diff --git "a/trainer_state.json" "b/trainer_state.json" --- "a/trainer_state.json" +++ "b/trainer_state.json" @@ -1,23369 +1,26369 @@ { "best_metric": null, "best_model_checkpoint": null, - "epoch": 1.9994859933179132, + "epoch": 2.0, "eval_steps": 500, - "global_step": 3890, + "global_step": 4390, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, - "learning_rate": 1.7094017094017097e-07, - "loss": 2.0264, + "learning_rate": 1.5151515151515152e-07, + "loss": 1.9482, "step": 1 }, { "epoch": 0.0, - "learning_rate": 3.4188034188034194e-07, - "loss": 2.0957, + "learning_rate": 3.0303030303030305e-07, + "loss": 2.1938, "step": 2 }, { "epoch": 0.0, - "learning_rate": 5.128205128205128e-07, - "loss": 2.146, + "learning_rate": 4.5454545454545457e-07, + "loss": 2.0854, "step": 3 }, { "epoch": 0.0, - "learning_rate": 6.837606837606839e-07, - "loss": 2.1265, + "learning_rate": 6.060606060606061e-07, + "loss": 2.1196, "step": 4 }, { "epoch": 0.0, - "learning_rate": 8.547008547008548e-07, - "loss": 2.0854, + "learning_rate": 7.575757575757576e-07, + "loss": 2.146, "step": 5 }, { "epoch": 0.0, - "learning_rate": 1.0256410256410257e-06, - "loss": 2.0713, + "learning_rate": 9.090909090909091e-07, + "loss": 2.0386, "step": 6 }, { "epoch": 0.0, - "learning_rate": 1.1965811965811968e-06, - "loss": 2.0996, + "learning_rate": 1.0606060606060608e-06, + "loss": 2.1294, "step": 7 }, { "epoch": 0.0, - "learning_rate": 1.3675213675213678e-06, - "loss": 2.0396, + "learning_rate": 1.2121212121212122e-06, + "loss": 2.0112, "step": 8 }, { "epoch": 0.0, - "learning_rate": 1.5384615384615387e-06, - "loss": 2.0151, + "learning_rate": 1.3636363636363636e-06, + "loss": 1.9995, "step": 9 }, { - "epoch": 0.01, - "learning_rate": 1.7094017094017097e-06, - "loss": 1.9233, + "epoch": 0.0, + "learning_rate": 1.5151515151515152e-06, + "loss": 2.0156, "step": 10 }, { "epoch": 0.01, - "learning_rate": 1.8803418803418804e-06, - "loss": 2.0352, + "learning_rate": 1.6666666666666667e-06, + "loss": 2.0845, "step": 11 }, { "epoch": 0.01, - "learning_rate": 2.0512820512820513e-06, - "loss": 1.832, + "learning_rate": 1.8181818181818183e-06, + "loss": 1.8462, "step": 12 }, { "epoch": 0.01, - "learning_rate": 2.222222222222222e-06, - "loss": 1.8682, + "learning_rate": 1.96969696969697e-06, + "loss": 1.8755, "step": 13 }, { "epoch": 0.01, - "learning_rate": 2.3931623931623937e-06, - "loss": 1.7954, + "learning_rate": 2.1212121212121216e-06, + "loss": 1.9092, "step": 14 }, { "epoch": 0.01, - "learning_rate": 2.564102564102564e-06, - "loss": 1.7231, + "learning_rate": 2.2727272727272728e-06, + "loss": 1.7007, "step": 15 }, { "epoch": 0.01, - "learning_rate": 2.7350427350427355e-06, - "loss": 1.5986, + "learning_rate": 2.4242424242424244e-06, + "loss": 1.7026, "step": 16 }, { "epoch": 0.01, - "learning_rate": 2.9059829059829063e-06, - "loss": 1.5469, + "learning_rate": 2.575757575757576e-06, + "loss": 1.5977, "step": 17 }, { "epoch": 0.01, - "learning_rate": 3.0769230769230774e-06, - "loss": 1.5488, + "learning_rate": 2.7272727272727272e-06, + "loss": 1.5713, "step": 18 }, { "epoch": 0.01, - "learning_rate": 3.247863247863248e-06, - "loss": 1.4927, + "learning_rate": 2.8787878787878793e-06, + "loss": 1.5552, "step": 19 }, { "epoch": 0.01, - "learning_rate": 3.4188034188034193e-06, - "loss": 1.5078, + "learning_rate": 3.0303030303030305e-06, + "loss": 1.499, "step": 20 }, { "epoch": 0.01, - "learning_rate": 3.58974358974359e-06, - "loss": 1.4165, + "learning_rate": 3.181818181818182e-06, + "loss": 1.5508, "step": 21 }, { "epoch": 0.01, - "learning_rate": 3.760683760683761e-06, - "loss": 1.4531, + "learning_rate": 3.3333333333333333e-06, + "loss": 1.4629, "step": 22 }, { "epoch": 0.01, - "learning_rate": 3.9316239316239315e-06, - "loss": 1.3994, + "learning_rate": 3.4848484848484854e-06, + "loss": 1.4473, "step": 23 }, { "epoch": 0.01, - "learning_rate": 4.102564102564103e-06, - "loss": 1.3589, + "learning_rate": 3.6363636363636366e-06, + "loss": 1.4233, "step": 24 }, { "epoch": 0.01, - "learning_rate": 4.273504273504274e-06, - "loss": 1.3364, + "learning_rate": 3.7878787878787882e-06, + "loss": 1.4194, "step": 25 }, { "epoch": 0.01, - "learning_rate": 4.444444444444444e-06, - "loss": 1.3667, + "learning_rate": 3.93939393939394e-06, + "loss": 1.4087, "step": 26 }, { "epoch": 0.01, - "learning_rate": 4.615384615384616e-06, - "loss": 1.2896, + "learning_rate": 4.0909090909090915e-06, + "loss": 1.3838, "step": 27 }, { "epoch": 0.01, - "learning_rate": 4.786324786324787e-06, - "loss": 1.2954, + "learning_rate": 4.242424242424243e-06, + "loss": 1.2866, "step": 28 }, { "epoch": 0.01, - "learning_rate": 4.957264957264958e-06, - "loss": 1.2891, + "learning_rate": 4.393939393939394e-06, + "loss": 1.3447, "step": 29 }, { - "epoch": 0.02, - "learning_rate": 5.128205128205128e-06, - "loss": 1.2769, + "epoch": 0.01, + "learning_rate": 4.5454545454545455e-06, + "loss": 1.3164, "step": 30 }, { - "epoch": 0.02, - "learning_rate": 5.2991452991453e-06, - "loss": 1.2124, + "epoch": 0.01, + "learning_rate": 4.696969696969698e-06, + "loss": 1.2598, "step": 31 }, { - "epoch": 0.02, - "learning_rate": 5.470085470085471e-06, - "loss": 1.2036, + "epoch": 0.01, + "learning_rate": 4.848484848484849e-06, + "loss": 1.2871, "step": 32 }, { "epoch": 0.02, - "learning_rate": 5.641025641025641e-06, - "loss": 1.1768, + "learning_rate": 5e-06, + "loss": 1.2769, "step": 33 }, { "epoch": 0.02, - "learning_rate": 5.8119658119658126e-06, - "loss": 1.2378, + "learning_rate": 5.151515151515152e-06, + "loss": 1.2185, "step": 34 }, { "epoch": 0.02, - "learning_rate": 5.982905982905983e-06, - "loss": 1.1794, + "learning_rate": 5.303030303030303e-06, + "loss": 1.2256, "step": 35 }, { "epoch": 0.02, - "learning_rate": 6.153846153846155e-06, - "loss": 1.1924, + "learning_rate": 5.4545454545454545e-06, + "loss": 1.2263, "step": 36 }, { "epoch": 0.02, - "learning_rate": 6.324786324786325e-06, - "loss": 1.2134, + "learning_rate": 5.606060606060606e-06, + "loss": 1.1558, "step": 37 }, { "epoch": 0.02, - "learning_rate": 6.495726495726496e-06, - "loss": 1.1753, + "learning_rate": 5.7575757575757586e-06, + "loss": 1.2319, "step": 38 }, { "epoch": 0.02, - "learning_rate": 6.666666666666667e-06, - "loss": 1.1555, + "learning_rate": 5.90909090909091e-06, + "loss": 1.2461, "step": 39 }, { "epoch": 0.02, - "learning_rate": 6.837606837606839e-06, - "loss": 1.0706, + "learning_rate": 6.060606060606061e-06, + "loss": 1.1069, "step": 40 }, { "epoch": 0.02, - "learning_rate": 7.008547008547009e-06, - "loss": 1.1941, + "learning_rate": 6.212121212121213e-06, + "loss": 1.1309, "step": 41 }, { "epoch": 0.02, - "learning_rate": 7.17948717948718e-06, - "loss": 1.1208, + "learning_rate": 6.363636363636364e-06, + "loss": 1.2004, "step": 42 }, { "epoch": 0.02, - "learning_rate": 7.350427350427351e-06, - "loss": 1.0945, + "learning_rate": 6.515151515151516e-06, + "loss": 1.1833, "step": 43 }, { "epoch": 0.02, - "learning_rate": 7.521367521367522e-06, - "loss": 1.0579, + "learning_rate": 6.666666666666667e-06, + "loss": 1.1614, "step": 44 }, { "epoch": 0.02, - "learning_rate": 7.692307692307694e-06, - "loss": 1.0784, + "learning_rate": 6.818181818181818e-06, + "loss": 1.1538, "step": 45 }, { "epoch": 0.02, - "learning_rate": 7.863247863247863e-06, - "loss": 1.0669, + "learning_rate": 6.969696969696971e-06, + "loss": 1.1836, "step": 46 }, { "epoch": 0.02, - "learning_rate": 8.034188034188036e-06, - "loss": 1.1111, + "learning_rate": 7.121212121212122e-06, + "loss": 1.1677, "step": 47 }, { "epoch": 0.02, - "learning_rate": 8.205128205128205e-06, - "loss": 1.0869, + "learning_rate": 7.272727272727273e-06, + "loss": 1.1489, "step": 48 }, { - "epoch": 0.03, - "learning_rate": 8.376068376068377e-06, - "loss": 1.0684, + "epoch": 0.02, + "learning_rate": 7.424242424242425e-06, + "loss": 1.1201, "step": 49 }, { - "epoch": 0.03, - "learning_rate": 8.547008547008548e-06, - "loss": 1.1077, + "epoch": 0.02, + "learning_rate": 7.5757575757575764e-06, + "loss": 1.0979, "step": 50 }, { - "epoch": 0.03, - "learning_rate": 8.717948717948719e-06, - "loss": 1.145, + "epoch": 0.02, + "learning_rate": 7.727272727272727e-06, + "loss": 1.0916, "step": 51 }, { - "epoch": 0.03, - "learning_rate": 8.888888888888888e-06, - "loss": 1.082, + "epoch": 0.02, + "learning_rate": 7.87878787878788e-06, + "loss": 1.0916, "step": 52 }, { - "epoch": 0.03, - "learning_rate": 9.059829059829061e-06, - "loss": 1.031, + "epoch": 0.02, + "learning_rate": 8.03030303030303e-06, + "loss": 1.1724, "step": 53 }, { - "epoch": 0.03, - "learning_rate": 9.230769230769232e-06, - "loss": 1.0999, + "epoch": 0.02, + "learning_rate": 8.181818181818183e-06, + "loss": 1.103, "step": 54 }, { "epoch": 0.03, - "learning_rate": 9.401709401709402e-06, - "loss": 1.0732, + "learning_rate": 8.333333333333334e-06, + "loss": 0.9871, "step": 55 }, { "epoch": 0.03, - "learning_rate": 9.572649572649575e-06, - "loss": 1.116, + "learning_rate": 8.484848484848486e-06, + "loss": 1.1475, "step": 56 }, { "epoch": 0.03, - "learning_rate": 9.743589743589744e-06, - "loss": 1.064, + "learning_rate": 8.636363636363637e-06, + "loss": 1.0271, "step": 57 }, { "epoch": 0.03, - "learning_rate": 9.914529914529915e-06, - "loss": 1.0757, + "learning_rate": 8.787878787878788e-06, + "loss": 1.1558, "step": 58 }, { "epoch": 0.03, - "learning_rate": 1.0085470085470086e-05, - "loss": 1.0081, + "learning_rate": 8.93939393939394e-06, + "loss": 1.073, "step": 59 }, { "epoch": 0.03, - "learning_rate": 1.0256410256410256e-05, - "loss": 1.0151, + "learning_rate": 9.090909090909091e-06, + "loss": 1.0532, "step": 60 }, { "epoch": 0.03, - "learning_rate": 1.0427350427350429e-05, - "loss": 0.9919, + "learning_rate": 9.242424242424244e-06, + "loss": 0.9819, "step": 61 }, { "epoch": 0.03, - "learning_rate": 1.05982905982906e-05, - "loss": 0.9861, + "learning_rate": 9.393939393939396e-06, + "loss": 1.0618, "step": 62 }, { "epoch": 0.03, - "learning_rate": 1.076923076923077e-05, - "loss": 1.011, + "learning_rate": 9.545454545454547e-06, + "loss": 1.0269, "step": 63 }, { "epoch": 0.03, - "learning_rate": 1.0940170940170942e-05, - "loss": 1.009, + "learning_rate": 9.696969696969698e-06, + "loss": 1.025, "step": 64 }, { "epoch": 0.03, - "learning_rate": 1.1111111111111113e-05, - "loss": 1.0298, + "learning_rate": 9.84848484848485e-06, + "loss": 1.0427, "step": 65 }, { "epoch": 0.03, - "learning_rate": 1.1282051282051283e-05, - "loss": 1.0054, + "learning_rate": 1e-05, + "loss": 1.0562, "step": 66 }, { "epoch": 0.03, - "learning_rate": 1.1452991452991454e-05, - "loss": 1.0244, + "learning_rate": 1.0151515151515152e-05, + "loss": 1.0061, "step": 67 }, { "epoch": 0.03, - "learning_rate": 1.1623931623931625e-05, - "loss": 1.0059, + "learning_rate": 1.0303030303030304e-05, + "loss": 1.0615, "step": 68 }, { - "epoch": 0.04, - "learning_rate": 1.1794871794871796e-05, - "loss": 1.0125, + "epoch": 0.03, + "learning_rate": 1.0454545454545455e-05, + "loss": 1.0444, "step": 69 }, { - "epoch": 0.04, - "learning_rate": 1.1965811965811966e-05, - "loss": 1.0134, + "epoch": 0.03, + "learning_rate": 1.0606060606060606e-05, + "loss": 0.9779, "step": 70 }, { - "epoch": 0.04, - "learning_rate": 1.2136752136752137e-05, - "loss": 0.967, + "epoch": 0.03, + "learning_rate": 1.0757575757575758e-05, + "loss": 1.0332, "step": 71 }, { - "epoch": 0.04, - "learning_rate": 1.230769230769231e-05, - "loss": 1.0378, + "epoch": 0.03, + "learning_rate": 1.0909090909090909e-05, + "loss": 1.0676, "step": 72 }, { - "epoch": 0.04, - "learning_rate": 1.247863247863248e-05, - "loss": 1.042, + "epoch": 0.03, + "learning_rate": 1.1060606060606061e-05, + "loss": 1.0046, "step": 73 }, { - "epoch": 0.04, - "learning_rate": 1.264957264957265e-05, - "loss": 0.9844, + "epoch": 0.03, + "learning_rate": 1.1212121212121212e-05, + "loss": 0.99, "step": 74 }, { - "epoch": 0.04, - "learning_rate": 1.2820512820512823e-05, - "loss": 0.9673, + "epoch": 0.03, + "learning_rate": 1.1363636363636366e-05, + "loss": 1.0425, "step": 75 }, { - "epoch": 0.04, - "learning_rate": 1.2991452991452993e-05, - "loss": 0.9707, + "epoch": 0.03, + "learning_rate": 1.1515151515151517e-05, + "loss": 1.0251, "step": 76 }, { "epoch": 0.04, - "learning_rate": 1.3162393162393164e-05, - "loss": 0.9529, + "learning_rate": 1.1666666666666668e-05, + "loss": 0.9465, "step": 77 }, { "epoch": 0.04, - "learning_rate": 1.3333333333333333e-05, - "loss": 0.9758, + "learning_rate": 1.181818181818182e-05, + "loss": 0.9038, "step": 78 }, { "epoch": 0.04, - "learning_rate": 1.3504273504273506e-05, - "loss": 0.9514, + "learning_rate": 1.1969696969696971e-05, + "loss": 0.9629, "step": 79 }, { "epoch": 0.04, - "learning_rate": 1.3675213675213677e-05, - "loss": 1.0239, + "learning_rate": 1.2121212121212122e-05, + "loss": 0.9443, "step": 80 }, { "epoch": 0.04, - "learning_rate": 1.3846153846153847e-05, - "loss": 0.9673, + "learning_rate": 1.2272727272727274e-05, + "loss": 0.9783, "step": 81 }, { "epoch": 0.04, - "learning_rate": 1.4017094017094018e-05, - "loss": 0.9438, + "learning_rate": 1.2424242424242425e-05, + "loss": 0.9816, "step": 82 }, { "epoch": 0.04, - "learning_rate": 1.4188034188034189e-05, - "loss": 1.0127, + "learning_rate": 1.2575757575757576e-05, + "loss": 0.9575, "step": 83 }, { "epoch": 0.04, - "learning_rate": 1.435897435897436e-05, - "loss": 1.0229, + "learning_rate": 1.2727272727272728e-05, + "loss": 0.9688, "step": 84 }, { "epoch": 0.04, - "learning_rate": 1.4529914529914531e-05, - "loss": 1.0015, + "learning_rate": 1.287878787878788e-05, + "loss": 0.9153, "step": 85 }, { "epoch": 0.04, - "learning_rate": 1.4700854700854703e-05, - "loss": 0.9939, + "learning_rate": 1.3030303030303032e-05, + "loss": 0.9961, "step": 86 }, { "epoch": 0.04, - "learning_rate": 1.4871794871794874e-05, - "loss": 0.9541, + "learning_rate": 1.3181818181818183e-05, + "loss": 1.0491, "step": 87 }, { - "epoch": 0.05, - "learning_rate": 1.5042735042735043e-05, - "loss": 1.0034, + "epoch": 0.04, + "learning_rate": 1.3333333333333333e-05, + "loss": 1.0227, "step": 88 }, { - "epoch": 0.05, - "learning_rate": 1.5213675213675214e-05, - "loss": 1.0315, + "epoch": 0.04, + "learning_rate": 1.3484848484848486e-05, + "loss": 0.9215, "step": 89 }, { - "epoch": 0.05, - "learning_rate": 1.5384615384615387e-05, - "loss": 0.9839, + "epoch": 0.04, + "learning_rate": 1.3636363636363637e-05, + "loss": 1.0056, "step": 90 }, { - "epoch": 0.05, - "learning_rate": 1.555555555555556e-05, - "loss": 0.9927, + "epoch": 0.04, + "learning_rate": 1.378787878787879e-05, + "loss": 1.0032, "step": 91 }, { - "epoch": 0.05, - "learning_rate": 1.5726495726495726e-05, - "loss": 0.9768, + "epoch": 0.04, + "learning_rate": 1.3939393939393942e-05, + "loss": 0.959, "step": 92 }, { - "epoch": 0.05, - "learning_rate": 1.5897435897435897e-05, - "loss": 0.9617, + "epoch": 0.04, + "learning_rate": 1.4090909090909092e-05, + "loss": 0.8544, "step": 93 }, { - "epoch": 0.05, - "learning_rate": 1.6068376068376072e-05, - "loss": 0.9297, + "epoch": 0.04, + "learning_rate": 1.4242424242424245e-05, + "loss": 0.9751, "step": 94 }, { - "epoch": 0.05, - "learning_rate": 1.623931623931624e-05, - "loss": 0.9993, + "epoch": 0.04, + "learning_rate": 1.4393939393939396e-05, + "loss": 0.9895, "step": 95 }, { - "epoch": 0.05, - "learning_rate": 1.641025641025641e-05, - "loss": 0.9077, + "epoch": 0.04, + "learning_rate": 1.4545454545454546e-05, + "loss": 0.9609, "step": 96 }, { - "epoch": 0.05, - "learning_rate": 1.6581196581196585e-05, - "loss": 0.9746, + "epoch": 0.04, + "learning_rate": 1.4696969696969699e-05, + "loss": 0.9536, "step": 97 }, { - "epoch": 0.05, - "learning_rate": 1.6752136752136753e-05, - "loss": 0.9543, + "epoch": 0.04, + "learning_rate": 1.484848484848485e-05, + "loss": 0.981, "step": 98 }, { "epoch": 0.05, - "learning_rate": 1.6923076923076924e-05, - "loss": 0.96, + "learning_rate": 1.5000000000000002e-05, + "loss": 0.9548, "step": 99 }, { "epoch": 0.05, - "learning_rate": 1.7094017094017095e-05, - "loss": 0.9949, + "learning_rate": 1.5151515151515153e-05, + "loss": 0.9641, "step": 100 }, { "epoch": 0.05, - "learning_rate": 1.7264957264957267e-05, - "loss": 0.9385, + "learning_rate": 1.5303030303030304e-05, + "loss": 1.0332, "step": 101 }, { "epoch": 0.05, - "learning_rate": 1.7435897435897438e-05, - "loss": 0.978, + "learning_rate": 1.5454545454545454e-05, + "loss": 0.9839, "step": 102 }, { "epoch": 0.05, - "learning_rate": 1.760683760683761e-05, - "loss": 0.9729, + "learning_rate": 1.5606060606060605e-05, + "loss": 0.9597, "step": 103 }, { "epoch": 0.05, - "learning_rate": 1.7777777777777777e-05, - "loss": 1.0295, + "learning_rate": 1.575757575757576e-05, + "loss": 0.9692, "step": 104 }, { "epoch": 0.05, - "learning_rate": 1.794871794871795e-05, - "loss": 0.9651, + "learning_rate": 1.590909090909091e-05, + "loss": 1.0295, "step": 105 }, { "epoch": 0.05, - "learning_rate": 1.8119658119658122e-05, - "loss": 0.8958, + "learning_rate": 1.606060606060606e-05, + "loss": 0.9497, "step": 106 }, { "epoch": 0.05, - "learning_rate": 1.829059829059829e-05, - "loss": 0.9497, + "learning_rate": 1.6212121212121212e-05, + "loss": 0.9202, "step": 107 }, { - "epoch": 0.06, - "learning_rate": 1.8461538461538465e-05, - "loss": 0.9302, + "epoch": 0.05, + "learning_rate": 1.6363636363636366e-05, + "loss": 0.9541, "step": 108 }, { - "epoch": 0.06, - "learning_rate": 1.8632478632478636e-05, - "loss": 0.9688, + "epoch": 0.05, + "learning_rate": 1.6515151515151517e-05, + "loss": 0.9468, "step": 109 }, { - "epoch": 0.06, - "learning_rate": 1.8803418803418804e-05, - "loss": 0.9509, + "epoch": 0.05, + "learning_rate": 1.6666666666666667e-05, + "loss": 0.9639, "step": 110 }, { - "epoch": 0.06, - "learning_rate": 1.8974358974358975e-05, - "loss": 0.9431, + "epoch": 0.05, + "learning_rate": 1.681818181818182e-05, + "loss": 0.939, "step": 111 }, { - "epoch": 0.06, - "learning_rate": 1.914529914529915e-05, - "loss": 0.9714, + "epoch": 0.05, + "learning_rate": 1.6969696969696972e-05, + "loss": 0.9971, "step": 112 }, { - "epoch": 0.06, - "learning_rate": 1.9316239316239317e-05, - "loss": 0.9753, + "epoch": 0.05, + "learning_rate": 1.7121212121212123e-05, + "loss": 0.9897, "step": 113 }, { - "epoch": 0.06, - "learning_rate": 1.9487179487179488e-05, - "loss": 0.9343, + "epoch": 0.05, + "learning_rate": 1.7272727272727274e-05, + "loss": 0.9705, "step": 114 }, { - "epoch": 0.06, - "learning_rate": 1.965811965811966e-05, - "loss": 0.9312, + "epoch": 0.05, + "learning_rate": 1.7424242424242425e-05, + "loss": 1.0078, "step": 115 }, { - "epoch": 0.06, - "learning_rate": 1.982905982905983e-05, - "loss": 0.9734, + "epoch": 0.05, + "learning_rate": 1.7575757575757576e-05, + "loss": 0.9932, "step": 116 }, { - "epoch": 0.06, - "learning_rate": 2e-05, - "loss": 0.9077, + "epoch": 0.05, + "learning_rate": 1.772727272727273e-05, + "loss": 0.9204, "step": 117 }, { - "epoch": 0.06, - "learning_rate": 1.9999996533460812e-05, - "loss": 0.8911, + "epoch": 0.05, + "learning_rate": 1.787878787878788e-05, + "loss": 0.9751, "step": 118 }, { - "epoch": 0.06, - "learning_rate": 1.999998613384565e-05, - "loss": 0.8911, + "epoch": 0.05, + "learning_rate": 1.803030303030303e-05, + "loss": 0.9744, "step": 119 }, { - "epoch": 0.06, - "learning_rate": 1.999996880116172e-05, - "loss": 0.9487, + "epoch": 0.05, + "learning_rate": 1.8181818181818182e-05, + "loss": 0.9016, "step": 120 }, { "epoch": 0.06, - "learning_rate": 1.9999944535421044e-05, - "loss": 0.9993, + "learning_rate": 1.8333333333333333e-05, + "loss": 0.9404, "step": 121 }, { "epoch": 0.06, - "learning_rate": 1.9999913336640445e-05, - "loss": 0.9524, + "learning_rate": 1.8484848484848487e-05, + "loss": 0.9763, "step": 122 }, { "epoch": 0.06, - "learning_rate": 1.9999875204841555e-05, - "loss": 0.9844, + "learning_rate": 1.8636363636363638e-05, + "loss": 0.9678, "step": 123 }, { "epoch": 0.06, - "learning_rate": 1.9999830140050802e-05, - "loss": 0.9673, + "learning_rate": 1.8787878787878792e-05, + "loss": 0.9695, "step": 124 }, { "epoch": 0.06, - "learning_rate": 1.999977814229944e-05, - "loss": 0.927, + "learning_rate": 1.8939393939393943e-05, + "loss": 0.9058, "step": 125 }, { "epoch": 0.06, - "learning_rate": 1.9999719211623518e-05, - "loss": 0.9258, + "learning_rate": 1.9090909090909094e-05, + "loss": 0.9985, "step": 126 }, { - "epoch": 0.07, - "learning_rate": 1.9999653348063886e-05, - "loss": 0.906, + "epoch": 0.06, + "learning_rate": 1.9242424242424244e-05, + "loss": 0.9551, "step": 127 }, { - "epoch": 0.07, - "learning_rate": 1.9999580551666215e-05, - "loss": 0.9587, + "epoch": 0.06, + "learning_rate": 1.9393939393939395e-05, + "loss": 0.8957, "step": 128 }, { - "epoch": 0.07, - "learning_rate": 1.9999500822480976e-05, - "loss": 0.9617, + "epoch": 0.06, + "learning_rate": 1.9545454545454546e-05, + "loss": 0.9875, "step": 129 }, { - "epoch": 0.07, - "learning_rate": 1.999941416056344e-05, - "loss": 0.8987, + "epoch": 0.06, + "learning_rate": 1.96969696969697e-05, + "loss": 0.9946, "step": 130 }, { - "epoch": 0.07, - "learning_rate": 1.999932056597369e-05, - "loss": 0.875, + "epoch": 0.06, + "learning_rate": 1.984848484848485e-05, + "loss": 0.9431, "step": 131 }, { - "epoch": 0.07, - "learning_rate": 1.999922003877662e-05, - "loss": 0.918, + "epoch": 0.06, + "learning_rate": 2e-05, + "loss": 0.9612, "step": 132 }, { - "epoch": 0.07, - "learning_rate": 1.9999112579041927e-05, - "loss": 0.9175, + "epoch": 0.06, + "learning_rate": 1.9999997278186176e-05, + "loss": 0.97, "step": 133 }, { - "epoch": 0.07, - "learning_rate": 1.9998998186844112e-05, - "loss": 0.916, + "epoch": 0.06, + "learning_rate": 1.999998911274618e-05, + "loss": 0.9465, "step": 134 }, { - "epoch": 0.07, - "learning_rate": 1.9998876862262485e-05, - "loss": 0.9529, + "epoch": 0.06, + "learning_rate": 1.9999975503684456e-05, + "loss": 0.8936, "step": 135 }, { - "epoch": 0.07, - "learning_rate": 1.9998748605381156e-05, - "loss": 0.9382, + "epoch": 0.06, + "learning_rate": 1.999995645100842e-05, + "loss": 0.912, "step": 136 }, { - "epoch": 0.07, - "learning_rate": 1.9998613416289054e-05, - "loss": 0.9814, + "epoch": 0.06, + "learning_rate": 1.999993195472844e-05, + "loss": 0.9236, "step": 137 }, { - "epoch": 0.07, - "learning_rate": 1.9998471295079908e-05, - "loss": 0.9607, + "epoch": 0.06, + "learning_rate": 1.9999902014857842e-05, + "loss": 0.9683, "step": 138 }, { - "epoch": 0.07, - "learning_rate": 1.9998322241852238e-05, - "loss": 0.9375, + "epoch": 0.06, + "learning_rate": 1.9999866631412933e-05, + "loss": 0.9045, "step": 139 }, { - "epoch": 0.07, - "learning_rate": 1.9998166256709396e-05, - "loss": 0.9177, + "epoch": 0.06, + "learning_rate": 1.9999825804412976e-05, + "loss": 0.9695, "step": 140 }, { - "epoch": 0.07, - "learning_rate": 1.9998003339759527e-05, - "loss": 0.9033, + "epoch": 0.06, + "learning_rate": 1.9999779533880195e-05, + "loss": 0.887, "step": 141 }, { - "epoch": 0.07, - "learning_rate": 1.999783349111558e-05, - "loss": 0.9841, + "epoch": 0.06, + "learning_rate": 1.9999727819839773e-05, + "loss": 0.877, "step": 142 }, { "epoch": 0.07, - "learning_rate": 1.999765671089531e-05, - "loss": 0.9258, + "learning_rate": 1.9999670662319865e-05, + "loss": 0.9302, "step": 143 }, { "epoch": 0.07, - "learning_rate": 1.9997472999221284e-05, - "loss": 0.8945, + "learning_rate": 1.999960806135158e-05, + "loss": 0.9148, "step": 144 }, { "epoch": 0.07, - "learning_rate": 1.999728235622087e-05, - "loss": 0.9226, + "learning_rate": 1.9999540016969004e-05, + "loss": 0.9016, "step": 145 }, { - "epoch": 0.08, - "learning_rate": 1.9997084782026243e-05, - "loss": 0.9104, + "epoch": 0.07, + "learning_rate": 1.9999466529209175e-05, + "loss": 0.9666, "step": 146 }, { - "epoch": 0.08, - "learning_rate": 1.9996880276774382e-05, - "loss": 0.9548, + "epoch": 0.07, + "learning_rate": 1.9999387598112093e-05, + "loss": 0.8746, "step": 147 }, { - "epoch": 0.08, - "learning_rate": 1.999666884060707e-05, - "loss": 0.9282, + "epoch": 0.07, + "learning_rate": 1.999930322372073e-05, + "loss": 0.8973, "step": 148 }, { - "epoch": 0.08, - "learning_rate": 1.9996450473670898e-05, - "loss": 0.9248, + "epoch": 0.07, + "learning_rate": 1.999921340608101e-05, + "loss": 0.9302, "step": 149 }, { - "epoch": 0.08, - "learning_rate": 1.9996225176117264e-05, - "loss": 0.9294, + "epoch": 0.07, + "learning_rate": 1.9999118145241836e-05, + "loss": 0.9363, "step": 150 }, { - "epoch": 0.08, - "learning_rate": 1.9995992948102366e-05, - "loss": 0.9739, + "epoch": 0.07, + "learning_rate": 1.9999017441255057e-05, + "loss": 0.8984, "step": 151 }, { - "epoch": 0.08, - "learning_rate": 1.9995753789787212e-05, - "loss": 0.9497, + "epoch": 0.07, + "learning_rate": 1.9998911294175494e-05, + "loss": 0.9561, "step": 152 }, { - "epoch": 0.08, - "learning_rate": 1.9995507701337606e-05, - "loss": 0.9463, + "epoch": 0.07, + "learning_rate": 1.999879970406093e-05, + "loss": 0.9771, "step": 153 }, { - "epoch": 0.08, - "learning_rate": 1.9995254682924172e-05, - "loss": 0.9004, + "epoch": 0.07, + "learning_rate": 1.999868267097211e-05, + "loss": 0.9172, "step": 154 }, { - "epoch": 0.08, - "learning_rate": 1.9994994734722326e-05, - "loss": 0.9729, + "epoch": 0.07, + "learning_rate": 1.9998560194972743e-05, + "loss": 0.9714, "step": 155 }, { - "epoch": 0.08, - "learning_rate": 1.999472785691229e-05, - "loss": 0.9541, + "epoch": 0.07, + "learning_rate": 1.99984322761295e-05, + "loss": 1.0137, "step": 156 }, { - "epoch": 0.08, - "learning_rate": 1.9994454049679096e-05, - "loss": 0.8608, + "epoch": 0.07, + "learning_rate": 1.999829891451202e-05, + "loss": 0.9202, "step": 157 }, { - "epoch": 0.08, - "learning_rate": 1.9994173313212576e-05, - "loss": 0.9661, + "epoch": 0.07, + "learning_rate": 1.9998160110192893e-05, + "loss": 0.9424, "step": 158 }, { - "epoch": 0.08, - "learning_rate": 1.9993885647707363e-05, - "loss": 0.9163, + "epoch": 0.07, + "learning_rate": 1.999801586324768e-05, + "loss": 0.929, "step": 159 }, { - "epoch": 0.08, - "learning_rate": 1.99935910533629e-05, - "loss": 0.9319, + "epoch": 0.07, + "learning_rate": 1.999786617375491e-05, + "loss": 0.9209, "step": 160 }, { - "epoch": 0.08, - "learning_rate": 1.9993289530383433e-05, - "loss": 0.9114, + "epoch": 0.07, + "learning_rate": 1.9997711041796058e-05, + "loss": 0.9177, "step": 161 }, { - "epoch": 0.08, - "learning_rate": 1.9992981078978007e-05, - "loss": 0.9141, + "epoch": 0.07, + "learning_rate": 1.9997550467455582e-05, + "loss": 0.8962, "step": 162 }, { - "epoch": 0.08, - "learning_rate": 1.9992665699360478e-05, - "loss": 0.9351, + "epoch": 0.07, + "learning_rate": 1.9997384450820884e-05, + "loss": 0.9475, "step": 163 }, { - "epoch": 0.08, - "learning_rate": 1.9992343391749502e-05, - "loss": 0.9026, + "epoch": 0.07, + "learning_rate": 1.9997212991982346e-05, + "loss": 0.9297, "step": 164 }, { "epoch": 0.08, - "learning_rate": 1.9992014156368532e-05, - "loss": 0.918, + "learning_rate": 1.99970360910333e-05, + "loss": 0.8904, "step": 165 }, { - "epoch": 0.09, - "learning_rate": 1.9991677993445832e-05, - "loss": 0.9668, + "epoch": 0.08, + "learning_rate": 1.9996853748070042e-05, + "loss": 0.9058, "step": 166 }, { - "epoch": 0.09, - "learning_rate": 1.9991334903214463e-05, - "loss": 0.9094, + "epoch": 0.08, + "learning_rate": 1.9996665963191836e-05, + "loss": 0.9795, "step": 167 }, { - "epoch": 0.09, - "learning_rate": 1.99909848859123e-05, - "loss": 0.907, + "epoch": 0.08, + "learning_rate": 1.9996472736500898e-05, + "loss": 0.8737, "step": 168 }, { - "epoch": 0.09, - "learning_rate": 1.9990627941782007e-05, - "loss": 0.9397, + "epoch": 0.08, + "learning_rate": 1.9996274068102424e-05, + "loss": 0.938, "step": 169 }, { - "epoch": 0.09, - "learning_rate": 1.9990264071071057e-05, - "loss": 0.9377, + "epoch": 0.08, + "learning_rate": 1.9996069958104556e-05, + "loss": 0.8962, "step": 170 }, { - "epoch": 0.09, - "learning_rate": 1.9989893274031727e-05, - "loss": 0.9087, + "epoch": 0.08, + "learning_rate": 1.9995860406618407e-05, + "loss": 0.8926, "step": 171 }, { - "epoch": 0.09, - "learning_rate": 1.9989515550921088e-05, - "loss": 0.8, + "epoch": 0.08, + "learning_rate": 1.9995645413758043e-05, + "loss": 0.9575, "step": 172 }, { - "epoch": 0.09, - "learning_rate": 1.9989130902001025e-05, - "loss": 0.8564, + "epoch": 0.08, + "learning_rate": 1.9995424979640503e-05, + "loss": 0.9404, "step": 173 }, { - "epoch": 0.09, - "learning_rate": 1.9988739327538212e-05, - "loss": 0.9243, + "epoch": 0.08, + "learning_rate": 1.9995199104385784e-05, + "loss": 0.9053, "step": 174 }, { - "epoch": 0.09, - "learning_rate": 1.9988340827804136e-05, - "loss": 0.9636, + "epoch": 0.08, + "learning_rate": 1.999496778811684e-05, + "loss": 0.9143, "step": 175 }, { - "epoch": 0.09, - "learning_rate": 1.998793540307508e-05, - "loss": 0.8899, + "epoch": 0.08, + "learning_rate": 1.999473103095959e-05, + "loss": 0.9343, "step": 176 }, { - "epoch": 0.09, - "learning_rate": 1.9987523053632118e-05, - "loss": 0.9207, + "epoch": 0.08, + "learning_rate": 1.999448883304292e-05, + "loss": 0.9453, "step": 177 }, { - "epoch": 0.09, - "learning_rate": 1.998710377976115e-05, - "loss": 0.8711, + "epoch": 0.08, + "learning_rate": 1.9994241194498678e-05, + "loss": 0.8984, "step": 178 }, { - "epoch": 0.09, - "learning_rate": 1.998667758175285e-05, - "loss": 0.885, + "epoch": 0.08, + "learning_rate": 1.999398811546166e-05, + "loss": 0.866, "step": 179 }, { - "epoch": 0.09, - "learning_rate": 1.998624445990271e-05, - "loss": 0.8855, + "epoch": 0.08, + "learning_rate": 1.9993729596069635e-05, + "loss": 0.8943, "step": 180 }, { - "epoch": 0.09, - "learning_rate": 1.9985804414511018e-05, - "loss": 0.9497, + "epoch": 0.08, + "learning_rate": 1.9993465636463333e-05, + "loss": 0.9468, "step": 181 }, { - "epoch": 0.09, - "learning_rate": 1.9985357445882855e-05, - "loss": 0.895, + "epoch": 0.08, + "learning_rate": 1.9993196236786444e-05, + "loss": 0.9065, "step": 182 }, { - "epoch": 0.09, - "learning_rate": 1.9984903554328116e-05, - "loss": 0.8992, + "epoch": 0.08, + "learning_rate": 1.9992921397185618e-05, + "loss": 0.8954, "step": 183 }, { - "epoch": 0.09, - "learning_rate": 1.998444274016148e-05, - "loss": 0.9453, + "epoch": 0.08, + "learning_rate": 1.9992641117810466e-05, + "loss": 0.8644, "step": 184 }, { - "epoch": 0.1, - "learning_rate": 1.9983975003702437e-05, - "loss": 0.9333, + "epoch": 0.08, + "learning_rate": 1.9992355398813566e-05, + "loss": 0.9302, "step": 185 }, { - "epoch": 0.1, - "learning_rate": 1.998350034527527e-05, - "loss": 0.9028, + "epoch": 0.08, + "learning_rate": 1.999206424035045e-05, + "loss": 0.8531, "step": 186 }, { - "epoch": 0.1, - "learning_rate": 1.9983018765209067e-05, - "loss": 0.8989, + "epoch": 0.09, + "learning_rate": 1.9991767642579614e-05, + "loss": 0.9355, "step": 187 }, { - "epoch": 0.1, - "learning_rate": 1.9982530263837708e-05, - "loss": 0.8601, + "epoch": 0.09, + "learning_rate": 1.9991465605662517e-05, + "loss": 0.928, "step": 188 }, { - "epoch": 0.1, - "learning_rate": 1.998203484149988e-05, - "loss": 0.9146, + "epoch": 0.09, + "learning_rate": 1.999115812976357e-05, + "loss": 0.9106, "step": 189 }, { - "epoch": 0.1, - "learning_rate": 1.9981532498539055e-05, - "loss": 0.8357, + "epoch": 0.09, + "learning_rate": 1.9990845215050164e-05, + "loss": 0.9919, "step": 190 }, { - "epoch": 0.1, - "learning_rate": 1.9981023235303517e-05, - "loss": 0.9194, + "epoch": 0.09, + "learning_rate": 1.9990526861692623e-05, + "loss": 0.9277, "step": 191 }, { - "epoch": 0.1, - "learning_rate": 1.9980507052146342e-05, - "loss": 0.8928, + "epoch": 0.09, + "learning_rate": 1.999020306986426e-05, + "loss": 0.8992, "step": 192 }, { - "epoch": 0.1, - "learning_rate": 1.99799839494254e-05, - "loss": 0.8923, + "epoch": 0.09, + "learning_rate": 1.9989873839741324e-05, + "loss": 0.9192, "step": 193 }, { - "epoch": 0.1, - "learning_rate": 1.9979453927503366e-05, - "loss": 0.9124, + "epoch": 0.09, + "learning_rate": 1.998953917150304e-05, + "loss": 0.9463, "step": 194 }, { - "epoch": 0.1, - "learning_rate": 1.9978916986747708e-05, - "loss": 0.9333, + "epoch": 0.09, + "learning_rate": 1.9989199065331593e-05, + "loss": 0.9807, "step": 195 }, { - "epoch": 0.1, - "learning_rate": 1.9978373127530684e-05, - "loss": 0.9661, + "epoch": 0.09, + "learning_rate": 1.998885352141212e-05, + "loss": 0.8953, "step": 196 }, { - "epoch": 0.1, - "learning_rate": 1.997782235022937e-05, - "loss": 0.8813, + "epoch": 0.09, + "learning_rate": 1.9988502539932725e-05, + "loss": 0.9836, "step": 197 }, { - "epoch": 0.1, - "learning_rate": 1.9977264655225614e-05, - "loss": 0.9275, + "epoch": 0.09, + "learning_rate": 1.9988146121084463e-05, + "loss": 0.8704, "step": 198 }, { - "epoch": 0.1, - "learning_rate": 1.9976700042906076e-05, - "loss": 0.8999, + "epoch": 0.09, + "learning_rate": 1.998778426506136e-05, + "loss": 0.8945, "step": 199 }, { - "epoch": 0.1, - "learning_rate": 1.9976128513662196e-05, + "epoch": 0.09, + "learning_rate": 1.99874169720604e-05, "loss": 0.9163, "step": 200 }, { - "epoch": 0.1, - "learning_rate": 1.997555006789023e-05, - "loss": 0.8701, + "epoch": 0.09, + "learning_rate": 1.998704424228152e-05, + "loss": 0.8992, "step": 201 }, { - "epoch": 0.1, - "learning_rate": 1.9974964705991217e-05, - "loss": 0.9473, + "epoch": 0.09, + "learning_rate": 1.9986666075927617e-05, + "loss": 0.9456, "step": 202 }, { - "epoch": 0.1, - "learning_rate": 1.9974372428370992e-05, - "loss": 0.8738, + "epoch": 0.09, + "learning_rate": 1.9986282473204554e-05, + "loss": 0.8915, "step": 203 }, { - "epoch": 0.1, - "learning_rate": 1.997377323544018e-05, - "loss": 0.8752, + "epoch": 0.09, + "learning_rate": 1.9985893434321153e-05, + "loss": 0.884, "step": 204 }, { - "epoch": 0.11, - "learning_rate": 1.9973167127614218e-05, - "loss": 0.8728, + "epoch": 0.09, + "learning_rate": 1.9985498959489187e-05, + "loss": 0.8727, "step": 205 }, { - "epoch": 0.11, - "learning_rate": 1.9972554105313317e-05, - "loss": 0.9434, + "epoch": 0.09, + "learning_rate": 1.9985099048923397e-05, + "loss": 0.9148, "step": 206 }, { - "epoch": 0.11, - "learning_rate": 1.997193416896249e-05, - "loss": 0.905, + "epoch": 0.09, + "learning_rate": 1.9984693702841474e-05, + "loss": 0.9324, "step": 207 }, { - "epoch": 0.11, - "learning_rate": 1.9971307318991546e-05, - "loss": 0.8396, + "epoch": 0.09, + "learning_rate": 1.9984282921464082e-05, + "loss": 0.8969, "step": 208 }, { - "epoch": 0.11, - "learning_rate": 1.9970673555835086e-05, - "loss": 0.9321, + "epoch": 0.1, + "learning_rate": 1.998386670501483e-05, + "loss": 0.927, "step": 209 }, { - "epoch": 0.11, - "learning_rate": 1.99700328799325e-05, - "loss": 0.9121, + "epoch": 0.1, + "learning_rate": 1.9983445053720292e-05, + "loss": 0.9309, "step": 210 }, { - "epoch": 0.11, - "learning_rate": 1.9969385291727977e-05, - "loss": 0.8979, + "epoch": 0.1, + "learning_rate": 1.9983017967809998e-05, + "loss": 0.9385, "step": 211 }, { - "epoch": 0.11, - "learning_rate": 1.9968730791670494e-05, - "loss": 0.8914, + "epoch": 0.1, + "learning_rate": 1.9982585447516437e-05, + "loss": 0.9241, "step": 212 }, { - "epoch": 0.11, - "learning_rate": 1.996806938021382e-05, - "loss": 0.8723, + "epoch": 0.1, + "learning_rate": 1.9982147493075058e-05, + "loss": 0.8931, "step": 213 }, { - "epoch": 0.11, - "learning_rate": 1.9967401057816515e-05, - "loss": 0.9119, + "epoch": 0.1, + "learning_rate": 1.9981704104724267e-05, + "loss": 0.9373, "step": 214 }, { - "epoch": 0.11, - "learning_rate": 1.9966725824941933e-05, - "loss": 0.9263, + "epoch": 0.1, + "learning_rate": 1.998125528270543e-05, + "loss": 0.8826, "step": 215 }, { - "epoch": 0.11, - "learning_rate": 1.9966043682058223e-05, - "loss": 0.8606, + "epoch": 0.1, + "learning_rate": 1.9980801027262863e-05, + "loss": 0.8557, "step": 216 }, { - "epoch": 0.11, - "learning_rate": 1.9965354629638314e-05, - "loss": 0.9497, + "epoch": 0.1, + "learning_rate": 1.9980341338643855e-05, + "loss": 0.9048, "step": 217 }, { - "epoch": 0.11, - "learning_rate": 1.9964658668159935e-05, - "loss": 0.9053, + "epoch": 0.1, + "learning_rate": 1.9979876217098636e-05, + "loss": 0.9146, "step": 218 }, { - "epoch": 0.11, - "learning_rate": 1.9963955798105598e-05, - "loss": 0.9377, + "epoch": 0.1, + "learning_rate": 1.9979405662880406e-05, + "loss": 0.8655, "step": 219 }, { - "epoch": 0.11, - "learning_rate": 1.9963246019962613e-05, - "loss": 0.8796, + "epoch": 0.1, + "learning_rate": 1.997892967624531e-05, + "loss": 0.8684, "step": 220 }, { - "epoch": 0.11, - "learning_rate": 1.9962529334223074e-05, - "loss": 0.854, + "epoch": 0.1, + "learning_rate": 1.9978448257452466e-05, + "loss": 0.8728, "step": 221 }, { - "epoch": 0.11, - "learning_rate": 1.9961805741383862e-05, - "loss": 0.9429, + "epoch": 0.1, + "learning_rate": 1.9977961406763935e-05, + "loss": 0.8843, "step": 222 }, { - "epoch": 0.11, - "learning_rate": 1.996107524194665e-05, - "loss": 0.8682, + "epoch": 0.1, + "learning_rate": 1.997746912444474e-05, + "loss": 0.9067, "step": 223 }, { - "epoch": 0.12, - "learning_rate": 1.99603378364179e-05, - "loss": 0.9019, + "epoch": 0.1, + "learning_rate": 1.9976971410762864e-05, + "loss": 0.9177, "step": 224 }, { - "epoch": 0.12, - "learning_rate": 1.9959593525308863e-05, - "loss": 0.8706, + "epoch": 0.1, + "learning_rate": 1.997646826598924e-05, + "loss": 0.8678, "step": 225 }, { - "epoch": 0.12, - "learning_rate": 1.995884230913557e-05, - "loss": 0.8516, + "epoch": 0.1, + "learning_rate": 1.997595969039777e-05, + "loss": 0.8975, "step": 226 }, { - "epoch": 0.12, - "learning_rate": 1.995808418841885e-05, - "loss": 0.8865, + "epoch": 0.1, + "learning_rate": 1.9975445684265295e-05, + "loss": 0.9399, "step": 227 }, { - "epoch": 0.12, - "learning_rate": 1.9957319163684314e-05, - "loss": 0.8452, + "epoch": 0.1, + "learning_rate": 1.997492624787162e-05, + "loss": 0.9495, "step": 228 }, { - "epoch": 0.12, - "learning_rate": 1.995654723546236e-05, - "loss": 0.8728, + "epoch": 0.1, + "learning_rate": 1.9974401381499515e-05, + "loss": 0.9631, "step": 229 }, { - "epoch": 0.12, - "learning_rate": 1.9955768404288167e-05, - "loss": 0.9177, + "epoch": 0.1, + "learning_rate": 1.997387108543469e-05, + "loss": 0.8721, "step": 230 }, { - "epoch": 0.12, - "learning_rate": 1.995498267070171e-05, - "loss": 0.8364, + "epoch": 0.11, + "learning_rate": 1.997333535996582e-05, + "loss": 0.9065, "step": 231 }, { - "epoch": 0.12, - "learning_rate": 1.995419003524774e-05, - "loss": 0.9104, + "epoch": 0.11, + "learning_rate": 1.9972794205384544e-05, + "loss": 0.9429, "step": 232 }, { - "epoch": 0.12, - "learning_rate": 1.99533904984758e-05, - "loss": 0.9067, + "epoch": 0.11, + "learning_rate": 1.9972247621985428e-05, + "loss": 0.9624, "step": 233 }, { - "epoch": 0.12, - "learning_rate": 1.9952584060940218e-05, - "loss": 0.8738, + "epoch": 0.11, + "learning_rate": 1.9971695610066028e-05, + "loss": 0.844, "step": 234 }, { - "epoch": 0.12, - "learning_rate": 1.9951770723200097e-05, - "loss": 0.9028, + "epoch": 0.11, + "learning_rate": 1.9971138169926827e-05, + "loss": 0.8855, "step": 235 }, { - "epoch": 0.12, - "learning_rate": 1.9950950485819334e-05, - "loss": 0.9141, + "epoch": 0.11, + "learning_rate": 1.997057530187128e-05, + "loss": 0.9146, "step": 236 }, { - "epoch": 0.12, - "learning_rate": 1.9950123349366607e-05, - "loss": 0.8889, + "epoch": 0.11, + "learning_rate": 1.9970007006205793e-05, + "loss": 0.8435, "step": 237 }, { - "epoch": 0.12, - "learning_rate": 1.9949289314415373e-05, - "loss": 0.9404, + "epoch": 0.11, + "learning_rate": 1.9969433283239726e-05, + "loss": 0.9187, "step": 238 }, { - "epoch": 0.12, - "learning_rate": 1.994844838154388e-05, - "loss": 0.8252, + "epoch": 0.11, + "learning_rate": 1.9968854133285383e-05, + "loss": 0.9111, "step": 239 }, { - "epoch": 0.12, - "learning_rate": 1.9947600551335147e-05, - "loss": 0.9084, + "epoch": 0.11, + "learning_rate": 1.9968269556658044e-05, + "loss": 0.9443, "step": 240 }, { - "epoch": 0.12, - "learning_rate": 1.9946745824376984e-05, - "loss": 0.8926, + "epoch": 0.11, + "learning_rate": 1.996767955367592e-05, + "loss": 0.8647, "step": 241 }, { - "epoch": 0.12, - "learning_rate": 1.9945884201261982e-05, - "loss": 0.8921, + "epoch": 0.11, + "learning_rate": 1.9967084124660197e-05, + "loss": 0.8772, "step": 242 }, { - "epoch": 0.12, - "learning_rate": 1.9945015682587512e-05, - "loss": 0.8523, + "epoch": 0.11, + "learning_rate": 1.9966483269934997e-05, + "loss": 0.8761, "step": 243 }, { - "epoch": 0.13, - "learning_rate": 1.994414026895572e-05, - "loss": 0.9075, + "epoch": 0.11, + "learning_rate": 1.9965876989827407e-05, + "loss": 0.9436, "step": 244 }, { - "epoch": 0.13, - "learning_rate": 1.9943257960973537e-05, - "loss": 0.8438, + "epoch": 0.11, + "learning_rate": 1.996526528466746e-05, + "loss": 0.9155, "step": 245 }, { - "epoch": 0.13, - "learning_rate": 1.994236875925268e-05, - "loss": 0.8518, + "epoch": 0.11, + "learning_rate": 1.9964648154788146e-05, + "loss": 0.8958, "step": 246 }, { - "epoch": 0.13, - "learning_rate": 1.9941472664409637e-05, - "loss": 0.8567, + "epoch": 0.11, + "learning_rate": 1.9964025600525406e-05, + "loss": 0.8242, "step": 247 }, { - "epoch": 0.13, - "learning_rate": 1.994056967706567e-05, - "loss": 0.9104, + "epoch": 0.11, + "learning_rate": 1.9963397622218143e-05, + "loss": 0.877, "step": 248 }, { - "epoch": 0.13, - "learning_rate": 1.993965979784684e-05, - "loss": 0.8613, + "epoch": 0.11, + "learning_rate": 1.9962764220208196e-05, + "loss": 0.9027, "step": 249 }, { - "epoch": 0.13, - "learning_rate": 1.9938743027383966e-05, - "loss": 0.8877, + "epoch": 0.11, + "learning_rate": 1.996212539484037e-05, + "loss": 0.9148, "step": 250 }, { - "epoch": 0.13, - "learning_rate": 1.993781936631265e-05, - "loss": 0.8484, + "epoch": 0.11, + "learning_rate": 1.996148114646242e-05, + "loss": 0.8701, "step": 251 }, { - "epoch": 0.13, - "learning_rate": 1.993688881527328e-05, - "loss": 0.9001, + "epoch": 0.11, + "learning_rate": 1.9960831475425043e-05, + "loss": 0.8154, "step": 252 }, { - "epoch": 0.13, - "learning_rate": 1.993595137491101e-05, - "loss": 0.8394, + "epoch": 0.12, + "learning_rate": 1.9960176382081902e-05, + "loss": 0.8845, "step": 253 }, { - "epoch": 0.13, - "learning_rate": 1.9935007045875776e-05, - "loss": 0.8789, + "epoch": 0.12, + "learning_rate": 1.9959515866789606e-05, + "loss": 0.8589, "step": 254 }, { - "epoch": 0.13, - "learning_rate": 1.993405582882229e-05, - "loss": 0.8784, + "epoch": 0.12, + "learning_rate": 1.9958849929907708e-05, + "loss": 0.848, "step": 255 }, { - "epoch": 0.13, - "learning_rate": 1.9933097724410033e-05, - "loss": 0.9128, + "epoch": 0.12, + "learning_rate": 1.9958178571798727e-05, + "loss": 0.9482, "step": 256 }, { - "epoch": 0.13, - "learning_rate": 1.9932132733303273e-05, - "loss": 0.8599, + "epoch": 0.12, + "learning_rate": 1.9957501792828123e-05, + "loss": 0.8579, "step": 257 }, { - "epoch": 0.13, - "learning_rate": 1.9931160856171044e-05, - "loss": 0.8755, + "epoch": 0.12, + "learning_rate": 1.995681959336431e-05, + "loss": 0.8638, "step": 258 }, { - "epoch": 0.13, - "learning_rate": 1.993018209368715e-05, - "loss": 0.9299, + "epoch": 0.12, + "learning_rate": 1.995613197377865e-05, + "loss": 0.9011, "step": 259 }, { - "epoch": 0.13, - "learning_rate": 1.9929196446530184e-05, - "loss": 0.9377, + "epoch": 0.12, + "learning_rate": 1.9955438934445456e-05, + "loss": 0.9006, "step": 260 }, { - "epoch": 0.13, - "learning_rate": 1.9928203915383497e-05, - "loss": 0.8855, + "epoch": 0.12, + "learning_rate": 1.9954740475741998e-05, + "loss": 0.8416, "step": 261 }, { - "epoch": 0.13, - "learning_rate": 1.992720450093522e-05, - "loss": 0.9084, + "epoch": 0.12, + "learning_rate": 1.9954036598048487e-05, + "loss": 0.8613, "step": 262 }, { - "epoch": 0.14, - "learning_rate": 1.992619820387826e-05, - "loss": 0.8564, + "epoch": 0.12, + "learning_rate": 1.9953327301748086e-05, + "loss": 0.8535, "step": 263 }, { - "epoch": 0.14, - "learning_rate": 1.992518502491028e-05, - "loss": 0.854, + "epoch": 0.12, + "learning_rate": 1.9952612587226914e-05, + "loss": 0.881, "step": 264 }, { - "epoch": 0.14, - "learning_rate": 1.992416496473373e-05, - "loss": 0.8569, + "epoch": 0.12, + "learning_rate": 1.995189245487404e-05, + "loss": 0.8989, "step": 265 }, { - "epoch": 0.14, - "learning_rate": 1.992313802405583e-05, - "loss": 0.9187, - "step": 266 + "epoch": 0.12, + "learning_rate": 1.995116690508146e-05, + "loss": 0.8284, + "step": 266 }, { - "epoch": 0.14, - "learning_rate": 1.992210420358856e-05, - "loss": 0.9106, + "epoch": 0.12, + "learning_rate": 1.995043593824415e-05, + "loss": 0.8875, "step": 267 }, { - "epoch": 0.14, - "learning_rate": 1.992106350404868e-05, - "loss": 0.8472, + "epoch": 0.12, + "learning_rate": 1.994969955476002e-05, + "loss": 0.8397, "step": 268 }, { - "epoch": 0.14, - "learning_rate": 1.9920015926157714e-05, - "loss": 0.8738, + "epoch": 0.12, + "learning_rate": 1.9948957755029927e-05, + "loss": 0.8342, "step": 269 }, { - "epoch": 0.14, - "learning_rate": 1.9918961470641955e-05, - "loss": 0.9287, + "epoch": 0.12, + "learning_rate": 1.994821053945768e-05, + "loss": 0.8936, "step": 270 }, { - "epoch": 0.14, - "learning_rate": 1.991790013823246e-05, - "loss": 0.9446, + "epoch": 0.12, + "learning_rate": 1.9947457908450033e-05, + "loss": 0.8649, "step": 271 }, { - "epoch": 0.14, - "learning_rate": 1.9916831929665074e-05, - "loss": 0.8872, + "epoch": 0.12, + "learning_rate": 1.9946699862416692e-05, + "loss": 0.8838, "step": 272 }, { - "epoch": 0.14, - "learning_rate": 1.9915756845680378e-05, - "loss": 0.9023, + "epoch": 0.12, + "learning_rate": 1.9945936401770312e-05, + "loss": 0.8376, "step": 273 }, { - "epoch": 0.14, - "learning_rate": 1.9914674887023748e-05, - "loss": 0.8938, + "epoch": 0.12, + "learning_rate": 1.994516752692649e-05, + "loss": 0.8807, "step": 274 }, { - "epoch": 0.14, - "learning_rate": 1.9913586054445306e-05, - "loss": 0.8564, + "epoch": 0.13, + "learning_rate": 1.994439323830377e-05, + "loss": 0.8608, "step": 275 }, { - "epoch": 0.14, - "learning_rate": 1.9912490348699953e-05, - "loss": 0.8391, + "epoch": 0.13, + "learning_rate": 1.9943613536323653e-05, + "loss": 0.8313, "step": 276 }, { - "epoch": 0.14, - "learning_rate": 1.9911387770547348e-05, - "loss": 0.7908, + "epoch": 0.13, + "learning_rate": 1.9942828421410575e-05, + "loss": 0.9368, "step": 277 }, { - "epoch": 0.14, - "learning_rate": 1.991027832075192e-05, - "loss": 0.8835, + "epoch": 0.13, + "learning_rate": 1.994203789399192e-05, + "loss": 0.9302, "step": 278 }, { - "epoch": 0.14, - "learning_rate": 1.9909162000082855e-05, - "loss": 0.8896, + "epoch": 0.13, + "learning_rate": 1.994124195449803e-05, + "loss": 0.8767, "step": 279 }, { - "epoch": 0.14, - "learning_rate": 1.9908038809314113e-05, - "loss": 0.8977, + "epoch": 0.13, + "learning_rate": 1.9940440603362177e-05, + "loss": 0.8711, "step": 280 }, { - "epoch": 0.14, - "learning_rate": 1.990690874922441e-05, - "loss": 0.845, + "epoch": 0.13, + "learning_rate": 1.993963384102059e-05, + "loss": 0.9104, "step": 281 }, { - "epoch": 0.14, - "learning_rate": 1.9905771820597214e-05, - "loss": 0.9316, + "epoch": 0.13, + "learning_rate": 1.9938821667912442e-05, + "loss": 0.8608, "step": 282 }, { - "epoch": 0.15, - "learning_rate": 1.990462802422078e-05, - "loss": 0.9189, + "epoch": 0.13, + "learning_rate": 1.9938004084479846e-05, + "loss": 0.8354, "step": 283 }, { - "epoch": 0.15, - "learning_rate": 1.9903477360888105e-05, - "loss": 0.8677, + "epoch": 0.13, + "learning_rate": 1.9937181091167868e-05, + "loss": 0.9082, "step": 284 }, { - "epoch": 0.15, - "learning_rate": 1.9902319831396956e-05, - "loss": 0.8713, + "epoch": 0.13, + "learning_rate": 1.9936352688424513e-05, + "loss": 0.8352, "step": 285 }, { - "epoch": 0.15, - "learning_rate": 1.9901155436549856e-05, - "loss": 0.8643, + "epoch": 0.13, + "learning_rate": 1.9935518876700732e-05, + "loss": 0.8906, "step": 286 }, { - "epoch": 0.15, - "learning_rate": 1.9899984177154087e-05, - "loss": 0.9072, + "epoch": 0.13, + "learning_rate": 1.9934679656450422e-05, + "loss": 0.9199, "step": 287 }, { - "epoch": 0.15, - "learning_rate": 1.9898806054021694e-05, - "loss": 0.8772, + "epoch": 0.13, + "learning_rate": 1.9933835028130426e-05, + "loss": 0.9351, "step": 288 }, { - "epoch": 0.15, - "learning_rate": 1.9897621067969483e-05, - "loss": 0.918, + "epoch": 0.13, + "learning_rate": 1.993298499220052e-05, + "loss": 0.8931, "step": 289 }, { - "epoch": 0.15, - "learning_rate": 1.9896429219819003e-05, - "loss": 0.8721, + "epoch": 0.13, + "learning_rate": 1.993212954912344e-05, + "loss": 0.8181, "step": 290 }, { - "epoch": 0.15, - "learning_rate": 1.9895230510396583e-05, - "loss": 0.873, + "epoch": 0.13, + "learning_rate": 1.9931268699364854e-05, + "loss": 0.8492, "step": 291 }, { - "epoch": 0.15, - "learning_rate": 1.989402494053329e-05, - "loss": 0.8562, + "epoch": 0.13, + "learning_rate": 1.9930402443393376e-05, + "loss": 0.8926, "step": 292 }, { - "epoch": 0.15, - "learning_rate": 1.9892812511064962e-05, - "loss": 0.8137, + "epoch": 0.13, + "learning_rate": 1.9929530781680566e-05, + "loss": 0.854, "step": 293 }, { - "epoch": 0.15, - "learning_rate": 1.989159322283218e-05, - "loss": 0.8589, + "epoch": 0.13, + "learning_rate": 1.992865371470092e-05, + "loss": 0.9211, "step": 294 }, { - "epoch": 0.15, - "learning_rate": 1.9890367076680292e-05, - "loss": 0.8972, + "epoch": 0.13, + "learning_rate": 1.9927771242931892e-05, + "loss": 0.8369, "step": 295 }, { - "epoch": 0.15, - "learning_rate": 1.988913407345939e-05, - "loss": 0.8237, + "epoch": 0.13, + "learning_rate": 1.992688336685385e-05, + "loss": 0.8187, "step": 296 }, { - "epoch": 0.15, - "learning_rate": 1.9887894214024324e-05, - "loss": 0.908, + "epoch": 0.14, + "learning_rate": 1.992599008695013e-05, + "loss": 0.8916, "step": 297 }, { - "epoch": 0.15, - "learning_rate": 1.98866474992347e-05, - "loss": 0.8625, + "epoch": 0.14, + "learning_rate": 1.9925091403706998e-05, + "loss": 0.8506, "step": 298 }, { - "epoch": 0.15, - "learning_rate": 1.9885393929954876e-05, - "loss": 0.8257, + "epoch": 0.14, + "learning_rate": 1.9924187317613665e-05, + "loss": 0.8557, "step": 299 }, { - "epoch": 0.15, - "learning_rate": 1.988413350705396e-05, - "loss": 0.8633, + "epoch": 0.14, + "learning_rate": 1.9923277829162283e-05, + "loss": 0.9028, "step": 300 }, { - "epoch": 0.15, - "learning_rate": 1.9882866231405812e-05, - "loss": 0.8123, + "epoch": 0.14, + "learning_rate": 1.9922362938847944e-05, + "loss": 0.8723, "step": 301 }, { - "epoch": 0.16, - "learning_rate": 1.988159210388905e-05, - "loss": 0.8933, + "epoch": 0.14, + "learning_rate": 1.992144264716868e-05, + "loss": 0.8296, "step": 302 }, { - "epoch": 0.16, - "learning_rate": 1.988031112538703e-05, - "loss": 0.8765, + "epoch": 0.14, + "learning_rate": 1.9920516954625455e-05, + "loss": 0.7948, "step": 303 }, { - "epoch": 0.16, - "learning_rate": 1.9879023296787866e-05, - "loss": 0.8257, + "epoch": 0.14, + "learning_rate": 1.9919585861722193e-05, + "loss": 0.8627, "step": 304 }, { - "epoch": 0.16, - "learning_rate": 1.987772861898442e-05, - "loss": 0.8804, + "epoch": 0.14, + "learning_rate": 1.991864936896574e-05, + "loss": 0.8721, "step": 305 }, { - "epoch": 0.16, - "learning_rate": 1.987642709287431e-05, - "loss": 0.8921, + "epoch": 0.14, + "learning_rate": 1.991770747686589e-05, + "loss": 0.8342, "step": 306 }, { - "epoch": 0.16, - "learning_rate": 1.987511871935988e-05, - "loss": 0.9338, + "epoch": 0.14, + "learning_rate": 1.9916760185935376e-05, + "loss": 0.8303, "step": 307 }, { - "epoch": 0.16, - "learning_rate": 1.9873803499348244e-05, - "loss": 0.8284, + "epoch": 0.14, + "learning_rate": 1.9915807496689863e-05, + "loss": 0.875, "step": 308 }, { - "epoch": 0.16, - "learning_rate": 1.9872481433751255e-05, - "loss": 0.814, + "epoch": 0.14, + "learning_rate": 1.9914849409647964e-05, + "loss": 0.8602, "step": 309 }, { - "epoch": 0.16, - "learning_rate": 1.9871152523485507e-05, - "loss": 0.8254, + "epoch": 0.14, + "learning_rate": 1.991388592533122e-05, + "loss": 0.9458, "step": 310 }, { - "epoch": 0.16, - "learning_rate": 1.986981676947235e-05, - "loss": 0.8479, + "epoch": 0.14, + "learning_rate": 1.9912917044264123e-05, + "loss": 0.915, "step": 311 }, { - "epoch": 0.16, - "learning_rate": 1.9868474172637864e-05, - "loss": 0.8691, + "epoch": 0.14, + "learning_rate": 1.9911942766974093e-05, + "loss": 0.8589, "step": 312 }, { - "epoch": 0.16, - "learning_rate": 1.986712473391289e-05, - "loss": 0.8281, + "epoch": 0.14, + "learning_rate": 1.991096309399149e-05, + "loss": 0.8354, "step": 313 }, { - "epoch": 0.16, - "learning_rate": 1.9865768454233003e-05, - "loss": 0.8613, + "epoch": 0.14, + "learning_rate": 1.9909978025849613e-05, + "loss": 0.8782, "step": 314 }, { - "epoch": 0.16, - "learning_rate": 1.9864405334538518e-05, - "loss": 0.7949, + "epoch": 0.14, + "learning_rate": 1.990898756308469e-05, + "loss": 0.9065, "step": 315 }, { - "epoch": 0.16, - "learning_rate": 1.9863035375774504e-05, - "loss": 0.771, + "epoch": 0.14, + "learning_rate": 1.99079917062359e-05, + "loss": 0.8082, "step": 316 }, { - "epoch": 0.16, - "learning_rate": 1.986165857889075e-05, - "loss": 0.8784, + "epoch": 0.14, + "learning_rate": 1.990699045584535e-05, + "loss": 0.8226, "step": 317 }, { - "epoch": 0.16, - "learning_rate": 1.9860274944841816e-05, - "loss": 0.8823, + "epoch": 0.14, + "learning_rate": 1.9905983812458078e-05, + "loss": 0.8804, "step": 318 }, { - "epoch": 0.16, - "learning_rate": 1.985888447458698e-05, - "loss": 0.8818, + "epoch": 0.15, + "learning_rate": 1.9904971776622067e-05, + "loss": 0.8416, "step": 319 }, { - "epoch": 0.16, - "learning_rate": 1.9857487169090265e-05, - "loss": 0.842, + "epoch": 0.15, + "learning_rate": 1.9903954348888228e-05, + "loss": 0.8628, "step": 320 }, { - "epoch": 0.16, - "learning_rate": 1.9856083029320436e-05, - "loss": 0.8616, + "epoch": 0.15, + "learning_rate": 1.9902931529810415e-05, + "loss": 0.9172, "step": 321 }, { - "epoch": 0.17, - "learning_rate": 1.9854672056250992e-05, - "loss": 0.8625, + "epoch": 0.15, + "learning_rate": 1.9901903319945413e-05, + "loss": 0.9102, "step": 322 }, { - "epoch": 0.17, - "learning_rate": 1.9853254250860174e-05, - "loss": 0.9026, + "epoch": 0.15, + "learning_rate": 1.9900869719852935e-05, + "loss": 0.8618, "step": 323 }, { - "epoch": 0.17, - "learning_rate": 1.9851829614130953e-05, - "loss": 0.8489, + "epoch": 0.15, + "learning_rate": 1.9899830730095645e-05, + "loss": 0.9197, "step": 324 }, { - "epoch": 0.17, - "learning_rate": 1.9850398147051045e-05, - "loss": 0.9231, + "epoch": 0.15, + "learning_rate": 1.989878635123912e-05, + "loss": 0.8765, "step": 325 }, { - "epoch": 0.17, - "learning_rate": 1.9848959850612895e-05, - "loss": 0.8958, + "epoch": 0.15, + "learning_rate": 1.9897736583851882e-05, + "loss": 0.8293, "step": 326 }, { - "epoch": 0.17, - "learning_rate": 1.984751472581369e-05, - "loss": 0.8926, + "epoch": 0.15, + "learning_rate": 1.989668142850539e-05, + "loss": 0.8445, "step": 327 }, { - "epoch": 0.17, - "learning_rate": 1.9846062773655343e-05, - "loss": 0.8879, + "epoch": 0.15, + "learning_rate": 1.9895620885774033e-05, + "loss": 0.8416, "step": 328 }, { - "epoch": 0.17, - "learning_rate": 1.98446039951445e-05, - "loss": 0.7971, + "epoch": 0.15, + "learning_rate": 1.9894554956235123e-05, + "loss": 0.9031, "step": 329 }, { - "epoch": 0.17, - "learning_rate": 1.9843138391292546e-05, - "loss": 0.8228, + "epoch": 0.15, + "learning_rate": 1.9893483640468922e-05, + "loss": 0.8784, "step": 330 }, { - "epoch": 0.17, - "learning_rate": 1.98416659631156e-05, - "loss": 0.8333, + "epoch": 0.15, + "learning_rate": 1.98924069390586e-05, + "loss": 0.7738, "step": 331 }, { - "epoch": 0.17, - "learning_rate": 1.9840186711634502e-05, - "loss": 0.9097, + "epoch": 0.15, + "learning_rate": 1.9891324852590293e-05, + "loss": 0.8567, "step": 332 }, { - "epoch": 0.17, - "learning_rate": 1.9838700637874834e-05, - "loss": 0.8564, + "epoch": 0.15, + "learning_rate": 1.989023738165303e-05, + "loss": 0.7922, "step": 333 }, { - "epoch": 0.17, - "learning_rate": 1.98372077428669e-05, - "loss": 0.8523, + "epoch": 0.15, + "learning_rate": 1.9889144526838802e-05, + "loss": 0.8673, "step": 334 }, { - "epoch": 0.17, - "learning_rate": 1.9835708027645738e-05, - "loss": 0.9167, + "epoch": 0.15, + "learning_rate": 1.9888046288742513e-05, + "loss": 0.9302, "step": 335 }, { - "epoch": 0.17, - "learning_rate": 1.9834201493251107e-05, - "loss": 0.8689, + "epoch": 0.15, + "learning_rate": 1.9886942667962002e-05, + "loss": 0.8374, "step": 336 }, { - "epoch": 0.17, - "learning_rate": 1.9832688140727502e-05, - "loss": 0.8428, + "epoch": 0.15, + "learning_rate": 1.9885833665098045e-05, + "loss": 0.8882, "step": 337 }, { - "epoch": 0.17, - "learning_rate": 1.9831167971124142e-05, - "loss": 0.8755, + "epoch": 0.15, + "learning_rate": 1.9884719280754334e-05, + "loss": 0.8231, "step": 338 }, { - "epoch": 0.17, - "learning_rate": 1.9829640985494977e-05, - "loss": 0.9248, + "epoch": 0.15, + "learning_rate": 1.9883599515537507e-05, + "loss": 0.8088, "step": 339 }, { - "epoch": 0.17, - "learning_rate": 1.982810718489867e-05, - "loss": 0.8784, + "epoch": 0.15, + "learning_rate": 1.988247437005711e-05, + "loss": 0.8298, "step": 340 }, { - "epoch": 0.18, - "learning_rate": 1.9826566570398622e-05, - "loss": 0.897, + "epoch": 0.16, + "learning_rate": 1.9881343844925648e-05, + "loss": 0.7955, "step": 341 }, { - "epoch": 0.18, - "learning_rate": 1.9825019143062953e-05, - "loss": 0.8379, + "epoch": 0.16, + "learning_rate": 1.988020794075852e-05, + "loss": 0.8682, "step": 342 }, { - "epoch": 0.18, - "learning_rate": 1.9823464903964504e-05, - "loss": 0.8708, + "epoch": 0.16, + "learning_rate": 1.9879066658174078e-05, + "loss": 0.8599, "step": 343 }, { - "epoch": 0.18, - "learning_rate": 1.9821903854180844e-05, - "loss": 0.8455, + "epoch": 0.16, + "learning_rate": 1.987791999779359e-05, + "loss": 0.9158, "step": 344 }, { - "epoch": 0.18, - "learning_rate": 1.982033599479426e-05, - "loss": 0.875, + "epoch": 0.16, + "learning_rate": 1.9876767960241264e-05, + "loss": 0.8582, "step": 345 }, { - "epoch": 0.18, - "learning_rate": 1.981876132689176e-05, - "loss": 0.8713, + "epoch": 0.16, + "learning_rate": 1.9875610546144216e-05, + "loss": 0.9666, "step": 346 }, { - "epoch": 0.18, - "learning_rate": 1.9817179851565075e-05, - "loss": 0.875, + "epoch": 0.16, + "learning_rate": 1.9874447756132505e-05, + "loss": 0.9175, "step": 347 }, { - "epoch": 0.18, - "learning_rate": 1.9815591569910654e-05, - "loss": 0.9185, + "epoch": 0.16, + "learning_rate": 1.987327959083911e-05, + "loss": 0.8816, "step": 348 }, { - "epoch": 0.18, - "learning_rate": 1.981399648302967e-05, - "loss": 0.8687, + "epoch": 0.16, + "learning_rate": 1.987210605089993e-05, + "loss": 0.876, "step": 349 }, { - "epoch": 0.18, - "learning_rate": 1.9812394592027994e-05, - "loss": 0.8396, + "epoch": 0.16, + "learning_rate": 1.9870927136953806e-05, + "loss": 0.8945, "step": 350 }, { - "epoch": 0.18, - "learning_rate": 1.9810785898016246e-05, - "loss": 0.823, + "epoch": 0.16, + "learning_rate": 1.986974284964249e-05, + "loss": 0.8518, "step": 351 }, { - "epoch": 0.18, - "learning_rate": 1.980917040210974e-05, - "loss": 0.8799, + "epoch": 0.16, + "learning_rate": 1.9868553189610663e-05, + "loss": 0.8552, "step": 352 }, { - "epoch": 0.18, - "learning_rate": 1.980754810542851e-05, - "loss": 0.8889, + "epoch": 0.16, + "learning_rate": 1.986735815750594e-05, + "loss": 0.7735, "step": 353 }, { - "epoch": 0.18, - "learning_rate": 1.9805919009097308e-05, - "loss": 0.8713, + "epoch": 0.16, + "learning_rate": 1.9866157753978838e-05, + "loss": 0.8251, "step": 354 }, { - "epoch": 0.18, - "learning_rate": 1.9804283114245605e-05, - "loss": 0.8711, + "epoch": 0.16, + "learning_rate": 1.986495197968282e-05, + "loss": 0.8655, "step": 355 }, { - "epoch": 0.18, - "learning_rate": 1.9802640422007574e-05, - "loss": 0.8782, + "epoch": 0.16, + "learning_rate": 1.9863740835274267e-05, + "loss": 0.8412, "step": 356 }, { - "epoch": 0.18, - "learning_rate": 1.9800990933522104e-05, - "loss": 0.8232, + "epoch": 0.16, + "learning_rate": 1.9862524321412477e-05, + "loss": 0.9058, "step": 357 }, { - "epoch": 0.18, - "learning_rate": 1.9799334649932804e-05, - "loss": 0.8655, + "epoch": 0.16, + "learning_rate": 1.9861302438759676e-05, + "loss": 0.8544, "step": 358 }, { - "epoch": 0.18, - "learning_rate": 1.9797671572387985e-05, - "loss": 0.9009, + "epoch": 0.16, + "learning_rate": 1.986007518798101e-05, + "loss": 0.9048, "step": 359 }, { - "epoch": 0.19, - "learning_rate": 1.979600170204067e-05, - "loss": 0.8376, + "epoch": 0.16, + "learning_rate": 1.985884256974455e-05, + "loss": 0.8348, "step": 360 }, { - "epoch": 0.19, - "learning_rate": 1.9794325040048598e-05, - "loss": 0.7925, + "epoch": 0.16, + "learning_rate": 1.985760458472129e-05, + "loss": 0.81, "step": 361 }, { - "epoch": 0.19, - "learning_rate": 1.9792641587574212e-05, - "loss": 0.8984, + "epoch": 0.16, + "learning_rate": 1.9856361233585133e-05, + "loss": 0.9072, "step": 362 }, { - "epoch": 0.19, - "learning_rate": 1.979095134578466e-05, - "loss": 0.9011, + "epoch": 0.17, + "learning_rate": 1.9855112517012928e-05, + "loss": 0.8667, "step": 363 }, { - "epoch": 0.19, - "learning_rate": 1.97892543158518e-05, - "loss": 0.8574, + "epoch": 0.17, + "learning_rate": 1.985385843568442e-05, + "loss": 0.8297, "step": 364 }, { - "epoch": 0.19, - "learning_rate": 1.9787550498952198e-05, - "loss": 0.7725, + "epoch": 0.17, + "learning_rate": 1.985259899028228e-05, + "loss": 0.896, "step": 365 }, { - "epoch": 0.19, - "learning_rate": 1.978583989626712e-05, - "loss": 0.9104, + "epoch": 0.17, + "learning_rate": 1.9851334181492117e-05, + "loss": 0.8467, "step": 366 }, { - "epoch": 0.19, - "learning_rate": 1.978412250898254e-05, - "loss": 0.8418, + "epoch": 0.17, + "learning_rate": 1.9850064010002436e-05, + "loss": 0.9292, "step": 367 }, { - "epoch": 0.19, - "learning_rate": 1.9782398338289143e-05, - "loss": 0.8455, + "epoch": 0.17, + "learning_rate": 1.9848788476504676e-05, + "loss": 0.8354, "step": 368 }, { - "epoch": 0.19, - "learning_rate": 1.9780667385382303e-05, - "loss": 0.8806, + "epoch": 0.17, + "learning_rate": 1.9847507581693183e-05, + "loss": 0.8065, "step": 369 }, { - "epoch": 0.19, - "learning_rate": 1.977892965146211e-05, - "loss": 0.8762, + "epoch": 0.17, + "learning_rate": 1.984622132626523e-05, + "loss": 0.832, "step": 370 }, { - "epoch": 0.19, - "learning_rate": 1.977718513773334e-05, - "loss": 0.8093, + "epoch": 0.17, + "learning_rate": 1.9844929710921014e-05, + "loss": 0.8447, "step": 371 }, { - "epoch": 0.19, - "learning_rate": 1.9775433845405483e-05, - "loss": 0.8267, + "epoch": 0.17, + "learning_rate": 1.984363273636364e-05, + "loss": 0.7839, "step": 372 }, { - "epoch": 0.19, - "learning_rate": 1.9773675775692727e-05, - "loss": 0.9141, + "epoch": 0.17, + "learning_rate": 1.9842330403299125e-05, + "loss": 0.8899, "step": 373 }, { - "epoch": 0.19, - "learning_rate": 1.9771910929813945e-05, - "loss": 0.8962, + "epoch": 0.17, + "learning_rate": 1.984102271243642e-05, + "loss": 0.8625, "step": 374 }, { - "epoch": 0.19, - "learning_rate": 1.977013930899273e-05, - "loss": 0.8269, + "epoch": 0.17, + "learning_rate": 1.9839709664487373e-05, + "loss": 0.8818, "step": 375 }, { - "epoch": 0.19, - "learning_rate": 1.9768360914457355e-05, - "loss": 0.8279, + "epoch": 0.17, + "learning_rate": 1.9838391260166768e-05, + "loss": 0.8467, "step": 376 }, { - "epoch": 0.19, - "learning_rate": 1.9766575747440795e-05, - "loss": 0.873, + "epoch": 0.17, + "learning_rate": 1.983706750019229e-05, + "loss": 0.8296, "step": 377 }, { - "epoch": 0.19, - "learning_rate": 1.976478380918072e-05, - "loss": 0.844, + "epoch": 0.17, + "learning_rate": 1.9835738385284552e-05, + "loss": 0.9395, "step": 378 }, { - "epoch": 0.19, - "learning_rate": 1.97629851009195e-05, - "loss": 0.8406, + "epoch": 0.17, + "learning_rate": 1.9834403916167068e-05, + "loss": 0.8542, "step": 379 }, { - "epoch": 0.2, - "learning_rate": 1.9761179623904187e-05, - "loss": 0.8567, + "epoch": 0.17, + "learning_rate": 1.9833064093566268e-05, + "loss": 0.7789, "step": 380 }, { - "epoch": 0.2, - "learning_rate": 1.975936737938653e-05, - "loss": 0.8352, + "epoch": 0.17, + "learning_rate": 1.9831718918211512e-05, + "loss": 0.8784, "step": 381 }, { - "epoch": 0.2, - "learning_rate": 1.9757548368622982e-05, - "loss": 0.8403, + "epoch": 0.17, + "learning_rate": 1.9830368390835057e-05, + "loss": 0.8821, "step": 382 }, { - "epoch": 0.2, - "learning_rate": 1.975572259287467e-05, - "loss": 0.8396, + "epoch": 0.17, + "learning_rate": 1.9829012512172084e-05, + "loss": 0.8538, "step": 383 }, { - "epoch": 0.2, - "learning_rate": 1.975389005340742e-05, - "loss": 0.9617, + "epoch": 0.17, + "learning_rate": 1.982765128296068e-05, + "loss": 0.8672, "step": 384 }, { - "epoch": 0.2, - "learning_rate": 1.975205075149175e-05, - "loss": 0.915, + "epoch": 0.18, + "learning_rate": 1.982628470394185e-05, + "loss": 0.8893, "step": 385 }, { - "epoch": 0.2, - "learning_rate": 1.975020468840286e-05, - "loss": 0.8733, + "epoch": 0.18, + "learning_rate": 1.9824912775859503e-05, + "loss": 0.9065, "step": 386 }, { - "epoch": 0.2, - "learning_rate": 1.9748351865420635e-05, - "loss": 0.8752, + "epoch": 0.18, + "learning_rate": 1.9823535499460472e-05, + "loss": 0.8943, "step": 387 }, { - "epoch": 0.2, - "learning_rate": 1.9746492283829658e-05, - "loss": 0.8359, + "epoch": 0.18, + "learning_rate": 1.9822152875494494e-05, + "loss": 0.8945, "step": 388 }, { - "epoch": 0.2, - "learning_rate": 1.9744625944919194e-05, - "loss": 0.8789, + "epoch": 0.18, + "learning_rate": 1.9820764904714217e-05, + "loss": 0.854, "step": 389 }, { - "epoch": 0.2, - "learning_rate": 1.974275284998318e-05, - "loss": 0.812, + "epoch": 0.18, + "learning_rate": 1.98193715878752e-05, + "loss": 0.8804, "step": 390 }, { - "epoch": 0.2, - "learning_rate": 1.9740873000320255e-05, - "loss": 0.8381, + "epoch": 0.18, + "learning_rate": 1.981797292573591e-05, + "loss": 0.8774, "step": 391 }, { - "epoch": 0.2, - "learning_rate": 1.9738986397233736e-05, - "loss": 0.8079, + "epoch": 0.18, + "learning_rate": 1.9816568919057733e-05, + "loss": 0.9187, "step": 392 }, { - "epoch": 0.2, - "learning_rate": 1.973709304203161e-05, - "loss": 0.8655, + "epoch": 0.18, + "learning_rate": 1.9815159568604955e-05, + "loss": 0.8672, "step": 393 }, { - "epoch": 0.2, - "learning_rate": 1.9735192936026564e-05, - "loss": 0.9353, + "epoch": 0.18, + "learning_rate": 1.9813744875144768e-05, + "loss": 0.8411, "step": 394 }, { - "epoch": 0.2, - "learning_rate": 1.973328608053595e-05, - "loss": 0.8376, + "epoch": 0.18, + "learning_rate": 1.981232483944729e-05, + "loss": 0.926, "step": 395 }, { - "epoch": 0.2, - "learning_rate": 1.973137247688181e-05, - "loss": 0.8469, + "epoch": 0.18, + "learning_rate": 1.9810899462285525e-05, + "loss": 0.833, "step": 396 }, { - "epoch": 0.2, - "learning_rate": 1.972945212639086e-05, - "loss": 0.8628, + "epoch": 0.18, + "learning_rate": 1.9809468744435404e-05, + "loss": 0.8179, "step": 397 }, { - "epoch": 0.2, - "learning_rate": 1.9727525030394495e-05, - "loss": 0.9031, + "epoch": 0.18, + "learning_rate": 1.9808032686675748e-05, + "loss": 0.908, "step": 398 }, { - "epoch": 0.21, - "learning_rate": 1.9725591190228782e-05, - "loss": 0.8038, + "epoch": 0.18, + "learning_rate": 1.98065912897883e-05, + "loss": 0.856, "step": 399 }, { - "epoch": 0.21, - "learning_rate": 1.9723650607234473e-05, - "loss": 0.8271, + "epoch": 0.18, + "learning_rate": 1.98051445545577e-05, + "loss": 0.8916, "step": 400 }, { - "epoch": 0.21, - "learning_rate": 1.9721703282756982e-05, - "loss": 0.8215, + "epoch": 0.18, + "learning_rate": 1.98036924817715e-05, + "loss": 0.8337, "step": 401 }, { - "epoch": 0.21, - "learning_rate": 1.9719749218146408e-05, - "loss": 0.8313, + "epoch": 0.18, + "learning_rate": 1.9802235072220147e-05, + "loss": 0.8564, "step": 402 }, { - "epoch": 0.21, - "learning_rate": 1.9717788414757523e-05, - "loss": 0.8374, + "epoch": 0.18, + "learning_rate": 1.9800772326697008e-05, + "loss": 0.8428, "step": 403 }, { - "epoch": 0.21, - "learning_rate": 1.971582087394976e-05, - "loss": 0.843, + "epoch": 0.18, + "learning_rate": 1.9799304245998344e-05, + "loss": 0.8743, "step": 404 }, { - "epoch": 0.21, - "learning_rate": 1.971384659708724e-05, - "loss": 0.804, + "epoch": 0.18, + "learning_rate": 1.9797830830923327e-05, + "loss": 0.8838, "step": 405 }, { - "epoch": 0.21, - "learning_rate": 1.9711865585538733e-05, - "loss": 0.8435, + "epoch": 0.18, + "learning_rate": 1.979635208227402e-05, + "loss": 0.9106, "step": 406 }, { - "epoch": 0.21, - "learning_rate": 1.97098778406777e-05, - "loss": 0.8601, + "epoch": 0.19, + "learning_rate": 1.9794868000855407e-05, + "loss": 0.8722, "step": 407 }, { - "epoch": 0.21, - "learning_rate": 1.9707883363882256e-05, - "loss": 0.876, + "epoch": 0.19, + "learning_rate": 1.9793378587475366e-05, + "loss": 0.8518, "step": 408 }, { - "epoch": 0.21, - "learning_rate": 1.9705882156535183e-05, - "loss": 0.9082, + "epoch": 0.19, + "learning_rate": 1.9791883842944674e-05, + "loss": 0.798, "step": 409 }, { - "epoch": 0.21, - "learning_rate": 1.9703874220023942e-05, - "loss": 0.8496, + "epoch": 0.19, + "learning_rate": 1.9790383768077018e-05, + "loss": 0.8235, "step": 410 }, { - "epoch": 0.21, - "learning_rate": 1.9701859555740647e-05, - "loss": 0.8674, + "epoch": 0.19, + "learning_rate": 1.9788878363688984e-05, + "loss": 0.8313, "step": 411 }, { - "epoch": 0.21, - "learning_rate": 1.9699838165082078e-05, - "loss": 0.8459, + "epoch": 0.19, + "learning_rate": 1.978736763060005e-05, + "loss": 0.8706, "step": 412 }, { - "epoch": 0.21, - "learning_rate": 1.969781004944969e-05, - "loss": 0.8494, + "epoch": 0.19, + "learning_rate": 1.9785851569632614e-05, + "loss": 0.8496, "step": 413 }, { - "epoch": 0.21, - "learning_rate": 1.969577521024958e-05, - "loss": 0.8655, + "epoch": 0.19, + "learning_rate": 1.978433018161196e-05, + "loss": 0.8613, "step": 414 }, { - "epoch": 0.21, - "learning_rate": 1.9693733648892525e-05, - "loss": 0.8801, + "epoch": 0.19, + "learning_rate": 1.978280346736627e-05, + "loss": 0.863, "step": 415 }, { - "epoch": 0.21, - "learning_rate": 1.9691685366793952e-05, - "loss": 0.9219, + "epoch": 0.19, + "learning_rate": 1.978127142772663e-05, + "loss": 0.8662, "step": 416 }, { - "epoch": 0.21, - "learning_rate": 1.9689630365373954e-05, - "loss": 0.8645, + "epoch": 0.19, + "learning_rate": 1.9779734063527033e-05, + "loss": 0.7991, "step": 417 }, { - "epoch": 0.21, - "learning_rate": 1.9687568646057277e-05, - "loss": 0.8252, + "epoch": 0.19, + "learning_rate": 1.9778191375604355e-05, + "loss": 0.8997, "step": 418 }, { - "epoch": 0.22, - "learning_rate": 1.968550021027333e-05, - "loss": 0.856, + "epoch": 0.19, + "learning_rate": 1.9776643364798385e-05, + "loss": 0.8569, "step": 419 }, { - "epoch": 0.22, - "learning_rate": 1.9683425059456177e-05, - "loss": 0.8416, + "epoch": 0.19, + "learning_rate": 1.97750900319518e-05, + "loss": 0.8562, "step": 420 }, { - "epoch": 0.22, - "learning_rate": 1.968134319504453e-05, - "loss": 0.802, + "epoch": 0.19, + "learning_rate": 1.9773531377910168e-05, + "loss": 0.8665, "step": 421 }, { - "epoch": 0.22, - "learning_rate": 1.9679254618481765e-05, - "loss": 0.8284, + "epoch": 0.19, + "learning_rate": 1.9771967403521976e-05, + "loss": 0.8713, "step": 422 }, { - "epoch": 0.22, - "learning_rate": 1.967715933121591e-05, - "loss": 0.8813, + "epoch": 0.19, + "learning_rate": 1.9770398109638584e-05, + "loss": 0.835, "step": 423 }, { - "epoch": 0.22, - "learning_rate": 1.9675057334699644e-05, - "loss": 0.835, + "epoch": 0.19, + "learning_rate": 1.976882349711426e-05, + "loss": 0.8684, "step": 424 }, { - "epoch": 0.22, - "learning_rate": 1.9672948630390296e-05, - "loss": 0.8716, + "epoch": 0.19, + "learning_rate": 1.9767243566806165e-05, + "loss": 0.8186, "step": 425 }, { - "epoch": 0.22, - "learning_rate": 1.967083321974985e-05, - "loss": 0.8047, + "epoch": 0.19, + "learning_rate": 1.9765658319574355e-05, + "loss": 0.8408, "step": 426 }, { - "epoch": 0.22, - "learning_rate": 1.966871110424493e-05, - "loss": 0.8367, + "epoch": 0.19, + "learning_rate": 1.976406775628178e-05, + "loss": 0.8463, "step": 427 }, { - "epoch": 0.22, - "learning_rate": 1.9666582285346823e-05, - "loss": 0.844, + "epoch": 0.19, + "learning_rate": 1.9762471877794277e-05, + "loss": 0.8774, "step": 428 }, { - "epoch": 0.22, - "learning_rate": 1.9664446764531454e-05, - "loss": 0.7917, + "epoch": 0.2, + "learning_rate": 1.9760870684980586e-05, + "loss": 0.8638, "step": 429 }, { - "epoch": 0.22, - "learning_rate": 1.9662304543279395e-05, - "loss": 0.8416, + "epoch": 0.2, + "learning_rate": 1.9759264178712345e-05, + "loss": 0.8716, "step": 430 }, { - "epoch": 0.22, - "learning_rate": 1.966015562307586e-05, - "loss": 0.8291, + "epoch": 0.2, + "learning_rate": 1.9757652359864066e-05, + "loss": 0.8311, "step": 431 }, { - "epoch": 0.22, - "learning_rate": 1.965800000541072e-05, - "loss": 0.8457, + "epoch": 0.2, + "learning_rate": 1.9756035229313165e-05, + "loss": 0.7719, "step": 432 }, { - "epoch": 0.22, - "learning_rate": 1.9655837691778483e-05, - "loss": 0.8469, + "epoch": 0.2, + "learning_rate": 1.9754412787939952e-05, + "loss": 0.8904, "step": 433 }, { - "epoch": 0.22, - "learning_rate": 1.965366868367829e-05, - "loss": 0.835, + "epoch": 0.2, + "learning_rate": 1.9752785036627623e-05, + "loss": 0.8374, "step": 434 }, { - "epoch": 0.22, - "learning_rate": 1.9651492982613935e-05, - "loss": 0.9033, + "epoch": 0.2, + "learning_rate": 1.975115197626226e-05, + "loss": 0.8862, "step": 435 }, { - "epoch": 0.22, - "learning_rate": 1.964931059009385e-05, - "loss": 0.822, + "epoch": 0.2, + "learning_rate": 1.9749513607732845e-05, + "loss": 0.8469, "step": 436 }, { - "epoch": 0.22, - "learning_rate": 1.9647121507631102e-05, - "loss": 0.8853, + "epoch": 0.2, + "learning_rate": 1.9747869931931242e-05, + "loss": 0.8051, "step": 437 }, { - "epoch": 0.23, - "learning_rate": 1.96449257367434e-05, - "loss": 0.8743, + "epoch": 0.2, + "learning_rate": 1.9746220949752208e-05, + "loss": 0.8542, "step": 438 }, { - "epoch": 0.23, - "learning_rate": 1.9642723278953097e-05, - "loss": 0.8652, + "epoch": 0.2, + "learning_rate": 1.974456666209339e-05, + "loss": 0.8276, "step": 439 }, { - "epoch": 0.23, - "learning_rate": 1.9640514135787158e-05, - "loss": 0.8599, + "epoch": 0.2, + "learning_rate": 1.9742907069855315e-05, + "loss": 0.8625, "step": 440 }, { - "epoch": 0.23, - "learning_rate": 1.963829830877721e-05, - "loss": 0.8965, + "epoch": 0.2, + "learning_rate": 1.974124217394141e-05, + "loss": 0.7797, "step": 441 }, { - "epoch": 0.23, - "learning_rate": 1.9636075799459506e-05, - "loss": 0.8733, + "epoch": 0.2, + "learning_rate": 1.9739571975257978e-05, + "loss": 0.8506, "step": 442 }, { - "epoch": 0.23, - "learning_rate": 1.963384660937492e-05, - "loss": 0.8557, + "epoch": 0.2, + "learning_rate": 1.973789647471421e-05, + "loss": 0.8774, "step": 443 }, { - "epoch": 0.23, - "learning_rate": 1.9631610740068974e-05, - "loss": 0.8479, + "epoch": 0.2, + "learning_rate": 1.9736215673222193e-05, + "loss": 0.8232, "step": 444 }, { - "epoch": 0.23, - "learning_rate": 1.962936819309181e-05, - "loss": 0.9038, + "epoch": 0.2, + "learning_rate": 1.973452957169689e-05, + "loss": 0.8102, "step": 445 }, { - "epoch": 0.23, - "learning_rate": 1.9627118969998204e-05, - "loss": 0.8328, + "epoch": 0.2, + "learning_rate": 1.973283817105615e-05, + "loss": 0.8491, "step": 446 }, { - "epoch": 0.23, - "learning_rate": 1.9624863072347565e-05, - "loss": 0.8743, + "epoch": 0.2, + "learning_rate": 1.9731141472220713e-05, + "loss": 0.8555, "step": 447 }, { - "epoch": 0.23, - "learning_rate": 1.9622600501703917e-05, - "loss": 0.8225, + "epoch": 0.2, + "learning_rate": 1.9729439476114195e-05, + "loss": 0.8848, "step": 448 }, { - "epoch": 0.23, - "learning_rate": 1.962033125963592e-05, - "loss": 0.9006, + "epoch": 0.2, + "learning_rate": 1.97277321836631e-05, + "loss": 0.8882, "step": 449 }, { - "epoch": 0.23, - "learning_rate": 1.9618055347716862e-05, - "loss": 0.8804, + "epoch": 0.21, + "learning_rate": 1.972601959579681e-05, + "loss": 0.8108, "step": 450 }, { - "epoch": 0.23, - "learning_rate": 1.9615772767524644e-05, - "loss": 0.8833, + "epoch": 0.21, + "learning_rate": 1.9724301713447604e-05, + "loss": 0.8191, "step": 451 }, { - "epoch": 0.23, - "learning_rate": 1.9613483520641803e-05, - "loss": 0.8813, + "epoch": 0.21, + "learning_rate": 1.972257853755063e-05, + "loss": 0.8376, "step": 452 }, { - "epoch": 0.23, - "learning_rate": 1.9611187608655484e-05, - "loss": 0.8994, + "epoch": 0.21, + "learning_rate": 1.972085006904391e-05, + "loss": 0.8547, "step": 453 }, { - "epoch": 0.23, - "learning_rate": 1.9608885033157467e-05, - "loss": 0.8689, + "epoch": 0.21, + "learning_rate": 1.9719116308868375e-05, + "loss": 0.8691, "step": 454 }, { - "epoch": 0.23, - "learning_rate": 1.9606575795744148e-05, - "loss": 0.8418, + "epoch": 0.21, + "learning_rate": 1.9717377257967807e-05, + "loss": 0.7996, "step": 455 }, { - "epoch": 0.23, - "learning_rate": 1.960425989801653e-05, - "loss": 0.8171, + "epoch": 0.21, + "learning_rate": 1.9715632917288884e-05, + "loss": 0.8115, "step": 456 }, { - "epoch": 0.23, - "learning_rate": 1.960193734158025e-05, - "loss": 0.8186, + "epoch": 0.21, + "learning_rate": 1.9713883287781163e-05, + "loss": 0.8367, "step": 457 }, { - "epoch": 0.24, - "learning_rate": 1.9599608128045554e-05, - "loss": 0.8237, + "epoch": 0.21, + "learning_rate": 1.9712128370397073e-05, + "loss": 0.8073, "step": 458 }, { - "epoch": 0.24, - "learning_rate": 1.9597272259027303e-05, - "loss": 0.8606, + "epoch": 0.21, + "learning_rate": 1.9710368166091925e-05, + "loss": 0.8833, "step": 459 }, { - "epoch": 0.24, - "learning_rate": 1.9594929736144978e-05, - "loss": 0.8618, + "epoch": 0.21, + "learning_rate": 1.9708602675823914e-05, + "loss": 0.843, "step": 460 }, { - "epoch": 0.24, - "learning_rate": 1.959258056102266e-05, - "loss": 0.8276, + "epoch": 0.21, + "learning_rate": 1.9706831900554107e-05, + "loss": 0.8176, "step": 461 }, { - "epoch": 0.24, - "learning_rate": 1.959022473528905e-05, - "loss": 0.7939, + "epoch": 0.21, + "learning_rate": 1.970505584124644e-05, + "loss": 0.8168, "step": 462 }, { - "epoch": 0.24, - "learning_rate": 1.9587862260577467e-05, - "loss": 0.9453, + "epoch": 0.21, + "learning_rate": 1.9703274498867742e-05, + "loss": 0.8076, "step": 463 }, { - "epoch": 0.24, - "learning_rate": 1.9585493138525833e-05, - "loss": 0.8621, + "epoch": 0.21, + "learning_rate": 1.970148787438771e-05, + "loss": 0.8702, "step": 464 }, { - "epoch": 0.24, - "learning_rate": 1.9583117370776677e-05, - "loss": 0.8457, + "epoch": 0.21, + "learning_rate": 1.9699695968778907e-05, + "loss": 0.7826, "step": 465 }, { - "epoch": 0.24, - "learning_rate": 1.9580734958977137e-05, - "loss": 0.7991, + "epoch": 0.21, + "learning_rate": 1.9697898783016787e-05, + "loss": 0.8372, "step": 466 }, { - "epoch": 0.24, - "learning_rate": 1.9578345904778956e-05, - "loss": 0.8176, + "epoch": 0.21, + "learning_rate": 1.9696096318079667e-05, + "loss": 0.8813, "step": 467 }, { - "epoch": 0.24, - "learning_rate": 1.957595020983849e-05, - "loss": 0.8618, + "epoch": 0.21, + "learning_rate": 1.9694288574948745e-05, + "loss": 0.8774, "step": 468 }, { - "epoch": 0.24, - "learning_rate": 1.9573547875816685e-05, - "loss": 0.8259, + "epoch": 0.21, + "learning_rate": 1.9692475554608087e-05, + "loss": 0.8188, "step": 469 }, { - "epoch": 0.24, - "learning_rate": 1.9571138904379104e-05, - "loss": 0.7869, + "epoch": 0.21, + "learning_rate": 1.969065725804464e-05, + "loss": 0.8899, "step": 470 }, { - "epoch": 0.24, - "learning_rate": 1.9568723297195907e-05, - "loss": 0.8318, + "epoch": 0.21, + "learning_rate": 1.9688833686248205e-05, + "loss": 0.8381, "step": 471 }, { - "epoch": 0.24, - "learning_rate": 1.956630105594185e-05, - "loss": 0.7783, + "epoch": 0.22, + "learning_rate": 1.9687004840211473e-05, + "loss": 0.8445, "step": 472 }, { - "epoch": 0.24, - "learning_rate": 1.9563872182296287e-05, - "loss": 0.8074, + "epoch": 0.22, + "learning_rate": 1.9685170720930006e-05, + "loss": 0.8311, "step": 473 }, { - "epoch": 0.24, - "learning_rate": 1.9561436677943183e-05, - "loss": 0.8433, + "epoch": 0.22, + "learning_rate": 1.968333132940222e-05, + "loss": 0.8248, "step": 474 }, { - "epoch": 0.24, - "learning_rate": 1.955899454457109e-05, - "loss": 0.8206, + "epoch": 0.22, + "learning_rate": 1.9681486666629413e-05, + "loss": 0.9266, "step": 475 }, { - "epoch": 0.24, - "learning_rate": 1.9556545783873154e-05, - "loss": 0.8853, + "epoch": 0.22, + "learning_rate": 1.9679636733615756e-05, + "loss": 0.8442, "step": 476 }, { - "epoch": 0.25, - "learning_rate": 1.955409039754713e-05, - "loss": 0.9084, + "epoch": 0.22, + "learning_rate": 1.9677781531368282e-05, + "loss": 0.8303, "step": 477 }, { - "epoch": 0.25, - "learning_rate": 1.9551628387295347e-05, - "loss": 0.8574, + "epoch": 0.22, + "learning_rate": 1.967592106089689e-05, + "loss": 0.8779, "step": 478 }, { - "epoch": 0.25, - "learning_rate": 1.954915975482474e-05, - "loss": 0.877, + "epoch": 0.22, + "learning_rate": 1.9674055323214354e-05, + "loss": 0.8542, "step": 479 }, { - "epoch": 0.25, - "learning_rate": 1.954668450184683e-05, - "loss": 0.8191, + "epoch": 0.22, + "learning_rate": 1.9672184319336318e-05, + "loss": 0.8433, "step": 480 }, { - "epoch": 0.25, - "learning_rate": 1.9544202630077733e-05, - "loss": 0.8423, + "epoch": 0.22, + "learning_rate": 1.9670308050281274e-05, + "loss": 0.8511, "step": 481 }, { - "epoch": 0.25, - "learning_rate": 1.9541714141238144e-05, - "loss": 0.8677, + "epoch": 0.22, + "learning_rate": 1.96684265170706e-05, + "loss": 0.8169, "step": 482 }, { - "epoch": 0.25, - "learning_rate": 1.9539219037053354e-05, - "loss": 0.8577, + "epoch": 0.22, + "learning_rate": 1.9666539720728533e-05, + "loss": 0.853, "step": 483 }, { - "epoch": 0.25, - "learning_rate": 1.953671731925324e-05, - "loss": 0.7942, + "epoch": 0.22, + "learning_rate": 1.9664647662282173e-05, + "loss": 0.8253, "step": 484 }, { - "epoch": 0.25, - "learning_rate": 1.9534208989572267e-05, - "loss": 0.866, + "epoch": 0.22, + "learning_rate": 1.9662750342761488e-05, + "loss": 0.8984, "step": 485 }, { - "epoch": 0.25, - "learning_rate": 1.9531694049749465e-05, - "loss": 0.8076, + "epoch": 0.22, + "learning_rate": 1.9660847763199306e-05, + "loss": 0.814, "step": 486 }, { - "epoch": 0.25, - "learning_rate": 1.952917250152848e-05, - "loss": 0.8142, + "epoch": 0.22, + "learning_rate": 1.9658939924631325e-05, + "loss": 0.9099, "step": 487 }, { - "epoch": 0.25, - "learning_rate": 1.9526644346657508e-05, - "loss": 0.8149, + "epoch": 0.22, + "learning_rate": 1.9657026828096092e-05, + "loss": 0.7628, "step": 488 }, { - "epoch": 0.25, - "learning_rate": 1.952410958688934e-05, - "loss": 0.8159, + "epoch": 0.22, + "learning_rate": 1.9655108474635037e-05, + "loss": 0.8564, "step": 489 }, { - "epoch": 0.25, - "learning_rate": 1.9521568223981348e-05, - "loss": 0.7778, + "epoch": 0.22, + "learning_rate": 1.9653184865292433e-05, + "loss": 0.8279, "step": 490 }, { - "epoch": 0.25, - "learning_rate": 1.951902025969548e-05, - "loss": 0.8894, + "epoch": 0.22, + "learning_rate": 1.9651256001115423e-05, + "loss": 0.8818, "step": 491 }, { - "epoch": 0.25, - "learning_rate": 1.951646569579826e-05, - "loss": 0.8094, + "epoch": 0.22, + "learning_rate": 1.9649321883154006e-05, + "loss": 0.8555, "step": 492 }, { - "epoch": 0.25, - "learning_rate": 1.9513904534060782e-05, - "loss": 0.7874, + "epoch": 0.22, + "learning_rate": 1.964738251246105e-05, + "loss": 0.8638, "step": 493 }, { - "epoch": 0.25, - "learning_rate": 1.951133677625872e-05, - "loss": 0.8213, + "epoch": 0.23, + "learning_rate": 1.964543789009227e-05, + "loss": 0.8158, "step": 494 }, { - "epoch": 0.25, - "learning_rate": 1.9508762424172326e-05, - "loss": 0.8376, + "epoch": 0.23, + "learning_rate": 1.964348801710625e-05, + "loss": 0.8135, "step": 495 }, { - "epoch": 0.25, - "learning_rate": 1.9506181479586417e-05, - "loss": 0.8701, + "epoch": 0.23, + "learning_rate": 1.964153289456443e-05, + "loss": 0.7817, "step": 496 }, { - "epoch": 0.26, - "learning_rate": 1.950359394429038e-05, - "loss": 0.8445, + "epoch": 0.23, + "learning_rate": 1.96395725235311e-05, + "loss": 0.8296, "step": 497 }, { - "epoch": 0.26, - "learning_rate": 1.9500999820078173e-05, - "loss": 0.8513, + "epoch": 0.23, + "learning_rate": 1.9637606905073413e-05, + "loss": 0.7765, "step": 498 }, { - "epoch": 0.26, - "learning_rate": 1.9498399108748324e-05, - "loss": 0.8379, + "epoch": 0.23, + "learning_rate": 1.9635636040261388e-05, + "loss": 0.8491, "step": 499 }, { - "epoch": 0.26, - "learning_rate": 1.9495791812103927e-05, - "loss": 0.8584, + "epoch": 0.23, + "learning_rate": 1.963365993016788e-05, + "loss": 0.8809, "step": 500 }, { - "epoch": 0.26, - "learning_rate": 1.949317793195264e-05, - "loss": 0.8721, + "epoch": 0.23, + "learning_rate": 1.963167857586861e-05, + "loss": 0.7588, "step": 501 }, { - "epoch": 0.26, - "learning_rate": 1.949055747010669e-05, - "loss": 0.8406, + "epoch": 0.23, + "learning_rate": 1.9629691978442165e-05, + "loss": 0.8533, "step": 502 }, { - "epoch": 0.26, - "learning_rate": 1.9487930428382856e-05, - "loss": 0.8535, + "epoch": 0.23, + "learning_rate": 1.962770013896996e-05, + "loss": 0.8948, "step": 503 }, { - "epoch": 0.26, - "learning_rate": 1.9485296808602494e-05, - "loss": 0.8303, + "epoch": 0.23, + "learning_rate": 1.9625703058536288e-05, + "loss": 0.8616, "step": 504 }, { - "epoch": 0.26, - "learning_rate": 1.9482656612591512e-05, - "loss": 0.8757, + "epoch": 0.23, + "learning_rate": 1.9623700738228285e-05, + "loss": 0.8987, "step": 505 }, { - "epoch": 0.26, - "learning_rate": 1.9480009842180378e-05, - "loss": 0.8298, + "epoch": 0.23, + "learning_rate": 1.962169317913593e-05, + "loss": 0.8271, "step": 506 }, { - "epoch": 0.26, - "learning_rate": 1.9477356499204113e-05, - "loss": 0.8093, + "epoch": 0.23, + "learning_rate": 1.9619680382352075e-05, + "loss": 0.8121, "step": 507 }, { - "epoch": 0.26, - "learning_rate": 1.947469658550231e-05, - "loss": 0.8652, + "epoch": 0.23, + "learning_rate": 1.9617662348972407e-05, + "loss": 0.8599, "step": 508 }, { - "epoch": 0.26, - "learning_rate": 1.9472030102919102e-05, - "loss": 0.8262, + "epoch": 0.23, + "learning_rate": 1.961563908009547e-05, + "loss": 0.8499, "step": 509 }, { - "epoch": 0.26, - "learning_rate": 1.9469357053303183e-05, - "loss": 0.8262, + "epoch": 0.23, + "learning_rate": 1.961361057682265e-05, + "loss": 0.8682, "step": 510 }, { - "epoch": 0.26, - "learning_rate": 1.9466677438507803e-05, - "loss": 0.8232, + "epoch": 0.23, + "learning_rate": 1.9611576840258193e-05, + "loss": 0.7726, "step": 511 }, { - "epoch": 0.26, - "learning_rate": 1.9463991260390753e-05, - "loss": 0.8435, + "epoch": 0.23, + "learning_rate": 1.960953787150919e-05, + "loss": 0.8638, "step": 512 }, { - "epoch": 0.26, - "learning_rate": 1.946129852081439e-05, - "loss": 0.8865, + "epoch": 0.23, + "learning_rate": 1.960749367168558e-05, + "loss": 0.936, "step": 513 }, { - "epoch": 0.26, - "learning_rate": 1.9458599221645606e-05, - "loss": 0.7957, + "epoch": 0.23, + "learning_rate": 1.960544424190015e-05, + "loss": 0.8302, "step": 514 }, { - "epoch": 0.26, - "learning_rate": 1.9455893364755845e-05, - "loss": 0.8362, + "epoch": 0.23, + "learning_rate": 1.960338958326853e-05, + "loss": 0.856, "step": 515 }, { - "epoch": 0.27, - "learning_rate": 1.94531809520211e-05, - "loss": 0.856, + "epoch": 0.24, + "learning_rate": 1.96013296969092e-05, + "loss": 0.8406, "step": 516 }, { - "epoch": 0.27, - "learning_rate": 1.945046198532191e-05, - "loss": 0.8354, + "epoch": 0.24, + "learning_rate": 1.9599264583943486e-05, + "loss": 0.8262, "step": 517 }, { - "epoch": 0.27, - "learning_rate": 1.9447736466543354e-05, - "loss": 0.8613, + "epoch": 0.24, + "learning_rate": 1.9597194245495562e-05, + "loss": 0.8137, "step": 518 }, { - "epoch": 0.27, - "learning_rate": 1.9445004397575058e-05, - "loss": 0.8577, + "epoch": 0.24, + "learning_rate": 1.9595118682692442e-05, + "loss": 0.8213, "step": 519 }, { - "epoch": 0.27, - "learning_rate": 1.9442265780311182e-05, - "loss": 0.8154, + "epoch": 0.24, + "learning_rate": 1.959303789666398e-05, + "loss": 0.822, "step": 520 }, { - "epoch": 0.27, - "learning_rate": 1.943952061665044e-05, - "loss": 0.8406, + "epoch": 0.24, + "learning_rate": 1.9590951888542883e-05, + "loss": 0.8889, "step": 521 }, { - "epoch": 0.27, - "learning_rate": 1.9436768908496063e-05, - "loss": 0.8523, + "epoch": 0.24, + "learning_rate": 1.95888606594647e-05, + "loss": 0.8799, "step": 522 }, { - "epoch": 0.27, - "learning_rate": 1.943401065775584e-05, - "loss": 0.863, + "epoch": 0.24, + "learning_rate": 1.958676421056781e-05, + "loss": 0.8481, "step": 523 }, { - "epoch": 0.27, - "learning_rate": 1.943124586634209e-05, - "loss": 0.8232, + "epoch": 0.24, + "learning_rate": 1.958466254299344e-05, + "loss": 0.8459, "step": 524 }, { - "epoch": 0.27, - "learning_rate": 1.9428474536171657e-05, - "loss": 0.7961, + "epoch": 0.24, + "learning_rate": 1.958255565788567e-05, + "loss": 0.799, "step": 525 }, { - "epoch": 0.27, - "learning_rate": 1.942569666916593e-05, - "loss": 0.9177, + "epoch": 0.24, + "learning_rate": 1.9580443556391404e-05, + "loss": 0.843, "step": 526 }, { - "epoch": 0.27, - "learning_rate": 1.9422912267250827e-05, - "loss": 0.7778, + "epoch": 0.24, + "learning_rate": 1.9578326239660393e-05, + "loss": 0.8606, "step": 527 }, { - "epoch": 0.27, - "learning_rate": 1.942012133235679e-05, - "loss": 0.8882, + "epoch": 0.24, + "learning_rate": 1.9576203708845223e-05, + "loss": 0.8391, "step": 528 }, { - "epoch": 0.27, - "learning_rate": 1.9417323866418808e-05, - "loss": 0.8162, + "epoch": 0.24, + "learning_rate": 1.957407596510132e-05, + "loss": 0.8271, "step": 529 }, { - "epoch": 0.27, - "learning_rate": 1.9414519871376373e-05, - "loss": 0.8462, + "epoch": 0.24, + "learning_rate": 1.9571943009586952e-05, + "loss": 0.8472, "step": 530 }, { - "epoch": 0.27, - "learning_rate": 1.941170934917352e-05, - "loss": 0.8472, + "epoch": 0.24, + "learning_rate": 1.9569804843463223e-05, + "loss": 0.824, "step": 531 }, { - "epoch": 0.27, - "learning_rate": 1.9408892301758816e-05, - "loss": 0.8892, + "epoch": 0.24, + "learning_rate": 1.9567661467894064e-05, + "loss": 0.8435, "step": 532 }, { - "epoch": 