diff --git "a/illad_llama2/training_graph.json" "b/illad_llama2/training_graph.json" new file mode 100644--- /dev/null +++ "b/illad_llama2/training_graph.json" @@ -0,0 +1,14750 @@ +[ + { + "current_steps": 0, + "loss": 2.3935, + "learning_rate": 1e-08, + "epoch": 0.001221001221001221 + }, + { + "current_steps": 1, + "loss": 2.427, + "learning_rate": 2e-08, + "epoch": 0.002442002442002442 + }, + { + "current_steps": 2, + "loss": 2.6282, + "learning_rate": 3e-08, + "epoch": 0.003663003663003663 + }, + { + "current_steps": 3, + "loss": 2.4957, + "learning_rate": 4e-08, + "epoch": 0.004884004884004884 + }, + { + "current_steps": 4, + "loss": 1.9569, + "learning_rate": 5e-08, + "epoch": 0.006105006105006105 + }, + { + "current_steps": 5, + "loss": 2.6674, + "learning_rate": 6e-08, + "epoch": 0.007326007326007326 + }, + { + "current_steps": 6, + "loss": 2.4842, + "learning_rate": 7e-08, + "epoch": 0.008547008547008548 + }, + { + "current_steps": 7, + "loss": 2.5716, + "learning_rate": 8e-08, + "epoch": 0.009768009768009768 + }, + { + "current_steps": 8, + "loss": 2.4324, + "learning_rate": 9e-08, + "epoch": 0.01098901098901099 + }, + { + "current_steps": 9, + "loss": 2.4255, + "learning_rate": 1e-07, + "epoch": 0.01221001221001221 + }, + { + "current_steps": 10, + "loss": 2.2315, + "learning_rate": 1.0999999999999999e-07, + "epoch": 0.013431013431013432 + }, + { + "current_steps": 11, + "loss": 2.7133, + "learning_rate": 1.2e-07, + "epoch": 0.014652014652014652 + }, + { + "current_steps": 12, + "loss": 2.5869, + "learning_rate": 1.3e-07, + "epoch": 0.015873015873015872 + }, + { + "current_steps": 13, + "loss": 2.3855, + "learning_rate": 1.4e-07, + "epoch": 0.017094017094017096 + }, + { + "current_steps": 14, + "loss": 2.5845, + "learning_rate": 1.5e-07, + "epoch": 0.018315018315018316 + }, + { + "current_steps": 15, + "loss": 2.6255, + "learning_rate": 1.6e-07, + "epoch": 0.019536019536019536 + }, + { + "current_steps": 16, + "loss": 2.5738, + "learning_rate": 1.7000000000000001e-07, + "epoch": 0.020757020757020756 + }, + { + "current_steps": 17, + "loss": 2.5871, + "learning_rate": 1.8e-07, + "epoch": 0.02197802197802198 + }, + { + "current_steps": 18, + "loss": 2.4754, + "learning_rate": 1.8999999999999998e-07, + "epoch": 0.0231990231990232 + }, + { + "current_steps": 19, + "loss": 2.4605, + "learning_rate": 2e-07, + "epoch": 0.02442002442002442 + }, + { + "current_steps": 20, + "loss": 2.6471, + "learning_rate": 2.0999999999999997e-07, + "epoch": 0.02564102564102564 + }, + { + "current_steps": 21, + "loss": 2.0259, + "learning_rate": 2.1999999999999998e-07, + "epoch": 0.026862026862026864 + }, + { + "current_steps": 22, + "loss": 2.6163, + "learning_rate": 2.3e-07, + "epoch": 0.028083028083028084 + }, + { + "current_steps": 23, + "loss": 2.6709, + "learning_rate": 2.4e-07, + "epoch": 0.029304029304029304 + }, + { + "current_steps": 24, + "loss": 2.3626, + "learning_rate": 2.5e-07, + "epoch": 0.030525030525030524 + }, + { + "current_steps": 25, + "loss": 2.627, + "learning_rate": 2.5e-07, + "epoch": 0.031746031746031744 + }, + { + "current_steps": 26, + "loss": 2.5365, + "learning_rate": 2.6e-07, + "epoch": 0.03296703296703297 + }, + { + "current_steps": 27, + "loss": 2.5879, + "learning_rate": 2.7e-07, + "epoch": 0.03418803418803419 + }, + { + "current_steps": 28, + "loss": 2.0731, + "learning_rate": 2.8e-07, + "epoch": 0.03540903540903541 + }, + { + "current_steps": 29, + "loss": 2.5338, + "learning_rate": 2.9e-07, + "epoch": 0.03663003663003663 + }, + { + "current_steps": 30, + "loss": 2.5705, + "learning_rate": 3e-07, + "epoch": 0.03785103785103785 + }, + { + "current_steps": 31, + "loss": 2.5661, + "learning_rate": 3.1e-07, + "epoch": 0.03907203907203907 + }, + { + "current_steps": 32, + "loss": 2.0758, + "learning_rate": 3.2e-07, + "epoch": 0.040293040293040296 + }, + { + "current_steps": 33, + "loss": 2.5949, + "learning_rate": 3.3e-07, + "epoch": 0.04151404151404151 + }, + { + "current_steps": 34, + "loss": 2.677, + "learning_rate": 3.4000000000000003e-07, + "epoch": 0.042735042735042736 + }, + { + "current_steps": 35, + "loss": 2.4305, + "learning_rate": 3.5e-07, + "epoch": 0.04395604395604396 + }, + { + "current_steps": 36, + "loss": 2.5018, + "learning_rate": 3.6e-07, + "epoch": 0.045177045177045176 + }, + { + "current_steps": 37, + "loss": 2.5925, + "learning_rate": 3.7e-07, + "epoch": 0.0463980463980464 + }, + { + "current_steps": 38, + "loss": 2.5883, + "learning_rate": 3.7999999999999996e-07, + "epoch": 0.047619047619047616 + }, + { + "current_steps": 39, + "loss": 2.8259, + "learning_rate": 3.8999999999999997e-07, + "epoch": 0.04884004884004884 + }, + { + "current_steps": 40, + "loss": 2.4843, + "learning_rate": 4e-07, + "epoch": 0.050061050061050064 + }, + { + "current_steps": 41, + "loss": 2.8473, + "learning_rate": 4.0999999999999994e-07, + "epoch": 0.05128205128205128 + }, + { + "current_steps": 42, + "loss": 1.9554, + "learning_rate": 4.1999999999999995e-07, + "epoch": 0.052503052503052504 + }, + { + "current_steps": 43, + "loss": 2.444, + "learning_rate": 4.2999999999999996e-07, + "epoch": 0.05372405372405373 + }, + { + "current_steps": 44, + "loss": 2.5349, + "learning_rate": 4.3999999999999997e-07, + "epoch": 0.054945054945054944 + }, + { + "current_steps": 45, + "loss": 2.2713, + "learning_rate": 4.5e-07, + "epoch": 0.05616605616605617 + }, + { + "current_steps": 46, + "loss": 2.4983, + "learning_rate": 4.6e-07, + "epoch": 0.057387057387057384 + }, + { + "current_steps": 47, + "loss": 2.5988, + "learning_rate": 4.6999999999999995e-07, + "epoch": 0.05860805860805861 + }, + { + "current_steps": 48, + "loss": 2.5586, + "learning_rate": 4.8e-07, + "epoch": 0.05982905982905983 + }, + { + "current_steps": 49, + "loss": 2.5492, + "learning_rate": 4.9e-07, + "epoch": 0.06105006105006105 + }, + { + "current_steps": 50, + "loss": 2.5681, + "learning_rate": 5e-07, + "epoch": 0.06227106227106227 + }, + { + "current_steps": 51, + "loss": 2.7799, + "learning_rate": 5.1e-07, + "epoch": 0.06349206349206349 + }, + { + "current_steps": 52, + "loss": 2.354, + "learning_rate": 5.1e-07, + "epoch": 0.06471306471306472 + }, + { + "current_steps": 53, + "loss": 2.5577, + "learning_rate": 5.2e-07, + "epoch": 0.06593406593406594 + }, + { + "current_steps": 54, + "loss": 2.6487, + "learning_rate": 5.3e-07, + "epoch": 0.06715506715506715 + }, + { + "current_steps": 55, + "loss": 2.5726, + "learning_rate": 5.4e-07, + "epoch": 0.06837606837606838 + }, + { + "current_steps": 56, + "loss": 2.4458, + "learning_rate": 5.5e-07, + "epoch": 0.0695970695970696 + }, + { + "current_steps": 57, + "loss": 2.4041, + "learning_rate": 5.6e-07, + "epoch": 0.07081807081807082 + }, + { + "current_steps": 58, + "loss": 2.5806, + "learning_rate": 5.699999999999999e-07, + "epoch": 0.07203907203907203 + }, + { + "current_steps": 59, + "loss": 2.6063, + "learning_rate": 5.8e-07, + "epoch": 0.07326007326007326 + }, + { + "current_steps": 60, + "loss": 2.0815, + "learning_rate": 5.9e-07, + "epoch": 0.07448107448107448 + }, + { + "current_steps": 61, + "loss": 2.3515, + "learning_rate": 6e-07, + "epoch": 0.0757020757020757 + }, + { + "current_steps": 62, + "loss": 2.4071, + "learning_rate": 6.1e-07, + "epoch": 0.07692307692307693 + }, + { + "current_steps": 63, + "loss": 2.5888, + "learning_rate": 6.2e-07, + "epoch": 0.07814407814407814 + }, + { + "current_steps": 64, + "loss": 2.583, + "learning_rate": 6.3e-07, + "epoch": 0.07936507936507936 + }, + { + "current_steps": 65, + "loss": 2.129, + "learning_rate": 6.4e-07, + "epoch": 0.08058608058608059 + }, + { + "current_steps": 66, + "loss": 2.6407, + "learning_rate": 6.4e-07, + "epoch": 0.08180708180708181 + }, + { + "current_steps": 67, + "loss": 2.3789, + "learning_rate": 6.5e-07, + "epoch": 0.08302808302808302 + }, + { + "current_steps": 68, + "loss": 2.5319, + "learning_rate": 6.6e-07, + "epoch": 0.08424908424908426 + }, + { + "current_steps": 69, + "loss": 2.4597, + "learning_rate": 6.7e-07, + "epoch": 0.08547008547008547 + }, + { + "current_steps": 70, + "loss": 2.4991, + "learning_rate": 6.800000000000001e-07, + "epoch": 0.08669108669108669 + }, + { + "current_steps": 71, + "loss": 2.5539, + "learning_rate": 6.9e-07, + "epoch": 0.08791208791208792 + }, + { + "current_steps": 72, + "loss": 2.5228, + "learning_rate": 7e-07, + "epoch": 0.08913308913308914 + }, + { + "current_steps": 73, + "loss": 2.8614, + "learning_rate": 7.1e-07, + "epoch": 0.09035409035409035 + }, + { + "current_steps": 74, + "loss": 2.8125, + "learning_rate": 7.2e-07, + "epoch": 0.09157509157509157 + }, + { + "current_steps": 75, + "loss": 2.708, + "learning_rate": 7.3e-07, + "epoch": 0.0927960927960928 + }, + { + "current_steps": 76, + "loss": 2.6315, + "learning_rate": 7.4e-07, + "epoch": 0.09401709401709402 + }, + { + "current_steps": 77, + "loss": 2.4394, + "learning_rate": 7.5e-07, + "epoch": 0.09523809523809523 + }, + { + "current_steps": 78, + "loss": 2.6056, + "learning_rate": 7.599999999999999e-07, + "epoch": 0.09645909645909646 + }, + { + "current_steps": 79, + "loss": 2.3799, + "learning_rate": 7.699999999999999e-07, + "epoch": 0.09768009768009768 + }, + { + "current_steps": 80, + "loss": 2.5796, + "learning_rate": 7.799999999999999e-07, + "epoch": 0.0989010989010989 + }, + { + "current_steps": 81, + "loss": 2.5984, + "learning_rate": 7.9e-07, + "epoch": 0.10012210012210013 + }, + { + "current_steps": 82, + "loss": 2.4946, + "learning_rate": 8e-07, + "epoch": 0.10134310134310134 + }, + { + "current_steps": 83, + "loss": 2.6209, + "learning_rate": 8.1e-07, + "epoch": 0.10256410256410256 + }, + { + "current_steps": 84, + "loss": 2.1809, + "learning_rate": 8.199999999999999e-07, + "epoch": 0.10378510378510379 + }, + { + "current_steps": 85, + "loss": 2.6441, + "learning_rate": 8.299999999999999e-07, + "epoch": 0.10500610500610501 + }, + { + "current_steps": 86, + "loss": 2.4489, + "learning_rate": 8.399999999999999e-07, + "epoch": 0.10622710622710622 + }, + { + "current_steps": 87, + "loss": 2.5332, + "learning_rate": 8.499999999999999e-07, + "epoch": 0.10744810744810745 + }, + { + "current_steps": 88, + "loss": 2.5269, + "learning_rate": 8.599999999999999e-07, + "epoch": 0.10866910866910867 + }, + { + "current_steps": 89, + "loss": 2.6248, + "learning_rate": 8.699999999999999e-07, + "epoch": 0.10989010989010989 + }, + { + "current_steps": 90, + "loss": 2.4317, + "learning_rate": 8.799999999999999e-07, + "epoch": 0.1111111111111111 + }, + { + "current_steps": 91, + "loss": 2.5338, + "learning_rate": 8.9e-07, + "epoch": 0.11233211233211234 + }, + { + "current_steps": 92, + "loss": 2.5597, + "learning_rate": 9e-07, + "epoch": 0.11355311355311355 + }, + { + "current_steps": 93, + "loss": 2.4402, + "learning_rate": 9.1e-07, + "epoch": 0.11477411477411477 + }, + { + "current_steps": 94, + "loss": 2.522, + "learning_rate": 9.2e-07, + "epoch": 0.115995115995116 + }, + { + "current_steps": 95, + "loss": 2.5582, + "learning_rate": 9.3e-07, + "epoch": 0.11721611721611722 + }, + { + "current_steps": 96, + "loss": 2.5761, + "learning_rate": 9.399999999999999e-07, + "epoch": 0.11843711843711843 + }, + { + "current_steps": 97, + "loss": 2.7143, + "learning_rate": 9.499999999999999e-07, + "epoch": 0.11965811965811966 + }, + { + "current_steps": 98, + "loss": 2.6796, + "learning_rate": 9.6e-07, + "epoch": 0.12087912087912088 + }, + { + "current_steps": 99, + "loss": 1.9913, + "learning_rate": 9.7e-07, + "epoch": 0.1221001221001221 + }, + { + "current_steps": 100, + "loss": 2.5512, + "learning_rate": 9.8e-07, + "epoch": 0.12332112332112333 + }, + { + "current_steps": 101, + "loss": 2.761, + "learning_rate": 9.9e-07, + "epoch": 0.12454212454212454 + }, + { + "current_steps": 102, + "loss": 2.7906, + "learning_rate": 1e-06, + "epoch": 0.12576312576312576 + }, + { + "current_steps": 103, + "loss": 2.5021, + "learning_rate": 9.995757318625371e-07, + "epoch": 0.12698412698412698 + }, + { + "current_steps": 104, + "loss": 2.606, + "learning_rate": 9.991514637250743e-07, + "epoch": 0.1282051282051282 + }, + { + "current_steps": 105, + "loss": 2.409, + "learning_rate": 9.987271955876113e-07, + "epoch": 0.12942612942612944 + }, + { + "current_steps": 106, + "loss": 2.8096, + "learning_rate": 9.983029274501484e-07, + "epoch": 0.13064713064713065 + }, + { + "current_steps": 107, + "loss": 2.5078, + "learning_rate": 9.978786593126856e-07, + "epoch": 0.13186813186813187 + }, + { + "current_steps": 108, + "loss": 2.5554, + "learning_rate": 9.974543911752228e-07, + "epoch": 0.1330891330891331 + }, + { + "current_steps": 109, + "loss": 2.5927, + "learning_rate": 9.970301230377597e-07, + "epoch": 0.1343101343101343 + }, + { + "current_steps": 110, + "loss": 2.6233, + "learning_rate": 9.966058549002969e-07, + "epoch": 0.13553113553113552 + }, + { + "current_steps": 111, + "loss": 2.5519, + "learning_rate": 9.96181586762834e-07, + "epoch": 0.13675213675213677 + }, + { + "current_steps": 112, + "loss": 2.4663, + "learning_rate": 9.957573186253712e-07, + "epoch": 0.13797313797313798 + }, + { + "current_steps": 113, + "loss": 2.4989, + "learning_rate": 9.953330504879082e-07, + "epoch": 0.1391941391941392 + }, + { + "current_steps": 114, + "loss": 2.5721, + "learning_rate": 9.949087823504454e-07, + "epoch": 0.14041514041514042 + }, + { + "current_steps": 115, + "loss": 2.5821, + "learning_rate": 9.944845142129825e-07, + "epoch": 0.14163614163614163 + }, + { + "current_steps": 116, + "loss": 2.4978, + "learning_rate": 9.940602460755197e-07, + "epoch": 0.14285714285714285 + }, + { + "current_steps": 117, + "loss": 2.5248, + "learning_rate": 9.936359779380567e-07, + "epoch": 0.14407814407814407 + }, + { + "current_steps": 118, + "loss": 2.4826, + "learning_rate": 9.932117098005938e-07, + "epoch": 0.1452991452991453 + }, + { + "current_steps": 119, + "loss": 1.7454, + "learning_rate": 9.927874416631312e-07, + "epoch": 0.14652014652014653 + }, + { + "current_steps": 120, + "loss": 1.9684, + "learning_rate": 9.923631735256682e-07, + "epoch": 0.14774114774114774 + }, + { + "current_steps": 121, + "loss": 2.5856, + "learning_rate": 9.919389053882053e-07, + "epoch": 0.14896214896214896 + }, + { + "current_steps": 122, + "loss": 2.3059, + "learning_rate": 9.915146372507425e-07, + "epoch": 0.15018315018315018 + }, + { + "current_steps": 123, + "loss": 2.7886, + "learning_rate": 9.910903691132797e-07, + "epoch": 0.1514041514041514 + }, + { + "current_steps": 124, + "loss": 2.6589, + "learning_rate": 9.906661009758166e-07, + "epoch": 0.15262515262515264 + }, + { + "current_steps": 125, + "loss": 2.7176, + "learning_rate": 9.902418328383538e-07, + "epoch": 0.15384615384615385 + }, + { + "current_steps": 126, + "loss": 2.5188, + "learning_rate": 9.89817564700891e-07, + "epoch": 0.15506715506715507 + }, + { + "current_steps": 127, + "loss": 2.5287, + "learning_rate": 9.893932965634281e-07, + "epoch": 0.1562881562881563 + }, + { + "current_steps": 128, + "loss": 2.403, + "learning_rate": 9.88969028425965e-07, + "epoch": 0.1575091575091575 + }, + { + "current_steps": 129, + "loss": 2.5564, + "learning_rate": 9.885447602885023e-07, + "epoch": 0.15873015873015872 + }, + { + "current_steps": 130, + "loss": 2.6201, + "learning_rate": 9.881204921510394e-07, + "epoch": 0.15995115995115994 + }, + { + "current_steps": 131, + "loss": 2.1575, + "learning_rate": 9.876962240135766e-07, + "epoch": 0.16117216117216118 + }, + { + "current_steps": 132, + "loss": 2.0815, + "learning_rate": 9.872719558761136e-07, + "epoch": 0.1623931623931624 + }, + { + "current_steps": 133, + "loss": 2.3951, + "learning_rate": 9.868476877386507e-07, + "epoch": 0.16361416361416362 + }, + { + "current_steps": 134, + "loss": 2.4849, + "learning_rate": 9.86423419601188e-07, + "epoch": 0.16483516483516483 + }, + { + "current_steps": 135, + "loss": 2.562, + "learning_rate": 9.85999151463725e-07, + "epoch": 0.16605616605616605 + }, + { + "current_steps": 136, + "loss": 2.0193, + "learning_rate": 9.855748833262623e-07, + "epoch": 0.16727716727716727 + }, + { + "current_steps": 137, + "loss": 2.3799, + "learning_rate": 9.851506151887992e-07, + "epoch": 0.1684981684981685 + }, + { + "current_steps": 138, + "loss": 2.6133, + "learning_rate": 9.847263470513364e-07, + "epoch": 0.16971916971916973 + }, + { + "current_steps": 139, + "loss": 2.6755, + "learning_rate": 9.843020789138735e-07, + "epoch": 0.17094017094017094 + }, + { + "current_steps": 140, + "loss": 2.6192, + "learning_rate": 9.838778107764107e-07, + "epoch": 0.17216117216117216 + }, + { + "current_steps": 141, + "loss": 2.6767, + "learning_rate": 9.834535426389477e-07, + "epoch": 0.17338217338217338 + }, + { + "current_steps": 142, + "loss": 2.6745, + "learning_rate": 9.830292745014848e-07, + "epoch": 0.1746031746031746 + }, + { + "current_steps": 143, + "loss": 2.6279, + "learning_rate": 9.82605006364022e-07, + "epoch": 0.17582417582417584 + }, + { + "current_steps": 144, + "loss": 2.3162, + "learning_rate": 9.821807382265592e-07, + "epoch": 0.17704517704517705 + }, + { + "current_steps": 145, + "loss": 2.7021, + "learning_rate": 9.817564700890961e-07, + "epoch": 0.17826617826617827 + }, + { + "current_steps": 146, + "loss": 2.4844, + "learning_rate": 9.813322019516333e-07, + "epoch": 0.1794871794871795 + }, + { + "current_steps": 147, + "loss": 2.4637, + "learning_rate": 9.809079338141705e-07, + "epoch": 0.1807081807081807 + }, + { + "current_steps": 148, + "loss": 2.718, + "learning_rate": 9.804836656767077e-07, + "epoch": 0.18192918192918192 + }, + { + "current_steps": 149, + "loss": 2.5759, + "learning_rate": 9.800593975392446e-07, + "epoch": 0.18315018315018314 + }, + { + "current_steps": 150, + "loss": 2.0082, + "learning_rate": 9.796351294017818e-07, + "epoch": 0.18437118437118438 + }, + { + "current_steps": 151, + "loss": 2.5261, + "learning_rate": 9.79210861264319e-07, + "epoch": 0.1855921855921856 + }, + { + "current_steps": 152, + "loss": 2.487, + "learning_rate": 9.787865931268561e-07, + "epoch": 0.18681318681318682 + }, + { + "current_steps": 153, + "loss": 2.5716, + "learning_rate": 9.783623249893933e-07, + "epoch": 0.18803418803418803 + }, + { + "current_steps": 154, + "loss": 2.4895, + "learning_rate": 9.779380568519305e-07, + "epoch": 0.18925518925518925 + }, + { + "current_steps": 155, + "loss": 2.5518, + "learning_rate": 9.775137887144676e-07, + "epoch": 0.19047619047619047 + }, + { + "current_steps": 156, + "loss": 2.654, + "learning_rate": 9.775137887144676e-07, + "epoch": 0.1916971916971917 + }, + { + "current_steps": 157, + "loss": 2.6914, + "learning_rate": 9.775137887144676e-07, + "epoch": 0.19291819291819293 + }, + { + "current_steps": 158, + "loss": 2.3965, + "learning_rate": 9.775137887144676e-07, + "epoch": 0.19413919413919414 + }, + { + "current_steps": 159, + "loss": 2.5333, + "learning_rate": 9.770895205770046e-07, + "epoch": 0.19536019536019536 + }, + { + "current_steps": 160, + "loss": 2.4514, + "learning_rate": 9.766652524395418e-07, + "epoch": 0.19658119658119658 + }, + { + "current_steps": 161, + "loss": 2.6335, + "learning_rate": 9.76240984302079e-07, + "epoch": 0.1978021978021978 + }, + { + "current_steps": 162, + "loss": 2.5331, + "learning_rate": 9.75816716164616e-07, + "epoch": 0.199023199023199 + }, + { + "current_steps": 163, + "loss": 2.4914, + "learning_rate": 9.75392448027153e-07, + "epoch": 0.20024420024420025 + }, + { + "current_steps": 164, + "loss": 2.5067, + "learning_rate": 9.749681798896902e-07, + "epoch": 0.20146520146520147 + }, + { + "current_steps": 165, + "loss": 2.0693, + "learning_rate": 9.745439117522274e-07, + "epoch": 0.2026862026862027 + }, + { + "current_steps": 166, + "loss": 2.5989, + "learning_rate": 9.741196436147646e-07, + "epoch": 0.2039072039072039 + }, + { + "current_steps": 167, + "loss": 2.4672, + "learning_rate": 9.736953754773015e-07, + "epoch": 0.20512820512820512 + }, + { + "current_steps": 168, + "loss": 2.6826, + "learning_rate": 9.732711073398387e-07, + "epoch": 0.20634920634920634 + }, + { + "current_steps": 169, + "loss": 2.7692, + "learning_rate": 9.728468392023759e-07, + "epoch": 0.20757020757020758 + }, + { + "current_steps": 170, + "loss": 2.3251, + "learning_rate": 9.72422571064913e-07, + "epoch": 0.2087912087912088 + }, + { + "current_steps": 171, + "loss": 2.799, + "learning_rate": 9.719983029274502e-07, + "epoch": 0.21001221001221002 + }, + { + "current_steps": 172, + "loss": 2.5995, + "learning_rate": 9.715740347899872e-07, + "epoch": 0.21123321123321123 + }, + { + "current_steps": 173, + "loss": 2.5914, + "learning_rate": 9.711497666525243e-07, + "epoch": 0.21245421245421245 + }, + { + "current_steps": 174, + "loss": 2.7071, + "learning_rate": 9.707254985150615e-07, + "epoch": 0.21367521367521367 + }, + { + "current_steps": 175, + "loss": 2.1536, + "learning_rate": 9.703012303775987e-07, + "epoch": 0.2148962148962149 + }, + { + "current_steps": 176, + "loss": 2.5152, + "learning_rate": 9.698769622401356e-07, + "epoch": 0.21611721611721613 + }, + { + "current_steps": 177, + "loss": 2.4975, + "learning_rate": 9.694526941026728e-07, + "epoch": 0.21733821733821734 + }, + { + "current_steps": 178, + "loss": 2.3497, + "learning_rate": 9.6902842596521e-07, + "epoch": 0.21855921855921856 + }, + { + "current_steps": 179, + "loss": 2.5726, + "learning_rate": 9.686041578277471e-07, + "epoch": 0.21978021978021978 + }, + { + "current_steps": 180, + "loss": 2.3357, + "learning_rate": 9.68179889690284e-07, + "epoch": 0.221001221001221 + }, + { + "current_steps": 181, + "loss": 2.5498, + "learning_rate": 9.677556215528213e-07, + "epoch": 0.2222222222222222 + }, + { + "current_steps": 182, + "loss": 2.612, + "learning_rate": 9.673313534153584e-07, + "epoch": 0.22344322344322345 + }, + { + "current_steps": 183, + "loss": 2.8084, + "learning_rate": 9.669070852778956e-07, + "epoch": 0.22466422466422467 + }, + { + "current_steps": 184, + "loss": 2.6041, + "learning_rate": 9.664828171404326e-07, + "epoch": 0.2258852258852259 + }, + { + "current_steps": 185, + "loss": 2.4154, + "learning_rate": 9.660585490029697e-07, + "epoch": 0.2271062271062271 + }, + { + "current_steps": 186, + "loss": 2.0642, + "learning_rate": 9.65634280865507e-07, + "epoch": 0.22832722832722832 + }, + { + "current_steps": 187, + "loss": 2.606, + "learning_rate": 9.65210012728044e-07, + "epoch": 0.22954822954822954 + }, + { + "current_steps": 188, + "loss": 2.6554, + "learning_rate": 9.647857445905812e-07, + "epoch": 0.23076923076923078 + }, + { + "current_steps": 189, + "loss": 2.5907, + "learning_rate": 9.643614764531182e-07, + "epoch": 0.231990231990232 + }, + { + "current_steps": 190, + "loss": 2.573, + "learning_rate": 9.639372083156556e-07, + "epoch": 0.23321123321123322 + }, + { + "current_steps": 191, + "loss": 2.4267, + "learning_rate": 9.635129401781925e-07, + "epoch": 0.23443223443223443 + }, + { + "current_steps": 192, + "loss": 2.5787, + "learning_rate": 9.630886720407297e-07, + "epoch": 0.23565323565323565 + }, + { + "current_steps": 193, + "loss": 2.6262, + "learning_rate": 9.626644039032669e-07, + "epoch": 0.23687423687423687 + }, + { + "current_steps": 194, + "loss": 2.601, + "learning_rate": 9.62240135765804e-07, + "epoch": 0.23809523809523808 + }, + { + "current_steps": 195, + "loss": 2.6435, + "learning_rate": 9.61815867628341e-07, + "epoch": 0.23931623931623933 + }, + { + "current_steps": 196, + "loss": 2.321, + "learning_rate": 9.613915994908782e-07, + "epoch": 0.24053724053724054 + }, + { + "current_steps": 197, + "loss": 2.4241, + "learning_rate": 9.609673313534154e-07, + "epoch": 0.24175824175824176 + }, + { + "current_steps": 198, + "loss": 2.5011, + "learning_rate": 9.605430632159525e-07, + "epoch": 0.24297924297924298 + }, + { + "current_steps": 199, + "loss": 2.6523, + "learning_rate": 9.601187950784895e-07, + "epoch": 0.2442002442002442 + }, + { + "current_steps": 200, + "loss": 2.3946, + "learning_rate": 9.596945269410267e-07, + "epoch": 0.2454212454212454 + }, + { + "current_steps": 201, + "loss": 2.5013, + "learning_rate": 9.592702588035638e-07, + "epoch": 0.24664224664224665 + }, + { + "current_steps": 202, + "loss": 2.4134, + "learning_rate": 9.58845990666101e-07, + "epoch": 0.24786324786324787 + }, + { + "current_steps": 203, + "loss": 2.4556, + "learning_rate": 9.584217225286382e-07, + "epoch": 0.2490842490842491 + }, + { + "current_steps": 204, + "loss": 2.5096, + "learning_rate": 9.579974543911751e-07, + "epoch": 0.2503052503052503 + }, + { + "current_steps": 205, + "loss": 2.4952, + "learning_rate": 9.575731862537123e-07, + "epoch": 0.2515262515262515 + }, + { + "current_steps": 206, + "loss": 2.7396, + "learning_rate": 9.571489181162495e-07, + "epoch": 0.25274725274725274 + }, + { + "current_steps": 207, + "loss": 2.5148, + "learning_rate": 9.567246499787866e-07, + "epoch": 0.25396825396825395 + }, + { + "current_steps": 208, + "loss": 2.5861, + "learning_rate": 9.563003818413236e-07, + "epoch": 0.25518925518925517 + }, + { + "current_steps": 209, + "loss": 2.5593, + "learning_rate": 9.558761137038608e-07, + "epoch": 0.2564102564102564 + }, + { + "current_steps": 210, + "loss": 2.5366, + "learning_rate": 9.55451845566398e-07, + "epoch": 0.2576312576312576 + }, + { + "current_steps": 211, + "loss": 2.5322, + "learning_rate": 9.55027577428935e-07, + "epoch": 0.2588522588522589 + }, + { + "current_steps": 212, + "loss": 2.4472, + "learning_rate": 9.54603309291472e-07, + "epoch": 0.2600732600732601 + }, + { + "current_steps": 213, + "loss": 2.308, + "learning_rate": 9.541790411540092e-07, + "epoch": 0.2612942612942613 + }, + { + "current_steps": 214, + "loss": 2.4911, + "learning_rate": 9.537547730165464e-07, + "epoch": 0.2625152625152625 + }, + { + "current_steps": 215, + "loss": 2.5503, + "learning_rate": 9.533305048790835e-07, + "epoch": 0.26373626373626374 + }, + { + "current_steps": 216, + "loss": 2.5303, + "learning_rate": 9.529062367416206e-07, + "epoch": 0.26495726495726496 + }, + { + "current_steps": 217, + "loss": 2.5558, + "learning_rate": 9.524819686041578e-07, + "epoch": 0.2661782661782662 + }, + { + "current_steps": 218, + "loss": 2.459, + "learning_rate": 9.520577004666949e-07, + "epoch": 0.2673992673992674 + }, + { + "current_steps": 219, + "loss": 2.3976, + "learning_rate": 9.51633432329232e-07, + "epoch": 0.2686202686202686 + }, + { + "current_steps": 220, + "loss": 2.6515, + "learning_rate": 9.512091641917691e-07, + "epoch": 0.2698412698412698 + }, + { + "current_steps": 221, + "loss": 2.4774, + "learning_rate": 9.507848960543063e-07, + "epoch": 0.27106227106227104 + }, + { + "current_steps": 222, + "loss": 2.319, + "learning_rate": 9.503606279168433e-07, + "epoch": 0.27228327228327226 + }, + { + "current_steps": 223, + "loss": 2.529, + "learning_rate": 9.499363597793806e-07, + "epoch": 0.27350427350427353 + }, + { + "current_steps": 224, + "loss": 2.5219, + "learning_rate": 9.495120916419177e-07, + "epoch": 0.27472527472527475 + }, + { + "current_steps": 225, + "loss": 2.4815, + "learning_rate": 9.490878235044548e-07, + "epoch": 0.27594627594627597 + }, + { + "current_steps": 226, + "loss": 2.6035, + "learning_rate": 9.486635553669919e-07, + "epoch": 0.2771672771672772 + }, + { + "current_steps": 227, + "loss": 2.5406, + "learning_rate": 9.482392872295291e-07, + "epoch": 0.2783882783882784 + }, + { + "current_steps": 228, + "loss": 2.4585, + "learning_rate": 9.478150190920661e-07, + "epoch": 0.2796092796092796 + }, + { + "current_steps": 229, + "loss": 2.5661, + "learning_rate": 9.473907509546033e-07, + "epoch": 0.28083028083028083 + }, + { + "current_steps": 230, + "loss": 2.6045, + "learning_rate": 9.469664828171404e-07, + "epoch": 0.28205128205128205 + }, + { + "current_steps": 231, + "loss": 2.5482, + "learning_rate": 9.465422146796775e-07, + "epoch": 0.28327228327228327 + }, + { + "current_steps": 232, + "loss": 2.4796, + "learning_rate": 9.461179465422147e-07, + "epoch": 0.2844932844932845 + }, + { + "current_steps": 233, + "loss": 2.5172, + "learning_rate": 9.456936784047518e-07, + "epoch": 0.2857142857142857 + }, + { + "current_steps": 234, + "loss": 2.3688, + "learning_rate": 9.452694102672889e-07, + "epoch": 0.2869352869352869 + }, + { + "current_steps": 235, + "loss": 2.7506, + "learning_rate": 9.44845142129826e-07, + "epoch": 0.28815628815628813 + }, + { + "current_steps": 236, + "loss": 2.0191, + "learning_rate": 9.444208739923632e-07, + "epoch": 0.2893772893772894 + }, + { + "current_steps": 237, + "loss": 1.8961, + "learning_rate": 9.439966058549002e-07, + "epoch": 0.2905982905982906 + }, + { + "current_steps": 238, + "loss": 2.5797, + "learning_rate": 9.435723377174374e-07, + "epoch": 0.29181929181929184 + }, + { + "current_steps": 239, + "loss": 2.5701, + "learning_rate": 9.431480695799745e-07, + "epoch": 0.29304029304029305 + }, + { + "current_steps": 240, + "loss": 2.3347, + "learning_rate": 9.427238014425116e-07, + "epoch": 0.29426129426129427 + }, + { + "current_steps": 241, + "loss": 2.3285, + "learning_rate": 9.422995333050487e-07, + "epoch": 0.2954822954822955 + }, + { + "current_steps": 242, + "loss": 2.5442, + "learning_rate": 9.418752651675859e-07, + "epoch": 0.2967032967032967 + }, + { + "current_steps": 243, + "loss": 2.5416, + "learning_rate": 9.414509970301229e-07, + "epoch": 0.2979242979242979 + }, + { + "current_steps": 244, + "loss": 2.3862, + "learning_rate": 9.410267288926601e-07, + "epoch": 0.29914529914529914 + }, + { + "current_steps": 245, + "loss": 2.4958, + "learning_rate": 9.406024607551972e-07, + "epoch": 0.30036630036630035 + }, + { + "current_steps": 246, + "loss": 1.8262, + "learning_rate": 9.401781926177344e-07, + "epoch": 0.30158730158730157 + }, + { + "current_steps": 247, + "loss": 2.5104, + "learning_rate": 9.397539244802714e-07, + "epoch": 0.3028083028083028 + }, + { + "current_steps": 248, + "loss": 2.3749, + "learning_rate": 9.393296563428086e-07, + "epoch": 0.304029304029304 + }, + { + "current_steps": 249, + "loss": 2.449, + "learning_rate": 9.389053882053458e-07, + "epoch": 0.3052503052503053 + }, + { + "current_steps": 250, + "loss": 2.3889, + "learning_rate": 9.384811200678828e-07, + "epoch": 0.3064713064713065 + }, + { + "current_steps": 251, + "loss": 2.5679, + "learning_rate": 9.3805685193042e-07, + "epoch": 0.3076923076923077 + }, + { + "current_steps": 252, + "loss": 2.5338, + "learning_rate": 9.37632583792957e-07, + "epoch": 0.3089133089133089 + }, + { + "current_steps": 253, + "loss": 2.7013, + "learning_rate": 9.372083156554942e-07, + "epoch": 0.31013431013431014 + }, + { + "current_steps": 254, + "loss": 2.5647, + "learning_rate": 9.367840475180313e-07, + "epoch": 0.31135531135531136 + }, + { + "current_steps": 255, + "loss": 2.5057, + "learning_rate": 9.363597793805685e-07, + "epoch": 0.3125763125763126 + }, + { + "current_steps": 256, + "loss": 2.4171, + "learning_rate": 9.359355112431055e-07, + "epoch": 0.3137973137973138 + }, + { + "current_steps": 257, + "loss": 2.6526, + "learning_rate": 9.355112431056428e-07, + "epoch": 0.315018315018315 + }, + { + "current_steps": 258, + "loss": 2.359, + "learning_rate": 9.350869749681799e-07, + "epoch": 0.3162393162393162 + }, + { + "current_steps": 259, + "loss": 2.6916, + "learning_rate": 9.34662706830717e-07, + "epoch": 0.31746031746031744 + }, + { + "current_steps": 260, + "loss": 2.4634, + "learning_rate": 9.342384386932541e-07, + "epoch": 0.31868131868131866 + }, + { + "current_steps": 261, + "loss": 2.4506, + "learning_rate": 9.338141705557913e-07, + "epoch": 0.3199023199023199 + }, + { + "current_steps": 262, + "loss": 2.6015, + "learning_rate": 9.333899024183283e-07, + "epoch": 0.32112332112332115 + }, + { + "current_steps": 263, + "loss": 2.5388, + "learning_rate": 9.329656342808655e-07, + "epoch": 0.32234432234432236 + }, + { + "current_steps": 264, + "loss": 1.9073, + "learning_rate": 9.325413661434027e-07, + "epoch": 0.3235653235653236 + }, + { + "current_steps": 265, + "loss": 2.4846, + "learning_rate": 9.321170980059397e-07, + "epoch": 0.3247863247863248 + }, + { + "current_steps": 266, + "loss": 2.5317, + "learning_rate": 9.316928298684769e-07, + "epoch": 0.326007326007326 + }, + { + "current_steps": 267, + "loss": 2.5807, + "learning_rate": 9.31268561731014e-07, + "epoch": 0.32722832722832723 + }, + { + "current_steps": 268, + "loss": 2.5551, + "learning_rate": 9.308442935935511e-07, + "epoch": 0.32844932844932845 + }, + { + "current_steps": 269, + "loss": 2.3323, + "learning_rate": 9.304200254560882e-07, + "epoch": 0.32967032967032966 + }, + { + "current_steps": 270, + "loss": 2.4286, + "learning_rate": 9.299957573186254e-07, + "epoch": 0.3308913308913309 + }, + { + "current_steps": 271, + "loss": 2.5475, + "learning_rate": 9.295714891811624e-07, + "epoch": 0.3321123321123321 + }, + { + "current_steps": 272, + "loss": 2.6514, + "learning_rate": 9.291472210436996e-07, + "epoch": 0.3333333333333333 + }, + { + "current_steps": 273, + "loss": 2.5392, + "learning_rate": 9.287229529062367e-07, + "epoch": 0.33455433455433453 + }, + { + "current_steps": 274, + "loss": 2.6212, + "learning_rate": 9.282986847687738e-07, + "epoch": 0.33577533577533575 + }, + { + "current_steps": 275, + "loss": 2.5317, + "learning_rate": 9.278744166313109e-07, + "epoch": 0.336996336996337 + }, + { + "current_steps": 276, + "loss": 2.418, + "learning_rate": 9.274501484938481e-07, + "epoch": 0.33821733821733824 + }, + { + "current_steps": 277, + "loss": 2.5307, + "learning_rate": 9.270258803563851e-07, + "epoch": 0.33943833943833945 + }, + { + "current_steps": 278, + "loss": 2.4276, + "learning_rate": 9.266016122189223e-07, + "epoch": 0.34065934065934067 + }, + { + "current_steps": 279, + "loss": 2.4839, + "learning_rate": 9.261773440814594e-07, + "epoch": 0.3418803418803419 + }, + { + "current_steps": 280, + "loss": 2.3871, + "learning_rate": 9.257530759439965e-07, + "epoch": 0.3431013431013431 + }, + { + "current_steps": 281, + "loss": 2.5531, + "learning_rate": 9.253288078065337e-07, + "epoch": 0.3443223443223443 + }, + { + "current_steps": 282, + "loss": 2.4392, + "learning_rate": 9.249045396690708e-07, + "epoch": 0.34554334554334554 + }, + { + "current_steps": 283, + "loss": 2.594, + "learning_rate": 9.244802715316079e-07, + "epoch": 0.34676434676434675 + }, + { + "current_steps": 284, + "loss": 2.2793, + "learning_rate": 9.24056003394145e-07, + "epoch": 0.34798534798534797 + }, + { + "current_steps": 285, + "loss": 2.7076, + "learning_rate": 9.236317352566822e-07, + "epoch": 0.3492063492063492 + }, + { + "current_steps": 286, + "loss": 2.4417, + "learning_rate": 9.232074671192192e-07, + "epoch": 0.3504273504273504 + }, + { + "current_steps": 287, + "loss": 2.6322, + "learning_rate": 9.227831989817564e-07, + "epoch": 0.3516483516483517 + }, + { + "current_steps": 288, + "loss": 2.4649, + "learning_rate": 9.223589308442935e-07, + "epoch": 0.3528693528693529 + }, + { + "current_steps": 289, + "loss": 2.4423, + "learning_rate": 9.219346627068306e-07, + "epoch": 0.3540903540903541 + }, + { + "current_steps": 290, + "loss": 2.5944, + "learning_rate": 9.215103945693677e-07, + "epoch": 0.3553113553113553 + }, + { + "current_steps": 291, + "loss": 2.455, + "learning_rate": 9.21086126431905e-07, + "epoch": 0.35653235653235654 + }, + { + "current_steps": 292, + "loss": 2.4218, + "learning_rate": 9.20661858294442e-07, + "epoch": 0.35775335775335776 + }, + { + "current_steps": 293, + "loss": 2.5434, + "learning_rate": 9.202375901569792e-07, + "epoch": 0.358974358974359 + }, + { + "current_steps": 294, + "loss": 2.6101, + "learning_rate": 9.198133220195163e-07, + "epoch": 0.3601953601953602 + }, + { + "current_steps": 295, + "loss": 2.4027, + "learning_rate": 9.193890538820535e-07, + "epoch": 0.3614163614163614 + }, + { + "current_steps": 296, + "loss": 2.4974, + "learning_rate": 9.189647857445906e-07, + "epoch": 0.3626373626373626 + }, + { + "current_steps": 297, + "loss": 2.5903, + "learning_rate": 9.185405176071277e-07, + "epoch": 0.36385836385836384 + }, + { + "current_steps": 298, + "loss": 2.1658, + "learning_rate": 9.181162494696649e-07, + "epoch": 0.36507936507936506 + }, + { + "current_steps": 299, + "loss": 2.4969, + "learning_rate": 9.176919813322019e-07, + "epoch": 0.3663003663003663 + }, + { + "current_steps": 300, + "loss": 2.404, + "learning_rate": 9.172677131947391e-07, + "epoch": 0.36752136752136755 + }, + { + "current_steps": 301, + "loss": 1.9013, + "learning_rate": 9.168434450572762e-07, + "epoch": 0.36874236874236876 + }, + { + "current_steps": 302, + "loss": 2.386, + "learning_rate": 9.164191769198133e-07, + "epoch": 0.36996336996337 + }, + { + "current_steps": 303, + "loss": 2.4, + "learning_rate": 9.159949087823504e-07, + "epoch": 0.3711843711843712 + }, + { + "current_steps": 304, + "loss": 2.4898, + "learning_rate": 9.155706406448876e-07, + "epoch": 0.3724053724053724 + }, + { + "current_steps": 305, + "loss": 2.6182, + "learning_rate": 9.151463725074246e-07, + "epoch": 0.37362637362637363 + }, + { + "current_steps": 306, + "loss": 2.551, + "learning_rate": 9.147221043699618e-07, + "epoch": 0.37484737484737485 + }, + { + "current_steps": 307, + "loss": 2.5828, + "learning_rate": 9.142978362324989e-07, + "epoch": 0.37606837606837606 + }, + { + "current_steps": 308, + "loss": 2.413, + "learning_rate": 9.13873568095036e-07, + "epoch": 0.3772893772893773 + }, + { + "current_steps": 309, + "loss": 2.536, + "learning_rate": 9.134492999575731e-07, + "epoch": 0.3785103785103785 + }, + { + "current_steps": 310, + "loss": 2.601, + "learning_rate": 9.130250318201103e-07, + "epoch": 0.3797313797313797 + }, + { + "current_steps": 311, + "loss": 2.392, + "learning_rate": 9.126007636826474e-07, + "epoch": 0.38095238095238093 + }, + { + "current_steps": 312, + "loss": 2.6274, + "learning_rate": 9.121764955451845e-07, + "epoch": 0.38217338217338215 + }, + { + "current_steps": 313, + "loss": 2.5095, + "learning_rate": 9.117522274077217e-07, + "epoch": 0.3833943833943834 + }, + { + "current_steps": 314, + "loss": 