baltop/zwave-dbgatekeeper-v0.4

README.md

@@ -16,7 +16,7 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1428
+- Loss: 0.0305
 
 ## Model description
 
@@ -48,18 +48,18 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.33          | 0.32  | 25   | 1.4419          |
-| 1.2025        | 0.65  | 50   | 1.0187          |
-| 0.9409        | 0.97  | 75   | 0.8595          |
-| 0.6082        | 1.3   | 100  | 0.6429          |
-| 0.5165        | 1.62  | 125  | 0.4607          |
-| 0.4367        | 1.95  | 150  | 0.3669          |
-| 0.2466        | 2.27  | 175  | 0.2839          |
-| 0.232         | 2.6   | 200  | 0.2115          |
-| 0.2304        | 2.92  | 225  | 0.2051          |
-| 0.1522        | 3.25  | 250  | 0.1678          |
-| 0.1393        | 3.57  | 275  | 0.1512          |
-| 0.1386        | 3.9   | 300  | 0.1428          |
+| 1.1899        | 0.17  | 25   | 0.3116          |
+| 0.1795        | 0.33  | 50   | 0.1088          |
+| 0.0819        | 0.5   | 75   | 0.0425          |
+| 0.0453        | 0.67  | 100  | 0.0419          |
+| 0.0534        | 0.83  | 125  | 0.0382          |
+| 0.0338        | 1.0   | 150  | 0.0315          |
+| 0.0358        | 1.17  | 175  | 0.0345          |
+| 0.0336        | 1.33  | 200  | 0.0334          |
+| 0.0401        | 1.5   | 225  | 0.0322          |
+| 0.0326        | 1.67  | 250  | 0.0308          |
+| 0.0396        | 1.83  | 275  | 0.0309          |
+| 0.0307        | 2.0   | 300  | 0.0305          |
 
 
 ### Framework versions

adapter_config.json

@@ -19,14 +19,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "gate_proj",
-    "o_proj",
-    "q_proj",
-    "lm_head",
     "k_proj",
     "up_proj",
-    "down_proj"
+    "down_proj",
+    "q_proj",
+    "lm_head",
+    "gate_proj",
+    "v_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70bb7e0c23edea9da34a70e42ea4507b899740c26bdc8f765561a24712abcb8e
+oid sha256:8818e6ea4830b84464c905ac6f94cfe80a63f77e51c2638d2bd0bcefa4dc7252
 size 864513616

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecef6b4bec0cb2d7724d5a4e16c19bb099fe287efac82f31c36c066849ed3433
+oid sha256:3590f49eb926244738eba44f5a2a5b93f3455bb0c8fe39c90b692c6cf1ea1736
 size 4664