diff --git "a/trainer_state.json" "b/trainer_state.json" --- "a/trainer_state.json" +++ "b/trainer_state.json" @@ -2,7 +2,7 @@ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, - "global_step": 1784, + "global_step": 892, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, @@ -10,10745 +10,5375 @@ { "epoch": 0.0, "learning_rate": 0.0, - "loss": 4.9191, + "loss": 4.8341, "step": 1 }, { "epoch": 0.0, "learning_rate": 0.0, - "loss": 5.0705, + "loss": 5.0803, "step": 2 }, - { - "epoch": 0.0, - "learning_rate": 0.0, - "loss": 5.1719, - "step": 3 - }, { "epoch": 0.0, "learning_rate": 6e-07, - "loss": 4.7228, - "step": 4 + "loss": 4.9484, + "step": 3 }, { "epoch": 0.0, "learning_rate": 1.2e-06, - "loss": 4.8112, - "step": 5 + "loss": 4.938, + "step": 4 }, { - "epoch": 0.0, + "epoch": 0.01, "learning_rate": 1.8e-06, - "loss": 4.822, - "step": 6 + "loss": 4.7551, + "step": 5 }, { - "epoch": 0.0, + "epoch": 0.01, "learning_rate": 2.4e-06, - "loss": 4.6902, - "step": 7 + "loss": 4.8735, + "step": 6 }, { - "epoch": 0.0, + "epoch": 0.01, "learning_rate": 2.9999999999999997e-06, - "loss": 4.8359, - "step": 8 + "loss": 4.8362, + "step": 7 }, { "epoch": 0.01, "learning_rate": 3.6e-06, - "loss": 5.0293, - "step": 9 + "loss": 4.7153, + "step": 8 }, { "epoch": 0.01, "learning_rate": 4.2e-06, - "loss": 4.6929, - "step": 10 + "loss": 4.845, + "step": 9 }, { "epoch": 0.01, "learning_rate": 4.8e-06, - "loss": 4.7256, - "step": 11 + "loss": 4.6926, + "step": 10 }, { "epoch": 0.01, "learning_rate": 5.399999999999999e-06, - "loss": 4.6387, - "step": 12 + "loss": 4.7464, + "step": 11 }, { "epoch": 0.01, "learning_rate": 5.999999999999999e-06, - "loss": 4.8209, - "step": 13 + "loss": 4.6924, + "step": 12 }, { "epoch": 0.01, "learning_rate": 6.599999999999999e-06, - "loss": 4.4256, - "step": 14 + "loss": 4.6138, + "step": 13 }, { - "epoch": 0.01, + "epoch": 0.02, "learning_rate": 7.2e-06, - "loss": 4.5333, - "step": 15 + "loss": 4.5776, + "step": 14 }, { - "epoch": 0.01, + "epoch": 0.02, "learning_rate": 7.799999999999998e-06, - "loss": 4.6495, - "step": 16 + "loss": 4.4967, + "step": 15 }, { - "epoch": 0.01, + "epoch": 0.02, "learning_rate": 8.4e-06, - "loss": 4.6274, - "step": 17 + "loss": 4.608, + "step": 16 }, { - "epoch": 0.01, + "epoch": 0.02, "learning_rate": 8.999999999999999e-06, - "loss": 4.4705, - "step": 18 + "loss": 4.5824, + "step": 17 }, { - "epoch": 0.01, + "epoch": 0.02, "learning_rate": 9.6e-06, - "loss": 4.4565, - "step": 19 + "loss": 4.6884, + "step": 18 }, { - "epoch": 0.01, + "epoch": 0.02, "learning_rate": 1.02e-05, - "loss": 4.7189, - "step": 20 + "loss": 4.3842, + "step": 19 }, { - "epoch": 0.01, + "epoch": 0.02, "learning_rate": 1.0799999999999998e-05, - "loss": 4.3876, - "step": 21 + "loss": 4.5262, + "step": 20 }, { - "epoch": 0.01, + "epoch": 0.02, "learning_rate": 1.14e-05, - "loss": 4.7851, - "step": 22 + "loss": 4.4212, + "step": 21 }, { - "epoch": 0.01, + "epoch": 0.02, "learning_rate": 1.1999999999999999e-05, - "loss": 4.5608, - "step": 23 + "loss": 4.4295, + "step": 22 }, { - "epoch": 0.01, + "epoch": 0.03, "learning_rate": 1.26e-05, - "loss": 4.3061, - "step": 24 + "loss": 4.4299, + "step": 23 }, { - "epoch": 0.01, + "epoch": 0.03, "learning_rate": 1.3199999999999997e-05, - "loss": 4.4556, - "step": 25 + "loss": 4.5379, + "step": 24 }, { - "epoch": 0.01, + "epoch": 0.03, "learning_rate": 1.3799999999999998e-05, - "loss": 4.591, - "step": 26 + "loss": 4.4186, + "step": 25 }, { - "epoch": 0.02, + "epoch": 0.03, "learning_rate": 1.44e-05, - "loss": 4.3579, - "step": 27 + "loss": 4.6126, + "step": 26 }, { - "epoch": 0.02, + "epoch": 0.03, "learning_rate": 1.4999999999999999e-05, - "loss": 4.1032, - "step": 28 + "loss": 4.3153, + "step": 27 }, { - "epoch": 0.02, + "epoch": 0.03, "learning_rate": 1.5599999999999996e-05, - "loss": 4.4301, - "step": 29 + "loss": 4.2003, + "step": 28 }, { - "epoch": 0.02, + "epoch": 0.03, "learning_rate": 1.6199999999999997e-05, - "loss": 4.3323, - "step": 30 + "loss": 4.2478, + "step": 29 }, { - "epoch": 0.02, + "epoch": 0.03, "learning_rate": 1.68e-05, - "loss": 4.2493, - "step": 31 + "loss": 4.4503, + "step": 30 }, { - "epoch": 0.02, + "epoch": 0.03, "learning_rate": 1.74e-05, - "loss": 4.5836, - "step": 32 + "loss": 4.4506, + "step": 31 }, { - "epoch": 0.02, + "epoch": 0.04, "learning_rate": 1.7999999999999997e-05, - "loss": 4.2934, - "step": 33 + "loss": 4.2016, + "step": 32 }, { - "epoch": 0.02, + "epoch": 0.04, "learning_rate": 1.8599999999999998e-05, - "loss": 4.1632, - "step": 34 + "loss": 4.3275, + "step": 33 }, { - "epoch": 0.02, + "epoch": 0.04, "learning_rate": 1.92e-05, - "loss": 4.4058, - "step": 35 + "loss": 4.2134, + "step": 34 }, { - "epoch": 0.02, + "epoch": 0.04, "learning_rate": 1.98e-05, - "loss": 4.6831, - "step": 36 + "loss": 4.4024, + "step": 35 }, { - "epoch": 0.02, + "epoch": 0.04, "learning_rate": 2.04e-05, - "loss": 4.295, - "step": 37 + "loss": 4.3417, + "step": 36 }, { - "epoch": 0.02, + "epoch": 0.04, "learning_rate": 2.1e-05, - "loss": 4.4446, - "step": 38 + "loss": 4.3674, + "step": 37 }, { - "epoch": 0.02, + "epoch": 0.04, "learning_rate": 2.1599999999999996e-05, - "loss": 4.5133, - "step": 39 + "loss": 4.3929, + "step": 38 }, { - "epoch": 0.02, + "epoch": 0.04, "learning_rate": 2.2199999999999998e-05, - "loss": 4.568, - "step": 40 + "loss": 4.5473, + "step": 39 }, { - "epoch": 0.02, + "epoch": 0.04, "learning_rate": 2.28e-05, - "loss": 4.3144, - "step": 41 + "loss": 4.3338, + "step": 40 }, { - "epoch": 0.02, + "epoch": 0.05, "learning_rate": 2.34e-05, - "loss": 4.1595, - "step": 42 + "loss": 4.2202, + "step": 41 }, { - "epoch": 0.02, + "epoch": 0.05, "learning_rate": 2.3999999999999997e-05, - "loss": 4.4335, - "step": 43 + "loss": 4.3845, + "step": 42 }, { - "epoch": 0.02, + "epoch": 0.05, "learning_rate": 2.4599999999999998e-05, - "loss": 4.2563, - "step": 44 + "loss": 4.1548, + "step": 43 }, { - "epoch": 0.03, + "epoch": 0.05, "learning_rate": 2.52e-05, - "loss": 4.5112, - "step": 45 + "loss": 4.3461, + "step": 44 }, { - "epoch": 0.03, + "epoch": 0.05, "learning_rate": 2.5799999999999997e-05, - "loss": 4.5207, - "step": 46 + "loss": 4.3869, + "step": 45 }, { - "epoch": 0.03, + "epoch": 0.05, "learning_rate": 2.6399999999999995e-05, - "loss": 4.5606, - "step": 47 + "loss": 4.5388, + "step": 46 }, { - "epoch": 0.03, + "epoch": 0.05, "learning_rate": 2.6999999999999996e-05, - "loss": 4.8714, - "step": 48 + "loss": 4.3964, + "step": 47 }, { - "epoch": 0.03, + "epoch": 0.05, "learning_rate": 2.7599999999999997e-05, - "loss": 4.8818, - "step": 49 + "loss": 4.7317, + "step": 48 }, { - "epoch": 0.03, + "epoch": 0.05, "learning_rate": 2.8199999999999998e-05, - "loss": 4.8186, - "step": 50 + "loss": 4.9068, + "step": 49 }, { - "epoch": 0.03, + "epoch": 0.06, "learning_rate": 2.88e-05, - "loss": 4.2243, - "step": 51 + "loss": 4.5485, + "step": 50 }, { - "epoch": 0.03, + "epoch": 0.06, "learning_rate": 2.94e-05, - "loss": 4.4017, - "step": 52 + "loss": 4.1691, + "step": 51 }, { - "epoch": 0.03, + "epoch": 0.06, "learning_rate": 2.9999999999999997e-05, - "loss": 4.4003, - "step": 53 + "loss": 4.3223, + "step": 52 }, { - "epoch": 0.03, + "epoch": 0.06, "learning_rate": 3.06e-05, - "loss": 4.2594, - "step": 54 + "loss": 4.1806, + "step": 53 }, { - "epoch": 0.03, + "epoch": 0.06, "learning_rate": 3.119999999999999e-05, - "loss": 4.3223, - "step": 55 + "loss": 4.2318, + "step": 54 }, { - "epoch": 0.03, + "epoch": 0.06, "learning_rate": 3.1799999999999994e-05, - "loss": 4.4145, - "step": 56 + "loss": 4.2415, + "step": 55 }, { - "epoch": 0.03, + "epoch": 0.06, "learning_rate": 3.2399999999999995e-05, - "loss": 4.3264, - "step": 57 + "loss": 4.3245, + "step": 56 }, { - "epoch": 0.03, + "epoch": 0.06, "learning_rate": 3.2999999999999996e-05, - "loss": 4.288, - "step": 58 + "loss": 4.3158, + "step": 57 }, { - "epoch": 0.03, + "epoch": 0.07, "learning_rate": 3.36e-05, - "loss": 4.317, - "step": 59 + "loss": 4.5113, + "step": 58 }, { - "epoch": 0.03, + "epoch": 0.07, "learning_rate": 3.42e-05, - "loss": 4.2235, - "step": 60 + "loss": 4.2822, + "step": 59 }, { - "epoch": 0.03, + "epoch": 0.07, "learning_rate": 3.48e-05, - "loss": 4.3378, - "step": 61 + "loss": 4.1347, + "step": 60 }, { - "epoch": 0.03, + "epoch": 0.07, "learning_rate": 3.539999999999999e-05, - "loss": 4.2344, - "step": 62 + "loss": 4.3788, + "step": 61 }, { - "epoch": 0.04, + "epoch": 0.07, "learning_rate": 3.5999999999999994e-05, - "loss": 4.6038, - "step": 63 + "loss": 4.3299, + "step": 62 }, { - "epoch": 0.04, + "epoch": 0.07, "learning_rate": 3.6599999999999995e-05, - "loss": 4.0756, - "step": 64 + "loss": 4.1659, + "step": 63 }, { - "epoch": 0.04, + "epoch": 0.07, "learning_rate": 3.7199999999999996e-05, - "loss": 4.2958, - "step": 65 + "loss": 4.3157, + "step": 64 }, { - "epoch": 0.04, + "epoch": 0.07, "learning_rate": 3.78e-05, - "loss": 4.4119, - "step": 66 + "loss": 4.1146, + "step": 65 }, { - "epoch": 0.04, + "epoch": 0.07, "learning_rate": 3.84e-05, - "loss": 4.3927, - "step": 67 + "loss": 4.3448, + "step": 66 }, { - "epoch": 0.04, + "epoch": 0.08, "learning_rate": 3.9e-05, - "loss": 4.4039, - "step": 68 + "loss": 4.1496, + "step": 67 }, { - "epoch": 0.04, + "epoch": 0.08, "learning_rate": 3.96e-05, - "loss": 4.3249, - "step": 69 + "loss": 4.1818, + "step": 68 }, { - "epoch": 0.04, + "epoch": 0.08, "learning_rate": 4.02e-05, - "loss": 4.2547, - "step": 70 + "loss": 4.1254, + "step": 69 }, { - "epoch": 0.04, + "epoch": 0.08, "learning_rate": 4.08e-05, - "loss": 4.3266, - "step": 71 + "loss": 4.2486, + "step": 70 }, { - "epoch": 0.04, + "epoch": 0.08, "learning_rate": 4.14e-05, - "loss": 4.0799, - "step": 72 + "loss": 4.4334, + "step": 71 }, { - "epoch": 0.04, + "epoch": 0.08, "learning_rate": 4.2e-05, - "loss": 4.3624, - "step": 73 + "loss": 4.3278, + "step": 72 }, { - "epoch": 0.04, + "epoch": 0.08, "learning_rate": 4.259999999999999e-05, - "loss": 4.1725, - "step": 74 + "loss": 4.2484, + "step": 73 }, { - "epoch": 0.04, + "epoch": 0.08, "learning_rate": 4.319999999999999e-05, - "loss": 4.6632, - "step": 75 + "loss": 4.2927, + "step": 74 }, { - "epoch": 0.04, + "epoch": 0.08, "learning_rate": 4.3799999999999994e-05, - "loss": 4.4145, - "step": 76 + "loss": 4.1144, + "step": 75 }, { - "epoch": 0.04, + "epoch": 0.09, "learning_rate": 4.4399999999999995e-05, - "loss": 4.2575, - "step": 77 + "loss": 4.3583, + "step": 76 }, { - "epoch": 0.04, + "epoch": 0.09, "learning_rate": 4.4999999999999996e-05, - "loss": 4.1846, - "step": 78 + "loss": 4.2762, + "step": 77 }, { - "epoch": 0.04, + "epoch": 0.09, "learning_rate": 4.56e-05, - "loss": 4.2059, - "step": 79 + "loss": 4.1962, + "step": 78 }, { - "epoch": 0.04, + "epoch": 0.09, "learning_rate": 4.62e-05, - "loss": 4.5336, - "step": 80 + "loss": 4.0682, + "step": 79 }, { - "epoch": 0.05, + "epoch": 0.09, "learning_rate": 4.68e-05, - "loss": 4.1647, - "step": 81 + "loss": 4.3296, + "step": 80 }, { - "epoch": 0.05, + "epoch": 0.09, "learning_rate": 4.7399999999999993e-05, - "loss": 4.309, - "step": 82 + "loss": 4.3782, + "step": 81 }, { - "epoch": 0.05, + "epoch": 0.09, "learning_rate": 4.7999999999999994e-05, - "loss": 4.1669, - "step": 83 + "loss": 4.1636, + "step": 82 }, { - "epoch": 0.05, + "epoch": 0.09, "learning_rate": 4.8599999999999995e-05, - "loss": 4.3329, - "step": 84 + "loss": 4.4043, + "step": 83 }, { - "epoch": 0.05, + "epoch": 0.09, "learning_rate": 4.9199999999999997e-05, - "loss": 4.2231, - "step": 85 + "loss": 4.367, + "step": 84 }, { - "epoch": 0.05, + "epoch": 0.1, "learning_rate": 4.98e-05, - "loss": 4.1957, - "step": 86 + "loss": 4.2638, + "step": 85 }, { - "epoch": 0.05, + "epoch": 0.1, "learning_rate": 5.04e-05, - "loss": 4.5915, - "step": 87 + "loss": 4.2507, + "step": 86 }, { - "epoch": 0.05, + "epoch": 0.1, "learning_rate": 5.1e-05, - "loss": 4.1467, - "step": 88 + "loss": 4.2596, + "step": 87 }, { - "epoch": 0.05, + "epoch": 0.1, "learning_rate": 5.1599999999999994e-05, - "loss": 4.5149, - "step": 89 + "loss": 4.2334, + "step": 88 }, { - "epoch": 0.05, + "epoch": 0.1, "learning_rate": 5.2199999999999995e-05, - "loss": 4.0831, - "step": 90 + "loss": 4.3171, + "step": 89 }, { - "epoch": 0.05, + "epoch": 0.1, "learning_rate": 5.279999999999999e-05, - "loss": 4.4672, - "step": 91 + "loss": 4.2596, + "step": 90 }, { - "epoch": 0.05, + "epoch": 0.1, "learning_rate": 5.339999999999999e-05, - "loss": 4.133, - "step": 92 + "loss": 4.4444, + "step": 91 }, { - "epoch": 0.05, + "epoch": 0.1, "learning_rate": 5.399999999999999e-05, - "loss": 3.9872, - "step": 93 + "loss": 4.39, + "step": 92 }, { - "epoch": 0.05, + "epoch": 0.1, "learning_rate": 5.459999999999999e-05, - "loss": 4.4158, - "step": 94 + "loss": 4.1187, + "step": 93 }, { - "epoch": 0.05, + "epoch": 0.11, "learning_rate": 5.519999999999999e-05, - "loss": 4.6163, - "step": 95 + "loss": 4.3139, + "step": 94 }, { - "epoch": 0.05, + "epoch": 0.11, "learning_rate": 5.5799999999999994e-05, - "loss": 4.3208, - "step": 96 + "loss": 4.604, + "step": 95 }, { - "epoch": 0.05, + "epoch": 0.11, "learning_rate": 5.6399999999999995e-05, - "loss": 4.5119, - "step": 97 + "loss": 4.5006, + "step": 96 }, { - "epoch": 0.05, + "epoch": 0.11, "learning_rate": 5.6999999999999996e-05, - "loss": 4.4762, - "step": 98 + "loss": 4.3104, + "step": 97 }, { - "epoch": 0.06, + "epoch": 0.11, "learning_rate": 5.76e-05, - "loss": 4.7493, - "step": 99 + "loss": 4.5887, + "step": 98 }, { - "epoch": 0.06, + "epoch": 0.11, "learning_rate": 5.82e-05, - "loss": 4.7019, - "step": 100 + "loss": 4.3251, + "step": 99 }, { - "epoch": 0.06, + "epoch": 0.11, "learning_rate": 5.88e-05, - "loss": 4.4056, - "step": 101 + "loss": 4.3612, + "step": 100 }, { - "epoch": 0.06, + "epoch": 0.11, "learning_rate": 5.94e-05, - "loss": 4.2964, - "step": 102 + "loss": 4.234, + "step": 101 }, { - "epoch": 0.06, + "epoch": 0.11, "learning_rate": 5.9999999999999995e-05, - "loss": 4.4131, - "step": 103 + "loss": 4.286, + "step": 102 }, { - "epoch": 0.06, + "epoch": 0.12, "learning_rate": 6.0599999999999996e-05, - "loss": 4.2915, - "step": 104 + "loss": 4.3518, + "step": 103 }, { - "epoch": 0.06, + "epoch": 0.12, "learning_rate": 6.12e-05, - "loss": 4.2907, - "step": 105 + "loss": 4.2703, + "step": 104 }, { - "epoch": 0.06, + "epoch": 0.12, "learning_rate": 6.18e-05, - "loss": 4.291, - "step": 106 + "loss": 4.1177, + "step": 105 }, { - "epoch": 0.06, + "epoch": 0.12, "learning_rate": 6.239999999999999e-05, - "loss": 4.3064, - "step": 107 + "loss": 4.3078, + "step": 106 }, { - "epoch": 0.06, + "epoch": 0.12, "learning_rate": 6.299999999999999e-05, - "loss": 4.4313, - "step": 108 + "loss": 4.3431, + "step": 107 }, { - "epoch": 0.06, + "epoch": 0.12, "learning_rate": 6.359999999999999e-05, - "loss": 4.3089, - "step": 109 + "loss": 4.4667, + "step": 108 }, { - "epoch": 0.06, + "epoch": 0.12, "learning_rate": 6.419999999999999e-05, - "loss": 4.3506, - "step": 110 + "loss": 4.0367, + "step": 109 }, { - "epoch": 0.06, + "epoch": 0.12, "learning_rate": 6.479999999999999e-05, - "loss": 4.3167, - "step": 111 + "loss": 4.1673, + "step": 110 }, { - "epoch": 0.06, + "epoch": 0.12, "learning_rate": 6.539999999999999e-05, - "loss": 4.1755, - "step": 112 + "loss": 4.3438, + "step": 111 }, { - "epoch": 0.06, + "epoch": 0.13, "learning_rate": 6.599999999999999e-05, - "loss": 4.3455, - "step": 113 + "loss": 4.2113, + "step": 112 }, { - "epoch": 0.06, + "epoch": 0.13, "learning_rate": 6.659999999999999e-05, - "loss": 4.0854, - "step": 114 + "loss": 4.2212, + "step": 113 }, { - "epoch": 0.06, + "epoch": 0.13, "learning_rate": 6.72e-05, - "loss": 4.0838, - "step": 115 + "loss": 4.1566, + "step": 114 }, { - "epoch": 0.07, + "epoch": 0.13, "learning_rate": 6.78e-05, - "loss": 4.2054, - "step": 116 + "loss": 4.2177, + "step": 115 }, { - "epoch": 0.07, + "epoch": 0.13, "learning_rate": 6.84e-05, - "loss": 4.418, - "step": 117 + "loss": 3.9686, + "step": 116 }, { - "epoch": 0.07, + "epoch": 0.13, "learning_rate": 6.9e-05, - "loss": 4.3662, - "step": 118 + "loss": 4.2853, + "step": 117 }, { - "epoch": 0.07, + "epoch": 0.13, "learning_rate": 6.96e-05, - "loss": 4.3506, - "step": 119 + "loss": 4.1564, + "step": 118 }, { - "epoch": 0.07, + "epoch": 0.13, "learning_rate": 7.02e-05, - "loss": 4.4331, - "step": 120 + "loss": 4.2868, + "step": 119 }, { - "epoch": 0.07, + "epoch": 0.13, "learning_rate": 7.079999999999999e-05, - "loss": 4.4678, - "step": 121 + "loss": 4.3348, + "step": 120 }, { - "epoch": 0.07, + "epoch": 0.14, "learning_rate": 7.139999999999999e-05, - "loss": 4.3463, - "step": 122 + "loss": 4.2666, + "step": 121 }, { - "epoch": 0.07, + "epoch": 0.14, "learning_rate": 7.199999999999999e-05, - "loss": 4.373, - "step": 123 + "loss": 4.2278, + "step": 122 }, { - "epoch": 0.07, + "epoch": 0.14, "learning_rate": 7.259999999999999e-05, - "loss": 4.3315, - "step": 124 + "loss": 4.1031, + "step": 123 }, { - "epoch": 0.07, + "epoch": 0.14, "learning_rate": 7.319999999999999e-05, - "loss": 4.04, - "step": 125 + "loss": 4.3656, + "step": 124 }, { - "epoch": 0.07, + "epoch": 0.14, "learning_rate": 7.379999999999999e-05, - "loss": 4.5966, - "step": 126 + "loss": 4.2813, + "step": 125 }, { - "epoch": 0.07, + "epoch": 0.14, "learning_rate": 7.439999999999999e-05, - "loss": 4.3558, - "step": 127 + "loss": 4.3306, + "step": 126 }, { - "epoch": 0.07, + "epoch": 0.14, "learning_rate": 7.5e-05, - "loss": 4.312, - "step": 128 + "loss": 4.3496, + "step": 127 }, { - "epoch": 0.07, + "epoch": 0.14, "learning_rate": 7.56e-05, - "loss": 4.259, - "step": 129 + "loss": 4.2343, + "step": 128 }, { - "epoch": 0.07, + "epoch": 0.14, "learning_rate": 7.62e-05, - "loss": 4.4242, - "step": 130 + "loss": 4.1858, + "step": 129 }, { - "epoch": 0.07, + "epoch": 0.15, "learning_rate": 7.68e-05, - "loss": 4.6572, - "step": 131 + "loss": 4.3679, + "step": 130 }, { - "epoch": 0.07, + "epoch": 0.15, "learning_rate": 7.74e-05, - "loss": 4.3397, - "step": 132 + "loss": 4.2642, + "step": 131 }, { - "epoch": 0.07, + "epoch": 0.15, "learning_rate": 7.8e-05, - "loss": 4.476, - "step": 133 + "loss": 4.3506, + "step": 132 }, { - "epoch": 0.08, + "epoch": 0.15, "learning_rate": 7.86e-05, - "loss": 4.3692, - "step": 134 + "loss": 4.3609, + "step": 133 }, { - "epoch": 0.08, + "epoch": 0.15, "learning_rate": 7.92e-05, - "loss": 4.2252, - "step": 135 + "loss": 4.3009, + "step": 134 }, { - "epoch": 0.08, + "epoch": 0.15, "learning_rate": 7.98e-05, - "loss": 4.5545, - "step": 136 + "loss": 4.1569, + "step": 135 }, { - "epoch": 0.08, + "epoch": 0.15, "learning_rate": 8.04e-05, - "loss": 4.284, - "step": 137 + "loss": 4.2765, + "step": 136 }, { - "epoch": 0.08, + "epoch": 0.15, "learning_rate": 8.1e-05, - "loss": 4.5312, - "step": 138 + "loss": 4.5165, + "step": 137 }, { - "epoch": 0.08, + "epoch": 0.15, "learning_rate": 8.16e-05, - "loss": 4.6545, - "step": 139 + "loss": 4.3997, + "step": 138 }, { - "epoch": 0.08, + "epoch": 0.16, "learning_rate": 8.22e-05, - "loss": 4.2548, - "step": 140 + "loss": 4.3523, + "step": 139 }, { - "epoch": 0.08, + "epoch": 0.16, "learning_rate": 8.28e-05, - "loss": 4.5537, - "step": 141 + "loss": 4.1739, + "step": 140 }, { - "epoch": 0.08, + "epoch": 0.16, "learning_rate": 8.34e-05, - "loss": 4.6685, - "step": 142 + "loss": 4.5118, + "step": 141 }, { - "epoch": 0.08, + "epoch": 0.16, "learning_rate": 8.4e-05, - "loss": 4.4057, - "step": 143 + "loss": 4.5215, + "step": 142 }, { - "epoch": 0.08, + "epoch": 0.16, "learning_rate": 8.459999999999998e-05, - "loss": 4.4351, - "step": 144 + "loss": 4.4022, + "step": 143 }, { - "epoch": 0.08, + "epoch": 0.16, "learning_rate": 8.519999999999998e-05, - "loss": 4.7667, - "step": 145 + "loss": 4.3231, + "step": 144 }, { - "epoch": 0.08, + "epoch": 0.16, "learning_rate": 8.579999999999998e-05, - "loss": 4.6425, - "step": 146 + "loss": 4.5579, + "step": 145 }, { - "epoch": 0.08, + "epoch": 0.16, "learning_rate": 8.639999999999999e-05, - "loss": 4.666, - "step": 147 + "loss": 4.3918, + "step": 146 }, { - "epoch": 0.08, + "epoch": 0.16, "learning_rate": 8.699999999999999e-05, - "loss": 4.6928, - "step": 148 + "loss": 4.4713, + "step": 147 }, { - "epoch": 0.08, + "epoch": 0.17, "learning_rate": 8.759999999999999e-05, - "loss": 4.827, - "step": 149 + "loss": 4.592, + "step": 148 }, { - "epoch": 0.08, + "epoch": 0.17, "learning_rate": 8.819999999999999e-05, - "loss": 4.3834, - "step": 150 + "loss": 4.681, + "step": 149 }, { - "epoch": 0.08, + "epoch": 0.17, "learning_rate": 8.879999999999999e-05, - "loss": 4.214, - "step": 151 + "loss": 4.3895, + "step": 150 }, { - "epoch": 0.09, + "epoch": 0.17, "learning_rate": 8.939999999999999e-05, - "loss": 4.6902, - "step": 152 + "loss": 4.4341, + "step": 151 }, { - "epoch": 0.09, + "epoch": 0.17, "learning_rate": 8.999999999999999e-05, - "loss": 4.1044, - "step": 153 + "loss": 4.3323, + "step": 152 }, { - "epoch": 0.09, + "epoch": 0.17, "learning_rate": 9.059999999999999e-05, - "loss": 4.6479, - "step": 154 + "loss": 4.4506, + "step": 153 }, { - "epoch": 0.09, + "epoch": 0.17, "learning_rate": 9.12e-05, - "loss": 4.4189, - "step": 155 + "loss": 4.1731, + "step": 154 }, { - "epoch": 0.09, + "epoch": 0.17, "learning_rate": 9.18e-05, - "loss": 4.7801, - "step": 156 + "loss": 4.1782, + "step": 155 }, { - "epoch": 0.09, + "epoch": 0.17, "learning_rate": 9.24e-05, - "loss": 4.569, - "step": 157 + "loss": 4.2343, + "step": 156 }, { - "epoch": 0.09, + "epoch": 0.18, "learning_rate": 9.3e-05, - "loss": 4.4603, - "step": 158 + "loss": 4.4489, + "step": 157 }, { - "epoch": 0.09, + "epoch": 0.18, "learning_rate": 9.36e-05, - "loss": 4.6648, - "step": 159 + "loss": 4.51, + "step": 158 }, { - "epoch": 0.09, + "epoch": 0.18, "learning_rate": 9.419999999999999e-05, - "loss": 4.6799, - "step": 160 + "loss": 4.5539, + "step": 159 }, { - "epoch": 0.09, + "epoch": 0.18, "learning_rate": 9.479999999999999e-05, - "loss": 4.494, - "step": 161 + "loss": 4.3013, + "step": 160 }, { - "epoch": 0.09, + "epoch": 0.18, "learning_rate": 9.539999999999999e-05, - "loss": 4.9181, - "step": 162 + "loss": 4.3347, + "step": 161 }, { - "epoch": 0.09, + "epoch": 0.18, "learning_rate": 9.599999999999999e-05, - "loss": 4.458, - "step": 163 + "loss": 4.2858, + "step": 162 }, { - "epoch": 0.09, + "epoch": 0.18, "learning_rate": 9.659999999999999e-05, - "loss": 4.8579, - "step": 164 + "loss": 4.3091, + "step": 163 }, { - "epoch": 0.09, + "epoch": 0.18, "learning_rate": 9.719999999999999e-05, - "loss": 4.469, - "step": 165 + "loss": 4.4466, + "step": 164 }, { - "epoch": 0.09, + "epoch": 0.18, "learning_rate": 9.779999999999999e-05, - "loss": 4.6277, - "step": 166 + "loss": 4.3117, + "step": 165 }, { - "epoch": 0.09, + "epoch": 0.19, "learning_rate": 9.839999999999999e-05, - "loss": 4.3751, - "step": 167 + "loss": 4.3672, + "step": 166 }, { - "epoch": 0.09, + "epoch": 0.19, "learning_rate": 9.9e-05, - "loss": 4.2988, - "step": 168 + "loss": 4.306, + "step": 167 }, { - "epoch": 0.09, + "epoch": 0.19, "learning_rate": 9.96e-05, - "loss": 4.275, - "step": 169 + "loss": 4.1518, + "step": 168 }, { - "epoch": 0.1, + "epoch": 0.19, "learning_rate": 0.0001002, - "loss": 4.4271, - "step": 170 + "loss": 4.2049, + "step": 169 }, { - "epoch": 0.1, + "epoch": 0.19, "learning_rate": 0.0001008, - "loss": 4.5926, - "step": 171 + "loss": 4.2427, + "step": 170 }, { - "epoch": 0.1, + "epoch": 0.19, "learning_rate": 0.0001014, - "loss": 5.6458, - "step": 172 + "loss": 4.4892, + "step": 171 }, { - "epoch": 0.1, + "epoch": 0.19, "learning_rate": 0.000102, - "loss": 4.417, - "step": 173 + "loss": 4.5519, + "step": 172 }, { - "epoch": 0.1, + "epoch": 0.19, "learning_rate": 0.0001026, - "loss": 4.6363, - "step": 174 + "loss": 4.3668, + "step": 173 }, { - "epoch": 0.1, + "epoch": 0.2, "learning_rate": 0.00010319999999999999, - "loss": 5.063, - "step": 175 + "loss": 4.1735, + "step": 174 }, { - "epoch": 0.1, + "epoch": 0.2, "learning_rate": 0.00010379999999999999, - "loss": 4.3426, - "step": 176 + "loss": 4.3279, + "step": 175 }, { - "epoch": 0.1, + "epoch": 0.2, "learning_rate": 0.00010439999999999999, - "loss": 4.6753, - "step": 177 + "loss": 4.2638, + "step": 176 }, { - "epoch": 0.1, + "epoch": 0.2, "learning_rate": 0.00010499999999999999, - "loss": 4.342, - "step": 178 + "loss": 4.2474, + "step": 177 }, { - "epoch": 0.1, + "epoch": 0.2, "learning_rate": 0.00010559999999999998, - "loss": 4.2017, - "step": 179 + "loss": 4.2505, + "step": 178 }, { - "epoch": 0.1, + "epoch": 0.2, "learning_rate": 0.00010619999999999998, - "loss": 4.9257, - "step": 180 + "loss": 4.3682, + "step": 179 }, { - "epoch": 0.1, + "epoch": 0.2, "learning_rate": 0.00010679999999999998, - "loss": 4.6383, - "step": 181 + "loss": 4.35, + "step": 180 }, { - "epoch": 0.1, + "epoch": 0.2, "learning_rate": 0.00010739999999999998, - "loss": 4.3348, - "step": 182 + "loss": 4.3573, + "step": 181 }, { - "epoch": 0.1, + "epoch": 0.2, "learning_rate": 0.00010799999999999998, - "loss": 4.8104, - "step": 183 + "loss": 4.3769, + "step": 182 }, { - "epoch": 0.1, + "epoch": 0.21, "learning_rate": 0.00010859999999999998, - "loss": 4.5299, - "step": 184 + "loss": 4.3471, + "step": 183 }, { - "epoch": 0.1, + "epoch": 0.21, "learning_rate": 0.00010919999999999998, - "loss": 4.661, - "step": 185 + "loss": 4.7017, + "step": 184 }, { - "epoch": 0.1, + "epoch": 0.21, "learning_rate": 0.00010979999999999999, - "loss": 4.4751, - "step": 186 + "loss": 4.3939, + "step": 185 }, { - "epoch": 0.1, + "epoch": 0.21, "learning_rate": 0.00011039999999999999, - "loss": 4.3936, - "step": 187 + "loss": 4.2426, + "step": 186 }, { - "epoch": 0.11, + "epoch": 0.21, "learning_rate": 0.00011099999999999999, - "loss": 4.6367, - "step": 188 + "loss": 4.4202, + "step": 187 }, { - "epoch": 0.11, + "epoch": 0.21, "learning_rate": 0.00011159999999999999, - "loss": 4.9446, - "step": 189 + "loss": 4.1531, + "step": 188 }, { - "epoch": 0.11, + "epoch": 0.21, "learning_rate": 0.00011219999999999999, - "loss": 4.6147, - "step": 190 + "loss": 4.2871, + "step": 189 }, { - "epoch": 0.11, + "epoch": 0.21, "learning_rate": 0.00011279999999999999, - "loss": 4.6915, - "step": 191 + "loss": 4.4863, + "step": 190 }, { - "epoch": 0.11, + "epoch": 0.21, "learning_rate": 0.00011339999999999999, - "loss": 4.4692, - "step": 192 + "loss": 4.3989, + "step": 191 }, { - "epoch": 0.11, + "epoch": 0.22, "learning_rate": 0.00011399999999999999, - "loss": 4.6347, - "step": 193 + "loss": 4.4133, + "step": 192 }, { - "epoch": 0.11, + "epoch": 0.22, "learning_rate": 0.0001146, - "loss": 4.5423, - "step": 194 + "loss": 4.5601, + "step": 193 }, { - "epoch": 0.11, + "epoch": 0.22, "learning_rate": 0.0001152, - "loss": 4.7142, - "step": 195 + "loss": 4.2958, + "step": 194 }, { - "epoch": 0.11, + "epoch": 0.22, "learning_rate": 0.0001158, - "loss": 4.776, - "step": 196 + "loss": 4.7989, + "step": 195 }, { - "epoch": 0.11, + "epoch": 0.22, "learning_rate": 0.0001164, - "loss": 5.3573, - "step": 197 + "loss": 5.0871, + "step": 196 }, { - "epoch": 0.11, + "epoch": 0.22, "learning_rate": 0.000117, - "loss": 4.7596, - "step": 198 + "loss": 4.6728, + "step": 197 }, { - "epoch": 0.11, + "epoch": 0.22, "learning_rate": 0.0001176, - "loss": 4.7079, - "step": 199 + "loss": 5.3896, + "step": 198 }, { - "epoch": 0.11, + "epoch": 0.22, "learning_rate": 0.0001182, - "loss": 4.8872, - "step": 200 + "loss": 5.0053, + "step": 199 }, { - "epoch": 0.11, + "epoch": 0.22, "learning_rate": 0.0001188, - "loss": 4.5131, - "step": 201 + "loss": 4.7674, + "step": 200 }, { - "epoch": 0.11, + "epoch": 0.23, "learning_rate": 0.0001194, - "loss": 4.451, - "step": 202 + "loss": 4.3577, + "step": 201 }, { - "epoch": 0.11, + "epoch": 0.23, "learning_rate": 0.00011999999999999999, - "loss": 4.7186, - "step": 203 + "loss": 4.4474, + "step": 202 }, { - "epoch": 0.11, + "epoch": 0.23, "learning_rate": 0.00012059999999999999, - "loss": 4.8889, - "step": 204 + "loss": 4.3866, + "step": 203 }, { - "epoch": 0.11, + "epoch": 0.23, "learning_rate": 0.00012119999999999999, - "loss": 4.4065, - "step": 205 + "loss": 4.3626, + "step": 204 }, { - "epoch": 0.12, + "epoch": 0.23, "learning_rate": 0.00012179999999999999, - "loss": 4.9451, - "step": 206 + "loss": 4.3345, + "step": 205 }, { - "epoch": 0.12, + "epoch": 0.23, "learning_rate": 0.0001224, - "loss": 4.5381, - "step": 207 + "loss": 4.2588, + "step": 206 }, { - "epoch": 0.12, + "epoch": 0.23, "learning_rate": 0.00012299999999999998, - "loss": 4.8009, - "step": 208 + "loss": 4.2876, + "step": 207 }, { - "epoch": 0.12, + "epoch": 0.23, "learning_rate": 0.0001236, - "loss": 4.448, - "step": 209 + "loss": 4.1413, + "step": 208 }, { - "epoch": 0.12, + "epoch": 0.23, "learning_rate": 0.00012419999999999998, - "loss": 4.6215, - "step": 210 + "loss": 4.4226, + "step": 209 }, { - "epoch": 0.12, + "epoch": 0.24, "learning_rate": 0.00012479999999999997, - "loss": 4.4547, - "step": 211 + "loss": 4.3473, + "step": 210 }, { - "epoch": 0.12, + "epoch": 0.24, "learning_rate": 0.00012539999999999999, - "loss": 4.8644, - "step": 212 + "loss": 4.3784, + "step": 211 }, { - "epoch": 0.12, + "epoch": 0.24, "learning_rate": 0.00012599999999999997, - "loss": 4.8106, - "step": 213 + "loss": 4.3692, + "step": 212 }, { - "epoch": 0.12, + "epoch": 0.24, "learning_rate": 0.0001266, - "loss": 4.3386, - "step": 214 + "loss": 