{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 5198, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "grad_norm": 5.272869393159265, "learning_rate": 1.282051282051282e-07, "loss": 1.1497, "step": 1 }, { "epoch": 0.0, "grad_norm": 4.028482960509657, "learning_rate": 2.564102564102564e-07, "loss": 0.8915, "step": 2 }, { "epoch": 0.0, "grad_norm": 6.441400103453322, "learning_rate": 3.846153846153847e-07, "loss": 1.3682, "step": 3 }, { "epoch": 0.0, "grad_norm": 5.690008511528528, "learning_rate": 5.128205128205128e-07, "loss": 1.3599, "step": 4 }, { "epoch": 0.0, "grad_norm": 6.730256837241916, "learning_rate": 6.41025641025641e-07, "loss": 1.3572, "step": 5 }, { "epoch": 0.0, "grad_norm": 5.930110009159658, "learning_rate": 7.692307692307694e-07, "loss": 1.3066, "step": 6 }, { "epoch": 0.0, "grad_norm": 6.80482958394566, "learning_rate": 8.974358974358975e-07, "loss": 1.4712, "step": 7 }, { "epoch": 0.0, "grad_norm": 6.579309639988835, "learning_rate": 1.0256410256410257e-06, "loss": 1.4775, "step": 8 }, { "epoch": 0.0, "grad_norm": 2.3996758487032075, "learning_rate": 1.153846153846154e-06, "loss": 0.8304, "step": 9 }, { "epoch": 0.0, "grad_norm": 4.701573071479006, "learning_rate": 1.282051282051282e-06, "loss": 1.2959, "step": 10 }, { "epoch": 0.0, "grad_norm": 4.8642964188292614, "learning_rate": 1.4102564102564104e-06, "loss": 1.3467, "step": 11 }, { "epoch": 0.0, "grad_norm": 4.43526218799144, "learning_rate": 1.5384615384615387e-06, "loss": 1.3403, "step": 12 }, { "epoch": 0.0, "grad_norm": 1.8550781717298401, "learning_rate": 1.6666666666666667e-06, "loss": 0.8266, "step": 13 }, { "epoch": 0.0, "grad_norm": 3.585601122876213, "learning_rate": 1.794871794871795e-06, "loss": 1.3257, "step": 14 }, { "epoch": 0.0, "grad_norm": 2.9413062834755155, "learning_rate": 1.9230769230769234e-06, "loss": 1.2998, "step": 15 }, { "epoch": 0.0, "grad_norm": 2.6798459616482853, "learning_rate": 2.0512820512820513e-06, "loss": 1.2134, "step": 16 }, { "epoch": 0.0, "grad_norm": 2.5137780070036944, "learning_rate": 2.1794871794871797e-06, "loss": 1.2476, "step": 17 }, { "epoch": 0.0, "grad_norm": 2.001379466789297, "learning_rate": 2.307692307692308e-06, "loss": 1.1746, "step": 18 }, { "epoch": 0.0, "grad_norm": 2.1102846374208863, "learning_rate": 2.435897435897436e-06, "loss": 1.1733, "step": 19 }, { "epoch": 0.0, "grad_norm": 2.147872830658793, "learning_rate": 2.564102564102564e-06, "loss": 1.1819, "step": 20 }, { "epoch": 0.0, "grad_norm": 1.9389239878253899, "learning_rate": 2.6923076923076923e-06, "loss": 1.1907, "step": 21 }, { "epoch": 0.0, "grad_norm": 1.9645695959590523, "learning_rate": 2.8205128205128207e-06, "loss": 1.156, "step": 22 }, { "epoch": 0.0, "grad_norm": 1.921692739737611, "learning_rate": 2.948717948717949e-06, "loss": 1.1345, "step": 23 }, { "epoch": 0.0, "grad_norm": 1.9662501106441028, "learning_rate": 3.0769230769230774e-06, "loss": 1.1553, "step": 24 }, { "epoch": 0.0, "grad_norm": 1.4525083270353352, "learning_rate": 3.205128205128206e-06, "loss": 0.8009, "step": 25 }, { "epoch": 0.01, "grad_norm": 1.6522053357356288, "learning_rate": 3.3333333333333333e-06, "loss": 1.1113, "step": 26 }, { "epoch": 0.01, "grad_norm": 1.6754362758826138, "learning_rate": 3.4615384615384617e-06, "loss": 1.1338, "step": 27 }, { "epoch": 0.01, "grad_norm": 1.7514565757171334, "learning_rate": 3.58974358974359e-06, "loss": 1.1609, "step": 28 }, { "epoch": 0.01, "grad_norm": 1.2317795969071326, "learning_rate": 3.7179487179487184e-06, "loss": 0.6268, "step": 29 }, { "epoch": 0.01, "grad_norm": 1.7835722036810548, "learning_rate": 3.846153846153847e-06, "loss": 1.1392, "step": 30 }, { "epoch": 0.01, "grad_norm": 1.7016502867183958, "learning_rate": 3.974358974358974e-06, "loss": 1.1143, "step": 31 }, { "epoch": 0.01, "grad_norm": 1.6854535289169768, "learning_rate": 4.102564102564103e-06, "loss": 1.0579, "step": 32 }, { "epoch": 0.01, "grad_norm": 1.672091824295481, "learning_rate": 4.230769230769231e-06, "loss": 1.0854, "step": 33 }, { "epoch": 0.01, "grad_norm": 1.3527707242364317, "learning_rate": 4.358974358974359e-06, "loss": 0.6808, "step": 34 }, { "epoch": 0.01, "grad_norm": 1.1547038608186884, "learning_rate": 4.487179487179488e-06, "loss": 0.7024, "step": 35 }, { "epoch": 0.01, "grad_norm": 1.2364129627567528, "learning_rate": 4.615384615384616e-06, "loss": 0.64, "step": 36 }, { "epoch": 0.01, "grad_norm": 1.4465977669644636, "learning_rate": 4.743589743589744e-06, "loss": 1.0215, "step": 37 }, { "epoch": 0.01, "grad_norm": 1.439965811891592, "learning_rate": 4.871794871794872e-06, "loss": 1.0466, "step": 38 }, { "epoch": 0.01, "grad_norm": 1.6858428242737775, "learning_rate": 5e-06, "loss": 1.1179, "step": 39 }, { "epoch": 0.01, "grad_norm": 1.1780858827985123, "learning_rate": 5.128205128205128e-06, "loss": 0.6895, "step": 40 }, { "epoch": 0.01, "grad_norm": 1.502901249579952, "learning_rate": 5.256410256410257e-06, "loss": 1.1096, "step": 41 }, { "epoch": 0.01, "grad_norm": 1.4215621974243065, "learning_rate": 5.384615384615385e-06, "loss": 1.0557, "step": 42 }, { "epoch": 0.01, "grad_norm": 1.4301700990784756, "learning_rate": 5.512820512820514e-06, "loss": 1.0312, "step": 43 }, { "epoch": 0.01, "grad_norm": 1.158303689450488, "learning_rate": 5.641025641025641e-06, "loss": 0.6734, "step": 44 }, { "epoch": 0.01, "grad_norm": 1.4025737609018762, "learning_rate": 5.769230769230769e-06, "loss": 1.0657, "step": 45 }, { "epoch": 0.01, "grad_norm": 1.454357748476422, "learning_rate": 5.897435897435898e-06, "loss": 1.052, "step": 46 }, { "epoch": 0.01, "grad_norm": 1.4309411968494603, "learning_rate": 6.025641025641026e-06, "loss": 1.0393, "step": 47 }, { "epoch": 0.01, "grad_norm": 1.305639620176256, "learning_rate": 6.153846153846155e-06, "loss": 1.0396, "step": 48 }, { "epoch": 0.01, "grad_norm": 1.2858351790848455, "learning_rate": 6.282051282051282e-06, "loss": 1.0547, "step": 49 }, { "epoch": 0.01, "grad_norm": 1.3390042807287241, "learning_rate": 6.410256410256412e-06, "loss": 1.0154, "step": 50 }, { "epoch": 0.01, "grad_norm": 1.5773674795081403, "learning_rate": 6.538461538461539e-06, "loss": 1.0254, "step": 51 }, { "epoch": 0.01, "grad_norm": 1.4837778025726258, "learning_rate": 6.666666666666667e-06, "loss": 1.0569, "step": 52 }, { "epoch": 0.01, "grad_norm": 1.6346709481491395, "learning_rate": 6.794871794871796e-06, "loss": 1.0442, "step": 53 }, { "epoch": 0.01, "grad_norm": 1.302001422729613, "learning_rate": 6.923076923076923e-06, "loss": 1.0093, "step": 54 }, { "epoch": 0.01, "grad_norm": 1.5913402060277173, "learning_rate": 7.051282051282053e-06, "loss": 1.0903, "step": 55 }, { "epoch": 0.01, "grad_norm": 1.1534420002930525, "learning_rate": 7.17948717948718e-06, "loss": 1.0007, "step": 56 }, { "epoch": 0.01, "grad_norm": 1.4163928269440913, "learning_rate": 7.307692307692308e-06, "loss": 0.9863, "step": 57 }, { "epoch": 0.01, "grad_norm": 1.3456215861439311, "learning_rate": 7.435897435897437e-06, "loss": 1.0693, "step": 58 }, { "epoch": 0.01, "grad_norm": 1.4944893934806598, "learning_rate": 7.564102564102564e-06, "loss": 1.0042, "step": 59 }, { "epoch": 0.01, "grad_norm": 1.3894254075884627, "learning_rate": 7.692307692307694e-06, "loss": 1.0032, "step": 60 }, { "epoch": 0.01, "grad_norm": 1.108284513357648, "learning_rate": 7.820512820512822e-06, "loss": 0.6406, "step": 61 }, { "epoch": 0.01, "grad_norm": 1.0191360455344682, "learning_rate": 7.948717948717949e-06, "loss": 0.6917, "step": 62 }, { "epoch": 0.01, "grad_norm": 1.397688359989314, "learning_rate": 8.076923076923077e-06, "loss": 1.0332, "step": 63 }, { "epoch": 0.01, "grad_norm": 1.3306359127683676, "learning_rate": 8.205128205128205e-06, "loss": 1.0576, "step": 64 }, { "epoch": 0.01, "grad_norm": 1.259535336145614, "learning_rate": 8.333333333333334e-06, "loss": 1.0422, "step": 65 }, { "epoch": 0.01, "grad_norm": 1.334458092485469, "learning_rate": 8.461538461538462e-06, "loss": 1.0798, "step": 66 }, { "epoch": 0.01, "grad_norm": 1.4938741150197572, "learning_rate": 8.58974358974359e-06, "loss": 1.0085, "step": 67 }, { "epoch": 0.01, "grad_norm": 1.20779036000262, "learning_rate": 8.717948717948719e-06, "loss": 1.0325, "step": 68 }, { "epoch": 0.01, "grad_norm": 1.408898902565923, "learning_rate": 8.846153846153847e-06, "loss": 1.0056, "step": 69 }, { "epoch": 0.01, "grad_norm": 1.2579852942133498, "learning_rate": 8.974358974358976e-06, "loss": 1.0212, "step": 70 }, { "epoch": 0.01, "grad_norm": 1.3773745487110527, "learning_rate": 9.102564102564104e-06, "loss": 0.9658, "step": 71 }, { "epoch": 0.01, "grad_norm": 1.3903793413657994, "learning_rate": 9.230769230769232e-06, "loss": 1.0706, "step": 72 }, { "epoch": 0.01, "grad_norm": 1.2765797605494476, "learning_rate": 9.358974358974359e-06, "loss": 1.0149, "step": 73 }, { "epoch": 0.01, "grad_norm": 1.3267890527437134, "learning_rate": 9.487179487179487e-06, "loss": 1.0405, "step": 74 }, { "epoch": 0.01, "grad_norm": 1.3916091600846476, "learning_rate": 9.615384615384616e-06, "loss": 1.0151, "step": 75 }, { "epoch": 0.01, "grad_norm": 1.2906461661718358, "learning_rate": 9.743589743589744e-06, "loss": 1.0076, "step": 76 }, { "epoch": 0.01, "grad_norm": 1.4007252010188993, "learning_rate": 9.871794871794872e-06, "loss": 0.9827, "step": 77 }, { "epoch": 0.02, "grad_norm": 1.466200387260476, "learning_rate": 1e-05, "loss": 1.0327, "step": 78 }, { "epoch": 0.02, "grad_norm": 1.0402382702401776, "learning_rate": 1.012820512820513e-05, "loss": 0.6461, "step": 79 }, { "epoch": 0.02, "grad_norm": 1.419372608461217, "learning_rate": 1.0256410256410256e-05, "loss": 1.0225, "step": 80 }, { "epoch": 0.02, "grad_norm": 1.3447359761051967, "learning_rate": 1.0384615384615386e-05, "loss": 0.9795, "step": 81 }, { "epoch": 0.02, "grad_norm": 1.4524752438979969, "learning_rate": 1.0512820512820514e-05, "loss": 1.0818, "step": 82 }, { "epoch": 0.02, "grad_norm": 1.1054322443956488, "learning_rate": 1.0641025641025643e-05, "loss": 0.6768, "step": 83 }, { "epoch": 0.02, "grad_norm": 1.2616565212162727, "learning_rate": 1.076923076923077e-05, "loss": 1.0132, "step": 84 }, { "epoch": 0.02, "grad_norm": 1.347710231722641, "learning_rate": 1.0897435897435898e-05, "loss": 1.0432, "step": 85 }, { "epoch": 0.02, "grad_norm": 1.1634027726555938, "learning_rate": 1.1025641025641028e-05, "loss": 0.9856, "step": 86 }, { "epoch": 0.02, "grad_norm": 1.2740263528189606, "learning_rate": 1.1153846153846154e-05, "loss": 0.9805, "step": 87 }, { "epoch": 0.02, "grad_norm": 1.258865345625575, "learning_rate": 1.1282051282051283e-05, "loss": 0.9956, "step": 88 }, { "epoch": 0.02, "grad_norm": 1.3671296063154637, "learning_rate": 1.1410256410256411e-05, "loss": 1.0449, "step": 89 }, { "epoch": 0.02, "grad_norm": 1.3332737245233313, "learning_rate": 1.1538461538461538e-05, "loss": 0.9797, "step": 90 }, { "epoch": 0.02, "grad_norm": 1.2314870607573325, "learning_rate": 1.1666666666666668e-05, "loss": 1.0078, "step": 91 }, { "epoch": 0.02, "grad_norm": 1.3679988161927163, "learning_rate": 1.1794871794871796e-05, "loss": 1.032, "step": 92 }, { "epoch": 0.02, "grad_norm": 1.2935230406409617, "learning_rate": 1.1923076923076925e-05, "loss": 0.9895, "step": 93 }, { "epoch": 0.02, "grad_norm": 1.3328350519358014, "learning_rate": 1.2051282051282051e-05, "loss": 1.0386, "step": 94 }, { "epoch": 0.02, "grad_norm": 1.1724134120288108, "learning_rate": 1.217948717948718e-05, "loss": 1.022, "step": 95 }, { "epoch": 0.02, "grad_norm": 1.1633888990295995, "learning_rate": 1.230769230769231e-05, "loss": 0.9675, "step": 96 }, { "epoch": 0.02, "grad_norm": 1.2522702204216996, "learning_rate": 1.2435897435897436e-05, "loss": 1.0154, "step": 97 }, { "epoch": 0.02, "grad_norm": 1.2110111227650737, "learning_rate": 1.2564102564102565e-05, "loss": 0.6767, "step": 98 }, { "epoch": 0.02, "grad_norm": 1.470530870312327, "learning_rate": 1.2692307692307693e-05, "loss": 0.9958, "step": 99 }, { "epoch": 0.02, "grad_norm": 1.284281071406656, "learning_rate": 1.2820512820512823e-05, "loss": 0.9551, "step": 100 }, { "epoch": 0.02, "grad_norm": 1.211824193999073, "learning_rate": 1.294871794871795e-05, "loss": 0.959, "step": 101 }, { "epoch": 0.02, "grad_norm": 1.310605592343218, "learning_rate": 1.3076923076923078e-05, "loss": 1.0107, "step": 102 }, { "epoch": 0.02, "grad_norm": 0.9544044326761209, "learning_rate": 1.3205128205128207e-05, "loss": 0.679, "step": 103 }, { "epoch": 0.02, "grad_norm": 1.4083310995336091, "learning_rate": 1.3333333333333333e-05, "loss": 0.9683, "step": 104 }, { "epoch": 0.02, "grad_norm": 1.3732008450892808, "learning_rate": 1.3461538461538463e-05, "loss": 0.9722, "step": 105 }, { "epoch": 0.02, "grad_norm": 1.2988128001520798, "learning_rate": 1.3589743589743592e-05, "loss": 1.0134, "step": 106 }, { "epoch": 0.02, "grad_norm": 1.2239138462389025, "learning_rate": 1.3717948717948718e-05, "loss": 1.0076, "step": 107 }, { "epoch": 0.02, "grad_norm": 1.271932758540261, "learning_rate": 1.3846153846153847e-05, "loss": 1.0286, "step": 108 }, { "epoch": 0.02, "grad_norm": 1.6611631066611594, "learning_rate": 1.3974358974358975e-05, "loss": 1.0422, "step": 109 }, { "epoch": 0.02, "grad_norm": 1.2220186638781443, "learning_rate": 1.4102564102564105e-05, "loss": 0.9814, "step": 110 }, { "epoch": 0.02, "grad_norm": 1.5385480731424164, "learning_rate": 1.4230769230769232e-05, "loss": 0.9746, "step": 111 }, { "epoch": 0.02, "grad_norm": 1.2571323628016182, "learning_rate": 1.435897435897436e-05, "loss": 0.9724, "step": 112 }, { "epoch": 0.02, "grad_norm": 1.2811354521975358, "learning_rate": 1.4487179487179489e-05, "loss": 0.9902, "step": 113 }, { "epoch": 0.02, "grad_norm": 1.52051728459411, "learning_rate": 1.4615384615384615e-05, "loss": 0.9829, "step": 114 }, { "epoch": 0.02, "grad_norm": 1.5097177785987863, "learning_rate": 1.4743589743589745e-05, "loss": 0.9873, "step": 115 }, { "epoch": 0.02, "grad_norm": 1.462961846599091, "learning_rate": 1.4871794871794874e-05, "loss": 1.0046, "step": 116 }, { "epoch": 0.02, "grad_norm": 0.9987506030112064, "learning_rate": 1.5000000000000002e-05, "loss": 0.6483, "step": 117 }, { "epoch": 0.02, "grad_norm": 1.416755811665733, "learning_rate": 1.5128205128205129e-05, "loss": 0.9883, "step": 118 }, { "epoch": 0.02, "grad_norm": 1.2914419864240638, "learning_rate": 1.5256410256410257e-05, "loss": 0.9695, "step": 119 }, { "epoch": 0.02, "grad_norm": 1.298336573672328, "learning_rate": 1.5384615384615387e-05, "loss": 0.9697, "step": 120 }, { "epoch": 0.02, "grad_norm": 1.2250975270155302, "learning_rate": 1.5512820512820516e-05, "loss": 0.9875, "step": 121 }, { "epoch": 0.02, "grad_norm": 1.2233678689991028, "learning_rate": 1.5641025641025644e-05, "loss": 1.0227, "step": 122 }, { "epoch": 0.02, "grad_norm": 1.3271870775892394, "learning_rate": 1.576923076923077e-05, "loss": 1.0339, "step": 123 }, { "epoch": 0.02, "grad_norm": 1.3030237624596555, "learning_rate": 1.5897435897435897e-05, "loss": 1.0696, "step": 124 }, { "epoch": 0.02, "grad_norm": 1.219743276883175, "learning_rate": 1.602564102564103e-05, "loss": 0.9885, "step": 125 }, { "epoch": 0.02, "grad_norm": 1.4075127508494674, "learning_rate": 1.6153846153846154e-05, "loss": 1.0471, "step": 126 }, { "epoch": 0.02, "grad_norm": 1.3104509449640485, "learning_rate": 1.6282051282051282e-05, "loss": 0.9604, "step": 127 }, { "epoch": 0.02, "grad_norm": 1.1528038714603774, "learning_rate": 1.641025641025641e-05, "loss": 1.001, "step": 128 }, { "epoch": 0.02, "grad_norm": 1.3671021717555805, "learning_rate": 1.653846153846154e-05, "loss": 1.0471, "step": 129 }, { "epoch": 0.03, "grad_norm": 1.2290155869051256, "learning_rate": 1.6666666666666667e-05, "loss": 1.0168, "step": 130 }, { "epoch": 0.03, "grad_norm": 1.221931200643548, "learning_rate": 1.6794871794871796e-05, "loss": 0.9922, "step": 131 }, { "epoch": 0.03, "grad_norm": 1.2966851090388118, "learning_rate": 1.6923076923076924e-05, "loss": 0.9548, "step": 132 }, { "epoch": 0.03, "grad_norm": 1.302399056343829, "learning_rate": 1.7051282051282053e-05, "loss": 1.0527, "step": 133 }, { "epoch": 0.03, "grad_norm": 1.1849429948865247, "learning_rate": 1.717948717948718e-05, "loss": 0.9751, "step": 134 }, { "epoch": 0.03, "grad_norm": 1.0891613073367714, "learning_rate": 1.730769230769231e-05, "loss": 0.7109, "step": 135 }, { "epoch": 0.03, "grad_norm": 1.1449376949354855, "learning_rate": 1.7435897435897438e-05, "loss": 0.9568, "step": 136 }, { "epoch": 0.03, "grad_norm": 1.3087197244915236, "learning_rate": 1.7564102564102566e-05, "loss": 0.999, "step": 137 }, { "epoch": 0.03, "grad_norm": 1.260659128669434, "learning_rate": 1.7692307692307694e-05, "loss": 1.0354, "step": 138 }, { "epoch": 0.03, "grad_norm": 1.3172128907470975, "learning_rate": 1.7820512820512823e-05, "loss": 1.0073, "step": 139 }, { "epoch": 0.03, "grad_norm": 1.3571246214477353, "learning_rate": 1.794871794871795e-05, "loss": 0.9521, "step": 140 }, { "epoch": 0.03, "grad_norm": 1.248188126283738, "learning_rate": 1.807692307692308e-05, "loss": 0.9619, "step": 141 }, { "epoch": 0.03, "grad_norm": 1.302504107715116, "learning_rate": 1.8205128205128208e-05, "loss": 1.0076, "step": 142 }, { "epoch": 0.03, "grad_norm": 1.248580258225782, "learning_rate": 1.8333333333333333e-05, "loss": 0.9861, "step": 143 }, { "epoch": 0.03, "grad_norm": 1.3324514635844147, "learning_rate": 1.8461538461538465e-05, "loss": 1.0378, "step": 144 }, { "epoch": 0.03, "grad_norm": 0.9570698573392553, "learning_rate": 1.8589743589743593e-05, "loss": 0.641, "step": 145 }, { "epoch": 0.03, "grad_norm": 1.1094796496969097, "learning_rate": 1.8717948717948718e-05, "loss": 0.9463, "step": 146 }, { "epoch": 0.03, "grad_norm": 1.4530194728742487, "learning_rate": 1.8846153846153846e-05, "loss": 1.0559, "step": 147 }, { "epoch": 0.03, "grad_norm": 1.5119523501232808, "learning_rate": 1.8974358974358975e-05, "loss": 1.0459, "step": 148 }, { "epoch": 0.03, "grad_norm": 1.2842127427680503, "learning_rate": 1.9102564102564106e-05, "loss": 0.9854, "step": 149 }, { "epoch": 0.03, "grad_norm": 1.2852527160441922, "learning_rate": 1.923076923076923e-05, "loss": 0.9807, "step": 150 }, { "epoch": 0.03, "grad_norm": 1.1382440528866125, "learning_rate": 1.935897435897436e-05, "loss": 0.9946, "step": 151 }, { "epoch": 0.03, "grad_norm": 0.9926528630141827, "learning_rate": 1.9487179487179488e-05, "loss": 0.6451, "step": 152 }, { "epoch": 0.03, "grad_norm": 1.1608312991753558, "learning_rate": 1.9615384615384617e-05, "loss": 1.002, "step": 153 }, { "epoch": 0.03, "grad_norm": 1.1223355833366804, "learning_rate": 1.9743589743589745e-05, "loss": 0.9675, "step": 154 }, { "epoch": 0.03, "grad_norm": 1.274907325784569, "learning_rate": 1.9871794871794873e-05, "loss": 1.0244, "step": 155 }, { "epoch": 0.03, "grad_norm": 1.1703903039801056, "learning_rate": 2e-05, "loss": 0.9524, "step": 156 }, { "epoch": 0.03, "grad_norm": 1.325597585343367, "learning_rate": 1.9999998058827844e-05, "loss": 0.9971, "step": 157 }, { "epoch": 0.03, "grad_norm": 1.203048277860976, "learning_rate": 1.9999992235312136e-05, "loss": 0.9712, "step": 158 }, { "epoch": 0.03, "grad_norm": 1.3357472983213847, "learning_rate": 1.9999982529455127e-05, "loss": 1.022, "step": 159 }, { "epoch": 0.03, "grad_norm": 1.2280997105201694, "learning_rate": 1.9999968941260596e-05, "loss": 1.0017, "step": 160 }, { "epoch": 0.03, "grad_norm": 1.34678582332703, "learning_rate": 1.9999951470733808e-05, "loss": 0.9709, "step": 161 }, { "epoch": 0.03, "grad_norm": 1.2219280063736826, "learning_rate": 1.9999930117881548e-05, "loss": 0.9521, "step": 162 }, { "epoch": 0.03, "grad_norm": 1.3803735934741903, "learning_rate": 1.9999904882712115e-05, "loss": 1.0706, "step": 163 }, { "epoch": 0.03, "grad_norm": 1.2359576868055602, "learning_rate": 1.99998757652353e-05, "loss": 0.9607, "step": 164 }, { "epoch": 0.03, "grad_norm": 2.0030329006724847, "learning_rate": 1.9999842765462403e-05, "loss": 1.0623, "step": 165 }, { "epoch": 0.03, "grad_norm": 1.1886742998625575, "learning_rate": 1.999980588340624e-05, "loss": 0.9351, "step": 166 }, { "epoch": 0.03, "grad_norm": 1.1848084223428894, "learning_rate": 1.9999765119081132e-05, "loss": 1.0657, "step": 167 }, { "epoch": 0.03, "grad_norm": 1.2288869317895377, "learning_rate": 1.9999720472502902e-05, "loss": 0.9768, "step": 168 }, { "epoch": 0.03, "grad_norm": 1.284296298443732, "learning_rate": 1.9999671943688885e-05, "loss": 1.0203, "step": 169 }, { "epoch": 0.03, "grad_norm": 1.1861644239011992, "learning_rate": 1.9999619532657915e-05, "loss": 1.0234, "step": 170 }, { "epoch": 0.03, "grad_norm": 1.0934889852350769, "learning_rate": 1.9999563239430352e-05, "loss": 0.6267, "step": 171 }, { "epoch": 0.03, "grad_norm": 1.1940367546958772, "learning_rate": 1.9999503064028043e-05, "loss": 0.9709, "step": 172 }, { "epoch": 0.03, "grad_norm": 1.2043408295745266, "learning_rate": 1.999943900647435e-05, "loss": 0.9866, "step": 173 }, { "epoch": 0.03, "grad_norm": 1.1996519607283096, "learning_rate": 1.9999371066794146e-05, "loss": 1.0601, "step": 174 }, { "epoch": 0.03, "grad_norm": 1.2301704832397347, "learning_rate": 1.9999299245013805e-05, "loss": 0.9336, "step": 175 }, { "epoch": 0.03, "grad_norm": 1.2165108382030674, "learning_rate": 1.999922354116121e-05, "loss": 0.9902, "step": 176 }, { "epoch": 0.03, "grad_norm": 1.0692582929631935, "learning_rate": 1.999914395526575e-05, "loss": 0.9619, "step": 177 }, { "epoch": 0.03, "grad_norm": 1.184333010158169, "learning_rate": 1.9999060487358333e-05, "loss": 0.9971, "step": 178 }, { "epoch": 0.03, "grad_norm": 1.1162260301492404, "learning_rate": 1.9998973137471352e-05, "loss": 0.9736, "step": 179 }, { "epoch": 0.03, "grad_norm": 1.2413779336034216, "learning_rate": 1.9998881905638727e-05, "loss": 0.9651, "step": 180 }, { "epoch": 0.03, "grad_norm": 1.2451582647541388, "learning_rate": 1.9998786791895874e-05, "loss": 1.0151, "step": 181 }, { "epoch": 0.04, "grad_norm": 1.4895106104180413, "learning_rate": 1.999868779627972e-05, "loss": 0.9924, "step": 182 }, { "epoch": 0.04, "grad_norm": 1.2157612115980667, "learning_rate": 1.9998584918828695e-05, "loss": 0.9907, "step": 183 }, { "epoch": 0.04, "grad_norm": 1.374749148580586, "learning_rate": 1.9998478159582747e-05, "loss": 0.9929, "step": 184 }, { "epoch": 0.04, "grad_norm": 1.2552461758590283, "learning_rate": 1.999836751858332e-05, "loss": 0.9172, "step": 185 }, { "epoch": 0.04, "grad_norm": 1.363240559573226, "learning_rate": 1.9998252995873367e-05, "loss": 1.0298, "step": 186 }, { "epoch": 0.04, "grad_norm": 1.0787824504119388, "learning_rate": 1.999813459149735e-05, "loss": 0.9731, "step": 187 }, { "epoch": 0.04, "grad_norm": 1.232827024584291, "learning_rate": 1.9998012305501243e-05, "loss": 0.969, "step": 188 }, { "epoch": 0.04, "grad_norm": 1.196278143268499, "learning_rate": 1.999788613793251e-05, "loss": 1.0259, "step": 189 }, { "epoch": 0.04, "grad_norm": 1.436370247907154, "learning_rate": 1.999775608884015e-05, "loss": 0.9724, "step": 190 }, { "epoch": 0.04, "grad_norm": 1.2994649163204097, "learning_rate": 1.9997622158274635e-05, "loss": 1.033, "step": 191 }, { "epoch": 0.04, "grad_norm": 1.2976828589989684, "learning_rate": 1.9997484346287973e-05, "loss": 0.9324, "step": 192 }, { "epoch": 0.04, "grad_norm": 1.2641930280259472, "learning_rate": 1.9997342652933668e-05, "loss": 0.9392, "step": 193 }, { "epoch": 0.04, "grad_norm": 1.2542510351499696, "learning_rate": 1.9997197078266723e-05, "loss": 0.9885, "step": 194 }, { "epoch": 0.04, "grad_norm": 1.2525162185573744, "learning_rate": 1.999704762234366e-05, "loss": 1.01, "step": 195 }, { "epoch": 0.04, "grad_norm": 1.2671642463537214, "learning_rate": 1.99968942852225e-05, "loss": 1.0186, "step": 196 }, { "epoch": 0.04, "grad_norm": 1.368993200916858, "learning_rate": 1.9996737066962778e-05, "loss": 1.0422, "step": 197 }, { "epoch": 0.04, "grad_norm": 1.1690958319742817, "learning_rate": 1.9996575967625525e-05, "loss": 0.9585, "step": 198 }, { "epoch": 0.04, "grad_norm": 1.1476082908085952, "learning_rate": 1.999641098727329e-05, "loss": 1.0084, "step": 199 }, { "epoch": 0.04, "grad_norm": 1.1890222829303494, "learning_rate": 1.999624212597013e-05, "loss": 0.9851, "step": 200 }, { "epoch": 0.04, "grad_norm": 1.2482827641605907, "learning_rate": 1.9996069383781587e-05, "loss": 1.0386, "step": 201 }, { "epoch": 0.04, "grad_norm": 1.2430371967407858, "learning_rate": 1.9995892760774738e-05, "loss": 0.9993, "step": 202 }, { "epoch": 0.04, "grad_norm": 1.0554002613969289, "learning_rate": 1.9995712257018153e-05, "loss": 0.6381, "step": 203 }, { "epoch": 0.04, "grad_norm": 1.3115137915423425, "learning_rate": 1.9995527872581903e-05, "loss": 0.9343, "step": 204 }, { "epoch": 0.04, "grad_norm": 1.2427313434342986, "learning_rate": 1.9995339607537578e-05, "loss": 0.9329, "step": 205 }, { "epoch": 0.04, "grad_norm": 1.230022928861151, "learning_rate": 1.9995147461958267e-05, "loss": 0.9734, "step": 206 }, { "epoch": 0.04, "grad_norm": 1.3091977899572647, "learning_rate": 1.999495143591857e-05, "loss": 0.9766, "step": 207 }, { "epoch": 0.04, "grad_norm": 1.3309047023935543, "learning_rate": 1.999475152949459e-05, "loss": 1.0474, "step": 208 }, { "epoch": 0.04, "grad_norm": 1.4151788065667266, "learning_rate": 1.9994547742763935e-05, "loss": 0.9731, "step": 209 }, { "epoch": 0.04, "grad_norm": 1.199413883225987, "learning_rate": 1.9994340075805724e-05, "loss": 1.0024, "step": 210 }, { "epoch": 0.04, "grad_norm": 1.326311482270992, "learning_rate": 1.9994128528700583e-05, "loss": 0.979, "step": 211 }, { "epoch": 0.04, "grad_norm": 1.1667705588794102, "learning_rate": 1.9993913101530635e-05, "loss": 0.6408, "step": 212 }, { "epoch": 0.04, "grad_norm": 1.137061806226485, "learning_rate": 1.9993693794379525e-05, "loss": 0.9521, "step": 213 }, { "epoch": 0.04, "grad_norm": 1.3172413069198279, "learning_rate": 1.9993470607332387e-05, "loss": 0.9905, "step": 214 }, { "epoch": 0.04, "grad_norm": 1.1724151268600442, "learning_rate": 1.999324354047588e-05, "loss": 1.0176, "step": 215 }, { "epoch": 0.04, "grad_norm": 1.2161223042253768, "learning_rate": 1.9993012593898146e-05, "loss": 1.0, "step": 216 }, { "epoch": 0.04, "grad_norm": 0.9764548754991592, "learning_rate": 1.9992777767688857e-05, "loss": 0.6678, "step": 217 }, { "epoch": 0.04, "grad_norm": 1.3723784840495754, "learning_rate": 1.9992539061939175e-05, "loss": 0.9995, "step": 218 }, { "epoch": 0.04, "grad_norm": 1.0999779257232467, "learning_rate": 1.999229647674178e-05, "loss": 0.97, "step": 219 }, { "epoch": 0.04, "grad_norm": 1.3453172447428843, "learning_rate": 1.9992050012190845e-05, "loss": 0.9705, "step": 220 }, { "epoch": 0.04, "grad_norm": 1.1851409896039096, "learning_rate": 1.9991799668382058e-05, "loss": 0.9568, "step": 221 }, { "epoch": 0.04, "grad_norm": 1.1196746089007168, "learning_rate": 1.9991545445412614e-05, "loss": 0.9722, "step": 222 }, { "epoch": 0.04, "grad_norm": 0.9482383467677992, "learning_rate": 1.9991287343381208e-05, "loss": 0.6391, "step": 223 }, { "epoch": 0.04, "grad_norm": 1.241533180188147, "learning_rate": 1.9991025362388044e-05, "loss": 0.9897, "step": 224 }, { "epoch": 0.04, "grad_norm": 1.3324094585694597, "learning_rate": 1.9990759502534835e-05, "loss": 1.0334, "step": 225 }, { "epoch": 0.04, "grad_norm": 1.1265209677595842, "learning_rate": 1.9990489763924796e-05, "loss": 0.9719, "step": 226 }, { "epoch": 0.04, "grad_norm": 0.9297964489033397, "learning_rate": 1.9990216146662648e-05, "loss": 0.6448, "step": 227 }, { "epoch": 0.04, "grad_norm": 0.8933609056626465, "learning_rate": 1.9989938650854618e-05, "loss": 0.6569, "step": 228 }, { "epoch": 0.04, "grad_norm": 1.2825744019823957, "learning_rate": 1.998965727660844e-05, "loss": 1.04, "step": 229 }, { "epoch": 0.04, "grad_norm": 1.391749744556782, "learning_rate": 1.9989372024033352e-05, "loss": 1.0205, "step": 230 }, { "epoch": 0.04, "grad_norm": 1.2335565141786156, "learning_rate": 1.99890828932401e-05, "loss": 1.0181, "step": 231 }, { "epoch": 0.04, "grad_norm": 0.9596689452976402, "learning_rate": 1.9988789884340938e-05, "loss": 0.6189, "step": 232 }, { "epoch": 0.04, "grad_norm": 1.2429238041907216, "learning_rate": 1.9988492997449615e-05, "loss": 0.99, "step": 233 }, { "epoch": 0.05, "grad_norm": 0.9844492311200472, "learning_rate": 1.9988192232681398e-05, "loss": 0.6673, "step": 234 }, { "epoch": 0.05, "grad_norm": 1.0348335032882376, "learning_rate": 1.9987887590153055e-05, "loss": 0.6793, "step": 235 }, { "epoch": 0.05, "grad_norm": 1.4308674713283738, "learning_rate": 1.9987579069982856e-05, "loss": 0.9126, "step": 236 }, { "epoch": 0.05, "grad_norm": 1.235734960369997, "learning_rate": 1.9987266672290577e-05, "loss": 0.9817, "step": 237 }, { "epoch": 0.05, "grad_norm": 1.1137134971888942, "learning_rate": 1.9986950397197503e-05, "loss": 0.6794, "step": 238 }, { "epoch": 0.05, "grad_norm": 1.2632536850244456, "learning_rate": 1.9986630244826425e-05, "loss": 0.9819, "step": 239 }, { "epoch": 0.05, "grad_norm": 1.6387221117810102, "learning_rate": 1.998630621530164e-05, "loss": 1.0396, "step": 240 }, { "epoch": 0.05, "grad_norm": 1.478300951436422, "learning_rate": 1.998597830874894e-05, "loss": 1.0405, "step": 241 }, { "epoch": 0.05, "grad_norm": 1.1219864474463404, "learning_rate": 1.9985646525295634e-05, "loss": 0.9358, "step": 242 }, { "epoch": 0.05, "grad_norm": 1.2607769994561242, "learning_rate": 1.998531086507053e-05, "loss": 0.9202, "step": 243 }, { "epoch": 0.05, "grad_norm": 1.1601494803375636, "learning_rate": 1.9984971328203945e-05, "loss": 0.9424, "step": 244 }, { "epoch": 0.05, "grad_norm": 1.4535226828904322, "learning_rate": 1.9984627914827698e-05, "loss": 0.9216, "step": 245 }, { "epoch": 0.05, "grad_norm": 1.182150951835412, "learning_rate": 1.9984280625075115e-05, "loss": 0.998, "step": 246 }, { "epoch": 0.05, "grad_norm": 1.3470845346998415, "learning_rate": 1.9983929459081022e-05, "loss": 0.9404, "step": 247 }, { "epoch": 0.05, "grad_norm": 1.238126800784689, "learning_rate": 1.998357441698176e-05, "loss": 1.0142, "step": 248 }, { "epoch": 0.05, "grad_norm": 1.1718365535787236, "learning_rate": 1.998321549891516e-05, "loss": 0.9878, "step": 249 }, { "epoch": 0.05, "grad_norm": 1.3501193187969303, "learning_rate": 1.9982852705020572e-05, "loss": 1.0371, "step": 250 }, { "epoch": 0.05, "grad_norm": 1.1808882710255602, "learning_rate": 1.9982486035438848e-05, "loss": 0.9883, "step": 251 }, { "epoch": 0.05, "grad_norm": 1.1447858826214836, "learning_rate": 1.9982115490312334e-05, "loss": 0.9683, "step": 252 }, { "epoch": 0.05, "grad_norm": 1.1448374058430004, "learning_rate": 1.9981741069784894e-05, "loss": 0.9485, "step": 253 }, { "epoch": 0.05, "grad_norm": 1.216974297916831, "learning_rate": 1.9981362774001886e-05, "loss": 0.9763, "step": 254 }, { "epoch": 0.05, "grad_norm": 1.1807928090067978, "learning_rate": 1.9980980603110185e-05, "loss": 0.9219, "step": 255 }, { "epoch": 0.05, "grad_norm": 1.1833894877151228, "learning_rate": 1.9980594557258158e-05, "loss": 1.0188, "step": 256 }, { "epoch": 0.05, "grad_norm": 1.2427834140054015, "learning_rate": 1.9980204636595682e-05, "loss": 0.9744, "step": 257 }, { "epoch": 0.05, "grad_norm": 1.1546735887083073, "learning_rate": 1.9979810841274135e-05, "loss": 0.9709, "step": 258 }, { "epoch": 0.05, "grad_norm": 1.0685358298402996, "learning_rate": 1.9979413171446403e-05, "loss": 0.9373, "step": 259 }, { "epoch": 0.05, "grad_norm": 1.1809431756601931, "learning_rate": 1.9979011627266884e-05, "loss": 0.9587, "step": 260 }, { "epoch": 0.05, "grad_norm": 1.1866684585610612, "learning_rate": 1.997860620889146e-05, "loss": 0.9277, "step": 261 }, { "epoch": 0.05, "grad_norm": 1.1295117450586207, "learning_rate": 1.997819691647753e-05, "loss": 0.918, "step": 262 }, { "epoch": 0.05, "grad_norm": 1.353427133378452, "learning_rate": 1.9977783750184e-05, "loss": 1.0249, "step": 263 }, { "epoch": 0.05, "grad_norm": 1.1608555826150475, "learning_rate": 1.9977366710171274e-05, "loss": 0.9575, "step": 264 }, { "epoch": 0.05, "grad_norm": 0.9060291430175452, "learning_rate": 1.9976945796601258e-05, "loss": 0.6077, "step": 265 }, { "epoch": 0.05, "grad_norm": 1.2991113196232338, "learning_rate": 1.9976521009637366e-05, "loss": 0.99, "step": 266 }, { "epoch": 0.05, "grad_norm": 1.3296654112737232, "learning_rate": 1.997609234944452e-05, "loss": 1.019, "step": 267 }, { "epoch": 0.05, "grad_norm": 1.2125568798392188, "learning_rate": 1.9975659816189137e-05, "loss": 1.0337, "step": 268 }, { "epoch": 0.05, "grad_norm": 1.1657205540581443, "learning_rate": 1.997522341003914e-05, "loss": 0.936, "step": 269 }, { "epoch": 0.05, "grad_norm": 1.147966192080248, "learning_rate": 1.9974783131163957e-05, "loss": 1.0017, "step": 270 }, { "epoch": 0.05, "grad_norm": 1.1783974571605205, "learning_rate": 1.9974338979734523e-05, "loss": 1.0476, "step": 271 }, { "epoch": 0.05, "grad_norm": 1.2261861862442398, "learning_rate": 1.997389095592327e-05, "loss": 1.0078, "step": 272 }, { "epoch": 0.05, "grad_norm": 1.1213231898664109, "learning_rate": 1.9973439059904133e-05, "loss": 0.958, "step": 273 }, { "epoch": 0.05, "grad_norm": 1.2283560015406387, "learning_rate": 1.9972983291852565e-05, "loss": 1.0125, "step": 274 }, { "epoch": 0.05, "grad_norm": 1.333382824662059, "learning_rate": 1.9972523651945496e-05, "loss": 1.0181, "step": 275 }, { "epoch": 0.05, "grad_norm": 1.104270281094484, "learning_rate": 1.9972060140361384e-05, "loss": 0.9255, "step": 276 }, { "epoch": 0.05, "grad_norm": 1.3407775371282498, "learning_rate": 1.997159275728018e-05, "loss": 1.1089, "step": 277 }, { "epoch": 0.05, "grad_norm": 1.2381264404794459, "learning_rate": 1.9971121502883332e-05, "loss": 0.9766, "step": 278 }, { "epoch": 0.05, "grad_norm": 0.865441228039131, "learning_rate": 1.9970646377353802e-05, "loss": 0.6113, "step": 279 }, { "epoch": 0.05, "grad_norm": 1.1181260506444828, "learning_rate": 1.997016738087605e-05, "loss": 0.9622, "step": 280 }, { "epoch": 0.05, "grad_norm": 1.1788872193512527, "learning_rate": 1.9969684513636035e-05, "loss": 0.905, "step": 281 }, { "epoch": 0.05, "grad_norm": 1.0790925925300592, "learning_rate": 1.9969197775821227e-05, "loss": 0.9651, "step": 282 }, { "epoch": 0.05, "grad_norm": 1.1236641827170633, "learning_rate": 1.9968707167620593e-05, "loss": 0.981, "step": 283 }, { "epoch": 0.05, "grad_norm": 1.2026206686100422, "learning_rate": 1.9968212689224603e-05, "loss": 0.8896, "step": 284 }, { "epoch": 0.05, "grad_norm": 1.1674693604454964, "learning_rate": 1.996771434082523e-05, "loss": 0.9741, "step": 285 }, { "epoch": 0.06, "grad_norm": 1.254869472121046, "learning_rate": 1.9967212122615958e-05, "loss": 0.9937, "step": 286 }, { "epoch": 0.06, "grad_norm": 1.1401114254745526, "learning_rate": 1.9966706034791752e-05, "loss": 0.9249, "step": 287 }, { "epoch": 0.06, "grad_norm": 0.8494298046356734, "learning_rate": 1.9966196077549106e-05, "loss": 0.6647, "step": 288 }, { "epoch": 0.06, "grad_norm": 1.3302011175678419, "learning_rate": 1.996568225108599e-05, "loss": 1.0061, "step": 289 }, { "epoch": 0.06, "grad_norm": 1.338603968730464, "learning_rate": 1.99651645556019e-05, "loss": 1.0134, "step": 290 }, { "epoch": 0.06, "grad_norm": 1.26514659536902, "learning_rate": 1.9964642991297817e-05, "loss": 0.9875, "step": 291 }, { "epoch": 0.06, "grad_norm": 1.2427026038469622, "learning_rate": 1.996411755837623e-05, "loss": 0.9871, "step": 292 }, { "epoch": 0.06, "grad_norm": 1.193730136727302, "learning_rate": 1.9963588257041137e-05, "loss": 0.9565, "step": 293 }, { "epoch": 0.06, "grad_norm": 1.1544507407414009, "learning_rate": 1.996305508749802e-05, "loss": 0.9749, "step": 294 }, { "epoch": 0.06, "grad_norm": 1.2075557265620225, "learning_rate": 1.9962518049953887e-05, "loss": 0.9822, "step": 295 }, { "epoch": 0.06, "grad_norm": 1.3613439465633659, "learning_rate": 1.9961977144617225e-05, "loss": 1.0117, "step": 296 }, { "epoch": 0.06, "grad_norm": 1.3467475484661646, "learning_rate": 1.996143237169803e-05, "loss": 1.0078, "step": 297 }, { "epoch": 0.06, "grad_norm": 1.3523080279033188, "learning_rate": 1.996088373140781e-05, "loss": 0.9587, "step": 298 }, { "epoch": 0.06, "grad_norm": 1.2428926968070197, "learning_rate": 1.9960331223959564e-05, "loss": 1.0022, "step": 299 }, { "epoch": 0.06, "grad_norm": 1.1928163219967325, "learning_rate": 1.995977484956779e-05, "loss": 1.0081, "step": 300 }, { "epoch": 0.06, "grad_norm": 0.9896167170442041, "learning_rate": 1.9959214608448495e-05, "loss": 0.6679, "step": 301 }, { "epoch": 0.06, "grad_norm": 1.3853076000651885, "learning_rate": 1.9958650500819183e-05, "loss": 0.9802, "step": 302 }, { "epoch": 0.06, "grad_norm": 1.2021426417453545, "learning_rate": 1.995808252689886e-05, "loss": 0.9741, "step": 303 }, { "epoch": 0.06, "grad_norm": 1.2113284769998782, "learning_rate": 1.9957510686908034e-05, "loss": 0.9871, "step": 304 }, { "epoch": 0.06, "grad_norm": 1.0695154209268292, "learning_rate": 1.9956934981068713e-05, "loss": 0.9385, "step": 305 }, { "epoch": 0.06, "grad_norm": 1.2660804579511495, "learning_rate": 1.9956355409604402e-05, "loss": 0.9758, "step": 306 }, { "epoch": 0.06, "grad_norm": 1.1918099465961471, "learning_rate": 1.9955771972740118e-05, "loss": 0.9661, "step": 307 }, { "epoch": 0.06, "grad_norm": 1.2337962652563519, "learning_rate": 1.9955184670702363e-05, "loss": 1.0247, "step": 308 }, { "epoch": 0.06, "grad_norm": 1.1730030015247621, "learning_rate": 1.995459350371915e-05, "loss": 1.0413, "step": 309 }, { "epoch": 0.06, "grad_norm": 1.2062644490367351, "learning_rate": 1.9953998472019996e-05, "loss": 0.9939, "step": 310 }, { "epoch": 0.06, "grad_norm": 1.2659042905306745, "learning_rate": 1.995339957583591e-05, "loss": 0.9817, "step": 311 }, { "epoch": 0.06, "grad_norm": 1.1315247385181697, "learning_rate": 1.9952796815399403e-05, "loss": 1.0271, "step": 312 }, { "epoch": 0.06, "grad_norm": 1.0302113295090236, "learning_rate": 1.9952190190944484e-05, "loss": 0.6838, "step": 313 }, { "epoch": 0.06, "grad_norm": 1.1038186429492804, "learning_rate": 1.9951579702706668e-05, "loss": 0.9802, "step": 314 }, { "epoch": 0.06, "grad_norm": 0.9334386430862823, "learning_rate": 1.9950965350922975e-05, "loss": 0.6318, "step": 315 }, { "epoch": 0.06, "grad_norm": 1.0814639836568836, "learning_rate": 1.9950347135831907e-05, "loss": 1.0098, "step": 316 }, { "epoch": 0.06, "grad_norm": 1.1248077987525862, "learning_rate": 1.994972505767348e-05, "loss": 0.9563, "step": 317 }, { "epoch": 0.06, "grad_norm": 1.145127048202733, "learning_rate": 1.994909911668921e-05, "loss": 0.9968, "step": 318 }, { "epoch": 0.06, "grad_norm": 1.2040885946251503, "learning_rate": 1.99484693131221e-05, "loss": 0.9807, "step": 319 }, { "epoch": 0.06, "grad_norm": 1.1075662484325683, "learning_rate": 1.994783564721667e-05, "loss": 0.9128, "step": 320 }, { "epoch": 0.06, "grad_norm": 1.1108366586828158, "learning_rate": 1.9947198119218924e-05, "loss": 0.9502, "step": 321 }, { "epoch": 0.06, "grad_norm": 1.1575494352034355, "learning_rate": 1.994655672937638e-05, "loss": 0.9537, "step": 322 }, { "epoch": 0.06, "grad_norm": 0.8780512722909773, "learning_rate": 1.9945911477938044e-05, "loss": 0.6568, "step": 323 }, { "epoch": 0.06, "grad_norm": 1.2690717074496538, "learning_rate": 1.994526236515442e-05, "loss": 0.9658, "step": 324 }, { "epoch": 0.06, "grad_norm": 1.1239820589971834, "learning_rate": 1.994460939127753e-05, "loss": 0.6212, "step": 325 }, { "epoch": 0.06, "grad_norm": 1.1115812039031645, "learning_rate": 1.9943952556560863e-05, "loss": 0.9568, "step": 326 }, { "epoch": 0.06, "grad_norm": 0.8567000326208367, "learning_rate": 1.9943291861259433e-05, "loss": 0.6584, "step": 327 }, { "epoch": 0.06, "grad_norm": 1.2342369781057938, "learning_rate": 1.9942627305629747e-05, "loss": 1.0173, "step": 328 }, { "epoch": 0.06, "grad_norm": 1.2373089082731712, "learning_rate": 1.9941958889929808e-05, "loss": 0.9934, "step": 329 }, { "epoch": 0.06, "grad_norm": 1.0676413742712236, "learning_rate": 1.9941286614419113e-05, "loss": 1.0662, "step": 330 }, { "epoch": 0.06, "grad_norm": 1.280544504731669, "learning_rate": 1.994061047935867e-05, "loss": 1.0356, "step": 331 }, { "epoch": 0.06, "grad_norm": 1.0377078240195161, "learning_rate": 1.9939930485010968e-05, "loss": 0.9888, "step": 332 }, { "epoch": 0.06, "grad_norm": 1.1365071312525685, "learning_rate": 1.9939246631640014e-05, "loss": 0.918, "step": 333 }, { "epoch": 0.06, "grad_norm": 1.253497769282689, "learning_rate": 1.99385589195113e-05, "loss": 1.0491, "step": 334 }, { "epoch": 0.06, "grad_norm": 1.0854615839486832, "learning_rate": 1.9937867348891815e-05, "loss": 0.9805, "step": 335 }, { "epoch": 0.06, "grad_norm": 1.128313961563376, "learning_rate": 1.9937171920050057e-05, "loss": 0.9875, "step": 336 }, { "epoch": 0.06, "grad_norm": 1.0690538707155317, "learning_rate": 1.9936472633256012e-05, "loss": 0.9653, "step": 337 }, { "epoch": 0.07, "grad_norm": 1.1452444843806546, "learning_rate": 1.9935769488781167e-05, "loss": 0.9111, "step": 338 }, { "epoch": 0.07, "grad_norm": 1.113884782117061, "learning_rate": 1.993506248689851e-05, "loss": 0.9673, "step": 339 }, { "epoch": 0.07, "grad_norm": 1.091526240528764, "learning_rate": 1.993435162788252e-05, "loss": 1.0007, "step": 340 }, { "epoch": 0.07, "grad_norm": 1.1407034421183837, "learning_rate": 1.993363691200918e-05, "loss": 0.9778, "step": 341 }, { "epoch": 0.07, "grad_norm": 1.193736331718521, "learning_rate": 1.9932918339555965e-05, "loss": 0.9802, "step": 342 }, { "epoch": 0.07, "grad_norm": 1.091379752815378, "learning_rate": 1.9932195910801848e-05, "loss": 0.9282, "step": 343 }, { "epoch": 0.07, "grad_norm": 1.2633091038833926, "learning_rate": 1.9931469626027305e-05, "loss": 0.9573, "step": 344 }, { "epoch": 0.07, "grad_norm": 1.1246443424704797, "learning_rate": 1.9930739485514304e-05, "loss": 1.0261, "step": 345 }, { "epoch": 0.07, "grad_norm": 1.2465736707891892, "learning_rate": 1.9930005489546308e-05, "loss": 0.9163, "step": 346 }, { "epoch": 0.07, "grad_norm": 1.136760478732638, "learning_rate": 1.9929267638408277e-05, "loss": 0.9778, "step": 347 }, { "epoch": 0.07, "grad_norm": 1.123473845462306, "learning_rate": 1.9928525932386678e-05, "loss": 0.9331, "step": 348 }, { "epoch": 0.07, "grad_norm": 1.0118317685922962, "learning_rate": 1.9927780371769463e-05, "loss": 0.6251, "step": 349 }, { "epoch": 0.07, "grad_norm": 1.3397160679866944, "learning_rate": 1.9927030956846083e-05, "loss": 0.968, "step": 350 }, { "epoch": 0.07, "grad_norm": 0.8691721444361743, "learning_rate": 1.992627768790749e-05, "loss": 0.6496, "step": 351 }, { "epoch": 0.07, "grad_norm": 1.4816154468412523, "learning_rate": 1.9925520565246125e-05, "loss": 1.0562, "step": 352 }, { "epoch": 0.07, "grad_norm": 0.9464851841468517, "learning_rate": 1.9924759589155932e-05, "loss": 0.6581, "step": 353 }, { "epoch": 0.07, "grad_norm": 0.933175812429748, "learning_rate": 1.9923994759932344e-05, "loss": 0.6331, "step": 354 }, { "epoch": 0.07, "grad_norm": 1.2028898053371786, "learning_rate": 1.9923226077872296e-05, "loss": 1.0325, "step": 355 }, { "epoch": 0.07, "grad_norm": 1.1847702983408093, "learning_rate": 1.9922453543274223e-05, "loss": 0.9661, "step": 356 }, { "epoch": 0.07, "grad_norm": 0.9011877914388539, "learning_rate": 1.9921677156438044e-05, "loss": 0.7085, "step": 357 }, { "epoch": 0.07, "grad_norm": 1.3114634079023217, "learning_rate": 1.9920896917665178e-05, "loss": 1.0129, "step": 358 }, { "epoch": 0.07, "grad_norm": 1.131860693676473, "learning_rate": 1.992011282725854e-05, "loss": 0.9895, "step": 359 }, { "epoch": 0.07, "grad_norm": 1.1048541310765008, "learning_rate": 1.9919324885522548e-05, "loss": 0.9136, "step": 360 }, { "epoch": 0.07, "grad_norm": 1.0388814886793802, "learning_rate": 1.99185330927631e-05, "loss": 0.9253, "step": 361 }, { "epoch": 0.07, "grad_norm": 1.04720683196483, "learning_rate": 1.99177374492876e-05, "loss": 1.0129, "step": 362 }, { "epoch": 0.07, "grad_norm": 1.131224330013488, "learning_rate": 1.991693795540494e-05, "loss": 0.9587, "step": 363 }, { "epoch": 0.07, "grad_norm": 1.2982350549592334, "learning_rate": 1.9916134611425522e-05, "loss": 0.9883, "step": 364 }, { "epoch": 0.07, "grad_norm": 1.2619321789494249, "learning_rate": 1.9915327417661226e-05, "loss": 1.0535, "step": 365 }, { "epoch": 0.07, "grad_norm": 0.965546671420336, "learning_rate": 1.991451637442543e-05, "loss": 0.6409, "step": 366 }, { "epoch": 0.07, "grad_norm": 1.3233476494713812, "learning_rate": 1.9913701482033008e-05, "loss": 1.0142, "step": 367 }, { "epoch": 0.07, "grad_norm": 1.0636795754807116, "learning_rate": 1.9912882740800336e-05, "loss": 0.9143, "step": 368 }, { "epoch": 0.07, "grad_norm": 1.1298647093373568, "learning_rate": 1.9912060151045273e-05, "loss": 0.9719, "step": 369 }, { "epoch": 0.07, "grad_norm": 1.172521350750779, "learning_rate": 1.9911233713087172e-05, "loss": 0.9304, "step": 370 }, { "epoch": 0.07, "grad_norm": 0.9493549611236642, "learning_rate": 1.9910403427246895e-05, "loss": 0.6462, "step": 371 }, { "epoch": 0.07, "grad_norm": 1.070086080207283, "learning_rate": 1.990956929384678e-05, "loss": 0.9197, "step": 372 }, { "epoch": 0.07, "grad_norm": 1.1649480220160084, "learning_rate": 1.990873131321067e-05, "loss": 1.0151, "step": 373 }, { "epoch": 0.07, "grad_norm": 1.1179545586271413, "learning_rate": 1.9907889485663897e-05, "loss": 0.9836, "step": 374 }, { "epoch": 0.07, "grad_norm": 1.1082755722310274, "learning_rate": 1.9907043811533283e-05, "loss": 0.9124, "step": 375 }, { "epoch": 0.07, "grad_norm": 1.1281842997134532, "learning_rate": 1.9906194291147155e-05, "loss": 0.968, "step": 376 }, { "epoch": 0.07, "grad_norm": 1.0257995821957306, "learning_rate": 1.9905340924835322e-05, "loss": 0.9417, "step": 377 }, { "epoch": 0.07, "grad_norm": 1.2222067066306619, "learning_rate": 1.9904483712929094e-05, "loss": 0.9612, "step": 378 }, { "epoch": 0.07, "grad_norm": 1.4562017160605283, "learning_rate": 1.9903622655761267e-05, "loss": 0.9709, "step": 379 }, { "epoch": 0.07, "grad_norm": 1.1100671455504927, "learning_rate": 1.990275775366613e-05, "loss": 0.6439, "step": 380 }, { "epoch": 0.07, "grad_norm": 1.1604213947455433, "learning_rate": 1.9901889006979473e-05, "loss": 0.9414, "step": 381 }, { "epoch": 0.07, "grad_norm": 1.27026522033468, "learning_rate": 1.990101641603857e-05, "loss": 0.9241, "step": 382 }, { "epoch": 0.07, "grad_norm": 1.1111206894379353, "learning_rate": 1.9900139981182193e-05, "loss": 0.9937, "step": 383 }, { "epoch": 0.07, "grad_norm": 1.1294521085391933, "learning_rate": 1.9899259702750604e-05, "loss": 0.9636, "step": 384 }, { "epoch": 0.07, "grad_norm": 1.0375630339287703, "learning_rate": 1.9898375581085555e-05, "loss": 0.9556, "step": 385 }, { "epoch": 0.07, "grad_norm": 1.3570360848168295, "learning_rate": 1.9897487616530296e-05, "loss": 0.9585, "step": 386 }, { "epoch": 0.07, "grad_norm": 1.0810056271874358, "learning_rate": 1.9896595809429565e-05, "loss": 0.9521, "step": 387 }, { "epoch": 0.07, "grad_norm": 1.327359097016251, "learning_rate": 1.9895700160129593e-05, "loss": 0.8767, "step": 388 }, { "epoch": 0.07, "grad_norm": 1.2908133717698231, "learning_rate": 1.9894800668978095e-05, "loss": 1.0154, "step": 389 }, { "epoch": 0.08, "grad_norm": 1.1085625898751712, "learning_rate": 1.9893897336324292e-05, "loss": 0.949, "step": 390 }, { "epoch": 0.08, "grad_norm": 1.2021003542316369, "learning_rate": 1.9892990162518884e-05, "loss": 0.9346, "step": 391 }, { "epoch": 0.08, "grad_norm": 1.2543422247055005, "learning_rate": 1.9892079147914072e-05, "loss": 0.9885, "step": 392 }, { "epoch": 0.08, "grad_norm": 1.3052302961741844, "learning_rate": 1.9891164292863537e-05, "loss": 1.0532, "step": 393 }, { "epoch": 0.08, "grad_norm": 1.2382124496624891, "learning_rate": 1.9890245597722465e-05, "loss": 0.9761, "step": 394 }, { "epoch": 0.08, "grad_norm": 0.9988638798460994, "learning_rate": 1.9889323062847516e-05, "loss": 0.6049, "step": 395 }, { "epoch": 0.08, "grad_norm": 1.185044434725718, "learning_rate": 1.988839668859686e-05, "loss": 0.9602, "step": 396 }, { "epoch": 0.08, "grad_norm": 1.2187175297461776, "learning_rate": 1.988746647533014e-05, "loss": 0.9385, "step": 397 }, { "epoch": 0.08, "grad_norm": 1.1012108299361811, "learning_rate": 1.9886532423408495e-05, "loss": 0.9546, "step": 398 }, { "epoch": 0.08, "grad_norm": 1.1786723148351825, "learning_rate": 1.9885594533194564e-05, "loss": 0.9519, "step": 399 }, { "epoch": 0.08, "grad_norm": 1.0813077558922772, "learning_rate": 1.9884652805052465e-05, "loss": 0.9753, "step": 400 }, { "epoch": 0.08, "grad_norm": 1.1361508388672934, "learning_rate": 1.9883707239347804e-05, "loss": 0.9644, "step": 401 }, { "epoch": 0.08, "grad_norm": 1.0004230194533141, "learning_rate": 1.988275783644769e-05, "loss": 0.9902, "step": 402 }, { "epoch": 0.08, "grad_norm": 1.1263817358425168, "learning_rate": 1.988180459672071e-05, "loss": 0.9551, "step": 403 }, { "epoch": 0.08, "grad_norm": 1.115686034242195, "learning_rate": 1.988084752053695e-05, "loss": 0.9216, "step": 404 }, { "epoch": 0.08, "grad_norm": 1.0377015236870242, "learning_rate": 1.9879886608267967e-05, "loss": 0.96, "step": 405 }, { "epoch": 0.08, "grad_norm": 1.2011204189040883, "learning_rate": 1.9878921860286832e-05, "loss": 0.9788, "step": 406 }, { "epoch": 0.08, "grad_norm": 1.1397586691973791, "learning_rate": 1.9877953276968088e-05, "loss": 0.9832, "step": 407 }, { "epoch": 0.08, "grad_norm": 1.0338068450758284, "learning_rate": 1.9876980858687777e-05, "loss": 0.9414, "step": 408 }, { "epoch": 0.08, "grad_norm": 1.1268451078396302, "learning_rate": 1.9876004605823417e-05, "loss": 0.9927, "step": 409 }, { "epoch": 0.08, "grad_norm": 1.3205093176781955, "learning_rate": 1.987502451875403e-05, "loss": 0.9866, "step": 410 }, { "epoch": 0.08, "grad_norm": 1.2039521802233109, "learning_rate": 1.987404059786012e-05, "loss": 0.9541, "step": 411 }, { "epoch": 0.08, "grad_norm": 1.0923210499663456, "learning_rate": 1.9873052843523676e-05, "loss": 0.9863, "step": 412 }, { "epoch": 0.08, "grad_norm": 1.0651822246383418, "learning_rate": 1.987206125612818e-05, "loss": 0.9634, "step": 413 }, { "epoch": 0.08, "grad_norm": 1.1109015604837293, "learning_rate": 1.98710658360586e-05, "loss": 0.9543, "step": 414 }, { "epoch": 0.08, "grad_norm": 1.1281205112907555, "learning_rate": 1.987006658370139e-05, "loss": 0.998, "step": 415 }, { "epoch": 0.08, "grad_norm": 1.2666530444256845, "learning_rate": 1.9869063499444495e-05, "loss": 0.9509, "step": 416 }, { "epoch": 0.08, "grad_norm": 1.2062312348294681, "learning_rate": 1.9868056583677346e-05, "loss": 0.9912, "step": 417 }, { "epoch": 0.08, "grad_norm": 0.9375100530144991, "learning_rate": 1.9867045836790867e-05, "loss": 0.6395, "step": 418 }, { "epoch": 0.08, "grad_norm": 1.1680770125336921, "learning_rate": 1.9866031259177463e-05, "loss": 0.9351, "step": 419 }, { "epoch": 0.08, "grad_norm": 1.0830235454321218, "learning_rate": 1.9865012851231022e-05, "loss": 0.9402, "step": 420 }, { "epoch": 0.08, "grad_norm": 0.8609054885789527, "learning_rate": 1.9863990613346936e-05, "loss": 0.6198, "step": 421 }, { "epoch": 0.08, "grad_norm": 1.2463091644279467, "learning_rate": 1.986296454592206e-05, "loss": 0.9236, "step": 422 }, { "epoch": 0.08, "grad_norm": 1.2196917763705792, "learning_rate": 1.9861934649354763e-05, "loss": 0.9878, "step": 423 }, { "epoch": 0.08, "grad_norm": 1.1767807093644334, "learning_rate": 1.9860900924044873e-05, "loss": 1.0181, "step": 424 }, { "epoch": 0.08, "grad_norm": 1.2135325432418764, "learning_rate": 1.9859863370393726e-05, "loss": 0.9751, "step": 425 }, { "epoch": 0.08, "grad_norm": 1.0160305171881254, "learning_rate": 1.9858821988804132e-05, "loss": 0.6306, "step": 426 }, { "epoch": 0.08, "grad_norm": 1.3091725699088845, "learning_rate": 1.9857776779680393e-05, "loss": 0.9746, "step": 427 }, { "epoch": 0.08, "grad_norm": 1.2167626587739597, "learning_rate": 1.98567277434283e-05, "loss": 0.9736, "step": 428 }, { "epoch": 0.08, "grad_norm": 1.1458533530942818, "learning_rate": 1.9855674880455115e-05, "loss": 0.9866, "step": 429 }, { "epoch": 0.08, "grad_norm": 1.1084668575293133, "learning_rate": 1.98546181911696e-05, "loss": 0.9983, "step": 430 }, { "epoch": 0.08, "grad_norm": 1.1692780110468812, "learning_rate": 1.9853557675982e-05, "loss": 0.9695, "step": 431 }, { "epoch": 0.08, "grad_norm": 1.1570032446501404, "learning_rate": 1.985249333530404e-05, "loss": 0.9692, "step": 432 }, { "epoch": 0.08, "grad_norm": 1.1767252291327333, "learning_rate": 1.9851425169548938e-05, "loss": 0.9885, "step": 433 }, { "epoch": 0.08, "grad_norm": 0.9126408117988579, "learning_rate": 1.9850353179131392e-05, "loss": 0.6505, "step": 434 }, { "epoch": 0.08, "grad_norm": 1.1041365402079046, "learning_rate": 1.9849277364467585e-05, "loss": 0.9531, "step": 435 }, { "epoch": 0.08, "grad_norm": 1.0540645236356527, "learning_rate": 1.984819772597518e-05, "loss": 0.9819, "step": 436 }, { "epoch": 0.08, "grad_norm": 1.0526116575867068, "learning_rate": 1.9847114264073336e-05, "loss": 0.978, "step": 437 }, { "epoch": 0.08, "grad_norm": 1.216960442495867, "learning_rate": 1.984602697918269e-05, "loss": 0.9426, "step": 438 }, { "epoch": 0.08, "grad_norm": 1.0586758347302045, "learning_rate": 1.9844935871725363e-05, "loss": 0.9756, "step": 439 }, { "epoch": 0.08, "grad_norm": 1.1244461379595785, "learning_rate": 1.9843840942124956e-05, "loss": 0.9644, "step": 440 }, { "epoch": 0.08, "grad_norm": 1.1673617021369718, "learning_rate": 1.9842742190806566e-05, "loss": 0.9756, "step": 441 }, { "epoch": 0.09, "grad_norm": 1.0754695927080284, "learning_rate": 1.984163961819676e-05, "loss": 0.9814, "step": 442 }, { "epoch": 0.09, "grad_norm": 1.170579620302529, "learning_rate": 1.9840533224723595e-05, "loss": 0.8972, "step": 443 }, { "epoch": 0.09, "grad_norm": 1.074451307786026, "learning_rate": 1.9839423010816616e-05, "loss": 0.9634, "step": 444 }, { "epoch": 0.09, "grad_norm": 1.0942948097818337, "learning_rate": 1.983830897690684e-05, "loss": 0.9761, "step": 445 }, { "epoch": 0.09, "grad_norm": 1.183153291421381, "learning_rate": 1.9837191123426777e-05, "loss": 1.0266, "step": 446 }, { "epoch": 0.09, "grad_norm": 1.2005928289523782, "learning_rate": 1.983606945081042e-05, "loss": 0.9121, "step": 447 }, { "epoch": 0.09, "grad_norm": 1.099011372513049, "learning_rate": 1.983494395949323e-05, "loss": 0.9636, "step": 448 }, { "epoch": 0.09, "grad_norm": 1.068534937334229, "learning_rate": 1.983381464991217e-05, "loss": 0.9712, "step": 449 }, { "epoch": 0.09, "grad_norm": 1.4359306513386392, "learning_rate": 1.9832681522505676e-05, "loss": 0.9966, "step": 450 }, { "epoch": 0.09, "grad_norm": 1.1006249699698867, "learning_rate": 1.9831544577713663e-05, "loss": 0.9675, "step": 451 }, { "epoch": 0.09, "grad_norm": 1.311239854897358, "learning_rate": 1.983040381597754e-05, "loss": 0.9983, "step": 452 }, { "epoch": 0.09, "grad_norm": 1.1357841975937024, "learning_rate": 1.982925923774018e-05, "loss": 0.9363, "step": 453 }, { "epoch": 0.09, "grad_norm": 0.9852554543318824, "learning_rate": 1.9828110843445954e-05, "loss": 0.672, "step": 454 }, { "epoch": 0.09, "grad_norm": 0.9549788143542691, "learning_rate": 1.982695863354071e-05, "loss": 0.6002, "step": 455 }, { "epoch": 0.09, "grad_norm": 1.1583337396561242, "learning_rate": 1.9825802608471767e-05, "loss": 0.9397, "step": 456 }, { "epoch": 0.09, "grad_norm": 0.9334311318723065, "learning_rate": 1.982464276868794e-05, "loss": 0.7101, "step": 457 }, { "epoch": 0.09, "grad_norm": 1.221651845190886, "learning_rate": 1.982347911463952e-05, "loss": 0.9968, "step": 458 }, { "epoch": 0.09, "grad_norm": 1.2394227601247227, "learning_rate": 1.9822311646778277e-05, "loss": 0.958, "step": 459 }, { "epoch": 0.09, "grad_norm": 1.07313308788259, "learning_rate": 1.982114036555746e-05, "loss": 0.9673, "step": 460 }, { "epoch": 0.09, "grad_norm": 0.9963539523480119, "learning_rate": 1.9819965271431797e-05, "loss": 0.9829, "step": 461 }, { "epoch": 0.09, "grad_norm": 1.273989333705547, "learning_rate": 1.9818786364857506e-05, "loss": 0.9675, "step": 462 }, { "epoch": 0.09, "grad_norm": 1.4171396072989744, "learning_rate": 1.9817603646292278e-05, "loss": 0.959, "step": 463 }, { "epoch": 0.09, "grad_norm": 1.2583668676273945, "learning_rate": 1.9816417116195287e-05, "loss": 1.0146, "step": 464 }, { "epoch": 0.09, "grad_norm": 1.333813499792961, "learning_rate": 1.9815226775027182e-05, "loss": 0.9412, "step": 465 }, { "epoch": 0.09, "grad_norm": 1.2380142544559027, "learning_rate": 1.9814032623250093e-05, "loss": 0.9636, "step": 466 }, { "epoch": 0.09, "grad_norm": 1.2432398842256194, "learning_rate": 1.9812834661327632e-05, "loss": 0.9602, "step": 467 }, { "epoch": 0.09, "grad_norm": 1.1213517338707828, "learning_rate": 1.9811632889724888e-05, "loss": 0.9771, "step": 468 }, { "epoch": 0.09, "grad_norm": 1.0982108573169174, "learning_rate": 1.9810427308908437e-05, "loss": 1.0083, "step": 469 }, { "epoch": 0.09, "grad_norm": 1.1777968647100743, "learning_rate": 1.9809217919346318e-05, "loss": 0.9385, "step": 470 }, { "epoch": 0.09, "grad_norm": 1.1725788260894072, "learning_rate": 1.980800472150806e-05, "loss": 0.9651, "step": 471 }, { "epoch": 0.09, "grad_norm": 1.1288378664485517, "learning_rate": 1.9806787715864674e-05, "loss": 0.9692, "step": 472 }, { "epoch": 0.09, "grad_norm": 1.347717964445497, "learning_rate": 1.9805566902888637e-05, "loss": 1.0085, "step": 473 }, { "epoch": 0.09, "grad_norm": 1.1626224937733782, "learning_rate": 1.9804342283053916e-05, "loss": 0.9578, "step": 474 }, { "epoch": 0.09, "grad_norm": 1.3187296998929912, "learning_rate": 1.980311385683594e-05, "loss": 0.9807, "step": 475 }, { "epoch": 0.09, "grad_norm": 1.1575780105494218, "learning_rate": 1.980188162471164e-05, "loss": 0.948, "step": 476 }, { "epoch": 0.09, "grad_norm": 1.0626748123971512, "learning_rate": 1.98006455871594e-05, "loss": 0.967, "step": 477 }, { "epoch": 0.09, "grad_norm": 1.416892319623044, "learning_rate": 1.97994057446591e-05, "loss": 0.6248, "step": 478 }, { "epoch": 0.09, "grad_norm": 1.1893042700663585, "learning_rate": 1.979816209769209e-05, "loss": 0.6736, "step": 479 }, { "epoch": 0.09, "grad_norm": 1.1242796250069627, "learning_rate": 1.9796914646741187e-05, "loss": 0.9609, "step": 480 }, { "epoch": 0.09, "grad_norm": 0.9533806036969469, "learning_rate": 1.9795663392290702e-05, "loss": 0.6623, "step": 481 }, { "epoch": 0.09, "grad_norm": 1.1317929275345373, "learning_rate": 1.9794408334826415e-05, "loss": 0.9636, "step": 482 }, { "epoch": 0.09, "grad_norm": 1.0933287784408514, "learning_rate": 1.979314947483558e-05, "loss": 0.9546, "step": 483 }, { "epoch": 0.09, "grad_norm": 1.154030830727427, "learning_rate": 1.9791886812806932e-05, "loss": 0.9886, "step": 484 }, { "epoch": 0.09, "grad_norm": 1.1404981195576427, "learning_rate": 1.9790620349230676e-05, "loss": 0.9692, "step": 485 }, { "epoch": 0.09, "grad_norm": 1.1065537139923658, "learning_rate": 1.9789350084598504e-05, "loss": 0.9568, "step": 486 }, { "epoch": 0.09, "grad_norm": 1.0405961044841874, "learning_rate": 1.9788076019403565e-05, "loss": 0.9646, "step": 487 }, { "epoch": 0.09, "grad_norm": 1.1782849408399731, "learning_rate": 1.9786798154140507e-05, "loss": 1.0022, "step": 488 }, { "epoch": 0.09, "grad_norm": 1.1013321737185378, "learning_rate": 1.9785516489305437e-05, "loss": 0.9512, "step": 489 }, { "epoch": 0.09, "grad_norm": 1.0523153565483803, "learning_rate": 1.9784231025395936e-05, "loss": 0.9348, "step": 490 }, { "epoch": 0.09, "grad_norm": 1.18076114042459, "learning_rate": 1.9782941762911075e-05, "loss": 0.9692, "step": 491 }, { "epoch": 0.09, "grad_norm": 1.2767187322483053, "learning_rate": 1.9781648702351383e-05, "loss": 0.9744, "step": 492 }, { "epoch": 0.09, "grad_norm": 1.0415955641565044, "learning_rate": 1.9780351844218874e-05, "loss": 0.9197, "step": 493 }, { "epoch": 0.1, "grad_norm": 1.076169696777964, "learning_rate": 1.977905118901703e-05, "loss": 0.9553, "step": 494 }, { "epoch": 0.1, "grad_norm": 1.1793598958045386, "learning_rate": 1.977774673725081e-05, "loss": 0.9763, "step": 495 }, { "epoch": 0.1, "grad_norm": 1.2219133984466461, "learning_rate": 1.977643848942665e-05, "loss": 0.957, "step": 496 }, { "epoch": 0.1, "grad_norm": 1.1503270523092686, "learning_rate": 1.977512644605246e-05, "loss": 0.9648, "step": 497 }, { "epoch": 0.1, "grad_norm": 1.112878111159377, "learning_rate": 1.9773810607637612e-05, "loss": 0.9001, "step": 498 }, { "epoch": 0.1, "grad_norm": 1.050304419318986, "learning_rate": 1.9772490974692962e-05, "loss": 0.9568, "step": 499 }, { "epoch": 0.1, "grad_norm": 1.0209430283311605, "learning_rate": 1.9771167547730844e-05, "loss": 0.9604, "step": 500 }, { "epoch": 0.1, "grad_norm": 1.205537038594498, "learning_rate": 1.976984032726505e-05, "loss": 1.0491, "step": 501 }, { "epoch": 0.1, "grad_norm": 1.1271613383624874, "learning_rate": 1.976850931381086e-05, "loss": 0.9419, "step": 502 }, { "epoch": 0.1, "grad_norm": 1.167018988632749, "learning_rate": 1.976717450788501e-05, "loss": 0.9631, "step": 503 }, { "epoch": 0.1, "grad_norm": 1.1351649600224507, "learning_rate": 1.9765835910005726e-05, "loss": 0.9275, "step": 504 }, { "epoch": 0.1, "grad_norm": 1.1462478066662483, "learning_rate": 1.9764493520692685e-05, "loss": 0.9238, "step": 505 }, { "epoch": 0.1, "grad_norm": 1.168709323998861, "learning_rate": 1.9763147340467067e-05, "loss": 0.6768, "step": 506 }, { "epoch": 0.1, "grad_norm": 1.1564925442210077, "learning_rate": 1.9761797369851498e-05, "loss": 0.9492, "step": 507 }, { "epoch": 0.1, "grad_norm": 1.3924273011977726, "learning_rate": 1.9760443609370074e-05, "loss": 0.978, "step": 508 }, { "epoch": 0.1, "grad_norm": 1.1091022617919768, "learning_rate": 1.975908605954838e-05, "loss": 0.8936, "step": 509 }, { "epoch": 0.1, "grad_norm": 1.099952604802854, "learning_rate": 1.9757724720913466e-05, "loss": 0.981, "step": 510 }, { "epoch": 0.1, "grad_norm": 1.119073830437072, "learning_rate": 1.9756359593993845e-05, "loss": 0.9683, "step": 511 }, { "epoch": 0.1, "grad_norm": 1.1357853161510696, "learning_rate": 1.975499067931951e-05, "loss": 1.0098, "step": 512 }, { "epoch": 0.1, "grad_norm": 1.310235950238609, "learning_rate": 1.975361797742192e-05, "loss": 0.988, "step": 513 }, { "epoch": 0.1, "grad_norm": 1.1744797448271733, "learning_rate": 1.9752241488834002e-05, "loss": 0.9534, "step": 514 }, { "epoch": 0.1, "grad_norm": 1.180558210653402, "learning_rate": 1.975086121409016e-05, "loss": 0.9412, "step": 515 }, { "epoch": 0.1, "grad_norm": 1.089924639046605, "learning_rate": 1.974947715372626e-05, "loss": 0.9919, "step": 516 }, { "epoch": 0.1, "grad_norm": 1.317820317476366, "learning_rate": 1.974808930827965e-05, "loss": 0.9607, "step": 517 }, { "epoch": 0.1, "grad_norm": 1.2279242373688815, "learning_rate": 1.9746697678289128e-05, "loss": 0.9741, "step": 518 }, { "epoch": 0.1, "grad_norm": 1.2258475482275475, "learning_rate": 1.9745302264294982e-05, "loss": 0.9058, "step": 519 }, { "epoch": 0.1, "grad_norm": 0.8756782394271861, "learning_rate": 1.9743903066838954e-05, "loss": 0.6506, "step": 520 }, { "epoch": 0.1, "grad_norm": 1.1287743454648442, "learning_rate": 1.9742500086464266e-05, "loss": 0.9146, "step": 521 }, { "epoch": 0.1, "grad_norm": 1.1357329727792895, "learning_rate": 1.9741093323715597e-05, "loss": 0.9321, "step": 522 }, { "epoch": 0.1, "grad_norm": 0.9751509110832239, "learning_rate": 1.9739682779139107e-05, "loss": 0.6003, "step": 523 }, { "epoch": 0.1, "grad_norm": 1.1621416572286334, "learning_rate": 1.9738268453282414e-05, "loss": 0.9492, "step": 524 }, { "epoch": 0.1, "grad_norm": 1.3462733007571208, "learning_rate": 1.9736850346694608e-05, "loss": 0.9834, "step": 525 }, { "epoch": 0.1, "grad_norm": 0.8137759800221339, "learning_rate": 1.973542845992625e-05, "loss": 0.644, "step": 526 }, { "epoch": 0.1, "grad_norm": 1.1888295852598643, "learning_rate": 1.9734002793529362e-05, "loss": 0.978, "step": 527 }, { "epoch": 0.1, "grad_norm": 1.3064109118496712, "learning_rate": 1.9732573348057437e-05, "loss": 0.9585, "step": 528 }, { "epoch": 0.1, "grad_norm": 0.9747714861514514, "learning_rate": 1.973114012406544e-05, "loss": 0.6436, "step": 529 }, { "epoch": 0.1, "grad_norm": 1.2048705322535214, "learning_rate": 1.9729703122109788e-05, "loss": 1.0259, "step": 530 }, { "epoch": 0.1, "grad_norm": 1.232256582030206, "learning_rate": 1.9728262342748384e-05, "loss": 0.9946, "step": 531 }, { "epoch": 0.1, "grad_norm": 1.045524375115536, "learning_rate": 1.9726817786540584e-05, "loss": 0.9441, "step": 532 }, { "epoch": 0.1, "grad_norm": 1.1703502059195414, "learning_rate": 1.9725369454047215e-05, "loss": 0.9785, "step": 533 }, { "epoch": 0.1, "grad_norm": 1.1553035798255977, "learning_rate": 1.9723917345830568e-05, "loss": 0.9771, "step": 534 }, { "epoch": 0.1, "grad_norm": 1.2590909629889018, "learning_rate": 1.9722461462454405e-05, "loss": 0.9414, "step": 535 }, { "epoch": 0.1, "grad_norm": 1.392425827724281, "learning_rate": 1.9721001804483947e-05, "loss": 0.9866, "step": 536 }, { "epoch": 0.1, "grad_norm": 1.124754810891678, "learning_rate": 1.9719538372485887e-05, "loss": 0.936, "step": 537 }, { "epoch": 0.1, "grad_norm": 1.2199479269482283, "learning_rate": 1.9718071167028376e-05, "loss": 0.9482, "step": 538 }, { "epoch": 0.1, "grad_norm": 1.1189501140043343, "learning_rate": 1.9716600188681038e-05, "loss": 0.9556, "step": 539 }, { "epoch": 0.1, "grad_norm": 1.1207559110596272, "learning_rate": 1.971512543801495e-05, "loss": 0.9817, "step": 540 }, { "epoch": 0.1, "grad_norm": 1.1404497831795, "learning_rate": 1.9713646915602663e-05, "loss": 0.9465, "step": 541 }, { "epoch": 0.1, "grad_norm": 1.0842796353145263, "learning_rate": 1.9712164622018197e-05, "loss": 0.9148, "step": 542 }, { "epoch": 0.1, "grad_norm": 1.0689576962804581, "learning_rate": 1.9710678557837024e-05, "loss": 0.9309, "step": 543 }, { "epoch": 0.1, "grad_norm": 1.1682994200609924, "learning_rate": 1.9709188723636088e-05, "loss": 0.9219, "step": 544 }, { "epoch": 0.1, "grad_norm": 1.0995542891884307, "learning_rate": 1.970769511999379e-05, "loss": 0.9451, "step": 545 }, { "epoch": 0.11, "grad_norm": 1.105640805952857, "learning_rate": 1.9706197747490004e-05, "loss": 0.9854, "step": 546 }, { "epoch": 0.11, "grad_norm": 1.0731665942164608, "learning_rate": 1.9704696606706055e-05, "loss": 0.9441, "step": 547 }, { "epoch": 0.11, "grad_norm": 1.224511514142387, "learning_rate": 1.9703191698224742e-05, "loss": 1.0183, "step": 548 }, { "epoch": 0.11, "grad_norm": 1.1182880039322274, "learning_rate": 1.9701683022630323e-05, "loss": 0.9822, "step": 549 }, { "epoch": 0.11, "grad_norm": 1.2658917707371922, "learning_rate": 1.9700170580508514e-05, "loss": 0.9717, "step": 550 }, { "epoch": 0.11, "grad_norm": 1.2059426516260126, "learning_rate": 1.9698654372446495e-05, "loss": 1.032, "step": 551 }, { "epoch": 0.11, "grad_norm": 0.9852252243350355, "learning_rate": 1.969713439903292e-05, "loss": 0.9653, "step": 552 }, { "epoch": 0.11, "grad_norm": 1.0033465747541013, "learning_rate": 1.9695610660857886e-05, "loss": 0.9695, "step": 553 }, { "epoch": 0.11, "grad_norm": 1.1307331654677661, "learning_rate": 1.9694083158512965e-05, "loss": 0.895, "step": 554 }, { "epoch": 0.11, "grad_norm": 0.8934887298879918, "learning_rate": 1.9692551892591185e-05, "loss": 0.6564, "step": 555 }, { "epoch": 0.11, "grad_norm": 1.1133387404371238, "learning_rate": 1.9691016863687037e-05, "loss": 0.9487, "step": 556 }, { "epoch": 0.11, "grad_norm": 1.1410821345032376, "learning_rate": 1.968947807239647e-05, "loss": 0.9272, "step": 557 }, { "epoch": 0.11, "grad_norm": 1.0140249386476192, "learning_rate": 1.9687935519316897e-05, "loss": 0.9492, "step": 558 }, { "epoch": 0.11, "grad_norm": 0.9152090104121787, "learning_rate": 1.9686389205047186e-05, "loss": 0.6281, "step": 559 }, { "epoch": 0.11, "grad_norm": 1.1283122675095316, "learning_rate": 1.9684839130187678e-05, "loss": 0.9519, "step": 560 }, { "epoch": 0.11, "grad_norm": 1.2531067153763216, "learning_rate": 1.968328529534016e-05, "loss": 0.9172, "step": 561 }, { "epoch": 0.11, "grad_norm": 1.1890084491699784, "learning_rate": 1.9681727701107885e-05, "loss": 0.9326, "step": 562 }, { "epoch": 0.11, "grad_norm": 1.0943694740336447, "learning_rate": 1.9680166348095568e-05, "loss": 0.9087, "step": 563 }, { "epoch": 0.11, "grad_norm": 1.1601978375425797, "learning_rate": 1.967860123690937e-05, "loss": 0.9741, "step": 564 }, { "epoch": 0.11, "grad_norm": 1.1899624336632608, "learning_rate": 1.9677032368156934e-05, "loss": 0.9873, "step": 565 }, { "epoch": 0.11, "grad_norm": 1.10782455258209, "learning_rate": 1.967545974244734e-05, "loss": 0.9443, "step": 566 }, { "epoch": 0.11, "grad_norm": 1.1486230679212028, "learning_rate": 1.9673883360391138e-05, "loss": 1.0029, "step": 567 }, { "epoch": 0.11, "grad_norm": 1.0127552266730546, "learning_rate": 1.9672303222600333e-05, "loss": 0.9707, "step": 568 }, { "epoch": 0.11, "grad_norm": 1.1577010914111636, "learning_rate": 1.967071932968839e-05, "loss": 0.95, "step": 569 }, { "epoch": 0.11, "grad_norm": 1.3171582472427508, "learning_rate": 1.9669131682270232e-05, "loss": 0.9727, "step": 570 }, { "epoch": 0.11, "grad_norm": 0.9862774727345232, "learning_rate": 1.9667540280962235e-05, "loss": 0.9104, "step": 571 }, { "epoch": 0.11, "grad_norm": 1.0631554804575154, "learning_rate": 1.966594512638224e-05, "loss": 0.9805, "step": 572 }, { "epoch": 0.11, "grad_norm": 1.106210918421462, "learning_rate": 1.9664346219149538e-05, "loss": 0.9717, "step": 573 }, { "epoch": 0.11, "grad_norm": 1.1629906222141868, "learning_rate": 1.966274355988488e-05, "loss": 0.998, "step": 574 }, { "epoch": 0.11, "grad_norm": 0.8424056061023073, "learning_rate": 1.9661137149210473e-05, "loss": 0.6361, "step": 575 }, { "epoch": 0.11, "grad_norm": 1.1500430486732505, "learning_rate": 1.9659526987749987e-05, "loss": 1.041, "step": 576 }, { "epoch": 0.11, "grad_norm": 1.0645091919175829, "learning_rate": 1.9657913076128532e-05, "loss": 0.9617, "step": 577 }, { "epoch": 0.11, "grad_norm": 1.2466642961130183, "learning_rate": 1.965629541497269e-05, "loss": 1.0044, "step": 578 }, { "epoch": 0.11, "grad_norm": 0.9481867325652029, "learning_rate": 1.9654674004910493e-05, "loss": 0.6272, "step": 579 }, { "epoch": 0.11, "grad_norm": 1.1918741093174898, "learning_rate": 1.9653048846571427e-05, "loss": 0.9272, "step": 580 }, { "epoch": 0.11, "grad_norm": 1.2749767615953476, "learning_rate": 1.9651419940586437e-05, "loss": 0.9963, "step": 581 }, { "epoch": 0.11, "grad_norm": 1.172390627472578, "learning_rate": 1.964978728758791e-05, "loss": 0.9612, "step": 582 }, { "epoch": 0.11, "grad_norm": 1.3534348981213977, "learning_rate": 1.9648150888209715e-05, "loss": 0.9932, "step": 583 }, { "epoch": 0.11, "grad_norm": 1.1379985579139007, "learning_rate": 1.9646510743087144e-05, "loss": 0.9143, "step": 584 }, { "epoch": 0.11, "grad_norm": 1.0658404639484962, "learning_rate": 1.964486685285697e-05, "loss": 0.9775, "step": 585 }, { "epoch": 0.11, "grad_norm": 1.188838639503324, "learning_rate": 1.9643219218157395e-05, "loss": 0.9795, "step": 586 }, { "epoch": 0.11, "grad_norm": 1.230402333117102, "learning_rate": 1.9641567839628092e-05, "loss": 0.9126, "step": 587 }, { "epoch": 0.11, "grad_norm": 1.1708679505452424, "learning_rate": 1.963991271791019e-05, "loss": 0.9233, "step": 588 }, { "epoch": 0.11, "grad_norm": 1.07939298802732, "learning_rate": 1.9638253853646255e-05, "loss": 0.9373, "step": 589 }, { "epoch": 0.11, "grad_norm": 1.1173523348010859, "learning_rate": 1.9636591247480323e-05, "loss": 0.9707, "step": 590 }, { "epoch": 0.11, "grad_norm": 1.1084080707240662, "learning_rate": 1.9634924900057867e-05, "loss": 0.939, "step": 591 }, { "epoch": 0.11, "grad_norm": 0.8239157504499409, "learning_rate": 1.963325481202583e-05, "loss": 0.6256, "step": 592 }, { "epoch": 0.11, "grad_norm": 1.0538828284679382, "learning_rate": 1.963158098403259e-05, "loss": 0.9075, "step": 593 }, { "epoch": 0.11, "grad_norm": 0.8919318207443264, "learning_rate": 1.9629903416727987e-05, "loss": 0.6512, "step": 594 }, { "epoch": 0.11, "grad_norm": 1.1300511910604134, "learning_rate": 1.962822211076331e-05, "loss": 0.9485, "step": 595 }, { "epoch": 0.11, "grad_norm": 1.2260979334308797, "learning_rate": 1.96265370667913e-05, "loss": 0.9688, "step": 596 }, { "epoch": 0.11, "grad_norm": 0.9582337991246165, "learning_rate": 1.9624848285466146e-05, "loss": 0.948, "step": 597 }, { "epoch": 0.12, "grad_norm": 1.1280655112376015, "learning_rate": 1.9623155767443498e-05, "loss": 0.9246, "step": 598 }, { "epoch": 0.12, "grad_norm": 1.0467873081089256, "learning_rate": 1.9621459513380445e-05, "loss": 0.958, "step": 599 }, { "epoch": 0.12, "grad_norm": 1.2118506084524627, "learning_rate": 1.9619759523935532e-05, "loss": 0.9873, "step": 600 }, { "epoch": 0.12, "grad_norm": 1.1411148178602784, "learning_rate": 1.9618055799768757e-05, "loss": 1.0249, "step": 601 }, { "epoch": 0.12, "grad_norm": 1.333521324500097, "learning_rate": 1.961634834154156e-05, "loss": 1.031, "step": 602 }, { "epoch": 0.12, "grad_norm": 1.3043926331961153, "learning_rate": 1.9614637149916834e-05, "loss": 0.9585, "step": 603 }, { "epoch": 0.12, "grad_norm": 1.02336194377377, "learning_rate": 1.9612922225558924e-05, "loss": 0.97, "step": 604 }, { "epoch": 0.12, "grad_norm": 1.0341322724096602, "learning_rate": 1.961120356913363e-05, "loss": 0.8757, "step": 605 }, { "epoch": 0.12, "grad_norm": 1.047465411233035, "learning_rate": 1.960948118130818e-05, "loss": 0.6206, "step": 606 }, { "epoch": 0.12, "grad_norm": 1.0402757123566886, "learning_rate": 1.9607755062751273e-05, "loss": 0.9636, "step": 607 }, { "epoch": 0.12, "grad_norm": 1.1738489939775205, "learning_rate": 1.9606025214133046e-05, "loss": 0.9631, "step": 608 }, { "epoch": 0.12, "grad_norm": 1.1292364429984965, "learning_rate": 1.9604291636125084e-05, "loss": 0.9763, "step": 609 }, { "epoch": 0.12, "grad_norm": 0.8119533141333786, "learning_rate": 1.960255432940043e-05, "loss": 0.6522, "step": 610 }, { "epoch": 0.12, "grad_norm": 1.0223682563315255, "learning_rate": 1.9600813294633552e-05, "loss": 0.8928, "step": 611 }, { "epoch": 0.12, "grad_norm": 1.0000706718476422, "learning_rate": 1.9599068532500394e-05, "loss": 0.9077, "step": 612 }, { "epoch": 0.12, "grad_norm": 1.1655011172114615, "learning_rate": 1.9597320043678322e-05, "loss": 0.9883, "step": 613 }, { "epoch": 0.12, "grad_norm": 1.144277802110654, "learning_rate": 1.9595567828846166e-05, "loss": 0.9543, "step": 614 }, { "epoch": 0.12, "grad_norm": 1.0985614636883008, "learning_rate": 1.9593811888684192e-05, "loss": 0.979, "step": 615 }, { "epoch": 0.12, "grad_norm": 1.1001939947254828, "learning_rate": 1.9592052223874115e-05, "loss": 1.0107, "step": 616 }, { "epoch": 0.12, "grad_norm": 1.2841782022329813, "learning_rate": 1.959028883509911e-05, "loss": 0.9133, "step": 617 }, { "epoch": 0.12, "grad_norm": 1.0652615264122323, "learning_rate": 1.9588521723043764e-05, "loss": 0.946, "step": 618 }, { "epoch": 0.12, "grad_norm": 1.0572396740134715, "learning_rate": 1.958675088839415e-05, "loss": 0.9272, "step": 619 }, { "epoch": 0.12, "grad_norm": 1.1716641357570625, "learning_rate": 1.9584976331837758e-05, "loss": 0.9639, "step": 620 }, { "epoch": 0.12, "grad_norm": 0.9416284704488138, "learning_rate": 1.9583198054063535e-05, "loss": 0.627, "step": 621 }, { "epoch": 0.12, "grad_norm": 0.8386343380530233, "learning_rate": 1.9581416055761865e-05, "loss": 0.6041, "step": 622 }, { "epoch": 0.12, "grad_norm": 1.0860968689818167, "learning_rate": 1.9579630337624585e-05, "loss": 0.9817, "step": 623 }, { "epoch": 0.12, "grad_norm": 1.0921879786106965, "learning_rate": 1.9577840900344974e-05, "loss": 0.864, "step": 624 }, { "epoch": 0.12, "grad_norm": 1.1624577476945834, "learning_rate": 1.9576047744617752e-05, "loss": 0.9763, "step": 625 }, { "epoch": 0.12, "grad_norm": 0.9637420491175167, "learning_rate": 1.957425087113908e-05, "loss": 0.9219, "step": 626 }, { "epoch": 0.12, "grad_norm": 0.8491807662195093, "learning_rate": 1.9572450280606568e-05, "loss": 0.6343, "step": 627 }, { "epoch": 0.12, "grad_norm": 1.2298704937134228, "learning_rate": 1.9570645973719273e-05, "loss": 0.9873, "step": 628 }, { "epoch": 0.12, "grad_norm": 1.2620704916439989, "learning_rate": 1.9568837951177677e-05, "loss": 0.9309, "step": 629 }, { "epoch": 0.12, "grad_norm": 1.1777291297795796, "learning_rate": 1.9567026213683728e-05, "loss": 0.9668, "step": 630 }, { "epoch": 0.12, "grad_norm": 1.2087528755499333, "learning_rate": 1.9565210761940798e-05, "loss": 0.9597, "step": 631 }, { "epoch": 0.12, "grad_norm": 1.1406380539548837, "learning_rate": 1.956339159665371e-05, "loss": 0.9651, "step": 632 }, { "epoch": 0.12, "grad_norm": 1.0767000279645056, "learning_rate": 1.956156871852873e-05, "loss": 0.9719, "step": 633 }, { "epoch": 0.12, "grad_norm": 1.1640834568444611, "learning_rate": 1.9559742128273558e-05, "loss": 0.9778, "step": 634 }, { "epoch": 0.12, "grad_norm": 1.1710307300669824, "learning_rate": 1.9557911826597337e-05, "loss": 0.9634, "step": 635 }, { "epoch": 0.12, "grad_norm": 1.0825675010376647, "learning_rate": 1.9556077814210662e-05, "loss": 0.9458, "step": 636 }, { "epoch": 0.12, "grad_norm": 0.8991496496584994, "learning_rate": 1.955424009182555e-05, "loss": 0.6163, "step": 637 }, { "epoch": 0.12, "grad_norm": 1.1477178428052044, "learning_rate": 1.955239866015547e-05, "loss": 1.031, "step": 638 }, { "epoch": 0.12, "grad_norm": 1.0773462354286962, "learning_rate": 1.9550553519915335e-05, "loss": 0.9255, "step": 639 }, { "epoch": 0.12, "grad_norm": 0.8598502004864275, "learning_rate": 1.954870467182149e-05, "loss": 0.6657, "step": 640 }, { "epoch": 0.12, "grad_norm": 1.0499680307749668, "learning_rate": 1.954685211659172e-05, "loss": 0.9509, "step": 641 }, { "epoch": 0.12, "grad_norm": 1.1444559263727225, "learning_rate": 1.9544995854945248e-05, "loss": 0.9385, "step": 642 }, { "epoch": 0.12, "grad_norm": 0.8280471564708667, "learning_rate": 1.954313588760274e-05, "loss": 0.6236, "step": 643 }, { "epoch": 0.12, "grad_norm": 1.0859755186288462, "learning_rate": 1.9541272215286304e-05, "loss": 0.9971, "step": 644 }, { "epoch": 0.12, "grad_norm": 1.1199396856659367, "learning_rate": 1.9539404838719477e-05, "loss": 0.9303, "step": 645 }, { "epoch": 0.12, "grad_norm": 1.0663899516075843, "learning_rate": 1.9537533758627242e-05, "loss": 0.9519, "step": 646 }, { "epoch": 0.12, "grad_norm": 1.189671100255921, "learning_rate": 1.953565897573601e-05, "loss": 0.9377, "step": 647 }, { "epoch": 0.12, "grad_norm": 1.301959591270639, "learning_rate": 1.9533780490773645e-05, "loss": 0.957, "step": 648 }, { "epoch": 0.12, "grad_norm": 1.0728072100893187, "learning_rate": 1.9531898304469435e-05, "loss": 0.9619, "step": 649 }, { "epoch": 0.13, "grad_norm": 1.2657179744958509, "learning_rate": 1.953001241755411e-05, "loss": 0.9546, "step": 650 }, { "epoch": 0.13, "grad_norm": 1.1063459607220014, "learning_rate": 1.952812283075984e-05, "loss": 0.8821, "step": 651 }, { "epoch": 0.13, "grad_norm": 0.8152181216709391, "learning_rate": 1.952622954482022e-05, "loss": 0.6837, "step": 652 }, { "epoch": 0.13, "grad_norm": 1.0043679140186812, "learning_rate": 1.9524332560470293e-05, "loss": 0.9246, "step": 653 }, { "epoch": 0.13, "grad_norm": 1.1387835485895854, "learning_rate": 1.9522431878446536e-05, "loss": 0.9265, "step": 654 }, { "epoch": 0.13, "grad_norm": 1.0020555038181003, "learning_rate": 