End of training

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-2b-it](https://huggingface.co/google/gemma-2b-it) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.7355
+- Loss: 2.5909
 
 ## Model description
 
@@ -52,9 +52,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.1332        | 3.0   | 3    | 2.5378          |
-| 0.0683        | 6.0   | 6    | 2.5858          |
-| 0.0236        | 9.0   | 9    | 2.7355          |
+| 0.1198        | 3.0   | 3    | 2.6224          |
+| 0.0479        | 6.0   | 6    | 2.4699          |
+| 0.0108        | 9.0   | 9    | 2.5909          |
 
 
 ### Framework versions

adapter_config.json

@@ -22,13 +22,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "up_proj",
+    "v_proj",
     "down_proj",
-    "gate_proj",
     "k_proj",
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1306fc825bd6b4779454a9c73f3b63a6ec5b4c832cf30bb173fa1849e5b3e3e4
+oid sha256:827386bfd3ec27f28c42b42e8391b339342f5fab12ff2b51a4c5bb73ce91f847
 size 4272785368

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2387bc0ec1e091240f40e33e26537876055316d5030ebd4f152ea413ca6d9d0
+oid sha256:edf15f7cd08dd8e2e4ba6e96e14521c7fa85a4bc691609dea16992db12bff92a
 size 4920