|
[ |
|
{ |
|
"current_steps": 0, |
|
"loss": 3.6926, |
|
"learning_rate": 0.0, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 1, |
|
"loss": 3.0107, |
|
"learning_rate": 0.0, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 2, |
|
"loss": 3.0688, |
|
"learning_rate": 0.0, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 3, |
|
"loss": 4.0176, |
|
"learning_rate": 0.0, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 4, |
|
"loss": 4.0609, |
|
"learning_rate": 0.0, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 5, |
|
"loss": 3.754, |
|
"learning_rate": 0.0, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 6, |
|
"loss": 3.1981, |
|
"learning_rate": 0.0, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 7, |
|
"loss": 2.7138, |
|
"learning_rate": 0.0, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 8, |
|
"loss": 3.8803, |
|
"learning_rate": 0.0, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 9, |
|
"loss": 3.5793, |
|
"learning_rate": 2.9999999999999997e-06, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 10, |
|
"loss": 2.8589, |
|
"learning_rate": 5.999999999999999e-06, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 11, |
|
"loss": 2.6536, |
|
"learning_rate": 8.999999999999999e-06, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 12, |
|
"loss": 4.1845, |
|
"learning_rate": 1.1999999999999999e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 13, |
|
"loss": 3.7447, |
|
"learning_rate": 1.4999999999999999e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 14, |
|
"loss": 2.9558, |
|
"learning_rate": 1.7999999999999997e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 15, |
|
"loss": 3.7552, |
|
"learning_rate": 2.1e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 16, |
|
"loss": 3.7336, |
|
"learning_rate": 2.3999999999999997e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 17, |
|
"loss": 2.484, |
|
"learning_rate": 2.6999999999999996e-05, |
|
"epoch": 0.26 |
|
}, |
|
{ |
|
"current_steps": 18, |
|
"loss": 3.7203, |
|
"learning_rate": 2.9999999999999997e-05, |
|
"epoch": 0.27 |
|
}, |
|
{ |
|
"current_steps": 19, |
|
"loss": 3.6129, |
|
"learning_rate": 2.9999999999999997e-05, |
|
"epoch": 0.29 |
|
}, |
|
{ |
|
"current_steps": 20, |
|
"loss": 2.2497, |
|
"learning_rate": 3.2999999999999996e-05, |
|
"epoch": 0.3 |
|
}, |
|
{ |
|
"current_steps": 21, |
|
"loss": 3.2732, |
|
"learning_rate": 3.5999999999999994e-05, |
|
"epoch": 0.31 |
|
}, |
|
{ |
|
"current_steps": 22, |
|
"loss": 2.4979, |
|
"learning_rate": 3.9e-05, |
|
"epoch": 0.33 |
|
}, |
|
{ |
|
"current_steps": 23, |
|
"loss": 3.043, |
|
"learning_rate": 4.2e-05, |
|
"epoch": 0.34 |
|
}, |
|
{ |
|
"current_steps": 24, |
|
"loss": 3.2435, |
|
"learning_rate": 4.4999999999999996e-05, |
|
"epoch": 0.36 |
|
}, |
|
{ |
|
"current_steps": 25, |
|
"loss": 3.3493, |
|
"learning_rate": 4.7999999999999994e-05, |
|
"epoch": 0.37 |
|
}, |
|
{ |
|
"current_steps": 26, |
|
"loss": 2.6339, |
|
"learning_rate": 5.1e-05, |
|
"epoch": 0.39 |
|
}, |
|
{ |
|
"current_steps": 27, |
|
"loss": 2.9486, |
|
