Sreenath/sqlm

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-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3477
+- Loss: 0.3458
 
 ## Model description
 
@@ -50,11 +50,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.552         | 0.03  | 20   | 0.4535          |
-| 0.4046        | 0.05  | 40   | 0.3840          |
-| 0.3788        | 0.08  | 60   | 0.3588          |
-| 0.3556        | 0.11  | 80   | 0.3501          |
-| 0.3305        | 0.13  | 100  | 0.3477          |
+| 0.5909        | 0.0   | 20   | 0.4721          |
+| 0.4063        | 0.0   | 40   | 0.3917          |
+| 0.3631        | 0.0   | 60   | 0.3612          |
+| 0.3543        | 0.0   | 80   | 0.3512          |
+| 0.3442        | 0.0   | 100  | 0.3458          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_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:c1ac68191e7ffd937408fe4a3d8e222654d55028a0f6b4821a311c070a6e5f76
+oid sha256:4ab0413bcceeaf0c5b7e16fef2b3e2cd6b3964556cfd9e1b92f04e74b476d512
 size 109069176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:290d63e1e5380e08f021b4862d7de7ba06d6b641c087a492438e40347efe61d6
+oid sha256:85a7f59bcf43c69f110f368c6c6bb3089265ecdd4886f79b48b2930a7c9a504f
 size 4856