982, "grad_norm": 0.8401399850845337, "learning_rate": 4.622248321828817e-06, "loss": 0.543, "step": 1031 }, { "epoch": 1.155713218820015, "grad_norm": 0.8284974098205566, "learning_rate": 4.621457527525051e-06, "loss": 0.5396, "step": 1032 }, { "epoch": 1.1568334578043316, "grad_norm": 0.8201552033424377, "learning_rate": 4.62066597414637e-06, "loss": 0.5641, "step": 1033 }, { "epoch": 1.1579536967886481, "grad_norm": 0.819282591342926, "learning_rate": 4.619873661976e-06, "loss": 0.5276, "step": 1034 }, { "epoch": 1.159073935772965, "grad_norm": 0.8161391615867615, "learning_rate": 4.619080591297435e-06, "loss": 0.5521, "step": 1035 }, { "epoch": 1.1601941747572815, "grad_norm": 0.8103516697883606, "learning_rate": 4.618286762394444e-06, "loss": 0.55, "step": 1036 }, { "epoch": 1.1613144137415983, "grad_norm": 0.8195378184318542, "learning_rate": 4.617492175551065e-06, "loss": 0.5367, "step": 1037 }, { "epoch": 1.1624346527259148, "grad_norm": 0.8827869892120361, "learning_rate": 4.6166968310516066e-06, "loss": 0.5464, "step": 1038 }, { "epoch": 1.1635548917102314, "grad_norm": 0.8650336861610413, "learning_rate": 4.6159007291806515e-06, "loss": 0.5257, "step": 1039 }, { "epoch": 1.1646751306945482, "grad_norm": 0.852587878704071, "learning_rate": 4.615103870223051e-06, "loss": 0.5225, "step": 1040 }, { "epoch": 1.1657953696788648, "grad_norm": 0.8107483983039856, "learning_rate": 4.614306254463926e-06, "loss": 0.56, "step": 1041 }, { "epoch": 1.1669156086631816, "grad_norm": 0.8535749912261963, "learning_rate": 4.613507882188671e-06, "loss": 0.5365, "step": 1042 }, { "epoch": 1.1680358476474981, "grad_norm": 0.8128278255462646, "learning_rate": 4.6127087536829514e-06, "loss": 0.5369, "step": 1043 }, { "epoch": 1.1691560866318147, "grad_norm": 0.8134152889251709, "learning_rate": 4.611908869232701e-06, "loss": 0.5621, "step": 1044 }, { "epoch": 1.1702763256161315, "grad_norm": 0.8495088815689087, "learning_rate": 4.611108229124124e-06, "loss": 0.581, "step": 1045 }, { "epoch": 1.171396564600448, "grad_norm": 0.8236438035964966, "learning_rate": 4.610306833643697e-06, "loss": 0.518, "step": 1046 }, { "epoch": 1.1725168035847648, "grad_norm": 0.793741762638092, "learning_rate": 4.6095046830781666e-06, "loss": 0.5389, "step": 1047 }, { "epoch": 1.1736370425690814, "grad_norm": 0.8526056408882141, "learning_rate": 4.608701777714547e-06, "loss": 0.5665, "step": 1048 }, { "epoch": 1.174757281553398, "grad_norm": 0.8603430986404419, "learning_rate": 4.6078981178401265e-06, "loss": 0.5524, "step": 1049 }, { "epoch": 1.1758775205377148, "grad_norm": 0.8882256150245667, "learning_rate": 4.607093703742459e-06, "loss": 0.5554, "step": 1050 }, { "epoch": 1.1769977595220313, "grad_norm": 0.8279406428337097, "learning_rate": 4.606288535709372e-06, "loss": 0.5506, "step": 1051 }, { "epoch": 1.1781179985063481, "grad_norm": 0.8276134133338928, "learning_rate": 4.605482614028961e-06, "loss": 0.538, "step": 1052 }, { "epoch": 1.1792382374906647, "grad_norm": 0.8543738126754761, "learning_rate": 4.604675938989591e-06, "loss": 0.5354, "step": 1053 }, { "epoch": 1.1803584764749813, "grad_norm": 0.8727709054946899, "learning_rate": 4.603868510879897e-06, "loss": 0.5543, "step": 1054 }, { "epoch": 1.181478715459298, "grad_norm": 0.8450466990470886, "learning_rate": 4.603060329988784e-06, "loss": 0.5412, "step": 1055 }, { "epoch": 1.1825989544436146, "grad_norm": 0.8641091585159302, "learning_rate": 4.602251396605425e-06, "loss": 0.5771, "step": 1056 }, { "epoch": 1.1837191934279314, "grad_norm": 0.8307204246520996, "learning_rate": 4.601441711019263e-06, "loss": 0.5457, "step": 1057 }, { "epoch": 1.184839432412248, "grad_norm": 0.8530333638191223, "learning_rate": 4.600631273520011e-06, "loss": 0.5494, "step": 1058 }, { "epoch": 1.1859596713965646, "grad_norm": 0.8765411376953125, "learning_rate": 4.599820084397649e-06, "loss": 0.5651, "step": 1059 }, { "epoch": 1.1870799103808813, "grad_norm": 0.8434428572654724, "learning_rate": 4.599008143942428e-06, "loss": 0.5585, "step": 1060 }, { "epoch": 1.188200149365198, "grad_norm": 0.8094550967216492, "learning_rate": 4.598195452444867e-06, "loss": 0.5651, "step": 1061 }, { "epoch": 1.1893203883495145, "grad_norm": 0.825619101524353, "learning_rate": 4.5973820101957535e-06, "loss": 0.5358, "step": 1062 }, { "epoch": 1.1904406273338313, "grad_norm": 0.7984577417373657, "learning_rate": 4.596567817486143e-06, "loss": 0.5305, "step": 1063 }, { "epoch": 1.1915608663181478, "grad_norm": 0.8166099786758423, "learning_rate": 4.595752874607362e-06, "loss": 0.5268, "step": 1064 }, { "epoch": 1.1926811053024644, "grad_norm": 0.8126864433288574, "learning_rate": 4.594937181851002e-06, "loss": 0.5416, "step": 1065 }, { "epoch": 1.1938013442867812, "grad_norm": 0.8082033395767212, "learning_rate": 4.594120739508925e-06, "loss": 0.556, "step": 1066 }, { "epoch": 1.1949215832710978, "grad_norm": 0.822907567024231, "learning_rate": 4.593303547873262e-06, "loss": 0.5374, "step": 1067 }, { "epoch": 1.1960418222554146, "grad_norm": 0.8471306562423706, "learning_rate": 4.59248560723641e-06, "loss": 0.5619, "step": 1068 }, { "epoch": 1.1971620612397311, "grad_norm": 0.849753201007843, "learning_rate": 4.591666917891034e-06, "loss": 0.5517, "step": 1069 }, { "epoch": 1.1982823002240477, "grad_norm": 0.8199844360351562, "learning_rate": 4.590847480130069e-06, "loss": 0.5431, "step": 1070 }, { "epoch": 1.1994025392083645, "grad_norm": 0.846013069152832, "learning_rate": 4.590027294246717e-06, "loss": 0.5463, "step": 1071 }, { "epoch": 1.200522778192681, "grad_norm": 0.8319349884986877, "learning_rate": 4.589206360534446e-06, "loss": 0.5374, "step": 1072 }, { "epoch": 1.2016430171769978, "grad_norm": 0.8070456981658936, "learning_rate": 4.5883846792869925e-06, "loss": 0.5283, "step": 1073 }, { "epoch": 1.2027632561613144, "grad_norm": 0.7885628342628479, "learning_rate": 4.5875622507983616e-06, "loss": 0.5542, "step": 1074 }, { "epoch": 1.203883495145631, "grad_norm": 0.8185691833496094, "learning_rate": 4.586739075362826e-06, "loss": 0.5316, "step": 1075 }, { "epoch": 1.2050037341299478, "grad_norm": 0.8217731714248657, "learning_rate": 4.585915153274924e-06, "loss": 0.5436, "step": 1076 }, { "epoch": 1.2061239731142643, "grad_norm": 0.8212025761604309, "learning_rate": 4.585090484829459e-06, "loss": 0.5589, "step": 1077 }, { "epoch": 1.2072442120985811, "grad_norm": 0.8024436831474304, "learning_rate": 4.5842650703215075e-06, "loss": 0.5324, "step": 1078 }, { "epoch": 1.2083644510828977, "grad_norm": 0.8126838803291321, "learning_rate": 4.583438910046409e-06, "loss": 0.5519, "step": 1079 }, { "epoch": 1.2094846900672143, "grad_norm": 0.819503128528595, "learning_rate": 4.582612004299769e-06, "loss": 0.5508, "step": 1080 }, { "epoch": 1.210604929051531, "grad_norm": 0.8436784148216248, "learning_rate": 4.581784353377463e-06, "loss": 0.5544, "step": 1081 }, { "epoch": 1.2117251680358476, "grad_norm": 0.8434869647026062, "learning_rate": 4.580955957575629e-06, "loss": 0.5531, "step": 1082 }, { "epoch": 1.2128454070201644, "grad_norm": 0.8168767094612122, "learning_rate": 4.580126817190676e-06, "loss": 0.5044, "step": 1083 }, { "epoch": 1.213965646004481, "grad_norm": 0.7980238199234009, "learning_rate": 4.579296932519276e-06, "loss": 0.5471, "step": 1084 }, { "epoch": 1.2150858849887975, "grad_norm": 0.8311899304389954, "learning_rate": 4.578466303858369e-06, "loss": 0.5315, "step": 1085 }, { "epoch": 1.2162061239731143, "grad_norm": 0.8057358860969543, "learning_rate": 4.577634931505162e-06, "loss": 0.5133, "step": 1086 }, { "epoch": 1.217326362957431, "grad_norm": 0.8055294156074524, "learning_rate": 4.5768028157571235e-06, "loss": 0.5525, "step": 1087 }, { "epoch": 1.2184466019417475, "grad_norm": 0.8826123476028442, "learning_rate": 4.575969956911994e-06, "loss": 0.5382, "step": 1088 }, { "epoch": 1.2195668409260643, "grad_norm": 0.8325172662734985, "learning_rate": 4.575136355267777e-06, "loss": 0.56, "step": 1089 }, { "epoch": 1.2206870799103808, "grad_norm": 0.843222439289093, "learning_rate": 4.574302011122741e-06, "loss": 0.5589, "step": 1090 }, { "epoch": 1.2218073188946976, "grad_norm": 0.8231297135353088, "learning_rate": 4.5734669247754225e-06, "loss": 0.5376, "step": 1091 }, { "epoch": 1.2229275578790142, "grad_norm": 0.8703131079673767, "learning_rate": 4.572631096524621e-06, "loss": 0.5415, "step": 1092 }, { "epoch": 1.2240477968633308, "grad_norm": 0.8341230154037476, "learning_rate": 4.571794526669404e-06, "loss": 0.5755, "step": 1093 }, { "epoch": 1.2251680358476476, "grad_norm": 0.8507810831069946, "learning_rate": 4.570957215509102e-06, "loss": 0.5324, "step": 1094 }, { "epoch": 1.2262882748319641, "grad_norm": 0.8084942698478699, "learning_rate": 4.570119163343312e-06, "loss": 0.56, "step": 1095 }, { "epoch": 1.2274085138162807, "grad_norm": 0.8282336592674255, "learning_rate": 4.569280370471896e-06, "loss": 0.5544, "step": 1096 }, { "epoch": 1.2285287528005975, "grad_norm": 0.789263904094696, "learning_rate": 4.568440837194981e-06, "loss": 0.5526, "step": 1097 }, { "epoch": 1.229648991784914, "grad_norm": 0.8346118330955505, "learning_rate": 4.567600563812958e-06, "loss": 0.5409, "step": 1098 }, { "epoch": 1.2307692307692308, "grad_norm": 0.8182159662246704, "learning_rate": 4.566759550626486e-06, "loss": 0.5391, "step": 1099 }, { "epoch": 1.2318894697535474, "grad_norm": 0.8271141648292542, "learning_rate": 4.5659177979364846e-06, "loss": 0.5368, "step": 1100 }, { "epoch": 1.233009708737864, "grad_norm": 0.804466187953949, "learning_rate": 4.56507530604414e-06, "loss": 0.5426, "step": 1101 }, { "epoch": 1.2341299477221808, "grad_norm": 0.836618959903717, "learning_rate": 4.564232075250904e-06, "loss": 0.5828, "step": 1102 }, { "epoch": 1.2352501867064973, "grad_norm": 0.8297340869903564, "learning_rate": 4.56338810585849e-06, "loss": 0.5259, "step": 1103 }, { "epoch": 1.2363704256908141, "grad_norm": 0.8460643887519836, "learning_rate": 4.562543398168876e-06, "loss": 0.5463, "step": 1104 }, { "epoch": 1.2374906646751307, "grad_norm": 0.8542268872261047, "learning_rate": 4.561697952484309e-06, "loss": 0.5487, "step": 1105 }, { "epoch": 1.2386109036594473, "grad_norm": 0.8352535963058472, "learning_rate": 4.560851769107294e-06, "loss": 0.5565, "step": 1106 }, { "epoch": 1.239731142643764, "grad_norm": 0.8429189324378967, "learning_rate": 4.560004848340602e-06, "loss": 0.5627, "step": 1107 }, { "epoch": 1.2408513816280806, "grad_norm": 0.8104339241981506, "learning_rate": 4.55915719048727e-06, "loss": 0.5535, "step": 1108 }, { "epoch": 1.2419716206123974, "grad_norm": 0.8268340229988098, "learning_rate": 4.5583087958505954e-06, "loss": 0.5557, "step": 1109 }, { "epoch": 1.243091859596714, "grad_norm": 0.8117450475692749, "learning_rate": 4.5574596647341414e-06, "loss": 0.5477, "step": 1110 }, { "epoch": 1.2442120985810305, "grad_norm": 0.8114601969718933, "learning_rate": 4.556609797441734e-06, "loss": 0.5413, "step": 1111 }, { "epoch": 1.2453323375653473, "grad_norm": 0.835013747215271, "learning_rate": 4.555759194277462e-06, "loss": 0.5319, "step": 1112 }, { "epoch": 1.246452576549664, "grad_norm": 0.7998044490814209, "learning_rate": 4.554907855545679e-06, "loss": 0.5397, "step": 1113 }, { "epoch": 1.2475728155339807, "grad_norm": 0.8180138468742371, "learning_rate": 4.554055781551002e-06, "loss": 0.5456, "step": 1114 }, { "epoch": 1.2486930545182973, "grad_norm": 0.8064574003219604, "learning_rate": 4.5532029725983086e-06, "loss": 0.568, "step": 1115 }, { "epoch": 1.2498132935026138, "grad_norm": 0.802710771560669, "learning_rate": 4.55234942899274e-06, "loss": 0.5389, "step": 1116 }, { "epoch": 1.2509335324869306, "grad_norm": 0.8466383814811707, "learning_rate": 4.551495151039703e-06, "loss": 0.5397, "step": 1117 }, { "epoch": 1.2520537714712472, "grad_norm": 0.8483602404594421, "learning_rate": 4.550640139044864e-06, "loss": 0.5491, "step": 1118 }, { "epoch": 1.253174010455564, "grad_norm": 0.8475786447525024, "learning_rate": 4.549784393314155e-06, "loss": 0.5303, "step": 1119 }, { "epoch": 1.2542942494398805, "grad_norm": 0.8381414413452148, "learning_rate": 4.548927914153766e-06, "loss": 0.5235, "step": 1120 }, { "epoch": 1.2554144884241971, "grad_norm": 0.8032870888710022, "learning_rate": 4.548070701870155e-06, "loss": 0.5321, "step": 1121 }, { "epoch": 1.2565347274085137, "grad_norm": 0.8096051812171936, "learning_rate": 4.547212756770039e-06, "loss": 0.5435, "step": 1122 }, { "epoch": 1.2576549663928305, "grad_norm": 0.8399277925491333, "learning_rate": 4.546354079160395e-06, "loss": 0.5434, "step": 1123 }, { "epoch": 1.258775205377147, "grad_norm": 0.8209378719329834, "learning_rate": 4.545494669348469e-06, "loss": 0.5584, "step": 1124 }, { "epoch": 1.2598954443614638, "grad_norm": 0.8418322801589966, "learning_rate": 4.544634527641764e-06, "loss": 0.5545, "step": 1125 }, { "epoch": 1.2610156833457804, "grad_norm": 0.8334120512008667, "learning_rate": 4.543773654348044e-06, "loss": 0.5252, "step": 1126 }, { "epoch": 1.262135922330097, "grad_norm": 0.8128974437713623, "learning_rate": 4.542912049775337e-06, "loss": 0.5421, "step": 1127 }, { "epoch": 1.2632561613144138, "grad_norm": 0.8154008984565735, "learning_rate": 4.542049714231932e-06, "loss": 0.5275, "step": 1128 }, { "epoch": 1.2643764002987303, "grad_norm": 0.831755518913269, "learning_rate": 4.541186648026381e-06, "loss": 0.523, "step": 1129 }, { "epoch": 1.2654966392830471, "grad_norm": 0.7766554355621338, "learning_rate": 4.540322851467496e-06, "loss": 0.5502, "step": 1130 }, { "epoch": 1.2666168782673637, "grad_norm": 0.8152607083320618, "learning_rate": 4.53945832486435e-06, "loss": 0.5464, "step": 1131 }, { "epoch": 1.2677371172516803, "grad_norm": 0.8785687685012817, "learning_rate": 4.538593068526277e-06, "loss": 0.5537, "step": 1132 }, { "epoch": 1.268857356235997, "grad_norm": 0.8451907634735107, "learning_rate": 4.537727082762873e-06, "loss": 0.5665, "step": 1133 }, { "epoch": 1.2699775952203136, "grad_norm": 0.8168203234672546, "learning_rate": 4.536860367883996e-06, "loss": 0.5637, "step": 1134 }, { "epoch": 1.2710978342046304, "grad_norm": 0.8470443487167358, "learning_rate": 4.535992924199764e-06, "loss": 0.5134, "step": 1135 }, { "epoch": 1.272218073188947, "grad_norm": 0.8196655511856079, "learning_rate": 4.535124752020552e-06, "loss": 0.5358, "step": 1136 }, { "epoch": 1.2733383121732635, "grad_norm": 0.8088006973266602, "learning_rate": 4.534255851657004e-06, "loss": 0.5317, "step": 1137 }, { "epoch": 1.2744585511575803, "grad_norm": 0.8026657700538635, "learning_rate": 4.533386223420017e-06, "loss": 0.5255, "step": 1138 }, { "epoch": 1.275578790141897, "grad_norm": 0.8050847053527832, "learning_rate": 4.53251586762075e-06, "loss": 0.5487, "step": 1139 }, { "epoch": 1.2766990291262137, "grad_norm": 0.828590989112854, "learning_rate": 4.5316447845706255e-06, "loss": 0.565, "step": 1140 }, { "epoch": 1.2778192681105303, "grad_norm": 0.8065359592437744, "learning_rate": 4.530772974581324e-06, "loss": 0.529, "step": 1141 }, { "epoch": 1.2789395070948468, "grad_norm": 0.8265255689620972, "learning_rate": 4.529900437964786e-06, "loss": 0.5246, "step": 1142 }, { "epoch": 1.2800597460791636, "grad_norm": 0.8076423406600952, "learning_rate": 4.5290271750332115e-06, "loss": 0.5584, "step": 1143 }, { "epoch": 1.2811799850634802, "grad_norm": 0.8156341314315796, "learning_rate": 4.528153186099062e-06, "loss": 0.5422, "step": 1144 }, { "epoch": 1.282300224047797, "grad_norm": 0.8484329581260681, "learning_rate": 4.527278471475057e-06, "loss": 0.5154, "step": 1145 }, { "epoch": 1.2834204630321135, "grad_norm": 0.7974900603294373, "learning_rate": 4.5264030314741784e-06, "loss": 0.5114, "step": 1146 }, { "epoch": 1.2845407020164301, "grad_norm": 0.8154396414756775, "learning_rate": 4.525526866409663e-06, "loss": 0.5435, "step": 1147 }, { "epoch": 1.285660941000747, "grad_norm": 0.8144055008888245, "learning_rate": 4.524649976595013e-06, "loss": 0.5548, "step": 1148 }, { "epoch": 1.2867811799850635, "grad_norm": 0.8400017619132996, "learning_rate": 4.5237723623439844e-06, "loss": 0.565, "step": 1149 }, { "epoch": 1.2879014189693803, "grad_norm": 0.8405039310455322, "learning_rate": 4.522894023970596e-06, "loss": 0.5222, "step": 1150 }, { "epoch": 1.2890216579536968, "grad_norm": 0.8041941523551941, "learning_rate": 4.522014961789124e-06, "loss": 0.5437, "step": 1151 }, { "epoch": 1.2901418969380134, "grad_norm": 0.9180984497070312, "learning_rate": 4.521135176114104e-06, "loss": 0.5371, "step": 1152 }, { "epoch": 1.29126213592233, "grad_norm": 0.839199423789978, "learning_rate": 4.520254667260331e-06, "loss": 0.5252, "step": 1153 }, { "epoch": 1.2923823749066468, "grad_norm": 0.8278453350067139, "learning_rate": 4.519373435542857e-06, "loss": 0.5851, "step": 1154 }, { "epoch": 1.2935026138909633, "grad_norm": 0.8621891736984253, "learning_rate": 4.518491481276997e-06, "loss": 0.581, "step": 1155 }, { "epoch": 1.2946228528752801, "grad_norm": 0.8634688258171082, "learning_rate": 4.517608804778317e-06, "loss": 0.5502, "step": 1156 }, { "epoch": 1.2957430918595967, "grad_norm": 0.8093946576118469, "learning_rate": 4.51672540636265e-06, "loss": 0.5402, "step": 1157 }, { "epoch": 1.2968633308439133, "grad_norm": 0.8530567288398743, "learning_rate": 4.515841286346081e-06, "loss": 0.5314, "step": 1158 }, { "epoch": 1.29798356982823, "grad_norm": 0.8433166146278381, "learning_rate": 4.514956445044955e-06, "loss": 0.5439, "step": 1159 }, { "epoch": 1.2991038088125466, "grad_norm": 0.8189598321914673, "learning_rate": 4.514070882775877e-06, "loss": 0.5388, "step": 1160 }, { "epoch": 1.3002240477968634, "grad_norm": 0.8377291560173035, "learning_rate": 4.513184599855708e-06, "loss": 0.5385, "step": 1161 }, { "epoch": 1.30134428678118, "grad_norm": 0.8701413869857788, "learning_rate": 4.512297596601567e-06, "loss": 0.5326, "step": 1162 }, { "epoch": 1.3024645257654965, "grad_norm": 0.8627327084541321, "learning_rate": 4.511409873330832e-06, "loss": 0.5465, "step": 1163 }, { "epoch": 1.3035847647498133, "grad_norm": 0.8221105933189392, "learning_rate": 4.510521430361135e-06, "loss": 0.5413, "step": 1164 }, { "epoch": 1.30470500373413, "grad_norm": 0.8241137266159058, "learning_rate": 4.5096322680103725e-06, "loss": 0.5246, "step": 1165 }, { "epoch": 1.3058252427184467, "grad_norm": 0.8309207558631897, "learning_rate": 4.50874238659669e-06, "loss": 0.5335, "step": 1166 }, { "epoch": 1.3069454817027633, "grad_norm": 0.848537027835846, "learning_rate": 4.507851786438496e-06, "loss": 0.561, "step": 1167 }, { "epoch": 1.3080657206870798, "grad_norm": 0.8590072393417358, "learning_rate": 4.506960467854454e-06, "loss": 0.5493, "step": 1168 }, { "epoch": 1.3091859596713966, "grad_norm": 0.8492612838745117, "learning_rate": 4.506068431163487e-06, "loss": 0.5442, "step": 1169 }, { "epoch": 1.3103061986557132, "grad_norm": 0.8207250833511353, "learning_rate": 4.505175676684771e-06, "loss": 0.5088, "step": 1170 }, { "epoch": 1.31142643764003, "grad_norm": 0.8155739307403564, "learning_rate": 4.5042822047377424e-06, "loss": 0.5686, "step": 1171 }, { "epoch": 1.3125466766243465, "grad_norm": 0.8703952431678772, "learning_rate": 4.503388015642091e-06, "loss": 0.5401, "step": 1172 }, { "epoch": 1.313666915608663, "grad_norm": 0.8210623860359192, "learning_rate": 4.502493109717766e-06, "loss": 0.5272, "step": 1173 }, { "epoch": 1.31478715459298, "grad_norm": 0.8164148926734924, "learning_rate": 4.5015974872849725e-06, "loss": 0.5416, "step": 1174 }, { "epoch": 1.3159073935772965, "grad_norm": 0.8628402352333069, "learning_rate": 4.500701148664171e-06, "loss": 0.5546, "step": 1175 }, { "epoch": 1.3170276325616133, "grad_norm": 0.8327616453170776, "learning_rate": 4.499804094176078e-06, "loss": 0.5482, "step": 1176 }, { "epoch": 1.3181478715459298, "grad_norm": 0.8208657503128052, "learning_rate": 4.498906324141669e-06, "loss": 0.5443, "step": 1177 }, { "epoch": 1.3192681105302464, "grad_norm": 0.807716429233551, "learning_rate": 4.498007838882172e-06, "loss": 0.526, "step": 1178 }, { "epoch": 1.3203883495145632, "grad_norm": 0.829759418964386, "learning_rate": 4.497108638719072e-06, "loss": 0.5528, "step": 1179 }, { "epoch": 1.3215085884988798, "grad_norm": 0.799696147441864, "learning_rate": 4.496208723974112e-06, "loss": 0.539, "step": 1180 }, { "epoch": 1.3226288274831965, "grad_norm": 0.8294451236724854, "learning_rate": 4.495308094969288e-06, "loss": 0.5443, "step": 1181 }, { "epoch": 1.3237490664675131, "grad_norm": 0.8449733257293701, "learning_rate": 4.494406752026851e-06, "loss": 0.5356, "step": 1182 }, { "epoch": 1.3248693054518297, "grad_norm": 0.8247659206390381, "learning_rate": 4.493504695469311e-06, "loss": 0.5608, "step": 1183 }, { "epoch": 1.3259895444361463, "grad_norm": 0.835203230381012, "learning_rate": 4.492601925619431e-06, "loss": 0.5756, "step": 1184 }, { "epoch": 1.327109783420463, "grad_norm": 0.8409526348114014, "learning_rate": 4.491698442800228e-06, "loss": 0.5582, "step": 1185 }, { "epoch": 1.3282300224047796, "grad_norm": 0.8321925401687622, "learning_rate": 4.490794247334977e-06, "loss": 0.5195, "step": 1186 }, { "epoch": 1.3293502613890964, "grad_norm": 0.8160293102264404, "learning_rate": 4.489889339547206e-06, "loss": 0.5383, "step": 1187 }, { "epoch": 1.330470500373413, "grad_norm": 0.8163958191871643, "learning_rate": 4.488983719760698e-06, "loss": 0.5617, "step": 1188 }, { "epoch": 1.3315907393577295, "grad_norm": 0.8268260359764099, "learning_rate": 4.488077388299492e-06, "loss": 0.5437, "step": 1189 }, { "epoch": 1.3327109783420463, "grad_norm": 0.838289201259613, "learning_rate": 4.48717034548788e-06, "loss": 0.5304, "step": 1190 }, { "epoch": 1.333831217326363, "grad_norm": 0.8222647309303284, "learning_rate": 4.48626259165041e-06, "loss": 0.5306, "step": 1191 }, { "epoch": 1.3349514563106797, "grad_norm": 0.7920235991477966, "learning_rate": 4.485354127111884e-06, "loss": 0.5501, "step": 1192 }, { "epoch": 1.3360716952949963, "grad_norm": 0.8315522074699402, "learning_rate": 4.484444952197358e-06, "loss": 0.5149, "step": 1193 }, { "epoch": 1.3371919342793128, "grad_norm": 0.813721776008606, "learning_rate": 4.483535067232141e-06, "loss": 0.58, "step": 1194 }, { "epoch": 1.3383121732636296, "grad_norm": 0.8278853893280029, "learning_rate": 4.482624472541799e-06, "loss": 0.5347, "step": 1195 }, { "epoch": 1.3394324122479462, "grad_norm": 0.8072376847267151, "learning_rate": 4.481713168452149e-06, "loss": 0.5417, "step": 1196 }, { "epoch": 1.340552651232263, "grad_norm": 0.8479835987091064, "learning_rate": 4.480801155289263e-06, "loss": 0.5545, "step": 1197 }, { "epoch": 1.3416728902165795, "grad_norm": 0.857487142086029, "learning_rate": 4.479888433379468e-06, "loss": 0.5542, "step": 1198 }, { "epoch": 1.342793129200896, "grad_norm": 0.8252971172332764, "learning_rate": 4.478975003049343e-06, "loss": 0.5599, "step": 1199 }, { "epoch": 1.343913368185213, "grad_norm": 0.8503106236457825, "learning_rate": 4.478060864625721e-06, "loss": 0.5351, "step": 1200 }, { "epoch": 1.3450336071695295, "grad_norm": 0.7950337529182434, "learning_rate": 4.477146018435687e-06, "loss": 0.5313, "step": 1201 }, { "epoch": 1.3461538461538463, "grad_norm": 0.8159598112106323, "learning_rate": 4.476230464806581e-06, "loss": 0.5472, "step": 1202 }, { "epoch": 1.3472740851381628, "grad_norm": 0.833303689956665, "learning_rate": 4.475314204065997e-06, "loss": 0.5386, "step": 1203 }, { "epoch": 1.3483943241224794, "grad_norm": 0.8313762545585632, "learning_rate": 4.474397236541779e-06, "loss": 0.562, "step": 1204 }, { "epoch": 1.3495145631067962, "grad_norm": 0.8206455707550049, "learning_rate": 4.4734795625620265e-06, "loss": 0.5418, "step": 1205 }, { "epoch": 1.3506348020911128, "grad_norm": 0.7903845906257629, "learning_rate": 4.47256118245509e-06, "loss": 0.5413, "step": 1206 }, { "epoch": 1.3517550410754295, "grad_norm": 0.8083523511886597, "learning_rate": 4.4716420965495735e-06, "loss": 0.5385, "step": 1207 }, { "epoch": 1.352875280059746, "grad_norm": 0.843407928943634, "learning_rate": 4.470722305174334e-06, "loss": 0.5568, "step": 1208 }, { "epoch": 1.3539955190440627, "grad_norm": 0.8617134094238281, "learning_rate": 4.46980180865848e-06, "loss": 0.55, "step": 1209 }, { "epoch": 1.3551157580283795, "grad_norm": 0.8540908098220825, "learning_rate": 4.468880607331373e-06, "loss": 0.5242, "step": 1210 }, { "epoch": 1.356235997012696, "grad_norm": 0.779636561870575, "learning_rate": 4.4679587015226255e-06, "loss": 0.5295, "step": 1211 }, { "epoch": 1.3573562359970128, "grad_norm": 0.826751172542572, "learning_rate": 4.467036091562105e-06, "loss": 0.5158, "step": 1212 }, { "epoch": 1.3584764749813294, "grad_norm": 0.854387104511261, "learning_rate": 4.466112777779927e-06, "loss": 0.5386, "step": 1213 }, { "epoch": 1.359596713965646, "grad_norm": 0.7959662675857544, "learning_rate": 4.465188760506461e-06, "loss": 0.5212, "step": 1214 }, { "epoch": 1.3607169529499625, "grad_norm": 0.8715735077857971, "learning_rate": 4.464264040072329e-06, "loss": 0.553, "step": 1215 }, { "epoch": 1.3618371919342793, "grad_norm": 0.8566111922264099, "learning_rate": 4.463338616808403e-06, "loss": 0.5478, "step": 1216 }, { "epoch": 1.362957430918596, "grad_norm": 0.8157747983932495, "learning_rate": 4.462412491045806e-06, "loss": 0.5432, "step": 1217 }, { "epoch": 1.3640776699029127, "grad_norm": 0.8130636215209961, "learning_rate": 4.461485663115915e-06, "loss": 0.5251, "step": 1218 }, { "epoch": 1.3651979088872293, "grad_norm": 0.8303166031837463, "learning_rate": 4.460558133350356e-06, "loss": 0.5606, "step": 1219 }, { "epoch": 1.3663181478715458, "grad_norm": 0.8391600847244263, "learning_rate": 4.459629902081007e-06, "loss": 0.5662, "step": 1220 }, { "epoch": 1.3674383868558626, "grad_norm": 0.8392864465713501, "learning_rate": 4.458700969639997e-06, "loss": 0.5547, "step": 1221 }, { "epoch": 1.3685586258401792, "grad_norm": 0.8507291674613953, "learning_rate": 4.457771336359703e-06, "loss": 0.5587, "step": 1222 }, { "epoch": 1.369678864824496, "grad_norm": 0.8064186573028564, "learning_rate": 4.456841002572759e-06, "loss": 0.5175, "step": 1223 }, { "epoch": 1.3707991038088125, "grad_norm": 0.8098925948143005, "learning_rate": 4.4559099686120445e-06, "loss": 0.5287, "step": 1224 }, { "epoch": 1.371919342793129, "grad_norm": 0.8226019144058228, "learning_rate": 4.454978234810692e-06, "loss": 0.5388, "step": 1225 }, { "epoch": 1.373039581777446, "grad_norm": 0.8429880142211914, "learning_rate": 4.454045801502082e-06, "loss": 0.5407, "step": 1226 }, { "epoch": 1.3741598207617625, "grad_norm": 0.8022751212120056, "learning_rate": 4.4531126690198476e-06, "loss": 0.5264, "step": 1227 }, { "epoch": 1.3752800597460793, "grad_norm": 0.7995109558105469, "learning_rate": 4.452178837697871e-06, "loss": 0.5557, "step": 1228 }, { "epoch": 1.3764002987303958, "grad_norm": 0.8224391937255859, "learning_rate": 4.451244307870285e-06, "loss": 0.5414, "step": 1229 }, { "epoch": 1.3775205377147124, "grad_norm": 0.8280567526817322, "learning_rate": 4.450309079871472e-06, "loss": 0.5489, "step": 1230 }, { "epoch": 1.3786407766990292, "grad_norm": 0.8450224995613098, "learning_rate": 4.449373154036064e-06, "loss": 0.5364, "step": 1231 }, { "epoch": 1.3797610156833457, "grad_norm": 0.7838452458381653, "learning_rate": 4.4484365306989434e-06, "loss": 0.5183, "step": 1232 }, { "epoch": 1.3808812546676625, "grad_norm": 0.8605710864067078, "learning_rate": 4.447499210195242e-06, "loss": 0.542, "step": 1233 }, { "epoch": 1.382001493651979, "grad_norm": 0.8326447606086731, "learning_rate": 4.44656119286034e-06, "loss": 0.5341, "step": 1234 }, { "epoch": 1.3831217326362957, "grad_norm": 0.8388296365737915, "learning_rate": 4.4456224790298666e-06, "loss": 0.5493, "step": 1235 }, { "epoch": 1.3842419716206125, "grad_norm": 0.8321563005447388, "learning_rate": 4.444683069039703e-06, "loss": 0.5719, "step": 1236 }, { "epoch": 1.385362210604929, "grad_norm": 0.8426681756973267, "learning_rate": 4.443742963225979e-06, "loss": 0.5329, "step": 1237 }, { "epoch": 1.3864824495892458, "grad_norm": 0.8210824728012085, "learning_rate": 4.44280216192507e-06, "loss": 0.5537, "step": 1238 }, { "epoch": 1.3876026885735624, "grad_norm": 0.8024011850357056, "learning_rate": 4.441860665473602e-06, "loss": 0.5084, "step": 1239 }, { "epoch": 1.388722927557879, "grad_norm": 0.8122202157974243, "learning_rate": 4.4409184742084514e-06, "loss": 0.5225, "step": 1240 }, { "epoch": 1.3898431665421958, "grad_norm": 0.8381528258323669, "learning_rate": 4.439975588466742e-06, "loss": 0.5325, "step": 1241 }, { "epoch": 1.3909634055265123, "grad_norm": 0.8207586407661438, "learning_rate": 4.439032008585846e-06, "loss": 0.5557, "step": 1242 }, { "epoch": 1.392083644510829, "grad_norm": 0.8223419189453125, "learning_rate": 4.438087734903385e-06, "loss": 0.544, "step": 1243 }, { "epoch": 1.3932038834951457, "grad_norm": 0.8231616020202637, "learning_rate": 4.437142767757225e-06, "loss": 0.5503, "step": 1244 }, { "epoch": 1.3943241224794622, "grad_norm": 0.8446402549743652, "learning_rate": 4.436197107485485e-06, "loss": 0.5196, "step": 1245 }, { "epoch": 1.3954443614637788, "grad_norm": 0.7973191142082214, "learning_rate": 4.43525075442653e-06, "loss": 0.5235, "step": 1246 }, { "epoch": 1.3965646004480956, "grad_norm": 0.812990128993988, "learning_rate": 4.4343037089189735e-06, "loss": 0.5423, "step": 1247 }, { "epoch": 1.3976848394324122, "grad_norm": 0.8209276795387268, "learning_rate": 4.4333559713016736e-06, "loss": 0.5169, "step": 1248 }, { "epoch": 1.398805078416729, "grad_norm": 0.8271411657333374, "learning_rate": 4.432407541913741e-06, "loss": 0.5337, "step": 1249 }, { "epoch": 1.3999253174010455, "grad_norm": 0.8020209670066833, "learning_rate": 4.431458421094531e-06, "loss": 0.5179, "step": 1250 }, { "epoch": 1.401045556385362, "grad_norm": 0.8035420775413513, "learning_rate": 4.430508609183647e-06, "loss": 0.5416, "step": 1251 }, { "epoch": 1.402165795369679, "grad_norm": 0.819017767906189, "learning_rate": 4.429558106520939e-06, "loss": 0.5261, "step": 1252 }, { "epoch": 1.4032860343539955, "grad_norm": 0.81986004114151, "learning_rate": 4.4286069134465035e-06, "loss": 0.5122, "step": 1253 }, { "epoch": 1.4044062733383122, "grad_norm": 0.8470500111579895, "learning_rate": 4.427655030300688e-06, "loss": 0.5393, "step": 1254 }, { "epoch": 1.4055265123226288, "grad_norm": 0.8163276314735413, "learning_rate": 4.426702457424082e-06, "loss": 0.5475, "step": 1255 }, { "epoch": 1.4066467513069454, "grad_norm": 0.8219355344772339, "learning_rate": 4.425749195157524e-06, "loss": 0.5343, "step": 1256 }, { "epoch": 1.4077669902912622, "grad_norm": 0.8590656518936157, "learning_rate": 4.424795243842099e-06, "loss": 0.5649, "step": 1257 }, { "epoch": 1.4088872292755787, "grad_norm": 0.837833046913147, "learning_rate": 4.423840603819141e-06, "loss": 0.5249, "step": 1258 }, { "epoch": 1.4100074682598955, "grad_norm": 0.8217041492462158, "learning_rate": 4.422885275430225e-06, "loss": 0.55, "step": 1259 }, { "epoch": 1.411127707244212, "grad_norm": 0.8252221941947937, "learning_rate": 4.421929259017176e-06, "loss": 0.5684, "step": 1260 }, { "epoch": 1.4122479462285287, "grad_norm": 0.8646223545074463, "learning_rate": 4.420972554922066e-06, "loss": 0.5623, "step": 1261 }, { "epoch": 1.4133681852128455, "grad_norm": 0.8612502217292786, "learning_rate": 4.42001516348721e-06, "loss": 0.5597, "step": 1262 }, { "epoch": 1.414488424197162, "grad_norm": 0.8005207180976868, "learning_rate": 4.419057085055171e-06, "loss": 0.5252, "step": 1263 }, { "epoch": 1.4156086631814788, "grad_norm": 0.813919723033905, "learning_rate": 4.418098319968758e-06, "loss": 0.5502, "step": 1264 }, { "epoch": 1.4167289021657954, "grad_norm": 0.8239195942878723, "learning_rate": 4.4171388685710234e-06, "loss": 0.5229, "step": 1265 }, { "epoch": 1.417849141150112, "grad_norm": 0.8362986445426941, "learning_rate": 4.416178731205269e-06, "loss": 0.5311, "step": 1266 }, { "epoch": 1.4189693801344287, "grad_norm": 0.8120007514953613, "learning_rate": 4.415217908215038e-06, "loss": 0.5479, "step": 1267 }, { "epoch": 1.4200896191187453, "grad_norm": 0.811576783657074, "learning_rate": 4.414256399944122e-06, "loss": 0.5542, "step": 1268 }, { "epoch": 1.421209858103062, "grad_norm": 0.8243828415870667, "learning_rate": 4.413294206736555e-06, "loss": 0.5555, "step": 1269 }, { "epoch": 1.4223300970873787, "grad_norm": 0.8122988343238831, "learning_rate": 4.41233132893662e-06, "loss": 0.5551, "step": 1270 }, { "epoch": 1.4234503360716952, "grad_norm": 0.8304051756858826, "learning_rate": 4.41136776688884e-06, "loss": 0.5734, "step": 1271 }, { "epoch": 1.4245705750560118, "grad_norm": 0.8483263850212097, "learning_rate": 4.410403520937987e-06, "loss": 0.5328, "step": 1272 }, { "epoch": 1.4256908140403286, "grad_norm": 0.837712287902832, "learning_rate": 4.409438591429075e-06, "loss": 0.542, "step": 1273 }, { "epoch": 1.4268110530246454, "grad_norm": 0.8439350128173828, "learning_rate": 4.408472978707365e-06, "loss": 0.5523, "step": 1274 }, { "epoch": 1.427931292008962, "grad_norm": 0.8609887957572937, "learning_rate": 4.4075066831183605e-06, "loss": 0.5462, "step": 1275 }, { "epoch": 1.4290515309932785, "grad_norm": 0.8378350734710693, "learning_rate": 4.406539705007809e-06, "loss": 0.5579, "step": 1276 }, { "epoch": 1.430171769977595, "grad_norm": 0.8463708758354187, "learning_rate": 4.4055720447217056e-06, "loss": 0.5634, "step": 1277 }, { "epoch": 1.4312920089619119, "grad_norm": 0.8240607976913452, "learning_rate": 4.404603702606286e-06, "loss": 0.5471, "step": 1278 }, { "epoch": 1.4324122479462285, "grad_norm": 0.8117276430130005, "learning_rate": 4.40363467900803e-06, "loss": 0.5614, "step": 1279 }, { "epoch": 1.4335324869305452, "grad_norm": 0.8322970271110535, "learning_rate": 4.402664974273662e-06, "loss": 0.5534, "step": 1280 }, { "epoch": 1.4346527259148618, "grad_norm": 0.8382965326309204, "learning_rate": 4.401694588750153e-06, "loss": 0.5546, "step": 1281 }, { "epoch": 1.4357729648991784, "grad_norm": 0.8176775574684143, "learning_rate": 4.400723522784712e-06, "loss": 0.5236, "step": 1282 }, { "epoch": 1.4368932038834952, "grad_norm": 0.8426209688186646, "learning_rate": 4.399751776724795e-06, "loss": 0.5527, "step": 1283 }, { "epoch": 1.4380134428678117, "grad_norm": 0.823796808719635, "learning_rate": 4.398779350918102e-06, "loss": 0.5662, "step": 1284 }, { "epoch": 1.4391336818521285, "grad_norm": 0.8374935388565063, "learning_rate": 4.397806245712573e-06, "loss": 0.5726, "step": 1285 }, { "epoch": 1.440253920836445, "grad_norm": 0.8143332600593567, "learning_rate": 4.3968324614563965e-06, "loss": 0.5077, "step": 1286 }, { "epoch": 1.4413741598207617, "grad_norm": 0.8215734958648682, "learning_rate": 4.395857998497996e-06, "loss": 0.5138, "step": 1287 }, { "epoch": 1.4424943988050785, "grad_norm": 0.7970778346061707, "learning_rate": 4.394882857186045e-06, "loss": 0.5088, "step": 1288 }, { "epoch": 1.443614637789395, "grad_norm": 0.8270483613014221, "learning_rate": 4.393907037869457e-06, "loss": 0.5374, "step": 1289 }, { "epoch": 1.4447348767737118, "grad_norm": 0.8275690078735352, "learning_rate": 4.3929305408973875e-06, "loss": 0.5122, "step": 1290 }, { "epoch": 1.4458551157580284, "grad_norm": 0.8330255746841431, "learning_rate": 4.3919533666192345e-06, "loss": 0.5562, "step": 1291 }, { "epoch": 1.446975354742345, "grad_norm": 0.8581027984619141, "learning_rate": 4.390975515384641e-06, "loss": 0.5542, "step": 1292 }, { "epoch": 1.4480955937266617, "grad_norm": 0.844085156917572, "learning_rate": 4.389996987543488e-06, "loss": 0.5506, "step": 1293 }, { "epoch": 1.4492158327109783, "grad_norm": 0.8119167685508728, "learning_rate": 4.389017783445903e-06, "loss": 0.5309, "step": 1294 }, { "epoch": 1.450336071695295, "grad_norm": 0.8669208288192749, "learning_rate": 4.388037903442251e-06, "loss": 0.5691, "step": 1295 }, { "epoch": 1.4514563106796117, "grad_norm": 0.8349128365516663, "learning_rate": 4.387057347883143e-06, "loss": 0.5426, "step": 1296 }, { "epoch": 1.4525765496639282, "grad_norm": 0.8149973750114441, "learning_rate": 4.386076117119429e-06, "loss": 0.544, "step": 1297 }, { "epoch": 1.453696788648245, "grad_norm": 0.8381718397140503, "learning_rate": 4.385094211502201e-06, "loss": 0.541, "step": 1298 }, { "epoch": 1.4548170276325616, "grad_norm": 0.8309394717216492, "learning_rate": 4.3841116313827924e-06, "loss": 0.555, "step": 1299 }, { "epoch": 1.4559372666168784, "grad_norm": 0.8401052951812744, "learning_rate": 4.383128377112781e-06, "loss": 0.5455, "step": 1300 }, { "epoch": 1.457057505601195, "grad_norm": 0.8229027390480042, "learning_rate": 4.38214444904398e-06, "loss": 0.5317, "step": 1301 }, { "epoch": 1.4581777445855115, "grad_norm": 0.822666347026825, "learning_rate": 4.38115984752845e-06, "loss": 0.5143, "step": 1302 }, { "epoch": 1.459297983569828, "grad_norm": 0.8157971501350403, "learning_rate": 4.3801745729184875e-06, "loss": 0.5317, "step": 1303 }, { "epoch": 1.4604182225541449, "grad_norm": 0.8346320390701294, "learning_rate": 4.379188625566632e-06, "loss": 0.5533, "step": 1304 }, { "epoch": 1.4615384615384617, "grad_norm": 0.8360608816146851, "learning_rate": 4.378202005825665e-06, "loss": 0.5403, "step": 1305 }, { "epoch": 1.4626587005227782, "grad_norm": 0.8309468030929565, "learning_rate": 4.3772147140486045e-06, "loss": 0.5028, "step": 1306 }, { "epoch": 1.4637789395070948, "grad_norm": 0.8045680522918701, "learning_rate": 4.376226750588714e-06, "loss": 0.5153, "step": 1307 }, { "epoch": 1.4648991784914114, "grad_norm": 0.826449990272522, "learning_rate": 4.375238115799494e-06, "loss": 0.5193, "step": 1308 }, { "epoch": 1.4660194174757282, "grad_norm": 0.8211467862129211, "learning_rate": 4.374248810034686e-06, "loss": 0.5236, "step": 1309 }, { "epoch": 1.4671396564600447, "grad_norm": 0.8300038576126099, "learning_rate": 4.373258833648273e-06, "loss": 0.554, "step": 1310 }, { "epoch": 1.4682598954443615, "grad_norm": 0.852250874042511, "learning_rate": 4.372268186994474e-06, "loss": 0.5673, "step": 1311 }, { "epoch": 1.469380134428678, "grad_norm": 0.8562779426574707, "learning_rate": 4.3712768704277535e-06, "loss": 0.5312, "step": 1312 }, { "epoch": 1.4705003734129947, "grad_norm": 0.8487451672554016, "learning_rate": 4.37028488430281e-06, "loss": 0.542, "step": 1313 }, { "epoch": 1.4716206123973115, "grad_norm": 0.8320393562316895, "learning_rate": 4.369292228974587e-06, "loss": 0.5256, "step": 1314 }, { "epoch": 1.472740851381628, "grad_norm": 0.821002185344696, "learning_rate": 4.368298904798263e-06, "loss": 0.5286, "step": 1315 }, { "epoch": 1.4738610903659448, "grad_norm": 0.8211376070976257, "learning_rate": 4.367304912129258e-06, "loss": 0.5692, "step": 1316 }, { "epoch": 1.4749813293502614, "grad_norm": 0.8837286233901978, "learning_rate": 4.3663102513232295e-06, "loss": 0.5346, "step": 1317 }, { "epoch": 1.476101568334578, "grad_norm": 0.8166071772575378, "learning_rate": 4.365314922736077e-06, "loss": 0.5528, "step": 1318 }, { "epoch": 1.4772218073188947, "grad_norm": 0.8274430632591248, "learning_rate": 4.364318926723937e-06, "loss": 0.5464, "step": 1319 }, { "epoch": 1.4783420463032113, "grad_norm": 0.8482112884521484, "learning_rate": 4.3633222636431845e-06, "loss": 0.5459, "step": 1320 }, { "epoch": 1.479462285287528, "grad_norm": 0.8600017428398132, "learning_rate": 4.362324933850435e-06, "loss": 0.5567, "step": 1321 }, { "epoch": 1.4805825242718447, "grad_norm": 0.8248361945152283, "learning_rate": 4.361326937702538e-06, "loss": 0.5479, "step": 1322 }, { "epoch": 1.4817027632561612, "grad_norm": 0.8052260279655457, "learning_rate": 4.3603282755565885e-06, "loss": 0.5388, "step": 1323 }, { "epoch": 1.482823002240478, "grad_norm": 0.8378350734710693, "learning_rate": 4.359328947769914e-06, "loss": 0.5475, "step": 1324 }, { "epoch": 1.4839432412247946, "grad_norm": 0.845522403717041, "learning_rate": 4.358328954700083e-06, "loss": 0.5133, "step": 1325 }, { "epoch": 1.4850634802091114, "grad_norm": 0.9849204421043396, "learning_rate": 4.3573282967049e-06, "loss": 0.5107, "step": 1326 }, { "epoch": 1.486183719193428, "grad_norm": 0.8313608765602112, "learning_rate": 4.356326974142411e-06, "loss": 0.5737, "step": 1327 }, { "epoch": 1.4873039581777445, "grad_norm": 0.8800959587097168, "learning_rate": 4.355324987370895e-06, "loss": 0.5312, "step": 1328 }, { "epoch": 1.4884241971620613, "grad_norm": 0.8424291014671326, "learning_rate": 4.354322336748872e-06, "loss": 0.5197, "step": 1329 }, { "epoch": 1.4895444361463779, "grad_norm": 0.820409893989563, "learning_rate": 4.353319022635098e-06, "loss": 0.5734, "step": 1330 }, { "epoch": 1.4906646751306947, "grad_norm": 0.8500661849975586, "learning_rate": 4.352315045388569e-06, "loss": 0.5342, "step": 1331 }, { "epoch": 1.4917849141150112, "grad_norm": 0.806735098361969, "learning_rate": 4.351310405368513e-06, "loss": 0.5213, "step": 1332 }, { "epoch": 1.4929051530993278, "grad_norm": 0.838384211063385, "learning_rate": 4.3503051029344025e-06, "loss": 0.5479, "step": 1333 }, { "epoch": 1.4940253920836444, "grad_norm": 0.8513844013214111, "learning_rate": 4.34929913844594e-06, "loss": 0.5406, "step": 1334 }, { "epoch": 1.4951456310679612, "grad_norm": 0.8119661211967468, "learning_rate": 4.348292512263068e-06, "loss": 0.5481, "step": 1335 }, { "epoch": 1.496265870052278, "grad_norm": 0.8307415843009949, "learning_rate": 4.347285224745967e-06, "loss": 0.5565, "step": 1336 }, { "epoch": 1.4973861090365945, "grad_norm": 0.8296387195587158, "learning_rate": 4.346277276255053e-06, "loss": 0.5067, "step": 1337 }, { "epoch": 1.498506348020911, "grad_norm": 0.8077414035797119, "learning_rate": 4.345268667150976e-06, "loss": 0.5209, "step": 1338 }, { "epoch": 1.4996265870052277, "grad_norm": 0.7943417429924011, "learning_rate": 4.344259397794626e-06, "loss": 0.5048, "step": 1339 }, { "epoch": 1.5007468259895445, "grad_norm": 0.7765065431594849, "learning_rate": 4.343249468547128e-06, "loss": 0.5567, "step": 1340 }, { "epoch": 1.5018670649738612, "grad_norm": 0.868191123008728, "learning_rate": 4.3422388797698435e-06, "loss": 0.5479, "step": 1341 }, { "epoch": 1.5029873039581778, "grad_norm": 0.830331027507782, "learning_rate": 4.341227631824368e-06, "loss": 0.5492, "step": 1342 }, { "epoch": 1.5041075429424944, "grad_norm": 0.8496562242507935, "learning_rate": 4.340215725072535e-06, "loss": 0.5541, "step": 1343 }, { "epoch": 1.505227781926811, "grad_norm": 0.8115208148956299, "learning_rate": 4.339203159876413e-06, "loss": 0.5429, "step": 1344 }, { "epoch": 1.5063480209111277, "grad_norm": 0.8215025067329407, "learning_rate": 4.338189936598307e-06, "loss": 0.5522, "step": 1345 }, { "epoch": 1.5074682598954443, "grad_norm": 0.8184052109718323, "learning_rate": 4.3371760556007545e-06, "loss": 0.527, "step": 1346 }, { "epoch": 1.508588498879761, "grad_norm": 0.7937412858009338, "learning_rate": 4.3361615172465325e-06, "loss": 0.5325, "step": 1347 }, { "epoch": 1.5097087378640777, "grad_norm": 0.8070276379585266, "learning_rate": 4.335146321898651e-06, "loss": 0.5279, "step": 1348 }, { "epoch": 1.5108289768483942, "grad_norm": 0.8029081225395203, "learning_rate": 4.334130469920354e-06, "loss": 0.5491, "step": 1349 }, { "epoch": 1.511949215832711, "grad_norm": 0.8653881549835205, "learning_rate": 4.333113961675122e-06, "loss": 0.5623, "step": 1350 }, { "epoch": 1.5130694548170276, "grad_norm": 0.8287846446037292, "learning_rate": 4.33209679752667e-06, "loss": 0.5579, "step": 1351 }, { "epoch": 1.5141896938013444, "grad_norm": 0.8319088220596313, "learning_rate": 4.331078977838949e-06, "loss": 0.5572, "step": 1352 }, { "epoch": 1.515309932785661, "grad_norm": 0.8489014506340027, "learning_rate": 4.3300605029761414e-06, "loss": 0.5302, "step": 1353 }, { "epoch": 1.5164301717699775, "grad_norm": 0.8003896474838257, "learning_rate": 4.329041373302667e-06, "loss": 0.5601, "step": 1354 }, { "epoch": 1.517550410754294, "grad_norm": 0.8308793306350708, "learning_rate": 4.328021589183179e-06, "loss": 0.5078, "step": 1355 }, { "epoch": 1.5186706497386109, "grad_norm": 0.8175726532936096, "learning_rate": 4.327001150982563e-06, "loss": 0.5434, "step": 1356 }, { "epoch": 1.5197908887229277, "grad_norm": 0.8181414008140564, "learning_rate": 4.325980059065942e-06, "loss": 0.545, "step": 1357 }, { "epoch": 1.5209111277072442, "grad_norm": 0.8243163228034973, "learning_rate": 4.32495831379867e-06, "loss": 0.5339, "step": 1358 }, { "epoch": 1.5220313666915608, "grad_norm": 0.8128981590270996, "learning_rate": 4.3239359155463356e-06, "loss": 0.5293, "step": 1359 }, { "epoch": 1.5231516056758774, "grad_norm": 0.8324003219604492, "learning_rate": 4.3229128646747615e-06, "loss": 0.5426, "step": 1360 }, { "epoch": 1.5242718446601942, "grad_norm": 0.8296977281570435, "learning_rate": 4.321889161550005e-06, "loss": 0.5626, "step": 1361 }, { "epoch": 1.525392083644511, "grad_norm": 0.8470244407653809, "learning_rate": 4.320864806538353e-06, "loss": 0.5524, "step": 1362 }, { "epoch": 1.5265123226288275, "grad_norm": 0.8672470450401306, "learning_rate": 4.31983980000633e-06, "loss": 0.5557, "step": 1363 }, { "epoch": 1.527632561613144, "grad_norm": 0.833143413066864, "learning_rate": 4.318814142320692e-06, "loss": 0.5337, "step": 1364 }, { "epoch": 1.5287528005974607, "grad_norm": 0.8296066522598267, "learning_rate": 4.317787833848426e-06, "loss": 0.5637, "step": 1365 }, { "epoch": 1.5298730395817774, "grad_norm": 0.8583776950836182, "learning_rate": 4.316760874956756e-06, "loss": 0.5429, "step": 1366 }, { "epoch": 1.5309932785660942, "grad_norm": 0.8318846821784973, "learning_rate": 4.3157332660131335e-06, "loss": 0.5584, "step": 1367 }, { "epoch": 1.5321135175504108, "grad_norm": 0.8015156984329224, "learning_rate": 4.314705007385248e-06, "loss": 0.5332, "step": 1368 }, { "epoch": 1.5332337565347274, "grad_norm": 0.8311407566070557, "learning_rate": 4.313676099441017e-06, "loss": 0.546, "step": 1369 }, { "epoch": 1.534353995519044, "grad_norm": 0.8014186024665833, "learning_rate": 4.312646542548593e-06, "loss": 0.5109, "step": 1370 }, { "epoch": 1.5354742345033607, "grad_norm": 0.8057787418365479, "learning_rate": 4.31161633707636e-06, "loss": 0.5369, "step": 1371 }, { "epoch": 1.5365944734876775, "grad_norm": 0.8253255486488342, "learning_rate": 4.310585483392933e-06, "loss": 0.5478, "step": 1372 }, { "epoch": 1.537714712471994, "grad_norm": 0.8418827056884766, "learning_rate": 4.309553981867162e-06, "loss": 0.5471, "step": 1373 }, { "epoch": 1.5388349514563107, "grad_norm": 0.8555072546005249, "learning_rate": 4.308521832868125e-06, "loss": 0.5381, "step": 1374 }, { "epoch": 1.5399551904406272, "grad_norm": 0.8227778077125549, "learning_rate": 4.307489036765134e-06, "loss": 0.55, "step": 1375 }, { "epoch": 1.541075429424944, "grad_norm": 0.8473497033119202, "learning_rate": 4.306455593927731e-06, "loss": 0.5355, "step": 1376 }, { "epoch": 1.5421956684092606, "grad_norm": 0.8366703987121582, "learning_rate": 4.305421504725691e-06, "loss": 0.5569, "step": 1377 }, { "epoch": 1.5433159073935774, "grad_norm": 0.815157413482666, "learning_rate": 4.30438676952902e-06, "loss": 0.5252, "step": 1378 }, { "epoch": 1.544436146377894, "grad_norm": 0.877655029296875, "learning_rate": 4.303351388707955e-06, "loss": 0.5393, "step": 1379 }, { "epoch": 1.5455563853622105, "grad_norm": 0.8467420935630798, "learning_rate": 4.302315362632963e-06, "loss": 0.5891, "step": 1380 }, { "epoch": 1.5466766243465273, "grad_norm": 0.8801563382148743, "learning_rate": 4.301278691674742e-06, "loss": 0.5599, "step": 1381 }, { "epoch": 1.5477968633308439, "grad_norm": 0.8227587342262268, "learning_rate": 4.300241376204223e-06, "loss": 0.5304, "step": 1382 }, { "epoch": 1.5489171023151607, "grad_norm": 0.852873682975769, "learning_rate": 4.299203416592565e-06, "loss": 0.5279, "step": 1383 }, { "epoch": 1.5500373412994772, "grad_norm": 0.8275724649429321, "learning_rate": 4.298164813211158e-06, "loss": 0.5514, "step": 1384 }, { "epoch": 1.5511575802837938, "grad_norm": 0.8230090737342834, "learning_rate": 4.297125566431624e-06, "loss": 0.5399, "step": 1385 }, { "epoch": 1.5522778192681104, "grad_norm": 0.8874813914299011, "learning_rate": 4.296085676625813e-06, "loss": 0.5386, "step": 1386 }, { "epoch": 1.5533980582524272, "grad_norm": 0.8467227816581726, "learning_rate": 4.295045144165807e-06, "loss": 0.5467, "step": 1387 }, { "epoch": 1.554518297236744, "grad_norm": 0.8453990817070007, "learning_rate": 4.2940039694239165e-06, "loss": 0.5677, "step": 1388 }, { "epoch": 1.5556385362210605, "grad_norm": 0.8536325097084045, "learning_rate": 4.292962152772682e-06, "loss": 0.5185, "step": 1389 }, { "epoch": 1.556758775205377, "grad_norm": 0.8449810743331909, "learning_rate": 4.291919694584875e-06, "loss": 0.546, "step": 1390 }, { "epoch": 1.5578790141896937, "grad_norm": 1.027535080909729, "learning_rate": 4.290876595233495e-06, "loss": 0.5516, "step": 1391 }, { "epoch": 1.5589992531740104, "grad_norm": 0.8208884000778198, "learning_rate": 4.289832855091772e-06, "loss": 0.5452, "step": 1392 }, { "epoch": 1.5601194921583272, "grad_norm": 0.8302054405212402, "learning_rate": 4.288788474533164e-06, "loss": 0.5374, "step": 1393 }, { "epoch": 1.5612397311426438, "grad_norm": 0.8338841199874878, "learning_rate": 4.28774345393136e-06, "loss": 0.5286, "step": 1394 }, { "epoch": 1.5623599701269604, "grad_norm": 0.8848025798797607, "learning_rate": 4.286697793660276e-06, "loss": 0.5503, "step": 1395 }, { "epoch": 1.563480209111277, "grad_norm": 0.8843843936920166, "learning_rate": 4.285651494094058e-06, "loss": 0.5394, "step": 1396 }, { "epoch": 1.5646004480955937, "grad_norm": 0.860697329044342, "learning_rate": 4.2846045556070805e-06, "loss": 0.5486, "step": 1397 }, { "epoch": 1.5657206870799105, "grad_norm": 0.8341761231422424, "learning_rate": 4.283556978573948e-06, "loss": 0.5845, "step": 1398 }, { "epoch": 1.566840926064227, "grad_norm": 0.8415078520774841, "learning_rate": 4.282508763369489e-06, "loss": 0.5396, "step": 1399 }, { "epoch": 1.5679611650485437, "grad_norm": 0.8659593462944031, "learning_rate": 4.2814599103687686e-06, "loss": 0.5341, "step": 1400 }, { "epoch": 1.5690814040328602, "grad_norm": 0.8313730955123901, "learning_rate": 4.2804104199470696e-06, "loss": 0.5388, "step": 1401 }, { "epoch": 1.570201643017177, "grad_norm": 0.8137566447257996, "learning_rate": 4.279360292479911e-06, "loss": 0.5298, "step": 1402 }, { "epoch": 1.5713218820014938, "grad_norm": 0.829147219657898, "learning_rate": 4.2783095283430365e-06, "loss": 0.5478, "step": 1403 }, { "epoch": 1.5724421209858104, "grad_norm": 0.8064625859260559, "learning_rate": 4.27725812791242e-06, "loss": 0.5332, "step": 1404 }, { "epoch": 1.573562359970127, "grad_norm": 0.828982949256897, "learning_rate": 4.276206091564257e-06, "loss": 0.5317, "step": 1405 }, { "epoch": 1.5746825989544435, "grad_norm": 0.8150440454483032, "learning_rate": 4.275153419674979e-06, "loss": 0.5502, "step": 1406 }, { "epoch": 1.5758028379387603, "grad_norm": 0.8187349438667297, "learning_rate": 4.274100112621238e-06, "loss": 0.5377, "step": 1407 }, { "epoch": 1.5769230769230769, "grad_norm": 0.8216383457183838, "learning_rate": 4.2730461707799174e-06, "loss": 0.5413, "step": 1408 }, { "epoch": 1.5780433159073937, "grad_norm": 0.8329434394836426, "learning_rate": 4.271991594528126e-06, "loss": 0.5372, "step": 1409 }, { "epoch": 1.5791635548917102, "grad_norm": 0.8837087750434875, "learning_rate": 4.270936384243198e-06, "loss": 0.5187, "step": 1410 }, { "epoch": 1.5802837938760268, "grad_norm": 0.851102888584137, "learning_rate": 4.2698805403027e-06, "loss": 0.5528, "step": 1411 }, { "epoch": 1.5814040328603436, "grad_norm": 0.8246365785598755, "learning_rate": 4.268824063084417e-06, "loss": 0.5276, "step": 1412 }, { "epoch": 1.5825242718446602, "grad_norm": 0.8388403654098511, "learning_rate": 4.267766952966369e-06, "loss": 0.5545, "step": 1413 }, { "epoch": 1.583644510828977, "grad_norm": 0.8562852740287781, "learning_rate": 4.2667092103267975e-06, "loss": 0.5512, "step": 1414 }, { "epoch": 1.5847647498132935, "grad_norm": 0.8856998682022095, "learning_rate": 4.2656508355441705e-06, "loss": 0.5534, "step": 1415 }, { "epoch": 1.58588498879761, "grad_norm": 0.9003668427467346, "learning_rate": 4.264591828997184e-06, "loss": 0.5061, "step": 1416 }, { "epoch": 1.5870052277819267, "grad_norm": 0.8696342706680298, "learning_rate": 4.263532191064759e-06, "loss": 0.5448, "step": 1417 }, { "epoch": 1.5881254667662434, "grad_norm": 0.8576314449310303, "learning_rate": 4.262471922126044e-06, "loss": 0.5117, "step": 1418 }, { "epoch": 1.5892457057505602, "grad_norm": 0.9128873348236084, "learning_rate": 4.261411022560411e-06, "loss": 0.5376, "step": 1419 }, { "epoch": 1.5903659447348768, "grad_norm": 0.8280308246612549, "learning_rate": 4.2603494927474575e-06, "loss": 0.5463, "step": 1420 }, { "epoch": 1.5914861837191934, "grad_norm": 0.8322044610977173, "learning_rate": 4.2592873330670085e-06, "loss": 0.5596, "step": 1421 }, { "epoch": 1.59260642270351, "grad_norm": 0.8214216232299805, "learning_rate": 4.2582245438991135e-06, "loss": 0.5135, "step": 1422 }, { "epoch": 1.5937266616878267, "grad_norm": 0.8392521142959595, "learning_rate": 4.257161125624047e-06, "loss": 0.5411, "step": 1423 }, { "epoch": 1.5948469006721435, "grad_norm": 0.8548365831375122, "learning_rate": 4.256097078622309e-06, "loss": 0.5287, "step": 1424 }, { "epoch": 1.59596713965646, "grad_norm": 0.8191155791282654, "learning_rate": 4.255032403274624e-06, "loss": 0.5239, "step": 1425 }, { "epoch": 1.5970873786407767, "grad_norm": 0.8004139065742493, "learning_rate": 4.253967099961942e-06, "loss": 0.5355, "step": 1426 }, { "epoch": 1.5982076176250932, "grad_norm": 0.8321914672851562, "learning_rate": 4.2529011690654366e-06, "loss": 0.5495, "step": 1427 }, { "epoch": 1.59932785660941, "grad_norm": 0.8587489724159241, "learning_rate": 4.2518346109665074e-06, "loss": 0.5502, "step": 1428 }, { "epoch": 1.6004480955937268, "grad_norm": 0.8176190853118896, "learning_rate": 4.250767426046777e-06, "loss": 0.5353, "step": 1429 }, { "epoch": 1.6015683345780434, "grad_norm": 0.8270806074142456, "learning_rate": 4.249699614688093e-06, "loss": 0.5449, "step": 1430 }, { "epoch": 1.60268857356236, "grad_norm": 0.8037596344947815, "learning_rate": 4.248631177272527e-06, "loss": 0.5775, "step": 1431 }, { "epoch": 1.6038088125466765, "grad_norm": 0.8505509495735168, "learning_rate": 4.247562114182375e-06, "loss": 0.5231, "step": 1432 }, { "epoch": 1.6049290515309933, "grad_norm": 0.8228225708007812, "learning_rate": 4.246492425800157e-06, "loss": 0.5336, "step": 1433 }, { "epoch": 1.60604929051531, "grad_norm": 0.8823798298835754, "learning_rate": 4.245422112508615e-06, "loss": 0.5549, "step": 1434 }, { "epoch": 1.6071695294996267, "grad_norm": 0.8225086331367493, "learning_rate": 4.244351174690717e-06, "loss": 0.5347, "step": 1435 }, { "epoch": 1.6082897684839432, "grad_norm": 0.8210791945457458, "learning_rate": 4.2432796127296535e-06, "loss": 0.5349, "step": 1436 }, { "epoch": 1.6094100074682598, "grad_norm": 0.8335378766059875, "learning_rate": 4.242207427008837e-06, "loss": 0.5575, "step": 1437 }, { "epoch": 1.6105302464525766, "grad_norm": 0.8326417207717896, "learning_rate": 4.241134617911905e-06, "loss": 0.5422, "step": 1438 }, { "epoch": 1.6116504854368932, "grad_norm": 0.8305699825286865, "learning_rate": 4.240061185822717e-06, "loss": 0.553, "step": 1439 }, { "epoch": 1.61277072442121, "grad_norm": 0.8145079016685486, "learning_rate": 4.238987131125357e-06, "loss": 0.5172, "step": 1440 }, { "epoch": 1.6138909634055265, "grad_norm": 0.8260290622711182, "learning_rate": 4.237912454204129e-06, "loss": 0.5287, "step": 1441 }, { "epoch": 1.615011202389843, "grad_norm": 0.812061071395874, "learning_rate": 4.236837155443562e-06, "loss": 0.5332, "step": 1442 }, { "epoch": 1.6161314413741599, "grad_norm": 0.7981239557266235, "learning_rate": 4.235761235228407e-06, "loss": 0.5563, "step": 1443 }, { "epoch": 1.6172516803584764, "grad_norm": 0.8434090614318848, "learning_rate": 4.234684693943637e-06, "loss": 0.5575, "step": 1444 }, { "epoch": 1.6183719193427932, "grad_norm": 0.8346796035766602, "learning_rate": 4.233607531974447e-06, "loss": 0.5328, "step": 1445 }, { "epoch": 1.6194921583271098, "grad_norm": 0.8098893761634827, "learning_rate": 4.232529749706254e-06, "loss": 0.5467, "step": 1446 }, { "epoch": 1.6206123973114264, "grad_norm": 0.8355947732925415, "learning_rate": 4.231451347524699e-06, "loss": 0.5432, "step": 1447 }, { "epoch": 1.621732636295743, "grad_norm": 0.8329986333847046, "learning_rate": 4.230372325815641e-06, "loss": 0.5622, "step": 1448 }, { "epoch": 1.6228528752800597, "grad_norm": 0.8184260725975037, "learning_rate": 4.229292684965163e-06, "loss": 0.5514, "step": 1449 }, { "epoch": 1.6239731142643765, "grad_norm": 0.8356477618217468, "learning_rate": 4.2282124253595715e-06, "loss": 0.546, "step": 1450 }, { "epoch": 1.625093353248693, "grad_norm": 0.8311543464660645, "learning_rate": 4.227131547385391e-06, "loss": 0.5234, "step": 1451 }, { "epoch": 1.6262135922330097, "grad_norm": 0.8295907974243164, "learning_rate": 4.226050051429367e-06, "loss": 0.4932, "step": 1452 }, { "epoch": 1.6273338312173262, "grad_norm": 0.7894620895385742, "learning_rate": 4.22496793787847e-06, "loss": 0.5641, "step": 1453 }, { "epoch": 1.628454070201643, "grad_norm": 0.8411605954170227, "learning_rate": 4.223885207119889e-06, "loss": 0.5417, "step": 1454 }, { "epoch": 1.6295743091859598, "grad_norm": 0.8090710639953613, "learning_rate": 4.222801859541031e-06, "loss": 0.5445, "step": 1455 }, { "epoch": 1.6306945481702764, "grad_norm": 0.8332550525665283, "learning_rate": 4.221717895529531e-06, "loss": 0.5471, "step": 1456 }, { "epoch": 1.631814787154593, "grad_norm": 0.9103831648826599, "learning_rate": 4.220633315473236e-06, "loss": 0.5384, "step": 1457 }, { "epoch": 1.6329350261389095, "grad_norm": 0.8271507620811462, "learning_rate": 4.21954811976022e-06, "loss": 0.5408, "step": 1458 }, { "epoch": 1.6340552651232263, "grad_norm": 0.8201518058776855, "learning_rate": 4.218462308778776e-06, "loss": 0.5633, "step": 1459 }, { "epoch": 1.635175504107543, "grad_norm": 0.8605701327323914, "learning_rate": 4.217375882917414e-06, "loss": 0.5498, "step": 1460 }, { "epoch": 1.6362957430918597, "grad_norm": 0.8359277844429016, "learning_rate": 4.2162888425648665e-06, "loss": 0.5467, "step": 1461 }, { "epoch": 1.6374159820761762, "grad_norm": 0.8181623816490173, "learning_rate": 4.215201188110086e-06, "loss": 0.5219, "step": 1462 }, { "epoch": 1.6385362210604928, "grad_norm": 0.8375784754753113, "learning_rate": 4.214112919942243e-06, "loss": 0.526, "step": 1463 }, { "epoch": 1.6396564600448096, "grad_norm": 0.7823356986045837, "learning_rate": 4.21302403845073e-06, "loss": 0.5204, "step": 1464 }, { "epoch": 1.6407766990291264, "grad_norm": 2.3768980503082275, "learning_rate": 4.211934544025158e-06, "loss": 0.5606, "step": 1465 }, { "epoch": 1.641896938013443, "grad_norm": 0.84914231300354, "learning_rate": 4.210844437055356e-06, "loss": 0.565, "step": 1466 }, { "epoch": 1.6430171769977595, "grad_norm": 0.8609841465950012, "learning_rate": 4.209753717931373e-06, "loss": 0.5757, "step": 1467 }, { "epoch": 1.644137415982076, "grad_norm": 0.8694177269935608, "learning_rate": 4.208662387043479e-06, "loss": 0.5502, "step": 1468 }, { "epoch": 1.6452576549663929, "grad_norm": 0.9158186316490173, "learning_rate": 4.20757044478216e-06, "loss": 0.5209, "step": 1469 }, { "epoch": 1.6463778939507094, "grad_norm": 0.8625397682189941, "learning_rate": 4.206477891538121e-06, "loss": 0.5609, "step": 1470 }, { "epoch": 1.6474981329350262, "grad_norm": 0.8475672006607056, "learning_rate": 4.205384727702288e-06, "loss": 0.5441, "step": 1471 }, { "epoch": 1.6486183719193428, "grad_norm": 0.818719744682312, "learning_rate": 4.204290953665804e-06, "loss": 0.5266, "step": 1472 }, { "epoch": 1.6497386109036594, "grad_norm": 0.8269298672676086, "learning_rate": 4.203196569820029e-06, "loss": 0.5263, "step": 1473 }, { "epoch": 1.6508588498879762, "grad_norm": 0.7849137187004089, "learning_rate": 4.2021015765565444e-06, "loss": 0.5495, "step": 1474 }, { "epoch": 1.6519790888722927, "grad_norm": 0.8485032320022583, "learning_rate": 4.201005974267146e-06, "loss": 0.5512, "step": 1475 }, { "epoch": 1.6530993278566095, "grad_norm": 0.8280136585235596, "learning_rate": 4.199909763343849e-06, "loss": 0.5227, "step": 1476 }, { "epoch": 1.654219566840926, "grad_norm": 0.8437508344650269, "learning_rate": 4.198812944178889e-06, "loss": 0.5635, "step": 1477 }, { "epoch": 1.6553398058252426, "grad_norm": 0.8449869751930237, "learning_rate": 4.197715517164716e-06, "loss": 0.5127, "step": 1478 }, { "epoch": 1.6564600448095592, "grad_norm": 0.8209198117256165, "learning_rate": 4.196617482693996e-06, "loss": 0.5483, "step": 1479 }, { "epoch": 1.657580283793876, "grad_norm": 0.8873897194862366, "learning_rate": 4.195518841159618e-06, "loss": 0.5537, "step": 1480 }, { "epoch": 1.6587005227781928, "grad_norm": 0.8520996570587158, "learning_rate": 4.194419592954684e-06, "loss": 0.5313, "step": 1481 }, { "epoch": 1.6598207617625094, "grad_norm": 0.8172207474708557, "learning_rate": 4.1933197384725135e-06, "loss": 0.54, "step": 1482 }, { "epoch": 1.660941000746826, "grad_norm": 0.8447046279907227, "learning_rate": 4.192219278106643e-06, "loss": 0.5205, "step": 1483 }, { "epoch": 1.6620612397311425, "grad_norm": 0.8111680746078491, "learning_rate": 4.191118212250827e-06, "loss": 0.5247, "step": 1484 }, { "epoch": 1.6631814787154593, "grad_norm": 0.8495075106620789, "learning_rate": 4.190016541299036e-06, "loss": 0.5079, "step": 1485 }, { "epoch": 1.664301717699776, "grad_norm": 0.8128763437271118, "learning_rate": 4.188914265645456e-06, "loss": 0.5415, "step": 1486 }, { "epoch": 1.6654219566840927, "grad_norm": 0.8739402890205383, "learning_rate": 4.1878113856844925e-06, "loss": 0.5658, "step": 1487 }, { "epoch": 1.6665421956684092, "grad_norm": 0.8443946242332458, "learning_rate": 4.186707901810762e-06, "loss": 0.537, "step": 1488 }, { "epoch": 1.6676624346527258, "grad_norm": 0.8422719836235046, "learning_rate": 4.1856038144191024e-06, "loss": 0.5278, "step": 1489 }, { "epoch": 1.6687826736370426, "grad_norm": 0.8393810987472534, "learning_rate": 4.184499123904564e-06, "loss": 0.5241, "step": 1490 }, { "epoch": 1.6699029126213594, "grad_norm": 0.8822279572486877, "learning_rate": 4.183393830662415e-06, "loss": 0.558, "step": 1491 }, { "epoch": 1.671023151605676, "grad_norm": 0.8313372731208801, "learning_rate": 4.182287935088138e-06, "loss": 0.538, "step": 1492 }, { "epoch": 1.6721433905899925, "grad_norm": 0.8423752188682556, "learning_rate": 4.181181437577429e-06, "loss": 0.5096, "step": 1493 }, { "epoch": 1.673263629574309, "grad_norm": 0.7942532896995544, "learning_rate": 4.180074338526208e-06, "loss": 0.5513, "step": 1494 }, { "epoch": 1.6743838685586259, "grad_norm": 0.843720555305481, "learning_rate": 4.178966638330598e-06, "loss": 0.5704, "step": 1495 }, { "epoch": 1.6755041075429427, "grad_norm": 0.8642749786376953, "learning_rate": 4.177858337386946e-06, "loss": 0.5316, "step": 1496 }, { "epoch": 1.6766243465272592, "grad_norm": 0.8187930583953857, "learning_rate": 4.176749436091811e-06, "loss": 0.5251, "step": 1497 }, { "epoch": 1.6777445855115758, "grad_norm": 0.8171431422233582, "learning_rate": 4.175639934841967e-06, "loss": 0.5336, "step": 1498 }, { "epoch": 1.6788648244958924, "grad_norm": 0.8119639158248901, "learning_rate": 4.174529834034403e-06, "loss": 0.5314, "step": 1499 }, { "epoch": 1.6799850634802092, "grad_norm": 0.8608358502388, "learning_rate": 4.173419134066321e-06, "loss": 0.5341, "step": 1500 }, { "epoch": 1.6811053024645257, "grad_norm": 0.8582233786582947, "learning_rate": 4.17230783533514e-06, "loss": 0.5484, "step": 1501 }, { "epoch": 1.6822255414488425, "grad_norm": 0.8320852518081665, "learning_rate": 4.17119593823849e-06, "loss": 0.51, "step": 1502 }, { "epoch": 1.683345780433159, "grad_norm": 0.8468641638755798, "learning_rate": 4.170083443174218e-06, "loss": 0.5572, "step": 1503 }, { "epoch": 1.6844660194174756, "grad_norm": 0.8393252491950989, "learning_rate": 4.168970350540385e-06, "loss": 0.5348, "step": 1504 }, { "epoch": 1.6855862584017924, "grad_norm": 0.8738113045692444, "learning_rate": 4.167856660735262e-06, "loss": 0.5524, "step": 1505 }, { "epoch": 1.686706497386109, "grad_norm": 0.8472318649291992, "learning_rate": 4.166742374157339e-06, "loss": 0.5133, "step": 1506 }, { "epoch": 1.6878267363704258, "grad_norm": 0.8055902123451233, "learning_rate": 4.165627491205314e-06, "loss": 0.511, "step": 1507 }, { "epoch": 1.6889469753547424, "grad_norm": 0.8492250442504883, "learning_rate": 4.164512012278104e-06, "loss": 0.5621, "step": 1508 }, { "epoch": 1.690067214339059, "grad_norm": 0.8291061520576477, "learning_rate": 4.163395937774836e-06, "loss": 0.5533, "step": 1509 }, { "epoch": 1.6911874533233755, "grad_norm": 0.8331051468849182, "learning_rate": 4.16227926809485e-06, "loss": 0.5192, "step": 1510 }, { "epoch": 1.6923076923076923, "grad_norm": 0.8490992188453674, "learning_rate": 4.1611620036376985e-06, "loss": 0.5357, "step": 1511 }, { "epoch": 1.693427931292009, "grad_norm": 0.8369888663291931, "learning_rate": 4.160044144803151e-06, "loss": 0.5342, "step": 1512 }, { "epoch": 1.6945481702763256, "grad_norm": 0.8247721195220947, "learning_rate": 4.158925691991184e-06, "loss": 0.5368, "step": 1513 }, { "epoch": 1.6956684092606422, "grad_norm": 0.8113073706626892, "learning_rate": 4.1578066456019885e-06, "loss": 0.5555, "step": 1514 }, { "epoch": 1.6967886482449588, "grad_norm": 0.8781044483184814, "learning_rate": 4.15668700603597e-06, "loss": 0.53, "step": 1515 }, { "epoch": 1.6979088872292756, "grad_norm": 0.8180976510047913, "learning_rate": 4.1555667736937455e-06, "loss": 0.5474, "step": 1516 }, { "epoch": 1.6990291262135924, "grad_norm": 0.8118385076522827, "learning_rate": 4.154445948976141e-06, "loss": 0.5292, "step": 1517 }, { "epoch": 1.700149365197909, "grad_norm": 0.8206310272216797, "learning_rate": 4.1533245322842e-06, "loss": 0.5406, "step": 1518 }, { "epoch": 1.7012696041822255, "grad_norm": 0.8399862051010132, "learning_rate": 4.152202524019171e-06, "loss": 0.5417, "step": 1519 }, { "epoch": 1.702389843166542, "grad_norm": 0.8626686334609985, "learning_rate": 4.151079924582519e-06, "loss": 0.5104, "step": 1520 }, { "epoch": 1.7035100821508589, "grad_norm": 0.8447391986846924, "learning_rate": 4.149956734375922e-06, "loss": 0.5332, "step": 1521 }, { "epoch": 1.7046303211351757, "grad_norm": 0.8259961605072021, "learning_rate": 4.148832953801262e-06, "loss": 0.5242, "step": 1522 }, { "epoch": 1.7057505601194922, "grad_norm": 0.8265607357025146, "learning_rate": 4.14770858326064e-06, "loss": 0.5204, "step": 1523 }, { "epoch": 1.7068707991038088, "grad_norm": 0.8091963529586792, "learning_rate": 4.146583623156365e-06, "loss": 0.5253, "step": 1524 }, { "epoch": 1.7079910380881254, "grad_norm": 0.830488920211792, "learning_rate": 4.145458073890955e-06, "loss": 0.5344, "step": 1525 }, { "epoch": 1.7091112770724421, "grad_norm": 0.8003833889961243, "learning_rate": 4.144331935867144e-06, "loss": 0.5294, "step": 1526 }, { "epoch": 1.710231516056759, "grad_norm": 0.8505309224128723, "learning_rate": 4.143205209487869e-06, "loss": 0.531, "step": 1527 }, { "epoch": 1.7113517550410755, "grad_norm": 0.8250753879547119, "learning_rate": 4.1420778951562866e-06, "loss": 0.5421, "step": 1528 }, { "epoch": 1.712471994025392, "grad_norm": 0.8263447284698486, "learning_rate": 4.140949993275756e-06, "loss": 0.5461, "step": 1529 }, { "epoch": 1.7135922330097086, "grad_norm": 0.8574968576431274, "learning_rate": 4.13982150424985e-06, "loss": 0.5499, "step": 1530 }, { "epoch": 1.7147124719940254, "grad_norm": 0.8031488060951233, "learning_rate": 4.138692428482353e-06, "loss": 0.5163, "step": 1531 }, { "epoch": 1.715832710978342, "grad_norm": 0.8235338926315308, "learning_rate": 4.137562766377256e-06, "loss": 0.5346, "step": 1532 }, { "epoch": 1.7169529499626588, "grad_norm": 0.8231131434440613, "learning_rate": 4.136432518338762e-06, "loss": 0.5442, "step": 1533 }, { "epoch": 1.7180731889469754, "grad_norm": 0.8224930763244629, "learning_rate": 4.135301684771283e-06, "loss": 0.545, "step": 1534 }, { "epoch": 1.719193427931292, "grad_norm": 0.7999832034111023, "learning_rate": 4.1341702660794395e-06, "loss": 0.5226, "step": 1535 }, { "epoch": 1.7203136669156085, "grad_norm": 0.8502464294433594, "learning_rate": 4.1330382626680635e-06, "loss": 0.5513, "step": 1536 }, { "epoch": 1.7214339058999253, "grad_norm": 0.8491352200508118, "learning_rate": 4.131905674942196e-06, "loss": 0.5178, "step": 1537 }, { "epoch": 1.722554144884242, "grad_norm": 0.8294553756713867, "learning_rate": 4.1307725033070835e-06, "loss": 0.5415, "step": 1538 }, { "epoch": 1.7236743838685586, "grad_norm": 0.8187465667724609, "learning_rate": 4.129638748168187e-06, "loss": 0.5575, "step": 1539 }, { "epoch": 1.7247946228528752, "grad_norm": 0.8333837985992432, "learning_rate": 4.128504409931172e-06, "loss": 0.5359, "step": 1540 }, { "epoch": 1.7259148618371918, "grad_norm": 0.8331719636917114, "learning_rate": 4.127369489001914e-06, "loss": 0.5513, "step": 1541 }, { "epoch": 1.7270351008215086, "grad_norm": 0.8731279969215393, "learning_rate": 4.126233985786497e-06, "loss": 0.5464, "step": 1542 }, { "epoch": 1.7281553398058254, "grad_norm": 0.8208237886428833, "learning_rate": 4.125097900691213e-06, "loss": 0.5614, "step": 1543 }, { "epoch": 1.729275578790142, "grad_norm": 0.8664867281913757, "learning_rate": 4.1239612341225636e-06, "loss": 0.5328, "step": 1544 }, { "epoch": 1.7303958177744585, "grad_norm": 0.810331404209137, "learning_rate": 4.122823986487257e-06, "loss": 0.5303, "step": 1545 }, { "epoch": 1.731516056758775, "grad_norm": 0.8227166533470154, "learning_rate": 4.121686158192209e-06, "loss": 0.5506, "step": 1546 }, { "epoch": 1.7326362957430919, "grad_norm": 0.8276739716529846, "learning_rate": 4.120547749644545e-06, "loss": 0.5355, "step": 1547 }, { "epoch": 1.7337565347274086, "grad_norm": 0.8266296982765198, "learning_rate": 4.1194087612515965e-06, "loss": 0.5661, "step": 1548 }, { "epoch": 1.7348767737117252, "grad_norm": 0.8601844310760498, "learning_rate": 4.118269193420903e-06, "loss": 0.5089, "step": 1549 }, { "epoch": 1.7359970126960418, "grad_norm": 0.8149077296257019, "learning_rate": 4.117129046560211e-06, "loss": 0.5679, "step": 1550 }, { "epoch": 1.7371172516803584, "grad_norm": 0.8324862122535706, "learning_rate": 4.115988321077474e-06, "loss": 0.5541, "step": 1551 }, { "epoch": 1.7382374906646751, "grad_norm": 0.8243516087532043, "learning_rate": 4.114847017380854e-06, "loss": 0.5364, "step": 1552 }, { "epoch": 1.739357729648992, "grad_norm": 0.8432444930076599, "learning_rate": 4.1137051358787185e-06, "loss": 0.5574, "step": 1553 }, { "epoch": 1.7404779686333085, "grad_norm": 0.8552629351615906, "learning_rate": 4.112562676979641e-06, "loss": 0.5233, "step": 1554 }, { "epoch": 1.741598207617625, "grad_norm": 0.8027449250221252, "learning_rate": 4.111419641092404e-06, "loss": 0.565, "step": 1555 }, { "epoch": 1.7427184466019416, "grad_norm": 0.8295990228652954, "learning_rate": 4.110276028625995e-06, "loss": 0.5056, "step": 1556 }, { "epoch": 1.7438386855862584, "grad_norm": 0.8083453178405762, "learning_rate": 4.1091318399896065e-06, "loss": 0.5476, "step": 1557 }, { "epoch": 1.7449589245705752, "grad_norm": 0.8240988254547119, "learning_rate": 4.107987075592641e-06, "loss": 0.5275, "step": 1558 }, { "epoch": 1.7460791635548918, "grad_norm": 0.8225562572479248, "learning_rate": 4.1068417358447024e-06, "loss": 0.5498, "step": 1559 }, { "epoch": 1.7471994025392084, "grad_norm": 0.8333079814910889, "learning_rate": 4.105695821155604e-06, "loss": 0.5372, "step": 1560 }, { "epoch": 1.748319641523525, "grad_norm": 0.8118395209312439, "learning_rate": 4.104549331935362e-06, "loss": 0.5467, "step": 1561 }, { "epoch": 1.7494398805078417, "grad_norm": 0.812199056148529, "learning_rate": 4.103402268594202e-06, "loss": 0.5412, "step": 1562 }, { "epoch": 1.7505601194921583, "grad_norm": 0.8283849954605103, "learning_rate": 4.102254631542549e-06, "loss": 0.551, "step": 1563 }, { "epoch": 1.751680358476475, "grad_norm": 0.8368584513664246, "learning_rate": 4.101106421191041e-06, "loss": 0.5585, "step": 1564 }, { "epoch": 1.7528005974607916, "grad_norm": 0.824888288974762, "learning_rate": 4.099957637950516e-06, "loss": 0.5421, "step": 1565 }, { "epoch": 1.7539208364451082, "grad_norm": 0.8353846669197083, "learning_rate": 4.0988082822320165e-06, "loss": 0.5398, "step": 1566 }, { "epoch": 1.7550410754294248, "grad_norm": 0.8127483129501343, "learning_rate": 4.097658354446792e-06, "loss": 0.5484, "step": 1567 }, { "epoch": 1.7561613144137416, "grad_norm": 0.83433598279953, "learning_rate": 4.096507855006297e-06, "loss": 0.52, "step": 1568 }, { "epoch": 1.7572815533980584, "grad_norm": 0.8318457007408142, "learning_rate": 4.095356784322189e-06, "loss": 0.5435, "step": 1569 }, { "epoch": 1.758401792382375, "grad_norm": 0.84352707862854, "learning_rate": 4.09420514280633e-06, "loss": 0.5318, "step": 1570 }, { "epoch": 1.7595220313666915, "grad_norm": 