update model card README.md

README.md

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [vinai/bertweet-base](https://huggingface.co/vinai/bertweet-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0590
+- Loss: 0.0490
 
 ## Model description
 
@@ -38,20 +38,22 @@ 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: 3.0
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.1308        | 1.0   | 1465 | 0.1093          |
-| 0.0665        | 2.0   | 2930 | 0.0638          |
-| 0.0579        | 3.0   | 4395 | 0.0590          |
+| 0.0787        | 1.0   | 1465 | 0.0751          |
+| 0.0662        | 2.0   | 2930 | 0.0628          |
+| 0.053         | 3.0   | 4395 | 0.0531          |
+| 0.0452        | 4.0   | 5860 | 0.0490          |
 
 
 ### Framework versions
 
 - Transformers 4.15.0
 - Pytorch 1.10.0+cu111
-- Datasets 1.17.0
+- Datasets 1.18.0
 - Tokenizers 0.10.3