4.3243, + "step": 213 }, { - "epoch": 0.12, + "epoch": 0.24, "learning_rate": 0.00012719999999999997, - "loss": 5.0399, - "step": 215 + "loss": 4.5017, + "step": 214 }, { - "epoch": 0.12, + "epoch": 0.24, "learning_rate": 0.0001278, - "loss": 4.1736, - "step": 216 + "loss": 4.2635, + "step": 215 }, { - "epoch": 0.12, + "epoch": 0.24, "learning_rate": 0.00012839999999999998, - "loss": 4.5797, - "step": 217 + "loss": 4.3944, + "step": 216 }, { - "epoch": 0.12, + "epoch": 0.24, "learning_rate": 0.000129, - "loss": 4.419, - "step": 218 + "loss": 4.5001, + "step": 217 }, { - "epoch": 0.12, + "epoch": 0.24, "learning_rate": 0.00012959999999999998, - "loss": 4.7578, - "step": 219 + "loss": 4.3534, + "step": 218 }, { - "epoch": 0.12, + "epoch": 0.25, "learning_rate": 0.0001302, - "loss": 4.9465, - "step": 220 + "loss": 4.4056, + "step": 219 }, { - "epoch": 0.12, + "epoch": 0.25, "learning_rate": 0.00013079999999999998, - "loss": 4.5708, - "step": 221 + "loss": 4.3954, + "step": 220 }, { - "epoch": 0.12, + "epoch": 0.25, "learning_rate": 0.0001314, - "loss": 5.0395, - "step": 222 + "loss": 4.2565, + "step": 221 }, { - "epoch": 0.12, + "epoch": 0.25, "learning_rate": 0.00013199999999999998, - "loss": 4.4636, - "step": 223 + "loss": 4.3935, + "step": 222 }, { - "epoch": 0.13, + "epoch": 0.25, "learning_rate": 0.0001326, - "loss": 4.5197, - "step": 224 + "loss": 4.4942, + "step": 223 }, { - "epoch": 0.13, + "epoch": 0.25, "learning_rate": 0.00013319999999999999, - "loss": 4.7159, - "step": 225 + "loss": 4.3912, + "step": 224 }, { - "epoch": 0.13, + "epoch": 0.25, "learning_rate": 0.0001338, - "loss": 4.7991, - "step": 226 + "loss": 4.5875, + "step": 225 }, { - "epoch": 0.13, + "epoch": 0.25, "learning_rate": 0.0001344, - "loss": 4.6542, - "step": 227 + "loss": 4.5546, + "step": 226 }, { - "epoch": 0.13, + "epoch": 0.25, "learning_rate": 0.000135, - "loss": 4.4733, - "step": 228 + "loss": 4.4474, + "step": 227 }, { - "epoch": 0.13, + "epoch": 0.26, "learning_rate": 0.0001356, - "loss": 4.5371, - "step": 229 + "loss": 4.2645, + "step": 228 }, { - "epoch": 0.13, + "epoch": 0.26, "learning_rate": 0.0001362, - "loss": 4.4531, - "step": 230 + "loss": 4.3784, + "step": 229 }, { - "epoch": 0.13, + "epoch": 0.26, "learning_rate": 0.0001368, - "loss": 4.4613, - "step": 231 + "loss": 4.4013, + "step": 230 }, { - "epoch": 0.13, + "epoch": 0.26, "learning_rate": 0.0001374, - "loss": 4.956, - "step": 232 + "loss": 4.7712, + "step": 231 }, { - "epoch": 0.13, + "epoch": 0.26, "learning_rate": 0.000138, - "loss": 4.7992, - "step": 233 + "loss": 4.5995, + "step": 232 }, { - "epoch": 0.13, + "epoch": 0.26, "learning_rate": 0.0001386, - "loss": 4.62, - "step": 234 + "loss": 4.3516, + "step": 233 }, { - "epoch": 0.13, + "epoch": 0.26, "learning_rate": 0.0001392, - "loss": 4.4231, - "step": 235 + "loss": 4.6203, + "step": 234 }, { - "epoch": 0.13, + "epoch": 0.26, "learning_rate": 0.00013979999999999998, - "loss": 5.0488, - "step": 236 + "loss": 4.5716, + "step": 235 }, { - "epoch": 0.13, + "epoch": 0.26, "learning_rate": 0.0001404, - "loss": 4.6777, - "step": 237 + "loss": 4.3419, + "step": 236 }, { - "epoch": 0.13, + "epoch": 0.27, "learning_rate": 0.00014099999999999998, - "loss": 4.9638, - "step": 238 + "loss": 4.2867, + "step": 237 }, { - "epoch": 0.13, + "epoch": 0.27, "learning_rate": 0.00014159999999999997, - "loss": 5.4151, - "step": 239 + "loss": 4.5775, + "step": 238 }, { - "epoch": 0.13, + "epoch": 0.27, "learning_rate": 0.0001422, - "loss": 4.5313, - "step": 240 + "loss": 4.4182, + "step": 239 }, { - "epoch": 0.14, + "epoch": 0.27, "learning_rate": 0.00014279999999999997, - "loss": 4.7198, - "step": 241 + "loss": 4.4953, + "step": 240 }, { - "epoch": 0.14, + "epoch": 0.27, "learning_rate": 0.0001434, - "loss": 4.504, - "step": 242 + "loss": 4.6497, + "step": 241 }, { - "epoch": 0.14, + "epoch": 0.27, "learning_rate": 0.00014399999999999998, - "loss": 5.7226, - "step": 243 + "loss": 4.5663, + "step": 242 }, { - "epoch": 0.14, + "epoch": 0.27, "learning_rate": 0.0001446, - "loss": 5.7546, - "step": 244 + "loss": 5.0165, + "step": 243 }, { - "epoch": 0.14, + "epoch": 0.27, "learning_rate": 0.00014519999999999998, - "loss": 4.7633, - "step": 245 + "loss": 5.0933, + "step": 244 }, { - "epoch": 0.14, + "epoch": 0.27, "learning_rate": 0.0001458, - "loss": 4.754, - "step": 246 + "loss": 4.8255, + "step": 245 }, { - "epoch": 0.14, + "epoch": 0.28, "learning_rate": 0.00014639999999999998, - "loss": 5.2264, - "step": 247 + "loss": 4.6016, + "step": 246 }, { - "epoch": 0.14, + "epoch": 0.28, "learning_rate": 0.000147, - "loss": 4.9353, - "step": 248 + "loss": 5.0706, + "step": 247 }, { - "epoch": 0.14, + "epoch": 0.28, "learning_rate": 0.00014759999999999998, - "loss": 4.5743, - "step": 249 + "loss": 4.8076, + "step": 248 }, { - "epoch": 0.14, + "epoch": 0.28, "learning_rate": 0.0001482, - "loss": 6.3781, - "step": 250 + "loss": 5.0906, + "step": 249 }, { - "epoch": 0.14, + "epoch": 0.28, "learning_rate": 0.00014879999999999998, - "loss": 4.7726, - "step": 251 + "loss": 4.3328, + "step": 250 }, { - "epoch": 0.14, + "epoch": 0.28, "learning_rate": 0.0001494, - "loss": 5.9184, - "step": 252 + "loss": 4.7998, + "step": 251 }, { - "epoch": 0.14, + "epoch": 0.28, "learning_rate": 0.00015, - "loss": 5.0706, - "step": 253 + "loss": 4.3878, + "step": 252 }, { - "epoch": 0.14, + "epoch": 0.28, "learning_rate": 0.00015059999999999997, - "loss": 4.6637, - "step": 254 + "loss": 4.5456, + "step": 253 }, { - "epoch": 0.14, + "epoch": 0.28, "learning_rate": 0.0001512, - "loss": 4.8221, - "step": 255 + "loss": 4.4241, + "step": 254 }, { - "epoch": 0.14, + "epoch": 0.29, "learning_rate": 0.00015179999999999998, - "loss": 4.5849, - "step": 256 + "loss": 4.4375, + "step": 255 }, { - "epoch": 0.14, + "epoch": 0.29, "learning_rate": 0.0001524, - "loss": 4.6238, - "step": 257 + "loss": 4.5144, + "step": 256 }, { - "epoch": 0.14, + "epoch": 0.29, "learning_rate": 0.00015299999999999998, - "loss": 5.7408, - "step": 258 + "loss": 4.4489, + "step": 257 }, { - "epoch": 0.15, + "epoch": 0.29, "learning_rate": 0.0001536, - "loss": 4.8199, - "step": 259 + "loss": 4.3156, + "step": 258 }, { - "epoch": 0.15, + "epoch": 0.29, "learning_rate": 0.00015419999999999998, - "loss": 4.526, - "step": 260 + "loss": 4.5425, + "step": 259 }, { - "epoch": 0.15, + "epoch": 0.29, "learning_rate": 0.0001548, - "loss": 5.0876, + "loss": 4.4513, + "step": 260 + }, + { + "epoch": 0.29, + "learning_rate": 0.00015539999999999998, + "loss": 4.5724, "step": 261 }, { - "epoch": 0.15, - "learning_rate": 0.0001548, - "loss": 5.1673, + "epoch": 0.29, + "learning_rate": 0.000156, + "loss": 4.5021, "step": 262 }, { - "epoch": 0.15, - "learning_rate": 0.00015539999999999998, - "loss": 4.9192, + "epoch": 0.29, + "learning_rate": 0.00015659999999999998, + "loss": 4.4703, "step": 263 }, { - "epoch": 0.15, - "learning_rate": 0.000156, - "loss": 5.4747, + "epoch": 0.3, + "learning_rate": 0.0001572, + "loss": 4.4154, "step": 264 }, { - "epoch": 0.15, - "learning_rate": 0.00015659999999999998, - "loss": 4.8794, + "epoch": 0.3, + "learning_rate": 0.0001578, + "loss": 4.5204, "step": 265 }, { - "epoch": 0.15, - "learning_rate": 0.0001572, - "loss": 4.2857, + "epoch": 0.3, + "learning_rate": 0.0001584, + "loss": 4.8227, "step": 266 }, { - "epoch": 0.15, - "learning_rate": 0.0001578, - "loss": 5.4136, + "epoch": 0.3, + "learning_rate": 0.000159, + "loss": 4.4607, "step": 267 }, { - "epoch": 0.15, - "learning_rate": 0.0001584, - "loss": 4.8737, + "epoch": 0.3, + "learning_rate": 0.0001596, + "loss": 4.6159, "step": 268 }, { - "epoch": 0.15, - "learning_rate": 0.000159, - "loss": 4.7834, + "epoch": 0.3, + "learning_rate": 0.0001602, + "loss": 4.3676, "step": 269 }, { - "epoch": 0.15, - "learning_rate": 0.0001596, - "loss": 4.3439, + "epoch": 0.3, + "learning_rate": 0.0001608, + "loss": 4.584, "step": 270 }, { - "epoch": 0.15, - "learning_rate": 0.0001602, - "loss": 4.5798, + "epoch": 0.3, + "learning_rate": 0.0001614, + "loss": 4.2784, "step": 271 }, { - "epoch": 0.15, - "learning_rate": 0.0001608, - "loss": 4.9763, + "epoch": 0.3, + "learning_rate": 0.000162, + "loss": 4.4427, "step": 272 }, { - "epoch": 0.15, - "learning_rate": 0.0001614, - "loss": 4.8468, + "epoch": 0.31, + "learning_rate": 0.0001626, + "loss": 4.7132, "step": 273 }, { - "epoch": 0.15, - "learning_rate": 0.000162, - "loss": 5.0948, + "epoch": 0.31, + "learning_rate": 0.0001632, + "loss": 4.3542, "step": 274 }, { - "epoch": 0.15, - "learning_rate": 0.0001626, - "loss": 4.6469, + "epoch": 0.31, + "learning_rate": 0.0001638, + "loss": 4.8528, "step": 275 }, { - "epoch": 0.15, - "learning_rate": 0.0001632, - "loss": 5.6602, + "epoch": 0.31, + "learning_rate": 0.0001644, + "loss": 4.848, "step": 276 }, { - "epoch": 0.16, - "learning_rate": 0.0001638, - "loss": 4.7986, + "epoch": 0.31, + "learning_rate": 0.000165, + "loss": 4.6258, "step": 277 }, { - "epoch": 0.16, - "learning_rate": 0.0001644, - "loss": 4.7869, + "epoch": 0.31, + "learning_rate": 0.0001656, + "loss": 4.2584, "step": 278 }, { - "epoch": 0.16, - "learning_rate": 0.000165, - "loss": 4.3733, + "epoch": 0.31, + "learning_rate": 0.0001662, + "loss": 4.4303, "step": 279 }, { - "epoch": 0.16, - "learning_rate": 0.0001656, - "loss": 4.4388, + "epoch": 0.31, + "learning_rate": 0.0001668, + "loss": 4.7359, "step": 280 }, { - "epoch": 0.16, - "learning_rate": 0.0001662, - "loss": 4.8015, + "epoch": 0.32, + "learning_rate": 0.0001674, + "loss": 4.4162, "step": 281 }, { - "epoch": 0.16, - "learning_rate": 0.0001668, - "loss": 5.3186, + "epoch": 0.32, + "learning_rate": 0.000168, + "loss": 4.4254, "step": 282 }, { - "epoch": 0.16, - "learning_rate": 0.0001674, - "loss": 5.2024, + "epoch": 0.32, + "learning_rate": 0.0001686, + "loss": 4.1851, "step": 283 }, { - "epoch": 0.16, - "learning_rate": 0.000168, - "loss": 4.8717, + "epoch": 0.32, + "learning_rate": 0.00016919999999999997, + "loss": 4.5322, "step": 284 }, { - "epoch": 0.16, - "learning_rate": 0.0001686, - "loss": 4.8849, + "epoch": 0.32, + "learning_rate": 0.00016979999999999998, + "loss": 4.6086, "step": 285 }, { - "epoch": 0.16, - "learning_rate": 0.00016919999999999997, - "loss": 4.8802, + "epoch": 0.32, + "learning_rate": 0.00017039999999999997, + "loss": 4.4425, "step": 286 }, { - "epoch": 0.16, - "learning_rate": 0.00016979999999999998, - "loss": 4.698, + "epoch": 0.32, + "learning_rate": 0.00017099999999999998, + "loss": 4.7046, "step": 287 }, { - "epoch": 0.16, - "learning_rate": 0.00017039999999999997, - "loss": 4.8804, + "epoch": 0.32, + "learning_rate": 0.00017159999999999997, + "loss": 4.6408, "step": 288 }, { - "epoch": 0.16, - "learning_rate": 0.00017099999999999998, - "loss": 4.6567, + "epoch": 0.32, + "learning_rate": 0.00017219999999999998, + "loss": 4.6942, "step": 289 }, { - "epoch": 0.16, - "learning_rate": 0.00017159999999999997, - "loss": 5.226, + "epoch": 0.33, + "learning_rate": 0.00017279999999999997, + "loss": 4.6128, "step": 290 }, { - "epoch": 0.16, - "learning_rate": 0.00017219999999999998, - "loss": 4.6562, + "epoch": 0.33, + "learning_rate": 0.00017339999999999996, + "loss": 4.6296, "step": 291 }, { - "epoch": 0.16, - "learning_rate": 0.00017279999999999997, - "loss": 5.9367, + "epoch": 0.33, + "learning_rate": 0.00017399999999999997, + "loss": 4.3983, "step": 292 }, { - "epoch": 0.16, - "learning_rate": 0.00017339999999999996, - "loss": 4.9672, + "epoch": 0.33, + "learning_rate": 0.00017459999999999996, + "loss": 5.7599, "step": 293 }, { - "epoch": 0.16, - "learning_rate": 0.00017399999999999997, - "loss": 4.8979, + "epoch": 0.33, + "learning_rate": 0.00017519999999999998, + "loss": 4.4654, "step": 294 }, { - "epoch": 0.17, - "learning_rate": 0.00017459999999999996, - "loss": 4.6291, + "epoch": 0.33, + "learning_rate": 0.00017579999999999996, + "loss": 4.4359, "step": 295 }, { - "epoch": 0.17, - "learning_rate": 0.00017519999999999998, - "loss": 5.3115, + "epoch": 0.33, + "learning_rate": 0.00017639999999999998, + "loss": 5.1782, "step": 296 }, { - "epoch": 0.17, - "learning_rate": 0.00017579999999999996, - "loss": 5.4386, + "epoch": 0.33, + "learning_rate": 0.00017699999999999997, + "loss": 5.5602, "step": 297 }, { - "epoch": 0.17, - "learning_rate": 0.00017639999999999998, - "loss": 4.9214, + "epoch": 0.33, + "learning_rate": 0.00017759999999999998, + "loss": 4.4444, "step": 298 }, { - "epoch": 0.17, - "learning_rate": 0.00017699999999999997, - "loss": 4.6251, + "epoch": 0.34, + "learning_rate": 0.00017819999999999997, + "loss": 5.1858, "step": 299 }, { - "epoch": 0.17, - "learning_rate": 0.00017759999999999998, - "loss": 5.9639, + "epoch": 0.34, + "learning_rate": 0.00017879999999999998, + "loss": 4.8036, "step": 300 }, { - "epoch": 0.17, - "learning_rate": 0.00017819999999999997, - "loss": 5.1335, + "epoch": 0.34, + "learning_rate": 0.00017939999999999997, + "loss": 4.6789, "step": 301 }, { - "epoch": 0.17, - "learning_rate": 0.00017879999999999998, - "loss": 5.1075, + "epoch": 0.34, + "learning_rate": 0.00017999999999999998, + "loss": 4.4956, "step": 302 }, { - "epoch": 0.17, - "learning_rate": 0.00017939999999999997, - "loss": 4.7564, + "epoch": 0.34, + "learning_rate": 0.00018059999999999997, + "loss": 4.4828, "step": 303 }, { - "epoch": 0.17, - "learning_rate": 0.00017999999999999998, - "loss": 4.6956, + "epoch": 0.34, + "learning_rate": 0.00018119999999999999, + "loss": 4.4864, "step": 304 }, { - "epoch": 0.17, - "learning_rate": 0.00018059999999999997, - "loss": 5.9229, + "epoch": 0.34, + "learning_rate": 0.00018179999999999997, + "loss": 4.4415, "step": 305 }, { - "epoch": 0.17, - "learning_rate": 0.00018119999999999999, - "loss": 4.9089, + "epoch": 0.34, + "learning_rate": 0.0001824, + "loss": 4.3694, "step": 306 }, { - "epoch": 0.17, - "learning_rate": 0.00018179999999999997, - "loss": 4.6924, + "epoch": 0.34, + "learning_rate": 0.00018299999999999998, + "loss": 4.3808, "step": 307 }, { - "epoch": 0.17, - "learning_rate": 0.0001824, - "loss": 6.4496, + "epoch": 0.35, + "learning_rate": 0.0001836, + "loss": 5.1051, "step": 308 }, { - "epoch": 0.17, - "learning_rate": 0.00018299999999999998, - "loss": 4.9163, + "epoch": 0.35, + "learning_rate": 0.00018419999999999998, + "loss": 4.9031, "step": 309 }, { - "epoch": 0.17, - "learning_rate": 0.0001836, - "loss": 5.1547, + "epoch": 0.35, + "learning_rate": 0.0001848, + "loss": 4.5493, "step": 310 }, { - "epoch": 0.17, - "learning_rate": 0.00018419999999999998, - "loss": 4.757, + "epoch": 0.35, + "learning_rate": 0.00018539999999999998, + "loss": 4.6737, "step": 311 }, { - "epoch": 0.17, - "learning_rate": 0.0001848, - "loss": 4.8216, + "epoch": 0.35, + "learning_rate": 0.000186, + "loss": 4.6674, "step": 312 }, { - "epoch": 0.18, - "learning_rate": 0.00018539999999999998, - "loss": 5.1995, + "epoch": 0.35, + "learning_rate": 0.00018659999999999998, + "loss": 4.5483, "step": 313 }, { - "epoch": 0.18, - "learning_rate": 0.000186, - "loss": 5.3359, + "epoch": 0.35, + "learning_rate": 0.0001872, + "loss": 4.6706, "step": 314 }, { - "epoch": 0.18, - "learning_rate": 0.00018659999999999998, - "loss": 4.6453, + "epoch": 0.35, + "learning_rate": 0.00018779999999999998, + "loss": 4.4163, "step": 315 }, { - "epoch": 0.18, - "learning_rate": 0.0001872, - "loss": 4.521, + "epoch": 0.35, + "learning_rate": 0.00018839999999999997, + "loss": 4.7195, "step": 316 }, { - "epoch": 0.18, - "learning_rate": 0.00018779999999999998, - "loss": 4.5169, + "epoch": 0.36, + "learning_rate": 0.00018899999999999999, + "loss": 4.3358, "step": 317 }, { - "epoch": 0.18, - "learning_rate": 0.00018839999999999997, - "loss": 4.5329, + "epoch": 0.36, + "learning_rate": 0.00018959999999999997, + "loss": 4.6431, "step": 318 }, { - "epoch": 0.18, - "learning_rate": 0.00018899999999999999, - "loss": 5.2241, + "epoch": 0.36, + "learning_rate": 0.0001902, + "loss": 4.5899, "step": 319 }, { - "epoch": 0.18, - "learning_rate": 0.00018959999999999997, - "loss": 5.3391, + "epoch": 0.36, + "learning_rate": 0.00019079999999999998, + "loss": 4.5086, "step": 320 }, { - "epoch": 0.18, - "learning_rate": 0.0001902, - "loss": 5.2073, + "epoch": 0.36, + "learning_rate": 0.0001914, + "loss": 4.9276, "step": 321 }, { - "epoch": 0.18, - "learning_rate": 0.00019079999999999998, - "loss": 4.8598, + "epoch": 0.36, + "learning_rate": 0.00019199999999999998, + "loss": 4.3389, "step": 322 }, { - "epoch": 0.18, - "learning_rate": 0.0001914, - "loss": 5.1992, + "epoch": 0.36, + "learning_rate": 0.0001926, + "loss": 4.6948, "step": 323 }, { - "epoch": 0.18, - "learning_rate": 0.00019199999999999998, - "loss": 4.5836, + "epoch": 0.36, + "learning_rate": 0.00019319999999999998, + "loss": 4.7336, "step": 324 }, { - "epoch": 0.18, - "learning_rate": 0.0001926, - "loss": 4.9225, + "epoch": 0.36, + "learning_rate": 0.0001938, + "loss": 4.9553, "step": 325 }, { - "epoch": 0.18, - "learning_rate": 0.00019319999999999998, - "loss": 5.1464, + "epoch": 0.37, + "learning_rate": 0.00019439999999999998, + "loss": 4.5859, "step": 326 }, { - "epoch": 0.18, - "learning_rate": 0.0001938, - "loss": 4.9925, + "epoch": 0.37, + "learning_rate": 0.000195, + "loss": 4.2546, "step": 327 }, { - "epoch": 0.18, - "learning_rate": 0.00019439999999999998, - "loss": 5.9207, + "epoch": 0.37, + "learning_rate": 0.00019559999999999998, + "loss": 4.4114, "step": 328 }, { - "epoch": 0.18, - "learning_rate": 0.000195, - "loss": 4.5853, + "epoch": 0.37, + "learning_rate": 0.0001962, + "loss": 5.0732, "step": 329 }, { - "epoch": 0.18, - "learning_rate": 0.00019559999999999998, - "loss": 5.196, + "epoch": 0.37, + "learning_rate": 0.00019679999999999999, + "loss": 5.1987, "step": 330 }, { - "epoch": 0.19, - "learning_rate": 0.0001962, - "loss": 4.6906, + "epoch": 0.37, + "learning_rate": 0.0001974, + "loss": 4.4289, "step": 331 }, { - "epoch": 0.19, - "learning_rate": 0.00019679999999999999, - "loss": 4.988, + "epoch": 0.37, + "learning_rate": 0.000198, + "loss": 4.5965, "step": 332 }, { - "epoch": 0.19, - "learning_rate": 0.0001974, - "loss": 5.5124, + "epoch": 0.37, + "learning_rate": 0.0001986, + "loss": 4.67, "step": 333 }, { - "epoch": 0.19, - "learning_rate": 0.000198, - "loss": 4.9945, + "epoch": 0.37, + "learning_rate": 0.0001992, + "loss": 4.697, "step": 334 }, { - "epoch": 0.19, - "learning_rate": 0.0001986, - "loss": 5.0522, + "epoch": 0.38, + "learning_rate": 0.0001998, + "loss": 4.7254, "step": 335 }, { - "epoch": 0.19, - "learning_rate": 0.0001992, - "loss": 4.9636, + "epoch": 0.38, + "learning_rate": 0.0002004, + "loss": 4.4706, "step": 336 }, { - "epoch": 0.19, - "learning_rate": 0.0001998, - "loss": 4.6617, + "epoch": 0.38, + "learning_rate": 0.000201, + "loss": 4.472, "step": 337 }, { - "epoch": 0.19, - "learning_rate": 0.0002004, - "loss": 4.7841, + "epoch": 0.38, + "learning_rate": 0.0002016, + "loss": 4.5389, "step": 338 }, { - "epoch": 0.19, - "learning_rate": 0.000201, - "loss": 4.5353, + "epoch": 0.38, + "learning_rate": 0.0002022, + "loss": 4.5032, "step": 339 }, { - "epoch": 0.19, - "learning_rate": 0.0002016, - "loss": 4.6245, + "epoch": 0.38, + "learning_rate": 0.0002028, + "loss": 4.5175, "step": 340 }, { - "epoch": 0.19, - "learning_rate": 0.0002022, - "loss": 4.5246, + "epoch": 0.38, + "learning_rate": 0.00020339999999999998, + "loss": 5.2613, "step": 341 }, { - "epoch": 0.19, - "learning_rate": 0.0002028, - "loss": 4.7354, + "epoch": 0.38, + "learning_rate": 0.000204, + "loss": 4.5937, "step": 342 }, { - "epoch": 0.19, - "learning_rate": 0.00020339999999999998, - "loss": 5.0673, + "epoch": 0.38, + "learning_rate": 0.00020459999999999999, + "loss": 4.6838, "step": 343 }, { - "epoch": 0.19, - "learning_rate": 0.000204, - "loss": 4.4705, + "epoch": 0.39, + "learning_rate": 0.0002052, + "loss": 4.5572, "step": 344 }, { - "epoch": 0.19, - "learning_rate": 0.00020459999999999999, - "loss": 6.2521, + "epoch": 0.39, + "learning_rate": 0.0002058, + "loss": 4.5096, "step": 345 }, { - "epoch": 0.19, - "learning_rate": 0.0002052, - "loss": 4.4391, + "epoch": 0.39, + "learning_rate": 0.00020639999999999998, + "loss": 4.8472, "step": 346 }, { - "epoch": 0.19, - "learning_rate": 0.0002058, - "loss": 5.2762, + "epoch": 0.39, + "learning_rate": 0.00020699999999999996, + "loss": 5.5112, "step": 347 }, { - "epoch": 0.2, - "learning_rate": 0.00020639999999999998, - "loss": 5.1449, + "epoch": 0.39, + "learning_rate": 0.00020759999999999998, + "loss": 4.5788, "step": 348 }, { - "epoch": 0.2, - "learning_rate": 0.00020699999999999996, - "loss": 6.8858, + "epoch": 0.39, + "learning_rate": 0.00020819999999999996, + "loss": 4.7881, "step": 349 }, { - "epoch": 0.2, - "learning_rate": 0.00020759999999999998, - "loss": 6.0183, + "epoch": 0.39, + "learning_rate": 0.00020879999999999998, + "loss": 4.8584, "step": 350 }, { - "epoch": 0.2, - "learning_rate": 0.00020819999999999996, - "loss": 5.0835, + "epoch": 0.39, + "learning_rate": 0.00020939999999999997, + "loss": 4.9164, "step": 351 }, { - "epoch": 0.2, - "learning_rate": 0.00020879999999999998, - "loss": 4.8358, + "epoch": 0.39, + "learning_rate": 0.00020999999999999998, + "loss": 4.659, "step": 352 }, { - "epoch": 0.2, - "learning_rate": 0.00020939999999999997, - "loss": 4.8581, + "epoch": 0.4, + "learning_rate": 0.00021059999999999997, + "loss": 4.6836, "step": 353 }, { - "epoch": 0.2, - "learning_rate": 0.00020999999999999998, - "loss": 4.7694, + "epoch": 0.4, + "learning_rate": 0.00021119999999999996, + "loss": 4.9139, "step": 354 }, { - "epoch": 0.2, - "learning_rate": 0.00021059999999999997, - "loss": 4.6657, + "epoch": 0.4, + "learning_rate": 0.00021179999999999997, + "loss": 5.4537, "step": 355 }, { - "epoch": 0.2, - "learning_rate": 0.00021119999999999996, - "loss": 4.8611, + "epoch": 0.4, + "learning_rate": 0.00021239999999999996, + "loss": 5.1954, "step": 356 }, { - "epoch": 0.2, - "learning_rate": 0.00021179999999999997, - "loss": 4.974, + "epoch": 0.4, + "learning_rate": 0.00021299999999999997, + "loss": 4.8089, "step": 357 }, { - "epoch": 0.2, - "learning_rate": 0.00021239999999999996, - "loss": 5.1016, + "epoch": 0.4, + "learning_rate": 0.00021359999999999996, + "loss": 5.0957, "step": 358 }, { - "epoch": 0.2, - "learning_rate": 0.00021299999999999997, - "loss": 5.6709, + "epoch": 0.4, + "learning_rate": 0.00021419999999999998, + "loss": 4.6529, "step": 359 }, { - "epoch": 0.2, - "learning_rate": 0.00021359999999999996, - "loss": 4.8099, + "epoch": 0.4, + "learning_rate": 0.00021479999999999996, + "loss": 4.7965, "step": 360 }, { - "epoch": 0.2, - "learning_rate": 0.00021419999999999998, - "loss": 5.1745, + "epoch": 0.4, + "learning_rate": 0.00021539999999999998, + "loss": 4.8971, "step": 361 }, { - "epoch": 0.2, - "learning_rate": 0.00021479999999999996, - "loss": 4.556, + "epoch": 0.41, + "learning_rate": 0.00021599999999999996, + "loss": 4.5586, "step": 362 }, { - "epoch": 0.2, - "learning_rate": 0.00021539999999999998, - "loss": 5.0925, + "epoch": 0.41, + "learning_rate": 0.00021659999999999998, + "loss": 4.4938, "step": 363 }, { - "epoch": 0.2, - "learning_rate": 0.00021599999999999996, - "loss": 4.9719, + "epoch": 0.41, + "learning_rate": 0.00021719999999999997, + "loss": 4.777, "step": 364 }, { - "epoch": 0.2, - "learning_rate": 0.00021659999999999998, - "loss": 5.4165, + "epoch": 0.41, + "learning_rate": 0.00021779999999999998, + "loss": 4.4398, "step": 365 }, { - "epoch": 0.21, - "learning_rate": 0.00021719999999999997, - "loss": 5.3538, + "epoch": 0.41, + "learning_rate": 0.00021839999999999997, + "loss": 4.9263, "step": 366 }, { - "epoch": 0.21, - "learning_rate": 0.00021779999999999998, - "loss": 4.6024, + "epoch": 0.41, + "learning_rate": 0.00021899999999999998, + "loss": 4.6826, "step": 367 }, { - "epoch": 0.21, - "learning_rate": 0.00021839999999999997, - "loss": 4.6038, + "epoch": 0.41, + "learning_rate": 0.00021959999999999997, + "loss": 4.5316, "step": 368 }, { - "epoch": 0.21, - "learning_rate": 0.00021899999999999998, - "loss": 6.0151, + "epoch": 0.41, + "learning_rate": 0.00022019999999999999, + "loss": 4.7346, "step": 369 }, { - "epoch": 0.21, - "learning_rate": 0.00021959999999999997, - "loss": 5.0663, + "epoch": 0.41, + "learning_rate": 0.00022079999999999997, + "loss": 4.7118, "step": 370 }, { - "epoch": 0.21, - "learning_rate": 0.00022019999999999999, - "loss": 4.5145, + "epoch": 0.42, + "learning_rate": 0.0002214, + "loss": 4.4928, "step": 371 }, { - "epoch": 0.21, - "learning_rate": 0.00022079999999999997, - "loss": 5.5039, + "epoch": 0.42, + "learning_rate": 0.00022199999999999998, + "loss": 4.8548, "step": 372 }, { - "epoch": 0.21, - "learning_rate": 0.0002214, - "loss": 5.2572, + "epoch": 0.42, + "learning_rate": 0.0002226, + "loss": 4.7205, "step": 373 }, { - "epoch": 0.21, - "learning_rate": 0.00022199999999999998, - "loss": 5.0802, + "epoch": 0.42, + "learning_rate": 0.00022319999999999998, + "loss": 4.9808, "step": 374 }, { - "epoch": 0.21, - "learning_rate": 0.0002226, - "loss": 4.4259, + "epoch": 0.42, + "learning_rate": 0.0002238, + "loss": 4.4609, "step": 375 }, { - "epoch": 0.21, - "learning_rate": 0.00022319999999999998, - "loss": 4.7037, + "epoch": 0.42, + "learning_rate": 0.00022439999999999998, + "loss": 4.9471, "step": 376 }, { - "epoch": 0.21, - "learning_rate": 0.0002238, - "loss": 4.6645, + "epoch": 0.42, + "learning_rate": 0.000225, + "loss": 4.4643, "step": 377 }, { - "epoch": 0.21, - "learning_rate": 0.00022439999999999998, - "loss": 4.5333, + "epoch": 0.42, + "learning_rate": 0.00022559999999999998, + "loss": 4.6635, "step": 378 }, { - "epoch": 0.21, - "learning_rate": 0.000225, - "loss": 4.5828, + "epoch": 0.42, + "learning_rate": 0.00022619999999999997, + "loss": 4.5312, "step": 379 }, { - "epoch": 0.21, - "learning_rate": 0.00022559999999999998, - "loss": 5.0351, + "epoch": 0.43, + "learning_rate": 0.00022679999999999998, + "loss": 4.7006, "step": 380 }, { - "epoch": 0.21, - "learning_rate": 0.00022619999999999997, - "loss": 4.3385, + "epoch": 0.43, + "learning_rate": 0.00022739999999999997, + "loss": 4.5056, "step": 381 }, { - "epoch": 0.21, - "learning_rate": 0.00022679999999999998, - "loss": 4.7117, + "epoch": 0.43, + "learning_rate": 0.00022799999999999999, + "loss": 4.463, "step": 382 }, { - "epoch": 0.21, - "learning_rate": 0.00022739999999999997, - "loss": 4.6039, + "epoch": 0.43, + "learning_rate": 0.00022859999999999997, + "loss": 5.1356, "step": 383 }, { - "epoch": 0.22, - "learning_rate": 0.00022799999999999999, - "loss": 5.4067, + "epoch": 0.43, + "learning_rate": 0.0002292, + "loss": 4.6337, "step": 384 }, { - "epoch": 0.22, - "learning_rate": 0.00022859999999999997, - "loss": 4.9805, + "epoch": 0.43, + "learning_rate": 0.00022979999999999997, + "loss": 4.6499, "step": 385 }, { - "epoch": 0.22, - "learning_rate": 0.0002292, - "loss": 4.7761, + "epoch": 0.43, + "learning_rate": 0.0002304, + "loss": 4.8683, "step": 386 }, { - "epoch": 0.22, - "learning_rate": 0.00022979999999999997, - "loss": 6.7761, + "epoch": 0.43, + "learning_rate": 0.00023099999999999998, + "loss": 4.6877, "step": 387 }, { - "epoch": 0.22, - "learning_rate": 0.0002304, - "loss": 4.4744, + "epoch": 0.43, + "learning_rate": 0.0002316, + "loss": 4.7703, "step": 388 }, { - "epoch": 0.22, - "learning_rate": 0.00023099999999999998, - "loss": 5.0283, + "epoch": 0.44, + "learning_rate": 0.00023219999999999998, + "loss": 4.6602, "step": 389 }, { - "epoch": 0.22, - "learning_rate": 0.0002316, - "loss": 6.5362, + "epoch": 0.44, + "learning_rate": 0.0002328, + "loss": 5.0511, "step": 390 }, { - "epoch": 0.22, - "learning_rate": 0.00023219999999999998, - "loss": 4.4811, + "epoch": 0.44, + "learning_rate": 0.00023339999999999998, + "loss": 4.9178, "step": 391 }, { - "epoch": 0.22, - "learning_rate": 0.0002328, - "loss": 5.2497, + "epoch": 0.44, + "learning_rate": 0.000234, + "loss": 4.8365, "step": 392 }, { - "epoch": 0.22, - "learning_rate": 0.00023339999999999998, - "loss": 4.9157, + "epoch": 0.44, + "learning_rate": 0.00023459999999999998, + "loss": 5.0203, "step": 393 }, { - "epoch": 0.22, - "learning_rate": 0.000234, - "loss": 5.0237, + "epoch": 0.44, + "learning_rate": 0.0002352, + "loss": 4.8814, "step": 394 }, { - "epoch": 0.22, - "learning_rate": 0.00023459999999999998, - "loss": 6.4047, + "epoch": 0.44, + "learning_rate": 0.00023579999999999999, + "loss": 5.312, "step": 395 }, { - "epoch": 0.22, - "learning_rate": 0.0002352, - "loss": 6.2959, + "epoch": 0.44, + "learning_rate": 0.0002364, + "loss": 5.3549, "step": 396 }, { - "epoch": 0.22, - "learning_rate": 0.00023579999999999999, - "loss": 5.8696, + "epoch": 0.45, + "learning_rate": 0.000237, + "loss": 5.0147, "step": 397 }, { - "epoch": 0.22, - "learning_rate": 0.0002364, - "loss": 7.4495, + "epoch": 0.45, + "learning_rate": 0.0002376, + "loss": 4.7298, "step": 398 }, { - "epoch": 0.22, - "learning_rate": 0.000237, - "loss": 6.94, + "epoch": 0.45, + "learning_rate": 0.0002382, + "loss": 4.702, "step": 399 }, { - "epoch": 0.22, - "learning_rate": 0.0002376, - "loss": 5.3495, + "epoch": 0.45, + "learning_rate": 0.0002388, + "loss": 5.215, "step": 400 }, { - "epoch": 0.22, - "learning_rate": 0.0002382, - "loss": 5.2584, + "epoch": 0.45, + "learning_rate": 0.0002394, + "loss": 4.9992, "step": 401 }, { - "epoch": 