mistral_7b_admiral_instruct

README.md

@@ -20,7 +20,7 @@ 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 generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2637
+- Loss: 1.2642
 
 ## Model description
 
@@ -52,11 +52,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.5871        | 0.16  | 20   | 1.4508          |
-| 1.4009        | 0.33  | 40   | 1.2985          |
-| 1.3499        | 0.49  | 60   | 1.2842          |
-| 1.3251        | 0.65  | 80   | 1.2721          |
-| 1.3741        | 0.81  | 100  | 1.2637          |
+| 1.5866        | 0.16  | 20   | 1.4485          |
+| 1.4016        | 0.33  | 40   | 1.3008          |
+| 1.3506        | 0.49  | 60   | 1.2847          |
+| 1.3256        | 0.65  | 80   | 1.2730          |
+| 1.3746        | 0.81  | 100  | 1.2642          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61bc96c4e810998535ff7a8c957b0f5916ff3e922a2ca3eae05138e1c7f1b33f
+oid sha256:0bf57fa010d71a1c47a34777a4627a2b4b7dee01860a6c2222fa3c125477ddcc
 size 109069176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e795171346d7e37928821c285368490b74f64ec42779607dd3623f3663b97278
+oid sha256:2b19d9c0b18ca94f2d478371f7abfb76257b35fc2e6eb6dc76ec4e2c3f27a6c4
 size 4920