End of training

README.md

@@ -96,7 +96,7 @@ xformers_attention: null
 
 This model is a fine-tuned version of [unsloth/Llama-3.2-3B](https://huggingface.co/unsloth/Llama-3.2-3B) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1499
+- Loss: 2.1502
 
 ## Model description
 
@@ -132,9 +132,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 2.0097        | 0.0002 | 1    | 2.2259          |
-| 2.2435        | 0.0006 | 3    | 2.2231          |
-| 2.2226        | 0.0011 | 6    | 2.2023          |
-| 2.0588        | 0.0017 | 9    | 2.1499          |
+| 2.2437        | 0.0006 | 3    | 2.2234          |
+| 2.223         | 0.0011 | 6    | 2.2032          |
+| 2.0592        | 0.0017 | 9    | 2.1502          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "v_proj",
+    "k_proj",
     "down_proj",
     "q_proj",
-    "k_proj",
-    "v_proj",
     "gate_proj",
+    "o_proj",
     "up_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:832b9de840c40548e18228595f8ca5f88407132d11637a0800f13ccf1ce8453a
+oid sha256:4e09fe26b8841656ff3a1fa7570a8a85a042d17173203919a52c45f2c6ef0304
 size 48768810

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a117cc31d99f1148ed7c20934770701243424d0e2a7705a96bc92b94633d5f7f
+oid sha256:1837de8c2c0ae3a2f2f3846fbbd705e8cd52007adce1b834ff59810d4ca67e84
 size 48679352

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abb88f4cc1adc89d4050bb1bb8aee4d5e2999228bec3f38fcda07d103361cace
+oid sha256:acaeb28a4fb49aa88292474a6784853956ad77b62156abc6a5e8cbc29594a649
 size 6776