0.23, - "learning_rate": 0.0002388, - "loss": 4.8706, + "epoch": 0.45, + "learning_rate": 0.00023999999999999998, + "loss": 4.897, "step": 402 }, { - "epoch": 0.23, - "learning_rate": 0.0002394, - "loss": 4.6789, + "epoch": 0.45, + "learning_rate": 0.0002406, + "loss": 5.1686, "step": 403 }, { - "epoch": 0.23, - "learning_rate": 0.00023999999999999998, - "loss": 5.1852, + "epoch": 0.45, + "learning_rate": 0.00024119999999999998, + "loss": 4.7273, "step": 404 }, { - "epoch": 0.23, - "learning_rate": 0.0002406, - "loss": 4.6802, + "epoch": 0.45, + "learning_rate": 0.0002418, + "loss": 4.8053, "step": 405 }, { - "epoch": 0.23, - "learning_rate": 0.00024119999999999998, - "loss": 5.2712, + "epoch": 0.46, + "learning_rate": 0.00024239999999999998, + "loss": 4.9928, "step": 406 }, { - "epoch": 0.23, - "learning_rate": 0.0002418, - "loss": 5.1058, + "epoch": 0.46, + "learning_rate": 0.000243, + "loss": 4.5314, "step": 407 }, { - "epoch": 0.23, - "learning_rate": 0.00024239999999999998, - "loss": 4.9108, + "epoch": 0.46, + "learning_rate": 0.00024359999999999999, + "loss": 4.4265, "step": 408 }, { - "epoch": 0.23, - "learning_rate": 0.000243, - "loss": 5.5337, + "epoch": 0.46, + "learning_rate": 0.00024419999999999997, + "loss": 4.6468, "step": 409 }, { - "epoch": 0.23, - "learning_rate": 0.00024359999999999999, - "loss": 5.1354, + "epoch": 0.46, + "learning_rate": 0.0002448, + "loss": 4.8918, "step": 410 }, { - "epoch": 0.23, - "learning_rate": 0.00024419999999999997, - "loss": 5.484, + "epoch": 0.46, + "learning_rate": 0.00024539999999999995, + "loss": 4.6892, "step": 411 }, { - "epoch": 0.23, - "learning_rate": 0.0002448, - "loss": 5.2163, + "epoch": 0.46, + "learning_rate": 0.00024599999999999996, + "loss": 4.8, "step": 412 }, { - "epoch": 0.23, - "learning_rate": 0.00024539999999999995, - "loss": 5.5183, + "epoch": 0.46, + "learning_rate": 0.0002466, + "loss": 5.212, "step": 413 }, { - "epoch": 0.23, - "learning_rate": 0.00024599999999999996, - "loss": 5.0414, + "epoch": 0.46, + "learning_rate": 0.0002472, + "loss": 4.5123, "step": 414 }, { - "epoch": 0.23, - "learning_rate": 0.0002466, - "loss": 4.9839, + "epoch": 0.47, + "learning_rate": 0.00024779999999999995, + "loss": 4.8282, "step": 415 }, { - "epoch": 0.23, - "learning_rate": 0.0002472, - "loss": 4.7387, + "epoch": 0.47, + "learning_rate": 0.00024839999999999997, + "loss": 4.6498, "step": 416 }, { - "epoch": 0.23, - "learning_rate": 0.00024779999999999995, - "loss": 5.3157, + "epoch": 0.47, + "learning_rate": 0.000249, + "loss": 4.7483, "step": 417 }, { - "epoch": 0.23, - "learning_rate": 0.00024839999999999997, - "loss": 4.8673, + "epoch": 0.47, + "learning_rate": 0.00024959999999999994, + "loss": 4.7704, "step": 418 }, { - "epoch": 0.23, - "learning_rate": 0.000249, - "loss": 4.8801, + "epoch": 0.47, + "learning_rate": 0.00025019999999999996, + "loss": 4.5658, "step": 419 }, { - "epoch": 0.24, - "learning_rate": 0.00024959999999999994, - "loss": 4.8833, + "epoch": 0.47, + "learning_rate": 0.00025079999999999997, + "loss": 4.6681, "step": 420 }, { - "epoch": 0.24, - "learning_rate": 0.00025019999999999996, - "loss": 4.7498, + "epoch": 0.47, + "learning_rate": 0.0002514, + "loss": 4.4978, "step": 421 }, { - "epoch": 0.24, - "learning_rate": 0.00025079999999999997, - "loss": 4.9571, + "epoch": 0.47, + "learning_rate": 0.00025199999999999995, + "loss": 5.0288, "step": 422 }, { - "epoch": 0.24, - "learning_rate": 0.0002514, - "loss": 5.0206, + "epoch": 0.47, + "learning_rate": 0.00025259999999999996, + "loss": 4.9343, "step": 423 }, { - "epoch": 0.24, - "learning_rate": 0.00025199999999999995, - "loss": 5.1335, + "epoch": 0.48, + "learning_rate": 0.0002532, + "loss": 4.6185, "step": 424 }, { - "epoch": 0.24, - "learning_rate": 0.00025259999999999996, - "loss": 4.8988, + "epoch": 0.48, + "learning_rate": 0.0002538, + "loss": 4.7412, "step": 425 }, { - "epoch": 0.24, - "learning_rate": 0.0002532, - "loss": 4.7224, + "epoch": 0.48, + "learning_rate": 0.00025439999999999995, + "loss": 4.8531, "step": 426 }, { - "epoch": 0.24, - "learning_rate": 0.0002538, - "loss": 6.0535, + "epoch": 0.48, + "learning_rate": 0.00025499999999999996, + "loss": 4.684, "step": 427 }, { - "epoch": 0.24, - "learning_rate": 0.00025439999999999995, - "loss": 6.2138, + "epoch": 0.48, + "learning_rate": 0.0002556, + "loss": 4.8392, "step": 428 }, { - "epoch": 0.24, - "learning_rate": 0.00025499999999999996, - "loss": 4.9605, + "epoch": 0.48, + "learning_rate": 0.0002562, + "loss": 5.0586, "step": 429 }, { - "epoch": 0.24, - "learning_rate": 0.0002556, - "loss": 4.7416, + "epoch": 0.48, + "learning_rate": 0.00025679999999999995, + "loss": 4.7774, "step": 430 }, { - "epoch": 0.24, - "learning_rate": 0.0002562, - "loss": 4.7265, + "epoch": 0.48, + "learning_rate": 0.00025739999999999997, + "loss": 4.9703, "step": 431 }, { - "epoch": 0.24, - "learning_rate": 0.00025679999999999995, - "loss": 4.7472, + "epoch": 0.48, + "learning_rate": 0.000258, + "loss": 5.1179, "step": 432 }, { - "epoch": 0.24, - "learning_rate": 0.00025739999999999997, - "loss": 4.6764, + "epoch": 0.49, + "learning_rate": 0.0002586, + "loss": 4.4454, "step": 433 }, { - "epoch": 0.24, - "learning_rate": 0.000258, - "loss": 4.8154, + "epoch": 0.49, + "learning_rate": 0.00025919999999999996, + "loss": 4.9024, "step": 434 }, { - "epoch": 0.24, - "learning_rate": 0.0002586, - "loss": 4.7714, + "epoch": 0.49, + "learning_rate": 0.00025979999999999997, + "loss": 4.6437, "step": 435 }, { - "epoch": 0.24, - "learning_rate": 0.00025919999999999996, - "loss": 4.6739, + "epoch": 0.49, + "learning_rate": 0.0002604, + "loss": 5.0195, "step": 436 }, { - "epoch": 0.24, - "learning_rate": 0.00025979999999999997, - "loss": 4.9073, + "epoch": 0.49, + "learning_rate": 0.000261, + "loss": 4.8932, "step": 437 }, { - "epoch": 0.25, - "learning_rate": 0.0002604, - "loss": 4.9831, + "epoch": 0.49, + "learning_rate": 0.00026159999999999996, + "loss": 4.7963, "step": 438 }, { - "epoch": 0.25, - "learning_rate": 0.000261, - "loss": 4.5282, + "epoch": 0.49, + "learning_rate": 0.0002622, + "loss": 4.9568, "step": 439 }, { - "epoch": 0.25, - "learning_rate": 0.00026159999999999996, - "loss": 4.8109, + "epoch": 0.49, + "learning_rate": 0.0002628, + "loss": 5.165, "step": 440 }, { - "epoch": 0.25, - "learning_rate": 0.0002622, - "loss": 5.5664, + "epoch": 0.49, + "learning_rate": 0.00026339999999999995, + "loss": 4.9899, "step": 441 }, { - "epoch": 0.25, - "learning_rate": 0.0002628, - "loss": 4.956, + "epoch": 0.5, + "learning_rate": 0.00026399999999999997, + "loss": 4.4689, "step": 442 }, { - "epoch": 0.25, - "learning_rate": 0.00026339999999999995, - "loss": 4.6528, + "epoch": 0.5, + "learning_rate": 0.0002646, + "loss": 4.7734, "step": 443 }, { - "epoch": 0.25, - "learning_rate": 0.00026399999999999997, - "loss": 5.2091, + "epoch": 0.5, + "learning_rate": 0.0002652, + "loss": 4.9954, "step": 444 }, { - "epoch": 0.25, - "learning_rate": 0.0002646, - "loss": 4.7121, + "epoch": 0.5, + "learning_rate": 0.00026579999999999996, + "loss": 4.7262, "step": 445 }, { - "epoch": 0.25, - "learning_rate": 0.0002652, - "loss": 8.2418, + "epoch": 0.5, + "learning_rate": 0.00026639999999999997, + "loss": 4.3192, "step": 446 }, { - "epoch": 0.25, - "learning_rate": 0.00026579999999999996, - "loss": 7.9474, + "epoch": 0.5, + "learning_rate": 0.000267, + "loss": 4.6139, "step": 447 }, { - "epoch": 0.25, - "learning_rate": 0.00026639999999999997, - "loss": 5.4328, + "epoch": 0.5, + "learning_rate": 0.0002676, + "loss": 5.2607, "step": 448 }, { - "epoch": 0.25, - "learning_rate": 0.000267, - "loss": 8.2889, + "epoch": 0.5, + "learning_rate": 0.00026819999999999996, + "loss": 5.7778, "step": 449 }, { - "epoch": 0.25, - "learning_rate": 0.0002676, - "loss": 4.8928, + "epoch": 0.5, + "learning_rate": 0.0002688, + "loss": 6.5607, "step": 450 }, { - "epoch": 0.25, - "learning_rate": 0.00026819999999999996, - "loss": 4.4413, + "epoch": 0.51, + "learning_rate": 0.0002694, + "loss": 5.1812, "step": 451 }, { - "epoch": 0.25, - "learning_rate": 0.0002688, - "loss": 4.9016, + "epoch": 0.51, + "learning_rate": 0.00027, + "loss": 5.031, "step": 452 }, { - "epoch": 0.25, - "learning_rate": 0.0002694, - "loss": 5.7164, + "epoch": 0.51, + "learning_rate": 0.00027059999999999996, + "loss": 5.1089, "step": 453 }, { - "epoch": 0.25, - "learning_rate": 0.00027, - "loss": 4.5628, + "epoch": 0.51, + "learning_rate": 0.0002712, + "loss": 4.565, "step": 454 }, { - "epoch": 0.26, - "learning_rate": 0.00027059999999999996, - "loss": 4.5877, + "epoch": 0.51, + "learning_rate": 0.0002718, + "loss": 5.0395, "step": 455 }, { - "epoch": 0.26, - "learning_rate": 0.0002712, - "loss": 4.6684, + "epoch": 0.51, + "learning_rate": 0.0002724, + "loss": 4.711, "step": 456 }, { - "epoch": 0.26, - "learning_rate": 0.0002718, - "loss": 4.8451, + "epoch": 0.51, + "learning_rate": 0.00027299999999999997, + "loss": 5.1613, "step": 457 }, { - "epoch": 0.26, - "learning_rate": 0.0002724, - "loss": 4.5488, + "epoch": 0.51, + "learning_rate": 0.0002736, + "loss": 4.7766, "step": 458 }, { - "epoch": 0.26, - "learning_rate": 0.00027299999999999997, - "loss": 4.6508, + "epoch": 0.51, + "learning_rate": 0.0002742, + "loss": 4.7893, "step": 459 }, { - "epoch": 0.26, - "learning_rate": 0.0002736, - "loss": 5.476, + "epoch": 0.52, + "learning_rate": 0.0002748, + "loss": 4.9041, "step": 460 }, { - "epoch": 0.26, - "learning_rate": 0.0002742, - "loss": 5.3327, + "epoch": 0.52, + "learning_rate": 0.00027539999999999997, + "loss": 4.5892, "step": 461 }, { - "epoch": 0.26, - "learning_rate": 0.0002748, - "loss": 4.8982, + "epoch": 0.52, + "learning_rate": 0.000276, + "loss": 4.9282, "step": 462 }, { - "epoch": 0.26, - "learning_rate": 0.00027539999999999997, - "loss": 4.9985, + "epoch": 0.52, + "learning_rate": 0.0002766, + "loss": 4.9861, "step": 463 }, { - "epoch": 0.26, - "learning_rate": 0.000276, - "loss": 4.5718, + "epoch": 0.52, + "learning_rate": 0.0002772, + "loss": 4.3995, "step": 464 }, { - "epoch": 0.26, - "learning_rate": 0.0002766, - "loss": 4.5092, + "epoch": 0.52, + "learning_rate": 0.0002778, + "loss": 4.5684, "step": 465 }, { - "epoch": 0.26, - "learning_rate": 0.0002772, - "loss": 4.9586, + "epoch": 0.52, + "learning_rate": 0.0002784, + "loss": 5.0256, "step": 466 }, { - "epoch": 0.26, - "learning_rate": 0.0002778, - "loss": 4.8314, + "epoch": 0.52, + "learning_rate": 0.000279, + "loss": 4.7077, "step": 467 }, { - "epoch": 0.26, - "learning_rate": 0.0002784, - "loss": 4.8822, + "epoch": 0.52, + "learning_rate": 0.00027959999999999997, + "loss": 4.6122, "step": 468 }, { - "epoch": 0.26, - "learning_rate": 0.000279, - "loss": 4.8299, + "epoch": 0.53, + "learning_rate": 0.0002802, + "loss": 4.9348, "step": 469 }, { - "epoch": 0.26, - "learning_rate": 0.00027959999999999997, - "loss": 4.9152, + "epoch": 0.53, + "learning_rate": 0.0002808, + "loss": 4.5782, "step": 470 }, { - "epoch": 0.26, - "learning_rate": 0.0002802, - "loss": 5.2663, + "epoch": 0.53, + "learning_rate": 0.00028139999999999996, + "loss": 4.492, "step": 471 }, { - "epoch": 0.26, - "learning_rate": 0.0002808, - "loss": 5.0269, + "epoch": 0.53, + "learning_rate": 0.00028199999999999997, + "loss": 4.6235, "step": 472 }, { - "epoch": 0.27, - "learning_rate": 0.00028139999999999996, - "loss": 4.7528, + "epoch": 0.53, + "learning_rate": 0.0002826, + "loss": 6.0461, "step": 473 }, { - "epoch": 0.27, - "learning_rate": 0.00028199999999999997, - "loss": 5.4397, + "epoch": 0.53, + "learning_rate": 0.00028319999999999994, + "loss": 4.8847, "step": 474 }, { - "epoch": 0.27, - "learning_rate": 0.0002826, - "loss": 4.7406, + "epoch": 0.53, + "learning_rate": 0.00028379999999999996, + "loss": 4.8343, "step": 475 }, { - "epoch": 0.27, - "learning_rate": 0.00028319999999999994, - "loss": 5.0112, + "epoch": 0.53, + "learning_rate": 0.0002844, + "loss": 5.1263, "step": 476 }, { - "epoch": 0.27, - "learning_rate": 0.00028379999999999996, - "loss": 5.1672, + "epoch": 0.53, + "learning_rate": 0.000285, + "loss": 5.1252, "step": 477 }, { - "epoch": 0.27, - "learning_rate": 0.0002844, - "loss": 4.7126, + "epoch": 0.54, + "learning_rate": 0.00028559999999999995, + "loss": 4.7088, "step": 478 }, { - "epoch": 0.27, - "learning_rate": 0.000285, - "loss": 5.3694, + "epoch": 0.54, + "learning_rate": 0.00028619999999999996, + "loss": 4.519, "step": 479 }, { - "epoch": 0.27, - "learning_rate": 0.00028559999999999995, - "loss": 6.1383, + "epoch": 0.54, + "learning_rate": 0.0002868, + "loss": 4.7786, "step": 480 }, { - "epoch": 0.27, - "learning_rate": 0.00028619999999999996, - "loss": 4.9536, + "epoch": 0.54, + "learning_rate": 0.00028739999999999994, + "loss": 4.6808, "step": 481 }, { - "epoch": 0.27, - "learning_rate": 0.0002868, - "loss": 6.0078, + "epoch": 0.54, + "learning_rate": 0.00028799999999999995, + "loss": 4.6608, "step": 482 }, { - "epoch": 0.27, - "learning_rate": 0.00028739999999999994, - "loss": 5.4143, + "epoch": 0.54, + "learning_rate": 0.00028859999999999997, + "loss": 4.6107, "step": 483 }, { - "epoch": 0.27, - "learning_rate": 0.00028799999999999995, - "loss": 5.0113, + "epoch": 0.54, + "learning_rate": 0.0002892, + "loss": 4.8761, "step": 484 }, { - "epoch": 0.27, - "learning_rate": 0.00028859999999999997, - "loss": 5.2095, + "epoch": 0.54, + "learning_rate": 0.00028979999999999994, + "loss": 4.8144, "step": 485 }, { - "epoch": 0.27, - "learning_rate": 0.0002892, - "loss": 5.9215, + "epoch": 0.54, + "learning_rate": 0.00029039999999999996, + "loss": 4.587, "step": 486 }, { - "epoch": 0.27, - "learning_rate": 0.00028979999999999994, - "loss": 4.9041, + "epoch": 0.55, + "learning_rate": 0.00029099999999999997, + "loss": 4.7896, "step": 487 }, { - "epoch": 0.27, - "learning_rate": 0.00029039999999999996, - "loss": 5.1816, + "epoch": 0.55, + "learning_rate": 0.0002916, + "loss": 4.4324, "step": 488 }, { - "epoch": 0.27, - "learning_rate": 0.00029099999999999997, - "loss": 5.742, + "epoch": 0.55, + "learning_rate": 0.00029219999999999995, + "loss": 4.9277, "step": 489 }, { - "epoch": 0.27, - "learning_rate": 0.0002916, - "loss": 4.9566, + "epoch": 0.55, + "learning_rate": 0.00029279999999999996, + "loss": 4.734, "step": 490 }, { - "epoch": 0.28, - "learning_rate": 0.00029219999999999995, - "loss": 5.0792, + "epoch": 0.55, + "learning_rate": 0.0002934, + "loss": 4.4104, "step": 491 }, { - "epoch": 0.28, - "learning_rate": 0.00029279999999999996, - "loss": 5.49, + "epoch": 0.55, + "learning_rate": 0.000294, + "loss": 4.9825, "step": 492 }, { - "epoch": 0.28, - "learning_rate": 0.0002934, - "loss": 4.9835, + "epoch": 0.55, + "learning_rate": 0.00029459999999999995, + "loss": 5.4558, "step": 493 }, { - "epoch": 0.28, - "learning_rate": 0.000294, - "loss": 5.5644, + "epoch": 0.55, + "learning_rate": 0.00029519999999999997, + "loss": 4.5947, "step": 494 }, { - "epoch": 0.28, - "learning_rate": 0.00029459999999999995, - "loss": 5.0931, + "epoch": 0.55, + "learning_rate": 0.0002958, + "loss": 5.2108, "step": 495 }, { - "epoch": 0.28, - "learning_rate": 0.00029519999999999997, - "loss": 5.0932, + "epoch": 0.56, + "learning_rate": 0.0002964, + "loss": 4.7311, "step": 496 }, { - "epoch": 0.28, - "learning_rate": 0.0002958, - "loss": 5.0974, + "epoch": 0.56, + "learning_rate": 0.00029699999999999996, + "loss": 4.2711, "step": 497 }, { - "epoch": 0.28, - "learning_rate": 0.0002964, - "loss": 7.747, + "epoch": 0.56, + "learning_rate": 0.00029759999999999997, + "loss": 5.0972, "step": 498 }, { - "epoch": 0.28, - "learning_rate": 0.00029699999999999996, - "loss": 5.264, + "epoch": 0.56, + "learning_rate": 0.0002982, + "loss": 4.9771, "step": 499 }, { - "epoch": 0.28, - "learning_rate": 0.00029759999999999997, - "loss": 4.6975, + "epoch": 0.56, + "learning_rate": 0.0002988, + "loss": 4.4548, "step": 500 }, { - "epoch": 0.28, - "eval_loss": 5.36206579208374, - "eval_runtime": 955.9194, - "eval_samples_per_second": 2.764, - "eval_steps_per_second": 0.346, - "eval_wer": 1.9585878619595398, + "epoch": 0.56, + "eval_loss": 5.143069744110107, + "eval_runtime": 936.1477, + "eval_samples_per_second": 2.822, + "eval_steps_per_second": 0.354, + "eval_wer": 1.9922848076160253, "step": 500 }, { - "epoch": 0.28, - "learning_rate": 0.0002982, - "loss": 5.234, + "epoch": 0.56, + "learning_rate": 0.00029939999999999996, + "loss": 5.4289, "step": 501 }, { - "epoch": 0.28, - "learning_rate": 0.0002988, - "loss": 5.0553, + "epoch": 0.56, + "learning_rate": 0.0003, + "loss": 4.5335, "step": 502 }, { - "epoch": 0.28, - "learning_rate": 0.00029939999999999996, - "loss": 5.4419, + "epoch": 0.56, + "learning_rate": 0.000299234693877551, + "loss": 4.9574, "step": 503 }, { - "epoch": 0.28, - "learning_rate": 0.0003, - "loss": 4.9003, + "epoch": 0.57, + "learning_rate": 0.00029846938775510205, + "loss": 5.1802, "step": 504 }, { - "epoch": 0.28, - "learning_rate": 0.0002997663551401869, - "loss": 5.9319, + "epoch": 0.57, + "learning_rate": 0.00029770408163265304, + "loss": 5.0481, "step": 505 }, { - "epoch": 0.28, - "learning_rate": 0.00029953271028037383, - "loss": 5.2144, + "epoch": 0.57, + "learning_rate": 0.0002969387755102041, + "loss": 4.7687, "step": 506 }, { - "epoch": 0.28, - "learning_rate": 0.00029929906542056073, - "loss": 4.9505, + "epoch": 0.57, + "learning_rate": 0.00029617346938775506, + "loss": 5.1309, "step": 507 }, { - "epoch": 0.28, - "learning_rate": 0.00029906542056074763, - "loss": 4.8884, + "epoch": 0.57, + "learning_rate": 0.0002954081632653061, + "loss": 5.1812, "step": 508 }, { - "epoch": 0.29, - "learning_rate": 0.0002988317757009346, - "loss": 5.7785, + "epoch": 0.57, + "learning_rate": 0.0002946428571428571, + "loss": 5.1551, "step": 509 }, { - "epoch": 0.29, - "learning_rate": 0.0002985981308411215, - "loss": 5.3499, + "epoch": 0.57, + "learning_rate": 0.0002938775510204081, + "loss": 5.0555, "step": 510 }, { - "epoch": 0.29, - "learning_rate": 0.0002983644859813084, - "loss": 5.1846, + "epoch": 0.57, + "learning_rate": 0.00029311224489795917, + "loss": 4.8552, "step": 511 }, { - "epoch": 0.29, - "learning_rate": 0.0002981308411214953, - "loss": 5.1604, + "epoch": 0.57, + "learning_rate": 0.0002923469387755102, + "loss": 4.909, "step": 512 }, { - "epoch": 0.29, - "learning_rate": 0.00029789719626168224, - "loss": 5.2411, + "epoch": 0.58, + "learning_rate": 0.0002915816326530612, + "loss": 5.4875, "step": 513 }, { - "epoch": 0.29, - "learning_rate": 0.00029766355140186914, - "loss": 4.5981, + "epoch": 0.58, + "learning_rate": 0.00029081632653061223, + "loss": 5.1756, "step": 514 }, { - "epoch": 0.29, - "learning_rate": 0.00029742990654205604, - "loss": 4.6763, + "epoch": 0.58, + "learning_rate": 0.0002900510204081632, + "loss": 4.9279, "step": 515 }, { - "epoch": 0.29, - "learning_rate": 0.00029719626168224294, - "loss": 5.7062, + "epoch": 0.58, + "learning_rate": 0.00028928571428571425, + "loss": 4.7192, "step": 516 }, { - "epoch": 0.29, - "learning_rate": 0.0002969626168224299, - "loss": 4.9783, + "epoch": 0.58, + "learning_rate": 0.0002885204081632653, + "loss": 4.8411, "step": 517 }, { - "epoch": 0.29, - "learning_rate": 0.0002967289719626168, - "loss": 5.6825, + "epoch": 0.58, + "learning_rate": 0.0002877551020408163, + "loss": 4.8069, "step": 518 }, { - "epoch": 0.29, - "learning_rate": 0.0002964953271028037, - "loss": 4.8631, + "epoch": 0.58, + "learning_rate": 0.0002869897959183673, + "loss": 5.3111, "step": 519 }, { - "epoch": 0.29, - "learning_rate": 0.00029626168224299065, - "loss": 4.8226, + "epoch": 0.58, + "learning_rate": 0.00028622448979591836, + "loss": 4.9504, "step": 520 }, { - "epoch": 0.29, - "learning_rate": 0.00029602803738317755, - "loss": 4.4902, + "epoch": 0.58, + "learning_rate": 0.0002854591836734694, + "loss": 4.7647, "step": 521 }, { - "epoch": 0.29, - "learning_rate": 0.0002957943925233645, - "loss": 4.7859, + "epoch": 0.59, + "learning_rate": 0.0002846938775510204, + "loss": 4.6403, "step": 522 }, { - "epoch": 0.29, - "learning_rate": 0.00029556074766355135, - "loss": 5.0049, + "epoch": 0.59, + "learning_rate": 0.00028392857142857137, + "loss": 5.0066, "step": 523 }, { - "epoch": 0.29, - "learning_rate": 0.0002953271028037383, - "loss": 4.9996, + "epoch": 0.59, + "learning_rate": 0.0002831632653061224, + "loss": 4.6506, "step": 524 }, { - "epoch": 0.29, - "learning_rate": 0.0002950934579439252, - "loss": 6.3883, + "epoch": 0.59, + "learning_rate": 0.00028239795918367345, + "loss": 5.4097, "step": 525 }, { - "epoch": 0.29, - "learning_rate": 0.00029485981308411215, - "loss": 5.216, + "epoch": 0.59, + "learning_rate": 0.0002816326530612245, + "loss": 4.9555, "step": 526 }, { - "epoch": 0.3, - "learning_rate": 0.00029462616822429905, - "loss": 5.5867, + "epoch": 0.59, + "learning_rate": 0.00028086734693877547, + "loss": 4.9541, "step": 527 }, { - "epoch": 0.3, - "learning_rate": 0.00029439252336448596, - "loss": 4.5898, + "epoch": 0.59, + "learning_rate": 0.0002801020408163265, + "loss": 4.9159, "step": 528 }, { - "epoch": 0.3, - "learning_rate": 0.00029415887850467286, - "loss": 5.0142, + "epoch": 0.59, + "learning_rate": 0.00027933673469387755, + "loss": 4.8878, "step": 529 }, { - "epoch": 0.3, - "learning_rate": 0.0002939252336448598, - "loss": 6.5835, + "epoch": 0.59, + "learning_rate": 0.00027857142857142854, + "loss": 5.0741, "step": 530 }, { - "epoch": 0.3, - "learning_rate": 0.0002936915887850467, - "loss": 4.7601, + "epoch": 0.6, + "learning_rate": 0.0002778061224489796, + "loss": 5.0853, "step": 531 }, { - "epoch": 0.3, - "learning_rate": 0.0002934579439252336, - "loss": 4.6357, + "epoch": 0.6, + "learning_rate": 0.00027704081632653056, + "loss": 4.572, "step": 532 }, { - "epoch": 0.3, - "learning_rate": 0.00029322429906542056, - "loss": 5.1137, + "epoch": 0.6, + "learning_rate": 0.0002762755102040816, + "loss": 4.6755, "step": 533 }, { - "epoch": 0.3, - "learning_rate": 0.00029299065420560746, - "loss": 4.5619, + "epoch": 0.6, + "learning_rate": 0.00027551020408163264, + "loss": 4.5139, "step": 534 }, { - "epoch": 0.3, - "learning_rate": 0.00029275700934579436, - "loss": 5.2228, + "epoch": 0.6, + "learning_rate": 0.0002747448979591837, + "loss": 4.8561, "step": 535 }, { - "epoch": 0.3, - "learning_rate": 0.00029252336448598126, - "loss": 4.8179, + "epoch": 0.6, + "learning_rate": 0.00027397959183673466, + "loss": 5.2083, "step": 536 }, { - "epoch": 0.3, - "learning_rate": 0.0002922897196261682, - "loss": 4.8649, + "epoch": 0.6, + "learning_rate": 0.0002732142857142857, + "loss": 4.9467, "step": 537 }, { - "epoch": 0.3, - "learning_rate": 0.0002920560747663551, - "loss": 5.2219, + "epoch": 0.6, + "learning_rate": 0.0002724489795918367, + "loss": 4.9502, "step": 538 }, { - "epoch": 0.3, - "learning_rate": 0.000291822429906542, - "loss": 5.2631, + "epoch": 0.6, + "learning_rate": 0.00027168367346938773, + "loss": 4.6417, "step": 539 }, { - "epoch": 0.3, - "learning_rate": 0.0002915887850467289, - "loss": 4.9496, + "epoch": 0.61, + "learning_rate": 0.0002709183673469387, + "loss": 5.0591, "step": 540 }, { - "epoch": 0.3, - "learning_rate": 0.00029135514018691587, - "loss": 5.2277, + "epoch": 0.61, + "learning_rate": 0.00027015306122448975, + "loss": 4.9864, "step": 541 }, { - "epoch": 0.3, - "learning_rate": 0.0002911214953271028, - "loss": 5.0561, + "epoch": 0.61, + "learning_rate": 0.0002693877551020408, + "loss": 4.7817, "step": 542 }, { - "epoch": 0.3, - "learning_rate": 0.0002908878504672897, - "loss": 6.3632, + "epoch": 0.61, + "learning_rate": 0.00026862244897959183, + "loss": 4.9888, "step": 543 }, { - "epoch": 0.3, - "learning_rate": 0.00029065420560747663, - "loss": 4.7369, + "epoch": 0.61, + "learning_rate": 0.00026785714285714287, + "loss": 5.5872, "step": 544 }, { - "epoch": 0.31, - "learning_rate": 0.00029042056074766353, - "loss": 4.5289, + "epoch": 0.61, + "learning_rate": 0.00026709183673469386, + "loss": 5.6725, "step": 545 }, { - "epoch": 0.31, - "learning_rate": 0.0002901869158878505, - "loss": 6.4188, + "epoch": 0.61, + "learning_rate": 0.0002663265306122449, + "loss": 5.0365, "step": 546 }, { - "epoch": 0.31, - "learning_rate": 0.00028995327102803733, - "loss": 5.8594, + "epoch": 0.61, + "learning_rate": 0.0002655612244897959, + "loss": 5.4094, "step": 547 }, { - "epoch": 0.31, - "learning_rate": 0.0002897196261682243, - "loss": 6.4309, + "epoch": 0.61, + "learning_rate": 0.0002647959183673469, + "loss": 5.0726, "step": 548 }, { - "epoch": 0.31, - "learning_rate": 0.0002894859813084112, - "loss": 5.3478, + "epoch": 0.62, + "learning_rate": 0.0002640306122448979, + "loss": 4.5608, "step": 549 }, { - "epoch": 0.31, - "learning_rate": 0.00028925233644859814, - "loss": 4.9924, + "epoch": 0.62, + "learning_rate": 0.00026326530612244894, + "loss": 5.6574, "step": 550 }, { - "epoch": 0.31, - "learning_rate": 0.00028901869158878504, - "loss": 5.3905, + "epoch": 0.62, + "learning_rate": 0.0002625, + "loss": 4.9341, "step": 551 }, { - "epoch": 0.31, - "learning_rate": 0.00028878504672897194, - "loss": 6.1307, + "epoch": 0.62, + "learning_rate": 0.000261734693877551, + "loss": 5.1029, "step": 552 }, { - "epoch": 0.31, - "learning_rate": 0.00028855140186915884, - "loss": 6.4807, + "epoch": 0.62, + "learning_rate": 0.000260969387755102, + "loss": 4.759, "step": 553 }, { - "epoch": 0.31, - "learning_rate": 0.0002883177570093458, - "loss": 4.9175, + "epoch": 0.62, + "learning_rate": 0.00026020408163265305, + "loss": 4.5206, "step": 554 }, { - "epoch": 0.31, - "learning_rate": 0.0002880841121495327, - "loss": 4.8074, + "epoch": 0.62, + "learning_rate": 0.00025943877551020403, + "loss": 4.5575, "step": 555 }, { - "epoch": 0.31, - "learning_rate": 0.0002878504672897196, - "loss": 5.5366, + "epoch": 0.62, + "learning_rate": 0.00025867346938775507, + "loss": 4.9083, "step": 556 }, { - "epoch": 0.31, - "learning_rate": 0.00028761682242990655, - "loss": 5.5351, + "epoch": 0.62, + "learning_rate": 0.0002579081632653061, + "loss": 4.6324, "step": 557 }, { - "epoch": 0.31, - "learning_rate": 0.00028738317757009345, - "loss": 4.978, + "epoch": 0.63, + "learning_rate": 0.0002571428571428571, + "loss": 4.5767, "step": 558 }, { - "epoch": 0.31, - "learning_rate": 0.00028714953271028035, - "loss": 4.8939, + "epoch": 0.63, + "learning_rate": 0.00025637755102040814, + "loss": 4.5067, "step": 559 }, { - "epoch": 0.31, - "learning_rate": 0.00028691588785046725, - "loss": 5.0922, + "epoch": 0.63, + "learning_rate": 0.0002556122448979592, + "loss": 5.0567, "step": 560 }, { - "epoch": 0.31, - "learning_rate": 0.0002866822429906542, - "loss": 5.2023, + "epoch": 0.63, + "learning_rate": 0.0002548469387755102, + "loss": 4.9046, "step": 561 }, { - "epoch": 0.32, - "learning_rate": 0.0002864485981308411, - "loss": 5.2508, + "epoch": 0.63, + "learning_rate": 0.0002540816326530612, + "loss": 4.7074, "step": 562 }, { - "epoch": 0.32, - "learning_rate": 0.000286214953271028, - "loss": 4.6636, + "epoch": 0.63, + "learning_rate": 0.0002533163265306122, + "loss": 4.8394, "step": 563 }, { - "epoch": 0.32, - "learning_rate": 0.0002859813084112149, - "loss": 5.1418, + "epoch": 0.63, + "learning_rate": 0.0002525510204081632, + "loss": 4.9009, "step": 564 }, { - "epoch": 0.32, - "learning_rate": 0.00028574766355140185, - "loss": 5.9888, + "epoch": 0.63, + "learning_rate": 0.00025178571428571426, + "loss": 4.7557, "step": 565 }, { - "epoch": 0.32, - "learning_rate": 0.00028551401869158875, - "loss": 4.7364, + "epoch": 0.63, + "learning_rate": 0.0002510204081632653, + "loss": 4.6785, "step": 566 }, { - "epoch": 0.32, - "learning_rate": 0.00028528037383177565, - "loss": 4.7401, + "epoch": 0.64, + "learning_rate": 0.0002502551020408163, + "loss": 4.7509, "step": 567 }, { - "epoch": 0.32, - "learning_rate": 0.0002850467289719626, - "loss": 5.0348, + "epoch": 0.64, + "learning_rate": 0.00024948979591836733, + "loss": 4.5759, "step": 568 }, { - "epoch": 0.32, - "learning_rate": 0.0002848130841121495, - "loss": 4.7841, + "epoch": 0.64, + "learning_rate": 0.00024872448979591837, + "loss": 4.5382, "step": 569 }, { - "epoch": 0.32, - "learning_rate": 0.00028457943925233646, - "loss": 5.2597, + "epoch": 0.64, + "learning_rate": 0.00024795918367346935, + "loss": 4.8662, "step": 570 }, { - "epoch": 0.32, - "learning_rate": 0.0002843457943925233, - "loss": 4.7545, + "epoch": 0.64, + "learning_rate": 0.0002471938775510204, + "loss": 4.7793, "step": 571 }, { - "epoch": 0.32, - "learning_rate": 0.00028411214953271026, - "loss": 5.0025, + "epoch": 0.64, + "learning_rate": 0.0002464285714285714, + "loss": 4.6157, "step": 572 }, { - "epoch": 0.32, - "learning_rate": 0.00028387850467289716, - "loss": 6.9179, + "epoch": 0.64, + "learning_rate": 0.0002456632653061224, + "loss": 4.56, "step": 573 }, { - "epoch": 0.32, - "learning_rate": 0.0002836448598130841, - "loss": 4.9346, + "epoch": 0.64, + "learning_rate": 0.00024489795918367346, + "loss": 4.6583, "step": 574 }, { - "epoch": 0.32, - "learning_rate": 0.000283411214953271, - "loss": 4.6494, + "epoch": 0.64, + "learning_rate": 0.00024413265306122447, + "loss": 4.9936, "step": 575 }, { - "epoch": 0.32, - "learning_rate": 0.0002831775700934579, - "loss": 4.7804, + "epoch": 0.65, + "learning_rate": 0.00024336734693877548, + "loss": 4.7007, "step": 576 }, { - "epoch": 0.32, - "learning_rate": 0.0002829439252336448, - "loss": 5.0705, + "epoch": 0.65, + "learning_rate": 0.0002426020408163265, + "loss": 4.6896, "step": 577 }, { - "epoch": 0.32, - "learning_rate": 0.00028271028037383177, - "loss": 4.968, + "epoch": 0.65, + "learning_rate": 0.00024183673469387753, + "loss": 4.8833, "step": 578 }, { - "epoch": 0.32, - "learning_rate": 0.00028247663551401867, - "loss": 4.9716, + "epoch": 0.65, + "learning_rate": 0.00024107142857142857, + "loss": 4.2799, "step": 579 }, { - "epoch": 0.33, - "learning_rate": 0.00028224299065420557, - "loss": 5.7594, + "epoch": 0.65, + "learning_rate": 0.00024030612244897956, + "loss": 5.2556, "step": 580 }, { - "epoch": 0.33, - "learning_rate": 0.0002820093457943925, - "loss": 4.8463, + "epoch": 0.65, + "learning_rate": 0.00023954081632653057, + "loss": 4.6452, "step": 581 }, { - "epoch": 0.33, - "learning_rate": 0.0002817757009345794, - "loss": 5.5102, + "epoch": 0.65, + "learning_rate": 0.0002387755102040816, + "loss": 4.9398, "step": 582 }, { - "epoch": 0.33, - "learning_rate": 0.0002815420560747663, - "loss": 4.946, + "epoch": 0.65, + "learning_rate": 0.00023801020408163265, + "loss": 5.2117, "step": 583 }, { - "epoch": 0.33, - "learning_rate": 0.0002813084112149532, - "loss": 5.2296, + "epoch": 0.65, + "learning_rate": 0.00023724489795918366, + "loss": 4.6235, "step": 584 }, { - "epoch": 0.33, - "learning_rate": 0.0002810747663551402, - "loss": 5.8994, + "epoch": 0.66, + "learning_rate": 0.00023647959183673467, + "loss": 5.0091, "step": 585 }, { - "epoch": 0.33, - "learning_rate": 0.0002808411214953271, - "loss": 4.8968, + "epoch": 0.66, + "learning_rate": 0.00023571428571428569, + "loss": 4.8234, "step": 586 }, { - "epoch": 0.33, - "learning_rate": 0.000280607476635514, - "loss": 5.8706, + "epoch": 0.66, + "learning_rate": 0.00023494897959183673, + "loss": 5.1262, "step": 587 }, { - "epoch": 0.33, - "learning_rate": 0.0002803738317757009, - "loss": 4.8684, + "epoch": 0.66, + "learning_rate": 0.00023418367346938774, + "loss": 4.6342, "step": 588 }, { - "epoch": 0.33, - "learning_rate": 0.00028014018691588784, - "loss": 5.7679, + "epoch": 0.66, + "learning_rate": 0.00023341836734693875, + "loss": 4.6927, "step": 589 }, { - "epoch": 0.33, - "learning_rate": 0.00027990654205607474, - "loss": 5.1306, + "epoch": 0.66, + "learning_rate": 0.00023265306122448976, + "loss": 4.845, "step": 590 }, { - "epoch": 0.33, - "learning_rate": 0.00027967289719626164, - "loss": 4.8464, + "epoch": 0.66, + "learning_rate": 0.0002318877551020408, + "loss": 4.5989, "step": 591 }, { - "epoch": 0.33, - "learning_rate": 0.0002794392523364486, - "loss": 5.3824, + "epoch": 0.66, + "learning_rate": 0.00023112244897959181, + "loss": 4.9955, "step": 592 }, { - "epoch": 0.33, - "learning_rate": 0.0002792056074766355, - "loss": 5.3421, + "epoch": 0.66, + "learning_rate": 0.00023035714285714285, + "loss": 5.0505, "step": 593 }, { - "epoch": 0.33, - "learning_rate": 0.00027897196261682244, - "loss": 5.1075, + "epoch": 0.67, + "learning_rate": 0.00022959183673469384, + "loss": 4.5788, "step": 594 }, { - "epoch": 0.33, - "learning_rate": 0.0002787383177570093, - "loss": 4.8415, + "epoch": 0.67, + "learning_rate": 0.00022882653061224488, + "loss": 5.231, "step": 595 }, { - "epoch": 0.33, - "learning_rate": 0.00027850467289719624, - "loss": 5.016, + "epoch": 0.67, + "learning_rate": 0.0002280612244897959, + "loss": 4.7032, "step": 596 }, { - "epoch": 0.33, - "learning_rate": 0.00027827102803738314, - "loss": 7.5516, + "epoch": 0.67, + "learning_rate": 0.00022729591836734693, + "loss": 4.8108, "step": 597 }, { - "epoch": 0.34, - "learning_rate": 0.0002780373831775701, - "loss": 7.2357, + "epoch": 0.67, + "learning_rate": 0.00022653061224489791, + "loss": 4.9854, "step": 598 }, { - "epoch": 0.34, - "learning_rate": 0.000277803738317757, - "loss": 5.1243, + "epoch": 0.67, + "learning_rate": 0.00022576530612244895, + "loss": 5.7071, "step": 599 }, { - "epoch": 0.34, - "learning_rate": 0.0002775700934579439, - "loss": 5.3606, + "epoch": 0.67, + "learning_rate": 0.000225, + "loss": 4.4493, "step": 600 }, { - "epoch": 0.34, - "learning_rate": 0.0002773364485981308, - "loss": 4.7568, + "epoch": 0.67, + "learning_rate": 0.000224234693877551, + "loss": 4.8242, "step": 601 }, { - "epoch": 0.34, - "learning_rate": 0.00027710280373831775, - "loss": 5.1812, + "epoch": 0.67, + "learning_rate": 0.00022346938775510205, + "loss": 4.5986, "step": 602 }, { - "epoch": 0.34, - "learning_rate": 0.00027686915887850465, - "loss": 4.7293, + "epoch": 0.68, + "learning_rate": 0.00022270408163265303, + "loss": 4.9151, "step": 603 }, { - "epoch": 0.34, - "learning_rate": 0.00027663551401869155, - "loss": 4.8121, + "epoch": 0.68, + "learning_rate": 0.00022193877551020407, + "loss": 4.845, "step": 604 }, { - "epoch": 0.34, - "learning_rate": 0.0002764018691588785, - "loss": 5.1333, + "epoch": 0.68, + "learning_rate": 0.00022117346938775508, + "loss": 4.6539, "step": 605 }, { - "epoch": 0.34, - "learning_rate": 0.0002761682242990654, - "loss": 4.6236, + "epoch": 0.68, + "learning_rate": 0.00022040816326530612, + "loss": 4.8174, "step": 606 }, { - "epoch": 0.34, - "learning_rate": 0.0002759345794392523, - "loss": 6.4633, + "epoch": 0.68, + "learning_rate": 0.0002196428571428571, + "loss": 4.932, "step": 607 }, { - "epoch": 0.34, - "learning_rate": 0.0002757009345794392, - "loss": 5.1159, + "epoch": 0.68, + "learning_rate": 0.00021887755102040815, + "loss": 4.6845, "step": 608 }, { - "epoch": 0.34, - "learning_rate": 0.00027546728971962616, - "loss": 5.6834, + "epoch": 0.68, + "learning_rate": 0.00021811224489795916, + "loss": 4.6099, "step": 609 }, { - "epoch": 0.34, - "learning_rate": 0.00027523364485981306, - "loss": 5.0198, + "epoch": 0.68, + "learning_rate": 0.0002173469387755102, + "loss": 4.7819, "step": 610 }, { - "epoch": 0.34, - "learning_rate": 0.00027499999999999996, - "loss": 5.7727, + "epoch": 0.68, + "learning_rate": 0.0002165816326530612, + "loss": 4.7864, "step": 611 }, { - "epoch": 0.34, - "learning_rate": 0.00027476635514018686, - "loss": 4.7997, + "epoch": 0.69, + "learning_rate": 0.00021581632653061222, + "loss": 4.8726, "step": 612 }, { - "epoch": 0.34, - "learning_rate": 0.0002745327102803738, - "loss": 4.9228, + "epoch": 0.69, + "learning_rate": 0.00021505102040816324, + "loss": 4.8126, "step": 613 }, { - "epoch": 0.34, - "learning_rate": 0.0002742990654205607, - "loss": 5.3284, + "epoch": 0.69, + "learning_rate": 0.00021428571428571427, + "loss": 4.8606, "step": 614 }, { - "epoch": 0.34, - "learning_rate": 0.0002740654205607476, - "loss": 5.0978, + "epoch": 0.69, + "learning_rate": 0.0002135204081632653, + "loss": 4.7156, "step": 615 }, { - "epoch": 0.35, - "learning_rate": 0.00027383177570093457, - "loss": 4.8642, + "epoch": 0.69, + "learning_rate": 0.0002127551020408163, + "loss": 4.6851, "step": 616 }, { - "epoch": 0.35, - "learning_rate": 0.00027359813084112147, - "loss": 5.3107, + "epoch": 0.69, + "learning_rate": 0.0002119897959183673, + "loss": 4.6363, "step": 617 }, { - "epoch": 0.35, - "learning_rate": 0.0002733644859813084, - "loss": 4.7842, + "epoch": 0.69, + "learning_rate": 0.00021122448979591835, + "loss": 4.4001, "step": 618 }, { - "epoch": 0.35, - "learning_rate": 0.00027313084112149527, - "loss": 5.0604, + "epoch": 0.69, + "learning_rate": 0.0002104591836734694, + "loss": 4.5045, "step": 619 }, { - "epoch": 0.35, - "learning_rate": 0.0002728971962616822, - "loss": 5.8362, + "epoch": 0.7, + "learning_rate": 0.0002096938775510204, + "loss": 4.5599, "step": 620 }, { - "epoch": 0.35, - "learning_rate": 0.0002726635514018691, - "loss": 5.2535, + "epoch": 0.7, + "learning_rate": 0.0002089285714285714, + "loss": 4.7667, "step": 621 }, { - "epoch": 0.35, - "learning_rate": 0.0002724299065420561, - "loss": 5.1767, + "epoch": 0.7, + "learning_rate": 0.00020816326530612243, + "loss": 4.6612, "step": 622 }, { - "epoch": 0.35, - "learning_rate": 0.000272196261682243, - "loss": 4.9363, + "epoch": 0.7, + "learning_rate": 0.00020739795918367347, + "loss": 4.6999, "step": 623 }, { - "epoch": 0.35, - "learning_rate": 0.0002719626168224299, - "loss": 5.9812, + "epoch": 0.7, + "learning_rate": 0.00020663265306122448, + "loss": 4.6427, "step": 624 }, { - "epoch": 0.35, - "learning_rate": 0.0002717289719626168, - "loss": 4.9427, + "epoch": 0.7, + "learning_rate": 0.0002058673469387755, + "loss": 4.9789, "step": 625 }, { - "epoch": 0.35, - "learning_rate": 0.00027149532710280373, - "loss": 4.7792, + "epoch": 0.7, + "learning_rate": 0.0002051020408163265, + "loss": 4.7343, "step": 626 }, { - "epoch": 0.35, - "learning_rate": 0.00027126168224299063, - "loss": 4.7056, + "epoch": 0.7, + "learning_rate": 0.00020433673469387754, + "loss": 4.5023, "step": 627 }, { - "epoch": 0.35, - "learning_rate": 0.00027102803738317753, - "loss": 6.4446, + "epoch": 0.7, + "learning_rate": 0.00020357142857142856, + "loss": 4.6263, "step": 628 }, { - "epoch": 0.35, - "learning_rate": 0.0002707943925233645, - "loss": 6.5847, + "epoch": 0.71, + "learning_rate": 0.00020280612244897957, + "loss": 4.4406, "step": 629 }, { - "epoch": 0.35, - "learning_rate": 0.0002705607476635514, - "loss": 4.7228, + "epoch": 0.71, + "learning_rate": 0.00020204081632653058, + "loss": 4.9718, "step": 630 }, { - "epoch": 0.35, - "learning_rate": 0.0002703271028037383, - "loss": 4.8777, + "epoch": 0.71, + "learning_rate": 0.00020127551020408162, + "loss": 4.7535, "step": 631 }, { - "epoch": 0.35, - "learning_rate": 0.0002700934579439252, - "loss": 5.2618, + "epoch": 0.71, + "learning_rate": 0.00020051020408163263, + "loss": 4.8225, "step": 632 }, { - "epoch": 0.35, - "learning_rate": 0.00026985981308411214, - "loss": 4.8416, + "epoch": 0.71, + "learning_rate": 0.00019974489795918367, + "loss": 4.7128, "step": 633 }, { - "epoch": 0.36, - "learning_rate": 0.00026962616822429904, - "loss": 4.8463, + "epoch": 0.71, + "learning_rate": 0.00019897959183673466, + "loss": 4.4988, "step": 634 }, { - "epoch": 0.36, - "learning_rate": 0.00026939252336448594, - "loss": 4.8081, + "epoch": 0.71, + "learning_rate": 0.0001982142857142857, + "loss": 4.61, "step": 635 }, { - "epoch": 0.36, - "learning_rate": 0.00026915887850467284, - "loss": 4.8507, + "epoch": 0.71, + "learning_rate": 0.0001974489795918367, + "loss": 4.5949, "step": 636 }, { - "epoch": 0.36, - "learning_rate": 0.0002689252336448598, - "loss": 4.7788, + "epoch": 0.71, + "learning_rate": 0.00019668367346938775, + "loss": 4.5996, "step": 637 }, { - "epoch": 0.36, - "learning_rate": 0.0002686915887850467, - "loss": 4.5288, + "epoch": 0.72, + "learning_rate": 0.00019591836734693873, + "loss": 4.434, "step": 638 }, { - "epoch": 0.36, - "learning_rate": 0.0002684579439252336, - "loss": 5.093, + "epoch": 0.72, + "learning_rate": 0.00019515306122448977, + "loss": 4.5636, "step": 639 }, { - "epoch": 0.36, - "learning_rate": 0.00026822429906542055, - "loss": 5.6213, + "epoch": 0.72, + "learning_rate": 0.0001943877551020408, + "loss": 5.0026, "step": 640 }, { - "epoch": 0.36, - "learning_rate": 0.00026799065420560745, - "loss": 5.2758, + "epoch": 0.72, + "learning_rate": 0.00019362244897959182, + "loss": 4.5496, "step": 641 }, { - "epoch": 0.36, - "learning_rate": 0.0002677570093457944, - "loss": 5.7338, + "epoch": 0.72, + "learning_rate": 0.00019285714285714286, + "loss": 5.6601, "step": 642 }, { - "epoch": 0.36, - "learning_rate": 0.00026752336448598125, - "loss": 5.3946, + "epoch": 0.72, + "learning_rate": 0.00019209183673469385, + "loss": 5.4602, "step": 643 }, { - "epoch": 0.36, - "learning_rate": 0.0002672897196261682, - "loss": 4.9805, + "epoch": 0.72, + "learning_rate": 0.0001913265306122449, + "loss": 4.4974, "step": 644 }, { - "epoch": 0.36, - "learning_rate": 0.0002670560747663551, - "loss": 4.7258, + "epoch": 0.72, + "learning_rate": 0.0001905612244897959, + "loss": 4.2682, "step": 645 }, { - "epoch": 0.36, - "learning_rate": 0.00026682242990654206, - "loss": 4.9951, + "epoch": 0.72, + "learning_rate": 0.00018979591836734694, + "loss": 4.5693, "step": 646 }, { - "epoch": 0.36, - "learning_rate": 0.00026658878504672896, - "loss": 6.1827, + "epoch": 0.73, + "learning_rate": 0.00018903061224489793, + "loss": 4.4621, "step": 647 }, { - "epoch": 0.36, - "learning_rate": 0.00026635514018691586, - "loss": 6.0104, + "epoch": 0.73, + "learning_rate": 0.00018826530612244896, + "loss": 4.9392, "step": 648 }, { - "epoch": 0.36, - "learning_rate": 0.00026612149532710276, - "loss": 5.3547, + "epoch": 0.73, + "learning_rate": 0.00018749999999999998, + "loss": 4.9068, "step": 649 }, { - "epoch": 0.36, - "learning_rate": 0.0002658878504672897, - "loss": 5.3086, + "epoch": 0.73, + "learning_rate": 0.00018673469387755102, + "loss": 4.451, "step": 650 }, { - "epoch": 0.36, - "learning_rate": 0.0002656542056074766, - "loss": 5.1426, + "epoch": 0.73, + "learning_rate": 0.00018596938775510203, + "loss": 4.7976, "step": 651 }, { - "epoch": 0.37, - "learning_rate": 0.0002654205607476635, - "loss": 4.9117, + "epoch": 0.73, + "learning_rate": 0.00018520408163265304, + "loss": 4.8455, "step": 652 }, { - "epoch": 0.37, - "learning_rate": 0.00026518691588785047, - "loss": 4.7895, + "epoch": 0.73, + "learning_rate": 0.00018443877551020405, + "loss": 4.6031, "step": 653 }, { - "epoch": 0.37, - "learning_rate": 0.00026495327102803737, - "loss": 4.7424, + "epoch": 0.73, + "learning_rate": 0.0001836734693877551, + "loss": 4.8781, "step": 654 }, { - "epoch": 0.37, - "learning_rate": 0.00026471962616822427, - "loss": 5.8121, + "epoch": 0.73, + "learning_rate": 0.0001829081632653061, + "loss": 4.602, "step": 655 }, { - "epoch": 0.37, - "learning_rate": 0.00026448598130841117, - "loss": 4.7262, + "epoch": 0.74, + "learning_rate": 0.00018214285714285712, + "loss": 4.7275, "step": 656 }, { - "epoch": 0.37, - "learning_rate": 0.0002642523364485981, - "loss": 4.6964, + "epoch": 0.74, + "learning_rate": 0.00018137755102040813, + "loss": 4.8361, "step": 657 }, { - "epoch": 0.37, - "learning_rate": 0.000264018691588785, - "loss": 6.4787, + "epoch": 0.74, + "learning_rate": 0.00018061224489795917, + "loss": 4.7144, "step": 658 }, { - "epoch": 0.37, - "learning_rate": 0.0002637850467289719, - "loss": 5.052, + "epoch": 0.74, + "learning_rate": 0.0001798469387755102, + "loss": 4.5318, "step": 659 }, { - "epoch": 0.37, - "learning_rate": 0.0002635514018691588, - "loss": 4.8896, + "epoch": 0.74, + "learning_rate": 0.00017908163265306122, + "loss": 4.8038, "step": 660 }, { - "epoch": 0.37, - "learning_rate": 0.0002633177570093458, - "loss": 6.0785, + "epoch": 0.74, + "learning_rate": 0.0001783163265306122, + "loss": 4.4598, "step": 661 }, { - "epoch": 0.37, - "learning_rate": 0.0002630841121495327, - "loss": 4.8776, + "epoch": 0.74, + "learning_rate": 0.00017755102040816325, + "loss": 4.3151, "step": 662 }, { - "epoch": 0.37, - "learning_rate": 0.0002628504672897196, - "loss": 4.7447, + "epoch": 0.74, + "learning_rate": 0.00017678571428571428, + "loss": 4.7638, "step": 663 }, { - "epoch": 0.37, - "learning_rate": 0.00026261682242990653, - "loss": 5.4587, + "epoch": 0.74, + "learning_rate": 0.0001760204081632653, + "loss": 4.5215, "step": 664 }, { - "epoch": 0.37, - "learning_rate": 0.00026238317757009343, - "loss": 4.9692, + "epoch": 0.75, + "learning_rate": 0.0001752551020408163, + "loss": 4.3488, "step": 665 }, { - "epoch": 0.37, - "learning_rate": 0.0002621495327102804, - "loss": 5.5604, + "epoch": 0.75, + "learning_rate": 0.00017448979591836732, + "loss": 4.8026, "step": 666 }, { - "epoch": 0.37, - "learning_rate": 0.00026191588785046723, - "loss": 4.7909, + "epoch": 0.75, + "learning_rate": 0.00017372448979591836, + "loss": 4.4306, "step": 667 }, { - "epoch": 0.37, - "learning_rate": 0.0002616822429906542, - "loss": 5.2694, + "epoch": 0.75, + "learning_rate": 0.00017295918367346937, + "loss": 4.5775, "step": 668 }, { - "epoch": 0.38, - "learning_rate": 0.0002614485981308411, - "loss": 4.6327, + "epoch": 0.75, + "learning_rate": 0.0001721938775510204, + "loss": 4.8122, "step": 669 }, { - "epoch": 0.38, - "learning_rate": 0.00026121495327102804, - "loss": 4.9776, + "epoch": 0.75, + "learning_rate": 0.0001714285714285714, + "loss": 4.8343, "step": 670 }, { - "epoch": 0.38, - "learning_rate": 0.00026098130841121494, - "loss": 4.9354, + "epoch": 0.75, + "learning_rate": 0.00017066326530612244, + "loss": 4.3346, "step": 671 }, { - "epoch": 0.38, - "learning_rate": 0.00026074766355140184, - "loss": 5.4778, + "epoch": 0.75, + "learning_rate": 0.00016989795918367345, + "loss": 4.4829, "step": 672 }, { - "epoch": 0.38, - "learning_rate": 0.00026051401869158874, - "loss": 4.9254, + "epoch": 0.75, + "learning_rate": 0.0001691326530612245, + "loss": 4.494, "step": 673 }, { - "epoch": 0.38, - "learning_rate": 0.0002602803738317757, - "loss": 4.6548, + "epoch": 0.76, + "learning_rate": 0.00016836734693877547, + "loss": 4.3151, "step": 674 }, { - "epoch": 0.38, - "learning_rate": 0.0002600467289719626, - "loss": 4.915, + "epoch": 0.76, + "learning_rate": 0.00016760204081632651, + "loss": 4.3759, "step": 675 }, { - "epoch": 0.38, - "learning_rate": 0.0002598130841121495, - "loss": 4.8809, + "epoch": 0.76, + "learning_rate": 0.00016683673469387753, + "loss": 4.8447, "step": 676 }, { - "epoch": 0.38, - "learning_rate": 0.00025957943925233645, - "loss": 4.595, + "epoch": 0.76, + "learning_rate": 0.00016607142857142857, + "loss": 4.3537, "step": 677 }, { - "epoch": 0.38, - "learning_rate": 0.00025934579439252335, - "loss": 4.68, + "epoch": 0.76, + "learning_rate": 0.00016530612244897955, + "loss": 4.2273, "step": 678 }, { - "epoch": 0.38, - "learning_rate": 0.00025911214953271025, - "loss": 5.2213, + "epoch": 0.76, + "learning_rate": 0.0001645408163265306, + "loss": 4.4868, "step": 679 }, { - "epoch": 0.38, - "learning_rate": 0.00025887850467289715, - "loss": 6.0867, + "epoch": 0.76, + "learning_rate": 0.00016377551020408163, + "loss": 4.8668, "step": 680 }, { - "epoch": 0.38, - "learning_rate": 0.0002586448598130841, - "loss": 4.9661, + "epoch": 0.76, + "learning_rate": 0.00016301020408163264, + "loss": 4.9554, "step": 681 }, { - "epoch": 0.38, - "learning_rate": 0.000258411214953271, - "loss": 4.7829, + "epoch": 0.76, + "learning_rate": 0.00016224489795918368, + "loss": 4.5154, "step": 682 }, { - "epoch": 0.38, - "learning_rate": 0.0002581775700934579, - "loss": 5.8107, + "epoch": 0.77, + "learning_rate": 0.00016147959183673467, + "loss": 4.6888, "step": 683 }, { - "epoch": 0.38, - "learning_rate": 0.0002579439252336448, - "loss": 5.0299, + "epoch": 0.77, + "learning_rate": 0.0001607142857142857, + "loss": 4.6942, "step": 684 }, { - "epoch": 0.38, - "learning_rate": 0.00025771028037383176, - "loss": 5.315, + "epoch": 0.77, + "learning_rate": 0.00015994897959183672, + "loss": 4.659, "step": 685 }, { - "epoch": 0.38, - "learning_rate": 0.00025747663551401866, - "loss": 5.4344, + "epoch": 0.77, + "learning_rate": 0.00015918367346938776, + "loss": 4.8683, "step": 686 }, { - "epoch": 0.39, - "learning_rate": 0.00025724299065420556, - "loss": 4.7482, + "epoch": 0.77, + "learning_rate": 0.00015841836734693874, + "loss": 4.5763, "step": 687 }, { - "epoch": 0.39, - "learning_rate": 0.0002570093457943925, - "loss": 4.7386, + "epoch": 0.77, + "learning_rate": 0.00015765306122448978, + "loss": 4.5797, "step": 688 }, { - "epoch": 0.39, - "learning_rate": 0.0002567757009345794, - "loss": 5.1951, + "epoch": 0.77, + "learning_rate": 0.0001568877551020408, + "loss": 4.6032, "step": 689 }, { - "epoch": 0.39, - "learning_rate": 0.00025654205607476637, - "loss": 4.8158, + "epoch": 0.77, + "learning_rate": 0.00015612244897959183, + "loss": 4.8889, "step": 690 }, { - "epoch": 0.39, - "learning_rate": 0.0002563084112149532, - "loss": 4.5983, + "epoch": 0.77, + "learning_rate": 0.00015535714285714285, + "loss": 4.5367, "step": 691 }, { - "epoch": 0.39, - "learning_rate": 0.00025607476635514017, - "loss": 6.1425, + "epoch": 0.78, + "learning_rate": 0.00015459183673469386, + "loss": 4.5178, "step": 692 }, { - "epoch": 0.39, - "learning_rate": 0.00025584112149532707, - "loss": 5.402, + "epoch": 0.78, + "learning_rate": 0.00015382653061224487, + "loss": 4.3197, "step": 693 }, { - "epoch": 0.39, - "learning_rate": 0.000255607476635514, - "loss": 4.8156, + "epoch": 0.78, + "learning_rate": 0.0001530612244897959, + "loss": 5.5082, "step": 694 }, { - "epoch": 0.39, - "learning_rate": 0.0002553738317757009, - "loss": 5.0172, + "epoch": 0.78, + "learning_rate": 0.00015229591836734692, + "loss": 4.8537, "step": 695 }, { - "epoch": 0.39, - "learning_rate": 0.0002551401869158878, - "loss": 4.9831, + "epoch": 0.78, + "learning_rate": 0.00015153061224489794, + "loss": 4.6284, "step": 696 }, { - "epoch": 0.39, - "learning_rate": 0.0002549065420560747, - "loss": 4.5366, + "epoch": 0.78, + "learning_rate": 0.00015076530612244895, + "loss": 4.9042, "step": 697 }, { - "epoch": 0.39, - "learning_rate": 0.0002546728971962617, - "loss": 4.8433, + "epoch": 0.78, + "learning_rate": 0.00015, + "loss": 4.5487, "step": 698 }, { - "epoch": 0.39, - "learning_rate": 0.0002544392523364486, - "loss": 6.9107, + "epoch": 0.78, + "learning_rate": 0.00014923469387755103, + "loss": 4.8411, "step": 699 }, { - "epoch": 0.39, - "learning_rate": 0.0002542056074766355, - "loss": 4.7848, + "epoch": 0.78, + "learning_rate": 0.00014846938775510204, + "loss": 4.6106, "step": 700 }, { - "epoch": 0.39, - "learning_rate": 0.00025397196261682243, - "loss": 4.5614, + "epoch": 0.79, + "learning_rate": 0.00014770408163265305, + "loss": 4.3733, "step": 701 }, { - "epoch": 0.39, - "learning_rate": 0.00025373831775700933, - "loss": 4.7327, + "epoch": 0.79, + "learning_rate": 0.00014693877551020406, + "loss": 4.6806, "step": 702 }, { - "epoch": 0.39, - "learning_rate": 0.00025350467289719623, - "loss": 5.4214, + "epoch": 0.79, + "learning_rate": 0.0001461734693877551, + "loss": 4.4325, "step": 703 }, { - "epoch": 0.39, - "learning_rate": 0.00025327102803738313, - "loss": 6.0193, + "epoch": 0.79, + "learning_rate": 0.00014540816326530611, + "loss": 4.5601, "step": 704 }, { - "epoch": 0.4, - "learning_rate": 0.0002530373831775701, - "loss": 5.8451, + "epoch": 0.79, + "learning_rate": 0.00014464285714285713, + "loss": 4.7532, "step": 705 }, { - "epoch": 0.4, - "learning_rate": 0.000252803738317757, - "loss": 5.0033, + "epoch": 0.79, + "learning_rate": 0.00014387755102040814, + "loss": 4.8566, "step": 706 }, { - "epoch": 0.4, - "learning_rate": 0.0002525700934579439, - "loss": 5.2146, + "epoch": 0.79, + "learning_rate": 0.00014311224489795918, + "loss": 4.8353, "step": 707 }, { - "epoch": 0.4, - "learning_rate": 0.0002523364485981308, - "loss": 5.0324, + "epoch": 0.79, + "learning_rate": 0.0001423469387755102, + "loss": 4.9163, "step": 708 }, { - "epoch": 0.4, - "learning_rate": 0.00025210280373831774, - "loss": 4.9895, + "epoch": 0.79, + "learning_rate": 0.0001415816326530612, + "loss": 4.8582, "step": 709 }, { - "epoch": 0.4, - "learning_rate": 0.00025186915887850464, - "loss": 5.2213, + "epoch": 0.8, + "learning_rate": 0.00014081632653061224, + "loss": 4.7769, "step": 710 }, { - "epoch": 0.4, - "learning_rate": 0.00025163551401869154, - "loss": 5.1836, + "epoch": 0.8, + "learning_rate": 0.00014005102040816326, + "loss": 4.4617, "step": 711 }, { - "epoch": 0.4, - "learning_rate": 0.0002514018691588785, - "loss": 4.9742, + "epoch": 0.8, + "learning_rate": 0.00013928571428571427, + "loss": 4.4321, "step": 712 }, { - "epoch": 0.4, - "learning_rate": 0.0002511682242990654, - "loss": 4.7988, + "epoch": 0.8, + "learning_rate": 0.00013852040816326528, + "loss": 4.5018, "step": 713 }, { - "epoch": 0.4, - "learning_rate": 0.00025093457943925235, - "loss": 5.2016, + "epoch": 0.8, + "learning_rate": 0.00013775510204081632, + "loss": 4.7764, "step": 714 }, { - "epoch": 0.4, - "learning_rate": 0.0002507009345794392, - "loss": 5.1895, + "epoch": 0.8, + "learning_rate": 0.00013698979591836733, + "loss": 4.8378, "step": 715 }, { - "epoch": 0.4, - "learning_rate": 0.00025046728971962615, - "loss": 4.5532, + "epoch": 0.8, + "learning_rate": 0.00013622448979591834, + "loss": 4.4279, "step": 716 }, { - "epoch": 0.4, - "learning_rate": 0.00025023364485981305, - "loss": 4.8191, + "epoch": 0.8, + "learning_rate": 0.00013545918367346936, + "loss": 4.6902, "step": 717 }, { - "epoch": 0.4, - "learning_rate": 0.00025, - "loss": 4.9591, + "epoch": 0.8, + "learning_rate": 0.0001346938775510204, + "loss": 4.541, "step": 718 }, { - "epoch": 0.4, - "learning_rate": 0.0002497663551401869, - "loss": 4.8775, + "epoch": 0.81, + "learning_rate": 0.00013392857142857144, + "loss": 4.2557, "step": 719 }, { - "epoch": 0.4, - "learning_rate": 0.0002495327102803738, - "loss": 4.7128, + "epoch": 0.81, + "learning_rate": 0.00013316326530612245, + "loss": 4.4988, "step": 720 }, { - "epoch": 0.4, - "learning_rate": 0.0002492990654205607, - "loss": 5.2117, + "epoch": 0.81, + "learning_rate": 0.00013239795918367346, + "loss": 4.4368, "step": 721 }, { - "epoch": 0.4, - "learning_rate": 0.00024906542056074766, - "loss": 5.1305, + "epoch": 0.81, + "learning_rate": 0.00013163265306122447, + "loss": 4.3217, "step": 722 }, { - "epoch": 0.41, - "learning_rate": 0.00024883177570093456, - "loss": 4.6492, + "epoch": 0.81, + "learning_rate": 0.0001308673469387755, + "loss": 4.5789, "step": 723 }, { - "epoch": 0.41, - "learning_rate": 0.00024859813084112146, - "loss": 5.5524, + "epoch": 0.81, + "learning_rate": 0.00013010204081632652, + "loss": 4.5359, "step": 724 }, { - "epoch": 0.41, - "learning_rate": 0.0002483644859813084, - "loss": 4.8542, + "epoch": 0.81, + "learning_rate": 0.00012933673469387754, + "loss": 4.5571, "step": 725 }, { - "epoch": 0.41, - "learning_rate": 0.0002481308411214953, - "loss": 5.6067, + "epoch": 0.81, + "learning_rate": 0.00012857142857142855, + "loss": 4.7745, "step": 726 }, { - "epoch": 0.41, - "learning_rate": 0.0002478971962616822, - "loss": 4.2927, + "epoch": 0.82, + "learning_rate": 0.0001278061224489796, + "loss": 4.4231, "step": 727 }, { - "epoch": 0.41, - "learning_rate": 0.0002476635514018691, - "loss": 5.0961, + "epoch": 0.82, + "learning_rate": 0.0001270408163265306, + "loss": 4.3674, "step": 728 }, { - "epoch": 0.41, - "learning_rate": 0.00024742990654205607, - "loss": 4.6596, + "epoch": 0.82, + "learning_rate": 0.0001262755102040816, + "loss": 4.2422, "step": 729 }, { - "epoch": 0.41, - "learning_rate": 0.00024719626168224297, - "loss": 4.9432, + "epoch": 0.82, + "learning_rate": 0.00012551020408163265, + "loss": 4.7642, "step": 730 }, { - "epoch": 0.41, - "learning_rate": 0.00024696261682242987, - "loss": 4.634, + "epoch": 0.82, + "learning_rate": 0.00012474489795918366, + "loss": 5.37, "step": 731 }, { - "epoch": 0.41, - "learning_rate": 0.00024672897196261677, - "loss": 4.5998, + "epoch": 0.82, + "learning_rate": 0.00012397959183673468, + "loss": 4.8652, "step": 732 }, { - "epoch": 0.41, - "learning_rate": 0.0002464953271028037, - "loss": 6.063, + "epoch": 0.82, + "learning_rate": 0.0001232142857142857, + "loss": 4.3529, "step": 733 }, { - "epoch": 0.41, - "learning_rate": 0.0002462616822429906, - "loss": 4.6758, + "epoch": 0.82, + "learning_rate": 0.00012244897959183673, + "loss": 4.7189, "step": 734 }, { - "epoch": 0.41, - "learning_rate": 0.0002460280373831775, - "loss": 5.2033, + "epoch": 0.82, + "learning_rate": 0.00012168367346938774, + "loss": 4.2646, "step": 735 }, { - "epoch": 0.41, - "learning_rate": 0.0002457943925233645, - "loss": 4.8956, + "epoch": 0.83, + "learning_rate": 0.00012091836734693877, + "loss": 4.4345, "step": 736 }, { - "epoch": 0.41, - "learning_rate": 0.0002455607476635514, - "loss": 4.7879, + "epoch": 0.83, + "learning_rate": 0.00012015306122448978, + "loss": 4.4738, "step": 737 }, { - "epoch": 0.41, - "learning_rate": 0.00024532710280373833, - "loss": 5.2447, + "epoch": 0.83, + "learning_rate": 0.0001193877551020408, + "loss": 4.4329, "step": 738 }, { - "epoch": 0.41, - "learning_rate": 0.0002450934579439252, - "loss": 5.9277, + "epoch": 0.83, + "learning_rate": 0.00011862244897959183, + "loss": 4.4029, "step": 739 }, { - "epoch": 0.41, - "learning_rate": 0.00024485981308411213, - "loss": 4.8356, + "epoch": 0.83, + "learning_rate": 0.00011785714285714284, + "loss": 4.6458, "step": 740 }, { - "epoch": 0.42, - "learning_rate": 0.00024462616822429903, - "loss": 5.7938, + "epoch": 0.83, + "learning_rate": 0.00011709183673469387, + "loss": 4.6905, "step": 741 }, { - "epoch": 0.42, - "learning_rate": 0.000244392523364486, - "loss": 4.7628, + "epoch": 0.83, + "learning_rate": 0.00011632653061224488, + "loss": 4.5926, "step": 742 }, { - "epoch": 0.42, - "learning_rate": 0.0002441588785046729, - "loss": 6.2093, + "epoch": 0.83, + "learning_rate": 0.00011556122448979591, + "loss": 4.1697, "step": 743 }, { - "epoch": 0.42, - "learning_rate": 0.0002439252336448598, - "loss": 4.9553, + "epoch": 0.83, + "learning_rate": 0.00011479591836734692, + "loss": 4.4294, "step": 744 }, { - "epoch": 0.42, - "learning_rate": 0.00024369158878504671, - "loss": 5.8293, + "epoch": 0.84, + "learning_rate": 0.00011403061224489795, + "loss": 4.5201, "step": 745 }, { - "epoch": 0.42, - "learning_rate": 0.00024345794392523364, - "loss": 4.9584, + "epoch": 