Training in progress, step 100

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d3bac2018fb39764f96cf64f3e1b1aa8334f137d5effe5453b4439958689932
+oid sha256:6f1bb44247997e29206bfdca014d4083541c345de3be5a6160cd23c5988817e0
 size 50056096

runs/May19_11-56-52_deep-diver-main-moody-turtle-1-0-0/events.out.tfevents.1716134365.deep-diver-main-moody-turtle-1-0-0.385.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f811f6adddb4cbe7e0cdb682e920de85fb856e9d6616e5d80ee46197b7fd2c7
+size 9974

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f10ba2a5dfc42e7decd9fac2d091c02a3b18cbb0207f5ccd145d79b675458eaf
+oid sha256:8520f1612dff28fadbb42f98d8f739873baec7da95f5082b1d4be9232d1241da
 size 5368