End of training

README.md

@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 1.0
+- num_epochs: 3.0
 
 ### Training results
 

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "gate_proj",
-    "down_proj",
+    "up_proj",
+    "k_proj",
     "o_proj",
+    "v_proj",
     "q_proj",
-    "up_proj",
-    "k_proj"
+    "down_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d76f65284f6d3ba7a231816db6faf900737efafef90e1f6956d39702aa079a7
+oid sha256:12359a1c213add3322cef965d71bc1b725ccfa074fa57094776c0b6c411e2b13
 size 167832240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ad42ab9a4d07f1c2cb98b20079993e9d0bf410690d42150c17546e0b8707878
+oid sha256:705a6867a8a0f4cf3d9ff7d61b5c919fb3405706a5264a78924d85e3f2711e4b
 size 5368