"learning_rate": 5.399999999999999e-05, |
|
"epoch": 0.4 |
|
}, |
|
{ |
|
"current_steps": 28, |
|
"loss": 2.3865, |
|
"learning_rate": 5.6999999999999996e-05, |
|
"epoch": 0.41 |
|
}, |
|
{ |
|
"current_steps": 29, |
|
"loss": 2.3687, |
|
"learning_rate": 5.9999999999999995e-05, |
|
"epoch": 0.43 |
|
}, |
|
{ |
|
"current_steps": 30, |
|
"loss": 2.3417, |
|
"learning_rate": 6.299999999999999e-05, |
|
"epoch": 0.44 |
|
}, |
|
{ |
|
"current_steps": 31, |
|
"loss": 2.5443, |
|
"learning_rate": 6.599999999999999e-05, |
|
"epoch": 0.46 |
|
}, |
|
{ |
|
"current_steps": 32, |
|
"loss": 2.4717, |
|
"learning_rate": 6.9e-05, |
|
"epoch": 0.47 |
|
}, |
|
{ |
|
"current_steps": 33, |
|
"loss": 2.2291, |
|
"learning_rate": 7.199999999999999e-05, |
|
"epoch": 0.49 |
|
}, |
|
{ |
|
"current_steps": 34, |
|
"loss": 2.4815, |
|
"learning_rate": 7.5e-05, |
|
"epoch": 0.5 |
|
}, |
|
{ |
|
"current_steps": 35, |
|
"loss": 2.4468, |
|
"learning_rate": 7.8e-05, |
|
"epoch": 0.51 |
|
}, |
|
{ |
|
"current_steps": 36, |
|
"loss": 2.4246, |
|
"learning_rate": 8.1e-05, |
|
"epoch": 0.53 |
|
}, |
|
{ |
|
"current_steps": 37, |
|
"loss": 2.3154, |
|
"learning_rate": 8.4e-05, |
|
"epoch": 0.54 |
|
}, |
|
{ |
|
"current_steps": 38, |
|
"loss": 1.9939, |
|
"learning_rate": 8.699999999999999e-05, |
|
"epoch": 0.56 |
|
}, |
|
{ |
|
"current_steps": 39, |
|
"loss": 1.8099, |
|
"learning_rate": 8.999999999999999e-05, |
|
"epoch": 0.57 |
|
}, |
|
{ |
|
"current_steps": 40, |
|
"loss": 1.865, |
|
"learning_rate": 9.3e-05, |
|
"epoch": 0.59 |
|
}, |
|
{ |
|
"current_steps": 41, |
|
"loss": 1.4322, |
|
"learning_rate": 9.599999999999999e-05, |
|
"epoch": 0.6 |
|
}, |
|
{ |
|
"current_steps": 42, |
|
"loss": 2.3252, |
|
"learning_rate": 9.9e-05, |
|
"epoch": 0.61 |
|
}, |
|
{ |
|
"current_steps": 43, |
|
"loss": 1.7521, |
|
"learning_rate": 0.000102, |
|
"epoch": 0.63 |
|
}, |
|
{ |
|
"current_steps": 44, |
|
"loss": 2.145, |
|
"learning_rate": 0.00010499999999999999, |
|
"epoch": 0.64 |
|
}, |
|
{ |
|
"current_steps": 45, |
|
"loss": 1.6641, |
|
"learning_rate": 0.00010799999999999998, |
|
"epoch": 0.66 |
|
}, |
|
{ |
|
"current_steps": 46, |
|
"loss": 1.8938, |
|
"learning_rate": 0.00011099999999999999, |
|
"epoch": 0.67 |
|
}, |
|
{ |
|
"current_steps": 47, |
|
"loss": 1.5194, |
|
"learning_rate": 0.00011399999999999999, |
|
"epoch": 0.69 |
|
}, |
|
{ |
|
"current_steps": 48, |
|
"loss": 1.4478, |
|
"learning_rate": 0.000117, |
|
"epoch": 0.7 |
|
}, |
|
{ |
|
"current_steps": 49, |
|
"loss": 1.9414, |
|
"learning_rate": 0.00011999999999999999, |
|
"epoch": 0.71 |
|
}, |
|
{ |
|
"current_steps": 50, |
|
"loss": 1.5601, |
|
"learning_rate": 0.00012299999999999998, |
|
"epoch": 0.73 |
|
}, |
|
{ |
|
"current_steps": 51, |
|
"loss": 1.9015, |
|
"learning_rate": 0.00012599999999999997, |
|
"epoch": 0.74 |
|
}, |
|
{ |
|
"current_steps": 52, |
|
"loss": 1.7384, |
|
"learning_rate": 0.000129, |
|
"epoch": 0.76 |
|
}, |
|
{ |
|
"current_steps": 53, |
|
"loss": 1.7282, |
|
"learning_rate": 0.00013199999999999998, |
|
"epoch": 0.77 |
|
}, |
|
{ |
|
"current_steps": 54, |
|
"loss": 1.6877, |
