End of training

README.md

@@ -53,8 +53,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 11   | 0.3420          |
-| No log        | 2.0   | 22   | 0.3019          |
+| No log        | 1.0   | 11   | 0.3415          |
+| No log        | 2.0   | 22   | 0.3013          |
 | 0.4           | 3.0   | 33   | 0.3063          |
 
 

adapter_config.json

@@ -26,8 +26,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": null,
   "use_dora": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:890251c4b261df030b5f7c04c91f8ffd2a16668ae0237a28eca8c648040cacd8
+oid sha256:18fbfe514757cf182cab1caf580ccb4f7a26f595ad6ea2238b823b13508a18d7
 size 252726072

runs/Feb10_21-44-01_idc-training-gpu-compute-03/events.out.tfevents.1739223841.idc-training-gpu-compute-03.368456.45

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fcacef42bf6b52d41d703b6151a7d630bae7d9740d6193f1c6e1e06e4823f47
+size 7478

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee0745313fb705d6a236bdfd7480abb512f259e559a52e504a8e5c93eb8a76cb
+oid sha256:682809e2f0f3d076a8d18158c1e0282fd0158364847f9ec8d9bc9deac3e73b9d
 size 5624