End of training

README.md

@@ -102,7 +102,7 @@ xformers_attention: true
 
 This model is a fine-tuned version of [unsloth/gemma-2-2b-it](https://huggingface.co/unsloth/gemma-2-2b-it) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1903
+- Loss: 1.1900
 
 ## Model description
 
@@ -140,8 +140,8 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 1.6302        | 0.0243 | 1    | 1.7624          |
-| 1.1406        | 0.6070 | 25   | 1.2204          |
-| 1.2105        | 1.2140 | 50   | 1.1903          |
+| 1.1406        | 0.6070 | 25   | 1.2200          |
+| 1.2105        | 1.2140 | 50   | 1.1900          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
     "v_proj",
-    "down_proj",
-    "up_proj",
+    "gate_proj",
     "k_proj",
-    "gate_proj"
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "o_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:a4264bbe65930e5eb3e9eb562a64472cf30b3a5889d919a3bf818413708bfd04
+oid sha256:6cb68f30813a6031b596115ad98aae577a4553b98417d18568f1276271f7cf64
 size 166265274

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:267f48741f563a59b32da005a28611785fc7d08be02f9cd34083012162535288
+oid sha256:e8ef91d1d9630f9c8ac56a9dd8353d6179e0d98ec4168cba2208b741e4b4cb91
 size 166182480

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7f0262936f29db7120a92e75b37b15c657a864512415a0d04c326c07b5bf68a
+oid sha256:f0682ef37f1c43ecbd1dc3b77fe3639e4b844f66014f2d9ceeb47c4d5bd9e5e2
 size 6776