2.6844, + "learning_rate": 9.113279592702587e-07, + "epoch": 0.38461538461538464 + }, + { + "current_steps": 315, + "loss": 2.5858, + "learning_rate": 9.109036911327959e-07, + "epoch": 0.38583638583638585 + }, + { + "current_steps": 316, + "loss": 2.3619, + "learning_rate": 9.10479422995333e-07, + "epoch": 0.38705738705738707 + }, + { + "current_steps": 317, + "loss": 2.5468, + "learning_rate": 9.100551548578701e-07, + "epoch": 0.3882783882783883 + }, + { + "current_steps": 318, + "loss": 2.4857, + "learning_rate": 9.096308867204072e-07, + "epoch": 0.3894993894993895 + }, + { + "current_steps": 319, + "loss": 2.5754, + "learning_rate": 9.092066185829444e-07, + "epoch": 0.3907203907203907 + }, + { + "current_steps": 320, + "loss": 2.5166, + "learning_rate": 9.087823504454814e-07, + "epoch": 0.39194139194139194 + }, + { + "current_steps": 321, + "loss": 2.6506, + "learning_rate": 9.083580823080186e-07, + "epoch": 0.39316239316239315 + }, + { + "current_steps": 322, + "loss": 2.5307, + "learning_rate": 9.079338141705557e-07, + "epoch": 0.39438339438339437 + }, + { + "current_steps": 323, + "loss": 2.577, + "learning_rate": 9.075095460330928e-07, + "epoch": 0.3956043956043956 + }, + { + "current_steps": 324, + "loss": 2.6592, + "learning_rate": 9.0708527789563e-07, + "epoch": 0.3968253968253968 + }, + { + "current_steps": 325, + "loss": 2.3876, + "learning_rate": 9.066610097581672e-07, + "epoch": 0.398046398046398 + }, + { + "current_steps": 326, + "loss": 2.4858, + "learning_rate": 9.062367416207043e-07, + "epoch": 0.3992673992673993 + }, + { + "current_steps": 327, + "loss": 2.4384, + "learning_rate": 9.058124734832414e-07, + "epoch": 0.4004884004884005 + }, + { + "current_steps": 328, + "loss": 2.4979, + "learning_rate": 9.053882053457786e-07, + "epoch": 0.4017094017094017 + }, + { + "current_steps": 329, + "loss": 2.4446, + "learning_rate": 9.049639372083156e-07, + "epoch": 0.40293040293040294 + }, + { + "current_steps": 330, + "loss": 2.6621, + "learning_rate": 9.045396690708528e-07, + "epoch": 0.40415140415140416 + }, + { + "current_steps": 331, + "loss": 2.4863, + "learning_rate": 9.041154009333899e-07, + "epoch": 0.4053724053724054 + }, + { + "current_steps": 332, + "loss": 2.5744, + "learning_rate": 9.03691132795927e-07, + "epoch": 0.4065934065934066 + }, + { + "current_steps": 333, + "loss": 2.5646, + "learning_rate": 9.032668646584641e-07, + "epoch": 0.4078144078144078 + }, + { + "current_steps": 334, + "loss": 1.925, + "learning_rate": 9.028425965210013e-07, + "epoch": 0.409035409035409 + }, + { + "current_steps": 335, + "loss": 2.5033, + "learning_rate": 9.024183283835383e-07, + "epoch": 0.41025641025641024 + }, + { + "current_steps": 336, + "loss": 2.5145, + "learning_rate": 9.019940602460755e-07, + "epoch": 0.41147741147741146 + }, + { + "current_steps": 337, + "loss": 2.519, + "learning_rate": 9.015697921086126e-07, + "epoch": 0.4126984126984127 + }, + { + "current_steps": 338, + "loss": 2.3268, + "learning_rate": 9.011455239711497e-07, + "epoch": 0.4139194139194139 + }, + { + "current_steps": 339, + "loss": 2.4844, + "learning_rate": 9.007212558336868e-07, + "epoch": 0.41514041514041516 + }, + { + "current_steps": 340, + "loss": 2.4087, + "learning_rate": 9.00296987696224e-07, + "epoch": 0.4163614163614164 + }, + { + "current_steps": 341, + "loss": 2.4918, + "learning_rate": 8.99872719558761e-07, + "epoch": 0.4175824175824176 + }, + { + "current_steps": 342, + "loss": 2.0654, + "learning_rate": 8.994484514212982e-07, + "epoch": 0.4188034188034188 + }, + { + "current_steps": 343, + "loss": 2.3477, + "learning_rate": 8.990241832838354e-07, + "epoch": 0.42002442002442003 + }, + { + "current_steps": 344, + "loss": 2.546, + "learning_rate": 8.985999151463725e-07, + "epoch": 0.42124542124542125 + }, + { + "current_steps": 345, + "loss": 2.7334, + "learning_rate": 8.981756470089096e-07, + "epoch": 0.42246642246642246 + }, + { + "current_steps": 346, + "loss": 2.4553, + "learning_rate": 8.977513788714467e-07, + "epoch": 0.4236874236874237 + }, + { + "current_steps": 347, + "loss": 2.4473, + "learning_rate": 8.973271107339839e-07, + "epoch": 0.4249084249084249 + }, + { + "current_steps": 348, + "loss": 2.5877, + "learning_rate": 8.969028425965209e-07, + "epoch": 0.4261294261294261 + }, + { + "current_steps": 349, + "loss": 2.4633, + "learning_rate": 8.964785744590581e-07, + "epoch": 0.42735042735042733 + }, + { + "current_steps": 350, + "loss": 2.5954, + "learning_rate": 8.960543063215952e-07, + "epoch": 0.42857142857142855 + }, + { + "current_steps": 351, + "loss": 2.5026, + "learning_rate": 8.956300381841323e-07, + "epoch": 0.4297924297924298 + }, + { + "current_steps": 352, + "loss": 2.4859, + "learning_rate": 8.952057700466694e-07, + "epoch": 0.43101343101343104 + }, + { + "current_steps": 353, + "loss": 2.0817, + "learning_rate": 8.947815019092066e-07, + "epoch": 0.43223443223443225 + }, + { + "current_steps": 354, + "loss": 2.3657, + "learning_rate": 8.943572337717436e-07, + "epoch": 0.43345543345543347 + }, + { + "current_steps": 355, + "loss": 2.5672, + "learning_rate": 8.939329656342808e-07, + "epoch": 0.4346764346764347 + }, + { + "current_steps": 356, + "loss": 2.4731, + "learning_rate": 8.935086974968179e-07, + "epoch": 0.4358974358974359 + }, + { + "current_steps": 357, + "loss": 2.4002, + "learning_rate": 8.93084429359355e-07, + "epoch": 0.4371184371184371 + }, + { + "current_steps": 358, + "loss": 2.4937, + "learning_rate": 8.926601612218923e-07, + "epoch": 0.43833943833943834 + }, + { + "current_steps": 359, + "loss": 2.1892, + "learning_rate": 8.922358930844294e-07, + "epoch": 0.43956043956043955 + }, + { + "current_steps": 360, + "loss": 2.4664, + "learning_rate": 8.918116249469665e-07, + "epoch": 0.44078144078144077 + }, + { + "current_steps": 361, + "loss": 2.2707, + "learning_rate": 8.913873568095036e-07, + "epoch": 0.442002442002442 + }, + { + "current_steps": 362, + "loss": 2.6654, + "learning_rate": 8.909630886720408e-07, + "epoch": 0.4432234432234432 + }, + { + "current_steps": 363, + "loss": 2.5825, + "learning_rate": 8.905388205345778e-07, + "epoch": 0.4444444444444444 + }, + { + "current_steps": 364, + "loss": 2.4859, + "learning_rate": 8.90114552397115e-07, + "epoch": 0.4456654456654457 + }, + { + "current_steps": 365, + "loss": 2.3529, + "learning_rate": 8.896902842596521e-07, + "epoch": 0.4468864468864469 + }, + { + "current_steps": 366, + "loss": 2.4116, + "learning_rate": 8.892660161221892e-07, + "epoch": 0.4481074481074481 + }, + { + "current_steps": 367, + "loss": 2.5233, + "learning_rate": 8.888417479847263e-07, + "epoch": 0.44932844932844934 + }, + { + "current_steps": 368, + "loss": 2.5339, + "learning_rate": 8.884174798472635e-07, + "epoch": 0.45054945054945056 + }, + { + "current_steps": 369, + "loss": 1.8529, + "learning_rate": 8.879932117098005e-07, + "epoch": 0.4517704517704518 + }, + { + "current_steps": 370, + "loss": 1.7668, + "learning_rate": 8.875689435723377e-07, + "epoch": 0.452991452991453 + }, + { + "current_steps": 371, + "loss": 2.5387, + "learning_rate": 8.871446754348748e-07, + "epoch": 0.4542124542124542 + }, + { + "current_steps": 372, + "loss": 2.6434, + "learning_rate": 8.867204072974119e-07, + "epoch": 0.4554334554334554 + }, + { + "current_steps": 373, + "loss": 2.5722, + "learning_rate": 8.86296139159949e-07, + "epoch": 0.45665445665445664 + }, + { + "current_steps": 374, + "loss": 2.3377, + "learning_rate": 8.858718710224862e-07, + "epoch": 0.45787545787545786 + }, + { + "current_steps": 375, + "loss": 2.5193, + "learning_rate": 8.854476028850233e-07, + "epoch": 0.4590964590964591 + }, + { + "current_steps": 376, + "loss": 2.4304, + "learning_rate": 8.850233347475604e-07, + "epoch": 0.4603174603174603 + }, + { + "current_steps": 377, + "loss": 2.6172, + "learning_rate": 8.845990666100976e-07, + "epoch": 0.46153846153846156 + }, + { + "current_steps": 378, + "loss": 2.5628, + "learning_rate": 8.841747984726346e-07, + "epoch": 0.4627594627594628 + }, + { + "current_steps": 379, + "loss": 2.3285, + "learning_rate": 8.837505303351718e-07, + "epoch": 0.463980463980464 + }, + { + "current_steps": 380, + "loss": 2.5392, + "learning_rate": 8.833262621977089e-07, + "epoch": 0.4652014652014652 + }, + { + "current_steps": 381, + "loss": 2.4594, + "learning_rate": 8.82901994060246e-07, + "epoch": 0.46642246642246643 + }, + { + "current_steps": 382, + "loss": 2.5926, + "learning_rate": 8.824777259227831e-07, + "epoch": 0.46764346764346765 + }, + { + "current_steps": 383, + "loss": 2.4984, + "learning_rate": 8.820534577853203e-07, + "epoch": 0.46886446886446886 + }, + { + "current_steps": 384, + "loss": 2.5409, + "learning_rate": 8.816291896478573e-07, + "epoch": 0.4700854700854701 + }, + { + "current_steps": 385, + "loss": 2.5692, + "learning_rate": 8.812049215103945e-07, + "epoch": 0.4713064713064713 + }, + { + "current_steps": 386, + "loss": 2.4496, + "learning_rate": 8.807806533729316e-07, + "epoch": 0.4725274725274725 + }, + { + "current_steps": 387, + "loss": 2.4642, + "learning_rate": 8.803563852354687e-07, + "epoch": 0.47374847374847373 + }, + { + "current_steps": 388, + "loss": 2.4806, + "learning_rate": 8.799321170980058e-07, + "epoch": 0.47496947496947495 + }, + { + "current_steps": 389, + "loss": 2.3746, + "learning_rate": 8.79507848960543e-07, + "epoch": 0.47619047619047616 + }, + { + "current_steps": 390, + "loss": 2.5567, + "learning_rate": 8.7908358082308e-07, + "epoch": 0.47741147741147744 + }, + { + "current_steps": 391, + "loss": 2.3122, + "learning_rate": 8.786593126856172e-07, + "epoch": 0.47863247863247865 + }, + { + "current_steps": 392, + "loss": 2.2947, + "learning_rate": 8.782350445481545e-07, + "epoch": 0.47985347985347987 + }, + { + "current_steps": 393, + "loss": 2.6552, + "learning_rate": 8.778107764106916e-07, + "epoch": 0.4810744810744811 + }, + { + "current_steps": 394, + "loss": 2.5077, + "learning_rate": 8.773865082732287e-07, + "epoch": 0.4822954822954823 + }, + { + "current_steps": 395, + "loss": 1.9898, + "learning_rate": 8.769622401357658e-07, + "epoch": 0.4835164835164835 + }, + { + "current_steps": 396, + "loss": 2.426, + "learning_rate": 8.76537971998303e-07, + "epoch": 0.48473748473748474 + }, + { + "current_steps": 397, + "loss": 2.4618, + "learning_rate": 8.7611370386084e-07, + "epoch": 0.48595848595848595 + }, + { + "current_steps": 398, + "loss": 2.5705, + "learning_rate": 8.756894357233772e-07, + "epoch": 0.48717948717948717 + }, + { + "current_steps": 399, + "loss": 1.9704, + "learning_rate": 8.752651675859143e-07, + "epoch": 0.4884004884004884 + }, + { + "current_steps": 400, + "loss": 2.5088, + "learning_rate": 8.748408994484514e-07, + "epoch": 0.4896214896214896 + }, + { + "current_steps": 401, + "loss": 2.6465, + "learning_rate": 8.744166313109885e-07, + "epoch": 0.4908424908424908 + }, + { + "current_steps": 402, + "loss": 2.3905, + "learning_rate": 8.739923631735257e-07, + "epoch": 0.49206349206349204 + }, + { + "current_steps": 403, + "loss": 2.4167, + "learning_rate": 8.735680950360627e-07, + "epoch": 0.4932844932844933 + }, + { + "current_steps": 404, + "loss": 2.0632, + "learning_rate": 8.731438268985999e-07, + "epoch": 0.4945054945054945 + }, + { + "current_steps": 405, + "loss": 2.6302, + "learning_rate": 8.72719558761137e-07, + "epoch": 0.49572649572649574 + }, + { + "current_steps": 406, + "loss": 2.3099, + "learning_rate": 8.722952906236741e-07, + "epoch": 0.49694749694749696 + }, + { + "current_steps": 407, + "loss": 2.5567, + "learning_rate": 8.718710224862113e-07, + "epoch": 0.4981684981684982 + }, + { + "current_steps": 408, + "loss": 2.4689, + "learning_rate": 8.714467543487484e-07, + "epoch": 0.4993894993894994 + }, + { + "current_steps": 409, + "loss": 2.0092, + "learning_rate": 8.710224862112855e-07, + "epoch": 0.5006105006105006 + }, + { + "current_steps": 410, + "loss": 2.4745, + "learning_rate": 8.705982180738226e-07, + "epoch": 0.5018315018315018 + }, + { + "current_steps": 411, + "loss": 2.5643, + "learning_rate": 8.701739499363598e-07, + "epoch": 0.503052503052503 + }, + { + "current_steps": 412, + "loss": 2.5108, + "learning_rate": 8.697496817988968e-07, + "epoch": 0.5042735042735043 + }, + { + "current_steps": 413, + "loss": 2.2128, + "learning_rate": 8.69325413661434e-07, + "epoch": 0.5054945054945055 + }, + { + "current_steps": 414, + "loss": 2.3987, + "learning_rate": 8.689011455239711e-07, + "epoch": 0.5067155067155067 + }, + { + "current_steps": 415, + "loss": 2.3095, + "learning_rate": 8.684768773865082e-07, + "epoch": 0.5079365079365079 + }, + { + "current_steps": 416, + "loss": 2.4348, + "learning_rate": 8.680526092490453e-07, + "epoch": 0.5091575091575091 + }, + { + "current_steps": 417, + "loss": 2.5095, + "learning_rate": 8.676283411115825e-07, + "epoch": 0.5103785103785103 + }, + { + "current_steps": 418, + "loss": 2.6054, + "learning_rate": 8.672040729741195e-07, + "epoch": 0.5115995115995116 + }, + { + "current_steps": 419, + "loss": 2.3229, + "learning_rate": 8.667798048366567e-07, + "epoch": 0.5128205128205128 + }, + { + "current_steps": 420, + "loss": 2.5557, + "learning_rate": 8.663555366991938e-07, + "epoch": 0.514041514041514 + }, + { + "current_steps": 421, + "loss": 2.529, + "learning_rate": 8.659312685617309e-07, + "epoch": 0.5152625152625152 + }, + { + "current_steps": 422, + "loss": 2.238, + "learning_rate": 8.65507000424268e-07, + "epoch": 0.5164835164835165 + }, + { + "current_steps": 423, + "loss": 2.3358, + "learning_rate": 8.650827322868052e-07, + "epoch": 0.5177045177045178 + }, + { + "current_steps": 424, + "loss": 2.343, + "learning_rate": 8.646584641493423e-07, + "epoch": 0.518925518925519 + }, + { + "current_steps": 425, + "loss": 2.3827, + "learning_rate": 8.642341960118795e-07, + "epoch": 0.5201465201465202 + }, + { + "current_steps": 426, + "loss": 2.2401, + "learning_rate": 8.638099278744167e-07, + "epoch": 0.5213675213675214 + }, + { + "current_steps": 427, + "loss": 2.3548, + "learning_rate": 8.633856597369537e-07, + "epoch": 0.5225885225885226 + }, + { + "current_steps": 428, + "loss": 1.9978, + "learning_rate": 8.629613915994909e-07, + "epoch": 0.5238095238095238 + }, + { + "current_steps": 429, + "loss": 2.4635, + "learning_rate": 8.62537123462028e-07, + "epoch": 0.525030525030525 + }, + { + "current_steps": 430, + "loss": 2.5778, + "learning_rate": 8.621128553245651e-07, + "epoch": 0.5262515262515263 + }, + { + "current_steps": 431, + "loss": 2.3932, + "learning_rate": 8.616885871871022e-07, + "epoch": 0.5274725274725275 + }, + { + "current_steps": 432, + "loss": 2.2644, + "learning_rate": 8.612643190496394e-07, + "epoch": 0.5286935286935287 + }, + { + "current_steps": 433, + "loss": 2.7243, + "learning_rate": 8.608400509121764e-07, + "epoch": 0.5299145299145299 + }, + { + "current_steps": 434, + "loss": 2.6023, + "learning_rate": 8.604157827747136e-07, + "epoch": 0.5311355311355311 + }, + { + "current_steps": 435, + "loss": 2.632, + "learning_rate": 8.599915146372507e-07, + "epoch": 0.5323565323565324 + }, + { + "current_steps": 436, + "loss": 2.4355, + "learning_rate": 8.595672464997878e-07, + "epoch": 0.5335775335775336 + }, + { + "current_steps": 437, + "loss": 2.612, + "learning_rate": 8.59142978362325e-07, + "epoch": 0.5347985347985348 + }, + { + "current_steps": 438, + "loss": 2.3946, + "learning_rate": 8.587187102248621e-07, + "epoch": 0.536019536019536 + }, + { + "current_steps": 439, + "loss": 2.0078, + "learning_rate": 8.582944420873993e-07, + "epoch": 0.5372405372405372 + }, + { + "current_steps": 440, + "loss": 2.4813, + "learning_rate": 8.578701739499363e-07, + "epoch": 0.5384615384615384 + }, + { + "current_steps": 441, + "loss": 2.4947, + "learning_rate": 8.574459058124735e-07, + "epoch": 0.5396825396825397 + }, + { + "current_steps": 442, + "loss": 2.4577, + "learning_rate": 8.570216376750106e-07, + "epoch": 0.5409035409035409 + }, + { + "current_steps": 443, + "loss": 2.6112, + "learning_rate": 8.565973695375477e-07, + "epoch": 0.5421245421245421 + }, + { + "current_steps": 444, + "loss": 2.3543, + "learning_rate": 8.561731014000848e-07, + "epoch": 0.5433455433455433 + }, + { + "current_steps": 445, + "loss": 2.5516, + "learning_rate": 8.55748833262622e-07, + "epoch": 0.5445665445665445 + }, + { + "current_steps": 446, + "loss": 2.0377, + "learning_rate": 8.55324565125159e-07, + "epoch": 0.5457875457875457 + }, + { + "current_steps": 447, + "loss": 2.4604, + "learning_rate": 8.549002969876962e-07, + "epoch": 0.5470085470085471 + }, + { + "current_steps": 448, + "loss": 2.2759, + "learning_rate": 8.544760288502333e-07, + "epoch": 0.5482295482295483 + }, + { + "current_steps": 449, + "loss": 2.5937, + "learning_rate": 8.540517607127704e-07, + "epoch": 0.5494505494505495 + }, + { + "current_steps": 450, + "loss": 2.5132, + "learning_rate": 8.536274925753075e-07, + "epoch": 0.5506715506715507 + }, + { + "current_steps": 451, + "loss": 2.398, + "learning_rate": 8.532032244378447e-07, + "epoch": 0.5518925518925519 + }, + { + "current_steps": 452, + "loss": 2.399, + "learning_rate": 8.527789563003817e-07, + "epoch": 0.5531135531135531 + }, + { + "current_steps": 453, + "loss": 2.5029, + "learning_rate": 8.523546881629189e-07, + "epoch": 0.5543345543345544 + }, + { + "current_steps": 454, + "loss": 2.3415, + "learning_rate": 8.519304200254561e-07, + "epoch": 0.5555555555555556 + }, + { + "current_steps": 455, + "loss": 2.3794, + "learning_rate": 8.515061518879931e-07, + "epoch": 0.5567765567765568 + }, + { + "current_steps": 456, + "loss": 2.5511, + "learning_rate": 8.510818837505303e-07, + "epoch": 0.557997557997558 + }, + { + "current_steps": 457, + "loss": 2.5691, + "learning_rate": 8.506576156130674e-07, + "epoch": 0.5592185592185592 + }, + { + "current_steps": 458, + "loss": 2.4797, + "learning_rate": 8.502333474756045e-07, + "epoch": 0.5604395604395604 + }, + { + "current_steps": 459, + "loss": 2.5448, + "learning_rate": 8.498090793381417e-07, + "epoch": 0.5616605616605617 + }, + { + "current_steps": 460, + "loss": 2.35, + "learning_rate": 8.493848112006789e-07, + "epoch": 0.5628815628815629 + }, + { + "current_steps": 461, + "loss": 2.4782, + "learning_rate": 8.489605430632159e-07, + "epoch": 0.5641025641025641 + }, + { + "current_steps": 462, + "loss": 2.4067, + "learning_rate": 8.485362749257531e-07, + "epoch": 0.5653235653235653 + }, + { + "current_steps": 463, + "loss": 2.5913, + "learning_rate": 8.481120067882902e-07, + "epoch": 0.5665445665445665 + }, + { + "current_steps": 464, + "loss": 1.6706, + "learning_rate": 8.476877386508273e-07, + "epoch": 0.5677655677655677 + }, + { + "current_steps": 465, + "loss": 2.0787, + "learning_rate": 8.472634705133644e-07, + "epoch": 0.568986568986569 + }, + { + "current_steps": 466, + "loss": 2.3041, + "learning_rate": 8.468392023759016e-07, + "epoch": 0.5702075702075702 + }, + { + "current_steps": 467, + "loss": 2.338, + "learning_rate": 8.464149342384386e-07, + "epoch": 0.5714285714285714 + }, + { + "current_steps": 468, + "loss": 2.3682, + "learning_rate": 8.459906661009758e-07, + "epoch": 0.5726495726495726 + }, + { + "current_steps": 469, + "loss": 2.4828, + "learning_rate": 8.45566397963513e-07, + "epoch": 0.5738705738705738 + }, + { + "current_steps": 470, + "loss": 2.4472, + "learning_rate": 8.4514212982605e-07, + "epoch": 0.575091575091575 + }, + { + "current_steps": 471, + "loss": 2.2963, + "learning_rate": 8.447178616885872e-07, + "epoch": 0.5763125763125763 + }, + { + "current_steps": 472, + "loss": 2.5166, + "learning_rate": 8.442935935511243e-07, + "epoch": 0.5775335775335775 + }, + { + "current_steps": 473, + "loss": 2.7243, + "learning_rate": 8.438693254136614e-07, + "epoch": 0.5787545787545788 + }, + { + "current_steps": 474, + "loss": 2.417, + "learning_rate": 8.434450572761985e-07, + "epoch": 0.57997557997558 + }, + { + "current_steps": 475, + "loss": 2.4493, + "learning_rate": 8.430207891387357e-07, + "epoch": 0.5811965811965812 + }, + { + "current_steps": 476, + "loss": 2.3438, + "learning_rate": 8.425965210012727e-07, + "epoch": 0.5824175824175825 + }, + { + "current_steps": 477, + "loss": 2.5377, + "learning_rate": 8.421722528638099e-07, + "epoch": 0.5836385836385837 + }, + { + "current_steps": 478, + "loss": 2.5322, + "learning_rate": 8.41747984726347e-07, + "epoch": 0.5848595848595849 + }, + { + "current_steps": 479, + "loss": 2.585, + "learning_rate": 8.413237165888841e-07, + "epoch": 0.5860805860805861 + }, + { + "current_steps": 480, + "loss": 2.543, + "learning_rate": 8.408994484514212e-07, + "epoch": 0.5873015873015873 + }, + { + "current_steps": 481, + "loss": 2.7428, + "learning_rate": 8.404751803139584e-07, + "epoch": 0.5885225885225885 + }, + { + "current_steps": 482, + "loss": 2.3634, + "learning_rate": 8.400509121764954e-07, + "epoch": 0.5897435897435898 + }, + { + "current_steps": 483, + "loss": 2.5013, + "learning_rate": 8.396266440390326e-07, + "epoch": 0.590964590964591 + }, + { + "current_steps": 484, + "loss": 2.4862, + "learning_rate": 8.392023759015697e-07, + "epoch": 0.5921855921855922 + }, + { + "current_steps": 485, + "loss": 2.457, + "learning_rate": 8.387781077641068e-07, + "epoch": 0.5934065934065934 + }, + { + "current_steps": 486, + "loss": 2.4714, + "learning_rate": 8.38353839626644e-07, + "epoch": 0.5946275946275946 + }, + { + "current_steps": 487, + "loss": 2.4756, + "learning_rate": 8.379295714891811e-07, + "epoch": 0.5958485958485958 + }, + { + "current_steps": 488, + "loss": 2.3591, + "learning_rate": 8.375053033517183e-07, + "epoch": 0.5970695970695971 + }, + { + "current_steps": 489, + "loss": 2.4849, + "learning_rate": 8.370810352142553e-07, + "epoch": 0.5982905982905983 + }, + { + "current_steps": 490, + "loss": 2.4724, + "learning_rate": 8.366567670767925e-07, + "epoch": 0.5995115995115995 + }, + { + "current_steps": 491, + "loss": 2.3189, + "learning_rate": 8.362324989393295e-07, + "epoch": 0.6007326007326007 + }, + { + "current_steps": 492, + "loss": 2.4547, + "learning_rate": 8.358082308018667e-07, + "epoch": 0.6019536019536019 + }, + { + "current_steps": 493, + "loss": 2.3789, + "learning_rate": 8.353839626644039e-07, + "epoch": 0.6031746031746031 + }, + { + "current_steps": 494, + "loss": 2.7593, + "learning_rate": 8.349596945269411e-07, + "epoch": 0.6043956043956044 + }, + { + "current_steps": 495, + "loss": 2.3845, + "learning_rate": 8.345354263894781e-07, + "epoch": 0.6056166056166056 + }, + { + "current_steps": 496, + "loss": 2.328, + "learning_rate": 8.341111582520153e-07, + "epoch": 0.6068376068376068 + }, + { + "current_steps": 497, + "loss": 2.6742, + "learning_rate": 8.336868901145524e-07, + "epoch": 0.608058608058608 + }, + { + "current_steps": 498, + "loss": 2.3736, + "learning_rate": 8.332626219770895e-07, + "epoch": 0.6092796092796092 + }, + { + "current_steps": 499, + "loss": 2.3569, + "learning_rate": 8.328383538396266e-07, + "epoch": 0.6105006105006106 + }, + { + "current_steps": 500, + "loss": 2.3843, + "learning_rate": 8.324140857021638e-07, + "epoch": 0.6117216117216118 + }, + { + "current_steps": 501, + "loss": 2.3838, + "learning_rate": 8.319898175647009e-07, + "epoch": 0.612942612942613 + }, + { + "current_steps": 502, + "loss": 2.4341, + "learning_rate": 8.31565549427238e-07, + "epoch": 0.6141636141636142 + }, + { + "current_steps": 503, + "loss": 2.4574, + "learning_rate": 8.311412812897752e-07, + "epoch": 0.6153846153846154 + }, + { + "current_steps": 504, + "loss": 2.4118, + "learning_rate": 8.307170131523122e-07, + "epoch": 0.6166056166056166 + }, + { + "current_steps": 505, + "loss": 2.477, + "learning_rate": 8.302927450148494e-07, + "epoch": 0.6178266178266179 + }, + { + "current_steps": 506, + "loss": 2.4236, + "learning_rate": 8.298684768773865e-07, + "epoch": 0.6190476190476191 + }, + { + "current_steps": 507, + "loss": 2.0212, + "learning_rate": 8.294442087399236e-07, + "epoch": 0.6202686202686203 + }, + { + "current_steps": 508, + "loss": 2.4185, + "learning_rate": 8.290199406024607e-07, + "epoch": 0.6214896214896215 + }, + { + "current_steps": 509, + "loss": 2.4317, + "learning_rate": 8.285956724649979e-07, + "epoch": 0.6227106227106227 + }, + { + "current_steps": 510, + "loss": 2.3712, + "learning_rate": 8.281714043275349e-07, + "epoch": 0.6239316239316239 + }, + { + "current_steps": 511, + "loss": 2.4103, + "learning_rate": 8.277471361900721e-07, + "epoch": 0.6251526251526252 + }, + { + "current_steps": 512, + "loss": 2.4014, + "learning_rate": 8.273228680526092e-07, + "epoch": 0.6263736263736264 + }, + { + "current_steps": 513, + "loss": 2.5516, + "learning_rate": 8.268985999151463e-07, + "epoch": 0.6275946275946276 + }, + { + "current_steps": 514, + "loss": 2.5376, + "learning_rate": 8.264743317776834e-07, + "epoch": 0.6288156288156288 + }, + { + "current_steps": 515, + "loss": 2.4263, + "learning_rate": 8.260500636402206e-07, + "epoch": 0.63003663003663 + }, + { + "current_steps": 516, + "loss": 2.4614, + "learning_rate": 8.256257955027576e-07, + "epoch": 0.6312576312576312 + }, + { + "current_steps": 517, + "loss": 2.5797, + "learning_rate": 8.252015273652948e-07, + "epoch": 0.6324786324786325 + }, + { + "current_steps": 518, + "loss": 2.4647, + "learning_rate": 8.24777259227832e-07, + "epoch": 0.6336996336996337 + }, + { + "current_steps": 519, + "loss": 2.4601, + "learning_rate": 8.24352991090369e-07, + "epoch": 0.6349206349206349 + }, + { + "current_steps": 520, + "loss": 2.3465, + "learning_rate": 8.239287229529062e-07, + "epoch": 0.6361416361416361 + }, + { + "current_steps": 521, + "loss": 2.1939, + "learning_rate": 8.235044548154433e-07, + "epoch": 0.6373626373626373 + }, + { + "current_steps": 522, + "loss": 2.5246, + "learning_rate": 8.230801866779804e-07, + "epoch": 0.6385836385836385 + }, + { + "current_steps": 523, + "loss": 2.4489, + "learning_rate": 8.226559185405175e-07, + "epoch": 0.6398046398046398 + }, + { + "current_steps": 524, + "loss": 2.2654, + "learning_rate": 8.222316504030547e-07, + "epoch": 0.6410256410256411 + }, + { + "current_steps": 525, + "loss": 2.0933, + "learning_rate": 8.218073822655917e-07, + "epoch": 0.6422466422466423 + }, + { + "current_steps": 526, + "loss": 2.3711, + "learning_rate": 8.21383114128129e-07, + "epoch": 0.6434676434676435 + }, + { + "current_steps": 527, + "loss": 2.376, + "learning_rate": 8.209588459906661e-07, + "epoch": 0.6446886446886447 + }, + { + "current_steps": 528, + "loss": 2.3484, + "learning_rate": 8.205345778532032e-07, + "epoch": 0.645909645909646 + }, + { + "current_steps": 529, + "loss": 2.3694, + "learning_rate": 8.201103097157403e-07, + "epoch": 0.6471306471306472 + }, + { + "current_steps": 530, + "loss": 2.4523, + "learning_rate": 8.196860415782775e-07, + "epoch": 0.6483516483516484 + }, + { + "current_steps": 531, + "loss": 2.4694, + "learning_rate": 8.192617734408145e-07, + "epoch": 0.6495726495726496 + }, + { + "current_steps": 532, + "loss": 2.6247, + "learning_rate": 8.188375053033517e-07, + "epoch": 0.6507936507936508 + }, + { + "current_steps": 533, + "loss": 2.5112, + "learning_rate": 8.184132371658889e-07, + "epoch": 0.652014652014652 + }, + { + "current_steps": 534, + "loss": 2.478, + "learning_rate": 8.17988969028426e-07, + "epoch": 0.6532356532356532 + }, + { + "current_steps": 535, + "loss": 2.3409, + "learning_rate": 8.175647008909631e-07, + "epoch": 0.6544566544566545 + }, + { + "current_steps": 536, + "loss": 2.4053, + "learning_rate": 8.171404327535002e-07, + "epoch": 0.6556776556776557 + }, + { + "current_steps": 537, + "loss": 2.4357, + "learning_rate": 8.167161646160374e-07, + "epoch": 0.6568986568986569 + }, + { + "current_steps": 538, + "loss": 2.5225, + "learning_rate": 8.162918964785744e-07, + "epoch": 0.6581196581196581 + }, + { + "current_steps": 539, + "loss": 2.4411, + "learning_rate": 8.158676283411116e-07, + "epoch": 0.6593406593406593 + }, + { + "current_steps": 540, + "loss": 2.4389, + "learning_rate": 8.154433602036487e-07, + "epoch": 0.6605616605616605 + }, + { + "current_steps": 541, + "loss": 2.2126, + "learning_rate": 8.150190920661858e-07, + "epoch": 0.6617826617826618 + }, + { + "current_steps": 542, + "loss": 2.4935, + "learning_rate": 8.145948239287229e-07, + "epoch": 0.663003663003663 + }, + { + "current_steps": 543, + "loss": 2.4402, + "learning_rate": 8.141705557912601e-07, + "epoch": 0.6642246642246642 + }, + { + "current_steps": 544, + "loss": 2.6183, + "learning_rate": 8.137462876537971e-07, + "epoch": 0.6654456654456654 + }, + { + "current_steps": 545, + "loss": 2.576, + "learning_rate": 8.133220195163343e-07, + "epoch": 0.6666666666666666 + }, + { + "current_steps": 546, + "loss": 2.521, + "learning_rate": 8.128977513788714e-07, + "epoch": 0.6678876678876678 + }, + { + "current_steps": 547, + "loss": 2.4004, + "learning_rate": 8.124734832414085e-07, + "epoch": 0.6691086691086691 + }, + { + "current_steps": 548, + "loss": 2.3097, + "learning_rate": 8.120492151039456e-07, + "epoch": 0.6703296703296703 + }, + { + "current_steps": 549, + "loss": 2.4704, + "learning_rate": 8.116249469664828e-07, + "epoch": 0.6715506715506715 + }, + { + "current_steps": 550, + "loss": 2.3374, + "learning_rate": 8.112006788290199e-07, + "epoch": 0.6727716727716728 + }, + { + "current_steps": 551, + "loss": 2.7208, + "learning_rate": 8.10776410691557e-07, + "epoch": 0.673992673992674 + }, + { + "current_steps": 552, + "loss": 2.3493, + "learning_rate": 8.103521425540942e-07, + "epoch": 0.6752136752136753 + }, + { + "current_steps": 553, + "loss": 2.1285, + "learning_rate": 8.099278744166312e-07, + "epoch": 0.6764346764346765 + }, + { + "current_steps": 554, + "loss": 2.4088, + "learning_rate": 8.095036062791684e-07, + "epoch": 0.6776556776556777 + }, + { + "current_steps": 555, + "loss": 2.5023, + "learning_rate": 8.090793381417055e-07, + "epoch": 0.6788766788766789 + }, + { + "current_steps": 556, + "loss": 2.3455, + "learning_rate": 8.086550700042426e-07, + "epoch": 0.6800976800976801 + }, + { + "current_steps": 557, + "loss": 2.3108, + "learning_rate": 8.082308018667797e-07, + "epoch": 0.6813186813186813 + }, + { + "current_steps": 558, + "loss": 2.4222, + "learning_rate": 8.078065337293169e-07, + "epoch": 0.6825396825396826 + }, + { + "current_steps": 559, + "loss": 2.3429, + "learning_rate": 8.073822655918539e-07, + "epoch": 0.6837606837606838 + }, + { + "current_steps": 560, + "loss": 2.583, + "learning_rate": 8.069579974543912e-07, + "epoch": 0.684981684981685 + }, + { + "current_steps": 561, + "loss": 2.3894, + "learning_rate": 8.065337293169283e-07, + "epoch": 0.6862026862026862 + }, + { + "current_steps": 562, + "loss": 2.2774, + "learning_rate": 8.061094611794654e-07, + "epoch": 0.6874236874236874 + }, + { + "current_steps": 563, + "loss": 2.5586, + "learning_rate": 8.056851930420025e-07, + "epoch": 0.6886446886446886 + }, + { + "current_steps": 564, + "loss": 2.4774, + "learning_rate": 8.052609249045397e-07, + "epoch": 0.6898656898656899 + }, + { + "current_steps": 565, + "loss": 2.5266, + "learning_rate": 8.048366567670768e-07, + "epoch": 0.6910866910866911 + }, + { + "current_steps": 566, + "loss": 2.3909, + "learning_rate": 8.044123886296139e-07, + "epoch": 0.6923076923076923 + }, + { + "current_steps": 567, + "loss": 2.4, + "learning_rate": 8.039881204921511e-07, + "epoch": 0.6935286935286935 + }, + { + "current_steps": 568, + "loss": 2.4204, + "learning_rate": 8.035638523546881e-07, + "epoch": 0.6947496947496947 + }, + { + "current_steps": 569, + "loss": 2.4304, + "learning_rate": 8.031395842172253e-07, + "epoch": 0.6959706959706959 + }, + { + "current_steps": 570, + "loss": 2.4109, + "learning_rate": 8.027153160797624e-07, + "epoch": 0.6971916971916972 + }, + { + "current_steps": 571, + "loss": 2.3583, + "learning_rate": 8.022910479422995e-07, + "epoch": 0.6984126984126984 + }, + { + "current_steps": 572, + "loss": 2.3682, + "learning_rate": 8.018667798048366e-07, + "epoch": 0.6996336996336996 + }, + { + "current_steps": 573, + "loss": 2.5905, + "learning_rate": 8.014425116673738e-07, + "epoch": 0.7008547008547008 + }, + { + "current_steps": 574, + "loss": 2.3571, + "learning_rate": 8.010182435299108e-07, + "epoch": 0.702075702075702 + }, + { + "current_steps": 575, + "loss": 2.3488, + "learning_rate": 8.00593975392448e-07, + "epoch": 0.7032967032967034 + }, + { + "current_steps": 576, + "loss": 1.9226, + "learning_rate": 8.001697072549851e-07, + "epoch": 0.7045177045177046 + }, + { + "current_steps": 577, + "loss": 2.3161, + "learning_rate": 7.997454391175222e-07, + "epoch": 0.7057387057387058 + }, + { + "current_steps": 578, + "loss": 2.2022, + "learning_rate": 7.993211709800593e-07, + "epoch": 0.706959706959707 + }, + { + "current_steps": 579, + "loss": 2.3923, + "learning_rate": 7.988969028425965e-07, + "epoch": 0.7081807081807082 + }, + { + "current_steps": 580, + "loss": 2.5653, + "learning_rate": 7.984726347051336e-07, + "epoch": 0.7094017094017094 + }, + { + "current_steps": 581, + "loss": 2.5353, + "learning_rate": 7.980483665676707e-07, + "epoch": 0.7106227106227107 + }, + { + "current_steps": 582, + "loss": 2.4601, + "learning_rate": 7.976240984302079e-07, + "epoch": 0.7118437118437119 + }, + { + "current_steps": 583, + "loss": 2.4203, + "learning_rate": 7.971998302927449e-07, + "epoch": 0.7130647130647131 + }, + { + "current_steps": 584, + "loss": 2.2009, + "learning_rate": 7.967755621552821e-07, + "epoch": 0.7142857142857143 + }, + { + "current_steps": 585, + "loss": 2.7196, + "learning_rate": 7.963512940178192e-07, + "epoch": 0.7155067155067155 + }, + { + "current_steps": 586, + "loss": 2.3957, + "learning_rate": 7.959270258803564e-07, + "epoch": 0.7167277167277167 + }, + { + "current_steps": 587, + "loss": 2.2288, + "learning_rate": 7.955027577428934e-07, + "epoch": 0.717948717948718 + }, + { + "current_steps": 588, + "loss": 2.5856, + "learning_rate": 7.950784896054306e-07, + "epoch": 0.7191697191697192 + }, + { + "current_steps": 589, + "loss": 2.4869, + "learning_rate": 7.946542214679676e-07, + "epoch": 0.7203907203907204 + }, + { + "current_steps": 590, + "loss": 2.3062, + "learning_rate": 7.942299533305048e-07, + "epoch": 0.7216117216117216 + }, + { + "current_steps": 591, + "loss": 2.5309, + "learning_rate": 7.938056851930419e-07, + "epoch": 0.7228327228327228 + }, + { + "current_steps": 592, + "loss": 2.4145, + "learning_rate": 7.93381417055579e-07, + "epoch": 0.724053724053724 + }, + { + "current_steps": 593, + "loss": 2.4498, + "learning_rate": 7.929571489181161e-07, + "epoch": 0.7252747252747253 + }, + { + "current_steps": 594, + "loss": 2.4868, + "learning_rate": 7.925328807806534e-07, + "epoch": 0.7264957264957265 + }, + { + "current_steps": 595, + "loss": 2.4073, + "learning_rate": 7.921086126431906e-07, + "epoch": 0.7277167277167277 + }, + { + "current_steps": 596, + "loss": 2.4312, + "learning_rate": 7.916843445057276e-07, + "epoch": 0.7289377289377289 + }, + { + "current_steps": 597, + "loss": 2.4097, + "learning_rate": 7.912600763682648e-07, + "epoch": 0.7301587301587301 + }, + { + "current_steps": 598, + "loss": 2.3293, + "learning_rate": 7.908358082308019e-07, + "epoch": 0.7313797313797313 + }, + { + "current_steps": 599, + "loss": 2.299, + "learning_rate": 7.90411540093339e-07, + "epoch": 0.7326007326007326 + }, + { + "current_steps": 600, + "loss": 2.4052, + "learning_rate": 7.899872719558761e-07, + "epoch": 0.7338217338217338 + }, + { + "current_steps": 601, + "loss": 2.5236, + "learning_rate": 7.895630038184133e-07, + "epoch": 0.7350427350427351 + }, + { + "current_steps": 602, + "loss": 2.3635, + "learning_rate": 7.891387356809503e-07, + "epoch": 0.7362637362637363 + }, + { + "current_steps": 603, + "loss": 2.373, + "learning_rate": 7.887144675434875e-07, + "epoch": 0.7374847374847375 + }, + { + "current_steps": 604, + "loss": 2.2931, + "learning_rate": 7.882901994060246e-07, + "epoch": 0.7387057387057387 + }, + { + "current_steps": 605, + "loss": 2.5737, + "learning_rate": 7.878659312685617e-07, + "epoch": 0.73992673992674 + }, + { + "current_steps": 606, + "loss": 2.4363, + "learning_rate": 7.874416631310988e-07, + "epoch": 0.7411477411477412 + }, + { + "current_steps": 607, + "loss": 2.202, + "learning_rate": 7.87017394993636e-07, + "epoch": 0.7423687423687424 + }, + { + "current_steps": 608, + "loss": 2.2882, + "learning_rate": 7.86593126856173e-07, + "epoch": 0.7435897435897436 + }, + { + "current_steps": 609, + "loss": 2.241, + "learning_rate": 7.861688587187102e-07, + "epoch": 0.7448107448107448 + }, + { + "current_steps": 610, + "loss": 2.458, + "learning_rate": 7.857445905812473e-07, + "epoch": 0.746031746031746 + }, + { + "current_steps": 611, + "loss": 2.3939, + "learning_rate": 7.853203224437844e-07, + "epoch": 0.7472527472527473 + }, + { + "current_steps": 612, + "loss": 2.3099, + "learning_rate": 7.848960543063216e-07, + "epoch": 0.7484737484737485 + }, + { + "current_steps": 613, + "loss": 2.4326, + "learning_rate": 7.844717861688587e-07, + "epoch": 0.7496947496947497 + }, + { + "current_steps": 614, + "loss": 2.2266, + "learning_rate": 7.840475180313958e-07, + "epoch": 0.7509157509157509 + }, + { + "current_steps": 615, + "loss": 2.4437, + "learning_rate": 7.836232498939329e-07, + "epoch": 0.7521367521367521 + }, + { + "current_steps": 616, + "loss": 2.2536, + "learning_rate": 7.831989817564701e-07, + "epoch": 0.7533577533577533 + }, + { + "current_steps": 617, + "loss": 2.2506, + "learning_rate": 7.827747136190071e-07, + "epoch": 0.7545787545787546 + }, + { + "current_steps": 618, + "loss": 2.5573, + "learning_rate": 7.823504454815443e-07, + "epoch": 0.7557997557997558 + }, + { + "current_steps": 619, + "loss": 2.3315, + "learning_rate": 7.819261773440814e-07, + "epoch": 0.757020757020757 + }, + { + "current_steps": 620, + "loss": 2.2204, + "learning_rate": 7.815019092066185e-07, + "epoch": 0.7582417582417582 + }, + { + "current_steps": 621, + "loss": 2.5033, + "learning_rate": 7.810776410691556e-07, + "epoch": 0.7594627594627594 + }, + { + "current_steps": 