0.27, - "learning_rate": 1.9406068731085327e-05, - "loss": 0.7551, + "epoch": 0.24, + "learning_rate": 1.956551288404625e-05, + "loss": 0.7777, "step": 533 }, { - "epoch": 0.27, - "learning_rate": 1.9403238639110667e-05, - "loss": 0.8003, + "epoch": 0.24, + "learning_rate": 1.9563359093089396e-05, + "loss": 0.8722, "step": 534 }, { - "epoch": 0.27, - "learning_rate": 1.9400402027796955e-05, - "loss": 0.8687, + "epoch": 0.24, + "learning_rate": 1.956120009619594e-05, + "loss": 0.8508, "step": 535 }, { - "epoch": 0.28, - "learning_rate": 1.939755889911084e-05, - "loss": 0.7749, + "epoch": 0.24, + "learning_rate": 1.955903589454116e-05, + "loss": 0.8008, "step": 536 }, { - "epoch": 0.28, - "learning_rate": 1.9394709255023488e-05, - "loss": 0.8484, + "epoch": 0.24, + "learning_rate": 1.955686648930317e-05, + "loss": 0.843, "step": 537 }, { - "epoch": 0.28, - "learning_rate": 1.939185309751057e-05, - "loss": 0.8579, + "epoch": 0.25, + "learning_rate": 1.955469188166291e-05, + "loss": 0.8386, "step": 538 }, { - "epoch": 0.28, - "learning_rate": 1.9388990428552294e-05, - "loss": 0.856, + "epoch": 0.25, + "learning_rate": 1.9552512072804158e-05, + "loss": 0.8296, "step": 539 }, { - "epoch": 0.28, - "learning_rate": 1.938612125013336e-05, - "loss": 0.8306, + "epoch": 0.25, + "learning_rate": 1.955032706391352e-05, + "loss": 0.8269, "step": 540 }, { - "epoch": 0.28, - "learning_rate": 1.9383245564243e-05, - "loss": 0.8823, + "epoch": 0.25, + "learning_rate": 1.954813685618043e-05, + "loss": 0.8596, "step": 541 }, { - "epoch": 0.28, - "learning_rate": 1.9380363372874946e-05, - "loss": 0.7778, + "epoch": 0.25, + "learning_rate": 1.9545941450797163e-05, + "loss": 0.8135, "step": 542 }, { - "epoch": 0.28, - "learning_rate": 1.9377474678027442e-05, - "loss": 0.8215, + "epoch": 0.25, + "learning_rate": 1.954374084895881e-05, + "loss": 0.8511, "step": 543 }, { - "epoch": 0.28, - "learning_rate": 1.9374579481703244e-05, - "loss": 0.8159, + "epoch": 0.25, + "learning_rate": 1.9541535051863294e-05, + "loss": 0.8772, "step": 544 }, { - "epoch": 0.28, - "learning_rate": 1.9371677785909617e-05, - "loss": 0.8447, + "epoch": 0.25, + "learning_rate": 1.9539324060711378e-05, + "loss": 0.8669, "step": 545 }, { - "epoch": 0.28, - "learning_rate": 1.936876959265833e-05, - "loss": 0.7952, + "epoch": 0.25, + "learning_rate": 1.9537107876706635e-05, + "loss": 0.8171, "step": 546 }, { - "epoch": 0.28, - "learning_rate": 1.936585490396565e-05, - "loss": 0.7905, + "epoch": 0.25, + "learning_rate": 1.953488650105548e-05, + "loss": 0.8699, "step": 547 }, { - "epoch": 0.28, - "learning_rate": 1.936293372185236e-05, - "loss": 0.8638, + "epoch": 0.25, + "learning_rate": 1.953265993496714e-05, + "loss": 0.7878, "step": 548 }, { - "epoch": 0.28, - "learning_rate": 1.9360006048343735e-05, - "loss": 0.8298, + "epoch": 0.25, + "learning_rate": 1.953042817965368e-05, + "loss": 0.7866, "step": 549 }, { - "epoch": 0.28, - "learning_rate": 1.9357071885469553e-05, - "loss": 0.8162, + "epoch": 0.25, + "learning_rate": 1.952819123632998e-05, + "loss": 0.825, "step": 550 }, { - "epoch": 0.28, - "learning_rate": 1.93541312352641e-05, - "loss": 0.7925, + "epoch": 0.25, + "learning_rate": 1.9525949106213757e-05, + "loss": 0.8987, "step": 551 }, { - "epoch": 0.28, - "learning_rate": 1.935118409976614e-05, - "loss": 0.7905, + "epoch": 0.25, + "learning_rate": 1.9523701790525536e-05, + "loss": 0.8538, "step": 552 }, { - "epoch": 0.28, - "learning_rate": 1.9348230481018953e-05, - "loss": 0.8857, + "epoch": 0.25, + "learning_rate": 1.952144929048867e-05, + "loss": 0.7917, "step": 553 }, { - "epoch": 0.28, - "learning_rate": 1.93452703810703e-05, - "loss": 0.8467, + "epoch": 0.25, + "learning_rate": 1.951919160732934e-05, + "loss": 0.8555, "step": 554 }, { - "epoch": 0.29, - "learning_rate": 1.9342303801972452e-05, - "loss": 0.7969, + "epoch": 0.25, + "learning_rate": 1.951692874227655e-05, + "loss": 0.8657, "step": 555 }, { - "epoch": 0.29, - "learning_rate": 1.9339330745782154e-05, - "loss": 0.8152, + "epoch": 0.25, + "learning_rate": 1.9514660696562107e-05, + "loss": 0.8352, "step": 556 }, { - "epoch": 0.29, - "learning_rate": 1.9336351214560648e-05, - "loss": 0.8589, + "epoch": 0.25, + "learning_rate": 1.9512387471420663e-05, + "loss": 0.8608, "step": 557 }, { - "epoch": 0.29, - "learning_rate": 1.9333365210373668e-05, - "loss": 0.8232, + "epoch": 0.25, + "learning_rate": 1.9510109068089668e-05, + "loss": 0.8247, "step": 558 }, { - "epoch": 0.29, - "learning_rate": 1.9330372735291436e-05, - "loss": 0.8523, + "epoch": 0.25, + "learning_rate": 1.9507825487809403e-05, + "loss": 0.8323, "step": 559 }, { - "epoch": 0.29, - "learning_rate": 1.9327373791388656e-05, - "loss": 0.7891, + "epoch": 0.26, + "learning_rate": 1.9505536731822968e-05, + "loss": 0.8804, "step": 560 }, { - "epoch": 0.29, - "learning_rate": 1.9324368380744522e-05, - "loss": 0.8445, + "epoch": 0.26, + "learning_rate": 1.950324280137627e-05, + "loss": 0.8704, "step": 561 }, { - "epoch": 0.29, - "learning_rate": 1.9321356505442707e-05, - "loss": 0.8225, + "epoch": 0.26, + "learning_rate": 1.9500943697718043e-05, + "loss": 0.8176, "step": 562 }, { - "epoch": 0.29, - "learning_rate": 1.931833816757137e-05, - "loss": 0.8667, + "epoch": 0.26, + "learning_rate": 1.9498639422099835e-05, + "loss": 0.7637, "step": 563 }, { - "epoch": 0.29, - "learning_rate": 1.9315313369223142e-05, - "loss": 0.8472, + "epoch": 0.26, + "learning_rate": 1.9496329975776003e-05, + "loss": 0.7556, "step": 564 }, { - "epoch": 0.29, - "learning_rate": 1.9312282112495146e-05, - "loss": 0.7744, + "epoch": 0.26, + "learning_rate": 1.949401536000373e-05, + "loss": 0.8134, "step": 565 }, { - "epoch": 0.29, - "learning_rate": 1.930924439948897e-05, - "loss": 0.8435, + "epoch": 0.26, + "learning_rate": 1.9491695576042996e-05, + "loss": 0.876, "step": 566 }, { - "epoch": 0.29, - "learning_rate": 1.930620023231069e-05, - "loss": 0.7998, + "epoch": 0.26, + "learning_rate": 1.948937062515662e-05, + "loss": 0.8138, "step": 567 }, { - "epoch": 0.29, - "learning_rate": 1.9303149613070852e-05, - "loss": 0.7932, + "epoch": 0.26, + "learning_rate": 1.9487040508610208e-05, + "loss": 0.823, "step": 568 }, { - "epoch": 0.29, - "learning_rate": 1.9300092543884467e-05, - "loss": 0.8091, + "epoch": 0.26, + "learning_rate": 1.948470522767219e-05, + "loss": 0.8206, "step": 569 }, { - "epoch": 0.29, - "learning_rate": 1.929702902687103e-05, - "loss": 0.8213, + "epoch": 0.26, + "learning_rate": 1.9482364783613805e-05, + "loss": 0.7487, "step": 570 }, { - "epoch": 0.29, - "learning_rate": 1.92939590641545e-05, - "loss": 0.7808, + "epoch": 0.26, + "learning_rate": 1.948001917770911e-05, + "loss": 0.7452, "step": 571 }, { - "epoch": 0.29, - "learning_rate": 1.929088265786331e-05, - "loss": 0.8171, + "epoch": 0.26, + "learning_rate": 1.947766841123496e-05, + "loss": 0.8503, "step": 572 }, { - "epoch": 0.29, - "learning_rate": 1.928779981013035e-05, - "loss": 0.8513, + "epoch": 0.26, + "learning_rate": 1.9475312485471024e-05, + "loss": 0.8472, "step": 573 }, { - "epoch": 0.3, - "learning_rate": 1.9284710523092985e-05, - "loss": 0.7979, + "epoch": 0.26, + "learning_rate": 1.9472951401699786e-05, + "loss": 0.8132, "step": 574 }, { - "epoch": 0.3, - "learning_rate": 1.9281614798893046e-05, - "loss": 0.8726, + "epoch": 0.26, + "learning_rate": 1.9470585161206526e-05, + "loss": 0.9075, "step": 575 }, { - "epoch": 0.3, - "learning_rate": 1.9278512639676817e-05, - "loss": 0.8191, + "epoch": 0.26, + "learning_rate": 1.9468213765279343e-05, + "loss": 0.8363, "step": 576 }, { - "epoch": 0.3, - "learning_rate": 1.9275404047595052e-05, - "loss": 0.8384, + "epoch": 0.26, + "learning_rate": 1.9465837215209127e-05, + "loss": 0.7649, "step": 577 }, { - "epoch": 0.3, - "learning_rate": 1.9272289024802963e-05, - "loss": 0.7886, + "epoch": 0.26, + "learning_rate": 1.9463455512289597e-05, + "loss": 0.8325, "step": 578 }, { - "epoch": 0.3, - "learning_rate": 1.926916757346022e-05, - "loss": 0.8413, + "epoch": 0.26, + "learning_rate": 1.9461068657817254e-05, + "loss": 0.8109, "step": 579 }, { - "epoch": 0.3, - "learning_rate": 1.9266039695730943e-05, - "loss": 0.7954, + "epoch": 0.26, + "learning_rate": 1.9458676653091413e-05, + "loss": 0.8302, "step": 580 }, { - "epoch": 0.3, - "learning_rate": 1.9262905393783725e-05, - "loss": 0.8064, + "epoch": 0.26, + "learning_rate": 1.9456279499414195e-05, + "loss": 0.8496, "step": 581 }, { - "epoch": 0.3, - "learning_rate": 1.9259764669791597e-05, - "loss": 0.8726, + "epoch": 0.27, + "learning_rate": 1.945387719809052e-05, + "loss": 0.8877, "step": 582 }, { - "epoch": 0.3, - "learning_rate": 1.9256617525932045e-05, - "loss": 0.8494, + "epoch": 0.27, + "learning_rate": 1.9451469750428115e-05, + "loss": 0.7408, "step": 583 }, { - "epoch": 0.3, - "learning_rate": 1.9253463964387014e-05, - "loss": 0.802, + "epoch": 0.27, + "learning_rate": 1.9449057157737497e-05, + "loss": 0.8059, "step": 584 }, { - "epoch": 0.3, - "learning_rate": 1.9250303987342883e-05, - "loss": 0.854, + "epoch": 0.27, + "learning_rate": 1.9446639421331997e-05, + "loss": 0.8611, "step": 585 }, { - "epoch": 0.3, - "learning_rate": 1.92471375969905e-05, - "loss": 0.7493, + "epoch": 0.27, + "learning_rate": 1.944421654252774e-05, + "loss": 0.7341, "step": 586 }, { - "epoch": 0.3, - "learning_rate": 1.9243964795525144e-05, - "loss": 0.8269, + "epoch": 0.27, + "learning_rate": 1.9441788522643653e-05, + "loss": 0.8738, "step": 587 }, { - "epoch": 0.3, - "learning_rate": 1.9240785585146545e-05, - "loss": 0.8093, + "epoch": 0.27, + "learning_rate": 1.9439355363001457e-05, + "loss": 0.8767, "step": 588 }, { - "epoch": 0.3, - "learning_rate": 1.923759996805887e-05, - "loss": 0.8931, + "epoch": 0.27, + "learning_rate": 1.9436917064925675e-05, + "loss": 0.813, "step": 589 }, { - "epoch": 0.3, - "learning_rate": 1.9234407946470735e-05, - "loss": 0.8274, + "epoch": 0.27, + "learning_rate": 1.9434473629743624e-05, + "loss": 0.8198, "step": 590 }, { - "epoch": 0.3, - "learning_rate": 1.9231209522595192e-05, - "loss": 0.8152, + "epoch": 0.27, + "learning_rate": 1.9432025058785416e-05, + "loss": 0.801, "step": 591 }, { - "epoch": 0.3, - "learning_rate": 1.9228004698649736e-05, - "loss": 0.8716, + "epoch": 0.27, + "learning_rate": 1.942957135338397e-05, + "loss": 0.7968, "step": 592 }, { - "epoch": 0.3, - "learning_rate": 1.9224793476856293e-05, - "loss": 0.8162, + "epoch": 0.27, + "learning_rate": 1.9427112514874986e-05, + "loss": 0.8379, "step": 593 }, { - "epoch": 0.31, - "learning_rate": 1.9221575859441235e-05, - "loss": 0.7874, + "epoch": 0.27, + "learning_rate": 1.9424648544596965e-05, + "loss": 0.8174, "step": 594 }, { - "epoch": 0.31, - "learning_rate": 1.9218351848635356e-05, - "loss": 0.8835, + "epoch": 0.27, + "learning_rate": 1.9422179443891205e-05, + "loss": 0.842, "step": 595 }, { - "epoch": 0.31, - "learning_rate": 1.9215121446673883e-05, - "loss": 0.8374, + "epoch": 0.27, + "learning_rate": 1.9419705214101787e-05, + "loss": 0.8794, "step": 596 }, { - "epoch": 0.31, - "learning_rate": 1.921188465579649e-05, - "loss": 0.7886, + "epoch": 0.27, + "learning_rate": 1.941722585657559e-05, + "loss": 0.8505, "step": 597 }, { - "epoch": 0.31, - "learning_rate": 1.9208641478247263e-05, - "loss": 0.8191, + "epoch": 0.27, + "learning_rate": 1.9414741372662287e-05, + "loss": 0.886, "step": 598 }, { - "epoch": 0.31, - "learning_rate": 1.9205391916274726e-05, - "loss": 0.844, + "epoch": 0.27, + "learning_rate": 1.9412251763714334e-05, + "loss": 0.8076, "step": 599 }, { - "epoch": 0.31, - "learning_rate": 1.920213597213182e-05, - "loss": 0.7695, + "epoch": 0.27, + "learning_rate": 1.9409757031086987e-05, + "loss": 0.8219, "step": 600 }, { - "epoch": 0.31, - "learning_rate": 1.919887364807592e-05, - "loss": 0.7969, + "epoch": 0.27, + "learning_rate": 1.9407257176138284e-05, + "loss": 0.8369, "step": 601 }, { - "epoch": 0.31, - "learning_rate": 1.9195604946368825e-05, - "loss": 0.8069, + "epoch": 0.27, + "learning_rate": 1.9404752200229047e-05, + "loss": 0.8447, "step": 602 }, { - "epoch": 0.31, - "learning_rate": 1.9192329869276742e-05, - "loss": 0.8345, + "epoch": 0.27, + "learning_rate": 1.9402242104722902e-05, + "loss": 0.7809, "step": 603 }, { - "epoch": 0.31, - "learning_rate": 1.9189048419070316e-05, - "loss": 0.8125, + "epoch": 0.28, + "learning_rate": 1.939972689098624e-05, + "loss": 0.8447, "step": 604 }, { - "epoch": 0.31, - "learning_rate": 1.91857605980246e-05, - "loss": 0.7788, + "epoch": 0.28, + "learning_rate": 1.939720656038826e-05, + "loss": 0.8657, "step": 605 }, { - "epoch": 0.31, - "learning_rate": 1.9182466408419062e-05, - "loss": 0.8169, + "epoch": 0.28, + "learning_rate": 1.9394681114300934e-05, + "loss": 0.8218, "step": 606 }, { - "epoch": 0.31, - "learning_rate": 1.9179165852537596e-05, - "loss": 0.7815, + "epoch": 0.28, + "learning_rate": 1.9392150554099014e-05, + "loss": 0.8401, "step": 607 }, { - "epoch": 0.31, - "learning_rate": 1.91758589326685e-05, - "loss": 0.8152, + "epoch": 0.28, + "learning_rate": 1.938961488116005e-05, + "loss": 0.8521, "step": 608 }, { - "epoch": 0.31, - "learning_rate": 1.9172545651104485e-05, - "loss": 0.8545, + "epoch": 0.28, + "learning_rate": 1.9387074096864365e-05, + "loss": 0.8687, "step": 609 }, { - "epoch": 0.31, - "learning_rate": 1.9169226010142678e-05, - "loss": 0.8645, + "epoch": 0.28, + "learning_rate": 1.9384528202595065e-05, + "loss": 0.8567, "step": 610 }, { - "epoch": 0.31, - "learning_rate": 1.916590001208461e-05, - "loss": 0.7932, + "epoch": 0.28, + "learning_rate": 1.9381977199738045e-05, + "loss": 0.8083, "step": 611 }, { - "epoch": 0.31, - "learning_rate": 1.9162567659236227e-05, - "loss": 0.8901, + "epoch": 0.28, + "learning_rate": 1.9379421089681975e-05, + "loss": 0.8207, "step": 612 }, { - "epoch": 0.32, - "learning_rate": 1.9159228953907873e-05, - "loss": 0.7883, + "epoch": 0.28, + "learning_rate": 1.9376859873818303e-05, + "loss": 0.8345, "step": 613 }, { - "epoch": 0.32, - "learning_rate": 1.9155883898414292e-05, - "loss": 0.8315, + "epoch": 0.28, + "learning_rate": 1.9374293553541258e-05, + "loss": 0.7959, "step": 614 }, { - "epoch": 0.32, - "learning_rate": 1.9152532495074645e-05, - "loss": 0.7925, + "epoch": 0.28, + "learning_rate": 1.937172213024786e-05, + "loss": 0.8546, "step": 615 }, { - "epoch": 0.32, - "learning_rate": 1.914917474621248e-05, - "loss": 0.8301, + "epoch": 0.28, + "learning_rate": 1.9369145605337883e-05, + "loss": 0.8391, "step": 616 }, { - "epoch": 0.32, - "learning_rate": 1.9145810654155762e-05, - "loss": 0.8352, + "epoch": 0.28, + "learning_rate": 1.9366563980213897e-05, + "loss": 0.8994, "step": 617 }, { - "epoch": 0.32, - "learning_rate": 1.9142440221236828e-05, - "loss": 0.8237, + "epoch": 0.28, + "learning_rate": 1.9363977256281243e-05, + "loss": 0.8093, "step": 618 }, { - "epoch": 0.32, - "learning_rate": 1.9139063449792435e-05, - "loss": 0.875, + "epoch": 0.28, + "learning_rate": 1.9361385434948037e-05, + "loss": 0.8215, "step": 619 }, { - "epoch": 0.32, - "learning_rate": 1.913568034216372e-05, - "loss": 0.802, + "epoch": 0.28, + "learning_rate": 1.935878851762517e-05, + "loss": 0.8708, "step": 620 }, { - "epoch": 0.32, - "learning_rate": 1.913229090069622e-05, - "loss": 0.7825, + "epoch": 0.28, + "learning_rate": 1.9356186505726308e-05, + "loss": 0.8516, "step": 621 }, { - "epoch": 0.32, - "learning_rate": 1.9128895127739865e-05, - "loss": 0.8274, + "epoch": 0.28, + "learning_rate": 1.935357940066789e-05, + "loss": 0.8564, "step": 622 }, { - "epoch": 0.32, - "learning_rate": 1.9125493025648963e-05, - "loss": 0.8169, + "epoch": 0.28, + "learning_rate": 1.935096720386912e-05, + "loss": 0.7146, "step": 623 }, { - "epoch": 0.32, - "learning_rate": 1.9122084596782224e-05, - "loss": 0.8169, + "epoch": 0.28, + "learning_rate": 1.934834991675199e-05, + "loss": 0.8054, "step": 624 }, { - "epoch": 0.32, - "learning_rate": 1.9118669843502736e-05, - "loss": 0.7957, + "epoch": 0.28, + "learning_rate": 1.9345727540741247e-05, + "loss": 0.8494, "step": 625 }, { - "epoch": 0.32, - "learning_rate": 1.911524876817798e-05, - "loss": 0.8428, + "epoch": 0.29, + "learning_rate": 1.9343100077264415e-05, + "loss": 0.8276, "step": 626 }, { - "epoch": 0.32, - "learning_rate": 1.9111821373179806e-05, - "loss": 0.8059, + "epoch": 0.29, + "learning_rate": 1.934046752775179e-05, + "loss": 0.8459, "step": 627 }, { - "epoch": 0.32, - "learning_rate": 1.9108387660884456e-05, - "loss": 0.8191, + "epoch": 0.29, + "learning_rate": 1.9337829893636438e-05, + "loss": 0.8049, "step": 628 }, { - "epoch": 0.32, - "learning_rate": 1.9104947633672554e-05, - "loss": 0.8206, + "epoch": 0.29, + "learning_rate": 1.9335187176354183e-05, + "loss": 0.8438, "step": 629 }, { - "epoch": 0.32, - "learning_rate": 1.9101501293929092e-05, - "loss": 0.8547, + "epoch": 0.29, + "learning_rate": 1.9332539377343622e-05, + "loss": 0.7913, "step": 630 }, { - "epoch": 0.32, - "learning_rate": 1.909804864404345e-05, - "loss": 0.7861, + "epoch": 0.29, + "learning_rate": 1.932988649804612e-05, + "loss": 0.8313, "step": 631 }, { - "epoch": 0.32, - "learning_rate": 1.9094589686409373e-05, - "loss": 0.8481, + "epoch": 0.29, + "learning_rate": 1.9327228539905804e-05, + "loss": 0.8083, "step": 632 }, { - "epoch": 0.33, - "learning_rate": 1.9091124423424984e-05, - "loss": 0.7864, + "epoch": 0.29, + "learning_rate": 1.932456550436957e-05, + "loss": 0.7935, "step": 633 }, { - "epoch": 0.33, - "learning_rate": 1.908765285749278e-05, - "loss": 0.8423, + "epoch": 0.29, + "learning_rate": 1.9321897392887075e-05, + "loss": 0.7552, "step": 634 }, { - "epoch": 0.33, - "learning_rate": 1.9084174991019622e-05, - "loss": 0.8135, + "epoch": 0.29, + "learning_rate": 1.9319224206910734e-05, + "loss": 0.813, "step": 635 }, { - "epoch": 0.33, - "learning_rate": 1.9080690826416742e-05, - "loss": 0.7925, + "epoch": 0.29, + "learning_rate": 1.9316545947895737e-05, + "loss": 0.7607, "step": 636 }, { - "epoch": 0.33, - "learning_rate": 1.9077200366099743e-05, - "loss": 0.8528, + "epoch": 0.29, + "learning_rate": 1.9313862617300025e-05, + "loss": 0.8396, "step": 637 }, { - "epoch": 0.33, - "learning_rate": 1.907370361248858e-05, - "loss": 0.7603, + "epoch": 0.29, + "learning_rate": 1.9311174216584307e-05, + "loss": 0.8948, "step": 638 }, { - "epoch": 0.33, - "learning_rate": 1.9070200568007585e-05, - "loss": 0.7605, + "epoch": 0.29, + "learning_rate": 1.930848074721204e-05, + "loss": 0.8064, "step": 639 }, { - "epoch": 0.33, - "learning_rate": 1.906669123508545e-05, - "loss": 0.7891, + "epoch": 0.29, + "learning_rate": 1.930578221064946e-05, + "loss": 0.8374, "step": 640 }, { - "epoch": 0.33, - "learning_rate": 1.9063175616155214e-05, - "loss": 0.8242, + "epoch": 0.29, + "learning_rate": 1.930307860836554e-05, + "loss": 0.8104, "step": 641 }, { - "epoch": 0.33, - "learning_rate": 1.905965371365429e-05, - "loss": 0.8311, + "epoch": 0.29, + "learning_rate": 1.9300369941832025e-05, + "loss": 0.7677, "step": 642 }, { - "epoch": 0.33, - "learning_rate": 1.905612553002444e-05, - "loss": 0.8196, + "epoch": 0.29, + "learning_rate": 1.929765621252341e-05, + "loss": 0.8093, "step": 643 }, { - "epoch": 0.33, - "learning_rate": 1.905259106771178e-05, - "loss": 0.7583, + "epoch": 0.29, + "learning_rate": 1.9294937421916952e-05, + "loss": 0.7964, "step": 644 }, { - "epoch": 0.33, - "learning_rate": 1.9049050329166778e-05, - "loss": 0.8323, + "epoch": 0.29, + "learning_rate": 1.9292213571492655e-05, + "loss": 0.8506, "step": 645 }, { - "epoch": 0.33, - "learning_rate": 1.904550331684426e-05, - "loss": 0.7937, + "epoch": 0.29, + "learning_rate": 1.928948466273328e-05, + "loss": 0.8267, "step": 646 }, { - "epoch": 0.33, - "learning_rate": 1.9041950033203395e-05, - "loss": 0.7234, + "epoch": 0.29, + "learning_rate": 1.928675069712435e-05, + "loss": 0.7954, "step": 647 }, { - "epoch": 0.33, - "learning_rate": 1.90383904807077e-05, - "loss": 0.7981, + "epoch": 0.3, + "learning_rate": 1.9284011676154134e-05, + "loss": 0.8101, "step": 648 }, { - "epoch": 0.33, - "learning_rate": 1.9034824661825048e-05, - "loss": 0.7954, + "epoch": 0.3, + "learning_rate": 1.928126760131365e-05, + "loss": 0.7849, "step": 649 }, { - "epoch": 0.33, - "learning_rate": 1.9031252579027644e-05, - "loss": 0.842, + "epoch": 0.3, + "learning_rate": 1.9278518474096664e-05, + "loss": 0.8385, "step": 650 }, { - "epoch": 0.33, - "learning_rate": 1.902767423479204e-05, - "loss": 0.8225, + "epoch": 0.3, + "learning_rate": 1.927576429599971e-05, + "loss": 0.8066, "step": 651 }, { - "epoch": 0.34, - "learning_rate": 1.9024089631599136e-05, - "loss": 0.8289, + "epoch": 0.3, + "learning_rate": 1.9273005068522055e-05, + "loss": 0.8726, "step": 652 }, { - "epoch": 0.34, - "learning_rate": 1.9020498771934156e-05, - "loss": 0.8582, + "epoch": 0.3, + "learning_rate": 1.9270240793165714e-05, + "loss": 0.863, "step": 653 }, { - "epoch": 0.34, - "learning_rate": 1.901690165828668e-05, - "loss": 0.804, + "epoch": 0.3, + "learning_rate": 1.9267471471435467e-05, + "loss": 0.8472, "step": 654 }, { - "epoch": 0.34, - "learning_rate": 1.9013298293150613e-05, - "loss": 0.7939, + "epoch": 0.3, + "learning_rate": 1.926469710483882e-05, + "loss": 0.795, "step": 655 }, { - "epoch": 0.34, - "learning_rate": 1.900968867902419e-05, - "loss": 0.8391, + "epoch": 0.3, + "learning_rate": 1.926191769488604e-05, + "loss": 0.8015, "step": 656 }, { - "epoch": 0.34, - "learning_rate": 1.9006072818409994e-05, - "loss": 0.8286, + "epoch": 0.3, + "learning_rate": 1.925913324309013e-05, + "loss": 0.8442, "step": 657 }, { - "epoch": 0.34, - "learning_rate": 1.9002450713814925e-05, - "loss": 0.7805, + "epoch": 0.3, + "learning_rate": 1.9256343750966846e-05, + "loss": 0.9016, "step": 658 }, { - "epoch": 0.34, - "learning_rate": 1.8998822367750215e-05, - "loss": 0.8213, + "epoch": 0.3, + "learning_rate": 1.9253549220034682e-05, + "loss": 0.8494, "step": 659 }, { - "epoch": 0.34, - "learning_rate": 1.899518778273143e-05, - "loss": 0.832, + "epoch": 0.3, + "learning_rate": 1.9250749651814878e-05, + "loss": 0.7942, "step": 660 }, { - "epoch": 0.34, - "learning_rate": 1.899154696127845e-05, - "loss": 0.8062, + "epoch": 0.3, + "learning_rate": 1.9247945047831414e-05, + "loss": 0.8406, "step": 661 }, { - "epoch": 0.34, - "learning_rate": 1.898789990591549e-05, - "loss": 0.8276, + "epoch": 0.3, + "learning_rate": 1.924513540961101e-05, + "loss": 0.8577, "step": 662 }, { - "epoch": 0.34, - "learning_rate": 1.8984246619171075e-05, - "loss": 0.7683, + "epoch": 0.3, + "learning_rate": 1.9242320738683134e-05, + "loss": 0.8068, "step": 663 }, { - "epoch": 0.34, - "learning_rate": 1.8980587103578062e-05, - "loss": 0.7954, + "epoch": 0.3, + "learning_rate": 1.923950103657998e-05, + "loss": 0.8192, "step": 664 }, { - "epoch": 0.34, - "learning_rate": 1.8976921361673628e-05, - "loss": 0.7593, + "epoch": 0.3, + "learning_rate": 1.923667630483649e-05, + "loss": 0.8445, "step": 665 }, { - "epoch": 0.34, - "learning_rate": 1.897324939599925e-05, - "loss": 0.8257, + "epoch": 0.3, + "learning_rate": 1.923384654499035e-05, + "loss": 0.8704, "step": 666 }, { - "epoch": 0.34, - "learning_rate": 1.8969571209100738e-05, - "loss": 0.8311, + "epoch": 0.3, + "learning_rate": 1.923101175858197e-05, + "loss": 0.7881, "step": 667 }, { - "epoch": 0.34, - "learning_rate": 1.8965886803528203e-05, - "loss": 0.7729, + "epoch": 0.3, + "learning_rate": 1.9228171947154502e-05, + "loss": 0.7917, "step": 668 }, { - "epoch": 0.34, - "learning_rate": 1.8962196181836078e-05, - "loss": 0.8083, + "epoch": 0.3, + "learning_rate": 1.922532711225384e-05, + "loss": 0.8005, "step": 669 }, { - "epoch": 0.34, - "learning_rate": 1.8958499346583092e-05, - "loss": 0.8193, + "epoch": 0.31, + "learning_rate": 1.9222477255428597e-05, + "loss": 0.8365, "step": 670 }, { - "epoch": 0.34, - "learning_rate": 1.8954796300332295e-05, - "loss": 0.8127, + "epoch": 0.31, + "learning_rate": 1.9219622378230137e-05, + "loss": 0.8259, "step": 671 }, { - "epoch": 0.35, - "learning_rate": 1.895108704565104e-05, - "loss": 0.7744, + "epoch": 0.31, + "learning_rate": 1.9216762482212545e-05, + "loss": 0.8818, "step": 672 }, { - "epoch": 0.35, - "learning_rate": 1.8947371585110978e-05, - "loss": 0.8025, + "epoch": 0.31, + "learning_rate": 1.9213897568932638e-05, + "loss": 0.7852, "step": 673 }, { - "epoch": 0.35, - "learning_rate": 1.8943649921288067e-05, - "loss": 0.8025, + "epoch": 0.31, + "learning_rate": 1.9211027639949977e-05, + "loss": 0.8468, "step": 674 }, { - "epoch": 0.35, - "learning_rate": 1.893992205676257e-05, - "loss": 0.8206, + "epoch": 0.31, + "learning_rate": 1.9208152696826835e-05, + "loss": 0.8342, "step": 675 }, { - "epoch": 0.35, - "learning_rate": 1.8936187994119037e-05, - "loss": 0.8184, + "epoch": 0.31, + "learning_rate": 1.9205272741128232e-05, + "loss": 0.8455, "step": 676 }, { - "epoch": 0.35, - "learning_rate": 1.8932447735946332e-05, - "loss": 0.7974, + "epoch": 0.31, + "learning_rate": 1.9202387774421907e-05, + "loss": 0.8199, "step": 677 }, { - "epoch": 0.35, - "learning_rate": 1.8928701284837597e-05, - "loss": 0.8926, + "epoch": 0.31, + "learning_rate": 1.9199497798278324e-05, + "loss": 0.8108, "step": 678 }, { - "epoch": 0.35, - "learning_rate": 1.8924948643390283e-05, - "loss": 0.8374, + "epoch": 0.31, + "learning_rate": 1.919660281427068e-05, + "loss": 0.8479, "step": 679 }, { - "epoch": 0.35, - "learning_rate": 1.8921189814206122e-05, - "loss": 0.844, + "epoch": 0.31, + "learning_rate": 1.91937028239749e-05, + "loss": 0.8632, "step": 680 }, { - "epoch": 0.35, - "learning_rate": 1.891742479989114e-05, - "loss": 0.8252, + "epoch": 0.31, + "learning_rate": 1.919079782896963e-05, + "loss": 0.842, "step": 681 }, { - "epoch": 0.35, - "learning_rate": 1.891365360305565e-05, - "loss": 0.8328, + "epoch": 0.31, + "learning_rate": 1.9187887830836235e-05, + "loss": 0.8306, "step": 682 }, { - "epoch": 0.35, - "learning_rate": 1.8909876226314255e-05, - "loss": 0.8018, + "epoch": 0.31, + "learning_rate": 1.9184972831158818e-05, + "loss": 0.8037, "step": 683 }, { - "epoch": 0.35, - "learning_rate": 1.8906092672285842e-05, - "loss": 0.8433, + "epoch": 0.31, + "learning_rate": 1.918205283152419e-05, + "loss": 0.8484, "step": 684 }, { - "epoch": 0.35, - "learning_rate": 1.890230294359357e-05, - "loss": 0.7729, + "epoch": 0.31, + "learning_rate": 1.9179127833521892e-05, + "loss": 0.7916, "step": 685 }, { - "epoch": 0.35, - "learning_rate": 1.8898507042864893e-05, - "loss": 0.824, + "epoch": 0.31, + "learning_rate": 1.917619783874419e-05, + "loss": 0.7625, "step": 686 }, { - "epoch": 0.35, - "learning_rate": 1.889470497273154e-05, - "loss": 0.8213, + "epoch": 0.31, + "learning_rate": 1.9173262848786052e-05, + "loss": 0.8474, "step": 687 }, { - "epoch": 0.35, - "learning_rate": 1.8890896735829517e-05, - "loss": 0.781, + "epoch": 0.31, + "learning_rate": 1.9170322865245188e-05, + "loss": 0.8735, "step": 688 }, { - "epoch": 0.35, - "learning_rate": 1.8887082334799098e-05, - "loss": 0.8604, + "epoch": 0.31, + "learning_rate": 1.916737788972201e-05, + "loss": 0.8655, "step": 689 }, { - "epoch": 0.35, - "learning_rate": 1.8883261772284844e-05, - "loss": 0.7966, + "epoch": 0.31, + "learning_rate": 1.9164427923819655e-05, + "loss": 0.7996, "step": 690 }, { - "epoch": 0.36, - "learning_rate": 1.8879435050935577e-05, - "loss": 0.7739, + "epoch": 0.31, + "learning_rate": 1.9161472969143974e-05, + "loss": 0.8574, "step": 691 }, { - "epoch": 0.36, - "learning_rate": 1.8875602173404393e-05, - "loss": 0.7791, + "epoch": 0.32, + "learning_rate": 1.9158513027303533e-05, + "loss": 0.8425, "step": 692 }, { - "epoch": 0.36, - "learning_rate": 1.8871763142348657e-05, - "loss": 0.8704, + "epoch": 0.32, + "learning_rate": 1.9155548099909618e-05, + "loss": 0.8364, "step": 693 }, { - "epoch": 0.36, - "learning_rate": 1.886791796043e-05, - "loss": 0.7837, + "epoch": 0.32, + "learning_rate": 1.9152578188576222e-05, + "loss": 0.8457, "step": 694 }, { - "epoch": 0.36, - "learning_rate": 1.8864066630314318e-05, - "loss": 0.7703, + "epoch": 0.32, + "learning_rate": 1.9149603294920056e-05, + "loss": 0.8164, "step": 695 }, { - "epoch": 0.36, - "learning_rate": 1.886020915467176e-05, - "loss": 0.8228, + "epoch": 0.32, + "learning_rate": 1.914662342056054e-05, + "loss": 0.8796, "step": 696 }, { - "epoch": 0.36, - "learning_rate": 1.885634553617676e-05, - "loss": 0.781, + "epoch": 0.32, + "learning_rate": 1.91436385671198e-05, + "loss": 0.8125, "step": 697 }, { - "epoch": 0.36, - "learning_rate": 1.8852475777507983e-05, - "loss": 0.7974, + "epoch": 0.32, + "learning_rate": 1.914064873622269e-05, + "loss": 0.8088, "step": 698 }, { - "epoch": 0.36, - "learning_rate": 1.884859988134836e-05, - "loss": 0.7827, + "epoch": 0.32, + "learning_rate": 1.913765392949676e-05, + "loss": 0.7963, "step": 699 }, { - "epoch": 0.36, - "learning_rate": 1.884471785038509e-05, - "loss": 0.7817, + "epoch": 0.32, + "learning_rate": 1.9134654148572268e-05, + "loss": 0.8018, "step": 700 }, { - "epoch": 0.36, - "learning_rate": 1.8840829687309608e-05, - "loss": 0.8113, + "epoch": 0.32, + "learning_rate": 1.9131649395082186e-05, + "loss": 0.8319, "step": 701 }, { - "epoch": 0.36, - "learning_rate": 1.8836935394817613e-05, - "loss": 0.8435, + "epoch": 0.32, + "learning_rate": 1.9128639670662187e-05, + "loss": 0.8679, "step": 702 }, { - "epoch": 0.36, - "learning_rate": 1.883303497560905e-05, - "loss": 0.7854, + "epoch": 0.32, + "learning_rate": 1.9125624976950655e-05, + "loss": 0.9109, "step": 703 }, { - "epoch": 0.36, - "learning_rate": 1.8829128432388103e-05, - "loss": 0.8735, + "epoch": 0.32, + "learning_rate": 1.912260531558868e-05, + "loss": 0.8816, "step": 704 }, { - "epoch": 0.36, - "learning_rate": 1.8825215767863215e-05, - "loss": 0.838, + "epoch": 0.32, + "learning_rate": 1.9119580688220044e-05, + "loss": 0.8315, "step": 705 }, { - "epoch": 0.36, - "learning_rate": 1.882129698474706e-05, - "loss": 0.8232, + "epoch": 0.32, + "learning_rate": 1.911655109649125e-05, + "loss": 0.816, "step": 706 }, { - "epoch": 0.36, - "learning_rate": 1.881737208575657e-05, - "loss": 0.8257, + "epoch": 0.32, + "learning_rate": 1.9113516542051494e-05, + "loss": 0.8158, "step": 707 }, { - "epoch": 0.36, - "learning_rate": 1.8813441073612907e-05, - "loss": 0.8049, + "epoch": 0.32, + "learning_rate": 1.911047702655267e-05, + "loss": 0.7859, "step": 708 }, { - "epoch": 0.36, - "learning_rate": 1.8809503951041466e-05, - "loss": 0.8027, + "epoch": 0.32, + "learning_rate": 1.910743255164938e-05, + "loss": 0.8107, "step": 709 }, { - "epoch": 0.36, - "learning_rate": 1.880556072077189e-05, - "loss": 0.7649, + "epoch": 0.32, + "learning_rate": 1.9104383118998923e-05, + "loss": 0.7916, "step": 710 }, { - "epoch": 0.37, - "learning_rate": 1.8801611385538047e-05, - "loss": 0.7654, + "epoch": 0.32, + "learning_rate": 1.9101328730261296e-05, + "loss": 0.8549, "step": 711 }, { - "epoch": 0.37, - "learning_rate": 1.879765594807805e-05, - "loss": 0.8472, + "epoch": 0.32, + "learning_rate": 1.9098269387099195e-05, + "loss": 0.8262, "step": 712 }, { - "epoch": 0.37, - "learning_rate": 1.879369441113423e-05, - "loss": 0.8374, + "epoch": 0.32, + "learning_rate": 1.909520509117801e-05, + "loss": 0.7935, "step": 713 }, { - "epoch": 0.37, - "learning_rate": 1.8789726777453146e-05, - "loss": 0.8276, - "step": 714 + "epoch": 0.33, + "learning_rate": 1.9092135844165834e-05, + "loss": 0.7832, + "step": 714 }, { - "epoch": 0.37, - "learning_rate": 1.87857530497856e-05, - "loss": 0.7947, + "epoch": 0.33, + "learning_rate": 1.908906164773345e-05, + "loss": 0.9116, "step": 715 }, { - "epoch": 0.37, - "learning_rate": 1.87817732308866e-05, - "loss": 0.8354, + "epoch": 0.33, + "learning_rate": 1.908598250355433e-05, + "loss": 0.782, "step": 716 }, { - "epoch": 0.37, - "learning_rate": 1.8777787323515394e-05, - "loss": 0.7983, + "epoch": 0.33, + "learning_rate": 1.9082898413304652e-05, + "loss": 0.8055, "step": 717 }, { - "epoch": 0.37, - "learning_rate": 1.8773795330435433e-05, - "loss": 0.7771, + "epoch": 0.33, + "learning_rate": 1.9079809378663275e-05, + "loss": 0.8379, "step": 718 }, { - "epoch": 0.37, - "learning_rate": 1.8769797254414406e-05, - "loss": 0.824, + "epoch": 0.33, + "learning_rate": 1.9076715401311763e-05, + "loss": 0.8162, "step": 719 }, { - "epoch": 0.37, - "learning_rate": 1.8765793098224204e-05, - "loss": 0.8521, + "epoch": 0.33, + "learning_rate": 1.9073616482934355e-05, + "loss": 0.7957, "step": 720 }, { - "epoch": 0.37, - "learning_rate": 1.8761782864640944e-05, + "epoch": 0.33, + "learning_rate": 1.9070512625217986e-05, "loss": 0.8677, "step": 721 }, { - "epoch": 0.37, - "learning_rate": 1.875776655644495e-05, - "loss": 0.7996, + "epoch": 0.33, + "learning_rate": 1.906740382985228e-05, + "loss": 0.8425, "step": 722 }, { - "epoch": 0.37, - "learning_rate": 1.8753744176420764e-05, - "loss": 0.7947, + "epoch": 0.33, + "learning_rate": 1.9064290098529558e-05, + "loss": 0.7966, "step": 723 }, { - "epoch": 0.37, - "learning_rate": 1.8749715727357128e-05, - "loss": 0.8442, + "epoch": 0.33, + "learning_rate": 1.906117143294481e-05, + "loss": 0.8767, "step": 724 }, { - "epoch": 0.37, - "learning_rate": 1.8745681212046998e-05, - "loss": 0.7524, + "epoch": 0.33, + "learning_rate": 1.9058047834795728e-05, + "loss": 0.7666, "step": 725 }, { - "epoch": 0.37, - "learning_rate": 1.874164063328754e-05, - "loss": 0.8176, + "epoch": 0.33, + "learning_rate": 1.9054919305782677e-05, + "loss": 0.8643, "step": 726 }, { - "epoch": 0.37, - "learning_rate": 1.873759399388011e-05, - "loss": 0.8313, + "epoch": 0.33, + "learning_rate": 1.9051785847608718e-05, + "loss": 0.7977, "step": 727 }, { - "epoch": 0.37, - "learning_rate": 1.873354129663029e-05, - "loss": 0.8582, + "epoch": 0.33, + "learning_rate": 1.904864746197958e-05, + "loss": 0.8264, "step": 728 }, { - "epoch": 0.37, - "learning_rate": 1.872948254434783e-05, - "loss": 0.8384, + "epoch": 0.33, + "learning_rate": 1.9045504150603688e-05, + "loss": 0.8516, "step": 729 }, { - "epoch": 0.38, - "learning_rate": 1.8725417739846703e-05, - "loss": 0.7979, + "epoch": 0.33, + "learning_rate": 1.904235591519215e-05, + "loss": 0.8621, "step": 730 }, { - "epoch": 0.38, - "learning_rate": 1.8721346885945067e-05, - "loss": 0.7778, + "epoch": 0.33, + "learning_rate": 1.9039202757458736e-05, + "loss": 0.8413, "step": 731 }, { - "epoch": 0.38, - "learning_rate": 1.8717269985465286e-05, - "loss": 0.761, + "epoch": 0.33, + "learning_rate": 1.9036044679119916e-05, + "loss": 0.833, "step": 732 }, { - "epoch": 0.38, - "learning_rate": 1.8713187041233896e-05, - "loss": 0.7886, + "epoch": 0.33, + "learning_rate": 1.903288168189483e-05, + "loss": 0.8337, "step": 733 }, { - "epoch": 0.38, - "learning_rate": 1.8709098056081636e-05, - "loss": 0.8416, + "epoch": 0.33, + "learning_rate": 1.9029713767505292e-05, + "loss": 0.8182, "step": 734 }, { - "epoch": 0.38, - "learning_rate": 1.8705003032843438e-05, - "loss": 0.8254, + "epoch": 0.33, + "learning_rate": 1.90265409376758e-05, + "loss": 0.8943, "step": 735 }, { - "epoch": 0.38, - "learning_rate": 1.8700901974358406e-05, - "loss": 0.8037, + "epoch": 0.34, + "learning_rate": 1.9023363194133525e-05, + "loss": 0.8525, "step": 736 }, { - "epoch": 0.38, - "learning_rate": 1.869679488346984e-05, - "loss": 0.7947, + "epoch": 0.34, + "learning_rate": 1.9020180538608305e-05, + "loss": 0.7705, "step": 737 }, { - "epoch": 0.38, - "learning_rate": 1.869268176302522e-05, - "loss": 0.8125, + "epoch": 0.34, + "learning_rate": 1.9016992972832667e-05, + "loss": 0.7634, "step": 738 }, { - "epoch": 0.38, - "learning_rate": 1.8688562615876198e-05, - "loss": 0.8186, + "epoch": 0.34, + "learning_rate": 1.9013800498541804e-05, + "loss": 0.8188, "step": 739 }, { - "epoch": 0.38, - "learning_rate": 1.868443744487862e-05, - "loss": 0.8015, + "epoch": 0.34, + "learning_rate": 1.9010603117473575e-05, + "loss": 0.8369, "step": 740 }, { - "epoch": 0.38, - "learning_rate": 1.868030625289249e-05, - "loss": 0.821, + "epoch": 0.34, + "learning_rate": 1.9007400831368517e-05, + "loss": 0.8547, "step": 741 }, { - "epoch": 0.38, - "learning_rate": 1.8676169042782e-05, - "loss": 0.8137, + "epoch": 0.34, + "learning_rate": 1.9004193641969833e-05, + "loss": 0.8236, "step": 742 }, { - "epoch": 0.38, - "learning_rate": 1.8672025817415514e-05, - "loss": 0.8062, + "epoch": 0.34, + "learning_rate": 1.90009815510234e-05, + "loss": 0.7341, "step": 743 }, { - "epoch": 0.38, - "learning_rate": 1.8667876579665556e-05, - "loss": 0.79, + "epoch": 0.34, + "learning_rate": 1.8997764560277764e-05, + "loss": 0.8723, "step": 744 }, { - "epoch": 0.38, - "learning_rate": 1.866372133240883e-05, - "loss": 0.8047, + "epoch": 0.34, + "learning_rate": 1.899454267148413e-05, + "loss": 0.8213, "step": 745 }, { - "epoch": 0.38, - "learning_rate": 1.8659560078526203e-05, - "loss": 0.7817, + "epoch": 0.34, + "learning_rate": 1.8991315886396374e-05, + "loss": 0.7837, "step": 746 }, { - "epoch": 0.38, - "learning_rate": 1.8655392820902695e-05, - "loss": 0.8191, + "epoch": 0.34, + "learning_rate": 1.8988084206771037e-05, + "loss": 0.8325, "step": 747 }, { - "epoch": 0.38, - "learning_rate": 1.8651219562427513e-05, - "loss": 0.8306, + "epoch": 0.34, + "learning_rate": 1.8984847634367335e-05, + "loss": 0.8398, "step": 748 }, { - "epoch": 0.38, - "learning_rate": 1.8647040305994e-05, - "loss": 0.8582, + "epoch": 0.34, + "learning_rate": 1.8981606170947123e-05, + "loss": 0.8085, "step": 749 }, { - "epoch": 0.39, - "learning_rate": 1.8642855054499663e-05, - "loss": 0.8176, + "epoch": 0.34, + "learning_rate": 1.8978359818274944e-05, + "loss": 0.803, "step": 750 }, { - "epoch": 0.39, - "learning_rate": 1.863866381084618e-05, - "loss": 0.7903, + "epoch": 0.34, + "learning_rate": 1.8975108578117987e-05, + "loss": 0.9006, "step": 751 }, { - "epoch": 0.39, - "learning_rate": 1.8634466577939368e-05, - "loss": 0.7742, + "epoch": 0.34, + "learning_rate": 1.8971852452246106e-05, + "loss": 0.8088, "step": 752 }, { - "epoch": 0.39, - "learning_rate": 1.8630263358689202e-05, - "loss": 0.7898, + "epoch": 0.34, + "learning_rate": 1.8968591442431816e-05, + "loss": 0.8252, "step": 753 }, { - "epoch": 0.39, - "learning_rate": 1.8626054156009807e-05, - "loss": 0.793, + "epoch": 0.34, + "learning_rate": 1.8965325550450288e-05, + "loss": 0.814, "step": 754 }, { - "epoch": 0.39, - "learning_rate": 1.862183897281946e-05, - "loss": 0.8184, + "epoch": 0.34, + "learning_rate": 1.8962054778079353e-05, + "loss": 0.8174, "step": 755 }, { - "epoch": 0.39, - "learning_rate": 1.8617617812040572e-05, - "loss": 0.824, + "epoch": 0.34, + "learning_rate": 1.8958779127099497e-05, + "loss": 0.7424, "step": 756 }, { - "epoch": 0.39, - "learning_rate": 1.8613390676599716e-05, - "loss": 0.8062, + "epoch": 0.34, + "learning_rate": 1.8955498599293862e-05, + "loss": 0.7834, "step": 757 }, { - "epoch": 0.39, - "learning_rate": 1.8609157569427593e-05, - "loss": 0.8157, + "epoch": 0.35, + "learning_rate": 1.8952213196448245e-05, + "loss": 0.7839, "step": 758 }, { - "epoch": 0.39, - "learning_rate": 1.8604918493459048e-05, - "loss": 0.7637, + "epoch": 0.35, + "learning_rate": 1.89489229203511e-05, + "loss": 0.8467, "step": 759 }, { - "epoch": 0.39, - "learning_rate": 1.8600673451633067e-05, - "loss": 0.7822, + "epoch": 0.35, + "learning_rate": 1.894562777279353e-05, + "loss": 0.8224, "step": 760 }, { - "epoch": 0.39, - "learning_rate": 1.8596422446892774e-05, - "loss": 0.7825, + "epoch": 0.35, + "learning_rate": 1.8942327755569286e-05, + "loss": 0.8052, "step": 761 }, { - "epoch": 0.39, - "learning_rate": 1.8592165482185424e-05, - "loss": 0.7966, + "epoch": 0.35, + "learning_rate": 1.893902287047478e-05, + "loss": 0.8457, "step": 762 }, { - "epoch": 0.39, - "learning_rate": 1.85879025604624e-05, - "loss": 0.7581, + "epoch": 0.35, + "learning_rate": 1.8935713119309064e-05, + "loss": 0.8121, "step": 763 }, { - "epoch": 0.39, - "learning_rate": 1.8583633684679218e-05, - "loss": 0.7739, + "epoch": 0.35, + "learning_rate": 1.893239850387385e-05, + "loss": 0.8198, "step": 764 }, { - "epoch": 0.39, - "learning_rate": 1.857935885779553e-05, - "loss": 0.8218, + "epoch": 0.35, + "learning_rate": 1.8929079025973483e-05, + "loss": 0.832, "step": 765 }, { - "epoch": 0.39, - "learning_rate": 1.8575078082775096e-05, - "loss": 0.821, + "epoch": 0.35, + "learning_rate": 1.8925754687414967e-05, + "loss": 0.8296, "step": 766 }, { - "epoch": 0.39, - "learning_rate": 1.8570791362585823e-05, - "loss": 0.776, + "epoch": 0.35, + "learning_rate": 1.892242549000795e-05, + "loss": 0.8809, "step": 767 }, { - "epoch": 0.39, - "learning_rate": 1.856649870019972e-05, - "loss": 0.8171, + "epoch": 0.35, + "learning_rate": 1.8919091435564716e-05, + "loss": 0.8542, "step": 768 }, { - "epoch": 0.4, - "learning_rate": 1.8562200098592927e-05, - "loss": 0.866, + "epoch": 0.35, + "learning_rate": 1.891575252590021e-05, + "loss": 0.8005, "step": 769 }, { - "epoch": 0.4, - "learning_rate": 1.8557895560745695e-05, - "loss": 0.8579, + "epoch": 0.35, + "learning_rate": 1.8912408762832e-05, + "loss": 0.825, "step": 770 }, { - "epoch": 0.4, - "learning_rate": 1.8553585089642395e-05, - "loss": 0.8032, + "epoch": 0.35, + "learning_rate": 1.890906014818032e-05, + "loss": 0.7415, "step": 771 }, { - "epoch": 0.4, - "learning_rate": 1.8549268688271517e-05, - "loss": 0.7986, + "epoch": 0.35, + "learning_rate": 1.8905706683768018e-05, + "loss": 0.832, "step": 772 }, { - "epoch": 0.4, - "learning_rate": 1.8544946359625644e-05, - "loss": 0.7905, + "epoch": 0.35, + "learning_rate": 1.8902348371420598e-05, + "loss": 0.7957, "step": 773 }, { - "epoch": 0.4, - "learning_rate": 1.854061810670149e-05, - "loss": 0.7419, + "epoch": 0.35, + "learning_rate": 1.8898985212966203e-05, + "loss": 0.7866, "step": 774 }, { - "epoch": 0.4, - "learning_rate": 1.853628393249986e-05, - "loss": 0.8467, + "epoch": 0.35, + "learning_rate": 1.8895617210235613e-05, + "loss": 0.8356, "step": 775 }, { - "epoch": 0.4, - "learning_rate": 1.8531943840025673e-05, - "loss": 0.7917, + "epoch": 0.35, + "learning_rate": 1.8892244365062237e-05, + "loss": 0.8538, "step": 776 }, { - "epoch": 0.4, - "learning_rate": 1.8527597832287954e-05, - "loss": 0.8071, + "epoch": 0.35, + "learning_rate": 1.8888866679282133e-05, + "loss": 0.8325, "step": 777 }, { - "epoch": 0.4, - "learning_rate": 1.852324591229982e-05, - "loss": 0.7722, + "epoch": 0.35, + "learning_rate": 1.8885484154733983e-05, + "loss": 0.7896, "step": 778 }, { - "epoch": 0.4, - "learning_rate": 1.851888808307849e-05, - "loss": 0.8276, + "epoch": 0.35, + "learning_rate": 1.8882096793259107e-05, + "loss": 0.7698, "step": 779 }, { - "epoch": 0.4, - "learning_rate": 1.8514524347645282e-05, - "loss": 0.8562, + "epoch": 0.36, + "learning_rate": 1.887870459670146e-05, + "loss": 0.8157, "step": 780 }, { - "epoch": 0.4, - "learning_rate": 1.851015470902561e-05, - "loss": 0.845, + "epoch": 0.36, + "learning_rate": 1.8875307566907626e-05, + "loss": 0.7635, "step": 781 }, { - "epoch": 0.4, - "learning_rate": 1.8505779170248978e-05, - "loss": 0.8223, + "epoch": 0.36, + "learning_rate": 1.8871905705726827e-05, + "loss": 0.8584, "step": 782 }, { - "epoch": 0.4, - "learning_rate": 1.8501397734348977e-05, - "loss": 0.7664, + "epoch": 0.36, + "learning_rate": 1.8868499015010902e-05, + "loss": 0.7751, "step": 783 }, { - "epoch": 0.4, - "learning_rate": 1.8497010404363297e-05, - "loss": 0.8181, + "epoch": 0.36, + "learning_rate": 1.886508749661433e-05, + "loss": 0.7816, "step": 784 }, { - "epoch": 0.4, - "learning_rate": 1.8492617183333705e-05, - "loss": 0.8296, + "epoch": 0.36, + "learning_rate": 1.886167115239422e-05, + "loss": 0.8411, "step": 785 }, { - "epoch": 0.4, - "learning_rate": 1.848821807430606e-05, - "loss": 0.8049, + "epoch": 0.36, + "learning_rate": 1.8858249984210295e-05, + "loss": 0.802, "step": 786 }, { - "epoch": 0.4, - "learning_rate": 1.8483813080330294e-05, - "loss": 0.8269, + "epoch": 0.36, + "learning_rate": 1.885482399392491e-05, + "loss": 0.7324, "step": 787 }, { - "epoch": 0.41, - "learning_rate": 1.847940220446042e-05, - "loss": 0.8186, + "epoch": 0.36, + "learning_rate": 1.8851393183403055e-05, + "loss": 0.7986, "step": 788 }, { - "epoch": 0.41, - "learning_rate": 1.8474985449754543e-05, - "loss": 0.7998, + "epoch": 0.36, + "learning_rate": 1.8847957554512327e-05, + "loss": 0.7867, "step": 789 }, { - "epoch": 0.41, - "learning_rate": 1.8470562819274825e-05, - "loss": 0.7793, + "epoch": 0.36, + "learning_rate": 1.8844517109122965e-05, + "loss": 0.7476, "step": 790 }, { - "epoch": 0.41, - "learning_rate": 1.8466134316087518e-05, - "loss": 0.8003, + "epoch": 0.36, + "learning_rate": 1.8841071849107808e-05, + "loss": 0.7495, "step": 791 }, { - "epoch": 0.41, - "learning_rate": 1.846169994326293e-05, - "loss": 0.7993, + "epoch": 0.36, + "learning_rate": 1.8837621776342334e-05, + "loss": 0.8334, "step": 792 }, { - "epoch": 0.41, - "learning_rate": 1.8457259703875453e-05, - "loss": 0.8345, + "epoch": 0.36, + "learning_rate": 1.883416689270463e-05, + "loss": 0.8213, "step": 793 }, { - "epoch": 0.41, - "learning_rate": 1.8452813601003537e-05, - "loss": 0.7253, + "epoch": 0.36, + "learning_rate": 1.8830707200075408e-05, + "loss": 0.8513, "step": 794 }, { - "epoch": 0.41, - "learning_rate": 1.8448361637729698e-05, - "loss": 0.7979, + "epoch": 0.36, + "learning_rate": 1.8827242700337994e-05, + "loss": 0.7954, "step": 795 }, { - "epoch": 0.41, - "learning_rate": 1.8443903817140517e-05, - "loss": 0.7383, + "epoch": 0.36, + "learning_rate": 1.882377339537834e-05, + "loss": 0.7977, "step": 796 }, { - "epoch": 0.41, - "learning_rate": 1.8439440142326642e-05, - "loss": 0.8054, + "epoch": 0.36, + "learning_rate": 1.8820299287084996e-05, + "loss": 0.8831, "step": 797 }, { - "epoch": 0.41, - "learning_rate": 1.843497061638277e-05, - "loss": 0.8411, + "epoch": 0.36, + "learning_rate": 1.881682037734915e-05, + "loss": 0.8445, "step": 798 }, { - "epoch": 0.41, - "learning_rate": 1.843049524240766e-05, - "loss": 0.8447, + "epoch": 0.36, + "learning_rate": 1.8813336668064576e-05, + "loss": 0.8464, "step": 799 }, { - "epoch": 0.41, - "learning_rate": 1.8426014023504115e-05, - "loss": 0.8318, + "epoch": 0.36, + "learning_rate": 1.8809848161127685e-05, + "loss": 0.8032, "step": 800 }, { - "epoch": 0.41, - "learning_rate": 1.842152696277901e-05, - "loss": 0.7944, + "epoch": 0.36, + "learning_rate": 1.8806354858437488e-05, + "loss": 0.8821, "step": 801 }, { - "epoch": 0.41, - "learning_rate": 1.8417034063343255e-05, - "loss": 0.8022, + "epoch": 0.37, + "learning_rate": 1.880285676189561e-05, + "loss": 0.8401, "step": 802 }, { - "epoch": 0.41, - "learning_rate": 1.8412535328311813e-05, - "loss": 0.813, + "epoch": 0.37, + "learning_rate": 1.8799353873406283e-05, + "loss": 0.8474, "step": 803 }, { - "epoch": 0.41, - "learning_rate": 1.840803076080369e-05, - "loss": 0.8545, + "epoch": 0.37, + "learning_rate": 1.879584619487635e-05, + "loss": 0.8115, "step": 804 }, { - "epoch": 0.41, - "learning_rate": 1.8403520363941945e-05, - "loss": 0.8091, + "epoch": 0.37, + "learning_rate": 1.8792333728215258e-05, + "loss": 0.8398, "step": 805 }, { - "epoch": 0.41, - "learning_rate": 1.8399004140853663e-05, - "loss": 0.7705, + "epoch": 0.37, + "learning_rate": 1.878881647533507e-05, + "loss": 0.7587, "step": 806 }, { - "epoch": 0.41, - "learning_rate": 1.839448209466998e-05, - "loss": 0.7842, + "epoch": 0.37, + "learning_rate": 1.878529443815044e-05, + "loss": 0.877, "step": 807 }, { - "epoch": 0.42, - "learning_rate": 1.838995422852607e-05, - "loss": 0.8196, + "epoch": 0.37, + "learning_rate": 1.8781767618578637e-05, + "loss": 0.8149, "step": 808 }, { - "epoch": 0.42, - "learning_rate": 1.8385420545561134e-05, - "loss": 0.7788, + "epoch": 0.37, + "learning_rate": 1.877823601853953e-05, + "loss": 0.8157, "step": 809 }, { - "epoch": 0.42, - "learning_rate": 1.8380881048918406e-05, - "loss": 0.8328, + "epoch": 0.37, + "learning_rate": 1.8774699639955593e-05, + "loss": 0.7871, "step": 810 }, { - "epoch": 0.42, - "learning_rate": 1.8376335741745164e-05, - "loss": 0.8186, + "epoch": 0.37, + "learning_rate": 1.8771158484751893e-05, + "loss": 0.7883, "step": 811 }, { - "epoch": 0.42, - "learning_rate": 1.83717846271927e-05, - "loss": 0.7527, + "epoch": 0.37, + "learning_rate": 1.8767612554856104e-05, + "loss": 0.8076, "step": 812 }, { - "epoch": 0.42, - "learning_rate": 1.8367227708416334e-05, - "loss": 0.7732, + "epoch": 0.37, + "learning_rate": 1.8764061852198505e-05, + "loss": 0.7646, "step": 813 }, { - "epoch": 0.42, - "learning_rate": 1.836266498857542e-05, - "loss": 0.8091, + "epoch": 0.37, + "learning_rate": 1.8760506378711962e-05, + "loss": 0.884, "step": 814 }, { - "epoch": 0.42, - "learning_rate": 1.8358096470833325e-05, - "loss": 0.8179, + "epoch": 0.37, + "learning_rate": 1.875694613633194e-05, + "loss": 0.8436, "step": 815 }, { - "epoch": 0.42, - "learning_rate": 1.8353522158357434e-05, - "loss": 0.802, + "epoch": 0.37, + "learning_rate": 1.8753381126996504e-05, + "loss": 0.7876, "step": 816 }, { - "epoch": 0.42, - "learning_rate": 1.8348942054319164e-05, - "loss": 0.822, + "epoch": 0.37, + "learning_rate": 1.8749811352646316e-05, + "loss": 0.8135, "step": 817 }, { - "epoch": 0.42, - "learning_rate": 1.8344356161893925e-05, - "loss": 0.8186, + "epoch": 0.37, + "learning_rate": 1.8746236815224623e-05, + "loss": 0.8325, "step": 818 }, { - "epoch": 0.42, - "learning_rate": 1.833976448426116e-05, - "loss": 0.8149, + "epoch": 0.37, + "learning_rate": 1.8742657516677272e-05, + "loss": 0.7566, "step": 819 }, { - "epoch": 0.42, - "learning_rate": 1.833516702460431e-05, - "loss": 0.8621, + "epoch": 0.37, + "learning_rate": 1.8739073458952704e-05, + "loss": 0.8147, "step": 820 }, { - "epoch": 0.42, - "learning_rate": 1.8330563786110837e-05, - "loss": 0.7905, + "epoch": 0.37, + "learning_rate": 1.8735484644001938e-05, + "loss": 0.8286, "step": 821 }, { - "epoch": 0.42, - "learning_rate": 1.8325954771972192e-05, - "loss": 0.8076, + "epoch": 0.37, + "learning_rate": 1.8731891073778597e-05, + "loss": 0.8125, "step": 822 }, { - "epoch": 0.42, - "learning_rate": 1.832133998538385e-05, - "loss": 0.8616, + "epoch": 0.37, + "learning_rate": 1.8728292750238887e-05, + "loss": 0.7747, "step": 823 }, { - "epoch": 0.42, - "learning_rate": 1.8316719429545277e-05, - "loss": 0.8086, + "epoch": 0.38, + "learning_rate": 1.8724689675341602e-05, + "loss": 0.8904, "step": 824 }, { - "epoch": 0.42, - "learning_rate": 1.8312093107659935e-05, - "loss": 0.7573, + "epoch": 0.38, + "learning_rate": 1.8721081851048118e-05, + "loss": 0.7783, "step": 825 }, { - "epoch": 0.42, - "learning_rate": 1.8307461022935295e-05, - "loss": 0.8005, + "epoch": 0.38, + "learning_rate": 1.87174692793224e-05, + "loss": 0.8254, "step": 826 }, { - "epoch": 0.43, - "learning_rate": 1.8302823178582812e-05, - "loss": 0.7898, + "epoch": 0.38, + "learning_rate": 1.8713851962131003e-05, + "loss": 0.804, "step": 827 }, { - "epoch": 0.43, - "learning_rate": 1.8298179577817948e-05, - "loss": 0.7473, + "epoch": 0.38, + "learning_rate": 1.8710229901443056e-05, + "loss": 0.8195, "step": 828 }, { - "epoch": 0.43, - "learning_rate": 1.8293530223860144e-05, - "loss": 0.7961, + "epoch": 0.38, + "learning_rate": 1.8706603099230275e-05, + "loss": 0.7372, "step": 829 }, { - "epoch": 0.43, - "learning_rate": 1.828887511993283e-05, - "loss": 0.7905, + "epoch": 0.38, + "learning_rate": 1.8702971557466953e-05, + "loss": 0.8181, "step": 830 }, { - "epoch": 0.43, - "learning_rate": 1.828421426926343e-05, - "loss": 0.8115, + "epoch": 0.38, + "learning_rate": 1.8699335278129968e-05, + "loss": 0.7687, "step": 831 }, { - "epoch": 0.43, - "learning_rate": 1.8279547675083343e-05, - "loss": 0.8081, + "epoch": 0.38, + "learning_rate": 1.869569426319878e-05, + "loss": 0.8263, "step": 832 }, { - "epoch": 0.43, - "learning_rate": 1.8274875340627966e-05, - "loss": 0.8408, + "epoch": 0.38, + "learning_rate": 1.8692048514655414e-05, + "loss": 0.814, "step": 833 }, { - "epoch": 0.43, - "learning_rate": 1.8270197269136654e-05, - "loss": 0.8369, + "epoch": 0.38, + "learning_rate": 1.8688398034484483e-05, + "loss": 0.8203, "step": 834 }, { - "epoch": 0.43, - "learning_rate": 1.8265513463852754e-05, - "loss": 0.7925, + "epoch": 0.38, + "learning_rate": 1.8684742824673177e-05, + "loss": 0.7308, "step": 835 }, { - "epoch": 0.43, - "learning_rate": 1.826082392802359e-05, - "loss": 0.8269, + "epoch": 0.38, + "learning_rate": 1.8681082887211248e-05, + "loss": 0.8367, "step": 836 }, { - "epoch": 0.43, - "learning_rate": 1.8256128664900453e-05, - "loss": 0.7603, + "epoch": 0.38, + "learning_rate": 1.8677418224091038e-05, + "loss": 0.7709, "step": 837 }, { - "epoch": 0.43, - "learning_rate": 1.8251427677738596e-05, - "loss": 0.7891, + "epoch": 0.38, + "learning_rate": 1.8673748837307445e-05, + "loss": 0.7848, "step": 838 }, { - "epoch": 0.43, - "learning_rate": 1.824672096979726e-05, - "loss": 0.8159, + "epoch": 0.38, + "learning_rate": 1.867007472885795e-05, + "loss": 0.8694, "step": 839 }, { - "epoch": 0.43, - "learning_rate": 1.824200854433964e-05, - "loss": 0.8433, + "epoch": 0.38, + "learning_rate": 1.8666395900742603e-05, + "loss": 0.8057, "step": 840 }, { - "epoch": 0.43, - "learning_rate": 1.8237290404632896e-05, - "loss": 0.793, + "epoch": 0.38, + "learning_rate": 1.866271235496402e-05, + "loss": 0.7793, "step": 841 }, { - "epoch": 0.43, - "learning_rate": 1.8232566553948152e-05, - "loss": 0.7771, + "epoch": 0.38, + "learning_rate": 1.8659024093527387e-05, + "loss": 0.8293, "step": 842 }, { - "epoch": 0.43, - "learning_rate": 1.822783699556049e-05, - "loss": 0.7888, + "epoch": 0.38, + "learning_rate": 1.8655331118440453e-05, + "loss": 0.8237, "step": 843 }, { - "epoch": 0.43, - "learning_rate": 1.8223101732748952e-05, - "loss": 0.8159, + "epoch": 0.38, + "learning_rate": 1.8651633431713536e-05, + "loss": 0.8423, "step": 844 }, { - "epoch": 0.43, - "learning_rate": 1.8218360768796534e-05, - "loss": 0.8027, + "epoch": 0.38, + "learning_rate": 1.8647931035359522e-05, + "loss": 0.7727, "step": 845 }, { - "epoch": 0.43, - "learning_rate": 1.821361410699018e-05, - "loss": 0.8208, + "epoch": 0.39, + "learning_rate": 1.8644223931393857e-05, + "loss": 0.8413, "step": 846 }, { - "epoch": 0.44, - "learning_rate": 1.820886175062079e-05, - "loss": 0.8269, + "epoch": 0.39, + "learning_rate": 1.8640512121834548e-05, + "loss": 0.7198, "step": 847 }, { - "epoch": 0.44, - "learning_rate": 1.8204103702983206e-05, - "loss": 0.8564, + "epoch": 0.39, + "learning_rate": 1.863679560870217e-05, + "loss": 0.7747, "step": 848 }, { - "epoch": 0.44, - "learning_rate": 1.819933996737622e-05, - "loss": 0.8342, + "epoch": 0.39, + "learning_rate": 1.863307439401985e-05, + "loss": 0.821, "step": 849 }, { - "epoch": 0.44, - "learning_rate": 1.8194570547102577e-05, - "loss": 0.8599, + "epoch": 0.39, + "learning_rate": 1.8629348479813284e-05, + "loss": 0.7723, "step": 850 }, { - "epoch": 0.44, - "learning_rate": 1.818979544546894e-05, - "loss": 0.8301, + "epoch": 0.39, + "learning_rate": 1.8625617868110715e-05, + "loss": 0.8031, "step": 851 }, { - "epoch": 0.44, - "learning_rate": 1.8185014665785936e-05, - "loss": 0.8506, + "epoch": 0.39, + "learning_rate": 1.8621882560942954e-05, + "loss": 0.8584, "step": 852 }, { - "epoch": 0.44, - "learning_rate": 1.8180228211368113e-05, - "loss": 0.7922, + "epoch": 0.39, + "learning_rate": 1.861814256034336e-05, + "loss": 0.8143, "step": 853 }, { - "epoch": 0.44, - "learning_rate": 1.817543608553395e-05, - "loss": 0.8025, + "epoch": 0.39, + "learning_rate": 1.861439786834785e-05, + "loss": 0.812, "step": 854 }, { - "epoch": 0.44, - "learning_rate": 1.8170638291605874e-05, - "loss": 0.8381, + "epoch": 0.39, + "learning_rate": 1.8610648486994897e-05, + "loss": 0.8066, "step": 855 }, { - "epoch": 0.44, - "learning_rate": 1.816583483291023e-05, - "loss": 0.8198, + "epoch": 0.39, + "learning_rate": 1.8606894418325524e-05, + "loss": 0.8459, "step": 856 }, { - "epoch": 0.44, - "learning_rate": 1.8161025712777296e-05, - "loss": 0.7969, + "epoch": 0.39, + "learning_rate": 1.8603135664383307e-05, + "loss": 0.8168, "step": 857 }, { - "epoch": 0.44, - "learning_rate": 1.815621093454127e-05, - "loss": 0.8083, + "epoch": 0.39, + "learning_rate": 1.8599372227214366e-05, + "loss": 0.8196, "step": 858 }, { - "epoch": 0.44, - "learning_rate": 1.8151390501540276e-05, - "loss": 0.7942, + "epoch": 0.39, + "learning_rate": 1.8595604108867386e-05, + "loss": 0.8022, "step": 859 }, { - "epoch": 0.44, - "learning_rate": 1.8146564417116355e-05, - "loss": 0.8074, + "epoch": 0.39, + "learning_rate": 1.8591831311393583e-05, + "loss": 0.7584, "step": 860 }, { - "epoch": 0.44, - "learning_rate": 1.8141732684615478e-05, - "loss": 0.7837, + "epoch": 0.39, + "learning_rate": 1.858805383684673e-05, + "loss": 0.7991, "step": 861 }, { - "epoch": 0.44, - "learning_rate": 1.8136895307387513e-05, - "loss": 0.8123, + "epoch": 0.39, + "learning_rate": 1.8584271687283138e-05, + "loss": 0.804, "step": 862 }, { - "epoch": 0.44, - "learning_rate": 1.8132052288786262e-05, - "loss": 0.8091, + "epoch": 0.39, + "learning_rate": 1.8580484864761678e-05, + "loss": 0.8484, "step": 863 }, { - "epoch": 0.44, - "learning_rate": 1.8127203632169416e-05, - "loss": 0.7864, + "epoch": 0.39, + "learning_rate": 1.857669337134375e-05, + "loss": 0.729, "step": 864 }, { - "epoch": 0.44, - "learning_rate": 1.8122349340898596e-05, - "loss": 0.7878, + "epoch": 0.39, + "learning_rate": 1.85728972090933e-05, + "loss": 0.8086, "step": 865 }, { - "epoch": 0.45, - "learning_rate": 1.8117489418339317e-05, - "loss": 0.8269, + "epoch": 0.39, + "learning_rate": 1.856909638007682e-05, + "loss": 0.875, "step": 866 }, { - "epoch": 0.45, - "learning_rate": 1.8112623867861e-05, - "loss": 0.7539, + "epoch": 0.39, + "learning_rate": 1.856529088636334e-05, + "loss": 0.781, "step": 867 }, { - "epoch": 0.45, - "learning_rate": 1.8107752692836967e-05, - "loss": 0.8169, + "epoch": 0.4, + "learning_rate": 1.856148073002443e-05, + "loss": 0.8337, "step": 868 }, { - "epoch": 0.45, - "learning_rate": 1.810287589664445e-05, - "loss": 0.8298, + "epoch": 0.4, + "learning_rate": 1.8557665913134193e-05, + "loss": 0.7932, "step": 869 }, { - "epoch": 0.45, - "learning_rate": 1.8097993482664563e-05, - "loss": 0.7629, + "epoch": 0.4, + "learning_rate": 1.8553846437769278e-05, + "loss": 0.7555, "step": 870 }, { - "epoch": 0.45, - "learning_rate": 1.8093105454282325e-05, - "loss": 0.8259, + "epoch": 0.4, + "learning_rate": 1.8550022306008864e-05, + "loss": 0.7903, "step": 871 }, { - "epoch": 0.45, - "learning_rate": 1.808821181488664e-05, - "loss": 0.8621, + "epoch": 0.4, + "learning_rate": 1.8546193519934664e-05, + "loss": 0.7867, "step": 872 }, { - "epoch": 0.45, - "learning_rate": 1.8083312567870315e-05, - "loss": 0.7712, + "epoch": 0.4, + "learning_rate": 1.8542360081630928e-05, + "loss": 0.8114, "step": 873 }, { - "epoch": 0.45, - "learning_rate": 1.8078407716630025e-05, - "loss": 0.7781, + "epoch": 0.4, + "learning_rate": 1.8538521993184436e-05, + "loss": 0.7705, "step": 874 }, { - "epoch": 0.45, - "learning_rate": 1.8073497264566354e-05, - "loss": 0.8337, + "epoch": 0.4, + "learning_rate": 1.85346792566845e-05, + "loss": 0.8296, "step": 875 }, { - "epoch": 0.45, - "learning_rate": 1.8068581215083752e-05, - "loss": 0.8149, + "epoch": 0.4, + "learning_rate": 1.8530831874222966e-05, + "loss": 0.8091, "step": 876 }, { - "epoch": 0.45, - "learning_rate": 1.8063659571590547e-05, - "loss": 0.8323, + "epoch": 0.4, + "learning_rate": 1.8526979847894203e-05, + "loss": 0.7998, "step": 877 }, { - "epoch": 0.45, - "learning_rate": 1.8058732337498965e-05, - "loss": 0.7871, + "epoch": 0.4, + "learning_rate": 1.852312317979511e-05, + "loss": 0.7522, "step": 878 }, { - "epoch": 0.45, - "learning_rate": 1.805379951622509e-05, - "loss": 0.8354, + "epoch": 0.4, + "learning_rate": 1.851926187202512e-05, + "loss": 0.8032, "step": 879 }, { - "epoch": 0.45, - "learning_rate": 1.8048861111188886e-05, - "loss": 0.7832, + "epoch": 0.4, + "learning_rate": 1.8515395926686176e-05, + "loss": 0.7854, "step": 880 }, { - "epoch": 0.45, - "learning_rate": 1.8043917125814186e-05, - "loss": 0.8262, + "epoch": 0.4, + "learning_rate": 1.851152534588276e-05, + "loss": 0.8291, "step": 881 }, { - "epoch": 0.45, - "learning_rate": 1.80389675635287e-05, - "loss": 0.8655, + "epoch": 0.4, + "learning_rate": 1.850765013172187e-05, + "loss": 0.8118, "step": 882 }, { - "epoch": 0.45, - "learning_rate": 1.803401242776399e-05, - "loss": 0.8013, + "epoch": 0.4, + "learning_rate": 1.850377028631303e-05, + "loss": 0.7349, "step": 883 }, { - "epoch": 0.45, - "learning_rate": 1.80290517219555e-05, - "loss": 0.8125, + "epoch": 0.4, + "learning_rate": 1.849988581176828e-05, + "loss": 0.8276, "step": 884 }, { - "epoch": 0.45, - "learning_rate": 1.8024085449542518e-05, - "loss": 0.8044, + "epoch": 0.4, + "learning_rate": 1.8495996710202187e-05, + "loss": 0.8088, "step": 885 }, { - "epoch": 0.46, - "learning_rate": 1.8019113613968204e-05, - "loss": 0.7737, + "epoch": 0.4, + "learning_rate": 1.849210298373183e-05, + "loss": 0.8052, "step": 886 }, { - "epoch": 0.46, - "learning_rate": 1.8014136218679566e-05, - "loss": 0.7942, + "epoch": 0.4, + "learning_rate": 1.8488204634476817e-05, + "loss": 0.7764, "step": 887 }, { - "epoch": 0.46, - "learning_rate": 1.8009153267127478e-05, - "loss": 0.8274, + "epoch": 0.4, + "learning_rate": 1.8484301664559253e-05, + "loss": 0.8279, "step": 888 }, { - "epoch": 0.46, - "learning_rate": 1.8004164762766655e-05, - "loss": 0.7996, + "epoch": 0.41, + "learning_rate": 1.8480394076103773e-05, + "loss": 0.8215, "step": 889 }, { - "epoch": 0.46, - "learning_rate": 1.7999170709055668e-05, - "loss": 0.8184, + "epoch": 0.41, + "learning_rate": 1.8476481871237527e-05, + "loss": 0.8442, "step": 890 }, { - "epoch": 0.46, - "learning_rate": 1.799417110945693e-05, - "loss": 0.7322, + "epoch": 0.41, + "learning_rate": 1.847256505209017e-05, + "loss": 0.8042, "step": 891 }, { - "epoch": 0.46, - "learning_rate": 1.7989165967436707e-05, - "loss": 0.7915, + "epoch": 0.41, + "learning_rate": 1.846864362079387e-05, + "loss": 0.8306, "step": 892 }, { - "epoch": 0.46, - "learning_rate": 1.7984155286465103e-05, - "loss": 0.7864, + "epoch": 0.41, + "learning_rate": 1.8464717579483313e-05, + "loss": 0.8103, "step": 893 }, { - "epoch": 0.46, - "learning_rate": 1.7979139070016054e-05, - "loss": 0.7595, + "epoch": 0.41, + "learning_rate": 1.846078693029569e-05, + "loss": 0.8015, "step": 894 }, { - "epoch": 0.46, - "learning_rate": 1.7974117321567355e-05, - "loss": 0.8149, + "epoch": 0.41, + "learning_rate": 1.8456851675370694e-05, + "loss": 0.8059, "step": 895 }, { - "epoch": 0.46, - "learning_rate": 1.7969090044600618e-05, - "loss": 0.7683, + "epoch": 0.41, + "learning_rate": 1.845291181685054e-05, + "loss": 0.8169, "step": 896 }, { - "epoch": 0.46, - "learning_rate": 1.796405724260129e-05, - "loss": 0.7874, + "epoch": 0.41, + "learning_rate": 1.8448967356879933e-05, + "loss": 0.8064, "step": 897 }, { - "epoch": 0.46, - "learning_rate": 1.7959018919058654e-05, - "loss": 0.7507, + "epoch": 0.41, + "learning_rate": 1.844501829760609e-05, + "loss": 0.8105, "step": 898 }, { - "epoch": 0.46, - "learning_rate": 1.795397507746582e-05, - "loss": 0.7605, + "epoch": 0.41, + "learning_rate": 1.8441064641178737e-05, + "loss": 0.7388, "step": 899 }, { - "epoch": 0.46, - "learning_rate": 1.7948925721319728e-05, - "loss": 0.7852, + "epoch": 0.41, + "learning_rate": 1.8437106389750098e-05, + "loss": 0.8108, "step": 900 }, { - "epoch": 0.46, - "learning_rate": 1.7943870854121126e-05, - "loss": 0.8083, + "epoch": 0.41, + "learning_rate": 1.843314354547489e-05, + "loss": 0.7744, "step": 901 }, { - "epoch": 0.46, - "learning_rate": 1.7938810479374603e-05, - "loss": 0.8108, + "epoch": 0.41, + "learning_rate": 1.8429176110510343e-05, + "loss": 0.8628, "step": 902 }, { - "epoch": 0.46, - "learning_rate": 1.793374460058855e-05, - "loss": 0.8018, + "epoch": 0.41, + "learning_rate": 1.842520408701618e-05, + "loss": 0.829, "step": 903 }, { - "epoch": 0.46, - "learning_rate": 1.792867322127518e-05, - "loss": 0.7871, + "epoch": 0.41, + "learning_rate": 1.8421227477154625e-05, + "loss": 0.8057, "step": 904 }, { - "epoch": 0.47, - "learning_rate": 1.7923596344950524e-05, - "loss": 0.7825, + "epoch": 0.41, + "learning_rate": 1.8417246283090394e-05, + "loss": 0.7863, "step": 905 }, { - "epoch": 0.47, - "learning_rate": 1.7918513975134422e-05, - "loss": 0.7156, + "epoch": 0.41, + "learning_rate": 1.84132605069907e-05, + "loss": 0.8228, "step": 906 }, { - "epoch": 0.47, - "learning_rate": 1.7913426115350514e-05, - "loss": 0.8167, + "epoch": 0.41, + "learning_rate": 1.8409270151025254e-05, + "loss": 0.8096, "step": 907 }, { - "epoch": 0.47, - "learning_rate": 1.7908332769126255e-05, - "loss": 0.7473, + "epoch": 0.41, + "learning_rate": 1.8405275217366255e-05, + "loss": 0.8296, "step": 908 }, { - "epoch": 0.47, - "learning_rate": 1.7903233939992904e-05, - "loss": 0.7859, + "epoch": 0.41, + "learning_rate": 1.8401275708188395e-05, + "loss": 0.7759, "step": 909 }, { - "epoch": 0.47, - "learning_rate": 1.7898129631485522e-05, - "loss": 0.8215, + "epoch": 0.41, + "learning_rate": 1.8397271625668864e-05, + "loss": 0.8145, "step": 910 }, { - "epoch": 0.47, - "learning_rate": 1.789301984714296e-05, - "loss": 0.7917, + "epoch": 0.42, + "learning_rate": 1.8393262971987324e-05, + "loss": 0.8384, "step": 911 }, { - "epoch": 0.47, - "learning_rate": 1.7887904590507874e-05, - "loss": 0.8386, + "epoch": 0.42, + "learning_rate": 1.8389249749325946e-05, + "loss": 0.8359, "step": 912 }, { - "epoch": 0.47, - "learning_rate": 1.788278386512671e-05, - "loss": 0.8066, + "epoch": 0.42, + "learning_rate": 1.8385231959869377e-05, + "loss": 0.8203, "step": 913 }, { - "epoch": 0.47, - "learning_rate": 1.787765767454971e-05, - "loss": 0.7817, + "epoch": 0.42, + "learning_rate": 1.8381209605804754e-05, + "loss": 0.8394, "step": 914 }, { - "epoch": 0.47, - "learning_rate": 1.7872526022330902e-05, - "loss": 0.7505, + "epoch": 0.42, + "learning_rate": 1.8377182689321692e-05, + "loss": 0.7502, "step": 915 }, { - "epoch": 0.47, - "learning_rate": 1.78673889120281e-05, - "loss": 0.7753, + "epoch": 0.42, + "learning_rate": 1.8373151212612298e-05, + "loss": 0.8164, "step": 916 }, { - "epoch": 0.47, - "learning_rate": 1.78622463472029e-05, - "loss": 0.7771, + "epoch": 0.42, + "learning_rate": 1.8369115177871153e-05, + "loss": 0.801, "step": 917 }, { - "epoch": 0.47, - "learning_rate": 1.7857098331420685e-05, - "loss": 0.8201, + "epoch": 0.42, + "learning_rate": 1.8365074587295332e-05, + "loss": 0.8118, "step": 918 }, { - "epoch": 0.47, - "learning_rate": 1.7851944868250616e-05, - "loss": 0.8293, + "epoch": 0.42, + "learning_rate": 1.8361029443084377e-05, + "loss": 0.854, "step": 919 }, { - "epoch": 0.47, - "learning_rate": 1.784678596126563e-05, - "loss": 0.7996, + "epoch": 0.42, + "learning_rate": 1.835697974744031e-05, + "loss": 0.7369, "step": 920 }, { - "epoch": 0.47, - "learning_rate": 1.784162161404243e-05, - "loss": 0.8208, + "epoch": 0.42, + "learning_rate": 1.8352925502567646e-05, + "loss": 0.8547, "step": 921 }, { - "epoch": 0.47, - "learning_rate": 1.7836451830161508e-05, - "loss": 0.804, + "epoch": 0.42, + "learning_rate": 1.8348866710673355e-05, + "loss": 0.8403, "step": 922 }, { - "epoch": 0.47, - "learning_rate": 1.783127661320711e-05, - "loss": 0.8313, + "epoch": 0.42, + "learning_rate": 1.8344803373966895e-05, + "loss": 0.8218, "step": 923 }, { - "epoch": 0.47, - "learning_rate": 1.7826095966767256e-05, - "loss": 0.8271, + "epoch": 0.42, + "learning_rate": 1.8340735494660195e-05, + "loss": 0.7418, "step": 924 }, { - "epoch": 0.48, - "learning_rate": 1.782090989443373e-05, - "loss": 0.7971, + "epoch": 0.42, + "learning_rate": 1.8336663074967656e-05, + "loss": 0.7966, "step": 925 }, { - "epoch": 0.48, - "learning_rate": 1.7815718399802074e-05, - "loss": 0.7717, + "epoch": 0.42, + "learning_rate": 1.833258611710616e-05, + "loss": 0.7615, "step": 926 }, { - "epoch": 0.48, - "learning_rate": 1.7810521486471593e-05, - "loss": 0.802, + "epoch": 0.42, + "learning_rate": 1.832850462329504e-05, + "loss": 0.835, "step": 927 }, { - "epoch": 0.48, - "learning_rate": 1.7805319158045353e-05, - "loss": 0.8129, + "epoch": 0.42, + "learning_rate": 1.832441859575611e-05, + "loss": 0.7894, "step": 928 }, { - "epoch": 0.48, - "learning_rate": 1.7800111418130157e-05, - "loss": 0.7317, + "epoch": 0.42, + "learning_rate": 1.832032803671366e-05, + "loss": 0.7792, "step": 929 }, { - "epoch": 0.48, - "learning_rate": 1.7794898270336585e-05, - "loss": 0.7756, + "epoch": 0.42, + "learning_rate": 1.831623294839443e-05, + "loss": 0.7578, "step": 930 }, { - "epoch": 0.48, - "learning_rate": 1.7789679718278944e-05, - "loss": 0.8142, + "epoch": 0.42, + "learning_rate": 1.8312133333027633e-05, + "loss": 0.8689, "step": 931 }, { - "epoch": 0.48, - "learning_rate": 1.7784455765575302e-05, - "loss": 0.7485, + "epoch": 0.42, + "learning_rate": 1.8308029192844954e-05, + "loss": 0.8408, "step": 932 }, { - "epoch": 0.48, - "learning_rate": 1.7779226415847466e-05, - "loss": 0.7572, + "epoch": 0.43, + "learning_rate": 1.830392053008053e-05, + "loss": 0.7788, "step": 933 }, { - "epoch": 0.48, - "learning_rate": 1.777399167272098e-05, - "loss": 0.8096, + "epoch": 0.43, + "learning_rate": 1.8299807346970966e-05, + "loss": 0.853, "step": 934 }, { - "epoch": 0.48, - "learning_rate": 1.776875153982514e-05, - "loss": 0.7617, + "epoch": 0.43, + "learning_rate": 1.8295689645755322e-05, + "loss": 0.8228, "step": 935 }, { - "epoch": 0.48, - "learning_rate": 1.7763506020792968e-05, - "loss": 0.8857, + "epoch": 0.43, + "learning_rate": 1.8291567428675124e-05, + "loss": 0.8574, "step": 936 }, { - "epoch": 0.48, - "learning_rate": 1.775825511926122e-05, - "loss": 0.7593, + "epoch": 0.43, + "learning_rate": 1.828744069797435e-05, + "loss": 0.8354, "step": 937 }, { - "epoch": 0.48, - "learning_rate": 1.775299883887039e-05, - "loss": 0.7681, + "epoch": 0.43, + "learning_rate": 1.8283309455899444e-05, + "loss": 0.7888, "step": 938 }, { - "epoch": 0.48, - "learning_rate": 1.77477371832647e-05, - "loss": 0.8235, + "epoch": 0.43, + "learning_rate": 1.8279173704699298e-05, + "loss": 0.7579, "step": 939 }, { - "epoch": 0.48, - "learning_rate": 1.7742470156092095e-05, - "loss": 0.8403, + "epoch": 0.43, + "learning_rate": 1.8275033446625264e-05, + "loss": 0.8147, "step": 940 }, { - "epoch": 0.48, - "learning_rate": 1.7737197761004248e-05, - "loss": 0.8049, + "epoch": 0.43, + "learning_rate": 1.8270888683931134e-05, + "loss": 0.7751, "step": 941 }, { - "epoch": 0.48, - "learning_rate": 1.773192000165655e-05, - "loss": 0.8313, + "epoch": 0.43, + "learning_rate": 1.8266739418873174e-05, + "loss": 0.8042, "step": 942 }, { - "epoch": 0.48, - "learning_rate": 1.7726636881708114e-05, - "loss": 0.7712, + "epoch": 0.43, + "learning_rate": 1.8262585653710087e-05, + "loss": 0.7847, "step": 943 }, { - "epoch": 0.49, - "learning_rate": 1.772134840482177e-05, - "loss": 0.7661, + "epoch": 0.43, + "learning_rate": 1.8258427390703022e-05, + "loss": 0.7957, "step": 944 }, { - "epoch": 0.49, - "learning_rate": 1.7716054574664054e-05, - "loss": 0.7502, + "epoch": 0.43, + "learning_rate": 1.8254264632115586e-05, + "loss": 0.7311, "step": 945 }, { - "epoch": 0.49, - "learning_rate": 1.771075539490523e-05, - "loss": 0.8062, + "epoch": 0.43, + "learning_rate": 1.825009738021383e-05, + "loss": 0.8365, "step": 946 }, { - "epoch": 0.49, - "learning_rate": 1.770545086921925e-05, - "loss": 0.7922, + "epoch": 0.43, + "learning_rate": 1.8245925637266254e-05, + "loss": 0.8096, "step": 947 }, { - "epoch": 0.49, - "learning_rate": 1.770014100128379e-05, - "loss": 0.7632, + "epoch": 0.43, + "learning_rate": 1.8241749405543796e-05, + "loss": 0.7327, "step": 948 }, { - "epoch": 0.49, - "learning_rate": 1.769482579478022e-05, - "loss": 0.8069, + "epoch": 0.43, + "learning_rate": 1.8237568687319842e-05, + "loss": 0.79, "step": 949 }, { - "epoch": 0.49, - "learning_rate": 1.768950525339362e-05, - "loss": 0.8179, + "epoch": 0.43, + "learning_rate": 1.823338348487022e-05, + "loss": 0.7457, "step": 950 }, { - "epoch": 0.49, - "learning_rate": 1.7684179380812757e-05, - "loss": 0.8364, + "epoch": 0.43, + "learning_rate": 1.8229193800473192e-05, + "loss": 0.8259, "step": 951 }, { - "epoch": 0.49, - "learning_rate": 1.7678848180730108e-05, - "loss": 0.7798, + "epoch": 0.43, + "learning_rate": 1.8224999636409473e-05, + "loss": 0.7389, "step": 952 }, { - "epoch": 0.49, - "learning_rate": 1.7673511656841822e-05, - "loss": 0.791, + "epoch": 0.43, + "learning_rate": 1.822080099496221e-05, + "loss": 0.7419, "step": 953 }, { - "epoch": 0.49, - "learning_rate": 1.7668169812847768e-05, - "loss": 0.7957, + "epoch": 0.43, + "learning_rate": 1.8216597878416985e-05, + "loss": 0.8076, "step": 954 }, { - "epoch": 0.49, - "learning_rate": 1.766282265245147e-05, - "loss": 0.8123, + "epoch": 0.44, + "learning_rate": 1.8212390289061823e-05, + "loss": 0.7361, "step": 955 }, { - "epoch": 0.49, - "learning_rate": 1.7657470179360178e-05, - "loss": 0.8398, + "epoch": 0.44, + "learning_rate": 1.820817822918717e-05, + "loss": 0.7316, "step": 956 }, { - "epoch": 0.49, - "learning_rate": 1.765211239728479e-05, - "loss": 0.7786, + "epoch": 0.44, + "learning_rate": 1.820396170108592e-05, + "loss": 0.7737, "step": 957 }, { - "epoch": 0.49, - "learning_rate": 1.7646749309939898e-05, - "loss": 0.7883, + "epoch": 0.44, + "learning_rate": 1.8199740707053394e-05, + "loss": 0.7546, "step": 958 }, { - "epoch": 0.49, - "learning_rate": 1.764138092104378e-05, - "loss": 0.78, + "epoch": 0.44, + "learning_rate": 1.819551524938734e-05, + "loss": 0.8364, "step": 959 }, { - "epoch": 0.49, - "learning_rate": 1.7636007234318378e-05, - "loss": 0.7205, + "epoch": 0.44, + "learning_rate": 1.819128533038794e-05, + "loss": 0.7384, "step": 960 }, { - "epoch": 0.49, - "learning_rate": 1.7630628253489307e-05, - "loss": 0.8181, + "epoch": 0.44, + "learning_rate": 1.8187050952357815e-05, + "loss": 0.8438, "step": 961 }, { - "epoch": 0.49, - "learning_rate": 1.7625243982285867e-05, - "loss": 0.7761, + "epoch": 0.44, + "learning_rate": 1.818281211760199e-05, + "loss": 0.8726, "step": 962 }, { - "epoch": 0.49, - "learning_rate": 1.7619854424441005e-05, - "loss": 0.7954, + "epoch": 0.44, + "learning_rate": 1.8178568828427934e-05, + "loss": 0.793, "step": 963 }, { - "epoch": 0.5, - "learning_rate": 1.7614459583691346e-05, - "loss": 0.7988, + "epoch": 0.44, + "learning_rate": 1.8174321087145535e-05, + "loss": 0.7485, "step": 964 }, { - "epoch": 0.5, - "learning_rate": 1.7609059463777178e-05, - "loss": 0.8105, + "epoch": 0.44, + "learning_rate": 1.817006889606711e-05, + "loss": 0.7842, "step": 965 }, { - "epoch": 0.5, - "learning_rate": 1.7603654068442447e-05, - "loss": 0.772, + "epoch": 0.44, + "learning_rate": 1.8165812257507385e-05, + "loss": 0.8459, "step": 966 }, { - "epoch": 0.5, - "learning_rate": 1.7598243401434753e-05, - "loss": 0.8223, + "epoch": 0.44, + "learning_rate": 1.816155117378352e-05, + "loss": 0.8347, "step": 967 }, { - "epoch": 0.5, - "learning_rate": 1.7592827466505357e-05, - "loss": 0.6865, + "epoch": 0.44, + "learning_rate": 1.8157285647215092e-05, + "loss": 0.8391, "step": 968 }, { - "epoch": 0.5, - "learning_rate": 1.7587406267409166e-05, - "loss": 0.7793, + "epoch": 0.44, + "learning_rate": 1.815301568012409e-05, + "loss": 0.7991, "step": 969 }, { - "epoch": 0.5, - "learning_rate": 1.7581979807904743e-05, - "loss": 0.7715, + "epoch": 0.44, + "learning_rate": 1.814874127483493e-05, + "loss": 0.7161, "step": 970 }, { - "epoch": 0.5, - "learning_rate": 1.757654809175429e-05, - "loss": 0.7585, + "epoch": 0.44, + "learning_rate": 1.8144462433674433e-05, + "loss": 0.7588, "step": 971 }, { - "epoch": 0.5, - "learning_rate": 1.757111112272366e-05, - "loss": 0.8477, + "epoch": 0.44, + "learning_rate": 1.8140179158971847e-05, + "loss": 0.7747, "step": 972 }, { - "epoch": 0.5, - "learning_rate": 1.7565668904582357e-05, - "loss": 0.7791, + "epoch": 0.44, + "learning_rate": 1.8135891453058824e-05, + "loss": 0.8345, "step": 973 }, { - "epoch": 0.5, - "learning_rate": 1.75602214411035e-05, - "loss": 0.7451, + "epoch": 0.44, + "learning_rate": 1.8131599318269437e-05, + "loss": 0.7822, "step": 974 }, { - "epoch": 0.5, - "learning_rate": 1.7554768736063858e-05, - "loss": 0.7935, + "epoch": 0.44, + "learning_rate": 1.8127302756940155e-05, + "loss": 0.7542, "step": 975 }, { - "epoch": 0.5, - "learning_rate": 1.754931079324384e-05, - "loss": 0.8188, + "epoch": 0.44, + "learning_rate": 1.812300177140987e-05, + "loss": 0.7803, "step": 976 }, { - "epoch": 0.5, - "learning_rate": 1.754384761642748e-05, - "loss": 0.8022, + "epoch": 0.45, + "learning_rate": 1.8118696364019882e-05, + "loss": 0.8164, "step": 977 }, { - "epoch": 0.5, - "learning_rate": 1.7538379209402442e-05, - "loss": 0.8562, + "epoch": 0.45, + "learning_rate": 1.811438653711389e-05, + "loss": 0.7561, "step": 978 }, { - "epoch": 0.5, - "learning_rate": 1.7532905575960012e-05, - "loss": 0.8091, + "epoch": 0.45, + "learning_rate": 1.8110072293038005e-05, + "loss": 0.8757, "step": 979 }, { - "epoch": 0.5, - "learning_rate": 1.7527426719895106e-05, - "loss": 0.7983, + "epoch": 0.45, + "learning_rate": 1.8105753634140744e-05, + "loss": 0.8577, "step": 980 }, { - "epoch": 0.5, - "learning_rate": 1.752194264500626e-05, - "loss": 0.7644, + "epoch": 0.45, + "learning_rate": 1.8101430562773018e-05, + "loss": 0.8337, "step": 981 }, { - "epoch": 0.5, - "learning_rate": 1.7516453355095614e-05, - "loss": 0.8188, + "epoch": 0.45, + "learning_rate": 1.809710308128815e-05, + "loss": 0.7656, "step": 982 }, { - "epoch": 0.51, - "learning_rate": 1.7510958853968952e-05, - "loss": 0.7786, + "epoch": 0.45, + "learning_rate": 1.8092771192041856e-05, + "loss": 0.7725, "step": 983 }, { - "epoch": 0.51, - "learning_rate": 1.7505459145435643e-05, - "loss": 0.8511, + "epoch": 0.45, + "learning_rate": 1.808843489739226e-05, + "loss": 0.7616, "step": 984 }, { - "epoch": 0.51, - "learning_rate": 1.7499954233308686e-05, - "loss": 0.8071, + "epoch": 0.45, + "learning_rate": 1.8084094199699878e-05, + "loss": 0.7747, "step": 985 }, { - "epoch": 0.51, - "learning_rate": 1.7494444121404673e-05, - "loss": 0.8162, + "epoch": 0.45, + "learning_rate": 1.807974910132762e-05, + "loss": 0.7839, "step": 986 }, { - "epoch": 0.51, - "learning_rate": 1.7488928813543814e-05, - "loss": 0.7751, + "epoch": 0.45, + "learning_rate": 1.8075399604640802e-05, + "loss": 0.7876, "step": 987 }, { - "epoch": 0.51, - "learning_rate": 1.7483408313549904e-05, - "loss": 0.748, + "epoch": 0.45, + "learning_rate": 1.8071045712007124e-05, + "loss": 0.8203, "step": 988 }, { - "epoch": 0.51, - "learning_rate": 1.7477882625250365e-05, - "loss": 0.7712, + "epoch": 0.45, + "learning_rate": 1.806668742579669e-05, + "loss": 0.786, "step": 989 }, { - "epoch": 0.51, - "learning_rate": 1.7472351752476188e-05, - "loss": 0.8003, + "epoch": 0.45, + "learning_rate": 1.8062324748381975e-05, + "loss": 0.7766, "step": 990 }, { - "epoch": 0.51, - "learning_rate": 1.7466815699061978e-05, - "loss": 0.7847, + "epoch": 0.45, + "learning_rate": 1.805795768213787e-05, + "loss": 0.799, "step": 991 }, { - "epoch": 0.51, - "learning_rate": 1.7461274468845917e-05, - "loss": 0.7585, + "epoch": 0.45, + "learning_rate": 1.805358622944164e-05, + "loss": 0.7888, "step": 992 }, { - "epoch": 0.51, - "learning_rate": 1.7455728065669786e-05, - "loss": 0.7349, + "epoch": 0.45, + "learning_rate": 1.804921039267294e-05, + "loss": 0.8511, "step": 993 }, { - "epoch": 0.51, - "learning_rate": 1.7450176493378954e-05, - "loss": 0.7795, + "epoch": 0.45, + "learning_rate": 1.804483017421381e-05, + "loss": 0.8116, "step": 994 }, { - "epoch": 0.51, - "learning_rate": 1.7444619755822364e-05, - "loss": 0.7915, + "epoch": 0.45, + "learning_rate": 1.8040445576448683e-05, + "loss": 0.8008, "step": 995 }, { - "epoch": 0.51, - "learning_rate": 1.7439057856852545e-05, - "loss": 0.7915, + "epoch": 0.45, + "learning_rate": 1.803605660176437e-05, + "loss": 0.8171, "step": 996 }, { - "epoch": 0.51, - "learning_rate": 1.7433490800325614e-05, - "loss": 0.8372, + "epoch": 0.45, + "learning_rate": 1.8031663252550064e-05, + "loss": 0.7905, "step": 997 }, { - "epoch": 0.51, - "learning_rate": 1.7427918590101246e-05, - "loss": 0.7878, + "epoch": 0.45, + "learning_rate": 1.802726553119734e-05, + "loss": 0.8333, "step": 998 }, { - "epoch": 0.51, - "learning_rate": 1.74223412300427e-05, - "loss": 0.7827, + "epoch": 0.46, + "learning_rate": 1.8022863440100154e-05, + "loss": 0.7893, "step": 999 }, { - "epoch": 0.51, - "learning_rate": 1.7416758724016808e-05, - "loss": 0.7444, + "epoch": 0.46, + "learning_rate": 1.8018456981654838e-05, + "loss": 0.8254, "step": 1000 }, { - "epoch": 0.51, - "learning_rate": 1.7411171075893957e-05, - "loss": 0.7688, + "epoch": 0.46, + "learning_rate": 1.8014046158260113e-05, + "loss": 0.8206, "step": 1001 }, { - "epoch": 0.52, - "learning_rate": 1.7405578289548114e-05, - "loss": 0.7869, + "epoch": 0.46, + "learning_rate": 1.800963097231706e-05, + "loss": 0.7795, "step": 1002 }, { - "epoch": 0.52, - "learning_rate": 1.73999803688568e-05, - "loss": 0.7849, + "epoch": 0.46, + "learning_rate": 1.800521142622914e-05, + "loss": 0.8494, "step": 1003 }, { - "epoch": 0.52, - "learning_rate": 1.7394377317701097e-05, - "loss": 0.7866, + "epoch": 0.46, + "learning_rate": 1.8000787522402193e-05, + "loss": 0.8394, "step": 1004 }, { - "epoch": 0.52, - "learning_rate": 1.7388769139965642e-05, - "loss": 0.7661, + "epoch": 0.46, + "learning_rate": 1.7996359263244427e-05, + "loss": 0.8567, "step": 1005 }, { - "epoch": 0.52, - "learning_rate": 1.7383155839538634e-05, - "loss": 0.7834, + "epoch": 0.46, + "learning_rate": 1.799192665116642e-05, + "loss": 0.8547, "step": 1006 }, { - "epoch": 0.52, - "learning_rate": 1.737753742031181e-05, - "loss": 0.739, + "epoch": 0.46, + "learning_rate": 1.7987489688581123e-05, + "loss": 0.825, "step": 1007 }, { - "epoch": 0.52, - "learning_rate": 1.7371913886180473e-05, - "loss": 0.7664, + "epoch": 0.46, + "learning_rate": 1.7983048377903856e-05, + "loss": 0.7876, "step": 1008 }, { - "epoch": 0.52, - "learning_rate": 1.7366285241043458e-05, - "loss": 0.8162, + "epoch": 0.46, + "learning_rate": 1.7978602721552294e-05, + "loss": 0.7937, "step": 1009 }, { - "epoch": 0.52, - "learning_rate": 1.7360651488803148e-05, - "loss": 0.7957, + "epoch": 0.46, + "learning_rate": 1.7974152721946493e-05, + "loss": 0.7988, "step": 1010 }, { - "epoch": 0.52, - "learning_rate": 1.735501263336547e-05, - "loss": 0.7913, + "epoch": 0.46, + "learning_rate": 1.796969838150887e-05, + "loss": 0.7979, "step": 1011 }, { - "epoch": 0.52, - "learning_rate": 1.734936867863989e-05, - "loss": 0.7732, + "epoch": 0.46, + "learning_rate": 1.7965239702664193e-05, + "loss": 0.8101, "step": 1012 }, { - "epoch": 0.52, - "learning_rate": 1.7343719628539396e-05, - "loss": 0.7732, + "epoch": 0.46, + "learning_rate": 1.796077668783961e-05, + "loss": 0.8022, "step": 1013 }, { - "epoch": 0.52, - "learning_rate": 1.7338065486980533e-05, - "loss": 0.7957, + "epoch": 0.46, + "learning_rate": 1.7956309339464616e-05, + "loss": 0.7332, "step": 1014 }, { - "epoch": 0.52, - "learning_rate": 1.7332406257883345e-05, - "loss": 0.7854, + "epoch": 0.46, + "learning_rate": 1.795183765997107e-05, + "loss": 0.7922, "step": 1015 }, { - "epoch": 0.52, - "learning_rate": 1.7326741945171435e-05, - "loss": 0.8066, + "epoch": 0.46, + "learning_rate": 1.794736165179318e-05, + "loss": 0.6985, "step": 1016 }, { - "epoch": 0.52, - "learning_rate": 1.732107255277191e-05, - "loss": 0.8169, + "epoch": 0.46, + "learning_rate": 1.7942881317367537e-05, + "loss": 0.8008, "step": 1017 }, { - "epoch": 0.52, - "learning_rate": 1.7315398084615395e-05, - "loss": 0.8108, + "epoch": 0.46, + "learning_rate": 1.7938396659133047e-05, + "loss": 0.804, "step": 1018 }, { - "epoch": 0.52, - "learning_rate": 1.7309718544636057e-05, - "loss": 0.7856, + "epoch": 0.46, + "learning_rate": 1.7933907679531003e-05, + "loss": 0.812, "step": 1019 }, { - "epoch": 0.52, - "learning_rate": 1.7304033936771557e-05, - "loss": 0.8025, + "epoch": 0.46, + "learning_rate": 1.792941438100504e-05, + "loss": 0.7892, "step": 1020 }, { - "epoch": 0.52, - "learning_rate": 1.7298344264963084e-05, - "loss": 0.7485, + "epoch": 0.47, + "learning_rate": 1.7924916766001133e-05, + "loss": 0.811, "step": 1021 }, { - "epoch": 0.53, - "learning_rate": 1.729264953315533e-05, - "loss": 0.7129, + "epoch": 0.47, + "learning_rate": 1.7920414836967625e-05, + "loss": 0.8046, "step": 1022 }, { - "epoch": 0.53, - "learning_rate": 1.7286949745296494e-05, - "loss": 0.7683, + "epoch": 0.47, + "learning_rate": 1.791590859635519e-05, + "loss": 0.8193, "step": 1023 }, { - "epoch": 0.53, - "learning_rate": 1.7281244905338284e-05, - "loss": 0.8159, + "epoch": 0.47, + "learning_rate": 1.791139804661687e-05, + "loss": 0.7705, "step": 1024 }, { - "epoch": 0.53, - "learning_rate": 1.7275535017235918e-05, - "loss": 0.8293, + "epoch": 0.47, + "learning_rate": 1.7906883190208028e-05, + "loss": 0.8169, "step": 1025 }, { - "epoch": 0.53, - "learning_rate": 1.7269820084948094e-05, - "loss": 0.8477, + "epoch": 0.47, + "learning_rate": 1.7902364029586388e-05, + "loss": 0.7751, "step": 1026 }, { - "epoch": 0.53, - "learning_rate": 1.726410011243703e-05, - "loss": 0.76, + "epoch": 0.47, + "learning_rate": 1.7897840567212018e-05, + "loss": 0.7681, "step": 1027 }, { - "epoch": 0.53, - "learning_rate": 1.7258375103668422e-05, - "loss": 0.8118, + "epoch": 0.47, + "learning_rate": 1.7893312805547313e-05, + "loss": 0.6829, "step": 1028 }, { - "epoch": 0.53, - "learning_rate": 1.7252645062611467e-05, - "loss": 0.7708, + "epoch": 0.47, + "learning_rate": 1.788878074705702e-05, + "loss": 0.8301, "step": 1029 }, { - "epoch": 0.53, - "learning_rate": 1.7246909993238844e-05, - "loss": 0.7852, + "epoch": 0.47, + "learning_rate": 1.7884244394208233e-05, + "loss": 0.8159, "step": 1030 }, { - "epoch": 0.53, - "learning_rate": 1.7241169899526722e-05, - "loss": 0.8152, + "epoch": 0.47, + "learning_rate": 1.7879703749470363e-05, + "loss": 0.8525, "step": 1031 }, { - "epoch": 0.53, - "learning_rate": 1.7235424785454757e-05, - "loss": 0.7463, + "epoch": 0.47, + "learning_rate": 1.787515881531517e-05, + "loss": 0.8005, "step": 1032 }, { - "epoch": 0.53, - "learning_rate": 1.7229674655006073e-05, - "loss": 0.8782, + "epoch": 0.47, + "learning_rate": 1.787060959421675e-05, + "loss": 0.8115, "step": 1033 }, { - "epoch": 0.53, - "learning_rate": 1.7223919512167292e-05, - "loss": 0.8157, + "epoch": 0.47, + "learning_rate": 1.786605608865153e-05, + "loss": 0.7362, "step": 1034 }, { - "epoch": 0.53, - "learning_rate": 1.7218159360928486e-05, - "loss": 0.8044, + "epoch": 0.47, + "learning_rate": 1.786149830109826e-05, + "loss": 0.8206, "step": 1035 }, { - "epoch": 0.53, - "learning_rate": 1.7212394205283227e-05, - "loss": 0.8008, + "epoch": 0.47, + "learning_rate": 1.785693623403804e-05, + "loss": 0.8069, "step": 1036 }, { - "epoch": 0.53, - "learning_rate": 1.7206624049228533e-05, - "loss": 0.8511, + "epoch": 0.47, + "learning_rate": 1.7852369889954286e-05, + "loss": 0.7781, "step": 1037 }, { - "epoch": 0.53, - "learning_rate": 1.7200848896764902e-05, - "loss": 0.8267, + "epoch": 0.47, + "learning_rate": 1.7847799271332747e-05, + "loss": 0.8174, "step": 1038 }, { - "epoch": 0.53, - "learning_rate": 1.7195068751896294e-05, - "loss": 0.7634, + "epoch": 0.47, + "learning_rate": 1.7843224380661493e-05, + "loss": 0.8127, "step": 1039 }, { - "epoch": 0.53, - "learning_rate": 1.7189283618630125e-05, - "loss": 0.8092, + "epoch": 0.47, + "learning_rate": 1.7838645220430928e-05, + "loss": 0.7871, "step": 1040 }, { - "epoch": 0.54, - "learning_rate": 1.7183493500977277e-05, - "loss": 0.7974, + "epoch": 0.47, + "learning_rate": 1.7834061793133773e-05, + "loss": 0.7834, "step": 1041 }, { - "epoch": 0.54, - "learning_rate": 1.717769840295208e-05, - "loss": 0.7583, + "epoch": 0.47, + "learning_rate": 1.7829474101265084e-05, + "loss": 0.7737, "step": 1042 }, { - "epoch": 0.54, - "learning_rate": 1.7171898328572325e-05, - "loss": 0.8818, + "epoch": 0.48, + "learning_rate": 1.7824882147322218e-05, + "loss": 0.7666, "step": 1043 }, { - "epoch": 0.54, - "learning_rate": 1.7166093281859245e-05, - "loss": 0.8096, + "epoch": 0.48, + "learning_rate": 1.782028593380487e-05, + "loss": 0.7859, "step": 1044 }, { - "epoch": 0.54, - "learning_rate": 1.7160283266837526e-05, - "loss": 0.7791, + "epoch": 0.48, + "learning_rate": 1.781568546321505e-05, + "loss": 0.7517, "step": 1045 }, { - "epoch": 0.54, - "learning_rate": 1.71544682875353e-05, - "loss": 0.8264, + "epoch": 0.48, + "learning_rate": 1.7811080738057075e-05, + "loss": 0.8403, "step": 1046 }, { - "epoch": 0.54, - "learning_rate": 1.7148648347984132e-05, - "loss": 0.7839, + "epoch": 0.48, + "learning_rate": 1.7806471760837594e-05, + "loss": 0.8167, "step": 1047 }, { - "epoch": 0.54, - "learning_rate": 1.7142823452219036e-05, - "loss": 0.8262, + "epoch": 0.48, + "learning_rate": 1.7801858534065557e-05, + "loss": 0.7574, "step": 1048 }, { - "epoch": 0.54, - "learning_rate": 1.7136993604278458e-05, - "loss": 0.7739, + "epoch": 0.48, + "learning_rate": 1.7797241060252234e-05, + "loss": 0.8009, "step": 1049 }, { - "epoch": 0.54, - "learning_rate": 1.7131158808204277e-05, - "loss": 0.8201, + "epoch": 0.48, + "learning_rate": 1.7792619341911207e-05, + "loss": 0.8022, "step": 1050 }, { - "epoch": 0.54, - "learning_rate": 1.7125319068041796e-05, - "loss": 0.833, + "epoch": 0.48, + "learning_rate": 1.778799338155837e-05, + "loss": 0.7913, "step": 1051 }, { - "epoch": 0.54, - "learning_rate": 1.7119474387839764e-05, - "loss": 0.7805, + "epoch": 0.48, + "learning_rate": 1.7783363181711917e-05, + "loss": 0.7524, "step": 1052 }, { - "epoch": 0.54, - "learning_rate": 1.7113624771650333e-05, - "loss": 0.7773, + "epoch": 0.48, + "learning_rate": 1.777872874489236e-05, + "loss": 0.7915, "step": 1053 }, { - "epoch": 0.54, - "learning_rate": 1.7107770223529095e-05, - "loss": 0.7957, + "epoch": 0.48, + "learning_rate": 1.7774090073622514e-05, + "loss": 0.7657, "step": 1054 }, { - "epoch": 0.54, - "learning_rate": 1.7101910747535054e-05, - "loss": 0.7542, + "epoch": 0.48, + "learning_rate": 1.77694471704275e-05, + "loss": 