0.8551493287086487, "learning_rate": 4.093052930870788e-06, "loss": 0.5502, "step": 1571 }, { "epoch": 1.760642270351008, "grad_norm": 0.8463614583015442, "learning_rate": 4.091900148927833e-06, "loss": 0.546, "step": 1572 }, { "epoch": 1.7617625093353249, "grad_norm": 0.8330878019332886, "learning_rate": 4.090746797389941e-06, "loss": 0.5365, "step": 1573 }, { "epoch": 1.7628827483196416, "grad_norm": 0.8032608032226562, "learning_rate": 4.0895928766697885e-06, "loss": 0.5196, "step": 1574 }, { "epoch": 1.7640029873039582, "grad_norm": 0.8519574403762817, "learning_rate": 4.088438387180261e-06, "loss": 0.5473, "step": 1575 }, { "epoch": 1.7651232262882748, "grad_norm": 0.8020384907722473, "learning_rate": 4.08728332933444e-06, "loss": 0.5086, "step": 1576 }, { "epoch": 1.7662434652725914, "grad_norm": 0.8228726387023926, "learning_rate": 4.086127703545618e-06, "loss": 0.5573, "step": 1577 }, { "epoch": 1.7673637042569081, "grad_norm": 0.8214651346206665, "learning_rate": 4.084971510227286e-06, "loss": 0.5533, "step": 1578 }, { "epoch": 1.768483943241225, "grad_norm": 0.8368930220603943, "learning_rate": 4.08381474979314e-06, "loss": 0.5333, "step": 1579 }, { "epoch": 1.7696041822255415, "grad_norm": 0.8381990194320679, "learning_rate": 4.082657422657079e-06, "loss": 0.5473, "step": 1580 }, { "epoch": 1.770724421209858, "grad_norm": 0.796229362487793, "learning_rate": 4.0814995292332035e-06, "loss": 0.5128, "step": 1581 }, { "epoch": 1.7718446601941746, "grad_norm": 0.8201373815536499, "learning_rate": 4.080341069935817e-06, "loss": 0.5469, "step": 1582 }, { "epoch": 1.7729648991784914, "grad_norm": 0.8479568958282471, "learning_rate": 4.079182045179425e-06, "loss": 0.5328, "step": 1583 }, { "epoch": 1.7740851381628082, "grad_norm": 0.87519371509552, "learning_rate": 4.078022455378738e-06, "loss": 0.5291, "step": 1584 }, { "epoch": 1.7752053771471248, "grad_norm": 0.8594712018966675, "learning_rate": 4.076862300948665e-06, "loss": 0.5579, "step": 1585 }, { "epoch": 1.7763256161314414, "grad_norm": 0.8597174286842346, "learning_rate": 4.075701582304321e-06, "loss": 0.5325, "step": 1586 }, { "epoch": 1.777445855115758, "grad_norm": 0.7930446863174438, "learning_rate": 4.074540299861018e-06, "loss": 0.53, "step": 1587 }, { "epoch": 1.7785660941000747, "grad_norm": 0.8580162525177002, "learning_rate": 4.073378454034273e-06, "loss": 0.5043, "step": 1588 }, { "epoch": 1.7796863330843915, "grad_norm": 0.8035150170326233, "learning_rate": 4.0722160452398054e-06, "loss": 0.546, "step": 1589 }, { "epoch": 1.780806572068708, "grad_norm": 0.8199040293693542, "learning_rate": 4.0710530738935336e-06, "loss": 0.5545, "step": 1590 }, { "epoch": 1.7819268110530246, "grad_norm": 0.8304824829101562, "learning_rate": 4.069889540411579e-06, "loss": 0.5173, "step": 1591 }, { "epoch": 1.7830470500373412, "grad_norm": 0.8335815072059631, "learning_rate": 4.068725445210263e-06, "loss": 0.5091, "step": 1592 }, { "epoch": 1.784167289021658, "grad_norm": 0.8112631440162659, "learning_rate": 4.067560788706107e-06, "loss": 0.5397, "step": 1593 }, { "epoch": 1.7852875280059746, "grad_norm": 0.8443027138710022, "learning_rate": 4.066395571315837e-06, "loss": 0.5341, "step": 1594 }, { "epoch": 1.7864077669902914, "grad_norm": 0.8510046005249023, "learning_rate": 4.065229793456377e-06, "loss": 0.5669, "step": 1595 }, { "epoch": 1.787528005974608, "grad_norm": 0.8445265889167786, "learning_rate": 4.0640634555448496e-06, "loss": 0.5349, "step": 1596 }, { "epoch": 1.7886482449589245, "grad_norm": 0.8498575687408447, "learning_rate": 4.062896557998582e-06, "loss": 0.5549, "step": 1597 }, { "epoch": 1.789768483943241, "grad_norm": 0.8104247450828552, "learning_rate": 4.0617291012351e-06, "loss": 0.507, "step": 1598 }, { "epoch": 1.7908887229275579, "grad_norm": 0.7849128842353821, "learning_rate": 4.060561085672128e-06, "loss": 0.5209, "step": 1599 }, { "epoch": 1.7920089619118746, "grad_norm": 0.8311539888381958, "learning_rate": 4.059392511727592e-06, "loss": 0.5432, "step": 1600 }, { "epoch": 1.7931292008961912, "grad_norm": 0.8311768174171448, "learning_rate": 4.0582233798196185e-06, "loss": 0.5458, "step": 1601 }, { "epoch": 1.7942494398805078, "grad_norm": 0.8668813705444336, "learning_rate": 4.057053690366531e-06, "loss": 0.5252, "step": 1602 }, { "epoch": 1.7953696788648243, "grad_norm": 0.8628605604171753, "learning_rate": 4.0558834437868536e-06, "loss": 0.5246, "step": 1603 }, { "epoch": 1.7964899178491411, "grad_norm": 0.8353387117385864, "learning_rate": 4.054712640499312e-06, "loss": 0.5666, "step": 1604 }, { "epoch": 1.797610156833458, "grad_norm": 0.8165217638015747, "learning_rate": 4.053541280922828e-06, "loss": 0.5054, "step": 1605 }, { "epoch": 1.7987303958177745, "grad_norm": 0.8124107718467712, "learning_rate": 4.052369365476524e-06, "loss": 0.5548, "step": 1606 }, { "epoch": 1.799850634802091, "grad_norm": 0.8459861874580383, "learning_rate": 4.051196894579721e-06, "loss": 0.5398, "step": 1607 }, { "epoch": 1.8009708737864076, "grad_norm": 0.8248313069343567, "learning_rate": 4.050023868651938e-06, "loss": 0.5538, "step": 1608 }, { "epoch": 1.8020911127707244, "grad_norm": 0.8126117587089539, "learning_rate": 4.048850288112895e-06, "loss": 0.5538, "step": 1609 }, { "epoch": 1.8032113517550412, "grad_norm": 0.8366143107414246, "learning_rate": 4.047676153382506e-06, "loss": 0.495, "step": 1610 }, { "epoch": 1.8043315907393578, "grad_norm": 0.7833600044250488, "learning_rate": 4.046501464880888e-06, "loss": 0.5553, "step": 1611 }, { "epoch": 1.8054518297236744, "grad_norm": 0.8468241095542908, "learning_rate": 4.045326223028355e-06, "loss": 0.5166, "step": 1612 }, { "epoch": 1.806572068707991, "grad_norm": 0.8318121433258057, "learning_rate": 4.044150428245416e-06, "loss": 0.5451, "step": 1613 }, { "epoch": 1.8076923076923077, "grad_norm": 0.852816641330719, "learning_rate": 4.042974080952782e-06, "loss": 0.561, "step": 1614 }, { "epoch": 1.8088125466766245, "grad_norm": 0.8474749326705933, "learning_rate": 4.041797181571358e-06, "loss": 0.5503, "step": 1615 }, { "epoch": 1.809932785660941, "grad_norm": 0.8417901992797852, "learning_rate": 4.040619730522249e-06, "loss": 0.5342, "step": 1616 }, { "epoch": 1.8110530246452576, "grad_norm": 0.791199266910553, "learning_rate": 4.039441728226757e-06, "loss": 0.5099, "step": 1617 }, { "epoch": 1.8121732636295742, "grad_norm": 0.8117905259132385, "learning_rate": 4.0382631751063804e-06, "loss": 0.5572, "step": 1618 }, { "epoch": 1.813293502613891, "grad_norm": 0.8146982789039612, "learning_rate": 4.037084071582816e-06, "loss": 0.5264, "step": 1619 }, { "epoch": 1.8144137415982076, "grad_norm": 0.8424848914146423, "learning_rate": 4.035904418077955e-06, "loss": 0.5204, "step": 1620 }, { "epoch": 1.8155339805825244, "grad_norm": 0.8367023468017578, "learning_rate": 4.034724215013889e-06, "loss": 0.5185, "step": 1621 }, { "epoch": 1.816654219566841, "grad_norm": 0.8297321200370789, "learning_rate": 4.0335434628129025e-06, "loss": 0.5693, "step": 1622 }, { "epoch": 1.8177744585511575, "grad_norm": 0.8517071008682251, "learning_rate": 4.03236216189748e-06, "loss": 0.5769, "step": 1623 }, { "epoch": 1.8188946975354743, "grad_norm": 0.8563759326934814, "learning_rate": 4.031180312690301e-06, "loss": 0.5452, "step": 1624 }, { "epoch": 1.8200149365197908, "grad_norm": 0.8202133178710938, "learning_rate": 4.029997915614238e-06, "loss": 0.5263, "step": 1625 }, { "epoch": 1.8211351755041076, "grad_norm": 0.8332318663597107, "learning_rate": 4.028814971092365e-06, "loss": 0.5736, "step": 1626 }, { "epoch": 1.8222554144884242, "grad_norm": 0.8340821266174316, "learning_rate": 4.027631479547949e-06, "loss": 0.5138, "step": 1627 }, { "epoch": 1.8233756534727408, "grad_norm": 0.7971771359443665, "learning_rate": 4.026447441404452e-06, "loss": 0.5253, "step": 1628 }, { "epoch": 1.8244958924570573, "grad_norm": 0.8240051865577698, "learning_rate": 4.025262857085532e-06, "loss": 0.5102, "step": 1629 }, { "epoch": 1.8256161314413741, "grad_norm": 0.8214726448059082, "learning_rate": 4.024077727015045e-06, "loss": 0.5374, "step": 1630 }, { "epoch": 1.826736370425691, "grad_norm": 0.8141801953315735, "learning_rate": 4.02289205161704e-06, "loss": 0.5187, "step": 1631 }, { "epoch": 1.8278566094100075, "grad_norm": 0.8089074492454529, "learning_rate": 4.02170583131576e-06, "loss": 0.552, "step": 1632 }, { "epoch": 1.828976848394324, "grad_norm": 0.8477803468704224, "learning_rate": 4.020519066535645e-06, "loss": 0.5334, "step": 1633 }, { "epoch": 1.8300970873786406, "grad_norm": 0.8391149044036865, "learning_rate": 4.019331757701329e-06, "loss": 0.5253, "step": 1634 }, { "epoch": 1.8312173263629574, "grad_norm": 0.8368405103683472, "learning_rate": 4.018143905237643e-06, "loss": 0.5265, "step": 1635 }, { "epoch": 1.8323375653472742, "grad_norm": 0.8110945224761963, "learning_rate": 4.016955509569605e-06, "loss": 0.5556, "step": 1636 }, { "epoch": 1.8334578043315908, "grad_norm": 0.8260793089866638, "learning_rate": 4.015766571122438e-06, "loss": 0.5588, "step": 1637 }, { "epoch": 1.8345780433159073, "grad_norm": 0.8496139645576477, "learning_rate": 4.0145770903215525e-06, "loss": 0.5297, "step": 1638 }, { "epoch": 1.835698282300224, "grad_norm": 0.8399412035942078, "learning_rate": 4.013387067592553e-06, "loss": 0.5402, "step": 1639 }, { "epoch": 1.8368185212845407, "grad_norm": 0.8328200578689575, "learning_rate": 4.012196503361242e-06, "loss": 0.525, "step": 1640 }, { "epoch": 1.8379387602688575, "grad_norm": 0.8379107713699341, "learning_rate": 4.01100539805361e-06, "loss": 0.5741, "step": 1641 }, { "epoch": 1.839058999253174, "grad_norm": 0.8842681646347046, "learning_rate": 4.009813752095847e-06, "loss": 0.5449, "step": 1642 }, { "epoch": 1.8401792382374906, "grad_norm": 0.8259784579277039, "learning_rate": 4.008621565914332e-06, "loss": 0.545, "step": 1643 }, { "epoch": 1.8412994772218072, "grad_norm": 0.8219314813613892, "learning_rate": 4.0074288399356394e-06, "loss": 0.5463, "step": 1644 }, { "epoch": 1.842419716206124, "grad_norm": 0.8393583297729492, "learning_rate": 4.006235574586537e-06, "loss": 0.5381, "step": 1645 }, { "epoch": 1.8435399551904408, "grad_norm": 0.8115900158882141, "learning_rate": 4.005041770293985e-06, "loss": 0.5264, "step": 1646 }, { "epoch": 1.8446601941747574, "grad_norm": 0.7949982285499573, "learning_rate": 4.003847427485135e-06, "loss": 0.5305, "step": 1647 }, { "epoch": 1.845780433159074, "grad_norm": 0.8323104381561279, "learning_rate": 4.002652546587334e-06, "loss": 0.5218, "step": 1648 }, { "epoch": 1.8469006721433905, "grad_norm": 0.8135440349578857, "learning_rate": 4.001457128028118e-06, "loss": 0.5555, "step": 1649 }, { "epoch": 1.8480209111277073, "grad_norm": 0.8250274062156677, "learning_rate": 4.00026117223522e-06, "loss": 0.5608, "step": 1650 }, { "epoch": 1.8491411501120238, "grad_norm": 0.8387907147407532, "learning_rate": 3.999064679636564e-06, "loss": 0.5507, "step": 1651 }, { "epoch": 1.8502613890963406, "grad_norm": 0.8458473682403564, "learning_rate": 3.997867650660261e-06, "loss": 0.5633, "step": 1652 }, { "epoch": 1.8513816280806572, "grad_norm": 0.8356611132621765, "learning_rate": 3.99667008573462e-06, "loss": 0.5467, "step": 1653 }, { "epoch": 1.8525018670649738, "grad_norm": 0.8319884538650513, "learning_rate": 3.99547198528814e-06, "loss": 0.5245, "step": 1654 }, { "epoch": 1.8536221060492906, "grad_norm": 0.8177763223648071, "learning_rate": 3.99427334974951e-06, "loss": 0.5418, "step": 1655 }, { "epoch": 1.8547423450336071, "grad_norm": 0.8282372951507568, "learning_rate": 3.9930741795476114e-06, "loss": 0.5273, "step": 1656 }, { "epoch": 1.855862584017924, "grad_norm": 0.822182297706604, "learning_rate": 3.991874475111518e-06, "loss": 0.5441, "step": 1657 }, { "epoch": 1.8569828230022405, "grad_norm": 0.8694227337837219, "learning_rate": 3.990674236870494e-06, "loss": 0.5492, "step": 1658 }, { "epoch": 1.858103061986557, "grad_norm": 0.8233626484870911, "learning_rate": 3.989473465253995e-06, "loss": 0.5377, "step": 1659 }, { "epoch": 1.8592233009708736, "grad_norm": 0.8524294495582581, "learning_rate": 3.988272160691665e-06, "loss": 0.5188, "step": 1660 }, { "epoch": 1.8603435399551904, "grad_norm": 0.8165991306304932, "learning_rate": 3.987070323613343e-06, "loss": 0.5407, "step": 1661 }, { "epoch": 1.8614637789395072, "grad_norm": 0.8025708198547363, "learning_rate": 3.9858679544490535e-06, "loss": 0.5267, "step": 1662 }, { "epoch": 1.8625840179238238, "grad_norm": 0.7899367809295654, "learning_rate": 3.984665053629016e-06, "loss": 0.5652, "step": 1663 }, { "epoch": 1.8637042569081403, "grad_norm": 0.8292130827903748, "learning_rate": 3.983461621583638e-06, "loss": 0.5166, "step": 1664 }, { "epoch": 1.864824495892457, "grad_norm": 0.8118554949760437, "learning_rate": 3.982257658743518e-06, "loss": 0.5058, "step": 1665 }, { "epoch": 1.8659447348767737, "grad_norm": 0.8407183289527893, "learning_rate": 3.9810531655394415e-06, "loss": 0.5383, "step": 1666 }, { "epoch": 1.8670649738610905, "grad_norm": 0.8522183895111084, "learning_rate": 3.979848142402388e-06, "loss": 0.5174, "step": 1667 }, { "epoch": 1.868185212845407, "grad_norm": 0.827687680721283, "learning_rate": 3.978642589763525e-06, "loss": 0.533, "step": 1668 }, { "epoch": 1.8693054518297236, "grad_norm": 0.8289827704429626, "learning_rate": 3.977436508054207e-06, "loss": 0.5342, "step": 1669 }, { "epoch": 1.8704256908140402, "grad_norm": 0.803909957408905, "learning_rate": 3.976229897705981e-06, "loss": 0.5312, "step": 1670 }, { "epoch": 1.871545929798357, "grad_norm": 0.8095699548721313, "learning_rate": 3.975022759150584e-06, "loss": 0.4865, "step": 1671 }, { "epoch": 1.8726661687826738, "grad_norm": 0.8200787305831909, "learning_rate": 3.973815092819937e-06, "loss": 0.5401, "step": 1672 }, { "epoch": 1.8737864077669903, "grad_norm": 0.8103435635566711, "learning_rate": 3.972606899146155e-06, "loss": 0.5535, "step": 1673 }, { "epoch": 1.874906646751307, "grad_norm": 0.8428035378456116, "learning_rate": 3.9713981785615385e-06, "loss": 0.5437, "step": 1674 }, { "epoch": 1.8760268857356235, "grad_norm": 0.8183536529541016, "learning_rate": 3.970188931498578e-06, "loss": 0.5282, "step": 1675 }, { "epoch": 1.8771471247199403, "grad_norm": 0.8357205390930176, "learning_rate": 3.968979158389952e-06, "loss": 0.5431, "step": 1676 }, { "epoch": 1.878267363704257, "grad_norm": 0.8381440043449402, "learning_rate": 3.9677688596685285e-06, "loss": 0.5373, "step": 1677 }, { "epoch": 1.8793876026885736, "grad_norm": 0.8339812159538269, "learning_rate": 3.966558035767359e-06, "loss": 0.5426, "step": 1678 }, { "epoch": 1.8805078416728902, "grad_norm": 0.821755588054657, "learning_rate": 3.96534668711969e-06, "loss": 0.5035, "step": 1679 }, { "epoch": 1.8816280806572068, "grad_norm": 0.8362539410591125, "learning_rate": 3.96413481415895e-06, "loss": 0.5392, "step": 1680 }, { "epoch": 1.8827483196415236, "grad_norm": 0.8103832602500916, "learning_rate": 3.962922417318758e-06, "loss": 0.5537, "step": 1681 }, { "epoch": 1.8838685586258401, "grad_norm": 0.8064588904380798, "learning_rate": 3.961709497032918e-06, "loss": 0.5397, "step": 1682 }, { "epoch": 1.884988797610157, "grad_norm": 0.8112618923187256, "learning_rate": 3.960496053735424e-06, "loss": 0.5337, "step": 1683 }, { "epoch": 1.8861090365944735, "grad_norm": 0.8196645975112915, "learning_rate": 3.959282087860456e-06, "loss": 0.5607, "step": 1684 }, { "epoch": 1.88722927557879, "grad_norm": 0.8481451272964478, "learning_rate": 3.958067599842381e-06, "loss": 0.5439, "step": 1685 }, { "epoch": 1.8883495145631068, "grad_norm": 0.8333935141563416, "learning_rate": 3.9568525901157525e-06, "loss": 0.5695, "step": 1686 }, { "epoch": 1.8894697535474234, "grad_norm": 0.8329671621322632, "learning_rate": 3.955637059115311e-06, "loss": 0.526, "step": 1687 }, { "epoch": 1.8905899925317402, "grad_norm": 0.8062114715576172, "learning_rate": 3.954421007275984e-06, "loss": 0.5299, "step": 1688 }, { "epoch": 1.8917102315160568, "grad_norm": 0.8448646664619446, "learning_rate": 3.9532044350328825e-06, "loss": 0.5409, "step": 1689 }, { "epoch": 1.8928304705003733, "grad_norm": 0.8065194487571716, "learning_rate": 3.95198734282131e-06, "loss": 0.5319, "step": 1690 }, { "epoch": 1.89395070948469, "grad_norm": 0.8324974775314331, "learning_rate": 3.950769731076748e-06, "loss": 0.5018, "step": 1691 }, { "epoch": 1.8950709484690067, "grad_norm": 0.8186408877372742, "learning_rate": 3.949551600234871e-06, "loss": 0.5073, "step": 1692 }, { "epoch": 1.8961911874533235, "grad_norm": 0.8118941783905029, "learning_rate": 3.948332950731535e-06, "loss": 0.5357, "step": 1693 }, { "epoch": 1.89731142643764, "grad_norm": 0.7879785895347595, "learning_rate": 3.947113783002782e-06, "loss": 0.5113, "step": 1694 }, { "epoch": 1.8984316654219566, "grad_norm": 0.826366126537323, "learning_rate": 3.9458940974848415e-06, "loss": 0.5432, "step": 1695 }, { "epoch": 1.8995519044062732, "grad_norm": 0.8095139265060425, "learning_rate": 3.944673894614127e-06, "loss": 0.5322, "step": 1696 }, { "epoch": 1.90067214339059, "grad_norm": 0.8329222202301025, "learning_rate": 3.943453174827236e-06, "loss": 0.5352, "step": 1697 }, { "epoch": 1.9017923823749068, "grad_norm": 0.8235338926315308, "learning_rate": 3.942231938560953e-06, "loss": 0.5404, "step": 1698 }, { "epoch": 1.9029126213592233, "grad_norm": 0.8362364768981934, "learning_rate": 3.941010186252247e-06, "loss": 0.5373, "step": 1699 }, { "epoch": 1.90403286034354, "grad_norm": 0.8214544653892517, "learning_rate": 3.939787918338269e-06, "loss": 0.5123, "step": 1700 }, { "epoch": 1.9051530993278565, "grad_norm": 0.8045482635498047, "learning_rate": 3.938565135256359e-06, "loss": 0.4988, "step": 1701 }, { "epoch": 1.9062733383121733, "grad_norm": 0.7857670187950134, "learning_rate": 3.9373418374440354e-06, "loss": 0.524, "step": 1702 }, { "epoch": 1.90739357729649, "grad_norm": 0.84732586145401, "learning_rate": 3.936118025339007e-06, "loss": 0.5146, "step": 1703 }, { "epoch": 1.9085138162808066, "grad_norm": 0.82671058177948, "learning_rate": 3.9348936993791645e-06, "loss": 0.5369, "step": 1704 }, { "epoch": 1.9096340552651232, "grad_norm": 0.8431946039199829, "learning_rate": 3.933668860002579e-06, "loss": 0.5433, "step": 1705 }, { "epoch": 1.9107542942494398, "grad_norm": 0.8344864249229431, "learning_rate": 3.932443507647509e-06, "loss": 0.5607, "step": 1706 }, { "epoch": 1.9118745332337566, "grad_norm": 0.8002555966377258, "learning_rate": 3.9312176427523965e-06, "loss": 0.5378, "step": 1707 }, { "epoch": 1.9129947722180733, "grad_norm": 0.7870469093322754, "learning_rate": 3.9299912657558656e-06, "loss": 0.5147, "step": 1708 }, { "epoch": 1.91411501120239, "grad_norm": 0.8041394948959351, "learning_rate": 3.928764377096723e-06, "loss": 0.5302, "step": 1709 }, { "epoch": 1.9152352501867065, "grad_norm": 0.8553950786590576, "learning_rate": 3.927536977213962e-06, "loss": 0.5389, "step": 1710 }, { "epoch": 1.916355489171023, "grad_norm": 0.8105883002281189, "learning_rate": 3.926309066546754e-06, "loss": 0.5367, "step": 1711 }, { "epoch": 1.9174757281553398, "grad_norm": 0.8396196961402893, "learning_rate": 3.925080645534457e-06, "loss": 0.5253, "step": 1712 }, { "epoch": 1.9185959671396564, "grad_norm": 0.8068451881408691, "learning_rate": 3.923851714616609e-06, "loss": 0.537, "step": 1713 }, { "epoch": 1.9197162061239732, "grad_norm": 0.8422108292579651, "learning_rate": 3.922622274232933e-06, "loss": 0.5659, "step": 1714 }, { "epoch": 1.9208364451082898, "grad_norm": 0.8337264657020569, "learning_rate": 3.921392324823331e-06, "loss": 0.5298, "step": 1715 }, { "epoch": 1.9219566840926063, "grad_norm": 0.8670448660850525, "learning_rate": 3.92016186682789e-06, "loss": 0.5484, "step": 1716 }, { "epoch": 1.9230769230769231, "grad_norm": 0.8477528691291809, "learning_rate": 3.918930900686878e-06, "loss": 0.5279, "step": 1717 }, { "epoch": 1.9241971620612397, "grad_norm": 0.8477908968925476, "learning_rate": 3.917699426840745e-06, "loss": 0.5633, "step": 1718 }, { "epoch": 1.9253174010455565, "grad_norm": 0.813227117061615, "learning_rate": 3.916467445730121e-06, "loss": 0.5443, "step": 1719 }, { "epoch": 1.926437640029873, "grad_norm": 0.821105420589447, "learning_rate": 3.915234957795821e-06, "loss": 0.5424, "step": 1720 }, { "epoch": 1.9275578790141896, "grad_norm": 0.8325830101966858, "learning_rate": 3.9140019634788385e-06, "loss": 0.5218, "step": 1721 }, { "epoch": 1.9286781179985062, "grad_norm": 0.8530997037887573, "learning_rate": 3.9127684632203485e-06, "loss": 0.5805, "step": 1722 }, { "epoch": 1.929798356982823, "grad_norm": 0.836625874042511, "learning_rate": 3.911534457461708e-06, "loss": 0.5117, "step": 1723 }, { "epoch": 1.9309185959671398, "grad_norm": 0.8190492391586304, "learning_rate": 3.910299946644455e-06, "loss": 0.5275, "step": 1724 }, { "epoch": 1.9320388349514563, "grad_norm": 0.8174676299095154, "learning_rate": 3.909064931210306e-06, "loss": 0.5219, "step": 1725 }, { "epoch": 1.933159073935773, "grad_norm": 0.8266441822052002, "learning_rate": 3.907829411601161e-06, "loss": 0.532, "step": 1726 }, { "epoch": 1.9342793129200895, "grad_norm": 0.8342094421386719, "learning_rate": 3.906593388259098e-06, "loss": 0.5507, "step": 1727 }, { "epoch": 1.9353995519044063, "grad_norm": 0.8714757561683655, "learning_rate": 3.905356861626377e-06, "loss": 0.5371, "step": 1728 }, { "epoch": 1.936519790888723, "grad_norm": 0.8320139050483704, "learning_rate": 3.904119832145437e-06, "loss": 0.5143, "step": 1729 }, { "epoch": 1.9376400298730396, "grad_norm": 0.7936547994613647, "learning_rate": 3.902882300258898e-06, "loss": 0.551, "step": 1730 }, { "epoch": 1.9387602688573562, "grad_norm": 0.8392663598060608, "learning_rate": 3.9016442664095585e-06, "loss": 0.558, "step": 1731 }, { "epoch": 1.9398805078416728, "grad_norm": 0.8122281432151794, "learning_rate": 3.900405731040397e-06, "loss": 0.5134, "step": 1732 }, { "epoch": 1.9410007468259896, "grad_norm": 0.8271510601043701, "learning_rate": 3.8991666945945735e-06, "loss": 0.5211, "step": 1733 }, { "epoch": 1.9421209858103063, "grad_norm": 0.8124710321426392, "learning_rate": 3.897927157515423e-06, "loss": 0.5532, "step": 1734 }, { "epoch": 1.943241224794623, "grad_norm": 0.8266910314559937, "learning_rate": 3.896687120246462e-06, "loss": 0.5363, "step": 1735 }, { "epoch": 1.9443614637789395, "grad_norm": 0.9358043074607849, "learning_rate": 3.895446583231387e-06, "loss": 0.5286, "step": 1736 }, { "epoch": 1.945481702763256, "grad_norm": 0.8380877375602722, "learning_rate": 3.8942055469140726e-06, "loss": 0.5401, "step": 1737 }, { "epoch": 1.9466019417475728, "grad_norm": 0.820033073425293, "learning_rate": 3.892964011738571e-06, "loss": 0.5398, "step": 1738 }, { "epoch": 1.9477221807318896, "grad_norm": 0.8377394676208496, "learning_rate": 3.891721978149115e-06, "loss": 0.5261, "step": 1739 }, { "epoch": 1.9488424197162062, "grad_norm": 0.8230284452438354, "learning_rate": 3.890479446590113e-06, "loss": 0.5449, "step": 1740 }, { "epoch": 1.9499626587005228, "grad_norm": 0.8403946757316589, "learning_rate": 3.889236417506153e-06, "loss": 0.5317, "step": 1741 }, { "epoch": 1.9510828976848393, "grad_norm": 0.8075201511383057, "learning_rate": 3.887992891342002e-06, "loss": 0.5229, "step": 1742 }, { "epoch": 1.9522031366691561, "grad_norm": 0.8129234313964844, "learning_rate": 3.886748868542604e-06, "loss": 0.533, "step": 1743 }, { "epoch": 1.9533233756534727, "grad_norm": 0.8530985713005066, "learning_rate": 3.8855043495530785e-06, "loss": 0.5253, "step": 1744 }, { "epoch": 1.9544436146377895, "grad_norm": 0.8068393468856812, "learning_rate": 3.884259334818726e-06, "loss": 0.534, "step": 1745 }, { "epoch": 1.955563853622106, "grad_norm": 0.8525707125663757, "learning_rate": 3.883013824785024e-06, "loss": 0.5254, "step": 1746 }, { "epoch": 1.9566840926064226, "grad_norm": 0.8301211595535278, "learning_rate": 3.881767819897625e-06, "loss": 0.5394, "step": 1747 }, { "epoch": 1.9578043315907394, "grad_norm": 0.8432576656341553, "learning_rate": 3.88052132060236e-06, "loss": 0.5368, "step": 1748 }, { "epoch": 1.958924570575056, "grad_norm": 0.8383322954177856, "learning_rate": 3.879274327345236e-06, "loss": 0.5672, "step": 1749 }, { "epoch": 1.9600448095593728, "grad_norm": 0.8277074098587036, "learning_rate": 3.878026840572438e-06, "loss": 0.5356, "step": 1750 }, { "epoch": 1.9611650485436893, "grad_norm": 0.8360003232955933, "learning_rate": 3.876778860730328e-06, "loss": 0.5381, "step": 1751 }, { "epoch": 1.962285287528006, "grad_norm": 0.8012877702713013, "learning_rate": 3.8755303882654425e-06, "loss": 0.5176, "step": 1752 }, { "epoch": 1.9634055265123225, "grad_norm": 0.811970055103302, "learning_rate": 3.874281423624495e-06, "loss": 0.5243, "step": 1753 }, { "epoch": 1.9645257654966393, "grad_norm": 0.8069865107536316, "learning_rate": 3.873031967254375e-06, "loss": 0.5329, "step": 1754 }, { "epoch": 1.965646004480956, "grad_norm": 0.8421149253845215, "learning_rate": 3.871782019602148e-06, "loss": 0.4976, "step": 1755 }, { "epoch": 1.9667662434652726, "grad_norm": 0.7935910224914551, "learning_rate": 3.870531581115058e-06, "loss": 0.4977, "step": 1756 }, { "epoch": 1.9678864824495892, "grad_norm": 0.7953087091445923, "learning_rate": 3.86928065224052e-06, "loss": 0.5169, "step": 1757 }, { "epoch": 1.9690067214339058, "grad_norm": 0.8351732492446899, "learning_rate": 3.868029233426127e-06, "loss": 0.5329, "step": 1758 }, { "epoch": 1.9701269604182226, "grad_norm": 0.8786207437515259, "learning_rate": 3.8667773251196466e-06, "loss": 0.5645, "step": 1759 }, { "epoch": 1.9712471994025393, "grad_norm": 0.8424807190895081, "learning_rate": 3.865524927769023e-06, "loss": 0.5236, "step": 1760 }, { "epoch": 1.972367438386856, "grad_norm": 0.8212794661521912, "learning_rate": 3.8642720418223725e-06, "loss": 0.5448, "step": 1761 }, { "epoch": 1.9734876773711725, "grad_norm": 0.8219057321548462, "learning_rate": 3.863018667727989e-06, "loss": 0.5176, "step": 1762 }, { "epoch": 1.974607916355489, "grad_norm": 0.8447268009185791, "learning_rate": 3.86176480593434e-06, "loss": 0.5134, "step": 1763 }, { "epoch": 1.9757281553398058, "grad_norm": 0.8190571665763855, "learning_rate": 3.8605104568900685e-06, "loss": 0.5135, "step": 1764 }, { "epoch": 1.9768483943241226, "grad_norm": 0.8249821662902832, "learning_rate": 3.859255621043989e-06, "loss": 0.527, "step": 1765 }, { "epoch": 1.9779686333084392, "grad_norm": 0.805282711982727, "learning_rate": 3.8580002988450934e-06, "loss": 0.5639, "step": 1766 }, { "epoch": 1.9790888722927558, "grad_norm": 0.8726804256439209, "learning_rate": 3.8567444907425464e-06, "loss": 0.5074, "step": 1767 }, { "epoch": 1.9802091112770723, "grad_norm": 0.8451085090637207, "learning_rate": 3.855488197185685e-06, "loss": 0.5287, "step": 1768 }, { "epoch": 1.9813293502613891, "grad_norm": 0.8440846800804138, "learning_rate": 3.8542314186240224e-06, "loss": 0.5283, "step": 1769 }, { "epoch": 1.982449589245706, "grad_norm": 0.8287026286125183, "learning_rate": 3.8529741555072446e-06, "loss": 0.5188, "step": 1770 }, { "epoch": 1.9835698282300225, "grad_norm": 0.8392443656921387, "learning_rate": 3.85171640828521e-06, "loss": 0.5208, "step": 1771 }, { "epoch": 1.984690067214339, "grad_norm": 0.8401972651481628, "learning_rate": 3.8504581774079514e-06, "loss": 0.5358, "step": 1772 }, { "epoch": 1.9858103061986556, "grad_norm": 0.8330747485160828, "learning_rate": 3.849199463325674e-06, "loss": 0.5419, "step": 1773 }, { "epoch": 1.9869305451829724, "grad_norm": 0.8241636753082275, "learning_rate": 3.847940266488755e-06, "loss": 0.5277, "step": 1774 }, { "epoch": 1.988050784167289, "grad_norm": 0.868881344795227, "learning_rate": 3.846680587347747e-06, "loss": 0.5098, "step": 1775 }, { "epoch": 1.9891710231516058, "grad_norm": 0.7896348237991333, "learning_rate": 3.845420426353371e-06, "loss": 0.5078, "step": 1776 }, { "epoch": 1.9902912621359223, "grad_norm": 0.8297612071037292, "learning_rate": 3.844159783956527e-06, "loss": 0.5341, "step": 1777 }, { "epoch": 1.991411501120239, "grad_norm": 0.828650176525116, "learning_rate": 3.84289866060828e-06, "loss": 0.54, "step": 1778 }, { "epoch": 1.9925317401045557, "grad_norm": 0.8304623961448669, "learning_rate": 3.84163705675987e-06, "loss": 0.5255, "step": 1779 }, { "epoch": 1.9936519790888723, "grad_norm": 0.7775478959083557, "learning_rate": 3.840374972862712e-06, "loss": 0.5496, "step": 1780 }, { "epoch": 1.994772218073189, "grad_norm": 0.844093382358551, "learning_rate": 3.839112409368389e-06, "loss": 0.5448, "step": 1781 }, { "epoch": 1.9958924570575056, "grad_norm": 0.8264373540878296, "learning_rate": 3.837849366728653e-06, "loss": 0.5093, "step": 1782 }, { "epoch": 1.9970126960418222, "grad_norm": 0.8227883577346802, "learning_rate": 3.8365858453954365e-06, "loss": 0.5544, "step": 1783 }, { "epoch": 1.9981329350261388, "grad_norm": 0.8628005385398865, "learning_rate": 3.835321845820834e-06, "loss": 0.5297, "step": 1784 }, { "epoch": 1.9992531740104555, "grad_norm": 0.8216269612312317, "learning_rate": 3.834057368457117e-06, "loss": 0.5228, "step": 1785 }, { "epoch": 2.0, "grad_norm": 0.9554227590560913, "learning_rate": 3.832792413756724e-06, "loss": 0.5473, "step": 1786 }, { "epoch": 2.0011202389843166, "grad_norm": 0.9830635786056519, "learning_rate": 3.831526982172269e-06, "loss": 0.4768, "step": 1787 }, { "epoch": 2.002240477968633, "grad_norm": 0.8145297169685364, "learning_rate": 3.8302610741565304e-06, "loss": 0.4791, "step": 1788 }, { "epoch": 2.00336071695295, "grad_norm": 0.8074555993080139, "learning_rate": 3.828994690162463e-06, "loss": 0.5028, "step": 1789 }, { "epoch": 2.0044809559372667, "grad_norm": 0.8487861156463623, "learning_rate": 3.827727830643188e-06, "loss": 0.5146, "step": 1790 }, { "epoch": 2.0056011949215833, "grad_norm": 0.8484593629837036, "learning_rate": 3.826460496051999e-06, "loss": 0.5056, "step": 1791 }, { "epoch": 2.0067214339059, "grad_norm": 0.8377561569213867, "learning_rate": 3.825192686842358e-06, "loss": 0.5094, "step": 1792 }, { "epoch": 2.0078416728902164, "grad_norm": 0.8648749589920044, "learning_rate": 3.823924403467899e-06, "loss": 0.5108, "step": 1793 }, { "epoch": 2.0089619118745334, "grad_norm": 0.8434236645698547, "learning_rate": 3.822655646382422e-06, "loss": 0.5219, "step": 1794 }, { "epoch": 2.01008215085885, "grad_norm": 0.8540623784065247, "learning_rate": 3.8213864160399e-06, "loss": 0.498, "step": 1795 }, { "epoch": 2.0112023898431666, "grad_norm": 0.8224656581878662, "learning_rate": 3.820116712894473e-06, "loss": 0.5011, "step": 1796 }, { "epoch": 2.012322628827483, "grad_norm": 0.8320565223693848, "learning_rate": 3.818846537400454e-06, "loss": 0.5045, "step": 1797 }, { "epoch": 2.0134428678117997, "grad_norm": 0.8107923269271851, "learning_rate": 3.8175758900123185e-06, "loss": 0.5197, "step": 1798 }, { "epoch": 2.0145631067961167, "grad_norm": 0.8018215298652649, "learning_rate": 3.8163047711847165e-06, "loss": 0.4832, "step": 1799 }, { "epoch": 2.0156833457804333, "grad_norm": 0.8177446126937866, "learning_rate": 3.815033181372466e-06, "loss": 0.4916, "step": 1800 }, { "epoch": 2.01680358476475, "grad_norm": 0.8444321155548096, "learning_rate": 3.813761121030549e-06, "loss": 0.4911, "step": 1801 }, { "epoch": 2.0179238237490664, "grad_norm": 0.8429933190345764, "learning_rate": 3.812488590614122e-06, "loss": 0.5117, "step": 1802 }, { "epoch": 2.019044062733383, "grad_norm": 0.8364393711090088, "learning_rate": 3.8112155905785053e-06, "loss": 0.5166, "step": 1803 }, { "epoch": 2.0201643017176996, "grad_norm": 0.8408747315406799, "learning_rate": 3.80994212137919e-06, "loss": 0.485, "step": 1804 }, { "epoch": 2.0212845407020166, "grad_norm": 0.8304954767227173, "learning_rate": 3.8086681834718333e-06, "loss": 0.4929, "step": 1805 }, { "epoch": 2.022404779686333, "grad_norm": 0.8179794549942017, "learning_rate": 3.8073937773122586e-06, "loss": 0.4917, "step": 1806 }, { "epoch": 2.0235250186706497, "grad_norm": 0.8311576247215271, "learning_rate": 3.8061189033564623e-06, "loss": 0.4908, "step": 1807 }, { "epoch": 2.0246452576549663, "grad_norm": 0.8560750484466553, "learning_rate": 3.804843562060603e-06, "loss": 0.5049, "step": 1808 }, { "epoch": 2.025765496639283, "grad_norm": 0.8328870534896851, "learning_rate": 3.803567753881007e-06, "loss": 0.506, "step": 1809 }, { "epoch": 2.0268857356236, "grad_norm": 0.8351078629493713, "learning_rate": 3.8022914792741724e-06, "loss": 0.487, "step": 1810 }, { "epoch": 2.0280059746079164, "grad_norm": 0.8184784650802612, "learning_rate": 3.801014738696758e-06, "loss": 0.4948, "step": 1811 }, { "epoch": 2.029126213592233, "grad_norm": 0.8258534073829651, "learning_rate": 3.7997375326055917e-06, "loss": 0.4944, "step": 1812 }, { "epoch": 2.0302464525765496, "grad_norm": 0.8394405245780945, "learning_rate": 3.7984598614576707e-06, "loss": 0.5008, "step": 1813 }, { "epoch": 2.031366691560866, "grad_norm": 0.8758392333984375, "learning_rate": 3.797181725710155e-06, "loss": 0.5062, "step": 1814 }, { "epoch": 2.032486930545183, "grad_norm": 0.8151667714118958, "learning_rate": 3.7959031258203715e-06, "loss": 0.5156, "step": 1815 }, { "epoch": 2.0336071695294997, "grad_norm": 0.837206244468689, "learning_rate": 3.7946240622458135e-06, "loss": 0.5061, "step": 1816 }, { "epoch": 2.0347274085138163, "grad_norm": 0.8452504277229309, "learning_rate": 3.793344535444142e-06, "loss": 0.492, "step": 1817 }, { "epoch": 2.035847647498133, "grad_norm": 0.8355044722557068, "learning_rate": 3.792064545873182e-06, "loss": 0.5304, "step": 1818 }, { "epoch": 2.0369678864824494, "grad_norm": 0.8552300930023193, "learning_rate": 3.7907840939909222e-06, "loss": 0.5281, "step": 1819 }, { "epoch": 2.0380881254667664, "grad_norm": 0.8608221411705017, "learning_rate": 3.789503180255521e-06, "loss": 0.4942, "step": 1820 }, { "epoch": 2.039208364451083, "grad_norm": 0.8243234753608704, "learning_rate": 3.7882218051252984e-06, "loss": 0.4756, "step": 1821 }, { "epoch": 2.0403286034353996, "grad_norm": 0.8148723244667053, "learning_rate": 3.7869399690587427e-06, "loss": 0.4788, "step": 1822 }, { "epoch": 2.041448842419716, "grad_norm": 0.8518677949905396, "learning_rate": 3.7856576725145033e-06, "loss": 0.5115, "step": 1823 }, { "epoch": 2.0425690814040327, "grad_norm": 0.8011455535888672, "learning_rate": 3.7843749159513975e-06, "loss": 0.4773, "step": 1824 }, { "epoch": 2.0436893203883497, "grad_norm": 0.8626595735549927, "learning_rate": 3.7830916998284074e-06, "loss": 0.5061, "step": 1825 }, { "epoch": 2.0448095593726663, "grad_norm": 0.8581843972206116, "learning_rate": 3.781808024604675e-06, "loss": 0.4922, "step": 1826 }, { "epoch": 2.045929798356983, "grad_norm": 0.8505298495292664, "learning_rate": 3.7805238907395124e-06, "loss": 0.4874, "step": 1827 }, { "epoch": 2.0470500373412994, "grad_norm": 0.8307416439056396, "learning_rate": 3.7792392986923925e-06, "loss": 0.5099, "step": 1828 }, { "epoch": 2.048170276325616, "grad_norm": 0.895459771156311, "learning_rate": 3.7779542489229526e-06, "loss": 0.4976, "step": 1829 }, { "epoch": 2.049290515309933, "grad_norm": 0.8365398645401001, "learning_rate": 3.7766687418909954e-06, "loss": 0.5027, "step": 1830 }, { "epoch": 2.0504107542942496, "grad_norm": 0.8353927731513977, "learning_rate": 3.775382778056484e-06, "loss": 0.5216, "step": 1831 }, { "epoch": 2.051530993278566, "grad_norm": 0.829200029373169, "learning_rate": 3.7740963578795482e-06, "loss": 0.5063, "step": 1832 }, { "epoch": 2.0526512322628827, "grad_norm": 0.8570011258125305, "learning_rate": 3.7728094818204786e-06, "loss": 0.4999, "step": 1833 }, { "epoch": 2.0537714712471993, "grad_norm": 0.8207477927207947, "learning_rate": 3.7715221503397304e-06, "loss": 0.4924, "step": 1834 }, { "epoch": 2.054891710231516, "grad_norm": 0.8230429291725159, "learning_rate": 3.770234363897922e-06, "loss": 0.4989, "step": 1835 }, { "epoch": 2.056011949215833, "grad_norm": 0.8623048067092896, "learning_rate": 3.768946122955833e-06, "loss": 0.481, "step": 1836 }, { "epoch": 2.0571321882001494, "grad_norm": 0.8201838731765747, "learning_rate": 3.767657427974407e-06, "loss": 0.5133, "step": 1837 }, { "epoch": 2.058252427184466, "grad_norm": 0.8305184841156006, "learning_rate": 3.7663682794147504e-06, "loss": 0.5046, "step": 1838 }, { "epoch": 2.0593726661687826, "grad_norm": 0.8417003750801086, "learning_rate": 3.7650786777381306e-06, "loss": 0.4916, "step": 1839 }, { "epoch": 2.060492905153099, "grad_norm": 0.8460232615470886, "learning_rate": 3.763788623405977e-06, "loss": 0.497, "step": 1840 }, { "epoch": 2.061613144137416, "grad_norm": 0.8541492223739624, "learning_rate": 3.762498116879882e-06, "loss": 0.4948, "step": 1841 }, { "epoch": 2.0627333831217327, "grad_norm": 0.8219219446182251, "learning_rate": 3.7612071586216e-06, "loss": 0.4925, "step": 1842 }, { "epoch": 2.0638536221060493, "grad_norm": 0.8921184539794922, "learning_rate": 3.759915749093045e-06, "loss": 0.4975, "step": 1843 }, { "epoch": 2.064973861090366, "grad_norm": 0.8499891757965088, "learning_rate": 3.7586238887562964e-06, "loss": 0.4982, "step": 1844 }, { "epoch": 2.0660941000746824, "grad_norm": 0.8204718828201294, "learning_rate": 3.7573315780735902e-06, "loss": 0.4877, "step": 1845 }, { "epoch": 2.0672143390589994, "grad_norm": 0.8329854011535645, "learning_rate": 3.7560388175073264e-06, "loss": 0.4804, "step": 1846 }, { "epoch": 2.068334578043316, "grad_norm": 0.8173015117645264, "learning_rate": 3.754745607520066e-06, "loss": 0.491, "step": 1847 }, { "epoch": 2.0694548170276326, "grad_norm": 0.8652282953262329, "learning_rate": 3.7534519485745292e-06, "loss": 0.4915, "step": 1848 }, { "epoch": 2.070575056011949, "grad_norm": 0.8487930297851562, "learning_rate": 3.7521578411335984e-06, "loss": 0.5154, "step": 1849 }, { "epoch": 2.0716952949962657, "grad_norm": 0.8414106369018555, "learning_rate": 3.7508632856603156e-06, "loss": 0.5028, "step": 1850 }, { "epoch": 2.0728155339805827, "grad_norm": 0.8425125479698181, "learning_rate": 3.749568282617884e-06, "loss": 0.4982, "step": 1851 }, { "epoch": 2.0739357729648993, "grad_norm": 0.8153639435768127, "learning_rate": 3.748272832469665e-06, "loss": 0.5031, "step": 1852 }, { "epoch": 2.075056011949216, "grad_norm": 0.8913668394088745, "learning_rate": 3.7469769356791825e-06, "loss": 0.5055, "step": 1853 }, { "epoch": 2.0761762509335324, "grad_norm": 0.8388772010803223, "learning_rate": 3.745680592710118e-06, "loss": 0.499, "step": 1854 }, { "epoch": 2.077296489917849, "grad_norm": 0.8543771505355835, "learning_rate": 3.7443838040263146e-06, "loss": 0.487, "step": 1855 }, { "epoch": 2.078416728902166, "grad_norm": 0.8422806859016418, "learning_rate": 3.7430865700917735e-06, "loss": 0.4986, "step": 1856 }, { "epoch": 2.0795369678864826, "grad_norm": 0.8473921418190002, "learning_rate": 3.7417888913706556e-06, "loss": 0.5085, "step": 1857 }, { "epoch": 2.080657206870799, "grad_norm": 0.8434934020042419, "learning_rate": 3.7404907683272817e-06, "loss": 0.5284, "step": 1858 }, { "epoch": 2.0817774458551157, "grad_norm": 0.8642371892929077, "learning_rate": 3.73919220142613e-06, "loss": 0.5062, "step": 1859 }, { "epoch": 2.0828976848394323, "grad_norm": 0.8436400890350342, "learning_rate": 3.7378931911318388e-06, "loss": 0.4993, "step": 1860 }, { "epoch": 2.0840179238237493, "grad_norm": 0.8185716271400452, "learning_rate": 3.7365937379092043e-06, "loss": 0.4973, "step": 1861 }, { "epoch": 2.085138162808066, "grad_norm": 0.8414385914802551, "learning_rate": 3.7352938422231817e-06, "loss": 0.5059, "step": 1862 }, { "epoch": 2.0862584017923824, "grad_norm": 0.8180663585662842, "learning_rate": 3.7339935045388844e-06, "loss": 0.5022, "step": 1863 }, { "epoch": 2.087378640776699, "grad_norm": 0.8477697968482971, "learning_rate": 3.7326927253215837e-06, "loss": 0.4917, "step": 1864 }, { "epoch": 2.0884988797610156, "grad_norm": 0.8425041437149048, "learning_rate": 3.73139150503671e-06, "loss": 0.5097, "step": 1865 }, { "epoch": 2.089619118745332, "grad_norm": 0.8433413505554199, "learning_rate": 3.730089844149849e-06, "loss": 0.5053, "step": 1866 }, { "epoch": 2.090739357729649, "grad_norm": 0.8344539403915405, "learning_rate": 3.7287877431267474e-06, "loss": 0.4825, "step": 1867 }, { "epoch": 2.0918595967139657, "grad_norm": 0.8527227640151978, "learning_rate": 3.727485202433306e-06, "loss": 0.4921, "step": 1868 }, { "epoch": 2.0929798356982823, "grad_norm": 0.8533576130867004, "learning_rate": 3.7261822225355854e-06, "loss": 0.4751, "step": 1869 }, { "epoch": 2.094100074682599, "grad_norm": 0.8286004662513733, "learning_rate": 3.7248788038998022e-06, "loss": 0.4964, "step": 1870 }, { "epoch": 2.0952203136669154, "grad_norm": 0.8334503173828125, "learning_rate": 3.723574946992331e-06, "loss": 0.4918, "step": 1871 }, { "epoch": 2.0963405526512324, "grad_norm": 0.8255897760391235, "learning_rate": 3.7222706522797023e-06, "loss": 0.482, "step": 1872 }, { "epoch": 2.097460791635549, "grad_norm": 0.8529343008995056, "learning_rate": 3.7209659202286024e-06, "loss": 0.5181, "step": 1873 }, { "epoch": 2.0985810306198656, "grad_norm": 0.9045861959457397, "learning_rate": 3.7196607513058756e-06, "loss": 0.4878, "step": 1874 }, { "epoch": 2.099701269604182, "grad_norm": 0.8299806714057922, "learning_rate": 3.7183551459785235e-06, "loss": 0.5199, "step": 1875 }, { "epoch": 2.1008215085884987, "grad_norm": 0.8488248586654663, "learning_rate": 3.7170491047137e-06, "loss": 0.507, "step": 1876 }, { "epoch": 2.1019417475728157, "grad_norm": 0.8219304084777832, "learning_rate": 3.7157426279787195e-06, "loss": 0.5109, "step": 1877 }, { "epoch": 2.1030619865571323, "grad_norm": 0.8332011103630066, "learning_rate": 3.7144357162410494e-06, "loss": 0.5054, "step": 1878 }, { "epoch": 2.104182225541449, "grad_norm": 0.842372715473175, "learning_rate": 3.7131283699683128e-06, "loss": 0.5002, "step": 1879 }, { "epoch": 2.1053024645257654, "grad_norm": 0.8399741649627686, "learning_rate": 3.711820589628289e-06, "loss": 0.4907, "step": 1880 }, { "epoch": 2.106422703510082, "grad_norm": 0.8838251233100891, "learning_rate": 3.7105123756889126e-06, "loss": 0.518, "step": 1881 }, { "epoch": 2.107542942494399, "grad_norm": 0.8261753916740417, "learning_rate": 3.7092037286182747e-06, "loss": 0.4876, "step": 1882 }, { "epoch": 2.1086631814787156, "grad_norm": 0.8443511128425598, "learning_rate": 3.707894648884618e-06, "loss": 0.489, "step": 1883 }, { "epoch": 2.109783420463032, "grad_norm": 0.8565778732299805, "learning_rate": 3.706585136956344e-06, "loss": 0.5185, "step": 1884 }, { "epoch": 2.1109036594473487, "grad_norm": 0.8526867628097534, "learning_rate": 3.705275193302005e-06, "loss": 0.5285, "step": 1885 }, { "epoch": 2.1120238984316653, "grad_norm": 0.8625830411911011, "learning_rate": 3.70396481839031e-06, "loss": 0.4955, "step": 1886 }, { "epoch": 2.1131441374159823, "grad_norm": 0.8518421053886414, "learning_rate": 3.7026540126901224e-06, "loss": 0.4968, "step": 1887 }, { "epoch": 2.114264376400299, "grad_norm": 0.8656520843505859, "learning_rate": 3.701342776670458e-06, "loss": 0.5122, "step": 1888 }, { "epoch": 2.1153846153846154, "grad_norm": 0.838792085647583, "learning_rate": 3.70003111080049e-06, "loss": 0.4866, "step": 1889 }, { "epoch": 2.116504854368932, "grad_norm": 0.8452437520027161, "learning_rate": 3.6987190155495413e-06, "loss": 0.4944, "step": 1890 }, { "epoch": 2.1176250933532486, "grad_norm": 0.8631121516227722, "learning_rate": 3.697406491387092e-06, "loss": 0.5075, "step": 1891 }, { "epoch": 2.118745332337565, "grad_norm": 0.85835200548172, "learning_rate": 3.6960935387827725e-06, "loss": 0.5016, "step": 1892 }, { "epoch": 2.119865571321882, "grad_norm": 0.8112966418266296, "learning_rate": 3.694780158206368e-06, "loss": 0.4915, "step": 1893 }, { "epoch": 2.1209858103061987, "grad_norm": 0.8134414553642273, "learning_rate": 3.6934663501278177e-06, "loss": 0.4733, "step": 1894 }, { "epoch": 2.1221060492905153, "grad_norm": 0.8541563153266907, "learning_rate": 3.6921521150172134e-06, "loss": 0.5133, "step": 1895 }, { "epoch": 2.123226288274832, "grad_norm": 0.8401772379875183, "learning_rate": 3.6908374533447976e-06, "loss": 0.5068, "step": 1896 }, { "epoch": 2.1243465272591484, "grad_norm": 0.8458466529846191, "learning_rate": 3.689522365580968e-06, "loss": 0.5044, "step": 1897 }, { "epoch": 2.1254667662434654, "grad_norm": 0.8499308824539185, "learning_rate": 3.6882068521962745e-06, "loss": 0.4814, "step": 1898 }, { "epoch": 2.126587005227782, "grad_norm": 0.8103798031806946, "learning_rate": 3.6868909136614173e-06, "loss": 0.4841, "step": 1899 }, { "epoch": 2.1277072442120986, "grad_norm": 0.8305712938308716, "learning_rate": 3.68557455044725e-06, "loss": 0.4771, "step": 1900 }, { "epoch": 2.128827483196415, "grad_norm": 0.8110742568969727, "learning_rate": 3.684257763024779e-06, "loss": 0.4984, "step": 1901 }, { "epoch": 2.1299477221807317, "grad_norm": 0.8472273945808411, "learning_rate": 3.6829405518651613e-06, "loss": 0.5081, "step": 1902 }, { "epoch": 2.1310679611650487, "grad_norm": 0.8632811307907104, "learning_rate": 3.6816229174397054e-06, "loss": 0.4873, "step": 1903 }, { "epoch": 2.1321882001493653, "grad_norm": 0.8640954494476318, "learning_rate": 3.680304860219873e-06, "loss": 0.523, "step": 1904 }, { "epoch": 2.133308439133682, "grad_norm": 0.8435152769088745, "learning_rate": 3.678986380677274e-06, "loss": 0.4995, "step": 1905 }, { "epoch": 2.1344286781179984, "grad_norm": 0.8632457852363586, "learning_rate": 3.677667479283673e-06, "loss": 0.4874, "step": 1906 }, { "epoch": 2.135548917102315, "grad_norm": 0.8460482954978943, "learning_rate": 3.676348156510983e-06, "loss": 0.5164, "step": 1907 }, { "epoch": 2.136669156086632, "grad_norm": 0.8797248601913452, "learning_rate": 3.6750284128312672e-06, "loss": 0.5137, "step": 1908 }, { "epoch": 2.1377893950709486, "grad_norm": 0.8512508273124695, "learning_rate": 3.673708248716743e-06, "loss": 0.4971, "step": 1909 }, { "epoch": 2.138909634055265, "grad_norm": 0.8335486650466919, "learning_rate": 3.6723876646397745e-06, "loss": 0.4995, "step": 1910 }, { "epoch": 2.1400298730395817, "grad_norm": 0.861346423625946, "learning_rate": 3.671066661072878e-06, "loss": 0.4872, "step": 1911 }, { "epoch": 2.1411501120238983, "grad_norm": 0.9068320393562317, "learning_rate": 3.6697452384887196e-06, "loss": 0.4879, "step": 1912 }, { "epoch": 2.1422703510082153, "grad_norm": 0.8171181082725525, "learning_rate": 3.668423397360114e-06, "loss": 0.4992, "step": 1913 }, { "epoch": 2.143390589992532, "grad_norm": 0.865473747253418, "learning_rate": 3.667101138160028e-06, "loss": 0.5057, "step": 1914 }, { "epoch": 2.1445108289768484, "grad_norm": 0.8296788334846497, "learning_rate": 3.6657784613615766e-06, "loss": 0.4897, "step": 1915 }, { "epoch": 2.145631067961165, "grad_norm": 0.8298725485801697, "learning_rate": 3.6644553674380247e-06, "loss": 0.4519, "step": 1916 }, { "epoch": 2.1467513069454816, "grad_norm": 0.8304535746574402, "learning_rate": 3.663131856862785e-06, "loss": 0.5257, "step": 1917 }, { "epoch": 2.1478715459297986, "grad_norm": 0.8580611944198608, "learning_rate": 3.661807930109422e-06, "loss": 0.4987, "step": 1918 }, { "epoch": 2.148991784914115, "grad_norm": 0.849623441696167, "learning_rate": 3.6604835876516464e-06, "loss": 0.4922, "step": 1919 }, { "epoch": 2.1501120238984317, "grad_norm": 0.8662089109420776, "learning_rate": 3.6591588299633184e-06, "loss": 0.5379, "step": 1920 }, { "epoch": 2.1512322628827483, "grad_norm": 0.8471651077270508, "learning_rate": 3.6578336575184485e-06, "loss": 0.4977, "step": 1921 }, { "epoch": 2.152352501867065, "grad_norm": 0.8559797406196594, "learning_rate": 3.656508070791194e-06, "loss": 0.514, "step": 1922 }, { "epoch": 2.153472740851382, "grad_norm": 0.8553304076194763, "learning_rate": 3.6551820702558604e-06, "loss": 0.5295, "step": 1923 }, { "epoch": 2.1545929798356984, "grad_norm": 0.8374724984169006, "learning_rate": 3.653855656386901e-06, "loss": 0.4863, "step": 1924 }, { "epoch": 2.155713218820015, "grad_norm": 0.8591656684875488, "learning_rate": 3.652528829658919e-06, "loss": 0.4846, "step": 1925 }, { "epoch": 2.1568334578043316, "grad_norm": 0.8574816584587097, "learning_rate": 3.6512015905466623e-06, "loss": 0.5228, "step": 1926 }, { "epoch": 2.157953696788648, "grad_norm": 0.8352214097976685, "learning_rate": 3.6498739395250283e-06, "loss": 0.5095, "step": 1927 }, { "epoch": 2.1590739357729647, "grad_norm": 0.8466954827308655, "learning_rate": 3.6485458770690626e-06, "loss": 0.5379, "step": 1928 }, { "epoch": 2.1601941747572817, "grad_norm": 0.8624870181083679, "learning_rate": 3.6472174036539557e-06, "loss": 0.4936, "step": 1929 }, { "epoch": 2.1613144137415983, "grad_norm": 0.828642725944519, "learning_rate": 3.645888519755047e-06, "loss": 0.4938, "step": 1930 }, { "epoch": 2.162434652725915, "grad_norm": 0.8420208692550659, "learning_rate": 3.644559225847822e-06, "loss": 0.5014, "step": 1931 }, { "epoch": 2.1635548917102314, "grad_norm": 0.8717163801193237, "learning_rate": 3.6432295224079123e-06, "loss": 0.5114, "step": 1932 }, { "epoch": 2.164675130694548, "grad_norm": 0.881081223487854, "learning_rate": 3.6418994099110967e-06, "loss": 0.4985, "step": 1933 }, { "epoch": 2.165795369678865, "grad_norm": 0.8498573899269104, "learning_rate": 3.6405688888333006e-06, "loss": 0.5017, "step": 1934 }, { "epoch": 2.1669156086631816, "grad_norm": 0.8568539619445801, "learning_rate": 3.6392379596505962e-06, "loss": 0.5221, "step": 1935 }, { "epoch": 2.168035847647498, "grad_norm": 0.8705431222915649, "learning_rate": 3.6379066228392e-06, "loss": 0.4816, "step": 1936 }, { "epoch": 2.1691560866318147, "grad_norm": 0.8458359837532043, "learning_rate": 3.6365748788754752e-06, "loss": 0.494, "step": 1937 }, { "epoch": 2.1702763256161313, "grad_norm": 0.8290570974349976, "learning_rate": 3.6352427282359316e-06, "loss": 0.5044, "step": 1938 }, { "epoch": 2.1713965646004483, "grad_norm": 0.8545880913734436, "learning_rate": 3.6339101713972227e-06, "loss": 0.5458, "step": 1939 }, { "epoch": 2.172516803584765, "grad_norm": 0.8655086755752563, "learning_rate": 3.6325772088361482e-06, "loss": 0.4895, "step": 1940 }, { "epoch": 2.1736370425690814, "grad_norm": 0.8618749976158142, "learning_rate": 3.6312438410296535e-06, "loss": 0.5221, "step": 1941 }, { "epoch": 2.174757281553398, "grad_norm": 0.8247333765029907, "learning_rate": 3.629910068454829e-06, "loss": 0.4777, "step": 1942 }, { "epoch": 2.1758775205377145, "grad_norm": 0.8565616607666016, "learning_rate": 3.6285758915889087e-06, "loss": 0.4876, "step": 1943 }, { "epoch": 2.1769977595220316, "grad_norm": 0.8307002782821655, "learning_rate": 3.627241310909271e-06, "loss": 0.4846, "step": 1944 }, { "epoch": 2.178117998506348, "grad_norm": 0.8267696499824524, "learning_rate": 3.625906326893443e-06, "loss": 0.4826, "step": 1945 }, { "epoch": 2.1792382374906647, "grad_norm": 0.8736403584480286, "learning_rate": 3.6245709400190905e-06, "loss": 0.5215, "step": 1946 }, { "epoch": 2.1803584764749813, "grad_norm": 0.8597437143325806, "learning_rate": 3.623235150764025e-06, "loss": 0.517, "step": 1947 }, { "epoch": 2.181478715459298, "grad_norm": 0.8561327457427979, "learning_rate": 3.621898959606206e-06, "loss": 0.506, "step": 1948 }, { "epoch": 2.1825989544436144, "grad_norm": 0.8596240878105164, "learning_rate": 3.620562367023731e-06, "loss": 0.5112, "step": 1949 }, { "epoch": 2.1837191934279314, "grad_norm": 0.8769569396972656, "learning_rate": 3.6192253734948447e-06, "loss": 0.5201, "step": 1950 }, { "epoch": 2.184839432412248, "grad_norm": 0.8514807224273682, "learning_rate": 3.617887979497935e-06, "loss": 0.5154, "step": 1951 }, { "epoch": 2.1859596713965646, "grad_norm": 0.8302696943283081, "learning_rate": 3.6165501855115315e-06, "loss": 0.4925, "step": 1952 }, { "epoch": 2.187079910380881, "grad_norm": 0.8395659327507019, "learning_rate": 3.6152119920143085e-06, "loss": 0.5097, "step": 1953 }, { "epoch": 2.1882001493651977, "grad_norm": 0.8565195798873901, "learning_rate": 3.613873399485081e-06, "loss": 0.5081, "step": 1954 }, { "epoch": 2.1893203883495147, "grad_norm": 0.8226524591445923, "learning_rate": 3.6125344084028108e-06, "loss": 0.4904, "step": 1955 }, { "epoch": 2.1904406273338313, "grad_norm": 0.8355268836021423, "learning_rate": 3.611195019246599e-06, "loss": 0.4955, "step": 1956 }, { "epoch": 2.191560866318148, "grad_norm": 0.8485004901885986, "learning_rate": 3.6098552324956894e-06, "loss": 0.4969, "step": 1957 }, { "epoch": 2.1926811053024644, "grad_norm": 0.8435720801353455, "learning_rate": 3.608515048629469e-06, "loss": 0.4955, "step": 1958 }, { "epoch": 2.193801344286781, "grad_norm": 0.8444412350654602, "learning_rate": 3.607174468127467e-06, "loss": 0.4994, "step": 1959 }, { "epoch": 2.194921583271098, "grad_norm": 0.886957585811615, "learning_rate": 3.605833491469354e-06, "loss": 0.4965, "step": 1960 }, { "epoch": 2.1960418222554146, "grad_norm": 0.9054564237594604, "learning_rate": 3.6044921191349415e-06, "loss": 0.5261, "step": 1961 }, { "epoch": 2.197162061239731, "grad_norm": 0.8841832876205444, "learning_rate": 3.603150351604185e-06, "loss": 0.4987, "step": 1962 }, { "epoch": 2.1982823002240477, "grad_norm": 0.8463117480278015, "learning_rate": 3.601808189357179e-06, "loss": 0.4811, "step": 1963 }, { "epoch": 2.1994025392083643, "grad_norm": 0.8431236147880554, "learning_rate": 3.60046563287416e-06, "loss": 0.4929, "step": 1964 }, { "epoch": 2.2005227781926813, "grad_norm": 0.8763803243637085, "learning_rate": 3.599122682635507e-06, "loss": 0.5039, "step": 1965 }, { "epoch": 2.201643017176998, "grad_norm": 0.8361983895301819, "learning_rate": 3.5977793391217375e-06, "loss": 0.4871, "step": 1966 }, { "epoch": 2.2027632561613144, "grad_norm": 0.8294758796691895, "learning_rate": 3.5964356028135105e-06, "loss": 0.5083, "step": 1967 }, { "epoch": 2.203883495145631, "grad_norm": 0.8522728085517883, "learning_rate": 3.5950914741916267e-06, "loss": 0.5358, "step": 1968 }, { "epoch": 2.2050037341299475, "grad_norm": 0.8258055448532104, "learning_rate": 3.593746953737026e-06, "loss": 0.491, "step": 1969 }, { "epoch": 2.2061239731142646, "grad_norm": 0.8740357756614685, "learning_rate": 3.592402041930789e-06, "loss": 0.4866, "step": 1970 }, { "epoch": 2.207244212098581, "grad_norm": 0.8416232466697693, "learning_rate": 3.5910567392541362e-06, "loss": 0.4606, "step": 1971 }, { "epoch": 2.2083644510828977, "grad_norm": 0.8606379628181458, "learning_rate": 3.589711046188428e-06, "loss": 0.5079, "step": 1972 }, { "epoch": 2.2094846900672143, "grad_norm": 0.8743149042129517, "learning_rate": 3.5883649632151645e-06, "loss": 0.4929, "step": 1973 }, { "epoch": 2.210604929051531, "grad_norm": 0.8415257334709167, "learning_rate": 3.5870184908159846e-06, "loss": 0.4865, "step": 1974 }, { "epoch": 2.211725168035848, "grad_norm": 0.8407385945320129, "learning_rate": 3.585671629472668e-06, "loss": 0.4843, "step": 1975 }, { "epoch": 2.2128454070201644, "grad_norm": 0.8784340620040894, "learning_rate": 3.584324379667132e-06, "loss": 0.4937, "step": 1976 }, { "epoch": 2.213965646004481, "grad_norm": 0.8729920983314514, "learning_rate": 3.5829767418814344e-06, "loss": 0.5201, "step": 1977 }, { "epoch": 2.2150858849887975, "grad_norm": 0.8514240980148315, "learning_rate": 3.5816287165977703e-06, "loss": 0.5091, "step": 1978 }, { "epoch": 2.216206123973114, "grad_norm": 0.9066476821899414, "learning_rate": 3.5802803042984745e-06, "loss": 0.4852, "step": 1979 }, { "epoch": 2.217326362957431, "grad_norm": 0.8683227896690369, "learning_rate": 3.57893150546602e-06, "loss": 0.4887, "step": 1980 }, { "epoch": 2.2184466019417477, "grad_norm": 0.8426591157913208, "learning_rate": 3.5775823205830184e-06, "loss": 0.515, "step": 1981 }, { "epoch": 2.2195668409260643, "grad_norm": 0.8792897462844849, "learning_rate": 3.576232750132219e-06, "loss": 0.5144, "step": 1982 }, { "epoch": 2.220687079910381, "grad_norm": 0.9246968030929565, "learning_rate": 3.5748827945965093e-06, "loss": 0.5022, "step": 1983 }, { "epoch": 2.2218073188946974, "grad_norm": 0.8582632541656494, "learning_rate": 3.5735324544589135e-06, "loss": 0.4956, "step": 1984 }, { "epoch": 2.2229275578790144, "grad_norm": 0.835827648639679, "learning_rate": 3.5721817302025953e-06, "loss": 0.4855, "step": 1985 }, { "epoch": 2.224047796863331, "grad_norm": 0.8583594560623169, "learning_rate": 3.5708306223108553e-06, "loss": 0.5238, "step": 1986 }, { "epoch": 2.2251680358476476, "grad_norm": 0.8356433510780334, "learning_rate": 3.5694791312671297e-06, "loss": 0.49, "step": 1987 }, { "epoch": 2.226288274831964, "grad_norm": 0.8775174617767334, "learning_rate": 3.5681272575549936e-06, "loss": 0.4959, "step": 1988 }, { "epoch": 2.2274085138162807, "grad_norm": 0.9226460456848145, "learning_rate": 3.566775001658159e-06, "loss": 0.5202, "step": 1989 }, { "epoch": 2.2285287528005973, "grad_norm": 0.864155650138855, "learning_rate": 3.5654223640604748e-06, "loss": 0.491, "step": 1990 }, { "epoch": 2.2296489917849143, "grad_norm": 0.8630480766296387, "learning_rate": 3.5640693452459237e-06, "loss": 0.5046, "step": 1991 }, { "epoch": 2.230769230769231, "grad_norm": 0.8776357173919678, "learning_rate": 3.562715945698628e-06, "loss": 0.5311, "step": 1992 }, { "epoch": 2.2318894697535474, "grad_norm": 0.8397099375724792, "learning_rate": 3.5613621659028463e-06, "loss": 0.4891, "step": 1993 }, { "epoch": 2.233009708737864, "grad_norm": 0.8616359829902649, "learning_rate": 3.560008006342971e-06, "loss": 0.469, "step": 1994 }, { "epoch": 2.2341299477221805, "grad_norm": 0.8550127744674683, "learning_rate": 3.5586534675035304e-06, "loss": 0.5277, "step": 1995 }, { "epoch": 2.2352501867064976, "grad_norm": 0.8481236696243286, "learning_rate": 3.5572985498691925e-06, "loss": 0.4791, "step": 1996 }, { "epoch": 2.236370425690814, "grad_norm": 0.851659893989563, "learning_rate": 3.5559432539247556e-06, "loss": 0.4955, "step": 1997 }, { "epoch": 2.2374906646751307, "grad_norm": 0.8698470592498779, "learning_rate": 3.554587580155156e-06, "loss": 0.5197, "step": 1998 }, { "epoch": 2.2386109036594473, "grad_norm": 0.8410050868988037, "learning_rate": 3.5532315290454662e-06, "loss": 0.5159, "step": 1999 }, { "epoch": 2.239731142643764, "grad_norm": 0.8416511416435242, "learning_rate": 3.5518751010808904e-06, "loss": 0.4676, "step": 2000 }, { "epoch": 2.240851381628081, "grad_norm": 0.8407989740371704, "learning_rate": 3.550518296746771e-06, "loss": 0.5219, "step": 2001 }, { "epoch": 2.2419716206123974, "grad_norm": 0.8447951674461365, "learning_rate": 3.5491611165285844e-06, "loss": 0.4988, "step": 2002 }, { "epoch": 2.243091859596714, "grad_norm": 0.8581940531730652, "learning_rate": 3.5478035609119393e-06, "loss": 0.5219, "step": 2003 }, { "epoch": 2.2442120985810305, "grad_norm": 0.8733254075050354, "learning_rate": 3.5464456303825804e-06, "loss": 0.538, "step": 2004 }, { "epoch": 2.245332337565347, "grad_norm": 0.8641485571861267, "learning_rate": 3.5450873254263877e-06, "loss": 0.4995, "step": 2005 }, { "epoch": 2.246452576549664, "grad_norm": 0.8334444761276245, "learning_rate": 3.543728646529373e-06, "loss": 0.5145, "step": 2006 }, { "epoch": 2.2475728155339807, "grad_norm": 0.8602999448776245, "learning_rate": 3.5423695941776827e-06, "loss": 0.5063, "step": 2007 }, { "epoch": 2.2486930545182973, "grad_norm": 0.8438096642494202, "learning_rate": 3.541010168857596e-06, "loss": 0.5223, "step": 2008 }, { "epoch": 2.249813293502614, "grad_norm": 0.8495678305625916, "learning_rate": 3.5396503710555288e-06, "loss": 0.4879, "step": 2009 }, { "epoch": 2.2509335324869304, "grad_norm": 0.8465366959571838, "learning_rate": 3.5382902012580257e-06, "loss": 0.5004, "step": 2010 }, { "epoch": 2.252053771471247, "grad_norm": 0.8735441565513611, "learning_rate": 3.536929659951768e-06, "loss": 0.4675, "step": 2011 }, { "epoch": 2.253174010455564, "grad_norm": 0.8345158100128174, "learning_rate": 3.5355687476235673e-06, "loss": 0.5067, "step": 2012 }, { "epoch": 2.2542942494398805, "grad_norm": 0.8861410021781921, "learning_rate": 3.5342074647603704e-06, "loss": 0.5101, "step": 2013 }, { "epoch": 2.255414488424197, "grad_norm": 0.8888171911239624, "learning_rate": 3.5328458118492544e-06, "loss": 0.5135, "step": 2014 }, { "epoch": 2.2565347274085137, "grad_norm": 0.8463373184204102, "learning_rate": 3.53148378937743e-06, "loss": 0.4905, "step": 2015 }, { "epoch": 2.2576549663928303, "grad_norm": 0.8727759122848511, "learning_rate": 3.530121397832242e-06, "loss": 0.5174, "step": 2016 }, { "epoch": 2.2587752053771473, "grad_norm": 0.853564977645874, "learning_rate": 3.528758637701163e-06, "loss": 0.4975, "step": 2017 }, { "epoch": 2.259895444361464, "grad_norm": 0.9036617875099182, "learning_rate": 3.5273955094718e-06, "loss": 0.5157, "step": 2018 }, { "epoch": 2.2610156833457804, "grad_norm": 0.8799504041671753, "learning_rate": 3.5260320136318927e-06, "loss": 0.4791, "step": 2019 }, { "epoch": 2.262135922330097, "grad_norm": 0.8200225830078125, "learning_rate": 3.52466815066931e-06, "loss": 0.4914, "step": 2020 }, { "epoch": 2.2632561613144135, "grad_norm": 0.8564799427986145, "learning_rate": 3.5233039210720532e-06, "loss": 0.4882, "step": 2021 }, { "epoch": 2.2643764002987306, "grad_norm": 0.8228212594985962, "learning_rate": 3.5219393253282557e-06, "loss": 0.4989, "step": 2022 }, { "epoch": 2.265496639283047, "grad_norm": 0.8644258379936218, "learning_rate": 3.5205743639261806e-06, "loss": 0.5068, "step": 2023 }, { "epoch": 2.2666168782673637, "grad_norm": 0.8672634363174438, "learning_rate": 3.519209037354222e-06, "loss": 0.4876, "step": 2024 }, { "epoch": 2.2677371172516803, "grad_norm": 0.840275764465332, "learning_rate": 3.517843346100906e-06, "loss": 0.501, "step": 2025 }, { "epoch": 2.268857356235997, "grad_norm": 0.8575993180274963, "learning_rate": 3.516477290654887e-06, "loss": 0.5117, "step": 2026 }, { "epoch": 2.269977595220314, "grad_norm": 0.8623318076133728, "learning_rate": 3.5151108715049512e-06, "loss": 0.4982, "step": 2027 }, { "epoch": 2.2710978342046304, "grad_norm": 0.9008529782295227, "learning_rate": 3.513744089140014e-06, "loss": 0.5082, "step": 2028 }, { "epoch": 2.272218073188947, "grad_norm": 0.8302580714225769, "learning_rate": 3.5123769440491235e-06, "loss": 0.4897, "step": 2029 }, { "epoch": 2.2733383121732635, "grad_norm": 0.8337039351463318, "learning_rate": 3.511009436721453e-06, "loss": 0.5021, "step": 2030 }, { "epoch": 2.27445855115758, "grad_norm": 0.8491420149803162, "learning_rate": 3.509641567646309e-06, "loss": 0.509, "step": 2031 }, { "epoch": 2.275578790141897, "grad_norm": 0.8538939952850342, "learning_rate": 3.508273337313126e-06, "loss": 0.5086, "step": 2032 }, { "epoch": 2.2766990291262137, "grad_norm": 0.8574468493461609, "learning_rate": 3.506904746211468e-06, "loss": 0.5092, "step": 2033 }, { "epoch": 2.2778192681105303, "grad_norm": 0.8784538507461548, "learning_rate": 3.505535794831029e-06, "loss": 0.5213, "step": 2034 }, { "epoch": 2.278939507094847, "grad_norm": 0.8519439697265625, "learning_rate": 3.5041664836616284e-06, "loss": 0.4919, "step": 2035 }, { "epoch": 2.2800597460791634, "grad_norm": 0.8415244817733765, "learning_rate": 3.5027968131932204e-06, "loss": 0.4941, "step": 2036 }, { "epoch": 2.2811799850634804, "grad_norm": 0.838026762008667, "learning_rate": 3.5014267839158822e-06, "loss": 0.4807, "step": 2037 }, { "epoch": 2.282300224047797, "grad_norm": 0.891518771648407, "learning_rate": 3.500056396319822e-06, "loss": 0.511, "step": 2038 }, { "epoch": 2.2834204630321135, "grad_norm": 0.8848864436149597, "learning_rate": 3.4986856508953764e-06, "loss": 0.5145, "step": 2039 }, { "epoch": 2.28454070201643, "grad_norm": 0.8630772829055786, "learning_rate": 3.4973145481330085e-06, "loss": 0.5135, "step": 2040 }, { "epoch": 2.2856609410007467, "grad_norm": 0.9140154719352722, "learning_rate": 3.4959430885233104e-06, "loss": 0.5163, "step": 2041 }, { "epoch": 2.2867811799850637, "grad_norm": 0.8681530952453613, "learning_rate": 3.4945712725570008e-06, "loss": 0.4672, "step": 2042 }, { "epoch": 2.2879014189693803, "grad_norm": 0.8333169221878052, "learning_rate": 3.493199100724929e-06, "loss": 0.4883, "step": 2043 }, { "epoch": 2.289021657953697, "grad_norm": 0.8437874913215637, "learning_rate": 3.491826573518067e-06, "loss": 0.4876, "step": 2044 }, { "epoch": 2.2901418969380134, "grad_norm": 0.8394180536270142, "learning_rate": 3.4904536914275167e-06, "loss": 0.5048, "step": 2045 }, { "epoch": 2.29126213592233, "grad_norm": 0.8552835583686829, "learning_rate": 3.489080454944508e-06, "loss": 0.4907, "step": 2046 }, { "epoch": 2.292382374906647, "grad_norm": 0.8728405833244324, "learning_rate": 3.487706864560394e-06, "loss": 0.498, "step": 2047 }, { "epoch": 2.2935026138909635, "grad_norm": 0.8613417744636536, "learning_rate": 3.4863329207666584e-06, "loss": 0.5002, "step": 2048 }, { "epoch": 2.29462285287528, "grad_norm": 0.8382084965705872, "learning_rate": 3.4849586240549093e-06, "loss": 0.4724, "step": 2049 }, { "epoch": 2.2957430918595967, "grad_norm": 0.8366925716400146, "learning_rate": 3.4835839749168815e-06, "loss": 0.4942, "step": 2050 }, { "epoch": 2.2968633308439133, "grad_norm": 0.8718281388282776, "learning_rate": 3.4822089738444344e-06, "loss": 0.4966, "step": 2051 }, { "epoch": 2.2979835698282303, "grad_norm": 0.8739128708839417, "learning_rate": 3.4808336213295556e-06, "loss": 0.4985, "step": 2052 }, { "epoch": 2.299103808812547, "grad_norm": 0.8389970064163208, "learning_rate": 3.4794579178643578e-06, "loss": 0.4769, "step": 2053 }, { "epoch": 2.3002240477968634, "grad_norm": 0.8571019172668457, "learning_rate": 3.4780818639410783e-06, "loss": 0.5121, "step": 2054 }, { "epoch": 2.30134428678118, "grad_norm": 0.8321137428283691, "learning_rate": 3.476705460052081e-06, "loss": 0.4893, "step": 2055 }, { "epoch": 2.3024645257654965, "grad_norm": 0.8281792998313904, "learning_rate": 3.475328706689855e-06, "loss": 0.4899, "step": 2056 }, { "epoch": 2.303584764749813, "grad_norm": 0.8503859639167786, "learning_rate": 3.4739516043470128e-06, "loss": 0.4987, "step": 2057 }, { "epoch": 2.30470500373413, "grad_norm": 0.8555354475975037, "learning_rate": 3.4725741535162934e-06, "loss": 0.5206, "step": 2058 }, { "epoch": 2.3058252427184467, "grad_norm": 0.8421693444252014, "learning_rate": 3.47119635469056e-06, "loss": 0.5074, "step": 2059 }, { "epoch": 2.3069454817027633, "grad_norm": 0.8656131029129028, "learning_rate": 3.4698182083628e-06, "loss": 0.4981, "step": 2060 }, { "epoch": 2.30806572068708, "grad_norm": 0.8868282437324524, "learning_rate": 3.4684397150261266e-06, "loss": 0.5189, "step": 2061 }, { "epoch": 2.3091859596713964, "grad_norm": 0.8733910918235779, "learning_rate": 3.4670608751737746e-06, "loss": 0.5173, "step": 2062 }, { "epoch": 2.3103061986557134, "grad_norm": 0.8609498143196106, "learning_rate": 3.465681689299105e-06, "loss": 0.4865, "step": 2063 }, { "epoch": 2.31142643764003, "grad_norm": 0.8635644316673279, "learning_rate": 3.4643021578956028e-06, "loss": 0.4955, "step": 2064 }, { "epoch": 2.3125466766243465, "grad_norm": 0.8351870775222778, "learning_rate": 3.4629222814568732e-06, "loss": 0.4802, "step": 2065 }, { "epoch": 2.313666915608663, "grad_norm": 0.8436661958694458, "learning_rate": 3.461542060476649e-06, "loss": 0.5057, "step": 2066 }, { "epoch": 2.3147871545929797, "grad_norm": 0.8615201115608215, "learning_rate": 3.460161495448784e-06, "loss": 0.5015, "step": 2067 }, { "epoch": 2.3159073935772962, "grad_norm": 0.8696888089179993, "learning_rate": 3.4587805868672558e-06, "loss": 0.5046, "step": 2068 }, { "epoch": 2.3170276325616133, "grad_norm": 0.8789259791374207, "learning_rate": 3.457399335226166e-06, "loss": 0.499, "step": 2069 }, { "epoch": 2.31814787154593, "grad_norm": 0.8261885643005371, "learning_rate": 3.4560177410197366e-06, "loss": 0.489, "step": 2070 }, { "epoch": 2.3192681105302464, "grad_norm": 0.8724235892295837, "learning_rate": 3.4546358047423136e-06, "loss": 0.4949, "step": 2071 }, { "epoch": 2.320388349514563, "grad_norm": 0.8574761152267456, "learning_rate": 3.4532535268883637e-06, "loss": 0.4934, "step": 2072 }, { "epoch": 2.3215085884988795, "grad_norm": 0.8616077899932861, "learning_rate": 3.451870907952479e-06, "loss": 0.4927, "step": 2073 }, { "epoch": 2.3226288274831965, "grad_norm": 0.8631961941719055, "learning_rate": 3.4504879484293726e-06, "loss": 0.5184, "step": 2074 }, { "epoch": 2.323749066467513, "grad_norm": 0.8587513566017151, "learning_rate": 3.4491046488138768e-06, "loss": 0.5135, "step": 2075 }, { "epoch": 2.3248693054518297, "grad_norm": 0.8380201458930969, "learning_rate": 3.447721009600949e-06, "loss": 0.4905, "step": 2076 }, { "epoch": 2.3259895444361463, "grad_norm": 0.867155134677887, "learning_rate": 3.446337031285666e-06, "loss": 0.494, "step": 2077 }, { "epoch": 2.327109783420463, "grad_norm": 0.8349313735961914, "learning_rate": 3.4449527143632253e-06, "loss": 0.4977, "step": 2078 }, { "epoch": 2.32823002240478, "grad_norm": 0.8265823721885681, "learning_rate": 3.44356805932895e-06, "loss": 0.4565, "step": 2079 }, { "epoch": 2.3293502613890964, "grad_norm": 0.8207617998123169, "learning_rate": 3.4421830666782786e-06, "loss": 0.4961, "step": 2080 }, { "epoch": 2.330470500373413, "grad_norm": 0.9040359258651733, "learning_rate": 3.4407977369067738e-06, "loss": 0.5083, "step": 2081 }, { "epoch": 2.3315907393577295, "grad_norm": 0.8762617111206055, "learning_rate": 3.4394120705101175e-06, "loss": 0.5094, "step": 2082 }, { "epoch": 2.332710978342046, "grad_norm": 0.8367526531219482, "learning_rate": 3.4380260679841127e-06, "loss": 0.478, "step": 2083 }, { "epoch": 2.333831217326363, "grad_norm": 0.8553252220153809, "learning_rate": 3.436639729824683e-06, "loss": 0.4752, "step": 2084 }, { "epoch": 2.3349514563106797, "grad_norm": 0.8465068340301514, "learning_rate": 3.4352530565278696e-06, "loss": 0.4866, "step": 2085 }, { "epoch": 2.3360716952949963, "grad_norm": 0.8600947260856628, "learning_rate": 3.4338660485898385e-06, "loss": 0.4925, "step": 2086 }, { "epoch": 2.337191934279313, "grad_norm": 0.887150764465332, "learning_rate": 3.43247870650687e-06, "loss": 0.5197, "step": 2087 }, { "epoch": 2.3383121732636294, "grad_norm": 0.9654474258422852, "learning_rate": 3.431091030775369e-06, "loss": 0.5001, "step": 2088 }, { "epoch": 2.3394324122479464, "grad_norm": 0.8413697481155396, "learning_rate": 3.4297030218918535e-06, "loss": 0.4801, "step": 2089 }, { "epoch": 2.340552651232263, "grad_norm": 0.8691710233688354, "learning_rate": 3.428314680352969e-06, "loss": 0.505, "step": 2090 }, { "epoch": 2.3416728902165795, "grad_norm": 0.8958663940429688, "learning_rate": 3.426926006655472e-06, "loss": 0.5128, "step": 2091 }, { "epoch": 2.342793129200896, "grad_norm": 0.8288049697875977, "learning_rate": 3.425537001296243e-06, "loss": 0.4951, "step": 2092 }, { "epoch": 2.3439133681852127, "grad_norm": 0.8372279405593872, "learning_rate": 3.424147664772279e-06, "loss": 0.5079, "step": 2093 }, { "epoch": 2.3450336071695297, "grad_norm": 0.8544606566429138, "learning_rate": 3.4227579975806962e-06, "loss": 0.5084, "step": 2094 }, { "epoch": 2.3461538461538463, "grad_norm": 0.8715816736221313, "learning_rate": 3.421368000218729e-06, "loss": 0.4942, "step": 2095 }, { "epoch": 2.347274085138163, "grad_norm": 0.884482204914093, "learning_rate": 3.4199776731837296e-06, "loss": 0.5186, "step": 2096 }, { "epoch": 2.3483943241224794, "grad_norm": 0.8694517016410828, "learning_rate": 3.418587016973169e-06, "loss": 0.5014, "step": 2097 }, { "epoch": 2.349514563106796, "grad_norm": 0.8869951367378235, "learning_rate": 3.4171960320846343e-06, "loss": 0.5155, "step": 2098 }, { "epoch": 2.350634802091113, "grad_norm": 0.8707970380783081, "learning_rate": 3.415804719015832e-06, "loss": 0.5137, "step": 2099 }, { "epoch": 2.3517550410754295, "grad_norm": 0.8910504579544067, "learning_rate": 3.4144130782645852e-06, "loss": 0.4969, "step": 2100 }, { "epoch": 2.352875280059746, "grad_norm": 0.860688328742981, "learning_rate": 3.413021110328835e-06, "loss": 0.502, "step": 2101 }, { "epoch": 2.3539955190440627, "grad_norm": 0.9706821441650391, "learning_rate": 3.4116288157066378e-06, "loss": 0.5004, "step": 2102 }, { "epoch": 2.3551157580283792, "grad_norm": 0.8977230191230774, "learning_rate": 3.410236194896169e-06, "loss": 0.5093, "step": 2103 }, { "epoch": 2.3562359970126963, "grad_norm": 0.8539577126502991, "learning_rate": 3.4088432483957203e-06, "loss": 0.5142, "step": 2104 }, { "epoch": 2.357356235997013, "grad_norm": 0.8535719513893127, "learning_rate": 3.4074499767036974e-06, "loss": 0.4823, "step": 2105 }, { "epoch": 2.3584764749813294, "grad_norm": 0.8751472234725952, "learning_rate": 3.4060563803186255e-06, "loss": 0.4935, "step": 2106 }, { "epoch": 2.359596713965646, "grad_norm": 0.8545224070549011, "learning_rate": 3.404662459739145e-06, "loss": 0.4749, "step": 2107 }, { "epoch": 2.3607169529499625, "grad_norm": 0.870175302028656, "learning_rate": 3.403268215464013e-06, "loss": 0.5278, "step": 2108 }, { "epoch": 2.3618371919342795, "grad_norm": 0.8567377328872681, "learning_rate": 3.401873647992099e-06, "loss": 0.5014, "step": 2109 }, { "epoch": 2.362957430918596, "grad_norm": 0.8736950159072876, "learning_rate": 3.400478757822393e-06, "loss": 