|
"learning_rate": 0.000135, |
|
"epoch": 0.79 |
|
}, |
|
{ |
|
"current_steps": 55, |
|
"loss": 1.0647, |
|
"learning_rate": 0.000138, |
|
"epoch": 0.8 |
|
}, |
|
{ |
|
"current_steps": 56, |
|
"loss": 1.755, |
|
"learning_rate": 0.00014099999999999998, |
|
"epoch": 0.81 |
|
}, |
|
{ |
|
"current_steps": 57, |
|
"loss": 1.516, |
|
"learning_rate": 0.00014399999999999998, |
|
"epoch": 0.83 |
|
}, |
|
{ |
|
"current_steps": 58, |
|
"loss": 1.3498, |
|
"learning_rate": 0.000147, |
|
"epoch": 0.84 |
|
}, |
|
{ |
|
"current_steps": 59, |
|
"loss": 1.6789, |
|
"learning_rate": 0.00015, |
|
"epoch": 0.86 |
|
}, |
|
{ |
|
"current_steps": 60, |
|
"loss": 1.3651, |
|
"learning_rate": 0.00015299999999999998, |
|
"epoch": 0.87 |
|
}, |
|
{ |
|
"current_steps": 61, |
|
"loss": 1.2967, |
|
"learning_rate": 0.000156, |
|
"epoch": 0.89 |
|
}, |
|
{ |
|
"current_steps": 62, |
|
"loss": 1.3998, |
|
"learning_rate": 0.000159, |
|
"epoch": 0.9 |
|
}, |
|
{ |
|
"current_steps": 63, |
|
"loss": 1.1989, |
|
"learning_rate": 0.000162, |
|
"epoch": 0.91 |
|
}, |
|
{ |
|
"current_steps": 64, |
|
"loss": 1.029, |
|
"learning_rate": 0.000165, |
|
"epoch": 0.93 |
|
}, |
|
{ |
|
"current_steps": 65, |
|
"loss": 1.4441, |
|
"learning_rate": 0.000168, |
|
"epoch": 0.94 |
|
}, |
|
{ |
|
"current_steps": 66, |
|
"loss": 1.1804, |
|
"learning_rate": 0.00017099999999999998, |
|
"epoch": 0.96 |
|
}, |
|
{ |
|
"current_steps": 67, |
|
"loss": 1.2868, |
|
"learning_rate": 0.00017399999999999997, |
|
"epoch": 0.97 |
|
}, |
|
{ |
|
"current_steps": 68, |
|
"loss": 1.1724, |
|
"learning_rate": 0.00017699999999999997, |
|
"epoch": 0.99 |
|
}, |
|
{ |
|
"current_steps": 69, |
|
"loss": 1.4346, |
|
"learning_rate": 0.00017999999999999998, |
|
"epoch": 1.0 |
|
}, |
|
{ |
|
"current_steps": 70, |
|
"loss": 1.0183, |
|
"learning_rate": 0.00018299999999999998, |
|
"epoch": 1.01 |
|
}, |
|
{ |
|
"current_steps": 71, |
|
"loss": 1.1259, |
|
"learning_rate": 0.000186, |
|
"epoch": 1.03 |
|
}, |
|
{ |
|
"current_steps": 72, |
|
"loss": 1.1713, |
|
"learning_rate": 0.00018899999999999999, |
|
"epoch": 1.04 |
|
}, |
|
{ |
|
"current_steps": 73, |
|
"loss": 1.0773, |
|
"learning_rate": 0.00019199999999999998, |
|
"epoch": 1.06 |
|
}, |
|
{ |
|
"current_steps": 74, |
|
"loss": 1.2956, |
|
"learning_rate": 0.000195, |
|
"epoch": 1.07 |
|
}, |
|
{ |
|
"current_steps": 75, |
|
"loss": 0.9359, |
|
"learning_rate": 0.000198, |
|
"epoch": 1.09 |
|
}, |
|
{ |
|
"current_steps": 76, |
|
"loss": 0.9838, |
|
"learning_rate": 0.000201, |
|
"epoch": 1.1 |
|
}, |
|
{ |
|
"current_steps": 77, |
|
"loss": 0.9488, |
|
"learning_rate": 0.000204, |
|
"epoch": 1.11 |
|
}, |
|
{ |
|
"current_steps": 78, |
|
"loss": 1.0748, |
|
"learning_rate": 0.00020699999999999996, |
|
"epoch": 1.13 |
|
}, |
|
{ |
|
"current_steps": 79, |
|
"loss": 1.0914, |
|
"learning_rate": 0.00020999999999999998, |
|
"epoch": 1.14 |
|
}, |
|
{ |
|
"current_steps": 80, |
|
"loss": 0.5364, |
|
"learning_rate": 0.00021299999999999997, |
|
"epoch": 1.16 |
|
}, |
|
{ |
|
"current_steps": 81, |
|
"loss": 0.4909, |
|
"learning_rate": 0.00021599999999999996, |