0.84, + "learning_rate": 0.00011326530612244896, + "loss": 5.5063, "step": 746 }, { - "epoch": 0.42, - "learning_rate": 0.00024322429906542051, - "loss": 5.0734, + "epoch": 0.84, + "learning_rate": 0.0001125, + "loss": 4.3831, "step": 747 }, { - "epoch": 0.42, - "learning_rate": 0.00024299065420560744, - "loss": 5.0013, + "epoch": 0.84, + "learning_rate": 0.00011173469387755102, + "loss": 4.5783, "step": 748 }, { - "epoch": 0.42, - "learning_rate": 0.00024275700934579437, - "loss": 4.6312, + "epoch": 0.84, + "learning_rate": 0.00011096938775510204, + "loss": 4.9205, "step": 749 }, { - "epoch": 0.42, - "learning_rate": 0.0002425233644859813, - "loss": 4.9714, + "epoch": 0.84, + "learning_rate": 0.00011020408163265306, + "loss": 4.4522, "step": 750 }, { - "epoch": 0.42, - "learning_rate": 0.0002422897196261682, - "loss": 5.5628, + "epoch": 0.84, + "learning_rate": 0.00010943877551020407, + "loss": 4.5486, "step": 751 }, { - "epoch": 0.42, - "learning_rate": 0.00024205607476635512, - "loss": 5.0227, + "epoch": 0.84, + "learning_rate": 0.0001086734693877551, + "loss": 4.4711, "step": 752 }, { - "epoch": 0.42, - "learning_rate": 0.00024182242990654205, - "loss": 4.8764, + "epoch": 0.84, + "learning_rate": 0.00010790816326530611, + "loss": 4.5152, "step": 753 }, { - "epoch": 0.42, - "learning_rate": 0.00024158878504672895, - "loss": 4.951, + "epoch": 0.85, + "learning_rate": 0.00010714285714285714, + "loss": 4.7207, "step": 754 }, { - "epoch": 0.42, - "learning_rate": 0.00024135514018691585, - "loss": 4.7861, + "epoch": 0.85, + "learning_rate": 0.00010637755102040815, + "loss": 4.6543, "step": 755 }, { - "epoch": 0.42, - "learning_rate": 0.00024112149532710278, - "loss": 5.217, + "epoch": 0.85, + "learning_rate": 0.00010561224489795918, + "loss": 4.612, "step": 756 }, { - "epoch": 0.42, - "learning_rate": 0.0002408878504672897, - "loss": 5.5545, + "epoch": 0.85, + "learning_rate": 0.0001048469387755102, + "loss": 4.5727, "step": 757 }, { - "epoch": 0.42, - "learning_rate": 0.00024065420560747663, - "loss": 4.999, + "epoch": 0.85, + "learning_rate": 0.00010408163265306121, + "loss": 4.4984, "step": 758 }, { - "epoch": 0.43, - "learning_rate": 0.0002404205607476635, - "loss": 4.7915, + "epoch": 0.85, + "learning_rate": 0.00010331632653061224, + "loss": 4.3676, "step": 759 }, { - "epoch": 0.43, - "learning_rate": 0.00024018691588785043, - "loss": 4.6985, + "epoch": 0.85, + "learning_rate": 0.00010255102040816325, + "loss": 4.3851, "step": 760 }, { - "epoch": 0.43, - "learning_rate": 0.00023995327102803736, - "loss": 5.0491, + "epoch": 0.85, + "learning_rate": 0.00010178571428571428, + "loss": 4.3398, "step": 761 }, { - "epoch": 0.43, - "learning_rate": 0.00023971962616822429, - "loss": 4.8354, + "epoch": 0.85, + "learning_rate": 0.00010102040816326529, + "loss": 4.3349, "step": 762 }, { - "epoch": 0.43, - "learning_rate": 0.00023948598130841119, - "loss": 4.698, + "epoch": 0.86, + "learning_rate": 0.00010025510204081632, + "loss": 4.3309, "step": 763 }, { - "epoch": 0.43, - "learning_rate": 0.0002392523364485981, - "loss": 4.4355, + "epoch": 0.86, + "learning_rate": 9.948979591836733e-05, + "loss": 4.3001, "step": 764 }, { - "epoch": 0.43, - "learning_rate": 0.00023901869158878504, - "loss": 4.5091, + "epoch": 0.86, + "learning_rate": 9.872448979591835e-05, + "loss": 4.7146, "step": 765 }, { - "epoch": 0.43, - "learning_rate": 0.00023878504672897194, - "loss": 5.0876, + "epoch": 0.86, + "learning_rate": 9.795918367346937e-05, + "loss": 4.4401, "step": 766 }, { - "epoch": 0.43, - "learning_rate": 0.00023855140186915884, - "loss": 5.7448, + "epoch": 0.86, + "learning_rate": 9.71938775510204e-05, + "loss": 4.344, "step": 767 }, { - "epoch": 0.43, - "learning_rate": 0.00023831775700934577, - "loss": 4.5224, + "epoch": 0.86, + "learning_rate": 9.642857142857143e-05, + "loss": 4.3721, "step": 768 }, { - "epoch": 0.43, - "learning_rate": 0.0002380841121495327, - "loss": 5.4974, + "epoch": 0.86, + "learning_rate": 9.566326530612244e-05, + "loss": 4.6081, "step": 769 }, { - "epoch": 0.43, - "learning_rate": 0.00023785046728971962, - "loss": 4.7424, + "epoch": 0.86, + "learning_rate": 9.489795918367347e-05, + "loss": 4.5487, "step": 770 }, { - "epoch": 0.43, - "learning_rate": 0.0002376168224299065, - "loss": 5.2753, + "epoch": 0.86, + "learning_rate": 9.413265306122448e-05, + "loss": 4.4123, "step": 771 }, { - "epoch": 0.43, - "learning_rate": 0.00023738317757009342, - "loss": 4.7534, + "epoch": 0.87, + "learning_rate": 9.336734693877551e-05, + "loss": 4.6984, "step": 772 }, { - "epoch": 0.43, - "learning_rate": 0.00023714953271028035, - "loss": 4.8753, + "epoch": 0.87, + "learning_rate": 9.260204081632652e-05, + "loss": 4.7009, "step": 773 }, { - "epoch": 0.43, - "learning_rate": 0.00023691588785046728, - "loss": 5.0408, + "epoch": 0.87, + "learning_rate": 9.183673469387755e-05, + "loss": 4.132, "step": 774 }, { - "epoch": 0.43, - "learning_rate": 0.00023668224299065418, - "loss": 4.702, + "epoch": 0.87, + "learning_rate": 9.107142857142856e-05, + "loss": 4.1582, "step": 775 }, { - "epoch": 0.43, - "learning_rate": 0.0002364485981308411, - "loss": 4.8086, + "epoch": 0.87, + "learning_rate": 9.030612244897958e-05, + "loss": 4.8277, "step": 776 }, { - "epoch": 0.44, - "learning_rate": 0.00023621495327102803, - "loss": 4.4968, + "epoch": 0.87, + "learning_rate": 8.954081632653061e-05, + "loss": 4.2984, "step": 777 }, { - "epoch": 0.44, - "learning_rate": 0.00023598130841121493, - "loss": 5.0478, + "epoch": 0.87, + "learning_rate": 8.877551020408162e-05, + "loss": 4.4968, "step": 778 }, { - "epoch": 0.44, - "learning_rate": 0.00023574766355140183, - "loss": 4.9104, + "epoch": 0.87, + "learning_rate": 8.801020408163265e-05, + "loss": 4.4658, "step": 779 }, { - "epoch": 0.44, - "learning_rate": 0.00023551401869158876, - "loss": 4.8108, + "epoch": 0.87, + "learning_rate": 8.724489795918366e-05, + "loss": 4.3005, "step": 780 }, { - "epoch": 0.44, - "learning_rate": 0.00023528037383177569, - "loss": 4.7577, + "epoch": 0.88, + "learning_rate": 8.647959183673469e-05, + "loss": 4.3646, "step": 781 }, { - "epoch": 0.44, - "learning_rate": 0.0002350467289719626, - "loss": 4.873, + "epoch": 0.88, + "learning_rate": 8.57142857142857e-05, + "loss": 4.409, "step": 782 }, { - "epoch": 0.44, - "learning_rate": 0.00023481308411214949, - "loss": 4.8684, + "epoch": 0.88, + "learning_rate": 8.494897959183672e-05, + "loss": 4.5502, "step": 783 }, { - "epoch": 0.44, - "learning_rate": 0.0002345794392523364, - "loss": 4.6435, + "epoch": 0.88, + "learning_rate": 8.418367346938774e-05, + "loss": 4.2776, "step": 784 }, { - "epoch": 0.44, - "learning_rate": 0.00023434579439252334, - "loss": 4.9673, + "epoch": 0.88, + "learning_rate": 8.341836734693876e-05, + "loss": 4.3157, "step": 785 }, { - "epoch": 0.44, - "learning_rate": 0.00023411214953271027, - "loss": 5.372, + "epoch": 0.88, + "learning_rate": 8.265306122448978e-05, + "loss": 4.2001, "step": 786 }, { - "epoch": 0.44, - "learning_rate": 0.00023387850467289717, - "loss": 4.9279, + "epoch": 0.88, + "learning_rate": 8.188775510204081e-05, + "loss": 4.5778, "step": 787 }, { - "epoch": 0.44, - "learning_rate": 0.0002336448598130841, - "loss": 5.1448, + "epoch": 0.88, + "learning_rate": 8.112244897959184e-05, + "loss": 4.3841, "step": 788 }, { - "epoch": 0.44, - "learning_rate": 0.00023341121495327102, - "loss": 5.4371, + "epoch": 0.88, + "learning_rate": 8.035714285714285e-05, + "loss": 4.4634, "step": 789 }, { - "epoch": 0.44, - "learning_rate": 0.00023317757009345792, - "loss": 5.2811, + "epoch": 0.89, + "learning_rate": 7.959183673469388e-05, + "loss": 4.3567, "step": 790 }, { - "epoch": 0.44, - "learning_rate": 0.00023294392523364482, - "loss": 5.1184, + "epoch": 0.89, + "learning_rate": 7.882653061224489e-05, + "loss": 4.4466, "step": 791 }, { - "epoch": 0.44, - "learning_rate": 0.00023271028037383175, - "loss": 5.3196, + "epoch": 0.89, + "learning_rate": 7.806122448979592e-05, + "loss": 4.2954, "step": 792 }, { - "epoch": 0.44, - "learning_rate": 0.00023247663551401868, - "loss": 5.7307, + "epoch": 0.89, + "learning_rate": 7.729591836734693e-05, + "loss": 4.376, "step": 793 }, { - "epoch": 0.45, - "learning_rate": 0.0002322429906542056, - "loss": 4.8618, + "epoch": 0.89, + "learning_rate": 7.653061224489796e-05, + "loss": 4.5405, "step": 794 }, { - "epoch": 0.45, - "learning_rate": 0.00023200934579439248, - "loss": 5.3565, + "epoch": 0.89, + "learning_rate": 7.576530612244897e-05, + "loss": 4.5937, "step": 795 }, { - "epoch": 0.45, - "learning_rate": 0.0002317757009345794, - "loss": 6.2956, + "epoch": 0.89, + "learning_rate": 7.5e-05, + "loss": 4.3019, "step": 796 }, { - "epoch": 0.45, - "learning_rate": 0.00023154205607476633, - "loss": 5.663, + "epoch": 0.89, + "learning_rate": 7.423469387755102e-05, + "loss": 4.4521, "step": 797 }, { - "epoch": 0.45, - "learning_rate": 0.00023130841121495326, - "loss": 5.2661, + "epoch": 0.89, + "learning_rate": 7.346938775510203e-05, + "loss": 4.5045, "step": 798 }, { - "epoch": 0.45, - "learning_rate": 0.00023107476635514016, - "loss": 5.2952, + "epoch": 0.9, + "learning_rate": 7.270408163265306e-05, + "loss": 4.7686, "step": 799 }, { - "epoch": 0.45, - "learning_rate": 0.00023084112149532709, - "loss": 5.0248, + "epoch": 0.9, + "learning_rate": 7.193877551020407e-05, + "loss": 4.5522, "step": 800 }, { - "epoch": 0.45, - "learning_rate": 0.000230607476635514, - "loss": 5.6063, + "epoch": 0.9, + "learning_rate": 7.11734693877551e-05, + "loss": 4.3942, "step": 801 }, { - "epoch": 0.45, - "learning_rate": 0.0002303738317757009, - "loss": 5.2341, + "epoch": 0.9, + "learning_rate": 7.040816326530612e-05, + "loss": 4.2739, "step": 802 }, { - "epoch": 0.45, - "learning_rate": 0.0002301401869158878, - "loss": 5.4602, + "epoch": 0.9, + "learning_rate": 6.964285714285713e-05, + "loss": 4.4157, "step": 803 }, { - "epoch": 0.45, - "learning_rate": 0.00022990654205607474, - "loss": 5.0137, + "epoch": 0.9, + "learning_rate": 6.887755102040816e-05, + "loss": 4.3858, "step": 804 }, { - "epoch": 0.45, - "learning_rate": 0.00022967289719626167, - "loss": 5.2147, + "epoch": 0.9, + "learning_rate": 6.811224489795917e-05, + "loss": 4.1583, "step": 805 }, { - "epoch": 0.45, - "learning_rate": 0.0002294392523364486, - "loss": 5.2667, + "epoch": 0.9, + "learning_rate": 6.73469387755102e-05, + "loss": 4.5902, "step": 806 }, { - "epoch": 0.45, - "learning_rate": 0.00022920560747663547, - "loss": 5.0235, + "epoch": 0.9, + "learning_rate": 6.658163265306122e-05, + "loss": 4.3665, "step": 807 }, { - "epoch": 0.45, - "learning_rate": 0.0002289719626168224, - "loss": 4.6348, + "epoch": 0.91, + "learning_rate": 6.581632653061224e-05, + "loss": 4.2522, "step": 808 }, { - "epoch": 0.45, - "learning_rate": 0.00022873831775700932, - "loss": 4.9595, + "epoch": 0.91, + "learning_rate": 6.505102040816326e-05, + "loss": 4.6056, "step": 809 }, { - "epoch": 0.45, - "learning_rate": 0.00022850467289719625, - "loss": 5.1711, + "epoch": 0.91, + "learning_rate": 6.428571428571427e-05, + "loss": 4.1505, "step": 810 }, { - "epoch": 0.45, - "learning_rate": 0.00022827102803738315, - "loss": 5.1581, + "epoch": 0.91, + "learning_rate": 6.35204081632653e-05, + "loss": 4.5202, "step": 811 }, { - "epoch": 0.46, - "learning_rate": 0.00022803738317757008, - "loss": 5.154, + "epoch": 0.91, + "learning_rate": 6.275510204081633e-05, + "loss": 4.5724, "step": 812 }, { - "epoch": 0.46, - "learning_rate": 0.000227803738317757, - "loss": 5.4425, + "epoch": 0.91, + "learning_rate": 6.198979591836734e-05, + "loss": 4.1591, "step": 813 }, { - "epoch": 0.46, - "learning_rate": 0.0002275700934579439, - "loss": 4.5514, + "epoch": 0.91, + "learning_rate": 6.122448979591836e-05, + "loss": 4.2601, "step": 814 }, { - "epoch": 0.46, - "learning_rate": 0.0002273364485981308, - "loss": 4.6538, + "epoch": 0.91, + "learning_rate": 6.045918367346938e-05, + "loss": 4.2979, "step": 815 }, { - "epoch": 0.46, - "learning_rate": 0.00022710280373831773, - "loss": 4.6742, + "epoch": 0.91, + "learning_rate": 5.96938775510204e-05, + "loss": 4.3289, "step": 816 }, { - "epoch": 0.46, - "learning_rate": 0.00022686915887850466, - "loss": 4.835, + "epoch": 0.92, + "learning_rate": 5.892857142857142e-05, + "loss": 4.4371, "step": 817 }, { - "epoch": 0.46, - "learning_rate": 0.00022663551401869158, - "loss": 5.1699, + "epoch": 0.92, + "learning_rate": 5.816326530612244e-05, + "loss": 4.321, "step": 818 }, { - "epoch": 0.46, - "learning_rate": 0.00022640186915887846, - "loss": 4.7688, + "epoch": 0.92, + "learning_rate": 5.739795918367346e-05, + "loss": 4.1933, "step": 819 }, { - "epoch": 0.46, - "learning_rate": 0.00022616822429906539, - "loss": 4.7451, + "epoch": 0.92, + "learning_rate": 5.663265306122448e-05, + "loss": 4.3224, "step": 820 }, { - "epoch": 0.46, - "learning_rate": 0.0002259345794392523, - "loss": 4.9778, + "epoch": 0.92, + "learning_rate": 5.586734693877551e-05, + "loss": 4.4234, "step": 821 }, - { - "epoch": 0.46, - "learning_rate": 0.00022570093457943924, - "loss": 4.8394, - "step": 822 - }, - { - "epoch": 0.46, - "learning_rate": 0.00022546728971962614, - "loss": 6.198, - "step": 823 - }, - { - "epoch": 0.46, - "learning_rate": 0.00022523364485981307, - "loss": 4.9316, - "step": 824 - }, - { - "epoch": 0.46, - "learning_rate": 0.000225, - "loss": 4.8827, - "step": 825 - }, - { - "epoch": 0.46, - "learning_rate": 0.0002247663551401869, - "loss": 4.8518, - "step": 826 - }, - { - "epoch": 0.46, - "learning_rate": 0.00022453271028037382, - "loss": 5.825, - "step": 827 - }, - { - "epoch": 0.46, - "learning_rate": 0.00022429906542056072, - "loss": 4.9195, - "step": 828 - }, - { - "epoch": 0.46, - "learning_rate": 0.00022406542056074765, - "loss": 5.0547, - "step": 829 - }, - { - "epoch": 0.47, - "learning_rate": 0.00022383177570093458, - "loss": 4.8494, - "step": 830 - }, - { - "epoch": 0.47, - "learning_rate": 0.0002235981308411215, - "loss": 4.9152, - "step": 831 - }, - { - "epoch": 0.47, - "learning_rate": 0.00022336448598130838, - "loss": 5.4614, - "step": 832 - }, - { - "epoch": 0.47, - "learning_rate": 0.0002231308411214953, - "loss": 4.9862, - "step": 833 - }, - { - "epoch": 0.47, - "learning_rate": 0.00022289719626168223, - "loss": 4.3363, - "step": 834 - }, - { - "epoch": 0.47, - "learning_rate": 0.00022266355140186916, - "loss": 4.8868, - "step": 835 - }, - { - "epoch": 0.47, - "learning_rate": 0.00022242990654205606, - "loss": 4.8546, - "step": 836 - }, - { - "epoch": 0.47, - "learning_rate": 0.00022219626168224296, - "loss": 4.8257, - "step": 837 - }, - { - "epoch": 0.47, - "learning_rate": 0.00022196261682242988, - "loss": 4.6675, - "step": 838 - }, - { - "epoch": 0.47, - "learning_rate": 0.0002217289719626168, - "loss": 4.4901, - "step": 839 - }, - { - "epoch": 0.47, - "learning_rate": 0.0002214953271028037, - "loss": 5.3061, - "step": 840 - }, - { - "epoch": 0.47, - "learning_rate": 0.00022126168224299064, - "loss": 4.8716, - "step": 841 - }, - { - "epoch": 0.47, - "learning_rate": 0.00022102803738317757, - "loss": 4.7561, - "step": 842 - }, - { - "epoch": 0.47, - "learning_rate": 0.0002207943925233645, - "loss": 4.5837, - "step": 843 - }, - { - "epoch": 0.47, - "learning_rate": 0.00022056074766355137, - "loss": 4.992, - "step": 844 - }, - { - "epoch": 0.47, - "learning_rate": 0.0002203271028037383, - "loss": 4.4575, - "step": 845 - }, - { - "epoch": 0.47, - "learning_rate": 0.00022009345794392522, - "loss": 4.5631, - "step": 846 - }, - { - "epoch": 0.47, - "learning_rate": 0.00021985981308411215, - "loss": 4.4217, - "step": 847 - }, - { - "epoch": 0.48, - "learning_rate": 0.00021962616822429905, - "loss": 5.031, - "step": 848 - }, - { - "epoch": 0.48, - "learning_rate": 0.00021939252336448595, - "loss": 4.937, - "step": 849 - }, - { - "epoch": 0.48, - "learning_rate": 0.00021915887850467288, - "loss": 5.8297, - "step": 850 - }, - { - "epoch": 0.48, - "learning_rate": 0.0002189252336448598, - "loss": 4.7925, - "step": 851 - }, - { - "epoch": 0.48, - "learning_rate": 0.0002186915887850467, - "loss": 4.9439, - "step": 852 - }, - { - "epoch": 0.48, - "learning_rate": 0.00021845794392523363, - "loss": 5.0574, - "step": 853 - }, - { - "epoch": 0.48, - "learning_rate": 0.00021822429906542056, - "loss": 4.7829, - "step": 854 - }, - { - "epoch": 0.48, - "learning_rate": 0.00021799065420560748, - "loss": 4.7982, - "step": 855 - }, - { - "epoch": 0.48, - "learning_rate": 0.00021775700934579436, - "loss": 5.0788, - "step": 856 - }, - { - "epoch": 0.48, - "learning_rate": 0.00021752336448598128, - "loss": 4.7978, - "step": 857 - }, - { - "epoch": 0.48, - "learning_rate": 0.0002172897196261682, - "loss": 4.9343, - "step": 858 - }, - { - "epoch": 0.48, - "learning_rate": 0.00021705607476635514, - "loss": 5.4761, - "step": 859 - }, - { - "epoch": 0.48, - "learning_rate": 0.00021682242990654204, - "loss": 5.4207, - "step": 860 - }, - { - "epoch": 0.48, - "learning_rate": 0.00021658878504672894, - "loss": 4.7182, - "step": 861 - }, - { - "epoch": 0.48, - "learning_rate": 0.00021635514018691587, - "loss": 5.0069, - "step": 862 - }, - { - "epoch": 0.48, - "learning_rate": 0.0002161214953271028, - "loss": 5.4644, - "step": 863 - }, - { - "epoch": 0.48, - "learning_rate": 0.0002158878504672897, - "loss": 5.0994, - "step": 864 - }, - { - "epoch": 0.48, - "learning_rate": 0.00021565420560747662, - "loss": 6.0339, - "step": 865 - }, - { - "epoch": 0.49, - "learning_rate": 0.00021542056074766355, - "loss": 4.9237, - "step": 866 - }, - { - "epoch": 0.49, - "learning_rate": 0.00021518691588785047, - "loss": 4.9902, - "step": 867 - }, - { - "epoch": 0.49, - "learning_rate": 0.00021495327102803735, - "loss": 5.1716, - "step": 868 - }, - { - "epoch": 0.49, - "learning_rate": 0.00021471962616822427, - "loss": 4.7076, - "step": 869 - }, - { - "epoch": 0.49, - "learning_rate": 0.0002144859813084112, - "loss": 4.6398, - "step": 870 - }, - { - "epoch": 0.49, - "learning_rate": 0.00021425233644859813, - "loss": 4.9443, - "step": 871 - }, - { - "epoch": 0.49, - "learning_rate": 0.00021401869158878503, - "loss": 5.1819, - "step": 872 - }, - { - "epoch": 0.49, - "learning_rate": 0.00021378504672897193, - "loss": 5.0882, - "step": 873 - }, - { - "epoch": 0.49, - "learning_rate": 0.00021355140186915886, - "loss": 4.8802, - "step": 874 - }, - { - "epoch": 0.49, - "learning_rate": 0.00021331775700934578, - "loss": 4.9635, - "step": 875 - }, - { - "epoch": 0.49, - "learning_rate": 0.00021308411214953268, - "loss": 5.3377, - "step": 876 - }, - { - "epoch": 0.49, - "learning_rate": 0.0002128504672897196, - "loss": 5.2022, - "step": 877 - }, - { - "epoch": 0.49, - "learning_rate": 0.00021261682242990654, - "loss": 4.7017, - "step": 878 - }, - { - "epoch": 0.49, - "learning_rate": 0.00021238317757009347, - "loss": 4.9366, - "step": 879 - }, - { - "epoch": 0.49, - "learning_rate": 0.00021214953271028034, - "loss": 4.8696, - "step": 880 - }, - { - "epoch": 0.49, - "learning_rate": 0.00021191588785046727, - "loss": 5.307, - "step": 881 - }, - { - "epoch": 0.49, - "learning_rate": 0.0002116822429906542, - "loss": 4.9404, - "step": 882 - }, - { - "epoch": 0.49, - "learning_rate": 0.00021144859813084112, - "loss": 5.1903, - "step": 883 - }, - { - "epoch": 0.5, - "learning_rate": 0.00021121495327102802, - "loss": 5.1313, - "step": 884 - }, - { - "epoch": 0.5, - "learning_rate": 0.00021098130841121492, - "loss": 5.414, - "step": 885 - }, - { - "epoch": 0.5, - "learning_rate": 0.00021074766355140185, - "loss": 5.2771, - "step": 886 - }, - { - "epoch": 0.5, - "learning_rate": 0.00021051401869158877, - "loss": 5.2225, - "step": 887 - }, - { - "epoch": 0.5, - "learning_rate": 0.00021028037383177567, - "loss": 4.8134, - "step": 888 - }, - { - "epoch": 0.5, - "learning_rate": 0.0002100467289719626, - "loss": 6.0559, - "step": 889 - }, - { - "epoch": 0.5, - "learning_rate": 0.00020981308411214953, - "loss": 4.9572, - "step": 890 - }, - { - "epoch": 0.5, - "learning_rate": 0.00020957943925233646, - "loss": 4.7058, - "step": 891 - }, - { - "epoch": 0.5, - "learning_rate": 0.00020934579439252333, - "loss": 4.861, - "step": 892 - }, - { - "epoch": 0.5, - "learning_rate": 0.00020911214953271026, - "loss": 5.5404, - "step": 893 - }, - { - "epoch": 0.5, - "learning_rate": 0.00020887850467289718, - "loss": 4.8124, - "step": 894 - }, - { - "epoch": 0.5, - "learning_rate": 0.0002086448598130841, - "loss": 4.9068, - "step": 895 - }, - { - "epoch": 0.5, - "learning_rate": 0.000208411214953271, - "loss": 4.7271, - "step": 896 - }, - { - "epoch": 0.5, - "learning_rate": 0.0002081775700934579, - "loss": 4.6452, - "step": 897 - }, - { - "epoch": 0.5, - "learning_rate": 0.00020794392523364484, - "loss": 5.9051, - "step": 898 - }, - { - "epoch": 0.5, - "learning_rate": 0.00020771028037383176, - "loss": 5.2778, - "step": 899 - }, - { - "epoch": 0.5, - "learning_rate": 0.00020747663551401867, - "loss": 7.3259, - "step": 900 - }, - { - "epoch": 0.51, - "learning_rate": 0.0002072429906542056, - "loss": 4.765, - "step": 901 - }, - { - "epoch": 0.51, - "learning_rate": 0.00020700934579439252, - "loss": 4.7879, - "step": 902 - }, - { - "epoch": 0.51, - "learning_rate": 0.00020677570093457945, - "loss": 5.0419, - "step": 903 - }, - { - "epoch": 0.51, - "learning_rate": 0.00020654205607476632, - "loss": 4.8084, - "step": 904 - }, - { - "epoch": 0.51, - "learning_rate": 0.00020630841121495325, - "loss": 4.9252, - "step": 905 - }, - { - "epoch": 0.51, - "learning_rate": 0.00020607476635514017, - "loss": 5.2601, - "step": 906 - }, - { - "epoch": 0.51, - "learning_rate": 0.0002058411214953271, - "loss": 5.0961, - "step": 907 - }, - { - "epoch": 0.51, - "learning_rate": 0.000205607476635514, - "loss": 4.6176, - "step": 908 - }, - { - "epoch": 0.51, - "learning_rate": 0.0002053738317757009, - "loss": 4.8595, - "step": 909 - }, - { - "epoch": 0.51, - "learning_rate": 0.00020514018691588783, - "loss": 4.7741, - "step": 910 - }, - { - "epoch": 0.51, - "learning_rate": 0.00020490654205607476, - "loss": 5.0659, - "step": 911 - }, - { - "epoch": 0.51, - "learning_rate": 0.00020467289719626166, - "loss": 5.0062, - "step": 912 - }, - { - "epoch": 0.51, - "learning_rate": 0.00020443925233644858, - "loss": 5.1703, - "step": 913 - }, - { - "epoch": 0.51, - "learning_rate": 0.0002042056074766355, - "loss": 4.7855, - "step": 914 - }, - { - "epoch": 0.51, - "learning_rate": 0.00020397196261682244, - "loss": 5.2949, - "step": 915 - }, - { - "epoch": 0.51, - "learning_rate": 0.0002037383177570093, - "loss": 4.9399, - "step": 916 - }, - { - "epoch": 0.51, - "learning_rate": 0.00020350467289719624, - "loss": 4.4994, - "step": 917 - }, - { - "epoch": 0.51, - "learning_rate": 0.00020327102803738316, - "loss": 5.7767, - "step": 918 - }, - { - "epoch": 0.52, - "learning_rate": 0.0002030373831775701, - "loss": 4.9287, - "step": 919 - }, - { - "epoch": 0.52, - "learning_rate": 0.000202803738317757, - "loss": 4.4382, - "step": 920 - }, - { - "epoch": 0.52, - "learning_rate": 0.0002025700934579439, - "loss": 4.5871, - "step": 921 - }, - { - "epoch": 0.52, - "learning_rate": 0.00020233644859813082, - "loss": 4.6164, - "step": 922 - }, - { - "epoch": 0.52, - "learning_rate": 0.00020210280373831775, - "loss": 4.6487, - "step": 923 - }, - { - "epoch": 0.52, - "learning_rate": 0.00020186915887850465, - "loss": 4.9002, - "step": 924 - }, - { - "epoch": 0.52, - "learning_rate": 0.00020163551401869157, - "loss": 4.9545, - "step": 925 - }, - { - "epoch": 0.52, - "learning_rate": 0.0002014018691588785, - "loss": 5.6048, - "step": 926 - }, - { - "epoch": 0.52, - "learning_rate": 0.00020116822429906543, - "loss": 4.53, - "step": 927 - }, - { - "epoch": 0.52, - "learning_rate": 0.0002009345794392523, - "loss": 4.6416, - "step": 928 - }, - { - "epoch": 0.52, - "learning_rate": 0.00020070093457943923, - "loss": 4.6922, - "step": 929 - }, - { - "epoch": 0.52, - "learning_rate": 0.00020046728971962616, - "loss": 5.1571, - "step": 930 - }, - { - "epoch": 0.52, - "learning_rate": 0.00020023364485981308, - "loss": 5.0766, - "step": 931 - }, - { - "epoch": 0.52, - "learning_rate": 0.00019999999999999998, - "loss": 5.1544, - "step": 932 - }, - { - "epoch": 0.52, - "learning_rate": 0.00019976635514018688, - "loss": 5.2045, - "step": 933 - }, - { - "epoch": 0.52, - "learning_rate": 0.0001995327102803738, - "loss": 4.811, - "step": 934 - }, - { - "epoch": 0.52, - "learning_rate": 0.00019929906542056074, - "loss": 5.5609, - "step": 935 - }, - { - "epoch": 0.52, - "learning_rate": 0.00019906542056074764, - "loss": 4.8119, - "step": 936 - }, - { - "epoch": 0.53, - "learning_rate": 0.00019883177570093456, - "loss": 4.868, - "step": 937 - }, - { - "epoch": 0.53, - "learning_rate": 0.0001985981308411215, - "loss": 4.4322, - "step": 938 - }, - { - "epoch": 0.53, - "learning_rate": 0.00019836448598130842, - "loss": 4.5209, - "step": 939 - }, - { - "epoch": 0.53, - "learning_rate": 0.0001981308411214953, - "loss": 4.8857, - "step": 940 - }, - { - "epoch": 0.53, - "learning_rate": 0.00019789719626168222, - "loss": 4.8078, - "step": 941 - }, - { - "epoch": 0.53, - "learning_rate": 0.00019766355140186915, - "loss": 4.7044, - "step": 942 - }, - { - "epoch": 0.53, - "learning_rate": 0.00019742990654205607, - "loss": 5.7056, - "step": 943 - }, - { - "epoch": 0.53, - "learning_rate": 0.00019719626168224297, - "loss": 5.0788, - "step": 944 - }, - { - "epoch": 0.53, - "learning_rate": 0.00019696261682242987, - "loss": 4.9353, - "step": 945 - }, - { - "epoch": 0.53, - "learning_rate": 0.0001967289719626168, - "loss": 4.8164, - "step": 946 - }, - { - "epoch": 0.53, - "learning_rate": 0.00019649532710280373, - "loss": 4.731, - "step": 947 - }, - { - "epoch": 0.53, - "learning_rate": 0.00019626168224299063, - "loss": 4.8129, - "step": 948 - }, - { - "epoch": 0.53, - "learning_rate": 0.00019602803738317755, - "loss": 6.1351, - "step": 949 - }, - { - "epoch": 0.53, - "learning_rate": 0.00019579439252336448, - "loss": 4.363, - "step": 950 - }, - { - "epoch": 0.53, - "learning_rate": 0.0001955607476635514, - "loss": 4.8442, - "step": 951 - }, - { - "epoch": 0.53, - "learning_rate": 0.00019532710280373828, - "loss": 4.8557, - "step": 952 - }, - { - "epoch": 0.53, - "learning_rate": 0.0001950934579439252, - "loss": 5.169, - "step": 953 - }, - { - "epoch": 0.53, - "learning_rate": 0.00019485981308411214, - "loss": 4.4149, - "step": 954 - }, - { - "epoch": 0.54, - "learning_rate": 0.00019462616822429906, - "loss": 4.8122, - "step": 955 - }, - { - "epoch": 0.54, - "learning_rate": 0.00019439252336448596, - "loss": 4.7216, - "step": 956 - }, - { - "epoch": 0.54, - "learning_rate": 0.00019415887850467286, - "loss": 4.8773, - "step": 957 - }, - { - "epoch": 0.54, - "learning_rate": 0.0001939252336448598, - "loss": 5.039, - "step": 958 - }, - { - "epoch": 0.54, - "learning_rate": 0.00019369158878504672, - "loss": 5.3189, - "step": 959 - }, - { - "epoch": 0.54, - "learning_rate": 0.00019345794392523362, - "loss": 4.9981, - "step": 960 - }, - { - "epoch": 0.54, - "learning_rate": 0.00019322429906542055, - "loss": 4.5038, - "step": 961 - }, - { - "epoch": 0.54, - "learning_rate": 0.00019299065420560747, - "loss": 4.7899, - "step": 962 - }, - { - "epoch": 0.54, - "learning_rate": 0.0001927570093457944, - "loss": 5.127, - "step": 963 - }, - { - "epoch": 0.54, - "learning_rate": 0.00019252336448598127, - "loss": 5.4685, - "step": 964 - }, - { - "epoch": 0.54, - "learning_rate": 0.0001922897196261682, - "loss": 4.5723, - "step": 965 - }, - { - "epoch": 0.54, - "learning_rate": 0.00019205607476635513, - "loss": 4.5695, - "step": 966 - }, - { - "epoch": 0.54, - "learning_rate": 0.00019182242990654205, - "loss": 5.0523, - "step": 967 - }, - { - "epoch": 0.54, - "learning_rate": 0.00019158878504672895, - "loss": 4.6699, - "step": 968 - }, - { - "epoch": 0.54, - "learning_rate": 0.00019135514018691585, - "loss": 5.0118, - "step": 969 - }, - { - "epoch": 0.54, - "learning_rate": 0.00019112149532710278, - "loss": 4.5245, - "step": 970 - }, - { - "epoch": 0.54, - "learning_rate": 0.0001908878504672897, - "loss": 4.5746, - "step": 971 - }, - { - "epoch": 0.54, - "learning_rate": 0.0001906542056074766, - "loss": 4.7121, - "step": 972 - }, - { - "epoch": 0.55, - "learning_rate": 0.00019042056074766354, - "loss": 4.7673, - "step": 973 - }, - { - "epoch": 0.55, - "learning_rate": 0.00019018691588785046, - "loss": 5.4171, - "step": 974 - }, - { - "epoch": 0.55, - "learning_rate": 0.0001899532710280374, - "loss": 4.7849, - "step": 975 - }, - { - "epoch": 0.55, - "learning_rate": 0.00018971962616822426, - "loss": 4.885, - "step": 976 - }, - { - "epoch": 0.55, - "learning_rate": 0.0001894859813084112, - "loss": 5.6078, - "step": 977 - }, - { - "epoch": 0.55, - "learning_rate": 0.00018925233644859812, - "loss": 4.8714, - "step": 978 - }, - { - "epoch": 0.55, - "learning_rate": 0.00018901869158878504, - "loss": 4.8016, - "step": 979 - }, - { - "epoch": 0.55, - "learning_rate": 0.00018878504672897195, - "loss": 4.5862, - "step": 980 - }, - { - "epoch": 0.55, - "learning_rate": 0.00018855140186915885, - "loss": 4.269, - "step": 981 - }, - { - "epoch": 0.55, - "learning_rate": 0.00018831775700934577, - "loss": 4.3237, - "step": 982 - }, - { - "epoch": 