End of training

README.md

@@ -103,7 +103,7 @@ xformers_attention: true
 
 This model is a fine-tuned version of [unsloth/llama-3-8b-Instruct](https://huggingface.co/unsloth/llama-3-8b-Instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4731
+- Loss: 0.4736
 
 ## Model description
 
@@ -141,8 +141,8 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 4.4381        | 0.0045 | 1    | 5.9517          |
-| 1.2538        | 0.1130 | 25   | 0.5836          |
-| 1.1494        | 0.2260 | 50   | 0.4731          |
+| 1.2577        | 0.1130 | 25   | 0.5865          |
+| 1.1515        | 0.2260 | 50   | 0.4736          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "v_proj",
-    "down_proj",
     "q_proj",
-    "k_proj",
     "up_proj",
-    "o_proj"
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "down_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:a9e024141b2693f3fe0b589cae15df9ebb3fd557057c84fea577dbacf23a92c3
+oid sha256:1bc7a01a089732ad7f1ed50687f321bf0ff80804b3be2ff17729ac9872c27068
 size 335706186

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e5a0b95359ef08bb75ad0c2fa48434aff777e65083a2ce6d910d1f38e9fd3a2
+oid sha256:612ddbfa96cf4f5d94a77303d7f648ad07c281c25d4848df4f45c5d7deb33bea
 size 335604696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b1ed99eafc3aa4e5c1234fbb3f8fea5495f15776a8fad9e6bcf523c30127ac1
+oid sha256:b0afb748b58c0b9ce3e85a2547829320a38677356c8a89e965a722aa1104d447
 size 6776