622, + "loss": 2.5044, + "learning_rate": 7.806533729316928e-07, + "epoch": 0.7606837606837606 + }, + { + "current_steps": 623, + "loss": 2.066, + "learning_rate": 7.802291047942298e-07, + "epoch": 0.7619047619047619 + }, + { + "current_steps": 624, + "loss": 2.163, + "learning_rate": 7.79804836656767e-07, + "epoch": 0.7631257631257631 + }, + { + "current_steps": 625, + "loss": 2.4655, + "learning_rate": 7.793805685193041e-07, + "epoch": 0.7643467643467643 + }, + { + "current_steps": 626, + "loss": 2.4958, + "learning_rate": 7.789563003818412e-07, + "epoch": 0.7655677655677655 + }, + { + "current_steps": 627, + "loss": 2.4526, + "learning_rate": 7.785320322443785e-07, + "epoch": 0.7667887667887668 + }, + { + "current_steps": 628, + "loss": 2.4643, + "learning_rate": 7.781077641069156e-07, + "epoch": 0.7680097680097681 + }, + { + "current_steps": 629, + "loss": 2.5018, + "learning_rate": 7.776834959694528e-07, + "epoch": 0.7692307692307693 + }, + { + "current_steps": 630, + "loss": 2.4327, + "learning_rate": 7.772592278319898e-07, + "epoch": 0.7704517704517705 + }, + { + "current_steps": 631, + "loss": 2.4172, + "learning_rate": 7.76834959694527e-07, + "epoch": 0.7716727716727717 + }, + { + "current_steps": 632, + "loss": 2.4721, + "learning_rate": 7.76410691557064e-07, + "epoch": 0.7728937728937729 + }, + { + "current_steps": 633, + "loss": 2.4092, + "learning_rate": 7.759864234196012e-07, + "epoch": 0.7741147741147741 + }, + { + "current_steps": 634, + "loss": 2.4659, + "learning_rate": 7.755621552821383e-07, + "epoch": 0.7753357753357754 + }, + { + "current_steps": 635, + "loss": 2.3509, + "learning_rate": 7.751378871446755e-07, + "epoch": 0.7765567765567766 + }, + { + "current_steps": 636, + "loss": 2.4203, + "learning_rate": 7.747136190072125e-07, + "epoch": 0.7777777777777778 + }, + { + "current_steps": 637, + "loss": 2.3564, + "learning_rate": 7.742893508697497e-07, + "epoch": 0.778998778998779 + }, + { + "current_steps": 638, + "loss": 2.4774, + "learning_rate": 7.738650827322868e-07, + "epoch": 0.7802197802197802 + }, + { + "current_steps": 639, + "loss": 2.3605, + "learning_rate": 7.734408145948239e-07, + "epoch": 0.7814407814407814 + }, + { + "current_steps": 640, + "loss": 2.1573, + "learning_rate": 7.73016546457361e-07, + "epoch": 0.7826617826617827 + }, + { + "current_steps": 641, + "loss": 2.2626, + "learning_rate": 7.725922783198982e-07, + "epoch": 0.7838827838827839 + }, + { + "current_steps": 642, + "loss": 2.4945, + "learning_rate": 7.721680101824352e-07, + "epoch": 0.7851037851037851 + }, + { + "current_steps": 643, + "loss": 2.5277, + "learning_rate": 7.717437420449724e-07, + "epoch": 0.7863247863247863 + }, + { + "current_steps": 644, + "loss": 2.473, + "learning_rate": 7.713194739075096e-07, + "epoch": 0.7875457875457875 + }, + { + "current_steps": 645, + "loss": 2.5574, + "learning_rate": 7.708952057700466e-07, + "epoch": 0.7887667887667887 + }, + { + "current_steps": 646, + "loss": 2.4524, + "learning_rate": 7.704709376325838e-07, + "epoch": 0.78998778998779 + }, + { + "current_steps": 647, + "loss": 2.3952, + "learning_rate": 7.700466694951209e-07, + "epoch": 0.7912087912087912 + }, + { + "current_steps": 648, + "loss": 2.4496, + "learning_rate": 7.69622401357658e-07, + "epoch": 0.7924297924297924 + }, + { + "current_steps": 649, + "loss": 2.3344, + "learning_rate": 7.691981332201951e-07, + "epoch": 0.7936507936507936 + }, + { + "current_steps": 650, + "loss": 2.3052, + "learning_rate": 7.687738650827323e-07, + "epoch": 0.7948717948717948 + }, + { + "current_steps": 651, + "loss": 2.3252, + "learning_rate": 7.683495969452693e-07, + "epoch": 0.796092796092796 + }, + { + "current_steps": 652, + "loss": 2.4578, + "learning_rate": 7.679253288078065e-07, + "epoch": 0.7973137973137974 + }, + { + "current_steps": 653, + "loss": 2.3262, + "learning_rate": 7.675010606703436e-07, + "epoch": 0.7985347985347986 + }, + { + "current_steps": 654, + "loss": 2.3897, + "learning_rate": 7.670767925328807e-07, + "epoch": 0.7997557997557998 + }, + { + "current_steps": 655, + "loss": 2.3535, + "learning_rate": 7.666525243954178e-07, + "epoch": 0.800976800976801 + }, + { + "current_steps": 656, + "loss": 2.5409, + "learning_rate": 7.66228256257955e-07, + "epoch": 0.8021978021978022 + }, + { + "current_steps": 657, + "loss": 2.4117, + "learning_rate": 7.65803988120492e-07, + "epoch": 0.8034188034188035 + }, + { + "current_steps": 658, + "loss": 2.4844, + "learning_rate": 7.653797199830292e-07, + "epoch": 0.8046398046398047 + }, + { + "current_steps": 659, + "loss": 2.4408, + "learning_rate": 7.649554518455663e-07, + "epoch": 0.8058608058608059 + }, + { + "current_steps": 660, + "loss": 2.3985, + "learning_rate": 7.645311837081034e-07, + "epoch": 0.8070818070818071 + }, + { + "current_steps": 661, + "loss": 2.4679, + "learning_rate": 7.641069155706407e-07, + "epoch": 0.8083028083028083 + }, + { + "current_steps": 662, + "loss": 2.4028, + "learning_rate": 7.636826474331778e-07, + "epoch": 0.8095238095238095 + }, + { + "current_steps": 663, + "loss": 2.499, + "learning_rate": 7.632583792957149e-07, + "epoch": 0.8107448107448108 + }, + { + "current_steps": 664, + "loss": 2.1812, + "learning_rate": 7.62834111158252e-07, + "epoch": 0.811965811965812 + }, + { + "current_steps": 665, + "loss": 2.6066, + "learning_rate": 7.624098430207892e-07, + "epoch": 0.8131868131868132 + }, + { + "current_steps": 666, + "loss": 2.3826, + "learning_rate": 7.619855748833262e-07, + "epoch": 0.8144078144078144 + }, + { + "current_steps": 667, + "loss": 2.4019, + "learning_rate": 7.615613067458634e-07, + "epoch": 0.8156288156288156 + }, + { + "current_steps": 668, + "loss": 2.4065, + "learning_rate": 7.611370386084005e-07, + "epoch": 0.8168498168498168 + }, + { + "current_steps": 669, + "loss": 2.3815, + "learning_rate": 7.607127704709376e-07, + "epoch": 0.818070818070818 + }, + { + "current_steps": 670, + "loss": 2.4692, + "learning_rate": 7.602885023334747e-07, + "epoch": 0.8192918192918193 + }, + { + "current_steps": 671, + "loss": 2.2878, + "learning_rate": 7.598642341960119e-07, + "epoch": 0.8205128205128205 + }, + { + "current_steps": 672, + "loss": 2.4088, + "learning_rate": 7.594399660585489e-07, + "epoch": 0.8217338217338217 + }, + { + "current_steps": 673, + "loss": 2.3955, + "learning_rate": 7.590156979210861e-07, + "epoch": 0.8229548229548229 + }, + { + "current_steps": 674, + "loss": 2.4895, + "learning_rate": 7.585914297836232e-07, + "epoch": 0.8241758241758241 + }, + { + "current_steps": 675, + "loss": 1.8632, + "learning_rate": 7.581671616461603e-07, + "epoch": 0.8253968253968254 + }, + { + "current_steps": 676, + "loss": 2.4763, + "learning_rate": 7.577428935086975e-07, + "epoch": 0.8266178266178266 + }, + { + "current_steps": 677, + "loss": 2.3983, + "learning_rate": 7.573186253712346e-07, + "epoch": 0.8278388278388278 + }, + { + "current_steps": 678, + "loss": 2.3688, + "learning_rate": 7.568943572337717e-07, + "epoch": 0.8290598290598291 + }, + { + "current_steps": 679, + "loss": 2.4496, + "learning_rate": 7.564700890963088e-07, + "epoch": 0.8302808302808303 + }, + { + "current_steps": 680, + "loss": 2.376, + "learning_rate": 7.56045820958846e-07, + "epoch": 0.8315018315018315 + }, + { + "current_steps": 681, + "loss": 2.4987, + "learning_rate": 7.55621552821383e-07, + "epoch": 0.8327228327228328 + }, + { + "current_steps": 682, + "loss": 2.5293, + "learning_rate": 7.551972846839202e-07, + "epoch": 0.833943833943834 + }, + { + "current_steps": 683, + "loss": 2.3763, + "learning_rate": 7.547730165464573e-07, + "epoch": 0.8351648351648352 + }, + { + "current_steps": 684, + "loss": 2.5537, + "learning_rate": 7.543487484089945e-07, + "epoch": 0.8363858363858364 + }, + { + "current_steps": 685, + "loss": 2.4575, + "learning_rate": 7.539244802715315e-07, + "epoch": 0.8376068376068376 + }, + { + "current_steps": 686, + "loss": 2.3282, + "learning_rate": 7.535002121340687e-07, + "epoch": 0.8388278388278388 + }, + { + "current_steps": 687, + "loss": 2.2933, + "learning_rate": 7.530759439966057e-07, + "epoch": 0.8400488400488401 + }, + { + "current_steps": 688, + "loss": 2.3368, + "learning_rate": 7.526516758591429e-07, + "epoch": 0.8412698412698413 + }, + { + "current_steps": 689, + "loss": 2.2983, + "learning_rate": 7.5222740772168e-07, + "epoch": 0.8424908424908425 + }, + { + "current_steps": 690, + "loss": 2.3795, + "learning_rate": 7.518031395842172e-07, + "epoch": 0.8437118437118437 + }, + { + "current_steps": 691, + "loss": 2.3829, + "learning_rate": 7.513788714467543e-07, + "epoch": 0.8449328449328449 + }, + { + "current_steps": 692, + "loss": 2.2515, + "learning_rate": 7.509546033092914e-07, + "epoch": 0.8461538461538461 + }, + { + "current_steps": 693, + "loss": 2.5386, + "learning_rate": 7.505303351718286e-07, + "epoch": 0.8473748473748474 + }, + { + "current_steps": 694, + "loss": 2.4401, + "learning_rate": 7.501060670343656e-07, + "epoch": 0.8485958485958486 + }, + { + "current_steps": 695, + "loss": 2.4599, + "learning_rate": 7.496817988969029e-07, + "epoch": 0.8498168498168498 + }, + { + "current_steps": 696, + "loss": 2.355, + "learning_rate": 7.4925753075944e-07, + "epoch": 0.851037851037851 + }, + { + "current_steps": 697, + "loss": 2.3693, + "learning_rate": 7.488332626219771e-07, + "epoch": 0.8522588522588522 + }, + { + "current_steps": 698, + "loss": 2.3803, + "learning_rate": 7.484089944845142e-07, + "epoch": 0.8534798534798534 + }, + { + "current_steps": 699, + "loss": 2.3216, + "learning_rate": 7.479847263470514e-07, + "epoch": 0.8547008547008547 + }, + { + "current_steps": 700, + "loss": 2.3852, + "learning_rate": 7.475604582095884e-07, + "epoch": 0.8559218559218559 + }, + { + "current_steps": 701, + "loss": 2.3847, + "learning_rate": 7.471361900721256e-07, + "epoch": 0.8571428571428571 + }, + { + "current_steps": 702, + "loss": 2.4728, + "learning_rate": 7.467119219346627e-07, + "epoch": 0.8583638583638583 + }, + { + "current_steps": 703, + "loss": 2.4103, + "learning_rate": 7.462876537971998e-07, + "epoch": 0.8595848595848596 + }, + { + "current_steps": 704, + "loss": 2.2518, + "learning_rate": 7.458633856597369e-07, + "epoch": 0.8608058608058609 + }, + { + "current_steps": 705, + "loss": 2.4516, + "learning_rate": 7.454391175222741e-07, + "epoch": 0.8620268620268621 + }, + { + "current_steps": 706, + "loss": 2.321, + "learning_rate": 7.450148493848112e-07, + "epoch": 0.8632478632478633 + }, + { + "current_steps": 707, + "loss": 2.4704, + "learning_rate": 7.445905812473483e-07, + "epoch": 0.8644688644688645 + }, + { + "current_steps": 708, + "loss": 2.2885, + "learning_rate": 7.441663131098855e-07, + "epoch": 0.8656898656898657 + }, + { + "current_steps": 709, + "loss": 2.377, + "learning_rate": 7.437420449724225e-07, + "epoch": 0.8669108669108669 + }, + { + "current_steps": 710, + "loss": 2.2656, + "learning_rate": 7.433177768349597e-07, + "epoch": 0.8681318681318682 + }, + { + "current_steps": 711, + "loss": 2.4201, + "learning_rate": 7.428935086974968e-07, + "epoch": 0.8693528693528694 + }, + { + "current_steps": 712, + "loss": 2.3026, + "learning_rate": 7.424692405600339e-07, + "epoch": 0.8705738705738706 + }, + { + "current_steps": 713, + "loss": 2.2784, + "learning_rate": 7.42044972422571e-07, + "epoch": 0.8717948717948718 + }, + { + "current_steps": 714, + "loss": 2.4246, + "learning_rate": 7.416207042851082e-07, + "epoch": 0.873015873015873 + }, + { + "current_steps": 715, + "loss": 1.9103, + "learning_rate": 7.411964361476452e-07, + "epoch": 0.8742368742368742 + }, + { + "current_steps": 716, + "loss": 2.381, + "learning_rate": 7.407721680101824e-07, + "epoch": 0.8754578754578755 + }, + { + "current_steps": 717, + "loss": 2.4872, + "learning_rate": 7.403478998727195e-07, + "epoch": 0.8766788766788767 + }, + { + "current_steps": 718, + "loss": 2.2723, + "learning_rate": 7.399236317352566e-07, + "epoch": 0.8778998778998779 + }, + { + "current_steps": 719, + "loss": 2.2035, + "learning_rate": 7.394993635977937e-07, + "epoch": 0.8791208791208791 + }, + { + "current_steps": 720, + "loss": 2.3118, + "learning_rate": 7.390750954603309e-07, + "epoch": 0.8803418803418803 + }, + { + "current_steps": 721, + "loss": 2.2506, + "learning_rate": 7.386508273228679e-07, + "epoch": 0.8815628815628815 + }, + { + "current_steps": 722, + "loss": 2.6092, + "learning_rate": 7.382265591854051e-07, + "epoch": 0.8827838827838828 + }, + { + "current_steps": 723, + "loss": 1.9771, + "learning_rate": 7.378022910479423e-07, + "epoch": 0.884004884004884 + }, + { + "current_steps": 724, + "loss": 2.2507, + "learning_rate": 7.373780229104793e-07, + "epoch": 0.8852258852258852 + }, + { + "current_steps": 725, + "loss": 2.4446, + "learning_rate": 7.369537547730165e-07, + "epoch": 0.8864468864468864 + }, + { + "current_steps": 726, + "loss": 2.4548, + "learning_rate": 7.365294866355536e-07, + "epoch": 0.8876678876678876 + }, + { + "current_steps": 727, + "loss": 2.3634, + "learning_rate": 7.361052184980907e-07, + "epoch": 0.8888888888888888 + }, + { + "current_steps": 728, + "loss": 2.3383, + "learning_rate": 7.356809503606279e-07, + "epoch": 0.8901098901098901 + }, + { + "current_steps": 729, + "loss": 2.2737, + "learning_rate": 7.352566822231651e-07, + "epoch": 0.8913308913308914 + }, + { + "current_steps": 730, + "loss": 2.3812, + "learning_rate": 7.348324140857021e-07, + "epoch": 0.8925518925518926 + }, + { + "current_steps": 731, + "loss": 2.437, + "learning_rate": 7.344081459482393e-07, + "epoch": 0.8937728937728938 + }, + { + "current_steps": 732, + "loss": 2.5315, + "learning_rate": 7.339838778107764e-07, + "epoch": 0.894993894993895 + }, + { + "current_steps": 733, + "loss": 2.4212, + "learning_rate": 7.335596096733136e-07, + "epoch": 0.8962148962148963 + }, + { + "current_steps": 734, + "loss": 2.409, + "learning_rate": 7.331353415358506e-07, + "epoch": 0.8974358974358975 + }, + { + "current_steps": 735, + "loss": 1.9581, + "learning_rate": 7.327110733983878e-07, + "epoch": 0.8986568986568987 + }, + { + "current_steps": 736, + "loss": 2.4427, + "learning_rate": 7.322868052609249e-07, + "epoch": 0.8998778998778999 + }, + { + "current_steps": 737, + "loss": 2.3496, + "learning_rate": 7.31862537123462e-07, + "epoch": 0.9010989010989011 + }, + { + "current_steps": 738, + "loss": 2.2771, + "learning_rate": 7.314382689859992e-07, + "epoch": 0.9023199023199023 + }, + { + "current_steps": 739, + "loss": 2.499, + "learning_rate": 7.310140008485363e-07, + "epoch": 0.9035409035409036 + }, + { + "current_steps": 740, + "loss": 2.4191, + "learning_rate": 7.305897327110734e-07, + "epoch": 0.9047619047619048 + }, + { + "current_steps": 741, + "loss": 1.8152, + "learning_rate": 7.301654645736105e-07, + "epoch": 0.905982905982906 + }, + { + "current_steps": 742, + "loss": 2.2972, + "learning_rate": 7.297411964361477e-07, + "epoch": 0.9072039072039072 + }, + { + "current_steps": 743, + "loss": 2.3035, + "learning_rate": 7.293169282986847e-07, + "epoch": 0.9084249084249084 + }, + { + "current_steps": 744, + "loss": 2.3255, + "learning_rate": 7.288926601612219e-07, + "epoch": 0.9096459096459096 + }, + { + "current_steps": 745, + "loss": 2.3649, + "learning_rate": 7.28468392023759e-07, + "epoch": 0.9108669108669109 + }, + { + "current_steps": 746, + "loss": 2.4836, + "learning_rate": 7.280441238862961e-07, + "epoch": 0.9120879120879121 + }, + { + "current_steps": 747, + "loss": 2.3354, + "learning_rate": 7.276198557488332e-07, + "epoch": 0.9133089133089133 + }, + { + "current_steps": 748, + "loss": 2.0722, + "learning_rate": 7.271955876113704e-07, + "epoch": 0.9145299145299145 + }, + { + "current_steps": 749, + "loss": 2.392, + "learning_rate": 7.267713194739074e-07, + "epoch": 0.9157509157509157 + }, + { + "current_steps": 750, + "loss": 2.5263, + "learning_rate": 7.263470513364446e-07, + "epoch": 0.9169719169719169 + }, + { + "current_steps": 751, + "loss": 2.5742, + "learning_rate": 7.259227831989817e-07, + "epoch": 0.9181929181929182 + }, + { + "current_steps": 752, + "loss": 2.3132, + "learning_rate": 7.254985150615188e-07, + "epoch": 0.9194139194139194 + }, + { + "current_steps": 753, + "loss": 2.4107, + "learning_rate": 7.250742469240559e-07, + "epoch": 0.9206349206349206 + }, + { + "current_steps": 754, + "loss": 2.395, + "learning_rate": 7.246499787865931e-07, + "epoch": 0.9218559218559218 + }, + { + "current_steps": 755, + "loss": 2.3304, + "learning_rate": 7.242257106491302e-07, + "epoch": 0.9230769230769231 + }, + { + "current_steps": 756, + "loss": 2.3967, + "learning_rate": 7.238014425116673e-07, + "epoch": 0.9242979242979243 + }, + { + "current_steps": 757, + "loss": 2.2601, + "learning_rate": 7.233771743742045e-07, + "epoch": 0.9255189255189256 + }, + { + "current_steps": 758, + "loss": 2.4768, + "learning_rate": 7.229529062367415e-07, + "epoch": 0.9267399267399268 + }, + { + "current_steps": 759, + "loss": 2.3564, + "learning_rate": 7.225286380992787e-07, + "epoch": 0.927960927960928 + }, + { + "current_steps": 760, + "loss": 2.4531, + "learning_rate": 7.221043699618158e-07, + "epoch": 0.9291819291819292 + }, + { + "current_steps": 761, + "loss": 2.305, + "learning_rate": 7.216801018243529e-07, + "epoch": 0.9304029304029304 + }, + { + "current_steps": 762, + "loss": 2.3552, + "learning_rate": 7.212558336868901e-07, + "epoch": 0.9316239316239316 + }, + { + "current_steps": 763, + "loss": 2.5643, + "learning_rate": 7.208315655494273e-07, + "epoch": 0.9328449328449329 + }, + { + "current_steps": 764, + "loss": 2.2658, + "learning_rate": 7.204072974119643e-07, + "epoch": 0.9340659340659341 + }, + { + "current_steps": 765, + "loss": 2.5122, + "learning_rate": 7.199830292745015e-07, + "epoch": 0.9352869352869353 + }, + { + "current_steps": 766, + "loss": 2.3411, + "learning_rate": 7.195587611370386e-07, + "epoch": 0.9365079365079365 + }, + { + "current_steps": 767, + "loss": 2.218, + "learning_rate": 7.191344929995757e-07, + "epoch": 0.9377289377289377 + }, + { + "current_steps": 768, + "loss": 2.3462, + "learning_rate": 7.187102248621128e-07, + "epoch": 0.938949938949939 + }, + { + "current_steps": 769, + "loss": 2.2769, + "learning_rate": 7.1828595672465e-07, + "epoch": 0.9401709401709402 + }, + { + "current_steps": 770, + "loss": 2.351, + "learning_rate": 7.178616885871871e-07, + "epoch": 0.9413919413919414 + }, + { + "current_steps": 771, + "loss": 2.439, + "learning_rate": 7.174374204497242e-07, + "epoch": 0.9426129426129426 + }, + { + "current_steps": 772, + "loss": 2.4471, + "learning_rate": 7.170131523122614e-07, + "epoch": 0.9438339438339438 + }, + { + "current_steps": 773, + "loss": 2.4828, + "learning_rate": 7.165888841747984e-07, + "epoch": 0.945054945054945 + }, + { + "current_steps": 774, + "loss": 2.3889, + "learning_rate": 7.161646160373356e-07, + "epoch": 0.9462759462759462 + }, + { + "current_steps": 775, + "loss": 2.5006, + "learning_rate": 7.157403478998727e-07, + "epoch": 0.9474969474969475 + }, + { + "current_steps": 776, + "loss": 2.315, + "learning_rate": 7.153160797624098e-07, + "epoch": 0.9487179487179487 + }, + { + "current_steps": 777, + "loss": 2.351, + "learning_rate": 7.148918116249469e-07, + "epoch": 0.9499389499389499 + }, + { + "current_steps": 778, + "loss": 2.4471, + "learning_rate": 7.144675434874841e-07, + "epoch": 0.9511599511599511 + }, + { + "current_steps": 779, + "loss": 2.439, + "learning_rate": 7.140432753500211e-07, + "epoch": 0.9523809523809523 + }, + { + "current_steps": 780, + "loss": 2.2608, + "learning_rate": 7.136190072125583e-07, + "epoch": 0.9536019536019537 + }, + { + "current_steps": 781, + "loss": 2.2876, + "learning_rate": 7.131947390750954e-07, + "epoch": 0.9548229548229549 + }, + { + "current_steps": 782, + "loss": 2.4642, + "learning_rate": 7.127704709376326e-07, + "epoch": 0.9560439560439561 + }, + { + "current_steps": 783, + "loss": 2.282, + "learning_rate": 7.123462028001696e-07, + "epoch": 0.9572649572649573 + }, + { + "current_steps": 784, + "loss": 2.3532, + "learning_rate": 7.119219346627068e-07, + "epoch": 0.9584859584859585 + }, + { + "current_steps": 785, + "loss": 2.2962, + "learning_rate": 7.114976665252438e-07, + "epoch": 0.9597069597069597 + }, + { + "current_steps": 786, + "loss": 2.2834, + "learning_rate": 7.11073398387781e-07, + "epoch": 0.960927960927961 + }, + { + "current_steps": 787, + "loss": 2.4695, + "learning_rate": 7.106491302503182e-07, + "epoch": 0.9621489621489622 + }, + { + "current_steps": 788, + "loss": 2.2706, + "learning_rate": 7.102248621128553e-07, + "epoch": 0.9633699633699634 + }, + { + "current_steps": 789, + "loss": 2.4042, + "learning_rate": 7.098005939753924e-07, + "epoch": 0.9645909645909646 + }, + { + "current_steps": 790, + "loss": 2.3795, + "learning_rate": 7.093763258379295e-07, + "epoch": 0.9658119658119658 + }, + { + "current_steps": 791, + "loss": 2.4496, + "learning_rate": 7.089520577004667e-07, + "epoch": 0.967032967032967 + }, + { + "current_steps": 792, + "loss": 2.5771, + "learning_rate": 7.085277895630037e-07, + "epoch": 0.9682539682539683 + }, + { + "current_steps": 793, + "loss": 2.4001, + "learning_rate": 7.081035214255409e-07, + "epoch": 0.9694749694749695 + }, + { + "current_steps": 794, + "loss": 2.384, + "learning_rate": 7.07679253288078e-07, + "epoch": 0.9706959706959707 + }, + { + "current_steps": 795, + "loss": 2.5688, + "learning_rate": 7.072549851506151e-07, + "epoch": 0.9719169719169719 + }, + { + "current_steps": 796, + "loss": 2.2825, + "learning_rate": 7.068307170131523e-07, + "epoch": 0.9731379731379731 + }, + { + "current_steps": 797, + "loss": 2.5268, + "learning_rate": 7.064064488756895e-07, + "epoch": 0.9743589743589743 + }, + { + "current_steps": 798, + "loss": 2.3906, + "learning_rate": 7.059821807382265e-07, + "epoch": 0.9755799755799756 + }, + { + "current_steps": 799, + "loss": 2.3617, + "learning_rate": 7.055579126007637e-07, + "epoch": 0.9768009768009768 + }, + { + "current_steps": 800, + "loss": 2.5088, + "learning_rate": 7.051336444633008e-07, + "epoch": 0.978021978021978 + }, + { + "current_steps": 801, + "loss": 2.2276, + "learning_rate": 7.047093763258379e-07, + "epoch": 0.9792429792429792 + }, + { + "current_steps": 802, + "loss": 1.6384, + "learning_rate": 7.042851081883751e-07, + "epoch": 0.9804639804639804 + }, + { + "current_steps": 803, + "loss": 2.2942, + "learning_rate": 7.038608400509122e-07, + "epoch": 0.9816849816849816 + }, + { + "current_steps": 804, + "loss": 2.2414, + "learning_rate": 7.034365719134493e-07, + "epoch": 0.9829059829059829 + }, + { + "current_steps": 805, + "loss": 2.6297, + "learning_rate": 7.030123037759864e-07, + "epoch": 0.9841269841269841 + }, + { + "current_steps": 806, + "loss": 2.3205, + "learning_rate": 7.025880356385236e-07, + "epoch": 0.9853479853479854 + }, + { + "current_steps": 807, + "loss": 2.4005, + "learning_rate": 7.021637675010606e-07, + "epoch": 0.9865689865689866 + }, + { + "current_steps": 808, + "loss": 2.4325, + "learning_rate": 7.017394993635978e-07, + "epoch": 0.9877899877899878 + }, + { + "current_steps": 809, + "loss": 2.4885, + "learning_rate": 7.013152312261349e-07, + "epoch": 0.989010989010989 + }, + { + "current_steps": 810, + "loss": 2.3762, + "learning_rate": 7.00890963088672e-07, + "epoch": 0.9902319902319903 + }, + { + "current_steps": 811, + "loss": 2.3454, + "learning_rate": 7.004666949512091e-07, + "epoch": 0.9914529914529915 + }, + { + "current_steps": 812, + "loss": 2.321, + "learning_rate": 7.000424268137463e-07, + "epoch": 0.9926739926739927 + }, + { + "current_steps": 813, + "loss": 2.29, + "learning_rate": 6.996181586762833e-07, + "epoch": 0.9938949938949939 + }, + { + "current_steps": 814, + "loss": 2.2783, + "learning_rate": 6.991938905388205e-07, + "epoch": 0.9951159951159951 + }, + { + "current_steps": 815, + "loss": 2.2008, + "learning_rate": 6.987696224013576e-07, + "epoch": 0.9963369963369964 + }, + { + "current_steps": 816, + "loss": 2.3641, + "learning_rate": 6.983453542638947e-07, + "epoch": 0.9975579975579976 + }, + { + "current_steps": 817, + "loss": 2.4528, + "learning_rate": 6.979210861264318e-07, + "epoch": 0.9987789987789988 + }, + { + "current_steps": 818, + "loss": 2.6774, + "learning_rate": 6.97496817988969e-07, + "epoch": 1.0 + }, + { + "current_steps": 819, + "loss": 2.1175, + "learning_rate": 6.970725498515061e-07, + "epoch": 1.0012210012210012 + }, + { + "current_steps": 820, + "loss": 2.2671, + "learning_rate": 6.966482817140432e-07, + "epoch": 1.0024420024420024 + }, + { + "current_steps": 821, + "loss": 2.292, + "learning_rate": 6.962240135765804e-07, + "epoch": 1.0036630036630036 + }, + { + "current_steps": 822, + "loss": 2.3291, + "learning_rate": 6.957997454391174e-07, + "epoch": 1.0048840048840049 + }, + { + "current_steps": 823, + "loss": 2.3619, + "learning_rate": 6.953754773016546e-07, + "epoch": 1.006105006105006 + }, + { + "current_steps": 824, + "loss": 2.208, + "learning_rate": 6.949512091641917e-07, + "epoch": 1.0073260073260073 + }, + { + "current_steps": 825, + "loss": 2.5134, + "learning_rate": 6.945269410267288e-07, + "epoch": 1.0085470085470085 + }, + { + "current_steps": 826, + "loss": 2.4692, + "learning_rate": 6.941026728892659e-07, + "epoch": 1.0097680097680097 + }, + { + "current_steps": 827, + "loss": 2.4758, + "learning_rate": 6.936784047518031e-07, + "epoch": 1.010989010989011 + }, + { + "current_steps": 828, + "loss": 2.3495, + "learning_rate": 6.932541366143401e-07, + "epoch": 1.0122100122100122 + }, + { + "current_steps": 829, + "loss": 2.3487, + "learning_rate": 6.928298684768774e-07, + "epoch": 1.0134310134310134 + }, + { + "current_steps": 830, + "loss": 2.2628, + "learning_rate": 6.924056003394145e-07, + "epoch": 1.0146520146520146 + }, + { + "current_steps": 831, + "loss": 2.4076, + "learning_rate": 6.919813322019517e-07, + "epoch": 1.0158730158730158 + }, + { + "current_steps": 832, + "loss": 2.729, + "learning_rate": 6.915570640644887e-07, + "epoch": 1.017094017094017 + }, + { + "current_steps": 833, + "loss": 2.3974, + "learning_rate": 6.911327959270259e-07, + "epoch": 1.0183150183150182 + }, + { + "current_steps": 834, + "loss": 2.3257, + "learning_rate": 6.907085277895631e-07, + "epoch": 1.0195360195360195 + }, + { + "current_steps": 835, + "loss": 2.3384, + "learning_rate": 6.902842596521001e-07, + "epoch": 1.0207570207570207 + }, + { + "current_steps": 836, + "loss": 2.4479, + "learning_rate": 6.898599915146373e-07, + "epoch": 1.021978021978022 + }, + { + "current_steps": 837, + "loss": 2.3651, + "learning_rate": 6.894357233771744e-07, + "epoch": 1.0231990231990231 + }, + { + "current_steps": 838, + "loss": 2.4723, + "learning_rate": 6.890114552397115e-07, + "epoch": 1.0244200244200243 + }, + { + "current_steps": 839, + "loss": 2.2568, + "learning_rate": 6.885871871022486e-07, + "epoch": 1.0256410256410255 + }, + { + "current_steps": 840, + "loss": 2.3863, + "learning_rate": 6.881629189647858e-07, + "epoch": 1.0268620268620268 + }, + { + "current_steps": 841, + "loss": 2.2514, + "learning_rate": 6.877386508273228e-07, + "epoch": 1.028083028083028 + }, + { + "current_steps": 842, + "loss": 2.6491, + "learning_rate": 6.8731438268986e-07, + "epoch": 1.0293040293040292 + }, + { + "current_steps": 843, + "loss": 2.4095, + "learning_rate": 6.868901145523971e-07, + "epoch": 1.0305250305250304 + }, + { + "current_steps": 844, + "loss": 2.3834, + "learning_rate": 6.864658464149342e-07, + "epoch": 1.0317460317460316 + }, + { + "current_steps": 845, + "loss": 2.397, + "learning_rate": 6.860415782774713e-07, + "epoch": 1.032967032967033 + }, + { + "current_steps": 846, + "loss": 2.1143, + "learning_rate": 6.856173101400085e-07, + "epoch": 1.0341880341880343 + }, + { + "current_steps": 847, + "loss": 2.3587, + "learning_rate": 6.851930420025455e-07, + "epoch": 1.0354090354090355 + }, + { + "current_steps": 848, + "loss": 2.4577, + "learning_rate": 6.847687738650827e-07, + "epoch": 1.0366300366300367 + }, + { + "current_steps": 849, + "loss": 1.538, + "learning_rate": 6.843445057276199e-07, + "epoch": 1.037851037851038 + }, + { + "current_steps": 850, + "loss": 2.2828, + "learning_rate": 6.839202375901569e-07, + "epoch": 1.0390720390720392 + }, + { + "current_steps": 851, + "loss": 2.22, + "learning_rate": 6.834959694526941e-07, + "epoch": 1.0402930402930404 + }, + { + "current_steps": 852, + "loss": 2.247, + "learning_rate": 6.830717013152312e-07, + "epoch": 1.0415140415140416 + }, + { + "current_steps": 853, + "loss": 2.3967, + "learning_rate": 6.826474331777683e-07, + "epoch": 1.0427350427350428 + }, + { + "current_steps": 854, + "loss": 2.1841, + "learning_rate": 6.822231650403054e-07, + "epoch": 1.043956043956044 + }, + { + "current_steps": 855, + "loss": 2.4467, + "learning_rate": 6.817988969028426e-07, + "epoch": 1.0451770451770452 + }, + { + "current_steps": 856, + "loss": 2.429, + "learning_rate": 6.813746287653796e-07, + "epoch": 1.0463980463980465 + }, + { + "current_steps": 857, + "loss": 2.3784, + "learning_rate": 6.809503606279168e-07, + "epoch": 1.0476190476190477 + }, + { + "current_steps": 858, + "loss": 2.3747, + "learning_rate": 6.805260924904539e-07, + "epoch": 1.0488400488400489 + }, + { + "current_steps": 859, + "loss": 2.3006, + "learning_rate": 6.80101824352991e-07, + "epoch": 1.05006105006105 + }, + { + "current_steps": 860, + "loss": 2.4579, + "learning_rate": 6.796775562155281e-07, + "epoch": 1.0512820512820513 + }, + { + "current_steps": 861, + "loss": 2.3069, + "learning_rate": 6.792532880780653e-07, + "epoch": 1.0525030525030525 + }, + { + "current_steps": 862, + "loss": 2.4791, + "learning_rate": 6.788290199406023e-07, + "epoch": 1.0537240537240538 + }, + { + "current_steps": 863, + "loss": 2.453, + "learning_rate": 6.784047518031396e-07, + "epoch": 1.054945054945055 + }, + { + "current_steps": 864, + "loss": 2.3214, + "learning_rate": 6.779804836656768e-07, + "epoch": 1.0561660561660562 + }, + { + "current_steps": 865, + "loss": 2.3234, + "learning_rate": 6.775562155282138e-07, + "epoch": 1.0573870573870574 + }, + { + "current_steps": 866, + "loss": 2.304, + "learning_rate": 6.77131947390751e-07, + "epoch": 1.0586080586080586 + }, + { + "current_steps": 867, + "loss": 2.3804, + "learning_rate": 6.767076792532881e-07, + "epoch": 1.0598290598290598 + }, + { + "current_steps": 868, + "loss": 2.2922, + "learning_rate": 6.762834111158252e-07, + "epoch": 1.061050061050061 + }, + { + "current_steps": 869, + "loss": 2.3768, + "learning_rate": 6.758591429783623e-07, + "epoch": 1.0622710622710623 + }, + { + "current_steps": 870, + "loss": 2.3072, + "learning_rate": 6.754348748408995e-07, + "epoch": 1.0634920634920635 + }, + { + "current_steps": 871, + "loss": 2.2768, + "learning_rate": 6.750106067034365e-07, + "epoch": 1.0647130647130647 + }, + { + "current_steps": 872, + "loss": 2.3247, + "learning_rate": 6.745863385659737e-07, + "epoch": 1.065934065934066 + }, + { + "current_steps": 873, + "loss": 2.0815, + "learning_rate": 6.741620704285108e-07, + "epoch": 1.0671550671550671 + }, + { + "current_steps": 874, + "loss": 2.4108, + "learning_rate": 6.73737802291048e-07, + "epoch": 1.0683760683760684 + }, + { + "current_steps": 875, + "loss": 1.9925, + "learning_rate": 6.73313534153585e-07, + "epoch": 1.0695970695970696 + }, + { + "current_steps": 876, + "loss": 2.3896, + "learning_rate": 6.728892660161222e-07, + "epoch": 1.0708180708180708 + }, + { + "current_steps": 877, + "loss": 2.3782, + "learning_rate": 6.724649978786592e-07, + "epoch": 1.072039072039072 + }, + { + "current_steps": 878, + "loss": 2.3915, + "learning_rate": 6.720407297411964e-07, + "epoch": 1.0732600732600732 + }, + { + "current_steps": 879, + "loss": 2.3317, + "learning_rate": 6.716164616037335e-07, + "epoch": 1.0744810744810744 + }, + { + "current_steps": 880, + "loss": 2.2453, + "learning_rate": 6.711921934662707e-07, + "epoch": 1.0757020757020757 + }, + { + "current_steps": 881, + "loss": 2.3328, + "learning_rate": 6.707679253288078e-07, + "epoch": 1.0769230769230769 + }, + { + "current_steps": 882, + "loss": 2.1701, + "learning_rate": 6.703436571913449e-07, + "epoch": 1.078144078144078 + }, + { + "current_steps": 883, + "loss": 2.5368, + "learning_rate": 6.699193890538821e-07, + "epoch": 1.0793650793650793 + }, + { + "current_steps": 884, + "loss": 2.3038, + "learning_rate": 6.694951209164191e-07, + "epoch": 1.0805860805860805 + }, + { + "current_steps": 885, + "loss": 2.3156, + "learning_rate": 6.690708527789563e-07, + "epoch": 1.0818070818070817 + }, + { + "current_steps": 886, + "loss": 2.2488, + "learning_rate": 6.686465846414934e-07, + "epoch": 1.083028083028083 + }, + { + "current_steps": 887, + "loss": 2.2655, + "learning_rate": 6.682223165040305e-07, + "epoch": 1.0842490842490842 + }, + { + "current_steps": 888, + "loss": 2.5276, + "learning_rate": 6.677980483665676e-07, + "epoch": 1.0854700854700854 + }, + { + "current_steps": 889, + "loss": 2.4105, + "learning_rate": 6.673737802291048e-07, + "epoch": 1.0866910866910866 + }, + { + "current_steps": 890, + "loss": 2.341, + "learning_rate": 6.669495120916418e-07, + "epoch": 1.0879120879120878 + }, + { + "current_steps": 891, + "loss": 2.319, + "learning_rate": 6.66525243954179e-07, + "epoch": 1.089133089133089 + }, + { + "current_steps": 892, + "loss": 2.3557, + "learning_rate": 6.661009758167161e-07, + "epoch": 1.0903540903540903 + }, + { + "current_steps": 893, + "loss": 2.2305, + "learning_rate": 6.656767076792532e-07, + "epoch": 1.0915750915750915 + }, + { + "current_steps": 894, + "loss": 2.4857, + "learning_rate": 6.652524395417903e-07, + "epoch": 1.092796092796093 + }, + { + "current_steps": 895, + "loss": 2.4055, + "learning_rate": 6.648281714043275e-07, + "epoch": 1.0940170940170941 + }, + { + "current_steps": 896, + "loss": 2.3123, + "learning_rate": 6.644039032668645e-07, + "epoch": 1.0952380952380953 + }, + { + "current_steps": 897, + "loss": 2.4367, + "learning_rate": 6.639796351294018e-07, + "epoch": 1.0964590964590966 + }, + { + "current_steps": 898, + "loss": 2.3946, + "learning_rate": 6.63555366991939e-07, + "epoch": 1.0976800976800978 + }, + { + "current_steps": 899, + "loss": 2.3873, + "learning_rate": 6.63131098854476e-07, + "epoch": 1.098901098901099 + }, + { + "current_steps": 900, + "loss": 1.5138, + "learning_rate": 6.627068307170132e-07, + "epoch": 1.1001221001221002 + }, + { + "current_steps": 901, + "loss": 2.3876, + "learning_rate": 6.622825625795503e-07, + "epoch": 1.1013431013431014 + }, + { + "current_steps": 902, + "loss": 2.2766, + "learning_rate": 6.618582944420874e-07, + "epoch": 1.1025641025641026 + }, + { + "current_steps": 903, + "loss": 2.3665, + "learning_rate": 6.614340263046245e-07, + "epoch": 1.1037851037851039 + }, + { + "current_steps": 904, + "loss": 2.3511, + "learning_rate": 6.610097581671617e-07, + "epoch": 1.105006105006105 + }, + { + "current_steps": 905, + "loss": 2.2468, + "learning_rate": 6.605854900296987e-07, + "epoch": 1.1062271062271063 + }, + { + "current_steps": 906, + "loss": 2.4167, + "learning_rate": 6.601612218922359e-07, + "epoch": 1.1074481074481075 + }, + { + "current_steps": 907, + "loss": 2.4303, + "learning_rate": 6.59736953754773e-07, + "epoch": 1.1086691086691087 + }, + { + "current_steps": 908, + "loss": 2.3391, + "learning_rate": 6.593126856173101e-07, + "epoch": 1.10989010989011 + }, + { + "current_steps": 909, + "loss": 2.4514, + "learning_rate": 6.588884174798472e-07, + "epoch": 1.1111111111111112 + }, + { + "current_steps": 910, + "loss": 2.4378, + "learning_rate": 6.584641493423844e-07, + "epoch": 1.1123321123321124 + }, + { + "current_steps": 911, + "loss": 2.348, + "learning_rate": 6.580398812049214e-07, + "epoch": 1.1135531135531136 + }, + { + "current_steps": 912, + "loss": 2.4422, + "learning_rate": 6.576156130674586e-07, + "epoch": 1.1147741147741148 + }, + { + "current_steps": 913, + "loss": 2.4376, + "learning_rate": 6.571913449299958e-07, + "epoch": 1.115995115995116 + }, + { + "current_steps": 914, + "loss": 2.4417, + "learning_rate": 6.567670767925328e-07, + "epoch": 1.1172161172161172 + }, + { + "current_steps": 915, + "loss": 2.2753, + "learning_rate": 6.5634280865507e-07, + "epoch": 1.1184371184371185 + }, + { + "current_steps": 916, + "loss": 2.3375, + "learning_rate": 6.559185405176071e-07, + "epoch": 1.1196581196581197 + }, + { + "current_steps": 917, + "loss": 2.2042, + "learning_rate": 6.554942723801442e-07, + "epoch": 1.120879120879121 + }, + { + "current_steps": 918, + "loss": 2.4154, + "learning_rate": 6.550700042426813e-07, + "epoch": 1.122100122100122 + }, + { + "current_steps": 919, + "loss": 2.2118, + "learning_rate": 6.546457361052185e-07, + "epoch": 1.1233211233211233 + }, + { + "current_steps": 920, + "loss": 2.2533, + "learning_rate": 6.542214679677555e-07, + "epoch": 1.1245421245421245 + }, + { + "current_steps": 921, + "loss": 2.2498, + "learning_rate": 6.537971998302927e-07, + "epoch": 1.1257631257631258 + }, + { + "current_steps": 922, + "loss": 2.469, + "learning_rate": 6.533729316928298e-07, + "epoch": 1.126984126984127 + }, + { + "current_steps": 923, + "loss": 2.3965, + "learning_rate": 6.529486635553669e-07, + "epoch": 1.1282051282051282 + }, + { + "current_steps": 924, + "loss": 2.5654, + "learning_rate": 6.52524395417904e-07, + "epoch": 1.1294261294261294 + }, + { + "current_steps": 925, + "loss": 2.5071, + "learning_rate": 6.521001272804412e-07, + "epoch": 1.1306471306471306 + }, + { + "current_steps": 926, + "loss": 2.3034, + "learning_rate": 6.516758591429782e-07, + "epoch": 1.1318681318681318 + }, + { + "current_steps": 927, + "loss": 2.4157, + "learning_rate": 6.512515910055154e-07, + "epoch": 1.133089133089133 + }, + { + "current_steps": 928, + "loss": 2.2285, + "learning_rate": 6.508273228680525e-07, + "epoch": 1.1343101343101343 + }, + { + "current_steps": 929, + "loss": 2.4468, + "learning_rate": 6.504030547305896e-07, + "epoch": 1.1355311355311355 + }, + { + "current_steps": 930, + "loss": 2.3693, + "learning_rate": 6.499787865931269e-07, + "epoch": 