0.55, - "learning_rate": 0.0001880841121495327, - "loss": 4.916, - "step": 983 - }, - { - "epoch": 0.55, - "learning_rate": 0.0001878504672897196, - "loss": 5.238, - "step": 984 - }, - { - "epoch": 0.55, - "learning_rate": 0.00018761682242990653, - "loss": 4.4024, - "step": 985 - }, - { - "epoch": 0.55, - "learning_rate": 0.00018738317757009345, - "loss": 4.9999, - "step": 986 - }, - { - "epoch": 0.55, - "learning_rate": 0.00018714953271028038, - "loss": 4.7281, - "step": 987 - }, - { - "epoch": 0.55, - "learning_rate": 0.00018691588785046725, - "loss": 4.6421, - "step": 988 - }, - { - "epoch": 0.55, - "learning_rate": 0.00018668224299065418, - "loss": 4.9122, - "step": 989 - }, - { - "epoch": 0.55, - "learning_rate": 0.0001864485981308411, - "loss": 4.4793, - "step": 990 - }, - { - "epoch": 0.56, - "learning_rate": 0.00018621495327102804, - "loss": 5.2538, - "step": 991 - }, - { - "epoch": 0.56, - "learning_rate": 0.00018598130841121494, - "loss": 5.0608, - "step": 992 - }, - { - "epoch": 0.56, - "learning_rate": 0.00018574766355140184, - "loss": 5.2613, - "step": 993 - }, - { - "epoch": 0.56, - "learning_rate": 0.00018551401869158876, - "loss": 5.7212, - "step": 994 - }, - { - "epoch": 0.56, - "learning_rate": 0.0001852803738317757, - "loss": 4.695, - "step": 995 - }, - { - "epoch": 0.56, - "learning_rate": 0.0001850467289719626, - "loss": 4.4236, - "step": 996 - }, - { - "epoch": 0.56, - "learning_rate": 0.00018481308411214952, - "loss": 5.0098, - "step": 997 - }, - { - "epoch": 0.56, - "learning_rate": 0.00018457943925233644, - "loss": 5.2913, - "step": 998 - }, - { - "epoch": 0.56, - "learning_rate": 0.00018434579439252337, - "loss": 4.9825, - "step": 999 - }, - { - "epoch": 0.56, - "learning_rate": 0.00018411214953271024, - "loss": 4.5835, - "step": 1000 - }, - { - "epoch": 0.56, - "eval_loss": 5.410597324371338, - "eval_runtime": 965.7729, - "eval_samples_per_second": 2.736, - "eval_steps_per_second": 0.343, - "eval_wer": 1.8471241570805237, - "step": 1000 - }, - { - "epoch": 0.56, - "learning_rate": 0.00018387850467289717, - "loss": 5.295, - "step": 1001 - }, - { - "epoch": 0.56, - "learning_rate": 0.0001836448598130841, - "loss": 4.6254, - "step": 1002 - }, - { - "epoch": 0.56, - "learning_rate": 0.00018341121495327103, - "loss": 4.825, - "step": 1003 - }, - { - "epoch": 0.56, - "learning_rate": 0.00018317757009345793, - "loss": 5.1412, - "step": 1004 - }, - { - "epoch": 0.56, - "learning_rate": 0.00018294392523364483, - "loss": 4.8463, - "step": 1005 - }, - { - "epoch": 0.56, - "learning_rate": 0.00018271028037383175, - "loss": 4.7254, - "step": 1006 - }, - { - "epoch": 0.56, - "learning_rate": 0.00018247663551401868, - "loss": 5.6083, - "step": 1007 - }, - { - "epoch": 0.57, - "learning_rate": 0.00018224299065420558, - "loss": 5.0419, - "step": 1008 - }, - { - "epoch": 0.57, - "learning_rate": 0.0001820093457943925, - "loss": 4.8468, - "step": 1009 - }, - { - "epoch": 0.57, - "learning_rate": 0.00018177570093457944, - "loss": 4.4734, - "step": 1010 - }, - { - "epoch": 0.57, - "learning_rate": 0.00018154205607476636, - "loss": 4.8522, - "step": 1011 - }, - { - "epoch": 0.57, - "learning_rate": 0.00018130841121495324, - "loss": 4.7889, - "step": 1012 - }, - { - "epoch": 0.57, - "learning_rate": 0.00018107476635514016, - "loss": 4.8581, - "step": 1013 - }, - { - "epoch": 0.57, - "learning_rate": 0.0001808411214953271, - "loss": 5.084, - "step": 1014 - }, - { - "epoch": 0.57, - "learning_rate": 0.00018060747663551402, - "loss": 5.7797, - "step": 1015 - }, - { - "epoch": 0.57, - "learning_rate": 0.00018037383177570092, - "loss": 4.9604, - "step": 1016 - }, - { - "epoch": 0.57, - "learning_rate": 0.00018014018691588782, - "loss": 4.7936, - "step": 1017 - }, - { - "epoch": 0.57, - "learning_rate": 0.00017990654205607474, - "loss": 4.7201, - "step": 1018 - }, - { - "epoch": 0.57, - "learning_rate": 0.00017967289719626167, - "loss": 5.5697, - "step": 1019 - }, - { - "epoch": 0.57, - "learning_rate": 0.00017943925233644857, - "loss": 5.1766, - "step": 1020 - }, - { - "epoch": 0.57, - "learning_rate": 0.0001792056074766355, - "loss": 5.1022, - "step": 1021 - }, - { - "epoch": 0.57, - "learning_rate": 0.00017897196261682243, - "loss": 4.9122, - "step": 1022 - }, - { - "epoch": 0.57, - "learning_rate": 0.00017873831775700935, - "loss": 4.8288, - "step": 1023 - }, - { - "epoch": 0.57, - "learning_rate": 0.00017850467289719623, - "loss": 5.0913, - "step": 1024 - }, - { - "epoch": 0.57, - "learning_rate": 0.00017827102803738315, - "loss": 4.9974, - "step": 1025 - }, - { - "epoch": 0.58, - "learning_rate": 0.00017803738317757008, - "loss": 4.7814, - "step": 1026 - }, - { - "epoch": 0.58, - "learning_rate": 0.000177803738317757, - "loss": 4.8031, - "step": 1027 - }, - { - "epoch": 0.58, - "learning_rate": 0.0001775700934579439, - "loss": 5.5837, - "step": 1028 - }, - { - "epoch": 0.58, - "learning_rate": 0.0001773364485981308, - "loss": 5.1744, - "step": 1029 - }, - { - "epoch": 0.58, - "learning_rate": 0.00017710280373831773, - "loss": 4.9649, - "step": 1030 - }, - { - "epoch": 0.58, - "learning_rate": 0.00017686915887850466, - "loss": 4.8444, - "step": 1031 - }, - { - "epoch": 0.58, - "learning_rate": 0.00017663551401869156, - "loss": 4.8534, - "step": 1032 - }, - { - "epoch": 0.58, - "learning_rate": 0.0001764018691588785, - "loss": 4.8322, - "step": 1033 - }, - { - "epoch": 0.58, - "learning_rate": 0.00017616822429906542, - "loss": 4.5182, - "step": 1034 - }, - { - "epoch": 0.58, - "learning_rate": 0.00017593457943925234, - "loss": 4.7217, - "step": 1035 - }, - { - "epoch": 0.58, - "learning_rate": 0.00017570093457943922, - "loss": 5.0039, - "step": 1036 - }, - { - "epoch": 0.58, - "learning_rate": 0.00017546728971962614, - "loss": 4.793, - "step": 1037 - }, - { - "epoch": 0.58, - "learning_rate": 0.00017523364485981307, - "loss": 4.8074, - "step": 1038 - }, - { - "epoch": 0.58, - "learning_rate": 0.000175, - "loss": 4.6361, - "step": 1039 - }, - { - "epoch": 0.58, - "learning_rate": 0.0001747663551401869, - "loss": 5.7843, - "step": 1040 - }, - { - "epoch": 0.58, - "learning_rate": 0.0001745327102803738, - "loss": 5.2601, - "step": 1041 - }, - { - "epoch": 0.58, - "learning_rate": 0.00017429906542056073, - "loss": 4.8, - "step": 1042 - }, - { - "epoch": 0.58, - "learning_rate": 0.00017406542056074765, - "loss": 5.39, - "step": 1043 - }, - { - "epoch": 0.59, - "learning_rate": 0.00017383177570093455, - "loss": 4.7599, - "step": 1044 - }, - { - "epoch": 0.59, - "learning_rate": 0.00017359813084112148, - "loss": 5.3108, - "step": 1045 - }, - { - "epoch": 0.59, - "learning_rate": 0.0001733644859813084, - "loss": 4.7564, - "step": 1046 - }, - { - "epoch": 0.59, - "learning_rate": 0.00017313084112149533, - "loss": 5.168, - "step": 1047 - }, - { - "epoch": 0.59, - "learning_rate": 0.0001728971962616822, - "loss": 4.5637, - "step": 1048 - }, - { - "epoch": 0.59, - "learning_rate": 0.00017266355140186913, - "loss": 5.2341, - "step": 1049 - }, - { - "epoch": 0.59, - "learning_rate": 0.00017242990654205606, - "loss": 5.6461, - "step": 1050 - }, - { - "epoch": 0.59, - "learning_rate": 0.000172196261682243, - "loss": 6.0758, - "step": 1051 - }, - { - "epoch": 0.59, - "learning_rate": 0.0001719626168224299, - "loss": 4.6076, - "step": 1052 - }, - { - "epoch": 0.59, - "learning_rate": 0.0001717289719626168, - "loss": 4.7063, - "step": 1053 - }, - { - "epoch": 0.59, - "learning_rate": 0.00017149532710280372, - "loss": 4.5084, - "step": 1054 - }, - { - "epoch": 0.59, - "learning_rate": 0.00017126168224299064, - "loss": 4.7528, - "step": 1055 - }, - { - "epoch": 0.59, - "learning_rate": 0.00017102803738317754, - "loss": 4.6317, - "step": 1056 - }, - { - "epoch": 0.59, - "learning_rate": 0.00017079439252336447, - "loss": 5.2335, - "step": 1057 - }, - { - "epoch": 0.59, - "learning_rate": 0.0001705607476635514, - "loss": 4.738, - "step": 1058 - }, - { - "epoch": 0.59, - "learning_rate": 0.00017032710280373833, - "loss": 5.386, - "step": 1059 - }, - { - "epoch": 0.59, - "learning_rate": 0.0001700934579439252, - "loss": 4.5184, - "step": 1060 - }, - { - "epoch": 0.59, - "learning_rate": 0.00016985981308411213, - "loss": 4.9902, - "step": 1061 - }, - { - "epoch": 0.6, - "learning_rate": 0.00016962616822429905, - "loss": 4.6804, - "step": 1062 - }, - { - "epoch": 0.6, - "learning_rate": 0.00016939252336448598, - "loss": 5.2153, - "step": 1063 - }, - { - "epoch": 0.6, - "learning_rate": 0.00016915887850467288, - "loss": 4.3548, - "step": 1064 - }, - { - "epoch": 0.6, - "learning_rate": 0.00016892523364485978, - "loss": 4.8669, - "step": 1065 - }, - { - "epoch": 0.6, - "learning_rate": 0.0001686915887850467, - "loss": 4.2073, - "step": 1066 - }, - { - "epoch": 0.6, - "learning_rate": 0.00016845794392523363, - "loss": 4.7525, - "step": 1067 - }, - { - "epoch": 0.6, - "learning_rate": 0.00016822429906542053, - "loss": 4.8545, - "step": 1068 - }, - { - "epoch": 0.6, - "learning_rate": 0.00016799065420560746, - "loss": 4.8557, - "step": 1069 - }, - { - "epoch": 0.6, - "learning_rate": 0.0001677570093457944, - "loss": 4.6872, - "step": 1070 - }, - { - "epoch": 0.6, - "learning_rate": 0.00016752336448598132, - "loss": 4.6, - "step": 1071 - }, - { - "epoch": 0.6, - "learning_rate": 0.0001672897196261682, - "loss": 4.4089, - "step": 1072 - }, - { - "epoch": 0.6, - "learning_rate": 0.00016705607476635512, - "loss": 4.6911, - "step": 1073 - }, - { - "epoch": 0.6, - "learning_rate": 0.00016682242990654204, - "loss": 4.8998, - "step": 1074 - }, - { - "epoch": 0.6, - "learning_rate": 0.00016658878504672897, - "loss": 5.007, - "step": 1075 - }, - { - "epoch": 0.6, - "learning_rate": 0.00016635514018691587, - "loss": 5.0844, - "step": 1076 - }, - { - "epoch": 0.6, - "learning_rate": 0.00016612149532710277, - "loss": 4.6756, - "step": 1077 - }, - { - "epoch": 0.6, - "learning_rate": 0.0001658878504672897, - "loss": 4.6908, - "step": 1078 - }, - { - "epoch": 0.6, - "learning_rate": 0.00016565420560747662, - "loss": 4.6606, - "step": 1079 - }, - { - "epoch": 0.61, - "learning_rate": 0.00016542056074766352, - "loss": 5.0731, - "step": 1080 - }, - { - "epoch": 0.61, - "learning_rate": 0.00016518691588785045, - "loss": 4.9576, - "step": 1081 - }, - { - "epoch": 0.61, - "learning_rate": 0.00016495327102803738, - "loss": 5.0817, - "step": 1082 - }, - { - "epoch": 0.61, - "learning_rate": 0.0001647196261682243, - "loss": 4.3867, - "step": 1083 - }, - { - "epoch": 0.61, - "learning_rate": 0.00016448598130841118, - "loss": 4.7917, - "step": 1084 - }, - { - "epoch": 0.61, - "learning_rate": 0.0001642523364485981, - "loss": 4.579, - "step": 1085 - }, - { - "epoch": 0.61, - "learning_rate": 0.00016401869158878503, - "loss": 5.0803, - "step": 1086 - }, - { - "epoch": 0.61, - "learning_rate": 0.00016378504672897196, - "loss": 4.8967, - "step": 1087 - }, - { - "epoch": 0.61, - "learning_rate": 0.00016355140186915886, - "loss": 5.1008, - "step": 1088 - }, - { - "epoch": 0.61, - "learning_rate": 0.00016331775700934576, - "loss": 5.0885, - "step": 1089 - }, - { - "epoch": 0.61, - "learning_rate": 0.0001630841121495327, - "loss": 4.4591, - "step": 1090 - }, - { - "epoch": 0.61, - "learning_rate": 0.00016285046728971962, - "loss": 4.6559, - "step": 1091 - }, - { - "epoch": 0.61, - "learning_rate": 0.00016261682242990652, - "loss": 4.7686, - "step": 1092 - }, - { - "epoch": 0.61, - "learning_rate": 0.00016238317757009344, - "loss": 5.0468, - "step": 1093 - }, - { - "epoch": 0.61, - "learning_rate": 0.00016214953271028037, - "loss": 5.0606, - "step": 1094 - }, - { - "epoch": 0.61, - "learning_rate": 0.0001619158878504673, - "loss": 4.85, - "step": 1095 - }, - { - "epoch": 0.61, - "learning_rate": 0.00016168224299065417, - "loss": 5.7264, - "step": 1096 - }, - { - "epoch": 0.61, - "learning_rate": 0.0001614485981308411, - "loss": 5.1977, - "step": 1097 - }, - { - "epoch": 0.62, - "learning_rate": 0.00016121495327102802, - "loss": 5.7266, - "step": 1098 - }, - { - "epoch": 0.62, - "learning_rate": 0.00016098130841121495, - "loss": 4.8753, - "step": 1099 - }, - { - "epoch": 0.62, - "learning_rate": 0.00016074766355140185, - "loss": 5.4758, - "step": 1100 - }, - { - "epoch": 0.62, - "learning_rate": 0.00016051401869158875, - "loss": 4.5965, - "step": 1101 - }, - { - "epoch": 0.62, - "learning_rate": 0.00016028037383177568, - "loss": 4.7508, - "step": 1102 - }, - { - "epoch": 0.62, - "learning_rate": 0.0001600467289719626, - "loss": 4.7677, - "step": 1103 - }, - { - "epoch": 0.62, - "learning_rate": 0.0001598130841121495, - "loss": 4.483, - "step": 1104 - }, - { - "epoch": 0.62, - "learning_rate": 0.00015957943925233643, - "loss": 4.5089, - "step": 1105 - }, - { - "epoch": 0.62, - "learning_rate": 0.00015934579439252336, - "loss": 4.39, - "step": 1106 - }, - { - "epoch": 0.62, - "learning_rate": 0.0001591121495327103, - "loss": 4.8008, - "step": 1107 - }, - { - "epoch": 0.62, - "learning_rate": 0.00015887850467289716, - "loss": 4.4434, - "step": 1108 - }, - { - "epoch": 0.62, - "learning_rate": 0.0001586448598130841, - "loss": 4.649, - "step": 1109 - }, - { - "epoch": 0.62, - "learning_rate": 0.00015841121495327101, - "loss": 4.9156, - "step": 1110 - }, - { - "epoch": 0.62, - "learning_rate": 0.00015817757009345794, - "loss": 4.7616, - "step": 1111 - }, - { - "epoch": 0.62, - "learning_rate": 0.00015794392523364484, - "loss": 4.8166, - "step": 1112 - }, - { - "epoch": 0.62, - "learning_rate": 0.00015771028037383174, - "loss": 5.0782, - "step": 1113 - }, - { - "epoch": 0.62, - "learning_rate": 0.00015747663551401867, - "loss": 5.1502, - "step": 1114 - }, - { - "epoch": 0.62, - "learning_rate": 0.0001572429906542056, - "loss": 4.9949, - "step": 1115 - }, - { - "epoch": 0.63, - "learning_rate": 0.0001570093457943925, - "loss": 4.5315, - "step": 1116 - }, - { - "epoch": 0.63, - "learning_rate": 0.00015677570093457942, - "loss": 4.7678, - "step": 1117 - }, - { - "epoch": 0.63, - "learning_rate": 0.00015654205607476635, - "loss": 5.0043, - "step": 1118 - }, - { - "epoch": 0.63, - "learning_rate": 0.00015630841121495328, - "loss": 4.6046, - "step": 1119 - }, - { - "epoch": 0.63, - "learning_rate": 0.00015607476635514015, - "loss": 4.8182, - "step": 1120 - }, - { - "epoch": 0.63, - "learning_rate": 0.00015584112149532708, - "loss": 4.6555, - "step": 1121 - }, - { - "epoch": 0.63, - "learning_rate": 0.000155607476635514, - "loss": 4.7102, - "step": 1122 - }, - { - "epoch": 0.63, - "learning_rate": 0.00015537383177570093, - "loss": 4.6659, - "step": 1123 - }, - { - "epoch": 0.63, - "learning_rate": 0.00015514018691588783, - "loss": 4.4469, - "step": 1124 - }, - { - "epoch": 0.63, - "learning_rate": 0.00015490654205607473, - "loss": 5.221, - "step": 1125 - }, - { - "epoch": 0.63, - "learning_rate": 0.00015467289719626166, - "loss": 5.0621, - "step": 1126 - }, - { - "epoch": 0.63, - "learning_rate": 0.0001544392523364486, - "loss": 4.4351, - "step": 1127 - }, - { - "epoch": 0.63, - "learning_rate": 0.0001542056074766355, - "loss": 5.1425, - "step": 1128 - }, - { - "epoch": 0.63, - "learning_rate": 0.00015397196261682241, - "loss": 4.2831, - "step": 1129 - }, - { - "epoch": 0.63, - "learning_rate": 0.00015373831775700934, - "loss": 4.8776, - "step": 1130 - }, - { - "epoch": 0.63, - "learning_rate": 0.00015350467289719627, - "loss": 4.7883, - "step": 1131 - }, - { - "epoch": 0.63, - "learning_rate": 0.00015327102803738314, - "loss": 4.5857, - "step": 1132 - }, - { - "epoch": 0.64, - "learning_rate": 0.00015303738317757007, - "loss": 4.4969, - "step": 1133 - }, - { - "epoch": 0.64, - "learning_rate": 0.000152803738317757, - "loss": 4.6381, - "step": 1134 - }, - { - "epoch": 0.64, - "learning_rate": 0.00015257009345794392, - "loss": 4.9661, - "step": 1135 - }, - { - "epoch": 0.64, - "learning_rate": 0.00015233644859813082, - "loss": 4.4861, - "step": 1136 - }, - { - "epoch": 0.64, - "learning_rate": 0.00015210280373831772, - "loss": 5.4212, - "step": 1137 - }, - { - "epoch": 0.64, - "learning_rate": 0.00015186915887850465, - "loss": 4.6819, - "step": 1138 - }, - { - "epoch": 0.64, - "learning_rate": 0.00015163551401869158, - "loss": 4.4423, - "step": 1139 - }, - { - "epoch": 0.64, - "learning_rate": 0.00015140186915887848, - "loss": 5.239, - "step": 1140 - }, - { - "epoch": 0.64, - "learning_rate": 0.0001511682242990654, - "loss": 4.5624, - "step": 1141 - }, - { - "epoch": 0.64, - "learning_rate": 0.00015093457943925233, - "loss": 5.0742, - "step": 1142 - }, - { - "epoch": 0.64, - "learning_rate": 0.00015070093457943926, - "loss": 5.5032, - "step": 1143 - }, - { - "epoch": 0.64, - "learning_rate": 0.00015046728971962613, - "loss": 4.8996, - "step": 1144 - }, - { - "epoch": 0.64, - "learning_rate": 0.00015023364485981306, - "loss": 4.4813, - "step": 1145 - }, - { - "epoch": 0.64, - "learning_rate": 0.00015, - "loss": 4.8392, - "step": 1146 - }, - { - "epoch": 0.64, - "learning_rate": 0.00014976635514018691, - "loss": 4.8239, - "step": 1147 - }, - { - "epoch": 0.64, - "learning_rate": 0.00014953271028037381, - "loss": 4.9859, - "step": 1148 - }, - { - "epoch": 0.64, - "learning_rate": 0.00014929906542056074, - "loss": 5.3989, - "step": 1149 - }, - { - "epoch": 0.64, - "learning_rate": 0.00014906542056074764, - "loss": 4.6126, - "step": 1150 - }, - { - "epoch": 0.65, - "learning_rate": 0.00014883177570093457, - "loss": 4.6598, - "step": 1151 - }, - { - "epoch": 0.65, - "learning_rate": 0.00014859813084112147, - "loss": 5.1152, - "step": 1152 - }, - { - "epoch": 0.65, - "learning_rate": 0.0001483644859813084, - "loss": 4.7685, - "step": 1153 - }, - { - "epoch": 0.65, - "learning_rate": 0.00014813084112149532, - "loss": 4.7041, - "step": 1154 - }, - { - "epoch": 0.65, - "learning_rate": 0.00014789719626168225, - "loss": 4.6951, - "step": 1155 - }, - { - "epoch": 0.65, - "learning_rate": 0.00014766355140186915, - "loss": 4.8288, - "step": 1156 - }, - { - "epoch": 0.65, - "learning_rate": 0.00014742990654205608, - "loss": 4.4557, - "step": 1157 - }, - { - "epoch": 0.65, - "learning_rate": 0.00014719626168224298, - "loss": 5.1399, - "step": 1158 - }, - { - "epoch": 0.65, - "learning_rate": 0.0001469626168224299, - "loss": 4.4466, - "step": 1159 - }, - { - "epoch": 0.65, - "learning_rate": 0.0001467289719626168, - "loss": 4.7221, - "step": 1160 - }, - { - "epoch": 0.65, - "learning_rate": 0.00014649532710280373, - "loss": 4.6735, - "step": 1161 - }, - { - "epoch": 0.65, - "learning_rate": 0.00014626168224299063, - "loss": 4.5965, - "step": 1162 - }, - { - "epoch": 0.65, - "learning_rate": 0.00014602803738317756, - "loss": 4.8673, - "step": 1163 - }, - { - "epoch": 0.65, - "learning_rate": 0.00014579439252336446, - "loss": 4.4736, - "step": 1164 - }, - { - "epoch": 0.65, - "learning_rate": 0.0001455607476635514, - "loss": 4.5029, - "step": 1165 - }, - { - "epoch": 0.65, - "learning_rate": 0.00014532710280373831, - "loss": 4.8494, - "step": 1166 - }, - { - "epoch": 0.65, - "learning_rate": 0.00014509345794392524, - "loss": 4.7616, - "step": 1167 - }, - { - "epoch": 0.65, - "learning_rate": 0.00014485981308411214, - "loss": 4.4232, - "step": 1168 - }, - { - "epoch": 0.66, - "learning_rate": 0.00014462616822429907, - "loss": 4.6749, - "step": 1169 - }, - { - "epoch": 0.66, - "learning_rate": 0.00014439252336448597, - "loss": 4.9082, - "step": 1170 - }, - { - "epoch": 0.66, - "learning_rate": 0.0001441588785046729, - "loss": 4.8845, - "step": 1171 - }, - { - "epoch": 0.66, - "learning_rate": 0.0001439252336448598, - "loss": 4.4151, - "step": 1172 - }, - { - "epoch": 0.66, - "learning_rate": 0.00014369158878504672, - "loss": 4.849, - "step": 1173 - }, - { - "epoch": 0.66, - "learning_rate": 0.00014345794392523362, - "loss": 4.4945, - "step": 1174 - }, - { - "epoch": 0.66, - "learning_rate": 0.00014322429906542055, - "loss": 4.5113, - "step": 1175 - }, - { - "epoch": 0.66, - "learning_rate": 0.00014299065420560745, - "loss": 4.7946, - "step": 1176 - }, - { - "epoch": 0.66, - "learning_rate": 0.00014275700934579438, - "loss": 4.9471, - "step": 1177 - }, - { - "epoch": 0.66, - "learning_rate": 0.0001425233644859813, - "loss": 4.8622, - "step": 1178 - }, - { - "epoch": 0.66, - "learning_rate": 0.00014228971962616823, - "loss": 4.4475, - "step": 1179 - }, - { - "epoch": 0.66, - "learning_rate": 0.00014205607476635513, - "loss": 4.6637, - "step": 1180 - }, - { - "epoch": 0.66, - "learning_rate": 0.00014182242990654206, - "loss": 4.4574, - "step": 1181 - }, - { - "epoch": 0.66, - "learning_rate": 0.00014158878504672896, - "loss": 5.1628, - "step": 1182 - }, - { - "epoch": 0.66, - "learning_rate": 0.00014135514018691589, - "loss": 4.5182, - "step": 1183 - }, - { - "epoch": 0.66, - "learning_rate": 0.00014112149532710279, - "loss": 4.5129, - "step": 1184 - }, - { - "epoch": 0.66, - "learning_rate": 0.0001408878504672897, - "loss": 5.1486, - "step": 1185 - }, - { - "epoch": 0.66, - "learning_rate": 0.0001406542056074766, - "loss": 4.9022, - "step": 1186 - }, - { - "epoch": 0.67, - "learning_rate": 0.00014042056074766354, - "loss": 5.0993, - "step": 1187 - }, - { - "epoch": 0.67, - "learning_rate": 0.00014018691588785044, - "loss": 4.6432, - "step": 1188 - }, - { - "epoch": 0.67, - "learning_rate": 0.00013995327102803737, - "loss": 4.6778, - "step": 1189 - }, - { - "epoch": 0.67, - "learning_rate": 0.0001397196261682243, - "loss": 4.7929, - "step": 1190 - }, - { - "epoch": 0.67, - "learning_rate": 0.00013948598130841122, - "loss": 4.8013, - "step": 1191 - }, - { - "epoch": 0.67, - "learning_rate": 0.00013925233644859812, - "loss": 4.8677, - "step": 1192 - }, - { - "epoch": 0.67, - "learning_rate": 0.00013901869158878505, - "loss": 5.5184, - "step": 1193 - }, - { - "epoch": 0.67, - "learning_rate": 0.00013878504672897195, - "loss": 4.7271, - "step": 1194 - }, - { - "epoch": 0.67, - "learning_rate": 0.00013855140186915888, - "loss": 5.0457, - "step": 1195 - }, - { - "epoch": 0.67, - "learning_rate": 0.00013831775700934578, - "loss": 4.5563, - "step": 1196 - }, - { - "epoch": 0.67, - "learning_rate": 0.0001380841121495327, - "loss": 4.4929, - "step": 1197 - }, - { - "epoch": 0.67, - "learning_rate": 0.0001378504672897196, - "loss": 4.8084, - "step": 1198 - }, - { - "epoch": 0.67, - "learning_rate": 0.00013761682242990653, - "loss": 4.8272, - "step": 1199 - }, - { - "epoch": 0.67, - "learning_rate": 0.00013738317757009343, - "loss": 4.3984, - "step": 1200 - }, - { - "epoch": 0.67, - "learning_rate": 0.00013714953271028036, - "loss": 4.8269, - "step": 1201 - }, - { - "epoch": 0.67, - "learning_rate": 0.00013691588785046729, - "loss": 4.7607, - "step": 1202 - }, - { - "epoch": 0.67, - "learning_rate": 0.0001366822429906542, - "loss": 4.4335, - "step": 1203 - }, - { - "epoch": 0.67, - "learning_rate": 0.0001364485981308411, - "loss": 4.3747, - "step": 1204 - }, - { - "epoch": 0.68, - "learning_rate": 0.00013621495327102804, - "loss": 4.3018, - "step": 1205 - }, - { - "epoch": 0.68, - "learning_rate": 0.00013598130841121494, - "loss": 4.7087, - "step": 1206 - }, - { - "epoch": 0.68, - "learning_rate": 0.00013574766355140187, - "loss": 5.3858, - "step": 1207 - }, - { - "epoch": 0.68, - "learning_rate": 0.00013551401869158877, - "loss": 4.5392, - "step": 1208 - }, - { - "epoch": 0.68, - "learning_rate": 0.0001352803738317757, - "loss": 4.8387, - "step": 1209 - }, - { - "epoch": 0.68, - "learning_rate": 0.0001350467289719626, - "loss": 4.5507, - "step": 1210 - }, - { - "epoch": 0.68, - "learning_rate": 0.00013481308411214952, - "loss": 4.837, - "step": 1211 - }, - { - "epoch": 0.68, - "learning_rate": 0.00013457943925233642, - "loss": 5.2707, - "step": 1212 - }, - { - "epoch": 0.68, - "learning_rate": 0.00013434579439252335, - "loss": 4.72, - "step": 1213 - }, - { - "epoch": 0.68, - "learning_rate": 0.00013411214953271028, - "loss": 4.4775, - "step": 1214 - }, - { - "epoch": 0.68, - "learning_rate": 0.0001338785046728972, - "loss": 4.5884, - "step": 1215 - }, - { - "epoch": 0.68, - "learning_rate": 0.0001336448598130841, - "loss": 4.8038, - "step": 1216 - }, - { - "epoch": 0.68, - "learning_rate": 0.00013341121495327103, - "loss": 4.7295, - "step": 1217 - }, - { - "epoch": 0.68, - "learning_rate": 0.00013317757009345793, - "loss": 4.2418, - "step": 1218 - }, - { - "epoch": 0.68, - "learning_rate": 0.00013294392523364486, - "loss": 4.3116, - "step": 1219 - }, - { - "epoch": 0.68, - "learning_rate": 0.00013271028037383176, - "loss": 4.8137, - "step": 1220 - }, - { - "epoch": 0.68, - "learning_rate": 0.00013247663551401869, - "loss": 4.4608, - "step": 1221 - }, - { - "epoch": 0.68, - "learning_rate": 0.00013224299065420559, - "loss": 4.3006, - "step": 1222 - }, - { - "epoch": 0.69, - "learning_rate": 0.0001320093457943925, - "loss": 4.6606, - "step": 1223 - }, - { - "epoch": 0.69, - "learning_rate": 0.0001317757009345794, - "loss": 5.075, - "step": 1224 - }, - { - "epoch": 0.69, - "learning_rate": 0.00013154205607476634, - "loss": 5.2593, - "step": 1225 - }, - { - "epoch": 0.69, - "learning_rate": 0.00013130841121495327, - "loss": 4.6197, - "step": 1226 - }, - { - "epoch": 0.69, - "learning_rate": 0.0001310747663551402, - "loss": 4.4475, - "step": 1227 - }, - { - "epoch": 0.69, - "learning_rate": 0.0001308411214953271, - "loss": 4.4669, - "step": 1228 - }, - { - "epoch": 0.69, - "learning_rate": 0.00013060747663551402, - "loss": 4.3557, - "step": 1229 - }, - { - "epoch": 0.69, - "learning_rate": 0.00013037383177570092, - "loss": 4.934, - "step": 1230 - }, - { - "epoch": 0.69, - "learning_rate": 0.00013014018691588785, - "loss": 4.7828, - "step": 1231 - }, - { - "epoch": 0.69, - "learning_rate": 0.00012990654205607475, - "loss": 5.1254, - "step": 1232 - }, - { - "epoch": 0.69, - "learning_rate": 0.00012967289719626168, - "loss": 4.7875, - "step": 1233 - }, - { - "epoch": 0.69, - "learning_rate": 0.00012943925233644858, - "loss": 4.4031, - "step": 1234 - }, - { - "epoch": 0.69, - "learning_rate": 0.0001292056074766355, - "loss": 4.8587, - "step": 1235 - }, - { - "epoch": 0.69, - "learning_rate": 0.0001289719626168224, - "loss": 4.6119, - "step": 1236 - }, - { - "epoch": 0.69, - "learning_rate": 0.00012873831775700933, - "loss": 4.6509, - "step": 1237 - }, - { - "epoch": 0.69, - "learning_rate": 0.00012850467289719626, - "loss": 4.3835, - "step": 1238 - }, - { - "epoch": 0.69, - "learning_rate": 0.00012827102803738318, - "loss": 4.9575, - "step": 1239 - }, - { - "epoch": 0.7, - "learning_rate": 0.00012803738317757008, - "loss": 5.0068, - "step": 1240 - }, - { - "epoch": 0.7, - "learning_rate": 0.000127803738317757, - "loss": 4.6508, - "step": 1241 - }, - { - "epoch": 0.7, - "learning_rate": 0.0001275700934579439, - "loss": 4.9891, - "step": 1242 - }, - { - "epoch": 0.7, - "learning_rate": 0.00012733644859813084, - "loss": 5.044, - "step": 1243 - }, - { - "epoch": 0.7, - "learning_rate": 0.00012710280373831774, - "loss": 4.5446, - "step": 1244 - }, - { - "epoch": 0.7, - "learning_rate": 0.00012686915887850467, - "loss": 4.2537, - "step": 1245 - }, - { - "epoch": 0.7, - "learning_rate": 0.00012663551401869157, - "loss": 4.8145, - "step": 1246 - }, - { - "epoch": 0.7, - "learning_rate": 0.0001264018691588785, - "loss": 4.827, - "step": 1247 - }, - { - "epoch": 0.7, - "learning_rate": 0.0001261682242990654, - "loss": 4.7165, - "step": 1248 - }, - { - "epoch": 0.7, - "learning_rate": 0.00012593457943925232, - "loss": 4.753, - "step": 1249 - }, - { - "epoch": 0.7, - "learning_rate": 0.00012570093457943925, - "loss": 4.9449, - "step": 1250 - }, - { - "epoch": 0.7, - "learning_rate": 0.00012546728971962618, - "loss": 4.856, - "step": 1251 - }, - { - "epoch": 0.7, - "learning_rate": 0.00012523364485981308, - "loss": 4.8752, - "step": 1252 - }, - { - "epoch": 0.7, - "learning_rate": 0.000125, - "loss": 4.8258, - "step": 1253 - }, - { - "epoch": 0.7, - "learning_rate": 0.0001247663551401869, - "loss": 4.8502, - "step": 1254 - }, - { - "epoch": 0.7, - "learning_rate": 0.00012453271028037383, - "loss": 5.0675, - "step": 1255 - }, - { - "epoch": 0.7, - "learning_rate": 0.00012429906542056073, - "loss": 4.4932, - "step": 1256 - }, - { - "epoch": 0.7, - "learning_rate": 0.00012406542056074766, - "loss": 4.4368, - "step": 1257 - }, - { - "epoch": 0.71, - "learning_rate": 0.00012383177570093456, - "loss": 4.3429, - "step": 1258 - }, - { - "epoch": 0.71, - "learning_rate": 0.00012359813084112148, - "loss": 4.6, - "step": 1259 - }, - { - "epoch": 0.71, - "learning_rate": 0.00012336448598130838, - "loss": 4.865, - "step": 1260 - }, - { - "epoch": 0.71, - "learning_rate": 0.0001231308411214953, - "loss": 4.3833, - "step": 1261 - }, - { - "epoch": 0.71, - "learning_rate": 0.00012289719626168224, - "loss": 4.8291, - "step": 1262 - }, - { - "epoch": 0.71, - "learning_rate": 0.00012266355140186917, - "loss": 4.8238, - "step": 1263 - }, - { - "epoch": 0.71, - "learning_rate": 0.00012242990654205607, - "loss": 4.4584, - "step": 1264 - }, - { - "epoch": 0.71, - "learning_rate": 0.000122196261682243, - "loss": 5.0505, - "step": 1265 - }, - { - "epoch": 0.71, - "learning_rate": 0.0001219626168224299, - "loss": 4.7391, - "step": 1266 - }, - { - "epoch": 0.71, - "learning_rate": 0.00012172897196261682, - "loss": 4.8012, - "step": 1267 - }, - { - "epoch": 