1.9520527499486856e-05, "loss": 0.8997, "step": 655 }, { "epoch": 0.13, "grad_norm": 1.0089739582049808, "learning_rate": 1.95186194243306e-05, "loss": 0.9373, "step": 656 }, { "epoch": 0.13, "grad_norm": 1.1845104799152977, "learning_rate": 1.9516707653718546e-05, "loss": 1.0081, "step": 657 }, { "epoch": 0.13, "grad_norm": 1.1667522618723898, "learning_rate": 1.9514792188392914e-05, "loss": 0.9377, "step": 658 }, { "epoch": 0.13, "grad_norm": 1.098137391602751, "learning_rate": 1.9512873029097347e-05, "loss": 0.9348, "step": 659 }, { "epoch": 0.13, "grad_norm": 1.0545626100576873, "learning_rate": 1.9510950176576933e-05, "loss": 0.9575, "step": 660 }, { "epoch": 0.13, "grad_norm": 1.1856396261168258, "learning_rate": 1.950902363157819e-05, "loss": 0.9346, "step": 661 }, { "epoch": 0.13, "grad_norm": 1.212146700874606, "learning_rate": 1.950709339484907e-05, "loss": 0.9731, "step": 662 }, { "epoch": 0.13, "grad_norm": 1.158000627203628, "learning_rate": 1.9505159467138954e-05, "loss": 0.9968, "step": 663 }, { "epoch": 0.13, "grad_norm": 0.9848674280933233, "learning_rate": 1.9503221849198655e-05, "loss": 0.9438, "step": 664 }, { "epoch": 0.13, "grad_norm": 1.1200134818419034, "learning_rate": 1.9501280541780435e-05, "loss": 0.6798, "step": 665 }, { "epoch": 0.13, "grad_norm": 1.2638179743975149, "learning_rate": 1.9499335545637968e-05, "loss": 0.9587, "step": 666 }, { "epoch": 0.13, "grad_norm": 1.1015088921380711, "learning_rate": 1.949738686152637e-05, "loss": 0.9834, "step": 667 }, { "epoch": 0.13, "grad_norm": 1.0986557445252072, "learning_rate": 1.9495434490202188e-05, "loss": 0.9668, "step": 668 }, { "epoch": 0.13, "grad_norm": 1.026901530685207, "learning_rate": 1.94934784324234e-05, "loss": 0.9551, "step": 669 }, { "epoch": 0.13, "grad_norm": 1.060719934766364, "learning_rate": 1.9491518688949417e-05, "loss": 0.9639, "step": 670 }, { "epoch": 0.13, "grad_norm": 1.3145099463941938, "learning_rate": 1.9489555260541074e-05, "loss": 0.9255, "step": 671 }, { "epoch": 0.13, "grad_norm": 1.2846587901003195, "learning_rate": 1.948758814796064e-05, "loss": 0.9302, "step": 672 }, { "epoch": 0.13, "grad_norm": 1.1189831378234532, "learning_rate": 1.9485617351971827e-05, "loss": 0.97, "step": 673 }, { "epoch": 0.13, "grad_norm": 1.2364325153503992, "learning_rate": 1.9483642873339753e-05, "loss": 0.9941, "step": 674 }, { "epoch": 0.13, "grad_norm": 1.0962919187024343, "learning_rate": 1.9481664712830987e-05, "loss": 0.9258, "step": 675 }, { "epoch": 0.13, "grad_norm": 1.0608225612537183, "learning_rate": 1.9479682871213515e-05, "loss": 0.9556, "step": 676 }, { "epoch": 0.13, "grad_norm": 1.1782445941120534, "learning_rate": 1.9477697349256756e-05, "loss": 0.9712, "step": 677 }, { "epoch": 0.13, "grad_norm": 1.038550040560395, "learning_rate": 1.947570814773156e-05, "loss": 0.9373, "step": 678 }, { "epoch": 0.13, "grad_norm": 1.127574776054642, "learning_rate": 1.9473715267410206e-05, "loss": 0.9824, "step": 679 }, { "epoch": 0.13, "grad_norm": 1.0731454476760394, "learning_rate": 1.9471718709066392e-05, "loss": 0.9626, "step": 680 }, { "epoch": 0.13, "grad_norm": 1.141597636234851, "learning_rate": 1.9469718473475256e-05, "loss": 1.0393, "step": 681 }, { "epoch": 0.13, "grad_norm": 1.0337496195129232, "learning_rate": 1.9467714561413358e-05, "loss": 0.9177, "step": 682 }, { "epoch": 0.13, "grad_norm": 0.8448725672047368, "learning_rate": 1.9465706973658683e-05, "loss": 0.653, "step": 683 }, { "epoch": 0.13, "grad_norm": 1.113844478080697, "learning_rate": 1.9463695710990648e-05, "loss": 0.9663, "step": 684 }, { "epoch": 0.13, "grad_norm": 1.0039935848639467, "learning_rate": 1.946168077419009e-05, "loss": 0.9326, "step": 685 }, { "epoch": 0.13, "grad_norm": 0.9927392311664884, "learning_rate": 1.9459662164039283e-05, "loss": 0.9377, "step": 686 }, { "epoch": 0.13, "grad_norm": 1.0893719501778905, "learning_rate": 1.9457639881321917e-05, "loss": 0.8948, "step": 687 }, { "epoch": 0.13, "grad_norm": 1.0289006655953534, "learning_rate": 1.9455613926823115e-05, "loss": 0.9656, "step": 688 }, { "epoch": 0.13, "grad_norm": 1.3497067823810704, "learning_rate": 1.945358430132942e-05, "loss": 0.9668, "step": 689 }, { "epoch": 0.13, "grad_norm": 1.101223730775677, "learning_rate": 1.9451551005628803e-05, "loss": 0.9678, "step": 690 }, { "epoch": 0.13, "grad_norm": 1.1270935852837725, "learning_rate": 1.9449514040510654e-05, "loss": 0.9192, "step": 691 }, { "epoch": 0.13, "grad_norm": 1.2375284218850715, "learning_rate": 1.9447473406765803e-05, "loss": 0.9941, "step": 692 }, { "epoch": 0.13, "grad_norm": 1.2190952163619608, "learning_rate": 1.9445429105186487e-05, "loss": 0.95, "step": 693 }, { "epoch": 0.13, "grad_norm": 0.8729477165756334, "learning_rate": 1.9443381136566382e-05, "loss": 0.6304, "step": 694 }, { "epoch": 0.13, "grad_norm": 1.117794083516751, "learning_rate": 1.9441329501700568e-05, "loss": 0.9539, "step": 695 }, { "epoch": 0.13, "grad_norm": 1.2060073747698343, "learning_rate": 1.943927420138557e-05, "loss": 0.9093, "step": 696 }, { "epoch": 0.13, "grad_norm": 1.0972899563095802, "learning_rate": 1.9437215236419322e-05, "loss": 0.97, "step": 697 }, { "epoch": 0.13, "grad_norm": 1.164697589757477, "learning_rate": 1.9435152607601187e-05, "loss": 0.9587, "step": 698 }, { "epoch": 0.13, "grad_norm": 1.094263265018975, "learning_rate": 1.943308631573195e-05, "loss": 0.9197, "step": 699 }, { "epoch": 0.13, "grad_norm": 1.1629379442148078, "learning_rate": 1.9431016361613816e-05, "loss": 0.9968, "step": 700 }, { "epoch": 0.13, "grad_norm": 1.115401619878011, "learning_rate": 1.9428942746050406e-05, "loss": 0.9331, "step": 701 }, { "epoch": 0.14, "grad_norm": 1.1339738676318265, "learning_rate": 1.9426865469846773e-05, "loss": 0.9915, "step": 702 }, { "epoch": 0.14, "grad_norm": 1.103923757369389, "learning_rate": 1.9424784533809393e-05, "loss": 0.9624, "step": 703 }, { "epoch": 0.14, "grad_norm": 1.112425791265829, "learning_rate": 1.942269993874615e-05, "loss": 0.9023, "step": 704 }, { "epoch": 0.14, "grad_norm": 1.107906260847134, "learning_rate": 1.9420611685466358e-05, "loss": 0.9937, "step": 705 }, { "epoch": 0.14, "grad_norm": 1.1170336907761047, "learning_rate": 1.9418519774780748e-05, "loss": 1.0032, "step": 706 }, { "epoch": 0.14, "grad_norm": 0.8268336234062807, "learning_rate": 1.9416424207501474e-05, "loss": 0.6514, "step": 707 }, { "epoch": 0.14, "grad_norm": 1.1359827237099698, "learning_rate": 1.9414324984442102e-05, "loss": 0.9966, "step": 708 }, { "epoch": 0.14, "grad_norm": 1.1200151326316563, "learning_rate": 1.9412222106417632e-05, "loss": 0.9692, "step": 709 }, { "epoch": 0.14, "grad_norm": 1.154996657006088, "learning_rate": 1.9410115574244462e-05, "loss": 0.946, "step": 710 }, { "epoch": 0.14, "grad_norm": 1.1474463029699276, "learning_rate": 1.9408005388740433e-05, "loss": 0.8669, "step": 711 }, { "epoch": 0.14, "grad_norm": 1.1483571878397218, "learning_rate": 1.9405891550724778e-05, "loss": 0.9158, "step": 712 }, { "epoch": 0.14, "grad_norm": 1.364292272338701, "learning_rate": 1.940377406101817e-05, "loss": 0.8896, "step": 713 }, { "epoch": 0.14, "grad_norm": 1.0364365283121675, "learning_rate": 1.9401652920442694e-05, "loss": 0.95, "step": 714 }, { "epoch": 0.14, "grad_norm": 1.1512801450485552, "learning_rate": 1.9399528129821842e-05, "loss": 0.8916, "step": 715 }, { "epoch": 0.14, "grad_norm": 1.1735725418145626, "learning_rate": 1.939739968998054e-05, "loss": 0.896, "step": 716 }, { "epoch": 0.14, "grad_norm": 1.0803886681963166, "learning_rate": 1.939526760174511e-05, "loss": 0.9626, "step": 717 }, { "epoch": 0.14, "grad_norm": 1.3204303906080026, "learning_rate": 1.939313186594331e-05, "loss": 0.9574, "step": 718 }, { "epoch": 0.14, "grad_norm": 1.128701104966055, "learning_rate": 1.9390992483404308e-05, "loss": 0.8984, "step": 719 }, { "epoch": 0.14, "grad_norm": 0.9180716482280025, "learning_rate": 1.938884945495868e-05, "loss": 0.6848, "step": 720 }, { "epoch": 0.14, "grad_norm": 1.0572809595653643, "learning_rate": 1.9386702781438425e-05, "loss": 0.9771, "step": 721 }, { "epoch": 0.14, "grad_norm": 1.032896170016986, "learning_rate": 1.938455246367696e-05, "loss": 0.9377, "step": 722 }, { "epoch": 0.14, "grad_norm": 1.3039424119258098, "learning_rate": 1.9382398502509107e-05, "loss": 1.01, "step": 723 }, { "epoch": 0.14, "grad_norm": 1.097943141843758, "learning_rate": 1.938024089877111e-05, "loss": 0.9204, "step": 724 }, { "epoch": 0.14, "grad_norm": 1.1920810797265986, "learning_rate": 1.9378079653300624e-05, "loss": 0.9885, "step": 725 }, { "epoch": 0.14, "grad_norm": 1.237436173534819, "learning_rate": 1.9375914766936723e-05, "loss": 0.9751, "step": 726 }, { "epoch": 0.14, "grad_norm": 1.079218832285128, "learning_rate": 1.9373746240519884e-05, "loss": 0.9771, "step": 727 }, { "epoch": 0.14, "grad_norm": 1.0698188496937648, "learning_rate": 1.937157407489201e-05, "loss": 0.9626, "step": 728 }, { "epoch": 0.14, "grad_norm": 1.2296841985988107, "learning_rate": 1.9369398270896403e-05, "loss": 0.9333, "step": 729 }, { "epoch": 0.14, "grad_norm": 1.031159573305749, "learning_rate": 1.936721882937779e-05, "loss": 1.0, "step": 730 }, { "epoch": 0.14, "grad_norm": 1.0729754283894952, "learning_rate": 1.9365035751182307e-05, "loss": 0.9736, "step": 731 }, { "epoch": 0.14, "grad_norm": 1.092797322561928, "learning_rate": 1.93628490371575e-05, "loss": 0.928, "step": 732 }, { "epoch": 0.14, "grad_norm": 0.9663240791475584, "learning_rate": 1.9360658688152322e-05, "loss": 0.6512, "step": 733 }, { "epoch": 0.14, "grad_norm": 1.069182563042137, "learning_rate": 1.9358464705017143e-05, "loss": 0.9619, "step": 734 }, { "epoch": 0.14, "grad_norm": 1.1324155961030713, "learning_rate": 1.9356267088603745e-05, "loss": 0.9541, "step": 735 }, { "epoch": 0.14, "grad_norm": 0.9714199608019582, "learning_rate": 1.9354065839765316e-05, "loss": 0.9106, "step": 736 }, { "epoch": 0.14, "grad_norm": 0.8242188538137705, "learning_rate": 1.9351860959356462e-05, "loss": 0.6089, "step": 737 }, { "epoch": 0.14, "grad_norm": 1.197810244216942, "learning_rate": 1.9349652448233187e-05, "loss": 0.9185, "step": 738 }, { "epoch": 0.14, "grad_norm": 0.8177580556044691, "learning_rate": 1.934744030725291e-05, "loss": 0.6338, "step": 739 }, { "epoch": 0.14, "grad_norm": 1.052151011443827, "learning_rate": 1.934522453727447e-05, "loss": 0.9368, "step": 740 }, { "epoch": 0.14, "grad_norm": 0.9827116142971604, "learning_rate": 1.93430051391581e-05, "loss": 0.9199, "step": 741 }, { "epoch": 0.14, "grad_norm": 1.1250349206397203, "learning_rate": 1.934078211376544e-05, "loss": 0.9553, "step": 742 }, { "epoch": 0.14, "grad_norm": 1.0699117735470836, "learning_rate": 1.9338555461959554e-05, "loss": 0.9126, "step": 743 }, { "epoch": 0.14, "grad_norm": 0.9743141480169539, "learning_rate": 1.93363251846049e-05, "loss": 0.9597, "step": 744 }, { "epoch": 0.14, "grad_norm": 1.1004635991219411, "learning_rate": 1.9334091282567352e-05, "loss": 0.9263, "step": 745 }, { "epoch": 0.14, "grad_norm": 1.0483510117186927, "learning_rate": 1.9331853756714185e-05, "loss": 0.9323, "step": 746 }, { "epoch": 0.14, "grad_norm": 0.8740964340916235, "learning_rate": 1.9329612607914088e-05, "loss": 0.6522, "step": 747 }, { "epoch": 0.14, "grad_norm": 1.5269782377170236, "learning_rate": 1.9327367837037142e-05, "loss": 0.9573, "step": 748 }, { "epoch": 0.14, "grad_norm": 0.9353847940642827, "learning_rate": 1.9325119444954855e-05, "loss": 0.9534, "step": 749 }, { "epoch": 0.14, "grad_norm": 1.2249523557884645, "learning_rate": 1.9322867432540126e-05, "loss": 1.002, "step": 750 }, { "epoch": 0.14, "grad_norm": 1.1764124185339861, "learning_rate": 1.9320611800667268e-05, "loss": 0.887, "step": 751 }, { "epoch": 0.14, "grad_norm": 1.1244480290599241, "learning_rate": 1.9318352550211986e-05, "loss": 1.0024, "step": 752 }, { "epoch": 0.14, "grad_norm": 1.0443477410301676, "learning_rate": 1.9316089682051403e-05, "loss": 0.967, "step": 753 }, { "epoch": 0.15, "grad_norm": 1.0524409292976946, "learning_rate": 1.9313823197064042e-05, "loss": 0.8524, "step": 754 }, { "epoch": 0.15, "grad_norm": 0.8850069409029375, "learning_rate": 1.9311553096129835e-05, "loss": 0.6357, "step": 755 }, { "epoch": 0.15, "grad_norm": 1.0760948418395275, "learning_rate": 1.9309279380130112e-05, "loss": 0.9583, "step": 756 }, { "epoch": 0.15, "grad_norm": 0.9973220682495442, "learning_rate": 1.93070020499476e-05, "loss": 0.9446, "step": 757 }, { "epoch": 0.15, "grad_norm": 1.1313304953329353, "learning_rate": 1.930472110646645e-05, "loss": 0.9153, "step": 758 }, { "epoch": 0.15, "grad_norm": 1.0553037772334954, "learning_rate": 1.9302436550572187e-05, "loss": 0.9407, "step": 759 }, { "epoch": 0.15, "grad_norm": 1.1915759614546229, "learning_rate": 1.930014838315177e-05, "loss": 1.0005, "step": 760 }, { "epoch": 0.15, "grad_norm": 1.0786778660352498, "learning_rate": 1.9297856605093534e-05, "loss": 0.895, "step": 761 }, { "epoch": 0.15, "grad_norm": 1.1929516376686995, "learning_rate": 1.9295561217287226e-05, "loss": 0.9468, "step": 762 }, { "epoch": 0.15, "grad_norm": 1.0527926194015051, "learning_rate": 1.9293262220624002e-05, "loss": 0.9436, "step": 763 }, { "epoch": 0.15, "grad_norm": 1.0696662910752375, "learning_rate": 1.9290959615996407e-05, "loss": 0.9426, "step": 764 }, { "epoch": 0.15, "grad_norm": 1.0188085433072585, "learning_rate": 1.9288653404298392e-05, "loss": 0.9495, "step": 765 }, { "epoch": 0.15, "grad_norm": 1.2205900317255962, "learning_rate": 1.9286343586425307e-05, "loss": 0.9971, "step": 766 }, { "epoch": 0.15, "grad_norm": 1.1272448186198787, "learning_rate": 1.9284030163273907e-05, "loss": 0.9138, "step": 767 }, { "epoch": 0.15, "grad_norm": 0.9903637170965466, "learning_rate": 1.9281713135742333e-05, "loss": 0.9268, "step": 768 }, { "epoch": 0.15, "grad_norm": 1.0470032938055853, "learning_rate": 1.9279392504730147e-05, "loss": 0.9802, "step": 769 }, { "epoch": 0.15, "grad_norm": 0.9331334774598534, "learning_rate": 1.9277068271138287e-05, "loss": 0.6391, "step": 770 }, { "epoch": 0.15, "grad_norm": 1.079245616178507, "learning_rate": 1.9274740435869107e-05, "loss": 0.9277, "step": 771 }, { "epoch": 0.15, "grad_norm": 1.0949496367138678, "learning_rate": 1.927240899982635e-05, "loss": 0.9312, "step": 772 }, { "epoch": 0.15, "grad_norm": 1.1079446754441094, "learning_rate": 1.9270073963915162e-05, "loss": 1.0161, "step": 773 }, { "epoch": 0.15, "grad_norm": 1.11169336341337, "learning_rate": 1.9267735329042086e-05, "loss": 0.9387, "step": 774 }, { "epoch": 0.15, "grad_norm": 0.9798725849976617, "learning_rate": 1.9265393096115056e-05, "loss": 0.6686, "step": 775 }, { "epoch": 0.15, "grad_norm": 0.971364814213732, "learning_rate": 1.926304726604341e-05, "loss": 0.908, "step": 776 }, { "epoch": 0.15, "grad_norm": 1.1640812862123633, "learning_rate": 1.9260697839737875e-05, "loss": 0.9709, "step": 777 }, { "epoch": 0.15, "grad_norm": 1.1188458059355046, "learning_rate": 1.925834481811059e-05, "loss": 0.9863, "step": 778 }, { "epoch": 0.15, "grad_norm": 0.9687061165283918, "learning_rate": 1.9255988202075065e-05, "loss": 0.9614, "step": 779 }, { "epoch": 0.15, "grad_norm": 1.0521902078360588, "learning_rate": 1.925362799254623e-05, "loss": 0.937, "step": 780 }, { "epoch": 0.15, "grad_norm": 0.8757762483212368, "learning_rate": 1.9251264190440398e-05, "loss": 0.6673, "step": 781 }, { "epoch": 0.15, "grad_norm": 1.008149953187908, "learning_rate": 1.9248896796675277e-05, "loss": 0.9282, "step": 782 }, { "epoch": 0.15, "grad_norm": 1.022149746611143, "learning_rate": 1.924652581216997e-05, "loss": 0.957, "step": 783 }, { "epoch": 0.15, "grad_norm": 0.999706684435566, "learning_rate": 1.9244151237844975e-05, "loss": 0.9111, "step": 784 }, { "epoch": 0.15, "grad_norm": 1.0869227453572188, "learning_rate": 1.9241773074622182e-05, "loss": 0.9084, "step": 785 }, { "epoch": 0.15, "grad_norm": 1.1468190284760225, "learning_rate": 1.923939132342488e-05, "loss": 1.0007, "step": 786 }, { "epoch": 0.15, "grad_norm": 1.150720576521038, "learning_rate": 1.923700598517775e-05, "loss": 0.9119, "step": 787 }, { "epoch": 0.15, "grad_norm": 1.0773018782157262, "learning_rate": 1.923461706080685e-05, "loss": 0.9578, "step": 788 }, { "epoch": 0.15, "grad_norm": 1.1214464684460868, "learning_rate": 1.923222455123965e-05, "loss": 0.959, "step": 789 }, { "epoch": 0.15, "grad_norm": 1.1043188625655902, "learning_rate": 1.9229828457405005e-05, "loss": 0.9888, "step": 790 }, { "epoch": 0.15, "grad_norm": 1.2376303127642618, "learning_rate": 1.9227428780233162e-05, "loss": 0.8956, "step": 791 }, { "epoch": 0.15, "grad_norm": 1.020460455311276, "learning_rate": 1.922502552065576e-05, "loss": 0.9299, "step": 792 }, { "epoch": 0.15, "grad_norm": 1.1253385361457737, "learning_rate": 1.922261867960582e-05, "loss": 0.8894, "step": 793 }, { "epoch": 0.15, "grad_norm": 1.2419386582972687, "learning_rate": 1.9220208258017763e-05, "loss": 0.9773, "step": 794 }, { "epoch": 0.15, "grad_norm": 1.1040563648942443, "learning_rate": 1.92177942568274e-05, "loss": 0.9351, "step": 795 }, { "epoch": 0.15, "grad_norm": 1.1109662600257169, "learning_rate": 1.921537667697193e-05, "loss": 0.9424, "step": 796 }, { "epoch": 0.15, "grad_norm": 1.2861165347622472, "learning_rate": 1.9212955519389938e-05, "loss": 0.9395, "step": 797 }, { "epoch": 0.15, "grad_norm": 1.0524048327044573, "learning_rate": 1.9210530785021405e-05, "loss": 0.9783, "step": 798 }, { "epoch": 0.15, "grad_norm": 1.0065767752937285, "learning_rate": 1.9208102474807692e-05, "loss": 0.9316, "step": 799 }, { "epoch": 0.15, "grad_norm": 1.1392010960619123, "learning_rate": 1.920567058969155e-05, "loss": 0.9478, "step": 800 }, { "epoch": 0.15, "grad_norm": 1.041436714865553, "learning_rate": 1.920323513061713e-05, "loss": 0.9829, "step": 801 }, { "epoch": 0.15, "grad_norm": 1.1352357171765237, "learning_rate": 1.9200796098529956e-05, "loss": 0.9021, "step": 802 }, { "epoch": 0.15, "grad_norm": 0.9602210106341365, "learning_rate": 1.919835349437694e-05, "loss": 0.9075, "step": 803 }, { "epoch": 0.15, "grad_norm": 1.0905113959946175, "learning_rate": 1.9195907319106394e-05, "loss": 0.926, "step": 804 }, { "epoch": 0.15, "grad_norm": 1.0427044627825273, "learning_rate": 1.9193457573667996e-05, "loss": 0.937, "step": 805 }, { "epoch": 0.16, "grad_norm": 1.017576402527272, "learning_rate": 1.919100425901283e-05, "loss": 0.6838, "step": 806 }, { "epoch": 0.16, "grad_norm": 1.057765122816641, "learning_rate": 1.9188547376093355e-05, "loss": 0.9512, "step": 807 }, { "epoch": 0.16, "grad_norm": 1.1035079704711237, "learning_rate": 1.918608692586342e-05, "loss": 0.9497, "step": 808 }, { "epoch": 0.16, "grad_norm": 1.032162674719524, "learning_rate": 1.918362290927825e-05, "loss": 0.6526, "step": 809 }, { "epoch": 0.16, "grad_norm": 1.0770321322376195, "learning_rate": 1.9181155327294468e-05, "loss": 0.9373, "step": 810 }, { "epoch": 0.16, "grad_norm": 1.1715239078380488, "learning_rate": 1.9178684180870072e-05, "loss": 1.0093, "step": 811 }, { "epoch": 0.16, "grad_norm": 1.124672005775334, "learning_rate": 1.9176209470964446e-05, "loss": 0.9314, "step": 812 }, { "epoch": 0.16, "grad_norm": 1.1909062426819905, "learning_rate": 1.9173731198538354e-05, "loss": 0.8909, "step": 813 }, { "epoch": 0.16, "grad_norm": 1.0773183138778943, "learning_rate": 1.9171249364553956e-05, "loss": 0.8804, "step": 814 }, { "epoch": 0.16, "grad_norm": 1.1756877009469524, "learning_rate": 1.9168763969974773e-05, "loss": 0.9763, "step": 815 }, { "epoch": 0.16, "grad_norm": 1.1184649801758693, "learning_rate": 1.916627501576573e-05, "loss": 1.0032, "step": 816 }, { "epoch": 0.16, "grad_norm": 1.0895633035449468, "learning_rate": 1.916378250289312e-05, "loss": 0.9353, "step": 817 }, { "epoch": 0.16, "grad_norm": 1.0150219946278298, "learning_rate": 1.9161286432324628e-05, "loss": 0.8931, "step": 818 }, { "epoch": 0.16, "grad_norm": 1.1259053101042162, "learning_rate": 1.9158786805029307e-05, "loss": 0.9341, "step": 819 }, { "epoch": 0.16, "grad_norm": 1.0616799038985016, "learning_rate": 1.9156283621977603e-05, "loss": 0.8948, "step": 820 }, { "epoch": 0.16, "grad_norm": 1.0864518042458806, "learning_rate": 1.9153776884141336e-05, "loss": 0.9719, "step": 821 }, { "epoch": 0.16, "grad_norm": 1.1416522056434966, "learning_rate": 1.915126659249371e-05, "loss": 1.0186, "step": 822 }, { "epoch": 0.16, "grad_norm": 0.9673233320760632, "learning_rate": 1.9148752748009304e-05, "loss": 0.8552, "step": 823 }, { "epoch": 0.16, "grad_norm": 1.053315102782541, "learning_rate": 1.914623535166408e-05, "loss": 0.8413, "step": 824 }, { "epoch": 0.16, "grad_norm": 1.0932537796699975, "learning_rate": 1.9143714404435382e-05, "loss": 0.9395, "step": 825 }, { "epoch": 0.16, "grad_norm": 1.189687003747625, "learning_rate": 1.9141189907301922e-05, "loss": 0.9138, "step": 826 }, { "epoch": 0.16, "grad_norm": 0.8997288320345731, "learning_rate": 1.9138661861243802e-05, "loss": 0.9016, "step": 827 }, { "epoch": 0.16, "grad_norm": 1.125567590542296, "learning_rate": 1.913613026724249e-05, "loss": 0.9299, "step": 828 }, { "epoch": 0.16, "grad_norm": 1.0497253061932996, "learning_rate": 1.9133595126280848e-05, "loss": 1.0061, "step": 829 }, { "epoch": 0.16, "grad_norm": 1.2544778645455177, "learning_rate": 1.9131056439343095e-05, "loss": 0.9351, "step": 830 }, { "epoch": 0.16, "grad_norm": 1.099310226978815, "learning_rate": 1.9128514207414838e-05, "loss": 0.8926, "step": 831 }, { "epoch": 0.16, "grad_norm": 1.170058752492579, "learning_rate": 1.9125968431483068e-05, "loss": 0.9475, "step": 832 }, { "epoch": 0.16, "grad_norm": 1.3022391158533109, "learning_rate": 1.9123419112536132e-05, "loss": 0.9385, "step": 833 }, { "epoch": 0.16, "grad_norm": 1.2026284527697835, "learning_rate": 1.912086625156377e-05, "loss": 1.0073, "step": 834 }, { "epoch": 0.16, "grad_norm": 0.9694829726812008, "learning_rate": 1.911830984955709e-05, "loss": 0.9875, "step": 835 }, { "epoch": 0.16, "grad_norm": 1.0438515665215016, "learning_rate": 1.911574990750857e-05, "loss": 0.9829, "step": 836 }, { "epoch": 0.16, "grad_norm": 0.9412916381306944, "learning_rate": 1.9113186426412073e-05, "loss": 0.6284, "step": 837 }, { "epoch": 0.16, "grad_norm": 1.1422494195404695, "learning_rate": 1.9110619407262828e-05, "loss": 1.0164, "step": 838 }, { "epoch": 0.16, "grad_norm": 0.9974397699632145, "learning_rate": 1.9108048851057447e-05, "loss": 0.9563, "step": 839 }, { "epoch": 0.16, "grad_norm": 1.1519629936435853, "learning_rate": 1.9105474758793897e-05, "loss": 0.9333, "step": 840 }, { "epoch": 0.16, "grad_norm": 0.9539704390112723, "learning_rate": 1.9102897131471536e-05, "loss": 0.9287, "step": 841 }, { "epoch": 0.16, "grad_norm": 1.082505129467562, "learning_rate": 1.9100315970091088e-05, "loss": 0.9358, "step": 842 }, { "epoch": 0.16, "grad_norm": 1.133610274513537, "learning_rate": 1.9097731275654645e-05, "loss": 0.9387, "step": 843 }, { "epoch": 0.16, "grad_norm": 0.9817247296654678, "learning_rate": 1.909514304916568e-05, "loss": 0.925, "step": 844 }, { "epoch": 0.16, "grad_norm": 1.142674192441014, "learning_rate": 1.9092551291629026e-05, "loss": 0.9995, "step": 845 }, { "epoch": 0.16, "grad_norm": 1.0592030655663605, "learning_rate": 1.9089956004050893e-05, "loss": 0.9939, "step": 846 }, { "epoch": 0.16, "grad_norm": 1.1223318581168185, "learning_rate": 1.908735718743887e-05, "loss": 0.9995, "step": 847 }, { "epoch": 0.16, "grad_norm": 1.1032732338668818, "learning_rate": 1.908475484280189e-05, "loss": 0.9358, "step": 848 }, { "epoch": 0.16, "grad_norm": 1.1627892661137833, "learning_rate": 1.908214897115029e-05, "loss": 0.9397, "step": 849 }, { "epoch": 0.16, "grad_norm": 1.237060440346544, "learning_rate": 1.907953957349575e-05, "loss": 0.9546, "step": 850 }, { "epoch": 0.16, "grad_norm": 1.2206185836127101, "learning_rate": 1.907692665085133e-05, "loss": 0.9966, "step": 851 }, { "epoch": 0.16, "grad_norm": 1.0035377216347154, "learning_rate": 1.9074310204231457e-05, "loss": 0.9194, "step": 852 }, { "epoch": 0.16, "grad_norm": 0.9388708572442948, "learning_rate": 1.9071690234651923e-05, "loss": 0.9302, "step": 853 }, { "epoch": 0.16, "grad_norm": 1.129747513292248, "learning_rate": 1.9069066743129893e-05, "loss": 0.902, "step": 854 }, { "epoch": 0.16, "grad_norm": 0.9674457284864971, "learning_rate": 1.90664397306839e-05, "loss": 0.9099, "step": 855 }, { "epoch": 0.16, "grad_norm": 1.1824380810275728, "learning_rate": 1.9063809198333832e-05, "loss": 0.946, "step": 856 }, { "epoch": 0.16, "grad_norm": 1.2376210554173432, "learning_rate": 1.9061175147100957e-05, "loss": 0.9673, "step": 857 }, { "epoch": 0.17, "grad_norm": 1.126350502234873, "learning_rate": 1.905853757800791e-05, "loss": 0.9409, "step": 858 }, { "epoch": 0.17, "grad_norm": 1.0183087323542332, "learning_rate": 1.9055896492078675e-05, "loss": 0.9429, "step": 859 }, { "epoch": 0.17, "grad_norm": 1.0092338951523363, "learning_rate": 1.905325189033862e-05, "loss": 0.9509, "step": 860 }, { "epoch": 0.17, "grad_norm": 1.0565985172804937, "learning_rate": 1.905060377381447e-05, "loss": 0.95, "step": 861 }, { "epoch": 0.17, "grad_norm": 1.156470677623178, "learning_rate": 1.904795214353431e-05, "loss": 0.9497, "step": 862 }, { "epoch": 0.17, "grad_norm": 1.0589651671619675, "learning_rate": 1.90452970005276e-05, "loss": 0.9648, "step": 863 }, { "epoch": 0.17, "grad_norm": 0.9849453448866047, "learning_rate": 1.9042638345825155e-05, "loss": 0.8872, "step": 864 }, { "epoch": 0.17, "grad_norm": 1.1115057621849063, "learning_rate": 1.9039976180459158e-05, "loss": 0.9675, "step": 865 }, { "epoch": 0.17, "grad_norm": 0.9869777353153905, "learning_rate": 1.9037310505463153e-05, "loss": 0.9194, "step": 866 }, { "epoch": 0.17, "grad_norm": 0.9746577294123346, "learning_rate": 1.9034641321872043e-05, "loss": 0.9553, "step": 867 }, { "epoch": 0.17, "grad_norm": 1.031689067231893, "learning_rate": 1.9031968630722104e-05, "loss": 0.9434, "step": 868 }, { "epoch": 0.17, "grad_norm": 1.084487423072731, "learning_rate": 1.902929243305096e-05, "loss": 0.9819, "step": 869 }, { "epoch": 0.17, "grad_norm": 0.6998712123442432, "learning_rate": 1.902661272989761e-05, "loss": 0.3332, "step": 870 }, { "epoch": 0.17, "grad_norm": 1.1056364181034695, "learning_rate": 1.9023929522302394e-05, "loss": 0.9141, "step": 871 }, { "epoch": 0.17, "grad_norm": 1.1140716269301147, "learning_rate": 1.9021242811307044e-05, "loss": 0.9409, "step": 872 }, { "epoch": 0.17, "grad_norm": 1.0855680362914775, "learning_rate": 1.901855259795462e-05, "loss": 0.981, "step": 873 }, { "epoch": 0.17, "grad_norm": 1.036531582744266, "learning_rate": 1.9015858883289556e-05, "loss": 0.9136, "step": 874 }, { "epoch": 0.17, "grad_norm": 1.198806496615718, "learning_rate": 1.9013161668357655e-05, "loss": 0.9358, "step": 875 }, { "epoch": 0.17, "grad_norm": 1.1365839353479275, "learning_rate": 1.901046095420606e-05, "loss": 0.9167, "step": 876 }, { "epoch": 0.17, "grad_norm": 1.0942310999439322, "learning_rate": 1.9007756741883284e-05, "loss": 0.9387, "step": 877 }, { "epoch": 0.17, "grad_norm": 1.1041573051364677, "learning_rate": 1.9005049032439193e-05, "loss": 0.9592, "step": 878 }, { "epoch": 0.17, "grad_norm": 0.9793735473422495, "learning_rate": 1.9002337826925012e-05, "loss": 0.9673, "step": 879 }, { "epoch": 0.17, "grad_norm": 1.1145523389977365, "learning_rate": 1.899962312639333e-05, "loss": 0.8779, "step": 880 }, { "epoch": 0.17, "grad_norm": 1.0919759531849302, "learning_rate": 1.8996904931898085e-05, "loss": 0.9236, "step": 881 }, { "epoch": 0.17, "grad_norm": 1.0405662996767957, "learning_rate": 1.899418324449457e-05, "loss": 0.9119, "step": 882 }, { "epoch": 0.17, "grad_norm": 1.0612039958354575, "learning_rate": 1.8991458065239444e-05, "loss": 0.6887, "step": 883 }, { "epoch": 0.17, "grad_norm": 1.059344945619471, "learning_rate": 1.8988729395190712e-05, "loss": 0.9517, "step": 884 }, { "epoch": 0.17, "grad_norm": 0.9502614680447578, "learning_rate": 1.8985997235407735e-05, "loss": 0.6379, "step": 885 }, { "epoch": 0.17, "grad_norm": 0.8466118124822443, "learning_rate": 1.898326158695124e-05, "loss": 0.6049, "step": 886 }, { "epoch": 0.17, "grad_norm": 0.9266863677068238, "learning_rate": 1.8980522450883287e-05, "loss": 0.9241, "step": 887 }, { "epoch": 0.17, "grad_norm": 1.2395095051055818, "learning_rate": 1.8977779828267314e-05, "loss": 0.9539, "step": 888 }, { "epoch": 0.17, "grad_norm": 1.005451022861987, "learning_rate": 1.8975033720168094e-05, "loss": 0.8914, "step": 889 }, { "epoch": 0.17, "grad_norm": 1.1345444819149364, "learning_rate": 1.897228412765177e-05, "loss": 0.9253, "step": 890 }, { "epoch": 0.17, "grad_norm": 1.0332539150215263, "learning_rate": 1.896953105178582e-05, "loss": 0.9863, "step": 891 }, { "epoch": 0.17, "grad_norm": 0.9721472673065746, "learning_rate": 1.8966774493639084e-05, "loss": 0.9131, "step": 892 }, { "epoch": 0.17, "grad_norm": 1.2987142534460623, "learning_rate": 1.896401445428176e-05, "loss": 0.8965, "step": 893 }, { "epoch": 0.17, "grad_norm": 1.106737985310506, "learning_rate": 1.896125093478538e-05, "loss": 0.9346, "step": 894 }, { "epoch": 0.17, "grad_norm": 1.0397356943036964, "learning_rate": 1.895848393622284e-05, "loss": 0.9595, "step": 895 }, { "epoch": 0.17, "grad_norm": 1.0864118059738197, "learning_rate": 1.895571345966839e-05, "loss": 0.9431, "step": 896 }, { "epoch": 0.17, "grad_norm": 1.202220138538901, "learning_rate": 1.8952939506197622e-05, "loss": 0.926, "step": 897 }, { "epoch": 0.17, "grad_norm": 1.046265309144104, "learning_rate": 1.8950162076887477e-05, "loss": 0.9067, "step": 898 }, { "epoch": 0.17, "grad_norm": 1.0927945907120389, "learning_rate": 1.894738117281625e-05, "loss": 0.9541, "step": 899 }, { "epoch": 0.17, "grad_norm": 1.3289202752878586, "learning_rate": 1.8944596795063584e-05, "loss": 0.9392, "step": 900 }, { "epoch": 0.17, "grad_norm": 1.1126599364125214, "learning_rate": 1.894180894471047e-05, "loss": 0.9944, "step": 901 }, { "epoch": 0.17, "grad_norm": 1.059381329695463, "learning_rate": 1.8939017622839253e-05, "loss": 0.9219, "step": 902 }, { "epoch": 0.17, "grad_norm": 1.0845591140507609, "learning_rate": 1.8936222830533613e-05, "loss": 0.9565, "step": 903 }, { "epoch": 0.17, "grad_norm": 0.9721326198885942, "learning_rate": 1.8933424568878586e-05, "loss": 0.6654, "step": 904 }, { "epoch": 0.17, "grad_norm": 1.1262953739894372, "learning_rate": 1.8930622838960555e-05, "loss": 0.9385, "step": 905 }, { "epoch": 0.17, "grad_norm": 1.0194936398030985, "learning_rate": 1.8927817641867244e-05, "loss": 0.9563, "step": 906 }, { "epoch": 0.17, "grad_norm": 1.0559825431144743, "learning_rate": 1.8925008978687737e-05, "loss": 0.9839, "step": 907 }, { "epoch": 0.17, "grad_norm": 1.08523967599803, "learning_rate": 1.8922196850512446e-05, "loss": 0.9597, "step": 908 }, { "epoch": 0.17, "grad_norm": 0.9856217280266971, "learning_rate": 1.8919381258433135e-05, "loss": 0.9277, "step": 909 }, { "epoch": 0.18, "grad_norm": 1.1268812985976115, "learning_rate": 1.8916562203542916e-05, "loss": 0.9731, "step": 910 }, { "epoch": 0.18, "grad_norm": 1.0346391861977582, "learning_rate": 1.8913739686936244e-05, "loss": 0.9702, "step": 911 }, { "epoch": 0.18, "grad_norm": 1.0613001844844177, "learning_rate": 1.8910913709708918e-05, "loss": 0.9065, "step": 912 }, { "epoch": 0.18, "grad_norm": 1.0919843838542, "learning_rate": 1.8908084272958077e-05, "loss": 0.9238, "step": 913 }, { "epoch": 0.18, "grad_norm": 1.1711756184879265, "learning_rate": 1.8905251377782206e-05, "loss": 0.9531, "step": 914 }, { "epoch": 0.18, "grad_norm": 1.0809207999619002, "learning_rate": 1.8902415025281136e-05, "loss": 0.967, "step": 915 }, { "epoch": 0.18, "grad_norm": 1.1394954777327764, "learning_rate": 1.889957521655603e-05, "loss": 0.9976, "step": 916 }, { "epoch": 0.18, "grad_norm": 1.1630306765258598, "learning_rate": 1.8896731952709408e-05, "loss": 0.9595, "step": 917 }, { "epoch": 0.18, "grad_norm": 1.3443980724765296, "learning_rate": 1.8893885234845117e-05, "loss": 0.8593, "step": 918 }, { "epoch": 0.18, "grad_norm": 1.032991833886911, "learning_rate": 1.8891035064068354e-05, "loss": 0.8596, "step": 919 }, { "epoch": 0.18, "grad_norm": 0.9776083982850831, "learning_rate": 1.888818144148565e-05, "loss": 0.9822, "step": 920 }, { "epoch": 0.18, "grad_norm": 1.0576848030931263, "learning_rate": 1.888532436820488e-05, "loss": 1.0125, "step": 921 }, { "epoch": 0.18, "grad_norm": 2.0424999721288097, "learning_rate": 1.8882463845335263e-05, "loss": 0.9036, "step": 922 }, { "epoch": 0.18, "grad_norm": 1.2073129360736614, "learning_rate": 1.8879599873987343e-05, "loss": 0.9856, "step": 923 }, { "epoch": 0.18, "grad_norm": 1.086440599961961, "learning_rate": 1.8876732455273022e-05, "loss": 0.9517, "step": 924 }, { "epoch": 0.18, "grad_norm": 0.9406060752061919, "learning_rate": 1.8873861590305527e-05, "loss": 0.8706, "step": 925 }, { "epoch": 0.18, "grad_norm": 1.0614226338568618, "learning_rate": 1.8870987280199428e-05, "loss": 0.9573, "step": 926 }, { "epoch": 0.18, "grad_norm": 0.9202617754592579, "learning_rate": 1.886810952607063e-05, "loss": 0.8936, "step": 927 }, { "epoch": 0.18, "grad_norm": 1.1798111232267798, "learning_rate": 1.8865228329036372e-05, "loss": 0.9211, "step": 928 }, { "epoch": 0.18, "grad_norm": 0.9088845742047567, "learning_rate": 1.886234369021524e-05, "loss": 0.6132, "step": 929 }, { "epoch": 0.18, "grad_norm": 1.1214351595254537, "learning_rate": 1.885945561072715e-05, "loss": 0.9485, "step": 930 }, { "epoch": 0.18, "grad_norm": 1.0223518452745801, "learning_rate": 1.885656409169335e-05, "loss": 0.9014, "step": 931 }, { "epoch": 0.18, "grad_norm": 1.0286775185487504, "learning_rate": 1.885366913423643e-05, "loss": 0.9321, "step": 932 }, { "epoch": 0.18, "grad_norm": 1.0973986207941422, "learning_rate": 1.8850770739480312e-05, "loss": 0.9194, "step": 933 }, { "epoch": 0.18, "grad_norm": 0.8664262290638357, "learning_rate": 1.8847868908550252e-05, "loss": 0.635, "step": 934 }, { "epoch": 0.18, "grad_norm": 0.9929171682450452, "learning_rate": 1.8844963642572837e-05, "loss": 0.9309, "step": 935 }, { "epoch": 0.18, "grad_norm": 1.127196047556886, "learning_rate": 1.8842054942676e-05, "loss": 0.925, "step": 936 }, { "epoch": 0.18, "grad_norm": 1.0029468404905837, "learning_rate": 1.8839142809988987e-05, "loss": 0.9446, "step": 937 }, { "epoch": 0.18, "grad_norm": 0.8570939123271268, "learning_rate": 1.88362272456424e-05, "loss": 0.6223, "step": 938 }, { "epoch": 0.18, "grad_norm": 1.028832131629365, "learning_rate": 1.8833308250768153e-05, "loss": 0.9353, "step": 939 }, { "epoch": 0.18, "grad_norm": 0.8493448336136719, "learning_rate": 1.8830385826499507e-05, "loss": 0.6246, "step": 940 }, { "epoch": 0.18, "grad_norm": 0.8888599943991279, "learning_rate": 1.882745997397104e-05, "loss": 0.6944, "step": 941 }, { "epoch": 0.18, "grad_norm": 1.1018808061179468, "learning_rate": 1.8824530694318675e-05, "loss": 0.9568, "step": 942 }, { "epoch": 0.18, "grad_norm": 0.9951077443012663, "learning_rate": 1.882159798867966e-05, "loss": 0.9287, "step": 943 }, { "epoch": 0.18, "grad_norm": 1.1089235236267896, "learning_rate": 1.8818661858192562e-05, "loss": 0.9233, "step": 944 }, { "epoch": 0.18, "grad_norm": 1.1305661616078395, "learning_rate": 1.88157223039973e-05, "loss": 0.9607, "step": 945 }, { "epoch": 0.18, "grad_norm": 1.073243018168231, "learning_rate": 1.8812779327235106e-05, "loss": 0.9731, "step": 946 }, { "epoch": 0.18, "grad_norm": 0.986025181126998, "learning_rate": 1.880983292904854e-05, "loss": 0.9109, "step": 947 }, { "epoch": 0.18, "grad_norm": 0.9206140699578624, "learning_rate": 1.88068831105815e-05, "loss": 0.6443, "step": 948 }, { "epoch": 0.18, "grad_norm": 0.9785941657793775, "learning_rate": 1.8803929872979214e-05, "loss": 0.9189, "step": 949 }, { "epoch": 0.18, "grad_norm": 1.1978333878767213, "learning_rate": 1.8800973217388215e-05, "loss": 0.9709, "step": 950 }, { "epoch": 0.18, "grad_norm": 1.0915104523594112, "learning_rate": 1.879801314495639e-05, "loss": 0.9932, "step": 951 }, { "epoch": 0.18, "grad_norm": 1.0323700666373319, "learning_rate": 1.879504965683294e-05, "loss": 0.9839, "step": 952 }, { "epoch": 0.18, "grad_norm": 1.0757342232275293, "learning_rate": 1.8792082754168385e-05, "loss": 0.9807, "step": 953 }, { "epoch": 0.18, "grad_norm": 1.0870544246781682, "learning_rate": 1.878911243811459e-05, "loss": 0.9727, "step": 954 }, { "epoch": 0.18, "grad_norm": 1.088080517386113, "learning_rate": 1.8786138709824726e-05, "loss": 0.9033, "step": 955 }, { "epoch": 0.18, "grad_norm": 1.407968559285497, "learning_rate": 1.8783161570453295e-05, "loss": 1.0139, "step": 956 }, { "epoch": 0.18, "grad_norm": 1.0655131617642313, "learning_rate": 1.878018102115614e-05, "loss": 0.9338, "step": 957 }, { "epoch": 0.18, "grad_norm": 1.284947122136321, "learning_rate": 1.8777197063090394e-05, "loss": 0.9067, "step": 958 }, { "epoch": 0.18, "grad_norm": 1.157653016269976, "learning_rate": 1.877420969741454e-05, "loss": 0.9265, "step": 959 }, { "epoch": 0.18, "grad_norm": 1.0445764680426564, "learning_rate": 1.877121892528838e-05, "loss": 0.9668, "step": 960 }, { "epoch": 0.18, "grad_norm": 0.8982914431428335, "learning_rate": 1.876822474787303e-05, "loss": 0.6772, "step": 961 }, { "epoch": 0.19, "grad_norm": 1.140996450369516, "learning_rate": 1.8765227166330933e-05, "loss": 0.897, "step": 962 }, { "epoch": 0.19, "grad_norm": 1.076748166087786, "learning_rate": 1.8762226181825857e-05, "loss": 0.9829, "step": 963 }, { "epoch": 0.19, "grad_norm": 1.173509706626929, "learning_rate": 1.875922179552288e-05, "loss": 0.9521, "step": 964 }, { "epoch": 0.19, "grad_norm": 1.054388882165325, "learning_rate": 1.875621400858842e-05, "loss": 0.957, "step": 965 }, { "epoch": 0.19, "grad_norm": 0.8991524967583954, "learning_rate": 1.875320282219019e-05, "loss": 0.6481, "step": 966 }, { "epoch": 0.19, "grad_norm": 1.113261388300353, "learning_rate": 1.8750188237497247e-05, "loss": 0.9373, "step": 967 }, { "epoch": 0.19, "grad_norm": 0.8359744011452775, "learning_rate": 1.874717025567995e-05, "loss": 0.6237, "step": 968 }, { "epoch": 0.19, "grad_norm": 1.0412693170822709, "learning_rate": 1.874414887790999e-05, "loss": 0.9363, "step": 969 }, { "epoch": 0.19, "grad_norm": 0.8746748824758088, "learning_rate": 1.8741124105360363e-05, "loss": 0.6427, "step": 970 }, { "epoch": 0.19, "grad_norm": 1.163774261955556, "learning_rate": 1.873809593920539e-05, "loss": 0.9067, "step": 971 }, { "epoch": 0.19, "grad_norm": 0.989354737025201, "learning_rate": 1.8735064380620717e-05, "loss": 0.9209, "step": 972 }, { "epoch": 0.19, "grad_norm": 1.0634809584566167, "learning_rate": 1.873202943078329e-05, "loss": 0.9968, "step": 973 }, { "epoch": 0.19, "grad_norm": 0.9955109195424989, "learning_rate": 1.8728991090871387e-05, "loss": 0.9563, "step": 974 }, { "epoch": 0.19, "grad_norm": 0.9272577501983541, "learning_rate": 1.8725949362064596e-05, "loss": 0.671, "step": 975 }, { "epoch": 0.19, "grad_norm": 1.0643724100325844, "learning_rate": 1.8722904245543817e-05, "loss": 0.9036, "step": 976 }, { "epoch": 0.19, "grad_norm": 1.2060488194929064, "learning_rate": 1.871985574249127e-05, "loss": 0.9304, "step": 977 }, { "epoch": 0.19, "grad_norm": 1.1324623952190875, "learning_rate": 1.8716803854090495e-05, "loss": 0.9336, "step": 978 }, { "epoch": 0.19, "grad_norm": 1.0257554890120903, "learning_rate": 1.8713748581526334e-05, "loss": 0.9668, "step": 979 }, { "epoch": 0.19, "grad_norm": 1.0696640693497634, "learning_rate": 1.871068992598495e-05, "loss": 0.8982, "step": 980 }, { "epoch": 0.19, "grad_norm": 1.1266193219896032, "learning_rate": 1.8707627888653816e-05, "loss": 0.9778, "step": 981 }, { "epoch": 0.19, "grad_norm": 1.0816777060347895, "learning_rate": 1.8704562470721728e-05, "loss": 0.9565, "step": 982 }, { "epoch": 0.19, "grad_norm": 0.9460504600608909, "learning_rate": 1.870149367337878e-05, "loss": 0.6549, "step": 983 }, { "epoch": 0.19, "grad_norm": 1.0642792944753665, "learning_rate": 1.8698421497816386e-05, "loss": 0.9084, "step": 984 }, { "epoch": 0.19, "grad_norm": 0.9387389966276041, "learning_rate": 1.869534594522727e-05, "loss": 0.9775, "step": 985 }, { "epoch": 0.19, "grad_norm": 0.8460684586282237, "learning_rate": 1.8692267016805473e-05, "loss": 0.6567, "step": 986 }, { "epoch": 0.19, "grad_norm": 1.041817197142872, "learning_rate": 1.8689184713746333e-05, "loss": 0.9731, "step": 987 }, { "epoch": 0.19, "grad_norm": 1.012139053334717, "learning_rate": 1.868609903724651e-05, "loss": 0.926, "step": 988 }, { "epoch": 0.19, "grad_norm": 0.9736265801179579, "learning_rate": 1.8683009988503972e-05, "loss": 0.9192, "step": 989 }, { "epoch": 0.19, "grad_norm": 1.072114868609868, "learning_rate": 1.867991756871799e-05, "loss": 0.926, "step": 990 }, { "epoch": 0.19, "grad_norm": 1.236653838522055, "learning_rate": 1.867682177908915e-05, "loss": 1.0342, "step": 991 }, { "epoch": 0.19, "grad_norm": 1.0950882018294399, "learning_rate": 1.867372262081934e-05, "loss": 0.929, "step": 992 }, { "epoch": 0.19, "grad_norm": 0.8625835852499399, "learning_rate": 1.8670620095111766e-05, "loss": 0.6326, "step": 993 }, { "epoch": 0.19, "grad_norm": 1.084777876675205, "learning_rate": 1.8667514203170934e-05, "loss": 0.9004, "step": 994 }, { "epoch": 0.19, "grad_norm": 1.10396912927867, "learning_rate": 1.8664404946202658e-05, "loss": 0.9294, "step": 995 }, { "epoch": 0.19, "grad_norm": 0.9917382216660601, "learning_rate": 1.8661292325414058e-05, "loss": 0.9075, "step": 996 }, { "epoch": 0.19, "grad_norm": 1.0264978126063247, "learning_rate": 1.865817634201356e-05, "loss": 0.8877, "step": 997 }, { "epoch": 0.19, "grad_norm": 1.064757689161226, "learning_rate": 1.8655056997210893e-05, "loss": 0.9822, "step": 998 }, { "epoch": 0.19, "grad_norm": 1.2360164487133871, "learning_rate": 1.8651934292217097e-05, "loss": 0.9761, "step": 999 }, { "epoch": 0.19, "grad_norm": 1.2411484008509848, "learning_rate": 1.864880822824452e-05, "loss": 0.9297, "step": 1000 }, { "epoch": 0.19, "grad_norm": 1.0277074194642348, "learning_rate": 1.8645678806506795e-05, "loss": 0.9133, "step": 1001 }, { "epoch": 0.19, "grad_norm": 0.9983422817081796, "learning_rate": 1.864254602821888e-05, "loss": 0.8889, "step": 1002 }, { "epoch": 0.19, "grad_norm": 1.0468893767417669, "learning_rate": 1.8639409894597026e-05, "loss": 0.8975, "step": 1003 }, { "epoch": 0.19, "grad_norm": 1.0784402259903714, "learning_rate": 1.8636270406858786e-05, "loss": 0.9492, "step": 1004 }, { "epoch": 0.19, "grad_norm": 1.1100450854378512, "learning_rate": 1.8633127566223023e-05, "loss": 0.9138, "step": 1005 }, { "epoch": 0.19, "grad_norm": 1.0657970643422172, "learning_rate": 1.862998137390989e-05, "loss": 0.9761, "step": 1006 }, { "epoch": 0.19, "grad_norm": 1.0540783979875659, "learning_rate": 1.8626831831140845e-05, "loss": 0.9441, "step": 1007 }, { "epoch": 0.19, "grad_norm": 1.1195505294034864, "learning_rate": 1.8623678939138652e-05, "loss": 0.9797, "step": 1008 }, { "epoch": 0.19, "grad_norm": 1.107273181914426, "learning_rate": 1.8620522699127374e-05, "loss": 0.9521, "step": 1009 }, { "epoch": 0.19, "grad_norm": 0.978205120481307, "learning_rate": 1.8617363112332376e-05, "loss": 0.6362, "step": 1010 }, { "epoch": 0.19, "grad_norm": 1.1754860030064471, "learning_rate": 1.8614200179980307e-05, "loss": 0.8801, "step": 1011 }, { "epoch": 0.19, "grad_norm": 1.0184757598916514, "learning_rate": 1.8611033903299136e-05, "loss": 0.8999, "step": 1012 }, { "epoch": 0.19, "grad_norm": 1.0292943882278789, "learning_rate": 1.8607864283518116e-05, "loss": 0.9509, "step": 1013 }, { "epoch": 0.2, "grad_norm": 1.1585050127330343, "learning_rate": 1.8604691321867804e-05, "loss": 0.9258, "step": 1014 }, { "epoch": 0.2, "grad_norm": 0.8407814709733638, "learning_rate": 1.8601515019580053e-05, "loss": 0.6432, "step": 1015 }, { "epoch": 0.2, "grad_norm": 1.2334701186151116, "learning_rate": 1.8598335377888012e-05, "loss": 0.9668, "step": 1016 }, { "epoch": 0.2, "grad_norm": 1.0250235254652527, "learning_rate": 1.8595152398026128e-05, "loss": 0.957, "step": 1017 }, { "epoch": 0.2, "grad_norm": 1.0670472799546775, "learning_rate": 1.8591966081230142e-05, "loss": 0.9136, "step": 1018 }, { "epoch": 0.2, "grad_norm": 1.0591702894929564, "learning_rate": 1.8588776428737095e-05, "loss": 0.9353, "step": 1019 }, { "epoch": 0.2, "grad_norm": 1.1091150299057781, "learning_rate": 1.858558344178532e-05, "loss": 0.9587, "step": 1020 }, { "epoch": 0.2, "grad_norm": 1.150835055615197, "learning_rate": 1.8582387121614437e-05, "loss": 0.8784, "step": 1021 }, { "epoch": 0.2, "grad_norm": 1.025824899332194, "learning_rate": 1.857918746946538e-05, "loss": 0.9365, "step": 1022 }, { "epoch": 0.2, "grad_norm": 1.233597366754715, "learning_rate": 1.8575984486580353e-05, "loss": 0.9336, "step": 1023 }, { "epoch": 0.2, "grad_norm": 0.9922478593653989, "learning_rate": 1.857277817420287e-05, "loss": 0.6511, "step": 1024 }, { "epoch": 0.2, "grad_norm": 1.1162679994320424, "learning_rate": 1.8569568533577727e-05, "loss": 0.948, "step": 1025 }, { "epoch": 0.2, "grad_norm": 1.1663442734399485, "learning_rate": 1.8566355565951023e-05, "loss": 1.0107, "step": 1026 }, { "epoch": 0.2, "grad_norm": 1.0459983931078018, "learning_rate": 1.8563139272570142e-05, "loss": 0.8992, "step": 1027 }, { "epoch": 0.2, "grad_norm": 1.0130233740228216, "learning_rate": 1.8559919654683756e-05, "loss": 0.927, "step": 1028 }, { "epoch": 0.2, "grad_norm": 1.0964036982346113, "learning_rate": 1.8556696713541833e-05, "loss": 0.908, "step": 1029 }, { "epoch": 0.2, "grad_norm": 1.0887297222795345, "learning_rate": 1.855347045039563e-05, "loss": 0.9443, "step": 1030 }, { "epoch": 0.2, "grad_norm": 0.9464577759686446, "learning_rate": 1.8550240866497697e-05, "loss": 0.9644, "step": 1031 }, { "epoch": 0.2, "grad_norm": 1.0943476666099887, "learning_rate": 1.854700796310186e-05, "loss": 0.9529, "step": 1032 }, { "epoch": 0.2, "grad_norm": 1.1639519232315987, "learning_rate": 1.8543771741463254e-05, "loss": 0.9326, "step": 1033 }, { "epoch": 0.2, "grad_norm": 1.2093689488658779, "learning_rate": 1.8540532202838286e-05, "loss": 0.8982, "step": 1034 }, { "epoch": 0.2, "grad_norm": 0.9810689337301884, "learning_rate": 1.8537289348484658e-05, "loss": 0.9106, "step": 1035 }, { "epoch": 0.2, "grad_norm": 1.0289349725026395, "learning_rate": 1.8534043179661357e-05, "loss": 0.958, "step": 1036 }, { "epoch": 0.2, "grad_norm": 1.1893784056372705, "learning_rate": 1.8530793697628658e-05, "loss": 0.9521, "step": 1037 }, { "epoch": 0.2, "grad_norm": 1.0044726302920488, "learning_rate": 1.8527540903648122e-05, "loss": 0.958, "step": 1038 }, { "epoch": 0.2, "grad_norm": 1.1572209594486298, "learning_rate": 1.8524284798982595e-05, "loss": 0.979, "step": 1039 }, { "epoch": 0.2, "grad_norm": 1.2430339506912442, "learning_rate": 1.852102538489621e-05, "loss": 0.8914, "step": 1040 }, { "epoch": 0.2, "grad_norm": 1.0026480698158933, "learning_rate": 1.8517762662654383e-05, "loss": 0.9014, "step": 1041 }, { "epoch": 0.2, "grad_norm": 0.8506085084051198, "learning_rate": 1.851449663352381e-05, "loss": 0.6384, "step": 1042 }, { "epoch": 0.2, "grad_norm": 1.1498049227029215, "learning_rate": 1.851122729877249e-05, "loss": 0.9907, "step": 1043 }, { "epoch": 0.2, "grad_norm": 1.0191206679678395, "learning_rate": 1.8507954659669677e-05, "loss": 0.9343, "step": 1044 }, { "epoch": 0.2, "grad_norm": 0.8520526428256973, "learning_rate": 1.850467871748593e-05, "loss": 0.6024, "step": 1045 }, { "epoch": 0.2, "grad_norm": 1.1461070510466875, "learning_rate": 1.850139947349308e-05, "loss": 0.9207, "step": 1046 }, { "epoch": 0.2, "grad_norm": 0.8094891674584318, "learning_rate": 1.8498116928964244e-05, "loss": 0.6453, "step": 1047 }, { "epoch": 0.2, "grad_norm": 1.0049135755560477, "learning_rate": 1.849483108517381e-05, "loss": 0.9316, "step": 1048 }, { "epoch": 0.2, "grad_norm": 0.9931268525631468, "learning_rate": 1.849154194339747e-05, "loss": 0.9558, "step": 1049 }, { "epoch": 0.2, "grad_norm": 1.082121183861666, "learning_rate": 1.8488249504912173e-05, "loss": 0.9172, "step": 1050 }, { "epoch": 0.2, "grad_norm": 1.2636238684887966, "learning_rate": 1.8484953770996163e-05, "loss": 0.9326, "step": 1051 }, { "epoch": 0.2, "grad_norm": 1.0738593796510756, "learning_rate": 1.848165474292895e-05, "loss": 0.9512, "step": 1052 }, { "epoch": 0.2, "grad_norm": 1.1503540609666099, "learning_rate": 1.8478352421991334e-05, "loss": 0.9265, "step": 1053 }, { "epoch": 0.2, "grad_norm": 1.0369497904242153, "learning_rate": 1.847504680946539e-05, "loss": 0.895, "step": 1054 }, { "epoch": 0.2, "grad_norm": 1.094536080854328, "learning_rate": 1.847173790663447e-05, "loss": 0.8831, "step": 1055 }, { "epoch": 0.2, "grad_norm": 1.067220176934619, "learning_rate": 1.8468425714783206e-05, "loss": 0.9712, "step": 1056 }, { "epoch": 0.2, "grad_norm": 1.2858457494770883, "learning_rate": 1.84651102351975e-05, "loss": 0.9656, "step": 1057 }, { "epoch": 0.2, "grad_norm": 0.9848842694264153, "learning_rate": 1.846179146916454e-05, "loss": 0.8986, "step": 1058 }, { "epoch": 0.2, "grad_norm": 0.945098273504261, "learning_rate": 1.8458469417972783e-05, "loss": 0.6627, "step": 1059 }, { "epoch": 0.2, "grad_norm": 1.1923910296139026, "learning_rate": 1.8455144082911965e-05, "loss": 0.8843, "step": 1060 }, { "epoch": 0.2, "grad_norm": 0.8145035764107355, "learning_rate": 1.8451815465273097e-05, "loss": 0.658, "step": 1061 }, { "epoch": 0.2, "grad_norm": 0.9785722252899866, "learning_rate": 1.8448483566348456e-05, "loss": 0.8909, "step": 1062 }, { "epoch": 0.2, "grad_norm": 1.0599636789191205, "learning_rate": 1.8445148387431605e-05, "loss": 0.9207, "step": 1063 }, { "epoch": 0.2, "grad_norm": 1.008365456305721, "learning_rate": 1.8441809929817382e-05, "loss": 0.8933, "step": 1064 }, { "epoch": 0.2, "grad_norm": 1.0194720375744968, "learning_rate": 1.8438468194801876e-05, "loss": 0.9514, "step": 1065 }, { "epoch": 0.21, "grad_norm": 1.137017916526766, "learning_rate": 1.8435123183682475e-05, "loss": 0.9146, "step": 1066 }, { "epoch": 0.21, "grad_norm": 1.0673533203905372, "learning_rate": 1.8431774897757824e-05, "loss": 0.9568, "step": 1067 }, { "epoch": 0.21, "grad_norm": 1.1282535888834881, "learning_rate": 1.8428423338327847e-05, "loss": 0.9758, "step": 1068 }, { "epoch": 0.21, "grad_norm": 0.8558275154169682, "learning_rate": 1.8425068506693727e-05, "loss": 0.6766, "step": 1069 }, { "epoch": 0.21, "grad_norm": 1.156815606496017, "learning_rate": 1.842171040415793e-05, "loss": 0.978, "step": 1070 }, { "epoch": 0.21, "grad_norm": 1.1206235528870492, "learning_rate": 1.8418349032024185e-05, "loss": 0.9639, "step": 1071 }, { "epoch": 0.21, "grad_norm": 1.116603689919841, "learning_rate": 1.8414984391597492e-05, "loss": 0.9644, "step": 1072 }, { "epoch": 0.21, "grad_norm": 1.0190074962004139, "learning_rate": 1.8411616484184126e-05, "loss": 0.9553, "step": 1073 }, { "epoch": 0.21, "grad_norm": 1.033171939469351, "learning_rate": 1.8408245311091618e-05, "loss": 0.9131, "step": 1074 }, { "epoch": 0.21, "grad_norm": 1.0426134382043808, "learning_rate": 1.8404870873628774e-05, "loss": 0.998, "step": 1075 }, { "epoch": 0.21, "grad_norm": 1.0753926967368104, "learning_rate": 1.8401493173105675e-05, "loss": 0.8901, "step": 1076 }, { "epoch": 0.21, "grad_norm": 1.0303261813452766, "learning_rate": 1.8398112210833648e-05, "loss": 0.9731, "step": 1077 }, { "epoch": 0.21, "grad_norm": 0.8355939751966474, "learning_rate": 1.8394727988125308e-05, "loss": 0.6151, "step": 1078 }, { "epoch": 0.21, "grad_norm": 1.2050887141002065, "learning_rate": 1.8391340506294524e-05, "loss": 1.0027, "step": 1079 }, { "epoch": 0.21, "grad_norm": 1.237961832826065, "learning_rate": 1.8387949766656434e-05, "loss": 0.9417, "step": 1080 }, { "epoch": 0.21, "grad_norm": 0.982064707153108, "learning_rate": 1.8384555770527438e-05, "loss": 0.9377, "step": 1081 }, { "epoch": 0.21, "grad_norm": 1.4089189393593817, "learning_rate": 1.8381158519225204e-05, "loss": 0.9883, "step": 1082 }, { "epoch": 0.21, "grad_norm": 1.0331772982888474, "learning_rate": 1.8377758014068662e-05, "loss": 0.6411, "step": 1083 }, { "epoch": 0.21, "grad_norm": 0.9739982336289478, "learning_rate": 1.8374354256378e-05, "loss": 0.968, "step": 1084 }, { "epoch": 0.21, "grad_norm": 1.0730767552104195, "learning_rate": 1.837094724747468e-05, "loss": 0.9421, "step": 1085 }, { "epoch": 0.21, "grad_norm": 1.2841908809768716, "learning_rate": 1.8367536988681422e-05, "loss": 0.9404, "step": 1086 }, { "epoch": 0.21, "grad_norm": 1.123488998045172, "learning_rate": 1.83641234813222e-05, "loss": 0.8816, "step": 1087 }, { "epoch": 0.21, "grad_norm": 0.945720568521259, "learning_rate": 1.8360706726722253e-05, "loss": 0.693, "step": 1088 }, { "epoch": 0.21, "grad_norm": 0.9831253262522023, "learning_rate": 1.835728672620809e-05, "loss": 0.9231, "step": 1089 }, { "epoch": 0.21, "grad_norm": 1.0225074134928214, "learning_rate": 1.8353863481107473e-05, "loss": 0.9387, "step": 1090 }, { "epoch": 0.21, "grad_norm": 0.8875386322245081, "learning_rate": 1.835043699274942e-05, "loss": 0.6273, "step": 1091 }, { "epoch": 0.21, "grad_norm": 1.0880103470220468, "learning_rate": 1.8347007262464206e-05, "loss": 0.9619, "step": 1092 }, { "epoch": 0.21, "grad_norm": 0.9484995412703988, "learning_rate": 1.8343574291583385e-05, "loss": 0.8782, "step": 1093 }, { "epoch": 0.21, "grad_norm": 1.192303320197761, "learning_rate": 1.8340138081439743e-05, "loss": 0.9292, "step": 1094 }, { "epoch": 0.21, "grad_norm": 0.9657932071334411, "learning_rate": 1.833669863336734e-05, "loss": 0.906, "step": 1095 }, { "epoch": 0.21, "grad_norm": 0.9889690174388761, "learning_rate": 1.833325594870148e-05, "loss": 0.9434, "step": 1096 }, { "epoch": 0.21, "grad_norm": 1.051353043757473, "learning_rate": 1.8329810028778747e-05, "loss": 0.6766, "step": 1097 }, { "epoch": 0.21, "grad_norm": 0.9507138500189386, "learning_rate": 1.8326360874936952e-05, "loss": 0.9514, "step": 1098 }, { "epoch": 0.21, "grad_norm": 0.9946790445188142, "learning_rate": 1.8322908488515182e-05, "loss": 0.9375, "step": 1099 }, { "epoch": 0.21, "grad_norm": 0.9840679140290667, "learning_rate": 1.8319452870853772e-05, "loss": 0.9016, "step": 1100 }, { "epoch": 0.21, "grad_norm": 1.0990142884762575, "learning_rate": 1.8315994023294306e-05, "loss": 0.97, "step": 1101 }, { "epoch": 0.21, "grad_norm": 0.9570659016885152, "learning_rate": 1.8312531947179634e-05, "loss": 0.8992, "step": 1102 }, { "epoch": 0.21, "grad_norm": 1.1750345317407596, "learning_rate": 1.8309066643853854e-05, "loss": 0.9292, "step": 1103 }, { "epoch": 0.21, "grad_norm": 1.0523462048766028, "learning_rate": 1.8305598114662312e-05, "loss": 0.9294, "step": 1104 }, { "epoch": 0.21, "grad_norm": 1.2573839640079547, "learning_rate": 1.830212636095161e-05, "loss": 0.9465, "step": 1105 }, { "epoch": 0.21, "grad_norm": 1.097555764696399, "learning_rate": 1.8298651384069605e-05, "loss": 0.8616, "step": 1106 }, { "epoch": 0.21, "grad_norm": 1.1248484015146714, "learning_rate": 1.8295173185365405e-05, "loss": 0.9636, "step": 1107 }, { "epoch": 0.21, "grad_norm": 1.0839509522809838, "learning_rate": 1.829169176618936e-05, "loss": 0.8975, "step": 1108 }, { "epoch": 0.21, "grad_norm": 1.0737524153950222, "learning_rate": 1.828820712789308e-05, "loss": 0.8755, "step": 1109 }, { "epoch": 0.21, "grad_norm": 0.9730470154381998, "learning_rate": 1.828471927182942e-05, "loss": 0.8887, "step": 1110 }, { "epoch": 0.21, "grad_norm": 1.2118012412655792, "learning_rate": 1.828122819935249e-05, "loss": 0.928, "step": 1111 }, { "epoch": 0.21, "grad_norm": 1.1163812646712763, "learning_rate": 1.8277733911817642e-05, "loss": 0.9919, "step": 1112 }, { "epoch": 0.21, "grad_norm": 0.9494982101264566, "learning_rate": 1.8274236410581478e-05, "loss": 0.7131, "step": 1113 }, { "epoch": 0.21, "grad_norm": 1.1135736486151968, "learning_rate": 1.827073569700185e-05, "loss": 0.9167, "step": 1114 }, { "epoch": 0.21, "grad_norm": 0.9774699829799552, "learning_rate": 1.8267231772437854e-05, "loss": 0.8743, "step": 1115 }, { "epoch": 0.21, "grad_norm": 1.2552163128076539, "learning_rate": 1.8263724638249834e-05, "loss": 0.9529, "step": 1116 }, { "epoch": 0.21, "grad_norm": 0.9223189839327494, "learning_rate": 1.8260214295799382e-05, "loss": 0.6813, "step": 1117 }, { "epoch": 0.22, "grad_norm": 1.1745442344906114, "learning_rate": 1.825670074644933e-05, "loss": 0.981, "step": 1118 }, { "epoch": 0.22, "grad_norm": 1.0842941410773848, "learning_rate": 1.8253183991563768e-05, "loss": 0.9299, "step": 1119 }, { "epoch": 0.22, "grad_norm": 1.1055360352777506, "learning_rate": 1.824966403250801e-05, "loss": 0.9006, "step": 1120 }, { "epoch": 0.22, "grad_norm": 1.0474154670536675, "learning_rate": 1.8246140870648633e-05, "loss": 0.9204, "step": 1121 }, { "epoch": 0.22, "grad_norm": 1.0695595106921978, "learning_rate": 1.8242614507353446e-05, "loss": 0.9546, "step": 1122 }, { "epoch": 0.22, "grad_norm": 1.0198190459189893, "learning_rate": 1.8239084943991507e-05, "loss": 0.8896, "step": 1123 }, { "epoch": 0.22, "grad_norm": 1.0509031062924086, "learning_rate": 1.823555218193311e-05, "loss": 0.9985, "step": 1124 }, { "epoch": 0.22, "grad_norm": 1.0225957409987052, "learning_rate": 1.8232016222549797e-05, "loss": 0.929, "step": 1125 }, { "epoch": 0.22, "grad_norm": 1.1546826480426722, "learning_rate": 1.8228477067214352e-05, "loss": 0.9294, "step": 1126 }, { "epoch": 0.22, "grad_norm": 1.083332183889626, "learning_rate": 1.8224934717300794e-05, "loss": 0.8872, "step": 1127 }, { "epoch": 0.22, "grad_norm": 1.1418373914264819, "learning_rate": 1.8221389174184385e-05, "loss": 0.9976, "step": 1128 }, { "epoch": 0.22, "grad_norm": 1.1483007758361186, "learning_rate": 1.8217840439241633e-05, "loss": 0.9106, "step": 1129 }, { "epoch": 0.22, "grad_norm": 0.8461292851302198, "learning_rate": 1.8214288513850267e-05, "loss": 0.6718, "step": 1130 }, { "epoch": 0.22, "grad_norm": 0.9133887416147323, "learning_rate": 1.8210733399389277e-05, "loss": 0.8782, "step": 1131 }, { "epoch": 0.22, "grad_norm": 1.1755649464322842, "learning_rate": 1.820717509723888e-05, "loss": 0.9626, "step": 1132 }, { "epoch": 0.22, "grad_norm": 1.0238146937681667, "learning_rate": 1.8203613608780525e-05, "loss": 0.9673, "step": 1133 }, { "epoch": 0.22, "grad_norm": 1.1149197659109344, "learning_rate": 1.8200048935396908e-05, "loss": 0.8115, "step": 1134 }, { "epoch": 0.22, "grad_norm": 1.0121949793663527, "learning_rate": 1.819648107847196e-05, "loss": 0.8989, "step": 1135 }, { "epoch": 0.22, "grad_norm": 1.2563317683727924, "learning_rate": 1.8192910039390844e-05, "loss": 0.9617, "step": 1136 }, { "epoch": 0.22, "grad_norm": 1.27196789921843, "learning_rate": 1.8189335819539963e-05, "loss": 0.948, "step": 1137 }, { "epoch": 0.22, "grad_norm": 0.6517850973598525, "learning_rate": 1.8185758420306947e-05, "loss": 0.3599, "step": 1138 }, { "epoch": 0.22, "grad_norm": 1.2644704951288486, "learning_rate": 1.818217784308067e-05, "loss": 0.8694, "step": 1139 }, { "epoch": 0.22, "grad_norm": 1.0649299291921892, "learning_rate": 1.817859408925123e-05, "loss": 0.9529, "step": 1140 }, { "epoch": 0.22, "grad_norm": 0.7766308573666082, "learning_rate": 1.817500716020997e-05, "loss": 0.6089, "step": 1141 }, { "epoch": 0.22, "grad_norm": 1.0181596632080707, "learning_rate": 1.8171417057349457e-05, "loss": 0.9368, "step": 1142 }, { "epoch": 0.22, "grad_norm": 1.169195350796188, "learning_rate": 1.816782378206349e-05, "loss": 0.8953, "step": 1143 }, { "epoch": 0.22, "grad_norm": 0.9766448861179385, "learning_rate": 1.8164227335747108e-05, "loss": 0.8433, "step": 1144 }, { "epoch": 0.22, "grad_norm": 0.7996526155534558, "learning_rate": 1.8160627719796568e-05, "loss": 0.6178, "step": 1145 }, { "epoch": 0.22, "grad_norm": 1.0113767854665272, "learning_rate": 1.815702493560937e-05, "loss": 0.913, "step": 1146 }, { "epoch": 0.22, "grad_norm": 1.1137472252491436, "learning_rate": 1.8153418984584238e-05, "loss": 0.9065, "step": 1147 }, { "epoch": 0.22, "grad_norm": 1.1465850656701715, "learning_rate": 1.8149809868121125e-05, "loss": 0.9185, "step": 1148 }, { "epoch": 0.22, "grad_norm": 0.9266777117012296, "learning_rate": 1.8146197587621217e-05, "loss": 0.6072, "step": 1149 }, { "epoch": 0.22, "grad_norm": 1.0923176273759794, "learning_rate": 1.814258214448692e-05, "loss": 0.9465, "step": 1150 }, { "epoch": 0.22, "grad_norm": 1.0929495245167682, "learning_rate": 1.8138963540121878e-05, "loss": 0.9766, "step": 1151 }, { "epoch": 0.22, "grad_norm": 0.9957496761729404, "learning_rate": 1.813534177593096e-05, "loss": 0.8904, "step": 1152 }, { "epoch": 0.22, "grad_norm": 0.944910238968246, "learning_rate": 1.8131716853320254e-05, "loss": 0.9001, "step": 1153 }, { "epoch": 0.22, "grad_norm": 0.9944534508669542, "learning_rate": 1.8128088773697086e-05, "loss": 0.9336, "step": 1154 }, { "epoch": 0.22, "grad_norm": 1.0835876172620338, "learning_rate": 1.8124457538469996e-05, "loss": 0.9175, "step": 1155 }, { "epoch": 0.22, "grad_norm": 1.0456891147598022, "learning_rate": 1.8120823149048753e-05, "loss": 0.9478, "step": 1156 }, { "epoch": 0.22, "grad_norm": 0.8864976298968488, "learning_rate": 1.811718560684436e-05, "loss": 0.6495, "step": 1157 }, { "epoch": 0.22, "grad_norm": 1.0718557553946166, "learning_rate": 1.8113544913269025e-05, "loss": 0.9182, "step": 1158 }, { "epoch": 0.22, "grad_norm": 0.9611694253044054, "learning_rate": 1.8109901069736202e-05, "loss": 0.8669, "step": 1159 }, { "epoch": 0.22, "grad_norm": 0.9845657882783234, "learning_rate": 1.8106254077660552e-05, "loss": 0.9431, "step": 1160 }, { "epoch": 0.22, "grad_norm": 1.0730164353809761, "learning_rate": 1.810260393845796e-05, "loss": 1.0088, "step": 1161 }, { "epoch": 0.22, "grad_norm": 1.0257859485239704, "learning_rate": 1.809895065354554e-05, "loss": 0.896, "step": 1162 }, { "epoch": 0.22, "grad_norm": 1.0539916436217107, "learning_rate": 1.8095294224341622e-05, "loss": 0.929, "step": 1163 }, { "epoch": 0.22, "grad_norm": 1.3997659420518302, "learning_rate": 1.8091634652265755e-05, "loss": 0.9568, "step": 1164 }, { "epoch": 0.22, "grad_norm": 1.09346138401039, "learning_rate": 1.8087971938738715e-05, "loss": 0.9839, "step": 1165 }, { "epoch": 0.22, "grad_norm": 1.1523872904714607, "learning_rate": 1.808430608518249e-05, "loss": 0.9832, "step": 1166 }, { "epoch": 0.22, "grad_norm": 1.0337968440513414, "learning_rate": 1.808063709302029e-05, "loss": 0.9165, "step": 1167 }, { "epoch": 0.22, "grad_norm": 1.0727769257129312, "learning_rate": 1.807696496367655e-05, "loss": 0.9534, "step": 1168 }, { "epoch": 0.22, "grad_norm": 0.995434980308402, "learning_rate": 1.8073289698576913e-05, "loss": 0.8823, "step": 1169 }, { "epoch": 0.23, "grad_norm": 0.8827495402170271, "learning_rate": 1.8069611299148236e-05, "loss": 0.6786, "step": 1170 }, { "epoch": 0.23, "grad_norm": 1.0686007249746472, "learning_rate": 1.8065929766818617e-05, "loss": 0.9253, "step": 1171 }, { "epoch": 0.23, "grad_norm": 1.0737842890672094, "learning_rate": 1.806224510301734e-05, "loss": 0.9712, "step": 1172 }, { "epoch": 0.23, "grad_norm": 1.1300914150640662, "learning_rate": 1.8058557309174926e-05, "loss": 0.8861, "step": 1173 }, { "epoch": 0.23, "grad_norm": 1.0100325203098848, "learning_rate": 1.8054866386723096e-05, "loss": 0.9241, "step": 1174 }, { "epoch": 0.23, "grad_norm": 1.0658200464078806, "learning_rate": 1.80511723370948e-05, "loss": 0.9033, "step": 1175 }, { "epoch": 0.23, "grad_norm": 0.995962139041396, "learning_rate": 1.804747516172419e-05, "loss": 0.9128, "step": 1176 }, { "epoch": 0.23, "grad_norm": 1.0648977852509987, "learning_rate": 1.8043774862046644e-05, "loss": 0.9731, "step": 1177 }, { "epoch": 0.23, "grad_norm": 1.0985873168426132, "learning_rate": 1.804007143949874e-05, "loss": 0.9678, "step": 1178 }, { "epoch": 0.23, "grad_norm": 1.0563180129305538, "learning_rate": 1.8036364895518272e-05, "loss": 0.9236, "step": 1179 }, { "epoch": 0.23, "grad_norm": 0.9376607282764743, "learning_rate": 1.8032655231544253e-05, "loss": 0.8989, "step": 1180 }, { "epoch": 0.23, "grad_norm": 1.2381773391380326, "learning_rate": 1.8028942449016903e-05, "loss": 0.9878, "step": 1181 }, { "epoch": 0.23, "grad_norm": 1.1275555659007652, "learning_rate": 1.8025226549377647e-05, "loss": 0.9077, "step": 1182 }, { "epoch": 0.23, "grad_norm": 1.201472777479429, "learning_rate": 1.8021507534069133e-05, "loss": 0.9973, "step": 1183 }, { "epoch": 0.23, "grad_norm": 1.0840343661422542, "learning_rate": 1.8017785404535198e-05, "loss": 0.9089, "step": 1184 }, { "epoch": 0.23, "grad_norm": 1.0654421696556724, "learning_rate": 1.8014060162220916e-05, "loss": 0.9233, "step": 1185 }, { "epoch": 0.23, "grad_norm": 0.8320761738993309, "learning_rate": 1.801033180857254e-05, "loss": 0.5805, "step": 1186 }, { "epoch": 0.23, "grad_norm": 1.1252865470887394, "learning_rate": 1.8006600345037558e-05, "loss": 0.9128, "step": 1187 }, { "epoch": 0.23, "grad_norm": 1.0809541625810983, "learning_rate": 1.8002865773064644e-05, "loss": 0.9119, "step": 1188 }, { "epoch": 0.23, "grad_norm": 1.0069947288644188, "learning_rate": 1.799912809410369e-05, "loss": 0.9041, "step": 1189 }, { "epoch": 0.23, "grad_norm": 1.2072622578121648, "learning_rate": 1.799538730960579e-05, "loss": 0.9038, "step": 1190 }, { "epoch": 0.23, "grad_norm": 1.0775414050064498, "learning_rate": 1.799164342102325e-05, "loss": 0.9054, "step": 1191 }, { "epoch": 0.23, "grad_norm": 1.059497227323624, "learning_rate": 1.7987896429809573e-05, "loss": 0.9236, "step": 1192 }, { "epoch": 0.23, "grad_norm": 1.2463460312034778, "learning_rate": 1.798414633741947e-05, "loss": 0.9727, "step": 1193 }, { "epoch": 0.23, "grad_norm": 1.0682605451650125, "learning_rate": 1.7980393145308857e-05, "loss": 0.9048, "step": 1194 }, { "epoch": 0.23, "grad_norm": 1.2510916335362054, "learning_rate": 1.797663685493485e-05, "loss": 0.99, "step": 1195 }, { "epoch": 0.23, "grad_norm": 0.855799625153138, "learning_rate": 1.7972877467755777e-05, "loss": 0.6445, "step": 1196 }, { "epoch": 0.23, "grad_norm": 1.2791538038403734, "learning_rate": 1.7969114985231152e-05, "loss": 0.9431, "step": 1197 }, { "epoch": 0.23, "grad_norm": 1.1178410373755048, "learning_rate": 1.796534940882171e-05, "loss": 0.9553, "step": 1198 }, { "epoch": 0.23, "grad_norm": 1.0767212947691662, "learning_rate": 1.7961580739989365e-05, "loss": 0.9771, "step": 1199 }, { "epoch": 0.23, "grad_norm": 1.0487231771700685, "learning_rate": 1.795780898019726e-05, "loss": 0.9573, "step": 1200 }, { "epoch": 0.23, "grad_norm": 1.141055312640999, "learning_rate": 1.795403413090971e-05, "loss": 0.9668, "step": 1201 }, { "epoch": 0.23, "grad_norm": 1.0536002265796032, "learning_rate": 1.7950256193592243e-05, "loss": 0.9385, "step": 1202 }, { "epoch": 0.23, "grad_norm": 0.9053531753582292, "learning_rate": 1.794647516971159e-05, "loss": 0.6125, "step": 1203 }, { "epoch": 0.23, "grad_norm": 1.163712536526238, "learning_rate": 1.7942691060735666e-05, "loss": 0.9279, "step": 1204 }, { "epoch": 0.23, "grad_norm": 1.1113627608345746, "learning_rate": 1.79389038681336e-05, "loss": 0.9377, "step": 1205 }, { "epoch": 0.23, "grad_norm": 1.0613336364913977, "learning_rate": 1.7935113593375707e-05, "loss": 0.897, "step": 1206 }, { "epoch": 0.23, "grad_norm": 1.1950448759614216, "learning_rate": 1.7931320237933503e-05, "loss": 0.9241, "step": 1207 }, { "epoch": 0.23, "grad_norm": 0.8193515968190349, "learning_rate": 1.79275238032797e-05, "loss": 0.6141, "step": 1208 }, { "epoch": 0.23, "grad_norm": 1.0707906455313911, "learning_rate": 1.7923724290888205e-05, "loss": 0.9092, "step": 1209 }, { "epoch": 0.23, "grad_norm": 1.0612002010457389, "learning_rate": 1.791992170223412e-05, "loss": 0.9341, "step": 1210 }, { "epoch": 0.23, "grad_norm": 0.9855588781353127, "learning_rate": 1.791611603879374e-05, "loss": 0.8701, "step": 1211 }, { "epoch": 0.23, "grad_norm": 1.0262296471734864, "learning_rate": 1.791230730204455e-05, "loss": 0.9141, "step": 1212 }, { "epoch": 0.23, "grad_norm": 1.1413454287709766, "learning_rate": 1.7908495493465236e-05, "loss": 0.6177, "step": 1213 }, { "epoch": 0.23, "grad_norm": 1.0866709051168464, "learning_rate": 1.7904680614535675e-05, "loss": 0.9785, "step": 1214 }, { "epoch": 0.23, "grad_norm": 1.0531190083719562, "learning_rate": 1.7900862666736935e-05, "loss": 0.928, "step": 1215 }, { "epoch": 0.23, "grad_norm": 1.0925427217564427, "learning_rate": 1.789704165155127e-05, "loss": 0.9543, "step": 1216 }, { "epoch": 0.23, "grad_norm": 1.0911638384700475, "learning_rate": 1.7893217570462134e-05, "loss": 0.9282, "step": 1217 }, { "epoch": 0.23, "grad_norm": 1.200099222668161, "learning_rate": 1.7889390424954168e-05, "loss": 0.9724, "step": 1218 }, { "epoch": 0.23, "grad_norm": 1.101824334068246, "learning_rate": 1.78855602165132e-05, "loss": 0.9695, "step": 1219 }, { "epoch": 0.23, "grad_norm": 1.1755781824100466, "learning_rate": 1.7881726946626244e-05, "loss": 0.9028, "step": 1220 }, { "epoch": 0.23, "grad_norm": 1.0076278389820454, "learning_rate": 1.787789061678151e-05, "loss": 0.9426, "step": 1221 }, { "epoch": 0.24, "grad_norm": 1.0112452510543493, "learning_rate": 1.78740512284684e-05, "loss": 0.9277, "step": 1222 }, { "epoch": 0.24, "grad_norm": 1.0283479069859183, "learning_rate": 1.787020878317749e-05, "loss": 0.8721, "step": 1223 }, { "epoch": 0.24, "grad_norm": 1.0015982311662461, "learning_rate": 1.7866363282400555e-05, "loss": 0.9053, "step": 1224 }, { "epoch": 0.24, "grad_norm": 1.120780148324142, "learning_rate": 1.7862514727630543e-05, "loss": 0.6289, "step": 1225 }, { "epoch": 0.24, "grad_norm": 1.1117795677180238, "learning_rate": 1.7858663120361597e-05, "loss": 0.9224, "step": 1226 }, { "epoch": 0.24, "grad_norm": 1.130792443694579, "learning_rate": 1.785480846208905e-05, "loss": 0.9631, "step": 1227 }, { "epoch": 0.24, "grad_norm": 1.028949031152237, "learning_rate": 1.7850950754309405e-05, "loss": 0.9773, "step": 1228 }, { "epoch": 0.24, "grad_norm": 1.0899608151396445, "learning_rate": 1.7847089998520365e-05, "loss": 0.8412, "step": 1229 }, { "epoch": 0.24, "grad_norm": 1.0577285515121762, "learning_rate": 1.7843226196220803e-05, "loss": 0.9414, "step": 1230 }, { "epoch": 0.24, "grad_norm": 1.0480373558706213, "learning_rate": 1.783935934891078e-05, "loss": 0.9407, "step": 1231 }, { "epoch": 0.24, "grad_norm": 1.1685739519290115, "learning_rate": 1.7835489458091544e-05, "loss": 0.9343, "step": 1232 }, { "epoch": 0.24, "grad_norm": 0.816277583948308, "learning_rate": 1.7831616525265515e-05, "loss": 0.6852, "step": 1233 }, { "epoch": 0.24, "grad_norm": 0.9786260584419755, "learning_rate": 1.7827740551936296e-05, "loss": 0.886, "step": 1234 }, { "epoch": 0.24, "grad_norm": 0.9714852033004941, "learning_rate": 1.7823861539608686e-05, "loss": 0.8862, "step": 1235 }, { "epoch": 0.24, "grad_norm": 1.0734265645699028, "learning_rate": 1.7819979489788638e-05, "loss": 0.9026, "step": 1236 }, { "epoch": 0.24, "grad_norm": 0.9884546646297946, "learning_rate": 1.7816094403983298e-05, "loss": 0.9409, "step": 1237 }, { "epoch": 0.24, "grad_norm": 1.015760508195, "learning_rate": 1.7812206283701002e-05, "loss": 0.9319, "step": 1238 }, { "epoch": 0.24, "grad_norm": 1.012766973025584, "learning_rate": 1.7808315130451244e-05, "loss": 0.8811, "step": 1239 }, { "epoch": 0.24, "grad_norm": 0.9404290012107556, "learning_rate": 1.78044209457447e-05, "loss": 0.8945, "step": 1240 }, { "epoch": 0.24, "grad_norm": 0.9334140331775774, "learning_rate": 1.7800523731093232e-05, "loss": 0.8928, "step": 1241 }, { "epoch": 0.24, "grad_norm": 1.100911000941317, "learning_rate": 1.7796623488009875e-05, "loss": 0.9448, "step": 1242 }, { "epoch": 0.24, "grad_norm": 1.1474888477583434, "learning_rate": 1.7792720218008826e-05, "loss": 0.9385, "step": 1243 }, { "epoch": 0.24, "grad_norm": 1.0464856334203834, "learning_rate": 1.7788813922605488e-05, "loss": 0.9602, "step": 1244 }, { "epoch": 0.24, "grad_norm": 1.0900173054404991, "learning_rate": 1.7784904603316402e-05, "loss": 0.9719, "step": 1245 }, { "epoch": 0.24, "grad_norm": 1.0730506849342814, "learning_rate": 1.7780992261659305e-05, "loss": 0.9688, "step": 1246 }, { "epoch": 0.24, "grad_norm": 1.2011206906741123, "learning_rate": 1.777707689915311e-05, "loss": 0.9551, "step": 1247 }, { "epoch": 0.24, "grad_norm": 0.9690380804912551, "learning_rate": 1.777315851731789e-05, "loss": 0.9495, "step": 1248 }, { "epoch": 0.24, "grad_norm": 0.9823428550228152, "learning_rate": 1.7769237117674893e-05, "loss": 0.9583, "step": 1249 }, { "epoch": 0.24, "grad_norm": 1.0730112782379693, "learning_rate": 1.7765312701746543e-05, "loss": 0.8728, "step": 1250 }, { "epoch": 0.24, "grad_norm": 1.1158908337443416, "learning_rate": 1.7761385271056436e-05, "loss": 0.8892, "step": 1251 }, { "epoch": 0.24, "grad_norm": 0.8671586170412707, "learning_rate": 1.7757454827129338e-05, "loss": 0.6313, "step": 1252 }, { "epoch": 0.24, "grad_norm": 1.0727181524170801, "learning_rate": 1.7753521371491174e-05, "loss": 0.9268, "step": 1253 }, { "epoch": 0.24, "grad_norm": 1.1636417075597727, "learning_rate": 1.7749584905669057e-05, "loss": 0.9438, "step": 1254 }, { "epoch": 0.24, "grad_norm": 1.2261606975533892, "learning_rate": 1.774564543119125e-05, "loss": 0.9351, "step": 1255 }, { "epoch": 0.24, "grad_norm": 1.08250354342942, "learning_rate": 1.7741702949587196e-05, "loss": 0.9377, "step": 1256 }, { "epoch": 0.24, "grad_norm": 0.9904611812613939, "learning_rate": 1.7737757462387507e-05, "loss": 0.916, "step": 1257 }, { "epoch": 0.24, "grad_norm": 1.1260050950318594, "learning_rate": 1.7733808971123946e-05, "loss": 0.9075, "step": 1258 }, { "epoch": 0.24, "grad_norm": 1.1168992814502263, "learning_rate": 1.7729857477329463e-05, "loss": 0.9573, "step": 1259 }, { "epoch": 0.24, "grad_norm": 1.0932288847495337, "learning_rate": 1.7725902982538162e-05, "loss": 0.9646, "step": 1260 }, { "epoch": 0.24, "grad_norm": 1.133866854314525, "learning_rate": 1.772194548828531e-05, "loss": 0.9768, "step": 1261 }, { "epoch": 0.24, "grad_norm": 1.0697038264807217, "learning_rate": 1.7717984996107346e-05, "loss": 0.8938, "step": 1262 }, { "epoch": 0.24, "grad_norm": 1.0583562925539123, "learning_rate": 1.771402150754187e-05, "loss": 0.9004, "step": 1263 }, { "epoch": 0.24, "grad_norm": 1.093345123736815, "learning_rate": 1.7710055024127637e-05, "loss": 0.9727, "step": 1264 }, { "epoch": 0.24, "grad_norm": 0.9485533632918701, "learning_rate": 1.7706085547404582e-05, "loss": 0.8662, "step": 1265 }, { "epoch": 0.24, "grad_norm": 0.8836200233684225, "learning_rate": 1.770211307891379e-05, "loss": 0.6906, "step": 1266 }, { "epoch": 0.24, "grad_norm": 1.0693511410943146, "learning_rate": 1.769813762019751e-05, "loss": 0.9363, "step": 1267 }, { "epoch": 0.24, "grad_norm": 1.0098090346946196, "learning_rate": 1.769415917279915e-05, "loss": 0.9436, "step": 1268 }, { "epoch": 0.24, "grad_norm": 1.0506572995945198, "learning_rate": 1.7690177738263284e-05, "loss": 0.9434, "step": 1269 }, { "epoch": 0.24, "grad_norm": 1.0502056775424937, "learning_rate": 1.7686193318135635e-05, "loss": 0.9387, "step": 1270 }, { "epoch": 0.24, "grad_norm": 0.9854957560835962, "learning_rate": 1.76822059139631e-05, "loss": 0.9856, "step": 1271 }, { "epoch": 0.24, "grad_norm": 0.8243292298328984, "learning_rate": 1.7678215527293724e-05, "loss": 0.6244, "step": 1272 }, { "epoch": 0.24, "grad_norm": 1.0800754765241822, "learning_rate": 1.767422215967671e-05, "loss": 0.8833, "step": 1273 }, { "epoch": 0.25, "grad_norm": 0.9391296423609503, "learning_rate": 1.767022581266242e-05, "loss": 0.6641, "step": 1274 }, { "epoch": 0.25, "grad_norm": 1.0493215551467465, "learning_rate": 1.766622648780238e-05, "loss": 0.9077, "step": 1275 }, { "epoch": 0.25, "grad_norm": 1.0354907743621584, "learning_rate": 1.766222418664926e-05, "loss": 0.8965, "step": 1276 }, { "epoch": 0.25, "grad_norm": 1.0635356672097067, "learning_rate": 1.765821891075689e-05, "loss": 0.9827, "step": 1277 }, { "epoch": 0.25, "grad_norm": 1.1551826520785284, "learning_rate": 1.7654210661680263e-05, "loss": 0.9622, "step": 1278 }, { "epoch": 0.25, "grad_norm": 1.0002972806604657, "learning_rate": 1.765019944097551e-05, "loss": 0.9387, "step": 1279 }, { "epoch": 0.25, "grad_norm": 1.2064781021008695, "learning_rate": 1.7646185250199936e-05, "loss": 0.8811, "step": 1280 }, { "epoch": 0.25, "grad_norm": 1.1728714140038636, "learning_rate": 1.7642168090911976e-05, "loss": 0.9196, "step": 1281 }, { "epoch": 0.25, "grad_norm": 1.0101691614267732, "learning_rate": 1.763814796467124e-05, "loss": 0.9321, "step": 1282 }, { "epoch": 0.25, "grad_norm": 1.0454976505367906, "learning_rate": 1.763412487303847e-05, "loss": 0.9089, "step": 1283 }, { "epoch": 0.25, "grad_norm": 1.0154030940287508, "learning_rate": 1.7630098817575578e-05, "loss": 0.8672, "step": 1284 }, { "epoch": 0.25, "grad_norm": 1.0836982886508444, "learning_rate": 1.762606979984561e-05, "loss": 0.9583, "step": 1285 }, { "epoch": 0.25, "grad_norm": 1.0090889051205654, "learning_rate": 1.7622037821412775e-05, "loss": 0.8931, "step": 1286 }, { "epoch": 0.25, "grad_norm": 1.0133811339873764, "learning_rate": 1.7618002883842426e-05, "loss": 0.8777, "step": 1287 }, { "epoch": 0.25, "grad_norm": 1.0389469352924563, "learning_rate": 1.7613964988701057e-05, "loss": 0.9207, "step": 1288 }, { "epoch": 0.25, "grad_norm": 1.0579822703569295, "learning_rate": 1.7609924137556326e-05, "loss": 0.9214, "step": 1289 }, { "epoch": 0.25, "grad_norm": 1.1583677501742964, "learning_rate": 1.7605880331977022e-05, "loss": 0.9932, "step": 1290 }, { "epoch": 0.25, "grad_norm": 1.0682576183784758, "learning_rate": 1.76018335735331e-05, "loss": 0.9419, "step": 1291 }, { "epoch": 0.25, "grad_norm": 0.8442608955491858, "learning_rate": 1.7597783863795644e-05, "loss": 0.6917, "step": 1292 }, { "epoch": 0.25, "grad_norm": 0.9262210969523395, "learning_rate": 1.7593731204336895e-05, "loss": 0.624, "step": 1293 }, { "epoch": 0.25, "grad_norm": 1.0585089227034632, "learning_rate": 1.7589675596730233e-05, "loss": 0.9094, "step": 1294 }, { "epoch": 0.25, "grad_norm": 1.0765147511048634, "learning_rate": 1.758561704255018e-05, "loss": 0.9446, "step": 1295 }, { "epoch": 0.25, "grad_norm": 1.2279799188667078, "learning_rate": 1.7581555543372413e-05, "loss": 0.9512, "step": 1296 }, { "epoch": 0.25, "grad_norm": 1.1840305254244161, "learning_rate": 1.7577491100773744e-05, "loss": 0.9912, "step": 1297 }, { "epoch": 0.25, "grad_norm": 1.0555176942229412, "learning_rate": 1.7573423716332128e-05, "loss": 0.926, "step": 1298 }, { "epoch": 0.25, "grad_norm": 1.1326503049722334, "learning_rate": 1.7569353391626665e-05, "loss": 0.8953, "step": 1299 }, { "epoch": 0.25, "grad_norm": 0.9329546669810064, "learning_rate": 1.7565280128237595e-05, "loss": 0.9392, "step": 1300 }, { "epoch": 0.25, "grad_norm": 1.0748104199979798, "learning_rate": 1.75612039277463e-05, "loss": 0.9255, "step": 1301 }, { "epoch": 0.25, "grad_norm": 1.0542618803357262, "learning_rate": 1.75571247917353e-05, "loss": 0.9082, "step": 1302 }, { "epoch": 0.25, "grad_norm": 1.0339141361582358, "learning_rate": 1.7553042721788255e-05, "loss": 0.591, "step": 1303 }, { "epoch": 0.25, "grad_norm": 1.0637426726476071, "learning_rate": 1.754895771948997e-05, "loss": 0.9224, "step": 1304 }, { "epoch": 0.25, "grad_norm": 1.1673961627511802, "learning_rate": 1.754486978642637e-05, "loss": 0.9988, "step": 1305 }, { "epoch": 0.25, "grad_norm": 1.0649612884904291, "learning_rate": 