End of training

README.md

@@ -102,7 +102,7 @@ xformers_attention: true
 
 This model is a fine-tuned version of [NousResearch/Nous-Hermes-2-Mistral-7B-DPO](https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2026
+- Loss: 1.2036
 
 ## Model description
 
@@ -140,8 +140,8 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 29.8366       | 0.0201 | 1    | 1.9029          |
-| 20.1636       | 0.5013 | 25   | 1.2464          |
-| 19.3901       | 1.0025 | 50   | 1.2026          |
+| 20.1689       | 0.5013 | 25   | 1.2497          |
+| 19.4229       | 1.0025 | 50   | 1.2036          |
 
 
 ### Framework versions

adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "up_proj",
+    "o_proj",
     "v_proj",
-    "k_proj",
-    "q_proj",
     "down_proj",
-    "o_proj",
-    "gate_proj"
+    "k_proj",
+    "gate_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41020d03ea7e756f2e8138fe4ff157960ef3d6ba284e7c8e59f3a6430556d89e
+oid sha256:22ba84c6c50888d849bc81c6d9d46ef1c61c6447618934b1f88f7b5bc0106a7c
 size 335706186

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc541a5e2f6ab287dd5d927da237acf49a2f6908fcdea5a3b379204e1ed0bee1
+oid sha256:c5804f7ce3e4f165e38c00a62ab27ff1015149bd69f49f81ccf5098224bb7fc3
 size 335604696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7110c76ab6599cc95833cc63d481839aa6a5296b3d3896723abb98e54f6d9f6f
+oid sha256:49aff211ae8ea18a4c81022d1a6bf1adb7442e3700fb490be0575b42e1f1010b
 size 6776