Training in progress, step 3800

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "down_proj",
-    "k_proj",
-    "gate_proj",
     "q_proj",
+    "k_proj",
     "o_proj",
-    "up_proj"
+    "gate_proj",
+    "up_proj",
+    "down_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:ca3ab8beda6a1b218a58e0c472258515b4627d9e68adaa52c01f9b2ffc6ff374
+oid sha256:e950ed847e6ae58457864f4db5a2f173866a4502b5413d8d18bc84a2a77f3620
 size 1600180696

runs/Sep19_17-16-33_m3h111/events.out.tfevents.1758266889.m3h111.863562.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d390c14de96ac0f041e0182a77d49291de61e870bc6b96b12bc7f690b0497bc
+size 8075

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0157e1efd8063deaae5bc8338b469d4b6fe1a96ffb032bbc00795caa07b1970f
+oid sha256:18e838240c59455f1fec1e7a211dbb6abdb4d79b442463b041bdfb666a537a8d
 size 6904