0.7754, "step": 1055 }, { - "epoch": 0.54, - "learning_rate": 1.7096046347730626e-05, - "loss": 0.7087, + "epoch": 0.48, + "learning_rate": 1.7764800037834742e-05, + "loss": 0.7517, "step": 1056 }, { - "epoch": 0.54, - "learning_rate": 1.7090177028181648e-05, - "loss": 0.8005, + "epoch": 0.48, + "learning_rate": 1.7760148678373964e-05, + "loss": 0.8024, "step": 1057 }, { - "epoch": 0.54, - "learning_rate": 1.7084302792957365e-05, - "loss": 0.7303, + "epoch": 0.48, + "learning_rate": 1.775549309457719e-05, + "loss": 0.7556, "step": 1058 }, { - "epoch": 0.54, - "learning_rate": 1.707842364613043e-05, - "loss": 0.7722, + "epoch": 0.48, + "learning_rate": 1.7750833288978754e-05, + "loss": 0.8419, "step": 1059 }, { - "epoch": 0.54, - "learning_rate": 1.7072539591776902e-05, - "loss": 0.7666, + "epoch": 0.48, + "learning_rate": 1.7746169264115273e-05, + "loss": 0.7365, "step": 1060 }, { - "epoch": 0.55, - "learning_rate": 1.7066650633976243e-05, - "loss": 0.7676, + "epoch": 0.48, + "learning_rate": 1.774150102252567e-05, + "loss": 0.7405, "step": 1061 }, { - "epoch": 0.55, - "learning_rate": 1.706075677681131e-05, - "loss": 0.7842, + "epoch": 0.48, + "learning_rate": 1.7736828566751167e-05, + "loss": 0.8113, "step": 1062 }, { - "epoch": 0.55, - "learning_rate": 1.7054858024368365e-05, - "loss": 0.7681, + "epoch": 0.48, + "learning_rate": 1.773215189933527e-05, + "loss": 0.8086, "step": 1063 }, { - "epoch": 0.55, - "learning_rate": 1.7048954380737057e-05, - "loss": 0.7883, + "epoch": 0.48, + "learning_rate": 1.7727471022823787e-05, + "loss": 0.7667, "step": 1064 }, { - "epoch": 0.55, - "learning_rate": 1.704304585001043e-05, - "loss": 0.7524, + "epoch": 0.49, + "learning_rate": 1.7722785939764805e-05, + "loss": 0.7876, "step": 1065 }, { - "epoch": 0.55, - "learning_rate": 1.703713243628491e-05, - "loss": 0.8105, + "epoch": 0.49, + "learning_rate": 1.771809665270872e-05, + "loss": 0.7524, "step": 1066 }, { - "epoch": 0.55, - "learning_rate": 1.7031214143660317e-05, - "loss": 0.7954, + "epoch": 0.49, + "learning_rate": 1.7713403164208193e-05, + "loss": 0.8296, "step": 1067 }, { - "epoch": 0.55, - "learning_rate": 1.702529097623985e-05, - "loss": 0.7869, + "epoch": 0.49, + "learning_rate": 1.7708705476818196e-05, + "loss": 0.8462, "step": 1068 }, { - "epoch": 0.55, - "learning_rate": 1.7019362938130085e-05, - "loss": 0.7786, + "epoch": 0.49, + "learning_rate": 1.770400359309597e-05, + "loss": 0.7991, "step": 1069 }, { - "epoch": 0.55, - "learning_rate": 1.701343003344098e-05, - "loss": 0.7554, - "step": 1070 + "epoch": 0.49, + "learning_rate": 1.769929751560104e-05, + "loss": 0.8103, + "step": 1070 }, { - "epoch": 0.55, - "learning_rate": 1.700749226628586e-05, - "loss": 0.7634, + "epoch": 0.49, + "learning_rate": 1.7694587246895226e-05, + "loss": 0.8015, "step": 1071 }, { - "epoch": 0.55, - "learning_rate": 1.7001549640781435e-05, - "loss": 0.7786, + "epoch": 0.49, + "learning_rate": 1.768987278954262e-05, + "loss": 0.7257, "step": 1072 }, { - "epoch": 0.55, - "learning_rate": 1.6995602161047763e-05, - "loss": 0.7642, + "epoch": 0.49, + "learning_rate": 1.76851541461096e-05, + "loss": 0.7552, "step": 1073 }, { - "epoch": 0.55, - "learning_rate": 1.6989649831208286e-05, - "loss": 0.7654, + "epoch": 0.49, + "learning_rate": 1.7680431319164822e-05, + "loss": 0.7717, "step": 1074 }, { - "epoch": 0.55, - "learning_rate": 1.6983692655389794e-05, - "loss": 0.8293, + "epoch": 0.49, + "learning_rate": 1.7675704311279213e-05, + "loss": 0.8081, "step": 1075 }, { - "epoch": 0.55, - "learning_rate": 1.6977730637722446e-05, - "loss": 0.7871, + "epoch": 0.49, + "learning_rate": 1.7670973125025973e-05, + "loss": 0.741, "step": 1076 }, { - "epoch": 0.55, - "learning_rate": 1.697176378233976e-05, - "loss": 0.7625, + "epoch": 0.49, + "learning_rate": 1.76662377629806e-05, + "loss": 0.7947, "step": 1077 }, { - "epoch": 0.55, - "learning_rate": 1.69657920933786e-05, - "loss": 0.811, + "epoch": 0.49, + "learning_rate": 1.7661498227720835e-05, + "loss": 0.7974, "step": 1078 }, { - "epoch": 0.55, - "learning_rate": 1.6959815574979183e-05, - "loss": 0.7446, + "epoch": 0.49, + "learning_rate": 1.765675452182671e-05, + "loss": 0.7344, "step": 1079 }, { - "epoch": 0.56, - "learning_rate": 1.695383423128508e-05, - "loss": 0.7937, + "epoch": 0.49, + "learning_rate": 1.765200664788052e-05, + "loss": 0.8337, "step": 1080 }, { - "epoch": 0.56, - "learning_rate": 1.6947848066443204e-05, - "loss": 0.7539, + "epoch": 0.49, + "learning_rate": 1.7647254608466833e-05, + "loss": 0.8418, "step": 1081 }, { - "epoch": 0.56, - "learning_rate": 1.6941857084603806e-05, - "loss": 0.8328, + "epoch": 0.49, + "learning_rate": 1.764249840617248e-05, + "loss": 0.7318, "step": 1082 }, { - "epoch": 0.56, - "learning_rate": 1.693586128992048e-05, - "loss": 0.7625, + "epoch": 0.49, + "learning_rate": 1.7637738043586563e-05, + "loss": 0.76, "step": 1083 }, { - "epoch": 0.56, - "learning_rate": 1.692986068655016e-05, - "loss": 0.7705, + "epoch": 0.49, + "learning_rate": 1.7632973523300446e-05, + "loss": 0.7439, "step": 1084 }, { - "epoch": 0.56, - "learning_rate": 1.6923855278653114e-05, - "loss": 0.7207, + "epoch": 0.49, + "learning_rate": 1.7628204847907752e-05, + "loss": 0.804, "step": 1085 }, { - "epoch": 0.56, - "learning_rate": 1.6917845070392936e-05, - "loss": 0.7632, + "epoch": 0.49, + "learning_rate": 1.7623432020004376e-05, + "loss": 0.7031, "step": 1086 }, { - "epoch": 0.56, - "learning_rate": 1.6911830065936546e-05, - "loss": 0.7876, + "epoch": 0.5, + "learning_rate": 1.7618655042188466e-05, + "loss": 0.7975, "step": 1087 }, { - "epoch": 0.56, - "learning_rate": 1.6905810269454202e-05, - "loss": 0.7776, + "epoch": 0.5, + "learning_rate": 1.7613873917060428e-05, + "loss": 0.8296, "step": 1088 }, { - "epoch": 0.56, - "learning_rate": 1.6899785685119468e-05, - "loss": 0.8108, + "epoch": 0.5, + "learning_rate": 1.760908864722293e-05, + "loss": 0.7944, "step": 1089 }, { - "epoch": 0.56, - "learning_rate": 1.689375631710924e-05, - "loss": 0.7737, + "epoch": 0.5, + "learning_rate": 1.7604299235280898e-05, + "loss": 0.7427, "step": 1090 }, { - "epoch": 0.56, - "learning_rate": 1.6887722169603732e-05, - "loss": 0.8271, + "epoch": 0.5, + "learning_rate": 1.759950568384151e-05, + "loss": 0.783, "step": 1091 }, { - "epoch": 0.56, - "learning_rate": 1.6881683246786452e-05, - "loss": 0.7554, + "epoch": 0.5, + "learning_rate": 1.759470799551419e-05, + "loss": 0.791, "step": 1092 }, { - "epoch": 0.56, - "learning_rate": 1.687563955284424e-05, - "loss": 0.7157, + "epoch": 0.5, + "learning_rate": 1.758990617291062e-05, + "loss": 0.7526, "step": 1093 }, { - "epoch": 0.56, - "learning_rate": 1.686959109196724e-05, - "loss": 0.7698, + "epoch": 0.5, + "learning_rate": 1.7585100218644746e-05, + "loss": 0.8171, "step": 1094 }, { - "epoch": 0.56, - "learning_rate": 1.686353786834889e-05, - "loss": 0.7712, + "epoch": 0.5, + "learning_rate": 1.7580290135332742e-05, + "loss": 0.7781, "step": 1095 }, { - "epoch": 0.56, - "learning_rate": 1.6857479886185942e-05, - "loss": 0.7295, + "epoch": 0.5, + "learning_rate": 1.7575475925593037e-05, + "loss": 0.8352, "step": 1096 }, { - "epoch": 0.56, - "learning_rate": 1.6851417149678442e-05, - "loss": 0.8081, + "epoch": 0.5, + "learning_rate": 1.757065759204631e-05, + "loss": 0.8164, "step": 1097 }, { - "epoch": 0.56, - "learning_rate": 1.6845349663029734e-05, - "loss": 0.833, + "epoch": 0.5, + "learning_rate": 1.7565835137315482e-05, + "loss": 0.803, "step": 1098 }, { - "epoch": 0.56, - "learning_rate": 1.6839277430446447e-05, - "loss": 0.7598, + "epoch": 0.5, + "learning_rate": 1.7561008564025716e-05, + "loss": 0.7722, "step": 1099 }, { - "epoch": 0.57, - "learning_rate": 1.6833200456138518e-05, - "loss": 0.79, + "epoch": 0.5, + "learning_rate": 1.7556177874804424e-05, + "loss": 0.8569, "step": 1100 }, { - "epoch": 0.57, - "learning_rate": 1.6827118744319153e-05, - "loss": 0.7671, + "epoch": 0.5, + "learning_rate": 1.755134307228125e-05, + "loss": 0.7869, "step": 1101 }, { - "epoch": 0.57, - "learning_rate": 1.6821032299204856e-05, - "loss": 0.7852, + "epoch": 0.5, + "learning_rate": 1.7546504159088074e-05, + "loss": 0.7344, "step": 1102 }, { - "epoch": 0.57, - "learning_rate": 1.6814941125015398e-05, - "loss": 0.7485, + "epoch": 0.5, + "learning_rate": 1.7541661137859032e-05, + "loss": 0.7979, "step": 1103 }, { - "epoch": 0.57, - "learning_rate": 1.680884522597385e-05, - "loss": 0.7585, + "epoch": 0.5, + "learning_rate": 1.7536814011230477e-05, + "loss": 0.7998, "step": 1104 }, { - "epoch": 0.57, - "learning_rate": 1.6802744606306537e-05, - "loss": 0.7886, + "epoch": 0.5, + "learning_rate": 1.753196278184101e-05, + "loss": 0.7816, "step": 1105 }, { - "epoch": 0.57, - "learning_rate": 1.6796639270243068e-05, - "loss": 0.8164, + "epoch": 0.5, + "learning_rate": 1.752710745233145e-05, + "loss": 0.8179, "step": 1106 }, { - "epoch": 0.57, - "learning_rate": 1.6790529222016328e-05, - "loss": 0.7617, + "epoch": 0.5, + "learning_rate": 1.7522248025344867e-05, + "loss": 0.726, "step": 1107 }, { - "epoch": 0.57, - "learning_rate": 1.6784414465862452e-05, - "loss": 0.804, + "epoch": 0.5, + "learning_rate": 1.7517384503526547e-05, + "loss": 0.8645, "step": 1108 }, { - "epoch": 0.57, - "learning_rate": 1.677829500602085e-05, - "loss": 0.7913, + "epoch": 0.51, + "learning_rate": 1.7512516889524012e-05, + "loss": 0.7994, "step": 1109 }, { - "epoch": 0.57, - "learning_rate": 1.67721708467342e-05, - "loss": 0.7766, + "epoch": 0.51, + "learning_rate": 1.750764518598701e-05, + "loss": 0.7294, "step": 1110 }, { - "epoch": 0.57, - "learning_rate": 1.6766041992248415e-05, - "loss": 0.7783, + "epoch": 0.51, + "learning_rate": 1.7502769395567513e-05, + "loss": 0.7671, "step": 1111 }, { - "epoch": 0.57, - "learning_rate": 1.6759908446812692e-05, - "loss": 0.7917, + "epoch": 0.51, + "learning_rate": 1.7497889520919724e-05, + "loss": 0.6997, "step": 1112 }, { - "epoch": 0.57, - "learning_rate": 1.6753770214679457e-05, - "loss": 0.7354, + "epoch": 0.51, + "learning_rate": 1.749300556470006e-05, + "loss": 0.7581, "step": 1113 }, { - "epoch": 0.57, - "learning_rate": 1.67476273001044e-05, - "loss": 0.7722, + "epoch": 0.51, + "learning_rate": 1.748811752956717e-05, + "loss": 0.8049, "step": 1114 }, { - "epoch": 0.57, - "learning_rate": 1.6741479707346445e-05, - "loss": 0.8137, + "epoch": 0.51, + "learning_rate": 1.748322541818191e-05, + "loss": 0.6864, "step": 1115 }, { - "epoch": 0.57, - "learning_rate": 1.6735327440667775e-05, - "loss": 0.7942, + "epoch": 0.51, + "learning_rate": 1.7478329233207375e-05, + "loss": 0.8082, "step": 1116 }, { - "epoch": 0.57, - "learning_rate": 1.67291705043338e-05, - "loss": 0.7673, + "epoch": 0.51, + "learning_rate": 1.747342897730886e-05, + "loss": 0.8137, "step": 1117 }, { - "epoch": 0.57, - "learning_rate": 1.672300890261317e-05, - "loss": 0.8015, + "epoch": 0.51, + "learning_rate": 1.7468524653153878e-05, + "loss": 0.78, "step": 1118 }, { - "epoch": 0.58, - "learning_rate": 1.6716842639777775e-05, - "loss": 0.7915, + "epoch": 0.51, + "learning_rate": 1.7463616263412163e-05, + "loss": 0.7394, "step": 1119 }, { - "epoch": 0.58, - "learning_rate": 1.6710671720102732e-05, - "loss": 0.7957, + "epoch": 0.51, + "learning_rate": 1.7458703810755665e-05, + "loss": 0.8552, "step": 1120 }, { - "epoch": 0.58, - "learning_rate": 1.670449614786639e-05, - "loss": 0.813, + "epoch": 0.51, + "learning_rate": 1.7453787297858533e-05, + "loss": 0.7917, "step": 1121 }, { - "epoch": 0.58, - "learning_rate": 1.669831592735032e-05, - "loss": 0.79, + "epoch": 0.51, + "learning_rate": 1.7448866727397135e-05, + "loss": 0.7605, "step": 1122 }, { - "epoch": 0.58, - "learning_rate": 1.6692131062839315e-05, - "loss": 0.7275, + "epoch": 0.51, + "learning_rate": 1.7443942102050047e-05, + "loss": 0.7728, "step": 1123 }, { - "epoch": 0.58, - "learning_rate": 1.6685941558621398e-05, - "loss": 0.7646, + "epoch": 0.51, + "learning_rate": 1.743901342449806e-05, + "loss": 0.7825, "step": 1124 }, { - "epoch": 0.58, - "learning_rate": 1.667974741898779e-05, - "loss": 0.7516, + "epoch": 0.51, + "learning_rate": 1.743408069742415e-05, + "loss": 0.7561, "step": 1125 }, { - "epoch": 0.58, - "learning_rate": 1.6673548648232946e-05, - "loss": 0.7871, + "epoch": 0.51, + "learning_rate": 1.7429143923513514e-05, + "loss": 0.782, "step": 1126 }, { - "epoch": 0.58, - "learning_rate": 1.6667345250654517e-05, - "loss": 0.7954, + "epoch": 0.51, + "learning_rate": 1.742420310545355e-05, + "loss": 0.8181, "step": 1127 }, { - "epoch": 0.58, - "learning_rate": 1.6661137230553366e-05, - "loss": 0.771, + "epoch": 0.51, + "learning_rate": 1.7419258245933854e-05, + "loss": 0.7864, "step": 1128 }, { - "epoch": 0.58, - "learning_rate": 1.665492459223357e-05, - "loss": 0.7537, + "epoch": 0.51, + "learning_rate": 1.7414309347646223e-05, + "loss": 0.8219, "step": 1129 }, { - "epoch": 0.58, - "learning_rate": 1.6648707340002387e-05, - "loss": 0.7795, + "epoch": 0.51, + "learning_rate": 1.7409356413284654e-05, + "loss": 0.7671, "step": 1130 }, { - "epoch": 0.58, - "learning_rate": 1.66424854781703e-05, - "loss": 0.8118, + "epoch": 0.52, + "learning_rate": 1.740439944554534e-05, + "loss": 0.7852, "step": 1131 }, { - "epoch": 0.58, - "learning_rate": 1.663625901105096e-05, - "loss": 0.7708, + "epoch": 0.52, + "learning_rate": 1.739943844712667e-05, + "loss": 0.7805, "step": 1132 }, { - "epoch": 0.58, - "learning_rate": 1.6630027942961243e-05, - "loss": 0.8064, + "epoch": 0.52, + "learning_rate": 1.7394473420729224e-05, + "loss": 0.7454, "step": 1133 }, { - "epoch": 0.58, - "learning_rate": 1.662379227822119e-05, - "loss": 0.7825, + "epoch": 0.52, + "learning_rate": 1.7389504369055783e-05, + "loss": 0.7908, "step": 1134 }, { - "epoch": 0.58, - "learning_rate": 1.6617552021154025e-05, - "loss": 0.8035, + "epoch": 0.52, + "learning_rate": 1.7384531294811305e-05, + "loss": 0.7524, "step": 1135 }, { - "epoch": 0.58, - "learning_rate": 1.6611307176086183e-05, - "loss": 0.8328, + "epoch": 0.52, + "learning_rate": 1.7379554200702955e-05, + "loss": 0.8337, "step": 1136 }, { - "epoch": 0.58, - "learning_rate": 1.6605057747347256e-05, - "loss": 0.7949, + "epoch": 0.52, + "learning_rate": 1.737457308944008e-05, + "loss": 0.6904, "step": 1137 }, { - "epoch": 0.58, - "learning_rate": 1.6598803739270023e-05, - "loss": 0.7751, + "epoch": 0.52, + "learning_rate": 1.7369587963734197e-05, + "loss": 0.729, "step": 1138 }, { - "epoch": 0.59, - "learning_rate": 1.6592545156190437e-05, - "loss": 0.781, + "epoch": 0.52, + "learning_rate": 1.7364598826299035e-05, + "loss": 0.821, "step": 1139 }, { - "epoch": 0.59, - "learning_rate": 1.658628200244763e-05, - "loss": 0.7891, + "epoch": 0.52, + "learning_rate": 1.7359605679850493e-05, + "loss": 0.8191, "step": 1140 }, { - "epoch": 0.59, - "learning_rate": 1.658001428238388e-05, - "loss": 0.8145, + "epoch": 0.52, + "learning_rate": 1.735460852710665e-05, + "loss": 0.8, "step": 1141 }, { - "epoch": 0.59, - "learning_rate": 1.657374200034466e-05, - "loss": 0.8376, + "epoch": 0.52, + "learning_rate": 1.7349607370787775e-05, + "loss": 0.7551, "step": 1142 }, { - "epoch": 0.59, - "learning_rate": 1.6567465160678587e-05, - "loss": 0.7974, + "epoch": 0.52, + "learning_rate": 1.7344602213616307e-05, + "loss": 0.7777, "step": 1143 }, { - "epoch": 0.59, - "learning_rate": 1.656118376773744e-05, - "loss": 0.8516, + "epoch": 0.52, + "learning_rate": 1.7339593058316867e-05, + "loss": 0.7842, "step": 1144 }, { - "epoch": 0.59, - "learning_rate": 1.655489782587617e-05, - "loss": 0.7693, + "epoch": 0.52, + "learning_rate": 1.7334579907616258e-05, + "loss": 0.8206, "step": 1145 }, { - "epoch": 0.59, - "learning_rate": 1.6548607339452853e-05, - "loss": 0.7529, + "epoch": 0.52, + "learning_rate": 1.732956276424345e-05, + "loss": 0.7756, "step": 1146 }, { - "epoch": 0.59, - "learning_rate": 1.654231231282874e-05, - "loss": 0.7542, + "epoch": 0.52, + "learning_rate": 1.7324541630929586e-05, + "loss": 0.7815, "step": 1147 }, { - "epoch": 0.59, - "learning_rate": 1.6536012750368228e-05, - "loss": 0.7791, + "epoch": 0.52, + "learning_rate": 1.7319516510407983e-05, + "loss": 0.7156, "step": 1148 }, { - "epoch": 0.59, - "learning_rate": 1.652970865643885e-05, - "loss": 0.7681, + "epoch": 0.52, + "learning_rate": 1.7314487405414136e-05, + "loss": 0.7499, "step": 1149 }, { - "epoch": 0.59, - "learning_rate": 1.6523400035411278e-05, - "loss": 0.7942, + "epoch": 0.52, + "learning_rate": 1.73094543186857e-05, + "loss": 0.7761, "step": 1150 }, { - "epoch": 0.59, - "learning_rate": 1.6517086891659335e-05, - "loss": 0.7595, + "epoch": 0.52, + "learning_rate": 1.7304417252962496e-05, + "loss": 0.7438, "step": 1151 }, { - "epoch": 0.59, - "learning_rate": 1.651076922955997e-05, - "loss": 0.7607, + "epoch": 0.52, + "learning_rate": 1.729937621098652e-05, + "loss": 0.7986, "step": 1152 }, { - "epoch": 0.59, - "learning_rate": 1.6504447053493264e-05, - "loss": 0.7356, + "epoch": 0.53, + "learning_rate": 1.7294331195501926e-05, + "loss": 0.793, "step": 1153 }, { - "epoch": 0.59, - "learning_rate": 1.649812036784244e-05, - "loss": 0.7329, + "epoch": 0.53, + "learning_rate": 1.7289282209255032e-05, + "loss": 0.7306, "step": 1154 }, { - "epoch": 0.59, - "learning_rate": 1.6491789176993833e-05, - "loss": 0.7896, + "epoch": 0.53, + "learning_rate": 1.7284229254994314e-05, + "loss": 0.7515, "step": 1155 }, { - "epoch": 0.59, - "learning_rate": 1.6485453485336907e-05, - "loss": 0.7778, + "epoch": 0.53, + "learning_rate": 1.7279172335470423e-05, + "loss": 0.7976, "step": 1156 }, { - "epoch": 0.59, - "learning_rate": 1.6479113297264246e-05, - "loss": 0.7856, + "epoch": 0.53, + "learning_rate": 1.7274111453436152e-05, + "loss": 0.7903, "step": 1157 }, { - "epoch": 0.6, - "learning_rate": 1.6472768617171558e-05, - "loss": 0.7749, + "epoch": 0.53, + "learning_rate": 1.7269046611646448e-05, + "loss": 0.7622, "step": 1158 }, { - "epoch": 0.6, - "learning_rate": 1.6466419449457655e-05, - "loss": 0.8098, + "epoch": 0.53, + "learning_rate": 1.7263977812858437e-05, + "loss": 0.7969, "step": 1159 }, { - "epoch": 0.6, - "learning_rate": 1.6460065798524464e-05, - "loss": 0.7507, + "epoch": 0.53, + "learning_rate": 1.7258905059831374e-05, + "loss": 0.7363, "step": 1160 }, { - "epoch": 0.6, - "learning_rate": 1.6453707668777022e-05, - "loss": 0.7634, + "epoch": 0.53, + "learning_rate": 1.7253828355326683e-05, + "loss": 0.7664, "step": 1161 }, { - "epoch": 0.6, - "learning_rate": 1.644734506462347e-05, - "loss": 0.7126, + "epoch": 0.53, + "learning_rate": 1.724874770210793e-05, + "loss": 0.7939, "step": 1162 }, { - "epoch": 0.6, - "learning_rate": 1.6440977990475054e-05, - "loss": 0.7976, + "epoch": 0.53, + "learning_rate": 1.7243663102940833e-05, + "loss": 0.814, "step": 1163 }, { - "epoch": 0.6, - "learning_rate": 1.6434606450746113e-05, - "loss": 0.7483, + "epoch": 0.53, + "learning_rate": 1.723857456059326e-05, + "loss": 0.8577, "step": 1164 }, { - "epoch": 0.6, - "learning_rate": 1.6428230449854087e-05, - "loss": 0.8306, + "epoch": 0.53, + "learning_rate": 1.723348207783522e-05, + "loss": 0.7249, "step": 1165 }, { - "epoch": 0.6, - "learning_rate": 1.6421849992219504e-05, - "loss": 0.7917, + "epoch": 0.53, + "learning_rate": 1.7228385657438877e-05, + "loss": 0.7983, "step": 1166 }, { - "epoch": 0.6, - "learning_rate": 1.641546508226599e-05, - "loss": 0.751, + "epoch": 0.53, + "learning_rate": 1.722328530217853e-05, + "loss": 0.761, "step": 1167 }, { - "epoch": 0.6, - "learning_rate": 1.6409075724420253e-05, - "loss": 0.7656, + "epoch": 0.53, + "learning_rate": 1.721818101483062e-05, + "loss": 0.7886, "step": 1168 }, { - "epoch": 0.6, - "learning_rate": 1.6402681923112084e-05, - "loss": 0.7368, + "epoch": 0.53, + "learning_rate": 1.721307279817374e-05, + "loss": 0.7732, "step": 1169 }, { - "epoch": 0.6, - "learning_rate": 1.6396283682774354e-05, - "loss": 0.7583, + "epoch": 0.53, + "learning_rate": 1.72079606549886e-05, + "loss": 0.7188, "step": 1170 }, { - "epoch": 0.6, - "learning_rate": 1.6389881007843015e-05, - "loss": 0.8374, + "epoch": 0.53, + "learning_rate": 1.7202844588058066e-05, + "loss": 0.7905, "step": 1171 }, { - "epoch": 0.6, - "learning_rate": 1.6383473902757083e-05, - "loss": 0.802, + "epoch": 0.53, + "learning_rate": 1.7197724600167135e-05, + "loss": 0.7214, "step": 1172 }, { - "epoch": 0.6, - "learning_rate": 1.637706237195867e-05, - "loss": 0.8049, + "epoch": 0.53, + "learning_rate": 1.719260069410294e-05, + "loss": 0.7949, "step": 1173 }, { - "epoch": 0.6, - "learning_rate": 1.637064641989293e-05, - "loss": 0.7427, + "epoch": 0.53, + "learning_rate": 1.718747287265474e-05, + "loss": 0.7126, "step": 1174 }, { - "epoch": 0.6, - "learning_rate": 1.6364226051008096e-05, - "loss": 0.8037, + "epoch": 0.54, + "learning_rate": 1.7182341138613935e-05, + "loss": 0.8145, "step": 1175 }, { - "epoch": 0.6, - "learning_rate": 1.6357801269755457e-05, - "loss": 0.8071, + "epoch": 0.54, + "learning_rate": 1.7177205494774044e-05, + "loss": 0.7776, "step": 1176 }, { - "epoch": 0.6, - "learning_rate": 1.6351372080589368e-05, - "loss": 0.7563, + "epoch": 0.54, + "learning_rate": 1.7172065943930727e-05, + "loss": 0.7384, "step": 1177 }, { - "epoch": 0.61, - "learning_rate": 1.6344938487967238e-05, - "loss": 0.7803, + "epoch": 0.54, + "learning_rate": 1.716692248888176e-05, + "loss": 0.8049, "step": 1178 }, { - "epoch": 0.61, - "learning_rate": 1.6338500496349516e-05, - "loss": 0.7798, + "epoch": 0.54, + "learning_rate": 1.7161775132427046e-05, + "loss": 0.8236, "step": 1179 }, { - "epoch": 0.61, - "learning_rate": 1.633205811019973e-05, - "loss": 0.7363, + "epoch": 0.54, + "learning_rate": 1.715662387736862e-05, + "loss": 0.777, "step": 1180 }, { - "epoch": 0.61, - "learning_rate": 1.632561133398442e-05, - "loss": 0.7759, + "epoch": 0.54, + "learning_rate": 1.715146872651063e-05, + "loss": 0.7529, "step": 1181 }, { - "epoch": 0.61, - "learning_rate": 1.631916017217319e-05, - "loss": 0.7871, + "epoch": 0.54, + "learning_rate": 1.7146309682659346e-05, + "loss": 0.8057, "step": 1182 }, { - "epoch": 0.61, - "learning_rate": 1.631270462923869e-05, - "loss": 0.7566, + "epoch": 0.54, + "learning_rate": 1.714114674862317e-05, + "loss": 0.7041, "step": 1183 }, { - "epoch": 0.61, - "learning_rate": 1.6306244709656597e-05, - "loss": 0.7888, + "epoch": 0.54, + "learning_rate": 1.7135979927212597e-05, + "loss": 0.736, "step": 1184 }, { - "epoch": 0.61, - "learning_rate": 1.6299780417905614e-05, - "loss": 0.7764, + "epoch": 0.54, + "learning_rate": 1.7130809221240262e-05, + "loss": 0.7454, "step": 1185 }, { - "epoch": 0.61, - "learning_rate": 1.629331175846749e-05, - "loss": 0.7657, + "epoch": 0.54, + "learning_rate": 1.71256346335209e-05, + "loss": 0.8262, "step": 1186 }, { - "epoch": 0.61, - "learning_rate": 1.6286838735827e-05, - "loss": 0.7861, + "epoch": 0.54, + "learning_rate": 1.7120456166871365e-05, + "loss": 0.8096, "step": 1187 }, { - "epoch": 0.61, - "learning_rate": 1.628036135447194e-05, - "loss": 0.7754, + "epoch": 0.54, + "learning_rate": 1.7115273824110618e-05, + "loss": 0.7297, "step": 1188 }, { - "epoch": 0.61, - "learning_rate": 1.627387961889313e-05, - "loss": 0.8152, + "epoch": 0.54, + "learning_rate": 1.7110087608059744e-05, + "loss": 0.7955, "step": 1189 }, { - "epoch": 0.61, - "learning_rate": 1.62673935335844e-05, - "loss": 0.7893, + "epoch": 0.54, + "learning_rate": 1.7104897521541914e-05, + "loss": 0.7987, "step": 1190 }, { - "epoch": 0.61, - "learning_rate": 1.626090310304262e-05, - "loss": 0.7363, + "epoch": 0.54, + "learning_rate": 1.7099703567382424e-05, + "loss": 0.7827, "step": 1191 }, { - "epoch": 0.61, - "learning_rate": 1.625440833176764e-05, - "loss": 0.7954, + "epoch": 0.54, + "learning_rate": 1.709450574840867e-05, + "loss": 0.8051, "step": 1192 }, { - "epoch": 0.61, - "learning_rate": 1.6247909224262346e-05, - "loss": 0.7922, + "epoch": 0.54, + "learning_rate": 1.708930406745015e-05, + "loss": 0.7737, "step": 1193 }, { - "epoch": 0.61, - "learning_rate": 1.6241405785032616e-05, - "loss": 0.7715, + "epoch": 0.54, + "learning_rate": 1.708409852733846e-05, + "loss": 0.7773, "step": 1194 }, { - "epoch": 0.61, - "learning_rate": 1.6234898018587336e-05, - "loss": 0.8264, + "epoch": 0.54, + "learning_rate": 1.707888913090731e-05, + "loss": 0.7872, "step": 1195 }, { - "epoch": 0.61, - "learning_rate": 1.622838592943839e-05, - "loss": 0.8391, + "epoch": 0.54, + "learning_rate": 1.7073675880992494e-05, + "loss": 0.762, "step": 1196 }, { - "epoch": 0.62, - "learning_rate": 1.622186952210067e-05, - "loss": 0.7312, + "epoch": 0.55, + "learning_rate": 1.7068458780431922e-05, + "loss": 0.7579, "step": 1197 }, { - "epoch": 0.62, - "learning_rate": 1.6215348801092037e-05, - "loss": 0.7368, + "epoch": 0.55, + "learning_rate": 1.7063237832065578e-05, + "loss": 0.7747, "step": 1198 }, { - "epoch": 0.62, - "learning_rate": 1.6208823770933372e-05, - "loss": 0.7698, + "epoch": 0.55, + "learning_rate": 1.7058013038735556e-05, + "loss": 0.8169, "step": 1199 }, { - "epoch": 0.62, - "learning_rate": 1.6202294436148516e-05, - "loss": 0.7629, + "epoch": 0.55, + "learning_rate": 1.7052784403286044e-05, + "loss": 0.8071, "step": 1200 }, { - "epoch": 0.62, - "learning_rate": 1.6195760801264317e-05, - "loss": 0.7114, + "epoch": 0.55, + "learning_rate": 1.7047551928563306e-05, + "loss": 0.7747, "step": 1201 }, { - "epoch": 0.62, - "learning_rate": 1.6189222870810596e-05, - "loss": 0.8254, + "epoch": 0.55, + "learning_rate": 1.7042315617415718e-05, + "loss": 0.8022, "step": 1202 }, { - "epoch": 0.62, - "learning_rate": 1.6182680649320145e-05, - "loss": 0.7878, + "epoch": 0.55, + "learning_rate": 1.7037075472693724e-05, + "loss": 0.7986, "step": 1203 }, { - "epoch": 0.62, - "learning_rate": 1.6176134141328747e-05, - "loss": 0.7576, + "epoch": 0.55, + "learning_rate": 1.7031831497249868e-05, + "loss": 0.7842, "step": 1204 }, { - "epoch": 0.62, - "learning_rate": 1.6169583351375137e-05, - "loss": 0.7373, + "epoch": 0.55, + "learning_rate": 1.7026583693938773e-05, + "loss": 0.7615, "step": 1205 }, { - "epoch": 0.62, - "learning_rate": 1.6163028284001034e-05, - "loss": 0.7632, + "epoch": 0.55, + "learning_rate": 1.7021332065617152e-05, + "loss": 0.7867, "step": 1206 }, { - "epoch": 0.62, - "learning_rate": 1.615646894375112e-05, - "loss": 0.7764, + "epoch": 0.55, + "learning_rate": 1.701607661514379e-05, + "loss": 0.7534, "step": 1207 }, { - "epoch": 0.62, - "learning_rate": 1.614990533517303e-05, - "loss": 0.8225, + "epoch": 0.55, + "learning_rate": 1.701081734537956e-05, + "loss": 0.8289, "step": 1208 }, { - "epoch": 0.62, - "learning_rate": 1.6143337462817372e-05, - "loss": 0.7358, + "epoch": 0.55, + "learning_rate": 1.7005554259187416e-05, + "loss": 0.734, "step": 1209 }, { - "epoch": 0.62, - "learning_rate": 1.61367653312377e-05, - "loss": 0.7695, + "epoch": 0.55, + "learning_rate": 1.700028735943238e-05, + "loss": 0.8054, "step": 1210 }, { - "epoch": 0.62, - "learning_rate": 1.6130188944990526e-05, - "loss": 0.7664, + "epoch": 0.55, + "learning_rate": 1.6995016648981563e-05, + "loss": 0.7384, "step": 1211 }, { - "epoch": 0.62, - "learning_rate": 1.6123608308635307e-05, - "loss": 0.7651, + "epoch": 0.55, + "learning_rate": 1.6989742130704142e-05, + "loss": 0.7424, "step": 1212 }, { - "epoch": 0.62, - "learning_rate": 1.6117023426734455e-05, - "loss": 0.7522, + "epoch": 0.55, + "learning_rate": 1.6984463807471364e-05, + "loss": 0.814, "step": 1213 }, { - "epoch": 0.62, - "learning_rate": 1.6110434303853317e-05, - "loss": 0.7817, + "epoch": 0.55, + "learning_rate": 1.6979181682156557e-05, + "loss": 0.7498, "step": 1214 }, { - "epoch": 0.62, - "learning_rate": 1.6103840944560185e-05, - "loss": 0.7583, + "epoch": 0.55, + "learning_rate": 1.6973895757635104e-05, + "loss": 0.7668, "step": 1215 }, { - "epoch": 0.63, - "learning_rate": 1.609724335342628e-05, - "loss": 0.8223, + "epoch": 0.55, + "learning_rate": 1.696860603678448e-05, + "loss": 0.7863, "step": 1216 }, { - "epoch": 0.63, - "learning_rate": 1.6090641535025773e-05, - "loss": 0.751, + "epoch": 0.55, + "learning_rate": 1.6963312522484203e-05, + "loss": 0.7794, "step": 1217 }, { - "epoch": 0.63, - "learning_rate": 1.6084035493935753e-05, - "loss": 0.7734, + "epoch": 0.55, + "learning_rate": 1.6958015217615863e-05, + "loss": 0.8438, "step": 1218 }, { - "epoch": 0.63, - "learning_rate": 1.6077425234736236e-05, - "loss": 0.7458, + "epoch": 0.56, + "learning_rate": 1.6952714125063123e-05, + "loss": 0.8356, "step": 1219 }, { - "epoch": 0.63, - "learning_rate": 1.6070810762010175e-05, - "loss": 0.7659, + "epoch": 0.56, + "learning_rate": 1.6947409247711693e-05, + "loss": 0.7832, "step": 1220 }, { - "epoch": 0.63, - "learning_rate": 1.6064192080343426e-05, - "loss": 0.7136, + "epoch": 0.56, + "learning_rate": 1.694210058844936e-05, + "loss": 0.7659, "step": 1221 }, { - "epoch": 0.63, - "learning_rate": 1.6057569194324783e-05, - "loss": 0.7966, + "epoch": 0.56, + "learning_rate": 1.6936788150165945e-05, + "loss": 0.7825, "step": 1222 }, { - "epoch": 0.63, - "learning_rate": 1.6050942108545938e-05, - "loss": 0.7559, + "epoch": 0.56, + "learning_rate": 1.6931471935753356e-05, + "loss": 0.713, "step": 1223 }, { - "epoch": 0.63, - "learning_rate": 1.6044310827601502e-05, - "loss": 0.7771, + "epoch": 0.56, + "learning_rate": 1.692615194810554e-05, + "loss": 0.7616, "step": 1224 }, { - "epoch": 0.63, - "learning_rate": 1.6037675356088994e-05, - "loss": 0.8159, + "epoch": 0.56, + "learning_rate": 1.6920828190118492e-05, + "loss": 0.7637, "step": 1225 }, { - "epoch": 0.63, - "learning_rate": 1.603103569860884e-05, - "loss": 0.7107, + "epoch": 0.56, + "learning_rate": 1.6915500664690275e-05, + "loss": 0.7117, "step": 1226 }, { - "epoch": 0.63, - "learning_rate": 1.6024391859764368e-05, - "loss": 0.7666, + "epoch": 0.56, + "learning_rate": 1.6910169374720997e-05, + "loss": 0.7732, "step": 1227 }, { - "epoch": 0.63, - "learning_rate": 1.6017743844161802e-05, - "loss": 0.8381, + "epoch": 0.56, + "learning_rate": 1.6904834323112807e-05, + "loss": 0.8103, "step": 1228 }, { - "epoch": 0.63, - "learning_rate": 1.601109165641026e-05, - "loss": 0.8462, + "epoch": 0.56, + "learning_rate": 1.6899495512769914e-05, + "loss": 0.741, "step": 1229 }, { - "epoch": 0.63, - "learning_rate": 1.6004435301121762e-05, - "loss": 0.8101, + "epoch": 0.56, + "learning_rate": 1.689415294659856e-05, + "loss": 0.802, "step": 1230 }, { - "epoch": 0.63, - "learning_rate": 1.5997774782911205e-05, - "loss": 0.7627, + "epoch": 0.56, + "learning_rate": 1.688880662750705e-05, + "loss": 0.8008, "step": 1231 }, { - "epoch": 0.63, - "learning_rate": 1.5991110106396385e-05, - "loss": 0.7734, + "epoch": 0.56, + "learning_rate": 1.6883456558405713e-05, + "loss": 0.8035, "step": 1232 }, { - "epoch": 0.63, - "learning_rate": 1.5984441276197967e-05, - "loss": 0.7698, + "epoch": 0.56, + "learning_rate": 1.6878102742206934e-05, + "loss": 0.8013, "step": 1233 }, { - "epoch": 0.63, - "learning_rate": 1.597776829693951e-05, - "loss": 0.7776, + "epoch": 0.56, + "learning_rate": 1.687274518182512e-05, + "loss": 0.7063, "step": 1234 }, { - "epoch": 0.63, - "learning_rate": 1.5971091173247442e-05, - "loss": 0.8176, + "epoch": 0.56, + "learning_rate": 1.6867383880176737e-05, + "loss": 0.7749, "step": 1235 }, { - "epoch": 0.64, - "learning_rate": 1.596440990975106e-05, - "loss": 0.7595, + "epoch": 0.56, + "learning_rate": 1.686201884018028e-05, + "loss": 0.7821, "step": 1236 }, { - "epoch": 0.64, - "learning_rate": 1.595772451108254e-05, - "loss": 0.7695, + "epoch": 0.56, + "learning_rate": 1.6856650064756266e-05, + "loss": 0.821, "step": 1237 }, { - "epoch": 0.64, - "learning_rate": 1.5951034981876926e-05, - "loss": 0.7993, + "epoch": 0.56, + "learning_rate": 1.6851277556827265e-05, + "loss": 0.7725, "step": 1238 }, { - "epoch": 0.64, - "learning_rate": 1.5944341326772112e-05, - "loss": 0.8022, + "epoch": 0.56, + "learning_rate": 1.684590131931787e-05, + "loss": 0.79, "step": 1239 }, { - "epoch": 0.64, - "learning_rate": 1.593764355040887e-05, - "loss": 0.7622, + "epoch": 0.56, + "learning_rate": 1.68405213551547e-05, + "loss": 0.8064, "step": 1240 }, { - "epoch": 0.64, - "learning_rate": 1.5930941657430808e-05, - "loss": 0.7595, + "epoch": 0.57, + "learning_rate": 1.683513766726641e-05, + "loss": 0.7455, "step": 1241 }, { - "epoch": 0.64, - "learning_rate": 1.5924235652484416e-05, - "loss": 0.7424, + "epoch": 0.57, + "learning_rate": 1.682975025858368e-05, + "loss": 0.7823, "step": 1242 }, { - "epoch": 0.64, - "learning_rate": 1.591752554021901e-05, - "loss": 0.7681, + "epoch": 0.57, + "learning_rate": 1.6824359132039215e-05, + "loss": 0.7391, "step": 1243 }, { - "epoch": 0.64, - "learning_rate": 1.5910811325286768e-05, - "loss": 0.717, + "epoch": 0.57, + "learning_rate": 1.6818964290567742e-05, + "loss": 0.7686, "step": 1244 }, { - "epoch": 0.64, - "learning_rate": 1.5904093012342707e-05, - "loss": 0.811, + "epoch": 0.57, + "learning_rate": 1.681356573710601e-05, + "loss": 0.7695, "step": 1245 }, { - "epoch": 0.64, - "learning_rate": 1.5897370606044683e-05, - "loss": 0.7461, + "epoch": 0.57, + "learning_rate": 1.6808163474592792e-05, + "loss": 0.8137, "step": 1246 }, { - "epoch": 0.64, - "learning_rate": 1.5890644111053396e-05, - "loss": 0.7637, + "epoch": 0.57, + "learning_rate": 1.6802757505968883e-05, + "loss": 0.7601, "step": 1247 }, { - "epoch": 0.64, - "learning_rate": 1.588391353203238e-05, - "loss": 0.7773, + "epoch": 0.57, + "learning_rate": 1.6797347834177086e-05, + "loss": 0.7803, "step": 1248 }, { - "epoch": 0.64, - "learning_rate": 1.587717887364799e-05, - "loss": 0.7883, + "epoch": 0.57, + "learning_rate": 1.6791934462162224e-05, + "loss": 0.7952, "step": 1249 }, { - "epoch": 0.64, - "learning_rate": 1.587044014056943e-05, - "loss": 0.7725, + "epoch": 0.57, + "learning_rate": 1.678651739287114e-05, + "loss": 0.8086, "step": 1250 }, { - "epoch": 0.64, - "learning_rate": 1.5863697337468704e-05, - "loss": 0.6641, + "epoch": 0.57, + "learning_rate": 1.678109662925268e-05, + "loss": 0.7109, "step": 1251 }, { - "epoch": 0.64, - "learning_rate": 1.5856950469020656e-05, - "loss": 0.7244, + "epoch": 0.57, + "learning_rate": 1.6775672174257706e-05, + "loss": 0.7883, "step": 1252 }, { - "epoch": 0.64, - "learning_rate": 1.5850199539902944e-05, - "loss": 0.8079, + "epoch": 0.57, + "learning_rate": 1.6770244030839095e-05, + "loss": 0.7321, "step": 1253 }, { - "epoch": 0.64, - "learning_rate": 1.584344455479604e-05, - "loss": 0.7649, + "epoch": 0.57, + "learning_rate": 1.676481220195172e-05, + "loss": 0.7646, "step": 1254 }, { - "epoch": 0.65, - "learning_rate": 1.583668551838322e-05, - "loss": 0.8162, + "epoch": 0.57, + "learning_rate": 1.6759376690552472e-05, + "loss": 0.7964, "step": 1255 }, { - "epoch": 0.65, - "learning_rate": 1.582992243535059e-05, - "loss": 0.7505, + "epoch": 0.57, + "learning_rate": 1.6753937499600236e-05, + "loss": 0.7295, "step": 1256 }, { - "epoch": 0.65, - "learning_rate": 1.5823155310387036e-05, - "loss": 0.7397, + "epoch": 0.57, + "learning_rate": 1.6748494632055908e-05, + "loss": 0.8083, "step": 1257 }, { - "epoch": 0.65, - "learning_rate": 1.5816384148184273e-05, - "loss": 0.7354, + "epoch": 0.57, + "learning_rate": 1.6743048090882376e-05, + "loss": 0.7993, "step": 1258 }, { - "epoch": 0.65, - "learning_rate": 1.5809608953436786e-05, - "loss": 0.7573, + "epoch": 0.57, + "learning_rate": 1.6737597879044547e-05, + "loss": 0.7993, "step": 1259 }, { - "epoch": 0.65, - "learning_rate": 1.5802829730841877e-05, - "loss": 0.7598, + "epoch": 0.57, + "learning_rate": 1.67321439995093e-05, + "loss": 0.8005, "step": 1260 }, { - "epoch": 0.65, - "learning_rate": 1.5796046485099633e-05, - "loss": 0.7671, + "epoch": 0.57, + "learning_rate": 1.6726686455245534e-05, + "loss": 0.8325, "step": 1261 }, { - "epoch": 0.65, - "learning_rate": 1.5789259220912938e-05, - "loss": 0.7798, + "epoch": 0.57, + "learning_rate": 1.6721225249224127e-05, + "loss": 0.7483, "step": 1262 }, { - "epoch": 0.65, - "learning_rate": 1.5782467942987448e-05, - "loss": 0.748, + "epoch": 0.58, + "learning_rate": 1.6715760384417955e-05, + "loss": 0.7256, "step": 1263 }, { - "epoch": 0.65, - "learning_rate": 1.577567265603161e-05, - "loss": 0.8193, + "epoch": 0.58, + "learning_rate": 1.6710291863801896e-05, + "loss": 0.7891, "step": 1264 }, { - "epoch": 0.65, - "learning_rate": 1.5768873364756653e-05, - "loss": 0.7208, + "epoch": 0.58, + "learning_rate": 1.6704819690352796e-05, + "loss": 0.7797, "step": 1265 }, { - "epoch": 0.65, - "learning_rate": 1.5762070073876574e-05, - "loss": 0.7991, + "epoch": 0.58, + "learning_rate": 1.6699343867049514e-05, + "loss": 0.7896, "step": 1266 }, { - "epoch": 0.65, - "learning_rate": 1.5755262788108152e-05, - "loss": 0.6616, + "epoch": 0.58, + "learning_rate": 1.6693864396872877e-05, + "loss": 0.7991, "step": 1267 }, { - "epoch": 0.65, - "learning_rate": 1.574845151217093e-05, - "loss": 0.7556, + "epoch": 0.58, + "learning_rate": 1.668838128280571e-05, + "loss": 0.7683, "step": 1268 }, { - "epoch": 0.65, - "learning_rate": 1.574163625078722e-05, - "loss": 0.801, + "epoch": 0.58, + "learning_rate": 1.668289452783281e-05, + "loss": 0.7527, "step": 1269 }, { - "epoch": 0.65, - "learning_rate": 1.5734817008682098e-05, - "loss": 0.7852, + "epoch": 0.58, + "learning_rate": 1.6677404134940966e-05, + "loss": 0.7665, "step": 1270 }, { - "epoch": 0.65, - "learning_rate": 1.5727993790583392e-05, - "loss": 0.8025, + "epoch": 0.58, + "learning_rate": 1.6671910107118944e-05, + "loss": 0.7012, "step": 1271 }, { - "epoch": 0.65, - "learning_rate": 1.5721166601221697e-05, - "loss": 0.7249, + "epoch": 0.58, + "learning_rate": 1.666641244735749e-05, + "loss": 0.7993, "step": 1272 }, { - "epoch": 0.65, - "learning_rate": 1.571433544533036e-05, - "loss": 0.8416, + "epoch": 0.58, + "learning_rate": 1.6660911158649317e-05, + "loss": 0.7531, "step": 1273 }, { - "epoch": 0.65, - "learning_rate": 1.5707500327645468e-05, - "loss": 0.7664, + "epoch": 0.58, + "learning_rate": 1.665540624398913e-05, + "loss": 0.7659, "step": 1274 }, { - "epoch": 0.66, - "learning_rate": 1.570066125290586e-05, - "loss": 0.7112, + "epoch": 0.58, + "learning_rate": 1.6649897706373595e-05, + "loss": 0.7695, "step": 1275 }, { - "epoch": 0.66, - "learning_rate": 1.569381822585313e-05, - "loss": 0.7554, + "epoch": 0.58, + "learning_rate": 1.664438554880136e-05, + "loss": 0.7046, "step": 1276 }, { - "epoch": 0.66, - "learning_rate": 1.5686971251231597e-05, - "loss": 0.7576, + "epoch": 0.58, + "learning_rate": 1.663886977427303e-05, + "loss": 0.7206, "step": 1277 }, { - "epoch": 0.66, - "learning_rate": 1.568012033378832e-05, - "loss": 0.7832, + "epoch": 0.58, + "learning_rate": 1.6633350385791194e-05, + "loss": 0.7745, "step": 1278 }, { - "epoch": 0.66, - "learning_rate": 1.56732654782731e-05, - "loss": 0.7832, + "epoch": 0.58, + "learning_rate": 1.66278273863604e-05, + "loss": 0.7429, "step": 1279 }, { - "epoch": 0.66, - "learning_rate": 1.5666406689438455e-05, - "loss": 0.8081, + "epoch": 0.58, + "learning_rate": 1.662230077898716e-05, + "loss": 0.8086, "step": 1280 }, { - "epoch": 0.66, - "learning_rate": 1.5659543972039637e-05, - "loss": 0.7761, + "epoch": 0.58, + "learning_rate": 1.661677056667996e-05, + "loss": 0.782, "step": 1281 }, { - "epoch": 0.66, - "learning_rate": 1.565267733083463e-05, - "loss": 0.709, + "epoch": 0.58, + "learning_rate": 1.6611236752449236e-05, + "loss": 0.7764, "step": 1282 }, { - "epoch": 0.66, - "learning_rate": 1.5645806770584122e-05, - "loss": 0.7998, + "epoch": 0.58, + "learning_rate": 1.6605699339307392e-05, + "loss": 0.7937, "step": 1283 }, { - "epoch": 0.66, - "learning_rate": 1.563893229605153e-05, - "loss": 0.7512, + "epoch": 0.58, + "learning_rate": 1.660015833026879e-05, + "loss": 0.791, "step": 1284 }, { - "epoch": 0.66, - "learning_rate": 1.563205391200298e-05, - "loss": 0.786, + "epoch": 0.59, + "learning_rate": 1.6594613728349748e-05, + "loss": 0.8042, "step": 1285 }, { - "epoch": 0.66, - "learning_rate": 1.562517162320731e-05, - "loss": 0.7654, + "epoch": 0.59, + "learning_rate": 1.6589065536568543e-05, + "loss": 0.7975, "step": 1286 }, { - "epoch": 0.66, - "learning_rate": 1.5618285434436068e-05, - "loss": 0.7151, + "epoch": 0.59, + "learning_rate": 1.6583513757945403e-05, + "loss": 0.7429, "step": 1287 }, { - "epoch": 0.66, - "learning_rate": 1.5611395350463494e-05, - "loss": 0.8213, + "epoch": 0.59, + "learning_rate": 1.6577958395502507e-05, + "loss": 0.8328, "step": 1288 }, { - "epoch": 0.66, - "learning_rate": 1.5604501376066544e-05, - "loss": 0.7933, + "epoch": 0.59, + "learning_rate": 1.657239945226399e-05, + "loss": 0.8152, "step": 1289 }, { - "epoch": 0.66, - "learning_rate": 1.5597603516024865e-05, - "loss": 0.7751, + "epoch": 0.59, + "learning_rate": 1.6566836931255934e-05, + "loss": 0.7815, "step": 1290 }, { - "epoch": 0.66, - "learning_rate": 1.5590701775120794e-05, - "loss": 0.7686, + "epoch": 0.59, + "learning_rate": 1.656127083550637e-05, + "loss": 0.7805, "step": 1291 }, { - "epoch": 0.66, - "learning_rate": 1.5583796158139364e-05, - "loss": 0.8103, + "epoch": 0.59, + "learning_rate": 1.6555701168045266e-05, + "loss": 0.8372, "step": 1292 }, { - "epoch": 0.66, - "learning_rate": 1.5576886669868297e-05, - "loss": 0.8252, + "epoch": 0.59, + "learning_rate": 1.655012793190455e-05, + "loss": 0.7678, "step": 1293 }, { - "epoch": 0.67, - "learning_rate": 1.5569973315097985e-05, - "loss": 0.7043, + "epoch": 0.59, + "learning_rate": 1.6544551130118078e-05, + "loss": 0.8174, "step": 1294 }, { - "epoch": 0.67, - "learning_rate": 1.556305609862152e-05, - "loss": 0.8149, + "epoch": 0.59, + "learning_rate": 1.6538970765721657e-05, + "loss": 0.7043, "step": 1295 }, { - "epoch": 0.67, - "learning_rate": 1.555613502523466e-05, - "loss": 0.791, + "epoch": 0.59, + "learning_rate": 1.653338684175303e-05, + "loss": 0.8496, "step": 1296 }, { - "epoch": 0.67, - "learning_rate": 1.554921009973584e-05, - "loss": 0.7883, + "epoch": 0.59, + "learning_rate": 1.6527799361251876e-05, + "loss": 0.7827, "step": 1297 }, { - "epoch": 0.67, - "learning_rate": 1.5542281326926162e-05, - "loss": 0.8289, + "epoch": 0.59, + "learning_rate": 1.6522208327259806e-05, + "loss": 0.7493, "step": 1298 }, { - "epoch": 0.67, - "learning_rate": 1.5535348711609402e-05, - "loss": 0.7214, + "epoch": 0.59, + "learning_rate": 1.651661374282038e-05, + "loss": 0.7739, "step": 1299 }, { - "epoch": 0.67, - "learning_rate": 1.5528412258591994e-05, - "loss": 0.8027, + "epoch": 0.59, + "learning_rate": 1.6511015610979074e-05, + "loss": 0.7942, "step": 1300 }, { - "epoch": 0.67, - "learning_rate": 1.552147197268304e-05, - "loss": 0.7949, + "epoch": 0.59, + "learning_rate": 1.6505413934783313e-05, + "loss": 0.71, "step": 1301 }, { - "epoch": 0.67, - "learning_rate": 1.5514527858694286e-05, - "loss": 0.7673, + "epoch": 0.59, + "learning_rate": 1.6499808717282427e-05, + "loss": 0.7725, "step": 1302 }, { - "epoch": 0.67, - "learning_rate": 1.550757992144015e-05, - "loss": 0.7449, + "epoch": 0.59, + "learning_rate": 1.6494199961527698e-05, + "loss": 0.7017, "step": 1303 }, { - "epoch": 0.67, - "learning_rate": 1.5500628165737682e-05, - "loss": 0.7922, + "epoch": 0.59, + "learning_rate": 1.648858767057232e-05, + "loss": 0.7893, "step": 1304 }, { - "epoch": 0.67, - "learning_rate": 1.54936725964066e-05, - "loss": 0.7021, + "epoch": 0.59, + "learning_rate": 1.6482971847471417e-05, + "loss": 0.8054, "step": 1305 }, { - "epoch": 0.67, - "learning_rate": 1.5486713218269244e-05, - "loss": 0.7686, + "epoch": 0.59, + "learning_rate": 1.6477352495282026e-05, + "loss": 0.7695, "step": 1306 }, { - "epoch": 0.67, - "learning_rate": 1.5479750036150614e-05, - "loss": 0.759, + "epoch": 0.6, + "learning_rate": 1.6471729617063126e-05, + "loss": 0.7759, "step": 1307 }, { - "epoch": 0.67, - "learning_rate": 1.5472783054878332e-05, - "loss": 0.7988, + "epoch": 0.6, + "learning_rate": 1.6466103215875592e-05, + "loss": 0.731, "step": 1308 }, { - "epoch": 0.67, - "learning_rate": 1.546581227928267e-05, - "loss": 0.7744, + "epoch": 0.6, + "learning_rate": 1.6460473294782237e-05, + "loss": 0.7629, "step": 1309 }, { - "epoch": 0.67, - "learning_rate": 1.5458837714196504e-05, - "loss": 0.7742, + "epoch": 0.6, + "learning_rate": 1.645483985684777e-05, + "loss": 0.7495, "step": 1310 }, { - "epoch": 0.67, - "learning_rate": 1.545185936445537e-05, - "loss": 0.7979, + "epoch": 0.6, + "learning_rate": 1.6449202905138832e-05, + "loss": 0.6982, "step": 1311 }, { - "epoch": 0.67, - "learning_rate": 1.544487723489741e-05, - "loss": 0.7371, + "epoch": 0.6, + "learning_rate": 1.6443562442723964e-05, + "loss": 0.761, "step": 1312 }, { - "epoch": 0.67, - "learning_rate": 1.5437891330363387e-05, - "loss": 0.8445, + "epoch": 0.6, + "learning_rate": 1.6437918472673634e-05, + "loss": 0.8484, "step": 1313 }, { - "epoch": 0.68, - "learning_rate": 1.5430901655696683e-05, - "loss": 0.7612, + "epoch": 0.6, + "learning_rate": 1.6432270998060195e-05, + "loss": 0.8167, "step": 1314 }, { - "epoch": 0.68, - "learning_rate": 1.542390821574329e-05, - "loss": 0.7671, + "epoch": 0.6, + "learning_rate": 1.642662002195793e-05, + "loss": 0.7418, "step": 1315 }, { - "epoch": 0.68, - "learning_rate": 1.5416911015351827e-05, - "loss": 0.762, + "epoch": 0.6, + "learning_rate": 1.6420965547443023e-05, + "loss": 0.8335, "step": 1316 }, { - "epoch": 0.68, - "learning_rate": 1.54099100593735e-05, - "loss": 0.741, + "epoch": 0.6, + "learning_rate": 1.6415307577593553e-05, + "loss": 0.7781, "step": 1317 }, { - "epoch": 0.68, - "learning_rate": 1.5402905352662125e-05, - "loss": 0.7244, + "epoch": 0.6, + "learning_rate": 1.640964611548951e-05, + "loss": 0.8052, "step": 1318 }, { - "epoch": 0.68, - "learning_rate": 1.5395896900074122e-05, - "loss": 0.7485, + "epoch": 0.6, + "learning_rate": 1.6403981164212786e-05, + "loss": 0.7153, "step": 1319 }, { - "epoch": 0.68, - "learning_rate": 1.5388884706468504e-05, - "loss": 0.7915, + "epoch": 0.6, + "learning_rate": 1.6398312726847166e-05, + "loss": 0.7871, "step": 1320 }, { - "epoch": 0.68, - "learning_rate": 1.5381868776706883e-05, - "loss": 0.7549, + "epoch": 0.6, + "learning_rate": 1.6392640806478337e-05, + "loss": 0.7775, "step": 1321 }, { - "epoch": 0.68, - "learning_rate": 1.537484911565346e-05, - "loss": 0.7371, + "epoch": 0.6, + "learning_rate": 1.6386965406193886e-05, + "loss": 0.8101, "step": 1322 }, { - "epoch": 0.68, - "learning_rate": 1.5367825728175018e-05, - "loss": 0.7473, + "epoch": 0.6, + "learning_rate": 1.6381286529083278e-05, + "loss": 0.7964, "step": 1323 }, { - "epoch": 0.68, - "learning_rate": 1.5360798619140923e-05, - "loss": 0.7461, + "epoch": 0.6, + "learning_rate": 1.637560417823789e-05, + "loss": 0.8206, "step": 1324 }, { - "epoch": 0.68, - "learning_rate": 1.535376779342313e-05, - "loss": 0.7732, + "epoch": 0.6, + "learning_rate": 1.6369918356750985e-05, + "loss": 0.7576, "step": 1325 }, { - "epoch": 0.68, - "learning_rate": 1.5346733255896165e-05, - "loss": 0.8093, + "epoch": 0.6, + "learning_rate": 1.636422906771771e-05, + "loss": 0.7284, "step": 1326 }, { - "epoch": 0.68, - "learning_rate": 1.5339695011437128e-05, - "loss": 0.741, + "epoch": 0.6, + "learning_rate": 1.6358536314235103e-05, + "loss": 0.8047, "step": 1327 }, { - "epoch": 0.68, - "learning_rate": 1.5332653064925683e-05, - "loss": 0.8618, + "epoch": 0.61, + "learning_rate": 1.6352840099402084e-05, + "loss": 0.7969, "step": 1328 }, { - "epoch": 0.68, - "learning_rate": 1.532560742124408e-05, - "loss": 0.7507, + "epoch": 0.61, + "learning_rate": 1.6347140426319462e-05, + "loss": 0.8005, "step": 1329 }, { - "epoch": 0.68, - "learning_rate": 1.5318558085277103e-05, - "loss": 0.7627, + "epoch": 0.61, + "learning_rate": 1.6341437298089922e-05, + "loss": 0.7478, "step": 1330 }, { - "epoch": 0.68, - "learning_rate": 1.5311505061912123e-05, - "loss": 0.7468, + "epoch": 0.61, + "learning_rate": 1.6335730717818043e-05, + "loss": 0.7903, "step": 1331 }, { - "epoch": 0.68, - "learning_rate": 1.5304448356039054e-05, - "loss": 0.6926, + "epoch": 0.61, + "learning_rate": 1.633002068861027e-05, + "loss": 0.7944, "step": 1332 }, { - "epoch": 0.69, - "learning_rate": 1.5297387972550363e-05, - "loss": 0.7632, + "epoch": 0.61, + "learning_rate": 1.6324307213574934e-05, + "loss": 0.7883, "step": 1333 }, { - "epoch": 0.69, - "learning_rate": 1.5290323916341074e-05, - "loss": 0.7385, + "epoch": 0.61, + "learning_rate": 1.631859029582223e-05, + "loss": 0.7651, "step": 1334 }, { - "epoch": 0.69, - "learning_rate": 1.5283256192308744e-05, - "loss": 0.7996, + "epoch": 0.61, + "learning_rate": 1.6312869938464248e-05, + "loss": 0.7473, "step": 1335 }, { - "epoch": 0.69, - "learning_rate": 1.5276184805353492e-05, - "loss": 0.7981, + "epoch": 0.61, + "learning_rate": 1.6307146144614922e-05, + "loss": 0.8447, "step": 1336 }, { - "epoch": 0.69, - "learning_rate": 1.526910976037796e-05, - "loss": 0.8682, + "epoch": 0.61, + "learning_rate": 1.6301418917390088e-05, + "loss": 0.7469, "step": 1337 }, { - "epoch": 0.69, - "learning_rate": 1.526203106228733e-05, - "loss": 0.7568, + "epoch": 0.61, + "learning_rate": 1.629568825990742e-05, + "loss": 0.784, "step": 1338 }, { - "epoch": 0.69, - "learning_rate": 1.5254948715989324e-05, - "loss": 0.7671, + "epoch": 0.61, + "learning_rate": 1.6289954175286488e-05, + "loss": 0.733, "step": 1339 }, { - "epoch": 0.69, - "learning_rate": 1.5247862726394184e-05, - "loss": 0.7725, + "epoch": 0.61, + "learning_rate": 1.6284216666648705e-05, + "loss": 0.8311, "step": 1340 }, { - "epoch": 0.69, - "learning_rate": 1.5240773098414687e-05, - "loss": 0.7246, + "epoch": 0.61, + "learning_rate": 1.627847573711736e-05, + "loss": 0.7732, "step": 1341 }, { - "epoch": 0.69, - "learning_rate": 1.5233679836966122e-05, - "loss": 0.8093, + "epoch": 0.61, + "learning_rate": 1.6272731389817606e-05, + "loss": 0.7783, "step": 1342 }, { - "epoch": 0.69, - "learning_rate": 1.5226582946966306e-05, - "loss": 0.7365, + "epoch": 0.61, + "learning_rate": 1.6266983627876442e-05, + "loss": 0.7794, "step": 1343 }, { - "epoch": 0.69, - "learning_rate": 1.521948243333557e-05, - "loss": 0.7397, + "epoch": 0.61, + "learning_rate": 1.6261232454422744e-05, + "loss": 0.8364, "step": 1344 }, { - "epoch": 0.69, - "learning_rate": 1.5212378300996751e-05, - "loss": 0.7305, + "epoch": 0.61, + "learning_rate": 1.6255477872587234e-05, + "loss": 0.7888, "step": 1345 }, { - "epoch": 0.69, - "learning_rate": 1.5205270554875205e-05, - "loss": 0.8049, + "epoch": 0.61, + "learning_rate": 1.624971988550249e-05, + "loss": 0.7916, "step": 1346 }, { - "epoch": 0.69, - "learning_rate": 1.5198159199898785e-05, - "loss": 0.7622, + "epoch": 0.61, + "learning_rate": 1.624395849630295e-05, + "loss": 0.7524, "step": 1347 }, { - "epoch": 0.69, - "learning_rate": 1.5191044240997847e-05, - "loss": 0.7759, + "epoch": 0.61, + "learning_rate": 1.6238193708124894e-05, + "loss": 0.724, "step": 1348 }, { - "epoch": 0.69, - "learning_rate": 1.5183925683105254e-05, - "loss": 0.7588, + "epoch": 0.61, + "learning_rate": 1.623242552410646e-05, + "loss": 0.7781, "step": 1349 }, { - "epoch": 0.69, - "learning_rate": 1.517680353115635e-05, - "loss": 0.772, - "step": 1350 + "epoch": 0.62, + "learning_rate": 1.6226653947387642e-05, + "loss": 0.7572, + "step": 1350 }, { - "epoch": 0.69, - "learning_rate": 1.5169677790088986e-05, - "loss": 0.7615, + "epoch": 0.62, + "learning_rate": 1.6220878981110256e-05, + "loss": 0.7849, "step": 1351 }, { - "epoch": 0.69, - "learning_rate": 1.5162548464843491e-05, - "loss": 0.7495, + "epoch": 0.62, + "learning_rate": 1.621510062841799e-05, + "loss": 0.7354, "step": 1352 }, { - "epoch": 0.7, - "learning_rate": 1.5155415560362681e-05, - "loss": 0.7231, + "epoch": 0.62, + "learning_rate": 1.6209318892456356e-05, + "loss": 0.792, "step": 1353 }, { - "epoch": 0.7, - "learning_rate": 1.514827908159186e-05, - "loss": 0.7881, + "epoch": 0.62, + "learning_rate": 1.620353377637272e-05, + "loss": 0.7839, "step": 1354 }, { - "epoch": 0.7, - "learning_rate": 1.5141139033478796e-05, - "loss": 0.7668, + "epoch": 0.62, + "learning_rate": 1.6197745283316287e-05, + "loss": 0.8245, "step": 1355 }, { - "epoch": 0.7, - "learning_rate": 1.5133995420973746e-05, - "loss": 0.8, + "epoch": 0.62, + "learning_rate": 1.6191953416438092e-05, + "loss": 0.7556, "step": 1356 }, { - "epoch": 0.7, - "learning_rate": 1.5126848249029433e-05, - "loss": 0.7695, + "epoch": 0.62, + "learning_rate": 1.6186158178891013e-05, + "loss": 0.8447, "step": 1357 }, { - "epoch": 0.7, - "learning_rate": 1.5119697522601043e-05, - "loss": 0.7988, + "epoch": 0.62, + "learning_rate": 1.618035957382976e-05, + "loss": 0.7809, "step": 1358 }, { - "epoch": 0.7, - "learning_rate": 1.5112543246646237e-05, - "loss": 0.769, + "epoch": 0.62, + "learning_rate": 1.6174557604410885e-05, + "loss": 0.7385, "step": 1359 }, { - "epoch": 0.7, - "learning_rate": 1.5105385426125123e-05, - "loss": 0.7605, + "epoch": 0.62, + "learning_rate": 1.6168752273792753e-05, + "loss": 0.7761, "step": 1360 }, { - "epoch": 0.7, - "learning_rate": 1.5098224066000282e-05, - "loss": 0.7576, + "epoch": 0.62, + "learning_rate": 1.616294358513558e-05, + "loss": 0.8008, "step": 1361 }, { - "epoch": 0.7, - "learning_rate": 1.5091059171236734e-05, - "loss": 0.7107, + "epoch": 0.62, + "learning_rate": 1.6157131541601394e-05, + "loss": 0.7621, "step": 1362 }, { - "epoch": 0.7, - "learning_rate": 1.5083890746801962e-05, - "loss": 0.7595, + "epoch": 0.62, + "learning_rate": 1.6151316146354055e-05, + "loss": 0.7673, "step": 1363 }, { - "epoch": 0.7, - "learning_rate": 1.5076718797665888e-05, - "loss": 0.7246, + "epoch": 0.62, + "learning_rate": 1.614549740255925e-05, + "loss": 0.8115, "step": 1364 }, { - "epoch": 0.7, - "learning_rate": 1.5069543328800881e-05, - "loss": 0.8015, + "epoch": 0.62, + "learning_rate": 1.6139675313384486e-05, + "loss": 0.7877, "step": 1365 }, { - "epoch": 0.7, - "learning_rate": 1.5062364345181752e-05, - "loss": 0.7559, + "epoch": 0.62, + "learning_rate": 1.613384988199909e-05, + "loss": 0.7531, "step": 1366 }, { - "epoch": 0.7, - "learning_rate": 1.5055181851785743e-05, - "loss": 0.7625, + "epoch": 0.62, + "learning_rate": 1.6128021111574212e-05, + "loss": 0.7693, "step": 1367 }, { - "epoch": 0.7, - "learning_rate": 1.5047995853592533e-05, - "loss": 0.8071, + "epoch": 0.62, + "learning_rate": 1.6122189005282812e-05, + "loss": 0.7661, "step": 1368 }, { - "epoch": 0.7, - "learning_rate": 1.5040806355584235e-05, - "loss": 0.7981, + "epoch": 0.62, + "learning_rate": 1.6116353566299684e-05, + "loss": 0.7439, "step": 1369 }, { - "epoch": 0.7, - "learning_rate": 1.503361336274538e-05, - "loss": 0.7502, + "epoch": 0.62, + "learning_rate": 1.611051479780141e-05, + "loss": 0.8408, "step": 1370 }, { - "epoch": 0.7, - "learning_rate": 1.5026416880062932e-05, - "loss": 0.7791, + "epoch": 0.62, + "learning_rate": 1.6104672702966407e-05, + "loss": 0.8215, "step": 1371 }, { - "epoch": 0.71, - "learning_rate": 1.5019216912526262e-05, - "loss": 0.7483, + "epoch": 0.63, + "learning_rate": 1.609882728497489e-05, + "loss": 0.7213, "step": 1372 }, { - "epoch": 0.71, - "learning_rate": 1.5012013465127169e-05, - "loss": 0.7776, + "epoch": 0.63, + "learning_rate": 1.6092978547008886e-05, + "loss": 0.7404, "step": 1373 }, { - "epoch": 0.71, - "learning_rate": 1.5004806542859855e-05, - "loss": 0.7959, + "epoch": 0.63, + "learning_rate": 1.6087126492252233e-05, + "loss": 0.8068, "step": 1374 }, { - "epoch": 0.71, - "learning_rate": 1.4997596150720939e-05, - "loss": 0.7241, + "epoch": 0.63, + "learning_rate": 1.6081271123890575e-05, + "loss": 0.7915, "step": 1375 }, { - "epoch": 0.71, - "learning_rate": 1.4990382293709442e-05, - "loss": 0.835, + "epoch": 0.63, + "learning_rate": 1.6075412445111346e-05, + "loss": 0.6618, "step": 1376 }, { - "epoch": 0.71, - "learning_rate": 1.4983164976826788e-05, - "loss": 0.7388, + "epoch": 0.63, + "learning_rate": 1.6069550459103803e-05, + "loss": 0.7693, "step": 1377 }, { - "epoch": 0.71, - "learning_rate": 1.4975944205076796e-05, - "loss": 0.668, + "epoch": 0.63, + "learning_rate": 1.6063685169058983e-05, + "loss": 0.8225, "step": 1378 }, { - "epoch": 0.71, - "learning_rate": 1.4968719983465687e-05, - "loss": 0.7288, + "epoch": 0.63, + "learning_rate": 1.6057816578169742e-05, + "loss": 0.8318, "step": 1379 }, { - "epoch": 0.71, - "learning_rate": 1.496149231700207e-05, - "loss": 0.697, + "epoch": 0.63, + "learning_rate": 1.6051944689630717e-05, + "loss": 0.7661, "step": 1380 }, { - "epoch": 0.71, - "learning_rate": 1.4954261210696945e-05, - "loss": 0.7683, + "epoch": 0.63, + "learning_rate": 1.6046069506638345e-05, + "loss": 0.7817, "step": 1381 }, { - "epoch": 0.71, - "learning_rate": 1.4947026669563687e-05, - "loss": 0.7258, + "epoch": 0.63, + "learning_rate": 1.604019103239086e-05, + "loss": 0.7583, "step": 1382 }, { - "epoch": 0.71, - "learning_rate": 1.493978869861807e-05, - "loss": 0.7571, + "epoch": 0.63, + "learning_rate": 1.603430927008828e-05, + "loss": 0.7883, "step": 1383 }, { - "epoch": 0.71, - "learning_rate": 1.4932547302878228e-05, - "loss": 0.772, + "epoch": 0.63, + "learning_rate": 1.602842422293242e-05, + "loss": 0.7345, "step": 1384 }, { - "epoch": 0.71, - "learning_rate": 1.4925302487364684e-05, - "loss": 0.7563, + "epoch": 0.63, + "learning_rate": 1.602253589412688e-05, + "loss": 0.7876, "step": 1385 }, { - "epoch": 0.71, - "learning_rate": 1.491805425710032e-05, - "loss": 0.7622, + "epoch": 0.63, + "learning_rate": 1.601664428687705e-05, + "loss": 0.6794, "step": 1386 }, { - "epoch": 0.71, - "learning_rate": 1.4910802617110392e-05, - "loss": 0.7617, + "epoch": 0.63, + "learning_rate": 1.6010749404390097e-05, + "loss": 0.7668, "step": 1387 }, { - "epoch": 0.71, - "learning_rate": 1.490354757242252e-05, - "loss": 0.7456, + "epoch": 0.63, + "learning_rate": 1.6004851249874976e-05, + "loss": 0.6643, "step": 1388 }, { - "epoch": 0.71, - "learning_rate": 1.4896289128066684e-05, - "loss": 0.7505, + "epoch": 0.63, + "learning_rate": 1.599894982654243e-05, + "loss": 0.7584, "step": 1389 }, { - "epoch": 0.71, - "learning_rate": 1.4889027289075218e-05, - "loss": 0.8069, + "epoch": 0.63, + "learning_rate": 1.599304513760496e-05, + "loss": 0.7634, "step": 1390 }, { - "epoch": 0.71, - "learning_rate": 1.4881762060482814e-05, - "loss": 0.7375, + "epoch": 0.63, + "learning_rate": 1.5987137186276873e-05, + "loss": 0.7808, "step": 1391 }, { - "epoch": 0.72, - "learning_rate": 1.4874493447326513e-05, - "loss": 0.7798, + "epoch": 0.63, + "learning_rate": 1.5981225975774227e-05, + "loss": 0.8133, "step": 1392 }, { - "epoch": 0.72, - "learning_rate": 1.4867221454645696e-05, - "loss": 0.7534, + "epoch": 0.63, + "learning_rate": 1.5975311509314876e-05, + "loss": 0.785, "step": 1393 }, { - "epoch": 0.72, - "learning_rate": 1.4859946087482097e-05, - "loss": 0.7195, + "epoch": 0.64, + "learning_rate": 1.5969393790118422e-05, + "loss": 0.8152, "step": 1394 }, { - "epoch": 0.72, - "learning_rate": 1.4852667350879787e-05, - "loss": 0.8042, + "epoch": 0.64, + "learning_rate": 1.5963472821406264e-05, + "loss": 0.8171, "step": 1395 }, { - "epoch": 0.72, - "learning_rate": 1.484538524988517e-05, - "loss": 0.728, + "epoch": 0.64, + "learning_rate": 1.5957548606401548e-05, + "loss": 0.7686, "step": 1396 }, { - "epoch": 0.72, - "learning_rate": 1.4838099789546976e-05, - "loss": 0.759, + "epoch": 0.64, + "learning_rate": 1.5951621148329197e-05, + "loss": 0.7163, "step": 1397 }, { - "epoch": 0.72, - "learning_rate": 1.483081097491628e-05, - "loss": 0.7891, + "epoch": 0.64, + "learning_rate": 1.59456904504159e-05, + "loss": 0.7759, "step": 1398 }, { - "epoch": 0.72, - "learning_rate": 1.4823518811046474e-05, - "loss": 0.7856, + "epoch": 0.64, + "learning_rate": 1.593975651589011e-05, + "loss": 0.7615, "step": 1399 }, { - "epoch": 0.72, - "learning_rate": 1.4816223302993269e-05, - "loss": 0.7844, + "epoch": 0.64, + "learning_rate": 1.593381934798204e-05, + "loss": 0.7585, "step": 1400 }, { - "epoch": 0.72, - "learning_rate": 1.4808924455814701e-05, - "loss": 0.7231, + "epoch": 0.64, + "learning_rate": 1.592787894992366e-05, + "loss": 0.738, "step": 1401 }, { - "epoch": 0.72, - "learning_rate": 1.4801622274571114e-05, - "loss": 0.7605, + "epoch": 0.64, + "learning_rate": 1.5921935324948706e-05, + "loss": 0.7183, "step": 1402 }, { - "epoch": 0.72, - "learning_rate": 1.4794316764325174e-05, - "loss": 0.7463, + "epoch": 0.64, + "learning_rate": 1.5915988476292662e-05, + "loss": 0.7839, "step": 1403 }, { - "epoch": 0.72, - "learning_rate": 1.4787007930141841e-05, - "loss": 0.7185, + "epoch": 0.64, + "learning_rate": 1.5910038407192772e-05, + "loss": 0.8025, "step": 1404 }, { - "epoch": 0.72, - "learning_rate": 1.4779695777088392e-05, - "loss": 0.7659, + "epoch": 0.64, + "learning_rate": 1.5904085120888032e-05, + "loss": 0.772, "step": 1405 }, { - "epoch": 0.72, - "learning_rate": 1.4772380310234397e-05, - "loss": 0.7544, + "epoch": 0.64, + "learning_rate": 1.5898128620619187e-05, + "loss": 0.7979, "step": 1406 }, { - "epoch": 0.72, - "learning_rate": 1.4765061534651728e-05, - "loss": 0.7671, + "epoch": 0.64, + "learning_rate": 1.589216890962874e-05, + "loss": 0.7073, "step": 1407 }, { - "epoch": 0.72, - "learning_rate": 1.4757739455414553e-05, - "loss": 0.8091, + "epoch": 0.64, + "learning_rate": 1.588620599116093e-05, + "loss": 0.7537, "step": 1408 }, { - "epoch": 0.72, - "learning_rate": 1.4750414077599318e-05, - "loss": 0.7905, + "epoch": 0.64, + "learning_rate": 1.5880239868461753e-05, + "loss": 0.7959, "step": 1409 }, { - "epoch": 0.72, - "learning_rate": 1.4743085406284774e-05, - "loss": 0.7493, + "epoch": 0.64, + "learning_rate": 1.587427054477894e-05, + "loss": 0.8145, "step": 1410 }, { - "epoch": 0.73, - "learning_rate": 1.4735753446551941e-05, - "loss": 0.771, + "epoch": 0.64, + "learning_rate": 1.586829802336197e-05, + "loss": 0.7712, "step": 1411 }, { - "epoch": 0.73, - "learning_rate": 1.4728418203484125e-05, - "loss": 0.7512, + "epoch": 0.64, + "learning_rate": 1.5862322307462063e-05, + "loss": 0.7737, "step": 1412 }, { - "epoch": 0.73, - "learning_rate": 1.472107968216691e-05, - "loss": 0.7668, + "epoch": 0.64, + "learning_rate": 1.585634340033217e-05, + "loss": 0.7419, "step": 1413 }, { - "epoch": 0.73, - "learning_rate": 1.4713737887688146e-05, - "loss": 0.741, + "epoch": 0.64, + "learning_rate": 1.585036130522699e-05, + "loss": 0.7594, "step": 1414 }, { - "epoch": 0.73, - "learning_rate": 1.4706392825137962e-05, - "loss": 0.6943, + "epoch": 0.64, + "learning_rate": 1.584437602540296e-05, + "loss": 0.8027, "step": 1415 }, { - "epoch": 0.73, - "learning_rate": 1.4699044499608745e-05, - "loss": 0.781, + "epoch": 0.65, + "learning_rate": 1.5838387564118226e-05, + "loss": 0.8066, "step": 1416 }, { - "epoch": 0.73, - "learning_rate": 1.4691692916195144e-05, - "loss": 0.7075, + "epoch": 0.65, + "learning_rate": 1.58323959246327e-05, + "loss": 0.7571, "step": 1417 }, { - "epoch": 0.73, - "learning_rate": 1.4684338079994071e-05, - "loss": 0.7585, + "epoch": 0.65, + "learning_rate": 1.5826401110208e-05, + "loss": 0.7581, "step": 1418 }, { - "epoch": 0.73, - "learning_rate": 1.4676979996104694e-05, - "loss": 0.7407, + "epoch": 0.65, + "learning_rate": 1.5820403124107478e-05, + "loss": 0.8401, "step": 1419 }, { - "epoch": 0.73, - "learning_rate": 1.4669618669628429e-05, - "loss": 0.7267, + "epoch": 0.65, + "learning_rate": 1.5814401969596218e-05, + "loss": 0.7454, "step": 1420 }, { - "epoch": 0.73, - "learning_rate": 1.466225410566894e-05, - "loss": 0.7427, + "epoch": 0.65, + "learning_rate": 1.5808397649941026e-05, + "loss": 0.8064, "step": 1421 }, { - "epoch": 0.73, - "learning_rate": 1.4654886309332137e-05, - "loss": 0.7773, + "epoch": 0.65, + "learning_rate": 1.5802390168410427e-05, + "loss": 0.7833, "step": 1422 }, { - "epoch": 0.73, - "learning_rate": 1.4647515285726173e-05, - "loss": 0.7361, + "epoch": 0.65, + "learning_rate": 1.579637952827467e-05, + "loss": 0.774, "step": 1423 }, { - "epoch": 0.73, - "learning_rate": 1.4640141039961433e-05, - "loss": 0.7854, + "epoch": 0.65, + "learning_rate": 1.5790365732805724e-05, + "loss": 0.7573, "step": 1424 }, { - "epoch": 0.73, - "learning_rate": 1.4632763577150544e-05, - "loss": 0.7476, + "epoch": 0.65, + "learning_rate": 1.5784348785277278e-05, + "loss": 0.7664, "step": 1425 }, { - "epoch": 0.73, - "learning_rate": 1.4625382902408356e-05, - "loss": 0.7383, + "epoch": 0.65, + "learning_rate": 1.577832868896473e-05, + "loss": 0.7825, "step": 1426 }, { - "epoch": 0.73, - "learning_rate": 1.4617999020851947e-05, - "loss": 0.772, + "epoch": 0.65, + "learning_rate": 1.5772305447145205e-05, + "loss": 0.825, "step": 1427 }, { - "epoch": 0.73, - "learning_rate": 1.4610611937600623e-05, - "loss": 0.7947, + "epoch": 0.65, + "learning_rate": 1.576627906309752e-05, + "loss": 0.6926, "step": 1428 }, { - "epoch": 0.73, - "learning_rate": 1.4603221657775905e-05, - "loss": 0.7329, + "epoch": 0.65, + "learning_rate": 1.576024954010222e-05, + "loss": 0.7827, "step": 1429 }, { - "epoch": 0.74, - "learning_rate": 1.4595828186501532e-05, - "loss": 0.7229, + "epoch": 0.65, + "learning_rate": 1.5754216881441556e-05, + "loss": 0.7347, "step": 1430 }, { - "epoch": 0.74, - "learning_rate": 1.458843152890346e-05, - "loss": 0.7708, + "epoch": 0.65, + "learning_rate": 1.5748181090399474e-05, + "loss": 0.6939, "step": 1431 }, { - "epoch": 0.74, - "learning_rate": 1.4581031690109841e-05, - "loss": 0.7502, + "epoch": 0.65, + "learning_rate": 1.574214217026164e-05, + "loss": 0.824, "step": 1432 }, { - "epoch": 0.74, - "learning_rate": 1.4573628675251051e-05, - "loss": 0.7231, + "epoch": 0.65, + "learning_rate": 1.5736100124315417e-05, + "loss": 0.7413, "step": 1433 }, { - "epoch": 0.74, - "learning_rate": 1.4566222489459647e-05, - "loss": 0.7859, + "epoch": 0.65, + "learning_rate": 1.573005495584987e-05, + "loss": 0.7979, "step": 1434 }, { - "epoch": 0.74, - "learning_rate": 1.4558813137870407e-05, - "loss": 0.7874, + "epoch": 0.65, + "learning_rate": 1.5724006668155757e-05, + "loss": 0.7075, "step": 1435 }, { - "epoch": 0.74, - "learning_rate": 1.4551400625620287e-05, - "loss": 0.7283, + "epoch": 0.65, + "learning_rate": 1.571795526452555e-05, + "loss": 0.7957, "step": 1436 }, { - "epoch": 0.74, - "learning_rate": 1.4543984957848438e-05, - "loss": 0.7637, + "epoch": 0.65, + "learning_rate": 1.571190074825341e-05, + "loss": 0.7806, "step": 1437 }, { - "epoch": 0.74, - "learning_rate": 1.4536566139696207e-05, - "loss": 0.7051, + "epoch": 0.66, + "learning_rate": 1.5705843122635177e-05, + "loss": 0.7605, "step": 1438 }, { - "epoch": 0.74, - "learning_rate": 1.4529144176307108e-05, - "loss": 0.7971, + "epoch": 0.66, + "learning_rate": 1.5699782390968405e-05, + "loss": 0.729, "step": 1439 }, { - "epoch": 0.74, - "learning_rate": 1.4521719072826858e-05, - "loss": 0.7817, + "epoch": 0.66, + "learning_rate": 1.569371855655233e-05, + "loss": 0.7659, "step": 1440 }, { - "epoch": 0.74, - "learning_rate": 1.4514290834403336e-05, - "loss": 0.7383, + "epoch": 0.66, + "learning_rate": 1.5687651622687877e-05, + "loss": 0.731, "step": 1441 }, { - "epoch": 0.74, - "learning_rate": 1.4506859466186591e-05, - "loss": 0.8447, + "epoch": 0.66, + "learning_rate": 1.568158159267766e-05, + "loss": 0.7771, "step": 1442 }, { - "epoch": 0.74, - "learning_rate": 1.4499424973328857e-05, - "loss": 0.783, + "epoch": 0.66, + "learning_rate": 1.567550846982598e-05, + "loss": 0.7366, "step": 1443 }, { - "epoch": 0.74, - "learning_rate": 1.4491987360984524e-05, - "loss": 0.7617, + "epoch": 0.66, + "learning_rate": 1.566943225743881e-05, + "loss": 0.7396, "step": 1444 }, { - "epoch": 0.74, - "learning_rate": 1.4484546634310146e-05, - "loss": 0.79, + "epoch": 0.66, + "learning_rate": 1.5663352958823822e-05, + "loss": 0.8162, "step": 1445 }, { - "epoch": 0.74, - "learning_rate": 1.4477102798464437e-05, - "loss": 0.7639, + "epoch": 0.66, + "learning_rate": 1.5657270577290356e-05, + "loss": 0.7861, "step": 1446 }, { - "epoch": 0.74, - "learning_rate": 1.4469655858608267e-05, - "loss": 0.7249, + "epoch": 0.66, + "learning_rate": 1.5651185116149436e-05, + "loss": 0.8267, "step": 1447 }, { - "epoch": 0.74, - "learning_rate": 1.4462205819904658e-05, - "loss": 0.7288, + "epoch": 0.66, + "learning_rate": 1.564509657871376e-05, + "loss": 0.7847, "step": 1448 }, { - "epoch": 0.74, - "learning_rate": 1.4454752687518782e-05, - "loss": 0.7585, + "epoch": 0.66, + "learning_rate": 1.56390049682977e-05, + "loss": 0.7771, "step": 1449 }, { - "epoch": 0.75, - "learning_rate": 1.444729646661795e-05, - "loss": 0.7798, + "epoch": 0.66, + "learning_rate": 1.5632910288217304e-05, + "loss": 0.7656, "step": 1450 }, { - "epoch": 0.75, - "learning_rate": 1.4439837162371623e-05, - "loss": 0.7874, + "epoch": 0.66, + "learning_rate": 1.5626812541790287e-05, + "loss": 0.7686, "step": 1451 }, { - "epoch": 0.75, - "learning_rate": 1.4432374779951392e-05, - "loss": 0.7454, + "epoch": 0.66, + "learning_rate": 1.5620711732336034e-05, + "loss": 0.761, "step": 1452 }, { - "epoch": 0.75, - "learning_rate": 1.4424909324530985e-05, - "loss": 0.7589, + "epoch": 0.66, + "learning_rate": 1.56146078631756e-05, + "loss": 0.7881, "step": 1453 }, { - "epoch": 0.75, - "learning_rate": 1.4417440801286263e-05, - "loss": 0.7148, + "epoch": 0.66, + "learning_rate": 1.5608500937631705e-05, + "loss": 0.7573, "step": 1454 }, { - "epoch": 0.75, - "learning_rate": 1.440996921539521e-05, - "loss": 0.7571, + "epoch": 0.66, + "learning_rate": 1.5602390959028732e-05, + "loss": 0.7859, "step": 1455 }, { - "epoch": 0.75, - "learning_rate": 1.4402494572037934e-05, - "loss": 0.7385, + "epoch": 0.66, + "learning_rate": 1.5596277930692723e-05, + "loss": 0.7549, "step": 1456 }, { - "epoch": 0.75, - "learning_rate": 1.4395016876396666e-05, - "loss": 0.7698, + "epoch": 0.66, + "learning_rate": 1.5590161855951386e-05, + "loss": 0.7599, "step": 1457 }, { - "epoch": 0.75, - "learning_rate": 1.438753613365575e-05, - "loss": 0.7214, + "epoch": 0.66, + "learning_rate": 1.5584042738134085e-05, + "loss": 0.7354, "step": 1458 }, { - "epoch": 0.75, - "learning_rate": 1.4380052349001647e-05, - "loss": 0.7397, + "epoch": 0.66, + "learning_rate": 1.5577920580571835e-05, + "loss": 0.7981, "step": 1459 }, { - "epoch": 0.75, - "learning_rate": 1.437256552762292e-05, - "loss": 0.7896, + "epoch": 0.67, + "learning_rate": 1.5571795386597318e-05, + "loss": 0.7339, "step": 1460 }, { - "epoch": 0.75, - "learning_rate": 1.4365075674710238e-05, - "loss": 0.6931, + "epoch": 0.67, + "learning_rate": 1.556566715954485e-05, + "loss": 0.7533, "step": 1461 }, { - "epoch": 0.75, - "learning_rate": 1.435758279545638e-05, - "loss": 0.8064, + "epoch": 0.67, + "learning_rate": 1.5559535902750424e-05, + "loss": 0.7554, "step": 1462 }, { - "epoch": 0.75, - "learning_rate": 1.4350086895056214e-05, - "loss": 0.7812, + "epoch": 0.67, + "learning_rate": 1.5553401619551657e-05, + "loss": 0.7527, "step": 1463 }, { - "epoch": 0.75, - "learning_rate": 1.4342587978706713e-05, - "loss": 0.7539, + "epoch": 0.67, + "learning_rate": 1.5547264313287832e-05, + "loss": 0.7615, "step": 1464 }, { - "epoch": 0.75, - "learning_rate": 1.4335086051606928e-05, - "loss": 0.7799, + "epoch": 0.67, + "learning_rate": 1.5541123987299864e-05, + "loss": 0.801, "step": 1465 }, { - "epoch": 0.75, - "learning_rate": 1.4327581118958005e-05, + "epoch": 0.67, + "learning_rate": 1.553498064493032e-05, "loss": 0.7441, "step": 1466 }, { - "epoch": 0.75, - "learning_rate": 1.4320073185963175e-05, - "loss": 0.7322, + "epoch": 0.67, + "learning_rate": 1.5528834289523406e-05, + "loss": 0.7961, "step": 1467 }, { - "epoch": 0.75, - "learning_rate": 1.4312562257827742e-05, - "loss": 0.7151, + "epoch": 0.67, + "learning_rate": 1.5522684924424968e-05, + "loss": 0.7231, "step": 1468 }, { - "epoch": 0.76, - "learning_rate": 1.4305048339759099e-05, - "loss": 0.7632, + "epoch": 0.67, + "learning_rate": 1.55165325529825e-05, + "loss": 0.7419, "step": 1469 }, { - "epoch": 0.76, - "learning_rate": 1.42975314369667e-05, - "loss": 0.7407, + "epoch": 0.67, + "learning_rate": 1.551037717854511e-05, + "loss": 0.7355, "step": 1470 }, { - "epoch": 0.76, - "learning_rate": 1.4290011554662069e-05, - "loss": 0.7822, + "epoch": 0.67, + "learning_rate": 1.5504218804463564e-05, + "loss": 0.7076, "step": 1471 }, { - "epoch": 0.76, - "learning_rate": 1.4282488698058803e-05, - "loss": 0.7966, + "epoch": 0.67, + "learning_rate": 1.5498057434090252e-05, + "loss": 0.7507, "step": 1472 }, { - "epoch": 0.76, - "learning_rate": 1.427496287237256e-05, - "loss": 0.7705, + "epoch": 0.67, + "learning_rate": 1.549189307077919e-05, + "loss": 0.731, "step": 1473 }, { - "epoch": 0.76, - "learning_rate": 1.426743408282105e-05, - "loss": 0.7502, + "epoch": 0.67, + "learning_rate": 1.5485725717886032e-05, + "loss": 0.7389, "step": 1474 }, { - "epoch": 0.76, - "learning_rate": 1.4259902334624043e-05, - "loss": 0.7627, + "epoch": 0.67, + "learning_rate": 1.547955537876805e-05, + "loss": 0.7357, "step": 1475 }, { - "epoch": 0.76, - "learning_rate": 1.4252367633003358e-05, - "loss": 0.761, + "epoch": 0.67, + "learning_rate": 1.547338205678415e-05, + "loss": 0.7358, "step": 1476 }, { - "epoch": 0.76, - "learning_rate": 1.4244829983182866e-05, - "loss": 0.7751, + "epoch": 0.67, + "learning_rate": 1.5467205755294865e-05, + "loss": 0.7725, "step": 1477 }, { - "epoch": 0.76, - "learning_rate": 1.4237289390388476e-05, - "loss": 0.7483, + "epoch": 0.67, + "learning_rate": 1.546102647766233e-05, + "loss": 0.791, "step": 1478 }, { - "epoch": 0.76, - "learning_rate": 1.422974585984814e-05, - "loss": 0.7427, + "epoch": 0.67, + "learning_rate": 1.5454844227250324e-05, + "loss": 0.7118, "step": 1479 }, { - "epoch": 0.76, - "learning_rate": 1.4222199396791849e-05, - "loss": 0.8206, + "epoch": 0.67, + "learning_rate": 1.544865900742423e-05, + "loss": 0.752, "step": 1480 }, { - "epoch": 0.76, - "learning_rate": 1.4214650006451622e-05, - "loss": 0.729, + "epoch": 0.67, + "learning_rate": 1.5442470821551053e-05, + "loss": 0.7644, "step": 1481 }, { - "epoch": 0.76, - "learning_rate": 1.4207097694061514e-05, - "loss": 0.7676, + "epoch": 0.68, + "learning_rate": 1.543627967299941e-05, + "loss": 0.7035, "step": 1482 }, { - "epoch": 0.76, - "learning_rate": 1.4199542464857597e-05, - "loss": 0.7224, + "epoch": 0.68, + "learning_rate": 1.543008556513953e-05, + "loss": 0.7366, "step": 1483 }, { - "epoch": 0.76, - "learning_rate": 1.4191984324077977e-05, - "loss": 0.7341, + "epoch": 0.68, + "learning_rate": 1.542388850134326e-05, + "loss": 0.78, "step": 1484 }, { - "epoch": 0.76, - "learning_rate": 1.4184423276962766e-05, - "loss": 0.7563, + "epoch": 0.68, + "learning_rate": 1.5417688484984042e-05, + "loss": 0.7693, "step": 1485 }, { - "epoch": 0.76, - "learning_rate": 1.4176859328754103e-05, - "loss": 0.7412, + "epoch": 0.68, + "learning_rate": 1.5411485519436946e-05, + "loss": 0.7566, "step": 1486 }, { - "epoch": 0.76, - "learning_rate": 1.4169292484696132e-05, - "loss": 0.8296, + "epoch": 0.68, + "learning_rate": 1.5405279608078626e-05, + "loss": 0.7086, "step": 1487 }, { - "epoch": 0.76, - "learning_rate": 1.4161722750034997e-05, - "loss": 0.7805, + "epoch": 0.68, + "learning_rate": 1.539907075428735e-05, + "loss": 0.757, "step": 1488 }, { - "epoch": 0.77, - "learning_rate": 1.4154150130018867e-05, - "loss": 0.7073, + "epoch": 0.68, + "learning_rate": 1.539285896144299e-05, + "loss": 0.7533, "step": 1489 }, { - "epoch": 0.77, - "learning_rate": 1.414657462989789e-05, - "loss": 0.7625, + "epoch": 0.68, + "learning_rate": 1.5386644232927013e-05, + "loss": 0.7542, "step": 1490 }, { - "epoch": 0.77, - "learning_rate": 1.413899625492422e-05, - "loss": 0.7949, + "epoch": 0.68, + "learning_rate": 1.5380426572122492e-05, + "loss": 0.7594, "step": 1491 }, { - "epoch": 0.77, - "learning_rate": 1.4131415010352007e-05, - "loss": 0.7688, + "epoch": 0.68, + "learning_rate": 1.5374205982414077e-05, + "loss": 0.7515, "step": 1492 }, { - "epoch": 0.77, - "learning_rate": 1.4123830901437388e-05, - "loss": 0.7576, + "epoch": 0.68, + "learning_rate": 1.5367982467188035e-05, + "loss": 0.7495, "step": 1493 }, { - "epoch": 0.77, - "learning_rate": 1.4116243933438483e-05, - "loss": 0.7886, + "epoch": 0.68, + "learning_rate": 1.5361756029832215e-05, + "loss": 0.7456, "step": 1494 }, { - "epoch": 0.77, - "learning_rate": 1.4108654111615397e-05, - "loss": 0.7283, + "epoch": 0.68, + "learning_rate": 1.5355526673736054e-05, + "loss": 0.7196, "step": 1495 }, { - "epoch": 0.77, - "learning_rate": 1.4101061441230209e-05, - "loss": 0.7219, + "epoch": 0.68, + "learning_rate": 1.5349294402290586e-05, + "loss": 0.8005, "step": 1496 }, { - "epoch": 0.77, - "learning_rate": 1.4093465927546984e-05, - "loss": 0.7495, + "epoch": 0.68, + "learning_rate": 1.5343059218888425e-05, + "loss": 0.8103, "step": 1497 }, { - "epoch": 0.77, - "learning_rate": 1.4085867575831744e-05, - "loss": 0.7557, + "epoch": 0.68, + "learning_rate": 1.533682112692377e-05, + "loss": 0.8428, "step": 1498 }, { - "epoch": 0.77, - "learning_rate": 1.4078266391352494e-05, - "loss": 0.8093, + "epoch": 0.68, + "learning_rate": 1.5330580129792414e-05, + "loss": 0.7744, "step": 1499 }, { - "epoch": 0.77, - "learning_rate": 1.407066237937919e-05, - "loss": 0.7412, + "epoch": 0.68, + "learning_rate": 1.5324336230891715e-05, + "loss": 0.8, "step": 1500 }, { - "epoch": 0.77, - "learning_rate": 1.406305554518375e-05, - "loss": 0.7444, + "epoch": 0.68, + "learning_rate": 1.5318089433620626e-05, + "loss": 0.7103, "step": 1501 }, { - "epoch": 0.77, - "learning_rate": 1.4055445894040056e-05, - "loss": 0.7195, + "epoch": 0.68, + "learning_rate": 1.5311839741379663e-05, + "loss": 0.8059, "step": 1502 }, { - "epoch": 0.77, - "learning_rate": 1.4047833431223938e-05, - "loss": 0.7483, + "epoch": 0.68, + "learning_rate": 1.5305587157570933e-05, + "loss": 0.7207, "step": 1503 }, { - "epoch": 0.77, - "learning_rate": 1.404021816201318e-05, - "loss": 0.811, + "epoch": 0.69, + "learning_rate": 1.5299331685598106e-05, + "loss": 0.6924, "step": 1504 }, { - "epoch": 0.77, - "learning_rate": 1.40326000916875e-05, - "loss": 0.7354, + "epoch": 0.69, + "learning_rate": 1.529307332886643e-05, + "loss": 0.8118, "step": 1505 }, { - "epoch": 0.77, - "learning_rate": 1.402497922552857e-05, - "loss": 0.7273, + "epoch": 0.69, + "learning_rate": 1.5286812090782718e-05, + "loss": 0.7559, "step": 1506 }, { - "epoch": 0.77, - "learning_rate": 1.4017355568819996e-05, - "loss": 0.7563, + "epoch": 0.69, + "learning_rate": 1.528054797475536e-05, + "loss": 0.8171, "step": 1507 }, { - "epoch": 0.78, - "learning_rate": 1.4009729126847317e-05, - "loss": 0.7407, + "epoch": 0.69, + "learning_rate": 1.5274280984194306e-05, + "loss": 0.7546, "step": 1508 }, { - "epoch": 0.78, - "learning_rate": 1.4002099904898011e-05, - "loss": 0.7063, + "epoch": 0.69, + "learning_rate": 1.5268011122511065e-05, + "loss": 0.7495, "step": 1509 }, { - "epoch": 0.78, - "learning_rate": 1.3994467908261474e-05, - "loss": 0.7546, + "epoch": 0.69, + "learning_rate": 1.5261738393118732e-05, + "loss": 0.7739, "step": 1510 }, { - "epoch": 0.78, - "learning_rate": 1.3986833142229024e-05, - "loss": 0.7769, + "epoch": 0.69, + "learning_rate": 1.5255462799431931e-05, + "loss": 0.7634, "step": 1511 }, { - "epoch": 0.78, - "learning_rate": 1.397919561209391e-05, - "loss": 0.7896, + "epoch": 0.69, + "learning_rate": 1.5249184344866867e-05, + "loss": 0.7351, "step": 1512 }, { - "epoch": 0.78, - "learning_rate": 1.3971555323151291e-05, - "loss": 0.7395, + "epoch": 0.69, + "learning_rate": 1.5242903032841301e-05, + "loss": 0.6992, "step": 1513 }, { - "epoch": 0.78, - "learning_rate": 1.3963912280698238e-05, - "loss": 0.7109, + "epoch": 0.69, + "learning_rate": 1.5236618866774543e-05, + "loss": 0.8047, "step": 1514 }, { - "epoch": 0.78, - "learning_rate": 1.3956266490033731e-05, - "loss": 0.7104, + "epoch": 0.69, + "learning_rate": 1.5230331850087457e-05, + "loss": 0.7263, "step": 1515 }, { - "epoch": 0.78, - "learning_rate": 1.3948617956458659e-05, - "loss": 0.7646, + "epoch": 0.69, + "learning_rate": 1.522404198620246e-05, + "loss": 0.8298, "step": 1516 }, { - "epoch": 0.78, - "learning_rate": 1.3940966685275812e-05, - "loss": 0.6914, + "epoch": 0.69, + "learning_rate": 1.5217749278543526e-05, + "loss": 0.7769, "step": 1517 }, { - "epoch": 0.78, - "learning_rate": 1.3933312681789867e-05, - "loss": 0.7612, + "epoch": 0.69, + "learning_rate": 1.5211453730536166e-05, + "loss": 0.7567, "step": 1518 }, { - "epoch": 0.78, - "learning_rate": 1.3925655951307417e-05, - "loss": 0.8008, + "epoch": 0.69, + "learning_rate": 1.520515534560744e-05, + "loss": 0.8118, "step": 1519 }, { - "epoch": 0.78, - "learning_rate": 1.3917996499136928e-05, - "loss": 0.752, + "epoch": 0.69, + "learning_rate": 1.5198854127185958e-05, + "loss": 0.7372, "step": 1520 }, { - "epoch": 0.78, - "learning_rate": 1.3910334330588753e-05, - "loss": 0.6926, + "epoch": 0.69, + "learning_rate": 1.519255007870187e-05, + "loss": 0.7362, "step": 1521 }, { - "epoch": 0.78, - "learning_rate": 1.3902669450975139e-05, - "loss": 0.759, + "epoch": 0.69, + "learning_rate": 1.5186243203586859e-05, + "loss": 0.7258, "step": 1522 }, { - "epoch": 0.78, - "learning_rate": 1.3895001865610209e-05, - "loss": 0.7307, + "epoch": 0.69, + "learning_rate": 1.5179933505274157e-05, + "loss": 0.7637, "step": 1523 }, { - "epoch": 0.78, - "learning_rate": 1.3887331579809958e-05, - "loss": 0.7961, + "epoch": 0.69, + "learning_rate": 1.5173620987198534e-05, + "loss": 0.8101, "step": 1524 }, { - "epoch": 0.78, - "learning_rate": 1.3879658598892254e-05, - "loss": 0.7212, + "epoch": 0.69, + "learning_rate": 1.516730565279628e-05, + "loss": 0.8091, "step": 1525 }, { - "epoch": 0.78, - "learning_rate": 1.3871982928176833e-05, - "loss": 0.7625, + "epoch": 0.7, + "learning_rate": 1.5160987505505232e-05, + "loss": 0.7058, "step": 1526 }, { - "epoch": 0.78, - "learning_rate": 1.3864304572985301e-05, - "loss": 0.738, + "epoch": 0.7, + "learning_rate": 1.5154666548764758e-05, + "loss": 0.7584, "step": 1527 }, { - "epoch": 0.79, - "learning_rate": 1.3856623538641121e-05, - "loss": 0.7969, + "epoch": 0.7, + "learning_rate": 1.5148342786015743e-05, + "loss": 0.7561, "step": 1528 }, { - "epoch": 0.79, - "learning_rate": 1.3848939830469617e-05, - "loss": 0.7258, + "epoch": 0.7, + "learning_rate": 1.5142016220700617e-05, + "loss": 0.7424, "step": 1529 }, { - "epoch": 0.79, - "learning_rate": 1.3841253453797958e-05, - "loss": 0.7922, + "epoch": 0.7, + "learning_rate": 1.5135686856263321e-05, + "loss": 0.7495, "step": 1530 }, { - "epoch": 0.79, - "learning_rate": 1.3833564413955171e-05, - "loss": 0.7744, + "epoch": 0.7, + "learning_rate": 1.5129354696149325e-05, + "loss": 0.6814, "step": 1531 }, { - "epoch": 0.79, - "learning_rate": 1.3825872716272134e-05, - "loss": 0.7468, + "epoch": 0.7, + "learning_rate": 1.5123019743805624e-05, + "loss": 0.7388, "step": 1532 }, { - "epoch": 0.79, - "learning_rate": 1.3818178366081552e-05, - "loss": 0.7239, + "epoch": 0.7, + "learning_rate": 1.5116682002680732e-05, + "loss": 0.7834, "step": 1533 }, { - "epoch": 0.79, - "learning_rate": 1.3810481368717988e-05, - "loss": 0.7617, + "epoch": 0.7, + "learning_rate": 1.5110341476224673e-05, + "loss": 0.8286, "step": 1534 }, { - "epoch": 0.79, - "learning_rate": 1.380278172951782e-05, - "loss": 0.7594, + "epoch": 0.7, + "learning_rate": 1.5103998167888999e-05, + "loss": 0.7936, "step": 1535 }, { - "epoch": 0.79, - "learning_rate": 1.3795079453819276e-05, - "loss": 0.7688, + "epoch": 0.7, + "learning_rate": 1.5097652081126766e-05, + "loss": 0.813, "step": 1536 }, { - "epoch": 0.79, - "learning_rate": 1.37873745469624e-05, - "loss": 0.7153, + "epoch": 0.7, + "learning_rate": 1.5091303219392552e-05, + "loss": 0.7795, "step": 1537 }, { - "epoch": 0.79, - "learning_rate": 1.3779667014289067e-05, - "loss": 0.7686, + "epoch": 0.7, + "learning_rate": 1.508495158614244e-05, + "loss": 0.8091, "step": 1538 }, { - "epoch": 0.79, - "learning_rate": 1.377195686114297e-05, - "loss": 0.6909, + "epoch": 0.7, + "learning_rate": 1.507859718483402e-05, + "loss": 0.785, "step": 1539 }, { - "epoch": 0.79, - "learning_rate": 1.3764244092869617e-05, - "loss": 0.7568, + "epoch": 0.7, + "learning_rate": 1.5072240018926396e-05, + "loss": 0.7764, "step": 1540 }, { - "epoch": 0.79, - "learning_rate": 1.3756528714816328e-05, - "loss": 0.7585, + "epoch": 0.7, + "learning_rate": 1.5065880091880167e-05, + "loss": 0.7869, "step": 1541 }, { - "epoch": 0.79, - "learning_rate": 1.3748810732332238e-05, - "loss": 0.7327, + "epoch": 0.7, + "learning_rate": 1.5059517407157445e-05, + "loss": 0.7263, "step": 1542 }, { - "epoch": 0.79, - "learning_rate": 1.3741090150768287e-05, - "loss": 0.7681, + "epoch": 0.7, + "learning_rate": 1.5053151968221835e-05, + "loss": 0.7308, "step": 1543 }, { - "epoch": 0.79, - "learning_rate": 1.3733366975477216e-05, - "loss": 0.7812, + "epoch": 0.7, + "learning_rate": 1.5046783778538448e-05, + "loss": 0.7452, "step": 1544 }, { - "epoch": 0.79, - "learning_rate": 1.3725641211813557e-05, - "loss": 0.7542, + "epoch": 0.7, + "learning_rate": 1.5040412841573886e-05, + "loss": 0.8086, "step": 1545 }, { - "epoch": 0.79, - "learning_rate": 1.3717912865133642e-05, - "loss": 0.748, + "epoch": 0.7, + "learning_rate": 1.5034039160796254e-05, + "loss": 0.84, "step": 1546 }, { - "epoch": 0.8, - "learning_rate": 1.37101819407956e-05, - "loss": 0.679, + "epoch": 0.7, + "learning_rate": 1.5027662739675144e-05, + "loss": 0.7229, "step": 1547 }, { - "epoch": 0.8, - "learning_rate": 1.3702448444159338e-05, - "loss": 0.7339, + "epoch": 0.71, + "learning_rate": 1.502128358168164e-05, + "loss": 0.7233, "step": 1548 }, { - "epoch": 0.8, - "learning_rate": 1.3694712380586552e-05, - "loss": 0.7588, + "epoch": 0.71, + "learning_rate": 1.5014901690288323e-05, + "loss": 0.7263, "step": 1549 }, { - "epoch": 0.8, - "learning_rate": 1.3686973755440714e-05, - "loss": 0.7773, + "epoch": 0.71, + "learning_rate": 1.5008517068969255e-05, + "loss": 0.7805, "step": 1550 }, { - "epoch": 0.8, - "learning_rate": 1.3679232574087072e-05, - "loss": 0.7688, + "epoch": 0.71, + "learning_rate": 1.5002129721199987e-05, + "loss": 0.7695, "step": 1551 }, { - "epoch": 0.8, - "learning_rate": 1.3671488841892648e-05, - "loss": 0.8237, + "epoch": 0.71, + "learning_rate": 1.4995739650457552e-05, + "loss": 0.7458, "step": 1552 }, { - "epoch": 0.8, - "learning_rate": 1.3663742564226237e-05, - "loss": 0.7512, + "epoch": 0.71, + "learning_rate": 1.4989346860220464e-05, + "loss": 0.7885, "step": 1553 }, { - "epoch": 0.8, - "learning_rate": 1.365599374645839e-05, - "loss": 0.79, + "epoch": 0.71, + "learning_rate": 1.4982951353968726e-05, + "loss": 0.754, "step": 1554 }, { - "epoch": 0.8, - "learning_rate": 1.3648242393961421e-05, - "loss": 0.7815, + "epoch": 0.71, + "learning_rate": 1.4976553135183807e-05, + "loss": 0.7766, "step": 1555 }, { - "epoch": 0.8, - "learning_rate": 1.364048851210941e-05, - "loss": 0.7842, + "epoch": 0.71, + "learning_rate": 1.4970152207348663e-05, + "loss": 0.7222, "step": 1556 }, { - "epoch": 0.8, - "learning_rate": 1.3632732106278174e-05, - "loss": 0.7578, + "epoch": 0.71, + "learning_rate": 1.4963748573947723e-05, + "loss": 0.7104, "step": 1557 }, { - "epoch": 0.8, - "learning_rate": 1.3624973181845302e-05, - "loss": 0.7705, + "epoch": 0.71, + "learning_rate": 1.4957342238466881e-05, + "loss": 0.7812, "step": 1558 }, { - "epoch": 0.8, - "learning_rate": 1.361721174419011e-05, - "loss": 0.7463, + "epoch": 0.71, + "learning_rate": 1.495093320439351e-05, + "loss": 0.7742, "step": 1559 }, { - "epoch": 0.8, - "learning_rate": 1.3609447798693665e-05, - "loss": 0.7683, + "epoch": 0.71, + "learning_rate": 1.494452147521645e-05, + "loss": 0.6997, "step": 1560 }, { - "epoch": 0.8, - "learning_rate": 1.360168135073877e-05, - "loss": 0.7585, + "epoch": 0.71, + "learning_rate": 1.4938107054426008e-05, + "loss": 0.7532, "step": 1561 }, { - "epoch": 0.8, - "learning_rate": 1.3593912405709964e-05, - "loss": 0.6992, + "epoch": 0.71, + "learning_rate": 1.4931689945513954e-05, + "loss": 0.798, "step": 1562 }, { - "epoch": 0.8, - "learning_rate": 1.358614096899352e-05, - "loss": 0.7627, + "epoch": 0.71, + "learning_rate": 1.4925270151973525e-05, + "loss": 0.7604, "step": 1563 }, { - "epoch": 0.8, - "learning_rate": 1.3578367045977436e-05, - "loss": 0.7124, + "epoch": 0.71, + "learning_rate": 1.4918847677299417e-05, + "loss": 0.7483, "step": 1564 }, { - "epoch": 0.8, - "learning_rate": 1.3570590642051433e-05, - "loss": 0.7432, + "epoch": 0.71, + "learning_rate": 1.4912422524987787e-05, + "loss": 0.7771, "step": 1565 }, { - "epoch": 0.8, - "learning_rate": 1.356281176260695e-05, - "loss": 0.707, + "epoch": 0.71, + "learning_rate": 1.4905994698536243e-05, + "loss": 0.7937, "step": 1566 }, { - "epoch": 0.81, - "learning_rate": 1.3555030413037147e-05, - "loss": 0.7612, + "epoch": 0.71, + "learning_rate": 1.4899564201443861e-05, + "loss": 0.7449, "step": 1567 }, { - "epoch": 0.81, - "learning_rate": 1.3547246598736896e-05, - "loss": 0.7878, + "epoch": 0.71, + "learning_rate": 1.4893131037211167e-05, + "loss": 0.7451, "step": 1568 }, { - "epoch": 0.81, - "learning_rate": 1.3539460325102779e-05, - "loss": 0.7427, + "epoch": 0.71, + "learning_rate": 1.4886695209340123e-05, + "loss": 0.641, "step": 1569 }, { - "epoch": 0.81, - "learning_rate": 1.3531671597533074e-05, - "loss": 0.8005, + "epoch": 0.72, + "learning_rate": 1.4880256721334168e-05, + "loss": 0.7587, "step": 1570 }, { - "epoch": 0.81, - "learning_rate": 1.3523880421427768e-05, - "loss": 0.7747, + "epoch": 0.72, + "learning_rate": 1.4873815576698168e-05, + "loss": 0.7268, "step": 1571 }, { - "epoch": 0.81, - "learning_rate": 1.3516086802188546e-05, - "loss": 0.7495, + "epoch": 0.72, + "learning_rate": 1.486737177893844e-05, + "loss": 0.7484, "step": 1572 }, { - "epoch": 0.81, - "learning_rate": 1.3508290745218789e-05, - "loss": 0.7764, + "epoch": 0.72, + "learning_rate": 1.4860925331562757e-05, + "loss": 0.7772, "step": 1573 }, { - "epoch": 0.81, - "learning_rate": 1.350049225592356e-05, - "loss": 0.7998, + "epoch": 0.72, + "learning_rate": 1.4854476238080315e-05, + "loss": 0.8022, "step": 1574 }, { - "epoch": 0.81, - "learning_rate": 1.3492691339709613e-05, - "loss": 0.7209, + "epoch": 0.72, + "learning_rate": 