0.5069, "step": 2110 }, { "epoch": 2.3640776699029127, "grad_norm": 0.8862476348876953, "learning_rate": 3.3990835454539967e-06, "loss": 0.5162, "step": 2111 }, { "epoch": 2.3651979088872293, "grad_norm": 0.8995987772941589, "learning_rate": 3.397688011386129e-06, "loss": 0.506, "step": 2112 }, { "epoch": 2.366318147871546, "grad_norm": 0.8504335880279541, "learning_rate": 3.3962921561181237e-06, "loss": 0.5157, "step": 2113 }, { "epoch": 2.367438386855863, "grad_norm": 0.8582834005355835, "learning_rate": 3.39489598014943e-06, "loss": 0.4944, "step": 2114 }, { "epoch": 2.3685586258401794, "grad_norm": 0.8631083369255066, "learning_rate": 3.39349948397961e-06, "loss": 0.4954, "step": 2115 }, { "epoch": 2.369678864824496, "grad_norm": 0.8761064410209656, "learning_rate": 3.3921026681083406e-06, "loss": 0.5287, "step": 2116 }, { "epoch": 2.3707991038088125, "grad_norm": 0.8665860891342163, "learning_rate": 3.390705533035416e-06, "loss": 0.4969, "step": 2117 }, { "epoch": 2.371919342793129, "grad_norm": 0.8257828950881958, "learning_rate": 3.389308079260742e-06, "loss": 0.4928, "step": 2118 }, { "epoch": 2.3730395817774457, "grad_norm": 0.8442469835281372, "learning_rate": 3.387910307284338e-06, "loss": 0.498, "step": 2119 }, { "epoch": 2.3741598207617627, "grad_norm": 0.8559431433677673, "learning_rate": 3.386512217606339e-06, "loss": 0.5205, "step": 2120 }, { "epoch": 2.3752800597460793, "grad_norm": 0.8691369295120239, "learning_rate": 3.385113810726994e-06, "loss": 0.4808, "step": 2121 }, { "epoch": 2.376400298730396, "grad_norm": 0.8768832683563232, "learning_rate": 3.383715087146663e-06, "loss": 0.4958, "step": 2122 }, { "epoch": 2.3775205377147124, "grad_norm": 0.8587091565132141, "learning_rate": 3.3823160473658213e-06, "loss": 0.4865, "step": 2123 }, { "epoch": 2.378640776699029, "grad_norm": 0.8592469692230225, "learning_rate": 3.380916691885057e-06, "loss": 0.5044, "step": 2124 }, { "epoch": 2.379761015683346, "grad_norm": 0.8586136698722839, "learning_rate": 3.3795170212050694e-06, "loss": 0.5162, "step": 2125 }, { "epoch": 2.3808812546676625, "grad_norm": 0.8494666218757629, "learning_rate": 3.378117035826674e-06, "loss": 0.4969, "step": 2126 }, { "epoch": 2.382001493651979, "grad_norm": 0.8583998680114746, "learning_rate": 3.3767167362507975e-06, "loss": 0.5093, "step": 2127 }, { "epoch": 2.3831217326362957, "grad_norm": 0.848042368888855, "learning_rate": 3.375316122978477e-06, "loss": 0.5032, "step": 2128 }, { "epoch": 2.3842419716206122, "grad_norm": 0.8475974798202515, "learning_rate": 3.3739151965108643e-06, "loss": 0.5153, "step": 2129 }, { "epoch": 2.385362210604929, "grad_norm": 0.8740301132202148, "learning_rate": 3.372513957349222e-06, "loss": 0.5105, "step": 2130 }, { "epoch": 2.386482449589246, "grad_norm": 0.8647029399871826, "learning_rate": 3.371112405994925e-06, "loss": 0.5094, "step": 2131 }, { "epoch": 2.3876026885735624, "grad_norm": 0.861386775970459, "learning_rate": 3.3697105429494604e-06, "loss": 0.4982, "step": 2132 }, { "epoch": 2.388722927557879, "grad_norm": 0.8488511443138123, "learning_rate": 3.3683083687144247e-06, "loss": 0.5034, "step": 2133 }, { "epoch": 2.3898431665421955, "grad_norm": 0.8515283465385437, "learning_rate": 3.3669058837915304e-06, "loss": 0.4768, "step": 2134 }, { "epoch": 2.390963405526512, "grad_norm": 0.8620295524597168, "learning_rate": 3.365503088682595e-06, "loss": 0.4986, "step": 2135 }, { "epoch": 2.392083644510829, "grad_norm": 0.8835116624832153, "learning_rate": 3.3640999838895516e-06, "loss": 0.5051, "step": 2136 }, { "epoch": 2.3932038834951457, "grad_norm": 0.9169773459434509, "learning_rate": 3.362696569914442e-06, "loss": 0.4846, "step": 2137 }, { "epoch": 2.3943241224794622, "grad_norm": 0.9183397889137268, "learning_rate": 3.3612928472594207e-06, "loss": 0.4742, "step": 2138 }, { "epoch": 2.395444361463779, "grad_norm": 0.8789238333702087, "learning_rate": 3.359888816426749e-06, "loss": 0.5021, "step": 2139 }, { "epoch": 2.3965646004480954, "grad_norm": 0.8425140976905823, "learning_rate": 3.358484477918802e-06, "loss": 0.4755, "step": 2140 }, { "epoch": 2.3976848394324124, "grad_norm": 0.8540031909942627, "learning_rate": 3.3570798322380634e-06, "loss": 0.4812, "step": 2141 }, { "epoch": 2.398805078416729, "grad_norm": 0.8540413975715637, "learning_rate": 3.3556748798871263e-06, "loss": 0.5057, "step": 2142 }, { "epoch": 2.3999253174010455, "grad_norm": 0.8316277861595154, "learning_rate": 3.3542696213686953e-06, "loss": 0.4832, "step": 2143 }, { "epoch": 2.401045556385362, "grad_norm": 0.8740952610969543, "learning_rate": 3.3528640571855837e-06, "loss": 0.5005, "step": 2144 }, { "epoch": 2.4021657953696787, "grad_norm": 0.9072818756103516, "learning_rate": 3.3514581878407116e-06, "loss": 0.5164, "step": 2145 }, { "epoch": 2.4032860343539957, "grad_norm": 0.8888911604881287, "learning_rate": 3.3500520138371123e-06, "loss": 0.5324, "step": 2146 }, { "epoch": 2.4044062733383122, "grad_norm": 0.861375093460083, "learning_rate": 3.3486455356779268e-06, "loss": 0.5261, "step": 2147 }, { "epoch": 2.405526512322629, "grad_norm": 0.8532165288925171, "learning_rate": 3.3472387538664035e-06, "loss": 0.5013, "step": 2148 }, { "epoch": 2.4066467513069454, "grad_norm": 0.8964754343032837, "learning_rate": 3.345831668905901e-06, "loss": 0.504, "step": 2149 }, { "epoch": 2.407766990291262, "grad_norm": 0.8514949679374695, "learning_rate": 3.3444242812998857e-06, "loss": 0.504, "step": 2150 }, { "epoch": 2.408887229275579, "grad_norm": 0.8734633922576904, "learning_rate": 3.3430165915519323e-06, "loss": 0.5102, "step": 2151 }, { "epoch": 2.4100074682598955, "grad_norm": 0.8263325691223145, "learning_rate": 3.3416086001657235e-06, "loss": 0.4909, "step": 2152 }, { "epoch": 2.411127707244212, "grad_norm": 0.9003376960754395, "learning_rate": 3.3402003076450505e-06, "loss": 0.4848, "step": 2153 }, { "epoch": 2.4122479462285287, "grad_norm": 0.9014631509780884, "learning_rate": 3.3387917144938125e-06, "loss": 0.5054, "step": 2154 }, { "epoch": 2.4133681852128452, "grad_norm": 0.8547587394714355, "learning_rate": 3.3373828212160153e-06, "loss": 0.4919, "step": 2155 }, { "epoch": 2.4144884241971623, "grad_norm": 0.8509113788604736, "learning_rate": 3.3359736283157717e-06, "loss": 0.5147, "step": 2156 }, { "epoch": 2.415608663181479, "grad_norm": 0.8465393781661987, "learning_rate": 3.334564136297304e-06, "loss": 0.5052, "step": 2157 }, { "epoch": 2.4167289021657954, "grad_norm": 0.8792532682418823, "learning_rate": 3.333154345664939e-06, "loss": 0.5138, "step": 2158 }, { "epoch": 2.417849141150112, "grad_norm": 0.8844321370124817, "learning_rate": 3.3317442569231107e-06, "loss": 0.4862, "step": 2159 }, { "epoch": 2.4189693801344285, "grad_norm": 0.8596680760383606, "learning_rate": 3.330333870576361e-06, "loss": 0.4999, "step": 2160 }, { "epoch": 2.4200896191187455, "grad_norm": 0.88459312915802, "learning_rate": 3.3289231871293393e-06, "loss": 0.5157, "step": 2161 }, { "epoch": 2.421209858103062, "grad_norm": 0.8407149910926819, "learning_rate": 3.327512207086798e-06, "loss": 0.4759, "step": 2162 }, { "epoch": 2.4223300970873787, "grad_norm": 0.8220493197441101, "learning_rate": 3.3261009309535965e-06, "loss": 0.4927, "step": 2163 }, { "epoch": 2.4234503360716952, "grad_norm": 0.8431199789047241, "learning_rate": 3.324689359234703e-06, "loss": 0.5043, "step": 2164 }, { "epoch": 2.424570575056012, "grad_norm": 0.8559691905975342, "learning_rate": 3.323277492435189e-06, "loss": 0.5069, "step": 2165 }, { "epoch": 2.425690814040329, "grad_norm": 0.8464775085449219, "learning_rate": 3.32186533106023e-06, "loss": 0.5078, "step": 2166 }, { "epoch": 2.4268110530246454, "grad_norm": 0.8448901176452637, "learning_rate": 3.320452875615112e-06, "loss": 0.5069, "step": 2167 }, { "epoch": 2.427931292008962, "grad_norm": 0.8362756371498108, "learning_rate": 3.319040126605222e-06, "loss": 0.4849, "step": 2168 }, { "epoch": 2.4290515309932785, "grad_norm": 0.8609240651130676, "learning_rate": 3.3176270845360518e-06, "loss": 0.5118, "step": 2169 }, { "epoch": 2.430171769977595, "grad_norm": 0.873492956161499, "learning_rate": 3.3162137499132014e-06, "loss": 0.5111, "step": 2170 }, { "epoch": 2.431292008961912, "grad_norm": 0.8407337069511414, "learning_rate": 3.3148001232423727e-06, "loss": 0.4992, "step": 2171 }, { "epoch": 2.4324122479462287, "grad_norm": 0.8559135794639587, "learning_rate": 3.313386205029372e-06, "loss": 0.4785, "step": 2172 }, { "epoch": 2.4335324869305452, "grad_norm": 0.8654513955116272, "learning_rate": 3.3119719957801122e-06, "loss": 0.5185, "step": 2173 }, { "epoch": 2.434652725914862, "grad_norm": 0.8587852120399475, "learning_rate": 3.310557496000609e-06, "loss": 0.4965, "step": 2174 }, { "epoch": 2.4357729648991784, "grad_norm": 0.85335773229599, "learning_rate": 3.3091427061969817e-06, "loss": 0.4863, "step": 2175 }, { "epoch": 2.436893203883495, "grad_norm": 0.8485393524169922, "learning_rate": 3.3077276268754523e-06, "loss": 0.4756, "step": 2176 }, { "epoch": 2.438013442867812, "grad_norm": 0.8571751117706299, "learning_rate": 3.3063122585423503e-06, "loss": 0.4794, "step": 2177 }, { "epoch": 2.4391336818521285, "grad_norm": 0.8614619970321655, "learning_rate": 3.3048966017041044e-06, "loss": 0.4889, "step": 2178 }, { "epoch": 2.440253920836445, "grad_norm": 0.8468948006629944, "learning_rate": 3.3034806568672486e-06, "loss": 0.4894, "step": 2179 }, { "epoch": 2.4413741598207617, "grad_norm": 0.8461976647377014, "learning_rate": 3.3020644245384193e-06, "loss": 0.5001, "step": 2180 }, { "epoch": 2.4424943988050782, "grad_norm": 0.8258972764015198, "learning_rate": 3.300647905224357e-06, "loss": 0.4802, "step": 2181 }, { "epoch": 2.4436146377893952, "grad_norm": 0.8601251244544983, "learning_rate": 3.2992310994319033e-06, "loss": 0.4877, "step": 2182 }, { "epoch": 2.444734876773712, "grad_norm": 0.8463799953460693, "learning_rate": 3.2978140076680025e-06, "loss": 0.4869, "step": 2183 }, { "epoch": 2.4458551157580284, "grad_norm": 0.8288507461547852, "learning_rate": 3.2963966304397034e-06, "loss": 0.4965, "step": 2184 }, { "epoch": 2.446975354742345, "grad_norm": 0.8194431066513062, "learning_rate": 3.294978968254153e-06, "loss": 0.4689, "step": 2185 }, { "epoch": 2.4480955937266615, "grad_norm": 0.853531002998352, "learning_rate": 3.2935610216186026e-06, "loss": 0.5152, "step": 2186 }, { "epoch": 2.4492158327109785, "grad_norm": 0.8578755259513855, "learning_rate": 3.292142791040407e-06, "loss": 0.5001, "step": 2187 }, { "epoch": 2.450336071695295, "grad_norm": 0.868257999420166, "learning_rate": 3.29072427702702e-06, "loss": 0.5069, "step": 2188 }, { "epoch": 2.4514563106796117, "grad_norm": 0.8743165731430054, "learning_rate": 3.289305480085997e-06, "loss": 0.525, "step": 2189 }, { "epoch": 2.4525765496639282, "grad_norm": 0.875088632106781, "learning_rate": 3.2878864007249955e-06, "loss": 0.5061, "step": 2190 }, { "epoch": 2.453696788648245, "grad_norm": 0.8818257451057434, "learning_rate": 3.286467039451774e-06, "loss": 0.4922, "step": 2191 }, { "epoch": 2.4548170276325614, "grad_norm": 0.8908629417419434, "learning_rate": 3.285047396774191e-06, "loss": 0.4995, "step": 2192 }, { "epoch": 2.4559372666168784, "grad_norm": 0.8496206402778625, "learning_rate": 3.2836274732002054e-06, "loss": 0.5001, "step": 2193 }, { "epoch": 2.457057505601195, "grad_norm": 0.879574716091156, "learning_rate": 3.28220726923788e-06, "loss": 0.4909, "step": 2194 }, { "epoch": 2.4581777445855115, "grad_norm": 0.8405442833900452, "learning_rate": 3.280786785395374e-06, "loss": 0.4714, "step": 2195 }, { "epoch": 2.459297983569828, "grad_norm": 0.8576659560203552, "learning_rate": 3.279366022180948e-06, "loss": 0.5202, "step": 2196 }, { "epoch": 2.4604182225541447, "grad_norm": 0.8551929593086243, "learning_rate": 3.2779449801029637e-06, "loss": 0.524, "step": 2197 }, { "epoch": 2.4615384615384617, "grad_norm": 0.8500196933746338, "learning_rate": 3.2765236596698814e-06, "loss": 0.5021, "step": 2198 }, { "epoch": 2.4626587005227782, "grad_norm": 0.8721874356269836, "learning_rate": 3.2751020613902594e-06, "loss": 0.5058, "step": 2199 }, { "epoch": 2.463778939507095, "grad_norm": 0.85982745885849, "learning_rate": 3.273680185772759e-06, "loss": 0.5023, "step": 2200 }, { "epoch": 2.4648991784914114, "grad_norm": 0.8610902428627014, "learning_rate": 3.2722580333261387e-06, "loss": 0.5138, "step": 2201 }, { "epoch": 2.466019417475728, "grad_norm": 0.8613830804824829, "learning_rate": 3.270835604559257e-06, "loss": 0.4921, "step": 2202 }, { "epoch": 2.467139656460045, "grad_norm": 0.8543768525123596, "learning_rate": 3.2694128999810686e-06, "loss": 0.5133, "step": 2203 }, { "epoch": 2.4682598954443615, "grad_norm": 0.9026292562484741, "learning_rate": 3.267989920100631e-06, "loss": 0.5064, "step": 2204 }, { "epoch": 2.469380134428678, "grad_norm": 0.8928825855255127, "learning_rate": 3.266566665427097e-06, "loss": 0.4924, "step": 2205 }, { "epoch": 2.4705003734129947, "grad_norm": 0.8641089797019958, "learning_rate": 3.265143136469719e-06, "loss": 0.5063, "step": 2206 }, { "epoch": 2.4716206123973112, "grad_norm": 0.865753173828125, "learning_rate": 3.2637193337378465e-06, "loss": 0.4766, "step": 2207 }, { "epoch": 2.4727408513816282, "grad_norm": 0.8399942517280579, "learning_rate": 3.2622952577409295e-06, "loss": 0.4923, "step": 2208 }, { "epoch": 2.473861090365945, "grad_norm": 0.8588327169418335, "learning_rate": 3.260870908988513e-06, "loss": 0.4904, "step": 2209 }, { "epoch": 2.4749813293502614, "grad_norm": 0.8598349690437317, "learning_rate": 3.2594462879902403e-06, "loss": 0.4817, "step": 2210 }, { "epoch": 2.476101568334578, "grad_norm": 0.8382421731948853, "learning_rate": 3.2580213952558537e-06, "loss": 0.4746, "step": 2211 }, { "epoch": 2.4772218073188945, "grad_norm": 0.8629277348518372, "learning_rate": 3.256596231295191e-06, "loss": 0.4984, "step": 2212 }, { "epoch": 2.4783420463032115, "grad_norm": 0.8480556607246399, "learning_rate": 3.255170796618187e-06, "loss": 0.5234, "step": 2213 }, { "epoch": 2.479462285287528, "grad_norm": 0.8841990232467651, "learning_rate": 3.253745091734874e-06, "loss": 0.5051, "step": 2214 }, { "epoch": 2.4805825242718447, "grad_norm": 0.8626237511634827, "learning_rate": 3.252319117155382e-06, "loss": 0.5021, "step": 2215 }, { "epoch": 2.4817027632561612, "grad_norm": 0.8746356964111328, "learning_rate": 3.250892873389935e-06, "loss": 0.5043, "step": 2216 }, { "epoch": 2.482823002240478, "grad_norm": 0.8607040047645569, "learning_rate": 3.249466360948856e-06, "loss": 0.5031, "step": 2217 }, { "epoch": 2.483943241224795, "grad_norm": 0.871214747428894, "learning_rate": 3.2480395803425622e-06, "loss": 0.5015, "step": 2218 }, { "epoch": 2.4850634802091114, "grad_norm": 0.8517579436302185, "learning_rate": 3.246612532081567e-06, "loss": 0.4887, "step": 2219 }, { "epoch": 2.486183719193428, "grad_norm": 0.8962544202804565, "learning_rate": 3.2451852166764803e-06, "loss": 0.5011, "step": 2220 }, { "epoch": 2.4873039581777445, "grad_norm": 0.867358922958374, "learning_rate": 3.2437576346380077e-06, "loss": 0.4944, "step": 2221 }, { "epoch": 2.488424197162061, "grad_norm": 0.8719667792320251, "learning_rate": 3.24232978647695e-06, "loss": 0.5382, "step": 2222 }, { "epoch": 2.489544436146378, "grad_norm": 0.8656331300735474, "learning_rate": 3.2409016727042015e-06, "loss": 0.5208, "step": 2223 }, { "epoch": 2.4906646751306947, "grad_norm": 0.8580676317214966, "learning_rate": 3.2394732938307547e-06, "loss": 0.4933, "step": 2224 }, { "epoch": 2.4917849141150112, "grad_norm": 0.8583241105079651, "learning_rate": 3.238044650367694e-06, "loss": 0.5157, "step": 2225 }, { "epoch": 2.492905153099328, "grad_norm": 0.8458554744720459, "learning_rate": 3.236615742826201e-06, "loss": 0.472, "step": 2226 }, { "epoch": 2.4940253920836444, "grad_norm": 0.8734139204025269, "learning_rate": 3.235186571717549e-06, "loss": 0.5034, "step": 2227 }, { "epoch": 2.4951456310679614, "grad_norm": 0.8527739644050598, "learning_rate": 3.2337571375531084e-06, "loss": 0.5027, "step": 2228 }, { "epoch": 2.496265870052278, "grad_norm": 0.8626096844673157, "learning_rate": 3.2323274408443427e-06, "loss": 0.5152, "step": 2229 }, { "epoch": 2.4973861090365945, "grad_norm": 0.8441228270530701, "learning_rate": 3.2308974821028076e-06, "loss": 0.484, "step": 2230 }, { "epoch": 2.498506348020911, "grad_norm": 0.8634074926376343, "learning_rate": 3.2294672618401558e-06, "loss": 0.5195, "step": 2231 }, { "epoch": 2.4996265870052277, "grad_norm": 0.8627569079399109, "learning_rate": 3.2280367805681307e-06, "loss": 0.5034, "step": 2232 }, { "epoch": 2.5007468259895447, "grad_norm": 0.9074681997299194, "learning_rate": 3.22660603879857e-06, "loss": 0.4881, "step": 2233 }, { "epoch": 2.5018670649738612, "grad_norm": 0.8471819758415222, "learning_rate": 3.225175037043406e-06, "loss": 0.4712, "step": 2234 }, { "epoch": 2.502987303958178, "grad_norm": 0.8409309983253479, "learning_rate": 3.223743775814663e-06, "loss": 0.501, "step": 2235 }, { "epoch": 2.5041075429424944, "grad_norm": 0.8440718650817871, "learning_rate": 3.222312255624456e-06, "loss": 0.5151, "step": 2236 }, { "epoch": 2.505227781926811, "grad_norm": 0.8704239726066589, "learning_rate": 3.2208804769849967e-06, "loss": 0.4973, "step": 2237 }, { "epoch": 2.506348020911128, "grad_norm": 0.8592371344566345, "learning_rate": 3.2194484404085867e-06, "loss": 0.4913, "step": 2238 }, { "epoch": 2.507468259895444, "grad_norm": 0.8596307635307312, "learning_rate": 3.218016146407619e-06, "loss": 0.5126, "step": 2239 }, { "epoch": 2.508588498879761, "grad_norm": 0.826443612575531, "learning_rate": 3.2165835954945823e-06, "loss": 0.4961, "step": 2240 }, { "epoch": 2.5097087378640777, "grad_norm": 0.8654544353485107, "learning_rate": 3.215150788182055e-06, "loss": 0.5156, "step": 2241 }, { "epoch": 2.5108289768483942, "grad_norm": 0.8411900997161865, "learning_rate": 3.2137177249827058e-06, "loss": 0.5087, "step": 2242 }, { "epoch": 2.5119492158327112, "grad_norm": 0.8518447875976562, "learning_rate": 3.2122844064092966e-06, "loss": 0.4792, "step": 2243 }, { "epoch": 2.5130694548170274, "grad_norm": 0.8505799174308777, "learning_rate": 3.2108508329746816e-06, "loss": 0.516, "step": 2244 }, { "epoch": 2.5141896938013444, "grad_norm": 0.8669551014900208, "learning_rate": 3.209417005191805e-06, "loss": 0.5077, "step": 2245 }, { "epoch": 2.515309932785661, "grad_norm": 0.8504314422607422, "learning_rate": 3.2079829235737014e-06, "loss": 0.4974, "step": 2246 }, { "epoch": 2.5164301717699775, "grad_norm": 0.870469331741333, "learning_rate": 3.2065485886334974e-06, "loss": 0.4754, "step": 2247 }, { "epoch": 2.517550410754294, "grad_norm": 0.8379542827606201, "learning_rate": 3.20511400088441e-06, "loss": 0.541, "step": 2248 }, { "epoch": 2.5186706497386107, "grad_norm": 0.8724898099899292, "learning_rate": 3.2036791608397465e-06, "loss": 0.4879, "step": 2249 }, { "epoch": 2.5197908887229277, "grad_norm": 0.8554635047912598, "learning_rate": 3.202244069012904e-06, "loss": 0.5315, "step": 2250 }, { "epoch": 2.5209111277072442, "grad_norm": 0.8781859874725342, "learning_rate": 3.20080872591737e-06, "loss": 0.527, "step": 2251 }, { "epoch": 2.522031366691561, "grad_norm": 0.8610695004463196, "learning_rate": 3.1993731320667222e-06, "loss": 0.5213, "step": 2252 }, { "epoch": 2.5231516056758774, "grad_norm": 0.8765854835510254, "learning_rate": 3.1979372879746285e-06, "loss": 0.5016, "step": 2253 }, { "epoch": 2.524271844660194, "grad_norm": 0.8472765684127808, "learning_rate": 3.1965011941548454e-06, "loss": 0.507, "step": 2254 }, { "epoch": 2.525392083644511, "grad_norm": 0.867659866809845, "learning_rate": 3.1950648511212182e-06, "loss": 0.5193, "step": 2255 }, { "epoch": 2.5265123226288275, "grad_norm": 0.8853083252906799, "learning_rate": 3.1936282593876844e-06, "loss": 0.5213, "step": 2256 }, { "epoch": 2.527632561613144, "grad_norm": 0.8362092971801758, "learning_rate": 3.1921914194682652e-06, "loss": 0.4976, "step": 2257 }, { "epoch": 2.5287528005974607, "grad_norm": 0.8529360294342041, "learning_rate": 3.190754331877076e-06, "loss": 0.5055, "step": 2258 }, { "epoch": 2.5298730395817772, "grad_norm": 0.8700896501541138, "learning_rate": 3.1893169971283177e-06, "loss": 0.5175, "step": 2259 }, { "epoch": 2.5309932785660942, "grad_norm": 0.8914162516593933, "learning_rate": 3.187879415736281e-06, "loss": 0.524, "step": 2260 }, { "epoch": 2.532113517550411, "grad_norm": 0.8478696346282959, "learning_rate": 3.186441588215344e-06, "loss": 0.4854, "step": 2261 }, { "epoch": 2.5332337565347274, "grad_norm": 0.8528444766998291, "learning_rate": 3.1850035150799728e-06, "loss": 0.5039, "step": 2262 }, { "epoch": 2.534353995519044, "grad_norm": 0.8406314253807068, "learning_rate": 3.1835651968447225e-06, "loss": 0.5033, "step": 2263 }, { "epoch": 2.5354742345033605, "grad_norm": 0.9195207357406616, "learning_rate": 3.182126634024235e-06, "loss": 0.4884, "step": 2264 }, { "epoch": 2.5365944734876775, "grad_norm": 0.8332640528678894, "learning_rate": 3.180687827133239e-06, "loss": 0.4934, "step": 2265 }, { "epoch": 2.537714712471994, "grad_norm": 0.8233417868614197, "learning_rate": 3.1792487766865527e-06, "loss": 0.5013, "step": 2266 }, { "epoch": 2.5388349514563107, "grad_norm": 0.8668580651283264, "learning_rate": 3.177809483199079e-06, "loss": 0.5219, "step": 2267 }, { "epoch": 2.5399551904406272, "grad_norm": 0.8715213537216187, "learning_rate": 3.17636994718581e-06, "loss": 0.5071, "step": 2268 }, { "epoch": 2.541075429424944, "grad_norm": 0.8468725085258484, "learning_rate": 3.174930169161823e-06, "loss": 0.4952, "step": 2269 }, { "epoch": 2.542195668409261, "grad_norm": 0.8500487208366394, "learning_rate": 3.173490149642282e-06, "loss": 0.4976, "step": 2270 }, { "epoch": 2.5433159073935774, "grad_norm": 0.8467937111854553, "learning_rate": 3.1720498891424382e-06, "loss": 0.5427, "step": 2271 }, { "epoch": 2.544436146377894, "grad_norm": 0.8808364272117615, "learning_rate": 3.1706093881776283e-06, "loss": 0.5016, "step": 2272 }, { "epoch": 2.5455563853622105, "grad_norm": 0.8626870512962341, "learning_rate": 3.1691686472632764e-06, "loss": 0.5019, "step": 2273 }, { "epoch": 2.546676624346527, "grad_norm": 0.853863000869751, "learning_rate": 3.1677276669148904e-06, "loss": 0.5017, "step": 2274 }, { "epoch": 2.547796863330844, "grad_norm": 0.873598039150238, "learning_rate": 3.1662864476480655e-06, "loss": 0.5109, "step": 2275 }, { "epoch": 2.5489171023151607, "grad_norm": 0.8360571265220642, "learning_rate": 3.1648449899784812e-06, "loss": 0.4851, "step": 2276 }, { "epoch": 2.5500373412994772, "grad_norm": 0.8515551090240479, "learning_rate": 3.163403294421903e-06, "loss": 0.4779, "step": 2277 }, { "epoch": 2.551157580283794, "grad_norm": 0.8656654953956604, "learning_rate": 3.1619613614941818e-06, "loss": 0.5017, "step": 2278 }, { "epoch": 2.5522778192681104, "grad_norm": 0.8253311514854431, "learning_rate": 3.160519191711252e-06, "loss": 0.4855, "step": 2279 }, { "epoch": 2.5533980582524274, "grad_norm": 0.8128666281700134, "learning_rate": 3.159076785589136e-06, "loss": 0.5061, "step": 2280 }, { "epoch": 2.554518297236744, "grad_norm": 0.8662984371185303, "learning_rate": 3.157634143643936e-06, "loss": 0.5085, "step": 2281 }, { "epoch": 2.5556385362210605, "grad_norm": 0.8589586615562439, "learning_rate": 3.1561912663918428e-06, "loss": 0.5027, "step": 2282 }, { "epoch": 2.556758775205377, "grad_norm": 0.8686463236808777, "learning_rate": 3.1547481543491292e-06, "loss": 0.5046, "step": 2283 }, { "epoch": 2.5578790141896937, "grad_norm": 0.8754316568374634, "learning_rate": 3.153304808032152e-06, "loss": 0.5153, "step": 2284 }, { "epoch": 2.5589992531740107, "grad_norm": 0.8793729543685913, "learning_rate": 3.1518612279573534e-06, "loss": 0.4961, "step": 2285 }, { "epoch": 2.5601194921583272, "grad_norm": 0.8859439492225647, "learning_rate": 3.150417414641257e-06, "loss": 0.5197, "step": 2286 }, { "epoch": 2.561239731142644, "grad_norm": 0.8563268780708313, "learning_rate": 3.148973368600472e-06, "loss": 0.4964, "step": 2287 }, { "epoch": 2.5623599701269604, "grad_norm": 0.8604695200920105, "learning_rate": 3.1475290903516904e-06, "loss": 0.5073, "step": 2288 }, { "epoch": 2.563480209111277, "grad_norm": 0.834644079208374, "learning_rate": 3.1460845804116858e-06, "loss": 0.4882, "step": 2289 }, { "epoch": 2.564600448095594, "grad_norm": 0.8490285277366638, "learning_rate": 3.144639839297315e-06, "loss": 0.5161, "step": 2290 }, { "epoch": 2.5657206870799105, "grad_norm": 0.83893883228302, "learning_rate": 3.1431948675255195e-06, "loss": 0.4855, "step": 2291 }, { "epoch": 2.566840926064227, "grad_norm": 0.8559224009513855, "learning_rate": 3.141749665613322e-06, "loss": 0.5165, "step": 2292 }, { "epoch": 2.5679611650485437, "grad_norm": 0.8598194122314453, "learning_rate": 3.1403042340778276e-06, "loss": 0.5053, "step": 2293 }, { "epoch": 2.5690814040328602, "grad_norm": 0.826887845993042, "learning_rate": 3.1388585734362233e-06, "loss": 0.5041, "step": 2294 }, { "epoch": 2.5702016430171772, "grad_norm": 0.8546226620674133, "learning_rate": 3.1374126842057783e-06, "loss": 0.4969, "step": 2295 }, { "epoch": 2.571321882001494, "grad_norm": 0.875771164894104, "learning_rate": 3.135966566903844e-06, "loss": 0.5159, "step": 2296 }, { "epoch": 2.5724421209858104, "grad_norm": 0.877555787563324, "learning_rate": 3.134520222047852e-06, "loss": 0.4801, "step": 2297 }, { "epoch": 2.573562359970127, "grad_norm": 0.8296717405319214, "learning_rate": 3.133073650155318e-06, "loss": 0.4999, "step": 2298 }, { "epoch": 2.5746825989544435, "grad_norm": 0.8727453947067261, "learning_rate": 3.1316268517438354e-06, "loss": 0.4902, "step": 2299 }, { "epoch": 2.5758028379387605, "grad_norm": 0.8608389496803284, "learning_rate": 3.1301798273310818e-06, "loss": 0.4756, "step": 2300 }, { "epoch": 2.5769230769230766, "grad_norm": 0.8369489312171936, "learning_rate": 3.1287325774348143e-06, "loss": 0.4899, "step": 2301 }, { "epoch": 2.5780433159073937, "grad_norm": 0.8775545954704285, "learning_rate": 3.1272851025728705e-06, "loss": 0.516, "step": 2302 }, { "epoch": 2.5791635548917102, "grad_norm": 0.8843596577644348, "learning_rate": 3.1258374032631694e-06, "loss": 0.5102, "step": 2303 }, { "epoch": 2.580283793876027, "grad_norm": 0.8720864653587341, "learning_rate": 3.1243894800237085e-06, "loss": 0.5027, "step": 2304 }, { "epoch": 2.581404032860344, "grad_norm": 0.8487012982368469, "learning_rate": 3.122941333372568e-06, "loss": 0.5108, "step": 2305 }, { "epoch": 2.58252427184466, "grad_norm": 0.8674491047859192, "learning_rate": 3.1214929638279058e-06, "loss": 0.5252, "step": 2306 }, { "epoch": 2.583644510828977, "grad_norm": 0.8482593894004822, "learning_rate": 3.12004437190796e-06, "loss": 0.511, "step": 2307 }, { "epoch": 2.5847647498132935, "grad_norm": 0.8408525586128235, "learning_rate": 3.1185955581310503e-06, "loss": 0.4893, "step": 2308 }, { "epoch": 2.58588498879761, "grad_norm": 0.8581867218017578, "learning_rate": 3.1171465230155724e-06, "loss": 0.51, "step": 2309 }, { "epoch": 2.5870052277819267, "grad_norm": 0.872101902961731, "learning_rate": 3.115697267080004e-06, "loss": 0.5238, "step": 2310 }, { "epoch": 2.588125466766243, "grad_norm": 0.8767650127410889, "learning_rate": 3.1142477908429004e-06, "loss": 0.5102, "step": 2311 }, { "epoch": 2.5892457057505602, "grad_norm": 0.8765872716903687, "learning_rate": 3.112798094822896e-06, "loss": 0.5085, "step": 2312 }, { "epoch": 2.590365944734877, "grad_norm": 0.851503312587738, "learning_rate": 3.111348179538704e-06, "loss": 0.5256, "step": 2313 }, { "epoch": 2.5914861837191934, "grad_norm": 0.8170521259307861, "learning_rate": 3.109898045509116e-06, "loss": 0.4838, "step": 2314 }, { "epoch": 2.59260642270351, "grad_norm": 0.8554751873016357, "learning_rate": 3.1084476932530027e-06, "loss": 0.4979, "step": 2315 }, { "epoch": 2.5937266616878265, "grad_norm": 0.8707568645477295, "learning_rate": 3.1069971232893108e-06, "loss": 0.503, "step": 2316 }, { "epoch": 2.5948469006721435, "grad_norm": 0.8619703054428101, "learning_rate": 3.1055463361370666e-06, "loss": 0.5065, "step": 2317 }, { "epoch": 2.59596713965646, "grad_norm": 0.8812270164489746, "learning_rate": 3.1040953323153737e-06, "loss": 0.4923, "step": 2318 }, { "epoch": 2.5970873786407767, "grad_norm": 0.8786489367485046, "learning_rate": 3.1026441123434127e-06, "loss": 0.5056, "step": 2319 }, { "epoch": 2.5982076176250932, "grad_norm": 0.8664147853851318, "learning_rate": 3.1011926767404433e-06, "loss": 0.5064, "step": 2320 }, { "epoch": 2.59932785660941, "grad_norm": 0.896233856678009, "learning_rate": 3.0997410260257995e-06, "loss": 0.4897, "step": 2321 }, { "epoch": 2.600448095593727, "grad_norm": 0.8755943775177002, "learning_rate": 3.0982891607188948e-06, "loss": 0.5049, "step": 2322 }, { "epoch": 2.6015683345780434, "grad_norm": 0.8787568807601929, "learning_rate": 3.0968370813392184e-06, "loss": 0.4582, "step": 2323 }, { "epoch": 2.60268857356236, "grad_norm": 0.8649211525917053, "learning_rate": 3.095384788406336e-06, "loss": 0.496, "step": 2324 }, { "epoch": 2.6038088125466765, "grad_norm": 0.8402095437049866, "learning_rate": 3.0939322824398898e-06, "loss": 0.4866, "step": 2325 }, { "epoch": 2.604929051530993, "grad_norm": 0.8820649981498718, "learning_rate": 3.092479563959599e-06, "loss": 0.5087, "step": 2326 }, { "epoch": 2.60604929051531, "grad_norm": 0.8772176504135132, "learning_rate": 3.091026633485258e-06, "loss": 0.5183, "step": 2327 }, { "epoch": 2.6071695294996267, "grad_norm": 0.8521697521209717, "learning_rate": 3.089573491536736e-06, "loss": 0.4914, "step": 2328 }, { "epoch": 2.6082897684839432, "grad_norm": 0.8851868510246277, "learning_rate": 3.088120138633981e-06, "loss": 0.5279, "step": 2329 }, { "epoch": 2.60941000746826, "grad_norm": 0.8758088946342468, "learning_rate": 3.086666575297014e-06, "loss": 0.5149, "step": 2330 }, { "epoch": 2.6105302464525764, "grad_norm": 0.8580572009086609, "learning_rate": 3.085212802045931e-06, "loss": 0.4742, "step": 2331 }, { "epoch": 2.6116504854368934, "grad_norm": 0.8293384313583374, "learning_rate": 3.0837588194009043e-06, "loss": 0.4732, "step": 2332 }, { "epoch": 2.61277072442121, "grad_norm": 0.8433744311332703, "learning_rate": 3.0823046278821823e-06, "loss": 0.5185, "step": 2333 }, { "epoch": 2.6138909634055265, "grad_norm": 0.897965669631958, "learning_rate": 3.0808502280100842e-06, "loss": 0.5027, "step": 2334 }, { "epoch": 2.615011202389843, "grad_norm": 0.846929669380188, "learning_rate": 3.0793956203050084e-06, "loss": 0.508, "step": 2335 }, { "epoch": 2.6161314413741596, "grad_norm": 0.8433253765106201, "learning_rate": 3.077940805287425e-06, "loss": 0.4897, "step": 2336 }, { "epoch": 2.6172516803584767, "grad_norm": 0.8623118996620178, "learning_rate": 3.0764857834778772e-06, "loss": 0.5123, "step": 2337 }, { "epoch": 2.6183719193427932, "grad_norm": 0.9227802753448486, "learning_rate": 3.0750305553969855e-06, "loss": 0.5031, "step": 2338 }, { "epoch": 2.61949215832711, "grad_norm": 0.8735331892967224, "learning_rate": 3.073575121565442e-06, "loss": 0.5086, "step": 2339 }, { "epoch": 2.6206123973114264, "grad_norm": 0.8640878200531006, "learning_rate": 3.0721194825040125e-06, "loss": 0.4986, "step": 2340 }, { "epoch": 2.621732636295743, "grad_norm": 0.8609946370124817, "learning_rate": 3.0706636387335366e-06, "loss": 0.5116, "step": 2341 }, { "epoch": 2.62285287528006, "grad_norm": 0.8769159913063049, "learning_rate": 3.0692075907749276e-06, "loss": 0.4831, "step": 2342 }, { "epoch": 2.6239731142643765, "grad_norm": 0.868038535118103, "learning_rate": 3.0677513391491713e-06, "loss": 0.4866, "step": 2343 }, { "epoch": 2.625093353248693, "grad_norm": 0.8561162948608398, "learning_rate": 3.066294884377326e-06, "loss": 0.4967, "step": 2344 }, { "epoch": 2.6262135922330097, "grad_norm": 0.8393054604530334, "learning_rate": 3.064838226980524e-06, "loss": 0.483, "step": 2345 }, { "epoch": 2.627333831217326, "grad_norm": 0.843198299407959, "learning_rate": 3.0633813674799683e-06, "loss": 0.4916, "step": 2346 }, { "epoch": 2.6284540702016432, "grad_norm": 0.8483894467353821, "learning_rate": 3.0619243063969363e-06, "loss": 0.4927, "step": 2347 }, { "epoch": 2.62957430918596, "grad_norm": 0.9489533305168152, "learning_rate": 3.060467044252775e-06, "loss": 0.5067, "step": 2348 }, { "epoch": 2.6306945481702764, "grad_norm": 0.8475867509841919, "learning_rate": 3.059009581568907e-06, "loss": 0.5065, "step": 2349 }, { "epoch": 2.631814787154593, "grad_norm": 0.8757182955741882, "learning_rate": 3.0575519188668218e-06, "loss": 0.5135, "step": 2350 }, { "epoch": 2.6329350261389095, "grad_norm": 0.8705437779426575, "learning_rate": 3.056094056668084e-06, "loss": 0.5082, "step": 2351 }, { "epoch": 2.6340552651232265, "grad_norm": 0.8706598281860352, "learning_rate": 3.0546359954943295e-06, "loss": 0.5049, "step": 2352 }, { "epoch": 2.635175504107543, "grad_norm": 0.8445271253585815, "learning_rate": 3.0531777358672636e-06, "loss": 0.5065, "step": 2353 }, { "epoch": 2.6362957430918597, "grad_norm": 0.8397110104560852, "learning_rate": 3.0517192783086645e-06, "loss": 0.4993, "step": 2354 }, { "epoch": 2.6374159820761762, "grad_norm": 0.8805637359619141, "learning_rate": 3.050260623340379e-06, "loss": 0.4987, "step": 2355 }, { "epoch": 2.638536221060493, "grad_norm": 0.8420522212982178, "learning_rate": 3.0488017714843276e-06, "loss": 0.4906, "step": 2356 }, { "epoch": 2.63965646004481, "grad_norm": 0.8677417039871216, "learning_rate": 3.0473427232624973e-06, "loss": 0.4824, "step": 2357 }, { "epoch": 2.6407766990291264, "grad_norm": 0.8870840072631836, "learning_rate": 3.045883479196948e-06, "loss": 0.5144, "step": 2358 }, { "epoch": 2.641896938013443, "grad_norm": 0.9830486178398132, "learning_rate": 3.0444240398098114e-06, "loss": 0.5111, "step": 2359 }, { "epoch": 2.6430171769977595, "grad_norm": 0.8618080615997314, "learning_rate": 3.0429644056232852e-06, "loss": 0.4875, "step": 2360 }, { "epoch": 2.644137415982076, "grad_norm": 0.8597109317779541, "learning_rate": 3.041504577159638e-06, "loss": 0.5136, "step": 2361 }, { "epoch": 2.645257654966393, "grad_norm": 0.8126705288887024, "learning_rate": 3.0400445549412096e-06, "loss": 0.4807, "step": 2362 }, { "epoch": 2.646377893950709, "grad_norm": 0.8725939989089966, "learning_rate": 3.0385843394904067e-06, "loss": 0.5201, "step": 2363 }, { "epoch": 2.6474981329350262, "grad_norm": 0.8507259488105774, "learning_rate": 3.037123931329707e-06, "loss": 0.4858, "step": 2364 }, { "epoch": 2.648618371919343, "grad_norm": 0.8696798086166382, "learning_rate": 3.0356633309816563e-06, "loss": 0.4996, "step": 2365 }, { "epoch": 2.6497386109036594, "grad_norm": 0.8645357489585876, "learning_rate": 3.03420253896887e-06, "loss": 0.494, "step": 2366 }, { "epoch": 2.6508588498879764, "grad_norm": 0.8421913981437683, "learning_rate": 3.0327415558140316e-06, "loss": 0.48, "step": 2367 }, { "epoch": 2.6519790888722925, "grad_norm": 0.8547452688217163, "learning_rate": 3.0312803820398917e-06, "loss": 0.4895, "step": 2368 }, { "epoch": 2.6530993278566095, "grad_norm": 0.8346211910247803, "learning_rate": 3.029819018169271e-06, "loss": 0.4891, "step": 2369 }, { "epoch": 2.654219566840926, "grad_norm": 0.9009495973587036, "learning_rate": 3.028357464725058e-06, "loss": 0.5312, "step": 2370 }, { "epoch": 2.6553398058252426, "grad_norm": 0.9038102030754089, "learning_rate": 3.0268957222302076e-06, "loss": 0.4917, "step": 2371 }, { "epoch": 2.656460044809559, "grad_norm": 0.850988507270813, "learning_rate": 3.025433791207743e-06, "loss": 0.4856, "step": 2372 }, { "epoch": 2.657580283793876, "grad_norm": 0.8733913898468018, "learning_rate": 3.0239716721807567e-06, "loss": 0.4756, "step": 2373 }, { "epoch": 2.658700522778193, "grad_norm": 0.8819043040275574, "learning_rate": 3.022509365672405e-06, "loss": 0.519, "step": 2374 }, { "epoch": 2.6598207617625094, "grad_norm": 0.8623571395874023, "learning_rate": 3.0210468722059143e-06, "loss": 0.4984, "step": 2375 }, { "epoch": 2.660941000746826, "grad_norm": 0.8807154893875122, "learning_rate": 3.019584192304577e-06, "loss": 0.4936, "step": 2376 }, { "epoch": 2.6620612397311425, "grad_norm": 0.8504209518432617, "learning_rate": 3.0181213264917514e-06, "loss": 0.4965, "step": 2377 }, { "epoch": 2.663181478715459, "grad_norm": 0.8873822689056396, "learning_rate": 3.0166582752908624e-06, "loss": 0.5087, "step": 2378 }, { "epoch": 2.664301717699776, "grad_norm": 0.850253701210022, "learning_rate": 3.0151950392254025e-06, "loss": 0.4973, "step": 2379 }, { "epoch": 2.6654219566840927, "grad_norm": 0.8492952585220337, "learning_rate": 3.0137316188189303e-06, "loss": 0.4565, "step": 2380 }, { "epoch": 2.666542195668409, "grad_norm": 0.8439289927482605, "learning_rate": 3.012268014595068e-06, "loss": 0.4984, "step": 2381 }, { "epoch": 2.667662434652726, "grad_norm": 0.8757115006446838, "learning_rate": 3.0108042270775054e-06, "loss": 0.5242, "step": 2382 }, { "epoch": 2.6687826736370424, "grad_norm": 0.8562095165252686, "learning_rate": 3.0093402567899993e-06, "loss": 0.468, "step": 2383 }, { "epoch": 2.6699029126213594, "grad_norm": 0.8343717455863953, "learning_rate": 3.0078761042563687e-06, "loss": 0.4794, "step": 2384 }, { "epoch": 2.671023151605676, "grad_norm": 0.8829678297042847, "learning_rate": 3.0064117700004996e-06, "loss": 0.4904, "step": 2385 }, { "epoch": 2.6721433905899925, "grad_norm": 0.8728051781654358, "learning_rate": 3.0049472545463438e-06, "loss": 0.491, "step": 2386 }, { "epoch": 2.673263629574309, "grad_norm": 0.8628445267677307, "learning_rate": 3.003482558417916e-06, "loss": 0.4857, "step": 2387 }, { "epoch": 2.6743838685586256, "grad_norm": 0.8683882355690002, "learning_rate": 3.0020176821392965e-06, "loss": 0.5073, "step": 2388 }, { "epoch": 2.6755041075429427, "grad_norm": 0.8757364153862, "learning_rate": 3.0005526262346307e-06, "loss": 0.4957, "step": 2389 }, { "epoch": 2.6766243465272592, "grad_norm": 0.8593702912330627, "learning_rate": 2.999087391228127e-06, "loss": 0.5127, "step": 2390 }, { "epoch": 2.677744585511576, "grad_norm": 0.8934119343757629, "learning_rate": 2.9976219776440583e-06, "loss": 0.5204, "step": 2391 }, { "epoch": 2.6788648244958924, "grad_norm": 0.8637343049049377, "learning_rate": 2.996156386006763e-06, "loss": 0.5099, "step": 2392 }, { "epoch": 2.679985063480209, "grad_norm": 0.8718932271003723, "learning_rate": 2.99469061684064e-06, "loss": 0.521, "step": 2393 }, { "epoch": 2.681105302464526, "grad_norm": 0.8932037949562073, "learning_rate": 2.993224670670155e-06, "loss": 0.4949, "step": 2394 }, { "epoch": 2.6822255414488425, "grad_norm": 0.8508710861206055, "learning_rate": 2.991758548019835e-06, "loss": 0.5034, "step": 2395 }, { "epoch": 2.683345780433159, "grad_norm": 0.8577131628990173, "learning_rate": 2.9902922494142704e-06, "loss": 0.5038, "step": 2396 }, { "epoch": 2.6844660194174756, "grad_norm": 0.8710799217224121, "learning_rate": 2.9888257753781156e-06, "loss": 0.4913, "step": 2397 }, { "epoch": 2.685586258401792, "grad_norm": 0.8628936409950256, "learning_rate": 2.9873591264360857e-06, "loss": 0.4921, "step": 2398 }, { "epoch": 2.6867064973861092, "grad_norm": 0.8444120287895203, "learning_rate": 2.985892303112961e-06, "loss": 0.4959, "step": 2399 }, { "epoch": 2.687826736370426, "grad_norm": 0.8642388582229614, "learning_rate": 2.984425305933583e-06, "loss": 0.4841, "step": 2400 }, { "epoch": 2.6889469753547424, "grad_norm": 0.8402368426322937, "learning_rate": 2.982958135422855e-06, "loss": 0.481, "step": 2401 }, { "epoch": 2.690067214339059, "grad_norm": 0.8632341027259827, "learning_rate": 2.9814907921057417e-06, "loss": 0.4889, "step": 2402 }, { "epoch": 2.6911874533233755, "grad_norm": 0.8587676286697388, "learning_rate": 2.9800232765072724e-06, "loss": 0.5013, "step": 2403 }, { "epoch": 2.6923076923076925, "grad_norm": 0.8571732640266418, "learning_rate": 2.9785555891525353e-06, "loss": 0.5015, "step": 2404 }, { "epoch": 2.693427931292009, "grad_norm": 0.8795887231826782, "learning_rate": 2.9770877305666795e-06, "loss": 0.495, "step": 2405 }, { "epoch": 2.6945481702763256, "grad_norm": 0.8554339408874512, "learning_rate": 2.9756197012749195e-06, "loss": 0.4866, "step": 2406 }, { "epoch": 2.695668409260642, "grad_norm": 0.8625249862670898, "learning_rate": 2.974151501802527e-06, "loss": 0.4865, "step": 2407 }, { "epoch": 2.696788648244959, "grad_norm": 0.8751096725463867, "learning_rate": 2.972683132674835e-06, "loss": 0.4937, "step": 2408 }, { "epoch": 2.697908887229276, "grad_norm": 0.8692423701286316, "learning_rate": 2.9712145944172398e-06, "loss": 0.5183, "step": 2409 }, { "epoch": 2.6990291262135924, "grad_norm": 0.8435822129249573, "learning_rate": 2.9697458875551956e-06, "loss": 0.5012, "step": 2410 }, { "epoch": 2.700149365197909, "grad_norm": 0.836523711681366, "learning_rate": 2.9682770126142163e-06, "loss": 0.5291, "step": 2411 }, { "epoch": 2.7012696041822255, "grad_norm": 0.8764259815216064, "learning_rate": 2.9668079701198793e-06, "loss": 0.529, "step": 2412 }, { "epoch": 2.702389843166542, "grad_norm": 0.8949002027511597, "learning_rate": 2.96533876059782e-06, "loss": 0.4933, "step": 2413 }, { "epoch": 2.703510082150859, "grad_norm": 0.8729102611541748, "learning_rate": 2.9638693845737336e-06, "loss": 0.5073, "step": 2414 }, { "epoch": 2.7046303211351757, "grad_norm": 0.8688413500785828, "learning_rate": 2.9623998425733734e-06, "loss": 0.5041, "step": 2415 }, { "epoch": 2.705750560119492, "grad_norm": 0.8891053795814514, "learning_rate": 2.9609301351225555e-06, "loss": 0.5078, "step": 2416 }, { "epoch": 2.706870799103809, "grad_norm": 0.8614200949668884, "learning_rate": 2.9594602627471524e-06, "loss": 0.4937, "step": 2417 }, { "epoch": 2.7079910380881254, "grad_norm": 0.8369882702827454, "learning_rate": 2.957990225973096e-06, "loss": 0.503, "step": 2418 }, { "epoch": 2.7091112770724424, "grad_norm": 0.8833905458450317, "learning_rate": 2.956520025326378e-06, "loss": 0.4829, "step": 2419 }, { "epoch": 2.710231516056759, "grad_norm": 0.8580949306488037, "learning_rate": 2.955049661333049e-06, "loss": 0.4995, "step": 2420 }, { "epoch": 2.7113517550410755, "grad_norm": 0.8628931045532227, "learning_rate": 2.9535791345192167e-06, "loss": 0.5065, "step": 2421 }, { "epoch": 2.712471994025392, "grad_norm": 0.8835195302963257, "learning_rate": 2.9521084454110466e-06, "loss": 0.507, "step": 2422 }, { "epoch": 2.7135922330097086, "grad_norm": 0.9092869758605957, "learning_rate": 2.950637594534765e-06, "loss": 0.495, "step": 2423 }, { "epoch": 2.7147124719940257, "grad_norm": 0.8806353807449341, "learning_rate": 2.9491665824166536e-06, "loss": 0.527, "step": 2424 }, { "epoch": 2.715832710978342, "grad_norm": 0.8758179545402527, "learning_rate": 2.9476954095830517e-06, "loss": 0.5066, "step": 2425 }, { "epoch": 2.716952949962659, "grad_norm": 0.8730995655059814, "learning_rate": 2.9462240765603597e-06, "loss": 0.5045, "step": 2426 }, { "epoch": 2.7180731889469754, "grad_norm": 0.8930565714836121, "learning_rate": 2.94475258387503e-06, "loss": 0.4751, "step": 2427 }, { "epoch": 2.719193427931292, "grad_norm": 0.8398765325546265, "learning_rate": 2.9432809320535767e-06, "loss": 0.5051, "step": 2428 }, { "epoch": 2.7203136669156085, "grad_norm": 0.8807529211044312, "learning_rate": 2.941809121622567e-06, "loss": 0.4963, "step": 2429 }, { "epoch": 2.721433905899925, "grad_norm": 0.8392361402511597, "learning_rate": 2.940337153108628e-06, "loss": 0.4962, "step": 2430 }, { "epoch": 2.722554144884242, "grad_norm": 0.9106119275093079, "learning_rate": 2.9388650270384415e-06, "loss": 0.4733, "step": 2431 }, { "epoch": 2.7236743838685586, "grad_norm": 0.8861887454986572, "learning_rate": 2.9373927439387468e-06, "loss": 0.5126, "step": 2432 }, { "epoch": 2.724794622852875, "grad_norm": 0.8502021431922913, "learning_rate": 2.9359203043363387e-06, "loss": 0.5046, "step": 2433 }, { "epoch": 2.725914861837192, "grad_norm": 0.8468950390815735, "learning_rate": 2.9344477087580687e-06, "loss": 0.4998, "step": 2434 }, { "epoch": 2.7270351008215084, "grad_norm": 0.8743936419487, "learning_rate": 2.932974957730842e-06, "loss": 0.5038, "step": 2435 }, { "epoch": 2.7281553398058254, "grad_norm": 0.852532148361206, "learning_rate": 2.9315020517816227e-06, "loss": 0.4888, "step": 2436 }, { "epoch": 2.729275578790142, "grad_norm": 0.8676307797431946, "learning_rate": 2.9300289914374287e-06, "loss": 0.5027, "step": 2437 }, { "epoch": 2.7303958177744585, "grad_norm": 0.8548722267150879, "learning_rate": 2.928555777225331e-06, "loss": 0.497, "step": 2438 }, { "epoch": 2.731516056758775, "grad_norm": 0.8914284110069275, "learning_rate": 2.9270824096724594e-06, "loss": 0.4908, "step": 2439 }, { "epoch": 2.7326362957430916, "grad_norm": 0.8795185089111328, "learning_rate": 2.925608889305997e-06, "loss": 0.524, "step": 2440 }, { "epoch": 2.7337565347274086, "grad_norm": 0.864770233631134, "learning_rate": 2.924135216653181e-06, "loss": 0.4924, "step": 2441 }, { "epoch": 2.734876773711725, "grad_norm": 0.8417432308197021, "learning_rate": 2.922661392241303e-06, "loss": 0.4782, "step": 2442 }, { "epoch": 2.735997012696042, "grad_norm": 0.8988954424858093, "learning_rate": 2.921187416597711e-06, "loss": 0.5168, "step": 2443 }, { "epoch": 2.7371172516803584, "grad_norm": 0.8535281419754028, "learning_rate": 2.9197132902498043e-06, "loss": 0.4803, "step": 2444 }, { "epoch": 2.738237490664675, "grad_norm": 0.8362544775009155, "learning_rate": 2.9182390137250376e-06, "loss": 0.4714, "step": 2445 }, { "epoch": 2.739357729648992, "grad_norm": 0.842233419418335, "learning_rate": 2.9167645875509193e-06, "loss": 0.473, "step": 2446 }, { "epoch": 2.7404779686333085, "grad_norm": 0.8494930267333984, "learning_rate": 2.9152900122550116e-06, "loss": 0.49, "step": 2447 }, { "epoch": 2.741598207617625, "grad_norm": 0.8490485548973083, "learning_rate": 2.913815288364929e-06, "loss": 0.4959, "step": 2448 }, { "epoch": 2.7427184466019416, "grad_norm": 0.8299700617790222, "learning_rate": 2.9123404164083403e-06, "loss": 0.4908, "step": 2449 }, { "epoch": 2.743838685586258, "grad_norm": 0.8653092980384827, "learning_rate": 2.910865396912966e-06, "loss": 0.4983, "step": 2450 }, { "epoch": 2.744958924570575, "grad_norm": 0.8607711791992188, "learning_rate": 2.9093902304065813e-06, "loss": 0.4741, "step": 2451 }, { "epoch": 2.746079163554892, "grad_norm": 0.844461977481842, "learning_rate": 2.9079149174170116e-06, "loss": 0.4886, "step": 2452 }, { "epoch": 2.7471994025392084, "grad_norm": 0.8855992555618286, "learning_rate": 2.906439458472138e-06, "loss": 0.5457, "step": 2453 }, { "epoch": 2.748319641523525, "grad_norm": 0.8756692409515381, "learning_rate": 2.90496385409989e-06, "loss": 0.5031, "step": 2454 }, { "epoch": 2.7494398805078415, "grad_norm": 0.865491509437561, "learning_rate": 2.903488104828251e-06, "loss": 0.4733, "step": 2455 }, { "epoch": 2.7505601194921585, "grad_norm": 0.8648385405540466, "learning_rate": 2.9020122111852574e-06, "loss": 0.4971, "step": 2456 }, { "epoch": 2.751680358476475, "grad_norm": 0.8742687106132507, "learning_rate": 2.900536173698995e-06, "loss": 0.5072, "step": 2457 }, { "epoch": 2.7528005974607916, "grad_norm": 0.8725389838218689, "learning_rate": 2.8990599928976026e-06, "loss": 0.4954, "step": 2458 }, { "epoch": 2.753920836445108, "grad_norm": 0.8771463632583618, "learning_rate": 2.897583669309269e-06, "loss": 0.5059, "step": 2459 }, { "epoch": 2.755041075429425, "grad_norm": 0.8856315612792969, "learning_rate": 2.896107203462236e-06, "loss": 0.5001, "step": 2460 }, { "epoch": 2.756161314413742, "grad_norm": 0.8620632290840149, "learning_rate": 2.8946305958847953e-06, "loss": 0.5024, "step": 2461 }, { "epoch": 2.7572815533980584, "grad_norm": 0.8758069276809692, "learning_rate": 2.8931538471052884e-06, "loss": 0.5115, "step": 2462 }, { "epoch": 2.758401792382375, "grad_norm": 0.8567253947257996, "learning_rate": 2.8916769576521086e-06, "loss": 0.4884, "step": 2463 }, { "epoch": 2.7595220313666915, "grad_norm": 0.8616679310798645, "learning_rate": 2.890199928053699e-06, "loss": 0.4916, "step": 2464 }, { "epoch": 2.760642270351008, "grad_norm": 0.8416816592216492, "learning_rate": 2.8887227588385518e-06, "loss": 0.4802, "step": 2465 }, { "epoch": 2.761762509335325, "grad_norm": 0.8369020223617554, "learning_rate": 2.887245450535212e-06, "loss": 0.5019, "step": 2466 }, { "epoch": 2.7628827483196416, "grad_norm": 0.8758065104484558, "learning_rate": 2.885768003672272e-06, "loss": 0.495, "step": 2467 }, { "epoch": 2.764002987303958, "grad_norm": 0.8446704745292664, "learning_rate": 2.8842904187783744e-06, "loss": 0.502, "step": 2468 }, { "epoch": 2.765123226288275, "grad_norm": 0.8771148324012756, "learning_rate": 2.8828126963822105e-06, "loss": 0.5322, "step": 2469 }, { "epoch": 2.7662434652725914, "grad_norm": 0.8560802340507507, "learning_rate": 2.881334837012523e-06, "loss": 0.4891, "step": 2470 }, { "epoch": 2.7673637042569084, "grad_norm": 0.8589470982551575, "learning_rate": 2.8798568411981e-06, "loss": 0.4728, "step": 2471 }, { "epoch": 2.768483943241225, "grad_norm": 0.8527939319610596, "learning_rate": 2.878378709467783e-06, "loss": 0.4712, "step": 2472 }, { "epoch": 2.7696041822255415, "grad_norm": 0.8786166906356812, "learning_rate": 2.876900442350458e-06, "loss": 0.468, "step": 2473 }, { "epoch": 2.770724421209858, "grad_norm": 0.8291136622428894, "learning_rate": 2.875422040375061e-06, "loss": 0.4982, "step": 2474 }, { "epoch": 2.7718446601941746, "grad_norm": 0.900550127029419, "learning_rate": 2.8739435040705777e-06, "loss": 0.484, "step": 2475 }, { "epoch": 2.7729648991784916, "grad_norm": 0.8594408631324768, "learning_rate": 2.872464833966039e-06, "loss": 0.5008, "step": 2476 }, { "epoch": 2.774085138162808, "grad_norm": 0.8992912769317627, "learning_rate": 2.870986030590527e-06, "loss": 0.4859, "step": 2477 }, { "epoch": 2.775205377147125, "grad_norm": 0.8712731003761292, "learning_rate": 2.8695070944731673e-06, "loss": 0.5245, "step": 2478 }, { "epoch": 2.7763256161314414, "grad_norm": 0.872295618057251, "learning_rate": 2.868028026143137e-06, "loss": 0.4929, "step": 2479 }, { "epoch": 2.777445855115758, "grad_norm": 0.8739529252052307, "learning_rate": 2.8665488261296594e-06, "loss": 0.5216, "step": 2480 }, { "epoch": 2.778566094100075, "grad_norm": 0.848881721496582, "learning_rate": 2.865069494962003e-06, "loss": 0.4865, "step": 2481 }, { "epoch": 2.7796863330843915, "grad_norm": 0.8745750188827515, "learning_rate": 2.863590033169485e-06, "loss": 0.503, "step": 2482 }, { "epoch": 2.780806572068708, "grad_norm": 0.8576851487159729, "learning_rate": 2.8621104412814692e-06, "loss": 0.5097, "step": 2483 }, { "epoch": 2.7819268110530246, "grad_norm": 0.8470255732536316, "learning_rate": 2.860630719827366e-06, "loss": 0.5138, "step": 2484 }, { "epoch": 2.783047050037341, "grad_norm": 0.848564624786377, "learning_rate": 2.8591508693366317e-06, "loss": 0.5033, "step": 2485 }, { "epoch": 2.784167289021658, "grad_norm": 0.8589666485786438, "learning_rate": 2.8576708903387677e-06, "loss": 0.4832, "step": 2486 }, { "epoch": 2.7852875280059743, "grad_norm": 0.8428047895431519, "learning_rate": 2.856190783363325e-06, "loss": 0.4902, "step": 2487 }, { "epoch": 2.7864077669902914, "grad_norm": 0.8564459681510925, "learning_rate": 2.8547105489398967e-06, "loss": 0.4954, "step": 2488 }, { "epoch": 2.787528005974608, "grad_norm": 0.8349265456199646, "learning_rate": 2.8532301875981226e-06, "loss": 0.4884, "step": 2489 }, { "epoch": 2.7886482449589245, "grad_norm": 0.8930822014808655, "learning_rate": 2.8517496998676884e-06, "loss": 0.5052, "step": 2490 }, { "epoch": 2.789768483943241, "grad_norm": 0.8711863160133362, "learning_rate": 2.850269086278325e-06, "loss": 0.4851, "step": 2491 }, { "epoch": 2.7908887229275576, "grad_norm": 0.8282707929611206, "learning_rate": 2.848788347359808e-06, "loss": 0.5081, "step": 2492 }, { "epoch": 2.7920089619118746, "grad_norm": 0.8801392316818237, "learning_rate": 2.8473074836419573e-06, "loss": 0.4994, "step": 2493 }, { "epoch": 2.793129200896191, "grad_norm": 0.8567204475402832, "learning_rate": 2.8458264956546396e-06, "loss": 0.5201, "step": 2494 }, { "epoch": 2.794249439880508, "grad_norm": 0.8866332769393921, "learning_rate": 2.844345383927763e-06, "loss": 0.4939, "step": 2495 }, { "epoch": 2.7953696788648243, "grad_norm": 0.8432731628417969, "learning_rate": 2.8428641489912817e-06, "loss": 0.5017, "step": 2496 }, { "epoch": 2.796489917849141, "grad_norm": 0.8859289884567261, "learning_rate": 2.8413827913751945e-06, "loss": 0.505, "step": 2497 }, { "epoch": 2.797610156833458, "grad_norm": 0.8460291028022766, "learning_rate": 2.839901311609542e-06, "loss": 0.5037, "step": 2498 }, { "epoch": 2.7987303958177745, "grad_norm": 0.8474265933036804, "learning_rate": 2.8384197102244116e-06, "loss": 0.513, "step": 2499 }, { "epoch": 2.799850634802091, "grad_norm": 0.854310929775238, "learning_rate": 2.836937987749931e-06, "loss": 0.5104, "step": 2500 }, { "epoch": 2.8009708737864076, "grad_norm": 0.8452836871147156, "learning_rate": 2.835456144716274e-06, "loss": 0.4921, "step": 2501 }, { "epoch": 2.802091112770724, "grad_norm": 0.8501790761947632, "learning_rate": 2.833974181653654e-06, "loss": 0.4897, "step": 2502 }, { "epoch": 2.803211351755041, "grad_norm": 0.8873399496078491, "learning_rate": 2.8324920990923323e-06, "loss": 0.498, "step": 2503 }, { "epoch": 2.804331590739358, "grad_norm": 0.8479447960853577, "learning_rate": 2.8310098975626076e-06, "loss": 0.489, "step": 2504 }, { "epoch": 2.8054518297236744, "grad_norm": 0.8633539080619812, "learning_rate": 2.8295275775948257e-06, "loss": 0.5023, "step": 2505 }, { "epoch": 2.806572068707991, "grad_norm": 0.891167402267456, "learning_rate": 2.828045139719372e-06, "loss": 0.5122, "step": 2506 }, { "epoch": 2.8076923076923075, "grad_norm": 0.8650275468826294, "learning_rate": 2.826562584466675e-06, "loss": 0.487, "step": 2507 }, { "epoch": 2.8088125466766245, "grad_norm": 0.862446129322052, "learning_rate": 2.8250799123672056e-06, "loss": 0.509, "step": 2508 }, { "epoch": 2.809932785660941, "grad_norm": 0.8905578255653381, "learning_rate": 2.823597123951475e-06, "loss": 0.5108, "step": 2509 }, { "epoch": 2.8110530246452576, "grad_norm": 0.8368377089500427, "learning_rate": 2.822114219750038e-06, "loss": 0.4671, "step": 2510 }, { "epoch": 2.812173263629574, "grad_norm": 0.8432770371437073, "learning_rate": 2.8206312002934895e-06, "loss": 0.5093, "step": 2511 }, { "epoch": 2.8132935026138908, "grad_norm": 0.9145288467407227, "learning_rate": 2.8191480661124664e-06, "loss": 0.5007, "step": 2512 }, { "epoch": 2.814413741598208, "grad_norm": 0.8606106638908386, "learning_rate": 2.8176648177376453e-06, "loss": 0.5012, "step": 2513 }, { "epoch": 2.8155339805825244, "grad_norm": 0.8530259132385254, "learning_rate": 2.816181455699746e-06, "loss": 0.4948, "step": 2514 }, { "epoch": 2.816654219566841, "grad_norm": 0.8375036120414734, "learning_rate": 2.8146979805295275e-06, "loss": 0.4741, "step": 2515 }, { "epoch": 2.8177744585511575, "grad_norm": 0.8396695852279663, "learning_rate": 2.813214392757788e-06, "loss": 0.4714, "step": 2516 }, { "epoch": 2.818894697535474, "grad_norm": 0.8519940376281738, "learning_rate": 2.8117306929153687e-06, "loss": 0.4915, "step": 2517 }, { "epoch": 2.820014936519791, "grad_norm": 0.8329366445541382, "learning_rate": 2.8102468815331487e-06, "loss": 0.5037, "step": 2518 }, { "epoch": 2.8211351755041076, "grad_norm": 0.8568314909934998, "learning_rate": 2.808762959142049e-06, "loss": 0.5232, "step": 2519 }, { "epoch": 2.822255414488424, "grad_norm": 0.8812794089317322, "learning_rate": 2.8072789262730277e-06, "loss": 0.5169, "step": 2520 }, { "epoch": 2.8233756534727408, "grad_norm": 0.856034517288208, "learning_rate": 2.8057947834570854e-06, "loss": 0.4764, "step": 2521 }, { "epoch": 2.8244958924570573, "grad_norm": 0.8641175031661987, "learning_rate": 2.80431053122526e-06, "loss": 0.4787, "step": 2522 }, { "epoch": 2.8256161314413744, "grad_norm": 0.8512842059135437, "learning_rate": 2.8028261701086285e-06, "loss": 0.5199, "step": 2523 }, { "epoch": 2.826736370425691, "grad_norm": 0.8573279976844788, "learning_rate": 2.8013417006383078e-06, "loss": 0.4868, "step": 2524 }, { "epoch": 2.8278566094100075, "grad_norm": 0.8996847867965698, "learning_rate": 2.799857123345454e-06, "loss": 0.5124, "step": 2525 }, { "epoch": 2.828976848394324, "grad_norm": 0.8502402901649475, "learning_rate": 2.79837243876126e-06, "loss": 0.4776, "step": 2526 }, { "epoch": 2.8300970873786406, "grad_norm": 0.889544665813446, "learning_rate": 2.7968876474169605e-06, "loss": 0.5068, "step": 2527 }, { "epoch": 2.8312173263629576, "grad_norm": 0.8850241303443909, "learning_rate": 2.795402749843823e-06, "loss": 0.4962, "step": 2528 }, { "epoch": 2.832337565347274, "grad_norm": 0.8504249453544617, "learning_rate": 2.793917746573157e-06, "loss": 0.4691, "step": 2529 }, { "epoch": 2.833457804331591, "grad_norm": 0.8746246099472046, "learning_rate": 2.79243263813631e-06, "loss": 0.5153, "step": 2530 }, { "epoch": 2.8345780433159073, "grad_norm": 0.8711211681365967, "learning_rate": 2.790947425064664e-06, "loss": 0.4949, "step": 2531 }, { "epoch": 2.835698282300224, "grad_norm": 0.8668767809867859, "learning_rate": 2.789462107889642e-06, "loss": 0.4682, "step": 2532 }, { "epoch": 2.836818521284541, "grad_norm": 0.8503642678260803, "learning_rate": 2.7879766871427022e-06, "loss": 0.5278, "step": 2533 }, { "epoch": 2.8379387602688575, "grad_norm": 0.8793665170669556, "learning_rate": 2.7864911633553402e-06, "loss": 0.51, "step": 2534 }, { "epoch": 2.839058999253174, "grad_norm": 0.8411306738853455, "learning_rate": 2.7850055370590895e-06, "loss": 0.4834, "step": 2535 }, { "epoch": 2.8401792382374906, "grad_norm": 0.8666971325874329, "learning_rate": 2.7835198087855176e-06, "loss": 0.4844, "step": 2536 }, { "epoch": 2.841299477221807, "grad_norm": 0.8778252601623535, "learning_rate": 2.782033979066232e-06, "loss": 0.5215, "step": 2537 }, { "epoch": 2.842419716206124, "grad_norm": 0.8797460198402405, "learning_rate": 2.7805480484328733e-06, "loss": 0.5016, "step": 2538 }, { "epoch": 2.843539955190441, "grad_norm": 0.8927376866340637, "learning_rate": 2.7790620174171213e-06, "loss": 0.4917, "step": 2539 }, { "epoch": 2.8446601941747574, "grad_norm": 0.8486242890357971, "learning_rate": 2.7775758865506886e-06, "loss": 0.5029, "step": 2540 }, { "epoch": 2.845780433159074, "grad_norm": 0.8546323776245117, "learning_rate": 2.7760896563653263e-06, "loss": 0.472, "step": 2541 }, { "epoch": 2.8469006721433905, "grad_norm": 0.8809824585914612, "learning_rate": 2.774603327392819e-06, "loss": 0.4991, "step": 2542 }, { "epoch": 2.8480209111277075, "grad_norm": 0.8782169222831726, "learning_rate": 2.7731169001649864e-06, "loss": 0.4974, "step": 2543 }, { "epoch": 2.8491411501120236, "grad_norm": 0.8729709982872009, "learning_rate": 2.7716303752136865e-06, "loss": 0.4924, "step": 2544 }, { "epoch": 2.8502613890963406, "grad_norm": 0.8596822619438171, "learning_rate": 2.770143753070809e-06, "loss": 0.5162, "step": 2545 }, { "epoch": 2.851381628080657, "grad_norm": 0.8613413572311401, "learning_rate": 2.7686570342682795e-06, "loss": 0.4895, "step": 2546 }, { "epoch": 2.8525018670649738, "grad_norm": 0.8631966710090637, "learning_rate": 2.7671702193380585e-06, "loss": 0.5084, "step": 2547 }, { "epoch": 2.853622106049291, "grad_norm": 0.9180245995521545, "learning_rate": 2.7656833088121403e-06, "loss": 0.492, "step": 2548 }, { "epoch": 2.854742345033607, "grad_norm": 0.8539132475852966, "learning_rate": 2.7641963032225536e-06, "loss": 0.4859, "step": 2549 }, { "epoch": 2.855862584017924, "grad_norm": 0.8613910675048828, "learning_rate": 2.7627092031013613e-06, "loss": 0.4925, "step": 2550 }, { "epoch": 2.8569828230022405, "grad_norm": 0.8804489374160767, "learning_rate": 2.76122200898066e-06, "loss": 0.4769, "step": 2551 }, { "epoch": 2.858103061986557, "grad_norm": 0.847905158996582, "learning_rate": 2.759734721392581e-06, "loss": 0.4941, "step": 2552 }, { "epoch": 2.8592233009708736, "grad_norm": 0.8646116256713867, "learning_rate": 2.7582473408692857e-06, "loss": 0.5145, "step": 2553 }, { "epoch": 2.86034353995519, "grad_norm": 0.9086596965789795, "learning_rate": 2.756759867942973e-06, "loss": 0.4856, "step": 2554 }, { "epoch": 2.861463778939507, "grad_norm": 0.8482518196105957, "learning_rate": 2.7552723031458727e-06, "loss": 0.501, "step": 2555 }, { "epoch": 2.8625840179238238, "grad_norm": 0.8859201073646545, "learning_rate": 2.753784647010247e-06, "loss": 0.5284, "step": 2556 }, { "epoch": 2.8637042569081403, "grad_norm": 0.8666086196899414, "learning_rate": 2.7522969000683912e-06, "loss": 0.4932, "step": 2557 }, { "epoch": 2.864824495892457, "grad_norm": 0.8424382209777832, "learning_rate": 2.7508090628526353e-06, "loss": 0.495, "step": 2558 }, { "epoch": 2.8659447348767735, "grad_norm": 0.8514565229415894, "learning_rate": 2.7493211358953377e-06, "loss": 0.5041, "step": 2559 }, { "epoch": 2.8670649738610905, "grad_norm": 0.8672460913658142, "learning_rate": 2.747833119728891e-06, "loss": 0.5037, "step": 2560 }, { "epoch": 2.868185212845407, "grad_norm": 0.9057784676551819, "learning_rate": 2.7463450148857206e-06, "loss": 0.4917, "step": 2561 }, { "epoch": 2.8693054518297236, "grad_norm": 0.8559522032737732, "learning_rate": 2.744856821898283e-06, "loss": 0.4959, "step": 2562 }, { "epoch": 2.87042569081404, "grad_norm": 0.844237744808197, "learning_rate": 2.7433685412990636e-06, "loss": 0.4762, "step": 2563 }, { "epoch": 2.8715459297983568, "grad_norm": 0.8255409598350525, "learning_rate": 2.741880173620583e-06, "loss": 0.4987, "step": 2564 }, { "epoch": 2.872666168782674, "grad_norm": 0.8825394511222839, "learning_rate": 2.7403917193953918e-06, "loss": 0.525, "step": 2565 }, { "epoch": 2.8737864077669903, "grad_norm": 0.8740024566650391, "learning_rate": 2.7389031791560704e-06, "loss": 0.4793, "step": 2566 }, { "epoch": 2.874906646751307, "grad_norm": 0.8691585063934326, "learning_rate": 2.7374145534352305e-06, "loss": 0.4823, "step": 2567 }, { "epoch": 2.8760268857356235, "grad_norm": 0.8766407370567322, "learning_rate": 2.7359258427655156e-06, "loss": 0.477, "step": 2568 }, { "epoch": 2.87714712471994, "grad_norm": 0.8478973507881165, "learning_rate": 2.7344370476795972e-06, "loss": 0.4962, "step": 2569 }, { "epoch": 2.878267363704257, "grad_norm": 0.8552764654159546, "learning_rate": 2.7329481687101795e-06, "loss": 0.4831, "step": 2570 }, { "epoch": 2.8793876026885736, "grad_norm": 0.8708025813102722, "learning_rate": 2.7314592063899948e-06, "loss": 0.532, "step": 2571 }, { "epoch": 2.88050784167289, "grad_norm": 0.9043700695037842, "learning_rate": 2.729970161251807e-06, "loss": 0.5151, "step": 2572 }, { "epoch": 2.8816280806572068, "grad_norm": 0.8796886801719666, "learning_rate": 2.728481033828408e-06, "loss": 0.5081, "step": 2573 }, { "epoch": 2.8827483196415233, "grad_norm": 0.8772388100624084, "learning_rate": 2.72699182465262e-06, "loss": 0.4965, "step": 2574 }, { "epoch": 2.8838685586258404, "grad_norm": 0.8683493137359619, "learning_rate": 2.7255025342572944e-06, "loss": 0.5127, "step": 2575 }, { "epoch": 2.884988797610157, "grad_norm": 0.8315615057945251, "learning_rate": 2.724013163175311e-06, "loss": 0.4813, "step": 2576 }, { "epoch": 2.8861090365944735, "grad_norm": 0.8701000213623047, "learning_rate": 2.7225237119395793e-06, "loss": 0.4951, "step": 2577 }, { "epoch": 2.88722927557879, "grad_norm": 0.8777037262916565, "learning_rate": 2.7210341810830377e-06, "loss": 0.4917, "step": 2578 }, { "epoch": 2.8883495145631066, "grad_norm": 0.8521256446838379, "learning_rate": 2.719544571138652e-06, "loss": 0.4874, "step": 2579 }, { "epoch": 2.8894697535474236, "grad_norm": 0.8774807453155518, "learning_rate": 2.7180548826394166e-06, "loss": 0.5038, "step": 2580 }, { "epoch": 2.89058999253174, "grad_norm": 0.8586145043373108, "learning_rate": 2.7165651161183547e-06, "loss": 0.4988, "step": 2581 }, { "epoch": 2.8917102315160568, "grad_norm": 0.852111279964447, "learning_rate": 2.7150752721085178e-06, "loss": 0.4981, "step": 2582 }, { "epoch": 2.8928304705003733, "grad_norm": 0.8639662265777588, "learning_rate": 2.713585351142982e-06, "loss": 0.5198, "step": 2583 }, { "epoch": 2.89395070948469, "grad_norm": 0.8989830017089844, "learning_rate": 2.712095353754855e-06, "loss": 0.525, "step": 2584 }, { "epoch": 2.895070948469007, "grad_norm": 0.8851444721221924, "learning_rate": 2.710605280477271e-06, "loss": 0.5027, "step": 2585 }, { "epoch": 2.8961911874533235, "grad_norm": 0.8629617094993591, "learning_rate": 2.7091151318433886e-06, "loss": 0.4803, "step": 2586 }, { "epoch": 2.89731142643764, "grad_norm": 0.8342243432998657, "learning_rate": 2.7076249083863947e-06, "loss": 0.487, "step": 2587 }, { "epoch": 2.8984316654219566, "grad_norm": 0.8678092360496521, "learning_rate": 2.706134610639506e-06, "loss": 0.5264, "step": 2588 }, { "epoch": 2.899551904406273, "grad_norm": 0.8524137735366821, "learning_rate": 2.704644239135962e-06, "loss": 0.5013, "step": 2589 }, { "epoch": 2.90067214339059, "grad_norm": 0.881604015827179, "learning_rate": 2.7031537944090285e-06, "loss": 0.5057, "step": 2590 }, { "epoch": 2.9017923823749068, "grad_norm": 0.88266921043396, "learning_rate": 2.701663276992e-06, "loss": 0.4914, "step": 2591 }, { "epoch": 2.9029126213592233, "grad_norm": 0.8646906018257141, "learning_rate": 2.7001726874181977e-06, "loss": 0.4834, "step": 2592 }, { "epoch": 2.90403286034354, "grad_norm": 0.8400508165359497, "learning_rate": 2.698682026220964e-06, "loss": 0.4951, "step": 2593 }, { "epoch": 2.9051530993278565, "grad_norm": 0.8870416879653931, "learning_rate": 2.6971912939336707e-06, "loss": 0.5299, "step": 2594 }, { "epoch": 2.9062733383121735, "grad_norm": 0.8528817296028137, "learning_rate": 2.6957004910897144e-06, "loss": 0.507, "step": 2595 }, { "epoch": 2.90739357729649, "grad_norm": 0.8484136462211609, "learning_rate": 2.6942096182225163e-06, "loss": 0.4862, "step": 2596 }, { "epoch": 2.9085138162808066, "grad_norm": 0.9011573195457458, "learning_rate": 2.692718675865522e-06, "loss": 0.489, "step": 2597 }, { "epoch": 2.909634055265123, "grad_norm": 0.8476819396018982, "learning_rate": 2.6912276645522046e-06, "loss": 0.5072, "step": 2598 }, { "epoch": 2.9107542942494398, "grad_norm": 0.878099799156189, "learning_rate": 2.68973658481606e-06, "loss": 0.5086, "step": 2599 }, { "epoch": 2.911874533233757, "grad_norm": 0.8766030073165894, "learning_rate": 2.688245437190607e-06, "loss": 0.5166, "step": 2600 }, { "epoch": 2.9129947722180733, "grad_norm": 0.8980215191841125, "learning_rate": 2.686754222209393e-06, "loss": 0.5127, "step": 2601 }, { "epoch": 2.91411501120239, "grad_norm": 0.8219769597053528, "learning_rate": 2.6852629404059848e-06, "loss": 0.4935, "step": 2602 }, { "epoch": 2.9152352501867065, "grad_norm": 0.8770792484283447, "learning_rate": 2.6837715923139755e-06, "loss": 0.5133, "step": 2603 }, { "epoch": 2.916355489171023, "grad_norm": 0.8702791929244995, "learning_rate": 2.682280178466983e-06, "loss": 0.4873, "step": 2604 }, { "epoch": 2.91747572815534, "grad_norm": 0.871311604976654, "learning_rate": 2.680788699398647e-06, "loss": 0.5086, "step": 2605 }, { "epoch": 2.918595967139656, "grad_norm": 0.8897058963775635, "learning_rate": 2.6792971556426306e-06, "loss": 0.5118, "step": 2606 }, { "epoch": 2.919716206123973, "grad_norm": 0.881560742855072, "learning_rate": 2.67780554773262e-06, "loss": 0.4814, "step": 2607 }, { "epoch": 2.9208364451082898, "grad_norm": 0.8690676093101501, "learning_rate": 2.676313876202325e-06, "loss": 0.4854, "step": 2608 }, { "epoch": 2.9219566840926063, "grad_norm": 0.8799586892127991, "learning_rate": 2.6748221415854784e-06, "loss": 0.4941, "step": 2609 }, { "epoch": 2.9230769230769234, "grad_norm": 0.8628149032592773, "learning_rate": 2.673330344415835e-06, "loss": 0.5126, "step": 2610 }, { "epoch": 2.9241971620612395, "grad_norm": 0.8801175951957703, "learning_rate": 2.671838485227171e-06, "loss": 0.4663, "step": 2611 }, { "epoch": 2.9253174010455565, "grad_norm": 0.8407777547836304, "learning_rate": 2.670346564553288e-06, "loss": 0.505, "step": 2612 }, { "epoch": 2.926437640029873, "grad_norm": 0.849215030670166, "learning_rate": 2.6688545829280057e-06, "loss": 0.4837, "step": 2613 }, { "epoch": 2.9275578790141896, "grad_norm": 0.8828933238983154, "learning_rate": 2.6673625408851674e-06, "loss": 0.5016, "step": 2614 }, { "epoch": 2.928678117998506, "grad_norm": 0.9499262571334839, "learning_rate": 2.6658704389586387e-06, "loss": 0.5025, "step": 2615 }, { "epoch": 2.9297983569828228, "grad_norm": 0.8724127411842346, "learning_rate": 2.6643782776823064e-06, "loss": 0.4863, "step": 2616 }, { "epoch": 2.9309185959671398, "grad_norm": 0.8497906923294067, "learning_rate": 2.6628860575900754e-06, "loss": 0.4931, "step": 2617 }, { "epoch": 2.9320388349514563, "grad_norm": 0.8728849291801453, "learning_rate": 2.661393779215878e-06, "loss": 0.5143, "step": 2618 }, { "epoch": 2.933159073935773, "grad_norm": 0.8659804463386536, "learning_rate": 2.659901443093661e-06, "loss": 0.4935, "step": 2619 }, { "epoch": 2.9342793129200895, "grad_norm": 0.8464012145996094, "learning_rate": 2.6584090497573956e-06, "loss": 0.4831, "step": 2620 }, { "epoch": 2.935399551904406, "grad_norm": 0.8562572598457336, "learning_rate": 2.656916599741072e-06, "loss": 0.4787, "step": 2621 }, { "epoch": 2.936519790888723, "grad_norm": 0.8672524094581604, "learning_rate": 2.655424093578702e-06, "loss": 0.4972, "step": 2622 }, { "epoch": 2.9376400298730396, "grad_norm": 0.8614441156387329, "learning_rate": 2.653931531804315e-06, "loss": 0.496, "step": 2623 }, { "epoch": 2.938760268857356, "grad_norm": 0.88051837682724, "learning_rate": 2.652438914951962e-06, "loss": 0.4999, "step": 2624 }, { "epoch": 2.9398805078416728, "grad_norm": 0.9057163000106812, "learning_rate": 2.6509462435557155e-06, "loss": 0.5122, "step": 2625 }, { "epoch": 2.9410007468259893, "grad_norm": 0.8641107082366943, "learning_rate": 2.649453518149664e-06, "loss": 0.4883, "step": 2626 }, { "epoch": 2.9421209858103063, "grad_norm": 0.8474313020706177, "learning_rate": 2.6479607392679164e-06, "loss": 0.5244, "step": 2627 }, { "epoch": 2.943241224794623, "grad_norm": 0.8845592141151428, "learning_rate": 2.6464679074446027e-06, "loss": 0.4883, "step": 2628 }, { "epoch": 2.9443614637789395, "grad_norm": 0.8404150605201721, "learning_rate": 2.6449750232138693e-06, "loss": 0.5026, "step": 2629 }, { "epoch": 2.945481702763256, "grad_norm": 0.8707073330879211, "learning_rate": 2.6434820871098827e-06, "loss": 0.518, "step": 2630 }, { "epoch": 2.9466019417475726, "grad_norm": 0.887103259563446, "learning_rate": 2.6419890996668278e-06, "loss": 0.5262, "step": 2631 }, { "epoch": 2.9477221807318896, "grad_norm": 0.8781498074531555, "learning_rate": 2.6404960614189077e-06, "loss": 0.4963, "step": 2632 }, { "epoch": 2.948842419716206, "grad_norm": 0.8372603058815002, "learning_rate": 2.6390029729003446e-06, "loss": 0.4924, "step": 2633 }, { "epoch": 2.9499626587005228, "grad_norm": 0.8783357739448547, "learning_rate": 2.637509834645376e-06, "loss": 0.5005, "step": 2634 }, { "epoch": 2.9510828976848393, "grad_norm": 0.8917863368988037, "learning_rate": 2.636016647188261e-06, "loss": 0.5172, "step": 2635 }, { "epoch": 2.952203136669156, "grad_norm": 0.8559481501579285, "learning_rate": 2.6345234110632728e-06, "loss": 0.4911, "step": 2636 }, { "epoch": 2.953323375653473, "grad_norm": 0.8633483648300171, "learning_rate": 2.6330301268047036e-06, "loss": 0.5212, "step": 2637 }, { "epoch": 2.9544436146377895, "grad_norm": 0.868951678276062, "learning_rate": 2.631536794946864e-06, "loss": 0.4855, "step": 2638 }, { "epoch": 2.955563853622106, "grad_norm": 0.8894789218902588, "learning_rate": 2.6300434160240796e-06, "loss": 0.5059, "step": 2639 }, { "epoch": 2.9566840926064226, "grad_norm": 0.8686272501945496, "learning_rate": 2.6285499905706933e-06, "loss": 0.4928, "step": 2640 }, { "epoch": 2.957804331590739, "grad_norm": 0.8529327511787415, "learning_rate": 2.6270565191210657e-06, "loss": 0.5026, "step": 2641 }, { "epoch": 2.958924570575056, "grad_norm": 0.8973804116249084, "learning_rate": 2.625563002209573e-06, "loss": 0.4921, "step": 2642 }, { "epoch": 2.9600448095593728, "grad_norm": 0.8534948825836182, "learning_rate": 2.6240694403706075e-06, "loss": 0.4997, "step": 2643 }, { "epoch": 2.9611650485436893, "grad_norm": 0.8553454279899597, "learning_rate": 2.6225758341385766e-06, "loss": 0.4652, "step": 2644 }, { "epoch": 2.962285287528006, "grad_norm": 0.8579944968223572, "learning_rate": 2.6210821840479077e-06, "loss": 0.482, "step": 2645 }, { "epoch": 2.9634055265123225, "grad_norm": 0.8731046915054321, "learning_rate": 2.61958849063304e-06, "loss": 0.4903, "step": 2646 }, { "epoch": 2.9645257654966395, "grad_norm": 0.8604210615158081, "learning_rate": 2.6180947544284278e-06, "loss": 0.4957, "step": 2647 }, { "epoch": 2.965646004480956, "grad_norm": 0.8838042616844177, "learning_rate": 2.616600975968544e-06, "loss": 0.5233, "step": 2648 }, { "epoch": 2.9667662434652726, "grad_norm": 0.8812302350997925, "learning_rate": 2.6151071557878744e-06, "loss": 0.5209, "step": 2649 }, { "epoch": 2.967886482449589, "grad_norm": 