{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.26355605446825126, "eval_steps": 900, "global_step": 1800, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "grad_norm": 1.867297319395897, "learning_rate": 8.99868209108215e-05, "loss": 3.2458, "step": 1 }, { "epoch": 0.0, "grad_norm": 31.122135116455087, "learning_rate": 8.9973641821643e-05, "loss": 6.8269, "step": 2 }, { "epoch": 0.0, "grad_norm": 10.493605611332246, "learning_rate": 8.99604627324645e-05, "loss": 6.1526, "step": 3 }, { "epoch": 0.0, "grad_norm": 20.993597101446063, "learning_rate": 8.994728364328598e-05, "loss": 6.2791, "step": 4 }, { "epoch": 0.0, "grad_norm": 6.994941997336733, "learning_rate": 8.993410455410749e-05, "loss": 5.5069, "step": 5 }, { "epoch": 0.0, "grad_norm": 9.044801050606559, "learning_rate": 8.992092546492898e-05, "loss": 5.2917, "step": 6 }, { "epoch": 0.0, "grad_norm": 7.371025975927372, "learning_rate": 8.990774637575048e-05, "loss": 5.0841, "step": 7 }, { "epoch": 0.0, "grad_norm": 3.095134034689849, "learning_rate": 8.989456728657198e-05, "loss": 4.6676, "step": 8 }, { "epoch": 0.0, "grad_norm": 2.727749907194312, "learning_rate": 8.988138819739348e-05, "loss": 4.4157, "step": 9 }, { "epoch": 0.0, "grad_norm": 3.1785847861912533, "learning_rate": 8.986820910821497e-05, "loss": 4.3083, "step": 10 }, { "epoch": 0.0, "grad_norm": 1.5890441000530777, "learning_rate": 8.985503001903648e-05, "loss": 4.0652, "step": 11 }, { "epoch": 0.0, "grad_norm": 3.7851888183485998, "learning_rate": 8.984185092985796e-05, "loss": 4.0157, "step": 12 }, { "epoch": 0.0, "grad_norm": 2.177578439182146, "learning_rate": 8.982867184067945e-05, "loss": 3.8923, "step": 13 }, { "epoch": 0.0, "grad_norm": 4.189312958133593, "learning_rate": 8.981549275150096e-05, "loss": 3.8165, "step": 14 }, { "epoch": 0.0, "grad_norm": 2.135971084370728, "learning_rate": 8.980231366232245e-05, "loss": 3.7407, "step": 15 }, { "epoch": 0.0, "grad_norm": 1.6742409253843133, "learning_rate": 8.978913457314395e-05, "loss": 3.6203, "step": 16 }, { "epoch": 0.0, "grad_norm": 1.740647923231835, "learning_rate": 8.977595548396545e-05, "loss": 3.5358, "step": 17 }, { "epoch": 0.0, "grad_norm": 1.3386504358864526, "learning_rate": 8.976277639478695e-05, "loss": 3.4649, "step": 18 }, { "epoch": 0.0, "grad_norm": 1.4146027388570108, "learning_rate": 8.974959730560844e-05, "loss": 3.4096, "step": 19 }, { "epoch": 0.0, "grad_norm": 1.3101076465055932, "learning_rate": 8.973641821642993e-05, "loss": 3.3495, "step": 20 }, { "epoch": 0.0, "grad_norm": 1.3979232652764932, "learning_rate": 8.972323912725143e-05, "loss": 3.2864, "step": 21 }, { "epoch": 0.0, "grad_norm": 1.112058959017875, "learning_rate": 8.971006003807292e-05, "loss": 3.2272, "step": 22 }, { "epoch": 0.0, "grad_norm": 1.5723342224397572, "learning_rate": 8.969688094889443e-05, "loss": 3.202, "step": 23 }, { "epoch": 0.0, "grad_norm": 1.6929219679520722, "learning_rate": 8.968370185971592e-05, "loss": 3.1556, "step": 24 }, { "epoch": 0.0, "grad_norm": 1.0947475079787117, "learning_rate": 8.967052277053742e-05, "loss": 3.1127, "step": 25 }, { "epoch": 0.0, "grad_norm": 1.0263062806535903, "learning_rate": 8.965734368135892e-05, "loss": 3.07, "step": 26 }, { "epoch": 0.0, "grad_norm": 0.9314787514966034, "learning_rate": 8.964416459218042e-05, "loss": 3.0321, "step": 27 }, { "epoch": 0.0, "grad_norm": 0.8258215193640202, "learning_rate": 8.96309855030019e-05, "loss": 2.9997, "step": 28 }, { "epoch": 0.0, "grad_norm": 0.8854426518873304, "learning_rate": 8.96178064138234e-05, "loss": 2.9693, "step": 29 }, { "epoch": 0.0, "grad_norm": 0.7136563954565109, "learning_rate": 8.96046273246449e-05, "loss": 2.9337, "step": 30 }, { "epoch": 0.0, "grad_norm": 0.8520936236031108, "learning_rate": 8.959144823546639e-05, "loss": 2.8958, "step": 31 }, { "epoch": 0.0, "grad_norm": 0.7069687542653055, "learning_rate": 8.95782691462879e-05, "loss": 2.8893, "step": 32 }, { "epoch": 0.0, "grad_norm": 0.6112456126798674, "learning_rate": 8.95650900571094e-05, "loss": 2.8452, "step": 33 }, { "epoch": 0.0, "grad_norm": 0.6182491443128697, "learning_rate": 8.955191096793089e-05, "loss": 2.8375, "step": 34 }, { "epoch": 0.01, "grad_norm": 0.6354831752982139, "learning_rate": 8.95387318787524e-05, "loss": 2.8036, "step": 35 }, { "epoch": 0.01, "grad_norm": 0.5551758024561351, "learning_rate": 8.952555278957388e-05, "loss": 2.7898, "step": 36 }, { "epoch": 0.01, "grad_norm": 0.5385458807945395, "learning_rate": 8.951237370039537e-05, "loss": 2.7654, "step": 37 }, { "epoch": 0.01, "grad_norm": 0.611312479127073, "learning_rate": 8.949919461121688e-05, "loss": 2.7404, "step": 38 }, { "epoch": 0.01, "grad_norm": 0.41994683299580327, "learning_rate": 8.948601552203837e-05, "loss": 2.727, "step": 39 }, { "epoch": 0.01, "grad_norm": 0.4844003990796705, "learning_rate": 8.947283643285986e-05, "loss": 2.7055, "step": 40 }, { "epoch": 0.01, "grad_norm": 0.5096807026587409, "learning_rate": 8.945965734368137e-05, "loss": 2.6912, "step": 41 }, { "epoch": 0.01, "grad_norm": 0.7522366060460143, "learning_rate": 8.944647825450286e-05, "loss": 2.681, "step": 42 }, { "epoch": 0.01, "grad_norm": 0.9331119398395223, "learning_rate": 8.943329916532436e-05, "loss": 2.6557, "step": 43 }, { "epoch": 0.01, "grad_norm": 1.012546232060092, "learning_rate": 8.942012007614585e-05, "loss": 2.6533, "step": 44 }, { "epoch": 0.01, "grad_norm": 0.8636983952962917, "learning_rate": 8.940694098696735e-05, "loss": 2.6397, "step": 45 }, { "epoch": 0.01, "grad_norm": 0.7226119626951081, "learning_rate": 8.939376189778884e-05, "loss": 2.6172, "step": 46 }, { "epoch": 0.01, "grad_norm": 0.8159190836781818, "learning_rate": 8.938058280861035e-05, "loss": 2.601, "step": 47 }, { "epoch": 0.01, "grad_norm": 0.8397723356140642, "learning_rate": 8.936740371943184e-05, "loss": 2.5913, "step": 48 }, { "epoch": 0.01, "grad_norm": 0.9302397602027757, "learning_rate": 8.935422463025333e-05, "loss": 2.5779, "step": 49 }, { "epoch": 0.01, "grad_norm": 0.9294815366036785, "learning_rate": 8.934104554107484e-05, "loss": 2.5666, "step": 50 }, { "epoch": 0.01, "grad_norm": 0.9876017326778281, "learning_rate": 8.932786645189634e-05, "loss": 2.559, "step": 51 }, { "epoch": 0.01, "grad_norm": 1.0531686104317621, "learning_rate": 8.931468736271782e-05, "loss": 2.5426, "step": 52 }, { "epoch": 0.01, "grad_norm": 0.9432926643235091, "learning_rate": 8.930150827353932e-05, "loss": 2.5324, "step": 53 }, { "epoch": 0.01, "grad_norm": 1.0147959053073372, "learning_rate": 8.928832918436082e-05, "loss": 2.5166, "step": 54 }, { "epoch": 0.01, "grad_norm": 0.8370421203774538, "learning_rate": 8.927515009518231e-05, "loss": 2.5035, "step": 55 }, { "epoch": 0.01, "grad_norm": 0.7658170492109742, "learning_rate": 8.926197100600382e-05, "loss": 2.5064, "step": 56 }, { "epoch": 0.01, "grad_norm": 0.5836453359341242, "learning_rate": 8.924879191682531e-05, "loss": 2.4889, "step": 57 }, { "epoch": 0.01, "grad_norm": 0.6774145346502838, "learning_rate": 8.92356128276468e-05, "loss": 2.4773, "step": 58 }, { "epoch": 0.01, "grad_norm": 0.6303115552198764, "learning_rate": 8.922243373846831e-05, "loss": 2.4746, "step": 59 }, { "epoch": 0.01, "grad_norm": 0.4733727246322016, "learning_rate": 8.920925464928979e-05, "loss": 2.4583, "step": 60 }, { "epoch": 0.01, "grad_norm": 0.66470201831204, "learning_rate": 8.919607556011129e-05, "loss": 2.4509, "step": 61 }, { "epoch": 0.01, "grad_norm": 0.6356308149108085, "learning_rate": 8.91828964709328e-05, "loss": 2.4375, "step": 62 }, { "epoch": 0.01, "grad_norm": 0.46831466582575737, "learning_rate": 8.916971738175429e-05, "loss": 2.4314, "step": 63 }, { "epoch": 0.01, "grad_norm": 0.5711699065497955, "learning_rate": 8.915653829257578e-05, "loss": 2.42, "step": 64 }, { "epoch": 0.01, "grad_norm": 0.5389976605269295, "learning_rate": 8.914335920339729e-05, "loss": 2.4161, "step": 65 }, { "epoch": 0.01, "grad_norm": 0.5007278366304382, "learning_rate": 8.913018011421878e-05, "loss": 2.3977, "step": 66 }, { "epoch": 0.01, "grad_norm": 0.487467802029198, "learning_rate": 8.911700102504028e-05, "loss": 2.4007, "step": 67 }, { "epoch": 0.01, "grad_norm": 0.4113420784339612, "learning_rate": 8.910382193586177e-05, "loss": 2.3966, "step": 68 }, { "epoch": 0.01, "grad_norm": 0.4504091272252521, "learning_rate": 8.909064284668326e-05, "loss": 2.3862, "step": 69 }, { "epoch": 0.01, "grad_norm": 0.34513031845084635, "learning_rate": 8.907746375750476e-05, "loss": 2.3712, "step": 70 }, { "epoch": 0.01, "grad_norm": 0.5047955438477213, "learning_rate": 8.906428466832626e-05, "loss": 2.3695, "step": 71 }, { "epoch": 0.01, "grad_norm": 0.5024769592440181, "learning_rate": 8.905110557914776e-05, "loss": 2.3644, "step": 72 }, { "epoch": 0.01, "grad_norm": 0.4721080086046586, "learning_rate": 8.903792648996925e-05, "loss": 2.3555, "step": 73 }, { "epoch": 0.01, "grad_norm": 0.4591297268523745, "learning_rate": 8.902474740079076e-05, "loss": 2.3376, "step": 74 }, { "epoch": 0.01, "grad_norm": 0.5656344865220397, "learning_rate": 8.901156831161225e-05, "loss": 2.3398, "step": 75 }, { "epoch": 0.01, "grad_norm": 0.6500485453460426, "learning_rate": 8.899838922243373e-05, "loss": 2.3325, "step": 76 }, { "epoch": 0.01, "grad_norm": 0.6536690673884828, "learning_rate": 8.898521013325524e-05, "loss": 2.3345, "step": 77 }, { "epoch": 0.01, "grad_norm": 0.5143484723108316, "learning_rate": 8.897203104407673e-05, "loss": 2.3139, "step": 78 }, { "epoch": 0.01, "grad_norm": 0.37322968848559845, "learning_rate": 8.895885195489823e-05, "loss": 2.3079, "step": 79 }, { "epoch": 0.01, "grad_norm": 0.34462618220763114, "learning_rate": 8.894567286571974e-05, "loss": 2.2973, "step": 80 }, { "epoch": 0.01, "grad_norm": 0.38708375377202425, "learning_rate": 8.893249377654123e-05, "loss": 2.2951, "step": 81 }, { "epoch": 0.01, "grad_norm": 0.421171485688958, "learning_rate": 8.891931468736272e-05, "loss": 2.2951, "step": 82 }, { "epoch": 0.01, "grad_norm": 0.4465155129873313, "learning_rate": 8.890613559818423e-05, "loss": 2.2908, "step": 83 }, { "epoch": 0.01, "grad_norm": 0.42100671498868236, "learning_rate": 8.889295650900571e-05, "loss": 2.2862, "step": 84 }, { "epoch": 0.01, "grad_norm": 0.4308804247735972, "learning_rate": 8.88797774198272e-05, "loss": 2.2868, "step": 85 }, { "epoch": 0.01, "grad_norm": 0.4490696078386771, "learning_rate": 8.886659833064871e-05, "loss": 2.2784, "step": 86 }, { "epoch": 0.01, "grad_norm": 0.4720132579092968, "learning_rate": 8.88534192414702e-05, "loss": 2.2596, "step": 87 }, { "epoch": 0.01, "grad_norm": 0.5051381693356659, "learning_rate": 8.88402401522917e-05, "loss": 2.2644, "step": 88 }, { "epoch": 0.01, "grad_norm": 0.5161793827955174, "learning_rate": 8.88270610631132e-05, "loss": 2.2561, "step": 89 }, { "epoch": 0.01, "grad_norm": 0.5947828202225921, "learning_rate": 8.88138819739347e-05, "loss": 2.2485, "step": 90 }, { "epoch": 0.01, "grad_norm": 0.7363411963455597, "learning_rate": 8.88007028847562e-05, "loss": 2.256, "step": 91 }, { "epoch": 0.01, "grad_norm": 0.7827586632222484, "learning_rate": 8.878752379557769e-05, "loss": 2.2498, "step": 92 }, { "epoch": 0.01, "grad_norm": 0.5518918442765439, "learning_rate": 8.877434470639918e-05, "loss": 2.242, "step": 93 }, { "epoch": 0.01, "grad_norm": 0.47976621209079673, "learning_rate": 8.876116561722067e-05, "loss": 2.2336, "step": 94 }, { "epoch": 0.01, "grad_norm": 0.6515602255953327, "learning_rate": 8.874798652804218e-05, "loss": 2.2348, "step": 95 }, { "epoch": 0.01, "grad_norm": 0.6536808073233461, "learning_rate": 8.873480743886368e-05, "loss": 2.2269, "step": 96 }, { "epoch": 0.01, "grad_norm": 0.45429917400178504, "learning_rate": 8.872162834968517e-05, "loss": 2.2215, "step": 97 }, { "epoch": 0.01, "grad_norm": 0.6059083408950834, "learning_rate": 8.870844926050668e-05, "loss": 2.2141, "step": 98 }, { "epoch": 0.01, "grad_norm": 0.6153517456337565, "learning_rate": 8.869527017132817e-05, "loss": 2.2135, "step": 99 }, { "epoch": 0.01, "grad_norm": 0.4350225773043892, "learning_rate": 8.868209108214965e-05, "loss": 2.2046, "step": 100 }, { "epoch": 0.01, "grad_norm": 0.7538851308577357, "learning_rate": 8.866891199297116e-05, "loss": 2.1987, "step": 101 }, { "epoch": 0.01, "grad_norm": 0.7783668567986096, "learning_rate": 8.865573290379265e-05, "loss": 2.1944, "step": 102 }, { "epoch": 0.02, "grad_norm": 0.6152937329119922, "learning_rate": 8.864255381461415e-05, "loss": 2.1976, "step": 103 }, { "epoch": 0.02, "grad_norm": 0.8129985392759269, "learning_rate": 8.862937472543565e-05, "loss": 2.1969, "step": 104 }, { "epoch": 0.02, "grad_norm": 0.658961787535577, "learning_rate": 8.861619563625715e-05, "loss": 2.1916, "step": 105 }, { "epoch": 0.02, "grad_norm": 0.5694890400136322, "learning_rate": 8.860301654707864e-05, "loss": 2.1853, "step": 106 }, { "epoch": 0.02, "grad_norm": 0.8449981372046623, "learning_rate": 8.858983745790015e-05, "loss": 2.1918, "step": 107 }, { "epoch": 0.02, "grad_norm": 0.6504754487654488, "learning_rate": 8.857665836872163e-05, "loss": 2.18, "step": 108 }, { "epoch": 0.02, "grad_norm": 0.5770328719385773, "learning_rate": 8.856347927954312e-05, "loss": 2.1726, "step": 109 }, { "epoch": 0.02, "grad_norm": 0.876682475915139, "learning_rate": 8.855030019036463e-05, "loss": 2.1697, "step": 110 }, { "epoch": 0.02, "grad_norm": 0.6193197639347029, "learning_rate": 8.853712110118612e-05, "loss": 2.1762, "step": 111 }, { "epoch": 0.02, "grad_norm": 0.5205430357287273, "learning_rate": 8.852394201200762e-05, "loss": 2.1643, "step": 112 }, { "epoch": 0.02, "grad_norm": 0.6357317276650712, "learning_rate": 8.851076292282912e-05, "loss": 2.1698, "step": 113 }, { "epoch": 0.02, "grad_norm": 0.5337930185336511, "learning_rate": 8.849758383365062e-05, "loss": 2.1533, "step": 114 }, { "epoch": 0.02, "grad_norm": 0.5062081503044676, "learning_rate": 8.848440474447211e-05, "loss": 2.1554, "step": 115 }, { "epoch": 0.02, "grad_norm": 0.4764632463998196, "learning_rate": 8.84712256552936e-05, "loss": 2.1505, "step": 116 }, { "epoch": 0.02, "grad_norm": 0.41457257334024383, "learning_rate": 8.84580465661151e-05, "loss": 2.1467, "step": 117 }, { "epoch": 0.02, "grad_norm": 0.5065884475761684, "learning_rate": 8.844486747693659e-05, "loss": 2.1422, "step": 118 }, { "epoch": 0.02, "grad_norm": 0.4564614277589642, "learning_rate": 8.84316883877581e-05, "loss": 2.1412, "step": 119 }, { "epoch": 0.02, "grad_norm": 0.3554317111825436, "learning_rate": 8.84185092985796e-05, "loss": 2.1455, "step": 120 }, { "epoch": 0.02, "grad_norm": 0.42806997535938857, "learning_rate": 8.840533020940109e-05, "loss": 2.1275, "step": 121 }, { "epoch": 0.02, "grad_norm": 0.42000313047228083, "learning_rate": 8.83921511202226e-05, "loss": 2.1342, "step": 122 }, { "epoch": 0.02, "grad_norm": 0.3885632469021741, "learning_rate": 8.837897203104409e-05, "loss": 2.1307, "step": 123 }, { "epoch": 0.02, "grad_norm": 0.47343669511945285, "learning_rate": 8.836579294186557e-05, "loss": 2.1317, "step": 124 }, { "epoch": 0.02, "grad_norm": 0.48475235283422596, "learning_rate": 8.835261385268708e-05, "loss": 2.1161, "step": 125 }, { "epoch": 0.02, "grad_norm": 0.566942141589765, "learning_rate": 8.833943476350857e-05, "loss": 2.1182, "step": 126 }, { "epoch": 0.02, "grad_norm": 0.6962692105838626, "learning_rate": 8.832625567433006e-05, "loss": 2.1201, "step": 127 }, { "epoch": 0.02, "grad_norm": 0.8872705283662579, "learning_rate": 8.831307658515157e-05, "loss": 2.1125, "step": 128 }, { "epoch": 0.02, "grad_norm": 1.0040048160020307, "learning_rate": 8.829989749597306e-05, "loss": 2.1243, "step": 129 }, { "epoch": 0.02, "grad_norm": 0.8763157343936164, "learning_rate": 8.828671840679456e-05, "loss": 2.135, "step": 130 }, { "epoch": 0.02, "grad_norm": 0.4928878082025761, "learning_rate": 8.827353931761607e-05, "loss": 2.1159, "step": 131 }, { "epoch": 0.02, "grad_norm": 0.5070687239013271, "learning_rate": 8.826036022843755e-05, "loss": 2.1048, "step": 132 }, { "epoch": 0.02, "grad_norm": 0.7840409646534107, "learning_rate": 8.824718113925904e-05, "loss": 2.1037, "step": 133 }, { "epoch": 0.02, "grad_norm": 0.5221585439101886, "learning_rate": 8.823400205008055e-05, "loss": 2.0959, "step": 134 }, { "epoch": 0.02, "grad_norm": 0.4568661842831729, "learning_rate": 8.822082296090204e-05, "loss": 2.0918, "step": 135 }, { "epoch": 0.02, "grad_norm": 0.5841088902261057, "learning_rate": 8.820764387172353e-05, "loss": 2.0916, "step": 136 }, { "epoch": 0.02, "grad_norm": 0.5321596782302892, "learning_rate": 8.819446478254504e-05, "loss": 2.0897, "step": 137 }, { "epoch": 0.02, "grad_norm": 0.4811464623013186, "learning_rate": 8.818128569336654e-05, "loss": 2.0797, "step": 138 }, { "epoch": 0.02, "grad_norm": 0.45409201842843017, "learning_rate": 8.816810660418803e-05, "loss": 2.0809, "step": 139 }, { "epoch": 0.02, "grad_norm": 0.5436744181229896, "learning_rate": 8.815492751500952e-05, "loss": 2.0768, "step": 140 }, { "epoch": 0.02, "grad_norm": 0.465625799362755, "learning_rate": 8.814174842583102e-05, "loss": 2.0801, "step": 141 }, { "epoch": 0.02, "grad_norm": 0.4631920693131495, "learning_rate": 8.812856933665251e-05, "loss": 2.0729, "step": 142 }, { "epoch": 0.02, "grad_norm": 0.4973179737348441, "learning_rate": 8.811539024747402e-05, "loss": 2.0765, "step": 143 }, { "epoch": 0.02, "grad_norm": 0.3900332148198551, "learning_rate": 8.810221115829551e-05, "loss": 2.0688, "step": 144 }, { "epoch": 0.02, "grad_norm": 0.45058451016387613, "learning_rate": 8.8089032069117e-05, "loss": 2.0684, "step": 145 }, { "epoch": 0.02, "grad_norm": 0.35118754238330746, "learning_rate": 8.807585297993851e-05, "loss": 2.0681, "step": 146 }, { "epoch": 0.02, "grad_norm": 0.33942242720035193, "learning_rate": 8.806267389076e-05, "loss": 2.0626, "step": 147 }, { "epoch": 0.02, "grad_norm": 0.34835606297437544, "learning_rate": 8.804949480158149e-05, "loss": 2.0611, "step": 148 }, { "epoch": 0.02, "grad_norm": 0.33374548138193794, "learning_rate": 8.8036315712403e-05, "loss": 2.0589, "step": 149 }, { "epoch": 0.02, "grad_norm": 0.3554684609547751, "learning_rate": 8.802313662322449e-05, "loss": 2.0531, "step": 150 }, { "epoch": 0.02, "grad_norm": 0.30356995848645646, "learning_rate": 8.800995753404598e-05, "loss": 2.0527, "step": 151 }, { "epoch": 0.02, "grad_norm": 0.3749048670516549, "learning_rate": 8.799677844486749e-05, "loss": 2.0409, "step": 152 }, { "epoch": 0.02, "grad_norm": 0.44906357358681387, "learning_rate": 8.798359935568898e-05, "loss": 2.0455, "step": 153 }, { "epoch": 0.02, "grad_norm": 0.4937506907032551, "learning_rate": 8.797042026651048e-05, "loss": 2.0593, "step": 154 }, { "epoch": 0.02, "grad_norm": 0.6302087869169094, "learning_rate": 8.795724117733198e-05, "loss": 2.0444, "step": 155 }, { "epoch": 0.02, "grad_norm": 0.7666465190058978, "learning_rate": 8.794406208815346e-05, "loss": 2.0482, "step": 156 }, { "epoch": 0.02, "grad_norm": 0.8415113455563511, "learning_rate": 8.793088299897496e-05, "loss": 2.0553, "step": 157 }, { "epoch": 0.02, "grad_norm": 0.6599046675210126, "learning_rate": 8.791770390979646e-05, "loss": 2.0346, "step": 158 }, { "epoch": 0.02, "grad_norm": 0.4286698284091557, "learning_rate": 8.790452482061796e-05, "loss": 2.0364, "step": 159 }, { "epoch": 0.02, "grad_norm": 0.4636961335954888, "learning_rate": 8.789134573143945e-05, "loss": 2.027, "step": 160 }, { "epoch": 0.02, "grad_norm": 0.4729809233526084, "learning_rate": 8.787816664226096e-05, "loss": 2.0344, "step": 161 }, { "epoch": 0.02, "grad_norm": 0.5102897103629896, "learning_rate": 8.786498755308245e-05, "loss": 2.0313, "step": 162 }, { "epoch": 0.02, "grad_norm": 0.3821986499935569, "learning_rate": 8.785180846390395e-05, "loss": 2.0281, "step": 163 }, { "epoch": 0.02, "grad_norm": 0.31922482573170025, "learning_rate": 8.783862937472544e-05, "loss": 2.0246, "step": 164 }, { "epoch": 0.02, "grad_norm": 0.4125805076448191, "learning_rate": 8.782545028554693e-05, "loss": 2.0209, "step": 165 }, { "epoch": 0.02, "grad_norm": 0.3584157670577966, "learning_rate": 8.781227119636843e-05, "loss": 2.0201, "step": 166 }, { "epoch": 0.02, "grad_norm": 0.3732188737105076, "learning_rate": 8.779909210718993e-05, "loss": 2.0181, "step": 167 }, { "epoch": 0.02, "grad_norm": 0.34438987877017796, "learning_rate": 8.778591301801143e-05, "loss": 2.0155, "step": 168 }, { "epoch": 0.02, "grad_norm": 0.322936068818923, "learning_rate": 8.777273392883292e-05, "loss": 2.0206, "step": 169 }, { "epoch": 0.02, "grad_norm": 0.3671965249502594, "learning_rate": 8.775955483965443e-05, "loss": 2.0215, "step": 170 }, { "epoch": 0.03, "grad_norm": 0.3303955763338707, "learning_rate": 8.774637575047592e-05, "loss": 2.0134, "step": 171 }, { "epoch": 0.03, "grad_norm": 0.26010553136423376, "learning_rate": 8.77331966612974e-05, "loss": 1.9998, "step": 172 }, { "epoch": 0.03, "grad_norm": 0.28273036383624667, "learning_rate": 8.772001757211891e-05, "loss": 2.008, "step": 173 }, { "epoch": 0.03, "grad_norm": 0.3493466030437232, "learning_rate": 8.77068384829404e-05, "loss": 2.0077, "step": 174 }, { "epoch": 0.03, "grad_norm": 0.3240073311732844, "learning_rate": 8.76936593937619e-05, "loss": 2.0005, "step": 175 }, { "epoch": 0.03, "grad_norm": 0.37871862295109215, "learning_rate": 8.76804803045834e-05, "loss": 1.9947, "step": 176 }, { "epoch": 0.03, "grad_norm": 0.36425872526816194, "learning_rate": 8.76673012154049e-05, "loss": 2.0012, "step": 177 }, { "epoch": 0.03, "grad_norm": 0.3146144912051344, "learning_rate": 8.765412212622639e-05, "loss": 1.9888, "step": 178 }, { "epoch": 0.03, "grad_norm": 0.32672427059297815, "learning_rate": 8.764094303704789e-05, "loss": 1.9914, "step": 179 }, { "epoch": 0.03, "grad_norm": 0.2874426352457461, "learning_rate": 8.762776394786938e-05, "loss": 1.991, "step": 180 }, { "epoch": 0.03, "grad_norm": 0.304367486735733, "learning_rate": 8.761458485869087e-05, "loss": 1.9806, "step": 181 }, { "epoch": 0.03, "grad_norm": 0.37875831866804927, "learning_rate": 8.760140576951238e-05, "loss": 1.9924, "step": 182 }, { "epoch": 0.03, "grad_norm": 0.4835755191486126, "learning_rate": 8.758822668033388e-05, "loss": 1.9921, "step": 183 }, { "epoch": 0.03, "grad_norm": 0.5565270140077677, "learning_rate": 8.757504759115537e-05, "loss": 1.9822, "step": 184 }, { "epoch": 0.03, "grad_norm": 0.5464855527172483, "learning_rate": 8.756186850197688e-05, "loss": 1.9839, "step": 185 }, { "epoch": 0.03, "grad_norm": 0.4989777454659821, "learning_rate": 8.754868941279837e-05, "loss": 1.9867, "step": 186 }, { "epoch": 0.03, "grad_norm": 0.4574274365674215, "learning_rate": 8.753551032361986e-05, "loss": 1.9837, "step": 187 }, { "epoch": 0.03, "grad_norm": 0.47786281828321875, "learning_rate": 8.752233123444136e-05, "loss": 1.989, "step": 188 }, { "epoch": 0.03, "grad_norm": 0.5193952650470612, "learning_rate": 8.750915214526285e-05, "loss": 1.9721, "step": 189 }, { "epoch": 0.03, "grad_norm": 0.46706899407183416, "learning_rate": 8.749597305608435e-05, "loss": 1.9721, "step": 190 }, { "epoch": 0.03, "grad_norm": 0.41004377608522635, "learning_rate": 8.748279396690585e-05, "loss": 1.9736, "step": 191 }, { "epoch": 0.03, "grad_norm": 0.4094480903013732, "learning_rate": 8.746961487772735e-05, "loss": 1.9714, "step": 192 }, { "epoch": 0.03, "grad_norm": 0.5224817485503537, "learning_rate": 8.745643578854884e-05, "loss": 1.9775, "step": 193 }, { "epoch": 0.03, "grad_norm": 0.5763427830733111, "learning_rate": 8.744325669937035e-05, "loss": 1.9691, "step": 194 }, { "epoch": 0.03, "grad_norm": 0.45154944484866116, "learning_rate": 8.743007761019184e-05, "loss": 1.9685, "step": 195 }, { "epoch": 0.03, "grad_norm": 0.29409144127731623, "learning_rate": 8.741689852101332e-05, "loss": 1.9665, "step": 196 }, { "epoch": 0.03, "grad_norm": 0.3391706172784746, "learning_rate": 8.740371943183483e-05, "loss": 1.9657, "step": 197 }, { "epoch": 0.03, "grad_norm": 0.3584680315892078, "learning_rate": 8.739054034265632e-05, "loss": 1.9662, "step": 198 }, { "epoch": 0.03, "grad_norm": 0.32480662203931654, "learning_rate": 8.737736125347782e-05, "loss": 1.967, "step": 199 }, { "epoch": 0.03, "grad_norm": 0.2678893712664796, "learning_rate": 8.736418216429932e-05, "loss": 1.9667, "step": 200 }, { "epoch": 0.03, "grad_norm": 0.3034157270439372, "learning_rate": 8.735100307512082e-05, "loss": 1.9639, "step": 201 }, { "epoch": 0.03, "grad_norm": 0.38638946729313517, "learning_rate": 8.733782398594231e-05, "loss": 1.9654, "step": 202 }, { "epoch": 0.03, "grad_norm": 0.44116092753081665, "learning_rate": 8.73246448967638e-05, "loss": 1.9662, "step": 203 }, { "epoch": 0.03, "grad_norm": 0.5599610453487487, "learning_rate": 8.73114658075853e-05, "loss": 1.9589, "step": 204 }, { "epoch": 0.03, "grad_norm": 0.6813838919621874, "learning_rate": 8.729828671840679e-05, "loss": 1.96, "step": 205 }, { "epoch": 0.03, "grad_norm": 0.6749810768948219, "learning_rate": 8.72851076292283e-05, "loss": 1.9669, "step": 206 }, { "epoch": 0.03, "grad_norm": 0.5474380551907909, "learning_rate": 8.727192854004979e-05, "loss": 1.9479, "step": 207 }, { "epoch": 0.03, "grad_norm": 0.39912501114471677, "learning_rate": 8.725874945087129e-05, "loss": 1.9591, "step": 208 }, { "epoch": 0.03, "grad_norm": 0.3704777650253716, "learning_rate": 8.72455703616928e-05, "loss": 1.9535, "step": 209 }, { "epoch": 0.03, "grad_norm": 0.45420800985949406, "learning_rate": 8.723239127251429e-05, "loss": 1.9476, "step": 210 }, { "epoch": 0.03, "grad_norm": 0.5106582102448923, "learning_rate": 8.721921218333578e-05, "loss": 1.954, "step": 211 }, { "epoch": 0.03, "grad_norm": 1.648206578856157, "learning_rate": 8.720603309415728e-05, "loss": 1.963, "step": 212 }, { "epoch": 0.03, "grad_norm": 0.35693125434587636, "learning_rate": 8.719285400497877e-05, "loss": 1.9419, "step": 213 }, { "epoch": 0.03, "grad_norm": 0.6519985094603863, "learning_rate": 8.717967491580026e-05, "loss": 1.9445, "step": 214 }, { "epoch": 0.03, "grad_norm": 0.6567675718025047, "learning_rate": 8.716649582662177e-05, "loss": 1.9469, "step": 215 }, { "epoch": 0.03, "grad_norm": 0.4872034695801568, "learning_rate": 8.715331673744326e-05, "loss": 1.9495, "step": 216 }, { "epoch": 0.03, "grad_norm": 0.4145209119308714, "learning_rate": 8.714013764826476e-05, "loss": 1.9486, "step": 217 }, { "epoch": 0.03, "grad_norm": 0.4775886307734156, "learning_rate": 8.712695855908626e-05, "loss": 1.9496, "step": 218 }, { "epoch": 0.03, "grad_norm": 0.40804530533441385, "learning_rate": 8.711377946990776e-05, "loss": 1.9419, "step": 219 }, { "epoch": 0.03, "grad_norm": 0.3313950875913946, "learning_rate": 8.710060038072924e-05, "loss": 1.9372, "step": 220 }, { "epoch": 0.03, "grad_norm": 0.3887501325873841, "learning_rate": 8.708742129155075e-05, "loss": 1.9421, "step": 221 }, { "epoch": 0.03, "grad_norm": 0.4319364449745349, "learning_rate": 8.707424220237224e-05, "loss": 1.9385, "step": 222 }, { "epoch": 0.03, "grad_norm": 0.39127832437474, "learning_rate": 8.706106311319373e-05, "loss": 1.935, "step": 223 }, { "epoch": 0.03, "grad_norm": 0.36405269202971846, "learning_rate": 8.704788402401524e-05, "loss": 1.9395, "step": 224 }, { "epoch": 0.03, "grad_norm": 0.3815614792943797, "learning_rate": 8.703470493483673e-05, "loss": 1.9351, "step": 225 }, { "epoch": 0.03, "grad_norm": 0.43828706493068725, "learning_rate": 8.702152584565823e-05, "loss": 1.9217, "step": 226 }, { "epoch": 0.03, "grad_norm": 0.39922403213927826, "learning_rate": 8.700834675647972e-05, "loss": 1.9289, "step": 227 }, { "epoch": 0.03, "grad_norm": 0.3844142284075385, "learning_rate": 8.699516766730122e-05, "loss": 1.9248, "step": 228 }, { "epoch": 0.03, "grad_norm": 0.38881007783639865, "learning_rate": 8.698198857812271e-05, "loss": 1.9201, "step": 229 }, { "epoch": 0.03, "grad_norm": 0.2975403535899065, "learning_rate": 8.696880948894422e-05, "loss": 1.928, "step": 230 }, { "epoch": 0.03, "grad_norm": 0.2832203830943493, "learning_rate": 8.695563039976571e-05, "loss": 1.9162, "step": 231 }, { "epoch": 0.03, "grad_norm": 0.2979487231657903, "learning_rate": 8.69424513105872e-05, "loss": 1.9271, "step": 232 }, { "epoch": 0.03, "grad_norm": 0.3621148892850887, "learning_rate": 8.692927222140871e-05, "loss": 1.9156, "step": 233 }, { "epoch": 0.03, "grad_norm": 0.3252924764609856, "learning_rate": 8.69160931322302e-05, "loss": 1.9208, "step": 234 }, { "epoch": 0.03, "grad_norm": 0.38778060232379175, "learning_rate": 8.69029140430517e-05, "loss": 1.9137, "step": 235 }, { "epoch": 0.03, "grad_norm": 0.5259448310725102, "learning_rate": 8.688973495387319e-05, "loss": 1.915, "step": 236 }, { "epoch": 0.03, "grad_norm": 0.6748649230965568, "learning_rate": 8.687655586469469e-05, "loss": 1.9335, "step": 237 }, { "epoch": 0.03, "grad_norm": 0.7329646137433606, "learning_rate": 8.686337677551618e-05, "loss": 1.921, "step": 238 }, { "epoch": 0.03, "grad_norm": 0.6477306709245009, "learning_rate": 8.685019768633769e-05, "loss": 1.9107, "step": 239 }, { "epoch": 0.04, "grad_norm": 0.4249940595660931, "learning_rate": 8.683701859715918e-05, "loss": 1.9074, "step": 240 }, { "epoch": 0.04, "grad_norm": 0.40780487506439317, "learning_rate": 8.682383950798068e-05, "loss": 1.9121, "step": 241 }, { "epoch": 0.04, "grad_norm": 0.5063150515112605, "learning_rate": 8.681066041880218e-05, "loss": 1.9122, "step": 242 }, { "epoch": 0.04, "grad_norm": 0.43654436775464556, "learning_rate": 8.679748132962368e-05, "loss": 1.9101, "step": 243 }, { "epoch": 0.04, "grad_norm": 0.28693671377727636, "learning_rate": 8.678430224044516e-05, "loss": 1.9071, "step": 244 }, { "epoch": 0.04, "grad_norm": 0.35062666021736943, "learning_rate": 8.677112315126666e-05, "loss": 1.9052, "step": 245 }, { "epoch": 0.04, "grad_norm": 0.4571466841247422, "learning_rate": 8.675794406208816e-05, "loss": 1.9037, "step": 246 }, { "epoch": 0.04, "grad_norm": 0.3856445615558911, "learning_rate": 8.674476497290965e-05, "loss": 1.9033, "step": 247 }, { "epoch": 0.04, "grad_norm": 0.3233514425302591, "learning_rate": 8.673158588373116e-05, "loss": 1.904, "step": 248 }, { "epoch": 0.04, "grad_norm": 0.4212339592559155, "learning_rate": 8.671840679455265e-05, "loss": 1.9029, "step": 249 }, { "epoch": 0.04, "grad_norm": 0.4275588677912957, "learning_rate": 8.670522770537415e-05, "loss": 1.8994, "step": 250 }, { "epoch": 0.04, "grad_norm": 0.29035057566401584, "learning_rate": 8.669204861619564e-05, "loss": 1.8968, "step": 251 }, { "epoch": 0.04, "grad_norm": 0.3292457727990474, "learning_rate": 8.667886952701713e-05, "loss": 1.8971, "step": 252 }, { "epoch": 0.04, "grad_norm": 0.39002632439582646, "learning_rate": 8.666569043783863e-05, "loss": 1.9019, "step": 253 }, { "epoch": 0.04, "grad_norm": 0.3058384482996071, "learning_rate": 8.665251134866013e-05, "loss": 1.8991, "step": 254 }, { "epoch": 0.04, "grad_norm": 0.33747054066822696, "learning_rate": 8.663933225948163e-05, "loss": 1.8891, "step": 255 }, { "epoch": 0.04, "grad_norm": 0.35931140472197654, "learning_rate": 8.662615317030312e-05, "loss": 1.9025, "step": 256 }, { "epoch": 0.04, "grad_norm": 0.312755193621967, "learning_rate": 8.661297408112463e-05, "loss": 1.8904, "step": 257 }, { "epoch": 0.04, "grad_norm": 0.24759800889452924, "learning_rate": 8.659979499194612e-05, "loss": 1.8957, "step": 258 }, { "epoch": 0.04, "grad_norm": 0.23365570528449237, "learning_rate": 8.658661590276762e-05, "loss": 1.8895, "step": 259 }, { "epoch": 0.04, "grad_norm": 0.26012031059809776, "learning_rate": 8.657343681358911e-05, "loss": 1.874, "step": 260 }, { "epoch": 0.04, "grad_norm": 0.2369419439744028, "learning_rate": 8.65602577244106e-05, "loss": 1.8888, "step": 261 }, { "epoch": 0.04, "grad_norm": 0.23737605818719734, "learning_rate": 8.65470786352321e-05, "loss": 1.892, "step": 262 }, { "epoch": 0.04, "grad_norm": 0.20560803394813162, "learning_rate": 8.65338995460536e-05, "loss": 1.8902, "step": 263 }, { "epoch": 0.04, "grad_norm": 0.23756980446551546, "learning_rate": 8.65207204568751e-05, "loss": 1.8914, "step": 264 }, { "epoch": 0.04, "grad_norm": 0.2955355993564412, "learning_rate": 8.650754136769659e-05, "loss": 1.8741, "step": 265 }, { "epoch": 0.04, "grad_norm": 0.36625312284796796, "learning_rate": 8.649436227851809e-05, "loss": 1.8849, "step": 266 }, { "epoch": 0.04, "grad_norm": 0.4377187791569674, "learning_rate": 8.64811831893396e-05, "loss": 1.875, "step": 267 }, { "epoch": 0.04, "grad_norm": 0.4751457670664482, "learning_rate": 8.646800410016107e-05, "loss": 1.887, "step": 268 }, { "epoch": 0.04, "grad_norm": 0.5124162062393218, "learning_rate": 8.645482501098258e-05, "loss": 1.8759, "step": 269 }, { "epoch": 0.04, "grad_norm": 0.5128407598622339, "learning_rate": 8.644164592180407e-05, "loss": 1.884, "step": 270 }, { "epoch": 0.04, "grad_norm": 0.4645016436292238, "learning_rate": 8.642846683262557e-05, "loss": 1.8748, "step": 271 }, { "epoch": 0.04, "grad_norm": 0.42963082194049396, "learning_rate": 8.641528774344708e-05, "loss": 1.8725, "step": 272 }, { "epoch": 0.04, "grad_norm": 0.41218244280637906, "learning_rate": 8.640210865426857e-05, "loss": 1.8791, "step": 273 }, { "epoch": 0.04, "grad_norm": 0.34726276152467556, "learning_rate": 8.638892956509006e-05, "loss": 1.8742, "step": 274 }, { "epoch": 0.04, "grad_norm": 0.328823655826036, "learning_rate": 8.637575047591156e-05, "loss": 1.8721, "step": 275 }, { "epoch": 0.04, "grad_norm": 0.3686461464930126, "learning_rate": 8.636257138673305e-05, "loss": 1.8687, "step": 276 }, { "epoch": 0.04, "grad_norm": 0.3656673874029743, "learning_rate": 8.634939229755454e-05, "loss": 1.8654, "step": 277 }, { "epoch": 0.04, "grad_norm": 0.30525439673036175, "learning_rate": 8.633621320837605e-05, "loss": 1.8746, "step": 278 }, { "epoch": 0.04, "grad_norm": 0.3007226581860427, "learning_rate": 8.632303411919755e-05, "loss": 1.8664, "step": 279 }, { "epoch": 0.04, "grad_norm": 0.3849279004150829, "learning_rate": 8.630985503001904e-05, "loss": 1.8717, "step": 280 }, { "epoch": 0.04, "grad_norm": 0.43777228984264327, "learning_rate": 8.629667594084055e-05, "loss": 1.8776, "step": 281 }, { "epoch": 0.04, "grad_norm": 0.4220356221423105, "learning_rate": 8.628349685166204e-05, "loss": 1.8705, "step": 282 }, { "epoch": 0.04, "grad_norm": 0.4049297705769528, "learning_rate": 8.627031776248353e-05, "loss": 1.8702, "step": 283 }, { "epoch": 0.04, "grad_norm": 0.3919834421059084, "learning_rate": 8.625713867330503e-05, "loss": 1.8672, "step": 284 }, { "epoch": 0.04, "grad_norm": 0.3713089483320666, "learning_rate": 8.624395958412652e-05, "loss": 1.8626, "step": 285 }, { "epoch": 0.04, "grad_norm": 0.3604341363789889, "learning_rate": 8.623078049494802e-05, "loss": 1.8724, "step": 286 }, { "epoch": 0.04, "grad_norm": 0.39717353573166714, "learning_rate": 8.621760140576952e-05, "loss": 1.8646, "step": 287 }, { "epoch": 0.04, "grad_norm": 0.44719078220357295, "learning_rate": 8.620442231659102e-05, "loss": 1.8582, "step": 288 }, { "epoch": 0.04, "grad_norm": 0.4513680274672226, "learning_rate": 8.619124322741251e-05, "loss": 1.8696, "step": 289 }, { "epoch": 0.04, "grad_norm": 0.43023542467375564, "learning_rate": 8.6178064138234e-05, "loss": 1.8699, "step": 290 }, { "epoch": 0.04, "grad_norm": 0.43858266418234654, "learning_rate": 8.616488504905551e-05, "loss": 1.86, "step": 291 }, { "epoch": 0.04, "grad_norm": 0.5064425360850751, "learning_rate": 8.615170595987699e-05, "loss": 1.858, "step": 292 }, { "epoch": 0.04, "grad_norm": 0.48407682623823045, "learning_rate": 8.61385268706985e-05, "loss": 1.853, "step": 293 }, { "epoch": 0.04, "grad_norm": 0.46114150689754957, "learning_rate": 8.612534778151999e-05, "loss": 1.8598, "step": 294 }, { "epoch": 0.04, "grad_norm": 0.44714939482574123, "learning_rate": 8.611216869234149e-05, "loss": 1.8571, "step": 295 }, { "epoch": 0.04, "grad_norm": 0.29499856062245083, "learning_rate": 8.6098989603163e-05, "loss": 1.85, "step": 296 }, { "epoch": 0.04, "grad_norm": 0.27237302520628326, "learning_rate": 8.608581051398449e-05, "loss": 1.8633, "step": 297 }, { "epoch": 0.04, "grad_norm": 0.3852560547170149, "learning_rate": 8.607263142480598e-05, "loss": 1.84, "step": 298 }, { "epoch": 0.04, "grad_norm": 0.4338967169702793, "learning_rate": 8.605945233562747e-05, "loss": 1.86, "step": 299 }, { "epoch": 0.04, "grad_norm": 0.3952031517559691, "learning_rate": 8.604627324644897e-05, "loss": 1.8473, "step": 300 }, { "epoch": 0.04, "grad_norm": 0.25514061111362424, "learning_rate": 8.603309415727046e-05, "loss": 1.8464, "step": 301 }, { "epoch": 0.04, "grad_norm": 0.3078510816972887, "learning_rate": 8.601991506809197e-05, "loss": 1.8518, "step": 302 }, { "epoch": 0.04, "grad_norm": 0.38406564873200627, "learning_rate": 8.600673597891346e-05, "loss": 1.8453, "step": 303 }, { "epoch": 0.04, "grad_norm": 0.29032703723109443, "learning_rate": 8.599355688973496e-05, "loss": 1.8426, "step": 304 }, { "epoch": 0.04, "grad_norm": 0.21551221995312625, "learning_rate": 8.598037780055646e-05, "loss": 1.8407, "step": 305 }, { "epoch": 0.04, "grad_norm": 0.25104013568498373, "learning_rate": 8.596719871137796e-05, "loss": 1.8412, "step": 306 }, { "epoch": 0.04, "grad_norm": 0.2753448788479235, "learning_rate": 8.595401962219945e-05, "loss": 1.85, "step": 307 }, { "epoch": 0.05, "grad_norm": 0.28287628219754707, "learning_rate": 8.594084053302095e-05, "loss": 1.8393, "step": 308 }, { "epoch": 0.05, "grad_norm": 0.29153292982905893, "learning_rate": 8.592766144384244e-05, "loss": 1.8436, "step": 309 }, { "epoch": 0.05, "grad_norm": 0.3356468622059691, "learning_rate": 8.591448235466393e-05, "loss": 1.8501, "step": 310 }, { "epoch": 0.05, "grad_norm": 0.3668022644305236, "learning_rate": 8.590130326548544e-05, "loss": 1.8442, "step": 311 }, { "epoch": 0.05, "grad_norm": 0.35131341619593265, "learning_rate": 8.588812417630693e-05, "loss": 1.8385, "step": 312 }, { "epoch": 0.05, "grad_norm": 0.32173508052581773, "learning_rate": 8.587494508712843e-05, "loss": 1.8436, "step": 313 }, { "epoch": 0.05, "grad_norm": 0.300778040243218, "learning_rate": 8.586176599794992e-05, "loss": 1.8382, "step": 314 }, { "epoch": 0.05, "grad_norm": 0.30861066996157027, "learning_rate": 8.584858690877143e-05, "loss": 1.8351, "step": 315 }, { "epoch": 0.05, "grad_norm": 0.34553615609293836, "learning_rate": 8.583540781959291e-05, "loss": 1.8326, "step": 316 }, { "epoch": 0.05, "grad_norm": 0.3945637083333217, "learning_rate": 8.582222873041442e-05, "loss": 1.8439, "step": 317 }, { "epoch": 0.05, "grad_norm": 0.4185609027500278, "learning_rate": 8.580904964123591e-05, "loss": 1.836, "step": 318 }, { "epoch": 0.05, "grad_norm": 0.4737109913412694, "learning_rate": 8.57958705520574e-05, "loss": 1.8349, "step": 319 }, { "epoch": 0.05, "grad_norm": 0.542744291036962, "learning_rate": 8.578269146287891e-05, "loss": 1.8369, "step": 320 }, { "epoch": 0.05, "grad_norm": 0.5698184063084959, "learning_rate": 8.57695123737004e-05, "loss": 1.8364, "step": 321 }, { "epoch": 0.05, "grad_norm": 0.5216244389865377, "learning_rate": 8.57563332845219e-05, "loss": 1.8391, "step": 322 }, { "epoch": 0.05, "grad_norm": 0.4349460582065712, "learning_rate": 8.574315419534339e-05, "loss": 1.8316, "step": 323 }, { "epoch": 0.05, "grad_norm": 0.4060439023599905, "learning_rate": 8.572997510616489e-05, "loss": 1.829, "step": 324 }, { "epoch": 0.05, "grad_norm": 0.4006651254790203, "learning_rate": 8.571679601698638e-05, "loss": 1.8289, "step": 325 }, { "epoch": 0.05, "grad_norm": 0.35982668295004727, "learning_rate": 8.570361692780789e-05, "loss": 1.8345, "step": 326 }, { "epoch": 0.05, "grad_norm": 0.34270943020191247, "learning_rate": 8.569043783862938e-05, "loss": 1.8244, "step": 327 }, { "epoch": 0.05, "grad_norm": 0.35208015052905844, "learning_rate": 8.567725874945087e-05, "loss": 1.8395, "step": 328 }, { "epoch": 0.05, "grad_norm": 0.3560007421719364, "learning_rate": 8.566407966027238e-05, "loss": 1.8244, "step": 329 }, { "epoch": 0.05, "grad_norm": 0.36632340017442266, "learning_rate": 8.565090057109388e-05, "loss": 1.8225, "step": 330 }, { "epoch": 0.05, "grad_norm": 0.33466423040979987, "learning_rate": 8.563772148191537e-05, "loss": 1.829, "step": 331 }, { "epoch": 0.05, "grad_norm": 0.2716882763297445, "learning_rate": 8.562454239273686e-05, "loss": 1.8341, "step": 332 }, { "epoch": 0.05, "grad_norm": 0.26453069945784297, "learning_rate": 8.561136330355836e-05, "loss": 1.834, "step": 333 }, { "epoch": 0.05, "grad_norm": 0.2678715963585482, "learning_rate": 8.559818421437985e-05, "loss": 1.8246, "step": 334 }, { "epoch": 0.05, "grad_norm": 0.28963443783737886, "learning_rate": 8.558500512520136e-05, "loss": 1.8217, "step": 335 }, { "epoch": 0.05, "grad_norm": 0.2799148037129182, "learning_rate": 8.557182603602285e-05, "loss": 1.8232, "step": 336 }, { "epoch": 0.05, "grad_norm": 0.25449424333816384, "learning_rate": 8.555864694684435e-05, "loss": 1.8211, "step": 337 }, { "epoch": 0.05, "grad_norm": 0.29873070853220085, "learning_rate": 8.554546785766584e-05, "loss": 1.8218, "step": 338 }, { "epoch": 0.05, "grad_norm": 0.31256528253176236, "learning_rate": 8.553228876848735e-05, "loss": 1.8184, "step": 339 }, { "epoch": 0.05, "grad_norm": 0.2579289256497001, "learning_rate": 8.551910967930883e-05, "loss": 1.8285, "step": 340 }, { "epoch": 0.05, "grad_norm": 0.2692223001749751, "learning_rate": 8.550593059013033e-05, "loss": 1.8199, "step": 341 }, { "epoch": 0.05, "grad_norm": 0.2828285551419333, "learning_rate": 8.549275150095183e-05, "loss": 1.812, "step": 342 }, { "epoch": 0.05, "grad_norm": 0.25760648063355074, "learning_rate": 8.547957241177332e-05, "loss": 1.8196, "step": 343 }, { "epoch": 0.05, "grad_norm": 0.3229138587412795, "learning_rate": 8.546639332259483e-05, "loss": 1.8168, "step": 344 }, { "epoch": 0.05, "grad_norm": 0.32584515922858565, "learning_rate": 8.545321423341632e-05, "loss": 1.821, "step": 345 }, { "epoch": 0.05, "grad_norm": 0.2785648276363959, "learning_rate": 8.544003514423782e-05, "loss": 1.8226, "step": 346 }, { "epoch": 0.05, "grad_norm": 0.32332023531594767, "learning_rate": 8.542685605505931e-05, "loss": 1.8067, "step": 347 }, { "epoch": 0.05, "grad_norm": 0.30635180846369325, "learning_rate": 8.54136769658808e-05, "loss": 1.8132, "step": 348 }, { "epoch": 0.05, "grad_norm": 0.29630729064298555, "learning_rate": 8.54004978767023e-05, "loss": 1.8101, "step": 349 }, { "epoch": 0.05, "grad_norm": 0.34621816808581285, "learning_rate": 8.53873187875238e-05, "loss": 1.8176, "step": 350 }, { "epoch": 0.05, "grad_norm": 0.37813665939757496, "learning_rate": 8.53741396983453e-05, "loss": 1.8118, "step": 351 }, { "epoch": 0.05, "grad_norm": 0.4024072071879195, "learning_rate": 8.536096060916679e-05, "loss": 1.8151, "step": 352 }, { "epoch": 0.05, "grad_norm": 0.4804782375915566, "learning_rate": 8.534778151998829e-05, "loss": 1.8163, "step": 353 }, { "epoch": 0.05, "grad_norm": 0.5127084558984112, "learning_rate": 8.533460243080979e-05, "loss": 1.811, "step": 354 }, { "epoch": 0.05, "grad_norm": 0.4388610896297329, "learning_rate": 8.532142334163129e-05, "loss": 1.8137, "step": 355 }, { "epoch": 0.05, "grad_norm": 0.3221135161434642, "learning_rate": 8.530824425245278e-05, "loss": 1.7968, "step": 356 }, { "epoch": 0.05, "grad_norm": 0.340563157991881, "learning_rate": 8.529506516327427e-05, "loss": 1.8103, "step": 357 }, { "epoch": 0.05, "grad_norm": 0.39991989603879213, "learning_rate": 8.528188607409577e-05, "loss": 1.8087, "step": 358 }, { "epoch": 0.05, "grad_norm": 0.4120407943765869, "learning_rate": 8.526870698491728e-05, "loss": 1.805, "step": 359 }, { "epoch": 0.05, "grad_norm": 0.34596624387275093, "learning_rate": 8.525552789573877e-05, "loss": 1.8035, "step": 360 }, { "epoch": 0.05, "grad_norm": 0.25789497090466024, "learning_rate": 8.524234880656026e-05, "loss": 1.8058, "step": 361 }, { "epoch": 0.05, "grad_norm": 0.30263266008859196, "learning_rate": 8.522916971738176e-05, "loss": 1.8084, "step": 362 }, { "epoch": 0.05, "grad_norm": 0.3562148440043474, "learning_rate": 8.521599062820326e-05, "loss": 1.799, "step": 363 }, { "epoch": 0.05, "grad_norm": 0.30587484606473564, "learning_rate": 8.520281153902474e-05, "loss": 1.8003, "step": 364 }, { "epoch": 0.05, "grad_norm": 0.27973522082893804, "learning_rate": 8.518963244984625e-05, "loss": 1.8153, "step": 365 }, { "epoch": 0.05, "grad_norm": 0.28180525427229874, "learning_rate": 8.517645336066775e-05, "loss": 1.7987, "step": 366 }, { "epoch": 0.05, "grad_norm": 0.24578221711398116, "learning_rate": 8.516327427148924e-05, "loss": 1.8116, "step": 367 }, { "epoch": 0.05, "grad_norm": 0.265330003846191, "learning_rate": 8.515009518231075e-05, "loss": 1.8034, "step": 368 }, { "epoch": 0.05, "grad_norm": 0.2777372207789329, "learning_rate": 8.513691609313224e-05, "loss": 1.793, "step": 369 }, { "epoch": 0.05, "grad_norm": 0.22568033781908964, "learning_rate": 8.512373700395373e-05, "loss": 1.8029, "step": 370 }, { "epoch": 0.05, "grad_norm": 0.25601857440834863, "learning_rate": 8.511055791477523e-05, "loss": 1.7958, "step": 371 }, { "epoch": 0.05, "grad_norm": 0.31701347224825027, "learning_rate": 8.509737882559672e-05, "loss": 1.8006, "step": 372 }, { "epoch": 0.05, "grad_norm": 0.2911487871418614, "learning_rate": 8.508419973641821e-05, "loss": 1.7955, "step": 373 }, { "epoch": 0.05, "grad_norm": 0.2082178563597066, "learning_rate": 8.507102064723972e-05, "loss": 1.797, "step": 374 }, { "epoch": 0.05, "grad_norm": 0.25022339272015853, "learning_rate": 8.505784155806122e-05, "loss": 1.7918, "step": 375 }, { "epoch": 0.06, "grad_norm": 0.2857289749098349, "learning_rate": 8.504466246888271e-05, "loss": 1.7919, "step": 376 }, { "epoch": 0.06, "grad_norm": 0.2982765315572785, "learning_rate": 8.50314833797042e-05, "loss": 1.7945, "step": 377 }, { "epoch": 0.06, "grad_norm": 0.3632832111118879, "learning_rate": 8.501830429052571e-05, "loss": 1.7891, "step": 378 }, { "epoch": 0.06, "grad_norm": 0.4582525250106023, "learning_rate": 8.50051252013472e-05, "loss": 1.7909, "step": 379 }, { "epoch": 0.06, "grad_norm": 0.49699840172624643, "learning_rate": 8.49919461121687e-05, "loss": 1.7971, "step": 380 }, { "epoch": 0.06, "grad_norm": 0.4504572316819271, "learning_rate": 8.497876702299019e-05, "loss": 1.8089, "step": 381 }, { "epoch": 0.06, "grad_norm": 0.3849459017582572, "learning_rate": 8.496558793381169e-05, "loss": 1.8009, "step": 382 }, { "epoch": 0.06, "grad_norm": 0.3899357827016154, "learning_rate": 8.495240884463319e-05, "loss": 1.7915, "step": 383 }, { "epoch": 0.06, "grad_norm": 0.3914658024096451, "learning_rate": 8.493922975545469e-05, "loss": 1.7883, "step": 384 }, { "epoch": 0.06, "grad_norm": 0.3709299103461753, "learning_rate": 8.492605066627618e-05, "loss": 1.7951, "step": 385 }, { "epoch": 0.06, "grad_norm": 0.3506925098949618, "learning_rate": 8.491287157709767e-05, "loss": 1.7889, "step": 386 }, { "epoch": 0.06, "grad_norm": 0.29624563115275554, "learning_rate": 8.489969248791918e-05, "loss": 1.7831, "step": 387 }, { "epoch": 0.06, "grad_norm": 0.25682264450924897, "learning_rate": 8.488651339874066e-05, "loss": 1.7874, "step": 388 }, { "epoch": 0.06, "grad_norm": 0.2460261750961129, "learning_rate": 8.487333430956217e-05, "loss": 1.7828, "step": 389 }, { "epoch": 0.06, "grad_norm": 0.24758082633885842, "learning_rate": 8.486015522038366e-05, "loss": 1.7794, "step": 390 }, { "epoch": 0.06, "grad_norm": 0.33054734116446843, "learning_rate": 8.484697613120516e-05, "loss": 1.7818, "step": 391 }, { "epoch": 0.06, "grad_norm": 0.4561811736514614, "learning_rate": 8.483379704202666e-05, "loss": 1.7922, "step": 392 }, { "epoch": 0.06, "grad_norm": 0.49921174238421934, "learning_rate": 8.482061795284816e-05, "loss": 1.7798, "step": 393 }, { "epoch": 0.06, "grad_norm": 0.4554136076143871, "learning_rate": 8.480743886366965e-05, "loss": 1.7822, "step": 394 }, { "epoch": 0.06, "grad_norm": 0.41157410101274916, "learning_rate": 8.479425977449115e-05, "loss": 1.7798, "step": 395 }, { "epoch": 0.06, "grad_norm": 0.40589712484793644, "learning_rate": 8.478108068531264e-05, "loss": 1.7865, "step": 396 }, { "epoch": 0.06, "grad_norm": 0.41969602312949894, "learning_rate": 8.476790159613413e-05, "loss": 1.7846, "step": 397 }, { "epoch": 0.06, "grad_norm": 0.3716209700804159, "learning_rate": 8.475472250695564e-05, "loss": 1.7831, "step": 398 }, { "epoch": 0.06, "grad_norm": 0.2807622431725275, "learning_rate": 8.474154341777713e-05, "loss": 1.7785, "step": 399 }, { "epoch": 0.06, "grad_norm": 0.2882135171870514, "learning_rate": 8.472836432859863e-05, "loss": 1.7955, "step": 400 }, { "epoch": 0.06, "grad_norm": 0.33929519699606947, "learning_rate": 8.471518523942012e-05, "loss": 1.7821, "step": 401 }, { "epoch": 0.06, "grad_norm": 0.36786610502124734, "learning_rate": 8.470200615024163e-05, "loss": 1.776, "step": 402 }, { "epoch": 0.06, "grad_norm": 0.3364252349308489, "learning_rate": 8.468882706106312e-05, "loss": 1.7886, "step": 403 }, { "epoch": 0.06, "grad_norm": 0.2402932781772499, "learning_rate": 8.467564797188462e-05, "loss": 1.7841, "step": 404 }, { "epoch": 0.06, "grad_norm": 0.25361231156390895, "learning_rate": 8.466246888270611e-05, "loss": 1.7807, "step": 405 }, { "epoch": 0.06, "grad_norm": 0.2615629884646646, "learning_rate": 8.46492897935276e-05, "loss": 1.7791, "step": 406 }, { "epoch": 0.06, "grad_norm": 0.28499785308119957, "learning_rate": 8.463611070434911e-05, "loss": 1.7755, "step": 407 }, { "epoch": 0.06, "grad_norm": 0.3356974383461246, "learning_rate": 8.46229316151706e-05, "loss": 1.7711, "step": 408 }, { "epoch": 0.06, "grad_norm": 0.30749102123781535, "learning_rate": 8.46097525259921e-05, "loss": 1.7825, "step": 409 }, { "epoch": 0.06, "grad_norm": 0.2672389622630441, "learning_rate": 8.459657343681359e-05, "loss": 1.7726, "step": 410 }, { "epoch": 0.06, "grad_norm": 0.2658653893968794, "learning_rate": 8.45833943476351e-05, "loss": 1.7919, "step": 411 }, { "epoch": 0.06, "grad_norm": 0.28816762727415146, "learning_rate": 8.457021525845658e-05, "loss": 1.774, "step": 412 }, { "epoch": 0.06, "grad_norm": 0.3546252508516257, "learning_rate": 8.455703616927809e-05, "loss": 1.7764, "step": 413 }, { "epoch": 0.06, "grad_norm": 0.3982229064694483, "learning_rate": 8.454385708009958e-05, "loss": 1.7797, "step": 414 }, { "epoch": 0.06, "grad_norm": 0.39743403855878273, "learning_rate": 8.453067799092107e-05, "loss": 1.7818, "step": 415 }, { "epoch": 0.06, "grad_norm": 0.3565095947734143, "learning_rate": 8.451749890174258e-05, "loss": 1.7689, "step": 416 }, { "epoch": 0.06, "grad_norm": 0.33445086643446986, "learning_rate": 8.450431981256408e-05, "loss": 1.7703, "step": 417 }, { "epoch": 0.06, "grad_norm": 0.3315820482846953, "learning_rate": 8.449114072338557e-05, "loss": 1.7695, "step": 418 }, { "epoch": 0.06, "grad_norm": 0.28800691098886155, "learning_rate": 8.447796163420706e-05, "loss": 1.7735, "step": 419 }, { "epoch": 0.06, "grad_norm": 0.2801123597101435, "learning_rate": 8.446478254502856e-05, "loss": 1.7727, "step": 420 }, { "epoch": 0.06, "grad_norm": 0.3002418032943439, "learning_rate": 8.445160345585005e-05, "loss": 1.7694, "step": 421 }, { "epoch": 0.06, "grad_norm": 0.3105457712936389, "learning_rate": 8.443842436667156e-05, "loss": 1.7743, "step": 422 }, { "epoch": 0.06, "grad_norm": 0.31681589803189375, "learning_rate": 8.442524527749305e-05, "loss": 1.7754, "step": 423 }, { "epoch": 0.06, "grad_norm": 0.29540052374128717, "learning_rate": 8.441206618831454e-05, "loss": 1.7676, "step": 424 }, { "epoch": 0.06, "grad_norm": 0.2786507071219561, "learning_rate": 8.439888709913604e-05, "loss": 1.7768, "step": 425 }, { "epoch": 0.06, "grad_norm": 0.2882558823750487, "learning_rate": 8.438570800995755e-05, "loss": 1.7559, "step": 426 }, { "epoch": 0.06, "grad_norm": 0.3231073755842465, "learning_rate": 8.437252892077904e-05, "loss": 1.7718, "step": 427 }, { "epoch": 0.06, "grad_norm": 0.3009918727669168, "learning_rate": 8.435934983160053e-05, "loss": 1.7558, "step": 428 }, { "epoch": 0.06, "grad_norm": 0.2628726596154197, "learning_rate": 8.434617074242203e-05, "loss": 1.7592, "step": 429 }, { "epoch": 0.06, "grad_norm": 0.28399571790394734, "learning_rate": 8.433299165324352e-05, "loss": 1.7671, "step": 430 }, { "epoch": 0.06, "grad_norm": 0.25544475849265763, "learning_rate": 8.431981256406503e-05, "loss": 1.7663, "step": 431 }, { "epoch": 0.06, "grad_norm": 0.23553288100790656, "learning_rate": 8.430663347488652e-05, "loss": 1.7739, "step": 432 }, { "epoch": 0.06, "grad_norm": 0.2775059913303605, "learning_rate": 8.429345438570802e-05, "loss": 1.7679, "step": 433 }, { "epoch": 0.06, "grad_norm": 0.3075973810425004, "learning_rate": 8.428027529652951e-05, "loss": 1.7615, "step": 434 }, { "epoch": 0.06, "grad_norm": 0.2930374223294978, "learning_rate": 8.426709620735102e-05, "loss": 1.7666, "step": 435 }, { "epoch": 0.06, "grad_norm": 0.2579433797280727, "learning_rate": 8.42539171181725e-05, "loss": 1.767, "step": 436 }, { "epoch": 0.06, "grad_norm": 0.24664576276610475, "learning_rate": 8.4240738028994e-05, "loss": 1.7673, "step": 437 }, { "epoch": 0.06, "grad_norm": 0.2369430249499012, "learning_rate": 8.42275589398155e-05, "loss": 1.7651, "step": 438 }, { "epoch": 0.06, "grad_norm": 0.22260512529991971, "learning_rate": 8.421437985063699e-05, "loss": 1.7656, "step": 439 }, { "epoch": 0.06, "grad_norm": 0.2500300140196859, "learning_rate": 8.420120076145849e-05, "loss": 1.7563, "step": 440 }, { "epoch": 0.06, "grad_norm": 0.2973553354592089, "learning_rate": 8.418802167227999e-05, "loss": 1.7686, "step": 441 }, { "epoch": 0.06, "grad_norm": 0.3473837490426601, "learning_rate": 8.417484258310149e-05, "loss": 1.766, "step": 442 }, { "epoch": 0.06, "grad_norm": 0.37681005189169203, "learning_rate": 8.416166349392298e-05, "loss": 1.7644, "step": 443 }, { "epoch": 0.07, "grad_norm": 0.43730723219972917, "learning_rate": 8.414848440474447e-05, "loss": 1.755, "step": 444 }, { "epoch": 0.07, "grad_norm": 0.48972509251420343, "learning_rate": 8.413530531556597e-05, "loss": 1.7574, "step": 445 }, { "epoch": 0.07, "grad_norm": 0.4405993959888919, "learning_rate": 8.412212622638747e-05, "loss": 1.7486, "step": 446 }, { "epoch": 0.07, "grad_norm": 0.3363658300532759, "learning_rate": 8.410894713720897e-05, "loss": 1.7578, "step": 447 }, { "epoch": 0.07, "grad_norm": 0.2582139601078949, "learning_rate": 8.409576804803046e-05, "loss": 1.7612, "step": 448 }, { "epoch": 0.07, "grad_norm": 0.2811740539218468, "learning_rate": 8.408258895885196e-05, "loss": 1.7597, "step": 449 }, { "epoch": 0.07, "grad_norm": 0.2754375286092553, "learning_rate": 8.406940986967346e-05, "loss": 1.7618, "step": 450 }, { "epoch": 0.07, "grad_norm": 0.2708471785317565, "learning_rate": 8.405623078049496e-05, "loss": 1.7566, "step": 451 }, { "epoch": 0.07, "grad_norm": 0.27721812968333487, "learning_rate": 8.404305169131645e-05, "loss": 1.7546, "step": 452 }, { "epoch": 0.07, "grad_norm": 0.23002196109659534, "learning_rate": 8.402987260213794e-05, "loss": 1.7563, "step": 453 }, { "epoch": 0.07, "grad_norm": 0.26623499924803207, "learning_rate": 