End of training

README.md

@@ -105,7 +105,7 @@ xformers_attention: true
 
 This model is a fine-tuned version of [NousResearch/Yarn-Mistral-7b-128k](https://huggingface.co/NousResearch/Yarn-Mistral-7b-128k) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8842
+- Loss: 0.8843
 
 ## Model description
 
@@ -143,8 +143,8 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 1.1322        | 0.0008 | 1    | 1.5847          |
-| 1.2929        | 0.0210 | 25   | 0.9329          |
-| 1.1451        | 0.0420 | 50   | 0.8842          |
+| 1.2911        | 0.0210 | 25   | 0.9318          |
+| 1.1406        | 0.0420 | 50   | 0.8843          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "down_proj",
-    "k_proj",
     "o_proj",
-    "up_proj",
+    "k_proj",
     "gate_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8e2ec2c8c08e3ed12169c7882f7f545995fb3c4e81c571bc645d5dd040544fe
+oid sha256:61ce9568dcfea58192db0c2b38acc6f8ff08a34a86f0a0299e64ac034b8cac4d
 size 335706186

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d117bbf168d69f60a424a760bef6fccfca0091958260bd87f76e3d6a8ae886d1
+oid sha256:d8c4390df21e68610fbe4614aa868b686c741edd9e413d9af9231973d4a6652c
 size 335604696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1cacc4070899ec6140ce624ad9111e3cd3116b234a9d45e345cdf260945df5f
+oid sha256:06ea9b0e7461d608bdc78005e0ce4a13003303f92c48ee59de6dd64648eec034
 size 6776