Model save

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the dialogstudio dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1617
+- Loss: 1.8479
 
 ## Model description
 
@@ -45,17 +45,17 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.05
-- num_epochs: 7
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.7993        | 1.4   | 77   | 1.8588          |
-| 1.5367        | 2.8   | 154  | 1.8706          |
-| 1.1499        | 4.2   | 231  | 2.0429          |
-| 1.1036        | 5.6   | 308  | 2.1262          |
-| 0.9217        | 7.0   | 385  | 2.1617          |
+| 1.8459        | 0.6   | 33   | 1.8965          |
+| 1.7921        | 1.2   | 66   | 1.8626          |
+| 1.7595        | 1.8   | 99   | 1.8452          |
+| 1.6381        | 2.4   | 132  | 1.8500          |
+| 1.6185        | 3.0   | 165  | 1.8479          |
 
 
 ### Framework versions