gemma2_9b_it_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-it](https://huggingface.co/google/gemma-2-9b-it) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0985
+- Loss: 0.3680
 
 ## Model description
 
@@ -51,16 +51,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.6407        | 0.0960 | 50   | 0.2799          |
-| 0.2055        | 0.1920 | 100  | 0.1750          |
-| 0.1627        | 0.2879 | 150  | 0.1522          |
-| 0.1454        | 0.3839 | 200  | 0.1379          |
-| 0.1331        | 0.4799 | 250  | 0.1272          |
-| 0.1204        | 0.5759 | 300  | 0.1059          |
-| 0.1048        | 0.6718 | 350  | 0.1032          |
-| 0.1018        | 0.7678 | 400  | 0.1006          |
-| 0.1002        | 0.8638 | 450  | 0.0992          |
-| 0.0987        | 0.9598 | 500  | 0.0985          |
+| 0.6654        | 0.6033 | 50   | 0.3680          |
 
 
 ### Framework versions

adapter_config.json

@@ -22,8 +22,8 @@
   "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:aefbcd32d51076bc328e7333fac199a6db37000c45bbcf9a57b4719f63d2b15c
+oid sha256:943feff3e45cce2d21ad7fa74689f047fdefc68cfa1eb8fad0ad1f5eddee36de
 size 8967968

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28802312c084eb584f2bd658de409d86a745135b5fce0d8b53c4b579010584d2
+oid sha256:07920fba78b8b657fa73c5c659555b2d26b706975e54c2f23992b1577b0e6916
 size 5560