End of training

README.md

@@ -103,7 +103,7 @@ xformers_attention: true
 
 This model is a fine-tuned version of [UCLA-AGI/Gemma-2-9B-It-SPPO-Iter2](https://huggingface.co/UCLA-AGI/Gemma-2-9B-It-SPPO-Iter2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7182
+- Loss: 0.7138
 
 ## Model description
 
@@ -135,7 +135,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.5323        | 0.0002 | 10   | 0.7182          |
+| 0.5258        | 0.0002 | 10   | 0.7138          |
 
 
 ### Framework versions

adapter_config.json

@@ -21,11 +21,11 @@
   "revision": null,
   "target_modules": [
     "up_proj",
+    "v_proj",
+    "gate_proj",
     "down_proj",
     "o_proj",
-    "gate_proj",
     "k_proj",
-    "v_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac50c8dc0677333db0d2d9674a7aa6e3dcf567a9d660a4af3edb6ec82085e6ce
+oid sha256:7789771f9cb512c89fe0333ebf8ee7c2731c7eee526dbf9a682d9e6e8e807faa
 size 216284090

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c961c169dfe42e8e367c4ccef846b4a23ebffb79278121b87fb11b0d6701e6b
+oid sha256:3d4bcc4dc11d7d8e56003e258778a55538250dda5ed8838131ec1381fb792ebc
 size 216151256

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34c0a4dfad0d34a995cc329aae43855a8a4c6d2ea5141723489f8a99e5e983f8
+oid sha256:9cb5fdf2d06b318865cee65dfc8f4119cabbe3c5273190785df1942baeb4bbdb
 size 6776