End of training

README.md

@@ -105,7 +105,7 @@ xformers_attention: true
 
 This model is a fine-tuned version of [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6188
+- Loss: 0.6203
 
 ## Model description
 
@@ -143,8 +143,8 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 0.823         | 0.0015 | 1    | 0.8924          |
-| 0.687         | 0.0379 | 25   | 0.6584          |
-| 0.4238        | 0.0757 | 50   | 0.6188          |
+| 0.6746        | 0.0379 | 25   | 0.6640          |
+| 0.4266        | 0.0757 | 50   | 0.6203          |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9971317b702abecc5a2255263e9b7aba5cb671c26db964f32cc7b6f79b15ac1a
+oid sha256:ae8d493fcdb6cb16b630ab3c86e4cc18ce215b009992e3b8b0f3c45de97ac338
 size 335706186

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d0c21db8dc2809183a66794a457c0618b4627535d1395657275471c32b74e87
+oid sha256:9090ecb0cc714cbd70939408cd6f730e26a153e93efb9e6a2cf4b099b0b2b513
 size 335604696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36eaf4c354bb4f7511d71516f0afec7cdd347e6910b4fa4c5cf3334981bb9cf5
+oid sha256:8141129d94476201c2b4daf126b869603966afe064b925e53d4d737eb4a766c8
 size 6776