1.4848024502001765e-05, + "loss": 0.7947, "step": 1575 }, { - "epoch": 0.81, - "learning_rate": 1.3484888001985388e-05, - "loss": 0.7761, + "epoch": 0.72, + "learning_rate": 1.4841570126839196e-05, + "loss": 0.7703, "step": 1576 }, { - "epoch": 0.81, - "learning_rate": 1.3477082248160993e-05, - "loss": 0.7568, + "epoch": 0.72, + "learning_rate": 1.4835113116106122e-05, + "loss": 0.7656, "step": 1577 }, { - "epoch": 0.81, - "learning_rate": 1.3469274083648224e-05, - "loss": 0.7957, + "epoch": 0.72, + "learning_rate": 1.48286534733175e-05, + "loss": 0.7322, "step": 1578 }, { - "epoch": 0.81, - "learning_rate": 1.3461463513860544e-05, - "loss": 0.7888, + "epoch": 0.72, + "learning_rate": 1.4822191201989725e-05, + "loss": 0.7406, "step": 1579 }, { - "epoch": 0.81, - "learning_rate": 1.3453650544213078e-05, - "loss": 0.793, + "epoch": 0.72, + "learning_rate": 1.481572630564061e-05, + "loss": 0.7888, "step": 1580 }, { - "epoch": 0.81, - "learning_rate": 1.3445835180122622e-05, - "loss": 0.75, + "epoch": 0.72, + "learning_rate": 1.4809258787789407e-05, + "loss": 0.7131, "step": 1581 }, { - "epoch": 0.81, - "learning_rate": 1.3438017427007624e-05, - "loss": 0.7012, + "epoch": 0.72, + "learning_rate": 1.4802788651956794e-05, + "loss": 0.7786, "step": 1582 }, { - "epoch": 0.81, - "learning_rate": 1.34301972902882e-05, - "loss": 0.7737, + "epoch": 0.72, + "learning_rate": 1.4796315901664868e-05, + "loss": 0.7708, "step": 1583 }, { - "epoch": 0.81, - "learning_rate": 1.342237477538611e-05, - "loss": 0.7473, + "epoch": 0.72, + "learning_rate": 1.4789840540437154e-05, + "loss": 0.8022, "step": 1584 }, { - "epoch": 0.81, - "learning_rate": 1.3414549887724763e-05, - "loss": 0.7766, + "epoch": 0.72, + "learning_rate": 1.4783362571798603e-05, + "loss": 0.7418, "step": 1585 }, { - "epoch": 0.82, - "learning_rate": 1.3406722632729219e-05, - "loss": 0.7859, + "epoch": 0.72, + "learning_rate": 1.477688199927557e-05, + "loss": 0.7739, "step": 1586 }, { - "epoch": 0.82, - "learning_rate": 1.3398893015826166e-05, - "loss": 0.7666, + "epoch": 0.72, + "learning_rate": 1.4770398826395846e-05, + "loss": 0.7792, "step": 1587 }, { - "epoch": 0.82, - "learning_rate": 1.3391061042443951e-05, - "loss": 0.7261, + "epoch": 0.72, + "learning_rate": 1.4763913056688629e-05, + "loss": 0.749, "step": 1588 }, { - "epoch": 0.82, - "learning_rate": 1.3383226718012538e-05, - "loss": 0.719, + "epoch": 0.72, + "learning_rate": 1.4757424693684521e-05, + "loss": 0.7455, "step": 1589 }, { - "epoch": 0.82, - "learning_rate": 1.3375390047963522e-05, - "loss": 0.792, + "epoch": 0.72, + "learning_rate": 1.4750933740915557e-05, + "loss": 0.7184, "step": 1590 }, { - "epoch": 0.82, - "learning_rate": 1.3367551037730129e-05, - "loss": 0.7659, + "epoch": 0.72, + "learning_rate": 1.474444020191516e-05, + "loss": 0.7842, "step": 1591 }, { - "epoch": 0.82, - "learning_rate": 1.3359709692747207e-05, - "loss": 0.7346, + "epoch": 0.73, + "learning_rate": 1.4737944080218176e-05, + "loss": 0.7819, "step": 1592 }, { - "epoch": 0.82, - "learning_rate": 1.3351866018451226e-05, - "loss": 0.7234, + "epoch": 0.73, + "learning_rate": 1.4731445379360855e-05, + "loss": 0.8342, "step": 1593 }, { - "epoch": 0.82, - "learning_rate": 1.3344020020280262e-05, - "loss": 0.7195, + "epoch": 0.73, + "learning_rate": 1.4724944102880841e-05, + "loss": 0.7345, "step": 1594 }, { - "epoch": 0.82, - "learning_rate": 1.3336171703674005e-05, - "loss": 0.762, + "epoch": 0.73, + "learning_rate": 1.471844025431719e-05, + "loss": 0.8213, "step": 1595 }, { - "epoch": 0.82, - "learning_rate": 1.332832107407376e-05, - "loss": 0.7815, + "epoch": 0.73, + "learning_rate": 1.4711933837210358e-05, + "loss": 0.7952, "step": 1596 }, { - "epoch": 0.82, - "learning_rate": 1.3320468136922427e-05, - "loss": 0.7043, + "epoch": 0.73, + "learning_rate": 1.4705424855102189e-05, + "loss": 0.7886, "step": 1597 }, { - "epoch": 0.82, - "learning_rate": 1.3312612897664509e-05, - "loss": 0.7346, + "epoch": 0.73, + "learning_rate": 1.4698913311535934e-05, + "loss": 0.6894, "step": 1598 }, { - "epoch": 0.82, - "learning_rate": 1.3304755361746108e-05, - "loss": 0.7339, + "epoch": 0.73, + "learning_rate": 1.4692399210056238e-05, + "loss": 0.736, "step": 1599 }, { - "epoch": 0.82, - "learning_rate": 1.329689553461491e-05, - "loss": 0.7642, + "epoch": 0.73, + "learning_rate": 1.4685882554209133e-05, + "loss": 0.814, "step": 1600 }, { - "epoch": 0.82, - "learning_rate": 1.32890334217202e-05, - "loss": 0.7665, + "epoch": 0.73, + "learning_rate": 1.4679363347542044e-05, + "loss": 0.759, "step": 1601 }, { - "epoch": 0.82, - "learning_rate": 1.3281169028512838e-05, - "loss": 0.7512, + "epoch": 0.73, + "learning_rate": 1.467284159360378e-05, + "loss": 0.7859, "step": 1602 }, { - "epoch": 0.82, - "learning_rate": 1.327330236044527e-05, - "loss": 0.7185, + "epoch": 0.73, + "learning_rate": 1.4666317295944544e-05, + "loss": 0.7014, "step": 1603 }, { - "epoch": 0.82, - "learning_rate": 1.3265433422971525e-05, - "loss": 0.7056, + "epoch": 0.73, + "learning_rate": 1.4659790458115927e-05, + "loss": 0.7303, "step": 1604 }, { - "epoch": 0.82, - "learning_rate": 1.325756222154719e-05, + "epoch": 0.73, + "learning_rate": 1.465326108367089e-05, "loss": 0.7527, "step": 1605 }, { - "epoch": 0.83, - "learning_rate": 1.3249688761629434e-05, - "loss": 0.7788, + "epoch": 0.73, + "learning_rate": 1.4646729176163779e-05, + "loss": 0.7563, "step": 1606 }, { - "epoch": 0.83, - "learning_rate": 1.3241813048676991e-05, - "loss": 0.7583, + "epoch": 0.73, + "learning_rate": 1.4640194739150326e-05, + "loss": 0.7561, "step": 1607 }, { - "epoch": 0.83, - "learning_rate": 1.3233935088150154e-05, - "loss": 0.7393, + "epoch": 0.73, + "learning_rate": 1.4633657776187636e-05, + "loss": 0.7847, "step": 1608 }, { - "epoch": 0.83, - "learning_rate": 1.3226054885510774e-05, - "loss": 0.7268, + "epoch": 0.73, + "learning_rate": 1.4627118290834184e-05, + "loss": 0.717, "step": 1609 }, { - "epoch": 0.83, - "learning_rate": 1.321817244622225e-05, - "loss": 0.8101, + "epoch": 0.73, + "learning_rate": 1.4620576286649825e-05, + "loss": 0.7607, "step": 1610 }, { - "epoch": 0.83, - "learning_rate": 1.321028777574955e-05, - "loss": 0.7856, + "epoch": 0.73, + "learning_rate": 1.461403176719578e-05, + "loss": 0.6768, "step": 1611 }, { - "epoch": 0.83, - "learning_rate": 1.3202400879559174e-05, - "loss": 0.7683, + "epoch": 0.73, + "learning_rate": 1.4607484736034648e-05, + "loss": 0.7354, "step": 1612 }, { - "epoch": 0.83, - "learning_rate": 1.319451176311917e-05, - "loss": 0.6917, + "epoch": 0.73, + "learning_rate": 1.4600935196730382e-05, + "loss": 0.7803, "step": 1613 }, { - "epoch": 0.83, - "learning_rate": 1.3186620431899121e-05, - "loss": 0.7751, + "epoch": 0.74, + "learning_rate": 1.4594383152848309e-05, + "loss": 0.7552, "step": 1614 }, { - "epoch": 0.83, - "learning_rate": 1.317872689137015e-05, - "loss": 0.7252, + "epoch": 0.74, + "learning_rate": 1.4587828607955119e-05, + "loss": 0.7515, "step": 1615 }, { - "epoch": 0.83, - "learning_rate": 1.317083114700491e-05, - "loss": 0.7456, + "epoch": 0.74, + "learning_rate": 1.4581271565618862e-05, + "loss": 0.7837, "step": 1616 }, { - "epoch": 0.83, - "learning_rate": 1.3162933204277587e-05, - "loss": 0.7285, + "epoch": 0.74, + "learning_rate": 1.4574712029408946e-05, + "loss": 0.7197, "step": 1617 }, { - "epoch": 0.83, - "learning_rate": 1.3155033068663881e-05, - "loss": 0.7673, + "epoch": 0.74, + "learning_rate": 1.4568150002896145e-05, + "loss": 0.7031, "step": 1618 }, { - "epoch": 0.83, - "learning_rate": 1.3147130745641018e-05, - "loss": 0.7268, + "epoch": 0.74, + "learning_rate": 1.456158548965257e-05, + "loss": 0.8181, "step": 1619 }, { - "epoch": 0.83, - "learning_rate": 1.3139226240687747e-05, - "loss": 0.7441, + "epoch": 0.74, + "learning_rate": 1.4555018493251706e-05, + "loss": 0.6703, "step": 1620 }, { - "epoch": 0.83, - "learning_rate": 1.3131319559284315e-05, - "loss": 0.759, + "epoch": 0.74, + "learning_rate": 1.4548449017268383e-05, + "loss": 0.7605, "step": 1621 }, { - "epoch": 0.83, - "learning_rate": 1.312341070691249e-05, - "loss": 0.7227, + "epoch": 0.74, + "learning_rate": 1.4541877065278774e-05, + "loss": 0.7549, "step": 1622 }, { - "epoch": 0.83, - "learning_rate": 1.3115499689055543e-05, - "loss": 0.7607, + "epoch": 0.74, + "learning_rate": 1.4535302640860405e-05, + "loss": 0.8037, "step": 1623 }, { - "epoch": 0.83, - "learning_rate": 1.3107586511198243e-05, - "loss": 0.7186, + "epoch": 0.74, + "learning_rate": 1.4528725747592152e-05, + "loss": 0.8193, "step": 1624 }, { - "epoch": 0.84, - "learning_rate": 1.3099671178826856e-05, - "loss": 0.76, + "epoch": 0.74, + "learning_rate": 1.4522146389054225e-05, + "loss": 0.7141, "step": 1625 }, { - "epoch": 0.84, - "learning_rate": 1.3091753697429148e-05, - "loss": 0.7263, + "epoch": 0.74, + "learning_rate": 1.4515564568828188e-05, + "loss": 0.7751, "step": 1626 }, { - "epoch": 0.84, - "learning_rate": 1.3083834072494368e-05, - "loss": 0.7209, + "epoch": 0.74, + "learning_rate": 1.4508980290496935e-05, + "loss": 0.7817, "step": 1627 }, { - "epoch": 0.84, - "learning_rate": 1.3075912309513256e-05, - "loss": 0.7352, + "epoch": 0.74, + "learning_rate": 1.4502393557644703e-05, + "loss": 0.7573, "step": 1628 }, { - "epoch": 0.84, - "learning_rate": 1.3067988413978032e-05, - "loss": 0.7859, + "epoch": 0.74, + "learning_rate": 1.4495804373857063e-05, + "loss": 0.7158, "step": 1629 }, { - "epoch": 0.84, - "learning_rate": 1.3060062391382393e-05, - "loss": 0.7524, + "epoch": 0.74, + "learning_rate": 1.4489212742720924e-05, + "loss": 0.752, "step": 1630 }, { - "epoch": 0.84, - "learning_rate": 1.3052134247221514e-05, - "loss": 0.6975, + "epoch": 0.74, + "learning_rate": 1.4482618667824521e-05, + "loss": 0.7429, "step": 1631 }, { - "epoch": 0.84, - "learning_rate": 1.304420398699204e-05, - "loss": 0.7463, + "epoch": 0.74, + "learning_rate": 1.4476022152757427e-05, + "loss": 0.7551, "step": 1632 }, { - "epoch": 0.84, - "learning_rate": 1.3036271616192083e-05, - "loss": 0.7285, + "epoch": 0.74, + "learning_rate": 1.4469423201110535e-05, + "loss": 0.7845, "step": 1633 }, { - "epoch": 0.84, - "learning_rate": 1.3028337140321214e-05, - "loss": 0.783, + "epoch": 0.74, + "learning_rate": 1.446282181647607e-05, + "loss": 0.7207, "step": 1634 }, { - "epoch": 0.84, - "learning_rate": 1.302040056488047e-05, - "loss": 0.7822, + "epoch": 0.74, + "learning_rate": 1.4456218002447581e-05, + "loss": 0.7585, "step": 1635 }, { - "epoch": 0.84, - "learning_rate": 1.3012461895372343e-05, - "loss": 0.7288, + "epoch": 0.75, + "learning_rate": 1.4449611762619937e-05, + "loss": 0.7476, "step": 1636 }, { - "epoch": 0.84, - "learning_rate": 1.3004521137300774e-05, - "loss": 0.7434, + "epoch": 0.75, + "learning_rate": 1.4443003100589335e-05, + "loss": 0.8147, "step": 1637 }, { - "epoch": 0.84, - "learning_rate": 1.299657829617115e-05, - "loss": 0.7461, + "epoch": 0.75, + "learning_rate": 1.4436392019953273e-05, + "loss": 0.71, "step": 1638 }, { - "epoch": 0.84, - "learning_rate": 1.2988633377490307e-05, - "loss": 0.7529, + "epoch": 0.75, + "learning_rate": 1.4429778524310587e-05, + "loss": 0.7163, "step": 1639 }, { - "epoch": 0.84, - "learning_rate": 1.2980686386766519e-05, - "loss": 0.7424, + "epoch": 0.75, + "learning_rate": 1.4423162617261415e-05, + "loss": 0.7742, "step": 1640 }, { - "epoch": 0.84, - "learning_rate": 1.2972737329509494e-05, - "loss": 0.7419, + "epoch": 0.75, + "learning_rate": 1.4416544302407207e-05, + "loss": 0.712, "step": 1641 }, { - "epoch": 0.84, - "learning_rate": 1.2964786211230384e-05, - "loss": 0.8198, + "epoch": 0.75, + "learning_rate": 1.440992358335073e-05, + "loss": 0.8159, "step": 1642 }, { - "epoch": 0.84, - "learning_rate": 1.2956833037441756e-05, - "loss": 0.7185, + "epoch": 0.75, + "learning_rate": 1.4403300463696062e-05, + "loss": 0.734, "step": 1643 }, { - "epoch": 0.85, - "learning_rate": 1.2948877813657607e-05, - "loss": 0.7046, + "epoch": 0.75, + "learning_rate": 1.4396674947048573e-05, + "loss": 0.7618, "step": 1644 }, { - "epoch": 0.85, - "learning_rate": 1.2940920545393354e-05, - "loss": 0.7686, + "epoch": 0.75, + "learning_rate": 1.4390047037014953e-05, + "loss": 0.7964, "step": 1645 }, { - "epoch": 0.85, - "learning_rate": 1.2932961238165837e-05, - "loss": 0.7339, + "epoch": 0.75, + "learning_rate": 1.438341673720319e-05, + "loss": 0.7006, "step": 1646 }, { - "epoch": 0.85, - "learning_rate": 1.2924999897493308e-05, - "loss": 0.74, + "epoch": 0.75, + "learning_rate": 1.437678405122257e-05, + "loss": 0.7698, "step": 1647 }, { - "epoch": 0.85, - "learning_rate": 1.2917036528895426e-05, - "loss": 0.7217, + "epoch": 0.75, + "learning_rate": 1.4370148982683683e-05, + "loss": 0.7913, "step": 1648 }, { - "epoch": 0.85, - "learning_rate": 1.2909071137893254e-05, - "loss": 0.7502, + "epoch": 0.75, + "learning_rate": 1.4363511535198407e-05, + "loss": 0.6846, "step": 1649 }, { - "epoch": 0.85, - "learning_rate": 1.2901103730009261e-05, - "loss": 0.6873, + "epoch": 0.75, + "learning_rate": 1.435687171237993e-05, + "loss": 0.6934, "step": 1650 }, { - "epoch": 0.85, - "learning_rate": 1.2893134310767313e-05, - "loss": 0.7117, + "epoch": 0.75, + "learning_rate": 1.435022951784272e-05, + "loss": 0.7356, "step": 1651 }, { - "epoch": 0.85, - "learning_rate": 1.2885162885692672e-05, - "loss": 0.7852, + "epoch": 0.75, + "learning_rate": 1.4343584955202538e-05, + "loss": 0.7327, "step": 1652 }, { - "epoch": 0.85, - "learning_rate": 1.2877189460311989e-05, - "loss": 0.7839, + "epoch": 0.75, + "learning_rate": 1.4336938028076439e-05, + "loss": 0.6807, "step": 1653 }, { - "epoch": 0.85, - "learning_rate": 1.2869214040153304e-05, - "loss": 0.7949, + "epoch": 0.75, + "learning_rate": 1.4330288740082765e-05, + "loss": 0.7906, "step": 1654 }, { - "epoch": 0.85, - "learning_rate": 1.2861236630746032e-05, - "loss": 0.7156, + "epoch": 0.75, + "learning_rate": 1.4323637094841136e-05, + "loss": 0.7991, "step": 1655 }, { - "epoch": 0.85, - "learning_rate": 1.2853257237620982e-05, - "loss": 0.7886, + "epoch": 0.75, + "learning_rate": 1.4316983095972464e-05, + "loss": 0.7688, "step": 1656 }, { - "epoch": 0.85, - "learning_rate": 1.2845275866310325e-05, - "loss": 0.7344, + "epoch": 0.75, + "learning_rate": 1.4310326747098937e-05, + "loss": 0.7739, "step": 1657 }, { - "epoch": 0.85, - "learning_rate": 1.283729252234761e-05, - "loss": 0.7573, + "epoch": 0.76, + "learning_rate": 1.4303668051844021e-05, + "loss": 0.7942, "step": 1658 }, { - "epoch": 0.85, - "learning_rate": 1.2829307211267752e-05, - "loss": 0.783, + "epoch": 0.76, + "learning_rate": 1.4297007013832466e-05, + "loss": 0.7603, "step": 1659 }, { - "epoch": 0.85, - "learning_rate": 1.2821319938607027e-05, - "loss": 0.7302, + "epoch": 0.76, + "learning_rate": 1.429034363669029e-05, + "loss": 0.7949, "step": 1660 }, { - "epoch": 0.85, - "learning_rate": 1.2813330709903074e-05, - "loss": 0.7881, + "epoch": 0.76, + "learning_rate": 1.4283677924044787e-05, + "loss": 0.7516, "step": 1661 }, { - "epoch": 0.85, - "learning_rate": 1.2805339530694894e-05, - "loss": 0.7888, + "epoch": 0.76, + "learning_rate": 1.4277009879524528e-05, + "loss": 0.7573, "step": 1662 }, { - "epoch": 0.85, - "learning_rate": 1.2797346406522825e-05, - "loss": 0.7458, + "epoch": 0.76, + "learning_rate": 1.427033950675934e-05, + "loss": 0.7896, "step": 1663 }, { - "epoch": 0.86, - "learning_rate": 1.278935134292857e-05, - "loss": 0.7803, + "epoch": 0.76, + "learning_rate": 1.4263666809380333e-05, + "loss": 0.7307, "step": 1664 }, { - "epoch": 0.86, - "learning_rate": 1.2781354345455168e-05, - "loss": 0.7383, + "epoch": 0.76, + "learning_rate": 1.425699179101987e-05, + "loss": 0.7192, "step": 1665 }, { - "epoch": 0.86, - "learning_rate": 1.2773355419646994e-05, - "loss": 0.717, + "epoch": 0.76, + "learning_rate": 1.4250314455311585e-05, + "loss": 0.7852, "step": 1666 }, { - "epoch": 0.86, - "learning_rate": 1.2765354571049774e-05, - "loss": 0.7551, + "epoch": 0.76, + "learning_rate": 1.424363480589037e-05, + "loss": 0.7789, "step": 1667 }, { - "epoch": 0.86, - "learning_rate": 1.2757351805210557e-05, - "loss": 0.7307, + "epoch": 0.76, + "learning_rate": 1.4236952846392378e-05, + "loss": 0.7769, "step": 1668 }, { - "epoch": 0.86, - "learning_rate": 1.2749347127677718e-05, - "loss": 0.7458, + "epoch": 0.76, + "learning_rate": 1.4230268580455018e-05, + "loss": 0.7698, "step": 1669 }, { - "epoch": 0.86, - "learning_rate": 1.2741340544000968e-05, - "loss": 0.7175, + "epoch": 0.76, + "learning_rate": 1.4223582011716954e-05, + "loss": 0.7405, "step": 1670 }, { - "epoch": 0.86, - "learning_rate": 1.2733332059731333e-05, - "loss": 0.7415, + "epoch": 0.76, + "learning_rate": 1.421689314381811e-05, + "loss": 0.8027, "step": 1671 }, { - "epoch": 0.86, - "learning_rate": 1.2725321680421159e-05, - "loss": 0.7256, + "epoch": 0.76, + "learning_rate": 1.4210201980399655e-05, + "loss": 0.7646, "step": 1672 }, { - "epoch": 0.86, - "learning_rate": 1.2717309411624101e-05, - "loss": 0.697, + "epoch": 0.76, + "learning_rate": 1.4203508525104005e-05, + "loss": 0.7129, "step": 1673 }, { - "epoch": 0.86, - "learning_rate": 1.270929525889513e-05, - "loss": 0.7705, + "epoch": 0.76, + "learning_rate": 1.4196812781574831e-05, + "loss": 0.7863, "step": 1674 }, { - "epoch": 0.86, - "learning_rate": 1.2701279227790523e-05, - "loss": 0.7166, + "epoch": 0.76, + "learning_rate": 1.4190114753457047e-05, + "loss": 0.7439, "step": 1675 }, { - "epoch": 0.86, - "learning_rate": 1.2693261323867856e-05, - "loss": 0.7249, + "epoch": 0.76, + "learning_rate": 1.418341444439681e-05, + "loss": 0.772, "step": 1676 }, { - "epoch": 0.86, - "learning_rate": 1.2685241552686004e-05, - "loss": 0.7612, + "epoch": 0.76, + "learning_rate": 1.4176711858041519e-05, + "loss": 0.7123, "step": 1677 }, { - "epoch": 0.86, - "learning_rate": 1.2677219919805137e-05, - "loss": 0.7927, + "epoch": 0.76, + "learning_rate": 1.4170006998039809e-05, + "loss": 0.7296, "step": 1678 }, { - "epoch": 0.86, - "learning_rate": 1.2669196430786715e-05, - "loss": 0.7737, + "epoch": 0.76, + "learning_rate": 1.4163299868041561e-05, + "loss": 0.7693, "step": 1679 }, { - "epoch": 0.86, - "learning_rate": 1.2661171091193487e-05, - "loss": 0.762, + "epoch": 0.77, + "learning_rate": 1.4156590471697881e-05, + "loss": 0.8037, "step": 1680 }, { - "epoch": 0.86, - "learning_rate": 1.265314390658948e-05, - "loss": 0.7336, + "epoch": 0.77, + "learning_rate": 1.4149878812661124e-05, + "loss": 0.7863, "step": 1681 }, { - "epoch": 0.86, - "learning_rate": 1.2645114882540015e-05, - "loss": 0.7488, + "epoch": 0.77, + "learning_rate": 1.4143164894584857e-05, + "loss": 0.7861, "step": 1682 }, { - "epoch": 0.87, - "learning_rate": 1.2637084024611665e-05, - "loss": 0.7292, + "epoch": 0.77, + "learning_rate": 1.4136448721123892e-05, + "loss": 0.7708, "step": 1683 }, { - "epoch": 0.87, - "learning_rate": 1.2629051338372293e-05, - "loss": 0.7729, + "epoch": 0.77, + "learning_rate": 1.4129730295934265e-05, + "loss": 0.7483, "step": 1684 }, { - "epoch": 0.87, - "learning_rate": 1.2621016829391022e-05, - "loss": 0.7297, + "epoch": 0.77, + "learning_rate": 1.4123009622673232e-05, + "loss": 0.7574, "step": 1685 }, { - "epoch": 0.87, - "learning_rate": 1.2612980503238242e-05, - "loss": 0.7761, + "epoch": 0.77, + "learning_rate": 1.411628670499928e-05, + "loss": 0.712, "step": 1686 }, { - "epoch": 0.87, - "learning_rate": 1.2604942365485598e-05, - "loss": 0.739, + "epoch": 0.77, + "learning_rate": 1.4109561546572117e-05, + "loss": 0.7153, "step": 1687 }, { - "epoch": 0.87, - "learning_rate": 1.2596902421705997e-05, - "loss": 0.7322, + "epoch": 0.77, + "learning_rate": 1.4102834151052667e-05, + "loss": 0.757, "step": 1688 }, { - "epoch": 0.87, - "learning_rate": 1.2588860677473588e-05, - "loss": 0.7781, + "epoch": 0.77, + "learning_rate": 1.4096104522103072e-05, + "loss": 0.7131, "step": 1689 }, { - "epoch": 0.87, - "learning_rate": 1.258081713836378e-05, - "loss": 0.6777, + "epoch": 0.77, + "learning_rate": 1.4089372663386693e-05, + "loss": 0.8058, "step": 1690 }, { - "epoch": 0.87, - "learning_rate": 1.2572771809953228e-05, - "loss": 0.6914, + "epoch": 0.77, + "learning_rate": 1.4082638578568105e-05, + "loss": 0.7301, "step": 1691 }, { - "epoch": 0.87, - "learning_rate": 1.2564724697819814e-05, - "loss": 0.7842, + "epoch": 0.77, + "learning_rate": 1.4075902271313087e-05, + "loss": 0.6902, "step": 1692 }, { - "epoch": 0.87, - "learning_rate": 1.2556675807542665e-05, - "loss": 0.7391, + "epoch": 0.77, + "learning_rate": 1.4069163745288642e-05, + "loss": 0.7201, "step": 1693 }, { - "epoch": 0.87, - "learning_rate": 1.2548625144702137e-05, - "loss": 0.749, + "epoch": 0.77, + "learning_rate": 1.4062423004162966e-05, + "loss": 0.7361, "step": 1694 }, { - "epoch": 0.87, - "learning_rate": 1.2540572714879819e-05, - "loss": 0.6777, + "epoch": 0.77, + "learning_rate": 1.4055680051605474e-05, + "loss": 0.7162, "step": 1695 }, { - "epoch": 0.87, - "learning_rate": 1.2532518523658533e-05, - "loss": 0.7444, + "epoch": 0.77, + "learning_rate": 1.404893489128677e-05, + "loss": 0.7798, "step": 1696 }, { - "epoch": 0.87, - "learning_rate": 1.2524462576622298e-05, - "loss": 0.7377, + "epoch": 0.77, + "learning_rate": 1.4042187526878673e-05, + "loss": 0.8, "step": 1697 }, { - "epoch": 0.87, - "learning_rate": 1.2516404879356379e-05, - "loss": 0.7239, + "epoch": 0.77, + "learning_rate": 1.40354379620542e-05, + "loss": 0.7847, "step": 1698 }, { - "epoch": 0.87, - "learning_rate": 1.2508345437447226e-05, - "loss": 0.7131, + "epoch": 0.77, + "learning_rate": 1.4028686200487554e-05, + "loss": 0.7563, "step": 1699 }, { - "epoch": 0.87, - "learning_rate": 1.2500284256482526e-05, - "loss": 0.7559, + "epoch": 0.77, + "learning_rate": 1.402193224585415e-05, + "loss": 0.7656, "step": 1700 }, { - "epoch": 0.87, - "learning_rate": 1.2492221342051153e-05, - "loss": 0.7683, + "epoch": 0.77, + "learning_rate": 1.401517610183059e-05, + "loss": 0.7444, "step": 1701 }, { - "epoch": 0.87, - "learning_rate": 1.2484156699743192e-05, - "loss": 0.7551, + "epoch": 0.78, + "learning_rate": 1.4008417772094663e-05, + "loss": 0.7891, "step": 1702 }, { - "epoch": 0.88, - "learning_rate": 1.2476090335149922e-05, - "loss": 0.7319, + "epoch": 0.78, + "learning_rate": 1.400165726032535e-05, + "loss": 0.7572, "step": 1703 }, { - "epoch": 0.88, - "learning_rate": 1.2468022253863811e-05, - "loss": 0.7344, + "epoch": 0.78, + "learning_rate": 1.3994894570202828e-05, + "loss": 0.7451, "step": 1704 }, { - "epoch": 0.88, - "learning_rate": 1.2459952461478528e-05, - "loss": 0.7505, + "epoch": 0.78, + "learning_rate": 1.398812970540845e-05, + "loss": 0.7429, "step": 1705 }, { - "epoch": 0.88, - "learning_rate": 1.2451880963588927e-05, - "loss": 0.8354, + "epoch": 0.78, + "learning_rate": 1.3981362669624764e-05, + "loss": 0.7703, "step": 1706 }, { - "epoch": 0.88, - "learning_rate": 1.2443807765791034e-05, - "loss": 0.7531, + "epoch": 0.78, + "learning_rate": 1.3974593466535477e-05, + "loss": 0.782, "step": 1707 }, { - "epoch": 0.88, - "learning_rate": 1.2435732873682065e-05, - "loss": 0.7686, + "epoch": 0.78, + "learning_rate": 1.3967822099825505e-05, + "loss": 0.7698, "step": 1708 }, { - "epoch": 0.88, - "learning_rate": 1.2427656292860399e-05, - "loss": 0.7612, + "epoch": 0.78, + "learning_rate": 1.3961048573180924e-05, + "loss": 0.7515, "step": 1709 }, { - "epoch": 0.88, - "learning_rate": 1.2419578028925601e-05, - "loss": 0.7114, + "epoch": 0.78, + "learning_rate": 1.3954272890288987e-05, + "loss": 0.7025, "step": 1710 }, { - "epoch": 0.88, - "learning_rate": 1.241149808747839e-05, - "loss": 0.7715, + "epoch": 0.78, + "learning_rate": 1.3947495054838122e-05, + "loss": 0.7786, "step": 1711 }, { - "epoch": 0.88, - "learning_rate": 1.2403416474120657e-05, - "loss": 0.7123, + "epoch": 0.78, + "learning_rate": 1.394071507051794e-05, + "loss": 0.7307, "step": 1712 }, { - "epoch": 0.88, - "learning_rate": 1.2395333194455444e-05, - "loss": 0.7593, + "epoch": 0.78, + "learning_rate": 1.3933932941019201e-05, + "loss": 0.7542, "step": 1713 }, { - "epoch": 0.88, - "learning_rate": 1.2387248254086952e-05, - "loss": 0.7534, + "epoch": 0.78, + "learning_rate": 1.392714867003385e-05, + "loss": 0.745, "step": 1714 }, { - "epoch": 0.88, - "learning_rate": 1.2379161658620533e-05, - "loss": 0.6996, + "epoch": 0.78, + "learning_rate": 1.3920362261254989e-05, + "loss": 0.7773, "step": 1715 }, { - "epoch": 0.88, - "learning_rate": 1.237107341366269e-05, - "loss": 0.7407, + "epoch": 0.78, + "learning_rate": 1.3913573718376885e-05, + "loss": 0.7004, "step": 1716 }, { - "epoch": 0.88, - "learning_rate": 1.2362983524821069e-05, - "loss": 0.7292, + "epoch": 0.78, + "learning_rate": 1.3906783045094974e-05, + "loss": 0.7511, "step": 1717 }, { - "epoch": 0.88, - "learning_rate": 1.2354891997704445e-05, - "loss": 0.7373, + "epoch": 0.78, + "learning_rate": 1.389999024510584e-05, + "loss": 0.7693, "step": 1718 }, { - "epoch": 0.88, - "learning_rate": 1.2346798837922745e-05, - "loss": 0.7393, + "epoch": 0.78, + "learning_rate": 1.3893195322107228e-05, + "loss": 0.7722, "step": 1719 }, { - "epoch": 0.88, - "learning_rate": 1.2338704051087014e-05, - "loss": 0.7291, + "epoch": 0.78, + "learning_rate": 1.388639827979805e-05, + "loss": 0.8228, "step": 1720 }, { - "epoch": 0.88, - "learning_rate": 1.2330607642809435e-05, - "loss": 0.7266, + "epoch": 0.78, + "learning_rate": 1.3879599121878355e-05, + "loss": 0.7822, "step": 1721 }, { - "epoch": 0.89, - "learning_rate": 1.2322509618703311e-05, - "loss": 0.7661, + "epoch": 0.78, + "learning_rate": 1.3872797852049356e-05, + "loss": 0.7642, "step": 1722 }, { - "epoch": 0.89, - "learning_rate": 1.2314409984383066e-05, - "loss": 0.7366, + "epoch": 0.78, + "learning_rate": 1.386599447401341e-05, + "loss": 0.7947, "step": 1723 }, { - "epoch": 0.89, - "learning_rate": 1.2306308745464237e-05, - "loss": 0.7615, + "epoch": 0.79, + "learning_rate": 1.385918899147402e-05, + "loss": 0.7493, "step": 1724 }, { - "epoch": 0.89, - "learning_rate": 1.2298205907563479e-05, - "loss": 0.7451, + "epoch": 0.79, + "learning_rate": 1.3852381408135837e-05, + "loss": 0.7769, "step": 1725 }, { - "epoch": 0.89, - "learning_rate": 1.2290101476298553e-05, - "loss": 0.7302, + "epoch": 0.79, + "learning_rate": 1.3845571727704666e-05, + "loss": 0.7104, "step": 1726 }, { - "epoch": 0.89, - "learning_rate": 1.2281995457288324e-05, - "loss": 0.7217, + "epoch": 0.79, + "learning_rate": 1.3838759953887429e-05, + "loss": 0.7043, "step": 1727 }, { - "epoch": 0.89, - "learning_rate": 1.227388785615276e-05, - "loss": 0.761, + "epoch": 0.79, + "learning_rate": 1.3831946090392208e-05, + "loss": 0.7037, "step": 1728 }, { - "epoch": 0.89, - "learning_rate": 1.226577867851292e-05, - "loss": 0.731, + "epoch": 0.79, + "learning_rate": 1.382513014092822e-05, + "loss": 0.7334, "step": 1729 }, { - "epoch": 0.89, - "learning_rate": 1.2257667929990964e-05, - "loss": 0.7434, + "epoch": 0.79, + "learning_rate": 1.3818312109205812e-05, + "loss": 0.772, "step": 1730 }, { - "epoch": 0.89, - "learning_rate": 1.2249555616210137e-05, - "loss": 0.698, + "epoch": 0.79, + "learning_rate": 1.3811491998936463e-05, + "loss": 0.7791, "step": 1731 }, { - "epoch": 0.89, - "learning_rate": 1.2241441742794772e-05, - "loss": 0.7827, + "epoch": 0.79, + "learning_rate": 1.3804669813832793e-05, + "loss": 0.7715, "step": 1732 }, { - "epoch": 0.89, - "learning_rate": 1.223332631537028e-05, - "loss": 0.7407, + "epoch": 0.79, + "learning_rate": 1.379784555760854e-05, + "loss": 0.7991, "step": 1733 }, { - "epoch": 0.89, - "learning_rate": 1.2225209339563144e-05, - "loss": 0.6781, + "epoch": 0.79, + "learning_rate": 1.379101923397858e-05, + "loss": 0.7407, "step": 1734 }, { - "epoch": 0.89, - "learning_rate": 1.2217090821000934e-05, - "loss": 0.7654, + "epoch": 0.79, + "learning_rate": 1.3784190846658905e-05, + "loss": 0.8011, "step": 1735 }, { - "epoch": 0.89, - "learning_rate": 1.2208970765312285e-05, - "loss": 0.7756, + "epoch": 0.79, + "learning_rate": 1.3777360399366638e-05, + "loss": 0.788, "step": 1736 }, { - "epoch": 0.89, - "learning_rate": 1.2200849178126886e-05, - "loss": 0.7505, + "epoch": 0.79, + "learning_rate": 1.3770527895820019e-05, + "loss": 0.7378, "step": 1737 }, { - "epoch": 0.89, - "learning_rate": 1.2192726065075506e-05, - "loss": 0.7361, + "epoch": 0.79, + "learning_rate": 1.3763693339738404e-05, + "loss": 0.8364, "step": 1738 }, { - "epoch": 0.89, - "learning_rate": 1.2184601431789956e-05, - "loss": 0.7537, + "epoch": 0.79, + "learning_rate": 1.3756856734842281e-05, + "loss": 0.7568, "step": 1739 }, { - "epoch": 0.89, - "learning_rate": 1.2176475283903109e-05, - "loss": 0.7129, + "epoch": 0.79, + "learning_rate": 1.3750018084853235e-05, + "loss": 0.7552, "step": 1740 }, { - "epoch": 0.89, - "learning_rate": 1.2168347627048891e-05, - "loss": 0.7476, + "epoch": 0.79, + "learning_rate": 1.3743177393493973e-05, + "loss": 0.701, "step": 1741 }, { - "epoch": 0.9, - "learning_rate": 1.216021846686227e-05, - "loss": 0.7571, + "epoch": 0.79, + "learning_rate": 1.3736334664488318e-05, + "loss": 0.7219, "step": 1742 }, { - "epoch": 0.9, - "learning_rate": 1.2152087808979253e-05, - "loss": 0.707, + "epoch": 0.79, + "learning_rate": 1.372948990156119e-05, + "loss": 0.741, "step": 1743 }, { - "epoch": 0.9, - "learning_rate": 1.214395565903689e-05, - "loss": 0.6968, + "epoch": 0.79, + "learning_rate": 1.3722643108438629e-05, + "loss": 0.7903, "step": 1744 }, { - "epoch": 0.9, - "learning_rate": 1.2135822022673263e-05, - "loss": 0.7805, + "epoch": 0.79, + "learning_rate": 1.3715794288847773e-05, + "loss": 0.7866, "step": 1745 }, { - "epoch": 0.9, - "learning_rate": 1.212768690552749e-05, - "loss": 0.7681, + "epoch": 0.8, + "learning_rate": 1.370894344651686e-05, + "loss": 0.6677, "step": 1746 }, { - "epoch": 0.9, - "learning_rate": 1.2119550313239709e-05, - "loss": 0.6924, + "epoch": 0.8, + "learning_rate": 1.3702090585175239e-05, + "loss": 0.7745, "step": 1747 }, { - "epoch": 0.9, - "learning_rate": 1.2111412251451085e-05, - "loss": 0.7314, + "epoch": 0.8, + "learning_rate": 1.369523570855335e-05, + "loss": 0.7418, "step": 1748 }, { - "epoch": 0.9, - "learning_rate": 1.2103272725803794e-05, - "loss": 0.7769, + "epoch": 0.8, + "learning_rate": 1.368837882038273e-05, + "loss": 0.7689, "step": 1749 }, { - "epoch": 0.9, - "learning_rate": 1.2095131741941038e-05, - "loss": 0.741, + "epoch": 0.8, + "learning_rate": 1.3681519924396018e-05, + "loss": 0.7341, "step": 1750 }, { - "epoch": 0.9, - "learning_rate": 1.2086989305507026e-05, - "loss": 0.7502, + "epoch": 0.8, + "learning_rate": 1.367465902432694e-05, + "loss": 0.7047, "step": 1751 }, { - "epoch": 0.9, - "learning_rate": 1.2078845422146972e-05, - "loss": 0.8064, + "epoch": 0.8, + "learning_rate": 1.3667796123910312e-05, + "loss": 0.7168, "step": 1752 }, { - "epoch": 0.9, - "learning_rate": 1.2070700097507093e-05, - "loss": 0.7593, + "epoch": 0.8, + "learning_rate": 1.3660931226882049e-05, + "loss": 0.752, "step": 1753 }, { - "epoch": 0.9, - "learning_rate": 1.2062553337234604e-05, - "loss": 0.7502, + "epoch": 0.8, + "learning_rate": 1.3654064336979136e-05, + "loss": 0.8252, "step": 1754 }, { - "epoch": 0.9, - "learning_rate": 1.2054405146977719e-05, - "loss": 0.7166, + "epoch": 0.8, + "learning_rate": 1.3647195457939657e-05, + "loss": 0.767, "step": 1755 }, { - "epoch": 0.9, - "learning_rate": 1.204625553238565e-05, - "loss": 0.7754, + "epoch": 0.8, + "learning_rate": 1.3640324593502777e-05, + "loss": 0.7593, "step": 1756 }, { - "epoch": 0.9, - "learning_rate": 1.2038104499108579e-05, - "loss": 0.7278, + "epoch": 0.8, + "learning_rate": 1.363345174740873e-05, + "loss": 0.7537, "step": 1757 }, { - "epoch": 0.9, - "learning_rate": 1.2029952052797685e-05, - "loss": 0.6921, + "epoch": 0.8, + "learning_rate": 1.3626576923398844e-05, + "loss": 0.7295, "step": 1758 }, { - "epoch": 0.9, - "learning_rate": 1.202179819910512e-05, - "loss": 0.6592, + "epoch": 0.8, + "learning_rate": 1.3619700125215518e-05, + "loss": 0.7415, "step": 1759 }, { - "epoch": 0.9, - "learning_rate": 1.2013642943684016e-05, - "loss": 0.6963, + "epoch": 0.8, + "learning_rate": 1.3612821356602221e-05, + "loss": 0.6881, "step": 1760 }, { - "epoch": 0.91, - "learning_rate": 1.2005486292188481e-05, - "loss": 0.7676, + "epoch": 0.8, + "learning_rate": 1.3605940621303499e-05, + "loss": 0.7043, "step": 1761 }, { - "epoch": 0.91, - "learning_rate": 1.1997328250273582e-05, - "loss": 0.7756, + "epoch": 0.8, + "learning_rate": 1.3599057923064973e-05, + "loss": 0.6388, "step": 1762 }, { - "epoch": 0.91, - "learning_rate": 1.198916882359535e-05, - "loss": 0.8022, + "epoch": 0.8, + "learning_rate": 1.3592173265633321e-05, + "loss": 0.7981, "step": 1763 }, { - "epoch": 0.91, - "learning_rate": 1.1981008017810778e-05, - "loss": 0.7549, + "epoch": 0.8, + "learning_rate": 1.3585286652756295e-05, + "loss": 0.7556, "step": 1764 }, { - "epoch": 0.91, - "learning_rate": 1.1972845838577825e-05, - "loss": 0.7534, + "epoch": 0.8, + "learning_rate": 1.3578398088182718e-05, + "loss": 0.7173, "step": 1765 }, { - "epoch": 0.91, - "learning_rate": 1.196468229155539e-05, - "loss": 0.8162, + "epoch": 0.8, + "learning_rate": 1.357150757566246e-05, + "loss": 0.7036, "step": 1766 }, { - "epoch": 0.91, - "learning_rate": 1.195651738240332e-05, - "loss": 0.7651, + "epoch": 0.81, + "learning_rate": 1.3564615118946463e-05, + "loss": 0.7332, "step": 1767 }, { - "epoch": 0.91, - "learning_rate": 1.1948351116782418e-05, - "loss": 0.7461, + "epoch": 0.81, + "learning_rate": 1.3557720721786722e-05, + "loss": 0.754, "step": 1768 }, { - "epoch": 0.91, - "learning_rate": 1.194018350035441e-05, - "loss": 0.7456, + "epoch": 0.81, + "learning_rate": 1.3550824387936292e-05, + "loss": 0.7817, "step": 1769 }, { - "epoch": 0.91, - "learning_rate": 1.193201453878198e-05, - "loss": 0.7317, + "epoch": 0.81, + "learning_rate": 1.354392612114928e-05, + "loss": 0.7439, "step": 1770 }, { - "epoch": 0.91, - "learning_rate": 1.1923844237728727e-05, - "loss": 0.7227, + "epoch": 0.81, + "learning_rate": 1.3537025925180842e-05, + "loss": 0.7161, "step": 1771 }, { - "epoch": 0.91, - "learning_rate": 1.1915672602859185e-05, - "loss": 0.7756, + "epoch": 0.81, + "learning_rate": 1.3530123803787195e-05, + "loss": 0.7257, "step": 1772 }, { - "epoch": 0.91, - "learning_rate": 1.1907499639838812e-05, - "loss": 0.733, + "epoch": 0.81, + "learning_rate": 1.352321976072559e-05, + "loss": 0.7017, "step": 1773 }, { - "epoch": 0.91, - "learning_rate": 1.1899325354333987e-05, - "loss": 0.7217, + "epoch": 0.81, + "learning_rate": 1.3516313799754333e-05, + "loss": 0.7537, "step": 1774 }, { - "epoch": 0.91, - "learning_rate": 1.1891149752012008e-05, - "loss": 0.709, + "epoch": 0.81, + "learning_rate": 1.3509405924632776e-05, + "loss": 0.7959, "step": 1775 }, { - "epoch": 0.91, - "learning_rate": 1.1882972838541084e-05, - "loss": 0.7371, + "epoch": 0.81, + "learning_rate": 1.3502496139121303e-05, + "loss": 0.7141, "step": 1776 }, { - "epoch": 0.91, - "learning_rate": 1.1874794619590336e-05, - "loss": 0.7407, + "epoch": 0.81, + "learning_rate": 1.349558444698135e-05, + "loss": 0.7527, "step": 1777 }, { - "epoch": 0.91, - "learning_rate": 1.1866615100829777e-05, - "loss": 0.6666, + "epoch": 0.81, + "learning_rate": 1.3488670851975379e-05, + "loss": 0.7019, "step": 1778 }, { - "epoch": 0.91, - "learning_rate": 1.1858434287930342e-05, - "loss": 0.7598, + "epoch": 0.81, + "learning_rate": 1.3481755357866894e-05, + "loss": 0.7162, "step": 1779 }, { - "epoch": 0.91, - "learning_rate": 1.1850252186563851e-05, - "loss": 0.771, + "epoch": 0.81, + "learning_rate": 1.3474837968420437e-05, + "loss": 0.7419, "step": 1780 }, { - "epoch": 0.92, - "learning_rate": 1.1842068802403016e-05, - "loss": 0.7625, + "epoch": 0.81, + "learning_rate": 1.3467918687401578e-05, + "loss": 0.7441, "step": 1781 }, { - "epoch": 0.92, - "learning_rate": 1.1833884141121442e-05, - "loss": 0.7166, + "epoch": 0.81, + "learning_rate": 1.3460997518576908e-05, + "loss": 0.7446, "step": 1782 }, { - "epoch": 0.92, - "learning_rate": 1.182569820839362e-05, - "loss": 0.7429, + "epoch": 0.81, + "learning_rate": 1.345407446571406e-05, + "loss": 0.7522, "step": 1783 }, { - "epoch": 0.92, - "learning_rate": 1.1817511009894917e-05, - "loss": 0.7144, + "epoch": 0.81, + "learning_rate": 1.3447149532581687e-05, + "loss": 0.7145, "step": 1784 }, { - "epoch": 0.92, - "learning_rate": 1.180932255130159e-05, - "loss": 0.77, + "epoch": 0.81, + "learning_rate": 1.3440222722949458e-05, + "loss": 0.7717, "step": 1785 }, { - "epoch": 0.92, - "learning_rate": 1.1801132838290755e-05, - "loss": 0.7273, + "epoch": 0.81, + "learning_rate": 1.3433294040588078e-05, + "loss": 0.7499, "step": 1786 }, { - "epoch": 0.92, - "learning_rate": 1.179294187654041e-05, - "loss": 0.7773, + "epoch": 0.81, + "learning_rate": 1.342636348926926e-05, + "loss": 0.7607, "step": 1787 }, { - "epoch": 0.92, - "learning_rate": 1.1784749671729402e-05, - "loss": 0.7551, + "epoch": 0.81, + "learning_rate": 1.3419431072765738e-05, + "loss": 0.7324, "step": 1788 }, { - "epoch": 0.92, - "learning_rate": 1.1776556229537461e-05, - "loss": 0.7346, + "epoch": 0.82, + "learning_rate": 1.3412496794851264e-05, + "loss": 0.7522, "step": 1789 }, { - "epoch": 0.92, - "learning_rate": 1.1768361555645164e-05, - "loss": 0.7542, + "epoch": 0.82, + "learning_rate": 1.3405560659300596e-05, + "loss": 0.73, "step": 1790 }, { - "epoch": 0.92, - "learning_rate": 1.1760165655733941e-05, - "loss": 0.667, + "epoch": 0.82, + "learning_rate": 1.3398622669889509e-05, + "loss": 0.7319, "step": 1791 }, { - "epoch": 0.92, - "learning_rate": 1.1751968535486073e-05, - "loss": 0.7732, + "epoch": 0.82, + "learning_rate": 1.3391682830394793e-05, + "loss": 0.7651, "step": 1792 }, { - "epoch": 0.92, - "learning_rate": 1.1743770200584685e-05, - "loss": 0.7236, + "epoch": 0.82, + "learning_rate": 1.3384741144594226e-05, + "loss": 0.8088, "step": 1793 }, { - "epoch": 0.92, - "learning_rate": 1.1735570656713749e-05, - "loss": 0.7681, + "epoch": 0.82, + "learning_rate": 1.3377797616266615e-05, + "loss": 0.7825, "step": 1794 }, { - "epoch": 0.92, - "learning_rate": 1.1727369909558078e-05, - "loss": 0.7019, + "epoch": 0.82, + "learning_rate": 1.3370852249191753e-05, + "loss": 0.7729, "step": 1795 }, { - "epoch": 0.92, - "learning_rate": 1.1719167964803306e-05, - "loss": 0.7336, + "epoch": 0.82, + "learning_rate": 1.3363905047150438e-05, + "loss": 0.7717, "step": 1796 }, { - "epoch": 0.92, - "learning_rate": 1.1710964828135913e-05, - "loss": 0.7058, + "epoch": 0.82, + "learning_rate": 1.3356956013924468e-05, + "loss": 0.7649, "step": 1797 }, { - "epoch": 0.92, - "learning_rate": 1.1702760505243191e-05, - "loss": 0.7532, + "epoch": 0.82, + "learning_rate": 1.3350005153296646e-05, + "loss": 0.7338, "step": 1798 }, { - "epoch": 0.92, - "learning_rate": 1.1694555001813265e-05, - "loss": 0.7261, + "epoch": 0.82, + "learning_rate": 1.334305246905075e-05, + "loss": 0.7283, "step": 1799 }, { - "epoch": 0.93, - "learning_rate": 1.1686348323535078e-05, - "loss": 0.676, + "epoch": 0.82, + "learning_rate": 1.3336097964971568e-05, + "loss": 0.7168, "step": 1800 }, { - "epoch": 0.93, - "learning_rate": 1.1678140476098379e-05, - "loss": 0.7202, + "epoch": 0.82, + "learning_rate": 1.3329141644844876e-05, + "loss": 0.728, "step": 1801 }, { - "epoch": 0.93, - "learning_rate": 1.1669931465193735e-05, - "loss": 0.7439, + "epoch": 0.82, + "learning_rate": 1.332218351245743e-05, + "loss": 0.7612, "step": 1802 }, { - "epoch": 0.93, - "learning_rate": 1.1661721296512516e-05, - "loss": 0.751, + "epoch": 0.82, + "learning_rate": 1.331522357159698e-05, + "loss": 0.8013, "step": 1803 }, { - "epoch": 0.93, - "learning_rate": 1.1653509975746899e-05, - "loss": 0.6973, + "epoch": 0.82, + "learning_rate": 1.3308261826052262e-05, + "loss": 0.7214, "step": 1804 }, { - "epoch": 0.93, - "learning_rate": 1.1645297508589856e-05, - "loss": 0.697, + "epoch": 0.82, + "learning_rate": 1.3301298279612984e-05, + "loss": 0.7522, "step": 1805 }, { - "epoch": 0.93, - "learning_rate": 1.1637083900735157e-05, - "loss": 0.7595, + "epoch": 0.82, + "learning_rate": 1.3294332936069849e-05, + "loss": 0.7649, "step": 1806 }, { - "epoch": 0.93, - "learning_rate": 1.1628869157877358e-05, - "loss": 0.7078, + "epoch": 0.82, + "learning_rate": 1.3287365799214529e-05, + "loss": 0.7598, "step": 1807 }, { - "epoch": 0.93, - "learning_rate": 1.1620653285711803e-05, - "loss": 0.7527, + "epoch": 0.82, + "learning_rate": 1.328039687283967e-05, + "loss": 0.7837, "step": 1808 }, { - "epoch": 0.93, - "learning_rate": 1.161243628993462e-05, - "loss": 0.7695, + "epoch": 0.82, + "learning_rate": 1.32734261607389e-05, + "loss": 0.7854, "step": 1809 }, { - "epoch": 0.93, - "learning_rate": 1.1604218176242725e-05, - "loss": 0.7083, + "epoch": 0.82, + "learning_rate": 1.3266453666706811e-05, + "loss": 0.771, "step": 1810 }, { - "epoch": 0.93, - "learning_rate": 1.1595998950333794e-05, - "loss": 0.7209, + "epoch": 0.83, + "learning_rate": 1.3259479394538975e-05, + "loss": 0.6985, "step": 1811 }, { - "epoch": 0.93, - "learning_rate": 1.158777861790628e-05, - "loss": 0.7075, + "epoch": 0.83, + "learning_rate": 1.325250334803192e-05, + "loss": 0.772, "step": 1812 }, { - "epoch": 0.93, - "learning_rate": 1.1579557184659404e-05, - "loss": 0.7937, + "epoch": 0.83, + "learning_rate": 1.324552553098315e-05, + "loss": 0.7241, "step": 1813 }, { - "epoch": 0.93, - "learning_rate": 1.1571334656293154e-05, - "loss": 0.7483, + "epoch": 0.83, + "learning_rate": 1.3238545947191127e-05, + "loss": 0.7302, "step": 1814 }, { - "epoch": 0.93, - "learning_rate": 1.156311103850827e-05, - "loss": 0.7388, + "epoch": 0.83, + "learning_rate": 1.3231564600455279e-05, + "loss": 0.7515, "step": 1815 }, { - "epoch": 0.93, - "learning_rate": 1.1554886337006254e-05, - "loss": 0.6929, + "epoch": 0.83, + "learning_rate": 1.3224581494575985e-05, + "loss": 0.7537, "step": 1816 }, { - "epoch": 0.93, - "learning_rate": 1.1546660557489354e-05, - "loss": 0.7449, + "epoch": 0.83, + "learning_rate": 1.3217596633354596e-05, + "loss": 0.7463, "step": 1817 }, { - "epoch": 0.93, - "learning_rate": 1.1538433705660561e-05, - "loss": 0.7288, + "epoch": 0.83, + "learning_rate": 1.3210610020593405e-05, + "loss": 0.7693, "step": 1818 }, { - "epoch": 0.93, - "learning_rate": 1.1530205787223624e-05, - "loss": 0.749, + "epoch": 0.83, + "learning_rate": 1.3203621660095665e-05, + "loss": 0.7098, "step": 1819 }, { - "epoch": 0.94, - "learning_rate": 1.1521976807883024e-05, - "loss": 0.751, + "epoch": 0.83, + "learning_rate": 1.319663155566558e-05, + "loss": 0.7528, "step": 1820 }, { - "epoch": 0.94, - "learning_rate": 1.1513746773343975e-05, - "loss": 0.7045, + "epoch": 0.83, + "learning_rate": 1.3189639711108301e-05, + "loss": 0.7687, "step": 1821 }, { - "epoch": 0.94, - "learning_rate": 1.1505515689312424e-05, - "loss": 0.7559, + "epoch": 0.83, + "learning_rate": 1.3182646130229929e-05, + "loss": 0.7656, "step": 1822 }, { - "epoch": 0.94, - "learning_rate": 1.149728356149504e-05, - "loss": 0.7305, + "epoch": 0.83, + "learning_rate": 1.317565081683751e-05, + "loss": 0.7739, "step": 1823 }, { - "epoch": 0.94, - "learning_rate": 1.1489050395599231e-05, - "loss": 0.7188, + "epoch": 0.83, + "learning_rate": 1.316865377473903e-05, + "loss": 0.6962, "step": 1824 }, { - "epoch": 0.94, - "learning_rate": 1.148081619733311e-05, - "loss": 0.7031, + "epoch": 0.83, + "learning_rate": 1.316165500774342e-05, + "loss": 0.7358, "step": 1825 }, { - "epoch": 0.94, - "learning_rate": 1.1472580972405519e-05, - "loss": 0.7185, + "epoch": 0.83, + "learning_rate": 1.315465451966055e-05, + "loss": 0.6897, "step": 1826 }, { - "epoch": 0.94, - "learning_rate": 1.1464344726525993e-05, - "loss": 0.7474, + "epoch": 0.83, + "learning_rate": 1.3147652314301218e-05, + "loss": 0.7423, "step": 1827 }, { - "epoch": 0.94, - "learning_rate": 1.1456107465404792e-05, - "loss": 0.7278, + "epoch": 0.83, + "learning_rate": 1.3140648395477171e-05, + "loss": 0.7411, "step": 1828 }, { - "epoch": 0.94, - "learning_rate": 1.1447869194752869e-05, - "loss": 0.7222, + "epoch": 0.83, + "learning_rate": 1.3133642767001077e-05, + "loss": 0.766, "step": 1829 }, { - "epoch": 0.94, - "learning_rate": 1.1439629920281889e-05, - "loss": 0.7456, + "epoch": 0.83, + "learning_rate": 1.3126635432686544e-05, + "loss": 0.7156, "step": 1830 }, { - "epoch": 0.94, - "learning_rate": 1.1431389647704203e-05, - "loss": 0.6912, + "epoch": 0.83, + "learning_rate": 1.31196263963481e-05, + "loss": 0.7014, "step": 1831 }, { - "epoch": 0.94, - "learning_rate": 1.1423148382732854e-05, - "loss": 0.6893, + "epoch": 0.83, + "learning_rate": 1.3112615661801202e-05, + "loss": 0.7211, "step": 1832 }, { - "epoch": 0.94, - "learning_rate": 1.1414906131081575e-05, - "loss": 0.6875, + "epoch": 0.84, + "learning_rate": 1.3105603232862239e-05, + "loss": 0.7278, "step": 1833 }, { - "epoch": 0.94, - "learning_rate": 1.1406662898464786e-05, - "loss": 0.7756, + "epoch": 0.84, + "learning_rate": 1.3098589113348513e-05, + "loss": 0.812, "step": 1834 }, { - "epoch": 0.94, - "learning_rate": 1.1398418690597585e-05, - "loss": 0.6943, + "epoch": 0.84, + "learning_rate": 1.3091573307078247e-05, + "loss": 0.6837, "step": 1835 }, { - "epoch": 0.94, - "learning_rate": 1.1390173513195747e-05, - "loss": 0.7551, + "epoch": 0.84, + "learning_rate": 1.3084555817870586e-05, + "loss": 0.7441, "step": 1836 }, { - "epoch": 0.94, - "learning_rate": 1.1381927371975716e-05, - "loss": 0.7344, + "epoch": 0.84, + "learning_rate": 1.3077536649545593e-05, + "loss": 0.7322, "step": 1837 }, { - "epoch": 0.94, - "learning_rate": 1.1373680272654606e-05, - "loss": 0.7561, + "epoch": 0.84, + "learning_rate": 1.3070515805924235e-05, + "loss": 0.84, "step": 1838 }, { - "epoch": 0.95, - "learning_rate": 1.1365432220950195e-05, - "loss": 0.7065, + "epoch": 0.84, + "learning_rate": 1.3063493290828405e-05, + "loss": 0.7795, "step": 1839 }, { - "epoch": 0.95, - "learning_rate": 1.1357183222580923e-05, - "loss": 0.7349, + "epoch": 0.84, + "learning_rate": 1.3056469108080899e-05, + "loss": 0.6643, "step": 1840 }, { - "epoch": 0.95, - "learning_rate": 1.1348933283265887e-05, - "loss": 0.7415, + "epoch": 0.84, + "learning_rate": 1.3049443261505412e-05, + "loss": 0.774, "step": 1841 }, { - "epoch": 0.95, - "learning_rate": 1.1340682408724834e-05, - "loss": 0.7964, + "epoch": 0.84, + "learning_rate": 1.3042415754926564e-05, + "loss": 0.7697, "step": 1842 }, { - "epoch": 0.95, - "learning_rate": 1.1332430604678158e-05, - "loss": 0.7083, + "epoch": 0.84, + "learning_rate": 1.303538659216986e-05, + "loss": 0.7203, "step": 1843 }, { - "epoch": 0.95, - "learning_rate": 1.1324177876846897e-05, - "loss": 0.7378, + "epoch": 0.84, + "learning_rate": 1.3028355777061718e-05, + "loss": 0.787, "step": 1844 }, { - "epoch": 0.95, - "learning_rate": 1.1315924230952742e-05, - "loss": 0.7334, + "epoch": 0.84, + "learning_rate": 1.3021323313429453e-05, + "loss": 0.7238, "step": 1845 }, { - "epoch": 0.95, - "learning_rate": 1.1307669672718e-05, - "loss": 0.7407, + "epoch": 0.84, + "learning_rate": 1.3014289205101271e-05, + "loss": 0.6912, "step": 1846 }, { - "epoch": 0.95, - "learning_rate": 1.1299414207865626e-05, - "loss": 0.7017, + "epoch": 0.84, + "learning_rate": 1.3007253455906286e-05, + "loss": 0.7043, "step": 1847 }, { - "epoch": 0.95, - "learning_rate": 1.1291157842119196e-05, - "loss": 0.7654, + "epoch": 0.84, + "learning_rate": 1.3000216069674494e-05, + "loss": 0.7266, "step": 1848 }, { - "epoch": 0.95, - "learning_rate": 1.1282900581202912e-05, - "loss": 0.7148, + "epoch": 0.84, + "learning_rate": 1.2993177050236782e-05, + "loss": 0.7145, "step": 1849 }, { - "epoch": 0.95, - "learning_rate": 1.1274642430841603e-05, - "loss": 0.7205, + "epoch": 0.84, + "learning_rate": 1.2986136401424937e-05, + "loss": 0.7218, "step": 1850 }, { - "epoch": 0.95, - "learning_rate": 1.1266383396760706e-05, - "loss": 0.739, + "epoch": 0.84, + "learning_rate": 1.2979094127071625e-05, + "loss": 0.7874, "step": 1851 }, { - "epoch": 0.95, - "learning_rate": 1.1258123484686277e-05, - "loss": 0.731, + "epoch": 0.84, + "learning_rate": 1.2972050231010393e-05, + "loss": 0.7102, "step": 1852 }, { - "epoch": 0.95, - "learning_rate": 1.1249862700344969e-05, - "loss": 0.7058, + "epoch": 0.84, + "learning_rate": 1.2965004717075682e-05, + "loss": 0.7954, "step": 1853 }, { - "epoch": 0.95, - "learning_rate": 1.1241601049464056e-05, - "loss": 0.7124, + "epoch": 0.84, + "learning_rate": 1.2957957589102801e-05, + "loss": 0.7294, "step": 1854 }, { - "epoch": 0.95, - "learning_rate": 1.1233338537771408e-05, - "loss": 0.7881, + "epoch": 0.85, + "learning_rate": 1.295090885092795e-05, + "loss": 0.7991, "step": 1855 }, { - "epoch": 0.95, - "learning_rate": 1.1225075170995485e-05, - "loss": 0.7522, + "epoch": 0.85, + "learning_rate": 1.2943858506388197e-05, + "loss": 0.6796, "step": 1856 }, { - "epoch": 0.95, - "learning_rate": 1.1216810954865342e-05, - "loss": 0.7803, + "epoch": 0.85, + "learning_rate": 1.2936806559321487e-05, + "loss": 0.7715, "step": 1857 }, { - "epoch": 0.96, - "learning_rate": 1.1208545895110623e-05, - "loss": 0.7307, + "epoch": 0.85, + "learning_rate": 1.2929753013566635e-05, + "loss": 0.7029, "step": 1858 }, { - "epoch": 0.96, - "learning_rate": 1.1200279997461568e-05, - "loss": 0.6858, + "epoch": 0.85, + "learning_rate": 1.2922697872963337e-05, + "loss": 0.7131, "step": 1859 }, { - "epoch": 0.96, - "learning_rate": 1.1192013267648982e-05, - "loss": 0.8108, + "epoch": 0.85, + "learning_rate": 1.2915641141352138e-05, + "loss": 0.7222, "step": 1860 }, { - "epoch": 0.96, - "learning_rate": 1.1183745711404257e-05, - "loss": 0.7258, + "epoch": 0.85, + "learning_rate": 1.2908582822574465e-05, + "loss": 0.6711, "step": 1861 }, { - "epoch": 0.96, - "learning_rate": 1.117547733445935e-05, - "loss": 0.731, + "epoch": 0.85, + "learning_rate": 1.2901522920472606e-05, + "loss": 0.7454, "step": 1862 }, { - "epoch": 0.96, - "learning_rate": 1.116720814254679e-05, - "loss": 0.7279, + "epoch": 0.85, + "learning_rate": 1.2894461438889707e-05, + "loss": 0.7627, "step": 1863 }, { - "epoch": 0.96, - "learning_rate": 1.115893814139968e-05, - "loss": 0.7002, + "epoch": 0.85, + "learning_rate": 1.2887398381669776e-05, + "loss": 0.7322, "step": 1864 }, { - "epoch": 0.96, - "learning_rate": 1.1150667336751675e-05, - "loss": 0.7822, + "epoch": 0.85, + "learning_rate": 1.2880333752657674e-05, + "loss": 0.7673, "step": 1865 }, { - "epoch": 0.96, - "learning_rate": 1.1142395734336986e-05, - "loss": 0.7036, + "epoch": 0.85, + "learning_rate": 1.2873267555699127e-05, + "loss": 0.7732, "step": 1866 }, { - "epoch": 0.96, - "learning_rate": 1.1134123339890376e-05, - "loss": 0.7078, + "epoch": 0.85, + "learning_rate": 1.2866199794640713e-05, + "loss": 0.793, "step": 1867 }, { - "epoch": 0.96, - "learning_rate": 1.1125850159147168e-05, - "loss": 0.738, + "epoch": 0.85, + "learning_rate": 1.2859130473329848e-05, + "loss": 0.6575, "step": 1868 }, { - "epoch": 0.96, - "learning_rate": 1.1117576197843223e-05, - "loss": 0.6881, + "epoch": 0.85, + "learning_rate": 1.2852059595614815e-05, + "loss": 0.7937, "step": 1869 }, { - "epoch": 0.96, - "learning_rate": 1.110930146171494e-05, - "loss": 0.6858, + "epoch": 0.85, + "learning_rate": 1.2844987165344734e-05, + "loss": 0.7175, "step": 1870 }, { - "epoch": 0.96, - "learning_rate": 1.1101025956499258e-05, - "loss": 0.7153, + "epoch": 0.85, + "learning_rate": 1.2837913186369571e-05, + "loss": 0.7025, "step": 1871 }, { - "epoch": 0.96, - "learning_rate": 1.109274968793365e-05, - "loss": 0.7471, + "epoch": 0.85, + "learning_rate": 1.2830837662540139e-05, + "loss": 0.6617, "step": 1872 }, { - "epoch": 0.96, - "learning_rate": 1.1084472661756119e-05, - "loss": 0.7212, + "epoch": 0.85, + "learning_rate": 1.2823760597708087e-05, + "loss": 0.7448, "step": 1873 }, { - "epoch": 0.96, - "learning_rate": 1.1076194883705194e-05, - "loss": 0.7349, + "epoch": 0.85, + "learning_rate": 1.281668199572591e-05, + "loss": 0.7471, "step": 1874 }, { - "epoch": 0.96, - "learning_rate": 1.1067916359519919e-05, - "loss": 0.6782, + "epoch": 0.85, + "learning_rate": 1.2809601860446937e-05, + "loss": 0.7095, "step": 1875 }, { - "epoch": 0.96, - "learning_rate": 1.1059637094939864e-05, - "loss": 0.6932, + "epoch": 0.85, + "learning_rate": 1.280252019572532e-05, + "loss": 0.769, "step": 1876 }, { - "epoch": 0.96, - "learning_rate": 1.1051357095705102e-05, - "loss": 0.7495, + "epoch": 0.86, + "learning_rate": 1.2795437005416063e-05, + "loss": 0.7815, "step": 1877 }, { - "epoch": 0.97, - "learning_rate": 1.1043076367556228e-05, - "loss": 0.7253, + "epoch": 0.86, + "learning_rate": 1.2788352293374989e-05, + "loss": 0.7974, "step": 1878 }, { - "epoch": 0.97, - "learning_rate": 1.1034794916234331e-05, - "loss": 0.7361, + "epoch": 0.86, + "learning_rate": 1.2781266063458749e-05, + "loss": 0.7507, "step": 1879 }, { - "epoch": 0.97, - "learning_rate": 1.102651274748101e-05, - "loss": 0.7351, + "epoch": 0.86, + "learning_rate": 1.2774178319524821e-05, + "loss": 0.7037, "step": 1880 }, { - "epoch": 0.97, - "learning_rate": 1.1018229867038358e-05, - "loss": 0.6624, + "epoch": 0.86, + "learning_rate": 1.2767089065431516e-05, + "loss": 0.7617, "step": 1881 }, { - "epoch": 0.97, - "learning_rate": 1.1009946280648953e-05, - "loss": 0.7031, + "epoch": 0.86, + "learning_rate": 1.2759998305037955e-05, + "loss": 0.704, "step": 1882 }, { - "epoch": 0.97, - "learning_rate": 1.1001661994055876e-05, - "loss": 0.6857, + "epoch": 0.86, + "learning_rate": 1.2752906042204085e-05, + "loss": 0.6782, "step": 1883 }, { - "epoch": 0.97, - "learning_rate": 1.099337701300269e-05, - "loss": 0.6993, + "epoch": 0.86, + "learning_rate": 1.2745812280790668e-05, + "loss": 0.7496, "step": 1884 }, { - "epoch": 0.97, - "learning_rate": 1.0985091343233437e-05, - "loss": 0.7354, + "epoch": 0.86, + "learning_rate": 1.2738717024659286e-05, + "loss": 0.7468, "step": 1885 }, { - "epoch": 0.97, - "learning_rate": 1.0976804990492633e-05, - "loss": 0.7305, + "epoch": 0.86, + "learning_rate": 1.2731620277672332e-05, + "loss": 0.6844, "step": 1886 }, { - "epoch": 0.97, - "learning_rate": 1.096851796052527e-05, - "loss": 0.7537, + "epoch": 0.86, + "learning_rate": 1.272452204369301e-05, + "loss": 0.715, "step": 1887 }, { - "epoch": 0.97, - "learning_rate": 1.0960230259076819e-05, - "loss": 0.7791, + "epoch": 0.86, + "learning_rate": 1.2717422326585333e-05, + "loss": 0.7302, "step": 1888 }, { - "epoch": 0.97, - "learning_rate": 1.0951941891893201e-05, - "loss": 0.7488, + "epoch": 0.86, + "learning_rate": 1.2710321130214128e-05, + "loss": 0.7163, "step": 1889 }, { - "epoch": 0.97, - "learning_rate": 1.0943652864720808e-05, - "loss": 0.7258, + "epoch": 0.86, + "learning_rate": 1.2703218458445012e-05, + "loss": 0.7036, "step": 1890 }, { - "epoch": 0.97, - "learning_rate": 1.0935363183306489e-05, - "loss": 0.7146, + "epoch": 0.86, + "learning_rate": 1.2696114315144424e-05, + "loss": 0.7375, "step": 1891 }, { - "epoch": 0.97, - "learning_rate": 1.0927072853397542e-05, - "loss": 0.7212, + "epoch": 0.86, + "learning_rate": 1.2689008704179596e-05, + "loss": 0.7422, "step": 1892 }, { - "epoch": 0.97, - "learning_rate": 1.091878188074172e-05, - "loss": 0.7341, + "epoch": 0.86, + "learning_rate": 1.2681901629418549e-05, + "loss": 0.7825, "step": 1893 }, { - "epoch": 0.97, - "learning_rate": 1.0910490271087219e-05, - "loss": 0.7285, + "epoch": 0.86, + "learning_rate": 1.2674793094730115e-05, + "loss": 0.7368, "step": 1894 }, { - "epoch": 0.97, - "learning_rate": 1.0902198030182677e-05, - "loss": 0.7957, + "epoch": 0.86, + "learning_rate": 1.2667683103983919e-05, + "loss": 0.7526, "step": 1895 }, { - "epoch": 0.97, - "learning_rate": 1.0893905163777172e-05, - "loss": 0.7253, + "epoch": 0.86, + "learning_rate": 1.266057166105037e-05, + "loss": 0.7216, "step": 1896 }, { - "epoch": 0.98, - "learning_rate": 1.0885611677620206e-05, - "loss": 0.7571, + "epoch": 0.86, + "learning_rate": 1.2653458769800673e-05, + "loss": 0.7666, "step": 1897 }, { - "epoch": 0.98, - "learning_rate": 1.0877317577461723e-05, - "loss": 0.7358, + "epoch": 0.86, + "learning_rate": 1.2646344434106828e-05, + "loss": 0.6843, "step": 1898 }, { - "epoch": 0.98, - "learning_rate": 1.0869022869052091e-05, - "loss": 0.7644, + "epoch": 0.87, + "learning_rate": 1.2639228657841605e-05, + "loss": 0.7542, "step": 1899 }, { - "epoch": 0.98, - "learning_rate": 1.0860727558142093e-05, - "loss": 0.7323, + "epoch": 0.87, + "learning_rate": 1.2632111444878574e-05, + "loss": 0.6997, "step": 1900 }, { - "epoch": 0.98, - "learning_rate": 1.085243165048293e-05, - "loss": 0.738, + "epoch": 0.87, + "learning_rate": 1.2624992799092075e-05, + "loss": 0.7521, "step": 1901 }, { - "epoch": 0.98, - "learning_rate": 1.084413515182622e-05, - "loss": 0.7615, + "epoch": 0.87, + "learning_rate": 1.2617872724357238e-05, + "loss": 0.7156, "step": 1902 }, { - "epoch": 0.98, - "learning_rate": 1.0835838067923997e-05, - "loss": 0.783, + "epoch": 0.87, + "learning_rate": 1.2610751224549971e-05, + "loss": 0.7112, "step": 1903 }, { - "epoch": 0.98, - "learning_rate": 1.0827540404528689e-05, - "loss": 0.7515, + "epoch": 0.87, + "learning_rate": 1.2603628303546944e-05, + "loss": 0.7223, "step": 1904 }, { - "epoch": 0.98, - "learning_rate": 1.0819242167393136e-05, - "loss": 0.719, + "epoch": 0.87, + "learning_rate": 1.2596503965225613e-05, + "loss": 0.7463, "step": 1905 }, { - "epoch": 0.98, - "learning_rate": 1.0810943362270563e-05, - "loss": 0.7983, + "epoch": 0.87, + "learning_rate": 1.2589378213464207e-05, + "loss": 0.7354, "step": 1906 }, { - "epoch": 0.98, - "learning_rate": 1.0802643994914601e-05, - "loss": 0.7087, + "epoch": 0.87, + "learning_rate": 1.2582251052141713e-05, + "loss": 0.755, "step": 1907 }, { - "epoch": 0.98, - "learning_rate": 1.0794344071079267e-05, - "loss": 0.7256, + "epoch": 0.87, + "learning_rate": 1.2575122485137898e-05, + "loss": 0.7175, "step": 1908 }, { - "epoch": 0.98, - "learning_rate": 1.0786043596518964e-05, - "loss": 0.7573, + "epoch": 0.87, + "learning_rate": 1.2567992516333287e-05, + "loss": 0.7209, "step": 1909 }, { - "epoch": 0.98, - "learning_rate": 1.0777742576988474e-05, - "loss": 0.6467, + "epoch": 0.87, + "learning_rate": 1.2560861149609166e-05, + "loss": 0.7008, "step": 1910 }, { - "epoch": 0.98, - "learning_rate": 1.0769441018242961e-05, - "loss": 0.6794, + "epoch": 0.87, + "learning_rate": 1.2553728388847593e-05, + "loss": 0.7146, "step": 1911 }, { - "epoch": 0.98, - "learning_rate": 1.0761138926037957e-05, - "loss": 0.7234, + "epoch": 0.87, + "learning_rate": 1.2546594237931368e-05, + "loss": 0.7349, "step": 1912 }, { - "epoch": 0.98, - "learning_rate": 1.0752836306129369e-05, - "loss": 0.6943, + "epoch": 0.87, + "learning_rate": 1.2539458700744065e-05, + "loss": 0.6799, "step": 1913 }, { - "epoch": 0.98, - "learning_rate": 1.0744533164273472e-05, - "loss": 0.6687, + "epoch": 0.87, + "learning_rate": 1.2532321781170002e-05, + "loss": 0.7445, "step": 1914 }, { - "epoch": 0.98, - "learning_rate": 1.0736229506226896e-05, - "loss": 0.7026, + "epoch": 0.87, + "learning_rate": 1.252518348309425e-05, + "loss": 0.7467, "step": 1915 }, { - "epoch": 0.98, - "learning_rate": 1.0727925337746633e-05, - "loss": 0.686, + "epoch": 0.87, + "learning_rate": 1.2518043810402633e-05, + "loss": 0.7339, "step": 1916 }, { - "epoch": 0.99, - "learning_rate": 1.0719620664590027e-05, - "loss": 0.7415, + "epoch": 0.87, + "learning_rate": 1.251090276698173e-05, + "loss": 0.7175, "step": 1917 }, { - "epoch": 0.99, - "learning_rate": 1.0711315492514773e-05, - "loss": 0.7048, + "epoch": 0.87, + "learning_rate": 1.2503760356718848e-05, + "loss": 0.7581, "step": 1918 }, { - "epoch": 0.99, - "learning_rate": 1.0703009827278916e-05, - "loss": 0.6853, + "epoch": 0.87, + "learning_rate": 1.2496616583502056e-05, + "loss": 0.7484, "step": 1919 }, { - "epoch": 0.99, - "learning_rate": 1.0694703674640835e-05, - "loss": 0.7405, + "epoch": 0.87, + "learning_rate": 1.248947145122016e-05, + "loss": 0.724, "step": 1920 }, { - "epoch": 0.99, - "learning_rate": 1.0686397040359253e-05, - "loss": 0.7598, + "epoch": 0.88, + "learning_rate": 1.24823249637627e-05, + "loss": 0.7273, "step": 1921 }, { - "epoch": 0.99, - "learning_rate": 1.067808993019322e-05, - "loss": 0.7322, + "epoch": 0.88, + "learning_rate": 1.247517712501996e-05, + "loss": 0.7559, "step": 1922 }, { - "epoch": 0.99, - "learning_rate": 1.0669782349902122e-05, - "loss": 0.7754, + "epoch": 0.88, + "learning_rate": 1.2468027938882952e-05, + "loss": 0.7478, "step": 1923 }, { - "epoch": 0.99, - "learning_rate": 1.0661474305245677e-05, - "loss": 0.7234, + "epoch": 0.88, + "learning_rate": 1.246087740924343e-05, + "loss": 0.7168, "step": 1924 }, { - "epoch": 0.99, - "learning_rate": 1.0653165801983907e-05, - "loss": 0.738, + "epoch": 0.88, + "learning_rate": 1.2453725539993882e-05, + "loss": 0.7529, "step": 1925 }, { - "epoch": 0.99, - "learning_rate": 1.0644856845877169e-05, - "loss": 0.7869, + "epoch": 0.88, + "learning_rate": 1.244657233502751e-05, + "loss": 0.7582, "step": 1926 }, { - "epoch": 0.99, - "learning_rate": 1.0636547442686124e-05, - "loss": 0.7402, + "epoch": 0.88, + "learning_rate": 1.2439417798238255e-05, + "loss": 0.7537, "step": 1927 }, { - "epoch": 0.99, - "learning_rate": 1.0628237598171749e-05, - "loss": 0.7249, + "epoch": 0.88, + "learning_rate": 1.2432261933520789e-05, + "loss": 0.6842, "step": 1928 }, { - "epoch": 0.99, - "learning_rate": 1.0619927318095322e-05, - "loss": 0.6655, + "epoch": 0.88, + "learning_rate": 1.2425104744770485e-05, + "loss": 0.7322, "step": 1929 }, { - "epoch": 0.99, - "learning_rate": 1.0611616608218429e-05, - "loss": 0.7281, + "epoch": 0.88, + "learning_rate": 1.2417946235883456e-05, + "loss": 0.7073, "step": 1930 }, { - "epoch": 0.99, - "learning_rate": 1.0603305474302947e-05, - "loss": 0.7134, + "epoch": 0.88, + "learning_rate": 1.2410786410756532e-05, + "loss": 0.7317, "step": 1931 }, { - "epoch": 0.99, - "learning_rate": 1.059499392211105e-05, - "loss": 0.7551, + "epoch": 0.88, + "learning_rate": 1.2403625273287248e-05, + "loss": 0.743, "step": 1932 }, { - "epoch": 0.99, - "learning_rate": 1.0586681957405202e-05, - "loss": 0.7522, + "epoch": 0.88, + "learning_rate": 1.2396462827373865e-05, + "loss": 0.7756, "step": 1933 }, { - "epoch": 0.99, - "learning_rate": 1.0578369585948155e-05, - "loss": 0.7019, + "epoch": 0.88, + "learning_rate": 1.2389299076915351e-05, + "loss": 0.7168, "step": 1934 }, { - "epoch": 0.99, - "learning_rate": 1.0570056813502945e-05, - "loss": 0.7351, + "epoch": 0.88, + "learning_rate": 1.2382134025811384e-05, + "loss": 0.7168, "step": 1935 }, { - "epoch": 1.0, - "learning_rate": 1.0561743645832876e-05, - "loss": 0.77, + "epoch": 0.88, + "learning_rate": 1.2374967677962353e-05, + "loss": 0.7339, "step": 1936 }, { - "epoch": 1.0, - "learning_rate": 1.0553430088701533e-05, - "loss": 0.6638, + "epoch": 0.88, + "learning_rate": 1.2367800037269348e-05, + "loss": 0.7134, "step": 1937 }, { - "epoch": 1.0, - "learning_rate": 1.0545116147872771e-05, - "loss": 0.7869, + "epoch": 0.88, + "learning_rate": 1.2360631107634167e-05, + "loss": 0.6885, "step": 1938 }, { - "epoch": 1.0, - "learning_rate": 1.0536801829110714e-05, - "loss": 0.729, + "epoch": 0.88, + "learning_rate": 1.2353460892959311e-05, + "loss": 0.7635, "step": 1939 }, { - "epoch": 1.0, - "learning_rate": 1.0528487138179741e-05, - "loss": 0.6992, + "epoch": 0.88, + "learning_rate": 1.2346289397147971e-05, + "loss": 0.7104, "step": 1940 }, { - "epoch": 1.0, - "learning_rate": 1.0520172080844495e-05, - "loss": 0.7769, + "epoch": 0.88, + "learning_rate": 1.233911662410405e-05, + "loss": 0.7539, "step": 1941 }, { - "epoch": 1.0, - "learning_rate": 1.0511856662869865e-05, - "loss": 0.7839, + "epoch": 0.88, + "learning_rate": 1.2331942577732137e-05, + "loss": 0.7517, "step": 1942 }, { - "epoch": 1.0, - "learning_rate": 1.0503540890020997e-05, - "loss": 0.7263, + "epoch": 0.89, + "learning_rate": 1.232476726193751e-05, + "loss": 0.7346, "step": 1943 }, { - "epoch": 1.0, - "learning_rate": 1.0495224768063288e-05, - "loss": 0.8005, + "epoch": 0.89, + "learning_rate": 1.2317590680626152e-05, + "loss": 0.7407, "step": 1944 }, { - "epoch": 1.0, - "learning_rate": 1.0486908302762364e-05, - "loss": 0.687, + "epoch": 0.89, + "learning_rate": 1.231041283770472e-05, + "loss": 0.7246, "step": 1945 }, { - "epoch": 1.0, - "learning_rate": 1.0478591499884099e-05, - "loss": 0.7246, + "epoch": 0.89, + "learning_rate": 1.2303233737080567e-05, + "loss": 0.7222, "step": 1946 }, { - "epoch": 1.0, - "learning_rate": 1.0470274365194592e-05, - "loss": 0.6256, + "epoch": 0.89, + "learning_rate": 1.229605338266173e-05, + "loss": 0.7524, "step": 1947 }, { - "epoch": 1.0, - "learning_rate": 1.0461956904460182e-05, - "loss": 0.6088, + "epoch": 0.89, + "learning_rate": 1.2288871778356923e-05, + "loss": 0.7598, "step": 1948 }, { - "epoch": 1.0, - "learning_rate": 1.0453639123447431e-05, - "loss": 0.6617, + "epoch": 0.89, + "learning_rate": 1.2281688928075544e-05, + "loss": 0.6888, "step": 1949 }, { - "epoch": 1.0, - "learning_rate": 1.0445321027923123e-05, - "loss": 0.6104, + "epoch": 0.89, + "learning_rate": 1.2274504835727675e-05, + "loss": 0.7542, "step": 1950 }, { - "epoch": 1.0, - "learning_rate": 1.0437002623654256e-05, - "loss": 0.6262, + "epoch": 0.89, + "learning_rate": 1.2267319505224062e-05, + "loss": 0.7678, "step": 1951 }, { - "epoch": 1.0, - "learning_rate": 1.0428683916408038e-05, - "loss": 0.6381, + "epoch": 0.89, + "learning_rate": 1.2260132940476132e-05, + "loss": 0.7401, "step": 1952 }, { - "epoch": 1.0, - "learning_rate": 1.0420364911951906e-05, - "loss": 0.615, + "epoch": 0.89, + "learning_rate": 1.225294514539599e-05, + "loss": 0.7522, "step": 1953 }, { - "epoch": 1.0, - "learning_rate": 1.0412045616053486e-05, - "loss": 0.5698, + "epoch": 0.89, + "learning_rate": 1.2245756123896394e-05, + "loss": 0.7421, "step": 1954 }, { - "epoch": 1.0, - "learning_rate": 1.040372603448061e-05, - "loss": 0.6215, + "epoch": 0.89, + "learning_rate": 1.2238565879890783e-05, + "loss": 0.7236, "step": 1955 }, { - "epoch": 1.01, - "learning_rate": 1.0395406173001313e-05, - "loss": 0.6169, + "epoch": 0.89, + "learning_rate": 1.2231374417293265e-05, + "loss": 0.6813, "step": 1956 }, { - "epoch": 1.01, - "learning_rate": 1.0387086037383809e-05, - "loss": 0.6069, + "epoch": 0.89, + "learning_rate": 1.2224181740018595e-05, + "loss": 0.752, "step": 1957 }, { - "epoch": 1.01, - "learning_rate": 1.0378765633396526e-05, - "loss": 0.6089, + "epoch": 0.89, + "learning_rate": 1.2216987851982204e-05, + "loss": 0.7312, "step": 1958 }, { - "epoch": 1.01, - "learning_rate": 1.0370444966808062e-05, - "loss": 0.5735, + "epoch": 0.89, + "learning_rate": 1.2209792757100175e-05, + "loss": 0.7256, "step": 1959 }, { - "epoch": 1.01, - "learning_rate": 1.03621240433872e-05, - "loss": 0.6382, + "epoch": 0.89, + "learning_rate": 1.2202596459289251e-05, + "loss": 0.8055, "step": 1960 }, { - "epoch": 1.01, - "learning_rate": 1.0353802868902899e-05, - "loss": 0.63, + "epoch": 0.89, + "learning_rate": 1.2195398962466829e-05, + "loss": 0.7556, "step": 1961 }, { - "epoch": 1.01, - "learning_rate": 1.0345481449124293e-05, - "loss": 0.5972, + "epoch": 0.89, + "learning_rate": 1.2188200270550956e-05, + "loss": 0.7346, "step": 1962 }, { - "epoch": 1.01, - "learning_rate": 1.0337159789820692e-05, - "loss": 0.5979, + "epoch": 0.89, + "learning_rate": 1.2181000387460332e-05, + "loss": 0.7212, "step": 1963 }, { - "epoch": 1.01, - "learning_rate": 1.032883789676157e-05, - "loss": 0.6257, + "epoch": 0.89, + "learning_rate": 1.2173799317114308e-05, + "loss": 0.7749, "step": 1964 }, { - "epoch": 1.01, - "learning_rate": 1.0320515775716556e-05, - "loss": 0.6685, + "epoch": 0.9, + "learning_rate": 1.2166597063432874e-05, + "loss": 0.7162, "step": 1965 }, { - "epoch": 1.01, - "learning_rate": 1.0312193432455438e-05, - "loss": 0.5996, + "epoch": 0.9, + "learning_rate": 1.2159393630336673e-05, + "loss": 0.7417, "step": 1966 }, { - "epoch": 1.01, - "learning_rate": 1.0303870872748167e-05, - "loss": 0.599, + "epoch": 0.9, + "learning_rate": 1.2152189021746987e-05, + "loss": 0.7073, "step": 1967 }, { - "epoch": 1.01, - "learning_rate": 1.0295548102364841e-05, - "loss": 0.6278, + "epoch": 0.9, + "learning_rate": 1.2144983241585731e-05, + "loss": 0.7131, "step": 1968 }, { - "epoch": 1.01, - "learning_rate": 1.02872251270757e-05, - "loss": 0.5989, + "epoch": 0.9, + "learning_rate": 1.2137776293775465e-05, + "loss": 0.7007, "step": 1969 }, { - "epoch": 1.01, - "learning_rate": 1.0278901952651126e-05, - "loss": 0.5792, + "epoch": 0.9, + "learning_rate": 1.2130568182239389e-05, + "loss": 0.7666, "step": 1970 }, { - "epoch": 1.01, - "learning_rate": 1.027057858486164e-05, - "loss": 0.5952, + "epoch": 0.9, + "learning_rate": 1.2123358910901322e-05, + "loss": 0.783, "step": 1971 }, { - "epoch": 1.01, - "learning_rate": 1.02622550294779e-05, - "loss": 0.6317, + "epoch": 0.9, + "learning_rate": 1.2116148483685727e-05, + "loss": 0.7479, "step": 1972 }, { - "epoch": 1.01, - "learning_rate": 1.0253931292270695e-05, - "loss": 0.6272, + "epoch": 0.9, + "learning_rate": 1.2108936904517694e-05, + "loss": 0.7172, "step": 1973 }, { - "epoch": 1.01, - "learning_rate": 1.0245607379010938e-05, - "loss": 0.656, + "epoch": 0.9, + "learning_rate": 1.2101724177322931e-05, + "loss": 0.7563, "step": 1974 }, { - "epoch": 1.02, - "learning_rate": 1.0237283295469655e-05, - "loss": 0.6521, + "epoch": 0.9, + "learning_rate": 1.209451030602779e-05, + "loss": 0.7629, "step": 1975 }, { - "epoch": 1.02, - "learning_rate": 1.0228959047418005e-05, - "loss": 0.647, + "epoch": 0.9, + "learning_rate": 1.2087295294559223e-05, + "loss": 0.6624, "step": 1976 }, { - "epoch": 1.02, - "learning_rate": 1.0220634640627252e-05, - "loss": 0.5795, + "epoch": 0.9, + "learning_rate": 1.2080079146844819e-05, + "loss": 0.7413, "step": 1977 }, { - "epoch": 1.02, - "learning_rate": 1.0212310080868774e-05, - "loss": 0.6385, + "epoch": 0.9, + "learning_rate": 1.2072861866812777e-05, + "loss": 0.7562, "step": 1978 }, { - "epoch": 1.02, - "learning_rate": 1.0203985373914056e-05, - "loss": 0.6222, + "epoch": 0.9, + "learning_rate": 1.206564345839192e-05, + "loss": 0.7686, "step": 1979 }, { - "epoch": 1.02, - "learning_rate": 1.0195660525534677e-05, - "loss": 0.6223, + "epoch": 0.9, + "learning_rate": 1.2058423925511677e-05, + "loss": 0.7415, "step": 1980 }, { - "epoch": 1.02, - "learning_rate": 1.0187335541502321e-05, - "loss": 0.5988, + "epoch": 0.9, + "learning_rate": 1.2051203272102095e-05, + "loss": 0.7396, "step": 1981 }, { - "epoch": 1.02, - "learning_rate": 1.0179010427588765e-05, - "loss": 0.6113, + "epoch": 0.9, + "learning_rate": 1.2043981502093824e-05, + "loss": 0.7676, "step": 1982 }, { - "epoch": 1.02, - "learning_rate": 1.0170685189565878e-05, - "loss": 0.6252, + "epoch": 0.9, + "learning_rate": 1.2036758619418137e-05, + "loss": 0.7095, "step": 1983 }, { - "epoch": 1.02, - "learning_rate": 1.0162359833205613e-05, - "loss": 0.5636, + "epoch": 0.9, + "learning_rate": 1.2029534628006892e-05, + "loss": 0.7688, "step": 1984 }, { - "epoch": 1.02, - "learning_rate": 1.0154034364280003e-05, - "loss": 0.627, + "epoch": 0.9, + "learning_rate": 1.2022309531792565e-05, + "loss": 0.7223, "step": 1985 }, { - "epoch": 1.02, - "learning_rate": 1.0145708788561157e-05, - "loss": 0.5862, + "epoch": 0.9, + "learning_rate": 1.2015083334708228e-05, + "loss": 0.7483, "step": 1986 }, { - "epoch": 1.02, - "learning_rate": 1.0137383111821267e-05, - "loss": 0.5946, + "epoch": 0.91, + "learning_rate": 1.2007856040687558e-05, + "loss": 0.7856, "step": 1987 }, { - "epoch": 1.02, - "learning_rate": 1.0129057339832592e-05, - "loss": 0.6356, + "epoch": 0.91, + "learning_rate": 1.2000627653664818e-05, + "loss": 0.7311, "step": 1988 }, { - "epoch": 1.02, - "learning_rate": 1.012073147836745e-05, - "loss": 0.6248, + "epoch": 0.91, + "learning_rate": 1.199339817757488e-05, + "loss": 0.7471, "step": 1989 }, { - "epoch": 1.02, - "learning_rate": 1.0112405533198228e-05, - "loss": 0.6346, + "epoch": 0.91, + "learning_rate": 1.1986167616353194e-05, + "loss": 0.7336, "step": 1990 }, { - "epoch": 1.02, - "learning_rate": 1.0104079510097367e-05, - "loss": 0.6353, + "epoch": 0.91, + "learning_rate": 1.1978935973935815e-05, + "loss": 0.7483, "step": 1991 }, { - "epoch": 1.02, - "learning_rate": 1.0095753414837366e-05, - "loss": 0.593, + "epoch": 0.91, + "learning_rate": 1.1971703254259376e-05, + "loss": 0.7361, "step": 1992 }, { - "epoch": 1.02, - "learning_rate": 1.0087427253190775e-05, - "loss": 0.6428, + "epoch": 0.91, + "learning_rate": 1.1964469461261103e-05, + "loss": 0.728, "step": 1993 }, { - "epoch": 1.02, - "learning_rate": 1.0079101030930183e-05, - "loss": 0.6044, + "epoch": 0.91, + "learning_rate": 1.1957234598878802e-05, + "loss": 0.7106, "step": 1994 }, { - "epoch": 1.03, - "learning_rate": 1.0070774753828228e-05, - "loss": 0.6235, + "epoch": 0.91, + "learning_rate": 1.1949998671050862e-05, + "loss": 0.7289, "step": 1995 }, { - "epoch": 1.03, - "learning_rate": 1.0062448427657575e-05, - "loss": 0.6261, + "epoch": 0.91, + "learning_rate": 1.194276168171625e-05, + "loss": 0.7161, "step": 1996 }, { - "epoch": 1.03, - "learning_rate": 1.0054122058190943e-05, - "loss": 0.5815, + "epoch": 0.91, + "learning_rate": 1.1935523634814522e-05, + "loss": 0.7283, "step": 1997 }, { - "epoch": 1.03, - "learning_rate": 1.0045795651201062e-05, - "loss": 0.6282, + "epoch": 0.91, + "learning_rate": 1.1928284534285793e-05, + "loss": 0.7369, "step": 1998 }, { - "epoch": 1.03, - "learning_rate": 1.00374692124607e-05, - "loss": 0.6022, + "epoch": 0.91, + "learning_rate": 1.1921044384070763e-05, + "loss": 0.7461, "step": 1999 }, { - "epoch": 1.03, - "learning_rate": 1.0029142747742637e-05, - "loss": 0.6418, + "epoch": 0.91, + "learning_rate": 1.1913803188110702e-05, + "loss": 0.6992, "step": 2000 }, { - "epoch": 1.03, - "learning_rate": 1.0020816262819678e-05, - "loss": 0.5807, + "epoch": 0.91, + "learning_rate": 1.1906560950347444e-05, + "loss": 0.7448, "step": 2001 }, { - "epoch": 1.03, - "learning_rate": 1.0012489763464639e-05, - "loss": 0.5817, + "epoch": 0.91, + "learning_rate": 1.1899317674723394e-05, + "loss": 0.7278, "step": 2002 }, { - "epoch": 1.03, - "learning_rate": 1.0004163255450355e-05, - "loss": 0.6149, + "epoch": 0.91, + "learning_rate": 1.1892073365181525e-05, + "loss": 0.7583, "step": 2003 }, { - "epoch": 1.03, - "learning_rate": 9.99583674454965e-06, - "loss": 0.6375, + "epoch": 0.91, + "learning_rate": 1.1884828025665364e-05, + "loss": 0.7805, "step": 2004 }, { - "epoch": 1.03, - "learning_rate": 9.987510236535363e-06, - "loss": 0.5782, + "epoch": 0.91, + "learning_rate": 1.187758166011901e-05, + "loss": 0.7465, "step": 2005 }, { - "epoch": 1.03, - "learning_rate": 9.979183737180324e-06, - "loss": 0.577, + "epoch": 0.91, + "learning_rate": 1.1870334272487111e-05, + "loss": 0.709, "step": 2006 }, { - "epoch": 1.03, - "learning_rate": 9.970857252257368e-06, - "loss": 0.5455, + "epoch": 0.91, + "learning_rate": 1.1863085866714875e-05, + "loss": 0.7341, "step": 2007 }, { - "epoch": 1.03, - "learning_rate": 9.962530787539305e-06, - "loss": 0.6572, + "epoch": 0.91, + "learning_rate": 1.1855836446748064e-05, + "loss": 0.7129, "step": 2008 }, { - "epoch": 1.03, - "learning_rate": 9.954204348798938e-06, - "loss": 0.6007, + "epoch": 0.92, + "learning_rate": 1.1848586016532994e-05, + "loss": 0.6979, "step": 2009 }, { - "epoch": 1.03, - "learning_rate": 9.945877941809059e-06, - "loss": 0.5775, + "epoch": 0.92, + "learning_rate": 1.1841334580016528e-05, + "loss": 0.7516, "step": 2010 }, { - "epoch": 1.03, - "learning_rate": 9.937551572342426e-06, - "loss": 0.5924, + "epoch": 0.92, + "learning_rate": 1.1834082141146079e-05, + "loss": 0.7568, "step": 2011 }, { - "epoch": 1.03, - "learning_rate": 9.929225246171776e-06, - "loss": 0.6025, + "epoch": 0.92, + "learning_rate": 1.1826828703869603e-05, + "loss": 0.7462, "step": 2012 }, { - "epoch": 1.03, - "learning_rate": 9.92089896906982e-06, - "loss": 0.6427, + "epoch": 0.92, + "learning_rate": 1.1819574272135603e-05, + "loss": 0.7457, "step": 2013 }, { - "epoch": 1.04, - "learning_rate": 9.912572746809228e-06, - "loss": 0.6229, + "epoch": 0.92, + "learning_rate": 1.1812318849893123e-05, + "loss": 0.7306, "step": 2014 }, { - "epoch": 1.04, - "learning_rate": 9.904246585162637e-06, - "loss": 0.6311, + "epoch": 0.92, + "learning_rate": 1.1805062441091739e-05, + "loss": 0.7554, "step": 2015 }, { - "epoch": 1.04, - "learning_rate": 9.895920489902634e-06, - "loss": 0.6119, + "epoch": 0.92, + "learning_rate": 1.1797805049681577e-05, + "loss": 0.7058, "step": 2016 }, { - "epoch": 1.04, - "learning_rate": 9.887594466801777e-06, - "loss": 0.6482, + "epoch": 0.92, + "learning_rate": 1.1790546679613285e-05, + "loss": 0.7522, "step": 2017 }, { - "epoch": 1.04, - "learning_rate": 9.879268521632555e-06, - "loss": 0.6274, + "epoch": 0.92, + "learning_rate": 1.1783287334838049e-05, + "loss": 0.7639, "step": 2018 }, { - "epoch": 1.04, - "learning_rate": 9.87094266016741e-06, - "loss": 0.5975, + "epoch": 0.92, + "learning_rate": 1.1776027019307592e-05, + "loss": 0.7673, "step": 2019 }, { - "epoch": 1.04, - "learning_rate": 9.862616888178733e-06, - "loss": 0.5989, + "epoch": 0.92, + "learning_rate": 1.1768765736974152e-05, + "loss": 0.6968, "step": 2020 }, { - "epoch": 1.04, - "learning_rate": 9.854291211438846e-06, - "loss": 0.5793, + "epoch": 0.92, + "learning_rate": 1.1761503491790506e-05, + "loss": 0.7408, "step": 2021 }, { - "epoch": 1.04, - "learning_rate": 9.84596563572e-06, - "loss": 0.6357, + "epoch": 0.92, + "learning_rate": 1.1754240287709951e-05, + "loss": 0.6591, "step": 2022 }, { - "epoch": 1.04, - "learning_rate": 9.83764016679439e-06, - "loss": 0.6133, + "epoch": 0.92, + "learning_rate": 1.1746976128686298e-05, + "loss": 0.7634, "step": 2023 }, { - "epoch": 1.04, - "learning_rate": 9.829314810434123e-06, - "loss": 0.5616, + "epoch": 0.92, + "learning_rate": 1.1739711018673892e-05, + "loss": 0.7646, "step": 2024 }, { - "epoch": 1.04, - "learning_rate": 9.820989572411238e-06, - "loss": 0.6055, + "epoch": 0.92, + "learning_rate": 1.1732444961627584e-05, + "loss": 0.8162, "step": 2025 }, { - "epoch": 1.04, - "learning_rate": 9.812664458497682e-06, - "loss": 0.6606, + "epoch": 0.92, + "learning_rate": 1.1725177961502745e-05, + "loss": 0.7252, "step": 2026 }, { - "epoch": 1.04, - "learning_rate": 9.804339474465328e-06, - "loss": 0.6278, + "epoch": 0.92, + "learning_rate": 1.1717910022255261e-05, + "loss": 0.7749, "step": 2027 }, { - "epoch": 1.04, - "learning_rate": 9.79601462608595e-06, - "loss": 0.6208, + "epoch": 0.92, + "learning_rate": 1.1710641147841529e-05, + "loss": 0.7673, "step": 2028 }, { - "epoch": 1.04, - "learning_rate": 9.787689919131226e-06, - "loss": 0.6606, + "epoch": 0.92, + "learning_rate": 1.170337134221845e-05, + "loss": 0.7241, "step": 2029 }, { - "epoch": 1.04, - "learning_rate": 9.77936535937275e-06, - "loss": 0.6487, + "epoch": 0.92, + "learning_rate": 1.1696100609343439e-05, + "loss": 0.7493, "step": 2030 }, { - "epoch": 1.04, - "learning_rate": 9.771040952581998e-06, - "loss": 0.5975, + "epoch": 0.93, + "learning_rate": 1.1688828953174408e-05, + "loss": 0.7668, "step": 2031 }, { - "epoch": 1.04, - "learning_rate": 9.762716704530346e-06, - "loss": 0.5861, + "epoch": 0.93, + "learning_rate": 1.1681556377669777e-05, + "loss": 0.7034, "step": 2032 }, { - "epoch": 1.04, - "learning_rate": 9.754392620989065e-06, - "loss": 0.6404, + "epoch": 0.93, + "learning_rate": 1.1674282886788468e-05, + "loss": 0.7328, "step": 2033 }, { - "epoch": 1.05, - "learning_rate": 9.746068707729306e-06, - "loss": 0.6376, + "epoch": 0.93, + "learning_rate": 1.1667008484489897e-05, + "loss": 0.7363, "step": 2034 }, { - "epoch": 1.05, - "learning_rate": 9.737744970522101e-06, - "loss": 0.6099, + "epoch": 0.93, + "learning_rate": 1.1659733174733976e-05, + "loss": 0.7169, "step": 2035 }, { - "epoch": 1.05, - "learning_rate": 9.729421415138362e-06, - "loss": 0.5934, + "epoch": 0.93, + "learning_rate": 1.1652456961481117e-05, + "loss": 0.7047, "step": 2036 }, { - "epoch": 1.05, - "learning_rate": 9.72109804734888e-06, - "loss": 0.6254, + "epoch": 0.93, + "learning_rate": 1.1645179848692218e-05, + "loss": 0.7881, "step": 2037 }, { - "epoch": 1.05, - "learning_rate": 9.712774872924305e-06, - "loss": 0.6306, + "epoch": 0.93, + "learning_rate": 1.1637901840328665e-05, + "loss": 0.7834, "step": 2038 }, { - "epoch": 1.05, - "learning_rate": 9.704451897635159e-06, - "loss": 0.6312, + "epoch": 0.93, + "learning_rate": 1.163062294035234e-05, + "loss": 0.7179, "step": 2039 }, { - "epoch": 1.05, - "learning_rate": 9.696129127251833e-06, - "loss": 0.6024, + "epoch": 0.93, + "learning_rate": 1.1623343152725599e-05, + "loss": 0.6996, "step": 2040 }, { - "epoch": 1.05, - "learning_rate": 9.687806567544566e-06, - "loss": 0.6063, + "epoch": 0.93, + "learning_rate": 1.161606248141129e-05, + "loss": 0.7091, "step": 2041 }, { - "epoch": 1.05, - "learning_rate": 9.67948422428345e-06, - "loss": 0.5857, + "epoch": 0.93, + "learning_rate": 1.1608780930372741e-05, + "loss": 0.8042, "step": 2042 }, { - "epoch": 1.05, - "learning_rate": 9.671162103238435e-06, - "loss": 0.629, + "epoch": 0.93, + "learning_rate": 1.1601498503573756e-05, + "loss": 0.6908, "step": 2043 }, { - "epoch": 1.05, - "learning_rate": 9.66284021017931e-06, - "loss": 0.6335, + "epoch": 0.93, + "learning_rate": 1.1594215204978618e-05, + "loss": 0.7122, "step": 2044 }, { - "epoch": 1.05, - "learning_rate": 9.65451855087571e-06, - "loss": 0.5989, + "epoch": 0.93, + "learning_rate": 1.1586931038552083e-05, + "loss": 0.6851, "step": 2045 }, { - "epoch": 1.05, - "learning_rate": 9.646197131097106e-06, - "loss": 0.6024, + "epoch": 0.93, + "learning_rate": 1.1579646008259377e-05, + "loss": 0.7245, "step": 2046 }, { - "epoch": 1.05, - "learning_rate": 9.637875956612805e-06, - "loss": 0.6305, + "epoch": 0.93, + "learning_rate": 1.1572360118066208e-05, + "loss": 0.7454, "step": 2047 }, { - "epoch": 1.05, - "learning_rate": 9.629555033191937e-06, - "loss": 0.5994, + "epoch": 0.93, + "learning_rate": 1.1565073371938733e-05, + "loss": 0.7222, "step": 2048 }, { - "epoch": 1.05, - "learning_rate": 9.621234366603474e-06, - "loss": 0.6339, + "epoch": 0.93, + "learning_rate": 1.1557785773843589e-05, + "loss": 0.7148, "step": 2049 }, { - "epoch": 1.05, - "learning_rate": 9.612913962616191e-06, - "loss": 0.6154, + "epoch": 0.93, + "learning_rate": 1.1550497327747877e-05, + "loss": 0.7021, "step": 2050 }, { - "epoch": 1.05, - "learning_rate": 9.604593826998692e-06, - "loss": 0.5769, + "epoch": 0.93, + "learning_rate": 1.1543208037619147e-05, + "loss": 0.6863, "step": 2051 }, { - "epoch": 1.05, - "learning_rate": 9.596273965519393e-06, - "loss": 0.5808, + "epoch": 0.93, + "learning_rate": 1.1535917907425426e-05, + "loss": 0.7428, "step": 2052 }, { - "epoch": 1.06, - "learning_rate": 9.587954383946518e-06, - "loss": 0.6072, + "epoch": 0.94, + "learning_rate": 1.1528626941135187e-05, + "loss": 0.7505, "step": 2053 }, { - "epoch": 1.06, - "learning_rate": 9.579635088048097e-06, - "loss": 0.5875, + "epoch": 0.94, + "learning_rate": 1.1521335142717356e-05, + "loss": 0.7495, "step": 2054 }, { - "epoch": 1.06, - "learning_rate": 9.571316083591965e-06, - "loss": 0.6499, + "epoch": 0.94, + "learning_rate": 1.1514042516141322e-05, + "loss": 0.7034, "step": 2055 }, { - "epoch": 1.06, - "learning_rate": 9.56299737634575e-06, - "loss": 0.5919, + "epoch": 0.94, + "learning_rate": 1.1506749065376917e-05, + "loss": 0.7351, "step": 2056 }, { - "epoch": 1.06, - "learning_rate": 9.554678972076882e-06, - "loss": 0.6182, + "epoch": 0.94, + "learning_rate": 1.1499454794394422e-05, + "loss": 0.7529, "step": 2057 }, { - "epoch": 1.06, - "learning_rate": 9.546360876552567e-06, - "loss": 0.5879, + "epoch": 0.94, + "learning_rate": 1.1492159707164571e-05, + "loss": 0.7107, "step": 2058 }, { - "epoch": 1.06, - "learning_rate": 9.538043095539818e-06, - "loss": 0.6008, + "epoch": 0.94, + "learning_rate": 1.1484863807658537e-05, + "loss": 0.74, "step": 2059 }, { - "epoch": 1.06, - "learning_rate": 9.529725634805411e-06, - "loss": 0.584, + "epoch": 0.94, + "learning_rate": 1.1477567099847934e-05, + "loss": 0.7754, "step": 2060 }, { - "epoch": 1.06, - "learning_rate": 9.521408500115905e-06, - "loss": 0.6072, + "epoch": 0.94, + "learning_rate": 1.147026958770482e-05, + "loss": 0.7511, "step": 2061 }, { - "epoch": 1.06, - "learning_rate": 9.513091697237638e-06, - "loss": 0.6229, + "epoch": 0.94, + "learning_rate": 1.1462971275201685e-05, + "loss": 0.6793, "step": 2062 }, { - "epoch": 1.06, - "learning_rate": 9.504775231936716e-06, - "loss": 0.6442, + "epoch": 0.94, + "learning_rate": 1.145567216631146e-05, + "loss": 0.6904, "step": 2063 }, { - "epoch": 1.06, - "learning_rate": 9.496459109979004e-06, - "loss": 0.5784, + "epoch": 0.94, + "learning_rate": 1.1448372265007512e-05, + "loss": 0.7068, "step": 2064 }, { - "epoch": 1.06, - "learning_rate": 9.488143337130139e-06, - "loss": 0.6271, + "epoch": 0.94, + "learning_rate": 1.1441071575263631e-05, + "loss": 0.7881, "step": 2065 }, { - "epoch": 1.06, - "learning_rate": 9.47982791915551e-06, - "loss": 0.6143, + "epoch": 0.94, + "learning_rate": 1.1433770101054046e-05, + "loss": 0.7722, "step": 2066 }, { - "epoch": 1.06, - "learning_rate": 9.471512861820262e-06, - "loss": 0.6201, + "epoch": 0.94, + "learning_rate": 1.1426467846353401e-05, + "loss": 0.6971, "step": 2067 }, { - "epoch": 1.06, - "learning_rate": 9.463198170889286e-06, - "loss": 0.6002, + "epoch": 0.94, + "learning_rate": 1.1419164815136774e-05, + "loss": 0.6866, "step": 2068 }, { - "epoch": 1.06, - "learning_rate": 9.454883852127229e-06, - "loss": 0.5966, + "epoch": 0.94, + "learning_rate": 1.1411861011379667e-05, + "loss": 0.719, "step": 2069 }, { - "epoch": 1.06, - "learning_rate": 9.446569911298469e-06, - "loss": 0.6143, + "epoch": 0.94, + "learning_rate": 1.1404556439057994e-05, + "loss": 0.766, "step": 2070 }, { - "epoch": 1.06, - "learning_rate": 9.438256354167125e-06, - "loss": 0.6158, + "epoch": 0.94, + "learning_rate": 1.1397251102148092e-05, + "loss": 0.686, "step": 2071 }, { - "epoch": 1.07, - "learning_rate": 9.429943186497057e-06, - "loss": 0.6051, + "epoch": 0.94, + "learning_rate": 1.1389945004626722e-05, + "loss": 0.7896, "step": 2072 }, { - "epoch": 1.07, - "learning_rate": 9.421630414051846e-06, - "loss": 0.5969, + "epoch": 0.94, + "learning_rate": 1.1382638150471042e-05, + "loss": 0.7551, "step": 2073 }, { - "epoch": 1.07, - "learning_rate": 9.413318042594801e-06, - "loss": 0.6348, + "epoch": 0.94, + "learning_rate": 1.1375330543658634e-05, + "loss": 0.7482, "step": 2074 }, { - "epoch": 1.07, - "learning_rate": 9.405006077888954e-06, - "loss": 0.6616, + "epoch": 0.95, + "learning_rate": 1.136802218816749e-05, + "loss": 0.6969, "step": 2075 }, { - "epoch": 1.07, - "learning_rate": 9.396694525697058e-06, - "loss": 0.6158, + "epoch": 0.95, + "learning_rate": 1.1360713087976003e-05, + "loss": 0.7847, "step": 2076 }, { - "epoch": 1.07, - "learning_rate": 9.388383391781576e-06, - "loss": 0.6071, + "epoch": 0.95, + "learning_rate": 1.1353403247062982e-05, + "loss": 0.6711, "step": 2077 }, { - "epoch": 1.07, - "learning_rate": 9.380072681904679e-06, - "loss": 0.6443, + "epoch": 0.95, + "learning_rate": 1.1346092669407622e-05, + "loss": 0.7059, "step": 2078 }, { - "epoch": 1.07, - "learning_rate": 9.371762401828253e-06, - "loss": 0.6272, + "epoch": 0.95, + "learning_rate": 1.1338781358989534e-05, + "loss": 0.6912, "step": 2079 }, { - "epoch": 1.07, - "learning_rate": 9.363452557313879e-06, - "loss": 0.5909, + "epoch": 0.95, + "learning_rate": 1.1331469319788727e-05, + "loss": 0.7466, "step": 2080 }, { - "epoch": 1.07, - "learning_rate": 9.355143154122833e-06, - "loss": 0.6611, + "epoch": 0.95, + "learning_rate": 1.1324156555785597e-05, + "loss": 0.7009, "step": 2081 }, { - "epoch": 1.07, - "learning_rate": 9.346834198016096e-06, - "loss": 0.5837, + "epoch": 0.95, + "learning_rate": 1.1316843070960943e-05, + "loss": 0.7649, "step": 2082 }, { - "epoch": 1.07, - "learning_rate": 9.338525694754328e-06, - "loss": 0.6395, + "epoch": 0.95, + "learning_rate": 1.1309528869295955e-05, + "loss": 0.7308, "step": 2083 }, { - "epoch": 1.07, - "learning_rate": 9.330217650097881e-06, - "loss": 0.6316, + "epoch": 0.95, + "learning_rate": 1.130221395477221e-05, + "loss": 0.6748, "step": 2084 }, { - "epoch": 1.07, - "learning_rate": 9.321910069806782e-06, - "loss": 0.6278, + "epoch": 0.95, + "learning_rate": 1.1294898331371673e-05, + "loss": 0.7622, "step": 2085 }, { - "epoch": 1.07, - "learning_rate": 9.313602959640754e-06, - "loss": 0.6047, + "epoch": 0.95, + "learning_rate": 1.1287582003076704e-05, + "loss": 0.668, "step": 2086 }, { - "epoch": 1.07, - "learning_rate": 9.305296325359168e-06, - "loss": 0.5734, + "epoch": 0.95, + "learning_rate": 1.1280264973870032e-05, + "loss": 0.8269, "step": 2087 }, { - "epoch": 1.07, - "learning_rate": 9.296990172721084e-06, - "loss": 0.6163, + "epoch": 0.95, + "learning_rate": 1.1272947247734783e-05, + "loss": 0.7529, "step": 2088 }, { - "epoch": 1.07, - "learning_rate": 9.288684507485226e-06, - "loss": 0.5916, + "epoch": 0.95, + "learning_rate": 1.1265628828654444e-05, + "loss": 0.7891, "step": 2089 }, { - "epoch": 1.07, - "learning_rate": 9.280379335409974e-06, - "loss": 0.5764, + "epoch": 0.95, + "learning_rate": 1.12583097206129e-05, + "loss": 0.7742, "step": 2090 }, { - "epoch": 1.07, - "learning_rate": 9.272074662253368e-06, - "loss": 0.6133, + "epoch": 0.95, + "learning_rate": 1.1250989927594398e-05, + "loss": 0.7859, "step": 2091 }, { - "epoch": 1.08, - "learning_rate": 9.263770493773105e-06, - "loss": 0.6199, + "epoch": 0.95, + "learning_rate": 1.1243669453583557e-05, + "loss": 0.7671, "step": 2092 }, { - "epoch": 1.08, - "learning_rate": 9.255466835726531e-06, - "loss": 0.6007, + "epoch": 0.95, + "learning_rate": 1.1236348302565374e-05, + "loss": 0.709, "step": 2093 }, { - "epoch": 1.08, - "learning_rate": 9.247163693870633e-06, - "loss": 0.6132, + "epoch": 0.95, + "learning_rate": 1.1229026478525214e-05, + "loss": 0.7015, "step": 2094 }, { - "epoch": 1.08, - "learning_rate": 