update ernie tiny acc (#1494)

Author: LiuChiachi

examples/model_compression/pp-minilm/README.md

@@ -45,7 +45,7 @@ PP-MiniLM 压缩方案以面向预训练模型的任务无关知识蒸馏(Task-a
 | TinyBERT<sub>6</sub>    | 59.7M   | 5.44B  | 1.66x   | 72.59 | 55.70 | 57.64   | 79.57 | 73.97 | 76.32       | 80.00 | 70.83       |
 | UER-py RoBERTa L6- H768 | 59.7M   | 5.44B  | 1.66x   | 69.62 | 66.45 | 59.91   | 76.89 | 71.36 | 71.05       | 82.87 | 71.16       |
 | RBT6, Chinese           | 59.7M   | 5.44B  | 1.66x   | 73.93 | 56.63 | 59.79   | 79.28 | 73.12 | 77.30       | 80.80 | 71.55       |
-| ERNIE-Tiny              | 90.7M   | 4.83B  | 1.89x   | 70.67 | 55.60 | 59.91   | 75.74 | 71.36 | 67.11       | 76.70 | 68.16       |
+| ERNIE-Tiny              | 90.7M   | 4.83B  | 1.89x   | 71.55 | 58.34 | 61.41   | 76.81 | 71.46 | 72.04       | 79.13 | 70.11       |
 | PP-MiniLM 6L-768H       | 59.7M   | 5.44B  | 1.66x   | 74.14 | 57.43 | 61.75   | 81.01 | 76.17 | 86.18       | 79.17 | 73.69       |
 | PP-MiniLM 裁剪后        | 49.1M   | 4.08B  | 2.00x   | 73.91 | 57.44 | 61.64   | 81.10 | 75.59 | 85.86       | 78.53 | 73.44       |
 | PP-MiniLM 量化后        | 49.2M   | -      | 4.15x   | 74.00 | 57.37 | 61.33   | 81.09 | 75.56 | 85.85       | 78.57 | 73.40       |