0.8956620693206787, "learning_rate": 2.613613294420919e-06, "loss": 0.5061, "step": 2650 }, { "epoch": 2.9690067214339058, "grad_norm": 0.8874725699424744, "learning_rate": 2.612119392402194e-06, "loss": 0.4931, "step": 2651 }, { "epoch": 2.9701269604182228, "grad_norm": 0.8518476486206055, "learning_rate": 2.6106254502662316e-06, "loss": 0.4778, "step": 2652 }, { "epoch": 2.9712471994025393, "grad_norm": 0.8592997193336487, "learning_rate": 2.609131468547575e-06, "loss": 0.5088, "step": 2653 }, { "epoch": 2.972367438386856, "grad_norm": 0.8544372320175171, "learning_rate": 2.607637447780782e-06, "loss": 0.5083, "step": 2654 }, { "epoch": 2.9734876773711725, "grad_norm": 0.8625590205192566, "learning_rate": 2.6061433885004285e-06, "loss": 0.4884, "step": 2655 }, { "epoch": 2.974607916355489, "grad_norm": 0.8606609106063843, "learning_rate": 2.604649291241099e-06, "loss": 0.4997, "step": 2656 }, { "epoch": 2.975728155339806, "grad_norm": 0.8672904968261719, "learning_rate": 2.603155156537393e-06, "loss": 0.482, "step": 2657 }, { "epoch": 2.9768483943241226, "grad_norm": 0.8632087111473083, "learning_rate": 2.601660984923926e-06, "loss": 0.4949, "step": 2658 }, { "epoch": 2.977968633308439, "grad_norm": 0.9019870758056641, "learning_rate": 2.600166776935325e-06, "loss": 0.5098, "step": 2659 }, { "epoch": 2.9790888722927558, "grad_norm": 0.8395412564277649, "learning_rate": 2.598672533106229e-06, "loss": 0.4827, "step": 2660 }, { "epoch": 2.9802091112770723, "grad_norm": 0.8568052053451538, "learning_rate": 2.5971782539712902e-06, "loss": 0.5091, "step": 2661 }, { "epoch": 2.9813293502613893, "grad_norm": 0.8251040577888489, "learning_rate": 2.595683940065175e-06, "loss": 0.4852, "step": 2662 }, { "epoch": 2.982449589245706, "grad_norm": 0.8852142095565796, "learning_rate": 2.5941895919225613e-06, "loss": 0.5315, "step": 2663 }, { "epoch": 2.9835698282300225, "grad_norm": 0.8898788690567017, "learning_rate": 2.592695210078137e-06, "loss": 0.4762, "step": 2664 }, { "epoch": 2.984690067214339, "grad_norm": 0.8610514998435974, "learning_rate": 2.5912007950666076e-06, "loss": 0.5198, "step": 2665 }, { "epoch": 2.9858103061986556, "grad_norm": 0.8922441005706787, "learning_rate": 2.5897063474226845e-06, "loss": 0.5081, "step": 2666 }, { "epoch": 2.9869305451829726, "grad_norm": 0.8607761263847351, "learning_rate": 2.588211867681094e-06, "loss": 0.488, "step": 2667 }, { "epoch": 2.9880507841672888, "grad_norm": 0.8792994022369385, "learning_rate": 2.5867173563765735e-06, "loss": 0.4925, "step": 2668 }, { "epoch": 2.9891710231516058, "grad_norm": 0.8323893547058105, "learning_rate": 2.585222814043871e-06, "loss": 0.4966, "step": 2669 }, { "epoch": 2.9902912621359223, "grad_norm": 0.8891013264656067, "learning_rate": 2.583728241217746e-06, "loss": 0.4981, "step": 2670 }, { "epoch": 2.991411501120239, "grad_norm": 0.8685591816902161, "learning_rate": 2.5822336384329692e-06, "loss": 0.51, "step": 2671 }, { "epoch": 2.992531740104556, "grad_norm": 0.8748711943626404, "learning_rate": 2.5807390062243222e-06, "loss": 0.5134, "step": 2672 }, { "epoch": 2.993651979088872, "grad_norm": 0.8709676265716553, "learning_rate": 2.5792443451265963e-06, "loss": 0.4817, "step": 2673 }, { "epoch": 2.994772218073189, "grad_norm": 0.8639750480651855, "learning_rate": 2.5777496556745924e-06, "loss": 0.5006, "step": 2674 }, { "epoch": 2.9958924570575056, "grad_norm": 0.8494576811790466, "learning_rate": 2.576254938403124e-06, "loss": 0.4835, "step": 2675 }, { "epoch": 2.997012696041822, "grad_norm": 0.873468816280365, "learning_rate": 2.5747601938470133e-06, "loss": 0.4767, "step": 2676 }, { "epoch": 2.9981329350261388, "grad_norm": 0.8700335621833801, "learning_rate": 2.5732654225410916e-06, "loss": 0.5246, "step": 2677 }, { "epoch": 2.9992531740104553, "grad_norm": 0.8851879239082336, "learning_rate": 2.5717706250201998e-06, "loss": 0.5037, "step": 2678 }, { "epoch": 3.0, "grad_norm": 1.1746418476104736, "learning_rate": 2.5702758018191897e-06, "loss": 0.4858, "step": 2679 }, { "epoch": 3.0011202389843166, "grad_norm": 0.8134752511978149, "learning_rate": 2.5687809534729215e-06, "loss": 0.4425, "step": 2680 }, { "epoch": 3.002240477968633, "grad_norm": 0.8517206311225891, "learning_rate": 2.567286080516263e-06, "loss": 0.4712, "step": 2681 }, { "epoch": 3.00336071695295, "grad_norm": 0.8616065979003906, "learning_rate": 2.5657911834840933e-06, "loss": 0.4892, "step": 2682 }, { "epoch": 3.0044809559372667, "grad_norm": 0.8430594801902771, "learning_rate": 2.5642962629112973e-06, "loss": 0.4694, "step": 2683 }, { "epoch": 3.0056011949215833, "grad_norm": 0.8607933521270752, "learning_rate": 2.562801319332771e-06, "loss": 0.4657, "step": 2684 }, { "epoch": 3.0067214339059, "grad_norm": 0.8505658507347107, "learning_rate": 2.5613063532834177e-06, "loss": 0.4631, "step": 2685 }, { "epoch": 3.0078416728902164, "grad_norm": 0.8604072332382202, "learning_rate": 2.5598113652981476e-06, "loss": 0.4592, "step": 2686 }, { "epoch": 3.0089619118745334, "grad_norm": 0.8461195826530457, "learning_rate": 2.558316355911881e-06, "loss": 0.4263, "step": 2687 }, { "epoch": 3.01008215085885, "grad_norm": 0.9018260836601257, "learning_rate": 2.5568213256595426e-06, "loss": 0.5037, "step": 2688 }, { "epoch": 3.0112023898431666, "grad_norm": 0.8664760589599609, "learning_rate": 2.5553262750760683e-06, "loss": 0.4694, "step": 2689 }, { "epoch": 3.012322628827483, "grad_norm": 0.8757667541503906, "learning_rate": 2.553831204696398e-06, "loss": 0.4784, "step": 2690 }, { "epoch": 3.0134428678117997, "grad_norm": 0.8643698692321777, "learning_rate": 2.552336115055481e-06, "loss": 0.458, "step": 2691 }, { "epoch": 3.0145631067961167, "grad_norm": 0.8526175618171692, "learning_rate": 2.550841006688273e-06, "loss": 0.4677, "step": 2692 }, { "epoch": 3.0156833457804333, "grad_norm": 0.9155191779136658, "learning_rate": 2.5493458801297357e-06, "loss": 0.494, "step": 2693 }, { "epoch": 3.01680358476475, "grad_norm": 0.89806067943573, "learning_rate": 2.547850735914836e-06, "loss": 0.4882, "step": 2694 }, { "epoch": 3.0179238237490664, "grad_norm": 0.8634794354438782, "learning_rate": 2.546355574578552e-06, "loss": 0.4514, "step": 2695 }, { "epoch": 3.019044062733383, "grad_norm": 0.8650118112564087, "learning_rate": 2.5448603966558626e-06, "loss": 0.4801, "step": 2696 }, { "epoch": 3.0201643017176996, "grad_norm": 0.8250251412391663, "learning_rate": 2.543365202681755e-06, "loss": 0.4556, "step": 2697 }, { "epoch": 3.0212845407020166, "grad_norm": 0.835252046585083, "learning_rate": 2.5418699931912216e-06, "loss": 0.4614, "step": 2698 }, { "epoch": 3.022404779686333, "grad_norm": 0.8702393174171448, "learning_rate": 2.5403747687192616e-06, "loss": 0.4748, "step": 2699 }, { "epoch": 3.0235250186706497, "grad_norm": 0.871504008769989, "learning_rate": 2.538879529800878e-06, "loss": 0.4799, "step": 2700 }, { "epoch": 3.0246452576549663, "grad_norm": 0.840194582939148, "learning_rate": 2.537384276971079e-06, "loss": 0.44, "step": 2701 }, { "epoch": 3.025765496639283, "grad_norm": 0.8506622910499573, "learning_rate": 2.535889010764879e-06, "loss": 0.4463, "step": 2702 }, { "epoch": 3.0268857356236, "grad_norm": 0.8934537768363953, "learning_rate": 2.5343937317172964e-06, "loss": 0.468, "step": 2703 }, { "epoch": 3.0280059746079164, "grad_norm": 0.8534190058708191, "learning_rate": 2.5328984403633545e-06, "loss": 0.4837, "step": 2704 }, { "epoch": 3.029126213592233, "grad_norm": 0.8662252426147461, "learning_rate": 2.5314031372380805e-06, "loss": 0.4769, "step": 2705 }, { "epoch": 3.0302464525765496, "grad_norm": 0.8875354528427124, "learning_rate": 2.5299078228765066e-06, "loss": 0.4793, "step": 2706 }, { "epoch": 3.031366691560866, "grad_norm": 0.8789662718772888, "learning_rate": 2.528412497813668e-06, "loss": 0.4629, "step": 2707 }, { "epoch": 3.032486930545183, "grad_norm": 0.890751838684082, "learning_rate": 2.5269171625846045e-06, "loss": 0.4742, "step": 2708 }, { "epoch": 3.0336071695294997, "grad_norm": 0.8761585354804993, "learning_rate": 2.5254218177243595e-06, "loss": 0.4719, "step": 2709 }, { "epoch": 3.0347274085138163, "grad_norm": 0.8734204173088074, "learning_rate": 2.523926463767979e-06, "loss": 0.4527, "step": 2710 }, { "epoch": 3.035847647498133, "grad_norm": 0.8940438628196716, "learning_rate": 2.5224311012505145e-06, "loss": 0.4726, "step": 2711 }, { "epoch": 3.0369678864824494, "grad_norm": 0.8808375000953674, "learning_rate": 2.5209357307070164e-06, "loss": 0.4649, "step": 2712 }, { "epoch": 3.0380881254667664, "grad_norm": 0.8905283212661743, "learning_rate": 2.519440352672543e-06, "loss": 0.4684, "step": 2713 }, { "epoch": 3.039208364451083, "grad_norm": 0.8525053858757019, "learning_rate": 2.5179449676821523e-06, "loss": 0.4521, "step": 2714 }, { "epoch": 3.0403286034353996, "grad_norm": 0.8682737946510315, "learning_rate": 2.5164495762709036e-06, "loss": 0.4498, "step": 2715 }, { "epoch": 3.041448842419716, "grad_norm": 0.8663793206214905, "learning_rate": 2.5149541789738622e-06, "loss": 0.4512, "step": 2716 }, { "epoch": 3.0425690814040327, "grad_norm": 0.9454430937767029, "learning_rate": 2.5134587763260926e-06, "loss": 0.4932, "step": 2717 }, { "epoch": 3.0436893203883497, "grad_norm": 0.8557133078575134, "learning_rate": 2.511963368862662e-06, "loss": 0.4781, "step": 2718 }, { "epoch": 3.0448095593726663, "grad_norm": 0.8949810266494751, "learning_rate": 2.5104679571186406e-06, "loss": 0.4747, "step": 2719 }, { "epoch": 3.045929798356983, "grad_norm": 0.9084694385528564, "learning_rate": 2.5089725416290984e-06, "loss": 0.4832, "step": 2720 }, { "epoch": 3.0470500373412994, "grad_norm": 0.8710305094718933, "learning_rate": 2.5074771229291066e-06, "loss": 0.4671, "step": 2721 }, { "epoch": 3.048170276325616, "grad_norm": 0.8714442849159241, "learning_rate": 2.505981701553739e-06, "loss": 0.4573, "step": 2722 }, { "epoch": 3.049290515309933, "grad_norm": 0.834107518196106, "learning_rate": 2.504486278038069e-06, "loss": 0.4453, "step": 2723 }, { "epoch": 3.0504107542942496, "grad_norm": 0.8909593820571899, "learning_rate": 2.502990852917173e-06, "loss": 0.4774, "step": 2724 }, { "epoch": 3.051530993278566, "grad_norm": 0.8741366863250732, "learning_rate": 2.5014954267261243e-06, "loss": 0.4647, "step": 2725 }, { "epoch": 3.0526512322628827, "grad_norm": 0.8731307983398438, "learning_rate": 2.5e-06, "loss": 0.442, "step": 2726 }, { "epoch": 3.0537714712471993, "grad_norm": 0.8524160981178284, "learning_rate": 2.4985045732738765e-06, "loss": 0.4676, "step": 2727 }, { "epoch": 3.054891710231516, "grad_norm": 0.8872650861740112, "learning_rate": 2.4970091470828278e-06, "loss": 0.4847, "step": 2728 }, { "epoch": 3.056011949215833, "grad_norm": 0.8527272343635559, "learning_rate": 2.4955137219619315e-06, "loss": 0.4466, "step": 2729 }, { "epoch": 3.0571321882001494, "grad_norm": 0.8499764204025269, "learning_rate": 2.494018298446262e-06, "loss": 0.4433, "step": 2730 }, { "epoch": 3.058252427184466, "grad_norm": 0.8729113936424255, "learning_rate": 2.4925228770708943e-06, "loss": 0.4684, "step": 2731 }, { "epoch": 3.0593726661687826, "grad_norm": 0.8633613586425781, "learning_rate": 2.491027458370903e-06, "loss": 0.4522, "step": 2732 }, { "epoch": 3.060492905153099, "grad_norm": 0.8741328120231628, "learning_rate": 2.4895320428813594e-06, "loss": 0.49, "step": 2733 }, { "epoch": 3.061613144137416, "grad_norm": 0.8745251893997192, "learning_rate": 2.488036631137338e-06, "loss": 0.4638, "step": 2734 }, { "epoch": 3.0627333831217327, "grad_norm": 0.9085991978645325, "learning_rate": 2.4865412236739074e-06, "loss": 0.4612, "step": 2735 }, { "epoch": 3.0638536221060493, "grad_norm": 0.8825574517250061, "learning_rate": 2.4850458210261386e-06, "loss": 0.4721, "step": 2736 }, { "epoch": 3.064973861090366, "grad_norm": 0.8798938989639282, "learning_rate": 2.4835504237290972e-06, "loss": 0.4715, "step": 2737 }, { "epoch": 3.0660941000746824, "grad_norm": 0.8731242418289185, "learning_rate": 2.482055032317849e-06, "loss": 0.4752, "step": 2738 }, { "epoch": 3.0672143390589994, "grad_norm": 0.8503509163856506, "learning_rate": 2.4805596473274577e-06, "loss": 0.4397, "step": 2739 }, { "epoch": 3.068334578043316, "grad_norm": 0.9025517106056213, "learning_rate": 2.479064269292984e-06, "loss": 0.4833, "step": 2740 }, { "epoch": 3.0694548170276326, "grad_norm": 0.8780611753463745, "learning_rate": 2.4775688987494868e-06, "loss": 0.4589, "step": 2741 }, { "epoch": 3.070575056011949, "grad_norm": 0.8546797633171082, "learning_rate": 2.4760735362320214e-06, "loss": 0.4546, "step": 2742 }, { "epoch": 3.0716952949962657, "grad_norm": 0.9120870232582092, "learning_rate": 2.4745781822756417e-06, "loss": 0.4727, "step": 2743 }, { "epoch": 3.0728155339805827, "grad_norm": 0.8507209420204163, "learning_rate": 2.473082837415397e-06, "loss": 0.4205, "step": 2744 }, { "epoch": 3.0739357729648993, "grad_norm": 0.8955381512641907, "learning_rate": 2.4715875021863332e-06, "loss": 0.4609, "step": 2745 }, { "epoch": 3.075056011949216, "grad_norm": 0.8982617259025574, "learning_rate": 2.4700921771234933e-06, "loss": 0.4823, "step": 2746 }, { "epoch": 3.0761762509335324, "grad_norm": 0.9183934926986694, "learning_rate": 2.46859686276192e-06, "loss": 0.4909, "step": 2747 }, { "epoch": 3.077296489917849, "grad_norm": 0.899067223072052, "learning_rate": 2.467101559636646e-06, "loss": 0.4506, "step": 2748 }, { "epoch": 3.078416728902166, "grad_norm": 0.8917112946510315, "learning_rate": 2.465606268282704e-06, "loss": 0.4935, "step": 2749 }, { "epoch": 3.0795369678864826, "grad_norm": 0.8968915343284607, "learning_rate": 2.4641109892351217e-06, "loss": 0.476, "step": 2750 }, { "epoch": 3.080657206870799, "grad_norm": 0.8970828056335449, "learning_rate": 2.4626157230289223e-06, "loss": 0.4641, "step": 2751 }, { "epoch": 3.0817774458551157, "grad_norm": 0.8856856822967529, "learning_rate": 2.461120470199123e-06, "loss": 0.4899, "step": 2752 }, { "epoch": 3.0828976848394323, "grad_norm": 0.9088665843009949, "learning_rate": 2.459625231280739e-06, "loss": 0.5004, "step": 2753 }, { "epoch": 3.0840179238237493, "grad_norm": 0.8407161235809326, "learning_rate": 2.4581300068087793e-06, "loss": 0.4626, "step": 2754 }, { "epoch": 3.085138162808066, "grad_norm": 0.8867538571357727, "learning_rate": 2.4566347973182458e-06, "loss": 0.4747, "step": 2755 }, { "epoch": 3.0862584017923824, "grad_norm": 0.8620869517326355, "learning_rate": 2.4551396033441387e-06, "loss": 0.4585, "step": 2756 }, { "epoch": 3.087378640776699, "grad_norm": 0.892745316028595, "learning_rate": 2.453644425421449e-06, "loss": 0.4602, "step": 2757 }, { "epoch": 3.0884988797610156, "grad_norm": 0.8679863810539246, "learning_rate": 2.4521492640851643e-06, "loss": 0.4702, "step": 2758 }, { "epoch": 3.089619118745332, "grad_norm": 0.8784655928611755, "learning_rate": 2.4506541198702656e-06, "loss": 0.4566, "step": 2759 }, { "epoch": 3.090739357729649, "grad_norm": 0.8805121183395386, "learning_rate": 2.4491589933117276e-06, "loss": 0.4544, "step": 2760 }, { "epoch": 3.0918595967139657, "grad_norm": 0.9022408127784729, "learning_rate": 2.447663884944519e-06, "loss": 0.4657, "step": 2761 }, { "epoch": 3.0929798356982823, "grad_norm": 0.9114617705345154, "learning_rate": 2.4461687953036024e-06, "loss": 0.4509, "step": 2762 }, { "epoch": 3.094100074682599, "grad_norm": 0.8653596639633179, "learning_rate": 2.4446737249239326e-06, "loss": 0.4697, "step": 2763 }, { "epoch": 3.0952203136669154, "grad_norm": 0.8815144896507263, "learning_rate": 2.4431786743404582e-06, "loss": 0.4699, "step": 2764 }, { "epoch": 3.0963405526512324, "grad_norm": 0.8851364254951477, "learning_rate": 2.4416836440881196e-06, "loss": 0.4659, "step": 2765 }, { "epoch": 3.097460791635549, "grad_norm": 0.9197531938552856, "learning_rate": 2.4401886347018528e-06, "loss": 0.4753, "step": 2766 }, { "epoch": 3.0985810306198656, "grad_norm": 0.8860110640525818, "learning_rate": 2.438693646716583e-06, "loss": 0.4528, "step": 2767 }, { "epoch": 3.099701269604182, "grad_norm": 0.8947100639343262, "learning_rate": 2.4371986806672295e-06, "loss": 0.4645, "step": 2768 }, { "epoch": 3.1008215085884987, "grad_norm": 0.8808680772781372, "learning_rate": 2.4357037370887035e-06, "loss": 0.47, "step": 2769 }, { "epoch": 3.1019417475728157, "grad_norm": 0.90251225233078, "learning_rate": 2.4342088165159084e-06, "loss": 0.4899, "step": 2770 }, { "epoch": 3.1030619865571323, "grad_norm": 0.8833252191543579, "learning_rate": 2.4327139194837378e-06, "loss": 0.4641, "step": 2771 }, { "epoch": 3.104182225541449, "grad_norm": 0.8824754357337952, "learning_rate": 2.4312190465270798e-06, "loss": 0.4856, "step": 2772 }, { "epoch": 3.1053024645257654, "grad_norm": 0.8787384629249573, "learning_rate": 2.42972419818081e-06, "loss": 0.4697, "step": 2773 }, { "epoch": 3.106422703510082, "grad_norm": 0.8959699869155884, "learning_rate": 2.4282293749798e-06, "loss": 0.4951, "step": 2774 }, { "epoch": 3.107542942494399, "grad_norm": 0.8893037438392639, "learning_rate": 2.4267345774589093e-06, "loss": 0.4559, "step": 2775 }, { "epoch": 3.1086631814787156, "grad_norm": 0.9221355319023132, "learning_rate": 2.425239806152987e-06, "loss": 0.4595, "step": 2776 }, { "epoch": 3.109783420463032, "grad_norm": 0.8828059434890747, "learning_rate": 2.4237450615968762e-06, "loss": 0.4968, "step": 2777 }, { "epoch": 3.1109036594473487, "grad_norm": 0.8700497150421143, "learning_rate": 2.4222503443254084e-06, "loss": 0.4686, "step": 2778 }, { "epoch": 3.1120238984316653, "grad_norm": 0.8817747235298157, "learning_rate": 2.4207556548734045e-06, "loss": 0.4514, "step": 2779 }, { "epoch": 3.1131441374159823, "grad_norm": 0.8888804912567139, "learning_rate": 2.419260993775678e-06, "loss": 0.4767, "step": 2780 }, { "epoch": 3.114264376400299, "grad_norm": 0.890070378780365, "learning_rate": 2.4177663615670316e-06, "loss": 0.465, "step": 2781 }, { "epoch": 3.1153846153846154, "grad_norm": 0.910909116268158, "learning_rate": 2.4162717587822547e-06, "loss": 0.467, "step": 2782 }, { "epoch": 3.116504854368932, "grad_norm": 0.8825702667236328, "learning_rate": 2.4147771859561302e-06, "loss": 0.4689, "step": 2783 }, { "epoch": 3.1176250933532486, "grad_norm": 0.8801292181015015, "learning_rate": 2.413282643623428e-06, "loss": 0.4782, "step": 2784 }, { "epoch": 3.118745332337565, "grad_norm": 0.8911852836608887, "learning_rate": 2.411788132318907e-06, "loss": 0.4462, "step": 2785 }, { "epoch": 3.119865571321882, "grad_norm": 0.8880387544631958, "learning_rate": 2.410293652577316e-06, "loss": 0.4664, "step": 2786 }, { "epoch": 3.1209858103061987, "grad_norm": 0.8773893713951111, "learning_rate": 2.408799204933393e-06, "loss": 0.4894, "step": 2787 }, { "epoch": 3.1221060492905153, "grad_norm": 0.8712835311889648, "learning_rate": 2.407304789921863e-06, "loss": 0.4749, "step": 2788 }, { "epoch": 3.123226288274832, "grad_norm": 0.8873152732849121, "learning_rate": 2.4058104080774395e-06, "loss": 0.4656, "step": 2789 }, { "epoch": 3.1243465272591484, "grad_norm": 0.8793221712112427, "learning_rate": 2.4043160599348257e-06, "loss": 0.4477, "step": 2790 }, { "epoch": 3.1254667662434654, "grad_norm": 0.8945302367210388, "learning_rate": 2.40282174602871e-06, "loss": 0.4787, "step": 2791 }, { "epoch": 3.126587005227782, "grad_norm": 0.8939030170440674, "learning_rate": 2.4013274668937715e-06, "loss": 0.4626, "step": 2792 }, { "epoch": 3.1277072442120986, "grad_norm": 0.9204237461090088, "learning_rate": 2.399833223064676e-06, "loss": 0.4978, "step": 2793 }, { "epoch": 3.128827483196415, "grad_norm": 0.864976167678833, "learning_rate": 2.3983390150760747e-06, "loss": 0.4365, "step": 2794 }, { "epoch": 3.1299477221807317, "grad_norm": 0.9067941904067993, "learning_rate": 2.3968448434626077e-06, "loss": 0.4822, "step": 2795 }, { "epoch": 3.1310679611650487, "grad_norm": 0.9481852650642395, "learning_rate": 2.395350708758903e-06, "loss": 0.4931, "step": 2796 }, { "epoch": 3.1321882001493653, "grad_norm": 0.9209596514701843, "learning_rate": 2.393856611499573e-06, "loss": 0.4755, "step": 2797 }, { "epoch": 3.133308439133682, "grad_norm": 0.8985818028450012, "learning_rate": 2.3923625522192183e-06, "loss": 0.4912, "step": 2798 }, { "epoch": 3.1344286781179984, "grad_norm": 0.9003480672836304, "learning_rate": 2.390868531452426e-06, "loss": 0.4733, "step": 2799 }, { "epoch": 3.135548917102315, "grad_norm": 0.8905757665634155, "learning_rate": 2.389374549733769e-06, "loss": 0.4867, "step": 2800 }, { "epoch": 3.136669156086632, "grad_norm": 0.8903768658638, "learning_rate": 2.387880607597806e-06, "loss": 0.477, "step": 2801 }, { "epoch": 3.1377893950709486, "grad_norm": 0.8727596402168274, "learning_rate": 2.3863867055790818e-06, "loss": 0.4943, "step": 2802 }, { "epoch": 3.138909634055265, "grad_norm": 0.9004273414611816, "learning_rate": 2.3848928442121264e-06, "loss": 0.4788, "step": 2803 }, { "epoch": 3.1400298730395817, "grad_norm": 0.8927457928657532, "learning_rate": 2.3833990240314564e-06, "loss": 0.491, "step": 2804 }, { "epoch": 3.1411501120238983, "grad_norm": 0.873522162437439, "learning_rate": 2.3819052455715726e-06, "loss": 0.4587, "step": 2805 }, { "epoch": 3.1422703510082153, "grad_norm": 0.8878270983695984, "learning_rate": 2.3804115093669608e-06, "loss": 0.4743, "step": 2806 }, { "epoch": 3.143390589992532, "grad_norm": 0.9085186123847961, "learning_rate": 2.3789178159520927e-06, "loss": 0.4725, "step": 2807 }, { "epoch": 3.1445108289768484, "grad_norm": 0.8919894099235535, "learning_rate": 2.377424165861424e-06, "loss": 0.4877, "step": 2808 }, { "epoch": 3.145631067961165, "grad_norm": 0.8809217214584351, "learning_rate": 2.3759305596293937e-06, "loss": 0.4805, "step": 2809 }, { "epoch": 3.1467513069454816, "grad_norm": 0.9143190979957581, "learning_rate": 2.3744369977904286e-06, "loss": 0.4651, "step": 2810 }, { "epoch": 3.1478715459297986, "grad_norm": 0.8801463842391968, "learning_rate": 2.3729434808789355e-06, "loss": 0.468, "step": 2811 }, { "epoch": 3.148991784914115, "grad_norm": 0.8931465744972229, "learning_rate": 2.371450009429308e-06, "loss": 0.4862, "step": 2812 }, { "epoch": 3.1501120238984317, "grad_norm": 0.8998441696166992, "learning_rate": 2.3699565839759208e-06, "loss": 0.4713, "step": 2813 }, { "epoch": 3.1512322628827483, "grad_norm": 0.8716554641723633, "learning_rate": 2.3684632050531366e-06, "loss": 0.4592, "step": 2814 }, { "epoch": 3.152352501867065, "grad_norm": 0.8740878701210022, "learning_rate": 2.366969873195297e-06, "loss": 0.472, "step": 2815 }, { "epoch": 3.153472740851382, "grad_norm": 0.8939603567123413, "learning_rate": 2.365476588936728e-06, "loss": 0.4458, "step": 2816 }, { "epoch": 3.1545929798356984, "grad_norm": 0.8950668573379517, "learning_rate": 2.36398335281174e-06, "loss": 0.4711, "step": 2817 }, { "epoch": 3.155713218820015, "grad_norm": 0.8842800855636597, "learning_rate": 2.3624901653546244e-06, "loss": 0.453, "step": 2818 }, { "epoch": 3.1568334578043316, "grad_norm": 0.8791018724441528, "learning_rate": 2.360997027099656e-06, "loss": 0.4417, "step": 2819 }, { "epoch": 3.157953696788648, "grad_norm": 0.8849508762359619, "learning_rate": 2.3595039385810927e-06, "loss": 0.4757, "step": 2820 }, { "epoch": 3.1590739357729647, "grad_norm": 0.8945475816726685, "learning_rate": 2.358010900333173e-06, "loss": 0.4811, "step": 2821 }, { "epoch": 3.1601941747572817, "grad_norm": 0.8846893310546875, "learning_rate": 2.3565179128901177e-06, "loss": 0.4688, "step": 2822 }, { "epoch": 3.1613144137415983, "grad_norm": 0.8607355952262878, "learning_rate": 2.3550249767861316e-06, "loss": 0.4534, "step": 2823 }, { "epoch": 3.162434652725915, "grad_norm": 0.8719488382339478, "learning_rate": 2.3535320925553986e-06, "loss": 0.4489, "step": 2824 }, { "epoch": 3.1635548917102314, "grad_norm": 0.8726834654808044, "learning_rate": 2.3520392607320844e-06, "loss": 0.4596, "step": 2825 }, { "epoch": 3.164675130694548, "grad_norm": 0.8961896896362305, "learning_rate": 2.350546481850336e-06, "loss": 0.4617, "step": 2826 }, { "epoch": 3.165795369678865, "grad_norm": 0.9827616214752197, "learning_rate": 2.349053756444285e-06, "loss": 0.4767, "step": 2827 }, { "epoch": 3.1669156086631816, "grad_norm": 0.8993396759033203, "learning_rate": 2.3475610850480377e-06, "loss": 0.4729, "step": 2828 }, { "epoch": 3.168035847647498, "grad_norm": 0.9027233123779297, "learning_rate": 2.346068468195686e-06, "loss": 0.4653, "step": 2829 }, { "epoch": 3.1691560866318147, "grad_norm": 0.9424562454223633, "learning_rate": 2.344575906421299e-06, "loss": 0.4648, "step": 2830 }, { "epoch": 3.1702763256161313, "grad_norm": 0.9034714698791504, "learning_rate": 2.3430834002589282e-06, "loss": 0.4691, "step": 2831 }, { "epoch": 3.1713965646004483, "grad_norm": 0.8714960217475891, "learning_rate": 2.3415909502426052e-06, "loss": 0.4692, "step": 2832 }, { "epoch": 3.172516803584765, "grad_norm": 0.9146521091461182, "learning_rate": 2.3400985569063393e-06, "loss": 0.4746, "step": 2833 }, { "epoch": 3.1736370425690814, "grad_norm": 0.9221817851066589, "learning_rate": 2.338606220784123e-06, "loss": 0.4812, "step": 2834 }, { "epoch": 3.174757281553398, "grad_norm": 0.9583678841590881, "learning_rate": 2.3371139424099254e-06, "loss": 0.4999, "step": 2835 }, { "epoch": 3.1758775205377145, "grad_norm": 0.9435810446739197, "learning_rate": 2.3356217223176953e-06, "loss": 0.5054, "step": 2836 }, { "epoch": 3.1769977595220316, "grad_norm": 0.881100594997406, "learning_rate": 2.3341295610413625e-06, "loss": 0.4543, "step": 2837 }, { "epoch": 3.178117998506348, "grad_norm": 0.8753137588500977, "learning_rate": 2.332637459114834e-06, "loss": 0.4676, "step": 2838 }, { "epoch": 3.1792382374906647, "grad_norm": 0.8902580738067627, "learning_rate": 2.331145417071995e-06, "loss": 0.4772, "step": 2839 }, { "epoch": 3.1803584764749813, "grad_norm": 0.9511560797691345, "learning_rate": 2.3296534354467125e-06, "loss": 0.4728, "step": 2840 }, { "epoch": 3.181478715459298, "grad_norm": 0.9156246781349182, "learning_rate": 2.328161514772829e-06, "loss": 0.4938, "step": 2841 }, { "epoch": 3.1825989544436144, "grad_norm": 0.8992390632629395, "learning_rate": 2.326669655584166e-06, "loss": 0.4753, "step": 2842 }, { "epoch": 3.1837191934279314, "grad_norm": 0.8753165006637573, "learning_rate": 2.325177858414522e-06, "loss": 0.4762, "step": 2843 }, { "epoch": 3.184839432412248, "grad_norm": 0.9003334045410156, "learning_rate": 2.3236861237976755e-06, "loss": 0.4718, "step": 2844 }, { "epoch": 3.1859596713965646, "grad_norm": 0.8966636657714844, "learning_rate": 2.322194452267381e-06, "loss": 0.4797, "step": 2845 }, { "epoch": 3.187079910380881, "grad_norm": 0.9280106425285339, "learning_rate": 2.32070284435737e-06, "loss": 0.4748, "step": 2846 }, { "epoch": 3.1882001493651977, "grad_norm": 0.9427135586738586, "learning_rate": 2.319211300601354e-06, "loss": 0.4859, "step": 2847 }, { "epoch": 3.1893203883495147, "grad_norm": 0.9198667407035828, "learning_rate": 2.3177198215330176e-06, "loss": 0.4769, "step": 2848 }, { "epoch": 3.1904406273338313, "grad_norm": 0.8763008117675781, "learning_rate": 2.316228407686025e-06, "loss": 0.4547, "step": 2849 }, { "epoch": 3.191560866318148, "grad_norm": 0.9393436908721924, "learning_rate": 2.3147370595940165e-06, "loss": 0.4818, "step": 2850 }, { "epoch": 3.1926811053024644, "grad_norm": 0.8865958452224731, "learning_rate": 2.3132457777906088e-06, "loss": 0.47, "step": 2851 }, { "epoch": 3.193801344286781, "grad_norm": 0.9242629408836365, "learning_rate": 2.311754562809393e-06, "loss": 0.4662, "step": 2852 }, { "epoch": 3.194921583271098, "grad_norm": 0.8833946585655212, "learning_rate": 2.3102634151839405e-06, "loss": 0.4658, "step": 2853 }, { "epoch": 3.1960418222554146, "grad_norm": 0.9340330362319946, "learning_rate": 2.3087723354477953e-06, "loss": 0.4716, "step": 2854 }, { "epoch": 3.197162061239731, "grad_norm": 0.8694081902503967, "learning_rate": 2.3072813241344783e-06, "loss": 0.4575, "step": 2855 }, { "epoch": 3.1982823002240477, "grad_norm": 0.9129896759986877, "learning_rate": 2.3057903817774845e-06, "loss": 0.4963, "step": 2856 }, { "epoch": 3.1994025392083643, "grad_norm": 0.8710014820098877, "learning_rate": 2.3042995089102864e-06, "loss": 0.4715, "step": 2857 }, { "epoch": 3.2005227781926813, "grad_norm": 0.8899341821670532, "learning_rate": 2.30280870606633e-06, "loss": 0.4891, "step": 2858 }, { "epoch": 3.201643017176998, "grad_norm": 0.8640789985656738, "learning_rate": 2.3013179737790363e-06, "loss": 0.4646, "step": 2859 }, { "epoch": 3.2027632561613144, "grad_norm": 0.9049296975135803, "learning_rate": 2.299827312581803e-06, "loss": 0.4707, "step": 2860 }, { "epoch": 3.203883495145631, "grad_norm": 0.9031786322593689, "learning_rate": 2.2983367230080002e-06, "loss": 0.4739, "step": 2861 }, { "epoch": 3.2050037341299475, "grad_norm": 0.8974542617797852, "learning_rate": 2.296846205590972e-06, "loss": 0.4739, "step": 2862 }, { "epoch": 3.2061239731142646, "grad_norm": 0.8927215337753296, "learning_rate": 2.2953557608640394e-06, "loss": 0.4781, "step": 2863 }, { "epoch": 3.207244212098581, "grad_norm": 0.9131977558135986, "learning_rate": 2.293865389360495e-06, "loss": 0.4757, "step": 2864 }, { "epoch": 3.2083644510828977, "grad_norm": 0.8882164359092712, "learning_rate": 2.292375091613606e-06, "loss": 0.4669, "step": 2865 }, { "epoch": 3.2094846900672143, "grad_norm": 0.903255820274353, "learning_rate": 2.2908848681566127e-06, "loss": 0.4681, "step": 2866 }, { "epoch": 3.210604929051531, "grad_norm": 0.9582553505897522, "learning_rate": 2.2893947195227295e-06, "loss": 0.5097, "step": 2867 }, { "epoch": 3.211725168035848, "grad_norm": 0.9242427349090576, "learning_rate": 2.2879046462451447e-06, "loss": 0.4646, "step": 2868 }, { "epoch": 3.2128454070201644, "grad_norm": 0.932808518409729, "learning_rate": 2.2864146488570186e-06, "loss": 0.471, "step": 2869 }, { "epoch": 3.213965646004481, "grad_norm": 0.9045302867889404, "learning_rate": 2.284924727891483e-06, "loss": 0.487, "step": 2870 }, { "epoch": 3.2150858849887975, "grad_norm": 0.8895891308784485, "learning_rate": 2.2834348838816457e-06, "loss": 0.4875, "step": 2871 }, { "epoch": 3.216206123973114, "grad_norm": 0.8829043507575989, "learning_rate": 2.2819451173605842e-06, "loss": 0.4795, "step": 2872 }, { "epoch": 3.217326362957431, "grad_norm": 0.8776723146438599, "learning_rate": 2.2804554288613488e-06, "loss": 0.4833, "step": 2873 }, { "epoch": 3.2184466019417477, "grad_norm": 0.8925765156745911, "learning_rate": 2.278965818916963e-06, "loss": 0.4641, "step": 2874 }, { "epoch": 3.2195668409260643, "grad_norm": 0.9302591681480408, "learning_rate": 2.2774762880604216e-06, "loss": 0.4535, "step": 2875 }, { "epoch": 3.220687079910381, "grad_norm": 0.874092698097229, "learning_rate": 2.27598683682469e-06, "loss": 0.4676, "step": 2876 }, { "epoch": 3.2218073188946974, "grad_norm": 0.8361105918884277, "learning_rate": 2.274497465742707e-06, "loss": 0.4451, "step": 2877 }, { "epoch": 3.2229275578790144, "grad_norm": 0.9030993580818176, "learning_rate": 2.2730081753473815e-06, "loss": 0.4931, "step": 2878 }, { "epoch": 3.224047796863331, "grad_norm": 0.8758410215377808, "learning_rate": 2.2715189661715925e-06, "loss": 0.4699, "step": 2879 }, { "epoch": 3.2251680358476476, "grad_norm": 0.9000892639160156, "learning_rate": 2.270029838748193e-06, "loss": 0.4713, "step": 2880 }, { "epoch": 3.226288274831964, "grad_norm": 0.9128881096839905, "learning_rate": 2.268540793610005e-06, "loss": 0.4765, "step": 2881 }, { "epoch": 3.2274085138162807, "grad_norm": 0.8809553384780884, "learning_rate": 2.2670518312898214e-06, "loss": 0.4747, "step": 2882 }, { "epoch": 3.2285287528005973, "grad_norm": 0.8851008415222168, "learning_rate": 2.265562952320403e-06, "loss": 0.4834, "step": 2883 }, { "epoch": 3.2296489917849143, "grad_norm": 0.892426073551178, "learning_rate": 2.2640741572344856e-06, "loss": 0.4616, "step": 2884 }, { "epoch": 3.230769230769231, "grad_norm": 0.9042345881462097, "learning_rate": 2.2625854465647703e-06, "loss": 0.4887, "step": 2885 }, { "epoch": 3.2318894697535474, "grad_norm": 0.9297722578048706, "learning_rate": 2.26109682084393e-06, "loss": 0.4888, "step": 2886 }, { "epoch": 3.233009708737864, "grad_norm": 0.9199649691581726, "learning_rate": 2.259608280604609e-06, "loss": 0.4606, "step": 2887 }, { "epoch": 3.2341299477221805, "grad_norm": 0.8793584704399109, "learning_rate": 2.2581198263794176e-06, "loss": 0.4616, "step": 2888 }, { "epoch": 3.2352501867064976, "grad_norm": 0.8984830379486084, "learning_rate": 2.2566314587009372e-06, "loss": 0.4787, "step": 2889 }, { "epoch": 3.236370425690814, "grad_norm": 0.8963854908943176, "learning_rate": 2.2551431781017184e-06, "loss": 0.4635, "step": 2890 }, { "epoch": 3.2374906646751307, "grad_norm": 0.8452900052070618, "learning_rate": 2.25365498511428e-06, "loss": 0.4215, "step": 2891 }, { "epoch": 3.2386109036594473, "grad_norm": 0.8694685697555542, "learning_rate": 2.252166880271109e-06, "loss": 0.434, "step": 2892 }, { "epoch": 3.239731142643764, "grad_norm": 1.1372522115707397, "learning_rate": 2.250678864104663e-06, "loss": 0.4724, "step": 2893 }, { "epoch": 3.240851381628081, "grad_norm": 0.8852602243423462, "learning_rate": 2.249190937147365e-06, "loss": 0.4764, "step": 2894 }, { "epoch": 3.2419716206123974, "grad_norm": 0.8999150991439819, "learning_rate": 2.2477030999316088e-06, "loss": 0.4661, "step": 2895 }, { "epoch": 3.243091859596714, "grad_norm": 0.8807189464569092, "learning_rate": 2.246215352989754e-06, "loss": 0.4677, "step": 2896 }, { "epoch": 3.2442120985810305, "grad_norm": 0.8494924306869507, "learning_rate": 2.244727696854128e-06, "loss": 0.4662, "step": 2897 }, { "epoch": 3.245332337565347, "grad_norm": 0.8791207671165466, "learning_rate": 2.2432401320570276e-06, "loss": 0.4571, "step": 2898 }, { "epoch": 3.246452576549664, "grad_norm": 0.9616562128067017, "learning_rate": 2.241752659130715e-06, "loss": 0.4862, "step": 2899 }, { "epoch": 3.2475728155339807, "grad_norm": 0.8803429007530212, "learning_rate": 2.2402652786074205e-06, "loss": 0.4536, "step": 2900 }, { "epoch": 3.2486930545182973, "grad_norm": 0.8827470541000366, "learning_rate": 2.2387779910193407e-06, "loss": 0.4442, "step": 2901 }, { "epoch": 3.249813293502614, "grad_norm": 0.9066334366798401, "learning_rate": 2.23729079689864e-06, "loss": 0.4747, "step": 2902 }, { "epoch": 3.2509335324869304, "grad_norm": 0.9237440228462219, "learning_rate": 2.2358036967774476e-06, "loss": 0.4747, "step": 2903 }, { "epoch": 3.252053771471247, "grad_norm": 0.9289774894714355, "learning_rate": 2.234316691187861e-06, "loss": 0.4853, "step": 2904 }, { "epoch": 3.253174010455564, "grad_norm": 0.8846302032470703, "learning_rate": 2.2328297806619428e-06, "loss": 0.449, "step": 2905 }, { "epoch": 3.2542942494398805, "grad_norm": 0.8956130743026733, "learning_rate": 2.231342965731721e-06, "loss": 0.4759, "step": 2906 }, { "epoch": 3.255414488424197, "grad_norm": 0.8990398049354553, "learning_rate": 2.229856246929191e-06, "loss": 0.4746, "step": 2907 }, { "epoch": 3.2565347274085137, "grad_norm": 0.8766493797302246, "learning_rate": 2.228369624786314e-06, "loss": 0.4413, "step": 2908 }, { "epoch": 3.2576549663928303, "grad_norm": 0.8767910599708557, "learning_rate": 2.226883099835014e-06, "loss": 0.4642, "step": 2909 }, { "epoch": 3.2587752053771473, "grad_norm": 0.8917639851570129, "learning_rate": 2.2253966726071817e-06, "loss": 0.4373, "step": 2910 }, { "epoch": 3.259895444361464, "grad_norm": 0.8712226152420044, "learning_rate": 2.2239103436346745e-06, "loss": 0.4657, "step": 2911 }, { "epoch": 3.2610156833457804, "grad_norm": 0.9096734523773193, "learning_rate": 2.2224241134493122e-06, "loss": 0.4795, "step": 2912 }, { "epoch": 3.262135922330097, "grad_norm": 0.9282961487770081, "learning_rate": 2.220937982582879e-06, "loss": 0.487, "step": 2913 }, { "epoch": 3.2632561613144135, "grad_norm": 0.9049886465072632, "learning_rate": 2.2194519515671275e-06, "loss": 0.4775, "step": 2914 }, { "epoch": 3.2643764002987306, "grad_norm": 0.9115628600120544, "learning_rate": 2.2179660209337693e-06, "loss": 0.4881, "step": 2915 }, { "epoch": 3.265496639283047, "grad_norm": 0.9155592322349548, "learning_rate": 2.2164801912144833e-06, "loss": 0.49, "step": 2916 }, { "epoch": 3.2666168782673637, "grad_norm": 0.9180135726928711, "learning_rate": 2.2149944629409117e-06, "loss": 0.4892, "step": 2917 }, { "epoch": 3.2677371172516803, "grad_norm": 0.9059298634529114, "learning_rate": 2.2135088366446606e-06, "loss": 0.466, "step": 2918 }, { "epoch": 3.268857356235997, "grad_norm": 0.8738517761230469, "learning_rate": 2.212023312857298e-06, "loss": 0.4722, "step": 2919 }, { "epoch": 3.269977595220314, "grad_norm": 0.8914937376976013, "learning_rate": 2.2105378921103587e-06, "loss": 0.4728, "step": 2920 }, { "epoch": 3.2710978342046304, "grad_norm": 0.892943799495697, "learning_rate": 2.2090525749353364e-06, "loss": 0.479, "step": 2921 }, { "epoch": 3.272218073188947, "grad_norm": 0.8903093338012695, "learning_rate": 2.207567361863691e-06, "loss": 0.4722, "step": 2922 }, { "epoch": 3.2733383121732635, "grad_norm": 0.8944401741027832, "learning_rate": 2.206082253426844e-06, "loss": 0.4618, "step": 2923 }, { "epoch": 3.27445855115758, "grad_norm": 0.9200566411018372, "learning_rate": 2.2045972501561776e-06, "loss": 0.4751, "step": 2924 }, { "epoch": 3.275578790141897, "grad_norm": 0.9060561656951904, "learning_rate": 2.2031123525830408e-06, "loss": 0.5009, "step": 2925 }, { "epoch": 3.2766990291262137, "grad_norm": 0.8847519755363464, "learning_rate": 2.20162756123874e-06, "loss": 0.4774, "step": 2926 }, { "epoch": 3.2778192681105303, "grad_norm": 0.8664527535438538, "learning_rate": 2.2001428766545464e-06, "loss": 0.4576, "step": 2927 }, { "epoch": 3.278939507094847, "grad_norm": 0.8821858167648315, "learning_rate": 2.1986582993616926e-06, "loss": 0.4676, "step": 2928 }, { "epoch": 3.2800597460791634, "grad_norm": 0.9057906270027161, "learning_rate": 2.197173829891373e-06, "loss": 0.4681, "step": 2929 }, { "epoch": 3.2811799850634804, "grad_norm": 0.8983535766601562, "learning_rate": 2.1956894687747416e-06, "loss": 0.4804, "step": 2930 }, { "epoch": 3.282300224047797, "grad_norm": 0.911388635635376, "learning_rate": 2.1942052165429163e-06, "loss": 0.4482, "step": 2931 }, { "epoch": 3.2834204630321135, "grad_norm": 0.9332646727561951, "learning_rate": 2.1927210737269727e-06, "loss": 0.4872, "step": 2932 }, { "epoch": 3.28454070201643, "grad_norm": 0.9055399894714355, "learning_rate": 2.191237040857952e-06, "loss": 0.4738, "step": 2933 }, { "epoch": 3.2856609410007467, "grad_norm": 0.9225751161575317, "learning_rate": 2.1897531184668517e-06, "loss": 0.4626, "step": 2934 }, { "epoch": 3.2867811799850637, "grad_norm": 0.8852779865264893, "learning_rate": 2.188269307084632e-06, "loss": 0.4589, "step": 2935 }, { "epoch": 3.2879014189693803, "grad_norm": 0.9004586338996887, "learning_rate": 2.186785607242213e-06, "loss": 0.4592, "step": 2936 }, { "epoch": 3.289021657953697, "grad_norm": 0.903821587562561, "learning_rate": 2.1853020194704733e-06, "loss": 0.4689, "step": 2937 }, { "epoch": 3.2901418969380134, "grad_norm": 0.9063395261764526, "learning_rate": 2.1838185443002542e-06, "loss": 0.4764, "step": 2938 }, { "epoch": 3.29126213592233, "grad_norm": 0.8771997094154358, "learning_rate": 2.182335182262355e-06, "loss": 0.4517, "step": 2939 }, { "epoch": 3.292382374906647, "grad_norm": 0.8944980502128601, "learning_rate": 2.1808519338875344e-06, "loss": 0.4825, "step": 2940 }, { "epoch": 3.2935026138909635, "grad_norm": 0.9060550928115845, "learning_rate": 2.1793687997065113e-06, "loss": 0.475, "step": 2941 }, { "epoch": 3.29462285287528, "grad_norm": 0.8911871314048767, "learning_rate": 2.1778857802499633e-06, "loss": 0.4665, "step": 2942 }, { "epoch": 3.2957430918595967, "grad_norm": 0.873059868812561, "learning_rate": 2.176402876048526e-06, "loss": 0.4693, "step": 2943 }, { "epoch": 3.2968633308439133, "grad_norm": 0.9015711545944214, "learning_rate": 2.1749200876327957e-06, "loss": 0.4783, "step": 2944 }, { "epoch": 3.2979835698282303, "grad_norm": 0.8899682760238647, "learning_rate": 2.173437415533325e-06, "loss": 0.4658, "step": 2945 }, { "epoch": 3.299103808812547, "grad_norm": 0.8819183707237244, "learning_rate": 2.1719548602806282e-06, "loss": 0.4834, "step": 2946 }, { "epoch": 3.3002240477968634, "grad_norm": 0.9030231237411499, "learning_rate": 2.1704724224051747e-06, "loss": 0.4759, "step": 2947 }, { "epoch": 3.30134428678118, "grad_norm": 0.8803368210792542, "learning_rate": 2.1689901024373928e-06, "loss": 0.464, "step": 2948 }, { "epoch": 3.3024645257654965, "grad_norm": 0.8923086524009705, "learning_rate": 2.167507900907669e-06, "loss": 0.4724, "step": 2949 }, { "epoch": 3.303584764749813, "grad_norm": 0.8860946893692017, "learning_rate": 2.1660258183463466e-06, "loss": 0.4811, "step": 2950 }, { "epoch": 3.30470500373413, "grad_norm": 0.894370436668396, "learning_rate": 2.164543855283727e-06, "loss": 0.4517, "step": 2951 }, { "epoch": 3.3058252427184467, "grad_norm": 0.8812042474746704, "learning_rate": 2.1630620122500695e-06, "loss": 0.4866, "step": 2952 }, { "epoch": 3.3069454817027633, "grad_norm": 0.8670552968978882, "learning_rate": 2.1615802897755893e-06, "loss": 0.4574, "step": 2953 }, { "epoch": 3.30806572068708, "grad_norm": 0.8947192430496216, "learning_rate": 2.1600986883904582e-06, "loss": 0.4611, "step": 2954 }, { "epoch": 3.3091859596713964, "grad_norm": 0.8878957033157349, "learning_rate": 2.1586172086248068e-06, "loss": 0.4866, "step": 2955 }, { "epoch": 3.3103061986557134, "grad_norm": 0.9235371947288513, "learning_rate": 2.15713585100872e-06, "loss": 0.4912, "step": 2956 }, { "epoch": 3.31142643764003, "grad_norm": 0.8742043375968933, "learning_rate": 2.1556546160722384e-06, "loss": 0.4716, "step": 2957 }, { "epoch": 3.3125466766243465, "grad_norm": 0.901650071144104, "learning_rate": 2.154173504345362e-06, "loss": 0.4464, "step": 2958 }, { "epoch": 3.313666915608663, "grad_norm": 0.8967529535293579, "learning_rate": 2.1526925163580426e-06, "loss": 0.4771, "step": 2959 }, { "epoch": 3.3147871545929797, "grad_norm": 0.9066073298454285, "learning_rate": 2.1512116526401928e-06, "loss": 0.4807, "step": 2960 }, { "epoch": 3.3159073935772962, "grad_norm": 0.9109763503074646, "learning_rate": 2.149730913721675e-06, "loss": 0.4786, "step": 2961 }, { "epoch": 3.3170276325616133, "grad_norm": 0.8713757395744324, "learning_rate": 2.148250300132312e-06, "loss": 0.4764, "step": 2962 }, { "epoch": 3.31814787154593, "grad_norm": 0.8987650871276855, "learning_rate": 2.1467698124018783e-06, "loss": 0.471, "step": 2963 }, { "epoch": 3.3192681105302464, "grad_norm": 0.8933551907539368, "learning_rate": 2.1452894510601037e-06, "loss": 0.4787, "step": 2964 }, { "epoch": 3.320388349514563, "grad_norm": 0.8718818426132202, "learning_rate": 2.1438092166366754e-06, "loss": 0.4589, "step": 2965 }, { "epoch": 3.3215085884988795, "grad_norm": 0.8748862147331238, "learning_rate": 2.1423291096612327e-06, "loss": 0.4734, "step": 2966 }, { "epoch": 3.3226288274831965, "grad_norm": 0.8925787806510925, "learning_rate": 2.140849130663369e-06, "loss": 0.4703, "step": 2967 }, { "epoch": 3.323749066467513, "grad_norm": 0.9141579270362854, "learning_rate": 2.139369280172635e-06, "loss": 0.4907, "step": 2968 }, { "epoch": 3.3248693054518297, "grad_norm": 0.8761618733406067, "learning_rate": 2.137889558718532e-06, "loss": 0.4532, "step": 2969 }, { "epoch": 3.3259895444361463, "grad_norm": 0.8717297911643982, "learning_rate": 2.136409966830516e-06, "loss": 0.443, "step": 2970 }, { "epoch": 3.327109783420463, "grad_norm": 0.9014648795127869, "learning_rate": 2.1349305050379984e-06, "loss": 0.492, "step": 2971 }, { "epoch": 3.32823002240478, "grad_norm": 0.9155656695365906, "learning_rate": 2.133451173870341e-06, "loss": 0.4905, "step": 2972 }, { "epoch": 3.3293502613890964, "grad_norm": 0.86625075340271, "learning_rate": 2.1319719738568636e-06, "loss": 0.4716, "step": 2973 }, { "epoch": 3.330470500373413, "grad_norm": 0.8960084915161133, "learning_rate": 2.130492905526833e-06, "loss": 0.4895, "step": 2974 }, { "epoch": 3.3315907393577295, "grad_norm": 0.8851491808891296, "learning_rate": 2.129013969409474e-06, "loss": 0.4657, "step": 2975 }, { "epoch": 3.332710978342046, "grad_norm": 0.8647192120552063, "learning_rate": 2.1275351660339616e-06, "loss": 0.4803, "step": 2976 }, { "epoch": 3.333831217326363, "grad_norm": 0.8691505789756775, "learning_rate": 2.126056495929423e-06, "loss": 0.4503, "step": 2977 }, { "epoch": 3.3349514563106797, "grad_norm": 0.8689329028129578, "learning_rate": 2.1245779596249394e-06, "loss": 0.4262, "step": 2978 }, { "epoch": 3.3360716952949963, "grad_norm": 0.8592463135719299, "learning_rate": 2.1230995576495434e-06, "loss": 0.4622, "step": 2979 }, { "epoch": 3.337191934279313, "grad_norm": 0.9283711910247803, "learning_rate": 2.121621290532218e-06, "loss": 0.4841, "step": 2980 }, { "epoch": 3.3383121732636294, "grad_norm": 0.9075528383255005, "learning_rate": 2.1201431588019004e-06, "loss": 0.4794, "step": 2981 }, { "epoch": 3.3394324122479464, "grad_norm": 0.8847140073776245, "learning_rate": 2.1186651629874784e-06, "loss": 0.4722, "step": 2982 }, { "epoch": 3.340552651232263, "grad_norm": 0.8786520957946777, "learning_rate": 2.1171873036177907e-06, "loss": 0.4637, "step": 2983 }, { "epoch": 3.3416728902165795, "grad_norm": 0.9059654474258423, "learning_rate": 2.115709581221627e-06, "loss": 0.4931, "step": 2984 }, { "epoch": 3.342793129200896, "grad_norm": 0.925986111164093, "learning_rate": 2.114231996327728e-06, "loss": 0.4885, "step": 2985 }, { "epoch": 3.3439133681852127, "grad_norm": 0.9071976542472839, "learning_rate": 2.1127545494647883e-06, "loss": 0.4584, "step": 2986 }, { "epoch": 3.3450336071695297, "grad_norm": 0.8735948204994202, "learning_rate": 2.1112772411614486e-06, "loss": 0.4576, "step": 2987 }, { "epoch": 3.3461538461538463, "grad_norm": 0.9060523509979248, "learning_rate": 2.109800071946302e-06, "loss": 0.469, "step": 2988 }, { "epoch": 3.347274085138163, "grad_norm": 0.8822818994522095, "learning_rate": 2.1083230423478923e-06, "loss": 0.4586, "step": 2989 }, { "epoch": 3.3483943241224794, "grad_norm": 0.8791356682777405, "learning_rate": 2.1068461528947124e-06, "loss": 0.4689, "step": 2990 }, { "epoch": 3.349514563106796, "grad_norm": 0.8902460336685181, "learning_rate": 2.105369404115205e-06, "loss": 0.4814, "step": 2991 }, { "epoch": 3.350634802091113, "grad_norm": 1.011919379234314, "learning_rate": 2.1038927965377643e-06, "loss": 0.4733, "step": 2992 }, { "epoch": 3.3517550410754295, "grad_norm": 0.8847132325172424, "learning_rate": 2.1024163306907318e-06, "loss": 0.4708, "step": 2993 }, { "epoch": 3.352875280059746, "grad_norm": 0.8767319917678833, "learning_rate": 2.1009400071023983e-06, "loss": 0.4691, "step": 2994 }, { "epoch": 3.3539955190440627, "grad_norm": 0.8783242106437683, "learning_rate": 2.099463826301006e-06, "loss": 0.4647, "step": 2995 }, { "epoch": 3.3551157580283792, "grad_norm": 0.9078060388565063, "learning_rate": 2.097987788814744e-06, "loss": 0.4808, "step": 2996 }, { "epoch": 3.3562359970126963, "grad_norm": 0.8521413803100586, "learning_rate": 2.0965118951717497e-06, "loss": 0.448, "step": 2997 }, { "epoch": 3.357356235997013, "grad_norm": 0.9378989338874817, "learning_rate": 2.09503614590011e-06, "loss": 0.4966, "step": 2998 }, { "epoch": 3.3584764749813294, "grad_norm": 0.9206695556640625, "learning_rate": 2.093560541527862e-06, "loss": 0.4849, "step": 2999 }, { "epoch": 3.359596713965646, "grad_norm": 0.9005029797554016, "learning_rate": 2.0920850825829884e-06, "loss": 0.472, "step": 3000 }, { "epoch": 3.3607169529499625, "grad_norm": 0.8877847194671631, "learning_rate": 2.0906097695934187e-06, "loss": 0.4799, "step": 3001 }, { "epoch": 3.3618371919342795, "grad_norm": 0.9107876420021057, "learning_rate": 2.0891346030870342e-06, "loss": 0.4745, "step": 3002 }, { "epoch": 3.362957430918596, "grad_norm": 0.8996928930282593, "learning_rate": 2.087659583591661e-06, "loss": 0.462, "step": 3003 }, { "epoch": 3.3640776699029127, "grad_norm": 0.9198017120361328, "learning_rate": 2.0861847116350716e-06, "loss": 0.4811, "step": 3004 }, { "epoch": 3.3651979088872293, "grad_norm": 0.9110401272773743, "learning_rate": 2.0847099877449892e-06, "loss": 0.4877, "step": 3005 }, { "epoch": 3.366318147871546, "grad_norm": 0.8642563819885254, "learning_rate": 2.0832354124490816e-06, "loss": 0.4513, "step": 3006 }, { "epoch": 3.367438386855863, "grad_norm": 0.8927781581878662, "learning_rate": 2.0817609862749633e-06, "loss": 0.4703, "step": 3007 }, { "epoch": 3.3685586258401794, "grad_norm": 0.909242570400238, "learning_rate": 2.080286709750197e-06, "loss": 0.4862, "step": 3008 }, { "epoch": 3.369678864824496, "grad_norm": 0.896375834941864, "learning_rate": 2.0788125834022906e-06, "loss": 0.4529, "step": 3009 }, { "epoch": 3.3707991038088125, "grad_norm": 0.9076802134513855, "learning_rate": 2.0773386077586975e-06, "loss": 0.4826, "step": 3010 }, { "epoch": 3.371919342793129, "grad_norm": 0.9062982797622681, "learning_rate": 2.0758647833468203e-06, "loss": 0.4515, "step": 3011 }, { "epoch": 3.3730395817774457, "grad_norm": 0.8983246684074402, "learning_rate": 2.0743911106940035e-06, "loss": 0.4881, "step": 3012 }, { "epoch": 3.3741598207617627, "grad_norm": 0.8858281970024109, "learning_rate": 2.072917590327541e-06, "loss": 0.4485, "step": 3013 }, { "epoch": 3.3752800597460793, "grad_norm": 0.8974294066429138, "learning_rate": 2.07144422277467e-06, "loss": 0.4608, "step": 3014 }, { "epoch": 3.376400298730396, "grad_norm": 0.9049943089485168, "learning_rate": 2.0699710085625726e-06, "loss": 0.4776, "step": 3015 }, { "epoch": 3.3775205377147124, "grad_norm": 0.8882352709770203, "learning_rate": 2.0684979482183777e-06, "loss": 0.4536, "step": 3016 }, { "epoch": 3.378640776699029, "grad_norm": 0.8853976726531982, "learning_rate": 2.0670250422691586e-06, "loss": 0.4725, "step": 3017 }, { "epoch": 3.379761015683346, "grad_norm": 0.9062387347221375, "learning_rate": 2.065552291241932e-06, "loss": 0.5045, "step": 3018 }, { "epoch": 3.3808812546676625, "grad_norm": 0.8972408771514893, "learning_rate": 2.0640796956636617e-06, "loss": 0.4713, "step": 3019 }, { "epoch": 3.382001493651979, "grad_norm": 0.8782559633255005, "learning_rate": 2.062607256061254e-06, "loss": 0.4515, "step": 3020 }, { "epoch": 3.3831217326362957, "grad_norm": 0.90228271484375, "learning_rate": 2.061134972961559e-06, "loss": 0.4838, "step": 3021 }, { "epoch": 3.3842419716206122, "grad_norm": 0.9130343794822693, "learning_rate": 2.059662846891373e-06, "loss": 0.478, "step": 3022 }, { "epoch": 3.385362210604929, "grad_norm": 0.8885895013809204, "learning_rate": 2.0581908783774343e-06, "loss": 0.4651, "step": 3023 }, { "epoch": 3.386482449589246, "grad_norm": 0.8962217569351196, "learning_rate": 2.0567190679464246e-06, "loss": 0.4819, "step": 3024 }, { "epoch": 3.3876026885735624, "grad_norm": 0.9044322967529297, "learning_rate": 2.05524741612497e-06, "loss": 0.4793, "step": 3025 }, { "epoch": 3.388722927557879, "grad_norm": 0.885781466960907, "learning_rate": 2.0537759234396407e-06, "loss": 0.4723, "step": 3026 }, { "epoch": 3.3898431665421955, "grad_norm": 0.8596463203430176, "learning_rate": 2.0523045904169483e-06, "loss": 0.4382, "step": 3027 }, { "epoch": 3.390963405526512, "grad_norm": 0.9821591973304749, "learning_rate": 2.0508334175833473e-06, "loss": 0.4749, "step": 3028 }, { "epoch": 3.392083644510829, "grad_norm": 0.9015606641769409, "learning_rate": 2.049362405465236e-06, "loss": 0.5015, "step": 3029 }, { "epoch": 3.3932038834951457, "grad_norm": 0.9307698011398315, "learning_rate": 2.0478915545889543e-06, "loss": 0.4787, "step": 3030 }, { "epoch": 3.3943241224794622, "grad_norm": 0.895620584487915, "learning_rate": 2.046420865480784e-06, "loss": 0.4764, "step": 3031 }, { "epoch": 3.395444361463779, "grad_norm": 0.9106772541999817, "learning_rate": 2.0449503386669516e-06, "loss": 0.4946, "step": 3032 }, { "epoch": 3.3965646004480954, "grad_norm": 0.8733712434768677, "learning_rate": 2.043479974673623e-06, "loss": 0.4616, "step": 3033 }, { "epoch": 3.3976848394324124, "grad_norm": 0.9288838505744934, "learning_rate": 2.0420097740269045e-06, "loss": 0.4844, "step": 3034 }, { "epoch": 3.398805078416729, "grad_norm": 0.8912079334259033, "learning_rate": 2.040539737252849e-06, "loss": 0.4666, "step": 3035 }, { "epoch": 3.3999253174010455, "grad_norm": 0.9082255959510803, "learning_rate": 2.0390698648774457e-06, "loss": 0.465, "step": 3036 }, { "epoch": 3.401045556385362, "grad_norm": 0.9198353886604309, "learning_rate": 2.037600157426627e-06, "loss": 0.491, "step": 3037 }, { "epoch": 3.4021657953696787, "grad_norm": 0.9249067306518555, "learning_rate": 2.036130615426267e-06, "loss": 0.4931, "step": 3038 }, { "epoch": 3.4032860343539957, "grad_norm": 0.852662205696106, "learning_rate": 2.0346612394021796e-06, "loss": 0.4392, "step": 3039 }, { "epoch": 3.4044062733383122, "grad_norm": 0.9173987507820129, "learning_rate": 2.0331920298801207e-06, "loss": 0.4675, "step": 3040 }, { "epoch": 3.405526512322629, "grad_norm": 0.8715569376945496, "learning_rate": 2.031722987385784e-06, "loss": 0.4646, "step": 3041 }, { "epoch": 3.4066467513069454, "grad_norm": 0.8980058431625366, "learning_rate": 2.0302541124448056e-06, "loss": 0.4801, "step": 3042 }, { "epoch": 3.407766990291262, "grad_norm": 0.9002090096473694, "learning_rate": 2.028785405582761e-06, "loss": 0.498, "step": 3043 }, { "epoch": 3.408887229275579, "grad_norm": 0.9097305536270142, "learning_rate": 2.0273168673251657e-06, "loss": 0.4816, "step": 3044 }, { "epoch": 3.4100074682598955, "grad_norm": 0.9651245474815369, "learning_rate": 2.025848498197474e-06, "loss": 0.4791, "step": 3045 }, { "epoch": 3.411127707244212, "grad_norm": 0.8583818078041077, "learning_rate": 2.0243802987250817e-06, "loss": 0.4535, "step": 3046 }, { "epoch": 3.4122479462285287, "grad_norm": 0.883411705493927, "learning_rate": 2.0229122694333214e-06, "loss": 0.4755, "step": 3047 }, { "epoch": 3.4133681852128452, "grad_norm": 0.9027534127235413, "learning_rate": 2.0214444108474664e-06, "loss": 0.4729, "step": 3048 }, { "epoch": 3.4144884241971623, "grad_norm": 0.8674365878105164, "learning_rate": 2.019976723492729e-06, "loss": 0.4553, "step": 3049 }, { "epoch": 3.415608663181479, "grad_norm": 0.8886181116104126, "learning_rate": 2.018509207894259e-06, "loss": 0.4673, "step": 3050 }, { "epoch": 3.4167289021657954, "grad_norm": 0.9348891973495483, "learning_rate": 2.0170418645771455e-06, "loss": 0.4828, "step": 3051 }, { "epoch": 3.417849141150112, "grad_norm": 0.8894866704940796, "learning_rate": 2.0155746940664173e-06, "loss": 0.4625, "step": 3052 }, { "epoch": 3.4189693801344285, "grad_norm": 0.8905395865440369, "learning_rate": 2.014107696887039e-06, "loss": 0.4676, "step": 3053 }, { "epoch": 3.4200896191187455, "grad_norm": 0.8887937068939209, "learning_rate": 2.0126408735639147e-06, "loss": 0.4344, "step": 3054 }, { "epoch": 3.421209858103062, "grad_norm": 0.9145782589912415, "learning_rate": 2.0111742246218852e-06, "loss": 0.4721, "step": 3055 }, { "epoch": 3.4223300970873787, "grad_norm": 0.8887604475021362, "learning_rate": 2.0097077505857304e-06, "loss": 0.4447, "step": 3056 }, { "epoch": 3.4234503360716952, "grad_norm": 0.899592936038971, "learning_rate": 2.008241451980166e-06, "loss": 0.4792, "step": 3057 }, { "epoch": 3.424570575056012, "grad_norm": 0.9190428853034973, "learning_rate": 2.0067753293298454e-06, "loss": 0.473, "step": 3058 }, { "epoch": 3.425690814040329, "grad_norm": 0.8965968489646912, "learning_rate": 2.0053093831593607e-06, "loss": 0.4715, "step": 3059 }, { "epoch": 3.4268110530246454, "grad_norm": 0.88483065366745, "learning_rate": 2.0038436139932384e-06, "loss": 0.47, "step": 3060 }, { "epoch": 3.427931292008962, "grad_norm": 0.8784518241882324, "learning_rate": 2.002378022355942e-06, "loss": 0.4603, "step": 3061 }, { "epoch": 3.4290515309932785, "grad_norm": 0.9156959056854248, "learning_rate": 2.000912608771874e-06, "loss": 0.4549, "step": 3062 }, { "epoch": 3.430171769977595, "grad_norm": 0.9033367037773132, "learning_rate": 1.9994473737653706e-06, "loss": 0.4807, "step": 3063 }, { "epoch": 3.431292008961912, "grad_norm": 0.8896963596343994, "learning_rate": 1.9979823178607044e-06, "loss": 0.4637, "step": 3064 }, { "epoch": 3.4324122479462287, "grad_norm": 0.9032397270202637, "learning_rate": 1.9965174415820843e-06, "loss": 0.479, "step": 3065 }, { "epoch": 3.4335324869305452, "grad_norm": 0.8870329260826111, "learning_rate": 1.9950527454536566e-06, "loss": 0.4608, "step": 3066 }, { "epoch": 3.434652725914862, "grad_norm": 0.9028913378715515, "learning_rate": 1.993588229999501e-06, "loss": 0.4711, "step": 3067 }, { "epoch": 3.4357729648991784, "grad_norm": 0.890121340751648, "learning_rate": 1.992123895743632e-06, "loss": 0.4766, "step": 3068 }, { "epoch": 3.436893203883495, "grad_norm": 0.8935912847518921, "learning_rate": 1.990659743210001e-06, "loss": 0.4732, "step": 3069 }, { "epoch": 3.438013442867812, "grad_norm": 0.8871170282363892, "learning_rate": 1.989195772922495e-06, "loss": 0.4697, "step": 3070 }, { "epoch": 3.4391336818521285, "grad_norm": 0.907689094543457, "learning_rate": 1.9877319854049333e-06, "loss": 0.475, "step": 3071 }, { "epoch": 3.440253920836445, "grad_norm": 0.8883797526359558, "learning_rate": 1.9862683811810706e-06, "loss": 0.4811, "step": 3072 }, { "epoch": 3.4413741598207617, "grad_norm": 0.9052229523658752, "learning_rate": 1.9848049607745983e-06, "loss": 0.4677, "step": 3073 }, { "epoch": 3.4424943988050782, "grad_norm": 0.9068377614021301, "learning_rate": 1.9833417247091384e-06, "loss": 0.4709, "step": 3074 }, { "epoch": 3.4436146377893952, "grad_norm": 1.094725489616394, "learning_rate": 1.9818786735082495e-06, "loss": 0.5004, "step": 3075 }, { "epoch": 3.444734876773712, "grad_norm": 0.9113338589668274, "learning_rate": 1.980415807695424e-06, "loss": 0.4602, "step": 3076 }, { "epoch": 3.4458551157580284, "grad_norm": 0.9088565707206726, "learning_rate": 1.978953127794087e-06, "loss": 0.4756, "step": 3077 }, { "epoch": 3.446975354742345, "grad_norm": 0.9180811047554016, "learning_rate": 1.9774906343275953e-06, "loss": 0.4766, "step": 3078 }, { "epoch": 3.4480955937266615, "grad_norm": 0.8921608924865723, "learning_rate": 1.9760283278192437e-06, "loss": 0.4701, "step": 3079 }, { "epoch": 3.4492158327109785, "grad_norm": 0.9099887013435364, "learning_rate": 1.9745662087922574e-06, "loss": 0.4716, "step": 3080 }, { "epoch": 3.450336071695295, "grad_norm": 0.8737456202507019, "learning_rate": 1.9731042777697932e-06, "loss": 0.4699, "step": 3081 }, { "epoch": 3.4514563106796117, "grad_norm": 0.9046941995620728, "learning_rate": 1.971642535274943e-06, "loss": 0.5093, "step": 3082 }, { "epoch": 3.4525765496639282, "grad_norm": 0.8937767148017883, "learning_rate": 1.9701809818307294e-06, "loss": 0.4811, "step": 3083 }, { "epoch": 3.453696788648245, "grad_norm": 0.9059481024742126, "learning_rate": 1.968719617960109e-06, "loss": 0.482, "step": 3084 }, { "epoch": 3.4548170276325614, "grad_norm": 0.9018389582633972, "learning_rate": 1.967258444185969e-06, "loss": 0.4632, "step": 3085 }, { "epoch": 3.4559372666168784, "grad_norm": 0.9016770720481873, "learning_rate": 1.9657974610311305e-06, "loss": 0.4618, "step": 3086 }, { "epoch": 3.457057505601195, "grad_norm": 0.8880774974822998, "learning_rate": 1.9643366690183445e-06, "loss": 0.4754, "step": 3087 }, { "epoch": 3.4581777445855115, "grad_norm": 0.891247034072876, "learning_rate": 1.962876068670294e-06, "loss": 0.4868, "step": 3088 }, { "epoch": 3.459297983569828, "grad_norm": 0.9227710366249084, "learning_rate": 1.9614156605095945e-06, "loss": 0.4816, "step": 3089 }, { "epoch": 3.4604182225541447, "grad_norm": 0.8883443474769592, "learning_rate": 1.959955445058792e-06, "loss": 0.4719, "step": 3090 }, { "epoch": 3.4615384615384617, "grad_norm": 0.9139862656593323, "learning_rate": 1.9584954228403622e-06, "loss": 0.4867, "step": 3091 }, { "epoch": 3.4626587005227782, "grad_norm": 1.0329859256744385, "learning_rate": 1.957035594376715e-06, "loss": 0.4557, "step": 3092 }, { "epoch": 3.463778939507095, "grad_norm": 0.9025547504425049, "learning_rate": 1.9555759601901885e-06, "loss": 0.4625, "step": 3093 }, { "epoch": 3.4648991784914114, "grad_norm": 0.9389105439186096, "learning_rate": 1.9541165208030515e-06, "loss": 0.4823, "step": 3094 }, { "epoch": 3.466019417475728, "grad_norm": 0.8866137862205505, "learning_rate": 1.952657276737503e-06, "loss": 0.4718, "step": 3095 }, { "epoch": 3.467139656460045, "grad_norm": 0.9028794765472412, "learning_rate": 1.9511982285156732e-06, "loss": 0.4888, "step": 3096 }, { "epoch": 3.4682598954443615, "grad_norm": 0.9230520725250244, "learning_rate": 1.9497393766596217e-06, "loss": 0.4816, "step": 3097 }, { "epoch": 3.469380134428678, "grad_norm": 0.8764287233352661, "learning_rate": 1.948280721691336e-06, "loss": 0.4622, "step": 3098 }, { "epoch": 3.4705003734129947, "grad_norm": 0.8796346783638, "learning_rate": 1.946822264132737e-06, "loss": 0.4848, "step": 3099 }, { "epoch": 3.4716206123973112, "grad_norm": 0.8827326893806458, "learning_rate": 1.9453640045056714e-06, "loss": 0.466, "step": 3100 }, { "epoch": 3.4727408513816282, "grad_norm": 0.9263519048690796, "learning_rate": 1.9439059433319164e-06, "loss": 0.4648, "step": 3101 }, { "epoch": 3.473861090365945, "grad_norm": 0.8937462568283081, "learning_rate": 1.942448081133179e-06, "loss": 0.4705, "step": 3102 }, { "epoch": 3.4749813293502614, "grad_norm": 0.8788604140281677, "learning_rate": 1.9409904184310948e-06, "loss": 0.4584, "step": 3103 }, { "epoch": 3.476101568334578, "grad_norm": 0.8764767646789551, "learning_rate": 1.939532955747225e-06, "loss": 0.4753, "step": 3104 }, { "epoch": 3.4772218073188945, "grad_norm": 0.8962751626968384, "learning_rate": 1.938075693603064e-06, "loss": 0.4711, "step": 3105 }, { "epoch": 3.4783420463032115, "grad_norm": 0.9014900922775269, "learning_rate": 1.9366186325200313e-06, "loss": 0.4834, "step": 3106 }, { "epoch": 3.479462285287528, "grad_norm": 0.8872891664505005, "learning_rate": 1.9351617730194765e-06, "loss": 0.465, "step": 3107 }, { "epoch": 3.4805825242718447, "grad_norm": 0.9116504788398743, "learning_rate": 1.9337051156226745e-06, "loss": 0.459, "step": 3108 }, { "epoch": 3.4817027632561612, "grad_norm": 0.9077987670898438, "learning_rate": 1.932248660850829e-06, "loss": 0.4959, "step": 3109 }, { "epoch": 3.482823002240478, "grad_norm": 0.927905261516571, "learning_rate": 1.930792409225073e-06, "loss": 0.4786, "step": 3110 }, { "epoch": 3.483943241224795, "grad_norm": 0.8846545219421387, "learning_rate": 1.9293363612664643e-06, "loss": 0.4581, "step": 3111 }, { "epoch": 3.4850634802091114, "grad_norm": 0.9181705117225647, "learning_rate": 1.9278805174959883e-06, "loss": 0.4731, "step": 3112 }, { "epoch": 3.486183719193428, "grad_norm": 0.9095129370689392, "learning_rate": 1.926424878434559e-06, "loss": 0.4699, "step": 3113 }, { "epoch": 3.4873039581777445, "grad_norm": 0.9082843661308289, "learning_rate": 1.9249694446030158e-06, "loss": 0.479, "step": 3114 }, { "epoch": 3.488424197162061, "grad_norm": 0.9202296137809753, "learning_rate": 1.9235142165221236e-06, "loss": 0.4847, "step": 3115 }, { "epoch": 3.489544436146378, "grad_norm": 0.9420201778411865, "learning_rate": 1.922059194712577e-06, "loss": 0.4587, "step": 3116 }, { "epoch": 3.4906646751306947, "grad_norm": 0.9165387153625488, "learning_rate": 1.920604379694993e-06, "loss": 0.4807, "step": 3117 }, { "epoch": 3.4917849141150112, "grad_norm": 0.889249861240387, "learning_rate": 1.919149771989916e-06, "loss": 0.4562, "step": 3118 }, { "epoch": 3.492905153099328, "grad_norm": 0.9261665940284729, "learning_rate": 1.917695372117818e-06, "loss": 0.4838, "step": 3119 }, { "epoch": 3.4940253920836444, "grad_norm": 0.8773506283760071, "learning_rate": 1.9162411805990957e-06, "loss": 0.4434, "step": 3120 }, { "epoch": 3.4951456310679614, "grad_norm": 0.8854514956474304, "learning_rate": 1.91478719795407e-06, "loss": 0.4693, "step": 3121 }, { "epoch": 3.496265870052278, "grad_norm": 0.8938907384872437, "learning_rate": 1.9133334247029866e-06, "loss": 0.4794, "step": 3122 }, { "epoch": 3.4973861090365945, "grad_norm": 0.9062140583992004, "learning_rate": 1.9118798613660194e-06, "loss": 0.4806, "step": 3123 }, { "epoch": 3.498506348020911, "grad_norm": 0.890254557132721, "learning_rate": 1.9104265084632643e-06, "loss": 0.4729, "step": 3124 }, { "epoch": 3.4996265870052277, "grad_norm": 0.9119646549224854, "learning_rate": 1.908973366514743e-06, "loss": 0.4557, "step": 3125 }, { "epoch": 3.5007468259895447, "grad_norm": 0.878225564956665, "learning_rate": 1.9075204360404017e-06, "loss": 0.4599, "step": 3126 }, { "epoch": 3.5018670649738612, "grad_norm": 0.8916877508163452, "learning_rate": 1.906067717560111e-06, "loss": 0.4615, "step": 3127 }, { "epoch": 3.502987303958178, "grad_norm": 0.910254955291748, "learning_rate": 1.9046152115936648e-06, "loss": 0.4634, "step": 3128 }, { "epoch": 3.5041075429424944, "grad_norm": 0.9213933944702148, "learning_rate": 1.9031629186607825e-06, "loss": 0.4796, "step": 3129 }, { "epoch": 3.505227781926811, "grad_norm": 0.8748009204864502, "learning_rate": 1.9017108392811065e-06, "loss": 0.4583, "step": 3130 }, { "epoch": 3.506348020911128, "grad_norm": 0.8991055488586426, "learning_rate": 1.9002589739742007e-06, "loss": 0.4733, "step": 3131 }, { "epoch": 3.507468259895444, "grad_norm": 0.9172875881195068, "learning_rate": 1.8988073232595577e-06, "loss": 0.4784, "step": 3132 }, { "epoch": 3.508588498879761, "grad_norm": 0.9289745092391968, "learning_rate": 1.8973558876565873e-06, "loss": 0.4993, "step": 3133 }, { "epoch": 3.5097087378640777, "grad_norm": 0.9053197503089905, "learning_rate": 1.895904667684627e-06, "loss": 0.4935, "step": 3134 }, { "epoch": 3.5108289768483942, "grad_norm": 0.9255849123001099, "learning_rate": 1.8944536638629343e-06, "loss": 0.5045, "step": 3135 }, { "epoch": 3.5119492158327112, "grad_norm": 0.9016849994659424, "learning_rate": 1.8930028767106898e-06, "loss": 0.4721, "step": 3136 }, { "epoch": 3.5130694548170274, "grad_norm": 0.8845933079719543, "learning_rate": 1.8915523067469982e-06, "loss": 0.4665, "step": 3137 }, { "epoch": 3.5141896938013444, "grad_norm": 0.9056075811386108, "learning_rate": 1.8901019544908846e-06, "loss": 0.4855, "step": 3138 }, { "epoch": 3.515309932785661, "grad_norm": 0.8945724368095398, "learning_rate": 1.8886518204612966e-06, "loss": 0.4712, "step": 3139 }, { "epoch": 3.5164301717699775, "grad_norm": 0.8938843011856079, "learning_rate": 1.8872019051771052e-06, "loss": 0.469, "step": 3140 }, { "epoch": 3.517550410754294, "grad_norm": 0.8376768231391907, "learning_rate": 1.8857522091571009e-06, "loss": 0.4363, "step": 3141 }, { "epoch": 3.5186706497386107, "grad_norm": 0.8898146152496338, "learning_rate": 1.884302732919997e-06, "loss": 0.4825, "step": 3142 }, { "epoch": 3.5197908887229277, "grad_norm": 0.8933739066123962, "learning_rate": 1.8828534769844287e-06, "loss": 0.4654, "step": 3143 }, { "epoch": 3.5209111277072442, "grad_norm": 0.871864378452301, "learning_rate": 1.8814044418689504e-06, "loss": 0.4711, "step": 3144 }, { "epoch": 3.522031366691561, "grad_norm": 0.9002297520637512, "learning_rate": 1.8799556280920403e-06, "loss": 0.4742, "step": 3145 }, { "epoch": 3.5231516056758774, "grad_norm": 0.8928772807121277, "learning_rate": 1.8785070361720946e-06, "loss": 0.4842, "step": 3146 }, { "epoch": 3.524271844660194, "grad_norm": 0.8720741868019104, "learning_rate": 1.8770586666274326e-06, "loss": 0.4538, "step": 3147 }, { "epoch": 3.525392083644511, "grad_norm": 0.8787303566932678, "learning_rate": 1.875610519976292e-06, "loss": 0.459, "step": 3148 }, { "epoch": 3.5265123226288275, "grad_norm": 0.9099289774894714, "learning_rate": 1.8741625967368312e-06, "loss": 0.4953, "step": 3149 }, { "epoch": 3.527632561613144, "grad_norm": 0.8992205262184143, "learning_rate": 1.87271489742713e-06, "loss": 0.482, "step": 3150 }, { "epoch": 3.5287528005974607, "grad_norm": 0.9039930105209351, "learning_rate": 1.8712674225651867e-06, "loss": 0.4715, "step": 3151 }, { "epoch": 3.5298730395817772, "grad_norm": 0.88331538438797, "learning_rate": 1.8698201726689188e-06, "loss": 0.4566, "step": 3152 }, { "epoch": 3.5309932785660942, "grad_norm": 0.8823280930519104, "learning_rate": 1.8683731482561656e-06, "loss": 0.468, "step": 3153 }, { "epoch": 3.532113517550411, "grad_norm": 0.8982490301132202, "learning_rate": 1.8669263498446837e-06, "loss": 0.4887, "step": 3154 }, { "epoch": 3.5332337565347274, "grad_norm": 0.906599760055542, "learning_rate": 1.8654797779521489e-06, "loss": 0.4645, "step": 3155 }, { "epoch": 3.534353995519044, "grad_norm": 0.8811005353927612, "learning_rate": 1.8640334330961574e-06, "loss": 0.4723, "step": 3156 }, { "epoch": 3.5354742345033605, "grad_norm": 0.9330654740333557, "learning_rate": 1.8625873157942232e-06, "loss": 0.4749, "step": 3157 }, { "epoch": 3.5365944734876775, "grad_norm": 0.9042448997497559, "learning_rate": 1.861141426563777e-06, "loss": 0.4481, "step": 3158 }, { "epoch": 3.537714712471994, "grad_norm": 0.9265058636665344, "learning_rate": 1.8596957659221726e-06, "loss": 0.4697, "step": 3159 }, { "epoch": 3.5388349514563107, "grad_norm": 0.9087609052658081, "learning_rate": 1.8582503343866778e-06, "loss": 0.4675, "step": 3160 }, { "epoch": 3.5399551904406272, "grad_norm": 0.9114390015602112, "learning_rate": 1.8568051324744807e-06, "loss": 0.4634, "step": 3161 }, { "epoch": 3.541075429424944, "grad_norm": 0.8984902501106262, "learning_rate": 1.8553601607026858e-06, "loss": 0.4725, "step": 3162 }, { "epoch": 3.542195668409261, "grad_norm": 0.8920361399650574, "learning_rate": 1.8539154195883153e-06, "loss": 0.4644, "step": 3163 }, { "epoch": 3.5433159073935774, "grad_norm": 0.9203718304634094, "learning_rate": 1.8524709096483106e-06, "loss": 0.4632, "step": 3164 }, { "epoch": 3.544436146377894, "grad_norm": 0.9027872085571289, "learning_rate": 1.8510266313995284e-06, "loss": 0.468, "step": 3165 }, { "epoch": 3.5455563853622105, "grad_norm": 0.8890506625175476, "learning_rate": 1.8495825853587435e-06, "loss": 0.4566, "step": 3166 }, { "epoch": 3.546676624346527, "grad_norm": 0.8776019215583801, "learning_rate": 1.8481387720426477e-06, "loss": 0.4793, "step": 3167 }, { "epoch": 3.547796863330844, "grad_norm": 0.9331218004226685, "learning_rate": 1.8466951919678491e-06, "loss": 0.4599, "step": 3168 }, { "epoch": 3.5489171023151607, "grad_norm": 0.8889367580413818, "learning_rate": 1.845251845650872e-06, "loss": 0.4624, "step": 3169 }, { "epoch": 3.5500373412994772, "grad_norm": 0.8865241408348083, "learning_rate": 1.8438087336081583e-06, "loss": 0.4628, "step": 3170 }, { "epoch": 3.551157580283794, "grad_norm": 0.9205052852630615, "learning_rate": 1.8423658563560642e-06, "loss": 0.4723, "step": 3171 }, { "epoch": 3.5522778192681104, "grad_norm": 0.859010636806488, "learning_rate": 1.840923214410865e-06, "loss": 0.4589, "step": 3172 }, { "epoch": 3.5533980582524274, "grad_norm": 0.9040504097938538, "learning_rate": 1.8394808082887478e-06, "loss": 0.4783, "step": 3173 }, { "epoch": 3.554518297236744, "grad_norm": 0.8909608721733093, "learning_rate": 1.838038638505819e-06, "loss": 0.4399, "step": 3174 }, { "epoch": 3.5556385362210605, "grad_norm": 0.9190822839736938, "learning_rate": 1.8365967055780978e-06, "loss": 0.481, "step": 3175 }, { "epoch": 3.556758775205377, "grad_norm": 0.9102426767349243, "learning_rate": 1.8351550100215194e-06, "loss": 0.4766, "step": 3176 }, { "epoch": 3.5578790141896937, "grad_norm": 0.911824643611908, "learning_rate": 1.8337135523519354e-06, "loss": 0.4725, "step": 3177 }, { "epoch": 3.5589992531740107, "grad_norm": 0.8935957551002502, "learning_rate": 1.8322723330851106e-06, "loss": 0.4711, "step": 3178 }, { "epoch": 3.5601194921583272, "grad_norm": 0.8897913098335266, "learning_rate": 1.8308313527367242e-06, "loss": 0.446, "step": 3179 }, { "epoch": 3.561239731142644, "grad_norm": 0.90127032995224, "learning_rate": 1.829390611822372e-06, "loss": 0.4809, "step": 3180 }, { "epoch": 3.5623599701269604, "grad_norm": 0.8886820673942566, "learning_rate": 1.8279501108575628e-06, "loss": 0.472, "step": 3181 }, { "epoch": 3.563480209111277, "grad_norm": 0.9303297996520996, "learning_rate": 1.826509850357719e-06, "loss": 0.4641, "step": 3182 }, { "epoch": 3.564600448095594, "grad_norm": 0.9053724408149719, "learning_rate": 1.8250698308381782e-06, "loss": 0.4922, "step": 3183 }, { "epoch": 3.5657206870799105, "grad_norm": 0.8963432908058167, "learning_rate": 1.8236300528141905e-06, "loss": 0.4755, "step": 3184 }, { "epoch": 3.566840926064227, "grad_norm": 0.8679113388061523, "learning_rate": 1.8221905168009213e-06, "loss": 0.457, "step": 3185 }, { "epoch": 3.5679611650485437, "grad_norm": 0.8845415115356445, "learning_rate": 1.8207512233134483e-06, "loss": 0.4851, "step": 3186 }, { "epoch": 3.5690814040328602, "grad_norm": 0.9045202136039734, "learning_rate": 1.8193121728667612e-06, "loss": 0.4395, "step": 3187 }, { "epoch": 3.5702016430171772, "grad_norm": 0.9207714200019836, "learning_rate": 1.817873365975766e-06, "loss": 0.468, "step": 3188 }, { "epoch": 3.571321882001494, "grad_norm": 