update model card README.md

README.md

@@ -13,10 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_base_cased_MultiClass_Sentiment_A
 
-This model was trained from scratch on the None dataset.
+This model is a fine-tuned version of [HMEXBI/bert_base_cased_MultiClass](https://huggingface.co/HMEXBI/bert_base_cased_MultiClass) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4761
-- Accuracy: 0.7647
+- Loss: 1.0470
+- Accuracy: 0.8093
 
 ## Model description
 
@@ -41,17 +41,15 @@ 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: 5
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 401  | 1.4504          | 0.7563   |
-| 0.2511        | 2.0   | 802  | 1.4350          | 0.7591   |
-| 0.2382        | 3.0   | 1203 | 1.4892          | 0.7647   |
-| 0.0975        | 4.0   | 1604 | 1.4405          | 0.7759   |
-| 0.0494        | 5.0   | 2005 | 1.4761          | 0.7647   |
+| No log        | 1.0   | 357  | 1.0515          | 0.7700   |
+| 0.3375        | 2.0   | 714  | 1.0273          | 0.7854   |
+| 0.1605        | 3.0   | 1071 | 1.0470          | 0.8093   |
 
 
 ### Framework versions