1.7540778924184553e-05, "loss": 0.9902, "step": 1306 }, { "epoch": 0.25, "grad_norm": 1.0415335977143017, "learning_rate": 1.7536685134352717e-05, "loss": 0.8911, "step": 1307 }, { "epoch": 0.25, "grad_norm": 1.2256844237829831, "learning_rate": 1.7532588418520215e-05, "loss": 0.8473, "step": 1308 }, { "epoch": 0.25, "grad_norm": 1.1419614378826282, "learning_rate": 1.7528488778277535e-05, "loss": 0.9785, "step": 1309 }, { "epoch": 0.25, "grad_norm": 1.0547537452812334, "learning_rate": 1.75243862152163e-05, "loss": 0.9084, "step": 1310 }, { "epoch": 0.25, "grad_norm": 0.998749935116724, "learning_rate": 1.752028073092926e-05, "loss": 0.9485, "step": 1311 }, { "epoch": 0.25, "grad_norm": 0.8246661622720798, "learning_rate": 1.7516172327010314e-05, "loss": 0.6462, "step": 1312 }, { "epoch": 0.25, "grad_norm": 1.2046096343589976, "learning_rate": 1.751206100505448e-05, "loss": 1.0183, "step": 1313 }, { "epoch": 0.25, "grad_norm": 0.9880026274494775, "learning_rate": 1.7507946766657914e-05, "loss": 0.9209, "step": 1314 }, { "epoch": 0.25, "grad_norm": 1.088573126151985, "learning_rate": 1.7503829613417905e-05, "loss": 0.8777, "step": 1315 }, { "epoch": 0.25, "grad_norm": 1.2039136101802834, "learning_rate": 1.749970954693288e-05, "loss": 0.9163, "step": 1316 }, { "epoch": 0.25, "grad_norm": 1.2950510267002415, "learning_rate": 1.7495586568802384e-05, "loss": 0.9873, "step": 1317 }, { "epoch": 0.25, "grad_norm": 1.055079213224455, "learning_rate": 1.7491460680627105e-05, "loss": 0.9912, "step": 1318 }, { "epoch": 0.25, "grad_norm": 1.1278010469417232, "learning_rate": 1.7487331884008845e-05, "loss": 0.9844, "step": 1319 }, { "epoch": 0.25, "grad_norm": 1.125009965521331, "learning_rate": 1.7483200180550554e-05, "loss": 0.9309, "step": 1320 }, { "epoch": 0.25, "grad_norm": 1.1507491061621842, "learning_rate": 1.74790655718563e-05, "loss": 0.9751, "step": 1321 }, { "epoch": 0.25, "grad_norm": 1.0399516286051134, "learning_rate": 1.747492805953128e-05, "loss": 0.9316, "step": 1322 }, { "epoch": 0.25, "grad_norm": 0.9349677171196386, "learning_rate": 1.7470787645181818e-05, "loss": 0.9329, "step": 1323 }, { "epoch": 0.25, "grad_norm": 1.1399964301408694, "learning_rate": 1.7466644330415362e-05, "loss": 0.9487, "step": 1324 }, { "epoch": 0.25, "grad_norm": 1.0528726240380093, "learning_rate": 1.7462498116840496e-05, "loss": 0.9197, "step": 1325 }, { "epoch": 0.26, "grad_norm": 1.0288247239360577, "learning_rate": 1.745834900606692e-05, "loss": 0.88, "step": 1326 }, { "epoch": 0.26, "grad_norm": 0.950981739332321, "learning_rate": 1.7454196999705458e-05, "loss": 0.8708, "step": 1327 }, { "epoch": 0.26, "grad_norm": 0.9792700909834605, "learning_rate": 1.7450042099368066e-05, "loss": 0.9277, "step": 1328 }, { "epoch": 0.26, "grad_norm": 0.9535757143851059, "learning_rate": 1.7445884306667823e-05, "loss": 0.8706, "step": 1329 }, { "epoch": 0.26, "grad_norm": 1.0430106233199117, "learning_rate": 1.7441723623218917e-05, "loss": 0.8982, "step": 1330 }, { "epoch": 0.26, "grad_norm": 1.0297329856875834, "learning_rate": 1.7437560050636678e-05, "loss": 0.876, "step": 1331 }, { "epoch": 0.26, "grad_norm": 0.9085753534320961, "learning_rate": 1.7433393590537543e-05, "loss": 0.6678, "step": 1332 }, { "epoch": 0.26, "grad_norm": 0.8059975056889287, "learning_rate": 1.7429224244539077e-05, "loss": 0.584, "step": 1333 }, { "epoch": 0.26, "grad_norm": 1.0702677310809368, "learning_rate": 1.7425052014259965e-05, "loss": 0.9482, "step": 1334 }, { "epoch": 0.26, "grad_norm": 1.089333314191587, "learning_rate": 1.7420876901320006e-05, "loss": 0.8845, "step": 1335 }, { "epoch": 0.26, "grad_norm": 0.8226463795191595, "learning_rate": 1.7416698907340128e-05, "loss": 0.5768, "step": 1336 }, { "epoch": 0.26, "grad_norm": 0.9515354472106012, "learning_rate": 1.741251803394237e-05, "loss": 0.9253, "step": 1337 }, { "epoch": 0.26, "grad_norm": 0.9118496204096508, "learning_rate": 1.740833428274989e-05, "loss": 0.9163, "step": 1338 }, { "epoch": 0.26, "grad_norm": 1.109826678097499, "learning_rate": 1.7404147655386966e-05, "loss": 0.8616, "step": 1339 }, { "epoch": 0.26, "grad_norm": 1.127335497167679, "learning_rate": 1.739995815347899e-05, "loss": 1.0012, "step": 1340 }, { "epoch": 0.26, "grad_norm": 0.9758369649200758, "learning_rate": 1.739576577865247e-05, "loss": 0.925, "step": 1341 }, { "epoch": 0.26, "grad_norm": 1.1401963389898242, "learning_rate": 1.739157053253503e-05, "loss": 0.9587, "step": 1342 }, { "epoch": 0.26, "grad_norm": 0.9873287539232598, "learning_rate": 1.738737241675541e-05, "loss": 0.8936, "step": 1343 }, { "epoch": 0.26, "grad_norm": 0.9076131386129926, "learning_rate": 1.7383171432943466e-05, "loss": 0.8838, "step": 1344 }, { "epoch": 0.26, "grad_norm": 0.824718694056724, "learning_rate": 1.737896758273016e-05, "loss": 0.6468, "step": 1345 }, { "epoch": 0.26, "grad_norm": 1.0056397570967717, "learning_rate": 1.7374760867747574e-05, "loss": 0.9031, "step": 1346 }, { "epoch": 0.26, "grad_norm": 1.0634125457320764, "learning_rate": 1.7370551289628895e-05, "loss": 0.855, "step": 1347 }, { "epoch": 0.26, "grad_norm": 1.0727804708729487, "learning_rate": 1.7366338850008432e-05, "loss": 0.9243, "step": 1348 }, { "epoch": 0.26, "grad_norm": 1.0261726610186515, "learning_rate": 1.73621235505216e-05, "loss": 0.8611, "step": 1349 }, { "epoch": 0.26, "grad_norm": 1.0122066036376196, "learning_rate": 1.7357905392804918e-05, "loss": 0.8204, "step": 1350 }, { "epoch": 0.26, "grad_norm": 1.0434122666158387, "learning_rate": 1.735368437849602e-05, "loss": 0.8928, "step": 1351 }, { "epoch": 0.26, "grad_norm": 1.0893403329656945, "learning_rate": 1.7349460509233654e-05, "loss": 0.9141, "step": 1352 }, { "epoch": 0.26, "grad_norm": 1.0928194472689612, "learning_rate": 1.734523378665767e-05, "loss": 0.9771, "step": 1353 }, { "epoch": 0.26, "grad_norm": 1.1531343629148076, "learning_rate": 1.7341004212409026e-05, "loss": 0.926, "step": 1354 }, { "epoch": 0.26, "grad_norm": 1.0358108260424905, "learning_rate": 1.7336771788129785e-05, "loss": 0.9441, "step": 1355 }, { "epoch": 0.26, "grad_norm": 0.7641673267503394, "learning_rate": 1.7332536515463126e-05, "loss": 0.6263, "step": 1356 }, { "epoch": 0.26, "grad_norm": 0.9895774309919246, "learning_rate": 1.7328298396053324e-05, "loss": 0.9465, "step": 1357 }, { "epoch": 0.26, "grad_norm": 1.121264304751721, "learning_rate": 1.7324057431545768e-05, "loss": 0.8792, "step": 1358 }, { "epoch": 0.26, "grad_norm": 1.0603398227199858, "learning_rate": 1.7319813623586935e-05, "loss": 0.887, "step": 1359 }, { "epoch": 0.26, "grad_norm": 1.1815772648446634, "learning_rate": 1.7315566973824433e-05, "loss": 0.9441, "step": 1360 }, { "epoch": 0.26, "grad_norm": 1.0591926313603302, "learning_rate": 1.7311317483906946e-05, "loss": 0.9409, "step": 1361 }, { "epoch": 0.26, "grad_norm": 1.0911372730864672, "learning_rate": 1.730706515548427e-05, "loss": 0.9402, "step": 1362 }, { "epoch": 0.26, "grad_norm": 1.1056202150345622, "learning_rate": 1.730280999020732e-05, "loss": 0.9546, "step": 1363 }, { "epoch": 0.26, "grad_norm": 1.166411842806586, "learning_rate": 1.729855198972808e-05, "loss": 0.9719, "step": 1364 }, { "epoch": 0.26, "grad_norm": 1.025330403466875, "learning_rate": 1.729429115569967e-05, "loss": 0.9531, "step": 1365 }, { "epoch": 0.26, "grad_norm": 0.8415918689721954, "learning_rate": 1.729002748977628e-05, "loss": 0.6409, "step": 1366 }, { "epoch": 0.26, "grad_norm": 1.1143311288159672, "learning_rate": 1.7285760993613215e-05, "loss": 0.9255, "step": 1367 }, { "epoch": 0.26, "grad_norm": 1.1900611884853942, "learning_rate": 1.7281491668866874e-05, "loss": 0.8992, "step": 1368 }, { "epoch": 0.26, "grad_norm": 1.0090580454236575, "learning_rate": 1.727721951719476e-05, "loss": 0.928, "step": 1369 }, { "epoch": 0.26, "grad_norm": 0.9570712329336472, "learning_rate": 1.7272944540255468e-05, "loss": 0.9297, "step": 1370 }, { "epoch": 0.26, "grad_norm": 1.104225968556191, "learning_rate": 1.726866673970869e-05, "loss": 0.9563, "step": 1371 }, { "epoch": 0.26, "grad_norm": 0.9774967090585286, "learning_rate": 1.7264386117215216e-05, "loss": 0.9103, "step": 1372 }, { "epoch": 0.26, "grad_norm": 1.1014100304896002, "learning_rate": 1.7260102674436933e-05, "loss": 0.906, "step": 1373 }, { "epoch": 0.26, "grad_norm": 0.9722718214973247, "learning_rate": 1.7255816413036818e-05, "loss": 0.8342, "step": 1374 }, { "epoch": 0.26, "grad_norm": 1.0432738350613935, "learning_rate": 1.7251527334678946e-05, "loss": 0.9492, "step": 1375 }, { "epoch": 0.26, "grad_norm": 0.9974861424463954, "learning_rate": 1.7247235441028486e-05, "loss": 0.5928, "step": 1376 }, { "epoch": 0.26, "grad_norm": 0.9386187202233041, "learning_rate": 1.7242940733751696e-05, "loss": 0.8938, "step": 1377 }, { "epoch": 0.27, "grad_norm": 0.9814426474274088, "learning_rate": 1.7238643214515934e-05, "loss": 0.9609, "step": 1378 }, { "epoch": 0.27, "grad_norm": 1.059029005036974, "learning_rate": 1.7234342884989642e-05, "loss": 0.834, "step": 1379 }, { "epoch": 0.27, "grad_norm": 1.1837882884910005, "learning_rate": 1.7230039746842352e-05, "loss": 0.9653, "step": 1380 }, { "epoch": 0.27, "grad_norm": 1.0683156702806322, "learning_rate": 1.7225733801744698e-05, "loss": 0.9226, "step": 1381 }, { "epoch": 0.27, "grad_norm": 1.069107886387366, "learning_rate": 1.7221425051368394e-05, "loss": 0.9326, "step": 1382 }, { "epoch": 0.27, "grad_norm": 1.0267056614584407, "learning_rate": 1.7217113497386245e-05, "loss": 0.9739, "step": 1383 }, { "epoch": 0.27, "grad_norm": 1.1848851066320405, "learning_rate": 1.721279914147214e-05, "loss": 0.864, "step": 1384 }, { "epoch": 0.27, "grad_norm": 0.9937877201960269, "learning_rate": 1.7208481985301065e-05, "loss": 0.9343, "step": 1385 }, { "epoch": 0.27, "grad_norm": 1.0569509329982114, "learning_rate": 1.7204162030549093e-05, "loss": 0.978, "step": 1386 }, { "epoch": 0.27, "grad_norm": 0.8961503318383008, "learning_rate": 1.7199839278893368e-05, "loss": 0.6486, "step": 1387 }, { "epoch": 0.27, "grad_norm": 1.0631760797999816, "learning_rate": 1.719551373201214e-05, "loss": 0.9175, "step": 1388 }, { "epoch": 0.27, "grad_norm": 0.9527141822084255, "learning_rate": 1.7191185391584736e-05, "loss": 0.681, "step": 1389 }, { "epoch": 0.27, "grad_norm": 1.079248308327481, "learning_rate": 1.7186854259291558e-05, "loss": 0.9744, "step": 1390 }, { "epoch": 0.27, "grad_norm": 1.233449013293012, "learning_rate": 1.7182520336814105e-05, "loss": 0.9541, "step": 1391 }, { "epoch": 0.27, "grad_norm": 0.9128977733415027, "learning_rate": 1.717818362583496e-05, "loss": 0.9348, "step": 1392 }, { "epoch": 0.27, "grad_norm": 1.0446941163164198, "learning_rate": 1.7173844128037777e-05, "loss": 0.8904, "step": 1393 }, { "epoch": 0.27, "grad_norm": 0.9346739274069086, "learning_rate": 1.71695018451073e-05, "loss": 0.651, "step": 1394 }, { "epoch": 0.27, "grad_norm": 0.9468715313721615, "learning_rate": 1.7165156778729355e-05, "loss": 0.8782, "step": 1395 }, { "epoch": 0.27, "grad_norm": 0.8893832287477669, "learning_rate": 1.7160808930590845e-05, "loss": 0.6847, "step": 1396 }, { "epoch": 0.27, "grad_norm": 1.0710334325051987, "learning_rate": 1.7156458302379753e-05, "loss": 0.9873, "step": 1397 }, { "epoch": 0.27, "grad_norm": 1.0429137250899323, "learning_rate": 1.7152104895785147e-05, "loss": 0.9641, "step": 1398 }, { "epoch": 0.27, "grad_norm": 1.1486078723080277, "learning_rate": 1.7147748712497162e-05, "loss": 0.9138, "step": 1399 }, { "epoch": 0.27, "grad_norm": 1.014501696201609, "learning_rate": 1.7143389754207026e-05, "loss": 0.9099, "step": 1400 }, { "epoch": 0.27, "grad_norm": 0.9258995455901942, "learning_rate": 1.713902802260703e-05, "loss": 0.6051, "step": 1401 }, { "epoch": 0.27, "grad_norm": 0.8392908754953687, "learning_rate": 1.7134663519390557e-05, "loss": 0.6133, "step": 1402 }, { "epoch": 0.27, "grad_norm": 1.0926776776700904, "learning_rate": 1.7130296246252048e-05, "loss": 0.9146, "step": 1403 }, { "epoch": 0.27, "grad_norm": 1.0538210170544882, "learning_rate": 1.7125926204887034e-05, "loss": 0.9417, "step": 1404 }, { "epoch": 0.27, "grad_norm": 1.1279438769286072, "learning_rate": 1.712155339699211e-05, "loss": 0.9458, "step": 1405 }, { "epoch": 0.27, "grad_norm": 0.7919926698491548, "learning_rate": 1.7117177824264962e-05, "loss": 0.6011, "step": 1406 }, { "epoch": 0.27, "grad_norm": 1.1851854932260153, "learning_rate": 1.7112799488404327e-05, "loss": 0.9255, "step": 1407 }, { "epoch": 0.27, "grad_norm": 1.0282535135050221, "learning_rate": 1.7108418391110033e-05, "loss": 0.9211, "step": 1408 }, { "epoch": 0.27, "grad_norm": 1.1965971773749216, "learning_rate": 1.7104034534082968e-05, "loss": 0.8596, "step": 1409 }, { "epoch": 0.27, "grad_norm": 0.900753520882448, "learning_rate": 1.7099647919025096e-05, "loss": 0.6139, "step": 1410 }, { "epoch": 0.27, "grad_norm": 1.0302293019988131, "learning_rate": 1.7095258547639456e-05, "loss": 0.9812, "step": 1411 }, { "epoch": 0.27, "grad_norm": 0.9455020353455571, "learning_rate": 1.709086642163015e-05, "loss": 0.9019, "step": 1412 }, { "epoch": 0.27, "grad_norm": 1.0582593570272982, "learning_rate": 1.7086471542702355e-05, "loss": 0.9026, "step": 1413 }, { "epoch": 0.27, "grad_norm": 1.0514508275759236, "learning_rate": 1.708207391256231e-05, "loss": 0.9048, "step": 1414 }, { "epoch": 0.27, "grad_norm": 1.1765963473286274, "learning_rate": 1.707767353291733e-05, "loss": 0.9377, "step": 1415 }, { "epoch": 0.27, "grad_norm": 1.006788230800832, "learning_rate": 1.7073270405475796e-05, "loss": 0.929, "step": 1416 }, { "epoch": 0.27, "grad_norm": 1.1100276209847038, "learning_rate": 1.7068864531947147e-05, "loss": 0.9446, "step": 1417 }, { "epoch": 0.27, "grad_norm": 1.4347126126070127, "learning_rate": 1.70644559140419e-05, "loss": 0.9202, "step": 1418 }, { "epoch": 0.27, "grad_norm": 1.0567225870217265, "learning_rate": 1.706004455347163e-05, "loss": 0.9368, "step": 1419 }, { "epoch": 0.27, "grad_norm": 0.9822818053568414, "learning_rate": 1.705563045194898e-05, "loss": 0.9258, "step": 1420 }, { "epoch": 0.27, "grad_norm": 0.9523996369022796, "learning_rate": 1.7051213611187657e-05, "loss": 0.6148, "step": 1421 }, { "epoch": 0.27, "grad_norm": 0.8896583134964569, "learning_rate": 1.704679403290243e-05, "loss": 0.6588, "step": 1422 }, { "epoch": 0.27, "grad_norm": 0.9011396970065904, "learning_rate": 1.7042371718809132e-05, "loss": 0.8671, "step": 1423 }, { "epoch": 0.27, "grad_norm": 0.9323986200539839, "learning_rate": 1.7037946670624652e-05, "loss": 0.6375, "step": 1424 }, { "epoch": 0.27, "grad_norm": 1.230342977014665, "learning_rate": 1.7033518890066956e-05, "loss": 0.8667, "step": 1425 }, { "epoch": 0.27, "grad_norm": 1.019587164702998, "learning_rate": 1.7029088378855055e-05, "loss": 0.9207, "step": 1426 }, { "epoch": 0.27, "grad_norm": 1.038573293994874, "learning_rate": 1.7024655138709025e-05, "loss": 0.8835, "step": 1427 }, { "epoch": 0.27, "grad_norm": 1.0248600301099766, "learning_rate": 1.7020219171350004e-05, "loss": 0.9321, "step": 1428 }, { "epoch": 0.27, "grad_norm": 1.0829178118738298, "learning_rate": 1.7015780478500187e-05, "loss": 0.9247, "step": 1429 }, { "epoch": 0.28, "grad_norm": 1.1077922854593507, "learning_rate": 1.701133906188283e-05, "loss": 0.8994, "step": 1430 }, { "epoch": 0.28, "grad_norm": 1.0076052141578085, "learning_rate": 1.700689492322224e-05, "loss": 0.8779, "step": 1431 }, { "epoch": 0.28, "grad_norm": 1.0614985798238854, "learning_rate": 1.700244806424379e-05, "loss": 0.9592, "step": 1432 }, { "epoch": 0.28, "grad_norm": 1.2374404826686807, "learning_rate": 1.6997998486673893e-05, "loss": 0.9646, "step": 1433 }, { "epoch": 0.28, "grad_norm": 0.9969225877030216, "learning_rate": 1.699354619224004e-05, "loss": 0.9551, "step": 1434 }, { "epoch": 0.28, "grad_norm": 1.1839524752734905, "learning_rate": 1.698909118267076e-05, "loss": 0.9424, "step": 1435 }, { "epoch": 0.28, "grad_norm": 0.9862969433699538, "learning_rate": 1.6984633459695646e-05, "loss": 0.6456, "step": 1436 }, { "epoch": 0.28, "grad_norm": 1.0935991866580514, "learning_rate": 1.6980173025045328e-05, "loss": 0.9443, "step": 1437 }, { "epoch": 0.28, "grad_norm": 1.1523879083157593, "learning_rate": 1.697570988045151e-05, "loss": 0.8774, "step": 1438 }, { "epoch": 0.28, "grad_norm": 0.9605142082195499, "learning_rate": 1.6971244027646937e-05, "loss": 0.8882, "step": 1439 }, { "epoch": 0.28, "grad_norm": 1.0622996244749991, "learning_rate": 1.69667754683654e-05, "loss": 0.9167, "step": 1440 }, { "epoch": 0.28, "grad_norm": 1.0085326888672954, "learning_rate": 1.6962304204341758e-05, "loss": 0.9382, "step": 1441 }, { "epoch": 0.28, "grad_norm": 1.223879108830366, "learning_rate": 1.6957830237311904e-05, "loss": 0.8987, "step": 1442 }, { "epoch": 0.28, "grad_norm": 1.5271656500840005, "learning_rate": 1.6953353569012784e-05, "loss": 0.9133, "step": 1443 }, { "epoch": 0.28, "grad_norm": 0.9870072543136768, "learning_rate": 1.6948874201182402e-05, "loss": 0.9548, "step": 1444 }, { "epoch": 0.28, "grad_norm": 1.0846784850212043, "learning_rate": 1.6944392135559798e-05, "loss": 0.9126, "step": 1445 }, { "epoch": 0.28, "grad_norm": 1.0405164210785829, "learning_rate": 1.6939907373885062e-05, "loss": 0.894, "step": 1446 }, { "epoch": 0.28, "grad_norm": 1.0048390002194763, "learning_rate": 1.6935419917899335e-05, "loss": 0.8706, "step": 1447 }, { "epoch": 0.28, "grad_norm": 0.8480792396551158, "learning_rate": 1.6930929769344807e-05, "loss": 0.6503, "step": 1448 }, { "epoch": 0.28, "grad_norm": 1.000630790256918, "learning_rate": 1.69264369299647e-05, "loss": 0.884, "step": 1449 }, { "epoch": 0.28, "grad_norm": 0.8967603520216046, "learning_rate": 1.692194140150329e-05, "loss": 0.6674, "step": 1450 }, { "epoch": 0.28, "grad_norm": 1.0768714043379202, "learning_rate": 1.69174431857059e-05, "loss": 0.9446, "step": 1451 }, { "epoch": 0.28, "grad_norm": 1.1823120267837615, "learning_rate": 1.6912942284318898e-05, "loss": 1.0415, "step": 1452 }, { "epoch": 0.28, "grad_norm": 1.0969466413566178, "learning_rate": 1.6908438699089674e-05, "loss": 0.9424, "step": 1453 }, { "epoch": 0.28, "grad_norm": 0.7744529998149635, "learning_rate": 1.690393243176668e-05, "loss": 0.3506, "step": 1454 }, { "epoch": 0.28, "grad_norm": 0.8192692170808742, "learning_rate": 1.6899423484099413e-05, "loss": 0.6259, "step": 1455 }, { "epoch": 0.28, "grad_norm": 1.0477041980126183, "learning_rate": 1.6894911857838394e-05, "loss": 0.8796, "step": 1456 }, { "epoch": 0.28, "grad_norm": 1.058513121310028, "learning_rate": 1.689039755473519e-05, "loss": 0.9138, "step": 1457 }, { "epoch": 0.28, "grad_norm": 1.182903484699486, "learning_rate": 1.6885880576542417e-05, "loss": 0.9246, "step": 1458 }, { "epoch": 0.28, "grad_norm": 1.0128672350627907, "learning_rate": 1.6881360925013712e-05, "loss": 0.9285, "step": 1459 }, { "epoch": 0.28, "grad_norm": 0.9946296819001265, "learning_rate": 1.6876838601903765e-05, "loss": 0.905, "step": 1460 }, { "epoch": 0.28, "grad_norm": 0.8047645150638862, "learning_rate": 1.6872313608968296e-05, "loss": 0.6338, "step": 1461 }, { "epoch": 0.28, "grad_norm": 0.9180229944576894, "learning_rate": 1.6867785947964065e-05, "loss": 0.6667, "step": 1462 }, { "epoch": 0.28, "grad_norm": 1.006189475243978, "learning_rate": 1.6863255620648866e-05, "loss": 0.8899, "step": 1463 }, { "epoch": 0.28, "grad_norm": 0.9707876038920926, "learning_rate": 1.685872262878152e-05, "loss": 0.9097, "step": 1464 }, { "epoch": 0.28, "grad_norm": 1.1331108610861111, "learning_rate": 1.6854186974121903e-05, "loss": 0.9207, "step": 1465 }, { "epoch": 0.28, "grad_norm": 1.1100588242149767, "learning_rate": 1.68496486584309e-05, "loss": 0.8945, "step": 1466 }, { "epoch": 0.28, "grad_norm": 0.9408140457925409, "learning_rate": 1.6845107683470453e-05, "loss": 0.8848, "step": 1467 }, { "epoch": 0.28, "grad_norm": 0.8339144979802651, "learning_rate": 1.6840564051003517e-05, "loss": 0.6367, "step": 1468 }, { "epoch": 0.28, "grad_norm": 0.9917799340649641, "learning_rate": 1.6836017762794087e-05, "loss": 0.8972, "step": 1469 }, { "epoch": 0.28, "grad_norm": 1.1653189311973104, "learning_rate": 1.6831468820607192e-05, "loss": 0.6152, "step": 1470 }, { "epoch": 0.28, "grad_norm": 0.9912331947402224, "learning_rate": 1.6826917226208886e-05, "loss": 0.8977, "step": 1471 }, { "epoch": 0.28, "grad_norm": 1.2143759484168963, "learning_rate": 1.6822362981366257e-05, "loss": 0.9819, "step": 1472 }, { "epoch": 0.28, "grad_norm": 1.038897469194519, "learning_rate": 1.6817806087847417e-05, "loss": 0.9636, "step": 1473 }, { "epoch": 0.28, "grad_norm": 0.9988071782303067, "learning_rate": 1.681324654742151e-05, "loss": 0.8704, "step": 1474 }, { "epoch": 0.28, "grad_norm": 1.1978904770280878, "learning_rate": 1.6808684361858706e-05, "loss": 0.896, "step": 1475 }, { "epoch": 0.28, "grad_norm": 0.9604599527380755, "learning_rate": 1.6804119532930202e-05, "loss": 0.9636, "step": 1476 }, { "epoch": 0.28, "grad_norm": 0.7687133476244354, "learning_rate": 1.6799552062408225e-05, "loss": 0.5399, "step": 1477 }, { "epoch": 0.28, "grad_norm": 1.008725263894511, "learning_rate": 1.6794981952066018e-05, "loss": 0.9297, "step": 1478 }, { "epoch": 0.28, "grad_norm": 1.125164240613512, "learning_rate": 1.6790409203677863e-05, "loss": 0.9138, "step": 1479 }, { "epoch": 0.28, "grad_norm": 1.0924090298995723, "learning_rate": 1.6785833819019052e-05, "loss": 0.9426, "step": 1480 }, { "epoch": 0.28, "grad_norm": 1.0022553465411534, "learning_rate": 1.678125579986591e-05, "loss": 0.9309, "step": 1481 }, { "epoch": 0.29, "grad_norm": 1.0282951999017895, "learning_rate": 1.677667514799578e-05, "loss": 0.8945, "step": 1482 }, { "epoch": 0.29, "grad_norm": 1.0330600739775542, "learning_rate": 1.6772091865187032e-05, "loss": 0.9307, "step": 1483 }, { "epoch": 0.29, "grad_norm": 1.0331993421826042, "learning_rate": 1.676750595321905e-05, "loss": 0.9727, "step": 1484 }, { "epoch": 0.29, "grad_norm": 0.7387500618236797, "learning_rate": 1.6762917413872246e-05, "loss": 0.5961, "step": 1485 }, { "epoch": 0.29, "grad_norm": 1.0184784489917296, "learning_rate": 1.675832624892805e-05, "loss": 0.9017, "step": 1486 }, { "epoch": 0.29, "grad_norm": 1.0548216447469114, "learning_rate": 1.6753732460168907e-05, "loss": 0.9299, "step": 1487 }, { "epoch": 0.29, "grad_norm": 0.9960204413028485, "learning_rate": 1.674913604937828e-05, "loss": 0.947, "step": 1488 }, { "epoch": 0.29, "grad_norm": 1.004491218948973, "learning_rate": 1.6744537018340662e-05, "loss": 0.9146, "step": 1489 }, { "epoch": 0.29, "grad_norm": 1.0098360607070498, "learning_rate": 1.6739935368841555e-05, "loss": 1.0044, "step": 1490 }, { "epoch": 0.29, "grad_norm": 1.0613216079524814, "learning_rate": 1.6735331102667475e-05, "loss": 0.9197, "step": 1491 }, { "epoch": 0.29, "grad_norm": 0.8886827216691624, "learning_rate": 1.6730724221605955e-05, "loss": 0.6707, "step": 1492 }, { "epoch": 0.29, "grad_norm": 1.0557007447996956, "learning_rate": 1.6726114727445547e-05, "loss": 0.8821, "step": 1493 }, { "epoch": 0.29, "grad_norm": 1.1103376991174818, "learning_rate": 1.6721502621975813e-05, "loss": 0.9172, "step": 1494 }, { "epoch": 0.29, "grad_norm": 1.0149653052874057, "learning_rate": 1.6716887906987332e-05, "loss": 0.9526, "step": 1495 }, { "epoch": 0.29, "grad_norm": 0.9977178766201414, "learning_rate": 1.6712270584271703e-05, "loss": 0.905, "step": 1496 }, { "epoch": 0.29, "grad_norm": 1.1527705469017995, "learning_rate": 1.670765065562152e-05, "loss": 0.9487, "step": 1497 }, { "epoch": 0.29, "grad_norm": 1.022555079584802, "learning_rate": 1.67030281228304e-05, "loss": 0.9202, "step": 1498 }, { "epoch": 0.29, "grad_norm": 1.0370171170498759, "learning_rate": 1.6698402987692968e-05, "loss": 0.8777, "step": 1499 }, { "epoch": 0.29, "grad_norm": 0.9102588211279254, "learning_rate": 1.6693775252004866e-05, "loss": 0.8755, "step": 1500 }, { "epoch": 0.29, "grad_norm": 1.0257541246070787, "learning_rate": 1.668914491756274e-05, "loss": 0.9551, "step": 1501 }, { "epoch": 0.29, "grad_norm": 1.1344723615935768, "learning_rate": 1.668451198616424e-05, "loss": 0.9131, "step": 1502 }, { "epoch": 0.29, "grad_norm": 1.0619293599695854, "learning_rate": 1.6679876459608033e-05, "loss": 0.9183, "step": 1503 }, { "epoch": 0.29, "grad_norm": 1.015676062244808, "learning_rate": 1.667523833969379e-05, "loss": 0.9307, "step": 1504 }, { "epoch": 0.29, "grad_norm": 1.1076039910055853, "learning_rate": 1.667059762822219e-05, "loss": 0.8958, "step": 1505 }, { "epoch": 0.29, "grad_norm": 1.0058215942046496, "learning_rate": 1.666595432699491e-05, "loss": 0.8953, "step": 1506 }, { "epoch": 0.29, "grad_norm": 1.2755086997129579, "learning_rate": 1.6661308437814652e-05, "loss": 0.9624, "step": 1507 }, { "epoch": 0.29, "grad_norm": 1.00892637752455, "learning_rate": 1.6656659962485097e-05, "loss": 0.9043, "step": 1508 }, { "epoch": 0.29, "grad_norm": 1.0604852487027283, "learning_rate": 1.6652008902810952e-05, "loss": 0.9348, "step": 1509 }, { "epoch": 0.29, "grad_norm": 1.0076166157111748, "learning_rate": 1.6647355260597915e-05, "loss": 0.9387, "step": 1510 }, { "epoch": 0.29, "grad_norm": 0.9639950765729033, "learning_rate": 1.664269903765269e-05, "loss": 0.8516, "step": 1511 }, { "epoch": 0.29, "grad_norm": 0.8980750021236185, "learning_rate": 1.6638040235782983e-05, "loss": 0.6356, "step": 1512 }, { "epoch": 0.29, "grad_norm": 1.034344821845171, "learning_rate": 1.6633378856797505e-05, "loss": 0.9248, "step": 1513 }, { "epoch": 0.29, "grad_norm": 1.092283714653295, "learning_rate": 1.662871490250596e-05, "loss": 0.9004, "step": 1514 }, { "epoch": 0.29, "grad_norm": 1.103637687295771, "learning_rate": 1.662404837471905e-05, "loss": 0.9854, "step": 1515 }, { "epoch": 0.29, "grad_norm": 1.1184713611868868, "learning_rate": 1.66193792752485e-05, "loss": 0.9434, "step": 1516 }, { "epoch": 0.29, "grad_norm": 1.1011546775872845, "learning_rate": 1.6614707605906995e-05, "loss": 0.8535, "step": 1517 }, { "epoch": 0.29, "grad_norm": 0.884189325656777, "learning_rate": 1.661003336850825e-05, "loss": 0.9277, "step": 1518 }, { "epoch": 0.29, "grad_norm": 0.8871593488771606, "learning_rate": 1.660535656486696e-05, "loss": 0.8818, "step": 1519 }, { "epoch": 0.29, "grad_norm": 0.8105735204235135, "learning_rate": 1.660067719679882e-05, "loss": 0.5931, "step": 1520 }, { "epoch": 0.29, "grad_norm": 1.0864156674332213, "learning_rate": 1.6595995266120528e-05, "loss": 0.8948, "step": 1521 }, { "epoch": 0.29, "grad_norm": 0.9980962377395344, "learning_rate": 1.6591310774649766e-05, "loss": 0.9128, "step": 1522 }, { "epoch": 0.29, "grad_norm": 0.8274033678847781, "learning_rate": 1.6586623724205216e-05, "loss": 0.6791, "step": 1523 }, { "epoch": 0.29, "grad_norm": 0.9447852767390819, "learning_rate": 1.6581934116606554e-05, "loss": 0.9138, "step": 1524 }, { "epoch": 0.29, "grad_norm": 1.0325767237598273, "learning_rate": 1.657724195367444e-05, "loss": 0.9626, "step": 1525 }, { "epoch": 0.29, "grad_norm": 1.056297944306197, "learning_rate": 1.657254723723054e-05, "loss": 0.8743, "step": 1526 }, { "epoch": 0.29, "grad_norm": 1.0154983635272528, "learning_rate": 1.6567849969097505e-05, "loss": 0.9377, "step": 1527 }, { "epoch": 0.29, "grad_norm": 1.1192572416009794, "learning_rate": 1.6563150151098973e-05, "loss": 0.9149, "step": 1528 }, { "epoch": 0.29, "grad_norm": 1.1102057655236042, "learning_rate": 1.6558447785059577e-05, "loss": 0.8987, "step": 1529 }, { "epoch": 0.29, "grad_norm": 1.2892841739138157, "learning_rate": 1.655374287280494e-05, "loss": 0.9392, "step": 1530 }, { "epoch": 0.29, "grad_norm": 1.0499030053874057, "learning_rate": 1.6549035416161662e-05, "loss": 0.9399, "step": 1531 }, { "epoch": 0.29, "grad_norm": 1.0258189655460854, "learning_rate": 1.654432541695735e-05, "loss": 0.9075, "step": 1532 }, { "epoch": 0.29, "grad_norm": 1.048370647044503, "learning_rate": 1.653961287702058e-05, "loss": 0.9055, "step": 1533 }, { "epoch": 0.3, "grad_norm": 0.8946070593408858, "learning_rate": 1.653489779818093e-05, "loss": 0.8945, "step": 1534 }, { "epoch": 0.3, "grad_norm": 1.1252105620562098, "learning_rate": 1.6530180182268946e-05, "loss": 0.9648, "step": 1535 }, { "epoch": 0.3, "grad_norm": 1.1039363485263725, "learning_rate": 1.652546003111618e-05, "loss": 0.96, "step": 1536 }, { "epoch": 0.3, "grad_norm": 1.0778821425684098, "learning_rate": 1.652073734655515e-05, "loss": 0.8672, "step": 1537 }, { "epoch": 0.3, "grad_norm": 1.0719955962896663, "learning_rate": 1.6516012130419366e-05, "loss": 0.9353, "step": 1538 }, { "epoch": 0.3, "grad_norm": 1.1717886773740889, "learning_rate": 1.6511284384543317e-05, "loss": 1.0027, "step": 1539 }, { "epoch": 0.3, "grad_norm": 0.9433681843525986, "learning_rate": 1.6506554110762483e-05, "loss": 0.8591, "step": 1540 }, { "epoch": 0.3, "grad_norm": 0.9999716929810235, "learning_rate": 1.650182131091332e-05, "loss": 0.8472, "step": 1541 }, { "epoch": 0.3, "grad_norm": 1.1413957327262536, "learning_rate": 1.6497085986833252e-05, "loss": 0.9475, "step": 1542 }, { "epoch": 0.3, "grad_norm": 0.9717585390291941, "learning_rate": 1.6492348140360704e-05, "loss": 0.8857, "step": 1543 }, { "epoch": 0.3, "grad_norm": 1.1039350148394562, "learning_rate": 1.6487607773335074e-05, "loss": 0.897, "step": 1544 }, { "epoch": 0.3, "grad_norm": 0.9755285615392351, "learning_rate": 1.648286488759673e-05, "loss": 0.8884, "step": 1545 }, { "epoch": 0.3, "grad_norm": 1.12523009137723, "learning_rate": 1.6478119484987026e-05, "loss": 0.8745, "step": 1546 }, { "epoch": 0.3, "grad_norm": 0.8983270105547742, "learning_rate": 1.6473371567348287e-05, "loss": 0.6288, "step": 1547 }, { "epoch": 0.3, "grad_norm": 1.048810883243568, "learning_rate": 1.6468621136523823e-05, "loss": 0.915, "step": 1548 }, { "epoch": 0.3, "grad_norm": 1.1215414915742248, "learning_rate": 1.646386819435791e-05, "loss": 0.9053, "step": 1549 }, { "epoch": 0.3, "grad_norm": 1.0971399251887635, "learning_rate": 1.6459112742695807e-05, "loss": 0.8745, "step": 1550 }, { "epoch": 0.3, "grad_norm": 1.0590321782796752, "learning_rate": 1.6454354783383748e-05, "loss": 0.8776, "step": 1551 }, { "epoch": 0.3, "grad_norm": 0.8692884097201804, "learning_rate": 1.644959431826893e-05, "loss": 0.5951, "step": 1552 }, { "epoch": 0.3, "grad_norm": 0.9341591668821103, "learning_rate": 1.6444831349199528e-05, "loss": 0.8875, "step": 1553 }, { "epoch": 0.3, "grad_norm": 1.272762819023481, "learning_rate": 1.6440065878024697e-05, "loss": 0.9114, "step": 1554 }, { "epoch": 0.3, "grad_norm": 1.0859983340554595, "learning_rate": 1.6435297906594553e-05, "loss": 0.9192, "step": 1555 }, { "epoch": 0.3, "grad_norm": 1.1574194746341784, "learning_rate": 1.643052743676019e-05, "loss": 0.9004, "step": 1556 }, { "epoch": 0.3, "grad_norm": 1.1921242971450092, "learning_rate": 1.6425754470373667e-05, "loss": 0.8955, "step": 1557 }, { "epoch": 0.3, "grad_norm": 0.9295221798328904, "learning_rate": 1.642097900928801e-05, "loss": 0.6062, "step": 1558 }, { "epoch": 0.3, "grad_norm": 0.8126228267189964, "learning_rate": 1.6416201055357225e-05, "loss": 0.6197, "step": 1559 }, { "epoch": 0.3, "grad_norm": 0.8213812275132546, "learning_rate": 1.641142061043627e-05, "loss": 0.6444, "step": 1560 }, { "epoch": 0.3, "grad_norm": 0.8194369239941762, "learning_rate": 1.640663767638108e-05, "loss": 0.608, "step": 1561 }, { "epoch": 0.3, "grad_norm": 1.0851432508056673, "learning_rate": 1.6401852255048564e-05, "loss": 0.9167, "step": 1562 }, { "epoch": 0.3, "grad_norm": 0.7816110398101971, "learning_rate": 1.6397064348296578e-05, "loss": 0.6175, "step": 1563 }, { "epoch": 0.3, "grad_norm": 0.94704718381584, "learning_rate": 1.6392273957983955e-05, "loss": 0.6656, "step": 1564 }, { "epoch": 0.3, "grad_norm": 1.193110014621283, "learning_rate": 1.638748108597049e-05, "loss": 0.9299, "step": 1565 }, { "epoch": 0.3, "grad_norm": 1.0443609929365385, "learning_rate": 1.6382685734116934e-05, "loss": 0.8907, "step": 1566 }, { "epoch": 0.3, "grad_norm": 1.0344743362927358, "learning_rate": 1.6377887904285018e-05, "loss": 0.9436, "step": 1567 }, { "epoch": 0.3, "grad_norm": 1.0593169390629258, "learning_rate": 1.637308759833742e-05, "loss": 0.896, "step": 1568 }, { "epoch": 0.3, "grad_norm": 0.9410754584464259, "learning_rate": 1.6368284818137787e-05, "loss": 0.929, "step": 1569 }, { "epoch": 0.3, "grad_norm": 0.948201804769508, "learning_rate": 1.636347956555072e-05, "loss": 0.8923, "step": 1570 }, { "epoch": 0.3, "grad_norm": 0.8433778455897244, "learning_rate": 1.635867184244178e-05, "loss": 0.6384, "step": 1571 }, { "epoch": 0.3, "grad_norm": 1.092189154500895, "learning_rate": 1.63538616506775e-05, "loss": 0.9553, "step": 1572 }, { "epoch": 0.3, "grad_norm": 1.0343961626467373, "learning_rate": 1.6349048992125358e-05, "loss": 0.9438, "step": 1573 }, { "epoch": 0.3, "grad_norm": 1.1598619234617205, "learning_rate": 1.634423386865379e-05, "loss": 0.9172, "step": 1574 }, { "epoch": 0.3, "grad_norm": 1.0766794598723828, "learning_rate": 1.6339416282132196e-05, "loss": 0.9395, "step": 1575 }, { "epoch": 0.3, "grad_norm": 1.0365940466454986, "learning_rate": 1.633459623443093e-05, "loss": 0.9319, "step": 1576 }, { "epoch": 0.3, "grad_norm": 0.9005058730959263, "learning_rate": 1.6329773727421297e-05, "loss": 0.67, "step": 1577 }, { "epoch": 0.3, "grad_norm": 0.9951600214356209, "learning_rate": 1.6324948762975567e-05, "loss": 0.9226, "step": 1578 }, { "epoch": 0.3, "grad_norm": 1.1124803858137005, "learning_rate": 1.632012134296695e-05, "loss": 0.8923, "step": 1579 }, { "epoch": 0.3, "grad_norm": 1.1493193788754978, "learning_rate": 1.6315291469269617e-05, "loss": 0.9585, "step": 1580 }, { "epoch": 0.3, "grad_norm": 0.9520553654640466, "learning_rate": 1.63104591437587e-05, "loss": 0.8989, "step": 1581 }, { "epoch": 0.3, "grad_norm": 1.0664066181077425, "learning_rate": 1.6305624368310265e-05, "loss": 0.865, "step": 1582 }, { "epoch": 0.3, "grad_norm": 1.0988469733144919, "learning_rate": 1.630078714480134e-05, "loss": 0.9214, "step": 1583 }, { "epoch": 0.3, "grad_norm": 1.0763453548856523, "learning_rate": 1.6295947475109904e-05, "loss": 0.9285, "step": 1584 }, { "epoch": 0.3, "grad_norm": 1.0509997314883144, "learning_rate": 1.629110536111488e-05, "loss": 0.9077, "step": 1585 }, { "epoch": 0.31, "grad_norm": 0.9843357383234393, "learning_rate": 1.628626080469615e-05, "loss": 0.9211, "step": 1586 }, { "epoch": 0.31, "grad_norm": 1.0245380093664034, "learning_rate": 1.628141380773453e-05, "loss": 0.9075, "step": 1587 }, { "epoch": 0.31, "grad_norm": 0.9689892712031255, "learning_rate": 1.6276564372111797e-05, "loss": 0.9202, "step": 1588 }, { "epoch": 0.31, "grad_norm": 1.0932919961059904, "learning_rate": 1.6271712499710663e-05, "loss": 0.9844, "step": 1589 }, { "epoch": 0.31, "grad_norm": 0.9989018147139028, "learning_rate": 1.62668581924148e-05, "loss": 0.9365, "step": 1590 }, { "epoch": 0.31, "grad_norm": 1.0129578900860199, "learning_rate": 1.6262001452108807e-05, "loss": 0.8608, "step": 1591 }, { "epoch": 0.31, "grad_norm": 0.9777379082607525, "learning_rate": 1.6257142280678247e-05, "loss": 0.8799, "step": 1592 }, { "epoch": 0.31, "grad_norm": 1.1108372981702541, "learning_rate": 1.6252280680009613e-05, "loss": 0.8806, "step": 1593 }, { "epoch": 0.31, "grad_norm": 1.0408121437078615, "learning_rate": 1.6247416651990343e-05, "loss": 0.9193, "step": 1594 }, { "epoch": 0.31, "grad_norm": 0.9978387465394105, "learning_rate": 1.624255019850883e-05, "loss": 0.8735, "step": 1595 }, { "epoch": 0.31, "grad_norm": 0.9706630892815693, "learning_rate": 1.6237681321454387e-05, "loss": 0.9443, "step": 1596 }, { "epoch": 0.31, "grad_norm": 1.0017454367096488, "learning_rate": 1.623281002271729e-05, "loss": 0.8906, "step": 1597 }, { "epoch": 0.31, "grad_norm": 1.1249201712332824, "learning_rate": 1.6227936304188738e-05, "loss": 0.8833, "step": 1598 }, { "epoch": 0.31, "grad_norm": 1.0679166572175205, "learning_rate": 1.622306016776088e-05, "loss": 0.9214, "step": 1599 }, { "epoch": 0.31, "grad_norm": 0.9077225708388919, "learning_rate": 1.6218181615326795e-05, "loss": 0.9104, "step": 1600 }, { "epoch": 0.31, "grad_norm": 1.0034826315860714, "learning_rate": 1.6213300648780515e-05, "loss": 0.9319, "step": 1601 }, { "epoch": 0.31, "grad_norm": 0.9102828180581313, "learning_rate": 1.620841727001699e-05, "loss": 0.845, "step": 1602 }, { "epoch": 0.31, "grad_norm": 1.0783471128335476, "learning_rate": 1.6203531480932114e-05, "loss": 0.8645, "step": 1603 }, { "epoch": 0.31, "grad_norm": 0.9827037883393703, "learning_rate": 1.619864328342273e-05, "loss": 0.8977, "step": 1604 }, { "epoch": 0.31, "grad_norm": 0.9325367235004498, "learning_rate": 1.6193752679386593e-05, "loss": 0.8894, "step": 1605 }, { "epoch": 0.31, "grad_norm": 0.9989905382241309, "learning_rate": 1.6188859670722414e-05, "loss": 0.8643, "step": 1606 }, { "epoch": 0.31, "grad_norm": 1.0732925043555215, "learning_rate": 1.6183964259329817e-05, "loss": 0.8662, "step": 1607 }, { "epoch": 0.31, "grad_norm": 1.063320059728454, "learning_rate": 1.6179066447109376e-05, "loss": 0.9011, "step": 1608 }, { "epoch": 0.31, "grad_norm": 1.0034300131666616, "learning_rate": 1.6174166235962588e-05, "loss": 0.8315, "step": 1609 }, { "epoch": 0.31, "grad_norm": 1.0516985818571698, "learning_rate": 1.6169263627791886e-05, "loss": 0.9238, "step": 1610 }, { "epoch": 0.31, "grad_norm": 1.2805244732899301, "learning_rate": 1.616435862450063e-05, "loss": 0.9409, "step": 1611 }, { "epoch": 0.31, "grad_norm": 0.7880260293790156, "learning_rate": 1.615945122799311e-05, "loss": 0.6542, "step": 1612 }, { "epoch": 0.31, "grad_norm": 1.0311138336818628, "learning_rate": 1.6154541440174547e-05, "loss": 0.9185, "step": 1613 }, { "epoch": 0.31, "grad_norm": 0.832890766748678, "learning_rate": 1.614962926295109e-05, "loss": 0.6267, "step": 1614 }, { "epoch": 0.31, "grad_norm": 0.6131302978454313, "learning_rate": 1.6144714698229814e-05, "loss": 0.3549, "step": 1615 }, { "epoch": 0.31, "grad_norm": 1.008838469097706, "learning_rate": 1.6139797747918725e-05, "loss": 0.8577, "step": 1616 }, { "epoch": 0.31, "grad_norm": 1.0721305379258712, "learning_rate": 1.613487841392675e-05, "loss": 0.8918, "step": 1617 }, { "epoch": 0.31, "grad_norm": 0.9790239931362291, "learning_rate": 1.612995669816375e-05, "loss": 0.8879, "step": 1618 }, { "epoch": 0.31, "grad_norm": 0.9794751113038243, "learning_rate": 1.6125032602540492e-05, "loss": 0.8633, "step": 1619 }, { "epoch": 0.31, "grad_norm": 1.148937919964361, "learning_rate": 1.6120106128968686e-05, "loss": 0.8125, "step": 1620 }, { "epoch": 0.31, "grad_norm": 1.0297741198637935, "learning_rate": 1.6115177279360965e-05, "loss": 0.9163, "step": 1621 }, { "epoch": 0.31, "grad_norm": 1.0442788482940706, "learning_rate": 1.611024605563087e-05, "loss": 0.8989, "step": 1622 }, { "epoch": 0.31, "grad_norm": 1.7043718675616792, "learning_rate": 1.610531245969287e-05, "loss": 0.845, "step": 1623 }, { "epoch": 0.31, "grad_norm": 1.0493850332764403, "learning_rate": 1.6100376493462368e-05, "loss": 0.9023, "step": 1624 }, { "epoch": 0.31, "grad_norm": 1.1422346870522442, "learning_rate": 1.6095438158855668e-05, "loss": 0.9512, "step": 1625 }, { "epoch": 0.31, "grad_norm": 1.042655197839665, "learning_rate": 1.609049745779e-05, "loss": 0.8877, "step": 1626 }, { "epoch": 0.31, "grad_norm": 1.1305855607315287, "learning_rate": 1.6085554392183517e-05, "loss": 0.8887, "step": 1627 }, { "epoch": 0.31, "grad_norm": 1.1383871193548867, "learning_rate": 1.608060896395529e-05, "loss": 0.8878, "step": 1628 }, { "epoch": 0.31, "grad_norm": 1.0978343049650727, "learning_rate": 1.60756611750253e-05, "loss": 0.8726, "step": 1629 }, { "epoch": 0.31, "grad_norm": 1.13265283709062, "learning_rate": 1.6070711027314446e-05, "loss": 0.9512, "step": 1630 }, { "epoch": 0.31, "grad_norm": 1.0387014852239835, "learning_rate": 1.606575852274456e-05, "loss": 0.9221, "step": 1631 }, { "epoch": 0.31, "grad_norm": 0.9589850359922177, "learning_rate": 1.6060803663238357e-05, "loss": 0.9224, "step": 1632 }, { "epoch": 0.31, "grad_norm": 0.9559456092829398, "learning_rate": 1.6055846450719498e-05, "loss": 0.8867, "step": 1633 }, { "epoch": 0.31, "grad_norm": 1.0455783604444147, "learning_rate": 1.6050886887112535e-05, "loss": 0.8914, "step": 1634 }, { "epoch": 0.31, "grad_norm": 1.11586823045886, "learning_rate": 1.6045924974342945e-05, "loss": 0.9294, "step": 1635 }, { "epoch": 0.31, "grad_norm": 1.1323585406353747, "learning_rate": 1.604096071433711e-05, "loss": 0.8547, "step": 1636 }, { "epoch": 0.31, "grad_norm": 1.0106880684890158, "learning_rate": 1.6035994109022333e-05, "loss": 0.9214, "step": 1637 }, { "epoch": 0.32, "grad_norm": 0.9271017422236922, "learning_rate": 1.6031025160326814e-05, "loss": 0.8748, "step": 1638 }, { "epoch": 0.32, "grad_norm": 1.0976111762967162, "learning_rate": 1.6026053870179678e-05, "loss": 0.9438, "step": 1639 }, { "epoch": 0.32, "grad_norm": 0.9265828339265739, "learning_rate": 1.6021080240510943e-05, "loss": 0.8645, "step": 1640 }, { "epoch": 0.32, "grad_norm": 0.8401223665882961, "learning_rate": 1.601610427325155e-05, "loss": 0.6387, "step": 1641 }, { "epoch": 0.32, "grad_norm": 1.046270326628569, "learning_rate": 1.6011125970333333e-05, "loss": 0.9026, "step": 1642 }, { "epoch": 0.32, "grad_norm": 0.8147513320491091, "learning_rate": 1.600614533368905e-05, "loss": 0.6035, "step": 1643 }, { "epoch": 0.32, "grad_norm": 0.9719766644621617, "learning_rate": 1.6001162365252348e-05, "loss": 0.9106, "step": 1644 }, { "epoch": 0.32, "grad_norm": 0.78936879013338, "learning_rate": 1.5996177066957787e-05, "loss": 0.5654, "step": 1645 }, { "epoch": 0.32, "grad_norm": 0.9936628532088214, "learning_rate": 1.5991189440740838e-05, "loss": 0.8562, "step": 1646 }, { "epoch": 0.32, "grad_norm": 0.9712519400274158, "learning_rate": 1.5986199488537867e-05, "loss": 0.8911, "step": 1647 }, { "epoch": 0.32, "grad_norm": 1.160828548723674, "learning_rate": 1.598120721228614e-05, "loss": 0.9204, "step": 1648 }, { "epoch": 0.32, "grad_norm": 1.0145168898397627, "learning_rate": 1.5976212613923836e-05, "loss": 0.8997, "step": 1649 }, { "epoch": 0.32, "grad_norm": 1.1101215305862215, "learning_rate": 1.5971215695390026e-05, "loss": 0.9363, "step": 1650 }, { "epoch": 0.32, "grad_norm": 0.9269070841740253, "learning_rate": 1.5966216458624692e-05, "loss": 0.9177, "step": 1651 }, { "epoch": 0.32, "grad_norm": 1.0201988546499339, "learning_rate": 1.5961214905568705e-05, "loss": 0.8696, "step": 1652 }, { "epoch": 0.32, "grad_norm": 1.1460710873992788, "learning_rate": 1.595621103816384e-05, "loss": 0.9456, "step": 1653 }, { "epoch": 0.32, "grad_norm": 1.2435345283136683, "learning_rate": 1.5951204858352772e-05, "loss": 0.8489, "step": 1654 }, { "epoch": 0.32, "grad_norm": 0.9672154178060514, "learning_rate": 1.594619636807907e-05, "loss": 0.8134, "step": 1655 }, { "epoch": 0.32, "grad_norm": 1.1971000464324317, "learning_rate": 1.5941185569287206e-05, "loss": 0.9326, "step": 1656 }, { "epoch": 0.32, "grad_norm": 1.1449615404861397, "learning_rate": 1.5936172463922542e-05, "loss": 0.999, "step": 1657 }, { "epoch": 0.32, "grad_norm": 1.080868371877632, "learning_rate": 1.593115705393134e-05, "loss": 0.8757, "step": 1658 }, { "epoch": 0.32, "grad_norm": 0.84959675996009, "learning_rate": 1.5926139341260755e-05, "loss": 0.6494, "step": 1659 }, { "epoch": 0.32, "grad_norm": 0.920939432320891, "learning_rate": 1.5921119327858835e-05, "loss": 0.8816, "step": 1660 }, { "epoch": 0.32, "grad_norm": 0.9847760025892046, "learning_rate": 1.5916097015674518e-05, "loss": 0.9414, "step": 1661 }, { "epoch": 0.32, "grad_norm": 1.0154081092382685, "learning_rate": 1.5911072406657646e-05, "loss": 0.874, "step": 1662 }, { "epoch": 0.32, "grad_norm": 1.091370280013715, "learning_rate": 1.5906045502758943e-05, "loss": 0.9253, "step": 1663 }, { "epoch": 0.32, "grad_norm": 0.979357908106948, "learning_rate": 1.590101630593002e-05, "loss": 0.9214, "step": 1664 }, { "epoch": 0.32, "grad_norm": 1.2173601504979354, "learning_rate": 1.5895984818123392e-05, "loss": 0.9155, "step": 1665 }, { "epoch": 0.32, "grad_norm": 0.7660301779148075, "learning_rate": 1.5890951041292453e-05, "loss": 0.6024, "step": 1666 }, { "epoch": 0.32, "grad_norm": 1.0060510266457174, "learning_rate": 1.588591497739149e-05, "loss": 0.9368, "step": 1667 }, { "epoch": 0.32, "grad_norm": 1.1283902668740489, "learning_rate": 1.5880876628375668e-05, "loss": 0.8862, "step": 1668 }, { "epoch": 0.32, "grad_norm": 1.0870412020000169, "learning_rate": 1.587583599620106e-05, "loss": 0.906, "step": 1669 }, { "epoch": 0.32, "grad_norm": 1.0216829946078283, "learning_rate": 1.5870793082824604e-05, "loss": 0.7885, "step": 1670 }, { "epoch": 0.32, "grad_norm": 1.0947937358840012, "learning_rate": 1.5865747890204138e-05, "loss": 0.9294, "step": 1671 }, { "epoch": 0.32, "grad_norm": 1.1202334849348217, "learning_rate": 1.5860700420298377e-05, "loss": 0.9663, "step": 1672 }, { "epoch": 0.32, "grad_norm": 1.1020657268350749, "learning_rate": 1.5855650675066924e-05, "loss": 0.9297, "step": 1673 }, { "epoch": 0.32, "grad_norm": 1.054026718457405, "learning_rate": 1.5850598656470265e-05, "loss": 0.8462, "step": 1674 }, { "epoch": 0.32, "grad_norm": 0.9238741569109794, "learning_rate": 1.584554436646976e-05, "loss": 0.9001, "step": 1675 }, { "epoch": 0.32, "grad_norm": 0.9826633391728886, "learning_rate": 1.5840487807027665e-05, "loss": 0.938, "step": 1676 }, { "epoch": 0.32, "grad_norm": 0.9106767155275465, "learning_rate": 1.5835428980107113e-05, "loss": 0.8706, "step": 1677 }, { "epoch": 0.32, "grad_norm": 0.9767958543444606, "learning_rate": 1.583036788767211e-05, "loss": 0.9172, "step": 1678 }, { "epoch": 0.32, "grad_norm": 0.8822437042756611, "learning_rate": 1.5825304531687548e-05, "loss": 0.5668, "step": 1679 }, { "epoch": 0.32, "grad_norm": 1.1185885575207015, "learning_rate": 1.5820238914119195e-05, "loss": 0.8972, "step": 1680 }, { "epoch": 0.32, "grad_norm": 1.0559854820946366, "learning_rate": 1.5815171036933697e-05, "loss": 0.938, "step": 1681 }, { "epoch": 0.32, "grad_norm": 0.9434545962037011, "learning_rate": 1.5810100902098582e-05, "loss": 0.8816, "step": 1682 }, { "epoch": 0.32, "grad_norm": 1.0969355624165813, "learning_rate": 1.580502851158225e-05, "loss": 0.9622, "step": 1683 }, { "epoch": 0.32, "grad_norm": 0.7984395230327366, "learning_rate": 1.5799953867353975e-05, "loss": 0.6141, "step": 1684 }, { "epoch": 0.32, "grad_norm": 1.0218978264146497, "learning_rate": 1.579487697138391e-05, "loss": 0.8748, "step": 1685 }, { "epoch": 0.32, "grad_norm": 1.066394692640417, "learning_rate": 1.5789797825643086e-05, "loss": 0.9678, "step": 1686 }, { "epoch": 0.32, "grad_norm": 0.8140412026214588, "learning_rate": 1.5784716432103394e-05, "loss": 0.6036, "step": 1687 }, { "epoch": 0.32, "grad_norm": 1.1635497323139845, "learning_rate": 1.5779632792737608e-05, "loss": 0.635, "step": 1688 }, { "epoch": 0.32, "grad_norm": 1.1705877597424348, "learning_rate": 1.5774546909519376e-05, "loss": 0.8756, "step": 1689 }, { "epoch": 0.33, "grad_norm": 1.0639990249192144, "learning_rate": 1.5769458784423206e-05, "loss": 0.9048, "step": 1690 }, { "epoch": 0.33, "grad_norm": 0.9522201479292676, "learning_rate": 1.5764368419424488e-05, "loss": 0.884, "step": 1691 }, { "epoch": 0.33, "grad_norm": 1.2322582373899167, "learning_rate": 1.575927581649948e-05, "loss": 0.9944, "step": 1692 }, { "epoch": 0.33, "grad_norm": 1.2603614691760696, "learning_rate": 1.5754180977625303e-05, "loss": 0.9194, "step": 1693 }, { "epoch": 0.33, "grad_norm": 1.0506769759172465, "learning_rate": 1.574908390477995e-05, "loss": 0.9313, "step": 1694 }, { "epoch": 0.33, "grad_norm": 0.9957183325611857, "learning_rate": 1.5743984599942273e-05, "loss": 0.9148, "step": 1695 }, { "epoch": 0.33, "grad_norm": 1.0317367112743097, "learning_rate": 1.5738883065092005e-05, "loss": 0.8809, "step": 1696 }, { "epoch": 0.33, "grad_norm": 0.9733655836889558, "learning_rate": 1.5733779302209735e-05, "loss": 0.8984, "step": 1697 }, { "epoch": 0.33, "grad_norm": 1.0538657377867864, "learning_rate": 1.572867331327692e-05, "loss": 0.9338, "step": 1698 }, { "epoch": 0.33, "grad_norm": 1.06728885704793, "learning_rate": 1.5723565100275884e-05, "loss": 0.8718, "step": 1699 }, { "epoch": 0.33, "grad_norm": 1.008629411895014, "learning_rate": 1.5718454665189806e-05, "loss": 0.9045, "step": 1700 }, { "epoch": 0.33, "grad_norm": 0.9647213949004926, "learning_rate": 1.5713342010002733e-05, "loss": 0.8518, "step": 1701 }, { "epoch": 0.33, "grad_norm": 0.929749890696278, "learning_rate": 1.5708227136699578e-05, "loss": 0.9495, "step": 1702 }, { "epoch": 0.33, "grad_norm": 1.045229265642256, "learning_rate": 1.5703110047266105e-05, "loss": 0.9089, "step": 1703 }, { "epoch": 0.33, "grad_norm": 0.9627232011879335, "learning_rate": 1.569799074368895e-05, "loss": 0.8167, "step": 1704 }, { "epoch": 0.33, "grad_norm": 0.9754623551035363, "learning_rate": 1.5692869227955603e-05, "loss": 0.8582, "step": 1705 }, { "epoch": 0.33, "grad_norm": 1.0074040919324798, "learning_rate": 1.5687745502054407e-05, "loss": 0.9993, "step": 1706 }, { "epoch": 0.33, "grad_norm": 1.094808156888644, "learning_rate": 1.5682619567974575e-05, "loss": 0.9065, "step": 1707 }, { "epoch": 0.33, "grad_norm": 0.9175777322842216, "learning_rate": 1.567749142770617e-05, "loss": 0.6218, "step": 1708 }, { "epoch": 0.33, "grad_norm": 1.1047363732269448, "learning_rate": 1.5672361083240106e-05, "loss": 0.8188, "step": 1709 }, { "epoch": 0.33, "grad_norm": 1.028545753423108, "learning_rate": 1.5667228536568167e-05, "loss": 0.8677, "step": 1710 }, { "epoch": 0.33, "grad_norm": 0.9044681670317557, "learning_rate": 1.566209378968298e-05, "loss": 0.8848, "step": 1711 }, { "epoch": 0.33, "grad_norm": 1.1562072173706073, "learning_rate": 1.565695684457803e-05, "loss": 0.9026, "step": 1712 }, { "epoch": 0.33, "grad_norm": 1.1482090854642557, "learning_rate": 1.5651817703247666e-05, "loss": 0.8884, "step": 1713 }, { "epoch": 0.33, "grad_norm": 0.9397274400500268, "learning_rate": 1.5646676367687067e-05, "loss": 0.927, "step": 1714 }, { "epoch": 0.33, "grad_norm": 1.0837249913768923, "learning_rate": 1.564153283989228e-05, "loss": 0.9468, "step": 1715 }, { "epoch": 0.33, "grad_norm": 0.9454329996114432, "learning_rate": 1.5636387121860207e-05, "loss": 0.9436, "step": 1716 }, { "epoch": 0.33, "grad_norm": 0.9590337423992452, "learning_rate": 1.5631239215588578e-05, "loss": 0.9102, "step": 1717 }, { "epoch": 0.33, "grad_norm": 0.985468318659794, "learning_rate": 1.5626089123076004e-05, "loss": 0.9111, "step": 1718 }, { "epoch": 0.33, "grad_norm": 1.0907693338093338, "learning_rate": 1.5620936846321917e-05, "loss": 0.9121, "step": 1719 }, { "epoch": 0.33, "grad_norm": 1.0698445357156778, "learning_rate": 1.561578238732661e-05, "loss": 0.8807, "step": 1720 }, { "epoch": 0.33, "grad_norm": 1.1356535234881744, "learning_rate": 1.561062574809123e-05, "loss": 0.8821, "step": 1721 }, { "epoch": 0.33, "grad_norm": 0.881954362195146, "learning_rate": 1.5605466930617747e-05, "loss": 0.6221, "step": 1722 }, { "epoch": 0.33, "grad_norm": 1.0907804300202757, "learning_rate": 1.5600305936909005e-05, "loss": 0.8738, "step": 1723 }, { "epoch": 0.33, "grad_norm": 1.3234352699399488, "learning_rate": 1.559514276896867e-05, "loss": 0.9219, "step": 1724 }, { "epoch": 0.33, "grad_norm": 1.0329153677870297, "learning_rate": 1.558997742880127e-05, "loss": 0.9165, "step": 1725 }, { "epoch": 0.33, "grad_norm": 1.1412892779239, "learning_rate": 1.5584809918412158e-05, "loss": 0.679, "step": 1726 }, { "epoch": 0.33, "grad_norm": 1.1890413909804143, "learning_rate": 1.557964023980755e-05, "loss": 0.9487, "step": 1727 }, { "epoch": 0.33, "grad_norm": 1.0547250745402625, "learning_rate": 1.5574468394994486e-05, "loss": 0.9341, "step": 1728 }, { "epoch": 0.33, "grad_norm": 1.019254165276923, "learning_rate": 1.5569294385980856e-05, "loss": 0.855, "step": 1729 }, { "epoch": 0.33, "grad_norm": 1.0064752306767426, "learning_rate": 1.556411821477539e-05, "loss": 0.9546, "step": 1730 }, { "epoch": 0.33, "grad_norm": 1.1330265360907572, "learning_rate": 1.5558939883387657e-05, "loss": 0.8728, "step": 1731 }, { "epoch": 0.33, "grad_norm": 1.0946857213374221, "learning_rate": 1.5553759393828058e-05, "loss": 0.9661, "step": 1732 }, { "epoch": 0.33, "grad_norm": 1.0058754361823998, "learning_rate": 1.554857674810784e-05, "loss": 0.9653, "step": 1733 }, { "epoch": 0.33, "grad_norm": 1.1557763009708657, "learning_rate": 1.554339194823909e-05, "loss": 0.9197, "step": 1734 }, { "epoch": 0.33, "grad_norm": 1.063479310330781, "learning_rate": 1.553820499623472e-05, "loss": 0.8811, "step": 1735 }, { "epoch": 0.33, "grad_norm": 1.1211792760800356, "learning_rate": 1.553301589410848e-05, "loss": 0.9404, "step": 1736 }, { "epoch": 0.33, "grad_norm": 0.9975108123787623, "learning_rate": 1.5527824643874968e-05, "loss": 0.9277, "step": 1737 }, { "epoch": 0.33, "grad_norm": 1.0345777735117938, "learning_rate": 1.5522631247549598e-05, "loss": 0.9358, "step": 1738 }, { "epoch": 0.33, "grad_norm": 1.054652365125775, "learning_rate": 1.5517435707148628e-05, "loss": 0.8787, "step": 1739 }, { "epoch": 0.33, "grad_norm": 1.1621498247127238, "learning_rate": 1.5512238024689144e-05, "loss": 0.9529, "step": 1740 }, { "epoch": 0.33, "grad_norm": 1.0512102084203214, "learning_rate": 1.550703820218907e-05, "loss": 0.9365, "step": 1741 }, { "epoch": 0.34, "grad_norm": 1.0557171175714064, "learning_rate": 1.550183624166715e-05, "loss": 0.917, "step": 1742 }, { "epoch": 0.34, "grad_norm": 1.127807459772906, "learning_rate": 1.549663214514297e-05, "loss": 0.9089, "step": 1743 }, { "epoch": 0.34, "grad_norm": 1.0901020181558467, "learning_rate": 1.5491425914636934e-05, "loss": 0.9626, "step": 1744 }, { "epoch": 0.34, "grad_norm": 1.060308634491029, "learning_rate": 1.5486217552170283e-05, "loss": 0.9885, "step": 1745 }, { "epoch": 0.34, "grad_norm": 1.125445631960997, "learning_rate": 1.548100705976508e-05, "loss": 0.9502, "step": 1746 }, { "epoch": 0.34, "grad_norm": 1.0979981971591675, "learning_rate": 1.5475794439444226e-05, "loss": 0.8989, "step": 1747 }, { "epoch": 0.34, "grad_norm": 1.047759186449345, "learning_rate": 1.5470579693231432e-05, "loss": 0.9456, "step": 1748 }, { "epoch": 0.34, "grad_norm": 0.9626668095408127, "learning_rate": 1.5465362823151245e-05, "loss": 0.9382, "step": 1749 }, { "epoch": 0.34, "grad_norm": 0.8401038252326172, "learning_rate": 1.5460143831229026e-05, "loss": 0.5873, "step": 1750 }, { "epoch": 0.34, "grad_norm": 1.057183335975549, "learning_rate": 1.545492271949098e-05, "loss": 0.9771, "step": 1751 }, { "epoch": 0.34, "grad_norm": 1.2111318755273097, "learning_rate": 1.544969948996411e-05, "loss": 0.9172, "step": 1752 }, { "epoch": 0.34, "grad_norm": 0.8279286134289475, "learning_rate": 1.544447414467626e-05, "loss": 0.5846, "step": 1753 }, { "epoch": 0.34, "grad_norm": 1.0495153345510915, "learning_rate": 1.5439246685656093e-05, "loss": 0.8833, "step": 1754 }, { "epoch": 0.34, "grad_norm": 1.11551417045192, "learning_rate": 1.5434017114933082e-05, "loss": 0.9463, "step": 1755 }, { "epoch": 0.34, "grad_norm": 1.018317088360149, "learning_rate": 1.5428785434537527e-05, "loss": 0.9026, "step": 1756 }, { "epoch": 0.34, "grad_norm": 0.9341910638102552, "learning_rate": 1.542355164650055e-05, "loss": 0.8774, "step": 1757 }, { "epoch": 0.34, "grad_norm": 0.9998058362493308, "learning_rate": 1.541831575285408e-05, "loss": 0.8605, "step": 1758 }, { "epoch": 0.34, "grad_norm": 1.145470233822807, "learning_rate": 1.541307775563088e-05, "loss": 0.9443, "step": 1759 }, { "epoch": 0.34, "grad_norm": 0.9825188425871363, "learning_rate": 1.540783765686452e-05, "loss": 0.9109, "step": 1760 }, { "epoch": 0.34, "grad_norm": 1.073791878155459, "learning_rate": 1.540259545858938e-05, "loss": 0.9258, "step": 1761 }, { "epoch": 0.34, "grad_norm": 0.8184154271945555, "learning_rate": 1.539735116284067e-05, "loss": 0.6127, "step": 1762 }, { "epoch": 0.34, "grad_norm": 1.0849517413924752, "learning_rate": 1.53921047716544e-05, "loss": 0.9148, "step": 1763 }, { "epoch": 0.34, "grad_norm": 0.9676778002194423, "learning_rate": 1.53868562870674e-05, "loss": 0.9526, "step": 1764 }, { "epoch": 0.34, "grad_norm": 1.09321967129694, "learning_rate": 1.5381605711117318e-05, "loss": 0.8752, "step": 1765 }, { "epoch": 0.34, "grad_norm": 0.9736584922575884, "learning_rate": 1.5376353045842604e-05, "loss": 0.8799, "step": 1766 }, { "epoch": 0.34, "grad_norm": 1.0251482897454374, "learning_rate": 1.5371098293282526e-05, "loss": 0.8781, "step": 1767 }, { "epoch": 0.34, "grad_norm": 1.1064482332815624, "learning_rate": 1.5365841455477158e-05, "loss": 0.98, "step": 1768 }, { "epoch": 0.34, "grad_norm": 0.9234557260632487, "learning_rate": 1.5360582534467382e-05, "loss": 0.9509, "step": 1769 }, { "epoch": 0.34, "grad_norm": 1.036790605495116, "learning_rate": 1.5355321532294897e-05, "loss": 0.8984, "step": 1770 }, { "epoch": 0.34, "grad_norm": 1.0753894967503834, "learning_rate": 1.5350058451002204e-05, "loss": 0.86, "step": 1771 }, { "epoch": 0.34, "grad_norm": 0.9389378393270349, "learning_rate": 1.5344793292632614e-05, "loss": 0.8972, "step": 1772 }, { "epoch": 0.34, "grad_norm": 0.8931687502620176, "learning_rate": 1.533952605923024e-05, "loss": 0.8831, "step": 1773 }, { "epoch": 0.34, "grad_norm": 0.896958254328376, "learning_rate": 1.5334256752840007e-05, "loss": 0.8767, "step": 1774 }, { "epoch": 0.34, "grad_norm": 0.9989615998748822, "learning_rate": 1.532898537550764e-05, "loss": 0.9124, "step": 1775 }, { "epoch": 0.34, "grad_norm": 0.917826383031186, "learning_rate": 1.532371192927966e-05, "loss": 0.8811, "step": 1776 }, { "epoch": 0.34, "grad_norm": 1.1809749225588289, "learning_rate": 1.5318436416203412e-05, "loss": 0.9778, "step": 1777 }, { "epoch": 0.34, "grad_norm": 0.9642065989595744, "learning_rate": 1.531315883832703e-05, "loss": 0.8391, "step": 1778 }, { "epoch": 0.34, "grad_norm": 1.178809411123898, "learning_rate": 1.530787919769945e-05, "loss": 0.9077, "step": 1779 }, { "epoch": 0.34, "grad_norm": 0.9400608913226085, "learning_rate": 1.5302597496370408e-05, "loss": 0.8733, "step": 1780 }, { "epoch": 0.34, "grad_norm": 1.052602088610561, "learning_rate": 1.5297313736390447e-05, "loss": 0.9307, "step": 1781 }, { "epoch": 0.34, "grad_norm": 1.0754625024609565, "learning_rate": 1.5292027919810898e-05, "loss": 0.9138, "step": 1782 }, { "epoch": 0.34, "grad_norm": 1.1084963483249741, "learning_rate": 1.52867400486839e-05, "loss": 0.9636, "step": 1783 }, { "epoch": 0.34, "grad_norm": 1.0736283393166055, "learning_rate": 1.528145012506239e-05, "loss": 0.9111, "step": 1784 }, { "epoch": 0.34, "grad_norm": 1.0558957472932016, "learning_rate": 1.5276158151000096e-05, "loss": 0.9219, "step": 1785 }, { "epoch": 0.34, "grad_norm": 1.1705894939557488, "learning_rate": 1.5270864128551542e-05, "loss": 0.9128, "step": 1786 }, { "epoch": 0.34, "grad_norm": 0.9156878356134779, "learning_rate": 1.5265568059772053e-05, "loss": 0.8918, "step": 1787 }, { "epoch": 0.34, "grad_norm": 0.9766074947482015, "learning_rate": 1.5260269946717746e-05, "loss": 0.8887, "step": 1788 }, { "epoch": 0.34, "grad_norm": 0.9287884901209598, "learning_rate": 1.5254969791445526e-05, "loss": 0.8591, "step": 1789 }, { "epoch": 0.34, "grad_norm": 1.0383618164055324, "learning_rate": 1.5249667596013102e-05, "loss": 0.9805, "step": 1790 }, { "epoch": 0.34, "grad_norm": 1.0373179889089015, "learning_rate": 1.5244363362478967e-05, "loss": 0.8577, "step": 1791 }, { "epoch": 0.34, "grad_norm": 0.9710125432409443, "learning_rate": 1.5239057092902404e-05, "loss": 0.9221, "step": 1792 }, { "epoch": 0.34, "grad_norm": 1.1144682733934905, "learning_rate": 1.523374878934349e-05, "loss": 0.9136, "step": 1793 }, { "epoch": 0.35, "grad_norm": 0.8067478877558717, "learning_rate": 1.5228438453863095e-05, "loss": 0.6259, "step": 1794 }, { "epoch": 0.35, "grad_norm": 1.0710158488699615, "learning_rate": 1.522312608852287e-05, "loss": 0.9695, "step": 1795 }, { "epoch": 0.35, "grad_norm": 1.0903874719296334, "learning_rate": 1.5217811695385263e-05, "loss": 0.9102, "step": 1796 }, { "epoch": 0.35, "grad_norm": 1.0864704015762707, "learning_rate": 1.52124952765135e-05, "loss": 0.9521, "step": 1797 }, { "epoch": 0.35, "grad_norm": 1.0278944986438847, "learning_rate": 1.5207176833971598e-05, "loss": 0.9561, "step": 1798 }, { "epoch": 0.35, "grad_norm": 1.0732831092405468, "learning_rate": 1.520185636982436e-05, "loss": 0.9402, "step": 1799 }, { "epoch": 0.35, "grad_norm": 1.050040107323647, "learning_rate": 1.5196533886137376e-05, "loss": 0.9202, "step": 1800 }, { "epoch": 0.35, "grad_norm": 0.9352768400536485, "learning_rate": 1.5191209384977014e-05, "loss": 0.907, "step": 1801 }, { "epoch": 0.35, "grad_norm": 0.8272766690294262, "learning_rate": 1.5185882868410431e-05, "loss": 0.6175, "step": 1802 }, { "epoch": 0.35, "grad_norm": 0.782017629469787, "learning_rate": 1.5180554338505564e-05, "loss": 0.6407, "step": 1803 }, { "epoch": 0.35, "grad_norm": 0.8235970749789734, "learning_rate": 1.517522379733113e-05, "loss": 0.6569, "step": 1804 }, { "epoch": 0.35, "grad_norm": 0.9716208435336781, "learning_rate": 1.5169891246956629e-05, "loss": 0.8669, "step": 1805 }, { "epoch": 0.35, "grad_norm": 1.1166392831726584, "learning_rate": 1.5164556689452346e-05, "loss": 0.8958, "step": 1806 }, { "epoch": 0.35, "grad_norm": 0.9789047200479447, "learning_rate": 1.5159220126889329e-05, "loss": 0.8884, "step": 1807 }, { "epoch": 0.35, "grad_norm": 0.8577561841444532, "learning_rate": 1.5153881561339426e-05, "loss": 0.6469, "step": 1808 }, { "epoch": 0.35, "grad_norm": 1.0265290806830523, "learning_rate": 1.5148540994875242e-05, "loss": 0.9126, "step": 1809 }, { "epoch": 0.35, "grad_norm": 0.9512446423891081, "learning_rate": 1.5143198429570181e-05, "loss": 0.8518, "step": 1810 }, { "epoch": 0.35, "grad_norm": 1.14973211000263, "learning_rate": 1.5137853867498403e-05, "loss": 0.8914, "step": 1811 }, { "epoch": 0.35, "grad_norm": 1.0693943808971451, "learning_rate": 1.5132507310734847e-05, "loss": 0.9485, "step": 1812 }, { "epoch": 0.35, "grad_norm": 1.0051538805705382, "learning_rate": 1.5127158761355241e-05, "loss": 0.8821, "step": 1813 }, { "epoch": 0.35, "grad_norm": 1.0164619657082743, "learning_rate": 1.512180822143607e-05, "loss": 0.9324, "step": 1814 }, { "epoch": 0.35, "grad_norm": 1.163926027365897, "learning_rate": 1.5116455693054594e-05, "loss": 0.9336, "step": 1815 }, { "epoch": 0.35, "grad_norm": 1.2135849699049275, "learning_rate": 1.5111101178288858e-05, "loss": 0.926, "step": 1816 }, { "epoch": 0.35, "grad_norm": 0.9503108801646823, "learning_rate": 1.510574467921766e-05, "loss": 0.9614, "step": 1817 }, { "epoch": 0.35, "grad_norm": 1.0382768213475086, "learning_rate": 1.5100386197920585e-05, "loss": 0.8689, "step": 1818 }, { "epoch": 0.35, "grad_norm": 0.9844490257123647, "learning_rate": 1.5095025736477977e-05, "loss": 0.8745, "step": 1819 }, { "epoch": 0.35, "grad_norm": 1.0922350339085884, "learning_rate": 1.5089663296970952e-05, "loss": 0.8724, "step": 1820 }, { "epoch": 0.35, "grad_norm": 1.1505902696760084, "learning_rate": 1.5084298881481388e-05, "loss": 0.9656, "step": 1821 }, { "epoch": 0.35, "grad_norm": 1.0561191632547564, "learning_rate": 1.5078932492091942e-05, "loss": 0.9214, "step": 1822 }, { "epoch": 0.35, "grad_norm": 1.0469553002787917, "learning_rate": 1.5073564130886032e-05, "loss": 0.8633, "step": 1823 }, { "epoch": 0.35, "grad_norm": 0.9672572525694384, "learning_rate": 1.506819379994784e-05, "loss": 0.8677, "step": 1824 }, { "epoch": 0.35, "grad_norm": 1.007211764193451, "learning_rate": 1.5062821501362308e-05, "loss": 0.9231, "step": 1825 }, { "epoch": 0.35, "grad_norm": 1.086479225558625, "learning_rate": 1.5057447237215152e-05, "loss": 0.9705, "step": 1826 }, { "epoch": 0.35, "grad_norm": 1.104964359417186, "learning_rate": 1.5052071009592846e-05, "loss": 0.9185, "step": 1827 }, { "epoch": 0.35, "grad_norm": 1.0205449080455569, "learning_rate": 1.5046692820582625e-05, "loss": 0.9451, "step": 1828 }, { "epoch": 0.35, "grad_norm": 1.1265249397508292, "learning_rate": 1.504131267227249e-05, "loss": 0.8552, "step": 1829 }, { "epoch": 0.35, "grad_norm": 1.0800521297327281, "learning_rate": 1.5035930566751198e-05, "loss": 0.8811, "step": 1830 }, { "epoch": 0.35, "grad_norm": 1.0204895214102552, "learning_rate": 1.5030546506108268e-05, "loss": 0.8909, "step": 1831 }, { "epoch": 0.35, "grad_norm": 0.9653910476317132, "learning_rate": 1.5025160492433976e-05, "loss": 0.8953, "step": 1832 }, { "epoch": 0.35, "grad_norm": 1.069478697152682, "learning_rate": 1.501977252781936e-05, "loss": 0.9355, "step": 1833 }, { "epoch": 0.35, "grad_norm": 0.9767677735116532, "learning_rate": 1.5014382614356213e-05, "loss": 0.9006, "step": 1834 }, { "epoch": 0.35, "grad_norm": 1.076826867455158, "learning_rate": 1.5008990754137088e-05, "loss": 0.9258, "step": 1835 }, { "epoch": 0.35, "grad_norm": 0.9785222912987708, "learning_rate": 1.5003596949255284e-05, "loss": 0.8494, "step": 1836 }, { "epoch": 0.35, "grad_norm": 1.087153108461934, "learning_rate": 1.4998201201804867e-05, "loss": 0.8945, "step": 1837 }, { "epoch": 0.35, "grad_norm": 1.0909414983931267, "learning_rate": 1.499280351388065e-05, "loss": 0.9612, "step": 1838 }, { "epoch": 0.35, "grad_norm": 1.0290382476999687, "learning_rate": 1.49874038875782e-05, "loss": 0.9448, "step": 1839 }, { "epoch": 0.35, "grad_norm": 0.8062171326589662, "learning_rate": 1.498200232499384e-05, "loss": 0.6014, "step": 1840 }, { "epoch": 0.35, "grad_norm": 0.9897915656094181, "learning_rate": 1.4976598828224643e-05, "loss": 0.8838, "step": 1841 }, { "epoch": 0.35, "grad_norm": 0.6927049227889912, "learning_rate": 1.497119339936843e-05, "loss": 0.3602, "step": 1842 }, { "epoch": 0.35, "grad_norm": 0.9025692713413531, "learning_rate": 1.4965786040523779e-05, "loss": 0.8938, "step": 1843 }, { "epoch": 0.35, "grad_norm": 0.8124878715105082, "learning_rate": 1.496037675379001e-05, "loss": 0.632, "step": 1844 }, { "epoch": 0.35, "grad_norm": 1.1292218652734107, "learning_rate": 1.4954965541267192e-05, "loss": 0.9434, "step": 1845 }, { "epoch": 0.36, "grad_norm": 0.9336490714469482, "learning_rate": 1.494955240505615e-05, "loss": 0.9324, "step": 1846 }, { "epoch": 0.36, "grad_norm": 0.9886165686605326, "learning_rate": 1.494413734725844e-05, "loss": 0.8792, "step": 1847 }, { "epoch": 0.36, "grad_norm": 0.9305813669818968, "learning_rate": 1.4938720369976385e-05, "loss": 0.9146, "step": 1848 }, { "epoch": 0.36, "grad_norm": 1.0266413183061527, "learning_rate": 1.4933301475313036e-05, "loss": 0.9172, "step": 1849 }, { "epoch": 0.36, "grad_norm": 1.14388357497874, "learning_rate": 1.4927880665372197e-05, "loss": 0.9385, "step": 1850 }, { "epoch": 0.36, "grad_norm": 0.9819820601700845, "learning_rate": 1.4922457942258411e-05, "loss": 0.9399, "step": 1851 }, { "epoch": 0.36, "grad_norm": 0.9751332011021767, "learning_rate": 1.4917033308076967e-05, "loss": 0.8618, "step": 1852 }, { "epoch": 0.36, "grad_norm": 1.211762583846398, "learning_rate": 1.4911606764933892e-05, "loss": 0.9182, "step": 1853 }, { "epoch": 0.36, "grad_norm": 0.9376732452575365, "learning_rate": 1.490617831493596e-05, "loss": 0.6152, "step": 1854 }, { "epoch": 0.36, "grad_norm": 1.0571971712690542, "learning_rate": 1.4900747960190682e-05, "loss": 0.9167, "step": 1855 }, { "epoch": 0.36, "grad_norm": 0.9059679331302924, "learning_rate": 1.489531570280631e-05, "loss": 0.8425, "step": 1856 }, { "epoch": 0.36, "grad_norm": 1.109100945968008, "learning_rate": 1.488988154489183e-05, "loss": 0.9321, "step": 1857 }, { "epoch": 0.36, "grad_norm": 0.9796349282624076, "learning_rate": 1.4884445488556972e-05, "loss": 0.9055, "step": 1858 }, { "epoch": 0.36, "grad_norm": 0.942848430501434, "learning_rate": 1.4879007535912198e-05, "loss": 0.884, "step": 1859 }, { "epoch": 0.36, "grad_norm": 0.9865862433093066, "learning_rate": 1.4873567689068708e-05, "loss": 0.8113, "step": 1860 }, { "epoch": 0.36, "grad_norm": 0.9858476689024814, "learning_rate": 1.4868125950138442e-05, "loss": 0.8567, "step": 1861 }, { "epoch": 0.36, "grad_norm": 0.976462244371231, "learning_rate": 1.4862682321234064e-05, "loss": 0.8495, "step": 1862 }, { "epoch": 0.36, "grad_norm": 0.8388436918387702, "learning_rate": 1.4857236804468983e-05, "loss": 0.6189, "step": 1863 }, { "epoch": 0.36, "grad_norm": 1.1772758874876872, "learning_rate": 1.4851789401957338e-05, "loss": 0.9697, "step": 1864 }, { "epoch": 0.36, "grad_norm": 1.1186464501853823, "learning_rate": 1.4846340115813993e-05, "loss": 0.9087, "step": 1865 }, { "epoch": 0.36, "grad_norm": 0.9974104641302132, "learning_rate": 1.484088894815455e-05, "loss": 0.979, "step": 1866 }, { "epoch": 0.36, "grad_norm": 0.7768189588295775, "learning_rate": 1.4835435901095341e-05, "loss": 0.5955, "step": 1867 }, { "epoch": 0.36, "grad_norm": 0.880919406726165, "learning_rate": 1.4829980976753426e-05, "loss": 0.6885, "step": 1868 }, { "epoch": 0.36, "grad_norm": 0.8035907486023335, "learning_rate": 1.4824524177246597e-05, "loss": 0.6286, "step": 1869 }, { "epoch": 0.36, "grad_norm": 0.902932949393427, "learning_rate": 1.4819065504693365e-05, "loss": 0.8909, "step": 1870 }, { "epoch": 0.36, "grad_norm": 1.0420266720429128, "learning_rate": 1.4813604961212984e-05, "loss": 0.8845, "step": 1871 }, { "epoch": 0.36, "grad_norm": 1.0330766501744677, "learning_rate": 1.4808142548925417e-05, "loss": 0.9507, "step": 1872 }, { "epoch": 0.36, "grad_norm": 0.9443997346281349, "learning_rate": 1.4802678269951365e-05, "loss": 0.8365, "step": 1873 }, { "epoch": 0.36, "grad_norm": 1.319576134265578, "learning_rate": 1.4797212126412243e-05, "loss": 0.8245, "step": 1874 }, { "epoch": 0.36, "grad_norm": 0.9611158883818487, "learning_rate": 1.4791744120430202e-05, "loss": 0.8948, "step": 1875 }, { "epoch": 0.36, "grad_norm": 1.0852791781277595, "learning_rate": 1.4786274254128112e-05, "loss": 0.9082, "step": 1876 }, { "epoch": 0.36, "grad_norm": 1.1124584300650766, "learning_rate": 1.4780802529629559e-05, "loss": 0.894, "step": 1877 }, { "epoch": 0.36, "grad_norm": 1.0105559752266144, "learning_rate": 1.4775328949058856e-05, "loss": 0.8726, "step": 1878 }, { "epoch": 0.36, "grad_norm": 0.8784687248629922, "learning_rate": 1.4769853514541037e-05, "loss": 0.6484, "step": 1879 }, { "epoch": 0.36, "grad_norm": 1.03856979336892, "learning_rate": 1.4764376228201848e-05, "loss": 0.8992, "step": 1880 }, { "epoch": 0.36, "grad_norm": 1.112357568279252, "learning_rate": 1.475889709216777e-05, "loss": 0.905, "step": 1881 }, { "epoch": 0.36, "grad_norm": 1.051779489329251, "learning_rate": 1.4753416108565985e-05, "loss": 0.8853, "step": 1882 }, { "epoch": 0.36, "grad_norm": 0.9688855112957112, "learning_rate": 1.47479332795244e-05, "loss": 0.8833, "step": 1883 }, { "epoch": 0.36, "grad_norm": 0.9385365006541581, "learning_rate": 1.4742448607171644e-05, "loss": 0.5746, "step": 1884 }, { "epoch": 0.36, "grad_norm": 1.0993549953003363, "learning_rate": 1.473696209363705e-05, "loss": 0.9202, "step": 1885 }, { "epoch": 0.36, "grad_norm": 1.2300281006228502, "learning_rate": 1.4731473741050673e-05, "loss": 0.9238, "step": 1886 }, { "epoch": 0.36, "grad_norm": 1.2845787923941006, "learning_rate": 1.4725983551543279e-05, "loss": 0.9124, "step": 1887 }, { "epoch": 0.36, "grad_norm": 0.9774677121240125, "learning_rate": 1.472049152724635e-05, "loss": 0.9434, "step": 1888 }, { "epoch": 0.36, "grad_norm": 1.0293356454512685, "learning_rate": 1.471499767029208e-05, "loss": 0.9092, "step": 1889 }, { "epoch": 0.36, "grad_norm": 1.0021709596663961, "learning_rate": 1.470950198281337e-05, "loss": 0.8696, "step": 1890 }, { "epoch": 0.36, "grad_norm": 0.978067833956942, "learning_rate": 1.470400446694384e-05, "loss": 0.8631, "step": 1891 }, { "epoch": 0.36, "grad_norm": 1.02191498033666, "learning_rate": 1.4698505124817811e-05, "loss": 0.9062, "step": 1892 }, { "epoch": 0.36, "grad_norm": 0.9039805328347078, "learning_rate": 1.4693003958570318e-05, "loss": 0.5874, "step": 1893 }, { "epoch": 0.36, "grad_norm": 0.9952700565831228, "learning_rate": 1.4687500970337103e-05, "loss": 0.8875, "step": 1894 }, { "epoch": 0.36, "grad_norm": 0.9656091184095154, "learning_rate": 1.4681996162254618e-05, "loss": 0.8896, "step": 1895 }, { "epoch": 0.36, "grad_norm": 0.9655277829638493, "learning_rate": 1.4676489536460015e-05, "loss": 0.9001, "step": 1896 }, { "epoch": 0.36, "grad_norm": 1.0419358494766526, "learning_rate": 1.467098109509116e-05, "loss": 0.8977, "step": 1897 }, { "epoch": 0.37, "grad_norm": 1.033565965013739, "learning_rate": 1.4665470840286614e-05, "loss": 0.918, "step": 1898 }, { "epoch": 0.37, "grad_norm": 1.0628550165142632, "learning_rate": 1.4659958774185654e-05, "loss": 0.8728, "step": 1899 }, { "epoch": 0.37, "grad_norm": 1.1182032078549922, "learning_rate": 1.4654444898928249e-05, "loss": 0.8999, "step": 1900 }, { "epoch": 0.37, "grad_norm": 0.9987126570378055, "learning_rate": 1.4648929216655077e-05, "loss": 0.8525, "step": 1901 }, { "epoch": 0.37, "grad_norm": 1.086037882660897, "learning_rate": 1.4643411729507517e-05, "loss": 0.8628, "step": 1902 }, { "epoch": 0.37, "grad_norm": 1.0410237147614523, "learning_rate": 1.4637892439627644e-05, "loss": 0.9211, "step": 1903 }, { "epoch": 0.37, "grad_norm": 1.0156030851989186, "learning_rate": 1.4632371349158241e-05, "loss": 0.8831, "step": 1904 }, { "epoch": 0.37, "grad_norm": 1.0008405406922605, "learning_rate": 1.4626848460242782e-05, "loss": 0.8628, "step": 1905 }, { "epoch": 0.37, "grad_norm": 1.0135829429212413, "learning_rate": 1.4621323775025444e-05, "loss": 0.926, "step": 1906 }, { "epoch": 0.37, "grad_norm": 0.7926177069362581, "learning_rate": 1.4615797295651099e-05, "loss": 0.6625, "step": 1907 }, { "epoch": 0.37, "grad_norm": 1.0033996071028828, "learning_rate": 1.4610269024265317e-05, "loss": 0.8789, "step": 1908 }, { "epoch": 0.37, "grad_norm": 1.0903546212030484, "learning_rate": 1.4604738963014365e-05, "loss": 0.8826, "step": 1909 }, { "epoch": 0.37, "grad_norm": 0.8376426346461645, "learning_rate": 1.4599207114045202e-05, "loss": 0.5821, "step": 1910 }, { "epoch": 0.37, "grad_norm": 1.1511569098045789, "learning_rate": 1.4593673479505482e-05, "loss": 0.9399, "step": 1911 }, { "epoch": 0.37, "grad_norm": 1.0126016997971148, "learning_rate": 1.4588138061543551e-05, "loss": 0.9153, "step": 1912 }, { "epoch": 0.37, "grad_norm": 1.336897576859498, "learning_rate": 1.458260086230845e-05, "loss": 0.8976, "step": 1913 }, { "epoch": 0.37, "grad_norm": 1.249937665398369, "learning_rate": 1.4577061883949912e-05, "loss": 0.9148, "step": 1914 }, { "epoch": 0.37, "grad_norm": 1.0447565306660136, "learning_rate": 1.4571521128618358e-05, "loss": 0.866, "step": 1915 }, { "epoch": 0.37, "grad_norm": 1.1011138973360892, "learning_rate": 1.4565978598464895e-05, "loss": 0.9011, "step": 1916 }, { "epoch": 0.37, "grad_norm": 1.1208019092723984, "learning_rate": 1.4560434295641338e-05, "loss": 0.9302, "step": 1917 }, { "epoch": 0.37, "grad_norm": 0.7138375885733166, "learning_rate": 1.455488822230016e-05, "loss": 0.3785, "step": 1918 }, { "epoch": 0.37, "grad_norm": 1.0740875796949105, "learning_rate": 1.4549340380594545e-05, "loss": 0.8933, "step": 1919 }, { "epoch": 0.37, "grad_norm": 0.99131600757946, "learning_rate": 1.454379077267836e-05, "loss": 0.8958, "step": 1920 }, { "epoch": 0.37, "grad_norm": 0.7876745542386958, "learning_rate": 1.4538239400706147e-05, "loss": 0.5903, "step": 1921 }, { "epoch": 0.37, "grad_norm": 0.9581971684971313, "learning_rate": 1.4532686266833143e-05, "loss": 0.8726, "step": 1922 }, { "epoch": 0.37, "grad_norm": 1.1156279514319452, "learning_rate": 1.4527131373215265e-05, "loss": 0.8218, "step": 1923 }, { "epoch": 0.37, "grad_norm": 1.0141347912723528, "learning_rate": 1.4521574722009115e-05, "loss": 0.8687, "step": 1924 }, { "epoch": 0.37, "grad_norm": 1.0312124705168675, "learning_rate": 1.4516016315371974e-05, "loss": 0.9006, "step": 1925 }, { "epoch": 0.37, "grad_norm": 1.0959455938787492, "learning_rate": 1.4510456155461807e-05, "loss": 0.917, "step": 1926 }, { "epoch": 0.37, "grad_norm": 0.9963651831902813, "learning_rate": 1.4504894244437264e-05, "loss": 0.9209, "step": 1927 }, { "epoch": 0.37, "grad_norm": 1.0353376825597194, "learning_rate": 1.4499330584457667e-05, "loss": 0.926, "step": 1928 }, { "epoch": 0.37, "grad_norm": 1.0716544345861556, "learning_rate": 1.4493765177683017e-05, "loss": 0.9207, "step": 1929 }, { "epoch": 0.37, "grad_norm": 1.1266377718936105, "learning_rate": 1.4488198026274007e-05, "loss": 0.869, "step": 1930 }, { "epoch": 0.37, "grad_norm": 1.163045571793419, "learning_rate": 1.4482629132391985e-05, "loss": 0.881, "step": 1931 }, { "epoch": 0.37, "grad_norm": 1.0058286632089855, "learning_rate": 1.4477058498198993e-05, "loss": 0.9023, "step": 1932 }, { "epoch": 0.37, "grad_norm": 0.9811212483867554, "learning_rate": 1.4471486125857743e-05, "loss": 0.8723, "step": 1933 }, { "epoch": 0.37, "grad_norm": 0.9971987691061406, "learning_rate": 1.446591201753162e-05, "loss": 0.9207, "step": 1934 }, { "epoch": 0.37, "grad_norm": 1.096625305485115, "learning_rate": 1.4460336175384688e-05, "loss": 0.959, "step": 1935 }, { "epoch": 0.37, "grad_norm": 1.089771242703592, "learning_rate": 1.4454758601581675e-05, "loss": 0.9182, "step": 1936 }, { "epoch": 0.37, "grad_norm": 0.9349376793886741, "learning_rate": 1.4449179298287999e-05, "loss": 0.9104, "step": 1937 }, { "epoch": 0.37, "grad_norm": 1.063528300481411, "learning_rate": 1.4443598267669723e-05, "loss": 0.8513, "step": 1938 }, { "epoch": 0.37, "grad_norm": 1.02492928412743, "learning_rate": 1.4438015511893602e-05, "loss": 0.9141, "step": 1939 }, { "epoch": 0.37, "grad_norm": 1.0884285768304829, "learning_rate": 1.4432431033127056e-05, "loss": 0.9224, "step": 1940 }, { "epoch": 0.37, "grad_norm": 0.995321912080976, "learning_rate": 1.442684483353817e-05, "loss": 0.9619, "step": 1941 }, { "epoch": 0.37, "grad_norm": 0.9045984224231635, "learning_rate": 1.4421256915295697e-05, "loss": 0.9036, "step": 1942 }, { "epoch": 0.37, "grad_norm": 0.990002980602915, "learning_rate": 1.4415667280569064e-05, "loss": 0.9321, "step": 1943 }, { "epoch": 0.37, "grad_norm": 1.032417979870837, "learning_rate": 1.4410075931528356e-05, "loss": 0.9014, "step": 1944 }, { "epoch": 0.37, "grad_norm": 1.1306240326092822, "learning_rate": 1.4404482870344322e-05, "loss": 0.8523, "step": 1945 }, { "epoch": 0.37, "grad_norm": 0.8102557047120184, "learning_rate": 1.4398888099188396e-05, "loss": 0.5959, "step": 1946 }, { "epoch": 0.37, "grad_norm": 0.9570661536002169, "learning_rate": 1.4393291620232646e-05, "loss": 0.8774, "step": 1947 }, { "epoch": 0.37, "grad_norm": 0.9323759974173033, "learning_rate": 1.4387693435649826e-05, "loss": 0.9321, "step": 1948 }, { "epoch": 0.37, "grad_norm": 1.0129666824708077, "learning_rate": 1.4382093547613338e-05, "loss": 0.9204, "step": 1949 }, { "epoch": 0.38, "grad_norm": 0.9431588367491968, "learning_rate": 1.4376491958297263e-05, "loss": 0.9062, "step": 1950 }, { "epoch": 0.38, "grad_norm": 0.9019534423630554, "learning_rate": 1.4370888669876317e-05, "loss": 0.6058, "step": 1951 }, { "epoch": 0.38, "grad_norm": 1.070906566142537, "learning_rate": 1.4365283684525895e-05, "loss": 0.916, "step": 1952 }, { "epoch": 0.38, "grad_norm": 1.0689560782709229, "learning_rate": 1.4359677004422045e-05, "loss": 0.939, "step": 1953 }, { "epoch": 0.38, "grad_norm": 0.9299102599474509, "learning_rate": 1.4354068631741476e-05, "loss": 