|
"epoch": 1.17 |
|
}, |
|
{ |
|
"current_steps": 82, |
|
"loss": 1.0176, |
|
"learning_rate": 0.00021899999999999998, |
|
"epoch": 1.19 |
|
}, |
|
{ |
|
"current_steps": 83, |
|
"loss": 1.0543, |
|
"learning_rate": 0.00022199999999999998, |
|
"epoch": 1.2 |
|
}, |
|
{ |
|
"current_steps": 84, |
|
"loss": 0.9092, |
|
"learning_rate": 0.000225, |
|
"epoch": 1.21 |
|
}, |
|
{ |
|
"current_steps": 85, |
|
"loss": 0.5678, |
|
"learning_rate": 0.00022799999999999999, |
|
"epoch": 1.23 |
|
}, |
|
{ |
|
"current_steps": 86, |
|
"loss": 0.8385, |
|
"learning_rate": 0.00023099999999999998, |
|
"epoch": 1.24 |
|
}, |
|
{ |
|
"current_steps": 87, |
|
"loss": 1.6241, |
|
"learning_rate": 0.000234, |
|
"epoch": 1.26 |
|
}, |
|
{ |
|
"current_steps": 88, |
|
"loss": 0.8294, |
|
"learning_rate": 0.000237, |
|
"epoch": 1.27 |
|
}, |
|
{ |
|
"current_steps": 89, |
|
"loss": 1.2953, |
|
"learning_rate": 0.00023999999999999998, |
|
"epoch": 1.29 |
|
}, |
|
{ |
|
"current_steps": 90, |
|
"loss": 0.5297, |
|
"learning_rate": 0.000243, |
|
"epoch": 1.3 |
|
}, |
|
{ |
|
"current_steps": 91, |
|
"loss": 1.1592, |
|
"learning_rate": 0.00024599999999999996, |
|
"epoch": 1.31 |
|
}, |
|
{ |
|
"current_steps": 92, |
|
"loss": 1.1055, |
|
"learning_rate": 0.000249, |
|
"epoch": 1.33 |
|
}, |
|
{ |
|
"current_steps": 93, |
|
"loss": 0.9804, |
|
"learning_rate": 0.00025199999999999995, |
|
"epoch": 1.34 |
|
}, |
|
{ |
|
"current_steps": 94, |
|
"loss": 0.8683, |
|
"learning_rate": 0.00025499999999999996, |
|
"epoch": 1.36 |
|
}, |
|
{ |
|
"current_steps": 95, |
|
"loss": 0.9698, |
|
"learning_rate": 0.000258, |
|
"epoch": 1.37 |
|
}, |
|
{ |
|
"current_steps": 96, |
|
"loss": 1.037, |
|
"learning_rate": 0.000261, |
|
"epoch": 1.39 |
|
}, |
|
{ |
|
"current_steps": 97, |
|
"loss": 0.5479, |
|
"learning_rate": 0.00026399999999999997, |
|
"epoch": 1.4 |
|
}, |
|
{ |
|
"current_steps": 98, |
|
"loss": 0.598, |
|
"learning_rate": 0.000267, |
|
"epoch": 1.41 |
|
}, |
|
{ |
|
"current_steps": 99, |
|
"loss": 0.3627, |
|
"learning_rate": 0.00027, |
|
"epoch": 1.43 |
|
}, |
|
{ |
|
"current_steps": 100, |
|
"loss": 0.8042, |
|
"learning_rate": 0.00027299999999999997, |
|
"epoch": 1.44 |
|
}, |
|
{ |
|
"current_steps": 101, |
|
"loss": 1.0378, |
|
"learning_rate": 0.000276, |
|
"epoch": 1.46 |
|
}, |
|
{ |
|
"current_steps": 102, |
|
"loss": 1.0192, |
|
"learning_rate": 0.000279, |
|
"epoch": 1.47 |
|
}, |
|
{ |
|
"current_steps": 103, |
|
"loss": 1.4654, |
|
"learning_rate": 0.00028199999999999997, |
|
"epoch": 1.49 |
|
}, |
|
{ |
|
"current_steps": 104, |
|
"loss": 1.0614, |
|
"learning_rate": 0.000285, |
|
"epoch": 1.5 |
|
}, |
|
{ |
|
"current_steps": 105, |
|
"loss": 0.779, |
|
"learning_rate": 0.00028799999999999995, |
|
"epoch": 1.51 |
|
}, |
|
{ |
|
"current_steps": 106, |
|
"loss": 1.0255, |
|
"learning_rate": 0.00029099999999999997, |
|
"epoch": 1.53 |
|
}, |
|
{ |
|
"current_steps": 107, |
|
"loss": 1.0924, |
|
"learning_rate": 0.000294, |
|
"epoch": 1.54 |
|
}, |
|
{ |
|
"current_steps": 108, |
|
"loss": 1.1016, |
|
"learning_rate": 0.00029699999999999996, |
