rafaeloc15/mistral-small-v4

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: 0.0263
+- Loss: 0.0370
 
 ## Model description
 
@@ -52,8 +52,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.0369        | 1.0   | 252  | 0.0341          |
-| 0.0296        | 2.0   | 504  | 0.0263          |
+| 0.0516        | 1.0   | 268  | 0.0495          |
+| 0.0393        | 2.0   | 536  | 0.0370          |
 
 
 ### 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 sha256:380ccb4a952986cc4551ac5fd5ed1efffe1d5a5c176c8bba57fd396d1f5243f7
+oid sha256:d6c0cde07c559318e0dc4af4c3a278cc3547384e114ac2aa9aa78216f957ed1d
 size 109069176

runs/Apr11_02-17-45_b6aa82fb97e0/events.out.tfevents.1712801907.b6aa82fb97e0.1026.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34ea8977f6e1a8fee38066c56e4fee32bc5077a6dc928cbb03656e142219d768
+size 17092

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da370bc65ce8fdf0a4ba75f433927f8e33d4419a1a3565eea110ea5244c0fb60
+oid sha256:56b2d091aa5702b516be959e5dd70db67e57a0104418c5551125ccf39e7f7272
 size 4920