update model card README.md

README.md

@@ -14,7 +14,7 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0106
+- Loss: 0.9521
 
 ## Model description
 
@@ -34,27 +34,18 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 8    | 5.5543          |
-| No log        | 2.0   | 16   | 4.7926          |
-| No log        | 3.0   | 24   | 4.0727          |
-| No log        | 4.0   | 32   | 3.4744          |
-| No log        | 5.0   | 40   | 3.0025          |
-| No log        | 6.0   | 48   | 2.5881          |
-| No log        | 7.0   | 56   | 2.2895          |
-| No log        | 8.0   | 64   | 2.1821          |
-| No log        | 9.0   | 72   | 2.0595          |
-| No log        | 10.0  | 80   | 2.0106          |
+| 0.8543        | 1.0   | 3016 | 0.9521          |
 
 
 ### Framework versions