|
"epoch": 1.56 |
|
}, |
|
{ |
|
"current_steps": 109, |
|
"loss": 0.8748, |
|
"learning_rate": 0.0003, |
|
"epoch": 1.57 |
|
}, |
|
{ |
|
"current_steps": 110, |
|
"loss": 0.8048, |
|
"learning_rate": 0.00029727272727272724, |
|
"epoch": 1.59 |
|
}, |
|
{ |
|
"current_steps": 111, |
|
"loss": 1.0229, |
|
"learning_rate": 0.0002945454545454545, |
|
"epoch": 1.6 |
|
}, |
|
{ |
|
"current_steps": 112, |
|
"loss": 0.9677, |
|
"learning_rate": 0.0002918181818181818, |
|
"epoch": 1.61 |
|
}, |
|
{ |
|
"current_steps": 113, |
|
"loss": 0.5605, |
|
"learning_rate": 0.00028909090909090904, |
|
"epoch": 1.63 |
|
}, |
|
{ |
|
"current_steps": 114, |
|
"loss": 0.9392, |
|
"learning_rate": 0.00028636363636363636, |
|
"epoch": 1.64 |
|
}, |
|
{ |
|
"current_steps": 115, |
|
"loss": 1.0068, |
|
"learning_rate": 0.0002836363636363636, |
|
"epoch": 1.66 |
|
}, |
|
{ |
|
"current_steps": 116, |
|
"loss": 0.898, |
|
"learning_rate": 0.0002809090909090909, |
|
"epoch": 1.67 |
|
}, |
|
{ |
|
"current_steps": 117, |
|
"loss": 1.1297, |
|
"learning_rate": 0.00027818181818181815, |
|
"epoch": 1.69 |
|
}, |
|
{ |
|
"current_steps": 118, |
|
"loss": 0.8696, |
|
"learning_rate": 0.0002754545454545454, |
|
"epoch": 1.7 |
|
}, |
|
{ |
|
"current_steps": 119, |
|
"loss": 0.975, |
|
"learning_rate": 0.0002727272727272727, |
|
"epoch": 1.71 |
|
}, |
|
{ |
|
"current_steps": 120, |
|
"loss": 1.107, |
|
"learning_rate": 0.00027, |
|
"epoch": 1.73 |
|
}, |
|
{ |
|
"current_steps": 121, |
|
"loss": 1.1696, |
|
"learning_rate": 0.0002672727272727272, |
|
"epoch": 1.74 |
|
}, |
|
{ |
|
"current_steps": 122, |
|
"loss": 0.7181, |
|
"learning_rate": 0.00026454545454545453, |
|
"epoch": 1.76 |
|
}, |
|
{ |
|
"current_steps": 123, |
|
"loss": 0.4008, |
|
"learning_rate": 0.0002618181818181818, |
|
"epoch": 1.77 |
|
}, |
|
{ |
|
"current_steps": 124, |
|
"loss": 0.6227, |
|
"learning_rate": 0.00025909090909090907, |
|
"epoch": 1.79 |
|
}, |
|
{ |
|
"current_steps": 125, |
|
"loss": 1.4091, |
|
"learning_rate": 0.00025636363636363633, |
|
"epoch": 1.8 |
|
}, |
|
{ |
|
"current_steps": 126, |
|
"loss": 0.7953, |
|
"learning_rate": 0.0002536363636363636, |
|
"epoch": 1.81 |
|
}, |
|
{ |
|
"current_steps": 127, |
|
"loss": 1.1635, |
|
"learning_rate": 0.00025090909090909086, |
|
"epoch": 1.83 |
|
}, |
|
{ |
|
"current_steps": 128, |
|
"loss": 0.6109, |
|
"learning_rate": 0.0002481818181818182, |
|
"epoch": 1.84 |
|
}, |
|
{ |
|
"current_steps": 129, |
|
"loss": 0.7244, |
|
"learning_rate": 0.00024545454545454545, |
|
"epoch": 1.86 |
|
}, |
|
{ |
|
"current_steps": 130, |
|
"loss": 1.0868, |
|
"learning_rate": 0.0002427272727272727, |
|
"epoch": 1.87 |
|
}, |
|
{ |
|
"current_steps": 131, |
|
"loss": 1.1968, |
|
"learning_rate": 0.00023999999999999998, |
|
"epoch": 1.89 |
|
}, |
|
{ |
|
"current_steps": 132, |
|
"loss": 1.109, |
|
"learning_rate": 0.00023727272727272724, |
|
"epoch": 1.9 |
|
}, |
|
{ |
|
"current_steps": 133, |
|
"loss": 0.8744, |
|
"learning_rate": 0.00023454545454545454, |
|
"epoch": 1.91 |
|
}, |
|
{ |
|
"current_steps": 134, |
|
"loss": 0.6971, |