0.8706, "step": 1954 }, { "epoch": 0.38, "grad_norm": 1.016759222023544, "learning_rate": 1.4348458568661548e-05, "loss": 0.8574, "step": 1955 }, { "epoch": 0.38, "grad_norm": 1.0393117728004693, "learning_rate": 1.434284681736028e-05, "loss": 0.8818, "step": 1956 }, { "epoch": 0.38, "grad_norm": 0.924436291659695, "learning_rate": 1.4337233380016354e-05, "loss": 0.9019, "step": 1957 }, { "epoch": 0.38, "grad_norm": 0.8832054065605702, "learning_rate": 1.433161825880909e-05, "loss": 0.6035, "step": 1958 }, { "epoch": 0.38, "grad_norm": 1.0075811973855693, "learning_rate": 1.432600145591848e-05, "loss": 0.8875, "step": 1959 }, { "epoch": 0.38, "grad_norm": 0.9135435769250039, "learning_rate": 1.4320382973525151e-05, "loss": 0.8921, "step": 1960 }, { "epoch": 0.38, "grad_norm": 1.1674130417096407, "learning_rate": 1.43147628138104e-05, "loss": 0.9272, "step": 1961 }, { "epoch": 0.38, "grad_norm": 1.0150848992879957, "learning_rate": 1.4309140978956161e-05, "loss": 0.9031, "step": 1962 }, { "epoch": 0.38, "grad_norm": 0.9158659955891143, "learning_rate": 1.430351747114503e-05, "loss": 0.9331, "step": 1963 }, { "epoch": 0.38, "grad_norm": 0.9696867356952743, "learning_rate": 1.429789229256024e-05, "loss": 0.8711, "step": 1964 }, { "epoch": 0.38, "grad_norm": 1.054981016448293, "learning_rate": 1.429226544538568e-05, "loss": 0.9028, "step": 1965 }, { "epoch": 0.38, "grad_norm": 1.0394932068881446, "learning_rate": 1.4286636931805887e-05, "loss": 0.8867, "step": 1966 }, { "epoch": 0.38, "grad_norm": 1.1510996196219692, "learning_rate": 1.4281006754006045e-05, "loss": 0.8962, "step": 1967 }, { "epoch": 0.38, "grad_norm": 0.9333466026642885, "learning_rate": 1.427537491417198e-05, "loss": 0.8833, "step": 1968 }, { "epoch": 0.38, "grad_norm": 1.0032775338600828, "learning_rate": 1.426974141449017e-05, "loss": 0.8818, "step": 1969 }, { "epoch": 0.38, "grad_norm": 1.1401919815099508, "learning_rate": 1.4264106257147732e-05, "loss": 0.8285, "step": 1970 }, { "epoch": 0.38, "grad_norm": 1.017461049708947, "learning_rate": 1.4258469444332423e-05, "loss": 0.9165, "step": 1971 }, { "epoch": 0.38, "grad_norm": 0.9880258028379324, "learning_rate": 1.4252830978232658e-05, "loss": 0.9216, "step": 1972 }, { "epoch": 0.38, "grad_norm": 0.9604234430163869, "learning_rate": 1.4247190861037474e-05, "loss": 0.8389, "step": 1973 }, { "epoch": 0.38, "grad_norm": 1.1026589275242191, "learning_rate": 1.4241549094936567e-05, "loss": 0.8823, "step": 1974 }, { "epoch": 0.38, "grad_norm": 1.0034327401514893, "learning_rate": 1.4235905682120255e-05, "loss": 0.8547, "step": 1975 }, { "epoch": 0.38, "grad_norm": 1.046337492443979, "learning_rate": 1.4230260624779512e-05, "loss": 0.9128, "step": 1976 }, { "epoch": 0.38, "grad_norm": 1.08514206899683, "learning_rate": 1.4224613925105947e-05, "loss": 0.8965, "step": 1977 }, { "epoch": 0.38, "grad_norm": 1.0737134363775986, "learning_rate": 1.4218965585291792e-05, "loss": 0.9285, "step": 1978 }, { "epoch": 0.38, "grad_norm": 1.1454354266981783, "learning_rate": 1.4213315607529939e-05, "loss": 0.9622, "step": 1979 }, { "epoch": 0.38, "grad_norm": 1.0702716970149377, "learning_rate": 1.4207663994013896e-05, "loss": 0.9248, "step": 1980 }, { "epoch": 0.38, "grad_norm": 1.1268233153422795, "learning_rate": 1.4202010746937815e-05, "loss": 0.7439, "step": 1981 }, { "epoch": 0.38, "grad_norm": 1.115070179570064, "learning_rate": 1.4196355868496485e-05, "loss": 0.8975, "step": 1982 }, { "epoch": 0.38, "grad_norm": 0.9986624655209043, "learning_rate": 1.4190699360885323e-05, "loss": 0.8933, "step": 1983 }, { "epoch": 0.38, "grad_norm": 0.7778111284097043, "learning_rate": 1.4185041226300376e-05, "loss": 0.5981, "step": 1984 }, { "epoch": 0.38, "grad_norm": 1.4300963310373829, "learning_rate": 1.4179381466938332e-05, "loss": 0.8845, "step": 1985 }, { "epoch": 0.38, "grad_norm": 0.9053848680516776, "learning_rate": 1.4173720084996501e-05, "loss": 0.8945, "step": 1986 }, { "epoch": 0.38, "grad_norm": 0.9477289897683785, "learning_rate": 1.4168057082672828e-05, "loss": 0.8679, "step": 1987 }, { "epoch": 0.38, "grad_norm": 0.9114443293982946, "learning_rate": 1.4162392462165884e-05, "loss": 0.632, "step": 1988 }, { "epoch": 0.38, "grad_norm": 1.0329352143721207, "learning_rate": 1.4156726225674874e-05, "loss": 0.9062, "step": 1989 }, { "epoch": 0.38, "grad_norm": 1.07993906153705, "learning_rate": 1.415105837539962e-05, "loss": 0.918, "step": 1990 }, { "epoch": 0.38, "grad_norm": 1.013658158948195, "learning_rate": 1.414538891354058e-05, "loss": 0.9229, "step": 1991 }, { "epoch": 0.38, "grad_norm": 1.05417880113167, "learning_rate": 1.4139717842298835e-05, "loss": 0.9355, "step": 1992 }, { "epoch": 0.38, "grad_norm": 0.886426862782416, "learning_rate": 1.4134045163876086e-05, "loss": 0.864, "step": 1993 }, { "epoch": 0.38, "grad_norm": 0.9629300249194388, "learning_rate": 1.4128370880474667e-05, "loss": 0.9136, "step": 1994 }, { "epoch": 0.38, "grad_norm": 0.9768515265243276, "learning_rate": 1.412269499429753e-05, "loss": 0.8972, "step": 1995 }, { "epoch": 0.38, "grad_norm": 1.109116703424251, "learning_rate": 1.4117017507548244e-05, "loss": 0.8867, "step": 1996 }, { "epoch": 0.38, "grad_norm": 1.108727848996653, "learning_rate": 1.4111338422431013e-05, "loss": 0.9119, "step": 1997 }, { "epoch": 0.38, "grad_norm": 0.8769902912263137, "learning_rate": 1.4105657741150648e-05, "loss": 0.5941, "step": 1998 }, { "epoch": 0.38, "grad_norm": 0.9439970321090078, "learning_rate": 1.4099975465912584e-05, "loss": 0.6058, "step": 1999 }, { "epoch": 0.38, "grad_norm": 1.0126283684659818, "learning_rate": 1.4094291598922877e-05, "loss": 0.8682, "step": 2000 }, { "epoch": 0.38, "grad_norm": 1.0367208870556341, "learning_rate": 1.40886061423882e-05, "loss": 0.877, "step": 2001 }, { "epoch": 0.39, "grad_norm": 0.9829666883714266, "learning_rate": 1.4082919098515846e-05, "loss": 0.8611, "step": 2002 }, { "epoch": 0.39, "grad_norm": 1.0658145798481287, "learning_rate": 1.407723046951372e-05, "loss": 0.8444, "step": 2003 }, { "epoch": 0.39, "grad_norm": 1.0228447298568704, "learning_rate": 1.4071540257590341e-05, "loss": 0.9031, "step": 2004 }, { "epoch": 0.39, "grad_norm": 1.0324399086145426, "learning_rate": 1.4065848464954848e-05, "loss": 0.9211, "step": 2005 }, { "epoch": 0.39, "grad_norm": 0.8350737343551917, "learning_rate": 1.4060155093816988e-05, "loss": 0.629, "step": 2006 }, { "epoch": 0.39, "grad_norm": 0.9168975977308533, "learning_rate": 1.4054460146387124e-05, "loss": 0.632, "step": 2007 }, { "epoch": 0.39, "grad_norm": 1.2075001909424772, "learning_rate": 1.4048763624876233e-05, "loss": 0.9138, "step": 2008 }, { "epoch": 0.39, "grad_norm": 0.9609602651913617, "learning_rate": 1.4043065531495904e-05, "loss": 0.8682, "step": 2009 }, { "epoch": 0.39, "grad_norm": 1.0453681273655548, "learning_rate": 1.4037365868458325e-05, "loss": 0.8898, "step": 2010 }, { "epoch": 0.39, "grad_norm": 1.034600303704724, "learning_rate": 1.4031664637976305e-05, "loss": 0.9126, "step": 2011 }, { "epoch": 0.39, "grad_norm": 1.0513117437795445, "learning_rate": 1.402596184226326e-05, "loss": 0.8604, "step": 2012 }, { "epoch": 0.39, "grad_norm": 1.0132819419834949, "learning_rate": 1.4020257483533208e-05, "loss": 0.8574, "step": 2013 }, { "epoch": 0.39, "grad_norm": 0.9357727120149787, "learning_rate": 1.401455156400078e-05, "loss": 0.8674, "step": 2014 }, { "epoch": 0.39, "grad_norm": 0.9955768630205831, "learning_rate": 1.400884408588121e-05, "loss": 0.9036, "step": 2015 }, { "epoch": 0.39, "grad_norm": 0.8643897190296631, "learning_rate": 1.400313505139034e-05, "loss": 0.6138, "step": 2016 }, { "epoch": 0.39, "grad_norm": 0.8842625005878099, "learning_rate": 1.3997424462744607e-05, "loss": 0.5983, "step": 2017 }, { "epoch": 0.39, "grad_norm": 1.0949574270900142, "learning_rate": 1.3991712322161065e-05, "loss": 0.9417, "step": 2018 }, { "epoch": 0.39, "grad_norm": 0.9562321450476999, "learning_rate": 1.3985998631857359e-05, "loss": 0.8916, "step": 2019 }, { "epoch": 0.39, "grad_norm": 1.140505709966786, "learning_rate": 1.398028339405174e-05, "loss": 0.9302, "step": 2020 }, { "epoch": 0.39, "grad_norm": 0.9536778832941109, "learning_rate": 1.3974566610963068e-05, "loss": 0.8297, "step": 2021 }, { "epoch": 0.39, "grad_norm": 1.1054541777267008, "learning_rate": 1.3968848284810785e-05, "loss": 0.8635, "step": 2022 }, { "epoch": 0.39, "grad_norm": 0.893580453662741, "learning_rate": 1.3963128417814951e-05, "loss": 0.8921, "step": 2023 }, { "epoch": 0.39, "grad_norm": 0.9926127633311482, "learning_rate": 1.3957407012196204e-05, "loss": 0.9297, "step": 2024 }, { "epoch": 0.39, "grad_norm": 1.1914252602123678, "learning_rate": 1.3951684070175802e-05, "loss": 0.9634, "step": 2025 }, { "epoch": 0.39, "grad_norm": 0.8029832074337658, "learning_rate": 1.3945959593975582e-05, "loss": 0.615, "step": 2026 }, { "epoch": 0.39, "grad_norm": 0.9641638596829792, "learning_rate": 1.3940233585817984e-05, "loss": 0.8423, "step": 2027 }, { "epoch": 0.39, "grad_norm": 1.0553546373964464, "learning_rate": 1.3934506047926042e-05, "loss": 0.8599, "step": 2028 }, { "epoch": 0.39, "grad_norm": 0.9744460721845654, "learning_rate": 1.3928776982523384e-05, "loss": 0.8945, "step": 2029 }, { "epoch": 0.39, "grad_norm": 1.2765210822491164, "learning_rate": 1.3923046391834229e-05, "loss": 0.9412, "step": 2030 }, { "epoch": 0.39, "grad_norm": 0.9927035117697316, "learning_rate": 1.3917314278083391e-05, "loss": 0.8892, "step": 2031 }, { "epoch": 0.39, "grad_norm": 0.8227477641541414, "learning_rate": 1.3911580643496272e-05, "loss": 0.5742, "step": 2032 }, { "epoch": 0.39, "grad_norm": 0.9596062210533985, "learning_rate": 1.3905845490298867e-05, "loss": 0.8457, "step": 2033 }, { "epoch": 0.39, "grad_norm": 0.8412410529916833, "learning_rate": 1.390010882071776e-05, "loss": 0.6255, "step": 2034 }, { "epoch": 0.39, "grad_norm": 0.9907831043849605, "learning_rate": 1.3894370636980128e-05, "loss": 0.8701, "step": 2035 }, { "epoch": 0.39, "grad_norm": 1.210274786689387, "learning_rate": 1.3888630941313728e-05, "loss": 0.9038, "step": 2036 }, { "epoch": 0.39, "grad_norm": 1.0166315415338334, "learning_rate": 1.3882889735946901e-05, "loss": 0.8823, "step": 2037 }, { "epoch": 0.39, "grad_norm": 0.9918895139264042, "learning_rate": 1.3877147023108592e-05, "loss": 0.876, "step": 2038 }, { "epoch": 0.39, "grad_norm": 1.1480453184071178, "learning_rate": 1.3871402805028314e-05, "loss": 0.9321, "step": 2039 }, { "epoch": 0.39, "grad_norm": 1.0619425251222738, "learning_rate": 1.3865657083936167e-05, "loss": 0.9521, "step": 2040 }, { "epoch": 0.39, "grad_norm": 0.9222719077575293, "learning_rate": 1.3859909862062844e-05, "loss": 0.6323, "step": 2041 }, { "epoch": 0.39, "grad_norm": 1.0306978992020874, "learning_rate": 1.385416114163961e-05, "loss": 0.897, "step": 2042 }, { "epoch": 0.39, "grad_norm": 0.938180060641578, "learning_rate": 1.3848410924898321e-05, "loss": 0.62, "step": 2043 }, { "epoch": 0.39, "grad_norm": 0.97804149830746, "learning_rate": 1.3842659214071406e-05, "loss": 0.9199, "step": 2044 }, { "epoch": 0.39, "grad_norm": 0.9600161378178582, "learning_rate": 1.3836906011391878e-05, "loss": 0.9451, "step": 2045 }, { "epoch": 0.39, "grad_norm": 0.94723737271444, "learning_rate": 1.3831151319093323e-05, "loss": 0.8772, "step": 2046 }, { "epoch": 0.39, "grad_norm": 1.1101018912003724, "learning_rate": 1.382539513940992e-05, "loss": 0.925, "step": 2047 }, { "epoch": 0.39, "grad_norm": 1.032312080852157, "learning_rate": 1.3819637474576411e-05, "loss": 0.9001, "step": 2048 }, { "epoch": 0.39, "grad_norm": 1.0347201924648377, "learning_rate": 1.381387832682812e-05, "loss": 0.8611, "step": 2049 }, { "epoch": 0.39, "grad_norm": 0.918635832723443, "learning_rate": 1.380811769840095e-05, "loss": 0.9158, "step": 2050 }, { "epoch": 0.39, "grad_norm": 1.046058082395391, "learning_rate": 1.3802355591531366e-05, "loss": 0.9084, "step": 2051 }, { "epoch": 0.39, "grad_norm": 0.9697121864494067, "learning_rate": 1.3796592008456427e-05, "loss": 0.9077, "step": 2052 }, { "epoch": 0.39, "grad_norm": 0.9727242508972921, "learning_rate": 1.3790826951413747e-05, "loss": 0.8899, "step": 2053 }, { "epoch": 0.4, "grad_norm": 0.8411578471203727, "learning_rate": 1.3785060422641526e-05, "loss": 0.6281, "step": 2054 }, { "epoch": 0.4, "grad_norm": 1.0836130401861472, "learning_rate": 1.3779292424378521e-05, "loss": 0.9016, "step": 2055 }, { "epoch": 0.4, "grad_norm": 0.9440793784345544, "learning_rate": 1.3773522958864076e-05, "loss": 0.8584, "step": 2056 }, { "epoch": 0.4, "grad_norm": 1.052483901746118, "learning_rate": 1.3767752028338091e-05, "loss": 0.8882, "step": 2057 }, { "epoch": 0.4, "grad_norm": 1.1588308358567396, "learning_rate": 1.376197963504104e-05, "loss": 0.9402, "step": 2058 }, { "epoch": 0.4, "grad_norm": 0.9828578389756023, "learning_rate": 1.3756205781213965e-05, "loss": 0.9373, "step": 2059 }, { "epoch": 0.4, "grad_norm": 1.0188933657039372, "learning_rate": 1.375043046909848e-05, "loss": 0.8748, "step": 2060 }, { "epoch": 0.4, "grad_norm": 1.0838000841107949, "learning_rate": 1.3744653700936752e-05, "loss": 0.9324, "step": 2061 }, { "epoch": 0.4, "grad_norm": 1.071515906475275, "learning_rate": 1.3738875478971526e-05, "loss": 0.9346, "step": 2062 }, { "epoch": 0.4, "grad_norm": 0.8130226057842734, "learning_rate": 1.3733095805446107e-05, "loss": 0.5901, "step": 2063 }, { "epoch": 0.4, "grad_norm": 1.126611085091575, "learning_rate": 1.372731468260436e-05, "loss": 0.8877, "step": 2064 }, { "epoch": 0.4, "grad_norm": 1.0466974141382839, "learning_rate": 1.372153211269072e-05, "loss": 0.8943, "step": 2065 }, { "epoch": 0.4, "grad_norm": 1.0124651553989192, "learning_rate": 1.3715748097950176e-05, "loss": 0.8621, "step": 2066 }, { "epoch": 0.4, "grad_norm": 1.0663385546597837, "learning_rate": 1.3709962640628284e-05, "loss": 0.9377, "step": 2067 }, { "epoch": 0.4, "grad_norm": 1.0253616051881649, "learning_rate": 1.3704175742971158e-05, "loss": 0.8862, "step": 2068 }, { "epoch": 0.4, "grad_norm": 0.9804977803567926, "learning_rate": 1.369838740722547e-05, "loss": 0.9255, "step": 2069 }, { "epoch": 0.4, "grad_norm": 0.998667236770355, "learning_rate": 1.3692597635638452e-05, "loss": 0.8608, "step": 2070 }, { "epoch": 0.4, "grad_norm": 1.1949405629111134, "learning_rate": 1.368680643045789e-05, "loss": 0.9011, "step": 2071 }, { "epoch": 0.4, "grad_norm": 0.966723147504698, "learning_rate": 1.3681013793932132e-05, "loss": 0.9038, "step": 2072 }, { "epoch": 0.4, "grad_norm": 1.0594258418672597, "learning_rate": 1.3675219728310076e-05, "loss": 0.8992, "step": 2073 }, { "epoch": 0.4, "grad_norm": 1.0466405317724052, "learning_rate": 1.3669424235841185e-05, "loss": 0.9438, "step": 2074 }, { "epoch": 0.4, "grad_norm": 1.0600318379278442, "learning_rate": 1.3663627318775459e-05, "loss": 0.8896, "step": 2075 }, { "epoch": 0.4, "grad_norm": 0.8624036622515208, "learning_rate": 1.3657828979363468e-05, "loss": 0.6573, "step": 2076 }, { "epoch": 0.4, "grad_norm": 1.142699643136873, "learning_rate": 1.3652029219856324e-05, "loss": 0.9487, "step": 2077 }, { "epoch": 0.4, "grad_norm": 0.9382017658197432, "learning_rate": 1.3646228042505694e-05, "loss": 0.8419, "step": 2078 }, { "epoch": 0.4, "grad_norm": 1.020179974221245, "learning_rate": 1.3640425449563793e-05, "loss": 0.9292, "step": 2079 }, { "epoch": 0.4, "grad_norm": 1.0266809883252035, "learning_rate": 1.3634621443283389e-05, "loss": 0.8796, "step": 2080 }, { "epoch": 0.4, "grad_norm": 0.8514681449946019, "learning_rate": 1.36288160259178e-05, "loss": 0.6245, "step": 2081 }, { "epoch": 0.4, "grad_norm": 0.9821293200461357, "learning_rate": 1.3623009199720882e-05, "loss": 0.8643, "step": 2082 }, { "epoch": 0.4, "grad_norm": 0.9395515663929549, "learning_rate": 1.3617200966947053e-05, "loss": 0.8765, "step": 2083 }, { "epoch": 0.4, "grad_norm": 0.961800788851755, "learning_rate": 1.3611391329851262e-05, "loss": 0.9148, "step": 2084 }, { "epoch": 0.4, "grad_norm": 1.1460036430711609, "learning_rate": 1.3605580290689013e-05, "loss": 0.9314, "step": 2085 }, { "epoch": 0.4, "grad_norm": 0.9548510013723058, "learning_rate": 1.3599767851716353e-05, "loss": 0.8872, "step": 2086 }, { "epoch": 0.4, "grad_norm": 1.0284825132107578, "learning_rate": 1.3593954015189867e-05, "loss": 0.9507, "step": 2087 }, { "epoch": 0.4, "grad_norm": 0.9900118358621308, "learning_rate": 1.3588138783366692e-05, "loss": 0.9429, "step": 2088 }, { "epoch": 0.4, "grad_norm": 0.9326921992068847, "learning_rate": 1.3582322158504495e-05, "loss": 0.8374, "step": 2089 }, { "epoch": 0.4, "grad_norm": 1.0769576855304528, "learning_rate": 1.3576504142861496e-05, "loss": 0.9431, "step": 2090 }, { "epoch": 0.4, "grad_norm": 1.037135718795911, "learning_rate": 1.3570684738696444e-05, "loss": 0.9197, "step": 2091 }, { "epoch": 0.4, "grad_norm": 1.06316178018185, "learning_rate": 1.3564863948268631e-05, "loss": 0.8801, "step": 2092 }, { "epoch": 0.4, "grad_norm": 0.868119909420993, "learning_rate": 1.3559041773837898e-05, "loss": 0.6123, "step": 2093 }, { "epoch": 0.4, "grad_norm": 0.8001517049842943, "learning_rate": 1.3553218217664603e-05, "loss": 0.6508, "step": 2094 }, { "epoch": 0.4, "grad_norm": 1.0345766546803243, "learning_rate": 1.3547393282009656e-05, "loss": 0.9487, "step": 2095 }, { "epoch": 0.4, "grad_norm": 0.9754706936147337, "learning_rate": 1.3541566969134496e-05, "loss": 0.9001, "step": 2096 }, { "epoch": 0.4, "grad_norm": 0.9798849125296536, "learning_rate": 1.3535739281301102e-05, "loss": 0.8931, "step": 2097 }, { "epoch": 0.4, "grad_norm": 1.139224268298282, "learning_rate": 1.3529910220771975e-05, "loss": 0.936, "step": 2098 }, { "epoch": 0.4, "grad_norm": 1.0378784275522666, "learning_rate": 1.3524079789810163e-05, "loss": 0.8923, "step": 2099 }, { "epoch": 0.4, "grad_norm": 1.0243809004162607, "learning_rate": 1.3518247990679241e-05, "loss": 0.949, "step": 2100 }, { "epoch": 0.4, "grad_norm": 1.0273756998591237, "learning_rate": 1.3512414825643312e-05, "loss": 0.9309, "step": 2101 }, { "epoch": 0.4, "grad_norm": 1.2146358806619226, "learning_rate": 1.3506580296967011e-05, "loss": 0.9458, "step": 2102 }, { "epoch": 0.4, "grad_norm": 0.9317992795551133, "learning_rate": 1.3500744406915505e-05, "loss": 0.8572, "step": 2103 }, { "epoch": 0.4, "grad_norm": 0.8607210345349163, "learning_rate": 1.3494907157754485e-05, "loss": 0.5845, "step": 2104 }, { "epoch": 0.4, "grad_norm": 1.1976641373676338, "learning_rate": 1.348906855175017e-05, "loss": 0.8296, "step": 2105 }, { "epoch": 0.41, "grad_norm": 0.9201669830890042, "learning_rate": 1.3483228591169315e-05, "loss": 0.8538, "step": 2106 }, { "epoch": 0.41, "grad_norm": 0.9260848215102202, "learning_rate": 1.347738727827919e-05, "loss": 0.8743, "step": 2107 }, { "epoch": 0.41, "grad_norm": 0.7900811120526294, "learning_rate": 1.3471544615347591e-05, "loss": 0.6318, "step": 2108 }, { "epoch": 0.41, "grad_norm": 1.0114281174317006, "learning_rate": 1.3465700604642847e-05, "loss": 0.8816, "step": 2109 }, { "epoch": 0.41, "grad_norm": 1.0220036301473294, "learning_rate": 1.34598552484338e-05, "loss": 0.8984, "step": 2110 }, { "epoch": 0.41, "grad_norm": 0.9943606962376513, "learning_rate": 1.3454008548989816e-05, "loss": 0.8955, "step": 2111 }, { "epoch": 0.41, "grad_norm": 0.9975732411556983, "learning_rate": 1.3448160508580789e-05, "loss": 0.9033, "step": 2112 }, { "epoch": 0.41, "grad_norm": 1.0016737170964372, "learning_rate": 1.3442311129477133e-05, "loss": 0.8936, "step": 2113 }, { "epoch": 0.41, "grad_norm": 1.0607248494152397, "learning_rate": 1.343646041394977e-05, "loss": 0.8901, "step": 2114 }, { "epoch": 0.41, "grad_norm": 1.0725848358144277, "learning_rate": 1.3430608364270156e-05, "loss": 0.9146, "step": 2115 }, { "epoch": 0.41, "grad_norm": 0.9754423342702944, "learning_rate": 1.3424754982710256e-05, "loss": 0.6321, "step": 2116 }, { "epoch": 0.41, "grad_norm": 0.9779917169615363, "learning_rate": 1.3418900271542552e-05, "loss": 0.9321, "step": 2117 }, { "epoch": 0.41, "grad_norm": 1.1320505228847058, "learning_rate": 1.3413044233040045e-05, "loss": 0.8928, "step": 2118 }, { "epoch": 0.41, "grad_norm": 1.0130394826224967, "learning_rate": 1.3407186869476253e-05, "loss": 0.9065, "step": 2119 }, { "epoch": 0.41, "grad_norm": 1.114853955446366, "learning_rate": 1.3401328183125208e-05, "loss": 0.9512, "step": 2120 }, { "epoch": 0.41, "grad_norm": 1.1446444270132352, "learning_rate": 1.339546817626145e-05, "loss": 0.8943, "step": 2121 }, { "epoch": 0.41, "grad_norm": 0.9682171547311159, "learning_rate": 1.3389606851160037e-05, "loss": 0.8853, "step": 2122 }, { "epoch": 0.41, "grad_norm": 0.96849636766068, "learning_rate": 1.3383744210096537e-05, "loss": 0.8574, "step": 2123 }, { "epoch": 0.41, "grad_norm": 0.9422976905051568, "learning_rate": 1.3377880255347026e-05, "loss": 0.8584, "step": 2124 }, { "epoch": 0.41, "grad_norm": 0.9551972590879704, "learning_rate": 1.3372014989188098e-05, "loss": 0.9065, "step": 2125 }, { "epoch": 0.41, "grad_norm": 1.0435460172739603, "learning_rate": 1.3366148413896851e-05, "loss": 0.9146, "step": 2126 }, { "epoch": 0.41, "grad_norm": 0.9582547619043479, "learning_rate": 1.3360280531750886e-05, "loss": 0.8547, "step": 2127 }, { "epoch": 0.41, "grad_norm": 1.076529615407611, "learning_rate": 1.3354411345028324e-05, "loss": 0.8992, "step": 2128 }, { "epoch": 0.41, "grad_norm": 0.967538487046378, "learning_rate": 1.3348540856007782e-05, "loss": 0.9473, "step": 2129 }, { "epoch": 0.41, "grad_norm": 1.0409705188508789, "learning_rate": 1.3342669066968385e-05, "loss": 0.9189, "step": 2130 }, { "epoch": 0.41, "grad_norm": 0.9641071586586348, "learning_rate": 1.3336795980189763e-05, "loss": 0.8379, "step": 2131 }, { "epoch": 0.41, "grad_norm": 1.0258606362565672, "learning_rate": 1.3330921597952056e-05, "loss": 0.8989, "step": 2132 }, { "epoch": 0.41, "grad_norm": 1.1620860680478875, "learning_rate": 1.3325045922535896e-05, "loss": 0.8916, "step": 2133 }, { "epoch": 0.41, "grad_norm": 1.1449017623778264, "learning_rate": 1.3319168956222423e-05, "loss": 0.8909, "step": 2134 }, { "epoch": 0.41, "grad_norm": 1.0230585194646367, "learning_rate": 1.331329070129328e-05, "loss": 0.8829, "step": 2135 }, { "epoch": 0.41, "grad_norm": 0.9451613268386378, "learning_rate": 1.3307411160030608e-05, "loss": 0.8845, "step": 2136 }, { "epoch": 0.41, "grad_norm": 1.0943125446810897, "learning_rate": 1.3301530334717046e-05, "loss": 0.9009, "step": 2137 }, { "epoch": 0.41, "grad_norm": 1.0025940292070894, "learning_rate": 1.3295648227635729e-05, "loss": 0.8892, "step": 2138 }, { "epoch": 0.41, "grad_norm": 1.0982635674387544, "learning_rate": 1.32897648410703e-05, "loss": 0.9214, "step": 2139 }, { "epoch": 0.41, "grad_norm": 1.0858134435342826, "learning_rate": 1.328388017730489e-05, "loss": 0.8779, "step": 2140 }, { "epoch": 0.41, "grad_norm": 0.9694752257019271, "learning_rate": 1.327799423862413e-05, "loss": 0.9299, "step": 2141 }, { "epoch": 0.41, "grad_norm": 1.0297693524475162, "learning_rate": 1.3272107027313142e-05, "loss": 0.8901, "step": 2142 }, { "epoch": 0.41, "grad_norm": 1.0035997237737142, "learning_rate": 1.3266218545657541e-05, "loss": 0.8567, "step": 2143 }, { "epoch": 0.41, "grad_norm": 1.1535094031060518, "learning_rate": 1.326032879594344e-05, "loss": 0.928, "step": 2144 }, { "epoch": 0.41, "grad_norm": 0.8610294858549574, "learning_rate": 1.3254437780457448e-05, "loss": 0.6207, "step": 2145 }, { "epoch": 0.41, "grad_norm": 1.0902574439360482, "learning_rate": 1.3248545501486654e-05, "loss": 0.8806, "step": 2146 }, { "epoch": 0.41, "grad_norm": 0.9515414286243384, "learning_rate": 1.3242651961318646e-05, "loss": 0.8989, "step": 2147 }, { "epoch": 0.41, "grad_norm": 1.1194937997129073, "learning_rate": 1.32367571622415e-05, "loss": 0.874, "step": 2148 }, { "epoch": 0.41, "grad_norm": 1.0533740324372651, "learning_rate": 1.3230861106543777e-05, "loss": 0.8875, "step": 2149 }, { "epoch": 0.41, "grad_norm": 1.0143915370684926, "learning_rate": 1.3224963796514532e-05, "loss": 0.8861, "step": 2150 }, { "epoch": 0.41, "grad_norm": 1.0284782135152337, "learning_rate": 1.32190652344433e-05, "loss": 0.8723, "step": 2151 }, { "epoch": 0.41, "grad_norm": 0.9752385070449747, "learning_rate": 1.3213165422620111e-05, "loss": 0.8608, "step": 2152 }, { "epoch": 0.41, "grad_norm": 1.0661086492061318, "learning_rate": 1.3207264363335472e-05, "loss": 0.9043, "step": 2153 }, { "epoch": 0.41, "grad_norm": 0.7977714352427803, "learning_rate": 1.3201362058880375e-05, "loss": 0.6165, "step": 2154 }, { "epoch": 0.41, "grad_norm": 0.9732468247901236, "learning_rate": 1.3195458511546307e-05, "loss": 0.8424, "step": 2155 }, { "epoch": 0.41, "grad_norm": 1.0170274653331735, "learning_rate": 1.3189553723625217e-05, "loss": 0.8982, "step": 2156 }, { "epoch": 0.41, "grad_norm": 1.0419416795231968, "learning_rate": 1.318364769740955e-05, "loss": 0.9153, "step": 2157 }, { "epoch": 0.42, "grad_norm": 1.1766950817126607, "learning_rate": 1.3177740435192235e-05, "loss": 0.8595, "step": 2158 }, { "epoch": 0.42, "grad_norm": 1.0398531684943335, "learning_rate": 1.3171831939266668e-05, "loss": 0.8608, "step": 2159 }, { "epoch": 0.42, "grad_norm": 1.1086897484027662, "learning_rate": 1.3165922211926734e-05, "loss": 0.9685, "step": 2160 }, { "epoch": 0.42, "grad_norm": 1.0142231855288486, "learning_rate": 1.3160011255466791e-05, "loss": 0.8804, "step": 2161 }, { "epoch": 0.42, "grad_norm": 1.1856693323590914, "learning_rate": 1.3154099072181677e-05, "loss": 0.9153, "step": 2162 }, { "epoch": 0.42, "grad_norm": 0.8243150781888084, "learning_rate": 1.3148185664366704e-05, "loss": 0.5713, "step": 2163 }, { "epoch": 0.42, "grad_norm": 1.1179259276744222, "learning_rate": 1.314227103431766e-05, "loss": 0.8762, "step": 2164 }, { "epoch": 0.42, "grad_norm": 1.1427762426290735, "learning_rate": 1.3136355184330809e-05, "loss": 0.8901, "step": 2165 }, { "epoch": 0.42, "grad_norm": 1.0137448831223599, "learning_rate": 1.3130438116702888e-05, "loss": 0.9026, "step": 2166 }, { "epoch": 0.42, "grad_norm": 0.9417056682385199, "learning_rate": 1.3124519833731106e-05, "loss": 0.8376, "step": 2167 }, { "epoch": 0.42, "grad_norm": 1.1080503694453243, "learning_rate": 1.3118600337713146e-05, "loss": 0.876, "step": 2168 }, { "epoch": 0.42, "grad_norm": 0.9405663849957585, "learning_rate": 1.3112679630947156e-05, "loss": 0.8723, "step": 2169 }, { "epoch": 0.42, "grad_norm": 1.0701597025930876, "learning_rate": 1.310675771573176e-05, "loss": 0.9307, "step": 2170 }, { "epoch": 0.42, "grad_norm": 1.1200941082606322, "learning_rate": 1.310083459436605e-05, "loss": 0.9387, "step": 2171 }, { "epoch": 0.42, "grad_norm": 0.9369817883540275, "learning_rate": 1.3094910269149587e-05, "loss": 0.9163, "step": 2172 }, { "epoch": 0.42, "grad_norm": 0.8403599041500521, "learning_rate": 1.3088984742382395e-05, "loss": 0.6234, "step": 2173 }, { "epoch": 0.42, "grad_norm": 1.048041958767155, "learning_rate": 1.3083058016364972e-05, "loss": 0.8542, "step": 2174 }, { "epoch": 0.42, "grad_norm": 1.1846075806883716, "learning_rate": 1.3077130093398274e-05, "loss": 0.9023, "step": 2175 }, { "epoch": 0.42, "grad_norm": 0.9966795932912511, "learning_rate": 1.3071200975783725e-05, "loss": 0.8159, "step": 2176 }, { "epoch": 0.42, "grad_norm": 1.1441359866788336, "learning_rate": 1.3065270665823206e-05, "loss": 0.8789, "step": 2177 }, { "epoch": 0.42, "grad_norm": 0.7407823909758479, "learning_rate": 1.3059339165819082e-05, "loss": 0.564, "step": 2178 }, { "epoch": 0.42, "grad_norm": 1.3159910730215691, "learning_rate": 1.3053406478074155e-05, "loss": 0.9351, "step": 2179 }, { "epoch": 0.42, "grad_norm": 1.089595018245111, "learning_rate": 1.3047472604891701e-05, "loss": 0.9082, "step": 2180 }, { "epoch": 0.42, "grad_norm": 1.0774110100520373, "learning_rate": 1.3041537548575455e-05, "loss": 0.9116, "step": 2181 }, { "epoch": 0.42, "grad_norm": 1.040878232259566, "learning_rate": 1.303560131142961e-05, "loss": 0.9089, "step": 2182 }, { "epoch": 0.42, "grad_norm": 1.0062374542130617, "learning_rate": 1.3029663895758814e-05, "loss": 0.9026, "step": 2183 }, { "epoch": 0.42, "grad_norm": 1.1231326359677063, "learning_rate": 1.3023725303868183e-05, "loss": 0.9534, "step": 2184 }, { "epoch": 0.42, "grad_norm": 1.0515390664960693, "learning_rate": 1.3017785538063277e-05, "loss": 0.8843, "step": 2185 }, { "epoch": 0.42, "grad_norm": 0.9241063377518862, "learning_rate": 1.3011844600650121e-05, "loss": 0.8809, "step": 2186 }, { "epoch": 0.42, "grad_norm": 0.9478510736066846, "learning_rate": 1.300590249393519e-05, "loss": 0.8943, "step": 2187 }, { "epoch": 0.42, "grad_norm": 1.1275849087875227, "learning_rate": 1.2999959220225416e-05, "loss": 0.8848, "step": 2188 }, { "epoch": 0.42, "grad_norm": 0.9348076946903902, "learning_rate": 1.299401478182818e-05, "loss": 0.874, "step": 2189 }, { "epoch": 0.42, "grad_norm": 1.018046019141893, "learning_rate": 1.2988069181051314e-05, "loss": 0.9246, "step": 2190 }, { "epoch": 0.42, "grad_norm": 1.0234423047600867, "learning_rate": 1.2982122420203114e-05, "loss": 0.8225, "step": 2191 }, { "epoch": 0.42, "grad_norm": 1.142805146013942, "learning_rate": 1.2976174501592313e-05, "loss": 0.9221, "step": 2192 }, { "epoch": 0.42, "grad_norm": 0.9332750492963302, "learning_rate": 1.2970225427528098e-05, "loss": 0.6277, "step": 2193 }, { "epoch": 0.42, "grad_norm": 1.0717937146720058, "learning_rate": 1.2964275200320104e-05, "loss": 0.8918, "step": 2194 }, { "epoch": 0.42, "grad_norm": 0.8155473664166523, "learning_rate": 1.2958323822278413e-05, "loss": 0.6381, "step": 2195 }, { "epoch": 0.42, "grad_norm": 1.1546539884394986, "learning_rate": 1.2952371295713558e-05, "loss": 0.8696, "step": 2196 }, { "epoch": 0.42, "grad_norm": 1.1384162204838368, "learning_rate": 1.2946417622936512e-05, "loss": 0.9319, "step": 2197 }, { "epoch": 0.42, "grad_norm": 1.2830492316389714, "learning_rate": 1.2940462806258696e-05, "loss": 0.9414, "step": 2198 }, { "epoch": 0.42, "grad_norm": 1.0987230282935818, "learning_rate": 1.2934506847991976e-05, "loss": 0.9233, "step": 2199 }, { "epoch": 0.42, "grad_norm": 1.0897368779046144, "learning_rate": 1.2928549750448661e-05, "loss": 0.8794, "step": 2200 }, { "epoch": 0.42, "grad_norm": 1.0628360970970339, "learning_rate": 1.2922591515941498e-05, "loss": 0.7964, "step": 2201 }, { "epoch": 0.42, "grad_norm": 1.1076028682675778, "learning_rate": 1.2916632146783683e-05, "loss": 0.8191, "step": 2202 }, { "epoch": 0.42, "grad_norm": 0.9905333587247978, "learning_rate": 1.2910671645288841e-05, "loss": 0.8826, "step": 2203 }, { "epoch": 0.42, "grad_norm": 0.9567840342023275, "learning_rate": 1.2904710013771054e-05, "loss": 0.8049, "step": 2204 }, { "epoch": 0.42, "grad_norm": 1.0193185611829185, "learning_rate": 1.2898747254544826e-05, "loss": 0.9343, "step": 2205 }, { "epoch": 0.42, "grad_norm": 1.025810238947178, "learning_rate": 1.2892783369925105e-05, "loss": 0.835, "step": 2206 }, { "epoch": 0.42, "grad_norm": 0.9585572197497209, "learning_rate": 1.2886818362227283e-05, "loss": 0.8948, "step": 2207 }, { "epoch": 0.42, "grad_norm": 1.013610743597695, "learning_rate": 1.2880852233767174e-05, "loss": 0.906, "step": 2208 }, { "epoch": 0.42, "grad_norm": 0.8662301881751905, "learning_rate": 1.2874884986861038e-05, "loss": 0.5972, "step": 2209 }, { "epoch": 0.43, "grad_norm": 1.0296754638434396, "learning_rate": 1.2868916623825561e-05, "loss": 0.9106, "step": 2210 }, { "epoch": 0.43, "grad_norm": 1.0371119753756495, "learning_rate": 1.2862947146977876e-05, "loss": 0.9001, "step": 2211 }, { "epoch": 0.43, "grad_norm": 1.049829760296399, "learning_rate": 1.2856976558635532e-05, "loss": 0.9341, "step": 2212 }, { "epoch": 0.43, "grad_norm": 1.268364293682499, "learning_rate": 1.2851004861116519e-05, "loss": 0.9221, "step": 2213 }, { "epoch": 0.43, "grad_norm": 0.9207560998364341, "learning_rate": 1.2845032056739257e-05, "loss": 0.9097, "step": 2214 }, { "epoch": 0.43, "grad_norm": 0.9568407916539443, "learning_rate": 1.2839058147822595e-05, "loss": 0.8867, "step": 2215 }, { "epoch": 0.43, "grad_norm": 0.9502918320824354, "learning_rate": 1.2833083136685803e-05, "loss": 0.9036, "step": 2216 }, { "epoch": 0.43, "grad_norm": 1.09884536891009, "learning_rate": 1.2827107025648595e-05, "loss": 0.8955, "step": 2217 }, { "epoch": 0.43, "grad_norm": 1.2772987030409646, "learning_rate": 1.2821129817031099e-05, "loss": 0.8835, "step": 2218 }, { "epoch": 0.43, "grad_norm": 0.9730214196839537, "learning_rate": 1.2815151513153874e-05, "loss": 0.9541, "step": 2219 }, { "epoch": 0.43, "grad_norm": 0.9719972374336514, "learning_rate": 1.2809172116337903e-05, "loss": 0.9348, "step": 2220 }, { "epoch": 0.43, "grad_norm": 0.9155292939483216, "learning_rate": 1.2803191628904594e-05, "loss": 0.9202, "step": 2221 }, { "epoch": 0.43, "grad_norm": 0.9908306059254722, "learning_rate": 1.2797210053175779e-05, "loss": 0.8582, "step": 2222 }, { "epoch": 0.43, "grad_norm": 0.9642092160492044, "learning_rate": 1.2791227391473706e-05, "loss": 0.9172, "step": 2223 }, { "epoch": 0.43, "grad_norm": 1.1556465325614378, "learning_rate": 1.2785243646121059e-05, "loss": 0.8708, "step": 2224 }, { "epoch": 0.43, "grad_norm": 1.0158702028219018, "learning_rate": 1.277925881944093e-05, "loss": 0.9214, "step": 2225 }, { "epoch": 0.43, "grad_norm": 1.0749837241008013, "learning_rate": 1.2773272913756833e-05, "loss": 0.9011, "step": 2226 }, { "epoch": 0.43, "grad_norm": 0.989766564366874, "learning_rate": 1.2767285931392705e-05, "loss": 0.8677, "step": 2227 }, { "epoch": 0.43, "grad_norm": 0.9793782270110722, "learning_rate": 1.27612978746729e-05, "loss": 0.6337, "step": 2228 }, { "epoch": 0.43, "grad_norm": 0.8223150916861831, "learning_rate": 1.2755308745922182e-05, "loss": 0.6296, "step": 2229 }, { "epoch": 0.43, "grad_norm": 1.0167708257145924, "learning_rate": 1.2749318547465742e-05, "loss": 0.9082, "step": 2230 }, { "epoch": 0.43, "grad_norm": 1.0091660984538942, "learning_rate": 1.2743327281629181e-05, "loss": 0.887, "step": 2231 }, { "epoch": 0.43, "grad_norm": 1.0850994715244655, "learning_rate": 1.2737334950738512e-05, "loss": 0.874, "step": 2232 }, { "epoch": 0.43, "grad_norm": 1.0282906847722246, "learning_rate": 1.273134155712017e-05, "loss": 0.8499, "step": 2233 }, { "epoch": 0.43, "grad_norm": 1.130250227915469, "learning_rate": 1.272534710310099e-05, "loss": 0.9712, "step": 2234 }, { "epoch": 0.43, "grad_norm": 0.9444914718572602, "learning_rate": 1.2719351591008228e-05, "loss": 0.8389, "step": 2235 }, { "epoch": 0.43, "grad_norm": 0.8200445577716899, "learning_rate": 1.2713355023169547e-05, "loss": 0.5933, "step": 2236 }, { "epoch": 0.43, "grad_norm": 1.059971774203841, "learning_rate": 1.2707357401913022e-05, "loss": 0.9326, "step": 2237 }, { "epoch": 0.43, "grad_norm": 0.972297146634107, "learning_rate": 1.270135872956714e-05, "loss": 0.8865, "step": 2238 }, { "epoch": 0.43, "grad_norm": 1.0953737498442775, "learning_rate": 1.2695359008460785e-05, "loss": 0.8899, "step": 2239 }, { "epoch": 0.43, "grad_norm": 0.976038307409051, "learning_rate": 1.2689358240923264e-05, "loss": 0.9329, "step": 2240 }, { "epoch": 0.43, "grad_norm": 1.0736976011778718, "learning_rate": 1.2683356429284273e-05, "loss": 0.947, "step": 2241 }, { "epoch": 0.43, "grad_norm": 1.0800425674955967, "learning_rate": 1.2677353575873926e-05, "loss": 0.885, "step": 2242 }, { "epoch": 0.43, "grad_norm": 1.0485085109376338, "learning_rate": 1.2671349683022736e-05, "loss": 0.9421, "step": 2243 }, { "epoch": 0.43, "grad_norm": 0.9376268196755465, "learning_rate": 1.2665344753061622e-05, "loss": 0.6255, "step": 2244 }, { "epoch": 0.43, "grad_norm": 1.209226058751057, "learning_rate": 1.2659338788321904e-05, "loss": 0.9272, "step": 2245 }, { "epoch": 0.43, "grad_norm": 0.9580723928369057, "learning_rate": 1.2653331791135308e-05, "loss": 0.8591, "step": 2246 }, { "epoch": 0.43, "grad_norm": 1.0068736596538104, "learning_rate": 1.2647323763833952e-05, "loss": 0.9407, "step": 2247 }, { "epoch": 0.43, "grad_norm": 1.018027127489327, "learning_rate": 1.264131470875036e-05, "loss": 0.8816, "step": 2248 }, { "epoch": 0.43, "grad_norm": 0.9743473390175105, "learning_rate": 1.2635304628217452e-05, "loss": 0.845, "step": 2249 }, { "epoch": 0.43, "grad_norm": 1.0016939816152153, "learning_rate": 1.2629293524568555e-05, "loss": 0.9475, "step": 2250 }, { "epoch": 0.43, "grad_norm": 1.0442008168830996, "learning_rate": 1.2623281400137383e-05, "loss": 0.8594, "step": 2251 }, { "epoch": 0.43, "grad_norm": 0.9688272257949043, "learning_rate": 1.2617268257258051e-05, "loss": 0.9065, "step": 2252 }, { "epoch": 0.43, "grad_norm": 0.8922752829420129, "learning_rate": 1.2611254098265063e-05, "loss": 0.8271, "step": 2253 }, { "epoch": 0.43, "grad_norm": 0.8303809771913588, "learning_rate": 1.2605238925493326e-05, "loss": 0.5854, "step": 2254 }, { "epoch": 0.43, "grad_norm": 1.0040362029070558, "learning_rate": 1.2599222741278136e-05, "loss": 0.9211, "step": 2255 }, { "epoch": 0.43, "grad_norm": 0.9528895285356438, "learning_rate": 1.2593205547955185e-05, "loss": 0.9102, "step": 2256 }, { "epoch": 0.43, "grad_norm": 0.9823280602751767, "learning_rate": 1.2587187347860554e-05, "loss": 0.8269, "step": 2257 }, { "epoch": 0.43, "grad_norm": 1.063457260052994, "learning_rate": 1.2581168143330716e-05, "loss": 0.824, "step": 2258 }, { "epoch": 0.43, "grad_norm": 0.7705191528612294, "learning_rate": 1.2575147936702531e-05, "loss": 0.603, "step": 2259 }, { "epoch": 0.43, "grad_norm": 0.869583504196847, "learning_rate": 1.2569126730313255e-05, "loss": 0.6201, "step": 2260 }, { "epoch": 0.43, "grad_norm": 0.9923054761563982, "learning_rate": 1.2563104526500523e-05, "loss": 0.915, "step": 2261 }, { "epoch": 0.44, "grad_norm": 0.7826373992439639, "learning_rate": 1.2557081327602361e-05, "loss": 0.6157, "step": 2262 }, { "epoch": 0.44, "grad_norm": 1.04163434355972, "learning_rate": 1.2551057135957187e-05, "loss": 0.9045, "step": 2263 }, { "epoch": 0.44, "grad_norm": 0.9704874900613966, "learning_rate": 1.2545031953903796e-05, "loss": 0.8408, "step": 2264 }, { "epoch": 0.44, "grad_norm": 0.9639378560894675, "learning_rate": 1.2539005783781374e-05, "loss": 0.8796, "step": 2265 }, { "epoch": 0.44, "grad_norm": 0.9462329564424142, "learning_rate": 1.2532978627929486e-05, "loss": 0.957, "step": 2266 }, { "epoch": 0.44, "grad_norm": 1.094606275100762, "learning_rate": 1.2526950488688083e-05, "loss": 0.9551, "step": 2267 }, { "epoch": 0.44, "grad_norm": 1.0533702669087701, "learning_rate": 1.2520921368397492e-05, "loss": 0.9265, "step": 2268 }, { "epoch": 0.44, "grad_norm": 0.9675130894497306, "learning_rate": 1.2514891269398429e-05, "loss": 0.8701, "step": 2269 }, { "epoch": 0.44, "grad_norm": 1.0848668428472956, "learning_rate": 1.2508860194031986e-05, "loss": 0.9355, "step": 2270 }, { "epoch": 0.44, "grad_norm": 1.1110158537711619, "learning_rate": 1.2502828144639629e-05, "loss": 0.8323, "step": 2271 }, { "epoch": 0.44, "grad_norm": 1.0007873284176159, "learning_rate": 1.2496795123563218e-05, "loss": 0.9041, "step": 2272 }, { "epoch": 0.44, "grad_norm": 1.0980606869738458, "learning_rate": 1.249076113314497e-05, "loss": 0.8943, "step": 2273 }, { "epoch": 0.44, "grad_norm": 1.1435796163237786, "learning_rate": 1.248472617572749e-05, "loss": 0.866, "step": 2274 }, { "epoch": 0.44, "grad_norm": 1.0303623472964583, "learning_rate": 1.2478690253653756e-05, "loss": 0.9199, "step": 2275 }, { "epoch": 0.44, "grad_norm": 1.0127715702369249, "learning_rate": 1.2472653369267122e-05, "loss": 0.918, "step": 2276 }, { "epoch": 0.44, "grad_norm": 1.0244450712192859, "learning_rate": 1.2466615524911316e-05, "loss": 0.8738, "step": 2277 }, { "epoch": 0.44, "grad_norm": 1.1272774183063028, "learning_rate": 1.2460576722930432e-05, "loss": 0.8972, "step": 2278 }, { "epoch": 0.44, "grad_norm": 1.0552766287033655, "learning_rate": 1.2454536965668949e-05, "loss": 0.8799, "step": 2279 }, { "epoch": 0.44, "grad_norm": 0.979954602784457, "learning_rate": 1.24484962554717e-05, "loss": 0.8831, "step": 2280 }, { "epoch": 0.44, "grad_norm": 1.0634495989653932, "learning_rate": 1.24424545946839e-05, "loss": 0.8948, "step": 2281 }, { "epoch": 0.44, "grad_norm": 0.9975338086462926, "learning_rate": 1.2436411985651131e-05, "loss": 0.9102, "step": 2282 }, { "epoch": 0.44, "grad_norm": 0.9033936490111246, "learning_rate": 1.2430368430719342e-05, "loss": 0.8562, "step": 2283 }, { "epoch": 0.44, "grad_norm": 1.0146215529822402, "learning_rate": 1.242432393223485e-05, "loss": 0.917, "step": 2284 }, { "epoch": 0.44, "grad_norm": 0.7802382360975703, "learning_rate": 1.2418278492544328e-05, "loss": 0.6277, "step": 2285 }, { "epoch": 0.44, "grad_norm": 0.9681703228119949, "learning_rate": 1.2412232113994841e-05, "loss": 0.8704, "step": 2286 }, { "epoch": 0.44, "grad_norm": 1.0044385199633985, "learning_rate": 1.2406184798933786e-05, "loss": 0.8726, "step": 2287 }, { "epoch": 0.44, "grad_norm": 1.0569694953875566, "learning_rate": 1.2400136549708945e-05, "loss": 0.8833, "step": 2288 }, { "epoch": 0.44, "grad_norm": 0.9080954384026767, "learning_rate": 1.239408736866846e-05, "loss": 0.8784, "step": 2289 }, { "epoch": 0.44, "grad_norm": 0.9038578431690704, "learning_rate": 1.2388037258160823e-05, "loss": 0.6353, "step": 2290 }, { "epoch": 0.44, "grad_norm": 1.0903873160525839, "learning_rate": 1.23819862205349e-05, "loss": 0.9067, "step": 2291 }, { "epoch": 0.44, "grad_norm": 1.0288390959394371, "learning_rate": 1.2375934258139917e-05, "loss": 0.9084, "step": 2292 }, { "epoch": 0.44, "grad_norm": 1.1243984672242793, "learning_rate": 1.2369881373325448e-05, "loss": 0.8481, "step": 2293 }, { "epoch": 0.44, "grad_norm": 1.066762207607063, "learning_rate": 1.236382756844143e-05, "loss": 0.8916, "step": 2294 }, { "epoch": 0.44, "grad_norm": 0.9193873043076916, "learning_rate": 1.2357772845838159e-05, "loss": 0.6447, "step": 2295 }, { "epoch": 0.44, "grad_norm": 0.9761348976721848, "learning_rate": 1.2351717207866292e-05, "loss": 0.9097, "step": 2296 }, { "epoch": 0.44, "grad_norm": 0.9986188186628963, "learning_rate": 1.2345660656876832e-05, "loss": 0.9441, "step": 2297 }, { "epoch": 0.44, "grad_norm": 0.9859798619151758, "learning_rate": 1.233960319522114e-05, "loss": 0.8713, "step": 2298 }, { "epoch": 0.44, "grad_norm": 1.0503786771200463, "learning_rate": 1.2333544825250938e-05, "loss": 0.8376, "step": 2299 }, { "epoch": 0.44, "grad_norm": 1.0307674032837915, "learning_rate": 1.2327485549318285e-05, "loss": 0.9075, "step": 2300 }, { "epoch": 0.44, "grad_norm": 1.9690033866915921, "learning_rate": 1.2321425369775601e-05, "loss": 0.9131, "step": 2301 }, { "epoch": 0.44, "grad_norm": 0.9055576269324204, "learning_rate": 1.2315364288975665e-05, "loss": 0.6766, "step": 2302 }, { "epoch": 0.44, "grad_norm": 0.9920602417889188, "learning_rate": 1.2309302309271587e-05, "loss": 0.8591, "step": 2303 }, { "epoch": 0.44, "grad_norm": 0.9837724922266031, "learning_rate": 1.2303239433016842e-05, "loss": 0.9116, "step": 2304 }, { "epoch": 0.44, "grad_norm": 1.0154472649467747, "learning_rate": 1.2297175662565248e-05, "loss": 0.9041, "step": 2305 }, { "epoch": 0.44, "grad_norm": 1.0570140087907702, "learning_rate": 1.229111100027097e-05, "loss": 0.9553, "step": 2306 }, { "epoch": 0.44, "grad_norm": 0.9883644804944408, "learning_rate": 1.228504544848851e-05, "loss": 0.8337, "step": 2307 }, { "epoch": 0.44, "grad_norm": 0.9754997977660478, "learning_rate": 1.2278979009572736e-05, "loss": 0.9067, "step": 2308 }, { "epoch": 0.44, "grad_norm": 1.1098200894102344, "learning_rate": 1.2272911685878841e-05, "loss": 0.9092, "step": 2309 }, { "epoch": 0.44, "grad_norm": 1.1182844984169418, "learning_rate": 1.2266843479762372e-05, "loss": 0.9075, "step": 2310 }, { "epoch": 0.44, "grad_norm": 0.9643545015547526, "learning_rate": 1.2260774393579209e-05, "loss": 0.927, "step": 2311 }, { "epoch": 0.44, "grad_norm": 1.1586448851593005, "learning_rate": 1.2254704429685593e-05, "loss": 0.8538, "step": 2312 }, { "epoch": 0.44, "grad_norm": 1.099051500860053, "learning_rate": 1.2248633590438084e-05, "loss": 0.9497, "step": 2313 }, { "epoch": 0.45, "grad_norm": 1.0449565877228897, "learning_rate": 1.2242561878193589e-05, "loss": 0.8735, "step": 2314 }, { "epoch": 0.45, "grad_norm": 1.0192998341662651, "learning_rate": 1.2236489295309362e-05, "loss": 0.8367, "step": 2315 }, { "epoch": 0.45, "grad_norm": 1.3679379722933438, "learning_rate": 1.2230415844142984e-05, "loss": 0.9622, "step": 2316 }, { "epoch": 0.45, "grad_norm": 0.9951181078327255, "learning_rate": 1.2224341527052378e-05, "loss": 0.8889, "step": 2317 }, { "epoch": 0.45, "grad_norm": 1.164445959527902, "learning_rate": 1.2218266346395811e-05, "loss": 0.8728, "step": 2318 }, { "epoch": 0.45, "grad_norm": 0.8725297965264639, "learning_rate": 1.221219030453187e-05, "loss": 0.8447, "step": 2319 }, { "epoch": 0.45, "grad_norm": 1.0162001010863948, "learning_rate": 1.220611340381948e-05, "loss": 0.887, "step": 2320 }, { "epoch": 0.45, "grad_norm": 0.9807356180563647, "learning_rate": 1.2200035646617912e-05, "loss": 0.8809, "step": 2321 }, { "epoch": 0.45, "grad_norm": 0.8646581917161508, "learning_rate": 1.2193957035286757e-05, "loss": 0.6635, "step": 2322 }, { "epoch": 0.45, "grad_norm": 1.0361148158981435, "learning_rate": 1.2187877572185937e-05, "loss": 0.8774, "step": 2323 }, { "epoch": 0.45, "grad_norm": 1.1157858125353375, "learning_rate": 1.2181797259675713e-05, "loss": 0.8447, "step": 2324 }, { "epoch": 0.45, "grad_norm": 0.8205559411878707, "learning_rate": 1.2175716100116677e-05, "loss": 0.6125, "step": 2325 }, { "epoch": 0.45, "grad_norm": 1.0668617880748446, "learning_rate": 1.2169634095869736e-05, "loss": 0.897, "step": 2326 }, { "epoch": 0.45, "grad_norm": 1.0010781323841398, "learning_rate": 1.2163551249296132e-05, "loss": 0.866, "step": 2327 }, { "epoch": 0.45, "grad_norm": 0.9423774583199944, "learning_rate": 1.2157467562757443e-05, "loss": 0.9082, "step": 2328 }, { "epoch": 0.45, "grad_norm": 0.9944515909424286, "learning_rate": 1.2151383038615563e-05, "loss": 0.9016, "step": 2329 }, { "epoch": 0.45, "grad_norm": 1.1425699677950514, "learning_rate": 1.214529767923271e-05, "loss": 0.885, "step": 2330 }, { "epoch": 0.45, "grad_norm": 0.9423803219490544, "learning_rate": 1.2139211486971436e-05, "loss": 0.8909, "step": 2331 }, { "epoch": 0.45, "grad_norm": 0.9792053391191239, "learning_rate": 1.213312446419461e-05, "loss": 0.8857, "step": 2332 }, { "epoch": 0.45, "grad_norm": 1.0106359910922058, "learning_rate": 1.2127036613265418e-05, "loss": 0.8887, "step": 2333 }, { "epoch": 0.45, "grad_norm": 0.990151897546967, "learning_rate": 1.2120947936547375e-05, "loss": 0.8586, "step": 2334 }, { "epoch": 0.45, "grad_norm": 1.0320396557502782, "learning_rate": 1.2114858436404322e-05, "loss": 0.8943, "step": 2335 }, { "epoch": 0.45, "grad_norm": 1.0135312781052888, "learning_rate": 1.2108768115200405e-05, "loss": 0.8975, "step": 2336 }, { "epoch": 0.45, "grad_norm": 0.8150236455106914, "learning_rate": 1.2102676975300095e-05, "loss": 0.5607, "step": 2337 }, { "epoch": 0.45, "grad_norm": 1.0832436947940876, "learning_rate": 1.209658501906819e-05, "loss": 0.9001, "step": 2338 }, { "epoch": 0.45, "grad_norm": 1.2240403918690985, "learning_rate": 1.2090492248869795e-05, "loss": 0.9375, "step": 2339 }, { "epoch": 0.45, "grad_norm": 0.8385852785781611, "learning_rate": 1.2084398667070325e-05, "loss": 0.6486, "step": 2340 }, { "epoch": 0.45, "grad_norm": 0.9847187848538509, "learning_rate": 1.2078304276035527e-05, "loss": 0.8555, "step": 2341 }, { "epoch": 0.45, "grad_norm": 1.2003843687808724, "learning_rate": 1.2072209078131451e-05, "loss": 0.9617, "step": 2342 }, { "epoch": 0.45, "grad_norm": 0.9827390015786835, "learning_rate": 1.2066113075724461e-05, "loss": 0.8484, "step": 2343 }, { "epoch": 0.45, "grad_norm": 1.0400004442414894, "learning_rate": 1.206001627118124e-05, "loss": 0.8621, "step": 2344 }, { "epoch": 0.45, "grad_norm": 1.0154259752622832, "learning_rate": 1.2053918666868776e-05, "loss": 0.8474, "step": 2345 }, { "epoch": 0.45, "grad_norm": 1.1266866551559958, "learning_rate": 1.2047820265154362e-05, "loss": 0.9004, "step": 2346 }, { "epoch": 0.45, "grad_norm": 0.9883508598838142, "learning_rate": 1.2041721068405614e-05, "loss": 0.8828, "step": 2347 }, { "epoch": 0.45, "grad_norm": 0.9996767710282979, "learning_rate": 1.203562107899045e-05, "loss": 0.8967, "step": 2348 }, { "epoch": 0.45, "grad_norm": 1.228825128379329, "learning_rate": 1.2029520299277095e-05, "loss": 0.9905, "step": 2349 }, { "epoch": 0.45, "grad_norm": 0.9419904991706621, "learning_rate": 1.2023418731634078e-05, "loss": 0.8328, "step": 2350 }, { "epoch": 0.45, "grad_norm": 0.9914208450644649, "learning_rate": 1.2017316378430244e-05, "loss": 0.8979, "step": 2351 }, { "epoch": 0.45, "grad_norm": 1.0407917712885613, "learning_rate": 1.2011213242034733e-05, "loss": 0.8513, "step": 2352 }, { "epoch": 0.45, "grad_norm": 1.1092344891020862, "learning_rate": 1.2005109324816992e-05, "loss": 0.8643, "step": 2353 }, { "epoch": 0.45, "grad_norm": 0.9435974009859814, "learning_rate": 1.1999004629146775e-05, "loss": 0.8394, "step": 2354 }, { "epoch": 0.45, "grad_norm": 0.9823586217707669, "learning_rate": 1.1992899157394133e-05, "loss": 0.9092, "step": 2355 }, { "epoch": 0.45, "grad_norm": 0.8921971160041439, "learning_rate": 1.1986792911929418e-05, "loss": 0.6381, "step": 2356 }, { "epoch": 0.45, "grad_norm": 1.0701058840498436, "learning_rate": 1.198068589512329e-05, "loss": 0.9124, "step": 2357 }, { "epoch": 0.45, "grad_norm": 1.07034260188013, "learning_rate": 1.1974578109346702e-05, "loss": 0.8699, "step": 2358 }, { "epoch": 0.45, "grad_norm": 0.8474429486794854, "learning_rate": 1.1968469556970905e-05, "loss": 0.6251, "step": 2359 }, { "epoch": 0.45, "grad_norm": 1.1869185994513347, "learning_rate": 1.1962360240367445e-05, "loss": 0.8818, "step": 2360 }, { "epoch": 0.45, "grad_norm": 0.910201394410448, "learning_rate": 1.1956250161908179e-05, "loss": 0.6259, "step": 2361 }, { "epoch": 0.45, "grad_norm": 0.9995040892098774, "learning_rate": 1.195013932396524e-05, "loss": 0.9163, "step": 2362 }, { "epoch": 0.45, "grad_norm": 1.059244389222281, "learning_rate": 1.1944027728911072e-05, "loss": 0.9395, "step": 2363 }, { "epoch": 0.45, "grad_norm": 1.010468182072923, "learning_rate": 1.1937915379118406e-05, "loss": 0.8794, "step": 2364 }, { "epoch": 0.45, "grad_norm": 0.8328873414738919, "learning_rate": 1.1931802276960265e-05, "loss": 0.6481, "step": 2365 }, { "epoch": 0.46, "grad_norm": 1.0723836040038832, "learning_rate": 1.1925688424809965e-05, "loss": 0.9224, "step": 2366 }, { "epoch": 0.46, "grad_norm": 1.0500107999779102, "learning_rate": 1.1919573825041115e-05, "loss": 0.8616, "step": 2367 }, { "epoch": 0.46, "grad_norm": 1.027274894242625, "learning_rate": 1.1913458480027614e-05, "loss": 0.8882, "step": 2368 }, { "epoch": 0.46, "grad_norm": 1.0095310798843995, "learning_rate": 1.1907342392143646e-05, "loss": 0.9272, "step": 2369 }, { "epoch": 0.46, "grad_norm": 1.145824141944159, "learning_rate": 1.1901225563763694e-05, "loss": 0.9373, "step": 2370 }, { "epoch": 0.46, "grad_norm": 0.9947794157562887, "learning_rate": 1.1895107997262516e-05, "loss": 0.9116, "step": 2371 }, { "epoch": 0.46, "grad_norm": 0.9292355660352103, "learning_rate": 1.1888989695015166e-05, "loss": 0.8525, "step": 2372 }, { "epoch": 0.46, "grad_norm": 0.9433410678048716, "learning_rate": 1.1882870659396968e-05, "loss": 0.8623, "step": 2373 }, { "epoch": 0.46, "grad_norm": 1.043050181387936, "learning_rate": 1.1876750892783558e-05, "loss": 0.9246, "step": 2374 }, { "epoch": 0.46, "grad_norm": 1.0766295856884653, "learning_rate": 1.1870630397550831e-05, "loss": 0.8562, "step": 2375 }, { "epoch": 0.46, "grad_norm": 1.0273360880549716, "learning_rate": 1.1864509176074974e-05, "loss": 0.9509, "step": 2376 }, { "epoch": 0.46, "grad_norm": 1.168208841538064, "learning_rate": 1.185838723073246e-05, "loss": 0.8717, "step": 2377 }, { "epoch": 0.46, "grad_norm": 1.040011210135805, "learning_rate": 1.1852264563900038e-05, "loss": 0.8137, "step": 2378 }, { "epoch": 0.46, "grad_norm": 0.9716638585339682, "learning_rate": 1.1846141177954733e-05, "loss": 0.9197, "step": 2379 }, { "epoch": 0.46, "grad_norm": 0.9754553522863282, "learning_rate": 1.1840017075273861e-05, "loss": 0.9255, "step": 2380 }, { "epoch": 0.46, "grad_norm": 1.0628179038861911, "learning_rate": 1.1833892258235008e-05, "loss": 0.8678, "step": 2381 }, { "epoch": 0.46, "grad_norm": 1.1000641251764907, "learning_rate": 1.1827766729216035e-05, "loss": 0.9341, "step": 2382 }, { "epoch": 0.46, "grad_norm": 1.0133540289360798, "learning_rate": 1.1821640490595086e-05, "loss": 0.8909, "step": 2383 }, { "epoch": 0.46, "grad_norm": 1.035341321285203, "learning_rate": 1.181551354475058e-05, "loss": 0.8811, "step": 2384 }, { "epoch": 0.46, "grad_norm": 0.9760827655236758, "learning_rate": 1.1809385894061206e-05, "loss": 0.856, "step": 2385 }, { "epoch": 0.46, "grad_norm": 0.8126133601263515, "learning_rate": 1.1803257540905926e-05, "loss": 0.6389, "step": 2386 }, { "epoch": 0.46, "grad_norm": 1.1023569722205508, "learning_rate": 1.1797128487663982e-05, "loss": 0.9343, "step": 2387 }, { "epoch": 0.46, "grad_norm": 0.8043091942854352, "learning_rate": 1.1790998736714882e-05, "loss": 0.6401, "step": 2388 }, { "epoch": 0.46, "grad_norm": 0.8798459038153839, "learning_rate": 1.1784868290438404e-05, "loss": 0.8198, "step": 2389 }, { "epoch": 0.46, "grad_norm": 1.0852598285916792, "learning_rate": 1.1778737151214606e-05, "loss": 0.9177, "step": 2390 }, { "epoch": 0.46, "grad_norm": 1.0499250134552383, "learning_rate": 1.17726053214238e-05, "loss": 0.9292, "step": 2391 }, { "epoch": 0.46, "grad_norm": 0.842456825011241, "learning_rate": 1.1766472803446577e-05, "loss": 0.6923, "step": 2392 }, { "epoch": 0.46, "grad_norm": 1.2983979513070505, "learning_rate": 1.1760339599663788e-05, "loss": 0.9385, "step": 2393 }, { "epoch": 0.46, "grad_norm": 1.009091816973494, "learning_rate": 1.1754205712456556e-05, "loss": 0.9246, "step": 2394 }, { "epoch": 0.46, "grad_norm": 0.9612550620227424, "learning_rate": 1.1748071144206266e-05, "loss": 0.8706, "step": 2395 }, { "epoch": 0.46, "grad_norm": 0.9872119937401814, "learning_rate": 1.1741935897294572e-05, "loss": 0.8647, "step": 2396 }, { "epoch": 0.46, "grad_norm": 0.9631678998587736, "learning_rate": 1.1735799974103388e-05, "loss": 0.885, "step": 2397 }, { "epoch": 0.46, "grad_norm": 0.9426517908143229, "learning_rate": 1.1729663377014888e-05, "loss": 0.8538, "step": 2398 }, { "epoch": 0.46, "grad_norm": 1.1143384481368275, "learning_rate": 1.172352610841151e-05, "loss": 0.8728, "step": 2399 }, { "epoch": 0.46, "grad_norm": 1.0996169298363052, "learning_rate": 1.1717388170675954e-05, "loss": 0.9292, "step": 2400 }, { "epoch": 0.46, "grad_norm": 1.0311840150956495, "learning_rate": 1.1711249566191179e-05, "loss": 0.8796, "step": 2401 }, { "epoch": 0.46, "grad_norm": 1.1018279441466197, "learning_rate": 1.17051102973404e-05, "loss": 0.8892, "step": 2402 }, { "epoch": 0.46, "grad_norm": 0.9769321294064803, "learning_rate": 1.1698970366507096e-05, "loss": 0.9236, "step": 2403 }, { "epoch": 0.46, "grad_norm": 1.049726053664076, "learning_rate": 1.1692829776074999e-05, "loss": 0.8369, "step": 2404 }, { "epoch": 0.46, "grad_norm": 0.9587178732807213, "learning_rate": 1.1686688528428099e-05, "loss": 0.8555, "step": 2405 }, { "epoch": 0.46, "grad_norm": 0.9866994895172789, "learning_rate": 1.1680546625950635e-05, "loss": 0.9382, "step": 2406 }, { "epoch": 0.46, "grad_norm": 1.083148740851257, "learning_rate": 1.167440407102711e-05, "loss": 0.865, "step": 2407 }, { "epoch": 0.46, "grad_norm": 1.0318915943310962, "learning_rate": 1.1668260866042271e-05, "loss": 0.8774, "step": 2408 }, { "epoch": 0.46, "grad_norm": 1.3192717785768502, "learning_rate": 1.1662117013381126e-05, "loss": 0.8767, "step": 2409 }, { "epoch": 0.46, "grad_norm": 0.9450765689206515, "learning_rate": 1.1655972515428928e-05, "loss": 0.8806, "step": 2410 }, { "epoch": 0.46, "grad_norm": 1.0097012900548925, "learning_rate": 1.1649827374571182e-05, "loss": 0.9363, "step": 2411 }, { "epoch": 0.46, "grad_norm": 1.0750706285947578, "learning_rate": 1.1643681593193642e-05, "loss": 0.9028, "step": 2412 }, { "epoch": 0.46, "grad_norm": 1.0420422054895482, "learning_rate": 1.1637535173682318e-05, "loss": 0.8643, "step": 2413 }, { "epoch": 0.46, "grad_norm": 1.0459431488211106, "learning_rate": 1.1631388118423457e-05, "loss": 0.8818, "step": 2414 }, { "epoch": 0.46, "grad_norm": 1.0488948569921395, "learning_rate": 1.1625240429803553e-05, "loss": 0.9333, "step": 2415 }, { "epoch": 0.46, "grad_norm": 0.9726936423389347, "learning_rate": 1.1619092110209361e-05, "loss": 0.835, "step": 2416 }, { "epoch": 0.46, "grad_norm": 0.8850314686185883, "learning_rate": 1.1612943162027863e-05, "loss": 0.6353, "step": 2417 }, { "epoch": 0.47, "grad_norm": 1.0834325507030051, "learning_rate": 1.1606793587646295e-05, "loss": 0.8862, "step": 2418 }, { "epoch": 0.47, "grad_norm": 1.003730730751251, "learning_rate": 1.160064338945213e-05, "loss": 0.8533, "step": 2419 }, { "epoch": 0.47, "grad_norm": 1.1719016707882144, "learning_rate": 1.1594492569833093e-05, "loss": 0.9032, "step": 2420 }, { "epoch": 0.47, "grad_norm": 1.1439366091751604, "learning_rate": 1.1588341131177137e-05, "loss": 0.8982, "step": 2421 }, { "epoch": 0.47, "grad_norm": 1.124660929894064, "learning_rate": 1.1582189075872467e-05, "loss": 0.887, "step": 2422 }, { "epoch": 0.47, "grad_norm": 0.9222986555607066, "learning_rate": 1.1576036406307523e-05, "loss": 0.8636, "step": 2423 }, { "epoch": 0.47, "grad_norm": 1.0759676246831, "learning_rate": 1.156988312487098e-05, "loss": 0.8452, "step": 2424 }, { "epoch": 0.47, "grad_norm": 1.0618958534965415, "learning_rate": 1.1563729233951757e-05, "loss": 0.916, "step": 2425 }, { "epoch": 0.47, "grad_norm": 1.0794839367103441, "learning_rate": 1.1557574735939003e-05, "loss": 0.8474, "step": 2426 }, { "epoch": 0.47, "grad_norm": 0.9651257584484187, "learning_rate": 1.1551419633222107e-05, "loss": 0.8567, "step": 2427 }, { "epoch": 0.47, "grad_norm": 1.0596247643661276, "learning_rate": 1.1545263928190692e-05, "loss": 0.8816, "step": 2428 }, { "epoch": 0.47, "grad_norm": 1.0089091466525282, "learning_rate": 1.1539107623234618e-05, "loss": 0.8823, "step": 2429 }, { "epoch": 0.47, "grad_norm": 0.9729145680810111, "learning_rate": 1.153295072074397e-05, "loss": 0.8564, "step": 2430 }, { "epoch": 0.47, "grad_norm": 0.9311574224144511, "learning_rate": 1.1526793223109072e-05, "loss": 0.8347, "step": 2431 }, { "epoch": 0.47, "grad_norm": 1.0866499335259663, "learning_rate": 1.1520635132720475e-05, "loss": 0.9216, "step": 2432 }, { "epoch": 0.47, "grad_norm": 1.1280523175709902, "learning_rate": 1.1514476451968961e-05, "loss": 0.8384, "step": 2433 }, { "epoch": 0.47, "grad_norm": 0.9480075674833964, "learning_rate": 1.1508317183245545e-05, "loss": 0.8792, "step": 2434 }, { "epoch": 0.47, "grad_norm": 1.011418067429974, "learning_rate": 1.1502157328941466e-05, "loss": 0.9072, "step": 2435 }, { "epoch": 0.47, "grad_norm": 1.0257473369432306, "learning_rate": 1.149599689144819e-05, "loss": 0.8716, "step": 2436 }, { "epoch": 0.47, "grad_norm": 1.0395109461063372, "learning_rate": 1.1489835873157414e-05, "loss": 0.907, "step": 2437 }, { "epoch": 0.47, "grad_norm": 1.0275122790751494, "learning_rate": 1.1483674276461053e-05, "loss": 0.8821, "step": 2438 }, { "epoch": 0.47, "grad_norm": 1.0154194950614686, "learning_rate": 1.1477512103751254e-05, "loss": 0.8635, "step": 2439 }, { "epoch": 0.47, "grad_norm": 0.9636583290377346, "learning_rate": 1.1471349357420384e-05, "loss": 0.9031, "step": 2440 }, { "epoch": 0.47, "grad_norm": 0.9465523272135282, "learning_rate": 1.1465186039861033e-05, "loss": 0.8523, "step": 2441 }, { "epoch": 0.47, "grad_norm": 0.9860108582898498, "learning_rate": 1.1459022153466016e-05, "loss": 0.8925, "step": 2442 }, { "epoch": 0.47, "grad_norm": 0.8828414449651723, "learning_rate": 1.1452857700628362e-05, "loss": 0.8972, "step": 2443 }, { "epoch": 0.47, "grad_norm": 0.9417525350523362, "learning_rate": 1.1446692683741326e-05, "loss": 0.8784, "step": 2444 }, { "epoch": 0.47, "grad_norm": 0.9864727153881683, "learning_rate": 1.1440527105198377e-05, "loss": 0.8289, "step": 2445 }, { "epoch": 0.47, "grad_norm": 1.1855501020912356, "learning_rate": 1.143436096739321e-05, "loss": 0.8618, "step": 2446 }, { "epoch": 0.47, "grad_norm": 1.005492167665118, "learning_rate": 1.1428194272719729e-05, "loss": 0.812, "step": 2447 }, { "epoch": 0.47, "grad_norm": 1.0633572539091236, "learning_rate": 1.1422027023572052e-05, "loss": 0.8953, "step": 2448 }, { "epoch": 0.47, "grad_norm": 0.9465434150351557, "learning_rate": 1.1415859222344525e-05, "loss": 0.8574, "step": 2449 }, { "epoch": 0.47, "grad_norm": 0.967713336108048, "learning_rate": 1.14096908714317e-05, "loss": 0.876, "step": 2450 }, { "epoch": 0.47, "grad_norm": 0.9691026079794648, "learning_rate": 1.1403521973228342e-05, "loss": 0.8862, "step": 2451 }, { "epoch": 0.47, "grad_norm": 0.9889370809281708, "learning_rate": 1.1397352530129428e-05, "loss": 0.8911, "step": 2452 }, { "epoch": 0.47, "grad_norm": 1.1360471265662766, "learning_rate": 1.139118254453015e-05, "loss": 0.9032, "step": 2453 }, { "epoch": 0.47, "grad_norm": 1.0165684169675655, "learning_rate": 1.1385012018825907e-05, "loss": 0.8909, "step": 2454 }, { "epoch": 0.47, "grad_norm": 1.078338698833415, "learning_rate": 1.1378840955412313e-05, "loss": 0.8899, "step": 2455 }, { "epoch": 0.47, "grad_norm": 1.0012026280313602, "learning_rate": 1.1372669356685185e-05, "loss": 0.8928, "step": 2456 }, { "epoch": 0.47, "grad_norm": 1.0409650908885213, "learning_rate": 1.1366497225040549e-05, "loss": 0.8818, "step": 2457 }, { "epoch": 0.47, "grad_norm": 1.436807632860269, "learning_rate": 1.1360324562874643e-05, "loss": 0.8147, "step": 2458 }, { "epoch": 0.47, "grad_norm": 0.8316369220622983, "learning_rate": 1.1354151372583901e-05, "loss": 0.5857, "step": 2459 }, { "epoch": 0.47, "grad_norm": 0.9919230256941128, "learning_rate": 1.1347977656564974e-05, "loss": 0.8735, "step": 2460 }, { "epoch": 0.47, "grad_norm": 0.9902918789981372, "learning_rate": 1.1341803417214705e-05, "loss": 0.8643, "step": 2461 }, { "epoch": 0.47, "grad_norm": 1.0545738717522941, "learning_rate": 1.1335628656930153e-05, "loss": 0.9077, "step": 2462 }, { "epoch": 0.47, "grad_norm": 0.9679700946827386, "learning_rate": 1.132945337810857e-05, "loss": 0.8677, "step": 2463 }, { "epoch": 0.47, "grad_norm": 0.815386495759762, "learning_rate": 1.132327758314741e-05, "loss": 0.6373, "step": 2464 }, { "epoch": 0.47, "grad_norm": 0.8609815638831194, "learning_rate": 1.131710127444433e-05, "loss": 0.6448, "step": 2465 }, { "epoch": 0.47, "grad_norm": 1.0516220808110448, "learning_rate": 1.1310924454397187e-05, "loss": 0.8733, "step": 2466 }, { "epoch": 0.47, "grad_norm": 0.9944553941378559, "learning_rate": 1.1304747125404031e-05, "loss": 0.8589, "step": 2467 }, { "epoch": 0.47, "grad_norm": 1.212516700922103, "learning_rate": 1.129856928986312e-05, "loss": 0.8655, "step": 2468 }, { "epoch": 0.47, "grad_norm": 1.1055626766113957, "learning_rate": 1.12923909501729e-05, "loss": 0.9619, "step": 2469 }, { "epoch": 0.48, "grad_norm": 0.9766147561397213, "learning_rate": 1.1286212108732015e-05, "loss": 0.9045, "step": 2470 }, { "epoch": 0.48, "grad_norm": 1.0959370266968684, "learning_rate": 1.1280032767939302e-05, "loss": 0.8621, "step": 2471 }, { "epoch": 0.48, "grad_norm": 0.9470503749310395, "learning_rate": 1.1273852930193798e-05, "loss": 0.873, "step": 2472 }, { "epoch": 0.48, "grad_norm": 1.0321451146429226, "learning_rate": 1.1267672597894725e-05, "loss": 0.9297, "step": 2473 }, { "epoch": 0.48, "grad_norm": 0.8152387175538015, "learning_rate": 1.12614917734415e-05, "loss": 0.6761, "step": 2474 }, { "epoch": 0.48, "grad_norm": 1.2868000962821138, "learning_rate": 1.1255310459233737e-05, "loss": 0.9324, "step": 2475 }, { "epoch": 0.48, "grad_norm": 0.928103360783178, "learning_rate": 1.1249128657671233e-05, "loss": 0.8459, "step": 2476 }, { "epoch": 0.48, "grad_norm": 0.996852544603383, "learning_rate": 1.1242946371153974e-05, "loss": 0.8809, "step": 2477 }, { "epoch": 0.48, "grad_norm": 1.1647204511427558, "learning_rate": 1.1236763602082136e-05, "loss": 0.9375, "step": 2478 }, { "epoch": 0.48, "grad_norm": 0.9647275050114219, "learning_rate": 1.1230580352856088e-05, "loss": 0.8748, "step": 2479 }, { "epoch": 0.48, "grad_norm": 1.1532684418676793, "learning_rate": 1.1224396625876375e-05, "loss": 0.863, "step": 2480 }, { "epoch": 0.48, "grad_norm": 0.9886548649267737, "learning_rate": 1.1218212423543734e-05, "loss": 0.8435, "step": 2481 }, { "epoch": 0.48, "grad_norm": 0.9308659801316846, "learning_rate": 1.1212027748259086e-05, "loss": 0.9128, "step": 2482 }, { "epoch": 0.48, "grad_norm": 1.0357690034477696, "learning_rate": 1.1205842602423537e-05, "loss": 0.9099, "step": 2483 }, { "epoch": 0.48, "grad_norm": 1.0216958643482703, "learning_rate": 1.1199656988438373e-05, "loss": 0.8979, "step": 2484 }, { "epoch": 0.48, "grad_norm": 0.9507217093449929, "learning_rate": 1.1193470908705055e-05, "loss": 0.8921, "step": 2485 }, { "epoch": 0.48, "grad_norm": 1.1941479471030223, "learning_rate": 1.1187284365625241e-05, "loss": 0.9375, "step": 2486 }, { "epoch": 0.48, "grad_norm": 1.0108674526912678, "learning_rate": 1.1181097361600754e-05, "loss": 0.9116, "step": 2487 }, { "epoch": 0.48, "grad_norm": 0.9289929964946145, "learning_rate": 1.1174909899033608e-05, "loss": 0.8823, "step": 2488 }, { "epoch": 0.48, "grad_norm": 1.0775404813899574, "learning_rate": 1.1168721980325987e-05, "loss": 0.8997, "step": 2489 }, { "epoch": 0.48, "grad_norm": 0.903489054178052, "learning_rate": 1.1162533607880251e-05, "loss": 0.8853, "step": 2490 }, { "epoch": 0.48, "grad_norm": 0.7754896495420555, "learning_rate": 1.1156344784098942e-05, "loss": 0.6553, "step": 2491 }, { "epoch": 0.48, "grad_norm": 1.0147397641127802, "learning_rate": 1.1150155511384772e-05, "loss": 0.8662, "step": 2492 }, { "epoch": 0.48, "grad_norm": 1.1016235180367155, "learning_rate": 1.1143965792140631e-05, "loss": 0.8931, "step": 2493 }, { "epoch": 0.48, "grad_norm": 0.9773811878322568, "learning_rate": 1.1137775628769584e-05, "loss": 0.8385, "step": 2494 }, { "epoch": 0.48, "grad_norm": 1.0273410127153664, "learning_rate": 1.1131585023674863e-05, "loss": 0.939, "step": 2495 }, { "epoch": 0.48, "grad_norm": 1.0629252193627652, "learning_rate": 1.1125393979259874e-05, "loss": 0.8873, "step": 2496 }, { "epoch": 0.48, "grad_norm": 0.9323311842774769, "learning_rate": 1.1119202497928192e-05, "loss": 0.8635, "step": 2497 }, { "epoch": 0.48, "grad_norm": 1.0042500957680112, "learning_rate": 1.1113010582083568e-05, "loss": 0.8833, "step": 2498 }, { "epoch": 0.48, "grad_norm": 1.0699969885173897, "learning_rate": 1.1106818234129913e-05, "loss": 0.8955, "step": 2499 }, { "epoch": 0.48, "grad_norm": 1.0660412147469187, "learning_rate": 1.1100625456471307e-05, "loss": 0.8306, "step": 2500 }, { "epoch": 0.48, "grad_norm": 1.0472857051965736, "learning_rate": 1.1094432251512006e-05, "loss": 0.8899, "step": 2501 }, { "epoch": 0.48, "grad_norm": 1.051135757623903, "learning_rate": 1.1088238621656422e-05, "loss": 0.8442, "step": 2502 }, { "epoch": 0.48, "grad_norm": 0.9881387987679886, "learning_rate": 1.1082044569309138e-05, "loss": 0.6177, "step": 2503 }, { "epoch": 0.48, "grad_norm": 1.012842390678808, "learning_rate": 1.1075850096874894e-05, "loss": 0.8757, "step": 2504 }, { "epoch": 0.48, "grad_norm": 0.9935622500129367, "learning_rate": 1.1069655206758603e-05, "loss": 0.9021, "step": 2505 }, { "epoch": 0.48, "grad_norm": 0.9335963506542678, "learning_rate": 1.1063459901365325e-05, "loss": 0.6062, "step": 2506 }, { "epoch": 0.48, "grad_norm": 1.0190899314441089, "learning_rate": 1.1057264183100303e-05, "loss": 0.8577, "step": 2507 }, { "epoch": 0.48, "grad_norm": 1.000600100878138, "learning_rate": 1.1051068054368921e-05, "loss": 0.8997, "step": 2508 }, { "epoch": 0.48, "grad_norm": 1.0283871866237368, "learning_rate": 1.104487151757673e-05, "loss": 0.9026, "step": 2509 }, { "epoch": 0.48, "grad_norm": 0.9293250143101001, "learning_rate": 1.1038674575129442e-05, "loss": 0.9272, "step": 2510 }, { "epoch": 0.48, "grad_norm": 0.9826562238880663, "learning_rate": 1.1032477229432921e-05, "loss": 0.8535, "step": 2511 }, { "epoch": 0.48, "grad_norm": 0.975647327755937, "learning_rate": 1.1026279482893187e-05, "loss": 0.9119, "step": 2512 }, { "epoch": 0.48, "grad_norm": 1.1176665863168842, "learning_rate": 1.1020081337916425e-05, "loss": 0.948, "step": 2513 }, { "epoch": 0.48, "grad_norm": 0.9792267026218042, "learning_rate": 1.1013882796908963e-05, "loss": 0.7898, "step": 2514 }, { "epoch": 0.48, "grad_norm": 1.2121835250745068, "learning_rate": 1.1007683862277292e-05, "loss": 0.8364, "step": 2515 }, { "epoch": 0.48, "grad_norm": 0.8388419977409516, "learning_rate": 1.1001484536428052e-05, "loss": 0.6079, "step": 2516 }, { "epoch": 0.48, "grad_norm": 0.9147893475590998, "learning_rate": 1.0995284821768029e-05, "loss": 0.8923, "step": 2517 }, { "epoch": 0.48, "grad_norm": 1.1398779759275512, "learning_rate": 1.098908472070417e-05, "loss": 0.9165, "step": 2518 }, { "epoch": 0.48, "grad_norm": 0.968043594924721, "learning_rate": 1.0982884235643567e-05, "loss": 0.8823, "step": 2519 }, { "epoch": 0.48, "grad_norm": 0.9640490141567577, "learning_rate": 1.0976683368993464e-05, "loss": 0.8452, "step": 2520 }, { "epoch": 0.48, "grad_norm": 1.0716250225568154, "learning_rate": 1.0970482123161249e-05, "loss": 0.9167, "step": 2521 }, { "epoch": 0.49, "grad_norm": 1.080721001505647, "learning_rate": 1.0964280500554459e-05, "loss": 0.9321, "step": 2522 }, { "epoch": 0.49, "grad_norm": 0.9861993861453996, "learning_rate": 1.0958078503580776e-05, "loss": 0.8574, "step": 2523 }, { "epoch": 0.49, "grad_norm": 0.9522975230263361, "learning_rate": 1.0951876134648032e-05, "loss": 0.8807, "step": 2524 }, { "epoch": 0.49, "grad_norm": 1.0268557087557408, "learning_rate": 1.0945673396164198e-05, "loss": 0.9321, "step": 2525 }, { "epoch": 0.49, "grad_norm": 1.0146611376271386, "learning_rate": 1.0939470290537389e-05, "loss": 0.8809, "step": 2526 }, { "epoch": 0.49, "grad_norm": 1.0503797646007533, "learning_rate": 1.0933266820175868e-05, "loss": 0.9407, "step": 2527 }, { "epoch": 0.49, "grad_norm": 1.0781933652238316, "learning_rate": 1.0927062987488035e-05, "loss": 0.887, "step": 2528 }, { "epoch": 0.49, "grad_norm": 1.0936748187162915, "learning_rate": 1.0920858794882429e-05, "loss": 0.8806, "step": 2529 }, { "epoch": 0.49, "grad_norm": 0.9516277743213226, "learning_rate": 1.0914654244767736e-05, "loss": 0.875, "step": 2530 }, { "epoch": 0.49, "grad_norm": 1.1801064742779714, "learning_rate": 1.0908449339552769e-05, "loss": 0.8879, "step": 2531 }, { "epoch": 0.49, "grad_norm": 1.0710961499385534, "learning_rate": 1.0902244081646489e-05, "loss": 0.8126, "step": 2532 }, { "epoch": 0.49, "grad_norm": 1.053405200090131, "learning_rate": 1.0896038473457993e-05, "loss": 0.908, "step": 2533 }, { "epoch": 0.49, "grad_norm": 1.0766488932109104, "learning_rate": 1.0889832517396511e-05, "loss": 0.8618, "step": 2534 }, { "epoch": 0.49, "grad_norm": 0.9618934140191827, "learning_rate": 1.0883626215871408e-05, "loss": 0.873, "step": 2535 }, { "epoch": 0.49, "grad_norm": 0.7876061885735778, "learning_rate": 1.0877419571292183e-05, "loss": 0.5658, "step": 2536 }, { "epoch": 0.49, "grad_norm": 0.9476639468103772, "learning_rate": 1.0871212586068469e-05, "loss": 0.8367, "step": 2537 }, { "epoch": 0.49, "grad_norm": 0.9402185477361696, "learning_rate": 1.0865005262610033e-05, "loss": 0.8887, "step": 2538 }, { "epoch": 0.49, "grad_norm": 1.0443400436511128, "learning_rate": 1.085879760332677e-05, "loss": 0.8933, "step": 2539 }, { "epoch": 0.49, "grad_norm": 1.0496954885510563, "learning_rate": 1.085258961062871e-05, "loss": 0.9146, "step": 2540 }, { "epoch": 0.49, "grad_norm": 1.1097535797863238, "learning_rate": 1.0846381286926007e-05, "loss": 0.8853, "step": 2541 }, { "epoch": 0.49, "grad_norm": 1.1431201567146072, "learning_rate": 1.0840172634628948e-05, "loss": 0.8348, "step": 2542 }, { "epoch": 0.49, "grad_norm": 1.214679038934642, "learning_rate": 1.0833963656147944e-05, "loss": 0.8887, "step": 2543 }, { "epoch": 0.49, "grad_norm": 1.2096502965207663, "learning_rate": 1.082775435389353e-05, "loss": 0.9539, "step": 2544 }, { "epoch": 0.49, "grad_norm": 1.065156987848064, "learning_rate": 1.0821544730276379e-05, "loss": 0.9011, "step": 2545 }, { "epoch": 0.49, "grad_norm": 0.9993063788450053, "learning_rate": 1.0815334787707277e-05, "loss": 0.8806, "step": 2546 }, { "epoch": 0.49, "grad_norm": 0.9859468620221556, "learning_rate": 1.0809124528597138e-05, "loss": 0.9238, "step": 2547 }, { "epoch": 0.49, "grad_norm": 0.9348458739116223, "learning_rate": 1.0802913955356998e-05, "loss": 0.8677, "step": 2548 }, { "epoch": 0.49, "grad_norm": 0.9904858771312225, "learning_rate": 1.0796703070398016e-05, "loss": 0.7988, "step": 2549 }, { "epoch": 0.49, "grad_norm": 1.2285266934094845, "learning_rate": 1.079049187613147e-05, "loss": 0.917, "step": 2550 }, { "epoch": 0.49, "grad_norm": 1.140196317548589, "learning_rate": 1.0784280374968761e-05, "loss": 0.8625, "step": 2551 }, { "epoch": 0.49, "grad_norm": 1.096341749492941, "learning_rate": 1.0778068569321403e-05, "loss": 0.8643, "step": 2552 }, { "epoch": 0.49, "grad_norm": 1.0228437783609936, "learning_rate": 1.077185646160104e-05, "loss": 0.8796, "step": 2553 }, { "epoch": 0.49, "grad_norm": 1.053657678105751, "learning_rate": 1.0765644054219422e-05, "loss": 0.8226, "step": 2554 }, { "epoch": 0.49, "grad_norm": 0.9911303378206836, "learning_rate": 1.0759431349588421e-05, "loss": 0.8718, "step": 2555 }, { "epoch": 0.49, "grad_norm": 0.7956259500909153, "learning_rate": 1.0753218350120023e-05, "loss": 0.562, "step": 2556 }, { "epoch": 0.49, "grad_norm": 1.1177790605732552, "learning_rate": 1.0747005058226325e-05, "loss": 0.8579, "step": 2557 }, { "epoch": 0.49, "grad_norm": 1.1095669850596834, "learning_rate": 1.0740791476319543e-05, "loss": 0.9692, "step": 2558 }, { "epoch": 0.49, "grad_norm": 1.1062238005186582, "learning_rate": 1.0734577606812007e-05, "loss": 0.896, "step": 2559 }, { "epoch": 0.49, "grad_norm": 0.9813200854124812, "learning_rate": 1.0728363452116149e-05, "loss": 0.8628, "step": 2560 }, { "epoch": 0.49, "grad_norm": 1.0238289804365899, "learning_rate": 1.0722149014644523e-05, "loss": 0.8999, "step": 2561 }, { "epoch": 0.49, "grad_norm": 0.9545418758974838, "learning_rate": 1.0715934296809782e-05, "loss": 0.8176, "step": 2562 }, { "epoch": 0.49, "grad_norm": 1.0742258676379826, "learning_rate": 1.0709719301024698e-05, "loss": 0.8682, "step": 2563 }, { "epoch": 0.49, "grad_norm": 1.025072149478347, "learning_rate": 1.0703504029702148e-05, "loss": 0.8823, "step": 2564 }, { "epoch": 0.49, "grad_norm": 1.104483852620638, "learning_rate": 1.0697288485255107e-05, "loss": 0.8679, "step": 2565 }, { "epoch": 0.49, "grad_norm": 1.0641178020717441, "learning_rate": 1.0691072670096669e-05, "loss": 0.9075, "step": 2566 }, { "epoch": 0.49, "grad_norm": 0.9701652391785699, "learning_rate": 1.0684856586640026e-05, "loss": 0.8682, "step": 2567 }, { "epoch": 0.49, "grad_norm": 0.971999259614552, "learning_rate": 1.0678640237298476e-05, "loss": 0.6361, "step": 2568 }, { "epoch": 0.49, "grad_norm": 1.1010453240479297, "learning_rate": 1.0672423624485423e-05, "loss": 0.9131, "step": 2569 }, { "epoch": 0.49, "grad_norm": 1.09274803294872, "learning_rate": 1.0666206750614363e-05, "loss": 0.9006, "step": 2570 }, { "epoch": 0.49, "grad_norm": 0.9644880637022055, "learning_rate": 1.0659989618098904e-05, "loss": 0.9021, "step": 2571 }, { "epoch": 0.49, "grad_norm": 1.0058098334083931, "learning_rate": 1.065377222935275e-05, "loss": 0.8679, "step": 2572 }, { "epoch": 0.49, "grad_norm": 0.7888629463001039, "learning_rate": 1.0647554586789708e-05, "loss": 0.6174, "step": 2573 }, { "epoch": 0.5, "grad_norm": 1.0634079801366838, "learning_rate": 1.064133669282368e-05, "loss": 0.8461, "step": 2574 }, { "epoch": 0.5, "grad_norm": 1.0486802166888574, "learning_rate": 1.0635118549868668e-05, "loss": 0.8853, "step": 2575 }, { "epoch": 0.5, "grad_norm": 1.1278014962725662, "learning_rate": 1.0628900160338764e-05, "loss": 0.8765, "step": 2576 }, { "epoch": 0.5, "grad_norm": 0.9826216499312208, "learning_rate": 1.0622681526648167e-05, "loss": 0.8801, "step": 2577 }, { "epoch": 0.5, "grad_norm": 1.4008294023985992, "learning_rate": 1.0616462651211156e-05, "loss": 0.8252, "step": 2578 }, { "epoch": 0.5, "grad_norm": 0.9922798690546166, "learning_rate": 1.0610243536442125e-05, "loss": 0.8547, "step": 2579 }, { "epoch": 0.5, "grad_norm": 1.2717009534245578, "learning_rate": 1.0604024184755539e-05, "loss": 0.8287, "step": 2580 }, { "epoch": 0.5, "grad_norm": 0.9169445568832362, "learning_rate": 1.0597804598565969e-05, "loss": 0.8921, "step": 2581 }, { "epoch": 0.5, "grad_norm": 0.8487406015806263, "learning_rate": 1.0591584780288069e-05, "loss": 0.5974, "step": 2582 }, { "epoch": 0.5, "grad_norm": 0.9764253391263876, "learning_rate": 1.0585364732336587e-05, "loss": 0.8735, "step": 2583 }, { "epoch": 0.5, "grad_norm": 0.911300751157046, "learning_rate": 1.0579144457126365e-05, "loss": 0.8711, "step": 2584 }, { "epoch": 0.5, "grad_norm": 0.8999390886326676, "learning_rate": 1.057292395707232e-05, "loss": 0.8511, "step": 2585 }, { "epoch": 0.5, "grad_norm": 0.9962763530120209, "learning_rate": 1.0566703234589471e-05, "loss": 0.9072, "step": 2586 }, { "epoch": 0.5, "grad_norm": 0.9087955707505158, "learning_rate": 1.0560482292092912e-05, "loss": 0.8218, "step": 2587 }, { "epoch": 0.5, "grad_norm": 1.0291534331569445, "learning_rate": 1.0554261131997833e-05, "loss": 0.8777, "step": 2588 }, { "epoch": 0.5, "grad_norm": 0.8673118077194916, "learning_rate": 1.0548039756719497e-05, "loss": 0.8513, "step": 2589 }, { "epoch": 0.5, "grad_norm": 1.0216430260272413, "learning_rate": 1.054181816867326e-05, "loss": 0.8511, "step": 2590 }, { "epoch": 0.5, "grad_norm": 0.8694393974488835, "learning_rate": 1.053559637027455e-05, "loss": 0.6333, "step": 2591 }, { "epoch": 0.5, "grad_norm": 0.9891842523378438, "learning_rate": 1.0529374363938888e-05, "loss": 0.8545, "step": 2592 }, { "epoch": 0.5, "grad_norm": 1.095415021381047, "learning_rate": 1.0523152152081875e-05, "loss": 0.897, "step": 2593 }, { "epoch": 0.5, "grad_norm": 0.9594402912010113, "learning_rate": 1.051692973711918e-05, "loss": 0.8453, "step": 2594 }, { "epoch": 0.5, "grad_norm": 1.0369282629887677, "learning_rate": 1.0510707121466568e-05, "loss": 0.8662, "step": 2595 }, { "epoch": 0.5, "grad_norm": 1.0559715927809517, "learning_rate": 1.0504484307539864e-05, "loss": 0.9297, "step": 2596 }, { "epoch": 0.5, "grad_norm": 0.9222414853633976, "learning_rate": 1.0498261297754984e-05, "loss": 0.842, "step": 2597 }, { "epoch": 0.5, "grad_norm": 0.9758455971005627, "learning_rate": 1.0492038094527907e-05, "loss": 0.8513, "step": 2598 }, { "epoch": 0.5, "grad_norm": 0.764035136458955, "learning_rate": 1.0485814700274706e-05, "loss": 0.5951, "step": 2599 }, { "epoch": 0.5, "grad_norm": 0.954569736376262, "learning_rate": 1.047959111741151e-05, "loss": 0.8392, "step": 2600 }, { "epoch": 0.5, "grad_norm": 0.9692144266070858, "learning_rate": 1.0473367348354529e-05, "loss": 0.8867, "step": 