0.9101921319961548, "learning_rate": 1.816434803155278e-06, "loss": 0.4794, "step": 3189 }, { "epoch": 3.5724421209858104, "grad_norm": 0.8836941719055176, "learning_rate": 1.8149964849200274e-06, "loss": 0.4648, "step": 3190 }, { "epoch": 3.573562359970127, "grad_norm": 0.9096801280975342, "learning_rate": 1.8135584117846567e-06, "loss": 0.4581, "step": 3191 }, { "epoch": 3.5746825989544435, "grad_norm": 0.9292516112327576, "learning_rate": 1.8121205842637198e-06, "loss": 0.479, "step": 3192 }, { "epoch": 3.5758028379387605, "grad_norm": 0.905788004398346, "learning_rate": 1.8106830028716827e-06, "loss": 0.4677, "step": 3193 }, { "epoch": 3.5769230769230766, "grad_norm": 0.8991992473602295, "learning_rate": 1.8092456681229248e-06, "loss": 0.4543, "step": 3194 }, { "epoch": 3.5780433159073937, "grad_norm": 0.9108956456184387, "learning_rate": 1.8078085805317358e-06, "loss": 0.4878, "step": 3195 }, { "epoch": 3.5791635548917102, "grad_norm": 0.9062317609786987, "learning_rate": 1.8063717406123171e-06, "loss": 0.4787, "step": 3196 }, { "epoch": 3.580283793876027, "grad_norm": 0.8880710601806641, "learning_rate": 1.8049351488787813e-06, "loss": 0.4482, "step": 3197 }, { "epoch": 3.581404032860344, "grad_norm": 0.9360930323600769, "learning_rate": 1.8034988058451553e-06, "loss": 0.4582, "step": 3198 }, { "epoch": 3.58252427184466, "grad_norm": 0.9268977642059326, "learning_rate": 1.802062712025372e-06, "loss": 0.4874, "step": 3199 }, { "epoch": 3.583644510828977, "grad_norm": 0.9165009260177612, "learning_rate": 1.8006268679332778e-06, "loss": 0.4667, "step": 3200 }, { "epoch": 3.5847647498132935, "grad_norm": 0.8919568061828613, "learning_rate": 1.7991912740826306e-06, "loss": 0.4584, "step": 3201 }, { "epoch": 3.58588498879761, "grad_norm": 0.9347192645072937, "learning_rate": 1.7977559309870972e-06, "loss": 0.5118, "step": 3202 }, { "epoch": 3.5870052277819267, "grad_norm": 0.8858456611633301, "learning_rate": 1.7963208391602544e-06, "loss": 0.4784, "step": 3203 }, { "epoch": 3.588125466766243, "grad_norm": 0.885890007019043, "learning_rate": 1.7948859991155909e-06, "loss": 0.463, "step": 3204 }, { "epoch": 3.5892457057505602, "grad_norm": 0.9072828888893127, "learning_rate": 1.7934514113665036e-06, "loss": 0.4679, "step": 3205 }, { "epoch": 3.590365944734877, "grad_norm": 0.9028578996658325, "learning_rate": 1.7920170764262993e-06, "loss": 0.47, "step": 3206 }, { "epoch": 3.5914861837191934, "grad_norm": 0.8855698704719543, "learning_rate": 1.790582994808196e-06, "loss": 0.4818, "step": 3207 }, { "epoch": 3.59260642270351, "grad_norm": 0.8978846669197083, "learning_rate": 1.7891491670253192e-06, "loss": 0.4528, "step": 3208 }, { "epoch": 3.5937266616878265, "grad_norm": 0.89417564868927, "learning_rate": 1.7877155935907042e-06, "loss": 0.4742, "step": 3209 }, { "epoch": 3.5948469006721435, "grad_norm": 0.9829598665237427, "learning_rate": 1.7862822750172957e-06, "loss": 0.4389, "step": 3210 }, { "epoch": 3.59596713965646, "grad_norm": 0.9261658191680908, "learning_rate": 1.7848492118179456e-06, "loss": 0.4859, "step": 3211 }, { "epoch": 3.5970873786407767, "grad_norm": 0.9410789608955383, "learning_rate": 1.7834164045054175e-06, "loss": 0.4804, "step": 3212 }, { "epoch": 3.5982076176250932, "grad_norm": 0.8875792026519775, "learning_rate": 1.7819838535923806e-06, "loss": 0.4805, "step": 3213 }, { "epoch": 3.59932785660941, "grad_norm": 0.8902440071105957, "learning_rate": 1.7805515595914142e-06, "loss": 0.4717, "step": 3214 }, { "epoch": 3.600448095593727, "grad_norm": 0.9007441997528076, "learning_rate": 1.7791195230150042e-06, "loss": 0.4624, "step": 3215 }, { "epoch": 3.6015683345780434, "grad_norm": 0.8869627714157104, "learning_rate": 1.777687744375544e-06, "loss": 0.4729, "step": 3216 }, { "epoch": 3.60268857356236, "grad_norm": 0.8734548687934875, "learning_rate": 1.776256224185338e-06, "loss": 0.464, "step": 3217 }, { "epoch": 3.6038088125466765, "grad_norm": 0.914516806602478, "learning_rate": 1.7748249629565944e-06, "loss": 0.4771, "step": 3218 }, { "epoch": 3.604929051530993, "grad_norm": 0.8961203694343567, "learning_rate": 1.77339396120143e-06, "loss": 0.4698, "step": 3219 }, { "epoch": 3.60604929051531, "grad_norm": 0.9044591784477234, "learning_rate": 1.7719632194318704e-06, "loss": 0.4769, "step": 3220 }, { "epoch": 3.6071695294996267, "grad_norm": 0.9193779230117798, "learning_rate": 1.7705327381598453e-06, "loss": 0.4691, "step": 3221 }, { "epoch": 3.6082897684839432, "grad_norm": 0.9105710983276367, "learning_rate": 1.7691025178971932e-06, "loss": 0.4817, "step": 3222 }, { "epoch": 3.60941000746826, "grad_norm": 0.9188927412033081, "learning_rate": 1.7676725591556585e-06, "loss": 0.5074, "step": 3223 }, { "epoch": 3.6105302464525764, "grad_norm": 0.8795026540756226, "learning_rate": 1.7662428624468914e-06, "loss": 0.4585, "step": 3224 }, { "epoch": 3.6116504854368934, "grad_norm": 0.9236079454421997, "learning_rate": 1.7648134282824514e-06, "loss": 0.4803, "step": 3225 }, { "epoch": 3.61277072442121, "grad_norm": 0.8754583597183228, "learning_rate": 1.7633842571738e-06, "loss": 0.4552, "step": 3226 }, { "epoch": 3.6138909634055265, "grad_norm": 0.9170207381248474, "learning_rate": 1.761955349632306e-06, "loss": 0.4748, "step": 3227 }, { "epoch": 3.615011202389843, "grad_norm": 0.9035067558288574, "learning_rate": 1.760526706169246e-06, "loss": 0.4924, "step": 3228 }, { "epoch": 3.6161314413741596, "grad_norm": 0.8940739631652832, "learning_rate": 1.7590983272957994e-06, "loss": 0.4662, "step": 3229 }, { "epoch": 3.6172516803584767, "grad_norm": 0.9048197865486145, "learning_rate": 1.757670213523051e-06, "loss": 0.4767, "step": 3230 }, { "epoch": 3.6183719193427932, "grad_norm": 0.9008917212486267, "learning_rate": 1.7562423653619931e-06, "loss": 0.4473, "step": 3231 }, { "epoch": 3.61949215832711, "grad_norm": 0.8892508149147034, "learning_rate": 1.7548147833235207e-06, "loss": 0.4714, "step": 3232 }, { "epoch": 3.6206123973114264, "grad_norm": 0.9011636972427368, "learning_rate": 1.753387467918434e-06, "loss": 0.4579, "step": 3233 }, { "epoch": 3.621732636295743, "grad_norm": 1.352868676185608, "learning_rate": 1.751960419657439e-06, "loss": 0.4735, "step": 3234 }, { "epoch": 3.62285287528006, "grad_norm": 0.9019132852554321, "learning_rate": 1.750533639051145e-06, "loss": 0.4607, "step": 3235 }, { "epoch": 3.6239731142643765, "grad_norm": 0.8836408853530884, "learning_rate": 1.7491071266100657e-06, "loss": 0.47, "step": 3236 }, { "epoch": 3.625093353248693, "grad_norm": 0.8957796096801758, "learning_rate": 1.7476808828446184e-06, "loss": 0.4543, "step": 3237 }, { "epoch": 3.6262135922330097, "grad_norm": 0.9233945608139038, "learning_rate": 1.7462549082651262e-06, "loss": 0.4868, "step": 3238 }, { "epoch": 3.627333831217326, "grad_norm": 0.8700676560401917, "learning_rate": 1.7448292033818138e-06, "loss": 0.4529, "step": 3239 }, { "epoch": 3.6284540702016432, "grad_norm": 0.9069575667381287, "learning_rate": 1.7434037687048094e-06, "loss": 0.4821, "step": 3240 }, { "epoch": 3.62957430918596, "grad_norm": 0.9073121547698975, "learning_rate": 1.7419786047441467e-06, "loss": 0.4708, "step": 3241 }, { "epoch": 3.6306945481702764, "grad_norm": 0.9006640315055847, "learning_rate": 1.74055371200976e-06, "loss": 0.4571, "step": 3242 }, { "epoch": 3.631814787154593, "grad_norm": 0.9110651016235352, "learning_rate": 1.7391290910114879e-06, "loss": 0.4729, "step": 3243 }, { "epoch": 3.6329350261389095, "grad_norm": 0.9307955503463745, "learning_rate": 1.7377047422590711e-06, "loss": 0.4776, "step": 3244 }, { "epoch": 3.6340552651232265, "grad_norm": 0.8872925639152527, "learning_rate": 1.736280666262154e-06, "loss": 0.465, "step": 3245 }, { "epoch": 3.635175504107543, "grad_norm": 0.8986032605171204, "learning_rate": 1.734856863530282e-06, "loss": 0.4589, "step": 3246 }, { "epoch": 3.6362957430918597, "grad_norm": 0.9043907523155212, "learning_rate": 1.733433334572904e-06, "loss": 0.4483, "step": 3247 }, { "epoch": 3.6374159820761762, "grad_norm": 0.9556801915168762, "learning_rate": 1.73201007989937e-06, "loss": 0.4906, "step": 3248 }, { "epoch": 3.638536221060493, "grad_norm": 0.9355320334434509, "learning_rate": 1.7305871000189316e-06, "loss": 0.5012, "step": 3249 }, { "epoch": 3.63965646004481, "grad_norm": 0.9301635026931763, "learning_rate": 1.7291643954407439e-06, "loss": 0.4878, "step": 3250 }, { "epoch": 3.6407766990291264, "grad_norm": 0.9100080728530884, "learning_rate": 1.727741966673861e-06, "loss": 0.4709, "step": 3251 }, { "epoch": 3.641896938013443, "grad_norm": 0.8853621482849121, "learning_rate": 1.7263198142272413e-06, "loss": 0.4702, "step": 3252 }, { "epoch": 3.6430171769977595, "grad_norm": 0.9045686721801758, "learning_rate": 1.7248979386097415e-06, "loss": 0.4683, "step": 3253 }, { "epoch": 3.644137415982076, "grad_norm": 0.889969527721405, "learning_rate": 1.7234763403301197e-06, "loss": 0.4729, "step": 3254 }, { "epoch": 3.645257654966393, "grad_norm": 0.9017740488052368, "learning_rate": 1.722055019897037e-06, "loss": 0.469, "step": 3255 }, { "epoch": 3.646377893950709, "grad_norm": 0.9049615859985352, "learning_rate": 1.7206339778190525e-06, "loss": 0.4773, "step": 3256 }, { "epoch": 3.6474981329350262, "grad_norm": 0.917921781539917, "learning_rate": 1.7192132146046264e-06, "loss": 0.4799, "step": 3257 }, { "epoch": 3.648618371919343, "grad_norm": 0.8881093859672546, "learning_rate": 1.7177927307621206e-06, "loss": 0.4675, "step": 3258 }, { "epoch": 3.6497386109036594, "grad_norm": 0.907099187374115, "learning_rate": 1.7163725267997955e-06, "loss": 0.476, "step": 3259 }, { "epoch": 3.6508588498879764, "grad_norm": 0.8914150595664978, "learning_rate": 1.7149526032258107e-06, "loss": 0.4564, "step": 3260 }, { "epoch": 3.6519790888722925, "grad_norm": 0.9187562465667725, "learning_rate": 1.7135329605482276e-06, "loss": 0.4871, "step": 3261 }, { "epoch": 3.6530993278566095, "grad_norm": 0.903536856174469, "learning_rate": 1.712113599275006e-06, "loss": 0.4787, "step": 3262 }, { "epoch": 3.654219566840926, "grad_norm": 0.9384742975234985, "learning_rate": 1.710694519914004e-06, "loss": 0.4972, "step": 3263 }, { "epoch": 3.6553398058252426, "grad_norm": 0.9178777933120728, "learning_rate": 1.70927572297298e-06, "loss": 0.4622, "step": 3264 }, { "epoch": 3.656460044809559, "grad_norm": 0.9116693735122681, "learning_rate": 1.707857208959593e-06, "loss": 0.4603, "step": 3265 }, { "epoch": 3.657580283793876, "grad_norm": 0.907081663608551, "learning_rate": 1.7064389783813976e-06, "loss": 0.4765, "step": 3266 }, { "epoch": 3.658700522778193, "grad_norm": 0.9318583607673645, "learning_rate": 1.7050210317458476e-06, "loss": 0.4722, "step": 3267 }, { "epoch": 3.6598207617625094, "grad_norm": 0.9200018644332886, "learning_rate": 1.7036033695602976e-06, "loss": 0.4829, "step": 3268 }, { "epoch": 3.660941000746826, "grad_norm": 0.8929603695869446, "learning_rate": 1.7021859923319982e-06, "loss": 0.4618, "step": 3269 }, { "epoch": 3.6620612397311425, "grad_norm": 0.915016233921051, "learning_rate": 1.700768900568097e-06, "loss": 0.4739, "step": 3270 }, { "epoch": 3.663181478715459, "grad_norm": 0.9123505353927612, "learning_rate": 1.6993520947756436e-06, "loss": 0.4474, "step": 3271 }, { "epoch": 3.664301717699776, "grad_norm": 0.9216330647468567, "learning_rate": 1.6979355754615814e-06, "loss": 0.4857, "step": 3272 }, { "epoch": 3.6654219566840927, "grad_norm": 0.8905513882637024, "learning_rate": 1.6965193431327522e-06, "loss": 0.4589, "step": 3273 }, { "epoch": 3.666542195668409, "grad_norm": 0.9219668507575989, "learning_rate": 1.6951033982958967e-06, "loss": 0.4696, "step": 3274 }, { "epoch": 3.667662434652726, "grad_norm": 0.8979023098945618, "learning_rate": 1.6936877414576511e-06, "loss": 0.4779, "step": 3275 }, { "epoch": 3.6687826736370424, "grad_norm": 0.921159029006958, "learning_rate": 1.6922723731245483e-06, "loss": 0.4836, "step": 3276 }, { "epoch": 3.6699029126213594, "grad_norm": 0.905030369758606, "learning_rate": 1.6908572938030194e-06, "loss": 0.464, "step": 3277 }, { "epoch": 3.671023151605676, "grad_norm": 0.901539146900177, "learning_rate": 1.689442503999391e-06, "loss": 0.4733, "step": 3278 }, { "epoch": 3.6721433905899925, "grad_norm": 0.8852400779724121, "learning_rate": 1.688028004219888e-06, "loss": 0.4883, "step": 3279 }, { "epoch": 3.673263629574309, "grad_norm": 0.9094024896621704, "learning_rate": 1.6866137949706285e-06, "loss": 0.4653, "step": 3280 }, { "epoch": 3.6743838685586256, "grad_norm": 0.8985669016838074, "learning_rate": 1.685199876757628e-06, "loss": 0.466, "step": 3281 }, { "epoch": 3.6755041075429427, "grad_norm": 0.8878425359725952, "learning_rate": 1.683786250086799e-06, "loss": 0.4593, "step": 3282 }, { "epoch": 3.6766243465272592, "grad_norm": 0.8862296342849731, "learning_rate": 1.6823729154639486e-06, "loss": 0.4594, "step": 3283 }, { "epoch": 3.677744585511576, "grad_norm": 0.8758686184883118, "learning_rate": 1.6809598733947789e-06, "loss": 0.4721, "step": 3284 }, { "epoch": 3.6788648244958924, "grad_norm": 0.8797963261604309, "learning_rate": 1.6795471243848884e-06, "loss": 0.4772, "step": 3285 }, { "epoch": 3.679985063480209, "grad_norm": 0.9134855270385742, "learning_rate": 1.6781346689397704e-06, "loss": 0.482, "step": 3286 }, { "epoch": 3.681105302464526, "grad_norm": 0.8983044624328613, "learning_rate": 1.6767225075648126e-06, "loss": 0.4725, "step": 3287 }, { "epoch": 3.6822255414488425, "grad_norm": 0.9092017412185669, "learning_rate": 1.675310640765298e-06, "loss": 0.4583, "step": 3288 }, { "epoch": 3.683345780433159, "grad_norm": 1.002763032913208, "learning_rate": 1.6738990690464046e-06, "loss": 0.4853, "step": 3289 }, { "epoch": 3.6844660194174756, "grad_norm": 0.9299412965774536, "learning_rate": 1.6724877929132032e-06, "loss": 0.4922, "step": 3290 }, { "epoch": 3.685586258401792, "grad_norm": 0.9284866452217102, "learning_rate": 1.671076812870661e-06, "loss": 0.4794, "step": 3291 }, { "epoch": 3.6867064973861092, "grad_norm": 0.9005563259124756, "learning_rate": 1.6696661294236388e-06, "loss": 0.4857, "step": 3292 }, { "epoch": 3.687826736370426, "grad_norm": 0.9378336668014526, "learning_rate": 1.66825574307689e-06, "loss": 0.47, "step": 3293 }, { "epoch": 3.6889469753547424, "grad_norm": 0.8827153444290161, "learning_rate": 1.666845654335062e-06, "loss": 0.4712, "step": 3294 }, { "epoch": 3.690067214339059, "grad_norm": 0.9103701710700989, "learning_rate": 1.6654358637026968e-06, "loss": 0.4654, "step": 3295 }, { "epoch": 3.6911874533233755, "grad_norm": 0.9104571342468262, "learning_rate": 1.6640263716842287e-06, "loss": 0.4649, "step": 3296 }, { "epoch": 3.6923076923076925, "grad_norm": 0.8829075694084167, "learning_rate": 1.6626171787839851e-06, "loss": 0.4617, "step": 3297 }, { "epoch": 3.693427931292009, "grad_norm": 0.9021503329277039, "learning_rate": 1.661208285506188e-06, "loss": 0.4915, "step": 3298 }, { "epoch": 3.6945481702763256, "grad_norm": 0.8958818912506104, "learning_rate": 1.6597996923549501e-06, "loss": 0.4913, "step": 3299 }, { "epoch": 3.695668409260642, "grad_norm": 0.8727694749832153, "learning_rate": 1.6583913998342772e-06, "loss": 0.4637, "step": 3300 }, { "epoch": 3.696788648244959, "grad_norm": 0.95951247215271, "learning_rate": 1.6569834084480691e-06, "loss": 0.4849, "step": 3301 }, { "epoch": 3.697908887229276, "grad_norm": 0.901313304901123, "learning_rate": 1.6555757187001158e-06, "loss": 0.4665, "step": 3302 }, { "epoch": 3.6990291262135924, "grad_norm": 0.8836582899093628, "learning_rate": 1.6541683310940996e-06, "loss": 0.4771, "step": 3303 }, { "epoch": 3.700149365197909, "grad_norm": 0.901357889175415, "learning_rate": 1.6527612461335965e-06, "loss": 0.4836, "step": 3304 }, { "epoch": 3.7012696041822255, "grad_norm": 0.9042583703994751, "learning_rate": 1.6513544643220737e-06, "loss": 0.4696, "step": 3305 }, { "epoch": 3.702389843166542, "grad_norm": 0.8670619130134583, "learning_rate": 1.649947986162888e-06, "loss": 0.4592, "step": 3306 }, { "epoch": 3.703510082150859, "grad_norm": 0.8825319409370422, "learning_rate": 1.6485418121592892e-06, "loss": 0.4765, "step": 3307 }, { "epoch": 3.7046303211351757, "grad_norm": 0.8816661834716797, "learning_rate": 1.6471359428144173e-06, "loss": 0.4733, "step": 3308 }, { "epoch": 3.705750560119492, "grad_norm": 0.9009128212928772, "learning_rate": 1.645730378631305e-06, "loss": 0.46, "step": 3309 }, { "epoch": 3.706870799103809, "grad_norm": 0.8889232277870178, "learning_rate": 1.644325120112874e-06, "loss": 0.4564, "step": 3310 }, { "epoch": 3.7079910380881254, "grad_norm": 0.869437038898468, "learning_rate": 1.6429201677619372e-06, "loss": 0.4667, "step": 3311 }, { "epoch": 3.7091112770724424, "grad_norm": 0.8959628939628601, "learning_rate": 1.641515522081199e-06, "loss": 0.4451, "step": 3312 }, { "epoch": 3.710231516056759, "grad_norm": 0.8937593102455139, "learning_rate": 1.6401111835732524e-06, "loss": 0.4624, "step": 3313 }, { "epoch": 3.7113517550410755, "grad_norm": 0.9148236513137817, "learning_rate": 1.6387071527405806e-06, "loss": 0.4567, "step": 3314 }, { "epoch": 3.712471994025392, "grad_norm": 0.9085429310798645, "learning_rate": 1.637303430085559e-06, "loss": 0.4847, "step": 3315 }, { "epoch": 3.7135922330097086, "grad_norm": 0.8844471573829651, "learning_rate": 1.6359000161104498e-06, "loss": 0.4926, "step": 3316 }, { "epoch": 3.7147124719940257, "grad_norm": 0.910338819026947, "learning_rate": 1.6344969113174058e-06, "loss": 0.4351, "step": 3317 }, { "epoch": 3.715832710978342, "grad_norm": 0.9512890577316284, "learning_rate": 1.6330941162084702e-06, "loss": 0.4697, "step": 3318 }, { "epoch": 3.716952949962659, "grad_norm": 0.927314043045044, "learning_rate": 1.6316916312855753e-06, "loss": 0.5053, "step": 3319 }, { "epoch": 3.7180731889469754, "grad_norm": 0.891511857509613, "learning_rate": 1.6302894570505406e-06, "loss": 0.4511, "step": 3320 }, { "epoch": 3.719193427931292, "grad_norm": 0.9140861630439758, "learning_rate": 1.6288875940050753e-06, "loss": 0.4576, "step": 3321 }, { "epoch": 3.7203136669156085, "grad_norm": 0.9085286259651184, "learning_rate": 1.6274860426507789e-06, "loss": 0.4582, "step": 3322 }, { "epoch": 3.721433905899925, "grad_norm": 0.9226665496826172, "learning_rate": 1.6260848034891366e-06, "loss": 0.4743, "step": 3323 }, { "epoch": 3.722554144884242, "grad_norm": 0.9061741828918457, "learning_rate": 1.6246838770215235e-06, "loss": 0.4663, "step": 3324 }, { "epoch": 3.7236743838685586, "grad_norm": 0.9356991648674011, "learning_rate": 1.6232832637492033e-06, "loss": 0.488, "step": 3325 }, { "epoch": 3.724794622852875, "grad_norm": 0.8829746842384338, "learning_rate": 1.6218829641733264e-06, "loss": 0.4564, "step": 3326 }, { "epoch": 3.725914861837192, "grad_norm": 0.8925449252128601, "learning_rate": 1.6204829787949312e-06, "loss": 0.4727, "step": 3327 }, { "epoch": 3.7270351008215084, "grad_norm": 0.8988202214241028, "learning_rate": 1.6190833081149448e-06, "loss": 0.4608, "step": 3328 }, { "epoch": 3.7281553398058254, "grad_norm": 0.9299589991569519, "learning_rate": 1.6176839526341804e-06, "loss": 0.4434, "step": 3329 }, { "epoch": 3.729275578790142, "grad_norm": 0.9376687407493591, "learning_rate": 1.6162849128533376e-06, "loss": 0.4777, "step": 3330 }, { "epoch": 3.7303958177744585, "grad_norm": 0.9198883175849915, "learning_rate": 1.614886189273006e-06, "loss": 0.4913, "step": 3331 }, { "epoch": 3.731516056758775, "grad_norm": 0.8843048214912415, "learning_rate": 1.613487782393661e-06, "loss": 0.456, "step": 3332 }, { "epoch": 3.7326362957430916, "grad_norm": 0.895012378692627, "learning_rate": 1.6120896927156627e-06, "loss": 0.4548, "step": 3333 }, { "epoch": 3.7337565347274086, "grad_norm": 0.9009767174720764, "learning_rate": 1.6106919207392586e-06, "loss": 0.4617, "step": 3334 }, { "epoch": 3.734876773711725, "grad_norm": 0.8903946876525879, "learning_rate": 1.6092944669645846e-06, "loss": 0.486, "step": 3335 }, { "epoch": 3.735997012696042, "grad_norm": 0.9117555618286133, "learning_rate": 1.6078973318916602e-06, "loss": 0.4798, "step": 3336 }, { "epoch": 3.7371172516803584, "grad_norm": 0.9027389287948608, "learning_rate": 1.6065005160203912e-06, "loss": 0.4731, "step": 3337 }, { "epoch": 3.738237490664675, "grad_norm": 0.9052563905715942, "learning_rate": 1.605104019850571e-06, "loss": 0.4739, "step": 3338 }, { "epoch": 3.739357729648992, "grad_norm": 0.904424250125885, "learning_rate": 1.603707843881877e-06, "loss": 0.4811, "step": 3339 }, { "epoch": 3.7404779686333085, "grad_norm": 0.9013927578926086, "learning_rate": 1.6023119886138716e-06, "loss": 0.482, "step": 3340 }, { "epoch": 3.741598207617625, "grad_norm": 0.9108819365501404, "learning_rate": 1.6009164545460044e-06, "loss": 0.474, "step": 3341 }, { "epoch": 3.7427184466019416, "grad_norm": 0.9179173111915588, "learning_rate": 1.5995212421776085e-06, "loss": 0.4734, "step": 3342 }, { "epoch": 3.743838685586258, "grad_norm": 0.925796627998352, "learning_rate": 1.5981263520079012e-06, "loss": 0.4681, "step": 3343 }, { "epoch": 3.744958924570575, "grad_norm": 0.8939782381057739, "learning_rate": 1.596731784535988e-06, "loss": 0.4523, "step": 3344 }, { "epoch": 3.746079163554892, "grad_norm": 0.9250951409339905, "learning_rate": 1.5953375402608548e-06, "loss": 0.4967, "step": 3345 }, { "epoch": 3.7471994025392084, "grad_norm": 0.871511697769165, "learning_rate": 1.5939436196813745e-06, "loss": 0.4586, "step": 3346 }, { "epoch": 3.748319641523525, "grad_norm": 0.910102128982544, "learning_rate": 1.5925500232963032e-06, "loss": 0.4646, "step": 3347 }, { "epoch": 3.7494398805078415, "grad_norm": 0.9197672605514526, "learning_rate": 1.5911567516042803e-06, "loss": 0.4895, "step": 3348 }, { "epoch": 3.7505601194921585, "grad_norm": 0.9209261536598206, "learning_rate": 1.589763805103831e-06, "loss": 0.4805, "step": 3349 }, { "epoch": 3.751680358476475, "grad_norm": 0.8977606296539307, "learning_rate": 1.5883711842933624e-06, "loss": 0.4675, "step": 3350 }, { "epoch": 3.7528005974607916, "grad_norm": 0.8971313238143921, "learning_rate": 1.5869788896711658e-06, "loss": 0.4811, "step": 3351 }, { "epoch": 3.753920836445108, "grad_norm": 0.931506335735321, "learning_rate": 1.5855869217354152e-06, "loss": 0.4757, "step": 3352 }, { "epoch": 3.755041075429425, "grad_norm": 0.9125519394874573, "learning_rate": 1.584195280984169e-06, "loss": 0.4795, "step": 3353 }, { "epoch": 3.756161314413742, "grad_norm": 0.9238584637641907, "learning_rate": 1.5828039679153667e-06, "loss": 0.4723, "step": 3354 }, { "epoch": 3.7572815533980584, "grad_norm": 1.0215137004852295, "learning_rate": 1.5814129830268327e-06, "loss": 0.4511, "step": 3355 }, { "epoch": 3.758401792382375, "grad_norm": 0.9007453918457031, "learning_rate": 1.5800223268162706e-06, "loss": 0.4846, "step": 3356 }, { "epoch": 3.7595220313666915, "grad_norm": 0.9050899147987366, "learning_rate": 1.5786319997812716e-06, "loss": 0.4622, "step": 3357 }, { "epoch": 3.760642270351008, "grad_norm": 0.9194679260253906, "learning_rate": 1.5772420024193038e-06, "loss": 0.4911, "step": 3358 }, { "epoch": 3.761762509335325, "grad_norm": 0.8904063701629639, "learning_rate": 1.5758523352277214e-06, "loss": 0.4654, "step": 3359 }, { "epoch": 3.7628827483196416, "grad_norm": 0.9330847263336182, "learning_rate": 1.5744629987037577e-06, "loss": 0.481, "step": 3360 }, { "epoch": 3.764002987303958, "grad_norm": 0.9033405184745789, "learning_rate": 1.5730739933445283e-06, "loss": 0.4695, "step": 3361 }, { "epoch": 3.765123226288275, "grad_norm": 0.9201274514198303, "learning_rate": 1.5716853196470319e-06, "loss": 0.4633, "step": 3362 }, { "epoch": 3.7662434652725914, "grad_norm": 0.9015469551086426, "learning_rate": 1.5702969781081467e-06, "loss": 0.4705, "step": 3363 }, { "epoch": 3.7673637042569084, "grad_norm": 0.8688425421714783, "learning_rate": 1.5689089692246322e-06, "loss": 0.4296, "step": 3364 }, { "epoch": 3.768483943241225, "grad_norm": 0.9178756475448608, "learning_rate": 1.5675212934931306e-06, "loss": 0.4831, "step": 3365 }, { "epoch": 3.7696041822255415, "grad_norm": 0.9014667868614197, "learning_rate": 1.5661339514101625e-06, "loss": 0.4584, "step": 3366 }, { "epoch": 3.770724421209858, "grad_norm": 0.8752158284187317, "learning_rate": 1.5647469434721308e-06, "loss": 0.4583, "step": 3367 }, { "epoch": 3.7718446601941746, "grad_norm": 0.9407939314842224, "learning_rate": 1.5633602701753187e-06, "loss": 0.4802, "step": 3368 }, { "epoch": 3.7729648991784916, "grad_norm": 0.9154378175735474, "learning_rate": 1.5619739320158884e-06, "loss": 0.4735, "step": 3369 }, { "epoch": 3.774085138162808, "grad_norm": 0.9019193649291992, "learning_rate": 1.5605879294898829e-06, "loss": 0.473, "step": 3370 }, { "epoch": 3.775205377147125, "grad_norm": 0.9015824198722839, "learning_rate": 1.5592022630932269e-06, "loss": 0.4555, "step": 3371 }, { "epoch": 3.7763256161314414, "grad_norm": 0.9065137505531311, "learning_rate": 1.5578169333217214e-06, "loss": 0.4814, "step": 3372 }, { "epoch": 3.777445855115758, "grad_norm": 0.902228593826294, "learning_rate": 1.5564319406710505e-06, "loss": 0.464, "step": 3373 }, { "epoch": 3.778566094100075, "grad_norm": 0.9221042990684509, "learning_rate": 1.5550472856367748e-06, "loss": 0.4991, "step": 3374 }, { "epoch": 3.7796863330843915, "grad_norm": 0.912912905216217, "learning_rate": 1.553662968714335e-06, "loss": 0.4852, "step": 3375 }, { "epoch": 3.780806572068708, "grad_norm": 0.8913193941116333, "learning_rate": 1.552278990399052e-06, "loss": 0.4526, "step": 3376 }, { "epoch": 3.7819268110530246, "grad_norm": 0.920112669467926, "learning_rate": 1.550895351186124e-06, "loss": 0.4636, "step": 3377 }, { "epoch": 3.783047050037341, "grad_norm": 0.8809874653816223, "learning_rate": 1.5495120515706282e-06, "loss": 0.4659, "step": 3378 }, { "epoch": 3.784167289021658, "grad_norm": 0.9030345678329468, "learning_rate": 1.5481290920475214e-06, "loss": 0.4801, "step": 3379 }, { "epoch": 3.7852875280059743, "grad_norm": 0.9057557582855225, "learning_rate": 1.5467464731116375e-06, "loss": 0.4787, "step": 3380 }, { "epoch": 3.7864077669902914, "grad_norm": 0.892302393913269, "learning_rate": 1.545364195257688e-06, "loss": 0.4522, "step": 3381 }, { "epoch": 3.787528005974608, "grad_norm": 0.921791672706604, "learning_rate": 1.543982258980265e-06, "loss": 0.4701, "step": 3382 }, { "epoch": 3.7886482449589245, "grad_norm": 0.9323793053627014, "learning_rate": 1.5426006647738342e-06, "loss": 0.4844, "step": 3383 }, { "epoch": 3.789768483943241, "grad_norm": 0.8722229599952698, "learning_rate": 1.541219413132744e-06, "loss": 0.4506, "step": 3384 }, { "epoch": 3.7908887229275576, "grad_norm": 0.8778660297393799, "learning_rate": 1.539838504551216e-06, "loss": 0.4713, "step": 3385 }, { "epoch": 3.7920089619118746, "grad_norm": 0.9058471322059631, "learning_rate": 1.5384579395233518e-06, "loss": 0.4713, "step": 3386 }, { "epoch": 3.793129200896191, "grad_norm": 0.9201521277427673, "learning_rate": 1.5370777185431278e-06, "loss": 0.47, "step": 3387 }, { "epoch": 3.794249439880508, "grad_norm": 0.8855250477790833, "learning_rate": 1.5356978421043983e-06, "loss": 0.4394, "step": 3388 }, { "epoch": 3.7953696788648243, "grad_norm": 0.9010716080665588, "learning_rate": 1.5343183107008952e-06, "loss": 0.4601, "step": 3389 }, { "epoch": 3.796489917849141, "grad_norm": 0.9014917016029358, "learning_rate": 1.532939124826226e-06, "loss": 0.4511, "step": 3390 }, { "epoch": 3.797610156833458, "grad_norm": 0.9095498919487, "learning_rate": 1.5315602849738742e-06, "loss": 0.4541, "step": 3391 }, { "epoch": 3.7987303958177745, "grad_norm": 0.8991059064865112, "learning_rate": 1.5301817916372005e-06, "loss": 0.4471, "step": 3392 }, { "epoch": 3.799850634802091, "grad_norm": 0.8911834955215454, "learning_rate": 1.5288036453094413e-06, "loss": 0.4532, "step": 3393 }, { "epoch": 3.8009708737864076, "grad_norm": 0.8832246661186218, "learning_rate": 1.5274258464837074e-06, "loss": 0.4646, "step": 3394 }, { "epoch": 3.802091112770724, "grad_norm": 0.8991692662239075, "learning_rate": 1.526048395652988e-06, "loss": 0.4638, "step": 3395 }, { "epoch": 3.803211351755041, "grad_norm": 0.9116536378860474, "learning_rate": 1.524671293310145e-06, "loss": 0.4971, "step": 3396 }, { "epoch": 3.804331590739358, "grad_norm": 0.9001349210739136, "learning_rate": 1.5232945399479187e-06, "loss": 0.4539, "step": 3397 }, { "epoch": 3.8054518297236744, "grad_norm": 0.9087321758270264, "learning_rate": 1.5219181360589219e-06, "loss": 0.463, "step": 3398 }, { "epoch": 3.806572068707991, "grad_norm": 0.9166393876075745, "learning_rate": 1.5205420821356427e-06, "loss": 0.4747, "step": 3399 }, { "epoch": 3.8076923076923075, "grad_norm": 0.9209263324737549, "learning_rate": 1.5191663786704448e-06, "loss": 0.4636, "step": 3400 }, { "epoch": 3.8088125466766245, "grad_norm": 0.9016203880310059, "learning_rate": 1.5177910261555664e-06, "loss": 0.4612, "step": 3401 }, { "epoch": 3.809932785660941, "grad_norm": 0.885080099105835, "learning_rate": 1.5164160250831196e-06, "loss": 0.438, "step": 3402 }, { "epoch": 3.8110530246452576, "grad_norm": 0.894392192363739, "learning_rate": 1.515041375945091e-06, "loss": 0.4706, "step": 3403 }, { "epoch": 3.812173263629574, "grad_norm": 0.8909797072410583, "learning_rate": 1.5136670792333422e-06, "loss": 0.464, "step": 3404 }, { "epoch": 3.8132935026138908, "grad_norm": 0.8697673678398132, "learning_rate": 1.5122931354396064e-06, "loss": 0.4447, "step": 3405 }, { "epoch": 3.814413741598208, "grad_norm": 0.9129351377487183, "learning_rate": 1.5109195450554934e-06, "loss": 0.4547, "step": 3406 }, { "epoch": 3.8155339805825244, "grad_norm": 0.9057024717330933, "learning_rate": 1.5095463085724843e-06, "loss": 0.485, "step": 3407 }, { "epoch": 3.816654219566841, "grad_norm": 0.8840788006782532, "learning_rate": 1.5081734264819342e-06, "loss": 0.4622, "step": 3408 }, { "epoch": 3.8177744585511575, "grad_norm": 0.896449863910675, "learning_rate": 1.5068008992750726e-06, "loss": 0.4476, "step": 3409 }, { "epoch": 3.818894697535474, "grad_norm": 0.8917468786239624, "learning_rate": 1.5054287274429994e-06, "loss": 0.4645, "step": 3410 }, { "epoch": 3.820014936519791, "grad_norm": 0.8881056904792786, "learning_rate": 1.5040569114766907e-06, "loss": 0.4383, "step": 3411 }, { "epoch": 3.8211351755041076, "grad_norm": 0.9141792058944702, "learning_rate": 1.502685451866992e-06, "loss": 0.4842, "step": 3412 }, { "epoch": 3.822255414488424, "grad_norm": 0.9199451804161072, "learning_rate": 1.5013143491046244e-06, "loss": 0.4761, "step": 3413 }, { "epoch": 3.8233756534727408, "grad_norm": 0.89295494556427, "learning_rate": 1.4999436036801784e-06, "loss": 0.4845, "step": 3414 }, { "epoch": 3.8244958924570573, "grad_norm": 0.9150795340538025, "learning_rate": 1.4985732160841182e-06, "loss": 0.4801, "step": 3415 }, { "epoch": 3.8256161314413744, "grad_norm": 0.8761351704597473, "learning_rate": 1.4972031868067804e-06, "loss": 0.4731, "step": 3416 }, { "epoch": 3.826736370425691, "grad_norm": 0.8937829732894897, "learning_rate": 1.4958335163383718e-06, "loss": 0.47, "step": 3417 }, { "epoch": 3.8278566094100075, "grad_norm": 0.8716656565666199, "learning_rate": 1.4944642051689722e-06, "loss": 0.4516, "step": 3418 }, { "epoch": 3.828976848394324, "grad_norm": 0.917995035648346, "learning_rate": 1.493095253788533e-06, "loss": 0.4658, "step": 3419 }, { "epoch": 3.8300970873786406, "grad_norm": 0.9073067307472229, "learning_rate": 1.491726662686875e-06, "loss": 0.4845, "step": 3420 }, { "epoch": 3.8312173263629576, "grad_norm": 0.9018508195877075, "learning_rate": 1.4903584323536919e-06, "loss": 0.4785, "step": 3421 }, { "epoch": 3.832337565347274, "grad_norm": 0.9023922681808472, "learning_rate": 1.4889905632785479e-06, "loss": 0.4632, "step": 3422 }, { "epoch": 3.833457804331591, "grad_norm": 0.8838424682617188, "learning_rate": 1.4876230559508767e-06, "loss": 0.4642, "step": 3423 }, { "epoch": 3.8345780433159073, "grad_norm": 0.8987653851509094, "learning_rate": 1.4862559108599856e-06, "loss": 0.4487, "step": 3424 }, { "epoch": 3.835698282300224, "grad_norm": 0.8916930556297302, "learning_rate": 1.4848891284950496e-06, "loss": 0.4607, "step": 3425 }, { "epoch": 3.836818521284541, "grad_norm": 0.94614177942276, "learning_rate": 1.4835227093451132e-06, "loss": 0.4974, "step": 3426 }, { "epoch": 3.8379387602688575, "grad_norm": 0.8910417556762695, "learning_rate": 1.4821566538990945e-06, "loss": 0.4685, "step": 3427 }, { "epoch": 3.839058999253174, "grad_norm": 0.9020832180976868, "learning_rate": 1.4807909626457785e-06, "loss": 0.4858, "step": 3428 }, { "epoch": 3.8401792382374906, "grad_norm": 0.8823392391204834, "learning_rate": 1.47942563607382e-06, "loss": 0.4643, "step": 3429 }, { "epoch": 3.841299477221807, "grad_norm": 0.8938576579093933, "learning_rate": 1.4780606746717451e-06, "loss": 0.4697, "step": 3430 }, { "epoch": 3.842419716206124, "grad_norm": 0.9452274441719055, "learning_rate": 1.4766960789279478e-06, "loss": 0.4869, "step": 3431 }, { "epoch": 3.843539955190441, "grad_norm": 0.8961730003356934, "learning_rate": 1.475331849330691e-06, "loss": 0.4869, "step": 3432 }, { "epoch": 3.8446601941747574, "grad_norm": 0.8824231624603271, "learning_rate": 1.4739679863681086e-06, "loss": 0.4556, "step": 3433 }, { "epoch": 3.845780433159074, "grad_norm": 0.9020287394523621, "learning_rate": 1.4726044905282011e-06, "loss": 0.4742, "step": 3434 }, { "epoch": 3.8469006721433905, "grad_norm": 0.8761239051818848, "learning_rate": 1.4712413622988384e-06, "loss": 0.4797, "step": 3435 }, { "epoch": 3.8480209111277075, "grad_norm": 0.9189838767051697, "learning_rate": 1.4698786021677587e-06, "loss": 0.4677, "step": 3436 }, { "epoch": 3.8491411501120236, "grad_norm": 0.8911225199699402, "learning_rate": 1.4685162106225698e-06, "loss": 0.4659, "step": 3437 }, { "epoch": 3.8502613890963406, "grad_norm": 0.8852312564849854, "learning_rate": 1.4671541881507462e-06, "loss": 0.4781, "step": 3438 }, { "epoch": 3.851381628080657, "grad_norm": 0.879968523979187, "learning_rate": 1.4657925352396302e-06, "loss": 0.4609, "step": 3439 }, { "epoch": 3.8525018670649738, "grad_norm": 0.929130494594574, "learning_rate": 1.4644312523764335e-06, "loss": 0.459, "step": 3440 }, { "epoch": 3.853622106049291, "grad_norm": 0.8907116055488586, "learning_rate": 1.4630703400482332e-06, "loss": 0.4578, "step": 3441 }, { "epoch": 3.854742345033607, "grad_norm": 0.9034139513969421, "learning_rate": 1.461709798741975e-06, "loss": 0.4606, "step": 3442 }, { "epoch": 3.855862584017924, "grad_norm": 0.9136622548103333, "learning_rate": 1.4603496289444719e-06, "loss": 0.4529, "step": 3443 }, { "epoch": 3.8569828230022405, "grad_norm": 0.8809947371482849, "learning_rate": 1.4589898311424038e-06, "loss": 0.4597, "step": 3444 }, { "epoch": 3.858103061986557, "grad_norm": 0.9032948613166809, "learning_rate": 1.4576304058223183e-06, "loss": 0.4638, "step": 3445 }, { "epoch": 3.8592233009708736, "grad_norm": 0.9402764439582825, "learning_rate": 1.456271353470628e-06, "loss": 0.4953, "step": 3446 }, { "epoch": 3.86034353995519, "grad_norm": 0.9058883786201477, "learning_rate": 1.454912674573613e-06, "loss": 0.4424, "step": 3447 }, { "epoch": 3.861463778939507, "grad_norm": 0.9233123660087585, "learning_rate": 1.4535543696174204e-06, "loss": 0.4965, "step": 3448 }, { "epoch": 3.8625840179238238, "grad_norm": 0.8945460915565491, "learning_rate": 1.452196439088061e-06, "loss": 0.4841, "step": 3449 }, { "epoch": 3.8637042569081403, "grad_norm": 0.9097782373428345, "learning_rate": 1.4508388834714165e-06, "loss": 0.4704, "step": 3450 }, { "epoch": 3.864824495892457, "grad_norm": 0.8987748622894287, "learning_rate": 1.4494817032532286e-06, "loss": 0.4603, "step": 3451 }, { "epoch": 3.8659447348767735, "grad_norm": 0.9208267331123352, "learning_rate": 1.44812489891911e-06, "loss": 0.5029, "step": 3452 }, { "epoch": 3.8670649738610905, "grad_norm": 0.8936381936073303, "learning_rate": 1.4467684709545348e-06, "loss": 0.4481, "step": 3453 }, { "epoch": 3.868185212845407, "grad_norm": 0.9143824577331543, "learning_rate": 1.4454124198448446e-06, "loss": 0.4668, "step": 3454 }, { "epoch": 3.8693054518297236, "grad_norm": 0.8762713074684143, "learning_rate": 1.4440567460752456e-06, "loss": 0.4497, "step": 3455 }, { "epoch": 3.87042569081404, "grad_norm": 0.9315913915634155, "learning_rate": 1.442701450130809e-06, "loss": 0.49, "step": 3456 }, { "epoch": 3.8715459297983568, "grad_norm": 0.8811686635017395, "learning_rate": 1.4413465324964692e-06, "loss": 0.4728, "step": 3457 }, { "epoch": 3.872666168782674, "grad_norm": 0.918918788433075, "learning_rate": 1.43999199365703e-06, "loss": 0.4442, "step": 3458 }, { "epoch": 3.8737864077669903, "grad_norm": 0.9101260304450989, "learning_rate": 1.4386378340971546e-06, "loss": 0.4951, "step": 3459 }, { "epoch": 3.874906646751307, "grad_norm": 0.9045308232307434, "learning_rate": 1.4372840543013728e-06, "loss": 0.465, "step": 3460 }, { "epoch": 3.8760268857356235, "grad_norm": 0.9043325781822205, "learning_rate": 1.4359306547540778e-06, "loss": 0.4868, "step": 3461 }, { "epoch": 3.87714712471994, "grad_norm": 0.9358153939247131, "learning_rate": 1.4345776359395271e-06, "loss": 0.4773, "step": 3462 }, { "epoch": 3.878267363704257, "grad_norm": 0.9161513447761536, "learning_rate": 1.4332249983418415e-06, "loss": 0.485, "step": 3463 }, { "epoch": 3.8793876026885736, "grad_norm": 0.9038947224617004, "learning_rate": 1.4318727424450064e-06, "loss": 0.4563, "step": 3464 }, { "epoch": 3.88050784167289, "grad_norm": 0.8951383233070374, "learning_rate": 1.430520868732871e-06, "loss": 0.4534, "step": 3465 }, { "epoch": 3.8816280806572068, "grad_norm": 0.9098047614097595, "learning_rate": 1.4291693776891458e-06, "loss": 0.4767, "step": 3466 }, { "epoch": 3.8827483196415233, "grad_norm": 0.9180130958557129, "learning_rate": 1.4278182697974053e-06, "loss": 0.4873, "step": 3467 }, { "epoch": 3.8838685586258404, "grad_norm": 0.9029364585876465, "learning_rate": 1.4264675455410875e-06, "loss": 0.455, "step": 3468 }, { "epoch": 3.884988797610157, "grad_norm": 0.8893053531646729, "learning_rate": 1.4251172054034924e-06, "loss": 0.4665, "step": 3469 }, { "epoch": 3.8861090365944735, "grad_norm": 0.8858007192611694, "learning_rate": 1.4237672498677811e-06, "loss": 0.4344, "step": 3470 }, { "epoch": 3.88722927557879, "grad_norm": 0.9333658814430237, "learning_rate": 1.422417679416982e-06, "loss": 0.4707, "step": 3471 }, { "epoch": 3.8883495145631066, "grad_norm": 0.9197208881378174, "learning_rate": 1.4210684945339803e-06, "loss": 0.475, "step": 3472 }, { "epoch": 3.8894697535474236, "grad_norm": 0.8882938027381897, "learning_rate": 1.4197196957015264e-06, "loss": 0.4576, "step": 3473 }, { "epoch": 3.89058999253174, "grad_norm": 0.903858482837677, "learning_rate": 1.4183712834022311e-06, "loss": 0.4708, "step": 3474 }, { "epoch": 3.8917102315160568, "grad_norm": 0.901128351688385, "learning_rate": 1.4170232581185673e-06, "loss": 0.4742, "step": 3475 }, { "epoch": 3.8928304705003733, "grad_norm": 0.8577115535736084, "learning_rate": 1.4156756203328686e-06, "loss": 0.4266, "step": 3476 }, { "epoch": 3.89395070948469, "grad_norm": 0.8734918832778931, "learning_rate": 1.414328370527333e-06, "loss": 0.4655, "step": 3477 }, { "epoch": 3.895070948469007, "grad_norm": 0.9189875721931458, "learning_rate": 1.4129815091840154e-06, "loss": 0.4721, "step": 3478 }, { "epoch": 3.8961911874533235, "grad_norm": 0.910969078540802, "learning_rate": 1.4116350367848357e-06, "loss": 0.4594, "step": 3479 }, { "epoch": 3.89731142643764, "grad_norm": 0.9062607288360596, "learning_rate": 1.4102889538115725e-06, "loss": 0.4722, "step": 3480 }, { "epoch": 3.8984316654219566, "grad_norm": 0.9278868436813354, "learning_rate": 1.4089432607458642e-06, "loss": 0.4818, "step": 3481 }, { "epoch": 3.899551904406273, "grad_norm": 0.9017317295074463, "learning_rate": 1.4075979580692118e-06, "loss": 0.4632, "step": 3482 }, { "epoch": 3.90067214339059, "grad_norm": 0.963753342628479, "learning_rate": 1.4062530462629753e-06, "loss": 0.4882, "step": 3483 }, { "epoch": 3.9017923823749068, "grad_norm": 0.918830931186676, "learning_rate": 1.404908525808374e-06, "loss": 0.4915, "step": 3484 }, { "epoch": 3.9029126213592233, "grad_norm": 0.9178673028945923, "learning_rate": 1.4035643971864903e-06, "loss": 0.4621, "step": 3485 }, { "epoch": 3.90403286034354, "grad_norm": 0.9238674640655518, "learning_rate": 1.402220660878264e-06, "loss": 0.5035, "step": 3486 }, { "epoch": 3.9051530993278565, "grad_norm": 0.8964166045188904, "learning_rate": 1.4008773173644944e-06, "loss": 0.4787, "step": 3487 }, { "epoch": 3.9062733383121735, "grad_norm": 0.9137935042381287, "learning_rate": 1.399534367125841e-06, "loss": 0.4776, "step": 3488 }, { "epoch": 3.90739357729649, "grad_norm": 0.9461027383804321, "learning_rate": 1.3981918106428215e-06, "loss": 0.4911, "step": 3489 }, { "epoch": 3.9085138162808066, "grad_norm": 0.9301370978355408, "learning_rate": 1.396849648395816e-06, "loss": 0.4981, "step": 3490 }, { "epoch": 3.909634055265123, "grad_norm": 0.9024360775947571, "learning_rate": 1.3955078808650585e-06, "loss": 0.4391, "step": 3491 }, { "epoch": 3.9107542942494398, "grad_norm": 0.8852247595787048, "learning_rate": 1.3941665085306466e-06, "loss": 0.4629, "step": 3492 }, { "epoch": 3.911874533233757, "grad_norm": 0.9008305668830872, "learning_rate": 1.3928255318725333e-06, "loss": 0.4557, "step": 3493 }, { "epoch": 3.9129947722180733, "grad_norm": 0.9083086252212524, "learning_rate": 1.3914849513705315e-06, "loss": 0.4663, "step": 3494 }, { "epoch": 3.91411501120239, "grad_norm": 0.9011377692222595, "learning_rate": 1.3901447675043117e-06, "loss": 0.4919, "step": 3495 }, { "epoch": 3.9152352501867065, "grad_norm": 0.8639941811561584, "learning_rate": 1.3888049807534021e-06, "loss": 0.4472, "step": 3496 }, { "epoch": 3.916355489171023, "grad_norm": 0.8973985910415649, "learning_rate": 1.387465591597189e-06, "loss": 0.4753, "step": 3497 }, { "epoch": 3.91747572815534, "grad_norm": 0.889623761177063, "learning_rate": 1.386126600514919e-06, "loss": 0.466, "step": 3498 }, { "epoch": 3.918595967139656, "grad_norm": 0.916378915309906, "learning_rate": 1.384788007985693e-06, "loss": 0.4827, "step": 3499 }, { "epoch": 3.919716206123973, "grad_norm": 0.9230771660804749, "learning_rate": 1.3834498144884695e-06, "loss": 0.4835, "step": 3500 }, { "epoch": 3.9208364451082898, "grad_norm": 0.9227744340896606, "learning_rate": 1.3821120205020663e-06, "loss": 0.4838, "step": 3501 }, { "epoch": 3.9219566840926063, "grad_norm": 0.9027947783470154, "learning_rate": 1.3807746265051553e-06, "loss": 0.4736, "step": 3502 }, { "epoch": 3.9230769230769234, "grad_norm": 0.9238545894622803, "learning_rate": 1.3794376329762696e-06, "loss": 0.4818, "step": 3503 }, { "epoch": 3.9241971620612395, "grad_norm": 0.9200093150138855, "learning_rate": 1.378101040393795e-06, "loss": 0.4913, "step": 3504 }, { "epoch": 3.9253174010455565, "grad_norm": 0.8996438384056091, "learning_rate": 1.3767648492359747e-06, "loss": 0.475, "step": 3505 }, { "epoch": 3.926437640029873, "grad_norm": 0.9447228312492371, "learning_rate": 1.3754290599809106e-06, "loss": 0.4824, "step": 3506 }, { "epoch": 3.9275578790141896, "grad_norm": 0.8953820466995239, "learning_rate": 1.374093673106558e-06, "loss": 0.4523, "step": 3507 }, { "epoch": 3.928678117998506, "grad_norm": 0.8935534954071045, "learning_rate": 1.372758689090729e-06, "loss": 0.4807, "step": 3508 }, { "epoch": 3.9297983569828228, "grad_norm": 0.8744407892227173, "learning_rate": 1.371424108411093e-06, "loss": 0.4564, "step": 3509 }, { "epoch": 3.9309185959671398, "grad_norm": 0.8906152844429016, "learning_rate": 1.3700899315451727e-06, "loss": 0.4894, "step": 3510 }, { "epoch": 3.9320388349514563, "grad_norm": 0.9047491550445557, "learning_rate": 1.3687561589703469e-06, "loss": 0.4815, "step": 3511 }, { "epoch": 3.933159073935773, "grad_norm": 0.9147272706031799, "learning_rate": 1.3674227911638526e-06, "loss": 0.4746, "step": 3512 }, { "epoch": 3.9342793129200895, "grad_norm": 0.9071229100227356, "learning_rate": 1.3660898286027786e-06, "loss": 0.4829, "step": 3513 }, { "epoch": 3.935399551904406, "grad_norm": 0.9311023354530334, "learning_rate": 1.3647572717640694e-06, "loss": 0.4801, "step": 3514 }, { "epoch": 3.936519790888723, "grad_norm": 0.920232892036438, "learning_rate": 1.3634251211245258e-06, "loss": 0.4601, "step": 3515 }, { "epoch": 3.9376400298730396, "grad_norm": 0.9136541485786438, "learning_rate": 1.3620933771608006e-06, "loss": 0.4739, "step": 3516 }, { "epoch": 3.938760268857356, "grad_norm": 0.8781163692474365, "learning_rate": 1.3607620403494044e-06, "loss": 0.4527, "step": 3517 }, { "epoch": 3.9398805078416728, "grad_norm": 0.9001836776733398, "learning_rate": 1.3594311111666992e-06, "loss": 0.4858, "step": 3518 }, { "epoch": 3.9410007468259893, "grad_norm": 0.9158074259757996, "learning_rate": 1.358100590088904e-06, "loss": 0.4579, "step": 3519 }, { "epoch": 3.9421209858103063, "grad_norm": 0.8895012140274048, "learning_rate": 1.3567704775920888e-06, "loss": 0.4727, "step": 3520 }, { "epoch": 3.943241224794623, "grad_norm": 0.9152185916900635, "learning_rate": 1.355440774152179e-06, "loss": 0.4619, "step": 3521 }, { "epoch": 3.9443614637789395, "grad_norm": 0.8864225745201111, "learning_rate": 1.354111480244954e-06, "loss": 0.4749, "step": 3522 }, { "epoch": 3.945481702763256, "grad_norm": 0.9478031396865845, "learning_rate": 1.3527825963460451e-06, "loss": 0.4841, "step": 3523 }, { "epoch": 3.9466019417475726, "grad_norm": 0.9268874526023865, "learning_rate": 1.3514541229309374e-06, "loss": 0.4623, "step": 3524 }, { "epoch": 3.9477221807318896, "grad_norm": 0.8927562832832336, "learning_rate": 1.350126060474972e-06, "loss": 0.4674, "step": 3525 }, { "epoch": 3.948842419716206, "grad_norm": 0.9160478711128235, "learning_rate": 1.3487984094533388e-06, "loss": 0.4731, "step": 3526 }, { "epoch": 3.9499626587005228, "grad_norm": 0.9029799103736877, "learning_rate": 1.3474711703410826e-06, "loss": 0.4528, "step": 3527 }, { "epoch": 3.9510828976848393, "grad_norm": 0.887220025062561, "learning_rate": 1.3461443436131e-06, "loss": 0.5015, "step": 3528 }, { "epoch": 3.952203136669156, "grad_norm": 0.8787983059883118, "learning_rate": 1.3448179297441402e-06, "loss": 0.4516, "step": 3529 }, { "epoch": 3.953323375653473, "grad_norm": 0.9008063673973083, "learning_rate": 1.3434919292088067e-06, "loss": 0.4603, "step": 3530 }, { "epoch": 3.9544436146377895, "grad_norm": 0.9315685629844666, "learning_rate": 1.3421663424815521e-06, "loss": 0.4676, "step": 3531 }, { "epoch": 3.955563853622106, "grad_norm": 0.9085510969161987, "learning_rate": 1.3408411700366814e-06, "loss": 0.453, "step": 3532 }, { "epoch": 3.9566840926064226, "grad_norm": 0.9041222333908081, "learning_rate": 1.3395164123483545e-06, "loss": 0.4724, "step": 3533 }, { "epoch": 3.957804331590739, "grad_norm": 0.8786797523498535, "learning_rate": 1.3381920698905788e-06, "loss": 0.4564, "step": 3534 }, { "epoch": 3.958924570575056, "grad_norm": 0.8901869654655457, "learning_rate": 1.3368681431372155e-06, "loss": 0.4549, "step": 3535 }, { "epoch": 3.9600448095593728, "grad_norm": 0.900690495967865, "learning_rate": 1.3355446325619764e-06, "loss": 0.4574, "step": 3536 }, { "epoch": 3.9611650485436893, "grad_norm": 0.8661190867424011, "learning_rate": 1.3342215386384245e-06, "loss": 0.4479, "step": 3537 }, { "epoch": 3.962285287528006, "grad_norm": 0.9094800353050232, "learning_rate": 1.3328988618399725e-06, "loss": 0.4525, "step": 3538 }, { "epoch": 3.9634055265123225, "grad_norm": 0.9223583936691284, "learning_rate": 1.331576602639887e-06, "loss": 0.4806, "step": 3539 }, { "epoch": 3.9645257654966395, "grad_norm": 0.9426891207695007, "learning_rate": 1.3302547615112821e-06, "loss": 0.4942, "step": 3540 }, { "epoch": 3.965646004480956, "grad_norm": 0.9248896241188049, "learning_rate": 1.3289333389271234e-06, "loss": 0.466, "step": 3541 }, { "epoch": 3.9667662434652726, "grad_norm": 0.9748967885971069, "learning_rate": 1.3276123353602261e-06, "loss": 0.4732, "step": 3542 }, { "epoch": 3.967886482449589, "grad_norm": 0.9092918634414673, "learning_rate": 1.326291751283258e-06, "loss": 0.4655, "step": 3543 }, { "epoch": 3.9690067214339058, "grad_norm": 0.9003869891166687, "learning_rate": 1.3249715871687336e-06, "loss": 0.4864, "step": 3544 }, { "epoch": 3.9701269604182228, "grad_norm": 0.8948836326599121, "learning_rate": 1.3236518434890178e-06, "loss": 0.4579, "step": 3545 }, { "epoch": 3.9712471994025393, "grad_norm": 0.8993564248085022, "learning_rate": 1.3223325207163273e-06, "loss": 0.462, "step": 3546 }, { "epoch": 3.972367438386856, "grad_norm": 0.9424558281898499, "learning_rate": 1.3210136193227262e-06, "loss": 0.4914, "step": 3547 }, { "epoch": 3.9734876773711725, "grad_norm": 0.8877697587013245, "learning_rate": 1.3196951397801278e-06, "loss": 0.4575, "step": 3548 }, { "epoch": 3.974607916355489, "grad_norm": 0.879502534866333, "learning_rate": 1.3183770825602954e-06, "loss": 0.4568, "step": 3549 }, { "epoch": 3.975728155339806, "grad_norm": 0.8967670202255249, "learning_rate": 1.31705944813484e-06, "loss": 0.4621, "step": 3550 }, { "epoch": 3.9768483943241226, "grad_norm": 0.9067457318305969, "learning_rate": 1.3157422369752215e-06, "loss": 0.4778, "step": 3551 }, { "epoch": 3.977968633308439, "grad_norm": 0.8908153176307678, "learning_rate": 1.3144254495527508e-06, "loss": 0.453, "step": 3552 }, { "epoch": 3.9790888722927558, "grad_norm": 0.9123955965042114, "learning_rate": 1.313109086338584e-06, "loss": 0.4746, "step": 3553 }, { "epoch": 3.9802091112770723, "grad_norm": 0.8924744725227356, "learning_rate": 1.3117931478037268e-06, "loss": 0.4494, "step": 3554 }, { "epoch": 3.9813293502613893, "grad_norm": 0.928989589214325, "learning_rate": 1.310477634419032e-06, "loss": 0.4773, "step": 3555 }, { "epoch": 3.982449589245706, "grad_norm": 0.9342179894447327, "learning_rate": 1.3091625466552026e-06, "loss": 0.4762, "step": 3556 }, { "epoch": 3.9835698282300225, "grad_norm": 0.903562605381012, "learning_rate": 1.3078478849827874e-06, "loss": 0.4667, "step": 3557 }, { "epoch": 3.984690067214339, "grad_norm": 0.9246814846992493, "learning_rate": 1.306533649872182e-06, "loss": 0.4627, "step": 3558 }, { "epoch": 3.9858103061986556, "grad_norm": 0.8697022199630737, "learning_rate": 1.305219841793632e-06, "loss": 0.4387, "step": 3559 }, { "epoch": 3.9869305451829726, "grad_norm": 0.8937549591064453, "learning_rate": 1.3039064612172283e-06, "loss": 0.484, "step": 3560 }, { "epoch": 3.9880507841672888, "grad_norm": 0.8901099562644958, "learning_rate": 1.3025935086129088e-06, "loss": 0.4751, "step": 3561 }, { "epoch": 3.9891710231516058, "grad_norm": 0.9084734320640564, "learning_rate": 1.3012809844504593e-06, "loss": 0.4791, "step": 3562 }, { "epoch": 3.9902912621359223, "grad_norm": 0.905987560749054, "learning_rate": 1.299968889199511e-06, "loss": 0.474, "step": 3563 }, { "epoch": 3.991411501120239, "grad_norm": 0.9215884804725647, "learning_rate": 1.298657223329543e-06, "loss": 0.4715, "step": 3564 }, { "epoch": 3.992531740104556, "grad_norm": 0.9081942439079285, "learning_rate": 1.2973459873098786e-06, "loss": 0.4728, "step": 3565 }, { "epoch": 3.993651979088872, "grad_norm": 0.9407914280891418, "learning_rate": 1.2960351816096911e-06, "loss": 0.4847, "step": 3566 }, { "epoch": 3.994772218073189, "grad_norm": 0.9335135221481323, "learning_rate": 1.2947248066979965e-06, "loss": 0.4819, "step": 3567 }, { "epoch": 3.9958924570575056, "grad_norm": 0.911342978477478, "learning_rate": 1.2934148630436578e-06, "loss": 0.4668, "step": 3568 }, { "epoch": 3.997012696041822, "grad_norm": 0.9433068037033081, "learning_rate": 1.2921053511153819e-06, "loss": 0.4913, "step": 3569 }, { "epoch": 3.9981329350261388, "grad_norm": 0.8788852095603943, "learning_rate": 1.290796271381726e-06, "loss": 0.4405, "step": 3570 }, { "epoch": 3.9992531740104553, "grad_norm": 0.8904021382331848, "learning_rate": 1.2894876243110876e-06, "loss": 0.4473, "step": 3571 }, { "epoch": 4.0, "grad_norm": 0.8904021382331848, "learning_rate": 1.2881794103717114e-06, "loss": 0.4444, "step": 3572 }, { "epoch": 4.001120238984317, "grad_norm": 1.2932510375976562, "learning_rate": 1.286871630031688e-06, "loss": 0.4353, "step": 3573 }, { "epoch": 4.002240477968633, "grad_norm": 0.8597673177719116, "learning_rate": 1.2855642837589516e-06, "loss": 0.4588, "step": 3574 }, { "epoch": 4.00336071695295, "grad_norm": 0.8825937509536743, "learning_rate": 1.2842573720212812e-06, "loss": 0.4557, "step": 3575 }, { "epoch": 4.004480955937266, "grad_norm": 0.9078790545463562, "learning_rate": 1.2829508952863006e-06, "loss": 0.4531, "step": 3576 }, { "epoch": 4.005601194921583, "grad_norm": 0.8729336261749268, "learning_rate": 1.2816448540214776e-06, "loss": 0.4313, "step": 3577 }, { "epoch": 4.0067214339059, "grad_norm": 0.8841822147369385, "learning_rate": 1.2803392486941243e-06, "loss": 0.4638, "step": 3578 }, { "epoch": 4.007841672890216, "grad_norm": 0.908047616481781, "learning_rate": 1.2790340797713982e-06, "loss": 0.4592, "step": 3579 }, { "epoch": 4.008961911874533, "grad_norm": 0.8804596662521362, "learning_rate": 1.277729347720299e-06, "loss": 0.4392, "step": 3580 }, { "epoch": 4.01008215085885, "grad_norm": 0.8957237005233765, "learning_rate": 1.27642505300767e-06, "loss": 0.4427, "step": 3581 }, { "epoch": 4.011202389843167, "grad_norm": 0.9172232747077942, "learning_rate": 1.2751211961001977e-06, "loss": 0.4833, "step": 3582 }, { "epoch": 4.012322628827484, "grad_norm": 0.903330385684967, "learning_rate": 1.273817777464415e-06, "loss": 0.4757, "step": 3583 }, { "epoch": 4.0134428678118, "grad_norm": 0.9298878908157349, "learning_rate": 1.2725147975666948e-06, "loss": 0.4517, "step": 3584 }, { "epoch": 4.014563106796117, "grad_norm": 0.9192859530448914, "learning_rate": 1.2712122568732528e-06, "loss": 0.4364, "step": 3585 }, { "epoch": 4.015683345780433, "grad_norm": 0.9160456657409668, "learning_rate": 1.269910155850151e-06, "loss": 0.4556, "step": 3586 }, { "epoch": 4.01680358476475, "grad_norm": 0.9060468077659607, "learning_rate": 1.2686084949632907e-06, "loss": 0.4344, "step": 3587 }, { "epoch": 4.017923823749067, "grad_norm": 0.9058763980865479, "learning_rate": 1.267307274678417e-06, "loss": 0.4775, "step": 3588 }, { "epoch": 4.019044062733383, "grad_norm": 0.9462049007415771, "learning_rate": 1.2660064954611165e-06, "loss": 0.471, "step": 3589 }, { "epoch": 4.0201643017177, "grad_norm": 0.9348622560501099, "learning_rate": 1.2647061577768194e-06, "loss": 0.4675, "step": 3590 }, { "epoch": 4.021284540702016, "grad_norm": 0.9133985638618469, "learning_rate": 1.2634062620907961e-06, "loss": 0.453, "step": 3591 }, { "epoch": 4.022404779686333, "grad_norm": 0.9197320342063904, "learning_rate": 1.262106808868162e-06, "loss": 0.4477, "step": 3592 }, { "epoch": 4.02352501867065, "grad_norm": 0.8993807435035706, "learning_rate": 1.260807798573871e-06, "loss": 0.4706, "step": 3593 }, { "epoch": 4.024645257654966, "grad_norm": 0.9324733018875122, "learning_rate": 1.2595092316727192e-06, "loss": 0.4715, "step": 3594 }, { "epoch": 4.025765496639283, "grad_norm": 0.9251439571380615, "learning_rate": 1.2582111086293441e-06, "loss": 0.4517, "step": 3595 }, { "epoch": 4.026885735623599, "grad_norm": 0.9102092981338501, "learning_rate": 1.2569134299082267e-06, "loss": 0.4544, "step": 3596 }, { "epoch": 4.028005974607916, "grad_norm": 0.9100639820098877, "learning_rate": 1.2556161959736858e-06, "loss": 0.4346, "step": 3597 }, { "epoch": 4.029126213592233, "grad_norm": 0.8728294372558594, "learning_rate": 1.2543194072898828e-06, "loss": 0.4477, "step": 3598 }, { "epoch": 4.03024645257655, "grad_norm": 0.9040402770042419, "learning_rate": 1.253023064320818e-06, "loss": 0.4487, "step": 3599 }, { "epoch": 4.031366691560867, "grad_norm": 0.9146487712860107, "learning_rate": 1.2517271675303356e-06, "loss": 0.4244, "step": 3600 }, { "epoch": 4.032486930545183, "grad_norm": 0.8769164085388184, "learning_rate": 1.250431717382117e-06, "loss": 0.4903, "step": 3601 }, { "epoch": 4.0336071695295, "grad_norm": 0.9113534688949585, "learning_rate": 1.2491367143396852e-06, "loss": 0.4553, "step": 3602 }, { "epoch": 4.034727408513817, "grad_norm": 0.9175356030464172, "learning_rate": 1.2478421588664027e-06, "loss": 0.4524, "step": 3603 }, { "epoch": 4.035847647498133, "grad_norm": 0.9189466834068298, "learning_rate": 1.246548051425472e-06, "loss": 0.4475, "step": 3604 }, { "epoch": 4.03696788648245, "grad_norm": 0.9085381031036377, "learning_rate": 1.2452543924799345e-06, "loss": 0.4518, "step": 3605 }, { "epoch": 4.038088125466766, "grad_norm": 0.897274374961853, "learning_rate": 1.2439611824926743e-06, "loss": 0.4401, "step": 3606 }, { "epoch": 4.039208364451083, "grad_norm": 0.9095062017440796, "learning_rate": 1.2426684219264106e-06, "loss": 0.4521, "step": 3607 }, { "epoch": 4.040328603435399, "grad_norm": 0.9386999011039734, "learning_rate": 1.241376111243704e-06, "loss": 0.4578, "step": 3608 }, { "epoch": 4.041448842419716, "grad_norm": 0.9363106489181519, "learning_rate": 1.2400842509069548e-06, "loss": 0.4596, "step": 3609 }, { "epoch": 4.042569081404033, "grad_norm": 0.8971771597862244, "learning_rate": 1.2387928413784008e-06, "loss": 0.4339, "step": 3610 }, { "epoch": 4.043689320388349, "grad_norm": 0.9222677946090698, "learning_rate": 1.2375018831201188e-06, "loss": 0.4476, "step": 3611 }, { "epoch": 4.044809559372666, "grad_norm": 0.8853550553321838, "learning_rate": 1.236211376594023e-06, "loss": 0.4527, "step": 3612 }, { "epoch": 4.045929798356982, "grad_norm": 0.9007314443588257, "learning_rate": 1.23492132226187e-06, "loss": 0.4387, "step": 3613 }, { "epoch": 4.047050037341299, "grad_norm": 0.9386903643608093, "learning_rate": 1.23363172058525e-06, "loss": 0.4385, "step": 3614 }, { "epoch": 4.048170276325616, "grad_norm": 0.8983497023582458, "learning_rate": 1.2323425720255932e-06, "loss": 0.45, "step": 3615 }, { "epoch": 4.049290515309933, "grad_norm": 0.9090794324874878, "learning_rate": 1.2310538770441677e-06, "loss": 0.4717, "step": 3616 }, { "epoch": 4.05041075429425, "grad_norm": 0.9135292768478394, "learning_rate": 1.2297656361020793e-06, "loss": 0.4802, "step": 3617 }, { "epoch": 4.051530993278566, "grad_norm": 0.8979698419570923, "learning_rate": 1.22847784966027e-06, "loss": 0.4492, "step": 3618 }, { "epoch": 4.052651232262883, "grad_norm": 0.9281032085418701, "learning_rate": 1.2271905181795225e-06, "loss": 0.4486, "step": 3619 }, { "epoch": 4.0537714712472, "grad_norm": 0.9743282198905945, "learning_rate": 1.2259036421204532e-06, "loss": 0.4405, "step": 3620 }, { "epoch": 4.054891710231516, "grad_norm": 0.9085750579833984, "learning_rate": 1.224617221943517e-06, "loss": 0.4432, "step": 3621 }, { "epoch": 4.056011949215833, "grad_norm": 0.9023826718330383, "learning_rate": 1.2233312581090052e-06, "loss": 0.4596, "step": 3622 }, { "epoch": 4.057132188200149, "grad_norm": 0.9243226051330566, "learning_rate": 1.2220457510770476e-06, "loss": 0.4713, "step": 3623 }, { "epoch": 4.058252427184466, "grad_norm": 0.9206832647323608, "learning_rate": 1.2207607013076081e-06, "loss": 0.4492, "step": 3624 }, { "epoch": 4.059372666168783, "grad_norm": 0.9094645380973816, "learning_rate": 1.2194761092604884e-06, "loss": 0.4432, "step": 3625 }, { "epoch": 4.060492905153099, "grad_norm": 0.8890080451965332, "learning_rate": 1.2181919753953254e-06, "loss": 0.4453, "step": 3626 }, { "epoch": 4.061613144137416, "grad_norm": 0.9123840928077698, "learning_rate": 1.2169083001715936e-06, "loss": 0.4527, "step": 3627 }, { "epoch": 4.062733383121732, "grad_norm": 0.9011054039001465, "learning_rate": 1.2156250840486027e-06, "loss": 0.434, "step": 3628 }, { "epoch": 4.063853622106049, "grad_norm": 0.885929524898529, "learning_rate": 1.2143423274854973e-06, "loss": 0.4636, "step": 3629 }, { "epoch": 4.064973861090366, "grad_norm": 0.9382648468017578, "learning_rate": 1.2130600309412585e-06, "loss": 0.4553, "step": 3630 }, { "epoch": 4.066094100074682, "grad_norm": 0.9170036911964417, "learning_rate": 1.2117781948747024e-06, "loss": 0.4505, "step": 3631 }, { "epoch": 4.067214339058999, "grad_norm": 0.9397698044776917, "learning_rate": 1.2104968197444794e-06, "loss": 0.4528, "step": 3632 }, { "epoch": 4.0683345780433156, "grad_norm": 0.908519446849823, "learning_rate": 1.2092159060090784e-06, "loss": 0.4344, "step": 3633 }, { "epoch": 4.069454817027633, "grad_norm": 0.919280469417572, "learning_rate": 1.2079354541268197e-06, "loss": 0.4705, "step": 3634 }, { "epoch": 4.07057505601195, "grad_norm": 0.9303897023200989, "learning_rate": 1.2066554645558578e-06, "loss": 0.4479, "step": 3635 }, { "epoch": 4.071695294996266, "grad_norm": 0.9202039241790771, "learning_rate": 1.2053759377541865e-06, "loss": 0.4618, "step": 3636 }, { "epoch": 4.072815533980583, "grad_norm": 0.925559401512146, "learning_rate": 1.2040968741796294e-06, "loss": 0.4501, "step": 3637 }, { "epoch": 4.073935772964899, "grad_norm": 0.9026938080787659, "learning_rate": 1.2028182742898462e-06, "loss": 0.4614, "step": 3638 }, { "epoch": 4.075056011949216, "grad_norm": 0.9154035449028015, "learning_rate": 1.2015401385423291e-06, "loss": 0.4349, "step": 3639 }, { "epoch": 4.076176250933533, "grad_norm": 0.9033060073852539, "learning_rate": 1.200262467394408e-06, "loss": 0.4424, "step": 3640 }, { "epoch": 4.077296489917849, "grad_norm": 0.896186888217926, "learning_rate": 1.198985261303243e-06, "loss": 0.4356, "step": 3641 }, { "epoch": 4.078416728902166, "grad_norm": 0.9219849109649658, "learning_rate": 1.1977085207258284e-06, "loss": 0.4281, "step": 3642 }, { "epoch": 4.079536967886482, "grad_norm": 0.903972327709198, "learning_rate": 1.1964322461189935e-06, "loss": 0.4604, "step": 3643 }, { "epoch": 4.080657206870799, "grad_norm": 0.9358931183815002, "learning_rate": 1.1951564379393988e-06, "loss": 0.4515, "step": 3644 }, { "epoch": 4.081777445855116, "grad_norm": 0.8930990695953369, "learning_rate": 1.1938810966435383e-06, "loss": 0.4407, "step": 3645 }, { "epoch": 4.082897684839432, "grad_norm": 0.9369300603866577, "learning_rate": 1.192606222687742e-06, "loss": 0.4675, "step": 3646 }, { "epoch": 4.084017923823749, "grad_norm": 0.9360557198524475, "learning_rate": 1.1913318165281684e-06, "loss": 0.4393, "step": 3647 }, { "epoch": 4.085138162808065, "grad_norm": 0.8961195945739746, "learning_rate": 1.1900578786208103e-06, "loss": 0.4411, "step": 3648 }, { "epoch": 4.086258401792382, "grad_norm": 0.9457536339759827, "learning_rate": 1.1887844094214949e-06, "loss": 0.4407, "step": 3649 }, { "epoch": 4.087378640776699, "grad_norm": 0.9183881878852844, "learning_rate": 1.1875114093858786e-06, "loss": 0.4643, "step": 3650 }, { "epoch": 4.088498879761016, "grad_norm": 0.8973663449287415, "learning_rate": 1.1862388789694514e-06, "loss": 0.4447, "step": 3651 }, { "epoch": 4.089619118745333, "grad_norm": 0.9056370258331299, "learning_rate": 1.1849668186275356e-06, "loss": 0.4482, "step": 3652 }, { "epoch": 4.090739357729649, "grad_norm": 0.9062683582305908, "learning_rate": 1.1836952288152834e-06, "loss": 0.4439, "step": 3653 }, { "epoch": 4.091859596713966, "grad_norm": 0.8898578882217407, "learning_rate": 1.1824241099876821e-06, "loss": 0.4475, "step": 3654 }, { "epoch": 4.092979835698283, "grad_norm": 0.9018241167068481, "learning_rate": 1.1811534625995475e-06, "loss": 0.4459, "step": 3655 }, { "epoch": 4.094100074682599, "grad_norm": 0.9100399613380432, "learning_rate": 1.1798832871055273e-06, "loss": 0.4471, "step": 3656 }, { "epoch": 4.095220313666916, "grad_norm": 0.8963956236839294, "learning_rate": 1.1786135839601015e-06, "loss": 0.4503, "step": 3657 }, { "epoch": 4.096340552651232, "grad_norm": 0.9050291180610657, "learning_rate": 1.17734435361758e-06, "loss": 0.433, "step": 3658 }, { "epoch": 4.097460791635549, "grad_norm": 0.8986698389053345, "learning_rate": 1.1760755965321021e-06, "loss": 0.4324, "step": 3659 }, { "epoch": 4.098581030619866, "grad_norm": 0.9247352480888367, "learning_rate": 1.1748073131576427e-06, "loss": 0.4336, "step": 3660 }, { "epoch": 4.099701269604182, "grad_norm": 0.9397906064987183, "learning_rate": 1.1735395039480021e-06, "loss": 0.4813, "step": 3661 }, { "epoch": 4.100821508588499, "grad_norm": 0.9537867307662964, "learning_rate": 1.1722721693568123e-06, "loss": 0.4384, "step": 3662 }, { "epoch": 4.101941747572815, "grad_norm": 0.9176379442214966, "learning_rate": 1.1710053098375377e-06, "loss": 0.4765, "step": 3663 }, { "epoch": 4.103061986557132, "grad_norm": 0.978173553943634, "learning_rate": 1.1697389258434702e-06, "loss": 0.4424, "step": 3664 }, { "epoch": 4.104182225541448, "grad_norm": 0.9222602248191833, "learning_rate": 1.1684730178277322e-06, "loss": 0.4477, "step": 3665 }, { "epoch": 4.105302464525765, "grad_norm": 0.9258934855461121, "learning_rate": 1.1672075862432755e-06, "loss": 0.4304, "step": 3666 }, { "epoch": 4.106422703510082, "grad_norm": 0.9188293218612671, "learning_rate": 1.1659426315428834e-06, "loss": 0.424, "step": 3667 }, { "epoch": 4.1075429424943986, "grad_norm": 0.9210534691810608, "learning_rate": 1.1646781541791663e-06, "loss": 0.4751, "step": 3668 }, { "epoch": 4.108663181478716, "grad_norm": 0.9185271263122559, "learning_rate": 1.1634141546045647e-06, "loss": 0.4531, "step": 3669 }, { "epoch": 4.109783420463032, "grad_norm": 0.9216379523277283, "learning_rate": 1.1621506332713475e-06, "loss": 0.463, "step": 3670 }, { "epoch": 4.110903659447349, "grad_norm": 0.9356661438941956, "learning_rate": 1.1608875906316133e-06, "loss": 0.4725, "step": 3671 }, { "epoch": 4.112023898431666, "grad_norm": 0.900882363319397, "learning_rate": 1.1596250271372885e-06, "loss": 0.4407, "step": 3672 }, { "epoch": 4.113144137415982, "grad_norm": 0.9132157564163208, "learning_rate": 1.15836294324013e-06, "loss": 0.4537, "step": 3673 }, { "epoch": 4.114264376400299, "grad_norm": 0.9120463728904724, "learning_rate": 1.1571013393917214e-06, "loss": 0.4426, "step": 3674 }, { "epoch": 4.115384615384615, "grad_norm": 0.9250821471214294, "learning_rate": 1.1558402160434733e-06, "loss": 0.4442, "step": 3675 }, { "epoch": 4.116504854368932, "grad_norm": 0.9143626093864441, "learning_rate": 1.1545795736466286e-06, "loss": 0.4725, "step": 3676 }, { "epoch": 4.117625093353249, "grad_norm": 0.9208996295928955, "learning_rate": 1.1533194126522543e-06, "loss": 0.4621, "step": 3677 }, { "epoch": 4.118745332337565, "grad_norm": 0.9244178533554077, "learning_rate": 1.152059733511246e-06, "loss": 0.4509, "step": 3678 }, { "epoch": 4.119865571321882, "grad_norm": 0.9651166796684265, "learning_rate": 1.1508005366743266e-06, "loss": 0.4606, "step": 3679 }, { "epoch": 4.120985810306198, "grad_norm": 0.9361422657966614, "learning_rate": 1.149541822592049e-06, "loss": 0.4244, "step": 3680 }, { "epoch": 4.122106049290515, "grad_norm": 0.9183467626571655, "learning_rate": 1.1482835917147903e-06, "loss": 0.4634, "step": 3681 }, { "epoch": 4.123226288274832, "grad_norm": 0.9642132520675659, "learning_rate": 1.1470258444927556e-06, "loss": 0.4575, "step": 3682 }, { "epoch": 4.124346527259148, "grad_norm": 0.956210196018219, "learning_rate": 1.145768581375978e-06, "loss": 0.4732, "step": 3683 }, { "epoch": 4.125466766243465, "grad_norm": 0.925435483455658, "learning_rate": 1.1445118028143157e-06, "loss": 0.4545, "step": 3684 }, { "epoch": 4.1265870052277815, "grad_norm": 0.9404733180999756, "learning_rate": 1.1432555092574548e-06, "loss": 0.4494, "step": 3685 }, { "epoch": 4.127707244212099, "grad_norm": 0.9339640736579895, "learning_rate": 1.1419997011549066e-06, "loss": 0.4622, "step": 3686 }, { "epoch": 4.128827483196416, "grad_norm": 0.9159396290779114, "learning_rate": 1.1407443789560113e-06, "loss": 0.433, "step": 3687 }, { "epoch": 4.129947722180732, "grad_norm": 0.9046245813369751, "learning_rate": 1.1394895431099315e-06, "loss": 0.4515, "step": 3688 }, { "epoch": 4.131067961165049, "grad_norm": 0.9260426759719849, "learning_rate": 1.1382351940656596e-06, "loss": 0.4463, "step": 3689 }, { "epoch": 4.132188200149365, "grad_norm": 0.9016514420509338, "learning_rate": 1.136981332272011e-06, "loss": 0.4549, "step": 3690 }, { "epoch": 4.133308439133682, "grad_norm": 0.9085134863853455, "learning_rate": 1.1357279581776285e-06, "loss": 0.4433, "step": 3691 }, { "epoch": 4.134428678117999, "grad_norm": 0.9333678483963013, "learning_rate": 1.1344750722309786e-06, "loss": 0.4879, "step": 3692 }, { "epoch": 4.135548917102315, "grad_norm": 0.9825479388237, "learning_rate": 1.1332226748803534e-06, "loss": 0.4515, "step": 3693 }, { "epoch": 4.136669156086632, "grad_norm": 0.893099844455719, "learning_rate": 1.1319707665738735e-06, "loss": 0.461, "step": 3694 }, { "epoch": 4.137789395070948, "grad_norm": 0.9001293182373047, "learning_rate": 1.1307193477594807e-06, "loss": 0.4429, "step": 3695 }, { "epoch": 4.138909634055265, "grad_norm": 0.9364205598831177, "learning_rate": 1.1294684188849427e-06, "loss": 0.4569, "step": 3696 }, { "epoch": 4.140029873039582, "grad_norm": 0.9197567105293274, "learning_rate": 1.128217980397852e-06, "loss": 0.4536, "step": 3697 }, { "epoch": 4.141150112023898, "grad_norm": 0.9364655613899231, "learning_rate": 1.1269680327456264e-06, "loss": 0.451, "step": 3698 }, { "epoch": 4.142270351008215, "grad_norm": 0.9083155393600464, "learning_rate": 1.125718576375506e-06, "loss": 0.4526, "step": 3699 }, { "epoch": 4.143390589992531, "grad_norm": 0.9199478030204773, "learning_rate": 1.1244696117345586e-06, "loss": 0.4634, "step": 3700 }, { "epoch": 4.144510828976848, "grad_norm": 0.9127255082130432, "learning_rate": 1.123221139269672e-06, "loss": 0.4405, "step": 3701 }, { "epoch": 4.145631067961165, "grad_norm": 0.9312313795089722, "learning_rate": 1.1219731594275619e-06, "loss": 0.4597, "step": 3702 }, { "epoch": 4.1467513069454816, "grad_norm": 0.9091891646385193, "learning_rate": 1.1207256726547644e-06, "loss": 0.421, "step": 3703 }, { "epoch": 4.147871545929799, "grad_norm": 0.9536944627761841, "learning_rate": 1.1194786793976412e-06, "loss": 0.4631, "step": 3704 }, { "epoch": 4.148991784914115, "grad_norm": 0.9433373808860779, "learning_rate": 1.118232180102376e-06, "loss": 0.488, "step": 3705 }, { "epoch": 4.150112023898432, "grad_norm": 0.9376880526542664, "learning_rate": 1.1169861752149761e-06, "loss": 0.4435, "step": 3706 }, { "epoch": 4.151232262882749, "grad_norm": 0.9072856903076172, "learning_rate": 1.115740665181274e-06, "loss": 0.4695, "step": 3707 }, { "epoch": 4.152352501867065, "grad_norm": 0.9386592507362366, "learning_rate": 1.114495650446922e-06, "loss": 0.4562, "step": 3708 }, { "epoch": 4.153472740851382, "grad_norm": 0.9518917202949524, "learning_rate": 1.1132511314573974e-06, "loss": 0.4464, "step": 3709 }, { "epoch": 4.154592979835698, "grad_norm": 0.8735892176628113, "learning_rate": 1.1120071086579988e-06, "loss": 0.4238, "step": 3710 }, { "epoch": 4.155713218820015, "grad_norm": 0.9260808229446411, "learning_rate": 1.1107635824938478e-06, "loss": 0.4632, "step": 3711 }, { "epoch": 4.156833457804332, "grad_norm": 0.948487401008606, "learning_rate": 1.1095205534098873e-06, "loss": 0.4557, "step": 3712 }, { "epoch": 4.157953696788648, "grad_norm": 0.9289817214012146, "learning_rate": 1.1082780218508857e-06, "loss": 0.452, "step": 3713 }, { "epoch": 4.159073935772965, "grad_norm": 0.9113280177116394, "learning_rate": 1.1070359882614294e-06, "loss": 0.4513, "step": 3714 }, { "epoch": 4.160194174757281, "grad_norm": 0.9354933500289917, "learning_rate": 1.1057944530859272e-06, "loss": 0.4552, "step": 3715 }, { "epoch": 4.161314413741598, "grad_norm": 0.9220413565635681, "learning_rate": 1.1045534167686131e-06, "loss": 0.467, "step": 3716 }, { "epoch": 4.162434652725915, "grad_norm": 0.9146202206611633, "learning_rate": 1.1033128797535386e-06, "loss": 0.4581, "step": 3717 }, { "epoch": 4.163554891710231, "grad_norm": 0.8790375590324402, "learning_rate": 1.1020728424845784e-06, "loss": 0.4381, "step": 3718 }, { "epoch": 4.164675130694548, "grad_norm": 0.9646771550178528, "learning_rate": 1.1008333054054276e-06, "loss": 0.4703, "step": 3719 }, { "epoch": 4.1657953696788645, "grad_norm": 0.9151301383972168, "learning_rate": 1.0995942689596023e-06, "loss": 0.4636, "step": 3720 }, { "epoch": 4.166915608663182, "grad_norm": 0.9289845824241638, "learning_rate": 1.0983557335904417e-06, "loss": 0.4374, "step": 3721 }, { "epoch": 4.168035847647499, "grad_norm": 0.9233942031860352, "learning_rate": 1.0971176997411024e-06, "loss": 0.4309, "step": 3722 }, { "epoch": 4.169156086631815, "grad_norm": 0.8963869214057922, "learning_rate": 1.0958801678545636e-06, "loss": 0.4482, "step": 3723 }, { "epoch": 4.170276325616132, "grad_norm": 0.8945997953414917, "learning_rate": 1.0946431383736242e-06, "loss": 0.4457, "step": 3724 }, { "epoch": 4.171396564600448, "grad_norm": 0.8992323875427246, "learning_rate": 1.0934066117409035e-06, "loss": 0.4763, "step": 3725 }, { "epoch": 4.172516803584765, "grad_norm": 0.9345870614051819, "learning_rate": 1.09217058839884e-06, "loss": 0.4566, "step": 3726 }, { "epoch": 4.173637042569082, "grad_norm": 0.9144310355186462, "learning_rate": 1.090935068789695e-06, "loss": 0.4486, "step": 3727 }, { "epoch": 4.174757281553398, "grad_norm": 0.9222366213798523, "learning_rate": 