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   | 7    | 0.5515          |
-| No log        | 2.0   | 14   | 0.2410          |
+| No log        | 1.0   | 7    | 0.5514          |
+| No log        | 2.0   | 14   | 0.2407          |
 | No log        | 3.0   | 21   | 0.1972          |
 
 

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:609faaa878dc00a43be2316b7485e6266bbe38c6b55cf154fc38d0f2f13d9fee
+oid sha256:616d96f56f35fcdd13208ae8c9284b249c65980c000285e554ac46f1d83992a6
 size 62969640

runs/Feb10_18-33-01_idc-training-gpu-compute-03/events.out.tfevents.1739212382.idc-training-gpu-compute-03.363500.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6eb829c9f90e3281e01b12fc4d1a1f27de068799c534e9009e1f2b3d02c0486
+size 7268

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dadf532dd06adfc14758f79f99f61e0dd8776bd8795ae2da40832212abab7638
+oid sha256:bd9f3ebff13928e55e0fcab0bbc39948b195abba86faafdc5478c0fec91b299e
 size 5624