End of training

README.md

@@ -33,7 +33,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2.5e-05
+- learning_rate: 1e-05
 - train_batch_size: 4
 - eval_batch_size: 8
 - seed: 0

adapter_config.json

@@ -22,9 +22,9 @@
   "spectral_top": true,
   "target_modules": [
     "o_proj",
-    "gate_proj",
     "k_proj",
     "v_proj",
+    "gate_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f2369637f091818eee9dd8e4e4ac5f63d3d75a8836e446ee237fe35219b949d
+oid sha256:753cf432421eee1ace5987dcf430d8002e59e29c92450a17da78e6e90d72bb94
 size 23111352

runs/May19_11-17-47_mert-lambda-scalar/events.out.tfevents.1716142667.mert-lambda-scalar.4142014.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e26a5f884be85808cf25b19756f8ec445c2f7c1f1e45abd71591265cfb3638f
+size 201994

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67e42acc01351cb172d8f7f31c9c618ab2e9c962f2916f8da3778b0d76b421f7
+oid sha256:f48ded3f569be922bb9f0558d5cf084654a66b4e5a8aeb152d5417e8559c2235
 size 4920