End of training

README.md

@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
-- num_epochs: 5
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -19,14 +19,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "v_proj",
-    "up_proj",
-    "q_proj",
     "lm_head",
-    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
     "o_proj",
-    "k_proj"
+    "up_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eb9f4305592c59e81d8e71302f47f82add0b03c09e4dfe01f5a1ac259b0ff61
+oid sha256:bd8850961d4e9b588991621616cef460b4b357d717b5708a847b1822f00f3adf
 size 694431312

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a87c98eb0151dad759c0c84aaeb7a6378998f4809a3413b83befa91d56db89a2
+oid sha256:5084b6220077ec47cb290257b691492aa4fe49992f105b31821a3a0b7226f299
 size 4728