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 [benjamin/gerpt2-large](https://huggingface.co/benjamin/gerpt2-large) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.2487
+- Loss: 3.4257
 
 ## Model description
 
@@ -40,25 +40,21 @@ 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_steps: 500
-- num_epochs: 8
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 3.5332        | 1.0   | 11347 | 3.5015          |
-| 3.1448        | 2.0   | 22694 | 3.4149          |
-| 2.8081        | 3.0   | 34041 | 3.4495          |
-| 2.4535        | 4.0   | 45388 | 3.5714          |
-| 2.1844        | 5.0   | 56735 | 3.7579          |
-| 1.9625        | 6.0   | 68082 | 3.9492          |
-| 1.7585        | 7.0   | 79429 | 4.1280          |
-| 1.6407        | 8.0   | 90776 | 4.2487          |
+| 3.4094        | 1.0   | 11308 | 3.3838          |
+| 3.0445        | 2.0   | 22616 | 3.3107          |
+| 2.7161        | 3.0   | 33924 | 3.3409          |
+| 2.4793        | 4.0   | 45232 | 3.4257          |
 
 
 ### Framework versions
 
-- Transformers 4.19.4
+- Transformers 4.20.1
 - Pytorch 1.11.0+cu113
 - Datasets 2.3.2
 - Tokenizers 0.12.1