update model card README.md

README.md

@@ -13,6 +13,8 @@ should probably proofread and complete it, then remove this comment. -->
 # gpt2lm
 
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2929
 
 ## Model description
 
@@ -41,10 +43,17 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1000
 - num_epochs: 1
-- mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 2.5666        | 0.16  | 5000  | 1.8018          |
+| 1.6685        | 0.31  | 10000 | 1.5932          |
+| 1.4956        | 0.47  | 15000 | 1.4797          |
+| 1.3802        | 0.62  | 20000 | 1.3924          |
+| 1.2885        | 0.78  | 25000 | 1.3243          |
+| 1.2355        | 0.93  | 30000 | 1.2929          |
 
 
 ### Framework versions