End of training

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [beomi/llama-2-ko-7b](https://huggingface.co/beomi/llama-2-ko-7b) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8276
+- Loss: 0.8265
 
 ## Model description
 
@@ -52,9 +52,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.9415        | 1.0   | 112  | 0.8208          |
-| 0.7231        | 2.0   | 225  | 0.7976          |
-| 0.5373        | 2.99  | 336  | 0.8276          |
+| 0.9417        | 1.0   | 112  | 0.8217          |
+| 0.7246        | 2.0   | 225  | 0.7960          |
+| 0.5382        | 2.99  | 336  | 0.8265          |
 
 
 ### Framework versions

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "k_proj",
-    "gate_proj",
+    "down_proj",
+    "q_proj",
     "o_proj",
+    "gate_proj",
+    "k_proj",
     "v_proj",
-    "down_proj",
-    "q_proj"
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca1ef97f3ec3b3a7b86761a6b409e9edb156f1add5e98eeadb16fd04bb589bcb
+oid sha256:249d6b71e16cdc532f0dac96c7ecaaccebed057563e0c6f4283e21820cfb53f0
 size 2158096728

runs/Apr19_17-24-13_50934c259f6c/events.out.tfevents.1713547473.50934c259f6c.295.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b80bdce282f5f57d0b3fe093adb7c74d378578637a2d515dc703186159f5c109
+size 8045

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7c8fc457370c558b86b2cd009785b810bd27a8a7ea55758f41a89ed537b2ad0
+oid sha256:790189610484119fa87f6e6e8d7db754c60972486383787cd886f9bbb1e09691
 size 4728