1.1367521367521367 + }, + { + "current_steps": 931, + "loss": 2.4188, + "learning_rate": 6.49554518455664e-07, + "epoch": 1.137973137973138 + }, + { + "current_steps": 932, + "loss": 2.5663, + "learning_rate": 6.491302503182012e-07, + "epoch": 1.1391941391941391 + }, + { + "current_steps": 933, + "loss": 1.5958, + "learning_rate": 6.487059821807382e-07, + "epoch": 1.1404151404151404 + }, + { + "current_steps": 934, + "loss": 2.1971, + "learning_rate": 6.482817140432754e-07, + "epoch": 1.1416361416361416 + }, + { + "current_steps": 935, + "loss": 2.4066, + "learning_rate": 6.478574459058125e-07, + "epoch": 1.1428571428571428 + }, + { + "current_steps": 936, + "loss": 2.4221, + "learning_rate": 6.474331777683496e-07, + "epoch": 1.144078144078144 + }, + { + "current_steps": 937, + "loss": 2.1776, + "learning_rate": 6.470089096308867e-07, + "epoch": 1.1452991452991452 + }, + { + "current_steps": 938, + "loss": 2.3922, + "learning_rate": 6.465846414934239e-07, + "epoch": 1.1465201465201464 + }, + { + "current_steps": 939, + "loss": 2.37, + "learning_rate": 6.461603733559609e-07, + "epoch": 1.1477411477411477 + }, + { + "current_steps": 940, + "loss": 2.485, + "learning_rate": 6.457361052184981e-07, + "epoch": 1.1489621489621489 + }, + { + "current_steps": 941, + "loss": 2.3641, + "learning_rate": 6.453118370810352e-07, + "epoch": 1.15018315018315 + }, + { + "current_steps": 942, + "loss": 2.4598, + "learning_rate": 6.448875689435723e-07, + "epoch": 1.1514041514041513 + }, + { + "current_steps": 943, + "loss": 2.3717, + "learning_rate": 6.444633008061094e-07, + "epoch": 1.1526251526251525 + }, + { + "current_steps": 944, + "loss": 2.4935, + "learning_rate": 6.440390326686466e-07, + "epoch": 1.1538461538461537 + }, + { + "current_steps": 945, + "loss": 2.4485, + "learning_rate": 6.436147645311837e-07, + "epoch": 1.155067155067155 + }, + { + "current_steps": 946, + "loss": 2.2732, + "learning_rate": 6.431904963937208e-07, + "epoch": 1.1562881562881562 + }, + { + "current_steps": 947, + "loss": 2.4666, + "learning_rate": 6.42766228256258e-07, + "epoch": 1.1575091575091574 + }, + { + "current_steps": 948, + "loss": 2.3071, + "learning_rate": 6.42341960118795e-07, + "epoch": 1.1587301587301586 + }, + { + "current_steps": 949, + "loss": 2.4951, + "learning_rate": 6.419176919813322e-07, + "epoch": 1.1599511599511598 + }, + { + "current_steps": 950, + "loss": 2.3543, + "learning_rate": 6.414934238438693e-07, + "epoch": 1.1611721611721613 + }, + { + "current_steps": 951, + "loss": 2.3184, + "learning_rate": 6.410691557064064e-07, + "epoch": 1.1623931623931625 + }, + { + "current_steps": 952, + "loss": 2.1606, + "learning_rate": 6.406448875689435e-07, + "epoch": 1.1636141636141637 + }, + { + "current_steps": 953, + "loss": 2.4665, + "learning_rate": 6.402206194314807e-07, + "epoch": 1.164835164835165 + }, + { + "current_steps": 954, + "loss": 2.2932, + "learning_rate": 6.397963512940177e-07, + "epoch": 1.1660561660561661 + }, + { + "current_steps": 955, + "loss": 2.5399, + "learning_rate": 6.393720831565549e-07, + "epoch": 1.1672771672771673 + }, + { + "current_steps": 956, + "loss": 2.4062, + "learning_rate": 6.38947815019092e-07, + "epoch": 1.1684981684981686 + }, + { + "current_steps": 957, + "loss": 2.3125, + "learning_rate": 6.385235468816291e-07, + "epoch": 1.1697191697191698 + }, + { + "current_steps": 958, + "loss": 2.1744, + "learning_rate": 6.380992787441662e-07, + "epoch": 1.170940170940171 + }, + { + "current_steps": 959, + "loss": 2.4678, + "learning_rate": 6.376750106067034e-07, + "epoch": 1.1721611721611722 + }, + { + "current_steps": 960, + "loss": 2.4814, + "learning_rate": 6.372507424692405e-07, + "epoch": 1.1733821733821734 + }, + { + "current_steps": 961, + "loss": 1.5218, + "learning_rate": 6.368264743317776e-07, + "epoch": 1.1746031746031746 + }, + { + "current_steps": 962, + "loss": 2.2987, + "learning_rate": 6.364022061943148e-07, + "epoch": 1.1758241758241759 + }, + { + "current_steps": 963, + "loss": 2.2639, + "learning_rate": 6.359779380568518e-07, + "epoch": 1.177045177045177 + }, + { + "current_steps": 964, + "loss": 2.2112, + "learning_rate": 6.355536699193891e-07, + "epoch": 1.1782661782661783 + }, + { + "current_steps": 965, + "loss": 2.4229, + "learning_rate": 6.351294017819262e-07, + "epoch": 1.1794871794871795 + }, + { + "current_steps": 966, + "loss": 2.5046, + "learning_rate": 6.347051336444633e-07, + "epoch": 1.1807081807081807 + }, + { + "current_steps": 967, + "loss": 2.4304, + "learning_rate": 6.342808655070004e-07, + "epoch": 1.181929181929182 + }, + { + "current_steps": 968, + "loss": 2.4924, + "learning_rate": 6.338565973695376e-07, + "epoch": 1.1831501831501832 + }, + { + "current_steps": 969, + "loss": 2.3628, + "learning_rate": 6.334323292320746e-07, + "epoch": 1.1843711843711844 + }, + { + "current_steps": 970, + "loss": 2.3764, + "learning_rate": 6.330080610946118e-07, + "epoch": 1.1855921855921856 + }, + { + "current_steps": 971, + "loss": 2.3585, + "learning_rate": 6.325837929571489e-07, + "epoch": 1.1868131868131868 + }, + { + "current_steps": 972, + "loss": 2.2891, + "learning_rate": 6.32159524819686e-07, + "epoch": 1.188034188034188 + }, + { + "current_steps": 973, + "loss": 2.1875, + "learning_rate": 6.317352566822231e-07, + "epoch": 1.1892551892551892 + }, + { + "current_steps": 974, + "loss": 2.5204, + "learning_rate": 6.313109885447603e-07, + "epoch": 1.1904761904761905 + }, + { + "current_steps": 975, + "loss": 2.351, + "learning_rate": 6.308867204072975e-07, + "epoch": 1.1916971916971917 + }, + { + "current_steps": 976, + "loss": 2.3086, + "learning_rate": 6.304624522698345e-07, + "epoch": 1.192918192918193 + }, + { + "current_steps": 977, + "loss": 2.3053, + "learning_rate": 6.300381841323717e-07, + "epoch": 1.1941391941391941 + }, + { + "current_steps": 978, + "loss": 2.3173, + "learning_rate": 6.296139159949088e-07, + "epoch": 1.1953601953601953 + }, + { + "current_steps": 979, + "loss": 2.3709, + "learning_rate": 6.291896478574459e-07, + "epoch": 1.1965811965811965 + }, + { + "current_steps": 980, + "loss": 2.5121, + "learning_rate": 6.28765379719983e-07, + "epoch": 1.1978021978021978 + }, + { + "current_steps": 981, + "loss": 2.5294, + "learning_rate": 6.283411115825202e-07, + "epoch": 1.199023199023199 + }, + { + "current_steps": 982, + "loss": 2.3755, + "learning_rate": 6.279168434450572e-07, + "epoch": 1.2002442002442002 + }, + { + "current_steps": 983, + "loss": 2.2767, + "learning_rate": 6.274925753075944e-07, + "epoch": 1.2014652014652014 + }, + { + "current_steps": 984, + "loss": 1.9341, + "learning_rate": 6.270683071701315e-07, + "epoch": 1.2026862026862026 + }, + { + "current_steps": 985, + "loss": 2.3872, + "learning_rate": 6.266440390326686e-07, + "epoch": 1.2039072039072038 + }, + { + "current_steps": 986, + "loss": 2.3304, + "learning_rate": 6.262197708952057e-07, + "epoch": 1.205128205128205 + }, + { + "current_steps": 987, + "loss": 2.3067, + "learning_rate": 6.257955027577429e-07, + "epoch": 1.2063492063492063 + }, + { + "current_steps": 988, + "loss": 2.4509, + "learning_rate": 6.253712346202799e-07, + "epoch": 1.2075702075702075 + }, + { + "current_steps": 989, + "loss": 2.2872, + "learning_rate": 6.249469664828171e-07, + "epoch": 1.2087912087912087 + }, + { + "current_steps": 990, + "loss": 2.296, + "learning_rate": 6.245226983453542e-07, + "epoch": 1.21001221001221 + }, + { + "current_steps": 991, + "loss": 2.3837, + "learning_rate": 6.240984302078913e-07, + "epoch": 1.2112332112332111 + }, + { + "current_steps": 992, + "loss": 2.2629, + "learning_rate": 6.236741620704285e-07, + "epoch": 1.2124542124542124 + }, + { + "current_steps": 993, + "loss": 2.2935, + "learning_rate": 6.232498939329656e-07, + "epoch": 1.2136752136752136 + }, + { + "current_steps": 994, + "loss": 2.3774, + "learning_rate": 6.228256257955027e-07, + "epoch": 1.214896214896215 + }, + { + "current_steps": 995, + "loss": 2.267, + "learning_rate": 6.224013576580398e-07, + "epoch": 1.2161172161172162 + }, + { + "current_steps": 996, + "loss": 2.4649, + "learning_rate": 6.21977089520577e-07, + "epoch": 1.2173382173382175 + }, + { + "current_steps": 997, + "loss": 2.1404, + "learning_rate": 6.21552821383114e-07, + "epoch": 1.2185592185592187 + }, + { + "current_steps": 998, + "loss": 2.4171, + "learning_rate": 6.211285532456513e-07, + "epoch": 1.2197802197802199 + }, + { + "current_steps": 999, + "loss": 2.4202, + "learning_rate": 6.207042851081884e-07, + "epoch": 1.221001221001221 + }, + { + "current_steps": 1000, + "loss": 2.1619, + "learning_rate": 6.202800169707255e-07, + "epoch": 1.2222222222222223 + }, + { + "current_steps": 1001, + "loss": 2.4177, + "learning_rate": 6.198557488332626e-07, + "epoch": 1.2234432234432235 + }, + { + "current_steps": 1002, + "loss": 2.3932, + "learning_rate": 6.194314806957998e-07, + "epoch": 1.2246642246642248 + }, + { + "current_steps": 1003, + "loss": 2.4368, + "learning_rate": 6.190072125583368e-07, + "epoch": 1.225885225885226 + }, + { + "current_steps": 1004, + "loss": 2.1866, + "learning_rate": 6.18582944420874e-07, + "epoch": 1.2271062271062272 + }, + { + "current_steps": 1005, + "loss": 2.4951, + "learning_rate": 6.181586762834111e-07, + "epoch": 1.2283272283272284 + }, + { + "current_steps": 1006, + "loss": 2.3437, + "learning_rate": 6.177344081459482e-07, + "epoch": 1.2295482295482296 + }, + { + "current_steps": 1007, + "loss": 2.309, + "learning_rate": 6.173101400084854e-07, + "epoch": 1.2307692307692308 + }, + { + "current_steps": 1008, + "loss": 2.3808, + "learning_rate": 6.168858718710225e-07, + "epoch": 1.231990231990232 + }, + { + "current_steps": 1009, + "loss": 2.3988, + "learning_rate": 6.164616037335596e-07, + "epoch": 1.2332112332112333 + }, + { + "current_steps": 1010, + "loss": 2.3819, + "learning_rate": 6.160373355960967e-07, + "epoch": 1.2344322344322345 + }, + { + "current_steps": 1011, + "loss": 2.2984, + "learning_rate": 6.156130674586339e-07, + "epoch": 1.2356532356532357 + }, + { + "current_steps": 1012, + "loss": 2.4364, + "learning_rate": 6.151887993211709e-07, + "epoch": 1.236874236874237 + }, + { + "current_steps": 1013, + "loss": 2.4017, + "learning_rate": 6.147645311837081e-07, + "epoch": 1.2380952380952381 + }, + { + "current_steps": 1014, + "loss": 2.3771, + "learning_rate": 6.143402630462452e-07, + "epoch": 1.2393162393162394 + }, + { + "current_steps": 1015, + "loss": 2.4161, + "learning_rate": 6.139159949087823e-07, + "epoch": 1.2405372405372406 + }, + { + "current_steps": 1016, + "loss": 2.2083, + "learning_rate": 6.134917267713194e-07, + "epoch": 1.2417582417582418 + }, + { + "current_steps": 1017, + "loss": 2.2831, + "learning_rate": 6.130674586338566e-07, + "epoch": 1.242979242979243 + }, + { + "current_steps": 1018, + "loss": 2.5344, + "learning_rate": 6.126431904963936e-07, + "epoch": 1.2442002442002442 + }, + { + "current_steps": 1019, + "loss": 2.3556, + "learning_rate": 6.122189223589308e-07, + "epoch": 1.2454212454212454 + }, + { + "current_steps": 1020, + "loss": 2.3422, + "learning_rate": 6.117946542214679e-07, + "epoch": 1.2466422466422467 + }, + { + "current_steps": 1021, + "loss": 2.1928, + "learning_rate": 6.11370386084005e-07, + "epoch": 1.2478632478632479 + }, + { + "current_steps": 1022, + "loss": 2.5092, + "learning_rate": 6.109461179465421e-07, + "epoch": 1.249084249084249 + }, + { + "current_steps": 1023, + "loss": 2.0862, + "learning_rate": 6.105218498090793e-07, + "epoch": 1.2503052503052503 + }, + { + "current_steps": 1024, + "loss": 2.199, + "learning_rate": 6.100975816716165e-07, + "epoch": 1.2515262515262515 + }, + { + "current_steps": 1025, + "loss": 2.3379, + "learning_rate": 6.096733135341535e-07, + "epoch": 1.2527472527472527 + }, + { + "current_steps": 1026, + "loss": 2.3512, + "learning_rate": 6.092490453966907e-07, + "epoch": 1.253968253968254 + }, + { + "current_steps": 1027, + "loss": 2.554, + "learning_rate": 6.088247772592277e-07, + "epoch": 1.2551892551892552 + }, + { + "current_steps": 1028, + "loss": 2.4017, + "learning_rate": 6.084005091217649e-07, + "epoch": 1.2564102564102564 + }, + { + "current_steps": 1029, + "loss": 2.5787, + "learning_rate": 6.07976240984302e-07, + "epoch": 1.2576312576312576 + }, + { + "current_steps": 1030, + "loss": 2.2813, + "learning_rate": 6.075519728468392e-07, + "epoch": 1.2588522588522588 + }, + { + "current_steps": 1031, + "loss": 2.5086, + "learning_rate": 6.071277047093763e-07, + "epoch": 1.26007326007326 + }, + { + "current_steps": 1032, + "loss": 2.3218, + "learning_rate": 6.067034365719135e-07, + "epoch": 1.2612942612942613 + }, + { + "current_steps": 1033, + "loss": 2.3019, + "learning_rate": 6.062791684344506e-07, + "epoch": 1.2625152625152625 + }, + { + "current_steps": 1034, + "loss": 2.1154, + "learning_rate": 6.058549002969877e-07, + "epoch": 1.2637362637362637 + }, + { + "current_steps": 1035, + "loss": 2.3384, + "learning_rate": 6.054306321595248e-07, + "epoch": 1.264957264957265 + }, + { + "current_steps": 1036, + "loss": 2.2845, + "learning_rate": 6.05006364022062e-07, + "epoch": 1.2661782661782661 + }, + { + "current_steps": 1037, + "loss": 2.4585, + "learning_rate": 6.04582095884599e-07, + "epoch": 1.2673992673992673 + }, + { + "current_steps": 1038, + "loss": 2.385, + "learning_rate": 6.041578277471362e-07, + "epoch": 1.2686202686202686 + }, + { + "current_steps": 1039, + "loss": 2.1363, + "learning_rate": 6.037335596096734e-07, + "epoch": 1.2698412698412698 + }, + { + "current_steps": 1040, + "loss": 2.2496, + "learning_rate": 6.033092914722104e-07, + "epoch": 1.271062271062271 + }, + { + "current_steps": 1041, + "loss": 2.6687, + "learning_rate": 6.028850233347476e-07, + "epoch": 1.2722832722832722 + }, + { + "current_steps": 1042, + "loss": 2.3106, + "learning_rate": 6.024607551972847e-07, + "epoch": 1.2735042735042734 + }, + { + "current_steps": 1043, + "loss": 2.1892, + "learning_rate": 6.020364870598218e-07, + "epoch": 1.2747252747252746 + }, + { + "current_steps": 1044, + "loss": 2.3665, + "learning_rate": 6.016122189223589e-07, + "epoch": 1.2759462759462759 + }, + { + "current_steps": 1045, + "loss": 2.2207, + "learning_rate": 6.011879507848961e-07, + "epoch": 1.277167277167277 + }, + { + "current_steps": 1046, + "loss": 2.2602, + "learning_rate": 6.007636826474331e-07, + "epoch": 1.2783882783882783 + }, + { + "current_steps": 1047, + "loss": 2.4087, + "learning_rate": 6.003394145099703e-07, + "epoch": 1.2796092796092795 + }, + { + "current_steps": 1048, + "loss": 2.1604, + "learning_rate": 5.999151463725074e-07, + "epoch": 1.2808302808302807 + }, + { + "current_steps": 1049, + "loss": 2.6119, + "learning_rate": 5.994908782350445e-07, + "epoch": 1.282051282051282 + }, + { + "current_steps": 1050, + "loss": 2.3627, + "learning_rate": 5.990666100975816e-07, + "epoch": 1.2832722832722832 + }, + { + "current_steps": 1051, + "loss": 2.1751, + "learning_rate": 5.986423419601188e-07, + "epoch": 1.2844932844932844 + }, + { + "current_steps": 1052, + "loss": 2.4803, + "learning_rate": 5.982180738226558e-07, + "epoch": 1.2857142857142856 + }, + { + "current_steps": 1053, + "loss": 2.3988, + "learning_rate": 5.97793805685193e-07, + "epoch": 1.2869352869352868 + }, + { + "current_steps": 1054, + "loss": 2.0773, + "learning_rate": 5.973695375477301e-07, + "epoch": 1.288156288156288 + }, + { + "current_steps": 1055, + "loss": 2.3533, + "learning_rate": 5.969452694102672e-07, + "epoch": 1.2893772893772895 + }, + { + "current_steps": 1056, + "loss": 2.3411, + "learning_rate": 5.965210012728044e-07, + "epoch": 1.2905982905982907 + }, + { + "current_steps": 1057, + "loss": 2.2694, + "learning_rate": 5.960967331353415e-07, + "epoch": 1.291819291819292 + }, + { + "current_steps": 1058, + "loss": 2.3889, + "learning_rate": 5.956724649978786e-07, + "epoch": 1.293040293040293 + }, + { + "current_steps": 1059, + "loss": 2.3612, + "learning_rate": 5.952481968604157e-07, + "epoch": 1.2942612942612943 + }, + { + "current_steps": 1060, + "loss": 2.3355, + "learning_rate": 5.948239287229529e-07, + "epoch": 1.2954822954822955 + }, + { + "current_steps": 1061, + "loss": 2.3553, + "learning_rate": 5.943996605854899e-07, + "epoch": 1.2967032967032968 + }, + { + "current_steps": 1062, + "loss": 2.4379, + "learning_rate": 5.939753924480271e-07, + "epoch": 1.297924297924298 + }, + { + "current_steps": 1063, + "loss": 2.3082, + "learning_rate": 5.935511243105642e-07, + "epoch": 1.2991452991452992 + }, + { + "current_steps": 1064, + "loss": 2.3373, + "learning_rate": 5.931268561731013e-07, + "epoch": 1.3003663003663004 + }, + { + "current_steps": 1065, + "loss": 2.4168, + "learning_rate": 5.927025880356385e-07, + "epoch": 1.3015873015873016 + }, + { + "current_steps": 1066, + "loss": 2.4598, + "learning_rate": 5.922783198981757e-07, + "epoch": 1.3028083028083028 + }, + { + "current_steps": 1067, + "loss": 2.2486, + "learning_rate": 5.918540517607127e-07, + "epoch": 1.304029304029304 + }, + { + "current_steps": 1068, + "loss": 2.4343, + "learning_rate": 5.914297836232499e-07, + "epoch": 1.3052503052503053 + }, + { + "current_steps": 1069, + "loss": 2.406, + "learning_rate": 5.91005515485787e-07, + "epoch": 1.3064713064713065 + }, + { + "current_steps": 1070, + "loss": 1.8697, + "learning_rate": 5.905812473483242e-07, + "epoch": 1.3076923076923077 + }, + { + "current_steps": 1071, + "loss": 2.3409, + "learning_rate": 5.901569792108613e-07, + "epoch": 1.308913308913309 + }, + { + "current_steps": 1072, + "loss": 2.4596, + "learning_rate": 5.897327110733984e-07, + "epoch": 1.3101343101343101 + }, + { + "current_steps": 1073, + "loss": 1.9979, + "learning_rate": 5.893084429359356e-07, + "epoch": 1.3113553113553114 + }, + { + "current_steps": 1074, + "loss": 2.2979, + "learning_rate": 5.888841747984726e-07, + "epoch": 1.3125763125763126 + }, + { + "current_steps": 1075, + "loss": 2.5241, + "learning_rate": 5.884599066610098e-07, + "epoch": 1.3137973137973138 + }, + { + "current_steps": 1076, + "loss": 2.4261, + "learning_rate": 5.880356385235469e-07, + "epoch": 1.315018315018315 + }, + { + "current_steps": 1077, + "loss": 2.5508, + "learning_rate": 5.87611370386084e-07, + "epoch": 1.3162393162393162 + }, + { + "current_steps": 1078, + "loss": 1.8118, + "learning_rate": 5.871871022486211e-07, + "epoch": 1.3174603174603174 + }, + { + "current_steps": 1079, + "loss": 2.2504, + "learning_rate": 5.867628341111583e-07, + "epoch": 1.3186813186813187 + }, + { + "current_steps": 1080, + "loss": 2.285, + "learning_rate": 5.863385659736953e-07, + "epoch": 1.3199023199023199 + }, + { + "current_steps": 1081, + "loss": 2.4024, + "learning_rate": 5.859142978362325e-07, + "epoch": 1.321123321123321 + }, + { + "current_steps": 1082, + "loss": 1.9697, + "learning_rate": 5.854900296987696e-07, + "epoch": 1.3223443223443223 + }, + { + "current_steps": 1083, + "loss": 2.4245, + "learning_rate": 5.850657615613067e-07, + "epoch": 1.3235653235653235 + }, + { + "current_steps": 1084, + "loss": 2.3426, + "learning_rate": 5.846414934238438e-07, + "epoch": 1.3247863247863247 + }, + { + "current_steps": 1085, + "loss": 2.3959, + "learning_rate": 5.84217225286381e-07, + "epoch": 1.326007326007326 + }, + { + "current_steps": 1086, + "loss": 2.4389, + "learning_rate": 5.837929571489181e-07, + "epoch": 1.3272283272283272 + }, + { + "current_steps": 1087, + "loss": 2.2394, + "learning_rate": 5.833686890114552e-07, + "epoch": 1.3284493284493284 + }, + { + "current_steps": 1088, + "loss": 2.4896, + "learning_rate": 5.829444208739924e-07, + "epoch": 1.3296703296703296 + }, + { + "current_steps": 1089, + "loss": 2.3645, + "learning_rate": 5.825201527365294e-07, + "epoch": 1.3308913308913308 + }, + { + "current_steps": 1090, + "loss": 2.3741, + "learning_rate": 5.820958845990666e-07, + "epoch": 1.332112332112332 + }, + { + "current_steps": 1091, + "loss": 2.3735, + "learning_rate": 5.816716164616037e-07, + "epoch": 1.3333333333333333 + }, + { + "current_steps": 1092, + "loss": 1.7982, + "learning_rate": 5.812473483241408e-07, + "epoch": 1.3345543345543345 + }, + { + "current_steps": 1093, + "loss": 2.3424, + "learning_rate": 5.808230801866779e-07, + "epoch": 1.3357753357753357 + }, + { + "current_steps": 1094, + "loss": 2.2928, + "learning_rate": 5.803988120492151e-07, + "epoch": 1.3369963369963371 + }, + { + "current_steps": 1095, + "loss": 2.5254, + "learning_rate": 5.799745439117521e-07, + "epoch": 1.3382173382173383 + }, + { + "current_steps": 1096, + "loss": 2.4458, + "learning_rate": 5.795502757742893e-07, + "epoch": 1.3394383394383396 + }, + { + "current_steps": 1097, + "loss": 2.3754, + "learning_rate": 5.791260076368264e-07, + "epoch": 1.3406593406593408 + }, + { + "current_steps": 1098, + "loss": 2.3338, + "learning_rate": 5.787017394993635e-07, + "epoch": 1.341880341880342 + }, + { + "current_steps": 1099, + "loss": 2.4025, + "learning_rate": 5.782774713619007e-07, + "epoch": 1.3431013431013432 + }, + { + "current_steps": 1100, + "loss": 2.4237, + "learning_rate": 5.778532032244379e-07, + "epoch": 1.3443223443223444 + }, + { + "current_steps": 1101, + "loss": 2.356, + "learning_rate": 5.77428935086975e-07, + "epoch": 1.3455433455433456 + }, + { + "current_steps": 1102, + "loss": 2.3457, + "learning_rate": 5.770046669495121e-07, + "epoch": 1.3467643467643469 + }, + { + "current_steps": 1103, + "loss": 2.3566, + "learning_rate": 5.765803988120493e-07, + "epoch": 1.347985347985348 + }, + { + "current_steps": 1104, + "loss": 2.279, + "learning_rate": 5.761561306745863e-07, + "epoch": 1.3492063492063493 + }, + { + "current_steps": 1105, + "loss": 2.3023, + "learning_rate": 5.757318625371235e-07, + "epoch": 1.3504273504273505 + }, + { + "current_steps": 1106, + "loss": 2.3654, + "learning_rate": 5.753075943996606e-07, + "epoch": 1.3516483516483517 + }, + { + "current_steps": 1107, + "loss": 2.2029, + "learning_rate": 5.748833262621977e-07, + "epoch": 1.352869352869353 + }, + { + "current_steps": 1108, + "loss": 2.3096, + "learning_rate": 5.744590581247348e-07, + "epoch": 1.3540903540903542 + }, + { + "current_steps": 1109, + "loss": 2.2822, + "learning_rate": 5.74034789987272e-07, + "epoch": 1.3553113553113554 + }, + { + "current_steps": 1110, + "loss": 2.4201, + "learning_rate": 5.73610521849809e-07, + "epoch": 1.3565323565323566 + }, + { + "current_steps": 1111, + "loss": 2.1705, + "learning_rate": 5.731862537123462e-07, + "epoch": 1.3577533577533578 + }, + { + "current_steps": 1112, + "loss": 2.3547, + "learning_rate": 5.727619855748833e-07, + "epoch": 1.358974358974359 + }, + { + "current_steps": 1113, + "loss": 2.0061, + "learning_rate": 5.723377174374204e-07, + "epoch": 1.3601953601953602 + }, + { + "current_steps": 1114, + "loss": 1.7312, + "learning_rate": 5.719134492999575e-07, + "epoch": 1.3614163614163615 + }, + { + "current_steps": 1115, + "loss": 2.452, + "learning_rate": 5.714891811624947e-07, + "epoch": 1.3626373626373627 + }, + { + "current_steps": 1116, + "loss": 2.3437, + "learning_rate": 5.710649130250317e-07, + "epoch": 1.363858363858364 + }, + { + "current_steps": 1117, + "loss": 2.4215, + "learning_rate": 5.706406448875689e-07, + "epoch": 1.3650793650793651 + }, + { + "current_steps": 1118, + "loss": 2.3536, + "learning_rate": 5.702163767501061e-07, + "epoch": 1.3663003663003663 + }, + { + "current_steps": 1119, + "loss": 2.1432, + "learning_rate": 5.697921086126431e-07, + "epoch": 1.3675213675213675 + }, + { + "current_steps": 1120, + "loss": 2.3019, + "learning_rate": 5.693678404751803e-07, + "epoch": 1.3687423687423688 + }, + { + "current_steps": 1121, + "loss": 2.3147, + "learning_rate": 5.689435723377174e-07, + "epoch": 1.36996336996337 + }, + { + "current_steps": 1122, + "loss": 2.5096, + "learning_rate": 5.685193042002546e-07, + "epoch": 1.3711843711843712 + }, + { + "current_steps": 1123, + "loss": 2.3093, + "learning_rate": 5.680950360627916e-07, + "epoch": 1.3724053724053724 + }, + { + "current_steps": 1124, + "loss": 2.3114, + "learning_rate": 5.676707679253288e-07, + "epoch": 1.3736263736263736 + }, + { + "current_steps": 1125, + "loss": 2.486, + "learning_rate": 5.672464997878658e-07, + "epoch": 1.3748473748473748 + }, + { + "current_steps": 1126, + "loss": 2.3469, + "learning_rate": 5.66822231650403e-07, + "epoch": 1.376068376068376 + }, + { + "current_steps": 1127, + "loss": 2.3604, + "learning_rate": 5.663979635129401e-07, + "epoch": 1.3772893772893773 + }, + { + "current_steps": 1128, + "loss": 2.269, + "learning_rate": 5.659736953754773e-07, + "epoch": 1.3785103785103785 + }, + { + "current_steps": 1129, + "loss": 2.0699, + "learning_rate": 5.655494272380143e-07, + "epoch": 1.3797313797313797 + }, + { + "current_steps": 1130, + "loss": 2.3382, + "learning_rate": 5.651251591005515e-07, + "epoch": 1.380952380952381 + }, + { + "current_steps": 1131, + "loss": 2.2554, + "learning_rate": 5.647008909630886e-07, + "epoch": 1.3821733821733821 + }, + { + "current_steps": 1132, + "loss": 2.4759, + "learning_rate": 5.642766228256258e-07, + "epoch": 1.3833943833943834 + }, + { + "current_steps": 1133, + "loss": 2.1913, + "learning_rate": 5.63852354688163e-07, + "epoch": 1.3846153846153846 + }, + { + "current_steps": 1134, + "loss": 2.3889, + "learning_rate": 5.634280865507001e-07, + "epoch": 1.3858363858363858 + }, + { + "current_steps": 1135, + "loss": 1.9016, + "learning_rate": 5.630038184132372e-07, + "epoch": 1.387057387057387 + }, + { + "current_steps": 1136, + "loss": 2.3995, + "learning_rate": 5.625795502757743e-07, + "epoch": 1.3882783882783882 + }, + { + "current_steps": 1137, + "loss": 2.4037, + "learning_rate": 5.621552821383115e-07, + "epoch": 1.3894993894993894 + }, + { + "current_steps": 1138, + "loss": 2.2118, + "learning_rate": 5.617310140008485e-07, + "epoch": 1.3907203907203907 + }, + { + "current_steps": 1139, + "loss": 2.3686, + "learning_rate": 5.613067458633857e-07, + "epoch": 1.3919413919413919 + }, + { + "current_steps": 1140, + "loss": 2.3193, + "learning_rate": 5.608824777259228e-07, + "epoch": 1.393162393162393 + }, + { + "current_steps": 1141, + "loss": 2.0834, + "learning_rate": 5.604582095884599e-07, + "epoch": 1.3943833943833943 + }, + { + "current_steps": 1142, + "loss": 2.4315, + "learning_rate": 5.60033941450997e-07, + "epoch": 1.3956043956043955 + }, + { + "current_steps": 1143, + "loss": 2.4638, + "learning_rate": 5.596096733135342e-07, + "epoch": 1.3968253968253967 + }, + { + "current_steps": 1144, + "loss": 2.4064, + "learning_rate": 5.591854051760712e-07, + "epoch": 1.398046398046398 + }, + { + "current_steps": 1145, + "loss": 2.4083, + "learning_rate": 5.587611370386084e-07, + "epoch": 1.3992673992673992 + }, + { + "current_steps": 1146, + "loss": 2.3466, + "learning_rate": 5.583368689011455e-07, + "epoch": 1.4004884004884004 + }, + { + "current_steps": 1147, + "loss": 2.3991, + "learning_rate": 5.579126007636826e-07, + "epoch": 1.4017094017094016 + }, + { + "current_steps": 1148, + "loss": 2.4057, + "learning_rate": 5.574883326262197e-07, + "epoch": 1.4029304029304028 + }, + { + "current_steps": 1149, + "loss": 2.4811, + "learning_rate": 5.570640644887569e-07, + "epoch": 1.404151404151404 + }, + { + "current_steps": 1150, + "loss": 2.5803, + "learning_rate": 5.56639796351294e-07, + "epoch": 1.4053724053724053 + }, + { + "current_steps": 1151, + "loss": 2.4254, + "learning_rate": 5.562155282138311e-07, + "epoch": 1.4065934065934065 + }, + { + "current_steps": 1152, + "loss": 2.5078, + "learning_rate": 5.557912600763683e-07, + "epoch": 1.4078144078144077 + }, + { + "current_steps": 1153, + "loss": 2.3224, + "learning_rate": 5.553669919389053e-07, + "epoch": 1.409035409035409 + }, + { + "current_steps": 1154, + "loss": 2.3232, + "learning_rate": 5.549427238014425e-07, + "epoch": 1.4102564102564101 + }, + { + "current_steps": 1155, + "loss": 2.3381, + "learning_rate": 5.545184556639796e-07, + "epoch": 1.4114774114774113 + }, + { + "current_steps": 1156, + "loss": 2.1894, + "learning_rate": 5.540941875265167e-07, + "epoch": 1.4126984126984126 + }, + { + "current_steps": 1157, + "loss": 2.2158, + "learning_rate": 5.536699193890538e-07, + "epoch": 1.4139194139194138 + }, + { + "current_steps": 1158, + "loss": 1.8241, + "learning_rate": 5.53245651251591e-07, + "epoch": 1.4151404151404152 + }, + { + "current_steps": 1159, + "loss": 2.2863, + "learning_rate": 5.52821383114128e-07, + "epoch": 1.4163614163614164 + }, + { + "current_steps": 1160, + "loss": 2.265, + "learning_rate": 5.523971149766652e-07, + "epoch": 1.4175824175824177 + }, + { + "current_steps": 1161, + "loss": 2.4503, + "learning_rate": 5.519728468392023e-07, + "epoch": 1.4188034188034189 + }, + { + "current_steps": 1162, + "loss": 2.4836, + "learning_rate": 5.515485787017394e-07, + "epoch": 1.42002442002442 + }, + { + "current_steps": 1163, + "loss": 2.3282, + "learning_rate": 5.511243105642765e-07, + "epoch": 1.4212454212454213 + }, + { + "current_steps": 1164, + "loss": 2.424, + "learning_rate": 5.507000424268137e-07, + "epoch": 1.4224664224664225 + }, + { + "current_steps": 1165, + "loss": 2.3049, + "learning_rate": 5.502757742893507e-07, + "epoch": 1.4236874236874237 + }, + { + "current_steps": 1166, + "loss": 2.2151, + "learning_rate": 5.49851506151888e-07, + "epoch": 1.424908424908425 + }, + { + "current_steps": 1167, + "loss": 2.3033, + "learning_rate": 5.494272380144252e-07, + "epoch": 1.4261294261294262 + }, + { + "current_steps": 1168, + "loss": 1.791, + "learning_rate": 5.490029698769623e-07, + "epoch": 1.4273504273504274 + }, + { + "current_steps": 1169, + "loss": 2.457, + "learning_rate": 5.485787017394994e-07, + "epoch": 1.4285714285714286 + }, + { + "current_steps": 1170, + "loss": 2.3169, + "learning_rate": 5.481544336020365e-07, + "epoch": 1.4297924297924298 + }, + { + "current_steps": 1171, + "loss": 2.3418, + "learning_rate": 5.477301654645737e-07, + "epoch": 1.431013431013431 + }, + { + "current_steps": 1172, + "loss": 2.5166, + "learning_rate": 5.473058973271107e-07, + "epoch": 1.4322344322344323 + }, + { + "current_steps": 1173, + "loss": 2.3905, + "learning_rate": 5.468816291896479e-07, + "epoch": 1.4334554334554335 + }, + { + "current_steps": 1174, + "loss": 2.4669, + "learning_rate": 5.46457361052185e-07, + "epoch": 1.4346764346764347 + }, + { + "current_steps": 1175, + "loss": 2.3464, + "learning_rate": 5.460330929147221e-07, + "epoch": 1.435897435897436 + }, + { + "current_steps": 1176, + "loss": 2.2919, + "learning_rate": 5.456088247772592e-07, + "epoch": 1.4371184371184371 + }, + { + "current_steps": 1177, + "loss": 2.232, + "learning_rate": 5.451845566397964e-07, + "epoch": 1.4383394383394383 + }, + { + "current_steps": 1178, + "loss": 2.2682, + "learning_rate": 5.447602885023334e-07, + "epoch": 1.4395604395604396 + }, + { + "current_steps": 1179, + "loss": 2.3147, + "learning_rate": 5.443360203648706e-07, + "epoch": 1.4407814407814408 + }, + { + "current_steps": 1180, + "loss": 2.3931, + "learning_rate": 5.439117522274077e-07, + "epoch": 1.442002442002442 + }, + { + "current_steps": 1181, + "loss": 2.4165, + "learning_rate": 5.434874840899448e-07, + "epoch": 1.4432234432234432 + }, + { + "current_steps": 1182, + "loss": 2.0831, + "learning_rate": 5.43063215952482e-07, + "epoch": 1.4444444444444444 + }, + { + "current_steps": 1183, + "loss": 2.2765, + "learning_rate": 5.426389478150191e-07, + "epoch": 1.4456654456654456 + }, + { + "current_steps": 1184, + "loss": 2.4668, + "learning_rate": 5.422146796775562e-07, + "epoch": 1.4468864468864469 + }, + { + "current_steps": 1185, + "loss": 2.2415, + "learning_rate": 5.417904115400933e-07, + "epoch": 1.448107448107448 + }, + { + "current_steps": 1186, + "loss": 2.2553, + "learning_rate": 5.413661434026305e-07, + "epoch": 1.4493284493284493 + }, + { + "current_steps": 1187, + "loss": 2.3801, + "learning_rate": 5.409418752651675e-07, + "epoch": 1.4505494505494505 + }, + { + "current_steps": 1188, + "loss": 2.3949, + "learning_rate": 5.405176071277047e-07, + "epoch": 1.4517704517704517 + }, + { + "current_steps": 1189, + "loss": 2.3772, + "learning_rate": 5.400933389902418e-07, + "epoch": 1.452991452991453 + }, + { + "current_steps": 1190, + "loss": 2.3463, + "learning_rate": 5.396690708527789e-07, + "epoch": 1.4542124542124542 + }, + { + "current_steps": 1191, + "loss": 2.4259, + "learning_rate": 5.39244802715316e-07, + "epoch": 1.4554334554334554 + }, + { + "current_steps": 1192, + "loss": 2.2588, + "learning_rate": 5.388205345778532e-07, + "epoch": 1.4566544566544566 + }, + { + "current_steps": 1193, + "loss": 2.3457, + "learning_rate": 5.383962664403902e-07, + "epoch": 1.4578754578754578 + }, + { + "current_steps": 1194, + "loss": 2.4887, + "learning_rate": 5.379719983029274e-07, + "epoch": 1.459096459096459 + }, + { + "current_steps": 1195, + "loss": 2.4925, + "learning_rate": 5.375477301654645e-07, + "epoch": 1.4603174603174602 + }, + { + "current_steps": 1196, + "loss": 2.2501, + "learning_rate": 5.371234620280016e-07, + "epoch": 1.4615384615384617 + }, + { + "current_steps": 1197, + "loss": 2.3915, + "learning_rate": 5.366991938905387e-07, + "epoch": 1.462759462759463 + }, + { + "current_steps": 1198, + "loss": 2.3213, + "learning_rate": 5.362749257530759e-07, + "epoch": 1.463980463980464 + }, + { + "current_steps": 1199, + "loss": 2.2002, + "learning_rate": 5.35850657615613e-07, + "epoch": 1.4652014652014653 + }, + { + "current_steps": 1200, + "loss": 2.3616, + "learning_rate": 5.354263894781502e-07, + "epoch": 1.4664224664224665 + }, + { + "current_steps": 1201, + "loss": 2.4152, + "learning_rate": 5.350021213406874e-07, + "epoch": 1.4676434676434678 + }, + { + "current_steps": 1202, + "loss": 2.374, + "learning_rate": 5.345778532032244e-07, + "epoch": 1.468864468864469 + }, + { + "current_steps": 1203, + "loss": 2.3815, + "learning_rate": 5.341535850657616e-07, + "epoch": 1.4700854700854702 + }, + { + "current_steps": 1204, + "loss": 2.2055, + "learning_rate": 5.337293169282987e-07, + "epoch": 1.4713064713064714 + }, + { + "current_steps": 1205, + "loss": 2.4198, + "learning_rate": 5.333050487908358e-07, + "epoch": 1.4725274725274726 + }, + { + "current_steps": 1206, + "loss": 2.3979, + "learning_rate": 5.328807806533729e-07, + "epoch": 1.4737484737484738 + }, + { + "current_steps": 1207, + "loss": 2.1756, + "learning_rate": 5.324565125159101e-07, + "epoch": 1.474969474969475 + }, + { + "current_steps": 1208, + "loss": 2.3783, + "learning_rate": 5.320322443784471e-07, + "epoch": 1.4761904761904763 + }, + { + "current_steps": 1209, + "loss": 2.5376, + "learning_rate": 5.316079762409843e-07, + "epoch": 1.4774114774114775 + }, + { + "current_steps": 1210, + "loss": 2.2331, + "learning_rate": 5.311837081035214e-07, + "epoch": 1.4786324786324787 + }, + { + "current_steps": 1211, + "loss": 2.3546, + "learning_rate": 5.307594399660585e-07, + "epoch": 1.47985347985348 + }, + { + "current_steps": 1212, + "loss": 2.2619, + "learning_rate": 5.303351718285956e-07, + "epoch": 1.4810744810744811 + }, + { + "current_steps": 1213, + "loss": 2.423, + "learning_rate": 5.299109036911328e-07, + "epoch": 1.4822954822954824 + }, + { + "current_steps": 1214, + "loss": 2.2535, + "learning_rate": 5.2948663555367e-07, + "epoch": 1.4835164835164836 + }, + { + "current_steps": 1215, + "loss": 2.2836, + "learning_rate": 5.29062367416207e-07, + "epoch": 1.4847374847374848 + }, + { + "current_steps": 1216, + "loss": 2.3586, + "learning_rate": 5.286380992787442e-07, + "epoch": 1.485958485958486 + }, + { + "current_steps": 1217, + "loss": 2.223, + "learning_rate": 5.282138311412812e-07, + "epoch": 1.4871794871794872 + }, + { + "current_steps": 1218, + "loss": 2.4393, + "learning_rate": 5.277895630038184e-07, + "epoch": 1.4884004884004884 + }, + { + "current_steps": 1219, + "loss": 2.3022, + "learning_rate": 5.273652948663555e-07, + "epoch": 1.4896214896214897 + }, + { + "current_steps": 1220, + "loss": 2.7348, + "learning_rate": 5.269410267288927e-07, + "epoch": 1.4908424908424909 + }, + { + "current_steps": 1221, + "loss": 1.2383, + "learning_rate": 5.265167585914297e-07, + "epoch": 1.492063492063492 + }, + { + "current_steps": 1222, + "loss": 2.4003, + "learning_rate": 5.260924904539669e-07, + "epoch": 1.4932844932844933 + }, + { + "current_steps": 1223, + "loss": 2.3748, + "learning_rate": 5.25668222316504e-07, + "epoch": 1.4945054945054945 + }, + { + "current_steps": 1224, + "loss": 2.4903, + "learning_rate": 5.252439541790411e-07, + "epoch": 1.4957264957264957 + }, + { + "current_steps": 1225, + "loss": 2.3928, + "learning_rate": 5.248196860415782e-07, + "epoch": 1.496947496947497 + }, + { + "current_steps": 1226, + "loss": 2.2037, + "learning_rate": 5.243954179041154e-07, + "epoch": 1.4981684981684982 + }, + { + "current_steps": 1227, + "loss": 2.0892, + "learning_rate": 5.239711497666524e-07, + "epoch": 1.4993894993894994 + }, + { + "current_steps": 1228, + "loss": 2.5068, + "learning_rate": 5.235468816291896e-07, + "epoch": 1.5006105006105006 + }, + { + "current_steps": 1229, + "loss": 2.4923, + "learning_rate": 5.231226134917268e-07, + "epoch": 1.5018315018315018 + }, + { + "current_steps": 1230, + "loss": 2.3432, + "learning_rate": 5.226983453542638e-07, + "epoch": 1.503052503052503 + }, + { + "current_steps": 1231, + "loss": 2.3196, + "learning_rate": 5.22274077216801e-07, + "epoch": 1.5042735042735043 + }, + { + "current_steps": 1232, + "loss": 2.4548, + "learning_rate": 5.218498090793381e-07, + "epoch": 1.5054945054945055 + }, + { + "current_steps": 1233, + "loss": 2.3036, + "learning_rate": 5.214255409418753e-07, + "epoch": 1.5067155067155067 + }, + { + "current_steps": 1234, + "loss": 2.4414, + "learning_rate": 5.210012728044124e-07, + "epoch": 1.507936507936508 + }, + { + "current_steps": 1235, + "loss": 2.1306, + "learning_rate": 5.205770046669496e-07, + "epoch": 1.5091575091575091 + }, + { + "current_steps": 1236, + "loss": 2.4196, + "learning_rate": 5.201527365294866e-07, + "epoch": 1.5103785103785103 + }, + { + "current_steps": 