End of training

README.md

@@ -95,7 +95,7 @@ xformers_attention: true
 
 This model is a fine-tuned version of [MNC-Jihun/Mistral-7B-AO-u0.5-b2-ver0.4](https://huggingface.co/MNC-Jihun/Mistral-7B-AO-u0.5-b2-ver0.4) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7395
+- Loss: 1.7409
 
 ## Model description
 
@@ -132,9 +132,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.707         | 0.0011 | 1    | 2.0192          |
-| 2.1519        | 0.0269 | 25   | 1.7509          |
-| 2.1614        | 0.0538 | 50   | 1.7395          |
+| 1.7307        | 0.0011 | 1    | 2.0657          |
+| 2.1511        | 0.0269 | 25   | 1.7535          |
+| 2.1672        | 0.0538 | 50   | 1.7409          |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4197433db3b3c46756d4d86e4e7cd0e492d264ae95064944875a5a8de7139dad
+oid sha256:f36fd5e6a797039548ee42e0ef8fb9a1e3dacd603438acc470c44efcf0b25e4a
 size 860011282

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:641eb0d184ee62ddb72b2621ad6e78f932ea4c29eca641c702063c63c6f10f77
+oid sha256:a098e4073b8a0fba6a26374975a056a3b02d4cf25c917449c64558f8aafcf8fa
 size 859909312

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:987fd07a10c7dc3d0202f3fd844ca5c32e5eda76cf15397ae30934c49a3acd1e
+oid sha256:cde298347aefb5569ecda1d0ffbfc1f74fe5a8aad71a508769958efdcaf21bdf
 size 6776