End of training

README.md

@@ -140,9 +140,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 2.5636        | 0.0002 | 1    | 2.5533          |
-| 2.6646        | 0.0005 | 3    | 2.5480          |
-| 2.4127        | 0.0010 | 6    | 2.4774          |
-| 2.4161        | 0.0015 | 9    | 2.3584          |
+| 2.6682        | 0.0005 | 3    | 2.5478          |
+| 2.4112        | 0.0010 | 6    | 2.4802          |
+| 2.414         | 0.0015 | 9    | 2.3584          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "k_proj",
     "up_proj",
     "v_proj",
-    "gate_proj",
     "q_proj",
-    "o_proj",
-    "down_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 sha256:5ca49bfb0d21e10c120b36783237145aa497b619666f90f1b75e741faf88f00f
+oid sha256:4717a5558861ebf4a1a9fd932ce2ec8bcc7348ddfdd276c00df3b386aeda6fb5
 size 45169354

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:793a799bd11b9689e570d44fdb6936c92fbe798e305f570153d92a14bc1561ba
+oid sha256:f89206345456e93eeb502b737e62178aea1cbc7e6cfa41c2424b03976e390f6a
 size 45118424

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef68a0fb19eac9987edac8323a4b4c1375436ffcccaab5f22193ad3a6254b248
+oid sha256:b3f5f24b610d814119114339e648d6ed3a2253ce76c1f667715f1aee5a38c459
 size 6776