9.238861073962047e-06, - "loss": 0.6176, + "epoch": 0.95, + "learning_rate": 1.1221703985448798e-05, + "loss": 0.7306, "step": 2095 }, { - "epoch": 1.08, - "learning_rate": 9.230558981757044e-06, - "loss": 0.6193, + "epoch": 0.95, + "learning_rate": 1.121438082732222e-05, + "loss": 0.7208, "step": 2096 }, { - "epoch": 1.08, - "learning_rate": 9.22225742301153e-06, - "loss": 0.6072, + "epoch": 0.96, + "learning_rate": 1.120705700813194e-05, + "loss": 0.6475, "step": 2097 }, { - "epoch": 1.08, - "learning_rate": 9.213956403481037e-06, - "loss": 0.6243, + "epoch": 0.96, + "learning_rate": 1.119973253186477e-05, + "loss": 0.77, "step": 2098 }, { - "epoch": 1.08, - "learning_rate": 9.205655928920734e-06, - "loss": 0.6213, + "epoch": 0.96, + "learning_rate": 1.1192407402507879e-05, + "loss": 0.6661, "step": 2099 }, { - "epoch": 1.08, - "learning_rate": 9.1973560050854e-06, - "loss": 0.6178, + "epoch": 0.96, + "learning_rate": 1.1185081624048802e-05, + "loss": 0.7607, "step": 2100 }, { - "epoch": 1.08, - "learning_rate": 9.189056637729438e-06, - "loss": 0.6235, + "epoch": 0.96, + "learning_rate": 1.117775520047541e-05, + "loss": 0.6838, "step": 2101 }, { - "epoch": 1.08, - "learning_rate": 9.180757832606868e-06, - "loss": 0.5621, + "epoch": 0.96, + "learning_rate": 1.1170428135775943e-05, + "loss": 0.7372, "step": 2102 }, { - "epoch": 1.08, - "learning_rate": 9.172459595471313e-06, - "loss": 0.6643, + "epoch": 0.96, + "learning_rate": 1.1163100433938978e-05, + "loss": 0.7206, "step": 2103 }, { - "epoch": 1.08, - "learning_rate": 9.164161932076007e-06, - "loss": 0.6351, + "epoch": 0.96, + "learning_rate": 1.1155772098953444e-05, + "loss": 0.6898, "step": 2104 }, { - "epoch": 1.08, - "learning_rate": 9.155864848173782e-06, - "loss": 0.6161, + "epoch": 0.96, + "learning_rate": 1.1148443134808618e-05, + "loss": 0.72, "step": 2105 }, { - "epoch": 1.08, - "learning_rate": 9.147568349517076e-06, - "loss": 0.6284, + "epoch": 0.96, + "learning_rate": 1.1141113545494107e-05, + "loss": 0.7306, "step": 2106 }, { - "epoch": 1.08, - "learning_rate": 9.139272441857914e-06, - "loss": 0.5664, + "epoch": 0.96, + "learning_rate": 1.1133783334999872e-05, + "loss": 0.7382, "step": 2107 }, { - "epoch": 1.08, - "learning_rate": 9.13097713094791e-06, - "loss": 0.6228, + "epoch": 0.96, + "learning_rate": 1.1126452507316209e-05, + "loss": 0.7441, "step": 2108 }, { - "epoch": 1.08, - "learning_rate": 9.122682422538277e-06, - "loss": 0.6488, + "epoch": 0.96, + "learning_rate": 1.111912106643374e-05, + "loss": 0.7124, "step": 2109 }, { - "epoch": 1.08, - "learning_rate": 9.114388322379797e-06, - "loss": 0.6299, + "epoch": 0.96, + "learning_rate": 1.1111789016343435e-05, + "loss": 0.7089, "step": 2110 }, { - "epoch": 1.09, - "learning_rate": 9.106094836222833e-06, - "loss": 0.645, + "epoch": 0.96, + "learning_rate": 1.1104456361036586e-05, + "loss": 0.7466, "step": 2111 }, { - "epoch": 1.09, - "learning_rate": 9.097801969817324e-06, - "loss": 0.6086, + "epoch": 0.96, + "learning_rate": 1.1097123104504816e-05, + "loss": 0.6958, "step": 2112 }, { - "epoch": 1.09, - "learning_rate": 9.089509728912784e-06, - "loss": 0.6367, + "epoch": 0.96, + "learning_rate": 1.1089789250740084e-05, + "loss": 0.7241, "step": 2113 }, { - "epoch": 1.09, - "learning_rate": 9.081218119258283e-06, - "loss": 0.5938, + "epoch": 0.96, + "learning_rate": 1.108245480373466e-05, + "loss": 0.7524, "step": 2114 }, { - "epoch": 1.09, - "learning_rate": 9.07292714660246e-06, - "loss": 0.5712, + "epoch": 0.96, + "learning_rate": 1.1075119767481145e-05, + "loss": 0.707, "step": 2115 }, { - "epoch": 1.09, - "learning_rate": 9.064636816693514e-06, - "loss": 0.6039, + "epoch": 0.96, + "learning_rate": 1.1067784145972463e-05, + "loss": 0.749, "step": 2116 }, { - "epoch": 1.09, - "learning_rate": 9.056347135279197e-06, - "loss": 0.6002, + "epoch": 0.96, + "learning_rate": 1.1060447943201846e-05, + "loss": 0.7349, "step": 2117 }, { - "epoch": 1.09, - "learning_rate": 9.0480581081068e-06, - "loss": 0.6129, + "epoch": 0.96, + "learning_rate": 1.1053111163162857e-05, + "loss": 0.8081, "step": 2118 }, { - "epoch": 1.09, - "learning_rate": 9.039769740923183e-06, - "loss": 0.5952, + "epoch": 0.97, + "learning_rate": 1.1045773809849364e-05, + "loss": 0.6912, "step": 2119 }, { - "epoch": 1.09, - "learning_rate": 9.031482039474731e-06, - "loss": 0.6389, + "epoch": 0.97, + "learning_rate": 1.1038435887255547e-05, + "loss": 0.7385, "step": 2120 }, { - "epoch": 1.09, - "learning_rate": 9.023195009507369e-06, - "loss": 0.5746, + "epoch": 0.97, + "learning_rate": 1.1031097399375898e-05, + "loss": 0.6862, "step": 2121 }, { - "epoch": 1.09, - "learning_rate": 9.014908656766565e-06, - "loss": 0.5848, + "epoch": 0.97, + "learning_rate": 1.1023758350205221e-05, + "loss": 0.7361, "step": 2122 }, { - "epoch": 1.09, - "learning_rate": 9.006622986997311e-06, - "loss": 0.6221, + "epoch": 0.97, + "learning_rate": 1.1016418743738615e-05, + "loss": 0.7498, "step": 2123 }, { - "epoch": 1.09, - "learning_rate": 8.998338005944125e-06, - "loss": 0.5792, + "epoch": 0.97, + "learning_rate": 1.1009078583971493e-05, + "loss": 0.6915, "step": 2124 }, { - "epoch": 1.09, - "learning_rate": 8.99005371935105e-06, - "loss": 0.6248, + "epoch": 0.97, + "learning_rate": 1.100173787489956e-05, + "loss": 0.7196, "step": 2125 }, { - "epoch": 1.09, - "learning_rate": 8.981770132961649e-06, - "loss": 0.6238, + "epoch": 0.97, + "learning_rate": 1.0994396620518827e-05, + "loss": 0.6827, "step": 2126 }, { - "epoch": 1.09, - "learning_rate": 8.97348725251899e-06, - "loss": 0.6521, + "epoch": 0.97, + "learning_rate": 1.0987054824825605e-05, + "loss": 0.7588, "step": 2127 }, { - "epoch": 1.09, - "learning_rate": 8.965205083765669e-06, - "loss": 0.5864, + "epoch": 0.97, + "learning_rate": 1.0979712491816486e-05, + "loss": 0.7363, "step": 2128 }, { - "epoch": 1.09, - "learning_rate": 8.956923632443774e-06, - "loss": 0.6417, + "epoch": 0.97, + "learning_rate": 1.0972369625488363e-05, + "loss": 0.7284, "step": 2129 }, { - "epoch": 1.09, - "learning_rate": 8.948642904294901e-06, - "loss": 0.5881, + "epoch": 0.97, + "learning_rate": 1.0965026229838426e-05, + "loss": 0.7314, "step": 2130 }, { - "epoch": 1.1, - "learning_rate": 8.94036290506014e-06, - "loss": 0.5792, + "epoch": 0.97, + "learning_rate": 1.095768230886414e-05, + "loss": 0.7092, "step": 2131 }, { - "epoch": 1.1, - "learning_rate": 8.932083640480084e-06, - "loss": 0.6044, + "epoch": 0.97, + "learning_rate": 1.0950337866563262e-05, + "loss": 0.7186, "step": 2132 }, { - "epoch": 1.1, - "learning_rate": 8.92380511629481e-06, - "loss": 0.5745, + "epoch": 0.97, + "learning_rate": 1.0942992906933843e-05, + "loss": 0.7437, "step": 2133 }, { - "epoch": 1.1, - "learning_rate": 8.915527338243883e-06, - "loss": 0.5801, + "epoch": 0.97, + "learning_rate": 1.093564743397419e-05, + "loss": 0.7096, "step": 2134 }, { - "epoch": 1.1, - "learning_rate": 8.907250312066352e-06, - "loss": 0.6208, + "epoch": 0.97, + "learning_rate": 1.0928301451682914e-05, + "loss": 0.6818, "step": 2135 }, { - "epoch": 1.1, - "learning_rate": 8.898974043500745e-06, - "loss": 0.5863, + "epoch": 0.97, + "learning_rate": 1.0920954964058896e-05, + "loss": 0.693, "step": 2136 }, { - "epoch": 1.1, - "learning_rate": 8.890698538285061e-06, - "loss": 0.5911, + "epoch": 0.97, + "learning_rate": 1.0913607975101284e-05, + "loss": 0.7172, "step": 2137 }, { - "epoch": 1.1, - "learning_rate": 8.882423802156777e-06, - "loss": 0.6548, + "epoch": 0.97, + "learning_rate": 1.0906260488809508e-05, + "loss": 0.675, "step": 2138 }, { - "epoch": 1.1, - "learning_rate": 8.874149840852832e-06, - "loss": 0.5818, + "epoch": 0.97, + "learning_rate": 1.0898912509183271e-05, + "loss": 0.733, "step": 2139 }, { - "epoch": 1.1, - "learning_rate": 8.865876660109625e-06, - "loss": 0.5425, + "epoch": 0.97, + "learning_rate": 1.089156404022253e-05, + "loss": 0.7477, "step": 2140 }, { - "epoch": 1.1, - "learning_rate": 8.857604265663016e-06, - "loss": 0.5991, + "epoch": 0.98, + "learning_rate": 1.0884215085927526e-05, + "loss": 0.6969, "step": 2141 }, { - "epoch": 1.1, - "learning_rate": 8.849332663248329e-06, - "loss": 0.611, + "epoch": 0.98, + "learning_rate": 1.087686565029875e-05, + "loss": 0.7131, "step": 2142 }, { - "epoch": 1.1, - "learning_rate": 8.841061858600321e-06, - "loss": 0.5889, + "epoch": 0.98, + "learning_rate": 1.0869515737336962e-05, + "loss": 0.7034, "step": 2143 }, { - "epoch": 1.1, - "learning_rate": 8.832791857453214e-06, - "loss": 0.6238, + "epoch": 0.98, + "learning_rate": 1.0862165351043188e-05, + "loss": 0.7471, "step": 2144 }, { - "epoch": 1.1, - "learning_rate": 8.824522665540656e-06, - "loss": 0.6235, + "epoch": 0.98, + "learning_rate": 1.0854814495418698e-05, + "loss": 0.7163, "step": 2145 }, { - "epoch": 1.1, - "learning_rate": 8.81625428859575e-06, - "loss": 0.6387, + "epoch": 0.98, + "learning_rate": 1.0847463174465026e-05, + "loss": 0.7537, "step": 2146 }, { - "epoch": 1.1, - "learning_rate": 8.807986732351018e-06, - "loss": 0.6423, + "epoch": 0.98, + "learning_rate": 1.0840111392183954e-05, + "loss": 0.6898, "step": 2147 }, { - "epoch": 1.1, - "learning_rate": 8.799720002538432e-06, - "loss": 0.6367, + "epoch": 0.98, + "learning_rate": 1.0832759152577524e-05, + "loss": 0.6648, "step": 2148 }, { - "epoch": 1.1, - "learning_rate": 8.791454104889377e-06, - "loss": 0.6035, + "epoch": 0.98, + "learning_rate": 1.082540645964802e-05, + "loss": 0.7594, "step": 2149 }, { - "epoch": 1.11, - "learning_rate": 8.783189045134661e-06, - "loss": 0.615, + "epoch": 0.98, + "learning_rate": 1.0818053317397969e-05, + "loss": 0.7228, "step": 2150 }, { - "epoch": 1.11, - "learning_rate": 8.774924829004519e-06, - "loss": 0.6262, + "epoch": 0.98, + "learning_rate": 1.0810699729830154e-05, + "loss": 0.7357, "step": 2151 }, { - "epoch": 1.11, - "learning_rate": 8.766661462228593e-06, - "loss": 0.6063, + "epoch": 0.98, + "learning_rate": 1.0803345700947596e-05, + "loss": 0.6478, "step": 2152 }, { - "epoch": 1.11, - "learning_rate": 8.758398950535945e-06, - "loss": 0.5823, + "epoch": 0.98, + "learning_rate": 1.0795991234753547e-05, + "loss": 0.723, "step": 2153 }, { - "epoch": 1.11, - "learning_rate": 8.750137299655034e-06, - "loss": 0.587, + "epoch": 0.98, + "learning_rate": 1.0788636335251507e-05, + "loss": 0.7451, "step": 2154 }, { - "epoch": 1.11, - "learning_rate": 8.741876515313728e-06, - "loss": 0.613, + "epoch": 0.98, + "learning_rate": 1.0781281006445217e-05, + "loss": 0.7216, "step": 2155 }, { - "epoch": 1.11, - "learning_rate": 8.733616603239299e-06, - "loss": 0.5885, + "epoch": 0.98, + "learning_rate": 1.0773925252338634e-05, + "loss": 0.7087, "step": 2156 }, { - "epoch": 1.11, - "learning_rate": 8.725357569158397e-06, - "loss": 0.6174, + "epoch": 0.98, + "learning_rate": 1.0766569076935958e-05, + "loss": 0.6847, "step": 2157 }, { - "epoch": 1.11, - "learning_rate": 8.717099418797088e-06, - "loss": 0.5919, + "epoch": 0.98, + "learning_rate": 1.0759212484241624e-05, + "loss": 0.7817, "step": 2158 }, { - "epoch": 1.11, - "learning_rate": 8.708842157880807e-06, - "loss": 0.6365, + "epoch": 0.98, + "learning_rate": 1.075185547826028e-05, + "loss": 0.7393, "step": 2159 }, { - "epoch": 1.11, - "learning_rate": 8.700585792134375e-06, - "loss": 0.6553, + "epoch": 0.98, + "learning_rate": 1.0744498062996811e-05, + "loss": 0.7329, "step": 2160 }, { - "epoch": 1.11, - "learning_rate": 8.692330327282003e-06, - "loss": 0.5851, + "epoch": 0.98, + "learning_rate": 1.0737140242456317e-05, + "loss": 0.6857, "step": 2161 }, { - "epoch": 1.11, - "learning_rate": 8.684075769047263e-06, - "loss": 0.6289, + "epoch": 0.98, + "learning_rate": 1.072978202064412e-05, + "loss": 0.7244, "step": 2162 }, { - "epoch": 1.11, - "learning_rate": 8.675822123153104e-06, - "loss": 0.5824, + "epoch": 0.99, + "learning_rate": 1.0722423401565768e-05, + "loss": 0.7072, "step": 2163 }, { - "epoch": 1.11, - "learning_rate": 8.667569395321845e-06, - "loss": 0.6107, - "step": 2164 + "epoch": 0.99, + "learning_rate": 1.0715064389227013e-05, + "loss": 0.6499, + "step": 2164 }, { - "epoch": 1.11, - "learning_rate": 8.659317591275169e-06, - "loss": 0.5682, + "epoch": 0.99, + "learning_rate": 1.0707704987633828e-05, + "loss": 0.731, "step": 2165 }, { - "epoch": 1.11, - "learning_rate": 8.651066716734116e-06, - "loss": 0.6223, + "epoch": 0.99, + "learning_rate": 1.0700345200792404e-05, + "loss": 0.7456, "step": 2166 }, { - "epoch": 1.11, - "learning_rate": 8.642816777419077e-06, - "loss": 0.6049, + "epoch": 0.99, + "learning_rate": 1.0692985032709124e-05, + "loss": 0.7705, "step": 2167 }, { - "epoch": 1.11, - "learning_rate": 8.634567779049807e-06, - "loss": 0.5995, + "epoch": 0.99, + "learning_rate": 1.06856244873906e-05, + "loss": 0.6941, "step": 2168 }, { - "epoch": 1.11, - "learning_rate": 8.626319727345399e-06, - "loss": 0.5837, + "epoch": 0.99, + "learning_rate": 1.0678263568843634e-05, + "loss": 0.7141, "step": 2169 }, { - "epoch": 1.12, - "learning_rate": 8.618072628024286e-06, - "loss": 0.5822, + "epoch": 0.99, + "learning_rate": 1.0670902281075234e-05, + "loss": 0.7317, "step": 2170 }, { - "epoch": 1.12, - "learning_rate": 8.609826486804256e-06, - "loss": 0.5535, + "epoch": 0.99, + "learning_rate": 1.0663540628092613e-05, + "loss": 0.6871, "step": 2171 }, { - "epoch": 1.12, - "learning_rate": 8.601581309402417e-06, - "loss": 0.6249, + "epoch": 0.99, + "learning_rate": 1.0656178613903183e-05, + "loss": 0.7859, "step": 2172 }, { - "epoch": 1.12, - "learning_rate": 8.593337101535217e-06, - "loss": 0.6259, + "epoch": 0.99, + "learning_rate": 1.0648816242514546e-05, + "loss": 0.7228, "step": 2173 }, { - "epoch": 1.12, - "learning_rate": 8.585093868918426e-06, - "loss": 0.5801, + "epoch": 0.99, + "learning_rate": 1.0641453517934506e-05, + "loss": 0.6781, "step": 2174 }, { - "epoch": 1.12, - "learning_rate": 8.576851617267151e-06, - "loss": 0.6091, + "epoch": 0.99, + "learning_rate": 1.0634090444171057e-05, + "loss": 0.6852, "step": 2175 }, { - "epoch": 1.12, - "learning_rate": 8.568610352295802e-06, - "loss": 0.5643, + "epoch": 0.99, + "learning_rate": 1.062672702523238e-05, + "loss": 0.6929, "step": 2176 }, { - "epoch": 1.12, - "learning_rate": 8.560370079718111e-06, - "loss": 0.588, + "epoch": 0.99, + "learning_rate": 1.0619363265126843e-05, + "loss": 0.7377, "step": 2177 }, { - "epoch": 1.12, - "learning_rate": 8.55213080524713e-06, - "loss": 0.5944, + "epoch": 0.99, + "learning_rate": 1.0611999167863009e-05, + "loss": 0.7266, "step": 2178 }, { - "epoch": 1.12, - "learning_rate": 8.543892534595212e-06, - "loss": 0.5905, + "epoch": 0.99, + "learning_rate": 1.0604634737449615e-05, + "loss": 0.6577, "step": 2179 }, { - "epoch": 1.12, - "learning_rate": 8.53565527347401e-06, - "loss": 0.5979, + "epoch": 0.99, + "learning_rate": 1.0597269977895585e-05, + "loss": 0.7883, "step": 2180 }, { - "epoch": 1.12, - "learning_rate": 8.527419027594486e-06, - "loss": 0.6541, + "epoch": 0.99, + "learning_rate": 1.0589904893210017e-05, + "loss": 0.7672, "step": 2181 }, { - "epoch": 1.12, - "learning_rate": 8.519183802666891e-06, - "loss": 0.5973, + "epoch": 0.99, + "learning_rate": 1.058253948740219e-05, + "loss": 0.7607, "step": 2182 }, { - "epoch": 1.12, - "learning_rate": 8.510949604400772e-06, - "loss": 0.6077, + "epoch": 0.99, + "learning_rate": 1.0575173764481556e-05, + "loss": 0.692, "step": 2183 }, { - "epoch": 1.12, - "learning_rate": 8.502716438504962e-06, - "loss": 0.6401, + "epoch": 0.99, + "learning_rate": 1.0567807728457743e-05, + "loss": 0.7285, "step": 2184 }, { - "epoch": 1.12, - "learning_rate": 8.494484310687581e-06, - "loss": 0.6121, + "epoch": 1.0, + "learning_rate": 1.0560441383340546e-05, + "loss": 0.7231, "step": 2185 }, { - "epoch": 1.12, - "learning_rate": 8.486253226656029e-06, - "loss": 0.597, + "epoch": 1.0, + "learning_rate": 1.0553074733139926e-05, + "loss": 0.7262, "step": 2186 }, { - "epoch": 1.12, - "learning_rate": 8.478023192116975e-06, - "loss": 0.5883, + "epoch": 1.0, + "learning_rate": 1.0545707781866012e-05, + "loss": 0.6747, "step": 2187 }, { - "epoch": 1.12, - "learning_rate": 8.469794212776376e-06, - "loss": 0.6482, + "epoch": 1.0, + "learning_rate": 1.0538340533529106e-05, + "loss": 0.7063, "step": 2188 }, { - "epoch": 1.13, - "learning_rate": 8.46156629433944e-06, - "loss": 0.624, + "epoch": 1.0, + "learning_rate": 1.0530972992139657e-05, + "loss": 0.7827, "step": 2189 }, { - "epoch": 1.13, - "learning_rate": 8.453339442510651e-06, - "loss": 0.6301, + "epoch": 1.0, + "learning_rate": 1.0523605161708279e-05, + "loss": 0.7249, "step": 2190 }, { - "epoch": 1.13, - "learning_rate": 8.445113662993749e-06, - "loss": 0.6161, + "epoch": 1.0, + "learning_rate": 1.051623704624575e-05, + "loss": 0.7134, "step": 2191 }, { - "epoch": 1.13, - "learning_rate": 8.436888961491731e-06, - "loss": 0.6157, + "epoch": 1.0, + "learning_rate": 1.0508868649762995e-05, + "loss": 0.751, "step": 2192 }, { - "epoch": 1.13, - "learning_rate": 8.42866534370685e-06, - "loss": 0.5894, + "epoch": 1.0, + "learning_rate": 1.0501499976271093e-05, + "loss": 0.6694, "step": 2193 }, { - "epoch": 1.13, - "learning_rate": 8.420442815340598e-06, - "loss": 0.6157, + "epoch": 1.0, + "learning_rate": 1.049413102978128e-05, + "loss": 0.6747, "step": 2194 }, { - "epoch": 1.13, - "learning_rate": 8.412221382093725e-06, - "loss": 0.6285, + "epoch": 1.0, + "learning_rate": 1.0486761814304932e-05, + "loss": 0.7676, "step": 2195 }, { - "epoch": 1.13, - "learning_rate": 8.404001049666211e-06, - "loss": 0.5759, + "epoch": 1.0, + "learning_rate": 1.0479392333853575e-05, + "loss": 0.6526, "step": 2196 }, { - "epoch": 1.13, - "learning_rate": 8.395781823757275e-06, - "loss": 0.5853, + "epoch": 1.0, + "learning_rate": 1.0472022592438885e-05, + "loss": 0.6829, "step": 2197 }, { - "epoch": 1.13, - "learning_rate": 8.387563710065378e-06, - "loss": 0.6002, + "epoch": 1.0, + "learning_rate": 1.0464652594072667e-05, + "loss": 0.6675, "step": 2198 }, { - "epoch": 1.13, - "learning_rate": 8.3793467142882e-06, - "loss": 0.6116, + "epoch": 1.0, + "learning_rate": 1.0457282342766881e-05, + "loss": 0.5706, "step": 2199 }, { - "epoch": 1.13, - "learning_rate": 8.371130842122644e-06, - "loss": 0.6075, + "epoch": 1.0, + "learning_rate": 1.0449911842533613e-05, + "loss": 0.6211, "step": 2200 }, { - "epoch": 1.13, - "learning_rate": 8.362916099264844e-06, - "loss": 0.6097, + "epoch": 1.0, + "learning_rate": 1.044254109738509e-05, + "loss": 0.6013, "step": 2201 }, { - "epoch": 1.13, - "learning_rate": 8.354702491410146e-06, - "loss": 0.5455, + "epoch": 1.0, + "learning_rate": 1.0435170111333674e-05, + "loss": 0.5997, "step": 2202 }, { - "epoch": 1.13, - "learning_rate": 8.346490024253103e-06, - "loss": 0.6191, + "epoch": 1.0, + "learning_rate": 1.0427798888391852e-05, + "loss": 0.6166, "step": 2203 }, { - "epoch": 1.13, - "learning_rate": 8.338278703487486e-06, - "loss": 0.5784, + "epoch": 1.0, + "learning_rate": 1.0420427432572242e-05, + "loss": 0.6896, "step": 2204 }, { - "epoch": 1.13, - "learning_rate": 8.33006853480627e-06, - "loss": 0.5981, + "epoch": 1.0, + "learning_rate": 1.0413055747887596e-05, + "loss": 0.6156, "step": 2205 }, { - "epoch": 1.13, - "learning_rate": 8.321859523901621e-06, - "loss": 0.5875, + "epoch": 1.01, + "learning_rate": 1.0405683838350778e-05, + "loss": 0.6532, "step": 2206 }, { - "epoch": 1.13, - "learning_rate": 8.313651676464924e-06, - "loss": 0.6432, + "epoch": 1.01, + "learning_rate": 1.0398311707974783e-05, + "loss": 0.6226, "step": 2207 }, { - "epoch": 1.13, - "learning_rate": 8.305444998186736e-06, - "loss": 0.6338, + "epoch": 1.01, + "learning_rate": 1.0390939360772729e-05, + "loss": 0.6034, "step": 2208 }, { - "epoch": 1.14, - "learning_rate": 8.29723949475681e-06, - "loss": 0.5812, + "epoch": 1.01, + "learning_rate": 1.038356680075784e-05, + "loss": 0.6055, "step": 2209 }, { - "epoch": 1.14, - "learning_rate": 8.28903517186409e-06, - "loss": 0.6353, + "epoch": 1.01, + "learning_rate": 1.0376194031943467e-05, + "loss": 0.6735, "step": 2210 }, { - "epoch": 1.14, - "learning_rate": 8.280832035196695e-06, - "loss": 0.5852, + "epoch": 1.01, + "learning_rate": 1.0368821058343071e-05, + "loss": 0.6056, "step": 2211 }, { - "epoch": 1.14, - "learning_rate": 8.272630090441926e-06, - "loss": 0.6174, + "epoch": 1.01, + "learning_rate": 1.0361447883970223e-05, + "loss": 0.6504, "step": 2212 }, { - "epoch": 1.14, - "learning_rate": 8.264429343286253e-06, - "loss": 0.621, + "epoch": 1.01, + "learning_rate": 1.035407451283861e-05, + "loss": 0.6351, "step": 2213 }, { - "epoch": 1.14, - "learning_rate": 8.256229799415318e-06, - "loss": 0.5813, + "epoch": 1.01, + "learning_rate": 1.0346700948962013e-05, + "loss": 0.6196, "step": 2214 }, { - "epoch": 1.14, - "learning_rate": 8.248031464513933e-06, - "loss": 0.5698, + "epoch": 1.01, + "learning_rate": 1.0339327196354328e-05, + "loss": 0.6853, "step": 2215 }, { - "epoch": 1.14, - "learning_rate": 8.23983434426606e-06, - "loss": 0.5908, + "epoch": 1.01, + "learning_rate": 1.0331953259029552e-05, + "loss": 0.6334, "step": 2216 }, { - "epoch": 1.14, - "learning_rate": 8.231638444354836e-06, - "loss": 0.5919, + "epoch": 1.01, + "learning_rate": 1.0324579141001782e-05, + "loss": 0.6229, "step": 2217 }, { - "epoch": 1.14, - "learning_rate": 8.223443770462539e-06, - "loss": 0.6201, + "epoch": 1.01, + "learning_rate": 1.0317204846285216e-05, + "loss": 0.6791, "step": 2218 }, { - "epoch": 1.14, - "learning_rate": 8.2152503282706e-06, - "loss": 0.5642, + "epoch": 1.01, + "learning_rate": 1.030983037889414e-05, + "loss": 0.6486, "step": 2219 }, { - "epoch": 1.14, - "learning_rate": 8.207058123459595e-06, - "loss": 0.6755, + "epoch": 1.01, + "learning_rate": 1.0302455742842943e-05, + "loss": 0.6498, "step": 2220 }, { - "epoch": 1.14, - "learning_rate": 8.198867161709247e-06, - "loss": 0.6125, + "epoch": 1.01, + "learning_rate": 1.0295080942146103e-05, + "loss": 0.6083, "step": 2221 }, { - "epoch": 1.14, - "learning_rate": 8.190677448698414e-06, - "loss": 0.5717, + "epoch": 1.01, + "learning_rate": 1.0287705980818183e-05, + "loss": 0.6548, "step": 2222 }, { - "epoch": 1.14, - "learning_rate": 8.182488990105086e-06, - "loss": 0.5879, + "epoch": 1.01, + "learning_rate": 1.028033086287384e-05, + "loss": 0.6348, "step": 2223 }, { - "epoch": 1.14, - "learning_rate": 8.174301791606384e-06, - "loss": 0.5991, + "epoch": 1.01, + "learning_rate": 1.0272955592327816e-05, + "loss": 0.6715, "step": 2224 }, { - "epoch": 1.14, - "learning_rate": 8.166115858878563e-06, - "loss": 0.583, + "epoch": 1.01, + "learning_rate": 1.0265580173194928e-05, + "loss": 0.6267, "step": 2225 }, { - "epoch": 1.14, - "learning_rate": 8.157931197596986e-06, - "loss": 0.6154, + "epoch": 1.01, + "learning_rate": 1.0258204609490083e-05, + "loss": 0.6652, "step": 2226 }, { - "epoch": 1.14, - "learning_rate": 8.14974781343615e-06, - "loss": 0.631, + "epoch": 1.01, + "learning_rate": 1.0250828905228265e-05, + "loss": 0.6324, "step": 2227 }, { - "epoch": 1.15, - "learning_rate": 8.14156571206966e-06, - "loss": 0.5953, + "epoch": 1.02, + "learning_rate": 1.0243453064424527e-05, + "loss": 0.6042, "step": 2228 }, { - "epoch": 1.15, - "learning_rate": 8.133384899170224e-06, - "loss": 0.6172, + "epoch": 1.02, + "learning_rate": 1.0236077091094008e-05, + "loss": 0.6215, "step": 2229 }, { - "epoch": 1.15, - "learning_rate": 8.12520538040967e-06, - "loss": 0.6099, + "epoch": 1.02, + "learning_rate": 1.0228700989251911e-05, + "loss": 0.6243, "step": 2230 }, { - "epoch": 1.15, - "learning_rate": 8.117027161458917e-06, - "loss": 0.6194, + "epoch": 1.02, + "learning_rate": 1.022132476291351e-05, + "loss": 0.616, "step": 2231 }, { - "epoch": 1.15, - "learning_rate": 8.108850247987995e-06, - "loss": 0.6311, + "epoch": 1.02, + "learning_rate": 1.0213948416094148e-05, + "loss": 0.6187, "step": 2232 }, { - "epoch": 1.15, - "learning_rate": 8.100674645666017e-06, - "loss": 0.6172, + "epoch": 1.02, + "learning_rate": 1.0206571952809238e-05, + "loss": 0.6453, "step": 2233 }, { - "epoch": 1.15, - "learning_rate": 8.092500360161192e-06, - "loss": 0.6277, + "epoch": 1.02, + "learning_rate": 1.0199195377074247e-05, + "loss": 0.6523, "step": 2234 }, { - "epoch": 1.15, - "learning_rate": 8.08432739714082e-06, - "loss": 0.6183, + "epoch": 1.02, + "learning_rate": 1.0191818692904712e-05, + "loss": 0.5451, "step": 2235 }, { - "epoch": 1.15, - "learning_rate": 8.076155762271274e-06, - "loss": 0.594, + "epoch": 1.02, + "learning_rate": 1.0184441904316218e-05, + "loss": 0.5869, "step": 2236 }, { - "epoch": 1.15, - "learning_rate": 8.06798546121802e-06, - "loss": 0.6281, + "epoch": 1.02, + "learning_rate": 1.017706501532442e-05, + "loss": 0.6431, "step": 2237 }, { - "epoch": 1.15, - "learning_rate": 8.05981649964559e-06, - "loss": 0.6056, + "epoch": 1.02, + "learning_rate": 1.0169688029945024e-05, + "loss": 0.6136, "step": 2238 }, { - "epoch": 1.15, - "learning_rate": 8.051648883217587e-06, - "loss": 0.5718, + "epoch": 1.02, + "learning_rate": 1.0162310952193782e-05, + "loss": 0.6515, "step": 2239 }, { - "epoch": 1.15, - "learning_rate": 8.043482617596681e-06, - "loss": 0.6083, + "epoch": 1.02, + "learning_rate": 1.0154933786086498e-05, + "loss": 0.6689, "step": 2240 }, { - "epoch": 1.15, - "learning_rate": 8.035317708444614e-06, - "loss": 0.5858, + "epoch": 1.02, + "learning_rate": 1.0147556535639033e-05, + "loss": 0.6399, "step": 2241 }, { - "epoch": 1.15, - "learning_rate": 8.02715416142218e-06, - "loss": 0.6388, + "epoch": 1.02, + "learning_rate": 1.0140179204867282e-05, + "loss": 0.6421, "step": 2242 }, { - "epoch": 1.15, - "learning_rate": 8.018991982189225e-06, - "loss": 0.6434, + "epoch": 1.02, + "learning_rate": 1.0132801797787192e-05, + "loss": 0.6322, "step": 2243 }, { - "epoch": 1.15, - "learning_rate": 8.010831176404656e-06, - "loss": 0.6394, + "epoch": 1.02, + "learning_rate": 1.0125424318414749e-05, + "loss": 0.6166, "step": 2244 }, { - "epoch": 1.15, - "learning_rate": 8.002671749726425e-06, - "loss": 0.5824, + "epoch": 1.02, + "learning_rate": 1.0118046770765975e-05, + "loss": 0.6428, "step": 2245 }, { - "epoch": 1.15, - "learning_rate": 7.99451370781152e-06, - "loss": 0.6033, + "epoch": 1.02, + "learning_rate": 1.0110669158856938e-05, + "loss": 0.6239, "step": 2246 }, { - "epoch": 1.15, - "learning_rate": 7.986357056315984e-06, - "loss": 0.5891, + "epoch": 1.02, + "learning_rate": 1.0103291486703728e-05, + "loss": 0.6512, "step": 2247 }, { - "epoch": 1.16, - "learning_rate": 7.978201800894883e-06, - "loss": 0.5931, + "epoch": 1.02, + "learning_rate": 1.009591375832248e-05, + "loss": 0.6025, "step": 2248 }, { - "epoch": 1.16, - "learning_rate": 7.97004794720232e-06, - "loss": 0.6599, + "epoch": 1.02, + "learning_rate": 1.0088535977729356e-05, + "loss": 0.6455, "step": 2249 }, { - "epoch": 1.16, - "learning_rate": 7.961895500891426e-06, - "loss": 0.6146, + "epoch": 1.03, + "learning_rate": 1.008115814894054e-05, + "loss": 0.6111, "step": 2250 }, { - "epoch": 1.16, - "learning_rate": 7.953744467614356e-06, - "loss": 0.5745, + "epoch": 1.03, + "learning_rate": 1.0073780275972249e-05, + "loss": 0.6111, "step": 2251 }, { - "epoch": 1.16, - "learning_rate": 7.945594853022283e-06, - "loss": 0.6118, + "epoch": 1.03, + "learning_rate": 1.0066402362840727e-05, + "loss": 0.6227, "step": 2252 }, { - "epoch": 1.16, - "learning_rate": 7.9374466627654e-06, - "loss": 0.6123, + "epoch": 1.03, + "learning_rate": 1.0059024413562226e-05, + "loss": 0.6044, "step": 2253 }, { - "epoch": 1.16, - "learning_rate": 7.929299902492913e-06, - "loss": 0.5978, + "epoch": 1.03, + "learning_rate": 1.0051646432153035e-05, + "loss": 0.6019, "step": 2254 }, { - "epoch": 1.16, - "learning_rate": 7.921154577853033e-06, - "loss": 0.5308, + "epoch": 1.03, + "learning_rate": 1.0044268422629446e-05, + "loss": 0.6012, "step": 2255 }, { - "epoch": 1.16, - "learning_rate": 7.913010694492974e-06, - "loss": 0.5803, + "epoch": 1.03, + "learning_rate": 1.0036890389007778e-05, + "loss": 0.5461, "step": 2256 }, { - "epoch": 1.16, - "learning_rate": 7.904868258058962e-06, - "loss": 0.6331, + "epoch": 1.03, + "learning_rate": 1.0029512335304359e-05, + "loss": 0.6659, "step": 2257 }, { - "epoch": 1.16, - "learning_rate": 7.896727274196209e-06, - "loss": 0.6111, + "epoch": 1.03, + "learning_rate": 1.002213426553552e-05, + "loss": 0.65, "step": 2258 }, { - "epoch": 1.16, - "learning_rate": 7.888587748548918e-06, - "loss": 0.5629, + "epoch": 1.03, + "learning_rate": 1.0014756183717612e-05, + "loss": 0.5872, "step": 2259 }, { - "epoch": 1.16, - "learning_rate": 7.880449686760293e-06, - "loss": 0.6255, + "epoch": 1.03, + "learning_rate": 1.0007378093866987e-05, + "loss": 0.5726, "step": 2260 }, { - "epoch": 1.16, - "learning_rate": 7.872313094472512e-06, - "loss": 0.6011, + "epoch": 1.03, + "learning_rate": 1e-05, + "loss": 0.6659, "step": 2261 }, { - "epoch": 1.16, - "learning_rate": 7.864177977326739e-06, - "loss": 0.6311, + "epoch": 1.03, + "learning_rate": 9.992621906133015e-06, + "loss": 0.6338, "step": 2262 }, { - "epoch": 1.16, - "learning_rate": 7.856044340963114e-06, - "loss": 0.6381, + "epoch": 1.03, + "learning_rate": 9.985243816282392e-06, + "loss": 0.666, "step": 2263 }, { - "epoch": 1.16, - "learning_rate": 7.847912191020752e-06, - "loss": 0.6082, + "epoch": 1.03, + "learning_rate": 9.977865734464482e-06, + "loss": 0.6096, "step": 2264 }, { - "epoch": 1.16, - "learning_rate": 7.839781533137737e-06, - "loss": 0.655, + "epoch": 1.03, + "learning_rate": 9.970487664695644e-06, + "loss": 0.5826, "step": 2265 }, { - "epoch": 1.16, - "learning_rate": 7.831652372951109e-06, - "loss": 0.6058, + "epoch": 1.03, + "learning_rate": 9.963109610992221e-06, + "loss": 0.645, "step": 2266 }, { - "epoch": 1.17, - "learning_rate": 7.823524716096891e-06, - "loss": 0.6621, + "epoch": 1.03, + "learning_rate": 9.955731577370556e-06, + "loss": 0.5999, "step": 2267 }, { - "epoch": 1.17, - "learning_rate": 7.81539856821005e-06, - "loss": 0.6005, + "epoch": 1.03, + "learning_rate": 9.948353567846967e-06, + "loss": 0.6154, "step": 2268 }, { - "epoch": 1.17, - "learning_rate": 7.807273934924498e-06, - "loss": 0.5691, + "epoch": 1.03, + "learning_rate": 9.940975586437777e-06, + "loss": 0.673, "step": 2269 }, { - "epoch": 1.17, - "learning_rate": 7.799150821873116e-06, - "loss": 0.6365, + "epoch": 1.03, + "learning_rate": 9.933597637159275e-06, + "loss": 0.6083, "step": 2270 }, { - "epoch": 1.17, - "learning_rate": 7.79102923468772e-06, - "loss": 0.6543, + "epoch": 1.03, + "learning_rate": 9.926219724027755e-06, + "loss": 0.6418, "step": 2271 }, { - "epoch": 1.17, - "learning_rate": 7.782909178999067e-06, - "loss": 0.5623, + "epoch": 1.04, + "learning_rate": 9.91884185105946e-06, + "loss": 0.6178, "step": 2272 }, { - "epoch": 1.17, - "learning_rate": 7.774790660436857e-06, - "loss": 0.5989, + "epoch": 1.04, + "learning_rate": 9.911464022270647e-06, + "loss": 0.6281, "step": 2273 }, { - "epoch": 1.17, - "learning_rate": 7.766673684629724e-06, - "loss": 0.6204, + "epoch": 1.04, + "learning_rate": 9.90408624167752e-06, + "loss": 0.5928, "step": 2274 }, { - "epoch": 1.17, - "learning_rate": 7.758558257205231e-06, - "loss": 0.5833, + "epoch": 1.04, + "learning_rate": 9.896708513296274e-06, + "loss": 0.6228, "step": 2275 }, { - "epoch": 1.17, - "learning_rate": 7.750444383789861e-06, - "loss": 0.5823, + "epoch": 1.04, + "learning_rate": 9.889330841143065e-06, + "loss": 0.6525, "step": 2276 }, { - "epoch": 1.17, - "learning_rate": 7.742332070009036e-06, - "loss": 0.5455, + "epoch": 1.04, + "learning_rate": 9.881953229234028e-06, + "loss": 0.6039, "step": 2277 }, { - "epoch": 1.17, - "learning_rate": 7.734221321487081e-06, - "loss": 0.5946, + "epoch": 1.04, + "learning_rate": 9.874575681585253e-06, + "loss": 0.5989, "step": 2278 }, { - "epoch": 1.17, - "learning_rate": 7.726112143847241e-06, - "loss": 0.6262, + "epoch": 1.04, + "learning_rate": 9.867198202212811e-06, + "loss": 0.6057, "step": 2279 }, { - "epoch": 1.17, - "learning_rate": 7.718004542711677e-06, - "loss": 0.6426, + "epoch": 1.04, + "learning_rate": 9.859820795132721e-06, + "loss": 0.6187, "step": 2280 }, { - "epoch": 1.17, - "learning_rate": 7.709898523701449e-06, - "loss": 0.5815, + "epoch": 1.04, + "learning_rate": 9.852443464360972e-06, + "loss": 0.5372, "step": 2281 }, { - "epoch": 1.17, - "learning_rate": 7.701794092436524e-06, - "loss": 0.6465, + "epoch": 1.04, + "learning_rate": 9.845066213913506e-06, + "loss": 0.6768, "step": 2282 }, { - "epoch": 1.17, - "learning_rate": 7.693691254535765e-06, - "loss": 0.5968, + "epoch": 1.04, + "learning_rate": 9.837689047806225e-06, + "loss": 0.5714, "step": 2283 }, { - "epoch": 1.17, - "learning_rate": 7.685590015616939e-06, - "loss": 0.6049, + "epoch": 1.04, + "learning_rate": 9.830311970054979e-06, + "loss": 0.6498, "step": 2284 }, { - "epoch": 1.17, - "learning_rate": 7.677490381296689e-06, - "loss": 0.5906, + "epoch": 1.04, + "learning_rate": 9.822934984675584e-06, + "loss": 0.6266, "step": 2285 }, { - "epoch": 1.18, - "learning_rate": 7.669392357190565e-06, - "loss": 0.5908, + "epoch": 1.04, + "learning_rate": 9.815558095683784e-06, + "loss": 0.6006, "step": 2286 }, { - "epoch": 1.18, - "learning_rate": 7.661295948912988e-06, - "loss": 0.6172, + "epoch": 1.04, + "learning_rate": 9.808181307095295e-06, + "loss": 0.6544, "step": 2287 }, { - "epoch": 1.18, - "learning_rate": 7.65320116207726e-06, - "loss": 0.598, + "epoch": 1.04, + "learning_rate": 9.800804622925756e-06, + "loss": 0.6113, "step": 2288 }, { - "epoch": 1.18, - "learning_rate": 7.645108002295557e-06, - "loss": 0.6285, + "epoch": 1.04, + "learning_rate": 9.793428047190767e-06, + "loss": 0.6328, "step": 2289 }, { - "epoch": 1.18, - "learning_rate": 7.637016475178934e-06, - "loss": 0.6125, + "epoch": 1.04, + "learning_rate": 9.786051583905854e-06, + "loss": 0.5745, "step": 2290 }, { - "epoch": 1.18, - "learning_rate": 7.628926586337311e-06, - "loss": 0.5874, + "epoch": 1.04, + "learning_rate": 9.778675237086494e-06, + "loss": 0.6458, "step": 2291 }, { - "epoch": 1.18, - "learning_rate": 7.620838341379471e-06, - "loss": 0.5956, + "epoch": 1.04, + "learning_rate": 9.77129901074809e-06, + "loss": 0.614, "step": 2292 }, { - "epoch": 1.18, - "learning_rate": 7.6127517459130515e-06, - "loss": 0.5878, + "epoch": 1.04, + "learning_rate": 9.763922908905995e-06, + "loss": 0.6267, "step": 2293 }, { - "epoch": 1.18, - "learning_rate": 7.604666805544561e-06, - "loss": 0.6198, + "epoch": 1.05, + "learning_rate": 9.756546935575474e-06, + "loss": 0.6522, "step": 2294 }, { - "epoch": 1.18, - "learning_rate": 7.596583525879344e-06, - "loss": 0.6055, + "epoch": 1.05, + "learning_rate": 9.749171094771735e-06, + "loss": 0.6172, "step": 2295 }, { - "epoch": 1.18, - "learning_rate": 7.58850191252161e-06, - "loss": 0.5919, + "epoch": 1.05, + "learning_rate": 9.74179539050992e-06, + "loss": 0.6421, "step": 2296 }, { - "epoch": 1.18, - "learning_rate": 7.580421971074401e-06, - "loss": 0.6211, + "epoch": 1.05, + "learning_rate": 9.734419826805074e-06, + "loss": 0.6311, "step": 2297 }, { - "epoch": 1.18, - "learning_rate": 7.5723437071396035e-06, - "loss": 0.6145, + "epoch": 1.05, + "learning_rate": 9.727044407672188e-06, + "loss": 0.6753, "step": 2298 }, { - "epoch": 1.18, - "learning_rate": 7.564267126317939e-06, - "loss": 0.5193, + "epoch": 1.05, + "learning_rate": 9.71966913712616e-06, + "loss": 0.6727, "step": 2299 }, { - "epoch": 1.18, - "learning_rate": 7.556192234208969e-06, - "loss": 0.5631, + "epoch": 1.05, + "learning_rate": 9.712294019181819e-06, + "loss": 0.6083, "step": 2300 }, { - "epoch": 1.18, - "learning_rate": 7.548119036411077e-06, - "loss": 0.6136, + "epoch": 1.05, + "learning_rate": 9.7049190578539e-06, + "loss": 0.6146, "step": 2301 }, { - "epoch": 1.18, - "learning_rate": 7.540047538521473e-06, - "loss": 0.5863, + "epoch": 1.05, + "learning_rate": 9.69754425715706e-06, + "loss": 0.6433, "step": 2302 }, { - "epoch": 1.18, - "learning_rate": 7.531977746136192e-06, - "loss": 0.5582, + "epoch": 1.05, + "learning_rate": 9.69016962110586e-06, + "loss": 0.6166, "step": 2303 }, { - "epoch": 1.18, - "learning_rate": 7.5239096648500835e-06, - "loss": 0.5667, + "epoch": 1.05, + "learning_rate": 9.682795153714785e-06, + "loss": 0.6508, "step": 2304 }, { - "epoch": 1.18, - "learning_rate": 7.515843300256808e-06, - "loss": 0.6229, + "epoch": 1.05, + "learning_rate": 9.675420858998218e-06, + "loss": 0.5719, "step": 2305 }, { - "epoch": 1.19, - "learning_rate": 7.507778657948847e-06, - "loss": 0.5804, + "epoch": 1.05, + "learning_rate": 9.66804674097045e-06, + "loss": 0.6689, "step": 2306 }, { - "epoch": 1.19, - "learning_rate": 7.499715743517475e-06, - "loss": 0.627, + "epoch": 1.05, + "learning_rate": 9.660672803645674e-06, + "loss": 0.6461, "step": 2307 }, { - "epoch": 1.19, - "learning_rate": 7.4916545625527745e-06, - "loss": 0.609, + "epoch": 1.05, + "learning_rate": 9.65329905103799e-06, + "loss": 0.5839, "step": 2308 }, { - "epoch": 1.19, - "learning_rate": 7.4835951206436255e-06, - "loss": 0.5864, + "epoch": 1.05, + "learning_rate": 9.645925487161391e-06, + "loss": 0.6082, "step": 2309 }, { - "epoch": 1.19, - "learning_rate": 7.475537423377704e-06, - "loss": 0.5597, - "step": 2310 + "epoch": 1.05, + "learning_rate": 9.63855211602978e-06, + "loss": 0.6184, + "step": 2310 }, { - "epoch": 1.19, - "learning_rate": 7.467481476341471e-06, - "loss": 0.6165, + "epoch": 1.05, + "learning_rate": 9.631178941656929e-06, + "loss": 0.6575, "step": 2311 }, { - "epoch": 1.19, - "learning_rate": 7.459427285120182e-06, - "loss": 0.6384, + "epoch": 1.05, + "learning_rate": 9.623805968056535e-06, + "loss": 0.5951, "step": 2312 }, { - "epoch": 1.19, - "learning_rate": 7.451374855297866e-06, - "loss": 0.58, + "epoch": 1.05, + "learning_rate": 9.616433199242163e-06, + "loss": 0.6254, "step": 2313 }, { - "epoch": 1.19, - "learning_rate": 7.443324192457341e-06, - "loss": 0.6472, + "epoch": 1.05, + "learning_rate": 9.609060639227276e-06, + "loss": 0.613, "step": 2314 }, { - "epoch": 1.19, - "learning_rate": 7.435275302180187e-06, - "loss": 0.5897, + "epoch": 1.05, + "learning_rate": 9.601688292025219e-06, + "loss": 0.6232, "step": 2315 }, { - "epoch": 1.19, - "learning_rate": 7.427228190046772e-06, - "loss": 0.6071, + "epoch": 1.06, + "learning_rate": 9.594316161649229e-06, + "loss": 0.6609, "step": 2316 }, { - "epoch": 1.19, - "learning_rate": 7.419182861636218e-06, - "loss": 0.604, + "epoch": 1.06, + "learning_rate": 9.586944252112408e-06, + "loss": 0.6234, "step": 2317 }, { - "epoch": 1.19, - "learning_rate": 7.411139322526415e-06, - "loss": 0.6289, + "epoch": 1.06, + "learning_rate": 9.57957256742776e-06, + "loss": 0.5938, "step": 2318 }, { - "epoch": 1.19, - "learning_rate": 7.4030975782940075e-06, - "loss": 0.624, + "epoch": 1.06, + "learning_rate": 9.572201111608152e-06, + "loss": 0.6436, "step": 2319 }, { - "epoch": 1.19, - "learning_rate": 7.395057634514404e-06, - "loss": 0.657, + "epoch": 1.06, + "learning_rate": 9.56482988866633e-06, + "loss": 0.6462, "step": 2320 }, { - "epoch": 1.19, - "learning_rate": 7.3870194967617615e-06, - "loss": 0.6316, + "epoch": 1.06, + "learning_rate": 9.557458902614912e-06, + "loss": 0.6184, "step": 2321 }, { - "epoch": 1.19, - "learning_rate": 7.378983170608982e-06, - "loss": 0.6039, + "epoch": 1.06, + "learning_rate": 9.550088157466392e-06, + "loss": 0.6342, "step": 2322 }, { - "epoch": 1.19, - "learning_rate": 7.370948661627709e-06, - "loss": 0.6481, + "epoch": 1.06, + "learning_rate": 9.542717657233122e-06, + "loss": 0.641, "step": 2323 }, { - "epoch": 1.19, - "learning_rate": 7.362915975388339e-06, - "loss": 0.5894, + "epoch": 1.06, + "learning_rate": 9.535347405927338e-06, + "loss": 0.6763, "step": 2324 }, { - "epoch": 1.2, - "learning_rate": 7.354885117459987e-06, - "loss": 0.5919, + "epoch": 1.06, + "learning_rate": 9.52797740756112e-06, + "loss": 0.6064, "step": 2325 }, { - "epoch": 1.2, - "learning_rate": 7.346856093410519e-06, - "loss": 0.6206, + "epoch": 1.06, + "learning_rate": 9.520607666146428e-06, + "loss": 0.5927, "step": 2326 }, { - "epoch": 1.2, - "learning_rate": 7.338828908806517e-06, - "loss": 0.5732, + "epoch": 1.06, + "learning_rate": 9.513238185695073e-06, + "loss": 0.6167, "step": 2327 }, { - "epoch": 1.2, - "learning_rate": 7.3308035692132896e-06, - "loss": 0.5637, + "epoch": 1.06, + "learning_rate": 9.505868970218725e-06, + "loss": 0.6166, "step": 2328 }, { - "epoch": 1.2, - "learning_rate": 7.322780080194867e-06, - "loss": 0.5789, + "epoch": 1.06, + "learning_rate": 9.49850002372891e-06, + "loss": 0.6562, "step": 2329 }, { - "epoch": 1.2, - "learning_rate": 7.314758447313999e-06, - "loss": 0.5884, + "epoch": 1.06, + "learning_rate": 9.491131350237007e-06, + "loss": 0.5862, "step": 2330 }, { - "epoch": 1.2, - "learning_rate": 7.3067386761321464e-06, - "loss": 0.5824, + "epoch": 1.06, + "learning_rate": 9.483762953754252e-06, + "loss": 0.6185, "step": 2331 }, { - "epoch": 1.2, - "learning_rate": 7.29872077220948e-06, - "loss": 0.6086, + "epoch": 1.06, + "learning_rate": 9.476394838291721e-06, + "loss": 0.6026, "step": 2332 }, { - "epoch": 1.2, - "learning_rate": 7.29070474110487e-06, - "loss": 0.6399, + "epoch": 1.06, + "learning_rate": 9.469027007860348e-06, + "loss": 0.6521, "step": 2333 }, { - "epoch": 1.2, - "learning_rate": 7.282690588375902e-06, - "loss": 0.6313, + "epoch": 1.06, + "learning_rate": 9.461659466470897e-06, + "loss": 0.6541, "step": 2334 }, { - "epoch": 1.2, - "learning_rate": 7.274678319578843e-06, - "loss": 0.5953, + "epoch": 1.06, + "learning_rate": 9.454292218133991e-06, + "loss": 0.5981, "step": 2335 }, { - "epoch": 1.2, - "learning_rate": 7.266667940268668e-06, - "loss": 0.6132, + "epoch": 1.06, + "learning_rate": 9.446925266860076e-06, + "loss": 0.6018, "step": 2336 }, { - "epoch": 1.2, - "learning_rate": 7.2586594559990335e-06, - "loss": 0.5898, + "epoch": 1.06, + "learning_rate": 9.439558616659458e-06, + "loss": 0.5669, "step": 2337 }, { - "epoch": 1.2, - "learning_rate": 7.250652872322286e-06, - "loss": 0.5974, + "epoch": 1.07, + "learning_rate": 9.432192271542258e-06, + "loss": 0.611, "step": 2338 }, { - "epoch": 1.2, - "learning_rate": 7.242648194789447e-06, - "loss": 0.5948, + "epoch": 1.07, + "learning_rate": 9.424826235518446e-06, + "loss": 0.6387, "step": 2339 }, { - "epoch": 1.2, - "learning_rate": 7.234645428950229e-06, - "loss": 0.588, + "epoch": 1.07, + "learning_rate": 9.417460512597812e-06, + "loss": 0.6552, "step": 2340 }, { - "epoch": 1.2, - "learning_rate": 7.2266445803530085e-06, - "loss": 0.5916, + "epoch": 1.07, + "learning_rate": 9.410095106789987e-06, + "loss": 0.6315, "step": 2341 }, { - "epoch": 1.2, - "learning_rate": 7.218645654544838e-06, - "loss": 0.5784, + "epoch": 1.07, + "learning_rate": 9.402730022104417e-06, + "loss": 0.6249, "step": 2342 }, { - "epoch": 1.2, - "learning_rate": 7.210648657071433e-06, - "loss": 0.6395, + "epoch": 1.07, + "learning_rate": 9.395365262550389e-06, + "loss": 0.5953, "step": 2343 }, { - "epoch": 1.2, - "learning_rate": 7.202653593477178e-06, - "loss": 0.5804, + "epoch": 1.07, + "learning_rate": 9.388000832136993e-06, + "loss": 0.6768, "step": 2344 }, { - "epoch": 1.21, - "learning_rate": 7.1946604693051084e-06, - "loss": 0.5811, + "epoch": 1.07, + "learning_rate": 9.380636734873159e-06, + "loss": 0.6378, "step": 2345 }, { - "epoch": 1.21, - "learning_rate": 7.186669290096926e-06, - "loss": 0.6367, + "epoch": 1.07, + "learning_rate": 9.373272974767624e-06, + "loss": 0.6317, "step": 2346 }, { - "epoch": 1.21, - "learning_rate": 7.178680061392977e-06, - "loss": 0.5931, + "epoch": 1.07, + "learning_rate": 9.365909555828948e-06, + "loss": 0.6399, "step": 2347 }, { - "epoch": 1.21, - "learning_rate": 7.170692788732251e-06, - "loss": 0.632, + "epoch": 1.07, + "learning_rate": 9.358546482065496e-06, + "loss": 0.6123, "step": 2348 }, { - "epoch": 1.21, - "learning_rate": 7.162707477652392e-06, - "loss": 0.6099, + "epoch": 1.07, + "learning_rate": 9.351183757485457e-06, + "loss": 0.6409, "step": 2349 }, { - "epoch": 1.21, - "learning_rate": 7.154724133689677e-06, - "loss": 0.6101, + "epoch": 1.07, + "learning_rate": 9.343821386096819e-06, + "loss": 0.5934, "step": 2350 }, { - "epoch": 1.21, - "learning_rate": 7.146742762379022e-06, - "loss": 0.6337, + "epoch": 1.07, + "learning_rate": 9.336459371907389e-06, + "loss": 0.5928, "step": 2351 }, { - "epoch": 1.21, - "learning_rate": 7.138763369253969e-06, - "loss": 0.5947, + "epoch": 1.07, + "learning_rate": 9.329097718924769e-06, + "loss": 0.5846, "step": 2352 }, { - "epoch": 1.21, - "learning_rate": 7.130785959846701e-06, - "loss": 0.611, + "epoch": 1.07, + "learning_rate": 9.321736431156371e-06, + "loss": 0.5992, "step": 2353 }, { - "epoch": 1.21, - "learning_rate": 7.122810539688015e-06, - "loss": 0.561, + "epoch": 1.07, + "learning_rate": 9.314375512609403e-06, + "loss": 0.5811, "step": 2354 }, { - "epoch": 1.21, - "learning_rate": 7.114837114307329e-06, - "loss": 0.5952, + "epoch": 1.07, + "learning_rate": 9.30701496729088e-06, + "loss": 0.6229, "step": 2355 }, { - "epoch": 1.21, - "learning_rate": 7.106865689232689e-06, - "loss": 0.582, + "epoch": 1.07, + "learning_rate": 9.299654799207601e-06, + "loss": 0.6566, "step": 2356 }, { - "epoch": 1.21, - "learning_rate": 7.098896269990743e-06, - "loss": 0.5963, + "epoch": 1.07, + "learning_rate": 9.292295012366175e-06, + "loss": 0.6006, "step": 2357 }, { - "epoch": 1.21, - "learning_rate": 7.090928862106747e-06, - "loss": 0.6521, + "epoch": 1.07, + "learning_rate": 9.284935610772992e-06, + "loss": 0.6592, "step": 2358 }, { - "epoch": 1.21, - "learning_rate": 7.0829634711045755e-06, - "loss": 0.6166, + "epoch": 1.07, + "learning_rate": 9.277576598434237e-06, + "loss": 0.6395, "step": 2359 }, { - "epoch": 1.21, - "learning_rate": 7.075000102506693e-06, - "loss": 0.6146, + "epoch": 1.08, + "learning_rate": 9.270217979355883e-06, + "loss": 0.6082, "step": 2360 }, { - "epoch": 1.21, - "learning_rate": 7.067038761834164e-06, - "loss": 0.6268, + "epoch": 1.08, + "learning_rate": 9.26285975754369e-06, + "loss": 0.6125, "step": 2361 }, { - "epoch": 1.21, - "learning_rate": 7.059079454606648e-06, - "loss": 0.6238, + "epoch": 1.08, + "learning_rate": 9.255501937003192e-06, + "loss": 0.599, "step": 2362 }, { - "epoch": 1.21, - "learning_rate": 7.051122186342399e-06, - "loss": 0.5874, + "epoch": 1.08, + "learning_rate": 9.248144521739721e-06, + "loss": 0.6342, "step": 2363 }, { - "epoch": 1.22, - "learning_rate": 7.04316696255825e-06, - "loss": 0.5834, + "epoch": 1.08, + "learning_rate": 9.24078751575838e-06, + "loss": 0.6077, "step": 2364 }, { - "epoch": 1.22, - "learning_rate": 7.035213788769617e-06, - "loss": 0.6123, + "epoch": 1.08, + "learning_rate": 9.233430923064043e-06, + "loss": 0.6515, "step": 2365 }, { - "epoch": 1.22, - "learning_rate": 7.027262670490505e-06, - "loss": 0.6055, + "epoch": 1.08, + "learning_rate": 9.226074747661371e-06, + "loss": 0.644, "step": 2366 }, { - "epoch": 1.22, - "learning_rate": 7.019313613233484e-06, - "loss": 0.593, + "epoch": 1.08, + "learning_rate": 9.218718993554785e-06, + "loss": 0.6746, "step": 2367 }, { - "epoch": 1.22, - "learning_rate": 7.011366622509694e-06, - "loss": 0.6204, + "epoch": 1.08, + "learning_rate": 9.211363664748494e-06, + "loss": 0.666, "step": 2368 }, { - "epoch": 1.22, - "learning_rate": 7.0034217038288524e-06, - "loss": 0.5917, + "epoch": 1.08, + "learning_rate": 9.204008765246453e-06, + "loss": 0.6243, "step": 2369 }, { - "epoch": 1.22, - "learning_rate": 6.99547886269923e-06, - "loss": 0.6097, + "epoch": 1.08, + "learning_rate": 9.196654299052408e-06, + "loss": 0.614, "step": 2370 }, { - "epoch": 1.22, - "learning_rate": 6.9875381046276605e-06, - "loss": 0.5818, + "epoch": 1.08, + "learning_rate": 9.189300270169846e-06, + "loss": 0.6241, "step": 2371 }, { - "epoch": 1.22, - "learning_rate": 6.979599435119531e-06, - "loss": 0.6433, + "epoch": 1.08, + "learning_rate": 9.181946682602033e-06, + "loss": 0.6013, "step": 2372 }, { - "epoch": 1.22, - "learning_rate": 6.971662859678789e-06, - "loss": 0.5854, + "epoch": 1.08, + "learning_rate": 9.174593540351983e-06, + "loss": 0.6304, "step": 2373 }, { - "epoch": 1.22, - "learning_rate": 6.96372838380792e-06, - "loss": 0.5586, + "epoch": 1.08, + "learning_rate": 9.16724084742248e-06, + "loss": 0.638, "step": 2374 }, { - "epoch": 1.22, - "learning_rate": 6.9557960130079615e-06, - "loss": 0.6185, + "epoch": 1.08, + "learning_rate": 9.159888607816046e-06, + "loss": 0.6093, "step": 2375 }, { - "epoch": 1.22, - "learning_rate": 6.947865752778489e-06, - "loss": 0.5739, + "epoch": 1.08, + "learning_rate": 9.152536825534978e-06, + "loss": 0.6238, "step": 2376 }, { - "epoch": 1.22, - "learning_rate": 6.939937608617611e-06, - "loss": 0.5537, + "epoch": 1.08, + "learning_rate": 9.145185504581304e-06, + "loss": 0.634, "step": 2377 }, { - "epoch": 1.22, - "learning_rate": 6.9320115860219705e-06, - "loss": 0.6244, + "epoch": 1.08, + "learning_rate": 9.137834648956816e-06, + "loss": 0.566, "step": 2378 }, { - "epoch": 1.22, - "learning_rate": 6.924087690486746e-06, - "loss": 0.5647, + "epoch": 1.08, + "learning_rate": 9.130484262663038e-06, + "loss": 0.6501, "step": 2379 }, { - "epoch": 1.22, - "learning_rate": 6.916165927505635e-06, - "loss": 0.5822, + "epoch": 1.08, + "learning_rate": 9.123134349701254e-06, + "loss": 0.6555, "step": 2380 }, { - "epoch": 1.22, - "learning_rate": 6.908246302570856e-06, - "loss": 0.5978, + "epoch": 1.08, + "learning_rate": 9.115784914072476e-06, + "loss": 0.6205, "step": 2381 }, { - "epoch": 1.22, - "learning_rate": 6.9003288211731455e-06, - "loss": 0.5952, + "epoch": 1.09, + "learning_rate": 9.108435959777476e-06, + "loss": 0.6211, "step": 2382 }, { - "epoch": 1.22, - "learning_rate": 6.892413488801762e-06, - "loss": 0.5651, + "epoch": 1.09, + "learning_rate": 9.101087490816732e-06, + "loss": 0.615, "step": 2383 }, { - "epoch": 1.23, - "learning_rate": 6.884500310944457e-06, - "loss": 0.6285, + "epoch": 1.09, + "learning_rate": 9.093739511190493e-06, + "loss": 0.6456, "step": 2384 }, { - "epoch": 1.23, - "learning_rate": 6.87658929308751e-06, - "loss": 0.5881, + "epoch": 1.09, + "learning_rate": 9.086392024898718e-06, + "loss": 0.6068, "step": 2385 }, { - "epoch": 1.23, - "learning_rate": 6.868680440715687e-06, - "loss": 0.5765, + "epoch": 1.09, + "learning_rate": 9.07904503594111e-06, + "loss": 0.6166, "step": 2386 }, { - "epoch": 1.23, - "learning_rate": 6.860773759312257e-06, - "loss": 0.5789, + "epoch": 1.09, + "learning_rate": 9.071698548317088e-06, + "loss": 0.6443, "step": 2387 }, { - "epoch": 1.23, - "learning_rate": 6.8528692543589824e-06, - "loss": 0.6101, + "epoch": 1.09, + "learning_rate": 9.064352566025814e-06, + "loss": 0.5974, "step": 2388 }, { - "epoch": 1.23, - "learning_rate": 6.844966931336122e-06, - "loss": 0.6307, + "epoch": 1.09, + "learning_rate": 9.057007093066162e-06, + "loss": 0.6398, "step": 2389 }, { - "epoch": 1.23, - "learning_rate": 6.837066795722417e-06, - "loss": 0.6292, + "epoch": 1.09, + "learning_rate": 9.04966213343674e-06, + "loss": 0.6016, "step": 2390 }, { - "epoch": 1.23, - "learning_rate": 6.8291688529950925e-06, - "loss": 0.6021, + "epoch": 1.09, + "learning_rate": 9.042317691135862e-06, + "loss": 0.6179, "step": 2391 }, { - "epoch": 1.23, - "learning_rate": 6.821273108629853e-06, - "loss": 0.6184, + "epoch": 1.09, + "learning_rate": 9.034973770161579e-06, + "loss": 0.6081, "step": 2392 }, { - "epoch": 1.23, - "learning_rate": 6.813379568100883e-06, - "loss": 0.5579, + "epoch": 1.09, + "learning_rate": 9.02763037451164e-06, + "loss": 0.6431, "step": 2393 }, { - "epoch": 1.23, - "learning_rate": 6.805488236880831e-06, - "loss": 0.5421, + "epoch": 1.09, + "learning_rate": 9.02028750818352e-06, + "loss": 0.6127, "step": 2394 }, { - "epoch": 1.23, - "learning_rate": 6.797599120440826e-06, - "loss": 0.5952, + "epoch": 1.09, + "learning_rate": 9.012945175174397e-06, + "loss": 0.6538, "step": 2395 }, { - "epoch": 1.23, - "learning_rate": 6.7897122242504506e-06, - "loss": 0.6377, + "epoch": 1.09, + "learning_rate": 9.005603379481178e-06, + "loss": 0.6343, "step": 2396 }, { - "epoch": 1.23, - "learning_rate": 6.781827553777751e-06, - "loss": 0.6106, + "epoch": 1.09, + "learning_rate": 8.998262125100442e-06, + "loss": 0.6702, "step": 2397 }, { - "epoch": 1.23, - "learning_rate": 6.773945114489231e-06, - "loss": 0.5995, + "epoch": 1.09, + "learning_rate": 8.990921416028509e-06, + "loss": 0.6267, "step": 2398 }, { - "epoch": 1.23, - "learning_rate": 6.76606491184985e-06, - "loss": 0.6223, + "epoch": 1.09, + "learning_rate": 8.983581256261388e-06, + "loss": 0.6276, "step": 2399 }, { - "epoch": 1.23, - "learning_rate": 6.7581869513230115e-06, - "loss": 0.6359, + "epoch": 1.09, + "learning_rate": 8.976241649794779e-06, + "loss": 0.652, "step": 2400 }, { - "epoch": 1.23, - "learning_rate": 6.750311238370571e-06, - "loss": 0.6263, + "epoch": 1.09, + "learning_rate": 8.968902600624104e-06, + "loss": 0.6443, "step": 2401 }, { - "epoch": 1.23, - "learning_rate": 6.742437778452814e-06, - "loss": 0.5424, + "epoch": 1.09, + "learning_rate": 8.961564112744453e-06, + "loss": 0.6689, "step": 2402 }, { - "epoch": 1.24, - "learning_rate": 6.734566577028481e-06, - "loss": 0.5782, + "epoch": 1.09, + "learning_rate": 8.954226190150637e-06, + "loss": 0.5636, "step": 2403 }, { - "epoch": 1.24, - "learning_rate": 6.7266976395547286e-06, - "loss": 0.5846, + "epoch": 1.1, + "learning_rate": 8.946888836837143e-06, + "loss": 0.6367, "step": 2404 }, { - "epoch": 1.24, - "learning_rate": 6.718830971487165e-06, - "loss": 0.538, + "epoch": 1.1, + "learning_rate": 8.939552056798155e-06, + "loss": 0.6173, "step": 2405 }, { - "epoch": 1.24, - "learning_rate": 6.710966578279802e-06, - "loss": 0.6024, + "epoch": 1.1, + "learning_rate": 8.93221585402754e-06, + "loss": 0.5958, "step": 2406 }, { - "epoch": 1.24, - "learning_rate": 6.703104465385093e-06, - "loss": 0.6267, + "epoch": 1.1, + "learning_rate": 8.924880232518857e-06, + "loss": 0.6383, "step": 2407 }, { - "epoch": 1.24, - "learning_rate": 6.695244638253895e-06, - "loss": 0.5178, + "epoch": 1.1, + "learning_rate": 8.91754519626534e-06, + "loss": 0.6063, "step": 2408 }, { - "epoch": 1.24, - "learning_rate": 6.687387102335492e-06, - "loss": 0.6113, + "epoch": 1.1, + "learning_rate": 8.910210749259918e-06, + "loss": 0.6093, "step": 2409 }, { - "epoch": 1.24, - "learning_rate": 6.679531863077577e-06, - "loss": 0.5905, + "epoch": 1.1, + "learning_rate": 8.902876895495184e-06, + "loss": 0.6097, "step": 2410 }, { - "epoch": 1.24, - "learning_rate": 6.671678925926244e-06, - "loss": 0.6326, + "epoch": 1.1, + "learning_rate": 8.895543638963418e-06, + "loss": 0.6486, "step": 2411 }, { - "epoch": 1.24, - "learning_rate": 6.663828296325998e-06, - "loss": 0.6112, + "epoch": 1.1, + "learning_rate": 8.888210983656568e-06, + "loss": 0.5951, "step": 2412 }, { - "epoch": 1.24, - "learning_rate": 6.655979979719744e-06, - "loss": 0.5564, + "epoch": 1.1, + "learning_rate": 8.880878933566263e-06, + "loss": 0.593, "step": 2413 }, { - "epoch": 1.24, - "learning_rate": 6.648133981548775e-06, - "loss": 0.5941, + "epoch": 1.1, + "learning_rate": 8.873547492683794e-06, + "loss": 0.6599, "step": 2414 }, { - "epoch": 1.24, - "learning_rate": 6.640290307252792e-06, - "loss": 0.5809, + "epoch": 1.1, + "learning_rate": 8.866216665000133e-06, + "loss": 0.6445, "step": 2415 }, { - "epoch": 1.24, - "learning_rate": 6.632448962269873e-06, - "loss": 0.5787, + "epoch": 1.1, + "learning_rate": 8.858886454505895e-06, + "loss": 0.6364, "step": 2416 }, { - "epoch": 1.24, - "learning_rate": 6.624609952036482e-06, - "loss": 0.58, + "epoch": 1.1, + "learning_rate": 8.851556865191387e-06, + "loss": 0.6418, "step": 2417 }, { - "epoch": 1.24, - "learning_rate": 6.616773281987465e-06, - "loss": 0.6212, + "epoch": 1.1, + "learning_rate": 8.844227901046557e-06, + "loss": 0.6241, "step": 2418 }, { - "epoch": 1.24, - "learning_rate": 6.60893895755605e-06, - "loss": 0.6068, + "epoch": 1.1, + "learning_rate": 8.836899566061027e-06, + "loss": 0.573, "step": 2419 }, { - "epoch": 1.24, - "learning_rate": 6.601106984173835e-06, - "loss": 0.6091, + "epoch": 1.1, + "learning_rate": 8.82957186422406e-06, + "loss": 0.6802, "step": 2420 }, { - "epoch": 1.24, - "learning_rate": 6.593277367270787e-06, - "loss": 0.5703, + "epoch": 1.1, + "learning_rate": 8.822244799524596e-06, + "loss": 0.5392, "step": 2421 }, { - "epoch": 1.24, - "learning_rate": 6.58545011227524e-06, - "loss": 0.5967, + "epoch": 1.1, + "learning_rate": 8.814918375951203e-06, + "loss": 0.5996, "step": 2422 }, { - "epoch": 1.25, - "learning_rate": 6.577625224613895e-06, - "loss": 0.5859, + "epoch": 1.1, + "learning_rate": 8.807592597492123e-06, + "loss": 0.6716, "step": 2423 }, { - "epoch": 1.25, - "learning_rate": 6.5698027097118e-06, - "loss": 0.5803, + "epoch": 1.1, + "learning_rate": 8.800267468135233e-06, + "loss": 0.6029, "step": 2424 }, { - "epoch": 1.25, - "learning_rate": 6.561982572992377e-06, - "loss": 0.5928, + "epoch": 1.1, + "learning_rate": 8.792942991868063e-06, + "loss": 0.5869, "step": 2425 }, { - "epoch": 1.25, - "learning_rate": 6.554164819877382e-06, - "loss": 0.6565, + "epoch": 1.11, + "learning_rate": 8.785619172677781e-06, + "loss": 0.6624, "step": 2426 }, { - "epoch": 1.25, - "learning_rate": 6.546349455786926e-06, - "loss": 0.5861, + "epoch": 1.11, + "learning_rate": 8.778296014551209e-06, + "loss": 0.649, "step": 2427 }, { - "epoch": 1.25, - "learning_rate": 6.538536486139457e-06, - "loss": 0.5875, + "epoch": 1.11, + "learning_rate": 8.770973521474791e-06, + "loss": 0.585, "step": 2428 }, { - "epoch": 1.25, - "learning_rate": 6.530725916351777e-06, - "loss": 0.597, + "epoch": 1.11, + "learning_rate": 8.763651697434628e-06, + "loss": 0.6152, "step": 2429 }, { - "epoch": 1.25, - "learning_rate": 6.522917751839011e-06, - "loss": 0.5466, + "epoch": 1.11, + "learning_rate": 8.756330546416445e-06, + "loss": 0.6235, "step": 2430 }, { - "epoch": 1.25, - "learning_rate": 6.515111998014618e-06, - "loss": 0.614, + "epoch": 1.11, + "learning_rate": 8.749010072405606e-06, + "loss": 0.6155, "step": 2431 }, { - "epoch": 1.25, - "learning_rate": 6.50730866029039e-06, - "loss": 0.564, + "epoch": 1.11, + "learning_rate": 8.741690279387103e-06, + "loss": 0.6171, "step": 2432 }, { - "epoch": 1.25, - "learning_rate": 6.499507744076444e-06, - "loss": 0.5984, + "epoch": 1.11, + "learning_rate": 8.734371171345554e-06, + "loss": 0.6437, "step": 2433 }, { - "epoch": 1.25, - "learning_rate": 6.491709254781211e-06, - "loss": 0.6243, + "epoch": 1.11, + "learning_rate": 8.72705275226522e-06, + "loss": 0.6151, "step": 2434 }, { - "epoch": 1.25, - "learning_rate": 6.483913197811454e-06, - "loss": 0.5781, + "epoch": 1.11, + "learning_rate": 8.719735026129968e-06, + "loss": 0.6143, "step": 2435 }, { - "epoch": 1.25, - "learning_rate": 6.476119578572235e-06, - "loss": 0.554, + "epoch": 1.11, + "learning_rate": 8.7124179969233e-06, + "loss": 0.6327, "step": 2436 }, { - "epoch": 1.25, - "learning_rate": 6.46832840246693e-06, - "loss": 0.5736, + "epoch": 1.11, + "learning_rate": 8.705101668628327e-06, + "loss": 0.6349, "step": 2437 }, { - "epoch": 1.25, - "learning_rate": 6.460539674897226e-06, - "loss": 0.616, + "epoch": 1.11, + "learning_rate": 8.697786045227793e-06, + "loss": 0.5916, "step": 2438 }, { - "epoch": 1.25, - "learning_rate": 6.4527534012631055e-06, - "loss": 0.5779, + "epoch": 1.11, + "learning_rate": 8.690471130704046e-06, + "loss": 0.6262, "step": 2439 }, { - "epoch": 1.25, - "learning_rate": 6.444969586962856e-06, - "loss": 0.6118, + "epoch": 1.11, + "learning_rate": 8.68315692903906e-06, + "loss": 0.6189, "step": 2440 }, { - "epoch": 1.25, - "learning_rate": 6.437188237393055e-06, - "loss": 0.5797, + "epoch": 1.11, + "learning_rate": 8.675843444214403e-06, + "loss": 0.6381, "step": 2441 }, { - "epoch": 1.26, - "learning_rate": 6.429409357948572e-06, - "loss": 0.5211, + "epoch": 1.11, + "learning_rate": 8.668530680211276e-06, + "loss": 0.6127, "step": 2442 }, { - "epoch": 1.26, - "learning_rate": 6.421632954022568e-06, - "loss": 0.6205, + "epoch": 1.11, + "learning_rate": 8.661218641010465e-06, + "loss": 0.5671, "step": 2443 }, { - "epoch": 1.26, - "learning_rate": 6.41385903100648e-06, - "loss": 0.6216, + "epoch": 1.11, + "learning_rate": 8.653907330592381e-06, + "loss": 0.6592, "step": 2444 }, { - "epoch": 1.26, - "learning_rate": 6.406087594290037e-06, - "loss": 0.6299, + "epoch": 1.11, + "learning_rate": 8.646596752937021e-06, + "loss": 0.5948, "step": 2445 }, { - "epoch": 1.26, - "learning_rate": 6.398318649261233e-06, - "loss": 0.5547, + "epoch": 1.11, + "learning_rate": 8.639286912023999e-06, + "loss": 0.5946, "step": 2446 }, { - "epoch": 1.26, - "learning_rate": 6.390552201306337e-06, - "loss": 0.5389, + "epoch": 1.11, + "learning_rate": 8.631977811832511e-06, + "loss": 0.5941, "step": 2447 }, { - "epoch": 1.26, - "learning_rate": 6.382788255809893e-06, - "loss": 0.6035, + "epoch": 1.12, + "learning_rate": 8.624669456341368e-06, + "loss": 0.6116, "step": 2448 }, { - "epoch": 1.26, - "learning_rate": 6.3750268181547e-06, - "loss": 0.6152, + "epoch": 1.12, + "learning_rate": 8.617361849528962e-06, + "loss": 0.5711, "step": 2449 }, { - "epoch": 1.26, - "learning_rate": 6.3672678937218266e-06, - "loss": 0.5916, + "epoch": 1.12, + "learning_rate": 8.610054995373282e-06, + "loss": 0.6129, "step": 2450 }, { - "epoch": 1.26, - "learning_rate": 6.359511487890595e-06, - "loss": 0.5955, + "epoch": 1.12, + "learning_rate": 8.60274889785191e-06, + "loss": 0.6697, "step": 2451 }, { - "epoch": 1.26, - "learning_rate": 6.351757606038582e-06, - "loss": 0.6105, + "epoch": 1.12, + "learning_rate": 8.595443560942011e-06, + "loss": 0.6246, "step": 2452 }, { - "epoch": 1.26, - "learning_rate": 6.344006253541612e-06, - "loss": 0.5941, + "epoch": 1.12, + "learning_rate": 8.588138988620336e-06, + "loss": 0.61, "step": 2453 }, { - "epoch": 1.26, - "learning_rate": 6.336257435773765e-06, - "loss": 0.6365, + "epoch": 1.12, + "learning_rate": 8.58083518486323e-06, + "loss": 0.5807, "step": 2454 }, { - "epoch": 1.26, - "learning_rate": 6.3285111581073535e-06, - "loss": 0.605, + "epoch": 1.12, + "learning_rate": 8.573532153646602e-06, + "loss": 0.5868, "step": 2455 }, { - "epoch": 1.26, - "learning_rate": 6.3207674259129325e-06, - "loss": 0.5239, + "epoch": 1.12, + "learning_rate": 8.566229898945959e-06, + "loss": 0.5568, "step": 2456 }, { - "epoch": 1.26, - "learning_rate": 6.313026244559289e-06, - "loss": 0.6262, + "epoch": 1.12, + "learning_rate": 8.55892842473637e-06, + "loss": 0.676, "step": 2457 }, { - "epoch": 1.26, - "learning_rate": 6.305287619413452e-06, - "loss": 0.6202, + "epoch": 1.12, + "learning_rate": 8.551627734992493e-06, + "loss": 0.6232, "step": 2458 }, { - "epoch": 1.26, - "learning_rate": 6.297551555840665e-06, - "loss": 0.5913, + "epoch": 1.12, + "learning_rate": 8.544327833688544e-06, + "loss": 0.6484, "step": 2459 }, { - "epoch": 1.26, - "learning_rate": 6.289818059204404e-06, - "loss": 0.6111, + "epoch": 1.12, + "learning_rate": 8.537028724798322e-06, + "loss": 0.632, "step": 2460 }, { - "epoch": 1.26, - "learning_rate": 6.28208713486636e-06, - "loss": 0.6178, + "epoch": 1.12, + "learning_rate": 8.529730412295186e-06, + "loss": 0.6288, "step": 2461 }, { - "epoch": 1.27, - "learning_rate": 6.2743587881864485e-06, - "loss": 0.5916, + "epoch": 1.12, + "learning_rate": 8.522432900152071e-06, + "loss": 0.569, "step": 2462 }, { - "epoch": 1.27, - "learning_rate": 6.266633024522786e-06, - "loss": 0.59, + "epoch": 1.12, + "learning_rate": 8.515136192341466e-06, + "loss": 0.6099, "step": 2463 }, { - "epoch": 1.27, - "learning_rate": 6.258909849231711e-06, - "loss": 0.5857, + "epoch": 1.12, + "learning_rate": 8.50784029283543e-06, + "loss": 0.6281, "step": 2464 }, { - "epoch": 1.27, - "learning_rate": 6.251189267667761e-06, - "loss": 0.6094, + "epoch": 1.12, + "learning_rate": 8.50054520560558e-06, + "loss": 0.6576, "step": 2465 }, { - "epoch": 1.27, - "learning_rate": 6.243471285183675e-06, - "loss": 0.6069, + "epoch": 1.12, + "learning_rate": 8.493250934623085e-06, + "loss": 0.575, "step": 2466 }, { - "epoch": 1.27, - "learning_rate": 6.235755907130387e-06, - "loss": 0.5895, + "epoch": 1.12, + "learning_rate": 8.48595748385868e-06, + "loss": 0.5906, "step": 2467 }, { - "epoch": 1.27, - "learning_rate": 6.228043138857034e-06, - "loss": 0.5961, + "epoch": 1.12, + "learning_rate": 8.478664857282646e-06, + "loss": 0.6035, "step": 2468 }, { - "epoch": 1.27, - "learning_rate": 6.220332985710936e-06, - "loss": 0.6226, + "epoch": 1.12, + "learning_rate": 8.471373058864817e-06, + "loss": 0.6219, "step": 2469 }, { - "epoch": 1.27, - "learning_rate": 6.212625453037604e-06, - "loss": 0.583, + "epoch": 1.13, + "learning_rate": 8.464082092574575e-06, + "loss": 0.6008, "step": 2470 }, { - "epoch": 1.27, - "learning_rate": 6.204920546180728e-06, - "loss": 0.5835, + "epoch": 1.13, + "learning_rate": 8.456791962380854e-06, + "loss": 0.5955, "step": 2471 }, { - "epoch": 1.27, - "learning_rate": 6.197218270482184e-06, - "loss": 0.5929, + "epoch": 1.13, + "learning_rate": 8.449502672252125e-06, + "loss": 0.6301, "step": 2472 }, { - "epoch": 1.27, - "learning_rate": 6.189518631282015e-06, - "loss": 0.6426, + "epoch": 1.13, + "learning_rate": 8.442214226156415e-06, + "loss": 0.5674, "step": 2473 }, { - "epoch": 1.27, - "learning_rate": 6.181821633918448e-06, - "loss": 0.5986, + "epoch": 1.13, + "learning_rate": 8.434926628061268e-06, + "loss": 0.5919, "step": 2474 }, { - "epoch": 1.27, - "learning_rate": 6.174127283727869e-06, - "loss": 0.6006, + "epoch": 1.13, + "learning_rate": 8.427639881933795e-06, + "loss": 0.6414, "step": 2475 }, { - "epoch": 1.27, - "learning_rate": 6.16643558604483e-06, - "loss": 0.6301, + "epoch": 1.13, + "learning_rate": 8.420353991740621e-06, + "loss": 0.6008, "step": 2476 }, { - "epoch": 1.27, - "learning_rate": 6.1587465462020445e-06, - "loss": 0.5858, + "epoch": 1.13, + "learning_rate": 8.41306896144792e-06, + "loss": 0.6476, "step": 2477 }, { - "epoch": 1.27, - "learning_rate": 6.1510601695303876e-06, - "loss": 0.5928, + "epoch": 1.13, + "learning_rate": 8.405784795021383e-06, + "loss": 0.5914, "step": 2478 }, { - "epoch": 1.27, - "learning_rate": 6.143376461358881e-06, - "loss": 0.5959, + "epoch": 1.13, + "learning_rate": 8.398501496426246e-06, + "loss": 0.6136, "step": 2479 }, { - "epoch": 1.27, - "learning_rate": 6.135695427014703e-06, - "loss": 0.5784, + "epoch": 1.13, + "learning_rate": 8.39121906962726e-06, + "loss": 0.6714, "step": 2480 }, { - "epoch": 1.28, - "learning_rate": 6.1280170718231706e-06, - "loss": 0.6145, + "epoch": 1.13, + "learning_rate": 8.383937518588713e-06, + "loss": 0.5617, "step": 2481 }, { - "epoch": 1.28, - "learning_rate": 6.120341401107751e-06, - "loss": 0.5663, + "epoch": 1.13, + "learning_rate": 8.376656847274404e-06, + "loss": 0.6189, "step": 2482 }, { - "epoch": 1.28, - "learning_rate": 6.112668420190042e-06, - "loss": 0.6382, + "epoch": 1.13, + "learning_rate": 8.369377059647666e-06, + "loss": 0.6254, "step": 2483 }, { - "epoch": 1.28, - "learning_rate": 6.104998134389791e-06, - "loss": 0.6282, + "epoch": 1.13, + "learning_rate": 8.362098159671339e-06, + "loss": 0.6277, "step": 2484 }, { - "epoch": 1.28, - "learning_rate": 6.09733054902486e-06, - "loss": 0.5786, + "epoch": 1.13, + "learning_rate": 8.354820151307787e-06, + "loss": 0.644, "step": 2485 }, { - "epoch": 1.28, - "learning_rate": 6.089665669411249e-06, - "loss": 0.5656, + "epoch": 1.13, + "learning_rate": 8.347543038518885e-06, + "loss": 0.6503, "step": 2486 }, { - "epoch": 1.28, - "learning_rate": 6.0820035008630765e-06, - "loss": 0.5818, + "epoch": 1.13, + "learning_rate": 8.340266825266026e-06, + "loss": 0.6641, "step": 2487 }, { - "epoch": 1.28, - "learning_rate": 6.074344048692585e-06, - "loss": 0.6066, + "epoch": 1.13, + "learning_rate": 8.332991515510106e-06, + "loss": 0.5824, "step": 2488 }, { - "epoch": 1.28, - "learning_rate": 6.0666873182101334e-06, - "loss": 0.5968, + "epoch": 1.13, + "learning_rate": 8.325717113211536e-06, + "loss": 0.594, "step": 2489 }, { - "epoch": 1.28, - "learning_rate": 6.059033314724194e-06, - "loss": 0.5781, + "epoch": 1.13, + "learning_rate": 8.318443622330227e-06, + "loss": 0.6462, "step": 2490 }, { - "epoch": 1.28, - "learning_rate": 6.0513820435413425e-06, - "loss": 0.5895, + "epoch": 1.13, + "learning_rate": 8.311171046825597e-06, + "loss": 0.6498, "step": 2491 }, { - "epoch": 1.28, - "learning_rate": 6.043733509966272e-06, - "loss": 0.6171, + "epoch": 1.14, + "learning_rate": 8.303899390656565e-06, + "loss": 0.6106, "step": 2492 }, { - "epoch": 1.28, - "learning_rate": 6.036087719301763e-06, - "loss": 0.563, + "epoch": 1.14, + "learning_rate": 8.296628657781556e-06, + "loss": 0.646, "step": 2493 }, { - "epoch": 1.28, - "learning_rate": 6.0284446768487105e-06, - "loss": 0.5782, + "epoch": 1.14, + "learning_rate": 8.289358852158473e-06, + "loss": 0.5817, "step": 2494 }, { - "epoch": 1.28, - "learning_rate": 6.020804387906091e-06, - "loss": 0.5637, + "epoch": 1.14, + "learning_rate": 8.282089977744742e-06, + "loss": 0.615, "step": 2495 }, { - "epoch": 1.28, - "learning_rate": 6.013166857770979e-06, - "loss": 0.5955, + "epoch": 1.14, + "learning_rate": 8.274822038497257e-06, + "loss": 0.6323, "step": 2496 }, { - "epoch": 1.28, - "learning_rate": 6.0055320917385305e-06, - "loss": 0.6274, + "epoch": 1.14, + "learning_rate": 8.267555038372421e-06, + "loss": 0.6543, "step": 2497 }, { - "epoch": 1.28, - "learning_rate": 5.997900095101992e-06, - "loss": 0.616, + "epoch": 1.14, + "learning_rate": 8.260288981326113e-06, + "loss": 0.6245, "step": 2498 }, { - "epoch": 1.28, - "learning_rate": 5.990270873152683e-06, - "loss": 0.5994, + "epoch": 1.14, + "learning_rate": 8.253023871313702e-06, + "loss": 0.6101, "step": 2499 }, { - "epoch": 1.29, - "learning_rate": 5.982644431180009e-06, - "loss": 0.6051, + "epoch": 1.14, + "learning_rate": 8.245759712290052e-06, + "loss": 0.6204, "step": 2500 }, { - "epoch": 1.29, - "learning_rate": 5.975020774471434e-06, - "loss": 0.6354, + "epoch": 1.14, + "learning_rate": 8.238496508209495e-06, + "loss": 0.5536, "step": 2501 }, { - "epoch": 1.29, - "learning_rate": 5.967399908312506e-06, - "loss": 0.5806, + "epoch": 1.14, + "learning_rate": 8.231234263025851e-06, + "loss": 0.6445, "step": 2502 }, { - "epoch": 1.29, - "learning_rate": 5.959781837986822e-06, - "loss": 0.6019, + "epoch": 1.14, + "learning_rate": 8.223972980692412e-06, + "loss": 0.5748, "step": 2503 }, { - "epoch": 1.29, - "learning_rate": 5.952166568776062e-06, - "loss": 0.6494, + "epoch": 1.14, + "learning_rate": 8.216712665161955e-06, + "loss": 0.6543, "step": 2504 }, { - "epoch": 1.29, - "learning_rate": 5.9445541059599455e-06, - "loss": 0.5681, + "epoch": 1.14, + "learning_rate": 8.209453320386717e-06, + "loss": 0.6136, "step": 2505 }, { - "epoch": 1.29, - "learning_rate": 5.936944454816254e-06, - "loss": 0.6221, + "epoch": 1.14, + "learning_rate": 8.202194950318426e-06, + "loss": 0.6469, "step": 2506 }, { - "epoch": 1.29, - "learning_rate": 5.929337620620814e-06, - "loss": 0.6167, + "epoch": 1.14, + "learning_rate": 8.194937558908261e-06, + "loss": 0.6482, "step": 2507 }, { - "epoch": 1.29, - "learning_rate": 5.921733608647509e-06, - "loss": 0.6091, + "epoch": 1.14, + "learning_rate": 8.18768115010688e-06, + "loss": 0.5924, "step": 2508 }, { - "epoch": 1.29, - "learning_rate": 5.914132424168258e-06, - "loss": 0.6409, + "epoch": 1.14, + "learning_rate": 8.180425727864397e-06, + "loss": 0.5719, "step": 2509 }, { - "epoch": 1.29, - "learning_rate": 5.90653407245302e-06, - "loss": 0.5988, + "epoch": 1.14, + "learning_rate": 8.173171296130398e-06, + "loss": 0.6416, "step": 2510 }, { - "epoch": 1.29, - "learning_rate": 5.8989385587697936e-06, - "loss": 0.582, + "epoch": 1.14, + "learning_rate": 8.16591785885392e-06, + "loss": 0.5848, "step": 2511 }, { - "epoch": 1.29, - "learning_rate": 5.89134588838461e-06, - "loss": 0.5538, + "epoch": 1.14, + "learning_rate": 8.158665419983475e-06, + "loss": 0.5783, "step": 2512 }, { - "epoch": 1.29, - "learning_rate": 5.883756066561519e-06, - "loss": 0.6184, + "epoch": 1.14, + "learning_rate": 8.151413983467007e-06, + "loss": 0.5676, "step": 2513 }, { - "epoch": 1.29, - "learning_rate": 5.876169098562614e-06, - "loss": 0.5555, + "epoch": 1.15, + "learning_rate": 8.144163553251937e-06, + "loss": 0.6241, "step": 2514 }, { - "epoch": 1.29, - "learning_rate": 5.868584989647994e-06, - "loss": 0.5471, + "epoch": 1.15, + "learning_rate": 8.136914133285127e-06, + "loss": 0.6133, "step": 2515 }, { - "epoch": 1.29, - "learning_rate": 5.861003745075783e-06, - "loss": 0.6031, + "epoch": 1.15, + "learning_rate": 8.129665727512894e-06, + "loss": 0.6387, "step": 2516 }, { - "epoch": 1.29, - "learning_rate": 5.853425370102114e-06, - "loss": 0.5986, + "epoch": 1.15, + "learning_rate": 8.122418339880992e-06, + "loss": 0.6151, "step": 2517 }, { - "epoch": 1.29, - "learning_rate": 5.845849869981137e-06, - "loss": 0.5898, + "epoch": 1.15, + "learning_rate": 8.115171974334639e-06, + "loss": 0.5906, "step": 2518 }, { - "epoch": 1.29, - "learning_rate": 5.838277249965003e-06, - "loss": 0.5947, + "epoch": 1.15, + "learning_rate": 8.107926634818477e-06, + "loss": 0.6577, "step": 2519 }, { - "epoch": 1.3, - "learning_rate": 5.830707515303872e-06, - "loss": 0.5801, + "epoch": 1.15, + "learning_rate": 8.100682325276609e-06, + "loss": 0.5904, "step": 2520 }, { - "epoch": 1.3, - "learning_rate": 5.8231406712459e-06, - "loss": 0.5872, + "epoch": 1.15, + "learning_rate": 8.09343904965256e-06, + "loss": 0.6503, "step": 2521 }, { - "epoch": 1.3, - "learning_rate": 5.8155767230372375e-06, - "loss": 0.6212, + "epoch": 1.15, + "learning_rate": 8.086196811889303e-06, + "loss": 0.6545, "step": 2522 }, { - "epoch": 1.3, - "learning_rate": 5.808015675922025e-06, - "loss": 0.5975, + "epoch": 1.15, + "learning_rate": 8.07895561592924e-06, + "loss": 0.5789, "step": 2523 }, { - "epoch": 1.3, - "learning_rate": 5.8004575351424044e-06, - "loss": 0.6116, + "epoch": 1.15, + "learning_rate": 8.071715465714212e-06, + "loss": 0.6134, "step": 2524 }, { - "epoch": 1.3, - "learning_rate": 5.792902305938491e-06, - "loss": 0.562, + "epoch": 1.15, + "learning_rate": 8.06447636518548e-06, + "loss": 0.59, "step": 2525 }, { - "epoch": 1.3, - "learning_rate": 5.785349993548382e-06, - "loss": 0.6156, + "epoch": 1.15, + "learning_rate": 8.057238318283755e-06, + "loss": 0.5771, "step": 2526 }, { - "epoch": 1.3, - "learning_rate": 5.777800603208155e-06, - "loss": 0.5789, - "step": 2527 + "epoch": 1.15, + "learning_rate": 8.050001328949142e-06, + "loss": 0.5969, + "step": 2527 }, { - "epoch": 1.3, - "learning_rate": 5.770254140151864e-06, - "loss": 0.5833, + "epoch": 1.15, + "learning_rate": 8.042765401121203e-06, + "loss": 0.6129, "step": 2528 }, { - "epoch": 1.3, - "learning_rate": 5.762710609611526e-06, - "loss": 0.6296, + "epoch": 1.15, + "learning_rate": 8.0355305387389e-06, + "loss": 0.567, "step": 2529 }, { - "epoch": 1.3, - "learning_rate": 5.755170016817135e-06, - "loss": 0.5809, + "epoch": 1.15, + "learning_rate": 8.028296745740627e-06, + "loss": 0.6262, "step": 2530 }, { - "epoch": 1.3, - "learning_rate": 5.747632366996644e-06, - "loss": 0.6105, + "epoch": 1.15, + "learning_rate": 8.021064026064188e-06, + "loss": 0.6736, "step": 2531 }, { - "epoch": 1.3, - "learning_rate": 5.740097665375956e-06, - "loss": 0.6062, + "epoch": 1.15, + "learning_rate": 8.013832383646806e-06, + "loss": 0.6243, "step": 2532 }, { - "epoch": 1.3, - "learning_rate": 5.732565917178952e-06, - "loss": 0.5779, + "epoch": 1.15, + "learning_rate": 8.006601822425122e-06, + "loss": 0.6355, "step": 2533 }, { - "epoch": 1.3, - "learning_rate": 5.725037127627442e-06, - "loss": 0.5851, + "epoch": 1.15, + "learning_rate": 7.999372346335182e-06, + "loss": 0.6256, "step": 2534 }, { - "epoch": 1.3, - "learning_rate": 5.7175113019411986e-06, - "loss": 0.5974, + "epoch": 1.15, + "learning_rate": 7.992143959312447e-06, + "loss": 0.6226, "step": 2535 }, { - "epoch": 1.3, - "learning_rate": 5.709988445337935e-06, - "loss": 0.6021, + "epoch": 1.16, + "learning_rate": 7.984916665291773e-06, + "loss": 0.6448, "step": 2536 }, { - "epoch": 1.3, - "learning_rate": 5.702468563033307e-06, - "loss": 0.6155, + "epoch": 1.16, + "learning_rate": 7.977690468207439e-06, + "loss": 0.5897, "step": 2537 }, { - "epoch": 1.3, - "learning_rate": 5.6949516602409064e-06, - "loss": 0.5634, + "epoch": 1.16, + "learning_rate": 7.97046537199311e-06, + "loss": 0.6034, "step": 2538 }, { - "epoch": 1.31, - "learning_rate": 5.687437742172258e-06, - "loss": 0.5729, + "epoch": 1.16, + "learning_rate": 7.963241380581867e-06, + "loss": 0.5985, "step": 2539 }, { - "epoch": 1.31, - "learning_rate": 5.6799268140368295e-06, - "loss": 0.6023, + "epoch": 1.16, + "learning_rate": 7.956018497906176e-06, + "loss": 0.6334, "step": 2540 }, { - "epoch": 1.31, - "learning_rate": 5.672418881041999e-06, - "loss": 0.5977, + "epoch": 1.16, + "learning_rate": 7.948796727897909e-06, + "loss": 0.6268, "step": 2541 }, { - "epoch": 1.31, - "learning_rate": 5.664913948393072e-06, - "loss": 0.5912, + "epoch": 1.16, + "learning_rate": 7.941576074488326e-06, + "loss": 0.6189, "step": 2542 }, { - "epoch": 1.31, - "learning_rate": 5.657412021293288e-06, - "loss": 0.6105, + "epoch": 1.16, + "learning_rate": 7.934356541608084e-06, + "loss": 0.6061, "step": 2543 }, { - "epoch": 1.31, - "learning_rate": 5.649913104943785e-06, - "loss": 0.5652, + "epoch": 1.16, + "learning_rate": 7.927138133187221e-06, + "loss": 0.5803, "step": 2544 }, { - "epoch": 1.31, - "learning_rate": 5.642417204543622e-06, - "loss": 0.6367, + "epoch": 1.16, + "learning_rate": 7.919920853155183e-06, + "loss": 0.6394, "step": 2545 }, { - "epoch": 1.31, - "learning_rate": 5.634924325289766e-06, - "loss": 0.5969, + "epoch": 1.16, + "learning_rate": 7.912704705440779e-06, + "loss": 0.5594, "step": 2546 }, { - "epoch": 1.31, - "learning_rate": 5.627434472377086e-06, - "loss": 0.6421, + "epoch": 1.16, + "learning_rate": 7.905489693972214e-06, + "loss": 0.6235, "step": 2547 }, { - "epoch": 1.31, - "learning_rate": 5.6199476509983546e-06, - "loss": 0.6349, + "epoch": 1.16, + "learning_rate": 7.898275822677069e-06, + "loss": 0.6245, "step": 2548 }, { - "epoch": 1.31, - "learning_rate": 5.6124638663442495e-06, - "loss": 0.6143, + "epoch": 1.16, + "learning_rate": 7.891063095482313e-06, + "loss": 0.6229, "step": 2549 }, { - "epoch": 1.31, - "learning_rate": 5.604983123603336e-06, - "loss": 0.5691, + "epoch": 1.16, + "learning_rate": 7.883851516314275e-06, + "loss": 0.6434, "step": 2550 }, { - "epoch": 1.31, - "learning_rate": 5.597505427962069e-06, - "loss": 0.5674, + "epoch": 1.16, + "learning_rate": 7.876641089098685e-06, + "loss": 0.6198, "step": 2551 }, { - "epoch": 1.31, - "learning_rate": 5.590030784604792e-06, - "loss": 0.6178, + "epoch": 1.16, + "learning_rate": 7.869431817760616e-06, + "loss": 0.6062, "step": 2552 }, { - "epoch": 1.31, - "learning_rate": 5.58255919871374e-06, - "loss": 0.6049, + "epoch": 1.16, + "learning_rate": 7.862223706224538e-06, + "loss": 0.6259, "step": 2553 }, { - "epoch": 1.31, - "learning_rate": 5.575090675469017e-06, - "loss": 0.6163, + "epoch": 1.16, + "learning_rate": 7.855016758414274e-06, + "loss": 0.5886, "step": 2554 }, { - "epoch": 1.31, - "learning_rate": 5.5676252200486115e-06, - "loss": 0.5708, + "epoch": 1.16, + "learning_rate": 7.847810978253018e-06, + "loss": 0.631, "step": 2555 }, { - "epoch": 1.31, - "learning_rate": 5.56016283762838e-06, - "loss": 0.5648, + "epoch": 1.16, + "learning_rate": 7.840606369663329e-06, + "loss": 0.5547, "step": 2556 }, { - "epoch": 1.31, - "learning_rate": 5.552703533382054e-06, - "loss": 0.6028, + "epoch": 1.16, + "learning_rate": 7.83340293656713e-06, + "loss": 0.6552, "step": 2557 }, { - "epoch": 1.31, - "learning_rate": 5.545247312481219e-06, - "loss": 0.6217, + "epoch": 1.17, + "learning_rate": 7.826200682885695e-06, + "loss": 0.6008, "step": 2558 }, { - "epoch": 1.32, - "learning_rate": 5.537794180095341e-06, - "loss": 0.6134, + "epoch": 1.17, + "learning_rate": 7.818999612539672e-06, + "loss": 0.6271, "step": 2559 }, { - "epoch": 1.32, - "learning_rate": 5.530344141391735e-06, - "loss": 0.547, + "epoch": 1.17, + "learning_rate": 7.811799729449047e-06, + "loss": 0.6073, "step": 2560 }, { - "epoch": 1.32, - "learning_rate": 5.522897201535567e-06, - "loss": 0.5878, + "epoch": 1.17, + "learning_rate": 7.804601037533176e-06, + "loss": 0.6398, "step": 2561 }, { - "epoch": 1.32, - "learning_rate": 5.515453365689853e-06, - "loss": 0.5808, + "epoch": 1.17, + "learning_rate": 7.797403540710752e-06, + "loss": 0.6351, "step": 2562 }, { - "epoch": 1.32, - "learning_rate": 5.508012639015476e-06, - "loss": 0.5969, + "epoch": 1.17, + "learning_rate": 7.79020724289983e-06, + "loss": 0.6462, "step": 2563 }, { - "epoch": 1.32, - "learning_rate": 5.500575026671144e-06, - "loss": 0.5684, + "epoch": 1.17, + "learning_rate": 7.783012148017797e-06, + "loss": 0.6168, "step": 2564 }, { - "epoch": 1.32, - "learning_rate": 5.49314053381341e-06, - "loss": 0.6233, + "epoch": 1.17, + "learning_rate": 7.77581825998141e-06, + "loss": 0.6067, "step": 2565 }, { - "epoch": 1.32, - "learning_rate": 5.485709165596669e-06, - "loss": 0.6093, + "epoch": 1.17, + "learning_rate": 7.768625582706738e-06, + "loss": 0.5759, "step": 2566 }, { - "epoch": 1.32, - "learning_rate": 5.478280927173145e-06, - "loss": 0.5898, + "epoch": 1.17, + "learning_rate": 7.761434120109217e-06, + "loss": 0.629, "step": 2567 }, { - "epoch": 1.32, - "learning_rate": 5.470855823692891e-06, - "loss": 0.5679, + "epoch": 1.17, + "learning_rate": 7.754243876103611e-06, + "loss": 0.6476, "step": 2568 }, { - "epoch": 1.32, - "learning_rate": 5.463433860303797e-06, - "loss": 0.5542, + "epoch": 1.17, + "learning_rate": 7.747054854604012e-06, + "loss": 0.6179, "step": 2569 }, { - "epoch": 1.32, - "learning_rate": 5.456015042151563e-06, - "loss": 0.5929, + "epoch": 1.17, + "learning_rate": 7.739867059523872e-06, + "loss": 0.6168, "step": 2570 }, { - "epoch": 1.32, - "learning_rate": 5.4485993743797175e-06, - "loss": 0.5826, + "epoch": 1.17, + "learning_rate": 7.73268049477594e-06, + "loss": 0.6382, "step": 2571 }, { - "epoch": 1.32, - "learning_rate": 5.441186862129592e-06, - "loss": 0.5939, + "epoch": 1.17, + "learning_rate": 7.725495164272327e-06, + "loss": 0.6182, "step": 2572 }, { - "epoch": 1.32, - "learning_rate": 5.433777510540352e-06, - "loss": 0.6167, + "epoch": 1.17, + "learning_rate": 7.718311071924456e-06, + "loss": 0.6328, "step": 2573 }, { - "epoch": 1.32, - "learning_rate": 5.4263713247489525e-06, - "loss": 0.5605, + "epoch": 1.17, + "learning_rate": 7.71112822164308e-06, + "loss": 0.6503, "step": 2574 }, { - "epoch": 1.32, - "learning_rate": 5.41896830989016e-06, - "loss": 0.6152, + "epoch": 1.17, + "learning_rate": 7.703946617338273e-06, + "loss": 0.603, "step": 2575 }, { - "epoch": 1.32, - "learning_rate": 5.4115684710965445e-06, - "loss": 0.5797, + "epoch": 1.17, + "learning_rate": 7.696766262919436e-06, + "loss": 0.5913, "step": 2576 }, { - "epoch": 1.32, - "learning_rate": 5.404171813498471e-06, - "loss": 0.5713, + "epoch": 1.17, + "learning_rate": 7.689587162295281e-06, + "loss": 0.6121, "step": 2577 }, { - "epoch": 1.33, - "learning_rate": 5.396778342224096e-06, - "loss": 0.5671, + "epoch": 1.17, + "learning_rate": 7.682409319373851e-06, + "loss": 0.611, "step": 2578 }, { - "epoch": 1.33, - "learning_rate": 5.389388062399379e-06, - "loss": 0.599, + "epoch": 1.17, + "learning_rate": 7.67523273806249e-06, + "loss": 0.6145, "step": 2579 }, { - "epoch": 1.33, - "learning_rate": 5.382000979148057e-06, - "loss": 0.5811, + "epoch": 1.18, + "learning_rate": 7.668057422267867e-06, + "loss": 0.6196, "step": 2580 }, { - "epoch": 1.33, - "learning_rate": 5.37461709759165e-06, - "loss": 0.6204, + "epoch": 1.18, + "learning_rate": 7.660883375895953e-06, + "loss": 0.6156, "step": 2581 }, { - "epoch": 1.33, - "learning_rate": 5.367236422849457e-06, - "loss": 0.5782, + "epoch": 1.18, + "learning_rate": 7.653710602852032e-06, + "loss": 0.5984, "step": 2582 }, { - "epoch": 1.33, - "learning_rate": 5.359858960038568e-06, - "loss": 0.6313, + "epoch": 1.18, + "learning_rate": 7.646539107040692e-06, + "loss": 0.5599, "step": 2583 }, { - "epoch": 1.33, - "learning_rate": 5.352484714273832e-06, - "loss": 0.551, + "epoch": 1.18, + "learning_rate": 7.639368892365838e-06, + "loss": 0.6951, "step": 2584 }, { - "epoch": 1.33, - "learning_rate": 5.345113690667867e-06, - "loss": 0.5422, + "epoch": 1.18, + "learning_rate": 7.632199962730655e-06, + "loss": 0.6013, "step": 2585 }, { - "epoch": 1.33, - "learning_rate": 5.337745894331066e-06, - "loss": 0.6301, + "epoch": 1.18, + "learning_rate": 7.625032322037652e-06, + "loss": 0.6394, "step": 2586 }, { - "epoch": 1.33, - "learning_rate": 5.330381330371577e-06, - "loss": 0.5731, + "epoch": 1.18, + "learning_rate": 7.617865974188618e-06, + "loss": 0.6531, "step": 2587 }, { - "epoch": 1.33, - "learning_rate": 5.323020003895307e-06, - "loss": 0.5913, + "epoch": 1.18, + "learning_rate": 7.610700923084653e-06, + "loss": 0.6829, "step": 2588 }, { - "epoch": 1.33, - "learning_rate": 5.31566192000593e-06, - "loss": 0.6274, + "epoch": 1.18, + "learning_rate": 7.6035371726261385e-06, + "loss": 0.6448, "step": 2589 }, { - "epoch": 1.33, - "learning_rate": 5.30830708380486e-06, - "loss": 0.5681, + "epoch": 1.18, + "learning_rate": 7.596374726712756e-06, + "loss": 0.6171, "step": 2590 }, { - "epoch": 1.33, - "learning_rate": 5.30095550039126e-06, - "loss": 0.588, + "epoch": 1.18, + "learning_rate": 7.589213589243471e-06, + "loss": 0.6396, "step": 2591 }, { - "epoch": 1.33, - "learning_rate": 5.2936071748620386e-06, - "loss": 0.5759, + "epoch": 1.18, + "learning_rate": 7.582053764116546e-06, + "loss": 0.6404, "step": 2592 }, { - "epoch": 1.33, - "learning_rate": 5.286262112311854e-06, - "loss": 0.5931, + "epoch": 1.18, + "learning_rate": 7.574895255229518e-06, + "loss": 0.619, "step": 2593 }, { - "epoch": 1.33, - "learning_rate": 5.278920317833092e-06, - "loss": 0.6252, + "epoch": 1.18, + "learning_rate": 7.5677380664792176e-06, + "loss": 0.5778, "step": 2594 }, { - "epoch": 1.33, - "learning_rate": 5.271581796515877e-06, - "loss": 0.571, + "epoch": 1.18, + "learning_rate": 7.560582201761746e-06, + "loss": 0.616, "step": 2595 }, { - "epoch": 1.33, - "learning_rate": 5.264246553448063e-06, - "loss": 0.5793, + "epoch": 1.18, + "learning_rate": 7.5534276649724946e-06, + "loss": 0.624, "step": 2596 }, { - "epoch": 1.33, - "learning_rate": 5.256914593715231e-06, - "loss": 0.5974, + "epoch": 1.18, + "learning_rate": 7.546274460006121e-06, + "loss": 0.6193, "step": 2597 }, { - "epoch": 1.34, - "learning_rate": 5.249585922400681e-06, - "loss": 0.5856, + "epoch": 1.18, + "learning_rate": 7.539122590756574e-06, + "loss": 0.5857, "step": 2598 }, { - "epoch": 1.34, - "learning_rate": 5.242260544585451e-06, - "loss": 0.5878, + "epoch": 1.18, + "learning_rate": 7.531972061117051e-06, + "loss": 0.6011, "step": 2599 }, { - "epoch": 1.34, - "learning_rate": 5.234938465348273e-06, - "loss": 0.5262, + "epoch": 1.18, + "learning_rate": 7.524822874980044e-06, + "loss": 0.6156, "step": 2600 }, { - "epoch": 1.34, - "learning_rate": 5.227619689765606e-06, - "loss": 0.5913, + "epoch": 1.18, + "learning_rate": 7.5176750362373044e-06, + "loss": 0.6395, "step": 2601 }, { - "epoch": 1.34, - "learning_rate": 5.22030422291161e-06, - "loss": 0.6207, + "epoch": 1.19, + "learning_rate": 7.51052854877984e-06, + "loss": 0.6338, "step": 2602 }, { - "epoch": 1.34, - "learning_rate": 5.21299206985816e-06, - "loss": 0.6028, + "epoch": 1.19, + "learning_rate": 7.503383416497946e-06, + "loss": 0.6077, "step": 2603 }, { - "epoch": 1.34, - "learning_rate": 5.205683235674829e-06, - "loss": 0.5941, + "epoch": 1.19, + "learning_rate": 7.496239643281152e-06, + "loss": 0.6339, "step": 2604 }, { - "epoch": 1.34, - "learning_rate": 5.198377725428887e-06, - "loss": 0.6331, + "epoch": 1.19, + "learning_rate": 7.4890972330182735e-06, + "loss": 0.6111, "step": 2605 }, { - "epoch": 1.34, - "learning_rate": 5.191075544185302e-06, - "loss": 0.5757, + "epoch": 1.19, + "learning_rate": 7.481956189597366e-06, + "loss": 0.6373, "step": 2606 }, { - "epoch": 1.34, - "learning_rate": 5.183776697006735e-06, - "loss": 0.5787, + "epoch": 1.19, + "learning_rate": 7.474816516905753e-06, + "loss": 0.6207, "step": 2607 }, { - "epoch": 1.34, - "learning_rate": 5.176481188953527e-06, - "loss": 0.6077, + "epoch": 1.19, + "learning_rate": 7.467678218829999e-06, + "loss": 0.5635, "step": 2608 }, { - "epoch": 1.34, - "learning_rate": 5.169189025083721e-06, - "loss": 0.5688, + "epoch": 1.19, + "learning_rate": 7.460541299255938e-06, + "loss": 0.6122, "step": 2609 }, { - "epoch": 1.34, - "learning_rate": 5.161900210453026e-06, - "loss": 0.5554, + "epoch": 1.19, + "learning_rate": 7.453405762068631e-06, + "loss": 0.6282, "step": 2610 }, { - "epoch": 1.34, - "learning_rate": 5.154614750114832e-06, - "loss": 0.6273, + "epoch": 1.19, + "learning_rate": 7.446271611152409e-06, + "loss": 0.6451, "step": 2611 }, { - "epoch": 1.34, - "learning_rate": 5.1473326491202135e-06, - "loss": 0.562, + "epoch": 1.19, + "learning_rate": 7.4391388503908335e-06, + "loss": 0.6202, "step": 2612 }, { - "epoch": 1.34, - "learning_rate": 5.140053912517903e-06, - "loss": 0.6304, + "epoch": 1.19, + "learning_rate": 7.432007483666717e-06, + "loss": 0.6281, "step": 2613 }, { - "epoch": 1.34, - "learning_rate": 5.132778545354305e-06, - "loss": 0.5956, + "epoch": 1.19, + "learning_rate": 7.424877514862104e-06, + "loss": 0.592, "step": 2614 }, { - "epoch": 1.34, - "learning_rate": 5.1255065526734915e-06, - "loss": 0.6179, + "epoch": 1.19, + "learning_rate": 7.41774894785829e-06, + "loss": 0.5887, "step": 2615 }, { - "epoch": 1.34, - "learning_rate": 5.11823793951719e-06, - "loss": 0.613, + "epoch": 1.19, + "learning_rate": 7.410621786535796e-06, + "loss": 0.6484, "step": 2616 }, { - "epoch": 1.35, - "learning_rate": 5.1109727109247865e-06, - "loss": 0.5581, + "epoch": 1.19, + "learning_rate": 7.403496034774389e-06, + "loss": 0.5778, "step": 2617 }, { - "epoch": 1.35, - "learning_rate": 5.103710871933319e-06, - "loss": 0.6204, + "epoch": 