8.401669351295944e-05, "loss": 1.7632, "step": 454 }, { "epoch": 0.07, "grad_norm": 0.31058712725330645, "learning_rate": 8.400351442378095e-05, "loss": 1.7554, "step": 455 }, { "epoch": 0.07, "grad_norm": 0.2565651528940601, "learning_rate": 8.399033533460244e-05, "loss": 1.7495, "step": 456 }, { "epoch": 0.07, "grad_norm": 0.22030881745923991, "learning_rate": 8.397715624542393e-05, "loss": 1.7516, "step": 457 }, { "epoch": 0.07, "grad_norm": 0.22786327950251026, "learning_rate": 8.396397715624543e-05, "loss": 1.7545, "step": 458 }, { "epoch": 0.07, "grad_norm": 0.22992085421490108, "learning_rate": 8.395079806706693e-05, "loss": 1.7524, "step": 459 }, { "epoch": 0.07, "grad_norm": 0.2745377165784387, "learning_rate": 8.393761897788841e-05, "loss": 1.757, "step": 460 }, { "epoch": 0.07, "grad_norm": 0.27034688441148863, "learning_rate": 8.392443988870992e-05, "loss": 1.7514, "step": 461 }, { "epoch": 0.07, "grad_norm": 0.21431031046245713, "learning_rate": 8.391126079953142e-05, "loss": 1.7516, "step": 462 }, { "epoch": 0.07, "grad_norm": 0.24404100887840613, "learning_rate": 8.389808171035291e-05, "loss": 1.7446, "step": 463 }, { "epoch": 0.07, "grad_norm": 0.25123054377636167, "learning_rate": 8.38849026211744e-05, "loss": 1.7375, "step": 464 }, { "epoch": 0.07, "grad_norm": 0.22147497464193822, "learning_rate": 8.387172353199591e-05, "loss": 1.7531, "step": 465 }, { "epoch": 0.07, "grad_norm": 0.2719165207073828, "learning_rate": 8.38585444428174e-05, "loss": 1.7427, "step": 466 }, { "epoch": 0.07, "grad_norm": 0.3072701977020835, "learning_rate": 8.38453653536389e-05, "loss": 1.7554, "step": 467 }, { "epoch": 0.07, "grad_norm": 0.3465803271567775, "learning_rate": 8.383218626446039e-05, "loss": 1.7362, "step": 468 }, { "epoch": 0.07, "grad_norm": 0.401606701101308, "learning_rate": 8.381900717528189e-05, "loss": 1.7487, "step": 469 }, { "epoch": 0.07, "grad_norm": 0.3606552145593931, "learning_rate": 8.380582808610339e-05, "loss": 1.7401, "step": 470 }, { "epoch": 0.07, "grad_norm": 0.31305392679932725, "learning_rate": 8.379264899692489e-05, "loss": 1.7426, "step": 471 }, { "epoch": 0.07, "grad_norm": 0.3283966913328143, "learning_rate": 8.377946990774638e-05, "loss": 1.745, "step": 472 }, { "epoch": 0.07, "grad_norm": 0.29719539854668975, "learning_rate": 8.376629081856787e-05, "loss": 1.7479, "step": 473 }, { "epoch": 0.07, "grad_norm": 0.2858720938289175, "learning_rate": 8.375311172938938e-05, "loss": 1.7471, "step": 474 }, { "epoch": 0.07, "grad_norm": 0.30869366396700376, "learning_rate": 8.373993264021087e-05, "loss": 1.7426, "step": 475 }, { "epoch": 0.07, "grad_norm": 0.2970917996723054, "learning_rate": 8.372675355103237e-05, "loss": 1.748, "step": 476 }, { "epoch": 0.07, "grad_norm": 0.31796639499576057, "learning_rate": 8.371357446185386e-05, "loss": 1.7482, "step": 477 }, { "epoch": 0.07, "grad_norm": 0.3755211025212181, "learning_rate": 8.370039537267536e-05, "loss": 1.7441, "step": 478 }, { "epoch": 0.07, "grad_norm": 0.4281842470615676, "learning_rate": 8.368721628349686e-05, "loss": 1.7413, "step": 479 }, { "epoch": 0.07, "grad_norm": 0.4094549002505819, "learning_rate": 8.367403719431836e-05, "loss": 1.7509, "step": 480 }, { "epoch": 0.07, "grad_norm": 0.3581404361289346, "learning_rate": 8.366085810513985e-05, "loss": 1.7416, "step": 481 }, { "epoch": 0.07, "grad_norm": 0.3304524068236931, "learning_rate": 8.364767901596134e-05, "loss": 1.7444, "step": 482 }, { "epoch": 0.07, "grad_norm": 0.35489265098811323, "learning_rate": 8.363449992678285e-05, "loss": 1.7506, "step": 483 }, { "epoch": 0.07, "grad_norm": 0.3714282179236144, "learning_rate": 8.362132083760433e-05, "loss": 1.745, "step": 484 }, { "epoch": 0.07, "grad_norm": 0.3586675337061257, "learning_rate": 8.360814174842584e-05, "loss": 1.7425, "step": 485 }, { "epoch": 0.07, "grad_norm": 0.2345396435881697, "learning_rate": 8.359496265924733e-05, "loss": 1.7367, "step": 486 }, { "epoch": 0.07, "grad_norm": 0.2053682387601687, "learning_rate": 8.358178357006883e-05, "loss": 1.7386, "step": 487 }, { "epoch": 0.07, "grad_norm": 0.2711812966223324, "learning_rate": 8.356860448089032e-05, "loss": 1.7337, "step": 488 }, { "epoch": 0.07, "grad_norm": 0.258724050629809, "learning_rate": 8.355542539171183e-05, "loss": 1.7356, "step": 489 }, { "epoch": 0.07, "grad_norm": 0.19885527922839485, "learning_rate": 8.354224630253332e-05, "loss": 1.7313, "step": 490 }, { "epoch": 0.07, "grad_norm": 0.23059280089577702, "learning_rate": 8.352906721335482e-05, "loss": 1.737, "step": 491 }, { "epoch": 0.07, "grad_norm": 0.2870358462685661, "learning_rate": 8.351588812417631e-05, "loss": 1.7349, "step": 492 }, { "epoch": 0.07, "grad_norm": 0.2633075013669381, "learning_rate": 8.35027090349978e-05, "loss": 1.7353, "step": 493 }, { "epoch": 0.07, "grad_norm": 0.3049199627731043, "learning_rate": 8.348952994581931e-05, "loss": 1.7384, "step": 494 }, { "epoch": 0.07, "grad_norm": 0.34926345039498624, "learning_rate": 8.34763508566408e-05, "loss": 1.7287, "step": 495 }, { "epoch": 0.07, "grad_norm": 0.31033645995550346, "learning_rate": 8.34631717674623e-05, "loss": 1.7386, "step": 496 }, { "epoch": 0.07, "grad_norm": 0.23708657622061127, "learning_rate": 8.344999267828379e-05, "loss": 1.7376, "step": 497 }, { "epoch": 0.07, "grad_norm": 0.2503644410759697, "learning_rate": 8.34368135891053e-05, "loss": 1.7286, "step": 498 }, { "epoch": 0.07, "grad_norm": 0.30108885609906977, "learning_rate": 8.342363449992679e-05, "loss": 1.7424, "step": 499 }, { "epoch": 0.07, "grad_norm": 0.3640305222721408, "learning_rate": 8.341045541074829e-05, "loss": 1.7365, "step": 500 }, { "epoch": 0.07, "grad_norm": 0.3862444666501204, "learning_rate": 8.339727632156978e-05, "loss": 1.7388, "step": 501 }, { "epoch": 0.07, "grad_norm": 0.33565159533458905, "learning_rate": 8.338409723239127e-05, "loss": 1.725, "step": 502 }, { "epoch": 0.07, "grad_norm": 0.24120380275839087, "learning_rate": 8.337091814321278e-05, "loss": 1.7386, "step": 503 }, { "epoch": 0.07, "grad_norm": 0.2019440056977102, "learning_rate": 8.335773905403427e-05, "loss": 1.7364, "step": 504 }, { "epoch": 0.07, "grad_norm": 0.19665207193807027, "learning_rate": 8.334455996485577e-05, "loss": 1.7384, "step": 505 }, { "epoch": 0.07, "grad_norm": 0.20041439367425065, "learning_rate": 8.333138087567726e-05, "loss": 1.7298, "step": 506 }, { "epoch": 0.07, "grad_norm": 0.22759855658411884, "learning_rate": 8.331820178649877e-05, "loss": 1.7374, "step": 507 }, { "epoch": 0.07, "grad_norm": 0.2237449007183391, "learning_rate": 8.330502269732025e-05, "loss": 1.736, "step": 508 }, { "epoch": 0.07, "grad_norm": 0.19892064401379644, "learning_rate": 8.329184360814176e-05, "loss": 1.7309, "step": 509 }, { "epoch": 0.07, "grad_norm": 0.21780921689097468, "learning_rate": 8.327866451896325e-05, "loss": 1.7247, "step": 510 }, { "epoch": 0.07, "grad_norm": 0.22223023552216575, "learning_rate": 8.326548542978474e-05, "loss": 1.7352, "step": 511 }, { "epoch": 0.07, "grad_norm": 0.23435078161758566, "learning_rate": 8.325230634060624e-05, "loss": 1.727, "step": 512 }, { "epoch": 0.08, "grad_norm": 0.25436357491660655, "learning_rate": 8.323912725142775e-05, "loss": 1.7182, "step": 513 }, { "epoch": 0.08, "grad_norm": 0.2542313172961627, "learning_rate": 8.322594816224924e-05, "loss": 1.7259, "step": 514 }, { "epoch": 0.08, "grad_norm": 0.25353563544590524, "learning_rate": 8.321276907307073e-05, "loss": 1.7131, "step": 515 }, { "epoch": 0.08, "grad_norm": 0.25178826296170725, "learning_rate": 8.319958998389223e-05, "loss": 1.7303, "step": 516 }, { "epoch": 0.08, "grad_norm": 0.24967442898411737, "learning_rate": 8.318641089471372e-05, "loss": 1.7156, "step": 517 }, { "epoch": 0.08, "grad_norm": 0.29093688012404956, "learning_rate": 8.317323180553523e-05, "loss": 1.7273, "step": 518 }, { "epoch": 0.08, "grad_norm": 0.3408463856901383, "learning_rate": 8.316005271635672e-05, "loss": 1.731, "step": 519 }, { "epoch": 0.08, "grad_norm": 0.3654511204209073, "learning_rate": 8.314687362717822e-05, "loss": 1.732, "step": 520 }, { "epoch": 0.08, "grad_norm": 0.3271746533985564, "learning_rate": 8.313369453799971e-05, "loss": 1.7295, "step": 521 }, { "epoch": 0.08, "grad_norm": 0.2717225234340834, "learning_rate": 8.312051544882122e-05, "loss": 1.7325, "step": 522 }, { "epoch": 0.08, "grad_norm": 0.3081217924018755, "learning_rate": 8.310733635964271e-05, "loss": 1.7246, "step": 523 }, { "epoch": 0.08, "grad_norm": 0.3527075080404129, "learning_rate": 8.30941572704642e-05, "loss": 1.7216, "step": 524 }, { "epoch": 0.08, "grad_norm": 0.4154842597521178, "learning_rate": 8.30809781812857e-05, "loss": 1.7255, "step": 525 }, { "epoch": 0.08, "grad_norm": 0.443067725739395, "learning_rate": 8.306779909210719e-05, "loss": 1.7281, "step": 526 }, { "epoch": 0.08, "grad_norm": 0.4106745425675618, "learning_rate": 8.305462000292868e-05, "loss": 1.7302, "step": 527 }, { "epoch": 0.08, "grad_norm": 0.33999747867070007, "learning_rate": 8.304144091375019e-05, "loss": 1.7267, "step": 528 }, { "epoch": 0.08, "grad_norm": 0.28901846740062775, "learning_rate": 8.302826182457169e-05, "loss": 1.7262, "step": 529 }, { "epoch": 0.08, "grad_norm": 0.29966915847542663, "learning_rate": 8.301508273539318e-05, "loss": 1.7313, "step": 530 }, { "epoch": 0.08, "grad_norm": 0.31328357913945787, "learning_rate": 8.300190364621469e-05, "loss": 1.7218, "step": 531 }, { "epoch": 0.08, "grad_norm": 0.2814137310527097, "learning_rate": 8.298872455703617e-05, "loss": 1.7215, "step": 532 }, { "epoch": 0.08, "grad_norm": 0.24123503809014038, "learning_rate": 8.297554546785767e-05, "loss": 1.7188, "step": 533 }, { "epoch": 0.08, "grad_norm": 0.28016429302641516, "learning_rate": 8.296236637867917e-05, "loss": 1.7198, "step": 534 }, { "epoch": 0.08, "grad_norm": 0.3117115191862107, "learning_rate": 8.294918728950066e-05, "loss": 1.7262, "step": 535 }, { "epoch": 0.08, "grad_norm": 0.278045134177961, "learning_rate": 8.293600820032216e-05, "loss": 1.723, "step": 536 }, { "epoch": 0.08, "grad_norm": 0.23769710910310898, "learning_rate": 8.292282911114366e-05, "loss": 1.723, "step": 537 }, { "epoch": 0.08, "grad_norm": 0.24511433211495529, "learning_rate": 8.290965002196516e-05, "loss": 1.7253, "step": 538 }, { "epoch": 0.08, "grad_norm": 0.2384929581877857, "learning_rate": 8.289647093278665e-05, "loss": 1.7122, "step": 539 }, { "epoch": 0.08, "grad_norm": 0.22551550594015082, "learning_rate": 8.288329184360814e-05, "loss": 1.7219, "step": 540 }, { "epoch": 0.08, "grad_norm": 0.23506955783092845, "learning_rate": 8.287011275442964e-05, "loss": 1.7233, "step": 541 }, { "epoch": 0.08, "grad_norm": 0.21860310689837917, "learning_rate": 8.285693366525115e-05, "loss": 1.7221, "step": 542 }, { "epoch": 0.08, "grad_norm": 0.20398647046618187, "learning_rate": 8.284375457607264e-05, "loss": 1.7213, "step": 543 }, { "epoch": 0.08, "grad_norm": 0.24633014333201053, "learning_rate": 8.283057548689413e-05, "loss": 1.7132, "step": 544 }, { "epoch": 0.08, "grad_norm": 0.2667137895735778, "learning_rate": 8.281739639771563e-05, "loss": 1.726, "step": 545 }, { "epoch": 0.08, "grad_norm": 0.21858001204347083, "learning_rate": 8.280421730853713e-05, "loss": 1.7112, "step": 546 }, { "epoch": 0.08, "grad_norm": 0.19721106291794568, "learning_rate": 8.279103821935863e-05, "loss": 1.722, "step": 547 }, { "epoch": 0.08, "grad_norm": 0.2051408273401384, "learning_rate": 8.277785913018012e-05, "loss": 1.7206, "step": 548 }, { "epoch": 0.08, "grad_norm": 0.21682627662474413, "learning_rate": 8.276468004100161e-05, "loss": 1.7151, "step": 549 }, { "epoch": 0.08, "grad_norm": 0.2438456543254191, "learning_rate": 8.275150095182311e-05, "loss": 1.711, "step": 550 }, { "epoch": 0.08, "grad_norm": 0.2629415416448845, "learning_rate": 8.27383218626446e-05, "loss": 1.7155, "step": 551 }, { "epoch": 0.08, "grad_norm": 0.29381087938708167, "learning_rate": 8.272514277346611e-05, "loss": 1.7184, "step": 552 }, { "epoch": 0.08, "grad_norm": 0.3068644717057271, "learning_rate": 8.27119636842876e-05, "loss": 1.7071, "step": 553 }, { "epoch": 0.08, "grad_norm": 0.3266717891225327, "learning_rate": 8.26987845951091e-05, "loss": 1.7144, "step": 554 }, { "epoch": 0.08, "grad_norm": 0.3342256318259162, "learning_rate": 8.26856055059306e-05, "loss": 1.7132, "step": 555 }, { "epoch": 0.08, "grad_norm": 0.3507430866157419, "learning_rate": 8.267242641675208e-05, "loss": 1.7222, "step": 556 }, { "epoch": 0.08, "grad_norm": 0.35401841712709037, "learning_rate": 8.265924732757359e-05, "loss": 1.7163, "step": 557 }, { "epoch": 0.08, "grad_norm": 0.29152885792134353, "learning_rate": 8.264606823839509e-05, "loss": 1.7021, "step": 558 }, { "epoch": 0.08, "grad_norm": 0.2321802057678123, "learning_rate": 8.263288914921658e-05, "loss": 1.715, "step": 559 }, { "epoch": 0.08, "grad_norm": 0.20521573981201763, "learning_rate": 8.261971006003807e-05, "loss": 1.7136, "step": 560 }, { "epoch": 0.08, "grad_norm": 0.22389843673660376, "learning_rate": 8.260653097085958e-05, "loss": 1.7145, "step": 561 }, { "epoch": 0.08, "grad_norm": 0.26769790258636306, "learning_rate": 8.259335188168107e-05, "loss": 1.7135, "step": 562 }, { "epoch": 0.08, "grad_norm": 0.263472778250681, "learning_rate": 8.258017279250257e-05, "loss": 1.7153, "step": 563 }, { "epoch": 0.08, "grad_norm": 0.20438761322969645, "learning_rate": 8.256699370332406e-05, "loss": 1.7053, "step": 564 }, { "epoch": 0.08, "grad_norm": 0.2711791794052338, "learning_rate": 8.255381461414556e-05, "loss": 1.7076, "step": 565 }, { "epoch": 0.08, "grad_norm": 0.29324151826012396, "learning_rate": 8.254063552496706e-05, "loss": 1.7162, "step": 566 }, { "epoch": 0.08, "grad_norm": 0.23680109722780296, "learning_rate": 8.252745643578856e-05, "loss": 1.7173, "step": 567 }, { "epoch": 0.08, "grad_norm": 0.3897963836334016, "learning_rate": 8.251427734661005e-05, "loss": 1.709, "step": 568 }, { "epoch": 0.08, "grad_norm": 0.3107639335861359, "learning_rate": 8.250109825743154e-05, "loss": 1.7108, "step": 569 }, { "epoch": 0.08, "grad_norm": 0.31507837210091977, "learning_rate": 8.248791916825305e-05, "loss": 1.7177, "step": 570 }, { "epoch": 0.08, "grad_norm": 0.407833593775017, "learning_rate": 8.247474007907455e-05, "loss": 1.7158, "step": 571 }, { "epoch": 0.08, "grad_norm": 0.33475655675893035, "learning_rate": 8.246156098989604e-05, "loss": 1.7159, "step": 572 }, { "epoch": 0.08, "grad_norm": 0.30470045477617375, "learning_rate": 8.244838190071753e-05, "loss": 1.7133, "step": 573 }, { "epoch": 0.08, "grad_norm": 0.2361385908228469, "learning_rate": 8.243520281153903e-05, "loss": 1.7138, "step": 574 }, { "epoch": 0.08, "grad_norm": 0.3028517511605204, "learning_rate": 8.242202372236052e-05, "loss": 1.7061, "step": 575 }, { "epoch": 0.08, "grad_norm": 0.26913911701533544, "learning_rate": 8.240884463318203e-05, "loss": 1.7081, "step": 576 }, { "epoch": 0.08, "grad_norm": 0.24779044758095875, "learning_rate": 8.239566554400352e-05, "loss": 1.708, "step": 577 }, { "epoch": 0.08, "grad_norm": 0.2233287796665562, "learning_rate": 8.238248645482501e-05, "loss": 1.7112, "step": 578 }, { "epoch": 0.08, "grad_norm": 0.2712079799980342, "learning_rate": 8.236930736564652e-05, "loss": 1.7124, "step": 579 }, { "epoch": 0.08, "grad_norm": 0.2094942014575434, "learning_rate": 8.2356128276468e-05, "loss": 1.7054, "step": 580 }, { "epoch": 0.09, "grad_norm": 0.21486524279150165, "learning_rate": 8.234294918728951e-05, "loss": 1.7119, "step": 581 }, { "epoch": 0.09, "grad_norm": 0.2090205889232179, "learning_rate": 8.2329770098111e-05, "loss": 1.7059, "step": 582 }, { "epoch": 0.09, "grad_norm": 0.20460593187920675, "learning_rate": 8.23165910089325e-05, "loss": 1.7066, "step": 583 }, { "epoch": 0.09, "grad_norm": 0.1767845416143033, "learning_rate": 8.230341191975399e-05, "loss": 1.7024, "step": 584 }, { "epoch": 0.09, "grad_norm": 0.17887391851705126, "learning_rate": 8.22902328305755e-05, "loss": 1.7067, "step": 585 }, { "epoch": 0.09, "grad_norm": 0.1695109544582885, "learning_rate": 8.227705374139699e-05, "loss": 1.6895, "step": 586 }, { "epoch": 0.09, "grad_norm": 0.2083349170582134, "learning_rate": 8.226387465221849e-05, "loss": 1.6915, "step": 587 }, { "epoch": 0.09, "grad_norm": 0.217567810379028, "learning_rate": 8.225069556303998e-05, "loss": 1.7014, "step": 588 }, { "epoch": 0.09, "grad_norm": 0.26578168421783505, "learning_rate": 8.223751647386147e-05, "loss": 1.6959, "step": 589 }, { "epoch": 0.09, "grad_norm": 0.26759525206680784, "learning_rate": 8.222433738468297e-05, "loss": 1.7081, "step": 590 }, { "epoch": 0.09, "grad_norm": 0.29241320421717, "learning_rate": 8.221115829550447e-05, "loss": 1.7, "step": 591 }, { "epoch": 0.09, "grad_norm": 0.2665660324658676, "learning_rate": 8.219797920632597e-05, "loss": 1.7116, "step": 592 }, { "epoch": 0.09, "grad_norm": 0.2543632897483254, "learning_rate": 8.218480011714746e-05, "loss": 1.6998, "step": 593 }, { "epoch": 0.09, "grad_norm": 0.24422324009786234, "learning_rate": 8.217162102796897e-05, "loss": 1.7032, "step": 594 }, { "epoch": 0.09, "grad_norm": 0.2412157212895076, "learning_rate": 8.215844193879046e-05, "loss": 1.7002, "step": 595 }, { "epoch": 0.09, "grad_norm": 0.22950526573401658, "learning_rate": 8.214526284961196e-05, "loss": 1.6968, "step": 596 }, { "epoch": 0.09, "grad_norm": 0.2405536739297689, "learning_rate": 8.213208376043345e-05, "loss": 1.7067, "step": 597 }, { "epoch": 0.09, "grad_norm": 0.22384819760583757, "learning_rate": 8.211890467125494e-05, "loss": 1.7002, "step": 598 }, { "epoch": 0.09, "grad_norm": 0.22165394505798217, "learning_rate": 8.210572558207644e-05, "loss": 1.7053, "step": 599 }, { "epoch": 0.09, "grad_norm": 0.22325001055054616, "learning_rate": 8.209254649289794e-05, "loss": 1.7076, "step": 600 }, { "epoch": 0.09, "grad_norm": 0.24437917178401694, "learning_rate": 8.207936740371944e-05, "loss": 1.6863, "step": 601 }, { "epoch": 0.09, "grad_norm": 0.24473623901397126, "learning_rate": 8.206618831454093e-05, "loss": 1.7029, "step": 602 }, { "epoch": 0.09, "grad_norm": 0.23793249982285095, "learning_rate": 8.205300922536244e-05, "loss": 1.7003, "step": 603 }, { "epoch": 0.09, "grad_norm": 0.27010899475555333, "learning_rate": 8.203983013618392e-05, "loss": 1.7035, "step": 604 }, { "epoch": 0.09, "grad_norm": 0.2974971413903659, "learning_rate": 8.202665104700543e-05, "loss": 1.6963, "step": 605 }, { "epoch": 0.09, "grad_norm": 0.3391211533028402, "learning_rate": 8.201347195782692e-05, "loss": 1.699, "step": 606 }, { "epoch": 0.09, "grad_norm": 0.401887788096081, "learning_rate": 8.200029286864841e-05, "loss": 1.7001, "step": 607 }, { "epoch": 0.09, "grad_norm": 0.4014157913865194, "learning_rate": 8.198711377946991e-05, "loss": 1.7035, "step": 608 }, { "epoch": 0.09, "grad_norm": 0.34227601583187883, "learning_rate": 8.197393469029142e-05, "loss": 1.7031, "step": 609 }, { "epoch": 0.09, "grad_norm": 0.2572596615978446, "learning_rate": 8.196075560111291e-05, "loss": 1.691, "step": 610 }, { "epoch": 0.09, "grad_norm": 0.25436898174940326, "learning_rate": 8.19475765119344e-05, "loss": 1.6983, "step": 611 }, { "epoch": 0.09, "grad_norm": 0.2966388678401186, "learning_rate": 8.19343974227559e-05, "loss": 1.6939, "step": 612 }, { "epoch": 0.09, "grad_norm": 0.2609270973789931, "learning_rate": 8.192121833357739e-05, "loss": 1.6882, "step": 613 }, { "epoch": 0.09, "grad_norm": 0.22900064576600393, "learning_rate": 8.190803924439888e-05, "loss": 1.6962, "step": 614 }, { "epoch": 0.09, "grad_norm": 0.2157661551046652, "learning_rate": 8.189486015522039e-05, "loss": 1.6889, "step": 615 }, { "epoch": 0.09, "grad_norm": 0.23909710323754044, "learning_rate": 8.188168106604189e-05, "loss": 1.6969, "step": 616 }, { "epoch": 0.09, "grad_norm": 0.25769486284072124, "learning_rate": 8.186850197686338e-05, "loss": 1.699, "step": 617 }, { "epoch": 0.09, "grad_norm": 0.23459236703850359, "learning_rate": 8.185532288768489e-05, "loss": 1.6904, "step": 618 }, { "epoch": 0.09, "grad_norm": 0.23197840287816318, "learning_rate": 8.184214379850638e-05, "loss": 1.6927, "step": 619 }, { "epoch": 0.09, "grad_norm": 0.22922928506230492, "learning_rate": 8.182896470932787e-05, "loss": 1.691, "step": 620 }, { "epoch": 0.09, "grad_norm": 0.20472350901775296, "learning_rate": 8.181578562014937e-05, "loss": 1.6988, "step": 621 }, { "epoch": 0.09, "grad_norm": 0.21293532425438386, "learning_rate": 8.180260653097086e-05, "loss": 1.6983, "step": 622 }, { "epoch": 0.09, "grad_norm": 0.25813129719442796, "learning_rate": 8.178942744179236e-05, "loss": 1.6977, "step": 623 }, { "epoch": 0.09, "grad_norm": 0.28731586003331094, "learning_rate": 8.177624835261386e-05, "loss": 1.6917, "step": 624 }, { "epoch": 0.09, "grad_norm": 0.27778976830351854, "learning_rate": 8.176306926343536e-05, "loss": 1.6904, "step": 625 }, { "epoch": 0.09, "grad_norm": 0.2667191282626614, "learning_rate": 8.174989017425685e-05, "loss": 1.6906, "step": 626 }, { "epoch": 0.09, "grad_norm": 0.27135549254051117, "learning_rate": 8.173671108507834e-05, "loss": 1.7077, "step": 627 }, { "epoch": 0.09, "grad_norm": 0.2737735487643415, "learning_rate": 8.172353199589984e-05, "loss": 1.6919, "step": 628 }, { "epoch": 0.09, "grad_norm": 0.23702108817197906, "learning_rate": 8.171035290672134e-05, "loss": 1.6833, "step": 629 }, { "epoch": 0.09, "grad_norm": 0.21824459389931547, "learning_rate": 8.169717381754284e-05, "loss": 1.6874, "step": 630 }, { "epoch": 0.09, "grad_norm": 0.2551514671888147, "learning_rate": 8.168399472836433e-05, "loss": 1.6964, "step": 631 }, { "epoch": 0.09, "grad_norm": 0.2888406849522713, "learning_rate": 8.167081563918583e-05, "loss": 1.686, "step": 632 }, { "epoch": 0.09, "grad_norm": 0.3043373169879388, "learning_rate": 8.165763655000733e-05, "loss": 1.6909, "step": 633 }, { "epoch": 0.09, "grad_norm": 0.31851826485165624, "learning_rate": 8.164445746082883e-05, "loss": 1.6955, "step": 634 }, { "epoch": 0.09, "grad_norm": 0.31677231407393813, "learning_rate": 8.163127837165032e-05, "loss": 1.6931, "step": 635 }, { "epoch": 0.09, "grad_norm": 0.3235809995826595, "learning_rate": 8.161809928247181e-05, "loss": 1.6919, "step": 636 }, { "epoch": 0.09, "grad_norm": 0.31715316802417376, "learning_rate": 8.160492019329331e-05, "loss": 1.6972, "step": 637 }, { "epoch": 0.09, "grad_norm": 0.258710234201555, "learning_rate": 8.15917411041148e-05, "loss": 1.6908, "step": 638 }, { "epoch": 0.09, "grad_norm": 0.19364210951795302, "learning_rate": 8.157856201493631e-05, "loss": 1.6893, "step": 639 }, { "epoch": 0.09, "grad_norm": 0.1934820062184886, "learning_rate": 8.15653829257578e-05, "loss": 1.6937, "step": 640 }, { "epoch": 0.09, "grad_norm": 0.22124564568502275, "learning_rate": 8.15522038365793e-05, "loss": 1.6857, "step": 641 }, { "epoch": 0.09, "grad_norm": 0.24527757345647355, "learning_rate": 8.15390247474008e-05, "loss": 1.6964, "step": 642 }, { "epoch": 0.09, "grad_norm": 0.31637585588010625, "learning_rate": 8.152584565822228e-05, "loss": 1.6911, "step": 643 }, { "epoch": 0.09, "grad_norm": 0.33231300289557464, "learning_rate": 8.151266656904379e-05, "loss": 1.6857, "step": 644 }, { "epoch": 0.09, "grad_norm": 0.2979233182409515, "learning_rate": 8.149948747986529e-05, "loss": 1.6907, "step": 645 }, { "epoch": 0.09, "grad_norm": 0.2637032106008522, "learning_rate": 8.148630839068678e-05, "loss": 1.6922, "step": 646 }, { "epoch": 0.09, "grad_norm": 0.2729619019235736, "learning_rate": 8.147312930150827e-05, "loss": 1.6919, "step": 647 }, { "epoch": 0.09, "grad_norm": 0.3056180656791934, "learning_rate": 8.145995021232978e-05, "loss": 1.6866, "step": 648 }, { "epoch": 0.1, "grad_norm": 0.3025381384222673, "learning_rate": 8.144677112315127e-05, "loss": 1.6895, "step": 649 }, { "epoch": 0.1, "grad_norm": 0.26847771781612867, "learning_rate": 8.143359203397277e-05, "loss": 1.6893, "step": 650 }, { "epoch": 0.1, "grad_norm": 0.2438844041255715, "learning_rate": 8.142041294479426e-05, "loss": 1.6777, "step": 651 }, { "epoch": 0.1, "grad_norm": 0.29212647337890685, "learning_rate": 8.140723385561575e-05, "loss": 1.6962, "step": 652 }, { "epoch": 0.1, "grad_norm": 0.3279764517256754, "learning_rate": 8.139405476643726e-05, "loss": 1.686, "step": 653 }, { "epoch": 0.1, "grad_norm": 0.3266201901472985, "learning_rate": 8.138087567725876e-05, "loss": 1.6861, "step": 654 }, { "epoch": 0.1, "grad_norm": 0.29731852257716146, "learning_rate": 8.136769658808025e-05, "loss": 1.684, "step": 655 }, { "epoch": 0.1, "grad_norm": 0.31099064594669873, "learning_rate": 8.135451749890174e-05, "loss": 1.6842, "step": 656 }, { "epoch": 0.1, "grad_norm": 0.3060576588797521, "learning_rate": 8.134133840972325e-05, "loss": 1.6891, "step": 657 }, { "epoch": 0.1, "grad_norm": 0.26004140101304163, "learning_rate": 8.132815932054474e-05, "loss": 1.6854, "step": 658 }, { "epoch": 0.1, "grad_norm": 0.268187676963691, "learning_rate": 8.131498023136624e-05, "loss": 1.6838, "step": 659 }, { "epoch": 0.1, "grad_norm": 0.2726005198375338, "learning_rate": 8.130180114218773e-05, "loss": 1.692, "step": 660 }, { "epoch": 0.1, "grad_norm": 0.23864901844548525, "learning_rate": 8.128862205300923e-05, "loss": 1.6849, "step": 661 }, { "epoch": 0.1, "grad_norm": 0.2244877830433347, "learning_rate": 8.127544296383072e-05, "loss": 1.6806, "step": 662 }, { "epoch": 0.1, "grad_norm": 0.21510789414916953, "learning_rate": 8.126226387465223e-05, "loss": 1.6835, "step": 663 }, { "epoch": 0.1, "grad_norm": 0.207451826116181, "learning_rate": 8.124908478547372e-05, "loss": 1.6731, "step": 664 }, { "epoch": 0.1, "grad_norm": 0.2410531205632606, "learning_rate": 8.123590569629521e-05, "loss": 1.679, "step": 665 }, { "epoch": 0.1, "grad_norm": 0.2658490081241801, "learning_rate": 8.122272660711672e-05, "loss": 1.683, "step": 666 }, { "epoch": 0.1, "grad_norm": 0.24153141494391162, "learning_rate": 8.12095475179382e-05, "loss": 1.6738, "step": 667 }, { "epoch": 0.1, "grad_norm": 0.23164870510130753, "learning_rate": 8.119636842875971e-05, "loss": 1.6867, "step": 668 }, { "epoch": 0.1, "grad_norm": 0.24233480776179323, "learning_rate": 8.11831893395812e-05, "loss": 1.6773, "step": 669 }, { "epoch": 0.1, "grad_norm": 0.2574837382310888, "learning_rate": 8.11700102504027e-05, "loss": 1.6844, "step": 670 }, { "epoch": 0.1, "grad_norm": 0.22126722703874208, "learning_rate": 8.115683116122419e-05, "loss": 1.6869, "step": 671 }, { "epoch": 0.1, "grad_norm": 0.17423158084927914, "learning_rate": 8.11436520720457e-05, "loss": 1.6826, "step": 672 }, { "epoch": 0.1, "grad_norm": 0.2011587498434974, "learning_rate": 8.113047298286719e-05, "loss": 1.6932, "step": 673 }, { "epoch": 0.1, "grad_norm": 0.23419572476137138, "learning_rate": 8.111729389368869e-05, "loss": 1.681, "step": 674 }, { "epoch": 0.1, "grad_norm": 0.21861982894310164, "learning_rate": 8.110411480451018e-05, "loss": 1.6845, "step": 675 }, { "epoch": 0.1, "grad_norm": 0.2020605297807059, "learning_rate": 8.109093571533167e-05, "loss": 1.6758, "step": 676 }, { "epoch": 0.1, "grad_norm": 0.200339221622581, "learning_rate": 8.107775662615317e-05, "loss": 1.6852, "step": 677 }, { "epoch": 0.1, "grad_norm": 0.2272004211020317, "learning_rate": 8.106457753697467e-05, "loss": 1.6754, "step": 678 }, { "epoch": 0.1, "grad_norm": 0.2639656585184034, "learning_rate": 8.105139844779617e-05, "loss": 1.6651, "step": 679 }, { "epoch": 0.1, "grad_norm": 0.2821270304501907, "learning_rate": 8.103821935861766e-05, "loss": 1.6727, "step": 680 }, { "epoch": 