1.0897000533555455e-06, "loss": 0.4656, "step": 3728 }, { "epoch": 4.175877520537715, "grad_norm": 0.9157934188842773, "learning_rate": 1.088465542538292e-06, "loss": 0.4412, "step": 3729 }, { "epoch": 4.176997759522031, "grad_norm": 0.9130349159240723, "learning_rate": 1.0872315367796519e-06, "loss": 0.4344, "step": 3730 }, { "epoch": 4.178117998506348, "grad_norm": 0.909132182598114, "learning_rate": 1.085998036521162e-06, "loss": 0.4575, "step": 3731 }, { "epoch": 4.179238237490664, "grad_norm": 0.9286696314811707, "learning_rate": 1.0847650422041794e-06, "loss": 0.4499, "step": 3732 }, { "epoch": 4.180358476474981, "grad_norm": 0.9114892482757568, "learning_rate": 1.083532554269879e-06, "loss": 0.4627, "step": 3733 }, { "epoch": 4.181478715459298, "grad_norm": 0.9175817370414734, "learning_rate": 1.0823005731592558e-06, "loss": 0.4365, "step": 3734 }, { "epoch": 4.182598954443614, "grad_norm": 0.9305630922317505, "learning_rate": 1.0810690993131226e-06, "loss": 0.4612, "step": 3735 }, { "epoch": 4.183719193427931, "grad_norm": 0.9275410175323486, "learning_rate": 1.079838133172111e-06, "loss": 0.4381, "step": 3736 }, { "epoch": 4.1848394324122475, "grad_norm": 0.8960487842559814, "learning_rate": 1.0786076751766702e-06, "loss": 0.4366, "step": 3737 }, { "epoch": 4.1859596713965646, "grad_norm": 0.9104733467102051, "learning_rate": 1.0773777257670686e-06, "loss": 0.4725, "step": 3738 }, { "epoch": 4.187079910380882, "grad_norm": 0.9126273989677429, "learning_rate": 1.0761482853833913e-06, "loss": 0.4477, "step": 3739 }, { "epoch": 4.188200149365198, "grad_norm": 0.9505194425582886, "learning_rate": 1.0749193544655435e-06, "loss": 0.4682, "step": 3740 }, { "epoch": 4.189320388349515, "grad_norm": 0.9069116115570068, "learning_rate": 1.0736909334532454e-06, "loss": 0.4554, "step": 3741 }, { "epoch": 4.190440627333831, "grad_norm": 0.9119701981544495, "learning_rate": 1.0724630227860381e-06, "loss": 0.4357, "step": 3742 }, { "epoch": 4.191560866318148, "grad_norm": 0.8906586170196533, "learning_rate": 1.0712356229032766e-06, "loss": 0.4778, "step": 3743 }, { "epoch": 4.192681105302465, "grad_norm": 0.9555360078811646, "learning_rate": 1.070008734244135e-06, "loss": 0.449, "step": 3744 }, { "epoch": 4.193801344286781, "grad_norm": 0.8981227874755859, "learning_rate": 1.0687823572476043e-06, "loss": 0.4362, "step": 3745 }, { "epoch": 4.194921583271098, "grad_norm": 0.9105731248855591, "learning_rate": 1.067556492352492e-06, "loss": 0.4672, "step": 3746 }, { "epoch": 4.196041822255414, "grad_norm": 0.9224116206169128, "learning_rate": 1.0663311399974218e-06, "loss": 0.4591, "step": 3747 }, { "epoch": 4.197162061239731, "grad_norm": 0.9398331642150879, "learning_rate": 1.0651063006208366e-06, "loss": 0.4268, "step": 3748 }, { "epoch": 4.198282300224048, "grad_norm": 0.8762515783309937, "learning_rate": 1.0638819746609929e-06, "loss": 0.4482, "step": 3749 }, { "epoch": 4.199402539208364, "grad_norm": 0.9052920341491699, "learning_rate": 1.0626581625559652e-06, "loss": 0.4618, "step": 3750 }, { "epoch": 4.200522778192681, "grad_norm": 0.9559775590896606, "learning_rate": 1.0614348647436426e-06, "loss": 0.4402, "step": 3751 }, { "epoch": 4.201643017176997, "grad_norm": 0.9115535020828247, "learning_rate": 1.060212081661732e-06, "loss": 0.4565, "step": 3752 }, { "epoch": 4.202763256161314, "grad_norm": 0.9455323219299316, "learning_rate": 1.0589898137477536e-06, "loss": 0.472, "step": 3753 }, { "epoch": 4.203883495145631, "grad_norm": 0.9387434124946594, "learning_rate": 1.0577680614390461e-06, "loss": 0.4718, "step": 3754 }, { "epoch": 4.2050037341299475, "grad_norm": 0.9219316840171814, "learning_rate": 1.0565468251727637e-06, "loss": 0.4558, "step": 3755 }, { "epoch": 4.206123973114265, "grad_norm": 0.9084392189979553, "learning_rate": 1.0553261053858733e-06, "loss": 0.4656, "step": 3756 }, { "epoch": 4.207244212098581, "grad_norm": 0.9559876918792725, "learning_rate": 1.0541059025151587e-06, "loss": 0.4394, "step": 3757 }, { "epoch": 4.208364451082898, "grad_norm": 0.9161111116409302, "learning_rate": 1.0528862169972188e-06, "loss": 0.4397, "step": 3758 }, { "epoch": 4.209484690067215, "grad_norm": 0.9553343057632446, "learning_rate": 1.0516670492684667e-06, "loss": 0.428, "step": 3759 }, { "epoch": 4.210604929051531, "grad_norm": 0.9005900025367737, "learning_rate": 1.0504483997651296e-06, "loss": 0.4482, "step": 3760 }, { "epoch": 4.211725168035848, "grad_norm": 0.938490092754364, "learning_rate": 1.0492302689232525e-06, "loss": 0.4466, "step": 3761 }, { "epoch": 4.212845407020164, "grad_norm": 0.9463299512863159, "learning_rate": 1.0480126571786914e-06, "loss": 0.4601, "step": 3762 }, { "epoch": 4.213965646004481, "grad_norm": 0.9516392946243286, "learning_rate": 1.046795564967118e-06, "loss": 0.4526, "step": 3763 }, { "epoch": 4.215085884988798, "grad_norm": 0.9116749167442322, "learning_rate": 1.045578992724018e-06, "loss": 0.4351, "step": 3764 }, { "epoch": 4.216206123973114, "grad_norm": 0.9417027831077576, "learning_rate": 1.0443629408846903e-06, "loss": 0.4558, "step": 3765 }, { "epoch": 4.217326362957431, "grad_norm": 0.8931170105934143, "learning_rate": 1.043147409884248e-06, "loss": 0.4168, "step": 3766 }, { "epoch": 4.218446601941747, "grad_norm": 0.8729584217071533, "learning_rate": 1.0419324001576194e-06, "loss": 0.4412, "step": 3767 }, { "epoch": 4.219566840926064, "grad_norm": 0.9340854287147522, "learning_rate": 1.0407179121395436e-06, "loss": 0.4418, "step": 3768 }, { "epoch": 4.220687079910381, "grad_norm": 0.9264068007469177, "learning_rate": 1.039503946264576e-06, "loss": 0.435, "step": 3769 }, { "epoch": 4.221807318894697, "grad_norm": 0.8993460536003113, "learning_rate": 1.0382905029670822e-06, "loss": 0.4642, "step": 3770 }, { "epoch": 4.222927557879014, "grad_norm": 0.9071006178855896, "learning_rate": 1.037077582681243e-06, "loss": 0.4676, "step": 3771 }, { "epoch": 4.2240477968633305, "grad_norm": 0.9450436234474182, "learning_rate": 1.0358651858410507e-06, "loss": 0.4563, "step": 3772 }, { "epoch": 4.2251680358476476, "grad_norm": 0.8972642421722412, "learning_rate": 1.0346533128803108e-06, "loss": 0.435, "step": 3773 }, { "epoch": 4.226288274831965, "grad_norm": 0.9062877893447876, "learning_rate": 1.0334419642326407e-06, "loss": 0.4421, "step": 3774 }, { "epoch": 4.227408513816281, "grad_norm": 0.9064728617668152, "learning_rate": 1.0322311403314727e-06, "loss": 0.4513, "step": 3775 }, { "epoch": 4.228528752800598, "grad_norm": 0.942784309387207, "learning_rate": 1.0310208416100484e-06, "loss": 0.4731, "step": 3776 }, { "epoch": 4.229648991784914, "grad_norm": 0.9346246719360352, "learning_rate": 1.029811068501423e-06, "loss": 0.4714, "step": 3777 }, { "epoch": 4.230769230769231, "grad_norm": 0.926162600517273, "learning_rate": 1.0286018214384627e-06, "loss": 0.4441, "step": 3778 }, { "epoch": 4.231889469753548, "grad_norm": 0.9109740853309631, "learning_rate": 1.0273931008538465e-06, "loss": 0.4639, "step": 3779 }, { "epoch": 4.233009708737864, "grad_norm": 0.9478312134742737, "learning_rate": 1.0261849071800635e-06, "loss": 0.4467, "step": 3780 }, { "epoch": 4.234129947722181, "grad_norm": 0.9327713847160339, "learning_rate": 1.0249772408494162e-06, "loss": 0.444, "step": 3781 }, { "epoch": 4.235250186706497, "grad_norm": 0.924805760383606, "learning_rate": 1.0237701022940185e-06, "loss": 0.4303, "step": 3782 }, { "epoch": 4.236370425690814, "grad_norm": 0.9011421799659729, "learning_rate": 1.0225634919457934e-06, "loss": 0.4573, "step": 3783 }, { "epoch": 4.23749066467513, "grad_norm": 0.9306401014328003, "learning_rate": 1.0213574102364759e-06, "loss": 0.4524, "step": 3784 }, { "epoch": 4.238610903659447, "grad_norm": 0.9292621612548828, "learning_rate": 1.0201518575976124e-06, "loss": 0.4665, "step": 3785 }, { "epoch": 4.239731142643764, "grad_norm": 0.9251322746276855, "learning_rate": 1.018946834460559e-06, "loss": 0.4432, "step": 3786 }, { "epoch": 4.24085138162808, "grad_norm": 0.9133168458938599, "learning_rate": 1.0177423412564824e-06, "loss": 0.469, "step": 3787 }, { "epoch": 4.241971620612397, "grad_norm": 0.9150897264480591, "learning_rate": 1.0165383784163618e-06, "loss": 0.451, "step": 3788 }, { "epoch": 4.2430918595967135, "grad_norm": 0.9365672469139099, "learning_rate": 1.015334946370984e-06, "loss": 0.4612, "step": 3789 }, { "epoch": 4.2442120985810305, "grad_norm": 0.9754878282546997, "learning_rate": 1.0141320455509471e-06, "loss": 0.4676, "step": 3790 }, { "epoch": 4.245332337565348, "grad_norm": 0.9070945978164673, "learning_rate": 1.0129296763866584e-06, "loss": 0.4596, "step": 3791 }, { "epoch": 4.246452576549664, "grad_norm": 0.9231680631637573, "learning_rate": 1.0117278393083357e-06, "loss": 0.4395, "step": 3792 }, { "epoch": 4.247572815533981, "grad_norm": 0.898967444896698, "learning_rate": 1.0105265347460056e-06, "loss": 0.4539, "step": 3793 }, { "epoch": 4.248693054518297, "grad_norm": 0.9164290428161621, "learning_rate": 1.0093257631295054e-06, "loss": 0.4517, "step": 3794 }, { "epoch": 4.249813293502614, "grad_norm": 0.8922174572944641, "learning_rate": 1.0081255248884816e-06, "loss": 0.4266, "step": 3795 }, { "epoch": 4.250933532486931, "grad_norm": 0.9130483269691467, "learning_rate": 1.0069258204523888e-06, "loss": 0.4293, "step": 3796 }, { "epoch": 4.252053771471247, "grad_norm": 0.9118824005126953, "learning_rate": 1.0057266502504912e-06, "loss": 0.4527, "step": 3797 }, { "epoch": 4.253174010455564, "grad_norm": 0.892975926399231, "learning_rate": 1.0045280147118612e-06, "loss": 0.4568, "step": 3798 }, { "epoch": 4.25429424943988, "grad_norm": 0.9228742122650146, "learning_rate": 1.0033299142653808e-06, "loss": 0.4657, "step": 3799 }, { "epoch": 4.255414488424197, "grad_norm": 0.9345189929008484, "learning_rate": 1.0021323493397394e-06, "loss": 0.477, "step": 3800 }, { "epoch": 4.256534727408514, "grad_norm": 0.9275545477867126, "learning_rate": 1.000935320363437e-06, "loss": 0.4469, "step": 3801 }, { "epoch": 4.25765496639283, "grad_norm": 0.9062563180923462, "learning_rate": 9.9973882776478e-07, "loss": 0.4618, "step": 3802 }, { "epoch": 4.258775205377147, "grad_norm": 0.9212909936904907, "learning_rate": 9.985428719718827e-07, "loss": 0.4475, "step": 3803 }, { "epoch": 4.259895444361463, "grad_norm": 0.9002099633216858, "learning_rate": 9.973474534126681e-07, "loss": 0.4685, "step": 3804 }, { "epoch": 4.26101568334578, "grad_norm": 0.9293535351753235, "learning_rate": 9.961525725148669e-07, "loss": 0.4515, "step": 3805 }, { "epoch": 4.262135922330097, "grad_norm": 0.8897074460983276, "learning_rate": 9.94958229706017e-07, "loss": 0.439, "step": 3806 }, { "epoch": 4.2632561613144135, "grad_norm": 0.8932860493659973, "learning_rate": 9.937644254134638e-07, "loss": 0.4494, "step": 3807 }, { "epoch": 4.2643764002987306, "grad_norm": 0.9553624987602234, "learning_rate": 9.925711600643603e-07, "loss": 0.472, "step": 3808 }, { "epoch": 4.265496639283047, "grad_norm": 0.9415077567100525, "learning_rate": 9.913784340856683e-07, "loss": 0.4593, "step": 3809 }, { "epoch": 4.266616878267364, "grad_norm": 0.9327034950256348, "learning_rate": 9.901862479041535e-07, "loss": 0.4587, "step": 3810 }, { "epoch": 4.267737117251681, "grad_norm": 0.9183216094970703, "learning_rate": 9.889946019463903e-07, "loss": 0.4491, "step": 3811 }, { "epoch": 4.268857356235997, "grad_norm": 0.9180659055709839, "learning_rate": 9.878034966387593e-07, "loss": 0.4476, "step": 3812 }, { "epoch": 4.269977595220314, "grad_norm": 0.9235206842422485, "learning_rate": 9.866129324074475e-07, "loss": 0.4679, "step": 3813 }, { "epoch": 4.27109783420463, "grad_norm": 0.9502838253974915, "learning_rate": 9.854229096784477e-07, "loss": 0.4316, "step": 3814 }, { "epoch": 4.272218073188947, "grad_norm": 0.8966188430786133, "learning_rate": 9.842334288775619e-07, "loss": 0.464, "step": 3815 }, { "epoch": 4.273338312173264, "grad_norm": 0.9004864692687988, "learning_rate": 9.830444904303952e-07, "loss": 0.4454, "step": 3816 }, { "epoch": 4.27445855115758, "grad_norm": 0.9234562516212463, "learning_rate": 9.81856094762359e-07, "loss": 0.4602, "step": 3817 }, { "epoch": 4.275578790141897, "grad_norm": 0.9406241774559021, "learning_rate": 9.806682422986716e-07, "loss": 0.4591, "step": 3818 }, { "epoch": 4.276699029126213, "grad_norm": 0.9198372960090637, "learning_rate": 9.79480933464356e-07, "loss": 0.439, "step": 3819 }, { "epoch": 4.27781926811053, "grad_norm": 0.912356972694397, "learning_rate": 9.782941686842405e-07, "loss": 0.4554, "step": 3820 }, { "epoch": 4.278939507094847, "grad_norm": 0.9130864143371582, "learning_rate": 9.771079483829599e-07, "loss": 0.4332, "step": 3821 }, { "epoch": 4.280059746079163, "grad_norm": 0.9224491715431213, "learning_rate": 9.759222729849544e-07, "loss": 0.4593, "step": 3822 }, { "epoch": 4.28117998506348, "grad_norm": 0.9403615593910217, "learning_rate": 9.747371429144676e-07, "loss": 0.4638, "step": 3823 }, { "epoch": 4.2823002240477965, "grad_norm": 0.9411090016365051, "learning_rate": 9.735525585955488e-07, "loss": 0.4699, "step": 3824 }, { "epoch": 4.2834204630321135, "grad_norm": 0.9046223163604736, "learning_rate": 9.72368520452052e-07, "loss": 0.4463, "step": 3825 }, { "epoch": 4.284540702016431, "grad_norm": 0.9243559241294861, "learning_rate": 9.711850289076358e-07, "loss": 0.4193, "step": 3826 }, { "epoch": 4.285660941000747, "grad_norm": 0.906290590763092, "learning_rate": 9.70002084385762e-07, "loss": 0.4396, "step": 3827 }, { "epoch": 4.286781179985064, "grad_norm": 0.9148289561271667, "learning_rate": 9.688196873097e-07, "loss": 0.4416, "step": 3828 }, { "epoch": 4.28790141896938, "grad_norm": 0.9446461200714111, "learning_rate": 9.676378381025203e-07, "loss": 0.4556, "step": 3829 }, { "epoch": 4.289021657953697, "grad_norm": 0.9237595200538635, "learning_rate": 9.66456537187098e-07, "loss": 0.4702, "step": 3830 }, { "epoch": 4.290141896938014, "grad_norm": 0.9529768824577332, "learning_rate": 9.65275784986112e-07, "loss": 0.4742, "step": 3831 }, { "epoch": 4.29126213592233, "grad_norm": 0.933364748954773, "learning_rate": 9.64095581922046e-07, "loss": 0.4392, "step": 3832 }, { "epoch": 4.292382374906647, "grad_norm": 0.9427585601806641, "learning_rate": 9.62915928417185e-07, "loss": 0.4566, "step": 3833 }, { "epoch": 4.293502613890963, "grad_norm": 0.9348896145820618, "learning_rate": 9.617368248936202e-07, "loss": 0.473, "step": 3834 }, { "epoch": 4.29462285287528, "grad_norm": 0.9225775599479675, "learning_rate": 9.60558271773243e-07, "loss": 0.4258, "step": 3835 }, { "epoch": 4.295743091859597, "grad_norm": 0.903752326965332, "learning_rate": 9.59380269477751e-07, "loss": 0.4511, "step": 3836 }, { "epoch": 4.296863330843913, "grad_norm": 0.9201604127883911, "learning_rate": 9.582028184286423e-07, "loss": 0.4607, "step": 3837 }, { "epoch": 4.29798356982823, "grad_norm": 0.929657518863678, "learning_rate": 9.57025919047219e-07, "loss": 0.4461, "step": 3838 }, { "epoch": 4.299103808812546, "grad_norm": 0.9024868607521057, "learning_rate": 9.558495717545843e-07, "loss": 0.4611, "step": 3839 }, { "epoch": 4.300224047796863, "grad_norm": 0.9095185995101929, "learning_rate": 9.54673776971646e-07, "loss": 0.4658, "step": 3840 }, { "epoch": 4.30134428678118, "grad_norm": 0.9154278039932251, "learning_rate": 9.534985351191117e-07, "loss": 0.444, "step": 3841 }, { "epoch": 4.3024645257654965, "grad_norm": 0.9158421158790588, "learning_rate": 9.523238466174942e-07, "loss": 0.4289, "step": 3842 }, { "epoch": 4.3035847647498136, "grad_norm": 0.9210811257362366, "learning_rate": 9.511497118871063e-07, "loss": 0.4758, "step": 3843 }, { "epoch": 4.30470500373413, "grad_norm": 0.9397215247154236, "learning_rate": 9.499761313480627e-07, "loss": 0.4605, "step": 3844 }, { "epoch": 4.305825242718447, "grad_norm": 0.9136872887611389, "learning_rate": 9.488031054202801e-07, "loss": 0.4715, "step": 3845 }, { "epoch": 4.306945481702764, "grad_norm": 0.9277961850166321, "learning_rate": 9.47630634523477e-07, "loss": 0.4476, "step": 3846 }, { "epoch": 4.30806572068708, "grad_norm": 0.9163387417793274, "learning_rate": 9.464587190771724e-07, "loss": 0.4499, "step": 3847 }, { "epoch": 4.309185959671397, "grad_norm": 0.9258783459663391, "learning_rate": 9.452873595006876e-07, "loss": 0.455, "step": 3848 }, { "epoch": 4.310306198655713, "grad_norm": 0.918402373790741, "learning_rate": 9.44116556213146e-07, "loss": 0.443, "step": 3849 }, { "epoch": 4.31142643764003, "grad_norm": 0.9006342887878418, "learning_rate": 9.429463096334695e-07, "loss": 0.4311, "step": 3850 }, { "epoch": 4.312546676624347, "grad_norm": 0.924345076084137, "learning_rate": 9.417766201803822e-07, "loss": 0.4565, "step": 3851 }, { "epoch": 4.313666915608663, "grad_norm": 0.9314975738525391, "learning_rate": 9.406074882724084e-07, "loss": 0.442, "step": 3852 }, { "epoch": 4.31478715459298, "grad_norm": 0.9144547581672668, "learning_rate": 9.394389143278729e-07, "loss": 0.4504, "step": 3853 }, { "epoch": 4.315907393577296, "grad_norm": 0.9297031164169312, "learning_rate": 9.382708987649006e-07, "loss": 0.4415, "step": 3854 }, { "epoch": 4.317027632561613, "grad_norm": 0.9217665791511536, "learning_rate": 9.371034420014182e-07, "loss": 0.4435, "step": 3855 }, { "epoch": 4.318147871545929, "grad_norm": 0.9170840978622437, "learning_rate": 9.359365444551513e-07, "loss": 0.4672, "step": 3856 }, { "epoch": 4.319268110530246, "grad_norm": 0.9285500645637512, "learning_rate": 9.347702065436245e-07, "loss": 0.4584, "step": 3857 }, { "epoch": 4.320388349514563, "grad_norm": 0.9560800194740295, "learning_rate": 9.336044286841639e-07, "loss": 0.4615, "step": 3858 }, { "epoch": 4.3215085884988795, "grad_norm": 0.8977309465408325, "learning_rate": 9.324392112938938e-07, "loss": 0.4489, "step": 3859 }, { "epoch": 4.3226288274831965, "grad_norm": 0.9604977369308472, "learning_rate": 9.312745547897378e-07, "loss": 0.4411, "step": 3860 }, { "epoch": 4.323749066467513, "grad_norm": 0.9247673749923706, "learning_rate": 9.301104595884216e-07, "loss": 0.4376, "step": 3861 }, { "epoch": 4.32486930545183, "grad_norm": 0.8877954483032227, "learning_rate": 9.28946926106466e-07, "loss": 0.4134, "step": 3862 }, { "epoch": 4.325989544436147, "grad_norm": 0.9250066876411438, "learning_rate": 9.277839547601943e-07, "loss": 0.4747, "step": 3863 }, { "epoch": 4.327109783420463, "grad_norm": 0.9424324035644531, "learning_rate": 9.266215459657269e-07, "loss": 0.4489, "step": 3864 }, { "epoch": 4.32823002240478, "grad_norm": 0.9162999391555786, "learning_rate": 9.254597001389831e-07, "loss": 0.4302, "step": 3865 }, { "epoch": 4.329350261389096, "grad_norm": 0.9228576421737671, "learning_rate": 9.242984176956804e-07, "loss": 0.4086, "step": 3866 }, { "epoch": 4.330470500373413, "grad_norm": 0.9121648073196411, "learning_rate": 9.231376990513358e-07, "loss": 0.4415, "step": 3867 }, { "epoch": 4.33159073935773, "grad_norm": 0.9236108660697937, "learning_rate": 9.219775446212625e-07, "loss": 0.4731, "step": 3868 }, { "epoch": 4.332710978342046, "grad_norm": 0.9360636472702026, "learning_rate": 9.208179548205754e-07, "loss": 0.4654, "step": 3869 }, { "epoch": 4.333831217326363, "grad_norm": 0.9141676425933838, "learning_rate": 9.196589300641842e-07, "loss": 0.4419, "step": 3870 }, { "epoch": 4.334951456310679, "grad_norm": 0.9231441020965576, "learning_rate": 9.185004707667977e-07, "loss": 0.4463, "step": 3871 }, { "epoch": 4.336071695294996, "grad_norm": 0.9187621474266052, "learning_rate": 9.17342577342922e-07, "loss": 0.4574, "step": 3872 }, { "epoch": 4.337191934279313, "grad_norm": 0.8982871174812317, "learning_rate": 9.161852502068611e-07, "loss": 0.4785, "step": 3873 }, { "epoch": 4.338312173263629, "grad_norm": 0.9295719861984253, "learning_rate": 9.150284897727146e-07, "loss": 0.4493, "step": 3874 }, { "epoch": 4.339432412247946, "grad_norm": 0.9271039366722107, "learning_rate": 9.138722964543825e-07, "loss": 0.4607, "step": 3875 }, { "epoch": 4.3405526512322625, "grad_norm": 0.9237571954727173, "learning_rate": 9.127166706655608e-07, "loss": 0.44, "step": 3876 }, { "epoch": 4.3416728902165795, "grad_norm": 0.9312848448753357, "learning_rate": 9.115616128197408e-07, "loss": 0.4466, "step": 3877 }, { "epoch": 4.3427931292008966, "grad_norm": 0.903756856918335, "learning_rate": 9.10407123330212e-07, "loss": 0.4182, "step": 3878 }, { "epoch": 4.343913368185213, "grad_norm": 0.9107953310012817, "learning_rate": 9.092532026100603e-07, "loss": 0.4562, "step": 3879 }, { "epoch": 4.34503360716953, "grad_norm": 0.9083762764930725, "learning_rate": 9.080998510721678e-07, "loss": 0.4714, "step": 3880 }, { "epoch": 4.346153846153846, "grad_norm": 0.9261408448219299, "learning_rate": 9.069470691292123e-07, "loss": 0.4623, "step": 3881 }, { "epoch": 4.347274085138163, "grad_norm": 0.9380280375480652, "learning_rate": 9.057948571936703e-07, "loss": 0.4426, "step": 3882 }, { "epoch": 4.34839432412248, "grad_norm": 0.9040005803108215, "learning_rate": 9.046432156778118e-07, "loss": 0.4367, "step": 3883 }, { "epoch": 4.349514563106796, "grad_norm": 0.9094467759132385, "learning_rate": 9.03492144993704e-07, "loss": 0.4402, "step": 3884 }, { "epoch": 4.350634802091113, "grad_norm": 0.9041321277618408, "learning_rate": 9.023416455532089e-07, "loss": 0.4359, "step": 3885 }, { "epoch": 4.351755041075429, "grad_norm": 0.8982166051864624, "learning_rate": 9.011917177679849e-07, "loss": 0.458, "step": 3886 }, { "epoch": 4.352875280059746, "grad_norm": 0.9039756059646606, "learning_rate": 9.000423620494849e-07, "loss": 0.4441, "step": 3887 }, { "epoch": 4.353995519044063, "grad_norm": 0.9410241842269897, "learning_rate": 8.988935788089592e-07, "loss": 0.4457, "step": 3888 }, { "epoch": 4.355115758028379, "grad_norm": 0.9315477609634399, "learning_rate": 8.977453684574502e-07, "loss": 0.4473, "step": 3889 }, { "epoch": 4.356235997012696, "grad_norm": 0.9125888347625732, "learning_rate": 8.965977314057991e-07, "loss": 0.4541, "step": 3890 }, { "epoch": 4.357356235997012, "grad_norm": 0.9189037680625916, "learning_rate": 8.954506680646385e-07, "loss": 0.4158, "step": 3891 }, { "epoch": 4.358476474981329, "grad_norm": 0.9169250130653381, "learning_rate": 8.943041788443971e-07, "loss": 0.4415, "step": 3892 }, { "epoch": 4.359596713965646, "grad_norm": 0.9340740442276001, "learning_rate": 8.931582641552985e-07, "loss": 0.4643, "step": 3893 }, { "epoch": 4.3607169529499625, "grad_norm": 0.9420515894889832, "learning_rate": 8.920129244073602e-07, "loss": 0.4387, "step": 3894 }, { "epoch": 4.3618371919342795, "grad_norm": 0.957955539226532, "learning_rate": 8.908681600103935e-07, "loss": 0.4338, "step": 3895 }, { "epoch": 4.362957430918596, "grad_norm": 0.9149394631385803, "learning_rate": 8.897239713740058e-07, "loss": 0.436, "step": 3896 }, { "epoch": 4.364077669902913, "grad_norm": 0.9127804040908813, "learning_rate": 8.885803589075967e-07, "loss": 0.4672, "step": 3897 }, { "epoch": 4.365197908887229, "grad_norm": 0.9435532689094543, "learning_rate": 8.874373230203597e-07, "loss": 0.4434, "step": 3898 }, { "epoch": 4.366318147871546, "grad_norm": 0.9353042840957642, "learning_rate": 8.862948641212829e-07, "loss": 0.4611, "step": 3899 }, { "epoch": 4.367438386855863, "grad_norm": 0.9392760992050171, "learning_rate": 8.851529826191463e-07, "loss": 0.4428, "step": 3900 }, { "epoch": 4.368558625840179, "grad_norm": 0.9260551333427429, "learning_rate": 8.840116789225264e-07, "loss": 0.4541, "step": 3901 }, { "epoch": 4.369678864824496, "grad_norm": 0.9218583106994629, "learning_rate": 8.828709534397892e-07, "loss": 0.4736, "step": 3902 }, { "epoch": 4.370799103808812, "grad_norm": 0.9223028421401978, "learning_rate": 8.817308065790975e-07, "loss": 0.4413, "step": 3903 }, { "epoch": 4.371919342793129, "grad_norm": 0.9321942925453186, "learning_rate": 8.805912387484039e-07, "loss": 0.4526, "step": 3904 }, { "epoch": 4.373039581777446, "grad_norm": 0.8988950848579407, "learning_rate": 8.794522503554556e-07, "loss": 0.471, "step": 3905 }, { "epoch": 4.374159820761762, "grad_norm": 0.938857913017273, "learning_rate": 8.783138418077919e-07, "loss": 0.4678, "step": 3906 }, { "epoch": 4.375280059746079, "grad_norm": 0.962287962436676, "learning_rate": 8.771760135127447e-07, "loss": 0.444, "step": 3907 }, { "epoch": 4.376400298730395, "grad_norm": 0.9215114116668701, "learning_rate": 8.760387658774372e-07, "loss": 0.452, "step": 3908 }, { "epoch": 4.377520537714712, "grad_norm": 0.9237968921661377, "learning_rate": 8.749020993087878e-07, "loss": 0.4389, "step": 3909 }, { "epoch": 4.378640776699029, "grad_norm": 0.9397491812705994, "learning_rate": 8.737660142135044e-07, "loss": 0.4476, "step": 3910 }, { "epoch": 4.3797610156833455, "grad_norm": 0.8900991678237915, "learning_rate": 8.726305109980876e-07, "loss": 0.4268, "step": 3911 }, { "epoch": 4.3808812546676625, "grad_norm": 0.9580149054527283, "learning_rate": 8.714955900688296e-07, "loss": 0.4573, "step": 3912 }, { "epoch": 4.382001493651979, "grad_norm": 0.9413899779319763, "learning_rate": 8.703612518318144e-07, "loss": 0.4437, "step": 3913 }, { "epoch": 4.383121732636296, "grad_norm": 1.0459883213043213, "learning_rate": 8.692274966929168e-07, "loss": 0.4436, "step": 3914 }, { "epoch": 4.384241971620613, "grad_norm": 0.9306219220161438, "learning_rate": 8.680943250578044e-07, "loss": 0.4364, "step": 3915 }, { "epoch": 4.385362210604929, "grad_norm": 0.9443317651748657, "learning_rate": 8.669617373319364e-07, "loss": 0.4838, "step": 3916 }, { "epoch": 4.386482449589246, "grad_norm": 0.9257446527481079, "learning_rate": 8.658297339205609e-07, "loss": 0.4408, "step": 3917 }, { "epoch": 4.387602688573562, "grad_norm": 0.9668862819671631, "learning_rate": 8.646983152287184e-07, "loss": 0.4647, "step": 3918 }, { "epoch": 4.388722927557879, "grad_norm": 0.9069690704345703, "learning_rate": 8.635674816612391e-07, "loss": 0.4473, "step": 3919 }, { "epoch": 4.389843166542196, "grad_norm": 0.9246066808700562, "learning_rate": 8.624372336227451e-07, "loss": 0.4303, "step": 3920 }, { "epoch": 4.390963405526512, "grad_norm": 0.924135148525238, "learning_rate": 8.613075715176484e-07, "loss": 0.4429, "step": 3921 }, { "epoch": 4.392083644510829, "grad_norm": 0.9132075309753418, "learning_rate": 8.601784957501502e-07, "loss": 0.455, "step": 3922 }, { "epoch": 4.393203883495145, "grad_norm": 0.936687171459198, "learning_rate": 8.590500067242449e-07, "loss": 0.4626, "step": 3923 }, { "epoch": 4.394324122479462, "grad_norm": 0.9379075169563293, "learning_rate": 8.579221048437145e-07, "loss": 0.4699, "step": 3924 }, { "epoch": 4.395444361463779, "grad_norm": 0.9209242463111877, "learning_rate": 8.567947905121313e-07, "loss": 0.4514, "step": 3925 }, { "epoch": 4.396564600448095, "grad_norm": 0.9357815980911255, "learning_rate": 8.556680641328577e-07, "loss": 0.4622, "step": 3926 }, { "epoch": 4.397684839432412, "grad_norm": 0.9293213486671448, "learning_rate": 8.545419261090449e-07, "loss": 0.4342, "step": 3927 }, { "epoch": 4.3988050784167285, "grad_norm": 0.9176010489463806, "learning_rate": 8.534163768436357e-07, "loss": 0.4328, "step": 3928 }, { "epoch": 4.3999253174010455, "grad_norm": 0.9091116786003113, "learning_rate": 8.522914167393598e-07, "loss": 0.4753, "step": 3929 }, { "epoch": 4.4010455563853625, "grad_norm": 0.9403444528579712, "learning_rate": 8.511670461987382e-07, "loss": 0.4372, "step": 3930 }, { "epoch": 4.402165795369679, "grad_norm": 0.9225047826766968, "learning_rate": 8.500432656240792e-07, "loss": 0.4619, "step": 3931 }, { "epoch": 4.403286034353996, "grad_norm": 0.9311700463294983, "learning_rate": 8.489200754174808e-07, "loss": 0.4485, "step": 3932 }, { "epoch": 4.404406273338312, "grad_norm": 0.9236305356025696, "learning_rate": 8.4779747598083e-07, "loss": 0.4614, "step": 3933 }, { "epoch": 4.405526512322629, "grad_norm": 0.9434030055999756, "learning_rate": 8.466754677158015e-07, "loss": 0.4385, "step": 3934 }, { "epoch": 4.406646751306946, "grad_norm": 0.8940929174423218, "learning_rate": 8.455540510238589e-07, "loss": 0.4386, "step": 3935 }, { "epoch": 4.407766990291262, "grad_norm": 0.9279996752738953, "learning_rate": 8.444332263062552e-07, "loss": 0.4453, "step": 3936 }, { "epoch": 4.408887229275579, "grad_norm": 0.9136689305305481, "learning_rate": 8.433129939640303e-07, "loss": 0.4462, "step": 3937 }, { "epoch": 4.410007468259895, "grad_norm": 0.9012227058410645, "learning_rate": 8.421933543980126e-07, "loss": 0.4512, "step": 3938 }, { "epoch": 4.411127707244212, "grad_norm": 0.9336970448493958, "learning_rate": 8.41074308008818e-07, "loss": 0.448, "step": 3939 }, { "epoch": 4.412247946228529, "grad_norm": 0.9353033304214478, "learning_rate": 8.399558551968501e-07, "loss": 0.473, "step": 3940 }, { "epoch": 4.413368185212845, "grad_norm": 0.9533092975616455, "learning_rate": 8.388379963623017e-07, "loss": 0.4514, "step": 3941 }, { "epoch": 4.414488424197162, "grad_norm": 0.9156346321105957, "learning_rate": 8.377207319051503e-07, "loss": 0.4298, "step": 3942 }, { "epoch": 4.415608663181478, "grad_norm": 0.8919798731803894, "learning_rate": 8.366040622251642e-07, "loss": 0.4325, "step": 3943 }, { "epoch": 4.416728902165795, "grad_norm": 0.9079018235206604, "learning_rate": 8.35487987721896e-07, "loss": 0.4407, "step": 3944 }, { "epoch": 4.417849141150112, "grad_norm": 0.9259285926818848, "learning_rate": 8.343725087946861e-07, "loss": 0.453, "step": 3945 }, { "epoch": 4.4189693801344285, "grad_norm": 0.9586077928543091, "learning_rate": 8.332576258426625e-07, "loss": 0.4603, "step": 3946 }, { "epoch": 4.4200896191187455, "grad_norm": 0.9165776968002319, "learning_rate": 8.32143339264739e-07, "loss": 0.4459, "step": 3947 }, { "epoch": 4.421209858103062, "grad_norm": 0.9017254710197449, "learning_rate": 8.310296494596159e-07, "loss": 0.4448, "step": 3948 }, { "epoch": 4.422330097087379, "grad_norm": 0.9146921038627625, "learning_rate": 8.299165568257822e-07, "loss": 0.4506, "step": 3949 }, { "epoch": 4.423450336071696, "grad_norm": 0.938081681728363, "learning_rate": 8.288040617615106e-07, "loss": 0.4703, "step": 3950 }, { "epoch": 4.424570575056012, "grad_norm": 0.9301877021789551, "learning_rate": 8.276921646648614e-07, "loss": 0.4595, "step": 3951 }, { "epoch": 4.425690814040329, "grad_norm": 0.8962886333465576, "learning_rate": 8.2658086593368e-07, "loss": 0.4459, "step": 3952 }, { "epoch": 4.426811053024645, "grad_norm": 0.9233502149581909, "learning_rate": 8.254701659655973e-07, "loss": 0.4668, "step": 3953 }, { "epoch": 4.427931292008962, "grad_norm": 0.9387287497520447, "learning_rate": 8.24360065158033e-07, "loss": 0.4611, "step": 3954 }, { "epoch": 4.429051530993279, "grad_norm": 0.926816999912262, "learning_rate": 8.232505639081892e-07, "loss": 0.456, "step": 3955 }, { "epoch": 4.430171769977595, "grad_norm": 0.9437996745109558, "learning_rate": 8.221416626130538e-07, "loss": 0.4574, "step": 3956 }, { "epoch": 4.431292008961912, "grad_norm": 0.9375920295715332, "learning_rate": 8.210333616694025e-07, "loss": 0.4364, "step": 3957 }, { "epoch": 4.432412247946228, "grad_norm": 0.9229516386985779, "learning_rate": 8.199256614737933e-07, "loss": 0.4819, "step": 3958 }, { "epoch": 4.433532486930545, "grad_norm": 0.9640870094299316, "learning_rate": 8.188185624225709e-07, "loss": 0.4621, "step": 3959 }, { "epoch": 4.434652725914862, "grad_norm": 0.9205599427223206, "learning_rate": 8.177120649118638e-07, "loss": 0.4622, "step": 3960 }, { "epoch": 4.435772964899178, "grad_norm": 0.9467553496360779, "learning_rate": 8.166061693375865e-07, "loss": 0.4825, "step": 3961 }, { "epoch": 4.436893203883495, "grad_norm": 0.9333498477935791, "learning_rate": 8.155008760954366e-07, "loss": 0.4545, "step": 3962 }, { "epoch": 4.4380134428678115, "grad_norm": 0.9351642727851868, "learning_rate": 8.143961855808985e-07, "loss": 0.4524, "step": 3963 }, { "epoch": 4.4391336818521285, "grad_norm": 0.9442983269691467, "learning_rate": 8.13292098189239e-07, "loss": 0.4761, "step": 3964 }, { "epoch": 4.4402539208364455, "grad_norm": 0.9126826524734497, "learning_rate": 8.121886143155092e-07, "loss": 0.4379, "step": 3965 }, { "epoch": 4.441374159820762, "grad_norm": 0.9414904117584229, "learning_rate": 8.110857343545448e-07, "loss": 0.4542, "step": 3966 }, { "epoch": 4.442494398805079, "grad_norm": 0.9439902305603027, "learning_rate": 8.099834587009648e-07, "loss": 0.4477, "step": 3967 }, { "epoch": 4.443614637789395, "grad_norm": 0.9214082360267639, "learning_rate": 8.08881787749174e-07, "loss": 0.4474, "step": 3968 }, { "epoch": 4.444734876773712, "grad_norm": 0.9016152024269104, "learning_rate": 8.077807218933576e-07, "loss": 0.444, "step": 3969 }, { "epoch": 4.445855115758029, "grad_norm": 0.9295966625213623, "learning_rate": 8.066802615274875e-07, "loss": 0.4484, "step": 3970 }, { "epoch": 4.446975354742345, "grad_norm": 0.9449937343597412, "learning_rate": 8.055804070453166e-07, "loss": 0.4729, "step": 3971 }, { "epoch": 4.448095593726662, "grad_norm": 0.9329589605331421, "learning_rate": 8.044811588403823e-07, "loss": 0.4668, "step": 3972 }, { "epoch": 4.449215832710978, "grad_norm": 0.9021746516227722, "learning_rate": 8.033825173060044e-07, "loss": 0.4379, "step": 3973 }, { "epoch": 4.450336071695295, "grad_norm": 0.935158908367157, "learning_rate": 8.022844828352857e-07, "loss": 0.4531, "step": 3974 }, { "epoch": 4.451456310679612, "grad_norm": 0.9230673909187317, "learning_rate": 8.011870558211113e-07, "loss": 0.4733, "step": 3975 }, { "epoch": 4.452576549663928, "grad_norm": 0.9744884967803955, "learning_rate": 8.000902366561511e-07, "loss": 0.4626, "step": 3976 }, { "epoch": 4.453696788648245, "grad_norm": 0.9312717318534851, "learning_rate": 7.989940257328552e-07, "loss": 0.44, "step": 3977 }, { "epoch": 4.454817027632561, "grad_norm": 0.9059916138648987, "learning_rate": 7.97898423443457e-07, "loss": 0.4561, "step": 3978 }, { "epoch": 4.455937266616878, "grad_norm": 0.9089498519897461, "learning_rate": 7.968034301799718e-07, "loss": 0.43, "step": 3979 }, { "epoch": 4.4570575056011945, "grad_norm": 0.9078904390335083, "learning_rate": 7.957090463341966e-07, "loss": 0.4349, "step": 3980 }, { "epoch": 4.4581777445855115, "grad_norm": 0.9066845178604126, "learning_rate": 7.946152722977124e-07, "loss": 0.4784, "step": 3981 }, { "epoch": 4.4592979835698285, "grad_norm": 0.9676226377487183, "learning_rate": 7.935221084618797e-07, "loss": 0.4561, "step": 3982 }, { "epoch": 4.460418222554145, "grad_norm": 0.9135673642158508, "learning_rate": 7.924295552178404e-07, "loss": 0.4502, "step": 3983 }, { "epoch": 4.461538461538462, "grad_norm": 0.9110312461853027, "learning_rate": 7.913376129565215e-07, "loss": 0.44, "step": 3984 }, { "epoch": 4.462658700522778, "grad_norm": 0.9248620867729187, "learning_rate": 7.902462820686272e-07, "loss": 0.4433, "step": 3985 }, { "epoch": 4.463778939507095, "grad_norm": 0.9411587715148926, "learning_rate": 7.891555629446451e-07, "loss": 0.4696, "step": 3986 }, { "epoch": 4.464899178491412, "grad_norm": 0.9733886122703552, "learning_rate": 7.880654559748432e-07, "loss": 0.4319, "step": 3987 }, { "epoch": 4.466019417475728, "grad_norm": 0.9340497255325317, "learning_rate": 7.869759615492709e-07, "loss": 0.4595, "step": 3988 }, { "epoch": 4.467139656460045, "grad_norm": 0.9520411491394043, "learning_rate": 7.858870800577576e-07, "loss": 0.4533, "step": 3989 }, { "epoch": 4.468259895444361, "grad_norm": 1.0182439088821411, "learning_rate": 7.847988118899153e-07, "loss": 0.4763, "step": 3990 }, { "epoch": 4.469380134428678, "grad_norm": 0.9602058529853821, "learning_rate": 7.837111574351344e-07, "loss": 0.4705, "step": 3991 }, { "epoch": 4.470500373412995, "grad_norm": 0.9420186877250671, "learning_rate": 7.826241170825871e-07, "loss": 0.441, "step": 3992 }, { "epoch": 4.471620612397311, "grad_norm": 0.9969696998596191, "learning_rate": 7.815376912212244e-07, "loss": 0.4613, "step": 3993 }, { "epoch": 4.472740851381628, "grad_norm": 0.930493950843811, "learning_rate": 7.804518802397795e-07, "loss": 0.4719, "step": 3994 }, { "epoch": 4.473861090365944, "grad_norm": 0.918645441532135, "learning_rate": 7.793666845267645e-07, "loss": 0.4679, "step": 3995 }, { "epoch": 4.474981329350261, "grad_norm": 0.9158954620361328, "learning_rate": 7.782821044704697e-07, "loss": 0.4562, "step": 3996 }, { "epoch": 4.476101568334578, "grad_norm": 0.8986881971359253, "learning_rate": 7.771981404589687e-07, "loss": 0.4378, "step": 3997 }, { "epoch": 4.4772218073188945, "grad_norm": 0.8984370827674866, "learning_rate": 7.761147928801122e-07, "loss": 0.4682, "step": 3998 }, { "epoch": 4.4783420463032115, "grad_norm": 0.9423932433128357, "learning_rate": 7.750320621215304e-07, "loss": 0.4639, "step": 3999 }, { "epoch": 4.479462285287528, "grad_norm": 0.9170299768447876, "learning_rate": 7.739499485706334e-07, "loss": 0.4327, "step": 4000 }, { "epoch": 4.480582524271845, "grad_norm": 0.9333274960517883, "learning_rate": 7.728684526146104e-07, "loss": 0.4436, "step": 4001 }, { "epoch": 4.481702763256162, "grad_norm": 0.9157150983810425, "learning_rate": 7.717875746404288e-07, "loss": 0.4272, "step": 4002 }, { "epoch": 4.482823002240478, "grad_norm": 0.8999400734901428, "learning_rate": 7.707073150348371e-07, "loss": 0.4608, "step": 4003 }, { "epoch": 4.483943241224795, "grad_norm": 0.9434642791748047, "learning_rate": 7.696276741843603e-07, "loss": 0.4675, "step": 4004 }, { "epoch": 4.485063480209111, "grad_norm": 0.9312248229980469, "learning_rate": 7.685486524753025e-07, "loss": 0.4606, "step": 4005 }, { "epoch": 4.486183719193428, "grad_norm": 0.9177544116973877, "learning_rate": 7.674702502937462e-07, "loss": 0.4607, "step": 4006 }, { "epoch": 4.487303958177745, "grad_norm": 0.9298065304756165, "learning_rate": 7.663924680255536e-07, "loss": 0.4512, "step": 4007 }, { "epoch": 4.488424197162061, "grad_norm": 0.9174136519432068, "learning_rate": 7.653153060563636e-07, "loss": 0.4198, "step": 4008 }, { "epoch": 4.489544436146378, "grad_norm": 0.9146814346313477, "learning_rate": 7.642387647715935e-07, "loss": 0.4417, "step": 4009 }, { "epoch": 4.490664675130694, "grad_norm": 0.9238666892051697, "learning_rate": 7.631628445564379e-07, "loss": 0.4353, "step": 4010 }, { "epoch": 4.491784914115011, "grad_norm": 0.8992002606391907, "learning_rate": 7.620875457958712e-07, "loss": 0.4628, "step": 4011 }, { "epoch": 4.492905153099328, "grad_norm": 0.9524484872817993, "learning_rate": 7.610128688746438e-07, "loss": 0.4539, "step": 4012 }, { "epoch": 4.494025392083644, "grad_norm": 0.9194216728210449, "learning_rate": 7.599388141772835e-07, "loss": 0.4666, "step": 4013 }, { "epoch": 4.495145631067961, "grad_norm": 0.9262797832489014, "learning_rate": 7.588653820880959e-07, "loss": 0.4583, "step": 4014 }, { "epoch": 4.4962658700522775, "grad_norm": 0.9279083609580994, "learning_rate": 7.577925729911642e-07, "loss": 0.4687, "step": 4015 }, { "epoch": 4.4973861090365945, "grad_norm": 0.9582187533378601, "learning_rate": 7.567203872703471e-07, "loss": 0.4522, "step": 4016 }, { "epoch": 4.4985063480209115, "grad_norm": 0.9156298637390137, "learning_rate": 7.556488253092834e-07, "loss": 0.4353, "step": 4017 }, { "epoch": 4.499626587005228, "grad_norm": 0.9353978633880615, "learning_rate": 7.545778874913853e-07, "loss": 0.464, "step": 4018 }, { "epoch": 4.500746825989545, "grad_norm": 0.9300918579101562, "learning_rate": 7.535075741998441e-07, "loss": 0.4514, "step": 4019 }, { "epoch": 4.501867064973861, "grad_norm": 0.9217422604560852, "learning_rate": 7.524378858176251e-07, "loss": 0.4533, "step": 4020 }, { "epoch": 4.502987303958178, "grad_norm": 0.9345660209655762, "learning_rate": 7.513688227274735e-07, "loss": 0.4498, "step": 4021 }, { "epoch": 4.504107542942494, "grad_norm": 0.9420390129089355, "learning_rate": 7.503003853119079e-07, "loss": 0.4638, "step": 4022 }, { "epoch": 4.505227781926811, "grad_norm": 0.9541316032409668, "learning_rate": 7.492325739532233e-07, "loss": 0.4323, "step": 4023 }, { "epoch": 4.506348020911128, "grad_norm": 0.9045413732528687, "learning_rate": 7.481653890334931e-07, "loss": 0.4687, "step": 4024 }, { "epoch": 4.507468259895444, "grad_norm": 0.9245474338531494, "learning_rate": 7.47098830934564e-07, "loss": 0.461, "step": 4025 }, { "epoch": 4.508588498879761, "grad_norm": 0.9387688040733337, "learning_rate": 7.460329000380586e-07, "loss": 0.4543, "step": 4026 }, { "epoch": 4.509708737864077, "grad_norm": 0.9194440841674805, "learning_rate": 7.449675967253766e-07, "loss": 0.4424, "step": 4027 }, { "epoch": 4.510828976848394, "grad_norm": 0.9143329858779907, "learning_rate": 7.439029213776919e-07, "loss": 0.4318, "step": 4028 }, { "epoch": 4.511949215832711, "grad_norm": 0.9193657636642456, "learning_rate": 7.428388743759532e-07, "loss": 0.4368, "step": 4029 }, { "epoch": 4.513069454817027, "grad_norm": 0.9206281304359436, "learning_rate": 7.41775456100887e-07, "loss": 0.4433, "step": 4030 }, { "epoch": 4.514189693801344, "grad_norm": 0.915283739566803, "learning_rate": 7.407126669329922e-07, "loss": 0.4316, "step": 4031 }, { "epoch": 4.5153099327856605, "grad_norm": 0.9029337763786316, "learning_rate": 7.396505072525434e-07, "loss": 0.4853, "step": 4032 }, { "epoch": 4.5164301717699775, "grad_norm": 0.9544621706008911, "learning_rate": 7.385889774395894e-07, "loss": 0.4715, "step": 4033 }, { "epoch": 4.5175504107542945, "grad_norm": 0.9304721355438232, "learning_rate": 7.375280778739557e-07, "loss": 0.4209, "step": 4034 }, { "epoch": 4.518670649738611, "grad_norm": 0.8884122967720032, "learning_rate": 7.364678089352406e-07, "loss": 0.4388, "step": 4035 }, { "epoch": 4.519790888722928, "grad_norm": 0.9325547814369202, "learning_rate": 7.354081710028155e-07, "loss": 0.4534, "step": 4036 }, { "epoch": 4.520911127707244, "grad_norm": 0.9428514242172241, "learning_rate": 7.343491644558296e-07, "loss": 0.4804, "step": 4037 }, { "epoch": 4.522031366691561, "grad_norm": 0.9327054619789124, "learning_rate": 7.33290789673203e-07, "loss": 0.4659, "step": 4038 }, { "epoch": 4.523151605675878, "grad_norm": 0.9265029430389404, "learning_rate": 7.322330470336314e-07, "loss": 0.436, "step": 4039 }, { "epoch": 4.524271844660194, "grad_norm": 0.9146674275398254, "learning_rate": 7.311759369155833e-07, "loss": 0.4679, "step": 4040 }, { "epoch": 4.525392083644511, "grad_norm": 0.9492097496986389, "learning_rate": 7.301194596973015e-07, "loss": 0.4644, "step": 4041 }, { "epoch": 4.526512322628827, "grad_norm": 0.9374755024909973, "learning_rate": 7.290636157568026e-07, "loss": 0.4541, "step": 4042 }, { "epoch": 4.527632561613144, "grad_norm": 0.9189525842666626, "learning_rate": 7.28008405471875e-07, "loss": 0.4344, "step": 4043 }, { "epoch": 4.528752800597461, "grad_norm": 0.910369873046875, "learning_rate": 7.269538292200831e-07, "loss": 0.4406, "step": 4044 }, { "epoch": 4.529873039581777, "grad_norm": 0.9067758917808533, "learning_rate": 7.258998873787626e-07, "loss": 0.4695, "step": 4045 }, { "epoch": 4.530993278566094, "grad_norm": 0.9400776624679565, "learning_rate": 7.248465803250215e-07, "loss": 0.4328, "step": 4046 }, { "epoch": 4.53211351755041, "grad_norm": 0.9275671243667603, "learning_rate": 7.237939084357432e-07, "loss": 0.4575, "step": 4047 }, { "epoch": 4.533233756534727, "grad_norm": 0.9497599005699158, "learning_rate": 7.227418720875814e-07, "loss": 0.4678, "step": 4048 }, { "epoch": 4.534353995519044, "grad_norm": 0.9599676132202148, "learning_rate": 7.216904716569639e-07, "loss": 0.4603, "step": 4049 }, { "epoch": 4.5354742345033605, "grad_norm": 0.9488062262535095, "learning_rate": 7.206397075200894e-07, "loss": 0.4596, "step": 4050 }, { "epoch": 4.5365944734876775, "grad_norm": 0.9216565489768982, "learning_rate": 7.195895800529309e-07, "loss": 0.4529, "step": 4051 }, { "epoch": 4.537714712471994, "grad_norm": 0.8997254967689514, "learning_rate": 7.185400896312328e-07, "loss": 0.438, "step": 4052 }, { "epoch": 4.538834951456311, "grad_norm": 0.9356870055198669, "learning_rate": 7.174912366305109e-07, "loss": 0.4505, "step": 4053 }, { "epoch": 4.539955190440628, "grad_norm": 0.9269409775733948, "learning_rate": 7.164430214260532e-07, "loss": 0.4781, "step": 4054 }, { "epoch": 4.541075429424944, "grad_norm": 0.9434599280357361, "learning_rate": 7.153954443929201e-07, "loss": 0.4523, "step": 4055 }, { "epoch": 4.542195668409261, "grad_norm": 0.931302547454834, "learning_rate": 7.143485059059424e-07, "loss": 0.4325, "step": 4056 }, { "epoch": 4.543315907393577, "grad_norm": 0.8985020518302917, "learning_rate": 7.133022063397247e-07, "loss": 0.4464, "step": 4057 }, { "epoch": 4.544436146377894, "grad_norm": 0.926993191242218, "learning_rate": 7.122565460686407e-07, "loss": 0.4472, "step": 4058 }, { "epoch": 4.545556385362211, "grad_norm": 0.9082745313644409, "learning_rate": 7.112115254668356e-07, "loss": 0.4383, "step": 4059 }, { "epoch": 4.546676624346527, "grad_norm": 0.9431625604629517, "learning_rate": 7.101671449082281e-07, "loss": 0.4727, "step": 4060 }, { "epoch": 4.547796863330844, "grad_norm": 0.9235348105430603, "learning_rate": 7.091234047665052e-07, "loss": 0.4297, "step": 4061 }, { "epoch": 4.54891710231516, "grad_norm": 0.8915677666664124, "learning_rate": 7.080803054151255e-07, "loss": 0.4525, "step": 4062 }, { "epoch": 4.550037341299477, "grad_norm": 0.9577835202217102, "learning_rate": 7.070378472273178e-07, "loss": 0.4685, "step": 4063 }, { "epoch": 4.551157580283794, "grad_norm": 0.9395867586135864, "learning_rate": 7.05996030576084e-07, "loss": 0.4603, "step": 4064 }, { "epoch": 4.55227781926811, "grad_norm": 0.9289235472679138, "learning_rate": 7.049548558341937e-07, "loss": 0.4636, "step": 4065 }, { "epoch": 4.553398058252427, "grad_norm": 0.958153486251831, "learning_rate": 7.039143233741877e-07, "loss": 0.4565, "step": 4066 }, { "epoch": 4.5545182972367435, "grad_norm": 0.8998987078666687, "learning_rate": 7.028744335683774e-07, "loss": 0.4521, "step": 4067 }, { "epoch": 4.5556385362210605, "grad_norm": 0.8992881178855896, "learning_rate": 7.018351867888434e-07, "loss": 0.4434, "step": 4068 }, { "epoch": 4.5567587752053775, "grad_norm": 0.9401063919067383, "learning_rate": 7.007965834074362e-07, "loss": 0.4559, "step": 4069 }, { "epoch": 4.557879014189694, "grad_norm": 0.937838077545166, "learning_rate": 6.997586237957782e-07, "loss": 0.4656, "step": 4070 }, { "epoch": 4.558999253174011, "grad_norm": 0.9157642722129822, "learning_rate": 6.987213083252589e-07, "loss": 0.4397, "step": 4071 }, { "epoch": 4.560119492158327, "grad_norm": 0.925748348236084, "learning_rate": 6.976846373670384e-07, "loss": 0.4478, "step": 4072 }, { "epoch": 4.561239731142644, "grad_norm": 0.908306896686554, "learning_rate": 6.966486112920456e-07, "loss": 0.4475, "step": 4073 }, { "epoch": 4.562359970126961, "grad_norm": 0.9561427235603333, "learning_rate": 6.956132304709804e-07, "loss": 0.44, "step": 4074 }, { "epoch": 4.563480209111277, "grad_norm": 0.9267794489860535, "learning_rate": 6.945784952743095e-07, "loss": 0.4299, "step": 4075 }, { "epoch": 4.564600448095594, "grad_norm": 0.9157537221908569, "learning_rate": 6.935444060722702e-07, "loss": 0.432, "step": 4076 }, { "epoch": 4.56572068707991, "grad_norm": 0.9326803088188171, "learning_rate": 6.92510963234867e-07, "loss": 0.4514, "step": 4077 }, { "epoch": 4.566840926064227, "grad_norm": 0.9216866493225098, "learning_rate": 6.914781671318757e-07, "loss": 0.4499, "step": 4078 }, { "epoch": 4.567961165048544, "grad_norm": 0.9382017254829407, "learning_rate": 6.904460181328387e-07, "loss": 0.4711, "step": 4079 }, { "epoch": 4.56908140403286, "grad_norm": 0.9096110463142395, "learning_rate": 6.894145166070673e-07, "loss": 0.4452, "step": 4080 }, { "epoch": 4.570201643017177, "grad_norm": 0.9343985915184021, "learning_rate": 6.883836629236412e-07, "loss": 0.4212, "step": 4081 }, { "epoch": 4.571321882001493, "grad_norm": 0.9278212189674377, "learning_rate": 6.873534574514082e-07, "loss": 0.4615, "step": 4082 }, { "epoch": 4.57244212098581, "grad_norm": 0.9517315030097961, "learning_rate": 6.863239005589836e-07, "loss": 0.4508, "step": 4083 }, { "epoch": 4.573562359970127, "grad_norm": 0.9245662689208984, "learning_rate": 6.852949926147531e-07, "loss": 0.4609, "step": 4084 }, { "epoch": 4.5746825989544435, "grad_norm": 0.9293527603149414, "learning_rate": 6.842667339868673e-07, "loss": 0.4428, "step": 4085 }, { "epoch": 4.5758028379387605, "grad_norm": 0.9278512001037598, "learning_rate": 6.832391250432447e-07, "loss": 0.4386, "step": 4086 }, { "epoch": 4.576923076923077, "grad_norm": 0.8991295099258423, "learning_rate": 6.82212166151574e-07, "loss": 0.4672, "step": 4087 }, { "epoch": 4.578043315907394, "grad_norm": 0.9402008056640625, "learning_rate": 6.811858576793088e-07, "loss": 0.4532, "step": 4088 }, { "epoch": 4.579163554891711, "grad_norm": 0.933037281036377, "learning_rate": 6.801601999936704e-07, "loss": 0.4473, "step": 4089 }, { "epoch": 4.580283793876027, "grad_norm": 0.9198400378227234, "learning_rate": 6.791351934616469e-07, "loss": 0.4392, "step": 4090 }, { "epoch": 4.581404032860344, "grad_norm": 0.9474571943283081, "learning_rate": 6.781108384499959e-07, "loss": 0.4564, "step": 4091 }, { "epoch": 4.58252427184466, "grad_norm": 0.9360840916633606, "learning_rate": 6.770871353252389e-07, "loss": 0.4572, "step": 4092 }, { "epoch": 4.583644510828977, "grad_norm": 0.9070881009101868, "learning_rate": 6.760640844536654e-07, "loss": 0.4376, "step": 4093 }, { "epoch": 4.584764749813294, "grad_norm": 0.916980504989624, "learning_rate": 6.750416862013312e-07, "loss": 0.4686, "step": 4094 }, { "epoch": 4.58588498879761, "grad_norm": 0.9142171740531921, "learning_rate": 6.740199409340592e-07, "loss": 0.4547, "step": 4095 }, { "epoch": 4.587005227781927, "grad_norm": 0.9384877681732178, "learning_rate": 6.729988490174371e-07, "loss": 0.4411, "step": 4096 }, { "epoch": 4.588125466766243, "grad_norm": 0.9221807718276978, "learning_rate": 6.719784108168217e-07, "loss": 0.4578, "step": 4097 }, { "epoch": 4.58924570575056, "grad_norm": 0.907423734664917, "learning_rate": 6.709586266973334e-07, "loss": 0.4259, "step": 4098 }, { "epoch": 4.590365944734877, "grad_norm": 0.9186950922012329, "learning_rate": 6.699394970238584e-07, "loss": 0.4544, "step": 4099 }, { "epoch": 4.591486183719193, "grad_norm": 0.9061620831489563, "learning_rate": 6.689210221610514e-07, "loss": 0.447, "step": 4100 }, { "epoch": 4.59260642270351, "grad_norm": 0.933733344078064, "learning_rate": 6.6790320247333e-07, "loss": 0.4583, "step": 4101 }, { "epoch": 4.5937266616878265, "grad_norm": 0.9531727433204651, "learning_rate": 6.668860383248787e-07, "loss": 0.4451, "step": 4102 }, { "epoch": 4.5948469006721435, "grad_norm": 0.9165147542953491, "learning_rate": 6.658695300796472e-07, "loss": 0.4622, "step": 4103 }, { "epoch": 4.5959671396564605, "grad_norm": 0.9480270743370056, "learning_rate": 6.648536781013496e-07, "loss": 0.4655, "step": 4104 }, { "epoch": 4.597087378640777, "grad_norm": 0.9341945648193359, "learning_rate": 6.638384827534677e-07, "loss": 0.4863, "step": 4105 }, { "epoch": 4.598207617625094, "grad_norm": 0.9378250241279602, "learning_rate": 6.628239443992457e-07, "loss": 0.4433, "step": 4106 }, { "epoch": 4.59932785660941, "grad_norm": 0.9318814277648926, "learning_rate": 6.618100634016941e-07, "loss": 0.4454, "step": 4107 }, { "epoch": 4.600448095593727, "grad_norm": 0.9068154096603394, "learning_rate": 6.607968401235876e-07, "loss": 0.4228, "step": 4108 }, { "epoch": 4.601568334578043, "grad_norm": 0.918131411075592, "learning_rate": 6.597842749274661e-07, "loss": 0.4383, "step": 4109 }, { "epoch": 4.60268857356236, "grad_norm": 0.9226629734039307, "learning_rate": 6.587723681756325e-07, "loss": 0.4409, "step": 4110 }, { "epoch": 4.603808812546677, "grad_norm": 0.9304752945899963, "learning_rate": 6.577611202301573e-07, "loss": 0.4571, "step": 4111 }, { "epoch": 4.604929051530993, "grad_norm": 0.9301896095275879, "learning_rate": 6.567505314528716e-07, "loss": 0.469, "step": 4112 }, { "epoch": 4.60604929051531, "grad_norm": 0.9338796734809875, "learning_rate": 6.557406022053739e-07, "loss": 0.4682, "step": 4113 }, { "epoch": 4.607169529499626, "grad_norm": 0.9308931231498718, "learning_rate": 6.547313328490243e-07, "loss": 0.4677, "step": 4114 }, { "epoch": 4.608289768483943, "grad_norm": 0.9474345445632935, "learning_rate": 6.537227237449482e-07, "loss": 0.4461, "step": 4115 }, { "epoch": 4.60941000746826, "grad_norm": 0.9112251400947571, "learning_rate": 6.527147752540334e-07, "loss": 0.4445, "step": 4116 }, { "epoch": 4.610530246452576, "grad_norm": 0.9181135296821594, "learning_rate": 6.517074877369317e-07, "loss": 0.4705, "step": 4117 }, { "epoch": 4.611650485436893, "grad_norm": 0.9425850510597229, "learning_rate": 6.507008615540606e-07, "loss": 0.4659, "step": 4118 }, { "epoch": 4.6127707244212095, "grad_norm": 0.9453258514404297, "learning_rate": 6.496948970655984e-07, "loss": 0.4529, "step": 4119 }, { "epoch": 4.6138909634055265, "grad_norm": 0.9168641567230225, "learning_rate": 6.486895946314872e-07, "loss": 0.4477, "step": 4120 }, { "epoch": 4.6150112023898435, "grad_norm": 0.9573792219161987, "learning_rate": 6.476849546114325e-07, "loss": 0.4666, "step": 4121 }, { "epoch": 4.61613144137416, "grad_norm": 0.9489296674728394, "learning_rate": 6.46680977364903e-07, "loss": 0.4435, "step": 4122 }, { "epoch": 4.617251680358477, "grad_norm": 0.9462327361106873, "learning_rate": 6.456776632511292e-07, "loss": 0.4728, "step": 4123 }, { "epoch": 4.618371919342793, "grad_norm": 0.956041693687439, "learning_rate": 6.446750126291062e-07, "loss": 0.449, "step": 4124 }, { "epoch": 4.61949215832711, "grad_norm": 0.927935004234314, "learning_rate": 6.436730258575904e-07, "loss": 0.4547, "step": 4125 }, { "epoch": 4.620612397311427, "grad_norm": 0.9211587309837341, "learning_rate": 6.426717032950999e-07, "loss": 0.4474, "step": 4126 }, { "epoch": 4.621732636295743, "grad_norm": 0.9410001039505005, "learning_rate": 6.416710452999176e-07, "loss": 0.4514, "step": 4127 }, { "epoch": 4.62285287528006, "grad_norm": 0.9120239019393921, "learning_rate": 6.406710522300863e-07, "loss": 0.4454, "step": 4128 }, { "epoch": 4.623973114264376, "grad_norm": 0.9053131937980652, "learning_rate": 6.396717244434122e-07, "loss": 0.4347, "step": 4129 }, { "epoch": 4.625093353248693, "grad_norm": 0.9306976795196533, "learning_rate": 6.386730622974624e-07, "loss": 0.4431, "step": 4130 }, { "epoch": 4.62621359223301, "grad_norm": 0.924906849861145, "learning_rate": 6.376750661495662e-07, "loss": 0.4689, "step": 4131 }, { "epoch": 4.627333831217326, "grad_norm": 0.9340663552284241, "learning_rate": 6.366777363568158e-07, "loss": 0.4589, "step": 4132 }, { "epoch": 4.628454070201643, "grad_norm": 0.9242619276046753, "learning_rate": 6.356810732760635e-07, "loss": 0.4293, "step": 4133 }, { "epoch": 4.629574309185959, "grad_norm": 0.8920029997825623, "learning_rate": 6.346850772639235e-07, "loss": 0.4243, "step": 4134 }, { "epoch": 4.630694548170276, "grad_norm": 0.9328439831733704, "learning_rate": 6.336897486767712e-07, "loss": 0.4594, "step": 4135 }, { "epoch": 4.6318147871545925, "grad_norm": 0.9390574097633362, "learning_rate": 6.326950878707439e-07, "loss": 0.4393, "step": 4136 }, { "epoch": 4.6329350261389095, "grad_norm": 0.8989868760108948, "learning_rate": 6.31701095201738e-07, "loss": 0.4465, "step": 4137 }, { "epoch": 4.6340552651232265, "grad_norm": 0.9282209277153015, "learning_rate": 6.307077710254139e-07, "loss": 0.4401, "step": 4138 }, { "epoch": 4.635175504107543, "grad_norm": 0.9029422998428345, "learning_rate": 6.297151156971898e-07, "loss": 0.4441, "step": 4139 }, { "epoch": 4.63629574309186, "grad_norm": 0.9351640939712524, "learning_rate": 6.28723129572247e-07, "loss": 0.4454, "step": 4140 }, { "epoch": 4.637415982076176, "grad_norm": 0.9223535656929016, "learning_rate": 6.277318130055263e-07, "loss": 0.4508, "step": 4141 }, { "epoch": 4.638536221060493, "grad_norm": 0.939888596534729, "learning_rate": 6.267411663517284e-07, "loss": 0.4421, "step": 4142 }, { "epoch": 4.63965646004481, "grad_norm": 0.9215380549430847, "learning_rate": 6.257511899653146e-07, "loss": 0.4452, "step": 4143 }, { "epoch": 4.640776699029126, "grad_norm": 0.9330728650093079, "learning_rate": 6.247618842005063e-07, "loss": 0.4543, "step": 4144 }, { "epoch": 4.641896938013443, "grad_norm": 0.9415512681007385, "learning_rate": 6.237732494112866e-07, "loss": 0.4512, "step": 4145 }, { "epoch": 4.643017176997759, "grad_norm": 0.9665389060974121, "learning_rate": 6.227852859513961e-07, "loss": 0.4522, "step": 4146 }, { "epoch": 4.644137415982076, "grad_norm": 0.9520583152770996, "learning_rate": 6.217979941743366e-07, "loss": 0.4666, "step": 4147 }, { "epoch": 4.645257654966393, "grad_norm": 0.9470130801200867, "learning_rate": 6.208113744333688e-07, "loss": 0.4806, "step": 4148 }, { "epoch": 4.646377893950709, "grad_norm": 0.9219042062759399, "learning_rate": 6.198254270815138e-07, "loss": 0.4439, "step": 4149 }, { "epoch": 4.647498132935026, "grad_norm": 0.9146936535835266, "learning_rate": 6.188401524715506e-07, "loss": 0.4383, "step": 4150 }, { "epoch": 4.648618371919342, "grad_norm": 0.9611854553222656, "learning_rate": 6.178555509560202e-07, "loss": 0.4576, "step": 4151 }, { "epoch": 4.649738610903659, "grad_norm": 0.9029427170753479, "learning_rate": 6.168716228872193e-07, "loss": 0.4534, "step": 4152 }, { "epoch": 4.650858849887976, "grad_norm": 0.9538477063179016, "learning_rate": 6.158883686172073e-07, "loss": 0.4439, "step": 4153 }, { "epoch": 4.6519790888722925, "grad_norm": 0.916519820690155, "learning_rate": 6.149057884978e-07, "loss": 0.4373, "step": 4154 }, { "epoch": 4.6530993278566095, "grad_norm": 0.9270740747451782, "learning_rate": 6.139238828805722e-07, "loss": 0.4824, "step": 4155 }, { "epoch": 4.654219566840926, "grad_norm": 0.9201117157936096, "learning_rate": 6.12942652116858e-07, "loss": 0.4643, "step": 4156 }, { "epoch": 4.655339805825243, "grad_norm": 0.9329781532287598, "learning_rate": 6.119620965577488e-07, "loss": 0.4424, "step": 4157 }, { "epoch": 4.65646004480956, "grad_norm": 0.9231156706809998, "learning_rate": 6.109822165540974e-07, "loss": 0.4545, "step": 4158 }, { "epoch": 4.657580283793876, "grad_norm": 0.9108720421791077, "learning_rate": 6.10003012456512e-07, "loss": 0.4733, "step": 4159 }, { "epoch": 4.658700522778193, "grad_norm": 0.9762923717498779, "learning_rate": 6.090244846153598e-07, "loss": 0.4605, "step": 4160 }, { "epoch": 4.659820761762509, "grad_norm": 0.8982598185539246, "learning_rate": 6.080466333807658e-07, "loss": 0.4669, "step": 4161 }, { "epoch": 4.660941000746826, "grad_norm": 0.9342713952064514, "learning_rate": 6.070694591026139e-07, "loss": 0.4483, "step": 4162 }, { "epoch": 4.662061239731143, "grad_norm": 0.9454380869865417, "learning_rate": 6.060929621305445e-07, "loss": 0.4527, "step": 4163 }, { "epoch": 4.663181478715459, "grad_norm": 0.9224340915679932, "learning_rate": 6.051171428139554e-07, "loss": 0.4436, "step": 4164 }, { "epoch": 4.664301717699776, "grad_norm": 0.915353000164032, "learning_rate": 6.041420015020041e-07, "loss": 0.4678, "step": 4165 }, { "epoch": 4.665421956684092, "grad_norm": 0.9488824605941772, "learning_rate": 6.031675385436042e-07, "loss": 0.4522, "step": 4166 }, { "epoch": 4.666542195668409, "grad_norm": 0.9321189522743225, "learning_rate": 6.021937542874265e-07, "loss": 0.4715, "step": 4167 }, { "epoch": 4.667662434652726, "grad_norm": 0.9300811886787415, "learning_rate": 6.012206490818987e-07, "loss": 0.4405, "step": 4168 }, { "epoch": 4.668782673637042, "grad_norm": 0.9205108880996704, "learning_rate": 6.002482232752055e-07, "loss": 0.4622, "step": 4169 }, { "epoch": 4.669902912621359, "grad_norm": 0.9342342019081116, "learning_rate": 5.992764772152892e-07, "loss": 0.4307, "step": 4170 }, { "epoch": 4.6710231516056755, "grad_norm": 0.9267442226409912, "learning_rate": 5.983054112498476e-07, "loss": 0.4792, "step": 4171 }, { "epoch": 4.6721433905899925, "grad_norm": 0.9508010149002075, "learning_rate": 5.97335025726338e-07, "loss": 0.4499, "step": 4172 }, { "epoch": 4.6732636295743095, "grad_norm": 0.9332929253578186, "learning_rate": 5.963653209919709e-07, "loss": 0.4676, "step": 4173 }, { "epoch": 4.674383868558626, "grad_norm": 0.9306592345237732, "learning_rate": 5.953962973937153e-07, "loss": 0.4448, "step": 4174 }, { "epoch": 4.675504107542943, "grad_norm": 0.946811318397522, "learning_rate": 5.94427955278295e-07, "loss": 0.4602, "step": 4175 }, { "epoch": 4.676624346527259, "grad_norm": 0.9560580849647522, "learning_rate": 5.934602949921914e-07, "loss": 0.4375, "step": 4176 }, { "epoch": 4.677744585511576, "grad_norm": 0.897026538848877, "learning_rate": 5.924933168816402e-07, "loss": 0.4458, "step": 4177 }, { "epoch": 4.678864824495893, "grad_norm": 0.9498981237411499, "learning_rate": 5.915270212926357e-07, "loss": 0.4571, "step": 4178 }, { "epoch": 4.679985063480209, "grad_norm": 0.9241230487823486, "learning_rate": 5.905614085709252e-07, "loss": 0.4548, "step": 4179 }, { "epoch": 4.681105302464526, "grad_norm": 0.931291937828064, "learning_rate": 5.895964790620137e-07, "loss": 0.4599, "step": 4180 }, { "epoch": 4.682225541448842, "grad_norm": 0.9431935548782349, "learning_rate": 5.886322331111608e-07, "loss": 0.4708, "step": 4181 }, { "epoch": 4.683345780433159, "grad_norm": 0.924246609210968, "learning_rate": 5.876686710633811e-07, "loss": 0.4512, "step": 4182 }, { "epoch": 4.684466019417476, "grad_norm": 0.9105916023254395, "learning_rate": 5.867057932634454e-07, "loss": 0.4389, "step": 4183 }, { "epoch": 4.685586258401792, "grad_norm": 0.9375534653663635, "learning_rate": 5.857436000558783e-07, "loss": 0.4318, "step": 4184 }, { "epoch": 4.686706497386109, "grad_norm": 0.902471661567688, "learning_rate": 5.84782091784962e-07, "loss": 0.4398, "step": 4185 }, { "epoch": 4.687826736370425, "grad_norm": 0.9046571850776672, "learning_rate": 5.838212687947314e-07, "loss": 0.4571, "step": 4186 }, { "epoch": 4.688946975354742, "grad_norm": 0.9131209850311279, "learning_rate": 5.828611314289768e-07, "loss": 0.4377, "step": 4187 }, { "epoch": 4.690067214339059, "grad_norm": 0.9439789652824402, "learning_rate": 5.81901680031243e-07, "loss": 0.445, "step": 4188 }, { "epoch": 4.6911874533233755, "grad_norm": 0.8982759118080139, "learning_rate": 5.809429149448298e-07, "loss": 0.433, "step": 4189 }, { "epoch": 4.6923076923076925, "grad_norm": 0.9293617606163025, "learning_rate": 5.799848365127906e-07, "loss": 0.4899, "step": 4190 }, { "epoch": 4.693427931292009, "grad_norm": 0.9288709759712219, "learning_rate": 5.790274450779349e-07, "loss": 0.4404, "step": 4191 }, { "epoch": 4.694548170276326, "grad_norm": 1.0062428712844849, "learning_rate": 5.780707409828237e-07, "loss": 0.4577, "step": 4192 }, { "epoch": 4.695668409260643, "grad_norm": 0.9465816617012024, "learning_rate": 5.771147245697756e-07, "loss": 0.4572, "step": 4193 }, { "epoch": 4.696788648244959, "grad_norm": 0.9431334137916565, "learning_rate": 5.761593961808598e-07, "loss": 0.4466, "step": 4194 }, { "epoch": 4.697908887229276, "grad_norm": 0.9252429008483887, "learning_rate": 5.752047561579008e-07, "loss": 0.42, "step": 4195 }, { "epoch": 4.699029126213592, "grad_norm": 0.9466513991355896, "learning_rate": 5.742508048424769e-07, "loss": 0.4596, "step": 4196 }, { "epoch": 4.700149365197909, "grad_norm": 0.9422347545623779, "learning_rate": 5.732975425759194e-07, "loss": 0.468, "step": 4197 }, { "epoch": 4.701269604182226, "grad_norm": 0.9394080638885498, "learning_rate": 5.723449696993127e-07, "loss": 0.4442, "step": 4198 }, { "epoch": 4.702389843166542, "grad_norm": 0.904458224773407, "learning_rate": 5.713930865534967e-07, "loss": 0.4415, "step": 4199 }, { "epoch": 4.703510082150859, "grad_norm": 0.9322583675384521, "learning_rate": 5.70441893479062e-07, "loss": 0.4323, "step": 4200 }, { "epoch": 4.704630321135175, "grad_norm": 0.9412566423416138, "learning_rate": 5.694913908163541e-07, "loss": 0.4653, "step": 4201 }, { "epoch": 4.705750560119492, "grad_norm": 0.9187472462654114, "learning_rate": 5.685415789054696e-07, "loss": 0.4734, "step": 4202 }, { "epoch": 4.706870799103809, "grad_norm": 0.9653197526931763, "learning_rate": 5.675924580862596e-07, "loss": 0.4353, "step": 4203 }, { "epoch": 4.707991038088125, "grad_norm": 0.9244787693023682, "learning_rate": 5.666440286983266e-07, "loss": 0.4725, "step": 4204 }, { "epoch": 4.709111277072442, "grad_norm": 0.9237177968025208, "learning_rate": 5.656962910810271e-07, "loss": 0.4559, "step": 4205 }, { "epoch": 4.7102315160567585, "grad_norm": 0.9188477396965027, "learning_rate": 5.647492455734699e-07, "loss": 0.4573, "step": 4206 }, { "epoch": 4.7113517550410755, "grad_norm": 0.9334102272987366, "learning_rate": 5.63802892514515e-07, "loss": 0.4447, "step": 4207 }, { "epoch": 4.7124719940253925, "grad_norm": 0.9301485419273376, "learning_rate": 5.628572322427755e-07, "loss": 0.4433, "step": 4208 }, { "epoch": 4.713592233009709, "grad_norm": 0.9197728633880615, "learning_rate": 5.619122650966164e-07, "loss": 0.4365, "step": 4209 }, { "epoch": 4.714712471994026, "grad_norm": 0.9701607823371887, "learning_rate": 5.609679914141545e-07, "loss": 0.4835, "step": 4210 }, { "epoch": 4.715832710978342, "grad_norm": 0.9289963841438293, "learning_rate": 5.600244115332579e-07, "loss": 0.4262, "step": 4211 }, { "epoch": 4.716952949962659, "grad_norm": 0.9190040230751038, "learning_rate": 5.590815257915489e-07, "loss": 0.4479, "step": 4212 }, { "epoch": 4.718073188946976, "grad_norm": 0.911891520023346, "learning_rate": 5.581393345263989e-07, "loss": 0.4682, "step": 4213 }, { "epoch": 4.719193427931292, "grad_norm": 0.9162346720695496, "learning_rate": 5.571978380749315e-07, "loss": 0.4637, "step": 4214 }, { "epoch": 4.720313666915609, "grad_norm": 0.9542143940925598, "learning_rate": 5.562570367740225e-07, "loss": 0.4633, "step": 4215 }, { "epoch": 4.721433905899925, "grad_norm": 0.9570946097373962, "learning_rate": 5.553169309602977e-07, "loss": 0.4739, "step": 4216 }, { "epoch": 4.722554144884242, "grad_norm": 0.940455973148346, "learning_rate": 5.543775209701341e-07, "loss": 0.4549, "step": 4217 }, { "epoch": 4.723674383868559, "grad_norm": 0.9529620409011841, "learning_rate": 5.534388071396616e-07, "loss": 0.4549, "step": 4218 }, { "epoch": 4.724794622852875, "grad_norm": 0.9247485995292664, "learning_rate": 5.525007898047588e-07, "loss": 0.4326, "step": 4219 }, { "epoch": 4.725914861837192, "grad_norm": 0.9098039269447327, "learning_rate": 5.515634693010569e-07, "loss": 0.4345, "step": 4220 }, { "epoch": 4.727035100821508, "grad_norm": 0.8979451060295105, "learning_rate": 5.506268459639363e-07, "loss": 0.4422, "step": 4221 }, { "epoch": 4.728155339805825, "grad_norm": 0.945388913154602, "learning_rate": 5.496909201285286e-07, "loss": 0.442, "step": 4222 }, { "epoch": 4.729275578790142, "grad_norm": 0.9156926870346069, "learning_rate": 5.487556921297157e-07, "loss": 0.441, "step": 4223 }, { "epoch": 4.7303958177744585, "grad_norm": 0.9001674056053162, "learning_rate": 5.478211623021302e-07, "loss": 0.4573, "step": 4224 }, { "epoch": 4.7315160567587755, "grad_norm": 0.9436423182487488, "learning_rate": 5.468873309801531e-07, "loss": 0.4559, "step": 4225 }, { "epoch": 4.732636295743092, "grad_norm": 0.9061970710754395, "learning_rate": 5.459541984979188e-07, "loss": 0.4464, "step": 4226 }, { "epoch": 4.733756534727409, "grad_norm": 0.9565758109092712, "learning_rate": 5.450217651893088e-07, "loss": 0.4799, "step": 4227 }, { "epoch": 4.734876773711726, "grad_norm": 0.9667009115219116, "learning_rate": 5.44090031387956e-07, "loss": 0.4604, "step": 4228 }, { "epoch": 4.735997012696042, "grad_norm": 0.9131165146827698, "learning_rate": 5.431589974272417e-07, "loss": 0.4402, "step": 4229 }, { "epoch": 4.737117251680359, "grad_norm": 0.9102067947387695, "learning_rate": 5.422286636402976e-07, "loss": 0.4642, "step": 4230 }, { "epoch": 4.738237490664675, "grad_norm": 0.9412233233451843, "learning_rate": 5.412990303600047e-07, "loss": 0.4642, "step": 4231 }, { "epoch": 4.739357729648992, "grad_norm": 0.9252609014511108, "learning_rate": 5.403700979189933e-07, "loss": 0.466, "step": 4232 }, { "epoch": 4.740477968633308, "grad_norm": 0.9651368856430054, "learning_rate": 5.39441866649644e-07, "loss": 0.4498, "step": 4233 }, { "epoch": 4.741598207617625, "grad_norm": 0.9044222235679626, "learning_rate": 5.385143368840851e-07, "loss": 0.4783, "step": 4234 }, { "epoch": 4.742718446601942, "grad_norm": 0.9301649928092957, "learning_rate": 5.375875089541943e-07, "loss": 0.4443, "step": 4235 }, { "epoch": 4.743838685586258, "grad_norm": 0.9100770354270935, "learning_rate": 5.366613831915979e-07, "loss": 0.4161, "step": 4236 }, { "epoch": 4.744958924570575, "grad_norm": 0.9203270077705383, "learning_rate": 5.357359599276718e-07, "loss": 0.4313, "step": 4237 }, { "epoch": 4.746079163554891, "grad_norm": 0.911040186882019, "learning_rate": 5.348112394935389e-07, "loss": 0.4582, "step": 4238 }, { "epoch": 4.747199402539208, "grad_norm": 0.9069752097129822, "learning_rate": 5.338872222200736e-07, "loss": 0.4621, "step": 4239 }, { "epoch": 4.748319641523525, "grad_norm": 0.9648212790489197, "learning_rate": 5.32963908437896e-07, "loss": 0.4464, "step": 4240 }, { "epoch": 4.7494398805078415, "grad_norm": 0.9476554989814758, "learning_rate": 5.320412984773749e-07, "loss": 0.4575, "step": 4241 }, { "epoch": 4.7505601194921585, "grad_norm": 0.9315900802612305, "learning_rate": 5.311193926686281e-07, "loss": 0.4646, "step": 4242 }, { "epoch": 4.751680358476475, "grad_norm": 0.9503670334815979, "learning_rate": 5.301981913415214e-07, "loss": 0.4471, "step": 4243 }, { "epoch": 4.752800597460792, "grad_norm": 0.9189484119415283, "learning_rate": 5.29277694825667e-07, "loss": 0.4341, "step": 4244 }, { "epoch": 4.753920836445109, "grad_norm": 0.9251331686973572, "learning_rate": 5.283579034504274e-07, "loss": 0.4533, "step": 4245 }, { "epoch": 4.755041075429425, "grad_norm": 0.9415379166603088, "learning_rate": 5.274388175449108e-07, "loss": 0.4299, "step": 4246 }, { "epoch": 4.756161314413742, "grad_norm": 0.9226387143135071, "learning_rate": 5.265204374379742e-07, "loss": 0.4362, "step": 4247 }, { "epoch": 4.757281553398058, "grad_norm": 0.915391206741333, "learning_rate": 5.256027634582214e-07, "loss": 0.4505, "step": 4248 }, { "epoch": 4.758401792382375, "grad_norm": 0.912260890007019, "learning_rate": 5.246857959340037e-07, "loss": 0.4677, "step": 4249 }, { "epoch": 4.759522031366692, "grad_norm": 0.9425484538078308, "learning_rate": 5.237695351934194e-07, "loss": 0.4366, "step": 4250 }, { "epoch": 4.760642270351008, "grad_norm": 0.9065099358558655, "learning_rate": 5.228539815643141e-07, "loss": 0.4585, "step": 4251 }, { "epoch": 4.761762509335325, "grad_norm": 0.9208546280860901, "learning_rate": 5.219391353742797e-07, "loss": 0.4441, "step": 4252 }, { "epoch": 4.762882748319641, "grad_norm": 0.9290627837181091, "learning_rate": 5.210249969506573e-07, "loss": 0.4412, "step": 4253 }, { "epoch": 4.764002987303958, "grad_norm": 0.9171655774116516, "learning_rate": 5.201115666205322e-07, "loss": 0.4536, "step": 4254 }, { "epoch": 4.765123226288274, "grad_norm": 0.9140334129333496, "learning_rate": 5.191988447107374e-07, "loss": 0.4518, "step": 4255 }, { "epoch": 4.766243465272591, "grad_norm": 0.9370642900466919, "learning_rate": 5.182868315478523e-07, "loss": 0.4791, "step": 4256 }, { "epoch": 4.767363704256908, "grad_norm": 0.9483113288879395, "learning_rate": 5.173755274582026e-07, "loss": 0.4383, "step": 4257 }, { "epoch": 4.7684839432412245, "grad_norm": 0.9247336983680725, "learning_rate": 5.164649327678597e-07, "loss": 0.4474, "step": 4258 }, { "epoch": 4.7696041822255415, "grad_norm": 0.9022761583328247, "learning_rate": 5.155550478026425e-07, "loss": 0.4599, "step": 4259 }, { "epoch": 4.770724421209858, "grad_norm": 0.9432147145271301, "learning_rate": 5.146458728881162e-07, "loss": 0.4482, "step": 4260 }, { "epoch": 4.771844660194175, "grad_norm": 0.920450747013092, "learning_rate": 5.137374083495902e-07, "loss": 0.4379, "step": 4261 }, { "epoch": 4.772964899178492, "grad_norm": 0.9478771686553955, "learning_rate": 5.128296545121205e-07, "loss": 0.4431, "step": 4262 }, { "epoch": 4.774085138162808, "grad_norm": 0.9522843360900879, "learning_rate": 5.119226117005088e-07, "loss": 0.4565, "step": 4263 }, { "epoch": 4.775205377147125, "grad_norm": 0.9081900715827942, "learning_rate": 5.110162802393029e-07, "loss": 0.4572, "step": 4264 }, { "epoch": 4.776325616131441, "grad_norm": 0.9320151209831238, "learning_rate": 5.101106604527947e-07, "loss": 0.4599, "step": 4265 }, { "epoch": 4.777445855115758, "grad_norm": 0.9217603802680969, "learning_rate": 5.092057526650235e-07, "loss": 0.4519, "step": 4266 }, { "epoch": 4.778566094100075, "grad_norm": 0.9558967351913452, "learning_rate": 5.083015571997726e-07, "loss": 0.472, "step": 4267 }, { "epoch": 4.779686333084391, "grad_norm": 0.9504961371421814, "learning_rate": 5.073980743805701e-07, "loss": 0.4458, "step": 4268 }, { "epoch": 4.780806572068708, "grad_norm": 0.9087985157966614, "learning_rate": 5.064953045306895e-07, "loss": 0.4423, "step": 4269 }, { "epoch": 4.781926811053024, "grad_norm": 0.9232906699180603, "learning_rate": 5.055932479731498e-07, "loss": 0.4485, "step": 4270 }, { "epoch": 4.783047050037341, "grad_norm": 0.9189038276672363, "learning_rate": 