2601 }, { "epoch": 0.5, "grad_norm": 1.057027074256862, "learning_rate": 1.0467143395520044e-05, "loss": 0.8538, "step": 2602 }, { "epoch": 0.5, "grad_norm": 1.001775630813657, "learning_rate": 1.046091926132441e-05, "loss": 0.8987, "step": 2603 }, { "epoch": 0.5, "grad_norm": 0.9787182935919014, "learning_rate": 1.0454694948184045e-05, "loss": 0.8896, "step": 2604 }, { "epoch": 0.5, "grad_norm": 0.8023464661912527, "learning_rate": 1.044847045851545e-05, "loss": 0.6115, "step": 2605 }, { "epoch": 0.5, "grad_norm": 0.9391794405822912, "learning_rate": 1.044224579473518e-05, "loss": 0.8757, "step": 2606 }, { "epoch": 0.5, "grad_norm": 1.050558293896055, "learning_rate": 1.0436020959259862e-05, "loss": 0.9089, "step": 2607 }, { "epoch": 0.5, "grad_norm": 0.9886497542748804, "learning_rate": 1.0429795954506203e-05, "loss": 0.8967, "step": 2608 }, { "epoch": 0.5, "grad_norm": 0.8142055562875119, "learning_rate": 1.0423570782890951e-05, "loss": 0.6027, "step": 2609 }, { "epoch": 0.5, "grad_norm": 1.0072253700411657, "learning_rate": 1.0417345446830938e-05, "loss": 0.8789, "step": 2610 }, { "epoch": 0.5, "grad_norm": 1.0597712864550568, "learning_rate": 1.0411119948743052e-05, "loss": 0.9128, "step": 2611 }, { "epoch": 0.5, "grad_norm": 0.8997549306508955, "learning_rate": 1.0404894291044247e-05, "loss": 0.906, "step": 2612 }, { "epoch": 0.5, "grad_norm": 1.1905995774636882, "learning_rate": 1.0398668476151538e-05, "loss": 0.968, "step": 2613 }, { "epoch": 0.5, "grad_norm": 1.0837226013541725, "learning_rate": 1.0392442506482e-05, "loss": 0.8608, "step": 2614 }, { "epoch": 0.5, "grad_norm": 0.835843385234746, "learning_rate": 1.038621638445277e-05, "loss": 0.6, "step": 2615 }, { "epoch": 0.5, "grad_norm": 1.0064218370924485, "learning_rate": 1.037999011248104e-05, "loss": 0.8404, "step": 2616 }, { "epoch": 0.5, "grad_norm": 1.125029640399193, "learning_rate": 1.0373763692984062e-05, "loss": 0.927, "step": 2617 }, { "epoch": 0.5, "grad_norm": 1.0215006963992292, "learning_rate": 1.0367537128379154e-05, "loss": 0.8623, "step": 2618 }, { "epoch": 0.5, "grad_norm": 0.7398659449293714, "learning_rate": 1.0361310421083677e-05, "loss": 0.5936, "step": 2619 }, { "epoch": 0.5, "grad_norm": 1.0265188640453555, "learning_rate": 1.0355083573515052e-05, "loss": 0.7979, "step": 2620 }, { "epoch": 0.5, "grad_norm": 0.9427418968467739, "learning_rate": 1.0348856588090764e-05, "loss": 0.8547, "step": 2621 }, { "epoch": 0.5, "grad_norm": 0.999634401165403, "learning_rate": 1.0342629467228331e-05, "loss": 0.9287, "step": 2622 }, { "epoch": 0.5, "grad_norm": 0.9969719422364274, "learning_rate": 1.0336402213345345e-05, "loss": 0.9077, "step": 2623 }, { "epoch": 0.5, "grad_norm": 0.8509167575741097, "learning_rate": 1.0330174828859434e-05, "loss": 0.6163, "step": 2624 }, { "epoch": 0.51, "grad_norm": 0.7176371824598734, "learning_rate": 1.0323947316188288e-05, "loss": 0.5892, "step": 2625 }, { "epoch": 0.51, "grad_norm": 1.0271976761668191, "learning_rate": 1.031771967774964e-05, "loss": 0.8867, "step": 2626 }, { "epoch": 0.51, "grad_norm": 0.9122108911214748, "learning_rate": 1.0311491915961271e-05, "loss": 0.8708, "step": 2627 }, { "epoch": 0.51, "grad_norm": 1.0502030468464911, "learning_rate": 1.030526403324102e-05, "loss": 0.9165, "step": 2628 }, { "epoch": 0.51, "grad_norm": 0.9523175605324926, "learning_rate": 1.0299036032006759e-05, "loss": 0.9011, "step": 2629 }, { "epoch": 0.51, "grad_norm": 0.972994384628558, "learning_rate": 1.0292807914676412e-05, "loss": 0.8582, "step": 2630 }, { "epoch": 0.51, "grad_norm": 1.0985214956897316, "learning_rate": 1.0286579683667952e-05, "loss": 0.8875, "step": 2631 }, { "epoch": 0.51, "grad_norm": 0.9279439052077904, "learning_rate": 1.0280351341399392e-05, "loss": 0.8315, "step": 2632 }, { "epoch": 0.51, "grad_norm": 1.2223166534580183, "learning_rate": 1.027412289028879e-05, "loss": 0.9006, "step": 2633 }, { "epoch": 0.51, "grad_norm": 1.1251312118701906, "learning_rate": 1.0267894332754243e-05, "loss": 0.9177, "step": 2634 }, { "epoch": 0.51, "grad_norm": 0.8687835139196938, "learning_rate": 1.0261665671213891e-05, "loss": 0.8413, "step": 2635 }, { "epoch": 0.51, "grad_norm": 0.9340073470406085, "learning_rate": 1.0255436908085919e-05, "loss": 0.8113, "step": 2636 }, { "epoch": 0.51, "grad_norm": 1.0649654465733707, "learning_rate": 1.024920804578854e-05, "loss": 0.9009, "step": 2637 }, { "epoch": 0.51, "grad_norm": 1.0795754889366775, "learning_rate": 1.0242979086740019e-05, "loss": 0.8887, "step": 2638 }, { "epoch": 0.51, "grad_norm": 0.9572487057354857, "learning_rate": 1.023675003335865e-05, "loss": 0.7988, "step": 2639 }, { "epoch": 0.51, "grad_norm": 1.0586838765242093, "learning_rate": 1.0230520888062765e-05, "loss": 0.8882, "step": 2640 }, { "epoch": 0.51, "grad_norm": 1.0187364753877808, "learning_rate": 1.0224291653270739e-05, "loss": 0.8601, "step": 2641 }, { "epoch": 0.51, "grad_norm": 1.304961657558024, "learning_rate": 1.0218062331400969e-05, "loss": 0.8972, "step": 2642 }, { "epoch": 0.51, "grad_norm": 1.1379047589843472, "learning_rate": 1.0211832924871889e-05, "loss": 0.8787, "step": 2643 }, { "epoch": 0.51, "grad_norm": 1.120315656813825, "learning_rate": 1.0205603436101978e-05, "loss": 0.8914, "step": 2644 }, { "epoch": 0.51, "grad_norm": 1.0665123945856714, "learning_rate": 1.0199373867509734e-05, "loss": 0.8838, "step": 2645 }, { "epoch": 0.51, "grad_norm": 0.9574947422053797, "learning_rate": 1.019314422151369e-05, "loss": 0.8992, "step": 2646 }, { "epoch": 0.51, "grad_norm": 0.8829779054599176, "learning_rate": 1.0186914500532408e-05, "loss": 0.6226, "step": 2647 }, { "epoch": 0.51, "grad_norm": 0.9966178257516866, "learning_rate": 1.0180684706984483e-05, "loss": 0.9126, "step": 2648 }, { "epoch": 0.51, "grad_norm": 1.0863737860035128, "learning_rate": 1.0174454843288533e-05, "loss": 0.9004, "step": 2649 }, { "epoch": 0.51, "grad_norm": 0.977482453120964, "learning_rate": 1.0168224911863205e-05, "loss": 0.8604, "step": 2650 }, { "epoch": 0.51, "grad_norm": 1.001785724907013, "learning_rate": 1.0161994915127173e-05, "loss": 0.8535, "step": 2651 }, { "epoch": 0.51, "grad_norm": 0.898143391827782, "learning_rate": 1.015576485549914e-05, "loss": 0.877, "step": 2652 }, { "epoch": 0.51, "grad_norm": 0.8354553193728527, "learning_rate": 1.0149534735397823e-05, "loss": 0.6622, "step": 2653 }, { "epoch": 0.51, "grad_norm": 1.1091193732393867, "learning_rate": 1.0143304557241979e-05, "loss": 0.8833, "step": 2654 }, { "epoch": 0.51, "grad_norm": 1.0060334235595245, "learning_rate": 1.0137074323450372e-05, "loss": 0.9048, "step": 2655 }, { "epoch": 0.51, "grad_norm": 1.0409945567255376, "learning_rate": 1.0130844036441787e-05, "loss": 0.8264, "step": 2656 }, { "epoch": 0.51, "grad_norm": 1.1667741962958025, "learning_rate": 1.0124613698635043e-05, "loss": 0.917, "step": 2657 }, { "epoch": 0.51, "grad_norm": 1.110150886928052, "learning_rate": 1.0118383312448973e-05, "loss": 0.9287, "step": 2658 }, { "epoch": 0.51, "grad_norm": 0.8992665464452598, "learning_rate": 1.0112152880302426e-05, "loss": 0.8521, "step": 2659 }, { "epoch": 0.51, "grad_norm": 1.0175028814788591, "learning_rate": 1.0105922404614265e-05, "loss": 0.9199, "step": 2660 }, { "epoch": 0.51, "grad_norm": 0.9532539586274945, "learning_rate": 1.0099691887803385e-05, "loss": 0.8484, "step": 2661 }, { "epoch": 0.51, "grad_norm": 1.0406106235736112, "learning_rate": 1.0093461332288678e-05, "loss": 0.8608, "step": 2662 }, { "epoch": 0.51, "grad_norm": 1.0459011973416759, "learning_rate": 1.0087230740489065e-05, "loss": 0.9124, "step": 2663 }, { "epoch": 0.51, "grad_norm": 0.8353419143016119, "learning_rate": 1.0081000114823473e-05, "loss": 0.59, "step": 2664 }, { "epoch": 0.51, "grad_norm": 0.8767272975987996, "learning_rate": 1.007476945771085e-05, "loss": 0.6234, "step": 2665 }, { "epoch": 0.51, "grad_norm": 1.0409781161165752, "learning_rate": 1.006853877157015e-05, "loss": 0.9006, "step": 2666 }, { "epoch": 0.51, "grad_norm": 0.9687223012294509, "learning_rate": 1.0062308058820337e-05, "loss": 0.8586, "step": 2667 }, { "epoch": 0.51, "grad_norm": 0.9741690682426621, "learning_rate": 1.0056077321880393e-05, "loss": 0.8289, "step": 2668 }, { "epoch": 0.51, "grad_norm": 1.1471909164721015, "learning_rate": 1.0049846563169297e-05, "loss": 0.8267, "step": 2669 }, { "epoch": 0.51, "grad_norm": 0.8337918980454844, "learning_rate": 1.0043615785106051e-05, "loss": 0.6497, "step": 2670 }, { "epoch": 0.51, "grad_norm": 1.0560396664979657, "learning_rate": 1.0037384990109658e-05, "loss": 0.8574, "step": 2671 }, { "epoch": 0.51, "grad_norm": 0.9874458939528631, "learning_rate": 1.0031154180599123e-05, "loss": 0.8494, "step": 2672 }, { "epoch": 0.51, "grad_norm": 0.9239134134195215, "learning_rate": 1.0024923358993458e-05, "loss": 0.8784, "step": 2673 }, { "epoch": 0.51, "grad_norm": 1.019420491017517, "learning_rate": 1.0018692527711695e-05, "loss": 0.8127, "step": 2674 }, { "epoch": 0.51, "grad_norm": 0.903531782424912, "learning_rate": 1.0012461689172846e-05, "loss": 0.8611, "step": 2675 }, { "epoch": 0.51, "grad_norm": 1.0091680245835732, "learning_rate": 1.0006230845795937e-05, "loss": 0.9172, "step": 2676 }, { "epoch": 0.52, "grad_norm": 1.0908073889411618, "learning_rate": 1e-05, "loss": 0.9253, "step": 2677 }, { "epoch": 0.52, "grad_norm": 1.1419925833799753, "learning_rate": 9.993769154204063e-06, "loss": 0.8865, "step": 2678 }, { "epoch": 0.52, "grad_norm": 1.1047658555947975, "learning_rate": 9.987538310827159e-06, "loss": 0.8359, "step": 2679 }, { "epoch": 0.52, "grad_norm": 0.935805699680844, "learning_rate": 9.981307472288308e-06, "loss": 0.8346, "step": 2680 }, { "epoch": 0.52, "grad_norm": 0.9867725702333435, "learning_rate": 9.975076641006542e-06, "loss": 0.8569, "step": 2681 }, { "epoch": 0.52, "grad_norm": 1.0199527825921473, "learning_rate": 9.968845819400883e-06, "loss": 0.8489, "step": 2682 }, { "epoch": 0.52, "grad_norm": 1.0668952531615723, "learning_rate": 9.962615009890346e-06, "loss": 0.8896, "step": 2683 }, { "epoch": 0.52, "grad_norm": 1.0217268955167735, "learning_rate": 9.956384214893949e-06, "loss": 0.8662, "step": 2684 }, { "epoch": 0.52, "grad_norm": 1.0135619310841022, "learning_rate": 9.950153436830707e-06, "loss": 0.832, "step": 2685 }, { "epoch": 0.52, "grad_norm": 0.9847323067450385, "learning_rate": 9.94392267811961e-06, "loss": 0.8889, "step": 2686 }, { "epoch": 0.52, "grad_norm": 0.9482557902750196, "learning_rate": 9.937691941179665e-06, "loss": 0.8687, "step": 2687 }, { "epoch": 0.52, "grad_norm": 1.010903167113975, "learning_rate": 9.931461228429856e-06, "loss": 0.8618, "step": 2688 }, { "epoch": 0.52, "grad_norm": 1.0444662468876542, "learning_rate": 9.925230542289151e-06, "loss": 0.8638, "step": 2689 }, { "epoch": 0.52, "grad_norm": 1.0440471316714792, "learning_rate": 9.91899988517653e-06, "loss": 0.9202, "step": 2690 }, { "epoch": 0.52, "grad_norm": 1.0075325960689723, "learning_rate": 9.912769259510938e-06, "loss": 0.8711, "step": 2691 }, { "epoch": 0.52, "grad_norm": 1.029562636237285, "learning_rate": 9.906538667711324e-06, "loss": 0.8538, "step": 2692 }, { "epoch": 0.52, "grad_norm": 0.9957465485318726, "learning_rate": 9.90030811219662e-06, "loss": 0.9058, "step": 2693 }, { "epoch": 0.52, "grad_norm": 1.0188411593698523, "learning_rate": 9.894077595385736e-06, "loss": 0.8677, "step": 2694 }, { "epoch": 0.52, "grad_norm": 0.8024782122438848, "learning_rate": 9.887847119697577e-06, "loss": 0.604, "step": 2695 }, { "epoch": 0.52, "grad_norm": 1.0763775027379043, "learning_rate": 9.881616687551032e-06, "loss": 0.9358, "step": 2696 }, { "epoch": 0.52, "grad_norm": 0.9842344580621059, "learning_rate": 9.875386301364958e-06, "loss": 0.9304, "step": 2697 }, { "epoch": 0.52, "grad_norm": 0.9492620465133299, "learning_rate": 9.869155963558215e-06, "loss": 0.8555, "step": 2698 }, { "epoch": 0.52, "grad_norm": 1.1423962955800955, "learning_rate": 9.862925676549635e-06, "loss": 0.876, "step": 2699 }, { "epoch": 0.52, "grad_norm": 1.001753031631295, "learning_rate": 9.856695442758023e-06, "loss": 0.8784, "step": 2700 }, { "epoch": 0.52, "grad_norm": 0.9548566442954701, "learning_rate": 9.850465264602175e-06, "loss": 0.8147, "step": 2701 }, { "epoch": 0.52, "grad_norm": 1.0413660916403835, "learning_rate": 9.844235144500865e-06, "loss": 0.832, "step": 2702 }, { "epoch": 0.52, "grad_norm": 1.0040234480394685, "learning_rate": 9.83800508487283e-06, "loss": 0.8948, "step": 2703 }, { "epoch": 0.52, "grad_norm": 0.906107525478214, "learning_rate": 9.831775088136797e-06, "loss": 0.6361, "step": 2704 }, { "epoch": 0.52, "grad_norm": 0.8425957883708601, "learning_rate": 9.82554515671147e-06, "loss": 0.6382, "step": 2705 }, { "epoch": 0.52, "grad_norm": 1.1750698852554518, "learning_rate": 9.819315293015519e-06, "loss": 0.8984, "step": 2706 }, { "epoch": 0.52, "grad_norm": 0.9540211010118544, "learning_rate": 9.813085499467594e-06, "loss": 0.8562, "step": 2707 }, { "epoch": 0.52, "grad_norm": 0.995828740428959, "learning_rate": 9.806855778486314e-06, "loss": 0.9202, "step": 2708 }, { "epoch": 0.52, "grad_norm": 0.9997699172972708, "learning_rate": 9.800626132490268e-06, "loss": 0.8628, "step": 2709 }, { "epoch": 0.52, "grad_norm": 1.0003440818410467, "learning_rate": 9.794396563898022e-06, "loss": 0.9146, "step": 2710 }, { "epoch": 0.52, "grad_norm": 0.9833118716459442, "learning_rate": 9.788167075128113e-06, "loss": 0.8669, "step": 2711 }, { "epoch": 0.52, "grad_norm": 1.0455516800014306, "learning_rate": 9.781937668599035e-06, "loss": 0.887, "step": 2712 }, { "epoch": 0.52, "grad_norm": 1.0401633532003147, "learning_rate": 9.775708346729263e-06, "loss": 0.9324, "step": 2713 }, { "epoch": 0.52, "grad_norm": 1.0049441333240947, "learning_rate": 9.769479111937238e-06, "loss": 0.8931, "step": 2714 }, { "epoch": 0.52, "grad_norm": 0.9622685602180044, "learning_rate": 9.763249966641352e-06, "loss": 0.8574, "step": 2715 }, { "epoch": 0.52, "grad_norm": 1.0648005771526143, "learning_rate": 9.757020913259986e-06, "loss": 0.8933, "step": 2716 }, { "epoch": 0.52, "grad_norm": 0.9634384771510524, "learning_rate": 9.750791954211464e-06, "loss": 0.8238, "step": 2717 }, { "epoch": 0.52, "grad_norm": 0.923203077051777, "learning_rate": 9.744563091914085e-06, "loss": 0.8706, "step": 2718 }, { "epoch": 0.52, "grad_norm": 0.783531807679605, "learning_rate": 9.738334328786114e-06, "loss": 0.623, "step": 2719 }, { "epoch": 0.52, "grad_norm": 1.1355572326038188, "learning_rate": 9.732105667245759e-06, "loss": 0.8525, "step": 2720 }, { "epoch": 0.52, "grad_norm": 0.8594661769941297, "learning_rate": 9.725877109711212e-06, "loss": 0.8467, "step": 2721 }, { "epoch": 0.52, "grad_norm": 1.0455217681602198, "learning_rate": 9.719648658600611e-06, "loss": 0.8687, "step": 2722 }, { "epoch": 0.52, "grad_norm": 1.022525866131112, "learning_rate": 9.71342031633205e-06, "loss": 0.9001, "step": 2723 }, { "epoch": 0.52, "grad_norm": 1.1126016037582243, "learning_rate": 9.70719208532359e-06, "loss": 0.9053, "step": 2724 }, { "epoch": 0.52, "grad_norm": 1.1573296565397329, "learning_rate": 9.700963967993246e-06, "loss": 0.8865, "step": 2725 }, { "epoch": 0.52, "grad_norm": 0.9325096838590264, "learning_rate": 9.694735966758982e-06, "loss": 0.9243, "step": 2726 }, { "epoch": 0.52, "grad_norm": 1.0776597025096464, "learning_rate": 9.688508084038729e-06, "loss": 0.896, "step": 2727 }, { "epoch": 0.52, "grad_norm": 0.9387323516450374, "learning_rate": 9.682280322250365e-06, "loss": 0.8035, "step": 2728 }, { "epoch": 0.53, "grad_norm": 1.1028444786394527, "learning_rate": 9.676052683811715e-06, "loss": 0.9121, "step": 2729 }, { "epoch": 0.53, "grad_norm": 0.951650361587594, "learning_rate": 9.669825171140568e-06, "loss": 0.887, "step": 2730 }, { "epoch": 0.53, "grad_norm": 0.6277472306407198, "learning_rate": 9.66359778665466e-06, "loss": 0.3264, "step": 2731 }, { "epoch": 0.53, "grad_norm": 0.950293466785235, "learning_rate": 9.657370532771672e-06, "loss": 0.8813, "step": 2732 }, { "epoch": 0.53, "grad_norm": 0.912104230862147, "learning_rate": 9.651143411909241e-06, "loss": 0.6742, "step": 2733 }, { "epoch": 0.53, "grad_norm": 0.9635820901989375, "learning_rate": 9.64491642648495e-06, "loss": 0.8887, "step": 2734 }, { "epoch": 0.53, "grad_norm": 1.1507649298492824, "learning_rate": 9.638689578916326e-06, "loss": 0.9387, "step": 2735 }, { "epoch": 0.53, "grad_norm": 0.9762326174510644, "learning_rate": 9.632462871620847e-06, "loss": 0.8975, "step": 2736 }, { "epoch": 0.53, "grad_norm": 0.9487966238566524, "learning_rate": 9.62623630701594e-06, "loss": 0.8352, "step": 2737 }, { "epoch": 0.53, "grad_norm": 0.8567920634506447, "learning_rate": 9.620009887518963e-06, "loss": 0.598, "step": 2738 }, { "epoch": 0.53, "grad_norm": 0.7870232619882638, "learning_rate": 9.613783615547233e-06, "loss": 0.613, "step": 2739 }, { "epoch": 0.53, "grad_norm": 0.9698817659771712, "learning_rate": 9.607557493518006e-06, "loss": 0.8459, "step": 2740 }, { "epoch": 0.53, "grad_norm": 1.1316510751829012, "learning_rate": 9.601331523848464e-06, "loss": 0.9097, "step": 2741 }, { "epoch": 0.53, "grad_norm": 0.9819183968487686, "learning_rate": 9.595105708955758e-06, "loss": 0.8508, "step": 2742 }, { "epoch": 0.53, "grad_norm": 1.0807807639072522, "learning_rate": 9.588880051256951e-06, "loss": 0.8933, "step": 2743 }, { "epoch": 0.53, "grad_norm": 0.9269596497842182, "learning_rate": 9.582654553169064e-06, "loss": 0.8696, "step": 2744 }, { "epoch": 0.53, "grad_norm": 1.1193876994436707, "learning_rate": 9.576429217109054e-06, "loss": 0.8926, "step": 2745 }, { "epoch": 0.53, "grad_norm": 1.0387826422570154, "learning_rate": 9.5702040454938e-06, "loss": 0.8708, "step": 2746 }, { "epoch": 0.53, "grad_norm": 0.9736496613975898, "learning_rate": 9.563979040740138e-06, "loss": 0.8757, "step": 2747 }, { "epoch": 0.53, "grad_norm": 1.111098094935244, "learning_rate": 9.557754205264826e-06, "loss": 0.8882, "step": 2748 }, { "epoch": 0.53, "grad_norm": 0.9320981929598873, "learning_rate": 9.551529541484554e-06, "loss": 0.6603, "step": 2749 }, { "epoch": 0.53, "grad_norm": 1.1172697690953308, "learning_rate": 9.545305051815957e-06, "loss": 0.8701, "step": 2750 }, { "epoch": 0.53, "grad_norm": 1.038795335225374, "learning_rate": 9.539080738675597e-06, "loss": 0.906, "step": 2751 }, { "epoch": 0.53, "grad_norm": 0.9662823803619701, "learning_rate": 9.53285660447996e-06, "loss": 0.8716, "step": 2752 }, { "epoch": 0.53, "grad_norm": 1.1241506628613593, "learning_rate": 9.526632651645476e-06, "loss": 0.9086, "step": 2753 }, { "epoch": 0.53, "grad_norm": 0.9941026057606579, "learning_rate": 9.520408882588497e-06, "loss": 0.8848, "step": 2754 }, { "epoch": 0.53, "grad_norm": 0.9628623378885368, "learning_rate": 9.514185299725299e-06, "loss": 0.8936, "step": 2755 }, { "epoch": 0.53, "grad_norm": 0.6998017633628811, "learning_rate": 9.507961905472093e-06, "loss": 0.3317, "step": 2756 }, { "epoch": 0.53, "grad_norm": 0.9081045435654506, "learning_rate": 9.501738702245023e-06, "loss": 0.7892, "step": 2757 }, { "epoch": 0.53, "grad_norm": 0.9387790428655163, "learning_rate": 9.495515692460138e-06, "loss": 0.6389, "step": 2758 }, { "epoch": 0.53, "grad_norm": 1.0883808604462897, "learning_rate": 9.489292878533436e-06, "loss": 0.8569, "step": 2759 }, { "epoch": 0.53, "grad_norm": 0.9611065236651173, "learning_rate": 9.483070262880823e-06, "loss": 0.8698, "step": 2760 }, { "epoch": 0.53, "grad_norm": 0.9784077321463304, "learning_rate": 9.476847847918126e-06, "loss": 0.8464, "step": 2761 }, { "epoch": 0.53, "grad_norm": 1.1009749769582087, "learning_rate": 9.47062563606111e-06, "loss": 0.9019, "step": 2762 }, { "epoch": 0.53, "grad_norm": 1.0869985181971498, "learning_rate": 9.464403629725454e-06, "loss": 0.9067, "step": 2763 }, { "epoch": 0.53, "grad_norm": 0.8261740838916369, "learning_rate": 9.458181831326744e-06, "loss": 0.6699, "step": 2764 }, { "epoch": 0.53, "grad_norm": 0.9354523035313779, "learning_rate": 9.451960243280506e-06, "loss": 0.8528, "step": 2765 }, { "epoch": 0.53, "grad_norm": 1.1803425746772727, "learning_rate": 9.44573886800217e-06, "loss": 0.9082, "step": 2766 }, { "epoch": 0.53, "grad_norm": 1.0741051052407713, "learning_rate": 9.43951770790709e-06, "loss": 0.8911, "step": 2767 }, { "epoch": 0.53, "grad_norm": 0.8230082707320303, "learning_rate": 9.433296765410534e-06, "loss": 0.6355, "step": 2768 }, { "epoch": 0.53, "grad_norm": 0.9486306345828044, "learning_rate": 9.427076042927683e-06, "loss": 0.8962, "step": 2769 }, { "epoch": 0.53, "grad_norm": 0.8482146879222998, "learning_rate": 9.420855542873638e-06, "loss": 0.5782, "step": 2770 }, { "epoch": 0.53, "grad_norm": 1.0855421900776803, "learning_rate": 9.414635267663416e-06, "loss": 0.8857, "step": 2771 }, { "epoch": 0.53, "grad_norm": 1.0011452218759844, "learning_rate": 9.408415219711934e-06, "loss": 0.8474, "step": 2772 }, { "epoch": 0.53, "grad_norm": 1.024938512312051, "learning_rate": 9.402195401434036e-06, "loss": 0.8699, "step": 2773 }, { "epoch": 0.53, "grad_norm": 1.1370338760178953, "learning_rate": 9.395975815244468e-06, "loss": 0.927, "step": 2774 }, { "epoch": 0.53, "grad_norm": 1.0982219557227435, "learning_rate": 9.389756463557878e-06, "loss": 0.8188, "step": 2775 }, { "epoch": 0.53, "grad_norm": 1.1143754074603527, "learning_rate": 9.383537348788844e-06, "loss": 0.9412, "step": 2776 }, { "epoch": 0.53, "grad_norm": 0.9563897136918519, "learning_rate": 9.377318473351838e-06, "loss": 0.8975, "step": 2777 }, { "epoch": 0.53, "grad_norm": 1.0688135460559918, "learning_rate": 9.371099839661238e-06, "loss": 0.8848, "step": 2778 }, { "epoch": 0.53, "grad_norm": 1.1091160350248026, "learning_rate": 9.364881450131335e-06, "loss": 0.9219, "step": 2779 }, { "epoch": 0.53, "grad_norm": 0.8166175794353612, "learning_rate": 9.358663307176323e-06, "loss": 0.8398, "step": 2780 }, { "epoch": 0.54, "grad_norm": 1.2810143210028186, "learning_rate": 9.352445413210294e-06, "loss": 0.8433, "step": 2781 }, { "epoch": 0.54, "grad_norm": 0.9904657039373211, "learning_rate": 9.346227770647251e-06, "loss": 0.8577, "step": 2782 }, { "epoch": 0.54, "grad_norm": 0.9311531561481391, "learning_rate": 9.3400103819011e-06, "loss": 0.8689, "step": 2783 }, { "epoch": 0.54, "grad_norm": 1.2534676173444734, "learning_rate": 9.33379324938564e-06, "loss": 0.8008, "step": 2784 }, { "epoch": 0.54, "grad_norm": 1.266319888801415, "learning_rate": 9.327576375514582e-06, "loss": 0.8792, "step": 2785 }, { "epoch": 0.54, "grad_norm": 1.0239318229886336, "learning_rate": 9.321359762701527e-06, "loss": 0.8367, "step": 2786 }, { "epoch": 0.54, "grad_norm": 1.1750016439773847, "learning_rate": 9.315143413359975e-06, "loss": 0.9358, "step": 2787 }, { "epoch": 0.54, "grad_norm": 0.9396019771089948, "learning_rate": 9.308927329903333e-06, "loss": 0.8755, "step": 2788 }, { "epoch": 0.54, "grad_norm": 0.9883269223583607, "learning_rate": 9.302711514744897e-06, "loss": 0.8262, "step": 2789 }, { "epoch": 0.54, "grad_norm": 1.1918859141599718, "learning_rate": 9.296495970297855e-06, "loss": 0.9624, "step": 2790 }, { "epoch": 0.54, "grad_norm": 1.0043451210584822, "learning_rate": 9.290280698975307e-06, "loss": 0.8956, "step": 2791 }, { "epoch": 0.54, "grad_norm": 0.8093445701723063, "learning_rate": 9.284065703190221e-06, "loss": 0.6083, "step": 2792 }, { "epoch": 0.54, "grad_norm": 0.9385220244230043, "learning_rate": 9.27785098535548e-06, "loss": 0.8423, "step": 2793 }, { "epoch": 0.54, "grad_norm": 0.830223274162577, "learning_rate": 9.271636547883856e-06, "loss": 0.615, "step": 2794 }, { "epoch": 0.54, "grad_norm": 0.9964019962281008, "learning_rate": 9.265422393187998e-06, "loss": 0.7961, "step": 2795 }, { "epoch": 0.54, "grad_norm": 1.0569269438883953, "learning_rate": 9.259208523680457e-06, "loss": 0.917, "step": 2796 }, { "epoch": 0.54, "grad_norm": 1.0348757691110018, "learning_rate": 9.252994941773679e-06, "loss": 0.9009, "step": 2797 }, { "epoch": 0.54, "grad_norm": 0.8528028717825231, "learning_rate": 9.24678164987998e-06, "loss": 0.5729, "step": 2798 }, { "epoch": 0.54, "grad_norm": 0.9577298665261474, "learning_rate": 9.24056865041158e-06, "loss": 0.8877, "step": 2799 }, { "epoch": 0.54, "grad_norm": 0.9325345299825175, "learning_rate": 9.234355945780581e-06, "loss": 0.8713, "step": 2800 }, { "epoch": 0.54, "grad_norm": 1.1389596859163376, "learning_rate": 9.228143538398963e-06, "loss": 0.9644, "step": 2801 }, { "epoch": 0.54, "grad_norm": 0.8880005253820578, "learning_rate": 9.221931430678598e-06, "loss": 0.8848, "step": 2802 }, { "epoch": 0.54, "grad_norm": 0.9785374702748629, "learning_rate": 9.215719625031245e-06, "loss": 0.8447, "step": 2803 }, { "epoch": 0.54, "grad_norm": 0.8204175277299783, "learning_rate": 9.209508123868534e-06, "loss": 0.5979, "step": 2804 }, { "epoch": 0.54, "grad_norm": 1.0137330367080026, "learning_rate": 9.203296929601986e-06, "loss": 0.87, "step": 2805 }, { "epoch": 0.54, "grad_norm": 0.9177200779520103, "learning_rate": 9.197086044643004e-06, "loss": 0.8728, "step": 2806 }, { "epoch": 0.54, "grad_norm": 1.0260647802126648, "learning_rate": 9.190875471402865e-06, "loss": 0.853, "step": 2807 }, { "epoch": 0.54, "grad_norm": 0.9927903766883044, "learning_rate": 9.184665212292723e-06, "loss": 0.8333, "step": 2808 }, { "epoch": 0.54, "grad_norm": 1.0177708126915286, "learning_rate": 9.178455269723623e-06, "loss": 0.8306, "step": 2809 }, { "epoch": 0.54, "grad_norm": 0.9623712702069568, "learning_rate": 9.172245646106471e-06, "loss": 0.8833, "step": 2810 }, { "epoch": 0.54, "grad_norm": 1.117671272848693, "learning_rate": 9.166036343852061e-06, "loss": 0.8604, "step": 2811 }, { "epoch": 0.54, "grad_norm": 0.9810835230795216, "learning_rate": 9.159827365371055e-06, "loss": 0.8643, "step": 2812 }, { "epoch": 0.54, "grad_norm": 0.767579436907727, "learning_rate": 9.153618713073995e-06, "loss": 0.5952, "step": 2813 }, { "epoch": 0.54, "grad_norm": 1.1780093097120679, "learning_rate": 9.14741038937129e-06, "loss": 0.8782, "step": 2814 }, { "epoch": 0.54, "grad_norm": 1.0204000610066122, "learning_rate": 9.141202396673232e-06, "loss": 0.843, "step": 2815 }, { "epoch": 0.54, "grad_norm": 1.0581852475084061, "learning_rate": 9.13499473738997e-06, "loss": 0.906, "step": 2816 }, { "epoch": 0.54, "grad_norm": 1.0921041678050658, "learning_rate": 9.128787413931536e-06, "loss": 0.8652, "step": 2817 }, { "epoch": 0.54, "grad_norm": 1.145806364510612, "learning_rate": 9.122580428707822e-06, "loss": 0.8496, "step": 2818 }, { "epoch": 0.54, "grad_norm": 1.0430176670768574, "learning_rate": 9.116373784128597e-06, "loss": 0.9072, "step": 2819 }, { "epoch": 0.54, "grad_norm": 0.9468016861092516, "learning_rate": 9.110167482603494e-06, "loss": 0.8884, "step": 2820 }, { "epoch": 0.54, "grad_norm": 0.9332442826639571, "learning_rate": 9.10396152654201e-06, "loss": 0.8027, "step": 2821 }, { "epoch": 0.54, "grad_norm": 1.033524255455384, "learning_rate": 9.097755918353513e-06, "loss": 0.9453, "step": 2822 }, { "epoch": 0.54, "grad_norm": 0.7659661435588756, "learning_rate": 9.091550660447236e-06, "loss": 0.5647, "step": 2823 }, { "epoch": 0.54, "grad_norm": 1.1382557018861765, "learning_rate": 9.08534575523227e-06, "loss": 0.9148, "step": 2824 }, { "epoch": 0.54, "grad_norm": 1.1363530535486246, "learning_rate": 9.079141205117573e-06, "loss": 0.8921, "step": 2825 }, { "epoch": 0.54, "grad_norm": 0.9546979608797697, "learning_rate": 9.072937012511968e-06, "loss": 0.886, "step": 2826 }, { "epoch": 0.54, "grad_norm": 0.7850643458240489, "learning_rate": 9.066733179824134e-06, "loss": 0.6194, "step": 2827 }, { "epoch": 0.54, "grad_norm": 1.1506457642924561, "learning_rate": 9.060529709462613e-06, "loss": 0.8672, "step": 2828 }, { "epoch": 0.54, "grad_norm": 1.0555432916189653, "learning_rate": 9.054326603835807e-06, "loss": 0.8601, "step": 2829 }, { "epoch": 0.54, "grad_norm": 1.0124069141642806, "learning_rate": 9.048123865351971e-06, "loss": 0.8936, "step": 2830 }, { "epoch": 0.54, "grad_norm": 1.1812066603444726, "learning_rate": 9.041921496419225e-06, "loss": 0.8955, "step": 2831 }, { "epoch": 0.54, "grad_norm": 1.1659646278679716, "learning_rate": 9.035719499445545e-06, "loss": 0.8914, "step": 2832 }, { "epoch": 0.55, "grad_norm": 1.1650038183849611, "learning_rate": 9.029517876838755e-06, "loss": 0.8779, "step": 2833 }, { "epoch": 0.55, "grad_norm": 1.0891290086885796, "learning_rate": 9.023316631006536e-06, "loss": 0.8539, "step": 2834 }, { "epoch": 0.55, "grad_norm": 1.068780883674325, "learning_rate": 9.017115764356436e-06, "loss": 0.9172, "step": 2835 }, { "epoch": 0.55, "grad_norm": 0.7337948812419539, "learning_rate": 9.010915279295833e-06, "loss": 0.5881, "step": 2836 }, { "epoch": 0.55, "grad_norm": 0.8647227997660717, "learning_rate": 9.004715178231975e-06, "loss": 0.5828, "step": 2837 }, { "epoch": 0.55, "grad_norm": 0.9107247465563272, "learning_rate": 8.998515463571953e-06, "loss": 0.8613, "step": 2838 }, { "epoch": 0.55, "grad_norm": 1.1561924403151014, "learning_rate": 8.992316137722711e-06, "loss": 0.9341, "step": 2839 }, { "epoch": 0.55, "grad_norm": 1.050847125470157, "learning_rate": 8.986117203091042e-06, "loss": 0.8679, "step": 2840 }, { "epoch": 0.55, "grad_norm": 1.1494619607465903, "learning_rate": 8.97991866208358e-06, "loss": 0.8667, "step": 2841 }, { "epoch": 0.55, "grad_norm": 0.8754448858655626, "learning_rate": 8.973720517106814e-06, "loss": 0.8296, "step": 2842 }, { "epoch": 0.55, "grad_norm": 1.052255944318754, "learning_rate": 8.967522770567086e-06, "loss": 0.8401, "step": 2843 }, { "epoch": 0.55, "grad_norm": 1.0081861995451693, "learning_rate": 8.961325424870561e-06, "loss": 0.8607, "step": 2844 }, { "epoch": 0.55, "grad_norm": 1.0000499600171748, "learning_rate": 8.955128482423271e-06, "loss": 0.856, "step": 2845 }, { "epoch": 0.55, "grad_norm": 0.8771844384391322, "learning_rate": 8.948931945631082e-06, "loss": 0.7922, "step": 2846 }, { "epoch": 0.55, "grad_norm": 1.024742722859919, "learning_rate": 8.9427358168997e-06, "loss": 0.9077, "step": 2847 }, { "epoch": 0.55, "grad_norm": 0.9303454627315063, "learning_rate": 8.936540098634675e-06, "loss": 0.8523, "step": 2848 }, { "epoch": 0.55, "grad_norm": 0.9193583934801679, "learning_rate": 8.930344793241404e-06, "loss": 0.8479, "step": 2849 }, { "epoch": 0.55, "grad_norm": 1.0702732808391682, "learning_rate": 8.924149903125108e-06, "loss": 0.948, "step": 2850 }, { "epoch": 0.55, "grad_norm": 1.0212568671130298, "learning_rate": 8.917955430690865e-06, "loss": 0.8794, "step": 2851 }, { "epoch": 0.55, "grad_norm": 0.9872292240745267, "learning_rate": 8.91176137834358e-06, "loss": 0.8684, "step": 2852 }, { "epoch": 0.55, "grad_norm": 0.97833193098866, "learning_rate": 8.905567748487997e-06, "loss": 0.9197, "step": 2853 }, { "epoch": 0.55, "grad_norm": 0.9855301288063855, "learning_rate": 8.899374543528695e-06, "loss": 0.8843, "step": 2854 }, { "epoch": 0.55, "grad_norm": 1.0842900163180862, "learning_rate": 8.893181765870094e-06, "loss": 0.9087, "step": 2855 }, { "epoch": 0.55, "grad_norm": 1.045979004293745, "learning_rate": 8.886989417916435e-06, "loss": 0.9219, "step": 2856 }, { "epoch": 0.55, "grad_norm": 1.0729610575613673, "learning_rate": 8.88079750207181e-06, "loss": 0.873, "step": 2857 }, { "epoch": 0.55, "grad_norm": 0.9296206149215928, "learning_rate": 8.87460602074013e-06, "loss": 0.8499, "step": 2858 }, { "epoch": 0.55, "grad_norm": 0.994006772295316, "learning_rate": 8.86841497632514e-06, "loss": 0.8936, "step": 2859 }, { "epoch": 0.55, "grad_norm": 0.8607955091942208, "learning_rate": 8.862224371230418e-06, "loss": 0.8796, "step": 2860 }, { "epoch": 0.55, "grad_norm": 1.0100493816363927, "learning_rate": 8.85603420785937e-06, "loss": 0.8994, "step": 2861 }, { "epoch": 0.55, "grad_norm": 1.1007354735439727, "learning_rate": 8.84984448861523e-06, "loss": 0.9226, "step": 2862 }, { "epoch": 0.55, "grad_norm": 1.012679601122558, "learning_rate": 8.84365521590106e-06, "loss": 0.8655, "step": 2863 }, { "epoch": 0.55, "grad_norm": 0.8091807430381529, "learning_rate": 8.837466392119752e-06, "loss": 0.6064, "step": 2864 }, { "epoch": 0.55, "grad_norm": 0.9770813393377619, "learning_rate": 8.831278019674017e-06, "loss": 0.6172, "step": 2865 }, { "epoch": 0.55, "grad_norm": 1.0179308368790994, "learning_rate": 8.825090100966396e-06, "loss": 0.8804, "step": 2866 }, { "epoch": 0.55, "grad_norm": 0.9721727114839078, "learning_rate": 8.818902638399247e-06, "loss": 0.8816, "step": 2867 }, { "epoch": 0.55, "grad_norm": 1.2604552972324417, "learning_rate": 8.81271563437476e-06, "loss": 0.7764, "step": 2868 }, { "epoch": 0.55, "grad_norm": 1.0498532443682491, "learning_rate": 8.806529091294948e-06, "loss": 0.9011, "step": 2869 }, { "epoch": 0.55, "grad_norm": 1.2710392069383114, "learning_rate": 8.800343011561633e-06, "loss": 0.8643, "step": 2870 }, { "epoch": 0.55, "grad_norm": 1.1252689212968061, "learning_rate": 8.794157397576464e-06, "loss": 0.905, "step": 2871 }, { "epoch": 0.55, "grad_norm": 0.9757443123836342, "learning_rate": 8.787972251740916e-06, "loss": 0.8267, "step": 2872 }, { "epoch": 0.55, "grad_norm": 1.0908071542550726, "learning_rate": 8.781787576456269e-06, "loss": 0.8474, "step": 2873 }, { "epoch": 0.55, "grad_norm": 1.1030159804445723, "learning_rate": 8.775603374123627e-06, "loss": 0.8765, "step": 2874 }, { "epoch": 0.55, "grad_norm": 1.1360854835859417, "learning_rate": 8.769419647143917e-06, "loss": 0.8807, "step": 2875 }, { "epoch": 0.55, "grad_norm": 0.8993627782628957, "learning_rate": 8.763236397917865e-06, "loss": 0.6106, "step": 2876 }, { "epoch": 0.55, "grad_norm": 1.038610148604217, "learning_rate": 8.757053628846028e-06, "loss": 0.8933, "step": 2877 }, { "epoch": 0.55, "grad_norm": 0.8577077616818661, "learning_rate": 8.75087134232877e-06, "loss": 0.6412, "step": 2878 }, { "epoch": 0.55, "grad_norm": 1.0312630745571898, "learning_rate": 8.744689540766265e-06, "loss": 0.925, "step": 2879 }, { "epoch": 0.55, "grad_norm": 1.1930539943058494, "learning_rate": 8.738508226558499e-06, "loss": 0.9084, "step": 2880 }, { "epoch": 0.55, "grad_norm": 0.9483412124695405, "learning_rate": 8.73232740210528e-06, "loss": 0.8491, "step": 2881 }, { "epoch": 0.55, "grad_norm": 1.0160963140919763, "learning_rate": 8.726147069806206e-06, "loss": 0.917, "step": 2882 }, { "epoch": 0.55, "grad_norm": 1.011094435181273, "learning_rate": 8.719967232060698e-06, "loss": 0.8372, "step": 2883 }, { "epoch": 0.55, "grad_norm": 1.0413667330967513, "learning_rate": 8.713787891267988e-06, "loss": 0.8643, "step": 2884 }, { "epoch": 0.56, "grad_norm": 0.742674425664363, "learning_rate": 8.707609049827102e-06, "loss": 0.621, "step": 2885 }, { "epoch": 0.56, "grad_norm": 1.0187820457869783, "learning_rate": 8.70143071013688e-06, "loss": 0.8204, "step": 2886 }, { "epoch": 0.56, "grad_norm": 1.098487666184741, "learning_rate": 8.695252874595972e-06, "loss": 0.9512, "step": 2887 }, { "epoch": 0.56, "grad_norm": 1.0068875282475016, "learning_rate": 8.689075545602816e-06, "loss": 0.9373, "step": 2888 }, { "epoch": 0.56, "grad_norm": 1.05837897443677, "learning_rate": 8.68289872555567e-06, "loss": 0.8623, "step": 2889 }, { "epoch": 0.56, "grad_norm": 0.9154660532462875, "learning_rate": 8.676722416852594e-06, "loss": 0.9421, "step": 2890 }, { "epoch": 0.56, "grad_norm": 1.2277945792747706, "learning_rate": 8.670546621891434e-06, "loss": 0.9099, "step": 2891 }, { "epoch": 0.56, "grad_norm": 0.9765647450659695, "learning_rate": 8.66437134306985e-06, "loss": 0.8464, "step": 2892 }, { "epoch": 0.56, "grad_norm": 0.9642714467445603, "learning_rate": 8.658196582785297e-06, "loss": 0.8833, "step": 2893 }, { "epoch": 0.56, "grad_norm": 0.9675176484058674, "learning_rate": 8.652022343435027e-06, "loss": 0.8403, "step": 2894 }, { "epoch": 0.56, "grad_norm": 0.98195189027893, "learning_rate": 8.645848627416102e-06, "loss": 0.8401, "step": 2895 }, { "epoch": 0.56, "grad_norm": 1.0522273110662737, "learning_rate": 8.63967543712536e-06, "loss": 0.8557, "step": 2896 }, { "epoch": 0.56, "grad_norm": 0.9438167081969988, "learning_rate": 8.633502774959453e-06, "loss": 0.8674, "step": 2897 }, { "epoch": 0.56, "grad_norm": 1.057596327539857, "learning_rate": 8.627330643314818e-06, "loss": 0.8286, "step": 2898 }, { "epoch": 0.56, "grad_norm": 0.9928184933019238, "learning_rate": 8.62115904458769e-06, "loss": 0.866, "step": 2899 }, { "epoch": 0.56, "grad_norm": 1.0720430190413064, "learning_rate": 8.614987981174093e-06, "loss": 0.8799, "step": 2900 }, { "epoch": 0.56, "grad_norm": 0.9664718628303095, "learning_rate": 8.608817455469854e-06, "loss": 0.9004, "step": 2901 }, { "epoch": 0.56, "grad_norm": 0.9871996279869181, "learning_rate": 8.602647469870573e-06, "loss": 0.8528, "step": 2902 }, { "epoch": 0.56, "grad_norm": 1.0859319854843306, "learning_rate": 8.596478026771658e-06, "loss": 0.8704, "step": 2903 }, { "epoch": 0.56, "grad_norm": 1.0678200295269773, "learning_rate": 8.590309128568303e-06, "loss": 0.8274, "step": 2904 }, { "epoch": 0.56, "grad_norm": 0.980358519736169, "learning_rate": 8.584140777655476e-06, "loss": 0.7975, "step": 2905 }, { "epoch": 0.56, "grad_norm": 1.0706175942287999, "learning_rate": 8.57797297642795e-06, "loss": 0.8679, "step": 2906 }, { "epoch": 0.56, "grad_norm": 0.9784814335841805, "learning_rate": 8.571805727280278e-06, "loss": 0.8767, "step": 2907 }, { "epoch": 0.56, "grad_norm": 1.136987887593669, "learning_rate": 8.565639032606794e-06, "loss": 0.5676, "step": 2908 }, { "epoch": 0.56, "grad_norm": 0.8648686252180874, "learning_rate": 8.559472894801623e-06, "loss": 0.619, "step": 2909 }, { "epoch": 0.56, "grad_norm": 1.0714004340479184, "learning_rate": 8.553307316258678e-06, "loss": 0.8623, "step": 2910 }, { "epoch": 0.56, "grad_norm": 1.0318882048397076, "learning_rate": 8.547142299371642e-06, "loss": 0.9211, "step": 2911 }, { "epoch": 0.56, "grad_norm": 1.1383562670957772, "learning_rate": 8.540977846533986e-06, "loss": 0.9175, "step": 2912 }, { "epoch": 0.56, "grad_norm": 0.9607588111946046, "learning_rate": 8.534813960138968e-06, "loss": 0.8879, "step": 2913 }, { "epoch": 0.56, "grad_norm": 0.7937833710591222, "learning_rate": 8.528650642579618e-06, "loss": 0.5573, "step": 2914 }, { "epoch": 0.56, "grad_norm": 0.9867815081603996, "learning_rate": 8.52248789624875e-06, "loss": 0.8687, "step": 2915 }, { "epoch": 0.56, "grad_norm": 1.0878315085344015, "learning_rate": 8.516325723538949e-06, "loss": 0.9294, "step": 2916 }, { "epoch": 0.56, "grad_norm": 0.9265379824609034, "learning_rate": 8.510164126842591e-06, "loss": 0.8062, "step": 2917 }, { "epoch": 0.56, "grad_norm": 1.157319816421326, "learning_rate": 8.504003108551814e-06, "loss": 0.9443, "step": 2918 }, { "epoch": 0.56, "grad_norm": 1.0696379296096243, "learning_rate": 8.497842671058539e-06, "loss": 0.8845, "step": 2919 }, { "epoch": 0.56, "grad_norm": 0.883058495963871, "learning_rate": 8.491682816754456e-06, "loss": 0.8491, "step": 2920 }, { "epoch": 0.56, "grad_norm": 0.9970356602910109, "learning_rate": 8.485523548031044e-06, "loss": 0.8367, "step": 2921 }, { "epoch": 0.56, "grad_norm": 0.9996494213265016, "learning_rate": 8.479364867279529e-06, "loss": 0.8086, "step": 2922 }, { "epoch": 0.56, "grad_norm": 1.093234068979633, "learning_rate": 8.47320677689093e-06, "loss": 0.875, "step": 2923 }, { "epoch": 0.56, "grad_norm": 0.9108177306708831, "learning_rate": 8.467049279256034e-06, "loss": 0.8247, "step": 2924 }, { "epoch": 0.56, "grad_norm": 1.050633462852865, "learning_rate": 8.460892376765387e-06, "loss": 0.8835, "step": 2925 }, { "epoch": 0.56, "grad_norm": 1.1948870483344434, "learning_rate": 8.45473607180931e-06, "loss": 0.8556, "step": 2926 }, { "epoch": 0.56, "grad_norm": 1.0639719693670502, "learning_rate": 8.448580366777898e-06, "loss": 0.9158, "step": 2927 }, { "epoch": 0.56, "grad_norm": 1.3881975819650776, "learning_rate": 8.442425264061e-06, "loss": 0.8345, "step": 2928 }, { "epoch": 0.56, "grad_norm": 1.0480256156048355, "learning_rate": 8.436270766048245e-06, "loss": 0.9192, "step": 2929 }, { "epoch": 0.56, "grad_norm": 1.0323812491542106, "learning_rate": 8.430116875129023e-06, "loss": 0.825, "step": 2930 }, { "epoch": 0.56, "grad_norm": 0.8496534297746116, "learning_rate": 8.42396359369248e-06, "loss": 0.6206, "step": 2931 }, { "epoch": 0.56, "grad_norm": 1.0304729973486417, "learning_rate": 8.417810924127533e-06, "loss": 0.8416, "step": 2932 }, { "epoch": 0.56, "grad_norm": 1.0679625106617405, "learning_rate": 8.411658868822866e-06, "loss": 0.8899, "step": 2933 }, { "epoch": 0.56, "grad_norm": 0.9803073896795724, "learning_rate": 8.40550743016691e-06, "loss": 0.9006, "step": 2934 }, { "epoch": 0.56, "grad_norm": 0.9740139963318936, "learning_rate": 8.39935661054787e-06, "loss": 0.8386, "step": 2935 }, { "epoch": 0.56, "grad_norm": 1.0859943073151606, "learning_rate": 8.393206412353709e-06, "loss": 0.8511, "step": 2936 }, { "epoch": 0.57, "grad_norm": 0.8748644082190287, "learning_rate": 8.38705683797214e-06, "loss": 0.6225, "step": 2937 }, { "epoch": 0.57, "grad_norm": 0.6710068847219928, "learning_rate": 8.38090788979064e-06, "loss": 0.3643, "step": 2938 }, { "epoch": 0.57, "grad_norm": 1.1118864645515651, "learning_rate": 8.374759570196448e-06, "loss": 0.9299, "step": 2939 }, { "epoch": 0.57, "grad_norm": 1.0154073428107475, "learning_rate": 8.368611881576547e-06, "loss": 0.8494, "step": 2940 }, { "epoch": 0.57, "grad_norm": 1.050694820596872, "learning_rate": 8.362464826317687e-06, "loss": 0.8684, "step": 2941 }, { "epoch": 0.57, "grad_norm": 1.058603614192837, "learning_rate": 8.35631840680636e-06, "loss": 0.8916, "step": 2942 }, { "epoch": 0.57, "grad_norm": 0.8430807521933504, "learning_rate": 8.35017262542882e-06, "loss": 0.6024, "step": 2943 }, { "epoch": 0.57, "grad_norm": 1.0562229603550763, "learning_rate": 8.344027484571075e-06, "loss": 0.8981, "step": 2944 }, { "epoch": 0.57, "grad_norm": 1.234155789358388, "learning_rate": 8.337882986618877e-06, "loss": 0.8706, "step": 2945 }, { "epoch": 0.57, "grad_norm": 1.1073043258788324, "learning_rate": 8.331739133957729e-06, "loss": 0.8848, "step": 2946 }, { "epoch": 0.57, "grad_norm": 0.8955726788540972, "learning_rate": 8.325595928972894e-06, "loss": 0.8489, "step": 2947 }, { "epoch": 0.57, "grad_norm": 0.9856367693234207, "learning_rate": 8.319453374049367e-06, "loss": 0.8506, "step": 2948 }, { "epoch": 0.57, "grad_norm": 1.0299000194406356, "learning_rate": 8.313311471571903e-06, "loss": 0.9082, "step": 2949 }, { "epoch": 0.57, "grad_norm": 1.0331157751513131, "learning_rate": 8.307170223925003e-06, "loss": 0.8999, "step": 2950 }, { "epoch": 0.57, "grad_norm": 0.9643999101563071, "learning_rate": 8.301029633492907e-06, "loss": 0.8669, "step": 2951 }, { "epoch": 0.57, "grad_norm": 1.0209272006565935, "learning_rate": 8.294889702659602e-06, "loss": 0.8955, "step": 2952 }, { "epoch": 0.57, "grad_norm": 1.0872316807875613, "learning_rate": 8.288750433808828e-06, "loss": 0.8931, "step": 2953 }, { "epoch": 0.57, "grad_norm": 0.8853047551460298, "learning_rate": 8.282611829324049e-06, "loss": 0.884, "step": 2954 }, { "epoch": 0.57, "grad_norm": 1.0170525932266568, "learning_rate": 8.276473891588492e-06, "loss": 0.86, "step": 2955 }, { "epoch": 0.57, "grad_norm": 0.8932459180503526, "learning_rate": 8.270336622985116e-06, "loss": 0.8467, "step": 2956 }, { "epoch": 0.57, "grad_norm": 1.0800914985611723, "learning_rate": 8.264200025896616e-06, "loss": 0.9426, "step": 2957 }, { "epoch": 0.57, "grad_norm": 1.1558634180813345, "learning_rate": 8.258064102705428e-06, "loss": 0.9243, "step": 2958 }, { "epoch": 0.57, "grad_norm": 1.126735629286387, "learning_rate": 8.251928855793736e-06, "loss": 0.8689, "step": 2959 }, { "epoch": 0.57, "grad_norm": 1.2397262938632247, "learning_rate": 8.245794287543447e-06, "loss": 0.8357, "step": 2960 }, { "epoch": 0.57, "grad_norm": 1.0090657445153834, "learning_rate": 8.239660400336213e-06, "loss": 0.9146, "step": 2961 }, { "epoch": 0.57, "grad_norm": 1.1487813683330346, "learning_rate": 8.233527196553428e-06, "loss": 0.9219, "step": 2962 }, { "epoch": 0.57, "grad_norm": 1.0195918338092993, "learning_rate": 8.227394678576204e-06, "loss": 0.8564, "step": 2963 }, { "epoch": 0.57, "grad_norm": 0.8529981374517275, "learning_rate": 8.221262848785395e-06, "loss": 0.5894, "step": 2964 }, { "epoch": 0.57, "grad_norm": 0.9828982048094504, "learning_rate": 8.215131709561597e-06, "loss": 0.843, "step": 2965 }, { "epoch": 0.57, "grad_norm": 1.0239749609215485, "learning_rate": 8.20900126328512e-06, "loss": 0.8789, "step": 2966 }, { "epoch": 0.57, "grad_norm": 1.254115433713503, "learning_rate": 8.202871512336023e-06, "loss": 0.8999, "step": 2967 }, { "epoch": 0.57, "grad_norm": 1.3060984885619473, "learning_rate": 8.196742459094079e-06, "loss": 0.8657, "step": 2968 }, { "epoch": 0.57, "grad_norm": 0.9919120946543978, "learning_rate": 8.190614105938796e-06, "loss": 0.8484, "step": 2969 }, { "epoch": 0.57, "grad_norm": 0.9485918010947858, "learning_rate": 8.184486455249424e-06, "loss": 0.8594, "step": 2970 }, { "epoch": 0.57, "grad_norm": 0.8687218789150013, "learning_rate": 8.178359509404916e-06, "loss": 0.6033, "step": 2971 }, { "epoch": 0.57, "grad_norm": 1.016111839395148, "learning_rate": 8.172233270783966e-06, "loss": 0.835, "step": 2972 }, { "epoch": 0.57, "grad_norm": 1.0484370953634423, "learning_rate": 8.166107741764997e-06, "loss": 0.8318, "step": 2973 }, { "epoch": 0.57, "grad_norm": 0.9313828266087354, "learning_rate": 8.15998292472614e-06, "loss": 0.8774, "step": 2974 }, { "epoch": 0.57, "grad_norm": 0.9466297860714286, "learning_rate": 8.153858822045267e-06, "loss": 0.9219, "step": 2975 }, { "epoch": 0.57, "grad_norm": 1.1543441060249897, "learning_rate": 8.147735436099967e-06, "loss": 0.9314, "step": 2976 }, { "epoch": 0.57, "grad_norm": 0.7781099869292825, "learning_rate": 8.141612769267543e-06, "loss": 0.6216, "step": 2977 }, { "epoch": 0.57, "grad_norm": 0.9791185625815975, "learning_rate": 8.135490823925027e-06, "loss": 0.9363, "step": 2978 }, { "epoch": 0.57, "grad_norm": 1.0731898372914654, "learning_rate": 8.129369602449176e-06, "loss": 0.8569, "step": 2979 }, { "epoch": 0.57, "grad_norm": 1.0064940871233745, "learning_rate": 8.123249107216446e-06, "loss": 0.9116, "step": 2980 }, { "epoch": 0.57, "grad_norm": 0.9988815491421369, "learning_rate": 8.117129340603032e-06, "loss": 0.8599, "step": 2981 }, { "epoch": 0.57, "grad_norm": 1.0088824576741229, "learning_rate": 8.111010304984841e-06, "loss": 0.8597, "step": 2982 }, { "epoch": 0.57, "grad_norm": 1.0060588917721225, "learning_rate": 8.104892002737488e-06, "loss": 0.8579, "step": 2983 }, { "epoch": 0.57, "grad_norm": 1.1230077691111184, "learning_rate": 8.098774436236308e-06, "loss": 0.8691, "step": 2984 }, { "epoch": 0.57, "grad_norm": 1.0109197156600616, "learning_rate": 8.092657607856356e-06, "loss": 0.8706, "step": 2985 }, { "epoch": 0.57, "grad_norm": 1.1330326363820218, "learning_rate": 8.086541519972388e-06, "loss": 0.9407, "step": 2986 }, { "epoch": 0.57, "grad_norm": 1.195401658016351, "learning_rate": 8.080426174958886e-06, "loss": 0.8457, "step": 2987 }, { "epoch": 0.57, "grad_norm": 1.0926376163340625, "learning_rate": 8.074311575190039e-06, "loss": 0.8933, "step": 2988 }, { "epoch": 0.58, "grad_norm": 1.0636737967238088, "learning_rate": 8.068197723039738e-06, "loss": 0.8279, "step": 2989 }, { "epoch": 0.58, "grad_norm": 1.007500541767251, "learning_rate": 8.062084620881598e-06, "loss": 0.8616, "step": 2990 }, { "epoch": 0.58, "grad_norm": 0.9739172852542545, "learning_rate": 8.055972271088933e-06, "loss": 0.8325, "step": 2991 }, { "epoch": 0.58, "grad_norm": 1.0978629858928919, "learning_rate": 8.049860676034762e-06, "loss": 0.8467, "step": 2992 }, { "epoch": 0.58, "grad_norm": 1.1552339542652188, "learning_rate": 8.043749838091828e-06, "loss": 0.8943, "step": 2993 }, { "epoch": 0.58, "grad_norm": 0.9932074441221753, "learning_rate": 8.037639759632558e-06, "loss": 0.9199, "step": 2994 }, { "epoch": 0.58, "grad_norm": 1.0233393086947937, "learning_rate": 8.031530443029099e-06, "loss": 0.8552, "step": 2995 }, { "epoch": 0.58, "grad_norm": 1.052991866096331, "learning_rate": 8.025421890653303e-06, "loss": 0.8838, "step": 2996 }, { "epoch": 0.58, "grad_norm": 1.1622465563595985, "learning_rate": 8.019314104876712e-06, "loss": 0.8228, "step": 2997 }, { "epoch": 0.58, "grad_norm": 0.9943834436390512, "learning_rate": 8.013207088070582e-06, "loss": 0.9321, "step": 2998 }, { "epoch": 0.58, "grad_norm": 0.8865775941782221, "learning_rate": 8.007100842605872e-06, "loss": 0.8494, "step": 2999 }, { "epoch": 0.58, "grad_norm": 1.0752707729052984, "learning_rate": 8.000995370853227e-06, "loss": 0.947, "step": 3000 }, { "epoch": 0.58, "grad_norm": 1.0665933264575214, "learning_rate": 7.994890675183008e-06, "loss": 0.853, "step": 3001 }, { "epoch": 0.58, "grad_norm": 1.0613208738036497, "learning_rate": 7.98878675796527e-06, "loss": 0.9023, "step": 3002 }, { "epoch": 0.58, "grad_norm": 1.1368842099762315, "learning_rate": 7.98268362156976e-06, "loss": 0.9727, "step": 3003 }, { "epoch": 0.58, "grad_norm": 0.7451583588763392, "learning_rate": 7.976581268365924e-06, "loss": 0.597, "step": 3004 }, { "epoch": 0.58, "grad_norm": 0.9769218665753964, "learning_rate": 7.97047970072291e-06, "loss": 0.8176, "step": 3005 }, { "epoch": 0.58, "grad_norm": 0.9747212319265972, "learning_rate": 7.964378921009552e-06, "loss": 0.9192, "step": 3006 }, { "epoch": 0.58, "grad_norm": 1.2451862920957095, "learning_rate": 7.958278931594385e-06, "loss": 0.8495, "step": 3007 }, { "epoch": 0.58, "grad_norm": 1.0131855695774161, "learning_rate": 7.952179734845642e-06, "loss": 0.8467, "step": 3008 }, { "epoch": 0.58, "grad_norm": 1.1790117327991907, "learning_rate": 7.946081333131227e-06, "loss": 0.8594, "step": 3009 }, { "epoch": 0.58, "grad_norm": 0.9263454450387757, "learning_rate": 7.93998372881876e-06, "loss": 0.9299, "step": 3010 }, { "epoch": 0.58, "grad_norm": 0.7983829308761211, "learning_rate": 7.93388692427554e-06, "loss": 0.5588, "step": 3011 }, { "epoch": 0.58, "grad_norm": 1.0598063309346617, "learning_rate": 7.92779092186855e-06, "loss": 0.8704, "step": 3012 }, { "epoch": 0.58, "grad_norm": 0.9793628025269132, "learning_rate": 7.921695723964473e-06, "loss": 0.8625, "step": 3013 }, { "epoch": 0.58, "grad_norm": 1.011382003889068, "learning_rate": 7.915601332929678e-06, "loss": 0.9204, "step": 3014 }, { "epoch": 0.58, "grad_norm": 0.8838597216733168, "learning_rate": 7.90950775113021e-06, "loss": 0.6357, "step": 3015 }, { "epoch": 0.58, "grad_norm": 0.9912979923974532, "learning_rate": 7.903414980931813e-06, "loss": 0.8884, "step": 3016 }, { "epoch": 0.58, "grad_norm": 0.7662285293499035, "learning_rate": 7.897323024699907e-06, "loss": 0.6066, "step": 3017 }, { "epoch": 0.58, "grad_norm": 1.1438093459745984, "learning_rate": 7.8912318847996e-06, "loss": 0.8606, "step": 3018 }, { "epoch": 0.58, "grad_norm": 1.1217529609210755, "learning_rate": 7.885141563595685e-06, "loss": 0.8501, "step": 3019 }, { "epoch": 0.58, "grad_norm": 1.011140877186971, "learning_rate": 7.879052063452626e-06, "loss": 0.8179, "step": 3020 }, { "epoch": 0.58, "grad_norm": 1.0206582684009178, "learning_rate": 7.872963386734584e-06, "loss": 0.8884, "step": 3021 }, { "epoch": 0.58, "grad_norm": 0.8292580585754751, "learning_rate": 7.866875535805394e-06, "loss": 0.5859, "step": 3022 }, { "epoch": 0.58, "grad_norm": 0.9956835768276544, "learning_rate": 7.860788513028566e-06, "loss": 0.9043, "step": 3023 }, { "epoch": 0.58, "grad_norm": 0.9592311353737507, "learning_rate": 7.85470232076729e-06, "loss": 0.8197, "step": 3024 }, { "epoch": 0.58, "grad_norm": 1.0373014828458804, "learning_rate": 7.848616961384442e-06, "loss": 0.9121, "step": 3025 }, { "epoch": 0.58, "grad_norm": 1.1782633453880982, "learning_rate": 7.842532437242559e-06, "loss": 0.8264, "step": 3026 }, { "epoch": 0.58, "grad_norm": 1.0698306875890788, "learning_rate": 7.83644875070387e-06, "loss": 0.8865, "step": 3027 }, { "epoch": 0.58, "grad_norm": 1.1167409264190442, "learning_rate": 7.83036590413027e-06, "loss": 0.9128, "step": 3028 }, { "epoch": 0.58, "grad_norm": 0.6161618396420776, "learning_rate": 7.824283899883327e-06, "loss": 0.3597, "step": 3029 }, { "epoch": 0.58, "grad_norm": 0.929594196017248, "learning_rate": 7.818202740324287e-06, "loss": 0.8684, "step": 3030 }, { "epoch": 0.58, "grad_norm": 1.029740810569939, "learning_rate": 7.812122427814068e-06, "loss": 0.8816, "step": 3031 }, { "epoch": 0.58, "grad_norm": 0.9939773872645646, "learning_rate": 7.806042964713248e-06, "loss": 0.8213, "step": 3032 }, { "epoch": 0.58, "grad_norm": 1.0214961300396004, "learning_rate": 7.79996435338209e-06, "loss": 0.8132, "step": 3033 }, { "epoch": 0.58, "grad_norm": 1.1774227115855176, "learning_rate": 7.793886596180521e-06, "loss": 0.8789, "step": 3034 }, { "epoch": 0.58, "grad_norm": 0.9846095778239488, "learning_rate": 7.787809695468134e-06, "loss": 0.8259, "step": 3035 }, { "epoch": 0.58, "grad_norm": 0.8436932075557735, "learning_rate": 7.78173365360419e-06, "loss": 0.6171, "step": 3036 }, { "epoch": 0.58, "grad_norm": 0.9454788441446997, "learning_rate": 7.775658472947623e-06, "loss": 0.8701, "step": 3037 }, { "epoch": 0.58, "grad_norm": 1.0855011260491023, "learning_rate": 7.769584155857019e-06, "loss": 0.9019, "step": 3038 }, { "epoch": 0.58, "grad_norm": 1.2096512273423126, "learning_rate": 7.763510704690645e-06, "loss": 0.916, "step": 3039 }, { "epoch": 0.58, "grad_norm": 1.0420243349675637, "learning_rate": 7.757438121806414e-06, "loss": 0.8733, "step": 3040 }, { "epoch": 0.59, "grad_norm": 1.0178092922318114, "learning_rate": 7.75136640956192e-06, "loss": 0.8582, "step": 3041 }, { "epoch": 0.59, "grad_norm": 1.028721956462377, "learning_rate": 7.745295570314412e-06, "loss": 0.8562, "step": 3042 }, { "epoch": 0.59, "grad_norm": 1.0494752867249697, "learning_rate": 7.739225606420793e-06, "loss": 0.7991, "step": 3043 }, { "epoch": 0.59, "grad_norm": 1.0133672729281022, "learning_rate": 7.733156520237633e-06, "loss": 0.8291, "step": 3044 }, { "epoch": 0.59, "grad_norm": 0.8810973180413915, "learning_rate": 7.727088314121165e-06, "loss": 0.5938, "step": 3045 }, { "epoch": 0.59, "grad_norm": 0.9320951745937331, "learning_rate": 7.721020990427268e-06, "loss": 0.8977, "step": 3046 }, { "epoch": 0.59, "grad_norm": 1.0045627071634737, "learning_rate": 7.714954551511489e-06, "loss": 0.8816, "step": 3047 }, { "epoch": 0.59, "grad_norm": 1.0111544816290998, "learning_rate": 7.708888999729036e-06, "loss": 0.8555, "step": 3048 }, { "epoch": 0.59, "grad_norm": 0.7930678697059844, "learning_rate": 7.702824337434756e-06, "loss": 0.5679, "step": 3049 }, { "epoch": 0.59, "grad_norm": 1.1428296869840102, "learning_rate": 7.69676056698316e-06, "loss": 0.8611, "step": 3050 }, { "epoch": 0.59, "grad_norm": 1.1689800412254432, "learning_rate": 7.690697690728417e-06, "loss": 0.8972, "step": 3051 }, { "epoch": 0.59, "grad_norm": 1.0087238713763567, "learning_rate": 7.68463571102434e-06, "loss": 0.8684, "step": 3052 }, { "epoch": 0.59, "grad_norm": 1.0407743017707507, "learning_rate": 7.678574630224399e-06, "loss": 0.8677, "step": 3053 }, { "epoch": 0.59, "grad_norm": 0.9137784422773947, "learning_rate": 7.672514450681721e-06, "loss": 0.554, "step": 3054 }, { "epoch": 0.59, "grad_norm": 0.9820227184186804, "learning_rate": 7.666455174749066e-06, "loss": 0.8402, "step": 3055 }, { "epoch": 0.59, "grad_norm": 1.0091954939973689, "learning_rate": 7.66039680477886e-06, "loss": 0.8247, "step": 3056 }, { "epoch": 0.59, "grad_norm": 0.9521924321696645, "learning_rate": 7.654339343123173e-06, "loss": 0.8328, "step": 3057 }, { "epoch": 0.59, "grad_norm": 1.1249883054251273, "learning_rate": 7.648282792133711e-06, "loss": 0.8303, "step": 3058 }, { "epoch": 0.59, "grad_norm": 0.9379621581034674, "learning_rate": 7.642227154161841e-06, "loss": 0.8879, "step": 3059 }, { "epoch": 0.59, "grad_norm": 1.091152369434868, "learning_rate": 7.636172431558575e-06, "loss": 0.8638, "step": 3060 }, { "epoch": 0.59, "grad_norm": 0.9867939393196007, "learning_rate": 7.630118626674557e-06, "loss": 0.8386, "step": 3061 }, { "epoch": 0.59, "grad_norm": 0.9642631380329337, "learning_rate": 7.6240657418600846e-06, "loss": 0.7883, "step": 3062 }, { "epoch": 0.59, "grad_norm": 0.8943358118290844, "learning_rate": 7.618013779465101e-06, "loss": 0.6345, "step": 3063 }, { "epoch": 0.59, "grad_norm": 1.0585408061150003, "learning_rate": 7.611962741839178e-06, "loss": 0.9045, "step": 3064 }, { "epoch": 0.59, "grad_norm": 1.050123830235129, "learning_rate": 7.6059126313315466e-06, "loss": 0.8191, "step": 3065 }, { "epoch": 0.59, "grad_norm": 1.096024037861199, "learning_rate": 7.599863450291056e-06, "loss": 0.9055, "step": 3066 }, { "epoch": 0.59, "grad_norm": 1.1872308356032446, "learning_rate": 7.593815201066215e-06, "loss": 0.8463, "step": 3067 }, { "epoch": 0.59, "grad_norm": 1.0201885686846415, "learning_rate": 7.587767886005164e-06, "loss": 0.8667, "step": 3068 }, { "epoch": 0.59, "grad_norm": 1.1212568095963542, "learning_rate": 7.581721507455672e-06, "loss": 0.8933, "step": 3069 }, { "epoch": 0.59, "grad_norm": 1.0863205405493146, "learning_rate": 7.575676067765154e-06, "loss": 0.8787, "step": 3070 }, { "epoch": 0.59, "grad_norm": 1.0316792236274868, "learning_rate": 7.569631569280662e-06, "loss": 0.8477, "step": 3071 }, { "epoch": 0.59, "grad_norm": 1.0221645650736824, "learning_rate": 7.563588014348871e-06, "loss": 0.9021, "step": 3072 }, { "epoch": 0.59, "grad_norm": 1.194708547110225, "learning_rate": 7.5575454053161e-06, "loss": 0.8906, "step": 3073 }, { "epoch": 0.59, "grad_norm": 1.1043422502974019, "learning_rate": 7.551503744528304e-06, "loss": 0.8918, "step": 3074 }, { "epoch": 0.59, "grad_norm": 0.9598300979040957, "learning_rate": 7.545463034331054e-06, "loss": 0.8789, "step": 3075 }, { "epoch": 0.59, "grad_norm": 0.9025333579988707, "learning_rate": 7.539423277069568e-06, "loss": 0.8669, "step": 3076 }, { "epoch": 0.59, "grad_norm": 0.7933559444297912, "learning_rate": 7.53338447508869e-06, "loss": 0.6586, "step": 3077 }, { "epoch": 0.59, "grad_norm": 0.9207645908843194, "learning_rate": 7.52734663073288e-06, "loss": 0.835, "step": 3078 }, { "epoch": 0.59, "grad_norm": 0.9726076733952573, "learning_rate": 7.521309746346246e-06, "loss": 0.8804, "step": 3079 }, { "epoch": 0.59, "grad_norm": 0.9910573943781783, "learning_rate": 7.515273824272516e-06, "loss": 0.8833, "step": 3080 }, { "epoch": 0.59, "grad_norm": 1.0307254165950168, "learning_rate": 7.509238866855033e-06, "loss": 0.8779, "step": 3081 }, { "epoch": 0.59, "grad_norm": 0.952998085811008, "learning_rate": 7.503204876436785e-06, "loss": 0.8892, "step": 3082 }, { "epoch": 0.59, "grad_norm": 1.0359989923858381, "learning_rate": 7.497171855360372e-06, "loss": 0.8547, "step": 3083 }, { "epoch": 0.59, "grad_norm": 1.0423178726897466, "learning_rate": 7.491139805968018e-06, "loss": 0.8728, "step": 3084 }, { "epoch": 0.59, "grad_norm": 1.1276297108449047, "learning_rate": 7.485108730601571e-06, "loss": 0.8794, "step": 3085 }, { "epoch": 0.59, "grad_norm": 0.8059265417181026, "learning_rate": 7.4790786316025125e-06, "loss": 0.5547, "step": 3086 }, { "epoch": 0.59, "grad_norm": 0.9404499162199706, "learning_rate": 7.473049511311921e-06, "loss": 0.796, "step": 3087 }, { "epoch": 0.59, "grad_norm": 0.8997222480338001, "learning_rate": 7.467021372070515e-06, "loss": 0.8342, "step": 3088 }, { "epoch": 0.59, "grad_norm": 1.0255145250124071, "learning_rate": 7.46099421621863e-06, "loss": 0.8623, "step": 3089 }, { "epoch": 0.59, "grad_norm": 1.069289692005021, "learning_rate": 7.4549680460962044e-06, "loss": 0.8655, "step": 3090 }, { "epoch": 0.59, "grad_norm": 1.0940412472060408, "learning_rate": 7.448942864042819e-06, "loss": 0.8884, "step": 3091 }, { "epoch": 0.59, "grad_norm": 0.9985373175208245, "learning_rate": 7.4429186723976425e-06, "loss": 0.8604, "step": 3092 }, { "epoch": 0.6, "grad_norm": 0.9950069512899143, "learning_rate": 7.43689547349948e-06, "loss": 0.9487, "step": 3093 }, { "epoch": 0.6, "grad_norm": 0.9733237756068988, "learning_rate": 7.43087326968675e-06, "loss": 0.9294, "step": 3094 }, { "epoch": 0.6, "grad_norm": 1.1480188700518785, "learning_rate": 7.42485206329747e-06, "loss": 0.896, "step": 3095 }, { "epoch": 0.6, "grad_norm": 0.9532690953062243, "learning_rate": 7.418831856669286e-06, "loss": 0.8179, "step": 3096 }, { "epoch": 0.6, "grad_norm": 0.9970086337374411, "learning_rate": 7.41281265213945e-06, "loss": 0.853, "step": 3097 }, { "epoch": 0.6, "grad_norm": 1.07468925857407, "learning_rate": 7.406794452044816e-06, "loss": 0.8657, "step": 3098 }, { "epoch": 0.6, "grad_norm": 0.9479552444012237, "learning_rate": 7.400777258721865e-06, "loss": 0.8004, "step": 3099 }, { "epoch": 0.6, "grad_norm": 0.9779133094587888, "learning_rate": 7.394761074506679e-06, "loss": 0.8394, "step": 3100 }, { "epoch": 0.6, "grad_norm": 0.9460658514107254, "learning_rate": 7.3887459017349405e-06, "loss": 0.8745, "step": 3101 }, { "epoch": 0.6, "grad_norm": 1.0610890763192065, "learning_rate": 7.382731742741953e-06, "loss": 0.8875, "step": 3102 }, { "epoch": 0.6, "grad_norm": 1.0416664787133365, "learning_rate": 7.376718599862621e-06, "loss": 0.8672, "step": 3103 }, { "epoch": 0.6, "grad_norm": 0.9649714845542983, "learning_rate": 7.370706475431446e-06, "loss": 0.8799, "step": 3104 }, { "epoch": 0.6, "grad_norm": 1.0453445170311104, "learning_rate": 7.364695371782547e-06, "loss": 0.8223, "step": 3105 }, { "epoch": 0.6, "grad_norm": 0.9011926759748645, "learning_rate": 7.358685291249644e-06, "loss": 0.8774, "step": 3106 }, { "epoch": 0.6, "grad_norm": 0.9927519165354144, "learning_rate": 7.352676236166051e-06, "loss": 0.8518, "step": 3107 }, { "epoch": 0.6, "grad_norm": 0.811089572711561, "learning_rate": 7.346668208864695e-06, "loss": 0.5993, "step": 3108 }, { "epoch": 0.6, "grad_norm": 1.0357794707470451, "learning_rate": 7.3406612116781e-06, "loss": 0.79, "step": 3109 }, { "epoch": 0.6, "grad_norm": 1.1094116276038735, "learning_rate": 7.33465524693838e-06, "loss": 0.8494, "step": 3110 }, { "epoch": 0.6, "grad_norm": 1.0351413703244896, "learning_rate": 7.328650316977265e-06, "loss": 0.8411, "step": 3111 }, { "epoch": 0.6, "grad_norm": 1.1003500182913437, "learning_rate": 7.322646424126079e-06, "loss": 0.8564, "step": 3112 }, { "epoch": 0.6, "grad_norm": 1.006374386770659, "learning_rate": 7.316643570715729e-06, "loss": 0.8057, "step": 3113 }, { "epoch": 0.6, "grad_norm": 1.0418150207307357, "learning_rate": 7.310641759076742e-06, "loss": 0.8542, "step": 3114 }, { "epoch": 0.6, "grad_norm": 1.0413198265919434, "learning_rate": 7.304640991539216e-06, "loss": 0.8381, "step": 3115 }, { "epoch": 0.6, "grad_norm": 1.045790769385014, "learning_rate": 7.2986412704328625e-06, "loss": 0.8452, "step": 3116 }, { "epoch": 0.6, "grad_norm": 1.004099774122547, "learning_rate": 7.292642598086982e-06, "loss": 0.8936, "step": 3117 }, { "epoch": 0.6, "grad_norm": 1.0503701004797927, "learning_rate": 7.286644976830457e-06, "loss": 0.8774, "step": 3118 }, { "epoch": 0.6, "grad_norm": 0.9097643848233024, "learning_rate": 7.280648408991775e-06, "loss": 0.8743, "step": 3119 }, { "epoch": 0.6, "grad_norm": 0.8604362179039496, "learning_rate": 7.274652896899015e-06, "loss": 0.6251, "step": 3120 }, { "epoch": 0.6, "grad_norm": 0.9714807458876118, "learning_rate": 7.268658442879834e-06, "loss": 0.8099, "step": 3121 }, { "epoch": 0.6, "grad_norm": 1.013186950333332, "learning_rate": 7.262665049261489e-06, "loss": 0.8522, "step": 3122 }, { "epoch": 0.6, "grad_norm": 1.016278305978796, "learning_rate": 7.256672718370824e-06, "loss": 0.8899, "step": 3123 }, { "epoch": 0.6, "grad_norm": 1.2707211865411787, "learning_rate": 7.250681452534261e-06, "loss": 0.9126, "step": 3124 }, { "epoch": 0.6, "grad_norm": 0.9772404979091204, "learning_rate": 7.2446912540778196e-06, "loss": 0.8446, "step": 3125 }, { "epoch": 0.6, "grad_norm": 1.0543140611205364, "learning_rate": 7.238702125327106e-06, "loss": 0.8777, "step": 3126 }, { "epoch": 0.6, "grad_norm": 1.0209214437715728, "learning_rate": 7.232714068607296e-06, "loss": 0.8682, "step": 3127 }, { "epoch": 0.6, "grad_norm": 0.8273621937960366, "learning_rate": 7.226727086243168e-06, "loss": 0.5989, "step": 3128 }, { "epoch": 0.6, "grad_norm": 1.1616812630680569, "learning_rate": 7.220741180559074e-06, "loss": 0.895, "step": 3129 }, { "epoch": 0.6, "grad_norm": 1.0316023233779157, "learning_rate": 7.214756353878942e-06, "loss": 0.8757, "step": 3130 }, { "epoch": 0.6, "grad_norm": 1.093987476802758, "learning_rate": 7.208772608526293e-06, "loss": 0.8284, "step": 3131 }, { "epoch": 0.6, "grad_norm": 0.9754652950126997, "learning_rate": 7.202789946824227e-06, "loss": 0.8979, "step": 3132 }, { "epoch": 0.6, "grad_norm": 0.9909410872769664, "learning_rate": 7.1968083710954075e-06, "loss": 0.854, "step": 3133 }, { "epoch": 0.6, "grad_norm": 0.9607018990240117, "learning_rate": 7.1908278836621e-06, "loss": 0.8132, "step": 3134 }, { "epoch": 0.6, "grad_norm": 0.9011611275441286, "learning_rate": 7.184848486846128e-06, "loss": 0.8711, "step": 3135 }, { "epoch": 0.6, "grad_norm": 1.0941791799331047, "learning_rate": 7.178870182968904e-06, "loss": 0.8344, "step": 3136 }, { "epoch": 0.6, "grad_norm": 0.9071151841598323, "learning_rate": 7.1728929743514065e-06, "loss": 0.8179, "step": 3137 }, { "epoch": 0.6, "grad_norm": 1.0602700343481635, "learning_rate": 7.166916863314199e-06, "loss": 0.8582, "step": 3138 }, { "epoch": 0.6, "grad_norm": 0.9844438922801965, "learning_rate": 7.1609418521774095e-06, "loss": 0.8599, "step": 3139 }, { "epoch": 0.6, "grad_norm": 1.1012085606396893, "learning_rate": 7.154967943260748e-06, "loss": 0.8472, "step": 3140 }, { "epoch": 0.6, "grad_norm": 0.9964689457404304, "learning_rate": 7.148995138883483e-06, "loss": 0.8221, "step": 3141 }, { "epoch": 0.6, "grad_norm": 1.1841227117412851, "learning_rate": 7.143023441364471e-06, "loss": 0.8167, "step": 3142 }, { "epoch": 0.6, "grad_norm": 1.1389648382060475, "learning_rate": 7.13705285302213e-06, "loss": 0.8687, "step": 3143 }, { "epoch": 0.6, "grad_norm": 1.1874646283319839, "learning_rate": 7.131083376174441e-06, "loss": 0.9014, "step": 3144 }, { "epoch": 0.61, "grad_norm": 1.12417756257681, "learning_rate": 7.125115013138966e-06, "loss": 0.8513, "step": 3145 }, { "epoch": 0.61, "grad_norm": 0.8579849472186057, "learning_rate": 7.119147766232832e-06, "loss": 0.5893, "step": 3146 }, { "epoch": 0.61, "grad_norm": 0.9977164843742753, "learning_rate": 7.113181637772721e-06, "loss": 0.8162, "step": 3147 }, { "epoch": 0.61, "grad_norm": 1.0438973883734621, "learning_rate": 7.107216630074895e-06, "loss": 0.9062, "step": 3148 }, { "epoch": 0.61, "grad_norm": 1.0967145117702133, "learning_rate": 7.1012527454551795e-06, "loss": 0.8662, "step": 3149 }, { "epoch": 0.61, "grad_norm": 1.1430752255646641, "learning_rate": 7.09528998622895e-06, "loss": 0.8403, "step": 3150 }, { "epoch": 0.61, "grad_norm": 0.9756570609689478, "learning_rate": 7.089328354711159e-06, "loss": 0.8477, "step": 3151 }, { "epoch": 0.61, "grad_norm": 1.0552277044718905, "learning_rate": 7.083367853216323e-06, "loss": 0.9575, "step": 3152 }, { "epoch": 0.61, "grad_norm": 1.084625699444145, "learning_rate": 7.077408484058505e-06, "loss": 0.8857, "step": 3153 }, { "epoch": 0.61, "grad_norm": 1.049337029642729, "learning_rate": 7.071450249551342e-06, "loss": 0.9065, "step": 3154 }, { "epoch": 0.61, "grad_norm": 0.9402975554548807, "learning_rate": 7.065493152008026e-06, "loss": 0.8696, "step": 3155 }, { "epoch": 0.61, "grad_norm": 1.0951051076692575, "learning_rate": 7.059537193741306e-06, "loss": 0.842, "step": 3156 }, { "epoch": 0.61, "grad_norm": 1.129709249814047, "learning_rate": 7.053582377063489e-06, "loss": 0.8682, "step": 3157 }, { "epoch": 0.61, "grad_norm": 1.0591478083327475, "learning_rate": 7.047628704286446e-06, "loss": 0.8767, "step": 3158 }, { "epoch": 0.61, "grad_norm": 0.8019289951728691, "learning_rate": 7.041676177721588e-06, "loss": 0.6154, "step": 3159 }, { "epoch": 0.61, "grad_norm": 1.002281874222701, "learning_rate": 7.035724799679898e-06, "loss": 0.8472, "step": 3160 }, { "epoch": 0.61, "grad_norm": 0.9565411871201737, "learning_rate": 7.029774572471904e-06, "loss": 0.8923, "step": 3161 }, { "epoch": 0.61, "grad_norm": 0.9861071030914086, "learning_rate": 7.023825498407689e-06, "loss": 0.812, "step": 3162 }, { "epoch": 0.61, "grad_norm": 0.9989373723766432, "learning_rate": 7.0178775797968855e-06, "loss": 0.877, "step": 3163 }, { "epoch": 0.61, "grad_norm": 1.0561438453004364, "learning_rate": 7.011930818948688e-06, "loss": 0.8276, "step": 3164 }, { "epoch": 0.61, "grad_norm": 1.1667763099352297, "learning_rate": 7.005985218171825e-06, "loss": 0.8779, "step": 3165 }, { "epoch": 0.61, "grad_norm": 1.0845612887335652, "learning_rate": 7.000040779774591e-06, "loss": 0.8594, "step": 3166 }, { "epoch": 0.61, "grad_norm": 0.7111929577648227, "learning_rate": 6.994097506064812e-06, "loss": 0.5627, "step": 3167 }, { "epoch": 0.61, "grad_norm": 1.0777319000584886, "learning_rate": 6.9881553993498805e-06, "loss": 0.8604, "step": 3168 }, { "epoch": 0.61, "grad_norm": 1.1007317185849157, "learning_rate": 6.9822144619367275e-06, "loss": 0.8423, "step": 3169 }, { "epoch": 0.61, "grad_norm": 0.8879936310290134, "learning_rate": 6.97627469613182e-06, "loss": 0.8213, "step": 3170 }, { "epoch": 0.61, "grad_norm": 1.157257898123725, "learning_rate": 6.970336104241186e-06, "loss": 0.8561, "step": 3171 }, { "epoch": 0.61, "grad_norm": 1.0430508737074569, "learning_rate": 6.9643986885703955e-06, "loss": 0.856, "step": 3172 }, { "epoch": 0.61, "grad_norm": 0.82992572970282, "learning_rate": 6.958462451424547e-06, "loss": 0.5792, "step": 3173 }, { "epoch": 0.61, "grad_norm": 1.0540363230969267, "learning_rate": 6.952527395108302e-06, "loss": 0.8772, "step": 3174 }, { "epoch": 0.61, "grad_norm": 1.053623098688672, "learning_rate": 6.9465935219258504e-06, "loss": 0.8477, "step": 3175 }, { "epoch": 0.61, "grad_norm": 0.9713670831576617, "learning_rate": 6.9406608341809215e-06, "loss": 0.8552, "step": 3176 }, { "epoch": 0.61, "grad_norm": 1.003944393001097, "learning_rate": 6.934729334176793e-06, "loss": 0.9116, "step": 3177 }, { "epoch": 0.61, "grad_norm": 1.0063295684347586, "learning_rate": 6.928799024216282e-06, "loss": 0.853, "step": 3178 }, { "epoch": 0.61, "grad_norm": 1.1518657444539635, "learning_rate": 6.92286990660173e-06, "loss": 0.9036, "step": 3179 }, { "epoch": 0.61, "grad_norm": 1.1555028753677132, "learning_rate": 6.91694198363503e-06, "loss": 0.8955, "step": 3180 }, { "epoch": 0.61, "grad_norm": 1.0143075244984003, "learning_rate": 6.911015257617606e-06, "loss": 0.8281, "step": 3181 }, { "epoch": 0.61, "grad_norm": 0.8143147778732082, "learning_rate": 6.905089730850416e-06, "loss": 0.5953, "step": 3182 }, { "epoch": 0.61, "grad_norm": 0.9301048867550257, "learning_rate": 6.8991654056339505e-06, "loss": 0.631, "step": 3183 }, { "epoch": 0.61, "grad_norm": 0.9839443601662503, "learning_rate": 6.893242284268244e-06, "loss": 0.8662, "step": 3184 }, { "epoch": 0.61, "grad_norm": 1.0819081534891168, "learning_rate": 6.887320369052848e-06, "loss": 0.8855, "step": 3185 }, { "epoch": 0.61, "grad_norm": 1.105439737427024, "learning_rate": 6.8813996622868584e-06, "loss": 0.8655, "step": 3186 }, { "epoch": 0.61, "grad_norm": 0.8904435129456216, "learning_rate": 6.8754801662688964e-06, "loss": 0.8319, "step": 3187 }, { "epoch": 0.61, "grad_norm": 1.0881546802679785, "learning_rate": 6.869561883297116e-06, "loss": 0.8989, "step": 3188 }, { "epoch": 0.61, "grad_norm": 0.8061402420750681, "learning_rate": 6.863644815669197e-06, "loss": 0.6772, "step": 3189 }, { "epoch": 0.61, "grad_norm": 1.0817403910231398, "learning_rate": 6.857728965682344e-06, "loss": 0.9109, "step": 3190 }, { "epoch": 0.61, "grad_norm": 0.9620316738513721, "learning_rate": 6.851814335633298e-06, "loss": 0.8984, "step": 3191 }, { "epoch": 0.61, "grad_norm": 0.9745260615850612, "learning_rate": 6.8459009278183275e-06, "loss": 0.8298, "step": 3192 }, { "epoch": 0.61, "grad_norm": 0.9838877931120428, "learning_rate": 6.839988744533211e-06, "loss": 0.842, "step": 3193 }, { "epoch": 0.61, "grad_norm": 0.983510760566408, "learning_rate": 6.834077788073268e-06, "loss": 0.8252, "step": 3194 }, { "epoch": 0.61, "grad_norm": 1.0545888413096773, "learning_rate": 6.8281680607333364e-06, "loss": 0.884, "step": 3195 }, { "epoch": 0.61, "grad_norm": 0.9147364524153211, "learning_rate": 6.822259564807768e-06, "loss": 0.8499, "step": 3196 }, { "epoch": 0.62, "grad_norm": 1.1270612428459093, "learning_rate": 6.81635230259045e-06, "loss": 0.8989, "step": 3197 }, { "epoch": 0.62, "grad_norm": 0.7798330518325122, "learning_rate": 6.810446276374789e-06, "loss": 0.5762, "step": 3198 }, { "epoch": 0.62, "grad_norm": 1.1131517157151178, "learning_rate": 6.8045414884536975e-06, "loss": 0.8281, "step": 3199 }, { "epoch": 0.62, "grad_norm": 0.894228370949442, "learning_rate": 6.7986379411196255e-06, "loss": 0.8447, "step": 3200 }, { "epoch": 0.62, "grad_norm": 0.8761306086882894, "learning_rate": 6.7927356366645315e-06, "loss": 0.5942, "step": 3201 }, { "epoch": 0.62, "grad_norm": 1.0183098870080691, "learning_rate": 6.786834577379893e-06, "loss": 0.8354, "step": 3202 }, { "epoch": 0.62, "grad_norm": 1.0318857267945063, "learning_rate": 6.780934765556702e-06, "loss": 0.8254, "step": 3203 }, { "epoch": 0.62, "grad_norm": 0.8502150140427712, "learning_rate": 6.775036203485472e-06, "loss": 0.5898, "step": 3204 }, { "epoch": 0.62, "grad_norm": 1.1058331506497232, "learning_rate": 6.769138893456225e-06, "loss": 0.8652, "step": 3205 }, { "epoch": 0.62, "grad_norm": 0.9736042806477593, "learning_rate": 6.763242837758504e-06, "loss": 0.8217, "step": 3206 }, { "epoch": 0.62, "grad_norm": 0.9611600074533077, "learning_rate": 6.757348038681357e-06, "loss": 0.8628, "step": 3207 }, { "epoch": 0.62, "grad_norm": 0.944449517398146, "learning_rate": 6.751454498513349e-06, "loss": 0.8357, "step": 3208 }, { "epoch": 0.62, "grad_norm": 0.9543089171556255, "learning_rate": 6.745562219542554e-06, "loss": 0.8438, "step": 3209 }, { "epoch": 0.62, "grad_norm": 1.1180261501902116, "learning_rate": 6.7396712040565625e-06, "loss": 0.9004, "step": 3210 }, { "epoch": 0.62, "grad_norm": 1.0756030393447549, "learning_rate": 6.733781454342463e-06, "loss": 0.8545, "step": 3211 }, { "epoch": 0.62, "grad_norm": 1.0740359111719875, "learning_rate": 6.727892972686861e-06, "loss": 0.8479, "step": 3212 }, { "epoch": 0.62, "grad_norm": 1.0433584154607343, "learning_rate": 6.722005761375873e-06, "loss": 0.8989, "step": 3213 }, { "epoch": 0.62, "grad_norm": 1.0558274274590764, "learning_rate": 6.716119822695111e-06, "loss": 0.8218, "step": 3214 }, { "epoch": 0.62, "grad_norm": 1.0580761507802137, "learning_rate": 6.710235158929703e-06, "loss": 0.8584, "step": 3215 }, { "epoch": 0.62, "grad_norm": 1.0292896425673517, "learning_rate": 6.704351772364274e-06, "loss": 0.8403, "step": 3216 }, { "epoch": 0.62, "grad_norm": 1.0503842297767545, "learning_rate": 6.698469665282958e-06, "loss": 0.8777, "step": 3217 }, { "epoch": 0.62, "grad_norm": 1.139131848469581, "learning_rate": 6.692588839969397e-06, "loss": 0.8557, "step": 3218 }, { "epoch": 0.62, "grad_norm": 0.9302556900934054, "learning_rate": 6.6867092987067214e-06, "loss": 0.8818, "step": 3219 }, { "epoch": 0.62, "grad_norm": 1.065852814376815, "learning_rate": 6.680831043777579e-06, "loss": 0.8816, "step": 3220 }, { "epoch": 0.62, "grad_norm": 1.0503737415483287, "learning_rate": 6.674954077464108e-06, "loss": 0.8734, "step": 3221 }, { "epoch": 0.62, "grad_norm": 1.0398132070029495, "learning_rate": 6.6690784020479484e-06, "loss": 0.874, "step": 3222 }, { "epoch": 0.62, "grad_norm": 1.0766303112365618, "learning_rate": 6.6632040198102364e-06, "loss": 0.8589, "step": 3223 }, { "epoch": 0.62, "grad_norm": 0.9895588794675418, "learning_rate": 6.657330933031619e-06, "loss": 0.845, "step": 3224 }, { "epoch": 0.62, "grad_norm": 1.0654039875902936, "learning_rate": 6.651459143992221e-06, "loss": 0.8318, "step": 3225 }, { "epoch": 0.62, "grad_norm": 1.0232901062096507, "learning_rate": 6.645588654971677e-06, "loss": 0.9163, "step": 3226 }, { "epoch": 0.62, "grad_norm": 0.8490555196649949, "learning_rate": 6.639719468249115e-06, "loss": 0.6526, "step": 3227 }, { "epoch": 0.62, "grad_norm": 0.9391025288155278, "learning_rate": 6.633851586103153e-06, "loss": 0.866, "step": 3228 }, { "epoch": 0.62, "grad_norm": 1.0431149722674269, "learning_rate": 6.627985010811903e-06, "loss": 0.8765, "step": 3229 }, { "epoch": 0.62, "grad_norm": 1.1912065132380754, "learning_rate": 6.622119744652977e-06, "loss": 0.8989, "step": 3230 }, { "epoch": 0.62, "grad_norm": 1.1202768933858986, "learning_rate": 6.616255789903467e-06, "loss": 0.8806, "step": 3231 }, { "epoch": 0.62, "grad_norm": 1.0195952545871785, "learning_rate": 6.610393148839964e-06, "loss": 0.8357, "step": 3232 }, { "epoch": 0.62, "grad_norm": 0.9823976304227054, "learning_rate": 6.6045318237385526e-06, "loss": 0.5611, "step": 3233 }, { "epoch": 0.62, "grad_norm": 0.974979355970635, "learning_rate": 6.598671816874794e-06, "loss": 0.9104, "step": 3234 }, { "epoch": 0.62, "grad_norm": 0.9601126866927924, "learning_rate": 6.5928131305237465e-06, "loss": 0.874, "step": 3235 }, { "epoch": 0.62, "grad_norm": 1.0940272933407666, "learning_rate": 6.586955766959958e-06, "loss": 0.8584, "step": 3236 }, { "epoch": 0.62, "grad_norm": 1.0317596232720387, "learning_rate": 6.581099728457451e-06, "loss": 0.8708, "step": 3237 }, { "epoch": 0.62, "grad_norm": 1.148076179915804, "learning_rate": 6.5752450172897466e-06, "loss": 0.8872, "step": 3238 }, { "epoch": 0.62, "grad_norm": 1.002035278675883, "learning_rate": 6.569391635729847e-06, "loss": 0.8665, "step": 3239 }, { "epoch": 0.62, "grad_norm": 1.0083003616793962, "learning_rate": 6.563539586050233e-06, "loss": 0.8003, "step": 3240 }, { "epoch": 0.62, "grad_norm": 1.0177201888746985, "learning_rate": 6.557688870522871e-06, "loss": 0.8303, "step": 3241 }, { "epoch": 0.62, "grad_norm": 0.8344086780988693, "learning_rate": 6.551839491419213e-06, "loss": 0.5963, "step": 3242 }, { "epoch": 0.62, "grad_norm": 1.0748758712029, "learning_rate": 6.545991451010185e-06, "loss": 0.9048, "step": 3243 }, { "epoch": 0.62, "grad_norm": 1.0087189333802329, "learning_rate": 6.5401447515662065e-06, "loss": 0.8369, "step": 3244 }, { "epoch": 0.62, "grad_norm": 1.1640800188333629, "learning_rate": 6.5342993953571556e-06, "loss": 0.8252, "step": 3245 }, { "epoch": 0.62, "grad_norm": 1.1465320085803838, "learning_rate": 6.52845538465241e-06, "loss": 0.8821, "step": 3246 }, { "epoch": 0.62, "grad_norm": 1.01502970617231, "learning_rate": 6.522612721720813e-06, "loss": 0.8459, "step": 3247 }, { "epoch": 0.62, "grad_norm": 0.9075568852002273, "learning_rate": 6.5167714088306865e-06, "loss": 0.832, "step": 3248 }, { "epoch": 0.63, "grad_norm": 0.8298427253615185, "learning_rate": 6.51093144824983e-06, "loss": 0.625, "step": 3249 }, { "epoch": 0.63, "grad_norm": 0.848341955915869, "learning_rate": 6.505092842245519e-06, "loss": 0.6309, "step": 3250 }, { "epoch": 0.63, "grad_norm": 0.8139486248320416, "learning_rate": 6.499255593084498e-06, "loss": 0.5713, "step": 3251 }, { "epoch": 0.63, "grad_norm": 1.0011990913899416, "learning_rate": 6.493419703032991e-06, "loss": 0.8838, "step": 3252 }, { "epoch": 0.63, "grad_norm": 0.9021574223825176, "learning_rate": 