0.1, "grad_norm": 0.2385914002979489, "learning_rate": 8.102504026943917e-05, "loss": 1.6757, "step": 681 }, { "epoch": 0.1, "grad_norm": 0.19689463498619292, "learning_rate": 8.101186118026066e-05, "loss": 1.675, "step": 682 }, { "epoch": 0.1, "grad_norm": 0.19388551672385698, "learning_rate": 8.099868209108216e-05, "loss": 1.6865, "step": 683 }, { "epoch": 0.1, "grad_norm": 0.21717430076929156, "learning_rate": 8.098550300190365e-05, "loss": 1.6786, "step": 684 }, { "epoch": 0.1, "grad_norm": 0.21911631079722832, "learning_rate": 8.097232391272514e-05, "loss": 1.677, "step": 685 }, { "epoch": 0.1, "grad_norm": 0.21899413808647583, "learning_rate": 8.095914482354664e-05, "loss": 1.6695, "step": 686 }, { "epoch": 0.1, "grad_norm": 0.256376958131802, "learning_rate": 8.094596573436814e-05, "loss": 1.681, "step": 687 }, { "epoch": 0.1, "grad_norm": 0.30968776120326585, "learning_rate": 8.093278664518964e-05, "loss": 1.6719, "step": 688 }, { "epoch": 0.1, "grad_norm": 0.3405179169627675, "learning_rate": 8.091960755601113e-05, "loss": 1.6729, "step": 689 }, { "epoch": 0.1, "grad_norm": 0.3758025068653412, "learning_rate": 8.090642846683264e-05, "loss": 1.6767, "step": 690 }, { "epoch": 0.1, "grad_norm": 0.37947974517090455, "learning_rate": 8.089324937765412e-05, "loss": 1.6722, "step": 691 }, { "epoch": 0.1, "grad_norm": 0.3209320177396622, "learning_rate": 8.088007028847563e-05, "loss": 1.6743, "step": 692 }, { "epoch": 0.1, "grad_norm": 0.2686562575879156, "learning_rate": 8.086689119929712e-05, "loss": 1.6722, "step": 693 }, { "epoch": 0.1, "grad_norm": 0.24152315432813073, "learning_rate": 8.085371211011861e-05, "loss": 1.6817, "step": 694 }, { "epoch": 0.1, "grad_norm": 0.25903562203260866, "learning_rate": 8.084053302094011e-05, "loss": 1.6808, "step": 695 }, { "epoch": 0.1, "grad_norm": 0.27215275116010934, "learning_rate": 8.082735393176162e-05, "loss": 1.6735, "step": 696 }, { "epoch": 0.1, "grad_norm": 0.2665073871904065, "learning_rate": 8.081417484258311e-05, "loss": 1.6813, "step": 697 }, { "epoch": 0.1, "grad_norm": 0.2595685011638328, "learning_rate": 8.08009957534046e-05, "loss": 1.6813, "step": 698 }, { "epoch": 0.1, "grad_norm": 0.2584829914241195, "learning_rate": 8.07878166642261e-05, "loss": 1.6699, "step": 699 }, { "epoch": 0.1, "grad_norm": 0.23308896936839194, "learning_rate": 8.077463757504759e-05, "loss": 1.6686, "step": 700 }, { "epoch": 0.1, "grad_norm": 0.18262768380478986, "learning_rate": 8.076145848586908e-05, "loss": 1.6727, "step": 701 }, { "epoch": 0.1, "grad_norm": 0.17402802326250397, "learning_rate": 8.074827939669059e-05, "loss": 1.671, "step": 702 }, { "epoch": 0.1, "grad_norm": 0.2079124720731814, "learning_rate": 8.073510030751208e-05, "loss": 1.6718, "step": 703 }, { "epoch": 0.1, "grad_norm": 0.21030626632342236, "learning_rate": 8.072192121833358e-05, "loss": 1.675, "step": 704 }, { "epoch": 0.1, "grad_norm": 0.19979944547574685, "learning_rate": 8.070874212915509e-05, "loss": 1.6719, "step": 705 }, { "epoch": 0.1, "grad_norm": 0.1960619390208134, "learning_rate": 8.069556303997658e-05, "loss": 1.6729, "step": 706 }, { "epoch": 0.1, "grad_norm": 0.1800588887952547, "learning_rate": 8.068238395079807e-05, "loss": 1.6742, "step": 707 }, { "epoch": 0.1, "grad_norm": 0.171338131397515, "learning_rate": 8.066920486161957e-05, "loss": 1.6681, "step": 708 }, { "epoch": 0.1, "grad_norm": 0.1952527594313872, "learning_rate": 8.065602577244106e-05, "loss": 1.672, "step": 709 }, { "epoch": 0.1, "grad_norm": 0.2029111128206527, "learning_rate": 8.064284668326255e-05, "loss": 1.6729, "step": 710 }, { "epoch": 0.1, "grad_norm": 0.2093511465528856, "learning_rate": 8.062966759408406e-05, "loss": 1.6662, "step": 711 }, { "epoch": 0.1, "grad_norm": 0.2355948665280437, "learning_rate": 8.061648850490556e-05, "loss": 1.6691, "step": 712 }, { "epoch": 0.1, "grad_norm": 0.25612769652057044, "learning_rate": 8.060330941572705e-05, "loss": 1.6691, "step": 713 }, { "epoch": 0.1, "grad_norm": 0.3178891893081287, "learning_rate": 8.059013032654856e-05, "loss": 1.6702, "step": 714 }, { "epoch": 0.1, "grad_norm": 0.32928109757980245, "learning_rate": 8.057695123737004e-05, "loss": 1.6804, "step": 715 }, { "epoch": 0.1, "grad_norm": 0.2732800407347181, "learning_rate": 8.056377214819154e-05, "loss": 1.6799, "step": 716 }, { "epoch": 0.1, "grad_norm": 0.24062058611392861, "learning_rate": 8.055059305901304e-05, "loss": 1.6678, "step": 717 }, { "epoch": 0.11, "grad_norm": 0.3002907368750325, "learning_rate": 8.053741396983453e-05, "loss": 1.6672, "step": 718 }, { "epoch": 0.11, "grad_norm": 0.31553599792720294, "learning_rate": 8.052423488065603e-05, "loss": 1.671, "step": 719 }, { "epoch": 0.11, "grad_norm": 0.25035709769683784, "learning_rate": 8.051105579147753e-05, "loss": 1.6746, "step": 720 }, { "epoch": 0.11, "grad_norm": 0.16571551955558791, "learning_rate": 8.049787670229903e-05, "loss": 1.6619, "step": 721 }, { "epoch": 0.11, "grad_norm": 0.21454683239201158, "learning_rate": 8.048469761312052e-05, "loss": 1.6686, "step": 722 }, { "epoch": 0.11, "grad_norm": 0.2310455452470971, "learning_rate": 8.047151852394201e-05, "loss": 1.6771, "step": 723 }, { "epoch": 0.11, "grad_norm": 0.1994236882273046, "learning_rate": 8.045833943476351e-05, "loss": 1.671, "step": 724 }, { "epoch": 0.11, "grad_norm": 0.18974389362814953, "learning_rate": 8.0445160345585e-05, "loss": 1.6675, "step": 725 }, { "epoch": 0.11, "grad_norm": 0.1860500322260672, "learning_rate": 8.043198125640651e-05, "loss": 1.658, "step": 726 }, { "epoch": 0.11, "grad_norm": 0.18863809672549492, "learning_rate": 8.0418802167228e-05, "loss": 1.6692, "step": 727 }, { "epoch": 0.11, "grad_norm": 0.19261227728615138, "learning_rate": 8.04056230780495e-05, "loss": 1.6722, "step": 728 }, { "epoch": 0.11, "grad_norm": 0.19104427920831676, "learning_rate": 8.0392443988871e-05, "loss": 1.6682, "step": 729 }, { "epoch": 0.11, "grad_norm": 0.19351874126385604, "learning_rate": 8.03792648996925e-05, "loss": 1.6698, "step": 730 }, { "epoch": 0.11, "grad_norm": 0.18561279955951115, "learning_rate": 8.036608581051399e-05, "loss": 1.6587, "step": 731 }, { "epoch": 0.11, "grad_norm": 0.20733342786735096, "learning_rate": 8.035290672133548e-05, "loss": 1.6686, "step": 732 }, { "epoch": 0.11, "grad_norm": 0.24389803201789031, "learning_rate": 8.033972763215698e-05, "loss": 1.6699, "step": 733 }, { "epoch": 0.11, "grad_norm": 0.3303044019383874, "learning_rate": 8.032654854297847e-05, "loss": 1.6685, "step": 734 }, { "epoch": 0.11, "grad_norm": 0.4326972184756624, "learning_rate": 8.031336945379998e-05, "loss": 1.671, "step": 735 }, { "epoch": 0.11, "grad_norm": 0.4749815372235629, "learning_rate": 8.030019036462147e-05, "loss": 1.6732, "step": 736 }, { "epoch": 0.11, "grad_norm": 0.4074470713549075, "learning_rate": 8.028701127544297e-05, "loss": 1.6627, "step": 737 }, { "epoch": 0.11, "grad_norm": 0.2325050031860467, "learning_rate": 8.027383218626447e-05, "loss": 1.6624, "step": 738 }, { "epoch": 0.11, "grad_norm": 0.26482099963107963, "learning_rate": 8.026065309708595e-05, "loss": 1.6714, "step": 739 }, { "epoch": 0.11, "grad_norm": 0.36679572880941774, "learning_rate": 8.024747400790746e-05, "loss": 1.6704, "step": 740 }, { "epoch": 0.11, "grad_norm": 0.26232767280919794, "learning_rate": 8.023429491872896e-05, "loss": 1.663, "step": 741 }, { "epoch": 0.11, "grad_norm": 0.21445846555925532, "learning_rate": 8.022111582955045e-05, "loss": 1.6525, "step": 742 }, { "epoch": 0.11, "grad_norm": 0.2532638225714052, "learning_rate": 8.020793674037194e-05, "loss": 1.6642, "step": 743 }, { "epoch": 0.11, "grad_norm": 0.2042942070651275, "learning_rate": 8.019475765119345e-05, "loss": 1.6598, "step": 744 }, { "epoch": 0.11, "grad_norm": 0.171722618385623, "learning_rate": 8.018157856201494e-05, "loss": 1.6588, "step": 745 }, { "epoch": 0.11, "grad_norm": 0.1858922147873516, "learning_rate": 8.016839947283644e-05, "loss": 1.6644, "step": 746 }, { "epoch": 0.11, "grad_norm": 0.1800446333017018, "learning_rate": 8.015522038365793e-05, "loss": 1.6596, "step": 747 }, { "epoch": 0.11, "grad_norm": 0.1803808001678191, "learning_rate": 8.014204129447943e-05, "loss": 1.672, "step": 748 }, { "epoch": 0.11, "grad_norm": 0.1768537234586101, "learning_rate": 8.012886220530092e-05, "loss": 1.6657, "step": 749 }, { "epoch": 0.11, "grad_norm": 0.19980216971257497, "learning_rate": 8.011568311612243e-05, "loss": 1.6534, "step": 750 }, { "epoch": 0.11, "grad_norm": 0.1832264261976631, "learning_rate": 8.010250402694392e-05, "loss": 1.6591, "step": 751 }, { "epoch": 0.11, "grad_norm": 0.16513639779797532, "learning_rate": 8.008932493776541e-05, "loss": 1.6648, "step": 752 }, { "epoch": 0.11, "grad_norm": 0.17022762074604036, "learning_rate": 8.007614584858692e-05, "loss": 1.6591, "step": 753 }, { "epoch": 0.11, "grad_norm": 0.1681936250352472, "learning_rate": 8.006296675940841e-05, "loss": 1.6571, "step": 754 }, { "epoch": 0.11, "grad_norm": 0.21312758323221945, "learning_rate": 8.004978767022991e-05, "loss": 1.6562, "step": 755 }, { "epoch": 0.11, "grad_norm": 0.2523673118943729, "learning_rate": 8.00366085810514e-05, "loss": 1.6663, "step": 756 }, { "epoch": 0.11, "grad_norm": 0.2623904537775464, "learning_rate": 8.00234294918729e-05, "loss": 1.6674, "step": 757 }, { "epoch": 0.11, "grad_norm": 0.24341343434762125, "learning_rate": 8.001025040269439e-05, "loss": 1.6713, "step": 758 }, { "epoch": 0.11, "grad_norm": 0.217043521795163, "learning_rate": 7.99970713135159e-05, "loss": 1.6706, "step": 759 }, { "epoch": 0.11, "grad_norm": 0.20902151519730236, "learning_rate": 7.998389222433739e-05, "loss": 1.664, "step": 760 }, { "epoch": 0.11, "grad_norm": 0.22505288309338028, "learning_rate": 7.997071313515888e-05, "loss": 1.6588, "step": 761 }, { "epoch": 0.11, "grad_norm": 0.22608418892993373, "learning_rate": 7.995753404598039e-05, "loss": 1.6617, "step": 762 }, { "epoch": 0.11, "grad_norm": 0.2204380979289179, "learning_rate": 7.994435495680187e-05, "loss": 1.6573, "step": 763 }, { "epoch": 0.11, "grad_norm": 0.1969471585321503, "learning_rate": 7.993117586762337e-05, "loss": 1.6601, "step": 764 }, { "epoch": 0.11, "grad_norm": 0.20082564014850096, "learning_rate": 7.991799677844487e-05, "loss": 1.6617, "step": 765 }, { "epoch": 0.11, "grad_norm": 0.20192437570777552, "learning_rate": 7.990481768926637e-05, "loss": 1.6544, "step": 766 }, { "epoch": 0.11, "grad_norm": 0.2574830285462354, "learning_rate": 7.989163860008786e-05, "loss": 1.6533, "step": 767 }, { "epoch": 0.11, "grad_norm": 0.23002776136831127, "learning_rate": 7.987845951090937e-05, "loss": 1.661, "step": 768 }, { "epoch": 0.11, "grad_norm": 0.22713613412496464, "learning_rate": 7.986528042173086e-05, "loss": 1.6663, "step": 769 }, { "epoch": 0.11, "grad_norm": 0.2042318478702029, "learning_rate": 7.985210133255236e-05, "loss": 1.6546, "step": 770 }, { "epoch": 0.11, "grad_norm": 0.20073586989829498, "learning_rate": 7.983892224337385e-05, "loss": 1.6591, "step": 771 }, { "epoch": 0.11, "grad_norm": 0.22156482786667436, "learning_rate": 7.982574315419534e-05, "loss": 1.6559, "step": 772 }, { "epoch": 0.11, "grad_norm": 0.23204275860685752, "learning_rate": 7.981256406501684e-05, "loss": 1.654, "step": 773 }, { "epoch": 0.11, "grad_norm": 0.22578907014380378, "learning_rate": 7.979938497583834e-05, "loss": 1.6598, "step": 774 }, { "epoch": 0.11, "grad_norm": 0.22278741960348777, "learning_rate": 7.978620588665984e-05, "loss": 1.6521, "step": 775 }, { "epoch": 0.11, "grad_norm": 0.21685600767937083, "learning_rate": 7.977302679748133e-05, "loss": 1.6607, "step": 776 }, { "epoch": 0.11, "grad_norm": 0.22266066710897367, "learning_rate": 7.975984770830284e-05, "loss": 1.6487, "step": 777 }, { "epoch": 0.11, "grad_norm": 0.19632860059659135, "learning_rate": 7.974666861912433e-05, "loss": 1.6613, "step": 778 }, { "epoch": 0.11, "grad_norm": 0.18234394704028628, "learning_rate": 7.973348952994583e-05, "loss": 1.6574, "step": 779 }, { "epoch": 0.11, "grad_norm": 0.177598112664479, "learning_rate": 7.972031044076732e-05, "loss": 1.6529, "step": 780 }, { "epoch": 0.11, "grad_norm": 0.19095741463896163, "learning_rate": 7.970713135158881e-05, "loss": 1.654, "step": 781 }, { "epoch": 0.11, "grad_norm": 0.23354657913440505, "learning_rate": 7.969395226241031e-05, "loss": 1.6568, "step": 782 }, { "epoch": 0.11, "grad_norm": 0.23167577068773595, "learning_rate": 7.968077317323181e-05, "loss": 1.6554, "step": 783 }, { "epoch": 0.11, "grad_norm": 0.21367008980339683, "learning_rate": 7.966759408405331e-05, "loss": 1.6495, "step": 784 }, { "epoch": 0.11, "grad_norm": 0.2207178544949823, "learning_rate": 7.96544149948748e-05, "loss": 1.6548, "step": 785 }, { "epoch": 0.12, "grad_norm": 0.21891851522878888, "learning_rate": 7.964123590569631e-05, "loss": 1.657, "step": 786 }, { "epoch": 0.12, "grad_norm": 0.24695814979029723, "learning_rate": 7.962805681651779e-05, "loss": 1.6488, "step": 787 }, { "epoch": 0.12, "grad_norm": 0.287912034486528, "learning_rate": 7.961487772733928e-05, "loss": 1.65, "step": 788 }, { "epoch": 0.12, "grad_norm": 0.3399743120660956, "learning_rate": 7.960169863816079e-05, "loss": 1.6526, "step": 789 }, { "epoch": 0.12, "grad_norm": 0.3616996652020229, "learning_rate": 7.958851954898228e-05, "loss": 1.6602, "step": 790 }, { "epoch": 0.12, "grad_norm": 0.3063137729348896, "learning_rate": 7.957534045980378e-05, "loss": 1.6573, "step": 791 }, { "epoch": 0.12, "grad_norm": 0.24333897069393048, "learning_rate": 7.956216137062529e-05, "loss": 1.6517, "step": 792 }, { "epoch": 0.12, "grad_norm": 0.2536956392375361, "learning_rate": 7.954898228144678e-05, "loss": 1.6548, "step": 793 }, { "epoch": 0.12, "grad_norm": 0.2992558453991358, "learning_rate": 7.953580319226827e-05, "loss": 1.6476, "step": 794 }, { "epoch": 0.12, "grad_norm": 0.2919938016387346, "learning_rate": 7.952262410308977e-05, "loss": 1.658, "step": 795 }, { "epoch": 0.12, "grad_norm": 0.22425446070873226, "learning_rate": 7.950944501391126e-05, "loss": 1.6561, "step": 796 }, { "epoch": 0.12, "grad_norm": 0.17979423947699205, "learning_rate": 7.949626592473275e-05, "loss": 1.6511, "step": 797 }, { "epoch": 0.12, "grad_norm": 0.2003220647484553, "learning_rate": 7.948308683555426e-05, "loss": 1.6584, "step": 798 }, { "epoch": 0.12, "grad_norm": 0.21655839117724143, "learning_rate": 7.946990774637576e-05, "loss": 1.6413, "step": 799 }, { "epoch": 0.12, "grad_norm": 0.19654884015176893, "learning_rate": 7.945672865719725e-05, "loss": 1.6478, "step": 800 }, { "epoch": 0.12, "grad_norm": 0.20643622425199437, "learning_rate": 7.944354956801876e-05, "loss": 1.6487, "step": 801 }, { "epoch": 0.12, "grad_norm": 0.2210426562771846, "learning_rate": 7.943037047884025e-05, "loss": 1.6417, "step": 802 }, { "epoch": 0.12, "grad_norm": 0.2370399462767824, "learning_rate": 7.941719138966174e-05, "loss": 1.6526, "step": 803 }, { "epoch": 0.12, "grad_norm": 0.27064884564726144, "learning_rate": 7.940401230048324e-05, "loss": 1.6452, "step": 804 }, { "epoch": 0.12, "grad_norm": 0.24922057360329597, "learning_rate": 7.939083321130473e-05, "loss": 1.6476, "step": 805 }, { "epoch": 0.12, "grad_norm": 0.22578777752481574, "learning_rate": 7.937765412212622e-05, "loss": 1.6512, "step": 806 }, { "epoch": 0.12, "grad_norm": 0.2450981377837511, "learning_rate": 7.936447503294773e-05, "loss": 1.6447, "step": 807 }, { "epoch": 0.12, "grad_norm": 0.274010641548682, "learning_rate": 7.935129594376923e-05, "loss": 1.6559, "step": 808 }, { "epoch": 0.12, "grad_norm": 0.25880479404705736, "learning_rate": 7.933811685459072e-05, "loss": 1.6489, "step": 809 }, { "epoch": 0.12, "grad_norm": 0.22048806582617783, "learning_rate": 7.932493776541223e-05, "loss": 1.6524, "step": 810 }, { "epoch": 0.12, "grad_norm": 0.1887738283254872, "learning_rate": 7.931175867623371e-05, "loss": 1.64, "step": 811 }, { "epoch": 0.12, "grad_norm": 0.18522517056579318, "learning_rate": 7.92985795870552e-05, "loss": 1.6494, "step": 812 }, { "epoch": 0.12, "grad_norm": 0.22546381379315691, "learning_rate": 7.928540049787671e-05, "loss": 1.6464, "step": 813 }, { "epoch": 0.12, "grad_norm": 0.2506628844421445, "learning_rate": 7.92722214086982e-05, "loss": 1.6542, "step": 814 }, { "epoch": 0.12, "grad_norm": 0.23722684616063827, "learning_rate": 7.92590423195197e-05, "loss": 1.6462, "step": 815 }, { "epoch": 0.12, "grad_norm": 0.21527026226593318, "learning_rate": 7.92458632303412e-05, "loss": 1.6429, "step": 816 }, { "epoch": 0.12, "grad_norm": 0.20417560769017126, "learning_rate": 7.92326841411627e-05, "loss": 1.6463, "step": 817 }, { "epoch": 0.12, "grad_norm": 0.25657787896551143, "learning_rate": 7.921950505198419e-05, "loss": 1.655, "step": 818 }, { "epoch": 0.12, "grad_norm": 0.267753342657363, "learning_rate": 7.920632596280568e-05, "loss": 1.6519, "step": 819 }, { "epoch": 0.12, "grad_norm": 0.24920909128098695, "learning_rate": 7.919314687362718e-05, "loss": 1.6473, "step": 820 }, { "epoch": 0.12, "grad_norm": 0.2478367552587059, "learning_rate": 7.917996778444867e-05, "loss": 1.6426, "step": 821 }, { "epoch": 0.12, "grad_norm": 0.2153066175677768, "learning_rate": 7.916678869527018e-05, "loss": 1.6491, "step": 822 }, { "epoch": 0.12, "grad_norm": 0.2014632227972863, "learning_rate": 7.915360960609167e-05, "loss": 1.6505, "step": 823 }, { "epoch": 0.12, "grad_norm": 0.2444739546695772, "learning_rate": 7.914043051691317e-05, "loss": 1.6481, "step": 824 }, { "epoch": 0.12, "grad_norm": 0.24448366789416284, "learning_rate": 7.912725142773467e-05, "loss": 1.6536, "step": 825 }, { "epoch": 0.12, "grad_norm": 0.18988494902818237, "learning_rate": 7.911407233855617e-05, "loss": 1.6527, "step": 826 }, { "epoch": 0.12, "grad_norm": 0.1596982906421288, "learning_rate": 7.910089324937766e-05, "loss": 1.6434, "step": 827 }, { "epoch": 0.12, "grad_norm": 0.18102812476693692, "learning_rate": 7.908771416019915e-05, "loss": 1.6518, "step": 828 }, { "epoch": 0.12, "grad_norm": 0.2102523140397989, "learning_rate": 7.907453507102065e-05, "loss": 1.6498, "step": 829 }, { "epoch": 0.12, "grad_norm": 0.23412540024706124, "learning_rate": 7.906135598184214e-05, "loss": 1.641, "step": 830 }, { "epoch": 0.12, "grad_norm": 0.24005571074787757, "learning_rate": 7.904817689266365e-05, "loss": 1.6431, "step": 831 }, { "epoch": 0.12, "grad_norm": 0.23238476130237243, "learning_rate": 7.903499780348514e-05, "loss": 1.6413, "step": 832 }, { "epoch": 0.12, "grad_norm": 0.1970713398858913, "learning_rate": 7.902181871430664e-05, "loss": 1.6423, "step": 833 }, { "epoch": 0.12, "grad_norm": 0.2242200272612161, "learning_rate": 7.900863962512814e-05, "loss": 1.6517, "step": 834 }, { "epoch": 0.12, "grad_norm": 0.22807610187834748, "learning_rate": 7.899546053594962e-05, "loss": 1.6406, "step": 835 }, { "epoch": 0.12, "grad_norm": 0.1972521968320005, "learning_rate": 7.898228144677112e-05, "loss": 1.6507, "step": 836 }, { "epoch": 0.12, "grad_norm": 0.23394212314333337, "learning_rate": 7.896910235759263e-05, "loss": 1.6534, "step": 837 }, { "epoch": 0.12, "grad_norm": 0.26703958427818103, "learning_rate": 7.895592326841412e-05, "loss": 1.6324, "step": 838 }, { "epoch": 0.12, "grad_norm": 0.22223709057066937, "learning_rate": 7.894274417923561e-05, "loss": 1.6472, "step": 839 }, { "epoch": 0.12, "grad_norm": 0.18015143412151977, "learning_rate": 7.892956509005712e-05, "loss": 1.6523, "step": 840 }, { "epoch": 0.12, "grad_norm": 0.16776687777891955, "learning_rate": 7.891638600087861e-05, "loss": 1.6408, "step": 841 }, { "epoch": 0.12, "grad_norm": 0.2110093032771735, "learning_rate": 7.890320691170011e-05, "loss": 1.6475, "step": 842 }, { "epoch": 0.12, "grad_norm": 0.21006634515360098, "learning_rate": 7.88900278225216e-05, "loss": 1.6495, "step": 843 }, { "epoch": 0.12, "grad_norm": 0.19405253109457415, "learning_rate": 7.88768487333431e-05, "loss": 1.6373, "step": 844 }, { "epoch": 0.12, "grad_norm": 0.17598128896680296, "learning_rate": 7.886366964416459e-05, "loss": 1.6319, "step": 845 }, { "epoch": 0.12, "grad_norm": 0.1649091128056297, "learning_rate": 7.88504905549861e-05, "loss": 1.6457, "step": 846 }, { "epoch": 0.12, "grad_norm": 0.15971492084809902, "learning_rate": 7.883731146580759e-05, "loss": 1.6352, "step": 847 }, { "epoch": 0.12, "grad_norm": 0.17712277192126102, "learning_rate": 7.882413237662908e-05, "loss": 1.6381, "step": 848 }, { "epoch": 0.12, "grad_norm": 0.20906554492964108, "learning_rate": 7.881095328745059e-05, "loss": 1.6437, "step": 849 }, { "epoch": 0.12, "grad_norm": 0.2142843140002136, "learning_rate": 7.879777419827209e-05, "loss": 1.6434, "step": 850 }, { "epoch": 0.12, "grad_norm": 0.21006215293899588, "learning_rate": 7.878459510909357e-05, "loss": 1.6427, "step": 851 }, { "epoch": 0.12, "grad_norm": 0.23775701204551145, "learning_rate": 7.877141601991507e-05, "loss": 1.6455, "step": 852 }, { "epoch": 0.12, "grad_norm": 0.2707019175159962, "learning_rate": 7.875823693073657e-05, "loss": 1.6456, "step": 853 }, { "epoch": 0.13, "grad_norm": 0.3127403618384618, "learning_rate": 7.874505784155806e-05, "loss": 1.6385, "step": 854 }, { "epoch": 0.13, "grad_norm": 0.36233560236813683, "learning_rate": 7.873187875237957e-05, "loss": 1.6392, "step": 855 }, { "epoch": 0.13, "grad_norm": 0.36917547935418177, "learning_rate": 7.871869966320106e-05, "loss": 1.643, "step": 856 }, { "epoch": 0.13, "grad_norm": 0.2799689100614571, "learning_rate": 7.870552057402255e-05, "loss": 1.6364, "step": 857 }, { "epoch": 0.13, "grad_norm": 0.1909288497464617, "learning_rate": 7.869234148484406e-05, "loss": 1.6442, "step": 858 }, { "epoch": 0.13, "grad_norm": 0.22049646685021101, "learning_rate": 7.867916239566554e-05, "loss": 1.6381, "step": 859 }, { "epoch": 0.13, "grad_norm": 0.2792850134812065, "learning_rate": 7.866598330648704e-05, "loss": 1.6439, "step": 860 }, { "epoch": 0.13, "grad_norm": 0.2767586748336834, "learning_rate": 7.865280421730854e-05, "loss": 1.6406, "step": 861 }, { "epoch": 0.13, "grad_norm": 0.1964234052122111, "learning_rate": 7.863962512813004e-05, "loss": 1.6403, "step": 862 }, { "epoch": 0.13, "grad_norm": 0.21916883082393832, "learning_rate": 7.862644603895153e-05, "loss": 1.6433, "step": 863 }, { "epoch": 0.13, "grad_norm": 0.2664436290112629, "learning_rate": 7.861326694977304e-05, "loss": 1.6422, "step": 864 }, { "epoch": 0.13, "grad_norm": 0.21301889349155526, "learning_rate": 7.860008786059453e-05, "loss": 1.6416, "step": 865 }, { "epoch": 0.13, "grad_norm": 0.17884914022978088, "learning_rate": 7.858690877141603e-05, "loss": 1.6312, "step": 866 }, { "epoch": 0.13, "grad_norm": 0.18843102073542442, "learning_rate": 7.857372968223752e-05, "loss": 1.6416, "step": 867 }, { "epoch": 0.13, "grad_norm": 0.18688924194495246, "learning_rate": 7.856055059305901e-05, "loss": 1.6441, "step": 868 }, { "epoch": 0.13, "grad_norm": 0.1650145694966954, "learning_rate": 7.854737150388051e-05, "loss": 1.6454, "step": 869 }, { "epoch": 0.13, "grad_norm": 0.1582803846188149, "learning_rate": 7.853419241470201e-05, "loss": 1.6359, "step": 870 }, { "epoch": 0.13, "grad_norm": 0.1914936260863352, "learning_rate": 7.852101332552351e-05, "loss": 1.6346, "step": 871 }, { "epoch": 0.13, "grad_norm": 0.2272665695903623, "learning_rate": 7.8507834236345e-05, "loss": 1.6424, "step": 872 }, { "epoch": 0.13, "grad_norm": 0.2918408917481599, "learning_rate": 7.849465514716651e-05, "loss": 1.6362, "step": 873 }, { "epoch": 0.13, "grad_norm": 0.33124958511818076, "learning_rate": 7.8481476057988e-05, "loss": 1.6457, "step": 874 }, { "epoch": 0.13, "grad_norm": 0.28392389646236854, "learning_rate": 7.846829696880948e-05, "loss": 1.636, "step": 875 }, { "epoch": 0.13, "grad_norm": 0.21187264881262416, "learning_rate": 7.845511787963099e-05, "loss": 1.6391, "step": 876 }, { "epoch": 0.13, "grad_norm": 0.19512382269665135, "learning_rate": 7.844193879045248e-05, "loss": 1.6375, "step": 877 }, { "epoch": 0.13, "grad_norm": 0.2315133095228095, "learning_rate": 7.842875970127398e-05, "loss": 1.6434, "step": 878 }, { "epoch": 0.13, "grad_norm": 0.22455542676851648, "learning_rate": 7.841558061209548e-05, "loss": 1.6375, "step": 879 }, { "epoch": 0.13, "grad_norm": 0.18274445518703517, "learning_rate": 7.840240152291698e-05, "loss": 1.6403, "step": 880 }, { "epoch": 0.13, "grad_norm": 0.1680652375376494, "learning_rate": 7.838922243373847e-05, "loss": 1.6253, "step": 881 }, { "epoch": 0.13, "grad_norm": 0.2029462350044378, "learning_rate": 7.837604334455998e-05, "loss": 1.6335, "step": 882 }, { "epoch": 0.13, "grad_norm": 0.2385785209220654, "learning_rate": 7.836286425538146e-05, "loss": 1.636, "step": 883 }, { "epoch": 0.13, "grad_norm": 0.22966225461134943, "learning_rate": 7.834968516620295e-05, "loss": 1.6351, "step": 884 }, { "epoch": 0.13, "grad_norm": 0.20620730487272254, "learning_rate": 7.833650607702446e-05, "loss": 1.64, "step": 885 }, { "epoch": 0.13, "grad_norm": 0.20815921246674304, "learning_rate": 7.832332698784595e-05, "loss": 1.642, "step": 886 }, { "epoch": 0.13, "grad_norm": 0.21329180245890958, "learning_rate": 7.831014789866745e-05, "loss": 1.6289, "step": 887 }, { "epoch": 0.13, "grad_norm": 0.20448951459967843, "learning_rate": 7.829696880948896e-05, "loss": 1.6327, "step": 888 }, { "epoch": 0.13, "grad_norm": 0.19419304903131157, "learning_rate": 7.828378972031045e-05, "loss": 1.6322, "step": 889 }, { "epoch": 0.13, "grad_norm": 0.18030150429004935, "learning_rate": 7.827061063113194e-05, "loss": 1.6331, "step": 890 }, { "epoch": 0.13, "grad_norm": 0.1898733739259939, "learning_rate": 7.825743154195344e-05, "loss": 1.6342, "step": 891 }, { "epoch": 0.13, "grad_norm": 0.21064065788890746, "learning_rate": 7.824425245277493e-05, "loss": 1.6407, "step": 892 }, { "epoch": 0.13, "grad_norm": 0.20679616302698337, "learning_rate": 7.823107336359642e-05, "loss": 1.6328, "step": 893 }, { "epoch": 0.13, "grad_norm": 0.21400981491846863, "learning_rate": 7.821789427441793e-05, "loss": 1.6426, "step": 894 }, { "epoch": 0.13, "grad_norm": 0.20061186083901789, "learning_rate": 7.820471518523943e-05, "loss": 1.6359, "step": 895 }, { "epoch": 0.13, "grad_norm": 0.18863815744505064, "learning_rate": 7.819153609606092e-05, "loss": 1.6307, "step": 896 }, { "epoch": 0.13, "grad_norm": 0.19996719699171972, "learning_rate": 7.817835700688243e-05, "loss": 1.6299, "step": 897 }, { "epoch": 0.13, "grad_norm": 0.2074855070501711, "learning_rate": 7.816517791770392e-05, "loss": 1.6431, "step": 898 }, { "epoch": 0.13, "grad_norm": 0.18908061531345277, "learning_rate": 7.81519988285254e-05, "loss": 1.6359, "step": 899 }, { "epoch": 0.13, "grad_norm": 0.1621341838335611, "learning_rate": 7.813881973934691e-05, "loss": 1.6334, "step": 900 }, { "epoch": 0.13, "eval_loss": 1.5936576128005981, "eval_runtime": 447.3124, "eval_samples_per_second": 40.274, "eval_steps_per_second": 0.06, "step": 900 }, { "epoch": 0.13, "grad_norm": 0.15865732799100835, "learning_rate": 7.81256406501684e-05, "loss": 1.6265, "step": 901 }, { "epoch": 0.13, "grad_norm": 0.16466989815596636, "learning_rate": 7.81124615609899e-05, "loss": 1.636, "step": 902 }, { "epoch": 0.13, "grad_norm": 0.18355978585759908, "learning_rate": 7.80992824718114e-05, "loss": 1.6412, "step": 903 }, { "epoch": 0.13, "grad_norm": 0.16881096243427599, "learning_rate": 7.80861033826329e-05, "loss": 1.6218, "step": 904 }, { "epoch": 0.13, "grad_norm": 0.17792146649092913, "learning_rate": 7.807292429345439e-05, "loss": 1.6351, "step": 905 }, { "epoch": 0.13, "grad_norm": 