5.046919050307131e-07, "loss": 0.4512, "step": 4271 }, { "epoch": 4.784167289021658, "grad_norm": 0.9199354648590088, "learning_rate": 5.037912760258881e-07, "loss": 0.4701, "step": 4272 }, { "epoch": 4.785287528005974, "grad_norm": 0.9477493762969971, "learning_rate": 5.028913612809278e-07, "loss": 0.4499, "step": 4273 }, { "epoch": 4.786407766990291, "grad_norm": 0.9463195204734802, "learning_rate": 5.019921611178288e-07, "loss": 0.4791, "step": 4274 }, { "epoch": 4.7875280059746075, "grad_norm": 0.948776364326477, "learning_rate": 5.010936758583318e-07, "loss": 0.4377, "step": 4275 }, { "epoch": 4.7886482449589245, "grad_norm": 0.9141539335250854, "learning_rate": 5.001959058239226e-07, "loss": 0.4531, "step": 4276 }, { "epoch": 4.7897684839432415, "grad_norm": 0.9105619192123413, "learning_rate": 4.992988513358305e-07, "loss": 0.4452, "step": 4277 }, { "epoch": 4.790888722927558, "grad_norm": 0.9315118193626404, "learning_rate": 4.984025127150289e-07, "loss": 0.4318, "step": 4278 }, { "epoch": 4.792008961911875, "grad_norm": 0.9412029981613159, "learning_rate": 4.975068902822347e-07, "loss": 0.4414, "step": 4279 }, { "epoch": 4.793129200896191, "grad_norm": 0.9294340014457703, "learning_rate": 4.966119843579101e-07, "loss": 0.4556, "step": 4280 }, { "epoch": 4.794249439880508, "grad_norm": 0.9536522030830383, "learning_rate": 4.957177952622588e-07, "loss": 0.4566, "step": 4281 }, { "epoch": 4.795369678864825, "grad_norm": 0.9378076195716858, "learning_rate": 4.948243233152297e-07, "loss": 0.4476, "step": 4282 }, { "epoch": 4.796489917849141, "grad_norm": 0.9063238501548767, "learning_rate": 4.93931568836514e-07, "loss": 0.4718, "step": 4283 }, { "epoch": 4.797610156833458, "grad_norm": 0.9453621506690979, "learning_rate": 4.930395321455466e-07, "loss": 0.4684, "step": 4284 }, { "epoch": 4.798730395817774, "grad_norm": 0.9396647810935974, "learning_rate": 4.921482135615049e-07, "loss": 0.4294, "step": 4285 }, { "epoch": 4.799850634802091, "grad_norm": 0.9044017195701599, "learning_rate": 4.912576134033107e-07, "loss": 0.4704, "step": 4286 }, { "epoch": 4.800970873786408, "grad_norm": 0.934414803981781, "learning_rate": 4.903677319896286e-07, "loss": 0.4466, "step": 4287 }, { "epoch": 4.802091112770724, "grad_norm": 0.9290842413902283, "learning_rate": 4.894785696388646e-07, "loss": 0.457, "step": 4288 }, { "epoch": 4.803211351755041, "grad_norm": 0.9248275756835938, "learning_rate": 4.88590126669169e-07, "loss": 0.4472, "step": 4289 }, { "epoch": 4.804331590739357, "grad_norm": 0.9523053765296936, "learning_rate": 4.877024033984334e-07, "loss": 0.4894, "step": 4290 }, { "epoch": 4.805451829723674, "grad_norm": 0.9456274509429932, "learning_rate": 4.868154001442926e-07, "loss": 0.4553, "step": 4291 }, { "epoch": 4.806572068707991, "grad_norm": 0.9505539536476135, "learning_rate": 4.859291172241232e-07, "loss": 0.4716, "step": 4292 }, { "epoch": 4.8076923076923075, "grad_norm": 0.9239053726196289, "learning_rate": 4.850435549550452e-07, "loss": 0.4422, "step": 4293 }, { "epoch": 4.8088125466766245, "grad_norm": 0.916587233543396, "learning_rate": 4.841587136539202e-07, "loss": 0.4401, "step": 4294 }, { "epoch": 4.809932785660941, "grad_norm": 0.890791118144989, "learning_rate": 4.832745936373512e-07, "loss": 0.4596, "step": 4295 }, { "epoch": 4.811053024645258, "grad_norm": 0.9477200508117676, "learning_rate": 4.823911952216836e-07, "loss": 0.4236, "step": 4296 }, { "epoch": 4.812173263629575, "grad_norm": 0.9055647850036621, "learning_rate": 4.81508518723005e-07, "loss": 0.4652, "step": 4297 }, { "epoch": 4.813293502613891, "grad_norm": 0.9267839193344116, "learning_rate": 4.806265644571432e-07, "loss": 0.4376, "step": 4298 }, { "epoch": 4.814413741598208, "grad_norm": 0.9169793128967285, "learning_rate": 4.797453327396695e-07, "loss": 0.4768, "step": 4299 }, { "epoch": 4.815533980582524, "grad_norm": 1.036017894744873, "learning_rate": 4.788648238858962e-07, "loss": 0.4444, "step": 4300 }, { "epoch": 4.816654219566841, "grad_norm": 0.921283483505249, "learning_rate": 4.779850382108764e-07, "loss": 0.4422, "step": 4301 }, { "epoch": 4.817774458551158, "grad_norm": 0.9319873452186584, "learning_rate": 4.771059760294045e-07, "loss": 0.4626, "step": 4302 }, { "epoch": 4.818894697535474, "grad_norm": 0.9589232206344604, "learning_rate": 4.76227637656016e-07, "loss": 0.4437, "step": 4303 }, { "epoch": 4.820014936519791, "grad_norm": 0.9246066808700562, "learning_rate": 4.753500234049879e-07, "loss": 0.4705, "step": 4304 }, { "epoch": 4.821135175504107, "grad_norm": 0.9548112154006958, "learning_rate": 4.7447313359033656e-07, "loss": 0.4233, "step": 4305 }, { "epoch": 4.822255414488424, "grad_norm": 0.904656708240509, "learning_rate": 4.735969685258224e-07, "loss": 0.4243, "step": 4306 }, { "epoch": 4.823375653472741, "grad_norm": 0.9241160750389099, "learning_rate": 4.727215285249431e-07, "loss": 0.4469, "step": 4307 }, { "epoch": 4.824495892457057, "grad_norm": 0.9491055607795715, "learning_rate": 4.718468139009388e-07, "loss": 0.4653, "step": 4308 }, { "epoch": 4.825616131441374, "grad_norm": 0.9176377654075623, "learning_rate": 4.7097282496678944e-07, "loss": 0.4529, "step": 4309 }, { "epoch": 4.8267363704256905, "grad_norm": 0.942794144153595, "learning_rate": 4.7009956203521503e-07, "loss": 0.4744, "step": 4310 }, { "epoch": 4.8278566094100075, "grad_norm": 0.9388131499290466, "learning_rate": 4.692270254186762e-07, "loss": 0.453, "step": 4311 }, { "epoch": 4.8289768483943245, "grad_norm": 0.932212233543396, "learning_rate": 4.6835521542937466e-07, "loss": 0.4492, "step": 4312 }, { "epoch": 4.830097087378641, "grad_norm": 0.923444390296936, "learning_rate": 4.674841323792498e-07, "loss": 0.4565, "step": 4313 }, { "epoch": 4.831217326362958, "grad_norm": 0.9487971067428589, "learning_rate": 4.6661377657998385e-07, "loss": 0.4526, "step": 4314 }, { "epoch": 4.832337565347274, "grad_norm": 0.9103789925575256, "learning_rate": 4.657441483429964e-07, "loss": 0.4439, "step": 4315 }, { "epoch": 4.833457804331591, "grad_norm": 0.9323000907897949, "learning_rate": 4.6487524797944774e-07, "loss": 0.4498, "step": 4316 }, { "epoch": 4.834578043315908, "grad_norm": 0.9388090968132019, "learning_rate": 4.640070758002374e-07, "loss": 0.4633, "step": 4317 }, { "epoch": 4.835698282300224, "grad_norm": 0.9469848871231079, "learning_rate": 4.6313963211600475e-07, "loss": 0.4448, "step": 4318 }, { "epoch": 4.836818521284541, "grad_norm": 0.9239835143089294, "learning_rate": 4.622729172371271e-07, "loss": 0.4364, "step": 4319 }, { "epoch": 4.837938760268857, "grad_norm": 0.9262151718139648, "learning_rate": 4.6140693147372407e-07, "loss": 0.4661, "step": 4320 }, { "epoch": 4.839058999253174, "grad_norm": 0.9190468192100525, "learning_rate": 4.6054167513565143e-07, "loss": 0.454, "step": 4321 }, { "epoch": 4.840179238237491, "grad_norm": 0.9476306438446045, "learning_rate": 4.5967714853250497e-07, "loss": 0.4453, "step": 4322 }, { "epoch": 4.841299477221807, "grad_norm": 0.9208006262779236, "learning_rate": 4.588133519736196e-07, "loss": 0.4384, "step": 4323 }, { "epoch": 4.842419716206124, "grad_norm": 0.9087784886360168, "learning_rate": 4.579502857680687e-07, "loss": 0.4683, "step": 4324 }, { "epoch": 4.84353995519044, "grad_norm": 0.9601429104804993, "learning_rate": 4.5708795022466416e-07, "loss": 0.4408, "step": 4325 }, { "epoch": 4.844660194174757, "grad_norm": 0.899463415145874, "learning_rate": 4.562263456519567e-07, "loss": 0.4444, "step": 4326 }, { "epoch": 4.845780433159074, "grad_norm": 0.9055320024490356, "learning_rate": 4.553654723582365e-07, "loss": 0.4521, "step": 4327 }, { "epoch": 4.8469006721433905, "grad_norm": 0.9372832775115967, "learning_rate": 4.5450533065153066e-07, "loss": 0.4346, "step": 4328 }, { "epoch": 4.8480209111277075, "grad_norm": 0.898810625076294, "learning_rate": 4.5364592083960464e-07, "loss": 0.45, "step": 4329 }, { "epoch": 4.849141150112024, "grad_norm": 0.9188463687896729, "learning_rate": 4.527872432299624e-07, "loss": 0.4231, "step": 4330 }, { "epoch": 4.850261389096341, "grad_norm": 0.9319808483123779, "learning_rate": 4.5192929812984564e-07, "loss": 0.4361, "step": 4331 }, { "epoch": 4.851381628080658, "grad_norm": 0.9291864037513733, "learning_rate": 4.510720858462339e-07, "loss": 0.4633, "step": 4332 }, { "epoch": 4.852501867064974, "grad_norm": 0.9364126324653625, "learning_rate": 4.50215606685846e-07, "loss": 0.4559, "step": 4333 }, { "epoch": 4.853622106049291, "grad_norm": 0.9302451014518738, "learning_rate": 4.493598609551364e-07, "loss": 0.4498, "step": 4334 }, { "epoch": 4.854742345033607, "grad_norm": 0.9591974020004272, "learning_rate": 4.4850484896029775e-07, "loss": 0.4341, "step": 4335 }, { "epoch": 4.855862584017924, "grad_norm": 0.9584932327270508, "learning_rate": 4.476505710072607e-07, "loss": 0.4268, "step": 4336 }, { "epoch": 4.856982823002241, "grad_norm": 0.9187148809432983, "learning_rate": 4.4679702740169306e-07, "loss": 0.4421, "step": 4337 }, { "epoch": 4.858103061986557, "grad_norm": 0.9255461096763611, "learning_rate": 4.4594421844899844e-07, "loss": 0.4743, "step": 4338 }, { "epoch": 4.859223300970874, "grad_norm": 0.9655919075012207, "learning_rate": 4.45092144454321e-07, "loss": 0.4437, "step": 4339 }, { "epoch": 4.86034353995519, "grad_norm": 0.9140148162841797, "learning_rate": 4.442408057225378e-07, "loss": 0.4555, "step": 4340 }, { "epoch": 4.861463778939507, "grad_norm": 0.9566812515258789, "learning_rate": 4.433902025582665e-07, "loss": 0.4549, "step": 4341 }, { "epoch": 4.862584017923824, "grad_norm": 0.9526204466819763, "learning_rate": 4.4254033526585917e-07, "loss": 0.4547, "step": 4342 }, { "epoch": 4.86370425690814, "grad_norm": 0.9460614919662476, "learning_rate": 4.416912041494051e-07, "loss": 0.4057, "step": 4343 }, { "epoch": 4.864824495892457, "grad_norm": 0.8953962922096252, "learning_rate": 4.408428095127307e-07, "loss": 0.4603, "step": 4344 }, { "epoch": 4.8659447348767735, "grad_norm": 0.9057366251945496, "learning_rate": 4.399951516593984e-07, "loss": 0.4535, "step": 4345 }, { "epoch": 4.8670649738610905, "grad_norm": 0.949625551700592, "learning_rate": 4.391482308927067e-07, "loss": 0.4751, "step": 4346 }, { "epoch": 4.8681852128454075, "grad_norm": 0.9475857615470886, "learning_rate": 4.3830204751569157e-07, "loss": 0.4552, "step": 4347 }, { "epoch": 4.869305451829724, "grad_norm": 0.8984320759773254, "learning_rate": 4.374566018311241e-07, "loss": 0.4304, "step": 4348 }, { "epoch": 4.870425690814041, "grad_norm": 0.9531437158584595, "learning_rate": 4.3661189414151176e-07, "loss": 0.4575, "step": 4349 }, { "epoch": 4.871545929798357, "grad_norm": 0.9300970435142517, "learning_rate": 4.3576792474909755e-07, "loss": 0.4165, "step": 4350 }, { "epoch": 4.872666168782674, "grad_norm": 0.9195587635040283, "learning_rate": 4.3492469395586044e-07, "loss": 0.4605, "step": 4351 }, { "epoch": 4.87378640776699, "grad_norm": 0.9189527034759521, "learning_rate": 4.34082202063516e-07, "loss": 0.4704, "step": 4352 }, { "epoch": 4.874906646751307, "grad_norm": 0.9538429379463196, "learning_rate": 4.332404493735143e-07, "loss": 0.4321, "step": 4353 }, { "epoch": 4.876026885735624, "grad_norm": 0.9246621131896973, "learning_rate": 4.323994361870421e-07, "loss": 0.4697, "step": 4354 }, { "epoch": 4.87714712471994, "grad_norm": 0.9305934309959412, "learning_rate": 4.3155916280502e-07, "loss": 0.4742, "step": 4355 }, { "epoch": 4.878267363704257, "grad_norm": 0.9238832592964172, "learning_rate": 4.307196295281052e-07, "loss": 0.448, "step": 4356 }, { "epoch": 4.879387602688573, "grad_norm": 0.9356378316879272, "learning_rate": 4.2988083665668924e-07, "loss": 0.4561, "step": 4357 }, { "epoch": 4.88050784167289, "grad_norm": 0.9160751104354858, "learning_rate": 4.2904278449089924e-07, "loss": 0.47, "step": 4358 }, { "epoch": 4.881628080657207, "grad_norm": 0.9258450865745544, "learning_rate": 4.282054733305965e-07, "loss": 0.433, "step": 4359 }, { "epoch": 4.882748319641523, "grad_norm": 0.9351587295532227, "learning_rate": 4.273689034753792e-07, "loss": 0.4529, "step": 4360 }, { "epoch": 4.88386855862584, "grad_norm": 0.923736035823822, "learning_rate": 4.2653307522457806e-07, "loss": 0.4766, "step": 4361 }, { "epoch": 4.8849887976101565, "grad_norm": 0.942572295665741, "learning_rate": 4.2569798887725944e-07, "loss": 0.4583, "step": 4362 }, { "epoch": 4.8861090365944735, "grad_norm": 0.9504854679107666, "learning_rate": 4.248636447322238e-07, "loss": 0.4555, "step": 4363 }, { "epoch": 4.8872292755787905, "grad_norm": 1.0231255292892456, "learning_rate": 4.240300430880062e-07, "loss": 0.4495, "step": 4364 }, { "epoch": 4.888349514563107, "grad_norm": 0.9118496775627136, "learning_rate": 4.23197184242877e-07, "loss": 0.4305, "step": 4365 }, { "epoch": 4.889469753547424, "grad_norm": 0.9120150208473206, "learning_rate": 4.2236506849483966e-07, "loss": 0.4647, "step": 4366 }, { "epoch": 4.89058999253174, "grad_norm": 0.9508500099182129, "learning_rate": 4.215336961416308e-07, "loss": 0.4694, "step": 4367 }, { "epoch": 4.891710231516057, "grad_norm": 0.9278097748756409, "learning_rate": 4.2070306748072414e-07, "loss": 0.4749, "step": 4368 }, { "epoch": 4.892830470500374, "grad_norm": 0.9223209619522095, "learning_rate": 4.1987318280932443e-07, "loss": 0.4518, "step": 4369 }, { "epoch": 4.89395070948469, "grad_norm": 0.9167549014091492, "learning_rate": 4.1904404242437137e-07, "loss": 0.4371, "step": 4370 }, { "epoch": 4.895070948469007, "grad_norm": 0.9249644875526428, "learning_rate": 4.1821564662253817e-07, "loss": 0.4498, "step": 4371 }, { "epoch": 4.896191187453323, "grad_norm": 0.9551383256912231, "learning_rate": 4.173879957002319e-07, "loss": 0.4376, "step": 4372 }, { "epoch": 4.89731142643764, "grad_norm": 0.9168882966041565, "learning_rate": 4.1656108995359154e-07, "loss": 0.4431, "step": 4373 }, { "epoch": 4.898431665421957, "grad_norm": 1.0189838409423828, "learning_rate": 4.157349296784927e-07, "loss": 0.4555, "step": 4374 }, { "epoch": 4.899551904406273, "grad_norm": 0.9273503422737122, "learning_rate": 4.149095151705415e-07, "loss": 0.4425, "step": 4375 }, { "epoch": 4.90067214339059, "grad_norm": 0.9047220349311829, "learning_rate": 4.140848467250777e-07, "loss": 0.455, "step": 4376 }, { "epoch": 4.901792382374906, "grad_norm": 0.9396485686302185, "learning_rate": 4.132609246371749e-07, "loss": 0.4283, "step": 4377 }, { "epoch": 4.902912621359223, "grad_norm": 0.9152921438217163, "learning_rate": 4.124377492016382e-07, "loss": 0.4343, "step": 4378 }, { "epoch": 4.9040328603435395, "grad_norm": 0.9590024352073669, "learning_rate": 4.1161532071300803e-07, "loss": 0.4713, "step": 4379 }, { "epoch": 4.9051530993278565, "grad_norm": 0.916021466255188, "learning_rate": 4.1079363946555457e-07, "loss": 0.4725, "step": 4380 }, { "epoch": 4.9062733383121735, "grad_norm": 0.9507703185081482, "learning_rate": 4.099727057532835e-07, "loss": 0.4654, "step": 4381 }, { "epoch": 4.90739357729649, "grad_norm": 0.9380786418914795, "learning_rate": 4.0915251986993086e-07, "loss": 0.4379, "step": 4382 }, { "epoch": 4.908513816280807, "grad_norm": 0.9078564643859863, "learning_rate": 4.083330821089662e-07, "loss": 0.4379, "step": 4383 }, { "epoch": 4.909634055265123, "grad_norm": 0.9434589743614197, "learning_rate": 4.0751439276359107e-07, "loss": 0.4467, "step": 4384 }, { "epoch": 4.91075429424944, "grad_norm": 0.9229798316955566, "learning_rate": 4.0669645212673884e-07, "loss": 0.471, "step": 4385 }, { "epoch": 4.911874533233757, "grad_norm": 0.9367823600769043, "learning_rate": 4.0587926049107497e-07, "loss": 0.4481, "step": 4386 }, { "epoch": 4.912994772218073, "grad_norm": 0.9278830885887146, "learning_rate": 4.0506281814899877e-07, "loss": 0.4368, "step": 4387 }, { "epoch": 4.91411501120239, "grad_norm": 0.9480023384094238, "learning_rate": 4.042471253926389e-07, "loss": 0.4545, "step": 4388 }, { "epoch": 4.915235250186706, "grad_norm": 0.9398188591003418, "learning_rate": 4.0343218251385765e-07, "loss": 0.4588, "step": 4389 }, { "epoch": 4.916355489171023, "grad_norm": 0.9381436109542847, "learning_rate": 4.026179898042476e-07, "loss": 0.4636, "step": 4390 }, { "epoch": 4.91747572815534, "grad_norm": 0.9219147562980652, "learning_rate": 4.0180454755513326e-07, "loss": 0.4441, "step": 4391 }, { "epoch": 4.918595967139656, "grad_norm": 0.9437147974967957, "learning_rate": 4.009918560575721e-07, "loss": 0.4591, "step": 4392 }, { "epoch": 4.919716206123973, "grad_norm": 0.9229478240013123, "learning_rate": 4.0017991560235084e-07, "loss": 0.447, "step": 4393 }, { "epoch": 4.920836445108289, "grad_norm": 0.9373252987861633, "learning_rate": 3.993687264799892e-07, "loss": 0.4716, "step": 4394 }, { "epoch": 4.921956684092606, "grad_norm": 0.9497496485710144, "learning_rate": 3.985582889807371e-07, "loss": 0.4543, "step": 4395 }, { "epoch": 4.923076923076923, "grad_norm": 0.9352072477340698, "learning_rate": 3.9774860339457546e-07, "loss": 0.4319, "step": 4396 }, { "epoch": 4.9241971620612395, "grad_norm": 0.9361475706100464, "learning_rate": 3.969396700112166e-07, "loss": 0.4433, "step": 4397 }, { "epoch": 4.9253174010455565, "grad_norm": 0.9261466264724731, "learning_rate": 3.9613148912010344e-07, "loss": 0.4644, "step": 4398 }, { "epoch": 4.926437640029873, "grad_norm": 0.9580411314964294, "learning_rate": 3.9532406101040975e-07, "loss": 0.4747, "step": 4399 }, { "epoch": 4.92755787901419, "grad_norm": 0.9282580614089966, "learning_rate": 3.9451738597103937e-07, "loss": 0.4686, "step": 4400 }, { "epoch": 4.928678117998507, "grad_norm": 0.9321779608726501, "learning_rate": 3.937114642906284e-07, "loss": 0.4644, "step": 4401 }, { "epoch": 4.929798356982823, "grad_norm": 0.9564039707183838, "learning_rate": 3.929062962575417e-07, "loss": 0.4304, "step": 4402 }, { "epoch": 4.93091859596714, "grad_norm": 0.9289804100990295, "learning_rate": 3.921018821598746e-07, "loss": 0.446, "step": 4403 }, { "epoch": 4.932038834951456, "grad_norm": 0.9363741278648376, "learning_rate": 3.9129822228545336e-07, "loss": 0.4286, "step": 4404 }, { "epoch": 4.933159073935773, "grad_norm": 0.9731482863426208, "learning_rate": 3.9049531692183423e-07, "loss": 0.4583, "step": 4405 }, { "epoch": 4.93427931292009, "grad_norm": 0.9337882995605469, "learning_rate": 3.896931663563036e-07, "loss": 0.4374, "step": 4406 }, { "epoch": 4.935399551904406, "grad_norm": 0.959056556224823, "learning_rate": 3.888917708758763e-07, "loss": 0.4596, "step": 4407 }, { "epoch": 4.936519790888723, "grad_norm": 0.9100942611694336, "learning_rate": 3.8809113076729994e-07, "loss": 0.4366, "step": 4408 }, { "epoch": 4.937640029873039, "grad_norm": 0.921071469783783, "learning_rate": 3.872912463170492e-07, "loss": 0.4583, "step": 4409 }, { "epoch": 4.938760268857356, "grad_norm": 0.9241031408309937, "learning_rate": 3.8649211781132926e-07, "loss": 0.4567, "step": 4410 }, { "epoch": 4.939880507841673, "grad_norm": 0.9210471510887146, "learning_rate": 3.8569374553607486e-07, "loss": 0.4294, "step": 4411 }, { "epoch": 4.941000746825989, "grad_norm": 0.9040893912315369, "learning_rate": 3.8489612977695045e-07, "loss": 0.4615, "step": 4412 }, { "epoch": 4.942120985810306, "grad_norm": 0.9190739989280701, "learning_rate": 3.8409927081934863e-07, "loss": 0.4248, "step": 4413 }, { "epoch": 4.9432412247946225, "grad_norm": 0.9190573692321777, "learning_rate": 3.833031689483932e-07, "loss": 0.4625, "step": 4414 }, { "epoch": 4.9443614637789395, "grad_norm": 0.9491841793060303, "learning_rate": 3.825078244489358e-07, "loss": 0.4655, "step": 4415 }, { "epoch": 4.9454817027632565, "grad_norm": 0.9264445304870605, "learning_rate": 3.8171323760555654e-07, "loss": 0.4408, "step": 4416 }, { "epoch": 4.946601941747573, "grad_norm": 0.9130584001541138, "learning_rate": 3.8091940870256525e-07, "loss": 0.455, "step": 4417 }, { "epoch": 4.94772218073189, "grad_norm": 0.9549928307533264, "learning_rate": 3.8012633802400084e-07, "loss": 0.4247, "step": 4418 }, { "epoch": 4.948842419716206, "grad_norm": 0.8888543844223022, "learning_rate": 3.7933402585363074e-07, "loss": 0.4655, "step": 4419 }, { "epoch": 4.949962658700523, "grad_norm": 0.9414843320846558, "learning_rate": 3.785424724749495e-07, "loss": 0.4853, "step": 4420 }, { "epoch": 4.95108289768484, "grad_norm": 0.9441660046577454, "learning_rate": 3.777516781711826e-07, "loss": 0.4516, "step": 4421 }, { "epoch": 4.952203136669156, "grad_norm": 0.9588351845741272, "learning_rate": 3.769616432252829e-07, "loss": 0.4369, "step": 4422 }, { "epoch": 4.953323375653473, "grad_norm": 0.9229773879051208, "learning_rate": 3.761723679199306e-07, "loss": 0.4436, "step": 4423 }, { "epoch": 4.954443614637789, "grad_norm": 0.9041887521743774, "learning_rate": 3.75383852537535e-07, "loss": 0.4587, "step": 4424 }, { "epoch": 4.955563853622106, "grad_norm": 0.9481687545776367, "learning_rate": 3.745960973602336e-07, "loss": 0.4335, "step": 4425 }, { "epoch": 4.956684092606423, "grad_norm": 0.9261795282363892, "learning_rate": 3.7380910266989116e-07, "loss": 0.4653, "step": 4426 }, { "epoch": 4.957804331590739, "grad_norm": 0.9398242235183716, "learning_rate": 3.7302286874810163e-07, "loss": 0.46, "step": 4427 }, { "epoch": 4.958924570575056, "grad_norm": 0.9530074596405029, "learning_rate": 3.7223739587618573e-07, "loss": 0.4289, "step": 4428 }, { "epoch": 4.960044809559372, "grad_norm": 0.9082716107368469, "learning_rate": 3.7145268433519175e-07, "loss": 0.4319, "step": 4429 }, { "epoch": 4.961165048543689, "grad_norm": 0.8991144895553589, "learning_rate": 3.7066873440589653e-07, "loss": 0.4517, "step": 4430 }, { "epoch": 4.962285287528006, "grad_norm": 0.9065014123916626, "learning_rate": 3.698855463688025e-07, "loss": 0.4589, "step": 4431 }, { "epoch": 4.9634055265123225, "grad_norm": 0.9363679885864258, "learning_rate": 3.6910312050414234e-07, "loss": 0.4439, "step": 4432 }, { "epoch": 4.9645257654966395, "grad_norm": 0.9318674802780151, "learning_rate": 3.6832145709187364e-07, "loss": 0.45, "step": 4433 }, { "epoch": 4.965646004480956, "grad_norm": 0.9239749312400818, "learning_rate": 3.675405564116816e-07, "loss": 0.4539, "step": 4434 }, { "epoch": 4.966766243465273, "grad_norm": 0.9601243138313293, "learning_rate": 3.667604187429802e-07, "loss": 0.4853, "step": 4435 }, { "epoch": 4.96788648244959, "grad_norm": 0.949225902557373, "learning_rate": 3.6598104436490786e-07, "loss": 0.4276, "step": 4436 }, { "epoch": 4.969006721433906, "grad_norm": 0.9397764801979065, "learning_rate": 3.65202433556332e-07, "loss": 0.4643, "step": 4437 }, { "epoch": 4.970126960418223, "grad_norm": 0.9268552660942078, "learning_rate": 3.644245865958451e-07, "loss": 0.4364, "step": 4438 }, { "epoch": 4.971247199402539, "grad_norm": 0.9209022521972656, "learning_rate": 3.636475037617679e-07, "loss": 0.4364, "step": 4439 }, { "epoch": 4.972367438386856, "grad_norm": 0.9267597794532776, "learning_rate": 3.628711853321462e-07, "loss": 0.4409, "step": 4440 }, { "epoch": 4.973487677371173, "grad_norm": 0.9307511448860168, "learning_rate": 3.6209563158475404e-07, "loss": 0.4701, "step": 4441 }, { "epoch": 4.974607916355489, "grad_norm": 0.9287337064743042, "learning_rate": 3.613208427970907e-07, "loss": 0.4764, "step": 4442 }, { "epoch": 4.975728155339806, "grad_norm": 0.9813134074211121, "learning_rate": 3.6054681924638154e-07, "loss": 0.4381, "step": 4443 }, { "epoch": 4.976848394324122, "grad_norm": 0.938197135925293, "learning_rate": 3.5977356120957845e-07, "loss": 0.4492, "step": 4444 }, { "epoch": 4.977968633308439, "grad_norm": 0.9644245505332947, "learning_rate": 3.5900106896336025e-07, "loss": 0.4532, "step": 4445 }, { "epoch": 4.979088872292756, "grad_norm": 0.9399021863937378, "learning_rate": 3.582293427841305e-07, "loss": 0.4552, "step": 4446 }, { "epoch": 4.980209111277072, "grad_norm": 0.9259142279624939, "learning_rate": 3.5745838294801884e-07, "loss": 0.4366, "step": 4447 }, { "epoch": 4.981329350261389, "grad_norm": 0.9344968795776367, "learning_rate": 3.5668818973088186e-07, "loss": 0.4284, "step": 4448 }, { "epoch": 4.9824495892457055, "grad_norm": 0.9245726466178894, "learning_rate": 3.5591876340830057e-07, "loss": 0.4472, "step": 4449 }, { "epoch": 4.9835698282300225, "grad_norm": 0.9432165026664734, "learning_rate": 3.5515010425558214e-07, "loss": 0.4688, "step": 4450 }, { "epoch": 4.9846900672143395, "grad_norm": 0.9561710357666016, "learning_rate": 3.5438221254775917e-07, "loss": 0.4517, "step": 4451 }, { "epoch": 4.985810306198656, "grad_norm": 0.9322413802146912, "learning_rate": 3.5361508855958933e-07, "loss": 0.4487, "step": 4452 }, { "epoch": 4.986930545182973, "grad_norm": 0.9511322975158691, "learning_rate": 3.5284873256555526e-07, "loss": 0.4602, "step": 4453 }, { "epoch": 4.988050784167289, "grad_norm": 0.9199652075767517, "learning_rate": 3.5208314483986677e-07, "loss": 0.4507, "step": 4454 }, { "epoch": 4.989171023151606, "grad_norm": 0.9358542561531067, "learning_rate": 3.51318325656457e-07, "loss": 0.4452, "step": 4455 }, { "epoch": 4.990291262135923, "grad_norm": 0.9046279191970825, "learning_rate": 3.5055427528898426e-07, "loss": 0.4483, "step": 4456 }, { "epoch": 4.991411501120239, "grad_norm": 0.9540025591850281, "learning_rate": 3.497909940108318e-07, "loss": 0.4529, "step": 4457 }, { "epoch": 4.992531740104556, "grad_norm": 0.9146817922592163, "learning_rate": 3.490284820951087e-07, "loss": 0.4559, "step": 4458 }, { "epoch": 4.993651979088872, "grad_norm": 0.9349808096885681, "learning_rate": 3.482667398146475e-07, "loss": 0.4493, "step": 4459 }, { "epoch": 4.994772218073189, "grad_norm": 0.9181099534034729, "learning_rate": 3.47505767442006e-07, "loss": 0.4799, "step": 4460 }, { "epoch": 4.995892457057506, "grad_norm": 0.9449354410171509, "learning_rate": 3.4674556524946556e-07, "loss": 0.4604, "step": 4461 }, { "epoch": 4.997012696041822, "grad_norm": 0.9438769221305847, "learning_rate": 3.459861335090342e-07, "loss": 0.4605, "step": 4462 }, { "epoch": 4.998132935026139, "grad_norm": 0.912046492099762, "learning_rate": 3.452274724924418e-07, "loss": 0.4271, "step": 4463 }, { "epoch": 4.999253174010455, "grad_norm": 0.9311015605926514, "learning_rate": 3.4446958247114416e-07, "loss": 0.4574, "step": 4464 }, { "epoch": 5.0, "grad_norm": 1.1133356094360352, "learning_rate": 3.4371246371632e-07, "loss": 0.4275, "step": 4465 }, { "epoch": 5.001120238984317, "grad_norm": 1.0603657960891724, "learning_rate": 3.4295611649887264e-07, "loss": 0.436, "step": 4466 }, { "epoch": 5.002240477968633, "grad_norm": 0.9246217608451843, "learning_rate": 3.4220054108942914e-07, "loss": 0.4177, "step": 4467 }, { "epoch": 5.00336071695295, "grad_norm": 0.9199775457382202, "learning_rate": 3.414457377583413e-07, "loss": 0.4421, "step": 4468 }, { "epoch": 5.004480955937266, "grad_norm": 0.9050055742263794, "learning_rate": 3.4069170677568377e-07, "loss": 0.406, "step": 4469 }, { "epoch": 5.005601194921583, "grad_norm": 0.9168269634246826, "learning_rate": 3.399384484112547e-07, "loss": 0.4512, "step": 4470 }, { "epoch": 5.0067214339059, "grad_norm": 0.9182127118110657, "learning_rate": 3.391859629345759e-07, "loss": 0.4713, "step": 4471 }, { "epoch": 5.007841672890216, "grad_norm": 0.929070234298706, "learning_rate": 3.3843425061489357e-07, "loss": 0.4245, "step": 4472 }, { "epoch": 5.008961911874533, "grad_norm": 0.9200793504714966, "learning_rate": 3.376833117211761e-07, "loss": 0.4452, "step": 4473 }, { "epoch": 5.01008215085885, "grad_norm": 0.9606031775474548, "learning_rate": 3.369331465221151e-07, "loss": 0.4641, "step": 4474 }, { "epoch": 5.011202389843167, "grad_norm": 0.9119938015937805, "learning_rate": 3.361837552861269e-07, "loss": 0.4431, "step": 4475 }, { "epoch": 5.012322628827484, "grad_norm": 0.9264625310897827, "learning_rate": 3.354351382813495e-07, "loss": 0.4375, "step": 4476 }, { "epoch": 5.0134428678118, "grad_norm": 0.9264098405838013, "learning_rate": 3.346872957756442e-07, "loss": 0.4457, "step": 4477 }, { "epoch": 5.014563106796117, "grad_norm": 0.9222391843795776, "learning_rate": 3.339402280365947e-07, "loss": 0.4447, "step": 4478 }, { "epoch": 5.015683345780433, "grad_norm": 0.9259154796600342, "learning_rate": 3.3319393533150833e-07, "loss": 0.4586, "step": 4479 }, { "epoch": 5.01680358476475, "grad_norm": 0.9054745435714722, "learning_rate": 3.324484179274143e-07, "loss": 0.4319, "step": 4480 }, { "epoch": 5.017923823749067, "grad_norm": 0.9116505980491638, "learning_rate": 3.317036760910655e-07, "loss": 0.4302, "step": 4481 }, { "epoch": 5.019044062733383, "grad_norm": 0.9430438876152039, "learning_rate": 3.3095971008893666e-07, "loss": 0.4557, "step": 4482 }, { "epoch": 5.0201643017177, "grad_norm": 0.9128756523132324, "learning_rate": 3.3021652018722486e-07, "loss": 0.4325, "step": 4483 }, { "epoch": 5.021284540702016, "grad_norm": 0.9682750105857849, "learning_rate": 3.2947410665184836e-07, "loss": 0.4451, "step": 4484 }, { "epoch": 5.022404779686333, "grad_norm": 0.9300528168678284, "learning_rate": 3.2873246974845093e-07, "loss": 0.4573, "step": 4485 }, { "epoch": 5.02352501867065, "grad_norm": 0.9525890946388245, "learning_rate": 3.279916097423949e-07, "loss": 0.4577, "step": 4486 }, { "epoch": 5.024645257654966, "grad_norm": 0.9463980197906494, "learning_rate": 3.272515268987664e-07, "loss": 0.4716, "step": 4487 }, { "epoch": 5.025765496639283, "grad_norm": 0.9238768219947815, "learning_rate": 3.2651222148237265e-07, "loss": 0.4334, "step": 4488 }, { "epoch": 5.026885735623599, "grad_norm": 0.9200389385223389, "learning_rate": 3.257736937577444e-07, "loss": 0.4341, "step": 4489 }, { "epoch": 5.028005974607916, "grad_norm": 0.9212284684181213, "learning_rate": 3.250359439891321e-07, "loss": 0.4215, "step": 4490 }, { "epoch": 5.029126213592233, "grad_norm": 0.9269955158233643, "learning_rate": 3.242989724405085e-07, "loss": 0.4623, "step": 4491 }, { "epoch": 5.03024645257655, "grad_norm": 0.9392098188400269, "learning_rate": 3.2356277937556884e-07, "loss": 0.4597, "step": 4492 }, { "epoch": 5.031366691560867, "grad_norm": 0.9398941397666931, "learning_rate": 3.228273650577282e-07, "loss": 0.447, "step": 4493 }, { "epoch": 5.032486930545183, "grad_norm": 0.9429778456687927, "learning_rate": 3.220927297501239e-07, "loss": 0.4339, "step": 4494 }, { "epoch": 5.0336071695295, "grad_norm": 0.9485498666763306, "learning_rate": 3.2135887371561536e-07, "loss": 0.4584, "step": 4495 }, { "epoch": 5.034727408513817, "grad_norm": 0.9680296182632446, "learning_rate": 3.206257972167817e-07, "loss": 0.4546, "step": 4496 }, { "epoch": 5.035847647498133, "grad_norm": 0.9280611872673035, "learning_rate": 3.1989350051592314e-07, "loss": 0.4393, "step": 4497 }, { "epoch": 5.03696788648245, "grad_norm": 0.9574146270751953, "learning_rate": 3.191619838750626e-07, "loss": 0.4381, "step": 4498 }, { "epoch": 5.038088125466766, "grad_norm": 0.956453800201416, "learning_rate": 3.184312475559423e-07, "loss": 0.4488, "step": 4499 }, { "epoch": 5.039208364451083, "grad_norm": 0.9455792307853699, "learning_rate": 3.1770129182002537e-07, "loss": 0.4307, "step": 4500 }, { "epoch": 5.040328603435399, "grad_norm": 0.9475489854812622, "learning_rate": 3.169721169284959e-07, "loss": 0.4519, "step": 4501 }, { "epoch": 5.041448842419716, "grad_norm": 0.928557276725769, "learning_rate": 3.162437231422594e-07, "loss": 0.4542, "step": 4502 }, { "epoch": 5.042569081404033, "grad_norm": 0.9349851608276367, "learning_rate": 3.1551611072194067e-07, "loss": 0.4451, "step": 4503 }, { "epoch": 5.043689320388349, "grad_norm": 0.9320597052574158, "learning_rate": 3.147892799278851e-07, "loss": 0.4309, "step": 4504 }, { "epoch": 5.044809559372666, "grad_norm": 0.9350014328956604, "learning_rate": 3.140632310201594e-07, "loss": 0.4394, "step": 4505 }, { "epoch": 5.045929798356982, "grad_norm": 0.939829409122467, "learning_rate": 3.1333796425854934e-07, "loss": 0.4411, "step": 4506 }, { "epoch": 5.047050037341299, "grad_norm": 0.9403044581413269, "learning_rate": 3.1261347990256095e-07, "loss": 0.4485, "step": 4507 }, { "epoch": 5.048170276325616, "grad_norm": 0.9497578740119934, "learning_rate": 3.1188977821142166e-07, "loss": 0.4477, "step": 4508 }, { "epoch": 5.049290515309933, "grad_norm": 0.9155399799346924, "learning_rate": 3.111668594440773e-07, "loss": 0.4694, "step": 4509 }, { "epoch": 5.05041075429425, "grad_norm": 1.000157117843628, "learning_rate": 3.1044472385919375e-07, "loss": 0.4588, "step": 4510 }, { "epoch": 5.051530993278566, "grad_norm": 0.9140987992286682, "learning_rate": 3.097233717151579e-07, "loss": 0.4268, "step": 4511 }, { "epoch": 5.052651232262883, "grad_norm": 0.9318459033966064, "learning_rate": 3.090028032700751e-07, "loss": 0.454, "step": 4512 }, { "epoch": 5.0537714712472, "grad_norm": 0.9183743000030518, "learning_rate": 3.0828301878177064e-07, "loss": 0.4369, "step": 4513 }, { "epoch": 5.054891710231516, "grad_norm": 0.9053483009338379, "learning_rate": 3.0756401850778884e-07, "loss": 0.4159, "step": 4514 }, { "epoch": 5.056011949215833, "grad_norm": 0.9537096619606018, "learning_rate": 3.06845802705395e-07, "loss": 0.4342, "step": 4515 }, { "epoch": 5.057132188200149, "grad_norm": 0.9313463568687439, "learning_rate": 3.061283716315719e-07, "loss": 0.4294, "step": 4516 }, { "epoch": 5.058252427184466, "grad_norm": 0.9025285243988037, "learning_rate": 3.054117255430222e-07, "loss": 0.413, "step": 4517 }, { "epoch": 5.059372666168783, "grad_norm": 0.939868688583374, "learning_rate": 3.046958646961681e-07, "loss": 0.4481, "step": 4518 }, { "epoch": 5.060492905153099, "grad_norm": 0.9357227683067322, "learning_rate": 3.0398078934715026e-07, "loss": 0.4491, "step": 4519 }, { "epoch": 5.061613144137416, "grad_norm": 0.9073203206062317, "learning_rate": 3.0326649975182866e-07, "loss": 0.4308, "step": 4520 }, { "epoch": 5.062733383121732, "grad_norm": 0.9469398856163025, "learning_rate": 3.025529961657811e-07, "loss": 0.4589, "step": 4521 }, { "epoch": 5.063853622106049, "grad_norm": 0.9444823861122131, "learning_rate": 3.0184027884430646e-07, "loss": 0.4549, "step": 4522 }, { "epoch": 5.064973861090366, "grad_norm": 0.9320961833000183, "learning_rate": 3.0112834804242014e-07, "loss": 0.451, "step": 4523 }, { "epoch": 5.066094100074682, "grad_norm": 0.9860808253288269, "learning_rate": 3.0041720401485617e-07, "loss": 0.4453, "step": 4524 }, { "epoch": 5.067214339058999, "grad_norm": 0.9412034153938293, "learning_rate": 2.997068470160691e-07, "loss": 0.4457, "step": 4525 }, { "epoch": 5.0683345780433156, "grad_norm": 0.9218186140060425, "learning_rate": 2.9899727730022976e-07, "loss": 0.4323, "step": 4526 }, { "epoch": 5.069454817027633, "grad_norm": 0.9173293113708496, "learning_rate": 2.982884951212281e-07, "loss": 0.4376, "step": 4527 }, { "epoch": 5.07057505601195, "grad_norm": 0.9404499530792236, "learning_rate": 2.9758050073267154e-07, "loss": 0.4484, "step": 4528 }, { "epoch": 5.071695294996266, "grad_norm": 0.9190145134925842, "learning_rate": 2.9687329438788743e-07, "loss": 0.4247, "step": 4529 }, { "epoch": 5.072815533980583, "grad_norm": 0.9442538022994995, "learning_rate": 2.9616687633991976e-07, "loss": 0.454, "step": 4530 }, { "epoch": 5.073935772964899, "grad_norm": 0.9541645646095276, "learning_rate": 2.9546124684152993e-07, "loss": 0.4357, "step": 4531 }, { "epoch": 5.075056011949216, "grad_norm": 0.9320339560508728, "learning_rate": 2.9475640614519877e-07, "loss": 0.4617, "step": 4532 }, { "epoch": 5.076176250933533, "grad_norm": 0.9768868088722229, "learning_rate": 2.9405235450312373e-07, "loss": 0.4572, "step": 4533 }, { "epoch": 5.077296489917849, "grad_norm": 0.926820695400238, "learning_rate": 2.9334909216721966e-07, "loss": 0.442, "step": 4534 }, { "epoch": 5.078416728902166, "grad_norm": 0.9585108757019043, "learning_rate": 2.926466193891209e-07, "loss": 0.4475, "step": 4535 }, { "epoch": 5.079536967886482, "grad_norm": 0.942474901676178, "learning_rate": 2.9194493642017706e-07, "loss": 0.4537, "step": 4536 }, { "epoch": 5.080657206870799, "grad_norm": 0.934763491153717, "learning_rate": 2.912440435114561e-07, "loss": 0.4421, "step": 4537 }, { "epoch": 5.081777445855116, "grad_norm": 0.9366642236709595, "learning_rate": 2.905439409137437e-07, "loss": 0.4308, "step": 4538 }, { "epoch": 5.082897684839432, "grad_norm": 0.9138128161430359, "learning_rate": 2.8984462887754224e-07, "loss": 0.4564, "step": 4539 }, { "epoch": 5.084017923823749, "grad_norm": 0.9196901917457581, "learning_rate": 2.8914610765307106e-07, "loss": 0.4316, "step": 4540 }, { "epoch": 5.085138162808065, "grad_norm": 0.9024386405944824, "learning_rate": 2.8844837749026607e-07, "loss": 0.4599, "step": 4541 }, { "epoch": 5.086258401792382, "grad_norm": 0.953579843044281, "learning_rate": 2.8775143863878253e-07, "loss": 0.4392, "step": 4542 }, { "epoch": 5.087378640776699, "grad_norm": 0.9316511750221252, "learning_rate": 2.870552913479899e-07, "loss": 0.4512, "step": 4543 }, { "epoch": 5.088498879761016, "grad_norm": 1.0493680238723755, "learning_rate": 2.8635993586697555e-07, "loss": 0.4676, "step": 4544 }, { "epoch": 5.089619118745333, "grad_norm": 0.9511628150939941, "learning_rate": 2.8566537244454326e-07, "loss": 0.4539, "step": 4545 }, { "epoch": 5.090739357729649, "grad_norm": 0.9277966022491455, "learning_rate": 2.8497160132921336e-07, "loss": 0.4456, "step": 4546 }, { "epoch": 5.091859596713966, "grad_norm": 0.9927770495414734, "learning_rate": 2.842786227692229e-07, "loss": 0.4228, "step": 4547 }, { "epoch": 5.092979835698283, "grad_norm": 0.9682099223136902, "learning_rate": 2.8358643701252577e-07, "loss": 0.4537, "step": 4548 }, { "epoch": 5.094100074682599, "grad_norm": 0.9356921315193176, "learning_rate": 2.8289504430679125e-07, "loss": 0.4609, "step": 4549 }, { "epoch": 5.095220313666916, "grad_norm": 0.9283875823020935, "learning_rate": 2.822044448994052e-07, "loss": 0.4358, "step": 4550 }, { "epoch": 5.096340552651232, "grad_norm": 0.9367570877075195, "learning_rate": 2.8151463903747065e-07, "loss": 0.4502, "step": 4551 }, { "epoch": 5.097460791635549, "grad_norm": 0.9035581946372986, "learning_rate": 2.8082562696780505e-07, "loss": 0.4348, "step": 4552 }, { "epoch": 5.098581030619866, "grad_norm": 0.9242878556251526, "learning_rate": 2.801374089369427e-07, "loss": 0.4349, "step": 4553 }, { "epoch": 5.099701269604182, "grad_norm": 0.931462824344635, "learning_rate": 2.7944998519113365e-07, "loss": 0.4425, "step": 4554 }, { "epoch": 5.100821508588499, "grad_norm": 0.9680558443069458, "learning_rate": 2.787633559763431e-07, "loss": 0.4589, "step": 4555 }, { "epoch": 5.101941747572815, "grad_norm": 0.8972948789596558, "learning_rate": 2.780775215382542e-07, "loss": 0.4493, "step": 4556 }, { "epoch": 5.103061986557132, "grad_norm": 0.957495391368866, "learning_rate": 2.773924821222629e-07, "loss": 0.4771, "step": 4557 }, { "epoch": 5.104182225541448, "grad_norm": 0.9153831005096436, "learning_rate": 2.7670823797348227e-07, "loss": 0.47, "step": 4558 }, { "epoch": 5.105302464525765, "grad_norm": 0.9020332098007202, "learning_rate": 2.760247893367407e-07, "loss": 0.4161, "step": 4559 }, { "epoch": 5.106422703510082, "grad_norm": 0.9286065101623535, "learning_rate": 2.753421364565814e-07, "loss": 0.4526, "step": 4560 }, { "epoch": 5.1075429424943986, "grad_norm": 0.9311904907226562, "learning_rate": 2.7466027957726265e-07, "loss": 0.4353, "step": 4561 }, { "epoch": 5.108663181478716, "grad_norm": 0.9229637384414673, "learning_rate": 2.739792189427595e-07, "loss": 0.4557, "step": 4562 }, { "epoch": 5.109783420463032, "grad_norm": 0.934284508228302, "learning_rate": 2.7329895479676044e-07, "loss": 0.4353, "step": 4563 }, { "epoch": 5.110903659447349, "grad_norm": 0.9653418064117432, "learning_rate": 2.7261948738266985e-07, "loss": 0.4611, "step": 4564 }, { "epoch": 5.112023898431666, "grad_norm": 0.9355107545852661, "learning_rate": 2.719408169436069e-07, "loss": 0.4381, "step": 4565 }, { "epoch": 5.113144137415982, "grad_norm": 0.9398424029350281, "learning_rate": 2.7126294372240485e-07, "loss": 0.4459, "step": 4566 }, { "epoch": 5.114264376400299, "grad_norm": 0.9364837408065796, "learning_rate": 2.705858679616127e-07, "loss": 0.4377, "step": 4567 }, { "epoch": 5.115384615384615, "grad_norm": 0.9107387065887451, "learning_rate": 2.6990958990349315e-07, "loss": 0.4314, "step": 4568 }, { "epoch": 5.116504854368932, "grad_norm": 0.9466438889503479, "learning_rate": 2.69234109790025e-07, "loss": 0.4539, "step": 4569 }, { "epoch": 5.117625093353249, "grad_norm": 0.940772294998169, "learning_rate": 2.685594278629003e-07, "loss": 0.4586, "step": 4570 }, { "epoch": 5.118745332337565, "grad_norm": 0.9417543411254883, "learning_rate": 2.678855443635253e-07, "loss": 0.4322, "step": 4571 }, { "epoch": 5.119865571321882, "grad_norm": 0.9195898771286011, "learning_rate": 2.6721245953302136e-07, "loss": 0.434, "step": 4572 }, { "epoch": 5.120985810306198, "grad_norm": 0.9505847096443176, "learning_rate": 2.665401736122236e-07, "loss": 0.4583, "step": 4573 }, { "epoch": 5.122106049290515, "grad_norm": 0.917012095451355, "learning_rate": 2.6586868684168127e-07, "loss": 0.4431, "step": 4574 }, { "epoch": 5.123226288274832, "grad_norm": 0.9423027634620667, "learning_rate": 2.6519799946165854e-07, "loss": 0.4578, "step": 4575 }, { "epoch": 5.124346527259148, "grad_norm": 0.9336528778076172, "learning_rate": 2.6452811171213234e-07, "loss": 0.4436, "step": 4576 }, { "epoch": 5.125466766243465, "grad_norm": 0.9163268804550171, "learning_rate": 2.638590238327937e-07, "loss": 0.4631, "step": 4577 }, { "epoch": 5.1265870052277815, "grad_norm": 0.9225417971611023, "learning_rate": 2.6319073606304867e-07, "loss": 0.428, "step": 4578 }, { "epoch": 5.127707244212099, "grad_norm": 0.9175869226455688, "learning_rate": 2.625232486420157e-07, "loss": 0.4211, "step": 4579 }, { "epoch": 5.128827483196416, "grad_norm": 0.9591111540794373, "learning_rate": 2.61856561808527e-07, "loss": 0.4465, "step": 4580 }, { "epoch": 5.129947722180732, "grad_norm": 0.9163994789123535, "learning_rate": 2.611906758011287e-07, "loss": 0.4258, "step": 4581 }, { "epoch": 5.131067961165049, "grad_norm": 0.8981887102127075, "learning_rate": 2.6052559085808006e-07, "loss": 0.4371, "step": 4582 }, { "epoch": 5.132188200149365, "grad_norm": 0.9181497693061829, "learning_rate": 2.5986130721735445e-07, "loss": 0.4419, "step": 4583 }, { "epoch": 5.133308439133682, "grad_norm": 0.934917151927948, "learning_rate": 2.591978251166377e-07, "loss": 0.4414, "step": 4584 }, { "epoch": 5.134428678117999, "grad_norm": 0.9327980279922485, "learning_rate": 2.585351447933296e-07, "loss": 0.4688, "step": 4585 }, { "epoch": 5.135548917102315, "grad_norm": 0.9308022260665894, "learning_rate": 2.578732664845418e-07, "loss": 0.4407, "step": 4586 }, { "epoch": 5.136669156086632, "grad_norm": 0.9512535929679871, "learning_rate": 2.572121904271005e-07, "loss": 0.4576, "step": 4587 }, { "epoch": 5.137789395070948, "grad_norm": 0.9237067103385925, "learning_rate": 2.565519168575431e-07, "loss": 0.4595, "step": 4588 }, { "epoch": 5.138909634055265, "grad_norm": 0.9545630216598511, "learning_rate": 2.5589244601212234e-07, "loss": 0.4646, "step": 4589 }, { "epoch": 5.140029873039582, "grad_norm": 0.9371485710144043, "learning_rate": 2.552337781268011e-07, "loss": 0.4179, "step": 4590 }, { "epoch": 5.141150112023898, "grad_norm": 0.9232279658317566, "learning_rate": 2.545759134372572e-07, "loss": 0.4408, "step": 4591 }, { "epoch": 5.142270351008215, "grad_norm": 0.9310293197631836, "learning_rate": 2.5391885217887933e-07, "loss": 0.4468, "step": 4592 }, { "epoch": 5.143390589992531, "grad_norm": 0.9141764640808105, "learning_rate": 2.532625945867695e-07, "loss": 0.4376, "step": 4593 }, { "epoch": 5.144510828976848, "grad_norm": 0.9096333384513855, "learning_rate": 2.526071408957423e-07, "loss": 0.4363, "step": 4594 }, { "epoch": 5.145631067961165, "grad_norm": 0.9497286677360535, "learning_rate": 2.519524913403237e-07, "loss": 0.4547, "step": 4595 }, { "epoch": 5.1467513069454816, "grad_norm": 0.9496031999588013, "learning_rate": 2.512986461547537e-07, "loss": 0.44, "step": 4596 }, { "epoch": 5.147871545929799, "grad_norm": 0.9198747873306274, "learning_rate": 2.506456055729831e-07, "loss": 0.4398, "step": 4597 }, { "epoch": 5.148991784914115, "grad_norm": 0.9189250469207764, "learning_rate": 2.4999336982867496e-07, "loss": 0.4075, "step": 4598 }, { "epoch": 5.150112023898432, "grad_norm": 0.9560924768447876, "learning_rate": 2.493419391552049e-07, "loss": 0.4624, "step": 4599 }, { "epoch": 5.151232262882749, "grad_norm": 0.9300789833068848, "learning_rate": 2.4869131378566005e-07, "loss": 0.4496, "step": 4600 }, { "epoch": 5.152352501867065, "grad_norm": 0.9609186053276062, "learning_rate": 2.480414939528386e-07, "loss": 0.4478, "step": 4601 }, { "epoch": 5.153472740851382, "grad_norm": 0.9303998351097107, "learning_rate": 2.4739247988925297e-07, "loss": 0.4309, "step": 4602 }, { "epoch": 5.154592979835698, "grad_norm": 0.9322366118431091, "learning_rate": 2.467442718271246e-07, "loss": 0.4713, "step": 4603 }, { "epoch": 5.155713218820015, "grad_norm": 0.9200579524040222, "learning_rate": 2.4609686999838846e-07, "loss": 0.433, "step": 4604 }, { "epoch": 5.156833457804332, "grad_norm": 0.9376956820487976, "learning_rate": 2.4545027463468984e-07, "loss": 0.4624, "step": 4605 }, { "epoch": 5.157953696788648, "grad_norm": 0.928155779838562, "learning_rate": 2.448044859673857e-07, "loss": 0.4411, "step": 4606 }, { "epoch": 5.159073935772965, "grad_norm": 0.9291398525238037, "learning_rate": 2.441595042275449e-07, "loss": 0.4544, "step": 4607 }, { "epoch": 5.160194174757281, "grad_norm": 0.925168514251709, "learning_rate": 2.4351532964594695e-07, "loss": 0.4439, "step": 4608 }, { "epoch": 5.161314413741598, "grad_norm": 0.9462092518806458, "learning_rate": 2.428719624530823e-07, "loss": 0.4416, "step": 4609 }, { "epoch": 5.162434652725915, "grad_norm": 0.944704532623291, "learning_rate": 2.422294028791539e-07, "loss": 0.4351, "step": 4610 }, { "epoch": 5.163554891710231, "grad_norm": 0.913290798664093, "learning_rate": 2.4158765115407464e-07, "loss": 0.4385, "step": 4611 }, { "epoch": 5.164675130694548, "grad_norm": 0.9447564482688904, "learning_rate": 2.409467075074684e-07, "loss": 0.4448, "step": 4612 }, { "epoch": 5.1657953696788645, "grad_norm": 0.9938027262687683, "learning_rate": 2.403065721686701e-07, "loss": 0.4939, "step": 4613 }, { "epoch": 5.166915608663182, "grad_norm": 0.9585856199264526, "learning_rate": 2.396672453667254e-07, "loss": 0.4435, "step": 4614 }, { "epoch": 5.168035847647499, "grad_norm": 0.9160904884338379, "learning_rate": 2.390287273303904e-07, "loss": 0.4513, "step": 4615 }, { "epoch": 5.169156086631815, "grad_norm": 0.9310513138771057, "learning_rate": 2.3839101828813215e-07, "loss": 0.4486, "step": 4616 }, { "epoch": 5.170276325616132, "grad_norm": 0.9579817056655884, "learning_rate": 2.3775411846812867e-07, "loss": 0.4685, "step": 4617 }, { "epoch": 5.171396564600448, "grad_norm": 0.9329991340637207, "learning_rate": 2.3711802809826796e-07, "loss": 0.4386, "step": 4618 }, { "epoch": 5.172516803584765, "grad_norm": 0.9068583846092224, "learning_rate": 2.364827474061482e-07, "loss": 0.4349, "step": 4619 }, { "epoch": 5.173637042569082, "grad_norm": 0.9425040483474731, "learning_rate": 2.3584827661907757e-07, "loss": 0.4446, "step": 4620 }, { "epoch": 5.174757281553398, "grad_norm": 0.9491515755653381, "learning_rate": 2.3521461596407557e-07, "loss": 0.4403, "step": 4621 }, { "epoch": 5.175877520537715, "grad_norm": 0.970004141330719, "learning_rate": 2.3458176566787034e-07, "loss": 0.4524, "step": 4622 }, { "epoch": 5.176997759522031, "grad_norm": 0.9213980436325073, "learning_rate": 2.3394972595690178e-07, "loss": 0.4516, "step": 4623 }, { "epoch": 5.178117998506348, "grad_norm": 0.933860182762146, "learning_rate": 2.333184970573188e-07, "loss": 0.4404, "step": 4624 }, { "epoch": 5.179238237490664, "grad_norm": 0.9053539633750916, "learning_rate": 2.3268807919497983e-07, "loss": 0.4389, "step": 4625 }, { "epoch": 5.180358476474981, "grad_norm": 0.9124186038970947, "learning_rate": 2.3205847259545388e-07, "loss": 0.4414, "step": 4626 }, { "epoch": 5.181478715459298, "grad_norm": 0.9100969433784485, "learning_rate": 2.3142967748401913e-07, "loss": 0.4277, "step": 4627 }, { "epoch": 5.182598954443614, "grad_norm": 0.9138221144676208, "learning_rate": 2.308016940856636e-07, "loss": 0.4216, "step": 4628 }, { "epoch": 5.183719193427931, "grad_norm": 0.9469823241233826, "learning_rate": 2.301745226250851e-07, "loss": 0.4496, "step": 4629 }, { "epoch": 5.1848394324122475, "grad_norm": 0.9441187977790833, "learning_rate": 2.295481633266905e-07, "loss": 0.4331, "step": 4630 }, { "epoch": 5.1859596713965646, "grad_norm": 0.9460280537605286, "learning_rate": 2.289226164145969e-07, "loss": 0.4376, "step": 4631 }, { "epoch": 5.187079910380882, "grad_norm": 0.9676334261894226, "learning_rate": 2.282978821126297e-07, "loss": 0.4521, "step": 4632 }, { "epoch": 5.188200149365198, "grad_norm": 0.9536194205284119, "learning_rate": 2.27673960644324e-07, "loss": 0.4291, "step": 4633 }, { "epoch": 5.189320388349515, "grad_norm": 0.9068063497543335, "learning_rate": 2.2705085223292372e-07, "loss": 0.4331, "step": 4634 }, { "epoch": 5.190440627333831, "grad_norm": 0.9301784634590149, "learning_rate": 2.2642855710138217e-07, "loss": 0.4259, "step": 4635 }, { "epoch": 5.191560866318148, "grad_norm": 0.971084475517273, "learning_rate": 2.2580707547236236e-07, "loss": 0.4563, "step": 4636 }, { "epoch": 5.192681105302465, "grad_norm": 0.9232094883918762, "learning_rate": 2.25186407568235e-07, "loss": 0.4354, "step": 4637 }, { "epoch": 5.193801344286781, "grad_norm": 0.9391321539878845, "learning_rate": 2.2456655361108027e-07, "loss": 0.4776, "step": 4638 }, { "epoch": 5.194921583271098, "grad_norm": 0.9337272047996521, "learning_rate": 2.239475138226871e-07, "loss": 0.446, "step": 4639 }, { "epoch": 5.196041822255414, "grad_norm": 0.9248101115226746, "learning_rate": 2.2332928842455275e-07, "loss": 0.427, "step": 4640 }, { "epoch": 5.197162061239731, "grad_norm": 0.9542722702026367, "learning_rate": 2.2271187763788338e-07, "loss": 0.4329, "step": 4641 }, { "epoch": 5.198282300224048, "grad_norm": 0.9422664642333984, "learning_rate": 2.2209528168359335e-07, "loss": 0.4548, "step": 4642 }, { "epoch": 5.199402539208364, "grad_norm": 0.9661060571670532, "learning_rate": 2.214795007823059e-07, "loss": 0.4449, "step": 4643 }, { "epoch": 5.200522778192681, "grad_norm": 0.9582899808883667, "learning_rate": 2.208645351543534e-07, "loss": 0.4565, "step": 4644 }, { "epoch": 5.201643017176997, "grad_norm": 0.9563512802124023, "learning_rate": 2.2025038501977485e-07, "loss": 0.4334, "step": 4645 }, { "epoch": 5.202763256161314, "grad_norm": 0.9315243363380432, "learning_rate": 2.1963705059831807e-07, "loss": 0.4351, "step": 4646 }, { "epoch": 5.203883495145631, "grad_norm": 0.9422560930252075, "learning_rate": 2.1902453210943974e-07, "loss": 0.4525, "step": 4647 }, { "epoch": 5.2050037341299475, "grad_norm": 0.9604800343513489, "learning_rate": 2.1841282977230315e-07, "loss": 0.4657, "step": 4648 }, { "epoch": 5.206123973114265, "grad_norm": 0.9480254054069519, "learning_rate": 2.1780194380578073e-07, "loss": 0.465, "step": 4649 }, { "epoch": 5.207244212098581, "grad_norm": 0.9481355547904968, "learning_rate": 2.171918744284529e-07, "loss": 0.4807, "step": 4650 }, { "epoch": 5.208364451082898, "grad_norm": 0.9225462675094604, "learning_rate": 2.1658262185860758e-07, "loss": 0.4258, "step": 4651 }, { "epoch": 5.209484690067215, "grad_norm": 0.954077422618866, "learning_rate": 2.159741863142395e-07, "loss": 0.4448, "step": 4652 }, { "epoch": 5.210604929051531, "grad_norm": 0.9136731028556824, "learning_rate": 2.153665680130526e-07, "loss": 0.431, "step": 4653 }, { "epoch": 5.211725168035848, "grad_norm": 0.929710328578949, "learning_rate": 2.1475976717245744e-07, "loss": 0.4827, "step": 4654 }, { "epoch": 5.212845407020164, "grad_norm": 0.928390622138977, "learning_rate": 2.1415378400957199e-07, "loss": 0.4669, "step": 4655 }, { "epoch": 5.213965646004481, "grad_norm": 0.9210307598114014, "learning_rate": 2.135486187412225e-07, "loss": 0.4642, "step": 4656 }, { "epoch": 5.215085884988798, "grad_norm": 0.9519626498222351, "learning_rate": 2.1294427158394222e-07, "loss": 0.472, "step": 4657 }, { "epoch": 5.216206123973114, "grad_norm": 0.9546903371810913, "learning_rate": 2.1234074275397116e-07, "loss": 0.4386, "step": 4658 }, { "epoch": 5.217326362957431, "grad_norm": 0.9268209934234619, "learning_rate": 2.1173803246725717e-07, "loss": 0.4519, "step": 4659 }, { "epoch": 5.218446601941747, "grad_norm": 0.9327588081359863, "learning_rate": 2.1113614093945467e-07, "loss": 0.4269, "step": 4660 }, { "epoch": 5.219566840926064, "grad_norm": 0.9639704823493958, "learning_rate": 2.105350683859253e-07, "loss": 0.4421, "step": 4661 }, { "epoch": 5.220687079910381, "grad_norm": 0.8940902948379517, "learning_rate": 2.0993481502173756e-07, "loss": 0.4443, "step": 4662 }, { "epoch": 5.221807318894697, "grad_norm": 0.9448248147964478, "learning_rate": 2.0933538106166802e-07, "loss": 0.4323, "step": 4663 }, { "epoch": 5.222927557879014, "grad_norm": 0.8969066739082336, "learning_rate": 2.087367667201984e-07, "loss": 0.4193, "step": 4664 }, { "epoch": 5.2240477968633305, "grad_norm": 0.9565142393112183, "learning_rate": 2.0813897221151764e-07, "loss": 0.4524, "step": 4665 }, { "epoch": 5.2251680358476476, "grad_norm": 0.9265009760856628, "learning_rate": 2.075419977495219e-07, "loss": 0.4568, "step": 4666 }, { "epoch": 5.226288274831965, "grad_norm": 0.9686599373817444, "learning_rate": 2.0694584354781334e-07, "loss": 0.4504, "step": 4667 }, { "epoch": 5.227408513816281, "grad_norm": 0.908989667892456, "learning_rate": 2.063505098197005e-07, "loss": 0.4435, "step": 4668 }, { "epoch": 5.228528752800598, "grad_norm": 0.9406648278236389, "learning_rate": 2.0575599677819942e-07, "loss": 0.4574, "step": 4669 }, { "epoch": 5.229648991784914, "grad_norm": 0.9263149499893188, "learning_rate": 2.05162304636031e-07, "loss": 0.4567, "step": 4670 }, { "epoch": 5.230769230769231, "grad_norm": 0.9291526675224304, "learning_rate": 2.0456943360562392e-07, "loss": 0.4412, "step": 4671 }, { "epoch": 5.231889469753548, "grad_norm": 0.9428799748420715, "learning_rate": 2.0397738389911188e-07, "loss": 0.4464, "step": 4672 }, { "epoch": 5.233009708737864, "grad_norm": 0.9183262586593628, "learning_rate": 2.033861557283351e-07, "loss": 0.4448, "step": 4673 }, { "epoch": 5.234129947722181, "grad_norm": 0.9210896492004395, "learning_rate": 2.027957493048399e-07, "loss": 0.4281, "step": 4674 }, { "epoch": 5.235250186706497, "grad_norm": 0.9162712693214417, "learning_rate": 2.0220616483987876e-07, "loss": 0.4432, "step": 4675 }, { "epoch": 5.236370425690814, "grad_norm": 0.9341638684272766, "learning_rate": 2.01617402544409e-07, "loss": 0.4333, "step": 4676 }, { "epoch": 5.23749066467513, "grad_norm": 0.957963228225708, "learning_rate": 2.0102946262909595e-07, "loss": 0.4463, "step": 4677 }, { "epoch": 5.238610903659447, "grad_norm": 0.926008403301239, "learning_rate": 2.0044234530430834e-07, "loss": 0.4415, "step": 4678 }, { "epoch": 5.239731142643764, "grad_norm": 0.8991934061050415, "learning_rate": 1.9985605078012199e-07, "loss": 0.4543, "step": 4679 }, { "epoch": 5.24085138162808, "grad_norm": 0.924156904220581, "learning_rate": 1.9927057926631798e-07, "loss": 0.4557, "step": 4680 }, { "epoch": 5.241971620612397, "grad_norm": 0.9237070679664612, "learning_rate": 1.9868593097238236e-07, "loss": 0.4618, "step": 4681 }, { "epoch": 5.2430918595967135, "grad_norm": 0.9530025124549866, "learning_rate": 1.9810210610750695e-07, "loss": 0.4601, "step": 4682 }, { "epoch": 5.2442120985810305, "grad_norm": 0.9113121628761292, "learning_rate": 1.975191048805894e-07, "loss": 0.4328, "step": 4683 }, { "epoch": 5.245332337565348, "grad_norm": 0.9277204275131226, "learning_rate": 1.9693692750023308e-07, "loss": 0.4559, "step": 4684 }, { "epoch": 5.246452576549664, "grad_norm": 0.9266679883003235, "learning_rate": 1.96355574174745e-07, "loss": 0.454, "step": 4685 }, { "epoch": 5.247572815533981, "grad_norm": 0.9416755437850952, "learning_rate": 1.9577504511213818e-07, "loss": 0.4418, "step": 4686 }, { "epoch": 5.248693054518297, "grad_norm": 0.9131762385368347, "learning_rate": 1.9519534052013094e-07, "loss": 0.4368, "step": 4687 }, { "epoch": 5.249813293502614, "grad_norm": 0.9271336197853088, "learning_rate": 1.9461646060614625e-07, "loss": 0.4434, "step": 4688 }, { "epoch": 5.250933532486931, "grad_norm": 0.9274469614028931, "learning_rate": 1.9403840557731147e-07, "loss": 0.4463, "step": 4689 }, { "epoch": 5.252053771471247, "grad_norm": 0.9401220679283142, "learning_rate": 1.9346117564046058e-07, "loss": 0.4461, "step": 4690 }, { "epoch": 5.253174010455564, "grad_norm": 0.9608445763587952, "learning_rate": 1.928847710021306e-07, "loss": 0.4414, "step": 4691 }, { "epoch": 5.25429424943988, "grad_norm": 0.9170461297035217, "learning_rate": 1.9230919186856406e-07, "loss": 0.4364, "step": 4692 }, { "epoch": 5.255414488424197, "grad_norm": 0.9566043019294739, "learning_rate": 1.9173443844570732e-07, "loss": 0.4389, "step": 4693 }, { "epoch": 5.256534727408514, "grad_norm": 0.9258144497871399, "learning_rate": 1.9116051093921257e-07, "loss": 0.4511, "step": 4694 }, { "epoch": 5.25765496639283, "grad_norm": 0.9847100973129272, "learning_rate": 1.9058740955443493e-07, "loss": 0.4594, "step": 4695 }, { "epoch": 5.258775205377147, "grad_norm": 0.9510859251022339, "learning_rate": 1.9001513449643572e-07, "loss": 0.4564, "step": 4696 }, { "epoch": 5.259895444361463, "grad_norm": 0.9372100234031677, "learning_rate": 1.894436859699786e-07, "loss": 0.4248, "step": 4697 }, { "epoch": 5.26101568334578, "grad_norm": 0.9169377684593201, "learning_rate": 1.888730641795339e-07, "loss": 0.4244, "step": 4698 }, { "epoch": 5.262135922330097, "grad_norm": 0.9405790567398071, "learning_rate": 1.8830326932927412e-07, "loss": 0.447, "step": 4699 }, { "epoch": 5.2632561613144135, "grad_norm": 0.9661789536476135, "learning_rate": 1.877343016230762e-07, "loss": 0.4597, "step": 4700 }, { "epoch": 5.2643764002987306, "grad_norm": 0.9385719895362854, "learning_rate": 1.8716616126452203e-07, "loss": 0.4483, "step": 4701 }, { "epoch": 5.265496639283047, "grad_norm": 0.9687328934669495, "learning_rate": 1.8659884845689647e-07, "loss": 0.4525, "step": 4702 }, { "epoch": 5.266616878267364, "grad_norm": 0.9271095395088196, "learning_rate": 1.8603236340318827e-07, "loss": 0.4241, "step": 4703 }, { "epoch": 5.267737117251681, "grad_norm": 0.9347548484802246, "learning_rate": 1.8546670630609166e-07, "loss": 0.4406, "step": 4704 }, { "epoch": 5.268857356235997, "grad_norm": 0.9517073035240173, "learning_rate": 1.8490187736800252e-07, "loss": 0.4609, "step": 4705 }, { "epoch": 5.269977595220314, "grad_norm": 0.9513397216796875, "learning_rate": 1.8433787679102172e-07, "loss": 0.4432, "step": 4706 }, { "epoch": 5.27109783420463, "grad_norm": 0.9054216146469116, "learning_rate": 1.837747047769528e-07, "loss": 0.4184, "step": 4707 }, { "epoch": 5.272218073188947, "grad_norm": 0.9458288550376892, "learning_rate": 1.8321236152730376e-07, "loss": 0.4514, "step": 4708 }, { "epoch": 5.273338312173264, "grad_norm": 0.9445774555206299, "learning_rate": 1.8265084724328503e-07, "loss": 0.4334, "step": 4709 }, { "epoch": 5.27445855115758, "grad_norm": 0.9306964874267578, "learning_rate": 1.8209016212581143e-07, "loss": 0.4501, "step": 4710 }, { "epoch": 5.275578790141897, "grad_norm": 0.9468525052070618, "learning_rate": 1.8153030637550112e-07, "loss": 0.4387, "step": 4711 }, { "epoch": 5.276699029126213, "grad_norm": 0.9632881283760071, "learning_rate": 1.8097128019267469e-07, "loss": 0.4697, "step": 4712 }, { "epoch": 5.27781926811053, "grad_norm": 0.9526273012161255, "learning_rate": 1.8041308377735628e-07, "loss": 0.4396, "step": 4713 }, { "epoch": 5.278939507094847, "grad_norm": 0.9529046416282654, "learning_rate": 1.798557173292731e-07, "loss": 0.4217, "step": 4714 }, { "epoch": 5.280059746079163, "grad_norm": 0.9229530096054077, "learning_rate": 1.792991810478556e-07, "loss": 0.4358, "step": 4715 }, { "epoch": 5.28117998506348, "grad_norm": 1.0097942352294922, "learning_rate": 1.7874347513223643e-07, "loss": 0.4409, "step": 4716 }, { "epoch": 5.2823002240477965, "grad_norm": 0.9517390131950378, "learning_rate": 1.781885997812527e-07, "loss": 0.441, "step": 4717 }, { "epoch": 5.2834204630321135, "grad_norm": 0.9631727337837219, "learning_rate": 1.7763455519344275e-07, "loss": 0.4636, "step": 4718 }, { "epoch": 5.284540702016431, "grad_norm": 0.949100136756897, "learning_rate": 1.770813415670486e-07, "loss": 0.4622, "step": 4719 }, { "epoch": 5.285660941000747, "grad_norm": 0.9417626857757568, "learning_rate": 1.7652895910001438e-07, "loss": 0.43, "step": 4720 }, { "epoch": 5.286781179985064, "grad_norm": 0.9244992733001709, "learning_rate": 1.7597740798998702e-07, "loss": 0.4204, "step": 4721 }, { "epoch": 5.28790141896938, "grad_norm": 0.9285283088684082, "learning_rate": 1.7542668843431589e-07, "loss": 0.4508, "step": 4722 }, { "epoch": 5.289021657953697, "grad_norm": 0.9073118567466736, "learning_rate": 1.7487680063005357e-07, "loss": 0.4515, "step": 4723 }, { "epoch": 5.290141896938014, "grad_norm": 0.9591776132583618, "learning_rate": 1.743277447739536e-07, "loss": 0.4565, "step": 4724 }, { "epoch": 5.29126213592233, "grad_norm": 0.9214715361595154, "learning_rate": 1.7377952106247376e-07, "loss": 0.4351, "step": 4725 }, { "epoch": 5.292382374906647, "grad_norm": 0.9219250082969666, "learning_rate": 1.7323212969177217e-07, "loss": 0.4381, "step": 4726 }, { "epoch": 5.293502613890963, "grad_norm": 0.9321299195289612, "learning_rate": 1.7268557085771048e-07, "loss": 0.4736, "step": 4727 }, { "epoch": 5.29462285287528, "grad_norm": 0.9223096966743469, "learning_rate": 1.7213984475585143e-07, "loss": 0.4465, "step": 4728 }, { "epoch": 5.295743091859597, "grad_norm": 0.9240570068359375, "learning_rate": 1.7159495158146051e-07, "loss": 0.4402, "step": 4729 }, { "epoch": 5.296863330843913, "grad_norm": 0.9778570532798767, "learning_rate": 1.710508915295045e-07, "loss": 0.4666, "step": 4730 }, { "epoch": 5.29798356982823, "grad_norm": 0.957037627696991, "learning_rate": 1.7050766479465326e-07, "loss": 0.4634, "step": 4731 }, { "epoch": 5.299103808812546, "grad_norm": 0.927044153213501, "learning_rate": 1.6996527157127767e-07, "loss": 0.4401, "step": 4732 }, { "epoch": 5.300224047796863, "grad_norm": 0.9256271123886108, "learning_rate": 1.6942371205345033e-07, "loss": 0.4297, "step": 4733 }, { "epoch": 5.30134428678118, "grad_norm": 0.9460833072662354, "learning_rate": 1.6888298643494588e-07, "loss": 0.4614, "step": 4734 }, { "epoch": 5.3024645257654965, "grad_norm": 0.9341505169868469, "learning_rate": 1.6834309490923988e-07, "loss": 0.4293, "step": 4735 }, { "epoch": 5.3035847647498136, "grad_norm": 0.9356633424758911, "learning_rate": 1.6780403766950976e-07, "loss": 0.4384, "step": 4736 }, { "epoch": 5.30470500373413, "grad_norm": 0.9572312831878662, "learning_rate": 1.6726581490863535e-07, "loss": 0.4474, "step": 4737 }, { "epoch": 5.305825242718447, "grad_norm": 0.9245519638061523, "learning_rate": 1.6672842681919737e-07, "loss": 0.4337, "step": 4738 }, { "epoch": 5.306945481702764, "grad_norm": 0.9303697347640991, "learning_rate": 1.66191873593477e-07, "loss": 0.4409, "step": 4739 }, { "epoch": 5.30806572068708, "grad_norm": 0.9167163372039795, "learning_rate": 1.6565615542345786e-07, "loss": 0.4484, "step": 4740 }, { "epoch": 5.309185959671397, "grad_norm": 0.9325287342071533, "learning_rate": 1.651212725008239e-07, "loss": 0.4311, "step": 4741 }, { "epoch": 5.310306198655713, "grad_norm": 0.9692436456680298, "learning_rate": 1.6458722501696084e-07, "loss": 0.455, "step": 4742 }, { "epoch": 5.31142643764003, "grad_norm": 0.9375421404838562, "learning_rate": 1.6405401316295505e-07, "loss": 0.4319, "step": 4743 }, { "epoch": 5.312546676624347, "grad_norm": 0.9159247279167175, "learning_rate": 1.6352163712959446e-07, "loss": 0.4399, "step": 4744 }, { "epoch": 5.313666915608663, "grad_norm": 0.9235893487930298, "learning_rate": 1.6299009710736724e-07, "loss": 0.436, "step": 4745 }, { "epoch": 5.31478715459298, "grad_norm": 0.9503622651100159, "learning_rate": 1.6245939328646322e-07, "loss": 0.4714, "step": 4746 }, { "epoch": 5.315907393577296, "grad_norm": 0.9352498650550842, "learning_rate": 1.6192952585677212e-07, "loss": 0.4378, "step": 4747 }, { "epoch": 5.317027632561613, "grad_norm": 0.9368075728416443, "learning_rate": 1.6140049500788513e-07, "loss": 0.4157, "step": 4748 }, { "epoch": 5.318147871545929, "grad_norm": 0.8980777263641357, "learning_rate": 1.6087230092909328e-07, "loss": 0.4377, "step": 4749 }, { "epoch": 5.319268110530246, "grad_norm": 0.9805579781532288, "learning_rate": 1.6034494380938903e-07, "loss": 0.4471, "step": 4750 }, { "epoch": 5.320388349514563, "grad_norm": 0.9132905006408691, "learning_rate": 1.5981842383746588e-07, "loss": 0.428, "step": 4751 }, { "epoch": 5.3215085884988795, "grad_norm": 0.947577178478241, "learning_rate": 1.5929274120171617e-07, "loss": 0.4217, "step": 4752 }, { "epoch": 5.3226288274831965, "grad_norm": 0.9227656722068787, "learning_rate": 1.5876789609023392e-07, "loss": 0.4269, "step": 4753 }, { "epoch": 5.323749066467513, "grad_norm": 0.9305824637413025, "learning_rate": 1.5824388869081248e-07, "loss": 0.464, "step": 4754 }, { "epoch": 5.32486930545183, "grad_norm": 0.9428150057792664, "learning_rate": 1.577207191909466e-07, "loss": 0.4729, "step": 4755 }, { "epoch": 5.325989544436147, "grad_norm": 0.93522709608078, "learning_rate": 1.571983877778299e-07, "loss": 0.4348, "step": 4756 }, { "epoch": 5.327109783420463, "grad_norm": 0.9124361276626587, "learning_rate": 1.5667689463835707e-07, "loss": 0.4632, "step": 4757 }, { "epoch": 5.32823002240478, "grad_norm": 0.9428891539573669, "learning_rate": 1.561562399591232e-07, "loss": 0.432, "step": 4758 }, { "epoch": 5.329350261389096, "grad_norm": 0.9482051134109497, "learning_rate": 1.556364239264224e-07, "loss": 0.4706, "step": 4759 }, { "epoch": 5.330470500373413, "grad_norm": 0.9491458535194397, "learning_rate": 1.5511744672624896e-07, "loss": 0.4361, "step": 4760 }, { "epoch": 5.33159073935773, "grad_norm": 0.9498257637023926, "learning_rate": 1.545993085442976e-07, "loss": 0.4578, "step": 4761 }, { "epoch": 5.332710978342046, "grad_norm": 0.9066762328147888, "learning_rate": 1.5408200956596147e-07, "loss": 0.4224, "step": 4762 }, { "epoch": 5.333831217326363, "grad_norm": 0.9445738792419434, "learning_rate": 1.5356554997633583e-07, "loss": 0.438, "step": 4763 }, { "epoch": 5.334951456310679, "grad_norm": 0.9480857849121094, "learning_rate": 1.5304992996021285e-07, "loss": 0.4346, "step": 4764 }, { "epoch": 5.336071695294996, "grad_norm": 0.9449244737625122, "learning_rate": 1.5253514970208633e-07, "loss": 0.4724, "step": 4765 }, { "epoch": 5.337191934279313, "grad_norm": 0.9034796357154846, "learning_rate": 1.5202120938614895e-07, "loss": 0.4124, "step": 4766 }, { "epoch": 5.338312173263629, "grad_norm": 0.9190748333930969, "learning_rate": 1.515081091962925e-07, "loss": 0.4432, "step": 4767 }, { "epoch": 5.339432412247946, "grad_norm": 0.9455049633979797, "learning_rate": 1.5099584931610845e-07, "loss": 0.4477, "step": 4768 }, { "epoch": 5.3405526512322625, "grad_norm": 0.9273570775985718, "learning_rate": 1.5048442992888739e-07, "loss": 0.4392, "step": 4769 }, { "epoch": 5.3416728902165795, "grad_norm": 0.928281307220459, "learning_rate": 1.4997385121761966e-07, "loss": 0.4372, "step": 4770 }, { "epoch": 5.3427931292008966, "grad_norm": 0.9404027462005615, "learning_rate": 1.4946411336499434e-07, "loss": 0.4591, "step": 4771 }, { "epoch": 5.343913368185213, "grad_norm": 0.9462456107139587, "learning_rate": 1.4895521655340028e-07, "loss": 0.4431, "step": 4772 }, { "epoch": 5.34503360716953, "grad_norm": 0.9184474945068359, "learning_rate": 1.4844716096492435e-07, "loss": 0.4369, "step": 4773 }, { "epoch": 5.346153846153846, "grad_norm": 0.9048774838447571, "learning_rate": 1.4793994678135333e-07, "loss": 0.4333, "step": 4774 }, { "epoch": 5.347274085138163, "grad_norm": 0.9357523918151855, "learning_rate": 1.4743357418417258e-07, "loss": 0.4416, "step": 4775 }, { "epoch": 5.34839432412248, "grad_norm": 0.9440808296203613, "learning_rate": 1.4692804335456585e-07, "loss": 0.4433, "step": 4776 }, { "epoch": 5.349514563106796, "grad_norm": 0.9419532418251038, "learning_rate": 1.4642335447341672e-07, "loss": 0.4414, "step": 4777 }, { "epoch": 5.350634802091113, "grad_norm": 0.9246070384979248, "learning_rate": 1.4591950772130714e-07, "loss": 0.4431, "step": 4778 }, { "epoch": 5.351755041075429, "grad_norm": 0.9264365434646606, "learning_rate": 1.4541650327851765e-07, "loss": 0.4301, "step": 4779 }, { "epoch": 5.352875280059746, "grad_norm": 0.9275360107421875, "learning_rate": 1.4491434132502728e-07, "loss": 0.4569, "step": 4780 }, { "epoch": 5.353995519044063, "grad_norm": 0.9224424958229065, "learning_rate": 1.444130220405135e-07, "loss": 0.4413, "step": 4781 }, { "epoch": 5.355115758028379, "grad_norm": 0.913727879524231, "learning_rate": 1.4391254560435247e-07, "loss": 0.4165, "step": 4782 }, { "epoch": 5.356235997012696, "grad_norm": 0.9495196342468262, "learning_rate": 1.434129121956185e-07, "loss": 0.4342, "step": 4783 }, { "epoch": 5.357356235997012, "grad_norm": 0.9160268306732178, "learning_rate": 1.429141219930852e-07, "loss": 0.4653, "step": 4784 }, { "epoch": 5.358476474981329, "grad_norm": 0.9551105499267578, "learning_rate": 1.4241617517522343e-07, "loss": 0.4373, "step": 4785 }, { "epoch": 5.359596713965646, "grad_norm": 0.9185729622840881, "learning_rate": 1.4191907192020265e-07, "loss": 0.4164, "step": 4786 }, { "epoch": 5.3607169529499625, "grad_norm": 0.9282314777374268, "learning_rate": 1.4142281240589084e-07, "loss": 0.4366, "step": 4787 }, { "epoch": 5.3618371919342795, "grad_norm": 0.9460967183113098, "learning_rate": 1.4092739680985319e-07, "loss": 0.4312, "step": 4788 }, { "epoch": 5.362957430918596, "grad_norm": 0.9304709434509277, "learning_rate": 1.4043282530935316e-07, "loss": 0.4536, "step": 4789 }, { "epoch": 5.364077669902913, "grad_norm": 0.9274122714996338, "learning_rate": 1.3993909808135365e-07, "loss": 0.4355, "step": 4790 }, { "epoch": 5.365197908887229, "grad_norm": 0.9306550025939941, "learning_rate": 1.3944621530251305e-07, "loss": 0.4305, "step": 4791 }, { "epoch": 5.366318147871546, "grad_norm": 0.9279627799987793, "learning_rate": 1.3895417714919008e-07, "loss": 0.4424, "step": 4792 }, { "epoch": 5.367438386855863, "grad_norm": 0.9383232593536377, "learning_rate": 1.3846298379743938e-07, "loss": 0.4407, "step": 4793 }, { "epoch": 5.368558625840179, "grad_norm": 0.9174227714538574, "learning_rate": 1.3797263542301404e-07, "loss": 0.4496, "step": 4794 }, { "epoch": 5.369678864824496, "grad_norm": 0.9297392964363098, "learning_rate": 1.374831322013645e-07, "loss": 0.4539, "step": 4795 }, { "epoch": 5.370799103808812, "grad_norm": 0.964374840259552, "learning_rate": 1.3699447430763958e-07, "loss": 0.4362, "step": 4796 }, { "epoch": 5.371919342793129, "grad_norm": 0.93047696352005, "learning_rate": 1.365066619166841e-07, "loss": 0.4324, "step": 4797 }, { "epoch": 5.373039581777446, "grad_norm": 0.9423669576644897, "learning_rate": 1.3601969520304238e-07, "loss": 0.4454, "step": 4798 }, { "epoch": 5.374159820761762, "grad_norm": 0.9473919868469238, "learning_rate": 1.35533574340955e-07, "loss": 0.4537, "step": 4799 }, { "epoch": 5.375280059746079, "grad_norm": 0.9249798059463501, "learning_rate": 1.350482995043595e-07, "loss": 0.4475, "step": 4800 }, { "epoch": 5.376400298730395, "grad_norm": 0.9383405447006226, "learning_rate": 1.3456387086689144e-07, "loss": 0.4534, "step": 4801 }, { "epoch": 5.377520537714712, "grad_norm": 0.9230560660362244, "learning_rate": 1.3408028860188272e-07, "loss": 0.4479, "step": 4802 }, { "epoch": 5.378640776699029, "grad_norm": 0.9062047004699707, "learning_rate": 1.3359755288236438e-07, "loss": 0.4571, "step": 4803 }, { "epoch": 5.3797610156833455, "grad_norm": 0.9332491159439087, "learning_rate": 1.3311566388106184e-07, "loss": 0.443, "step": 4804 }, { "epoch": 5.3808812546676625, "grad_norm": 0.9339637756347656, "learning_rate": 1.3263462177040026e-07, "loss": 0.4412, "step": 4805 }, { "epoch": 5.382001493651979, "grad_norm": 0.9219992160797119, "learning_rate": 1.3215442672249972e-07, "loss": 0.4379, "step": 4806 }, { "epoch": 5.383121732636296, "grad_norm": 0.9356063008308411, "learning_rate": 1.316750789091778e-07, "loss": 0.466, "step": 4807 }, { "epoch": 5.384241971620613, "grad_norm": 0.9417797327041626, "learning_rate": 1.311965785019495e-07, "loss": 0.4322, "step": 4808 }, { "epoch": 5.385362210604929, "grad_norm": 0.9237227439880371, "learning_rate": 1.3071892567202592e-07, "loss": 0.4385, "step": 4809 }, { "epoch": 5.386482449589246, "grad_norm": 0.9212344288825989, "learning_rate": 1.3024212059031483e-07, "loss": 0.4295, "step": 4810 }, { "epoch": 5.387602688573562, "grad_norm": 0.9223166108131409, "learning_rate": 1.2976616342742165e-07, "loss": 0.4551, "step": 4811 }, { "epoch": 5.388722927557879, "grad_norm": 0.9464121460914612, "learning_rate": 1.292910543536477e-07, "loss": 0.4339, "step": 