Training in progress, step 100

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "gate_proj",
     "up_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj",
     "k_proj",
     "o_proj",
-    "q_proj",
-    "v_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfaafda9c15fac898a9b7c7ddbcb867afd609319b38dfbaf8ded60247fdd5d8a
+oid sha256:0694b9bf292debb98879dda68792f6ccd6971acafc88941b5cea82d8d007a0fe
 size 671150064

runs/Apr12_22-15-14_mosaic-cirrascale-03.reviz.ai2.in/events.out.tfevents.1712985661.mosaic-cirrascale-03.reviz.ai2.in.10828.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291c61cf94dd8ca941e6e36ad0d62144d284339719037b992a3abefa8a3a48fd
+size 13431

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a623dccb6c0815f96e49f96c35a66bec9c2b7a096a9b47a228bc6badca49fa24
+oid sha256:4d93aab22cff04f95b419457da2abad617b73e321789fd03b6cf30ca659e8eae
 size 5112