1.19, + "learning_rate": 7.39637169645306e-06, + "loss": 0.6245, "step": 2618 }, { - "epoch": 1.35, - "learning_rate": 5.096452427577483e-06, - "loss": 0.5776, + "epoch": 1.19, + "learning_rate": 7.3892487754500345e-06, + "loss": 0.601, "step": 2619 }, { - "epoch": 1.35, - "learning_rate": 5.089197382889613e-06, - "loss": 0.5909, + "epoch": 1.19, + "learning_rate": 7.382127275642763e-06, + "loss": 0.6074, "step": 2620 }, { - "epoch": 1.35, - "learning_rate": 5.081945742899681e-06, - "loss": 0.595, + "epoch": 1.19, + "learning_rate": 7.375007200907929e-06, + "loss": 0.6136, "step": 2621 }, { - "epoch": 1.35, - "learning_rate": 5.074697512635318e-06, - "loss": 0.5889, + "epoch": 1.19, + "learning_rate": 7.367888555121429e-06, + "loss": 0.6005, "step": 2622 }, { - "epoch": 1.35, - "learning_rate": 5.067452697121773e-06, - "loss": 0.5691, + "epoch": 1.19, + "learning_rate": 7.3607713421584014e-06, + "loss": 0.5887, "step": 2623 }, { - "epoch": 1.35, - "learning_rate": 5.060211301381932e-06, - "loss": 0.6233, + "epoch": 1.2, + "learning_rate": 7.353655565893176e-06, + "loss": 0.5626, "step": 2624 }, { - "epoch": 1.35, - "learning_rate": 5.0529733304363145e-06, - "loss": 0.5879, + "epoch": 1.2, + "learning_rate": 7.346541230199329e-06, + "loss": 0.6084, "step": 2625 }, { - "epoch": 1.35, - "learning_rate": 5.045738789303061e-06, - "loss": 0.5996, + "epoch": 1.2, + "learning_rate": 7.339428338949632e-06, + "loss": 0.6174, "step": 2626 }, { - "epoch": 1.35, - "learning_rate": 5.038507682997934e-06, - "loss": 0.5714, + "epoch": 1.2, + "learning_rate": 7.332316896016085e-06, + "loss": 0.6237, "step": 2627 }, { - "epoch": 1.35, - "learning_rate": 5.031280016534314e-06, - "loss": 0.6029, + "epoch": 1.2, + "learning_rate": 7.325206905269888e-06, + "loss": 0.6118, "step": 2628 }, { - "epoch": 1.35, - "learning_rate": 5.024055794923206e-06, - "loss": 0.5818, + "epoch": 1.2, + "learning_rate": 7.318098370581457e-06, + "loss": 0.6145, "step": 2629 }, { - "epoch": 1.35, - "learning_rate": 5.016835023173216e-06, - "loss": 0.6353, + "epoch": 1.2, + "learning_rate": 7.310991295820408e-06, + "loss": 0.5754, "step": 2630 }, { - "epoch": 1.35, - "learning_rate": 5.0096177062905585e-06, - "loss": 0.6074, + "epoch": 1.2, + "learning_rate": 7.3038856848555785e-06, + "loss": 0.5651, "step": 2631 }, { - "epoch": 1.35, - "learning_rate": 5.002403849279063e-06, - "loss": 0.5946, + "epoch": 1.2, + "learning_rate": 7.2967815415549896e-06, + "loss": 0.6072, "step": 2632 }, { - "epoch": 1.35, - "learning_rate": 4.995193457140147e-06, - "loss": 0.5515, + "epoch": 1.2, + "learning_rate": 7.2896788697858765e-06, + "loss": 0.6252, "step": 2633 }, { - "epoch": 1.35, - "learning_rate": 4.987986534872835e-06, - "loss": 0.5964, + "epoch": 1.2, + "learning_rate": 7.28257767341467e-06, + "loss": 0.5942, "step": 2634 }, { - "epoch": 1.35, - "learning_rate": 4.98078308747374e-06, - "loss": 0.6185, + "epoch": 1.2, + "learning_rate": 7.275477956306991e-06, + "loss": 0.6218, "step": 2635 }, { - "epoch": 1.35, - "learning_rate": 4.973583119937072e-06, - "loss": 0.598, + "epoch": 1.2, + "learning_rate": 7.26837972232767e-06, + "loss": 0.6556, "step": 2636 }, { - "epoch": 1.36, - "learning_rate": 4.966386637254619e-06, - "loss": 0.5883, + "epoch": 1.2, + "learning_rate": 7.261282975340716e-06, + "loss": 0.6249, "step": 2637 }, { - "epoch": 1.36, - "learning_rate": 4.959193644415766e-06, - "loss": 0.5833, + "epoch": 1.2, + "learning_rate": 7.254187719209333e-06, + "loss": 0.5808, "step": 2638 }, { - "epoch": 1.36, - "learning_rate": 4.9520041464074675e-06, - "loss": 0.5758, + "epoch": 1.2, + "learning_rate": 7.247093957795917e-06, + "loss": 0.6195, "step": 2639 }, { - "epoch": 1.36, - "learning_rate": 4.944818148214261e-06, - "loss": 0.5973, + "epoch": 1.2, + "learning_rate": 7.240001694962048e-06, + "loss": 0.653, "step": 2640 }, { - "epoch": 1.36, - "learning_rate": 4.937635654818249e-06, - "loss": 0.6239, + "epoch": 1.2, + "learning_rate": 7.2329109345684835e-06, + "loss": 0.6229, "step": 2641 }, { - "epoch": 1.36, - "learning_rate": 4.9304566711991185e-06, - "loss": 0.587, + "epoch": 1.2, + "learning_rate": 7.22582168047518e-06, + "loss": 0.6055, "step": 2642 }, { - "epoch": 1.36, - "learning_rate": 4.923281202334114e-06, - "loss": 0.554, + "epoch": 1.2, + "learning_rate": 7.218733936541253e-06, + "loss": 0.6465, "step": 2643 }, { - "epoch": 1.36, - "learning_rate": 4.91610925319804e-06, - "loss": 0.5569, + "epoch": 1.2, + "learning_rate": 7.2116477066250135e-06, + "loss": 0.6475, "step": 2644 }, { - "epoch": 1.36, - "learning_rate": 4.908940828763269e-06, - "loss": 0.5853, + "epoch": 1.21, + "learning_rate": 7.204562994583937e-06, + "loss": 0.6189, "step": 2645 }, { - "epoch": 1.36, - "learning_rate": 4.9017759339997226e-06, - "loss": 0.5803, + "epoch": 1.21, + "learning_rate": 7.197479804274681e-06, + "loss": 0.6324, "step": 2646 }, { - "epoch": 1.36, - "learning_rate": 4.894614573874877e-06, - "loss": 0.5803, + "epoch": 1.21, + "learning_rate": 7.190398139553067e-06, + "loss": 0.5872, "step": 2647 }, { - "epoch": 1.36, - "learning_rate": 4.887456753353766e-06, - "loss": 0.5939, + "epoch": 1.21, + "learning_rate": 7.183318004274091e-06, + "loss": 0.5979, "step": 2648 }, { - "epoch": 1.36, - "learning_rate": 4.880302477398959e-06, - "loss": 0.6111, + "epoch": 1.21, + "learning_rate": 7.1762394022919125e-06, + "loss": 0.6534, "step": 2649 }, { - "epoch": 1.36, - "learning_rate": 4.873151750970572e-06, - "loss": 0.6165, + "epoch": 1.21, + "learning_rate": 7.169162337459865e-06, + "loss": 0.5986, "step": 2650 }, { - "epoch": 1.36, - "learning_rate": 4.866004579026254e-06, - "loss": 0.6007, + "epoch": 1.21, + "learning_rate": 7.162086813630432e-06, + "loss": 0.6262, "step": 2651 }, { - "epoch": 1.36, - "learning_rate": 4.858860966521206e-06, - "loss": 0.6116, + "epoch": 1.21, + "learning_rate": 7.155012834655271e-06, + "loss": 0.6086, "step": 2652 }, { - "epoch": 1.36, - "learning_rate": 4.851720918408144e-06, - "loss": 0.5906, + "epoch": 1.21, + "learning_rate": 7.147940404385189e-06, + "loss": 0.5768, "step": 2653 }, { - "epoch": 1.36, - "learning_rate": 4.844584439637321e-06, - "loss": 0.5638, + "epoch": 1.21, + "learning_rate": 7.140869526670157e-06, + "loss": 0.6423, "step": 2654 }, { - "epoch": 1.36, - "learning_rate": 4.837451535156513e-06, - "loss": 0.567, + "epoch": 1.21, + "learning_rate": 7.13380020535929e-06, + "loss": 0.5807, "step": 2655 }, { - "epoch": 1.37, - "learning_rate": 4.830322209911018e-06, - "loss": 0.6099, + "epoch": 1.21, + "learning_rate": 7.1267324443008765e-06, + "loss": 0.6002, "step": 2656 }, { - "epoch": 1.37, - "learning_rate": 4.823196468843651e-06, - "loss": 0.6248, + "epoch": 1.21, + "learning_rate": 7.119666247342327e-06, + "loss": 0.5942, "step": 2657 }, { - "epoch": 1.37, - "learning_rate": 4.81607431689475e-06, - "loss": 0.5942, + "epoch": 1.21, + "learning_rate": 7.112601618330229e-06, + "loss": 0.6133, "step": 2658 }, { - "epoch": 1.37, - "learning_rate": 4.808955759002156e-06, - "loss": 0.5933, + "epoch": 1.21, + "learning_rate": 7.105538561110297e-06, + "loss": 0.6201, "step": 2659 }, { - "epoch": 1.37, - "learning_rate": 4.8018408001012205e-06, - "loss": 0.6207, + "epoch": 1.21, + "learning_rate": 7.0984770795273986e-06, + "loss": 0.583, "step": 2660 }, { - "epoch": 1.37, - "learning_rate": 4.794729445124798e-06, - "loss": 0.5641, + "epoch": 1.21, + "learning_rate": 7.091417177425537e-06, + "loss": 0.6769, "step": 2661 }, { - "epoch": 1.37, - "learning_rate": 4.78762169900325e-06, + "epoch": 1.21, + "learning_rate": 7.084358858647868e-06, "loss": 0.6266, "step": 2662 }, { - "epoch": 1.37, - "learning_rate": 4.780517566664434e-06, - "loss": 0.5714, + "epoch": 1.21, + "learning_rate": 7.077302127036667e-06, + "loss": 0.6051, "step": 2663 }, { - "epoch": 1.37, - "learning_rate": 4.7734170530336965e-06, - "loss": 0.5808, + "epoch": 1.21, + "learning_rate": 7.070246986433367e-06, + "loss": 0.6716, "step": 2664 }, { - "epoch": 1.37, - "learning_rate": 4.766320163033882e-06, - "loss": 0.5739, + "epoch": 1.21, + "learning_rate": 7.063193440678516e-06, + "loss": 0.621, "step": 2665 }, { - "epoch": 1.37, - "learning_rate": 4.7592269015853186e-06, - "loss": 0.6276, + "epoch": 1.21, + "learning_rate": 7.056141493611807e-06, + "loss": 0.6765, "step": 2666 }, { - "epoch": 1.37, - "learning_rate": 4.752137273605817e-06, - "loss": 0.5928, + "epoch": 1.22, + "learning_rate": 7.049091149072054e-06, + "loss": 0.6089, "step": 2667 }, { - "epoch": 1.37, - "learning_rate": 4.745051284010679e-06, - "loss": 0.5735, + "epoch": 1.22, + "learning_rate": 7.0420424108971985e-06, + "loss": 0.6226, "step": 2668 }, { - "epoch": 1.37, - "learning_rate": 4.737968937712674e-06, - "loss": 0.5781, + "epoch": 1.22, + "learning_rate": 7.034995282924322e-06, + "loss": 0.6376, "step": 2669 }, { - "epoch": 1.37, - "learning_rate": 4.7308902396220455e-06, - "loss": 0.5406, + "epoch": 1.22, + "learning_rate": 7.027949768989608e-06, + "loss": 0.6465, "step": 2670 }, { - "epoch": 1.37, - "learning_rate": 4.723815194646508e-06, - "loss": 0.6079, + "epoch": 1.22, + "learning_rate": 7.020905872928379e-06, + "loss": 0.637, "step": 2671 }, { - "epoch": 1.37, - "learning_rate": 4.716743807691255e-06, - "loss": 0.5983, + "epoch": 1.22, + "learning_rate": 7.0138635985750636e-06, + "loss": 0.5525, "step": 2672 }, { - "epoch": 1.37, - "learning_rate": 4.7096760836589295e-06, - "loss": 0.5742, + "epoch": 1.22, + "learning_rate": 7.00682294976322e-06, + "loss": 0.5703, "step": 2673 }, { - "epoch": 1.37, - "learning_rate": 4.7026120274496375e-06, - "loss": 0.5725, + "epoch": 1.22, + "learning_rate": 6.999783930325507e-06, + "loss": 0.6545, "step": 2674 }, { - "epoch": 1.37, - "learning_rate": 4.695551643960949e-06, - "loss": 0.6086, + "epoch": 1.22, + "learning_rate": 6.992746544093716e-06, + "loss": 0.6208, "step": 2675 }, { - "epoch": 1.38, - "learning_rate": 4.68849493808788e-06, - "loss": 0.5825, + "epoch": 1.22, + "learning_rate": 6.985710794898728e-06, + "loss": 0.6044, "step": 2676 }, { - "epoch": 1.38, - "learning_rate": 4.681441914722898e-06, - "loss": 0.5829, + "epoch": 1.22, + "learning_rate": 6.9786766865705505e-06, + "loss": 0.6156, "step": 2677 }, { - "epoch": 1.38, - "learning_rate": 4.674392578755924e-06, - "loss": 0.5985, + "epoch": 1.22, + "learning_rate": 6.971644222938283e-06, + "loss": 0.6271, "step": 2678 }, { - "epoch": 1.38, - "learning_rate": 4.667346935074317e-06, - "loss": 0.5997, + "epoch": 1.22, + "learning_rate": 6.964613407830143e-06, + "loss": 0.6293, "step": 2679 }, { - "epoch": 1.38, - "learning_rate": 4.660304988562877e-06, - "loss": 0.5682, + "epoch": 1.22, + "learning_rate": 6.9575842450734365e-06, + "loss": 0.6036, "step": 2680 }, { - "epoch": 1.38, - "learning_rate": 4.653266744103836e-06, - "loss": 0.5918, + "epoch": 1.22, + "learning_rate": 6.95055673849459e-06, + "loss": 0.6278, "step": 2681 }, { - "epoch": 1.38, - "learning_rate": 4.646232206576871e-06, - "loss": 0.5967, + "epoch": 1.22, + "learning_rate": 6.943530891919104e-06, + "loss": 0.6353, "step": 2682 }, { - "epoch": 1.38, - "learning_rate": 4.639201380859079e-06, - "loss": 0.6272, + "epoch": 1.22, + "learning_rate": 6.936506709171596e-06, + "loss": 0.6223, "step": 2683 }, { - "epoch": 1.38, - "learning_rate": 4.632174271824987e-06, - "loss": 0.5887, + "epoch": 1.22, + "learning_rate": 6.929484194075767e-06, + "loss": 0.5944, "step": 2684 }, { - "epoch": 1.38, - "learning_rate": 4.625150884346544e-06, - "loss": 0.5839, + "epoch": 1.22, + "learning_rate": 6.922463350454413e-06, + "loss": 0.6233, "step": 2685 }, { - "epoch": 1.38, - "learning_rate": 4.618131223293119e-06, - "loss": 0.5709, + "epoch": 1.22, + "learning_rate": 6.9154441821294184e-06, + "loss": 0.6161, "step": 2686 }, { - "epoch": 1.38, - "learning_rate": 4.611115293531497e-06, - "loss": 0.6053, + "epoch": 1.22, + "learning_rate": 6.9084266929217595e-06, + "loss": 0.5618, "step": 2687 }, { - "epoch": 1.38, - "learning_rate": 4.6041030999258816e-06, - "loss": 0.5978, + "epoch": 1.22, + "learning_rate": 6.901410886651491e-06, + "loss": 0.6136, "step": 2688 }, { - "epoch": 1.38, - "learning_rate": 4.597094647337878e-06, - "loss": 0.5803, + "epoch": 1.23, + "learning_rate": 6.894396767137764e-06, + "loss": 0.6377, "step": 2689 }, { - "epoch": 1.38, - "learning_rate": 4.590089940626501e-06, - "loss": 0.6173, + "epoch": 1.23, + "learning_rate": 6.8873843381987995e-06, + "loss": 0.5867, "step": 2690 }, { - "epoch": 1.38, - "learning_rate": 4.583088984648172e-06, - "loss": 0.5923, + "epoch": 1.23, + "learning_rate": 6.880373603651904e-06, + "loss": 0.6233, "step": 2691 }, { - "epoch": 1.38, - "learning_rate": 4.576091784256707e-06, - "loss": 0.623, + "epoch": 1.23, + "learning_rate": 6.87336456731346e-06, + "loss": 0.632, "step": 2692 }, { - "epoch": 1.38, - "learning_rate": 4.569098344303319e-06, - "loss": 0.583, + "epoch": 1.23, + "learning_rate": 6.866357232998926e-06, + "loss": 0.6245, "step": 2693 }, { - "epoch": 1.38, - "learning_rate": 4.5621086696366155e-06, - "loss": 0.578, + "epoch": 1.23, + "learning_rate": 6.85935160452283e-06, + "loss": 0.6132, "step": 2694 }, { - "epoch": 1.39, - "learning_rate": 4.555122765102592e-06, - "loss": 0.5464, + "epoch": 1.23, + "learning_rate": 6.852347685698787e-06, + "loss": 0.5972, "step": 2695 }, { - "epoch": 1.39, - "learning_rate": 4.548140635544632e-06, - "loss": 0.5754, + "epoch": 1.23, + "learning_rate": 6.845345480339454e-06, + "loss": 0.6047, "step": 2696 }, { - "epoch": 1.39, - "learning_rate": 4.541162285803496e-06, - "loss": 0.553, + "epoch": 1.23, + "learning_rate": 6.838344992256582e-06, + "loss": 0.5691, "step": 2697 }, { - "epoch": 1.39, - "learning_rate": 4.534187720717335e-06, - "loss": 0.573, + "epoch": 1.23, + "learning_rate": 6.831346225260972e-06, + "loss": 0.5922, "step": 2698 }, { - "epoch": 1.39, - "learning_rate": 4.52721694512167e-06, - "loss": 0.5995, + "epoch": 1.23, + "learning_rate": 6.824349183162494e-06, + "loss": 0.6193, "step": 2699 }, { - "epoch": 1.39, - "learning_rate": 4.520249963849386e-06, - "loss": 0.5746, + "epoch": 1.23, + "learning_rate": 6.817353869770074e-06, + "loss": 0.6107, "step": 2700 }, { - "epoch": 1.39, - "learning_rate": 4.513286781730755e-06, - "loss": 0.5977, + "epoch": 1.23, + "learning_rate": 6.8103602888916995e-06, + "loss": 0.5983, "step": 2701 }, { - "epoch": 1.39, - "learning_rate": 4.5063274035934016e-06, - "loss": 0.5245, + "epoch": 1.23, + "learning_rate": 6.803368444334424e-06, + "loss": 0.605, "step": 2702 }, { - "epoch": 1.39, - "learning_rate": 4.499371834262317e-06, - "loss": 0.5757, + "epoch": 1.23, + "learning_rate": 6.796378339904337e-06, + "loss": 0.6259, "step": 2703 }, { - "epoch": 1.39, - "learning_rate": 4.492420078559854e-06, - "loss": 0.6036, + "epoch": 1.23, + "learning_rate": 6.789389979406599e-06, + "loss": 0.5907, "step": 2704 }, { - "epoch": 1.39, - "learning_rate": 4.485472141305718e-06, - "loss": 0.621, + "epoch": 1.23, + "learning_rate": 6.782403366645407e-06, + "loss": 0.6061, "step": 2705 }, { - "epoch": 1.39, - "learning_rate": 4.478528027316967e-06, - "loss": 0.5811, + "epoch": 1.23, + "learning_rate": 6.775418505424019e-06, + "loss": 0.6434, "step": 2706 }, { - "epoch": 1.39, - "learning_rate": 4.471587741408008e-06, - "loss": 0.5612, + "epoch": 1.23, + "learning_rate": 6.768435399544724e-06, + "loss": 0.6085, "step": 2707 }, { - "epoch": 1.39, - "learning_rate": 4.464651288390601e-06, - "loss": 0.5342, + "epoch": 1.23, + "learning_rate": 6.761454052808876e-06, + "loss": 0.6536, "step": 2708 }, { - "epoch": 1.39, - "learning_rate": 4.457718673073842e-06, - "loss": 0.5392, + "epoch": 1.23, + "learning_rate": 6.754474469016852e-06, + "loss": 0.6462, "step": 2709 }, { - "epoch": 1.39, - "learning_rate": 4.450789900264162e-06, - "loss": 0.5918, + "epoch": 1.23, + "learning_rate": 6.747496651968082e-06, + "loss": 0.5967, "step": 2710 }, { - "epoch": 1.39, - "learning_rate": 4.443864974765341e-06, - "loss": 0.5873, + "epoch": 1.24, + "learning_rate": 6.7405206054610275e-06, + "loss": 0.5524, "step": 2711 }, { - "epoch": 1.39, - "learning_rate": 4.436943901378481e-06, - "loss": 0.6016, + "epoch": 1.24, + "learning_rate": 6.733546333293191e-06, + "loss": 0.5925, "step": 2712 }, { - "epoch": 1.39, - "learning_rate": 4.430026684902017e-06, - "loss": 0.5201, + "epoch": 1.24, + "learning_rate": 6.726573839261101e-06, + "loss": 0.608, "step": 2713 }, { - "epoch": 1.4, - "learning_rate": 4.423113330131708e-06, - "loss": 0.6057, + "epoch": 1.24, + "learning_rate": 6.719603127160335e-06, + "loss": 0.5514, "step": 2714 }, { - "epoch": 1.4, - "learning_rate": 4.416203841860638e-06, - "loss": 0.5651, + "epoch": 1.24, + "learning_rate": 6.712634200785473e-06, + "loss": 0.6312, "step": 2715 }, { - "epoch": 1.4, - "learning_rate": 4.409298224879208e-06, - "loss": 0.5549, + "epoch": 1.24, + "learning_rate": 6.705667063930153e-06, + "loss": 0.5837, "step": 2716 }, { - "epoch": 1.4, - "learning_rate": 4.402396483975135e-06, - "loss": 0.571, + "epoch": 1.24, + "learning_rate": 6.698701720387017e-06, + "loss": 0.6442, "step": 2717 }, { - "epoch": 1.4, - "learning_rate": 4.395498623933456e-06, - "loss": 0.5756, + "epoch": 1.24, + "learning_rate": 6.691738173947744e-06, + "loss": 0.6211, "step": 2718 }, { - "epoch": 1.4, - "learning_rate": 4.388604649536507e-06, - "loss": 0.5598, + "epoch": 1.24, + "learning_rate": 6.684776428403024e-06, + "loss": 0.6584, "step": 2719 }, { - "epoch": 1.4, - "learning_rate": 4.3817145655639335e-06, - "loss": 0.5702, + "epoch": 1.24, + "learning_rate": 6.6778164875425755e-06, + "loss": 0.5612, "step": 2720 }, { - "epoch": 1.4, - "learning_rate": 4.3748283767926895e-06, - "loss": 0.6047, + "epoch": 1.24, + "learning_rate": 6.670858355155128e-06, + "loss": 0.5483, "step": 2721 }, { - "epoch": 1.4, - "learning_rate": 4.3679460879970214e-06, - "loss": 0.5881, + "epoch": 1.24, + "learning_rate": 6.663902035028435e-06, + "loss": 0.6194, "step": 2722 }, { - "epoch": 1.4, - "learning_rate": 4.361067703948473e-06, - "loss": 0.6067, + "epoch": 1.24, + "learning_rate": 6.656947530949254e-06, + "loss": 0.6156, "step": 2723 }, { - "epoch": 1.4, - "learning_rate": 4.354193229415882e-06, - "loss": 0.6221, + "epoch": 1.24, + "learning_rate": 6.64999484670336e-06, + "loss": 0.6061, "step": 2724 }, { - "epoch": 1.4, - "learning_rate": 4.3473226691653745e-06, - "loss": 0.5636, + "epoch": 1.24, + "learning_rate": 6.643043986075532e-06, + "loss": 0.5664, "step": 2725 }, { - "epoch": 1.4, - "learning_rate": 4.340456027960367e-06, - "loss": 0.5867, + "epoch": 1.24, + "learning_rate": 6.636094952849567e-06, + "loss": 0.6138, "step": 2726 }, { - "epoch": 1.4, - "learning_rate": 4.333593310561549e-06, - "loss": 0.5591, + "epoch": 1.24, + "learning_rate": 6.629147750808249e-06, + "loss": 0.593, "step": 2727 }, { - "epoch": 1.4, - "learning_rate": 4.326734521726905e-06, - "loss": 0.5793, + "epoch": 1.24, + "learning_rate": 6.62220238373339e-06, + "loss": 0.5652, "step": 2728 }, { - "epoch": 1.4, - "learning_rate": 4.3198796662116825e-06, - "loss": 0.5701, + "epoch": 1.24, + "learning_rate": 6.615258855405775e-06, + "loss": 0.6182, "step": 2729 }, { - "epoch": 1.4, - "learning_rate": 4.313028748768404e-06, - "loss": 0.6038, + "epoch": 1.24, + "learning_rate": 6.6083171696052125e-06, + "loss": 0.6334, "step": 2730 }, { - "epoch": 1.4, - "learning_rate": 4.306181774146872e-06, - "loss": 0.5911, + "epoch": 1.24, + "learning_rate": 6.601377330110492e-06, + "loss": 0.6343, "step": 2731 }, { - "epoch": 1.4, - "learning_rate": 4.299338747094141e-06, - "loss": 0.5946, + "epoch": 1.24, + "learning_rate": 6.59443934069941e-06, + "loss": 0.6077, "step": 2732 }, { - "epoch": 1.4, - "learning_rate": 4.292499672354538e-06, - "loss": 0.5696, + "epoch": 1.25, + "learning_rate": 6.5875032051487395e-06, + "loss": 0.5343, "step": 2733 }, { - "epoch": 1.41, - "learning_rate": 4.285664554669646e-06, - "loss": 0.5978, + "epoch": 1.25, + "learning_rate": 6.580568927234266e-06, + "loss": 0.6385, "step": 2734 }, { - "epoch": 1.41, - "learning_rate": 4.278833398778306e-06, - "loss": 0.6161, + "epoch": 1.25, + "learning_rate": 6.573636510730742e-06, + "loss": 0.6298, "step": 2735 }, { - "epoch": 1.41, - "learning_rate": 4.27200620941661e-06, - "loss": 0.5688, + "epoch": 1.25, + "learning_rate": 6.566705959411923e-06, + "loss": 0.63, "step": 2736 }, { - "epoch": 1.41, - "learning_rate": 4.265182991317904e-06, - "loss": 0.5623, + "epoch": 1.25, + "learning_rate": 6.559777277050543e-06, + "loss": 0.5618, "step": 2737 }, { - "epoch": 1.41, - "learning_rate": 4.258363749212782e-06, - "loss": 0.6129, + "epoch": 1.25, + "learning_rate": 6.552850467418314e-06, + "loss": 0.6525, "step": 2738 }, { - "epoch": 1.41, - "learning_rate": 4.2515484878290726e-06, - "loss": 0.6177, + "epoch": 1.25, + "learning_rate": 6.545925534285943e-06, + "loss": 0.6189, "step": 2739 }, { - "epoch": 1.41, - "learning_rate": 4.244737211891848e-06, - "loss": 0.6035, + "epoch": 1.25, + "learning_rate": 6.5390024814230925e-06, + "loss": 0.5895, "step": 2740 }, { - "epoch": 1.41, - "learning_rate": 4.237929926123427e-06, - "loss": 0.5696, + "epoch": 1.25, + "learning_rate": 6.532081312598426e-06, + "loss": 0.6024, "step": 2741 }, { - "epoch": 1.41, - "learning_rate": 4.231126635243351e-06, - "loss": 0.5948, + "epoch": 1.25, + "learning_rate": 6.5251620315795635e-06, + "loss": 0.5903, "step": 2742 }, { - "epoch": 1.41, - "learning_rate": 4.2243273439683926e-06, - "loss": 0.6074, + "epoch": 1.25, + "learning_rate": 6.518244642133107e-06, + "loss": 0.5607, "step": 2743 }, { - "epoch": 1.41, - "learning_rate": 4.217532057012557e-06, - "loss": 0.5704, + "epoch": 1.25, + "learning_rate": 6.511329148024624e-06, + "loss": 0.6234, "step": 2744 }, { - "epoch": 1.41, - "learning_rate": 4.2107407790870665e-06, - "loss": 0.5957, + "epoch": 1.25, + "learning_rate": 6.504415553018655e-06, + "loss": 0.5977, "step": 2745 }, { - "epoch": 1.41, - "learning_rate": 4.203953514900366e-06, - "loss": 0.5547, + "epoch": 1.25, + "learning_rate": 6.497503860878697e-06, + "loss": 0.613, "step": 2746 }, { - "epoch": 1.41, - "learning_rate": 4.197170269158125e-06, - "loss": 0.6176, + "epoch": 1.25, + "learning_rate": 6.490594075367227e-06, + "loss": 0.6198, "step": 2747 }, { - "epoch": 1.41, - "learning_rate": 4.190391046563218e-06, - "loss": 0.6235, + "epoch": 1.25, + "learning_rate": 6.483686200245667e-06, + "loss": 0.6193, "step": 2748 }, { - "epoch": 1.41, - "learning_rate": 4.1836158518157335e-06, - "loss": 0.6104, + "epoch": 1.25, + "learning_rate": 6.476780239274413e-06, + "loss": 0.5417, "step": 2749 }, { - "epoch": 1.41, - "learning_rate": 4.176844689612962e-06, - "loss": 0.6008, + "epoch": 1.25, + "learning_rate": 6.469876196212808e-06, + "loss": 0.5599, "step": 2750 }, { - "epoch": 1.41, - "learning_rate": 4.170077564649412e-06, - "loss": 0.5432, + "epoch": 1.25, + "learning_rate": 6.462974074819161e-06, + "loss": 0.6371, "step": 2751 }, { - "epoch": 1.41, - "learning_rate": 4.1633144816167805e-06, - "loss": 0.5973, + "epoch": 1.25, + "learning_rate": 6.456073878850721e-06, + "loss": 0.6053, "step": 2752 }, { - "epoch": 1.42, - "learning_rate": 4.156555445203965e-06, - "loss": 0.5621, + "epoch": 1.25, + "learning_rate": 6.449175612063713e-06, + "loss": 0.5872, "step": 2753 }, { - "epoch": 1.42, - "learning_rate": 4.149800460097059e-06, - "loss": 0.5646, + "epoch": 1.25, + "learning_rate": 6.442279278213279e-06, + "loss": 0.5982, "step": 2754 }, { - "epoch": 1.42, - "learning_rate": 4.143049530979347e-06, - "loss": 0.5615, + "epoch": 1.26, + "learning_rate": 6.435384881053541e-06, + "loss": 0.6157, "step": 2755 }, { - "epoch": 1.42, - "learning_rate": 4.136302662531297e-06, - "loss": 0.5708, + "epoch": 1.26, + "learning_rate": 6.428492424337543e-06, + "loss": 0.5997, "step": 2756 }, { - "epoch": 1.42, - "learning_rate": 4.129559859430573e-06, - "loss": 0.6272, + "epoch": 1.26, + "learning_rate": 6.4216019118172855e-06, + "loss": 0.6504, "step": 2757 }, { - "epoch": 1.42, - "learning_rate": 4.12282112635201e-06, - "loss": 0.5431, + "epoch": 1.26, + "learning_rate": 6.414713347243707e-06, + "loss": 0.6265, "step": 2758 }, { - "epoch": 1.42, - "learning_rate": 4.116086467967625e-06, - "loss": 0.589, + "epoch": 1.26, + "learning_rate": 6.4078267343666845e-06, + "loss": 0.5593, "step": 2759 }, { - "epoch": 1.42, - "learning_rate": 4.109355888946604e-06, - "loss": 0.5825, + "epoch": 1.26, + "learning_rate": 6.400942076935031e-06, + "loss": 0.5427, "step": 2760 }, { - "epoch": 1.42, - "learning_rate": 4.102629393955318e-06, - "loss": 0.5948, + "epoch": 1.26, + "learning_rate": 6.3940593786965035e-06, + "loss": 0.5493, "step": 2761 }, { - "epoch": 1.42, - "learning_rate": 4.095906987657298e-06, - "loss": 0.6228, + "epoch": 1.26, + "learning_rate": 6.387178643397782e-06, + "loss": 0.6301, "step": 2762 }, { - "epoch": 1.42, - "learning_rate": 4.0891886747132356e-06, - "loss": 0.6002, + "epoch": 1.26, + "learning_rate": 6.380299874784487e-06, + "loss": 0.5778, "step": 2763 }, { - "epoch": 1.42, - "learning_rate": 4.082474459780994e-06, - "loss": 0.5713, + "epoch": 1.26, + "learning_rate": 6.373423076601158e-06, + "loss": 0.5977, "step": 2764 }, { - "epoch": 1.42, - "learning_rate": 4.07576434751559e-06, - "loss": 0.5884, + "epoch": 1.26, + "learning_rate": 6.366548252591275e-06, + "loss": 0.6057, "step": 2765 }, { - "epoch": 1.42, - "learning_rate": 4.069058342569193e-06, - "loss": 0.6013, + "epoch": 1.26, + "learning_rate": 6.359675406497226e-06, + "loss": 0.6034, "step": 2766 }, { - "epoch": 1.42, - "learning_rate": 4.062356449591136e-06, - "loss": 0.5779, + "epoch": 1.26, + "learning_rate": 6.352804542060347e-06, + "loss": 0.5743, "step": 2767 }, { - "epoch": 1.42, - "learning_rate": 4.055658673227891e-06, - "loss": 0.5686, + "epoch": 1.26, + "learning_rate": 6.345935663020866e-06, + "loss": 0.6014, "step": 2768 }, { - "epoch": 1.42, - "learning_rate": 4.048965018123074e-06, - "loss": 0.552, + "epoch": 1.26, + "learning_rate": 6.339068773117954e-06, + "loss": 0.6481, "step": 2769 }, { - "epoch": 1.42, - "learning_rate": 4.042275488917457e-06, - "loss": 0.5935, + "epoch": 1.26, + "learning_rate": 6.332203876089688e-06, + "loss": 0.6268, "step": 2770 }, { - "epoch": 1.42, - "learning_rate": 4.03559009024894e-06, - "loss": 0.5656, + "epoch": 1.26, + "learning_rate": 6.32534097567306e-06, + "loss": 0.6267, "step": 2771 }, { - "epoch": 1.42, - "learning_rate": 4.02890882675256e-06, - "loss": 0.5685, + "epoch": 1.26, + "learning_rate": 6.318480075603986e-06, + "loss": 0.6506, "step": 2772 }, { - "epoch": 1.43, - "learning_rate": 4.0222317030604906e-06, - "loss": 0.564, + "epoch": 1.26, + "learning_rate": 6.311621179617271e-06, + "loss": 0.6056, "step": 2773 }, { - "epoch": 1.43, - "learning_rate": 4.015558723802035e-06, - "loss": 0.6201, + "epoch": 1.26, + "learning_rate": 6.304764291446654e-06, + "loss": 0.5668, "step": 2774 }, { - "epoch": 1.43, - "learning_rate": 4.008889893603621e-06, - "loss": 0.5999, + "epoch": 1.26, + "learning_rate": 6.2979094148247635e-06, + "loss": 0.6132, "step": 2775 }, { - "epoch": 1.43, - "learning_rate": 4.002225217088795e-06, - "loss": 0.5814, + "epoch": 1.26, + "learning_rate": 6.291056553483142e-06, + "loss": 0.5978, "step": 2776 }, { - "epoch": 1.43, - "learning_rate": 3.995564698878242e-06, - "loss": 0.5327, + "epoch": 1.27, + "learning_rate": 6.28420571115223e-06, + "loss": 0.6055, "step": 2777 }, { - "epoch": 1.43, - "learning_rate": 3.988908343589743e-06, - "loss": 0.5439, + "epoch": 1.27, + "learning_rate": 6.277356891561373e-06, + "loss": 0.572, "step": 2778 }, { - "epoch": 1.43, - "learning_rate": 3.982256155838199e-06, - "loss": 0.5421, + "epoch": 1.27, + "learning_rate": 6.270510098438809e-06, + "loss": 0.5885, "step": 2779 }, { - "epoch": 1.43, - "learning_rate": 3.975608140235633e-06, - "loss": 0.5771, + "epoch": 1.27, + "learning_rate": 6.263665335511684e-06, + "loss": 0.5823, "step": 2780 }, { - "epoch": 1.43, - "learning_rate": 3.96896430139116e-06, - "loss": 0.5813, + "epoch": 1.27, + "learning_rate": 6.256822606506028e-06, + "loss": 0.604, "step": 2781 }, { - "epoch": 1.43, - "learning_rate": 3.9623246439110075e-06, - "loss": 0.5852, + "epoch": 1.27, + "learning_rate": 6.249981915146769e-06, + "loss": 0.6282, "step": 2782 }, { - "epoch": 1.43, - "learning_rate": 3.955689172398502e-06, - "loss": 0.5814, + "epoch": 1.27, + "learning_rate": 6.243143265157723e-06, + "loss": 0.568, "step": 2783 }, { - "epoch": 1.43, - "learning_rate": 3.949057891454067e-06, - "loss": 0.6051, + "epoch": 1.27, + "learning_rate": 6.236306660261599e-06, + "loss": 0.6174, "step": 2784 }, { - "epoch": 1.43, - "learning_rate": 3.942430805675221e-06, - "loss": 0.6064, + "epoch": 1.27, + "learning_rate": 6.229472104179984e-06, + "loss": 0.5514, "step": 2785 }, { - "epoch": 1.43, - "learning_rate": 3.9358079196565735e-06, - "loss": 0.6208, + "epoch": 1.27, + "learning_rate": 6.222639600633369e-06, + "loss": 0.6029, "step": 2786 }, { - "epoch": 1.43, - "learning_rate": 3.929189237989828e-06, - "loss": 0.5675, + "epoch": 1.27, + "learning_rate": 6.215809153341097e-06, + "loss": 0.6636, "step": 2787 }, { - "epoch": 1.43, - "learning_rate": 3.9225747652637646e-06, - "loss": 0.5682, + "epoch": 1.27, + "learning_rate": 6.208980766021424e-06, + "loss": 0.6445, "step": 2788 }, { - "epoch": 1.43, - "learning_rate": 3.915964506064248e-06, - "loss": 0.5675, + "epoch": 1.27, + "learning_rate": 6.2021544423914624e-06, + "loss": 0.6011, "step": 2789 }, { - "epoch": 1.43, - "learning_rate": 3.909358464974228e-06, - "loss": 0.6372, + "epoch": 1.27, + "learning_rate": 6.195330186167212e-06, + "loss": 0.6445, "step": 2790 }, { - "epoch": 1.43, - "learning_rate": 3.902756646573721e-06, - "loss": 0.563, + "epoch": 1.27, + "learning_rate": 6.18850800106354e-06, + "loss": 0.6736, "step": 2791 }, { - "epoch": 1.44, - "learning_rate": 3.89615905543982e-06, - "loss": 0.6077, + "epoch": 1.27, + "learning_rate": 6.181687890794194e-06, + "loss": 0.5974, "step": 2792 }, { - "epoch": 1.44, - "learning_rate": 3.889565696146687e-06, - "loss": 0.579, + "epoch": 1.27, + "learning_rate": 6.174869859071782e-06, + "loss": 0.5139, "step": 2793 }, { - "epoch": 1.44, - "learning_rate": 3.882976573265548e-06, - "loss": 0.5884, + "epoch": 1.27, + "learning_rate": 6.168053909607794e-06, + "loss": 0.5753, "step": 2794 }, { - "epoch": 1.44, - "learning_rate": 3.876391691364696e-06, - "loss": 0.5709, + "epoch": 1.27, + "learning_rate": 6.161240046112575e-06, + "loss": 0.6029, "step": 2795 }, { - "epoch": 1.44, - "learning_rate": 3.8698110550094755e-06, - "loss": 0.5714, + "epoch": 1.27, + "learning_rate": 6.154428272295341e-06, + "loss": 0.5847, "step": 2796 }, { - "epoch": 1.44, - "learning_rate": 3.863234668762301e-06, - "loss": 0.5397, + "epoch": 1.27, + "learning_rate": 6.147618591864164e-06, + "loss": 0.6404, "step": 2797 }, { - "epoch": 1.44, - "learning_rate": 3.85666253718263e-06, - "loss": 0.5427, + "epoch": 1.27, + "learning_rate": 6.140811008525985e-06, + "loss": 0.6023, "step": 2798 }, { - "epoch": 1.44, - "learning_rate": 3.850094664826969e-06, - "loss": 0.5872, + "epoch": 1.28, + "learning_rate": 6.134005525986592e-06, + "loss": 0.611, "step": 2799 }, { - "epoch": 1.44, - "learning_rate": 3.8435310562488826e-06, - "loss": 0.5496, + "epoch": 1.28, + "learning_rate": 6.127202147950647e-06, + "loss": 0.6415, "step": 2800 }, { - "epoch": 1.44, - "learning_rate": 3.836971715998968e-06, - "loss": 0.6016, + "epoch": 1.28, + "learning_rate": 6.1204008781216465e-06, + "loss": 0.5932, "step": 2801 }, { - "epoch": 1.44, - "learning_rate": 3.830416648624865e-06, - "loss": 0.5775, + "epoch": 1.28, + "learning_rate": 6.113601720201952e-06, + "loss": 0.6111, "step": 2802 }, { - "epoch": 1.44, - "learning_rate": 3.823865858671257e-06, - "loss": 0.5618, + "epoch": 1.28, + "learning_rate": 6.106804677892774e-06, + "loss": 0.5476, "step": 2803 }, { - "epoch": 1.44, - "learning_rate": 3.8173193506798566e-06, - "loss": 0.5532, + "epoch": 1.28, + "learning_rate": 6.100009754894163e-06, + "loss": 0.6098, "step": 2804 }, { - "epoch": 1.44, - "learning_rate": 3.8107771291894092e-06, - "loss": 0.5231, + "epoch": 1.28, + "learning_rate": 6.093216954905029e-06, + "loss": 0.6497, "step": 2805 }, { - "epoch": 1.44, - "learning_rate": 3.804239198735683e-06, - "loss": 0.5802, + "epoch": 1.28, + "learning_rate": 6.0864262816231145e-06, + "loss": 0.6144, "step": 2806 }, { - "epoch": 1.44, - "learning_rate": 3.797705563851487e-06, - "loss": 0.6038, + "epoch": 1.28, + "learning_rate": 6.079637738745014e-06, + "loss": 0.5741, "step": 2807 }, { - "epoch": 1.44, - "learning_rate": 3.7911762290666343e-06, - "loss": 0.5939, + "epoch": 1.28, + "learning_rate": 6.072851329966152e-06, + "loss": 0.6249, "step": 2808 }, { - "epoch": 1.44, - "learning_rate": 3.7846511989079627e-06, - "loss": 0.5472, + "epoch": 1.28, + "learning_rate": 6.066067058980802e-06, + "loss": 0.6514, "step": 2809 }, { - "epoch": 1.44, - "learning_rate": 3.778130477899333e-06, - "loss": 0.5586, + "epoch": 1.28, + "learning_rate": 6.059284929482061e-06, + "loss": 0.6763, "step": 2810 }, { - "epoch": 1.44, - "learning_rate": 3.7716140705616087e-06, - "loss": 0.58, + "epoch": 1.28, + "learning_rate": 6.052504945161879e-06, + "loss": 0.5909, "step": 2811 }, { - "epoch": 1.45, - "learning_rate": 3.7651019814126656e-06, - "loss": 0.579, + "epoch": 1.28, + "learning_rate": 6.045727109711015e-06, + "loss": 0.6328, "step": 2812 }, { - "epoch": 1.45, - "learning_rate": 3.758594214967387e-06, - "loss": 0.5924, + "epoch": 1.28, + "learning_rate": 6.038951426819078e-06, + "loss": 0.6824, "step": 2813 }, { - "epoch": 1.45, - "learning_rate": 3.752090775737658e-06, - "loss": 0.6094, + "epoch": 1.28, + "learning_rate": 6.032177900174495e-06, + "loss": 0.6235, "step": 2814 }, { - "epoch": 1.45, - "learning_rate": 3.7455916682323645e-06, - "loss": 0.5631, + "epoch": 1.28, + "learning_rate": 6.025406533464524e-06, + "loss": 0.5872, "step": 2815 }, { - "epoch": 1.45, - "learning_rate": 3.7390968969573836e-06, - "loss": 0.5775, + "epoch": 1.28, + "learning_rate": 6.018637330375241e-06, + "loss": 0.6135, "step": 2816 }, { - "epoch": 1.45, - "learning_rate": 3.7326064664156e-06, - "loss": 0.5778, + "epoch": 1.28, + "learning_rate": 6.011870294591551e-06, + "loss": 0.5775, "step": 2817 }, { - "epoch": 1.45, - "learning_rate": 3.726120381106876e-06, - "loss": 0.5702, + "epoch": 1.28, + "learning_rate": 6.005105429797171e-06, + "loss": 0.5598, "step": 2818 }, { - "epoch": 1.45, - "learning_rate": 3.719638645528061e-06, - "loss": 0.6143, + "epoch": 1.28, + "learning_rate": 5.9983427396746515e-06, + "loss": 0.5713, "step": 2819 }, { - "epoch": 1.45, - "learning_rate": 3.713161264173001e-06, - "loss": 0.5989, + "epoch": 1.28, + "learning_rate": 5.991582227905341e-06, + "loss": 0.6494, "step": 2820 }, { - "epoch": 1.45, - "learning_rate": 3.7066882415325123e-06, - "loss": 0.6121, + "epoch": 1.29, + "learning_rate": 5.984823898169415e-06, + "loss": 0.6302, "step": 2821 }, { - "epoch": 1.45, - "learning_rate": 3.70021958209439e-06, - "loss": 0.6002, + "epoch": 1.29, + "learning_rate": 5.978067754145852e-06, + "loss": 0.6185, "step": 2822 }, { - "epoch": 1.45, - "learning_rate": 3.693755290343409e-06, - "loss": 0.6042, + "epoch": 1.29, + "learning_rate": 5.97131379951245e-06, + "loss": 0.6001, "step": 2823 }, { - "epoch": 1.45, - "learning_rate": 3.6872953707613113e-06, - "loss": 0.5819, + "epoch": 1.29, + "learning_rate": 5.9645620379458045e-06, + "loss": 0.62, "step": 2824 }, { - "epoch": 1.45, - "learning_rate": 3.680839827826812e-06, - "loss": 0.5487, + "epoch": 1.29, + "learning_rate": 5.957812473121331e-06, + "loss": 0.5956, "step": 2825 }, { - "epoch": 1.45, - "learning_rate": 3.674388666015584e-06, - "loss": 0.5386, + "epoch": 1.29, + "learning_rate": 5.9510651087132345e-06, + "loss": 0.6495, "step": 2826 }, { - "epoch": 1.45, - "learning_rate": 3.667941889800276e-06, - "loss": 0.589, + "epoch": 1.29, + "learning_rate": 5.944319948394533e-06, + "loss": 0.5781, "step": 2827 }, { - "epoch": 1.45, - "learning_rate": 3.6614995036504853e-06, - "loss": 0.5693, + "epoch": 1.29, + "learning_rate": 5.937576995837037e-06, + "loss": 0.6111, "step": 2828 }, { - "epoch": 1.45, - "learning_rate": 3.655061512032766e-06, - "loss": 0.5549, + "epoch": 1.29, + "learning_rate": 5.930836254711363e-06, + "loss": 0.6, "step": 2829 }, { - "epoch": 1.45, - "learning_rate": 3.6486279194106334e-06, - "loss": 0.5812, + "epoch": 1.29, + "learning_rate": 5.924097728686916e-06, + "loss": 0.6156, "step": 2830 }, { - "epoch": 1.46, - "learning_rate": 3.642198730244545e-06, - "loss": 0.5674, + "epoch": 1.29, + "learning_rate": 5.917361421431902e-06, + "loss": 0.619, "step": 2831 }, { - "epoch": 1.46, - "learning_rate": 3.6357739489919077e-06, - "loss": 0.574, + "epoch": 1.29, + "learning_rate": 5.910627336613309e-06, + "loss": 0.6746, "step": 2832 }, { - "epoch": 1.46, - "learning_rate": 3.6293535801070735e-06, - "loss": 0.6002, + "epoch": 1.29, + "learning_rate": 5.9038954778969324e-06, + "loss": 0.6115, "step": 2833 }, { - "epoch": 1.46, - "learning_rate": 3.622937628041334e-06, - "loss": 0.5634, + "epoch": 1.29, + "learning_rate": 5.897165848947337e-06, + "loss": 0.6046, "step": 2834 }, { - "epoch": 1.46, - "learning_rate": 3.616526097242916e-06, - "loss": 0.5554, + "epoch": 1.29, + "learning_rate": 5.890438453427887e-06, + "loss": 0.6121, "step": 2835 }, { - "epoch": 1.46, - "learning_rate": 3.61011899215699e-06, - "loss": 0.59, + "epoch": 1.29, + "learning_rate": 5.883713295000721e-06, + "loss": 0.5957, "step": 2836 }, { - "epoch": 1.46, - "learning_rate": 3.6037163172256497e-06, - "loss": 0.5795, + "epoch": 1.29, + "learning_rate": 5.8769903773267675e-06, + "loss": 0.6144, "step": 2837 }, { - "epoch": 1.46, - "learning_rate": 3.5973180768879203e-06, - "loss": 0.5846, + "epoch": 1.29, + "learning_rate": 5.870269704065739e-06, + "loss": 0.6829, "step": 2838 }, { - "epoch": 1.46, - "learning_rate": 3.5909242755797456e-06, - "loss": 0.6086, + "epoch": 1.29, + "learning_rate": 5.86355127887611e-06, + "loss": 0.5961, "step": 2839 }, { - "epoch": 1.46, - "learning_rate": 3.5845349177340083e-06, - "loss": 0.5479, + "epoch": 1.29, + "learning_rate": 5.856835105415146e-06, + "loss": 0.6514, "step": 2840 }, { - "epoch": 1.46, - "learning_rate": 3.5781500077804963e-06, - "loss": 0.5616, + "epoch": 1.29, + "learning_rate": 5.85012118733888e-06, + "loss": 0.6068, "step": 2841 }, { - "epoch": 1.46, - "learning_rate": 3.571769550145916e-06, - "loss": 0.6022, + "epoch": 1.29, + "learning_rate": 5.843409528302119e-06, + "loss": 0.5629, "step": 2842 }, { - "epoch": 1.46, - "learning_rate": 3.5653935492538905e-06, - "loss": 0.5938, + "epoch": 1.3, + "learning_rate": 5.836700131958439e-06, + "loss": 0.5869, "step": 2843 }, { - "epoch": 1.46, - "learning_rate": 3.5590220095249493e-06, - "loss": 0.5692, + "epoch": 1.3, + "learning_rate": 5.8299930019601944e-06, + "loss": 0.6448, "step": 2844 }, { - "epoch": 1.46, - "learning_rate": 3.5526549353765294e-06, - "loss": 0.5723, + "epoch": 1.3, + "learning_rate": 5.823288141958485e-06, + "loss": 0.6223, "step": 2845 }, { - "epoch": 1.46, - "learning_rate": 3.546292331222979e-06, - "loss": 0.5996, + "epoch": 1.3, + "learning_rate": 5.816585555603191e-06, + "loss": 0.6169, "step": 2846 }, { - "epoch": 1.46, - "learning_rate": 3.5399342014755388e-06, - "loss": 0.575, + "epoch": 1.3, + "learning_rate": 5.809885246542954e-06, + "loss": 0.5586, "step": 2847 }, { - "epoch": 1.46, - "learning_rate": 3.533580550542345e-06, - "loss": 0.5811, + "epoch": 1.3, + "learning_rate": 5.803187218425169e-06, + "loss": 0.5802, "step": 2848 }, { - "epoch": 1.46, - "learning_rate": 3.5272313828284423e-06, - "loss": 0.6013, + "epoch": 1.3, + "learning_rate": 5.796491474895995e-06, + "loss": 0.6174, "step": 2849 }, { - "epoch": 1.46, - "learning_rate": 3.520886702735753e-06, - "loss": 0.5662, + "epoch": 1.3, + "learning_rate": 5.78979801960035e-06, + "loss": 0.6694, "step": 2850 }, { - "epoch": 1.47, - "learning_rate": 3.5145465146630954e-06, - "loss": 0.5842, + "epoch": 1.3, + "learning_rate": 5.783106856181893e-06, + "loss": 0.5537, "step": 2851 }, { - "epoch": 1.47, - "learning_rate": 3.5082108230061708e-06, - "loss": 0.608, + "epoch": 1.3, + "learning_rate": 5.776417988283047e-06, + "loss": 0.61, "step": 2852 }, { - "epoch": 1.47, - "learning_rate": 3.5018796321575643e-06, - "loss": 0.5751, + "epoch": 1.3, + "learning_rate": 5.769731419544985e-06, + "loss": 0.6277, "step": 2853 }, { - "epoch": 1.47, - "learning_rate": 3.4955529465067394e-06, - "loss": 0.5923, + "epoch": 1.3, + "learning_rate": 5.763047153607628e-06, + "loss": 0.6111, "step": 2854 }, { - "epoch": 1.47, - "learning_rate": 3.489230770440033e-06, - "loss": 0.5999, + "epoch": 1.3, + "learning_rate": 5.7563651941096325e-06, + "loss": 0.6427, "step": 2855 }, { - "epoch": 1.47, - "learning_rate": 3.4829131083406684e-06, - "loss": 0.5804, + "epoch": 1.3, + "learning_rate": 5.7496855446884195e-06, + "loss": 0.5687, "step": 2856 }, { - "epoch": 1.47, - "learning_rate": 3.476599964588725e-06, - "loss": 0.5278, + "epoch": 1.3, + "learning_rate": 5.743008208980134e-06, + "loss": 0.5709, "step": 2857 }, { - "epoch": 1.47, - "learning_rate": 3.4702913435611505e-06, - "loss": 0.5642, + "epoch": 1.3, + "learning_rate": 5.736333190619671e-06, + "loss": 0.6066, "step": 2858 }, { - "epoch": 1.47, - "learning_rate": 3.4639872496317705e-06, - "loss": 0.5414, + "epoch": 1.3, + "learning_rate": 5.729660493240662e-06, + "loss": 0.5991, "step": 2859 }, { - "epoch": 1.47, - "learning_rate": 3.4576876871712585e-06, - "loss": 0.5813, + "epoch": 1.3, + "learning_rate": 5.722990120475479e-06, + "loss": 0.6108, "step": 2860 }, { - "epoch": 1.47, - "learning_rate": 3.4513926605471504e-06, - "loss": 0.6042, + "epoch": 1.3, + "learning_rate": 5.716322075955213e-06, + "loss": 0.6362, "step": 2861 }, { - "epoch": 1.47, - "learning_rate": 3.4451021741238365e-06, - "loss": 0.5872, + "epoch": 1.3, + "learning_rate": 5.709656363309715e-06, + "loss": 0.5858, "step": 2862 }, { - "epoch": 1.47, - "learning_rate": 3.4388162322625616e-06, - "loss": 0.593, + "epoch": 1.3, + "learning_rate": 5.702992986167538e-06, + "loss": 0.6067, "step": 2863 }, { - "epoch": 1.47, - "learning_rate": 3.4325348393214185e-06, - "loss": 0.5491, + "epoch": 1.3, + "learning_rate": 5.696331948155982e-06, + "loss": 0.5784, "step": 2864 }, { - "epoch": 1.47, - "learning_rate": 3.4262579996553425e-06, - "loss": 0.5782, + "epoch": 1.31, + "learning_rate": 5.689673252901067e-06, + "loss": 0.5847, "step": 2865 }, { - "epoch": 1.47, - "learning_rate": 3.4199857176161212e-06, - "loss": 0.5917, + "epoch": 1.31, + "learning_rate": 5.683016904027542e-06, + "loss": 0.5334, "step": 2866 }, { - "epoch": 1.47, - "learning_rate": 3.413717997552376e-06, - "loss": 0.5355, + "epoch": 1.31, + "learning_rate": 5.676362905158864e-06, + "loss": 0.6365, "step": 2867 }, { - "epoch": 1.47, - "learning_rate": 3.40745484380956e-06, - "loss": 0.5891, + "epoch": 1.31, + "learning_rate": 5.66971125991724e-06, + "loss": 0.5984, "step": 2868 }, { - "epoch": 1.47, - "learning_rate": 3.4011962607299765e-06, - "loss": 0.5726, + "epoch": 1.31, + "learning_rate": 5.663061971923564e-06, + "loss": 0.6094, "step": 2869 }, { - "epoch": 1.48, - "learning_rate": 3.3949422526527455e-06, - "loss": 0.6093, + "epoch": 1.31, + "learning_rate": 5.656415044797465e-06, + "loss": 0.5907, "step": 2870 }, { - "epoch": 1.48, - "learning_rate": 3.3886928239138196e-06, - "loss": 0.5615, + "epoch": 1.31, + "learning_rate": 5.649770482157284e-06, + "loss": 0.5929, "step": 2871 }, { - "epoch": 1.48, - "learning_rate": 3.3824479788459773e-06, - "loss": 0.5874, + "epoch": 1.31, + "learning_rate": 5.643128287620072e-06, + "loss": 0.6172, "step": 2872 }, { - "epoch": 1.48, - "learning_rate": 3.376207721778818e-06, - "loss": 0.5771, + "epoch": 1.31, + "learning_rate": 5.636488464801597e-06, + "loss": 0.6351, "step": 2873 }, { - "epoch": 1.48, - "learning_rate": 3.3699720570387607e-06, - "loss": 0.6135, + "epoch": 1.31, + "learning_rate": 5.629851017316319e-06, + "loss": 0.5945, "step": 2874 }, { - "epoch": 1.48, - "learning_rate": 3.363740988949038e-06, - "loss": 0.5784, + "epoch": 1.31, + "learning_rate": 5.623215948777434e-06, + "loss": 0.6467, "step": 2875 }, { - "epoch": 1.48, - "learning_rate": 3.3575145218297044e-06, - "loss": 0.5663, + "epoch": 1.31, + "learning_rate": 5.616583262796813e-06, + "loss": 0.5681, "step": 2876 }, { - "epoch": 1.48, - "learning_rate": 3.351292659997616e-06, - "loss": 0.5831, + "epoch": 1.31, + "learning_rate": 5.609952962985048e-06, + "loss": 0.5946, "step": 2877 }, { - "epoch": 1.48, - "learning_rate": 3.3450754077664337e-06, - "loss": 0.584, + "epoch": 1.31, + "learning_rate": 5.603325052951428e-06, + "loss": 0.6388, "step": 2878 }, { - "epoch": 1.48, - "learning_rate": 3.338862769446635e-06, - "loss": 0.5686, + "epoch": 1.31, + "learning_rate": 5.5966995363039435e-06, + "loss": 0.5966, "step": 2879 }, { - "epoch": 1.48, - "learning_rate": 3.3326547493454865e-06, - "loss": 0.5779, + "epoch": 1.31, + "learning_rate": 5.590076416649267e-06, + "loss": 0.6171, "step": 2880 }, { - "epoch": 1.48, - "learning_rate": 3.326451351767057e-06, - "loss": 0.5842, + "epoch": 1.31, + "learning_rate": 5.583455697592795e-06, + "loss": 0.5859, "step": 2881 }, { - "epoch": 1.48, - "learning_rate": 3.320252581012212e-06, - "loss": 0.5801, + "epoch": 1.31, + "learning_rate": 5.576837382738588e-06, + "loss": 0.6445, "step": 2882 }, { - "epoch": 1.48, - "learning_rate": 3.314058441378607e-06, - "loss": 0.5574, + "epoch": 1.31, + "learning_rate": 5.570221475689414e-06, + "loss": 0.562, "step": 2883 }, { - "epoch": 1.48, - "learning_rate": 3.3078689371606877e-06, - "loss": 0.601, + "epoch": 1.31, + "learning_rate": 5.563607980046727e-06, + "loss": 0.6372, "step": 2884 }, { - "epoch": 1.48, - "learning_rate": 3.3016840726496814e-06, - "loss": 0.6039, + "epoch": 1.31, + "learning_rate": 5.556996899410671e-06, + "loss": 0.519, "step": 2885 }, { - "epoch": 1.48, - "learning_rate": 3.2955038521336123e-06, - "loss": 0.5664, + "epoch": 1.31, + "learning_rate": 5.550388237380061e-06, + "loss": 0.6152, "step": 2886 }, { - "epoch": 1.48, - "learning_rate": 3.2893282798972702e-06, - "loss": 0.5751, + "epoch": 1.32, + "learning_rate": 5.543781997552422e-06, + "loss": 0.5305, "step": 2887 }, { - "epoch": 1.48, - "learning_rate": 3.2831573602222255e-06, - "loss": 0.568, + "epoch": 1.32, + "learning_rate": 5.5371781835239325e-06, + "loss": 0.5917, "step": 2888 }, { - "epoch": 1.48, - "learning_rate": 3.2769910973868314e-06, - "loss": 0.5193, + "epoch": 1.32, + "learning_rate": 5.530576798889468e-06, + "loss": 0.5873, "step": 2889 }, { - "epoch": 1.49, - "learning_rate": 3.2708294956662033e-06, - "loss": 0.561, + "epoch": 1.32, + "learning_rate": 5.5239778472425764e-06, + "loss": 0.6208, "step": 2890 }, { - "epoch": 1.49, - "learning_rate": 3.2646725593322283e-06, - "loss": 0.6057, + "epoch": 1.32, + "learning_rate": 5.517381332175484e-06, + "loss": 0.6129, "step": 2891 }, { - "epoch": 1.49, - "learning_rate": 3.2585202926535564e-06, - "loss": 0.5695, + "epoch": 1.32, + "learning_rate": 5.5107872572790775e-06, + "loss": 0.609, "step": 2892 }, { - "epoch": 1.49, - "learning_rate": 3.252372699895605e-06, - "loss": 0.5896, + "epoch": 1.32, + "learning_rate": 5.504195626142941e-06, + "loss": 0.5961, "step": 2893 }, { - "epoch": 1.49, - "learning_rate": 3.2462297853205472e-06, - "loss": 0.5997, + "epoch": 1.32, + "learning_rate": 5.497606442355301e-06, + "loss": 0.5968, "step": 2894 }, { - "epoch": 1.49, - "learning_rate": 3.24009155318731e-06, - "loss": 0.6161, + "epoch": 1.32, + "learning_rate": 5.491019709503068e-06, + "loss": 0.6096, "step": 2895 }, { - "epoch": 1.49, - "learning_rate": 3.2339580077515864e-06, - "loss": 0.5874, + "epoch": 1.32, + "learning_rate": 5.484435431171815e-06, + "loss": 0.6143, "step": 2896 }, { - "epoch": 1.49, - "learning_rate": 3.2278291532658057e-06, - "loss": 0.5673, + "epoch": 1.32, + "learning_rate": 5.477853610945781e-06, + "loss": 0.5979, "step": 2897 }, { - "epoch": 1.49, - "learning_rate": 3.221704993979149e-06, - "loss": 0.5988, + "epoch": 1.32, + "learning_rate": 5.471274252407855e-06, + "loss": 0.5841, "step": 2898 }, { - "epoch": 1.49, - "learning_rate": 3.2155855341375497e-06, - "loss": 0.6083, + "epoch": 1.32, + "learning_rate": 5.464697359139599e-06, + "loss": 0.6165, "step": 2899 }, { - "epoch": 1.49, - "learning_rate": 3.209470777983675e-06, - "loss": 0.5504, + "epoch": 1.32, + "learning_rate": 5.458122934721231e-06, + "loss": 0.6169, "step": 2900 }, { - "epoch": 1.49, - "learning_rate": 3.2033607297569326e-06, - "loss": 0.5438, + "epoch": 1.32, + "learning_rate": 5.4515509827316195e-06, + "loss": 0.5881, "step": 2901 }, { - "epoch": 1.49, - "learning_rate": 3.197255393693467e-06, - "loss": 0.5839, + "epoch": 1.32, + "learning_rate": 5.444981506748294e-06, + "loss": 0.6302, "step": 2902 }, { - "epoch": 1.49, - "learning_rate": 3.191154774026156e-06, - "loss": 0.5541, + "epoch": 1.32, + "learning_rate": 5.438414510347434e-06, + "loss": 0.5991, "step": 2903 }, { - "epoch": 1.49, - "learning_rate": 3.185058874984606e-06, - "loss": 0.5869, + "epoch": 1.32, + "learning_rate": 5.431849997103862e-06, + "loss": 0.6073, "step": 2904 }, { - "epoch": 1.49, - "learning_rate": 3.178967700795148e-06, - "loss": 0.5375, + "epoch": 1.32, + "learning_rate": 5.425287970591053e-06, + "loss": 0.6044, "step": 2905 }, { - "epoch": 1.49, - "learning_rate": 3.1728812556808498e-06, - "loss": 0.5994, + "epoch": 1.32, + "learning_rate": 5.418728434381142e-06, + "loss": 0.6096, "step": 2906 }, { - "epoch": 1.49, - "learning_rate": 3.166799543861485e-06, - "loss": 0.5637, + "epoch": 1.32, + "learning_rate": 5.4121713920448835e-06, + "loss": 0.5977, "step": 2907 }, { - "epoch": 1.49, - "learning_rate": 3.1607225695535514e-06, - "loss": 0.5743, + "epoch": 1.32, + "learning_rate": 5.405616847151694e-06, + "loss": 0.6096, "step": 2908 }, { - "epoch": 1.5, - "learning_rate": 3.1546503369702677e-06, - "loss": 0.5887, + "epoch": 1.33, + "learning_rate": 5.39906480326962e-06, + "loss": 0.6497, "step": 2909 }, { - "epoch": 1.5, - "learning_rate": 3.1485828503215588e-06, - "loss": 0.5598, + "epoch": 1.33, + "learning_rate": 5.392515263965358e-06, + "loss": 0.5835, "step": 2910 }, { - "epoch": 1.5, - "learning_rate": 3.1425201138140592e-06, - "loss": 0.5511, + "epoch": 1.33, + "learning_rate": 5.3859682328042185e-06, + "loss": 0.5938, "step": 2911 }, { - "epoch": 1.5, - "learning_rate": 3.1364621316511124e-06, - "loss": 0.5737, + "epoch": 1.33, + "learning_rate": 5.379423713350178e-06, + "loss": 0.5532, "step": 2912 }, { - "epoch": 1.5, - "learning_rate": 3.130408908032764e-06, - "loss": 0.5868, + "epoch": 1.33, + "learning_rate": 5.372881709165818e-06, + "loss": 0.5454, "step": 2913 }, { - "epoch": 1.5, - "learning_rate": 3.1243604471557633e-06, - "loss": 0.6089, + "epoch": 1.33, + "learning_rate": 5.3663422238123666e-06, + "loss": 0.6252, "step": 2914 }, { - "epoch": 1.5, - "learning_rate": 3.1183167532135505e-06, - "loss": 0.5684, + "epoch": 1.33, + "learning_rate": 5.359805260849674e-06, + "loss": 0.5836, "step": 2915 }, { - "epoch": 1.5, - "learning_rate": 3.112277830396273e-06, - "loss": 0.5808, + "epoch": 1.33, + "learning_rate": 5.3532708238362254e-06, + "loss": 0.6361, "step": 2916 }, { - "epoch": 1.5, - "learning_rate": 3.1062436828907605e-06, - "loss": 0.5919, + "epoch": 1.33, + "learning_rate": 5.346738916329115e-06, + "loss": 0.5927, "step": 2917 }, { - "epoch": 1.5, - "learning_rate": 3.100214314880531e-06, - "loss": 0.6067, + "epoch": 1.33, + "learning_rate": 5.340209541884076e-06, + "loss": 0.5885, "step": 2918 }, { - "epoch": 1.5, - "learning_rate": 3.0941897305458003e-06, - "loss": 0.5435, + "epoch": 1.33, + "learning_rate": 5.333682704055456e-06, + "loss": 0.65, "step": 2919 }, { - "epoch": 1.5, - "learning_rate": 3.088169934063454e-06, - "loss": 0.587, + "epoch": 1.33, + "learning_rate": 5.327158406396222e-06, + "loss": 0.5873, "step": 2920 }, { - "epoch": 1.5, - "learning_rate": 3.0821549296070674e-06, - "loss": 0.6122, + "epoch": 1.33, + "learning_rate": 5.32063665245796e-06, + "loss": 0.6188, "step": 2921 }, { - "epoch": 1.5, - "learning_rate": 3.0761447213468888e-06, - "loss": 0.5498, + "epoch": 1.33, + "learning_rate": 5.314117445790873e-06, + "loss": 0.6127, "step": 2922 }, { - "epoch": 1.5, - "learning_rate": 3.0701393134498425e-06, - "loss": 0.5837, + "epoch": 1.33, + "learning_rate": 5.307600789943765e-06, + "loss": 0.6271, "step": 2923 }, { - "epoch": 1.5, - "learning_rate": 3.0641387100795237e-06, - "loss": 0.5958, + "epoch": 1.33, + "learning_rate": 5.301086688464068e-06, + "loss": 0.5828, "step": 2924 }, { - "epoch": 1.5, - "learning_rate": 3.058142915396197e-06, - "loss": 0.5535, + "epoch": 1.33, + "learning_rate": 5.294575144897815e-06, + "loss": 0.6255, "step": 2925 }, { - "epoch": 1.5, - "learning_rate": 3.0521519335567994e-06, - "loss": 0.5681, + "epoch": 1.33, + "learning_rate": 5.28806616278965e-06, + "loss": 0.5951, "step": 2926 }, { - "epoch": 1.5, - "learning_rate": 3.0461657687149183e-06, - "loss": 0.6179, + "epoch": 1.33, + "learning_rate": 5.281559745682811e-06, + "loss": 0.6105, "step": 2927 }, { - "epoch": 1.51, - "learning_rate": 3.0401844250208157e-06, - "loss": 0.5631, + "epoch": 1.33, + "learning_rate": 5.275055897119163e-06, + "loss": 0.6152, "step": 2928 }, { - "epoch": 1.51, - "learning_rate": 3.0342079066214014e-06, - "loss": 0.578, + "epoch": 1.33, + "learning_rate": 5.26855462063915e-06, + "loss": 0.6339, "step": 2929 }, { - "epoch": 1.51, - "learning_rate": 3.028236217660241e-06, - "loss": 0.5344, + "epoch": 1.33, + "learning_rate": 5.262055919781826e-06, + "loss": 0.6277, "step": 2930 }, { - "epoch": 1.51, - "learning_rate": 3.0222693622775544e-06, - "loss": 0.6177, + "epoch": 1.34, + "learning_rate": 5.255559798084842e-06, + "loss": 0.5885, "step": 2931 }, { - "epoch": 1.51, - "learning_rate": 3.01630734461021e-06, - "loss": 0.5377, + "epoch": 1.34, + "learning_rate": 5.249066259084451e-06, + "loss": 0.6147, "step": 2932 }, { - "epoch": 1.51, - "learning_rate": 3.0103501687917192e-06, - "loss": 0.5939, + "epoch": 1.34, + "learning_rate": 5.24257530631548e-06, + "loss": 0.5638, "step": 2933 }, { - "epoch": 1.51, - "learning_rate": 3.0043978389522365e-06, - "loss": 0.5887, + "epoch": 1.34, + "learning_rate": 5.236086943311378e-06, + "loss": 0.6038, "step": 2934 }, { - "epoch": 1.51, - "learning_rate": 2.9984503592185665e-06, - "loss": 0.5955, + "epoch": 1.34, + "learning_rate": 5.229601173604157e-06, + "loss": 0.5485, "step": 2935 }, { - "epoch": 1.51, - "learning_rate": 2.9925077337141383e-06, - "loss": 0.5967, + "epoch": 1.34, + "learning_rate": 5.223118000724432e-06, + "loss": 0.6082, "step": 2936 }, { - "epoch": 1.51, - "learning_rate": 2.9865699665590185e-06, - "loss": 0.6327, + "epoch": 1.34, + "learning_rate": 5.216637428201401e-06, + "loss": 0.5874, "step": 2937 }, { - "epoch": 1.51, - "learning_rate": 2.9806370618699142e-06, - "loss": 0.6299, + "epoch": 1.34, + "learning_rate": 5.210159459562847e-06, + "loss": 0.6155, "step": 2938 }, { - "epoch": 1.51, - "learning_rate": 2.9747090237601505e-06, - "loss": 0.5889, + "epoch": 1.34, + "learning_rate": 5.203684098335133e-06, + "loss": 0.5886, "step": 2939 }, { - "epoch": 1.51, - "learning_rate": 2.968785856339684e-06, - "loss": 0.5748, + "epoch": 1.34, + "learning_rate": 5.197211348043207e-06, + "loss": 0.5028, "step": 2940 }, { - "epoch": 1.51, - "learning_rate": 2.962867563715093e-06, - "loss": 0.6146, + "epoch": 1.34, + "learning_rate": 5.190741212210596e-06, + "loss": 0.5913, "step": 2941 }, { - "epoch": 1.51, - "learning_rate": 2.956954149989575e-06, - "loss": 0.5742, + "epoch": 1.34, + "learning_rate": 5.184273694359394e-06, + "loss": 0.6433, "step": 2942 }, { - "epoch": 1.51, - "learning_rate": 2.9510456192629468e-06, - "loss": 0.5969, + "epoch": 1.34, + "learning_rate": 5.1778087980102785e-06, + "loss": 0.6066, "step": 2943 }, { - "epoch": 1.51, - "learning_rate": 2.945141975631637e-06, - "loss": 0.5874, + "epoch": 1.34, + "learning_rate": 5.171346526682501e-06, + "loss": 0.601, "step": 2944 }, { - "epoch": 1.51, - "learning_rate": 2.9392432231886914e-06, - "loss": 0.5935, + "epoch": 1.34, + "learning_rate": 5.164886883893885e-06, + "loss": 0.5975, "step": 2945 }, { - "epoch": 1.51, - "learning_rate": 2.933349366023761e-06, - "loss": 0.6042, + "epoch": 1.34, + "learning_rate": 5.158429873160805e-06, + "loss": 0.5878, "step": 2946 }, { - "epoch": 1.51, - "learning_rate": 2.9274604082230986e-06, - "loss": 0.5513, + "epoch": 1.34, + "learning_rate": 5.151975497998236e-06, + "loss": 0.6057, "step": 2947 }, { - "epoch": 1.52, - "learning_rate": 2.921576353869572e-06, - "loss": 0.5996, + "epoch": 1.34, + "learning_rate": 5.145523761919687e-06, + "loss": 0.6566, "step": 2948 }, { - "epoch": 1.52, - "learning_rate": 2.915697207042637e-06, - "loss": 0.5319, + "epoch": 1.34, + "learning_rate": 5.139074668437245e-06, + "loss": 0.5424, "step": 2949 }, { - "epoch": 1.52, - "learning_rate": 2.9098229718183546e-06, - "loss": 0.6011, + "epoch": 1.34, + "learning_rate": 5.132628221061559e-06, + "loss": 0.6465, "step": 2950 }, { - "epoch": 1.52, - "learning_rate": 2.9039536522693777e-06, - "loss": 0.5886, + "epoch": 1.34, + "learning_rate": 5.1261844233018386e-06, + "loss": 0.6023, "step": 2951 }, { - "epoch": 1.52, - "learning_rate": 2.8980892524649506e-06, - "loss": 0.571, + "epoch": 1.34, + "learning_rate": 5.119743278665834e-06, + "loss": 0.5849, "step": 2952 }, { - "epoch": 1.52, - "learning_rate": 2.8922297764709084e-06, - "loss": 0.5155, + "epoch": 1.35, + "learning_rate": 5.11330479065988e-06, + "loss": 0.577, "step": 2953 }, { - "epoch": 1.52, - "learning_rate": 2.8863752283496683e-06, - "loss": 0.5465, + "epoch": 1.35, + "learning_rate": 5.10686896278884e-06, + "loss": 0.5876, "step": 2954 }, { - "epoch": 1.52, - "learning_rate": 2.88052561216024e-06, - "loss": 0.559, + "epoch": 1.35, + "learning_rate": 5.100435798556141e-06, + "loss": 0.588, "step": 2955 }, { - "epoch": 1.52, - "learning_rate": 2.8746809319582058e-06, - "loss": 0.582, + "epoch": 1.35, + "learning_rate": 5.094005301463758e-06, + "loss": 0.5872, "step": 2956 }, { - "epoch": 1.52, - "learning_rate": 2.868841191795726e-06, - "loss": 0.595, + "epoch": 1.35, + "learning_rate": 5.087577475012221e-06, + "loss": 0.6189, "step": 2957 }, { - "epoch": 1.52, - "learning_rate": 2.8630063957215424e-06, - "loss": 0.5728, + "epoch": 1.35, + "learning_rate": 5.0811523227005846e-06, + "loss": 0.5742, "step": 2958 }, { - "epoch": 1.52, - "learning_rate": 2.8571765477809645e-06, - "loss": 0.5455, + "epoch": 1.35, + "learning_rate": 5.07472984802648e-06, + "loss": 0.5703, "step": 2959 }, { - "epoch": 1.52, - "learning_rate": 2.851351652015869e-06, - "loss": 0.6104, + "epoch": 1.35, + "learning_rate": 5.06831005448605e-06, + "loss": 0.5791, "step": 2960 }, { - "epoch": 1.52, - "learning_rate": 2.845531712464703e-06, - "loss": 0.5361, + "epoch": 1.35, + "learning_rate": 5.061892945573995e-06, + "loss": 0.6006, "step": 2961 }, { - "epoch": 1.52, - "learning_rate": 2.8397167331624755e-06, - "loss": 0.562, + "epoch": 1.35, + "learning_rate": 5.055478524783553e-06, + "loss": 0.5868, "step": 2962 }, { - "epoch": 1.52, - "learning_rate": 2.8339067181407588e-06, - "loss": 0.5829, + "epoch": 1.35, + "learning_rate": 5.049066795606495e-06, + "loss": 0.6362, "step": 2963 }, { - "epoch": 1.52, - "learning_rate": 2.8281016714276766e-06, - "loss": 0.5355, + "epoch": 1.35, + "learning_rate": 5.04265776153312e-06, + "loss": 0.6237, "step": 2964 }, { - "epoch": 1.52, - "learning_rate": 2.8223015970479207e-06, - "loss": 0.595, + "epoch": 1.35, + "learning_rate": 5.036251426052281e-06, + "loss": 0.5919, "step": 2965 }, { - "epoch": 1.52, - "learning_rate": 2.8165064990227255e-06, - "loss": 0.5454, + "epoch": 1.35, + "learning_rate": 5.029847792651339e-06, + "loss": 0.5853, "step": 2966 }, { - "epoch": 1.53, - "learning_rate": 2.8107163813698735e-06, - "loss": 0.5441, + "epoch": 1.35, + "learning_rate": 5.023446864816195e-06, + "loss": 0.61, "step": 2967 }, { - "epoch": 1.53, - "learning_rate": 2.804931248103706e-06, - "loss": 0.5996, + "epoch": 1.35, + "learning_rate": 5.017048646031278e-06, + "loss": 0.6716, "step": 2968 }, { - "epoch": 1.53, - "learning_rate": 2.7991511032350982e-06, - "loss": 0.5635, + "epoch": 1.35, + "learning_rate": 5.01065313977954e-06, + "loss": 0.646, "step": 2969 }, { - "epoch": 1.53, - "learning_rate": 2.7933759507714687e-06, - "loss": 0.5751, + "epoch": 1.35, + "learning_rate": 5.004260349542453e-06, + "loss": 0.6221, "step": 2970 }, { - "epoch": 1.53, - "learning_rate": 2.787605794716777e-06, - "loss": 0.5551, + "epoch": 1.35, + "learning_rate": 4.9978702788000125e-06, + "loss": 0.6251, "step": 2971 }, { - "epoch": 1.53, - "learning_rate": 2.7818406390715158e-06, - "loss": 0.5386, + "epoch": 1.35, + "learning_rate": 4.991482931030747e-06, + "loss": 0.6095, "step": 2972 }, { - "epoch": 1.53, - "learning_rate": 2.776080487832715e-06, - "loss": 0.5735, + "epoch": 1.35, + "learning_rate": 4.985098309711677e-06, + "loss": 0.5662, "step": 2973 }, { - "epoch": 1.53, - "learning_rate": 2.7703253449939284e-06, - "loss": 0.5657, + "epoch": 1.35, + "learning_rate": 4.97871641831836e-06, + "loss": 0.58, "step": 2974 }, { - "epoch": 1.53, - "learning_rate": 2.7645752145452485e-06, - "loss": 0.5741, + "epoch": 1.36, + "learning_rate": 4.972337260324857e-06, + "loss": 0.5931, "step": 2975 }, { - "epoch": 1.53, - "learning_rate": 2.758830100473281e-06, - "loss": 0.5992, + "epoch": 1.36, + "learning_rate": 4.965960839203751e-06, + "loss": 0.6167, "step": 2976 }, { - "epoch": 1.53, - "learning_rate": 2.7530900067611577e-06, - "loss": 0.5638, + "epoch": 1.36, + "learning_rate": 4.959587158426114e-06, + "loss": 0.5792, "step": 2977 }, { - "epoch": 1.53, - "learning_rate": 2.7473549373885345e-06, - "loss": 0.5944, + "epoch": 1.36, + "learning_rate": 4.953216221461556e-06, + "loss": 0.6736, "step": 2978 }, { - "epoch": 1.53, - "learning_rate": 2.7416248963315785e-06, - "loss": 0.5605, + "epoch": 1.36, + "learning_rate": 4.9468480317781675e-06, + "loss": 0.6078, "step": 2979 }, { - "epoch": 1.53, - "learning_rate": 2.7358998875629716e-06, - "loss": 0.5747, + "epoch": 1.36, + "learning_rate": 4.940482592842557e-06, + "loss": 0.6124, "step": 2980 }, { - "epoch": 1.53, - "learning_rate": 2.7301799150519073e-06, - "loss": 0.5835, + "epoch": 1.36, + "learning_rate": 4.9341199081198345e-06, + "loss": 0.6653, "step": 2981 }, { - "epoch": 1.53, - "learning_rate": 2.724464982764087e-06, - "loss": 0.5697, + "epoch": 1.36, + "learning_rate": 4.927759981073609e-06, + "loss": 0.5719, "step": 2982 }, { - "epoch": 1.53, - "learning_rate": 2.718755094661718e-06, - "loss": 0.5726, + "epoch": 1.36, + "learning_rate": 4.921402815165978e-06, + "loss": 0.5875, "step": 2983 }, { - "epoch": 1.53, - "learning_rate": 2.713050254703509e-06, - "loss": 0.5758, + "epoch": 1.36, + "learning_rate": 4.915048413857563e-06, + "loss": 0.5294, "step": 2984 }, { - "epoch": 1.53, - "learning_rate": 2.7073504668446738e-06, - "loss": 0.5886, + "epoch": 1.36, + "learning_rate": 4.9086967806074495e-06, + "loss": 0.6039, "step": 2985 }, { - "epoch": 1.53, - "learning_rate": 2.7016557350369187e-06, - "loss": 0.5881, + "epoch": 1.36, + "learning_rate": 4.902347918873235e-06, + "loss": 0.594, "step": 2986 }, { - "epoch": 1.54, - "learning_rate": 2.695966063228442e-06, - "loss": 0.5713, + "epoch": 1.36, + "learning_rate": 4.896001832111004e-06, + "loss": 0.5618, "step": 2987 }, { - "epoch": 1.54, - "learning_rate": 2.6902814553639443e-06, - "loss": 0.567, + "epoch": 1.36, + "learning_rate": 4.889658523775331e-06, + "loss": 0.6299, "step": 2988 }, { - "epoch": 1.54, - "learning_rate": 2.684601915384606e-06, - "loss": 0.5485, + "epoch": 1.36, + "learning_rate": 4.883317997319273e-06, + "loss": 0.6139, "step": 2989 }, { - "epoch": 1.54, - "learning_rate": 2.678927447228096e-06, - "loss": 0.585, + "epoch": 1.36, + "learning_rate": 4.8769802561943776e-06, + "loss": 0.6038, "step": 2990 }, { - "epoch": 1.54, - "learning_rate": 2.673258054828568e-06, - "loss": 0.5828, + "epoch": 1.36, + "learning_rate": 4.870645303850677e-06, + "loss": 0.6503, "step": 2991 }, { - "epoch": 1.54, - "learning_rate": 2.6675937421166564e-06, - "loss": 0.6185, + "epoch": 1.36, + "learning_rate": 4.864313143736682e-06, + "loss": 0.585, "step": 2992 }, { - "epoch": 1.54, - "learning_rate": 2.661934513019473e-06, - "loss": 0.6008, + "epoch": 1.36, + "learning_rate": 4.857983779299386e-06, + "loss": 0.6206, "step": 2993 }, { - "epoch": 1.54, - "learning_rate": 2.6562803714606033e-06, - "loss": 0.5735, + "epoch": 1.36, + "learning_rate": 4.851657213984261e-06, + "loss": 0.6119, "step": 2994 }, { - "epoch": 1.54, - "learning_rate": 2.650631321360113e-06, - "loss": 0.5803, + "epoch": 1.36, + "learning_rate": 4.845333451235247e-06, + "loss": 0.5597, "step": 2995 }, { - "epoch": 1.54, - "learning_rate": 2.6449873666345316e-06, - "loss": 0.5333, + "epoch": 1.36, + "learning_rate": 4.83901249449477e-06, + "loss": 0.5859, "step": 2996 }, { - "epoch": 1.54, - "learning_rate": 2.639348511196852e-06, - "loss": 0.5522, + "epoch": 1.37, + "learning_rate": 4.832694347203723e-06, + "loss": 0.6146, "step": 2997 }, { - "epoch": 1.54, - "learning_rate": 2.633714758956545e-06, - "loss": 0.5831, + "epoch": 1.37, + "learning_rate": 4.826379012801472e-06, + "loss": 0.635, "step": 2998 }, { - "epoch": 1.54, - "learning_rate": 2.62808611381953e-06, - "loss": 0.5874, + "epoch": 1.37, + "learning_rate": 4.820066494725842e-06, + "loss": 0.6243, "step": 2999 }, { - "epoch": 1.54, - "learning_rate": 2.622462579688192e-06, - "loss": 0.5713, + "epoch": 1.37, + "learning_rate": 4.813756796413144e-06, + "loss": 0.5803, "step": 3000 }, { - "epoch": 1.54, - "learning_rate": 2.6168441604613706e-06, - "loss": 0.5504, + "epoch": 1.37, + "learning_rate": 4.807449921298134e-06, + "loss": 0.5992, "step": 3001 }, { - "epoch": 1.54, - "learning_rate": 2.611230860034362e-06, - "loss": 0.5659, + "epoch": 1.37, + "learning_rate": 4.801145872814044e-06, + "loss": 0.6091, "step": 3002 }, { - "epoch": 1.54, - "learning_rate": 2.605622682298908e-06, - "loss": 0.559, + "epoch": 1.37, + "learning_rate": 4.794844654392562e-06, + "loss": 0.6132, "step": 3003 }, { - "epoch": 1.54, - "learning_rate": 2.6000196311432026e-06, - "loss": 0.5686, + "epoch": 1.37, + "learning_rate": 4.78854626946384e-06, + "loss": 0.6392, "step": 3004 }, { - "epoch": 1.54, - "learning_rate": 2.5944217104518877e-06, - "loss": 0.5536, + "epoch": 1.37, + "learning_rate": 4.782250721456475e-06, + "loss": 0.6124, "step": 3005 }, { - "epoch": 1.55, - "learning_rate": 2.588828924106046e-06, - "loss": 0.5817, + "epoch": 1.37, + "learning_rate": 4.775958013797539e-06, + "loss": 0.5521, "step": 3006 }, { - "epoch": 1.55, - "learning_rate": 2.5832412759831948e-06, - "loss": 0.5923, + "epoch": 1.37, + "learning_rate": 4.769668149912547e-06, + "loss": 0.5839, "step": 3007 }, { - "epoch": 1.55, - "learning_rate": 2.5776587699573007e-06, - "loss": 0.5469, + "epoch": 1.37, + "learning_rate": 4.763381133225461e-06, + "loss": 0.6265, "step": 3008 }, { - "epoch": 1.55, - "learning_rate": 2.5720814098987567e-06, - "loss": 0.5621, + "epoch": 1.37, + "learning_rate": 4.757096967158701e-06, + "loss": 0.5817, "step": 3009 }, { - "epoch": 1.55, - "learning_rate": 2.5665091996743898e-06, - "loss": 0.5665, + "epoch": 1.37, + "learning_rate": 4.750815655133134e-06, + "loss": 0.5522, "step": 3010 }, { - "epoch": 1.55, - "learning_rate": 2.5609421431474557e-06, - "loss": 0.5935, + "epoch": 1.37, + "learning_rate": 4.7445372005680714e-06, + "loss": 0.6443, "step": 3011 }, { - "epoch": 1.55, - "learning_rate": 2.555380244177641e-06, - "loss": 0.5718, + "epoch": 1.37, + "learning_rate": 4.738261606881271e-06, + "loss": 0.6006, "step": 3012 }, { - "epoch": 1.55, - "learning_rate": 2.549823506621052e-06, - "loss": 0.6316, + "epoch": 1.37, + "learning_rate": 4.731988877488935e-06, + "loss": 0.6072, "step": 3013 }, { - "epoch": 1.55, - "learning_rate": 2.5442719343302158e-06, - "loss": 0.5603, + "epoch": 1.37, + "learning_rate": 4.725719015805697e-06, + "loss": 0.6415, "step": 3014 }, { - "epoch": 1.55, - "learning_rate": 2.538725531154087e-06, - "loss": 0.5837, + "epoch": 1.37, + "learning_rate": 4.719452025244641e-06, + "loss": 0.5554, "step": 3015 }, { - "epoch": 1.55, - "learning_rate": 2.533184300938024e-06, - "loss": 0.5524, + "epoch": 1.37, + "learning_rate": 4.713187909217282e-06, + "loss": 0.6244, "step": 3016 }, { - "epoch": 1.55, - "learning_rate": 2.527648247523812e-06, - "loss": 0.5876, + "epoch": 1.37, + "learning_rate": 4.70692667113357e-06, + "loss": 0.5946, "step": 3017 }, { - "epoch": 1.55, - "learning_rate": 2.5221173747496365e-06, - "loss": 0.5287, + "epoch": 1.37, + "learning_rate": 4.700668314401894e-06, + "loss": 0.6133, "step": 3018 }, { - "epoch": 1.55, - "learning_rate": 2.516591686450095e-06, - "loss": 0.5432, + "epoch": 1.38, + "learning_rate": 4.6944128424290706e-06, + "loss": 0.5498, "step": 3019 }, { - "epoch": 1.55, - "learning_rate": 2.511071186456191e-06, - "loss": 0.6123, - "step": 3020 + "epoch": 1.38, + "learning_rate": 4.688160258620339e-06, + "loss": 0.6143, + "step": 3020 }, { - "epoch": 1.55, - "learning_rate": 2.5055558785953304e-06, - "loss": 0.5698, + "epoch": 1.38, + "learning_rate": 4.681910566379377e-06, + "loss": 0.6061, "step": 3021 }, { - "epoch": 1.55, - "learning_rate": 2.500045766691319e-06, - "loss": 0.5995, + "epoch": 1.38, + "learning_rate": 4.6756637691082865e-06, + "loss": 0.5775, "step": 3022 }, { - "epoch": 1.55, - "learning_rate": 2.49454085456436e-06, - "loss": 0.6211, + "epoch": 1.38, + "learning_rate": 4.669419870207591e-06, + "loss": 0.6179, "step": 3023 }, { - "epoch": 1.55, - "learning_rate": 2.4890411460310503e-06, - "loss": 0.5875, + "epoch": 1.38, + "learning_rate": 4.663178873076228e-06, + "loss": 0.6088, "step": 3024 }, { - "epoch": 1.55, - "learning_rate": 2.4835466449043866e-06, - "loss": 0.5659, + "epoch": 1.38, + "learning_rate": 4.6569407811115795e-06, + "loss": 0.5729, "step": 3025 }, { - "epoch": 1.56, - "learning_rate": 2.478057354993744e-06, - "loss": 0.5764, + "epoch": 1.38, + "learning_rate": 4.650705597709417e-06, + "loss": 0.6193, "step": 3026 }, { - "epoch": 1.56, - "learning_rate": 2.472573280104894e-06, - "loss": 0.5731, + "epoch": 1.38, + "learning_rate": 4.644473326263948e-06, + "loss": 0.599, "step": 3027 }, { - "epoch": 1.56, - "learning_rate": 2.4670944240399886e-06, - "loss": 0.5519, + "epoch": 1.38, + "learning_rate": 4.638243970167789e-06, + "loss": 0.6147, "step": 3028 }, { - "epoch": 1.56, - "learning_rate": 2.46162079059756e-06, - "loss": 0.6224, + "epoch": 1.38, + "learning_rate": 4.632017532811971e-06, + "loss": 0.5946, "step": 3029 }, { - "epoch": 1.56, - "learning_rate": 2.456152383572521e-06, - "loss": 0.5519, + "epoch": 1.38, + "learning_rate": 4.625794017585924e-06, + "loss": 0.5861, "step": 3030 }, { - "epoch": 1.56, - "learning_rate": 2.4506892067561625e-06, - "loss": 0.5664, + "epoch": 1.38, + "learning_rate": 4.619573427877515e-06, + "loss": 0.6268, "step": 3031 }, { - "epoch": 1.56, - "learning_rate": 2.4452312639361462e-06, - "loss": 0.5436, + "epoch": 1.38, + "learning_rate": 4.613355767072989e-06, + "loss": 0.6011, "step": 3032 }, { - "epoch": 1.56, - "learning_rate": 2.439778558896505e-06, - "loss": 0.6074, + "epoch": 1.38, + "learning_rate": 4.607141038557013e-06, + "loss": 0.6089, "step": 3033 }, { - "epoch": 1.56, - "learning_rate": 2.434331095417647e-06, - "loss": 0.5293, + "epoch": 1.38, + "learning_rate": 4.600929245712652e-06, + "loss": 0.5856, "step": 3034 }, { - "epoch": 1.56, - "learning_rate": 2.4288888772763385e-06, - "loss": 0.5762, + "epoch": 1.38, + "learning_rate": 4.5947203919213815e-06, + "loss": 0.5802, "step": 3035 }, { - "epoch": 1.56, - "learning_rate": 2.4234519082457096e-06, - "loss": 0.5299, + "epoch": 1.38, + "learning_rate": 4.588514480563057e-06, + "loss": 0.5737, "step": 3036 }, { - "epoch": 1.56, - "learning_rate": 2.4180201920952594e-06, - "loss": 0.5819, + "epoch": 1.38, + "learning_rate": 4.58231151501596e-06, + "loss": 0.5547, "step": 3037 }, { - "epoch": 1.56, - "learning_rate": 2.4125937325908357e-06, - "loss": 0.5756, + "epoch": 1.38, + "learning_rate": 4.5761114986567446e-06, + "loss": 0.6268, "step": 3038 }, { - "epoch": 1.56, - "learning_rate": 2.4071725334946463e-06, - "loss": 0.5714, + "epoch": 1.38, + "learning_rate": 4.569914434860472e-06, + "loss": 0.6339, "step": 3039 }, { - "epoch": 1.56, - "learning_rate": 2.401756598565249e-06, - "loss": 0.5702, + "epoch": 1.38, + "learning_rate": 4.563720327000593e-06, + "loss": 0.6138, "step": 3040 }, { - "epoch": 1.56, - "learning_rate": 2.3963459315575566e-06, - "loss": 0.51, + "epoch": 1.39, + "learning_rate": 4.557529178448949e-06, + "loss": 0.6019, "step": 3041 }, { - "epoch": 1.56, - "learning_rate": 2.3909405362228255e-06, - "loss": 0.5336, + "epoch": 1.39, + "learning_rate": 4.5513409925757744e-06, + "loss": 0.5886, "step": 3042 }, { - "epoch": 1.56, - "learning_rate": 2.3855404163086558e-06, - "loss": 0.6025, + "epoch": 1.39, + "learning_rate": 4.545155772749677e-06, + "loss": 0.6056, "step": 3043 }, { - "epoch": 1.56, - "learning_rate": 2.3801455755589987e-06, - "loss": 0.5776, + "epoch": 1.39, + "learning_rate": 4.538973522337673e-06, + "loss": 0.6029, "step": 3044 }, { - "epoch": 1.57, - "learning_rate": 2.374756017714137e-06, - "loss": 0.5709, + "epoch": 1.39, + "learning_rate": 4.53279424470514e-06, + "loss": 0.6207, "step": 3045 }, { - "epoch": 1.57, - "learning_rate": 2.3693717465106913e-06, - "loss": 0.5405, + "epoch": 1.39, + "learning_rate": 4.52661794321585e-06, + "loss": 0.5575, "step": 3046 }, { - "epoch": 1.57, - "learning_rate": 2.363992765681623e-06, - "loss": 0.6064, + "epoch": 1.39, + "learning_rate": 4.520444621231951e-06, + "loss": 0.6383, "step": 3047 }, { - "epoch": 1.57, - "learning_rate": 2.3586190789562203e-06, - "loss": 0.5437, + "epoch": 1.39, + "learning_rate": 4.514274282113973e-06, + "loss": 0.5973, "step": 3048 }, { - "epoch": 1.57, - "learning_rate": 2.3532506900601017e-06, - "loss": 0.6155, + "epoch": 1.39, + "learning_rate": 4.508106929220809e-06, + "loss": 0.6115, "step": 3049 }, { - "epoch": 1.57, - "learning_rate": 2.347887602715213e-06, - "loss": 0.5973, + "epoch": 1.39, + "learning_rate": 4.501942565909751e-06, + "loss": 0.5967, "step": 3050 }, { - "epoch": 1.57, - "learning_rate": 2.342529820639825e-06, - "loss": 0.5521, + "epoch": 1.39, + "learning_rate": 4.495781195536437e-06, + "loss": 0.6217, "step": 3051 }, { - "epoch": 1.57, - "learning_rate": 2.3371773475485304e-06, - "loss": 0.5774, + "epoch": 1.39, + "learning_rate": 4.489622821454891e-06, + "loss": 0.6145, "step": 3052 }, { - "epoch": 1.57, - "learning_rate": 2.3318301871522366e-06, - "loss": 0.6169, + "epoch": 1.39, + "learning_rate": 4.483467447017504e-06, + "loss": 0.5524, "step": 3053 }, { - "epoch": 1.57, - "learning_rate": 2.32648834315818e-06, - "loss": 0.5735, + "epoch": 1.39, + "learning_rate": 4.477315075575035e-06, + "loss": 0.611, "step": 3054 }, { - "epoch": 1.57, - "learning_rate": 2.3211518192698966e-06, - "loss": 0.6067, + "epoch": 1.39, + "learning_rate": 4.471165710476595e-06, + "loss": 0.5992, "step": 3055 }, { - "epoch": 1.57, - "learning_rate": 2.315820619187241e-06, - "loss": 0.5922, + "epoch": 1.39, + "learning_rate": 4.465019355069685e-06, + "loss": 0.5575, "step": 3056 }, { - "epoch": 1.57, - "learning_rate": 2.3104947466063785e-06, - "loss": 0.604, + "epoch": 1.39, + "learning_rate": 4.458876012700141e-06, + "loss": 0.6445, "step": 3057 }, { - "epoch": 1.57, - "learning_rate": 2.305174205219779e-06, - "loss": 0.5645, + "epoch": 1.39, + "learning_rate": 4.4527356867121716e-06, + "loss": 0.6, "step": 3058 }, { - "epoch": 1.57, - "learning_rate": 2.2998589987162124e-06, - "loss": 0.6121, + "epoch": 1.39, + "learning_rate": 4.446598380448343e-06, + "loss": 0.5867, "step": 3059 }, { - "epoch": 1.57, - "learning_rate": 2.2945491307807534e-06, - "loss": 0.5901, + "epoch": 1.39, + "learning_rate": 4.4404640972495806e-06, + "loss": 0.6046, "step": 3060 }, { - "epoch": 1.57, - "learning_rate": 2.289244605094777e-06, - "loss": 0.5598, + "epoch": 1.39, + "learning_rate": 4.434332840455151e-06, + "loss": 0.6125, "step": 3061 }, { - "epoch": 1.57, - "learning_rate": 2.2839454253359504e-06, - "loss": 0.5691, + "epoch": 1.39, + "learning_rate": 4.428204613402688e-06, + "loss": 0.6191, "step": 3062 }, { - "epoch": 1.57, - "learning_rate": 2.278651595178234e-06, - "loss": 0.5809, + "epoch": 1.4, + "learning_rate": 4.422079419428167e-06, + "loss": 0.5962, "step": 3063 }, { - "epoch": 1.57, - "learning_rate": 2.273363118291889e-06, - "loss": 0.5793, + "epoch": 1.4, + "learning_rate": 4.415957261865917e-06, + "loss": 0.5839, "step": 3064 }, { - "epoch": 1.58, - "learning_rate": 2.2680799983434532e-06, - "loss": 0.5725, + "epoch": 1.4, + "learning_rate": 4.409838144048615e-06, + "loss": 0.5885, "step": 3065 }, { - "epoch": 1.58, - "learning_rate": 2.2628022389957525e-06, - "loss": 0.5841, + "epoch": 1.4, + "learning_rate": 4.40372206930728e-06, + "loss": 0.5852, "step": 3066 }, { - "epoch": 1.58, - "learning_rate": 2.257529843907906e-06, - "loss": 0.5398, + "epoch": 1.4, + "learning_rate": 4.397609040971272e-06, + "loss": 0.6322, "step": 3067 }, { - "epoch": 1.58, - "learning_rate": 2.2522628167353023e-06, - "loss": 0.5494, + "epoch": 1.4, + "learning_rate": 4.391499062368297e-06, + "loss": 0.6157, "step": 3068 }, { - "epoch": 1.58, - "learning_rate": 2.2470011611296127e-06, - "loss": 0.5657, + "epoch": 1.4, + "learning_rate": 4.385392136824403e-06, + "loss": 0.558, "step": 3069 }, { - "epoch": 1.58, - "learning_rate": 2.241744880738784e-06, - "loss": 0.6107, + "epoch": 1.4, + "learning_rate": 4.379288267663973e-06, + "loss": 0.6027, "step": 3070 }, { - "epoch": 1.58, - "learning_rate": 2.2364939792070385e-06, - "loss": 0.5737, + "epoch": 1.4, + "learning_rate": 4.373187458209716e-06, + "loss": 0.5515, "step": 3071 }, { - "epoch": 1.58, - "learning_rate": 2.2312484601748652e-06, - "loss": 0.5853, + "epoch": 1.4, + "learning_rate": 4.367089711782701e-06, + "loss": 0.5521, "step": 3072 }, { - "epoch": 1.58, - "learning_rate": 2.2260083272790213e-06, - "loss": 0.5479, + "epoch": 1.4, + "learning_rate": 4.360995031702303e-06, + "loss": 0.5981, "step": 3073 }, { - "epoch": 1.58, - "learning_rate": 2.220773584152538e-06, - "loss": 0.5721, + "epoch": 1.4, + "learning_rate": 4.3549034212862396e-06, + "loss": 0.6199, "step": 3074 }, { - "epoch": 1.58, - "learning_rate": 2.2155442344247e-06, - "loss": 0.5781, + "epoch": 1.4, + "learning_rate": 4.348814883850566e-06, + "loss": 0.6001, "step": 3075 }, { - "epoch": 1.58, - "learning_rate": 2.2103202817210555e-06, - "loss": 0.5958, + "epoch": 1.4, + "learning_rate": 4.342729422709645e-06, + "loss": 0.5824, "step": 3076 }, { - "epoch": 1.58, - "learning_rate": 2.205101729663417e-06, - "loss": 0.5581, + "epoch": 1.4, + "learning_rate": 4.3366470411761794e-06, + "loss": 0.6147, "step": 3077 }, { - "epoch": 1.58, - "learning_rate": 2.1998885818698434e-06, - "loss": 0.6205, + "epoch": 1.4, + "learning_rate": 4.3305677425611904e-06, + "loss": 0.6075, "step": 3078 }, { - "epoch": 1.58, - "learning_rate": 2.1946808419546516e-06, - "loss": 0.5861, + "epoch": 1.4, + "learning_rate": 4.324491530174026e-06, + "loss": 0.5732, "step": 3079 }, { - "epoch": 1.58, - "learning_rate": 2.189478513528408e-06, - "loss": 0.5728, + "epoch": 1.4, + "learning_rate": 4.318418407322338e-06, + "loss": 0.6012, "step": 3080 }, { - "epoch": 1.58, - "learning_rate": 2.1842816001979293e-06, - "loss": 0.5452, + "epoch": 1.4, + "learning_rate": 4.312348377312125e-06, + "loss": 0.6562, "step": 3081 }, { - "epoch": 1.58, - "learning_rate": 2.1790901055662737e-06, - "loss": 0.6074, + "epoch": 1.4, + "learning_rate": 4.306281443447672e-06, + "loss": 0.6392, "step": 3082 }, { - "epoch": 1.58, - "learning_rate": 2.1739040332327454e-06, - "loss": 0.5636, + "epoch": 1.4, + "learning_rate": 4.3002176090315975e-06, + "loss": 0.5839, "step": 3083 }, { - "epoch": 1.59, - "learning_rate": 2.1687233867928927e-06, - "loss": 0.6031, + "epoch": 1.41, + "learning_rate": 4.294156877364824e-06, + "loss": 0.6122, "step": 3084 }, { - "epoch": 1.59, - "learning_rate": 2.163548169838495e-06, - "loss": 0.5724, + "epoch": 1.41, + "learning_rate": 4.288099251746597e-06, + "loss": 0.6237, "step": 3085 }, { - "epoch": 1.59, - "learning_rate": 2.15837838595757e-06, - "loss": 0.5652, + "epoch": 1.41, + "learning_rate": 4.282044735474451e-06, + "loss": 0.6289, "step": 3086 }, { - "epoch": 1.59, - "learning_rate": 2.1532140387343736e-06, - "loss": 0.532, + "epoch": 1.41, + "learning_rate": 4.2759933318442435e-06, + "loss": 0.6123, "step": 3087 }, { - "epoch": 1.59, - "learning_rate": 2.1480551317493847e-06, - "loss": 0.5892, + "epoch": 1.41, + "learning_rate": 4.269945044150135e-06, + "loss": 0.624, "step": 3088 }, { - "epoch": 1.59, - "learning_rate": 2.142901668579316e-06, - "loss": 0.5905, + "epoch": 1.41, + "learning_rate": 4.263899875684585e-06, + "loss": 0.5979, "step": 3089 }, { - "epoch": 1.59, - "learning_rate": 2.137753652797102e-06, - "loss": 0.5353, + "epoch": 1.41, + "learning_rate": 4.257857829738362e-06, + "loss": 0.5862, "step": 3090 }, { - "epoch": 1.59, - "learning_rate": 2.132611087971904e-06, - "loss": 0.5737, + "epoch": 1.41, + "learning_rate": 4.2518189096005315e-06, + "loss": 0.6138, "step": 3091 }, { - "epoch": 1.59, - "learning_rate": 2.1274739776691013e-06, - "loss": 0.5752, + "epoch": 1.41, + "learning_rate": 4.2457831185584505e-06, + "loss": 0.6191, "step": 3092 }, { - "epoch": 1.59, - "learning_rate": 2.1223423254502896e-06, - "loss": 0.5707, + "epoch": 1.41, + "learning_rate": 4.2397504598977825e-06, + "loss": 0.6492, "step": 3093 }, { - "epoch": 1.59, - "learning_rate": 2.117216134873291e-06, - "loss": 0.5895, + "epoch": 1.41, + "learning_rate": 4.233720936902483e-06, + "loss": 0.6237, "step": 3094 }, { - "epoch": 1.59, - "learning_rate": 2.1120954094921264e-06, - "loss": 0.5483, + "epoch": 1.41, + "learning_rate": 4.227694552854802e-06, + "loss": 0.6418, "step": 3095 }, { - "epoch": 1.59, - "learning_rate": 2.106980152857041e-06, - "loss": 0.5883, + "epoch": 1.41, + "learning_rate": 4.221671311035269e-06, + "loss": 0.63, "step": 3096 }, { - "epoch": 1.59, - "learning_rate": 2.1018703685144804e-06, - "loss": 0.5837, + "epoch": 1.41, + "learning_rate": 4.215651214722725e-06, + "loss": 0.6194, "step": 3097 }, { - "epoch": 1.59, - "learning_rate": 2.096766060007096e-06, - "loss": 0.566, + "epoch": 1.41, + "learning_rate": 4.209634267194279e-06, + "loss": 0.5897, "step": 3098 }, { - "epoch": 1.59, - "learning_rate": 2.0916672308737464e-06, - "loss": 0.5824, + "epoch": 1.41, + "learning_rate": 4.203620471725334e-06, + "loss": 0.5059, "step": 3099 }, { - "epoch": 1.59, - "learning_rate": 2.08657388464949e-06, - "loss": 0.5676, + "epoch": 1.41, + "learning_rate": 4.1976098315895765e-06, + "loss": 0.5509, "step": 3100 }, { - "epoch": 1.59, - "learning_rate": 2.081486024865582e-06, - "loss": 0.6135, + "epoch": 1.41, + "learning_rate": 4.19160235005898e-06, + "loss": 0.5837, "step": 3101 }, { - "epoch": 1.59, - "learning_rate": 2.076403655049478e-06, - "loss": 0.562, + "epoch": 1.41, + "learning_rate": 4.185598030403782e-06, + "loss": 0.5909, "step": 3102 }, { - "epoch": 1.59, - "learning_rate": 2.0713267787248204e-06, - "loss": 0.5588, + "epoch": 1.41, + "learning_rate": 4.179596875892526e-06, + "loss": 0.6515, "step": 3103 }, { - "epoch": 1.6, - "learning_rate": 2.066255399411453e-06, - "loss": 0.5697, + "epoch": 1.41, + "learning_rate": 4.1735988897920044e-06, + "loss": 0.5966, "step": 3104 }, { - "epoch": 1.6, - "learning_rate": 2.0611895206253974e-06, - "loss": 0.5247, + "epoch": 1.41, + "learning_rate": 4.167604075367303e-06, + "loss": 0.5465, "step": 3105 }, { - "epoch": 1.6, - "learning_rate": 2.0561291458788736e-06, - "loss": 0.5792, + "epoch": 1.42, + "learning_rate": 4.1616124358817744e-06, + "loss": 0.5856, "step": 3106 }, { - "epoch": 1.6, - "learning_rate": 2.051074278680274e-06, - "loss": 0.5889, + "epoch": 1.42, + "learning_rate": 4.155623974597044e-06, + "loss": 0.5537, "step": 3107 }, { - "epoch": 1.6, - "learning_rate": 2.04602492253418e-06, - "loss": 0.514, + "epoch": 1.42, + "learning_rate": 4.149638694773008e-06, + "loss": 0.5961, "step": 3108 }, { - "epoch": 1.6, - "learning_rate": 2.040981080941349e-06, - "loss": 0.511, + "epoch": 1.42, + "learning_rate": 4.143656599667829e-06, + "loss": 0.6226, "step": 3109 }, { - "epoch": 1.6, - "learning_rate": 2.0359427573987143e-06, - "loss": 0.6096, + "epoch": 1.42, + "learning_rate": 4.1376776925379415e-06, + "loss": 0.6007, "step": 3110 }, { - "epoch": 1.6, - "learning_rate": 2.0309099553993884e-06, - "loss": 0.6139, + "epoch": 1.42, + "learning_rate": 4.131701976638032e-06, + "loss": 0.6046, "step": 3111 }, { - "epoch": 1.6, - "learning_rate": 2.025882678432649e-06, - "loss": 0.5736, + "epoch": 1.42, + "learning_rate": 4.125729455221061e-06, + "loss": 0.5916, "step": 3112 }, { - "epoch": 1.6, - "learning_rate": 2.0208609299839465e-06, - "loss": 0.5927, + "epoch": 1.42, + "learning_rate": 4.119760131538248e-06, + "loss": 0.608, "step": 3113 }, { - "epoch": 1.6, - "learning_rate": 2.0158447135349023e-06, - "loss": 0.6133, + "epoch": 1.42, + "learning_rate": 4.113794008839072e-06, + "loss": 0.5631, "step": 3114 }, { - "epoch": 1.6, - "learning_rate": 2.0108340325632935e-06, - "loss": 0.5674, + "epoch": 1.42, + "learning_rate": 4.10783109037126e-06, + "loss": 0.6333, "step": 3115 }, { - "epoch": 1.6, - "learning_rate": 2.00582889054307e-06, - "loss": 0.5626, + "epoch": 1.42, + "learning_rate": 4.101871379380815e-06, + "loss": 0.573, "step": 3116 }, { - "epoch": 1.6, - "learning_rate": 2.000829290944334e-06, - "loss": 0.5648, + "epoch": 1.42, + "learning_rate": 4.095914879111973e-06, + "loss": 0.5432, "step": 3117 }, { - "epoch": 1.6, - "learning_rate": 1.995835237233347e-06, - "loss": 0.5603, + "epoch": 1.42, + "learning_rate": 4.089961592807231e-06, + "loss": 0.5697, "step": 3118 }, { - "epoch": 1.6, - "learning_rate": 1.9908467328725233e-06, - "loss": 0.5448, + "epoch": 1.42, + "learning_rate": 4.084011523707341e-06, + "loss": 0.5953, "step": 3119 }, { - "epoch": 1.6, - "learning_rate": 1.9858637813204352e-06, - "loss": 0.5482, + "epoch": 1.42, + "learning_rate": 4.078064675051299e-06, + "loss": 0.6023, "step": 3120 }, { - "epoch": 1.6, - "learning_rate": 1.9808863860317996e-06, - "loss": 0.5707, + "epoch": 1.42, + "learning_rate": 4.072121050076338e-06, + "loss": 0.6409, "step": 3121 }, { - "epoch": 1.6, - "learning_rate": 1.975914550457485e-06, - "loss": 0.571, + "epoch": 1.42, + "learning_rate": 4.066180652017963e-06, + "loss": 0.5129, "step": 3122 }, { - "epoch": 1.61, - "learning_rate": 1.9709482780445023e-06, - "loss": 0.5651, + "epoch": 1.42, + "learning_rate": 4.06024348410989e-06, + "loss": 0.6261, "step": 3123 }, { - "epoch": 1.61, - "learning_rate": 1.96598757223601e-06, - "loss": 0.5292, + "epoch": 1.42, + "learning_rate": 4.054309549584101e-06, + "loss": 0.5877, "step": 3124 }, { - "epoch": 1.61, - "learning_rate": 1.961032436471301e-06, - "loss": 0.5527, + "epoch": 1.42, + "learning_rate": 4.048378851670806e-06, + "loss": 0.6122, "step": 3125 }, { - "epoch": 1.61, - "learning_rate": 1.956082874185813e-06, - "loss": 0.5985, + "epoch": 1.42, + "learning_rate": 4.0424513935984584e-06, + "loss": 0.5636, "step": 3126 }, { - "epoch": 1.61, - "learning_rate": 1.951138888811115e-06, - "loss": 0.5626, + "epoch": 1.42, + "learning_rate": 4.036527178593739e-06, + "loss": 0.59, "step": 3127 }, { - "epoch": 1.61, - "learning_rate": 1.9462004837749117e-06, - "loss": 0.5187, + "epoch": 1.43, + "learning_rate": 4.030606209881581e-06, + "loss": 0.6108, "step": 3128 }, { - "epoch": 1.61, - "learning_rate": 1.9412676625010362e-06, - "loss": 0.564, + "epoch": 1.43, + "learning_rate": 4.0246884906851295e-06, + "loss": 0.5714, "step": 3129 }, { - "epoch": 1.61, - "learning_rate": 1.9363404284094533e-06, - "loss": 0.5999, + "epoch": 1.43, + "learning_rate": 4.018774024225774e-06, + "loss": 0.5637, "step": 3130 }, { - "epoch": 1.61, - "learning_rate": 1.9314187849162523e-06, - "loss": 0.561, + "epoch": 1.43, + "learning_rate": 4.01286281372313e-06, + "loss": 0.6371, "step": 3131 }, { - "epoch": 1.61, - "learning_rate": 1.926502735433646e-06, - "loss": 0.5979, + "epoch": 1.43, + "learning_rate": 4.006954862395044e-06, + "loss": 0.553, "step": 3132 }, { - "epoch": 1.61, - "learning_rate": 1.9215922833699743e-06, - "loss": 0.5505, + "epoch": 1.43, + "learning_rate": 4.001050173457577e-06, + "loss": 0.6187, "step": 3133 }, { - "epoch": 1.61, - "learning_rate": 1.916687432129688e-06, - "loss": 0.5479, + "epoch": 1.43, + "learning_rate": 3.995148750125026e-06, + "loss": 0.5837, "step": 3134 }, { - "epoch": 1.61, - "learning_rate": 1.911788185113359e-06, - "loss": 0.6287, + "epoch": 1.43, + "learning_rate": 3.989250595609906e-06, + "loss": 0.5786, "step": 3135 }, { - "epoch": 1.61, - "learning_rate": 1.9068945457176767e-06, - "loss": 0.5833, + "epoch": 1.43, + "learning_rate": 3.9833557131229515e-06, + "loss": 0.6106, "step": 3136 }, { - "epoch": 1.61, - "learning_rate": 1.9020065173354386e-06, - "loss": 0.5831, + "epoch": 1.43, + "learning_rate": 3.97746410587312e-06, + "loss": 0.5525, "step": 3137 }, { - "epoch": 1.61, - "learning_rate": 1.8971241033555521e-06, - "loss": 0.5837, + "epoch": 1.43, + "learning_rate": 3.971575777067583e-06, + "loss": 0.5924, "step": 3138 }, { - "epoch": 1.61, - "learning_rate": 1.8922473071630342e-06, - "loss": 0.6018, + "epoch": 1.43, + "learning_rate": 3.965690729911723e-06, + "loss": 0.5984, "step": 3139 }, { - "epoch": 1.61, - "learning_rate": 1.887376132139005e-06, - "loss": 0.5809, + "epoch": 1.43, + "learning_rate": 3.95980896760914e-06, + "loss": 0.5618, "step": 3140 }, { - "epoch": 1.61, - "learning_rate": 