4812 }, { "epoch": 5.389843166542196, "grad_norm": 0.9241475462913513, "learning_rate": 1.2881679353899086e-07, "loss": 0.4546, "step": 4813 }, { "epoch": 5.390963405526512, "grad_norm": 0.9365270137786865, "learning_rate": 1.283433811531451e-07, "loss": 0.445, "step": 4814 }, { "epoch": 5.392083644510829, "grad_norm": 0.9385351538658142, "learning_rate": 1.2787081736550133e-07, "loss": 0.4199, "step": 4815 }, { "epoch": 5.393203883495145, "grad_norm": 0.9090914130210876, "learning_rate": 1.2739910234514736e-07, "loss": 0.4111, "step": 4816 }, { "epoch": 5.394324122479462, "grad_norm": 0.9249600172042847, "learning_rate": 1.2692823626086647e-07, "loss": 0.4514, "step": 4817 }, { "epoch": 5.395444361463779, "grad_norm": 0.9792945981025696, "learning_rate": 1.2645821928113755e-07, "loss": 0.4599, "step": 4818 }, { "epoch": 5.396564600448095, "grad_norm": 0.9103566408157349, "learning_rate": 1.259890515741377e-07, "loss": 0.4186, "step": 4819 }, { "epoch": 5.397684839432412, "grad_norm": 0.9507943987846375, "learning_rate": 1.2552073330773878e-07, "loss": 0.4491, "step": 4820 }, { "epoch": 5.3988050784167285, "grad_norm": 0.9543315172195435, "learning_rate": 1.250532646495084e-07, "loss": 0.4506, "step": 4821 }, { "epoch": 5.3999253174010455, "grad_norm": 0.9156606197357178, "learning_rate": 1.245866457667111e-07, "loss": 0.4297, "step": 4822 }, { "epoch": 5.4010455563853625, "grad_norm": 0.9355423450469971, "learning_rate": 1.2412087682630664e-07, "loss": 0.4462, "step": 4823 }, { "epoch": 5.402165795369679, "grad_norm": 0.94163578748703, "learning_rate": 1.236559579949506e-07, "loss": 0.4575, "step": 4824 }, { "epoch": 5.403286034353996, "grad_norm": 0.9443382024765015, "learning_rate": 1.231918894389958e-07, "loss": 0.4345, "step": 4825 }, { "epoch": 5.404406273338312, "grad_norm": 0.9362183809280396, "learning_rate": 1.2272867132448907e-07, "loss": 0.4522, "step": 4826 }, { "epoch": 5.405526512322629, "grad_norm": 0.9279202222824097, "learning_rate": 1.2226630381717398e-07, "loss": 0.4453, "step": 4827 }, { "epoch": 5.406646751306946, "grad_norm": 0.9492947459220886, "learning_rate": 1.2180478708248928e-07, "loss": 0.4549, "step": 4828 }, { "epoch": 5.407766990291262, "grad_norm": 0.957879364490509, "learning_rate": 1.21344121285569e-07, "loss": 0.4371, "step": 4829 }, { "epoch": 5.408887229275579, "grad_norm": 0.9586416482925415, "learning_rate": 1.2088430659124378e-07, "loss": 0.4382, "step": 4830 }, { "epoch": 5.410007468259895, "grad_norm": 0.9220893383026123, "learning_rate": 1.204253431640387e-07, "loss": 0.4317, "step": 4831 }, { "epoch": 5.411127707244212, "grad_norm": 0.9194614887237549, "learning_rate": 1.1996723116817516e-07, "loss": 0.4313, "step": 4832 }, { "epoch": 5.412247946228529, "grad_norm": 0.9240323305130005, "learning_rate": 1.19509970767569e-07, "loss": 0.4253, "step": 4833 }, { "epoch": 5.413368185212845, "grad_norm": 0.9279079437255859, "learning_rate": 1.190535621258318e-07, "loss": 0.4519, "step": 4834 }, { "epoch": 5.414488424197162, "grad_norm": 0.9197219610214233, "learning_rate": 1.1859800540627048e-07, "loss": 0.4506, "step": 4835 }, { "epoch": 5.415608663181478, "grad_norm": 0.975220799446106, "learning_rate": 1.1814330077188657e-07, "loss": 0.4686, "step": 4836 }, { "epoch": 5.416728902165795, "grad_norm": 0.9262548685073853, "learning_rate": 1.1768944838537688e-07, "loss": 0.4311, "step": 4837 }, { "epoch": 5.417849141150112, "grad_norm": 0.9543802738189697, "learning_rate": 1.1723644840913456e-07, "loss": 0.4329, "step": 4838 }, { "epoch": 5.4189693801344285, "grad_norm": 0.971701443195343, "learning_rate": 1.1678430100524607e-07, "loss": 0.4332, "step": 4839 }, { "epoch": 5.4200896191187455, "grad_norm": 0.9203743934631348, "learning_rate": 1.1633300633549367e-07, "loss": 0.4292, "step": 4840 }, { "epoch": 5.421209858103062, "grad_norm": 0.9105783700942993, "learning_rate": 1.15882564561354e-07, "loss": 0.4267, "step": 4841 }, { "epoch": 5.422330097087379, "grad_norm": 0.9422838091850281, "learning_rate": 1.154329758439987e-07, "loss": 0.4485, "step": 4842 }, { "epoch": 5.423450336071696, "grad_norm": 0.9493690133094788, "learning_rate": 1.1498424034429495e-07, "loss": 0.4425, "step": 4843 }, { "epoch": 5.424570575056012, "grad_norm": 0.9260673522949219, "learning_rate": 1.1453635822280373e-07, "loss": 0.4331, "step": 4844 }, { "epoch": 5.425690814040329, "grad_norm": 0.9214688539505005, "learning_rate": 1.1408932963978047e-07, "loss": 0.4306, "step": 4845 }, { "epoch": 5.426811053024645, "grad_norm": 0.9646499156951904, "learning_rate": 1.136431547551764e-07, "loss": 0.4324, "step": 4846 }, { "epoch": 5.427931292008962, "grad_norm": 0.9017336368560791, "learning_rate": 1.1319783372863601e-07, "loss": 0.4373, "step": 4847 }, { "epoch": 5.429051530993279, "grad_norm": 0.9166968464851379, "learning_rate": 1.1275336671949911e-07, "loss": 0.417, "step": 4848 }, { "epoch": 5.430171769977595, "grad_norm": 0.9220467209815979, "learning_rate": 1.1230975388679954e-07, "loss": 0.4325, "step": 4849 }, { "epoch": 5.431292008961912, "grad_norm": 0.938759446144104, "learning_rate": 1.1186699538926565e-07, "loss": 0.4274, "step": 4850 }, { "epoch": 5.432412247946228, "grad_norm": 0.9414494037628174, "learning_rate": 1.114250913853196e-07, "loss": 0.4395, "step": 4851 }, { "epoch": 5.433532486930545, "grad_norm": 0.9817885160446167, "learning_rate": 1.1098404203307905e-07, "loss": 0.4704, "step": 4852 }, { "epoch": 5.434652725914862, "grad_norm": 0.9620175957679749, "learning_rate": 1.1054384749035473e-07, "loss": 0.469, "step": 4853 }, { "epoch": 5.435772964899178, "grad_norm": 0.9467974305152893, "learning_rate": 1.1010450791465204e-07, "loss": 0.4553, "step": 4854 }, { "epoch": 5.436893203883495, "grad_norm": 0.9521004557609558, "learning_rate": 1.0966602346316967e-07, "loss": 0.461, "step": 4855 }, { "epoch": 5.4380134428678115, "grad_norm": 1.0812932252883911, "learning_rate": 1.0922839429280157e-07, "loss": 0.4375, "step": 4856 }, { "epoch": 5.4391336818521285, "grad_norm": 0.9249654412269592, "learning_rate": 1.0879162056013498e-07, "loss": 0.436, "step": 4857 }, { "epoch": 5.4402539208364455, "grad_norm": 0.9406300783157349, "learning_rate": 1.0835570242145072e-07, "loss": 0.4523, "step": 4858 }, { "epoch": 5.441374159820762, "grad_norm": 0.9591256380081177, "learning_rate": 1.0792064003272429e-07, "loss": 0.4546, "step": 4859 }, { "epoch": 5.442494398805079, "grad_norm": 0.9475931525230408, "learning_rate": 1.0748643354962451e-07, "loss": 0.4538, "step": 4860 }, { "epoch": 5.443614637789395, "grad_norm": 0.9184625148773193, "learning_rate": 1.0705308312751433e-07, "loss": 0.4435, "step": 4861 }, { "epoch": 5.444734876773712, "grad_norm": 0.9385193586349487, "learning_rate": 1.0662058892144944e-07, "loss": 0.4352, "step": 4862 }, { "epoch": 5.445855115758029, "grad_norm": 0.9463768005371094, "learning_rate": 1.0618895108617993e-07, "loss": 0.464, "step": 4863 }, { "epoch": 5.446975354742345, "grad_norm": 0.9606723189353943, "learning_rate": 1.057581697761495e-07, "loss": 0.4253, "step": 4864 }, { "epoch": 5.448095593726662, "grad_norm": 0.9273378252983093, "learning_rate": 1.0532824514549538e-07, "loss": 0.4319, "step": 4865 }, { "epoch": 5.449215832710978, "grad_norm": 0.9443404078483582, "learning_rate": 1.0489917734804817e-07, "loss": 0.4481, "step": 4866 }, { "epoch": 5.450336071695295, "grad_norm": 0.9298003315925598, "learning_rate": 1.0447096653733169e-07, "loss": 0.4617, "step": 4867 }, { "epoch": 5.451456310679612, "grad_norm": 0.936625063419342, "learning_rate": 1.0404361286656312e-07, "loss": 0.4445, "step": 4868 }, { "epoch": 5.452576549663928, "grad_norm": 0.9193381071090698, "learning_rate": 1.0361711648865347e-07, "loss": 0.4519, "step": 4869 }, { "epoch": 5.453696788648245, "grad_norm": 0.9468556642532349, "learning_rate": 1.0319147755620651e-07, "loss": 0.4379, "step": 4870 }, { "epoch": 5.454817027632561, "grad_norm": 0.9311325550079346, "learning_rate": 1.0276669622151875e-07, "loss": 0.3899, "step": 4871 }, { "epoch": 5.455937266616878, "grad_norm": 0.9115637540817261, "learning_rate": 1.0234277263658165e-07, "loss": 0.4496, "step": 4872 }, { "epoch": 5.4570575056011945, "grad_norm": 0.9205859303474426, "learning_rate": 1.0191970695307751e-07, "loss": 0.4442, "step": 4873 }, { "epoch": 5.4581777445855115, "grad_norm": 0.9761693477630615, "learning_rate": 1.0149749932238329e-07, "loss": 0.4596, "step": 4874 }, { "epoch": 5.4592979835698285, "grad_norm": 0.9357373714447021, "learning_rate": 1.0107614989556813e-07, "loss": 0.4569, "step": 4875 }, { "epoch": 5.460418222554145, "grad_norm": 0.9188745617866516, "learning_rate": 1.0065565882339423e-07, "loss": 0.4388, "step": 4876 }, { "epoch": 5.461538461538462, "grad_norm": 0.9353392124176025, "learning_rate": 1.0023602625631707e-07, "loss": 0.4512, "step": 4877 }, { "epoch": 5.462658700522778, "grad_norm": 1.0122833251953125, "learning_rate": 9.981725234448375e-08, "loss": 0.4505, "step": 4878 }, { "epoch": 5.463778939507095, "grad_norm": 0.9383930563926697, "learning_rate": 9.93993372377361e-08, "loss": 0.4594, "step": 4879 }, { "epoch": 5.464899178491412, "grad_norm": 0.9439529180526733, "learning_rate": 9.898228108560726e-08, "loss": 0.4462, "step": 4880 }, { "epoch": 5.466019417475728, "grad_norm": 0.9366523623466492, "learning_rate": 9.856608403732315e-08, "loss": 0.4185, "step": 4881 }, { "epoch": 5.467139656460045, "grad_norm": 0.9941008687019348, "learning_rate": 9.815074624180215e-08, "loss": 0.4435, "step": 4882 }, { "epoch": 5.468259895444361, "grad_norm": 0.9119881391525269, "learning_rate": 9.773626784765622e-08, "loss": 0.4504, "step": 4883 }, { "epoch": 5.469380134428678, "grad_norm": 0.9270580410957336, "learning_rate": 9.732264900318866e-08, "loss": 0.4486, "step": 4884 }, { "epoch": 5.470500373412995, "grad_norm": 0.965878963470459, "learning_rate": 9.690988985639582e-08, "loss": 0.4382, "step": 4885 }, { "epoch": 5.471620612397311, "grad_norm": 0.963076651096344, "learning_rate": 9.649799055496679e-08, "loss": 0.445, "step": 4886 }, { "epoch": 5.472740851381628, "grad_norm": 0.9257535338401794, "learning_rate": 9.60869512462817e-08, "loss": 0.429, "step": 4887 }, { "epoch": 5.473861090365944, "grad_norm": 0.9147376418113708, "learning_rate": 9.56767720774146e-08, "loss": 0.4264, "step": 4888 }, { "epoch": 5.474981329350261, "grad_norm": 0.9316163659095764, "learning_rate": 9.526745319513031e-08, "loss": 0.4383, "step": 4889 }, { "epoch": 5.476101568334578, "grad_norm": 0.9454442858695984, "learning_rate": 9.485899474588667e-08, "loss": 0.4489, "step": 4890 }, { "epoch": 5.4772218073188945, "grad_norm": 0.9439064860343933, "learning_rate": 9.445139687583316e-08, "loss": 0.4363, "step": 4891 }, { "epoch": 5.4783420463032115, "grad_norm": 0.9270646572113037, "learning_rate": 9.404465973081256e-08, "loss": 0.4528, "step": 4892 }, { "epoch": 5.479462285287528, "grad_norm": 0.9383407235145569, "learning_rate": 9.36387834563579e-08, "loss": 0.4457, "step": 4893 }, { "epoch": 5.480582524271845, "grad_norm": 0.9024866223335266, "learning_rate": 9.323376819769552e-08, "loss": 0.4346, "step": 4894 }, { "epoch": 5.481702763256162, "grad_norm": 1.2444536685943604, "learning_rate": 9.282961409974256e-08, "loss": 0.432, "step": 4895 }, { "epoch": 5.482823002240478, "grad_norm": 0.9335572123527527, "learning_rate": 9.242632130710971e-08, "loss": 0.4324, "step": 4896 }, { "epoch": 5.483943241224795, "grad_norm": 0.9137328267097473, "learning_rate": 9.202388996409766e-08, "loss": 0.4651, "step": 4897 }, { "epoch": 5.485063480209111, "grad_norm": 0.936955451965332, "learning_rate": 9.162232021469958e-08, "loss": 0.4323, "step": 4898 }, { "epoch": 5.486183719193428, "grad_norm": 0.9421900510787964, "learning_rate": 9.122161220260078e-08, "loss": 0.4643, "step": 4899 }, { "epoch": 5.487303958177745, "grad_norm": 0.9465112090110779, "learning_rate": 9.082176607117798e-08, "loss": 0.4525, "step": 4900 }, { "epoch": 5.488424197162061, "grad_norm": 0.9424898624420166, "learning_rate": 9.042278196349924e-08, "loss": 0.445, "step": 4901 }, { "epoch": 5.489544436146378, "grad_norm": 0.9576553106307983, "learning_rate": 9.002466002232424e-08, "loss": 0.446, "step": 4902 }, { "epoch": 5.490664675130694, "grad_norm": 0.9291338324546814, "learning_rate": 8.962740039010459e-08, "loss": 0.4406, "step": 4903 }, { "epoch": 5.491784914115011, "grad_norm": 0.9292747378349304, "learning_rate": 8.923100320898215e-08, "loss": 0.4204, "step": 4904 }, { "epoch": 5.492905153099328, "grad_norm": 0.9206045269966125, "learning_rate": 8.883546862079234e-08, "loss": 0.4354, "step": 4905 }, { "epoch": 5.494025392083644, "grad_norm": 0.9124464988708496, "learning_rate": 8.844079676706002e-08, "loss": 0.446, "step": 4906 }, { "epoch": 5.495145631067961, "grad_norm": 0.9366148114204407, "learning_rate": 8.804698778900195e-08, "loss": 0.4324, "step": 4907 }, { "epoch": 5.4962658700522775, "grad_norm": 0.9331556558609009, "learning_rate": 8.765404182752624e-08, "loss": 0.4301, "step": 4908 }, { "epoch": 5.4973861090365945, "grad_norm": 0.9406682848930359, "learning_rate": 8.726195902323265e-08, "loss": 0.45, "step": 4909 }, { "epoch": 5.4985063480209115, "grad_norm": 0.9600517153739929, "learning_rate": 8.68707395164109e-08, "loss": 0.4612, "step": 4910 }, { "epoch": 5.499626587005228, "grad_norm": 0.9412708282470703, "learning_rate": 8.648038344704317e-08, "loss": 0.4333, "step": 4911 }, { "epoch": 5.500746825989545, "grad_norm": 0.9558222889900208, "learning_rate": 8.609089095480166e-08, "loss": 0.4279, "step": 4912 }, { "epoch": 5.501867064973861, "grad_norm": 0.9642518758773804, "learning_rate": 8.570226217905015e-08, "loss": 0.4278, "step": 4913 }, { "epoch": 5.502987303958178, "grad_norm": 0.9688398241996765, "learning_rate": 8.531449725884322e-08, "loss": 0.4659, "step": 4914 }, { "epoch": 5.504107542942494, "grad_norm": 0.9442703723907471, "learning_rate": 8.49275963329263e-08, "loss": 0.4585, "step": 4915 }, { "epoch": 5.505227781926811, "grad_norm": 0.9231207370758057, "learning_rate": 8.454155953973586e-08, "loss": 0.4148, "step": 4916 }, { "epoch": 5.506348020911128, "grad_norm": 0.9120611548423767, "learning_rate": 8.415638701739892e-08, "loss": 0.4508, "step": 4917 }, { "epoch": 5.507468259895444, "grad_norm": 0.9500012993812561, "learning_rate": 8.377207890373273e-08, "loss": 0.4639, "step": 4918 }, { "epoch": 5.508588498879761, "grad_norm": 0.9216427206993103, "learning_rate": 8.338863533624703e-08, "loss": 0.4645, "step": 4919 }, { "epoch": 5.509708737864077, "grad_norm": 0.9299259781837463, "learning_rate": 8.300605645214066e-08, "loss": 0.4445, "step": 4920 }, { "epoch": 5.510828976848394, "grad_norm": 0.9613505005836487, "learning_rate": 8.262434238830274e-08, "loss": 0.4369, "step": 4921 }, { "epoch": 5.511949215832711, "grad_norm": 0.9370993971824646, "learning_rate": 8.224349328131487e-08, "loss": 0.4167, "step": 4922 }, { "epoch": 5.513069454817027, "grad_norm": 0.9298410415649414, "learning_rate": 8.186350926744719e-08, "loss": 0.4451, "step": 4923 }, { "epoch": 5.514189693801344, "grad_norm": 0.93707674741745, "learning_rate": 8.148439048266177e-08, "loss": 0.4387, "step": 4924 }, { "epoch": 5.5153099327856605, "grad_norm": 0.9475067853927612, "learning_rate": 8.110613706260928e-08, "loss": 0.4393, "step": 4925 }, { "epoch": 5.5164301717699775, "grad_norm": 0.9321137070655823, "learning_rate": 8.072874914263312e-08, "loss": 0.4508, "step": 4926 }, { "epoch": 5.5175504107542945, "grad_norm": 0.9261823892593384, "learning_rate": 8.035222685776528e-08, "loss": 0.4412, "step": 4927 }, { "epoch": 5.518670649738611, "grad_norm": 0.9505816102027893, "learning_rate": 7.997657034272854e-08, "loss": 0.4266, "step": 4928 }, { "epoch": 5.519790888722928, "grad_norm": 0.9439249038696289, "learning_rate": 7.960177973193567e-08, "loss": 0.4325, "step": 4929 }, { "epoch": 5.520911127707244, "grad_norm": 0.9302672147750854, "learning_rate": 7.922785515949022e-08, "loss": 0.4266, "step": 4930 }, { "epoch": 5.522031366691561, "grad_norm": 0.9192835092544556, "learning_rate": 7.88547967591849e-08, "loss": 0.4502, "step": 4931 }, { "epoch": 5.523151605675878, "grad_norm": 0.9624350070953369, "learning_rate": 7.848260466450375e-08, "loss": 0.4533, "step": 4932 }, { "epoch": 5.524271844660194, "grad_norm": 0.9432851076126099, "learning_rate": 7.811127900861997e-08, "loss": 0.4635, "step": 4933 }, { "epoch": 5.525392083644511, "grad_norm": 0.9556381702423096, "learning_rate": 7.774081992439675e-08, "loss": 0.4278, "step": 4934 }, { "epoch": 5.526512322628827, "grad_norm": 0.9081565141677856, "learning_rate": 7.737122754438691e-08, "loss": 0.4569, "step": 4935 }, { "epoch": 5.527632561613144, "grad_norm": 0.9269652366638184, "learning_rate": 7.70025020008347e-08, "loss": 0.4557, "step": 4936 }, { "epoch": 5.528752800597461, "grad_norm": 0.948623776435852, "learning_rate": 7.663464342567262e-08, "loss": 0.4467, "step": 4937 }, { "epoch": 5.529873039581777, "grad_norm": 0.9134268164634705, "learning_rate": 7.626765195052344e-08, "loss": 0.4224, "step": 4938 }, { "epoch": 5.530993278566094, "grad_norm": 0.9243180155754089, "learning_rate": 7.590152770669962e-08, "loss": 0.436, "step": 4939 }, { "epoch": 5.53211351755041, "grad_norm": 0.9229423999786377, "learning_rate": 7.55362708252036e-08, "loss": 0.4297, "step": 4940 }, { "epoch": 5.533233756534727, "grad_norm": 0.9188770651817322, "learning_rate": 7.517188143672749e-08, "loss": 0.4606, "step": 4941 }, { "epoch": 5.534353995519044, "grad_norm": 0.958724856376648, "learning_rate": 7.480835967165228e-08, "loss": 0.4406, "step": 4942 }, { "epoch": 5.5354742345033605, "grad_norm": 0.8895087242126465, "learning_rate": 7.444570566004977e-08, "loss": 0.4136, "step": 4943 }, { "epoch": 5.5365944734876775, "grad_norm": 0.9197340607643127, "learning_rate": 7.408391953167976e-08, "loss": 0.4232, "step": 4944 }, { "epoch": 5.537714712471994, "grad_norm": 0.8908026814460754, "learning_rate": 7.372300141599231e-08, "loss": 0.4339, "step": 4945 }, { "epoch": 5.538834951456311, "grad_norm": 0.9578010439872742, "learning_rate": 7.336295144212773e-08, "loss": 0.4432, "step": 4946 }, { "epoch": 5.539955190440628, "grad_norm": 0.9140968322753906, "learning_rate": 7.300376973891437e-08, "loss": 0.4333, "step": 4947 }, { "epoch": 5.541075429424944, "grad_norm": 0.9380804896354675, "learning_rate": 7.264545643486997e-08, "loss": 0.4307, "step": 4948 }, { "epoch": 5.542195668409261, "grad_norm": 1.0141738653182983, "learning_rate": 7.228801165820253e-08, "loss": 0.4488, "step": 4949 }, { "epoch": 5.543315907393577, "grad_norm": 0.9352284669876099, "learning_rate": 7.193143553680865e-08, "loss": 0.4437, "step": 4950 }, { "epoch": 5.544436146377894, "grad_norm": 0.9616066813468933, "learning_rate": 7.157572819827401e-08, "loss": 0.4389, "step": 4951 }, { "epoch": 5.545556385362211, "grad_norm": 0.9332475662231445, "learning_rate": 7.122088976987351e-08, "loss": 0.4536, "step": 4952 }, { "epoch": 5.546676624346527, "grad_norm": 0.9388542175292969, "learning_rate": 7.086692037857196e-08, "loss": 0.4446, "step": 4953 }, { "epoch": 5.547796863330844, "grad_norm": 0.9296475648880005, "learning_rate": 7.051382015102165e-08, "loss": 0.4304, "step": 4954 }, { "epoch": 5.54891710231516, "grad_norm": 0.93614661693573, "learning_rate": 7.016158921356514e-08, "loss": 0.4437, "step": 4955 }, { "epoch": 5.550037341299477, "grad_norm": 0.9365259408950806, "learning_rate": 6.981022769223355e-08, "loss": 0.4489, "step": 4956 }, { "epoch": 5.551157580283794, "grad_norm": 0.97031569480896, "learning_rate": 6.945973571274689e-08, "loss": 0.4223, "step": 4957 }, { "epoch": 5.55227781926811, "grad_norm": 0.9004717469215393, "learning_rate": 6.911011340051398e-08, "loss": 0.4422, "step": 4958 }, { "epoch": 5.553398058252427, "grad_norm": 0.9328175783157349, "learning_rate": 6.876136088063257e-08, "loss": 0.4617, "step": 4959 }, { "epoch": 5.5545182972367435, "grad_norm": 0.9549636244773865, "learning_rate": 6.841347827788919e-08, "loss": 0.453, "step": 4960 }, { "epoch": 5.5556385362210605, "grad_norm": 0.9479957818984985, "learning_rate": 6.806646571675902e-08, "loss": 0.4347, "step": 4961 }, { "epoch": 5.5567587752053775, "grad_norm": 0.9500798583030701, "learning_rate": 6.772032332140633e-08, "loss": 0.4322, "step": 4962 }, { "epoch": 5.557879014189694, "grad_norm": 0.9668064713478088, "learning_rate": 6.737505121568345e-08, "loss": 0.4544, "step": 4963 }, { "epoch": 5.558999253174011, "grad_norm": 0.920799195766449, "learning_rate": 6.703064952313182e-08, "loss": 0.4321, "step": 4964 }, { "epoch": 5.560119492158327, "grad_norm": 0.947071373462677, "learning_rate": 6.668711836698066e-08, "loss": 0.4257, "step": 4965 }, { "epoch": 5.561239731142644, "grad_norm": 0.9289594292640686, "learning_rate": 6.634445787014831e-08, "loss": 0.4398, "step": 4966 }, { "epoch": 5.562359970126961, "grad_norm": 0.9757921695709229, "learning_rate": 6.600266815524225e-08, "loss": 0.4295, "step": 4967 }, { "epoch": 5.563480209111277, "grad_norm": 0.9536890983581543, "learning_rate": 6.566174934455688e-08, "loss": 0.4605, "step": 4968 }, { "epoch": 5.564600448095594, "grad_norm": 0.9070764183998108, "learning_rate": 6.532170156007627e-08, "loss": 0.4593, "step": 4969 }, { "epoch": 5.56572068707991, "grad_norm": 0.9359860420227051, "learning_rate": 6.498252492347201e-08, "loss": 0.445, "step": 4970 }, { "epoch": 5.566840926064227, "grad_norm": 0.9033626317977905, "learning_rate": 6.464421955610423e-08, "loss": 0.4031, "step": 4971 }, { "epoch": 5.567961165048544, "grad_norm": 0.9105306267738342, "learning_rate": 6.430678557902109e-08, "loss": 0.442, "step": 4972 }, { "epoch": 5.56908140403286, "grad_norm": 0.9194344878196716, "learning_rate": 6.397022311295991e-08, "loss": 0.4196, "step": 4973 }, { "epoch": 5.570201643017177, "grad_norm": 0.8966240286827087, "learning_rate": 6.363453227834548e-08, "loss": 0.4293, "step": 4974 }, { "epoch": 5.571321882001493, "grad_norm": 0.9588419198989868, "learning_rate": 6.329971319528977e-08, "loss": 0.4609, "step": 4975 }, { "epoch": 5.57244212098581, "grad_norm": 0.9420813322067261, "learning_rate": 6.296576598359499e-08, "loss": 0.4587, "step": 4976 }, { "epoch": 5.573562359970127, "grad_norm": 0.948427677154541, "learning_rate": 6.263269076274974e-08, "loss": 0.4797, "step": 4977 }, { "epoch": 5.5746825989544435, "grad_norm": 0.9331648945808411, "learning_rate": 6.230048765193091e-08, "loss": 0.443, "step": 4978 }, { "epoch": 5.5758028379387605, "grad_norm": 0.9337943196296692, "learning_rate": 6.196915677000343e-08, "loss": 0.4305, "step": 4979 }, { "epoch": 5.576923076923077, "grad_norm": 0.9375690817832947, "learning_rate": 6.163869823552049e-08, "loss": 0.4358, "step": 4980 }, { "epoch": 5.578043315907394, "grad_norm": 0.9160448312759399, "learning_rate": 6.130911216672281e-08, "loss": 0.4259, "step": 4981 }, { "epoch": 5.579163554891711, "grad_norm": 0.9527714848518372, "learning_rate": 6.09803986815391e-08, "loss": 0.434, "step": 4982 }, { "epoch": 5.580283793876027, "grad_norm": 0.9375268220901489, "learning_rate": 6.065255789758529e-08, "loss": 0.4524, "step": 4983 }, { "epoch": 5.581404032860344, "grad_norm": 0.9731276631355286, "learning_rate": 6.032558993216614e-08, "loss": 0.4366, "step": 4984 }, { "epoch": 5.58252427184466, "grad_norm": 0.9452029466629028, "learning_rate": 5.999949490227253e-08, "loss": 0.4599, "step": 4985 }, { "epoch": 5.583644510828977, "grad_norm": 0.9457641839981079, "learning_rate": 5.9674272924585e-08, "loss": 0.4324, "step": 4986 }, { "epoch": 5.584764749813294, "grad_norm": 0.9238290190696716, "learning_rate": 5.934992411547019e-08, "loss": 0.447, "step": 4987 }, { "epoch": 5.58588498879761, "grad_norm": 0.901781439781189, "learning_rate": 5.9026448590982497e-08, "loss": 0.4628, "step": 4988 }, { "epoch": 5.587005227781927, "grad_norm": 0.9303801655769348, "learning_rate": 5.8703846466864336e-08, "loss": 0.4442, "step": 4989 }, { "epoch": 5.588125466766243, "grad_norm": 0.9144951701164246, "learning_rate": 5.838211785854586e-08, "loss": 0.4513, "step": 4990 }, { "epoch": 5.58924570575056, "grad_norm": 0.9388846158981323, "learning_rate": 5.806126288114333e-08, "loss": 0.4554, "step": 4991 }, { "epoch": 5.590365944734877, "grad_norm": 0.9365740418434143, "learning_rate": 5.774128164946186e-08, "loss": 0.4358, "step": 4992 }, { "epoch": 5.591486183719193, "grad_norm": 0.9639397263526917, "learning_rate": 5.742217427799318e-08, "loss": 0.4393, "step": 4993 }, { "epoch": 5.59260642270351, "grad_norm": 0.9237720370292664, "learning_rate": 5.7103940880916807e-08, "loss": 0.4404, "step": 4994 }, { "epoch": 5.5937266616878265, "grad_norm": 0.9420956969261169, "learning_rate": 5.6786581572099155e-08, "loss": 0.4391, "step": 4995 }, { "epoch": 5.5948469006721435, "grad_norm": 0.918408989906311, "learning_rate": 5.647009646509355e-08, "loss": 0.4292, "step": 4996 }, { "epoch": 5.5959671396564605, "grad_norm": 0.9223766326904297, "learning_rate": 5.615448567314136e-08, "loss": 0.441, "step": 4997 }, { "epoch": 5.597087378640777, "grad_norm": 0.9440556168556213, "learning_rate": 5.5839749309170856e-08, "loss": 0.4223, "step": 4998 }, { "epoch": 5.598207617625094, "grad_norm": 0.9228045344352722, "learning_rate": 5.552588748579668e-08, "loss": 0.4426, "step": 4999 }, { "epoch": 5.59932785660941, "grad_norm": 0.9351444244384766, "learning_rate": 5.521290031532178e-08, "loss": 0.4323, "step": 5000 }, { "epoch": 5.600448095593727, "grad_norm": 0.9622311592102051, "learning_rate": 5.490078790973519e-08, "loss": 0.4434, "step": 5001 }, { "epoch": 5.601568334578043, "grad_norm": 0.948804497718811, "learning_rate": 5.4589550380713394e-08, "loss": 0.4514, "step": 5002 }, { "epoch": 5.60268857356236, "grad_norm": 0.9313174486160278, "learning_rate": 5.427918783962011e-08, "loss": 0.4532, "step": 5003 }, { "epoch": 5.603808812546677, "grad_norm": 0.9477012753486633, "learning_rate": 5.39697003975051e-08, "loss": 0.4659, "step": 5004 }, { "epoch": 5.604929051530993, "grad_norm": 0.921179473400116, "learning_rate": 5.366108816510562e-08, "loss": 0.4532, "step": 5005 }, { "epoch": 5.60604929051531, "grad_norm": 0.9506085515022278, "learning_rate": 5.335335125284557e-08, "loss": 0.4456, "step": 5006 }, { "epoch": 5.607169529499626, "grad_norm": 0.9283287525177002, "learning_rate": 5.304648977083604e-08, "loss": 0.4465, "step": 5007 }, { "epoch": 5.608289768483943, "grad_norm": 0.9420786499977112, "learning_rate": 5.274050382887419e-08, "loss": 0.4436, "step": 5008 }, { "epoch": 5.60941000746826, "grad_norm": 0.9651584625244141, "learning_rate": 5.2435393536444947e-08, "loss": 0.4515, "step": 5009 }, { "epoch": 5.610530246452576, "grad_norm": 0.9196774363517761, "learning_rate": 5.213115900271848e-08, "loss": 0.4332, "step": 5010 }, { "epoch": 5.611650485436893, "grad_norm": 0.9109760522842407, "learning_rate": 5.182780033655299e-08, "loss": 0.4517, "step": 5011 }, { "epoch": 5.6127707244212095, "grad_norm": 0.9602428674697876, "learning_rate": 5.152531764649249e-08, "loss": 0.4761, "step": 5012 }, { "epoch": 5.6138909634055265, "grad_norm": 0.9549228549003601, "learning_rate": 5.122371104076762e-08, "loss": 0.4518, "step": 5013 }, { "epoch": 5.6150112023898435, "grad_norm": 0.9305132627487183, "learning_rate": 5.092298062729567e-08, "loss": 0.4267, "step": 5014 }, { "epoch": 5.61613144137416, "grad_norm": 0.9246017932891846, "learning_rate": 5.062312651368112e-08, "loss": 0.4492, "step": 5015 }, { "epoch": 5.617251680358477, "grad_norm": 0.9391462802886963, "learning_rate": 5.032414880721343e-08, "loss": 0.4291, "step": 5016 }, { "epoch": 5.618371919342793, "grad_norm": 0.9422920942306519, "learning_rate": 5.0026047614869785e-08, "loss": 0.4666, "step": 5017 }, { "epoch": 5.61949215832711, "grad_norm": 0.9306696057319641, "learning_rate": 4.9728823043312945e-08, "loss": 0.4454, "step": 5018 }, { "epoch": 5.620612397311427, "grad_norm": 0.9531261324882507, "learning_rate": 4.9432475198892274e-08, "loss": 0.466, "step": 5019 }, { "epoch": 5.621732636295743, "grad_norm": 0.9429807066917419, "learning_rate": 4.913700418764378e-08, "loss": 0.4358, "step": 5020 }, { "epoch": 5.62285287528006, "grad_norm": 0.9192976951599121, "learning_rate": 4.8842410115289284e-08, "loss": 0.4482, "step": 5021 }, { "epoch": 5.623973114264376, "grad_norm": 0.9660887122154236, "learning_rate": 4.8548693087236696e-08, "loss": 0.4597, "step": 5022 }, { "epoch": 5.625093353248693, "grad_norm": 0.9241201281547546, "learning_rate": 4.825585320858084e-08, "loss": 0.4344, "step": 5023 }, { "epoch": 5.62621359223301, "grad_norm": 0.9499978423118591, "learning_rate": 4.796389058410178e-08, "loss": 0.4582, "step": 5024 }, { "epoch": 5.627333831217326, "grad_norm": 0.9370623230934143, "learning_rate": 4.767280531826624e-08, "loss": 0.4438, "step": 5025 }, { "epoch": 5.628454070201643, "grad_norm": 0.95489501953125, "learning_rate": 4.7382597515227e-08, "loss": 0.4492, "step": 5026 }, { "epoch": 5.629574309185959, "grad_norm": 0.9404643774032593, "learning_rate": 4.709326727882296e-08, "loss": 0.4614, "step": 5027 }, { "epoch": 5.630694548170276, "grad_norm": 0.9356158375740051, "learning_rate": 4.6804814712578525e-08, "loss": 0.4213, "step": 5028 }, { "epoch": 5.6318147871545925, "grad_norm": 0.9374412894248962, "learning_rate": 4.651723991970475e-08, "loss": 0.4524, "step": 5029 }, { "epoch": 5.6329350261389095, "grad_norm": 0.9404788017272949, "learning_rate": 4.6230543003098204e-08, "loss": 0.4433, "step": 5030 }, { "epoch": 5.6340552651232265, "grad_norm": 0.9479832053184509, "learning_rate": 4.5944724065341005e-08, "loss": 0.4558, "step": 5031 }, { "epoch": 5.635175504107543, "grad_norm": 0.91698157787323, "learning_rate": 4.5659783208701904e-08, "loss": 0.4245, "step": 5032 }, { "epoch": 5.63629574309186, "grad_norm": 0.9416079521179199, "learning_rate": 4.5375720535134616e-08, "loss": 0.4506, "step": 5033 }, { "epoch": 5.637415982076176, "grad_norm": 0.926604688167572, "learning_rate": 4.509253614627979e-08, "loss": 0.4512, "step": 5034 }, { "epoch": 5.638536221060493, "grad_norm": 0.9347836971282959, "learning_rate": 4.4810230143462754e-08, "loss": 0.4055, "step": 5035 }, { "epoch": 5.63965646004481, "grad_norm": 0.938878059387207, "learning_rate": 4.4528802627694935e-08, "loss": 0.4622, "step": 5036 }, { "epoch": 5.640776699029126, "grad_norm": 0.9338555932044983, "learning_rate": 4.424825369967328e-08, "loss": 0.4368, "step": 5037 }, { "epoch": 5.641896938013443, "grad_norm": 0.9382022619247437, "learning_rate": 4.396858345978056e-08, "loss": 0.4658, "step": 5038 }, { "epoch": 5.643017176997759, "grad_norm": 0.9405156373977661, "learning_rate": 4.368979200808504e-08, "loss": 0.4623, "step": 5039 }, { "epoch": 5.644137415982076, "grad_norm": 0.9451358914375305, "learning_rate": 4.3411879444340835e-08, "loss": 0.4374, "step": 5040 }, { "epoch": 5.645257654966393, "grad_norm": 0.9344345331192017, "learning_rate": 4.3134845867986996e-08, "loss": 0.4612, "step": 5041 }, { "epoch": 5.646377893950709, "grad_norm": 0.929823637008667, "learning_rate": 4.285869137814896e-08, "loss": 0.4306, "step": 5042 }, { "epoch": 5.647498132935026, "grad_norm": 0.9545930624008179, "learning_rate": 4.258341607363658e-08, "loss": 0.4484, "step": 5043 }, { "epoch": 5.648618371919342, "grad_norm": 0.9471821188926697, "learning_rate": 4.230902005294551e-08, "loss": 0.4389, "step": 5044 }, { "epoch": 5.649738610903659, "grad_norm": 0.9563241004943848, "learning_rate": 4.2035503414257494e-08, "loss": 0.4565, "step": 5045 }, { "epoch": 5.650858849887976, "grad_norm": 0.9443740248680115, "learning_rate": 4.176286625543841e-08, "loss": 0.4372, "step": 5046 }, { "epoch": 5.6519790888722925, "grad_norm": 0.9260571599006653, "learning_rate": 4.1491108674040496e-08, "loss": 0.4265, "step": 5047 }, { "epoch": 5.6530993278566095, "grad_norm": 0.9303834438323975, "learning_rate": 4.122023076730042e-08, "loss": 0.4392, "step": 5048 }, { "epoch": 5.654219566840926, "grad_norm": 0.9077342748641968, "learning_rate": 4.0950232632141205e-08, "loss": 0.4102, "step": 5049 }, { "epoch": 5.655339805825243, "grad_norm": 0.9114648699760437, "learning_rate": 4.068111436516975e-08, "loss": 0.4528, "step": 5050 }, { "epoch": 5.65646004480956, "grad_norm": 0.9574813842773438, "learning_rate": 4.041287606267902e-08, "loss": 0.4358, "step": 5051 }, { "epoch": 5.657580283793876, "grad_norm": 0.9544569849967957, "learning_rate": 4.014551782064668e-08, "loss": 0.4576, "step": 5052 }, { "epoch": 5.658700522778193, "grad_norm": 0.9298301339149475, "learning_rate": 3.987903973473622e-08, "loss": 0.4471, "step": 5053 }, { "epoch": 5.659820761762509, "grad_norm": 0.941632866859436, "learning_rate": 3.961344190029498e-08, "loss": 0.447, "step": 5054 }, { "epoch": 5.660941000746826, "grad_norm": 0.9469431638717651, "learning_rate": 3.934872441235665e-08, "loss": 0.4351, "step": 5055 }, { "epoch": 5.662061239731143, "grad_norm": 0.9444685578346252, "learning_rate": 3.908488736563909e-08, "loss": 0.4549, "step": 5056 }, { "epoch": 5.663181478715459, "grad_norm": 0.9237278699874878, "learning_rate": 3.882193085454539e-08, "loss": 0.4334, "step": 5057 }, { "epoch": 5.664301717699776, "grad_norm": 0.9296057820320129, "learning_rate": 3.855985497316361e-08, "loss": 0.4479, "step": 5058 }, { "epoch": 5.665421956684092, "grad_norm": 0.9460605382919312, "learning_rate": 3.8298659815266536e-08, "loss": 0.4433, "step": 5059 }, { "epoch": 5.666542195668409, "grad_norm": 0.9168534874916077, "learning_rate": 3.8038345474311624e-08, "loss": 0.4398, "step": 5060 }, { "epoch": 5.667662434652726, "grad_norm": 0.9438591599464417, "learning_rate": 3.777891204344214e-08, "loss": 0.4304, "step": 5061 }, { "epoch": 5.668782673637042, "grad_norm": 0.9704574942588806, "learning_rate": 3.752035961548522e-08, "loss": 0.4586, "step": 5062 }, { "epoch": 5.669902912621359, "grad_norm": 0.9392066597938538, "learning_rate": 3.7262688282952985e-08, "loss": 0.4334, "step": 5063 }, { "epoch": 5.6710231516056755, "grad_norm": 0.9381819367408752, "learning_rate": 3.700589813804223e-08, "loss": 0.4375, "step": 5064 }, { "epoch": 5.6721433905899925, "grad_norm": 0.96126389503479, "learning_rate": 3.6749989272634734e-08, "loss": 0.4451, "step": 5065 }, { "epoch": 5.6732636295743095, "grad_norm": 0.9626644253730774, "learning_rate": 3.64949617782967e-08, "loss": 0.4505, "step": 5066 }, { "epoch": 5.674383868558626, "grad_norm": 0.9321250319480896, "learning_rate": 3.6240815746279024e-08, "loss": 0.4575, "step": 5067 }, { "epoch": 5.675504107542943, "grad_norm": 0.9462364315986633, "learning_rate": 3.598755126751757e-08, "loss": 0.446, "step": 5068 }, { "epoch": 5.676624346527259, "grad_norm": 0.9179610013961792, "learning_rate": 3.5735168432632364e-08, "loss": 0.4472, "step": 5069 }, { "epoch": 5.677744585511576, "grad_norm": 0.9569368958473206, "learning_rate": 3.548366733192782e-08, "loss": 0.4366, "step": 5070 }, { "epoch": 5.678864824495893, "grad_norm": 0.9761717319488525, "learning_rate": 3.5233048055393074e-08, "loss": 0.4412, "step": 5071 }, { "epoch": 5.679985063480209, "grad_norm": 0.926044762134552, "learning_rate": 3.4983310692701945e-08, "loss": 0.4538, "step": 5072 }, { "epoch": 5.681105302464526, "grad_norm": 0.9307417869567871, "learning_rate": 3.47344553332124e-08, "loss": 0.4278, "step": 5073 }, { "epoch": 5.682225541448842, "grad_norm": 0.9000565409660339, "learning_rate": 3.448648206596711e-08, "loss": 0.4182, "step": 5074 }, { "epoch": 5.683345780433159, "grad_norm": 0.9185408353805542, "learning_rate": 3.4239390979692586e-08, "loss": 0.4606, "step": 5075 }, { "epoch": 5.684466019417476, "grad_norm": 0.9321529865264893, "learning_rate": 3.399318216280062e-08, "loss": 0.4259, "step": 5076 }, { "epoch": 5.685586258401792, "grad_norm": 0.9265441298484802, "learning_rate": 3.3747855703386015e-08, "loss": 0.4357, "step": 5077 }, { "epoch": 5.686706497386109, "grad_norm": 0.8842852711677551, "learning_rate": 3.350341168922938e-08, "loss": 0.4405, "step": 5078 }, { "epoch": 5.687826736370425, "grad_norm": 0.9060944318771362, "learning_rate": 3.325985020779382e-08, "loss": 0.4295, "step": 5079 }, { "epoch": 5.688946975354742, "grad_norm": 0.9133689999580383, "learning_rate": 3.3017171346228504e-08, "loss": 0.4154, "step": 5080 }, { "epoch": 5.690067214339059, "grad_norm": 0.9590209126472473, "learning_rate": 3.2775375191365645e-08, "loss": 0.4398, "step": 5081 }, { "epoch": 5.6911874533233755, "grad_norm": 0.9364238977432251, "learning_rate": 3.253446182972187e-08, "loss": 0.4278, "step": 5082 }, { "epoch": 5.6923076923076925, "grad_norm": 0.9395788908004761, "learning_rate": 3.229443134749793e-08, "loss": 0.4337, "step": 5083 }, { "epoch": 5.693427931292009, "grad_norm": 0.9334552884101868, "learning_rate": 3.205528383057876e-08, "loss": 0.4383, "step": 5084 }, { "epoch": 5.694548170276326, "grad_norm": 0.9298536777496338, "learning_rate": 3.181701936453313e-08, "loss": 0.4525, "step": 5085 }, { "epoch": 5.695668409260643, "grad_norm": 0.9191197156906128, "learning_rate": 3.1579638034614226e-08, "loss": 0.4243, "step": 5086 }, { "epoch": 5.696788648244959, "grad_norm": 0.9447920322418213, "learning_rate": 3.134313992575882e-08, "loss": 0.4541, "step": 5087 }, { "epoch": 5.697908887229276, "grad_norm": 0.9365633130073547, "learning_rate": 3.1107525122588134e-08, "loss": 0.4543, "step": 5088 }, { "epoch": 5.699029126213592, "grad_norm": 0.930171012878418, "learning_rate": 3.087279370940693e-08, "loss": 0.4284, "step": 5089 }, { "epoch": 5.700149365197909, "grad_norm": 0.9149145483970642, "learning_rate": 3.0638945770204153e-08, "loss": 0.4359, "step": 5090 }, { "epoch": 5.701269604182226, "grad_norm": 0.9500421285629272, "learning_rate": 3.040598138865258e-08, "loss": 0.437, "step": 5091 }, { "epoch": 5.702389843166542, "grad_norm": 0.9322507977485657, "learning_rate": 3.017390064810832e-08, "loss": 0.4146, "step": 5092 }, { "epoch": 5.703510082150859, "grad_norm": 0.9579601287841797, "learning_rate": 2.9942703631612167e-08, "loss": 0.4361, "step": 5093 }, { "epoch": 5.704630321135175, "grad_norm": 0.934381902217865, "learning_rate": 2.971239042188795e-08, "loss": 0.446, "step": 5094 }, { "epoch": 5.705750560119492, "grad_norm": 0.9407901763916016, "learning_rate": 2.9482961101344188e-08, "loss": 0.4501, "step": 5095 }, { "epoch": 5.706870799103809, "grad_norm": 1.1030011177062988, "learning_rate": 2.925441575207244e-08, "loss": 0.4465, "step": 5096 }, { "epoch": 5.707991038088125, "grad_norm": 0.930476188659668, "learning_rate": 2.902675445584785e-08, "loss": 0.4256, "step": 5097 }, { "epoch": 5.709111277072442, "grad_norm": 0.9282054305076599, "learning_rate": 2.879997729412942e-08, "loss": 0.4243, "step": 5098 }, { "epoch": 5.7102315160567585, "grad_norm": 0.9239363670349121, "learning_rate": 2.8574084348060306e-08, "loss": 0.4359, "step": 5099 }, { "epoch": 5.7113517550410755, "grad_norm": 0.953469455242157, "learning_rate": 2.8349075698466123e-08, "loss": 0.4516, "step": 5100 }, { "epoch": 5.7124719940253925, "grad_norm": 0.9589713215827942, "learning_rate": 2.812495142585775e-08, "loss": 0.4538, "step": 5101 }, { "epoch": 5.713592233009709, "grad_norm": 0.931533694267273, "learning_rate": 2.7901711610427983e-08, "loss": 0.4353, "step": 5102 }, { "epoch": 5.714712471994026, "grad_norm": 0.9510102272033691, "learning_rate": 2.767935633205432e-08, "loss": 0.4451, "step": 5103 }, { "epoch": 5.715832710978342, "grad_norm": 0.9269766807556152, "learning_rate": 2.7457885670297e-08, "loss": 0.4341, "step": 5104 }, { "epoch": 5.716952949962659, "grad_norm": 0.944033145904541, "learning_rate": 2.723729970440042e-08, "loss": 0.4402, "step": 5105 }, { "epoch": 5.718073188946976, "grad_norm": 0.9254393577575684, "learning_rate": 2.7017598513291165e-08, "loss": 0.4353, "step": 5106 }, { "epoch": 5.719193427931292, "grad_norm": 0.9342643022537231, "learning_rate": 2.6798782175581073e-08, "loss": 0.4433, "step": 5107 }, { "epoch": 5.720313666915609, "grad_norm": 0.9282763004302979, "learning_rate": 2.658085076956418e-08, "loss": 0.4638, "step": 5108 }, { "epoch": 5.721433905899925, "grad_norm": 0.9607644081115723, "learning_rate": 2.6363804373217838e-08, "loss": 0.4438, "step": 5109 }, { "epoch": 5.722554144884242, "grad_norm": 0.9449356198310852, "learning_rate": 2.6147643064203253e-08, "loss": 0.4584, "step": 5110 }, { "epoch": 5.723674383868559, "grad_norm": 0.9424293637275696, "learning_rate": 2.5932366919864947e-08, "loss": 0.4149, "step": 5111 }, { "epoch": 5.724794622852875, "grad_norm": 0.9091436266899109, "learning_rate": 2.571797601722992e-08, "loss": 0.4445, "step": 5112 }, { "epoch": 5.725914861837192, "grad_norm": 0.9216914772987366, "learning_rate": 2.55044704330093e-08, "loss": 0.4418, "step": 5113 }, { "epoch": 5.727035100821508, "grad_norm": 0.9333127737045288, "learning_rate": 2.5291850243597538e-08, "loss": 0.4373, "step": 5114 }, { "epoch": 5.728155339805825, "grad_norm": 0.936339795589447, "learning_rate": 2.508011552507128e-08, "loss": 0.4535, "step": 5115 }, { "epoch": 5.729275578790142, "grad_norm": 0.945304811000824, "learning_rate": 2.4869266353191035e-08, "loss": 0.453, "step": 5116 }, { "epoch": 5.7303958177744585, "grad_norm": 0.9366800785064697, "learning_rate": 2.465930280340062e-08, "loss": 0.421, "step": 5117 }, { "epoch": 5.7315160567587755, "grad_norm": 0.9493923187255859, "learning_rate": 2.4450224950826607e-08, "loss": 0.463, "step": 5118 }, { "epoch": 5.732636295743092, "grad_norm": 0.9144302010536194, "learning_rate": 2.42420328702786e-08, "loss": 0.4513, "step": 5119 }, { "epoch": 5.733756534727409, "grad_norm": 0.9114831686019897, "learning_rate": 2.4034726636249505e-08, "loss": 0.4086, "step": 5120 }, { "epoch": 5.734876773711726, "grad_norm": 0.9329635500907898, "learning_rate": 2.3828306322915272e-08, "loss": 0.4578, "step": 5121 }, { "epoch": 5.735997012696042, "grad_norm": 0.9302771091461182, "learning_rate": 2.3622772004134877e-08, "loss": 0.4266, "step": 5122 }, { "epoch": 5.737117251680359, "grad_norm": 0.9406921863555908, "learning_rate": 2.3418123753450316e-08, "loss": 0.4458, "step": 5123 }, { "epoch": 5.738237490664675, "grad_norm": 0.9414572715759277, "learning_rate": 2.3214361644085803e-08, "loss": 0.4471, "step": 5124 }, { "epoch": 5.739357729648992, "grad_norm": 0.9071601629257202, "learning_rate": 2.301148574894968e-08, "loss": 0.4325, "step": 5125 }, { "epoch": 5.740477968633308, "grad_norm": 0.9605470895767212, "learning_rate": 2.2809496140632492e-08, "loss": 0.4449, "step": 5126 }, { "epoch": 5.741598207617625, "grad_norm": 0.935355544090271, "learning_rate": 2.2608392891407537e-08, "loss": 0.4405, "step": 5127 }, { "epoch": 5.742718446601942, "grad_norm": 0.938082218170166, "learning_rate": 2.2408176073231426e-08, "loss": 0.4371, "step": 5128 }, { "epoch": 5.743838685586258, "grad_norm": 0.9339998960494995, "learning_rate": 2.2208845757743235e-08, "loss": 0.4604, "step": 5129 }, { "epoch": 5.744958924570575, "grad_norm": 0.9430969953536987, "learning_rate": 2.2010402016265086e-08, "loss": 0.4512, "step": 5130 }, { "epoch": 5.746079163554891, "grad_norm": 0.9422865509986877, "learning_rate": 2.1812844919801847e-08, "loss": 0.442, "step": 5131 }, { "epoch": 5.747199402539208, "grad_norm": 0.974510133266449, "learning_rate": 2.1616174539041136e-08, "loss": 0.4443, "step": 5132 }, { "epoch": 5.748319641523525, "grad_norm": 0.9284868240356445, "learning_rate": 2.1420390944352498e-08, "loss": 0.4435, "step": 5133 }, { "epoch": 5.7494398805078415, "grad_norm": 0.9491739273071289, "learning_rate": 2.12254942057899e-08, "loss": 0.4497, "step": 5134 }, { "epoch": 5.7505601194921585, "grad_norm": 0.9356716275215149, "learning_rate": 2.1031484393088387e-08, "loss": 0.4442, "step": 5135 }, { "epoch": 5.751680358476475, "grad_norm": 0.9487676620483398, "learning_rate": 2.08383615756666e-08, "loss": 0.4504, "step": 5136 }, { "epoch": 5.752800597460792, "grad_norm": 0.9076623916625977, "learning_rate": 2.0646125822625374e-08, "loss": 0.4437, "step": 5137 }, { "epoch": 5.753920836445109, "grad_norm": 0.9699704051017761, "learning_rate": 2.04547772027483e-08, "loss": 0.4486, "step": 5138 }, { "epoch": 5.755041075429425, "grad_norm": 0.9283297061920166, "learning_rate": 2.0264315784501167e-08, "loss": 0.4433, "step": 5139 }, { "epoch": 5.756161314413742, "grad_norm": 0.9528547525405884, "learning_rate": 2.007474163603279e-08, "loss": 0.4487, "step": 5140 }, { "epoch": 5.757281553398058, "grad_norm": 0.9525795578956604, "learning_rate": 1.9886054825174472e-08, "loss": 0.4629, "step": 5141 }, { "epoch": 5.758401792382375, "grad_norm": 0.9193012714385986, "learning_rate": 1.9698255419439983e-08, "loss": 0.4499, "step": 5142 }, { "epoch": 5.759522031366692, "grad_norm": 0.9279759526252747, "learning_rate": 1.9511343486025012e-08, "loss": 0.4673, "step": 5143 }, { "epoch": 5.760642270351008, "grad_norm": 0.9476650953292847, "learning_rate": 1.9325319091808847e-08, "loss": 0.4545, "step": 5144 }, { "epoch": 5.761762509335325, "grad_norm": 0.9521321654319763, "learning_rate": 1.9140182303352128e-08, "loss": 0.4487, "step": 5145 }, { "epoch": 5.762882748319641, "grad_norm": 0.9332004189491272, "learning_rate": 1.8955933186898256e-08, "loss": 0.433, "step": 5146 }, { "epoch": 5.764002987303958, "grad_norm": 0.9333416819572449, "learning_rate": 1.8772571808373107e-08, "loss": 0.4348, "step": 5147 }, { "epoch": 5.765123226288274, "grad_norm": 0.9315241575241089, "learning_rate": 1.8590098233385312e-08, "loss": 0.425, "step": 5148 }, { "epoch": 5.766243465272591, "grad_norm": 0.9360141158103943, "learning_rate": 1.8408512527224865e-08, "loss": 0.4537, "step": 5149 }, { "epoch": 5.767363704256908, "grad_norm": 0.9266819953918457, "learning_rate": 1.822781475486507e-08, "loss": 0.4471, "step": 5150 }, { "epoch": 5.7684839432412245, "grad_norm": 0.9555367827415466, "learning_rate": 1.8048004980960875e-08, "loss": 0.4285, "step": 5151 }, { "epoch": 5.7696041822255415, "grad_norm": 0.9334567189216614, "learning_rate": 1.786908326984943e-08, "loss": 0.4194, "step": 5152 }, { "epoch": 5.770724421209858, "grad_norm": 0.913274884223938, "learning_rate": 1.769104968555091e-08, "loss": 0.4322, "step": 5153 }, { "epoch": 5.771844660194175, "grad_norm": 0.9360448718070984, "learning_rate": 1.751390429176658e-08, "loss": 0.4441, "step": 5154 }, { "epoch": 5.772964899178492, "grad_norm": 0.9396491050720215, "learning_rate": 1.733764715188102e-08, "loss": 0.436, "step": 5155 }, { "epoch": 5.774085138162808, "grad_norm": 0.9085388779640198, "learning_rate": 1.7162278328960446e-08, "loss": 0.4367, "step": 5156 }, { "epoch": 5.775205377147125, "grad_norm": 0.9430856108665466, "learning_rate": 1.6987797885752998e-08, "loss": 0.443, "step": 5157 }, { "epoch": 5.776325616131441, "grad_norm": 0.9245429039001465, "learning_rate": 1.681420588468957e-08, "loss": 0.4415, "step": 5158 }, { "epoch": 5.777445855115758, "grad_norm": 0.9312726259231567, "learning_rate": 1.6641502387882424e-08, "loss": 0.4614, "step": 5159 }, { "epoch": 5.778566094100075, "grad_norm": 0.9446535706520081, "learning_rate": 1.6469687457126292e-08, "loss": 0.4316, "step": 5160 }, { "epoch": 5.779686333084391, "grad_norm": 0.948292076587677, "learning_rate": 1.6298761153898113e-08, "loss": 0.4381, "step": 5161 }, { "epoch": 5.780806572068708, "grad_norm": 0.9536921381950378, "learning_rate": 1.6128723539357017e-08, "loss": 0.4294, "step": 5162 }, { "epoch": 5.781926811053024, "grad_norm": 0.9324341416358948, "learning_rate": 1.5959574674343505e-08, "loss": 0.4532, "step": 5163 }, { "epoch": 5.783047050037341, "grad_norm": 0.9473848342895508, "learning_rate": 1.579131461938055e-08, "loss": 0.45, "step": 5164 }, { "epoch": 5.784167289021658, "grad_norm": 0.9504448175430298, "learning_rate": 1.562394343467277e-08, "loss": 0.4594, "step": 5165 }, { "epoch": 5.785287528005974, "grad_norm": 0.930695652961731, "learning_rate": 1.5457461180106993e-08, "loss": 0.444, "step": 5166 }, { "epoch": 5.786407766990291, "grad_norm": 0.9343944191932678, "learning_rate": 1.5291867915252223e-08, "loss": 0.4404, "step": 5167 }, { "epoch": 5.7875280059746075, "grad_norm": 0.9145981073379517, "learning_rate": 1.512716369935885e-08, "loss": 0.4417, "step": 5168 }, { "epoch": 5.7886482449589245, "grad_norm": 0.9341689348220825, "learning_rate": 1.496334859135945e-08, "loss": 0.4248, "step": 5169 }, { "epoch": 5.7897684839432415, "grad_norm": 0.9198418259620667, "learning_rate": 1.480042264986853e-08, "loss": 0.4394, "step": 5170 }, { "epoch": 5.790888722927558, "grad_norm": 0.9119905829429626, "learning_rate": 1.463838593318223e-08, "loss": 0.4206, "step": 5171 }, { "epoch": 5.792008961911875, "grad_norm": 0.9266424179077148, "learning_rate": 1.4477238499278624e-08, "loss": 0.4476, "step": 5172 }, { "epoch": 5.793129200896191, "grad_norm": 0.8908872604370117, "learning_rate": 1.4316980405817416e-08, "loss": 0.4219, "step": 5173 }, { "epoch": 5.794249439880508, "grad_norm": 0.9566959142684937, "learning_rate": 1.4157611710140517e-08, "loss": 0.4629, "step": 5174 }, { "epoch": 5.795369678864825, "grad_norm": 0.9315547347068787, "learning_rate": 1.3999132469270926e-08, "loss": 0.4565, "step": 5175 }, { "epoch": 5.796489917849141, "grad_norm": 0.9324604868888855, "learning_rate": 1.3841542739914671e-08, "loss": 0.4382, "step": 5176 }, { "epoch": 5.797610156833458, "grad_norm": 0.9520989060401917, "learning_rate": 1.3684842578457758e-08, "loss": 0.4751, "step": 5177 }, { "epoch": 5.798730395817774, "grad_norm": 0.9299716353416443, "learning_rate": 1.3529032040969503e-08, "loss": 0.4348, "step": 5178 }, { "epoch": 5.799850634802091, "grad_norm": 0.9259222149848938, "learning_rate": 1.3374111183199479e-08, "loss": 0.441, "step": 5179 }, { "epoch": 5.800970873786408, "grad_norm": 0.944946825504303, "learning_rate": 1.3220080060580287e-08, "loss": 0.4832, "step": 5180 }, { "epoch": 5.802091112770724, "grad_norm": 0.9561557769775391, "learning_rate": 1.3066938728225064e-08, "loss": 0.4365, "step": 5181 }, { "epoch": 5.803211351755041, "grad_norm": 0.9285265803337097, "learning_rate": 1.2914687240929424e-08, "loss": 0.4464, "step": 5182 }, { "epoch": 5.804331590739357, "grad_norm": 0.9494893550872803, "learning_rate": 1.276332565316979e-08, "loss": 0.4377, "step": 5183 }, { "epoch": 5.805451829723674, "grad_norm": 0.9636561870574951, "learning_rate": 1.2612854019104782e-08, "loss": 0.4346, "step": 5184 }, { "epoch": 5.806572068707991, "grad_norm": 0.8948811888694763, "learning_rate": 1.2463272392574666e-08, "loss": 0.4429, "step": 5185 }, { "epoch": 5.8076923076923075, "grad_norm": 0.9194246530532837, "learning_rate": 1.231458082710052e-08, "loss": 0.4205, "step": 5186 }, { "epoch": 5.8088125466766245, "grad_norm": 0.9340715408325195, "learning_rate": 1.2166779375885617e-08, "loss": 0.4287, "step": 5187 }, { "epoch": 5.809932785660941, "grad_norm": 0.9383190870285034, "learning_rate": 1.2019868091814324e-08, "loss": 0.4403, "step": 5188 }, { "epoch": 5.811053024645258, "grad_norm": 0.9189016819000244, "learning_rate": 1.1873847027452922e-08, "loss": 0.4475, "step": 5189 }, { "epoch": 5.812173263629575, "grad_norm": 0.9099273681640625, "learning_rate": 1.1728716235049065e-08, "loss": 0.4397, "step": 5190 }, { "epoch": 5.813293502613891, "grad_norm": 0.9373763203620911, "learning_rate": 1.1584475766531489e-08, "loss": 0.4417, "step": 5191 }, { "epoch": 5.814413741598208, "grad_norm": 0.9561903476715088, "learning_rate": 1.1441125673510856e-08, "loss": 0.459, "step": 5192 }, { "epoch": 5.815533980582524, "grad_norm": 0.9183167219161987, "learning_rate": 1.1298666007278913e-08, "loss": 0.4579, "step": 5193 }, { "epoch": 5.816654219566841, "grad_norm": 0.9770459532737732, "learning_rate": 1.1157096818808499e-08, "loss": 0.4584, "step": 5194 }, { "epoch": 5.817774458551158, "grad_norm": 0.9642400741577148, "learning_rate": 1.1016418158754927e-08, "loss": 0.4519, "step": 5195 }, { "epoch": 5.818894697535474, "grad_norm": 0.958884596824646, "learning_rate": 1.0876630077453487e-08, "loss": 0.4596, "step": 5196 }, { "epoch": 5.820014936519791, "grad_norm": 0.9514954090118408, "learning_rate": 1.0737732624922226e-08, "loss": 0.4429, "step": 5197 }, { "epoch": 5.821135175504107, "grad_norm": 0.9497402906417847, "learning_rate": 1.0599725850859166e-08, "loss": 0.4576, "step": 5198 }, { "epoch": 5.822255414488424, "grad_norm": 0.9300278425216675, "learning_rate": 1.046260980464453e-08, "loss": 0.446, "step": 5199 }, { "epoch": 5.823375653472741, "grad_norm": 0.9288781881332397, "learning_rate": 1.032638453533935e-08, "loss": 0.4216, "step": 5200 }, { "epoch": 5.824495892457057, "grad_norm": 0.9505265951156616, "learning_rate": 1.0191050091686583e-08, "loss": 0.4403, "step": 5201 }, { "epoch": 5.825616131441374, "grad_norm": 0.9399741888046265, "learning_rate": 1.0056606522109713e-08, "loss": 0.4478, "step": 5202 }, { "epoch": 5.8267363704256905, "grad_norm": 0.9153071641921997, "learning_rate": 9.923053874713872e-09, "loss": 0.434, "step": 5203 }, { "epoch": 5.8278566094100075, "grad_norm": 0.9460898041725159, "learning_rate": 9.790392197285004e-09, "loss": 0.4401, "step": 5204 }, { "epoch": 5.8289768483943245, "grad_norm": 0.9375331401824951, "learning_rate": 9.658621537290969e-09, "loss": 0.4437, "step": 5205 }, { "epoch": 5.830097087378641, "grad_norm": 0.9551233053207397, "learning_rate": 9.527741941880164e-09, "loss": 0.4453, "step": 5206 }, { "epoch": 5.831217326362958, "grad_norm": 0.9369692802429199, "learning_rate": 9.397753457882352e-09, "loss": 0.441, "step": 5207 }, { "epoch": 5.832337565347274, "grad_norm": 0.9248644113540649, "learning_rate": 9.268656131808385e-09, "loss": 0.4345, "step": 5208 }, { "epoch": 5.833457804331591, "grad_norm": 0.9489544034004211, "learning_rate": 9.140450009850754e-09, "loss": 0.4556, "step": 5209 }, { "epoch": 5.834578043315908, "grad_norm": 0.95416259765625, "learning_rate": 9.013135137882211e-09, "loss": 0.4614, "step": 5210 }, { "epoch": 5.835698282300224, "grad_norm": 0.9473898410797119, "learning_rate": 8.886711561457428e-09, "loss": 0.4476, "step": 5211 }, { "epoch": 5.836818521284541, "grad_norm": 0.9452112913131714, "learning_rate": 8.761179325811331e-09, "loss": 0.4553, "step": 5212 }, { "epoch": 5.837938760268857, "grad_norm": 0.9371291995048523, "learning_rate": 8.636538475860767e-09, "loss": 0.4256, "step": 5213 }, { "epoch": 5.839058999253174, "grad_norm": 0.9704864621162415, "learning_rate": 8.51278905620312e-09, "loss": 0.467, "step": 5214 }, { "epoch": 5.840179238237491, "grad_norm": 0.921305775642395, "learning_rate": 8.389931111117133e-09, "loss": 0.444, "step": 5215 }, { "epoch": 5.841299477221807, "grad_norm": 0.9225075840950012, "learning_rate": 8.26796468456209e-09, "loss": 0.4415, "step": 5216 }, { "epoch": 5.842419716206124, "grad_norm": 0.9183089137077332, "learning_rate": 8.146889820178915e-09, "loss": 0.4086, "step": 5217 }, { "epoch": 5.84353995519044, "grad_norm": 0.9084364771842957, "learning_rate": 8.026706561288788e-09, "loss": 0.4158, "step": 5218 }, { "epoch": 5.844660194174757, "grad_norm": 0.9355397820472717, "learning_rate": 7.90741495089481e-09, "loss": 0.4518, "step": 5219 }, { "epoch": 5.845780433159074, "grad_norm": 0.9374178647994995, "learning_rate": 7.789015031679781e-09, "loss": 0.4577, "step": 5220 }, { "epoch": 5.8469006721433905, "grad_norm": 0.9746025204658508, "learning_rate": 7.671506846008703e-09, "loss": 0.4243, "step": 5221 }, { "epoch": 5.8480209111277075, "grad_norm": 0.937898576259613, "learning_rate": 7.554890435926832e-09, "loss": 0.4497, "step": 5222 }, { "epoch": 5.849141150112024, "grad_norm": 0.9105003476142883, "learning_rate": 7.439165843160512e-09, "loss": 0.4252, "step": 5223 }, { "epoch": 5.850261389096341, "grad_norm": 0.9634050130844116, "learning_rate": 7.324333109116899e-09, "loss": 0.4458, "step": 5224 }, { "epoch": 5.851381628080658, "grad_norm": 0.964915931224823, "learning_rate": 7.210392274883959e-09, "loss": 0.4305, "step": 5225 }, { "epoch": 5.852501867064974, "grad_norm": 0.9199424386024475, "learning_rate": 7.097343381230748e-09, "loss": 0.4394, "step": 5226 }, { "epoch": 5.853622106049291, "grad_norm": 0.9280811548233032, "learning_rate": 6.985186468607408e-09, "loss": 0.4444, "step": 5227 }, { "epoch": 5.854742345033607, "grad_norm": 0.9110672473907471, "learning_rate": 6.873921577144061e-09, "loss": 0.4517, "step": 5228 }, { "epoch": 5.855862584017924, "grad_norm": 0.9581495523452759, "learning_rate": 6.763548746652471e-09, "loss": 0.4686, "step": 5229 }, { "epoch": 5.856982823002241, "grad_norm": 0.9365763664245605, "learning_rate": 6.654068016624937e-09, "loss": 0.4392, "step": 5230 }, { "epoch": 5.858103061986557, "grad_norm": 0.9527849555015564, "learning_rate": 6.545479426234846e-09, "loss": 0.4572, "step": 5231 }, { "epoch": 5.859223300970874, "grad_norm": 0.9232441782951355, "learning_rate": 6.437783014335563e-09, "loss": 0.437, "step": 5232 }, { "epoch": 5.86034353995519, "grad_norm": 0.9859960079193115, "learning_rate": 6.330978819461819e-09, "loss": 0.4423, "step": 5233 }, { "epoch": 5.861463778939507, "grad_norm": 0.9566417336463928, "learning_rate": 6.225066879829433e-09, "loss": 0.4384, "step": 5234 }, { "epoch": 5.862584017923824, "grad_norm": 0.8941682577133179, "learning_rate": 6.120047233334203e-09, "loss": 0.4125, "step": 5235 }, { "epoch": 5.86370425690814, "grad_norm": 0.9280607104301453, "learning_rate": 6.015919917553292e-09, "loss": 0.4202, "step": 5236 }, { "epoch": 5.864824495892457, "grad_norm": 0.916027843952179, "learning_rate": 5.91268496974412e-09, "loss": 0.4338, "step": 5237 }, { "epoch": 5.8659447348767735, "grad_norm": 0.9227666258811951, "learning_rate": 5.810342426844917e-09, "loss": 0.4246, "step": 5238 }, { "epoch": 5.8670649738610905, "grad_norm": 0.9268730282783508, "learning_rate": 5.708892325475002e-09, "loss": 0.4371, "step": 5239 }, { "epoch": 5.8681852128454075, "grad_norm": 0.9148648381233215, "learning_rate": 5.608334701933671e-09, "loss": 0.4316, "step": 5240 }, { "epoch": 5.869305451829724, "grad_norm": 0.9382950067520142, "learning_rate": 5.508669592201587e-09, "loss": 0.4445, "step": 5241 }, { "epoch": 5.870425690814041, "grad_norm": 0.9460995197296143, "learning_rate": 5.409897031939393e-09, "loss": 0.4592, "step": 5242 }, { "epoch": 5.871545929798357, "grad_norm": 0.9372912645339966, "learning_rate": 5.312017056489094e-09, "loss": 0.4723, "step": 5243 }, { "epoch": 5.872666168782674, "grad_norm": 0.9569844007492065, "learning_rate": 5.215029700872954e-09, "loss": 0.4513, "step": 5244 }, { "epoch": 5.87378640776699, "grad_norm": 0.914850652217865, "learning_rate": 5.11893499979349e-09, "loss": 0.431, "step": 5245 }, { "epoch": 5.874906646751307, "grad_norm": 0.9579251408576965, "learning_rate": 5.023732987634311e-09, "loss": 0.4611, "step": 5246 }, { "epoch": 5.876026885735624, "grad_norm": 0.9552035927772522, "learning_rate": 4.9294236984598344e-09, "loss": 0.4577, "step": 5247 }, { "epoch": 5.87714712471994, "grad_norm": 0.9273577332496643, "learning_rate": 4.836007166014179e-09, "loss": 0.4341, "step": 5248 }, { "epoch": 5.878267363704257, "grad_norm": 0.9276472330093384, "learning_rate": 4.743483423722828e-09, "loss": 0.4443, "step": 5249 }, { "epoch": 5.879387602688573, "grad_norm": 0.9049580097198486, "learning_rate": 4.651852504691523e-09, "loss": 0.4399, "step": 5250 }, { "epoch": 5.88050784167289, "grad_norm": 0.9013394117355347, "learning_rate": 4.56111444170626e-09, "loss": 0.4016, "step": 5251 }, { "epoch": 5.881628080657207, "grad_norm": 0.9314794540405273, "learning_rate": 4.471269267234401e-09, "loss": 0.4623, "step": 5252 }, { "epoch": 5.882748319641523, "grad_norm": 0.9425100684165955, "learning_rate": 4.38231701342301e-09, "loss": 0.4426, "step": 5253 }, { "epoch": 5.88386855862584, "grad_norm": 0.943638026714325, "learning_rate": 4.294257712099681e-09, "loss": 0.4261, "step": 5254 }, { "epoch": 5.8849887976101565, "grad_norm": 0.9129411578178406, "learning_rate": 4.2070913947731e-09, "loss": 0.421, "step": 5255 }, { "epoch": 5.8861090365944735, "grad_norm": 0.9454447031021118, "learning_rate": 4.120818092632206e-09, "loss": 0.4434, "step": 5256 }, { "epoch": 5.8872292755787905, "grad_norm": 0.9184751510620117, "learning_rate": 4.035437836545919e-09, "loss": 0.4173, "step": 5257 }, { "epoch": 5.888349514563107, "grad_norm": 0.9135808944702148, "learning_rate": 3.950950657063968e-09, "loss": 0.4484, "step": 5258 }, { "epoch": 5.889469753547424, "grad_norm": 0.9499017000198364, "learning_rate": 3.867356584416893e-09, "loss": 0.4563, "step": 5259 }, { "epoch": 5.89058999253174, "grad_norm": 0.9413933753967285, "learning_rate": 3.784655648515212e-09, "loss": 0.454, "step": 5260 }, { "epoch": 5.891710231516057, "grad_norm": 0.9678362011909485, "learning_rate": 3.7028478789499777e-09, "loss": 0.4388, "step": 5261 }, { "epoch": 5.892830470500374, "grad_norm": 0.9494689106941223, "learning_rate": 3.6219333049927753e-09, "loss": 0.442, "step": 5262 }, { "epoch": 5.89395070948469, "grad_norm": 0.9225361347198486, "learning_rate": 3.541911955595445e-09, "loss": 0.4556, "step": 5263 }, { "epoch": 5.895070948469007, "grad_norm": 0.9365661144256592, "learning_rate": 3.4627838593900843e-09, "loss": 0.4396, "step": 5264 }, { "epoch": 5.896191187453323, "grad_norm": 0.9467551112174988, "learning_rate": 3.3845490446896e-09, "loss": 0.4432, "step": 5265 }, { "epoch": 5.89731142643764, "grad_norm": 0.9156452417373657, "learning_rate": 3.3072075394868784e-09, "loss": 0.4499, "step": 5266 }, { "epoch": 5.898431665421957, "grad_norm": 0.9357219934463501, "learning_rate": 3.230759371455616e-09, "loss": 0.4502, "step": 5267 }, { "epoch": 5.899551904406273, "grad_norm": 0.916267991065979, "learning_rate": 3.1552045679494882e-09, "loss": 0.4071, "step": 5268 }, { "epoch": 5.90067214339059, "grad_norm": 0.9392920136451721, "learning_rate": 3.080543156002147e-09, "loss": 0.453, "step": 5269 }, { "epoch": 5.901792382374906, "grad_norm": 0.9510672092437744, "learning_rate": 3.00677516232889e-09, "loss": 0.4427, "step": 5270 }, { "epoch": 5.902912621359223, "grad_norm": 0.9225230813026428, "learning_rate": 2.933900613324159e-09, "loss": 0.4352, "step": 5271 }, { "epoch": 5.9040328603435395, "grad_norm": 0.9586344361305237, "learning_rate": 2.8619195350626516e-09, "loss": 0.4491, "step": 5272 }, { "epoch": 5.9051530993278565, "grad_norm": 0.9399868845939636, "learning_rate": 2.7908319533004326e-09, "loss": 0.4498, "step": 5273 }, { "epoch": 5.9062733383121735, "grad_norm": 0.911294162273407, "learning_rate": 2.7206378934729883e-09, "loss": 0.4272, "step": 5274 }, { "epoch": 5.90739357729649, "grad_norm": 0.959750771522522, "learning_rate": 2.6513373806960617e-09, "loss": 0.4331, "step": 5275 }, { "epoch": 5.908513816280807, "grad_norm": 0.922585129737854, "learning_rate": 2.582930439766207e-09, "loss": 0.4294, "step": 5276 }, { "epoch": 5.909634055265123, "grad_norm": 0.9231391549110413, "learning_rate": 2.5154170951599556e-09, "loss": 0.4389, "step": 5277 }, { "epoch": 5.91075429424944, "grad_norm": 0.95365971326828, "learning_rate": 2.448797371034095e-09, "loss": 0.4419, "step": 5278 }, { "epoch": 5.911874533233757, "grad_norm": 0.9095221757888794, "learning_rate": 2.383071291225947e-09, "loss": 0.4378, "step": 5279 }, { "epoch": 5.912994772218073, "grad_norm": 0.9631744623184204, "learning_rate": 2.318238879252255e-09, "loss": 0.4373, "step": 5280 }, { "epoch": 5.91411501120239, "grad_norm": 0.9247034788131714, "learning_rate": 2.2543001583114066e-09, "loss": 0.44, "step": 5281 }, { "epoch": 5.915235250186706, "grad_norm": 0.960638165473938, "learning_rate": 2.1912551512803803e-09, "loss": 0.465, "step": 5282 }, { "epoch": 5.916355489171023, "grad_norm": 0.936656653881073, "learning_rate": 2.129103880717798e-09, "loss": 0.4399, "step": 5283 }, { "epoch": 5.91747572815534, "grad_norm": 0.91994708776474, "learning_rate": 2.0678463688617033e-09, "loss": 0.4257, "step": 5284 }, { "epoch": 5.918595967139656, "grad_norm": 0.9506680369377136, "learning_rate": 2.007482637630398e-09, "loss": 0.4301, "step": 5285 }, { "epoch": 5.919716206123973, "grad_norm": 0.9183688163757324, "learning_rate": 1.9480127086224375e-09, "loss": 0.448, "step": 5286 }, { "epoch": 5.920836445108289, "grad_norm": 0.9322885870933533, "learning_rate": 1.8894366031171894e-09, "loss": 0.4365, "step": 5287 }, { "epoch": 5.921956684092606, "grad_norm": 0.945323646068573, "learning_rate": 1.8317543420731664e-09, "loss": 0.4402, "step": 5288 }, { "epoch": 5.923076923076923, "grad_norm": 0.9463900327682495, "learning_rate": 1.7749659461296919e-09, "loss": 0.4496, "step": 5289 }, { "epoch": 5.9241971620612395, "grad_norm": 0.9102851748466492, "learning_rate": 1.7190714356060678e-09, "loss": 0.4462, "step": 5290 }, { "epoch": 5.9253174010455565, "grad_norm": 0.9417319297790527, "learning_rate": 1.6640708305021292e-09, "loss": 0.4453, "step": 5291 }, { "epoch": 5.926437640029873, "grad_norm": 0.9399614930152893, "learning_rate": 1.609964150497134e-09, "loss": 0.4266, "step": 5292 }, { "epoch": 5.92755787901419, "grad_norm": 0.9275885224342346, "learning_rate": 1.5567514149508744e-09, "loss": 0.4394, "step": 5293 }, { "epoch": 5.928678117998507, "grad_norm": 0.8977965712547302, "learning_rate": 1.5044326429036748e-09, "loss": 0.4186, "step": 5294 }, { "epoch": 5.929798356982823, "grad_norm": 0.9469898343086243, "learning_rate": 1.453007853075561e-09, "loss": 0.4535, "step": 5295 }, { "epoch": 5.93091859596714, "grad_norm": 0.9316045045852661, "learning_rate": 1.4024770638662588e-09, "loss": 0.4297, "step": 5296 }, { "epoch": 5.932038834951456, "grad_norm": 0.9570934176445007, "learning_rate": 1.3528402933568607e-09, "loss": 0.4236, "step": 5297 }, { "epoch": 5.933159073935773, "grad_norm": 0.9548588991165161, "learning_rate": 1.3040975593070493e-09, "loss": 0.4525, "step": 5298 }, { "epoch": 5.93427931292009, "grad_norm": 0.9237076044082642, "learning_rate": 1.2562488791578731e-09, "loss": 0.4398, "step": 5299 }, { "epoch": 5.935399551904406, "grad_norm": 0.9269155263900757, "learning_rate": 1.2092942700298038e-09, "loss": 0.4466, "step": 5300 }, { "epoch": 5.936519790888723, "grad_norm": 0.9893193244934082, "learning_rate": 1.1632337487238465e-09, "loss": 0.4503, "step": 5301 }, { "epoch": 5.937640029873039, "grad_norm": 0.9254738688468933, "learning_rate": 1.1180673317201518e-09, "loss": 0.4458, "step": 5302 }, { "epoch": 5.938760268857356, "grad_norm": 0.8995742201805115, "learning_rate": 1.0737950351805138e-09, "loss": 0.4314, "step": 5303 }, { "epoch": 5.939880507841673, "grad_norm": 0.9708057045936584, "learning_rate": 1.030416874945317e-09, "loss": 0.4603, "step": 5304 }, { "epoch": 5.941000746825989, "grad_norm": 0.9245232343673706, "learning_rate": 9.879328665357567e-10, "loss": 0.4516, "step": 5305 }, { "epoch": 5.942120985810306, "grad_norm": 0.9299638271331787, "learning_rate": 9.463430251530071e-10, "loss": 0.4118, "step": 5306 }, { "epoch": 5.9432412247946225, "grad_norm": 0.9266724586486816, "learning_rate": 9.05647365678497e-10, "loss": 0.4539, "step": 5307 }, { "epoch": 5.9443614637789395, "grad_norm": 0.9498264789581299, "learning_rate": 8.658459026730792e-10, "loss": 0.455, "step": 5308 }, { "epoch": 5.9454817027632565, "grad_norm": 0.9113919734954834, "learning_rate": 8.269386503781395e-10, "loss": 0.4393, "step": 5309 }, { "epoch": 5.946601941747573, "grad_norm": 0.9509497880935669, "learning_rate": 7.889256227150421e-10, "loss": 0.4464, "step": 5310 }, { "epoch": 5.94772218073189, "grad_norm": 0.9380687475204468, "learning_rate": 7.518068332851291e-10, "loss": 0.4394, "step": 5311 }, { "epoch": 5.948842419716206, "grad_norm": 0.9112431406974792, "learning_rate": 7.155822953699987e-10, "loss": 0.4431, "step": 5312 }, { "epoch": 5.949962658700523, "grad_norm": 0.9073076248168945, "learning_rate": 6.802520219309494e-10, "loss": 0.4334, "step": 5313 }, { "epoch": 5.95108289768484, "grad_norm": 0.969815731048584, "learning_rate": 6.458160256092583e-10, "loss": 0.4504, "step": 5314 }, { "epoch": 5.952203136669156, "grad_norm": 0.9150419235229492, "learning_rate": 6.122743187267355e-10, "loss": 0.4357, "step": 5315 }, { "epoch": 5.953323375653473, "grad_norm": 0.9409524202346802, "learning_rate": 5.79626913284892e-10, "loss": 0.4423, "step": 5316 }, { "epoch": 5.954443614637789, "grad_norm": 0.9285082817077637, "learning_rate": 5.478738209649392e-10, "loss": 0.4261, "step": 5317 }, { "epoch": 5.955563853622106, "grad_norm": 0.9382633566856384, "learning_rate": 5.170150531283447e-10, "loss": 0.4367, "step": 5318 }, { "epoch": 5.956684092606423, "grad_norm": 0.9371407628059387, "learning_rate": 4.870506208171088e-10, "loss": 0.4212, "step": 5319 }, { "epoch": 5.957804331590739, "grad_norm": 0.9549720287322998, "learning_rate": 4.57980534752378e-10, "loss": 0.4487, "step": 5320 }, { "epoch": 5.958924570575056, "grad_norm": 0.9276226758956909, "learning_rate": 4.2980480533555415e-10, "loss": 0.4163, "step": 5321 }, { "epoch": 5.960044809559372, "grad_norm": 0.9237220883369446, "learning_rate": 4.0252344264857245e-10, "loss": 0.4382, "step": 5322 }, { "epoch": 5.961165048543689, "grad_norm": 0.928083062171936, "learning_rate": 3.761364564527914e-10, "loss": 0.432, "step": 5323 }, { "epoch": 5.962285287528006, "grad_norm": 0.9377661943435669, "learning_rate": 3.5064385618927e-10, "loss": 0.4503, "step": 5324 }, { "epoch": 5.9634055265123225, "grad_norm": 0.9240480065345764, "learning_rate": 3.260456509801557e-10, "loss": 0.4367, "step": 5325 }, { "epoch": 5.9645257654966395, "grad_norm": 0.9639571905136108, "learning_rate": 3.023418496261865e-10, "loss": 0.4597, "step": 5326 }, { "epoch": 5.965646004480956, "grad_norm": 0.9551587104797363, "learning_rate": 2.795324606094663e-10, "loss": 0.4463, "step": 5327 }, { "epoch": 5.966766243465273, "grad_norm": 0.9376123547554016, "learning_rate": 2.576174920906893e-10, "loss": 0.4582, "step": 5328 }, { "epoch": 5.96788648244959, "grad_norm": 0.9219816327095032, "learning_rate": 2.36596951911916e-10, "loss": 0.4376, "step": 5329 }, { "epoch": 5.969006721433906, "grad_norm": 0.9160928130149841, "learning_rate": 2.1647084759379712e-10, "loss": 0.4333, "step": 5330 }, { "epoch": 5.970126960418223, "grad_norm": 0.9377449750900269, "learning_rate": 1.972391863380718e-10, "loss": 0.4259, "step": 5331 }, { "epoch": 5.971247199402539, "grad_norm": 0.9307080507278442, "learning_rate": 1.7890197502590244e-10, "loss": 0.4422, "step": 5332 }, { "epoch": 5.972367438386856, "grad_norm": 0.9451398253440857, "learning_rate": 1.6145922021842952e-10, "loss": 0.4452, "step": 5333 }, { "epoch": 5.973487677371173, "grad_norm": 0.9307195544242859, "learning_rate": 1.449109281564942e-10, "loss": 0.4293, "step": 5334 }, { "epoch": 5.974607916355489, "grad_norm": 0.9635918140411377, "learning_rate": 1.2925710476202614e-10, "loss": 0.4735, "step": 5335 }, { "epoch": 5.975728155339806, "grad_norm": 0.950736939907074, "learning_rate": 1.1449775563526777e-10, "loss": 0.4471, "step": 5336 }, { "epoch": 5.976848394324122, "grad_norm": 0.9284517168998718, "learning_rate": 1.0063288605782762e-10, "loss": 0.4346, "step": 5337 }, { "epoch": 5.977968633308439, "grad_norm": 0.925519585609436, "learning_rate": 8.766250099018214e-11, "loss": 0.4514, "step": 5338 }, { "epoch": 5.979088872292756, "grad_norm": 0.9281167984008789, "learning_rate": 7.55866050736187e-11, "loss": 0.4402, "step": 5339 }, { "epoch": 5.980209111277072, "grad_norm": 0.959627091884613, "learning_rate": 6.440520262884775e-11, "loss": 0.442, "step": 5340 }, { "epoch": 5.981329350261389, "grad_norm": 0.9130333065986633, "learning_rate": 5.411829765655796e-11, "loss": 0.4346, "step": 5341 }, { "epoch": 5.9824495892457055, "grad_norm": 0.9627024531364441, "learning_rate": 4.4725893837693766e-11, "loss": 0.4511, "step": 5342 }, { "epoch": 5.9835698282300225, "grad_norm": 0.9444242119789124, "learning_rate": 3.6227994532622714e-11, "loss": 0.437, "step": 5343 }, { "epoch": 5.9846900672143395, "grad_norm": 0.9357147812843323, "learning_rate": 2.8624602782523213e-11, "loss": 0.4328, "step": 5344 }, { "epoch": 5.985810306198656, "grad_norm": 0.934400737285614, "learning_rate": 2.1915721307441684e-11, "loss": 0.4474, "step": 5345 }, { "epoch": 5.986930545182973, "grad_norm": 0.9486119151115417, "learning_rate": 1.6101352507957856e-11, "loss": 0.4515, "step": 5346 }, { "epoch": 5.988050784167289, "grad_norm": 0.9428676962852478, "learning_rate": 1.118149846462968e-11, "loss": 0.4479, "step": 5347 }, { "epoch": 5.989171023151606, "grad_norm": 0.9599880576133728, "learning_rate": 7.156160937715762e-12, "loss": 0.4614, "step": 5348 }, { "epoch": 5.990291262135923, "grad_norm": 0.9297438859939575, "learning_rate": 4.025341367730473e-12, "loss": 0.4589, "step": 5349 }, { "epoch": 5.991411501120239, "grad_norm": 0.9593260288238525, "learning_rate": 1.7890408746112919e-12, "loss": 0.4452, "step": 5350 }, { "epoch": 5.992531740104556, "grad_norm": 0.936557948589325, "learning_rate": 4.4726025855146294e-13, "loss": 0.467, "step": 5351 }, { "epoch": 5.993651979088872, "grad_norm": 0.9610553979873657, "learning_rate": 0.0, "loss": 0.4497, "step": 5352 } ], "logging_steps": 1, "max_steps": 5352, "num_input_tokens_seen": 0, "num_train_epochs": 6, "save_steps": 892, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.3514717333783839e+19, "train_batch_size": 4, "trial_name": null, "trial_params": null }