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 [ai-forever/rugpt3small_based_on_gpt2](https://huggingface.co/ai-forever/rugpt3small_based_on_gpt2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.5235
+- Loss: 2.7020
 
 ## Model description
 
@@ -38,15 +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
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 5    | 3.7794          |
-| No log        | 2.0   | 10   | 3.5884          |
-| No log        | 3.0   | 15   | 3.5235          |
+| No log        | 1.0   | 5    | 3.7450          |
+| No log        | 2.0   | 10   | 3.4688          |
+| No log        | 3.0   | 15   | 3.2667          |
+| No log        | 4.0   | 20   | 3.1067          |
+| No log        | 5.0   | 25   | 2.9798          |
+| No log        | 6.0   | 30   | 2.8797          |
+| No log        | 7.0   | 35   | 2.8035          |
+| No log        | 8.0   | 40   | 2.7485          |
+| No log        | 9.0   | 45   | 2.7147          |
+| No log        | 10.0  | 50   | 2.7020          |
 
 
 ### Framework versions