1237, + "loss": 2.4261, + "learning_rate": 5.197284683920238e-07, + "epoch": 1.5115995115995116 + }, + { + "current_steps": 1238, + "loss": 2.2576, + "learning_rate": 5.193042002545609e-07, + "epoch": 1.5128205128205128 + }, + { + "current_steps": 1239, + "loss": 2.4171, + "learning_rate": 5.18879932117098e-07, + "epoch": 1.514041514041514 + }, + { + "current_steps": 1240, + "loss": 2.35, + "learning_rate": 5.184556639796351e-07, + "epoch": 1.5152625152625152 + }, + { + "current_steps": 1241, + "loss": 2.1204, + "learning_rate": 5.180313958421723e-07, + "epoch": 1.5164835164835164 + }, + { + "current_steps": 1242, + "loss": 2.4403, + "learning_rate": 5.176071277047093e-07, + "epoch": 1.5177045177045176 + }, + { + "current_steps": 1243, + "loss": 2.2173, + "learning_rate": 5.171828595672465e-07, + "epoch": 1.5189255189255189 + }, + { + "current_steps": 1244, + "loss": 2.3192, + "learning_rate": 5.167585914297837e-07, + "epoch": 1.52014652014652 + }, + { + "current_steps": 1245, + "loss": 2.2199, + "learning_rate": 5.163343232923207e-07, + "epoch": 1.5213675213675213 + }, + { + "current_steps": 1246, + "loss": 2.2469, + "learning_rate": 5.159100551548579e-07, + "epoch": 1.5225885225885225 + }, + { + "current_steps": 1247, + "loss": 2.2354, + "learning_rate": 5.15485787017395e-07, + "epoch": 1.5238095238095237 + }, + { + "current_steps": 1248, + "loss": 2.4719, + "learning_rate": 5.150615188799321e-07, + "epoch": 1.525030525030525 + }, + { + "current_steps": 1249, + "loss": 2.2277, + "learning_rate": 5.146372507424692e-07, + "epoch": 1.5262515262515262 + }, + { + "current_steps": 1250, + "loss": 2.4243, + "learning_rate": 5.142129826050064e-07, + "epoch": 1.5274725274725274 + }, + { + "current_steps": 1251, + "loss": 2.3544, + "learning_rate": 5.137887144675434e-07, + "epoch": 1.5286935286935286 + }, + { + "current_steps": 1252, + "loss": 2.3254, + "learning_rate": 5.133644463300806e-07, + "epoch": 1.5299145299145298 + }, + { + "current_steps": 1253, + "loss": 2.3963, + "learning_rate": 5.129401781926177e-07, + "epoch": 1.531135531135531 + }, + { + "current_steps": 1254, + "loss": 2.386, + "learning_rate": 5.125159100551548e-07, + "epoch": 1.5323565323565322 + }, + { + "current_steps": 1255, + "loss": 2.3905, + "learning_rate": 5.120916419176919e-07, + "epoch": 1.5335775335775335 + }, + { + "current_steps": 1256, + "loss": 2.3982, + "learning_rate": 5.116673737802291e-07, + "epoch": 1.5347985347985347 + }, + { + "current_steps": 1257, + "loss": 2.371, + "learning_rate": 5.112431056427661e-07, + "epoch": 1.536019536019536 + }, + { + "current_steps": 1258, + "loss": 2.2114, + "learning_rate": 5.108188375053033e-07, + "epoch": 1.537240537240537 + }, + { + "current_steps": 1259, + "loss": 2.241, + "learning_rate": 5.103945693678404e-07, + "epoch": 1.5384615384615383 + }, + { + "current_steps": 1260, + "loss": 1.746, + "learning_rate": 5.099703012303775e-07, + "epoch": 1.5396825396825395 + }, + { + "current_steps": 1261, + "loss": 2.0718, + "learning_rate": 5.095460330929147e-07, + "epoch": 1.5409035409035408 + }, + { + "current_steps": 1262, + "loss": 2.3227, + "learning_rate": 5.091217649554518e-07, + "epoch": 1.542124542124542 + }, + { + "current_steps": 1263, + "loss": 2.3819, + "learning_rate": 5.086974968179889e-07, + "epoch": 1.5433455433455432 + }, + { + "current_steps": 1264, + "loss": 2.5729, + "learning_rate": 5.08273228680526e-07, + "epoch": 1.5445665445665444 + }, + { + "current_steps": 1265, + "loss": 2.5456, + "learning_rate": 5.078489605430632e-07, + "epoch": 1.5457875457875456 + }, + { + "current_steps": 1266, + "loss": 2.4519, + "learning_rate": 5.074246924056002e-07, + "epoch": 1.547008547008547 + }, + { + "current_steps": 1267, + "loss": 2.4303, + "learning_rate": 5.070004242681375e-07, + "epoch": 1.5482295482295483 + }, + { + "current_steps": 1268, + "loss": 2.4514, + "learning_rate": 5.065761561306746e-07, + "epoch": 1.5494505494505495 + }, + { + "current_steps": 1269, + "loss": 2.3713, + "learning_rate": 5.061518879932118e-07, + "epoch": 1.5506715506715507 + }, + { + "current_steps": 1270, + "loss": 2.4012, + "learning_rate": 5.057276198557488e-07, + "epoch": 1.551892551892552 + }, + { + "current_steps": 1271, + "loss": 2.4873, + "learning_rate": 5.05303351718286e-07, + "epoch": 1.5531135531135531 + }, + { + "current_steps": 1272, + "loss": 2.3525, + "learning_rate": 5.04879083580823e-07, + "epoch": 1.5543345543345544 + }, + { + "current_steps": 1273, + "loss": 2.3635, + "learning_rate": 5.044548154433602e-07, + "epoch": 1.5555555555555556 + }, + { + "current_steps": 1274, + "loss": 2.232, + "learning_rate": 5.040305473058973e-07, + "epoch": 1.5567765567765568 + }, + { + "current_steps": 1275, + "loss": 2.1777, + "learning_rate": 5.036062791684345e-07, + "epoch": 1.557997557997558 + }, + { + "current_steps": 1276, + "loss": 2.2609, + "learning_rate": 5.031820110309716e-07, + "epoch": 1.5592185592185592 + }, + { + "current_steps": 1277, + "loss": 2.2729, + "learning_rate": 5.027577428935087e-07, + "epoch": 1.5604395604395604 + }, + { + "current_steps": 1278, + "loss": 2.4496, + "learning_rate": 5.023334747560459e-07, + "epoch": 1.5616605616605617 + }, + { + "current_steps": 1279, + "loss": 2.4806, + "learning_rate": 5.019092066185829e-07, + "epoch": 1.5628815628815629 + }, + { + "current_steps": 1280, + "loss": 2.449, + "learning_rate": 5.014849384811201e-07, + "epoch": 1.564102564102564 + }, + { + "current_steps": 1281, + "loss": 2.2836, + "learning_rate": 5.010606703436572e-07, + "epoch": 1.5653235653235653 + }, + { + "current_steps": 1282, + "loss": 2.1613, + "learning_rate": 5.006364022061943e-07, + "epoch": 1.5665445665445665 + }, + { + "current_steps": 1283, + "loss": 2.2266, + "learning_rate": 5.002121340687314e-07, + "epoch": 1.5677655677655677 + }, + { + "current_steps": 1284, + "loss": 2.1743, + "learning_rate": 4.997878659312686e-07, + "epoch": 1.568986568986569 + }, + { + "current_steps": 1285, + "loss": 2.2913, + "learning_rate": 4.993635977938056e-07, + "epoch": 1.5702075702075702 + }, + { + "current_steps": 1286, + "loss": 2.3055, + "learning_rate": 4.989393296563428e-07, + "epoch": 1.5714285714285714 + }, + { + "current_steps": 1287, + "loss": 2.4059, + "learning_rate": 4.985150615188799e-07, + "epoch": 1.5726495726495726 + }, + { + "current_steps": 1288, + "loss": 2.4615, + "learning_rate": 4.98090793381417e-07, + "epoch": 1.5738705738705738 + }, + { + "current_steps": 1289, + "loss": 2.3735, + "learning_rate": 4.976665252439541e-07, + "epoch": 1.575091575091575 + }, + { + "current_steps": 1290, + "loss": 2.161, + "learning_rate": 4.972422571064913e-07, + "epoch": 1.5763125763125763 + }, + { + "current_steps": 1291, + "loss": 2.265, + "learning_rate": 4.968179889690283e-07, + "epoch": 1.5775335775335775 + }, + { + "current_steps": 1292, + "loss": 2.4331, + "learning_rate": 4.963937208315656e-07, + "epoch": 1.578754578754579 + }, + { + "current_steps": 1293, + "loss": 2.3457, + "learning_rate": 4.959694526941027e-07, + "epoch": 1.5799755799755801 + }, + { + "current_steps": 1294, + "loss": 2.3497, + "learning_rate": 4.955451845566398e-07, + "epoch": 1.5811965811965814 + }, + { + "current_steps": 1295, + "loss": 2.2674, + "learning_rate": 4.951209164191769e-07, + "epoch": 1.5824175824175826 + }, + { + "current_steps": 1296, + "loss": 2.3177, + "learning_rate": 4.946966482817141e-07, + "epoch": 1.5836385836385838 + }, + { + "current_steps": 1297, + "loss": 2.3371, + "learning_rate": 4.942723801442511e-07, + "epoch": 1.584859584859585 + }, + { + "current_steps": 1298, + "loss": 2.2432, + "learning_rate": 4.938481120067883e-07, + "epoch": 1.5860805860805862 + }, + { + "current_steps": 1299, + "loss": 2.4094, + "learning_rate": 4.934238438693254e-07, + "epoch": 1.5873015873015874 + }, + { + "current_steps": 1300, + "loss": 2.1098, + "learning_rate": 4.929995757318625e-07, + "epoch": 1.5885225885225887 + }, + { + "current_steps": 1301, + "loss": 2.4189, + "learning_rate": 4.925753075943996e-07, + "epoch": 1.5897435897435899 + }, + { + "current_steps": 1302, + "loss": 2.2669, + "learning_rate": 4.921510394569368e-07, + "epoch": 1.590964590964591 + }, + { + "current_steps": 1303, + "loss": 1.7863, + "learning_rate": 4.917267713194738e-07, + "epoch": 1.5921855921855923 + }, + { + "current_steps": 1304, + "loss": 2.2036, + "learning_rate": 4.91302503182011e-07, + "epoch": 1.5934065934065935 + }, + { + "current_steps": 1305, + "loss": 1.8346, + "learning_rate": 4.908782350445481e-07, + "epoch": 1.5946275946275947 + }, + { + "current_steps": 1306, + "loss": 2.4428, + "learning_rate": 4.904539669070852e-07, + "epoch": 1.595848595848596 + }, + { + "current_steps": 1307, + "loss": 2.3582, + "learning_rate": 4.900296987696223e-07, + "epoch": 1.5970695970695972 + }, + { + "current_steps": 1308, + "loss": 2.2904, + "learning_rate": 4.896054306321595e-07, + "epoch": 1.5982905982905984 + }, + { + "current_steps": 1309, + "loss": 2.3627, + "learning_rate": 4.891811624946966e-07, + "epoch": 1.5995115995115996 + }, + { + "current_steps": 1310, + "loss": 2.3421, + "learning_rate": 4.887568943572338e-07, + "epoch": 1.6007326007326008 + }, + { + "current_steps": 1311, + "loss": 2.5204, + "learning_rate": 4.883326262197709e-07, + "epoch": 1.601953601953602 + }, + { + "current_steps": 1312, + "loss": 2.3437, + "learning_rate": 4.87908358082308e-07, + "epoch": 1.6031746031746033 + }, + { + "current_steps": 1313, + "loss": 2.311, + "learning_rate": 4.874840899448451e-07, + "epoch": 1.6043956043956045 + }, + { + "current_steps": 1314, + "loss": 2.2271, + "learning_rate": 4.870598218073823e-07, + "epoch": 1.6056166056166057 + }, + { + "current_steps": 1315, + "loss": 2.2846, + "learning_rate": 4.866355536699193e-07, + "epoch": 1.606837606837607 + }, + { + "current_steps": 1316, + "loss": 2.2867, + "learning_rate": 4.862112855324565e-07, + "epoch": 1.6080586080586081 + }, + { + "current_steps": 1317, + "loss": 2.2752, + "learning_rate": 4.857870173949936e-07, + "epoch": 1.6092796092796093 + }, + { + "current_steps": 1318, + "loss": 2.1571, + "learning_rate": 4.853627492575308e-07, + "epoch": 1.6105006105006106 + }, + { + "current_steps": 1319, + "loss": 2.2042, + "learning_rate": 4.849384811200678e-07, + "epoch": 1.6117216117216118 + }, + { + "current_steps": 1320, + "loss": 2.4045, + "learning_rate": 4.84514212982605e-07, + "epoch": 1.612942612942613 + }, + { + "current_steps": 1321, + "loss": 2.3115, + "learning_rate": 4.84089944845142e-07, + "epoch": 1.6141636141636142 + }, + { + "current_steps": 1322, + "loss": 2.2927, + "learning_rate": 4.836656767076792e-07, + "epoch": 1.6153846153846154 + }, + { + "current_steps": 1323, + "loss": 2.2789, + "learning_rate": 4.832414085702163e-07, + "epoch": 1.6166056166056166 + }, + { + "current_steps": 1324, + "loss": 2.3045, + "learning_rate": 4.828171404327535e-07, + "epoch": 1.6178266178266179 + }, + { + "current_steps": 1325, + "loss": 2.429, + "learning_rate": 4.823928722952906e-07, + "epoch": 1.619047619047619 + }, + { + "current_steps": 1326, + "loss": 2.2771, + "learning_rate": 4.819686041578278e-07, + "epoch": 1.6202686202686203 + }, + { + "current_steps": 1327, + "loss": 2.4608, + "learning_rate": 4.815443360203649e-07, + "epoch": 1.6214896214896215 + }, + { + "current_steps": 1328, + "loss": 2.273, + "learning_rate": 4.81120067882902e-07, + "epoch": 1.6227106227106227 + }, + { + "current_steps": 1329, + "loss": 2.323, + "learning_rate": 4.806957997454391e-07, + "epoch": 1.623931623931624 + }, + { + "current_steps": 1330, + "loss": 2.5005, + "learning_rate": 4.802715316079763e-07, + "epoch": 1.6251526251526252 + }, + { + "current_steps": 1331, + "loss": 2.2453, + "learning_rate": 4.798472634705133e-07, + "epoch": 1.6263736263736264 + }, + { + "current_steps": 1332, + "loss": 2.4455, + "learning_rate": 4.794229953330505e-07, + "epoch": 1.6275946275946276 + }, + { + "current_steps": 1333, + "loss": 2.3871, + "learning_rate": 4.789987271955876e-07, + "epoch": 1.6288156288156288 + }, + { + "current_steps": 1334, + "loss": 2.5147, + "learning_rate": 4.785744590581247e-07, + "epoch": 1.63003663003663 + }, + { + "current_steps": 1335, + "loss": 2.4087, + "learning_rate": 4.781501909206618e-07, + "epoch": 1.6312576312576312 + }, + { + "current_steps": 1336, + "loss": 2.5962, + "learning_rate": 4.77725922783199e-07, + "epoch": 1.6324786324786325 + }, + { + "current_steps": 1337, + "loss": 2.6121, + "learning_rate": 4.77301654645736e-07, + "epoch": 1.6336996336996337 + }, + { + "current_steps": 1338, + "loss": 2.6134, + "learning_rate": 4.768773865082732e-07, + "epoch": 1.6349206349206349 + }, + { + "current_steps": 1339, + "loss": 2.4497, + "learning_rate": 4.764531183708103e-07, + "epoch": 1.636141636141636 + }, + { + "current_steps": 1340, + "loss": 2.2746, + "learning_rate": 4.7602885023334743e-07, + "epoch": 1.6373626373626373 + }, + { + "current_steps": 1341, + "loss": 2.4079, + "learning_rate": 4.7560458209588455e-07, + "epoch": 1.6385836385836385 + }, + { + "current_steps": 1342, + "loss": 2.5029, + "learning_rate": 4.7518031395842167e-07, + "epoch": 1.6398046398046398 + }, + { + "current_steps": 1343, + "loss": 2.3218, + "learning_rate": 4.7475604582095884e-07, + "epoch": 1.641025641025641 + }, + { + "current_steps": 1344, + "loss": 2.3609, + "learning_rate": 4.7433177768349595e-07, + "epoch": 1.6422466422466422 + }, + { + "current_steps": 1345, + "loss": 2.3155, + "learning_rate": 4.7390750954603307e-07, + "epoch": 1.6434676434676434 + }, + { + "current_steps": 1346, + "loss": 2.3401, + "learning_rate": 4.734832414085702e-07, + "epoch": 1.6446886446886446 + }, + { + "current_steps": 1347, + "loss": 2.4228, + "learning_rate": 4.7305897327110736e-07, + "epoch": 1.6459096459096458 + }, + { + "current_steps": 1348, + "loss": 2.1993, + "learning_rate": 4.7263470513364447e-07, + "epoch": 1.647130647130647 + }, + { + "current_steps": 1349, + "loss": 2.3047, + "learning_rate": 4.722104369961816e-07, + "epoch": 1.6483516483516483 + }, + { + "current_steps": 1350, + "loss": 2.3545, + "learning_rate": 4.717861688587187e-07, + "epoch": 1.6495726495726495 + }, + { + "current_steps": 1351, + "loss": 2.0477, + "learning_rate": 4.713619007212558e-07, + "epoch": 1.6507936507936507 + }, + { + "current_steps": 1352, + "loss": 2.332, + "learning_rate": 4.7093763258379294e-07, + "epoch": 1.652014652014652 + }, + { + "current_steps": 1353, + "loss": 2.2319, + "learning_rate": 4.7051336444633006e-07, + "epoch": 1.6532356532356531 + }, + { + "current_steps": 1354, + "loss": 2.2527, + "learning_rate": 4.700890963088672e-07, + "epoch": 1.6544566544566544 + }, + { + "current_steps": 1355, + "loss": 2.2515, + "learning_rate": 4.696648281714043e-07, + "epoch": 1.6556776556776556 + }, + { + "current_steps": 1356, + "loss": 2.2685, + "learning_rate": 4.692405600339414e-07, + "epoch": 1.6568986568986568 + }, + { + "current_steps": 1357, + "loss": 2.3754, + "learning_rate": 4.688162918964785e-07, + "epoch": 1.658119658119658 + }, + { + "current_steps": 1358, + "loss": 2.3318, + "learning_rate": 4.6839202375901564e-07, + "epoch": 1.6593406593406592 + }, + { + "current_steps": 1359, + "loss": 2.3226, + "learning_rate": 4.6796775562155276e-07, + "epoch": 1.6605616605616604 + }, + { + "current_steps": 1360, + "loss": 2.3604, + "learning_rate": 4.6754348748408993e-07, + "epoch": 1.6617826617826617 + }, + { + "current_steps": 1361, + "loss": 2.3868, + "learning_rate": 4.6711921934662705e-07, + "epoch": 1.6630036630036629 + }, + { + "current_steps": 1362, + "loss": 1.9365, + "learning_rate": 4.6669495120916416e-07, + "epoch": 1.664224664224664 + }, + { + "current_steps": 1363, + "loss": 2.4014, + "learning_rate": 4.6627068307170133e-07, + "epoch": 1.6654456654456653 + }, + { + "current_steps": 1364, + "loss": 2.3746, + "learning_rate": 4.6584641493423845e-07, + "epoch": 1.6666666666666665 + }, + { + "current_steps": 1365, + "loss": 2.275, + "learning_rate": 4.6542214679677557e-07, + "epoch": 1.6678876678876677 + }, + { + "current_steps": 1366, + "loss": 2.3941, + "learning_rate": 4.649978786593127e-07, + "epoch": 1.669108669108669 + }, + { + "current_steps": 1367, + "loss": 2.5218, + "learning_rate": 4.645736105218498e-07, + "epoch": 1.6703296703296702 + }, + { + "current_steps": 1368, + "loss": 2.184, + "learning_rate": 4.641493423843869e-07, + "epoch": 1.6715506715506714 + }, + { + "current_steps": 1369, + "loss": 2.3016, + "learning_rate": 4.6372507424692404e-07, + "epoch": 1.6727716727716728 + }, + { + "current_steps": 1370, + "loss": 2.236, + "learning_rate": 4.6330080610946115e-07, + "epoch": 1.673992673992674 + }, + { + "current_steps": 1371, + "loss": 2.4336, + "learning_rate": 4.6287653797199827e-07, + "epoch": 1.6752136752136753 + }, + { + "current_steps": 1372, + "loss": 2.4837, + "learning_rate": 4.624522698345354e-07, + "epoch": 1.6764346764346765 + }, + { + "current_steps": 1373, + "loss": 1.7942, + "learning_rate": 4.620280016970725e-07, + "epoch": 1.6776556776556777 + }, + { + "current_steps": 1374, + "loss": 2.2185, + "learning_rate": 4.616037335596096e-07, + "epoch": 1.678876678876679 + }, + { + "current_steps": 1375, + "loss": 2.2687, + "learning_rate": 4.6117946542214674e-07, + "epoch": 1.6800976800976801 + }, + { + "current_steps": 1376, + "loss": 2.2693, + "learning_rate": 4.6075519728468385e-07, + "epoch": 1.6813186813186813 + }, + { + "current_steps": 1377, + "loss": 2.4467, + "learning_rate": 4.60330929147221e-07, + "epoch": 1.6825396825396826 + }, + { + "current_steps": 1378, + "loss": 2.2277, + "learning_rate": 4.5990666100975814e-07, + "epoch": 1.6837606837606838 + }, + { + "current_steps": 1379, + "loss": 2.2346, + "learning_rate": 4.594823928722953e-07, + "epoch": 1.684981684981685 + }, + { + "current_steps": 1380, + "loss": 2.4123, + "learning_rate": 4.5905812473483243e-07, + "epoch": 1.6862026862026862 + }, + { + "current_steps": 1381, + "loss": 2.4866, + "learning_rate": 4.5863385659736955e-07, + "epoch": 1.6874236874236874 + }, + { + "current_steps": 1382, + "loss": 2.0674, + "learning_rate": 4.5820958845990666e-07, + "epoch": 1.6886446886446886 + }, + { + "current_steps": 1383, + "loss": 2.3077, + "learning_rate": 4.577853203224438e-07, + "epoch": 1.6898656898656899 + }, + { + "current_steps": 1384, + "loss": 2.3115, + "learning_rate": 4.573610521849809e-07, + "epoch": 1.691086691086691 + }, + { + "current_steps": 1385, + "loss": 2.4592, + "learning_rate": 4.56936784047518e-07, + "epoch": 1.6923076923076923 + }, + { + "current_steps": 1386, + "loss": 2.1593, + "learning_rate": 4.5651251591005513e-07, + "epoch": 1.6935286935286935 + }, + { + "current_steps": 1387, + "loss": 2.5197, + "learning_rate": 4.5608824777259225e-07, + "epoch": 1.6947496947496947 + }, + { + "current_steps": 1388, + "loss": 2.4313, + "learning_rate": 4.5566397963512936e-07, + "epoch": 1.695970695970696 + }, + { + "current_steps": 1389, + "loss": 2.3912, + "learning_rate": 4.552397114976665e-07, + "epoch": 1.6971916971916972 + }, + { + "current_steps": 1390, + "loss": 2.5397, + "learning_rate": 4.548154433602036e-07, + "epoch": 1.6984126984126984 + }, + { + "current_steps": 1391, + "loss": 2.2652, + "learning_rate": 4.543911752227407e-07, + "epoch": 1.6996336996336996 + }, + { + "current_steps": 1392, + "loss": 2.0074, + "learning_rate": 4.5396690708527783e-07, + "epoch": 1.7008547008547008 + }, + { + "current_steps": 1393, + "loss": 2.4166, + "learning_rate": 4.53542638947815e-07, + "epoch": 1.702075702075702 + }, + { + "current_steps": 1394, + "loss": 2.2856, + "learning_rate": 4.5311837081035217e-07, + "epoch": 1.7032967032967035 + }, + { + "current_steps": 1395, + "loss": 2.2585, + "learning_rate": 4.526941026728893e-07, + "epoch": 1.7045177045177047 + }, + { + "current_steps": 1396, + "loss": 2.3938, + "learning_rate": 4.522698345354264e-07, + "epoch": 1.705738705738706 + }, + { + "current_steps": 1397, + "loss": 2.2797, + "learning_rate": 4.518455663979635e-07, + "epoch": 1.7069597069597071 + }, + { + "current_steps": 1398, + "loss": 2.3795, + "learning_rate": 4.5142129826050064e-07, + "epoch": 1.7081807081807083 + }, + { + "current_steps": 1399, + "loss": 2.339, + "learning_rate": 4.5099703012303776e-07, + "epoch": 1.7094017094017095 + }, + { + "current_steps": 1400, + "loss": 2.3051, + "learning_rate": 4.505727619855749e-07, + "epoch": 1.7106227106227108 + }, + { + "current_steps": 1401, + "loss": 2.4315, + "learning_rate": 4.50148493848112e-07, + "epoch": 1.711843711843712 + }, + { + "current_steps": 1402, + "loss": 2.4366, + "learning_rate": 4.497242257106491e-07, + "epoch": 1.7130647130647132 + }, + { + "current_steps": 1403, + "loss": 1.9768, + "learning_rate": 4.492999575731862e-07, + "epoch": 1.7142857142857144 + }, + { + "current_steps": 1404, + "loss": 1.8328, + "learning_rate": 4.4887568943572334e-07, + "epoch": 1.7155067155067156 + }, + { + "current_steps": 1405, + "loss": 2.4186, + "learning_rate": 4.4845142129826046e-07, + "epoch": 1.7167277167277168 + }, + { + "current_steps": 1406, + "loss": 2.2672, + "learning_rate": 4.480271531607976e-07, + "epoch": 1.717948717948718 + }, + { + "current_steps": 1407, + "loss": 2.4336, + "learning_rate": 4.476028850233347e-07, + "epoch": 1.7191697191697193 + }, + { + "current_steps": 1408, + "loss": 2.3805, + "learning_rate": 4.471786168858718e-07, + "epoch": 1.7203907203907205 + }, + { + "current_steps": 1409, + "loss": 2.2837, + "learning_rate": 4.4675434874840893e-07, + "epoch": 1.7216117216117217 + }, + { + "current_steps": 1410, + "loss": 2.2865, + "learning_rate": 4.4633008061094615e-07, + "epoch": 1.722832722832723 + }, + { + "current_steps": 1411, + "loss": 2.2093, + "learning_rate": 4.4590581247348327e-07, + "epoch": 1.7240537240537241 + }, + { + "current_steps": 1412, + "loss": 2.3876, + "learning_rate": 4.454815443360204e-07, + "epoch": 1.7252747252747254 + }, + { + "current_steps": 1413, + "loss": 2.1873, + "learning_rate": 4.450572761985575e-07, + "epoch": 1.7264957264957266 + }, + { + "current_steps": 1414, + "loss": 2.3873, + "learning_rate": 4.446330080610946e-07, + "epoch": 1.7277167277167278 + }, + { + "current_steps": 1415, + "loss": 2.4309, + "learning_rate": 4.4420873992363174e-07, + "epoch": 1.728937728937729 + }, + { + "current_steps": 1416, + "loss": 2.5887, + "learning_rate": 4.4378447178616885e-07, + "epoch": 1.7301587301587302 + }, + { + "current_steps": 1417, + "loss": 1.9497, + "learning_rate": 4.4336020364870597e-07, + "epoch": 1.7313797313797314 + }, + { + "current_steps": 1418, + "loss": 2.4666, + "learning_rate": 4.429359355112431e-07, + "epoch": 1.7326007326007327 + }, + { + "current_steps": 1419, + "loss": 1.8444, + "learning_rate": 4.425116673737802e-07, + "epoch": 1.7338217338217339 + }, + { + "current_steps": 1420, + "loss": 2.2877, + "learning_rate": 4.420873992363173e-07, + "epoch": 1.735042735042735 + }, + { + "current_steps": 1421, + "loss": 2.3031, + "learning_rate": 4.4166313109885444e-07, + "epoch": 1.7362637362637363 + }, + { + "current_steps": 1422, + "loss": 2.2764, + "learning_rate": 4.4123886296139155e-07, + "epoch": 1.7374847374847375 + }, + { + "current_steps": 1423, + "loss": 2.2785, + "learning_rate": 4.4081459482392867e-07, + "epoch": 1.7387057387057387 + }, + { + "current_steps": 1424, + "loss": 2.3449, + "learning_rate": 4.403903266864658e-07, + "epoch": 1.73992673992674 + }, + { + "current_steps": 1425, + "loss": 2.2839, + "learning_rate": 4.399660585490029e-07, + "epoch": 1.7411477411477412 + }, + { + "current_steps": 1426, + "loss": 2.3748, + "learning_rate": 4.3954179041154e-07, + "epoch": 1.7423687423687424 + }, + { + "current_steps": 1427, + "loss": 2.2649, + "learning_rate": 4.3911752227407724e-07, + "epoch": 1.7435897435897436 + }, + { + "current_steps": 1428, + "loss": 2.3514, + "learning_rate": 4.3869325413661436e-07, + "epoch": 1.7448107448107448 + }, + { + "current_steps": 1429, + "loss": 2.4346, + "learning_rate": 4.382689859991515e-07, + "epoch": 1.746031746031746 + }, + { + "current_steps": 1430, + "loss": 2.642, + "learning_rate": 4.378447178616886e-07, + "epoch": 1.7472527472527473 + }, + { + "current_steps": 1431, + "loss": 2.3577, + "learning_rate": 4.374204497242257e-07, + "epoch": 1.7484737484737485 + }, + { + "current_steps": 1432, + "loss": 1.8706, + "learning_rate": 4.3699618158676283e-07, + "epoch": 1.7496947496947497 + }, + { + "current_steps": 1433, + "loss": 2.3927, + "learning_rate": 4.3657191344929995e-07, + "epoch": 1.750915750915751 + }, + { + "current_steps": 1434, + "loss": 2.4744, + "learning_rate": 4.3614764531183706e-07, + "epoch": 1.7521367521367521 + }, + { + "current_steps": 1435, + "loss": 2.5025, + "learning_rate": 4.357233771743742e-07, + "epoch": 1.7533577533577533 + }, + { + "current_steps": 1436, + "loss": 2.4665, + "learning_rate": 4.352991090369113e-07, + "epoch": 1.7545787545787546 + }, + { + "current_steps": 1437, + "loss": 2.4023, + "learning_rate": 4.348748408994484e-07, + "epoch": 1.7557997557997558 + }, + { + "current_steps": 1438, + "loss": 2.4083, + "learning_rate": 4.3445057276198553e-07, + "epoch": 1.757020757020757 + }, + { + "current_steps": 1439, + "loss": 2.4453, + "learning_rate": 4.3402630462452265e-07, + "epoch": 1.7582417582417582 + }, + { + "current_steps": 1440, + "loss": 2.2983, + "learning_rate": 4.3360203648705977e-07, + "epoch": 1.7594627594627594 + }, + { + "current_steps": 1441, + "loss": 2.4087, + "learning_rate": 4.331777683495969e-07, + "epoch": 1.7606837606837606 + }, + { + "current_steps": 1442, + "loss": 2.4437, + "learning_rate": 4.32753500212134e-07, + "epoch": 1.7619047619047619 + }, + { + "current_steps": 1443, + "loss": 2.4878, + "learning_rate": 4.3232923207467117e-07, + "epoch": 1.763125763125763 + }, + { + "current_steps": 1444, + "loss": 2.4311, + "learning_rate": 4.3190496393720834e-07, + "epoch": 1.7643467643467643 + }, + { + "current_steps": 1445, + "loss": 2.4447, + "learning_rate": 4.3148069579974546e-07, + "epoch": 1.7655677655677655 + }, + { + "current_steps": 1446, + "loss": 1.6019, + "learning_rate": 4.3105642766228257e-07, + "epoch": 1.7667887667887667 + }, + { + "current_steps": 1447, + "loss": 2.2599, + "learning_rate": 4.306321595248197e-07, + "epoch": 1.768009768009768 + }, + { + "current_steps": 1448, + "loss": 2.9023, + "learning_rate": 4.302078913873568e-07, + "epoch": 1.7692307692307692 + }, + { + "current_steps": 1449, + "loss": 2.3443, + "learning_rate": 4.297836232498939e-07, + "epoch": 1.7704517704517704 + }, + { + "current_steps": 1450, + "loss": 2.288, + "learning_rate": 4.2935935511243104e-07, + "epoch": 1.7716727716727716 + }, + { + "current_steps": 1451, + "loss": 2.3006, + "learning_rate": 4.2893508697496816e-07, + "epoch": 1.7728937728937728 + }, + { + "current_steps": 1452, + "loss": 2.2725, + "learning_rate": 4.285108188375053e-07, + "epoch": 1.774114774114774 + }, + { + "current_steps": 1453, + "loss": 2.3843, + "learning_rate": 4.280865507000424e-07, + "epoch": 1.7753357753357752 + }, + { + "current_steps": 1454, + "loss": 2.3453, + "learning_rate": 4.276622825625795e-07, + "epoch": 1.7765567765567765 + }, + { + "current_steps": 1455, + "loss": 1.8966, + "learning_rate": 4.272380144251166e-07, + "epoch": 1.7777777777777777 + }, + { + "current_steps": 1456, + "loss": 2.1956, + "learning_rate": 4.2681374628765374e-07, + "epoch": 1.778998778998779 + }, + { + "current_steps": 1457, + "loss": 2.2969, + "learning_rate": 4.2638947815019086e-07, + "epoch": 1.7802197802197801 + }, + { + "current_steps": 1458, + "loss": 2.3235, + "learning_rate": 4.2596521001272803e-07, + "epoch": 1.7814407814407813 + }, + { + "current_steps": 1459, + "loss": 2.3622, + "learning_rate": 4.2554094187526515e-07, + "epoch": 1.7826617826617825 + }, + { + "current_steps": 1460, + "loss": 2.4223, + "learning_rate": 4.2511667373780226e-07, + "epoch": 1.7838827838827838 + }, + { + "current_steps": 1461, + "loss": 2.1089, + "learning_rate": 4.2469240560033943e-07, + "epoch": 1.785103785103785 + }, + { + "current_steps": 1462, + "loss": 2.2835, + "learning_rate": 4.2426813746287655e-07, + "epoch": 1.7863247863247862 + }, + { + "current_steps": 1463, + "loss": 2.4276, + "learning_rate": 4.2384386932541367e-07, + "epoch": 1.7875457875457874 + }, + { + "current_steps": 1464, + "loss": 2.2805, + "learning_rate": 4.234196011879508e-07, + "epoch": 1.7887667887667886 + }, + { + "current_steps": 1465, + "loss": 2.3241, + "learning_rate": 4.229953330504879e-07, + "epoch": 1.7899877899877898 + }, + { + "current_steps": 1466, + "loss": 2.3517, + "learning_rate": 4.22571064913025e-07, + "epoch": 1.791208791208791 + }, + { + "current_steps": 1467, + "loss": 2.2617, + "learning_rate": 4.2214679677556214e-07, + "epoch": 1.7924297924297923 + }, + { + "current_steps": 1468, + "loss": 2.3573, + "learning_rate": 4.2172252863809925e-07, + "epoch": 1.7936507936507935 + }, + { + "current_steps": 1469, + "loss": 2.4241, + "learning_rate": 4.2129826050063637e-07, + "epoch": 1.7948717948717947 + }, + { + "current_steps": 1470, + "loss": 2.3407, + "learning_rate": 4.208739923631735e-07, + "epoch": 1.796092796092796 + }, + { + "current_steps": 1471, + "loss": 2.2203, + "learning_rate": 4.204497242257106e-07, + "epoch": 1.7973137973137974 + }, + { + "current_steps": 1472, + "loss": 2.3167, + "learning_rate": 4.200254560882477e-07, + "epoch": 1.7985347985347986 + }, + { + "current_steps": 1473, + "loss": 2.3293, + "learning_rate": 4.1960118795078484e-07, + "epoch": 1.7997557997557998 + }, + { + "current_steps": 1474, + "loss": 2.3742, + "learning_rate": 4.19176919813322e-07, + "epoch": 1.800976800976801 + }, + { + "current_steps": 1475, + "loss": 2.3629, + "learning_rate": 4.187526516758591e-07, + "epoch": 1.8021978021978022 + }, + { + "current_steps": 1476, + "loss": 2.2707, + "learning_rate": 4.1832838353839624e-07, + "epoch": 1.8034188034188035 + }, + { + "current_steps": 1477, + "loss": 2.2373, + "learning_rate": 4.1790411540093336e-07, + "epoch": 1.8046398046398047 + }, + { + "current_steps": 1478, + "loss": 2.482, + "learning_rate": 4.1747984726347053e-07, + "epoch": 1.8058608058608059 + }, + { + "current_steps": 1479, + "loss": 2.3133, + "learning_rate": 4.1705557912600765e-07, + "epoch": 1.807081807081807 + }, + { + "current_steps": 1480, + "loss": 2.4428, + "learning_rate": 4.1663131098854476e-07, + "epoch": 1.8083028083028083 + }, + { + "current_steps": 1481, + "loss": 2.2188, + "learning_rate": 4.162070428510819e-07, + "epoch": 1.8095238095238095 + }, + { + "current_steps": 1482, + "loss": 2.1513, + "learning_rate": 4.15782774713619e-07, + "epoch": 1.8107448107448108 + }, + { + "current_steps": 1483, + "loss": 2.2762, + "learning_rate": 4.153585065761561e-07, + "epoch": 1.811965811965812 + }, + { + "current_steps": 1484, + "loss": 2.1842, + "learning_rate": 4.1493423843869323e-07, + "epoch": 1.8131868131868132 + }, + { + "current_steps": 1485, + "loss": 2.4993, + "learning_rate": 4.1450997030123035e-07, + "epoch": 1.8144078144078144 + }, + { + "current_steps": 1486, + "loss": 2.3944, + "learning_rate": 4.1408570216376746e-07, + "epoch": 1.8156288156288156 + }, + { + "current_steps": 1487, + "loss": 2.2499, + "learning_rate": 4.136614340263046e-07, + "epoch": 1.8168498168498168 + }, + { + "current_steps": 1488, + "loss": 2.1806, + "learning_rate": 4.132371658888417e-07, + "epoch": 1.818070818070818 + }, + { + "current_steps": 1489, + "loss": 2.436, + "learning_rate": 4.128128977513788e-07, + "epoch": 1.8192918192918193 + }, + { + "current_steps": 1490, + "loss": 2.3977, + "learning_rate": 4.12388629613916e-07, + "epoch": 1.8205128205128205 + }, + { + "current_steps": 1491, + "loss": 2.32, + "learning_rate": 4.119643614764531e-07, + "epoch": 1.8217338217338217 + }, + { + "current_steps": 1492, + "loss": 2.2318, + "learning_rate": 4.115400933389902e-07, + "epoch": 1.822954822954823 + }, + { + "current_steps": 1493, + "loss": 2.4765, + "learning_rate": 4.1111582520152734e-07, + "epoch": 1.8241758241758241 + }, + { + "current_steps": 1494, + "loss": 2.3594, + "learning_rate": 4.106915570640645e-07, + "epoch": 1.8253968253968254 + }, + { + "current_steps": 1495, + "loss": 2.4189, + "learning_rate": 4.102672889266016e-07, + "epoch": 1.8266178266178266 + }, + { + "current_steps": 1496, + "loss": 2.2285, + "learning_rate": 4.0984302078913874e-07, + "epoch": 1.8278388278388278 + }, + { + "current_steps": 1497, + "loss": 2.2163, + "learning_rate": 4.0941875265167586e-07, + "epoch": 1.8290598290598292 + }, + { + "current_steps": 1498, + "loss": 2.4762, + "learning_rate": 4.08994484514213e-07, + "epoch": 1.8302808302808304 + }, + { + "current_steps": 1499, + "loss": 2.218, + "learning_rate": 4.085702163767501e-07, + "epoch": 1.8315018315018317 + }, + { + "current_steps": 1500, + "loss": 2.4371, + "learning_rate": 4.081459482392872e-07, + "epoch": 1.8327228327228329 + }, + { + "current_steps": 1501, + "loss": 2.2661, + "learning_rate": 4.077216801018243e-07, + "epoch": 1.833943833943834 + }, + { + "current_steps": 1502, + "loss": 2.3941, + "learning_rate": 4.0729741196436144e-07, + "epoch": 1.8351648351648353 + }, + { + "current_steps": 1503, + "loss": 2.2231, + "learning_rate": 4.0687314382689856e-07, + "epoch": 1.8363858363858365 + }, + { + "current_steps": 1504, + "loss": 2.3515, + "learning_rate": 4.064488756894357e-07, + "epoch": 1.8376068376068377 + }, + { + "current_steps": 1505, + "loss": 2.4279, + "learning_rate": 4.060246075519728e-07, + "epoch": 1.838827838827839 + }, + { + "current_steps": 1506, + "loss": 1.4052, + "learning_rate": 4.0560033941450996e-07, + "epoch": 1.8400488400488402 + }, + { + "current_steps": 1507, + "loss": 2.3104, + "learning_rate": 4.051760712770471e-07, + "epoch": 1.8412698412698414 + }, + { + "current_steps": 1508, + "loss": 2.2905, + "learning_rate": 4.047518031395842e-07, + "epoch": 1.8424908424908426 + }, + { + "current_steps": 1509, + "loss": 2.427, + "learning_rate": 4.043275350021213e-07, + "epoch": 1.8437118437118438 + }, + { + "current_steps": 1510, + "loss": 2.199, + "learning_rate": 4.0390326686465843e-07, + "epoch": 1.844932844932845 + }, + { + "current_steps": 1511, + "loss": 2.3386, + "learning_rate": 4.034789987271956e-07, + "epoch": 1.8461538461538463 + }, + { + "current_steps": 1512, + "loss": 2.349, + "learning_rate": 4.030547305897327e-07, + "epoch": 1.8473748473748475 + }, + { + "current_steps": 1513, + "loss": 2.2238, + "learning_rate": 4.0263046245226984e-07, + "epoch": 1.8485958485958487 + }, + { + "current_steps": 1514, + "loss": 2.3688, + "learning_rate": 4.0220619431480695e-07, + "epoch": 1.84981684981685 + }, + { + "current_steps": 1515, + "loss": 2.2775, + "learning_rate": 4.0178192617734407e-07, + "epoch": 1.8510378510378511 + }, + { + "current_steps": 1516, + "loss": 2.3378, + "learning_rate": 4.013576580398812e-07, + "epoch": 1.8522588522588523 + }, + { + "current_steps": 1517, + "loss": 2.4289, + "learning_rate": 4.009333899024183e-07, + "epoch": 1.8534798534798536 + }, + { + "current_steps": 1518, + "loss": 2.4298, + "learning_rate": 4.005091217649554e-07, + "epoch": 1.8547008547008548 + }, + { + "current_steps": 1519, + "loss": 2.4544, + "learning_rate": 4.0008485362749254e-07, + "epoch": 1.855921855921856 + }, + { + "current_steps": 1520, + "loss": 1.8478, + "learning_rate": 3.9966058549002965e-07, + "epoch": 1.8571428571428572 + }, + { + "current_steps": 1521, + "loss": 2.2153, + "learning_rate": 3.992363173525668e-07, + "epoch": 1.8583638583638584 + }, + { + "current_steps": 1522, + "loss": 2.4008, + "learning_rate": 3.9881204921510394e-07, + "epoch": 1.8595848595848596 + }, + { + "current_steps": 1523, + "loss": 2.3389, + "learning_rate": 3.9838778107764106e-07, + "epoch": 1.8608058608058609 + }, + { + "current_steps": 1524, + "loss": 2.1898, + "learning_rate": 3.979635129401782e-07, + "epoch": 1.862026862026862 + }, + { + "current_steps": 1525, + "loss": 2.4241, + "learning_rate": 3.975392448027153e-07, + "epoch": 1.8632478632478633 + }, + { + "current_steps": 1526, + "loss": 2.3177, + "learning_rate": 3.971149766652524e-07, + "epoch": 1.8644688644688645 + }, + { + "current_steps": 1527, + "loss": 2.1883, + "learning_rate": 3.966907085277895e-07, + "epoch": 1.8656898656898657 + }, + { + "current_steps": 1528, + "loss": 2.3575, + "learning_rate": 3.962664403903267e-07, + "epoch": 1.866910866910867 + }, + { + "current_steps": 1529, + "loss": 2.5606, + "learning_rate": 3.958421722528638e-07, + "epoch": 1.8681318681318682 + }, + { + "current_steps": 1530, + "loss": 2.2586, + "learning_rate": 3.9541790411540093e-07, + "epoch": 1.8693528693528694 + }, + { + "current_steps": 1531, + "loss": 2.2806, + "learning_rate": 3.9499363597793805e-07, + "epoch": 1.8705738705738706 + }, + { + "current_steps": 1532, + "loss": 2.2257, + "learning_rate": 3.9456936784047516e-07, + "epoch": 1.8717948717948718 + }, + { + "current_steps": 1533, + "loss": 2.564, + "learning_rate": 3.941450997030123e-07, + "epoch": 1.873015873015873 + }, + { + "current_steps": 1534, + "loss": 2.3962, + "learning_rate": 3.937208315655494e-07, + "epoch": 1.8742368742368742 + }, + { + "current_steps": 1535, + "loss": 2.3, + "learning_rate": 3.932965634280865e-07, + "epoch": 1.8754578754578755 + }, + { + "current_steps": 1536, + "loss": 1.8343, + "learning_rate": 3.9287229529062363e-07, + "epoch": 1.8766788766788767 + }, + { + "current_steps": 1537, + "loss": 2.4008, + "learning_rate": 3.924480271531608e-07, + "epoch": 1.877899877899878 + }, + { + "current_steps": 1538, + "loss": 2.339, + "learning_rate": 3.920237590156979e-07, + "epoch": 1.879120879120879 + }, + { + "current_steps": 1539, + "loss": 2.2094, + "learning_rate": 3.9159949087823504e-07, + "epoch": 1.8803418803418803 + }, + { + "current_steps": 1540, + "loss": 2.3057, + "learning_rate": 3.9117522274077215e-07, + "epoch": 1.8815628815628815 + }, + { + "current_steps": 1541, + "loss": 2.3317, + "learning_rate": 3.9075095460330927e-07, + "epoch": 1.8827838827838828 + }, + { + "current_steps": 1542, + "loss": 