1.882510581660687e-06, - "loss": 0.5837, + "epoch": 1.43, + "learning_rate": 3.953930493361656e-06, + "loss": 0.5796, "step": 3141 }, { - "epoch": 1.62, - "learning_rate": 1.8776506591014054e-06, - "loss": 0.5679, + "epoch": 1.43, + "learning_rate": 3.948055310369285e-06, + "loss": 0.6074, "step": 3142 }, { - "epoch": 1.62, - "learning_rate": 1.872796367830584e-06, - "loss": 0.5643, + "epoch": 1.43, + "learning_rate": 3.942183421830258e-06, + "loss": 0.572, "step": 3143 }, { - "epoch": 1.62, - "learning_rate": 1.8679477112137412e-06, - "loss": 0.5359, + "epoch": 1.43, + "learning_rate": 3.936314830941016e-06, + "loss": 0.6384, "step": 3144 }, { - "epoch": 1.62, - "learning_rate": 1.8631046926124852e-06, - "loss": 0.568, + "epoch": 1.43, + "learning_rate": 3.930449540896203e-06, + "loss": 0.5763, "step": 3145 }, { - "epoch": 1.62, - "learning_rate": 1.8582673153845233e-06, - "loss": 0.6149, + "epoch": 1.43, + "learning_rate": 3.924587554888654e-06, + "loss": 0.5823, "step": 3146 }, { - "epoch": 1.62, - "learning_rate": 1.8534355828836447e-06, - "loss": 0.5884, + "epoch": 1.43, + "learning_rate": 3.91872887610943e-06, + "loss": 0.5742, "step": 3147 }, { - "epoch": 1.62, - "learning_rate": 1.8486094984597268e-06, - "loss": 0.5688, + "epoch": 1.43, + "learning_rate": 3.9128735077477674e-06, + "loss": 0.599, "step": 3148 }, { - "epoch": 1.62, - "learning_rate": 1.8437890654587343e-06, - "loss": 0.5994, + "epoch": 1.43, + "learning_rate": 3.9070214529911144e-06, + "loss": 0.5813, "step": 3149 }, { - "epoch": 1.62, - "learning_rate": 1.838974287222708e-06, - "loss": 0.6012, + "epoch": 1.44, + "learning_rate": 3.901172715025111e-06, + "loss": 0.604, "step": 3150 }, { - "epoch": 1.62, - "learning_rate": 1.8341651670897742e-06, - "loss": 0.5594, + "epoch": 1.44, + "learning_rate": 3.895327297033598e-06, + "loss": 0.5852, "step": 3151 }, { - "epoch": 1.62, - "learning_rate": 1.8293617083941285e-06, - "loss": 0.5592, + "epoch": 1.44, + "learning_rate": 3.8894852021985895e-06, + "loss": 0.5702, "step": 3152 }, { - "epoch": 1.62, - "learning_rate": 1.8245639144660532e-06, - "loss": 0.5348, + "epoch": 1.44, + "learning_rate": 3.88364643370032e-06, + "loss": 0.6185, "step": 3153 }, { - "epoch": 1.62, - "learning_rate": 1.8197717886318932e-06, - "loss": 0.5931, + "epoch": 1.44, + "learning_rate": 3.877810994717188e-06, + "loss": 0.5459, "step": 3154 }, { - "epoch": 1.62, - "learning_rate": 1.8149853342140644e-06, - "loss": 0.6064, + "epoch": 1.44, + "learning_rate": 3.871978888425792e-06, + "loss": 0.5918, "step": 3155 }, { - "epoch": 1.62, - "learning_rate": 1.8102045545310588e-06, - "loss": 0.5432, + "epoch": 1.44, + "learning_rate": 3.866150118000912e-06, + "loss": 0.5625, "step": 3156 }, { - "epoch": 1.62, - "learning_rate": 1.8054294528974249e-06, - "loss": 0.5442, + "epoch": 1.44, + "learning_rate": 3.8603246866155195e-06, + "loss": 0.6206, "step": 3157 }, { - "epoch": 1.62, - "learning_rate": 1.8006600326237788e-06, - "loss": 0.616, + "epoch": 1.44, + "learning_rate": 3.8545025974407545e-06, + "loss": 0.6229, "step": 3158 }, { - "epoch": 1.62, - "learning_rate": 1.7958962970167982e-06, - "loss": 0.5876, + "epoch": 1.44, + "learning_rate": 3.848683853645948e-06, + "loss": 0.576, "step": 3159 }, { - "epoch": 1.62, - "learning_rate": 1.791138249379215e-06, - "loss": 0.6108, - "step": 3160 + "epoch": 1.44, + "learning_rate": 3.84286845839861e-06, + "loss": 0.6262, + "step": 3160 }, { - "epoch": 1.62, - "learning_rate": 1.7863858930098244e-06, - "loss": 0.5743, + "epoch": 1.44, + "learning_rate": 3.837056414864423e-06, + "loss": 0.621, "step": 3161 }, { - "epoch": 1.63, - "learning_rate": 1.781639231203467e-06, - "loss": 0.5438, + "epoch": 1.44, + "learning_rate": 3.8312477262072465e-06, + "loss": 0.5682, "step": 3162 }, { - "epoch": 1.63, - "learning_rate": 1.7768982672510481e-06, - "loss": 0.6389, + "epoch": 1.44, + "learning_rate": 3.82544239558912e-06, + "loss": 0.6769, "step": 3163 }, { - "epoch": 1.63, - "learning_rate": 1.772163004439511e-06, - "loss": 0.4996, + "epoch": 1.44, + "learning_rate": 3.8196404261702415e-06, + "loss": 0.5634, "step": 3164 }, { - "epoch": 1.63, - "learning_rate": 1.7674334460518484e-06, - "loss": 0.5393, + "epoch": 1.44, + "learning_rate": 3.81384182110899e-06, + "loss": 0.5856, "step": 3165 }, { - "epoch": 1.63, - "learning_rate": 1.7627095953671058e-06, - "loss": 0.5778, + "epoch": 1.44, + "learning_rate": 3.808046583561912e-06, + "loss": 0.5608, "step": 3166 }, { - "epoch": 1.63, - "learning_rate": 1.7579914556603617e-06, - "loss": 0.5978, + "epoch": 1.44, + "learning_rate": 3.80225471668372e-06, + "loss": 0.5652, "step": 3167 }, { - "epoch": 1.63, - "learning_rate": 1.7532790302027424e-06, - "loss": 0.5891, + "epoch": 1.44, + "learning_rate": 3.796466223627281e-06, + "loss": 0.5962, "step": 3168 }, { - "epoch": 1.63, - "learning_rate": 1.7485723222614059e-06, - "loss": 0.5784, + "epoch": 1.44, + "learning_rate": 3.7906811075436488e-06, + "loss": 0.6493, "step": 3169 }, { - "epoch": 1.63, - "learning_rate": 1.7438713350995529e-06, - "loss": 0.5635, + "epoch": 1.44, + "learning_rate": 3.784899371582017e-06, + "loss": 0.61, "step": 3170 }, { - "epoch": 1.63, - "learning_rate": 1.7391760719764116e-06, - "loss": 0.5475, + "epoch": 1.44, + "learning_rate": 3.7791210188897486e-06, + "loss": 0.6078, "step": 3171 }, { - "epoch": 1.63, - "learning_rate": 1.7344865361472452e-06, - "loss": 0.5422, + "epoch": 1.45, + "learning_rate": 3.7733460526123634e-06, + "loss": 0.6198, "step": 3172 }, { - "epoch": 1.63, - "learning_rate": 1.729802730863348e-06, - "loss": 0.583, + "epoch": 1.45, + "learning_rate": 3.7675744758935427e-06, + "loss": 0.5536, "step": 3173 }, { - "epoch": 1.63, - "learning_rate": 1.7251246593720361e-06, - "loss": 0.5876, + "epoch": 1.45, + "learning_rate": 3.7618062918751076e-06, + "loss": 0.5844, "step": 3174 }, { - "epoch": 1.63, - "learning_rate": 1.720452324916656e-06, - "loss": 0.5427, + "epoch": 1.45, + "learning_rate": 3.756041503697053e-06, + "loss": 0.6036, "step": 3175 }, { - "epoch": 1.63, - "learning_rate": 1.7157857307365733e-06, - "loss": 0.5471, + "epoch": 1.45, + "learning_rate": 3.750280114497514e-06, + "loss": 0.5483, "step": 3176 }, { - "epoch": 1.63, - "learning_rate": 1.7111248800671732e-06, - "loss": 0.5728, + "epoch": 1.45, + "learning_rate": 3.7445221274127695e-06, + "loss": 0.579, "step": 3177 }, { - "epoch": 1.63, - "learning_rate": 1.7064697761398607e-06, - "loss": 0.5723, + "epoch": 1.45, + "learning_rate": 3.738767545577259e-06, + "loss": 0.5698, "step": 3178 }, { - "epoch": 1.63, - "learning_rate": 1.7018204221820544e-06, - "loss": 0.5884, + "epoch": 1.45, + "learning_rate": 3.733016372123559e-06, + "loss": 0.5978, "step": 3179 }, { - "epoch": 1.63, - "learning_rate": 1.697176821417189e-06, - "loss": 0.5884, + "epoch": 1.45, + "learning_rate": 3.7272686101823973e-06, + "loss": 0.6274, "step": 3180 }, { - "epoch": 1.64, - "learning_rate": 1.6925389770647105e-06, - "loss": 0.5166, + "epoch": 1.45, + "learning_rate": 3.7215242628826397e-06, + "loss": 0.5715, "step": 3181 }, { - "epoch": 1.64, - "learning_rate": 1.6879068923400676e-06, - "loss": 0.5997, + "epoch": 1.45, + "learning_rate": 3.715783333351298e-06, + "loss": 0.579, "step": 3182 }, { - "epoch": 1.64, - "learning_rate": 1.6832805704547272e-06, - "loss": 0.5981, + "epoch": 1.45, + "learning_rate": 3.7100458247135163e-06, + "loss": 0.6423, "step": 3183 }, { - "epoch": 1.64, - "learning_rate": 1.6786600146161503e-06, - "loss": 0.5845, + "epoch": 1.45, + "learning_rate": 3.704311740092581e-06, + "loss": 0.5441, "step": 3184 }, { - "epoch": 1.64, - "learning_rate": 1.6740452280278087e-06, - "loss": 0.5897, + "epoch": 1.45, + "learning_rate": 3.6985810826099165e-06, + "loss": 0.5519, "step": 3185 }, { - "epoch": 1.64, - "learning_rate": 1.6694362138891674e-06, - "loss": 0.5889, + "epoch": 1.45, + "learning_rate": 3.6928538553850813e-06, + "loss": 0.6124, "step": 3186 }, { - "epoch": 1.64, - "learning_rate": 1.6648329753956917e-06, - "loss": 0.5754, + "epoch": 1.45, + "learning_rate": 3.6871300615357555e-06, + "loss": 0.6309, "step": 3187 }, { - "epoch": 1.64, - "learning_rate": 1.660235515738844e-06, - "loss": 0.571, + "epoch": 1.45, + "learning_rate": 3.681409704177772e-06, + "loss": 0.5684, "step": 3188 }, { - "epoch": 1.64, - "learning_rate": 1.655643838106078e-06, - "loss": 0.6016, + "epoch": 1.45, + "learning_rate": 3.67569278642507e-06, + "loss": 0.5815, "step": 3189 }, { - "epoch": 1.64, - "learning_rate": 1.6510579456808417e-06, - "loss": 0.5731, + "epoch": 1.45, + "learning_rate": 3.669979311389731e-06, + "loss": 0.6034, "step": 3190 }, { - "epoch": 1.64, - "learning_rate": 1.6464778416425675e-06, - "loss": 0.5315, + "epoch": 1.45, + "learning_rate": 3.664269282181958e-06, + "loss": 0.6016, "step": 3191 }, { - "epoch": 1.64, - "learning_rate": 1.6419035291666773e-06, - "loss": 0.5597, + "epoch": 1.45, + "learning_rate": 3.6585627019100824e-06, + "loss": 0.6117, "step": 3192 }, { - "epoch": 1.64, - "learning_rate": 1.6373350114245823e-06, - "loss": 0.556, + "epoch": 1.45, + "learning_rate": 3.652859573680542e-06, + "loss": 0.5986, "step": 3193 }, { - "epoch": 1.64, - "learning_rate": 1.6327722915836652e-06, - "loss": 0.5685, + "epoch": 1.46, + "learning_rate": 3.6471599005979208e-06, + "loss": 0.5796, "step": 3194 }, { - "epoch": 1.64, - "learning_rate": 1.6282153728073024e-06, - "loss": 0.5675, + "epoch": 1.46, + "learning_rate": 3.6414636857649e-06, + "loss": 0.6075, "step": 3195 }, { - "epoch": 1.64, - "learning_rate": 1.6236642582548368e-06, - "loss": 0.5848, + "epoch": 1.46, + "learning_rate": 3.635770932282291e-06, + "loss": 0.6078, "step": 3196 }, { - "epoch": 1.64, - "learning_rate": 1.6191189510815942e-06, - "loss": 0.5631, + "epoch": 1.46, + "learning_rate": 3.630081643249014e-06, + "loss": 0.585, "step": 3197 }, { - "epoch": 1.64, - "learning_rate": 1.6145794544388693e-06, - "loss": 0.5533, + "epoch": 1.46, + "learning_rate": 3.6243958217621123e-06, + "loss": 0.5726, "step": 3198 }, { - "epoch": 1.64, - "learning_rate": 1.6100457714739327e-06, - "loss": 0.5526, + "epoch": 1.46, + "learning_rate": 3.6187134709167227e-06, + "loss": 0.5568, "step": 3199 }, { - "epoch": 1.64, - "learning_rate": 1.6055179053300207e-06, - "loss": 0.5717, + "epoch": 1.46, + "learning_rate": 3.6130345938061217e-06, + "loss": 0.5955, "step": 3200 }, { - "epoch": 1.65, - "learning_rate": 1.6009958591463403e-06, - "loss": 0.5819, + "epoch": 1.46, + "learning_rate": 3.6073591935216656e-06, + "loss": 0.6115, "step": 3201 }, { - "epoch": 1.65, - "learning_rate": 1.596479636058057e-06, - "loss": 0.5958, + "epoch": 1.46, + "learning_rate": 3.6016872731528374e-06, + "loss": 0.5917, "step": 3202 }, { - "epoch": 1.65, - "learning_rate": 1.5919692391963103e-06, - "loss": 0.5439, + "epoch": 1.46, + "learning_rate": 3.596018835787216e-06, + "loss": 0.5924, "step": 3203 }, { - "epoch": 1.65, - "learning_rate": 1.587464671688187e-06, - "loss": 0.5531, + "epoch": 1.46, + "learning_rate": 3.5903538845104936e-06, + "loss": 0.6086, "step": 3204 }, { - "epoch": 1.65, - "learning_rate": 1.5829659366567462e-06, - "loss": 0.5663, + "epoch": 1.46, + "learning_rate": 3.584692422406447e-06, + "loss": 0.6283, "step": 3205 }, { - "epoch": 1.65, - "learning_rate": 1.578473037220991e-06, - "loss": 0.5354, + "epoch": 1.46, + "learning_rate": 3.579034452556981e-06, + "loss": 0.5874, "step": 3206 }, { - "epoch": 1.65, - "learning_rate": 1.5739859764958864e-06, - "loss": 0.5652, + "epoch": 1.46, + "learning_rate": 3.573379978042071e-06, + "loss": 0.578, "step": 3207 }, { - "epoch": 1.65, - "learning_rate": 1.5695047575923462e-06, - "loss": 0.5553, + "epoch": 1.46, + "learning_rate": 3.567729001939807e-06, + "loss": 0.6447, "step": 3208 }, { - "epoch": 1.65, - "learning_rate": 1.5650293836172325e-06, - "loss": 0.5355, + "epoch": 1.46, + "learning_rate": 3.562081527326371e-06, + "loss": 0.564, "step": 3209 }, { - "epoch": 1.65, - "learning_rate": 1.5605598576733604e-06, - "loss": 0.5918, + "epoch": 1.46, + "learning_rate": 3.556437557276036e-06, + "loss": 0.5997, "step": 3210 }, { - "epoch": 1.65, - "learning_rate": 1.5560961828594845e-06, - "loss": 0.5623, + "epoch": 1.46, + "learning_rate": 3.5507970948611727e-06, + "loss": 0.6027, "step": 3211 }, { - "epoch": 1.65, - "learning_rate": 1.5516383622703047e-06, - "loss": 0.5824, + "epoch": 1.46, + "learning_rate": 3.54516014315223e-06, + "loss": 0.554, "step": 3212 }, { - "epoch": 1.65, - "learning_rate": 1.5471863989964665e-06, - "loss": 0.5715, + "epoch": 1.46, + "learning_rate": 3.5395267052177675e-06, + "loss": 0.5476, "step": 3213 }, { - "epoch": 1.65, - "learning_rate": 1.5427402961245474e-06, - "loss": 0.5869, + "epoch": 1.46, + "learning_rate": 3.5338967841244075e-06, + "loss": 0.6044, "step": 3214 }, { - "epoch": 1.65, - "learning_rate": 1.5383000567370698e-06, - "loss": 0.536, + "epoch": 1.46, + "learning_rate": 3.5282703829368757e-06, + "loss": 0.5955, "step": 3215 }, { - "epoch": 1.65, - "learning_rate": 1.5338656839124844e-06, - "loss": 0.5718, + "epoch": 1.47, + "learning_rate": 3.522647504717973e-06, + "loss": 0.5607, "step": 3216 }, { - "epoch": 1.65, - "learning_rate": 1.529437180725175e-06, - "loss": 0.5436, + "epoch": 1.47, + "learning_rate": 3.517028152528589e-06, + "loss": 0.5823, "step": 3217 }, { - "epoch": 1.65, - "learning_rate": 1.5250145502454594e-06, - "loss": 0.5514, + "epoch": 1.47, + "learning_rate": 3.51141232942768e-06, + "loss": 0.5617, "step": 3218 }, { - "epoch": 1.65, - "learning_rate": 1.5205977955395812e-06, - "loss": 0.571, + "epoch": 1.47, + "learning_rate": 3.5058000384723046e-06, + "loss": 0.5979, "step": 3219 }, { - "epoch": 1.66, - "learning_rate": 1.5161869196697122e-06, - "loss": 0.6091, + "epoch": 1.47, + "learning_rate": 3.5001912827175744e-06, + "loss": 0.6168, "step": 3220 }, { - "epoch": 1.66, - "learning_rate": 1.5117819256939426e-06, - "loss": 0.5605, + "epoch": 1.47, + "learning_rate": 3.49458606521669e-06, + "loss": 0.5709, "step": 3221 }, { - "epoch": 1.66, - "learning_rate": 1.507382816666295e-06, - "loss": 0.5795, + "epoch": 1.47, + "learning_rate": 3.4889843890209242e-06, + "loss": 0.5807, "step": 3222 }, { - "epoch": 1.66, - "learning_rate": 1.5029895956367046e-06, - "loss": 0.5614, + "epoch": 1.47, + "learning_rate": 3.483386257179624e-06, + "loss": 0.62, "step": 3223 }, { - "epoch": 1.66, - "learning_rate": 1.4986022656510223e-06, - "loss": 0.5679, + "epoch": 1.47, + "learning_rate": 3.477791672740194e-06, + "loss": 0.6177, "step": 3224 }, { - "epoch": 1.66, - "learning_rate": 1.4942208297510252e-06, - "loss": 0.5817, + "epoch": 1.47, + "learning_rate": 3.47220063874813e-06, + "loss": 0.6014, "step": 3225 }, { - "epoch": 1.66, - "learning_rate": 1.489845290974392e-06, - "loss": 0.6198, + "epoch": 1.47, + "learning_rate": 3.466613158246974e-06, + "loss": 0.5746, "step": 3226 }, { - "epoch": 1.66, - "learning_rate": 1.4854756523547209e-06, - "loss": 0.5417, + "epoch": 1.47, + "learning_rate": 3.4610292342783447e-06, + "loss": 0.5869, "step": 3227 }, { - "epoch": 1.66, - "learning_rate": 1.4811119169215137e-06, - "loss": 0.5493, + "epoch": 1.47, + "learning_rate": 3.455448869881923e-06, + "loss": 0.5459, "step": 3228 }, { - "epoch": 1.66, - "learning_rate": 1.476754087700184e-06, - "loss": 0.5448, + "epoch": 1.47, + "learning_rate": 3.4498720680954556e-06, + "loss": 0.5533, "step": 3229 }, { - "epoch": 1.66, - "learning_rate": 1.4724021677120491e-06, - "loss": 0.5825, + "epoch": 1.47, + "learning_rate": 3.4442988319547377e-06, + "loss": 0.5883, "step": 3230 }, { - "epoch": 1.66, - "learning_rate": 1.468056159974327e-06, - "loss": 0.5592, + "epoch": 1.47, + "learning_rate": 3.438729164493636e-06, + "loss": 0.5862, "step": 3231 }, { - "epoch": 1.66, - "learning_rate": 1.4637160675001427e-06, - "loss": 0.5786, + "epoch": 1.47, + "learning_rate": 3.4331630687440688e-06, + "loss": 0.5796, "step": 3232 }, { - "epoch": 1.66, - "learning_rate": 1.4593818932985137e-06, - "loss": 0.5359, + "epoch": 1.47, + "learning_rate": 3.427600547736012e-06, + "loss": 0.5668, "step": 3233 }, { - "epoch": 1.66, - "learning_rate": 1.4550536403743564e-06, - "loss": 0.5723, + "epoch": 1.47, + "learning_rate": 3.422041604497495e-06, + "loss": 0.6154, "step": 3234 }, { - "epoch": 1.66, - "learning_rate": 1.450731311728486e-06, - "loss": 0.5801, + "epoch": 1.47, + "learning_rate": 3.416486242054602e-06, + "loss": 0.5627, "step": 3235 }, { - "epoch": 1.66, - "learning_rate": 1.446414910357604e-06, - "loss": 0.5793, + "epoch": 1.47, + "learning_rate": 3.41093446343146e-06, + "loss": 0.6299, "step": 3236 }, { - "epoch": 1.66, - "learning_rate": 1.442104439254307e-06, - "loss": 0.5425, + "epoch": 1.47, + "learning_rate": 3.405386271650254e-06, + "loss": 0.578, "step": 3237 }, { - "epoch": 1.66, - "learning_rate": 1.4377999014070764e-06, - "loss": 0.5634, + "epoch": 1.48, + "learning_rate": 3.399841669731212e-06, + "loss": 0.5605, "step": 3238 }, { - "epoch": 1.66, - "learning_rate": 1.433501299800283e-06, - "loss": 0.5996, + "epoch": 1.48, + "learning_rate": 3.394300660692613e-06, + "loss": 0.5402, "step": 3239 }, { - "epoch": 1.67, - "learning_rate": 1.4292086374141812e-06, - "loss": 0.571, + "epoch": 1.48, + "learning_rate": 3.388763247550765e-06, + "loss": 0.5527, "step": 3240 }, { - "epoch": 1.67, - "learning_rate": 1.4249219172249051e-06, - "loss": 0.5536, + "epoch": 1.48, + "learning_rate": 3.383229433320044e-06, + "loss": 0.5752, "step": 3241 }, { - "epoch": 1.67, - "learning_rate": 1.4206411422044752e-06, - "loss": 0.5665, + "epoch": 1.48, + "learning_rate": 3.377699221012842e-06, + "loss": 0.5868, "step": 3242 }, { - "epoch": 1.67, - "learning_rate": 1.4163663153207851e-06, - "loss": 0.5833, + "epoch": 1.48, + "learning_rate": 3.3721726136396007e-06, + "loss": 0.5763, "step": 3243 }, { - "epoch": 1.67, - "learning_rate": 1.412097439537603e-06, - "loss": 0.5793, + "epoch": 1.48, + "learning_rate": 3.366649614208809e-06, + "loss": 0.6166, "step": 3244 }, { - "epoch": 1.67, - "learning_rate": 1.407834517814578e-06, - "loss": 0.5496, + "epoch": 1.48, + "learning_rate": 3.3611302257269717e-06, + "loss": 0.5803, "step": 3245 }, { - "epoch": 1.67, - "learning_rate": 1.4035775531072259e-06, - "loss": 0.5518, + "epoch": 1.48, + "learning_rate": 3.3556144511986433e-06, + "loss": 0.5034, "step": 3246 }, { - "epoch": 1.67, - "learning_rate": 1.3993265483669328e-06, - "loss": 0.6229, + "epoch": 1.48, + "learning_rate": 3.350102293626405e-06, + "loss": 0.5592, "step": 3247 }, { - "epoch": 1.67, - "learning_rate": 1.395081506540955e-06, - "loss": 0.5322, + "epoch": 1.48, + "learning_rate": 3.344593756010874e-06, + "loss": 0.5392, "step": 3248 }, { - "epoch": 1.67, - "learning_rate": 1.3908424305724122e-06, - "loss": 0.5242, + "epoch": 1.48, + "learning_rate": 3.339088841350686e-06, + "loss": 0.6051, "step": 3249 }, { - "epoch": 1.67, - "learning_rate": 1.3866093234002887e-06, - "loss": 0.5564, + "epoch": 1.48, + "learning_rate": 3.333587552642514e-06, + "loss": 0.6355, "step": 3250 }, { - "epoch": 1.67, - "learning_rate": 1.3823821879594278e-06, - "loss": 0.5686, + "epoch": 1.48, + "learning_rate": 3.3280898928810567e-06, + "loss": 0.6506, "step": 3251 }, { - "epoch": 1.67, - "learning_rate": 1.3781610271805436e-06, - "loss": 0.5555, + "epoch": 1.48, + "learning_rate": 3.322595865059034e-06, + "loss": 0.6171, "step": 3252 }, { - "epoch": 1.67, - "learning_rate": 1.373945843990192e-06, - "loss": 0.5707, + "epoch": 1.48, + "learning_rate": 3.3171054721671902e-06, + "loss": 0.624, "step": 3253 }, { - "epoch": 1.67, - "learning_rate": 1.3697366413107982e-06, - "loss": 0.6031, + "epoch": 1.48, + "learning_rate": 3.3116187171942948e-06, + "loss": 0.6008, "step": 3254 }, { - "epoch": 1.67, - "learning_rate": 1.3655334220606332e-06, - "loss": 0.5634, + "epoch": 1.48, + "learning_rate": 3.306135603127126e-06, + "loss": 0.5292, "step": 3255 }, { - "epoch": 1.67, - "learning_rate": 1.3613361891538223e-06, - "loss": 0.5862, + "epoch": 1.48, + "learning_rate": 3.3006561329504892e-06, + "loss": 0.6091, "step": 3256 }, { - "epoch": 1.67, - "learning_rate": 1.3571449455003394e-06, - "loss": 0.5592, + "epoch": 1.48, + "learning_rate": 3.295180309647206e-06, + "loss": 0.5831, "step": 3257 }, { - "epoch": 1.67, - "learning_rate": 1.3529596940060064e-06, - "loss": 0.5609, + "epoch": 1.48, + "learning_rate": 3.289708136198112e-06, + "loss": 0.5402, "step": 3258 }, { - "epoch": 1.68, - "learning_rate": 1.3487804375724922e-06, - "loss": 0.5955, + "epoch": 1.48, + "learning_rate": 3.2842396155820455e-06, + "loss": 0.5728, "step": 3259 }, { - "epoch": 1.68, - "learning_rate": 1.3446071790973058e-06, - "loss": 0.5485, + "epoch": 1.49, + "learning_rate": 3.2787747507758783e-06, + "loss": 0.5842, "step": 3260 }, { - "epoch": 1.68, - "learning_rate": 1.3404399214738006e-06, - "loss": 0.5734, + "epoch": 1.49, + "learning_rate": 3.2733135447544705e-06, + "loss": 0.6157, "step": 3261 }, { - "epoch": 1.68, - "learning_rate": 1.336278667591171e-06, - "loss": 0.5703, + "epoch": 1.49, + "learning_rate": 3.2678560004907024e-06, + "loss": 0.5734, "step": 3262 }, { - "epoch": 1.68, - "learning_rate": 1.3321234203344435e-06, - "loss": 0.5916, + "epoch": 1.49, + "learning_rate": 3.262402120955457e-06, + "loss": 0.6062, "step": 3263 }, { - "epoch": 1.68, - "learning_rate": 1.3279741825844872e-06, - "loss": 0.542, + "epoch": 1.49, + "learning_rate": 3.2569519091176273e-06, + "loss": 0.6108, "step": 3264 }, { - "epoch": 1.68, - "learning_rate": 1.3238309572180008e-06, - "loss": 0.5648, + "epoch": 1.49, + "learning_rate": 3.2515053679440942e-06, + "loss": 0.5579, "step": 3265 }, { - "epoch": 1.68, - "learning_rate": 1.3196937471075134e-06, - "loss": 0.578, + "epoch": 1.49, + "learning_rate": 3.2460625003997683e-06, + "loss": 0.5598, "step": 3266 }, { - "epoch": 1.68, - "learning_rate": 1.3155625551213857e-06, - "loss": 0.601, + "epoch": 1.49, + "learning_rate": 3.2406233094475317e-06, + "loss": 0.5818, "step": 3267 }, { - "epoch": 1.68, - "learning_rate": 1.3114373841238059e-06, - "loss": 0.5623, + "epoch": 1.49, + "learning_rate": 3.2351877980482804e-06, + "loss": 0.5863, "step": 3268 }, { - "epoch": 1.68, - "learning_rate": 1.307318236974786e-06, - "loss": 0.5709, + "epoch": 1.49, + "learning_rate": 3.229755969160906e-06, + "loss": 0.6062, "step": 3269 }, { - "epoch": 1.68, - "learning_rate": 1.303205116530164e-06, - "loss": 0.6035, + "epoch": 1.49, + "learning_rate": 3.224327825742297e-06, + "loss": 0.5448, "step": 3270 }, { - "epoch": 1.68, - "learning_rate": 1.2990980256415964e-06, - "loss": 0.5426, + "epoch": 1.49, + "learning_rate": 3.2189033707473214e-06, + "loss": 0.6, "step": 3271 }, { - "epoch": 1.68, - "learning_rate": 1.2949969671565654e-06, - "loss": 0.5779, + "epoch": 1.49, + "learning_rate": 3.213482607128865e-06, + "loss": 0.6013, "step": 3272 }, { - "epoch": 1.68, - "learning_rate": 1.2909019439183635e-06, - "loss": 0.5474, + "epoch": 1.49, + "learning_rate": 3.2080655378377788e-06, + "loss": 0.5836, "step": 3273 }, { - "epoch": 1.68, - "learning_rate": 1.286812958766106e-06, - "loss": 0.5977, + "epoch": 1.49, + "learning_rate": 3.202652165822917e-06, + "loss": 0.6383, "step": 3274 }, { - "epoch": 1.68, - "learning_rate": 1.2827300145347165e-06, - "loss": 0.5571, + "epoch": 1.49, + "learning_rate": 3.1972424940311186e-06, + "loss": 0.6382, "step": 3275 }, { - "epoch": 1.68, - "learning_rate": 1.2786531140549319e-06, - "loss": 0.5785, + "epoch": 1.49, + "learning_rate": 3.191836525407207e-06, + "loss": 0.5616, "step": 3276 }, { - "epoch": 1.68, - "learning_rate": 1.2745822601532986e-06, - "loss": 0.5457, + "epoch": 1.49, + "learning_rate": 3.1864342628939904e-06, + "loss": 0.5583, "step": 3277 }, { - "epoch": 1.68, - "learning_rate": 1.2705174556521737e-06, - "loss": 0.5779, + "epoch": 1.49, + "learning_rate": 3.1810357094322595e-06, + "loss": 0.608, "step": 3278 }, { - "epoch": 1.69, - "learning_rate": 1.2664587033697162e-06, - "loss": 0.5581, + "epoch": 1.49, + "learning_rate": 3.1756408679607876e-06, + "loss": 0.5339, "step": 3279 }, { - "epoch": 1.69, - "learning_rate": 1.2624060061198917e-06, - "loss": 0.5332, + "epoch": 1.49, + "learning_rate": 3.1702497414163214e-06, + "loss": 0.5509, "step": 3280 }, { - "epoch": 1.69, - "learning_rate": 1.2583593667124638e-06, - "loss": 0.5835, + "epoch": 1.49, + "learning_rate": 3.1648623327335916e-06, + "loss": 0.5746, "step": 3281 }, { - "epoch": 1.69, - "learning_rate": 1.2543187879530049e-06, - "loss": 0.5599, + "epoch": 1.5, + "learning_rate": 3.159478644845302e-06, + "loss": 0.5909, "step": 3282 }, { - "epoch": 1.69, - "learning_rate": 1.2502842726428743e-06, - "loss": 0.6041, + "epoch": 1.5, + "learning_rate": 3.154098680682135e-06, + "loss": 0.5396, "step": 3283 }, { - "epoch": 1.69, - "learning_rate": 1.2462558235792388e-06, - "loss": 0.5778, + "epoch": 1.5, + "learning_rate": 3.148722443172735e-06, + "loss": 0.5673, "step": 3284 }, { - "epoch": 1.69, - "learning_rate": 1.242233443555051e-06, - "loss": 0.5641, + "epoch": 1.5, + "learning_rate": 3.1433499352437367e-06, + "loss": 0.5814, "step": 3285 }, { - "epoch": 1.69, - "learning_rate": 1.2382171353590578e-06, - "loss": 0.5579, + "epoch": 1.5, + "learning_rate": 3.1379811598197253e-06, + "loss": 0.6244, "step": 3286 }, { - "epoch": 1.69, - "learning_rate": 1.2342069017757974e-06, - "loss": 0.5641, + "epoch": 1.5, + "learning_rate": 3.132616119823264e-06, + "loss": 0.5233, "step": 3287 }, { - "epoch": 1.69, - "learning_rate": 1.2302027455855969e-06, - "loss": 0.5947, + "epoch": 1.5, + "learning_rate": 3.1272548181748817e-06, + "loss": 0.5756, "step": 3288 }, { - "epoch": 1.69, - "learning_rate": 1.2262046695645692e-06, - "loss": 0.5959, + "epoch": 1.5, + "learning_rate": 3.121897257793074e-06, + "loss": 0.5812, "step": 3289 }, { - "epoch": 1.69, - "learning_rate": 1.222212676484611e-06, - "loss": 0.546, + "epoch": 1.5, + "learning_rate": 3.1165434415942873e-06, + "loss": 0.6726, "step": 3290 }, { - "epoch": 1.69, - "learning_rate": 1.2182267691134008e-06, - "loss": 0.5879, + "epoch": 1.5, + "learning_rate": 3.1111933724929533e-06, + "loss": 0.5804, "step": 3291 }, { - "epoch": 1.69, - "learning_rate": 1.2142469502144027e-06, - "loss": 0.5756, + "epoch": 1.5, + "learning_rate": 3.1058470534014406e-06, + "loss": 0.5928, "step": 3292 }, { - "epoch": 1.69, - "learning_rate": 1.210273222546854e-06, - "loss": 0.5865, + "epoch": 1.5, + "learning_rate": 3.1005044872300894e-06, + "loss": 0.5914, "step": 3293 }, { - "epoch": 1.69, - "learning_rate": 1.2063055888657737e-06, - "loss": 0.5322, + "epoch": 1.5, + "learning_rate": 3.095165676887195e-06, + "loss": 0.5641, "step": 3294 }, { - "epoch": 1.69, - "learning_rate": 1.2023440519219508e-06, - "loss": 0.5995, + "epoch": 1.5, + "learning_rate": 3.0898306252790076e-06, + "loss": 0.5944, "step": 3295 }, { - "epoch": 1.69, - "learning_rate": 1.1983886144619527e-06, - "loss": 0.5603, + "epoch": 1.5, + "learning_rate": 3.084499335309723e-06, + "loss": 0.5813, "step": 3296 }, { - "epoch": 1.69, - "learning_rate": 1.1944392792281124e-06, - "loss": 0.5598, + "epoch": 1.5, + "learning_rate": 3.0791718098815104e-06, + "loss": 0.6113, "step": 3297 }, { - "epoch": 1.7, - "learning_rate": 1.190496048958536e-06, - "loss": 0.6144, + "epoch": 1.5, + "learning_rate": 3.0738480518944647e-06, + "loss": 0.608, "step": 3298 }, { - "epoch": 1.7, - "learning_rate": 1.1865589263870969e-06, - "loss": 0.5807, + "epoch": 1.5, + "learning_rate": 3.0685280642466455e-06, + "loss": 0.6334, "step": 3299 }, { - "epoch": 1.7, - "learning_rate": 1.1826279142434304e-06, - "loss": 0.5392, + "epoch": 1.5, + "learning_rate": 3.063211849834056e-06, + "loss": 0.6259, "step": 3300 }, { - "epoch": 1.7, - "learning_rate": 1.178703015252939e-06, - "loss": 0.5825, - "step": 3301 + "epoch": 1.5, + "learning_rate": 3.0578994115506477e-06, + "loss": 0.6063, + "step": 3301 }, { - "epoch": 1.7, - "learning_rate": 1.1747842321367886e-06, - "loss": 0.5421, + "epoch": 1.5, + "learning_rate": 3.0525907522883102e-06, + "loss": 0.5566, "step": 3302 }, { - "epoch": 1.7, - "learning_rate": 1.1708715676118976e-06, - "loss": 0.5344, + "epoch": 1.5, + "learning_rate": 3.0472858749368805e-06, + "loss": 0.6006, "step": 3303 }, { - "epoch": 1.7, - "learning_rate": 1.1669650243909525e-06, - "loss": 0.5676, + "epoch": 1.51, + "learning_rate": 3.0419847823841374e-06, + "loss": 0.5441, "step": 3304 }, { - "epoch": 1.7, - "learning_rate": 1.163064605182387e-06, - "loss": 0.5537, + "epoch": 1.51, + "learning_rate": 3.0366874775157993e-06, + "loss": 0.623, "step": 3305 }, { - "epoch": 1.7, - "learning_rate": 1.159170312690393e-06, - "loss": 0.5343, + "epoch": 1.51, + "learning_rate": 3.031393963215521e-06, + "loss": 0.5506, "step": 3306 }, { - "epoch": 1.7, - "learning_rate": 1.1552821496149136e-06, - "loss": 0.575, + "epoch": 1.51, + "learning_rate": 3.0261042423648968e-06, + "loss": 0.6522, "step": 3307 }, { - "epoch": 1.7, - "learning_rate": 1.1514001186516433e-06, - "loss": 0.5817, + "epoch": 1.51, + "learning_rate": 3.020818317843448e-06, + "loss": 0.5348, "step": 3308 }, { - "epoch": 1.7, - "learning_rate": 1.1475242224920234e-06, - "loss": 0.5599, + "epoch": 1.51, + "learning_rate": 3.015536192528635e-06, + "loss": 0.5715, "step": 3309 }, { - "epoch": 1.7, - "learning_rate": 1.143654463823245e-06, - "loss": 0.5082, + "epoch": 1.51, + "learning_rate": 3.0102578692958607e-06, + "loss": 0.6725, "step": 3310 }, { - "epoch": 1.7, - "learning_rate": 1.139790845328238e-06, - "loss": 0.5807, + "epoch": 1.51, + "learning_rate": 3.0049833510184377e-06, + "loss": 0.5862, "step": 3311 }, { - "epoch": 1.7, - "learning_rate": 1.1359333696856855e-06, - "loss": 0.541, + "epoch": 1.51, + "learning_rate": 2.999712640567619e-06, + "loss": 0.6042, "step": 3312 }, { - "epoch": 1.7, - "learning_rate": 1.1320820395700005e-06, - "loss": 0.5605, + "epoch": 1.51, + "learning_rate": 2.994445740812585e-06, + "loss": 0.5795, "step": 3313 }, { - "epoch": 1.7, - "learning_rate": 1.1282368576513436e-06, - "loss": 0.5435, + "epoch": 1.51, + "learning_rate": 2.989182654620443e-06, + "loss": 0.5453, "step": 3314 }, { - "epoch": 1.7, - "learning_rate": 1.124397826595609e-06, - "loss": 0.5647, + "epoch": 1.51, + "learning_rate": 2.9839233848562097e-06, + "loss": 0.5822, "step": 3315 }, { - "epoch": 1.7, - "learning_rate": 1.1205649490644255e-06, - "loss": 0.5564, + "epoch": 1.51, + "learning_rate": 2.9786679343828507e-06, + "loss": 0.6476, "step": 3316 }, { - "epoch": 1.7, - "learning_rate": 1.1167382277151596e-06, - "loss": 0.4952, + "epoch": 1.51, + "learning_rate": 2.9734163060612263e-06, + "loss": 0.5902, "step": 3317 }, { - "epoch": 1.71, - "learning_rate": 1.1129176652009043e-06, - "loss": 0.5804, + "epoch": 1.51, + "learning_rate": 2.9681685027501316e-06, + "loss": 0.5895, "step": 3318 }, { - "epoch": 1.71, - "learning_rate": 1.1091032641704869e-06, - "loss": 0.5742, + "epoch": 1.51, + "learning_rate": 2.962924527306276e-06, + "loss": 0.6194, "step": 3319 }, { - "epoch": 1.71, - "learning_rate": 1.1052950272684604e-06, - "loss": 0.5751, + "epoch": 1.51, + "learning_rate": 2.957684382584286e-06, + "loss": 0.567, "step": 3320 }, { - "epoch": 1.71, - "learning_rate": 1.1014929571351074e-06, - "loss": 0.6057, + "epoch": 1.51, + "learning_rate": 2.9524480714366953e-06, + "loss": 0.6008, "step": 3321 }, { - "epoch": 1.71, - "learning_rate": 1.0976970564064327e-06, - "loss": 0.5775, + "epoch": 1.51, + "learning_rate": 2.9472155967139604e-06, + "loss": 0.5636, "step": 3322 }, { - "epoch": 1.71, - "learning_rate": 1.0939073277141598e-06, - "loss": 0.5673, + "epoch": 1.51, + "learning_rate": 2.9419869612644445e-06, + "loss": 0.5582, "step": 3323 }, { - "epoch": 1.71, - "learning_rate": 1.090123773685744e-06, - "loss": 0.5648, + "epoch": 1.51, + "learning_rate": 2.936762167934425e-06, + "loss": 0.5519, "step": 3324 }, { - "epoch": 1.71, - "learning_rate": 1.0863463969443499e-06, - "loss": 0.5775, + "epoch": 1.51, + "learning_rate": 2.9315412195680816e-06, + "loss": 0.5732, "step": 3325 }, { - "epoch": 1.71, - "learning_rate": 1.0825752001088618e-06, - "loss": 0.6221, + "epoch": 1.52, + "learning_rate": 2.9263241190075087e-06, + "loss": 0.6213, "step": 3326 }, { - "epoch": 1.71, - "learning_rate": 1.0788101857938805e-06, - "loss": 0.5475, + "epoch": 1.52, + "learning_rate": 2.921110869092696e-06, + "loss": 0.5596, "step": 3327 }, { - "epoch": 1.71, - "learning_rate": 1.0750513566097198e-06, - "loss": 0.5298, + "epoch": 1.52, + "learning_rate": 2.9159014726615443e-06, + "loss": 0.6112, "step": 3328 }, { - "epoch": 1.71, - "learning_rate": 1.0712987151624056e-06, - "loss": 0.6001, + "epoch": 1.52, + "learning_rate": 2.910695932549856e-06, + "loss": 0.5984, "step": 3329 }, { - "epoch": 1.71, - "learning_rate": 1.0675522640536706e-06, - "loss": 0.5454, + "epoch": 1.52, + "learning_rate": 2.905494251591333e-06, + "loss": 0.6094, "step": 3330 }, { - "epoch": 1.71, - "learning_rate": 1.0638120058809641e-06, - "loss": 0.5319, + "epoch": 1.52, + "learning_rate": 2.9002964326175774e-06, + "loss": 0.5768, "step": 3331 }, { - "epoch": 1.71, - "learning_rate": 1.060077943237432e-06, - "loss": 0.5652, + "epoch": 1.52, + "learning_rate": 2.8951024784580906e-06, + "loss": 0.6398, "step": 3332 }, { - "epoch": 1.71, - "learning_rate": 1.056350078711934e-06, - "loss": 0.5333, + "epoch": 1.52, + "learning_rate": 2.8899123919402614e-06, + "loss": 0.5485, "step": 3333 }, { - "epoch": 1.71, - "learning_rate": 1.0526284148890242e-06, - "loss": 0.5811, + "epoch": 1.52, + "learning_rate": 2.884726175889383e-06, + "loss": 0.5521, "step": 3334 }, { - "epoch": 1.71, - "learning_rate": 1.0489129543489617e-06, - "loss": 0.5531, + "epoch": 1.52, + "learning_rate": 2.8795438331286395e-06, + "loss": 0.5952, "step": 3335 }, { - "epoch": 1.71, - "learning_rate": 1.045203699667705e-06, - "loss": 0.5264, + "epoch": 1.52, + "learning_rate": 2.874365366479107e-06, + "loss": 0.5598, "step": 3336 }, { - "epoch": 1.72, - "learning_rate": 1.0415006534169092e-06, - "loss": 0.5367, + "epoch": 1.52, + "learning_rate": 2.8691907787597405e-06, + "loss": 0.5707, "step": 3337 }, { - "epoch": 1.72, - "learning_rate": 1.037803818163926e-06, - "loss": 0.5637, + "epoch": 1.52, + "learning_rate": 2.864020072787407e-06, + "loss": 0.613, "step": 3338 }, { - "epoch": 1.72, - "learning_rate": 1.0341131964717988e-06, - "loss": 0.58, + "epoch": 1.52, + "learning_rate": 2.8588532513768354e-06, + "loss": 0.6162, "step": 3339 }, { - "epoch": 1.72, - "learning_rate": 1.0304287908992626e-06, - "loss": 0.5922, + "epoch": 1.52, + "learning_rate": 2.853690317340654e-06, + "loss": 0.6031, "step": 3340 }, { - "epoch": 1.72, - "learning_rate": 1.0267506040007503e-06, - "loss": 0.5208, + "epoch": 1.52, + "learning_rate": 2.848531273489372e-06, + "loss": 0.6628, "step": 3341 }, { - "epoch": 1.72, - "learning_rate": 1.0230786383263724e-06, - "loss": 0.582, + "epoch": 1.52, + "learning_rate": 2.843376122631385e-06, + "loss": 0.6151, "step": 3342 }, { - "epoch": 1.72, - "learning_rate": 1.0194128964219362e-06, - "loss": 0.5309, + "epoch": 1.52, + "learning_rate": 2.838224867572955e-06, + "loss": 0.593, "step": 3343 }, { - "epoch": 1.72, - "learning_rate": 1.0157533808289265e-06, - "loss": 0.5967, + "epoch": 1.52, + "learning_rate": 2.8330775111182427e-06, + "loss": 0.5897, "step": 3344 }, { - "epoch": 1.72, - "learning_rate": 1.012100094084515e-06, - "loss": 0.557, + "epoch": 1.52, + "learning_rate": 2.827934056069277e-06, + "loss": 0.6222, "step": 3345 }, { - "epoch": 1.72, - "learning_rate": 1.008453038721553e-06, - "loss": 0.5371, + "epoch": 1.52, + "learning_rate": 2.8227945052259585e-06, + "loss": 0.5846, "step": 3346 }, { - "epoch": 1.72, - "learning_rate": 1.0048122172685737e-06, - "loss": 0.5911, + "epoch": 1.52, + "learning_rate": 2.817658861386069e-06, + "loss": 0.5742, "step": 3347 }, { - "epoch": 1.72, - "learning_rate": 1.0011776322497868e-06, - "loss": 0.563, + "epoch": 1.53, + "learning_rate": 2.8125271273452616e-06, + "loss": 0.5833, "step": 3348 }, { - "epoch": 1.72, - "learning_rate": 9.975492861850778e-07, - "loss": 0.6255, + "epoch": 1.53, + "learning_rate": 2.807399305897063e-06, + "loss": 0.5914, "step": 3349 }, { - "epoch": 1.72, - "learning_rate": 9.939271815900065e-07, - "loss": 0.5751, + "epoch": 1.53, + "learning_rate": 2.8022753998328655e-06, + "loss": 0.5946, "step": 3350 }, { - "epoch": 1.72, - "learning_rate": 9.903113209758098e-07, - "loss": 0.5775, + "epoch": 1.53, + "learning_rate": 2.7971554119419386e-06, + "loss": 0.5487, "step": 3351 }, { - "epoch": 1.72, - "learning_rate": 9.867017068493878e-07, - "loss": 0.5546, + "epoch": 1.53, + "learning_rate": 2.7920393450114057e-06, + "loss": 0.5669, "step": 3352 }, { - "epoch": 1.72, - "learning_rate": 9.830983417133188e-07, - "loss": 0.5902, + "epoch": 1.53, + "learning_rate": 2.786927201826266e-06, + "loss": 0.578, "step": 3353 }, { - "epoch": 1.72, - "learning_rate": 9.795012280658434e-07, - "loss": 0.5668, + "epoch": 1.53, + "learning_rate": 2.78181898516938e-06, + "loss": 0.5917, "step": 3354 }, { - "epoch": 1.72, - "learning_rate": 9.759103684008664e-07, - "loss": 0.5554, + "epoch": 1.53, + "learning_rate": 2.7767146978214744e-06, + "loss": 0.6027, "step": 3355 }, { - "epoch": 1.73, - "learning_rate": 9.723257652079599e-07, - "loss": 0.6044, + "epoch": 1.53, + "learning_rate": 2.771614342561123e-06, + "loss": 0.5817, "step": 3356 }, { - "epoch": 1.73, - "learning_rate": 9.68747420972358e-07, - "loss": 0.5386, + "epoch": 1.53, + "learning_rate": 2.766517922164782e-06, + "loss": 0.6099, "step": 3357 }, { - "epoch": 1.73, - "learning_rate": 9.65175338174954e-07, - "loss": 0.5608, + "epoch": 1.53, + "learning_rate": 2.761425439406744e-06, + "loss": 0.5834, "step": 3358 }, { - "epoch": 1.73, - "learning_rate": 9.616095192923015e-07, - "loss": 0.5686, + "epoch": 1.53, + "learning_rate": 2.7563368970591696e-06, + "loss": 0.6344, "step": 3359 }, { - "epoch": 1.73, - "learning_rate": 9.58049966796607e-07, - "loss": 0.5847, + "epoch": 1.53, + "learning_rate": 2.751252297892072e-06, + "loss": 0.6211, "step": 3360 }, { - "epoch": 1.73, - "learning_rate": 9.544966831557434e-07, - "loss": 0.6042, + "epoch": 1.53, + "learning_rate": 2.746171644673321e-06, + "loss": 0.5671, "step": 3361 }, { - "epoch": 1.73, - "learning_rate": 9.509496708332233e-07, - "loss": 0.5519, + "epoch": 1.53, + "learning_rate": 2.741094940168625e-06, + "loss": 0.578, "step": 3362 }, { - "epoch": 1.73, - "learning_rate": 9.47408932288223e-07, - "loss": 0.5643, + "epoch": 1.53, + "learning_rate": 2.736022187141566e-06, + "loss": 0.5807, "step": 3363 }, { - "epoch": 1.73, - "learning_rate": 9.438744699755619e-07, - "loss": 0.5864, + "epoch": 1.53, + "learning_rate": 2.7309533883535533e-06, + "loss": 0.5411, "step": 3364 }, { - "epoch": 1.73, - "learning_rate": 9.403462863457113e-07, - "loss": 0.5989, + "epoch": 1.53, + "learning_rate": 2.725888546563853e-06, + "loss": 0.6146, "step": 3365 }, { - "epoch": 1.73, - "learning_rate": 9.368243838447877e-07, - "loss": 0.5815, + "epoch": 1.53, + "learning_rate": 2.7208276645295784e-06, + "loss": 0.6337, "step": 3366 }, { - "epoch": 1.73, - "learning_rate": 9.333087649145544e-07, - "loss": 0.5465, + "epoch": 1.53, + "learning_rate": 2.715770745005687e-06, + "loss": 0.6273, "step": 3367 }, { - "epoch": 1.73, - "learning_rate": 9.297994319924175e-07, - "loss": 0.5587, + "epoch": 1.53, + "learning_rate": 2.71071779074497e-06, + "loss": 0.5707, "step": 3368 }, { - "epoch": 1.73, - "learning_rate": 9.262963875114239e-07, - "loss": 0.577, + "epoch": 1.53, + "learning_rate": 2.7056688044980784e-06, + "loss": 0.6262, "step": 3369 }, { - "epoch": 1.73, - "learning_rate": 9.227996339002609e-07, - "loss": 0.5181, + "epoch": 1.54, + "learning_rate": 2.7006237890134825e-06, + "loss": 0.6187, "step": 3370 }, { - "epoch": 1.73, - "learning_rate": 9.193091735832593e-07, - "loss": 0.6013, + "epoch": 1.54, + "learning_rate": 2.695582747037506e-06, + "loss": 0.6161, "step": 3371 }, { - "epoch": 1.73, - "learning_rate": 9.158250089803789e-07, - "loss": 0.5785, + "epoch": 1.54, + "learning_rate": 2.690545681314303e-06, + "loss": 0.5818, "step": 3372 }, { - "epoch": 1.73, - "learning_rate": 9.123471425072205e-07, - "loss": 0.5554, + "epoch": 1.54, + "learning_rate": 2.6855125945858682e-06, + "loss": 0.6036, "step": 3373 }, { - "epoch": 1.73, - "learning_rate": 9.088755765750168e-07, - "loss": 0.5311, + "epoch": 1.54, + "learning_rate": 2.6804834895920194e-06, + "loss": 0.5668, "step": 3374 }, { - "epoch": 1.73, - "learning_rate": 9.05410313590629e-07, - "loss": 0.5492, + "epoch": 1.54, + "learning_rate": 2.6754583690704195e-06, + "loss": 0.5547, "step": 3375 }, { - "epoch": 1.74, - "learning_rate": 9.019513559565529e-07, - "loss": 0.5444, + "epoch": 1.54, + "learning_rate": 2.6704372357565545e-06, + "loss": 0.5801, "step": 3376 }, { - "epoch": 1.74, - "learning_rate": 8.984987060709094e-07, - "loss": 0.567, + "epoch": 1.54, + "learning_rate": 2.6654200923837436e-06, + "loss": 0.5923, "step": 3377 }, { - "epoch": 1.74, - "learning_rate": 8.950523663274501e-07, - "loss": 0.6042, + "epoch": 1.54, + "learning_rate": 2.6604069416831326e-06, + "loss": 0.5586, "step": 3378 }, { - "epoch": 1.74, - "learning_rate": 8.916123391155473e-07, - "loss": 0.5509, + "epoch": 1.54, + "learning_rate": 2.6553977863836943e-06, + "loss": 0.6124, "step": 3379 }, { - "epoch": 1.74, - "learning_rate": 8.881786268201975e-07, - "loss": 0.5685, + "epoch": 1.54, + "learning_rate": 2.6503926292122282e-06, + "loss": 0.5812, "step": 3380 }, { - "epoch": 1.74, - "learning_rate": 8.847512318220242e-07, - "loss": 0.5543, + "epoch": 1.54, + "learning_rate": 2.6453914728933492e-06, + "loss": 0.5909, "step": 3381 }, { - "epoch": 1.74, - "learning_rate": 8.813301564972631e-07, - "loss": 0.6223, + "epoch": 1.54, + "learning_rate": 2.6403943201495097e-06, + "loss": 0.556, "step": 3382 }, { - "epoch": 1.74, - "learning_rate": 8.779154032177772e-07, - "loss": 0.5454, + "epoch": 1.54, + "learning_rate": 2.6354011737009665e-06, + "loss": 0.5966, "step": 3383 }, { - "epoch": 1.74, - "learning_rate": 8.745069743510393e-07, - "loss": 0.5732, + "epoch": 1.54, + "learning_rate": 2.6304120362658035e-06, + "loss": 0.5798, "step": 3384 }, { - "epoch": 1.74, - "learning_rate": 8.71104872260139e-07, - "loss": 0.5581, + "epoch": 1.54, + "learning_rate": 2.625426910559924e-06, + "loss": 0.6105, "step": 3385 }, { - "epoch": 1.74, - "learning_rate": 8.677090993037817e-07, - "loss": 0.589, + "epoch": 1.54, + "learning_rate": 2.6204457992970466e-06, + "loss": 0.5389, "step": 3386 }, { - "epoch": 1.74, - "learning_rate": 8.643196578362833e-07, - "loss": 0.5488, + "epoch": 1.54, + "learning_rate": 2.6154687051886928e-06, + "loss": 0.6173, "step": 3387 }, { - "epoch": 1.74, - "learning_rate": 8.609365502075695e-07, - "loss": 0.5697, + "epoch": 1.54, + "learning_rate": 2.610495630944221e-06, + "loss": 0.5753, "step": 3388 }, { - "epoch": 1.74, - "learning_rate": 8.57559778763175e-07, - "loss": 0.5762, + "epoch": 1.54, + "learning_rate": 2.605526579270777e-06, + "loss": 0.5936, "step": 3389 }, { - "epoch": 1.74, - "learning_rate": 8.541893458442419e-07, - "loss": 0.5928, + "epoch": 1.54, + "learning_rate": 2.600561552873332e-06, + "loss": 0.5847, "step": 3390 }, { - "epoch": 1.74, - "learning_rate": 8.508252537875194e-07, - "loss": 0.5251, + "epoch": 1.54, + "learning_rate": 2.5956005544546613e-06, + "loss": 0.5934, "step": 3391 }, { - "epoch": 1.74, - "learning_rate": 8.474675049253555e-07, - "loss": 0.5184, + "epoch": 1.55, + "learning_rate": 2.590643586715349e-06, + "loss": 0.585, "step": 3392 }, { - "epoch": 1.74, - "learning_rate": 8.441161015857092e-07, - "loss": 0.582, + "epoch": 1.55, + "learning_rate": 2.5856906523537773e-06, + "loss": 0.5859, "step": 3393 }, { - "epoch": 1.74, - "learning_rate": 8.407710460921304e-07, - "loss": 0.5677, + "epoch": 1.55, + "learning_rate": 2.5807417540661496e-06, + "loss": 0.6074, "step": 3394 }, { - "epoch": 1.75, - "learning_rate": 8.374323407637741e-07, - "loss": 0.5328, + "epoch": 1.55, + "learning_rate": 2.575796894546453e-06, + "loss": 0.6313, "step": 3395 }, { - "epoch": 1.75, - "learning_rate": 8.340999879153899e-07, - "loss": 0.5845, + "epoch": 1.55, + "learning_rate": 2.570856076486489e-06, + "loss": 0.5839, "step": 3396 }, { - "epoch": 1.75, - "learning_rate": 8.307739898573241e-07, - "loss": 0.5691, + "epoch": 1.55, + "learning_rate": 2.5659193025758534e-06, + "loss": 0.5372, "step": 3397 }, { - "epoch": 1.75, - "learning_rate": 8.274543488955189e-07, - "loss": 0.5734, + "epoch": 1.55, + "learning_rate": 2.560986575501946e-06, + "loss": 0.6188, "step": 3398 }, { - "epoch": 1.75, - "learning_rate": 8.241410673315054e-07, - "loss": 0.558, + "epoch": 1.55, + "learning_rate": 2.556057897949953e-06, + "loss": 0.6403, "step": 3399 }, { - "epoch": 1.75, - "learning_rate": 8.208341474624071e-07, - "loss": 0.5662, + "epoch": 1.55, + "learning_rate": 2.551133272602867e-06, + "loss": 0.5779, "step": 3400 }, { - "epoch": 1.75, - "learning_rate": 8.175335915809402e-07, - "loss": 0.6031, + "epoch": 1.55, + "learning_rate": 2.5462127021414706e-06, + "loss": 0.5884, "step": 3401 }, { - "epoch": 1.75, - "learning_rate": 8.142394019754018e-07, - "loss": 0.5128, + "epoch": 1.55, + "learning_rate": 2.5412961892443387e-06, + "loss": 0.5627, "step": 3402 }, { - "epoch": 1.75, - "learning_rate": 8.109515809296853e-07, - "loss": 0.5494, + "epoch": 1.55, + "learning_rate": 2.5363837365878373e-06, + "loss": 0.5493, "step": 3403 }, { - "epoch": 1.75, - "learning_rate": 8.076701307232593e-07, - "loss": 0.5792, + "epoch": 1.55, + "learning_rate": 2.5314753468461274e-06, + "loss": 0.6119, "step": 3404 }, { - "epoch": 1.75, - "learning_rate": 8.043950536311795e-07, - "loss": 0.5575, + "epoch": 1.55, + "learning_rate": 2.5265710226911456e-06, + "loss": 0.597, "step": 3405 }, { - "epoch": 1.75, - "learning_rate": 8.01126351924082e-07, - "loss": 0.6127, + "epoch": 1.55, + "learning_rate": 2.5216707667926276e-06, + "loss": 0.5984, "step": 3406 }, { - "epoch": 1.75, - "learning_rate": 7.978640278681838e-07, - "loss": 0.5806, + "epoch": 1.55, + "learning_rate": 2.51677458181809e-06, + "loss": 0.5859, "step": 3407 }, { - "epoch": 1.75, - "learning_rate": 7.94608083725279e-07, - "loss": 0.5759, + "epoch": 1.55, + "learning_rate": 2.511882470432836e-06, + "loss": 0.5896, "step": 3408 }, { - "epoch": 1.75, - "learning_rate": 7.913585217527397e-07, - "loss": 0.5798, + "epoch": 1.55, + "learning_rate": 2.506994435299941e-06, + "loss": 0.5767, "step": 3409 }, { - "epoch": 1.75, - "learning_rate": 7.881153442035116e-07, - "loss": 0.5417, + "epoch": 1.55, + "learning_rate": 2.5021104790802773e-06, + "loss": 0.6128, "step": 3410 }, { - "epoch": 1.75, - "learning_rate": 7.848785533261161e-07, - "loss": 0.5481, + "epoch": 1.55, + "learning_rate": 2.497230604432489e-06, + "loss": 0.5536, "step": 3411 }, { - "epoch": 1.75, - "learning_rate": 7.816481513646468e-07, - "loss": 0.592, + "epoch": 1.55, + "learning_rate": 2.4923548140129904e-06, + "loss": 0.614, "step": 3412 }, { - "epoch": 1.75, - "learning_rate": 7.784241405587667e-07, - "loss": 0.5403, + "epoch": 1.55, + "learning_rate": 2.48748311047599e-06, + "loss": 0.5554, "step": 3413 }, { - "epoch": 1.75, - "learning_rate": 7.752065231437067e-07, - "loss": 0.5916, + "epoch": 1.56, + "learning_rate": 2.482615496473455e-06, + "loss": 0.58, "step": 3414 }, { - "epoch": 1.76, - "learning_rate": 7.719953013502657e-07, - "loss": 0.5703, + "epoch": 1.56, + "learning_rate": 2.477751974655135e-06, + "loss": 0.5383, "step": 3415 }, { - "epoch": 1.76, - "learning_rate": 7.687904774048094e-07, - "loss": 0.5381, + "epoch": 1.56, + "learning_rate": 2.4728925476685506e-06, + "loss": 0.6525, "step": 3416 }, { - "epoch": 1.76, - "learning_rate": 7.655920535292682e-07, - "loss": 0.5399, + "epoch": 1.56, + "learning_rate": 2.468037218158996e-06, + "loss": 0.5624, "step": 3417 }, { - "epoch": 1.76, - "learning_rate": 7.624000319411329e-07, - "loss": 0.5958, + "epoch": 1.56, + "learning_rate": 2.463185988769525e-06, + "loss": 0.5776, "step": 3418 }, { - "epoch": 1.76, - "learning_rate": 7.592144148534564e-07, - "loss": 0.5472, + "epoch": 1.56, + "learning_rate": 2.458338862140971e-06, + "loss": 0.613, "step": 3419 }, { - "epoch": 1.76, - "learning_rate": 7.560352044748553e-07, - "loss": 0.5482, + "epoch": 1.56, + "learning_rate": 2.453495840911927e-06, + "loss": 0.5708, "step": 3420 }, { - "epoch": 1.76, - "learning_rate": 7.528624030094978e-07, - "loss": 0.5814, + "epoch": 1.56, + "learning_rate": 2.4486569277187546e-06, + "loss": 0.5488, "step": 3421 }, { - "epoch": 1.76, - "learning_rate": 7.496960126571151e-07, - "loss": 0.6364, + "epoch": 1.56, + "learning_rate": 2.4438221251955773e-06, + "loss": 0.5859, "step": 3422 }, { - "epoch": 1.76, - "learning_rate": 7.465360356129892e-07, - "loss": 0.5833, + "epoch": 1.56, + "learning_rate": 2.438991435974286e-06, + "loss": 0.5608, "step": 3423 }, { - "epoch": 1.76, - "learning_rate": 7.433824740679551e-07, - "loss": 0.5647, + "epoch": 1.56, + "learning_rate": 2.4341648626845218e-06, + "loss": 0.6566, "step": 3424 }, { - "epoch": 1.76, - "learning_rate": 7.402353302084042e-07, - "loss": 0.5752, + "epoch": 1.56, + "learning_rate": 2.429342407953692e-06, + "loss": 0.6173, "step": 3425 }, { - "epoch": 1.76, - "learning_rate": 7.370946062162754e-07, - "loss": 0.5535, + "epoch": 1.56, + "learning_rate": 2.424524074406965e-06, + "loss": 0.6292, "step": 3426 }, { - "epoch": 1.76, - "learning_rate": 7.339603042690568e-07, - "loss": 0.5391, + "epoch": 1.56, + "learning_rate": 2.419709864667262e-06, + "loss": 0.6078, "step": 3427 }, { - "epoch": 1.76, - "learning_rate": 7.308324265397837e-07, - "loss": 0.6078, + "epoch": 1.56, + "learning_rate": 2.414899781355253e-06, + "loss": 0.5791, "step": 3428 }, { - "epoch": 1.76, - "learning_rate": 7.277109751970379e-07, - "loss": 0.5806, + "epoch": 1.56, + "learning_rate": 2.410093827089379e-06, + "loss": 0.6067, "step": 3429 }, { - "epoch": 1.76, - "learning_rate": 7.245959524049496e-07, - "loss": 0.5717, + "epoch": 1.56, + "learning_rate": 2.405292004485814e-06, + "loss": 0.5956, "step": 3430 }, { - "epoch": 1.76, - "learning_rate": 7.214873603231831e-07, - "loss": 0.5867, + "epoch": 1.56, + "learning_rate": 2.4004943161584937e-06, + "loss": 0.5737, "step": 3431 }, { - "epoch": 1.76, - "learning_rate": 7.183852011069559e-07, - "loss": 0.5448, + "epoch": 1.56, + "learning_rate": 2.395700764719102e-06, + "loss": 0.6183, "step": 3432 }, { - "epoch": 1.76, - "learning_rate": 7.152894769070152e-07, - "loss": 0.5958, + "epoch": 1.56, + "learning_rate": 2.390911352777072e-06, + "loss": 0.5681, "step": 3433 }, { - "epoch": 1.77, - "learning_rate": 7.122001898696518e-07, - "loss": 0.5243, + "epoch": 1.56, + "learning_rate": 2.386126082939573e-06, + "loss": 0.6234, "step": 3434 }, { - "epoch": 1.77, - "learning_rate": 7.091173421366937e-07, - "loss": 0.5283, + "epoch": 1.56, + "learning_rate": 2.381344957811538e-06, + "loss": 0.6053, "step": 3435 }, { - "epoch": 1.77, - "learning_rate": 7.060409358455011e-07, - "loss": 0.6025, + "epoch": 1.57, + "learning_rate": 2.3765679799956265e-06, + "loss": 0.5887, "step": 3436 }, { - "epoch": 1.77, - "learning_rate": 7.029709731289724e-07, - "loss": 0.5945, + "epoch": 1.57, + "learning_rate": 2.37179515209225e-06, + "loss": 0.6073, "step": 3437 }, { - "epoch": 1.77, - "learning_rate": 6.999074561155361e-07, - "loss": 0.5702, + "epoch": 1.57, + "learning_rate": 2.3670264766995576e-06, + "loss": 0.589, "step": 3438 }, { - "epoch": 1.77, - "learning_rate": 6.968503869291521e-07, - "loss": 0.5747, + "epoch": 1.57, + "learning_rate": 2.362261956413441e-06, + "loss": 0.6012, "step": 3439 }, { - "epoch": 1.77, - "learning_rate": 6.937997676893115e-07, - "loss": 0.5836, + "epoch": 1.57, + "learning_rate": 2.3575015938275203e-06, + "loss": 0.5914, "step": 3440 }, { - "epoch": 1.77, - "learning_rate": 6.907556005110305e-07, - "loss": 0.5454, + "epoch": 1.57, + "learning_rate": 2.352745391533171e-06, + "loss": 0.6183, "step": 3441 }, { - "epoch": 1.77, - "learning_rate": 6.877178875048573e-07, - "loss": 0.5201, + "epoch": 1.57, + "learning_rate": 2.3479933521194844e-06, + "loss": 0.5658, "step": 3442 }, { - "epoch": 1.77, - "learning_rate": 6.846866307768607e-07, - "loss": 0.6194, + "epoch": 1.57, + "learning_rate": 2.343245478173294e-06, + "loss": 0.5955, "step": 3443 }, + { + "epoch": 1.57, + "learning_rate": 2.338501772279168e-06, + "loss": 0.5876, + "step": 3444 + }, + { + "epoch": 1.57, + "learning_rate": 2.3337622370194035e-06, + "loss": 0.5229, + "step": 3445 + }, + { + "epoch": 1.57, + "learning_rate": 2.3290268749740285e-06, + "loss": 0.5864, + "step": 3446 + }, + { + "epoch": 1.57, + "learning_rate": 2.3242956887207903e-06, + "loss": 0.5338, + "step": 3447 + }, + { + "epoch": 1.57, + "learning_rate": 2.31956868083518e-06, + "loss": 0.5732, + "step": 3448 + }, + { + "epoch": 1.57, + "learning_rate": 2.3148458538903985e-06, + "loss": 0.6071, + "step": 3449 + }, + { + "epoch": 1.57, + "learning_rate": 2.310127210457379e-06, + "loss": 0.6124, + "step": 3450 + }, + { + "epoch": 1.57, + "learning_rate": 2.3054127531047754e-06, + "loss": 0.5687, + "step": 3451 + }, + { + "epoch": 1.57, + "learning_rate": 2.3007024843989643e-06, + "loss": 0.5818, + "step": 3452 + }, + { + "epoch": 1.57, + "learning_rate": 2.295996406904034e-06, + "loss": 0.5779, + "step": 3453 + }, + { + "epoch": 1.57, + "learning_rate": 2.2912945231818073e-06, + "loss": 0.5533, + "step": 3454 + }, + { + "epoch": 1.57, + "learning_rate": 2.286596835791808e-06, + "loss": 0.5809, + "step": 3455 + }, + { + "epoch": 1.57, + "learning_rate": 2.2819033472912833e-06, + "loss": 0.599, + "step": 3456 + }, + { + "epoch": 1.57, + "learning_rate": 2.2772140602351954e-06, + "loss": 0.5592, + "step": 3457 + }, + { + "epoch": 1.58, + "learning_rate": 2.2725289771762195e-06, + "loss": 0.5977, + "step": 3458 + }, + { + "epoch": 1.58, + "learning_rate": 2.26784810066473e-06, + "loss": 0.5667, + "step": 3459 + }, + { + "epoch": 1.58, + "learning_rate": 2.2631714332488365e-06, + "loss": 0.6234, + "step": 3460 + }, + { + "epoch": 1.58, + "learning_rate": 2.2584989774743326e-06, + "loss": 0.5951, + "step": 3461 + }, + { + "epoch": 1.58, + "learning_rate": 2.253830735884731e-06, + "loss": 0.578, + "step": 3462 + }, + { + "epoch": 1.58, + "learning_rate": 2.2491667110212513e-06, + "loss": 0.5936, + "step": 3463 + }, + { + "epoch": 1.58, + "learning_rate": 2.244506905422814e-06, + "loss": 0.597, + "step": 3464 + }, + { + "epoch": 1.58, + "learning_rate": 2.2398513216260385e-06, + "loss": 0.5286, + "step": 3465 + }, + { + "epoch": 1.58, + "learning_rate": 2.235199962165261e-06, + "loss": 0.5908, + "step": 3466 + }, + { + "epoch": 1.58, + "learning_rate": 2.230552829572501e-06, + "loss": 0.5867, + "step": 3467 + }, + { + "epoch": 1.58, + "learning_rate": 2.2259099263774865e-06, + "loss": 0.6049, + "step": 3468 + }, + { + "epoch": 1.58, + "learning_rate": 2.2212712551076408e-06, + "loss": 0.6083, + "step": 3469 + }, + { + "epoch": 1.58, + "learning_rate": 2.216636818288087e-06, + "loss": 0.5942, + "step": 3470 + }, + { + "epoch": 1.58, + "learning_rate": 2.2120066184416356e-06, + "loss": 0.5964, + "step": 3471 + }, + { + "epoch": 1.58, + "learning_rate": 2.2073806580887946e-06, + "loss": 0.552, + "step": 3472 + }, + { + "epoch": 1.58, + "learning_rate": 2.2027589397477676e-06, + "loss": 0.5747, + "step": 3473 + }, + { + "epoch": 1.58, + "learning_rate": 2.1981414659344456e-06, + "loss": 0.5482, + "step": 3474 + }, + { + "epoch": 1.58, + "learning_rate": 2.193528239162408e-06, + "loss": 0.6007, + "step": 3475 + }, + { + "epoch": 1.58, + "learning_rate": 2.188919261942928e-06, + "loss": 0.558, + "step": 3476 + }, + { + "epoch": 1.58, + "learning_rate": 2.1843145367849537e-06, + "loss": 0.6049, + "step": 3477 + }, + { + "epoch": 1.58, + "learning_rate": 2.179714066195129e-06, + "loss": 0.6041, + "step": 3478 + }, + { + "epoch": 1.58, + "learning_rate": 2.175117852677784e-06, + "loss": 0.5729, + "step": 3479 + }, + { + "epoch": 1.59, + "learning_rate": 2.1705258987349188e-06, + "loss": 0.5919, + "step": 3480 + }, + { + "epoch": 1.59, + "learning_rate": 2.165938206866226e-06, + "loss": 0.6022, + "step": 3481 + }, + { + "epoch": 1.59, + "learning_rate": 2.1613547795690725e-06, + "loss": 0.5918, + "step": 3482 + }, + { + "epoch": 1.59, + "learning_rate": 2.1567756193385104e-06, + "loss": 0.5664, + "step": 3483 + }, + { + "epoch": 1.59, + "learning_rate": 2.152200728667254e-06, + "loss": 0.6362, + "step": 3484 + }, + { + "epoch": 1.59, + "learning_rate": 2.1476301100457154e-06, + "loss": 0.5414, + "step": 3485 + }, + { + "epoch": 1.59, + "learning_rate": 2.1430637659619614e-06, + "loss": 0.5648, + "step": 3486 + }, + { + "epoch": 1.59, + "learning_rate": 2.1385016989017402e-06, + "loss": 0.5996, + "step": 3487 + }, + { + "epoch": 1.59, + "learning_rate": 2.133943911348473e-06, + "loss": 0.5767, + "step": 3488 + }, + { + "epoch": 1.59, + "learning_rate": 2.1293904057832528e-06, + "loss": 0.566, + "step": 3489 + }, + { + "epoch": 1.59, + "learning_rate": 2.1248411846848315e-06, + "loss": 0.5795, + "step": 3490 + }, + { + "epoch": 1.59, + "learning_rate": 2.1202962505296387e-06, + "loss": 0.606, + "step": 3491 + }, + { + "epoch": 1.59, + "learning_rate": 2.1157556057917695e-06, + "loss": 0.5565, + "step": 3492 + }, + { + "epoch": 1.59, + "learning_rate": 2.1112192529429787e-06, + "loss": 0.6138, + "step": 3493 + }, + { + "epoch": 1.59, + "learning_rate": 2.106687194452689e-06, + "loss": 0.5353, + "step": 3494 + }, + { + "epoch": 1.59, + "learning_rate": 2.102159432787988e-06, + "loss": 0.6034, + "step": 3495 + }, + { + "epoch": 1.59, + "learning_rate": 2.097635970413615e-06, + "loss": 0.5336, + "step": 3496 + }, + { + "epoch": 1.59, + "learning_rate": 2.093116809791975e-06, + "loss": 0.5817, + "step": 3497 + }, + { + "epoch": 1.59, + "learning_rate": 2.0886019533831337e-06, + "loss": 0.6088, + "step": 3498 + }, + { + "epoch": 1.59, + "learning_rate": 2.0840914036448122e-06, + "loss": 0.5668, + "step": 3499 + }, + { + "epoch": 1.59, + "learning_rate": 2.079585163032377e-06, + "loss": 0.6086, + "step": 3500 + }, + { + "epoch": 1.59, + "learning_rate": 2.0750832339988703e-06, + "loss": 0.588, + "step": 3501 + }, + { + "epoch": 1.6, + "learning_rate": 2.0705856189949646e-06, + "loss": 0.5471, + "step": 3502 + }, + { + "epoch": 1.6, + "learning_rate": 2.0660923204689976e-06, + "loss": 0.595, + "step": 3503 + }, + { + "epoch": 1.6, + "learning_rate": 2.0616033408669545e-06, + "loss": 0.5763, + "step": 3504 + }, + { + "epoch": 1.6, + "learning_rate": 2.0571186826324697e-06, + "loss": 0.549, + "step": 3505 + }, + { + "epoch": 1.6, + "learning_rate": 2.052638348206818e-06, + "loss": 0.5719, + "step": 3506 + }, + { + "epoch": 1.6, + "learning_rate": 2.0481623400289354e-06, + "loss": 0.528, + "step": 3507 + }, + { + "epoch": 1.6, + "learning_rate": 2.043690660535388e-06, + "loss": 0.5496, + "step": 3508 + }, + { + "epoch": 1.6, + "learning_rate": 2.0392233121603922e-06, + "loss": 0.5706, + "step": 3509 + }, + { + "epoch": 1.6, + "learning_rate": 2.0347602973358073e-06, + "loss": 0.5526, + "step": 3510 + }, + { + "epoch": 1.6, + "learning_rate": 2.030301618491135e-06, + "loss": 0.5948, + "step": 3511 + }, + { + "epoch": 1.6, + "learning_rate": 2.0258472780535066e-06, + "loss": 0.532, + "step": 3512 + }, + { + "epoch": 1.6, + "learning_rate": 2.0213972784477064e-06, + "loss": 0.5826, + "step": 3513 + }, + { + "epoch": 1.6, + "learning_rate": 2.0169516220961484e-06, + "loss": 0.5653, + "step": 3514 + }, + { + "epoch": 1.6, + "learning_rate": 2.0125103114188773e-06, + "loss": 0.5908, + "step": 3515 + }, + { + "epoch": 1.6, + "learning_rate": 2.00807334883358e-06, + "loss": 0.6633, + "step": 3516 + }, + { + "epoch": 1.6, + "learning_rate": 2.0036407367555743e-06, + "loss": 0.6543, + "step": 3517 + }, + { + "epoch": 1.6, + "learning_rate": 1.9992124775978084e-06, + "loss": 0.5938, + "step": 3518 + }, + { + "epoch": 1.6, + "learning_rate": 1.9947885737708604e-06, + "loss": 0.5876, + "step": 3519 + }, + { + "epoch": 1.6, + "learning_rate": 1.9903690276829445e-06, + "loss": 0.5382, + "step": 3520 + }, + { + "epoch": 1.6, + "learning_rate": 1.9859538417398895e-06, + "loss": 0.5791, + "step": 3521 + }, + { + "epoch": 1.6, + "learning_rate": 1.9815430183451613e-06, + "loss": 0.5862, + "step": 3522 + }, + { + "epoch": 1.61, + "learning_rate": 1.9771365598998483e-06, + "loss": 0.5873, + "step": 3523 + }, + { + "epoch": 1.61, + "learning_rate": 1.9727344688026652e-06, + "loss": 0.5856, + "step": 3524 + }, + { + "epoch": 1.61, + "learning_rate": 1.9683367474499383e-06, + "loss": 0.5635, + "step": 3525 + }, + { + "epoch": 1.61, + "learning_rate": 1.9639433982356336e-06, + "loss": 0.5913, + "step": 3526 + }, + { + "epoch": 1.61, + "learning_rate": 1.9595544235513187e-06, + "loss": 0.5558, + "step": 3527 + }, + { + "epoch": 1.61, + "learning_rate": 1.955169825786192e-06, + "loss": 0.6196, + "step": 3528 + }, + { + "epoch": 1.61, + "learning_rate": 1.9507896073270637e-06, + "loss": 0.5549, + "step": 3529 + }, + { + "epoch": 1.61, + "learning_rate": 1.9464137705583653e-06, + "loss": 0.5834, + "step": 3530 + }, + { + "epoch": 1.61, + "learning_rate": 1.9420423178621308e-06, + "loss": 0.6593, + "step": 3531 + }, + { + "epoch": 1.61, + "learning_rate": 1.9376752516180276e-06, + "loss": 0.5887, + "step": 3532 + }, + { + "epoch": 1.61, + "learning_rate": 1.9333125742033153e-06, + "loss": 0.5636, + "step": 3533 + }, + { + "epoch": 1.61, + "learning_rate": 1.928954287992876e-06, + "loss": 0.6111, + "step": 3534 + }, + { + "epoch": 1.61, + "learning_rate": 1.9246003953591983e-06, + "loss": 0.5856, + "step": 3535 + }, + { + "epoch": 1.61, + "learning_rate": 1.9202508986723824e-06, + "loss": 0.6116, + "step": 3536 + }, + { + "epoch": 1.61, + "learning_rate": 1.915905800300124e-06, + "loss": 0.5776, + "step": 3537 + }, + { + "epoch": 1.61, + "learning_rate": 1.911565102607743e-06, + "loss": 0.5592, + "step": 3538 + }, + { + "epoch": 1.61, + "learning_rate": 1.9072288079581458e-06, + "loss": 0.6023, + "step": 3539 + }, + { + "epoch": 1.61, + "learning_rate": 1.902896918711853e-06, + "loss": 0.5765, + "step": 3540 + }, + { + "epoch": 1.61, + "learning_rate": 1.8985694372269836e-06, + "loss": 0.5568, + "step": 3541 + }, + { + "epoch": 1.61, + "learning_rate": 1.8942463658592602e-06, + "loss": 0.5829, + "step": 3542 + }, + { + "epoch": 1.61, + "learning_rate": 1.8899277069619959e-06, + "loss": 0.5897, + "step": 3543 + }, + { + "epoch": 1.61, + "learning_rate": 1.8856134628861111e-06, + "loss": 0.6158, + "step": 3544 + }, + { + "epoch": 1.62, + "learning_rate": 1.8813036359801197e-06, + "loss": 0.5938, + "step": 3545 + }, + { + "epoch": 1.62, + "learning_rate": 1.87699822859013e-06, + "loss": 0.5933, + "step": 3546 + }, + { + "epoch": 1.62, + "learning_rate": 1.8726972430598466e-06, + "loss": 0.5575, + "step": 3547 + }, + { + "epoch": 1.62, + "learning_rate": 1.8684006817305655e-06, + "loss": 0.5895, + "step": 3548 + }, + { + "epoch": 1.62, + "learning_rate": 1.8641085469411779e-06, + "loss": 0.563, + "step": 3549 + }, + { + "epoch": 1.62, + "learning_rate": 1.8598208410281527e-06, + "loss": 0.5933, + "step": 3550 + }, + { + "epoch": 1.62, + "learning_rate": 1.8555375663255691e-06, + "loss": 0.6122, + "step": 3551 + }, + { + "epoch": 1.62, + "learning_rate": 1.8512587251650739e-06, + "loss": 0.5874, + "step": 3552 + }, + { + "epoch": 1.62, + "learning_rate": 1.846984319875912e-06, + "loss": 0.5792, + "step": 3553 + }, + { + "epoch": 1.62, + "learning_rate": 1.84271435278491e-06, + "loss": 0.5718, + "step": 3554 + }, + { + "epoch": 1.62, + "learning_rate": 1.8384488262164823e-06, + "loss": 0.5652, + "step": 3555 + }, + { + "epoch": 1.62, + "learning_rate": 1.8341877424926146e-06, + "loss": 0.6049, + "step": 3556 + }, + { + "epoch": 1.62, + "learning_rate": 1.8299311039328926e-06, + "loss": 0.5696, + "step": 3557 + }, + { + "epoch": 1.62, + "learning_rate": 1.825678912854465e-06, + "loss": 0.599, + "step": 3558 + }, + { + "epoch": 1.62, + "learning_rate": 1.8214311715720667e-06, + "loss": 0.55, + "step": 3559 + }, + { + "epoch": 1.62, + "learning_rate": 1.8171878823980104e-06, + "loss": 0.5809, + "step": 3560 + }, + { + "epoch": 1.62, + "learning_rate": 1.8129490476421897e-06, + "loss": 0.5586, + "step": 3561 + }, + { + "epoch": 1.62, + "learning_rate": 1.8087146696120606e-06, + "loss": 0.5853, + "step": 3562 + }, + { + "epoch": 1.62, + "learning_rate": 1.804484750612664e-06, + "loss": 0.6079, + "step": 3563 + }, + { + "epoch": 1.62, + "learning_rate": 1.800259292946611e-06, + "loss": 0.6105, + "step": 3564 + }, + { + "epoch": 1.62, + "learning_rate": 1.7960382989140835e-06, + "loss": 0.6088, + "step": 3565 + }, + { + "epoch": 1.62, + "learning_rate": 1.7918217708128326e-06, + "loss": 0.5851, + "step": 3566 + }, + { + "epoch": 1.63, + "learning_rate": 1.7876097109381819e-06, + "loss": 0.5809, + "step": 3567 + }, + { + "epoch": 1.63, + "learning_rate": 1.7834021215830154e-06, + "loss": 0.5771, + "step": 3568 + }, + { + "epoch": 1.63, + "learning_rate": 1.7791990050377905e-06, + "loss": 0.6232, + "step": 3569 + }, + { + "epoch": 1.63, + "learning_rate": 1.7750003635905278e-06, + "loss": 0.5985, + "step": 3570 + }, + { + "epoch": 1.63, + "learning_rate": 1.7708061995268121e-06, + "loss": 0.6172, + "step": 3571 + }, + { + "epoch": 1.63, + "learning_rate": 1.7666165151297854e-06, + "loss": 0.5023, + "step": 3572 + }, + { + "epoch": 1.63, + "learning_rate": 1.762431312680163e-06, + "loss": 0.574, + "step": 3573 + }, + { + "epoch": 1.63, + "learning_rate": 1.7582505944562078e-06, + "loss": 0.5355, + "step": 3574 + }, + { + "epoch": 1.63, + "learning_rate": 1.7540743627337487e-06, + "loss": 0.5747, + "step": 3575 + }, + { + "epoch": 1.63, + "learning_rate": 1.7499026197861713e-06, + "loss": 0.5763, + "step": 3576 + }, + { + "epoch": 1.63, + "learning_rate": 1.745735367884419e-06, + "loss": 0.6195, + "step": 3577 + }, + { + "epoch": 1.63, + "learning_rate": 1.741572609296981e-06, + "loss": 0.5121, + "step": 3578 + }, + { + "epoch": 1.63, + "learning_rate": 1.7374143462899163e-06, + "loss": 0.6294, + "step": 3579 + }, + { + "epoch": 1.63, + "learning_rate": 1.7332605811268288e-06, + "loss": 0.6086, + "step": 3580 + }, + { + "epoch": 1.63, + "learning_rate": 1.7291113160688645e-06, + "loss": 0.6008, + "step": 3581 + }, + { + "epoch": 1.63, + "learning_rate": 1.7249665533747406e-06, + "loss": 0.5819, + "step": 3582 + }, + { + "epoch": 1.63, + "learning_rate": 1.7208262953007027e-06, + "loss": 0.6112, + "step": 3583 + }, + { + "epoch": 1.63, + "learning_rate": 1.7166905441005555e-06, + "loss": 0.6207, + "step": 3584 + }, + { + "epoch": 1.63, + "learning_rate": 1.7125593020256493e-06, + "loss": 0.5828, + "step": 3585 + }, + { + "epoch": 1.63, + "learning_rate": 1.7084325713248807e-06, + "loss": 0.5715, + "step": 3586 + }, + { + "epoch": 1.63, + "learning_rate": 1.7043103542446816e-06, + "loss": 0.5824, + "step": 3587 + }, + { + "epoch": 1.63, + "learning_rate": 1.700192653029038e-06, + "loss": 0.5574, + "step": 3588 + }, + { + "epoch": 1.64, + "learning_rate": 1.6960794699194715e-06, + "loss": 0.5809, + "step": 3589 + }, + { + "epoch": 1.64, + "learning_rate": 1.6919708071550478e-06, + "loss": 0.6245, + "step": 3590 + }, + { + "epoch": 1.64, + "learning_rate": 1.6878666669723675e-06, + "loss": 0.5687, + "step": 3591 + }, + { + "epoch": 1.64, + "learning_rate": 1.683767051605576e-06, + "loss": 0.5933, + "step": 3592 + }, + { + "epoch": 1.64, + "learning_rate": 1.6796719632863457e-06, + "loss": 0.5665, + "step": 3593 + }, + { + "epoch": 1.64, + "learning_rate": 1.6755814042438934e-06, + "loss": 0.6052, + "step": 3594 + }, + { + "epoch": 1.64, + "learning_rate": 1.6714953767049647e-06, + "loss": 0.5819, + "step": 3595 + }, + { + "epoch": 1.64, + "learning_rate": 1.6674138828938468e-06, + "loss": 0.5558, + "step": 3596 + }, + { + "epoch": 1.64, + "learning_rate": 1.6633369250323427e-06, + "loss": 0.5806, + "step": 3597 + }, + { + "epoch": 1.64, + "learning_rate": 1.6592645053398083e-06, + "loss": 0.5638, + "step": 3598 + }, + { + "epoch": 1.64, + "learning_rate": 1.6551966260331076e-06, + "loss": 0.5769, + "step": 3599 + }, + { + "epoch": 1.64, + "learning_rate": 1.6511332893266474e-06, + "loss": 0.5695, + "step": 3600 + }, + { + "epoch": 1.64, + "learning_rate": 1.6470744974323561e-06, + "loss": 0.6001, + "step": 3601 + }, + { + "epoch": 1.64, + "learning_rate": 1.6430202525596916e-06, + "loss": 0.6198, + "step": 3602 + }, + { + "epoch": 1.64, + "learning_rate": 1.6389705569156255e-06, + "loss": 0.657, + "step": 3603 + }, + { + "epoch": 1.64, + "learning_rate": 1.634925412704671e-06, + "loss": 0.5887, + "step": 3604 + }, + { + "epoch": 1.64, + "learning_rate": 1.6308848221288487e-06, + "loss": 0.59, + "step": 3605 + }, + { + "epoch": 1.64, + "learning_rate": 1.626848787387706e-06, + "loss": 0.6149, + "step": 3606 + }, + { + "epoch": 1.64, + "learning_rate": 1.6228173106783108e-06, + "loss": 0.6099, + "step": 3607 + }, + { + "epoch": 1.64, + "learning_rate": 1.618790394195251e-06, + "loss": 0.5887, + "step": 3608 + }, + { + "epoch": 1.64, + "learning_rate": 1.6147680401306232e-06, + "loss": 0.5767, + "step": 3609 + }, + { + "epoch": 1.64, + "learning_rate": 1.6107502506740568e-06, + "loss": 0.589, + "step": 3610 + }, + { + "epoch": 1.65, + "learning_rate": 1.6067370280126793e-06, + "loss": 0.6338, + "step": 3611 + }, + { + "epoch": 1.65, + "learning_rate": 1.6027283743311417e-06, + "loss": 0.5935, + "step": 3612 + }, + { + "epoch": 1.65, + "learning_rate": 1.5987242918116064e-06, + "loss": 0.5625, + "step": 3613 + }, + { + "epoch": 1.65, + "learning_rate": 1.5947247826337465e-06, + "loss": 0.5693, + "step": 3614 + }, + { + "epoch": 1.65, + "learning_rate": 1.5907298489747491e-06, + "loss": 0.5518, + "step": 3615 + }, + { + "epoch": 1.65, + "learning_rate": 1.5867394930092994e-06, + "loss": 0.5539, + "step": 3616 + }, + { + "epoch": 1.65, + "learning_rate": 1.5827537169096074e-06, + "loss": 0.5599, + "step": 3617 + }, + { + "epoch": 1.65, + "learning_rate": 1.5787725228453754e-06, + "loss": 0.5811, + "step": 3618 + }, + { + "epoch": 1.65, + "learning_rate": 1.5747959129838198e-06, + "loss": 0.5997, + "step": 3619 + }, + { + "epoch": 1.65, + "learning_rate": 1.5708238894896577e-06, + "loss": 0.6326, + "step": 3620 + }, + { + "epoch": 1.65, + "learning_rate": 1.566856454525113e-06, + "loss": 0.5983, + "step": 3621 + }, + { + "epoch": 1.65, + "learning_rate": 1.5628936102499048e-06, + "loss": 0.5231, + "step": 3622 + }, + { + "epoch": 1.65, + "learning_rate": 1.558935358821264e-06, + "loss": 0.6405, + "step": 3623 + }, + { + "epoch": 1.65, + "learning_rate": 1.5549817023939119e-06, + "loss": 0.5942, + "step": 3624 + }, + { + "epoch": 1.65, + "learning_rate": 1.5510326431200707e-06, + "loss": 0.5629, + "step": 3625 + }, + { + "epoch": 1.65, + "learning_rate": 1.5470881831494634e-06, + "loss": 0.5834, + "step": 3626 + }, + { + "epoch": 1.65, + "learning_rate": 1.543148324629309e-06, + "loss": 0.5465, + "step": 3627 + }, + { + "epoch": 1.65, + "learning_rate": 1.5392130697043118e-06, + "loss": 0.5564, + "step": 3628 + }, + { + "epoch": 1.65, + "learning_rate": 1.5352824205166894e-06, + "loss": 0.5891, + "step": 3629 + }, + { + "epoch": 1.65, + "learning_rate": 1.5313563792061326e-06, + "loss": 0.5818, + "step": 3630 + }, + { + "epoch": 1.65, + "learning_rate": 1.5274349479098339e-06, + "loss": 0.5471, + "step": 3631 + }, + { + "epoch": 1.65, + "learning_rate": 1.5235181287624756e-06, + "loss": 0.5985, + "step": 3632 + }, + { + "epoch": 1.66, + "learning_rate": 1.5196059238962301e-06, + "loss": 0.5084, + "step": 3633 + }, + { + "epoch": 1.66, + "learning_rate": 1.5156983354407516e-06, + "loss": 0.564, + "step": 3634 + }, + { + "epoch": 1.66, + "learning_rate": 1.5117953655231876e-06, + "loss": 0.6189, + "step": 3635 + }, + { + "epoch": 1.66, + "learning_rate": 1.5078970162681693e-06, + "loss": 0.5446, + "step": 3636 + }, + { + "epoch": 1.66, + "learning_rate": 1.504003289797814e-06, + "loss": 0.5538, + "step": 3637 + }, + { + "epoch": 1.66, + "learning_rate": 1.5001141882317216e-06, + "loss": 0.5657, + "step": 3638 + }, + { + "epoch": 1.66, + "learning_rate": 1.4962297136869751e-06, + "loss": 0.6086, + "step": 3639 + }, + { + "epoch": 1.66, + "learning_rate": 1.4923498682781334e-06, + "loss": 0.5481, + "step": 3640 + }, + { + "epoch": 1.66, + "learning_rate": 1.4884746541172435e-06, + "loss": 0.6335, + "step": 3641 + }, + { + "epoch": 1.66, + "learning_rate": 1.4846040733138257e-06, + "loss": 0.5935, + "step": 3642 + }, + { + "epoch": 1.66, + "learning_rate": 1.4807381279748822e-06, + "loss": 0.5959, + "step": 3643 + }, + { + "epoch": 1.66, + "learning_rate": 1.4768768202048877e-06, + "loss": 0.5759, + "step": 3644 + }, + { + "epoch": 1.66, + "learning_rate": 1.4730201521057986e-06, + "loss": 0.5957, + "step": 3645 + }, + { + "epoch": 1.66, + "learning_rate": 1.4691681257770351e-06, + "loss": 0.6061, + "step": 3646 + }, + { + "epoch": 1.66, + "learning_rate": 1.4653207433154981e-06, + "loss": 0.5499, + "step": 3647 + }, + { + "epoch": 1.66, + "learning_rate": 1.4614780068155654e-06, + "loss": 0.575, + "step": 3648 + }, + { + "epoch": 1.66, + "learning_rate": 1.4576399183690736e-06, + "loss": 0.5659, + "step": 3649 + }, + { + "epoch": 1.66, + "learning_rate": 1.4538064800653373e-06, + "loss": 0.6267, + "step": 3650 + }, + { + "epoch": 1.66, + "learning_rate": 1.449977693991137e-06, + "loss": 0.5695, + "step": 3651 + }, + { + "epoch": 1.66, + "learning_rate": 1.4461535622307232e-06, + "loss": 0.6086, + "step": 3652 + }, + { + "epoch": 1.66, + "learning_rate": 1.4423340868658052e-06, + "loss": 0.5486, + "step": 3653 + }, + { + "epoch": 1.66, + "learning_rate": 1.4385192699755723e-06, + "loss": 0.5829, + "step": 3654 + }, + { + "epoch": 1.67, + "learning_rate": 1.4347091136366608e-06, + "loss": 0.6106, + "step": 3655 + }, + { + "epoch": 1.67, + "learning_rate": 1.4309036199231808e-06, + "loss": 0.5713, + "step": 3656 + }, + { + "epoch": 1.67, + "learning_rate": 1.4271027909067014e-06, + "loss": 0.5225, + "step": 3657 + }, + { + "epoch": 1.67, + "learning_rate": 1.4233066286562548e-06, + "loss": 0.5696, + "step": 3658 + }, + { + "epoch": 1.67, + "learning_rate": 1.419515135238325e-06, + "loss": 0.5482, + "step": 3659 + }, + { + "epoch": 1.67, + "learning_rate": 1.415728312716863e-06, + "loss": 0.6018, + "step": 3660 + }, + { + "epoch": 1.67, + "learning_rate": 1.4119461631532749e-06, + "loss": 0.5444, + "step": 3661 + }, + { + "epoch": 1.67, + "learning_rate": 1.4081686886064206e-06, + "loss": 0.5765, + "step": 3662 + }, + { + "epoch": 1.67, + "learning_rate": 1.404395891132616e-06, + "loss": 0.571, + "step": 3663 + }, + { + "epoch": 1.67, + "learning_rate": 1.4006277727856355e-06, + "loss": 0.5581, + "step": 3664 + }, + { + "epoch": 1.67, + "learning_rate": 1.3968643356166966e-06, + "loss": 0.6036, + "step": 3665 + }, + { + "epoch": 1.67, + "learning_rate": 1.3931055816744776e-06, + "loss": 0.5812, + "step": 3666 + }, + { + "epoch": 1.67, + "learning_rate": 1.3893515130051038e-06, + "loss": 0.5094, + "step": 3667 + }, + { + "epoch": 1.67, + "learning_rate": 1.3856021316521528e-06, + "loss": 0.5826, + "step": 3668 + }, + { + "epoch": 1.67, + "learning_rate": 1.3818574396566408e-06, + "loss": 0.6101, + "step": 3669 + }, + { + "epoch": 1.67, + "learning_rate": 1.3781174390570496e-06, + "loss": 0.5818, + "step": 3670 + }, + { + "epoch": 1.67, + "learning_rate": 1.374382131889287e-06, + "loss": 0.5792, + "step": 3671 + }, + { + "epoch": 1.67, + "learning_rate": 1.3706515201867176e-06, + "loss": 0.595, + "step": 3672 + }, + { + "epoch": 1.67, + "learning_rate": 1.3669256059801495e-06, + "loss": 0.5664, + "step": 3673 + }, + { + "epoch": 1.67, + "learning_rate": 1.3632043912978332e-06, + "loss": 0.5491, + "step": 3674 + }, + { + "epoch": 1.67, + "learning_rate": 1.359487878165452e-06, + "loss": 0.5869, + "step": 3675 + }, + { + "epoch": 1.67, + "learning_rate": 1.3557760686061461e-06, + "loss": 0.5349, + "step": 3676 + }, + { + "epoch": 1.68, + "learning_rate": 1.3520689646404806e-06, + "loss": 0.6005, + "step": 3677 + }, + { + "epoch": 1.68, + "learning_rate": 1.3483665682864654e-06, + "loss": 0.5845, + "step": 3678 + }, + { + "epoch": 1.68, + "learning_rate": 1.3446688815595499e-06, + "loss": 0.6184, + "step": 3679 + }, + { + "epoch": 1.68, + "learning_rate": 1.3409759064726169e-06, + "loss": 0.5936, + "step": 3680 + }, + { + "epoch": 1.68, + "learning_rate": 1.3372876450359795e-06, + "loss": 0.6033, + "step": 3681 + }, + { + "epoch": 1.68, + "learning_rate": 1.3336040992573961e-06, + "loss": 0.558, + "step": 3682 + }, + { + "epoch": 1.68, + "learning_rate": 1.3299252711420507e-06, + "loss": 0.5997, + "step": 3683 + }, + { + "epoch": 1.68, + "learning_rate": 1.3262511626925568e-06, + "loss": 0.5623, + "step": 3684 + }, + { + "epoch": 1.68, + "learning_rate": 1.3225817759089654e-06, + "loss": 0.5682, + "step": 3685 + }, + { + "epoch": 1.68, + "learning_rate": 1.3189171127887524e-06, + "loss": 0.6042, + "step": 3686 + }, + { + "epoch": 1.68, + "learning_rate": 1.3152571753268274e-06, + "loss": 0.594, + "step": 3687 + }, + { + "epoch": 1.68, + "learning_rate": 1.3116019655155166e-06, + "loss": 0.5442, + "step": 3688 + }, + { + "epoch": 1.68, + "learning_rate": 1.3079514853445886e-06, + "loss": 0.6035, + "step": 3689 + }, + { + "epoch": 1.68, + "learning_rate": 1.3043057368012235e-06, + "loss": 0.594, + "step": 3690 + }, + { + "epoch": 1.68, + "learning_rate": 1.300664721870033e-06, + "loss": 0.5968, + "step": 3691 + }, + { + "epoch": 1.68, + "learning_rate": 1.2970284425330504e-06, + "loss": 0.6003, + "step": 3692 + }, + { + "epoch": 1.68, + "learning_rate": 1.2933969007697312e-06, + "loss": 0.5698, + "step": 3693 + }, + { + "epoch": 1.68, + "learning_rate": 1.289770098556946e-06, + "loss": 0.5376, + "step": 3694 + }, + { + "epoch": 1.68, + "learning_rate": 1.2861480378690005e-06, + "loss": 0.5581, + "step": 3695 + }, + { + "epoch": 1.68, + "learning_rate": 1.2825307206776016e-06, + "loss": 0.6036, + "step": 3696 + }, + { + "epoch": 1.68, + "learning_rate": 1.2789181489518854e-06, + "loss": 0.606, + "step": 3697 + }, + { + "epoch": 1.68, + "learning_rate": 1.2753103246584009e-06, + "loss": 0.5884, + "step": 3698 + }, + { + "epoch": 1.69, + "learning_rate": 1.271707249761116e-06, + "loss": 0.6097, + "step": 3699 + }, + { + "epoch": 1.69, + "learning_rate": 1.268108926221403e-06, + "loss": 0.608, + "step": 3700 + }, + { + "epoch": 1.69, + "learning_rate": 1.2645153559980649e-06, + "loss": 0.5665, + "step": 3701 + }, + { + "epoch": 1.69, + "learning_rate": 1.2609265410473003e-06, + "loss": 0.5516, + "step": 3702 + }, + { + "epoch": 1.69, + "learning_rate": 1.2573424833227287e-06, + "loss": 0.6013, + "step": 3703 + }, + { + "epoch": 1.69, + "learning_rate": 1.2537631847753784e-06, + "loss": 0.5796, + "step": 3704 + }, + { + "epoch": 1.69, + "learning_rate": 1.2501886473536885e-06, + "loss": 0.6294, + "step": 3705 + }, + { + "epoch": 1.69, + "learning_rate": 1.2466188730034968e-06, + "loss": 0.6171, + "step": 3706 + }, + { + "epoch": 1.69, + "learning_rate": 1.2430538636680634e-06, + "loss": 0.5575, + "step": 3707 + }, + { + "epoch": 1.69, + "learning_rate": 1.2394936212880416e-06, + "loss": 0.6085, + "step": 3708 + }, + { + "epoch": 1.69, + "learning_rate": 1.2359381478014976e-06, + "loss": 0.5989, + "step": 3709 + }, + { + "epoch": 1.69, + "learning_rate": 1.2323874451438966e-06, + "loss": 0.5721, + "step": 3710 + }, + { + "epoch": 1.69, + "learning_rate": 1.2288415152481126e-06, + "loss": 0.5686, + "step": 3711 + }, + { + "epoch": 1.69, + "learning_rate": 1.2253003600444125e-06, + "loss": 0.5972, + "step": 3712 + }, + { + "epoch": 1.69, + "learning_rate": 1.221763981460472e-06, + "loss": 0.5927, + "step": 3713 + }, + { + "epoch": 1.69, + "learning_rate": 1.2182323814213649e-06, + "loss": 0.556, + "step": 3714 + }, + { + "epoch": 1.69, + "learning_rate": 1.2147055618495617e-06, + "loss": 0.5676, + "step": 3715 + }, + { + "epoch": 1.69, + "learning_rate": 1.2111835246649318e-06, + "loss": 0.5839, + "step": 3716 + }, + { + "epoch": 1.69, + "learning_rate": 1.2076662717847399e-06, + "loss": 0.5662, + "step": 3717 + }, + { + "epoch": 1.69, + "learning_rate": 1.2041538051236523e-06, + "loss": 0.5901, + "step": 3718 + }, + { + "epoch": 1.69, + "learning_rate": 1.2006461265937163e-06, + "loss": 0.5394, + "step": 3719 + }, + { + "epoch": 1.69, + "learning_rate": 1.1971432381043912e-06, + "loss": 0.6062, + "step": 3720 + }, + { + "epoch": 1.7, + "learning_rate": 1.1936451415625127e-06, + "loss": 0.5593, + "step": 3721 + }, + { + "epoch": 1.7, + "learning_rate": 1.1901518388723154e-06, + "loss": 0.601, + "step": 3722 + }, + { + "epoch": 1.7, + "learning_rate": 1.1866633319354247e-06, + "loss": 0.5652, + "step": 3723 + }, + { + "epoch": 1.7, + "learning_rate": 1.1831796226508552e-06, + "loss": 0.5554, + "step": 3724 + }, + { + "epoch": 1.7, + "learning_rate": 1.1797007129150018e-06, + "loss": 0.6489, + "step": 3725 + }, + { + "epoch": 1.7, + "learning_rate": 1.1762266046216618e-06, + "loss": 0.6101, + "step": 3726 + }, + { + "epoch": 1.7, + "learning_rate": 1.1727572996620062e-06, + "loss": 0.5638, + "step": 3727 + }, + { + "epoch": 1.7, + "learning_rate": 1.169292799924594e-06, + "loss": 0.5437, + "step": 3728 + }, + { + "epoch": 1.7, + "learning_rate": 1.1658331072953731e-06, + "loss": 0.5572, + "step": 3729 + }, + { + "epoch": 1.7, + "learning_rate": 1.162378223657672e-06, + "loss": 0.6163, + "step": 3730 + }, + { + "epoch": 1.7, + "learning_rate": 1.1589281508921958e-06, + "loss": 0.6003, + "step": 3731 + }, + { + "epoch": 1.7, + "learning_rate": 1.1554828908770388e-06, + "loss": 0.5635, + "step": 3732 + }, + { + "epoch": 1.7, + "learning_rate": 1.152042445487672e-06, + "loss": 0.6212, + "step": 3733 + }, + { + "epoch": 1.7, + "learning_rate": 1.1486068165969465e-06, + "loss": 0.6245, + "step": 3734 + }, + { + "epoch": 1.7, + "learning_rate": 1.1451760060750893e-06, + "loss": 0.5968, + "step": 3735 + }, + { + "epoch": 1.7, + "learning_rate": 1.1417500157897088e-06, + "loss": 0.5706, + "step": 3736 + }, + { + "epoch": 1.7, + "learning_rate": 1.138328847605783e-06, + "loss": 0.5471, + "step": 3737 + }, + { + "epoch": 1.7, + "learning_rate": 1.134912503385669e-06, + "loss": 0.528, + "step": 3738 + }, + { + "epoch": 1.7, + "learning_rate": 1.131500984989099e-06, + "loss": 0.5823, + "step": 3739 + }, + { + "epoch": 1.7, + "learning_rate": 1.1280942942731775e-06, + "loss": 0.5734, + "step": 3740 + }, + { + "epoch": 1.7, + "learning_rate": 1.1246924330923736e-06, + "loss": 0.5548, + "step": 3741 + }, + { + "epoch": 1.7, + "learning_rate": 1.1212954032985445e-06, + "loss": 0.5769, + "step": 3742 + }, + { + "epoch": 1.71, + "learning_rate": 1.117903206740898e-06, + "loss": 0.6061, + "step": 3743 + }, + { + "epoch": 1.71, + "learning_rate": 1.114515845266022e-06, + "loss": 0.5686, + "step": 3744 + }, + { + "epoch": 1.71, + "learning_rate": 1.111133320717871e-06, + "loss": 0.592, + "step": 3745 + }, + { + "epoch": 1.71, + "learning_rate": 1.107755634937766e-06, + "loss": 0.6151, + "step": 3746 + }, + { + "epoch": 1.71, + "learning_rate": 1.104382789764389e-06, + "loss": 0.5497, + "step": 3747 + }, + { + "epoch": 1.71, + "learning_rate": 1.101014787033796e-06, + "loss": 0.5701, + "step": 3748 + }, + { + "epoch": 1.71, + "learning_rate": 1.0976516285794037e-06, + "loss": 0.5723, + "step": 3749 + }, + { + "epoch": 1.71, + "learning_rate": 1.0942933162319858e-06, + "loss": 0.5753, + "step": 3750 + }, + { + "epoch": 1.71, + "learning_rate": 1.0909398518196834e-06, + "loss": 0.6069, + "step": 3751 + }, + { + "epoch": 1.71, + "learning_rate": 1.0875912371679987e-06, + "loss": 0.5496, + "step": 3752 + }, + { + "epoch": 1.71, + "learning_rate": 1.0842474740997921e-06, + "loss": 0.6207, + "step": 3753 + }, + { + "epoch": 1.71, + "learning_rate": 1.0809085644352846e-06, + "loss": 0.6119, + "step": 3754 + }, + { + "epoch": 1.71, + "learning_rate": 1.0775745099920554e-06, + "loss": 0.5989, + "step": 3755 + }, + { + "epoch": 1.71, + "learning_rate": 1.0742453125850373e-06, + "loss": 0.5776, + "step": 3756 + }, + { + "epoch": 1.71, + "learning_rate": 1.0709209740265215e-06, + "loss": 0.5557, + "step": 3757 + }, + { + "epoch": 1.71, + "learning_rate": 1.0676014961261538e-06, + "loss": 0.6141, + "step": 3758 + }, + { + "epoch": 1.71, + "learning_rate": 1.064286880690939e-06, + "loss": 0.649, + "step": 3759 + }, + { + "epoch": 1.71, + "learning_rate": 1.0609771295252214e-06, + "loss": 0.6134, + "step": 3760 + }, + { + "epoch": 1.71, + "learning_rate": 1.0576722444307164e-06, + "loss": 0.6077, + "step": 3761 + }, + { + "epoch": 1.71, + "learning_rate": 1.0543722272064738e-06, + "loss": 0.6089, + "step": 3762 + }, + { + "epoch": 1.71, + "learning_rate": 1.051077079648901e-06, + "loss": 0.6176, + "step": 3763 + }, + { + "epoch": 1.71, + "learning_rate": 1.0477868035517558e-06, + "loss": 0.5537, + "step": 3764 + }, + { + "epoch": 1.72, + "learning_rate": 1.0445014007061416e-06, + "loss": 0.5306, + "step": 3765 + }, + { + "epoch": 1.72, + "learning_rate": 1.0412208729005046e-06, + "loss": 0.587, + "step": 3766 + }, + { + "epoch": 1.72, + "learning_rate": 1.037945221920651e-06, + "loss": 0.5642, + "step": 3767 + }, + { + "epoch": 1.72, + "learning_rate": 1.0346744495497153e-06, + "loss": 0.5717, + "step": 3768 + }, + { + "epoch": 1.72, + "learning_rate": 1.0314085575681865e-06, + "loss": 0.5874, + "step": 3769 + }, + { + "epoch": 1.72, + "learning_rate": 1.0281475477538961e-06, + "loss": 0.5964, + "step": 3770 + }, + { + "epoch": 1.72, + "learning_rate": 1.024891421882016e-06, + "loss": 0.5898, + "step": 3771 + }, + { + "epoch": 1.72, + "learning_rate": 1.0216401817250564e-06, + "loss": 0.5543, + "step": 3772 + }, + { + "epoch": 1.72, + "learning_rate": 1.0183938290528784e-06, + "loss": 0.5912, + "step": 3773 + }, + { + "epoch": 1.72, + "learning_rate": 1.015152365632669e-06, + "loss": 0.5886, + "step": 3774 + }, + { + "epoch": 1.72, + "learning_rate": 1.0119157932289625e-06, + "loss": 0.6012, + "step": 3775 + }, + { + "epoch": 1.72, + "learning_rate": 1.0086841136036285e-06, + "loss": 0.5504, + "step": 3776 + }, + { + "epoch": 1.72, + "learning_rate": 1.0054573285158752e-06, + "loss": 0.5967, + "step": 3777 + }, + { + "epoch": 1.72, + "learning_rate": 1.002235439722239e-06, + "loss": 0.5771, + "step": 3778 + }, + { + "epoch": 1.72, + "learning_rate": 9.99018448976602e-07, + "loss": 0.6185, + "step": 3779 + }, + { + "epoch": 1.72, + "learning_rate": 9.958063580301703e-07, + "loss": 0.6021, + "step": 3780 + }, + { + "epoch": 1.72, + "learning_rate": 9.925991686314874e-07, + "loss": 0.519, + "step": 3781 + }, + { + "epoch": 1.72, + "learning_rate": 9.893968825264277e-07, + "loss": 0.5537, + "step": 3782 + }, + { + "epoch": 1.72, + "learning_rate": 9.861995014581982e-07, + "loss": 0.5481, + "step": 3783 + }, + { + "epoch": 1.72, + "learning_rate": 9.830070271673342e-07, + "loss": 0.5819, + "step": 3784 + }, + { + "epoch": 1.72, + "learning_rate": 9.798194613916944e-07, + "loss": 0.5536, + "step": 3785 + }, + { + "epoch": 1.72, + "learning_rate": 9.766368058664788e-07, + "loss": 0.5579, + "step": 3786 + }, + { + "epoch": 1.73, + "learning_rate": 9.734590623242012e-07, + "loss": 0.5388, + "step": 3787 + }, + { + "epoch": 1.73, + "learning_rate": 9.702862324947082e-07, + "loss": 0.5872, + "step": 3788 + }, + { + "epoch": 1.73, + "learning_rate": 9.671183181051714e-07, + "loss": 0.5994, + "step": 3789 + }, + { + "epoch": 1.73, + "learning_rate": 9.639553208800856e-07, + "loss": 0.6151, + "step": 3790 + }, + { + "epoch": 1.73, + "learning_rate": 9.607972425412637e-07, + "loss": 0.5941, + "step": 3791 + }, + { + "epoch": 1.73, + "learning_rate": 9.576440848078538e-07, + "loss": 0.5326, + "step": 3792 + }, + { + "epoch": 1.73, + "learning_rate": 9.54495849396312e-07, + "loss": 0.5673, + "step": 3793 + }, + { + "epoch": 1.73, + "learning_rate": 9.513525380204225e-07, + "loss": 0.5729, + "step": 3794 + }, + { + "epoch": 1.73, + "learning_rate": 9.482141523912858e-07, + "loss": 0.6011, + "step": 3795 + }, + { + "epoch": 1.73, + "learning_rate": 9.450806942173252e-07, + "loss": 0.5795, + "step": 3796 + }, + { + "epoch": 1.73, + "learning_rate": 9.419521652042729e-07, + "loss": 0.597, + "step": 3797 + }, + { + "epoch": 1.73, + "learning_rate": 9.3882856705519e-07, + "loss": 0.5823, + "step": 3798 + }, + { + "epoch": 1.73, + "learning_rate": 9.35709901470443e-07, + "loss": 0.5544, + "step": 3799 + }, + { + "epoch": 1.73, + "learning_rate": 9.325961701477182e-07, + "loss": 0.5361, + "step": 3800 + }, + { + "epoch": 1.73, + "learning_rate": 9.294873747820154e-07, + "loss": 0.5432, + "step": 3801 + }, + { + "epoch": 1.73, + "learning_rate": 9.263835170656488e-07, + "loss": 0.5522, + "step": 3802 + }, + { + "epoch": 1.73, + "learning_rate": 9.232845986882399e-07, + "loss": 0.5452, + "step": 3803 + }, + { + "epoch": 1.73, + "learning_rate": 9.20190621336724e-07, + "loss": 0.5548, + "step": 3804 + }, + { + "epoch": 1.73, + "learning_rate": 9.171015866953503e-07, + "loss": 0.5814, + "step": 3805 + }, + { + "epoch": 1.73, + "learning_rate": 9.140174964456716e-07, + "loss": 0.5297, + "step": 3806 + }, + { + "epoch": 1.73, + "learning_rate": 9.109383522665538e-07, + "loss": 0.5272, + "step": 3807 + }, + { + "epoch": 1.73, + "learning_rate": 9.078641558341694e-07, + "loss": 0.5852, + "step": 3808 + }, + { + "epoch": 1.74, + "learning_rate": 9.047949088219921e-07, + "loss": 0.5542, + "step": 3809 + }, + { + "epoch": 1.74, + "learning_rate": 9.017306129008086e-07, + "loss": 0.5715, + "step": 3810 + }, + { + "epoch": 1.74, + "learning_rate": 8.986712697387068e-07, + "loss": 0.5841, + "step": 3811 + }, + { + "epoch": 1.74, + "learning_rate": 8.956168810010802e-07, + "loss": 0.5496, + "step": 3812 + }, + { + "epoch": 1.74, + "learning_rate": 8.925674483506219e-07, + "loss": 0.5287, + "step": 3813 + }, + { + "epoch": 1.74, + "learning_rate": 8.895229734473332e-07, + "loss": 0.6085, + "step": 