|
"learning_rate": 0.0002318181818181818, |
|
"epoch": 1.93 |
|
}, |
|
{ |
|
"current_steps": 135, |
|
"loss": 0.827, |
|
"learning_rate": 0.00022909090909090907, |
|
"epoch": 1.94 |
|
}, |
|
{ |
|
"current_steps": 136, |
|
"loss": 0.8474, |
|
"learning_rate": 0.00022636363636363633, |
|
"epoch": 1.96 |
|
}, |
|
{ |
|
"current_steps": 137, |
|
"loss": 0.8051, |
|
"learning_rate": 0.00022363636363636363, |
|
"epoch": 1.97 |
|
}, |
|
{ |
|
"current_steps": 138, |
|
"loss": 0.8532, |
|
"learning_rate": 0.0002209090909090909, |
|
"epoch": 1.99 |
|
}, |
|
{ |
|
"current_steps": 139, |
|
"loss": 0.8277, |
|
"learning_rate": 0.00021818181818181816, |
|
"epoch": 2.0 |
|
}, |
|
{ |
|
"current_steps": 140, |
|
"loss": 0.3926, |
|
"learning_rate": 0.00021545454545454542, |
|
"epoch": 2.01 |
|
}, |
|
{ |
|
"current_steps": 141, |
|
"loss": 0.5717, |
|
"learning_rate": 0.00021272727272727272, |
|
"epoch": 2.03 |
|
}, |
|
{ |
|
"current_steps": 142, |
|
"loss": 0.6956, |
|
"learning_rate": 0.00020999999999999998, |
|
"epoch": 2.04 |
|
}, |
|
{ |
|
"current_steps": 143, |
|
"loss": 0.6353, |
|
"learning_rate": 0.00020727272727272725, |
|
"epoch": 2.06 |
|
}, |
|
{ |
|
"current_steps": 144, |
|
"loss": 0.4248, |
|
"learning_rate": 0.0002045454545454545, |
|
"epoch": 2.07 |
|
}, |
|
{ |
|
"current_steps": 145, |
|
"loss": 0.6299, |
|
"learning_rate": 0.0002018181818181818, |
|
"epoch": 2.09 |
|
}, |
|
{ |
|
"current_steps": 146, |
|
"loss": 0.3415, |
|
"learning_rate": 0.0001990909090909091, |
|
"epoch": 2.1 |
|
}, |
|
{ |
|
"current_steps": 147, |
|
"loss": 0.4788, |
|
"learning_rate": 0.00019636363636363634, |
|
"epoch": 2.11 |
|
}, |
|
{ |
|
"current_steps": 148, |
|
"loss": 0.6898, |
|
"learning_rate": 0.00019363636363636363, |
|
"epoch": 2.13 |
|
}, |
|
{ |
|
"current_steps": 149, |
|
"loss": 0.4212, |
|
"learning_rate": 0.0001909090909090909, |
|
"epoch": 2.14 |
|
}, |
|
{ |
|
"current_steps": 150, |
|
"loss": 0.6855, |
|
"learning_rate": 0.0001881818181818182, |
|
"epoch": 2.16 |
|
}, |
|
{ |
|
"current_steps": 151, |
|
"loss": 0.4411, |
|
"learning_rate": 0.00018545454545454543, |
|
"epoch": 2.17 |
|
}, |
|
{ |
|
"current_steps": 152, |
|
"loss": 0.4706, |
|
"learning_rate": 0.00018272727272727272, |
|
"epoch": 2.19 |
|
}, |
|
{ |
|
"current_steps": 153, |
|
"loss": 0.6222, |
|
"learning_rate": 0.00017999999999999998, |
|
"epoch": 2.2 |
|
}, |
|
{ |
|
"current_steps": 154, |
|
"loss": 0.6584, |
|
"learning_rate": 0.00017727272727272728, |
|
"epoch": 2.21 |
|
}, |
|
{ |
|
"current_steps": 155, |
|
"loss": 0.6037, |
|
"learning_rate": 0.00017454545454545452, |
|
"epoch": 2.23 |
|
}, |
|
{ |
|
"current_steps": 156, |
|
"loss": 0.6478, |
|
"learning_rate": 0.0001718181818181818, |
|
"epoch": 2.24 |
|
}, |
|
{ |
|
"current_steps": 157, |
|
"loss": 0.4591, |
|
"learning_rate": 0.00016909090909090907, |
|
"epoch": 2.26 |
|
}, |
|
{ |
|
"current_steps": 158, |
|
"loss": 0.4085, |
|
"learning_rate": 0.00016636363636363637, |
|
"epoch": 2.27 |
|
}, |
|
{ |
|
"current_steps": 159, |
|
"loss": 0.6747, |
|
"learning_rate": 0.0001636363636363636, |
|