2.4198, + "learning_rate": 3.903266864658464e-07, + "epoch": 1.884004884004884 + }, + { + "current_steps": 1543, + "loss": 1.7995, + "learning_rate": 3.899024183283835e-07, + "epoch": 1.8852258852258852 + }, + { + "current_steps": 1544, + "loss": 2.3492, + "learning_rate": 3.894781501909206e-07, + "epoch": 1.8864468864468864 + }, + { + "current_steps": 1545, + "loss": 1.8934, + "learning_rate": 3.890538820534578e-07, + "epoch": 1.8876678876678876 + }, + { + "current_steps": 1546, + "loss": 2.3125, + "learning_rate": 3.886296139159949e-07, + "epoch": 1.8888888888888888 + }, + { + "current_steps": 1547, + "loss": 2.4005, + "learning_rate": 3.88205345778532e-07, + "epoch": 1.89010989010989 + }, + { + "current_steps": 1548, + "loss": 2.467, + "learning_rate": 3.8778107764106914e-07, + "epoch": 1.8913308913308913 + }, + { + "current_steps": 1549, + "loss": 2.2963, + "learning_rate": 3.8735680950360626e-07, + "epoch": 1.8925518925518925 + }, + { + "current_steps": 1550, + "loss": 2.3194, + "learning_rate": 3.869325413661434e-07, + "epoch": 1.8937728937728937 + }, + { + "current_steps": 1551, + "loss": 2.2998, + "learning_rate": 3.865082732286805e-07, + "epoch": 1.894993894993895 + }, + { + "current_steps": 1552, + "loss": 2.0462, + "learning_rate": 3.860840050912176e-07, + "epoch": 1.8962148962148961 + }, + { + "current_steps": 1553, + "loss": 2.3261, + "learning_rate": 3.856597369537548e-07, + "epoch": 1.8974358974358974 + }, + { + "current_steps": 1554, + "loss": 2.4382, + "learning_rate": 3.852354688162919e-07, + "epoch": 1.8986568986568986 + }, + { + "current_steps": 1555, + "loss": 2.2285, + "learning_rate": 3.84811200678829e-07, + "epoch": 1.8998778998778998 + }, + { + "current_steps": 1556, + "loss": 2.2441, + "learning_rate": 3.8438693254136613e-07, + "epoch": 1.901098901098901 + }, + { + "current_steps": 1557, + "loss": 2.2537, + "learning_rate": 3.8396266440390325e-07, + "epoch": 1.9023199023199022 + }, + { + "current_steps": 1558, + "loss": 2.3275, + "learning_rate": 3.8353839626644036e-07, + "epoch": 1.9035409035409034 + }, + { + "current_steps": 1559, + "loss": 2.1317, + "learning_rate": 3.831141281289775e-07, + "epoch": 1.9047619047619047 + }, + { + "current_steps": 1560, + "loss": 1.653, + "learning_rate": 3.826898599915146e-07, + "epoch": 1.9059829059829059 + }, + { + "current_steps": 1561, + "loss": 2.4868, + "learning_rate": 3.822655918540517e-07, + "epoch": 1.907203907203907 + }, + { + "current_steps": 1562, + "loss": 2.402, + "learning_rate": 3.818413237165889e-07, + "epoch": 1.9084249084249083 + }, + { + "current_steps": 1563, + "loss": 2.383, + "learning_rate": 3.81417055579126e-07, + "epoch": 1.9096459096459095 + }, + { + "current_steps": 1564, + "loss": 2.155, + "learning_rate": 3.809927874416631e-07, + "epoch": 1.9108669108669107 + }, + { + "current_steps": 1565, + "loss": 2.3357, + "learning_rate": 3.8056851930420024e-07, + "epoch": 1.912087912087912 + }, + { + "current_steps": 1566, + "loss": 2.4143, + "learning_rate": 3.8014425116673735e-07, + "epoch": 1.9133089133089132 + }, + { + "current_steps": 1567, + "loss": 2.3218, + "learning_rate": 3.7971998302927447e-07, + "epoch": 1.9145299145299144 + }, + { + "current_steps": 1568, + "loss": 2.6906, + "learning_rate": 3.792957148918116e-07, + "epoch": 1.9157509157509156 + }, + { + "current_steps": 1569, + "loss": 2.3631, + "learning_rate": 3.7887144675434876e-07, + "epoch": 1.9169719169719168 + }, + { + "current_steps": 1570, + "loss": 2.4087, + "learning_rate": 3.784471786168859e-07, + "epoch": 1.918192918192918 + }, + { + "current_steps": 1571, + "loss": 2.404, + "learning_rate": 3.78022910479423e-07, + "epoch": 1.9194139194139193 + }, + { + "current_steps": 1572, + "loss": 2.3874, + "learning_rate": 3.775986423419601e-07, + "epoch": 1.9206349206349205 + }, + { + "current_steps": 1573, + "loss": 2.3802, + "learning_rate": 3.771743742044972e-07, + "epoch": 1.9218559218559217 + }, + { + "current_steps": 1574, + "loss": 2.4862, + "learning_rate": 3.7675010606703434e-07, + "epoch": 1.9230769230769231 + }, + { + "current_steps": 1575, + "loss": 2.2056, + "learning_rate": 3.7632583792957146e-07, + "epoch": 1.9242979242979243 + }, + { + "current_steps": 1576, + "loss": 2.182, + "learning_rate": 3.759015697921086e-07, + "epoch": 1.9255189255189256 + }, + { + "current_steps": 1577, + "loss": 2.3311, + "learning_rate": 3.754773016546457e-07, + "epoch": 1.9267399267399268 + }, + { + "current_steps": 1578, + "loss": 2.2679, + "learning_rate": 3.750530335171828e-07, + "epoch": 1.927960927960928 + }, + { + "current_steps": 1579, + "loss": 2.4803, + "learning_rate": 3.7462876537972e-07, + "epoch": 1.9291819291819292 + }, + { + "current_steps": 1580, + "loss": 2.3829, + "learning_rate": 3.742044972422571e-07, + "epoch": 1.9304029304029304 + }, + { + "current_steps": 1581, + "loss": 2.3868, + "learning_rate": 3.737802291047942e-07, + "epoch": 1.9316239316239316 + }, + { + "current_steps": 1582, + "loss": 2.3415, + "learning_rate": 3.7335596096733133e-07, + "epoch": 1.9328449328449329 + }, + { + "current_steps": 1583, + "loss": 2.3036, + "learning_rate": 3.7293169282986845e-07, + "epoch": 1.934065934065934 + }, + { + "current_steps": 1584, + "loss": 2.2922, + "learning_rate": 3.725074246924056e-07, + "epoch": 1.9352869352869353 + }, + { + "current_steps": 1585, + "loss": 1.9261, + "learning_rate": 3.7208315655494274e-07, + "epoch": 1.9365079365079365 + }, + { + "current_steps": 1586, + "loss": 2.4766, + "learning_rate": 3.7165888841747985e-07, + "epoch": 1.9377289377289377 + }, + { + "current_steps": 1587, + "loss": 2.3014, + "learning_rate": 3.7123462028001697e-07, + "epoch": 1.938949938949939 + }, + { + "current_steps": 1588, + "loss": 2.0451, + "learning_rate": 3.708103521425541e-07, + "epoch": 1.9401709401709402 + }, + { + "current_steps": 1589, + "loss": 2.3617, + "learning_rate": 3.703860840050912e-07, + "epoch": 1.9413919413919414 + }, + { + "current_steps": 1590, + "loss": 2.4153, + "learning_rate": 3.699618158676283e-07, + "epoch": 1.9426129426129426 + }, + { + "current_steps": 1591, + "loss": 2.272, + "learning_rate": 3.6953754773016544e-07, + "epoch": 1.9438339438339438 + }, + { + "current_steps": 1592, + "loss": 2.1797, + "learning_rate": 3.6911327959270255e-07, + "epoch": 1.945054945054945 + }, + { + "current_steps": 1593, + "loss": 2.5588, + "learning_rate": 3.6868901145523967e-07, + "epoch": 1.9462759462759462 + }, + { + "current_steps": 1594, + "loss": 2.2164, + "learning_rate": 3.682647433177768e-07, + "epoch": 1.9474969474969475 + }, + { + "current_steps": 1595, + "loss": 2.3577, + "learning_rate": 3.6784047518031396e-07, + "epoch": 1.9487179487179487 + }, + { + "current_steps": 1596, + "loss": 2.4741, + "learning_rate": 3.674162070428511e-07, + "epoch": 1.94993894993895 + }, + { + "current_steps": 1597, + "loss": 2.3374, + "learning_rate": 3.669919389053882e-07, + "epoch": 1.9511599511599511 + }, + { + "current_steps": 1598, + "loss": 2.1477, + "learning_rate": 3.665676707679253e-07, + "epoch": 1.9523809523809523 + }, + { + "current_steps": 1599, + "loss": 2.0703, + "learning_rate": 3.661434026304624e-07, + "epoch": 1.9536019536019538 + }, + { + "current_steps": 1600, + "loss": 2.2507, + "learning_rate": 3.657191344929996e-07, + "epoch": 1.954822954822955 + }, + { + "current_steps": 1601, + "loss": 2.449, + "learning_rate": 3.652948663555367e-07, + "epoch": 1.9560439560439562 + }, + { + "current_steps": 1602, + "loss": 2.3338, + "learning_rate": 3.6487059821807383e-07, + "epoch": 1.9572649572649574 + }, + { + "current_steps": 1603, + "loss": 2.5713, + "learning_rate": 3.6444633008061095e-07, + "epoch": 1.9584859584859586 + }, + { + "current_steps": 1604, + "loss": 1.9003, + "learning_rate": 3.6402206194314806e-07, + "epoch": 1.9597069597069599 + }, + { + "current_steps": 1605, + "loss": 2.4073, + "learning_rate": 3.635977938056852e-07, + "epoch": 1.960927960927961 + }, + { + "current_steps": 1606, + "loss": 2.3066, + "learning_rate": 3.631735256682223e-07, + "epoch": 1.9621489621489623 + }, + { + "current_steps": 1607, + "loss": 1.9298, + "learning_rate": 3.627492575307594e-07, + "epoch": 1.9633699633699635 + }, + { + "current_steps": 1608, + "loss": 2.3873, + "learning_rate": 3.6232498939329653e-07, + "epoch": 1.9645909645909647 + }, + { + "current_steps": 1609, + "loss": 2.3978, + "learning_rate": 3.6190072125583365e-07, + "epoch": 1.965811965811966 + }, + { + "current_steps": 1610, + "loss": 2.3139, + "learning_rate": 3.6147645311837077e-07, + "epoch": 1.9670329670329672 + }, + { + "current_steps": 1611, + "loss": 2.3546, + "learning_rate": 3.610521849809079e-07, + "epoch": 1.9682539682539684 + }, + { + "current_steps": 1612, + "loss": 2.3884, + "learning_rate": 3.6062791684344505e-07, + "epoch": 1.9694749694749696 + }, + { + "current_steps": 1613, + "loss": 2.3825, + "learning_rate": 3.6020364870598217e-07, + "epoch": 1.9706959706959708 + }, + { + "current_steps": 1614, + "loss": 2.4442, + "learning_rate": 3.597793805685193e-07, + "epoch": 1.971916971916972 + }, + { + "current_steps": 1615, + "loss": 2.2535, + "learning_rate": 3.593551124310564e-07, + "epoch": 1.9731379731379732 + }, + { + "current_steps": 1616, + "loss": 2.4084, + "learning_rate": 3.589308442935936e-07, + "epoch": 1.9743589743589745 + }, + { + "current_steps": 1617, + "loss": 2.4037, + "learning_rate": 3.585065761561307e-07, + "epoch": 1.9755799755799757 + }, + { + "current_steps": 1618, + "loss": 2.4603, + "learning_rate": 3.580823080186678e-07, + "epoch": 1.9768009768009769 + }, + { + "current_steps": 1619, + "loss": 2.5379, + "learning_rate": 3.576580398812049e-07, + "epoch": 1.978021978021978 + }, + { + "current_steps": 1620, + "loss": 2.3672, + "learning_rate": 3.5723377174374204e-07, + "epoch": 1.9792429792429793 + }, + { + "current_steps": 1621, + "loss": 2.2277, + "learning_rate": 3.5680950360627916e-07, + "epoch": 1.9804639804639805 + }, + { + "current_steps": 1622, + "loss": 2.4275, + "learning_rate": 3.563852354688163e-07, + "epoch": 1.9816849816849818 + }, + { + "current_steps": 1623, + "loss": 2.3355, + "learning_rate": 3.559609673313534e-07, + "epoch": 1.982905982905983 + }, + { + "current_steps": 1624, + "loss": 1.8276, + "learning_rate": 3.555366991938905e-07, + "epoch": 1.9841269841269842 + }, + { + "current_steps": 1625, + "loss": 2.3742, + "learning_rate": 3.5511243105642763e-07, + "epoch": 1.9853479853479854 + }, + { + "current_steps": 1626, + "loss": 2.4157, + "learning_rate": 3.5468816291896474e-07, + "epoch": 1.9865689865689866 + }, + { + "current_steps": 1627, + "loss": 2.3039, + "learning_rate": 3.5426389478150186e-07, + "epoch": 1.9877899877899878 + }, + { + "current_steps": 1628, + "loss": 2.2523, + "learning_rate": 3.53839626644039e-07, + "epoch": 1.989010989010989 + }, + { + "current_steps": 1629, + "loss": 2.3526, + "learning_rate": 3.5341535850657615e-07, + "epoch": 1.9902319902319903 + }, + { + "current_steps": 1630, + "loss": 2.37, + "learning_rate": 3.5299109036911326e-07, + "epoch": 1.9914529914529915 + }, + { + "current_steps": 1631, + "loss": 2.4206, + "learning_rate": 3.525668222316504e-07, + "epoch": 1.9926739926739927 + }, + { + "current_steps": 1632, + "loss": 2.2589, + "learning_rate": 3.5214255409418755e-07, + "epoch": 1.993894993894994 + }, + { + "current_steps": 1633, + "loss": 2.2542, + "learning_rate": 3.5171828595672467e-07, + "epoch": 1.9951159951159951 + }, + { + "current_steps": 1634, + "loss": 2.3225, + "learning_rate": 3.512940178192618e-07, + "epoch": 1.9963369963369964 + }, + { + "current_steps": 1635, + "loss": 2.2721, + "learning_rate": 3.508697496817989e-07, + "epoch": 1.9975579975579976 + }, + { + "current_steps": 1636, + "loss": 2.4384, + "learning_rate": 3.50445481544336e-07, + "epoch": 1.9987789987789988 + }, + { + "current_steps": 1637, + "loss": 2.0185, + "learning_rate": 3.5002121340687314e-07, + "epoch": 2.0 + }, + { + "current_steps": 1638, + "loss": 2.1683, + "learning_rate": 3.4959694526941025e-07, + "epoch": 2.001221001221001 + }, + { + "current_steps": 1639, + "loss": 2.3308, + "learning_rate": 3.4917267713194737e-07, + "epoch": 2.0024420024420024 + }, + { + "current_steps": 1640, + "loss": 2.303, + "learning_rate": 3.487484089944845e-07, + "epoch": 2.0036630036630036 + }, + { + "current_steps": 1641, + "loss": 2.2124, + "learning_rate": 3.483241408570216e-07, + "epoch": 2.004884004884005 + }, + { + "current_steps": 1642, + "loss": 2.4425, + "learning_rate": 3.478998727195587e-07, + "epoch": 2.006105006105006 + }, + { + "current_steps": 1643, + "loss": 2.3511, + "learning_rate": 3.4747560458209584e-07, + "epoch": 2.0073260073260073 + }, + { + "current_steps": 1644, + "loss": 2.1801, + "learning_rate": 3.4705133644463296e-07, + "epoch": 2.0085470085470085 + }, + { + "current_steps": 1645, + "loss": 1.8584, + "learning_rate": 3.4662706830717007e-07, + "epoch": 2.0097680097680097 + }, + { + "current_steps": 1646, + "loss": 2.2919, + "learning_rate": 3.4620280016970724e-07, + "epoch": 2.010989010989011 + }, + { + "current_steps": 1647, + "loss": 2.4054, + "learning_rate": 3.4577853203224436e-07, + "epoch": 2.012210012210012 + }, + { + "current_steps": 1648, + "loss": 2.3728, + "learning_rate": 3.4535426389478153e-07, + "epoch": 2.0134310134310134 + }, + { + "current_steps": 1649, + "loss": 2.3123, + "learning_rate": 3.4492999575731865e-07, + "epoch": 2.0146520146520146 + }, + { + "current_steps": 1650, + "loss": 2.3321, + "learning_rate": 3.4450572761985576e-07, + "epoch": 2.015873015873016 + }, + { + "current_steps": 1651, + "loss": 2.3379, + "learning_rate": 3.440814594823929e-07, + "epoch": 2.017094017094017 + }, + { + "current_steps": 1652, + "loss": 2.2951, + "learning_rate": 3.4365719134493e-07, + "epoch": 2.0183150183150182 + }, + { + "current_steps": 1653, + "loss": 2.3618, + "learning_rate": 3.432329232074671e-07, + "epoch": 2.0195360195360195 + }, + { + "current_steps": 1654, + "loss": 2.3149, + "learning_rate": 3.4280865507000423e-07, + "epoch": 2.0207570207570207 + }, + { + "current_steps": 1655, + "loss": 2.453, + "learning_rate": 3.4238438693254135e-07, + "epoch": 2.021978021978022 + }, + { + "current_steps": 1656, + "loss": 2.2308, + "learning_rate": 3.4196011879507846e-07, + "epoch": 2.023199023199023 + }, + { + "current_steps": 1657, + "loss": 2.4438, + "learning_rate": 3.415358506576156e-07, + "epoch": 2.0244200244200243 + }, + { + "current_steps": 1658, + "loss": 2.5334, + "learning_rate": 3.411115825201527e-07, + "epoch": 2.0256410256410255 + }, + { + "current_steps": 1659, + "loss": 2.4348, + "learning_rate": 3.406873143826898e-07, + "epoch": 2.0268620268620268 + }, + { + "current_steps": 1660, + "loss": 2.427, + "learning_rate": 3.4026304624522693e-07, + "epoch": 2.028083028083028 + }, + { + "current_steps": 1661, + "loss": 2.3093, + "learning_rate": 3.3983877810776405e-07, + "epoch": 2.029304029304029 + }, + { + "current_steps": 1662, + "loss": 2.2931, + "learning_rate": 3.3941450997030117e-07, + "epoch": 2.0305250305250304 + }, + { + "current_steps": 1663, + "loss": 1.6986, + "learning_rate": 3.389902418328384e-07, + "epoch": 2.0317460317460316 + }, + { + "current_steps": 1664, + "loss": 2.3932, + "learning_rate": 3.385659736953755e-07, + "epoch": 2.032967032967033 + }, + { + "current_steps": 1665, + "loss": 2.3777, + "learning_rate": 3.381417055579126e-07, + "epoch": 2.034188034188034 + }, + { + "current_steps": 1666, + "loss": 2.4158, + "learning_rate": 3.3771743742044974e-07, + "epoch": 2.0354090354090353 + }, + { + "current_steps": 1667, + "loss": 2.1572, + "learning_rate": 3.3729316928298686e-07, + "epoch": 2.0366300366300365 + }, + { + "current_steps": 1668, + "loss": 2.2962, + "learning_rate": 3.36868901145524e-07, + "epoch": 2.0378510378510377 + }, + { + "current_steps": 1669, + "loss": 2.3424, + "learning_rate": 3.364446330080611e-07, + "epoch": 2.039072039072039 + }, + { + "current_steps": 1670, + "loss": 2.6959, + "learning_rate": 3.360203648705982e-07, + "epoch": 2.04029304029304 + }, + { + "current_steps": 1671, + "loss": 2.3531, + "learning_rate": 3.355960967331353e-07, + "epoch": 2.0415140415140414 + }, + { + "current_steps": 1672, + "loss": 2.3657, + "learning_rate": 3.3517182859567244e-07, + "epoch": 2.0427350427350426 + }, + { + "current_steps": 1673, + "loss": 2.3204, + "learning_rate": 3.3474756045820956e-07, + "epoch": 2.043956043956044 + }, + { + "current_steps": 1674, + "loss": 2.4746, + "learning_rate": 3.343232923207467e-07, + "epoch": 2.045177045177045 + }, + { + "current_steps": 1675, + "loss": 2.2162, + "learning_rate": 3.338990241832838e-07, + "epoch": 2.0463980463980462 + }, + { + "current_steps": 1676, + "loss": 2.2832, + "learning_rate": 3.334747560458209e-07, + "epoch": 2.0476190476190474 + }, + { + "current_steps": 1677, + "loss": 2.2838, + "learning_rate": 3.3305048790835803e-07, + "epoch": 2.0488400488400487 + }, + { + "current_steps": 1678, + "loss": 2.0572, + "learning_rate": 3.3262621977089514e-07, + "epoch": 2.05006105006105 + }, + { + "current_steps": 1679, + "loss": 2.3399, + "learning_rate": 3.3220195163343226e-07, + "epoch": 2.051282051282051 + }, + { + "current_steps": 1680, + "loss": 2.3062, + "learning_rate": 3.317776834959695e-07, + "epoch": 2.0525030525030523 + }, + { + "current_steps": 1681, + "loss": 2.2698, + "learning_rate": 3.313534153585066e-07, + "epoch": 2.0537240537240535 + }, + { + "current_steps": 1682, + "loss": 2.4251, + "learning_rate": 3.309291472210437e-07, + "epoch": 2.0549450549450547 + }, + { + "current_steps": 1683, + "loss": 2.2483, + "learning_rate": 3.3050487908358084e-07, + "epoch": 2.056166056166056 + }, + { + "current_steps": 1684, + "loss": 2.3522, + "learning_rate": 3.3008061094611795e-07, + "epoch": 2.057387057387057 + }, + { + "current_steps": 1685, + "loss": 2.3982, + "learning_rate": 3.2965634280865507e-07, + "epoch": 2.0586080586080584 + }, + { + "current_steps": 1686, + "loss": 2.4538, + "learning_rate": 3.292320746711922e-07, + "epoch": 2.0598290598290596 + }, + { + "current_steps": 1687, + "loss": 2.3272, + "learning_rate": 3.288078065337293e-07, + "epoch": 2.061050061050061 + }, + { + "current_steps": 1688, + "loss": 1.8018, + "learning_rate": 3.283835383962664e-07, + "epoch": 2.062271062271062 + }, + { + "current_steps": 1689, + "loss": 2.3878, + "learning_rate": 3.2795927025880354e-07, + "epoch": 2.0634920634920633 + }, + { + "current_steps": 1690, + "loss": 2.3278, + "learning_rate": 3.2753500212134065e-07, + "epoch": 2.064713064713065 + }, + { + "current_steps": 1691, + "loss": 2.2975, + "learning_rate": 3.2711073398387777e-07, + "epoch": 2.065934065934066 + }, + { + "current_steps": 1692, + "loss": 2.2096, + "learning_rate": 3.266864658464149e-07, + "epoch": 2.0671550671550674 + }, + { + "current_steps": 1693, + "loss": 2.3675, + "learning_rate": 3.26262197708952e-07, + "epoch": 2.0683760683760686 + }, + { + "current_steps": 1694, + "loss": 2.1432, + "learning_rate": 3.258379295714891e-07, + "epoch": 2.06959706959707 + }, + { + "current_steps": 1695, + "loss": 2.3647, + "learning_rate": 3.2541366143402624e-07, + "epoch": 2.070818070818071 + }, + { + "current_steps": 1696, + "loss": 2.3304, + "learning_rate": 3.2498939329656346e-07, + "epoch": 2.0720390720390722 + }, + { + "current_steps": 1697, + "loss": 2.3849, + "learning_rate": 3.245651251591006e-07, + "epoch": 2.0732600732600734 + }, + { + "current_steps": 1698, + "loss": 2.3479, + "learning_rate": 3.241408570216377e-07, + "epoch": 2.0744810744810747 + }, + { + "current_steps": 1699, + "loss": 2.462, + "learning_rate": 3.237165888841748e-07, + "epoch": 2.075702075702076 + }, + { + "current_steps": 1700, + "loss": 2.1445, + "learning_rate": 3.2329232074671193e-07, + "epoch": 2.076923076923077 + }, + { + "current_steps": 1701, + "loss": 2.3924, + "learning_rate": 3.2286805260924905e-07, + "epoch": 2.0781440781440783 + }, + { + "current_steps": 1702, + "loss": 2.2986, + "learning_rate": 3.2244378447178616e-07, + "epoch": 2.0793650793650795 + }, + { + "current_steps": 1703, + "loss": 2.3417, + "learning_rate": 3.220195163343233e-07, + "epoch": 2.0805860805860807 + }, + { + "current_steps": 1704, + "loss": 2.157, + "learning_rate": 3.215952481968604e-07, + "epoch": 2.081807081807082 + }, + { + "current_steps": 1705, + "loss": 2.1219, + "learning_rate": 3.211709800593975e-07, + "epoch": 2.083028083028083 + }, + { + "current_steps": 1706, + "loss": 2.4021, + "learning_rate": 3.2074671192193463e-07, + "epoch": 2.0842490842490844 + }, + { + "current_steps": 1707, + "loss": 2.3424, + "learning_rate": 3.2032244378447175e-07, + "epoch": 2.0854700854700856 + }, + { + "current_steps": 1708, + "loss": 2.2467, + "learning_rate": 3.1989817564700887e-07, + "epoch": 2.086691086691087 + }, + { + "current_steps": 1709, + "loss": 2.3333, + "learning_rate": 3.19473907509546e-07, + "epoch": 2.087912087912088 + }, + { + "current_steps": 1710, + "loss": 2.2838, + "learning_rate": 3.190496393720831e-07, + "epoch": 2.0891330891330893 + }, + { + "current_steps": 1711, + "loss": 2.2704, + "learning_rate": 3.1862537123462027e-07, + "epoch": 2.0903540903540905 + }, + { + "current_steps": 1712, + "loss": 2.361, + "learning_rate": 3.182011030971574e-07, + "epoch": 2.0915750915750917 + }, + { + "current_steps": 1713, + "loss": 2.3799, + "learning_rate": 3.1777683495969456e-07, + "epoch": 2.092796092796093 + }, + { + "current_steps": 1714, + "loss": 2.1862, + "learning_rate": 3.173525668222317e-07, + "epoch": 2.094017094017094 + }, + { + "current_steps": 1715, + "loss": 2.3589, + "learning_rate": 3.169282986847688e-07, + "epoch": 2.0952380952380953 + }, + { + "current_steps": 1716, + "loss": 2.3416, + "learning_rate": 3.165040305473059e-07, + "epoch": 2.0964590964590966 + }, + { + "current_steps": 1717, + "loss": 2.3856, + "learning_rate": 3.16079762409843e-07, + "epoch": 2.0976800976800978 + }, + { + "current_steps": 1718, + "loss": 2.5146, + "learning_rate": 3.1565549427238014e-07, + "epoch": 2.098901098901099 + }, + { + "current_steps": 1719, + "loss": 2.3937, + "learning_rate": 3.1523122613491726e-07, + "epoch": 2.1001221001221 + }, + { + "current_steps": 1720, + "loss": 2.3759, + "learning_rate": 3.148069579974544e-07, + "epoch": 2.1013431013431014 + }, + { + "current_steps": 1721, + "loss": 2.4381, + "learning_rate": 3.143826898599915e-07, + "epoch": 2.1025641025641026 + }, + { + "current_steps": 1722, + "loss": 2.3556, + "learning_rate": 3.139584217225286e-07, + "epoch": 2.103785103785104 + }, + { + "current_steps": 1723, + "loss": 2.3761, + "learning_rate": 3.1353415358506573e-07, + "epoch": 2.105006105006105 + }, + { + "current_steps": 1724, + "loss": 2.3814, + "learning_rate": 3.1310988544760284e-07, + "epoch": 2.1062271062271063 + }, + { + "current_steps": 1725, + "loss": 2.3548, + "learning_rate": 3.1268561731013996e-07, + "epoch": 2.1074481074481075 + }, + { + "current_steps": 1726, + "loss": 2.3178, + "learning_rate": 3.122613491726771e-07, + "epoch": 2.1086691086691087 + }, + { + "current_steps": 1727, + "loss": 2.3806, + "learning_rate": 3.1183708103521425e-07, + "epoch": 2.10989010989011 + }, + { + "current_steps": 1728, + "loss": 2.2528, + "learning_rate": 3.1141281289775136e-07, + "epoch": 2.111111111111111 + }, + { + "current_steps": 1729, + "loss": 2.3164, + "learning_rate": 3.109885447602885e-07, + "epoch": 2.1123321123321124 + }, + { + "current_steps": 1730, + "loss": 2.4516, + "learning_rate": 3.1056427662282565e-07, + "epoch": 2.1135531135531136 + }, + { + "current_steps": 1731, + "loss": 2.0364, + "learning_rate": 3.1014000848536277e-07, + "epoch": 2.114774114774115 + }, + { + "current_steps": 1732, + "loss": 2.2336, + "learning_rate": 3.097157403478999e-07, + "epoch": 2.115995115995116 + }, + { + "current_steps": 1733, + "loss": 2.5108, + "learning_rate": 3.09291472210437e-07, + "epoch": 2.1172161172161172 + }, + { + "current_steps": 1734, + "loss": 2.3846, + "learning_rate": 3.088672040729741e-07, + "epoch": 2.1184371184371185 + }, + { + "current_steps": 1735, + "loss": 2.4173, + "learning_rate": 3.0844293593551124e-07, + "epoch": 2.1196581196581197 + }, + { + "current_steps": 1736, + "loss": 2.3528, + "learning_rate": 3.0801866779804835e-07, + "epoch": 2.120879120879121 + }, + { + "current_steps": 1737, + "loss": 2.3208, + "learning_rate": 3.0759439966058547e-07, + "epoch": 2.122100122100122 + }, + { + "current_steps": 1738, + "loss": 2.3612, + "learning_rate": 3.071701315231226e-07, + "epoch": 2.1233211233211233 + }, + { + "current_steps": 1739, + "loss": 2.371, + "learning_rate": 3.067458633856597e-07, + "epoch": 2.1245421245421245 + }, + { + "current_steps": 1740, + "loss": 2.3338, + "learning_rate": 3.063215952481968e-07, + "epoch": 2.1257631257631258 + }, + { + "current_steps": 1741, + "loss": 2.2368, + "learning_rate": 3.0589732711073394e-07, + "epoch": 2.126984126984127 + }, + { + "current_steps": 1742, + "loss": 2.4023, + "learning_rate": 3.0547305897327106e-07, + "epoch": 2.128205128205128 + }, + { + "current_steps": 1743, + "loss": 2.28, + "learning_rate": 3.050487908358082e-07, + "epoch": 2.1294261294261294 + }, + { + "current_steps": 1744, + "loss": 1.8878, + "learning_rate": 3.0462452269834534e-07, + "epoch": 2.1306471306471306 + }, + { + "current_steps": 1745, + "loss": 2.1939, + "learning_rate": 3.0420025456088246e-07, + "epoch": 2.131868131868132 + }, + { + "current_steps": 1746, + "loss": 2.2694, + "learning_rate": 3.037759864234196e-07, + "epoch": 2.133089133089133 + }, + { + "current_steps": 1747, + "loss": 2.1704, + "learning_rate": 3.0335171828595675e-07, + "epoch": 2.1343101343101343 + }, + { + "current_steps": 1748, + "loss": 2.323, + "learning_rate": 3.0292745014849386e-07, + "epoch": 2.1355311355311355 + }, + { + "current_steps": 1749, + "loss": 2.3971, + "learning_rate": 3.02503182011031e-07, + "epoch": 2.1367521367521367 + }, + { + "current_steps": 1750, + "loss": 2.3045, + "learning_rate": 3.020789138735681e-07, + "epoch": 2.137973137973138 + }, + { + "current_steps": 1751, + "loss": 2.4356, + "learning_rate": 3.016546457361052e-07, + "epoch": 2.139194139194139 + }, + { + "current_steps": 1752, + "loss": 2.2509, + "learning_rate": 3.0123037759864233e-07, + "epoch": 2.1404151404151404 + }, + { + "current_steps": 1753, + "loss": 2.3071, + "learning_rate": 3.0080610946117945e-07, + "epoch": 2.1416361416361416 + }, + { + "current_steps": 1754, + "loss": 2.3112, + "learning_rate": 3.0038184132371657e-07, + "epoch": 2.142857142857143 + }, + { + "current_steps": 1755, + "loss": 2.3049, + "learning_rate": 2.999575731862537e-07, + "epoch": 2.144078144078144 + }, + { + "current_steps": 1756, + "loss": 2.2896, + "learning_rate": 2.995333050487908e-07, + "epoch": 2.1452991452991452 + }, + { + "current_steps": 1757, + "loss": 1.9477, + "learning_rate": 2.991090369113279e-07, + "epoch": 2.1465201465201464 + }, + { + "current_steps": 1758, + "loss": 2.3702, + "learning_rate": 2.9868476877386503e-07, + "epoch": 2.1477411477411477 + }, + { + "current_steps": 1759, + "loss": 2.1579, + "learning_rate": 2.982605006364022e-07, + "epoch": 2.148962148962149 + }, + { + "current_steps": 1760, + "loss": 2.2503, + "learning_rate": 2.978362324989393e-07, + "epoch": 2.15018315018315 + }, + { + "current_steps": 1761, + "loss": 2.2973, + "learning_rate": 2.9741196436147644e-07, + "epoch": 2.1514041514041513 + }, + { + "current_steps": 1762, + "loss": 2.2992, + "learning_rate": 2.9698769622401355e-07, + "epoch": 2.1526251526251525 + }, + { + "current_steps": 1763, + "loss": 2.4293, + "learning_rate": 2.9656342808655067e-07, + "epoch": 2.1538461538461537 + }, + { + "current_steps": 1764, + "loss": 2.2893, + "learning_rate": 2.9613915994908784e-07, + "epoch": 2.155067155067155 + }, + { + "current_steps": 1765, + "loss": 2.0829, + "learning_rate": 2.9571489181162496e-07, + "epoch": 2.156288156288156 + }, + { + "current_steps": 1766, + "loss": 2.2789, + "learning_rate": 2.952906236741621e-07, + "epoch": 2.1575091575091574 + }, + { + "current_steps": 1767, + "loss": 2.3237, + "learning_rate": 2.948663555366992e-07, + "epoch": 2.1587301587301586 + }, + { + "current_steps": 1768, + "loss": 2.2719, + "learning_rate": 2.944420873992363e-07, + "epoch": 2.15995115995116 + }, + { + "current_steps": 1769, + "loss": 2.3137, + "learning_rate": 2.940178192617734e-07, + "epoch": 2.161172161172161 + }, + { + "current_steps": 1770, + "loss": 2.109, + "learning_rate": 2.9359355112431054e-07, + "epoch": 2.1623931623931623 + }, + { + "current_steps": 1771, + "loss": 2.3177, + "learning_rate": 2.9316928298684766e-07, + "epoch": 2.1636141636141635 + }, + { + "current_steps": 1772, + "loss": 2.3576, + "learning_rate": 2.927450148493848e-07, + "epoch": 2.1648351648351647 + }, + { + "current_steps": 1773, + "loss": 2.2637, + "learning_rate": 2.923207467119219e-07, + "epoch": 2.166056166056166 + }, + { + "current_steps": 1774, + "loss": 2.3942, + "learning_rate": 2.9189647857445906e-07, + "epoch": 2.167277167277167 + }, + { + "current_steps": 1775, + "loss": 2.4059, + "learning_rate": 2.914722104369962e-07, + "epoch": 2.1684981684981683 + }, + { + "current_steps": 1776, + "loss": 2.2588, + "learning_rate": 2.910479422995333e-07, + "epoch": 2.1697191697191696 + }, + { + "current_steps": 1777, + "loss": 2.4706, + "learning_rate": 2.906236741620704e-07, + "epoch": 2.1709401709401708 + }, + { + "current_steps": 1778, + "loss": 2.2937, + "learning_rate": 2.9019940602460753e-07, + "epoch": 2.172161172161172 + }, + { + "current_steps": 1779, + "loss": 2.3001, + "learning_rate": 2.8977513788714465e-07, + "epoch": 2.173382173382173 + }, + { + "current_steps": 1780, + "loss": 2.4129, + "learning_rate": 2.8935086974968177e-07, + "epoch": 2.1746031746031744 + }, + { + "current_steps": 1781, + "loss": 2.3389, + "learning_rate": 2.8892660161221894e-07, + "epoch": 2.1758241758241756 + }, + { + "current_steps": 1782, + "loss": 2.2185, + "learning_rate": 2.8850233347475605e-07, + "epoch": 2.177045177045177 + }, + { + "current_steps": 1783, + "loss": 2.2956, + "learning_rate": 2.8807806533729317e-07, + "epoch": 2.178266178266178 + }, + { + "current_steps": 1784, + "loss": 2.2339, + "learning_rate": 2.876537971998303e-07, + "epoch": 2.1794871794871793 + }, + { + "current_steps": 1785, + "loss": 2.4528, + "learning_rate": 2.872295290623674e-07, + "epoch": 2.1807081807081805 + }, + { + "current_steps": 1786, + "loss": 2.2057, + "learning_rate": 2.868052609249045e-07, + "epoch": 2.1819291819291817 + }, + { + "current_steps": 1787, + "loss": 2.1308, + "learning_rate": 2.8638099278744164e-07, + "epoch": 2.183150183150183 + }, + { + "current_steps": 1788, + "loss": 2.138, + "learning_rate": 2.8595672464997875e-07, + "epoch": 2.1843711843711846 + }, + { + "current_steps": 1789, + "loss": 2.372, + "learning_rate": 2.8553245651251587e-07, + "epoch": 2.185592185592186 + }, + { + "current_steps": 1790, + "loss": 2.3638, + "learning_rate": 2.8510818837505304e-07, + "epoch": 2.186813186813187 + }, + { + "current_steps": 1791, + "loss": 2.2453, + "learning_rate": 2.8468392023759016e-07, + "epoch": 2.1880341880341883 + }, + { + "current_steps": 1792, + "loss": 2.3724, + "learning_rate": 2.842596521001273e-07, + "epoch": 2.1892551892551895 + }, + { + "current_steps": 1793, + "loss": 2.4205, + "learning_rate": 2.838353839626644e-07, + "epoch": 2.1904761904761907 + }, + { + "current_steps": 1794, + "loss": 2.2451, + "learning_rate": 2.834111158252015e-07, + "epoch": 2.191697191697192 + }, + { + "current_steps": 1795, + "loss": 1.829, + "learning_rate": 2.8298684768773863e-07, + "epoch": 2.192918192918193 + }, + { + "current_steps": 1796, + "loss": 2.3138, + "learning_rate": 2.8256257955027574e-07, + "epoch": 2.1941391941391943 + }, + { + "current_steps": 1797, + "loss": 2.2359, + "learning_rate": 2.821383114128129e-07, + "epoch": 2.1953601953601956 + }, + { + "current_steps": 1798, + "loss": 2.4033, + "learning_rate": 2.8171404327535003e-07, + "epoch": 2.1965811965811968 + }, + { + "current_steps": 1799, + "loss": 2.3362, + "learning_rate": 2.8128977513788715e-07, + "epoch": 2.197802197802198 + }, + { + "current_steps": 1800, + "loss": 2.2479, + "learning_rate": 2.8086550700042426e-07, + "epoch": 2.199023199023199 + }, + { + "current_steps": 1801, + "loss": 2.5068, + "learning_rate": 2.804412388629614e-07, + "epoch": 2.2002442002442004 + }, + { + "current_steps": 1802, + "loss": 1.8402, + "learning_rate": 2.800169707254985e-07, + "epoch": 2.2014652014652016 + }, + { + "current_steps": 1803, + "loss": 2.3143, + "learning_rate": 2.795927025880356e-07, + "epoch": 2.202686202686203 + }, + { + "current_steps": 1804, + "loss": 2.301, + "learning_rate": 2.7916843445057273e-07, + "epoch": 2.203907203907204 + }, + { + "current_steps": 1805, + "loss": 2.414, + "learning_rate": 2.7874416631310985e-07, + "epoch": 2.2051282051282053 + }, + { + "current_steps": 1806, + "loss": 2.3364, + "learning_rate": 2.78319898175647e-07, + "epoch": 2.2063492063492065 + }, + { + "current_steps": 1807, + "loss": 2.3248, + "learning_rate": 2.7789563003818414e-07, + "epoch": 2.2075702075702077 + }, + { + "current_steps": 1808, + "loss": 2.2355, + "learning_rate": 2.7747136190072125e-07, + "epoch": 2.208791208791209 + }, + { + "current_steps": 1809, + "loss": 2.3131, + "learning_rate": 2.7704709376325837e-07, + "epoch": 2.21001221001221 + }, + { + "current_steps": 1810, + "loss": 2.2846, + "learning_rate": 2.766228256257955e-07, + "epoch": 2.2112332112332114 + }, + { + "current_steps": 1811, + "loss": 1.9561, + "learning_rate": 2.761985574883326e-07, + "epoch": 2.2124542124542126 + }, + { + "current_steps": 1812, + "loss": 2.2158, + "learning_rate": 2.757742893508697e-07, + "epoch": 2.213675213675214 + }, + { + "current_steps": 1813, + "loss": 2.2917, + "learning_rate": 2.7535002121340684e-07, + "epoch": 2.214896214896215 + }, + { + "current_steps": 1814, + "loss": 2.2301, + "learning_rate": 2.74925753075944e-07, + "epoch": 2.2161172161172162 + }, + { + "current_steps": 1815, + "loss": 2.3379, + "learning_rate": 2.745014849384811e-07, + "epoch": 2.2173382173382175 + }, + { + "current_steps": 1816, + "loss": 2.293, + "learning_rate": 2.7407721680101824e-07, + "epoch": 2.2185592185592187 + }, + { + "current_steps": 1817, + "loss": 2.1916, + "learning_rate": 2.7365294866355536e-07, + "epoch": 2.21978021978022 + }, + { + "current_steps": 1818, + "loss": 2.237, + "learning_rate": 2.732286805260925e-07, + "epoch": 2.221001221001221 + }, + { + "current_steps": 1819, + "loss": 2.3195, + "learning_rate": 2.728044123886296e-07, + "epoch": 2.2222222222222223 + }, + { + "current_steps": 1820, + "loss": 2.3067, + "learning_rate": 2.723801442511667e-07, + "epoch": 2.2234432234432235 + }, + { + "current_steps": 1821, + "loss": 2.1663, + "learning_rate": 2.7195587611370383e-07, + "epoch": 2.2246642246642248 + }, + { + "current_steps": 1822, + "loss": 2.2009, + "learning_rate": 2.71531607976241e-07, + "epoch": 2.225885225885226 + }, + { + "current_steps": 1823, + "loss": 2.2135, + "learning_rate": 2.711073398387781e-07, + "epoch": 2.227106227106227 + }, + { + "current_steps": 1824, + "loss": 1.9954, + "learning_rate": 2.7068307170131523e-07, + "epoch": 2.2283272283272284 + }, + { + "current_steps": 1825, + "loss": 2.3288, + "learning_rate": 2.7025880356385235e-07, + "epoch": 2.2295482295482296 + }, + { + "current_steps": 1826, + "loss": 2.4549, + "learning_rate": 2.6983453542638946e-07, + "epoch": 2.230769230769231 + }, + { + "current_steps": 1827, + "loss": 2.3289, + "learning_rate": 2.694102672889266e-07, + "epoch": 2.231990231990232 + }, + { + "current_steps": 1828, + "loss": 2.3872, + "learning_rate": 2.689859991514637e-07, + "epoch": 2.2332112332112333 + }, + { + "current_steps": 1829, + "loss": 2.2955, + "learning_rate": 2.685617310140008e-07, + "epoch": 2.2344322344322345 + }, + { + "current_steps": 1830, + "loss": 2.5568, + "learning_rate": 2.6813746287653793e-07, + "epoch": 2.2356532356532357 + }, + { + "current_steps": 1831, + "loss": 2.3429, + "learning_rate": 2.677131947390751e-07, + "epoch": 2.236874236874237 + }, + { + "current_steps": 1832, + "loss": 2.2947, + "learning_rate": 2.672889266016122e-07, + "epoch": 2.238095238095238 + }, + { + "current_steps": 1833, + "loss": 2.6994, + "learning_rate": 2.6686465846414934e-07, + "epoch": 2.2393162393162394 + }, + { + "current_steps": 1834, + "loss": 2.0483, + "learning_rate": 2.6644039032668645e-07, + "epoch": 2.2405372405372406 + }, + { + "current_steps": 1835, + "loss": 2.3781, + "learning_rate": 2.6601612218922357e-07, + "epoch": 2.241758241758242 + }, + { + "current_steps": 1836, + "loss": 2.1262, + "learning_rate": 2.655918540517607e-07, + "epoch": 2.242979242979243 + }, + { + "current_steps": 1837, + "loss": 2.3862, + "learning_rate": 2.651675859142978e-07, + "epoch": 2.244200244200244 + }, + { + "current_steps": 1838, + "loss": 2.532, + "learning_rate": 2.64743317776835e-07, + "epoch": 2.2454212454212454 + }, + { + "current_steps": 1839, + "loss": 2.2764, + "learning_rate": 2.643190496393721e-07, + "epoch": 2.2466422466422467 + }, + { + "current_steps": 1840, + "loss": 2.2471, + "learning_rate": 2.638947815019092e-07, + "epoch": 2.247863247863248 + }, + { + "current_steps": 1841, + "loss": 2.2968, + "learning_rate": 2.634705133644463e-07, + "epoch": 2.249084249084249 + }, + { + "current_steps": 1842, + "loss": 2.2871, + "learning_rate": 2.6304624522698344e-07, + "epoch": 2.2503052503052503 + }, + { + "current_steps": 1843, + "loss": 2.2256, + "learning_rate": 2.6262197708952056e-07, + "epoch": 2.2515262515262515 + }, + { + "current_steps": 1844, + "loss": 2.3099, + "learning_rate": 2.621977089520577e-07, + "epoch": 2.2527472527472527 + }, + { + "current_steps": 1845, + "loss": 2.2723, + "learning_rate": 2.617734408145948e-07, + "epoch": 2.253968253968254 + }, + { + "current_steps": 1846, + "loss": 2.3003, + "learning_rate": 2.613491726771319e-07, + "epoch": 2.255189255189255 + }, + { + "current_steps": 1847, + "loss": 2.3059, + "learning_rate": 