0.1861296128116092, "learning_rate": 7.80597452042759e-05, "loss": 1.6314, "step": 906 }, { "epoch": 0.13, "grad_norm": 0.19805706857044636, "learning_rate": 7.804656611509738e-05, "loss": 1.6274, "step": 907 }, { "epoch": 0.13, "grad_norm": 0.2477603308349337, "learning_rate": 7.803338702591887e-05, "loss": 1.6345, "step": 908 }, { "epoch": 0.13, "grad_norm": 0.3058009391702576, "learning_rate": 7.802020793674038e-05, "loss": 1.6349, "step": 909 }, { "epoch": 0.13, "grad_norm": 0.3285989768622068, "learning_rate": 7.800702884756187e-05, "loss": 1.6354, "step": 910 }, { "epoch": 0.13, "grad_norm": 0.29327673429046075, "learning_rate": 7.799384975838337e-05, "loss": 1.636, "step": 911 }, { "epoch": 0.13, "grad_norm": 0.23773885823846896, "learning_rate": 7.798067066920487e-05, "loss": 1.6264, "step": 912 }, { "epoch": 0.13, "grad_norm": 0.19226268966581236, "learning_rate": 7.796749158002637e-05, "loss": 1.635, "step": 913 }, { "epoch": 0.13, "grad_norm": 0.20182491167455907, "learning_rate": 7.795431249084786e-05, "loss": 1.638, "step": 914 }, { "epoch": 0.13, "grad_norm": 0.23238881306153533, "learning_rate": 7.794113340166935e-05, "loss": 1.6316, "step": 915 }, { "epoch": 0.13, "grad_norm": 0.23986180803329027, "learning_rate": 7.792795431249085e-05, "loss": 1.6258, "step": 916 }, { "epoch": 0.13, "grad_norm": 0.1961225124547818, "learning_rate": 7.791477522331234e-05, "loss": 1.6326, "step": 917 }, { "epoch": 0.13, "grad_norm": 0.16968519491312442, "learning_rate": 7.790159613413385e-05, "loss": 1.6357, "step": 918 }, { "epoch": 0.13, "grad_norm": 0.17723689039254287, "learning_rate": 7.788841704495534e-05, "loss": 1.6321, "step": 919 }, { "epoch": 0.13, "grad_norm": 0.19952319110339864, "learning_rate": 7.787523795577684e-05, "loss": 1.6294, "step": 920 }, { "epoch": 0.13, "grad_norm": 0.20482205553447078, "learning_rate": 7.786205886659834e-05, "loss": 1.6304, "step": 921 }, { "epoch": 0.13, "grad_norm": 0.19973731737429154, "learning_rate": 7.784887977741984e-05, "loss": 1.6305, "step": 922 }, { "epoch": 0.14, "grad_norm": 0.19968852921711655, "learning_rate": 7.783570068824132e-05, "loss": 1.6216, "step": 923 }, { "epoch": 0.14, "grad_norm": 0.2432499755542469, "learning_rate": 7.782252159906283e-05, "loss": 1.6183, "step": 924 }, { "epoch": 0.14, "grad_norm": 0.28904807766758667, "learning_rate": 7.780934250988432e-05, "loss": 1.6331, "step": 925 }, { "epoch": 0.14, "grad_norm": 0.30605720879153786, "learning_rate": 7.779616342070581e-05, "loss": 1.6429, "step": 926 }, { "epoch": 0.14, "grad_norm": 0.28776303552521276, "learning_rate": 7.778298433152732e-05, "loss": 1.6376, "step": 927 }, { "epoch": 0.14, "grad_norm": 0.26692576512866534, "learning_rate": 7.776980524234881e-05, "loss": 1.636, "step": 928 }, { "epoch": 0.14, "grad_norm": 0.23006966654469613, "learning_rate": 7.775662615317031e-05, "loss": 1.6375, "step": 929 }, { "epoch": 0.14, "grad_norm": 0.18021078514991914, "learning_rate": 7.774344706399181e-05, "loss": 1.6231, "step": 930 }, { "epoch": 0.14, "grad_norm": 0.18063501767218804, "learning_rate": 7.77302679748133e-05, "loss": 1.6316, "step": 931 }, { "epoch": 0.14, "grad_norm": 0.2146429092144611, "learning_rate": 7.771708888563479e-05, "loss": 1.6279, "step": 932 }, { "epoch": 0.14, "grad_norm": 0.20818499945204852, "learning_rate": 7.77039097964563e-05, "loss": 1.6269, "step": 933 }, { "epoch": 0.14, "grad_norm": 0.18354993630667119, "learning_rate": 7.769073070727779e-05, "loss": 1.6227, "step": 934 }, { "epoch": 0.14, "grad_norm": 0.18200851976694746, "learning_rate": 7.767755161809928e-05, "loss": 1.6351, "step": 935 }, { "epoch": 0.14, "grad_norm": 0.1865682691641124, "learning_rate": 7.766437252892079e-05, "loss": 1.6275, "step": 936 }, { "epoch": 0.14, "grad_norm": 0.1802592148443168, "learning_rate": 7.765119343974228e-05, "loss": 1.6275, "step": 937 }, { "epoch": 0.14, "grad_norm": 0.17289003336299882, "learning_rate": 7.763801435056378e-05, "loss": 1.6341, "step": 938 }, { "epoch": 0.14, "grad_norm": 0.1986135066316666, "learning_rate": 7.762483526138527e-05, "loss": 1.6196, "step": 939 }, { "epoch": 0.14, "grad_norm": 0.18010570303182816, "learning_rate": 7.761165617220677e-05, "loss": 1.624, "step": 940 }, { "epoch": 0.14, "grad_norm": 0.1673925458817595, "learning_rate": 7.759847708302826e-05, "loss": 1.6334, "step": 941 }, { "epoch": 0.14, "grad_norm": 0.17837996599687475, "learning_rate": 7.758529799384977e-05, "loss": 1.6344, "step": 942 }, { "epoch": 0.14, "grad_norm": 0.167225580195058, "learning_rate": 7.757211890467126e-05, "loss": 1.6311, "step": 943 }, { "epoch": 0.14, "grad_norm": 0.16484688881261245, "learning_rate": 7.755893981549275e-05, "loss": 1.633, "step": 944 }, { "epoch": 0.14, "grad_norm": 0.16970087441567513, "learning_rate": 7.754576072631426e-05, "loss": 1.6277, "step": 945 }, { "epoch": 0.14, "grad_norm": 0.17706071153067815, "learning_rate": 7.753258163713576e-05, "loss": 1.6276, "step": 946 }, { "epoch": 0.14, "grad_norm": 0.19185774572084416, "learning_rate": 7.751940254795724e-05, "loss": 1.6282, "step": 947 }, { "epoch": 0.14, "grad_norm": 0.21534610743277194, "learning_rate": 7.750622345877874e-05, "loss": 1.628, "step": 948 }, { "epoch": 0.14, "grad_norm": 0.22682207930909348, "learning_rate": 7.749304436960024e-05, "loss": 1.6351, "step": 949 }, { "epoch": 0.14, "grad_norm": 0.20425437523432943, "learning_rate": 7.747986528042173e-05, "loss": 1.6226, "step": 950 }, { "epoch": 0.14, "grad_norm": 0.1815592545929023, "learning_rate": 7.746668619124324e-05, "loss": 1.6294, "step": 951 }, { "epoch": 0.14, "grad_norm": 0.1914304657655877, "learning_rate": 7.745350710206473e-05, "loss": 1.624, "step": 952 }, { "epoch": 0.14, "grad_norm": 0.19841817505160111, "learning_rate": 7.744032801288623e-05, "loss": 1.626, "step": 953 }, { "epoch": 0.14, "grad_norm": 0.20513655191404673, "learning_rate": 7.742714892370773e-05, "loss": 1.625, "step": 954 }, { "epoch": 0.14, "grad_norm": 0.20690976922591042, "learning_rate": 7.741396983452921e-05, "loss": 1.6269, "step": 955 }, { "epoch": 0.14, "grad_norm": 0.20042970552356906, "learning_rate": 7.74007907453507e-05, "loss": 1.6227, "step": 956 }, { "epoch": 0.14, "grad_norm": 0.22313249765436127, "learning_rate": 7.738761165617221e-05, "loss": 1.6307, "step": 957 }, { "epoch": 0.14, "grad_norm": 0.24940862321038032, "learning_rate": 7.737443256699371e-05, "loss": 1.6262, "step": 958 }, { "epoch": 0.14, "grad_norm": 0.2733600251891239, "learning_rate": 7.73612534778152e-05, "loss": 1.6234, "step": 959 }, { "epoch": 0.14, "grad_norm": 0.27327679593574355, "learning_rate": 7.734807438863671e-05, "loss": 1.6204, "step": 960 }, { "epoch": 0.14, "grad_norm": 0.2528084631262215, "learning_rate": 7.73348952994582e-05, "loss": 1.6235, "step": 961 }, { "epoch": 0.14, "grad_norm": 0.21747127891255372, "learning_rate": 7.73217162102797e-05, "loss": 1.625, "step": 962 }, { "epoch": 0.14, "grad_norm": 0.1910347418430321, "learning_rate": 7.730853712110119e-05, "loss": 1.6167, "step": 963 }, { "epoch": 0.14, "grad_norm": 0.17541573212547087, "learning_rate": 7.729535803192268e-05, "loss": 1.627, "step": 964 }, { "epoch": 0.14, "grad_norm": 0.20823218712713615, "learning_rate": 7.728217894274418e-05, "loss": 1.6303, "step": 965 }, { "epoch": 0.14, "grad_norm": 0.20802148470127552, "learning_rate": 7.726899985356568e-05, "loss": 1.6278, "step": 966 }, { "epoch": 0.14, "grad_norm": 0.17924417756170902, "learning_rate": 7.725582076438718e-05, "loss": 1.6321, "step": 967 }, { "epoch": 0.14, "grad_norm": 0.16948531308406123, "learning_rate": 7.724264167520867e-05, "loss": 1.6243, "step": 968 }, { "epoch": 0.14, "grad_norm": 0.167050690087119, "learning_rate": 7.722946258603018e-05, "loss": 1.627, "step": 969 }, { "epoch": 0.14, "grad_norm": 0.1707462068741091, "learning_rate": 7.721628349685167e-05, "loss": 1.6105, "step": 970 }, { "epoch": 0.14, "grad_norm": 0.18254429275405454, "learning_rate": 7.720310440767315e-05, "loss": 1.6269, "step": 971 }, { "epoch": 0.14, "grad_norm": 0.1915398246036987, "learning_rate": 7.718992531849466e-05, "loss": 1.6143, "step": 972 }, { "epoch": 0.14, "grad_norm": 0.22066508050668615, "learning_rate": 7.717674622931615e-05, "loss": 1.6255, "step": 973 }, { "epoch": 0.14, "grad_norm": 0.21683723311113615, "learning_rate": 7.716356714013765e-05, "loss": 1.6297, "step": 974 }, { "epoch": 0.14, "grad_norm": 0.19079856723315286, "learning_rate": 7.715038805095916e-05, "loss": 1.626, "step": 975 }, { "epoch": 0.14, "grad_norm": 0.20257609739912277, "learning_rate": 7.713720896178065e-05, "loss": 1.6123, "step": 976 }, { "epoch": 0.14, "grad_norm": 0.19318811031897568, "learning_rate": 7.712402987260214e-05, "loss": 1.6269, "step": 977 }, { "epoch": 0.14, "grad_norm": 0.20006255429024558, "learning_rate": 7.711085078342365e-05, "loss": 1.6206, "step": 978 }, { "epoch": 0.14, "grad_norm": 0.20243419836299764, "learning_rate": 7.709767169424513e-05, "loss": 1.6224, "step": 979 }, { "epoch": 0.14, "grad_norm": 0.21154717766882877, "learning_rate": 7.708449260506662e-05, "loss": 1.6296, "step": 980 }, { "epoch": 0.14, "grad_norm": 0.2111145585800829, "learning_rate": 7.707131351588813e-05, "loss": 1.6246, "step": 981 }, { "epoch": 0.14, "grad_norm": 0.20904551886984418, "learning_rate": 7.705813442670962e-05, "loss": 1.6242, "step": 982 }, { "epoch": 0.14, "grad_norm": 0.2155821099387234, "learning_rate": 7.704495533753112e-05, "loss": 1.6157, "step": 983 }, { "epoch": 0.14, "grad_norm": 0.24171139714485312, "learning_rate": 7.703177624835263e-05, "loss": 1.6194, "step": 984 }, { "epoch": 0.14, "grad_norm": 0.24021769786284733, "learning_rate": 7.701859715917412e-05, "loss": 1.6179, "step": 985 }, { "epoch": 0.14, "grad_norm": 0.22097810478380417, "learning_rate": 7.700541806999561e-05, "loss": 1.6138, "step": 986 }, { "epoch": 0.14, "grad_norm": 0.20419669337349122, "learning_rate": 7.699223898081711e-05, "loss": 1.617, "step": 987 }, { "epoch": 0.14, "grad_norm": 0.18295944585814536, "learning_rate": 7.69790598916386e-05, "loss": 1.6192, "step": 988 }, { "epoch": 0.14, "grad_norm": 0.2017143911669201, "learning_rate": 7.69658808024601e-05, "loss": 1.6183, "step": 989 }, { "epoch": 0.14, "grad_norm": 0.2550706626997802, "learning_rate": 7.69527017132816e-05, "loss": 1.622, "step": 990 }, { "epoch": 0.15, "grad_norm": 0.2616391313909151, "learning_rate": 7.69395226241031e-05, "loss": 1.6148, "step": 991 }, { "epoch": 0.15, "grad_norm": 0.22476181941965861, "learning_rate": 7.692634353492459e-05, "loss": 1.6303, "step": 992 }, { "epoch": 0.15, "grad_norm": 0.16958496517690427, "learning_rate": 7.69131644457461e-05, "loss": 1.6289, "step": 993 }, { "epoch": 0.15, "grad_norm": 0.16535160221593995, "learning_rate": 7.689998535656759e-05, "loss": 1.6205, "step": 994 }, { "epoch": 0.15, "grad_norm": 0.19695198203233968, "learning_rate": 7.688680626738907e-05, "loss": 1.6244, "step": 995 }, { "epoch": 0.15, "grad_norm": 0.18773614722297197, "learning_rate": 7.687362717821058e-05, "loss": 1.6206, "step": 996 }, { "epoch": 0.15, "grad_norm": 0.16768417110529632, "learning_rate": 7.686044808903207e-05, "loss": 1.6164, "step": 997 }, { "epoch": 0.15, "grad_norm": 0.15543589531360824, "learning_rate": 7.684726899985357e-05, "loss": 1.6168, "step": 998 }, { "epoch": 0.15, "grad_norm": 0.15781452108271793, "learning_rate": 7.683408991067507e-05, "loss": 1.6169, "step": 999 }, { "epoch": 0.15, "grad_norm": 0.19721598910764596, "learning_rate": 7.682091082149657e-05, "loss": 1.6159, "step": 1000 }, { "epoch": 0.15, "grad_norm": 0.20319788131936403, "learning_rate": 7.680773173231806e-05, "loss": 1.6198, "step": 1001 }, { "epoch": 0.15, "grad_norm": 0.16718938876894052, "learning_rate": 7.679455264313957e-05, "loss": 1.6151, "step": 1002 }, { "epoch": 0.15, "grad_norm": 0.1287659352551544, "learning_rate": 7.678137355396105e-05, "loss": 1.6171, "step": 1003 }, { "epoch": 0.15, "grad_norm": 0.15368443936088208, "learning_rate": 7.676819446478254e-05, "loss": 1.6217, "step": 1004 }, { "epoch": 0.15, "grad_norm": 0.2007291365676937, "learning_rate": 7.675501537560405e-05, "loss": 1.6168, "step": 1005 }, { "epoch": 0.15, "grad_norm": 0.18906054405701359, "learning_rate": 7.674183628642554e-05, "loss": 1.621, "step": 1006 }, { "epoch": 0.15, "grad_norm": 0.1468837292776729, "learning_rate": 7.672865719724704e-05, "loss": 1.6129, "step": 1007 }, { "epoch": 0.15, "grad_norm": 0.13377111078446055, "learning_rate": 7.671547810806854e-05, "loss": 1.6155, "step": 1008 }, { "epoch": 0.15, "grad_norm": 0.1426223536761099, "learning_rate": 7.670229901889004e-05, "loss": 1.6115, "step": 1009 }, { "epoch": 0.15, "grad_norm": 0.17114665015966507, "learning_rate": 7.668911992971153e-05, "loss": 1.6281, "step": 1010 }, { "epoch": 0.15, "grad_norm": 0.1807116919105783, "learning_rate": 7.667594084053302e-05, "loss": 1.6159, "step": 1011 }, { "epoch": 0.15, "grad_norm": 0.17057827920089186, "learning_rate": 7.666276175135452e-05, "loss": 1.6246, "step": 1012 }, { "epoch": 0.15, "grad_norm": 0.18704211275868782, "learning_rate": 7.664958266217601e-05, "loss": 1.6119, "step": 1013 }, { "epoch": 0.15, "grad_norm": 0.2011380246874562, "learning_rate": 7.663640357299752e-05, "loss": 1.615, "step": 1014 }, { "epoch": 0.15, "grad_norm": 0.22834646726527497, "learning_rate": 7.662322448381901e-05, "loss": 1.6118, "step": 1015 }, { "epoch": 0.15, "grad_norm": 0.24388254809300247, "learning_rate": 7.661004539464051e-05, "loss": 1.6147, "step": 1016 }, { "epoch": 0.15, "grad_norm": 0.23555275478651708, "learning_rate": 7.659686630546201e-05, "loss": 1.6082, "step": 1017 }, { "epoch": 0.15, "grad_norm": 0.2273124399174075, "learning_rate": 7.658368721628351e-05, "loss": 1.6178, "step": 1018 }, { "epoch": 0.15, "grad_norm": 0.19649796595180624, "learning_rate": 7.657050812710499e-05, "loss": 1.6146, "step": 1019 }, { "epoch": 0.15, "grad_norm": 0.20344279211487082, "learning_rate": 7.65573290379265e-05, "loss": 1.6095, "step": 1020 }, { "epoch": 0.15, "grad_norm": 0.2203695405176659, "learning_rate": 7.654414994874799e-05, "loss": 1.6153, "step": 1021 }, { "epoch": 0.15, "grad_norm": 0.20941131575413013, "learning_rate": 7.653097085956948e-05, "loss": 1.6088, "step": 1022 }, { "epoch": 0.15, "grad_norm": 0.17696528858927837, "learning_rate": 7.651779177039099e-05, "loss": 1.6186, "step": 1023 }, { "epoch": 0.15, "grad_norm": 0.17541204603143867, "learning_rate": 7.650461268121248e-05, "loss": 1.6109, "step": 1024 }, { "epoch": 0.15, "grad_norm": 0.19137693781810725, "learning_rate": 7.649143359203398e-05, "loss": 1.6103, "step": 1025 }, { "epoch": 0.15, "grad_norm": 0.2104394048421515, "learning_rate": 7.647825450285549e-05, "loss": 1.6104, "step": 1026 }, { "epoch": 0.15, "grad_norm": 0.23866573734409802, "learning_rate": 7.646507541367697e-05, "loss": 1.6158, "step": 1027 }, { "epoch": 0.15, "grad_norm": 0.2711289371560318, "learning_rate": 7.645189632449846e-05, "loss": 1.6097, "step": 1028 }, { "epoch": 0.15, "grad_norm": 0.2903926058136879, "learning_rate": 7.643871723531997e-05, "loss": 1.6146, "step": 1029 }, { "epoch": 0.15, "grad_norm": 0.2578361261344392, "learning_rate": 7.642553814614146e-05, "loss": 1.6119, "step": 1030 }, { "epoch": 0.15, "grad_norm": 0.206355859168418, "learning_rate": 7.641235905696295e-05, "loss": 1.617, "step": 1031 }, { "epoch": 0.15, "grad_norm": 0.18121724499536424, "learning_rate": 7.639917996778446e-05, "loss": 1.617, "step": 1032 }, { "epoch": 0.15, "grad_norm": 0.1681573451991133, "learning_rate": 7.638600087860595e-05, "loss": 1.619, "step": 1033 }, { "epoch": 0.15, "grad_norm": 0.1868021605182587, "learning_rate": 7.637282178942745e-05, "loss": 1.6267, "step": 1034 }, { "epoch": 0.15, "grad_norm": 0.20048387395095732, "learning_rate": 7.635964270024894e-05, "loss": 1.6093, "step": 1035 }, { "epoch": 0.15, "grad_norm": 0.1902918229490612, "learning_rate": 7.634646361107044e-05, "loss": 1.6177, "step": 1036 }, { "epoch": 0.15, "grad_norm": 0.1995438979121453, "learning_rate": 7.633328452189193e-05, "loss": 1.6104, "step": 1037 }, { "epoch": 0.15, "grad_norm": 0.18509718339047015, "learning_rate": 7.632010543271344e-05, "loss": 1.6085, "step": 1038 }, { "epoch": 0.15, "grad_norm": 0.16406358483238698, "learning_rate": 7.630692634353493e-05, "loss": 1.6065, "step": 1039 }, { "epoch": 0.15, "grad_norm": 0.1686539810400193, "learning_rate": 7.629374725435642e-05, "loss": 1.6075, "step": 1040 }, { "epoch": 0.15, "grad_norm": 0.1616937354360527, "learning_rate": 7.628056816517793e-05, "loss": 1.6138, "step": 1041 }, { "epoch": 0.15, "grad_norm": 0.15587744447247096, "learning_rate": 7.626738907599943e-05, "loss": 1.6141, "step": 1042 }, { "epoch": 0.15, "grad_norm": 0.17054924211340525, "learning_rate": 7.62542099868209e-05, "loss": 1.6144, "step": 1043 }, { "epoch": 0.15, "grad_norm": 0.17357874700438133, "learning_rate": 7.624103089764241e-05, "loss": 1.6077, "step": 1044 }, { "epoch": 0.15, "grad_norm": 0.1884137124401568, "learning_rate": 7.622785180846391e-05, "loss": 1.6214, "step": 1045 }, { "epoch": 0.15, "grad_norm": 0.20954300727869857, "learning_rate": 7.62146727192854e-05, "loss": 1.6113, "step": 1046 }, { "epoch": 0.15, "grad_norm": 0.24486234826133343, "learning_rate": 7.620149363010691e-05, "loss": 1.6105, "step": 1047 }, { "epoch": 0.15, "grad_norm": 0.2829288363932686, "learning_rate": 7.61883145409284e-05, "loss": 1.6063, "step": 1048 }, { "epoch": 0.15, "grad_norm": 0.26289957468995534, "learning_rate": 7.61751354517499e-05, "loss": 1.6159, "step": 1049 }, { "epoch": 0.15, "grad_norm": 0.2063007086026833, "learning_rate": 7.61619563625714e-05, "loss": 1.6203, "step": 1050 }, { "epoch": 0.15, "grad_norm": 0.17189607819088035, "learning_rate": 7.614877727339288e-05, "loss": 1.6, "step": 1051 }, { "epoch": 0.15, "grad_norm": 0.1562689270878245, "learning_rate": 7.613559818421438e-05, "loss": 1.6137, "step": 1052 }, { "epoch": 0.15, "grad_norm": 0.18708728589568419, "learning_rate": 7.612241909503588e-05, "loss": 1.6039, "step": 1053 }, { "epoch": 0.15, "grad_norm": 0.19790043445558433, "learning_rate": 7.610924000585738e-05, "loss": 1.6106, "step": 1054 }, { "epoch": 0.15, "grad_norm": 0.17858565211710867, "learning_rate": 7.609606091667887e-05, "loss": 1.6109, "step": 1055 }, { "epoch": 0.15, "grad_norm": 0.16704932302988487, "learning_rate": 7.608288182750038e-05, "loss": 1.6118, "step": 1056 }, { "epoch": 0.15, "grad_norm": 0.17947082466270875, "learning_rate": 7.606970273832187e-05, "loss": 1.609, "step": 1057 }, { "epoch": 0.15, "grad_norm": 0.176708713327256, "learning_rate": 7.605652364914337e-05, "loss": 1.6191, "step": 1058 }, { "epoch": 0.16, "grad_norm": 0.1622950277483614, "learning_rate": 7.604334455996486e-05, "loss": 1.6116, "step": 1059 }, { "epoch": 0.16, "grad_norm": 0.14488222389166788, "learning_rate": 7.603016547078635e-05, "loss": 1.6051, "step": 1060 }, { "epoch": 0.16, "grad_norm": 0.14531527208325867, "learning_rate": 7.601698638160785e-05, "loss": 1.606, "step": 1061 }, { "epoch": 0.16, "grad_norm": 0.17752790968480894, "learning_rate": 7.600380729242935e-05, "loss": 1.6076, "step": 1062 }, { "epoch": 0.16, "grad_norm": 0.1957495026607104, "learning_rate": 7.599062820325085e-05, "loss": 1.6136, "step": 1063 }, { "epoch": 0.16, "grad_norm": 0.2202660125439618, "learning_rate": 7.597744911407234e-05, "loss": 1.6114, "step": 1064 }, { "epoch": 0.16, "grad_norm": 0.21781433216601626, "learning_rate": 7.596427002489385e-05, "loss": 1.6052, "step": 1065 }, { "epoch": 0.16, "grad_norm": 0.19946411918365636, "learning_rate": 7.595109093571534e-05, "loss": 1.6138, "step": 1066 }, { "epoch": 0.16, "grad_norm": 0.17221638475638887, "learning_rate": 7.593791184653682e-05, "loss": 1.6129, "step": 1067 }, { "epoch": 0.16, "grad_norm": 0.1531692080815194, "learning_rate": 7.592473275735833e-05, "loss": 1.6028, "step": 1068 }, { "epoch": 0.16, "grad_norm": 0.16538560411066186, "learning_rate": 7.591155366817982e-05, "loss": 1.6106, "step": 1069 }, { "epoch": 0.16, "grad_norm": 0.18631496746925127, "learning_rate": 7.589837457900132e-05, "loss": 1.5899, "step": 1070 }, { "epoch": 0.16, "grad_norm": 0.18424485959963482, "learning_rate": 7.588519548982283e-05, "loss": 1.6202, "step": 1071 }, { "epoch": 0.16, "grad_norm": 0.15671571674110887, "learning_rate": 7.587201640064432e-05, "loss": 1.6021, "step": 1072 }, { "epoch": 0.16, "grad_norm": 0.18127997297391865, "learning_rate": 7.585883731146581e-05, "loss": 1.6159, "step": 1073 }, { "epoch": 0.16, "grad_norm": 0.2259241643675569, "learning_rate": 7.584565822228732e-05, "loss": 1.6092, "step": 1074 }, { "epoch": 0.16, "grad_norm": 0.23587302884105796, "learning_rate": 7.58324791331088e-05, "loss": 1.6074, "step": 1075 }, { "epoch": 0.16, "grad_norm": 0.22149002998233225, "learning_rate": 7.58193000439303e-05, "loss": 1.6002, "step": 1076 }, { "epoch": 0.16, "grad_norm": 0.20000549277457733, "learning_rate": 7.58061209547518e-05, "loss": 1.6021, "step": 1077 }, { "epoch": 0.16, "grad_norm": 0.1867293286337856, "learning_rate": 7.57929418655733e-05, "loss": 1.6157, "step": 1078 }, { "epoch": 0.16, "grad_norm": 0.20901234864931093, "learning_rate": 7.577976277639479e-05, "loss": 1.6106, "step": 1079 }, { "epoch": 0.16, "grad_norm": 0.2329710725596326, "learning_rate": 7.57665836872163e-05, "loss": 1.5965, "step": 1080 }, { "epoch": 0.16, "grad_norm": 0.23558076759578483, "learning_rate": 7.575340459803779e-05, "loss": 1.6088, "step": 1081 }, { "epoch": 0.16, "grad_norm": 0.20255246934932447, "learning_rate": 7.574022550885928e-05, "loss": 1.6118, "step": 1082 }, { "epoch": 0.16, "grad_norm": 0.17105047596886078, "learning_rate": 7.572704641968078e-05, "loss": 1.6031, "step": 1083 }, { "epoch": 0.16, "grad_norm": 0.151575851349542, "learning_rate": 7.571386733050227e-05, "loss": 1.5992, "step": 1084 }, { "epoch": 0.16, "grad_norm": 0.14457999254055678, "learning_rate": 7.570068824132376e-05, "loss": 1.6028, "step": 1085 }, { "epoch": 0.16, "grad_norm": 0.17929756036682534, "learning_rate": 7.568750915214527e-05, "loss": 1.6093, "step": 1086 }, { "epoch": 0.16, "grad_norm": 0.22006099380977615, "learning_rate": 7.567433006296677e-05, "loss": 1.614, "step": 1087 }, { "epoch": 0.16, "grad_norm": 0.23725118276054816, "learning_rate": 7.566115097378826e-05, "loss": 1.6115, "step": 1088 }, { "epoch": 0.16, "grad_norm": 0.23038896462149644, "learning_rate": 7.564797188460977e-05, "loss": 1.6046, "step": 1089 }, { "epoch": 0.16, "grad_norm": 0.22163894578256085, "learning_rate": 7.563479279543126e-05, "loss": 1.6135, "step": 1090 }, { "epoch": 0.16, "grad_norm": 0.2103881958644772, "learning_rate": 7.562161370625274e-05, "loss": 1.6005, "step": 1091 }, { "epoch": 0.16, "grad_norm": 0.21034951411455005, "learning_rate": 7.560843461707425e-05, "loss": 1.6097, "step": 1092 }, { "epoch": 0.16, "grad_norm": 0.22289981805998374, "learning_rate": 7.559525552789574e-05, "loss": 1.5967, "step": 1093 }, { "epoch": 0.16, "grad_norm": 0.2756558475920652, "learning_rate": 7.558207643871724e-05, "loss": 1.606, "step": 1094 }, { "epoch": 0.16, "grad_norm": 0.24802208075338164, "learning_rate": 7.556889734953874e-05, "loss": 1.5984, "step": 1095 }, { "epoch": 0.16, "grad_norm": 0.21897014261396455, "learning_rate": 7.555571826036024e-05, "loss": 1.604, "step": 1096 }, { "epoch": 0.16, "grad_norm": 0.17301569858025576, "learning_rate": 7.554253917118173e-05, "loss": 1.6085, "step": 1097 }, { "epoch": 0.16, "grad_norm": 0.15443666681450202, "learning_rate": 7.552936008200324e-05, "loss": 1.5974, "step": 1098 }, { "epoch": 0.16, "grad_norm": 0.20297306903978035, "learning_rate": 7.551618099282472e-05, "loss": 1.6101, "step": 1099 }, { "epoch": 0.16, "grad_norm": 0.24144721356383153, "learning_rate": 7.550300190364621e-05, "loss": 1.598, "step": 1100 }, { "epoch": 0.16, "grad_norm": 0.22156745220232862, "learning_rate": 7.548982281446772e-05, "loss": 1.6168, "step": 1101 }, { "epoch": 0.16, "grad_norm": 0.193769033449188, "learning_rate": 7.547664372528921e-05, "loss": 1.6096, "step": 1102 }, { "epoch": 0.16, "grad_norm": 0.19547711850030344, "learning_rate": 7.54634646361107e-05, "loss": 1.6078, "step": 1103 }, { "epoch": 0.16, "grad_norm": 0.20219810170780822, "learning_rate": 7.545028554693221e-05, "loss": 1.6087, "step": 1104 }, { "epoch": 0.16, "grad_norm": 0.1656378663366526, "learning_rate": 7.543710645775371e-05, "loss": 1.6047, "step": 1105 }, { "epoch": 0.16, "grad_norm": 0.12279504679737889, "learning_rate": 7.54239273685752e-05, "loss": 1.608, "step": 1106 }, { "epoch": 0.16, "grad_norm": 0.14332841985114664, "learning_rate": 7.54107482793967e-05, "loss": 1.6007, "step": 1107 }, { "epoch": 0.16, "grad_norm": 0.17869073671045163, "learning_rate": 7.539756919021819e-05, "loss": 1.6018, "step": 1108 }, { "epoch": 0.16, "grad_norm": 0.17562435746125366, "learning_rate": 7.538439010103968e-05, "loss": 1.6085, "step": 1109 }, { "epoch": 0.16, "grad_norm": 0.15844195620891538, "learning_rate": 7.537121101186119e-05, "loss": 1.6046, "step": 1110 }, { "epoch": 0.16, "grad_norm": 0.15431885892046604, "learning_rate": 7.535803192268268e-05, "loss": 1.6017, "step": 1111 }, { "epoch": 0.16, "grad_norm": 0.16010284786126977, "learning_rate": 7.534485283350418e-05, "loss": 1.6078, "step": 1112 }, { "epoch": 0.16, "grad_norm": 0.14618258638327017, "learning_rate": 7.533167374432568e-05, "loss": 1.6061, "step": 1113 }, { "epoch": 0.16, "grad_norm": 0.16207811103063444, "learning_rate": 7.531849465514718e-05, "loss": 1.6015, "step": 1114 }, { "epoch": 0.16, "grad_norm": 0.195737447043241, "learning_rate": 7.530531556596866e-05, "loss": 1.5978, "step": 1115 }, { "epoch": 0.16, "grad_norm": 0.20987994206889682, "learning_rate": 7.529213647679017e-05, "loss": 1.6133, "step": 1116 }, { "epoch": 0.16, "grad_norm": 0.23671104304648102, "learning_rate": 7.527895738761166e-05, "loss": 1.5964, "step": 1117 }, { "epoch": 0.16, "grad_norm": 0.26675358723328, "learning_rate": 7.526577829843315e-05, "loss": 1.6112, "step": 1118 }, { "epoch": 0.16, "grad_norm": 0.26866295102797627, "learning_rate": 7.525259920925466e-05, "loss": 1.6018, "step": 1119 }, { "epoch": 0.16, "grad_norm": 0.23052925267631813, "learning_rate": 7.523942012007615e-05, "loss": 1.6133, "step": 1120 }, { "epoch": 0.16, "grad_norm": 0.17178396931122542, "learning_rate": 7.522624103089765e-05, "loss": 1.6071, "step": 1121 }, { "epoch": 0.16, "grad_norm": 0.16832141500530334, "learning_rate": 7.521306194171914e-05, "loss": 1.6034, "step": 1122 }, { "epoch": 0.16, "grad_norm": 0.22478896594336525, "learning_rate": 7.519988285254064e-05, "loss": 1.5981, "step": 1123 }, { "epoch": 0.16, "grad_norm": 0.22109419557694107, "learning_rate": 7.518670376336213e-05, "loss": 1.6036, "step": 1124 }, { "epoch": 0.16, "grad_norm": 0.2011335701566258, "learning_rate": 7.517352467418364e-05, "loss": 1.606, "step": 1125 }, { "epoch": 0.16, "grad_norm": 0.19999382668915064, "learning_rate": 7.516034558500513e-05, "loss": 1.5958, "step": 1126 }, { "epoch": 0.17, "grad_norm": 0.2087313106488091, "learning_rate": 7.514716649582662e-05, "loss": 1.6041, "step": 1127 }, { "epoch": 0.17, "grad_norm": 0.25624726246634655, "learning_rate": 7.513398740664813e-05, "loss": 1.6054, "step": 1128 }, { "epoch": 0.17, "grad_norm": 0.2760442187545006, "learning_rate": 7.512080831746963e-05, "loss": 1.6026, "step": 1129 }, { "epoch": 0.17, "grad_norm": 0.21828668039689092, "learning_rate": 7.510762922829112e-05, "loss": 1.6058, "step": 1130 }, { "epoch": 