baltop/zwave-dbgatekeeper-v0.3

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: 1.7687
+- Loss: 0.1428
 
 ## Model description
 
@@ -48,18 +48,18 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.349         | 0.52  | 25   | 1.5889          |
-| 1.1213        | 1.04  | 50   | 1.3232          |
-| 0.6369        | 1.56  | 75   | 1.3226          |
-| 0.525         | 2.08  | 100  | 1.3375          |
-| 0.256         | 2.6   | 125  | 1.5105          |
-| 0.2127        | 3.12  | 150  | 1.4755          |
-| 0.145         | 3.65  | 175  | 1.6525          |
-| 0.1388        | 4.17  | 200  | 1.7168          |
-| 0.114         | 4.69  | 225  | 1.7377          |
-| 0.1076        | 5.21  | 250  | 1.7087          |
-| 0.0986        | 5.73  | 275  | 1.7649          |
-| 0.0912        | 6.25  | 300  | 1.7687          |
+| 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          |
 
 
 ### Framework versions

adapter_config.json

@@ -19,14 +19,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
     "v_proj",
+    "gate_proj",
     "o_proj",
-    "k_proj",
-    "down_proj",
+    "q_proj",
     "lm_head",
-    "gate_proj",
-    "q_proj"
+    "k_proj",
+    "up_proj",
+    "down_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:e980d31e15e5b58f219649fd38ae0536d5685bc80e8d9498b9827804170779e7
+oid sha256:70bb7e0c23edea9da34a70e42ea4507b899740c26bdc8f765561a24712abcb8e
 size 864513616

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2ff09da45c5ecad2510f9bfecdd441b144eac70e7f493018f072bae08478ca6
+oid sha256:ecef6b4bec0cb2d7724d5a4e16c19bb099fe287efac82f31c36c066849ed3433
 size 4664