2.6092490453966903e-07, + "epoch": 2.2564102564102564 + }, + { + "current_steps": 1848, + "loss": 2.4324, + "learning_rate": 2.605006364022062e-07, + "epoch": 2.2576312576312576 + }, + { + "current_steps": 1849, + "loss": 2.2232, + "learning_rate": 2.600763682647433e-07, + "epoch": 2.258852258852259 + }, + { + "current_steps": 1850, + "loss": 2.5185, + "learning_rate": 2.5965210012728043e-07, + "epoch": 2.26007326007326 + }, + { + "current_steps": 1851, + "loss": 2.5252, + "learning_rate": 2.5922783198981755e-07, + "epoch": 2.2612942612942613 + }, + { + "current_steps": 1852, + "loss": 2.4562, + "learning_rate": 2.5880356385235467e-07, + "epoch": 2.2625152625152625 + }, + { + "current_steps": 1853, + "loss": 2.4528, + "learning_rate": 2.5837929571489184e-07, + "epoch": 2.2637362637362637 + }, + { + "current_steps": 1854, + "loss": 2.4561, + "learning_rate": 2.5795502757742895e-07, + "epoch": 2.264957264957265 + }, + { + "current_steps": 1855, + "loss": 2.4952, + "learning_rate": 2.5753075943996607e-07, + "epoch": 2.266178266178266 + }, + { + "current_steps": 1856, + "loss": 2.5522, + "learning_rate": 2.571064913025032e-07, + "epoch": 2.2673992673992673 + }, + { + "current_steps": 1857, + "loss": 2.3199, + "learning_rate": 2.566822231650403e-07, + "epoch": 2.2686202686202686 + }, + { + "current_steps": 1858, + "loss": 2.372, + "learning_rate": 2.562579550275774e-07, + "epoch": 2.2698412698412698 + }, + { + "current_steps": 1859, + "loss": 2.4797, + "learning_rate": 2.5583368689011454e-07, + "epoch": 2.271062271062271 + }, + { + "current_steps": 1860, + "loss": 2.3619, + "learning_rate": 2.5540941875265165e-07, + "epoch": 2.272283272283272 + }, + { + "current_steps": 1861, + "loss": 2.5059, + "learning_rate": 2.5498515061518877e-07, + "epoch": 2.2735042735042734 + }, + { + "current_steps": 1862, + "loss": 2.3848, + "learning_rate": 2.545608824777259e-07, + "epoch": 2.2747252747252746 + }, + { + "current_steps": 1863, + "loss": 2.0877, + "learning_rate": 2.54136614340263e-07, + "epoch": 2.275946275946276 + }, + { + "current_steps": 1864, + "loss": 2.2969, + "learning_rate": 2.537123462028001e-07, + "epoch": 2.277167277167277 + }, + { + "current_steps": 1865, + "loss": 2.3645, + "learning_rate": 2.532880780653373e-07, + "epoch": 2.2783882783882783 + }, + { + "current_steps": 1866, + "loss": 2.32, + "learning_rate": 2.528638099278744e-07, + "epoch": 2.2796092796092795 + }, + { + "current_steps": 1867, + "loss": 2.4709, + "learning_rate": 2.524395417904115e-07, + "epoch": 2.2808302808302807 + }, + { + "current_steps": 1868, + "loss": 2.3791, + "learning_rate": 2.5201527365294864e-07, + "epoch": 2.282051282051282 + }, + { + "current_steps": 1869, + "loss": 2.2379, + "learning_rate": 2.515910055154858e-07, + "epoch": 2.283272283272283 + }, + { + "current_steps": 1870, + "loss": 2.3933, + "learning_rate": 2.5116673737802293e-07, + "epoch": 2.2844932844932844 + }, + { + "current_steps": 1871, + "loss": 2.3183, + "learning_rate": 2.5074246924056005e-07, + "epoch": 2.2857142857142856 + }, + { + "current_steps": 1872, + "loss": 1.9115, + "learning_rate": 2.5031820110309716e-07, + "epoch": 2.286935286935287 + }, + { + "current_steps": 1873, + "loss": 2.3605, + "learning_rate": 2.498939329656343e-07, + "epoch": 2.288156288156288 + }, + { + "current_steps": 1874, + "loss": 2.2883, + "learning_rate": 2.494696648281714e-07, + "epoch": 2.2893772893772892 + }, + { + "current_steps": 1875, + "loss": 2.1858, + "learning_rate": 2.490453966907085e-07, + "epoch": 2.2905982905982905 + }, + { + "current_steps": 1876, + "loss": 2.2856, + "learning_rate": 2.4862112855324563e-07, + "epoch": 2.2918192918192917 + }, + { + "current_steps": 1877, + "loss": 2.2716, + "learning_rate": 2.481968604157828e-07, + "epoch": 2.293040293040293 + }, + { + "current_steps": 1878, + "loss": 2.2674, + "learning_rate": 2.477725922783199e-07, + "epoch": 2.294261294261294 + }, + { + "current_steps": 1879, + "loss": 2.5514, + "learning_rate": 2.4734832414085704e-07, + "epoch": 2.2954822954822953 + }, + { + "current_steps": 1880, + "loss": 2.1754, + "learning_rate": 2.4692405600339415e-07, + "epoch": 2.2967032967032965 + }, + { + "current_steps": 1881, + "loss": 2.3442, + "learning_rate": 2.4649978786593127e-07, + "epoch": 2.2979242979242978 + }, + { + "current_steps": 1882, + "loss": 2.281, + "learning_rate": 2.460755197284684e-07, + "epoch": 2.299145299145299 + }, + { + "current_steps": 1883, + "loss": 2.2516, + "learning_rate": 2.456512515910055e-07, + "epoch": 2.3003663003663 + }, + { + "current_steps": 1884, + "loss": 2.2985, + "learning_rate": 2.452269834535426e-07, + "epoch": 2.3015873015873014 + }, + { + "current_steps": 1885, + "loss": 2.5231, + "learning_rate": 2.4480271531607974e-07, + "epoch": 2.3028083028083026 + }, + { + "current_steps": 1886, + "loss": 1.9813, + "learning_rate": 2.443784471786169e-07, + "epoch": 2.304029304029304 + }, + { + "current_steps": 1887, + "loss": 2.426, + "learning_rate": 2.43954179041154e-07, + "epoch": 2.305250305250305 + }, + { + "current_steps": 1888, + "loss": 2.0312, + "learning_rate": 2.4352991090369114e-07, + "epoch": 2.3064713064713063 + }, + { + "current_steps": 1889, + "loss": 1.7675, + "learning_rate": 2.4310564276622826e-07, + "epoch": 2.3076923076923075 + }, + { + "current_steps": 1890, + "loss": 2.2756, + "learning_rate": 2.426813746287654e-07, + "epoch": 2.3089133089133087 + }, + { + "current_steps": 1891, + "loss": 2.1411, + "learning_rate": 2.422571064913025e-07, + "epoch": 2.31013431013431 + }, + { + "current_steps": 1892, + "loss": 2.42, + "learning_rate": 2.418328383538396e-07, + "epoch": 2.311355311355311 + }, + { + "current_steps": 1893, + "loss": 2.3417, + "learning_rate": 2.4140857021637673e-07, + "epoch": 2.3125763125763124 + }, + { + "current_steps": 1894, + "loss": 2.3645, + "learning_rate": 2.409843020789139e-07, + "epoch": 2.3137973137973136 + }, + { + "current_steps": 1895, + "loss": 2.3523, + "learning_rate": 2.40560033941451e-07, + "epoch": 2.315018315018315 + }, + { + "current_steps": 1896, + "loss": 2.3468, + "learning_rate": 2.4013576580398813e-07, + "epoch": 2.316239316239316 + }, + { + "current_steps": 1897, + "loss": 2.4445, + "learning_rate": 2.3971149766652525e-07, + "epoch": 2.317460317460317 + }, + { + "current_steps": 1898, + "loss": 2.3154, + "learning_rate": 2.3928722952906236e-07, + "epoch": 2.3186813186813184 + }, + { + "current_steps": 1899, + "loss": 2.4082, + "learning_rate": 2.388629613915995e-07, + "epoch": 2.3199023199023197 + }, + { + "current_steps": 1900, + "loss": 2.3034, + "learning_rate": 2.384386932541366e-07, + "epoch": 2.3211233211233213 + }, + { + "current_steps": 1901, + "loss": 2.3492, + "learning_rate": 2.3801442511667372e-07, + "epoch": 2.3223443223443225 + }, + { + "current_steps": 1902, + "loss": 2.3431, + "learning_rate": 2.3759015697921083e-07, + "epoch": 2.3235653235653237 + }, + { + "current_steps": 1903, + "loss": 2.3176, + "learning_rate": 2.3716588884174798e-07, + "epoch": 2.324786324786325 + }, + { + "current_steps": 1904, + "loss": 2.4006, + "learning_rate": 2.367416207042851e-07, + "epoch": 2.326007326007326 + }, + { + "current_steps": 1905, + "loss": 2.2698, + "learning_rate": 2.3631735256682224e-07, + "epoch": 2.3272283272283274 + }, + { + "current_steps": 1906, + "loss": 1.8629, + "learning_rate": 2.3589308442935935e-07, + "epoch": 2.3284493284493286 + }, + { + "current_steps": 1907, + "loss": 2.2455, + "learning_rate": 2.3546881629189647e-07, + "epoch": 2.32967032967033 + }, + { + "current_steps": 1908, + "loss": 2.2705, + "learning_rate": 2.350445481544336e-07, + "epoch": 2.330891330891331 + }, + { + "current_steps": 1909, + "loss": 2.2558, + "learning_rate": 2.346202800169707e-07, + "epoch": 2.3321123321123323 + }, + { + "current_steps": 1910, + "loss": 2.0813, + "learning_rate": 2.3419601187950782e-07, + "epoch": 2.3333333333333335 + }, + { + "current_steps": 1911, + "loss": 2.4157, + "learning_rate": 2.3377174374204497e-07, + "epoch": 2.3345543345543347 + }, + { + "current_steps": 1912, + "loss": 2.32, + "learning_rate": 2.3334747560458208e-07, + "epoch": 2.335775335775336 + }, + { + "current_steps": 1913, + "loss": 1.853, + "learning_rate": 2.3292320746711923e-07, + "epoch": 2.336996336996337 + }, + { + "current_steps": 1914, + "loss": 2.4771, + "learning_rate": 2.3249893932965634e-07, + "epoch": 2.3382173382173383 + }, + { + "current_steps": 1915, + "loss": 2.3492, + "learning_rate": 2.3207467119219346e-07, + "epoch": 2.3394383394383396 + }, + { + "current_steps": 1916, + "loss": 2.1293, + "learning_rate": 2.3165040305473058e-07, + "epoch": 2.340659340659341 + }, + { + "current_steps": 1917, + "loss": 2.3507, + "learning_rate": 2.312261349172677e-07, + "epoch": 2.341880341880342 + }, + { + "current_steps": 1918, + "loss": 2.4409, + "learning_rate": 2.308018667798048e-07, + "epoch": 2.343101343101343 + }, + { + "current_steps": 1919, + "loss": 2.3341, + "learning_rate": 2.3037759864234193e-07, + "epoch": 2.3443223443223444 + }, + { + "current_steps": 1920, + "loss": 2.2181, + "learning_rate": 2.2995333050487907e-07, + "epoch": 2.3455433455433456 + }, + { + "current_steps": 1921, + "loss": 2.3579, + "learning_rate": 2.2952906236741621e-07, + "epoch": 2.346764346764347 + }, + { + "current_steps": 1922, + "loss": 2.2909, + "learning_rate": 2.2910479422995333e-07, + "epoch": 2.347985347985348 + }, + { + "current_steps": 1923, + "loss": 2.3311, + "learning_rate": 2.2868052609249045e-07, + "epoch": 2.3492063492063493 + }, + { + "current_steps": 1924, + "loss": 2.2818, + "learning_rate": 2.2825625795502757e-07, + "epoch": 2.3504273504273505 + }, + { + "current_steps": 1925, + "loss": 2.3405, + "learning_rate": 2.2783198981756468e-07, + "epoch": 2.3516483516483517 + }, + { + "current_steps": 1926, + "loss": 2.2631, + "learning_rate": 2.274077216801018e-07, + "epoch": 2.352869352869353 + }, + { + "current_steps": 1927, + "loss": 2.4175, + "learning_rate": 2.2698345354263892e-07, + "epoch": 2.354090354090354 + }, + { + "current_steps": 1928, + "loss": 2.5585, + "learning_rate": 2.2655918540517609e-07, + "epoch": 2.3553113553113554 + }, + { + "current_steps": 1929, + "loss": 2.3585, + "learning_rate": 2.261349172677132e-07, + "epoch": 2.3565323565323566 + }, + { + "current_steps": 1930, + "loss": 2.3884, + "learning_rate": 2.2571064913025032e-07, + "epoch": 2.357753357753358 + }, + { + "current_steps": 1931, + "loss": 2.2091, + "learning_rate": 2.2528638099278744e-07, + "epoch": 2.358974358974359 + }, + { + "current_steps": 1932, + "loss": 2.3751, + "learning_rate": 2.2486211285532455e-07, + "epoch": 2.3601953601953602 + }, + { + "current_steps": 1933, + "loss": 2.3459, + "learning_rate": 2.2443784471786167e-07, + "epoch": 2.3614163614163615 + }, + { + "current_steps": 1934, + "loss": 2.3961, + "learning_rate": 2.240135765803988e-07, + "epoch": 2.3626373626373627 + }, + { + "current_steps": 1935, + "loss": 1.8716, + "learning_rate": 2.235893084429359e-07, + "epoch": 2.363858363858364 + }, + { + "current_steps": 1936, + "loss": 2.1698, + "learning_rate": 2.2316504030547308e-07, + "epoch": 2.365079365079365 + }, + { + "current_steps": 1937, + "loss": 2.2989, + "learning_rate": 2.227407721680102e-07, + "epoch": 2.3663003663003663 + }, + { + "current_steps": 1938, + "loss": 2.345, + "learning_rate": 2.223165040305473e-07, + "epoch": 2.3675213675213675 + }, + { + "current_steps": 1939, + "loss": 2.3008, + "learning_rate": 2.2189223589308443e-07, + "epoch": 2.3687423687423688 + }, + { + "current_steps": 1940, + "loss": 2.165, + "learning_rate": 2.2146796775562154e-07, + "epoch": 2.36996336996337 + }, + { + "current_steps": 1941, + "loss": 2.2777, + "learning_rate": 2.2104369961815866e-07, + "epoch": 2.371184371184371 + }, + { + "current_steps": 1942, + "loss": 2.3631, + "learning_rate": 2.2061943148069578e-07, + "epoch": 2.3724053724053724 + }, + { + "current_steps": 1943, + "loss": 2.1453, + "learning_rate": 2.201951633432329e-07, + "epoch": 2.3736263736263736 + }, + { + "current_steps": 1944, + "loss": 2.4456, + "learning_rate": 2.1977089520577e-07, + "epoch": 2.374847374847375 + }, + { + "current_steps": 1945, + "loss": 2.3044, + "learning_rate": 2.1934662706830718e-07, + "epoch": 2.376068376068376 + }, + { + "current_steps": 1946, + "loss": 2.0171, + "learning_rate": 2.189223589308443e-07, + "epoch": 2.3772893772893773 + }, + { + "current_steps": 1947, + "loss": 2.3619, + "learning_rate": 2.1849809079338141e-07, + "epoch": 2.3785103785103785 + }, + { + "current_steps": 1948, + "loss": 2.5325, + "learning_rate": 2.1807382265591853e-07, + "epoch": 2.3797313797313797 + }, + { + "current_steps": 1949, + "loss": 2.1639, + "learning_rate": 2.1764955451845565e-07, + "epoch": 2.380952380952381 + }, + { + "current_steps": 1950, + "loss": 2.2162, + "learning_rate": 2.1722528638099277e-07, + "epoch": 2.382173382173382 + }, + { + "current_steps": 1951, + "loss": 2.2121, + "learning_rate": 2.1680101824352988e-07, + "epoch": 2.3833943833943834 + }, + { + "current_steps": 1952, + "loss": 2.3775, + "learning_rate": 2.16376750106067e-07, + "epoch": 2.3846153846153846 + }, + { + "current_steps": 1953, + "loss": 2.3236, + "learning_rate": 2.1595248196860417e-07, + "epoch": 2.385836385836386 + }, + { + "current_steps": 1954, + "loss": 2.3717, + "learning_rate": 2.1552821383114129e-07, + "epoch": 2.387057387057387 + }, + { + "current_steps": 1955, + "loss": 1.8219, + "learning_rate": 2.151039456936784e-07, + "epoch": 2.3882783882783882 + }, + { + "current_steps": 1956, + "loss": 2.3973, + "learning_rate": 2.1467967755621552e-07, + "epoch": 2.3894993894993894 + }, + { + "current_steps": 1957, + "loss": 2.2745, + "learning_rate": 2.1425540941875264e-07, + "epoch": 2.3907203907203907 + }, + { + "current_steps": 1958, + "loss": 2.5568, + "learning_rate": 2.1383114128128975e-07, + "epoch": 2.391941391941392 + }, + { + "current_steps": 1959, + "loss": 2.0787, + "learning_rate": 2.1340687314382687e-07, + "epoch": 2.393162393162393 + }, + { + "current_steps": 1960, + "loss": 2.3355, + "learning_rate": 2.1298260500636402e-07, + "epoch": 2.3943833943833943 + }, + { + "current_steps": 1961, + "loss": 2.2804, + "learning_rate": 2.1255833686890113e-07, + "epoch": 2.3956043956043955 + }, + { + "current_steps": 1962, + "loss": 2.3236, + "learning_rate": 2.1213406873143828e-07, + "epoch": 2.3968253968253967 + }, + { + "current_steps": 1963, + "loss": 2.3031, + "learning_rate": 2.117098005939754e-07, + "epoch": 2.398046398046398 + }, + { + "current_steps": 1964, + "loss": 2.3209, + "learning_rate": 2.112855324565125e-07, + "epoch": 2.399267399267399 + }, + { + "current_steps": 1965, + "loss": 2.2853, + "learning_rate": 2.1086126431904963e-07, + "epoch": 2.4004884004884004 + }, + { + "current_steps": 1966, + "loss": 2.3409, + "learning_rate": 2.1043699618158674e-07, + "epoch": 2.4017094017094016 + }, + { + "current_steps": 1967, + "loss": 2.2827, + "learning_rate": 2.1001272804412386e-07, + "epoch": 2.402930402930403 + }, + { + "current_steps": 1968, + "loss": 2.5555, + "learning_rate": 2.09588459906661e-07, + "epoch": 2.404151404151404 + }, + { + "current_steps": 1969, + "loss": 2.3965, + "learning_rate": 2.0916419176919812e-07, + "epoch": 2.4053724053724053 + }, + { + "current_steps": 1970, + "loss": 2.3694, + "learning_rate": 2.0873992363173526e-07, + "epoch": 2.4065934065934065 + }, + { + "current_steps": 1971, + "loss": 2.4197, + "learning_rate": 2.0831565549427238e-07, + "epoch": 2.4078144078144077 + }, + { + "current_steps": 1972, + "loss": 2.4939, + "learning_rate": 2.078913873568095e-07, + "epoch": 2.409035409035409 + }, + { + "current_steps": 1973, + "loss": 2.3286, + "learning_rate": 2.0746711921934662e-07, + "epoch": 2.41025641025641 + }, + { + "current_steps": 1974, + "loss": 2.253, + "learning_rate": 2.0704285108188373e-07, + "epoch": 2.4114774114774113 + }, + { + "current_steps": 1975, + "loss": 2.4038, + "learning_rate": 2.0661858294442085e-07, + "epoch": 2.4126984126984126 + }, + { + "current_steps": 1976, + "loss": 2.3929, + "learning_rate": 2.06194314806958e-07, + "epoch": 2.413919413919414 + }, + { + "current_steps": 1977, + "loss": 2.2533, + "learning_rate": 2.057700466694951e-07, + "epoch": 2.415140415140415 + }, + { + "current_steps": 1978, + "loss": 2.2521, + "learning_rate": 2.0534577853203225e-07, + "epoch": 2.416361416361416 + }, + { + "current_steps": 1979, + "loss": 2.1968, + "learning_rate": 2.0492151039456937e-07, + "epoch": 2.4175824175824174 + }, + { + "current_steps": 1980, + "loss": 2.2948, + "learning_rate": 2.044972422571065e-07, + "epoch": 2.4188034188034186 + }, + { + "current_steps": 1981, + "loss": 2.3019, + "learning_rate": 2.040729741196436e-07, + "epoch": 2.42002442002442 + }, + { + "current_steps": 1982, + "loss": 2.3748, + "learning_rate": 2.0364870598218072e-07, + "epoch": 2.421245421245421 + }, + { + "current_steps": 1983, + "loss": 2.4876, + "learning_rate": 2.0322443784471784e-07, + "epoch": 2.4224664224664223 + }, + { + "current_steps": 1984, + "loss": 2.4283, + "learning_rate": 2.0280016970725498e-07, + "epoch": 2.4236874236874235 + }, + { + "current_steps": 1985, + "loss": 2.239, + "learning_rate": 2.023759015697921e-07, + "epoch": 2.4249084249084247 + }, + { + "current_steps": 1986, + "loss": 2.3602, + "learning_rate": 2.0195163343232922e-07, + "epoch": 2.426129426129426 + }, + { + "current_steps": 1987, + "loss": 2.3085, + "learning_rate": 2.0152736529486636e-07, + "epoch": 2.427350427350427 + }, + { + "current_steps": 1988, + "loss": 2.2905, + "learning_rate": 2.0110309715740348e-07, + "epoch": 2.4285714285714284 + }, + { + "current_steps": 1989, + "loss": 2.2281, + "learning_rate": 2.006788290199406e-07, + "epoch": 2.42979242979243 + }, + { + "current_steps": 1990, + "loss": 2.2252, + "learning_rate": 2.002545608824777e-07, + "epoch": 2.4310134310134313 + }, + { + "current_steps": 1991, + "loss": 2.282, + "learning_rate": 1.9983029274501483e-07, + "epoch": 2.4322344322344325 + }, + { + "current_steps": 1992, + "loss": 2.3771, + "learning_rate": 1.9940602460755197e-07, + "epoch": 2.4334554334554337 + }, + { + "current_steps": 1993, + "loss": 2.2417, + "learning_rate": 1.989817564700891e-07, + "epoch": 2.434676434676435 + }, + { + "current_steps": 1994, + "loss": 2.3672, + "learning_rate": 1.985574883326262e-07, + "epoch": 2.435897435897436 + }, + { + "current_steps": 1995, + "loss": 2.3645, + "learning_rate": 1.9813322019516335e-07, + "epoch": 2.4371184371184373 + }, + { + "current_steps": 1996, + "loss": 2.3234, + "learning_rate": 1.9770895205770047e-07, + "epoch": 2.4383394383394386 + }, + { + "current_steps": 1997, + "loss": 2.3066, + "learning_rate": 1.9728468392023758e-07, + "epoch": 2.4395604395604398 + }, + { + "current_steps": 1998, + "loss": 2.5407, + "learning_rate": 1.968604157827747e-07, + "epoch": 2.440781440781441 + }, + { + "current_steps": 1999, + "loss": 2.2712, + "learning_rate": 1.9643614764531182e-07, + "epoch": 2.442002442002442 + }, + { + "current_steps": 2000, + "loss": 2.2701, + "learning_rate": 1.9601187950784896e-07, + "epoch": 2.4432234432234434 + }, + { + "current_steps": 2001, + "loss": 2.5337, + "learning_rate": 1.9558761137038608e-07, + "epoch": 2.4444444444444446 + }, + { + "current_steps": 2002, + "loss": 2.355, + "learning_rate": 1.951633432329232e-07, + "epoch": 2.445665445665446 + }, + { + "current_steps": 2003, + "loss": 2.3893, + "learning_rate": 1.947390750954603e-07, + "epoch": 2.446886446886447 + }, + { + "current_steps": 2004, + "loss": 1.7646, + "learning_rate": 1.9431480695799745e-07, + "epoch": 2.4481074481074483 + }, + { + "current_steps": 2005, + "loss": 2.189, + "learning_rate": 1.9389053882053457e-07, + "epoch": 2.4493284493284495 + }, + { + "current_steps": 2006, + "loss": 2.2251, + "learning_rate": 1.934662706830717e-07, + "epoch": 2.4505494505494507 + }, + { + "current_steps": 2007, + "loss": 2.2975, + "learning_rate": 1.930420025456088e-07, + "epoch": 2.451770451770452 + }, + { + "current_steps": 2008, + "loss": 2.3376, + "learning_rate": 1.9261773440814595e-07, + "epoch": 2.452991452991453 + }, + { + "current_steps": 2009, + "loss": 2.244, + "learning_rate": 1.9219346627068307e-07, + "epoch": 2.4542124542124544 + }, + { + "current_steps": 2010, + "loss": 2.3259, + "learning_rate": 1.9176919813322018e-07, + "epoch": 2.4554334554334556 + }, + { + "current_steps": 2011, + "loss": 2.6229, + "learning_rate": 1.913449299957573e-07, + "epoch": 2.456654456654457 + }, + { + "current_steps": 2012, + "loss": 2.2022, + "learning_rate": 1.9092066185829444e-07, + "epoch": 2.457875457875458 + }, + { + "current_steps": 2013, + "loss": 2.3301, + "learning_rate": 1.9049639372083156e-07, + "epoch": 2.4590964590964592 + }, + { + "current_steps": 2014, + "loss": 2.2706, + "learning_rate": 1.9007212558336868e-07, + "epoch": 2.4603174603174605 + }, + { + "current_steps": 2015, + "loss": 2.2856, + "learning_rate": 1.896478574459058e-07, + "epoch": 2.4615384615384617 + }, + { + "current_steps": 2016, + "loss": 2.1094, + "learning_rate": 1.8922358930844294e-07, + "epoch": 2.462759462759463 + }, + { + "current_steps": 2017, + "loss": 2.37, + "learning_rate": 1.8879932117098005e-07, + "epoch": 2.463980463980464 + }, + { + "current_steps": 2018, + "loss": 2.3628, + "learning_rate": 1.8837505303351717e-07, + "epoch": 2.4652014652014653 + }, + { + "current_steps": 2019, + "loss": 2.3713, + "learning_rate": 1.879507848960543e-07, + "epoch": 2.4664224664224665 + }, + { + "current_steps": 2020, + "loss": 2.4334, + "learning_rate": 1.875265167585914e-07, + "epoch": 2.4676434676434678 + }, + { + "current_steps": 2021, + "loss": 2.4291, + "learning_rate": 1.8710224862112855e-07, + "epoch": 2.468864468864469 + }, + { + "current_steps": 2022, + "loss": 2.2715, + "learning_rate": 1.8667798048366567e-07, + "epoch": 2.47008547008547 + }, + { + "current_steps": 2023, + "loss": 2.3352, + "learning_rate": 1.862537123462028e-07, + "epoch": 2.4713064713064714 + }, + { + "current_steps": 2024, + "loss": 2.373, + "learning_rate": 1.8582944420873993e-07, + "epoch": 2.4725274725274726 + }, + { + "current_steps": 2025, + "loss": 2.151, + "learning_rate": 1.8540517607127704e-07, + "epoch": 2.473748473748474 + }, + { + "current_steps": 2026, + "loss": 1.9271, + "learning_rate": 1.8498090793381416e-07, + "epoch": 2.474969474969475 + }, + { + "current_steps": 2027, + "loss": 2.5252, + "learning_rate": 1.8455663979635128e-07, + "epoch": 2.4761904761904763 + }, + { + "current_steps": 2028, + "loss": 1.7795, + "learning_rate": 1.841323716588884e-07, + "epoch": 2.4774114774114775 + }, + { + "current_steps": 2029, + "loss": 2.2336, + "learning_rate": 1.8370810352142554e-07, + "epoch": 2.4786324786324787 + }, + { + "current_steps": 2030, + "loss": 1.8011, + "learning_rate": 1.8328383538396265e-07, + "epoch": 2.47985347985348 + }, + { + "current_steps": 2031, + "loss": 2.274, + "learning_rate": 1.828595672464998e-07, + "epoch": 2.481074481074481 + }, + { + "current_steps": 2032, + "loss": 2.3717, + "learning_rate": 1.8243529910903691e-07, + "epoch": 2.4822954822954824 + }, + { + "current_steps": 2033, + "loss": 2.4788, + "learning_rate": 1.8201103097157403e-07, + "epoch": 2.4835164835164836 + }, + { + "current_steps": 2034, + "loss": 2.4092, + "learning_rate": 1.8158676283411115e-07, + "epoch": 2.484737484737485 + }, + { + "current_steps": 2035, + "loss": 2.2434, + "learning_rate": 1.8116249469664827e-07, + "epoch": 2.485958485958486 + }, + { + "current_steps": 2036, + "loss": 2.1462, + "learning_rate": 1.8073822655918538e-07, + "epoch": 2.4871794871794872 + }, + { + "current_steps": 2037, + "loss": 2.2591, + "learning_rate": 1.8031395842172253e-07, + "epoch": 2.4884004884004884 + }, + { + "current_steps": 2038, + "loss": 2.1766, + "learning_rate": 1.7988969028425964e-07, + "epoch": 2.4896214896214897 + }, + { + "current_steps": 2039, + "loss": 2.3852, + "learning_rate": 1.794654221467968e-07, + "epoch": 2.490842490842491 + }, + { + "current_steps": 2040, + "loss": 2.3128, + "learning_rate": 1.790411540093339e-07, + "epoch": 2.492063492063492 + }, + { + "current_steps": 2041, + "loss": 2.2114, + "learning_rate": 1.7861688587187102e-07, + "epoch": 2.4932844932844933 + }, + { + "current_steps": 2042, + "loss": 2.2721, + "learning_rate": 1.7819261773440814e-07, + "epoch": 2.4945054945054945 + }, + { + "current_steps": 2043, + "loss": 2.233, + "learning_rate": 1.7776834959694525e-07, + "epoch": 2.4957264957264957 + }, + { + "current_steps": 2044, + "loss": 2.173, + "learning_rate": 1.7734408145948237e-07, + "epoch": 2.496947496947497 + }, + { + "current_steps": 2045, + "loss": 2.4484, + "learning_rate": 1.769198133220195e-07, + "epoch": 2.498168498168498 + }, + { + "current_steps": 2046, + "loss": 2.3147, + "learning_rate": 1.7649554518455663e-07, + "epoch": 2.4993894993894994 + }, + { + "current_steps": 2047, + "loss": 2.3854, + "learning_rate": 1.7607127704709378e-07, + "epoch": 2.5006105006105006 + }, + { + "current_steps": 2048, + "loss": 2.3446, + "learning_rate": 1.756470089096309e-07, + "epoch": 2.501831501831502 + }, + { + "current_steps": 2049, + "loss": 2.2997, + "learning_rate": 1.75222740772168e-07, + "epoch": 2.503052503052503 + }, + { + "current_steps": 2050, + "loss": 2.3197, + "learning_rate": 1.7479847263470513e-07, + "epoch": 2.5042735042735043 + }, + { + "current_steps": 2051, + "loss": 2.1818, + "learning_rate": 1.7437420449724224e-07, + "epoch": 2.5054945054945055 + }, + { + "current_steps": 2052, + "loss": 2.1457, + "learning_rate": 1.7394993635977936e-07, + "epoch": 2.5067155067155067 + }, + { + "current_steps": 2053, + "loss": 2.4051, + "learning_rate": 1.7352566822231648e-07, + "epoch": 2.507936507936508 + }, + { + "current_steps": 2054, + "loss": 2.3395, + "learning_rate": 1.7310140008485362e-07, + "epoch": 2.509157509157509 + }, + { + "current_steps": 2055, + "loss": 2.2293, + "learning_rate": 1.7267713194739076e-07, + "epoch": 2.5103785103785103 + }, + { + "current_steps": 2056, + "loss": 2.2245, + "learning_rate": 1.7225286380992788e-07, + "epoch": 2.5115995115995116 + }, + { + "current_steps": 2057, + "loss": 2.308, + "learning_rate": 1.71828595672465e-07, + "epoch": 2.5128205128205128 + }, + { + "current_steps": 2058, + "loss": 2.4403, + "learning_rate": 1.7140432753500212e-07, + "epoch": 2.514041514041514 + }, + { + "current_steps": 2059, + "loss": 2.2555, + "learning_rate": 1.7098005939753923e-07, + "epoch": 2.515262515262515 + }, + { + "current_steps": 2060, + "loss": 2.4808, + "learning_rate": 1.7055579126007635e-07, + "epoch": 2.5164835164835164 + }, + { + "current_steps": 2061, + "loss": 2.2379, + "learning_rate": 1.7013152312261347e-07, + "epoch": 2.5177045177045176 + }, + { + "current_steps": 2062, + "loss": 2.3881, + "learning_rate": 1.6970725498515058e-07, + "epoch": 2.518925518925519 + }, + { + "current_steps": 2063, + "loss": 2.2734, + "learning_rate": 1.6928298684768775e-07, + "epoch": 2.52014652014652 + }, + { + "current_steps": 2064, + "loss": 2.2963, + "learning_rate": 1.6885871871022487e-07, + "epoch": 2.5213675213675213 + }, + { + "current_steps": 2065, + "loss": 2.4179, + "learning_rate": 1.68434450572762e-07, + "epoch": 2.5225885225885225 + }, + { + "current_steps": 2066, + "loss": 2.4057, + "learning_rate": 1.680101824352991e-07, + "epoch": 2.5238095238095237 + }, + { + "current_steps": 2067, + "loss": 2.2904, + "learning_rate": 1.6758591429783622e-07, + "epoch": 2.525030525030525 + }, + { + "current_steps": 2068, + "loss": 2.1994, + "learning_rate": 1.6716164616037334e-07, + "epoch": 2.526251526251526 + }, + { + "current_steps": 2069, + "loss": 2.2846, + "learning_rate": 1.6673737802291046e-07, + "epoch": 2.5274725274725274 + }, + { + "current_steps": 2070, + "loss": 2.414, + "learning_rate": 1.6631310988544757e-07, + "epoch": 2.5286935286935286 + }, + { + "current_steps": 2071, + "loss": 2.2387, + "learning_rate": 1.6588884174798474e-07, + "epoch": 2.52991452991453 + }, + { + "current_steps": 2072, + "loss": 2.4206, + "learning_rate": 1.6546457361052186e-07, + "epoch": 2.531135531135531 + }, + { + "current_steps": 2073, + "loss": 2.3498, + "learning_rate": 1.6504030547305898e-07, + "epoch": 2.5323565323565322 + }, + { + "current_steps": 2074, + "loss": 2.388, + "learning_rate": 1.646160373355961e-07, + "epoch": 2.5335775335775335 + }, + { + "current_steps": 2075, + "loss": 2.311, + "learning_rate": 1.641917691981332e-07, + "epoch": 2.5347985347985347 + }, + { + "current_steps": 2076, + "loss": 2.4524, + "learning_rate": 1.6376750106067033e-07, + "epoch": 2.536019536019536 + }, + { + "current_steps": 2077, + "loss": 2.1886, + "learning_rate": 1.6334323292320744e-07, + "epoch": 2.537240537240537 + }, + { + "current_steps": 2078, + "loss": 2.3037, + "learning_rate": 1.6291896478574456e-07, + "epoch": 2.5384615384615383 + }, + { + "current_steps": 2079, + "loss": 2.2174, + "learning_rate": 1.6249469664828173e-07, + "epoch": 2.5396825396825395 + }, + { + "current_steps": 2080, + "loss": 2.1991, + "learning_rate": 1.6207042851081885e-07, + "epoch": 2.5409035409035408 + }, + { + "current_steps": 2081, + "loss": 1.8714, + "learning_rate": 1.6164616037335597e-07, + "epoch": 2.542124542124542 + }, + { + "current_steps": 2082, + "loss": 2.3357, + "learning_rate": 1.6122189223589308e-07, + "epoch": 2.543345543345543 + }, + { + "current_steps": 2083, + "loss": 2.2344, + "learning_rate": 1.607976240984302e-07, + "epoch": 2.5445665445665444 + }, + { + "current_steps": 2084, + "loss": 2.5011, + "learning_rate": 1.6037335596096732e-07, + "epoch": 2.5457875457875456 + }, + { + "current_steps": 2085, + "loss": 2.2071, + "learning_rate": 1.5994908782350443e-07, + "epoch": 2.547008547008547 + }, + { + "current_steps": 2086, + "loss": 2.5587, + "learning_rate": 1.5952481968604155e-07, + "epoch": 2.548229548229548 + }, + { + "current_steps": 2087, + "loss": 2.2655, + "learning_rate": 1.591005515485787e-07, + "epoch": 2.5494505494505493 + }, + { + "current_steps": 2088, + "loss": 2.3071, + "learning_rate": 1.5867628341111584e-07, + "epoch": 2.5506715506715505 + }, + { + "current_steps": 2089, + "loss": 2.2836, + "learning_rate": 1.5825201527365295e-07, + "epoch": 2.5518925518925517 + }, + { + "current_steps": 2090, + "loss": 2.3376, + "learning_rate": 1.5782774713619007e-07, + "epoch": 2.553113553113553 + }, + { + "current_steps": 2091, + "loss": 2.3765, + "learning_rate": 1.574034789987272e-07, + "epoch": 2.554334554334554 + }, + { + "current_steps": 2092, + "loss": 2.3, + "learning_rate": 1.569792108612643e-07, + "epoch": 2.5555555555555554 + }, + { + "current_steps": 2093, + "loss": 2.6804, + "learning_rate": 1.5655494272380142e-07, + "epoch": 2.5567765567765566 + }, + { + "current_steps": 2094, + "loss": 2.3521, + "learning_rate": 1.5613067458633854e-07, + "epoch": 2.557997557997558 + }, + { + "current_steps": 2095, + "loss": 2.2196, + "learning_rate": 1.5570640644887568e-07, + "epoch": 2.559218559218559 + }, + { + "current_steps": 2096, + "loss": 2.4008, + "learning_rate": 1.5528213831141283e-07, + "epoch": 2.5604395604395602 + }, + { + "current_steps": 2097, + "loss": 2.2789, + "learning_rate": 1.5485787017394994e-07, + "epoch": 2.5616605616605614 + }, + { + "current_steps": 2098, + "loss": 2.2195, + "learning_rate": 1.5443360203648706e-07, + "epoch": 2.5628815628815627 + }, + { + "current_steps": 2099, + "loss": 2.2049, + "learning_rate": 1.5400933389902418e-07, + "epoch": 2.564102564102564 + }, + { + "current_steps": 2100, + "loss": 2.2153, + "learning_rate": 1.535850657615613e-07, + "epoch": 2.565323565323565 + }, + { + "current_steps": 2101, + "loss": 2.3382, + "learning_rate": 1.531607976240984e-07, + "epoch": 2.5665445665445663 + }, + { + "current_steps": 2102, + "loss": 2.2611, + "learning_rate": 1.5273652948663553e-07, + "epoch": 2.5677655677655675 + }, + { + "current_steps": 2103, + "loss": 2.3056, + "learning_rate": 1.5231226134917267e-07, + "epoch": 2.5689865689865687 + }, + { + "current_steps": 2104, + "loss": 2.3392, + "learning_rate": 1.518879932117098e-07, + "epoch": 2.57020757020757 + }, + { + "current_steps": 2105, + "loss": 2.306, + "learning_rate": 1.5146372507424693e-07, + "epoch": 2.571428571428571 + }, + { + "current_steps": 2106, + "loss": 2.3784, + "learning_rate": 1.5103945693678405e-07, + "epoch": 2.5726495726495724 + }, + { + "current_steps": 2107, + "loss": 2.295, + "learning_rate": 1.5061518879932117e-07, + "epoch": 2.5738705738705736 + }, + { + "current_steps": 2108, + "loss": 2.5239, + "learning_rate": 1.5019092066185828e-07, + "epoch": 2.575091575091575 + }, + { + "current_steps": 2109, + "loss": 2.2725, + "learning_rate": 1.497666525243954e-07, + "epoch": 2.576312576312576 + }, + { + "current_steps": 2110, + "loss": 2.3634, + "learning_rate": 1.4934238438693252e-07, + "epoch": 2.5775335775335773 + }, + { + "current_steps": 2111, + "loss": 2.3172, + "learning_rate": 1.4891811624946966e-07, + "epoch": 2.578754578754579 + }, + { + "current_steps": 2112, + "loss": 2.3158, + "learning_rate": 1.4849384811200678e-07, + "epoch": 2.57997557997558 + }, + { + "current_steps": 2113, + "loss": 2.4466, + "learning_rate": 1.4806957997454392e-07, + "epoch": 2.5811965811965814 + }, + { + "current_steps": 2114, + "loss": 2.2945, + "learning_rate": 1.4764531183708104e-07, + "epoch": 2.5824175824175826 + }, + { + "current_steps": 2115, + "loss": 2.3319, + "learning_rate": 1.4722104369961815e-07, + "epoch": 2.583638583638584 + }, + { + "current_steps": 2116, + "loss": 2.3731, + "learning_rate": 1.4679677556215527e-07, + "epoch": 2.584859584859585 + }, + { + "current_steps": 2117, + "loss": 2.2877, + "learning_rate": 1.463725074246924e-07, + "epoch": 2.586080586080586 + }, + { + "current_steps": 2118, + "loss": 2.3454, + "learning_rate": 1.4594823928722953e-07, + "epoch": 2.5873015873015874 + }, + { + "current_steps": 2119, + "loss": 2.2179, + "learning_rate": 1.4552397114976665e-07, + "epoch": 2.5885225885225887 + }, + { + "current_steps": 2120, + "loss": 1.9025, + "learning_rate": 1.4509970301230377e-07, + "epoch": 2.58974358974359 + }, + { + "current_steps": 2121, + "loss": 2.3058, + "learning_rate": 1.4467543487484088e-07, + "epoch": 2.590964590964591 + }, + { + "current_steps": 2122, + "loss": 2.3476, + "learning_rate": 1.4425116673737803e-07, + "epoch": 2.5921855921855923 + }, + { + "current_steps": 2123, + "loss": 2.4316, + "learning_rate": 1.4382689859991514e-07, + "epoch": 2.5934065934065935 + }, + { + "current_steps": 2124, + "loss": 2.4445, + "learning_rate": 1.4340263046245226e-07, + "epoch": 2.5946275946275947 + }, + { + "current_steps": 2125, + "loss": 2.4108, + "learning_rate": 1.4297836232498938e-07, + "epoch": 2.595848595848596 + }, + { + "current_steps": 2126, + "loss": 2.1696, + "learning_rate": 1.4255409418752652e-07, + "epoch": 2.597069597069597 + }, + { + "current_steps": 2127, + "loss": 2.2162, + "learning_rate": 1.4212982605006364e-07, + "epoch": 2.5982905982905984 + }, + { + "current_steps": 2128, + "loss": 2.312, + "learning_rate": 1.4170555791260075e-07, + "epoch": 2.5995115995115996 + }, + { + "current_steps": 2129, + "loss": 2.333, + "learning_rate": 1.4128128977513787e-07, + "epoch": 2.600732600732601 + }, + { + "current_steps": 2130, + "loss": 2.2534, + "learning_rate": 1.4085702163767502e-07, + "epoch": 2.601953601953602 + }, + { + "current_steps": 2131, + "loss": 2.2413, + "learning_rate": 1.4043275350021213e-07, + "epoch": 2.6031746031746033 + }, + { + "current_steps": 2132, + "loss": 2.0244, + "learning_rate": 1.4000848536274925e-07, + "epoch": 2.6043956043956045 + }, + { + "current_steps": 2133, + "loss": 2.2318, + "learning_rate": 1.3958421722528637e-07, + "epoch": 2.6056166056166057 + }, + { + "current_steps": 2134, + "loss": 2.2803, + "learning_rate": 1.391599490878235e-07, + "epoch": 2.606837606837607 + }, + { + "current_steps": 2135, + "loss": 2.4421, + "learning_rate": 1.3873568095036063e-07, + "epoch": 2.608058608058608 + }, + { + "current_steps": 2136, + "loss": 2.3331, + "learning_rate": 1.3831141281289774e-07, + "epoch": 2.6092796092796093 + }, + { + "current_steps": 2137, + "loss": 2.2301, + "learning_rate": 1.3788714467543486e-07, + "epoch": 2.6105006105006106 + }, + { + "current_steps": 2138, + "loss": 2.3479, + "learning_rate": 1.37462876537972e-07, + "epoch": 2.6117216117216118 + }, + { + "current_steps": 2139, + "loss": 2.215, + "learning_rate": 1.3703860840050912e-07, + "epoch": 2.612942612942613 + }, + { + "current_steps": 2140, + "loss": 2.1311, + "learning_rate": 1.3661434026304624e-07, + "epoch": 2.614163614163614 + }, + { + "current_steps": 2141, + "loss": 2.4439, + "learning_rate": 1.3619007212558336e-07, + "epoch": 2.6153846153846154 + }, + { + "current_steps": 2142, + "loss": 2.2094, + "learning_rate": 1.357658039881205e-07, + "epoch": 2.6166056166056166 + }, + { + "current_steps": 2143, + "loss": 2.4846, + "learning_rate": 1.3534153585065762e-07, + "epoch": 2.617826617826618 + }, + { + "current_steps": 2144, + "loss": 2.2313, + "learning_rate": 1.3491726771319473e-07, + "epoch": 2.619047619047619 + }, + { + "current_steps": 2145, + "loss": 2.2845, + "learning_rate": 1.3449299957573185e-07, + "epoch": 2.6202686202686203 + }, + { + "current_steps": 2146, + "loss": 2.2651, + "learning_rate": 1.3406873143826897e-07, + "epoch": 2.6214896214896215 + }, + { + "current_steps": 2147, + "loss": 2.4734, + "learning_rate": 1.336444633008061e-07, + "epoch": 2.6227106227106227 + }, + { + "current_steps": 2148, + "loss": 2.355, + "learning_rate": 1.3322019516334323e-07, + "epoch": 2.623931623931624 + }, + { + "current_steps": 2149, + "loss": 2.4121, + "learning_rate": 1.3279592702588034e-07, + "epoch": 2.625152625152625 + }, + { + "current_steps": 2150, + "loss": 2.3335, + "learning_rate": 1.323716588884175e-07, + "epoch": 2.6263736263736264 + }, + { + "current_steps": 2151, + "loss": 2.3978, + "learning_rate": 1.319473907509546e-07, + "epoch": 2.6275946275946276 + }, + { + "current_steps": 2152, + "loss": 2.1764, + "learning_rate": 