0.17, "grad_norm": 0.15791621829412608, "learning_rate": 7.509445013911261e-05, "loss": 1.6009, "step": 1131 }, { "epoch": 0.17, "grad_norm": 0.1554563269196245, "learning_rate": 7.50812710499341e-05, "loss": 1.6036, "step": 1132 }, { "epoch": 0.17, "grad_norm": 0.16523751476714793, "learning_rate": 7.50680919607556e-05, "loss": 1.6029, "step": 1133 }, { "epoch": 0.17, "grad_norm": 0.17099491590982738, "learning_rate": 7.505491287157711e-05, "loss": 1.5972, "step": 1134 }, { "epoch": 0.17, "grad_norm": 0.17134299136620068, "learning_rate": 7.50417337823986e-05, "loss": 1.5904, "step": 1135 }, { "epoch": 0.17, "grad_norm": 0.18427242584450257, "learning_rate": 7.50285546932201e-05, "loss": 1.5935, "step": 1136 }, { "epoch": 0.17, "grad_norm": 0.17050705423416349, "learning_rate": 7.50153756040416e-05, "loss": 1.5972, "step": 1137 }, { "epoch": 0.17, "grad_norm": 0.16797826815156477, "learning_rate": 7.50021965148631e-05, "loss": 1.599, "step": 1138 }, { "epoch": 0.17, "grad_norm": 0.18202925378142923, "learning_rate": 7.498901742568458e-05, "loss": 1.6038, "step": 1139 }, { "epoch": 0.17, "grad_norm": 0.1986542020413657, "learning_rate": 7.497583833650608e-05, "loss": 1.6116, "step": 1140 }, { "epoch": 0.17, "grad_norm": 0.18787713595892783, "learning_rate": 7.496265924732758e-05, "loss": 1.6074, "step": 1141 }, { "epoch": 0.17, "grad_norm": 0.1601110159530077, "learning_rate": 7.494948015814907e-05, "loss": 1.6044, "step": 1142 }, { "epoch": 0.17, "grad_norm": 0.15871745658510408, "learning_rate": 7.493630106897058e-05, "loss": 1.6032, "step": 1143 }, { "epoch": 0.17, "grad_norm": 0.1430625947479129, "learning_rate": 7.492312197979207e-05, "loss": 1.5926, "step": 1144 }, { "epoch": 0.17, "grad_norm": 0.1469464248975521, "learning_rate": 7.490994289061357e-05, "loss": 1.6002, "step": 1145 }, { "epoch": 0.17, "grad_norm": 0.15258319044288818, "learning_rate": 7.489676380143506e-05, "loss": 1.5978, "step": 1146 }, { "epoch": 0.17, "grad_norm": 0.16643604102356668, "learning_rate": 7.488358471225655e-05, "loss": 1.599, "step": 1147 }, { "epoch": 0.17, "grad_norm": 0.16005469141475748, "learning_rate": 7.487040562307805e-05, "loss": 1.5864, "step": 1148 }, { "epoch": 0.17, "grad_norm": 0.15986595889960914, "learning_rate": 7.485722653389955e-05, "loss": 1.5997, "step": 1149 }, { "epoch": 0.17, "grad_norm": 0.15784680612918575, "learning_rate": 7.484404744472105e-05, "loss": 1.5986, "step": 1150 }, { "epoch": 0.17, "grad_norm": 0.15000600634626432, "learning_rate": 7.483086835554254e-05, "loss": 1.599, "step": 1151 }, { "epoch": 0.17, "grad_norm": 0.17485532780513346, "learning_rate": 7.481768926636405e-05, "loss": 1.6024, "step": 1152 }, { "epoch": 0.17, "grad_norm": 0.1967341085166345, "learning_rate": 7.480451017718554e-05, "loss": 1.5936, "step": 1153 }, { "epoch": 0.17, "grad_norm": 0.2344844762884148, "learning_rate": 7.479133108800704e-05, "loss": 1.5998, "step": 1154 }, { "epoch": 0.17, "grad_norm": 0.2497106189098422, "learning_rate": 7.477815199882853e-05, "loss": 1.596, "step": 1155 }, { "epoch": 0.17, "grad_norm": 0.2040425471013873, "learning_rate": 7.476497290965002e-05, "loss": 1.595, "step": 1156 }, { "epoch": 0.17, "grad_norm": 0.17477543215459185, "learning_rate": 7.475179382047152e-05, "loss": 1.5879, "step": 1157 }, { "epoch": 0.17, "grad_norm": 0.1747166451083869, "learning_rate": 7.473861473129302e-05, "loss": 1.5973, "step": 1158 }, { "epoch": 0.17, "grad_norm": 0.19091852317109032, "learning_rate": 7.472543564211452e-05, "loss": 1.5935, "step": 1159 }, { "epoch": 0.17, "grad_norm": 0.20616285346047855, "learning_rate": 7.471225655293601e-05, "loss": 1.5923, "step": 1160 }, { "epoch": 0.17, "grad_norm": 0.2014869666468898, "learning_rate": 7.469907746375752e-05, "loss": 1.5957, "step": 1161 }, { "epoch": 0.17, "grad_norm": 0.16960374414389154, "learning_rate": 7.468589837457901e-05, "loss": 1.5968, "step": 1162 }, { "epoch": 0.17, "grad_norm": 0.174537560571573, "learning_rate": 7.46727192854005e-05, "loss": 1.5975, "step": 1163 }, { "epoch": 0.17, "grad_norm": 0.2042247405656548, "learning_rate": 7.4659540196222e-05, "loss": 1.599, "step": 1164 }, { "epoch": 0.17, "grad_norm": 0.22065476727458821, "learning_rate": 7.46463611070435e-05, "loss": 1.5954, "step": 1165 }, { "epoch": 0.17, "grad_norm": 0.19733900341635885, "learning_rate": 7.463318201786499e-05, "loss": 1.5947, "step": 1166 }, { "epoch": 0.17, "grad_norm": 0.1531704474147821, "learning_rate": 7.46200029286865e-05, "loss": 1.5997, "step": 1167 }, { "epoch": 0.17, "grad_norm": 0.15625856015130773, "learning_rate": 7.460682383950799e-05, "loss": 1.605, "step": 1168 }, { "epoch": 0.17, "grad_norm": 0.18227226464739196, "learning_rate": 7.459364475032948e-05, "loss": 1.5843, "step": 1169 }, { "epoch": 0.17, "grad_norm": 0.18336918188164913, "learning_rate": 7.458046566115098e-05, "loss": 1.5955, "step": 1170 }, { "epoch": 0.17, "grad_norm": 0.1653696455586279, "learning_rate": 7.456728657197247e-05, "loss": 1.593, "step": 1171 }, { "epoch": 0.17, "grad_norm": 0.14145061297298278, "learning_rate": 7.455410748279396e-05, "loss": 1.5984, "step": 1172 }, { "epoch": 0.17, "grad_norm": 0.15177089703146257, "learning_rate": 7.454092839361547e-05, "loss": 1.5908, "step": 1173 }, { "epoch": 0.17, "grad_norm": 0.1657687250680247, "learning_rate": 7.452774930443697e-05, "loss": 1.5878, "step": 1174 }, { "epoch": 0.17, "grad_norm": 0.18104982414107768, "learning_rate": 7.451457021525846e-05, "loss": 1.5896, "step": 1175 }, { "epoch": 0.17, "grad_norm": 0.18058656545512794, "learning_rate": 7.450139112607997e-05, "loss": 1.5946, "step": 1176 }, { "epoch": 0.17, "grad_norm": 0.18947505554561722, "learning_rate": 7.448821203690146e-05, "loss": 1.595, "step": 1177 }, { "epoch": 0.17, "grad_norm": 0.23178548541042568, "learning_rate": 7.447503294772295e-05, "loss": 1.5883, "step": 1178 }, { "epoch": 0.17, "grad_norm": 0.2650401902604043, "learning_rate": 7.446185385854445e-05, "loss": 1.6039, "step": 1179 }, { "epoch": 0.17, "grad_norm": 0.2423595493228995, "learning_rate": 7.444867476936594e-05, "loss": 1.5925, "step": 1180 }, { "epoch": 0.17, "grad_norm": 0.21249249646756155, "learning_rate": 7.443549568018744e-05, "loss": 1.5979, "step": 1181 }, { "epoch": 0.17, "grad_norm": 0.24250610726543256, "learning_rate": 7.442231659100894e-05, "loss": 1.5969, "step": 1182 }, { "epoch": 0.17, "grad_norm": 0.2537655199876406, "learning_rate": 7.440913750183044e-05, "loss": 1.5933, "step": 1183 }, { "epoch": 0.17, "grad_norm": 0.21405956441015037, "learning_rate": 7.439595841265193e-05, "loss": 1.5954, "step": 1184 }, { "epoch": 0.17, "grad_norm": 0.16174367763094688, "learning_rate": 7.438277932347342e-05, "loss": 1.5946, "step": 1185 }, { "epoch": 0.17, "grad_norm": 0.17946717348892616, "learning_rate": 7.436960023429493e-05, "loss": 1.5911, "step": 1186 }, { "epoch": 0.17, "grad_norm": 0.20846968398819296, "learning_rate": 7.435642114511641e-05, "loss": 1.589, "step": 1187 }, { "epoch": 0.17, "grad_norm": 0.1856354988357816, "learning_rate": 7.434324205593792e-05, "loss": 1.5929, "step": 1188 }, { "epoch": 0.17, "grad_norm": 0.15578117731766, "learning_rate": 7.433006296675941e-05, "loss": 1.5966, "step": 1189 }, { "epoch": 0.17, "grad_norm": 0.1842436337816048, "learning_rate": 7.43168838775809e-05, "loss": 1.5932, "step": 1190 }, { "epoch": 0.17, "grad_norm": 0.20401450420216943, "learning_rate": 7.430370478840241e-05, "loss": 1.589, "step": 1191 }, { "epoch": 0.17, "grad_norm": 0.1571115083265962, "learning_rate": 7.429052569922391e-05, "loss": 1.5852, "step": 1192 }, { "epoch": 0.17, "grad_norm": 0.1406605676557017, "learning_rate": 7.42773466100454e-05, "loss": 1.5909, "step": 1193 }, { "epoch": 0.17, "grad_norm": 0.1581183982669551, "learning_rate": 7.42641675208669e-05, "loss": 1.5847, "step": 1194 }, { "epoch": 0.17, "grad_norm": 0.15952906110455567, "learning_rate": 7.425098843168839e-05, "loss": 1.5862, "step": 1195 }, { "epoch": 0.18, "grad_norm": 0.15607263351309267, "learning_rate": 7.423780934250988e-05, "loss": 1.5937, "step": 1196 }, { "epoch": 0.18, "grad_norm": 0.1310303481341675, "learning_rate": 7.422463025333139e-05, "loss": 1.594, "step": 1197 }, { "epoch": 0.18, "grad_norm": 0.12984942531622481, "learning_rate": 7.421145116415288e-05, "loss": 1.5939, "step": 1198 }, { "epoch": 0.18, "grad_norm": 0.14587642352300043, "learning_rate": 7.419827207497438e-05, "loss": 1.5882, "step": 1199 }, { "epoch": 0.18, "grad_norm": 0.15198871500094838, "learning_rate": 7.418509298579588e-05, "loss": 1.59, "step": 1200 }, { "epoch": 0.18, "grad_norm": 0.154450062692067, "learning_rate": 7.417191389661738e-05, "loss": 1.5888, "step": 1201 }, { "epoch": 0.18, "grad_norm": 0.18039937998823308, "learning_rate": 7.415873480743887e-05, "loss": 1.6007, "step": 1202 }, { "epoch": 0.18, "grad_norm": 0.18845018044860143, "learning_rate": 7.414555571826037e-05, "loss": 1.593, "step": 1203 }, { "epoch": 0.18, "grad_norm": 0.17172832353041226, "learning_rate": 7.413237662908186e-05, "loss": 1.5918, "step": 1204 }, { "epoch": 0.18, "grad_norm": 0.1581293047398025, "learning_rate": 7.411919753990335e-05, "loss": 1.6033, "step": 1205 }, { "epoch": 0.18, "grad_norm": 0.16734747711724823, "learning_rate": 7.410601845072486e-05, "loss": 1.5808, "step": 1206 }, { "epoch": 0.18, "grad_norm": 0.19019197233208932, "learning_rate": 7.409283936154635e-05, "loss": 1.5904, "step": 1207 }, { "epoch": 0.18, "grad_norm": 0.19620446308614556, "learning_rate": 7.407966027236785e-05, "loss": 1.5917, "step": 1208 }, { "epoch": 0.18, "grad_norm": 0.20898204213566193, "learning_rate": 7.406648118318934e-05, "loss": 1.5954, "step": 1209 }, { "epoch": 0.18, "grad_norm": 0.24614257226734018, "learning_rate": 7.405330209401085e-05, "loss": 1.5927, "step": 1210 }, { "epoch": 0.18, "grad_norm": 0.2653501164736441, "learning_rate": 7.404012300483233e-05, "loss": 1.5895, "step": 1211 }, { "epoch": 0.18, "grad_norm": 0.25455637155885896, "learning_rate": 7.402694391565384e-05, "loss": 1.5808, "step": 1212 }, { "epoch": 0.18, "grad_norm": 0.2219490743301624, "learning_rate": 7.401376482647533e-05, "loss": 1.5923, "step": 1213 }, { "epoch": 0.18, "grad_norm": 0.14713310813171854, "learning_rate": 7.400058573729682e-05, "loss": 1.5842, "step": 1214 }, { "epoch": 0.18, "grad_norm": 0.15660737876177702, "learning_rate": 7.398740664811833e-05, "loss": 1.5955, "step": 1215 }, { "epoch": 0.18, "grad_norm": 0.1811379789536238, "learning_rate": 7.397422755893982e-05, "loss": 1.5913, "step": 1216 }, { "epoch": 0.18, "grad_norm": 0.1961687660102907, "learning_rate": 7.396104846976132e-05, "loss": 1.5896, "step": 1217 }, { "epoch": 0.18, "grad_norm": 0.17373689540381426, "learning_rate": 7.394786938058281e-05, "loss": 1.5866, "step": 1218 }, { "epoch": 0.18, "grad_norm": 0.17773055257272066, "learning_rate": 7.39346902914043e-05, "loss": 1.5888, "step": 1219 }, { "epoch": 0.18, "grad_norm": 0.16536252481789593, "learning_rate": 7.39215112022258e-05, "loss": 1.5763, "step": 1220 }, { "epoch": 0.18, "grad_norm": 0.14193680341594905, "learning_rate": 7.390833211304731e-05, "loss": 1.5899, "step": 1221 }, { "epoch": 0.18, "grad_norm": 0.16528380516967012, "learning_rate": 7.38951530238688e-05, "loss": 1.5827, "step": 1222 }, { "epoch": 0.18, "grad_norm": 0.1585259135194698, "learning_rate": 7.38819739346903e-05, "loss": 1.5951, "step": 1223 }, { "epoch": 0.18, "grad_norm": 0.14843359958766764, "learning_rate": 7.38687948455118e-05, "loss": 1.5966, "step": 1224 }, { "epoch": 0.18, "grad_norm": 0.16795811232997543, "learning_rate": 7.38556157563333e-05, "loss": 1.5822, "step": 1225 }, { "epoch": 0.18, "grad_norm": 0.17063382746855169, "learning_rate": 7.384243666715479e-05, "loss": 1.5821, "step": 1226 }, { "epoch": 0.18, "grad_norm": 0.15646631540555336, "learning_rate": 7.382925757797628e-05, "loss": 1.5925, "step": 1227 }, { "epoch": 0.18, "grad_norm": 0.12663185635907337, "learning_rate": 7.381607848879778e-05, "loss": 1.5755, "step": 1228 }, { "epoch": 0.18, "grad_norm": 0.13506195484438943, "learning_rate": 7.380289939961927e-05, "loss": 1.5856, "step": 1229 }, { "epoch": 0.18, "grad_norm": 0.1355655412063337, "learning_rate": 7.378972031044078e-05, "loss": 1.5773, "step": 1230 }, { "epoch": 0.18, "grad_norm": 0.15651881391255412, "learning_rate": 7.377654122126227e-05, "loss": 1.5865, "step": 1231 }, { "epoch": 0.18, "grad_norm": 0.1577977275413669, "learning_rate": 7.376336213208377e-05, "loss": 1.5822, "step": 1232 }, { "epoch": 0.18, "grad_norm": 0.17044005631971684, "learning_rate": 7.375018304290526e-05, "loss": 1.5856, "step": 1233 }, { "epoch": 0.18, "grad_norm": 0.18593965782849248, "learning_rate": 7.373700395372677e-05, "loss": 1.5838, "step": 1234 }, { "epoch": 0.18, "grad_norm": 0.1939373178548821, "learning_rate": 7.372382486454825e-05, "loss": 1.5948, "step": 1235 }, { "epoch": 0.18, "grad_norm": 0.20068033024298984, "learning_rate": 7.371064577536975e-05, "loss": 1.5944, "step": 1236 }, { "epoch": 0.18, "grad_norm": 0.17164694369691896, "learning_rate": 7.369746668619125e-05, "loss": 1.584, "step": 1237 }, { "epoch": 0.18, "grad_norm": 0.1436238943749497, "learning_rate": 7.368428759701274e-05, "loss": 1.5878, "step": 1238 }, { "epoch": 0.18, "grad_norm": 0.15172544100061827, "learning_rate": 7.367110850783425e-05, "loss": 1.5892, "step": 1239 }, { "epoch": 0.18, "grad_norm": 0.15646725821374724, "learning_rate": 7.365792941865574e-05, "loss": 1.5964, "step": 1240 }, { "epoch": 0.18, "grad_norm": 0.15865900762765828, "learning_rate": 7.364475032947724e-05, "loss": 1.5952, "step": 1241 }, { "epoch": 0.18, "grad_norm": 0.18082519774905434, "learning_rate": 7.363157124029873e-05, "loss": 1.5729, "step": 1242 }, { "epoch": 0.18, "grad_norm": 0.20299924734651137, "learning_rate": 7.361839215112022e-05, "loss": 1.5865, "step": 1243 }, { "epoch": 0.18, "grad_norm": 0.19780510869427326, "learning_rate": 7.360521306194172e-05, "loss": 1.5848, "step": 1244 }, { "epoch": 0.18, "grad_norm": 0.1783130384452761, "learning_rate": 7.359203397276322e-05, "loss": 1.5903, "step": 1245 }, { "epoch": 0.18, "grad_norm": 0.15261926702540918, "learning_rate": 7.357885488358472e-05, "loss": 1.5879, "step": 1246 }, { "epoch": 0.18, "grad_norm": 0.13783811582529387, "learning_rate": 7.356567579440621e-05, "loss": 1.5747, "step": 1247 }, { "epoch": 0.18, "grad_norm": 0.1467529651088208, "learning_rate": 7.355249670522772e-05, "loss": 1.5808, "step": 1248 }, { "epoch": 0.18, "grad_norm": 0.16377764961345861, "learning_rate": 7.353931761604921e-05, "loss": 1.58, "step": 1249 }, { "epoch": 0.18, "grad_norm": 0.15000263884955514, "learning_rate": 7.352613852687069e-05, "loss": 1.5845, "step": 1250 }, { "epoch": 0.18, "grad_norm": 0.14171089245368748, "learning_rate": 7.35129594376922e-05, "loss": 1.5919, "step": 1251 }, { "epoch": 0.18, "grad_norm": 0.20435307840612746, "learning_rate": 7.34997803485137e-05, "loss": 1.5867, "step": 1252 }, { "epoch": 0.18, "grad_norm": 0.24045885356362473, "learning_rate": 7.348660125933519e-05, "loss": 1.584, "step": 1253 }, { "epoch": 0.18, "grad_norm": 0.28740932434468447, "learning_rate": 7.34734221701567e-05, "loss": 1.5936, "step": 1254 }, { "epoch": 0.18, "grad_norm": 0.3196108046291853, "learning_rate": 7.346024308097819e-05, "loss": 1.5997, "step": 1255 }, { "epoch": 0.18, "grad_norm": 0.2979197316242365, "learning_rate": 7.344706399179968e-05, "loss": 1.5838, "step": 1256 }, { "epoch": 0.18, "grad_norm": 0.22072665514336615, "learning_rate": 7.343388490262118e-05, "loss": 1.5819, "step": 1257 }, { "epoch": 0.18, "grad_norm": 0.15552888234227324, "learning_rate": 7.342070581344267e-05, "loss": 1.5833, "step": 1258 }, { "epoch": 0.18, "grad_norm": 0.20544194277297625, "learning_rate": 7.340752672426416e-05, "loss": 1.5921, "step": 1259 }, { "epoch": 0.18, "grad_norm": 0.26303138800180975, "learning_rate": 7.339434763508567e-05, "loss": 1.5859, "step": 1260 }, { "epoch": 0.18, "grad_norm": 0.22397522066945746, "learning_rate": 7.338116854590716e-05, "loss": 1.5841, "step": 1261 }, { "epoch": 0.18, "grad_norm": 0.14991417239420035, "learning_rate": 7.336798945672866e-05, "loss": 1.5841, "step": 1262 }, { "epoch": 0.18, "grad_norm": 0.16359585502730267, "learning_rate": 7.335481036755017e-05, "loss": 1.5816, "step": 1263 }, { "epoch": 0.19, "grad_norm": 0.19466431015661523, "learning_rate": 7.334163127837166e-05, "loss": 1.5828, "step": 1264 }, { "epoch": 0.19, "grad_norm": 0.17089651320335977, "learning_rate": 7.332845218919315e-05, "loss": 1.5876, "step": 1265 }, { "epoch": 0.19, "grad_norm": 0.13925314072410105, "learning_rate": 7.331527310001465e-05, "loss": 1.5885, "step": 1266 }, { "epoch": 0.19, "grad_norm": 0.14834175295114693, "learning_rate": 7.330209401083614e-05, "loss": 1.5785, "step": 1267 }, { "epoch": 0.19, "grad_norm": 0.1699156449333421, "learning_rate": 7.328891492165763e-05, "loss": 1.5804, "step": 1268 }, { "epoch": 0.19, "grad_norm": 0.15496535500653283, "learning_rate": 7.327573583247914e-05, "loss": 1.5786, "step": 1269 }, { "epoch": 0.19, "grad_norm": 0.1556764604070721, "learning_rate": 7.326255674330064e-05, "loss": 1.5873, "step": 1270 }, { "epoch": 0.19, "grad_norm": 0.18129236452074904, "learning_rate": 7.324937765412213e-05, "loss": 1.5908, "step": 1271 }, { "epoch": 0.19, "grad_norm": 0.1572516060188371, "learning_rate": 7.323619856494362e-05, "loss": 1.5834, "step": 1272 }, { "epoch": 0.19, "grad_norm": 0.15305720865121053, "learning_rate": 7.322301947576513e-05, "loss": 1.5848, "step": 1273 }, { "epoch": 0.19, "grad_norm": 0.1551328911651992, "learning_rate": 7.320984038658661e-05, "loss": 1.5902, "step": 1274 }, { "epoch": 0.19, "grad_norm": 0.1577934048703626, "learning_rate": 7.319666129740812e-05, "loss": 1.5794, "step": 1275 }, { "epoch": 0.19, "grad_norm": 0.16434049110207993, "learning_rate": 7.318348220822961e-05, "loss": 1.5783, "step": 1276 }, { "epoch": 0.19, "grad_norm": 0.16776089049627255, "learning_rate": 7.31703031190511e-05, "loss": 1.5768, "step": 1277 }, { "epoch": 0.19, "grad_norm": 0.16243702089894851, "learning_rate": 7.315712402987261e-05, "loss": 1.5826, "step": 1278 }, { "epoch": 0.19, "grad_norm": 0.1536195883355736, "learning_rate": 7.31439449406941e-05, "loss": 1.5788, "step": 1279 }, { "epoch": 0.19, "grad_norm": 0.17100276923275118, "learning_rate": 7.31307658515156e-05, "loss": 1.5801, "step": 1280 }, { "epoch": 0.19, "grad_norm": 0.17375573905803932, "learning_rate": 7.31175867623371e-05, "loss": 1.5781, "step": 1281 }, { "epoch": 0.19, "grad_norm": 0.1737765212522266, "learning_rate": 7.310440767315859e-05, "loss": 1.5841, "step": 1282 }, { "epoch": 0.19, "grad_norm": 0.1557338864747223, "learning_rate": 7.309122858398008e-05, "loss": 1.5839, "step": 1283 }, { "epoch": 0.19, "grad_norm": 0.1514952769269247, "learning_rate": 7.307804949480159e-05, "loss": 1.5838, "step": 1284 }, { "epoch": 0.19, "grad_norm": 0.15888225905146014, "learning_rate": 7.306487040562308e-05, "loss": 1.5728, "step": 1285 }, { "epoch": 0.19, "grad_norm": 0.15322549061770394, "learning_rate": 7.305169131644458e-05, "loss": 1.5807, "step": 1286 }, { "epoch": 0.19, "grad_norm": 0.16366336204652251, "learning_rate": 7.303851222726608e-05, "loss": 1.5878, "step": 1287 }, { "epoch": 0.19, "grad_norm": 0.16799314356241987, "learning_rate": 7.302533313808758e-05, "loss": 1.5737, "step": 1288 }, { "epoch": 0.19, "grad_norm": 0.15569342409500003, "learning_rate": 7.301215404890907e-05, "loss": 1.5863, "step": 1289 }, { "epoch": 0.19, "grad_norm": 0.13541629448681836, "learning_rate": 7.299897495973056e-05, "loss": 1.5886, "step": 1290 }, { "epoch": 0.19, "grad_norm": 0.1427857963080412, "learning_rate": 7.298579587055206e-05, "loss": 1.5741, "step": 1291 }, { "epoch": 0.19, "grad_norm": 0.1485360781927371, "learning_rate": 7.297261678137355e-05, "loss": 1.5666, "step": 1292 }, { "epoch": 0.19, "grad_norm": 0.15300033477123595, "learning_rate": 7.295943769219506e-05, "loss": 1.5881, "step": 1293 }, { "epoch": 0.19, "grad_norm": 0.1523533071984983, "learning_rate": 7.294625860301655e-05, "loss": 1.5833, "step": 1294 }, { "epoch": 0.19, "grad_norm": 0.14366735707085823, "learning_rate": 7.293307951383805e-05, "loss": 1.5852, "step": 1295 }, { "epoch": 0.19, "grad_norm": 0.15488474790280232, "learning_rate": 7.291990042465954e-05, "loss": 1.5764, "step": 1296 }, { "epoch": 0.19, "grad_norm": 0.17693604786333558, "learning_rate": 7.290672133548105e-05, "loss": 1.5823, "step": 1297 }, { "epoch": 0.19, "grad_norm": 0.2165069651574788, "learning_rate": 7.289354224630253e-05, "loss": 1.5885, "step": 1298 }, { "epoch": 0.19, "grad_norm": 0.2108685441610128, "learning_rate": 7.288036315712404e-05, "loss": 1.5763, "step": 1299 }, { "epoch": 0.19, "grad_norm": 0.19114050529562934, "learning_rate": 7.286718406794553e-05, "loss": 1.5822, "step": 1300 }, { "epoch": 0.19, "grad_norm": 0.21363514589823596, "learning_rate": 7.285400497876702e-05, "loss": 1.5893, "step": 1301 }, { "epoch": 0.19, "grad_norm": 0.2437901279010662, "learning_rate": 7.284082588958853e-05, "loss": 1.5778, "step": 1302 }, { "epoch": 0.19, "grad_norm": 0.26098162568490296, "learning_rate": 7.282764680041002e-05, "loss": 1.5849, "step": 1303 }, { "epoch": 0.19, "grad_norm": 0.25540292032332557, "learning_rate": 7.281446771123152e-05, "loss": 1.5831, "step": 1304 }, { "epoch": 0.19, "grad_norm": 0.21631749808313838, "learning_rate": 7.280128862205301e-05, "loss": 1.5734, "step": 1305 }, { "epoch": 0.19, "grad_norm": 0.1718013292626418, "learning_rate": 7.27881095328745e-05, "loss": 1.5828, "step": 1306 }, { "epoch": 0.19, "grad_norm": 0.13719025908171398, "learning_rate": 7.2774930443696e-05, "loss": 1.5808, "step": 1307 }, { "epoch": 0.19, "grad_norm": 0.1690183237112528, "learning_rate": 7.27617513545175e-05, "loss": 1.5817, "step": 1308 }, { "epoch": 0.19, "grad_norm": 0.1848978593010119, "learning_rate": 7.2748572265339e-05, "loss": 1.5762, "step": 1309 }, { "epoch": 0.19, "grad_norm": 0.15635718310334223, "learning_rate": 7.27353931761605e-05, "loss": 1.5757, "step": 1310 }, { "epoch": 0.19, "grad_norm": 0.14725817433618338, "learning_rate": 7.2722214086982e-05, "loss": 1.591, "step": 1311 }, { "epoch": 0.19, "grad_norm": 0.1512466403819289, "learning_rate": 7.27090349978035e-05, "loss": 1.5847, "step": 1312 }, { "epoch": 0.19, "grad_norm": 0.1335054707530398, "learning_rate": 7.269585590862499e-05, "loss": 1.5731, "step": 1313 }, { "epoch": 0.19, "grad_norm": 0.13882677911813507, "learning_rate": 7.268267681944648e-05, "loss": 1.5797, "step": 1314 }, { "epoch": 0.19, "grad_norm": 0.15268615715918724, "learning_rate": 7.266949773026798e-05, "loss": 1.5853, "step": 1315 }, { "epoch": 0.19, "grad_norm": 0.1488126658370855, "learning_rate": 7.265631864108947e-05, "loss": 1.5849, "step": 1316 }, { "epoch": 0.19, "grad_norm": 0.15007617848273547, "learning_rate": 7.264313955191098e-05, "loss": 1.5705, "step": 1317 }, { "epoch": 0.19, "grad_norm": 0.1584098535147045, "learning_rate": 7.262996046273247e-05, "loss": 1.5852, "step": 1318 }, { "epoch": 0.19, "grad_norm": 0.19072950094070457, "learning_rate": 7.261678137355396e-05, "loss": 1.5787, "step": 1319 }, { "epoch": 0.19, "grad_norm": 0.18522875418280946, "learning_rate": 7.260360228437546e-05, "loss": 1.586, "step": 1320 }, { "epoch": 0.19, "grad_norm": 0.16446527308539624, "learning_rate": 7.259042319519697e-05, "loss": 1.5847, "step": 1321 }, { "epoch": 0.19, "grad_norm": 0.13874396432926306, "learning_rate": 7.257724410601845e-05, "loss": 1.5756, "step": 1322 }, { "epoch": 0.19, "grad_norm": 0.13928631137367814, "learning_rate": 7.256406501683995e-05, "loss": 1.5738, "step": 1323 }, { "epoch": 0.19, "grad_norm": 0.1673872997735078, "learning_rate": 7.255088592766145e-05, "loss": 1.5789, "step": 1324 }, { "epoch": 0.19, "grad_norm": 0.17153496675553456, "learning_rate": 7.253770683848294e-05, "loss": 1.5791, "step": 1325 }, { "epoch": 0.19, "grad_norm": 0.1465187797607589, "learning_rate": 7.252452774930445e-05, "loss": 1.5703, "step": 1326 }, { "epoch": 0.19, "grad_norm": 0.1351520271793626, "learning_rate": 7.251134866012594e-05, "loss": 1.5778, "step": 1327 }, { "epoch": 0.19, "grad_norm": 0.13031490453618944, "learning_rate": 7.249816957094744e-05, "loss": 1.5792, "step": 1328 }, { "epoch": 0.19, "grad_norm": 0.1262777867945403, "learning_rate": 7.248499048176893e-05, "loss": 1.574, "step": 1329 }, { "epoch": 0.19, "grad_norm": 0.13212997342047494, "learning_rate": 7.247181139259042e-05, "loss": 1.58, "step": 1330 }, { "epoch": 0.19, "grad_norm": 0.14500318487143435, "learning_rate": 7.245863230341192e-05, "loss": 1.5681, "step": 1331 }, { "epoch": 0.2, "grad_norm": 0.17875663213637794, "learning_rate": 7.244545321423342e-05, "loss": 1.5719, "step": 1332 }, { "epoch": 0.2, "grad_norm": 0.20287564117034, "learning_rate": 7.243227412505492e-05, "loss": 1.5783, "step": 1333 }, { "epoch": 0.2, "grad_norm": 0.22538319404257154, "learning_rate": 7.241909503587641e-05, "loss": 1.5799, "step": 1334 }, { "epoch": 0.2, "grad_norm": 0.24510429626641428, "learning_rate": 7.240591594669792e-05, "loss": 1.5688, "step": 1335 }, { "epoch": 0.2, "grad_norm": 0.21758774192310035, "learning_rate": 7.239273685751941e-05, "loss": 1.5748, "step": 1336 }, { "epoch": 0.2, "grad_norm": 0.17046856072667518, "learning_rate": 7.23795577683409e-05, "loss": 1.5744, "step": 1337 }, { "epoch": 0.2, "grad_norm": 0.14997523013715272, "learning_rate": 7.23663786791624e-05, "loss": 1.5764, "step": 1338 }, { "epoch": 0.2, "grad_norm": 0.17864699485620184, "learning_rate": 7.23531995899839e-05, "loss": 1.5676, "step": 1339 }, { "epoch": 0.2, "grad_norm": 0.19732979726685498, "learning_rate": 7.234002050080539e-05, "loss": 1.5708, "step": 1340 }, { "epoch": 0.2, "grad_norm": 0.17655391742101245, "learning_rate": 7.23268414116269e-05, "loss": 1.5713, "step": 1341 }, { "epoch": 0.2, "grad_norm": 0.13019863917633345, "learning_rate": 7.231366232244839e-05, "loss": 1.5834, "step": 1342 }, { "epoch": 0.2, "grad_norm": 0.163754576536066, "learning_rate": 7.230048323326988e-05, "loss": 1.5819, "step": 1343 }, { "epoch": 0.2, "grad_norm": 0.22301870470160576, "learning_rate": 7.228730414409138e-05, "loss": 1.5806, "step": 1344 }, { "epoch": 0.2, "grad_norm": 0.22979909365643392, "learning_rate": 7.227412505491288e-05, "loss": 1.5801, "step": 1345 }, { "epoch": 0.2, "grad_norm": 0.18015517540086598, "learning_rate": 7.226094596573436e-05, "loss": 1.5767, "step": 1346 }, { "epoch": 0.2, "grad_norm": 0.1557837416424971, "learning_rate": 7.224776687655587e-05, "loss": 1.5728, "step": 1347 }, { "epoch": 0.2, "grad_norm": 0.1669198000676956, "learning_rate": 7.223458778737736e-05, "loss": 1.5767, "step": 1348 }, { "epoch": 0.2, "grad_norm": 0.15973163251561107, "learning_rate": 7.222140869819886e-05, "loss": 1.5817, "step": 1349 }, { "epoch": 0.2, "grad_norm": 0.16671599564277967, "learning_rate": 7.220822960902037e-05, "loss": 1.5737, "step": 1350 }, { "epoch": 0.2, "grad_norm": 0.15068265123287375, "learning_rate": 7.219505051984186e-05, "loss": 1.5796, "step": 1351 }, { "epoch": 0.2, "grad_norm": 0.1463851065191522, "learning_rate": 7.218187143066335e-05, "loss": 1.5666, "step": 1352 }, { "epoch": 0.2, "grad_norm": 0.14776418821561846, "learning_rate": 7.216869234148485e-05, "loss": 1.5812, "step": 1353 }, { "epoch": 0.2, "grad_norm": 0.16447130345045846, "learning_rate": 7.215551325230634e-05, "loss": 1.584, "step": 1354 }, { "epoch": 0.2, "grad_norm": 0.1488498411391017, "learning_rate": 