0.71, - "learning_rate": 0.00012149532710280372, - "loss": 4.5231, - "step": 1268 - }, - { - "epoch": 0.71, - "learning_rate": 0.00012126168224299065, - "loss": 4.6187, - "step": 1269 - }, - { - "epoch": 0.71, - "learning_rate": 0.00012102803738317756, - "loss": 4.5015, - "step": 1270 - }, - { - "epoch": 0.71, - "learning_rate": 0.00012079439252336448, - "loss": 4.7924, - "step": 1271 - }, - { - "epoch": 0.71, - "learning_rate": 0.00012056074766355139, - "loss": 4.6223, - "step": 1272 - }, - { - "epoch": 0.71, - "learning_rate": 0.00012032710280373832, - "loss": 4.8234, - "step": 1273 - }, - { - "epoch": 0.71, - "learning_rate": 0.00012009345794392522, - "loss": 4.4664, - "step": 1274 - }, - { - "epoch": 0.71, - "learning_rate": 0.00011985981308411214, - "loss": 4.5185, - "step": 1275 - }, - { - "epoch": 0.72, - "learning_rate": 0.00011962616822429906, - "loss": 4.8474, - "step": 1276 - }, - { - "epoch": 0.72, - "learning_rate": 0.00011939252336448597, - "loss": 4.6835, - "step": 1277 - }, - { - "epoch": 0.72, - "learning_rate": 0.00011915887850467288, - "loss": 4.7298, - "step": 1278 - }, - { - "epoch": 0.72, - "learning_rate": 0.00011892523364485981, - "loss": 4.7948, - "step": 1279 - }, - { - "epoch": 0.72, - "learning_rate": 0.00011869158878504671, - "loss": 4.7252, - "step": 1280 - }, - { - "epoch": 0.72, - "learning_rate": 0.00011845794392523364, - "loss": 4.5798, - "step": 1281 - }, - { - "epoch": 0.72, - "learning_rate": 0.00011822429906542055, - "loss": 4.5494, - "step": 1282 - }, - { - "epoch": 0.72, - "learning_rate": 0.00011799065420560747, - "loss": 4.7939, - "step": 1283 - }, - { - "epoch": 0.72, - "learning_rate": 0.00011775700934579438, - "loss": 4.4271, - "step": 1284 - }, - { - "epoch": 0.72, - "learning_rate": 0.0001175233644859813, - "loss": 4.5041, - "step": 1285 - }, - { - "epoch": 0.72, - "learning_rate": 0.0001172897196261682, - "loss": 4.6633, - "step": 1286 - }, - { - "epoch": 0.72, - "learning_rate": 0.00011705607476635513, - "loss": 4.7079, - "step": 1287 - }, - { - "epoch": 0.72, - "learning_rate": 0.00011682242990654205, - "loss": 4.4732, - "step": 1288 - }, - { - "epoch": 0.72, - "learning_rate": 0.00011658878504672896, - "loss": 4.5347, - "step": 1289 - }, - { - "epoch": 0.72, - "learning_rate": 0.00011635514018691587, - "loss": 4.4767, - "step": 1290 - }, - { - "epoch": 0.72, - "learning_rate": 0.0001161214953271028, - "loss": 4.7735, - "step": 1291 - }, - { - "epoch": 0.72, - "learning_rate": 0.0001158878504672897, - "loss": 5.2044, - "step": 1292 - }, - { - "epoch": 0.72, - "learning_rate": 0.00011565420560747663, - "loss": 6.1335, - "step": 1293 - }, - { - "epoch": 0.73, - "learning_rate": 0.00011542056074766354, - "loss": 4.3757, - "step": 1294 - }, - { - "epoch": 0.73, - "learning_rate": 0.00011518691588785046, - "loss": 4.2918, - "step": 1295 - }, - { - "epoch": 0.73, - "learning_rate": 0.00011495327102803737, - "loss": 4.2071, - "step": 1296 - }, - { - "epoch": 0.73, - "learning_rate": 0.0001147196261682243, - "loss": 4.2355, - "step": 1297 - }, - { - "epoch": 0.73, - "learning_rate": 0.0001144859813084112, - "loss": 4.0042, - "step": 1298 - }, - { - "epoch": 0.73, - "learning_rate": 0.00011425233644859812, - "loss": 5.7548, - "step": 1299 - }, - { - "epoch": 0.73, - "learning_rate": 0.00011401869158878504, - "loss": 4.3358, - "step": 1300 - }, - { - "epoch": 0.73, - "learning_rate": 0.00011378504672897195, - "loss": 5.1223, - "step": 1301 - }, - { - "epoch": 0.73, - "learning_rate": 0.00011355140186915887, - "loss": 4.8915, - "step": 1302 - }, - { - "epoch": 0.73, - "learning_rate": 0.00011331775700934579, - "loss": 4.5869, - "step": 1303 - }, - { - "epoch": 0.73, - "learning_rate": 0.00011308411214953269, - "loss": 4.5804, - "step": 1304 - }, - { - "epoch": 0.73, - "learning_rate": 0.00011285046728971962, - "loss": 4.5697, - "step": 1305 - }, - { - "epoch": 0.73, - "learning_rate": 0.00011261682242990653, - "loss": 4.5615, - "step": 1306 - }, - { - "epoch": 0.73, - "learning_rate": 0.00011238317757009345, - "loss": 4.5079, - "step": 1307 - }, - { - "epoch": 0.73, - "learning_rate": 0.00011214953271028036, - "loss": 4.2725, - "step": 1308 - }, - { - "epoch": 0.73, - "learning_rate": 0.00011191588785046729, - "loss": 4.7465, - "step": 1309 - }, - { - "epoch": 0.73, - "learning_rate": 0.00011168224299065419, - "loss": 4.4138, - "step": 1310 - }, - { - "epoch": 0.73, - "learning_rate": 0.00011144859813084112, - "loss": 4.3324, - "step": 1311 - }, - { - "epoch": 0.74, - "learning_rate": 0.00011121495327102803, - "loss": 4.7058, - "step": 1312 - }, - { - "epoch": 0.74, - "learning_rate": 0.00011098130841121494, - "loss": 4.4527, - "step": 1313 - }, - { - "epoch": 0.74, - "learning_rate": 0.00011074766355140186, - "loss": 4.362, - "step": 1314 - }, - { - "epoch": 0.74, - "learning_rate": 0.00011051401869158878, - "loss": 4.8449, - "step": 1315 - }, - { - "epoch": 0.74, - "learning_rate": 0.00011028037383177568, - "loss": 4.712, - "step": 1316 - }, - { - "epoch": 0.74, - "learning_rate": 0.00011004672897196261, - "loss": 4.3717, - "step": 1317 - }, - { - "epoch": 0.74, - "learning_rate": 0.00010981308411214952, - "loss": 5.2638, - "step": 1318 - }, - { - "epoch": 0.74, - "learning_rate": 0.00010957943925233644, - "loss": 4.5045, - "step": 1319 - }, - { - "epoch": 0.74, - "learning_rate": 0.00010934579439252335, - "loss": 4.1619, - "step": 1320 - }, - { - "epoch": 0.74, - "learning_rate": 0.00010911214953271028, - "loss": 4.258, - "step": 1321 - }, - { - "epoch": 0.74, - "learning_rate": 0.00010887850467289718, - "loss": 4.429, - "step": 1322 - }, - { - "epoch": 0.74, - "learning_rate": 0.0001086448598130841, - "loss": 4.4848, - "step": 1323 - }, - { - "epoch": 0.74, - "learning_rate": 0.00010841121495327102, - "loss": 4.4302, - "step": 1324 - }, - { - "epoch": 0.74, - "learning_rate": 0.00010817757009345793, - "loss": 4.698, - "step": 1325 - }, - { - "epoch": 0.74, - "learning_rate": 0.00010794392523364485, - "loss": 4.2455, - "step": 1326 - }, - { - "epoch": 0.74, - "learning_rate": 0.00010771028037383177, - "loss": 4.2599, - "step": 1327 - }, - { - "epoch": 0.74, - "learning_rate": 0.00010747663551401867, - "loss": 4.5794, - "step": 1328 - }, - { - "epoch": 0.74, - "learning_rate": 0.0001072429906542056, - "loss": 4.8533, - "step": 1329 - }, - { - "epoch": 0.75, - "learning_rate": 0.00010700934579439251, - "loss": 5.1244, - "step": 1330 - }, - { - "epoch": 0.75, - "learning_rate": 0.00010677570093457943, - "loss": 4.5778, - "step": 1331 - }, - { - "epoch": 0.75, - "learning_rate": 0.00010654205607476634, - "loss": 4.8532, - "step": 1332 - }, - { - "epoch": 0.75, - "learning_rate": 0.00010630841121495327, - "loss": 4.5821, - "step": 1333 - }, - { - "epoch": 0.75, - "learning_rate": 0.00010607476635514017, - "loss": 4.7136, - "step": 1334 - }, - { - "epoch": 0.75, - "learning_rate": 0.0001058411214953271, - "loss": 4.3164, - "step": 1335 - }, - { - "epoch": 0.75, - "learning_rate": 0.00010560747663551401, - "loss": 4.6951, - "step": 1336 - }, - { - "epoch": 0.75, - "learning_rate": 0.00010537383177570092, - "loss": 4.6578, - "step": 1337 - }, - { - "epoch": 0.75, - "learning_rate": 0.00010514018691588784, - "loss": 4.74, - "step": 1338 - }, - { - "epoch": 0.75, - "learning_rate": 0.00010490654205607476, - "loss": 4.818, - "step": 1339 - }, - { - "epoch": 0.75, - "learning_rate": 0.00010467289719626166, - "loss": 5.0079, - "step": 1340 - }, - { - "epoch": 0.75, - "learning_rate": 0.00010443925233644859, - "loss": 4.8286, - "step": 1341 - }, - { - "epoch": 0.75, - "learning_rate": 0.0001042056074766355, - "loss": 4.6649, - "step": 1342 - }, - { - "epoch": 0.75, - "learning_rate": 0.00010397196261682242, - "loss": 4.8123, - "step": 1343 - }, - { - "epoch": 0.75, - "learning_rate": 0.00010373831775700933, - "loss": 5.1213, - "step": 1344 - }, - { - "epoch": 0.75, - "learning_rate": 0.00010350467289719626, - "loss": 4.9489, - "step": 1345 - }, - { - "epoch": 0.75, - "learning_rate": 0.00010327102803738316, - "loss": 4.7282, - "step": 1346 - }, - { - "epoch": 0.76, - "learning_rate": 0.00010303738317757009, - "loss": 6.3758, - "step": 1347 - }, - { - "epoch": 0.76, - "learning_rate": 0.000102803738317757, - "loss": 4.4462, - "step": 1348 - }, - { - "epoch": 0.76, - "learning_rate": 0.00010257009345794391, - "loss": 4.8114, - "step": 1349 - }, - { - "epoch": 0.76, - "learning_rate": 0.00010233644859813083, - "loss": 4.7315, - "step": 1350 - }, - { - "epoch": 0.76, - "learning_rate": 0.00010210280373831776, - "loss": 4.8988, - "step": 1351 - }, - { - "epoch": 0.76, - "learning_rate": 0.00010186915887850466, - "loss": 4.7733, - "step": 1352 - }, - { - "epoch": 0.76, - "learning_rate": 0.00010163551401869158, - "loss": 4.6099, - "step": 1353 - }, - { - "epoch": 0.76, - "learning_rate": 0.0001014018691588785, - "loss": 4.9684, - "step": 1354 - }, - { - "epoch": 0.76, - "learning_rate": 0.00010116822429906541, - "loss": 4.4543, - "step": 1355 - }, - { - "epoch": 0.76, - "learning_rate": 0.00010093457943925232, - "loss": 4.7961, - "step": 1356 - }, - { - "epoch": 0.76, - "learning_rate": 0.00010070093457943925, - "loss": 4.2971, - "step": 1357 - }, - { - "epoch": 0.76, - "learning_rate": 0.00010046728971962615, - "loss": 4.7841, - "step": 1358 - }, - { - "epoch": 0.76, - "learning_rate": 0.00010023364485981308, - "loss": 4.8907, - "step": 1359 - }, - { - "epoch": 0.76, - "learning_rate": 9.999999999999999e-05, - "loss": 5.1793, - "step": 1360 - }, - { - "epoch": 0.76, - "learning_rate": 9.97663551401869e-05, - "loss": 4.5062, - "step": 1361 - }, - { - "epoch": 0.76, - "learning_rate": 9.953271028037382e-05, - "loss": 4.5876, - "step": 1362 - }, - { - "epoch": 0.76, - "learning_rate": 9.929906542056075e-05, - "loss": 4.4811, - "step": 1363 - }, - { - "epoch": 0.76, - "learning_rate": 9.906542056074765e-05, - "loss": 4.9852, - "step": 1364 - }, - { - "epoch": 0.77, - "learning_rate": 9.883177570093457e-05, - "loss": 4.6072, - "step": 1365 - }, - { - "epoch": 0.77, - "learning_rate": 9.859813084112149e-05, - "loss": 4.2691, - "step": 1366 - }, - { - "epoch": 0.77, - "learning_rate": 9.83644859813084e-05, - "loss": 4.7263, - "step": 1367 - }, - { - "epoch": 0.77, - "learning_rate": 9.813084112149531e-05, - "loss": 4.3674, - "step": 1368 - }, - { - "epoch": 0.77, - "learning_rate": 9.789719626168224e-05, - "loss": 4.6531, - "step": 1369 - }, - { - "epoch": 0.77, - "learning_rate": 9.766355140186914e-05, - "loss": 4.6705, - "step": 1370 - }, - { - "epoch": 0.77, - "learning_rate": 9.742990654205607e-05, - "loss": 5.0784, - "step": 1371 - }, - { - "epoch": 0.77, - "learning_rate": 9.719626168224298e-05, - "loss": 4.2388, - "step": 1372 - }, - { - "epoch": 0.77, - "learning_rate": 9.69626168224299e-05, - "loss": 4.5843, - "step": 1373 - }, - { - "epoch": 0.77, - "learning_rate": 9.672897196261681e-05, - "loss": 4.7276, - "step": 1374 - }, - { - "epoch": 0.77, - "learning_rate": 9.649532710280374e-05, - "loss": 4.3655, - "step": 1375 - }, - { - "epoch": 0.77, - "learning_rate": 9.626168224299064e-05, - "loss": 4.3753, - "step": 1376 - }, - { - "epoch": 0.77, - "learning_rate": 9.602803738317756e-05, - "loss": 4.6729, - "step": 1377 - }, - { - "epoch": 0.77, - "learning_rate": 9.579439252336448e-05, - "loss": 4.4771, - "step": 1378 - }, - { - "epoch": 0.77, - "learning_rate": 9.556074766355139e-05, - "loss": 4.4406, - "step": 1379 - }, - { - "epoch": 0.77, - "learning_rate": 9.53271028037383e-05, - "loss": 4.411, - "step": 1380 - }, - { - "epoch": 0.77, - "learning_rate": 9.509345794392523e-05, - "loss": 4.1252, - "step": 1381 - }, - { - "epoch": 0.77, - "learning_rate": 9.485981308411213e-05, - "loss": 4.5836, - "step": 1382 - }, - { - "epoch": 0.78, - "learning_rate": 9.462616822429906e-05, - "loss": 4.4135, - "step": 1383 - }, - { - "epoch": 0.78, - "learning_rate": 9.439252336448597e-05, - "loss": 5.0311, - "step": 1384 - }, - { - "epoch": 0.78, - "learning_rate": 9.415887850467289e-05, - "loss": 5.1987, - "step": 1385 - }, - { - "epoch": 0.78, - "learning_rate": 9.39252336448598e-05, - "loss": 4.7665, - "step": 1386 - }, - { - "epoch": 0.78, - "learning_rate": 9.369158878504673e-05, - "loss": 4.8896, - "step": 1387 - }, - { - "epoch": 0.78, - "learning_rate": 9.345794392523363e-05, - "loss": 4.5977, - "step": 1388 - }, - { - "epoch": 0.78, - "learning_rate": 9.322429906542055e-05, - "loss": 4.4149, - "step": 1389 - }, - { - "epoch": 0.78, - "learning_rate": 9.299065420560747e-05, - "loss": 4.8341, - "step": 1390 - }, - { - "epoch": 0.78, - "learning_rate": 9.275700934579438e-05, - "loss": 4.5592, - "step": 1391 - }, - { - "epoch": 0.78, - "learning_rate": 9.25233644859813e-05, - "loss": 4.6854, - "step": 1392 - }, - { - "epoch": 0.78, - "learning_rate": 9.228971962616822e-05, - "loss": 4.4339, - "step": 1393 - }, - { - "epoch": 0.78, - "learning_rate": 9.205607476635512e-05, - "loss": 4.6722, - "step": 1394 - }, - { - "epoch": 0.78, - "learning_rate": 9.182242990654205e-05, - "loss": 5.0204, - "step": 1395 - }, - { - "epoch": 0.78, - "learning_rate": 9.158878504672896e-05, - "loss": 4.5043, - "step": 1396 - }, - { - "epoch": 0.78, - "learning_rate": 9.135514018691588e-05, - "loss": 4.7303, - "step": 1397 - }, - { - "epoch": 0.78, - "learning_rate": 9.112149532710279e-05, - "loss": 4.5108, - "step": 1398 - }, - { - "epoch": 0.78, - "learning_rate": 9.088785046728972e-05, - "loss": 4.6094, - "step": 1399 - }, - { - "epoch": 0.78, - "learning_rate": 9.065420560747662e-05, - "loss": 4.7445, - "step": 1400 - }, - { - "epoch": 0.79, - "learning_rate": 9.042056074766354e-05, - "loss": 4.3028, - "step": 1401 - }, - { - "epoch": 0.79, - "learning_rate": 9.018691588785046e-05, - "loss": 4.7941, - "step": 1402 - }, - { - "epoch": 0.79, - "learning_rate": 8.995327102803737e-05, - "loss": 4.3965, - "step": 1403 - }, - { - "epoch": 0.79, - "learning_rate": 8.971962616822429e-05, - "loss": 4.5629, - "step": 1404 - }, - { - "epoch": 0.79, - "learning_rate": 8.948598130841121e-05, - "loss": 4.342, - "step": 1405 - }, - { - "epoch": 0.79, - "learning_rate": 8.925233644859811e-05, - "loss": 5.1776, - "step": 1406 - }, - { - "epoch": 0.79, - "learning_rate": 8.901869158878504e-05, - "loss": 4.5056, - "step": 1407 - }, - { - "epoch": 0.79, - "learning_rate": 8.878504672897195e-05, - "loss": 4.4902, - "step": 1408 - }, - { - "epoch": 0.79, - "learning_rate": 8.855140186915887e-05, - "loss": 4.421, - "step": 1409 - }, - { - "epoch": 0.79, - "learning_rate": 8.831775700934578e-05, - "loss": 4.4359, - "step": 1410 - }, - { - "epoch": 0.79, - "learning_rate": 8.808411214953271e-05, - "loss": 4.2247, - "step": 1411 - }, - { - "epoch": 0.79, - "learning_rate": 8.785046728971961e-05, - "loss": 4.2549, - "step": 1412 - }, - { - "epoch": 0.79, - "learning_rate": 8.761682242990654e-05, - "loss": 4.6357, - "step": 1413 - }, - { - "epoch": 0.79, - "learning_rate": 8.738317757009345e-05, - "loss": 5.0585, - "step": 1414 - }, - { - "epoch": 0.79, - "learning_rate": 8.714953271028036e-05, - "loss": 4.5275, - "step": 1415 - }, - { - "epoch": 0.79, - "learning_rate": 8.691588785046728e-05, - "loss": 4.6826, - "step": 1416 - }, - { - "epoch": 0.79, - "learning_rate": 8.66822429906542e-05, - "loss": 4.6638, - "step": 1417 - }, - { - "epoch": 0.79, - "learning_rate": 8.64485981308411e-05, - "loss": 4.7662, - "step": 1418 - }, - { - "epoch": 0.8, - "learning_rate": 8.621495327102803e-05, - "loss": 4.7948, - "step": 1419 - }, - { - "epoch": 0.8, - "learning_rate": 8.598130841121494e-05, - "loss": 4.4067, - "step": 1420 - }, - { - "epoch": 0.8, - "learning_rate": 8.574766355140186e-05, - "loss": 4.5369, - "step": 1421 - }, - { - "epoch": 0.8, - "learning_rate": 8.551401869158877e-05, - "loss": 4.7997, - "step": 1422 - }, - { - "epoch": 0.8, - "learning_rate": 8.52803738317757e-05, - "loss": 4.3982, - "step": 1423 - }, - { - "epoch": 0.8, - "learning_rate": 8.50467289719626e-05, - "loss": 4.581, - "step": 1424 - }, - { - "epoch": 0.8, - "learning_rate": 8.481308411214953e-05, - "loss": 5.0492, - "step": 1425 - }, - { - "epoch": 0.8, - "learning_rate": 8.457943925233644e-05, - "loss": 4.5919, - "step": 1426 - }, - { - "epoch": 0.8, - "learning_rate": 8.434579439252335e-05, - "loss": 4.2841, - "step": 1427 - }, - { - "epoch": 0.8, - "learning_rate": 8.411214953271027e-05, - "loss": 4.5089, - "step": 1428 - }, - { - "epoch": 0.8, - "learning_rate": 8.38785046728972e-05, - "loss": 4.9026, - "step": 1429 - }, - { - "epoch": 0.8, - "learning_rate": 8.36448598130841e-05, - "loss": 4.894, - "step": 1430 - }, - { - "epoch": 0.8, - "learning_rate": 8.341121495327102e-05, - "loss": 4.7668, - "step": 1431 - }, - { - "epoch": 0.8, - "learning_rate": 8.317757009345794e-05, - "loss": 4.5004, - "step": 1432 - }, - { - "epoch": 0.8, - "learning_rate": 8.294392523364485e-05, - "loss": 5.0434, - "step": 1433 - }, - { - "epoch": 0.8, - "learning_rate": 8.271028037383176e-05, - "loss": 4.2249, - "step": 1434 - }, - { - "epoch": 0.8, - "learning_rate": 8.247663551401869e-05, - "loss": 4.4143, - "step": 1435 - }, - { - "epoch": 0.8, - "learning_rate": 8.224299065420559e-05, - "loss": 4.5195, - "step": 1436 - }, - { - "epoch": 0.81, - "learning_rate": 8.200934579439252e-05, - "loss": 4.6534, - "step": 1437 - }, - { - "epoch": 0.81, - "learning_rate": 8.177570093457943e-05, - "loss": 4.6119, - "step": 1438 - }, - { - "epoch": 0.81, - "learning_rate": 8.154205607476634e-05, - "loss": 4.7469, - "step": 1439 - }, - { - "epoch": 0.81, - "learning_rate": 8.130841121495326e-05, - "loss": 4.5503, - "step": 1440 - }, - { - "epoch": 0.81, - "learning_rate": 8.107476635514018e-05, - "loss": 5.1977, - "step": 1441 - }, - { - "epoch": 0.81, - "learning_rate": 8.084112149532708e-05, - "loss": 4.3533, - "step": 1442 - }, - { - "epoch": 0.81, - "learning_rate": 8.060747663551401e-05, - "loss": 4.3092, - "step": 1443 - }, - { - "epoch": 0.81, - "learning_rate": 8.037383177570093e-05, - "loss": 4.4248, - "step": 1444 - }, - { - "epoch": 0.81, - "learning_rate": 8.014018691588784e-05, - "loss": 4.5158, - "step": 1445 - }, - { - "epoch": 0.81, - "learning_rate": 7.990654205607475e-05, - "loss": 5.0453, - "step": 1446 - }, - { - "epoch": 0.81, - "learning_rate": 7.967289719626168e-05, - "loss": 4.5608, - "step": 1447 - }, - { - "epoch": 0.81, - "learning_rate": 7.943925233644858e-05, - "loss": 4.7935, - "step": 1448 - }, - { - "epoch": 0.81, - "learning_rate": 7.920560747663551e-05, - "loss": 5.0555, - "step": 1449 - }, - { - "epoch": 0.81, - "learning_rate": 7.897196261682242e-05, - "loss": 4.4385, - "step": 1450 - }, - { - "epoch": 0.81, - "learning_rate": 7.873831775700933e-05, - "loss": 4.4105, - "step": 1451 - }, - { - "epoch": 0.81, - "learning_rate": 7.850467289719625e-05, - "loss": 4.5924, - "step": 1452 - }, - { - "epoch": 0.81, - "learning_rate": 7.827102803738318e-05, - "loss": 4.6003, - "step": 1453 - }, - { - "epoch": 0.82, - "learning_rate": 7.803738317757008e-05, - "loss": 4.3011, - "step": 1454 - }, - { - "epoch": 0.82, - "learning_rate": 7.7803738317757e-05, - "loss": 4.6797, - "step": 1455 - }, - { - "epoch": 0.82, - "learning_rate": 7.757009345794392e-05, - "loss": 4.5271, - "step": 1456 - }, - { - "epoch": 0.82, - "learning_rate": 7.733644859813083e-05, - "loss": 4.941, - "step": 1457 - }, - { - "epoch": 0.82, - "learning_rate": 7.710280373831774e-05, - "loss": 4.6652, - "step": 1458 - }, - { - "epoch": 0.82, - "learning_rate": 7.686915887850467e-05, - "loss": 4.4565, - "step": 1459 - }, - { - "epoch": 0.82, - "learning_rate": 7.663551401869157e-05, - "loss": 5.0369, - "step": 1460 - }, - { - "epoch": 0.82, - "learning_rate": 7.64018691588785e-05, - "loss": 4.5899, - "step": 1461 - }, - { - "epoch": 0.82, - "learning_rate": 7.616822429906541e-05, - "loss": 4.697, - "step": 1462 - }, - { - "epoch": 0.82, - "learning_rate": 7.593457943925233e-05, - "loss": 4.3769, - "step": 1463 - }, - { - "epoch": 0.82, - "learning_rate": 7.570093457943924e-05, - "loss": 4.5193, - "step": 1464 - }, - { - "epoch": 0.82, - "learning_rate": 7.546728971962617e-05, - "loss": 4.7798, - "step": 1465 - }, - { - "epoch": 0.82, - "learning_rate": 7.523364485981307e-05, - "loss": 4.2362, - "step": 1466 - }, - { - "epoch": 0.82, - "learning_rate": 7.5e-05, - "loss": 4.467, - "step": 1467 - }, - { - "epoch": 0.82, - "learning_rate": 7.476635514018691e-05, - "loss": 4.6296, - "step": 1468 - }, - { - "epoch": 0.82, - "learning_rate": 7.453271028037382e-05, - "loss": 4.2283, - "step": 1469 - }, - { - "epoch": 0.82, - "learning_rate": 7.429906542056073e-05, - "loss": 4.1876, - "step": 1470 - }, - { - "epoch": 0.82, - "learning_rate": 7.406542056074766e-05, - "loss": 4.5927, - "step": 1471 - }, - { - "epoch": 0.83, - "learning_rate": 7.383177570093458e-05, - "loss": 4.2189, - "step": 1472 - }, - { - "epoch": 0.83, - "learning_rate": 7.359813084112149e-05, - "loss": 4.3703, - "step": 1473 - }, - { - "epoch": 0.83, - "learning_rate": 7.33644859813084e-05, - "loss": 4.4537, - "step": 1474 - }, - { - "epoch": 0.83, - "learning_rate": 7.313084112149532e-05, - "loss": 4.6724, - "step": 1475 - }, - { - "epoch": 0.83, - "learning_rate": 7.289719626168223e-05, - "loss": 4.6432, - "step": 1476 - }, - { - "epoch": 0.83, - "learning_rate": 7.266355140186916e-05, - "loss": 4.5162, - "step": 1477 - }, - { - "epoch": 0.83, - "learning_rate": 7.242990654205607e-05, - "loss": 4.0905, - "step": 1478 - }, - { - "epoch": 0.83, - "learning_rate": 7.219626168224298e-05, - "loss": 4.4936, - "step": 1479 - }, - { - "epoch": 0.83, - "learning_rate": 7.19626168224299e-05, - "loss": 4.3097, - "step": 1480 - }, - { - "epoch": 0.83, - "learning_rate": 7.172897196261681e-05, - "loss": 4.5015, - "step": 1481 - }, - { - "epoch": 0.83, - "learning_rate": 7.149532710280372e-05, - "loss": 5.1634, - "step": 1482 - }, - { - "epoch": 0.83, - "learning_rate": 7.126168224299065e-05, - "loss": 4.4873, - "step": 1483 - }, - { - "epoch": 0.83, - "learning_rate": 7.102803738317757e-05, - "loss": 4.2809, - "step": 1484 - }, - { - "epoch": 0.83, - "learning_rate": 7.079439252336448e-05, - "loss": 4.4835, - "step": 1485 - }, - { - "epoch": 0.83, - "learning_rate": 7.056074766355139e-05, - "loss": 4.6959, - "step": 1486 - }, - { - "epoch": 0.83, - "learning_rate": 7.03271028037383e-05, - "loss": 4.5338, - "step": 1487 - }, - { - "epoch": 0.83, - "learning_rate": 7.009345794392522e-05, - "loss": 4.6072, - "step": 1488 - }, - { - "epoch": 0.83, - "learning_rate": 6.985981308411215e-05, - "loss": 4.6397, - "step": 1489 - }, - { - "epoch": 0.84, - "learning_rate": 6.962616822429906e-05, - "loss": 4.354, - "step": 1490 - }, - { - "epoch": 0.84, - "learning_rate": 6.939252336448597e-05, - "loss": 5.3741, - "step": 1491 - }, - { - "epoch": 0.84, - "learning_rate": 6.915887850467289e-05, - "loss": 4.5531, - "step": 1492 - }, - { - "epoch": 0.84, - "learning_rate": 6.89252336448598e-05, - "loss": 4.0635, - "step": 1493 - }, - { - "epoch": 0.84, - "learning_rate": 6.869158878504672e-05, - "loss": 4.3559, - "step": 1494 - }, - { - "epoch": 0.84, - "learning_rate": 6.845794392523364e-05, - "loss": 4.4344, - "step": 1495 - }, - { - "epoch": 0.84, - "learning_rate": 6.822429906542056e-05, - "loss": 5.8473, - "step": 1496 - }, - { - "epoch": 0.84, - "learning_rate": 6.799065420560747e-05, - "loss": 4.7009, - "step": 1497 - }, - { - "epoch": 0.84, - "learning_rate": 6.775700934579438e-05, - "loss": 4.8013, - "step": 1498 - }, - { - "epoch": 0.84, - "learning_rate": 6.75233644859813e-05, - "loss": 4.2303, - "step": 1499 - }, - { - "epoch": 0.84, - "learning_rate": 6.728971962616821e-05, - "loss": 4.584, - "step": 1500 - }, - { - "epoch": 0.84, - "eval_loss": 4.745861530303955, - "eval_runtime": 966.758, - "eval_samples_per_second": 2.733, - "eval_steps_per_second": 0.342, - "eval_wer": 1.976279254264181, - "step": 1500 - }, - { - "epoch": 0.84, - "learning_rate": 6.705607476635514e-05, - "loss": 4.4993, - "step": 1501 - }, - { - "epoch": 0.84, - "learning_rate": 6.682242990654205e-05, - "loss": 4.4733, - "step": 1502 - }, - { - "epoch": 0.84, - "learning_rate": 6.658878504672897e-05, - "loss": 4.8485, - "step": 1503 - }, - { - "epoch": 0.84, - "learning_rate": 6.635514018691588e-05, - "loss": 4.5777, - "step": 1504 - }, - { - "epoch": 0.84, - "learning_rate": 6.612149532710279e-05, - "loss": 4.6994, - "step": 1505 - }, - { - "epoch": 0.84, - "learning_rate": 6.58878504672897e-05, - "loss": 4.4798, - "step": 1506 - }, - { - "epoch": 0.84, - "learning_rate": 6.565420560747663e-05, - "loss": 4.4221, - "step": 1507 - }, - { - "epoch": 0.85, - "learning_rate": 6.542056074766355e-05, - "loss": 4.3991, - "step": 1508 - }, - { - "epoch": 0.85, - "learning_rate": 6.518691588785046e-05, - "loss": 4.5131, - "step": 1509 - }, - { - "epoch": 0.85, - "learning_rate": 6.495327102803737e-05, - "loss": 4.5206, - "step": 1510 - }, - { - "epoch": 0.85, - "learning_rate": 6.471962616822429e-05, - "loss": 4.2224, - "step": 1511 - }, - { - "epoch": 0.85, - "learning_rate": 6.44859813084112e-05, - "loss": 4.4976, - "step": 1512 - }, - { - "epoch": 0.85, - "learning_rate": 6.425233644859813e-05, - "loss": 4.1285, - "step": 1513 - }, - { - "epoch": 0.85, - "learning_rate": 6.401869158878504e-05, - "loss": 4.3656, - "step": 1514 - }, - { - "epoch": 0.85, - "learning_rate": 6.378504672897196e-05, - "loss": 4.4229, - "step": 1515 - }, - { - "epoch": 0.85, - "learning_rate": 6.355140186915887e-05, - "loss": 4.9607, - "step": 1516 - }, - { - "epoch": 0.85, - "learning_rate": 6.331775700934578e-05, - "loss": 4.32, - "step": 1517 - }, - { - "epoch": 0.85, - "learning_rate": 6.30841121495327e-05, - "loss": 4.8036, - "step": 1518 - }, - { - "epoch": 0.85, - "learning_rate": 6.285046728971962e-05, - "loss": 4.6417, - "step": 1519 - }, - { - "epoch": 0.85, - "learning_rate": 6.261682242990654e-05, - "loss": 4.5848, - "step": 1520 - }, - { - "epoch": 0.85, - "learning_rate": 6.238317757009345e-05, - "loss": 4.5558, - "step": 1521 - }, - { - "epoch": 0.85, - "learning_rate": 6.214953271028036e-05, - "loss": 4.7014, - "step": 1522 - }, - { - "epoch": 0.85, - "learning_rate": 6.191588785046728e-05, - "loss": 5.1218, - "step": 1523 - }, - { - "epoch": 0.85, - "learning_rate": 6.168224299065419e-05, - "loss": 4.2249, - "step": 1524 - }, - { - "epoch": 0.85, - "learning_rate": 6.144859813084112e-05, - "loss": 4.2695, - "step": 1525 - }, - { - "epoch": 0.86, - "learning_rate": 6.121495327102803e-05, - "loss": 4.2161, - "step": 1526 - }, - { - "epoch": 0.86, - "learning_rate": 6.098130841121495e-05, - "loss": 4.3758, - "step": 1527 - }, - { - "epoch": 0.86, - "learning_rate": 6.074766355140186e-05, - "loss": 4.37, - "step": 1528 - }, - { - "epoch": 0.86, - "learning_rate": 6.051401869158878e-05, - "loss": 4.2458, - "step": 1529 - }, - { - "epoch": 0.86, - "learning_rate": 6.0280373831775694e-05, - "loss": 4.439, - "step": 1530 - }, - { - "epoch": 0.86, - "learning_rate": 6.004672897196261e-05, - "loss": 4.399, - "step": 1531 - }, - { - "epoch": 0.86, - "learning_rate": 5.981308411214953e-05, - "loss": 4.2328, - "step": 1532 - }, - { - "epoch": 0.86, - "learning_rate": 5.957943925233644e-05, - "loss": 4.5931, - "step": 1533 - }, - { - "epoch": 0.86, - "learning_rate": 5.9345794392523356e-05, - "loss": 4.5764, - "step": 1534 - }, - { - "epoch": 0.86, - "learning_rate": 5.9112149532710276e-05, - "loss": 4.4689, - "step": 1535 - }, - { - "epoch": 0.86, - "learning_rate": 5.887850467289719e-05, - "loss": 4.1176, - "step": 1536 - }, - { - "epoch": 0.86, - "learning_rate": 5.86448598130841e-05, - "loss": 4.6403, - "step": 1537 - }, - { - "epoch": 0.86, - "learning_rate": 5.8411214953271024e-05, - "loss": 4.6772, - "step": 1538 - }, - { - "epoch": 0.86, - "learning_rate": 5.817757009345794e-05, - "loss": 4.3843, - "step": 1539 - }, - { - "epoch": 0.86, - "learning_rate": 5.794392523364485e-05, - "loss": 4.7563, - "step": 1540 - }, - { - "epoch": 0.86, - "learning_rate": 5.771028037383177e-05, - "loss": 4.9383, - "step": 1541 - }, - { - "epoch": 0.86, - "learning_rate": 5.7476635514018685e-05, - "loss": 4.3318, - "step": 1542 - }, - { - "epoch": 0.86, - "learning_rate": 5.72429906542056e-05, - "loss": 4.9106, - "step": 1543 - }, - { - "epoch": 0.87, - "learning_rate": 5.700934579439252e-05, - "loss": 4.6952, - "step": 1544 - }, - { - "epoch": 0.87, - "learning_rate": 5.677570093457943e-05, - "loss": 4.9123, - "step": 1545 - }, - { - "epoch": 0.87, - "learning_rate": 5.6542056074766346e-05, - "loss": 4.1529, - "step": 1546 - }, - { - "epoch": 0.87, - "learning_rate": 5.630841121495327e-05, - "loss": 4.5938, - "step": 1547 - }, - { - "epoch": 0.87, - "learning_rate": 5.607476635514018e-05, - "loss": 4.5772, - "step": 1548 - }, - { - "epoch": 0.87, - "learning_rate": 5.5841121495327094e-05, - "loss": 5.2856, - "step": 1549 - }, - { - "epoch": 0.87, - "learning_rate": 5.5607476635514014e-05, - "loss": 4.2405, - "step": 1550 - }, - { - "epoch": 0.87, - "learning_rate": 5.537383177570093e-05, - "loss": 4.8375, - "step": 1551 - }, - { - "epoch": 0.87, - "learning_rate": 5.514018691588784e-05, - "loss": 4.4389, - "step": 1552 - }, - { - "epoch": 0.87, - "learning_rate": 5.490654205607476e-05, - "loss": 4.3264, - "step": 1553 - }, - { - "epoch": 