update model card README.md

README.md

@@ -11,9 +11,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gpt2-reporter
 
-This model is a fine-tuned version of [uer/gpt2-chinese-cluecorpussmall](https://huggingface.co/uer/gpt2-chinese-cluecorpussmall) on an unknown dataset.
+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:
-- Loss: 2.4819
+- eval_loss: 2.4767
+- eval_runtime: 105.1103
+- eval_samples_per_second: 23.632
+- eval_steps_per_second: 2.959
+- epoch: 0.25
+- step: 4000
 
 ## Model description
 
@@ -41,19 +46,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 500
 - num_epochs: 2
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 2.7694        | 0.28  | 400  | 2.5751          |
-| 2.6336        | 0.56  | 800  | 2.5318          |
-| 2.5564        | 0.84  | 1200 | 2.5071          |
-| 2.482         | 1.12  | 1600 | 2.4993          |
-| 2.4243        | 1.4   | 2000 | 2.4910          |
-| 2.4009        | 1.68  | 2400 | 2.4850          |
-| 2.3865        | 1.96  | 2800 | 2.4819          |
-
-
 ### Framework versions
 
 - Transformers 4.25.1