"epoch": 2.29 |
|
}, |
|
{ |
|
"current_steps": 160, |
|
"loss": 0.4008, |
|
"learning_rate": 0.0001609090909090909, |
|
"epoch": 2.3 |
|
}, |
|
{ |
|
"current_steps": 161, |
|
"loss": 0.671, |
|
"learning_rate": 0.00015818181818181816, |
|
"epoch": 2.31 |
|
}, |
|
{ |
|
"current_steps": 162, |
|
"loss": 0.593, |
|
"learning_rate": 0.00015545454545454546, |
|
"epoch": 2.33 |
|
}, |
|
{ |
|
"current_steps": 163, |
|
"loss": 0.4881, |
|
"learning_rate": 0.0001527272727272727, |
|
"epoch": 2.34 |
|
}, |
|
{ |
|
"current_steps": 164, |
|
"loss": 0.6749, |
|
"learning_rate": 0.00015, |
|
"epoch": 2.36 |
|
}, |
|
{ |
|
"current_steps": 165, |
|
"loss": 0.7904, |
|
"learning_rate": 0.00014727272727272725, |
|
"epoch": 2.37 |
|
}, |
|
{ |
|
"current_steps": 166, |
|
"loss": 0.7036, |
|
"learning_rate": 0.00014454545454545452, |
|
"epoch": 2.39 |
|
}, |
|
{ |
|
"current_steps": 167, |
|
"loss": 0.5043, |
|
"learning_rate": 0.0001418181818181818, |
|
"epoch": 2.4 |
|
}, |
|
{ |
|
"current_steps": 168, |
|
"loss": 0.7245, |
|
"learning_rate": 0.00013909090909090908, |
|
"epoch": 2.41 |
|
}, |
|
{ |
|
"current_steps": 169, |
|
"loss": 0.7101, |
|
"learning_rate": 0.00013636363636363634, |
|
"epoch": 2.43 |
|
}, |
|
{ |
|
"current_steps": 170, |
|
"loss": 0.3898, |
|
"learning_rate": 0.0001336363636363636, |
|
"epoch": 2.44 |
|
}, |
|
{ |
|
"current_steps": 171, |
|
"loss": 0.4639, |
|
"learning_rate": 0.0001309090909090909, |
|
"epoch": 2.46 |
|
}, |
|
{ |
|
"current_steps": 172, |
|
"loss": 0.686, |
|
"learning_rate": 0.00012818181818181817, |
|
"epoch": 2.47 |
|
}, |
|
{ |
|
"current_steps": 173, |
|
"loss": 0.4952, |
|
"learning_rate": 0.00012545454545454543, |
|
"epoch": 2.49 |
|
}, |
|
{ |
|
"current_steps": 174, |
|
"loss": 0.2727, |
|
"learning_rate": 0.00012272727272727272, |
|
"epoch": 2.5 |
|
}, |
|
{ |
|
"current_steps": 175, |
|
"loss": 0.3428, |
|
"learning_rate": 0.00011999999999999999, |
|
"epoch": 2.51 |
|
}, |
|
{ |
|
"current_steps": 176, |
|
"loss": 0.253, |
|
"learning_rate": 0.00011727272727272727, |
|
"epoch": 2.53 |
|
}, |
|
{ |
|
"current_steps": 177, |
|
"loss": 0.5778, |
|
"learning_rate": 0.00011454545454545453, |
|
"epoch": 2.54 |
|
}, |
|
{ |
|
"current_steps": 178, |
|
"loss": 0.639, |
|
"learning_rate": 0.00011181818181818181, |
|
"epoch": 2.56 |
|
}, |
|
{ |
|
"current_steps": 179, |
|
"loss": 0.7327, |
|
"learning_rate": 0.00010909090909090908, |
|
"epoch": 2.57 |
|
}, |
|
{ |
|
"current_steps": 180, |
|
"loss": 0.4956, |
|
"learning_rate": 0.00010636363636363636, |
|
"epoch": 2.59 |
|
}, |
|
{ |
|
"current_steps": 181, |
|
"loss": 0.364, |
|
"learning_rate": 0.00010363636363636362, |
|
"epoch": 2.6 |
|
}, |
|
{ |
|
"current_steps": 182, |
|
"loss": 0.4497, |
|
"learning_rate": 0.0001009090909090909, |
|
"epoch": 2.61 |
|
}, |
|
{ |
|
"current_steps": 183, |
|
"loss": 0.7653, |
|
"learning_rate": 9.818181818181817e-05, |
|
"epoch": 2.63 |
|
}, |
|
{ |
|
"current_steps": 184, |
|
"loss": 0.6586, |
|
"learning_rate": 9.545454545454545e-05, |
|
"epoch": 2.64 |
|
}, |
|
{ |
|
"current_steps": 185, |
|
"loss": 0.4404, |
|