3814 + }, + { + "epoch": 1.74, + "learning_rate": 8.864834579485093e-07, + "loss": 0.5764, + "step": 3815 + }, + { + "epoch": 1.74, + "learning_rate": 8.834489035087501e-07, + "loss": 0.6072, + "step": 3816 + }, + { + "epoch": 1.74, + "learning_rate": 8.804193117799575e-07, + "loss": 0.5607, + "step": 3817 + }, + { + "epoch": 1.74, + "learning_rate": 8.773946844113235e-07, + "loss": 0.5967, + "step": 3818 + }, + { + "epoch": 1.74, + "learning_rate": 8.743750230493453e-07, + "loss": 0.5743, + "step": 3819 + }, + { + "epoch": 1.74, + "learning_rate": 8.713603293378137e-07, + "loss": 0.5837, + "step": 3820 + }, + { + "epoch": 1.74, + "learning_rate": 8.683506049178169e-07, + "loss": 0.5853, + "step": 3821 + }, + { + "epoch": 1.74, + "learning_rate": 8.653458514277335e-07, + "loss": 0.6404, + "step": 3822 + }, + { + "epoch": 1.74, + "learning_rate": 8.623460705032416e-07, + "loss": 0.5573, + "step": 3823 + }, + { + "epoch": 1.74, + "learning_rate": 8.593512637773105e-07, + "loss": 0.5667, + "step": 3824 + }, + { + "epoch": 1.74, + "learning_rate": 8.563614328802006e-07, + "loss": 0.6002, + "step": 3825 + }, + { + "epoch": 1.74, + "learning_rate": 8.533765794394655e-07, + "loss": 0.6035, + "step": 3826 + }, + { + "epoch": 1.74, + "learning_rate": 8.503967050799488e-07, + "loss": 0.6404, + "step": 3827 + }, + { + "epoch": 1.74, + "learning_rate": 8.474218114237809e-07, + "loss": 0.5406, + "step": 3828 + }, + { + "epoch": 1.74, + "learning_rate": 8.44451900090384e-07, + "loss": 0.6125, + "step": 3829 + }, + { + "epoch": 1.74, + "learning_rate": 8.41486972696467e-07, + "loss": 0.5969, + "step": 3830 + }, + { + "epoch": 1.75, + "learning_rate": 8.385270308560267e-07, + "loss": 0.5966, + "step": 3831 + }, + { + "epoch": 1.75, + "learning_rate": 8.355720761803454e-07, + "loss": 0.6124, + "step": 3832 + }, + { + "epoch": 1.75, + "learning_rate": 8.326221102779919e-07, + "loss": 0.5852, + "step": 3833 + }, + { + "epoch": 1.75, + "learning_rate": 8.296771347548139e-07, + "loss": 0.5792, + "step": 3834 + }, + { + "epoch": 1.75, + "learning_rate": 8.267371512139488e-07, + "loss": 0.5703, + "step": 3835 + }, + { + "epoch": 1.75, + "learning_rate": 8.238021612558133e-07, + "loss": 0.5615, + "step": 3836 + }, + { + "epoch": 1.75, + "learning_rate": 8.208721664781083e-07, + "loss": 0.6237, + "step": 3837 + }, + { + "epoch": 1.75, + "learning_rate": 8.179471684758112e-07, + "loss": 0.5245, + "step": 3838 + }, + { + "epoch": 1.75, + "learning_rate": 8.150271688411848e-07, + "loss": 0.5999, + "step": 3839 + }, + { + "epoch": 1.75, + "learning_rate": 8.121121691637667e-07, + "loss": 0.5474, + "step": 3840 + }, + { + "epoch": 1.75, + "learning_rate": 8.092021710303743e-07, + "loss": 0.5802, + "step": 3841 + }, + { + "epoch": 1.75, + "learning_rate": 8.062971760251015e-07, + "loss": 0.6292, + "step": 3842 + }, + { + "epoch": 1.75, + "learning_rate": 8.033971857293221e-07, + "loss": 0.5571, + "step": 3843 + }, + { + "epoch": 1.75, + "learning_rate": 8.005022017216779e-07, + "loss": 0.6057, + "step": 3844 + }, + { + "epoch": 1.75, + "learning_rate": 7.976122255780971e-07, + "loss": 0.5715, + "step": 3845 + }, + { + "epoch": 1.75, + "learning_rate": 7.947272588717691e-07, + "loss": 0.6406, + "step": 3846 + }, + { + "epoch": 1.75, + "learning_rate": 7.918473031731655e-07, + "loss": 0.5816, + "step": 3847 + }, + { + "epoch": 1.75, + "learning_rate": 7.889723600500254e-07, + "loss": 0.6141, + "step": 3848 + }, + { + "epoch": 1.75, + "learning_rate": 7.861024310673637e-07, + "loss": 0.561, + "step": 3849 + }, + { + "epoch": 1.75, + "learning_rate": 7.832375177874574e-07, + "loss": 0.5568, + "step": 3850 + }, + { + "epoch": 1.75, + "learning_rate": 7.803776217698633e-07, + "loss": 0.6179, + "step": 3851 + }, + { + "epoch": 1.75, + "learning_rate": 7.775227445714029e-07, + "loss": 0.5651, + "step": 3852 + }, + { + "epoch": 1.76, + "learning_rate": 7.746728877461618e-07, + "loss": 0.6228, + "step": 3853 + }, + { + "epoch": 1.76, + "learning_rate": 7.718280528454969e-07, + "loss": 0.5535, + "step": 3854 + }, + { + "epoch": 1.76, + "learning_rate": 7.689882414180305e-07, + "loss": 0.5571, + "step": 3855 + }, + { + "epoch": 1.76, + "learning_rate": 7.661534550096528e-07, + "loss": 0.5465, + "step": 3856 + }, + { + "epoch": 1.76, + "learning_rate": 7.633236951635093e-07, + "loss": 0.5515, + "step": 3857 + }, + { + "epoch": 1.76, + "learning_rate": 7.604989634200244e-07, + "loss": 0.556, + "step": 3858 + }, + { + "epoch": 1.76, + "learning_rate": 7.576792613168704e-07, + "loss": 0.5405, + "step": 3859 + }, + { + "epoch": 1.76, + "learning_rate": 7.548645903889906e-07, + "loss": 0.5955, + "step": 3860 + }, + { + "epoch": 1.76, + "learning_rate": 7.520549521685871e-07, + "loss": 0.5885, + "step": 3861 + }, + { + "epoch": 1.76, + "learning_rate": 7.492503481851232e-07, + "loss": 0.5818, + "step": 3862 + }, + { + "epoch": 1.76, + "learning_rate": 7.464507799653165e-07, + "loss": 0.5714, + "step": 3863 + }, + { + "epoch": 1.76, + "learning_rate": 7.436562490331544e-07, + "loss": 0.5791, + "step": 3864 + }, + { + "epoch": 1.76, + "learning_rate": 7.408667569098715e-07, + "loss": 0.6039, + "step": 3865 + }, + { + "epoch": 1.76, + "learning_rate": 7.380823051139629e-07, + "loss": 0.6147, + "step": 3866 + }, + { + "epoch": 1.76, + "learning_rate": 7.353028951611818e-07, + "loss": 0.5321, + "step": 3867 + }, + { + "epoch": 1.76, + "learning_rate": 7.325285285645367e-07, + "loss": 0.5577, + "step": 3868 + }, + { + "epoch": 1.76, + "learning_rate": 7.297592068342851e-07, + "loss": 0.5548, + "step": 3869 + }, + { + "epoch": 1.76, + "learning_rate": 7.26994931477949e-07, + "loss": 0.5529, + "step": 3870 + }, + { + "epoch": 1.76, + "learning_rate": 7.242357040002912e-07, + "loss": 0.5872, + "step": 3871 + }, + { + "epoch": 1.76, + "learning_rate": 7.214815259033359e-07, + "loss": 0.5864, + "step": 3872 + }, + { + "epoch": 1.76, + "learning_rate": 7.187323986863526e-07, + "loss": 0.5935, + "step": 3873 + }, + { + "epoch": 1.76, + "learning_rate": 7.159883238458675e-07, + "loss": 0.6138, + "step": 3874 + }, { "epoch": 1.77, - "learning_rate": 6.81661832428635e-07, - "loss": 0.5825, - "step": 3444 + "learning_rate": 7.132493028756493e-07, + "loss": 0.5606, + "step": 3875 }, { "epoch": 1.77, - "learning_rate": 6.78643494557295e-07, - "loss": 0.5406, - "step": 3445 + "learning_rate": 7.105153372667195e-07, + "loss": 0.5645, + "step": 3876 }, { "epoch": 1.77, - "learning_rate": 6.756316192554791e-07, - "loss": 0.5392, - "step": 3446 + "learning_rate": 7.077864285073477e-07, + "loss": 0.556, + "step": 3877 }, { "epoch": 1.77, - "learning_rate": 6.726262086113455e-07, - "loss": 0.5802, - "step": 3447 + "learning_rate": 7.050625780830511e-07, + "loss": 0.5822, + "step": 3878 }, { "epoch": 1.77, - "learning_rate": 6.696272647085667e-07, - "loss": 0.562, - "step": 3448 + "learning_rate": 7.023437874765903e-07, + "loss": 0.5725, + "step": 3879 }, { "epoch": 1.77, - "learning_rate": 6.666347896263326e-07, - "loss": 0.5803, - "step": 3449 + "learning_rate": 6.996300581679782e-07, + "loss": 0.5907, + "step": 3880 }, { "epoch": 1.77, - "learning_rate": 6.636487854393536e-07, - "loss": 0.5757, - "step": 3450 + "learning_rate": 6.969213916344619e-07, + "loss": 0.588, + "step": 3881 }, { "epoch": 1.77, - "learning_rate": 6.606692542178472e-07, - "loss": 0.5419, - "step": 3451 + "learning_rate": 6.942177893505431e-07, + "loss": 0.4935, + "step": 3882 }, { "epoch": 1.77, - "learning_rate": 6.576961980275476e-07, - "loss": 0.5812, - "step": 3452 + "learning_rate": 6.915192527879599e-07, + "loss": 0.6189, + "step": 3883 }, { "epoch": 1.77, - "learning_rate": 6.54729618929697e-07, - "loss": 0.5671, - "step": 3453 + "learning_rate": 6.888257834156953e-07, + "loss": 0.5518, + "step": 3884 + }, + { + "epoch": 1.77, + "learning_rate": 6.861373826999751e-07, + "loss": 0.5466, + "step": 3885 + }, + { + "epoch": 1.77, + "learning_rate": 6.834540521042643e-07, + "loss": 0.5635, + "step": 3886 + }, + { + "epoch": 1.77, + "learning_rate": 6.807757930892678e-07, + "loss": 0.5781, + "step": 3887 + }, + { + "epoch": 1.77, + "learning_rate": 6.781026071129282e-07, + "loss": 0.6016, + "step": 3888 + }, + { + "epoch": 1.77, + "learning_rate": 6.754344956304327e-07, + "loss": 0.5562, + "step": 3889 + }, + { + "epoch": 1.77, + "learning_rate": 6.72771460094197e-07, + "loss": 0.5626, + "step": 3890 + }, + { + "epoch": 1.77, + "learning_rate": 6.701135019538818e-07, + "loss": 0.582, + "step": 3891 + }, + { + "epoch": 1.77, + "learning_rate": 6.674606226563785e-07, + "loss": 0.532, + "step": 3892 + }, + { + "epoch": 1.77, + "learning_rate": 6.648128236458195e-07, + "loss": 0.5806, + "step": 3893 + }, + { + "epoch": 1.77, + "learning_rate": 6.621701063635622e-07, + "loss": 0.6121, + "step": 3894 + }, + { + "epoch": 1.77, + "learning_rate": 6.595324722482089e-07, + "loss": 0.5927, + "step": 3895 + }, + { + "epoch": 1.77, + "learning_rate": 6.568999227355855e-07, + "loss": 0.5028, + "step": 3896 }, { "epoch": 1.78, - "learning_rate": 6.517695189810491e-07, - "loss": 0.5814, - "step": 3454 + "learning_rate": 6.542724592587557e-07, + "loss": 0.601, + "step": 3897 }, { "epoch": 1.78, - "learning_rate": 6.488159002338623e-07, - "loss": 0.551, - "step": 3455 + "learning_rate": 6.516500832480133e-07, + "loss": 0.6001, + "step": 3898 }, { "epoch": 1.78, - "learning_rate": 6.458687647359041e-07, + "learning_rate": 6.490327961308829e-07, + "loss": 0.6246, + "step": 3899 + }, + { + "epoch": 1.78, + "learning_rate": 6.464205993321149e-07, + "loss": 0.5996, + "step": 3900 + }, + { + "epoch": 1.78, + "learning_rate": 6.43813494273694e-07, "loss": 0.5729, - "step": 3456 + "step": 3901 }, { "epoch": 1.78, - "learning_rate": 6.429281145304478e-07, - "loss": 0.572, - "step": 3457 + "learning_rate": 6.412114823748305e-07, + "loss": 0.5569, + "step": 3902 }, { "epoch": 1.78, - "learning_rate": 6.399939516562681e-07, - "loss": 0.5673, - "step": 3458 + "learning_rate": 6.386145650519637e-07, + "loss": 0.5801, + "step": 3903 }, { "epoch": 1.78, - "learning_rate": 6.370662781476423e-07, - "loss": 0.5753, - "step": 3459 + "learning_rate": 6.360227437187572e-07, + "loss": 0.5662, + "step": 3904 }, { "epoch": 1.78, - "learning_rate": 6.341450960343509e-07, - "loss": 0.6162, - "step": 3460 + "learning_rate": 6.334360197861056e-07, + "loss": 0.5383, + "step": 3905 }, { "epoch": 1.78, - "learning_rate": 6.31230407341672e-07, - "loss": 0.5358, - "step": 3461 + "learning_rate": 6.308543946621204e-07, + "loss": 0.5464, + "step": 3906 }, { "epoch": 1.78, - "learning_rate": 6.283222140903833e-07, - "loss": 0.5763, - "step": 3462 + "learning_rate": 6.282778697521452e-07, + "loss": 0.5778, + "step": 3907 }, { "epoch": 1.78, - "learning_rate": 6.254205182967566e-07, - "loss": 0.5431, - "step": 3463 + "learning_rate": 6.257064464587425e-07, + "loss": 0.577, + "step": 3908 }, { "epoch": 1.78, - "learning_rate": 6.225253219725613e-07, - "loss": 0.5593, - "step": 3464 + "learning_rate": 6.231401261817027e-07, + "loss": 0.6151, + "step": 3909 }, { "epoch": 1.78, - "learning_rate": 6.196366271250586e-07, - "loss": 0.53, - "step": 3465 + "learning_rate": 6.205789103180282e-07, + "loss": 0.6235, + "step": 3910 }, { "epoch": 1.78, - "learning_rate": 6.167544357570033e-07, - "loss": 0.5483, - "step": 3466 + "learning_rate": 6.180228002619581e-07, + "loss": 0.5864, + "step": 3911 }, { "epoch": 1.78, - "learning_rate": 6.138787498666421e-07, - "loss": 0.5248, - "step": 3467 + "learning_rate": 6.154717974049374e-07, + "loss": 0.5814, + "step": 3912 }, { "epoch": 1.78, - "learning_rate": 6.110095714477104e-07, - "loss": 0.5601, - "step": 3468 + "learning_rate": 6.129259031356383e-07, + "loss": 0.5441, + "step": 3913 }, { "epoch": 1.78, - "learning_rate": 6.081469024894293e-07, - "loss": 0.5399, - "step": 3469 + "learning_rate": 6.103851188399523e-07, + "loss": 0.5651, + "step": 3914 }, { "epoch": 1.78, - "learning_rate": 6.052907449765144e-07, - "loss": 0.5721, - "step": 3470 + "learning_rate": 6.078494459009887e-07, + "loss": 0.5867, + "step": 3915 }, { "epoch": 1.78, - "learning_rate": 6.024411008891584e-07, - "loss": 0.5728, - "step": 3471 + "learning_rate": 6.053188856990688e-07, + "loss": 0.5469, + "step": 3916 }, { "epoch": 1.78, - "learning_rate": 5.995979722030443e-07, - "loss": 0.5894, - "step": 3472 + "learning_rate": 6.027934396117397e-07, + "loss": 0.5763, + "step": 3917 + }, + { + "epoch": 1.78, + "learning_rate": 6.002731090137593e-07, + "loss": 0.5754, + "step": 3918 }, { "epoch": 1.79, - "learning_rate": 5.967613608893352e-07, - "loss": 0.5839, - "step": 3473 + "learning_rate": 5.977578952771013e-07, + "loss": 0.5912, + "step": 3919 }, { "epoch": 1.79, - "learning_rate": 5.939312689146747e-07, - "loss": 0.5645, - "step": 3474 + "learning_rate": 5.952477997709527e-07, + "loss": 0.5587, + "step": 3920 }, { "epoch": 1.79, - "learning_rate": 5.911076982411879e-07, - "loss": 0.5271, - "step": 3475 + "learning_rate": 5.927428238617184e-07, + "loss": 0.5629, + "step": 3921 + }, + { + "epoch": 1.79, + "learning_rate": 5.90242968913014e-07, + "loss": 0.59, + "step": 3922 + }, + { + "epoch": 1.79, + "learning_rate": 5.877482362856657e-07, + "loss": 0.5359, + "step": 3923 + }, + { + "epoch": 1.79, + "learning_rate": 5.852586273377158e-07, + "loss": 0.6233, + "step": 3924 }, { "epoch": 1.79, - "learning_rate": 5.882906508264796e-07, - "loss": 0.5823, - "step": 3476 + "learning_rate": 5.827741434244127e-07, + "loss": 0.5549, + "step": 3925 }, { "epoch": 1.79, - "learning_rate": 5.8548012862363e-07, - "loss": 0.5446, - "step": 3477 + "learning_rate": 5.802947858982156e-07, + "loss": 0.5964, + "step": 3926 }, { "epoch": 1.79, - "learning_rate": 5.82676133581197e-07, - "loss": 0.5546, - "step": 3478 + "learning_rate": 5.778205561087969e-07, + "loss": 0.5701, + "step": 3927 }, { "epoch": 1.79, - "learning_rate": 5.798786676432089e-07, - "loss": 0.5754, - "step": 3479 + "learning_rate": 5.75351455403036e-07, + "loss": 0.5854, + "step": 3928 }, { "epoch": 1.79, - "learning_rate": 5.770877327491753e-07, - "loss": 0.5911, - "step": 3480 + "learning_rate": 5.728874851250143e-07, + "loss": 0.558, + "step": 3929 }, { "epoch": 1.79, - "learning_rate": 5.743033308340707e-07, - "loss": 0.5038, - "step": 3481 + "learning_rate": 5.704286466160314e-07, + "loss": 0.5933, + "step": 3930 }, { "epoch": 1.79, - "learning_rate": 5.715254638283441e-07, - "loss": 0.5634, - "step": 3482 + "learning_rate": 5.679749412145841e-07, + "loss": 0.5953, + "step": 3931 }, { "epoch": 1.79, - "learning_rate": 5.687541336579127e-07, - "loss": 0.5638, - "step": 3483 + "learning_rate": 5.655263702563796e-07, + "loss": 0.5869, + "step": 3932 }, { "epoch": 1.79, - "learning_rate": 5.659893422441598e-07, - "loss": 0.5601, - "step": 3484 + "learning_rate": 5.630829350743272e-07, + "loss": 0.573, + "step": 3933 }, { "epoch": 1.79, - "learning_rate": 5.632310915039385e-07, - "loss": 0.5497, - "step": 3485 + "learning_rate": 5.606446369985452e-07, + "loss": 0.5774, + "step": 3934 }, { "epoch": 1.79, - "learning_rate": 5.604793833495637e-07, - "loss": 0.569, - "step": 3486 + "learning_rate": 5.582114773563474e-07, + "loss": 0.5676, + "step": 3935 }, { "epoch": 1.79, - "learning_rate": 5.577342196888192e-07, - "loss": 0.5402, - "step": 3487 + "learning_rate": 5.557834574722598e-07, + "loss": 0.6346, + "step": 3936 }, { "epoch": 1.79, - "learning_rate": 5.549956024249459e-07, - "loss": 0.5121, - "step": 3488 + "learning_rate": 5.533605786680041e-07, + "loss": 0.5565, + "step": 3937 }, { "epoch": 1.79, - "learning_rate": 5.522635334566473e-07, - "loss": 0.5847, - "step": 3489 + "learning_rate": 5.509428422625051e-07, + "loss": 0.5858, + "step": 3938 }, { "epoch": 1.79, - "learning_rate": 5.495380146780915e-07, - "loss": 0.5768, - "step": 3490 + "learning_rate": 5.48530249571888e-07, + "loss": 0.5458, + "step": 3939 }, { "epoch": 1.79, - "learning_rate": 5.468190479789015e-07, - "loss": 0.5145, - "step": 3491 + "learning_rate": 5.461228019094822e-07, + "loss": 0.5629, + "step": 3940 }, { - "epoch": 1.79, - "learning_rate": 5.441066352441581e-07, - "loss": 0.5483, - "step": 3492 + "epoch": 1.8, + "learning_rate": 5.43720500585806e-07, + "loss": 0.5603, + "step": 3941 }, { "epoch": 1.8, - "learning_rate": 5.414007783543985e-07, + "learning_rate": 5.413233469085888e-07, "loss": 0.5829, - "step": 3493 + "step": 3942 }, { "epoch": 1.8, - "learning_rate": 5.387014791856127e-07, - "loss": 0.5581, - "step": 3494 + "learning_rate": 5.389313421827491e-07, + "loss": 0.6198, + "step": 3943 }, { "epoch": 1.8, - "learning_rate": 5.360087396092473e-07, - "loss": 0.5444, - "step": 3495 + "learning_rate": 5.365444877104042e-07, + "loss": 0.589, + "step": 3944 }, { "epoch": 1.8, - "learning_rate": 5.333225614922e-07, - "loss": 0.5706, - "step": 3496 + "learning_rate": 5.341627847908715e-07, + "loss": 0.5864, + "step": 3945 }, { "epoch": 1.8, - "learning_rate": 5.306429466968188e-07, - "loss": 0.5586, - "step": 3497 + "learning_rate": 5.317862347206615e-07, + "loss": 0.6033, + "step": 3946 }, { "epoch": 1.8, - "learning_rate": 5.279698970809011e-07, - "loss": 0.5366, - "step": 3498 + "learning_rate": 5.294148387934761e-07, + "loss": 0.5961, + "step": 3947 }, { "epoch": 1.8, - "learning_rate": 5.253034144976921e-07, - "loss": 0.5491, - "step": 3499 + "learning_rate": 5.27048598300216e-07, + "loss": 0.5985, + "step": 3948 }, { "epoch": 1.8, - "learning_rate": 5.226435007958864e-07, - "loss": 0.5673, - "step": 3500 + "learning_rate": 5.246875145289765e-07, + "loss": 0.5583, + "step": 3949 }, { "epoch": 1.8, - "learning_rate": 5.199901578196254e-07, - "loss": 0.5824, - "step": 3501 + "learning_rate": 5.223315887650427e-07, + "loss": 0.5942, + "step": 3950 }, { "epoch": 1.8, - "learning_rate": 5.173433874084898e-07, - "loss": 0.6047, - "step": 3502 + "learning_rate": 5.19980822290892e-07, + "loss": 0.5897, + "step": 3951 }, { "epoch": 1.8, - "learning_rate": 5.147031913975065e-07, - "loss": 0.5585, - "step": 3503 + "learning_rate": 5.176352163861964e-07, + "loss": 0.5876, + "step": 3952 }, { "epoch": 1.8, - "learning_rate": 5.120695716171453e-07, - "loss": 0.4918, - "step": 3504 + "learning_rate": 5.152947723278145e-07, + "loss": 0.5455, + "step": 3953 }, { "epoch": 1.8, - "learning_rate": 5.094425298933136e-07, - "loss": 0.5646, - "step": 3505 + "learning_rate": 5.12959491389795e-07, + "loss": 0.6033, + "step": 3954 }, { "epoch": 1.8, - "learning_rate": 5.068220680473623e-07, - "loss": 0.6238, - "step": 3506 + "learning_rate": 5.106293748433833e-07, + "loss": 0.6282, + "step": 3955 }, { "epoch": 1.8, - "learning_rate": 5.042081878960759e-07, - "loss": 0.5485, - "step": 3507 + "learning_rate": 5.083044239570034e-07, + "loss": 0.5845, + "step": 3956 }, { "epoch": 1.8, - "learning_rate": 5.016008912516789e-07, - "loss": 0.5396, - "step": 3508 + "learning_rate": 5.059846399962742e-07, + "loss": 0.5765, + "step": 3957 }, { "epoch": 1.8, - "learning_rate": 4.990001799218292e-07, - "loss": 0.5557, - "step": 3509 + "learning_rate": 5.036700242239978e-07, + "loss": 0.5878, + "step": 3958 }, { "epoch": 1.8, - "learning_rate": 4.964060557096217e-07, - "loss": 0.5638, - "step": 3510 + "learning_rate": 5.013605779001685e-07, + "loss": 0.5292, + "step": 3959 }, { "epoch": 1.8, - "learning_rate": 4.938185204135837e-07, - "loss": 0.5126, - "step": 3511 + "learning_rate": 4.990563022819573e-07, + "loss": 0.5984, + "step": 3960 + }, + { + "epoch": 1.8, + "learning_rate": 4.967571986237319e-07, + "loss": 0.6156, + "step": 3961 }, { "epoch": 1.81, - "learning_rate": 4.912375758276744e-07, - "loss": 0.5692, - "step": 3512 + "learning_rate": 4.944632681770345e-07, + "loss": 0.5464, + "step": 3962 }, { "epoch": 1.81, - "learning_rate": 4.886632237412803e-07, - "loss": 0.5684, - "step": 3513 + "learning_rate": 4.921745121905974e-07, + "loss": 0.6262, + "step": 3963 }, { "epoch": 1.81, - "learning_rate": 4.860954659392214e-07, - "loss": 0.5803, - "step": 3514 + "learning_rate": 4.89890931910334e-07, + "loss": 0.5702, + "step": 3964 }, { "epoch": 1.81, - "learning_rate": 4.835343042017449e-07, - "loss": 0.5551, - "step": 3515 + "learning_rate": 4.876125285793409e-07, + "loss": 0.5728, + "step": 3965 }, { "epoch": 1.81, - "learning_rate": 4.809797403045224e-07, - "loss": 0.543, - "step": 3516 + "learning_rate": 4.853393034378928e-07, + "loss": 0.6198, + "step": 3966 }, { "epoch": 1.81, - "learning_rate": 4.784317760186541e-07, - "loss": 0.5765, - "step": 3517 + "learning_rate": 4.830712577234542e-07, + "loss": 0.5676, + "step": 3967 }, { "epoch": 1.81, - "learning_rate": 4.758904131106623e-07, - "loss": 0.5449, - "step": 3518 + "learning_rate": 4.808083926706597e-07, + "loss": 0.6017, + "step": 3968 }, { "epoch": 1.81, - "learning_rate": 4.7335565334249767e-07, - "loss": 0.5831, - "step": 3519 + "learning_rate": 4.785507095113318e-07, + "loss": 0.5748, + "step": 3969 }, { "epoch": 1.81, - "learning_rate": 4.708274984715233e-07, - "loss": 0.5654, - "step": 3520 + "learning_rate": 4.7629820947446726e-07, + "loss": 0.5808, + "step": 3970 }, { "epoch": 1.81, - "learning_rate": 4.6830595025053494e-07, - "loss": 0.5638, - "step": 3521 + "learning_rate": 4.7405089378624647e-07, + "loss": 0.5393, + "step": 3971 }, { "epoch": 1.81, - "learning_rate": 4.6579101042773745e-07, - "loss": 0.5806, - "step": 3522 + "learning_rate": 4.718087636700197e-07, + "loss": 0.5656, + "step": 3972 }, { "epoch": 1.81, - "learning_rate": 4.6328268074676054e-07, - "loss": 0.5739, - "step": 3523 + "learning_rate": 4.695718203463229e-07, + "loss": 0.6072, + "step": 3973 }, { "epoch": 1.81, - "learning_rate": 4.6078096294664643e-07, - "loss": 0.5806, - "step": 3524 + "learning_rate": 4.673400650328619e-07, + "loss": 0.5966, + "step": 3974 }, { "epoch": 1.81, - "learning_rate": 4.5828585876185883e-07, - "loss": 0.569, - "step": 3525 + "learning_rate": 4.6511349894452384e-07, + "loss": 0.6185, + "step": 3975 }, { "epoch": 1.81, - "learning_rate": 4.557973699222706e-07, - "loss": 0.5785, - "step": 3526 + "learning_rate": 4.6289212329336696e-07, + "loss": 0.5437, + "step": 3976 }, { "epoch": 1.81, - "learning_rate": 4.533154981531718e-07, - "loss": 0.5723, - "step": 3527 + "learning_rate": 4.606759392886262e-07, + "loss": 0.6128, + "step": 3977 }, { "epoch": 1.81, - "learning_rate": 4.5084024517526136e-07, - "loss": 0.5458, - "step": 3528 + "learning_rate": 4.5846494813670873e-07, + "loss": 0.5886, + "step": 3978 }, { "epoch": 1.81, - "learning_rate": 4.4837161270465445e-07, - "loss": 0.5403, - "step": 3529 + "learning_rate": 4.562591510411962e-07, + "loss": 0.6052, + "step": 3979 }, { "epoch": 1.81, - "learning_rate": 4.4590960245287086e-07, - "loss": 0.5585, - "step": 3530 + "learning_rate": 4.5405854920284153e-07, + "loss": 0.5557, + "step": 3980 }, { "epoch": 1.81, - "learning_rate": 4.4345421612684404e-07, - "loss": 0.583, - "step": 3531 + "learning_rate": 4.518631438195731e-07, + "loss": 0.5432, + "step": 3981 + }, + { + "epoch": 1.81, + "learning_rate": 4.4967293608648374e-07, + "loss": 0.5897, + "step": 3982 + }, + { + "epoch": 1.81, + "learning_rate": 4.4748792719584544e-07, + "loss": 0.6084, + "step": 3983 }, { "epoch": 1.82, - "learning_rate": 4.4100545542891227e-07, - "loss": 0.5834, - "step": 3532 + "learning_rate": 4.453081183370922e-07, + "loss": 0.6147, + "step": 3984 }, { "epoch": 1.82, - "learning_rate": 4.385633220568186e-07, - "loss": 0.5509, - "step": 3533 + "learning_rate": 4.431335106968315e-07, + "loss": 0.5957, + "step": 3985 }, { "epoch": 1.82, - "learning_rate": 4.361278177037154e-07, - "loss": 0.5677, - "step": 3534 + "learning_rate": 4.4096410545884094e-07, + "loss": 0.5685, + "step": 3986 }, { "epoch": 1.82, - "learning_rate": 4.3369894405815517e-07, - "loss": 0.5828, - "step": 3535 + "learning_rate": 4.3879990380406133e-07, + "loss": 0.6052, + "step": 3987 }, { "epoch": 1.82, - "learning_rate": 4.312767028040965e-07, - "loss": 0.5563, - "step": 3536 + "learning_rate": 4.366409069106059e-07, + "loss": 0.5898, + "step": 3988 }, { "epoch": 1.82, - "learning_rate": 4.2886109562089717e-07, - "loss": 0.5016, - "step": 3537 + "learning_rate": 4.344871159537489e-07, + "loss": 0.5839, + "step": 3989 }, { "epoch": 1.82, - "learning_rate": 4.264521241833153e-07, - "loss": 0.5527, - "step": 3538 + "learning_rate": 4.3233853210593813e-07, + "loss": 0.4975, + "step": 3990 }, { "epoch": 1.82, - "learning_rate": 4.240497901615126e-07, - "loss": 0.5465, - "step": 3539 + "learning_rate": 4.30195156536779e-07, + "loss": 0.5795, + "step": 3991 }, { "epoch": 1.82, - "learning_rate": 4.216540952210435e-07, - "loss": 0.5665, - "step": 3540 + "learning_rate": 4.2805699041304717e-07, + "loss": 0.5405, + "step": 3992 }, { "epoch": 1.82, - "learning_rate": 4.192650410228638e-07, - "loss": 0.5643, - "step": 3541 + "learning_rate": 4.2592403489867926e-07, + "loss": 0.5875, + "step": 3993 }, { "epoch": 1.82, - "learning_rate": 4.168826292233241e-07, - "loss": 0.572, - "step": 3542 + "learning_rate": 4.237962911547788e-07, + "loss": 0.6029, + "step": 3994 }, { "epoch": 1.82, - "learning_rate": 4.1450686147416763e-07, - "loss": 0.5663, - "step": 3543 + "learning_rate": 4.2167376033960925e-07, + "loss": 0.603, + "step": 3995 }, { "epoch": 1.82, - "learning_rate": 4.121377394225334e-07, - "loss": 0.5729, - "step": 3544 + "learning_rate": 4.195564436085975e-07, + "loss": 0.5803, + "step": 3996 }, { "epoch": 1.82, - "learning_rate": 4.0977526471095205e-07, - "loss": 0.5381, - "step": 3545 + "learning_rate": 4.174443421143315e-07, + "loss": 0.5785, + "step": 3997 }, { "epoch": 1.82, - "learning_rate": 4.074194389773456e-07, - "loss": 0.5591, - "step": 3546 + "learning_rate": 4.153374570065605e-07, + "loss": 0.5944, + "step": 3998 }, { "epoch": 1.82, - "learning_rate": 4.0507026385502747e-07, - "loss": 0.535, - "step": 3547 + "learning_rate": 4.132357894321948e-07, + "loss": 0.5549, + "step": 3999 }, { "epoch": 1.82, - "learning_rate": 4.027277409726971e-07, - "loss": 0.528, - "step": 3548 + "learning_rate": 4.111393405353048e-07, + "loss": 0.6117, + "step": 4000 }, { "epoch": 1.82, - "learning_rate": 4.003918719544464e-07, - "loss": 0.5626, - "step": 3549 + "learning_rate": 4.0904811145711653e-07, + "loss": 0.6096, + "step": 4001 }, { "epoch": 1.82, - "learning_rate": 3.980626584197489e-07, - "loss": 0.5603, - "step": 3550 + "learning_rate": 4.069621033360216e-07, + "loss": 0.6331, + "step": 4002 + }, + { + "epoch": 1.82, + "learning_rate": 4.0488131730756054e-07, + "loss": 0.5714, + "step": 4003 + }, + { + "epoch": 1.82, + "learning_rate": 4.028057545044384e-07, + "loss": 0.5656, + "step": 4004 + }, + { + "epoch": 1.82, + "learning_rate": 4.007354160565136e-07, + "loss": 0.5387, + "step": 4005 }, { "epoch": 1.83, - "learning_rate": 3.957401019834706e-07, - "loss": 0.566, - "step": 3551 + "learning_rate": 3.9867030309080346e-07, + "loss": 0.5883, + "step": 4006 }, { "epoch": 1.83, - "learning_rate": 3.934242042558545e-07, - "loss": 0.5332, - "step": 3552 + "learning_rate": 3.966104167314733e-07, + "loss": 0.5795, + "step": 4007 }, { "epoch": 1.83, - "learning_rate": 3.911149668425329e-07, - "loss": 0.5624, - "step": 3553 + "learning_rate": 3.9455575809985383e-07, + "loss": 0.5321, + "step": 4008 }, { "epoch": 1.83, - "learning_rate": 3.888123913445174e-07, - "loss": 0.5701, - "step": 3554 + "learning_rate": 3.925063283144226e-07, + "loss": 0.5688, + "step": 4009 }, { "epoch": 1.83, - "learning_rate": 3.86516479358201e-07, - "loss": 0.5449, - "step": 3555 + "learning_rate": 3.9046212849081166e-07, + "loss": 0.5717, + "step": 4010 }, { "epoch": 1.83, - "learning_rate": 3.842272324753582e-07, - "loss": 0.5369, - "step": 3556 + "learning_rate": 3.8842315974180975e-07, + "loss": 0.5714, + "step": 4011 }, { "epoch": 1.83, - "learning_rate": 3.819446522831416e-07, - "loss": 0.6267, - "step": 3557 + "learning_rate": 3.863894231773546e-07, + "loss": 0.6151, + "step": 4012 }, { "epoch": 1.83, - "learning_rate": 3.7966874036408085e-07, - "loss": 0.5745, - "step": 3558 + "learning_rate": 3.843609199045351e-07, + "loss": 0.5785, + "step": 4013 + }, + { + "epoch": 1.83, + "learning_rate": 3.8233765102759556e-07, + "loss": 0.5817, + "step": 4014 + }, + { + "epoch": 1.83, + "learning_rate": 3.8031961764792625e-07, + "loss": 0.6136, + "step": 4015 + }, + { + "epoch": 1.83, + "learning_rate": 3.7830682086407055e-07, + "loss": 0.6152, + "step": 4016 + }, + { + "epoch": 1.83, + "learning_rate": 3.762992617717187e-07, + "loss": 0.5791, + "step": 4017 }, { "epoch": 1.83, - "learning_rate": 3.7739949829608493e-07, - "loss": 0.5511, - "step": 3559 + "learning_rate": 3.742969414637143e-07, + "loss": 0.5886, + "step": 4018 }, { "epoch": 1.83, - "learning_rate": 3.7513692765243637e-07, - "loss": 0.5638, - "step": 3560 + "learning_rate": 3.722998610300399e-07, + "loss": 0.5881, + "step": 4019 }, { "epoch": 1.83, - "learning_rate": 3.728810300017949e-07, - "loss": 0.5454, - "step": 3561 + "learning_rate": 3.7030802155783806e-07, + "loss": 0.5676, + "step": 4020 }, { "epoch": 1.83, - "learning_rate": 3.7063180690819044e-07, - "loss": 0.5925, - "step": 3562 + "learning_rate": 3.6832142413138925e-07, + "loss": 0.5496, + "step": 4021 }, { "epoch": 1.83, - "learning_rate": 3.683892599310279e-07, - "loss": 0.5344, - "step": 3563 + "learning_rate": 3.663400698321229e-07, + "loss": 0.5333, + "step": 4022 }, { "epoch": 1.83, - "learning_rate": 3.6615339062508135e-07, - "loss": 0.5662, - "step": 3564 + "learning_rate": 3.6436395973861504e-07, + "loss": 0.5724, + "step": 4023 }, { "epoch": 1.83, - "learning_rate": 3.639242005404975e-07, - "loss": 0.606, - "step": 3565 + "learning_rate": 3.6239309492658634e-07, + "loss": 0.5541, + "step": 4024 }, { "epoch": 1.83, - "learning_rate": 3.6170169122279106e-07, - "loss": 0.5974, - "step": 3566 + "learning_rate": 3.604274764689042e-07, + "loss": 0.5574, + "step": 4025 }, { "epoch": 1.83, - "learning_rate": 3.5948586421284517e-07, - "loss": 0.5171, - "step": 3567 + "learning_rate": 3.584671054355726e-07, + "loss": 0.5658, + "step": 4026 }, { "epoch": 1.83, - "learning_rate": 3.572767210469086e-07, - "loss": 0.5277, - "step": 3568 + "learning_rate": 3.565119828937502e-07, + "loss": 0.5623, + "step": 4027 }, { - "epoch": 1.83, - "learning_rate": 3.5507426325659955e-07, - "loss": 0.5544, - "step": 3569 + "epoch": 1.84, + "learning_rate": 3.545621099077312e-07, + "loss": 0.625, + "step": 4028 }, { "epoch": 1.84, - "learning_rate": 3.5287849236889884e-07, - "loss": 0.5828, - "step": 3570 + "learning_rate": 3.5261748753895206e-07, + "loss": 0.5695, + "step": 4029 }, { "epoch": 1.84, - "learning_rate": 3.50689409906152e-07, - "loss": 0.5918, - "step": 3571 + "learning_rate": 3.5067811684599497e-07, + "loss": 0.6056, + "step": 4030 }, { "epoch": 1.84, - "learning_rate": 3.485070173860661e-07, - "loss": 0.5967, - "step": 3572 + "learning_rate": 3.487439988845809e-07, + "loss": 0.5728, + "step": 4031 }, { "epoch": 1.84, - "learning_rate": 3.463313163217119e-07, - "loss": 0.5806, - "step": 3573 + "learning_rate": 3.4681513470756877e-07, + "loss": 0.5515, + "step": 4032 }, { "epoch": 1.84, - "learning_rate": 3.4416230822151954e-07, - "loss": 0.5732, - "step": 3574 + "learning_rate": 3.448915253649654e-07, + "loss": 0.561, + "step": 4033 }, { "epoch": 1.84, - "learning_rate": 3.4199999458928045e-07, - "loss": 0.5375, - "step": 3575 + "learning_rate": 3.429731719039076e-07, + "loss": 0.5758, + "step": 4034 }, { "epoch": 1.84, - "learning_rate": 3.3984437692414105e-07, - "loss": 0.5476, - "step": 3576 + "learning_rate": 3.410600753686788e-07, + "loss": 0.6129, + "step": 4035 }, { "epoch": 1.84, - "learning_rate": 3.376954567206103e-07, - "loss": 0.5911, - "step": 3577 + "learning_rate": 3.39152236800695e-07, + "loss": 0.5658, + "step": 4036 }, { "epoch": 1.84, - "learning_rate": 3.3555323546854866e-07, - "loss": 0.568, - "step": 3578 + "learning_rate": 3.372496572385153e-07, + "loss": 0.5662, + "step": 4037 }, { "epoch": 1.84, - "learning_rate": 3.334177146531792e-07, - "loss": 0.5706, - "step": 3579 + "learning_rate": 3.35352337717828e-07, + "loss": 0.5286, + "step": 4038 }, { "epoch": 1.84, - "learning_rate": 3.3128889575507086e-07, - "loss": 0.5524, - "step": 3580 + "learning_rate": 3.334602792714703e-07, + "loss": 0.5627, + "step": 4039 }, { "epoch": 1.84, - "learning_rate": 3.2916678025015413e-07, - "loss": 0.5861, - "step": 3581 + "learning_rate": 3.315734829294026e-07, + "loss": 0.5787, + "step": 4040 }, { "epoch": 1.84, - "learning_rate": 3.2705136960970554e-07, - "loss": 0.5687, - "step": 3582 + "learning_rate": 3.2969194971872896e-07, + "loss": 0.6066, + "step": 4041 }, { "epoch": 1.84, - "learning_rate": 3.2494266530035844e-07, - "loss": 0.5435, - "step": 3583 + "learning_rate": 3.278156806636867e-07, + "loss": 0.5234, + "step": 4042 }, { "epoch": 1.84, - "learning_rate": 3.2284066878409124e-07, - "loss": 0.532, - "step": 3584 + "learning_rate": 3.2594467678564555e-07, + "loss": 0.5631, + "step": 4043 }, { "epoch": 1.84, - "learning_rate": 3.207453815182371e-07, - "loss": 0.5585, - "step": 3585 + "learning_rate": 3.2407893910311074e-07, + "loss": 0.5671, + "step": 4044 }, { "epoch": 1.84, - "learning_rate": 3.186568049554728e-07, - "loss": 0.5309, - "step": 3586 + "learning_rate": 3.222184686317198e-07, + "loss": 0.6013, + "step": 4045 }, { "epoch": 1.84, - "learning_rate": 3.1657494054382677e-07, - "loss": 0.5885, - "step": 3587 + "learning_rate": 3.2036326638424377e-07, + "loss": 0.5493, + "step": 4046 }, { "epoch": 1.84, - "learning_rate": 3.1449978972667104e-07, - "loss": 0.5416, - "step": 3588 + "learning_rate": 3.18513333370587e-07, + "loss": 0.5363, + "step": 4047 }, { "epoch": 1.84, - "learning_rate": 3.124313539427226e-07, - "loss": 0.5687, - "step": 3589 + "learning_rate": 3.1666867059778284e-07, + "loss": 0.6111, + "step": 4048 + }, + { + "epoch": 1.84, + "learning_rate": 3.1482927906999806e-07, + "loss": 0.594, + "step": 4049 }, { "epoch": 1.85, - "learning_rate": 3.1036963462604765e-07, - "loss": 0.5897, - "step": 3590 + "learning_rate": 3.1299515978852724e-07, + "loss": 0.5839, + "step": 4050 }, { "epoch": 1.85, - "learning_rate": 3.0831463320604935e-07, - "loss": 0.5303, - "step": 3591 + "learning_rate": 3.111663137517973e-07, + "loss": 0.5757, + "step": 4051 }, { "epoch": 1.85, - "learning_rate": 3.0626635110747816e-07, - "loss": 0.5721, - "step": 3592 + "learning_rate": 3.0934274195536405e-07, + "loss": 0.5441, + "step": 4052 }, { "epoch": 1.85, - "learning_rate": 3.0422478975042245e-07, - "loss": 0.5596, - "step": 3593 + "learning_rate": 3.075244453919135e-07, + "loss": 0.5754, + "step": 4053 }, { "epoch": 1.85, - "learning_rate": 3.021899505503145e-07, - "loss": 0.5291, - "step": 3594 + "learning_rate": 3.0571142505125606e-07, + "loss": 0.6158, + "step": 4054 }, { "epoch": 1.85, - "learning_rate": 3.001618349179225e-07, - "loss": 0.5724, - "step": 3595 + "learning_rate": 3.0390368192033446e-07, + "loss": 0.5958, + "step": 4055 }, { "epoch": 1.85, - "learning_rate": 2.9814044425935605e-07, - "loss": 0.5906, - "step": 3596 + "learning_rate": 3.0210121698321716e-07, + "loss": 0.5839, + "step": 4056 }, { "epoch": 1.85, - "learning_rate": 2.961257799760608e-07, - "loss": 0.5742, - "step": 3597 + "learning_rate": 3.0030403122109473e-07, + "loss": 0.5559, + "step": 4057 }, { "epoch": 1.85, - "learning_rate": 2.9411784346481844e-07, - "loss": 0.5901, - "step": 3598 + "learning_rate": 2.985121256122947e-07, + "loss": 0.5862, + "step": 4058 }, { "epoch": 1.85, - "learning_rate": 2.9211663611774745e-07, - "loss": 0.5681, - "step": 3599 + "learning_rate": 2.9672550113225786e-07, + "loss": 0.5928, + "step": 4059 }, { "epoch": 1.85, - "learning_rate": 2.901221593223025e-07, - "loss": 0.5768, - "step": 3600 + "learning_rate": 2.9494415875355954e-07, + "loss": 0.6132, + "step": 4060 }, { "epoch": 1.85, - "learning_rate": 2.8813441446126746e-07, - "loss": 0.5923, - "step": 3601 + "learning_rate": 2.931680994458952e-07, + "loss": 0.5948, + "step": 4061 }, { "epoch": 1.85, - "learning_rate": 2.861534029127633e-07, - "loss": 0.5782, - "step": 3602 + "learning_rate": 2.9139732417608593e-07, + "loss": 0.5772, + "step": 4062 }, { "epoch": 1.85, - "learning_rate": 2.841791260502402e-07, - "loss": 0.5437, - "step": 3603 + "learning_rate": 2.89631833908075e-07, + "loss": 0.5509, + "step": 4063 }, { "epoch": 1.85, - "learning_rate": 2.8221158524248003e-07, - "loss": 0.551, - "step": 3604 + "learning_rate": 2.8787162960292936e-07, + "loss": 0.5853, + "step": 4064 }, { "epoch": 1.85, - "learning_rate": 2.8025078185359265e-07, - "loss": 0.5782, - "step": 3605 + "learning_rate": 2.861167122188402e-07, + "loss": 0.5444, + "step": 4065 }, { "epoch": 1.85, - "learning_rate": 2.7829671724302063e-07, - "loss": 0.5725, - "step": 3606 + "learning_rate": 2.8436708271111666e-07, + "loss": 0.6118, + "step": 4066 }, { "epoch": 1.85, - "learning_rate": 2.763493927655314e-07, - "loss": 0.5416, - "step": 3607 + "learning_rate": 2.8262274203219474e-07, + "loss": 0.5505, + "step": 4067 }, { "epoch": 1.85, - "learning_rate": 2.744088097712183e-07, - "loss": 0.578, - "step": 3608 + "learning_rate": 2.808836911316282e-07, + "loss": 0.5832, + "step": 4068 + }, + { + "epoch": 1.85, + "learning_rate": 2.791499309560897e-07, + "loss": 0.6401, + "step": 4069 + }, + { + "epoch": 1.85, + "learning_rate": 2.774214624493743e-07, + "loss": 0.5934, + "step": 4070 + }, + { + "epoch": 1.85, + "learning_rate": 2.756982865523961e-07, + "loss": 0.5023, + "step": 4071 }, { "epoch": 1.86, - "learning_rate": 2.7247496960550513e-07, - "loss": 0.575, - "step": 3609 + "learning_rate": 2.739804042031891e-07, + "loss": 0.5872, + "step": 4072 }, { "epoch": 1.86, - "learning_rate": 2.7054787360913825e-07, - "loss": 0.52, - "step": 3610 + "learning_rate": 2.722678163369019e-07, + "loss": 0.5582, + "step": 4073 }, { "epoch": 1.86, - "learning_rate": 2.6862752311818895e-07, - "loss": 0.5999, - "step": 3611 + "learning_rate": 2.705605238858078e-07, + "loss": 0.5782, + "step": 4074 }, { "epoch": 1.86, - "learning_rate": 2.6671391946405003e-07, - "loss": 0.5581, - "step": 3612 + "learning_rate": 2.688585277792888e-07, + "loss": 0.5302, + "step": 4075 }, { "epoch": 1.86, - "learning_rate": 2.6480706397343794e-07, - "loss": 0.5563, - "step": 3613 + "learning_rate": 2.671618289438493e-07, + "loss": 0.557, + "step": 4076 }, { "epoch": 1.86, - "learning_rate": 2.6290695796839073e-07, - "loss": 0.5736, - "step": 3614 + "learning_rate": 2.6547042830311066e-07, + "loss": 0.5912, + "step": 4077 }, { "epoch": 1.86, - "learning_rate": 2.6101360276626795e-07, - "loss": 0.6029, - "step": 3615 + "learning_rate": 2.637843267778084e-07, + "loss": 0.542, + "step": 4078 }, { "epoch": 1.86, - "learning_rate": 2.591269996797452e-07, - "loss": 0.5844, - "step": 3616 + "learning_rate": 2.6210352528579064e-07, + "loss": 0.5851, + "step": 4079 }, { "epoch": 1.86, - "learning_rate": 2.5724715001682053e-07, - "loss": 0.5671, - "step": 3617 + "learning_rate": 2.604280247420266e-07, + "loss": 0.5244, + "step": 4080 }, { "epoch": 1.86, - "learning_rate": 2.5537405508080925e-07, - "loss": 0.5698, - "step": 3618 + "learning_rate": 2.587578260585932e-07, + "loss": 0.5652, + "step": 4081 }, { "epoch": 1.86, - "learning_rate": 2.535077161703414e-07, - "loss": 0.5536, - "step": 3619 + "learning_rate": 2.5709293014468675e-07, + "loss": 0.53, + "step": 4082 }, { "epoch": 1.86, - "learning_rate": 2.516481345793653e-07, - "loss": 0.5216, - "step": 3620 + "learning_rate": 2.554333379066132e-07, + "loss": 0.5865, + "step": 4083 }, { "epoch": 1.86, - "learning_rate": 2.49795311597143e-07, - "loss": 0.5533, - "step": 3621 + "learning_rate": 2.537790502477944e-07, + "loss": 0.5575, + "step": 4084 }, { "epoch": 1.86, - "learning_rate": 2.479492485082513e-07, - "loss": 0.5524, - "step": 3622 + "learning_rate": 2.5213006806875997e-07, + "loss": 0.595, + "step": 4085 }, { "epoch": 1.86, - "learning_rate": 2.461099465925798e-07, - "loss": 0.5443, - "step": 3623 + "learning_rate": 2.504863922671574e-07, + "loss": 0.5416, + "step": 4086 }, { "epoch": 1.86, - "learning_rate": 2.442774071253329e-07, - "loss": 0.603, - "step": 3624 + "learning_rate": 2.488480237377422e-07, + "loss": 0.6462, + "step": 4087 }, { "epoch": 1.86, - "learning_rate": 2.42451631377022e-07, - "loss": 0.5518, - "step": 3625 + "learning_rate": 2.472149633723797e-07, + "loss": 0.5453, + "step": 4088 }, { "epoch": 1.86, - "learning_rate": 2.406326206134724e-07, - "loss": 0.5715, - "step": 3626 + "learning_rate": 2.455872120600489e-07, + "loss": 0.6031, + "step": 4089 }, { "epoch": 1.86, - "learning_rate": 2.3882037609581743e-07, - "loss": 0.5885, - "step": 3627 + "learning_rate": 2.439647706868353e-07, + "loss": 0.5685, + "step": 4090 }, { "epoch": 1.86, - "learning_rate": 2.3701489908050435e-07, - "loss": 0.5751, - "step": 3628 + "learning_rate": 2.4234764013593594e-07, + "loss": 0.593, + "step": 4091 + }, + { + "epoch": 1.86, + "learning_rate": 2.407358212876576e-07, + "loss": 0.5955, + "step": 4092 + }, + { + "epoch": 1.86, + "learning_rate": 2.3912931501941405e-07, + "loss": 0.5851, + "step": 4093 }, { "epoch": 1.87, - "learning_rate": 2.352161908192796e-07, - "loss": 0.5482, - "step": 3629 + "learning_rate": 2.3752812220572686e-07, + "loss": 0.6034, + "step": 4094 }, { "epoch": 1.87, - "learning_rate": 2.3342425255920676e-07, - "loss": 0.576, - "step": 3630 + "learning_rate": 2.3593224371822542e-07, + "loss": 0.5701, + "step": 4095 }, { "epoch": 1.87, - "learning_rate": 2.3163908554264646e-07, - "loss": 0.5852, - "step": 3631 + "learning_rate": 2.343416804256482e-07, + "loss": 0.5939, + "step": 4096 }, { "epoch": 1.87, - "learning_rate": 2.2986069100727092e-07, - "loss": 0.5953, - "step": 3632 + "learning_rate": 2.3275643319383812e-07, + "loss": 0.558, + "step": 4097 }, { "epoch": 1.87, - "learning_rate": 2.2808907018605498e-07, - "loss": 0.5835, - "step": 3633 + "learning_rate": 2.3117650288574156e-07, + "loss": 0.5743, + "step": 4098 }, { "epoch": 1.87, - "learning_rate": 2.263242243072772e-07, - "loss": 0.5492, - "step": 3634 + "learning_rate": 2.2960189036141945e-07, + "loss": 0.5864, + "step": 4099 }, { "epoch": 1.87, - "learning_rate": 2.245661545945188e-07, - "loss": 0.5735, - "step": 3635 + "learning_rate": 2.2803259647802723e-07, + "loss": 0.5828, + "step": 4100 }, { "epoch": 1.87, - "learning_rate": 2.228148622666626e-07, - "loss": 0.5551, - "step": 3636 + "learning_rate": 2.2646862208983268e-07, + "loss": 0.5963, + "step": 4101 }, { "epoch": 1.87, - "learning_rate": 2.210703485378929e-07, - "loss": 0.5477, - "step": 3637 + "learning_rate": 2.2490996804820476e-07, + "loss": 0.5488, + "step": 4102 }, { "epoch": 1.87, - "learning_rate": 2.1933261461769772e-07, - "loss": 0.5603, - "step": 3638 + "learning_rate": 2.233566352016181e-07, + "loss": 0.5897, + "step": 4103 }, { "epoch": 1.87, - "learning_rate": 2.1760166171085785e-07, - "loss": 0.5504, - "step": 3639 + "learning_rate": 2.218086243956452e-07, + "loss": 0.5782, + "step": 4104 }, { "epoch": 1.87, - "learning_rate": 2.1587749101745992e-07, - "loss": 0.5864, - "step": 3640 + "learning_rate": 2.2026593647296978e-07, + "loss": 0.6102, + "step": 4105 + }, + { + "epoch": 1.87, + "learning_rate": 2.1872857227337118e-07, + "loss": 0.6151, + "step": 4106 + }, + { + "epoch": 1.87, + "learning_rate": 2.171965326337333e-07, + "loss": 0.5726, + "step": 4107 + }, + { + "epoch": 1.87, + "learning_rate": 2.1566981838804345e-07, + "loss": 0.609, + "step": 4108 + }, + { + "epoch": 1.87, + "learning_rate": 2.1414843036738687e-07, + "loss": 0.5325, + "step": 4109 + }, + { + "epoch": 1.87, + "learning_rate": 2.1263236939994769e-07, + "loss": 0.5493, + "step": 4110 }, { "epoch": 1.87, - "learning_rate": 2.1416010373288333e-07, - "loss": 0.5914, - "step": 3641 + "learning_rate": 2.1112163631101912e-07, + "loss": 0.6174, + "step": 4111 }, { "epoch": 1.87, - "learning_rate": 2.124495010478056e-07, - "loss": 0.5881, - "step": 3642 + "learning_rate": 2.096162319229833e-07, + "loss": 0.5786, + "step": 4112 }, { "epoch": 1.87, - "learning_rate": 2.1074568414820251e-07, - "loss": 0.5535, - "step": 3643 + "learning_rate": 2.0811615705532694e-07, + "loss": 0.6006, + "step": 4113 }, { "epoch": 1.87, - "learning_rate": 2.0904865421534248e-07, - "loss": 0.5659, - "step": 3644 + "learning_rate": 2.0662141252463685e-07, + "loss": 0.5778, + "step": 4114 }, { "epoch": 1.87, - "learning_rate": 2.0735841242578992e-07, - "loss": 0.5774, - "step": 3645 + "learning_rate": 2.0513199914459547e-07, + "loss": 0.5771, + "step": 4115 }, { - "epoch": 1.87, - "learning_rate": 2.0567495995140186e-07, - "loss": 0.5374, - "step": 3646 + "epoch": 1.88, + "learning_rate": 2.0364791772598203e-07, + "loss": 0.6299, + "step": 4116 }, { - "epoch": 1.87, - "learning_rate": 2.0399829795933024e-07, - "loss": 0.5875, - "step": 3647 + "epoch": 1.88, + "learning_rate": 2.0216916907667805e-07, + "loss": 0.5876, + "step": 4117 }, { "epoch": 1.88, - "learning_rate": 2.0232842761201854e-07, - "loss": 0.5664, - "step": 3648 + "learning_rate": 2.0069575400165743e-07, + "loss": 0.5704, + "step": 4118 }, { "epoch": 1.88, - "learning_rate": 2.0066535006719846e-07, - "loss": 0.5479, - "step": 3649 + "learning_rate": 1.9922767330299297e-07, + "loss": 0.6091, + "step": 4119 }, { "epoch": 1.88, - "learning_rate": 1.9900906647789764e-07, - "loss": 0.5826, - "step": 3650 + "learning_rate": 1.9776492777985323e-07, + "loss": 0.5512, + "step": 4120 }, { "epoch": 1.88, - "learning_rate": 1.9735957799242977e-07, - "loss": 0.5977, - "step": 3651 + "learning_rate": 1.9630751822850237e-07, + "loss": 0.6075, + "step": 4121 }, { "epoch": 1.88, - "learning_rate": 1.9571688575439672e-07, - "loss": 0.5662, - "step": 3652 + "learning_rate": 1.9485544544230018e-07, + "loss": 0.5962, + "step": 4122 }, { "epoch": 1.88, - "learning_rate": 1.9408099090269084e-07, - "loss": 0.5977, - "step": 3653 + "learning_rate": 1.9340871021169994e-07, + "loss": 0.6072, + "step": 4123 }, { "epoch": 1.88, - "learning_rate": 1.9245189457149148e-07, - "loss": 0.5376, - "step": 3654 + "learning_rate": 1.9196731332425277e-07, + "loss": 0.5614, + "step": 4124 }, { "epoch": 1.88, - "learning_rate": 1.90829597890263e-07, - "loss": 0.5369, - "step": 3655 + "learning_rate": 1.9053125556459884e-07, + "loss": 0.5516, + "step": 4125 }, { "epoch": 1.88, - "learning_rate": 1.8921410198375567e-07, - "loss": 0.5529, - "step": 3656 + "learning_rate": 1.891005377144761e-07, + "loss": 0.5454, + "step": 4126 }, { "epoch": 1.88, - "learning_rate": 1.8760540797200576e-07, - "loss": 0.5575, - "step": 3657 + "learning_rate": 1.8767516055271273e-07, + "loss": 0.5797, + "step": 4127 }, { "epoch": 1.88, - "learning_rate": 1.8600351697033558e-07, - "loss": 0.6207, - "step": 3658 + "learning_rate": 1.8625512485523357e-07, + "loss": 0.5723, + "step": 4128 }, { "epoch": 1.88, - "learning_rate": 1.844084300893456e-07, - "loss": 0.5394, - "step": 3659 + "learning_rate": 1.8484043139504916e-07, + "loss": 0.5699, + "step": 4129 }, { "epoch": 1.88, - "learning_rate": 1.828201484349257e-07, - "loss": 0.5531, - "step": 3660 + "learning_rate": 1.8343108094227012e-07, + "loss": 0.5719, + "step": 4130 }, { "epoch": 1.88, - "learning_rate": 1.812386731082405e-07, - "loss": 0.5745, - "step": 3661 + "learning_rate": 1.8202707426409171e-07, + "loss": 0.5994, + "step": 4131 }, { "epoch": 1.88, - "learning_rate": 1.796640052057419e-07, - "loss": 0.5659, - "step": 3662 + "learning_rate": 1.8062841212480253e-07, + "loss": 0.6228, + "step": 4132 }, { "epoch": 1.88, - "learning_rate": 1.7809614581915768e-07, - "loss": 0.5763, - "step": 3663 + "learning_rate": 1.7923509528578463e-07, + "loss": 0.5604, + "step": 4133 }, { "epoch": 1.88, - "learning_rate": 1.7653509603549723e-07, - "loss": 0.5371, - "step": 3664 + "learning_rate": 1.778471245055069e-07, + "loss": 0.5453, + "step": 4134 }, { "epoch": 1.88, - "learning_rate": 1.7498085693704926e-07, - "loss": 0.5215, - "step": 3665 + "learning_rate": 1.7646450053952825e-07, + "loss": 0.629, + "step": 4135 }, { "epoch": 1.88, - "learning_rate": 1.7343342960138064e-07, - "loss": 0.5736, - "step": 3666 + "learning_rate": 1.7508722414049662e-07, + "loss": 0.6196, + "step": 4136 }, { "epoch": 1.88, - "learning_rate": 1.7189281510133215e-07, - "loss": 0.5457, - "step": 3667 + "learning_rate": 1.7371529605815229e-07, + "loss": 0.5234, + "step": 4137 }, { "epoch": 1.89, - "learning_rate": 1.70359014505026e-07, - "loss": 0.5776, - "step": 3668 + "learning_rate": 1.723487170393212e-07, + "loss": 0.5925, + "step": 4138 }, { "epoch": 1.89, - "learning_rate": 1.6883202887585825e-07, - "loss": 0.5494, - "step": 3669 + "learning_rate": 1.7098748782791717e-07, + "loss": 0.5811, + "step": 4139 }, { "epoch": 1.89, - "learning_rate": 1.673118592724987e-07, - "loss": 0.5741, - "step": 3670 + "learning_rate": 1.6963160916494413e-07, + "loss": 0.5079, + "step": 4140 }, { "epoch": 1.89, - "learning_rate": 1.6579850674889541e-07, - "loss": 0.6226, - "step": 3671 + "learning_rate": 1.6828108178849056e-07, + "loss": 0.6189, + "step": 4141 }, { "epoch": 1.89, - "learning_rate": 1.6429197235426465e-07, - "loss": 0.5514, - "step": 3672 + "learning_rate": 1.6693590643373392e-07, + "loss": 0.6047, + "step": 4142 }, { "epoch": 1.89, - "learning_rate": 1.6279225713310088e-07, - "loss": 0.6152, - "step": 3673 + "learning_rate": 1.6559608383293735e-07, + "loss": 0.6166, + "step": 4143 }, { "epoch": 1.89, - "learning_rate": 1.6129936212516684e-07, - "loss": 0.5818, - "step": 3674 + "learning_rate": 1.6426161471544966e-07, + "loss": 0.5731, + "step": 4144 }, { "epoch": 1.89, - "learning_rate": 1.598132883654979e-07, - "loss": 0.5535, - "step": 3675 + "learning_rate": 1.6293249980770754e-07, + "loss": 0.5759, + "step": 4145 }, { "epoch": 1.89, - "learning_rate": 1.5833403688440218e-07, - "loss": 0.5854, - "step": 3676 + "learning_rate": 1.6160873983323222e-07, + "loss": 0.5884, + "step": 4146 }, { "epoch": 1.89, - "learning_rate": 1.568616087074548e-07, - "loss": 0.5636, - "step": 3677 + "learning_rate": 1.602903355126273e-07, + "loss": 0.5698, + "step": 4147 }, { "epoch": 1.89, - "learning_rate": 1.5539600485550366e-07, - "loss": 0.5677, - "step": 3678 + "learning_rate": 1.5897728756358421e-07, + "loss": 0.5337, + "step": 4148 }, { "epoch": 1.89, - "learning_rate": 1.5393722634466145e-07, - "loss": 0.5498, - "step": 3679 + "learning_rate": 1.5766959670087678e-07, + "loss": 0.5739, + "step": 4149 }, { "epoch": 1.89, - "learning_rate": 1.5248527418631254e-07, - "loss": 0.5676, - "step": 3680 + "learning_rate": 1.5636726363636446e-07, + "loss": 0.613, + "step": 4150 }, { "epoch": 1.89, - "learning_rate": 1.5104014938710498e-07, - "loss": 0.5519, - "step": 3681 + "learning_rate": 1.550702890789857e-07, + "loss": 0.6058, + "step": 4151 }, { "epoch": 1.89, - "learning_rate": 1.4960185294895736e-07, - "loss": 0.5533, - "step": 3682 + "learning_rate": 1.5377867373477019e-07, + "loss": 0.6235, + "step": 4152 }, { "epoch": 1.89, - "learning_rate": 1.4817038586904975e-07, - "loss": 0.5757, - "step": 3683 + "learning_rate": 1.5249241830682106e-07, + "loss": 0.5669, + "step": 4153 }, { "epoch": 1.89, - "learning_rate": 1.4674574913982942e-07, - "loss": 0.5603, - "step": 3684 + "learning_rate": 1.512115234953282e-07, + "loss": 0.5495, + "step": 4154 }, { "epoch": 1.89, - "learning_rate": 1.453279437490096e-07, - "loss": 0.5697, - "step": 3685 + "learning_rate": 1.499359899975661e-07, + "loss": 0.5497, + "step": 4155 }, { "epoch": 1.89, - "learning_rate": 1.4391697067956622e-07, - "loss": 0.605, - "step": 3686 + "learning_rate": 1.4866581850788486e-07, + "loss": 0.5784, + "step": 4156 }, { - "epoch": 1.9, - "learning_rate": 1.4251283090973567e-07, - "loss": 0.5785, - "step": 3687 + "epoch": 1.89, + "learning_rate": 1.474010097177192e-07, + "loss": 0.6519, + "step": 4157 + }, + { + "epoch": 1.89, + "learning_rate": 1.461415643155839e-07, + "loss": 0.6212, + "step": 4158 + }, + { + "epoch": 1.89, + "learning_rate": 1.448874829870761e-07, + "loss": 0.6035, + "step": 4159 }, { "epoch": 1.9, - "learning_rate": 1.411155254130203e-07, - "loss": 0.5741, - "step": 3688 + "learning_rate": 1.436387664148675e-07, + "loss": 0.5393, + "step": 4160 }, { "epoch": 1.9, - "learning_rate": 1.3972505515818412e-07, - "loss": 0.5673, - "step": 3689 + "learning_rate": 1.4239541527871436e-07, + "loss": 0.5369, + "step": 4161 }, { "epoch": 1.9, - "learning_rate": 1.383414211092493e-07, - "loss": 0.5725, - "step": 3690 + "learning_rate": 1.4115743025545192e-07, + "loss": 0.6041, + "step": 4162 }, { "epoch": 1.9, - "learning_rate": 1.3696462422550182e-07, - "loss": 0.563, - "step": 3691 + "learning_rate": 1.399248120189922e-07, + "loss": 0.5649, + "step": 4163 }, { "epoch": 1.9, - "learning_rate": 1.3559466546148369e-07, - "loss": 0.5486, - "step": 3692 + "learning_rate": 1.386975612403263e-07, + "loss": 0.5856, + "step": 4164 }, { "epoch": 1.9, - "learning_rate": 1.3423154576699958e-07, - "loss": 0.5818, - "step": 3693 + "learning_rate": 1.374756785875253e-07, + "loss": 0.574, + "step": 4165 }, { "epoch": 1.9, - "learning_rate": 1.3287526608711132e-07, - "loss": 0.5845, - "step": 3694 + "learning_rate": 1.3625916472573496e-07, + "loss": 0.5648, + "step": 4166 }, { "epoch": 1.9, - "learning_rate": 1.315258273621367e-07, - "loss": 0.5812, - "step": 3695 + "learning_rate": 1.3504802031718112e-07, + "loss": 0.5465, + "step": 4167 }, { "epoch": 1.9, - "learning_rate": 1.3018323052765402e-07, - "loss": 0.5817, - "step": 3696 + "learning_rate": 1.3384224602116413e-07, + "loss": 0.5504, + "step": 4168 }, { "epoch": 1.9, - "learning_rate": 1.2884747651449424e-07, - "loss": 0.5557, - "step": 3697 + "learning_rate": 1.3264184249406565e-07, + "loss": 0.6029, + "step": 4169 }, { "epoch": 1.9, - "learning_rate": 1.2751856624874658e-07, - "loss": 0.574, - "step": 3698 + "learning_rate": 1.3144681038933737e-07, + "loss": 0.5825, + "step": 4170 }, { "epoch": 1.9, - "learning_rate": 1.2619650065175627e-07, - "loss": 0.5751, - "step": 3699 + "learning_rate": 1.302571503575123e-07, + "loss": 0.5746, + "step": 4171 }, { "epoch": 1.9, - "learning_rate": 1.2488128064012117e-07, - "loss": 0.5333, - "step": 3700 + "learning_rate": 1.2907286304619682e-07, + "loss": 0.62, + "step": 4172 }, { "epoch": 1.9, - "learning_rate": 1.2357290712569304e-07, - "loss": 0.5417, - "step": 3701 + "learning_rate": 1.278939491000719e-07, + "loss": 0.6127, + "step": 4173 }, { "epoch": 1.9, - "learning_rate": 1.2227138101557845e-07, - "loss": 0.5717, - "step": 3702 + "learning_rate": 1.2672040916089535e-07, + "loss": 0.5898, + "step": 4174 }, { "epoch": 1.9, - "learning_rate": 1.209767032121345e-07, - "loss": 0.5449, - "step": 3703 + "learning_rate": 1.2555224386749832e-07, + "loss": 0.6033, + "step": 4175 }, { "epoch": 1.9, - "learning_rate": 1.1968887461297207e-07, - "loss": 0.5795, - "step": 3704 + "learning_rate": 1.243894538557855e-07, + "loss": 0.5397, + "step": 4176 }, { "epoch": 1.9, - "learning_rate": 1.1840789611095249e-07, + "learning_rate": 1.2323203975873943e-07, "loss": 0.5767, - "step": 3705 + "step": 4177 }, { "epoch": 1.9, - "learning_rate": 1.1713376859418868e-07, - "loss": 0.4988, - "step": 3706 + "learning_rate": 1.220800022064095e-07, + "loss": 0.6262, + "step": 4178 + }, + { + "epoch": 1.9, + "learning_rate": 1.2093334182592397e-07, + "loss": 0.5973, + "step": 4179 + }, + { + "epoch": 1.9, + "learning_rate": 1.1979205924148252e-07, + "loss": 0.571, + "step": 4180 + }, + { + "epoch": 1.9, + "learning_rate": 1.1865615507435702e-07, + "loss": 0.4904, + "step": 4181 }, { "epoch": 1.91, - "learning_rate": 1.158664929460429e-07, - "loss": 0.5508, - "step": 3707 + "learning_rate": 1.1752562994288952e-07, + "loss": 0.5924, + "step": 4182 }, { "epoch": 1.91, - "learning_rate": 1.1460607004512681e-07, - "loss": 0.5804, - "step": 3708 + "learning_rate": 1.1640048446249774e-07, + "loss": 0.572, + "step": 4183 }, { "epoch": 1.91, - "learning_rate": 1.1335250076530247e-07, - "loss": 0.6079, - "step": 3709 + "learning_rate": 1.152807192456673e-07, + "loss": 0.5979, + "step": 4184 }, { "epoch": 1.91, - "learning_rate": 1.1210578597567912e-07, - "loss": 0.5511, - "step": 3710 + "learning_rate": 1.1416633490195728e-07, + "loss": 0.604, + "step": 4185 }, { "epoch": 1.91, - "learning_rate": 1.1086592654061312e-07, - "loss": 0.5546, - "step": 3711 + "learning_rate": 1.1305733203799796e-07, + "loss": 0.5328, + "step": 4186 }, { "epoch": 1.91, - "learning_rate": 1.096329233197102e-07, - "loss": 0.5693, - "step": 3712 + "learning_rate": 1.1195371125748977e-07, + "loss": 0.6318, + "step": 4187 }, { "epoch": 1.91, - "learning_rate": 1.0840677716781988e-07, - "loss": 0.5631, - "step": 3713 + "learning_rate": 1.1085547316119993e-07, + "loss": 0.5566, + "step": 4188 }, { "epoch": 1.91, - "learning_rate": 1.0718748893503883e-07, - "loss": 0.6145, - "step": 3714 + "learning_rate": 1.0976261834697022e-07, + "loss": 0.5552, + "step": 4189 }, { "epoch": 1.91, - "learning_rate": 1.0597505946670972e-07, - "loss": 0.5558, - "step": 3715 + "learning_rate": 1.086751474097103e-07, + "loss": 0.5841, + "step": 4190 }, { "epoch": 1.91, - "learning_rate": 1.0476948960341904e-07, - "loss": 0.5959, - "step": 3716 + "learning_rate": 1.0759306094139887e-07, + "loss": 0.5403, + "step": 4191 }, { "epoch": 1.91, - "learning_rate": 1.035707801809982e-07, - "loss": 0.5684, - "step": 3717 + "learning_rate": 1.0651635953108253e-07, + "loss": 0.5747, + "step": 4192 }, { "epoch": 1.91, - "learning_rate": 1.023789320305213e-07, - "loss": 0.5576, - "step": 3718 + "learning_rate": 1.0544504376487796e-07, + "loss": 0.5876, + "step": 4193 }, { "epoch": 1.91, - "learning_rate": 1.0119394597830734e-07, - "loss": 0.5514, - "step": 3719 + "learning_rate": 1.0437911422597091e-07, + "loss": 0.59, + "step": 4194 }, { "epoch": 1.91, - "learning_rate": 1.0001582284591471e-07, - "loss": 0.5795, - "step": 3720 + "learning_rate": 1.0331857149461055e-07, + "loss": 0.5785, + "step": 4195 }, { "epoch": 1.91, - "learning_rate": 9.88445634501467e-08, - "loss": 0.5515, - "step": 3721 + "learning_rate": 1.0226341614811952e-07, + "loss": 0.5844, + "step": 4196 }, { "epoch": 1.91, - "learning_rate": 9.768016860304485e-08, - "loss": 0.5648, - "step": 3722 + "learning_rate": 1.0121364876088392e-07, + "loss": 0.6143, + "step": 4197 + }, + { + "epoch": 1.91, + "learning_rate": 1.0016926990435883e-07, + "loss": 0.5153, + "step": 4198 + }, + { + "epoch": 1.91, + "learning_rate": 9.913028014706505e-08, + "loss": 0.5529, + "step": 4199 + }, + { + "epoch": 1.91, + "learning_rate": 9.809668005459016e-08, + "loss": 0.5916, + "step": 4200 + }, + { + "epoch": 1.91, + "learning_rate": 9.706847018958521e-08, + "loss": 0.5895, + "step": 4201 + }, + { + "epoch": 1.91, + "learning_rate": 9.604565111177356e-08, + "loss": 0.5883, + "step": 4202 }, { "epoch": 1.91, - "learning_rate": 9.652263911189563e-08, - "loss": 0.5769, - "step": 3723 + "learning_rate": 9.502822337793649e-08, + "loss": 0.5784, + "step": 4203 }, { - "epoch": 1.91, - "learning_rate": 9.537197577922263e-08, - "loss": 0.5793, - "step": 3724 + "epoch": 1.92, + "learning_rate": 9.401618754192432e-08, + "loss": 0.5812, + "step": 4204 }, { - "epoch": 1.91, - "learning_rate": 9.422817940278773e-08, - "loss": 0.5472, - "step": 3725 + "epoch": 1.92, + "learning_rate": 9.300954415465191e-08, + "loss": 0.5251, + "step": 4205 }, { "epoch": 1.92, - "learning_rate": 9.309125077559655e-08, - "loss": 0.5206, - "step": 3726 + "learning_rate": 9.200829376409981e-08, + "loss": 0.5475, + "step": 4206 }, { "epoch": 1.92, - "learning_rate": 9.196119068588861e-08, - "loss": 0.5768, - "step": 3727 + "learning_rate": 9.101243691530981e-08, + "loss": 0.6012, + "step": 4207 }, { "epoch": 1.92, - "learning_rate": 9.083799991714493e-08, - "loss": 0.6023, - "step": 3728 + "learning_rate": 9.002197415039048e-08, + "loss": 0.536, + "step": 4208 }, { "epoch": 1.92, - "learning_rate": 8.972167924808151e-08, - "loss": 0.545, - "step": 3729 + "learning_rate": 8.903690600851167e-08, + "loss": 0.558, + "step": 4209 }, { "epoch": 1.92, - "learning_rate": 8.861222945265369e-08, - "loss": 0.5686, - "step": 3730 + "learning_rate": 8.805723302590774e-08, + "loss": 0.5901, + "step": 4210 }, { "epoch": 1.92, - "learning_rate": 8.750965130004951e-08, - "loss": 0.528, - "step": 3731 + "learning_rate": 8.708295573587766e-08, + "loss": 0.5581, + "step": 4211 }, { "epoch": 1.92, - "learning_rate": 8.64139455546964e-08, - "loss": 0.5186, - "step": 3732 + "learning_rate": 8.611407466878052e-08, + "loss": 0.5957, + "step": 4212 }, { "epoch": 1.92, - "learning_rate": 8.532511297625557e-08, - "loss": 0.5773, - "step": 3733 + "learning_rate": 8.515059035203887e-08, + "loss": 0.5707, + "step": 4213 }, { "epoch": 1.92, - "learning_rate": 8.424315431962316e-08, - "loss": 0.5089, - "step": 3734 + "learning_rate": 8.419250331013873e-08, + "loss": 0.5994, + "step": 4214 }, { "epoch": 1.92, - "learning_rate": 8.316807033493024e-08, - "loss": 0.574, - "step": 3735 + "learning_rate": 8.323981406462623e-08, + "loss": 0.5211, + "step": 4215 }, { "epoch": 1.92, - "learning_rate": 8.209986176753947e-08, - "loss": 0.5591, - "step": 3736 + "learning_rate": 8.229252313411096e-08, + "loss": 0.6379, + "step": 4216 }, { "epoch": 1.92, - "learning_rate": 8.103852935804845e-08, - "loss": 0.5699, - "step": 3737 + "learning_rate": 8.135063103426155e-08, + "loss": 0.5749, + "step": 4217 }, { "epoch": 1.92, - "learning_rate": 7.998407384228857e-08, - "loss": 0.5334, - "step": 3738 + "learning_rate": 8.041413827781008e-08, + "loss": 0.5702, + "step": 4218 }, { "epoch": 1.92, - "learning_rate": 7.893649595132058e-08, - "loss": 0.5127, - "step": 3739 + "learning_rate": 7.948304537454654e-08, + "loss": 0.558, + "step": 4219 }, { "epoch": 1.92, - "learning_rate": 7.789579641144018e-08, - "loss": 0.5867, - "step": 3740 + "learning_rate": 7.855735283132549e-08, + "loss": 0.5669, + "step": 4220 }, { "epoch": 1.92, - "learning_rate": 7.686197594417133e-08, - "loss": 0.5619, - "step": 3741 + "learning_rate": 7.763706115205716e-08, + "loss": 0.5514, + "step": 4221 }, { "epoch": 1.92, - "learning_rate": 7.583503526627067e-08, - "loss": 0.5673, - "step": 3742 + "learning_rate": 7.672217083771638e-08, + "loss": 0.5281, + "step": 4222 }, { "epoch": 1.92, - "learning_rate": 7.481497508972313e-08, - "loss": 0.5818, - "step": 3743 + "learning_rate": 7.581268238633477e-08, + "loss": 0.5126, + "step": 4223 }, { "epoch": 1.92, - "learning_rate": 7.38017961217441e-08, - "loss": 0.5651, - "step": 3744 + "learning_rate": 7.490859629300295e-08, + "loss": 0.5677, + "step": 4224 }, { "epoch": 1.92, - "learning_rate": 7.279549906478056e-08, - "loss": 0.5774, - "step": 3745 + "learning_rate": 7.400991304987281e-08, + "loss": 0.5658, + "step": 4225 }, { "epoch": 1.93, - "learning_rate": 7.179608461650445e-08, - "loss": 0.5804, - "step": 3746 + "learning_rate": 7.311663314615303e-08, + "loss": 0.5874, + "step": 4226 }, { "epoch": 1.93, - "learning_rate": 7.080355346981815e-08, - "loss": 0.5419, - "step": 3747 + "learning_rate": 7.222875706811239e-08, + "loss": 0.598, + "step": 4227 }, { "epoch": 1.93, - "learning_rate": 6.981790631285012e-08, - "loss": 0.5558, - "step": 3748 + "learning_rate": 7.134628529907872e-08, + "loss": 0.5853, + "step": 4228 }, { "epoch": 1.93, - "learning_rate": 6.883914382895929e-08, - "loss": 0.5583, - "step": 3749 + "learning_rate": 7.046921831943443e-08, + "loss": 0.5905, + "step": 4229 }, { "epoch": 1.93, - "learning_rate": 6.78672666967295e-08, - "loss": 0.588, - "step": 3750 + "learning_rate": 6.959755660662426e-08, + "loss": 0.5957, + "step": 4230 }, { "epoch": 1.93, - "learning_rate": 6.690227558996842e-08, - "loss": 0.5721, - "step": 3751 + "learning_rate": 6.873130063514755e-08, + "loss": 0.551, + "step": 4231 }, { "epoch": 1.93, - "learning_rate": 6.594417117771312e-08, - "loss": 0.5944, - "step": 3752 + "learning_rate": 6.787045087656152e-08, + "loss": 0.5742, + "step": 4232 }, { "epoch": 1.93, - "learning_rate": 6.499295412422668e-08, - "loss": 0.6128, - "step": 3753 + "learning_rate": 6.701500779948022e-08, + "loss": 0.5646, + "step": 4233 }, { "epoch": 1.93, - "learning_rate": 6.404862508899268e-08, - "loss": 0.5585, - "step": 3754 + "learning_rate": 6.616497186957671e-08, + "loss": 0.5631, + "step": 4234 }, { "epoch": 1.93, - "learning_rate": 6.311118472672184e-08, - "loss": 0.4968, - "step": 3755 + "learning_rate": 6.532034354957862e-08, + "loss": 0.5835, + "step": 4235 }, { "epoch": 1.93, - "learning_rate": 6.218063368735094e-08, - "loss": 0.5692, - "step": 3756 + "learning_rate": 6.448112329926814e-08, + "loss": 0.536, + "step": 4236 }, { "epoch": 1.93, - "learning_rate": 6.125697261603725e-08, - "loss": 0.5966, - "step": 3757 + "learning_rate": 6.364731157548765e-08, + "loss": 0.5682, + "step": 4237 }, { "epoch": 1.93, - "learning_rate": 6.034020215316184e-08, - "loss": 0.5854, - "step": 3758 + "learning_rate": 6.281890883213293e-08, + "loss": 0.5566, + "step": 4238 }, { "epoch": 1.93, - "learning_rate": 5.94303229343296e-08, - "loss": 0.5471, - "step": 3759 + "learning_rate": 6.199591552015439e-08, + "loss": 0.5499, + "step": 4239 }, { "epoch": 1.93, - "learning_rate": 5.852733559036705e-08, - "loss": 0.528, - "step": 3760 + "learning_rate": 6.117833208755919e-08, + "loss": 0.5822, + "step": 4240 }, { "epoch": 1.93, - "learning_rate": 5.763124074732118e-08, - "loss": 0.5625, - "step": 3761 + "learning_rate": 6.036615897941134e-08, + "loss": 0.5685, + "step": 4241 }, { "epoch": 1.93, - "learning_rate": 5.674203902646391e-08, - "loss": 0.5153, - "step": 3762 + "learning_rate": 5.955939663782495e-08, + "loss": 0.5924, + "step": 4242 }, { "epoch": 1.93, - "learning_rate": 5.5859731044282104e-08, - "loss": 0.5546, - "step": 3763 + "learning_rate": 5.875804550197317e-08, + "loss": 0.5847, + "step": 4243 }, { "epoch": 1.93, - "learning_rate": 5.498431741249089e-08, - "loss": 0.5808, - "step": 3764 + "learning_rate": 5.796210600808039e-08, + "loss": 0.5973, + "step": 4244 + }, + { + "epoch": 1.93, + "learning_rate": 5.717157858942779e-08, + "loss": 0.6027, + "step": 4245 + }, + { + "epoch": 1.93, + "learning_rate": 5.638646367634781e-08, + "loss": 0.5819, + "step": 4246 + }, + { + "epoch": 1.93, + "learning_rate": 5.560676169622859e-08, + "loss": 0.5831, + "step": 4247 }, { "epoch": 1.94, - "learning_rate": 5.411579873801809e-08, - "loss": 0.5428, - "step": 3765 + "learning_rate": 5.483247307351058e-08, + "loss": 0.5426, + "step": 4248 }, { "epoch": 1.94, - "learning_rate": 5.325417562301538e-08, - "loss": 0.5375, - "step": 3766 + "learning_rate": 5.4063598229687765e-08, + "loss": 0.6045, + "step": 4249 }, { "epoch": 1.94, - "learning_rate": 5.239944866485491e-08, - "loss": 0.5178, - "step": 3767 + "learning_rate": 5.330013758330754e-08, + "loss": 0.5764, + "step": 4250 }, { "epoch": 1.94, - "learning_rate": 5.1551618456122664e-08, - "loss": 0.5051, - "step": 3768 + "learning_rate": 5.254209154996859e-08, + "loss": 0.5648, + "step": 4251 }, { "epoch": 1.94, - "learning_rate": 5.071068558462733e-08, - "loss": 0.5477, - "step": 3769 + "learning_rate": 5.1789460542321926e-08, + "loss": 0.564, + "step": 4252 }, { "epoch": 1.94, - "learning_rate": 4.987665063339475e-08, - "loss": 0.6068, - "step": 3770 + "learning_rate": 5.1042244970075375e-08, + "loss": 0.598, + "step": 4253 }, { "epoch": 1.94, - "learning_rate": 4.904951418066684e-08, - "loss": 0.5688, - "step": 3771 + "learning_rate": 5.030044523998134e-08, + "loss": 0.5458, + "step": 4254 }, { "epoch": 1.94, - "learning_rate": 4.822927679990486e-08, - "loss": 0.5682, - "step": 3772 + "learning_rate": 4.956406175585016e-08, + "loss": 0.6011, + "step": 4255 }, { "epoch": 1.94, - "learning_rate": 4.741593905978503e-08, - "loss": 0.572, - "step": 3773 + "learning_rate": 4.883309491854116e-08, + "loss": 0.5902, + "step": 4256 }, { "epoch": 1.94, - "learning_rate": 4.660950152420074e-08, - "loss": 0.5573, - "step": 3774 + "learning_rate": 4.810754512596605e-08, + "loss": 0.5504, + "step": 4257 }, { "epoch": 1.94, - "learning_rate": 4.5809964752262513e-08, - "loss": 0.5555, - "step": 3775 + "learning_rate": 4.738741277308556e-08, + "loss": 0.5557, + "step": 4258 }, { "epoch": 1.94, - "learning_rate": 4.50173292982925e-08, - "loss": 0.5369, - "step": 3776 + "learning_rate": 4.667269825191389e-08, + "loss": 0.6053, + "step": 4259 }, { "epoch": 1.94, - "learning_rate": 4.423159571183555e-08, - "loss": 0.624, - "step": 3777 + "learning_rate": 4.5963401951515386e-08, + "loss": 0.5718, + "step": 4260 }, { "epoch": 1.94, - "learning_rate": 4.345276453764258e-08, - "loss": 0.5846, - "step": 3778 + "learning_rate": 4.5259524258003394e-08, + "loss": 0.5887, + "step": 4261 }, { "epoch": 1.94, - "learning_rate": 4.2680836315687205e-08, - "loss": 0.5731, - "step": 3779 + "learning_rate": 4.4561065554544757e-08, + "loss": 0.532, + "step": 4262 }, { "epoch": 1.94, - "learning_rate": 4.191581158115021e-08, - "loss": 0.5637, - "step": 3780 + "learning_rate": 4.3868026221352e-08, + "loss": 0.5438, + "step": 4263 }, { "epoch": 1.94, - "learning_rate": 4.1157690864430664e-08, - "loss": 0.5376, - "step": 3781 + "learning_rate": 4.318040663569112e-08, + "loss": 0.625, + "step": 4264 }, { "epoch": 1.94, - "learning_rate": 4.040647469114034e-08, - "loss": 0.5688, - "step": 3782 + "learning_rate": 4.249820717187714e-08, + "loss": 0.6113, + "step": 4265 }, { "epoch": 1.94, - "learning_rate": 3.9662163582101506e-08, - "loss": 0.5323, - "step": 3783 + "learning_rate": 4.182142820127299e-08, + "loss": 0.5583, + "step": 4266 + }, + { + "epoch": 1.94, + "learning_rate": 4.115007009229288e-08, + "loss": 0.5935, + "step": 4267 + }, + { + "epoch": 1.94, + "learning_rate": 4.048413321039779e-08, + "loss": 0.5079, + "step": 4268 + }, + { + "epoch": 1.94, + "learning_rate": 3.9823617918099965e-08, + "loss": 0.5918, + "step": 4269 }, { "epoch": 1.95, - "learning_rate": 3.8924758053351384e-08, - "loss": 0.5616, - "step": 3784 + "learning_rate": 3.9168524574959564e-08, + "loss": 0.6246, + "step": 4270 }, { "epoch": 1.95, - "learning_rate": 3.81942586161399e-08, - "loss": 0.5382, - "step": 3785 + "learning_rate": 3.8518853537584665e-08, + "loss": 0.5564, + "step": 4271 }, { "epoch": 1.95, - "learning_rate": 3.7470665776927485e-08, - "loss": 0.5724, - "step": 3786 + "learning_rate": 3.787460515963237e-08, + "loss": 0.5639, + "step": 4272 }, { "epoch": 1.95, - "learning_rate": 3.6753980037386174e-08, - "loss": 0.5884, - "step": 3787 + "learning_rate": 3.7235779791806593e-08, + "loss": 0.5704, + "step": 4273 }, { "epoch": 1.95, - "learning_rate": 3.604420189440183e-08, - "loss": 0.575, - "step": 3788 + "learning_rate": 3.6602377781860264e-08, + "loss": 0.5712, + "step": 4274 }, { "epoch": 1.95, - "learning_rate": 3.534133184006638e-08, - "loss": 0.559, - "step": 3789 + "learning_rate": 3.597439947459425e-08, + "loss": 0.5927, + "step": 4275 }, { "epoch": 1.95, - "learning_rate": 3.46453703616878e-08, - "loss": 0.5175, - "step": 3790 + "learning_rate": 3.5351845211857305e-08, + "loss": 0.6201, + "step": 4276 }, { "epoch": 1.95, - "learning_rate": 3.3956317941779004e-08, - "loss": 0.5223, - "step": 3791 + "learning_rate": 3.4734715332542804e-08, + "loss": 0.5889, + "step": 4277 }, { "epoch": 1.95, - "learning_rate": 3.327417505806785e-08, - "loss": 0.6215, - "step": 3792 + "learning_rate": 3.4123010172596446e-08, + "loss": 0.5966, + "step": 4278 }, { "epoch": 1.95, - "learning_rate": 3.259894218348714e-08, - "loss": 0.5509, - "step": 3793 + "learning_rate": 3.3516730065003e-08, + "loss": 0.5493, + "step": 4279 }, { "epoch": 1.95, - "learning_rate": 3.19306197861835e-08, - "loss": 0.5507, - "step": 3794 + "learning_rate": 3.291587533980401e-08, + "loss": 0.5504, + "step": 4280 }, { "epoch": 1.95, - "learning_rate": 3.126920832950853e-08, - "loss": 0.5631, - "step": 3795 + "learning_rate": 3.232044632407893e-08, + "loss": 0.5614, + "step": 4281 }, { "epoch": 1.95, - "learning_rate": 3.0614708272023175e-08, - "loss": 0.5376, - "step": 3796 + "learning_rate": 3.1730443341957404e-08, + "loss": 0.5741, + "step": 4282 }, { "epoch": 1.95, - "learning_rate": 2.996712006750002e-08, - "loss": 0.5564, - "step": 3797 + "learning_rate": 3.1145866714616945e-08, + "loss": 0.5776, + "step": 4283 }, { "epoch": 1.95, - "learning_rate": 2.932644416491437e-08, - "loss": 0.5721, - "step": 3798 + "learning_rate": 3.056671676027745e-08, + "loss": 0.579, + "step": 4284 }, { "epoch": 1.95, - "learning_rate": 2.8692681008454238e-08, - "loss": 0.5929, - "step": 3799 + "learning_rate": 2.9992993794207834e-08, + "loss": 0.5735, + "step": 4285 }, { "epoch": 1.95, - "learning_rate": 2.8065831037511483e-08, - "loss": 0.5952, - "step": 3800 + "learning_rate": 2.9424698128720507e-08, + "loss": 0.5859, + "step": 4286 }, { "epoch": 1.95, - "learning_rate": 2.7445894686685126e-08, - "loss": 0.597, - "step": 3801 + "learning_rate": 2.8861830073175778e-08, + "loss": 0.6365, + "step": 4287 }, { "epoch": 1.95, - "learning_rate": 2.6832872385783583e-08, - "loss": 0.5341, - "step": 3802 + "learning_rate": 2.8304389933976328e-08, + "loss": 0.5419, + "step": 4288 }, { "epoch": 1.95, - "learning_rate": 2.6226764559819095e-08, - "loss": 0.5824, - "step": 3803 + "learning_rate": 2.7752378014572756e-08, + "loss": 0.5999, + "step": 4289 + }, + { + "epoch": 1.95, + "learning_rate": 2.7205794615460247e-08, + "loss": 0.53, + "step": 4290 + }, + { + "epoch": 1.95, + "learning_rate": 2.666464003417857e-08, + "loss": 0.613, + "step": 4291 + }, + { + "epoch": 1.96, + "learning_rate": 2.612891456530986e-08, + "loss": 0.536, + "step": 4292 + }, + { + "epoch": 1.96, + "learning_rate": 2.5598618500486394e-08, + "loss": 0.5941, + "step": 4293 + }, + { + "epoch": 1.96, + "learning_rate": 2.507375212837948e-08, + "loss": 0.575, + "step": 4294 + }, + { + "epoch": 1.96, + "learning_rate": 2.4554315734707234e-08, + "loss": 0.5637, + "step": 4295 }, { "epoch": 1.96, - "learning_rate": 2.5627571629011082e-08, - "loss": 0.5504, - "step": 3804 + "learning_rate": 2.404030960223125e-08, + "loss": 0.5172, + "step": 4296 }, { "epoch": 1.96, - "learning_rate": 2.5035294008783907e-08, - "loss": 0.5507, - "step": 3805 + "learning_rate": 2.353173401075881e-08, + "loss": 0.5781, + "step": 4297 }, { "epoch": 1.96, - "learning_rate": 2.44499321097702e-08, - "loss": 0.5632, - "step": 3806 + "learning_rate": 2.3028589237137354e-08, + "loss": 0.6003, + "step": 4298 }, { "epoch": 1.96, - "learning_rate": 2.387148633780423e-08, - "loss": 0.5562, - "step": 3807 + "learning_rate": 2.2530875555262233e-08, + "loss": 0.4953, + "step": 4299 }, { "epoch": 1.96, - "learning_rate": 2.3299957093927407e-08, - "loss": 0.566, - "step": 3808 + "learning_rate": 2.203859323606783e-08, + "loss": 0.5415, + "step": 4300 }, { "epoch": 1.96, - "learning_rate": 2.2735344774387215e-08, - "loss": 0.5898, - "step": 3809 + "learning_rate": 2.1551742547536448e-08, + "loss": 0.4953, + "step": 4301 }, { "epoch": 1.96, - "learning_rate": 2.2177649770630528e-08, - "loss": 0.5862, - "step": 3810 + "learning_rate": 2.1070323754690537e-08, + "loss": 0.5549, + "step": 4302 }, { "epoch": 1.96, - "learning_rate": 2.162687246931472e-08, - "loss": 0.5432, - "step": 3811 + "learning_rate": 2.059433711959713e-08, + "loss": 0.54, + "step": 4303 }, { "epoch": 1.96, - "learning_rate": 2.108301325229545e-08, - "loss": 0.5781, - "step": 3812 + "learning_rate": 2.012378290136563e-08, + "loss": 0.5602, + "step": 4304 }, { "epoch": 1.96, - "learning_rate": 2.054607249663665e-08, - "loss": 0.5575, - "step": 3813 + "learning_rate": 1.965866135614669e-08, + "loss": 0.6307, + "step": 4305 }, { "epoch": 1.96, - "learning_rate": 2.0016050574602764e-08, - "loss": 0.5448, - "step": 3814 + "learning_rate": 1.9198972737137777e-08, + "loss": 0.5779, + "step": 4306 }, { "epoch": 1.96, - "learning_rate": 1.949294785366096e-08, - "loss": 0.5447, - "step": 3815 + "learning_rate": 1.8744717294573167e-08, + "loss": 0.5664, + "step": 4307 }, { "epoch": 1.96, - "learning_rate": 1.897676469648446e-08, - "loss": 0.6022, - "step": 3816 + "learning_rate": 1.8295895275735052e-08, + "loss": 0.5708, + "step": 4308 }, { "epoch": 1.96, - "learning_rate": 1.846750146094589e-08, - "loss": 0.5601, - "step": 3817 + "learning_rate": 1.7852506924944668e-08, + "loss": 0.5828, + "step": 4309 }, { "epoch": 1.96, - "learning_rate": 1.7965158500122815e-08, - "loss": 0.5829, - "step": 3818 + "learning_rate": 1.7414552483566716e-08, + "loss": 0.5942, + "step": 4310 }, { "epoch": 1.96, - "learning_rate": 1.7469736162291085e-08, + "learning_rate": 1.6982032190004938e-08, "loss": 0.5614, - "step": 3819 + "step": 4311 }, { "epoch": 1.96, - "learning_rate": 1.698123479093372e-08, - "loss": 0.6001, - "step": 3820 + "learning_rate": 1.6554946279710993e-08, + "loss": 0.5754, + "step": 4312 }, { "epoch": 1.96, - "learning_rate": 1.6499654724729808e-08, - "loss": 0.5636, - "step": 3821 + "learning_rate": 1.6133294985171134e-08, + "loss": 0.615, + "step": 4313 }, { - "epoch": 1.96, - "learning_rate": 1.602499629756449e-08, - "loss": 0.5471, - "step": 3822 + "epoch": 1.97, + "learning_rate": 1.5717078535918417e-08, + "loss": 0.5959, + "step": 4314 }, { "epoch": 1.97, - "learning_rate": 1.55572598385223e-08, - "loss": 0.5798, - "step": 3823 + "learning_rate": 1.530629715852494e-08, + "loss": 0.5815, + "step": 4315 }, { "epoch": 1.97, - "learning_rate": 1.509644567188717e-08, - "loss": 0.5326, - "step": 3824 + "learning_rate": 1.4900951076605163e-08, + "loss": 0.5764, + "step": 4316 }, { "epoch": 1.97, - "learning_rate": 1.464255411714577e-08, - "loss": 0.5876, - "step": 3825 + "learning_rate": 1.45010405108148e-08, + "loss": 0.6417, + "step": 4317 }, { "epoch": 1.97, - "learning_rate": 1.4195585488984143e-08, - "loss": 0.5734, - "step": 3826 + "learning_rate": 1.4106565678849715e-08, + "loss": 0.5065, + "step": 4318 }, { "epoch": 1.97, - "learning_rate": 1.3755540097291076e-08, - "loss": 0.5696, - "step": 3827 + "learning_rate": 1.3717526795447023e-08, + "loss": 0.5676, + "step": 4319 }, { "epoch": 1.97, - "learning_rate": 1.3322418247151414e-08, - "loss": 0.545, - "step": 3828 + "learning_rate": 1.3333924072385096e-08, + "loss": 0.576, + "step": 4320 }, { "epoch": 1.97, - "learning_rate": 1.289622023885273e-08, - "loss": 0.5902, - "step": 3829 + "learning_rate": 1.2955757718483563e-08, + "loss": 0.5553, + "step": 4321 }, { "epoch": 1.97, - "learning_rate": 1.2476946367881992e-08, - "loss": 0.5594, - "step": 3830 + "learning_rate": 1.25830279396022e-08, + "loss": 0.5626, + "step": 4322 }, { "epoch": 1.97, - "learning_rate": 1.2064596924924454e-08, - "loss": 0.5591, - "step": 3831 + "learning_rate": 1.2215734938639812e-08, + "loss": 0.5784, + "step": 4323 }, { "epoch": 1.97, - "learning_rate": 1.1659172195864766e-08, - "loss": 0.5833, - "step": 3832 + "learning_rate": 1.1853878915538686e-08, + "loss": 0.576, + "step": 4324 }, { "epoch": 1.97, - "learning_rate": 1.126067246178808e-08, - "loss": 0.5898, - "step": 3833 + "learning_rate": 1.1497460067279031e-08, + "loss": 0.5906, + "step": 4325 }, { "epoch": 1.97, - "learning_rate": 1.0869097998976729e-08, - "loss": 0.5648, - "step": 3834 + "learning_rate": 1.1146478587881205e-08, + "loss": 0.598, + "step": 4326 }, { "epoch": 1.97, - "learning_rate": 1.048444907891244e-08, - "loss": 0.5604, - "step": 3835 + "learning_rate": 1.0800934668407925e-08, + "loss": 0.5326, + "step": 4327 }, { "epoch": 1.97, - "learning_rate": 1.0106725968275222e-08, - "loss": 0.5891, - "step": 3836 + "learning_rate": 1.046082849696095e-08, + "loss": 0.5543, + "step": 4328 }, { "epoch": 1.97, - "learning_rate": 9.735928928943373e-09, - "loss": 0.5603, - "step": 3837 + "learning_rate": 1.0126160258678852e-08, + "loss": 0.6078, + "step": 4329 }, { "epoch": 1.97, - "learning_rate": 9.372058217993474e-09, - "loss": 0.5273, - "step": 3838 + "learning_rate": 9.796930135743676e-09, + "loss": 0.5948, + "step": 4330 }, { "epoch": 1.97, - "learning_rate": 9.015114087701503e-09, - "loss": 0.541, - "step": 3839 + "learning_rate": 9.473138307377617e-09, + "loss": 0.6052, + "step": 4331 }, { "epoch": 1.97, - "learning_rate": 8.665096785537286e-09, - "loss": 0.6013, - "step": 3840 + "learning_rate": 9.154784949838569e-09, + "loss": 0.5664, + "step": 4332 }, { "epoch": 1.97, - "learning_rate": 8.322006554171147e-09, - "loss": 0.5883, - "step": 3841 + "learning_rate": 8.841870236427908e-09, + "loss": 0.5249, + "step": 4333 }, { "epoch": 1.97, - "learning_rate": 7.985843631471702e-09, - "loss": 0.5521, - "step": 3842 + "learning_rate": 8.53439433748493e-09, + "loss": 0.603, + "step": 4334 + }, + { + "epoch": 1.97, + "learning_rate": 8.23235742038575e-09, + "loss": 0.5568, + "step": 4335 }, { "epoch": 1.98, - "learning_rate": 7.656608250501407e-09, - "loss": 0.5254, - "step": 3843 + "learning_rate": 7.935759649549957e-09, + "loss": 0.6298, + "step": 4336 }, { "epoch": 1.98, - "learning_rate": 7.3343006395221185e-09, - "loss": 0.5889, - "step": 3844 + "learning_rate": 7.644601186433954e-09, + "loss": 0.5621, + "step": 4337 }, { "epoch": 1.98, - "learning_rate": 7.018921021993974e-09, - "loss": 0.6321, - "step": 3845 + "learning_rate": 7.358882189534289e-09, + "loss": 0.5671, + "step": 4338 }, { "epoch": 1.98, - "learning_rate": 6.710469616569848e-09, - "loss": 0.543, - "step": 3846 + "learning_rate": 7.0786028143843276e-09, + "loss": 0.5604, + "step": 4339 }, { "epoch": 1.98, - "learning_rate": 6.408946637102009e-09, - "loss": 0.5477, - "step": 3847 + "learning_rate": 6.8037632135586895e-09, + "loss": 0.5811, + "step": 4340 }, { "epoch": 1.98, - "learning_rate": 6.114352292639902e-09, - "loss": 0.5828, - "step": 3848 + "learning_rate": 6.534363536668808e-09, + "loss": 0.585, + "step": 4341 }, { "epoch": 1.98, - "learning_rate": 5.826686787427927e-09, - "loss": 0.5714, - "step": 3849 + "learning_rate": 6.270403930367375e-09, + "loss": 0.588, + "step": 4342 }, { "epoch": 1.98, - "learning_rate": 5.545950320905435e-09, - "loss": 0.5726, - "step": 3850 + "learning_rate": 6.011884538342783e-09, + "loss": 0.5752, + "step": 4343 }, { "epoch": 1.98, - "learning_rate": 5.272143087711179e-09, - "loss": 0.5447, - "step": 3851 + "learning_rate": 5.758805501324682e-09, + "loss": 0.5487, + "step": 4344 }, { "epoch": 1.98, - "learning_rate": 5.00526527767553e-09, - "loss": 0.556, - "step": 3852 + "learning_rate": 5.5111669570784285e-09, + "loss": 0.5739, + "step": 4345 }, { "epoch": 1.98, - "learning_rate": 4.7453170758293695e-09, - "loss": 0.5612, - "step": 3853 + "learning_rate": 5.268969040410632e-09, + "loss": 0.6219, + "step": 4346 }, { "epoch": 1.98, - "learning_rate": 4.49229866239409e-09, - "loss": 0.5448, - "step": 3854 + "learning_rate": 5.032211883163607e-09, + "loss": 0.5881, + "step": 4347 }, { "epoch": 1.98, - "learning_rate": 4.246210212791591e-09, - "loss": 0.5546, - "step": 3855 + "learning_rate": 4.800895614219814e-09, + "loss": 0.5824, + "step": 4348 }, { "epoch": 1.98, - "learning_rate": 4.007051897636505e-09, - "loss": 0.548, - "step": 3856 + "learning_rate": 4.575020359498528e-09, + "loss": 0.5298, + "step": 4349 }, { "epoch": 1.98, - "learning_rate": 3.774823882738421e-09, - "loss": 0.5833, - "step": 3857 + "learning_rate": 4.354586241958059e-09, + "loss": 0.6091, + "step": 4350 }, { "epoch": 1.98, - "learning_rate": 3.549526329104103e-09, - "loss": 0.541, - "step": 3858 + "learning_rate": 4.139593381595752e-09, + "loss": 0.5688, + "step": 4351 }, { "epoch": 1.98, - "learning_rate": 3.3311593929330475e-09, - "loss": 0.5684, - "step": 3859 + "learning_rate": 3.930041895444658e-09, + "loss": 0.5966, + "step": 4352 }, { "epoch": 1.98, - "learning_rate": 3.1197232256208187e-09, - "loss": 0.538, - "step": 3860 + "learning_rate": 3.7259318975768624e-09, + "loss": 0.5581, + "step": 4353 }, { "epoch": 1.98, - "learning_rate": 2.9152179737579333e-09, - "loss": 0.5436, - "step": 3861 + "learning_rate": 3.5272634991023733e-09, + "loss": 0.5741, + "step": 4354 + }, + { + "epoch": 1.98, + "learning_rate": 3.3340368081680173e-09, + "loss": 0.5785, + "step": 4355 + }, + { + "epoch": 1.98, + "learning_rate": 3.146251929960764e-09, + "loss": 0.5184, + "step": 4356 + }, + { + "epoch": 1.98, + "learning_rate": 2.9639089667032883e-09, + "loss": 0.5851, + "step": 4357 }, { "epoch": 1.99, - "learning_rate": 2.717643779129864e-09, - "loss": 0.5923, - "step": 3862 + "learning_rate": 2.7870080176550796e-09, + "loss": 0.5168, + "step": 4358 }, { "epoch": 1.99, - "learning_rate": 2.527000778715927e-09, - "loss": 0.549, - "step": 3863 + "learning_rate": 2.6155491791157727e-09, + "loss": 0.5463, + "step": 4359 }, { "epoch": 1.99, - "learning_rate": 2.343289104690394e-09, - "loss": 0.5591, - "step": 3864 + "learning_rate": 2.4495325444207076e-09, + "loss": 0.5886, + "step": 4360 }, { "epoch": 1.99, - "learning_rate": 2.166508884421381e-09, - "loss": 0.5579, - "step": 3865 + "learning_rate": 2.288958203943148e-09, + "loss": 0.5658, + "step": 4361 }, { "epoch": 1.99, - "learning_rate": 1.9966602404730694e-09, - "loss": 0.5391, - "step": 3866 + "learning_rate": 2.1338262450931736e-09, + "loss": 0.5756, + "step": 4362 }, { "epoch": 1.99, - "learning_rate": 1.8337432906034846e-09, - "loss": 0.5278, - "step": 3867 + "learning_rate": 1.9841367523198983e-09, + "loss": 0.6019, + "step": 4363 }, { "epoch": 1.99, - "learning_rate": 1.677758147762276e-09, - "loss": 0.5854, - "step": 3868 + "learning_rate": 1.8398898071081418e-09, + "loss": 0.572, + "step": 4364 }, { "epoch": 1.99, - "learning_rate": 1.5287049200962688e-09, - "loss": 0.5868, - "step": 3869 + "learning_rate": 1.7010854879817574e-09, + "loss": 0.5367, + "step": 4365 }, { "epoch": 1.99, - "learning_rate": 1.3865837109461323e-09, - "loss": 0.5642, - "step": 3870 + "learning_rate": 1.5677238704980834e-09, + "loss": 0.5679, + "step": 4366 }, { "epoch": 1.99, - "learning_rate": 1.2513946188430492e-09, - "loss": 0.5872, - "step": 3871 + "learning_rate": 1.4398050272568242e-09, + "loss": 0.5745, + "step": 4367 }, { "epoch": 1.99, - "learning_rate": 1.123137737517599e-09, - "loss": 0.553, - "step": 3872 + "learning_rate": 1.3173290278911676e-09, + "loss": 0.5531, + "step": 4368 }, { "epoch": 1.99, - "learning_rate": 1.0018131558886535e-09, - "loss": 0.5646, - "step": 3873 + "learning_rate": 1.2002959390722268e-09, + "loss": 0.5748, + "step": 4369 }, { "epoch": 1.99, - "learning_rate": 8.874209580744808e-10, - "loss": 0.5594, - "step": 3874 + "learning_rate": 1.0887058245079297e-09, + "loss": 0.5503, + "step": 4370 }, { "epoch": 1.99, - "learning_rate": 7.799612233805321e-10, - "loss": 0.568, - "step": 3875 + "learning_rate": 9.82558744945239e-10, + "loss": 0.58, + "step": 4371 }, { "epoch": 1.99, - "learning_rate": 6.794340263127641e-10, - "loss": 0.5677, - "step": 3876 + "learning_rate": 8.818547581657122e-10, + "loss": 0.5789, + "step": 4372 }, { "epoch": 1.99, - "learning_rate": 5.858394365643172e-10, - "loss": 0.5568, - "step": 3877 + "learning_rate": 7.865939189899419e-10, + "loss": 0.6078, + "step": 4373 }, { "epoch": 1.99, - "learning_rate": 4.991775190277271e-10, - "loss": 0.6047, - "step": 3878 + "learning_rate": 6.967762792731147e-10, + "loss": 0.554, + "step": 4374 }, { "epoch": 1.99, - "learning_rate": 4.1944833378604334e-10, - "loss": 0.5623, - "step": 3879 + "learning_rate": 6.124018879083426e-10, + "loss": 0.5665, + "step": 4375 }, { "epoch": 1.99, - "learning_rate": 3.4665193611505e-10, - "loss": 0.5269, - "step": 3880 + "learning_rate": 5.334707908277725e-10, + "loss": 0.536, + "step": 4376 }, { "epoch": 1.99, - "learning_rate": 2.8078837648548576e-10, - "loss": 0.5702, - "step": 3881 + "learning_rate": 4.5998303099703543e-10, + "loss": 0.5817, + "step": 4377 + }, + { + "epoch": 1.99, + "learning_rate": 3.9193864841968744e-10, + "loss": 0.5415, + "step": 4378 + }, + { + "epoch": 1.99, + "learning_rate": 3.2933768013831967e-10, + "loss": 0.6022, + "step": 4379 }, { "epoch": 2.0, - "learning_rate": 2.2185770056082356e-10, - "loss": 0.5629, - "step": 3882 + "learning_rate": 2.721801602290075e-10, + "loss": 0.5721, + "step": 4380 }, { "epoch": 2.0, - "learning_rate": 1.69859949198381e-10, - "loss": 0.5465, - "step": 3883 + "learning_rate": 2.204661198068614e-10, + "loss": 0.5168, + "step": 4381 }, { "epoch": 2.0, - "learning_rate": 1.247951584482099e-10, - "loss": 0.5657, - "step": 3884 + "learning_rate": 1.7419558702380656e-10, + "loss": 0.5298, + "step": 4382 }, { "epoch": 2.0, - "learning_rate": 8.666335955531679e-11, - "loss": 0.5658, - "step": 3885 + "learning_rate": 1.3336858706636257e-10, + "loss": 0.5414, + "step": 4383 }, { "epoch": 2.0, - "learning_rate": 5.5464578956332394e-11, - "loss": 0.5916, - "step": 3886 + "learning_rate": 9.798514215897392e-11, + "loss": 0.5914, + "step": 4384 }, { "epoch": 2.0, - "learning_rate": 3.1198838280621644e-11, - "loss": 0.5825, - "step": 3887 + "learning_rate": 6.804527156512031e-11, + "loss": 0.5876, + "step": 4385 }, { "epoch": 2.0, - "learning_rate": 1.3866154352504268e-11, - "loss": 0.5057, - "step": 3888 + "learning_rate": 4.354899158176551e-11, + "loss": 0.5691, + "step": 4386 }, { "epoch": 2.0, - "learning_rate": 3.4665391890342793e-12, - "loss": 0.5383, - "step": 3889 + "learning_rate": 2.4496315543798278e-11, + "loss": 0.5857, + "step": 4387 + }, + { + "epoch": 2.0, + "learning_rate": 1.0887253821811882e-11, + "loss": 0.5691, + "step": 4388 + }, + { + "epoch": 2.0, + "learning_rate": 2.7218138254347936e-12, + "loss": 0.6042, + "step": 4389 }, { "epoch": 2.0, "learning_rate": 0.0, - "loss": 0.5565, - "step": 3890 + "loss": 0.5375, + "step": 4390 }, { "epoch": 2.0, - "step": 3890, - "total_flos": 3146065897553920.0, - "train_loss": 0.701528012783178, - "train_runtime": 39961.6809, - "train_samples_per_second": 24.92, - "train_steps_per_second": 0.097 + "step": 4390, + "total_flos": 3581670722043904.0, + "train_loss": 0.7055383425910272, + "train_runtime": 52034.6266, + "train_samples_per_second": 21.593, + "train_steps_per_second": 0.084 } ], "logging_steps": 1.0, - "max_steps": 3890, + "max_steps": 4390, "num_input_tokens_seen": 0, "num_train_epochs": 2, - "save_steps": 1946, - "total_flos": 3146065897553920.0, + "save_steps": 2196, + "total_flos": 3581670722043904.0, "train_batch_size": 16, "trial_name": null, "trial_params": null