update model card README.md

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [hfl/chinese-pert-large](https://huggingface.co/hfl/chinese-pert-large) on the cmrc2018 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5678
+- Loss: 0.8522
 
 ## Model description
 
@@ -41,22 +41,17 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 5
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss |
-|:-------------:|:-----:|:-----:|:---------------:|
-| 1.1216        | 1.0   | 1200  | 0.7522          |
-| 0.7144        | 2.0   | 2400  | 0.6930          |
-| 0.5018        | 3.0   | 3600  | 0.7647          |
-| 0.3669        | 4.0   | 4800  | 0.8131          |
-| 0.278         | 5.0   | 6000  | 0.9423          |
-| 0.2087        | 6.0   | 7200  | 1.0350          |
-| 0.1477        | 7.0   | 8400  | 1.1962          |
-| 0.1235        | 8.0   | 9600  | 1.3345          |
-| 0.0937        | 9.0   | 10800 | 1.4887          |
-| 0.0705        | 10.0  | 12000 | 1.5678          |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0891        | 1.0   | 1200 | 0.7374          |
+| 0.712         | 2.0   | 2400 | 0.6467          |
+| 0.5068        | 3.0   | 3600 | 0.7374          |
+| 0.3865        | 4.0   | 4800 | 0.7852          |
+| 0.3197        | 5.0   | 6000 | 0.8522          |
 
 
 ### Framework versions