6.487585174356691e-06, "loss": 0.8867, "step": 3253 }, { "epoch": 0.63, "grad_norm": 0.827788592500862, "learning_rate": 6.481752009320761e-06, "loss": 0.5946, "step": 3254 }, { "epoch": 0.63, "grad_norm": 1.0461024803035206, "learning_rate": 6.4759202101898366e-06, "loss": 0.9055, "step": 3255 }, { "epoch": 0.63, "grad_norm": 1.1586766348539064, "learning_rate": 6.4700897792280285e-06, "loss": 0.8857, "step": 3256 }, { "epoch": 0.63, "grad_norm": 1.0454641018222404, "learning_rate": 6.464260718698902e-06, "loss": 0.9204, "step": 3257 }, { "epoch": 0.63, "grad_norm": 1.002261447129138, "learning_rate": 6.458433030865503e-06, "loss": 0.8857, "step": 3258 }, { "epoch": 0.63, "grad_norm": 1.0900633574242238, "learning_rate": 6.452606717990346e-06, "loss": 0.8479, "step": 3259 }, { "epoch": 0.63, "grad_norm": 1.0831695260478253, "learning_rate": 6.4467817823354005e-06, "loss": 0.908, "step": 3260 }, { "epoch": 0.63, "grad_norm": 0.9873635342197533, "learning_rate": 6.440958226162104e-06, "loss": 0.8584, "step": 3261 }, { "epoch": 0.63, "grad_norm": 0.9320758464272934, "learning_rate": 6.43513605173137e-06, "loss": 0.8503, "step": 3262 }, { "epoch": 0.63, "grad_norm": 1.0708357992895479, "learning_rate": 6.4293152613035594e-06, "loss": 0.9282, "step": 3263 }, { "epoch": 0.63, "grad_norm": 0.9436900349637497, "learning_rate": 6.4234958571385095e-06, "loss": 0.8595, "step": 3264 }, { "epoch": 0.63, "grad_norm": 1.079551854084158, "learning_rate": 6.4176778414955075e-06, "loss": 0.8989, "step": 3265 }, { "epoch": 0.63, "grad_norm": 1.030324224377352, "learning_rate": 6.4118612166333124e-06, "loss": 0.8201, "step": 3266 }, { "epoch": 0.63, "grad_norm": 0.8607327105987445, "learning_rate": 6.4060459848101354e-06, "loss": 0.5873, "step": 3267 }, { "epoch": 0.63, "grad_norm": 1.087146028021745, "learning_rate": 6.400232148283651e-06, "loss": 0.8787, "step": 3268 }, { "epoch": 0.63, "grad_norm": 0.7962928719016588, "learning_rate": 6.3944197093109885e-06, "loss": 0.6278, "step": 3269 }, { "epoch": 0.63, "grad_norm": 1.0534636309588303, "learning_rate": 6.388608670148741e-06, "loss": 0.8948, "step": 3270 }, { "epoch": 0.63, "grad_norm": 1.1517012781173328, "learning_rate": 6.38279903305295e-06, "loss": 0.8997, "step": 3271 }, { "epoch": 0.63, "grad_norm": 1.0076305149780824, "learning_rate": 6.376990800279119e-06, "loss": 0.8152, "step": 3272 }, { "epoch": 0.63, "grad_norm": 0.9191071061816659, "learning_rate": 6.3711839740822035e-06, "loss": 0.8938, "step": 3273 }, { "epoch": 0.63, "grad_norm": 1.0367134860969829, "learning_rate": 6.3653785567166125e-06, "loss": 0.9238, "step": 3274 }, { "epoch": 0.63, "grad_norm": 0.9888820352245824, "learning_rate": 6.359574550436209e-06, "loss": 0.8594, "step": 3275 }, { "epoch": 0.63, "grad_norm": 0.9567701154364332, "learning_rate": 6.3537719574943105e-06, "loss": 0.8628, "step": 3276 }, { "epoch": 0.63, "grad_norm": 1.0936743953876964, "learning_rate": 6.347970780143678e-06, "loss": 0.8779, "step": 3277 }, { "epoch": 0.63, "grad_norm": 0.9800125298817399, "learning_rate": 6.342171020636533e-06, "loss": 0.8363, "step": 3278 }, { "epoch": 0.63, "grad_norm": 0.8284347130467041, "learning_rate": 6.336372681224543e-06, "loss": 0.6202, "step": 3279 }, { "epoch": 0.63, "grad_norm": 1.1028340664472138, "learning_rate": 6.330575764158819e-06, "loss": 0.8909, "step": 3280 }, { "epoch": 0.63, "grad_norm": 1.072767657390208, "learning_rate": 6.324780271689923e-06, "loss": 0.8521, "step": 3281 }, { "epoch": 0.63, "grad_norm": 0.8215892768360356, "learning_rate": 6.318986206067872e-06, "loss": 0.5834, "step": 3282 }, { "epoch": 0.63, "grad_norm": 0.7944108560294093, "learning_rate": 6.313193569542113e-06, "loss": 0.6002, "step": 3283 }, { "epoch": 0.63, "grad_norm": 1.0135276970743143, "learning_rate": 6.30740236436155e-06, "loss": 0.8506, "step": 3284 }, { "epoch": 0.63, "grad_norm": 0.9640012761835698, "learning_rate": 6.301612592774533e-06, "loss": 0.8743, "step": 3285 }, { "epoch": 0.63, "grad_norm": 1.034700928159037, "learning_rate": 6.295824257028844e-06, "loss": 0.8691, "step": 3286 }, { "epoch": 0.63, "grad_norm": 0.8364233121596113, "learning_rate": 6.290037359371717e-06, "loss": 0.5705, "step": 3287 }, { "epoch": 0.63, "grad_norm": 1.0755652822780162, "learning_rate": 6.284251902049827e-06, "loss": 0.8784, "step": 3288 }, { "epoch": 0.63, "grad_norm": 1.085771694235309, "learning_rate": 6.278467887309283e-06, "loss": 0.9111, "step": 3289 }, { "epoch": 0.63, "grad_norm": 0.9699233226212243, "learning_rate": 6.272685317395644e-06, "loss": 0.7871, "step": 3290 }, { "epoch": 0.63, "grad_norm": 0.8572643589914127, "learning_rate": 6.266904194553896e-06, "loss": 0.5341, "step": 3291 }, { "epoch": 0.63, "grad_norm": 1.0936963177815981, "learning_rate": 6.261124521028477e-06, "loss": 0.8589, "step": 3292 }, { "epoch": 0.63, "grad_norm": 1.1707087741781694, "learning_rate": 6.255346299063252e-06, "loss": 0.8313, "step": 3293 }, { "epoch": 0.63, "grad_norm": 1.0626582133518727, "learning_rate": 6.249569530901525e-06, "loss": 0.8657, "step": 3294 }, { "epoch": 0.63, "grad_norm": 1.0274943950206095, "learning_rate": 6.243794218786034e-06, "loss": 0.864, "step": 3295 }, { "epoch": 0.63, "grad_norm": 1.0463222435068733, "learning_rate": 6.238020364958964e-06, "loss": 0.811, "step": 3296 }, { "epoch": 0.63, "grad_norm": 1.147106666255175, "learning_rate": 6.232247971661912e-06, "loss": 0.8557, "step": 3297 }, { "epoch": 0.63, "grad_norm": 0.9586010791378687, "learning_rate": 6.2264770411359256e-06, "loss": 0.861, "step": 3298 }, { "epoch": 0.63, "grad_norm": 1.0739404176878615, "learning_rate": 6.22070757562148e-06, "loss": 0.8826, "step": 3299 }, { "epoch": 0.63, "grad_norm": 1.0792144511366977, "learning_rate": 6.214939577358479e-06, "loss": 0.866, "step": 3300 }, { "epoch": 0.64, "grad_norm": 1.167579737000423, "learning_rate": 6.209173048586253e-06, "loss": 0.8823, "step": 3301 }, { "epoch": 0.64, "grad_norm": 1.104850493164576, "learning_rate": 6.203407991543577e-06, "loss": 0.8604, "step": 3302 }, { "epoch": 0.64, "grad_norm": 1.0448673398947532, "learning_rate": 6.197644408468635e-06, "loss": 0.864, "step": 3303 }, { "epoch": 0.64, "grad_norm": 1.0389691401429637, "learning_rate": 6.191882301599052e-06, "loss": 0.8116, "step": 3304 }, { "epoch": 0.64, "grad_norm": 1.0167743962393805, "learning_rate": 6.186121673171882e-06, "loss": 0.8943, "step": 3305 }, { "epoch": 0.64, "grad_norm": 1.2280222287839384, "learning_rate": 6.180362525423591e-06, "loss": 0.9397, "step": 3306 }, { "epoch": 0.64, "grad_norm": 0.9517573143845994, "learning_rate": 6.174604860590081e-06, "loss": 0.8542, "step": 3307 }, { "epoch": 0.64, "grad_norm": 1.023527555016186, "learning_rate": 6.168848680906678e-06, "loss": 0.8489, "step": 3308 }, { "epoch": 0.64, "grad_norm": 1.068959449330093, "learning_rate": 6.163093988608127e-06, "loss": 0.8623, "step": 3309 }, { "epoch": 0.64, "grad_norm": 0.9508925190845705, "learning_rate": 6.157340785928595e-06, "loss": 0.8835, "step": 3310 }, { "epoch": 0.64, "grad_norm": 1.3058520594017382, "learning_rate": 6.151589075101681e-06, "loss": 0.843, "step": 3311 }, { "epoch": 0.64, "grad_norm": 1.012067383086828, "learning_rate": 6.145838858360391e-06, "loss": 0.8879, "step": 3312 }, { "epoch": 0.64, "grad_norm": 0.8872446812979483, "learning_rate": 6.140090137937158e-06, "loss": 0.6237, "step": 3313 }, { "epoch": 0.64, "grad_norm": 0.963940666778785, "learning_rate": 6.134342916063838e-06, "loss": 0.8718, "step": 3314 }, { "epoch": 0.64, "grad_norm": 0.9625175822952285, "learning_rate": 6.128597194971691e-06, "loss": 0.8328, "step": 3315 }, { "epoch": 0.64, "grad_norm": 0.9489445542958358, "learning_rate": 6.122852976891413e-06, "loss": 0.8989, "step": 3316 }, { "epoch": 0.64, "grad_norm": 1.0602713420392071, "learning_rate": 6.117110264053101e-06, "loss": 0.8396, "step": 3317 }, { "epoch": 0.64, "grad_norm": 1.026368311764349, "learning_rate": 6.111369058686276e-06, "loss": 0.8237, "step": 3318 }, { "epoch": 0.64, "grad_norm": 1.0002916707446916, "learning_rate": 6.105629363019875e-06, "loss": 0.8577, "step": 3319 }, { "epoch": 0.64, "grad_norm": 1.1447785845854548, "learning_rate": 6.099891179282242e-06, "loss": 0.8787, "step": 3320 }, { "epoch": 0.64, "grad_norm": 1.0050650047760947, "learning_rate": 6.094154509701133e-06, "loss": 0.8164, "step": 3321 }, { "epoch": 0.64, "grad_norm": 1.0308149271856555, "learning_rate": 6.088419356503732e-06, "loss": 0.8757, "step": 3322 }, { "epoch": 0.64, "grad_norm": 0.9496946954293759, "learning_rate": 6.082685721916612e-06, "loss": 0.5895, "step": 3323 }, { "epoch": 0.64, "grad_norm": 1.0462775767587649, "learning_rate": 6.076953608165772e-06, "loss": 0.8545, "step": 3324 }, { "epoch": 0.64, "grad_norm": 1.1119365832414965, "learning_rate": 6.07122301747662e-06, "loss": 0.8652, "step": 3325 }, { "epoch": 0.64, "grad_norm": 0.8148796927853778, "learning_rate": 6.065493952073961e-06, "loss": 0.5963, "step": 3326 }, { "epoch": 0.64, "grad_norm": 1.0424647136855623, "learning_rate": 6.0597664141820176e-06, "loss": 0.8613, "step": 3327 }, { "epoch": 0.64, "grad_norm": 1.0307799886117093, "learning_rate": 6.054040406024422e-06, "loss": 0.8721, "step": 3328 }, { "epoch": 0.64, "grad_norm": 1.0004590550571335, "learning_rate": 6.0483159298242e-06, "loss": 0.9014, "step": 3329 }, { "epoch": 0.64, "grad_norm": 1.0011185743031714, "learning_rate": 6.042592987803796e-06, "loss": 0.8818, "step": 3330 }, { "epoch": 0.64, "grad_norm": 0.7874676771717364, "learning_rate": 6.036871582185054e-06, "loss": 0.5764, "step": 3331 }, { "epoch": 0.64, "grad_norm": 0.9467378067547564, "learning_rate": 6.031151715189217e-06, "loss": 0.8191, "step": 3332 }, { "epoch": 0.64, "grad_norm": 0.9760085089025715, "learning_rate": 6.025433389036935e-06, "loss": 0.8687, "step": 3333 }, { "epoch": 0.64, "grad_norm": 1.1087685080661307, "learning_rate": 6.019716605948261e-06, "loss": 0.9143, "step": 3334 }, { "epoch": 0.64, "grad_norm": 1.107924956596511, "learning_rate": 6.014001368142643e-06, "loss": 0.8159, "step": 3335 }, { "epoch": 0.64, "grad_norm": 0.9077055906508501, "learning_rate": 6.008287677838937e-06, "loss": 0.8022, "step": 3336 }, { "epoch": 0.64, "grad_norm": 0.9621072059692857, "learning_rate": 6.002575537255395e-06, "loss": 0.8538, "step": 3337 }, { "epoch": 0.64, "grad_norm": 1.0938335850827774, "learning_rate": 5.996864948609662e-06, "loss": 0.8538, "step": 3338 }, { "epoch": 0.64, "grad_norm": 1.0951697203770672, "learning_rate": 5.9911559141187924e-06, "loss": 0.7893, "step": 3339 }, { "epoch": 0.64, "grad_norm": 1.026785965171259, "learning_rate": 5.9854484359992235e-06, "loss": 0.8911, "step": 3340 }, { "epoch": 0.64, "grad_norm": 0.8277133728921076, "learning_rate": 5.979742516466793e-06, "loss": 0.6631, "step": 3341 }, { "epoch": 0.64, "grad_norm": 0.9897129419558794, "learning_rate": 5.974038157736746e-06, "loss": 0.7894, "step": 3342 }, { "epoch": 0.64, "grad_norm": 1.1078311367444573, "learning_rate": 5.968335362023697e-06, "loss": 0.8887, "step": 3343 }, { "epoch": 0.64, "grad_norm": 0.9206423456472912, "learning_rate": 5.962634131541676e-06, "loss": 0.8887, "step": 3344 }, { "epoch": 0.64, "grad_norm": 0.9487829252771163, "learning_rate": 5.956934468504101e-06, "loss": 0.8149, "step": 3345 }, { "epoch": 0.64, "grad_norm": 1.1108833346394393, "learning_rate": 5.951236375123768e-06, "loss": 0.8125, "step": 3346 }, { "epoch": 0.64, "grad_norm": 1.0294077445259628, "learning_rate": 5.945539853612876e-06, "loss": 0.9209, "step": 3347 }, { "epoch": 0.64, "grad_norm": 1.0922515586440187, "learning_rate": 5.939844906183016e-06, "loss": 0.7993, "step": 3348 }, { "epoch": 0.64, "grad_norm": 1.0473271530429251, "learning_rate": 5.934151535045156e-06, "loss": 0.8711, "step": 3349 }, { "epoch": 0.64, "grad_norm": 1.0515942402076706, "learning_rate": 5.92845974240966e-06, "loss": 0.8157, "step": 3350 }, { "epoch": 0.64, "grad_norm": 1.0731419706544034, "learning_rate": 5.922769530486283e-06, "loss": 0.9072, "step": 3351 }, { "epoch": 0.64, "grad_norm": 0.9952714311968855, "learning_rate": 5.917080901484156e-06, "loss": 0.8499, "step": 3352 }, { "epoch": 0.65, "grad_norm": 1.0001788230911868, "learning_rate": 5.9113938576118e-06, "loss": 0.874, "step": 3353 }, { "epoch": 0.65, "grad_norm": 1.0141438442474027, "learning_rate": 5.905708401077128e-06, "loss": 0.8601, "step": 3354 }, { "epoch": 0.65, "grad_norm": 1.0219555833778355, "learning_rate": 5.900024534087421e-06, "loss": 0.8857, "step": 3355 }, { "epoch": 0.65, "grad_norm": 1.0229217796469419, "learning_rate": 5.894342258849355e-06, "loss": 0.8281, "step": 3356 }, { "epoch": 0.65, "grad_norm": 1.0017428664349246, "learning_rate": 5.88866157756899e-06, "loss": 0.8088, "step": 3357 }, { "epoch": 0.65, "grad_norm": 0.8995714093995534, "learning_rate": 5.882982492451757e-06, "loss": 0.6123, "step": 3358 }, { "epoch": 0.65, "grad_norm": 1.1367618261365195, "learning_rate": 5.877305005702471e-06, "loss": 0.8569, "step": 3359 }, { "epoch": 0.65, "grad_norm": 1.109056840820296, "learning_rate": 5.871629119525335e-06, "loss": 0.8574, "step": 3360 }, { "epoch": 0.65, "grad_norm": 1.004080234217407, "learning_rate": 5.865954836123915e-06, "loss": 0.8518, "step": 3361 }, { "epoch": 0.65, "grad_norm": 1.0409973002685355, "learning_rate": 5.860282157701167e-06, "loss": 0.8567, "step": 3362 }, { "epoch": 0.65, "grad_norm": 1.015445698215473, "learning_rate": 5.854611086459423e-06, "loss": 0.8445, "step": 3363 }, { "epoch": 0.65, "grad_norm": 1.0097781332512226, "learning_rate": 5.8489416246003814e-06, "loss": 0.9312, "step": 3364 }, { "epoch": 0.65, "grad_norm": 0.7900748689763192, "learning_rate": 5.8432737743251315e-06, "loss": 0.5477, "step": 3365 }, { "epoch": 0.65, "grad_norm": 1.1117121000871797, "learning_rate": 5.8376075378341194e-06, "loss": 0.8184, "step": 3366 }, { "epoch": 0.65, "grad_norm": 0.8093273414557336, "learning_rate": 5.831942917327172e-06, "loss": 0.6174, "step": 3367 }, { "epoch": 0.65, "grad_norm": 1.0063806223710123, "learning_rate": 5.826279915003503e-06, "loss": 0.9485, "step": 3368 }, { "epoch": 0.65, "grad_norm": 0.9127640228114087, "learning_rate": 5.8206185330616725e-06, "loss": 0.8179, "step": 3369 }, { "epoch": 0.65, "grad_norm": 0.9704861773873628, "learning_rate": 5.814958773699625e-06, "loss": 0.8669, "step": 3370 }, { "epoch": 0.65, "grad_norm": 1.0959997340895349, "learning_rate": 5.809300639114683e-06, "loss": 0.8701, "step": 3371 }, { "epoch": 0.65, "grad_norm": 1.0981109903640247, "learning_rate": 5.803644131503516e-06, "loss": 0.8999, "step": 3372 }, { "epoch": 0.65, "grad_norm": 0.9742666035442098, "learning_rate": 5.797989253062186e-06, "loss": 0.8259, "step": 3373 }, { "epoch": 0.65, "grad_norm": 1.0779885530944038, "learning_rate": 5.792336005986105e-06, "loss": 0.8896, "step": 3374 }, { "epoch": 0.65, "grad_norm": 1.048660153208226, "learning_rate": 5.786684392470064e-06, "loss": 0.9092, "step": 3375 }, { "epoch": 0.65, "grad_norm": 2.216515139603283, "learning_rate": 5.781034414708208e-06, "loss": 0.9053, "step": 3376 }, { "epoch": 0.65, "grad_norm": 1.0993581625914068, "learning_rate": 5.775386074894058e-06, "loss": 0.873, "step": 3377 }, { "epoch": 0.65, "grad_norm": 1.0974069266361317, "learning_rate": 5.769739375220489e-06, "loss": 0.9231, "step": 3378 }, { "epoch": 0.65, "grad_norm": 1.0704484832743468, "learning_rate": 5.7640943178797445e-06, "loss": 0.8851, "step": 3379 }, { "epoch": 0.65, "grad_norm": 1.0078178729516603, "learning_rate": 5.7584509050634395e-06, "loss": 0.8657, "step": 3380 }, { "epoch": 0.65, "grad_norm": 1.072310795032353, "learning_rate": 5.752809138962525e-06, "loss": 0.8562, "step": 3381 }, { "epoch": 0.65, "grad_norm": 0.9645252841206937, "learning_rate": 5.747169021767342e-06, "loss": 0.8633, "step": 3382 }, { "epoch": 0.65, "grad_norm": 0.8637040004487874, "learning_rate": 5.7415305556675805e-06, "loss": 0.5895, "step": 3383 }, { "epoch": 0.65, "grad_norm": 0.8932280120503866, "learning_rate": 5.73589374285227e-06, "loss": 0.8401, "step": 3384 }, { "epoch": 0.65, "grad_norm": 1.0429358760692709, "learning_rate": 5.730258585509832e-06, "loss": 0.8884, "step": 3385 }, { "epoch": 0.65, "grad_norm": 1.0849372418465908, "learning_rate": 5.724625085828022e-06, "loss": 0.8918, "step": 3386 }, { "epoch": 0.65, "grad_norm": 1.1635089864786707, "learning_rate": 5.718993245993958e-06, "loss": 0.8606, "step": 3387 }, { "epoch": 0.65, "grad_norm": 1.1387436111731717, "learning_rate": 5.713363068194115e-06, "loss": 0.8638, "step": 3388 }, { "epoch": 0.65, "grad_norm": 0.9554351710187855, "learning_rate": 5.7077345546143235e-06, "loss": 0.8342, "step": 3389 }, { "epoch": 0.65, "grad_norm": 0.9151493159265578, "learning_rate": 5.702107707439766e-06, "loss": 0.6215, "step": 3390 }, { "epoch": 0.65, "grad_norm": 0.9800580041088757, "learning_rate": 5.6964825288549745e-06, "loss": 0.7992, "step": 3391 }, { "epoch": 0.65, "grad_norm": 1.0334464604198654, "learning_rate": 5.690859021043842e-06, "loss": 0.8113, "step": 3392 }, { "epoch": 0.65, "grad_norm": 1.0140731422478644, "learning_rate": 5.685237186189601e-06, "loss": 0.8511, "step": 3393 }, { "epoch": 0.65, "grad_norm": 0.9716921956488878, "learning_rate": 5.679617026474853e-06, "loss": 0.6385, "step": 3394 }, { "epoch": 0.65, "grad_norm": 1.1658958824053798, "learning_rate": 5.673998544081527e-06, "loss": 0.9175, "step": 3395 }, { "epoch": 0.65, "grad_norm": 0.9858341975000809, "learning_rate": 5.6683817411909114e-06, "loss": 0.8477, "step": 3396 }, { "epoch": 0.65, "grad_norm": 1.0463186332893684, "learning_rate": 5.662766619983653e-06, "loss": 0.8975, "step": 3397 }, { "epoch": 0.65, "grad_norm": 1.053963306046729, "learning_rate": 5.65715318263972e-06, "loss": 0.8386, "step": 3398 }, { "epoch": 0.65, "grad_norm": 0.9868010305502599, "learning_rate": 5.651541431338454e-06, "loss": 0.8479, "step": 3399 }, { "epoch": 0.65, "grad_norm": 1.2389767683574897, "learning_rate": 5.645931368258527e-06, "loss": 0.9329, "step": 3400 }, { "epoch": 0.65, "grad_norm": 1.1310278267981857, "learning_rate": 5.640322995577958e-06, "loss": 0.8623, "step": 3401 }, { "epoch": 0.65, "grad_norm": 0.8216309091131919, "learning_rate": 5.634716315474109e-06, "loss": 0.5947, "step": 3402 }, { "epoch": 0.65, "grad_norm": 1.0678021279406014, "learning_rate": 5.629111330123689e-06, "loss": 0.8594, "step": 3403 }, { "epoch": 0.65, "grad_norm": 1.2091941449298165, "learning_rate": 5.623508041702743e-06, "loss": 0.8765, "step": 3404 }, { "epoch": 0.66, "grad_norm": 1.0491521728103654, "learning_rate": 5.617906452386659e-06, "loss": 0.9116, "step": 3405 }, { "epoch": 0.66, "grad_norm": 0.8995522507864403, "learning_rate": 5.612306564350179e-06, "loss": 0.5543, "step": 3406 }, { "epoch": 0.66, "grad_norm": 1.0428526658381223, "learning_rate": 5.6067083797673535e-06, "loss": 0.8486, "step": 3407 }, { "epoch": 0.66, "grad_norm": 1.2881768380186698, "learning_rate": 5.601111900811607e-06, "loss": 0.8645, "step": 3408 }, { "epoch": 0.66, "grad_norm": 0.9503509702976211, "learning_rate": 5.595517129655681e-06, "loss": 0.8328, "step": 3409 }, { "epoch": 0.66, "grad_norm": 0.7800179147859998, "learning_rate": 5.589924068471648e-06, "loss": 0.5745, "step": 3410 }, { "epoch": 0.66, "grad_norm": 0.9456265521188433, "learning_rate": 5.58433271943094e-06, "loss": 0.8574, "step": 3411 }, { "epoch": 0.66, "grad_norm": 0.9710695681520732, "learning_rate": 5.578743084704306e-06, "loss": 0.8521, "step": 3412 }, { "epoch": 0.66, "grad_norm": 0.8865430560434148, "learning_rate": 5.573155166461833e-06, "loss": 0.8276, "step": 3413 }, { "epoch": 0.66, "grad_norm": 0.751116158020413, "learning_rate": 5.567568966872947e-06, "loss": 0.6219, "step": 3414 }, { "epoch": 0.66, "grad_norm": 1.053345621329447, "learning_rate": 5.5619844881064e-06, "loss": 0.8716, "step": 3415 }, { "epoch": 0.66, "grad_norm": 1.0353218543317413, "learning_rate": 5.556401732330281e-06, "loss": 0.8713, "step": 3416 }, { "epoch": 0.66, "grad_norm": 1.0527286978357988, "learning_rate": 5.550820701712007e-06, "loss": 0.9023, "step": 3417 }, { "epoch": 0.66, "grad_norm": 1.0241580944264954, "learning_rate": 5.545241398418326e-06, "loss": 0.8564, "step": 3418 }, { "epoch": 0.66, "grad_norm": 1.158980581647324, "learning_rate": 5.539663824615312e-06, "loss": 0.8484, "step": 3419 }, { "epoch": 0.66, "grad_norm": 0.8027599970471249, "learning_rate": 5.534087982468384e-06, "loss": 0.6001, "step": 3420 }, { "epoch": 0.66, "grad_norm": 0.8863311785230915, "learning_rate": 5.5285138741422615e-06, "loss": 0.8107, "step": 3421 }, { "epoch": 0.66, "grad_norm": 1.1229900465975164, "learning_rate": 5.522941501801008e-06, "loss": 0.8279, "step": 3422 }, { "epoch": 0.66, "grad_norm": 1.08040973783348, "learning_rate": 5.517370867608021e-06, "loss": 0.8369, "step": 3423 }, { "epoch": 0.66, "grad_norm": 1.0962351242302462, "learning_rate": 5.511801973725997e-06, "loss": 0.8672, "step": 3424 }, { "epoch": 0.66, "grad_norm": 1.0134436652747059, "learning_rate": 5.506234822316983e-06, "loss": 0.8264, "step": 3425 }, { "epoch": 0.66, "grad_norm": 0.9289950110315288, "learning_rate": 5.500669415542336e-06, "loss": 0.5913, "step": 3426 }, { "epoch": 0.66, "grad_norm": 0.856896142331398, "learning_rate": 5.495105755562738e-06, "loss": 0.625, "step": 3427 }, { "epoch": 0.66, "grad_norm": 0.9302815897778804, "learning_rate": 5.4895438445381945e-06, "loss": 0.653, "step": 3428 }, { "epoch": 0.66, "grad_norm": 0.9989152564955178, "learning_rate": 5.48398368462803e-06, "loss": 0.8177, "step": 3429 }, { "epoch": 0.66, "grad_norm": 0.8631300124866033, "learning_rate": 5.4784252779908905e-06, "loss": 0.7944, "step": 3430 }, { "epoch": 0.66, "grad_norm": 1.0425043791233284, "learning_rate": 5.4728686267847354e-06, "loss": 0.865, "step": 3431 }, { "epoch": 0.66, "grad_norm": 1.1585071021686235, "learning_rate": 5.467313733166863e-06, "loss": 0.8792, "step": 3432 }, { "epoch": 0.66, "grad_norm": 1.019341434241738, "learning_rate": 5.461760599293855e-06, "loss": 0.8093, "step": 3433 }, { "epoch": 0.66, "grad_norm": 1.0047594508854607, "learning_rate": 5.456209227321643e-06, "loss": 0.9004, "step": 3434 }, { "epoch": 0.66, "grad_norm": 1.0292126887618456, "learning_rate": 5.450659619405458e-06, "loss": 0.8599, "step": 3435 }, { "epoch": 0.66, "grad_norm": 0.9689940291347233, "learning_rate": 5.445111777699842e-06, "loss": 0.8914, "step": 3436 }, { "epoch": 0.66, "grad_norm": 1.087088533195534, "learning_rate": 5.439565704358667e-06, "loss": 0.9177, "step": 3437 }, { "epoch": 0.66, "grad_norm": 0.7527286244691395, "learning_rate": 5.434021401535105e-06, "loss": 0.578, "step": 3438 }, { "epoch": 0.66, "grad_norm": 1.0196533326430188, "learning_rate": 5.428478871381646e-06, "loss": 0.8376, "step": 3439 }, { "epoch": 0.66, "grad_norm": 1.1471610403789374, "learning_rate": 5.422938116050092e-06, "loss": 0.8594, "step": 3440 }, { "epoch": 0.66, "grad_norm": 1.0979512327797163, "learning_rate": 5.417399137691552e-06, "loss": 0.8524, "step": 3441 }, { "epoch": 0.66, "grad_norm": 1.1119055270402283, "learning_rate": 5.411861938456453e-06, "loss": 0.885, "step": 3442 }, { "epoch": 0.66, "grad_norm": 1.1382902920582447, "learning_rate": 5.406326520494522e-06, "loss": 0.823, "step": 3443 }, { "epoch": 0.66, "grad_norm": 1.0218323882659381, "learning_rate": 5.400792885954802e-06, "loss": 0.8855, "step": 3444 }, { "epoch": 0.66, "grad_norm": 1.0241118728364083, "learning_rate": 5.395261036985635e-06, "loss": 0.8486, "step": 3445 }, { "epoch": 0.66, "grad_norm": 1.0637131671669218, "learning_rate": 5.389730975734686e-06, "loss": 0.8623, "step": 3446 }, { "epoch": 0.66, "grad_norm": 1.1946141286659597, "learning_rate": 5.384202704348902e-06, "loss": 0.8699, "step": 3447 }, { "epoch": 0.66, "grad_norm": 1.017597788622571, "learning_rate": 5.378676224974557e-06, "loss": 0.8269, "step": 3448 }, { "epoch": 0.66, "grad_norm": 0.9853469735814695, "learning_rate": 5.373151539757224e-06, "loss": 0.7976, "step": 3449 }, { "epoch": 0.66, "grad_norm": 0.9255516790190637, "learning_rate": 5.367628650841761e-06, "loss": 0.8833, "step": 3450 }, { "epoch": 0.66, "grad_norm": 0.9598481951515855, "learning_rate": 5.362107560372358e-06, "loss": 0.8408, "step": 3451 }, { "epoch": 0.66, "grad_norm": 1.0665150578588833, "learning_rate": 5.356588270492487e-06, "loss": 0.8394, "step": 3452 }, { "epoch": 0.66, "grad_norm": 0.9598427568318288, "learning_rate": 5.351070783344926e-06, "loss": 0.8787, "step": 3453 }, { "epoch": 0.66, "grad_norm": 1.0326186834255586, "learning_rate": 5.3455551010717545e-06, "loss": 0.8762, "step": 3454 }, { "epoch": 0.66, "grad_norm": 1.0771503357684649, "learning_rate": 5.34004122581435e-06, "loss": 0.8499, "step": 3455 }, { "epoch": 0.66, "grad_norm": 0.9861551313666287, "learning_rate": 5.334529159713389e-06, "loss": 0.8247, "step": 3456 }, { "epoch": 0.67, "grad_norm": 0.9332736219126803, "learning_rate": 5.329018904908841e-06, "loss": 0.8779, "step": 3457 }, { "epoch": 0.67, "grad_norm": 0.8149145983611653, "learning_rate": 5.323510463539989e-06, "loss": 0.6407, "step": 3458 }, { "epoch": 0.67, "grad_norm": 0.7556029238645562, "learning_rate": 5.318003837745382e-06, "loss": 0.5723, "step": 3459 }, { "epoch": 0.67, "grad_norm": 1.1297789056472987, "learning_rate": 5.3124990296628974e-06, "loss": 0.8833, "step": 3460 }, { "epoch": 0.67, "grad_norm": 1.0684431781320507, "learning_rate": 5.306996041429688e-06, "loss": 0.8987, "step": 3461 }, { "epoch": 0.67, "grad_norm": 1.2017207735893938, "learning_rate": 5.301494875182192e-06, "loss": 0.8413, "step": 3462 }, { "epoch": 0.67, "grad_norm": 0.8866634117936575, "learning_rate": 5.295995533056162e-06, "loss": 0.8054, "step": 3463 }, { "epoch": 0.67, "grad_norm": 1.2239872975718418, "learning_rate": 5.290498017186631e-06, "loss": 0.8909, "step": 3464 }, { "epoch": 0.67, "grad_norm": 0.9292266354798357, "learning_rate": 5.2850023297079235e-06, "loss": 0.8203, "step": 3465 }, { "epoch": 0.67, "grad_norm": 1.2177963480289407, "learning_rate": 5.279508472753654e-06, "loss": 0.8984, "step": 3466 }, { "epoch": 0.67, "grad_norm": 0.9313780168449836, "learning_rate": 5.274016448456725e-06, "loss": 0.8545, "step": 3467 }, { "epoch": 0.67, "grad_norm": 1.072087789946604, "learning_rate": 5.2685262589493314e-06, "loss": 0.8799, "step": 3468 }, { "epoch": 0.67, "grad_norm": 1.101802151182915, "learning_rate": 5.263037906362953e-06, "loss": 0.8889, "step": 3469 }, { "epoch": 0.67, "grad_norm": 1.050551273991586, "learning_rate": 5.257551392828359e-06, "loss": 0.8049, "step": 3470 }, { "epoch": 0.67, "grad_norm": 1.042314830838504, "learning_rate": 5.252066720475597e-06, "loss": 0.8896, "step": 3471 }, { "epoch": 0.67, "grad_norm": 1.0881113632284063, "learning_rate": 5.246583891434018e-06, "loss": 0.8774, "step": 3472 }, { "epoch": 0.67, "grad_norm": 1.029895970725115, "learning_rate": 5.241102907832232e-06, "loss": 0.8271, "step": 3473 }, { "epoch": 0.67, "grad_norm": 0.9519543386349086, "learning_rate": 5.235623771798151e-06, "loss": 0.8618, "step": 3474 }, { "epoch": 0.67, "grad_norm": 1.0499534415047689, "learning_rate": 5.23014648545897e-06, "loss": 0.8276, "step": 3475 }, { "epoch": 0.67, "grad_norm": 1.0267157423283473, "learning_rate": 5.224671050941146e-06, "loss": 0.8479, "step": 3476 }, { "epoch": 0.67, "grad_norm": 0.969800706763158, "learning_rate": 5.2191974703704425e-06, "loss": 0.6372, "step": 3477 }, { "epoch": 0.67, "grad_norm": 0.9758232387029132, "learning_rate": 5.213725745871889e-06, "loss": 0.8911, "step": 3478 }, { "epoch": 0.67, "grad_norm": 1.0156658246931856, "learning_rate": 5.208255879569799e-06, "loss": 0.8928, "step": 3479 }, { "epoch": 0.67, "grad_norm": 1.1303921289731886, "learning_rate": 5.20278787358776e-06, "loss": 0.8582, "step": 3480 }, { "epoch": 0.67, "grad_norm": 0.9688832771524976, "learning_rate": 5.197321730048641e-06, "loss": 0.8704, "step": 3481 }, { "epoch": 0.67, "grad_norm": 0.9789462298481842, "learning_rate": 5.1918574510745865e-06, "loss": 0.8445, "step": 3482 }, { "epoch": 0.67, "grad_norm": 1.0777011799340626, "learning_rate": 5.186395038787017e-06, "loss": 0.8398, "step": 3483 }, { "epoch": 0.67, "grad_norm": 1.0939033962719815, "learning_rate": 5.180934495306638e-06, "loss": 0.8677, "step": 3484 }, { "epoch": 0.67, "grad_norm": 0.8537269511801305, "learning_rate": 5.175475822753404e-06, "loss": 0.5947, "step": 3485 }, { "epoch": 0.67, "grad_norm": 1.1279532221613615, "learning_rate": 5.170019023246574e-06, "loss": 0.8872, "step": 3486 }, { "epoch": 0.67, "grad_norm": 1.0612045388561189, "learning_rate": 5.16456409890466e-06, "loss": 0.8865, "step": 3487 }, { "epoch": 0.67, "grad_norm": 0.9573682103035117, "learning_rate": 5.159111051845451e-06, "loss": 0.8187, "step": 3488 }, { "epoch": 0.67, "grad_norm": 1.0077179973720045, "learning_rate": 5.153659884186013e-06, "loss": 0.8447, "step": 3489 }, { "epoch": 0.67, "grad_norm": 1.0391709611239737, "learning_rate": 5.148210598042665e-06, "loss": 0.8735, "step": 3490 }, { "epoch": 0.67, "grad_norm": 0.8205565294670295, "learning_rate": 5.142763195531017e-06, "loss": 0.5797, "step": 3491 }, { "epoch": 0.67, "grad_norm": 1.1392185443118816, "learning_rate": 5.137317678765939e-06, "loss": 0.7886, "step": 3492 }, { "epoch": 0.67, "grad_norm": 0.931698464701446, "learning_rate": 5.131874049861563e-06, "loss": 0.8586, "step": 3493 }, { "epoch": 0.67, "grad_norm": 1.0047014907441951, "learning_rate": 5.126432310931295e-06, "loss": 0.8708, "step": 3494 }, { "epoch": 0.67, "grad_norm": 0.8301233974901426, "learning_rate": 5.120992464087807e-06, "loss": 0.5716, "step": 3495 }, { "epoch": 0.67, "grad_norm": 1.0486080837477982, "learning_rate": 5.115554511443033e-06, "loss": 0.8582, "step": 3496 }, { "epoch": 0.67, "grad_norm": 1.2172041226042838, "learning_rate": 5.1101184551081705e-06, "loss": 0.9172, "step": 3497 }, { "epoch": 0.67, "grad_norm": 1.0509687277731012, "learning_rate": 5.104684297193694e-06, "loss": 0.8721, "step": 3498 }, { "epoch": 0.67, "grad_norm": 1.0078400584544909, "learning_rate": 5.099252039809317e-06, "loss": 0.8599, "step": 3499 }, { "epoch": 0.67, "grad_norm": 1.1317032628472419, "learning_rate": 5.09382168506404e-06, "loss": 0.8652, "step": 3500 }, { "epoch": 0.67, "grad_norm": 0.9638050406189105, "learning_rate": 5.088393235066114e-06, "loss": 0.8967, "step": 3501 }, { "epoch": 0.67, "grad_norm": 0.9222060972556375, "learning_rate": 5.082966691923037e-06, "loss": 0.6045, "step": 3502 }, { "epoch": 0.67, "grad_norm": 1.214539466787419, "learning_rate": 5.077542057741592e-06, "loss": 0.8589, "step": 3503 }, { "epoch": 0.67, "grad_norm": 1.108024011820825, "learning_rate": 5.0721193346278066e-06, "loss": 0.895, "step": 3504 }, { "epoch": 0.67, "grad_norm": 0.8673306849820176, "learning_rate": 5.066698524686966e-06, "loss": 0.6091, "step": 3505 }, { "epoch": 0.67, "grad_norm": 1.0404271491961257, "learning_rate": 5.061279630023618e-06, "loss": 0.8799, "step": 3506 }, { "epoch": 0.67, "grad_norm": 1.0666783851500055, "learning_rate": 5.055862652741562e-06, "loss": 0.8586, "step": 3507 }, { "epoch": 0.67, "grad_norm": 1.0713946830266428, "learning_rate": 5.050447594943856e-06, "loss": 0.8862, "step": 3508 }, { "epoch": 0.68, "grad_norm": 1.0626342948021983, "learning_rate": 5.045034458732808e-06, "loss": 0.8379, "step": 3509 }, { "epoch": 0.68, "grad_norm": 1.0214747782652107, "learning_rate": 5.0396232462099945e-06, "loss": 0.8423, "step": 3510 }, { "epoch": 0.68, "grad_norm": 0.9530766708890229, "learning_rate": 5.034213959476222e-06, "loss": 0.8076, "step": 3511 }, { "epoch": 0.68, "grad_norm": 1.1470293223486052, "learning_rate": 5.028806600631569e-06, "loss": 0.8958, "step": 3512 }, { "epoch": 0.68, "grad_norm": 1.1349524078145448, "learning_rate": 5.023401171775357e-06, "loss": 0.9153, "step": 3513 }, { "epoch": 0.68, "grad_norm": 1.0561272037933678, "learning_rate": 5.017997675006161e-06, "loss": 0.8657, "step": 3514 }, { "epoch": 0.68, "grad_norm": 0.9695761841079459, "learning_rate": 5.012596112421806e-06, "loss": 0.8203, "step": 3515 }, { "epoch": 0.68, "grad_norm": 1.109676908913429, "learning_rate": 5.007196486119355e-06, "loss": 0.8528, "step": 3516 }, { "epoch": 0.68, "grad_norm": 0.9767107657891312, "learning_rate": 5.001798798195136e-06, "loss": 0.8188, "step": 3517 }, { "epoch": 0.68, "grad_norm": 0.8588767888773031, "learning_rate": 4.996403050744719e-06, "loss": 0.5861, "step": 3518 }, { "epoch": 0.68, "grad_norm": 1.1840937729872734, "learning_rate": 4.991009245862917e-06, "loss": 0.9048, "step": 3519 }, { "epoch": 0.68, "grad_norm": 0.9847790048916711, "learning_rate": 4.985617385643789e-06, "loss": 0.9114, "step": 3520 }, { "epoch": 0.68, "grad_norm": 0.9955922084260173, "learning_rate": 4.980227472180643e-06, "loss": 0.8894, "step": 3521 }, { "epoch": 0.68, "grad_norm": 0.9335712512200234, "learning_rate": 4.974839507566027e-06, "loss": 0.8499, "step": 3522 }, { "epoch": 0.68, "grad_norm": 1.0744039340140792, "learning_rate": 4.969453493891733e-06, "loss": 0.8672, "step": 3523 }, { "epoch": 0.68, "grad_norm": 0.998066179602977, "learning_rate": 4.9640694332488075e-06, "loss": 0.9087, "step": 3524 }, { "epoch": 0.68, "grad_norm": 1.084365436873537, "learning_rate": 4.958687327727511e-06, "loss": 0.8745, "step": 3525 }, { "epoch": 0.68, "grad_norm": 1.1393416757174597, "learning_rate": 4.953307179417376e-06, "loss": 0.886, "step": 3526 }, { "epoch": 0.68, "grad_norm": 0.7926640597575696, "learning_rate": 4.947928990407156e-06, "loss": 0.6034, "step": 3527 }, { "epoch": 0.68, "grad_norm": 1.1553363446354454, "learning_rate": 4.94255276278485e-06, "loss": 0.8767, "step": 3528 }, { "epoch": 0.68, "grad_norm": 1.1048271748825265, "learning_rate": 4.937178498637696e-06, "loss": 0.9526, "step": 3529 }, { "epoch": 0.68, "grad_norm": 0.9956516613658098, "learning_rate": 4.931806200052165e-06, "loss": 0.8608, "step": 3530 }, { "epoch": 0.68, "grad_norm": 1.0269512827001699, "learning_rate": 4.926435869113971e-06, "loss": 0.8303, "step": 3531 }, { "epoch": 0.68, "grad_norm": 1.1133019462134046, "learning_rate": 4.92106750790806e-06, "loss": 0.8577, "step": 3532 }, { "epoch": 0.68, "grad_norm": 1.281045523397124, "learning_rate": 4.915701118518616e-06, "loss": 0.9441, "step": 3533 }, { "epoch": 0.68, "grad_norm": 1.0812700347012398, "learning_rate": 4.910336703029055e-06, "loss": 0.8293, "step": 3534 }, { "epoch": 0.68, "grad_norm": 1.0572593020481431, "learning_rate": 4.904974263522025e-06, "loss": 0.8391, "step": 3535 }, { "epoch": 0.68, "grad_norm": 1.1518084143309164, "learning_rate": 4.899613802079419e-06, "loss": 0.8853, "step": 3536 }, { "epoch": 0.68, "grad_norm": 1.0217318026627658, "learning_rate": 4.8942553207823395e-06, "loss": 0.8813, "step": 3537 }, { "epoch": 0.68, "grad_norm": 1.0716720552148347, "learning_rate": 4.888898821711144e-06, "loss": 0.8645, "step": 3538 }, { "epoch": 0.68, "grad_norm": 1.1018633118924817, "learning_rate": 4.883544306945407e-06, "loss": 0.8523, "step": 3539 }, { "epoch": 0.68, "grad_norm": 0.8485065670566522, "learning_rate": 4.878191778563934e-06, "loss": 0.5724, "step": 3540 }, { "epoch": 0.68, "grad_norm": 0.7553231711742554, "learning_rate": 4.872841238644766e-06, "loss": 0.5831, "step": 3541 }, { "epoch": 0.68, "grad_norm": 1.0302759341123804, "learning_rate": 4.867492689265154e-06, "loss": 0.8696, "step": 3542 }, { "epoch": 0.68, "grad_norm": 0.9935722550773199, "learning_rate": 4.8621461325016015e-06, "loss": 0.9031, "step": 3543 }, { "epoch": 0.68, "grad_norm": 0.9417653771441218, "learning_rate": 4.856801570429822e-06, "loss": 0.8467, "step": 3544 }, { "epoch": 0.68, "grad_norm": 1.059677261127758, "learning_rate": 4.851459005124759e-06, "loss": 0.8239, "step": 3545 }, { "epoch": 0.68, "grad_norm": 0.9611660779488123, "learning_rate": 4.846118438660578e-06, "loss": 0.8352, "step": 3546 }, { "epoch": 0.68, "grad_norm": 1.009850297399323, "learning_rate": 4.840779873110675e-06, "loss": 0.9124, "step": 3547 }, { "epoch": 0.68, "grad_norm": 0.9976995740092814, "learning_rate": 4.83544331054766e-06, "loss": 0.828, "step": 3548 }, { "epoch": 0.68, "grad_norm": 1.0421017124010277, "learning_rate": 4.83010875304337e-06, "loss": 0.5567, "step": 3549 }, { "epoch": 0.68, "grad_norm": 0.7835308365011342, "learning_rate": 4.824776202668875e-06, "loss": 0.6064, "step": 3550 }, { "epoch": 0.68, "grad_norm": 1.1371787310527144, "learning_rate": 4.819445661494437e-06, "loss": 0.8899, "step": 3551 }, { "epoch": 0.68, "grad_norm": 1.0187753934745138, "learning_rate": 4.8141171315895694e-06, "loss": 0.9236, "step": 3552 }, { "epoch": 0.68, "grad_norm": 0.7975629292605322, "learning_rate": 4.808790615022987e-06, "loss": 0.6212, "step": 3553 }, { "epoch": 0.68, "grad_norm": 1.2607971662534805, "learning_rate": 4.803466113862626e-06, "loss": 0.9009, "step": 3554 }, { "epoch": 0.68, "grad_norm": 0.8243916291246325, "learning_rate": 4.798143630175642e-06, "loss": 0.5786, "step": 3555 }, { "epoch": 0.68, "grad_norm": 0.8424051332026254, "learning_rate": 4.792823166028405e-06, "loss": 0.5948, "step": 3556 }, { "epoch": 0.68, "grad_norm": 0.9583776089109607, "learning_rate": 4.787504723486505e-06, "loss": 0.8535, "step": 3557 }, { "epoch": 0.68, "grad_norm": 1.1720617811044751, "learning_rate": 4.7821883046147414e-06, "loss": 0.8787, "step": 3558 }, { "epoch": 0.68, "grad_norm": 1.0011677586152345, "learning_rate": 4.776873911477133e-06, "loss": 0.8513, "step": 3559 }, { "epoch": 0.68, "grad_norm": 0.9195644834503912, "learning_rate": 4.771561546136908e-06, "loss": 0.5535, "step": 3560 }, { "epoch": 0.69, "grad_norm": 1.0372667774630902, "learning_rate": 4.766251210656509e-06, "loss": 0.9277, "step": 3561 }, { "epoch": 0.69, "grad_norm": 0.941443294547161, "learning_rate": 4.760942907097601e-06, "loss": 0.8291, "step": 3562 }, { "epoch": 0.69, "grad_norm": 0.9541845202009315, "learning_rate": 4.755636637521035e-06, "loss": 0.761, "step": 3563 }, { "epoch": 0.69, "grad_norm": 0.974560762198286, "learning_rate": 4.750332403986902e-06, "loss": 0.8745, "step": 3564 }, { "epoch": 0.69, "grad_norm": 0.856649295537524, "learning_rate": 4.7450302085544735e-06, "loss": 0.5958, "step": 3565 }, { "epoch": 0.69, "grad_norm": 1.1006172792597406, "learning_rate": 4.739730053282255e-06, "loss": 0.8433, "step": 3566 }, { "epoch": 0.69, "grad_norm": 1.059672763151995, "learning_rate": 4.734431940227951e-06, "loss": 0.8962, "step": 3567 }, { "epoch": 0.69, "grad_norm": 1.094088896866179, "learning_rate": 4.7291358714484594e-06, "loss": 0.9087, "step": 3568 }, { "epoch": 0.69, "grad_norm": 1.0866280678149625, "learning_rate": 4.723841848999907e-06, "loss": 0.8679, "step": 3569 }, { "epoch": 0.69, "grad_norm": 1.0126662107606683, "learning_rate": 4.718549874937612e-06, "loss": 0.8569, "step": 3570 }, { "epoch": 0.69, "grad_norm": 0.8280195743215631, "learning_rate": 4.713259951316103e-06, "loss": 0.613, "step": 3571 }, { "epoch": 0.69, "grad_norm": 1.053677206586675, "learning_rate": 4.707972080189106e-06, "loss": 0.8708, "step": 3572 }, { "epoch": 0.69, "grad_norm": 0.9847481029747395, "learning_rate": 4.702686263609559e-06, "loss": 0.7993, "step": 3573 }, { "epoch": 0.69, "grad_norm": 1.083473397009056, "learning_rate": 4.697402503629596e-06, "loss": 0.8752, "step": 3574 }, { "epoch": 0.69, "grad_norm": 1.1204887719986039, "learning_rate": 4.69212080230055e-06, "loss": 0.8574, "step": 3575 }, { "epoch": 0.69, "grad_norm": 1.0013213122220102, "learning_rate": 4.686841161672974e-06, "loss": 0.8313, "step": 3576 }, { "epoch": 0.69, "grad_norm": 1.1065331055539351, "learning_rate": 4.681563583796587e-06, "loss": 0.8718, "step": 3577 }, { "epoch": 0.69, "grad_norm": 1.1304236955947569, "learning_rate": 4.67628807072034e-06, "loss": 0.865, "step": 3578 }, { "epoch": 0.69, "grad_norm": 0.9472005689048802, "learning_rate": 4.6710146244923645e-06, "loss": 0.8462, "step": 3579 }, { "epoch": 0.69, "grad_norm": 0.9695767154098347, "learning_rate": 4.665743247159995e-06, "loss": 0.7809, "step": 3580 }, { "epoch": 0.69, "grad_norm": 1.1058525335025478, "learning_rate": 4.660473940769761e-06, "loss": 0.8726, "step": 3581 }, { "epoch": 0.69, "grad_norm": 1.1369175833320067, "learning_rate": 4.655206707367388e-06, "loss": 0.8816, "step": 3582 }, { "epoch": 0.69, "grad_norm": 1.0412068678912858, "learning_rate": 4.649941548997797e-06, "loss": 0.8474, "step": 3583 }, { "epoch": 0.69, "grad_norm": 1.0491539383146222, "learning_rate": 4.644678467705101e-06, "loss": 0.854, "step": 3584 }, { "epoch": 0.69, "grad_norm": 0.9784443561884237, "learning_rate": 4.639417465532622e-06, "loss": 0.8894, "step": 3585 }, { "epoch": 0.69, "grad_norm": 1.1589168760436268, "learning_rate": 4.634158544522849e-06, "loss": 0.9021, "step": 3586 }, { "epoch": 0.69, "grad_norm": 0.973802340014463, "learning_rate": 4.628901706717476e-06, "loss": 0.833, "step": 3587 }, { "epoch": 0.69, "grad_norm": 0.9378800152188843, "learning_rate": 4.623646954157399e-06, "loss": 0.8962, "step": 3588 }, { "epoch": 0.69, "grad_norm": 1.1493736169224893, "learning_rate": 4.618394288882681e-06, "loss": 0.8608, "step": 3589 }, { "epoch": 0.69, "grad_norm": 0.9627710033795276, "learning_rate": 4.613143712932603e-06, "loss": 0.7981, "step": 3590 }, { "epoch": 0.69, "grad_norm": 1.1208381018674183, "learning_rate": 4.607895228345603e-06, "loss": 0.8198, "step": 3591 }, { "epoch": 0.69, "grad_norm": 0.9990345002472649, "learning_rate": 4.602648837159333e-06, "loss": 0.8235, "step": 3592 }, { "epoch": 0.69, "grad_norm": 0.9967754139941792, "learning_rate": 4.597404541410622e-06, "loss": 0.9529, "step": 3593 }, { "epoch": 0.69, "grad_norm": 1.0604961868988887, "learning_rate": 4.592162343135483e-06, "loss": 0.8247, "step": 3594 }, { "epoch": 0.69, "grad_norm": 0.994819508615639, "learning_rate": 4.586922244369122e-06, "loss": 0.8271, "step": 3595 }, { "epoch": 0.69, "grad_norm": 0.9522636865900393, "learning_rate": 4.5816842471459224e-06, "loss": 0.8364, "step": 3596 }, { "epoch": 0.69, "grad_norm": 0.7784526056195982, "learning_rate": 4.576448353499457e-06, "loss": 0.5714, "step": 3597 }, { "epoch": 0.69, "grad_norm": 1.0010720761017293, "learning_rate": 4.571214565462477e-06, "loss": 0.7981, "step": 3598 }, { "epoch": 0.69, "grad_norm": 0.9635588590971851, "learning_rate": 4.565982885066923e-06, "loss": 0.8196, "step": 3599 }, { "epoch": 0.69, "grad_norm": 0.8151352115101658, "learning_rate": 4.560753314343912e-06, "loss": 0.5445, "step": 3600 }, { "epoch": 0.69, "grad_norm": 1.0597613799631973, "learning_rate": 4.555525855323738e-06, "loss": 0.8442, "step": 3601 }, { "epoch": 0.69, "grad_norm": 1.0653970763218228, "learning_rate": 4.5503005100358945e-06, "loss": 0.8308, "step": 3602 }, { "epoch": 0.69, "grad_norm": 1.0357721279133978, "learning_rate": 4.545077280509022e-06, "loss": 0.8491, "step": 3603 }, { "epoch": 0.69, "grad_norm": 0.9925877191480735, "learning_rate": 4.539856168770974e-06, "loss": 0.813, "step": 3604 }, { "epoch": 0.69, "grad_norm": 1.0770696786738825, "learning_rate": 4.534637176848758e-06, "loss": 0.8254, "step": 3605 }, { "epoch": 0.69, "grad_norm": 0.9065956695333396, "learning_rate": 4.52942030676857e-06, "loss": 0.5809, "step": 3606 }, { "epoch": 0.69, "grad_norm": 1.0957495478538264, "learning_rate": 4.524205560555774e-06, "loss": 0.9124, "step": 3607 }, { "epoch": 0.69, "grad_norm": 1.0483062879356162, "learning_rate": 4.5189929402349175e-06, "loss": 0.871, "step": 3608 }, { "epoch": 0.69, "grad_norm": 1.0562464444623307, "learning_rate": 4.513782447829717e-06, "loss": 0.8083, "step": 3609 }, { "epoch": 0.69, "grad_norm": 1.0486641465743993, "learning_rate": 4.508574085363065e-06, "loss": 0.8674, "step": 3610 }, { "epoch": 0.69, "grad_norm": 1.0533064334498947, "learning_rate": 4.503367854857035e-06, "loss": 0.8501, "step": 3611 }, { "epoch": 0.69, "grad_norm": 0.9637483624529904, "learning_rate": 4.498163758332853e-06, "loss": 0.6418, "step": 3612 }, { "epoch": 0.7, "grad_norm": 1.1209791659487671, "learning_rate": 4.492961797810932e-06, "loss": 0.8101, "step": 3613 }, { "epoch": 0.7, "grad_norm": 1.1914785033931397, "learning_rate": 4.4877619753108605e-06, "loss": 0.8872, "step": 3614 }, { "epoch": 0.7, "grad_norm": 1.0189131744117594, "learning_rate": 4.4825642928513746e-06, "loss": 0.8596, "step": 3615 }, { "epoch": 0.7, "grad_norm": 0.8767085903302813, "learning_rate": 4.477368752450409e-06, "loss": 0.6094, "step": 3616 }, { "epoch": 0.7, "grad_norm": 1.0063168377763763, "learning_rate": 4.472175356125036e-06, "loss": 0.8674, "step": 3617 }, { "epoch": 0.7, "grad_norm": 1.0517287429628255, "learning_rate": 4.466984105891521e-06, "loss": 0.853, "step": 3618 }, { "epoch": 0.7, "grad_norm": 1.0504381109670715, "learning_rate": 4.461795003765285e-06, "loss": 0.8635, "step": 3619 }, { "epoch": 0.7, "grad_norm": 1.035778525176509, "learning_rate": 4.456608051760914e-06, "loss": 0.885, "step": 3620 }, { "epoch": 0.7, "grad_norm": 1.0943022887554288, "learning_rate": 4.45142325189216e-06, "loss": 0.8718, "step": 3621 }, { "epoch": 0.7, "grad_norm": 1.0119356148268461, "learning_rate": 4.446240606171945e-06, "loss": 0.8489, "step": 3622 }, { "epoch": 0.7, "grad_norm": 0.9911498705134965, "learning_rate": 4.4410601166123475e-06, "loss": 0.8503, "step": 3623 }, { "epoch": 0.7, "grad_norm": 1.019562842712685, "learning_rate": 4.4358817852246124e-06, "loss": 0.8647, "step": 3624 }, { "epoch": 0.7, "grad_norm": 1.0248716264804107, "learning_rate": 4.430705614019147e-06, "loss": 0.9048, "step": 3625 }, { "epoch": 0.7, "grad_norm": 1.1508459380618579, "learning_rate": 4.425531605005519e-06, "loss": 0.8923, "step": 3626 }, { "epoch": 0.7, "grad_norm": 1.0366143346791645, "learning_rate": 4.420359760192452e-06, "loss": 0.8481, "step": 3627 }, { "epoch": 0.7, "grad_norm": 1.088828758023468, "learning_rate": 4.4151900815878455e-06, "loss": 0.8486, "step": 3628 }, { "epoch": 0.7, "grad_norm": 1.0256298471871796, "learning_rate": 4.410022571198734e-06, "loss": 0.9053, "step": 3629 }, { "epoch": 0.7, "grad_norm": 1.0296135773483626, "learning_rate": 4.404857231031332e-06, "loss": 0.8357, "step": 3630 }, { "epoch": 0.7, "grad_norm": 0.9101424968277958, "learning_rate": 4.399694063090999e-06, "loss": 0.813, "step": 3631 }, { "epoch": 0.7, "grad_norm": 0.9944198692582453, "learning_rate": 4.394533069382255e-06, "loss": 0.9216, "step": 3632 }, { "epoch": 0.7, "grad_norm": 1.0335094024088227, "learning_rate": 4.3893742519087754e-06, "loss": 0.8606, "step": 3633 }, { "epoch": 0.7, "grad_norm": 0.9411270340396263, "learning_rate": 4.3842176126733914e-06, "loss": 0.801, "step": 3634 }, { "epoch": 0.7, "grad_norm": 0.9972783854906869, "learning_rate": 4.379063153678087e-06, "loss": 0.8755, "step": 3635 }, { "epoch": 0.7, "grad_norm": 1.0461339275843733, "learning_rate": 4.373910876923997e-06, "loss": 0.876, "step": 3636 }, { "epoch": 0.7, "grad_norm": 0.9485333604087706, "learning_rate": 4.368760784411423e-06, "loss": 0.8853, "step": 3637 }, { "epoch": 0.7, "grad_norm": 0.9278283090469591, "learning_rate": 4.363612878139799e-06, "loss": 0.8035, "step": 3638 }, { "epoch": 0.7, "grad_norm": 0.9805743506829403, "learning_rate": 4.3584671601077224e-06, "loss": 0.8741, "step": 3639 }, { "epoch": 0.7, "grad_norm": 0.8956234988780164, "learning_rate": 4.353323632312938e-06, "loss": 0.5924, "step": 3640 }, { "epoch": 0.7, "grad_norm": 1.080496366233088, "learning_rate": 4.348182296752336e-06, "loss": 0.8337, "step": 3641 }, { "epoch": 0.7, "grad_norm": 1.026566723887617, "learning_rate": 4.343043155421971e-06, "loss": 0.8516, "step": 3642 }, { "epoch": 0.7, "grad_norm": 1.0329257422832305, "learning_rate": 4.3379062103170214e-06, "loss": 0.7854, "step": 3643 }, { "epoch": 0.7, "grad_norm": 1.0527491206877444, "learning_rate": 4.332771463431837e-06, "loss": 0.8607, "step": 3644 }, { "epoch": 0.7, "grad_norm": 1.0260887258246045, "learning_rate": 4.327638916759898e-06, "loss": 0.8923, "step": 3645 }, { "epoch": 0.7, "grad_norm": 1.0594908449371705, "learning_rate": 4.322508572293836e-06, "loss": 0.8813, "step": 3646 }, { "epoch": 0.7, "grad_norm": 1.0468944113625578, "learning_rate": 4.317380432025428e-06, "loss": 0.8667, "step": 3647 }, { "epoch": 0.7, "grad_norm": 1.1863189479845355, "learning_rate": 4.312254497945595e-06, "loss": 0.8796, "step": 3648 }, { "epoch": 0.7, "grad_norm": 1.048612668818574, "learning_rate": 4.3071307720444015e-06, "loss": 0.8151, "step": 3649 }, { "epoch": 0.7, "grad_norm": 1.1435166233708893, "learning_rate": 4.3020092563110485e-06, "loss": 0.8401, "step": 3650 }, { "epoch": 0.7, "grad_norm": 1.0189413573853894, "learning_rate": 4.2968899527338984e-06, "loss": 0.8755, "step": 3651 }, { "epoch": 0.7, "grad_norm": 1.0126994123946051, "learning_rate": 4.291772863300428e-06, "loss": 0.8499, "step": 3652 }, { "epoch": 0.7, "grad_norm": 1.1451298074955671, "learning_rate": 4.2866579899972686e-06, "loss": 0.9197, "step": 3653 }, { "epoch": 0.7, "grad_norm": 1.1795149259109443, "learning_rate": 4.281545334810201e-06, "loss": 0.8992, "step": 3654 }, { "epoch": 0.7, "grad_norm": 0.9839984447000356, "learning_rate": 4.276434899724119e-06, "loss": 0.8479, "step": 3655 }, { "epoch": 0.7, "grad_norm": 1.0768907489283313, "learning_rate": 4.27132668672308e-06, "loss": 0.8384, "step": 3656 }, { "epoch": 0.7, "grad_norm": 1.1536830455633562, "learning_rate": 4.266220697790266e-06, "loss": 0.8853, "step": 3657 }, { "epoch": 0.7, "grad_norm": 0.9570260439458664, "learning_rate": 4.2611169349079985e-06, "loss": 0.8533, "step": 3658 }, { "epoch": 0.7, "grad_norm": 1.2177731790060522, "learning_rate": 4.25601540005773e-06, "loss": 0.8301, "step": 3659 }, { "epoch": 0.7, "grad_norm": 1.0304721474546326, "learning_rate": 4.250916095220056e-06, "loss": 0.8945, "step": 3660 }, { "epoch": 0.7, "grad_norm": 1.135054233998526, "learning_rate": 4.2458190223747e-06, "loss": 0.896, "step": 3661 }, { "epoch": 0.7, "grad_norm": 1.009336462674753, "learning_rate": 4.240724183500518e-06, "loss": 0.8403, "step": 3662 }, { "epoch": 0.7, "grad_norm": 1.0023403126039978, "learning_rate": 4.2356315805755135e-06, "loss": 0.8594, "step": 3663 }, { "epoch": 0.7, "grad_norm": 1.0245761353341711, "learning_rate": 4.230541215576798e-06, "loss": 0.8313, "step": 3664 }, { "epoch": 0.71, "grad_norm": 1.0498619851289288, "learning_rate": 4.225453090480631e-06, "loss": 0.876, "step": 3665 }, { "epoch": 0.71, "grad_norm": 0.9707029398298183, "learning_rate": 4.220367207262398e-06, "loss": 0.8652, "step": 3666 }, { "epoch": 0.71, "grad_norm": 0.9435505540007486, "learning_rate": 4.21528356789661e-06, "loss": 0.821, "step": 3667 }, { "epoch": 0.71, "grad_norm": 1.0669099025360997, "learning_rate": 4.210202174356922e-06, "loss": 0.8464, "step": 3668 }, { "epoch": 0.71, "grad_norm": 1.0197293092144146, "learning_rate": 4.20512302861609e-06, "loss": 0.834, "step": 3669 }, { "epoch": 0.71, "grad_norm": 1.157255588441103, "learning_rate": 4.2000461326460274e-06, "loss": 0.8862, "step": 3670 }, { "epoch": 0.71, "grad_norm": 0.9798696476190935, "learning_rate": 4.194971488417753e-06, "loss": 0.8616, "step": 3671 }, { "epoch": 0.71, "grad_norm": 1.0875054819264172, "learning_rate": 4.189899097901421e-06, "loss": 0.9028, "step": 3672 }, { "epoch": 0.71, "grad_norm": 0.6266818908196612, "learning_rate": 4.184828963066305e-06, "loss": 0.3339, "step": 3673 }, { "epoch": 0.71, "grad_norm": 1.0380261274783515, "learning_rate": 4.179761085880809e-06, "loss": 0.843, "step": 3674 }, { "epoch": 0.71, "grad_norm": 0.9267684123937432, "learning_rate": 4.174695468312456e-06, "loss": 0.895, "step": 3675 }, { "epoch": 0.71, "grad_norm": 1.3021496743150132, "learning_rate": 4.16963211232789e-06, "loss": 0.8702, "step": 3676 }, { "epoch": 0.71, "grad_norm": 1.0302887322208085, "learning_rate": 4.16457101989289e-06, "loss": 0.8557, "step": 3677 }, { "epoch": 0.71, "grad_norm": 1.1001104594542574, "learning_rate": 4.159512192972337e-06, "loss": 0.8811, "step": 3678 }, { "epoch": 0.71, "grad_norm": 0.848223563669891, "learning_rate": 4.15445563353024e-06, "loss": 0.8252, "step": 3679 }, { "epoch": 0.71, "grad_norm": 1.087832223935789, "learning_rate": 4.149401343529742e-06, "loss": 0.8406, "step": 3680 }, { "epoch": 0.71, "grad_norm": 0.8900848198030527, "learning_rate": 4.144349324933077e-06, "loss": 0.8201, "step": 3681 }, { "epoch": 0.71, "grad_norm": 1.1173314953335234, "learning_rate": 4.139299579701623e-06, "loss": 0.8665, "step": 3682 }, { "epoch": 0.71, "grad_norm": 1.062355779841874, "learning_rate": 4.134252109795863e-06, "loss": 0.8425, "step": 3683 }, { "epoch": 0.71, "grad_norm": 1.112861209817392, "learning_rate": 4.129206917175397e-06, "loss": 0.856, "step": 3684 }, { "epoch": 0.71, "grad_norm": 0.8427118604753198, "learning_rate": 4.124164003798944e-06, "loss": 0.5784, "step": 3685 }, { "epoch": 0.71, "grad_norm": 0.7888172166474263, "learning_rate": 4.119123371624335e-06, "loss": 0.588, "step": 3686 }, { "epoch": 0.71, "grad_norm": 0.9080592138215281, "learning_rate": 4.114085022608517e-06, "loss": 0.7916, "step": 3687 }, { "epoch": 0.71, "grad_norm": 1.0258378392178842, "learning_rate": 4.109048958707552e-06, "loss": 0.8179, "step": 3688 }, { "epoch": 0.71, "grad_norm": 0.8949641438467091, "learning_rate": 4.104015181876613e-06, "loss": 0.5499, "step": 3689 }, { "epoch": 0.71, "grad_norm": 1.1547124960785151, "learning_rate": 4.09898369406998e-06, "loss": 0.845, "step": 3690 }, { "epoch": 0.71, "grad_norm": 1.0325255505698372, "learning_rate": 4.0939544972410636e-06, "loss": 0.8572, "step": 3691 }, { "epoch": 0.71, "grad_norm": 1.055608103448508, "learning_rate": 4.0889275933423576e-06, "loss": 0.8086, "step": 3692 }, { "epoch": 0.71, "grad_norm": 1.090275593453073, "learning_rate": 4.0839029843254815e-06, "loss": 0.8369, "step": 3693 }, { "epoch": 0.71, "grad_norm": 0.9147153030847466, "learning_rate": 4.078880672141171e-06, "loss": 0.8982, "step": 3694 }, { "epoch": 0.71, "grad_norm": 0.9616882138959115, "learning_rate": 4.073860658739246e-06, "loss": 0.8647, "step": 3695 }, { "epoch": 0.71, "grad_norm": 0.9333599052839193, "learning_rate": 4.068842946068661e-06, "loss": 0.8376, "step": 3696 }, { "epoch": 0.71, "grad_norm": 0.9929930773963785, "learning_rate": 4.063827536077459e-06, "loss": 0.6121, "step": 3697 }, { "epoch": 0.71, "grad_norm": 1.1152414788906766, "learning_rate": 4.058814430712796e-06, "loss": 0.8857, "step": 3698 }, { "epoch": 0.71, "grad_norm": 0.9481649016186947, "learning_rate": 4.0538036319209325e-06, "loss": 0.8604, "step": 3699 }, { "epoch": 0.71, "grad_norm": 1.0601624644841583, "learning_rate": 4.0487951416472324e-06, "loss": 0.8706, "step": 3700 }, { "epoch": 0.71, "grad_norm": 0.9941713219720436, "learning_rate": 4.043788961836164e-06, "loss": 0.8867, "step": 3701 }, { "epoch": 0.71, "grad_norm": 1.0127883346969495, "learning_rate": 4.038785094431295e-06, "loss": 0.8577, "step": 3702 }, { "epoch": 0.71, "grad_norm": 1.0977825714880778, "learning_rate": 4.0337835413753116e-06, "loss": 0.8594, "step": 3703 }, { "epoch": 0.71, "grad_norm": 1.1227960184057766, "learning_rate": 4.0287843046099765e-06, "loss": 0.8989, "step": 3704 }, { "epoch": 0.71, "grad_norm": 1.2259985098257649, "learning_rate": 4.0237873860761645e-06, "loss": 0.9487, "step": 3705 }, { "epoch": 0.71, "grad_norm": 0.9562594289018729, "learning_rate": 4.018792787713865e-06, "loss": 0.7876, "step": 3706 }, { "epoch": 0.71, "grad_norm": 1.1706265530764333, "learning_rate": 4.013800511462135e-06, "loss": 0.8828, "step": 3707 }, { "epoch": 0.71, "grad_norm": 1.1225033122567514, "learning_rate": 4.008810559259162e-06, "loss": 0.8472, "step": 3708 }, { "epoch": 0.71, "grad_norm": 0.8345049845692766, "learning_rate": 4.003822933042213e-06, "loss": 0.5636, "step": 3709 }, { "epoch": 0.71, "grad_norm": 1.1086193276331833, "learning_rate": 3.998837634747655e-06, "loss": 0.8647, "step": 3710 }, { "epoch": 0.71, "grad_norm": 1.2436721700578963, "learning_rate": 3.993854666310955e-06, "loss": 0.8386, "step": 3711 }, { "epoch": 0.71, "grad_norm": 1.0884169879513046, "learning_rate": 3.98887402966667e-06, "loss": 0.8079, "step": 3712 }, { "epoch": 0.71, "grad_norm": 0.9951568757978501, "learning_rate": 3.983895726748455e-06, "loss": 0.9277, "step": 3713 }, { "epoch": 0.71, "grad_norm": 1.0825312429481964, "learning_rate": 3.97891975948906e-06, "loss": 0.8928, "step": 3714 }, { "epoch": 0.71, "grad_norm": 1.0288817720725703, "learning_rate": 3.973946129820326e-06, "loss": 0.8645, "step": 3715 }, { "epoch": 0.71, "grad_norm": 1.148445278177066, "learning_rate": 3.968974839673186e-06, "loss": 0.8342, "step": 3716 }, { "epoch": 0.72, "grad_norm": 1.08025645610561, "learning_rate": 3.964005890977672e-06, "loss": 0.8655, "step": 3717 }, { "epoch": 0.72, "grad_norm": 1.019433609947572, "learning_rate": 3.9590392856628946e-06, "loss": 0.8386, "step": 3718 }, { "epoch": 0.72, "grad_norm": 0.9797816592826781, "learning_rate": 3.954075025657058e-06, "loss": 0.865, "step": 3719 }, { "epoch": 0.72, "grad_norm": 1.0470797110418417, "learning_rate": 3.949113112887471e-06, "loss": 0.8633, "step": 3720 }, { "epoch": 0.72, "grad_norm": 0.990555207863716, "learning_rate": 3.944153549280506e-06, "loss": 0.8694, "step": 3721 }, { "epoch": 0.72, "grad_norm": 1.2707901185796944, "learning_rate": 3.939196336761645e-06, "loss": 0.8438, "step": 3722 }, { "epoch": 0.72, "grad_norm": 0.9361350184587129, "learning_rate": 3.934241477255445e-06, "loss": 0.8904, "step": 3723 }, { "epoch": 0.72, "grad_norm": 1.0330206515198976, "learning_rate": 3.929288972685555e-06, "loss": 0.8289, "step": 3724 }, { "epoch": 0.72, "grad_norm": 1.1858864222192766, "learning_rate": 3.924338824974705e-06, "loss": 0.9292, "step": 3725 }, { "epoch": 0.72, "grad_norm": 0.8963538744422356, "learning_rate": 3.919391036044715e-06, "loss": 0.6252, "step": 3726 }, { "epoch": 0.72, "grad_norm": 1.1047494868553875, "learning_rate": 3.914445607816486e-06, "loss": 0.834, "step": 3727 }, { "epoch": 0.72, "grad_norm": 0.9520148944126765, "learning_rate": 3.909502542210001e-06, "loss": 0.8311, "step": 3728 }, { "epoch": 0.72, "grad_norm": 0.9536766394014676, "learning_rate": 3.904561841144338e-06, "loss": 0.8176, "step": 3729 }, { "epoch": 0.72, "grad_norm": 1.041684772115557, "learning_rate": 3.899623506537635e-06, "loss": 0.8363, "step": 3730 }, { "epoch": 0.72, "grad_norm": 0.9772269334665443, "learning_rate": 3.894687540307127e-06, "loss": 0.8213, "step": 3731 }, { "epoch": 0.72, "grad_norm": 1.0138397036519804, "learning_rate": 3.8897539443691355e-06, "loss": 0.8948, "step": 3732 }, { "epoch": 0.72, "grad_norm": 0.8540360103644922, "learning_rate": 3.884822720639036e-06, "loss": 0.6311, "step": 3733 }, { "epoch": 0.72, "grad_norm": 0.9760893406204686, "learning_rate": 3.879893871031314e-06, "loss": 0.8506, "step": 3734 }, { "epoch": 0.72, "grad_norm": 0.9024240996764579, "learning_rate": 3.874967397459511e-06, "loss": 0.608, "step": 3735 }, { "epoch": 0.72, "grad_norm": 1.2121192230533884, "learning_rate": 3.870043301836256e-06, "loss": 0.865, "step": 3736 }, { "epoch": 0.72, "grad_norm": 0.9301685565758027, "learning_rate": 3.86512158607325e-06, "loss": 0.8486, "step": 3737 }, { "epoch": 0.72, "grad_norm": 1.291736540006822, "learning_rate": 3.860202252081276e-06, "loss": 0.866, "step": 3738 }, { "epoch": 0.72, "grad_norm": 1.0922242101992763, "learning_rate": 3.855285301770188e-06, "loss": 0.8229, "step": 3739 }, { "epoch": 0.72, "grad_norm": 1.1173562438445301, "learning_rate": 3.850370737048913e-06, "loss": 0.8325, "step": 3740 }, { "epoch": 0.72, "grad_norm": 1.0642419389022943, "learning_rate": 3.8454585598254565e-06, "loss": 0.8711, "step": 3741 }, { "epoch": 0.72, "grad_norm": 0.9404847536473822, "learning_rate": 3.840548772006891e-06, "loss": 0.6243, "step": 3742 }, { "epoch": 0.72, "grad_norm": 0.6481599253133513, "learning_rate": 3.835641375499375e-06, "loss": 0.326, "step": 3743 }, { "epoch": 0.72, "grad_norm": 1.0149960108437714, "learning_rate": 3.830736372208118e-06, "loss": 0.9001, "step": 3744 }, { "epoch": 0.72, "grad_norm": 1.085806324123481, "learning_rate": 3.8258337640374125e-06, "loss": 0.8828, "step": 3745 }, { "epoch": 0.72, "grad_norm": 1.0636503614632635, "learning_rate": 3.820933552890629e-06, "loss": 0.8093, "step": 3746 }, { "epoch": 0.72, "grad_norm": 1.0690823207425675, "learning_rate": 3.816035740670185e-06, "loss": 0.7917, "step": 3747 }, { "epoch": 0.72, "grad_norm": 1.098608204989886, "learning_rate": 3.811140329277591e-06, "loss": 0.8962, "step": 3748 }, { "epoch": 0.72, "grad_norm": 1.1291122081589946, "learning_rate": 3.8062473206134088e-06, "loss": 0.8469, "step": 3749 }, { "epoch": 0.72, "grad_norm": 1.0370685094300216, "learning_rate": 3.8013567165772735e-06, "loss": 0.8826, "step": 3750 }, { "epoch": 0.72, "grad_norm": 1.08554995627479, "learning_rate": 3.7964685190678874e-06, "loss": 0.9192, "step": 3751 }, { "epoch": 0.72, "grad_norm": 0.9806946084918347, "learning_rate": 3.7915827299830154e-06, "loss": 0.8242, "step": 3752 }, { "epoch": 0.72, "grad_norm": 1.099521549500914, "learning_rate": 3.7866993512194895e-06, "loss": 0.8835, "step": 3753 }, { "epoch": 0.72, "grad_norm": 1.1360861850992159, "learning_rate": 3.7818183846732024e-06, "loss": 0.8318, "step": 3754 }, { "epoch": 0.72, "grad_norm": 0.9157299923732602, "learning_rate": 3.776939832239125e-06, "loss": 0.8464, "step": 3755 }, { "epoch": 0.72, "grad_norm": 1.2463162580026896, "learning_rate": 3.7720636958112623e-06, "loss": 0.8145, "step": 3756 }, { "epoch": 0.72, "grad_norm": 1.0381411468667148, "learning_rate": 3.7671899772827113e-06, "loss": 0.8936, "step": 3757 }, { "epoch": 0.72, "grad_norm": 0.8467792209938348, "learning_rate": 3.7623186785456156e-06, "loss": 0.6243, "step": 3758 }, { "epoch": 0.72, "grad_norm": 0.8627350252876708, "learning_rate": 3.757449801491172e-06, "loss": 0.6407, "step": 3759 }, { "epoch": 0.72, "grad_norm": 0.8374485756593241, "learning_rate": 3.7525833480096575e-06, "loss": 0.584, "step": 3760 }, { "epoch": 0.72, "grad_norm": 0.9427228210474935, "learning_rate": 3.7477193199903903e-06, "loss": 0.8647, "step": 3761 }, { "epoch": 0.72, "grad_norm": 1.110531772820456, "learning_rate": 3.7428577193217563e-06, "loss": 0.8787, "step": 3762 }, { "epoch": 0.72, "grad_norm": 0.9449768218550642, "learning_rate": 3.737998547891195e-06, "loss": 0.8098, "step": 3763 }, { "epoch": 0.72, "grad_norm": 0.9891703751531701, "learning_rate": 3.7331418075852053e-06, "loss": 0.8481, "step": 3764 }, { "epoch": 0.72, "grad_norm": 1.0145868284064006, "learning_rate": 3.728287500289339e-06, "loss": 0.8623, "step": 3765 }, { "epoch": 0.72, "grad_norm": 1.055468486451258, "learning_rate": 3.7234356278882076e-06, "loss": 0.8076, "step": 3766 }, { "epoch": 0.72, "grad_norm": 1.1477042542847982, "learning_rate": 3.718586192265473e-06, "loss": 0.9075, "step": 3767 }, { "epoch": 0.72, "grad_norm": 0.9527127416701274, "learning_rate": 3.7137391953038516e-06, "loss": 0.7568, "step": 3768 }, { "epoch": 0.73, "grad_norm": 0.7448616881865767, "learning_rate": 3.7088946388851223e-06, "loss": 0.5571, "step": 3769 }, { "epoch": 0.73, "grad_norm": 1.0161014761965366, "learning_rate": 3.7040525248901003e-06, "loss": 0.8757, "step": 3770 }, { "epoch": 0.73, "grad_norm": 0.9997509821166145, "learning_rate": 3.6992128551986617e-06, "loss": 0.8611, "step": 3771 }, { "epoch": 0.73, "grad_norm": 0.7354763795476885, "learning_rate": 3.6943756316897406e-06, "loss": 0.5955, "step": 3772 }, { "epoch": 0.73, "grad_norm": 1.0783559458544805, "learning_rate": 3.6895408562413027e-06, "loss": 0.8767, "step": 3773 }, { "epoch": 0.73, "grad_norm": 0.9780499221930412, "learning_rate": 3.684708530730382e-06, "loss": 0.8955, "step": 3774 }, { "epoch": 0.73, "grad_norm": 0.983507943543633, "learning_rate": 3.6798786570330526e-06, "loss": 0.8557, "step": 3775 }, { "epoch": 0.73, "grad_norm": 1.037862484065532, "learning_rate": 3.6750512370244363e-06, "loss": 0.8361, "step": 3776 }, { "epoch": 0.73, "grad_norm": 1.0040375998395743, "learning_rate": 3.670226272578704e-06, "loss": 0.9006, "step": 3777 }, { "epoch": 0.73, "grad_norm": 0.9727945858943875, "learning_rate": 3.6654037655690732e-06, "loss": 0.8436, "step": 3778 }, { "epoch": 0.73, "grad_norm": 1.0429986373944555, "learning_rate": 3.660583717867807e-06, "loss": 0.8403, "step": 3779 }, { "epoch": 0.73, "grad_norm": 0.9498364746460605, "learning_rate": 3.655766131346211e-06, "loss": 0.8379, "step": 3780 }, { "epoch": 0.73, "grad_norm": 1.0489607295152503, "learning_rate": 3.650951007874648e-06, "loss": 0.8027, "step": 3781 }, { "epoch": 0.73, "grad_norm": 0.9867990979239142, "learning_rate": 3.6461383493225012e-06, "loss": 0.8556, "step": 3782 }, { "epoch": 0.73, "grad_norm": 1.095585671842829, "learning_rate": 3.6413281575582194e-06, "loss": 0.8752, "step": 3783 }, { "epoch": 0.73, "grad_norm": 0.9514236843885644, "learning_rate": 3.6365204344492867e-06, "loss": 0.8198, "step": 3784 }, { "epoch": 0.73, "grad_norm": 0.8156000436215858, "learning_rate": 3.6317151818622154e-06, "loss": 0.5699, "step": 3785 }, { "epoch": 0.73, "grad_norm": 1.0204169578582942, "learning_rate": 3.62691240166258e-06, "loss": 0.8677, "step": 3786 }, { "epoch": 0.73, "grad_norm": 1.05504868512919, "learning_rate": 3.6221120957149826e-06, "loss": 0.8362, "step": 3787 }, { "epoch": 0.73, "grad_norm": 1.0029385811468041, "learning_rate": 3.617314265883066e-06, "loss": 0.8643, "step": 3788 }, { "epoch": 0.73, "grad_norm": 1.1346007880266342, "learning_rate": 3.612518914029515e-06, "loss": 0.8394, "step": 3789 }, { "epoch": 0.73, "grad_norm": 0.9526729882344016, "learning_rate": 3.6077260420160487e-06, "loss": 0.8662, "step": 3790 }, { "epoch": 0.73, "grad_norm": 1.1030199433560162, "learning_rate": 3.602935651703424e-06, "loss": 0.8503, "step": 3791 }, { "epoch": 0.73, "grad_norm": 0.9993788427493512, "learning_rate": 3.598147744951438e-06, "loss": 0.8479, "step": 3792 }, { "epoch": 0.73, "grad_norm": 1.185670864049081, "learning_rate": 3.5933623236189198e-06, "loss": 0.9114, "step": 3793 }, { "epoch": 0.73, "grad_norm": 1.0667527551966596, "learning_rate": 3.58857938956373e-06, "loss": 0.7942, "step": 3794 }, { "epoch": 0.73, "grad_norm": 0.9897895224998252, "learning_rate": 3.58379894464278e-06, "loss": 0.8484, "step": 3795 }, { "epoch": 0.73, "grad_norm": 0.9751901045514457, "learning_rate": 3.57902099071199e-06, "loss": 0.8643, "step": 3796 }, { "epoch": 0.73, "grad_norm": 0.7708258762561404, "learning_rate": 3.5742455296263346e-06, "loss": 0.5528, "step": 3797 }, { "epoch": 0.73, "grad_norm": 1.0756684645074968, "learning_rate": 3.569472563239814e-06, "loss": 0.8069, "step": 3798 }, { "epoch": 0.73, "grad_norm": 0.8906800008404839, "learning_rate": 3.5647020934054465e-06, "loss": 0.8748, "step": 3799 }, { "epoch": 0.73, "grad_norm": 0.7582116761669957, "learning_rate": 3.559934121975304e-06, "loss": 0.5875, "step": 3800 }, { "epoch": 0.73, "grad_norm": 1.1186748782934857, "learning_rate": 3.5551686508004735e-06, "loss": 0.9006, "step": 3801 }, { "epoch": 0.73, "grad_norm": 1.0319198566194605, "learning_rate": 3.550405681731074e-06, "loss": 0.8813, "step": 3802 }, { "epoch": 0.73, "grad_norm": 0.9448153561908332, "learning_rate": 3.5456452166162547e-06, "loss": 0.7952, "step": 3803 }, { "epoch": 0.73, "grad_norm": 1.0683047514494601, "learning_rate": 3.540887257304193e-06, "loss": 0.8979, "step": 3804 }, { "epoch": 0.73, "grad_norm": 0.966312276400449, "learning_rate": 3.5361318056420925e-06, "loss": 0.8408, "step": 3805 }, { "epoch": 0.73, "grad_norm": 1.1410568618783081, "learning_rate": 3.531378863476178e-06, "loss": 0.9092, "step": 3806 }, { "epoch": 0.73, "grad_norm": 1.1211635047863844, "learning_rate": 3.5266284326517165e-06, "loss": 0.8337, "step": 3807 }, { "epoch": 0.73, "grad_norm": 1.088666965482446, "learning_rate": 3.5218805150129755e-06, "loss": 0.8381, "step": 3808 }, { "epoch": 0.73, "grad_norm": 1.0233053988229368, "learning_rate": 3.5171351124032703e-06, "loss": 0.825, "step": 3809 }, { "epoch": 0.73, "grad_norm": 1.0447816391453304, "learning_rate": 3.51239222666493e-06, "loss": 0.8713, "step": 3810 }, { "epoch": 0.73, "grad_norm": 1.0645059152514278, "learning_rate": 3.507651859639295e-06, "loss": 0.8269, "step": 3811 }, { "epoch": 0.73, "grad_norm": 0.9574682724366583, "learning_rate": 3.5029140131667493e-06, "loss": 0.8721, "step": 3812 }, { "epoch": 0.73, "grad_norm": 0.809370957440076, "learning_rate": 3.4981786890866853e-06, "loss": 0.5397, "step": 3813 }, { "epoch": 0.73, "grad_norm": 0.926615571837842, "learning_rate": 3.493445889237518e-06, "loss": 0.8374, "step": 3814 }, { "epoch": 0.73, "grad_norm": 0.8756124757554556, "learning_rate": 3.4887156154566847e-06, "loss": 0.6155, "step": 3815 }, { "epoch": 0.73, "grad_norm": 1.0149688596828836, "learning_rate": 3.4839878695806385e-06, "loss": 0.8711, "step": 3816 }, { "epoch": 0.73, "grad_norm": 1.0681385505311225, "learning_rate": 3.4792626534448547e-06, "loss": 0.8265, "step": 3817 }, { "epoch": 0.73, "grad_norm": 1.2747256475410313, "learning_rate": 3.4745399688838243e-06, "loss": 0.916, "step": 3818 }, { "epoch": 0.73, "grad_norm": 1.005572729330715, "learning_rate": 3.469819817731056e-06, "loss": 0.8376, "step": 3819 }, { "epoch": 0.73, "grad_norm": 0.9512987659263186, "learning_rate": 3.4651022018190715e-06, "loss": 0.8253, "step": 3820 }, { "epoch": 0.74, "grad_norm": 0.8092558762644622, "learning_rate": 3.460387122979423e-06, "loss": 0.6147, "step": 3821 }, { "epoch": 0.74, "grad_norm": 0.9654768230770855, "learning_rate": 3.455674583042652e-06, "loss": 0.8214, "step": 3822 }, { "epoch": 0.74, "grad_norm": 0.9332606587293084, "learning_rate": 3.4509645838383386e-06, "loss": 0.7712, "step": 3823 }, { "epoch": 0.74, "grad_norm": 1.0599152362860134, "learning_rate": 3.4462571271950674e-06, "loss": 0.8667, "step": 3824 }, { "epoch": 0.74, "grad_norm": 0.9917391086277192, "learning_rate": 3.4415522149404233e-06, "loss": 0.8254, "step": 3825 }, { "epoch": 0.74, "grad_norm": 0.9484480159096411, "learning_rate": 3.436849848901028e-06, "loss": 0.8501, "step": 3826 }, { "epoch": 0.74, "grad_norm": 1.0008718378830004, "learning_rate": 3.432150030902497e-06, "loss": 0.8206, "step": 3827 }, { "epoch": 0.74, "grad_norm": 1.1707951170639301, "learning_rate": 3.427452762769462e-06, "loss": 0.8682, "step": 3828 }, { "epoch": 0.74, "grad_norm": 0.995145573529371, "learning_rate": 3.4227580463255628e-06, "loss": 0.8618, "step": 3829 }, { "epoch": 0.74, "grad_norm": 1.029203707027087, "learning_rate": 3.4180658833934523e-06, "loss": 0.8369, "step": 3830 }, { "epoch": 0.74, "grad_norm": 0.9293492480979887, "learning_rate": 3.4133762757947873e-06, "loss": 0.8726, "step": 3831 }, { "epoch": 0.74, "grad_norm": 1.179981284909612, "learning_rate": 3.4086892253502344e-06, "loss": 0.9031, "step": 3832 }, { "epoch": 0.74, "grad_norm": 1.108801626613365, "learning_rate": 3.4040047338794756e-06, "loss": 0.8867, "step": 3833 }, { "epoch": 0.74, "grad_norm": 1.058113023522362, "learning_rate": 3.3993228032011784e-06, "loss": 0.8325, "step": 3834 }, { "epoch": 0.74, "grad_norm": 0.9673640824573997, "learning_rate": 3.3946434351330415e-06, "loss": 0.8713, "step": 3835 }, { "epoch": 0.74, "grad_norm": 0.968660823020739, "learning_rate": 3.3899666314917512e-06, "loss": 0.8384, "step": 3836 }, { "epoch": 0.74, "grad_norm": 0.9994916442165255, "learning_rate": 3.385292394093006e-06, "loss": 0.8489, "step": 3837 }, { "epoch": 0.74, "grad_norm": 0.9683867164403114, "learning_rate": 3.3806207247515068e-06, "loss": 0.8237, "step": 3838 }, { "epoch": 0.74, "grad_norm": 0.9580143132120459, "learning_rate": 3.375951625280948e-06, "loss": 0.8137, "step": 3839 }, { "epoch": 0.74, "grad_norm": 1.1558086589601044, "learning_rate": 3.3712850974940437e-06, "loss": 0.8853, "step": 3840 }, { "epoch": 0.74, "grad_norm": 0.9727248068092217, "learning_rate": 3.3666211432024974e-06, "loss": 0.7913, "step": 3841 }, { "epoch": 0.74, "grad_norm": 0.9466752213147845, "learning_rate": 3.361959764217018e-06, "loss": 0.8032, "step": 3842 }, { "epoch": 0.74, "grad_norm": 0.9101453880758851, "learning_rate": 3.357300962347313e-06, "loss": 0.7905, "step": 3843 }, { "epoch": 0.74, "grad_norm": 0.9943567506668344, "learning_rate": 3.3526447394020887e-06, "loss": 0.863, "step": 3844 }, { "epoch": 0.74, "grad_norm": 1.2021500332184156, "learning_rate": 3.3479910971890516e-06, "loss": 0.9041, "step": 3845 }, { "epoch": 0.74, "grad_norm": 1.1158040524097088, "learning_rate": 3.343340037514903e-06, "loss": 0.8535, "step": 3846 }, { "epoch": 0.74, "grad_norm": 0.9679987695124647, "learning_rate": 3.3386915621853533e-06, "loss": 0.8467, "step": 3847 }, { "epoch": 0.74, "grad_norm": 1.009558772698071, "learning_rate": 3.3340456730050887e-06, "loss": 0.8799, "step": 3848 }, { "epoch": 0.74, "grad_norm": 0.9540091184773795, "learning_rate": 3.3294023717778122e-06, "loss": 0.8164, "step": 3849 }, { "epoch": 0.74, "grad_norm": 1.0406188987217997, "learning_rate": 3.324761660306215e-06, "loss": 0.8542, "step": 3850 }, { "epoch": 0.74, "grad_norm": 1.012879235387129, "learning_rate": 3.3201235403919683e-06, "loss": 0.9116, "step": 3851 }, { "epoch": 0.74, "grad_norm": 0.9909471184242075, "learning_rate": 3.3154880138357626e-06, "loss": 0.8296, "step": 3852 }, { "epoch": 0.74, "grad_norm": 0.7185239919201453, "learning_rate": 3.3108550824372632e-06, "loss": 0.5501, "step": 3853 }, { "epoch": 0.74, "grad_norm": 1.0060911202124205, "learning_rate": 3.306224747995136e-06, "loss": 0.7933, "step": 3854 }, { "epoch": 0.74, "grad_norm": 1.1884314501843125, "learning_rate": 3.301597012307034e-06, "loss": 0.8828, "step": 3855 }, { "epoch": 0.74, "grad_norm": 1.1072606242862695, "learning_rate": 3.2969718771696047e-06, "loss": 0.8015, "step": 3856 }, { "epoch": 0.74, "grad_norm": 1.078683089548322, "learning_rate": 3.292349344378486e-06, "loss": 0.8125, "step": 3857 }, { "epoch": 0.74, "grad_norm": 0.7927525030503054, "learning_rate": 3.287729415728298e-06, "loss": 0.5731, "step": 3858 }, { "epoch": 0.74, "grad_norm": 0.8635111587317972, "learning_rate": 3.283112093012669e-06, "loss": 0.6042, "step": 3859 }, { "epoch": 0.74, "grad_norm": 1.071752886829833, "learning_rate": 3.278497378024187e-06, "loss": 0.811, "step": 3860 }, { "epoch": 0.74, "grad_norm": 1.0651298666212776, "learning_rate": 3.2738852725544547e-06, "loss": 0.8296, "step": 3861 }, { "epoch": 0.74, "grad_norm": 0.9947471784761887, "learning_rate": 3.2692757783940467e-06, "loss": 0.8557, "step": 3862 }, { "epoch": 0.74, "grad_norm": 1.0275729492788814, "learning_rate": 3.264668897332527e-06, "loss": 0.8792, "step": 3863 }, { "epoch": 0.74, "grad_norm": 1.186534754086911, "learning_rate": 3.2600646311584494e-06, "loss": 0.9128, "step": 3864 }, { "epoch": 0.74, "grad_norm": 1.2578937281419917, "learning_rate": 3.2554629816593375e-06, "loss": 0.8193, "step": 3865 }, { "epoch": 0.74, "grad_norm": 0.8643637437341363, "learning_rate": 3.250863950621721e-06, "loss": 0.5722, "step": 3866 }, { "epoch": 0.74, "grad_norm": 1.1173984001946422, "learning_rate": 3.2462675398310984e-06, "loss": 0.8867, "step": 3867 }, { "epoch": 0.74, "grad_norm": 0.9287295502583529, "learning_rate": 3.241673751071954e-06, "loss": 0.8069, "step": 3868 }, { "epoch": 0.74, "grad_norm": 0.9465845574750911, "learning_rate": 3.2370825861277567e-06, "loss": 0.8123, "step": 3869 }, { "epoch": 0.74, "grad_norm": 0.9867459141763042, "learning_rate": 3.2324940467809527e-06, "loss": 0.8179, "step": 3870 }, { "epoch": 0.74, "grad_norm": 1.1019384135035377, "learning_rate": 3.2279081348129713e-06, "loss": 0.8657, "step": 3871 }, { "epoch": 0.74, "grad_norm": 0.9858989456961694, "learning_rate": 3.223324852004219e-06, "loss": 0.8804, "step": 3872 }, { "epoch": 0.75, "grad_norm": 1.160449339389835, "learning_rate": 3.2187442001340942e-06, "loss": 0.8276, "step": 3873 }, { "epoch": 0.75, "grad_norm": 0.8524272632102998, "learning_rate": 3.21416618098095e-06, "loss": 0.6067, "step": 3874 }, { "epoch": 0.75, "grad_norm": 1.0220176690965221, "learning_rate": 3.2095907963221396e-06, "loss": 0.8279, "step": 3875 }, { "epoch": 0.75, "grad_norm": 0.9864334741833799, "learning_rate": 3.2050180479339865e-06, "loss": 0.856, "step": 3876 }, { "epoch": 0.75, "grad_norm": 0.9168256545202255, "learning_rate": 3.2004479375917783e-06, "loss": 0.8201, "step": 3877 }, { "epoch": 0.75, "grad_norm": 1.0658229594628572, "learning_rate": 3.1958804670698008e-06, "loss": 0.8459, "step": 3878 }, { "epoch": 0.75, "grad_norm": 0.9891936988897998, "learning_rate": 3.191315638141297e-06, "loss": 0.8015, "step": 3879 }, { "epoch": 0.75, "grad_norm": 1.2139180967591512, "learning_rate": 3.1867534525784937e-06, "loss": 0.925, "step": 3880 }, { "epoch": 0.75, "grad_norm": 1.0031741832287833, "learning_rate": 3.182193912152586e-06, "loss": 0.8672, "step": 3881 }, { "epoch": 0.75, "grad_norm": 0.9822521375920865, "learning_rate": 3.177637018633746e-06, "loss": 0.8896, "step": 3882 }, { "epoch": 0.75, "grad_norm": 1.2058250319596984, "learning_rate": 3.1730827737911163e-06, "loss": 0.8165, "step": 3883 }, { "epoch": 0.75, "grad_norm": 1.0842120648866695, "learning_rate": 3.1685311793928077e-06, "loss": 0.8826, "step": 3884 }, { "epoch": 0.75, "grad_norm": 1.2513823264337365, "learning_rate": 3.163982237205917e-06, "loss": 0.8975, "step": 3885 }, { "epoch": 0.75, "grad_norm": 1.012329016694337, "learning_rate": 3.1594359489964853e-06, "loss": 0.7585, "step": 3886 }, { "epoch": 0.75, "grad_norm": 1.0111910978349616, "learning_rate": 3.15489231652955e-06, "loss": 0.8438, "step": 3887 }, { "epoch": 0.75, "grad_norm": 1.0287811092766415, "learning_rate": 3.150351341569101e-06, "loss": 0.8291, "step": 3888 }, { "epoch": 0.75, "grad_norm": 0.9725312942408452, "learning_rate": 3.1458130258781006e-06, "loss": 0.8184, "step": 3889 }, { "epoch": 0.75, "grad_norm": 0.9214984985698705, "learning_rate": 3.141277371218484e-06, "loss": 0.8051, "step": 3890 }, { "epoch": 0.75, "grad_norm": 1.1450440743750205, "learning_rate": 3.136744379351139e-06, "loss": 0.8694, "step": 3891 }, { "epoch": 0.75, "grad_norm": 1.0333553962102062, "learning_rate": 3.1322140520359366e-06, "loss": 0.8391, "step": 3892 }, { "epoch": 0.75, "grad_norm": 0.6030900254664795, "learning_rate": 3.1276863910317057e-06, "loss": 0.3701, "step": 3893 }, { "epoch": 0.75, "grad_norm": 0.9568213716832207, "learning_rate": 3.1231613980962373e-06, "loss": 0.8386, "step": 3894 }, { "epoch": 0.75, "grad_norm": 1.0107951613379385, "learning_rate": 3.1186390749862904e-06, "loss": 0.7668, "step": 3895 }, { "epoch": 0.75, "grad_norm": 1.042587572711002, "learning_rate": 3.1141194234575878e-06, "loss": 0.8738, "step": 3896 }, { "epoch": 0.75, "grad_norm": 0.8577283587656491, "learning_rate": 3.1096024452648123e-06, "loss": 0.6249, "step": 3897 }, { "epoch": 0.75, "grad_norm": 1.14046646001877, "learning_rate": 3.1050881421616076e-06, "loss": 0.875, "step": 3898 }, { "epoch": 0.75, "grad_norm": 0.971217832474283, "learning_rate": 3.100576515900591e-06, "loss": 0.8425, "step": 3899 }, { "epoch": 0.75, "grad_norm": 1.1483963338413938, "learning_rate": 3.0960675682333186e-06, "loss": 0.8022, "step": 3900 }, { "epoch": 0.75, "grad_norm": 1.1007848553940294, "learning_rate": 3.0915613009103296e-06, "loss": 0.7898, "step": 3901 }, { "epoch": 0.75, "grad_norm": 0.9926105498709755, "learning_rate": 3.0870577156811077e-06, "loss": 0.8218, "step": 3902 }, { "epoch": 0.75, "grad_norm": 1.0126794246624669, "learning_rate": 3.0825568142940998e-06, "loss": 