7.214233416312783e-05, "loss": 1.5732, "step": 1355 }, { "epoch": 0.2, "grad_norm": 0.14942787853682804, "learning_rate": 7.212915507394934e-05, "loss": 1.5822, "step": 1356 }, { "epoch": 0.2, "grad_norm": 0.169962466274362, "learning_rate": 7.211597598477084e-05, "loss": 1.5807, "step": 1357 }, { "epoch": 0.2, "grad_norm": 0.17265910173066412, "learning_rate": 7.210279689559233e-05, "loss": 1.5732, "step": 1358 }, { "epoch": 0.2, "grad_norm": 0.16447068445486143, "learning_rate": 7.208961780641382e-05, "loss": 1.573, "step": 1359 }, { "epoch": 0.2, "grad_norm": 0.1382385456580122, "learning_rate": 7.207643871723533e-05, "loss": 1.5773, "step": 1360 }, { "epoch": 0.2, "grad_norm": 0.15127923245359043, "learning_rate": 7.206325962805682e-05, "loss": 1.575, "step": 1361 }, { "epoch": 0.2, "grad_norm": 0.14745332967548117, "learning_rate": 7.205008053887832e-05, "loss": 1.572, "step": 1362 }, { "epoch": 0.2, "grad_norm": 0.1409200003691044, "learning_rate": 7.203690144969981e-05, "loss": 1.5764, "step": 1363 }, { "epoch": 0.2, "grad_norm": 0.1602133318398135, "learning_rate": 7.20237223605213e-05, "loss": 1.58, "step": 1364 }, { "epoch": 0.2, "grad_norm": 0.1808418713819235, "learning_rate": 7.201054327134281e-05, "loss": 1.5771, "step": 1365 }, { "epoch": 0.2, "grad_norm": 0.18480911250072243, "learning_rate": 7.19973641821643e-05, "loss": 1.5766, "step": 1366 }, { "epoch": 0.2, "grad_norm": 0.19252559378380835, "learning_rate": 7.19841850929858e-05, "loss": 1.5743, "step": 1367 }, { "epoch": 0.2, "grad_norm": 0.20052408124118393, "learning_rate": 7.19710060038073e-05, "loss": 1.5709, "step": 1368 }, { "epoch": 0.2, "grad_norm": 0.17837119621041397, "learning_rate": 7.19578269146288e-05, "loss": 1.5734, "step": 1369 }, { "epoch": 0.2, "grad_norm": 0.14591392612986573, "learning_rate": 7.194464782545028e-05, "loss": 1.5716, "step": 1370 }, { "epoch": 0.2, "grad_norm": 0.14918642258613896, "learning_rate": 7.193146873627179e-05, "loss": 1.5718, "step": 1371 }, { "epoch": 0.2, "grad_norm": 0.1433548846051071, "learning_rate": 7.191828964709328e-05, "loss": 1.5796, "step": 1372 }, { "epoch": 0.2, "grad_norm": 0.17948405788478852, "learning_rate": 7.190511055791478e-05, "loss": 1.5835, "step": 1373 }, { "epoch": 0.2, "grad_norm": 0.2310307534670035, "learning_rate": 7.189193146873628e-05, "loss": 1.5771, "step": 1374 }, { "epoch": 0.2, "grad_norm": 0.25695389114643785, "learning_rate": 7.187875237955778e-05, "loss": 1.569, "step": 1375 }, { "epoch": 0.2, "grad_norm": 0.25999039315686817, "learning_rate": 7.186557329037927e-05, "loss": 1.5738, "step": 1376 }, { "epoch": 0.2, "grad_norm": 0.22576403415131382, "learning_rate": 7.185239420120076e-05, "loss": 1.5804, "step": 1377 }, { "epoch": 0.2, "grad_norm": 0.1845921032220699, "learning_rate": 7.183921511202226e-05, "loss": 1.5703, "step": 1378 }, { "epoch": 0.2, "grad_norm": 0.18950643124102381, "learning_rate": 7.182603602284375e-05, "loss": 1.5761, "step": 1379 }, { "epoch": 0.2, "grad_norm": 0.22317918435110773, "learning_rate": 7.181285693366526e-05, "loss": 1.5757, "step": 1380 }, { "epoch": 0.2, "grad_norm": 0.2454572265669023, "learning_rate": 7.179967784448675e-05, "loss": 1.576, "step": 1381 }, { "epoch": 0.2, "grad_norm": 0.20188147907095785, "learning_rate": 7.178649875530825e-05, "loss": 1.566, "step": 1382 }, { "epoch": 0.2, "grad_norm": 0.140275625579357, "learning_rate": 7.177331966612974e-05, "loss": 1.5719, "step": 1383 }, { "epoch": 0.2, "grad_norm": 0.18452131194815793, "learning_rate": 7.176014057695125e-05, "loss": 1.5657, "step": 1384 }, { "epoch": 0.2, "grad_norm": 0.22651983400307935, "learning_rate": 7.174696148777274e-05, "loss": 1.5739, "step": 1385 }, { "epoch": 0.2, "grad_norm": 0.19651377875239404, "learning_rate": 7.173378239859424e-05, "loss": 1.5773, "step": 1386 }, { "epoch": 0.2, "grad_norm": 0.13581992227920534, "learning_rate": 7.172060330941573e-05, "loss": 1.5669, "step": 1387 }, { "epoch": 0.2, "grad_norm": 0.1711417241102865, "learning_rate": 7.170742422023722e-05, "loss": 1.5708, "step": 1388 }, { "epoch": 0.2, "grad_norm": 0.1970811470534912, "learning_rate": 7.169424513105873e-05, "loss": 1.5707, "step": 1389 }, { "epoch": 0.2, "grad_norm": 0.1730218026826818, "learning_rate": 7.168106604188022e-05, "loss": 1.5753, "step": 1390 }, { "epoch": 0.2, "grad_norm": 0.14249391458274216, "learning_rate": 7.166788695270172e-05, "loss": 1.5703, "step": 1391 }, { "epoch": 0.2, "grad_norm": 0.15576625474276548, "learning_rate": 7.165470786352321e-05, "loss": 1.5658, "step": 1392 }, { "epoch": 0.2, "grad_norm": 0.16844771524906862, "learning_rate": 7.164152877434472e-05, "loss": 1.5638, "step": 1393 }, { "epoch": 0.2, "grad_norm": 0.14842972901098414, "learning_rate": 7.16283496851662e-05, "loss": 1.5684, "step": 1394 }, { "epoch": 0.2, "grad_norm": 0.13938539030658934, "learning_rate": 7.16151705959877e-05, "loss": 1.5826, "step": 1395 }, { "epoch": 0.2, "grad_norm": 0.150557903672672, "learning_rate": 7.16019915068092e-05, "loss": 1.5641, "step": 1396 }, { "epoch": 0.2, "grad_norm": 0.15543635281372953, "learning_rate": 7.15888124176307e-05, "loss": 1.5696, "step": 1397 }, { "epoch": 0.2, "grad_norm": 0.1665289062823907, "learning_rate": 7.15756333284522e-05, "loss": 1.5667, "step": 1398 }, { "epoch": 0.2, "grad_norm": 0.20038629439420957, "learning_rate": 7.15624542392737e-05, "loss": 1.5738, "step": 1399 }, { "epoch": 0.2, "grad_norm": 0.20404987893441098, "learning_rate": 7.154927515009519e-05, "loss": 1.5641, "step": 1400 }, { "epoch": 0.21, "grad_norm": 0.19056674005837818, "learning_rate": 7.153609606091668e-05, "loss": 1.5789, "step": 1401 }, { "epoch": 0.21, "grad_norm": 0.15936990939657109, "learning_rate": 7.152291697173818e-05, "loss": 1.5727, "step": 1402 }, { "epoch": 0.21, "grad_norm": 0.1327675837335293, "learning_rate": 7.150973788255967e-05, "loss": 1.5784, "step": 1403 }, { "epoch": 0.21, "grad_norm": 0.1410578829295748, "learning_rate": 7.149655879338118e-05, "loss": 1.5759, "step": 1404 }, { "epoch": 0.21, "grad_norm": 0.16837905654706764, "learning_rate": 7.148337970420267e-05, "loss": 1.5678, "step": 1405 }, { "epoch": 0.21, "grad_norm": 0.1576722100754528, "learning_rate": 7.147020061502416e-05, "loss": 1.5652, "step": 1406 }, { "epoch": 0.21, "grad_norm": 0.15260049321124103, "learning_rate": 7.145702152584566e-05, "loss": 1.5649, "step": 1407 }, { "epoch": 0.21, "grad_norm": 0.16787848023479865, "learning_rate": 7.144384243666717e-05, "loss": 1.5709, "step": 1408 }, { "epoch": 0.21, "grad_norm": 0.15351278195144266, "learning_rate": 7.143066334748866e-05, "loss": 1.5652, "step": 1409 }, { "epoch": 0.21, "grad_norm": 0.141387994112907, "learning_rate": 7.141748425831015e-05, "loss": 1.5714, "step": 1410 }, { "epoch": 0.21, "grad_norm": 0.13817472717587612, "learning_rate": 7.140430516913165e-05, "loss": 1.5696, "step": 1411 }, { "epoch": 0.21, "grad_norm": 0.14708798930634917, "learning_rate": 7.139112607995314e-05, "loss": 1.5721, "step": 1412 }, { "epoch": 0.21, "grad_norm": 0.16574803886961384, "learning_rate": 7.137794699077465e-05, "loss": 1.5788, "step": 1413 }, { "epoch": 0.21, "grad_norm": 0.16999064687089108, "learning_rate": 7.136476790159614e-05, "loss": 1.5711, "step": 1414 }, { "epoch": 0.21, "grad_norm": 0.15401061336166366, "learning_rate": 7.135158881241763e-05, "loss": 1.5694, "step": 1415 }, { "epoch": 0.21, "grad_norm": 0.1522428976991431, "learning_rate": 7.133840972323913e-05, "loss": 1.5768, "step": 1416 }, { "epoch": 0.21, "grad_norm": 0.1620006742059713, "learning_rate": 7.132523063406064e-05, "loss": 1.5684, "step": 1417 }, { "epoch": 0.21, "grad_norm": 0.14184632294364613, "learning_rate": 7.131205154488212e-05, "loss": 1.5677, "step": 1418 }, { "epoch": 0.21, "grad_norm": 0.12851766257232203, "learning_rate": 7.129887245570362e-05, "loss": 1.566, "step": 1419 }, { "epoch": 0.21, "grad_norm": 0.13223607719411584, "learning_rate": 7.128569336652512e-05, "loss": 1.5701, "step": 1420 }, { "epoch": 0.21, "grad_norm": 0.13725326932964607, "learning_rate": 7.127251427734661e-05, "loss": 1.5767, "step": 1421 }, { "epoch": 0.21, "grad_norm": 0.1402305033389597, "learning_rate": 7.125933518816812e-05, "loss": 1.565, "step": 1422 }, { "epoch": 0.21, "grad_norm": 0.14563085034581674, "learning_rate": 7.124615609898961e-05, "loss": 1.5727, "step": 1423 }, { "epoch": 0.21, "grad_norm": 0.15859311190689154, "learning_rate": 7.12329770098111e-05, "loss": 1.5723, "step": 1424 }, { "epoch": 0.21, "grad_norm": 0.1640105183898524, "learning_rate": 7.12197979206326e-05, "loss": 1.5712, "step": 1425 }, { "epoch": 0.21, "grad_norm": 0.16108347576592652, "learning_rate": 7.120661883145409e-05, "loss": 1.5634, "step": 1426 }, { "epoch": 0.21, "grad_norm": 0.14570669209087186, "learning_rate": 7.119343974227559e-05, "loss": 1.5625, "step": 1427 }, { "epoch": 0.21, "grad_norm": 0.13374217351027243, "learning_rate": 7.11802606530971e-05, "loss": 1.561, "step": 1428 }, { "epoch": 0.21, "grad_norm": 0.13131168220415707, "learning_rate": 7.116708156391859e-05, "loss": 1.5586, "step": 1429 }, { "epoch": 0.21, "grad_norm": 0.14256260061186307, "learning_rate": 7.115390247474008e-05, "loss": 1.5623, "step": 1430 }, { "epoch": 0.21, "grad_norm": 0.13433942314754024, "learning_rate": 7.114072338556158e-05, "loss": 1.5644, "step": 1431 }, { "epoch": 0.21, "grad_norm": 0.12327503612115467, "learning_rate": 7.112754429638308e-05, "loss": 1.5728, "step": 1432 }, { "epoch": 0.21, "grad_norm": 0.1304444249984789, "learning_rate": 7.111436520720458e-05, "loss": 1.5717, "step": 1433 }, { "epoch": 0.21, "grad_norm": 0.1372735123829869, "learning_rate": 7.110118611802607e-05, "loss": 1.5749, "step": 1434 }, { "epoch": 0.21, "grad_norm": 0.15481059663823463, "learning_rate": 7.108800702884756e-05, "loss": 1.5728, "step": 1435 }, { "epoch": 0.21, "grad_norm": 0.1727623966582496, "learning_rate": 7.107482793966906e-05, "loss": 1.5639, "step": 1436 }, { "epoch": 0.21, "grad_norm": 0.19401076610760798, "learning_rate": 7.106164885049056e-05, "loss": 1.5684, "step": 1437 }, { "epoch": 0.21, "grad_norm": 0.2156803932249311, "learning_rate": 7.104846976131206e-05, "loss": 1.5714, "step": 1438 }, { "epoch": 0.21, "grad_norm": 0.24393826691213036, "learning_rate": 7.103529067213355e-05, "loss": 1.5677, "step": 1439 }, { "epoch": 0.21, "grad_norm": 0.24729171934390767, "learning_rate": 7.102211158295505e-05, "loss": 1.5666, "step": 1440 }, { "epoch": 0.21, "grad_norm": 0.20257547505533538, "learning_rate": 7.100893249377655e-05, "loss": 1.5774, "step": 1441 }, { "epoch": 0.21, "grad_norm": 0.1381135615527873, "learning_rate": 7.099575340459803e-05, "loss": 1.5727, "step": 1442 }, { "epoch": 0.21, "grad_norm": 0.13699646040366453, "learning_rate": 7.098257431541954e-05, "loss": 1.5675, "step": 1443 }, { "epoch": 0.21, "grad_norm": 0.1898081051960504, "learning_rate": 7.096939522624103e-05, "loss": 1.5647, "step": 1444 }, { "epoch": 0.21, "grad_norm": 0.21299109026323154, "learning_rate": 7.095621613706253e-05, "loss": 1.5707, "step": 1445 }, { "epoch": 0.21, "grad_norm": 0.20428555413508584, "learning_rate": 7.094303704788402e-05, "loss": 1.5708, "step": 1446 }, { "epoch": 0.21, "grad_norm": 0.1560001862551339, "learning_rate": 7.092985795870553e-05, "loss": 1.5583, "step": 1447 }, { "epoch": 0.21, "grad_norm": 0.16279311630157717, "learning_rate": 7.091667886952702e-05, "loss": 1.5666, "step": 1448 }, { "epoch": 0.21, "grad_norm": 0.2254152694317573, "learning_rate": 7.090349978034852e-05, "loss": 1.5731, "step": 1449 }, { "epoch": 0.21, "grad_norm": 0.23812366301388427, "learning_rate": 7.089032069117001e-05, "loss": 1.5583, "step": 1450 }, { "epoch": 0.21, "grad_norm": 0.23617513876866209, "learning_rate": 7.08771416019915e-05, "loss": 1.5721, "step": 1451 }, { "epoch": 0.21, "grad_norm": 0.2107361838293821, "learning_rate": 7.086396251281301e-05, "loss": 1.5634, "step": 1452 }, { "epoch": 0.21, "grad_norm": 0.1723002286014294, "learning_rate": 7.08507834236345e-05, "loss": 1.5671, "step": 1453 }, { "epoch": 0.21, "grad_norm": 0.14627668143930986, "learning_rate": 7.0837604334456e-05, "loss": 1.568, "step": 1454 }, { "epoch": 0.21, "grad_norm": 0.1336544861801278, "learning_rate": 7.082442524527749e-05, "loss": 1.5683, "step": 1455 }, { "epoch": 0.21, "grad_norm": 0.14421751195441476, "learning_rate": 7.0811246156099e-05, "loss": 1.5617, "step": 1456 }, { "epoch": 0.21, "grad_norm": 0.15430975229793042, "learning_rate": 7.07980670669205e-05, "loss": 1.5667, "step": 1457 }, { "epoch": 0.21, "grad_norm": 0.16660631410876542, "learning_rate": 7.078488797774199e-05, "loss": 1.5632, "step": 1458 }, { "epoch": 0.21, "grad_norm": 0.15222909256571887, "learning_rate": 7.077170888856348e-05, "loss": 1.564, "step": 1459 }, { "epoch": 0.21, "grad_norm": 0.14623520946095997, "learning_rate": 7.075852979938498e-05, "loss": 1.5575, "step": 1460 }, { "epoch": 0.21, "grad_norm": 0.1440011629967226, "learning_rate": 7.074535071020648e-05, "loss": 1.5597, "step": 1461 }, { "epoch": 0.21, "grad_norm": 0.1469726202146802, "learning_rate": 7.073217162102798e-05, "loss": 1.5662, "step": 1462 }, { "epoch": 0.21, "grad_norm": 0.13611688819390158, "learning_rate": 7.071899253184947e-05, "loss": 1.5689, "step": 1463 }, { "epoch": 0.21, "grad_norm": 0.13792597129053707, "learning_rate": 7.070581344267096e-05, "loss": 1.563, "step": 1464 }, { "epoch": 0.21, "grad_norm": 0.1453080159775326, "learning_rate": 7.069263435349247e-05, "loss": 1.5589, "step": 1465 }, { "epoch": 0.21, "grad_norm": 0.1483809349019845, "learning_rate": 7.067945526431395e-05, "loss": 1.5655, "step": 1466 }, { "epoch": 0.21, "grad_norm": 0.16564527303263538, "learning_rate": 7.066627617513546e-05, "loss": 1.5599, "step": 1467 }, { "epoch": 0.21, "grad_norm": 0.1759936696979058, "learning_rate": 7.065309708595695e-05, "loss": 1.5643, "step": 1468 }, { "epoch": 0.22, "grad_norm": 0.17115919022752862, "learning_rate": 7.063991799677845e-05, "loss": 1.5635, "step": 1469 }, { "epoch": 0.22, "grad_norm": 0.15619582944022972, "learning_rate": 7.062673890759994e-05, "loss": 1.5671, "step": 1470 }, { "epoch": 0.22, "grad_norm": 0.14548556726946826, "learning_rate": 7.061355981842145e-05, "loss": 1.5658, "step": 1471 }, { "epoch": 0.22, "grad_norm": 0.14857073163622167, "learning_rate": 7.060038072924294e-05, "loss": 1.5647, "step": 1472 }, { "epoch": 0.22, "grad_norm": 0.15690757349631196, "learning_rate": 7.058720164006443e-05, "loss": 1.5606, "step": 1473 }, { "epoch": 0.22, "grad_norm": 0.16896840074122582, "learning_rate": 7.057402255088593e-05, "loss": 1.5589, "step": 1474 }, { "epoch": 0.22, "grad_norm": 0.20333875962129536, "learning_rate": 7.056084346170742e-05, "loss": 1.5637, "step": 1475 }, { "epoch": 0.22, "grad_norm": 0.20502555973413897, "learning_rate": 7.054766437252893e-05, "loss": 1.5543, "step": 1476 }, { "epoch": 0.22, "grad_norm": 0.20543728861342644, "learning_rate": 7.053448528335042e-05, "loss": 1.5653, "step": 1477 }, { "epoch": 0.22, "grad_norm": 0.20358492809509288, "learning_rate": 7.052130619417192e-05, "loss": 1.5601, "step": 1478 }, { "epoch": 0.22, "grad_norm": 0.1722967696401652, "learning_rate": 7.050812710499341e-05, "loss": 1.5684, "step": 1479 }, { "epoch": 0.22, "grad_norm": 0.14801484555166847, "learning_rate": 7.049494801581492e-05, "loss": 1.5683, "step": 1480 }, { "epoch": 0.22, "grad_norm": 0.14707235536972355, "learning_rate": 7.048176892663641e-05, "loss": 1.5618, "step": 1481 }, { "epoch": 0.22, "grad_norm": 0.17503038537922339, "learning_rate": 7.04685898374579e-05, "loss": 1.5639, "step": 1482 }, { "epoch": 0.22, "grad_norm": 0.18686745881119146, "learning_rate": 7.04554107482794e-05, "loss": 1.5591, "step": 1483 }, { "epoch": 0.22, "grad_norm": 0.17060754128859854, "learning_rate": 7.044223165910089e-05, "loss": 1.567, "step": 1484 }, { "epoch": 0.22, "grad_norm": 0.16148218226752092, "learning_rate": 7.04290525699224e-05, "loss": 1.5624, "step": 1485 }, { "epoch": 0.22, "grad_norm": 0.12392433723907219, "learning_rate": 7.04158734807439e-05, "loss": 1.563, "step": 1486 }, { "epoch": 0.22, "grad_norm": 0.12980946855498254, "learning_rate": 7.040269439156539e-05, "loss": 1.5632, "step": 1487 }, { "epoch": 0.22, "grad_norm": 0.14339395974650324, "learning_rate": 7.038951530238688e-05, "loss": 1.5669, "step": 1488 }, { "epoch": 0.22, "grad_norm": 0.1448792621127726, "learning_rate": 7.037633621320839e-05, "loss": 1.5609, "step": 1489 }, { "epoch": 0.22, "grad_norm": 0.13553794582560605, "learning_rate": 7.036315712402987e-05, "loss": 1.5622, "step": 1490 }, { "epoch": 0.22, "grad_norm": 0.13575873572440034, "learning_rate": 7.034997803485138e-05, "loss": 1.562, "step": 1491 }, { "epoch": 0.22, "grad_norm": 0.16082133760741707, "learning_rate": 7.033679894567287e-05, "loss": 1.5603, "step": 1492 }, { "epoch": 0.22, "grad_norm": 0.17242897281518704, "learning_rate": 7.032361985649436e-05, "loss": 1.5694, "step": 1493 }, { "epoch": 0.22, "grad_norm": 0.18542150498618903, "learning_rate": 7.031044076731586e-05, "loss": 1.5732, "step": 1494 }, { "epoch": 0.22, "grad_norm": 0.19823017532318143, "learning_rate": 7.029726167813736e-05, "loss": 1.5587, "step": 1495 }, { "epoch": 0.22, "grad_norm": 0.1727625831103123, "learning_rate": 7.028408258895886e-05, "loss": 1.5661, "step": 1496 }, { "epoch": 0.22, "grad_norm": 0.14792025021664829, "learning_rate": 7.027090349978035e-05, "loss": 1.5613, "step": 1497 }, { "epoch": 0.22, "grad_norm": 0.14369828058714515, "learning_rate": 7.025772441060185e-05, "loss": 1.557, "step": 1498 }, { "epoch": 0.22, "grad_norm": 0.13415550412624946, "learning_rate": 7.024454532142334e-05, "loss": 1.5696, "step": 1499 }, { "epoch": 0.22, "grad_norm": 0.12605195451631998, "learning_rate": 7.023136623224485e-05, "loss": 1.5578, "step": 1500 }, { "epoch": 0.22, "grad_norm": 0.13889230083947712, "learning_rate": 7.021818714306634e-05, "loss": 1.556, "step": 1501 }, { "epoch": 0.22, "grad_norm": 0.1625570831758341, "learning_rate": 7.020500805388783e-05, "loss": 1.566, "step": 1502 }, { "epoch": 0.22, "grad_norm": 0.159051736431182, "learning_rate": 7.019182896470933e-05, "loss": 1.5681, "step": 1503 }, { "epoch": 0.22, "grad_norm": 0.1391939881062468, "learning_rate": 7.017864987553084e-05, "loss": 1.5636, "step": 1504 }, { "epoch": 0.22, "grad_norm": 0.12197288438358046, "learning_rate": 7.016547078635233e-05, "loss": 1.5666, "step": 1505 }, { "epoch": 0.22, "grad_norm": 0.15668727220869816, "learning_rate": 7.015229169717382e-05, "loss": 1.5656, "step": 1506 }, { "epoch": 0.22, "grad_norm": 0.20314314799885375, "learning_rate": 7.013911260799532e-05, "loss": 1.5607, "step": 1507 }, { "epoch": 0.22, "grad_norm": 0.22504397291844602, "learning_rate": 7.012593351881681e-05, "loss": 1.5525, "step": 1508 }, { "epoch": 0.22, "grad_norm": 0.20827134396232042, "learning_rate": 7.011275442963832e-05, "loss": 1.5645, "step": 1509 }, { "epoch": 0.22, "grad_norm": 0.16572765862670633, "learning_rate": 7.009957534045981e-05, "loss": 1.5626, "step": 1510 }, { "epoch": 0.22, "grad_norm": 0.14238041254108588, "learning_rate": 7.00863962512813e-05, "loss": 1.5617, "step": 1511 }, { "epoch": 0.22, "grad_norm": 0.14194615976277775, "learning_rate": 7.00732171621028e-05, "loss": 1.564, "step": 1512 }, { "epoch": 0.22, "grad_norm": 0.1746649614952692, "learning_rate": 7.00600380729243e-05, "loss": 1.5662, "step": 1513 }, { "epoch": 0.22, "grad_norm": 0.17817314772801265, "learning_rate": 7.004685898374579e-05, "loss": 1.5567, "step": 1514 }, { "epoch": 0.22, "grad_norm": 0.1627679458697912, "learning_rate": 7.00336798945673e-05, "loss": 1.5641, "step": 1515 }, { "epoch": 0.22, "grad_norm": 0.15787514391777924, "learning_rate": 7.002050080538879e-05, "loss": 1.5632, "step": 1516 }, { "epoch": 0.22, "grad_norm": 0.15767476971003588, "learning_rate": 7.000732171621028e-05, "loss": 1.5689, "step": 1517 }, { "epoch": 0.22, "grad_norm": 0.1597712748945363, "learning_rate": 6.999414262703177e-05, "loss": 1.5524, "step": 1518 }, { "epoch": 0.22, "grad_norm": 0.14274879675979987, "learning_rate": 6.998096353785328e-05, "loss": 1.5627, "step": 1519 }, { "epoch": 0.22, "grad_norm": 0.13862167988922744, "learning_rate": 6.996778444867478e-05, "loss": 1.5619, "step": 1520 }, { "epoch": 0.22, "grad_norm": 0.1504538492286387, "learning_rate": 6.995460535949627e-05, "loss": 1.5574, "step": 1521 }, { "epoch": 0.22, "grad_norm": 0.15973123245612725, "learning_rate": 6.994142627031776e-05, "loss": 1.5571, "step": 1522 }, { "epoch": 0.22, "grad_norm": 0.1451140351390426, "learning_rate": 6.992824718113926e-05, "loss": 1.5565, "step": 1523 }, { "epoch": 0.22, "grad_norm": 0.14241471019026736, "learning_rate": 6.991506809196076e-05, "loss": 1.5607, "step": 1524 }, { "epoch": 0.22, "grad_norm": 0.16554926350590574, "learning_rate": 6.990188900278226e-05, "loss": 1.5662, "step": 1525 }, { "epoch": 0.22, "grad_norm": 0.18782873264693847, "learning_rate": 6.988870991360375e-05, "loss": 1.5574, "step": 1526 }, { "epoch": 0.22, "grad_norm": 0.21976343522446412, "learning_rate": 6.987553082442525e-05, "loss": 1.5565, "step": 1527 }, { "epoch": 0.22, "grad_norm": 0.2202794534236301, "learning_rate": 6.986235173524675e-05, "loss": 1.5581, "step": 1528 }, { "epoch": 0.22, "grad_norm": 0.18906491039358303, "learning_rate": 6.984917264606825e-05, "loss": 1.5616, "step": 1529 }, { "epoch": 0.22, "grad_norm": 0.1917135397649, "learning_rate": 6.983599355688974e-05, "loss": 1.5685, "step": 1530 }, { "epoch": 0.22, "grad_norm": 0.22376646705566025, "learning_rate": 6.982281446771123e-05, "loss": 1.5546, "step": 1531 }, { "epoch": 0.22, "grad_norm": 0.2557629632843123, "learning_rate": 6.980963537853273e-05, "loss": 1.567, "step": 1532 }, { "epoch": 0.22, "grad_norm": 0.26264014512059436, "learning_rate": 6.979645628935422e-05, "loss": 1.5558, "step": 1533 }, { "epoch": 0.22, "grad_norm": 0.23630888222603547, "learning_rate": 6.978327720017573e-05, "loss": 1.5639, "step": 1534 }, { "epoch": 0.22, "grad_norm": 0.18781426785491603, "learning_rate": 6.977009811099722e-05, "loss": 1.5656, "step": 1535 }, { "epoch": 0.22, "grad_norm": 0.1350962887962464, "learning_rate": 6.975691902181872e-05, "loss": 1.5589, "step": 1536 }, { "epoch": 0.23, "grad_norm": 0.15163336603393449, "learning_rate": 6.974373993264022e-05, "loss": 1.5632, "step": 1537 }, { "epoch": 0.23, "grad_norm": 0.18782571169299847, "learning_rate": 6.97305608434617e-05, "loss": 1.5544, "step": 1538 }, { "epoch": 0.23, "grad_norm": 0.18238881835124143, "learning_rate": 6.971738175428321e-05, "loss": 1.5558, "step": 1539 }, { "epoch": 0.23, "grad_norm": 0.14843644500290679, "learning_rate": 6.97042026651047e-05, "loss": 1.5525, "step": 1540 }, { "epoch": 0.23, "grad_norm": 0.14966300924676834, "learning_rate": 6.96910235759262e-05, "loss": 1.5652, "step": 1541 }, { "epoch": 0.23, "grad_norm": 0.15599352551366935, "learning_rate": 6.967784448674769e-05, "loss": 1.5456, "step": 1542 }, { "epoch": 0.23, "grad_norm": 0.15698421958524125, "learning_rate": 6.96646653975692e-05, "loss": 1.5608, "step": 1543 }, { "epoch": 0.23, "grad_norm": 0.13827373140596677, "learning_rate": 6.96514863083907e-05, "loss": 1.5597, "step": 1544 }, { "epoch": 0.23, "grad_norm": 0.11917501235585805, "learning_rate": 6.963830721921219e-05, "loss": 1.5675, "step": 1545 }, { "epoch": 0.23, "grad_norm": 0.13790903649987726, "learning_rate": 6.962512813003368e-05, "loss": 1.553, "step": 1546 }, { "epoch": 0.23, "grad_norm": 0.1388510888327217, "learning_rate": 6.961194904085517e-05, "loss": 1.5513, "step": 1547 }, { "epoch": 0.23, "grad_norm": 0.14143505987201108, "learning_rate": 6.959876995167668e-05, "loss": 1.5677, "step": 1548 }, { "epoch": 0.23, "grad_norm": 0.12073834211466171, "learning_rate": 6.958559086249818e-05, "loss": 1.5603, "step": 1549 }, { "epoch": 0.23, "grad_norm": 0.11587208279760582, "learning_rate": 6.957241177331967e-05, "loss": 1.5601, "step": 1550 }, { "epoch": 0.23, "grad_norm": 0.13943580533691913, "learning_rate": 6.955923268414116e-05, "loss": 1.555, "step": 1551 }, { "epoch": 0.23, "grad_norm": 0.13699092615514738, "learning_rate": 6.954605359496267e-05, "loss": 1.5589, "step": 1552 }, { "epoch": 0.23, "grad_norm": 0.13830957900595023, "learning_rate": 6.953287450578416e-05, "loss": 1.5535, "step": 1553 }, { "epoch": 0.23, "grad_norm": 0.15082247073447994, "learning_rate": 6.951969541660566e-05, "loss": 1.5615, "step": 1554 }, { "epoch": 0.23, "grad_norm": 0.15495371687796394, "learning_rate": 6.950651632742715e-05, "loss": 1.5549, "step": 1555 }, { "epoch": 0.23, "grad_norm": 0.15437640247134612, "learning_rate": 6.949333723824865e-05, "loss": 1.5552, "step": 1556 }, { "epoch": 0.23, "grad_norm": 0.14173062168904724, "learning_rate": 6.948015814907014e-05, "loss": 1.5542, "step": 1557 }, { "epoch": 0.23, "grad_norm": 0.13055811798338282, "learning_rate": 6.946697905989165e-05, "loss": 1.5582, "step": 1558 }, { "epoch": 0.23, "grad_norm": 0.12438424333989716, "learning_rate": 6.945379997071314e-05, "loss": 1.5665, "step": 1559 }, { "epoch": 0.23, "grad_norm": 0.14003970899149606, "learning_rate": 6.944062088153463e-05, "loss": 1.5609, "step": 1560 }, { "epoch": 0.23, "grad_norm": 0.13391975312221754, "learning_rate": 6.942744179235614e-05, "loss": 1.5572, "step": 1561 }, { "epoch": 0.23, "grad_norm": 0.13832258206726172, "learning_rate": 6.941426270317762e-05, "loss": 1.5555, "step": 1562 }, { "epoch": 0.23, "grad_norm": 0.17016478039826613, "learning_rate": 6.940108361399913e-05, "loss": 1.5565, "step": 1563 }, { "epoch": 0.23, "grad_norm": 0.1906472940652705, "learning_rate": 6.938790452482062e-05, "loss": 1.5606, "step": 1564 }, { "epoch": 0.23, "grad_norm": 0.18395224804146684, "learning_rate": 6.937472543564212e-05, "loss": 1.5533, "step": 1565 }, { "epoch": 0.23, "grad_norm": 0.1670491650995815, "learning_rate": 6.936154634646361e-05, "loss": 1.5517, "step": 1566 }, { "epoch": 0.23, "grad_norm": 0.15203633399251587, "learning_rate": 6.934836725728512e-05, "loss": 1.5623, "step": 1567 }, { "epoch": 0.23, "grad_norm": 0.1386523723876345, "learning_rate": 6.933518816810661e-05, "loss": 1.5525, "step": 1568 }, { "epoch": 0.23, "grad_norm": 0.1397326756350934, "learning_rate": 6.93220090789281e-05, "loss": 1.5544, "step": 1569 }, { "epoch": 0.23, "grad_norm": 0.17255065922931825, "learning_rate": 6.93088299897496e-05, "loss": 1.559, "step": 1570 }, { "epoch": 0.23, "grad_norm": 0.20704283710173185, "learning_rate": 6.929565090057109e-05, "loss": 1.5569, "step": 1571 }, { "epoch": 0.23, "grad_norm": 0.19968959715172496, "learning_rate": 6.92824718113926e-05, "loss": 1.5478, "step": 1572 }, { "epoch": 0.23, "grad_norm": 0.19230184134704087, "learning_rate": 6.92692927222141e-05, "loss": 1.5503, "step": 1573 }, { "epoch": 0.23, "grad_norm": 0.18909160244964154, "learning_rate": 6.925611363303559e-05, "loss": 1.5544, "step": 1574 }, { "epoch": 0.23, "grad_norm": 0.16844303612647166, "learning_rate": 6.924293454385708e-05, "loss": 1.5571, "step": 1575 }, { "epoch": 0.23, "grad_norm": 0.17285965640836326, "learning_rate": 6.922975545467859e-05, "loss": 1.5548, "step": 1576 }, { "epoch": 0.23, "grad_norm": 0.17097045311532186, "learning_rate": 6.921657636550008e-05, "loss": 1.5581, "step": 1577 }, { "epoch": 0.23, "grad_norm": 0.15208574230500754, "learning_rate": 6.920339727632158e-05, "loss": 1.559, "step": 1578 }, { "epoch": 0.23, "grad_norm": 0.1302108613879427, "learning_rate": 6.919021818714307e-05, "loss": 1.5559, "step": 1579 }, { "epoch": 0.23, "grad_norm": 0.14151167716760873, "learning_rate": 6.917703909796456e-05, "loss": 1.5617, "step": 1580 }, { "epoch": 0.23, "grad_norm": 0.13644332890371155, "learning_rate": 6.916386000878606e-05, "loss": 1.5599, "step": 1581 }, { "epoch": 0.23, "grad_norm": 0.12156665440722327, "learning_rate": 6.915068091960756e-05, "loss": 1.5524, "step": 1582 }, { "epoch": 0.23, "grad_norm": 0.11782989442486515, "learning_rate": 6.913750183042906e-05, "loss": 1.5557, "step": 1583 }, { "epoch": 0.23, "grad_norm": 0.10458106948141914, "learning_rate": 6.912432274125055e-05, "loss": 1.5525, "step": 1584 }, { "epoch": 0.23, "grad_norm": 0.11610078372776365, "learning_rate": 6.911114365207206e-05, "loss": 1.556, "step": 1585 }, { "epoch": 0.23, "grad_norm": 0.11430857791497404, "learning_rate": 6.909796456289354e-05, "loss": 1.5505, "step": 1586 }, { "epoch": 0.23, "grad_norm": 0.1312092908514261, "learning_rate": 6.908478547371505e-05, "loss": 1.5501, "step": 1587 }, { "epoch": 0.23, "grad_norm": 0.12575919071416639, "learning_rate": 6.907160638453654e-05, "loss": 1.554, "step": 1588 }, { "epoch": 0.23, "grad_norm": 0.12565900631995755, "learning_rate": 6.905842729535803e-05, "loss": 1.5528, "step": 1589 }, { "epoch": 0.23, "grad_norm": 0.1161327185864553, "learning_rate": 6.904524820617953e-05, "loss": 1.5516, "step": 1590 }, { "epoch": 0.23, "grad_norm": 0.11177341146138027, "learning_rate": 6.903206911700103e-05, "loss": 1.5486, "step": 1591 }, { "epoch": 0.23, "grad_norm": 0.11905598040671617, "learning_rate": 6.901889002782253e-05, "loss": 1.5568, "step": 1592 }, { "epoch": 0.23, "grad_norm": 0.12616538195900687, "learning_rate": 6.900571093864402e-05, "loss": 1.5502, "step": 1593 }, { "epoch": 0.23, "grad_norm": 0.17498550189708104, "learning_rate": 6.899253184946552e-05, "loss": 1.5654, "step": 1594 }, { "epoch": 0.23, "grad_norm": 0.2130377460518065, "learning_rate": 6.897935276028701e-05, "loss": 1.5627, "step": 1595 }, { "epoch": 0.23, "grad_norm": 0.2423218366499862, "learning_rate": 6.896617367110852e-05, "loss": 1.5502, "step": 1596 }, { "epoch": 0.23, "grad_norm": 0.3065417363260542, "learning_rate": 6.895299458193001e-05, "loss": 1.5481, "step": 1597 }, { "epoch": 0.23, "grad_norm": 0.3362504924186193, "learning_rate": 6.89398154927515e-05, "loss": 1.5511, "step": 1598 }, { "epoch": 0.23, "grad_norm": 0.2602709928671128, "learning_rate": 6.8926636403573e-05, "loss": 1.5533, "step": 1599 }, { "epoch": 0.23, "grad_norm": 0.1706302921715801, "learning_rate": 6.89134573143945e-05, "loss": 1.5543, "step": 1600 }, { "epoch": 0.23, "grad_norm": 0.18696585801693164, "learning_rate": 6.8900278225216e-05, "loss": 1.5513, "step": 1601 }, { "epoch": 0.23, "grad_norm": 0.2425990608578436, "learning_rate": 6.888709913603749e-05, "loss": 1.5568, "step": 1602 }, { "epoch": 0.23, "grad_norm": 0.25557402179698885, "learning_rate": 6.887392004685899e-05, "loss": 1.5583, "step": 1603 }, { "epoch": 0.23, "grad_norm": 0.19254643621502684, "learning_rate": 6.886074095768048e-05, "loss": 1.5558, "step": 1604 }, { "epoch": 0.24, "grad_norm": 0.1501256773970859, "learning_rate": 6.884756186850197e-05, "loss": 1.5483, "step": 1605 }, { "epoch": 0.24, "grad_norm": 0.18027674327204868, "learning_rate": 6.883438277932348e-05, "loss": 1.5482, "step": 1606 }, { "epoch": 0.24, "grad_norm": 0.18512324904623811, "learning_rate": 6.882120369014498e-05, "loss": 1.5534, "step": 1607 }, { "epoch": 0.24, "grad_norm": 0.15350827244461232, "learning_rate": 6.880802460096647e-05, "loss": 1.5546, "step": 1608 }, { "epoch": 0.24, "grad_norm": 0.12508392755322637, "learning_rate": 6.879484551178798e-05, "loss": 1.5482, "step": 1609 }, { "epoch": 0.24, "grad_norm": 0.14046849983607992, "learning_rate": 6.878166642260946e-05, "loss": 1.5483, "step": 1610 }, { "epoch": 0.24, "grad_norm": 0.14867576282964143, "learning_rate": 6.876848733343096e-05, "loss": 1.5476, "step": 1611 }, { "epoch": 0.24, "grad_norm": 0.1450045504632268, "learning_rate": 6.875530824425246e-05, "loss": 1.5608, "step": 1612 }, { "epoch": 0.24, "grad_norm": 0.12586038081984513, "learning_rate": 6.874212915507395e-05, "loss": 1.5556, "step": 1613 }, { "epoch": 0.24, "grad_norm": 0.13415831883493776, "learning_rate": 6.872895006589545e-05, "loss": 1.5563, "step": 1614 }, { "epoch": 0.24, "grad_norm": 0.1582235400657942, "learning_rate": 6.871577097671695e-05, "loss": 1.5543, "step": 1615 }, { "epoch": 0.24, "grad_norm": 0.16607748843590825, "learning_rate": 6.870259188753845e-05, "loss": 1.5536, "step": 1616 }, { "epoch": 0.24, "grad_norm": 0.16098113359203, "learning_rate": 6.868941279835994e-05, "loss": 1.5499, "step": 1617 }, { "epoch": 0.24, "grad_norm": 0.1533723936762229, "learning_rate": 6.867623370918143e-05, "loss": 1.5559, "step": 1618 }, { "epoch": 0.24, "grad_norm": 0.1419677865844217, "learning_rate": 6.866305462000293e-05, "loss": 1.5563, "step": 1619 }, { "epoch": 0.24, "grad_norm": 0.12337679315639093, "learning_rate": 6.864987553082442e-05, "loss": 1.5566, "step": 1620 }, { "epoch": 0.24, "grad_norm": 0.14008735419243357, "learning_rate": 6.863669644164593e-05, "loss": 1.5504, "step": 1621 }, { "epoch": 0.24, "grad_norm": 0.15354721125578877, "learning_rate": 6.862351735246742e-05, "loss": 1.5548, "step": 1622 }, { "epoch": 0.24, "grad_norm": 0.13722359030310177, "learning_rate": 6.861033826328892e-05, "loss": 1.5523, "step": 1623 }, { "epoch": 0.24, "grad_norm": 0.11942493175369336, "learning_rate": 6.859715917411042e-05, "loss": 1.5501, "step": 1624 }, { "epoch": 0.24, "grad_norm": 0.12604318775555223, "learning_rate": 6.858398008493192e-05, "loss": 1.5498, "step": 1625 }, { "epoch": 0.24, "grad_norm": 0.13370239925321337, "learning_rate": 6.857080099575341e-05, "loss": 1.559, "step": 1626 }, { "epoch": 0.24, "grad_norm": 0.12637856740613754, "learning_rate": 6.85576219065749e-05, "loss": 1.5547, "step": 1627 }, { "epoch": 0.24, "grad_norm": 0.12061462620393058, "learning_rate": 6.85444428173964e-05, "loss": 1.5455, "step": 1628 }, { "epoch": 0.24, "grad_norm": 0.13680049491771548, "learning_rate": 6.853126372821789e-05, "loss": 1.5471, "step": 1629 }, { "epoch": 0.24, "grad_norm": 0.14078602589632402, "learning_rate": 6.85180846390394e-05, "loss": 1.5499, "step": 1630 }, { "epoch": 0.24, "grad_norm": 0.14022146866088356, "learning_rate": 6.850490554986089e-05, "loss": 1.5475, "step": 1631 }, { "epoch": 0.24, "grad_norm": 0.15892178667718265, "learning_rate": 6.849172646068239e-05, "loss": 1.5415, "step": 1632 }, { "epoch": 0.24, "grad_norm": 0.15771824336327828, "learning_rate": 6.84785473715039e-05, "loss": 1.5491, "step": 1633 }, { "epoch": 0.24, "grad_norm": 0.15431553280773133, "learning_rate": 6.846536828232537e-05, "loss": 1.5538, "step": 1634 }, { "epoch": 0.24, "grad_norm": 0.146165745873896, "learning_rate": 6.845218919314688e-05, "loss": 1.5469, "step": 1635 }, { "epoch": 0.24, "grad_norm": 0.14787594181143815, "learning_rate": 6.843901010396838e-05, "loss": 1.5432, "step": 1636 }, { "epoch": 0.24, "grad_norm": 0.15702479363803623, "learning_rate": 6.842583101478987e-05, "loss": 1.5484, "step": 1637 }, { "epoch": 0.24, "grad_norm": 0.16689851495876992, "learning_rate": 6.841265192561136e-05, "loss": 1.552, "step": 1638 }, { "epoch": 0.24, "grad_norm": 0.1848572151341898, "learning_rate": 6.839947283643287e-05, "loss": 1.5525, "step": 1639 }, { "epoch": 0.24, "grad_norm": 0.1985667992824036, "learning_rate": 6.838629374725436e-05, "loss": 1.5527, "step": 1640 }, { "epoch": 0.24, "grad_norm": 0.19685054777178346, "learning_rate": 6.837311465807586e-05, "loss": 1.5566, "step": 1641 }, { "epoch": 0.24, "grad_norm": 0.17302806445483987, "learning_rate": 6.835993556889735e-05, "loss": 1.5552, "step": 1642 }, { "epoch": 0.24, "grad_norm": 0.1624047549497897, "learning_rate": 6.834675647971884e-05, "loss": 1.551, "step": 1643 }, { "epoch": 0.24, "grad_norm": 0.1541815338981589, "learning_rate": 6.833357739054034e-05, "loss": 1.5536, "step": 1644 }, { "epoch": 0.24, "grad_norm": 0.14690832457803973, "learning_rate": 6.832039830136185e-05, "loss": 1.5556, "step": 1645 }, { "epoch": 0.24, "grad_norm": 0.14114554865450257, "learning_rate": 6.830721921218334e-05, "loss": 1.5574, "step": 1646 }, { "epoch": 0.24, "grad_norm": 0.1374618278492853, "learning_rate": 6.829404012300483e-05, "loss": 1.5473, "step": 1647 }, { "epoch": 0.24, "grad_norm": 0.16334798339082507, "learning_rate": 6.828086103382634e-05, "loss": 1.5436, "step": 1648 }, { "epoch": 0.24, "grad_norm": 0.17823021166295652, "learning_rate": 6.826768194464783e-05, "loss": 1.5526, "step": 1649 }, { "epoch": 0.24, "grad_norm": 0.16491821517268068, "learning_rate": 6.825450285546933e-05, "loss": 1.5448, "step": 1650 }, { "epoch": 0.24, "grad_norm": 0.14340839944429526, "learning_rate": 6.824132376629082e-05, "loss": 1.5555, "step": 1651 }, { "epoch": 0.24, "grad_norm": 0.14459695445995016, "learning_rate": 6.822814467711232e-05, "loss": 1.5491, "step": 1652 }, { "epoch": 0.24, "grad_norm": 0.14087318597895018, "learning_rate": 6.821496558793381e-05, "loss": 1.5514, "step": 1653 }, { "epoch": 0.24, "grad_norm": 0.13530581550555565, "learning_rate": 6.820178649875532e-05, "loss": 1.5493, "step": 1654 }, { "epoch": 0.24, "grad_norm": 0.12914300472200602, "learning_rate": 6.818860740957681e-05, "loss": 1.5502, "step": 1655 }, { "epoch": 0.24, "grad_norm": 0.14791075998576286, "learning_rate": 6.81754283203983e-05, "loss": 1.5527, "step": 1656 }, { "epoch": 0.24, "grad_norm": 0.15767032298140526, "learning_rate": 6.816224923121981e-05, "loss": 1.5507, "step": 1657 }, { "epoch": 0.24, "grad_norm": 0.15762124335406885, "learning_rate": 6.814907014204129e-05, "loss": 1.5472, "step": 1658 }, { "epoch": 0.24, "grad_norm": 0.15770761252048401, "learning_rate": 6.81358910528628e-05, "loss": 1.5504, "step": 1659 }, { "epoch": 0.24, "grad_norm": 0.14539977323851627, "learning_rate": 6.812271196368429e-05, "loss": 1.5416, "step": 1660 }, { "epoch": 0.24, "grad_norm": 0.1360839511514339, "learning_rate": 6.810953287450579e-05, "loss": 1.5448, "step": 1661 }, { "epoch": 0.24, "grad_norm": 0.14633674426067697, "learning_rate": 6.809635378532728e-05, "loss": 1.5532, "step": 1662 }, { "epoch": 0.24, "grad_norm": 0.15741046997567085, "learning_rate": 6.808317469614879e-05, "loss": 1.5496, "step": 1663 }, { "epoch": 0.24, "grad_norm": 0.15335271399063555, "learning_rate": 6.806999560697028e-05, "loss": 1.5475, "step": 1664 }, { "epoch": 0.24, "grad_norm": 0.17257629000740207, "learning_rate": 6.805681651779178e-05, "loss": 1.5563, "step": 1665 }, { "epoch": 0.24, "grad_norm": 0.16040574818475473, "learning_rate": 6.804363742861327e-05, "loss": 1.5491, "step": 1666 }, { "epoch": 0.24, "grad_norm": 0.12827580813406658, "learning_rate": 6.803045833943476e-05, "loss": 1.5484, "step": 1667 }, { "epoch": 0.24, "grad_norm": 0.137000939385371, "learning_rate": 6.801727925025626e-05, "loss": 1.5539, "step": 1668 }, { "epoch": 0.24, "grad_norm": 0.14792870207776196, "learning_rate": 6.800410016107776e-05, "loss": 1.5398, "step": 1669 }, { "epoch": 0.24, "grad_norm": 0.13377235683031535, "learning_rate": 6.799092107189926e-05, "loss": 1.5506, "step": 1670 }, { "epoch": 0.24, "grad_norm": 0.12524350688472186, "learning_rate": 6.797774198272075e-05, "loss": 1.5477, "step": 1671 }, { "epoch": 0.24, "grad_norm": 0.1375908850825439, "learning_rate": 6.796456289354226e-05, "loss": 1.5516, "step": 1672 }, { "epoch": 0.24, "grad_norm": 0.16872797756026237, "learning_rate": 6.795138380436375e-05, "loss": 1.5524, "step": 1673 }, { "epoch": 0.25, "grad_norm": 0.17255656413666468, "learning_rate": 6.793820471518525e-05, "loss": 1.5519, "step": 1674 }, { "epoch": 0.25, "grad_norm": 0.15649581350662647, "learning_rate": 6.792502562600674e-05, "loss": 1.545, "step": 1675 }, { "epoch": 0.25, "grad_norm": 0.14603954181759182, "learning_rate": 6.791184653682823e-05, "loss": 1.5354, "step": 1676 }, { "epoch": 0.25, "grad_norm": 0.14996652222064816, "learning_rate": 6.789866744764973e-05, "loss": 1.5462, "step": 1677 }, { "epoch": 0.25, "grad_norm": 0.14098612021083787, "learning_rate": 6.788548835847123e-05, "loss": 1.5463, "step": 1678 }, { "epoch": 0.25, "grad_norm": 0.13786176118009635, "learning_rate": 6.787230926929273e-05, "loss": 1.55, "step": 1679 }, { "epoch": 0.25, "grad_norm": 0.15617176658263263, "learning_rate": 6.785913018011422e-05, "loss": 1.5469, "step": 1680 }, { "epoch": 0.25, "grad_norm": 0.1879698889780054, "learning_rate": 6.784595109093573e-05, "loss": 1.5485, "step": 1681 }, { "epoch": 0.25, "grad_norm": 0.22122586221883833, "learning_rate": 6.783277200175721e-05, "loss": 1.5461, "step": 1682 }, { "epoch": 0.25, "grad_norm": 0.22292103720296774, "learning_rate": 6.781959291257872e-05, "loss": 1.5543, "step": 1683 }, { "epoch": 0.25, "grad_norm": 0.1736273162608752, "learning_rate": 6.780641382340021e-05, "loss": 1.5501, "step": 1684 }, { "epoch": 0.25, "grad_norm": 0.11509864784919802, "learning_rate": 6.77932347342217e-05, "loss": 1.5532, "step": 1685 }, { "epoch": 0.25, "grad_norm": 0.12708499410489232, "learning_rate": 6.77800556450432e-05, "loss": 1.5358, "step": 1686 }, { "epoch": 0.25, "grad_norm": 0.17299827793930234, "learning_rate": 6.77668765558647e-05, "loss": 1.5481, "step": 1687 }, { "epoch": 0.25, "grad_norm": 0.1822316133159184, "learning_rate": 6.77536974666862e-05, "loss": 1.5497, "step": 1688 }, { "epoch": 0.25, "grad_norm": 0.17414788070503254, "learning_rate": 6.774051837750769e-05, "loss": 1.5487, "step": 1689 }, { "epoch": 0.25, "grad_norm": 0.15984217459846126, "learning_rate": 6.772733928832919e-05, "loss": 1.5434, "step": 1690 }, { "epoch": 0.25, "grad_norm": 0.1542107562856, "learning_rate": 6.771416019915068e-05, "loss": 1.5508, "step": 1691 }, { "epoch": 0.25, "grad_norm": 0.16229994239377557, "learning_rate": 6.770098110997217e-05, "loss": 1.5489, "step": 1692 }, { "epoch": 0.25, "grad_norm": 0.1546526960370925, "learning_rate": 6.768780202079368e-05, "loss": 1.5499, "step": 1693 }, { "epoch": 0.25, "grad_norm": 0.12279914387612359, "learning_rate": 6.767462293161517e-05, "loss": 1.5427, "step": 1694 }, { "epoch": 0.25, "grad_norm": 0.12975757335563615, "learning_rate": 6.766144384243667e-05, "loss": 1.5467, "step": 1695 }, { "epoch": 0.25, "grad_norm": 0.13422122080467072, "learning_rate": 6.764826475325818e-05, "loss": 1.5554, "step": 1696 }, { "epoch": 0.25, "grad_norm": 0.14192591482733333, "learning_rate": 6.763508566407967e-05, "loss": 1.5408, "step": 1697 }, { "epoch": 0.25, "grad_norm": 0.13893637523732244, "learning_rate": 6.762190657490116e-05, "loss": 1.5495, "step": 1698 }, { "epoch": 0.25, "grad_norm": 0.15491412035183788, "learning_rate": 6.760872748572266e-05, "loss": 1.5501, "step": 1699 }, { "epoch": 0.25, "grad_norm": 0.17883988461434905, "learning_rate": 6.759554839654415e-05, "loss": 1.5503, "step": 1700 }, { "epoch": 0.25, "grad_norm": 0.20265371705570628, "learning_rate": 6.758236930736564e-05, "loss": 1.5361, "step": 1701 }, { "epoch": 0.25, "grad_norm": 0.2139359712926301, "learning_rate": 6.756919021818715e-05, "loss": 1.5381, "step": 1702 }, { "epoch": 0.25, "grad_norm": 0.18614804141636146, "learning_rate": 6.755601112900865e-05, "loss": 1.5482, "step": 1703 }, { "epoch": 0.25, "grad_norm": 0.15804041466228397, "learning_rate": 6.754283203983014e-05, "loss": 1.5361, "step": 1704 }, { "epoch": 0.25, "grad_norm": 0.15062690335608622, "learning_rate": 6.752965295065165e-05, "loss": 1.5455, "step": 1705 }, { "epoch": 0.25, "grad_norm": 0.12443563823484106, "learning_rate": 6.751647386147313e-05, "loss": 1.5435, "step": 1706 }, { "epoch": 0.25, "grad_norm": 0.14089290268248464, "learning_rate": 6.750329477229462e-05, "loss": 1.5403, "step": 1707 }, { "epoch": 0.25, "grad_norm": 0.1550833858910459, "learning_rate": 6.749011568311613e-05, "loss": 1.5505, "step": 1708 }, { "epoch": 0.25, "grad_norm": 0.149359947538185, "learning_rate": 6.747693659393762e-05, "loss": 1.5469, "step": 1709 }, { "epoch": 0.25, "grad_norm": 0.15937266282828347, "learning_rate": 6.746375750475912e-05, "loss": 1.5419, "step": 1710 }, { "epoch": 0.25, "grad_norm": 0.1631750053650106, "learning_rate": 6.745057841558062e-05, "loss": 1.5399, "step": 1711 }, { "epoch": 0.25, "grad_norm": 0.14972740561419975, "learning_rate": 6.743739932640212e-05, "loss": 1.5528, "step": 1712 }, { "epoch": 0.25, "grad_norm": 0.1587005414140819, "learning_rate": 6.742422023722361e-05, "loss": 1.5471, "step": 1713 }, { "epoch": 0.25, "grad_norm": 0.16023087202413147, "learning_rate": 6.74110411480451e-05, "loss": 1.55, "step": 1714 }, { "epoch": 0.25, "grad_norm": 0.1507360827043738, "learning_rate": 6.73978620588666e-05, "loss": 1.5436, "step": 1715 }, { "epoch": 0.25, "grad_norm": 0.1447030944327568, "learning_rate": 6.738468296968809e-05, "loss": 1.5498, "step": 1716 }, { "epoch": 0.25, "grad_norm": 0.12385411311009659, "learning_rate": 6.73715038805096e-05, "loss": 1.5518, "step": 1717 }, { "epoch": 0.25, "grad_norm": 0.1164550428705913, "learning_rate": 6.735832479133109e-05, "loss": 1.5425, "step": 1718 }, { "epoch": 0.25, "grad_norm": 0.13629614084783107, "learning_rate": 6.734514570215259e-05, "loss": 1.5511, "step": 1719 }, { "epoch": 0.25, "grad_norm": 0.1506489926079727, "learning_rate": 6.73319666129741e-05, "loss": 1.5419, "step": 1720 }, { "epoch": 0.25, "grad_norm": 0.13855334627153476, "learning_rate": 6.731878752379559e-05, "loss": 1.5484, "step": 1721 }, { "epoch": 0.25, "grad_norm": 0.12832134059259032, "learning_rate": 6.730560843461708e-05, "loss": 1.5398, "step": 1722 }, { "epoch": 0.25, "grad_norm": 0.12090987219413707, "learning_rate": 6.729242934543857e-05, "loss": 1.5402, "step": 1723 }, { "epoch": 0.25, "grad_norm": 0.11453651059207949, "learning_rate": 6.727925025626007e-05, "loss": 1.5506, "step": 1724 }, { "epoch": 0.25, "grad_norm": 0.1196098497984597, "learning_rate": 6.726607116708156e-05, "loss": 1.5451, "step": 1725 }, { "epoch": 0.25, "grad_norm": 0.11367821126555626, "learning_rate": 6.725289207790307e-05, "loss": 1.5503, "step": 1726 }, { "epoch": 0.25, "grad_norm": 0.10401603162688644, "learning_rate": 6.723971298872456e-05, "loss": 1.5495, "step": 1727 }, { "epoch": 0.25, "grad_norm": 0.10956859510139251, "learning_rate": 6.722653389954606e-05, "loss": 1.5462, "step": 1728 }, { "epoch": 0.25, "grad_norm": 0.11932498061521109, "learning_rate": 6.721335481036756e-05, "loss": 1.5457, "step": 1729 }, { "epoch": 0.25, "grad_norm": 0.12531582645142714, "learning_rate": 6.720017572118904e-05, "loss": 1.5492, "step": 1730 }, { "epoch": 0.25, "grad_norm": 0.12833505710933477, "learning_rate": 6.718699663201054e-05, "loss": 1.5456, "step": 1731 }, { "epoch": 0.25, "grad_norm": 0.14072231726948428, "learning_rate": 6.717381754283205e-05, "loss": 1.5498, "step": 1732 }, { "epoch": 0.25, "grad_norm": 0.16831541592684482, "learning_rate": 6.716063845365354e-05, "loss": 1.5558, "step": 1733 }, { "epoch": 0.25, "grad_norm": 0.2093135547333804, "learning_rate": 6.714745936447503e-05, "loss": 1.5606, "step": 1734 }, { "epoch": 0.25, "grad_norm": 0.22413912594550753, "learning_rate": 6.713428027529654e-05, "loss": 1.5515, "step": 1735 }, { "epoch": 0.25, "grad_norm": 0.21448251347724995, "learning_rate": 6.712110118611803e-05, "loss": 1.5362, "step": 1736 }, { "epoch": 0.25, "grad_norm": 0.20678506449185255, "learning_rate": 6.710792209693953e-05, "loss": 1.5395, "step": 1737 }, { "epoch": 0.25, "grad_norm": 0.19348081818742874, "learning_rate": 6.709474300776102e-05, "loss": 1.5459, "step": 1738 }, { "epoch": 0.25, "grad_norm": 0.19216843244188353, "learning_rate": 6.708156391858252e-05, "loss": 1.5361, "step": 1739 }, { "epoch": 0.25, "grad_norm": 0.1950956680007854, "learning_rate": 6.706838482940401e-05, "loss": 1.5451, "step": 1740 }, { "epoch": 0.25, "grad_norm": 0.18065563157921122, "learning_rate": 6.705520574022552e-05, "loss": 1.535, "step": 1741 }, { "epoch": 0.26, "grad_norm": 0.1724051176877015, "learning_rate": 6.704202665104701e-05, "loss": 1.543, "step": 1742 }, { "epoch": 0.26, "grad_norm": 0.16492687488657337, "learning_rate": 6.70288475618685e-05, "loss": 1.5386, "step": 1743 }, { "epoch": 0.26, "grad_norm": 0.1713929297928792, "learning_rate": 6.701566847269001e-05, "loss": 1.541, "step": 1744 }, { "epoch": 0.26, "grad_norm": 0.17209785450990964, "learning_rate": 6.70024893835115e-05, "loss": 1.5393, "step": 1745 }, { "epoch": 0.26, "grad_norm": 0.12260311659465224, "learning_rate": 6.6989310294333e-05, "loss": 1.542, "step": 1746 }, { "epoch": 0.26, "grad_norm": 0.11796151518037762, "learning_rate": 6.697613120515449e-05, "loss": 1.546, "step": 1747 }, { "epoch": 0.26, "grad_norm": 0.14676550674762198, "learning_rate": 6.696295211597599e-05, "loss": 1.5407, "step": 1748 }, { "epoch": 0.26, "grad_norm": 0.14285664313926463, "learning_rate": 6.694977302679748e-05, "loss": 1.5432, "step": 1749 }, { "epoch": 0.26, "grad_norm": 0.15040983251816017, "learning_rate": 6.693659393761899e-05, "loss": 1.5471, "step": 1750 }, { "epoch": 0.26, "grad_norm": 0.14155615679807018, "learning_rate": 6.692341484844048e-05, "loss": 1.5444, "step": 1751 }, { "epoch": 0.26, "grad_norm": 0.12521018590917282, "learning_rate": 6.691023575926197e-05, "loss": 1.5415, "step": 1752 }, { "epoch": 0.26, "grad_norm": 0.1483724473478806, "learning_rate": 6.689705667008348e-05, "loss": 1.5462, "step": 1753 }, { "epoch": 0.26, "grad_norm": 0.16302152525308417, "learning_rate": 6.688387758090496e-05, "loss": 1.5435, "step": 1754 }, { "epoch": 0.26, "grad_norm": 0.1593150408912617, "learning_rate": 6.687069849172646e-05, "loss": 1.5455, "step": 1755 }, { "epoch": 0.26, "grad_norm": 0.15798766607610612, "learning_rate": 6.685751940254796e-05, "loss": 1.5424, "step": 1756 }, { "epoch": 0.26, "grad_norm": 0.15509643681103627, "learning_rate": 6.684434031336946e-05, "loss": 1.5474, "step": 1757 }, { "epoch": 0.26, "grad_norm": 0.15042707266000108, "learning_rate": 6.683116122419095e-05, "loss": 1.5386, "step": 1758 }, { "epoch": 0.26, "grad_norm": 0.12529483918638012, "learning_rate": 6.681798213501246e-05, "loss": 1.5483, "step": 1759 }, { "epoch": 0.26, "grad_norm": 0.16020600612445207, "learning_rate": 6.680480304583395e-05, "loss": 1.545, "step": 1760 }, { "epoch": 0.26, "grad_norm": 0.17365135713154362, "learning_rate": 6.679162395665545e-05, "loss": 1.5399, "step": 1761 }, { "epoch": 0.26, "grad_norm": 0.15617117207014766, "learning_rate": 6.677844486747694e-05, "loss": 1.5417, "step": 1762 }, { "epoch": 0.26, "grad_norm": 0.1826268055689078, "learning_rate": 6.676526577829843e-05, "loss": 1.5356, "step": 1763 }, { "epoch": 0.26, "grad_norm": 0.1792955657441501, "learning_rate": 6.675208668911993e-05, "loss": 1.5409, "step": 1764 }, { "epoch": 0.26, "grad_norm": 0.1549319116339377, "learning_rate": 6.673890759994143e-05, "loss": 1.5425, "step": 1765 }, { "epoch": 0.26, "grad_norm": 0.16797264760156416, "learning_rate": 6.672572851076293e-05, "loss": 1.5472, "step": 1766 }, { "epoch": 0.26, "grad_norm": 0.1689579541348412, "learning_rate": 6.671254942158442e-05, "loss": 1.5333, "step": 1767 }, { "epoch": 0.26, "grad_norm": 0.1443581888928475, "learning_rate": 6.669937033240593e-05, "loss": 1.549, "step": 1768 }, { "epoch": 0.26, "grad_norm": 0.12295030770476027, "learning_rate": 6.668619124322742e-05, "loss": 1.5471, "step": 1769 }, { "epoch": 0.26, "grad_norm": 0.14316536012437356, "learning_rate": 6.66730121540489e-05, "loss": 1.5388, "step": 1770 }, { "epoch": 0.26, "grad_norm": 0.16946707074936326, "learning_rate": 6.665983306487041e-05, "loss": 1.5449, "step": 1771 }, { "epoch": 0.26, "grad_norm": 0.19183626388609665, "learning_rate": 6.66466539756919e-05, "loss": 1.5525, "step": 1772 }, { "epoch": 0.26, "grad_norm": 0.17394581389516967, "learning_rate": 6.66334748865134e-05, "loss": 1.5455, "step": 1773 }, { "epoch": 0.26, "grad_norm": 0.13796787925409335, "learning_rate": 6.66202957973349e-05, "loss": 1.5453, "step": 1774 }, { "epoch": 0.26, "grad_norm": 0.14737682661347665, "learning_rate": 6.66071167081564e-05, "loss": 1.5383, "step": 1775 }, { "epoch": 0.26, "grad_norm": 0.1622449698758281, "learning_rate": 6.659393761897789e-05, "loss": 1.5412, "step": 1776 }, { "epoch": 0.26, "grad_norm": 0.16064176456627283, "learning_rate": 6.65807585297994e-05, "loss": 1.5452, "step": 1777 }, { "epoch": 0.26, "grad_norm": 0.15131456902589685, "learning_rate": 6.656757944062088e-05, "loss": 1.5393, "step": 1778 }, { "epoch": 0.26, "grad_norm": 0.1529436529522335, "learning_rate": 6.655440035144237e-05, "loss": 1.5382, "step": 1779 }, { "epoch": 0.26, "grad_norm": 0.15466089796538804, "learning_rate": 6.654122126226388e-05, "loss": 1.5321, "step": 1780 }, { "epoch": 0.26, "grad_norm": 0.13648831163966982, "learning_rate": 6.652804217308537e-05, "loss": 1.5435, "step": 1781 }, { "epoch": 0.26, "grad_norm": 0.13571229687876288, "learning_rate": 6.651486308390687e-05, "loss": 1.5326, "step": 1782 }, { "epoch": 0.26, "grad_norm": 0.14664723920130965, "learning_rate": 6.650168399472838e-05, "loss": 1.541, "step": 1783 }, { "epoch": 0.26, "grad_norm": 0.1322498917434933, "learning_rate": 6.648850490554987e-05, "loss": 1.5401, "step": 1784 }, { "epoch": 0.26, "grad_norm": 0.1157193538823997, "learning_rate": 6.647532581637136e-05, "loss": 1.5438, "step": 1785 }, { "epoch": 0.26, "grad_norm": 0.12401343440978063, "learning_rate": 6.646214672719286e-05, "loss": 1.537, "step": 1786 }, { "epoch": 0.26, "grad_norm": 0.13123152593043114, "learning_rate": 6.644896763801435e-05, "loss": 1.5407, "step": 1787 }, { "epoch": 0.26, "grad_norm": 0.1471707795413792, "learning_rate": 6.643578854883584e-05, "loss": 1.534, "step": 1788 }, { "epoch": 0.26, "grad_norm": 0.14848671197739402, "learning_rate": 6.642260945965735e-05, "loss": 1.5409, "step": 1789 }, { "epoch": 0.26, "grad_norm": 0.14341236634610707, "learning_rate": 6.640943037047885e-05, "loss": 1.5421, "step": 1790 }, { "epoch": 0.26, "grad_norm": 0.1326356379910537, "learning_rate": 6.639625128130034e-05, "loss": 1.5427, "step": 1791 }, { "epoch": 0.26, "grad_norm": 0.1223557409627182, "learning_rate": 6.638307219212185e-05, "loss": 1.5473, "step": 1792 }, { "epoch": 0.26, "grad_norm": 0.13155912571100425, "learning_rate": 6.636989310294334e-05, "loss": 1.5307, "step": 1793 }, { "epoch": 0.26, "grad_norm": 0.15378406626616598, "learning_rate": 6.635671401376482e-05, "loss": 1.5412, "step": 1794 }, { "epoch": 0.26, "grad_norm": 0.1479907048479965, "learning_rate": 6.634353492458633e-05, "loss": 1.5376, "step": 1795 }, { "epoch": 0.26, "grad_norm": 0.13370072014639775, "learning_rate": 6.633035583540782e-05, "loss": 1.5416, "step": 1796 }, { "epoch": 0.26, "grad_norm": 0.12079769907305982, "learning_rate": 6.631717674622931e-05, "loss": 1.5436, "step": 1797 }, { "epoch": 0.26, "grad_norm": 0.13715067412054485, "learning_rate": 6.630399765705082e-05, "loss": 1.5505, "step": 1798 }, { "epoch": 0.26, "grad_norm": 0.13862894618039118, "learning_rate": 6.629081856787232e-05, "loss": 1.5425, "step": 1799 }, { "epoch": 0.26, "grad_norm": 0.14258297871949263, "learning_rate": 6.627763947869381e-05, "loss": 1.5469, "step": 1800 }, { "epoch": 0.26, "eval_loss": 1.5050686597824097, "eval_runtime": 446.284, "eval_samples_per_second": 40.367, "eval_steps_per_second": 0.06, "step": 1800 } ], "logging_steps": 1, "max_steps": 6829, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 900, "total_flos": 4.267710225580032e+16, "train_batch_size": 42, "trial_name": null, "trial_params": null }