End of training

README.md

@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 1
+- num_epochs: 5
 
 ### Training results
 

adapter_config.json

@@ -20,11 +20,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
+    "k_proj",
     "gate_proj",
     "q_proj",
     "o_proj",
-    "k_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c1737928126f90d8d42507dee56bfa0df9d6a672314c94308398fab39c0e509
+oid sha256:d2c12b2bf4501a8850c3961eb04e3c3b6e908826484cf809e4fd5267348e3583
 size 23111032

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab118c0a55bb33d5f1ab9aed5bbc01cbd2e7d141d301cdb9e5a3b002800c92c1
+oid sha256:3ef10854e4a98dabc805e8d9c336beb47ec656609d48f36e6567269687e89a5e
 size 4920