End of training

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3757
+- Loss: 1.3627
 
 ## Model description
 
@@ -43,15 +43,18 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- num_epochs: 3
+- num_epochs: 6
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.3784        | 1.0   | 179  | 1.3965          |
-| 1.435         | 2.0   | 358  | 1.3774          |
-| 1.2838        | 3.0   | 537  | 1.3757          |
+| 1.3743        | 1.0   | 179  | 1.3920          |
+| 1.424         | 2.0   | 358  | 1.3706          |
+| 1.2688        | 3.0   | 537  | 1.3631          |
+| 1.4132        | 4.0   | 716  | 1.3620          |
+| 1.3061        | 5.0   | 895  | 1.3625          |
+| 1.2414        | 6.0   | 1074 | 1.3627          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "k_proj",
-    "o_proj",
-    "v_proj"
+    "q_proj",
+    "v_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5cf9245942ecd7eb126eb65f418e4a3ddcb8c4d3bd12207911a7ec4da1ed8f1
+oid sha256:fc55edce4b0a74aa81cd5dc036d25ce7d18b1567a2bac25a6792224568f76a89
 size 109086672

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4ef494958d1f6eb9cb07c6235c35e33988d09c7a08a088ba1ce7412876e0202
+oid sha256:4f7edd70b81ea4cf67a7c18ebdfcf815bdad0f5d346da96537a7d45865c828f5
 size 5496