End of training

README.md

@@ -102,7 +102,7 @@ xformers_attention: null
 
 This model is a fine-tuned version of [oopsung/llama2-7b-koNqa-test-v1](https://huggingface.co/oopsung/llama2-7b-koNqa-test-v1) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 12.1172
+- Loss: 12.0897
 
 ## Model description
 
@@ -138,9 +138,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 14.12         | 0.0008 | 1    | 16.0395         |
-| 17.5658       | 0.0024 | 3    | 16.0118         |
-| 14.5333       | 0.0049 | 6    | 15.2201         |
-| 13.1099       | 0.0073 | 9    | 12.1172         |
+| 17.5639       | 0.0024 | 3    | 16.0095         |
+| 14.5286       | 0.0049 | 6    | 15.2182         |
+| 13.0894       | 0.0073 | 9    | 12.0897         |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c66c14e524d8962baebe54df70c82640ef042e6c5a1755bbf5b5d494b50b7f7
+oid sha256:7ea4103164d3d4e789b02faaf53d91268c399104487e49c20cef2e4f5d57cf97
 size 80115210

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98a4a6013533b370515ea8a5910eaf0e999b88219095bba1ea648d832063869a
+oid sha256:826058b85016cb14fc1ae17bfa9dc4fc1a65f07a4d491c25399a5e72e2410f7e
 size 80013120

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6e1305fc8f281ddb72b2abbc2f99245c4a414545702847872a68fca4d715eef
+oid sha256:ba57699bba9b310c57bde7376897c4b366951d205389ca4384cb9831382eab5b
 size 6776