0.859, "step": 3903 }, { "epoch": 0.75, "grad_norm": 1.048394026331091, "learning_rate": 3.0780585984967113e-06, "loss": 0.8108, "step": 3904 }, { "epoch": 0.75, "grad_norm": 1.1433717186704275, "learning_rate": 3.073563070035305e-06, "loss": 0.8098, "step": 3905 }, { "epoch": 0.75, "grad_norm": 1.0073838276406644, "learning_rate": 3.069070230655198e-06, "loss": 0.7256, "step": 3906 }, { "epoch": 0.75, "grad_norm": 1.013919523064517, "learning_rate": 3.0645800821006667e-06, "loss": 0.8586, "step": 3907 }, { "epoch": 0.75, "grad_norm": 1.0093501011258352, "learning_rate": 3.060092626114941e-06, "loss": 0.8447, "step": 3908 }, { "epoch": 0.75, "grad_norm": 0.9581002318184997, "learning_rate": 3.0556078644402066e-06, "loss": 0.8787, "step": 3909 }, { "epoch": 0.75, "grad_norm": 1.0459787460824626, "learning_rate": 3.051125798817598e-06, "loss": 0.8735, "step": 3910 }, { "epoch": 0.75, "grad_norm": 1.0182627101016064, "learning_rate": 3.0466464309872167e-06, "loss": 0.8484, "step": 3911 }, { "epoch": 0.75, "grad_norm": 1.0075368116027752, "learning_rate": 3.042169762688096e-06, "loss": 0.8564, "step": 3912 }, { "epoch": 0.75, "grad_norm": 1.1068919968666475, "learning_rate": 3.0376957956582452e-06, "loss": 0.8381, "step": 3913 }, { "epoch": 0.75, "grad_norm": 1.190848845102036, "learning_rate": 3.0332245316346e-06, "loss": 0.8527, "step": 3914 }, { "epoch": 0.75, "grad_norm": 1.0402751881788206, "learning_rate": 3.0287559723530667e-06, "loss": 0.8884, "step": 3915 }, { "epoch": 0.75, "grad_norm": 1.0278306834196191, "learning_rate": 3.024290119548495e-06, "loss": 0.8555, "step": 3916 }, { "epoch": 0.75, "grad_norm": 1.0570156453007062, "learning_rate": 3.019826974954674e-06, "loss": 0.8662, "step": 3917 }, { "epoch": 0.75, "grad_norm": 1.061314001321096, "learning_rate": 3.0153665403043586e-06, "loss": 0.8347, "step": 3918 }, { "epoch": 0.75, "grad_norm": 0.9055172955452649, "learning_rate": 3.01090881732924e-06, "loss": 0.7811, "step": 3919 }, { "epoch": 0.75, "grad_norm": 1.1935069543890988, "learning_rate": 3.0064538077599603e-06, "loss": 0.9155, "step": 3920 }, { "epoch": 0.75, "grad_norm": 1.0673839375166274, "learning_rate": 3.002001513326107e-06, "loss": 0.8838, "step": 3921 }, { "epoch": 0.75, "grad_norm": 0.9782395732502583, "learning_rate": 2.9975519357562155e-06, "loss": 0.8149, "step": 3922 }, { "epoch": 0.75, "grad_norm": 0.9615966721040131, "learning_rate": 2.9931050767777626e-06, "loss": 0.8481, "step": 3923 }, { "epoch": 0.75, "grad_norm": 0.8103942490414106, "learning_rate": 2.9886609381171703e-06, "loss": 0.5926, "step": 3924 }, { "epoch": 0.76, "grad_norm": 1.108459147080476, "learning_rate": 2.984219521499816e-06, "loss": 0.8201, "step": 3925 }, { "epoch": 0.76, "grad_norm": 1.0164127960166547, "learning_rate": 2.9797808286499976e-06, "loss": 0.8757, "step": 3926 }, { "epoch": 0.76, "grad_norm": 0.8815318570271854, "learning_rate": 2.9753448612909775e-06, "loss": 0.5294, "step": 3927 }, { "epoch": 0.76, "grad_norm": 1.0657897315951765, "learning_rate": 2.9709116211449484e-06, "loss": 0.8862, "step": 3928 }, { "epoch": 0.76, "grad_norm": 1.051098225337221, "learning_rate": 2.966481109933047e-06, "loss": 0.863, "step": 3929 }, { "epoch": 0.76, "grad_norm": 1.077076712080962, "learning_rate": 2.9620533293753495e-06, "loss": 0.884, "step": 3930 }, { "epoch": 0.76, "grad_norm": 0.758153765671402, "learning_rate": 2.957628281190873e-06, "loss": 0.5673, "step": 3931 }, { "epoch": 0.76, "grad_norm": 0.9317096596157949, "learning_rate": 2.9532059670975732e-06, "loss": 0.7932, "step": 3932 }, { "epoch": 0.76, "grad_norm": 1.1499342325773927, "learning_rate": 2.948786388812346e-06, "loss": 0.9126, "step": 3933 }, { "epoch": 0.76, "grad_norm": 1.2870660517337609, "learning_rate": 2.9443695480510225e-06, "loss": 0.8621, "step": 3934 }, { "epoch": 0.76, "grad_norm": 0.9864229606368674, "learning_rate": 2.9399554465283742e-06, "loss": 0.832, "step": 3935 }, { "epoch": 0.76, "grad_norm": 0.8440687454460231, "learning_rate": 2.935544085958102e-06, "loss": 0.5692, "step": 3936 }, { "epoch": 0.76, "grad_norm": 1.0726520512113888, "learning_rate": 2.931135468052858e-06, "loss": 0.9048, "step": 3937 }, { "epoch": 0.76, "grad_norm": 0.9621407399096715, "learning_rate": 2.926729594524207e-06, "loss": 0.8457, "step": 3938 }, { "epoch": 0.76, "grad_norm": 1.1271643213452793, "learning_rate": 2.9223264670826746e-06, "loss": 0.8601, "step": 3939 }, { "epoch": 0.76, "grad_norm": 0.8063429606232703, "learning_rate": 2.9179260874376915e-06, "loss": 0.619, "step": 3940 }, { "epoch": 0.76, "grad_norm": 1.009928680919898, "learning_rate": 2.9135284572976486e-06, "loss": 0.9012, "step": 3941 }, { "epoch": 0.76, "grad_norm": 0.8772596933715697, "learning_rate": 2.9091335783698517e-06, "loss": 0.6069, "step": 3942 }, { "epoch": 0.76, "grad_norm": 0.9317593949913049, "learning_rate": 2.9047414523605467e-06, "loss": 0.803, "step": 3943 }, { "epoch": 0.76, "grad_norm": 1.0589470385991513, "learning_rate": 2.9003520809749053e-06, "loss": 0.8787, "step": 3944 }, { "epoch": 0.76, "grad_norm": 0.9891231138959621, "learning_rate": 2.8959654659170354e-06, "loss": 0.8472, "step": 3945 }, { "epoch": 0.76, "grad_norm": 1.0651853995505596, "learning_rate": 2.8915816088899696e-06, "loss": 0.8867, "step": 3946 }, { "epoch": 0.76, "grad_norm": 1.109451011891989, "learning_rate": 2.8872005115956746e-06, "loss": 0.856, "step": 3947 }, { "epoch": 0.76, "grad_norm": 1.1031491565693494, "learning_rate": 2.8828221757350406e-06, "loss": 0.8369, "step": 3948 }, { "epoch": 0.76, "grad_norm": 1.0237245178841166, "learning_rate": 2.8784466030078905e-06, "loss": 0.8533, "step": 3949 }, { "epoch": 0.76, "grad_norm": 1.1845956665605795, "learning_rate": 2.874073795112967e-06, "loss": 0.813, "step": 3950 }, { "epoch": 0.76, "grad_norm": 1.3162098601546706, "learning_rate": 2.8697037537479565e-06, "loss": 0.8682, "step": 3951 }, { "epoch": 0.76, "grad_norm": 1.0941904669072677, "learning_rate": 2.8653364806094454e-06, "loss": 0.8325, "step": 3952 }, { "epoch": 0.76, "grad_norm": 1.1840273258510603, "learning_rate": 2.86097197739297e-06, "loss": 0.8016, "step": 3953 }, { "epoch": 0.76, "grad_norm": 1.0701703810181808, "learning_rate": 2.856610245792976e-06, "loss": 0.8518, "step": 3954 }, { "epoch": 0.76, "grad_norm": 1.0162756410694087, "learning_rate": 2.8522512875028396e-06, "loss": 0.5772, "step": 3955 }, { "epoch": 0.76, "grad_norm": 0.9522305755154712, "learning_rate": 2.847895104214856e-06, "loss": 0.8176, "step": 3956 }, { "epoch": 0.76, "grad_norm": 1.0781584169557819, "learning_rate": 2.843541697620249e-06, "loss": 0.8459, "step": 3957 }, { "epoch": 0.76, "grad_norm": 1.063060194600373, "learning_rate": 2.8391910694091584e-06, "loss": 0.8799, "step": 3958 }, { "epoch": 0.76, "grad_norm": 1.0557546607601893, "learning_rate": 2.8348432212706443e-06, "loss": 0.8682, "step": 3959 }, { "epoch": 0.76, "grad_norm": 0.9661060097282994, "learning_rate": 2.8304981548927025e-06, "loss": 0.8853, "step": 3960 }, { "epoch": 0.76, "grad_norm": 0.8033604870316632, "learning_rate": 2.826155871962227e-06, "loss": 0.5914, "step": 3961 }, { "epoch": 0.76, "grad_norm": 0.9457830046823068, "learning_rate": 2.8218163741650415e-06, "loss": 0.9021, "step": 3962 }, { "epoch": 0.76, "grad_norm": 1.021207415185406, "learning_rate": 2.817479663185898e-06, "loss": 0.7825, "step": 3963 }, { "epoch": 0.76, "grad_norm": 1.0006655656529508, "learning_rate": 2.813145740708445e-06, "loss": 0.5688, "step": 3964 }, { "epoch": 0.76, "grad_norm": 0.9548360509516006, "learning_rate": 2.808814608415271e-06, "loss": 0.8601, "step": 3965 }, { "epoch": 0.76, "grad_norm": 1.3801717435437233, "learning_rate": 2.8044862679878605e-06, "loss": 0.8542, "step": 3966 }, { "epoch": 0.76, "grad_norm": 1.063269731675039, "learning_rate": 2.800160721106633e-06, "loss": 0.8462, "step": 3967 }, { "epoch": 0.76, "grad_norm": 0.8957402284946041, "learning_rate": 2.7958379694509108e-06, "loss": 0.589, "step": 3968 }, { "epoch": 0.76, "grad_norm": 1.0857993811439361, "learning_rate": 2.791518014698935e-06, "loss": 0.8364, "step": 3969 }, { "epoch": 0.76, "grad_norm": 1.013702996875052, "learning_rate": 2.787200858527862e-06, "loss": 0.8398, "step": 3970 }, { "epoch": 0.76, "grad_norm": 1.2826284376562724, "learning_rate": 2.7828865026137584e-06, "loss": 0.9241, "step": 3971 }, { "epoch": 0.76, "grad_norm": 1.0593741818819782, "learning_rate": 2.7785749486316085e-06, "loss": 0.8127, "step": 3972 }, { "epoch": 0.76, "grad_norm": 1.0385151076432129, "learning_rate": 2.774266198255303e-06, "loss": 0.873, "step": 3973 }, { "epoch": 0.76, "grad_norm": 1.2097905530107265, "learning_rate": 2.7699602531576496e-06, "loss": 0.8418, "step": 3974 }, { "epoch": 0.76, "grad_norm": 1.0350912020821617, "learning_rate": 2.765657115010364e-06, "loss": 0.8384, "step": 3975 }, { "epoch": 0.76, "grad_norm": 1.0386253114802688, "learning_rate": 2.7613567854840685e-06, "loss": 0.842, "step": 3976 }, { "epoch": 0.77, "grad_norm": 1.0308473823401956, "learning_rate": 2.7570592662483086e-06, "loss": 0.8364, "step": 3977 }, { "epoch": 0.77, "grad_norm": 0.9697125554873915, "learning_rate": 2.752764558971517e-06, "loss": 0.8625, "step": 3978 }, { "epoch": 0.77, "grad_norm": 1.2038968574317201, "learning_rate": 2.748472665321056e-06, "loss": 0.8789, "step": 3979 }, { "epoch": 0.77, "grad_norm": 1.0602079656991448, "learning_rate": 2.744183586963185e-06, "loss": 0.8149, "step": 3980 }, { "epoch": 0.77, "grad_norm": 0.953461182482485, "learning_rate": 2.739897325563069e-06, "loss": 0.7537, "step": 3981 }, { "epoch": 0.77, "grad_norm": 1.059795319270889, "learning_rate": 2.7356138827847856e-06, "loss": 0.8674, "step": 3982 }, { "epoch": 0.77, "grad_norm": 1.0547889396884642, "learning_rate": 2.731333260291311e-06, "loss": 0.8535, "step": 3983 }, { "epoch": 0.77, "grad_norm": 0.993432219888355, "learning_rate": 2.7270554597445343e-06, "loss": 0.8524, "step": 3984 }, { "epoch": 0.77, "grad_norm": 1.123521543305948, "learning_rate": 2.7227804828052384e-06, "loss": 0.8523, "step": 3985 }, { "epoch": 0.77, "grad_norm": 1.0992002134600423, "learning_rate": 2.7185083311331283e-06, "loss": 0.9082, "step": 3986 }, { "epoch": 0.77, "grad_norm": 1.04855433312216, "learning_rate": 2.7142390063867896e-06, "loss": 0.8945, "step": 3987 }, { "epoch": 0.77, "grad_norm": 1.026639611946602, "learning_rate": 2.709972510223725e-06, "loss": 0.8796, "step": 3988 }, { "epoch": 0.77, "grad_norm": 1.0491590246501987, "learning_rate": 2.7057088443003343e-06, "loss": 0.8435, "step": 3989 }, { "epoch": 0.77, "grad_norm": 1.1465855621625973, "learning_rate": 2.7014480102719174e-06, "loss": 0.8184, "step": 3990 }, { "epoch": 0.77, "grad_norm": 1.0607064038894205, "learning_rate": 2.697190009792685e-06, "loss": 0.8572, "step": 3991 }, { "epoch": 0.77, "grad_norm": 1.0034820396962583, "learning_rate": 2.692934844515729e-06, "loss": 0.79, "step": 3992 }, { "epoch": 0.77, "grad_norm": 1.0856373017363683, "learning_rate": 2.6886825160930587e-06, "loss": 0.8164, "step": 3993 }, { "epoch": 0.77, "grad_norm": 1.0332836836775836, "learning_rate": 2.6844330261755715e-06, "loss": 0.8062, "step": 3994 }, { "epoch": 0.77, "grad_norm": 1.008632169143404, "learning_rate": 2.6801863764130653e-06, "loss": 0.8481, "step": 3995 }, { "epoch": 0.77, "grad_norm": 1.118793196450261, "learning_rate": 2.675942568454236e-06, "loss": 0.8218, "step": 3996 }, { "epoch": 0.77, "grad_norm": 1.022227441209795, "learning_rate": 2.671701603946678e-06, "loss": 0.8242, "step": 3997 }, { "epoch": 0.77, "grad_norm": 1.054945714345085, "learning_rate": 2.667463484536876e-06, "loss": 0.8589, "step": 3998 }, { "epoch": 0.77, "grad_norm": 1.2732664997967622, "learning_rate": 2.6632282118702147e-06, "loss": 0.8789, "step": 3999 }, { "epoch": 0.77, "grad_norm": 1.0202087634944177, "learning_rate": 2.65899578759098e-06, "loss": 0.8059, "step": 4000 }, { "epoch": 0.77, "grad_norm": 1.0970653285174297, "learning_rate": 2.654766213342335e-06, "loss": 0.845, "step": 4001 }, { "epoch": 0.77, "grad_norm": 1.083366467194331, "learning_rate": 2.650539490766346e-06, "loss": 0.842, "step": 4002 }, { "epoch": 0.77, "grad_norm": 0.8160341315387323, "learning_rate": 2.646315621503983e-06, "loss": 0.6185, "step": 4003 }, { "epoch": 0.77, "grad_norm": 1.0351134352106948, "learning_rate": 2.642094607195085e-06, "loss": 0.8179, "step": 4004 }, { "epoch": 0.77, "grad_norm": 1.0932757471282624, "learning_rate": 2.6378764494784027e-06, "loss": 0.8772, "step": 4005 }, { "epoch": 0.77, "grad_norm": 0.9661495819789166, "learning_rate": 2.633661149991569e-06, "loss": 0.8398, "step": 4006 }, { "epoch": 0.77, "grad_norm": 1.0695269087528485, "learning_rate": 2.6294487103711064e-06, "loss": 0.8594, "step": 4007 }, { "epoch": 0.77, "grad_norm": 1.0507689353644922, "learning_rate": 2.6252391322524297e-06, "loss": 0.8083, "step": 4008 }, { "epoch": 0.77, "grad_norm": 1.093252805969109, "learning_rate": 2.6210324172698432e-06, "loss": 0.804, "step": 4009 }, { "epoch": 0.77, "grad_norm": 1.1778284378509323, "learning_rate": 2.6168285670565374e-06, "loss": 0.8304, "step": 4010 }, { "epoch": 0.77, "grad_norm": 0.9904047842417377, "learning_rate": 2.6126275832445892e-06, "loss": 0.8315, "step": 4011 }, { "epoch": 0.77, "grad_norm": 0.8360793702728343, "learning_rate": 2.6084294674649734e-06, "loss": 0.6252, "step": 4012 }, { "epoch": 0.77, "grad_norm": 0.8386412036934728, "learning_rate": 2.6042342213475346e-06, "loss": 0.5867, "step": 4013 }, { "epoch": 0.77, "grad_norm": 1.0067520095058653, "learning_rate": 2.6000418465210143e-06, "loss": 0.8636, "step": 4014 }, { "epoch": 0.77, "grad_norm": 1.1060791941828911, "learning_rate": 2.595852344613038e-06, "loss": 0.8491, "step": 4015 }, { "epoch": 0.77, "grad_norm": 0.9099637168658424, "learning_rate": 2.5916657172501103e-06, "loss": 0.8657, "step": 4016 }, { "epoch": 0.77, "grad_norm": 1.0992327217821858, "learning_rate": 2.587481966057633e-06, "loss": 0.8628, "step": 4017 }, { "epoch": 0.77, "grad_norm": 1.0689405061788695, "learning_rate": 2.583301092659872e-06, "loss": 0.877, "step": 4018 }, { "epoch": 0.77, "grad_norm": 1.0059170050222286, "learning_rate": 2.5791230986799944e-06, "loss": 0.8013, "step": 4019 }, { "epoch": 0.77, "grad_norm": 0.9914089162544939, "learning_rate": 2.5749479857400383e-06, "loss": 0.8284, "step": 4020 }, { "epoch": 0.77, "grad_norm": 1.03917257565746, "learning_rate": 2.5707757554609247e-06, "loss": 0.8352, "step": 4021 }, { "epoch": 0.77, "grad_norm": 0.9387910425275553, "learning_rate": 2.56660640946246e-06, "loss": 0.8862, "step": 4022 }, { "epoch": 0.77, "grad_norm": 1.0894190644885924, "learning_rate": 2.5624399493633257e-06, "loss": 0.8422, "step": 4023 }, { "epoch": 0.77, "grad_norm": 0.8964908764277224, "learning_rate": 2.558276376781086e-06, "loss": 0.8069, "step": 4024 }, { "epoch": 0.77, "grad_norm": 1.1196886633935612, "learning_rate": 2.55411569333218e-06, "loss": 0.8945, "step": 4025 }, { "epoch": 0.77, "grad_norm": 1.055573670970789, "learning_rate": 2.5499579006319365e-06, "loss": 0.844, "step": 4026 }, { "epoch": 0.77, "grad_norm": 1.0396449701275392, "learning_rate": 2.5458030002945457e-06, "loss": 0.856, "step": 4027 }, { "epoch": 0.77, "grad_norm": 1.0091408356717806, "learning_rate": 2.5416509939330836e-06, "loss": 0.842, "step": 4028 }, { "epoch": 0.78, "grad_norm": 1.0213744567534795, "learning_rate": 2.537501883159509e-06, "loss": 0.8381, "step": 4029 }, { "epoch": 0.78, "grad_norm": 0.8166204782034164, "learning_rate": 2.5333556695846384e-06, "loss": 0.5785, "step": 4030 }, { "epoch": 0.78, "grad_norm": 1.105330869328853, "learning_rate": 2.5292123548181847e-06, "loss": 0.8589, "step": 4031 }, { "epoch": 0.78, "grad_norm": 0.9012697804980028, "learning_rate": 2.525071940468722e-06, "loss": 0.6038, "step": 4032 }, { "epoch": 0.78, "grad_norm": 1.053205844345286, "learning_rate": 2.520934428143701e-06, "loss": 0.8979, "step": 4033 }, { "epoch": 0.78, "grad_norm": 1.040760029929526, "learning_rate": 2.5167998194494468e-06, "loss": 0.8655, "step": 4034 }, { "epoch": 0.78, "grad_norm": 1.0304225944734202, "learning_rate": 2.5126681159911558e-06, "loss": 0.8091, "step": 4035 }, { "epoch": 0.78, "grad_norm": 1.0166026456893076, "learning_rate": 2.5085393193729e-06, "loss": 0.8174, "step": 4036 }, { "epoch": 0.78, "grad_norm": 0.963611704921734, "learning_rate": 2.5044134311976156e-06, "loss": 0.8174, "step": 4037 }, { "epoch": 0.78, "grad_norm": 1.0616285209353846, "learning_rate": 2.5002904530671236e-06, "loss": 0.8141, "step": 4038 }, { "epoch": 0.78, "grad_norm": 1.0398756600683114, "learning_rate": 2.4961703865820974e-06, "loss": 0.9009, "step": 4039 }, { "epoch": 0.78, "grad_norm": 0.8298193445454675, "learning_rate": 2.492053233342091e-06, "loss": 0.5685, "step": 4040 }, { "epoch": 0.78, "grad_norm": 0.9193286198946197, "learning_rate": 2.487938994945527e-06, "loss": 0.5609, "step": 4041 }, { "epoch": 0.78, "grad_norm": 1.0449141094329197, "learning_rate": 2.4838276729896884e-06, "loss": 0.8376, "step": 4042 }, { "epoch": 0.78, "grad_norm": 1.0163813653930034, "learning_rate": 2.479719269070743e-06, "loss": 0.8298, "step": 4043 }, { "epoch": 0.78, "grad_norm": 0.7633468901846522, "learning_rate": 2.4756137847837025e-06, "loss": 0.575, "step": 4044 }, { "epoch": 0.78, "grad_norm": 1.1508419539127634, "learning_rate": 2.4715112217224657e-06, "loss": 0.8772, "step": 4045 }, { "epoch": 0.78, "grad_norm": 1.0175529838849917, "learning_rate": 2.467411581479786e-06, "loss": 0.8223, "step": 4046 }, { "epoch": 0.78, "grad_norm": 0.8173974377253461, "learning_rate": 2.463314865647286e-06, "loss": 0.6162, "step": 4047 }, { "epoch": 0.78, "grad_norm": 1.0504812442500935, "learning_rate": 2.45922107581545e-06, "loss": 0.8809, "step": 4048 }, { "epoch": 0.78, "grad_norm": 0.8955176539072707, "learning_rate": 2.4551302135736287e-06, "loss": 0.7791, "step": 4049 }, { "epoch": 0.78, "grad_norm": 1.1663461015977337, "learning_rate": 2.4510422805100366e-06, "loss": 0.8284, "step": 4050 }, { "epoch": 0.78, "grad_norm": 1.1197345314078335, "learning_rate": 2.446957278211746e-06, "loss": 0.859, "step": 4051 }, { "epoch": 0.78, "grad_norm": 1.0048001112146165, "learning_rate": 2.4428752082647044e-06, "loss": 0.9104, "step": 4052 }, { "epoch": 0.78, "grad_norm": 1.229263464292121, "learning_rate": 2.438796072253704e-06, "loss": 0.8716, "step": 4053 }, { "epoch": 0.78, "grad_norm": 0.9870249548153165, "learning_rate": 2.4347198717624054e-06, "loss": 0.8887, "step": 4054 }, { "epoch": 0.78, "grad_norm": 1.2023370487926153, "learning_rate": 2.4306466083733392e-06, "loss": 0.6147, "step": 4055 }, { "epoch": 0.78, "grad_norm": 0.9538515113704077, "learning_rate": 2.426576283667873e-06, "loss": 0.5824, "step": 4056 }, { "epoch": 0.78, "grad_norm": 1.1109045766476844, "learning_rate": 2.422508899226258e-06, "loss": 0.8174, "step": 4057 }, { "epoch": 0.78, "grad_norm": 1.095393124669287, "learning_rate": 2.418444456627589e-06, "loss": 0.833, "step": 4058 }, { "epoch": 0.78, "grad_norm": 0.8734721516351152, "learning_rate": 2.4143829574498224e-06, "loss": 0.5623, "step": 4059 }, { "epoch": 0.78, "grad_norm": 1.0814025919125094, "learning_rate": 2.4103244032697717e-06, "loss": 0.8752, "step": 4060 }, { "epoch": 0.78, "grad_norm": 0.956377851275774, "learning_rate": 2.406268795663108e-06, "loss": 0.8845, "step": 4061 }, { "epoch": 0.78, "grad_norm": 1.152711786884549, "learning_rate": 2.4022161362043574e-06, "loss": 0.8173, "step": 4062 }, { "epoch": 0.78, "grad_norm": 1.0233144003603434, "learning_rate": 2.3981664264669025e-06, "loss": 0.8274, "step": 4063 }, { "epoch": 0.78, "grad_norm": 0.8111256893964895, "learning_rate": 2.3941196680229794e-06, "loss": 0.6268, "step": 4064 }, { "epoch": 0.78, "grad_norm": 1.0461829534905067, "learning_rate": 2.3900758624436772e-06, "loss": 0.8208, "step": 4065 }, { "epoch": 0.78, "grad_norm": 0.9430720877103463, "learning_rate": 2.3860350112989473e-06, "loss": 0.8286, "step": 4066 }, { "epoch": 0.78, "grad_norm": 0.9221102504791516, "learning_rate": 2.3819971161575807e-06, "loss": 0.8376, "step": 4067 }, { "epoch": 0.78, "grad_norm": 1.1036323084793125, "learning_rate": 2.3779621785872252e-06, "loss": 0.9243, "step": 4068 }, { "epoch": 0.78, "grad_norm": 0.9945296499956016, "learning_rate": 2.3739302001543918e-06, "loss": 0.8098, "step": 4069 }, { "epoch": 0.78, "grad_norm": 1.0355899435348384, "learning_rate": 2.3699011824244234e-06, "loss": 0.8484, "step": 4070 }, { "epoch": 0.78, "grad_norm": 1.0554354686593554, "learning_rate": 2.365875126961531e-06, "loss": 0.7847, "step": 4071 }, { "epoch": 0.78, "grad_norm": 1.2924178131345567, "learning_rate": 2.3618520353287644e-06, "loss": 0.8862, "step": 4072 }, { "epoch": 0.78, "grad_norm": 0.8553180670739975, "learning_rate": 2.3578319090880263e-06, "loss": 0.5892, "step": 4073 }, { "epoch": 0.78, "grad_norm": 0.9316902002503832, "learning_rate": 2.3538147498000695e-06, "loss": 0.8251, "step": 4074 }, { "epoch": 0.78, "grad_norm": 1.078786407597208, "learning_rate": 2.349800559024492e-06, "loss": 0.8402, "step": 4075 }, { "epoch": 0.78, "grad_norm": 1.1653929062727846, "learning_rate": 2.3457893383197415e-06, "loss": 0.8735, "step": 4076 }, { "epoch": 0.78, "grad_norm": 0.9988670107795201, "learning_rate": 2.3417810892431104e-06, "loss": 0.7906, "step": 4077 }, { "epoch": 0.78, "grad_norm": 1.0309613787563099, "learning_rate": 2.3377758133507455e-06, "loss": 0.7939, "step": 4078 }, { "epoch": 0.78, "grad_norm": 0.8986169100784343, "learning_rate": 2.3337735121976247e-06, "loss": 0.5646, "step": 4079 }, { "epoch": 0.78, "grad_norm": 0.879091588850256, "learning_rate": 2.32977418733758e-06, "loss": 0.5645, "step": 4080 }, { "epoch": 0.79, "grad_norm": 0.982330795236302, "learning_rate": 2.3257778403232954e-06, "loss": 0.8792, "step": 4081 }, { "epoch": 0.79, "grad_norm": 1.0155539892433365, "learning_rate": 2.321784472706279e-06, "loss": 0.8638, "step": 4082 }, { "epoch": 0.79, "grad_norm": 1.1312713716691907, "learning_rate": 2.317794086036901e-06, "loss": 0.8262, "step": 4083 }, { "epoch": 0.79, "grad_norm": 0.9681722983959815, "learning_rate": 2.3138066818643647e-06, "loss": 0.8459, "step": 4084 }, { "epoch": 0.79, "grad_norm": 0.9541065085135477, "learning_rate": 2.3098222617367184e-06, "loss": 0.8176, "step": 4085 }, { "epoch": 0.79, "grad_norm": 1.1019346195399338, "learning_rate": 2.30584082720085e-06, "loss": 0.8375, "step": 4086 }, { "epoch": 0.79, "grad_norm": 1.0864034746858937, "learning_rate": 2.301862379802492e-06, "loss": 0.8284, "step": 4087 }, { "epoch": 0.79, "grad_norm": 0.7535235925971788, "learning_rate": 2.297886921086211e-06, "loss": 0.5599, "step": 4088 }, { "epoch": 0.79, "grad_norm": 0.9540686962866403, "learning_rate": 2.2939144525954194e-06, "loss": 0.8535, "step": 4089 }, { "epoch": 0.79, "grad_norm": 1.0197811962178873, "learning_rate": 2.2899449758723657e-06, "loss": 0.855, "step": 4090 }, { "epoch": 0.79, "grad_norm": 1.1495452954219911, "learning_rate": 2.285978492458134e-06, "loss": 0.8237, "step": 4091 }, { "epoch": 0.79, "grad_norm": 0.9465513116945755, "learning_rate": 2.282015003892659e-06, "loss": 0.8567, "step": 4092 }, { "epoch": 0.79, "grad_norm": 1.074316429227127, "learning_rate": 2.2780545117146947e-06, "loss": 0.8071, "step": 4093 }, { "epoch": 0.79, "grad_norm": 0.9437357671669818, "learning_rate": 2.2740970174618405e-06, "loss": 0.8354, "step": 4094 }, { "epoch": 0.79, "grad_norm": 0.9130974353229561, "learning_rate": 2.270142522670541e-06, "loss": 0.8274, "step": 4095 }, { "epoch": 0.79, "grad_norm": 1.0706103046107593, "learning_rate": 2.2661910288760545e-06, "loss": 0.8411, "step": 4096 }, { "epoch": 0.79, "grad_norm": 1.052972195330163, "learning_rate": 2.262242537612497e-06, "loss": 0.8428, "step": 4097 }, { "epoch": 0.79, "grad_norm": 1.0952645644280845, "learning_rate": 2.258297050412804e-06, "loss": 0.8445, "step": 4098 }, { "epoch": 0.79, "grad_norm": 1.0998264330579004, "learning_rate": 2.254354568808752e-06, "loss": 0.8735, "step": 4099 }, { "epoch": 0.79, "grad_norm": 0.9922750501978721, "learning_rate": 2.2504150943309455e-06, "loss": 0.8169, "step": 4100 }, { "epoch": 0.79, "grad_norm": 1.1744602717982302, "learning_rate": 2.246478628508827e-06, "loss": 0.9077, "step": 4101 }, { "epoch": 0.79, "grad_norm": 1.116412742983274, "learning_rate": 2.242545172870665e-06, "loss": 0.8525, "step": 4102 }, { "epoch": 0.79, "grad_norm": 0.8807717713758216, "learning_rate": 2.238614728943561e-06, "loss": 0.6021, "step": 4103 }, { "epoch": 0.79, "grad_norm": 0.9455912550695416, "learning_rate": 2.2346872982534584e-06, "loss": 0.7664, "step": 4104 }, { "epoch": 0.79, "grad_norm": 0.9725662108622044, "learning_rate": 2.2307628823251083e-06, "loss": 0.8496, "step": 4105 }, { "epoch": 0.79, "grad_norm": 0.96362907829649, "learning_rate": 2.2268414826821117e-06, "loss": 0.7947, "step": 4106 }, { "epoch": 0.79, "grad_norm": 1.0093036041709782, "learning_rate": 2.222923100846893e-06, "loss": 0.843, "step": 4107 }, { "epoch": 0.79, "grad_norm": 1.0843828813372256, "learning_rate": 2.2190077383406938e-06, "loss": 0.8596, "step": 4108 }, { "epoch": 0.79, "grad_norm": 0.8955685455585897, "learning_rate": 2.2150953966835996e-06, "loss": 0.6038, "step": 4109 }, { "epoch": 0.79, "grad_norm": 1.0083463746262302, "learning_rate": 2.211186077394516e-06, "loss": 0.8501, "step": 4110 }, { "epoch": 0.79, "grad_norm": 0.9856779918378812, "learning_rate": 2.207279781991173e-06, "loss": 0.7917, "step": 4111 }, { "epoch": 0.79, "grad_norm": 0.9303119161188632, "learning_rate": 2.2033765119901294e-06, "loss": 0.853, "step": 4112 }, { "epoch": 0.79, "grad_norm": 1.0424126725854534, "learning_rate": 2.1994762689067705e-06, "loss": 0.7959, "step": 4113 }, { "epoch": 0.79, "grad_norm": 0.8909974124774679, "learning_rate": 2.1955790542553036e-06, "loss": 0.5996, "step": 4114 }, { "epoch": 0.79, "grad_norm": 1.2019373931605277, "learning_rate": 2.1916848695487615e-06, "loss": 0.8306, "step": 4115 }, { "epoch": 0.79, "grad_norm": 0.9991339427113217, "learning_rate": 2.1877937162990015e-06, "loss": 0.8179, "step": 4116 }, { "epoch": 0.79, "grad_norm": 1.062466604493777, "learning_rate": 2.1839055960167e-06, "loss": 0.8071, "step": 4117 }, { "epoch": 0.79, "grad_norm": 1.0623889829596898, "learning_rate": 2.180020510211367e-06, "loss": 0.8823, "step": 4118 }, { "epoch": 0.79, "grad_norm": 1.035623563017349, "learning_rate": 2.1761384603913203e-06, "loss": 0.8562, "step": 4119 }, { "epoch": 0.79, "grad_norm": 0.880118707308719, "learning_rate": 2.172259448063704e-06, "loss": 0.6121, "step": 4120 }, { "epoch": 0.79, "grad_norm": 1.0660141030208463, "learning_rate": 2.1683834747344913e-06, "loss": 0.8635, "step": 4121 }, { "epoch": 0.79, "grad_norm": 1.020135978326275, "learning_rate": 2.1645105419084587e-06, "loss": 0.8352, "step": 4122 }, { "epoch": 0.79, "grad_norm": 0.9874661133952439, "learning_rate": 2.160640651089221e-06, "loss": 0.8236, "step": 4123 }, { "epoch": 0.79, "grad_norm": 0.9029216536194001, "learning_rate": 2.1567738037791998e-06, "loss": 0.5927, "step": 4124 }, { "epoch": 0.79, "grad_norm": 1.0212811844385654, "learning_rate": 2.152910001479638e-06, "loss": 0.8464, "step": 4125 }, { "epoch": 0.79, "grad_norm": 0.9802630262578252, "learning_rate": 2.1490492456905964e-06, "loss": 0.7666, "step": 4126 }, { "epoch": 0.79, "grad_norm": 1.0176943055529595, "learning_rate": 2.1451915379109546e-06, "loss": 0.8219, "step": 4127 }, { "epoch": 0.79, "grad_norm": 1.0219890962919638, "learning_rate": 2.141336879638406e-06, "loss": 0.8152, "step": 4128 }, { "epoch": 0.79, "grad_norm": 1.0878579295953605, "learning_rate": 2.1374852723694595e-06, "loss": 0.8831, "step": 4129 }, { "epoch": 0.79, "grad_norm": 1.1068911197222004, "learning_rate": 2.133636717599451e-06, "loss": 0.8085, "step": 4130 }, { "epoch": 0.79, "grad_norm": 1.0020847622152977, "learning_rate": 2.1297912168225086e-06, "loss": 0.8081, "step": 4131 }, { "epoch": 0.79, "grad_norm": 1.0425317438992099, "learning_rate": 2.1259487715316e-06, "loss": 0.8245, "step": 4132 }, { "epoch": 0.8, "grad_norm": 0.913044253076092, "learning_rate": 2.1221093832184903e-06, "loss": 0.6805, "step": 4133 }, { "epoch": 0.8, "grad_norm": 0.9154384571159588, "learning_rate": 2.118273053373757e-06, "loss": 0.8875, "step": 4134 }, { "epoch": 0.8, "grad_norm": 1.0559706882224094, "learning_rate": 2.1144397834868034e-06, "loss": 0.5951, "step": 4135 }, { "epoch": 0.8, "grad_norm": 0.9877487960947849, "learning_rate": 2.1106095750458332e-06, "loss": 0.833, "step": 4136 }, { "epoch": 0.8, "grad_norm": 1.0955996987289247, "learning_rate": 2.106782429537866e-06, "loss": 0.8464, "step": 4137 }, { "epoch": 0.8, "grad_norm": 0.8219073364757564, "learning_rate": 2.1029583484487315e-06, "loss": 0.5803, "step": 4138 }, { "epoch": 0.8, "grad_norm": 1.0767693165825893, "learning_rate": 2.0991373332630683e-06, "loss": 0.8767, "step": 4139 }, { "epoch": 0.8, "grad_norm": 1.139796004960564, "learning_rate": 2.0953193854643274e-06, "loss": 0.7611, "step": 4140 }, { "epoch": 0.8, "grad_norm": 0.9868263438072198, "learning_rate": 2.0915045065347673e-06, "loss": 0.8184, "step": 4141 }, { "epoch": 0.8, "grad_norm": 1.1423134464603437, "learning_rate": 2.0876926979554545e-06, "loss": 0.908, "step": 4142 }, { "epoch": 0.8, "grad_norm": 1.0560588418308454, "learning_rate": 2.0838839612062633e-06, "loss": 0.8132, "step": 4143 }, { "epoch": 0.8, "grad_norm": 0.9859860981531158, "learning_rate": 2.080078297765884e-06, "loss": 0.8435, "step": 4144 }, { "epoch": 0.8, "grad_norm": 1.0606623186327446, "learning_rate": 2.0762757091117937e-06, "loss": 0.8435, "step": 4145 }, { "epoch": 0.8, "grad_norm": 1.1051733831108441, "learning_rate": 2.0724761967202987e-06, "loss": 0.8674, "step": 4146 }, { "epoch": 0.8, "grad_norm": 0.9875944483043013, "learning_rate": 2.0686797620664987e-06, "loss": 0.8518, "step": 4147 }, { "epoch": 0.8, "grad_norm": 1.0471778654377744, "learning_rate": 2.0648864066242937e-06, "loss": 0.8181, "step": 4148 }, { "epoch": 0.8, "grad_norm": 0.9809599895821942, "learning_rate": 2.0610961318664013e-06, "loss": 0.8457, "step": 4149 }, { "epoch": 0.8, "grad_norm": 0.9468912972843354, "learning_rate": 2.0573089392643362e-06, "loss": 0.6293, "step": 4150 }, { "epoch": 0.8, "grad_norm": 1.2065584773398843, "learning_rate": 2.0535248302884147e-06, "loss": 0.8594, "step": 4151 }, { "epoch": 0.8, "grad_norm": 0.7571170687749533, "learning_rate": 2.0497438064077603e-06, "loss": 0.5666, "step": 4152 }, { "epoch": 0.8, "grad_norm": 1.0018759406348474, "learning_rate": 2.045965869090295e-06, "loss": 0.8787, "step": 4153 }, { "epoch": 0.8, "grad_norm": 0.987530214678898, "learning_rate": 2.0421910198027452e-06, "loss": 0.8401, "step": 4154 }, { "epoch": 0.8, "grad_norm": 0.9635734047581331, "learning_rate": 2.0384192600106335e-06, "loss": 0.8196, "step": 4155 }, { "epoch": 0.8, "grad_norm": 1.016865229104316, "learning_rate": 2.0346505911782956e-06, "loss": 0.8252, "step": 4156 }, { "epoch": 0.8, "grad_norm": 0.9693735335793646, "learning_rate": 2.0308850147688484e-06, "loss": 0.8899, "step": 4157 }, { "epoch": 0.8, "grad_norm": 1.0046925618352305, "learning_rate": 2.0271225322442255e-06, "loss": 0.8192, "step": 4158 }, { "epoch": 0.8, "grad_norm": 0.9816811775166081, "learning_rate": 2.0233631450651525e-06, "loss": 0.8591, "step": 4159 }, { "epoch": 0.8, "grad_norm": 1.0049541455484654, "learning_rate": 2.019606854691145e-06, "loss": 0.8533, "step": 4160 }, { "epoch": 0.8, "grad_norm": 1.0802884486665385, "learning_rate": 2.0158536625805325e-06, "loss": 0.8262, "step": 4161 }, { "epoch": 0.8, "grad_norm": 1.0896575354833729, "learning_rate": 2.01210357019043e-06, "loss": 0.8433, "step": 4162 }, { "epoch": 0.8, "grad_norm": 1.0736873613935758, "learning_rate": 2.008356578976752e-06, "loss": 0.8328, "step": 4163 }, { "epoch": 0.8, "grad_norm": 0.9637492756575677, "learning_rate": 2.004612690394212e-06, "loss": 0.834, "step": 4164 }, { "epoch": 0.8, "grad_norm": 1.0348655481431566, "learning_rate": 2.0008719058963144e-06, "loss": 0.8801, "step": 4165 }, { "epoch": 0.8, "grad_norm": 1.1469101024002724, "learning_rate": 1.997134226935361e-06, "loss": 0.8816, "step": 4166 }, { "epoch": 0.8, "grad_norm": 1.0152349965760346, "learning_rate": 1.9933996549624468e-06, "loss": 0.8347, "step": 4167 }, { "epoch": 0.8, "grad_norm": 1.1249791580494828, "learning_rate": 1.9896681914274616e-06, "loss": 0.8711, "step": 4168 }, { "epoch": 0.8, "grad_norm": 1.113952228725192, "learning_rate": 1.9859398377790872e-06, "loss": 0.8298, "step": 4169 }, { "epoch": 0.8, "grad_norm": 0.9779362159950689, "learning_rate": 1.982214595464804e-06, "loss": 0.8596, "step": 4170 }, { "epoch": 0.8, "grad_norm": 1.0099091031316072, "learning_rate": 1.97849246593087e-06, "loss": 0.8865, "step": 4171 }, { "epoch": 0.8, "grad_norm": 1.1970404751418997, "learning_rate": 1.9747734506223525e-06, "loss": 0.9043, "step": 4172 }, { "epoch": 0.8, "grad_norm": 1.0428369137175977, "learning_rate": 1.9710575509831008e-06, "loss": 0.885, "step": 4173 }, { "epoch": 0.8, "grad_norm": 0.958299383702586, "learning_rate": 1.967344768455747e-06, "loss": 0.8574, "step": 4174 }, { "epoch": 0.8, "grad_norm": 1.0933202804088538, "learning_rate": 1.9636351044817292e-06, "loss": 0.8845, "step": 4175 }, { "epoch": 0.8, "grad_norm": 0.7993044566855773, "learning_rate": 1.9599285605012643e-06, "loss": 0.6077, "step": 4176 }, { "epoch": 0.8, "grad_norm": 1.0014339120943352, "learning_rate": 1.9562251379533593e-06, "loss": 0.8445, "step": 4177 }, { "epoch": 0.8, "grad_norm": 1.0727984668095898, "learning_rate": 1.952524838275811e-06, "loss": 0.8499, "step": 4178 }, { "epoch": 0.8, "grad_norm": 0.9961955383128328, "learning_rate": 1.9488276629052026e-06, "loss": 0.8579, "step": 4179 }, { "epoch": 0.8, "grad_norm": 1.079169563269682, "learning_rate": 1.945133613276907e-06, "loss": 0.8745, "step": 4180 }, { "epoch": 0.8, "grad_norm": 0.9900129108677578, "learning_rate": 1.941442690825076e-06, "loss": 0.8127, "step": 4181 }, { "epoch": 0.8, "grad_norm": 1.0287372238921069, "learning_rate": 1.937754896982663e-06, "loss": 0.8555, "step": 4182 }, { "epoch": 0.8, "grad_norm": 1.0642983737499716, "learning_rate": 1.9340702331813842e-06, "loss": 0.7893, "step": 4183 }, { "epoch": 0.8, "grad_norm": 1.0786424065625573, "learning_rate": 1.9303887008517618e-06, "loss": 0.8303, "step": 4184 }, { "epoch": 0.81, "grad_norm": 0.9790688405180151, "learning_rate": 1.9267103014230935e-06, "loss": 0.8481, "step": 4185 }, { "epoch": 0.81, "grad_norm": 1.03149036553499, "learning_rate": 1.923035036323452e-06, "loss": 0.8545, "step": 4186 }, { "epoch": 0.81, "grad_norm": 1.0976528701356867, "learning_rate": 1.91936290697971e-06, "loss": 0.844, "step": 4187 }, { "epoch": 0.81, "grad_norm": 0.849475717307929, "learning_rate": 1.9156939148175125e-06, "loss": 0.5928, "step": 4188 }, { "epoch": 0.81, "grad_norm": 1.053106159948488, "learning_rate": 1.9120280612612873e-06, "loss": 0.8438, "step": 4189 }, { "epoch": 0.81, "grad_norm": 1.0524327240966571, "learning_rate": 1.9083653477342467e-06, "loss": 0.8696, "step": 4190 }, { "epoch": 0.81, "grad_norm": 0.9160949741545577, "learning_rate": 1.904705775658381e-06, "loss": 0.7957, "step": 4191 }, { "epoch": 0.81, "grad_norm": 1.0010811580113792, "learning_rate": 1.9010493464544621e-06, "loss": 0.8313, "step": 4192 }, { "epoch": 0.81, "grad_norm": 1.0749860353294012, "learning_rate": 1.8973960615420416e-06, "loss": 0.8164, "step": 4193 }, { "epoch": 0.81, "grad_norm": 0.8404651375172747, "learning_rate": 1.8937459223394517e-06, "loss": 0.5536, "step": 4194 }, { "epoch": 0.81, "grad_norm": 1.0101594680279795, "learning_rate": 1.8900989302637985e-06, "loss": 0.8748, "step": 4195 }, { "epoch": 0.81, "grad_norm": 0.7805168811400031, "learning_rate": 1.8864550867309771e-06, "loss": 0.5523, "step": 4196 }, { "epoch": 0.81, "grad_norm": 1.1748364696738156, "learning_rate": 1.8828143931556442e-06, "loss": 0.8503, "step": 4197 }, { "epoch": 0.81, "grad_norm": 1.1409175023980214, "learning_rate": 1.8791768509512487e-06, "loss": 0.8081, "step": 4198 }, { "epoch": 0.81, "grad_norm": 1.0266291829982104, "learning_rate": 1.875542461530011e-06, "loss": 0.8022, "step": 4199 }, { "epoch": 0.81, "grad_norm": 1.068738799609854, "learning_rate": 1.871911226302917e-06, "loss": 0.8687, "step": 4200 }, { "epoch": 0.81, "grad_norm": 1.0648664575357536, "learning_rate": 1.868283146679747e-06, "loss": 0.8892, "step": 4201 }, { "epoch": 0.81, "grad_norm": 0.8056270290301855, "learning_rate": 1.8646582240690414e-06, "loss": 0.567, "step": 4202 }, { "epoch": 0.81, "grad_norm": 0.8385368504155151, "learning_rate": 1.8610364598781227e-06, "loss": 0.6185, "step": 4203 }, { "epoch": 0.81, "grad_norm": 1.0632518865071545, "learning_rate": 1.8574178555130818e-06, "loss": 0.8357, "step": 4204 }, { "epoch": 0.81, "grad_norm": 0.9897703037020399, "learning_rate": 1.8538024123787868e-06, "loss": 0.8433, "step": 4205 }, { "epoch": 0.81, "grad_norm": 1.1907937058155358, "learning_rate": 1.8501901318788773e-06, "loss": 0.8523, "step": 4206 }, { "epoch": 0.81, "grad_norm": 0.8886856416668227, "learning_rate": 1.8465810154157626e-06, "loss": 0.8723, "step": 4207 }, { "epoch": 0.81, "grad_norm": 1.0277457838728326, "learning_rate": 1.8429750643906331e-06, "loss": 0.863, "step": 4208 }, { "epoch": 0.81, "grad_norm": 1.0503821086875227, "learning_rate": 1.8393722802034331e-06, "loss": 0.8145, "step": 4209 }, { "epoch": 0.81, "grad_norm": 1.1145780096602826, "learning_rate": 1.835772664252895e-06, "loss": 0.8494, "step": 4210 }, { "epoch": 0.81, "grad_norm": 1.0069282738685015, "learning_rate": 1.832176217936511e-06, "loss": 0.8389, "step": 4211 }, { "epoch": 0.81, "grad_norm": 0.9694439896713707, "learning_rate": 1.8285829426505453e-06, "loss": 0.8469, "step": 4212 }, { "epoch": 0.81, "grad_norm": 0.9946309431642286, "learning_rate": 1.8249928397900351e-06, "loss": 0.8962, "step": 4213 }, { "epoch": 0.81, "grad_norm": 1.095559126015527, "learning_rate": 1.8214059107487726e-06, "loss": 0.8359, "step": 4214 }, { "epoch": 0.81, "grad_norm": 0.9735095841451711, "learning_rate": 1.8178221569193343e-06, "loss": 0.8472, "step": 4215 }, { "epoch": 0.81, "grad_norm": 1.03974772792031, "learning_rate": 1.8142415796930568e-06, "loss": 0.8302, "step": 4216 }, { "epoch": 0.81, "grad_norm": 1.0446101369827192, "learning_rate": 1.8106641804600411e-06, "loss": 0.8726, "step": 4217 }, { "epoch": 0.81, "grad_norm": 1.0605415721492022, "learning_rate": 1.8070899606091586e-06, "loss": 0.9006, "step": 4218 }, { "epoch": 0.81, "grad_norm": 1.1495727192157676, "learning_rate": 1.8035189215280423e-06, "loss": 0.8271, "step": 4219 }, { "epoch": 0.81, "grad_norm": 1.056002925747551, "learning_rate": 1.799951064603095e-06, "loss": 0.9053, "step": 4220 }, { "epoch": 0.81, "grad_norm": 0.9415988223093956, "learning_rate": 1.7963863912194768e-06, "loss": 0.7294, "step": 4221 }, { "epoch": 0.81, "grad_norm": 1.0526263286829132, "learning_rate": 1.7928249027611255e-06, "loss": 0.822, "step": 4222 }, { "epoch": 0.81, "grad_norm": 0.9734183919984495, "learning_rate": 1.789266600610724e-06, "loss": 0.8491, "step": 4223 }, { "epoch": 0.81, "grad_norm": 1.0443684890700777, "learning_rate": 1.7857114861497337e-06, "loss": 0.8647, "step": 4224 }, { "epoch": 0.81, "grad_norm": 0.8973179507162738, "learning_rate": 1.782159560758373e-06, "loss": 0.5912, "step": 4225 }, { "epoch": 0.81, "grad_norm": 1.0796220361403468, "learning_rate": 1.7786108258156154e-06, "loss": 0.7849, "step": 4226 }, { "epoch": 0.81, "grad_norm": 0.9922571969708678, "learning_rate": 1.7750652826992077e-06, "loss": 0.824, "step": 4227 }, { "epoch": 0.81, "grad_norm": 1.1440914144202359, "learning_rate": 1.7715229327856498e-06, "loss": 0.8992, "step": 4228 }, { "epoch": 0.81, "grad_norm": 1.1599685371787147, "learning_rate": 1.7679837774502052e-06, "loss": 0.8562, "step": 4229 }, { "epoch": 0.81, "grad_norm": 1.0824324934626837, "learning_rate": 1.7644478180668945e-06, "loss": 0.7559, "step": 4230 }, { "epoch": 0.81, "grad_norm": 1.07961448803486, "learning_rate": 1.7609150560084986e-06, "loss": 0.8127, "step": 4231 }, { "epoch": 0.81, "grad_norm": 1.0466976384721511, "learning_rate": 1.7573854926465582e-06, "loss": 0.8718, "step": 4232 }, { "epoch": 0.81, "grad_norm": 0.9816177544052859, "learning_rate": 1.7538591293513685e-06, "loss": 0.8123, "step": 4233 }, { "epoch": 0.81, "grad_norm": 1.0800469647943183, "learning_rate": 1.7503359674919929e-06, "loss": 0.8628, "step": 4234 }, { "epoch": 0.81, "grad_norm": 1.3050094006799726, "learning_rate": 1.746816008436234e-06, "loss": 0.8196, "step": 4235 }, { "epoch": 0.81, "grad_norm": 0.9522105102601874, "learning_rate": 1.7432992535506687e-06, "loss": 0.8689, "step": 4236 }, { "epoch": 0.82, "grad_norm": 1.0151482211484713, "learning_rate": 1.7397857042006194e-06, "loss": 0.8232, "step": 4237 }, { "epoch": 0.82, "grad_norm": 0.9094544868933789, "learning_rate": 1.736275361750167e-06, "loss": 0.8008, "step": 4238 }, { "epoch": 0.82, "grad_norm": 0.9661114117072068, "learning_rate": 1.7327682275621506e-06, "loss": 0.8672, "step": 4239 }, { "epoch": 0.82, "grad_norm": 1.023423006186248, "learning_rate": 1.7292643029981525e-06, "loss": 0.8264, "step": 4240 }, { "epoch": 0.82, "grad_norm": 1.0366945505731537, "learning_rate": 1.7257635894185232e-06, "loss": 0.8262, "step": 4241 }, { "epoch": 0.82, "grad_norm": 1.038917686250217, "learning_rate": 1.7222660881823594e-06, "loss": 0.863, "step": 4242 }, { "epoch": 0.82, "grad_norm": 1.0669218045683428, "learning_rate": 1.7187718006475117e-06, "loss": 0.8567, "step": 4243 }, { "epoch": 0.82, "grad_norm": 1.1071875645370408, "learning_rate": 1.7152807281705809e-06, "loss": 0.8801, "step": 4244 }, { "epoch": 0.82, "grad_norm": 0.9866590501827521, "learning_rate": 1.7117928721069233e-06, "loss": 0.8608, "step": 4245 }, { "epoch": 0.82, "grad_norm": 1.1713046456207288, "learning_rate": 1.708308233810644e-06, "loss": 0.8418, "step": 4246 }, { "epoch": 0.82, "grad_norm": 1.196966446492938, "learning_rate": 1.704826814634597e-06, "loss": 0.8162, "step": 4247 }, { "epoch": 0.82, "grad_norm": 1.1325745268906853, "learning_rate": 1.701348615930397e-06, "loss": 0.8469, "step": 4248 }, { "epoch": 0.82, "grad_norm": 1.1277643575917546, "learning_rate": 1.6978736390483896e-06, "loss": 0.8914, "step": 4249 }, { "epoch": 0.82, "grad_norm": 1.1494463745492094, "learning_rate": 1.6944018853376898e-06, "loss": 0.8615, "step": 4250 }, { "epoch": 0.82, "grad_norm": 1.0457906539482564, "learning_rate": 1.6909333561461471e-06, "loss": 0.8787, "step": 4251 }, { "epoch": 0.82, "grad_norm": 0.7805456787947739, "learning_rate": 1.6874680528203657e-06, "loss": 0.5614, "step": 4252 }, { "epoch": 0.82, "grad_norm": 1.072558996384917, "learning_rate": 1.6840059767056949e-06, "loss": 0.8052, "step": 4253 }, { "epoch": 0.82, "grad_norm": 0.9795240938280378, "learning_rate": 1.6805471291462316e-06, "loss": 0.8552, "step": 4254 }, { "epoch": 0.82, "grad_norm": 0.9539593547421171, "learning_rate": 1.6770915114848197e-06, "loss": 0.7866, "step": 4255 }, { "epoch": 0.82, "grad_norm": 1.0787000480919313, "learning_rate": 1.67363912506305e-06, "loss": 0.8408, "step": 4256 }, { "epoch": 0.82, "grad_norm": 1.0619414402739076, "learning_rate": 1.6701899712212565e-06, "loss": 0.8535, "step": 4257 }, { "epoch": 0.82, "grad_norm": 1.1042917758667394, "learning_rate": 1.66674405129852e-06, "loss": 0.8481, "step": 4258 }, { "epoch": 0.82, "grad_norm": 0.9616474862978895, "learning_rate": 1.6633013666326636e-06, "loss": 0.78, "step": 4259 }, { "epoch": 0.82, "grad_norm": 0.8737414128803515, "learning_rate": 1.6598619185602616e-06, "loss": 0.5674, "step": 4260 }, { "epoch": 0.82, "grad_norm": 1.074159076507085, "learning_rate": 1.656425708416617e-06, "loss": 0.7573, "step": 4261 }, { "epoch": 0.82, "grad_norm": 0.9869726954787326, "learning_rate": 1.6529927375357957e-06, "loss": 0.8254, "step": 4262 }, { "epoch": 0.82, "grad_norm": 0.9296567742996426, "learning_rate": 1.6495630072505841e-06, "loss": 0.79, "step": 4263 }, { "epoch": 0.82, "grad_norm": 0.999269899630745, "learning_rate": 1.6461365188925304e-06, "loss": 0.6061, "step": 4264 }, { "epoch": 0.82, "grad_norm": 1.080434126800861, "learning_rate": 1.642713273791914e-06, "loss": 0.9282, "step": 4265 }, { "epoch": 0.82, "grad_norm": 0.9897976957361995, "learning_rate": 1.6392932732777489e-06, "loss": 0.8198, "step": 4266 }, { "epoch": 0.82, "grad_norm": 0.9259643948201512, "learning_rate": 1.6358765186778057e-06, "loss": 0.823, "step": 4267 }, { "epoch": 0.82, "grad_norm": 1.066472730031597, "learning_rate": 1.6324630113185835e-06, "loss": 0.8123, "step": 4268 }, { "epoch": 0.82, "grad_norm": 0.7971814335701493, "learning_rate": 1.629052752525323e-06, "loss": 0.5787, "step": 4269 }, { "epoch": 0.82, "grad_norm": 1.1244639565829981, "learning_rate": 1.625645743622003e-06, "loss": 0.853, "step": 4270 }, { "epoch": 0.82, "grad_norm": 1.1271186928880523, "learning_rate": 1.6222419859313443e-06, "loss": 0.876, "step": 4271 }, { "epoch": 0.82, "grad_norm": 1.30831883001524, "learning_rate": 1.6188414807747999e-06, "loss": 0.8767, "step": 4272 }, { "epoch": 0.82, "grad_norm": 1.0141688591221403, "learning_rate": 1.6154442294725636e-06, "loss": 0.8682, "step": 4273 }, { "epoch": 0.82, "grad_norm": 1.025045631137315, "learning_rate": 1.6120502333435695e-06, "loss": 0.8838, "step": 4274 }, { "epoch": 0.82, "grad_norm": 1.3787542195503597, "learning_rate": 1.6086594937054767e-06, "loss": 0.8616, "step": 4275 }, { "epoch": 0.82, "grad_norm": 0.9977664945595552, "learning_rate": 1.6052720118746923e-06, "loss": 0.8164, "step": 4276 }, { "epoch": 0.82, "grad_norm": 0.9869981323075913, "learning_rate": 1.6018877891663521e-06, "loss": 0.8652, "step": 4277 }, { "epoch": 0.82, "grad_norm": 1.1017441671635848, "learning_rate": 1.5985068268943283e-06, "loss": 0.8975, "step": 4278 }, { "epoch": 0.82, "grad_norm": 1.0751926731099744, "learning_rate": 1.5951291263712255e-06, "loss": 0.8123, "step": 4279 }, { "epoch": 0.82, "grad_norm": 0.8549024823021709, "learning_rate": 1.5917546889083834e-06, "loss": 0.5912, "step": 4280 }, { "epoch": 0.82, "grad_norm": 1.0555055233031028, "learning_rate": 1.5883835158158767e-06, "loss": 0.916, "step": 4281 }, { "epoch": 0.82, "grad_norm": 1.0585612475941066, "learning_rate": 1.5850156084025091e-06, "loss": 0.8459, "step": 4282 }, { "epoch": 0.82, "grad_norm": 1.042490621646871, "learning_rate": 1.5816509679758185e-06, "loss": 0.8129, "step": 4283 }, { "epoch": 0.82, "grad_norm": 1.0679945873242729, "learning_rate": 1.578289595842074e-06, "loss": 0.8463, "step": 4284 }, { "epoch": 0.82, "grad_norm": 0.9752206147004001, "learning_rate": 1.5749314933062754e-06, "loss": 0.8059, "step": 4285 }, { "epoch": 0.82, "grad_norm": 1.0814985627816758, "learning_rate": 1.5715766616721584e-06, "loss": 0.8821, "step": 4286 }, { "epoch": 0.82, "grad_norm": 1.0190026175201072, "learning_rate": 1.5682251022421757e-06, "loss": 0.8281, "step": 4287 }, { "epoch": 0.82, "grad_norm": 1.0035942436764855, "learning_rate": 1.5648768163175277e-06, "loss": 0.8079, "step": 4288 }, { "epoch": 0.83, "grad_norm": 1.1392701719654454, "learning_rate": 1.5615318051981243e-06, "loss": 0.7537, "step": 4289 }, { "epoch": 0.83, "grad_norm": 1.0678501936005835, "learning_rate": 1.5581900701826226e-06, "loss": 0.8625, "step": 4290 }, { "epoch": 0.83, "grad_norm": 0.8669715257461239, "learning_rate": 1.5548516125683976e-06, "loss": 0.5829, "step": 4291 }, { "epoch": 0.83, "grad_norm": 1.0181895013531241, "learning_rate": 1.5515164336515465e-06, "loss": 0.8738, "step": 4292 }, { "epoch": 0.83, "grad_norm": 1.121254352453618, "learning_rate": 1.5481845347269077e-06, "loss": 0.835, "step": 4293 }, { "epoch": 0.83, "grad_norm": 1.137437601329896, "learning_rate": 1.5448559170880373e-06, "loss": 0.8359, "step": 4294 }, { "epoch": 0.83, "grad_norm": 0.9068401943939156, "learning_rate": 1.5415305820272198e-06, "loss": 0.635, "step": 4295 }, { "epoch": 0.83, "grad_norm": 1.2189805891298717, "learning_rate": 1.5382085308354633e-06, "loss": 0.8279, "step": 4296 }, { "epoch": 0.83, "grad_norm": 1.0466448209226011, "learning_rate": 1.534889764802503e-06, "loss": 0.8706, "step": 4297 }, { "epoch": 0.83, "grad_norm": 0.9237035659558896, "learning_rate": 1.5315742852167992e-06, "loss": 0.793, "step": 4298 }, { "epoch": 0.83, "grad_norm": 1.0040854865035502, "learning_rate": 1.5282620933655312e-06, "loss": 0.8279, "step": 4299 }, { "epoch": 0.83, "grad_norm": 1.0873245781856808, "learning_rate": 1.5249531905346138e-06, "loss": 0.9053, "step": 4300 }, { "epoch": 0.83, "grad_norm": 1.060460479433094, "learning_rate": 1.521647578008667e-06, "loss": 0.8684, "step": 4301 }, { "epoch": 0.83, "grad_norm": 0.9411899986785757, "learning_rate": 1.5183452570710522e-06, "loss": 0.8059, "step": 4302 }, { "epoch": 0.83, "grad_norm": 1.1174680956219107, "learning_rate": 1.5150462290038392e-06, "loss": 0.8662, "step": 4303 }, { "epoch": 0.83, "grad_norm": 1.065282458553254, "learning_rate": 1.511750495087827e-06, "loss": 0.856, "step": 4304 }, { "epoch": 0.83, "grad_norm": 0.9697712608717353, "learning_rate": 1.5084580566025309e-06, "loss": 0.8865, "step": 4305 }, { "epoch": 0.83, "grad_norm": 1.0564659102230807, "learning_rate": 1.5051689148261895e-06, "loss": 0.8447, "step": 4306 }, { "epoch": 0.83, "grad_norm": 1.0595794923446216, "learning_rate": 1.5018830710357612e-06, "loss": 0.8337, "step": 4307 }, { "epoch": 0.83, "grad_norm": 0.8171035243596854, "learning_rate": 1.4986005265069204e-06, "loss": 0.5862, "step": 4308 }, { "epoch": 0.83, "grad_norm": 1.0507009126085183, "learning_rate": 1.4953212825140728e-06, "loss": 0.8789, "step": 4309 }, { "epoch": 0.83, "grad_norm": 1.1374295395969805, "learning_rate": 1.4920453403303249e-06, "loss": 0.8467, "step": 4310 }, { "epoch": 0.83, "grad_norm": 1.093924685454692, "learning_rate": 1.4887727012275112e-06, "loss": 0.8372, "step": 4311 }, { "epoch": 0.83, "grad_norm": 1.0098179404976584, "learning_rate": 1.4855033664761898e-06, "loss": 0.7543, "step": 4312 }, { "epoch": 0.83, "grad_norm": 0.8051262684011246, "learning_rate": 1.48223733734562e-06, "loss": 0.5964, "step": 4313 }, { "epoch": 0.83, "grad_norm": 0.9773492546664078, "learning_rate": 1.4789746151037942e-06, "loss": 0.823, "step": 4314 }, { "epoch": 0.83, "grad_norm": 0.9760441140937128, "learning_rate": 1.475715201017407e-06, "loss": 0.8401, "step": 4315 }, { "epoch": 0.83, "grad_norm": 1.1925400834087154, "learning_rate": 1.4724590963518803e-06, "loss": 0.8701, "step": 4316 }, { "epoch": 0.83, "grad_norm": 1.045169162455907, "learning_rate": 1.4692063023713444e-06, "loss": 0.8518, "step": 4317 }, { "epoch": 0.83, "grad_norm": 0.8956927613689423, "learning_rate": 1.4659568203386464e-06, "loss": 0.7567, "step": 4318 }, { "epoch": 0.83, "grad_norm": 0.879869718036107, "learning_rate": 1.4627106515153456e-06, "loss": 0.7822, "step": 4319 }, { "epoch": 0.83, "grad_norm": 0.7831891235059644, "learning_rate": 1.4594677971617178e-06, "loss": 0.6002, "step": 4320 }, { "epoch": 0.83, "grad_norm": 0.9831643675957843, "learning_rate": 1.4562282585367493e-06, "loss": 0.8331, "step": 4321 }, { "epoch": 0.83, "grad_norm": 1.0178009070079002, "learning_rate": 1.452992036898142e-06, "loss": 0.8386, "step": 4322 }, { "epoch": 0.83, "grad_norm": 0.9745241208619998, "learning_rate": 1.4497591335023087e-06, "loss": 0.8435, "step": 4323 }, { "epoch": 0.83, "grad_norm": 0.9716563141709723, "learning_rate": 1.446529549604373e-06, "loss": 0.897, "step": 4324 }, { "epoch": 0.83, "grad_norm": 1.0575593923106408, "learning_rate": 1.4433032864581687e-06, "loss": 0.8789, "step": 4325 }, { "epoch": 0.83, "grad_norm": 0.9854482044770078, "learning_rate": 1.4400803453162482e-06, "loss": 0.854, "step": 4326 }, { "epoch": 0.83, "grad_norm": 1.0066020972219645, "learning_rate": 1.4368607274298596e-06, "loss": 0.8792, "step": 4327 }, { "epoch": 0.83, "grad_norm": 1.0124984906768146, "learning_rate": 1.4336444340489775e-06, "loss": 0.9126, "step": 4328 }, { "epoch": 0.83, "grad_norm": 1.1366812608254004, "learning_rate": 1.430431466422273e-06, "loss": 0.8457, "step": 4329 }, { "epoch": 0.83, "grad_norm": 1.149651359088946, "learning_rate": 1.4272218257971327e-06, "loss": 0.875, "step": 4330 }, { "epoch": 0.83, "grad_norm": 0.8904487113579268, "learning_rate": 1.4240155134196499e-06, "loss": 0.6089, "step": 4331 }, { "epoch": 0.83, "grad_norm": 0.9856742003645197, "learning_rate": 1.4208125305346232e-06, "loss": 0.8765, "step": 4332 }, { "epoch": 0.83, "grad_norm": 0.99203982507336, "learning_rate": 1.4176128783855636e-06, "loss": 0.8357, "step": 4333 }, { "epoch": 0.83, "grad_norm": 0.9318052859613174, "learning_rate": 1.4144165582146819e-06, "loss": 0.8052, "step": 4334 }, { "epoch": 0.83, "grad_norm": 0.9977392181572858, "learning_rate": 1.4112235712629063e-06, "loss": 0.8462, "step": 4335 }, { "epoch": 0.83, "grad_norm": 0.9427907053569461, "learning_rate": 1.40803391876986e-06, "loss": 0.8639, "step": 4336 }, { "epoch": 0.83, "grad_norm": 1.1365066249283686, "learning_rate": 1.4048476019738756e-06, "loss": 0.8315, "step": 4337 }, { "epoch": 0.83, "grad_norm": 1.0825645016305594, "learning_rate": 1.4016646221119912e-06, "loss": 0.8496, "step": 4338 }, { "epoch": 0.83, "grad_norm": 1.0770484371230697, "learning_rate": 1.3984849804199485e-06, "loss": 0.8479, "step": 4339 }, { "epoch": 0.83, "grad_norm": 1.0286216088402174, "learning_rate": 1.395308678132199e-06, "loss": 0.7789, "step": 4340 }, { "epoch": 0.84, "grad_norm": 1.1016154280757395, "learning_rate": 1.392135716481885e-06, "loss": 0.8794, "step": 4341 }, { "epoch": 0.84, "grad_norm": 1.0204005721203713, "learning_rate": 1.3889660967008656e-06, "loss": 0.8345, "step": 4342 }, { "epoch": 0.84, "grad_norm": 1.068573590269882, "learning_rate": 1.3857998200196943e-06, "loss": 0.8191, "step": 4343 }, { "epoch": 0.84, "grad_norm": 0.9182929142579429, "learning_rate": 1.3826368876676278e-06, "loss": 0.8308, "step": 4344 }, { "epoch": 0.84, "grad_norm": 1.0590759945930877, "learning_rate": 1.379477300872626e-06, "loss": 0.8811, "step": 4345 }, { "epoch": 0.84, "grad_norm": 1.0563173815453366, "learning_rate": 1.3763210608613497e-06, "loss": 0.8745, "step": 4346 }, { "epoch": 0.84, "grad_norm": 1.2078034787840461, "learning_rate": 1.3731681688591593e-06, "loss": 0.8948, "step": 4347 }, { "epoch": 0.84, "grad_norm": 0.9345320856463818, "learning_rate": 1.370018626090116e-06, "loss": 0.8293, "step": 4348 }, { "epoch": 0.84, "grad_norm": 1.1373205629875558, "learning_rate": 1.3668724337769823e-06, "loss": 0.8408, "step": 4349 }, { "epoch": 0.84, "grad_norm": 0.9426622182843899, "learning_rate": 1.3637295931412153e-06, "loss": 0.8281, "step": 4350 }, { "epoch": 0.84, "grad_norm": 1.010937389468846, "learning_rate": 1.3605901054029746e-06, "loss": 0.8503, "step": 4351 }, { "epoch": 0.84, "grad_norm": 0.8947586463933197, "learning_rate": 1.3574539717811231e-06, "loss": 0.8552, "step": 4352 }, { "epoch": 0.84, "grad_norm": 1.0461064611763768, "learning_rate": 1.3543211934932065e-06, "loss": 0.8027, "step": 4353 }, { "epoch": 0.84, "grad_norm": 1.0341960689104588, "learning_rate": 1.3511917717554846e-06, "loss": 0.8779, "step": 4354 }, { "epoch": 0.84, "grad_norm": 0.7791836210825117, "learning_rate": 1.348065707782904e-06, "loss": 0.5914, "step": 4355 }, { "epoch": 0.84, "grad_norm": 1.119987610835977, "learning_rate": 1.3449430027891096e-06, "loss": 0.8109, "step": 4356 }, { "epoch": 0.84, "grad_norm": 1.1784885472451323, "learning_rate": 1.3418236579864452e-06, "loss": 0.9158, "step": 4357 }, { "epoch": 0.84, "grad_norm": 1.0595263136900397, "learning_rate": 1.338707674585945e-06, "loss": 0.8359, "step": 4358 }, { "epoch": 0.84, "grad_norm": 1.1956384300546614, "learning_rate": 1.3355950537973438e-06, "loss": 0.8894, "step": 4359 }, { "epoch": 0.84, "grad_norm": 1.0656417793794506, "learning_rate": 1.332485796829065e-06, "loss": 0.8486, "step": 4360 }, { "epoch": 0.84, "grad_norm": 1.0565285686060222, "learning_rate": 1.329379904888235e-06, "loss": 0.8296, "step": 4361 }, { "epoch": 0.84, "grad_norm": 0.9065461324919906, "learning_rate": 1.3262773791806617e-06, "loss": 0.5745, "step": 4362 }, { "epoch": 0.84, "grad_norm": 0.867023582340163, "learning_rate": 1.3231782209108546e-06, "loss": 0.6283, "step": 4363 }, { "epoch": 0.84, "grad_norm": 1.0127385190255316, "learning_rate": 1.3200824312820137e-06, "loss": 0.8574, "step": 4364 }, { "epoch": 0.84, "grad_norm": 1.1775313177817401, "learning_rate": 1.3169900114960298e-06, "loss": 0.9055, "step": 4365 }, { "epoch": 0.84, "grad_norm": 1.0956199724091011, "learning_rate": 1.3139009627534927e-06, "loss": 0.8706, "step": 4366 }, { "epoch": 0.84, "grad_norm": 0.9624307744129688, "learning_rate": 1.3108152862536683e-06, "loss": 0.8259, "step": 4367 }, { "epoch": 0.84, "grad_norm": 0.7934337475368153, "learning_rate": 1.3077329831945295e-06, "loss": 0.5685, "step": 4368 }, { "epoch": 0.84, "grad_norm": 1.0756989325158324, "learning_rate": 1.3046540547727305e-06, "loss": 0.8557, "step": 4369 }, { "epoch": 0.84, "grad_norm": 1.0621946397638844, "learning_rate": 1.3015785021836159e-06, "loss": 0.8065, "step": 4370 }, { "epoch": 0.84, "grad_norm": 1.0741198223251114, "learning_rate": 1.2985063266212229e-06, "loss": 0.8318, "step": 4371 }, { "epoch": 0.84, "grad_norm": 0.959306480004458, "learning_rate": 1.295437529278275e-06, "loss": 0.8611, "step": 4372 }, { "epoch": 0.84, "grad_norm": 1.079914951587896, "learning_rate": 1.2923721113461852e-06, "loss": 0.8425, "step": 4373 }, { "epoch": 0.84, "grad_norm": 1.1450926834603183, "learning_rate": 1.2893100740150522e-06, "loss": 0.9121, "step": 4374 }, { "epoch": 0.84, "grad_norm": 1.0767358891673449, "learning_rate": 1.2862514184736695e-06, "loss": 0.8527, "step": 4375 }, { "epoch": 0.84, "grad_norm": 0.9235090868966292, "learning_rate": 1.2831961459095088e-06, "loss": 0.6143, "step": 4376 }, { "epoch": 0.84, "grad_norm": 1.01409625231796, "learning_rate": 1.2801442575087296e-06, "loss": 0.7648, "step": 4377 }, { "epoch": 0.84, "grad_norm": 1.0610822409545766, "learning_rate": 1.2770957544561868e-06, "loss": 0.8811, "step": 4378 }, { "epoch": 0.84, "grad_norm": 0.9888655114390428, "learning_rate": 1.274050637935408e-06, "loss": 0.8303, "step": 4379 }, { "epoch": 0.84, "grad_norm": 1.0466945803202576, "learning_rate": 1.2710089091286148e-06, "loss": 0.8691, "step": 4380 }, { "epoch": 0.84, "grad_norm": 1.1692451484495718, "learning_rate": 1.2679705692167122e-06, "loss": 0.8419, "step": 4381 }, { "epoch": 0.84, "grad_norm": 0.9210865463485957, "learning_rate": 1.2649356193792873e-06, "loss": 0.7905, "step": 4382 }, { "epoch": 0.84, "grad_norm": 0.8259457248799797, "learning_rate": 1.261904060794612e-06, "loss": 0.5943, "step": 4383 }, { "epoch": 0.84, "grad_norm": 1.032049136986822, "learning_rate": 1.2588758946396417e-06, "loss": 0.8469, "step": 4384 }, { "epoch": 0.84, "grad_norm": 1.0759601040656583, "learning_rate": 1.2558511220900138e-06, "loss": 0.887, "step": 4385 }, { "epoch": 0.84, "grad_norm": 1.2962665671005584, "learning_rate": 1.2528297443200489e-06, "loss": 0.9146, "step": 4386 }, { "epoch": 0.84, "grad_norm": 0.7959477660186517, "learning_rate": 1.2498117625027562e-06, "loss": 0.5407, "step": 4387 }, { "epoch": 0.84, "grad_norm": 1.0475880432825784, "learning_rate": 1.246797177809812e-06, "loss": 0.8187, "step": 4388 }, { "epoch": 0.84, "grad_norm": 0.8034958111170372, "learning_rate": 1.2437859914115847e-06, "loss": 0.5493, "step": 4389 }, { "epoch": 0.84, "grad_norm": 0.9141205646695607, "learning_rate": 1.2407782044771222e-06, "loss": 0.5776, "step": 4390 }, { "epoch": 0.84, "grad_norm": 1.0564295594071789, "learning_rate": 1.237773818174146e-06, "loss": 0.874, "step": 4391 }, { "epoch": 0.84, "grad_norm": 1.175888355856478, "learning_rate": 1.23477283366907e-06, "loss": 0.839, "step": 4392 }, { "epoch": 0.85, "grad_norm": 0.958241435922626, "learning_rate": 1.2317752521269722e-06, "loss": 0.5873, "step": 4393 }, { "epoch": 0.85, "grad_norm": 1.1152477015168394, "learning_rate": 1.2287810747116224e-06, "loss": 0.855, "step": 4394 }, { "epoch": 0.85, "grad_norm": 0.9950799043594861, "learning_rate": 1.225790302585461e-06, "loss": 0.8635, "step": 4395 }, { "epoch": 0.85, "grad_norm": 1.0773068473241267, "learning_rate": 1.2228029369096094e-06, "loss": 0.8643, "step": 4396 }, { "epoch": 0.85, "grad_norm": 0.9349589467799436, "learning_rate": 1.2198189788438652e-06, "loss": 0.7922, "step": 4397 }, { "epoch": 0.85, "grad_norm": 0.9131502141615144, "learning_rate": 1.216838429546704e-06, "loss": 0.8447, "step": 4398 }, { "epoch": 0.85, "grad_norm": 0.9858896080916867, "learning_rate": 1.2138612901752777e-06, "loss": 0.8113, "step": 4399 }, { "epoch": 0.85, "grad_norm": 0.8075018845704932, "learning_rate": 1.2108875618854122e-06, "loss": 0.6042, "step": 4400 }, { "epoch": 0.85, "grad_norm": 0.9454943825781121, "learning_rate": 1.2079172458316168e-06, "loss": 0.8082, "step": 4401 }, { "epoch": 0.85, "grad_norm": 1.1169785643068815, "learning_rate": 1.204950343167065e-06, "loss": 0.8254, "step": 4402 }, { "epoch": 0.85, "grad_norm": 0.9765794201815584, "learning_rate": 1.2019868550436099e-06, "loss": 0.843, "step": 4403 }, { "epoch": 0.85, "grad_norm": 0.9403549035365198, "learning_rate": 1.1990267826117874e-06, "loss": 0.8293, "step": 4404 }, { "epoch": 0.85, "grad_norm": 1.1256849493616075, "learning_rate": 1.1960701270207885e-06, "loss": 0.8079, "step": 4405 }, { "epoch": 0.85, "grad_norm": 1.0476044154963031, "learning_rate": 1.1931168894184974e-06, "loss": 0.8533, "step": 4406 }, { "epoch": 0.85, "grad_norm": 0.9845344798861178, "learning_rate": 1.19016707095146e-06, "loss": 0.834, "step": 4407 }, { "epoch": 0.85, "grad_norm": 1.0724111605461435, "learning_rate": 1.187220672764897e-06, "loss": 0.9114, "step": 4408 }, { "epoch": 0.85, "grad_norm": 0.928729089600658, "learning_rate": 1.1842776960027014e-06, "loss": 0.8271, "step": 4409 }, { "epoch": 0.85, "grad_norm": 0.9736764227532813, "learning_rate": 1.1813381418074388e-06, "loss": 0.856, "step": 4410 }, { "epoch": 0.85, "grad_norm": 0.9397560293526083, "learning_rate": 1.1784020113203453e-06, "loss": 0.5867, "step": 4411 }, { "epoch": 0.85, "grad_norm": 1.0945151281820207, "learning_rate": 1.1754693056813272e-06, "loss": 0.8711, "step": 4412 }, { "epoch": 0.85, "grad_norm": 0.9758976281153978, "learning_rate": 1.172540026028962e-06, "loss": 0.8606, "step": 4413 }, { "epoch": 0.85, "grad_norm": 0.9857698940516222, "learning_rate": 1.169614173500494e-06, "loss": 0.8101, "step": 4414 }, { "epoch": 0.85, "grad_norm": 1.007492842731658, "learning_rate": 1.1666917492318486e-06, "loss": 0.7981, "step": 4415 }, { "epoch": 0.85, "grad_norm": 1.0486404554728346, "learning_rate": 1.1637727543576027e-06, "loss": 0.8109, "step": 4416 }, { "epoch": 0.85, "grad_norm": 1.0017643582469906, "learning_rate": 1.1608571900110122e-06, "loss": 0.791, "step": 4417 }, { "epoch": 0.85, "grad_norm": 0.9565564904807745, "learning_rate": 1.1579450573240058e-06, "loss": 0.8293, "step": 4418 }, { "epoch": 0.85, "grad_norm": 1.0003100139108252, "learning_rate": 1.1550363574271638e-06, "loss": 0.8428, "step": 4419 }, { "epoch": 0.85, "grad_norm": 0.8938486260684243, "learning_rate": 1.1521310914497518e-06, "loss": 0.8062, "step": 4420 }, { "epoch": 0.85, "grad_norm": 1.0893017158429463, "learning_rate": 1.149229260519691e-06, "loss": 0.874, "step": 4421 }, { "epoch": 0.85, "grad_norm": 1.2097052872896477, "learning_rate": 1.1463308657635718e-06, "loss": 0.7926, "step": 4422 }, { "epoch": 0.85, "grad_norm": 0.9677128178581469, "learning_rate": 1.1434359083066515e-06, "loss": 0.8535, "step": 4423 }, { "epoch": 0.85, "grad_norm": 0.8941958592021398, "learning_rate": 1.140544389272853e-06, "loss": 0.8513, "step": 4424 }, { "epoch": 0.85, "grad_norm": 0.9710691610272608, "learning_rate": 1.1376563097847616e-06, "loss": 0.788, "step": 4425 }, { "epoch": 0.85, "grad_norm": 0.9966262048765224, "learning_rate": 1.1347716709636282e-06, "loss": 0.8091, "step": 4426 }, { "epoch": 0.85, "grad_norm": 1.1891700808356935, "learning_rate": 1.1318904739293745e-06, "loss": 0.8579, "step": 4427 }, { "epoch": 0.85, "grad_norm": 0.8392438657628039, "learning_rate": 1.129012719800575e-06, "loss": 0.5891, "step": 4428 }, { "epoch": 0.85, "grad_norm": 1.1197482216848023, "learning_rate": 1.1261384096944728e-06, "loss": 0.8418, "step": 4429 }, { "epoch": 0.85, "grad_norm": 0.8392670700254226, "learning_rate": 1.1232675447269803e-06, "loss": 0.5923, "step": 4430 }, { "epoch": 0.85, "grad_norm": 1.1876732919778539, "learning_rate": 1.1204001260126574e-06, "loss": 0.7593, "step": 4431 }, { "epoch": 0.85, "grad_norm": 1.1425724514388373, "learning_rate": 1.1175361546647413e-06, "loss": 0.8354, "step": 4432 }, { "epoch": 0.85, "grad_norm": 1.0128311341579639, "learning_rate": 1.1146756317951224e-06, "loss": 0.842, "step": 4433 }, { "epoch": 0.85, "grad_norm": 1.1469722072231798, "learning_rate": 1.1118185585143536e-06, "loss": 0.8086, "step": 4434 }, { "epoch": 0.85, "grad_norm": 0.9506812771561762, "learning_rate": 1.1089649359316501e-06, "loss": 0.8169, "step": 4435 }, { "epoch": 0.85, "grad_norm": 0.8613991785098667, "learning_rate": 1.1061147651548855e-06, "loss": 0.626, "step": 4436 }, { "epoch": 0.85, "grad_norm": 0.9809325325746836, "learning_rate": 1.1032680472905932e-06, "loss": 0.7931, "step": 4437 }, { "epoch": 0.85, "grad_norm": 1.067476374494682, "learning_rate": 1.1004247834439697e-06, "loss": 0.8569, "step": 4438 }, { "epoch": 0.85, "grad_norm": 0.9838034879773436, "learning_rate": 1.097584974718866e-06, "loss": 0.8584, "step": 4439 }, { "epoch": 0.85, "grad_norm": 1.0069313182200208, "learning_rate": 1.0947486222177928e-06, "loss": 0.7893, "step": 4440 }, { "epoch": 0.85, "grad_norm": 1.0055833788561257, "learning_rate": 1.0919157270419257e-06, "loss": 0.821, "step": 4441 }, { "epoch": 0.85, "grad_norm": 1.1209338618075027, "learning_rate": 1.0890862902910849e-06, "loss": 0.7827, "step": 4442 }, { "epoch": 0.85, "grad_norm": 1.1469768507447569, "learning_rate": 1.0862603130637562e-06, "loss": 0.8401, "step": 4443 }, { "epoch": 0.85, "grad_norm": 1.2521575282547384, "learning_rate": 1.0834377964570863e-06, "loss": 0.8723, "step": 4444 }, { "epoch": 0.86, "grad_norm": 1.0678881117080008, "learning_rate": 1.0806187415668668e-06, "loss": 0.8347, "step": 4445 }, { "epoch": 0.86, "grad_norm": 1.1266940974515693, "learning_rate": 1.0778031494875574e-06, "loss": 0.8728, "step": 4446 }, { "epoch": 0.86, "grad_norm": 1.0202758460403647, "learning_rate": 1.0749910213122649e-06, "loss": 0.8564, "step": 4447 }, { "epoch": 0.86, "grad_norm": 0.9875183006443881, "learning_rate": 1.072182358132755e-06, "loss": 0.8152, "step": 4448 }, { "epoch": 0.86, "grad_norm": 1.066438870053355, "learning_rate": 1.0693771610394477e-06, "loss": 0.8032, "step": 4449 }, { "epoch": 0.86, "grad_norm": 1.0941069673971076, "learning_rate": 1.066575431121417e-06, "loss": 0.8464, "step": 4450 }, { "epoch": 0.86, "grad_norm": 1.0574723546972171, "learning_rate": 1.06377716946639e-06, "loss": 0.845, "step": 4451 }, { "epoch": 0.86, "grad_norm": 1.0621613897988573, "learning_rate": 1.0609823771607487e-06, "loss": 0.8853, "step": 4452 }, { "epoch": 0.86, "grad_norm": 1.0231271500261205, "learning_rate": 1.0581910552895302e-06, "loss": 0.8013, "step": 4453 }, { "epoch": 0.86, "grad_norm": 1.0600629310703673, "learning_rate": 1.055403204936416e-06, "loss": 0.8699, "step": 4454 }, { "epoch": 0.86, "grad_norm": 1.1063499041293807, "learning_rate": 1.0526188271837512e-06, "loss": 0.8533, "step": 4455 }, { "epoch": 0.86, "grad_norm": 1.1499092856074116, "learning_rate": 1.0498379231125278e-06, "loss": 0.8538, "step": 4456 }, { "epoch": 0.86, "grad_norm": 1.009808961143111, "learning_rate": 1.047060493802381e-06, "loss": 0.8086, "step": 4457 }, { "epoch": 0.86, "grad_norm": 1.0029409802821592, "learning_rate": 1.0442865403316117e-06, "loss": 0.7897, "step": 4458 }, { "epoch": 0.86, "grad_norm": 0.738253273604159, "learning_rate": 1.0415160637771604e-06, "loss": 0.5221, "step": 4459 }, { "epoch": 0.86, "grad_norm": 0.9660574505706183, "learning_rate": 1.0387490652146236e-06, "loss": 0.8237, "step": 4460 }, { "epoch": 0.86, "grad_norm": 1.0817646858510224, "learning_rate": 1.0359855457182455e-06, "loss": 0.8624, "step": 4461 }, { "epoch": 0.86, "grad_norm": 1.0147856628954801, "learning_rate": 1.0332255063609177e-06, "loss": 0.8777, "step": 4462 }, { "epoch": 0.86, "grad_norm": 1.1193168711066, "learning_rate": 1.0304689482141839e-06, "loss": 0.8162, "step": 4463 }, { "epoch": 0.86, "grad_norm": 1.0237528380224663, "learning_rate": 1.027715872348234e-06, "loss": 0.8062, "step": 4464 }, { "epoch": 0.86, "grad_norm": 0.8795501114909625, "learning_rate": 1.0249662798319072e-06, "loss": 0.7922, "step": 4465 }, { "epoch": 0.86, "grad_norm": 0.9651728695667801, "learning_rate": 1.0222201717326885e-06, "loss": 0.9221, "step": 4466 }, { "epoch": 0.86, "grad_norm": 1.0975770066885064, "learning_rate": 1.0194775491167164e-06, "loss": 0.8081, "step": 4467 }, { "epoch": 0.86, "grad_norm": 0.9830319933841873, "learning_rate": 1.0167384130487667e-06, "loss": 0.8269, "step": 4468 }, { "epoch": 0.86, "grad_norm": 1.005021674429329, "learning_rate": 1.0140027645922656e-06, "loss": 0.8601, "step": 4469 }, { "epoch": 0.86, "grad_norm": 0.9889834998996526, "learning_rate": 1.0112706048092924e-06, "loss": 0.8098, "step": 4470 }, { "epoch": 0.86, "grad_norm": 0.9933747018493467, "learning_rate": 1.0085419347605575e-06, "loss": 0.8643, "step": 4471 }, { "epoch": 0.86, "grad_norm": 1.260865545627639, "learning_rate": 1.00581675550543e-06, "loss": 0.8828, "step": 4472 }, { "epoch": 0.86, "grad_norm": 1.016943491026647, "learning_rate": 1.003095068101917e-06, "loss": 0.8599, "step": 4473 }, { "epoch": 0.86, "grad_norm": 1.1127341965474538, "learning_rate": 1.0003768736066722e-06, "loss": 0.9041, "step": 4474 }, { "epoch": 0.86, "grad_norm": 1.0282194492490428, "learning_rate": 9.976621730749892e-07, "loss": 0.8191, "step": 4475 }, { "epoch": 0.86, "grad_norm": 1.0186208043350844, "learning_rate": 9.949509675608115e-07, "loss": 0.8574, "step": 4476 }, { "epoch": 0.86, "grad_norm": 1.0466251095061487, "learning_rate": 9.922432581167207e-07, "loss": 0.8967, "step": 4477 }, { "epoch": 0.86, "grad_norm": 0.9876208053971921, "learning_rate": 9.895390457939414e-07, "loss": 0.8445, "step": 4478 }, { "epoch": 0.86, "grad_norm": 0.9917215980313014, "learning_rate": 9.86838331642348e-07, "loss": 0.8252, "step": 4479 }, { "epoch": 0.86, "grad_norm": 1.0404294213815073, "learning_rate": 9.84141116710442e-07, "loss": 0.9238, "step": 4480 }, { "epoch": 0.86, "grad_norm": 0.9931013545585547, "learning_rate": 9.814474020453824e-07, "loss": 0.8057, "step": 4481 }, { "epoch": 0.86, "grad_norm": 0.9585039955382837, "learning_rate": 9.787571886929604e-07, "loss": 0.8044, "step": 4482 }, { "epoch": 0.86, "grad_norm": 0.8183096888237388, "learning_rate": 9.76070477697605e-07, "loss": 0.6272, "step": 4483 }, { "epoch": 0.86, "grad_norm": 1.1917603666095684, "learning_rate": 9.733872701023938e-07, "loss": 0.8652, "step": 4484 }, { "epoch": 0.86, "grad_norm": 1.0571853525716142, "learning_rate": 9.707075669490407e-07, "loss": 0.8486, "step": 4485 }, { "epoch": 0.86, "grad_norm": 1.101562673318457, "learning_rate": 9.680313692778976e-07, "loss": 0.8206, "step": 4486 }, { "epoch": 0.86, "grad_norm": 1.0704576371498575, "learning_rate": 9.653586781279567e-07, "loss": 0.8495, "step": 4487 }, { "epoch": 0.86, "grad_norm": 1.0019208315428376, "learning_rate": 9.626894945368492e-07, "loss": 0.8726, "step": 4488 }, { "epoch": 0.86, "grad_norm": 0.9924025811683479, "learning_rate": 9.600238195408428e-07, "loss": 0.8457, "step": 4489 }, { "epoch": 0.86, "grad_norm": 1.1035775283312996, "learning_rate": 9.573616541748464e-07, "loss": 0.8696, "step": 4490 }, { "epoch": 0.86, "grad_norm": 1.046163848518277, "learning_rate": 9.547029994724023e-07, "loss": 0.8494, "step": 4491 }, { "epoch": 0.86, "grad_norm": 1.091711027501412, "learning_rate": 9.520478564656898e-07, "loss": 0.756, "step": 4492 }, { "epoch": 0.86, "grad_norm": 1.1257964905852813, "learning_rate": 9.49396226185535e-07, "loss": 0.8083, "step": 4493 }, { "epoch": 0.86, "grad_norm": 1.078488155073533, "learning_rate": 9.467481096613829e-07, "loss": 0.845, "step": 4494 }, { "epoch": 0.86, "grad_norm": 1.0893597963966166, "learning_rate": 9.441035079213267e-07, "loss": 0.8591, "step": 4495 }, { "epoch": 0.86, "grad_norm": 0.92126225483443, "learning_rate": 9.414624219920953e-07, "loss": 0.8374, "step": 4496 }, { "epoch": 0.87, "grad_norm": 1.004025577668963, "learning_rate": 9.38824852899043e-07, "loss": 0.8555, "step": 4497 }, { "epoch": 0.87, "grad_norm": 1.0678572948176503, "learning_rate": 9.361908016661703e-07, "loss": 0.8052, "step": 4498 }, { "epoch": 0.87, "grad_norm": 1.0311898409028861, "learning_rate": 9.335602693161039e-07, "loss": 0.8835, "step": 4499 }, { "epoch": 0.87, "grad_norm": 1.0827285350186113, "learning_rate": 9.309332568701079e-07, "loss": 0.8584, "step": 4500 }, { "epoch": 0.87, "grad_norm": 0.9907475630993338, "learning_rate": 9.283097653480788e-07, "loss": 0.8474, "step": 4501 }, { "epoch": 0.87, "grad_norm": 1.0934324857381363, "learning_rate": 9.256897957685463e-07, "loss": 0.8192, "step": 4502 }, { "epoch": 0.87, "grad_norm": 1.0165005953483157, "learning_rate": 9.230733491486721e-07, "loss": 0.8115, "step": 4503 }, { "epoch": 0.87, "grad_norm": 0.9469359527183042, "learning_rate": 9.204604265042505e-07, "loss": 0.8198, "step": 4504 }, { "epoch": 0.87, "grad_norm": 0.9869177839130499, "learning_rate": 9.178510288497123e-07, "loss": 0.8555, "step": 4505 }, { "epoch": 0.87, "grad_norm": 1.0726865001505554, "learning_rate": 9.15245157198108e-07, "loss": 0.801, "step": 4506 }, { "epoch": 0.87, "grad_norm": 1.1556301229375887, "learning_rate": 9.126428125611342e-07, "loss": 0.9094, "step": 4507 }, { "epoch": 0.87, "grad_norm": 1.0231798848534899, "learning_rate": 9.10043995949108e-07, "loss": 0.8787, "step": 4508 }, { "epoch": 0.87, "grad_norm": 0.9738133704505719, "learning_rate": 9.074487083709759e-07, "loss": 0.8098, "step": 4509 }, { "epoch": 0.87, "grad_norm": 0.9862395675249661, "learning_rate": 9.04856950834323e-07, "loss": 0.7886, "step": 4510 }, { "epoch": 0.87, "grad_norm": 1.0818239361592663, "learning_rate": 9.022687243453554e-07, "loss": 0.8789, "step": 4511 }, { "epoch": 0.87, "grad_norm": 1.0285915167014452, "learning_rate": 8.996840299089149e-07, "loss": 0.8259, "step": 4512 }, { "epoch": 0.87, "grad_norm": 0.9635508164463265, "learning_rate": 8.971028685284655e-07, "loss": 0.8394, "step": 4513 }, { "epoch": 0.87, "grad_norm": 1.0067985505295258, "learning_rate": 8.945252412061056e-07, "loss": 0.8442, "step": 4514 }, { "epoch": 0.87, "grad_norm": 0.9956086878048659, "learning_rate": 8.91951148942557e-07, "loss": 0.8491, "step": 4515 }, { "epoch": 0.87, "grad_norm": 0.9015874414045505, "learning_rate": 8.893805927371724e-07, "loss": 0.5939, "step": 4516 }, { "epoch": 0.87, "grad_norm": 1.149154069943946, "learning_rate": 8.868135735879291e-07, "loss": 0.8237, "step": 4517 }, { "epoch": 0.87, "grad_norm": 1.0249436680466968, "learning_rate": 8.842500924914299e-07, "loss": 0.8213, "step": 4518 }, { "epoch": 0.87, "grad_norm": 0.9496936661091198, "learning_rate": 8.816901504429143e-07, "loss": 0.8015, "step": 4519 }, { "epoch": 0.87, "grad_norm": 0.9839429688998408, "learning_rate": 8.791337484362305e-07, "loss": 0.833, "step": 4520 }, { "epoch": 0.87, "grad_norm": 1.1196219518506239, "learning_rate": 8.765808874638682e-07, "loss": 0.845, "step": 4521 }, { "epoch": 0.87, "grad_norm": 0.9733600286934256, "learning_rate": 8.740315685169364e-07, "loss": 0.8101, "step": 4522 }, { "epoch": 0.87, "grad_norm": 0.9538096832639429, "learning_rate": 8.714857925851617e-07, "loss": 0.8386, "step": 4523 }, { "epoch": 0.87, "grad_norm": 0.814702060703642, "learning_rate": 8.689435606569086e-07, "loss": 0.5394, "step": 4524 }, { "epoch": 0.87, "grad_norm": 1.1024354774320066, "learning_rate": 8.664048737191566e-07, "loss": 0.8569, "step": 4525 }, { "epoch": 0.87, "grad_norm": 1.1499691332313777, "learning_rate": 8.638697327575108e-07, "loss": 0.863, "step": 4526 }, { "epoch": 0.87, "grad_norm": 0.9706643626179873, "learning_rate": 8.613381387562015e-07, "loss": 0.8206, "step": 4527 }, { "epoch": 0.87, "grad_norm": 1.2651716869384635, "learning_rate": 8.588100926980802e-07, "loss": 0.9231, "step": 4528 }, { "epoch": 0.87, "grad_norm": 1.0672782687951794, "learning_rate": 8.56285595564621e-07, "loss": 0.8381, "step": 4529 }, { "epoch": 0.87, "grad_norm": 1.0838022708431687, "learning_rate": 8.537646483359185e-07, "loss": 0.8254, "step": 4530 }, { "epoch": 0.87, "grad_norm": 0.7745085255908521, "learning_rate": 8.512472519906978e-07, "loss": 0.6229, "step": 4531 }, { "epoch": 0.87, "grad_norm": 0.8829398532805895, "learning_rate": 8.487334075062914e-07, "loss": 0.605, "step": 4532 }, { "epoch": 0.87, "grad_norm": 1.1609061666026812, "learning_rate": 8.462231158586654e-07, "loss": 0.868, "step": 4533 }, { "epoch": 0.87, "grad_norm": 1.074954196640635, "learning_rate": 8.437163780224011e-07, "loss": 0.9329, "step": 4534 }, { "epoch": 0.87, "grad_norm": 1.1800005141066816, "learning_rate": 8.412131949706958e-07, "loss": 0.8203, "step": 4535 }, { "epoch": 0.87, "grad_norm": 1.0942048692645017, "learning_rate": 8.387135676753755e-07, "loss": 0.8142, "step": 4536 }, { "epoch": 0.87, "grad_norm": 1.0137351941717971, "learning_rate": 8.362174971068804e-07, "loss": 0.8206, "step": 4537 }, { "epoch": 0.87, "grad_norm": 0.9912491719383685, "learning_rate": 8.337249842342721e-07, "loss": 0.8909, "step": 4538 }, { "epoch": 0.87, "grad_norm": 0.8742477611286763, "learning_rate": 8.312360300252287e-07, "loss": 0.5771, "step": 4539 }, { "epoch": 0.87, "grad_norm": 1.0879368528238538, "learning_rate": 8.287506354460484e-07, "loss": 0.8979, "step": 4540 }, { "epoch": 0.87, "grad_norm": 0.7491249813893471, "learning_rate": 8.26268801461646e-07, "loss": 0.595, "step": 4541 }, { "epoch": 0.87, "grad_norm": 1.0675259365058039, "learning_rate": 8.237905290355563e-07, "loss": 0.7656, "step": 4542 }, { "epoch": 0.87, "grad_norm": 1.0762582976157624, "learning_rate": 8.213158191299297e-07, "loss": 0.8669, "step": 4543 }, { "epoch": 0.87, "grad_norm": 1.1222360013868717, "learning_rate": 8.188446727055311e-07, "loss": 0.8564, "step": 4544 }, { "epoch": 0.87, "grad_norm": 1.0297012095920717, "learning_rate": 8.163770907217506e-07, "loss": 0.8652, "step": 4545 }, { "epoch": 0.87, "grad_norm": 0.9653412543991258, "learning_rate": 8.139130741365819e-07, "loss": 0.7954, "step": 4546 }, { "epoch": 0.87, "grad_norm": 0.9243652176702085, "learning_rate": 8.114526239066456e-07, "loss": 0.8591, "step": 4547 }, { "epoch": 0.87, "grad_norm": 1.0695888860253215, "learning_rate": 8.08995740987173e-07, "loss": 0.8303, "step": 4548 }, { "epoch": 0.88, "grad_norm": 1.0322674156286176, "learning_rate": 8.065424263320054e-07, "loss": 0.8865, "step": 4549 }, { "epoch": 0.88, "grad_norm": 1.0800143580039712, "learning_rate": 8.040926808936112e-07, "loss": 0.884, "step": 4550 }, { "epoch": 0.88, "grad_norm": 1.025492210919202, "learning_rate": 8.016465056230616e-07, "loss": 0.793, "step": 4551 }, { "epoch": 0.88, "grad_norm": 