"learning_rate": 9.272727272727271e-05, |
|
"epoch": 2.66 |
|
}, |
|
{ |
|
"current_steps": 186, |
|
"loss": 0.7484, |
|
"learning_rate": 8.999999999999999e-05, |
|
"epoch": 2.67 |
|
}, |
|
{ |
|
"current_steps": 187, |
|
"loss": 0.6176, |
|
"learning_rate": 8.727272727272726e-05, |
|
"epoch": 2.69 |
|
}, |
|
{ |
|
"current_steps": 188, |
|
"loss": 0.7404, |
|
"learning_rate": 8.454545454545454e-05, |
|
"epoch": 2.7 |
|
}, |
|
{ |
|
"current_steps": 189, |
|
"loss": 0.8124, |
|
"learning_rate": 8.18181818181818e-05, |
|
"epoch": 2.71 |
|
}, |
|
{ |
|
"current_steps": 190, |
|
"loss": 0.6525, |
|
"learning_rate": 7.909090909090908e-05, |
|
"epoch": 2.73 |
|
}, |
|
{ |
|
"current_steps": 191, |
|
"loss": 0.5986, |
|
"learning_rate": 7.636363636363635e-05, |
|
"epoch": 2.74 |
|
}, |
|
{ |
|
"current_steps": 192, |
|
"loss": 0.294, |
|
"learning_rate": 7.363636363636363e-05, |
|
"epoch": 2.76 |
|
}, |
|
{ |
|
"current_steps": 193, |
|
"loss": 0.2973, |
|
"learning_rate": 7.09090909090909e-05, |
|
"epoch": 2.77 |
|
}, |
|
{ |
|
"current_steps": 194, |
|
"loss": 0.3589, |
|
"learning_rate": 6.818181818181817e-05, |
|
"epoch": 2.79 |
|
}, |
|
{ |
|
"current_steps": 195, |
|
"loss": 0.78, |
|
"learning_rate": 6.545454545454545e-05, |
|
"epoch": 2.8 |
|
}, |
|
{ |
|
"current_steps": 196, |
|
"loss": 0.4056, |
|
"learning_rate": 6.272727272727272e-05, |
|
"epoch": 2.81 |
|
}, |
|
{ |
|
"current_steps": 197, |
|
"loss": 0.5843, |
|
"learning_rate": 5.9999999999999995e-05, |
|
"epoch": 2.83 |
|
}, |
|
{ |
|
"current_steps": 198, |
|
"loss": 0.5745, |
|
"learning_rate": 5.727272727272727e-05, |
|
"epoch": 2.84 |
|
}, |
|
{ |
|
"current_steps": 199, |
|
"loss": 0.2763, |
|
"learning_rate": 5.454545454545454e-05, |
|
"epoch": 2.86 |
|
}, |
|
{ |
|
"current_steps": 200, |
|
"loss": 0.5494, |
|
"learning_rate": 5.181818181818181e-05, |
|
"epoch": 2.87 |
|
}, |
|
{ |
|
"current_steps": 201, |
|
"loss": 0.4962, |
|
"learning_rate": 4.9090909090909084e-05, |
|
"epoch": 2.89 |
|
}, |
|
{ |
|
"current_steps": 202, |
|
"loss": 0.5864, |
|
"learning_rate": 4.6363636363636356e-05, |
|
"epoch": 2.9 |
|
}, |
|
{ |
|
"current_steps": 203, |
|
"loss": 0.3165, |
|
"learning_rate": 4.363636363636363e-05, |
|
"epoch": 2.91 |
|
}, |
|
{ |
|
"current_steps": 204, |
|
"loss": 0.5969, |
|
"learning_rate": 4.09090909090909e-05, |
|
"epoch": 2.93 |
|
}, |
|
{ |
|
"current_steps": 205, |
|
"loss": 0.3003, |
|
"learning_rate": 3.8181818181818174e-05, |
|
"epoch": 2.94 |
|
}, |
|
{ |
|
"current_steps": 206, |
|
"loss": 0.6398, |
|
"learning_rate": 3.545454545454545e-05, |
|
"epoch": 2.96 |
|
}, |
|
{ |
|
"current_steps": 207, |
|
"loss": 0.604, |
|
"learning_rate": 3.2727272727272725e-05, |
|
"epoch": 2.97 |
|
}, |
|
{ |
|
"current_steps": 208, |
|
"loss": 0.6389, |
|
"learning_rate": 2.9999999999999997e-05, |
|
"epoch": 2.99 |
|
}, |
|
{ |
|
"current_steps": 209, |
|
"loss": 0.5865, |
|
"learning_rate": 2.727272727272727e-05, |
|
"epoch": 3.0 |
|
}, |
|
{ |
|
"current_steps": 209, |
|
"loss": 0.5865, |
|
"learning_rate": 2.727272727272727e-05, |
|
"epoch": 3.0 |
|
} |
|
] |