End of training

README.md

@@ -103,7 +103,7 @@ xformers_attention: true
 
 This model is a fine-tuned version of [unsloth/Qwen2-1.5B](https://huggingface.co/unsloth/Qwen2-1.5B) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4024
+- Loss: 0.4025
 
 ## Model description
 
@@ -141,8 +141,8 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 0.551         | 0.0478 | 1    | 0.5565          |
-| 0.4206        | 1.2179 | 25   | 0.4251          |
-| 0.3508        | 2.4358 | 50   | 0.4024          |
+| 0.4206        | 1.2179 | 25   | 0.4254          |
+| 0.3513        | 2.4358 | 50   | 0.4025          |
 
 
 ### Framework versions

adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "o_proj",
-    "v_proj",
     "down_proj",
-    "k_proj",
-    "up_proj",
     "gate_proj",
-    "q_proj"
+    "k_proj",
+    "v_proj",
+    "q_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:ff189ca5b402715ad1e81120d54b44603fc4a447f97bdea7e05456097d9164c3
+oid sha256:29104c3cc64f1f42fa03e677e6bce2083f5ba4b0461b658db58bba0dd6d874bc
 size 147859242

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a22f9375dd7f4f0ada7b41a4e0c78592fc31ad9f3bacce41636af8643d7395a5
+oid sha256:a704533d698c7ba0a63169225e51fe598844be04e0004f38d5f187079038e55d
 size 147770496

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3dea4593a7a820a778fc84ba6e04d4471ebc30e6df1994d208d89710cfaf65d
+oid sha256:e94c1e826225abe88b190761b2645c6636cea2d7bee422d5c89d0033daed0be6
 size 6776