update model card README.md

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5882
-- Accuracy: 0.86
+- Loss: 0.6310
+- Accuracy: 0.84
 
 ## Model description
 
@@ -45,33 +45,23 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 20
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.99  | 56   | 2.1716          | 0.42     |
-| No log        | 1.99  | 112  | 1.6734          | 0.42     |
-| No log        | 2.99  | 168  | 1.3642          | 0.57     |
-| 1.7593        | 3.99  | 224  | 1.0807          | 0.7      |
-| 1.7593        | 4.99  | 280  | 0.8708          | 0.73     |
-| 1.7593        | 5.99  | 336  | 0.7217          | 0.76     |
-| 1.7593        | 6.99  | 392  | 0.6897          | 0.84     |
-| 0.7084        | 7.99  | 448  | 0.6094          | 0.83     |
-| 0.7084        | 8.99  | 504  | 0.6122          | 0.85     |
-| 0.7084        | 9.99  | 560  | 0.5403          | 0.84     |
-| 0.7084        | 10.99 | 616  | 0.4917          | 0.85     |
-| 0.2248        | 11.99 | 672  | 0.5181          | 0.83     |
-| 0.2248        | 12.99 | 728  | 0.5342          | 0.87     |
-| 0.2248        | 13.99 | 784  | 0.5473          | 0.86     |
-| 0.2248        | 14.99 | 840  | 0.5961          | 0.86     |
-| 0.0508        | 15.99 | 896  | 0.5873          | 0.86     |
-| 0.0508        | 16.99 | 952  | 0.5756          | 0.86     |
-| 0.0508        | 17.99 | 1008 | 0.5925          | 0.86     |
-| 0.0508        | 18.99 | 1064 | 0.5922          | 0.87     |
-| 0.0206        | 19.99 | 1120 | 0.5882          | 0.86     |
+| No log        | 0.99  | 56   | 1.9996          | 0.4      |
+| 2.0202        | 1.99  | 112  | 1.5102          | 0.51     |
+| 2.0202        | 2.99  | 168  | 1.2698          | 0.67     |
+| 1.289         | 3.99  | 224  | 1.0391          | 0.73     |
+| 1.289         | 4.99  | 280  | 0.8988          | 0.75     |
+| 0.8787        | 5.99  | 336  | 0.7758          | 0.82     |
+| 0.8787        | 6.99  | 392  | 0.6896          | 0.83     |
+| 0.6254        | 7.99  | 448  | 0.6936          | 0.81     |
+| 0.6254        | 8.99  | 504  | 0.6433          | 0.84     |
+| 0.4879        | 9.99  | 560  | 0.6310          | 0.84     |
 
 
 ### Framework versions