1.3152312261349172e-07, + "epoch": 2.628815628815629 + }, + { + "current_steps": 2153, + "loss": 2.2845, + "learning_rate": 1.3109885447602884e-07, + "epoch": 2.63003663003663 + }, + { + "current_steps": 2154, + "loss": 2.3166, + "learning_rate": 1.3067458633856596e-07, + "epoch": 2.6312576312576312 + }, + { + "current_steps": 2155, + "loss": 2.2703, + "learning_rate": 1.302503182011031e-07, + "epoch": 2.6324786324786325 + }, + { + "current_steps": 2156, + "loss": 2.2819, + "learning_rate": 1.2982605006364022e-07, + "epoch": 2.6336996336996337 + }, + { + "current_steps": 2157, + "loss": 2.3247, + "learning_rate": 1.2940178192617733e-07, + "epoch": 2.634920634920635 + }, + { + "current_steps": 2158, + "loss": 2.395, + "learning_rate": 1.2897751378871448e-07, + "epoch": 2.636141636141636 + }, + { + "current_steps": 2159, + "loss": 2.3432, + "learning_rate": 1.285532456512516e-07, + "epoch": 2.6373626373626373 + }, + { + "current_steps": 2160, + "loss": 2.3076, + "learning_rate": 1.281289775137887e-07, + "epoch": 2.6385836385836385 + }, + { + "current_steps": 2161, + "loss": 2.4578, + "learning_rate": 1.2770470937632583e-07, + "epoch": 2.6398046398046398 + }, + { + "current_steps": 2162, + "loss": 2.3053, + "learning_rate": 1.2728044123886294e-07, + "epoch": 2.641025641025641 + }, + { + "current_steps": 2163, + "loss": 2.4069, + "learning_rate": 1.2685617310140006e-07, + "epoch": 2.642246642246642 + }, + { + "current_steps": 2164, + "loss": 2.2913, + "learning_rate": 1.264319049639372e-07, + "epoch": 2.6434676434676434 + }, + { + "current_steps": 2165, + "loss": 2.2683, + "learning_rate": 1.2600763682647432e-07, + "epoch": 2.6446886446886446 + }, + { + "current_steps": 2166, + "loss": 2.1902, + "learning_rate": 1.2558336868901147e-07, + "epoch": 2.645909645909646 + }, + { + "current_steps": 2167, + "loss": 2.2454, + "learning_rate": 1.2515910055154858e-07, + "epoch": 2.647130647130647 + }, + { + "current_steps": 2168, + "loss": 2.2985, + "learning_rate": 1.247348324140857e-07, + "epoch": 2.6483516483516483 + }, + { + "current_steps": 2169, + "loss": 2.4225, + "learning_rate": 1.2431056427662282e-07, + "epoch": 2.6495726495726495 + }, + { + "current_steps": 2170, + "loss": 2.1956, + "learning_rate": 1.2388629613915996e-07, + "epoch": 2.6507936507936507 + }, + { + "current_steps": 2171, + "loss": 2.2492, + "learning_rate": 1.2346202800169708e-07, + "epoch": 2.652014652014652 + }, + { + "current_steps": 2172, + "loss": 2.2563, + "learning_rate": 1.230377598642342e-07, + "epoch": 2.653235653235653 + }, + { + "current_steps": 2173, + "loss": 2.2344, + "learning_rate": 1.226134917267713e-07, + "epoch": 2.6544566544566544 + }, + { + "current_steps": 2174, + "loss": 2.5149, + "learning_rate": 1.2218922358930845e-07, + "epoch": 2.6556776556776556 + }, + { + "current_steps": 2175, + "loss": 2.3723, + "learning_rate": 1.2176495545184557e-07, + "epoch": 2.656898656898657 + }, + { + "current_steps": 2176, + "loss": 2.2168, + "learning_rate": 1.213406873143827e-07, + "epoch": 2.658119658119658 + }, + { + "current_steps": 2177, + "loss": 2.5341, + "learning_rate": 1.209164191769198e-07, + "epoch": 2.659340659340659 + }, + { + "current_steps": 2178, + "loss": 2.2187, + "learning_rate": 1.2049215103945695e-07, + "epoch": 2.6605616605616604 + }, + { + "current_steps": 2179, + "loss": 2.2792, + "learning_rate": 1.2006788290199407e-07, + "epoch": 2.6617826617826617 + }, + { + "current_steps": 2180, + "loss": 2.274, + "learning_rate": 1.1964361476453118e-07, + "epoch": 2.663003663003663 + }, + { + "current_steps": 2181, + "loss": 2.372, + "learning_rate": 1.192193466270683e-07, + "epoch": 2.664224664224664 + }, + { + "current_steps": 2182, + "loss": 2.2234, + "learning_rate": 1.1879507848960542e-07, + "epoch": 2.6654456654456653 + }, + { + "current_steps": 2183, + "loss": 2.2761, + "learning_rate": 1.1837081035214255e-07, + "epoch": 2.6666666666666665 + }, + { + "current_steps": 2184, + "loss": 2.4102, + "learning_rate": 1.1794654221467968e-07, + "epoch": 2.6678876678876677 + }, + { + "current_steps": 2185, + "loss": 2.3395, + "learning_rate": 1.175222740772168e-07, + "epoch": 2.669108669108669 + }, + { + "current_steps": 2186, + "loss": 2.3132, + "learning_rate": 1.1709800593975391e-07, + "epoch": 2.67032967032967 + }, + { + "current_steps": 2187, + "loss": 2.273, + "learning_rate": 1.1667373780229104e-07, + "epoch": 2.6715506715506714 + }, + { + "current_steps": 2188, + "loss": 2.1844, + "learning_rate": 1.1624946966482817e-07, + "epoch": 2.672771672771673 + }, + { + "current_steps": 2189, + "loss": 2.3874, + "learning_rate": 1.1582520152736529e-07, + "epoch": 2.6739926739926743 + }, + { + "current_steps": 2190, + "loss": 2.3512, + "learning_rate": 1.154009333899024e-07, + "epoch": 2.6752136752136755 + }, + { + "current_steps": 2191, + "loss": 2.3667, + "learning_rate": 1.1497666525243954e-07, + "epoch": 2.6764346764346767 + }, + { + "current_steps": 2192, + "loss": 2.1739, + "learning_rate": 1.1455239711497667e-07, + "epoch": 2.677655677655678 + }, + { + "current_steps": 2193, + "loss": 1.837, + "learning_rate": 1.1412812897751378e-07, + "epoch": 2.678876678876679 + }, + { + "current_steps": 2194, + "loss": 2.3347, + "learning_rate": 1.137038608400509e-07, + "epoch": 2.6800976800976803 + }, + { + "current_steps": 2195, + "loss": 2.0146, + "learning_rate": 1.1327959270258804e-07, + "epoch": 2.6813186813186816 + }, + { + "current_steps": 2196, + "loss": 2.3115, + "learning_rate": 1.1285532456512516e-07, + "epoch": 2.682539682539683 + }, + { + "current_steps": 2197, + "loss": 2.0527, + "learning_rate": 1.1243105642766228e-07, + "epoch": 2.683760683760684 + }, + { + "current_steps": 2198, + "loss": 2.4582, + "learning_rate": 1.120067882901994e-07, + "epoch": 2.684981684981685 + }, + { + "current_steps": 2199, + "loss": 2.3053, + "learning_rate": 1.1158252015273654e-07, + "epoch": 2.6862026862026864 + }, + { + "current_steps": 2200, + "loss": 2.3585, + "learning_rate": 1.1115825201527365e-07, + "epoch": 2.6874236874236876 + }, + { + "current_steps": 2201, + "loss": 2.3962, + "learning_rate": 1.1073398387781077e-07, + "epoch": 2.688644688644689 + }, + { + "current_steps": 2202, + "loss": 2.2848, + "learning_rate": 1.1030971574034789e-07, + "epoch": 2.68986568986569 + }, + { + "current_steps": 2203, + "loss": 1.8112, + "learning_rate": 1.09885447602885e-07, + "epoch": 2.6910866910866913 + }, + { + "current_steps": 2204, + "loss": 2.4333, + "learning_rate": 1.0946117946542215e-07, + "epoch": 2.6923076923076925 + }, + { + "current_steps": 2205, + "loss": 2.2612, + "learning_rate": 1.0903691132795927e-07, + "epoch": 2.6935286935286937 + }, + { + "current_steps": 2206, + "loss": 2.3539, + "learning_rate": 1.0861264319049638e-07, + "epoch": 2.694749694749695 + }, + { + "current_steps": 2207, + "loss": 2.364, + "learning_rate": 1.081883750530335e-07, + "epoch": 2.695970695970696 + }, + { + "current_steps": 2208, + "loss": 2.3548, + "learning_rate": 1.0776410691557064e-07, + "epoch": 2.6971916971916974 + }, + { + "current_steps": 2209, + "loss": 2.3617, + "learning_rate": 1.0733983877810776e-07, + "epoch": 2.6984126984126986 + }, + { + "current_steps": 2210, + "loss": 2.3402, + "learning_rate": 1.0691557064064488e-07, + "epoch": 2.6996336996337 + }, + { + "current_steps": 2211, + "loss": 2.3554, + "learning_rate": 1.0649130250318201e-07, + "epoch": 2.700854700854701 + }, + { + "current_steps": 2212, + "loss": 2.3918, + "learning_rate": 1.0606703436571914e-07, + "epoch": 2.7020757020757022 + }, + { + "current_steps": 2213, + "loss": 2.385, + "learning_rate": 1.0564276622825625e-07, + "epoch": 2.7032967032967035 + }, + { + "current_steps": 2214, + "loss": 2.3822, + "learning_rate": 1.0521849809079337e-07, + "epoch": 2.7045177045177047 + }, + { + "current_steps": 2215, + "loss": 2.3346, + "learning_rate": 1.047942299533305e-07, + "epoch": 2.705738705738706 + }, + { + "current_steps": 2216, + "loss": 2.3516, + "learning_rate": 1.0436996181586763e-07, + "epoch": 2.706959706959707 + }, + { + "current_steps": 2217, + "loss": 2.2385, + "learning_rate": 1.0394569367840475e-07, + "epoch": 2.7081807081807083 + }, + { + "current_steps": 2218, + "loss": 2.3307, + "learning_rate": 1.0352142554094187e-07, + "epoch": 2.7094017094017095 + }, + { + "current_steps": 2219, + "loss": 2.3854, + "learning_rate": 1.03097157403479e-07, + "epoch": 2.7106227106227108 + }, + { + "current_steps": 2220, + "loss": 2.2831, + "learning_rate": 1.0267288926601613e-07, + "epoch": 2.711843711843712 + }, + { + "current_steps": 2221, + "loss": 2.2441, + "learning_rate": 1.0224862112855324e-07, + "epoch": 2.713064713064713 + }, + { + "current_steps": 2222, + "loss": 2.3543, + "learning_rate": 1.0182435299109036e-07, + "epoch": 2.7142857142857144 + }, + { + "current_steps": 2223, + "loss": 2.3361, + "learning_rate": 1.0140008485362749e-07, + "epoch": 2.7155067155067156 + }, + { + "current_steps": 2224, + "loss": 2.4973, + "learning_rate": 1.0097581671616461e-07, + "epoch": 2.716727716727717 + }, + { + "current_steps": 2225, + "loss": 2.2315, + "learning_rate": 1.0055154857870174e-07, + "epoch": 2.717948717948718 + }, + { + "current_steps": 2226, + "loss": 2.2083, + "learning_rate": 1.0012728044123886e-07, + "epoch": 2.7191697191697193 + }, + { + "current_steps": 2227, + "loss": 2.3327, + "learning_rate": 9.970301230377599e-08, + "epoch": 2.7203907203907205 + }, + { + "current_steps": 2228, + "loss": 2.3661, + "learning_rate": 9.92787441663131e-08, + "epoch": 2.7216117216117217 + }, + { + "current_steps": 2229, + "loss": 2.335, + "learning_rate": 9.885447602885023e-08, + "epoch": 2.722832722832723 + }, + { + "current_steps": 2230, + "loss": 2.3135, + "learning_rate": 9.843020789138735e-08, + "epoch": 2.724053724053724 + }, + { + "current_steps": 2231, + "loss": 2.3121, + "learning_rate": 9.800593975392448e-08, + "epoch": 2.7252747252747254 + }, + { + "current_steps": 2232, + "loss": 2.4167, + "learning_rate": 9.75816716164616e-08, + "epoch": 2.7264957264957266 + }, + { + "current_steps": 2233, + "loss": 2.367, + "learning_rate": 9.715740347899873e-08, + "epoch": 2.727716727716728 + }, + { + "current_steps": 2234, + "loss": 2.4111, + "learning_rate": 9.673313534153584e-08, + "epoch": 2.728937728937729 + }, + { + "current_steps": 2235, + "loss": 2.3393, + "learning_rate": 9.630886720407297e-08, + "epoch": 2.7301587301587302 + }, + { + "current_steps": 2236, + "loss": 2.3968, + "learning_rate": 9.588459906661009e-08, + "epoch": 2.7313797313797314 + }, + { + "current_steps": 2237, + "loss": 2.176, + "learning_rate": 9.546033092914722e-08, + "epoch": 2.7326007326007327 + }, + { + "current_steps": 2238, + "loss": 2.2049, + "learning_rate": 9.503606279168434e-08, + "epoch": 2.733821733821734 + }, + { + "current_steps": 2239, + "loss": 2.2686, + "learning_rate": 9.461179465422147e-08, + "epoch": 2.735042735042735 + }, + { + "current_steps": 2240, + "loss": 1.874, + "learning_rate": 9.418752651675859e-08, + "epoch": 2.7362637362637363 + }, + { + "current_steps": 2241, + "loss": 2.4112, + "learning_rate": 9.37632583792957e-08, + "epoch": 2.7374847374847375 + }, + { + "current_steps": 2242, + "loss": 2.2755, + "learning_rate": 9.333899024183283e-08, + "epoch": 2.7387057387057387 + }, + { + "current_steps": 2243, + "loss": 2.3173, + "learning_rate": 9.291472210436996e-08, + "epoch": 2.73992673992674 + }, + { + "current_steps": 2244, + "loss": 2.211, + "learning_rate": 9.249045396690708e-08, + "epoch": 2.741147741147741 + }, + { + "current_steps": 2245, + "loss": 2.3583, + "learning_rate": 9.20661858294442e-08, + "epoch": 2.7423687423687424 + }, + { + "current_steps": 2246, + "loss": 1.732, + "learning_rate": 9.164191769198133e-08, + "epoch": 2.7435897435897436 + }, + { + "current_steps": 2247, + "loss": 2.4059, + "learning_rate": 9.121764955451846e-08, + "epoch": 2.744810744810745 + }, + { + "current_steps": 2248, + "loss": 2.2002, + "learning_rate": 9.079338141705557e-08, + "epoch": 2.746031746031746 + }, + { + "current_steps": 2249, + "loss": 2.1638, + "learning_rate": 9.036911327959269e-08, + "epoch": 2.7472527472527473 + }, + { + "current_steps": 2250, + "loss": 2.3776, + "learning_rate": 8.994484514212982e-08, + "epoch": 2.7484737484737485 + }, + { + "current_steps": 2251, + "loss": 2.2923, + "learning_rate": 8.952057700466695e-08, + "epoch": 2.7496947496947497 + }, + { + "current_steps": 2252, + "loss": 2.2843, + "learning_rate": 8.909630886720407e-08, + "epoch": 2.750915750915751 + }, + { + "current_steps": 2253, + "loss": 2.2442, + "learning_rate": 8.867204072974119e-08, + "epoch": 2.752136752136752 + }, + { + "current_steps": 2254, + "loss": 2.2948, + "learning_rate": 8.824777259227832e-08, + "epoch": 2.7533577533577533 + }, + { + "current_steps": 2255, + "loss": 2.3928, + "learning_rate": 8.782350445481545e-08, + "epoch": 2.7545787545787546 + }, + { + "current_steps": 2256, + "loss": 2.5001, + "learning_rate": 8.739923631735256e-08, + "epoch": 2.755799755799756 + }, + { + "current_steps": 2257, + "loss": 2.3728, + "learning_rate": 8.697496817988968e-08, + "epoch": 2.757020757020757 + }, + { + "current_steps": 2258, + "loss": 2.4411, + "learning_rate": 8.655070004242681e-08, + "epoch": 2.758241758241758 + }, + { + "current_steps": 2259, + "loss": 2.2603, + "learning_rate": 8.612643190496394e-08, + "epoch": 2.7594627594627594 + }, + { + "current_steps": 2260, + "loss": 1.9239, + "learning_rate": 8.570216376750106e-08, + "epoch": 2.7606837606837606 + }, + { + "current_steps": 2261, + "loss": 2.3511, + "learning_rate": 8.527789563003817e-08, + "epoch": 2.761904761904762 + }, + { + "current_steps": 2262, + "loss": 2.1307, + "learning_rate": 8.485362749257529e-08, + "epoch": 2.763125763125763 + }, + { + "current_steps": 2263, + "loss": 2.3682, + "learning_rate": 8.442935935511244e-08, + "epoch": 2.7643467643467643 + }, + { + "current_steps": 2264, + "loss": 2.0067, + "learning_rate": 8.400509121764955e-08, + "epoch": 2.7655677655677655 + }, + { + "current_steps": 2265, + "loss": 2.3597, + "learning_rate": 8.358082308018667e-08, + "epoch": 2.7667887667887667 + }, + { + "current_steps": 2266, + "loss": 1.8072, + "learning_rate": 8.315655494272379e-08, + "epoch": 2.768009768009768 + }, + { + "current_steps": 2267, + "loss": 2.2588, + "learning_rate": 8.273228680526093e-08, + "epoch": 2.769230769230769 + }, + { + "current_steps": 2268, + "loss": 2.368, + "learning_rate": 8.230801866779805e-08, + "epoch": 2.7704517704517704 + }, + { + "current_steps": 2269, + "loss": 2.3853, + "learning_rate": 8.188375053033516e-08, + "epoch": 2.7716727716727716 + }, + { + "current_steps": 2270, + "loss": 2.2699, + "learning_rate": 8.145948239287228e-08, + "epoch": 2.772893772893773 + }, + { + "current_steps": 2271, + "loss": 2.3314, + "learning_rate": 8.103521425540942e-08, + "epoch": 2.774114774114774 + }, + { + "current_steps": 2272, + "loss": 2.1347, + "learning_rate": 8.061094611794654e-08, + "epoch": 2.7753357753357752 + }, + { + "current_steps": 2273, + "loss": 2.055, + "learning_rate": 8.018667798048366e-08, + "epoch": 2.7765567765567765 + }, + { + "current_steps": 2274, + "loss": 1.8955, + "learning_rate": 7.976240984302078e-08, + "epoch": 2.7777777777777777 + }, + { + "current_steps": 2275, + "loss": 2.3385, + "learning_rate": 7.933814170555792e-08, + "epoch": 2.778998778998779 + }, + { + "current_steps": 2276, + "loss": 1.5853, + "learning_rate": 7.891387356809504e-08, + "epoch": 2.78021978021978 + }, + { + "current_steps": 2277, + "loss": 2.3445, + "learning_rate": 7.848960543063215e-08, + "epoch": 2.7814407814407813 + }, + { + "current_steps": 2278, + "loss": 2.4419, + "learning_rate": 7.806533729316927e-08, + "epoch": 2.7826617826617825 + }, + { + "current_steps": 2279, + "loss": 2.3401, + "learning_rate": 7.764106915570641e-08, + "epoch": 2.7838827838827838 + }, + { + "current_steps": 2280, + "loss": 2.4499, + "learning_rate": 7.721680101824353e-08, + "epoch": 2.785103785103785 + }, + { + "current_steps": 2281, + "loss": 2.3138, + "learning_rate": 7.679253288078065e-08, + "epoch": 2.786324786324786 + }, + { + "current_steps": 2282, + "loss": 2.2022, + "learning_rate": 7.636826474331776e-08, + "epoch": 2.7875457875457874 + }, + { + "current_steps": 2283, + "loss": 2.2981, + "learning_rate": 7.59439966058549e-08, + "epoch": 2.7887667887667886 + }, + { + "current_steps": 2284, + "loss": 2.2535, + "learning_rate": 7.551972846839202e-08, + "epoch": 2.78998778998779 + }, + { + "current_steps": 2285, + "loss": 2.4225, + "learning_rate": 7.509546033092914e-08, + "epoch": 2.791208791208791 + }, + { + "current_steps": 2286, + "loss": 1.8092, + "learning_rate": 7.467119219346626e-08, + "epoch": 2.7924297924297923 + }, + { + "current_steps": 2287, + "loss": 2.306, + "learning_rate": 7.424692405600339e-08, + "epoch": 2.7936507936507935 + }, + { + "current_steps": 2288, + "loss": 2.4514, + "learning_rate": 7.382265591854052e-08, + "epoch": 2.7948717948717947 + }, + { + "current_steps": 2289, + "loss": 2.4663, + "learning_rate": 7.339838778107764e-08, + "epoch": 2.796092796092796 + }, + { + "current_steps": 2290, + "loss": 2.2889, + "learning_rate": 7.297411964361477e-08, + "epoch": 2.797313797313797 + }, + { + "current_steps": 2291, + "loss": 2.2526, + "learning_rate": 7.254985150615188e-08, + "epoch": 2.7985347985347984 + }, + { + "current_steps": 2292, + "loss": 2.4232, + "learning_rate": 7.212558336868901e-08, + "epoch": 2.7997557997557996 + }, + { + "current_steps": 2293, + "loss": 1.8049, + "learning_rate": 7.170131523122613e-08, + "epoch": 2.800976800976801 + }, + { + "current_steps": 2294, + "loss": 2.2491, + "learning_rate": 7.127704709376326e-08, + "epoch": 2.802197802197802 + }, + { + "current_steps": 2295, + "loss": 2.33, + "learning_rate": 7.085277895630038e-08, + "epoch": 2.8034188034188032 + }, + { + "current_steps": 2296, + "loss": 2.3384, + "learning_rate": 7.042851081883751e-08, + "epoch": 2.8046398046398044 + }, + { + "current_steps": 2297, + "loss": 2.3845, + "learning_rate": 7.000424268137462e-08, + "epoch": 2.8058608058608057 + }, + { + "current_steps": 2298, + "loss": 2.4763, + "learning_rate": 6.957997454391175e-08, + "epoch": 2.807081807081807 + }, + { + "current_steps": 2299, + "loss": 2.4194, + "learning_rate": 6.915570640644887e-08, + "epoch": 2.808302808302808 + }, + { + "current_steps": 2300, + "loss": 2.1152, + "learning_rate": 6.8731438268986e-08, + "epoch": 2.8095238095238093 + }, + { + "current_steps": 2301, + "loss": 2.198, + "learning_rate": 6.830717013152312e-08, + "epoch": 2.8107448107448105 + }, + { + "current_steps": 2302, + "loss": 2.3239, + "learning_rate": 6.788290199406025e-08, + "epoch": 2.8119658119658117 + }, + { + "current_steps": 2303, + "loss": 2.3217, + "learning_rate": 6.745863385659737e-08, + "epoch": 2.813186813186813 + }, + { + "current_steps": 2304, + "loss": 1.9221, + "learning_rate": 6.703436571913448e-08, + "epoch": 2.814407814407814 + }, + { + "current_steps": 2305, + "loss": 2.3257, + "learning_rate": 6.661009758167161e-08, + "epoch": 2.8156288156288154 + }, + { + "current_steps": 2306, + "loss": 2.319, + "learning_rate": 6.618582944420874e-08, + "epoch": 2.8168498168498166 + }, + { + "current_steps": 2307, + "loss": 2.0597, + "learning_rate": 6.576156130674586e-08, + "epoch": 2.818070818070818 + }, + { + "current_steps": 2308, + "loss": 2.399, + "learning_rate": 6.533729316928298e-08, + "epoch": 2.819291819291819 + }, + { + "current_steps": 2309, + "loss": 2.2778, + "learning_rate": 6.491302503182011e-08, + "epoch": 2.8205128205128203 + }, + { + "current_steps": 2310, + "loss": 2.389, + "learning_rate": 6.448875689435724e-08, + "epoch": 2.8217338217338215 + }, + { + "current_steps": 2311, + "loss": 2.3437, + "learning_rate": 6.406448875689436e-08, + "epoch": 2.8229548229548227 + }, + { + "current_steps": 2312, + "loss": 2.3603, + "learning_rate": 6.364022061943147e-08, + "epoch": 2.824175824175824 + }, + { + "current_steps": 2313, + "loss": 1.9699, + "learning_rate": 6.32159524819686e-08, + "epoch": 2.825396825396825 + }, + { + "current_steps": 2314, + "loss": 2.3445, + "learning_rate": 6.279168434450573e-08, + "epoch": 2.8266178266178263 + }, + { + "current_steps": 2315, + "loss": 2.4858, + "learning_rate": 6.236741620704285e-08, + "epoch": 2.8278388278388276 + }, + { + "current_steps": 2316, + "loss": 2.316, + "learning_rate": 6.194314806957998e-08, + "epoch": 2.8290598290598292 + }, + { + "current_steps": 2317, + "loss": 2.4687, + "learning_rate": 6.15188799321171e-08, + "epoch": 2.8302808302808304 + }, + { + "current_steps": 2318, + "loss": 2.4508, + "learning_rate": 6.109461179465423e-08, + "epoch": 2.8315018315018317 + }, + { + "current_steps": 2319, + "loss": 2.5854, + "learning_rate": 6.067034365719134e-08, + "epoch": 2.832722832722833 + }, + { + "current_steps": 2320, + "loss": 2.3333, + "learning_rate": 6.024607551972847e-08, + "epoch": 2.833943833943834 + }, + { + "current_steps": 2321, + "loss": 2.3359, + "learning_rate": 5.982180738226559e-08, + "epoch": 2.8351648351648353 + }, + { + "current_steps": 2322, + "loss": 2.3567, + "learning_rate": 5.939753924480271e-08, + "epoch": 2.8363858363858365 + }, + { + "current_steps": 2323, + "loss": 2.4285, + "learning_rate": 5.897327110733984e-08, + "epoch": 2.8376068376068377 + }, + { + "current_steps": 2324, + "loss": 2.2869, + "learning_rate": 5.8549002969876955e-08, + "epoch": 2.838827838827839 + }, + { + "current_steps": 2325, + "loss": 2.3144, + "learning_rate": 5.8124734832414086e-08, + "epoch": 2.84004884004884 + }, + { + "current_steps": 2326, + "loss": 2.4109, + "learning_rate": 5.77004666949512e-08, + "epoch": 2.8412698412698414 + }, + { + "current_steps": 2327, + "loss": 2.3861, + "learning_rate": 5.727619855748833e-08, + "epoch": 2.8424908424908426 + }, + { + "current_steps": 2328, + "loss": 2.3683, + "learning_rate": 5.685193042002545e-08, + "epoch": 2.843711843711844 + }, + { + "current_steps": 2329, + "loss": 1.8366, + "learning_rate": 5.642766228256258e-08, + "epoch": 2.844932844932845 + }, + { + "current_steps": 2330, + "loss": 2.4092, + "learning_rate": 5.60033941450997e-08, + "epoch": 2.8461538461538463 + }, + { + "current_steps": 2331, + "loss": 2.259, + "learning_rate": 5.557912600763683e-08, + "epoch": 2.8473748473748475 + }, + { + "current_steps": 2332, + "loss": 2.2539, + "learning_rate": 5.5154857870173944e-08, + "epoch": 2.8485958485958487 + }, + { + "current_steps": 2333, + "loss": 2.2487, + "learning_rate": 5.4730589732711074e-08, + "epoch": 2.84981684981685 + }, + { + "current_steps": 2334, + "loss": 2.2885, + "learning_rate": 5.430632159524819e-08, + "epoch": 2.851037851037851 + }, + { + "current_steps": 2335, + "loss": 2.3332, + "learning_rate": 5.388205345778532e-08, + "epoch": 2.8522588522588523 + }, + { + "current_steps": 2336, + "loss": 2.1544, + "learning_rate": 5.345778532032244e-08, + "epoch": 2.8534798534798536 + }, + { + "current_steps": 2337, + "loss": 2.322, + "learning_rate": 5.303351718285957e-08, + "epoch": 2.8547008547008548 + }, + { + "current_steps": 2338, + "loss": 2.2034, + "learning_rate": 5.2609249045396686e-08, + "epoch": 2.855921855921856 + }, + { + "current_steps": 2339, + "loss": 2.4126, + "learning_rate": 5.2184980907933816e-08, + "epoch": 2.857142857142857 + }, + { + "current_steps": 2340, + "loss": 2.2966, + "learning_rate": 5.176071277047093e-08, + "epoch": 2.8583638583638584 + }, + { + "current_steps": 2341, + "loss": 2.3306, + "learning_rate": 5.1336444633008063e-08, + "epoch": 2.8595848595848596 + }, + { + "current_steps": 2342, + "loss": 2.2502, + "learning_rate": 5.091217649554518e-08, + "epoch": 2.860805860805861 + }, + { + "current_steps": 2343, + "loss": 2.3811, + "learning_rate": 5.0487908358082304e-08, + "epoch": 2.862026862026862 + }, + { + "current_steps": 2344, + "loss": 2.3066, + "learning_rate": 5.006364022061943e-08, + "epoch": 2.8632478632478633 + }, + { + "current_steps": 2345, + "loss": 2.397, + "learning_rate": 4.963937208315655e-08, + "epoch": 2.8644688644688645 + }, + { + "current_steps": 2346, + "loss": 1.8356, + "learning_rate": 4.9215103945693675e-08, + "epoch": 2.8656898656898657 + }, + { + "current_steps": 2347, + "loss": 2.3523, + "learning_rate": 4.87908358082308e-08, + "epoch": 2.866910866910867 + }, + { + "current_steps": 2348, + "loss": 2.3906, + "learning_rate": 4.836656767076792e-08, + "epoch": 2.868131868131868 + }, + { + "current_steps": 2349, + "loss": 2.2573, + "learning_rate": 4.7942299533305046e-08, + "epoch": 2.8693528693528694 + }, + { + "current_steps": 2350, + "loss": 2.3904, + "learning_rate": 4.751803139584217e-08, + "epoch": 2.8705738705738706 + }, + { + "current_steps": 2351, + "loss": 2.4532, + "learning_rate": 4.709376325837929e-08, + "epoch": 2.871794871794872 + }, + { + "current_steps": 2352, + "loss": 2.3393, + "learning_rate": 4.6669495120916416e-08, + "epoch": 2.873015873015873 + }, + { + "current_steps": 2353, + "loss": 2.2428, + "learning_rate": 4.624522698345354e-08, + "epoch": 2.8742368742368742 + }, + { + "current_steps": 2354, + "loss": 2.3871, + "learning_rate": 4.5820958845990664e-08, + "epoch": 2.8754578754578755 + }, + { + "current_steps": 2355, + "loss": 2.3687, + "learning_rate": 4.539669070852779e-08, + "epoch": 2.8766788766788767 + }, + { + "current_steps": 2356, + "loss": 2.2044, + "learning_rate": 4.497242257106491e-08, + "epoch": 2.877899877899878 + }, + { + "current_steps": 2357, + "loss": 2.2769, + "learning_rate": 4.4548154433602034e-08, + "epoch": 2.879120879120879 + }, + { + "current_steps": 2358, + "loss": 2.2971, + "learning_rate": 4.412388629613916e-08, + "epoch": 2.8803418803418803 + }, + { + "current_steps": 2359, + "loss": 2.3206, + "learning_rate": 4.369961815867628e-08, + "epoch": 2.8815628815628815 + }, + { + "current_steps": 2360, + "loss": 2.2323, + "learning_rate": 4.3275350021213405e-08, + "epoch": 2.8827838827838828 + }, + { + "current_steps": 2361, + "loss": 2.4294, + "learning_rate": 4.285108188375053e-08, + "epoch": 2.884004884004884 + }, + { + "current_steps": 2362, + "loss": 2.3607, + "learning_rate": 4.2426813746287646e-08, + "epoch": 2.885225885225885 + }, + { + "current_steps": 2363, + "loss": 2.4701, + "learning_rate": 4.2002545608824776e-08, + "epoch": 2.8864468864468864 + }, + { + "current_steps": 2364, + "loss": 2.3064, + "learning_rate": 4.157827747136189e-08, + "epoch": 2.8876678876678876 + }, + { + "current_steps": 2365, + "loss": 2.3943, + "learning_rate": 4.115400933389902e-08, + "epoch": 2.888888888888889 + }, + { + "current_steps": 2366, + "loss": 2.2281, + "learning_rate": 4.072974119643614e-08, + "epoch": 2.89010989010989 + }, + { + "current_steps": 2367, + "loss": 1.8235, + "learning_rate": 4.030547305897327e-08, + "epoch": 2.8913308913308913 + }, + { + "current_steps": 2368, + "loss": 2.5126, + "learning_rate": 3.988120492151039e-08, + "epoch": 2.8925518925518925 + }, + { + "current_steps": 2369, + "loss": 2.2756, + "learning_rate": 3.945693678404752e-08, + "epoch": 2.8937728937728937 + }, + { + "current_steps": 2370, + "loss": 2.2679, + "learning_rate": 3.9032668646584635e-08, + "epoch": 2.894993894993895 + }, + { + "current_steps": 2371, + "loss": 2.2957, + "learning_rate": 3.8608400509121765e-08, + "epoch": 2.896214896214896 + }, + { + "current_steps": 2372, + "loss": 2.5052, + "learning_rate": 3.818413237165888e-08, + "epoch": 2.8974358974358974 + }, + { + "current_steps": 2373, + "loss": 2.3287, + "learning_rate": 3.775986423419601e-08, + "epoch": 2.8986568986568986 + }, + { + "current_steps": 2374, + "loss": 2.155, + "learning_rate": 3.733559609673313e-08, + "epoch": 2.8998778998779 + }, + { + "current_steps": 2375, + "loss": 2.1737, + "learning_rate": 3.691132795927026e-08, + "epoch": 2.901098901098901 + }, + { + "current_steps": 2376, + "loss": 2.2687, + "learning_rate": 3.648705982180738e-08, + "epoch": 2.9023199023199022 + }, + { + "current_steps": 2377, + "loss": 2.2835, + "learning_rate": 3.6062791684344507e-08, + "epoch": 2.9035409035409034 + }, + { + "current_steps": 2378, + "loss": 2.4966, + "learning_rate": 3.563852354688163e-08, + "epoch": 2.9047619047619047 + }, + { + "current_steps": 2379, + "loss": 2.3746, + "learning_rate": 3.5214255409418754e-08, + "epoch": 2.905982905982906 + }, + { + "current_steps": 2380, + "loss": 2.3709, + "learning_rate": 3.478998727195588e-08, + "epoch": 2.907203907203907 + }, + { + "current_steps": 2381, + "loss": 2.3387, + "learning_rate": 3.4365719134493e-08, + "epoch": 2.9084249084249083 + }, + { + "current_steps": 2382, + "loss": 2.1701, + "learning_rate": 3.3941450997030125e-08, + "epoch": 2.9096459096459095 + }, + { + "current_steps": 2383, + "loss": 2.2256, + "learning_rate": 3.351718285956724e-08, + "epoch": 2.9108669108669107 + }, + { + "current_steps": 2384, + "loss": 2.4198, + "learning_rate": 3.309291472210437e-08, + "epoch": 2.912087912087912 + }, + { + "current_steps": 2385, + "loss": 2.2187, + "learning_rate": 3.266864658464149e-08, + "epoch": 2.913308913308913 + }, + { + "current_steps": 2386, + "loss": 2.37, + "learning_rate": 3.224437844717862e-08, + "epoch": 2.9145299145299144 + }, + { + "current_steps": 2387, + "loss": 2.2017, + "learning_rate": 3.1820110309715736e-08, + "epoch": 2.9157509157509156 + }, + { + "current_steps": 2388, + "loss": 2.1694, + "learning_rate": 3.1395842172252866e-08, + "epoch": 2.916971916971917 + }, + { + "current_steps": 2389, + "loss": 2.2133, + "learning_rate": 3.097157403478999e-08, + "epoch": 2.918192918192918 + }, + { + "current_steps": 2390, + "loss": 1.6933, + "learning_rate": 3.0547305897327113e-08, + "epoch": 2.9194139194139193 + }, + { + "current_steps": 2391, + "loss": 2.1093, + "learning_rate": 3.012303775986424e-08, + "epoch": 2.9206349206349205 + }, + { + "current_steps": 2392, + "loss": 2.2802, + "learning_rate": 2.9698769622401354e-08, + "epoch": 2.9218559218559217 + }, + { + "current_steps": 2393, + "loss": 2.405, + "learning_rate": 2.9274501484938478e-08, + "epoch": 2.9230769230769234 + }, + { + "current_steps": 2394, + "loss": 2.4009, + "learning_rate": 2.88502333474756e-08, + "epoch": 2.9242979242979246 + }, + { + "current_steps": 2395, + "loss": 2.2442, + "learning_rate": 2.8425965210012725e-08, + "epoch": 2.925518925518926 + }, + { + "current_steps": 2396, + "loss": 2.2175, + "learning_rate": 2.800169707254985e-08, + "epoch": 2.926739926739927 + }, + { + "current_steps": 2397, + "loss": 2.4253, + "learning_rate": 2.7577428935086972e-08, + "epoch": 2.927960927960928 + }, + { + "current_steps": 2398, + "loss": 2.1386, + "learning_rate": 2.7153160797624096e-08, + "epoch": 2.9291819291819294 + }, + { + "current_steps": 2399, + "loss": 2.3289, + "learning_rate": 2.672889266016122e-08, + "epoch": 2.9304029304029307 + }, + { + "current_steps": 2400, + "loss": 2.1604, + "learning_rate": 2.6304624522698343e-08, + "epoch": 2.931623931623932 + }, + { + "current_steps": 2401, + "loss": 2.3432, + "learning_rate": 2.5880356385235467e-08, + "epoch": 2.932844932844933 + }, + { + "current_steps": 2402, + "loss": 2.308, + "learning_rate": 2.545608824777259e-08, + "epoch": 2.9340659340659343 + }, + { + "current_steps": 2403, + "loss": 2.4584, + "learning_rate": 2.5031820110309714e-08, + "epoch": 2.9352869352869355 + }, + { + "current_steps": 2404, + "loss": 2.4627, + "learning_rate": 2.4607551972846837e-08, + "epoch": 2.9365079365079367 + }, + { + "current_steps": 2405, + "loss": 2.3277, + "learning_rate": 2.418328383538396e-08, + "epoch": 2.937728937728938 + }, + { + "current_steps": 2406, + "loss": 2.3532, + "learning_rate": 2.3759015697921085e-08, + "epoch": 2.938949938949939 + }, + { + "current_steps": 2407, + "loss": 2.2804, + "learning_rate": 2.3334747560458208e-08, + "epoch": 2.9401709401709404 + }, + { + "current_steps": 2408, + "loss": 2.3279, + "learning_rate": 2.2910479422995332e-08, + "epoch": 2.9413919413919416 + }, + { + "current_steps": 2409, + "loss": 2.3758, + "learning_rate": 2.2486211285532455e-08, + "epoch": 2.942612942612943 + }, + { + "current_steps": 2410, + "loss": 2.2391, + "learning_rate": 2.206194314806958e-08, + "epoch": 2.943833943833944 + }, + { + "current_steps": 2411, + "loss": 2.2717, + "learning_rate": 2.1637675010606703e-08, + "epoch": 2.9450549450549453 + }, + { + "current_steps": 2412, + "loss": 2.5684, + "learning_rate": 2.1213406873143823e-08, + "epoch": 2.9462759462759465 + }, + { + "current_steps": 2413, + "loss": 2.3079, + "learning_rate": 2.0789138735680947e-08, + "epoch": 2.9474969474969477 + }, + { + "current_steps": 2414, + "loss": 2.4746, + "learning_rate": 2.036487059821807e-08, + "epoch": 2.948717948717949 + }, + { + "current_steps": 2415, + "loss": 2.4864, + "learning_rate": 1.9940602460755194e-08, + "epoch": 2.94993894993895 + }, + { + "current_steps": 2416, + "loss": 2.2917, + "learning_rate": 1.9516334323292317e-08, + "epoch": 2.9511599511599513 + }, + { + "current_steps": 2417, + "loss": 2.2507, + "learning_rate": 1.909206618582944e-08, + "epoch": 2.9523809523809526 + }, + { + "current_steps": 2418, + "loss": 2.1328, + "learning_rate": 1.8667798048366565e-08, + "epoch": 2.9536019536019538 + }, + { + "current_steps": 2419, + "loss": 2.4277, + "learning_rate": 1.824352991090369e-08, + "epoch": 2.954822954822955 + }, + { + "current_steps": 2420, + "loss": 2.2185, + "learning_rate": 1.7819261773440815e-08, + "epoch": 2.956043956043956 + }, + { + "current_steps": 2421, + "loss": 2.3978, + "learning_rate": 1.739499363597794e-08, + "epoch": 2.9572649572649574 + }, + { + "current_steps": 2422, + "loss": 2.3468, + "learning_rate": 1.6970725498515062e-08, + "epoch": 2.9584859584859586 + }, + { + "current_steps": 2423, + "loss": 2.3693, + "learning_rate": 1.6546457361052186e-08, + "epoch": 2.95970695970696 + }, + { + "current_steps": 2424, + "loss": 2.4034, + "learning_rate": 1.612218922358931e-08, + "epoch": 2.960927960927961 + }, + { + "current_steps": 2425, + "loss": 2.7131, + "learning_rate": 1.5697921086126433e-08, + "epoch": 2.9621489621489623 + }, + { + "current_steps": 2426, + "loss": 2.1977, + "learning_rate": 1.5273652948663557e-08, + "epoch": 2.9633699633699635 + }, + { + "current_steps": 2427, + "loss": 2.2738, + "learning_rate": 1.4849384811200677e-08, + "epoch": 2.9645909645909647 + }, + { + "current_steps": 2428, + "loss": 2.3748, + "learning_rate": 1.44251166737378e-08, + "epoch": 2.965811965811966 + }, + { + "current_steps": 2429, + "loss": 2.3417, + "learning_rate": 1.4000848536274924e-08, + "epoch": 2.967032967032967 + }, + { + "current_steps": 2430, + "loss": 2.3007, + "learning_rate": 1.3576580398812048e-08, + "epoch": 2.9682539682539684 + }, + { + "current_steps": 2431, + "loss": 1.9648, + "learning_rate": 1.3152312261349171e-08, + "epoch": 2.9694749694749696 + }, + { + "current_steps": 2432, + "loss": 2.2465, + "learning_rate": 1.2728044123886295e-08, + "epoch": 2.970695970695971 + }, + { + "current_steps": 2433, + "loss": 2.1644, + "learning_rate": 1.2303775986423419e-08, + "epoch": 2.971916971916972 + }, + { + "current_steps": 2434, + "loss": 2.4691, + "learning_rate": 1.1879507848960542e-08, + "epoch": 2.9731379731379732 + }, + { + "current_steps": 2435, + "loss": 2.2385, + "learning_rate": 1.1455239711497666e-08, + "epoch": 2.9743589743589745 + }, + { + "current_steps": 2436, + "loss": 2.2653, + "learning_rate": 1.103097157403479e-08, + "epoch": 2.9755799755799757 + }, + { + "current_steps": 2437, + "loss": 2.3377, + "learning_rate": 1.0606703436571911e-08, + "epoch": 2.976800976800977 + }, + { + "current_steps": 2438, + "loss": 2.1703, + "learning_rate": 1.0182435299109035e-08, + "epoch": 2.978021978021978 + }, + { + "current_steps": 2439, + "loss": 2.2848, + "learning_rate": 9.758167161646159e-09, + "epoch": 2.9792429792429793 + }, + { + "current_steps": 2440, + "loss": 1.881, + "learning_rate": 9.333899024183282e-09, + "epoch": 2.9804639804639805 + }, + { + "current_steps": 2441, + "loss": 1.8604, + "learning_rate": 8.909630886720408e-09, + "epoch": 2.9816849816849818 + }, + { + "current_steps": 2442, + "loss": 2.4447, + "learning_rate": 8.485362749257531e-09, + "epoch": 2.982905982905983 + }, + { + "current_steps": 2443, + "loss": 1.8882, + "learning_rate": 8.061094611794655e-09, + "epoch": 2.984126984126984 + }, + { + "current_steps": 2444, + "loss": 2.4384, + "learning_rate": 7.636826474331778e-09, + "epoch": 2.9853479853479854 + }, + { + "current_steps": 2445, + "loss": 1.7699, + "learning_rate": 7.2125583368689e-09, + "epoch": 2.9865689865689866 + }, + { + "current_steps": 2446, + "loss": 2.2465, + "learning_rate": 6.788290199406024e-09, + "epoch": 2.987789987789988 + }, + { + "current_steps": 2447, + "loss": 2.308, + "learning_rate": 6.3640220619431475e-09, + "epoch": 2.989010989010989 + }, + { + "current_steps": 2448, + "loss": 2.2228, + "learning_rate": 5.939753924480271e-09, + "epoch": 2.9902319902319903 + }, + { + "current_steps": 2449, + "loss": 2.1106, + "learning_rate": 5.515485787017395e-09, + "epoch": 2.9914529914529915 + }, + { + "current_steps": 2450, + "loss": 2.7312, + "learning_rate": 5.0912176495545175e-09, + "epoch": 2.9926739926739927 + }, + { + "current_steps": 2451, + "loss": 2.339, + "learning_rate": 4.666949512091641e-09, + "epoch": 2.993894993894994 + }, + { + "current_steps": 2452, + "loss": 2.4764, + "learning_rate": 4.2426813746287656e-09, + "epoch": 2.995115995115995 + }, + { + "current_steps": 2453, + "loss": 2.4238, + "learning_rate": 3.818413237165889e-09, + "epoch": 2.9963369963369964 + }, + { + "current_steps": 2454, + "loss": 2.2424, + "learning_rate": 3.394145099703012e-09, + "epoch": 2.9975579975579976 + }, + { + "current_steps": 2455, + "loss": 2.2903, + "learning_rate": 2.9698769622401356e-09, + "epoch": 2.998778998778999 + }, + { + "current_steps": 2456, + "loss": 2.1927, + "learning_rate": 2.5456088247772588e-09, + "epoch": 3.0 + }, + { + "current_steps": 2456, + "loss": 2.1927, + "learning_rate": 2.5456088247772588e-09, + "epoch": 3.0 + } +] \ No newline at end of file