update model card README.md

README.md

@@ -13,12 +13,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [theta/gpt2-reporter](https://huggingface.co/theta/gpt2-reporter) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 2.4658
-- eval_runtime: 56.1154
-- eval_samples_per_second: 49.826
-- eval_steps_per_second: 3.119
-- epoch: 0.35
-- step: 6400
+- eval_loss: 2.4381
+- eval_runtime: 28.164
+- eval_samples_per_second: 50.667
+- eval_steps_per_second: 3.196
+- epoch: 0.55
+- step: 5200
 
 ## Model description
 
@@ -49,5 +49,5 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - Transformers 4.25.1
-- Pytorch 1.13.0+cu116
+- Pytorch 1.13.1+cu116
 - Tokenizers 0.13.2