End of training

README.md

@@ -103,7 +103,7 @@ xformers_attention: true
 
 This model is a fine-tuned version of [unsloth/codegemma-2b](https://huggingface.co/unsloth/codegemma-2b) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.2219
+- Loss: 3.2094
 
 ## Model description
 
@@ -135,7 +135,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 5.4915        | 0.0001 | 10   | 3.2219          |
+| 5.4834        | 0.0001 | 10   | 3.2094          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "up_proj",
     "v_proj",
-    "q_proj",
     "down_proj",
+    "o_proj",
+    "q_proj",
     "k_proj",
-    "o_proj"
+    "gate_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26e6a2af36bfa8b535273c346b14bd6c51b172310778b397af486cd1f115a3ca
+oid sha256:0d4745f22bb5b4b92181a482699721fe54e94a820b7511859e6e825f50f499c3
 size 78537274

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f203d788dcc1cb27d3a9cb6ca33c37381ca08e19638acaf63fdb4fabc2fa5881
+oid sha256:6e96ac6c096fc63d55f2a7ba265544c17c03103b79fa0617d548584a096ba130
 size 78480072

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:301b4d47f616d4b6cc1ace74be117c5f4a68933209583c1dacdf35a34bd0efa9
+oid sha256:6211da5b9065e2d926a02cd5a7aa101b89889d60f100c5e254fa041e8ff99426
 size 6776