0.87, - "learning_rate": 5.4672897196261676e-05, - "loss": 4.3232, - "step": 1554 - }, - { - "epoch": 0.87, - "learning_rate": 5.443925233644859e-05, - "loss": 4.6999, - "step": 1555 - }, - { - "epoch": 0.87, - "learning_rate": 5.420560747663551e-05, - "loss": 5.0299, - "step": 1556 - }, - { - "epoch": 0.87, - "learning_rate": 5.397196261682242e-05, - "loss": 4.5852, - "step": 1557 - }, - { - "epoch": 0.87, - "learning_rate": 5.373831775700934e-05, - "loss": 4.8394, - "step": 1558 - }, - { - "epoch": 0.87, - "learning_rate": 5.350467289719626e-05, - "loss": 4.4774, - "step": 1559 - }, - { - "epoch": 0.87, - "learning_rate": 5.327102803738317e-05, - "loss": 4.5569, - "step": 1560 - }, - { - "epoch": 0.88, - "learning_rate": 5.3037383177570085e-05, - "loss": 4.5835, - "step": 1561 - }, - { - "epoch": 0.88, - "learning_rate": 5.2803738317757005e-05, - "loss": 4.4451, - "step": 1562 - }, - { - "epoch": 0.88, - "learning_rate": 5.257009345794392e-05, - "loss": 4.6235, - "step": 1563 - }, - { - "epoch": 0.88, - "learning_rate": 5.233644859813083e-05, - "loss": 4.3973, - "step": 1564 - }, - { - "epoch": 0.88, - "learning_rate": 5.210280373831775e-05, - "loss": 4.5698, - "step": 1565 - }, - { - "epoch": 0.88, - "learning_rate": 5.1869158878504666e-05, - "loss": 4.3054, - "step": 1566 - }, - { - "epoch": 0.88, - "learning_rate": 5.163551401869158e-05, - "loss": 4.1368, - "step": 1567 - }, - { - "epoch": 0.88, - "learning_rate": 5.14018691588785e-05, - "loss": 4.4234, - "step": 1568 - }, - { - "epoch": 0.88, - "learning_rate": 5.1168224299065414e-05, - "loss": 4.5224, - "step": 1569 - }, - { - "epoch": 0.88, - "learning_rate": 5.093457943925233e-05, - "loss": 4.3323, - "step": 1570 - }, - { - "epoch": 0.88, - "learning_rate": 5.070093457943925e-05, - "loss": 4.3603, - "step": 1571 - }, - { - "epoch": 0.88, - "learning_rate": 5.046728971962616e-05, - "loss": 4.6431, - "step": 1572 - }, - { - "epoch": 0.88, - "learning_rate": 5.0233644859813075e-05, - "loss": 4.5945, - "step": 1573 - }, - { - "epoch": 0.88, - "learning_rate": 4.9999999999999996e-05, - "loss": 4.2551, - "step": 1574 - }, - { - "epoch": 0.88, - "learning_rate": 4.976635514018691e-05, - "loss": 4.1337, - "step": 1575 - }, - { - "epoch": 0.88, - "learning_rate": 4.953271028037382e-05, - "loss": 4.7356, - "step": 1576 - }, - { - "epoch": 0.88, - "learning_rate": 4.929906542056074e-05, - "loss": 4.267, - "step": 1577 - }, - { - "epoch": 0.88, - "learning_rate": 4.906542056074766e-05, - "loss": 4.6538, - "step": 1578 - }, - { - "epoch": 0.89, - "learning_rate": 4.883177570093457e-05, - "loss": 4.6813, - "step": 1579 - }, - { - "epoch": 0.89, - "learning_rate": 4.859813084112149e-05, - "loss": 4.966, - "step": 1580 - }, - { - "epoch": 0.89, - "learning_rate": 4.8364485981308405e-05, - "loss": 4.8133, - "step": 1581 - }, - { - "epoch": 0.89, - "learning_rate": 4.813084112149532e-05, - "loss": 4.5538, - "step": 1582 - }, - { - "epoch": 0.89, - "learning_rate": 4.789719626168224e-05, - "loss": 4.4093, - "step": 1583 - }, - { - "epoch": 0.89, - "learning_rate": 4.766355140186915e-05, - "loss": 4.2818, - "step": 1584 - }, - { - "epoch": 0.89, - "learning_rate": 4.7429906542056066e-05, - "loss": 4.3304, - "step": 1585 - }, - { - "epoch": 0.89, - "learning_rate": 4.7196261682242986e-05, - "loss": 4.3476, - "step": 1586 - }, - { - "epoch": 0.89, - "learning_rate": 4.69626168224299e-05, - "loss": 4.3852, - "step": 1587 - }, - { - "epoch": 0.89, - "learning_rate": 4.6728971962616814e-05, - "loss": 4.5344, - "step": 1588 - }, - { - "epoch": 0.89, - "learning_rate": 4.6495327102803734e-05, - "loss": 4.432, - "step": 1589 - }, - { - "epoch": 0.89, - "learning_rate": 4.626168224299065e-05, - "loss": 4.2759, - "step": 1590 - }, - { - "epoch": 0.89, - "learning_rate": 4.602803738317756e-05, - "loss": 4.3829, - "step": 1591 - }, - { - "epoch": 0.89, - "learning_rate": 4.579439252336448e-05, - "loss": 4.2902, - "step": 1592 - }, - { - "epoch": 0.89, - "learning_rate": 4.5560747663551395e-05, - "loss": 4.3176, - "step": 1593 - }, - { - "epoch": 0.89, - "learning_rate": 4.532710280373831e-05, - "loss": 4.3517, - "step": 1594 - }, - { - "epoch": 0.89, - "learning_rate": 4.509345794392523e-05, - "loss": 4.3353, - "step": 1595 - }, - { - "epoch": 0.89, - "learning_rate": 4.485981308411214e-05, - "loss": 4.555, - "step": 1596 - }, - { - "epoch": 0.9, - "learning_rate": 4.4626168224299057e-05, - "loss": 4.488, - "step": 1597 - }, - { - "epoch": 0.9, - "learning_rate": 4.439252336448598e-05, - "loss": 4.6808, - "step": 1598 - }, - { - "epoch": 0.9, - "learning_rate": 4.415887850467289e-05, - "loss": 5.3481, - "step": 1599 - }, - { - "epoch": 0.9, - "learning_rate": 4.3925233644859804e-05, - "loss": 4.8497, - "step": 1600 - }, - { - "epoch": 0.9, - "learning_rate": 4.3691588785046725e-05, - "loss": 4.4094, - "step": 1601 - }, - { - "epoch": 0.9, - "learning_rate": 4.345794392523364e-05, - "loss": 4.18, - "step": 1602 - }, - { - "epoch": 0.9, - "learning_rate": 4.322429906542055e-05, - "loss": 4.3318, - "step": 1603 - }, - { - "epoch": 0.9, - "learning_rate": 4.299065420560747e-05, - "loss": 4.4917, - "step": 1604 - }, - { - "epoch": 0.9, - "learning_rate": 4.2757009345794386e-05, - "loss": 4.1726, - "step": 1605 - }, - { - "epoch": 0.9, - "learning_rate": 4.25233644859813e-05, - "loss": 4.4581, - "step": 1606 - }, - { - "epoch": 0.9, - "learning_rate": 4.228971962616822e-05, - "loss": 4.4206, - "step": 1607 - }, - { - "epoch": 0.9, - "learning_rate": 4.2056074766355134e-05, - "loss": 4.3926, - "step": 1608 - }, - { - "epoch": 0.9, - "learning_rate": 4.182242990654205e-05, - "loss": 4.577, - "step": 1609 - }, - { - "epoch": 0.9, - "learning_rate": 4.158878504672897e-05, - "loss": 4.2954, - "step": 1610 - }, - { - "epoch": 0.9, - "learning_rate": 4.135514018691588e-05, - "loss": 4.5879, - "step": 1611 - }, - { - "epoch": 0.9, - "learning_rate": 4.1121495327102795e-05, - "loss": 4.3564, - "step": 1612 - }, - { - "epoch": 0.9, - "learning_rate": 4.0887850467289715e-05, - "loss": 4.818, - "step": 1613 - }, - { - "epoch": 0.9, - "learning_rate": 4.065420560747663e-05, - "loss": 4.1919, - "step": 1614 - }, - { - "epoch": 0.91, - "learning_rate": 4.042056074766354e-05, - "loss": 4.3982, - "step": 1615 - }, - { - "epoch": 0.91, - "learning_rate": 4.018691588785046e-05, - "loss": 4.5268, - "step": 1616 - }, - { - "epoch": 0.91, - "learning_rate": 3.9953271028037377e-05, - "loss": 4.6489, - "step": 1617 - }, - { - "epoch": 0.91, - "learning_rate": 3.971962616822429e-05, - "loss": 4.4834, - "step": 1618 - }, - { - "epoch": 0.91, - "learning_rate": 3.948598130841121e-05, - "loss": 4.3963, - "step": 1619 - }, - { - "epoch": 0.91, - "learning_rate": 3.9252336448598124e-05, - "loss": 4.4466, - "step": 1620 - }, - { - "epoch": 0.91, - "learning_rate": 3.901869158878504e-05, - "loss": 4.7742, - "step": 1621 - }, - { - "epoch": 0.91, - "learning_rate": 3.878504672897196e-05, - "loss": 4.106, - "step": 1622 - }, - { - "epoch": 0.91, - "learning_rate": 3.855140186915887e-05, - "loss": 4.5184, - "step": 1623 - }, - { - "epoch": 0.91, - "learning_rate": 3.8317757009345785e-05, - "loss": 4.1765, - "step": 1624 - }, - { - "epoch": 0.91, - "learning_rate": 3.8084112149532706e-05, - "loss": 4.4416, - "step": 1625 - }, - { - "epoch": 0.91, - "learning_rate": 3.785046728971962e-05, - "loss": 4.7439, - "step": 1626 - }, - { - "epoch": 0.91, - "learning_rate": 3.761682242990653e-05, - "loss": 4.4909, - "step": 1627 - }, - { - "epoch": 0.91, - "learning_rate": 3.7383177570093454e-05, - "loss": 4.2699, - "step": 1628 - }, - { - "epoch": 0.91, - "learning_rate": 3.714953271028037e-05, - "loss": 4.4583, - "step": 1629 - }, - { - "epoch": 0.91, - "learning_rate": 3.691588785046729e-05, - "loss": 4.4138, - "step": 1630 - }, - { - "epoch": 0.91, - "learning_rate": 3.66822429906542e-05, - "loss": 4.3643, - "step": 1631 - }, - { - "epoch": 0.91, - "learning_rate": 3.6448598130841115e-05, - "loss": 4.5636, - "step": 1632 - }, - { - "epoch": 0.92, - "learning_rate": 3.6214953271028035e-05, - "loss": 4.5343, - "step": 1633 - }, - { - "epoch": 0.92, - "learning_rate": 3.598130841121495e-05, - "loss": 4.2948, - "step": 1634 - }, - { - "epoch": 0.92, - "learning_rate": 3.574766355140186e-05, - "loss": 4.4291, - "step": 1635 - }, - { - "epoch": 0.92, - "learning_rate": 3.551401869158878e-05, - "loss": 4.3163, - "step": 1636 - }, - { - "epoch": 0.92, - "learning_rate": 3.5280373831775697e-05, - "loss": 4.2765, - "step": 1637 - }, - { - "epoch": 0.92, - "learning_rate": 3.504672897196261e-05, - "loss": 4.721, - "step": 1638 - }, - { - "epoch": 0.92, - "learning_rate": 3.481308411214953e-05, - "loss": 4.2184, - "step": 1639 - }, - { - "epoch": 0.92, - "learning_rate": 3.4579439252336444e-05, - "loss": 4.4389, - "step": 1640 - }, - { - "epoch": 0.92, - "learning_rate": 3.434579439252336e-05, - "loss": 4.6074, - "step": 1641 - }, - { - "epoch": 0.92, - "learning_rate": 3.411214953271028e-05, - "loss": 4.3708, - "step": 1642 - }, - { - "epoch": 0.92, - "learning_rate": 3.387850467289719e-05, - "loss": 4.4057, - "step": 1643 - }, - { - "epoch": 0.92, - "learning_rate": 3.3644859813084105e-05, - "loss": 4.4923, - "step": 1644 - }, - { - "epoch": 0.92, - "learning_rate": 3.3411214953271026e-05, - "loss": 4.911, - "step": 1645 - }, - { - "epoch": 0.92, - "learning_rate": 3.317757009345794e-05, - "loss": 4.8139, - "step": 1646 - }, - { - "epoch": 0.92, - "learning_rate": 3.294392523364485e-05, - "loss": 4.5291, - "step": 1647 - }, - { - "epoch": 0.92, - "learning_rate": 3.2710280373831774e-05, - "loss": 5.7156, - "step": 1648 - }, - { - "epoch": 0.92, - "learning_rate": 3.247663551401869e-05, - "loss": 4.6558, - "step": 1649 - }, { "epoch": 0.92, - "learning_rate": 3.22429906542056e-05, - "loss": 4.3577, - "step": 1650 - }, - { - "epoch": 0.93, - "learning_rate": 3.200934579439252e-05, - "loss": 4.4413, - "step": 1651 - }, - { - "epoch": 0.93, - "learning_rate": 3.1775700934579435e-05, - "loss": 4.4164, - "step": 1652 - }, - { - "epoch": 0.93, - "learning_rate": 3.154205607476635e-05, - "loss": 4.423, - "step": 1653 - }, - { - "epoch": 0.93, - "learning_rate": 3.130841121495327e-05, - "loss": 4.423, - "step": 1654 - }, - { - "epoch": 0.93, - "learning_rate": 3.107476635514018e-05, - "loss": 4.2193, - "step": 1655 - }, - { - "epoch": 0.93, - "learning_rate": 3.0841121495327096e-05, - "loss": 4.3391, - "step": 1656 - }, - { - "epoch": 0.93, - "learning_rate": 3.0607476635514017e-05, - "loss": 4.7696, - "step": 1657 - }, - { - "epoch": 0.93, - "learning_rate": 3.037383177570093e-05, - "loss": 4.5569, - "step": 1658 - }, - { - "epoch": 0.93, - "learning_rate": 3.0140186915887847e-05, - "loss": 4.3525, - "step": 1659 - }, - { - "epoch": 0.93, - "learning_rate": 2.9906542056074764e-05, - "loss": 4.3584, - "step": 1660 - }, - { - "epoch": 0.93, - "learning_rate": 2.9672897196261678e-05, - "loss": 4.4457, - "step": 1661 - }, - { - "epoch": 0.93, - "learning_rate": 2.9439252336448595e-05, - "loss": 4.4171, - "step": 1662 - }, - { - "epoch": 0.93, - "learning_rate": 2.9205607476635512e-05, - "loss": 4.125, - "step": 1663 - }, - { - "epoch": 0.93, - "learning_rate": 2.8971962616822425e-05, - "loss": 4.6175, - "step": 1664 - }, - { - "epoch": 0.93, - "learning_rate": 2.8738317757009342e-05, - "loss": 4.1978, - "step": 1665 - }, - { - "epoch": 0.93, - "learning_rate": 2.850467289719626e-05, - "loss": 4.5791, - "step": 1666 - }, - { - "epoch": 0.93, - "learning_rate": 2.8271028037383173e-05, - "loss": 4.3217, - "step": 1667 - }, - { - "epoch": 0.93, - "learning_rate": 2.803738317757009e-05, - "loss": 4.222, - "step": 1668 - }, - { - "epoch": 0.94, - "learning_rate": 2.7803738317757007e-05, - "loss": 4.2184, - "step": 1669 - }, - { - "epoch": 0.94, - "learning_rate": 2.757009345794392e-05, - "loss": 4.4783, - "step": 1670 - }, - { - "epoch": 0.94, - "learning_rate": 2.7336448598130838e-05, - "loss": 4.5503, - "step": 1671 - }, - { - "epoch": 0.94, - "learning_rate": 2.7102803738317755e-05, - "loss": 4.6221, - "step": 1672 - }, - { - "epoch": 0.94, - "learning_rate": 2.686915887850467e-05, - "loss": 4.3301, - "step": 1673 - }, - { - "epoch": 0.94, - "learning_rate": 2.6635514018691585e-05, - "loss": 4.4446, - "step": 1674 - }, - { - "epoch": 0.94, - "learning_rate": 2.6401869158878502e-05, - "loss": 4.7222, - "step": 1675 - }, - { - "epoch": 0.94, - "learning_rate": 2.6168224299065416e-05, - "loss": 4.2519, - "step": 1676 - }, - { - "epoch": 0.94, - "learning_rate": 2.5934579439252333e-05, - "loss": 4.1353, - "step": 1677 - }, - { - "epoch": 0.94, - "learning_rate": 2.570093457943925e-05, - "loss": 4.3722, - "step": 1678 + "learning_rate": 5.510204081632653e-05, + "loss": 4.1727, + "step": 822 }, { - "epoch": 0.94, - "learning_rate": 2.5467289719626164e-05, - "loss": 4.6245, - "step": 1679 + "epoch": 0.92, + "learning_rate": 5.433673469387755e-05, + "loss": 4.4697, + "step": 823 }, { - "epoch": 0.94, - "learning_rate": 2.523364485981308e-05, - "loss": 4.919, - "step": 1680 + "epoch": 0.92, + "learning_rate": 5.357142857142857e-05, + "loss": 4.3857, + "step": 824 }, { - "epoch": 0.94, - "learning_rate": 2.4999999999999998e-05, - "loss": 4.0354, - "step": 1681 + "epoch": 0.92, + "learning_rate": 5.280612244897959e-05, + "loss": 4.7006, + "step": 825 }, { - "epoch": 0.94, - "learning_rate": 2.476635514018691e-05, - "loss": 4.148, - "step": 1682 + "epoch": 0.93, + "learning_rate": 5.204081632653061e-05, + "loss": 4.3715, + "step": 826 }, { - "epoch": 0.94, - "learning_rate": 2.453271028037383e-05, - "loss": 4.5749, - "step": 1683 + "epoch": 0.93, + "learning_rate": 5.1275510204081626e-05, + "loss": 4.343, + "step": 827 }, { - "epoch": 0.94, - "learning_rate": 2.4299065420560745e-05, + "epoch": 0.93, + "learning_rate": 5.0510204081632645e-05, "loss": 4.1802, - "step": 1684 + "step": 828 }, { - "epoch": 0.94, - "learning_rate": 2.406542056074766e-05, - "loss": 4.5103, - "step": 1685 + "epoch": 0.93, + "learning_rate": 4.9744897959183664e-05, + "loss": 4.2783, + "step": 829 }, { - "epoch": 0.95, - "learning_rate": 2.3831775700934576e-05, - "loss": 4.4409, - "step": 1686 + "epoch": 0.93, + "learning_rate": 4.897959183673468e-05, + "loss": 4.6354, + "step": 830 }, { - "epoch": 0.95, - "learning_rate": 2.3598130841121493e-05, - "loss": 4.3141, - "step": 1687 + "epoch": 0.93, + "learning_rate": 4.8214285714285716e-05, + "loss": 4.1624, + "step": 831 }, { - "epoch": 0.95, - "learning_rate": 2.3364485981308407e-05, - "loss": 4.7447, - "step": 1688 + "epoch": 0.93, + "learning_rate": 4.7448979591836735e-05, + "loss": 4.2262, + "step": 832 }, { - "epoch": 0.95, - "learning_rate": 2.3130841121495324e-05, - "loss": 4.4204, - "step": 1689 + "epoch": 0.93, + "learning_rate": 4.6683673469387754e-05, + "loss": 4.5945, + "step": 833 }, { - "epoch": 0.95, - "learning_rate": 2.289719626168224e-05, - "loss": 4.2559, - "step": 1690 + "epoch": 0.93, + "learning_rate": 4.591836734693877e-05, + "loss": 4.271, + "step": 834 }, { - "epoch": 0.95, - "learning_rate": 2.2663551401869154e-05, - "loss": 4.6965, - "step": 1691 + "epoch": 0.94, + "learning_rate": 4.515306122448979e-05, + "loss": 4.2882, + "step": 835 }, { - "epoch": 0.95, - "learning_rate": 2.242990654205607e-05, - "loss": 4.6322, - "step": 1692 + "epoch": 0.94, + "learning_rate": 4.438775510204081e-05, + "loss": 4.3603, + "step": 836 }, { - "epoch": 0.95, - "learning_rate": 2.219626168224299e-05, - "loss": 4.635, - "step": 1693 + "epoch": 0.94, + "learning_rate": 4.362244897959183e-05, + "loss": 4.2375, + "step": 837 }, { - "epoch": 0.95, - "learning_rate": 2.1962616822429902e-05, - "loss": 4.7668, - "step": 1694 + "epoch": 0.94, + "learning_rate": 4.285714285714285e-05, + "loss": 4.74, + "step": 838 }, { - "epoch": 0.95, - "learning_rate": 2.172897196261682e-05, - "loss": 4.6812, - "step": 1695 + "epoch": 0.94, + "learning_rate": 4.209183673469387e-05, + "loss": 4.1787, + "step": 839 }, { - "epoch": 0.95, - "learning_rate": 2.1495327102803736e-05, - "loss": 6.8732, - "step": 1696 + "epoch": 0.94, + "learning_rate": 4.132653061224489e-05, + "loss": 4.3731, + "step": 840 }, { - "epoch": 0.95, - "learning_rate": 2.126168224299065e-05, - "loss": 4.3886, - "step": 1697 + "epoch": 0.94, + "learning_rate": 4.056122448979592e-05, + "loss": 4.4929, + "step": 841 }, { - "epoch": 0.95, - "learning_rate": 2.1028037383177567e-05, - "loss": 4.8438, - "step": 1698 + "epoch": 0.94, + "learning_rate": 3.979591836734694e-05, + "loss": 4.4278, + "step": 842 }, { "epoch": 0.95, - "learning_rate": 2.0794392523364484e-05, - "loss": 4.7797, - "step": 1699 + "learning_rate": 3.903061224489796e-05, + "loss": 4.5355, + "step": 843 }, { "epoch": 0.95, - "learning_rate": 2.0560747663551397e-05, - "loss": 4.7208, - "step": 1700 + "learning_rate": 3.826530612244898e-05, + "loss": 4.4494, + "step": 844 }, { "epoch": 0.95, - "learning_rate": 2.0327102803738314e-05, - "loss": 5.4447, - "step": 1701 + "learning_rate": 3.75e-05, + "loss": 4.6306, + "step": 845 }, { "epoch": 0.95, - "learning_rate": 2.009345794392523e-05, - "loss": 4.6347, - "step": 1702 + "learning_rate": 3.6734693877551016e-05, + "loss": 6.0223, + "step": 846 }, { "epoch": 0.95, - "learning_rate": 1.9859813084112145e-05, - "loss": 4.3577, - "step": 1703 - }, - { - "epoch": 0.96, - "learning_rate": 1.9626168224299062e-05, - "loss": 4.5445, - "step": 1704 - }, - { - "epoch": 0.96, - "learning_rate": 1.939252336448598e-05, - "loss": 4.3889, - "step": 1705 - }, - { - "epoch": 0.96, - "learning_rate": 1.9158878504672893e-05, - "loss": 4.2342, - "step": 1706 - }, - { - "epoch": 0.96, - "learning_rate": 1.892523364485981e-05, - "loss": 4.2112, - "step": 1707 - }, - { - "epoch": 0.96, - "learning_rate": 1.8691588785046727e-05, - "loss": 4.7281, - "step": 1708 + "learning_rate": 3.5969387755102035e-05, + "loss": 4.3618, + "step": 847 }, { - "epoch": 0.96, - "learning_rate": 1.8457943925233644e-05, - "loss": 4.9417, - "step": 1709 + "epoch": 0.95, + "learning_rate": 3.520408163265306e-05, + "loss": 5.3841, + "step": 848 }, { - "epoch": 0.96, - "learning_rate": 1.8224299065420557e-05, - "loss": 4.6363, - "step": 1710 + "epoch": 0.95, + "learning_rate": 3.443877551020408e-05, + "loss": 4.5419, + "step": 849 }, { - "epoch": 0.96, - "learning_rate": 1.7990654205607474e-05, - "loss": 4.3709, - "step": 1711 + "epoch": 0.95, + "learning_rate": 3.36734693877551e-05, + "loss": 4.3319, + "step": 850 }, { - "epoch": 0.96, - "learning_rate": 1.775700934579439e-05, - "loss": 4.4913, - "step": 1712 + "epoch": 0.95, + "learning_rate": 3.290816326530612e-05, + "loss": 4.4256, + "step": 851 }, { "epoch": 0.96, - "learning_rate": 1.7523364485981305e-05, - "loss": 4.924, - "step": 1713 + "learning_rate": 3.214285714285714e-05, + "loss": 4.6279, + "step": 852 }, { "epoch": 0.96, - "learning_rate": 1.7289719626168222e-05, - "loss": 4.3406, - "step": 1714 + "learning_rate": 3.137755102040816e-05, + "loss": 4.3228, + "step": 853 }, { "epoch": 0.96, - "learning_rate": 1.705607476635514e-05, - "loss": 4.381, - "step": 1715 + "learning_rate": 3.061224489795918e-05, + "loss": 4.3667, + "step": 854 }, { "epoch": 0.96, - "learning_rate": 1.6822429906542053e-05, - "loss": 4.6096, - "step": 1716 + "learning_rate": 2.98469387755102e-05, + "loss": 4.3636, + "step": 855 }, { "epoch": 0.96, - "learning_rate": 1.658878504672897e-05, - "loss": 4.8523, - "step": 1717 + "learning_rate": 2.908163265306122e-05, + "loss": 4.4012, + "step": 856 }, { "epoch": 0.96, - "learning_rate": 1.6355140186915887e-05, - "loss": 5.0614, - "step": 1718 + "learning_rate": 2.831632653061224e-05, + "loss": 4.6426, + "step": 857 }, { "epoch": 0.96, - "learning_rate": 1.61214953271028e-05, - "loss": 4.4435, - "step": 1719 + "learning_rate": 2.7551020408163265e-05, + "loss": 4.4105, + "step": 858 }, { "epoch": 0.96, - "learning_rate": 1.5887850467289717e-05, - "loss": 4.3249, - "step": 1720 + "learning_rate": 2.6785714285714284e-05, + "loss": 4.2464, + "step": 859 }, { "epoch": 0.96, - "learning_rate": 1.5654205607476634e-05, - "loss": 4.5801, - "step": 1721 - }, - { - "epoch": 0.97, - "learning_rate": 1.5420560747663548e-05, - "loss": 4.7013, - "step": 1722 - }, - { - "epoch": 0.97, - "learning_rate": 1.5186915887850465e-05, - "loss": 4.9319, - "step": 1723 - }, - { - "epoch": 0.97, - "learning_rate": 1.4953271028037382e-05, - "loss": 4.4212, - "step": 1724 - }, - { - "epoch": 0.97, - "learning_rate": 1.4719626168224297e-05, - "loss": 4.3575, - "step": 1725 - }, - { - "epoch": 0.97, - "learning_rate": 1.4485981308411213e-05, - "loss": 4.3268, - "step": 1726 - }, - { - "epoch": 0.97, - "learning_rate": 1.425233644859813e-05, - "loss": 4.7552, - "step": 1727 - }, - { - "epoch": 0.97, - "learning_rate": 1.4018691588785045e-05, - "loss": 4.5419, - "step": 1728 - }, - { - "epoch": 0.97, - "learning_rate": 1.378504672897196e-05, - "loss": 4.6466, - "step": 1729 - }, - { - "epoch": 0.97, - "learning_rate": 1.3551401869158877e-05, - "loss": 4.5341, - "step": 1730 + "learning_rate": 2.6020408163265303e-05, + "loss": 4.2655, + "step": 860 }, { "epoch": 0.97, - "learning_rate": 1.3317757009345793e-05, - "loss": 4.0522, - "step": 1731 + "learning_rate": 2.5255102040816323e-05, + "loss": 4.6105, + "step": 861 }, { "epoch": 0.97, - "learning_rate": 1.3084112149532708e-05, - "loss": 4.2971, - "step": 1732 + "learning_rate": 2.448979591836734e-05, + "loss": 4.2751, + "step": 862 }, { "epoch": 0.97, - "learning_rate": 1.2850467289719625e-05, - "loss": 4.3649, - "step": 1733 + "learning_rate": 2.3724489795918367e-05, + "loss": 4.5389, + "step": 863 }, { "epoch": 0.97, - "learning_rate": 1.261682242990654e-05, - "loss": 4.517, - "step": 1734 + "learning_rate": 2.2959183673469387e-05, + "loss": 4.6414, + "step": 864 }, { "epoch": 0.97, - "learning_rate": 1.2383177570093456e-05, - "loss": 4.6907, - "step": 1735 + "learning_rate": 2.2193877551020406e-05, + "loss": 4.4979, + "step": 865 }, { "epoch": 0.97, - "learning_rate": 1.2149532710280373e-05, - "loss": 5.157, - "step": 1736 + "learning_rate": 2.1428571428571425e-05, + "loss": 4.2482, + "step": 866 }, { "epoch": 0.97, - "learning_rate": 1.1915887850467288e-05, - "loss": 4.0792, - "step": 1737 + "learning_rate": 2.0663265306122444e-05, + "loss": 4.3489, + "step": 867 }, { "epoch": 0.97, - "learning_rate": 1.1682242990654203e-05, - "loss": 4.3858, - "step": 1738 + "learning_rate": 1.989795918367347e-05, + "loss": 4.2621, + "step": 868 }, { "epoch": 0.97, - "learning_rate": 1.144859813084112e-05, - "loss": 4.3711, - "step": 1739 - }, - { - "epoch": 0.98, - "learning_rate": 1.1214953271028036e-05, - "loss": 4.3268, - "step": 1740 - }, - { - "epoch": 0.98, - "learning_rate": 1.0981308411214951e-05, - "loss": 4.6023, - "step": 1741 - }, - { - "epoch": 0.98, - "learning_rate": 1.0747663551401868e-05, - "loss": 4.7392, - "step": 1742 - }, - { - "epoch": 0.98, - "learning_rate": 1.0514018691588783e-05, - "loss": 4.2426, - "step": 1743 - }, - { - "epoch": 0.98, - "learning_rate": 1.0280373831775699e-05, - "loss": 4.4313, - "step": 1744 - }, - { - "epoch": 0.98, - "learning_rate": 1.0046728971962616e-05, - "loss": 4.5677, - "step": 1745 - }, - { - "epoch": 0.98, - "learning_rate": 9.813084112149531e-06, - "loss": 4.55, - "step": 1746 - }, - { - "epoch": 0.98, - "learning_rate": 9.579439252336446e-06, - "loss": 4.5261, - "step": 1747 - }, - { - "epoch": 0.98, - "learning_rate": 9.345794392523363e-06, - "loss": 4.312, - "step": 1748 + "learning_rate": 1.913265306122449e-05, + "loss": 4.3633, + "step": 869 }, { "epoch": 0.98, - "learning_rate": 9.112149532710279e-06, - "loss": 4.4876, - "step": 1749 + "learning_rate": 1.8367346938775508e-05, + "loss": 4.5475, + "step": 870 }, { "epoch": 0.98, - "learning_rate": 8.878504672897196e-06, - "loss": 4.7372, - "step": 1750 + "learning_rate": 1.760204081632653e-05, + "loss": 4.3889, + "step": 871 }, { "epoch": 0.98, - "learning_rate": 8.644859813084111e-06, - "loss": 4.2251, - "step": 1751 + "learning_rate": 1.683673469387755e-05, + "loss": 4.4282, + "step": 872 }, { "epoch": 0.98, - "learning_rate": 8.411214953271026e-06, - "loss": 4.2393, - "step": 1752 + "learning_rate": 1.607142857142857e-05, + "loss": 4.3825, + "step": 873 }, { "epoch": 0.98, - "learning_rate": 8.177570093457943e-06, - "loss": 4.5664, - "step": 1753 + "learning_rate": 1.530612244897959e-05, + "loss": 4.2839, + "step": 874 }, { "epoch": 0.98, - "learning_rate": 7.943925233644859e-06, - "loss": 4.9451, - "step": 1754 + "learning_rate": 1.454081632653061e-05, + "loss": 4.5392, + "step": 875 }, { "epoch": 0.98, - "learning_rate": 7.710280373831774e-06, - "loss": 4.586, - "step": 1755 + "learning_rate": 1.3775510204081633e-05, + "loss": 4.298, + "step": 876 }, { "epoch": 0.98, - "learning_rate": 7.476635514018691e-06, - "loss": 4.2036, - "step": 1756 + "learning_rate": 1.3010204081632652e-05, + "loss": 4.2461, + "step": 877 }, { "epoch": 0.98, - "learning_rate": 7.242990654205606e-06, - "loss": 4.3517, - "step": 1757 - }, - { - "epoch": 0.99, - "learning_rate": 7.0093457943925225e-06, - "loss": 4.2392, - "step": 1758 - }, - { - "epoch": 0.99, - "learning_rate": 6.775700934579439e-06, - "loss": 4.8806, - "step": 1759 - }, - { - "epoch": 0.99, - "learning_rate": 6.542056074766354e-06, - "loss": 4.3799, - "step": 1760 - }, - { - "epoch": 0.99, - "learning_rate": 6.30841121495327e-06, - "loss": 4.7228, - "step": 1761 - }, - { - "epoch": 0.99, - "learning_rate": 6.074766355140186e-06, - "loss": 4.1935, - "step": 1762 - }, - { - "epoch": 0.99, - "learning_rate": 5.841121495327102e-06, - "loss": 4.376, - "step": 1763 - }, - { - "epoch": 0.99, - "learning_rate": 5.607476635514018e-06, - "loss": 4.623, - "step": 1764 - }, - { - "epoch": 0.99, - "learning_rate": 5.373831775700934e-06, - "loss": 4.2161, - "step": 1765 - }, - { - "epoch": 0.99, - "learning_rate": 5.140186915887849e-06, - "loss": 4.3338, - "step": 1766 + "learning_rate": 1.224489795918367e-05, + "loss": 4.351, + "step": 878 }, { "epoch": 0.99, - "learning_rate": 4.9065420560747655e-06, - "loss": 4.3949, - "step": 1767 + "learning_rate": 1.1479591836734693e-05, + "loss": 4.4149, + "step": 879 }, { "epoch": 0.99, - "learning_rate": 4.672897196261682e-06, - "loss": 4.2384, - "step": 1768 + "learning_rate": 1.0714285714285712e-05, + "loss": 4.5369, + "step": 880 }, { "epoch": 0.99, - "learning_rate": 4.439252336448598e-06, - "loss": 4.5483, - "step": 1769 + "learning_rate": 9.948979591836735e-06, + "loss": 4.1519, + "step": 881 }, { "epoch": 0.99, - "learning_rate": 4.205607476635513e-06, - "loss": 4.2237, - "step": 1770 + "learning_rate": 9.183673469387754e-06, + "loss": 4.3366, + "step": 882 }, { "epoch": 0.99, - "learning_rate": 3.971962616822429e-06, - "loss": 4.5197, - "step": 1771 + "learning_rate": 8.418367346938775e-06, + "loss": 4.3092, + "step": 883 }, { "epoch": 0.99, - "learning_rate": 3.7383177570093455e-06, - "loss": 4.3027, - "step": 1772 + "learning_rate": 7.653061224489796e-06, + "loss": 4.3208, + "step": 884 }, { "epoch": 0.99, - "learning_rate": 3.5046728971962613e-06, - "loss": 4.3541, - "step": 1773 + "learning_rate": 6.887755102040816e-06, + "loss": 4.3342, + "step": 885 }, { "epoch": 0.99, - "learning_rate": 3.271028037383177e-06, - "loss": 4.6148, - "step": 1774 + "learning_rate": 6.122448979591835e-06, + "loss": 4.5901, + "step": 886 }, { "epoch": 0.99, - "learning_rate": 3.037383177570093e-06, - "loss": 4.2731, - "step": 1775 - }, - { - "epoch": 1.0, - "learning_rate": 2.803738317757009e-06, - "loss": 4.3739, - "step": 1776 - }, - { - "epoch": 1.0, - "learning_rate": 2.5700934579439247e-06, - "loss": 4.6138, - "step": 1777 - }, - { - "epoch": 1.0, - "learning_rate": 2.336448598130841e-06, - "loss": 4.3659, - "step": 1778 - }, - { - "epoch": 1.0, - "learning_rate": 2.1028037383177566e-06, - "loss": 4.7944, - "step": 1779 + "learning_rate": 5.357142857142856e-06, + "loss": 4.1842, + "step": 887 }, { "epoch": 1.0, - "learning_rate": 1.8691588785046728e-06, - "loss": 4.4154, - "step": 1780 + "learning_rate": 4.591836734693877e-06, + "loss": 4.4027, + "step": 888 }, { "epoch": 1.0, - "learning_rate": 1.6355140186915885e-06, - "loss": 4.6139, - "step": 1781 + "learning_rate": 3.826530612244898e-06, + "loss": 4.5197, + "step": 889 }, { "epoch": 1.0, - "learning_rate": 1.4018691588785045e-06, - "loss": 4.3388, - "step": 1782 + "learning_rate": 3.0612244897959177e-06, + "loss": 4.2515, + "step": 890 }, { "epoch": 1.0, - "learning_rate": 1.1682242990654204e-06, - "loss": 5.1691, - "step": 1783 + "learning_rate": 2.2959183673469385e-06, + "loss": 4.6854, + "step": 891 }, { "epoch": 1.0, - "learning_rate": 9.345794392523364e-07, - "loss": 3.9784, - "step": 1784 + "learning_rate": 1.5306122448979589e-06, + "loss": 3.9886, + "step": 892 }, { "epoch": 1.0, - "step": 1784, + "step": 892, "total_flos": 0.0, - "train_loss": 4.819954753590272, - "train_runtime": 8574.3703, - "train_samples_per_second": 3.328, - "train_steps_per_second": 0.208 + "train_loss": 4.602872911590097, + "train_runtime": 6254.5702, + "train_samples_per_second": 4.563, + "train_steps_per_second": 0.143 } ], - "max_steps": 1784, + "max_steps": 892, "num_train_epochs": 1, "total_flos": 0.0, "trial_name": null,