Llama-2-7b-chat-hf-formula-peft

README.md

@@ -13,6 +13,8 @@ should probably proofread and complete it, then remove this comment. -->
 # Llama-2-7b-chat-hf-formula-peft
 
 This model is a fine-tuned version of [NousResearch/Llama-2-7b-chat-hf](https://huggingface.co/NousResearch/Llama-2-7b-chat-hf) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.0978
 
 ## Model description
 
@@ -44,6 +46,15 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 4.0878        | 1.43  | 10   | 3.5298          |
+| 2.7514        | 2.86  | 20   | 2.5999          |
+| 1.854         | 4.29  | 30   | 2.2461          |
+| 1.4716        | 5.71  | 40   | 2.1421          |
+| 1.3602        | 7.14  | 50   | 2.1016          |
+| 1.2029        | 8.57  | 60   | 2.0985          |
+| 1.1427        | 10.0  | 70   | 2.0978          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55865b86efbea088936fd2f2a97ffb086b1d2dda6cd51cce69f31ddd293e31ff
+oid sha256:2214f28b30579be29788e2a080ea339e509923551bb2e714c9eb36e1a45ff897
 size 134264202

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1461dba4797bde98de8f7303eaa811666f5dd1431838adccca7447489eafaf75
+oid sha256:16e6728232aa17e18af041b60632a992d653c3308e50f2c33c2e4dad9af0d61c
 size 4536