0.9820862496818964, "learning_rate": 7.99203901470047e-07, "loss": 0.8159, "step": 4552 }, { "epoch": 0.88, "grad_norm": 1.0764705846801774, "learning_rate": 7.967648693828712e-07, "loss": 0.8333, "step": 4553 }, { "epoch": 0.88, "grad_norm": 0.9346571750394278, "learning_rate": 7.943294103084487e-07, "loss": 0.7974, "step": 4554 }, { "epoch": 0.88, "grad_norm": 0.82144403838169, "learning_rate": 7.9189752519231e-07, "loss": 0.6039, "step": 4555 }, { "epoch": 0.88, "grad_norm": 0.9838874913915435, "learning_rate": 7.894692149785954e-07, "loss": 0.844, "step": 4556 }, { "epoch": 0.88, "grad_norm": 1.0550205948688327, "learning_rate": 7.870444806100619e-07, "loss": 0.8723, "step": 4557 }, { "epoch": 0.88, "grad_norm": 1.1708912851196298, "learning_rate": 7.846233230280698e-07, "loss": 0.833, "step": 4558 }, { "epoch": 0.88, "grad_norm": 1.008260682026805, "learning_rate": 7.822057431725994e-07, "loss": 0.835, "step": 4559 }, { "epoch": 0.88, "grad_norm": 1.123283866050368, "learning_rate": 7.797917419822377e-07, "loss": 0.8457, "step": 4560 }, { "epoch": 0.88, "grad_norm": 1.0056726246447274, "learning_rate": 7.773813203941827e-07, "loss": 0.842, "step": 4561 }, { "epoch": 0.88, "grad_norm": 0.8304694978108632, "learning_rate": 7.749744793442448e-07, "loss": 0.5699, "step": 4562 }, { "epoch": 0.88, "grad_norm": 1.0917864779385043, "learning_rate": 7.725712197668378e-07, "loss": 0.8406, "step": 4563 }, { "epoch": 0.88, "grad_norm": 0.9693225124954427, "learning_rate": 7.701715425949952e-07, "loss": 0.8318, "step": 4564 }, { "epoch": 0.88, "grad_norm": 1.0568380675966773, "learning_rate": 7.677754487603517e-07, "loss": 0.8125, "step": 4565 }, { "epoch": 0.88, "grad_norm": 1.0222821320690376, "learning_rate": 7.653829391931533e-07, "loss": 0.8453, "step": 4566 }, { "epoch": 0.88, "grad_norm": 0.9783200576077064, "learning_rate": 7.629940148222559e-07, "loss": 0.8608, "step": 4567 }, { "epoch": 0.88, "grad_norm": 0.9910300107315153, "learning_rate": 7.606086765751209e-07, "loss": 0.7832, "step": 4568 }, { "epoch": 0.88, "grad_norm": 1.081640406087982, "learning_rate": 7.582269253778185e-07, "loss": 0.875, "step": 4569 }, { "epoch": 0.88, "grad_norm": 0.985579056796487, "learning_rate": 7.55848762155027e-07, "loss": 0.8708, "step": 4570 }, { "epoch": 0.88, "grad_norm": 0.9755266143377109, "learning_rate": 7.534741878300333e-07, "loss": 0.8433, "step": 4571 }, { "epoch": 0.88, "grad_norm": 0.9051327244953822, "learning_rate": 7.511032033247256e-07, "loss": 0.6077, "step": 4572 }, { "epoch": 0.88, "grad_norm": 0.919382389940145, "learning_rate": 7.487358095596031e-07, "loss": 0.8369, "step": 4573 }, { "epoch": 0.88, "grad_norm": 1.0759972893270868, "learning_rate": 7.463720074537728e-07, "loss": 0.8572, "step": 4574 }, { "epoch": 0.88, "grad_norm": 1.0753181257016928, "learning_rate": 7.440117979249362e-07, "loss": 0.8635, "step": 4575 }, { "epoch": 0.88, "grad_norm": 1.0261456284907464, "learning_rate": 7.416551818894158e-07, "loss": 0.8213, "step": 4576 }, { "epoch": 0.88, "grad_norm": 0.9252417225599511, "learning_rate": 7.393021602621264e-07, "loss": 0.8245, "step": 4577 }, { "epoch": 0.88, "grad_norm": 1.0372812751418432, "learning_rate": 7.369527339565951e-07, "loss": 0.804, "step": 4578 }, { "epoch": 0.88, "grad_norm": 0.8562041422104687, "learning_rate": 7.346069038849469e-07, "loss": 0.5486, "step": 4579 }, { "epoch": 0.88, "grad_norm": 1.033665558176941, "learning_rate": 7.322646709579173e-07, "loss": 0.8315, "step": 4580 }, { "epoch": 0.88, "grad_norm": 1.0751569020611031, "learning_rate": 7.299260360848382e-07, "loss": 0.8433, "step": 4581 }, { "epoch": 0.88, "grad_norm": 1.0182919545146587, "learning_rate": 7.275910001736497e-07, "loss": 0.8164, "step": 4582 }, { "epoch": 0.88, "grad_norm": 1.160410347078589, "learning_rate": 7.252595641308957e-07, "loss": 0.8088, "step": 4583 }, { "epoch": 0.88, "grad_norm": 1.057464567023002, "learning_rate": 7.229317288617144e-07, "loss": 0.8337, "step": 4584 }, { "epoch": 0.88, "grad_norm": 1.0959172552779528, "learning_rate": 7.20607495269856e-07, "loss": 0.8806, "step": 4585 }, { "epoch": 0.88, "grad_norm": 0.7895973494980207, "learning_rate": 7.182868642576679e-07, "loss": 0.5809, "step": 4586 }, { "epoch": 0.88, "grad_norm": 1.100217628434679, "learning_rate": 7.15969836726097e-07, "loss": 0.7878, "step": 4587 }, { "epoch": 0.88, "grad_norm": 1.0566701283363955, "learning_rate": 7.13656413574696e-07, "loss": 0.7933, "step": 4588 }, { "epoch": 0.88, "grad_norm": 0.8756837589386705, "learning_rate": 7.113465957016097e-07, "loss": 0.6188, "step": 4589 }, { "epoch": 0.88, "grad_norm": 0.9901423190476115, "learning_rate": 7.090403840035942e-07, "loss": 0.8378, "step": 4590 }, { "epoch": 0.88, "grad_norm": 0.9411218687773845, "learning_rate": 7.067377793759999e-07, "loss": 0.8228, "step": 4591 }, { "epoch": 0.88, "grad_norm": 1.0937379825732247, "learning_rate": 7.044387827127752e-07, "loss": 0.8679, "step": 4592 }, { "epoch": 0.88, "grad_norm": 1.1024620514540924, "learning_rate": 7.021433949064704e-07, "loss": 0.832, "step": 4593 }, { "epoch": 0.88, "grad_norm": 1.0556259009427014, "learning_rate": 6.99851616848235e-07, "loss": 0.8567, "step": 4594 }, { "epoch": 0.88, "grad_norm": 1.1361830278926104, "learning_rate": 6.975634494278149e-07, "loss": 0.8545, "step": 4595 }, { "epoch": 0.88, "grad_norm": 0.9585386420807861, "learning_rate": 6.952788935335541e-07, "loss": 0.854, "step": 4596 }, { "epoch": 0.88, "grad_norm": 1.0987991389361433, "learning_rate": 6.92997950052402e-07, "loss": 0.8823, "step": 4597 }, { "epoch": 0.88, "grad_norm": 1.0432235253896973, "learning_rate": 6.907206198698912e-07, "loss": 0.9099, "step": 4598 }, { "epoch": 0.88, "grad_norm": 1.0781910586030892, "learning_rate": 6.884469038701646e-07, "loss": 0.8815, "step": 4599 }, { "epoch": 0.88, "grad_norm": 1.0252795588423647, "learning_rate": 6.861768029359595e-07, "loss": 0.8931, "step": 4600 }, { "epoch": 0.89, "grad_norm": 1.26118311052836, "learning_rate": 6.839103179485995e-07, "loss": 0.9292, "step": 4601 }, { "epoch": 0.89, "grad_norm": 1.0306233435613728, "learning_rate": 6.816474497880177e-07, "loss": 0.8604, "step": 4602 }, { "epoch": 0.89, "grad_norm": 1.0177881317929993, "learning_rate": 6.793881993327366e-07, "loss": 0.886, "step": 4603 }, { "epoch": 0.89, "grad_norm": 0.9888359749215613, "learning_rate": 6.77132567459875e-07, "loss": 0.8284, "step": 4604 }, { "epoch": 0.89, "grad_norm": 1.0886248949783355, "learning_rate": 6.748805550451453e-07, "loss": 0.8386, "step": 4605 }, { "epoch": 0.89, "grad_norm": 1.0126727882462714, "learning_rate": 6.726321629628585e-07, "loss": 0.854, "step": 4606 }, { "epoch": 0.89, "grad_norm": 1.011854458948353, "learning_rate": 6.703873920859161e-07, "loss": 0.833, "step": 4607 }, { "epoch": 0.89, "grad_norm": 1.1773278666037452, "learning_rate": 6.681462432858154e-07, "loss": 0.8425, "step": 4608 }, { "epoch": 0.89, "grad_norm": 1.052078610453789, "learning_rate": 6.659087174326506e-07, "loss": 0.8623, "step": 4609 }, { "epoch": 0.89, "grad_norm": 1.0329323710865586, "learning_rate": 6.636748153951e-07, "loss": 0.8467, "step": 4610 }, { "epoch": 0.89, "grad_norm": 1.0002646300973552, "learning_rate": 6.614445380404478e-07, "loss": 0.8452, "step": 4611 }, { "epoch": 0.89, "grad_norm": 1.0834387563788797, "learning_rate": 6.592178862345622e-07, "loss": 0.8491, "step": 4612 }, { "epoch": 0.89, "grad_norm": 0.9516893743714402, "learning_rate": 6.569948608419041e-07, "loss": 0.8721, "step": 4613 }, { "epoch": 0.89, "grad_norm": 0.8940910621220475, "learning_rate": 6.547754627255332e-07, "loss": 0.6184, "step": 4614 }, { "epoch": 0.89, "grad_norm": 0.9829597530510737, "learning_rate": 6.52559692747089e-07, "loss": 0.8645, "step": 4615 }, { "epoch": 0.89, "grad_norm": 1.1242414055179097, "learning_rate": 6.503475517668168e-07, "loss": 0.8662, "step": 4616 }, { "epoch": 0.89, "grad_norm": 0.9917598688914965, "learning_rate": 6.481390406435417e-07, "loss": 0.8706, "step": 4617 }, { "epoch": 0.89, "grad_norm": 1.0868702556842527, "learning_rate": 6.459341602346858e-07, "loss": 0.8083, "step": 4618 }, { "epoch": 0.89, "grad_norm": 1.1007108669279833, "learning_rate": 6.437329113962576e-07, "loss": 0.8965, "step": 4619 }, { "epoch": 0.89, "grad_norm": 1.2099088576025392, "learning_rate": 6.415352949828601e-07, "loss": 0.7986, "step": 4620 }, { "epoch": 0.89, "grad_norm": 0.9205141279451937, "learning_rate": 6.393413118476821e-07, "loss": 0.7637, "step": 4621 }, { "epoch": 0.89, "grad_norm": 1.0658083911592198, "learning_rate": 6.371509628425021e-07, "loss": 0.8359, "step": 4622 }, { "epoch": 0.89, "grad_norm": 1.0698886742668574, "learning_rate": 6.349642488176943e-07, "loss": 0.8093, "step": 4623 }, { "epoch": 0.89, "grad_norm": 0.8245304363529368, "learning_rate": 6.327811706222097e-07, "loss": 0.6008, "step": 4624 }, { "epoch": 0.89, "grad_norm": 1.195547869398719, "learning_rate": 6.306017291035981e-07, "loss": 0.8835, "step": 4625 }, { "epoch": 0.89, "grad_norm": 1.0730697197785806, "learning_rate": 6.284259251079939e-07, "loss": 0.8489, "step": 4626 }, { "epoch": 0.89, "grad_norm": 0.8095323607794794, "learning_rate": 6.262537594801177e-07, "loss": 0.6057, "step": 4627 }, { "epoch": 0.89, "grad_norm": 0.9528751368232303, "learning_rate": 6.240852330632796e-07, "loss": 0.8633, "step": 4628 }, { "epoch": 0.89, "grad_norm": 0.9812231012747467, "learning_rate": 6.219203466993762e-07, "loss": 0.8411, "step": 4629 }, { "epoch": 0.89, "grad_norm": 1.0081376922924266, "learning_rate": 6.197591012288918e-07, "loss": 0.8052, "step": 4630 }, { "epoch": 0.89, "grad_norm": 1.0219232991087925, "learning_rate": 6.17601497490895e-07, "loss": 0.8245, "step": 4631 }, { "epoch": 0.89, "grad_norm": 1.0986765720341556, "learning_rate": 6.154475363230417e-07, "loss": 0.8074, "step": 4632 }, { "epoch": 0.89, "grad_norm": 0.9671647622988143, "learning_rate": 6.132972185615749e-07, "loss": 0.8433, "step": 4633 }, { "epoch": 0.89, "grad_norm": 1.178429071309758, "learning_rate": 6.111505450413202e-07, "loss": 0.8738, "step": 4634 }, { "epoch": 0.89, "grad_norm": 1.0530591741900401, "learning_rate": 6.090075165956943e-07, "loss": 0.8525, "step": 4635 }, { "epoch": 0.89, "grad_norm": 1.1399295804555678, "learning_rate": 6.068681340566896e-07, "loss": 0.8887, "step": 4636 }, { "epoch": 0.89, "grad_norm": 0.8277453100932246, "learning_rate": 6.047323982548924e-07, "loss": 0.5802, "step": 4637 }, { "epoch": 0.89, "grad_norm": 1.039293563196851, "learning_rate": 6.026003100194633e-07, "loss": 0.9071, "step": 4638 }, { "epoch": 0.89, "grad_norm": 1.0177977440731116, "learning_rate": 6.004718701781575e-07, "loss": 0.8281, "step": 4639 }, { "epoch": 0.89, "grad_norm": 1.1250399312989203, "learning_rate": 5.983470795573088e-07, "loss": 0.9097, "step": 4640 }, { "epoch": 0.89, "grad_norm": 0.9844630872297149, "learning_rate": 5.962259389818292e-07, "loss": 0.8577, "step": 4641 }, { "epoch": 0.89, "grad_norm": 1.0162229125948437, "learning_rate": 5.941084492752236e-07, "loss": 0.8511, "step": 4642 }, { "epoch": 0.89, "grad_norm": 1.1100502613973446, "learning_rate": 5.91994611259572e-07, "loss": 0.8389, "step": 4643 }, { "epoch": 0.89, "grad_norm": 1.0596926556988837, "learning_rate": 5.898844257555392e-07, "loss": 0.8501, "step": 4644 }, { "epoch": 0.89, "grad_norm": 0.9894811134863967, "learning_rate": 5.87777893582372e-07, "loss": 0.8215, "step": 4645 }, { "epoch": 0.89, "grad_norm": 1.0713842665020363, "learning_rate": 5.856750155578983e-07, "loss": 0.8528, "step": 4646 }, { "epoch": 0.89, "grad_norm": 1.061784618475142, "learning_rate": 5.835757924985286e-07, "loss": 0.8679, "step": 4647 }, { "epoch": 0.89, "grad_norm": 1.0622004836686332, "learning_rate": 5.81480225219252e-07, "loss": 0.8567, "step": 4648 }, { "epoch": 0.89, "grad_norm": 1.0217157146604492, "learning_rate": 5.793883145336443e-07, "loss": 0.864, "step": 4649 }, { "epoch": 0.89, "grad_norm": 1.149950593899869, "learning_rate": 5.773000612538505e-07, "loss": 0.8831, "step": 4650 }, { "epoch": 0.89, "grad_norm": 0.9052412520914327, "learning_rate": 5.752154661906085e-07, "loss": 0.8142, "step": 4651 }, { "epoch": 0.89, "grad_norm": 1.142909856877354, "learning_rate": 5.731345301532265e-07, "loss": 0.8347, "step": 4652 }, { "epoch": 0.9, "grad_norm": 0.7946559321434914, "learning_rate": 5.710572539495962e-07, "loss": 0.6161, "step": 4653 }, { "epoch": 0.9, "grad_norm": 0.9992396730338085, "learning_rate": 5.68983638386188e-07, "loss": 0.8406, "step": 4654 }, { "epoch": 0.9, "grad_norm": 0.9791950693805366, "learning_rate": 5.669136842680512e-07, "loss": 0.8025, "step": 4655 }, { "epoch": 0.9, "grad_norm": 0.9269075736194047, "learning_rate": 5.648473923988129e-07, "loss": 0.8169, "step": 4656 }, { "epoch": 0.9, "grad_norm": 1.1178361039023088, "learning_rate": 5.627847635806771e-07, "loss": 0.8816, "step": 4657 }, { "epoch": 0.9, "grad_norm": 1.0628486315087362, "learning_rate": 5.607257986144321e-07, "loss": 0.8481, "step": 4658 }, { "epoch": 0.9, "grad_norm": 0.9953843416552802, "learning_rate": 5.58670498299434e-07, "loss": 0.8054, "step": 4659 }, { "epoch": 0.9, "grad_norm": 0.9839222364427873, "learning_rate": 5.566188634336212e-07, "loss": 0.8193, "step": 4660 }, { "epoch": 0.9, "grad_norm": 1.3599499096150056, "learning_rate": 5.545708948135142e-07, "loss": 0.9109, "step": 4661 }, { "epoch": 0.9, "grad_norm": 1.083490848421119, "learning_rate": 5.525265932341984e-07, "loss": 0.8296, "step": 4662 }, { "epoch": 0.9, "grad_norm": 1.234956609593786, "learning_rate": 5.504859594893475e-07, "loss": 0.8552, "step": 4663 }, { "epoch": 0.9, "grad_norm": 0.9965799216930784, "learning_rate": 5.484489943712013e-07, "loss": 0.8542, "step": 4664 }, { "epoch": 0.9, "grad_norm": 1.076564858126722, "learning_rate": 5.464156986705826e-07, "loss": 0.8257, "step": 4665 }, { "epoch": 0.9, "grad_norm": 1.0379173476323813, "learning_rate": 5.443860731768869e-07, "loss": 0.8232, "step": 4666 }, { "epoch": 0.9, "grad_norm": 0.8874503962108051, "learning_rate": 5.423601186780836e-07, "loss": 0.6112, "step": 4667 }, { "epoch": 0.9, "grad_norm": 1.0223324676996608, "learning_rate": 5.403378359607181e-07, "loss": 0.8445, "step": 4668 }, { "epoch": 0.9, "grad_norm": 1.0910139303701292, "learning_rate": 5.383192258099113e-07, "loss": 0.8109, "step": 4669 }, { "epoch": 0.9, "grad_norm": 0.99313335092241, "learning_rate": 5.36304289009355e-07, "loss": 0.8616, "step": 4670 }, { "epoch": 0.9, "grad_norm": 1.1356261988311631, "learning_rate": 5.342930263413193e-07, "loss": 0.8569, "step": 4671 }, { "epoch": 0.9, "grad_norm": 1.1329977607511326, "learning_rate": 5.322854385866439e-07, "loss": 0.8638, "step": 4672 }, { "epoch": 0.9, "grad_norm": 0.6154917492743239, "learning_rate": 5.302815265247452e-07, "loss": 0.3215, "step": 4673 }, { "epoch": 0.9, "grad_norm": 0.9794207306314129, "learning_rate": 5.282812909336077e-07, "loss": 0.7717, "step": 4674 }, { "epoch": 0.9, "grad_norm": 1.0185838520980421, "learning_rate": 5.262847325897968e-07, "loss": 0.8645, "step": 4675 }, { "epoch": 0.9, "grad_norm": 1.1993337556276626, "learning_rate": 5.242918522684392e-07, "loss": 0.8198, "step": 4676 }, { "epoch": 0.9, "grad_norm": 1.0303913587955078, "learning_rate": 5.22302650743245e-07, "loss": 0.833, "step": 4677 }, { "epoch": 0.9, "grad_norm": 1.06767867512818, "learning_rate": 5.203171287864872e-07, "loss": 0.8665, "step": 4678 }, { "epoch": 0.9, "grad_norm": 0.9236795757617668, "learning_rate": 5.183352871690162e-07, "loss": 0.8901, "step": 4679 }, { "epoch": 0.9, "grad_norm": 0.9649784870269422, "learning_rate": 5.163571266602485e-07, "loss": 0.8093, "step": 4680 }, { "epoch": 0.9, "grad_norm": 1.0720760452765639, "learning_rate": 5.143826480281778e-07, "loss": 0.8767, "step": 4681 }, { "epoch": 0.9, "grad_norm": 0.8939877351859231, "learning_rate": 5.124118520393606e-07, "loss": 0.5858, "step": 4682 }, { "epoch": 0.9, "grad_norm": 1.1157808960586988, "learning_rate": 5.104447394589295e-07, "loss": 0.8708, "step": 4683 }, { "epoch": 0.9, "grad_norm": 0.8265347521552292, "learning_rate": 5.084813110505871e-07, "loss": 0.5663, "step": 4684 }, { "epoch": 0.9, "grad_norm": 1.0255531666991602, "learning_rate": 5.065215675766023e-07, "loss": 0.8303, "step": 4685 }, { "epoch": 0.9, "grad_norm": 1.0910806677085703, "learning_rate": 5.045655097978131e-07, "loss": 0.8091, "step": 4686 }, { "epoch": 0.9, "grad_norm": 0.9514639311078101, "learning_rate": 5.026131384736321e-07, "loss": 0.8364, "step": 4687 }, { "epoch": 0.9, "grad_norm": 0.9214361515010839, "learning_rate": 5.006644543620342e-07, "loss": 0.8335, "step": 4688 }, { "epoch": 0.9, "grad_norm": 0.7903187107126476, "learning_rate": 4.987194582195687e-07, "loss": 0.5438, "step": 4689 }, { "epoch": 0.9, "grad_norm": 1.0482814139121384, "learning_rate": 4.967781508013459e-07, "loss": 0.7947, "step": 4690 }, { "epoch": 0.9, "grad_norm": 0.975943417059779, "learning_rate": 4.948405328610506e-07, "loss": 0.7695, "step": 4691 }, { "epoch": 0.9, "grad_norm": 0.9741888065753378, "learning_rate": 4.929066051509346e-07, "loss": 0.8293, "step": 4692 }, { "epoch": 0.9, "grad_norm": 0.9770147270726128, "learning_rate": 4.909763684218116e-07, "loss": 0.8682, "step": 4693 }, { "epoch": 0.9, "grad_norm": 1.185850993487826, "learning_rate": 4.890498234230689e-07, "loss": 0.8711, "step": 4694 }, { "epoch": 0.9, "grad_norm": 0.9771293880653836, "learning_rate": 4.871269709026561e-07, "loss": 0.8264, "step": 4695 }, { "epoch": 0.9, "grad_norm": 0.8597941508927207, "learning_rate": 4.852078116070902e-07, "loss": 0.5847, "step": 4696 }, { "epoch": 0.9, "grad_norm": 1.0745061881051226, "learning_rate": 4.832923462814565e-07, "loss": 0.8506, "step": 4697 }, { "epoch": 0.9, "grad_norm": 0.9528436831885608, "learning_rate": 4.813805756694035e-07, "loss": 0.8572, "step": 4698 }, { "epoch": 0.9, "grad_norm": 0.9616968284788265, "learning_rate": 4.794725005131462e-07, "loss": 0.8464, "step": 4699 }, { "epoch": 0.9, "grad_norm": 1.1638274539554554, "learning_rate": 4.775681215534656e-07, "loss": 0.8752, "step": 4700 }, { "epoch": 0.9, "grad_norm": 1.0046651691868378, "learning_rate": 4.7566743952970894e-07, "loss": 0.8467, "step": 4701 }, { "epoch": 0.9, "grad_norm": 0.8588973186201002, "learning_rate": 4.7377045517978173e-07, "loss": 0.5997, "step": 4702 }, { "epoch": 0.9, "grad_norm": 0.9352584210759145, "learning_rate": 4.7187716924016355e-07, "loss": 0.8906, "step": 4703 }, { "epoch": 0.9, "grad_norm": 0.9217592653923953, "learning_rate": 4.6998758244588995e-07, "loss": 0.8418, "step": 4704 }, { "epoch": 0.91, "grad_norm": 1.039235230099068, "learning_rate": 4.6810169553056616e-07, "loss": 0.8015, "step": 4705 }, { "epoch": 0.91, "grad_norm": 1.0108606217282898, "learning_rate": 4.662195092263566e-07, "loss": 0.8708, "step": 4706 }, { "epoch": 0.91, "grad_norm": 1.0935386408793404, "learning_rate": 4.643410242639912e-07, "loss": 0.8755, "step": 4707 }, { "epoch": 0.91, "grad_norm": 0.9942209436397896, "learning_rate": 4.6246624137276206e-07, "loss": 0.7659, "step": 4708 }, { "epoch": 0.91, "grad_norm": 1.0413695381501762, "learning_rate": 4.605951612805237e-07, "loss": 0.8153, "step": 4709 }, { "epoch": 0.91, "grad_norm": 1.0222835614631862, "learning_rate": 4.587277847136984e-07, "loss": 0.8369, "step": 4710 }, { "epoch": 0.91, "grad_norm": 1.1110125950221472, "learning_rate": 4.568641123972606e-07, "loss": 0.8319, "step": 4711 }, { "epoch": 0.91, "grad_norm": 1.0158579341450915, "learning_rate": 4.550041450547549e-07, "loss": 0.8303, "step": 4712 }, { "epoch": 0.91, "grad_norm": 1.0655310007451602, "learning_rate": 4.5314788340828365e-07, "loss": 0.8704, "step": 4713 }, { "epoch": 0.91, "grad_norm": 1.209187180174404, "learning_rate": 4.512953281785104e-07, "loss": 0.8638, "step": 4714 }, { "epoch": 0.91, "grad_norm": 0.8929488787532246, "learning_rate": 4.494464800846654e-07, "loss": 0.5894, "step": 4715 }, { "epoch": 0.91, "grad_norm": 1.1782839816828412, "learning_rate": 4.476013398445289e-07, "loss": 0.861, "step": 4716 }, { "epoch": 0.91, "grad_norm": 0.9850307244480321, "learning_rate": 4.4575990817445234e-07, "loss": 0.8215, "step": 4717 }, { "epoch": 0.91, "grad_norm": 1.0135550756683809, "learning_rate": 4.4392218578934164e-07, "loss": 0.8552, "step": 4718 }, { "epoch": 0.91, "grad_norm": 0.7757739238522742, "learning_rate": 4.4208817340266385e-07, "loss": 0.5595, "step": 4719 }, { "epoch": 0.91, "grad_norm": 1.0110557971467864, "learning_rate": 4.4025787172644495e-07, "loss": 0.8401, "step": 4720 }, { "epoch": 0.91, "grad_norm": 0.9768010539510316, "learning_rate": 4.384312814712721e-07, "loss": 0.8687, "step": 4721 }, { "epoch": 0.91, "grad_norm": 1.0443933012360864, "learning_rate": 4.366084033462914e-07, "loss": 0.8188, "step": 4722 }, { "epoch": 0.91, "grad_norm": 1.6240734123046328, "learning_rate": 4.3478923805920335e-07, "loss": 0.8831, "step": 4723 }, { "epoch": 0.91, "grad_norm": 1.0735097759593226, "learning_rate": 4.329737863162753e-07, "loss": 0.843, "step": 4724 }, { "epoch": 0.91, "grad_norm": 1.146089229955939, "learning_rate": 4.311620488223256e-07, "loss": 0.8148, "step": 4725 }, { "epoch": 0.91, "grad_norm": 1.0846573955911472, "learning_rate": 4.2935402628073166e-07, "loss": 0.8533, "step": 4726 }, { "epoch": 0.91, "grad_norm": 1.096048794838675, "learning_rate": 4.27549719393433e-07, "loss": 0.8645, "step": 4727 }, { "epoch": 0.91, "grad_norm": 1.0203333203563218, "learning_rate": 4.2574912886092166e-07, "loss": 0.8601, "step": 4728 }, { "epoch": 0.91, "grad_norm": 0.9454544431002758, "learning_rate": 4.239522553822495e-07, "loss": 0.78, "step": 4729 }, { "epoch": 0.91, "grad_norm": 0.9534394563101516, "learning_rate": 4.221590996550251e-07, "loss": 0.8009, "step": 4730 }, { "epoch": 0.91, "grad_norm": 1.083883642980561, "learning_rate": 4.203696623754139e-07, "loss": 0.7954, "step": 4731 }, { "epoch": 0.91, "grad_norm": 0.9036425189855031, "learning_rate": 4.1858394423813563e-07, "loss": 0.791, "step": 4732 }, { "epoch": 0.91, "grad_norm": 1.1679877857543628, "learning_rate": 4.1680194593646696e-07, "loss": 0.8552, "step": 4733 }, { "epoch": 0.91, "grad_norm": 1.091448220872395, "learning_rate": 4.1502366816224327e-07, "loss": 0.9087, "step": 4734 }, { "epoch": 0.91, "grad_norm": 1.0504865643067995, "learning_rate": 4.1324911160585014e-07, "loss": 0.8232, "step": 4735 }, { "epoch": 0.91, "grad_norm": 1.085478026582231, "learning_rate": 4.1147827695623643e-07, "loss": 0.8918, "step": 4736 }, { "epoch": 0.91, "grad_norm": 1.0705004597954066, "learning_rate": 4.097111649008967e-07, "loss": 0.8462, "step": 4737 }, { "epoch": 0.91, "grad_norm": 0.9864799753232059, "learning_rate": 4.0794777612588543e-07, "loss": 0.8152, "step": 4738 }, { "epoch": 0.91, "grad_norm": 0.9880767210590689, "learning_rate": 4.061881113158117e-07, "loss": 0.8175, "step": 4739 }, { "epoch": 0.91, "grad_norm": 1.1239748682454076, "learning_rate": 4.044321711538368e-07, "loss": 0.8606, "step": 4740 }, { "epoch": 0.91, "grad_norm": 1.1490021780337225, "learning_rate": 4.02679956321681e-07, "loss": 0.9021, "step": 4741 }, { "epoch": 0.91, "grad_norm": 0.8076707104812318, "learning_rate": 4.00931467499609e-07, "loss": 0.5898, "step": 4742 }, { "epoch": 0.91, "grad_norm": 1.1147506210830058, "learning_rate": 3.9918670536644776e-07, "loss": 0.8457, "step": 4743 }, { "epoch": 0.91, "grad_norm": 1.052821448698147, "learning_rate": 3.974456705995733e-07, "loss": 0.8735, "step": 4744 }, { "epoch": 0.91, "grad_norm": 1.0036209803704714, "learning_rate": 3.9570836387491487e-07, "loss": 0.8149, "step": 4745 }, { "epoch": 0.91, "grad_norm": 1.1928164613652728, "learning_rate": 3.9397478586695513e-07, "loss": 0.8611, "step": 4746 }, { "epoch": 0.91, "grad_norm": 0.9550951764080465, "learning_rate": 3.9224493724872915e-07, "loss": 0.8171, "step": 4747 }, { "epoch": 0.91, "grad_norm": 1.020632560077683, "learning_rate": 3.90518818691823e-07, "loss": 0.8479, "step": 4748 }, { "epoch": 0.91, "grad_norm": 1.11671322478938, "learning_rate": 3.8879643086637384e-07, "loss": 0.886, "step": 4749 }, { "epoch": 0.91, "grad_norm": 1.0222482404252842, "learning_rate": 3.8707777444107697e-07, "loss": 0.8706, "step": 4750 }, { "epoch": 0.91, "grad_norm": 0.9823487296162334, "learning_rate": 3.8536285008316854e-07, "loss": 0.8274, "step": 4751 }, { "epoch": 0.91, "grad_norm": 1.1278361533549848, "learning_rate": 3.8365165845844266e-07, "loss": 0.8467, "step": 4752 }, { "epoch": 0.91, "grad_norm": 1.074537076384774, "learning_rate": 3.819442002312457e-07, "loss": 0.8672, "step": 4753 }, { "epoch": 0.91, "grad_norm": 1.0696544819430405, "learning_rate": 3.8024047606446736e-07, "loss": 0.8547, "step": 4754 }, { "epoch": 0.91, "grad_norm": 1.0363725649782343, "learning_rate": 3.785404866195552e-07, "loss": 0.8008, "step": 4755 }, { "epoch": 0.91, "grad_norm": 1.0652388855080117, "learning_rate": 3.768442325565036e-07, "loss": 0.8745, "step": 4756 }, { "epoch": 0.92, "grad_norm": 1.1366112238703472, "learning_rate": 3.751517145338546e-07, "loss": 0.8491, "step": 4757 }, { "epoch": 0.92, "grad_norm": 1.0601230440969307, "learning_rate": 3.7346293320870363e-07, "loss": 0.8413, "step": 4758 }, { "epoch": 0.92, "grad_norm": 1.0292091474751845, "learning_rate": 3.717778892366941e-07, "loss": 0.8257, "step": 4759 }, { "epoch": 0.92, "grad_norm": 1.0731111089358483, "learning_rate": 3.700965832720171e-07, "loss": 0.8416, "step": 4760 }, { "epoch": 0.92, "grad_norm": 0.9889791029899134, "learning_rate": 3.684190159674117e-07, "loss": 0.8379, "step": 4761 }, { "epoch": 0.92, "grad_norm": 0.9110510051897236, "learning_rate": 3.6674518797417236e-07, "loss": 0.8215, "step": 4762 }, { "epoch": 0.92, "grad_norm": 1.1269659935383445, "learning_rate": 3.6507509994213155e-07, "loss": 0.855, "step": 4763 }, { "epoch": 0.92, "grad_norm": 0.8033201567192678, "learning_rate": 3.6340875251967946e-07, "loss": 0.5875, "step": 4764 }, { "epoch": 0.92, "grad_norm": 0.9266331130779318, "learning_rate": 3.617461463537464e-07, "loss": 0.8245, "step": 4765 }, { "epoch": 0.92, "grad_norm": 0.8049745434003021, "learning_rate": 3.6008728208981157e-07, "loss": 0.5944, "step": 4766 }, { "epoch": 0.92, "grad_norm": 0.9906443613831054, "learning_rate": 3.5843216037190873e-07, "loss": 0.8408, "step": 4767 }, { "epoch": 0.92, "grad_norm": 1.1323537584163594, "learning_rate": 3.5678078184260834e-07, "loss": 0.8628, "step": 4768 }, { "epoch": 0.92, "grad_norm": 1.040244058881049, "learning_rate": 3.5513314714303524e-07, "loss": 0.8562, "step": 4769 }, { "epoch": 0.92, "grad_norm": 1.0977223069280528, "learning_rate": 3.5348925691285675e-07, "loss": 0.8479, "step": 4770 }, { "epoch": 0.92, "grad_norm": 1.1786416949182503, "learning_rate": 3.518491117902878e-07, "loss": 0.8396, "step": 4771 }, { "epoch": 0.92, "grad_norm": 0.985474830427308, "learning_rate": 3.502127124120891e-07, "loss": 0.8682, "step": 4772 }, { "epoch": 0.92, "grad_norm": 1.0915264922314878, "learning_rate": 3.48580059413568e-07, "loss": 0.8223, "step": 4773 }, { "epoch": 0.92, "grad_norm": 1.0954222718682838, "learning_rate": 3.4695115342857524e-07, "loss": 0.845, "step": 4774 }, { "epoch": 0.92, "grad_norm": 1.046591390706889, "learning_rate": 3.4532599508950826e-07, "loss": 0.8694, "step": 4775 }, { "epoch": 0.92, "grad_norm": 1.0030477885139535, "learning_rate": 3.437045850273113e-07, "loss": 0.8777, "step": 4776 }, { "epoch": 0.92, "grad_norm": 1.006780931952518, "learning_rate": 3.420869238714708e-07, "loss": 0.559, "step": 4777 }, { "epoch": 0.92, "grad_norm": 0.8443008474682044, "learning_rate": 3.404730122500155e-07, "loss": 0.555, "step": 4778 }, { "epoch": 0.92, "grad_norm": 0.8811924638585826, "learning_rate": 3.3886285078952753e-07, "loss": 0.8105, "step": 4779 }, { "epoch": 0.92, "grad_norm": 1.1230168462968007, "learning_rate": 3.3725644011512125e-07, "loss": 0.8433, "step": 4780 }, { "epoch": 0.92, "grad_norm": 0.982246755639689, "learning_rate": 3.356537808504634e-07, "loss": 0.8872, "step": 4781 }, { "epoch": 0.92, "grad_norm": 1.063865834706782, "learning_rate": 3.3405487361776177e-07, "loss": 0.8259, "step": 4782 }, { "epoch": 0.92, "grad_norm": 0.940073833549698, "learning_rate": 3.3245971903776654e-07, "loss": 0.8044, "step": 4783 }, { "epoch": 0.92, "grad_norm": 1.1797929751772787, "learning_rate": 3.308683177297711e-07, "loss": 0.8496, "step": 4784 }, { "epoch": 0.92, "grad_norm": 0.787832649956284, "learning_rate": 3.292806703116125e-07, "loss": 0.5784, "step": 4785 }, { "epoch": 0.92, "grad_norm": 0.9567988855620835, "learning_rate": 3.2769677739966975e-07, "loss": 0.8608, "step": 4786 }, { "epoch": 0.92, "grad_norm": 1.0153466198489445, "learning_rate": 3.2611663960886665e-07, "loss": 0.8577, "step": 4787 }, { "epoch": 0.92, "grad_norm": 0.9776449828493541, "learning_rate": 3.245402575526646e-07, "loss": 0.8389, "step": 4788 }, { "epoch": 0.92, "grad_norm": 1.1266471906808537, "learning_rate": 3.2296763184306965e-07, "loss": 0.8226, "step": 4789 }, { "epoch": 0.92, "grad_norm": 0.8947379209783817, "learning_rate": 3.2139876309063233e-07, "loss": 0.587, "step": 4790 }, { "epoch": 0.92, "grad_norm": 1.0333543582953681, "learning_rate": 3.198336519044376e-07, "loss": 0.885, "step": 4791 }, { "epoch": 0.92, "grad_norm": 1.0788389696622367, "learning_rate": 3.182722988921161e-07, "loss": 0.8389, "step": 4792 }, { "epoch": 0.92, "grad_norm": 0.9672314013560226, "learning_rate": 3.167147046598418e-07, "loss": 0.8745, "step": 4793 }, { "epoch": 0.92, "grad_norm": 0.9783936879520242, "learning_rate": 3.151608698123232e-07, "loss": 0.8596, "step": 4794 }, { "epoch": 0.92, "grad_norm": 1.1207121874081198, "learning_rate": 3.1361079495281443e-07, "loss": 0.8252, "step": 4795 }, { "epoch": 0.92, "grad_norm": 1.1189462703521618, "learning_rate": 3.1206448068310635e-07, "loss": 0.8562, "step": 4796 }, { "epoch": 0.92, "grad_norm": 0.9812518428495515, "learning_rate": 3.1052192760353316e-07, "loss": 0.7854, "step": 4797 }, { "epoch": 0.92, "grad_norm": 1.0705668729469269, "learning_rate": 3.0898313631296586e-07, "loss": 0.833, "step": 4798 }, { "epoch": 0.92, "grad_norm": 1.1046026686432373, "learning_rate": 3.0744810740881646e-07, "loss": 0.8164, "step": 4799 }, { "epoch": 0.92, "grad_norm": 0.9720904636957833, "learning_rate": 3.0591684148703617e-07, "loss": 0.8684, "step": 4800 }, { "epoch": 0.92, "grad_norm": 1.0564978563913594, "learning_rate": 3.043893391421149e-07, "loss": 0.8679, "step": 4801 }, { "epoch": 0.92, "grad_norm": 0.7942313629711174, "learning_rate": 3.0286560096708275e-07, "loss": 0.5544, "step": 4802 }, { "epoch": 0.92, "grad_norm": 1.059699445537703, "learning_rate": 3.013456275535054e-07, "loss": 0.811, "step": 4803 }, { "epoch": 0.92, "grad_norm": 1.0638702336508117, "learning_rate": 2.998294194914897e-07, "loss": 0.7793, "step": 4804 }, { "epoch": 0.92, "grad_norm": 1.1706344600822618, "learning_rate": 2.983169773696815e-07, "loss": 0.8533, "step": 4805 }, { "epoch": 0.92, "grad_norm": 1.0450885849169955, "learning_rate": 2.968083017752599e-07, "loss": 0.8385, "step": 4806 }, { "epoch": 0.92, "grad_norm": 1.0946200792860457, "learning_rate": 2.953033932939464e-07, "loss": 0.894, "step": 4807 }, { "epoch": 0.92, "grad_norm": 1.0518315826426023, "learning_rate": 2.938022525099982e-07, "loss": 0.8347, "step": 4808 }, { "epoch": 0.93, "grad_norm": 1.1887213269598533, "learning_rate": 2.9230488000621003e-07, "loss": 0.824, "step": 4809 }, { "epoch": 0.93, "grad_norm": 1.116651298297892, "learning_rate": 2.908112763639137e-07, "loss": 0.8164, "step": 4810 }, { "epoch": 0.93, "grad_norm": 1.018897404667786, "learning_rate": 2.8932144216297643e-07, "loss": 0.8687, "step": 4811 }, { "epoch": 0.93, "grad_norm": 1.0054560461460715, "learning_rate": 2.878353779818044e-07, "loss": 0.8557, "step": 4812 }, { "epoch": 0.93, "grad_norm": 1.012120178007007, "learning_rate": 2.863530843973372e-07, "loss": 0.84, "step": 4813 }, { "epoch": 0.93, "grad_norm": 1.0891602624256784, "learning_rate": 2.848745619850546e-07, "loss": 0.8535, "step": 4814 }, { "epoch": 0.93, "grad_norm": 0.917512702527924, "learning_rate": 2.833998113189662e-07, "loss": 0.5676, "step": 4815 }, { "epoch": 0.93, "grad_norm": 1.0321806009385344, "learning_rate": 2.8192883297162634e-07, "loss": 0.8435, "step": 4816 }, { "epoch": 0.93, "grad_norm": 1.0757880309527683, "learning_rate": 2.804616275141148e-07, "loss": 0.8169, "step": 4817 }, { "epoch": 0.93, "grad_norm": 1.1004133311265967, "learning_rate": 2.7899819551605256e-07, "loss": 0.8616, "step": 4818 }, { "epoch": 0.93, "grad_norm": 1.1502534917367189, "learning_rate": 2.7753853754559634e-07, "loss": 0.8199, "step": 4819 }, { "epoch": 0.93, "grad_norm": 0.8275979951503526, "learning_rate": 2.760826541694328e-07, "loss": 0.5804, "step": 4820 }, { "epoch": 0.93, "grad_norm": 0.8970557061726937, "learning_rate": 2.746305459527876e-07, "loss": 0.592, "step": 4821 }, { "epoch": 0.93, "grad_norm": 0.9885861935597309, "learning_rate": 2.7318221345941865e-07, "loss": 0.8633, "step": 4822 }, { "epoch": 0.93, "grad_norm": 0.8613870611647026, "learning_rate": 2.717376572516184e-07, "loss": 0.6073, "step": 4823 }, { "epoch": 0.93, "grad_norm": 0.95772107319125, "learning_rate": 2.7029687789021377e-07, "loss": 0.8037, "step": 4824 }, { "epoch": 0.93, "grad_norm": 0.9630530464112025, "learning_rate": 2.688598759345651e-07, "loss": 0.7891, "step": 4825 }, { "epoch": 0.93, "grad_norm": 0.9156966019892714, "learning_rate": 2.67426651942565e-07, "loss": 0.7944, "step": 4826 }, { "epoch": 0.93, "grad_norm": 0.9807623351483648, "learning_rate": 2.659972064706406e-07, "loss": 0.8634, "step": 4827 }, { "epoch": 0.93, "grad_norm": 0.9928620471412757, "learning_rate": 2.645715400737536e-07, "loss": 0.8257, "step": 4828 }, { "epoch": 0.93, "grad_norm": 1.028383574346676, "learning_rate": 2.631496533053934e-07, "loss": 0.8445, "step": 4829 }, { "epoch": 0.93, "grad_norm": 0.9884168144116215, "learning_rate": 2.6173154671758847e-07, "loss": 0.8623, "step": 4830 }, { "epoch": 0.93, "grad_norm": 1.2304838845669481, "learning_rate": 2.603172208608962e-07, "loss": 0.8035, "step": 4831 }, { "epoch": 0.93, "grad_norm": 1.0442829195048136, "learning_rate": 2.589066762844039e-07, "loss": 0.8914, "step": 4832 }, { "epoch": 0.93, "grad_norm": 0.7529004438574343, "learning_rate": 2.57499913535737e-07, "loss": 0.5855, "step": 4833 }, { "epoch": 0.93, "grad_norm": 1.1423605162483985, "learning_rate": 2.5609693316104745e-07, "loss": 0.8911, "step": 4834 }, { "epoch": 0.93, "grad_norm": 1.0625524319481179, "learning_rate": 2.5469773570502063e-07, "loss": 0.8511, "step": 4835 }, { "epoch": 0.93, "grad_norm": 1.0634530824988933, "learning_rate": 2.5330232171087433e-07, "loss": 0.8796, "step": 4836 }, { "epoch": 0.93, "grad_norm": 1.0269150750658997, "learning_rate": 2.51910691720354e-07, "loss": 0.821, "step": 4837 }, { "epoch": 0.93, "grad_norm": 1.093279010828475, "learning_rate": 2.5052284627374077e-07, "loss": 0.8748, "step": 4838 }, { "epoch": 0.93, "grad_norm": 1.046294511336152, "learning_rate": 2.491387859098426e-07, "loss": 0.8857, "step": 4839 }, { "epoch": 0.93, "grad_norm": 1.0803503364752303, "learning_rate": 2.477585111659997e-07, "loss": 0.8691, "step": 4840 }, { "epoch": 0.93, "grad_norm": 1.030932584751687, "learning_rate": 2.463820225780811e-07, "loss": 0.8647, "step": 4841 }, { "epoch": 0.93, "grad_norm": 0.9389306083008224, "learning_rate": 2.4500932068049046e-07, "loss": 0.7834, "step": 4842 }, { "epoch": 0.93, "grad_norm": 1.16912762774563, "learning_rate": 2.4364040600615477e-07, "loss": 0.8618, "step": 4843 }, { "epoch": 0.93, "grad_norm": 0.9723703581111982, "learning_rate": 2.422752790865346e-07, "loss": 0.8267, "step": 4844 }, { "epoch": 0.93, "grad_norm": 0.9404108360268818, "learning_rate": 2.409139404516203e-07, "loss": 0.8325, "step": 4845 }, { "epoch": 0.93, "grad_norm": 1.1333831582953269, "learning_rate": 2.3955639062992696e-07, "loss": 0.8557, "step": 4846 }, { "epoch": 0.93, "grad_norm": 1.0320079388339252, "learning_rate": 2.3820263014850741e-07, "loss": 0.8567, "step": 4847 }, { "epoch": 0.93, "grad_norm": 0.9785602233673104, "learning_rate": 2.3685265953293345e-07, "loss": 0.8105, "step": 4848 }, { "epoch": 0.93, "grad_norm": 1.0800750249073177, "learning_rate": 2.3550647930731362e-07, "loss": 0.812, "step": 4849 }, { "epoch": 0.93, "grad_norm": 1.0164626067321128, "learning_rate": 2.3416408999427876e-07, "loss": 0.8213, "step": 4850 }, { "epoch": 0.93, "grad_norm": 0.9273460278085374, "learning_rate": 2.3282549211499307e-07, "loss": 0.8179, "step": 4851 }, { "epoch": 0.93, "grad_norm": 1.010998215014752, "learning_rate": 2.3149068618914417e-07, "loss": 0.8053, "step": 4852 }, { "epoch": 0.93, "grad_norm": 1.1875860081523264, "learning_rate": 2.3015967273494867e-07, "loss": 0.845, "step": 4853 }, { "epoch": 0.93, "grad_norm": 1.1746517210235783, "learning_rate": 2.2883245226915652e-07, "loss": 0.9082, "step": 4854 }, { "epoch": 0.93, "grad_norm": 0.9132762713108973, "learning_rate": 2.2750902530703667e-07, "loss": 0.821, "step": 4855 }, { "epoch": 0.93, "grad_norm": 1.0136842723457673, "learning_rate": 2.2618939236238924e-07, "loss": 0.8414, "step": 4856 }, { "epoch": 0.93, "grad_norm": 0.9438460160570256, "learning_rate": 2.2487355394754328e-07, "loss": 0.842, "step": 4857 }, { "epoch": 0.93, "grad_norm": 1.0416104252851455, "learning_rate": 2.2356151057334908e-07, "loss": 0.847, "step": 4858 }, { "epoch": 0.93, "grad_norm": 0.9504401405149728, "learning_rate": 2.2225326274919135e-07, "loss": 0.8323, "step": 4859 }, { "epoch": 0.93, "grad_norm": 0.92603964961826, "learning_rate": 2.209488109829727e-07, "loss": 0.8057, "step": 4860 }, { "epoch": 0.94, "grad_norm": 1.1582091658597116, "learning_rate": 2.196481557811303e-07, "loss": 0.8931, "step": 4861 }, { "epoch": 0.94, "grad_norm": 1.0808926954603189, "learning_rate": 2.1835129764861907e-07, "loss": 0.8206, "step": 4862 }, { "epoch": 0.94, "grad_norm": 1.0149054668701032, "learning_rate": 2.1705823708892737e-07, "loss": 0.8318, "step": 4863 }, { "epoch": 0.94, "grad_norm": 1.1604019307889375, "learning_rate": 2.1576897460406477e-07, "loss": 0.8274, "step": 4864 }, { "epoch": 0.94, "grad_norm": 1.1320977206538823, "learning_rate": 2.144835106945664e-07, "loss": 0.9329, "step": 4865 }, { "epoch": 0.94, "grad_norm": 0.9896844156353156, "learning_rate": 2.1320184585949532e-07, "loss": 0.8044, "step": 4866 }, { "epoch": 0.94, "grad_norm": 1.0070614473180122, "learning_rate": 2.119239805964357e-07, "loss": 0.8408, "step": 4867 }, { "epoch": 0.94, "grad_norm": 1.0787735475013676, "learning_rate": 2.106499154015018e-07, "loss": 0.8733, "step": 4868 }, { "epoch": 0.94, "grad_norm": 1.0893418682263327, "learning_rate": 2.0937965076932576e-07, "loss": 0.8303, "step": 4869 }, { "epoch": 0.94, "grad_norm": 0.9919420707519633, "learning_rate": 2.0811318719307194e-07, "loss": 0.8752, "step": 4870 }, { "epoch": 0.94, "grad_norm": 1.0080950402401574, "learning_rate": 2.0685052516442373e-07, "loss": 0.8254, "step": 4871 }, { "epoch": 0.94, "grad_norm": 0.9958351679664544, "learning_rate": 2.0559166517358787e-07, "loss": 0.8435, "step": 4872 }, { "epoch": 0.94, "grad_norm": 1.0815616541469004, "learning_rate": 2.0433660770930009e-07, "loss": 0.8152, "step": 4873 }, { "epoch": 0.94, "grad_norm": 1.0640431896528715, "learning_rate": 2.0308535325881616e-07, "loss": 0.8103, "step": 4874 }, { "epoch": 0.94, "grad_norm": 1.097410472109107, "learning_rate": 2.0183790230791532e-07, "loss": 0.8323, "step": 4875 }, { "epoch": 0.94, "grad_norm": 1.0762729735752494, "learning_rate": 2.0059425534090128e-07, "loss": 0.9041, "step": 4876 }, { "epoch": 0.94, "grad_norm": 1.0840181331489969, "learning_rate": 1.9935441284059998e-07, "loss": 0.8767, "step": 4877 }, { "epoch": 0.94, "grad_norm": 1.0883845415350253, "learning_rate": 1.981183752883631e-07, "loss": 0.863, "step": 4878 }, { "epoch": 0.94, "grad_norm": 0.9323907398753646, "learning_rate": 1.9688614316406006e-07, "loss": 0.8201, "step": 4879 }, { "epoch": 0.94, "grad_norm": 1.2158581589932491, "learning_rate": 1.9565771694608937e-07, "loss": 0.8247, "step": 4880 }, { "epoch": 0.94, "grad_norm": 1.0042452957478059, "learning_rate": 1.9443309711136393e-07, "loss": 0.8503, "step": 4881 }, { "epoch": 0.94, "grad_norm": 1.2001175603054897, "learning_rate": 1.9321228413532788e-07, "loss": 0.7766, "step": 4882 }, { "epoch": 0.94, "grad_norm": 1.0016493487846625, "learning_rate": 1.9199527849194098e-07, "loss": 0.8477, "step": 4883 }, { "epoch": 0.94, "grad_norm": 0.788096597426878, "learning_rate": 1.907820806536842e-07, "loss": 0.5654, "step": 4884 }, { "epoch": 0.94, "grad_norm": 1.1327436068566652, "learning_rate": 1.895726910915663e-07, "loss": 0.8853, "step": 4885 }, { "epoch": 0.94, "grad_norm": 1.048626901727517, "learning_rate": 1.883671102751128e-07, "loss": 0.8474, "step": 4886 }, { "epoch": 0.94, "grad_norm": 1.1671373883498735, "learning_rate": 1.8716533867237153e-07, "loss": 0.8683, "step": 4887 }, { "epoch": 0.94, "grad_norm": 1.0945452210055757, "learning_rate": 1.859673767499115e-07, "loss": 0.7859, "step": 4888 }, { "epoch": 0.94, "grad_norm": 1.3837786526379299, "learning_rate": 1.847732249728218e-07, "loss": 0.7695, "step": 4889 }, { "epoch": 0.94, "grad_norm": 0.9743999776330721, "learning_rate": 1.83582883804716e-07, "loss": 0.8977, "step": 4890 }, { "epoch": 0.94, "grad_norm": 0.9318470476296146, "learning_rate": 1.8239635370772223e-07, "loss": 0.791, "step": 4891 }, { "epoch": 0.94, "grad_norm": 1.0449136625617832, "learning_rate": 1.8121363514249534e-07, "loss": 0.813, "step": 4892 }, { "epoch": 0.94, "grad_norm": 1.215918131995196, "learning_rate": 1.8003472856820469e-07, "loss": 0.8047, "step": 4893 }, { "epoch": 0.94, "grad_norm": 0.9551037232063597, "learning_rate": 1.7885963444254528e-07, "loss": 0.886, "step": 4894 }, { "epoch": 0.94, "grad_norm": 0.9685952452089076, "learning_rate": 1.7768835322172552e-07, "loss": 0.8029, "step": 4895 }, { "epoch": 0.94, "grad_norm": 1.1107124496602365, "learning_rate": 1.7652088536048052e-07, "loss": 0.8237, "step": 4896 }, { "epoch": 0.94, "grad_norm": 1.0133254054225604, "learning_rate": 1.7535723131206106e-07, "loss": 0.8521, "step": 4897 }, { "epoch": 0.94, "grad_norm": 0.9756865425664749, "learning_rate": 1.7419739152823468e-07, "loss": 0.8169, "step": 4898 }, { "epoch": 0.94, "grad_norm": 1.0940999206799433, "learning_rate": 1.7304136645929448e-07, "loss": 0.8325, "step": 4899 }, { "epoch": 0.94, "grad_norm": 0.7981428390334698, "learning_rate": 1.7188915655404814e-07, "loss": 0.5474, "step": 4900 }, { "epoch": 0.94, "grad_norm": 0.9639345603758194, "learning_rate": 1.707407622598223e-07, "loss": 0.812, "step": 4901 }, { "epoch": 0.94, "grad_norm": 0.9651952900175012, "learning_rate": 1.695961840224636e-07, "loss": 0.8472, "step": 4902 }, { "epoch": 0.94, "grad_norm": 1.0501584838590996, "learning_rate": 1.6845542228633772e-07, "loss": 0.876, "step": 4903 }, { "epoch": 0.94, "grad_norm": 1.0501980525852417, "learning_rate": 1.6731847749432705e-07, "loss": 0.7715, "step": 4904 }, { "epoch": 0.94, "grad_norm": 1.0120452496475938, "learning_rate": 1.6618535008783075e-07, "loss": 0.8555, "step": 4905 }, { "epoch": 0.94, "grad_norm": 1.0046063025116296, "learning_rate": 1.6505604050677249e-07, "loss": 0.8635, "step": 4906 }, { "epoch": 0.94, "grad_norm": 1.0924258305662768, "learning_rate": 1.6393054918958373e-07, "loss": 0.8794, "step": 4907 }, { "epoch": 0.94, "grad_norm": 0.9989022815862855, "learning_rate": 1.6280887657322276e-07, "loss": 0.9199, "step": 4908 }, { "epoch": 0.94, "grad_norm": 0.8639596990675986, "learning_rate": 1.616910230931612e-07, "loss": 0.6185, "step": 4909 }, { "epoch": 0.94, "grad_norm": 1.0468074246114891, "learning_rate": 1.6057698918338526e-07, "loss": 0.8503, "step": 4910 }, { "epoch": 0.94, "grad_norm": 0.780232946171211, "learning_rate": 1.5946677527640563e-07, "loss": 0.5648, "step": 4911 }, { "epoch": 0.94, "grad_norm": 1.0135982025896806, "learning_rate": 1.5836038180324198e-07, "loss": 0.8435, "step": 4912 }, { "epoch": 0.95, "grad_norm": 0.9874551250010991, "learning_rate": 1.5725780919343624e-07, "loss": 0.8469, "step": 4913 }, { "epoch": 0.95, "grad_norm": 1.0091118403494892, "learning_rate": 1.561590578750438e-07, "loss": 0.8416, "step": 4914 }, { "epoch": 0.95, "grad_norm": 1.0711156805632778, "learning_rate": 1.55064128274639e-07, "loss": 0.792, "step": 4915 }, { "epoch": 0.95, "grad_norm": 1.0427602932879125, "learning_rate": 1.5397302081731069e-07, "loss": 0.811, "step": 4916 }, { "epoch": 0.95, "grad_norm": 1.1606238936666518, "learning_rate": 1.5288573592666445e-07, "loss": 0.8394, "step": 4917 }, { "epoch": 0.95, "grad_norm": 0.9712565626992965, "learning_rate": 1.518022740248215e-07, "loss": 0.8071, "step": 4918 }, { "epoch": 0.95, "grad_norm": 0.794495474223021, "learning_rate": 1.5072263553241872e-07, "loss": 0.6066, "step": 4919 }, { "epoch": 0.95, "grad_norm": 0.8983635172237139, "learning_rate": 1.4964682086861082e-07, "loss": 0.6292, "step": 4920 }, { "epoch": 0.95, "grad_norm": 1.1919214588641276, "learning_rate": 1.4857483045106258e-07, "loss": 0.8525, "step": 4921 }, { "epoch": 0.95, "grad_norm": 1.0962987987358495, "learning_rate": 1.475066646959611e-07, "loss": 0.8591, "step": 4922 }, { "epoch": 0.95, "grad_norm": 1.115440639354582, "learning_rate": 1.4644232401800352e-07, "loss": 0.8335, "step": 4923 }, { "epoch": 0.95, "grad_norm": 0.9289267610853273, "learning_rate": 1.4538180883040264e-07, "loss": 0.7991, "step": 4924 }, { "epoch": 0.95, "grad_norm": 1.081672977314629, "learning_rate": 1.4432511954488915e-07, "loss": 0.8384, "step": 4925 }, { "epoch": 0.95, "grad_norm": 0.8497426782092176, "learning_rate": 1.4327225657170485e-07, "loss": 0.5686, "step": 4926 }, { "epoch": 0.95, "grad_norm": 0.7938191469354655, "learning_rate": 1.4222322031960723e-07, "loss": 0.5706, "step": 4927 }, { "epoch": 0.95, "grad_norm": 1.006424863889993, "learning_rate": 1.411780111958694e-07, "loss": 0.8674, "step": 4928 }, { "epoch": 0.95, "grad_norm": 1.0729517860552011, "learning_rate": 1.4013662960627562e-07, "loss": 0.7759, "step": 4929 }, { "epoch": 0.95, "grad_norm": 1.0929530407783483, "learning_rate": 1.3909907595512806e-07, "loss": 0.832, "step": 4930 }, { "epoch": 0.95, "grad_norm": 1.0695023519324596, "learning_rate": 1.3806535064524006e-07, "loss": 0.8906, "step": 4931 }, { "epoch": 0.95, "grad_norm": 1.3544394270364932, "learning_rate": 1.3703545407793951e-07, "loss": 0.8716, "step": 4932 }, { "epoch": 0.95, "grad_norm": 1.0879312948324493, "learning_rate": 1.360093866530665e-07, "loss": 0.877, "step": 4933 }, { "epoch": 0.95, "grad_norm": 0.9712910059282936, "learning_rate": 1.34987148768978e-07, "loss": 0.8811, "step": 4934 }, { "epoch": 0.95, "grad_norm": 0.977989684078335, "learning_rate": 1.3396874082253986e-07, "loss": 0.825, "step": 4935 }, { "epoch": 0.95, "grad_norm": 1.0068075057408163, "learning_rate": 1.3295416320913357e-07, "loss": 0.8462, "step": 4936 }, { "epoch": 0.95, "grad_norm": 1.0407283228381405, "learning_rate": 1.3194341632265518e-07, "loss": 0.8677, "step": 4937 }, { "epoch": 0.95, "grad_norm": 0.8414013145106332, "learning_rate": 1.3093650055550855e-07, "loss": 0.5806, "step": 4938 }, { "epoch": 0.95, "grad_norm": 1.0603787552812058, "learning_rate": 1.2993341629861432e-07, "loss": 0.864, "step": 4939 }, { "epoch": 0.95, "grad_norm": 1.1679278022866748, "learning_rate": 1.2893416394140323e-07, "loss": 0.8199, "step": 4940 }, { "epoch": 0.95, "grad_norm": 1.0155381266412788, "learning_rate": 1.279387438718216e-07, "loss": 0.7877, "step": 4941 }, { "epoch": 0.95, "grad_norm": 1.064941039822116, "learning_rate": 1.269471564763247e-07, "loss": 0.8284, "step": 4942 }, { "epoch": 0.95, "grad_norm": 0.8039966817784006, "learning_rate": 1.2595940213988024e-07, "loss": 0.5604, "step": 4943 }, { "epoch": 0.95, "grad_norm": 1.1052583544369847, "learning_rate": 1.2497548124597026e-07, "loss": 0.8586, "step": 4944 }, { "epoch": 0.95, "grad_norm": 0.9561092086701592, "learning_rate": 1.2399539417658368e-07, "loss": 0.8223, "step": 4945 }, { "epoch": 0.95, "grad_norm": 1.0060388423476891, "learning_rate": 1.2301914131222726e-07, "loss": 0.8503, "step": 4946 }, { "epoch": 0.95, "grad_norm": 1.0330859198461888, "learning_rate": 1.2204672303191335e-07, "loss": 0.9055, "step": 4947 }, { "epoch": 0.95, "grad_norm": 1.082971074132155, "learning_rate": 1.2107813971317106e-07, "loss": 0.8804, "step": 4948 }, { "epoch": 0.95, "grad_norm": 1.0422005755595818, "learning_rate": 1.201133917320363e-07, "loss": 0.8564, "step": 4949 }, { "epoch": 0.95, "grad_norm": 1.0909175330015963, "learning_rate": 1.1915247946305498e-07, "loss": 0.896, "step": 4950 }, { "epoch": 0.95, "grad_norm": 0.8889793166797281, "learning_rate": 1.1819540327929092e-07, "loss": 0.5827, "step": 4951 }, { "epoch": 0.95, "grad_norm": 1.0018276149699537, "learning_rate": 1.1724216355231022e-07, "loss": 0.7825, "step": 4952 }, { "epoch": 0.95, "grad_norm": 1.1029048904899603, "learning_rate": 1.1629276065219575e-07, "loss": 0.8525, "step": 4953 }, { "epoch": 0.95, "grad_norm": 1.1939345447148957, "learning_rate": 1.1534719494753821e-07, "loss": 0.823, "step": 4954 }, { "epoch": 0.95, "grad_norm": 1.3131250590051926, "learning_rate": 1.144054668054373e-07, "loss": 0.8485, "step": 4955 }, { "epoch": 0.95, "grad_norm": 0.9639837224520507, "learning_rate": 1.1346757659150498e-07, "loss": 0.8306, "step": 4956 }, { "epoch": 0.95, "grad_norm": 0.9821883259580746, "learning_rate": 1.1253352466986334e-07, "loss": 0.8401, "step": 4957 }, { "epoch": 0.95, "grad_norm": 1.1237843022555127, "learning_rate": 1.116033114031434e-07, "loss": 0.8401, "step": 4958 }, { "epoch": 0.95, "grad_norm": 0.9624269051468365, "learning_rate": 1.1067693715248406e-07, "loss": 0.8083, "step": 4959 }, { "epoch": 0.95, "grad_norm": 0.8588465677974965, "learning_rate": 1.0975440227753764e-07, "loss": 0.5751, "step": 4960 }, { "epoch": 0.95, "grad_norm": 1.1084686315887082, "learning_rate": 1.0883570713646318e-07, "loss": 0.8464, "step": 4961 }, { "epoch": 0.95, "grad_norm": 0.9606314273197207, "learning_rate": 1.0792085208593095e-07, "loss": 0.8142, "step": 4962 }, { "epoch": 0.95, "grad_norm": 1.052952525302123, "learning_rate": 1.0700983748111792e-07, "loss": 0.8636, "step": 4963 }, { "epoch": 0.95, "grad_norm": 0.9696617426533967, "learning_rate": 1.061026636757101e-07, "loss": 0.7766, "step": 4964 }, { "epoch": 0.96, "grad_norm": 1.0238940005948263, "learning_rate": 1.0519933102190682e-07, "loss": 0.9092, "step": 4965 }, { "epoch": 0.96, "grad_norm": 0.8589708366753991, "learning_rate": 1.0429983987041092e-07, "loss": 0.5599, "step": 4966 }, { "epoch": 0.96, "grad_norm": 1.1191145306560895, "learning_rate": 1.0340419057043527e-07, "loss": 0.8499, "step": 4967 }, { "epoch": 0.96, "grad_norm": 1.0640977131631564, "learning_rate": 1.0251238346970393e-07, "loss": 0.8198, "step": 4968 }, { "epoch": 0.96, "grad_norm": 1.0562515948462718, "learning_rate": 1.0162441891444441e-07, "loss": 0.8088, "step": 4969 }, { "epoch": 0.96, "grad_norm": 1.0283405914643724, "learning_rate": 1.007402972493976e-07, "loss": 0.7465, "step": 4970 }, { "epoch": 0.96, "grad_norm": 1.1500491613461192, "learning_rate": 9.986001881780783e-08, "loss": 0.8982, "step": 4971 }, { "epoch": 0.96, "grad_norm": 1.1344058597865543, "learning_rate": 9.898358396143171e-08, "loss": 0.8748, "step": 4972 }, { "epoch": 0.96, "grad_norm": 1.1502492619260505, "learning_rate": 9.811099302052928e-08, "loss": 0.9109, "step": 4973 }, { "epoch": 0.96, "grad_norm": 0.8822608636319546, "learning_rate": 9.72422463338718e-08, "loss": 0.6189, "step": 4974 }, { "epoch": 0.96, "grad_norm": 0.9274403291808283, "learning_rate": 9.637734423873612e-08, "loss": 0.5557, "step": 4975 }, { "epoch": 0.96, "grad_norm": 0.9050449913316743, "learning_rate": 9.55162870709081e-08, "loss": 0.822, "step": 4976 }, { "epoch": 0.96, "grad_norm": 1.0321555356804233, "learning_rate": 9.465907516467698e-08, "loss": 0.8567, "step": 4977 }, { "epoch": 0.96, "grad_norm": 1.0414825200068358, "learning_rate": 9.380570885284546e-08, "loss": 0.8162, "step": 4978 }, { "epoch": 0.96, "grad_norm": 0.622296182454781, "learning_rate": 9.295618846671739e-08, "loss": 0.2805, "step": 4979 }, { "epoch": 0.96, "grad_norm": 1.1593096123186584, "learning_rate": 9.211051433610674e-08, "loss": 0.8965, "step": 4980 }, { "epoch": 0.96, "grad_norm": 1.0218537476061997, "learning_rate": 9.126868678933198e-08, "loss": 0.8779, "step": 4981 }, { "epoch": 0.96, "grad_norm": 1.059005169521835, "learning_rate": 9.04307061532217e-08, "loss": 0.7795, "step": 4982 }, { "epoch": 0.96, "grad_norm": 0.9739725523106664, "learning_rate": 8.959657275310674e-08, "loss": 0.833, "step": 4983 }, { "epoch": 0.96, "grad_norm": 1.176274385121593, "learning_rate": 8.876628691282918e-08, "loss": 0.8093, "step": 4984 }, { "epoch": 0.96, "grad_norm": 1.1044192798120767, "learning_rate": 8.793984895473117e-08, "loss": 0.8923, "step": 4985 }, { "epoch": 0.96, "grad_norm": 0.9881880519765246, "learning_rate": 8.711725919966718e-08, "loss": 0.832, "step": 4986 }, { "epoch": 0.96, "grad_norm": 0.9172356098863695, "learning_rate": 8.629851796699284e-08, "loss": 0.6046, "step": 4987 }, { "epoch": 0.96, "grad_norm": 0.9697876956105836, "learning_rate": 8.54836255745728e-08, "loss": 0.8374, "step": 4988 }, { "epoch": 0.96, "grad_norm": 0.915385770787097, "learning_rate": 8.467258233877728e-08, "loss": 0.8105, "step": 4989 }, { "epoch": 0.96, "grad_norm": 0.9163905672181056, "learning_rate": 8.386538857447779e-08, "loss": 0.5723, "step": 4990 }, { "epoch": 0.96, "grad_norm": 1.0561132467884111, "learning_rate": 8.306204459505807e-08, "loss": 0.8021, "step": 4991 }, { "epoch": 0.96, "grad_norm": 1.1023733518797447, "learning_rate": 8.226255071240308e-08, "loss": 0.9016, "step": 4992 }, { "epoch": 0.96, "grad_norm": 0.8612932400332006, "learning_rate": 8.146690723690342e-08, "loss": 0.7781, "step": 4993 }, { "epoch": 0.96, "grad_norm": 1.0987236263040727, "learning_rate": 8.067511447745535e-08, "loss": 0.8179, "step": 4994 }, { "epoch": 0.96, "grad_norm": 0.9732061842458587, "learning_rate": 7.988717274146074e-08, "loss": 0.8418, "step": 4995 }, { "epoch": 0.96, "grad_norm": 1.106112165286301, "learning_rate": 7.910308233482488e-08, "loss": 0.813, "step": 4996 }, { "epoch": 0.96, "grad_norm": 1.179575557955416, "learning_rate": 7.832284356195764e-08, "loss": 0.8278, "step": 4997 }, { "epoch": 0.96, "grad_norm": 0.9613399244481042, "learning_rate": 7.754645672577776e-08, "loss": 0.5604, "step": 4998 }, { "epoch": 0.96, "grad_norm": 0.8602481704411999, "learning_rate": 7.677392212770196e-08, "loss": 0.6074, "step": 4999 }, { "epoch": 0.96, "grad_norm": 1.0278536377491048, "learning_rate": 7.600524006765808e-08, "loss": 0.8481, "step": 5000 }, { "epoch": 0.96, "grad_norm": 1.0908343112306862, "learning_rate": 7.524041084407185e-08, "loss": 0.8584, "step": 5001 }, { "epoch": 0.96, "grad_norm": 1.0453330983292453, "learning_rate": 7.447943475387797e-08, "loss": 0.8108, "step": 5002 }, { "epoch": 0.96, "grad_norm": 0.9648774607846522, "learning_rate": 7.372231209251346e-08, "loss": 0.8254, "step": 5003 }, { "epoch": 0.96, "grad_norm": 1.045114780382975, "learning_rate": 7.296904315391873e-08, "loss": 0.8274, "step": 5004 }, { "epoch": 0.96, "grad_norm": 0.9368336109711779, "learning_rate": 7.221962823053874e-08, "loss": 0.8459, "step": 5005 }, { "epoch": 0.96, "grad_norm": 1.1455969161999742, "learning_rate": 7.147406761332298e-08, "loss": 0.8362, "step": 5006 }, { "epoch": 0.96, "grad_norm": 1.1753414640893276, "learning_rate": 7.073236159172325e-08, "loss": 0.8562, "step": 5007 }, { "epoch": 0.96, "grad_norm": 1.0141255729134389, "learning_rate": 6.999451045369587e-08, "loss": 0.8301, "step": 5008 }, { "epoch": 0.96, "grad_norm": 0.9640524039105003, "learning_rate": 6.926051448569948e-08, "loss": 0.8679, "step": 5009 }, { "epoch": 0.96, "grad_norm": 1.0195547704979795, "learning_rate": 6.853037397269724e-08, "loss": 0.5873, "step": 5010 }, { "epoch": 0.96, "grad_norm": 0.9133012285751716, "learning_rate": 6.78040891981524e-08, "loss": 0.8203, "step": 5011 }, { "epoch": 0.96, "grad_norm": 1.0603232038095658, "learning_rate": 6.70816604440383e-08, "loss": 0.749, "step": 5012 }, { "epoch": 0.96, "grad_norm": 0.9652880240502382, "learning_rate": 6.63630879908217e-08, "loss": 0.8286, "step": 5013 }, { "epoch": 0.96, "grad_norm": 1.1577280328177122, "learning_rate": 6.564837211748054e-08, "loss": 0.8391, "step": 5014 }, { "epoch": 0.96, "grad_norm": 0.8600386739082739, "learning_rate": 6.493751310149177e-08, "loss": 0.6054, "step": 5015 }, { "epoch": 0.96, "grad_norm": 0.7971782750018761, "learning_rate": 6.42305112188335e-08, "loss": 0.5901, "step": 5016 }, { "epoch": 0.97, "grad_norm": 0.9487011971721516, "learning_rate": 6.352736674398951e-08, "loss": 0.8206, "step": 5017 }, { "epoch": 0.97, "grad_norm": 1.1933106540857983, "learning_rate": 6.282807994994477e-08, "loss": 0.8816, "step": 5018 }, { "epoch": 0.97, "grad_norm": 1.0182710870639458, "learning_rate": 6.213265110818656e-08, "loss": 0.8467, "step": 5019 }, { "epoch": 0.97, "grad_norm": 0.8366749008916612, "learning_rate": 6.144108048870335e-08, "loss": 0.5219, "step": 5020 }, { "epoch": 0.97, "grad_norm": 0.7777454538468725, "learning_rate": 6.075336835998813e-08, "loss": 0.5504, "step": 5021 }, { "epoch": 0.97, "grad_norm": 1.1826369715484002, "learning_rate": 6.00695149890329e-08, "loss": 0.8259, "step": 5022 }, { "epoch": 0.97, "grad_norm": 1.0108856504784216, "learning_rate": 5.938952064133419e-08, "loss": 0.8403, "step": 5023 }, { "epoch": 0.97, "grad_norm": 0.9911045663348791, "learning_rate": 5.871338558088857e-08, "loss": 0.8151, "step": 5024 }, { "epoch": 0.97, "grad_norm": 1.0104802802432507, "learning_rate": 5.8041110070194976e-08, "loss": 0.8279, "step": 5025 }, { "epoch": 0.97, "grad_norm": 1.1169757452683622, "learning_rate": 5.7372694370254614e-08, "loss": 0.9038, "step": 5026 }, { "epoch": 0.97, "grad_norm": 1.0231658122432896, "learning_rate": 5.67081387405688e-08, "loss": 0.843, "step": 5027 }, { "epoch": 0.97, "grad_norm": 1.0336646861306489, "learning_rate": 5.6047443439141146e-08, "loss": 0.8562, "step": 5028 }, { "epoch": 0.97, "grad_norm": 1.1237507925701078, "learning_rate": 5.539060872247537e-08, "loss": 0.8879, "step": 5029 }, { "epoch": 0.97, "grad_norm": 1.037443275410836, "learning_rate": 5.47376348455797e-08, "loss": 0.8474, "step": 5030 }, { "epoch": 0.97, "grad_norm": 1.0337255427896002, "learning_rate": 5.408852206195914e-08, "loss": 0.8223, "step": 5031 }, { "epoch": 0.97, "grad_norm": 1.0219785436796935, "learning_rate": 5.344327062362098e-08, "loss": 0.8213, "step": 5032 }, { "epoch": 0.97, "grad_norm": 0.9487239768217949, "learning_rate": 5.2801880781075954e-08, "loss": 0.8303, "step": 5033 }, { "epoch": 0.97, "grad_norm": 1.1388661983916166, "learning_rate": 5.216435278333376e-08, "loss": 0.8132, "step": 5034 }, { "epoch": 0.97, "grad_norm": 1.0227785828511997, "learning_rate": 5.153068687790197e-08, "loss": 0.8298, "step": 5035 }, { "epoch": 0.97, "grad_norm": 1.0463241373974286, "learning_rate": 5.0900883310794903e-08, "loss": 0.8633, "step": 5036 }, { "epoch": 0.97, "grad_norm": 0.9439893205864255, "learning_rate": 5.0274942326521414e-08, "loss": 0.8489, "step": 5037 }, { "epoch": 0.97, "grad_norm": 0.9966616104655626, "learning_rate": 4.9652864168096e-08, "loss": 0.8528, "step": 5038 }, { "epoch": 0.97, "grad_norm": 1.0151793148503954, "learning_rate": 4.9034649077027706e-08, "loss": 0.8723, "step": 5039 }, { "epoch": 0.97, "grad_norm": 1.0989655579951703, "learning_rate": 4.84202972933312e-08, "loss": 0.8091, "step": 5040 }, { "epoch": 0.97, "grad_norm": 1.0108813194674908, "learning_rate": 4.7809809055517906e-08, "loss": 0.8485, "step": 5041 }, { "epoch": 0.97, "grad_norm": 1.013616200895357, "learning_rate": 4.720318460060047e-08, "loss": 0.6319, "step": 5042 }, { "epoch": 0.97, "grad_norm": 1.1004040844124283, "learning_rate": 4.6600424164091606e-08, "loss": 0.8237, "step": 5043 }, { "epoch": 0.97, "grad_norm": 1.0871051012507575, "learning_rate": 4.6001527980004125e-08, "loss": 0.8154, "step": 5044 }, { "epoch": 0.97, "grad_norm": 0.9342091207694683, "learning_rate": 4.54064962808487e-08, "loss": 0.8198, "step": 5045 }, { "epoch": 0.97, "grad_norm": 1.142476522378703, "learning_rate": 4.4815329297639434e-08, "loss": 0.8459, "step": 5046 }, { "epoch": 0.97, "grad_norm": 0.9617572232975081, "learning_rate": 4.422802725988606e-08, "loss": 0.7677, "step": 5047 }, { "epoch": 0.97, "grad_norm": 1.1322562165215868, "learning_rate": 4.364459039559843e-08, "loss": 0.8931, "step": 5048 }, { "epoch": 0.97, "grad_norm": 0.8622294875951545, "learning_rate": 4.3065018931289784e-08, "loss": 0.8293, "step": 5049 }, { "epoch": 0.97, "grad_norm": 1.0216119871833604, "learning_rate": 4.248931309196791e-08, "loss": 0.8625, "step": 5050 }, { "epoch": 0.97, "grad_norm": 0.9759344699348722, "learning_rate": 4.1917473101140696e-08, "loss": 0.8835, "step": 5051 }, { "epoch": 0.97, "grad_norm": 1.0007678376040927, "learning_rate": 4.134949918081832e-08, "loss": 0.8438, "step": 5052 }, { "epoch": 0.97, "grad_norm": 0.9917418368867589, "learning_rate": 4.0785391551506626e-08, "loss": 0.8906, "step": 5053 }, { "epoch": 0.97, "grad_norm": 0.9289167644404553, "learning_rate": 4.022515043221154e-08, "loss": 0.828, "step": 5054 }, { "epoch": 0.97, "grad_norm": 1.048516794923099, "learning_rate": 3.966877604043795e-08, "loss": 0.8369, "step": 5055 }, { "epoch": 0.97, "grad_norm": 1.031283292043348, "learning_rate": 3.9116268592189755e-08, "loss": 0.8538, "step": 5056 }, { "epoch": 0.97, "grad_norm": 1.066356064546543, "learning_rate": 3.8567628301969806e-08, "loss": 0.8817, "step": 5057 }, { "epoch": 0.97, "grad_norm": 1.100822619600932, "learning_rate": 3.802285538277772e-08, "loss": 0.8718, "step": 5058 }, { "epoch": 0.97, "grad_norm": 1.043979488541354, "learning_rate": 3.748195004611543e-08, "loss": 0.8376, "step": 5059 }, { "epoch": 0.97, "grad_norm": 1.1605569690498416, "learning_rate": 3.69449125019794e-08, "loss": 0.8699, "step": 5060 }, { "epoch": 0.97, "grad_norm": 0.9236843556007638, "learning_rate": 3.6411742958866184e-08, "loss": 0.6152, "step": 5061 }, { "epoch": 0.97, "grad_norm": 0.9927418421076607, "learning_rate": 3.588244162377019e-08, "loss": 0.8401, "step": 5062 }, { "epoch": 0.97, "grad_norm": 1.1392515270936763, "learning_rate": 3.5357008702185945e-08, "loss": 0.8116, "step": 5063 }, { "epoch": 0.97, "grad_norm": 0.9769349854103477, "learning_rate": 3.483544439810249e-08, "loss": 0.8396, "step": 5064 }, { "epoch": 0.97, "grad_norm": 1.0878574705079904, "learning_rate": 3.4317748914011187e-08, "loss": 0.8601, "step": 5065 }, { "epoch": 0.97, "grad_norm": 1.0424807062751804, "learning_rate": 3.3803922450897917e-08, "loss": 0.8428, "step": 5066 }, { "epoch": 0.97, "grad_norm": 1.1257404541377676, "learning_rate": 3.329396520824757e-08, "loss": 0.7769, "step": 5067 }, { "epoch": 0.97, "grad_norm": 1.1560652047929336, "learning_rate": 3.2787877384045095e-08, "loss": 0.8779, "step": 5068 }, { "epoch": 0.98, "grad_norm": 0.9897845594349115, "learning_rate": 3.228565917476889e-08, "loss": 0.8994, "step": 5069 }, { "epoch": 0.98, "grad_norm": 0.9323336527259096, "learning_rate": 3.178731077539743e-08, "loss": 0.8015, "step": 5070 }, { "epoch": 0.98, "grad_norm": 1.1835499879722393, "learning_rate": 3.129283237940928e-08, "loss": 0.8484, "step": 5071 }, { "epoch": 0.98, "grad_norm": 1.0211247177734564, "learning_rate": 3.080222417877421e-08, "loss": 0.8845, "step": 5072 }, { "epoch": 0.98, "grad_norm": 0.955108293249935, "learning_rate": 3.031548636396764e-08, "loss": 0.835, "step": 5073 }, { "epoch": 0.98, "grad_norm": 1.0756884792093995, "learning_rate": 2.983261912395397e-08, "loss": 0.801, "step": 5074 }, { "epoch": 0.98, "grad_norm": 1.0925655866168744, "learning_rate": 2.9353622646199898e-08, "loss": 0.8335, "step": 5075 }, { "epoch": 0.98, "grad_norm": 1.1026810952850823, "learning_rate": 2.8878497116671124e-08, "loss": 0.8396, "step": 5076 }, { "epoch": 0.98, "grad_norm": 1.0415548940509833, "learning_rate": 2.8407242719823424e-08, "loss": 0.8289, "step": 5077 }, { "epoch": 0.98, "grad_norm": 1.0875489072346218, "learning_rate": 2.7939859638617118e-08, "loss": 0.8467, "step": 5078 }, { "epoch": 0.98, "grad_norm": 1.0540473131950556, "learning_rate": 2.7476348054504832e-08, "loss": 0.9062, "step": 5079 }, { "epoch": 0.98, "grad_norm": 1.0077927528801334, "learning_rate": 2.7016708147439285e-08, "loss": 0.8457, "step": 5080 }, { "epoch": 0.98, "grad_norm": 1.0539022682740729, "learning_rate": 2.6560940095866626e-08, "loss": 0.8621, "step": 5081 }, { "epoch": 0.98, "grad_norm": 1.0835171848322749, "learning_rate": 2.6109044076733092e-08, "loss": 0.8682, "step": 5082 }, { "epoch": 0.98, "grad_norm": 1.0420009006906392, "learning_rate": 2.5661020265479452e-08, "loss": 0.78, "step": 5083 }, { "epoch": 0.98, "grad_norm": 0.8986552428120247, "learning_rate": 2.5216868836043242e-08, "loss": 0.7644, "step": 5084 }, { "epoch": 0.98, "grad_norm": 1.0110149707665685, "learning_rate": 2.4776589960862074e-08, "loss": 0.8186, "step": 5085 }, { "epoch": 0.98, "grad_norm": 0.8080937775114788, "learning_rate": 2.434018381086589e-08, "loss": 0.5997, "step": 5086 }, { "epoch": 0.98, "grad_norm": 1.059734769662694, "learning_rate": 2.3907650555481387e-08, "loss": 0.8459, "step": 5087 }, { "epoch": 0.98, "grad_norm": 0.9895835018602236, "learning_rate": 2.3478990362634235e-08, "loss": 0.8467, "step": 5088 }, { "epoch": 0.98, "grad_norm": 1.0510674747322277, "learning_rate": 2.3054203398743537e-08, "loss": 0.8689, "step": 5089 }, { "epoch": 0.98, "grad_norm": 0.9943529417085989, "learning_rate": 2.263328982872959e-08, "loss": 0.8474, "step": 5090 }, { "epoch": 0.98, "grad_norm": 0.9332549938756515, "learning_rate": 2.221624981600168e-08, "loss": 0.7942, "step": 5091 }, { "epoch": 0.98, "grad_norm": 1.1242508540115932, "learning_rate": 2.1803083522471402e-08, "loss": 0.9111, "step": 5092 }, { "epoch": 0.98, "grad_norm": 0.9888331444610562, "learning_rate": 2.1393791108542672e-08, "loss": 0.8423, "step": 5093 }, { "epoch": 0.98, "grad_norm": 1.000830551291026, "learning_rate": 2.098837273311838e-08, "loss": 0.8518, "step": 5094 }, { "epoch": 0.98, "grad_norm": 1.0640067842418233, "learning_rate": 2.058682855359595e-08, "loss": 0.8252, "step": 5095 }, { "epoch": 0.98, "grad_norm": 1.0727756126475376, "learning_rate": 2.0189158725867353e-08, "loss": 0.8524, "step": 5096 }, { "epoch": 0.98, "grad_norm": 1.157731627552193, "learning_rate": 1.979536340432131e-08, "loss": 0.8232, "step": 5097 }, { "epoch": 0.98, "grad_norm": 1.0241422810876852, "learning_rate": 1.9405442741844415e-08, "loss": 0.8896, "step": 5098 }, { "epoch": 0.98, "grad_norm": 1.077900112191843, "learning_rate": 1.9019396889816688e-08, "loss": 0.8684, "step": 5099 }, { "epoch": 0.98, "grad_norm": 0.9851718099225215, "learning_rate": 1.8637225998114904e-08, "loss": 0.8284, "step": 5100 }, { "epoch": 0.98, "grad_norm": 0.9744259593854411, "learning_rate": 1.825893021510927e-08, "loss": 0.8157, "step": 5101 }, { "epoch": 0.98, "grad_norm": 1.0474322816487984, "learning_rate": 1.7884509687668972e-08, "loss": 0.8367, "step": 5102 }, { "epoch": 0.98, "grad_norm": 0.9595246495047199, "learning_rate": 1.7513964561156617e-08, "loss": 0.8052, "step": 5103 }, { "epoch": 0.98, "grad_norm": 1.0399660037801055, "learning_rate": 1.714729497942935e-08, "loss": 0.8035, "step": 5104 }, { "epoch": 0.98, "grad_norm": 1.0088459005342958, "learning_rate": 1.6784501084843307e-08, "loss": 0.8547, "step": 5105 }, { "epoch": 0.98, "grad_norm": 1.0776430181890428, "learning_rate": 1.6425583018244706e-08, "loss": 0.8796, "step": 5106 }, { "epoch": 0.98, "grad_norm": 0.9804143743330992, "learning_rate": 1.607054091897986e-08, "loss": 0.8428, "step": 5107 }, { "epoch": 0.98, "grad_norm": 1.0772974965116149, "learning_rate": 1.57193749248874e-08, "loss": 0.8745, "step": 5108 }, { "epoch": 0.98, "grad_norm": 1.067605518463485, "learning_rate": 1.537208517230271e-08, "loss": 0.8389, "step": 5109 }, { "epoch": 0.98, "grad_norm": 0.9753389439642555, "learning_rate": 1.5028671796055715e-08, "loss": 0.8364, "step": 5110 }, { "epoch": 0.98, "grad_norm": 1.084218006044444, "learning_rate": 1.4689134929470884e-08, "loss": 0.7939, "step": 5111 }, { "epoch": 0.98, "grad_norm": 1.1942700245433464, "learning_rate": 1.435347470436832e-08, "loss": 0.7709, "step": 5112 }, { "epoch": 0.98, "grad_norm": 0.7918121771846408, "learning_rate": 1.4021691251062675e-08, "loss": 0.5909, "step": 5113 }, { "epoch": 0.98, "grad_norm": 0.7850484481924206, "learning_rate": 1.3693784698363133e-08, "loss": 0.6002, "step": 5114 }, { "epoch": 0.98, "grad_norm": 0.8987003487430216, "learning_rate": 1.3369755173575639e-08, "loss": 0.6063, "step": 5115 }, { "epoch": 0.98, "grad_norm": 1.0910223233378935, "learning_rate": 1.3049602802498451e-08, "loss": 0.7928, "step": 5116 }, { "epoch": 0.98, "grad_norm": 1.1162308605006377, "learning_rate": 1.273332770942659e-08, "loss": 0.813, "step": 5117 }, { "epoch": 0.98, "grad_norm": 0.9663076142936936, "learning_rate": 1.2420930017148503e-08, "loss": 0.833, "step": 5118 }, { "epoch": 0.98, "grad_norm": 1.0932428294249896, "learning_rate": 1.2112409846947171e-08, "loss": 0.8782, "step": 5119 }, { "epoch": 0.98, "grad_norm": 1.1122533413353486, "learning_rate": 1.1807767318602337e-08, "loss": 0.8171, "step": 5120 }, { "epoch": 0.99, "grad_norm": 0.9418695774302763, "learning_rate": 1.150700255038606e-08, "loss": 0.8796, "step": 5121 }, { "epoch": 0.99, "grad_norm": 1.0012143043475448, "learning_rate": 1.1210115659063825e-08, "loss": 0.8274, "step": 5122 }, { "epoch": 0.99, "grad_norm": 0.9988221257476798, "learning_rate": 1.0917106759900097e-08, "loss": 0.8027, "step": 5123 }, { "epoch": 0.99, "grad_norm": 1.0886352726159367, "learning_rate": 1.0627975966649439e-08, "loss": 0.8606, "step": 5124 }, { "epoch": 0.99, "grad_norm": 0.9993342995474558, "learning_rate": 1.034272339156206e-08, "loss": 0.7942, "step": 5125 }, { "epoch": 0.99, "grad_norm": 0.9833879063031953, "learning_rate": 1.0061349145383814e-08, "loss": 0.8127, "step": 5126 }, { "epoch": 0.99, "grad_norm": 1.0724501811425813, "learning_rate": 9.783853337353987e-09, "loss": 0.895, "step": 5127 }, { "epoch": 0.99, "grad_norm": 0.9718945217816762, "learning_rate": 9.510236075205292e-09, "loss": 0.8086, "step": 5128 }, { "epoch": 0.99, "grad_norm": 1.122143258744039, "learning_rate": 9.240497465164978e-09, "loss": 0.7924, "step": 5129 }, { "epoch": 0.99, "grad_norm": 1.2461231907966082, "learning_rate": 8.974637611955939e-09, "loss": 0.8401, "step": 5130 }, { "epoch": 0.99, "grad_norm": 1.0829885296614146, "learning_rate": 8.712656618793391e-09, "loss": 0.8894, "step": 5131 }, { "epoch": 0.99, "grad_norm": 1.0509518825819473, "learning_rate": 8.454554587388198e-09, "loss": 0.8479, "step": 5132 }, { "epoch": 0.99, "grad_norm": 0.9836444161180872, "learning_rate": 8.200331617943535e-09, "loss": 0.8328, "step": 5133 }, { "epoch": 0.99, "grad_norm": 1.098710358849895, "learning_rate": 7.949987809158232e-09, "loss": 0.8546, "step": 5134 }, { "epoch": 0.99, "grad_norm": 0.9661272072913826, "learning_rate": 7.703523258223433e-09, "loss": 0.8318, "step": 5135 }, { "epoch": 0.99, "grad_norm": 1.0600778842841836, "learning_rate": 7.460938060825929e-09, "loss": 0.8042, "step": 5136 }, { "epoch": 0.99, "grad_norm": 1.120206546212321, "learning_rate": 7.222232311145938e-09, "loss": 0.853, "step": 5137 }, { "epoch": 0.99, "grad_norm": 0.8957814746939915, "learning_rate": 6.987406101855998e-09, "loss": 0.821, "step": 5138 }, { "epoch": 0.99, "grad_norm": 1.0378208885159685, "learning_rate": 6.756459524125403e-09, "loss": 0.8152, "step": 5139 }, { "epoch": 0.99, "grad_norm": 1.0429325905614475, "learning_rate": 6.5293926676135434e-09, "loss": 0.8613, "step": 5140 }, { "epoch": 0.99, "grad_norm": 1.0758681331648121, "learning_rate": 6.306205620477679e-09, "loss": 0.8574, "step": 5141 }, { "epoch": 0.99, "grad_norm": 1.0495176491774354, "learning_rate": 6.086898469365166e-09, "loss": 0.8835, "step": 5142 }, { "epoch": 0.99, "grad_norm": 0.8601487121665353, "learning_rate": 5.871471299419007e-09, "loss": 0.5638, "step": 5143 }, { "epoch": 0.99, "grad_norm": 1.0683271598927746, "learning_rate": 5.6599241942767445e-09, "loss": 0.8384, "step": 5144 }, { "epoch": 0.99, "grad_norm": 1.0505869884826118, "learning_rate": 5.452257236066017e-09, "loss": 0.8757, "step": 5145 }, { "epoch": 0.99, "grad_norm": 0.987917956408378, "learning_rate": 5.248470505412328e-09, "loss": 0.6418, "step": 5146 }, { "epoch": 0.99, "grad_norm": 1.0609173518410997, "learning_rate": 5.0485640814312844e-09, "loss": 0.8782, "step": 5147 }, { "epoch": 0.99, "grad_norm": 1.0406817774061177, "learning_rate": 4.8525380417330234e-09, "loss": 0.8467, "step": 5148 }, { "epoch": 0.99, "grad_norm": 0.91247180338302, "learning_rate": 4.660392462424446e-09, "loss": 0.8625, "step": 5149 }, { "epoch": 0.99, "grad_norm": 1.1468350856559817, "learning_rate": 4.472127418099215e-09, "loss": 0.8447, "step": 5150 }, { "epoch": 0.99, "grad_norm": 1.054282596028737, "learning_rate": 4.287742981851084e-09, "loss": 0.8088, "step": 5151 }, { "epoch": 0.99, "grad_norm": 0.8087046669244895, "learning_rate": 4.1072392252639034e-09, "loss": 0.5653, "step": 5152 }, { "epoch": 0.99, "grad_norm": 0.928958345675643, "learning_rate": 3.930616218414951e-09, "loss": 0.8215, "step": 5153 }, { "epoch": 0.99, "grad_norm": 1.036073252658608, "learning_rate": 3.757874029874931e-09, "loss": 0.8511, "step": 5154 }, { "epoch": 0.99, "grad_norm": 1.1344045685922253, "learning_rate": 3.5890127267090844e-09, "loss": 0.8369, "step": 5155 }, { "epoch": 0.99, "grad_norm": 0.9493655895245635, "learning_rate": 3.424032374476083e-09, "loss": 0.8242, "step": 5156 }, { "epoch": 0.99, "grad_norm": 1.1031137338034631, "learning_rate": 3.2629330372246915e-09, "loss": 0.7877, "step": 5157 }, { "epoch": 0.99, "grad_norm": 1.0945615741938688, "learning_rate": 3.105714777501545e-09, "loss": 0.8054, "step": 5158 }, { "epoch": 0.99, "grad_norm": 0.8731923915467522, "learning_rate": 2.9523776563422644e-09, "loss": 0.562, "step": 5159 }, { "epoch": 0.99, "grad_norm": 1.0908262682524184, "learning_rate": 2.802921733278119e-09, "loss": 0.873, "step": 5160 }, { "epoch": 0.99, "grad_norm": 0.839643813054176, "learning_rate": 2.657347066333804e-09, "loss": 0.6339, "step": 5161 }, { "epoch": 0.99, "grad_norm": 0.8546738507760512, "learning_rate": 2.5156537120263335e-09, "loss": 0.5956, "step": 5162 }, { "epoch": 0.99, "grad_norm": 1.002047124319167, "learning_rate": 2.3778417253650376e-09, "loss": 0.8403, "step": 5163 }, { "epoch": 0.99, "grad_norm": 1.1770394862674398, "learning_rate": 2.2439111598537844e-09, "loss": 0.9075, "step": 5164 }, { "epoch": 0.99, "grad_norm": 0.7776569237000979, "learning_rate": 2.113862067488759e-09, "loss": 0.5947, "step": 5165 }, { "epoch": 0.99, "grad_norm": 1.0848628372320588, "learning_rate": 1.987694498760684e-09, "loss": 0.8113, "step": 5166 }, { "epoch": 0.99, "grad_norm": 1.0331159769678242, "learning_rate": 1.865408502650379e-09, "loss": 0.8347, "step": 5167 }, { "epoch": 0.99, "grad_norm": 1.0337525918589623, "learning_rate": 1.747004126635421e-09, "loss": 0.7686, "step": 5168 }, { "epoch": 0.99, "grad_norm": 1.0199316852290263, "learning_rate": 1.6324814166823744e-09, "loss": 0.8386, "step": 5169 }, { "epoch": 0.99, "grad_norm": 1.119525481461759, "learning_rate": 1.5218404172545609e-09, "loss": 0.824, "step": 5170 }, { "epoch": 0.99, "grad_norm": 1.0326995938665384, "learning_rate": 1.415081171305399e-09, "loss": 0.7708, "step": 5171 }, { "epoch": 0.99, "grad_norm": 1.1458784535900357, "learning_rate": 1.3122037202828452e-09, "loss": 0.8105, "step": 5172 }, { "epoch": 1.0, "grad_norm": 0.9805477647649683, "learning_rate": 1.2132081041282829e-09, "loss": 0.8103, "step": 5173 }, { "epoch": 1.0, "grad_norm": 1.1042021312356394, "learning_rate": 1.1180943612754124e-09, "loss": 0.8521, "step": 5174 }, { "epoch": 1.0, "grad_norm": 1.0698431741105094, "learning_rate": 1.026862528649142e-09, "loss": 0.8862, "step": 5175 }, { "epoch": 1.0, "grad_norm": 0.9648240793014491, "learning_rate": 9.39512641668916e-10, "loss": 0.8257, "step": 5176 }, { "epoch": 1.0, "grad_norm": 1.0162999654396119, "learning_rate": 8.560447342487177e-10, "loss": 0.8589, "step": 5177 }, { "epoch": 1.0, "grad_norm": 0.9971899064549632, "learning_rate": 7.764588387915161e-10, "loss": 0.8145, "step": 5178 }, { "epoch": 1.0, "grad_norm": 0.9441112092623923, "learning_rate": 7.007549861970387e-10, "loss": 0.8121, "step": 5179 }, { "epoch": 1.0, "grad_norm": 1.127520988058645, "learning_rate": 6.289332058551089e-10, "loss": 0.8987, "step": 5180 }, { "epoch": 1.0, "grad_norm": 0.9965896833939983, "learning_rate": 5.609935256500887e-10, "loss": 0.8667, "step": 5181 }, { "epoch": 1.0, "grad_norm": 0.9558693471874771, "learning_rate": 4.969359719586563e-10, "loss": 0.8257, "step": 5182 }, { "epoch": 1.0, "grad_norm": 0.9310303962260298, "learning_rate": 4.3676056964869764e-10, "loss": 0.8352, "step": 5183 }, { "epoch": 1.0, "grad_norm": 0.8870049796603872, "learning_rate": 3.804673420837457e-10, "loss": 0.5549, "step": 5184 }, { "epoch": 1.0, "grad_norm": 1.0379449850942533, "learning_rate": 3.2805631111743064e-10, "loss": 0.876, "step": 5185 }, { "epoch": 1.0, "grad_norm": 1.0160238401001278, "learning_rate": 2.795274971001405e-10, "loss": 0.8662, "step": 5186 }, { "epoch": 1.0, "grad_norm": 1.1185319784555885, "learning_rate": 2.3488091886902933e-10, "loss": 0.8796, "step": 5187 }, { "epoch": 1.0, "grad_norm": 1.0702274420973343, "learning_rate": 1.941165937602296e-10, "loss": 0.8208, "step": 5188 }, { "epoch": 1.0, "grad_norm": 0.9836354998667401, "learning_rate": 1.5723453759886042e-10, "loss": 0.8633, "step": 5189 }, { "epoch": 1.0, "grad_norm": 1.1211614139752795, "learning_rate": 1.2423476470346808e-10, "loss": 0.8281, "step": 5190 }, { "epoch": 1.0, "grad_norm": 0.9144638711934636, "learning_rate": 9.511728788602625e-11, "loss": 0.8179, "step": 5191 }, { "epoch": 1.0, "grad_norm": 0.9013785743045803, "learning_rate": 6.988211845082582e-11, "loss": 0.7883, "step": 5192 }, { "epoch": 1.0, "grad_norm": 1.0142858433793827, "learning_rate": 4.852926619447473e-11, "loss": 0.8116, "step": 5193 }, { "epoch": 1.0, "grad_norm": 0.9833958152472756, "learning_rate": 3.105873940811854e-11, "loss": 0.8059, "step": 5194 }, { "epoch": 1.0, "grad_norm": 1.0673712117261869, "learning_rate": 1.7470544874109706e-11, "loss": 0.8125, "step": 5195 }, { "epoch": 1.0, "grad_norm": 0.988139982078262, "learning_rate": 7.764687866007592e-12, "loss": 0.8452, "step": 5196 }, { "epoch": 1.0, "grad_norm": 0.9679005644742323, "learning_rate": 1.9411721552398123e-12, "loss": 0.8488, "step": 5197 }, { "epoch": 1.0, "grad_norm": 1.0112321806192759, "learning_rate": 0.0, "loss": 0.6831, "step": 5198 }, { "epoch": 1.0, "step": 5198, "total_flos": 1.8068423294096245e+19, "train_loss": 0.8593807418606014, "train_runtime": 41142.7159, "train_samples_per_second": 16.17, "train_steps_per_second": 0.126 } ], "logging_steps": 1.0, "max_steps": 5198, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 1000, "total_flos": 1.8068423294096245e+19, "train_batch_size": 8, "trial_name": null, "trial_params": null }