Training in progress, epoch 0

adapter_config.json

@@ -27,11 +27,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "q_proj",
     "v_proj",
+    "k_proj",
     "o_proj",
-    "dense"
+    "dense",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03b25f7fbe6470dc0fbb7b09ae3ccd818be3d3a74986e58c80583b5ebfd5e35c
+oid sha256:6e33a577518637996d1e65c0bff0d554a8df2b808a7845d9c4d02bff73694abb
 size 2732672640

runs/Jun02_20-25-53_qwang-test-16-gpu-f1c4cd-raycluster-8jwbf-wg-worker-9jb9f/events.out.tfevents.1748895970.qwang-test-16-gpu-f1c4cd-raycluster-8jwbf-wg-worker-9jb9f

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b36dd4bb59a6d9d069e8007a372a5c06deaeb28a21e55af56c564a01546a177e
+size 7046

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10e4482bb810d09ae7e94cc147b01b251650aef3787039659acd51325bf21514
+oid sha256:6ae66b4bdc9c4132a467c4b7c95e21e573f865ee1d644fc558b10ddb27af5b7f
 size 5816