gemma2_9b_bwgenerator

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/gemma-2-9b](https://huggingface.co/google/gemma-2-9b) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0768
+- Loss: 0.0776
 
 ## Model description
 
@@ -49,9 +49,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.1596        | 0.2568 | 1000 | 0.0956          |
-| 0.0875        | 0.5136 | 2000 | 0.0826          |
-| 0.0798        | 0.7704 | 3000 | 0.0768          |
+| 0.1614        | 0.2568 | 1000 | 0.0964          |
+| 0.0884        | 0.5136 | 2000 | 0.0833          |
+| 0.0803        | 0.7704 | 3000 | 0.0776          |
 
 
 ### Framework versions

adapter_config.json

@@ -22,8 +22,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_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:df6b0e33ec7ae39f54f6238e9387295f69cbec6ab4acbdc6818531a6b967bbf9
+oid sha256:835ec3beb8893a655e47089cf02df45048836f5e0babc6f99c6a3ef4e2e73a15
 size 8967968

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c78d9e6d877be6017a82ae7733ecd69c4a4b71ad6e852bbcdb9c39759fbe056a
+oid sha256:0160c1caac47f5c864aeb276010cc8907367b56ae9251623c4cd0091c7e73397
 size 5560